From 820ce8ed53ce2111aa5171f7349f289d7e9d0693 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Wed, 21 Aug 2024 22:02:05 +0200
Subject: [PATCH 0001/1530] gfs2: Rename GLF_VERIFY_EVICT to GLF_VERIFY_DELETE

Rename the GLF_VERIFY_EVICT flag to GLF_VERIFY_DELETE: that flag
indicates that we want to delete an inode / verify that it has been
deleted.

To match, rename gfs2_queue_verify_evict() to
gfs2_queue_verify_delete().

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c  | 14 +++++++-------
 fs/gfs2/incore.h |  2 +-
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 269c3bc7fced7..5addf4ebf33bd 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1013,11 +1013,11 @@ bool gfs2_queue_try_to_evict(struct gfs2_glock *gl)
 				  &gl->gl_delete, 0);
 }
 
-static bool gfs2_queue_verify_evict(struct gfs2_glock *gl)
+static bool gfs2_queue_verify_delete(struct gfs2_glock *gl)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 
-	if (test_and_set_bit(GLF_VERIFY_EVICT, &gl->gl_flags))
+	if (test_and_set_bit(GLF_VERIFY_DELETE, &gl->gl_flags))
 		return false;
 	return queue_delayed_work(sdp->sd_delete_wq,
 				  &gl->gl_delete, 5 * HZ);
@@ -1052,19 +1052,19 @@ static void delete_work_func(struct work_struct *work)
 		if (gfs2_try_evict(gl)) {
 			if (test_bit(SDF_KILL, &sdp->sd_flags))
 				goto out;
-			if (gfs2_queue_verify_evict(gl))
+			if (gfs2_queue_verify_delete(gl))
 				return;
 		}
 		goto out;
 	}
 
-	if (test_and_clear_bit(GLF_VERIFY_EVICT, &gl->gl_flags)) {
+	if (test_and_clear_bit(GLF_VERIFY_DELETE, &gl->gl_flags)) {
 		inode = gfs2_lookup_by_inum(sdp, no_addr, gl->gl_no_formal_ino,
 					    GFS2_BLKST_UNLINKED);
 		if (IS_ERR(inode)) {
 			if (PTR_ERR(inode) == -EAGAIN &&
 			    !test_bit(SDF_KILL, &sdp->sd_flags) &&
-			    gfs2_queue_verify_evict(gl))
+			    gfs2_queue_verify_delete(gl))
 				return;
 		} else {
 			d_prune_aliases(inode);
@@ -2118,7 +2118,7 @@ static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
 void gfs2_cancel_delete_work(struct gfs2_glock *gl)
 {
 	clear_bit(GLF_TRY_TO_EVICT, &gl->gl_flags);
-	clear_bit(GLF_VERIFY_EVICT, &gl->gl_flags);
+	clear_bit(GLF_VERIFY_DELETE, &gl->gl_flags);
 	if (cancel_delayed_work(&gl->gl_delete))
 		gfs2_glock_put(gl);
 }
@@ -2371,7 +2371,7 @@ static const char *gflags2str(char *buf, const struct gfs2_glock *gl)
 		*p++ = 'N';
 	if (test_bit(GLF_TRY_TO_EVICT, gflags))
 		*p++ = 'e';
-	if (test_bit(GLF_VERIFY_EVICT, gflags))
+	if (test_bit(GLF_VERIFY_DELETE, gflags))
 		*p++ = 'E';
 	*p = 0;
 	return buf;
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index aa4ef67a34e03..bd1348bff90eb 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -329,7 +329,7 @@ enum {
 	GLF_BLOCKING			= 15,
 	GLF_UNLOCKED			= 16, /* Wait for glock to be unlocked */
 	GLF_TRY_TO_EVICT		= 17, /* iopen glocks only */
-	GLF_VERIFY_EVICT		= 18, /* iopen glocks only */
+	GLF_VERIFY_DELETE		= 18, /* iopen glocks only */
 };
 
 struct gfs2_glock {

From 1072b3aa6863bc4d91006038b032bfb4dcc98dec Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Mon, 16 Sep 2024 15:42:57 +0200
Subject: [PATCH 0002/1530] gfs2: Initialize gl_no_formal_ino earlier

Set gl_no_formal_ino of the iopen glock to the generation of the
associated inode (ip->i_no_formal_ino) as soon as that value is known.
This saves us from setting it later, possibly repeatedly, when queuing
GLF_VERIFY_DELETE work.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c | 1 -
 fs/gfs2/glops.c | 9 ++++++++-
 fs/gfs2/inode.c | 1 +
 3 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 5addf4ebf33bd..96894243d03b5 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -980,7 +980,6 @@ static bool gfs2_try_evict(struct gfs2_glock *gl)
 		ip = NULL;
 	spin_unlock(&gl->gl_lockref.lock);
 	if (ip) {
-		gl->gl_no_formal_ino = ip->i_no_formal_ino;
 		set_bit(GIF_DEFERRED_DELETE, &ip->i_flags);
 		d_prune_aliases(&ip->i_inode);
 		iput(&ip->i_inode);
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 95d8081681dcc..dbc444bfc630d 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -494,11 +494,18 @@ int gfs2_inode_refresh(struct gfs2_inode *ip)
 static int inode_go_instantiate(struct gfs2_glock *gl)
 {
 	struct gfs2_inode *ip = gl->gl_object;
+	struct gfs2_glock *io_gl;
+	int error;
 
 	if (!ip) /* no inode to populate - read it in later */
 		return 0;
 
-	return gfs2_inode_refresh(ip);
+	error = gfs2_inode_refresh(ip);
+	if (error)
+		return error;
+	io_gl = ip->i_iopen_gh.gh_gl;
+	io_gl->gl_no_formal_ino = ip->i_no_formal_ino;
+	return 0;
 }
 
 static int inode_go_held(struct gfs2_holder *gh)
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 1b95db2c3aac3..6fbbaaad1cd05 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -750,6 +750,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	if (error)
 		goto fail_free_inode;
 	gfs2_cancel_delete_work(io_gl);
+	io_gl->gl_no_formal_ino = ip->i_no_formal_ino;
 
 retry:
 	error = insert_inode_locked4(inode, ip->i_no_addr, iget_test, &ip->i_no_addr);

From c940a66b3ac930227df0ab6e01f84bea1afa6c3f Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 2 May 2024 15:31:15 -0700
Subject: [PATCH 0003/1530] perf test: Be more tolerant of metricgroup failures

Previously "set -e" meant any non-zero exit code from perf stat would
cause a test failure. As a non-zero exit happens when there aren't
sufficient permissions, check for this case and make the exit code
2/skip for it.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Veronika Molnarova <vmolnaro@redhat.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20240502223115.2357499-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../perf/tests/shell/stat_all_metricgroups.sh | 36 +++++++++++++++----
 1 file changed, 30 insertions(+), 6 deletions(-)

diff --git a/tools/perf/tests/shell/stat_all_metricgroups.sh b/tools/perf/tests/shell/stat_all_metricgroups.sh
index 55ef9c9ded2d7..c6d61a4ac3e7d 100755
--- a/tools/perf/tests/shell/stat_all_metricgroups.sh
+++ b/tools/perf/tests/shell/stat_all_metricgroups.sh
@@ -1,9 +1,7 @@
-#!/bin/sh
+#!/bin/bash
 # perf all metricgroups test
 # SPDX-License-Identifier: GPL-2.0
 
-set -e
-
 ParanoidAndNotRoot()
 {
   [ "$(id -u)" != 0 ] && [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt $1 ]
@@ -14,11 +12,37 @@ if ParanoidAndNotRoot 0
 then
   system_wide_flag=""
 fi
-
+err=0
 for m in $(perf list --raw-dump metricgroups)
 do
   echo "Testing $m"
-  perf stat -M "$m" $system_wide_flag sleep 0.01
+  result=$(perf stat -M "$m" $system_wide_flag sleep 0.01 2>&1)
+  result_err=$?
+  if [[ $result_err -gt 0 ]]
+  then
+    if [[ "$result" =~ \
+          "Access to performance monitoring and observability operations is limited" ]]
+    then
+      echo "Permission failure"
+      echo $result
+      if [[ $err -eq 0 ]]
+      then
+        err=2 # Skip
+      fi
+    elif [[ "$result" =~ "in per-thread mode, enable system wide" ]]
+    then
+      echo "Permissions - need system wide mode"
+      echo $result
+      if [[ $err -eq 0 ]]
+      then
+        err=2 # Skip
+      fi
+    else
+      echo "Metric group $m failed"
+      echo $result
+      err=1 # Fail
+    fi
+  fi
 done
 
-exit 0
+exit $err

From 5afd032961e8465808c4bc385c06e7676fbe1951 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Mon, 16 Sep 2024 14:57:32 +0100
Subject: [PATCH 0004/1530] perf cs-etm: Don't flush when packet_queue fills up

cs_etm__flush(), like cs_etm__sample() is an operation that generates a
sample and then swaps the current with the previous packet. Calling
flush after processing the queues results in two swaps which corrupts
the next sample. Therefore it wasn't appropriate to call flush here so
remove it.

Flushing is still done on a discontinuity to explicitly clear the last
branch buffer, but when the packet_queue fills up before reaching a
timestamp, that's not a discontinuity and the call to
cs_etm__process_traceid_queue() already generated samples and drained
the buffers correctly.

This is visible by looking for a branch that has the same target as the
previous branch and the following source is before the address of the
last target, which is impossible as execution would have had to have
gone backwards:

  ffff800080849d40 _find_next_and_bit+0x78 => ffff80008011cadc update_sg_lb_stats+0x94
   (packet_queue fills here before a timestamp, resulting in a flush and
    branch target ffff80008011cadc is duplicated.)
  ffff80008011cb1c update_sg_lb_stats+0xd4 => ffff80008011cadc update_sg_lb_stats+0x94
  ffff8000801117c4 cpu_util+0x24 => ffff8000801117d4 cpu_util+0x34

After removing the flush the correct branch target is used for the
second sample, and ffff8000801117c4 is no longer before the previous
address:

  ffff800080849d40 _find_next_and_bit+0x78 => ffff80008011cadc update_sg_lb_stats+0x94
  ffff80008011cb1c update_sg_lb_stats+0xd4 => ffff8000801117a0 cpu_util+0x0
  ffff8000801117c4 cpu_util+0x24 => ffff8000801117d4 cpu_util+0x34

Make sure that a final branch stack is output at the end of the trace
by calling cs_etm__end_block(). This is already done for both the
timeless decode paths.

Fixes: 21fe8dc1191a ("perf cs-etm: Add support for CPU-wide trace scenarios")
Reported-by: Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>
Closes: https://lore.kernel.org/all/20240719092619.274730-1-gankulkarni@os.amperecomputing.com/
Reviewed-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Tested-by: Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>
Cc: Ben Gainey <ben.gainey@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ruidong Tian <tianruidong@linux.alibaba.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: coresight@lists.linaro.org
Cc: John Garry <john.g.garry@oracle.com>
Cc: scclevenger@os.amperecomputing.com
Link: https://lore.kernel.org/r/20240916135743.1490403-2-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/cs-etm.c | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 90f32f327b9b1..242788ac96259 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -2490,12 +2490,6 @@ static void cs_etm__clear_all_traceid_queues(struct cs_etm_queue *etmq)
 
 		/* Ignore return value */
 		cs_etm__process_traceid_queue(etmq, tidq);
-
-		/*
-		 * Generate an instruction sample with the remaining
-		 * branchstack entries.
-		 */
-		cs_etm__flush(etmq, tidq);
 	}
 }
 
@@ -2638,7 +2632,7 @@ static int cs_etm__process_timestamped_queues(struct cs_etm_auxtrace *etm)
 
 	while (1) {
 		if (!etm->heap.heap_cnt)
-			goto out;
+			break;
 
 		/* Take the entry at the top of the min heap */
 		cs_queue_nr = etm->heap.heap_array[0].queue_nr;
@@ -2721,6 +2715,23 @@ static int cs_etm__process_timestamped_queues(struct cs_etm_auxtrace *etm)
 		ret = auxtrace_heap__add(&etm->heap, cs_queue_nr, cs_timestamp);
 	}
 
+	for (i = 0; i < etm->queues.nr_queues; i++) {
+		struct int_node *inode;
+
+		etmq = etm->queues.queue_array[i].priv;
+		if (!etmq)
+			continue;
+
+		intlist__for_each_entry(inode, etmq->traceid_queues_list) {
+			int idx = (int)(intptr_t)inode->priv;
+
+			/* Flush any remaining branch stack entries */
+			tidq = etmq->traceid_queues[idx];
+			ret = cs_etm__end_block(etmq, tidq);
+			if (ret)
+				return ret;
+		}
+	}
 out:
 	return ret;
 }

From ba5ae78a5a2a956d281ac62f581ab95e618bbf18 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Mon, 16 Sep 2024 14:57:33 +0100
Subject: [PATCH 0005/1530] perf cs-etm: Use new OpenCSD consistency checks

Previously when the incorrect binary was used for decode, Perf would
silently continue to generate incorrect samples. With OpenCSD 1.5.4 we
can enable consistency checks that do a best effort to detect a mismatch
in the image. When one is detected a warning is printed and sample
generation stops until the trace resynchronizes with a good part of the
image.

Reported-by: Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>
Closes: https://lore.kernel.org/all/20240719092619.274730-1-gankulkarni@os.amperecomputing.com/
Reviewed-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Tested-by: Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>
Cc: Ben Gainey <ben.gainey@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ruidong Tian <tianruidong@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: coresight@lists.linaro.org
Cc: John Garry <john.g.garry@oracle.com>
Cc: scclevenger@os.amperecomputing.com
Link: https://lore.kernel.org/r/20240916135743.1490403-3-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/cs-etm-decoder/cs-etm-decoder.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index b78ef0262135c..b85a8837bddcd 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -685,9 +685,14 @@ cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params,
 	}
 
 	if (d_params->operation == CS_ETM_OPERATION_DECODE) {
+		int decode_flags = OCSD_CREATE_FLG_FULL_DECODER;
+#ifdef OCSD_OPFLG_N_UNCOND_DIR_BR_CHK
+		decode_flags |= OCSD_OPFLG_N_UNCOND_DIR_BR_CHK | OCSD_OPFLG_CHK_RANGE_CONTINUE |
+				ETM4_OPFLG_PKTDEC_AA64_OPCODE_CHK;
+#endif
 		if (ocsd_dt_create_decoder(decoder->dcd_tree,
 					   decoder->decoder_name,
-					   OCSD_CREATE_FLG_FULL_DECODER,
+					   decode_flags,
 					   trace_config, &csid))
 			return -1;
 

From 9943581c64b1d1edaf9985ee81e45e728f67cd2e Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Mon, 16 Sep 2024 14:57:34 +0100
Subject: [PATCH 0006/1530] perf scripting python: Add function to get a config
 value

This can be used to get config values like which objdump Perf uses for
disassembly.

Reviewed-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Tested-by: Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>
Cc: Ben Gainey <ben.gainey@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ruidong Tian <tianruidong@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: coresight@lists.linaro.org
Cc: John Garry <john.g.garry@oracle.com>
Cc: scclevenger@os.amperecomputing.com
Link: https://lore.kernel.org/r/20240916135743.1490403-4-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../perf/Documentation/perf-script-python.txt |  2 +-
 .../scripts/python/Perf-Trace-Util/Context.c  | 11 ++++++++++
 tools/perf/util/config.c                      | 22 +++++++++++++++++++
 tools/perf/util/config.h                      |  1 +
 4 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 13e37e9385ee4..27a1cac6fe763 100644
--- a/tools/perf/Documentation/perf-script-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -624,7 +624,7 @@ as perf_trace_context.perf_script_context .
  perf_set_itrace_options(context, itrace_options) - set --itrace options if they have not been set already
  perf_sample_srcline(context) - returns source_file_name, line_number
  perf_sample_srccode(context) - returns source_file_name, line_number, source_line
-
+ perf_config_get(config_name) - returns the value of the named config item, or None if unset
 
 Util.py Module
 ~~~~~~~~~~~~~~
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
index 3954bd1587ce9..01f54d6724a5f 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
@@ -12,6 +12,7 @@
 #define PY_SSIZE_T_CLEAN
 
 #include <Python.h>
+#include "../../../util/config.h"
 #include "../../../util/trace-event.h"
 #include "../../../util/event.h"
 #include "../../../util/symbol.h"
@@ -182,6 +183,15 @@ static PyObject *perf_sample_srccode(PyObject *obj, PyObject *args)
 	return perf_sample_src(obj, args, true);
 }
 
+static PyObject *__perf_config_get(PyObject *obj, PyObject *args)
+{
+	const char *config_name;
+
+	if (!PyArg_ParseTuple(args, "s", &config_name))
+		return NULL;
+	return Py_BuildValue("s", perf_config_get(config_name));
+}
+
 static PyMethodDef ContextMethods[] = {
 #ifdef HAVE_LIBTRACEEVENT
 	{ "common_pc", perf_trace_context_common_pc, METH_VARARGS,
@@ -199,6 +209,7 @@ static PyMethodDef ContextMethods[] = {
 	  METH_VARARGS,	"Get source file name and line number."},
 	{ "perf_sample_srccode", perf_sample_srccode,
 	  METH_VARARGS,	"Get source file name, line number and line."},
+	{ "perf_config_get", __perf_config_get, METH_VARARGS, "Get perf config entry"},
 	{ NULL, NULL, 0, NULL}
 };
 
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 7a650de0db83f..68f9407ca74b9 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -912,6 +912,7 @@ void set_buildid_dir(const char *dir)
 struct perf_config_scan_data {
 	const char *name;
 	const char *fmt;
+	const char *value;
 	va_list args;
 	int ret;
 };
@@ -939,3 +940,24 @@ int perf_config_scan(const char *name, const char *fmt, ...)
 
 	return d.ret;
 }
+
+static int perf_config_get_cb(const char *var, const char *value, void *data)
+{
+	struct perf_config_scan_data *d = data;
+
+	if (!strcmp(var, d->name))
+		d->value = value;
+
+	return 0;
+}
+
+const char *perf_config_get(const char *name)
+{
+	struct perf_config_scan_data d = {
+		.name = name,
+		.value = NULL,
+	};
+
+	perf_config(perf_config_get_cb, &d);
+	return d.value;
+}
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
index 2e5e808928a55..9971313d61c1e 100644
--- a/tools/perf/util/config.h
+++ b/tools/perf/util/config.h
@@ -30,6 +30,7 @@ typedef int (*config_fn_t)(const char *, const char *, void *);
 int perf_default_config(const char *, const char *, void *);
 int perf_config(config_fn_t fn, void *);
 int perf_config_scan(const char *name, const char *fmt, ...) __scanf(2, 3);
+const char *perf_config_get(const char *name);
 int perf_config_set(struct perf_config_set *set,
 		    config_fn_t fn, void *data);
 int perf_config_int(int *dest, const char *, const char *);

From 7b371afc9b67349c724c15d235924bc40694872a Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Mon, 16 Sep 2024 14:57:35 +0100
Subject: [PATCH 0007/1530] perf scripts python cs-etm: Update to use argparse

optparse is deprecated and less flexible than argparse so update it.

Reviewed-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Tested-by: Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>
Cc: Ben Gainey <ben.gainey@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ruidong Tian <tianruidong@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: coresight@lists.linaro.org
Cc: John Garry <john.g.garry@oracle.com>
Cc: scclevenger@os.amperecomputing.com
Link: https://lore.kernel.org/r/20240916135743.1490403-5-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../scripts/python/arm-cs-trace-disasm.py     | 28 +++++++------------
 1 file changed, 10 insertions(+), 18 deletions(-)

diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py
index 7aff02d84ffb3..45f682a8b34d7 100755
--- a/tools/perf/scripts/python/arm-cs-trace-disasm.py
+++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
@@ -11,7 +11,7 @@
 from os import path
 import re
 from subprocess import *
-from optparse import OptionParser, make_option
+import argparse
 
 from perf_trace_context import perf_set_itrace_options, \
 	perf_sample_insn, perf_sample_srccode
@@ -28,19 +28,11 @@
 #  perf script -s scripts/python/arm-cs-trace-disasm.py
 
 # Command line parsing.
-option_list = [
-	# formatting options for the bottom entry of the stack
-	make_option("-k", "--vmlinux", dest="vmlinux_name",
-		    help="Set path to vmlinux file"),
-	make_option("-d", "--objdump", dest="objdump_name",
-		    help="Set path to objdump executable file"),
-	make_option("-v", "--verbose", dest="verbose",
-		    action="store_true", default=False,
-		    help="Enable debugging log")
-]
-
-parser = OptionParser(option_list=option_list)
-(options, args) = parser.parse_args()
+args = argparse.ArgumentParser()
+args.add_argument("-k", "--vmlinux", help="Set path to vmlinux file")
+args.add_argument("-d", "--objdump", help="Set path to objdump executable file"),
+args.add_argument("-v", "--verbose", action="store_true", help="Enable debugging log")
+options = args.parse_args()
 
 # Initialize global dicts and regular expression
 disasm_cache = dict()
@@ -65,8 +57,8 @@ def get_offset(perf_dict, field):
 
 def get_dso_file_path(dso_name, dso_build_id):
 	if (dso_name == "[kernel.kallsyms]" or dso_name == "vmlinux"):
-		if (options.vmlinux_name):
-			return options.vmlinux_name;
+		if (options.vmlinux):
+			return options.vmlinux;
 		else:
 			return dso_name
 
@@ -92,7 +84,7 @@ def read_disam(dso_fname, dso_start, start_addr, stop_addr):
 	else:
 		start_addr = start_addr - dso_start;
 		stop_addr = stop_addr - dso_start;
-		disasm = [ options.objdump_name, "-d", "-z",
+		disasm = [ options.objdump, "-d", "-z",
 			   "--start-address="+format(start_addr,"#x"),
 			   "--stop-address="+format(stop_addr,"#x") ]
 		disasm += [ dso_fname ]
@@ -256,7 +248,7 @@ def process_event(param_dict):
 		print("Stop address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (stop_addr, int(dso_start), int(dso_end), dso))
 		return
 
-	if (options.objdump_name != None):
+	if (options.objdump != None):
 		# It doesn't need to decrease virtual memory offset for disassembly
 		# for kernel dso and executable file dso, so in this case we set
 		# vm_start to zero.

From 8286cc55a9a6f03d62bd140ce827025f9ed5e619 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Mon, 16 Sep 2024 14:57:36 +0100
Subject: [PATCH 0008/1530] perf scripts python cs-etm: Improve arguments

Make vmlinux detection automatic and use Perf's default objdump
when -d is specified. This will make it easier for a test to use the
script without having to provide arguments. And similarly for users.

Reviewed-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Tested-by: Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>
Cc: Ben Gainey <ben.gainey@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ruidong Tian <tianruidong@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: coresight@lists.linaro.org
Cc: John Garry <john.g.garry@oracle.com>
Cc: scclevenger@os.amperecomputing.com
Link: https://lore.kernel.org/r/20240916135743.1490403-6-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../scripts/python/arm-cs-trace-disasm.py     | 63 ++++++++++++++++---
 1 file changed, 55 insertions(+), 8 deletions(-)

diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py
index 45f682a8b34d7..02e957d037ea4 100755
--- a/tools/perf/scripts/python/arm-cs-trace-disasm.py
+++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
@@ -12,25 +12,48 @@
 import re
 from subprocess import *
 import argparse
+import platform
 
-from perf_trace_context import perf_set_itrace_options, \
-	perf_sample_insn, perf_sample_srccode
+from perf_trace_context import perf_sample_srccode, perf_config_get
 
 # Below are some example commands for using this script.
+# Note a --kcore recording is required for accurate decode
+# due to the alternatives patching mechanism. However this
+# script only supports reading vmlinux for disassembly dump,
+# meaning that any patched instructions will appear
+# as unpatched, but the instruction ranges themselves will
+# be correct. In addition to this, source line info comes
+# from Perf, and when using kcore there is no debug info. The
+# following lists the supported features in each mode:
+#
+# +-----------+-----------------+------------------+------------------+
+# | Recording | Accurate decode | Source line dump | Disassembly dump |
+# +-----------+-----------------+------------------+------------------+
+# | --kcore   | yes             | no               | yes              |
+# | normal    | no              | yes              | yes              |
+# +-----------+-----------------+------------------+------------------+
+#
+# Output disassembly with objdump and auto detect vmlinux
+# (when running on same machine.)
+#  perf script -s scripts/python/arm-cs-trace-disasm.py -d
 #
-# Output disassembly with objdump:
-#  perf script -s scripts/python/arm-cs-trace-disasm.py \
-#		-- -d objdump -k path/to/vmlinux
 # Output disassembly with llvm-objdump:
 #  perf script -s scripts/python/arm-cs-trace-disasm.py \
 #		-- -d llvm-objdump-11 -k path/to/vmlinux
+#
 # Output only source line and symbols:
 #  perf script -s scripts/python/arm-cs-trace-disasm.py
 
+def default_objdump():
+	config = perf_config_get("annotate.objdump")
+	return config if config else "objdump"
+
 # Command line parsing.
 args = argparse.ArgumentParser()
-args.add_argument("-k", "--vmlinux", help="Set path to vmlinux file")
-args.add_argument("-d", "--objdump", help="Set path to objdump executable file"),
+args.add_argument("-k", "--vmlinux",
+		  help="Set path to vmlinux file. Omit to autodetect if running on same machine")
+args.add_argument("-d", "--objdump", nargs="?", const=default_objdump(),
+		  help="Show disassembly. Can also be used to change the objdump path"),
 args.add_argument("-v", "--verbose", action="store_true", help="Enable debugging log")
 options = args.parse_args()
 
@@ -45,6 +68,17 @@
 glb_line_number		= None
 glb_dso			= None
 
+kver = platform.release()
+vmlinux_paths = [
+	f"/usr/lib/debug/boot/vmlinux-{kver}.debug",
+	f"/usr/lib/debug/lib/modules/{kver}/vmlinux",
+	f"/lib/modules/{kver}/build/vmlinux",
+	f"/usr/lib/debug/boot/vmlinux-{kver}",
+	f"/boot/vmlinux-{kver}",
+	f"/boot/vmlinux",
+	f"vmlinux"
+]
+
 def get_optional(perf_dict, field):
        if field in perf_dict:
                return perf_dict[field]
@@ -55,12 +89,25 @@ def get_offset(perf_dict, field):
 		return "+%#x" % perf_dict[field]
 	return ""
 
+def find_vmlinux():
+	if hasattr(find_vmlinux, "path"):
+		return find_vmlinux.path
+
+	for v in vmlinux_paths:
+		if os.access(v, os.R_OK):
+			find_vmlinux.path = v
+			break
+	else:
+		find_vmlinux.path = None
+
+	return find_vmlinux.path
+
 def get_dso_file_path(dso_name, dso_build_id):
 	if (dso_name == "[kernel.kallsyms]" or dso_name == "vmlinux"):
 		if (options.vmlinux):
 			return options.vmlinux;
 		else:
-			return dso_name
+			return find_vmlinux() if find_vmlinux() else dso_name
 
 	if (dso_name == "[vdso]") :
 		append = "/vdso"

From 66dd3b539efe0d4b44324c1fe39978db8111ed93 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Mon, 16 Sep 2024 14:57:37 +0100
Subject: [PATCH 0009/1530] perf scripts python cs-etm: Add start and stop
 arguments

Make it possible to only disassemble a range of timestamps or sample
indexes. This will be used by the test to limit the runtime, but it's
also useful for users.

Reviewed-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Tested-by: Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>
Cc: Ben Gainey <ben.gainey@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ruidong Tian <tianruidong@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: coresight@lists.linaro.org
Cc: John Garry <john.g.garry@oracle.com>
Cc: scclevenger@os.amperecomputing.com
Link: https://lore.kernel.org/r/20240916135743.1490403-7-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../scripts/python/arm-cs-trace-disasm.py     | 40 ++++++++++++++++++-
 1 file changed, 38 insertions(+), 2 deletions(-)

diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py
index 02e957d037ea4..1128d259b4f47 100755
--- a/tools/perf/scripts/python/arm-cs-trace-disasm.py
+++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
@@ -49,13 +49,36 @@ def default_objdump():
 	return config if config else "objdump"
 
 # Command line parsing.
+def int_arg(v):
+	v = int(v)
+	if v < 0:
+		raise argparse.ArgumentTypeError("Argument must be a positive integer")
+	return v
+
 args = argparse.ArgumentParser()
 args.add_argument("-k", "--vmlinux",
 		  help="Set path to vmlinux file. Omit to autodetect if running on same machine")
 args.add_argument("-d", "--objdump", nargs="?", const=default_objdump(),
 		  help="Show disassembly. Can also be used to change the objdump path"),
 args.add_argument("-v", "--verbose", action="store_true", help="Enable debugging log")
+args.add_argument("--start-time", type=int_arg, help="Monotonic clock time of sample to start from. "
+		  "See 'time' field on samples in -v mode.")
+args.add_argument("--stop-time", type=int_arg, help="Monotonic clock time of sample to stop at. "
+		  "See 'time' field on samples in -v mode.")
+args.add_argument("--start-sample", type=int_arg, help="Index of sample to start from. "
+		  "See 'index' field on samples in -v mode.")
+args.add_argument("--stop-sample", type=int_arg, help="Index of sample to stop at. "
+		  "See 'index' field on samples in -v mode.")
+
 options = args.parse_args()
+if (options.start_time and options.stop_time and
+    options.start_time >= options.stop_time):
+	print("--start-time must less than --stop-time")
+	exit(2)
+if (options.start_sample and options.stop_sample and
+    options.start_sample >= options.stop_sample):
+	print("--start-sample must less than --stop-sample")
+	exit(2)
 
 # Initialize global dicts and regular expression
 disasm_cache = dict()
@@ -63,6 +86,7 @@ def default_objdump():
 disasm_re = re.compile(r"^\s*([0-9a-fA-F]+):")
 disasm_func_re = re.compile(r"^\s*([0-9a-fA-F]+)\s.*:")
 cache_size = 64*1024
+sample_idx = -1
 
 glb_source_file_name	= None
 glb_line_number		= None
@@ -151,10 +175,10 @@ def print_disam(dso_fname, dso_start, start_addr, stop_addr):
 
 def print_sample(sample):
 	print("Sample = { cpu: %04d addr: 0x%016x phys_addr: 0x%016x ip: 0x%016x " \
-	      "pid: %d tid: %d period: %d time: %d }" % \
+	      "pid: %d tid: %d period: %d time: %d index: %d}" % \
 	      (sample['cpu'], sample['addr'], sample['phys_addr'], \
 	       sample['ip'], sample['pid'], sample['tid'], \
-	       sample['period'], sample['time']))
+	       sample['period'], sample['time'], sample_idx))
 
 def trace_begin():
 	print('ARM CoreSight Trace Data Assembler Dump')
@@ -216,6 +240,7 @@ def print_srccode(comm, param_dict, sample, symbol, dso):
 def process_event(param_dict):
 	global cache_size
 	global options
+	global sample_idx
 
 	sample = param_dict["sample"]
 	comm = param_dict["comm"]
@@ -231,6 +256,17 @@ def process_event(param_dict):
 	ip = sample["ip"]
 	addr = sample["addr"]
 
+	sample_idx += 1
+
+	if (options.start_time and sample["time"] < options.start_time):
+		return
+	if (options.stop_time and sample["time"] > options.stop_time):
+		exit(0)
+	if (options.start_sample and sample_idx < options.start_sample):
+		return
+	if (options.stop_sample and sample_idx > options.stop_sample):
+		exit(0)
+
 	if (options.verbose == True):
 		print("Event type: %s" % name)
 		print_sample(sample)

From eb0a59e9e1e799303bc421770dc039f96ab8b84d Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Mon, 16 Sep 2024 14:57:38 +0100
Subject: [PATCH 0010/1530] perf test: cs-etm: Test Coresight disassembly
 script

Run a few samples through the disassembly script and check to see that
at least one branch instruction is printed.

Signed-off-by: James Clark <james.clark@linaro.org>
Reviewed-by: Leo Yan <leo.yan@arm.com>
Tested-by: Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>
Cc: Ben Gainey <ben.gainey@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ruidong Tian <tianruidong@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: coresight@lists.linaro.org
Cc: John Garry <john.g.garry@oracle.com>
Cc: scclevenger@os.amperecomputing.com
Link: https://lore.kernel.org/r/20240916135743.1490403-8-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../tests/shell/test_arm_coresight_disasm.sh  | 65 +++++++++++++++++++
 1 file changed, 65 insertions(+)
 create mode 100755 tools/perf/tests/shell/test_arm_coresight_disasm.sh

diff --git a/tools/perf/tests/shell/test_arm_coresight_disasm.sh b/tools/perf/tests/shell/test_arm_coresight_disasm.sh
new file mode 100755
index 0000000000000..af63e3757cb0a
--- /dev/null
+++ b/tools/perf/tests/shell/test_arm_coresight_disasm.sh
@@ -0,0 +1,65 @@
+#!/bin/sh
+# Check Arm CoreSight disassembly script completes without errors
+# SPDX-License-Identifier: GPL-2.0
+
+# The disassembly script reconstructs ranges of instructions and gives these to objdump to
+# decode. objdump doesn't like ranges that go backwards, but these are a good indication
+# that decoding has gone wrong either in OpenCSD, Perf or in the range reconstruction in
+# the script. Test all 3 parts are working correctly by running the script.
+
+skip_if_no_cs_etm_event() {
+	perf list | grep -q 'cs_etm//' && return 0
+
+	# cs_etm event doesn't exist
+	return 2
+}
+
+skip_if_no_cs_etm_event || exit 2
+
+# Assume an error unless we reach the very end
+set -e
+glb_err=1
+
+perfdata_dir=$(mktemp -d /tmp/__perf_test.perf.data.XXXXX)
+perfdata=${perfdata_dir}/perf.data
+file=$(mktemp /tmp/temporary_file.XXXXX)
+# Relative path works whether it's installed or running from repo
+script_path=$(dirname "$0")/../../scripts/python/arm-cs-trace-disasm.py
+
+cleanup_files()
+{
+	set +e
+	rm -rf ${perfdata_dir}
+	rm -f ${file}
+	trap - EXIT TERM INT
+	exit $glb_err
+}
+
+trap cleanup_files EXIT TERM INT
+
+# Ranges start and end on branches, so check for some likely branch instructions
+sep="\s\|\s"
+branch_search="\sbl${sep}b${sep}b.ne${sep}b.eq${sep}cbz\s"
+
+## Test kernel ##
+if [ -e /proc/kcore ]; then
+	echo "Testing kernel disassembly"
+	perf record -o ${perfdata} -e cs_etm//k --kcore -- touch $file > /dev/null 2>&1
+	perf script -i ${perfdata} -s python:${script_path} -- \
+		-d --stop-sample=30 2> /dev/null > ${file}
+	grep -q -e ${branch_search} ${file}
+	echo "Found kernel branches"
+else
+	# kcore is required for correct kernel decode due to runtime code patching
+	echo "No kcore, skipping kernel test"
+fi
+
+## Test user ##
+echo "Testing userspace disassembly"
+perf record -o ${perfdata} -e cs_etm//u -- touch $file > /dev/null 2>&1
+perf script -i ${perfdata} -s python:${script_path} -- \
+	-d --stop-sample=30 2> /dev/null > ${file}
+grep -q -e ${branch_search} ${file}
+echo "Found userspace branches"
+
+glb_err=0

From f115506d2ce4549df306746cd0b1c5d7bf6537f5 Mon Sep 17 00:00:00 2001
From: Masum Reza <masumrezarock100@gmail.com>
Date: Sun, 22 Sep 2024 16:56:16 +0530
Subject: [PATCH 0011/1530] perf evsel: display dmesg command of showing a
 hardcoded path

In non-FHS compliant distros like NixOS, nothing resides in `/bin`
and `/usr/bin`. Instead dynamically symlinked into
`/run/current-system/sw/bin/`, the executable resides in `/nix/store`.

With this patch,`/bin` prefix from the dmesg command in the error
message is stripped.

Link: https://github.com/NixOS/nixpkgs/pull/258027

Signed-off-by: Masum Reza <masumrezarock100@gmail.com>
Cc: Yunseong Kim <yskelg@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20240922112619.149429-1-masumrezarock100@gmail.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/evsel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dbf9c8cee3c56..b9c18f3316997 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -3415,7 +3415,7 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
 
 	return scnprintf(msg, size,
 	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
-	"/bin/dmesg | grep -i perf may provide additional information.\n",
+	"\"dmesg | grep -i perf\" may provide additional information.\n",
 			 err, str_error_r(err, sbuf, sizeof(sbuf)), evsel__name(evsel));
 }
 

From 160bc9555d8654464cbbd7bb1f6687048471d2f6 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Tue, 24 Sep 2024 18:38:00 +0200
Subject: [PATCH 0012/1530] gfs2: Allow immediate GLF_VERIFY_DELETE work

Add an argument to gfs2_queue_verify_delete() that allows it to queue
GLF_VERIFY_DELETE work for immediate execution.  This is used in the
next patch.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 96894243d03b5..7119037a866c5 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1012,14 +1012,15 @@ bool gfs2_queue_try_to_evict(struct gfs2_glock *gl)
 				  &gl->gl_delete, 0);
 }
 
-static bool gfs2_queue_verify_delete(struct gfs2_glock *gl)
+static bool gfs2_queue_verify_delete(struct gfs2_glock *gl, bool later)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+	unsigned long delay;
 
 	if (test_and_set_bit(GLF_VERIFY_DELETE, &gl->gl_flags))
 		return false;
-	return queue_delayed_work(sdp->sd_delete_wq,
-				  &gl->gl_delete, 5 * HZ);
+	delay = later ? 5 * HZ : 0;
+	return queue_delayed_work(sdp->sd_delete_wq, &gl->gl_delete, delay);
 }
 
 static void delete_work_func(struct work_struct *work)
@@ -1051,7 +1052,7 @@ static void delete_work_func(struct work_struct *work)
 		if (gfs2_try_evict(gl)) {
 			if (test_bit(SDF_KILL, &sdp->sd_flags))
 				goto out;
-			if (gfs2_queue_verify_delete(gl))
+			if (gfs2_queue_verify_delete(gl, true))
 				return;
 		}
 		goto out;
@@ -1063,7 +1064,7 @@ static void delete_work_func(struct work_struct *work)
 		if (IS_ERR(inode)) {
 			if (PTR_ERR(inode) == -EAGAIN &&
 			    !test_bit(SDF_KILL, &sdp->sd_flags) &&
-			    gfs2_queue_verify_delete(gl))
+			    gfs2_queue_verify_delete(gl, true))
 				return;
 		} else {
 			d_prune_aliases(inode);

From 7c6f714d88475ceae5342264858a641eafa19632 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Mon, 26 Aug 2024 20:06:21 +0200
Subject: [PATCH 0013/1530] gfs2: Fix unlinked inode cleanup

Before commit f0e56edc2ec7 ("gfs2: Split the two kinds of glock "delete"
work"), function delete_work_func() was used to trigger the eviction of
in-memory inodes from remote as well as deleting unlinked inodes at a
later point.  These two kinds of work were then split into two kinds of
work, and the two places in the code were deferred deletion of inodes is
required accidentally ended up queuing the wrong kind of work.  This
caused unlinked inodes to be left behind, which could in the worst case
fill up filesystems and require a filesystem check to recover.

Fix that by queuing the right kind of work in try_rgrp_unlink() and
gfs2_drop_inode().

Fixes: f0e56edc2ec7 ("gfs2: Split the two kinds of glock "delete" work")
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c | 2 +-
 fs/gfs2/glock.h | 1 +
 fs/gfs2/rgrp.c  | 2 +-
 fs/gfs2/super.c | 2 +-
 4 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 7119037a866c5..9273ec5345eda 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1012,7 +1012,7 @@ bool gfs2_queue_try_to_evict(struct gfs2_glock *gl)
 				  &gl->gl_delete, 0);
 }
 
-static bool gfs2_queue_verify_delete(struct gfs2_glock *gl, bool later)
+bool gfs2_queue_verify_delete(struct gfs2_glock *gl, bool later)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	unsigned long delay;
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index adf0091cc98f9..63e101d448e96 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -245,6 +245,7 @@ static inline int gfs2_glock_nq_init(struct gfs2_glock *gl,
 void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state);
 void gfs2_glock_complete(struct gfs2_glock *gl, int ret);
 bool gfs2_queue_try_to_evict(struct gfs2_glock *gl);
+bool gfs2_queue_verify_delete(struct gfs2_glock *gl, bool later);
 void gfs2_cancel_delete_work(struct gfs2_glock *gl);
 void gfs2_flush_delete_work(struct gfs2_sbd *sdp);
 void gfs2_gl_hash_clear(struct gfs2_sbd *sdp);
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 29c7728167652..5393031297153 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1879,7 +1879,7 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip
 		 */
 		ip = gl->gl_object;
 
-		if (ip || !gfs2_queue_try_to_evict(gl))
+		if (ip || !gfs2_queue_verify_delete(gl, false))
 			gfs2_glock_put(gl);
 		else
 			found++;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 6678060ed4d2b..e22c1edc32b39 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1045,7 +1045,7 @@ static int gfs2_drop_inode(struct inode *inode)
 		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
 
 		gfs2_glock_hold(gl);
-		if (!gfs2_queue_try_to_evict(gl))
+		if (!gfs2_queue_verify_delete(gl, true))
 			gfs2_glock_put_async(gl);
 		return 0;
 	}

From e880a70f8046df0dd9089fa60dcb866a2cc69194 Mon Sep 17 00:00:00 2001
From: Levi Yun <yeoreum.yun@arm.com>
Date: Wed, 25 Sep 2024 14:20:21 +0100
Subject: [PATCH 0014/1530] perf stat: Close cork_fd when
 create_perf_stat_counter() failed

When create_perf_stat_counter() failed, it doesn't close workload.cork_fd
open in evlist__prepare_workload(). This could make too many open file
error while __run_perf_stat() repeats.

Introduce evlist__cancel_workload to close workload.cork_fd and
wait workload.child_pid until exit to clear child process
when create_perf_stat_counter() is failed.

Signed-off-by: Levi Yun <yeoreum.yun@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: nd@arm.com
Cc: howardchu95@gmail.com
Link: https://lore.kernel.org/r/20240925132022.2650180-2-yeoreum.yun@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-stat.c | 50 +++++++++++++++++++++++++++------------
 tools/perf/util/evlist.c  | 19 +++++++++++++--
 tools/perf/util/evlist.h  |  1 +
 3 files changed, 53 insertions(+), 17 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 689a3d43c2584..2c46bdbd9914d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -716,15 +716,19 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	}
 
 	if (!cpu_map__is_dummy(evsel_list->core.user_requested_cpus)) {
-		if (affinity__setup(&saved_affinity) < 0)
-			return -1;
+		if (affinity__setup(&saved_affinity) < 0) {
+			err = -1;
+			goto err_out;
+		}
 		affinity = &saved_affinity;
 	}
 
 	evlist__for_each_entry(evsel_list, counter) {
 		counter->reset_group = false;
-		if (bpf_counter__load(counter, &target))
-			return -1;
+		if (bpf_counter__load(counter, &target)) {
+			err = -1;
+			goto err_out;
+		}
 		if (!(evsel__is_bperf(counter)))
 			all_counters_use_bpf = false;
 	}
@@ -767,7 +771,8 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 
 			switch (stat_handle_error(counter)) {
 			case COUNTER_FATAL:
-				return -1;
+				err = -1;
+				goto err_out;
 			case COUNTER_RETRY:
 				goto try_again;
 			case COUNTER_SKIP:
@@ -808,7 +813,8 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 
 				switch (stat_handle_error(counter)) {
 				case COUNTER_FATAL:
-					return -1;
+					err = -1;
+					goto err_out;
 				case COUNTER_RETRY:
 					goto try_again_reset;
 				case COUNTER_SKIP:
@@ -833,8 +839,10 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			stat_config.unit_width = l;
 
 		if (evsel__should_store_id(counter) &&
-		    evsel__store_ids(counter, evsel_list))
-			return -1;
+		    evsel__store_ids(counter, evsel_list)) {
+			err = -1;
+			goto err_out;
+		}
 	}
 
 	if (evlist__apply_filters(evsel_list, &counter, &target)) {
@@ -855,20 +863,23 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		}
 
 		if (err < 0)
-			return err;
+			goto err_out;
 
 		err = perf_event__synthesize_stat_events(&stat_config, NULL, evsel_list,
 							 process_synthesized_event, is_pipe);
 		if (err < 0)
-			return err;
+			goto err_out;
+
 	}
 
 	if (target.initial_delay) {
 		pr_info(EVLIST_DISABLED_MSG);
 	} else {
 		err = enable_counters();
-		if (err)
-			return -1;
+		if (err) {
+			err = -1;
+			goto err_out;
+		}
 	}
 
 	/* Exec the command, if any */
@@ -878,8 +889,10 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	if (target.initial_delay > 0) {
 		usleep(target.initial_delay * USEC_PER_MSEC);
 		err = enable_counters();
-		if (err)
-			return -1;
+		if (err) {
+			err = -1;
+			goto err_out;
+		}
 
 		pr_info(EVLIST_ENABLED_MSG);
 	}
@@ -899,7 +912,8 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		if (workload_exec_errno) {
 			const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
 			pr_err("Workload failed: %s\n", emsg);
-			return -1;
+			err = -1;
+			goto err_out;
 		}
 
 		if (WIFSIGNALED(status))
@@ -946,6 +960,12 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		evlist__close(evsel_list);
 
 	return WEXITSTATUS(status);
+
+err_out:
+	if (forks)
+		evlist__cancel_workload(evsel_list);
+
+	return err;
 }
 
 static int run_perf_stat(int argc, const char **argv, int run_idx)
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index f14b7e6ff1dcc..a9df84692d4a8 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -48,6 +48,7 @@
 #include <sys/mman.h>
 #include <sys/prctl.h>
 #include <sys/timerfd.h>
+#include <sys/wait.h>
 
 #include <linux/bitops.h>
 #include <linux/hash.h>
@@ -1484,6 +1485,8 @@ int evlist__prepare_workload(struct evlist *evlist, struct target *target, const
 	int child_ready_pipe[2], go_pipe[2];
 	char bf;
 
+	evlist->workload.cork_fd = -1;
+
 	if (pipe(child_ready_pipe) < 0) {
 		perror("failed to create 'ready' pipe");
 		return -1;
@@ -1536,7 +1539,7 @@ int evlist__prepare_workload(struct evlist *evlist, struct target *target, const
 		 * For cancelling the workload without actually running it,
 		 * the parent will just close workload.cork_fd, without writing
 		 * anything, i.e. read will return zero and we just exit()
-		 * here.
+		 * here (See evlist__cancel_workload()).
 		 */
 		if (ret != 1) {
 			if (ret == -1)
@@ -1600,7 +1603,7 @@ int evlist__prepare_workload(struct evlist *evlist, struct target *target, const
 
 int evlist__start_workload(struct evlist *evlist)
 {
-	if (evlist->workload.cork_fd > 0) {
+	if (evlist->workload.cork_fd >= 0) {
 		char bf = 0;
 		int ret;
 		/*
@@ -1611,12 +1614,24 @@ int evlist__start_workload(struct evlist *evlist)
 			perror("unable to write to pipe");
 
 		close(evlist->workload.cork_fd);
+		evlist->workload.cork_fd = -1;
 		return ret;
 	}
 
 	return 0;
 }
 
+void evlist__cancel_workload(struct evlist *evlist)
+{
+	int status;
+
+	if (evlist->workload.cork_fd >= 0) {
+		close(evlist->workload.cork_fd);
+		evlist->workload.cork_fd = -1;
+		waitpid(evlist->workload.pid, &status, WNOHANG);
+	}
+}
+
 int evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct perf_sample *sample)
 {
 	struct evsel *evsel = evlist__event2evsel(evlist, event);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index bcc1c6984bb58..888fda751e1a6 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -186,6 +186,7 @@ int evlist__prepare_workload(struct evlist *evlist, struct target *target,
 			     const char *argv[], bool pipe_output,
 			     void (*exec_error)(int signo, siginfo_t *info, void *ucontext));
 int evlist__start_workload(struct evlist *evlist);
+void evlist__cancel_workload(struct evlist *evlist);
 
 struct option;
 

From b77f8c36ce0b23da97f5442c2f55cc98c2cb5567 Mon Sep 17 00:00:00 2001
From: Levi Yun <yeoreum.yun@arm.com>
Date: Wed, 25 Sep 2024 14:20:22 +0100
Subject: [PATCH 0015/1530] perf stat: Stop repeating when ref_perf_stat()
 returns -1

Exit when run_perf_stat() returns an error to avoid continuously
repeating the same error message. It's not expected that COUNTER_FATAL
or internal errors are recoverable so there's no point in retrying.

This fixes the following flood of error messages for permission issues,
for example when perf_event_paranoid==3:
  perf stat -r 1044 -- false

  Error:
  Access to performance monitoring and observability operations is limited.
  ...
  Error:
  Access to performance monitoring and observability operations is limited.
  ...
  (repeating for 1044 times).

Signed-off-by: Levi Yun <yeoreum.yun@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Cc: nd@arm.com
Cc: howardchu95@gmail.com
Link: https://lore.kernel.org/r/20240925132022.2650180-3-yeoreum.yun@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-stat.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 2c46bdbd9914d..6cad3435b1984 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -968,6 +968,14 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	return err;
 }
 
+/*
+ * Returns -1 for fatal errors which signifies to not continue
+ * when in repeat mode.
+ *
+ * Returns < -1 error codes when stat record is used. These
+ * result in the stat information being displayed, but writing
+ * to the file fails and is non fatal.
+ */
 static int run_perf_stat(int argc, const char **argv, int run_idx)
 {
 	int ret;
@@ -2899,7 +2907,10 @@ int cmd_stat(int argc, const char **argv)
 			evlist__reset_prev_raw_counts(evsel_list);
 
 		status = run_perf_stat(argc, argv, run_idx);
-		if (forever && status != -1 && !interval) {
+		if (status == -1)
+			break;
+
+		if (forever && !interval) {
 			print_counters(NULL, argc, argv);
 			perf_stat__reset_stats();
 		}

From 235f0da3274690f540aa53fccf77d433e344e4b8 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Tue, 24 Sep 2024 11:08:12 +0800
Subject: [PATCH 0016/1530] perf vendor events arm64: imx95: add
 imx95_bandwidth_usage.lpddr4x metric

Except lpddr5, i.MX95 also support lpddr4x. This will add a metric for
lpddr4x.

Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Cc: shawnguo@kernel.org
Cc: will@kernel.org
Cc: james.clark@linaro.org
Cc: mike.leach@linaro.org
Cc: imx@lists.linux.dev
Cc: john.g.garry@oracle.com
Cc: kernel@pengutronix.de
Cc: s.hauer@pengutronix.de
Link: https://lore.kernel.org/r/20240924030812.3211029-1-xu.yang_2@nxp.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../arch/arm64/freescale/imx95/sys/metrics.json           | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/perf/pmu-events/arch/arm64/freescale/imx95/sys/metrics.json b/tools/perf/pmu-events/arch/arm64/freescale/imx95/sys/metrics.json
index 126ce980f6f25..45a0d51dfb639 100644
--- a/tools/perf/pmu-events/arch/arm64/freescale/imx95/sys/metrics.json
+++ b/tools/perf/pmu-events/arch/arm64/freescale/imx95/sys/metrics.json
@@ -7,6 +7,14 @@
 		"Unit": "imx9_ddr",
 		"Compat": "imx95"
 	},
+	{
+		"BriefDescription": "bandwidth usage for lpddr4x evk board",
+		"MetricName": "imx95_bandwidth_usage.lpddr4x",
+		"MetricExpr": "(( imx9_ddr0@eddrtq_pm_rd_beat_filt0\\,axi_mask\\=0x000\\,axi_id\\=0x000@ + imx9_ddr0@eddrtq_pm_wr_beat_filt\\,axi_mask\\=0x000\\,axi_id\\=0x000@ ) * 32 / duration_time) / (4000 * 1000000 * 4)",
+		"ScaleUnit": "1e2%",
+		"Unit": "imx9_ddr",
+		"Compat": "imx95"
+	},
 	{
 		"BriefDescription": "bytes of all masters read from ddr",
 		"MetricName": "imx95_ddr_read.all",

From 77b004f4c5c3c90b20ad61c5fa2ba7d494c1dba1 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 12 Sep 2024 15:42:08 -0700
Subject: [PATCH 0017/1530] perf symbol: Do not fixup end address of labels

When it loads symbols from an ELF file, it loads label symbols which is
0 size.  Sometimes it has the same address with other symbols and might
shadow the original symbols because it fixes up the size of the symbol.

For example, in my system __do_softirq is shadowed and only accepts the
__softirqentry_text_start instead.  But it should accept __do_softirq.

  $ readelf -sW vmlinux | grep -e __do_softirq -e __softirqentry_text_start
  105089: ffffffff82000000   814 FUNC    GLOBAL DEFAULT    1 __do_softirq
  111954: ffffffff82000000     0 NOTYPE  GLOBAL DEFAULT    1 __softirqentry_text_start

  $ perf annotate --stdio __do_softirq
  Error:
  The perf.data data has no samples!

  $ perf annotate --stdio __softirqentry_text_start | head
   Percent |	Source code & Disassembly of vmlinux for cycles (26 samples, percent: local period)
  ---------------------------------------------------------------------------------------------------
           : 0                0xffffffff82000000 <__softirqentry_text_start>:
      0.00 :   ffffffff82000000:        nopl    (%rax,%rax)
     30.77 :   ffffffff82000005:        pushq   %rbp
      3.85 :   ffffffff82000006:        movq    %rsp, %rbp
      0.00 :   ffffffff82000009:        pushq   %r15
      3.85 :   ffffffff8200000b:        pushq   %r14
      3.85 :   ffffffff8200000d:        pushq   %r13
      0.00 :   ffffffff8200000f:        pushq   %r12

We can ignore NOTYPE symbols in the symbols__fixup_end() so that it can
pick the __do_softirq() in choose_best_symbol().  This should be fine
since most symbols have either STT_FUNC or STT_OBJECT.

Link: https://lore.kernel.org/r/20240912224208.3360116-1-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/symbol.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index a18927d792afc..d9ecef526645b 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -257,7 +257,7 @@ void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms)
 		 * like in:
 		 *   ffffffffc1937000 T hdmi_driver_init  [snd_hda_codec_hdmi]
 		 */
-		if (prev->end == prev->start) {
+		if (prev->end == prev->start && prev->type != STT_NOTYPE) {
 			const char *prev_mod;
 			const char *curr_mod;
 

From 7e73ea40295620e7be9b6da29c711514c287fb78 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 25 Sep 2024 10:30:13 -0700
Subject: [PATCH 0018/1530] perf test: Ignore security failures in all PMU test

Refactor code to have some more error diagnosis on traps, etc. and to
do less work on each line. Add an ignore situation for security failures.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20240925173013.12789-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/stat_all_pmu.sh | 52 ++++++++++++++++++++------
 1 file changed, 40 insertions(+), 12 deletions(-)

diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh
index d2a3506e0d196..42456d89c5da3 100755
--- a/tools/perf/tests/shell/stat_all_pmu.sh
+++ b/tools/perf/tests/shell/stat_all_pmu.sh
@@ -1,23 +1,51 @@
-#!/bin/sh
+#!/bin/bash
 # perf all PMU test
 # SPDX-License-Identifier: GPL-2.0
 
 set -e
+err=0
+result=""
+
+trap_cleanup() {
+  echo "Unexpected signal in ${FUNCNAME[1]}"
+  echo "$result"
+  exit 1
+}
+trap trap_cleanup EXIT TERM INT
 
 # Test all PMU events; however exclude parameterized ones (name contains '?')
-for p in $(perf list --raw-dump pmu | sed 's/[[:graph:]]\+?[[:graph:]]\+[[:space:]]//g'); do
+for p in $(perf list --raw-dump pmu | sed 's/[[:graph:]]\+?[[:graph:]]\+[[:space:]]//g')
+do
   echo "Testing $p"
   result=$(perf stat -e "$p" true 2>&1)
-  if ! echo "$result" | grep -q "$p" && ! echo "$result" | grep -q "<not supported>" ; then
-    # We failed to see the event and it is supported. Possibly the workload was
-    # too small so retry with something longer.
-    result=$(perf stat -e "$p" perf bench internals synthesize 2>&1)
-    if ! echo "$result" | grep -q "$p" ; then
-      echo "Event '$p' not printed in:"
-      echo "$result"
-      exit 1
-    fi
+  if echo "$result" | grep -q "$p"
+  then
+    # Event seen in output.
+    continue
+  fi
+  if echo "$result" | grep -q "<not supported>"
+  then
+    # Event not supported, so ignore.
+    continue
+  fi
+  if echo "$result" | grep -q "Access to performance monitoring and observability operations is limited."
+  then
+    # Access is limited, so ignore.
+    continue
+  fi
+
+  # We failed to see the event and it is supported. Possibly the workload was
+  # too small so retry with something longer.
+  result=$(perf stat -e "$p" perf bench internals synthesize 2>&1)
+  if echo "$result" | grep -q "$p"
+  then
+    # Event seen in output.
+    continue
   fi
+  echo "Error: event '$p' not printed in:"
+  echo "$result"
+  err=1
 done
 
-exit 0
+trap - EXIT TERM INT
+exit $err

From 22a4db3c36034e2b034c5b88414680857fc59cf4 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 26 Sep 2024 15:48:32 +0100
Subject: [PATCH 0019/1530] perf evsel: Add alternate_hw_config and use in
 evsel__match

There are cases where we want to match events like instructions and
cycles with legacy hardware values, in particular in stat-shadow's
hard coded metrics. An evsel's name isn't a good point of reference as
it gets altered, strstr would be too imprecise and re-parsing the
event from its name is silly. Instead, hold the legacy hardware event
name, determined during parsing, in the evsel for this matching case.

Inline evsel__match2 that is only used in builtin-diff.

Acked-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Dominique Martinet <asmadeus@codewreck.org>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Yunseong Kim <yskelg@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: ak@linux.intel.com
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Sun Haiyong <sunhaiyong@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20240926144851.245903-2-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-diff.c      |  6 ++--
 tools/perf/util/evsel.c        | 21 ++++++++++++
 tools/perf/util/evsel.h        | 19 ++---------
 tools/perf/util/parse-events.c | 59 +++++++++++++++++++++-------------
 tools/perf/util/parse-events.h |  8 ++++-
 tools/perf/util/parse-events.y |  2 +-
 tools/perf/util/pmu.c          |  6 +++-
 tools/perf/util/pmu.h          |  2 +-
 8 files changed, 77 insertions(+), 46 deletions(-)

diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 23326dd203339..82fb7773e03e6 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -469,13 +469,13 @@ static int diff__process_sample_event(const struct perf_tool *tool,
 
 static struct perf_diff pdiff;
 
-static struct evsel *evsel_match(struct evsel *evsel,
-				      struct evlist *evlist)
+static struct evsel *evsel_match(struct evsel *evsel, struct evlist *evlist)
 {
 	struct evsel *e;
 
 	evlist__for_each_entry(evlist, e) {
-		if (evsel__match2(evsel, e))
+		if ((evsel->core.attr.type == e->core.attr.type) &&
+		    (evsel->core.attr.config == e->core.attr.config))
 			return e;
 	}
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index b9c18f3316997..b9d7b56dfc5e9 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -299,6 +299,7 @@ void evsel__init(struct evsel *evsel,
 	evsel->pmu_name      = NULL;
 	evsel->group_pmu_name = NULL;
 	evsel->skippable     = false;
+	evsel->alternate_hw_config = PERF_COUNT_HW_MAX;
 }
 
 struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx)
@@ -445,6 +446,8 @@ struct evsel *evsel__clone(struct evsel *orig)
 	if (evsel__copy_config_terms(evsel, orig) < 0)
 		goto out_err;
 
+	evsel->alternate_hw_config = orig->alternate_hw_config;
+
 	return evsel;
 
 out_err:
@@ -1845,6 +1848,24 @@ static int evsel__read_tool(struct evsel *evsel, int cpu_map_idx, int thread)
 	return 0;
 }
 
+bool __evsel__match(const struct evsel *evsel, u32 type, u64 config)
+{
+
+	u32 e_type = evsel->core.attr.type;
+	u64 e_config = evsel->core.attr.config;
+
+	if (e_type != type) {
+		return type == PERF_TYPE_HARDWARE && evsel->pmu && evsel->pmu->is_core &&
+			evsel->alternate_hw_config == config;
+	}
+
+	if ((type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE) &&
+	    perf_pmus__supports_extended_type())
+		e_config &= PERF_HW_EVENT_MASK;
+
+	return e_config == config;
+}
+
 int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread)
 {
 	if (evsel__is_tool(evsel))
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 15e745a9a798f..cf6f11fdfd061 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -102,6 +102,7 @@ struct evsel {
 		int			bpf_fd;
 		struct bpf_object	*bpf_obj;
 		struct list_head	config_terms;
+		u64			alternate_hw_config;
 	};
 
 	/*
@@ -393,26 +394,10 @@ u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sam
 struct tep_format_field *evsel__field(struct evsel *evsel, const char *name);
 struct tep_format_field *evsel__common_field(struct evsel *evsel, const char *name);
 
-static inline bool __evsel__match(const struct evsel *evsel, u32 type, u64 config)
-{
-	if (evsel->core.attr.type != type)
-		return false;
-
-	if ((type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE)  &&
-	    perf_pmus__supports_extended_type())
-		return (evsel->core.attr.config & PERF_HW_EVENT_MASK) == config;
-
-	return evsel->core.attr.config == config;
-}
+bool __evsel__match(const struct evsel *evsel, u32 type, u64 config);
 
 #define evsel__match(evsel, t, c) __evsel__match(evsel, PERF_TYPE_##t, PERF_COUNT_##c)
 
-static inline bool evsel__match2(struct evsel *e1, struct evsel *e2)
-{
-	return (e1->core.attr.type == e2->core.attr.type) &&
-	       (e1->core.attr.config == e2->core.attr.config);
-}
-
 int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread);
 
 int __evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread, bool scale);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 9a8be1e46d674..fcc4dab618bee 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -228,7 +228,7 @@ __add_event(struct list_head *list, int *idx,
 	    bool init_attr,
 	    const char *name, const char *metric_id, struct perf_pmu *pmu,
 	    struct list_head *config_terms, bool auto_merge_stats,
-	    struct perf_cpu_map *cpu_list)
+	    struct perf_cpu_map *cpu_list, u64 alternate_hw_config)
 {
 	struct evsel *evsel;
 	struct perf_cpu_map *cpus = perf_cpu_map__is_empty(cpu_list) && pmu ? pmu->cpus : cpu_list;
@@ -264,6 +264,7 @@ __add_event(struct list_head *list, int *idx,
 	evsel->auto_merge_stats = auto_merge_stats;
 	evsel->pmu = pmu;
 	evsel->pmu_name = pmu ? strdup(pmu->name) : NULL;
+	evsel->alternate_hw_config = alternate_hw_config;
 
 	if (name)
 		evsel->name = strdup(name);
@@ -286,16 +287,19 @@ struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr,
 {
 	return __add_event(/*list=*/NULL, &idx, attr, /*init_attr=*/false, name,
 			   metric_id, pmu, /*config_terms=*/NULL,
-			   /*auto_merge_stats=*/false, /*cpu_list=*/NULL);
+			   /*auto_merge_stats=*/false, /*cpu_list=*/NULL,
+			   /*alternate_hw_config=*/PERF_COUNT_HW_MAX);
 }
 
 static int add_event(struct list_head *list, int *idx,
 		     struct perf_event_attr *attr, const char *name,
-		     const char *metric_id, struct list_head *config_terms)
+		     const char *metric_id, struct list_head *config_terms,
+		     u64 alternate_hw_config)
 {
 	return __add_event(list, idx, attr, /*init_attr*/true, name, metric_id,
 			   /*pmu=*/NULL, config_terms,
-			   /*auto_merge_stats=*/false, /*cpu_list=*/NULL) ? 0 : -ENOMEM;
+			   /*auto_merge_stats=*/false, /*cpu_list=*/NULL,
+			   alternate_hw_config) ? 0 : -ENOMEM;
 }
 
 static int add_event_tool(struct list_head *list, int *idx,
@@ -315,7 +319,8 @@ static int add_event_tool(struct list_head *list, int *idx,
 	evsel = __add_event(list, idx, &attr, /*init_attr=*/true, /*name=*/NULL,
 			    /*metric_id=*/NULL, /*pmu=*/NULL,
 			    /*config_terms=*/NULL, /*auto_merge_stats=*/false,
-			    cpu_list);
+			    cpu_list,
+			    /*alternate_hw_config=*/PERF_COUNT_HW_MAX);
 	perf_cpu_map__put(cpu_list);
 	if (!evsel)
 		return -ENOMEM;
@@ -450,7 +455,7 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
 static int parse_events_add_pmu(struct parse_events_state *parse_state,
 				struct list_head *list, struct perf_pmu *pmu,
 				const struct parse_events_terms *const_parsed_terms,
-				bool auto_merge_stats);
+				bool auto_merge_stats, u64 alternate_hw_config);
 
 int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 			   struct parse_events_state *parse_state,
@@ -476,7 +481,8 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 			 */
 			ret = parse_events_add_pmu(parse_state, list, pmu,
 						   parsed_terms,
-						   perf_pmu__auto_merge_stats(pmu));
+						   perf_pmu__auto_merge_stats(pmu),
+						   /*alternate_hw_config=*/PERF_COUNT_HW_MAX);
 			if (ret)
 				return ret;
 			continue;
@@ -507,7 +513,8 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 
 		if (__add_event(list, idx, &attr, /*init_attr*/true, config_name ?: name,
 				metric_id, pmu, &config_terms, /*auto_merge_stats=*/false,
-				/*cpu_list=*/NULL) == NULL)
+				/*cpu_list=*/NULL,
+				/*alternate_hw_config=*/PERF_COUNT_HW_MAX) == NULL)
 			return -ENOMEM;
 
 		free_config_terms(&config_terms);
@@ -772,7 +779,7 @@ int parse_events_add_breakpoint(struct parse_events_state *parse_state,
 	name = get_config_name(head_config);
 
 	return add_event(list, &parse_state->idx, &attr, name, /*mertic_id=*/NULL,
-			 &config_terms);
+			&config_terms, /*alternate_hw_config=*/PERF_COUNT_HW_MAX);
 }
 
 static int check_type_val(struct parse_events_term *term,
@@ -1072,6 +1079,7 @@ static int config_term_pmu(struct perf_event_attr *attr,
 		if (perf_pmu__have_event(pmu, term->config)) {
 			term->type_term = PARSE_EVENTS__TERM_TYPE_USER;
 			term->no_value = true;
+			term->alternate_hw_config = true;
 		} else {
 			attr->type = PERF_TYPE_HARDWARE;
 			attr->config = term->val.num;
@@ -1384,8 +1392,9 @@ static int __parse_events_add_numeric(struct parse_events_state *parse_state,
 	name = get_config_name(head_config);
 	metric_id = get_config_metric_id(head_config);
 	ret = __add_event(list, &parse_state->idx, &attr, /*init_attr*/true, name,
-			metric_id, pmu, &config_terms, /*auto_merge_stats=*/false,
-			/*cpu_list=*/NULL) ? 0 : -ENOMEM;
+			  metric_id, pmu, &config_terms, /*auto_merge_stats=*/false,
+			  /*cpu_list=*/NULL, /*alternate_hw_config=*/PERF_COUNT_HW_MAX
+		) == NULL ? -ENOMEM : 0;
 	free_config_terms(&config_terms);
 	return ret;
 }
@@ -1443,7 +1452,7 @@ static bool config_term_percore(struct list_head *config_terms)
 static int parse_events_add_pmu(struct parse_events_state *parse_state,
 				struct list_head *list, struct perf_pmu *pmu,
 				const struct parse_events_terms *const_parsed_terms,
-				bool auto_merge_stats)
+				bool auto_merge_stats, u64 alternate_hw_config)
 {
 	struct perf_event_attr attr;
 	struct perf_pmu_info info;
@@ -1480,7 +1489,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 				    /*init_attr=*/true, /*name=*/NULL,
 				    /*metric_id=*/NULL, pmu,
 				    /*config_terms=*/NULL, auto_merge_stats,
-				    /*cpu_list=*/NULL);
+				    /*cpu_list=*/NULL, alternate_hw_config);
 		return evsel ? 0 : -ENOMEM;
 	}
 
@@ -1501,7 +1510,8 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	/* Look for event names in the terms and rewrite into format based terms. */
 	if (perf_pmu__check_alias(pmu, &parsed_terms,
-				  &info, &alias_rewrote_terms, err)) {
+				  &info, &alias_rewrote_terms,
+				  &alternate_hw_config, err)) {
 		parse_events_terms__exit(&parsed_terms);
 		return -EINVAL;
 	}
@@ -1546,7 +1556,8 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 	evsel = __add_event(list, &parse_state->idx, &attr, /*init_attr=*/true,
 			    get_config_name(&parsed_terms),
 			    get_config_metric_id(&parsed_terms), pmu,
-			    &config_terms, auto_merge_stats, /*cpu_list=*/NULL);
+			    &config_terms, auto_merge_stats, /*cpu_list=*/NULL,
+			    alternate_hw_config);
 	if (!evsel) {
 		parse_events_terms__exit(&parsed_terms);
 		return -ENOMEM;
@@ -1567,7 +1578,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 }
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
-			       const char *event_name,
+			       const char *event_name, u64 hw_config,
 			       const struct parse_events_terms *const_parsed_terms,
 			       struct list_head **listp, void *loc_)
 {
@@ -1620,7 +1631,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 
 		auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
 		if (!parse_events_add_pmu(parse_state, list, pmu,
-					  &parsed_terms, auto_merge_stats)) {
+					  &parsed_terms, auto_merge_stats, hw_config)) {
 			struct strbuf sb;
 
 			strbuf_init(&sb, /*hint=*/ 0);
@@ -1633,7 +1644,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 
 	if (parse_state->fake_pmu) {
 		if (!parse_events_add_pmu(parse_state, list, perf_pmus__fake_pmu(), &parsed_terms,
-					  /*auto_merge_stats=*/true)) {
+					  /*auto_merge_stats=*/true, hw_config)) {
 			struct strbuf sb;
 
 			strbuf_init(&sb, /*hint=*/ 0);
@@ -1674,13 +1685,15 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state
 	/* Attempt to add to list assuming event_or_pmu is a PMU name. */
 	pmu = perf_pmus__find(event_or_pmu);
 	if (pmu && !parse_events_add_pmu(parse_state, *listp, pmu, const_parsed_terms,
-					/*auto_merge_stats=*/false))
+					 /*auto_merge_stats=*/false,
+					 /*alternate_hw_config=*/PERF_COUNT_HW_MAX))
 		return 0;
 
 	if (parse_state->fake_pmu) {
 		if (!parse_events_add_pmu(parse_state, *listp, perf_pmus__fake_pmu(),
 					  const_parsed_terms,
-					  /*auto_merge_stats=*/false))
+					  /*auto_merge_stats=*/false,
+					  /*alternate_hw_config=*/PERF_COUNT_HW_MAX))
 			return 0;
 	}
 
@@ -1693,7 +1706,8 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state
 
 			if (!parse_events_add_pmu(parse_state, *listp, pmu,
 						  const_parsed_terms,
-						  auto_merge_stats)) {
+						  auto_merge_stats,
+						  /*alternate_hw_config=*/PERF_COUNT_HW_MAX)) {
 				ok++;
 				parse_state->wild_card_pmus = true;
 			}
@@ -1704,7 +1718,8 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state
 
 	/* Failure to add, assume event_or_pmu is an event name. */
 	zfree(listp);
-	if (!parse_events_multi_pmu_add(parse_state, event_or_pmu, const_parsed_terms, listp, loc))
+	if (!parse_events_multi_pmu_add(parse_state, event_or_pmu, PERF_COUNT_HW_MAX,
+					const_parsed_terms, listp, loc))
 		return 0;
 
 	if (asprintf(&help, "Unable to find PMU or event on a PMU of '%s'", event_or_pmu) < 0)
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 10cc9c433116d..2b52f8d6aa29a 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -127,6 +127,12 @@ struct parse_events_term {
 	 * value is assumed to be 1. An event name also has no value.
 	 */
 	bool no_value;
+	/**
+	 * @alternate_hw_config: config is the event name but num is an
+	 * alternate PERF_TYPE_HARDWARE config value which is often nice for the
+	 * sake of quick matching.
+	 */
+	bool alternate_hw_config;
 };
 
 struct parse_events_error {
@@ -238,7 +244,7 @@ struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr,
 				      struct perf_pmu *pmu);
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
-			       const char *event_name,
+			       const char *event_name, u64 hw_config,
 			       const struct parse_events_terms *const_parsed_terms,
 			       struct list_head **listp, void *loc);
 
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index b3c51f06cbdc4..dcf47fabdfdd7 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -292,7 +292,7 @@ PE_NAME sep_dc
 	struct list_head *list;
 	int err;
 
-	err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list, &@1);
+	err = parse_events_multi_pmu_add(_parse_state, $1, PERF_COUNT_HW_MAX, NULL, &list, &@1);
 	if (err < 0) {
 		struct parse_events_state *parse_state = _parse_state;
 		struct parse_events_error *error = parse_state->error;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 61bdda01a05ac..e32d601b48f1e 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1606,7 +1606,7 @@ static int check_info_data(struct perf_pmu *pmu,
  */
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_terms,
 			  struct perf_pmu_info *info, bool *rewrote_terms,
-			  struct parse_events_error *err)
+			  u64 *alternate_hw_config, struct parse_events_error *err)
 {
 	struct parse_events_term *term, *h;
 	struct perf_pmu_alias *alias;
@@ -1638,6 +1638,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_
 						NULL);
 			return ret;
 		}
+
 		*rewrote_terms = true;
 		ret = check_info_data(pmu, alias, info, err, term->err_term);
 		if (ret)
@@ -1646,6 +1647,9 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_
 		if (alias->per_pkg)
 			info->per_pkg = true;
 
+		if (term->alternate_hw_config)
+			*alternate_hw_config = term->val.num;
+
 		list_del_init(&term->list);
 		parse_events_term__delete(term);
 	}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 4397c48ad569a..f4271395c3744 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -215,7 +215,7 @@ __u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name);
 int perf_pmu__format_type(struct perf_pmu *pmu, const char *name);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_terms,
 			  struct perf_pmu_info *info, bool *rewrote_terms,
-			  struct parse_events_error *err);
+			  u64 *alternate_hw_config, struct parse_events_error *err);
 int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, pmu_event_callback cb);
 
 void perf_pmu_format__set_value(void *format, int config, unsigned long *bits);

From 057f8bfc6f7070577523d1e3081081bbf4229c1c Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 26 Sep 2024 15:48:33 +0100
Subject: [PATCH 0020/1530] perf stat: Uniquify event name improvements

Without aggregation on Intel:
```
$ perf stat -e instructions,cycles ...
```
Will use "cycles" for the name of the legacy cycles event but as
"instructions" has a sysfs name it will and a "[cpu]" PMU suffix. This
often breaks things as the space between the event and the PMU name
look like an extra column. The existing uniquify logic was also
uniquifying in cases when all events are core and not with uncore
events, it was not correctly handling modifiers, etc.

Change the logic so that an initial pass that can disable
uniquification is run. For individual counters, disable uniquification
in more cases such as for consistency with legacy events or for
libpfm4 events. Don't use the "[pmu]" style suffix in uniquification,
always use "pmu/.../". Change how modifiers/terms are handled in the
uniquification so that they look like parse-able events.

This fixes "102: perf stat metrics (shadow stat) test:" that has been
failing due to "instructions [cpu]" breaking its column/awk logic when
values aren't aggregated. This started happening when instructions
could match a sysfs rather than a legacy event, so the fixes tag
reflects this.

Fixes: 617824a7f0f7 ("perf parse-events: Prefer sysfs/JSON hardware events over legacy")
Acked-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
[ Fix Intel TPEBS counting mode test ]
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Dominique Martinet <asmadeus@codewreck.org>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: ak@linux.intel.com
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Sun Haiyong <sunhaiyong@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20240926144851.245903-3-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../perf/tests/shell/test_stat_intel_tpebs.sh |  11 +-
 tools/perf/util/stat-display.c                | 101 ++++++++++++++----
 2 files changed, 85 insertions(+), 27 deletions(-)

diff --git a/tools/perf/tests/shell/test_stat_intel_tpebs.sh b/tools/perf/tests/shell/test_stat_intel_tpebs.sh
index c60b29add9801..9a11f42d153ca 100755
--- a/tools/perf/tests/shell/test_stat_intel_tpebs.sh
+++ b/tools/perf/tests/shell/test_stat_intel_tpebs.sh
@@ -8,12 +8,15 @@ grep -q GenuineIntel /proc/cpuinfo || { echo Skipping non-Intel; exit 2; }
 # Use this event for testing because it should exist in all platforms
 event=cache-misses:R
 
+# Hybrid platforms output like "cpu_atom/cache-misses/R", rather than as above
+alt_name=/cache-misses/R
+
 # Without this cmd option, default value or zero is returned
-echo "Testing without --record-tpebs"
-result=$(perf stat -e "$event" true 2>&1)
-[[ "$result" =~ $event ]] || exit 1
+#echo "Testing without --record-tpebs"
+#result=$(perf stat -e "$event" true 2>&1)
+#[[ "$result" =~ $event || "$result" =~ $alt_name ]] || exit 1
 
 # In platforms that do not support TPEBS, it should execute without error.
 echo "Testing with --record-tpebs"
 result=$(perf stat -e "$event" --record-tpebs -a sleep 0.01 2>&1)
-[[ "$result" =~ "perf record" && "$result" =~ $event ]] || exit 1
+[[ "$result" =~ "perf record" && "$result" =~ $event || "$result" =~ $alt_name ]] || exit 1
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index ea96e4ebad8c8..cbff43ff8d0fb 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -871,38 +871,66 @@ static void printout(struct perf_stat_config *config, struct outstate *os,
 
 static void uniquify_event_name(struct evsel *counter)
 {
-	char *new_name;
-	char *config;
-	int ret = 0;
+	const char *name, *pmu_name;
+	char *new_name, *config;
+	int ret;
 
-	if (counter->uniquified_name || counter->use_config_name ||
-	    !counter->pmu_name || !strncmp(evsel__name(counter), counter->pmu_name,
-					   strlen(counter->pmu_name)))
+	/* The evsel was already uniquified. */
+	if (counter->uniquified_name)
 		return;
 
-	config = strchr(counter->name, '/');
+	/* Avoid checking to uniquify twice. */
+	counter->uniquified_name = true;
+
+	/* The evsel has a "name=" config term or is from libpfm. */
+	if (counter->use_config_name || counter->is_libpfm_event)
+		return;
+
+	/* Legacy no PMU event, don't uniquify. */
+	if  (!counter->pmu ||
+	     (counter->pmu->type < PERF_TYPE_MAX && counter->pmu->type != PERF_TYPE_RAW))
+		return;
+
+	/* A sysfs or json event replacing a legacy event, don't uniquify. */
+	if (counter->pmu->is_core && counter->alternate_hw_config != PERF_COUNT_HW_MAX)
+		return;
+
+	name = evsel__name(counter);
+	pmu_name = counter->pmu->name;
+	/* Already prefixed by the PMU name. */
+	if (!strncmp(name, pmu_name, strlen(pmu_name)))
+		return;
+
+	config = strchr(name, '/');
 	if (config) {
-		if (asprintf(&new_name,
-			     "%s%s", counter->pmu_name, config) > 0) {
-			free(counter->name);
-			counter->name = new_name;
-		}
-	} else {
-		if (evsel__is_hybrid(counter)) {
-			ret = asprintf(&new_name, "%s/%s/",
-				       counter->pmu_name, counter->name);
+		int len = config - name;
+
+		if (config[1] == '/') {
+			/* case: event// */
+			ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 2);
 		} else {
-			ret = asprintf(&new_name, "%s [%s]",
-				       counter->name, counter->pmu_name);
+			/* case: event/.../ */
+			ret = asprintf(&new_name, "%s/%.*s,%s", pmu_name, len, name, config + 1);
 		}
+	} else {
+		config = strchr(name, ':');
+		if (config) {
+			/* case: event:.. */
+			int len = config - name;
 
-		if (ret) {
-			free(counter->name);
-			counter->name = new_name;
+			ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 1);
+		} else {
+			/* case: event */
+			ret = asprintf(&new_name, "%s/%s/", pmu_name, name);
 		}
 	}
-
-	counter->uniquified_name = true;
+	if (ret > 0) {
+		free(counter->name);
+		counter->name = new_name;
+	} else {
+		/* ENOMEM from asprintf. */
+		counter->uniquified_name = false;
+	}
 }
 
 static bool hybrid_uniquify(struct evsel *evsel, struct perf_stat_config *config)
@@ -1559,6 +1587,31 @@ static void print_cgroup_counter(struct perf_stat_config *config, struct evlist
 		print_metric_end(config, os);
 }
 
+static void disable_uniquify(struct evlist *evlist)
+{
+	struct evsel *counter;
+	struct perf_pmu *last_pmu = NULL;
+	bool first = true;
+
+	evlist__for_each_entry(evlist, counter) {
+		/* If PMUs vary then uniquify can be useful. */
+		if (!first && counter->pmu != last_pmu)
+			return;
+		first = false;
+		if (counter->pmu) {
+			/* Allow uniquify for uncore PMUs. */
+			if (!counter->pmu->is_core)
+				return;
+			/* Keep hybrid event names uniquified for clarity. */
+			if (perf_pmus__num_core_pmus() > 1)
+				return;
+		}
+	}
+	evlist__for_each_entry_continue(evlist, counter) {
+		counter->uniquified_name = true;
+	}
+}
+
 void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config,
 			    struct target *_target, struct timespec *ts,
 			    int argc, const char **argv)
@@ -1572,6 +1625,8 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf
 		.first = true,
 	};
 
+	disable_uniquify(evlist);
+
 	if (config->iostat_run)
 		evlist->selected = evlist__first(evlist);
 

From d38461e977baf93f9e01967caa9571ccd1694def Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 26 Sep 2024 15:48:34 +0100
Subject: [PATCH 0021/1530] perf stat: Remove evlist__add_default_attrs use
 strings

add_default_atttributes would add evsels by having pre-created
perf_event_attr, however, this needed fixing for hybrid as the
extended PMU type was necessary for each core PMU. The logic for this
was in an arch specific x86 function and wasn't present for ARM,
meaning that default events weren't being opened on all PMUs on
ARM. Change the creation of the default events to use parse_events and
strings as that will open the events on all PMUs.

Rather than try to detect events on PMUs before parsing, parse the
event but skip its output in stat-display.

The previous order of hardware events was: cycles,
stalled-cycles-frontend, stalled-cycles-backend, instructions. As
instructions is a more fundamental concept the order is changed to:
instructions, cycles, stalled-cycles-frontend, stalled-cycles-backend.

Closes: https://lore.kernel.org/lkml/CAP-5=fVABSBZnsmtRn1uF-k-G1GWM-L5SgiinhPTfHbQsKXb_g@mail.gmail.com/
Acked-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
[Don't display unsupported default events except 'cycles']
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Dominique Martinet <asmadeus@codewreck.org>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: ak@linux.intel.com
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Sun Haiyong <sunhaiyong@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20240926144851.245903-4-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/x86/util/evlist.c |  74 +-------
 tools/perf/builtin-stat.c         | 297 ++++++++++++------------------
 tools/perf/util/evlist.c          |  43 -----
 tools/perf/util/evlist.h          |  12 --
 tools/perf/util/stat-display.c    |   8 +
 tools/perf/util/stat-shadow.c     |   4 +-
 6 files changed, 131 insertions(+), 307 deletions(-)

diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index cebdd483149e8..3a4bf13b17593 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -1,78 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <stdio.h>
-#include "util/pmu.h"
-#include "util/pmus.h"
-#include "util/evlist.h"
-#include "util/parse-events.h"
-#include "util/event.h"
+#include <string.h>
+#include "../../../util/evlist.h"
+#include "../../../util/evsel.h"
 #include "topdown.h"
 #include "evsel.h"
 
-static int ___evlist__add_default_attrs(struct evlist *evlist,
-					struct perf_event_attr *attrs,
-					size_t nr_attrs)
-{
-	LIST_HEAD(head);
-	size_t i = 0;
-
-	for (i = 0; i < nr_attrs; i++)
-		event_attr_init(attrs + i);
-
-	if (perf_pmus__num_core_pmus() == 1)
-		return evlist__add_attrs(evlist, attrs, nr_attrs);
-
-	for (i = 0; i < nr_attrs; i++) {
-		struct perf_pmu *pmu = NULL;
-
-		if (attrs[i].type == PERF_TYPE_SOFTWARE) {
-			struct evsel *evsel = evsel__new(attrs + i);
-
-			if (evsel == NULL)
-				goto out_delete_partial_list;
-			list_add_tail(&evsel->core.node, &head);
-			continue;
-		}
-
-		while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
-			struct perf_cpu_map *cpus;
-			struct evsel *evsel;
-
-			evsel = evsel__new(attrs + i);
-			if (evsel == NULL)
-				goto out_delete_partial_list;
-			evsel->core.attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
-			cpus = perf_cpu_map__get(pmu->cpus);
-			evsel->core.cpus = cpus;
-			evsel->core.own_cpus = perf_cpu_map__get(cpus);
-			evsel->pmu_name = strdup(pmu->name);
-			list_add_tail(&evsel->core.node, &head);
-		}
-	}
-
-	evlist__splice_list_tail(evlist, &head);
-
-	return 0;
-
-out_delete_partial_list:
-	{
-		struct evsel *evsel, *n;
-
-		__evlist__for_each_entry_safe(&head, n, evsel)
-			evsel__delete(evsel);
-	}
-	return -1;
-}
-
-int arch_evlist__add_default_attrs(struct evlist *evlist,
-				   struct perf_event_attr *attrs,
-				   size_t nr_attrs)
-{
-	if (!nr_attrs)
-		return 0;
-
-	return ___evlist__add_default_attrs(evlist, attrs, nr_attrs);
-}
-
 int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 {
 	if (topdown_sys_has_perf_metrics() &&
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 6cad3435b1984..1521b6df26065 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1842,130 +1842,25 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
 }
 
 /*
- * Add default attributes, if there were no attributes specified or
+ * Add default events, if there were no attributes specified or
  * if -d/--detailed, -d -d or -d -d -d is used:
  */
-static int add_default_attributes(void)
+static int add_default_events(void)
 {
-	struct perf_event_attr default_attrs0[] = {
-
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK		},
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES	},
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS		},
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS		},
-
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES		},
-};
-	struct perf_event_attr frontend_attrs[] = {
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	},
-};
-	struct perf_event_attr backend_attrs[] = {
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND	},
-};
-	struct perf_event_attr default_attrs1[] = {
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS		},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS	},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES		},
-
-};
-
-/*
- * Detailed stats (-d), covering the L1 and last level data caches:
- */
-	struct perf_event_attr detailed_attrs[] = {
-
-  { .type = PERF_TYPE_HW_CACHE,
-    .config =
-	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
-	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
-	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
-
-  { .type = PERF_TYPE_HW_CACHE,
-    .config =
-	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
-	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
-	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
-
-  { .type = PERF_TYPE_HW_CACHE,
-    .config =
-	 PERF_COUNT_HW_CACHE_LL			<<  0  |
-	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
-	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
-
-  { .type = PERF_TYPE_HW_CACHE,
-    .config =
-	 PERF_COUNT_HW_CACHE_LL			<<  0  |
-	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
-	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
-};
-
-/*
- * Very detailed stats (-d -d), covering the instruction cache and the TLB caches:
- */
-	struct perf_event_attr very_detailed_attrs[] = {
-
-  { .type = PERF_TYPE_HW_CACHE,
-    .config =
-	 PERF_COUNT_HW_CACHE_L1I		<<  0  |
-	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
-	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
-
-  { .type = PERF_TYPE_HW_CACHE,
-    .config =
-	 PERF_COUNT_HW_CACHE_L1I		<<  0  |
-	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
-	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
-
-  { .type = PERF_TYPE_HW_CACHE,
-    .config =
-	 PERF_COUNT_HW_CACHE_DTLB		<<  0  |
-	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
-	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
-
-  { .type = PERF_TYPE_HW_CACHE,
-    .config =
-	 PERF_COUNT_HW_CACHE_DTLB		<<  0  |
-	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
-	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
-
-  { .type = PERF_TYPE_HW_CACHE,
-    .config =
-	 PERF_COUNT_HW_CACHE_ITLB		<<  0  |
-	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
-	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
-
-  { .type = PERF_TYPE_HW_CACHE,
-    .config =
-	 PERF_COUNT_HW_CACHE_ITLB		<<  0  |
-	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
-	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
-
-};
+	const char *pmu = parse_events_option_args.pmu_filter ?: "all";
+	struct parse_events_error err;
+	struct evlist *evlist = evlist__new();
+	struct evsel *evsel;
+	int ret = 0;
 
-/*
- * Very, very detailed stats (-d -d -d), adding prefetch events:
- */
-	struct perf_event_attr very_very_detailed_attrs[] = {
-
-  { .type = PERF_TYPE_HW_CACHE,
-    .config =
-	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
-	(PERF_COUNT_HW_CACHE_OP_PREFETCH	<<  8) |
-	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
-
-  { .type = PERF_TYPE_HW_CACHE,
-    .config =
-	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
-	(PERF_COUNT_HW_CACHE_OP_PREFETCH	<<  8) |
-	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
-};
+	if (!evlist)
+		return -ENOMEM;
 
-	struct perf_event_attr default_null_attrs[] = {};
-	const char *pmu = parse_events_option_args.pmu_filter ?: "all";
+	parse_events_error__init(&err);
 
 	/* Set attrs if no event is selected and !null_run: */
 	if (stat_config.null_run)
-		return 0;
+		goto out;
 
 	if (transaction_run) {
 		/* Handle -T as -M transaction. Once platform specific metrics
@@ -1975,9 +1870,10 @@ static int add_default_attributes(void)
 		 */
 		if (!metricgroup__has_metric(pmu, "transaction")) {
 			pr_err("Missing transaction metrics\n");
-			return -1;
+			ret = -1;
+			goto out;
 		}
-		return metricgroup__parse_groups(evsel_list, pmu, "transaction",
+		ret = metricgroup__parse_groups(evlist, pmu, "transaction",
 						stat_config.metric_no_group,
 						stat_config.metric_no_merge,
 						stat_config.metric_no_threshold,
@@ -1985,6 +1881,7 @@ static int add_default_attributes(void)
 						stat_config.system_wide,
 						stat_config.hardware_aware_grouping,
 						&stat_config.metric_events);
+		goto out;
 	}
 
 	if (smi_cost) {
@@ -1992,26 +1889,29 @@ static int add_default_attributes(void)
 
 		if (sysfs__read_int(FREEZE_ON_SMI_PATH, &smi) < 0) {
 			pr_err("freeze_on_smi is not supported.\n");
-			return -1;
+			ret = -1;
+			goto out;
 		}
 
 		if (!smi) {
 			if (sysfs__write_int(FREEZE_ON_SMI_PATH, 1) < 0) {
-				fprintf(stderr, "Failed to set freeze_on_smi.\n");
-				return -1;
+				pr_err("Failed to set freeze_on_smi.\n");
+				ret = -1;
+				goto out;
 			}
 			smi_reset = true;
 		}
 
 		if (!metricgroup__has_metric(pmu, "smi")) {
 			pr_err("Missing smi metrics\n");
-			return -1;
+			ret = -1;
+			goto out;
 		}
 
 		if (!force_metric_only)
 			stat_config.metric_only = true;
 
-		return metricgroup__parse_groups(evsel_list, pmu, "smi",
+		ret = metricgroup__parse_groups(evlist, pmu, "smi",
 						stat_config.metric_no_group,
 						stat_config.metric_no_merge,
 						stat_config.metric_no_threshold,
@@ -2019,6 +1919,7 @@ static int add_default_attributes(void)
 						stat_config.system_wide,
 						stat_config.hardware_aware_grouping,
 						&stat_config.metric_events);
+		goto out;
 	}
 
 	if (topdown_run) {
@@ -2031,21 +1932,23 @@ static int add_default_attributes(void)
 		if (!max_level) {
 			pr_err("Topdown requested but the topdown metric groups aren't present.\n"
 				"(See perf list the metric groups have names like TopdownL1)\n");
-			return -1;
+			ret = -1;
+			goto out;
 		}
 		if (stat_config.topdown_level > max_level) {
 			pr_err("Invalid top-down metrics level. The max level is %u.\n", max_level);
-			return -1;
-		} else if (!stat_config.topdown_level)
+			ret = -1;
+			goto out;
+		} else if (!stat_config.topdown_level) {
 			stat_config.topdown_level = 1;
-
+		}
 		if (!stat_config.interval && !stat_config.metric_only) {
 			fprintf(stat_config.output,
 				"Topdown accuracy may decrease when measuring long periods.\n"
 				"Please print the result regularly, e.g. -I1000\n");
 		}
 		str[8] = stat_config.topdown_level + '0';
-		if (metricgroup__parse_groups(evsel_list,
+		if (metricgroup__parse_groups(evlist,
 						pmu, str,
 						/*metric_no_group=*/false,
 						/*metric_no_merge=*/false,
@@ -2053,41 +1956,49 @@ static int add_default_attributes(void)
 						stat_config.user_requested_cpu_list,
 						stat_config.system_wide,
 						stat_config.hardware_aware_grouping,
-						&stat_config.metric_events) < 0)
-			return -1;
+						&stat_config.metric_events) < 0) {
+			ret = -1;
+			goto out;
+		}
 	}
 
 	if (!stat_config.topdown_level)
 		stat_config.topdown_level = 1;
 
-	if (!evsel_list->core.nr_entries) {
+	if (!evlist->core.nr_entries && !evsel_list->core.nr_entries) {
 		/* No events so add defaults. */
 		if (target__has_cpu(&target))
-			default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;
+			ret = parse_events(evlist, "cpu-clock", &err);
+		else
+			ret = parse_events(evlist, "task-clock", &err);
+		if (ret)
+			goto out;
+
+		ret = parse_events(evlist,
+				"context-switches,"
+				"cpu-migrations,"
+				"page-faults,"
+				"instructions,"
+				"cycles,"
+				"stalled-cycles-frontend,"
+				"stalled-cycles-backend,"
+				"branches,"
+				"branch-misses",
+				&err);
+		if (ret)
+			goto out;
 
-		if (evlist__add_default_attrs(evsel_list, default_attrs0) < 0)
-			return -1;
-		if (perf_pmus__have_event("cpu", "stalled-cycles-frontend")) {
-			if (evlist__add_default_attrs(evsel_list, frontend_attrs) < 0)
-				return -1;
-		}
-		if (perf_pmus__have_event("cpu", "stalled-cycles-backend")) {
-			if (evlist__add_default_attrs(evsel_list, backend_attrs) < 0)
-				return -1;
-		}
-		if (evlist__add_default_attrs(evsel_list, default_attrs1) < 0)
-			return -1;
 		/*
 		 * Add TopdownL1 metrics if they exist. To minimize
 		 * multiplexing, don't request threshold computation.
 		 */
 		if (metricgroup__has_metric(pmu, "Default")) {
 			struct evlist *metric_evlist = evlist__new();
-			struct evsel *metric_evsel;
-
-			if (!metric_evlist)
-				return -1;
 
+			if (!metric_evlist) {
+				ret = -ENOMEM;
+				goto out;
+			}
 			if (metricgroup__parse_groups(metric_evlist, pmu, "Default",
 							/*metric_no_group=*/false,
 							/*metric_no_merge=*/false,
@@ -2095,43 +2006,71 @@ static int add_default_attributes(void)
 							stat_config.user_requested_cpu_list,
 							stat_config.system_wide,
 							stat_config.hardware_aware_grouping,
-							&stat_config.metric_events) < 0)
-				return -1;
-
-			evlist__for_each_entry(metric_evlist, metric_evsel) {
-				metric_evsel->skippable = true;
-				metric_evsel->default_metricgroup = true;
+							&stat_config.metric_events) < 0) {
+				ret = -1;
+				goto out;
 			}
-			evlist__splice_list_tail(evsel_list, &metric_evlist->core.entries);
+
+			evlist__for_each_entry(metric_evlist, evsel)
+				evsel->default_metricgroup = true;
+
+			evlist__splice_list_tail(evlist, &metric_evlist->core.entries);
 			evlist__delete(metric_evlist);
 		}
-
-		/* Platform specific attrs */
-		if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0)
-			return -1;
 	}
 
 	/* Detailed events get appended to the event list: */
 
-	if (detailed_run <  1)
-		return 0;
-
-	/* Append detailed run extra attributes: */
-	if (evlist__add_default_attrs(evsel_list, detailed_attrs) < 0)
-		return -1;
-
-	if (detailed_run < 2)
-		return 0;
-
-	/* Append very detailed run extra attributes: */
-	if (evlist__add_default_attrs(evsel_list, very_detailed_attrs) < 0)
-		return -1;
-
-	if (detailed_run < 3)
-		return 0;
-
-	/* Append very, very detailed run extra attributes: */
-	return evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
+	if (!ret && detailed_run >=  1) {
+		/*
+		 * Detailed stats (-d), covering the L1 and last level data
+		 * caches:
+		 */
+		ret = parse_events(evlist,
+				"L1-dcache-loads,"
+				"L1-dcache-load-misses,"
+				"LLC-loads,"
+				"LLC-load-misses",
+				&err);
+	}
+	if (!ret && detailed_run >=  2) {
+		/*
+		 * Very detailed stats (-d -d), covering the instruction cache
+		 * and the TLB caches:
+		 */
+		ret = parse_events(evlist,
+				"L1-icache-loads,"
+				"L1-icache-load-misses,"
+				"dTLB-loads,"
+				"dTLB-load-misses,"
+				"iTLB-loads,"
+				"iTLB-load-misses",
+				&err);
+	}
+	if (!ret && detailed_run >=  3) {
+		/*
+		 * Very, very detailed stats (-d -d -d), adding prefetch events:
+		 */
+		ret = parse_events(evlist,
+				"L1-dcache-prefetches,"
+				"L1-dcache-prefetch-misses",
+				&err);
+	}
+out:
+	if (!ret) {
+		evlist__for_each_entry(evlist, evsel) {
+			/*
+			 * Make at least one event non-skippable so fatal errors are visible.
+			 * 'cycles' always used to be default and non-skippable, so use that.
+			 */
+			if (strcmp("cycles", evsel__name(evsel)))
+				evsel->skippable = true;
+		}
+	}
+	parse_events_error__exit(&err);
+	evlist__splice_list_tail(evsel_list, &evlist->core.entries);
+	evlist__delete(evlist);
+	return ret;
 }
 
 static const char * const stat_record_usage[] = {
@@ -2788,7 +2727,7 @@ int cmd_stat(int argc, const char **argv)
 		}
 	}
 
-	if (add_default_attributes())
+	if (add_default_events())
 		goto out;
 
 	if (stat_config.cgroup_list) {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a9df84692d4a8..7be0800b89d8d 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -320,49 +320,6 @@ struct evsel *evlist__add_sched_switch(struct evlist *evlist, bool system_wide)
 }
 #endif
 
-int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs)
-{
-	struct evsel *evsel, *n;
-	LIST_HEAD(head);
-	size_t i;
-
-	for (i = 0; i < nr_attrs; i++) {
-		evsel = evsel__new_idx(attrs + i, evlist->core.nr_entries + i);
-		if (evsel == NULL)
-			goto out_delete_partial_list;
-		list_add_tail(&evsel->core.node, &head);
-	}
-
-	evlist__splice_list_tail(evlist, &head);
-
-	return 0;
-
-out_delete_partial_list:
-	__evlist__for_each_entry_safe(&head, n, evsel)
-		evsel__delete(evsel);
-	return -1;
-}
-
-int __evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs)
-{
-	size_t i;
-
-	for (i = 0; i < nr_attrs; i++)
-		event_attr_init(attrs + i);
-
-	return evlist__add_attrs(evlist, attrs, nr_attrs);
-}
-
-__weak int arch_evlist__add_default_attrs(struct evlist *evlist,
-					  struct perf_event_attr *attrs,
-					  size_t nr_attrs)
-{
-	if (!nr_attrs)
-		return 0;
-
-	return __evlist__add_default_attrs(evlist, attrs, nr_attrs);
-}
-
 struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id)
 {
 	struct evsel *evsel;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 888fda751e1a6..cd80a470a4ba5 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -102,18 +102,6 @@ void evlist__delete(struct evlist *evlist);
 void evlist__add(struct evlist *evlist, struct evsel *entry);
 void evlist__remove(struct evlist *evlist, struct evsel *evsel);
 
-int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs);
-
-int __evlist__add_default_attrs(struct evlist *evlist,
-				     struct perf_event_attr *attrs, size_t nr_attrs);
-
-int arch_evlist__add_default_attrs(struct evlist *evlist,
-				   struct perf_event_attr *attrs,
-				   size_t nr_attrs);
-
-#define evlist__add_default_attrs(evlist, array) \
-	arch_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
-
 int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs);
 
 int evlist__add_dummy(struct evlist *evlist);
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index cbff43ff8d0fb..5402998881c44 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -7,6 +7,7 @@
 #include <perf/cpumap.h>
 #include "color.h"
 #include "counts.h"
+#include "debug.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "stat.h"
@@ -967,6 +968,13 @@ static bool should_skip_zero_counter(struct perf_stat_config *config,
 	struct perf_cpu cpu;
 	int idx;
 
+	/*
+	 * Skip unsupported default events when not verbose. (default events
+	 * are all marked 'skippable').
+	 */
+	if (verbose == 0 && counter->skippable && !counter->supported)
+		return true;
+
 	/*
 	 * Skip value 0 when enabling --per-thread globally,
 	 * otherwise it will have too many 0 output.
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 99376c12dd8ec..dd709a7315745 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -76,7 +76,7 @@ void perf_stat__reset_shadow_stats(void)
 	memset(&ru_stats, 0, sizeof(ru_stats));
 }
 
-static enum stat_type evsel__stat_type(const struct evsel *evsel)
+static enum stat_type evsel__stat_type(struct evsel *evsel)
 {
 	/* Fake perf_hw_cache_op_id values for use with evsel__match. */
 	u64 PERF_COUNT_hw_cache_l1d_miss = PERF_COUNT_HW_CACHE_L1D |
@@ -152,7 +152,7 @@ static const char *get_ratio_color(const double ratios[3], double val)
 
 static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type type)
 {
-	const struct evsel *cur;
+	struct evsel *cur;
 	int evsel_ctx = evsel_context(evsel);
 
 	evlist__for_each_entry(evsel->evlist, cur) {

From e2216fac1ee2bdfd7beab435ef1190a349cb3745 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 26 Sep 2024 15:48:35 +0100
Subject: [PATCH 0022/1530] perf evsel x86: Make evsel__has_perf_metrics work
 for legacy events

Use PMU interface to better detect core PMU for legacy events. Look
for slots event on core PMU if it is appropriate for the event.

Acked-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Dominique Martinet <asmadeus@codewreck.org>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Yunseong Kim <yskelg@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: ak@linux.intel.com
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Sun Haiyong <sunhaiyong@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20240926144851.245903-5-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/x86/util/evsel.c | 31 ++++++++++++++++++++++++++-----
 tools/perf/util/pmu.c            |  2 +-
 tools/perf/util/pmu.h            |  1 +
 3 files changed, 28 insertions(+), 6 deletions(-)

diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
index 090d0f371891f..ec2ac3bbb76f2 100644
--- a/tools/perf/arch/x86/util/evsel.c
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -21,7 +21,8 @@ void arch_evsel__set_sample_weight(struct evsel *evsel)
 /* Check whether the evsel's PMU supports the perf metrics */
 bool evsel__sys_has_perf_metrics(const struct evsel *evsel)
 {
-	const char *pmu_name = evsel->pmu_name ? evsel->pmu_name : "cpu";
+	struct perf_pmu *pmu;
+	u32 type = evsel->core.attr.type;
 
 	/*
 	 * The PERF_TYPE_RAW type is the core PMU type, e.g., "cpu" PMU
@@ -31,11 +32,31 @@ bool evsel__sys_has_perf_metrics(const struct evsel *evsel)
 	 * Checking both the PERF_TYPE_RAW type and the slots event
 	 * should be good enough to detect the perf metrics feature.
 	 */
-	if ((evsel->core.attr.type == PERF_TYPE_RAW) &&
-	    perf_pmus__have_event(pmu_name, "slots"))
-		return true;
+again:
+	switch (type) {
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		type = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT;
+		if (type)
+			goto again;
+		break;
+	case PERF_TYPE_RAW:
+		break;
+	default:
+		return false;
+	}
+
+	pmu = evsel->pmu;
+	if (pmu && perf_pmu__is_fake(pmu))
+		pmu = NULL;
 
-	return false;
+	if (!pmu) {
+		while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
+			if (pmu->type == PERF_TYPE_RAW)
+				break;
+		}
+	}
+	return pmu && perf_pmu__have_event(pmu, "slots");
 }
 
 bool arch_evsel__must_be_in_group(const struct evsel *evsel)
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index e32d601b48f1e..8993b5853687b 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1168,7 +1168,7 @@ struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pm
 	return pmu;
 }
 
-static bool perf_pmu__is_fake(const struct perf_pmu *pmu)
+bool perf_pmu__is_fake(const struct perf_pmu *pmu)
 {
 	return pmu->type == PERF_PMU_TYPE_FAKE;
 }
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index f4271395c3744..d352d53b8d55c 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -281,5 +281,6 @@ struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pm
 void perf_pmu__delete(struct perf_pmu *pmu);
 struct perf_pmu *perf_pmus__find_core_pmu(void);
 const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config);
+bool perf_pmu__is_fake(const struct perf_pmu *pmu);
 
 #endif /* __PMU_H */

From d7d156fc5e40cce21404579b0080dfc51399507b Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 26 Sep 2024 15:48:36 +0100
Subject: [PATCH 0023/1530] perf evsel: Remove pmu_name

"evsel->pmu_name" is only ever assigned a strdup of "pmu->name", a
strdup of "evsel->pmu_name" or NULL. As such, prefer to use
"pmu->name" directly and even to directly compare PMUs than PMU
names. For safety, add some additional NULL tests.

Acked-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
[ Fix arm-spe.c usage of pmu_name and empty PMU name ]
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Dominique Martinet <asmadeus@codewreck.org>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: ak@linux.intel.com
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Sun Haiyong <sunhaiyong@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20240926144851.245903-6-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/arm64/util/arm-spe.c |  4 ++--
 tools/perf/arch/x86/util/evsel.c     |  4 ++--
 tools/perf/tests/parse-events.c      |  2 +-
 tools/perf/util/evlist.c             |  3 ++-
 tools/perf/util/evsel.c              |  7 -------
 tools/perf/util/evsel.h              |  3 +--
 tools/perf/util/metricgroup.c        |  4 ++--
 tools/perf/util/parse-events.c       |  1 -
 tools/perf/util/stat-shadow.c        | 10 +++++-----
 tools/perf/util/stat.c               |  2 +-
 10 files changed, 16 insertions(+), 24 deletions(-)

diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 2be99fdf997db..59a85e6f3aa34 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -188,9 +188,9 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 
 	evlist__for_each_entry(evlist, evsel) {
 		if (evsel__is_aux_event(evsel)) {
-			if (!strstarts(evsel->pmu_name, ARM_SPE_PMU_NAME)) {
+			if (!strstarts(evsel->pmu->name, ARM_SPE_PMU_NAME)) {
 				pr_err("Found unexpected auxtrace event: %s\n",
-				       evsel->pmu_name);
+				       evsel->pmu->name);
 				return -EINVAL;
 			}
 			opts->full_auxtrace = true;
diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
index ec2ac3bbb76f2..cf7c116eeb8e4 100644
--- a/tools/perf/arch/x86/util/evsel.c
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -84,7 +84,7 @@ int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
 		return  scnprintf(bf, size, "%s", event_name);
 
 	return scnprintf(bf, size, "%s/%s/",
-			 evsel->pmu_name ? evsel->pmu_name : "cpu",
+			 evsel->pmu ? evsel->pmu->name : "cpu",
 			 event_name);
 }
 
@@ -129,7 +129,7 @@ int arch_evsel__open_strerror(struct evsel *evsel, char *msg, size_t size)
 		return 0;
 
 	if (!evsel->core.attr.precise_ip &&
-	    !(evsel->pmu_name && !strncmp(evsel->pmu_name, "ibs", 3)))
+	    !(evsel->pmu && !strncmp(evsel->pmu->name, "ibs", 3)))
 		return 0;
 
 	/* More verbose IBS errors. */
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 9e3086d021508..78e999f03d2d7 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -730,7 +730,7 @@ static int test__checkevent_pmu_events(struct evlist *evlist)
 
 	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type ||
-				      strcmp(evsel->pmu_name, "cpu"));
+				      strcmp(evsel->pmu->name, "cpu"));
 	TEST_ASSERT_VAL("wrong exclude_user",
 			!evsel->core.attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel",
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 7be0800b89d8d..37d0fc01c1800 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -2591,7 +2591,8 @@ void evlist__uniquify_name(struct evlist *evlist)
 		else
 			attributes = empty_attributes;
 
-		if (asprintf(&new_name, "%s/%s/%s", pos->pmu_name, pos->name, attributes + 1)) {
+		if (asprintf(&new_name, "%s/%s/%s", pos->pmu ? pos->pmu->name : "",
+			     pos->name, attributes + 1)) {
 			free(pos->name);
 			pos->name = new_name;
 		} else {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index b9d7b56dfc5e9..edfb376f06119 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -296,7 +296,6 @@ void evsel__init(struct evsel *evsel,
 	evsel->metric_events = NULL;
 	evsel->per_pkg_mask  = NULL;
 	evsel->collect_stat  = false;
-	evsel->pmu_name      = NULL;
 	evsel->group_pmu_name = NULL;
 	evsel->skippable     = false;
 	evsel->alternate_hw_config = PERF_COUNT_HW_MAX;
@@ -394,11 +393,6 @@ struct evsel *evsel__clone(struct evsel *orig)
 		if (evsel->group_name == NULL)
 			goto out_err;
 	}
-	if (orig->pmu_name) {
-		evsel->pmu_name = strdup(orig->pmu_name);
-		if (evsel->pmu_name == NULL)
-			goto out_err;
-	}
 	if (orig->group_pmu_name) {
 		evsel->group_pmu_name = strdup(orig->group_pmu_name);
 		if (evsel->group_pmu_name == NULL)
@@ -1497,7 +1491,6 @@ void evsel__exit(struct evsel *evsel)
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
 	zfree(&evsel->filter);
-	zfree(&evsel->pmu_name);
 	zfree(&evsel->group_pmu_name);
 	zfree(&evsel->unit);
 	zfree(&evsel->metric_id);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index cf6f11fdfd061..3e751ea769ac4 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -72,7 +72,6 @@ struct evsel {
 	struct {
 		char			*name;
 		char			*group_name;
-		const char		*pmu_name;
 		const char		*group_pmu_name;
 #ifdef HAVE_LIBTRACEEVENT
 		struct tep_event	*tp_format;
@@ -184,7 +183,7 @@ struct evsel {
 	unsigned long		open_flags;
 	int			precise_ip_original;
 
-	/* for missing_features */
+	/* The PMU the event is from. Used for missing_features, PMU name, etc. */
 	struct perf_pmu		*pmu;
 
 	/* For tool events */
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 4dff3e925a47b..9c6fa6b4f628c 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -297,8 +297,8 @@ static int setup_metric_events(const char *pmu, struct hashmap *ids,
 		struct expr_id_data *val_ptr;
 
 		/* Don't match events for the wrong hybrid PMU. */
-		if (!all_pmus && ev->pmu_name && evsel__is_hybrid(ev) &&
-		    strcmp(ev->pmu_name, pmu))
+		if (!all_pmus && ev->pmu && evsel__is_hybrid(ev) &&
+		    strcmp(ev->pmu->name, pmu))
 			continue;
 		/*
 		 * Check for duplicate events with the same name. For
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index fcc4dab618bee..e96cf13dc3961 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -263,7 +263,6 @@ __add_event(struct list_head *list, int *idx,
 	evsel->core.is_pmu_core = pmu ? pmu->is_core : false;
 	evsel->auto_merge_stats = auto_merge_stats;
 	evsel->pmu = pmu;
-	evsel->pmu_name = pmu ? strdup(pmu->name) : NULL;
 	evsel->alternate_hw_config = alternate_hw_config;
 
 	if (name)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index dd709a7315745..3ce756b8ede50 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -573,7 +573,7 @@ static void perf_stat__print_metricgroup_header(struct perf_stat_config *config,
 {
 	bool need_full_name = perf_pmus__num_core_pmus() > 1;
 	static const char *last_name;
-	static const char *last_pmu;
+	static const struct perf_pmu *last_pmu;
 	char full_name[64];
 
 	/*
@@ -584,21 +584,21 @@ static void perf_stat__print_metricgroup_header(struct perf_stat_config *config,
 	 * different metric events.
 	 */
 	if (last_name && !strcmp(last_name, name)) {
-		if (!need_full_name || !strcmp(last_pmu, evsel->pmu_name)) {
+		if (!need_full_name || last_pmu != evsel->pmu) {
 			out->print_metricgroup_header(config, ctxp, NULL);
 			return;
 		}
 	}
 
-	if (need_full_name)
-		scnprintf(full_name, sizeof(full_name), "%s (%s)", name, evsel->pmu_name);
+	if (need_full_name && evsel->pmu)
+		scnprintf(full_name, sizeof(full_name), "%s (%s)", name, evsel->pmu->name);
 	else
 		scnprintf(full_name, sizeof(full_name), "%s", name);
 
 	out->print_metricgroup_header(config, ctxp, full_name);
 
 	last_name = name;
-	last_pmu = evsel->pmu_name;
+	last_pmu = evsel->pmu;
 }
 
 /**
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 0bd5467389e46..7c2ccdcc3fdba 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -553,7 +553,7 @@ static bool evsel__is_alias(struct evsel *evsel_a, struct evsel *evsel_b)
 	if (evsel__is_clock(evsel_a) != evsel__is_clock(evsel_b))
 		return false;
 
-	return !!strcmp(evsel_a->pmu_name, evsel_b->pmu_name);
+	return evsel_a->pmu != evsel_b->pmu;
 }
 
 static void evsel__merge_aliases(struct evsel *evsel)

From 14b6b269f42a8fecc426ee940764251e621d943d Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Thu, 26 Sep 2024 15:48:37 +0100
Subject: [PATCH 0024/1530] perf test: Make stat test work on DT devices

PMUs aren't listed in /sys/devices/ on DT devices, so change the search
directory to /sys/bus/event_source/devices which works everywhere. Also
add armv8_cortex_* as a known PMU type to search for to make the test
run on more devices.

Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Dominique Martinet <asmadeus@codewreck.org>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Yunseong Kim <yskelg@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: ak@linux.intel.com
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Sun Haiyong <sunhaiyong@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20240926144851.245903-7-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/stat.sh | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh
index 3f1e67795490a..525d0c44fdc63 100755
--- a/tools/perf/tests/shell/stat.sh
+++ b/tools/perf/tests/shell/stat.sh
@@ -117,16 +117,18 @@ test_cputype() {
 
   # Find a known PMU for cputype.
   pmu=""
-  for i in cpu cpu_atom armv8_pmuv3_0
+  devs="/sys/bus/event_source/devices"
+  for i in $devs/cpu $devs/cpu_atom $devs/armv8_pmuv3_0 $devs/armv8_cortex_*
   do
-    if test -d "/sys/devices/$i"
+    i_base=$(basename "$i")
+    if test -d "$i"
     then
-      pmu="$i"
+      pmu="$i_base"
       break
     fi
-    if perf stat -e "$i/instructions/" true > /dev/null 2>&1
+    if perf stat -e "$i_base/instructions/" true > /dev/null 2>&1
     then
-      pmu="$i"
+      pmu="$i_base"
       break
     fi
   done

From 65d11821910bd910a2b4b5b005360d036c76ecef Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Thu, 26 Sep 2024 15:48:38 +0100
Subject: [PATCH 0025/1530] perf test: Add a test for default perf stat command

Test that one cycles event is opened for each core PMU when "perf stat"
is run without arguments.

The event line can either be output as "pmu/cycles/" or just "cycles" if
there is only one PMU. Include 2 spaces for padding in the one PMU case
to avoid matching when the word cycles is included in metric
descriptions.

Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Dominique Martinet <asmadeus@codewreck.org>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: ak@linux.intel.com
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Yanteng Si <siyanteng@loongson.cn>
Cc: Sun Haiyong <sunhaiyong@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20240926144851.245903-8-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/stat.sh | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh
index 525d0c44fdc63..5a2ca2bcf94d1 100755
--- a/tools/perf/tests/shell/stat.sh
+++ b/tools/perf/tests/shell/stat.sh
@@ -148,6 +148,30 @@ test_cputype() {
   echo "cputype test [Success]"
 }
 
+test_hybrid() {
+  # Test the default stat command on hybrid devices opens one cycles event for
+  # each CPU type.
+  echo "hybrid test"
+
+  # Count the number of core PMUs, assume minimum of 1
+  pmus=$(ls /sys/bus/event_source/devices/*/cpus 2>/dev/null | wc -l)
+  if [ "$pmus" -lt 1 ]
+  then
+    pmus=1
+  fi
+
+  # Run default Perf stat
+  cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/|  cycles  " | wc -l)
+
+  if [ "$pmus" -ne "$cycles_events" ]
+  then
+    echo "hybrid test [Found $pmus PMUs but $cycles_events cycles events. Failed]"
+    err=1
+    return
+  fi
+  echo "hybrid test [Success]"
+}
+
 test_default_stat
 test_stat_record_report
 test_stat_record_script
@@ -155,4 +179,5 @@ test_stat_repeat_weak_groups
 test_topdown_groups
 test_topdown_weak_groups
 test_cputype
+test_hybrid
 exit $err

From 6490dda55dcabbd5cf408387f932c9343a22c872 Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Sun, 15 Sep 2024 10:34:29 +0900
Subject: [PATCH 0026/1530] libperf: Explicitly specify install-html
 dependencies

install_doc of tools/lib/perf/Makefile invokes install-man,
install-html, and install-examples of
tools/lib/perf/Documentation/Makefile at once. This invocation succeeds
when make runs in serial but can fail when make runs in parallel because
while install-man of tools/lib/perf/Documentation/Makefile depends on
all, install-html depends on nothing and can run ahead of all.

Explicitly specify the dependencies of install-html to ensure that
they are resolved before install-html.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Link: https://lore.kernel.org/r/20240915-perf-v1-1-cbfd9cd1d482@daynix.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/lib/perf/Documentation/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/perf/Documentation/Makefile b/tools/lib/perf/Documentation/Makefile
index 972754082a854..573ca5b275567 100644
--- a/tools/lib/perf/Documentation/Makefile
+++ b/tools/lib/perf/Documentation/Makefile
@@ -121,7 +121,7 @@ install-man: all
 		$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir); \
 		$(INSTALL) -m 644 $(MAN_7) $(DESTDIR)$(man7dir);
 
-install-html:
+install-html: $(MAN_HTML)
 	$(call QUIET_INSTALL, html) \
 		$(INSTALL) -d -m 755 $(DESTDIR)$(htmldir); \
 		$(INSTALL) -m 644 $(MAN_HTML) $(DESTDIR)$(htmldir); \

From 6adeb277fea06eeed3e9658a2e72573ac70fd011 Mon Sep 17 00:00:00 2001
From: Madadi Vineeth Reddy <vineethr@linux.ibm.com>
Date: Tue, 17 Sep 2024 14:31:00 +0530
Subject: [PATCH 0027/1530] perf sched replay: Remove unused parts of the code

The sleep_sem semaphore and the specific_wait field (member of sched_atom)
are initialized but not used anywhere in the code, so this patch removes
them.

The SCHED_EVENT_MIGRATION case in perf_sched__process_event() is currently
not used and is also removed.

Additionally, prev_state in add_sched_event_sleep() is marked with
__maybe_unused and is not utilized anywhere in the function. This patch
removes the parameter.

If the task_state parameter was intended for future use, it can be
reintroduced when needed.

No functionality change intended.

Signed-off-by: Madadi Vineeth Reddy <vineethr@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20240917090100.42783-1-vineethr@linux.ibm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-sched.c | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 5981cc51abc88..fdf979aaf2758 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -68,7 +68,6 @@ struct task_desc {
 	struct sched_atom	**atoms;
 
 	pthread_t		thread;
-	sem_t			sleep_sem;
 
 	sem_t			ready_for_work;
 	sem_t			work_done_sem;
@@ -80,12 +79,10 @@ enum sched_event_type {
 	SCHED_EVENT_RUN,
 	SCHED_EVENT_SLEEP,
 	SCHED_EVENT_WAKEUP,
-	SCHED_EVENT_MIGRATION,
 };
 
 struct sched_atom {
 	enum sched_event_type	type;
-	int			specific_wait;
 	u64			timestamp;
 	u64			duration;
 	unsigned long		nr;
@@ -421,14 +418,13 @@ static void add_sched_event_wakeup(struct perf_sched *sched, struct task_desc *t
 
 	wakee_event->wait_sem = zalloc(sizeof(*wakee_event->wait_sem));
 	sem_init(wakee_event->wait_sem, 0, 0);
-	wakee_event->specific_wait = 1;
 	event->wait_sem = wakee_event->wait_sem;
 
 	sched->nr_wakeup_events++;
 }
 
 static void add_sched_event_sleep(struct perf_sched *sched, struct task_desc *task,
-				  u64 timestamp, const char task_state __maybe_unused)
+				  u64 timestamp)
 {
 	struct sched_atom *event = get_new_event(task, timestamp);
 
@@ -468,7 +464,7 @@ static struct task_desc *register_pid(struct perf_sched *sched,
 	 * every task starts in sleeping state - this gets ignored
 	 * if there's no wakeup pointing to this sleep state:
 	 */
-	add_sched_event_sleep(sched, task, 0, 0);
+	add_sched_event_sleep(sched, task, 0);
 
 	sched->pid_to_task[pid] = task;
 	sched->nr_tasks++;
@@ -529,8 +525,6 @@ static void perf_sched__process_event(struct perf_sched *sched,
 				ret = sem_post(atom->wait_sem);
 			BUG_ON(ret);
 			break;
-		case SCHED_EVENT_MIGRATION:
-			break;
 		default:
 			BUG_ON(1);
 	}
@@ -673,7 +667,6 @@ static void create_tasks(struct perf_sched *sched)
 		parms->task = task = sched->tasks[i];
 		parms->sched = sched;
 		parms->fd = self_open_counters(sched, i);
-		sem_init(&task->sleep_sem, 0, 0);
 		sem_init(&task->ready_for_work, 0, 0);
 		sem_init(&task->work_done_sem, 0, 0);
 		task->curr_event = 0;
@@ -697,7 +690,6 @@ static void destroy_tasks(struct perf_sched *sched)
 		task = sched->tasks[i];
 		err = pthread_join(task->thread, NULL);
 		BUG_ON(err);
-		sem_destroy(&task->sleep_sem);
 		sem_destroy(&task->ready_for_work);
 		sem_destroy(&task->work_done_sem);
 	}
@@ -751,7 +743,6 @@ static void wait_for_tasks(struct perf_sched *sched)
 
 	for (i = 0; i < sched->nr_tasks; i++) {
 		task = sched->tasks[i];
-		sem_init(&task->sleep_sem, 0, 0);
 		task->curr_event = 0;
 	}
 }
@@ -852,7 +843,6 @@ static int replay_switch_event(struct perf_sched *sched,
 		   *next_comm  = evsel__strval(evsel, sample, "next_comm");
 	const u32 prev_pid = evsel__intval(evsel, sample, "prev_pid"),
 		  next_pid = evsel__intval(evsel, sample, "next_pid");
-	const char prev_state = evsel__taskstate(evsel, sample, "prev_state");
 	struct task_desc *prev, __maybe_unused *next;
 	u64 timestamp0, timestamp = sample->time;
 	int cpu = sample->cpu;
@@ -884,7 +874,7 @@ static int replay_switch_event(struct perf_sched *sched,
 	sched->cpu_last_switched[cpu] = timestamp;
 
 	add_sched_event_run(sched, prev, timestamp, delta);
-	add_sched_event_sleep(sched, prev, timestamp, prev_state);
+	add_sched_event_sleep(sched, prev, timestamp);
 
 	return 0;
 }

From 4f23fc34cc68812c68c3a3dec15e26e87565f430 Mon Sep 17 00:00:00 2001
From: Thomas Falcon <thomas.falcon@intel.com>
Date: Thu, 26 Sep 2024 09:40:40 -0500
Subject: [PATCH 0028/1530] perf mem: Fix printing PERF_MEM_LVLNUM_{L2_MHB|MSC}

With commit 8ec9497d3ef34 ("tools/include: Sync uapi/linux/perf.h
with the kernel sources"), 'perf mem report' gives an incorrect memory
access string.
...
0.02%	1	3644	L5 hit	[.] 0x0000000000009b0e	mlc	[.] 0x00007fce43f59480
...

This occurs because, if no entry exists in mem_lvlnum, perf_mem__lvl_scnprintf
will default to 'L%d, lvl', which in this case for PERF_MEM_LVLNUM_L2_MHB is 0x05.
Add entries for PERF_MEM_LVLNUM_L2_MHB and PERF_MEM_LVLNUM_MSC to mem_lvlnum,
so that the correct strings are printed.
...
0.02%	1	3644	L2 MHB hit	[.] 0x0000000000009b0e	mlc	[.] 0x00007fce43f59480
...

Fixes: 8ec9497d3ef34 ("tools/include: Sync uapi/linux/perf.h with the kernel sources")
Suggested-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Thomas Falcon <thomas.falcon@intel.com>
Reviewed-by: Leo Yan <leo.yan@arm.com>
Link: https://lore.kernel.org/r/20240926144040.77897-1-thomas.falcon@intel.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/mem-events.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 051feb93ed8d4..bf5090f5220bb 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -366,6 +366,12 @@ static const char * const mem_lvl[] = {
 };
 
 static const char * const mem_lvlnum[] = {
+	[PERF_MEM_LVLNUM_L1] = "L1",
+	[PERF_MEM_LVLNUM_L2] = "L2",
+	[PERF_MEM_LVLNUM_L3] = "L3",
+	[PERF_MEM_LVLNUM_L4] = "L4",
+	[PERF_MEM_LVLNUM_L2_MHB] = "L2 MHB",
+	[PERF_MEM_LVLNUM_MSC] = "Memory-side Cache",
 	[PERF_MEM_LVLNUM_UNC] = "Uncached",
 	[PERF_MEM_LVLNUM_CXL] = "CXL",
 	[PERF_MEM_LVLNUM_IO] = "I/O",
@@ -448,7 +454,7 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, const struct mem_info *mem_inf
 		if (mem_lvlnum[lvl])
 			l += scnprintf(out + l, sz - l, mem_lvlnum[lvl]);
 		else
-			l += scnprintf(out + l, sz - l, "L%d", lvl);
+			l += scnprintf(out + l, sz - l, "Unknown level %d", lvl);
 
 		l += scnprintf(out + l, sz - l, " %s", hit_miss);
 		return l;

From b38c49d8296b9eee1ffb6471853d542fd76de2fb Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 17 Sep 2024 10:57:06 +0200
Subject: [PATCH 0029/1530] perf/test: Speed up test case perf annotate basic
 tests

perf test 70 takes a long time. One culprit is the output of command
perf annotate. Per default enabled are
 - demangle symbol names
 - interleave source code with assembly code.
Disable demangle of symbols and abort the annotation
after the first 250 lines.

This speeds up the test case considerable, for example
on s390:

Output before:
 # time  perf test 70
 70: perf annotate basic tests             : Ok
 .....
 real   2m7.467s
 user   1m26.869s
 sys    0m34.086s
 #

 Output after:
 # time perf test 70
 70: perf annotate basic tests             : Ok

 real   0m3.341s
 user   0m1.606s
 sys    0m0.362s
 #

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: sumanthk@linux.ibm.com
Link: https://lore.kernel.org/r/20240917085706.249691-1-tmricht@linux.ibm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/annotate.sh | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/perf/tests/shell/annotate.sh b/tools/perf/tests/shell/annotate.sh
index 2ccf4f1d46b60..1590a37363deb 100755
--- a/tools/perf/tests/shell/annotate.sh
+++ b/tools/perf/tests/shell/annotate.sh
@@ -44,7 +44,7 @@ test_basic() {
   fi
 
   # Generate the annotated output file
-  perf annotate -i "${perfdata}" --stdio 2> /dev/null > "${perfout}"
+  perf annotate --no-demangle -i "${perfdata}" --stdio 2> /dev/null | head -250 > "${perfout}"
 
   # check if it has the target symbol
   if ! grep "${testsym}" "${perfout}"
@@ -63,8 +63,8 @@ test_basic() {
   fi
 
   # check again with a target symbol name
-  if ! perf annotate -i "${perfdata}" "${testsym}" 2> /dev/null | \
-	  grep -m 3 "${disasm_regex}"
+  if ! perf annotate --no-demangle -i "${perfdata}" "${testsym}" 2> /dev/null | \
+	  head -250 | grep -m 3 "${disasm_regex}"
   then
     echo "Basic annotate [Failed: missing disasm output when specifying the target symbol]"
     err=1
@@ -72,8 +72,8 @@ test_basic() {
   fi
 
   # check one more with external objdump tool (forced by --objdump option)
-  if ! perf annotate -i "${perfdata}" --objdump=objdump 2> /dev/null | \
-	  grep -m 3 "${disasm_regex}"
+  if ! perf annotate --no-demangle -i "${perfdata}" --objdump=objdump 2> /dev/null | \
+	  head -250 | grep -m 3 "${disasm_regex}"
   then
     echo "Basic annotate [Failed: missing disasm output from non default disassembler (using --objdump)]"
     err=1

From c12fbeb200c137e83565c37b907c5f92c6f5b98c Mon Sep 17 00:00:00 2001
From: Joel Selvaraj <joelselvaraj.oss@gmail.com>
Date: Sat, 1 Jun 2024 15:44:43 -0500
Subject: [PATCH 0030/1530] Input: novatek-nvt-ts - replace generic i2c device
 id with specific IC variant

This is done in preparation to introduce other variants of the Novatek NVT
touchscreen controller that can be supported by the driver.

Signed-off-by: Joel Selvaraj <joelselvaraj.oss@gmail.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240601-nvt-ts-devicetree-regulator-support-v5-1-aa9bf986347d@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/novatek-nvt-ts.c       | 2 +-
 drivers/platform/x86/x86-android-tablets/other.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/touchscreen/novatek-nvt-ts.c b/drivers/input/touchscreen/novatek-nvt-ts.c
index 1a797e410a3fa..9bee3a0c122fb 100644
--- a/drivers/input/touchscreen/novatek-nvt-ts.c
+++ b/drivers/input/touchscreen/novatek-nvt-ts.c
@@ -278,7 +278,7 @@ static int nvt_ts_probe(struct i2c_client *client)
 }
 
 static const struct i2c_device_id nvt_ts_i2c_id[] = {
-	{ "NVT-ts" },
+	{ "nt11205-ts" },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, nvt_ts_i2c_id);
diff --git a/drivers/platform/x86/x86-android-tablets/other.c b/drivers/platform/x86/x86-android-tablets/other.c
index eb0e55c69dfed..129273df0fdeb 100644
--- a/drivers/platform/x86/x86-android-tablets/other.c
+++ b/drivers/platform/x86/x86-android-tablets/other.c
@@ -40,7 +40,7 @@ static const struct x86_i2c_client_info acer_b1_750_i2c_clients[] __initconst =
 	{
 		/* Novatek NVT-ts touchscreen */
 		.board_info = {
-			.type = "NVT-ts",
+			.type = "nt11205-ts",
 			.addr = 0x34,
 			.dev_name = "NVT-ts",
 		},

From 285fe9b5a34ea48e7db87870a503a5f67e9e582d Mon Sep 17 00:00:00 2001
From: Joel Selvaraj <joelselvaraj.oss@gmail.com>
Date: Sat, 1 Jun 2024 15:44:44 -0500
Subject: [PATCH 0031/1530] dt-bindings: input: document Novatek NVT
 touchscreen controller

Document the Novatek NVT touchscreen controller present in devices like
qcom/sdm845-xiaomi-beryllium-tianma.dts. Also, include the devictree
binding file in the MAINTAINERS file.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Joel Selvaraj <joelselvaraj.oss@gmail.com>
Link: https://lore.kernel.org/r/20240601-nvt-ts-devicetree-regulator-support-v5-2-aa9bf986347d@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../input/touchscreen/novatek,nvt-ts.yaml     | 62 +++++++++++++++++++
 MAINTAINERS                                   |  1 +
 2 files changed, 63 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/input/touchscreen/novatek,nvt-ts.yaml

diff --git a/Documentation/devicetree/bindings/input/touchscreen/novatek,nvt-ts.yaml b/Documentation/devicetree/bindings/input/touchscreen/novatek,nvt-ts.yaml
new file mode 100644
index 0000000000000..bd6a60486d1f1
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/novatek,nvt-ts.yaml
@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/touchscreen/novatek,nvt-ts.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Novatek NVT Touchscreen Controller
+
+maintainers:
+  - Hans de Goede <hdegoede@redhat.com>
+
+allOf:
+  - $ref: touchscreen.yaml#
+
+properties:
+  compatible:
+    enum:
+      - novatek,nt11205-ts
+      - novatek,nt36672a-ts
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  reset-gpios:
+    maxItems: 1
+
+  vcc-supply: true
+  iovcc-supply: true
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        touchscreen@1 {
+            compatible = "novatek,nt36672a-ts";
+            reg = <0x01>;
+            interrupts-extended = <&tlmm 31 IRQ_TYPE_EDGE_RISING>;
+            reset-gpios = <&tlmm 32 GPIO_ACTIVE_LOW>;
+            vcc-supply = <&vreg_l22a_2p85>;
+            iovcc-supply = <&vreg_l14a_1p8>;
+            pinctrl-0 = <&ts_int_default &ts_reset_default>;
+            pinctrl-1 = <&ts_int_sleep &ts_reset_sleep>;
+            pinctrl-names = "default", "sleep";
+            touchscreen-size-x = <1080>;
+            touchscreen-size-y = <2246>;
+        };
+    };
+
+...
diff --git a/MAINTAINERS b/MAINTAINERS
index 45f3960b27a37..a533d882b0022 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16260,6 +16260,7 @@ NOVATEK NVT-TS I2C TOUCHSCREEN DRIVER
 M:	Hans de Goede <hdegoede@redhat.com>
 L:	linux-input@vger.kernel.org
 S:	Maintained
+F:	Documentation/devicetree/bindings/input/touchscreen/novatek,nvt-ts.yaml
 F:	drivers/input/touchscreen/novatek-nvt-ts.c
 
 NSDEPS

From c7bf046925dc5885d9c4d8fbcbb7e4e73665bfcf Mon Sep 17 00:00:00 2001
From: Joel Selvaraj <joelselvaraj.oss@gmail.com>
Date: Sat, 1 Jun 2024 15:44:45 -0500
Subject: [PATCH 0032/1530] Input: novatek-nvt-ts - add support for NT36672A
 touchscreen

Extend the novatek touchscreen driver to support NT36672A chip which
is found in phones like qcom/sdm845-xiaomi-beryllium-tianma.dts.
Added devicetree support for the driver and used i2c chip data to handle
the variation in chip id and wake type. Also added vcc and iovcc
regulators which are used to power the touchscreen hardware.

Signed-off-by: Joel Selvaraj <joelselvaraj.oss@gmail.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240601-nvt-ts-devicetree-regulator-support-v5-3-aa9bf986347d@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/novatek-nvt-ts.c | 67 ++++++++++++++++++++--
 1 file changed, 61 insertions(+), 6 deletions(-)

diff --git a/drivers/input/touchscreen/novatek-nvt-ts.c b/drivers/input/touchscreen/novatek-nvt-ts.c
index 9bee3a0c122fb..b9ff97bf4d880 100644
--- a/drivers/input/touchscreen/novatek-nvt-ts.c
+++ b/drivers/input/touchscreen/novatek-nvt-ts.c
@@ -31,9 +31,6 @@
 #define NVT_TS_PARAMS_CHIP_ID		0x0e
 #define NVT_TS_PARAMS_SIZE		0x0f
 
-#define NVT_TS_SUPPORTED_WAKE_TYPE	0x05
-#define NVT_TS_SUPPORTED_CHIP_ID	0x05
-
 #define NVT_TS_MAX_TOUCHES		10
 #define NVT_TS_MAX_SIZE			4096
 
@@ -51,10 +48,16 @@ static const int nvt_ts_irq_type[4] = {
 	IRQF_TRIGGER_HIGH
 };
 
+struct nvt_ts_i2c_chip_data {
+	u8 wake_type;
+	u8 chip_id;
+};
+
 struct nvt_ts_data {
 	struct i2c_client *client;
 	struct input_dev *input;
 	struct gpio_desc *reset_gpio;
+	struct regulator_bulk_data regulators[2];
 	struct touchscreen_properties prop;
 	int max_touches;
 	u8 buf[NVT_TS_TOUCH_SIZE * NVT_TS_MAX_TOUCHES];
@@ -142,6 +145,13 @@ static irqreturn_t nvt_ts_irq(int irq, void *dev_id)
 static int nvt_ts_start(struct input_dev *dev)
 {
 	struct nvt_ts_data *data = input_get_drvdata(dev);
+	int error;
+
+	error = regulator_bulk_enable(ARRAY_SIZE(data->regulators), data->regulators);
+	if (error) {
+		dev_err(&data->client->dev, "failed to enable regulators\n");
+		return error;
+	}
 
 	enable_irq(data->client->irq);
 	gpiod_set_value_cansleep(data->reset_gpio, 0);
@@ -155,6 +165,7 @@ static void nvt_ts_stop(struct input_dev *dev)
 
 	disable_irq(data->client->irq);
 	gpiod_set_value_cansleep(data->reset_gpio, 1);
+	regulator_bulk_disable(ARRAY_SIZE(data->regulators), data->regulators);
 }
 
 static int nvt_ts_suspend(struct device *dev)
@@ -188,6 +199,7 @@ static int nvt_ts_probe(struct i2c_client *client)
 	struct device *dev = &client->dev;
 	int error, width, height, irq_type;
 	struct nvt_ts_data *data;
+	const struct nvt_ts_i2c_chip_data *chip;
 	struct input_dev *input;
 
 	if (!client->irq) {
@@ -199,12 +211,35 @@ static int nvt_ts_probe(struct i2c_client *client)
 	if (!data)
 		return -ENOMEM;
 
+	chip = device_get_match_data(&client->dev);
+	if (!chip)
+		return -EINVAL;
+
 	data->client = client;
 	i2c_set_clientdata(client, data);
 
+	/*
+	 * VCC is the analog voltage supply
+	 * IOVCC is the digital voltage supply
+	 */
+	data->regulators[0].supply = "vcc";
+	data->regulators[1].supply = "iovcc";
+	error = devm_regulator_bulk_get(dev, ARRAY_SIZE(data->regulators), data->regulators);
+	if (error) {
+		dev_err(dev, "cannot get regulators: %d\n", error);
+		return error;
+	}
+
+	error = regulator_bulk_enable(ARRAY_SIZE(data->regulators), data->regulators);
+	if (error) {
+		dev_err(dev, "failed to enable regulators: %d\n", error);
+		return error;
+	}
+
 	data->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
 	error = PTR_ERR_OR_ZERO(data->reset_gpio);
 	if (error) {
+		regulator_bulk_disable(ARRAY_SIZE(data->regulators), data->regulators);
 		dev_err(dev, "failed to request reset GPIO: %d\n", error);
 		return error;
 	}
@@ -214,6 +249,7 @@ static int nvt_ts_probe(struct i2c_client *client)
 	error = nvt_ts_read_data(data->client, NVT_TS_PARAMETERS_START,
 				 data->buf, NVT_TS_PARAMS_SIZE);
 	gpiod_set_value_cansleep(data->reset_gpio, 1); /* Put back in reset */
+	regulator_bulk_disable(ARRAY_SIZE(data->regulators), data->regulators);
 	if (error)
 		return error;
 
@@ -225,8 +261,8 @@ static int nvt_ts_probe(struct i2c_client *client)
 	if (width > NVT_TS_MAX_SIZE || height >= NVT_TS_MAX_SIZE ||
 	    data->max_touches > NVT_TS_MAX_TOUCHES ||
 	    irq_type >= ARRAY_SIZE(nvt_ts_irq_type) ||
-	    data->buf[NVT_TS_PARAMS_WAKE_TYPE] != NVT_TS_SUPPORTED_WAKE_TYPE ||
-	    data->buf[NVT_TS_PARAMS_CHIP_ID] != NVT_TS_SUPPORTED_CHIP_ID) {
+	    data->buf[NVT_TS_PARAMS_WAKE_TYPE] != chip->wake_type ||
+	    data->buf[NVT_TS_PARAMS_CHIP_ID] != chip->chip_id) {
 		dev_err(dev, "Unsupported touchscreen parameters: %*ph\n",
 			NVT_TS_PARAMS_SIZE, data->buf);
 		return -EIO;
@@ -277,8 +313,26 @@ static int nvt_ts_probe(struct i2c_client *client)
 	return 0;
 }
 
+static const struct nvt_ts_i2c_chip_data nvt_nt11205_ts_data = {
+	.wake_type = 0x05,
+	.chip_id = 0x05,
+};
+
+static const struct nvt_ts_i2c_chip_data nvt_nt36672a_ts_data = {
+	.wake_type = 0x01,
+	.chip_id = 0x08,
+};
+
+static const struct of_device_id nvt_ts_of_match[] = {
+	{ .compatible = "novatek,nt11205-ts", .data = &nvt_nt11205_ts_data },
+	{ .compatible = "novatek,nt36672a-ts", .data = &nvt_nt36672a_ts_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, nvt_ts_of_match);
+
 static const struct i2c_device_id nvt_ts_i2c_id[] = {
-	{ "nt11205-ts" },
+	{ "nt11205-ts", (unsigned long) &nvt_nt11205_ts_data },
+	{ "nt36672a-ts", (unsigned long) &nvt_nt36672a_ts_data },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, nvt_ts_i2c_id);
@@ -287,6 +341,7 @@ static struct i2c_driver nvt_ts_driver = {
 	.driver = {
 		.name	= "novatek-nvt-ts",
 		.pm	= pm_sleep_ptr(&nvt_ts_pm_ops),
+		.of_match_table = nvt_ts_of_match,
 	},
 	.probe = nvt_ts_probe,
 	.id_table = nvt_ts_i2c_id,

From b0352120afe43706258c5ae82174e08e324210d9 Mon Sep 17 00:00:00 2001
From: Yu Jiaoliang <yujiaoliang@vivo.com>
Date: Thu, 26 Sep 2024 11:14:43 +0800
Subject: [PATCH 0033/1530] input: Fix typos in comments across various files

This commit fixes several typographical errors in comments within
the driver/input directory. No functional changes are made.

Detected using codespell.

Signed-off-by: Yu Jiaoliang <yujiaoliang@vivo.com>
Reviewed-by: Oliver Graute <oliver.graute@kococonnector.com>
Link: https://lore.kernel.org/r/20240926031457.3479350-1-yujiaoliang@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/auo-pixcir-ts.c | 2 +-
 drivers/input/touchscreen/bcm_iproc_tsc.c | 2 +-
 drivers/input/touchscreen/edt-ft5x06.c    | 2 +-
 drivers/input/touchscreen/ili210x.c       | 2 +-
 drivers/input/touchscreen/pixcir_i2c_ts.c | 2 +-
 drivers/input/touchscreen/rohm_bu21023.c  | 4 ++--
 drivers/input/touchscreen/stmpe-ts.c      | 4 ++--
 drivers/input/touchscreen/wm97xx-core.c   | 4 ++--
 8 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/input/touchscreen/auo-pixcir-ts.c b/drivers/input/touchscreen/auo-pixcir-ts.c
index 8db2a112a4767..363a4a1f1560e 100644
--- a/drivers/input/touchscreen/auo-pixcir-ts.c
+++ b/drivers/input/touchscreen/auo-pixcir-ts.c
@@ -72,7 +72,7 @@
 
 /*
  * Interrupt modes:
- * periodical:		interrupt is asserted periodicaly
+ * periodical:		interrupt is asserted periodically
  * compare coordinates:	interrupt is asserted when coordinates change
  * indicate touch:	interrupt is asserted during touch
  */
diff --git a/drivers/input/touchscreen/bcm_iproc_tsc.c b/drivers/input/touchscreen/bcm_iproc_tsc.c
index 9c84235327bfb..e49bde50d77a2 100644
--- a/drivers/input/touchscreen/bcm_iproc_tsc.c
+++ b/drivers/input/touchscreen/bcm_iproc_tsc.c
@@ -217,7 +217,7 @@ static irqreturn_t iproc_touchscreen_interrupt(int irq, void *data)
 			"pen up-down (%d)\n", priv->pen_status);
 	}
 
-	/* coordinates in FIFO exceed the theshold */
+	/* coordinates in FIFO exceed the threshold */
 	if (intr_status & TS_FIFO_INTR_MASK) {
 		for (i = 0; i < priv->cfg_params.fifo_threshold; i++) {
 			regmap_read(priv->regmap, FIFO_DATA, &raw_coordinate);
diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
index e70415f189a55..8c77e9f347c52 100644
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@@ -1219,7 +1219,7 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client)
 	}
 
 	/*
-	 * Check which sleep modes we can support. Power-off requieres the
+	 * Check which sleep modes we can support. Power-off requires the
 	 * reset-pin to ensure correct power-down/power-up behaviour. Start with
 	 * the EDT_PMODE_POWEROFF test since this is the deepest possible sleep
 	 * mode.
diff --git a/drivers/input/touchscreen/ili210x.c b/drivers/input/touchscreen/ili210x.c
index 4573844c3395a..a8ecd0f980cb8 100644
--- a/drivers/input/touchscreen/ili210x.c
+++ b/drivers/input/touchscreen/ili210x.c
@@ -898,7 +898,7 @@ static umode_t ili210x_attributes_visible(struct kobject *kobj,
 	if (attr == &dev_attr_calibrate.attr)
 		return priv->chip->has_calibrate_reg ? attr->mode : 0;
 
-	/* Firmware/Kernel/Protocol/BootMode is implememted only for ILI251x */
+	/* Firmware/Kernel/Protocol/BootMode is implemented only for ILI251x */
 	if (!priv->chip->has_firmware_proto)
 		return 0;
 
diff --git a/drivers/input/touchscreen/pixcir_i2c_ts.c b/drivers/input/touchscreen/pixcir_i2c_ts.c
index 4ede0687beb09..1ea0b12b2635b 100644
--- a/drivers/input/touchscreen/pixcir_i2c_ts.c
+++ b/drivers/input/touchscreen/pixcir_i2c_ts.c
@@ -44,7 +44,7 @@ enum pixcir_power_mode {
 
 /*
  * Interrupt modes:
- * periodical: interrupt is asserted periodicaly
+ * periodical: interrupt is asserted periodically
  * diff coordinates: interrupt is asserted when coordinates change
  * level on touch: interrupt level asserted during touch
  * pulse on touch: interrupt pulse asserted during touch
diff --git a/drivers/input/touchscreen/rohm_bu21023.c b/drivers/input/touchscreen/rohm_bu21023.c
index 0e5cc9fbad177..295d8d75ba322 100644
--- a/drivers/input/touchscreen/rohm_bu21023.c
+++ b/drivers/input/touchscreen/rohm_bu21023.c
@@ -388,13 +388,13 @@ static int rohm_ts_manual_calibration(struct rohm_ts_data *ts)
 			err_y = (int)READ_CALIB_BUF(PRM1_Y_H) << 2 |
 				READ_CALIB_BUF(PRM1_Y_L);
 
-			/* X axis ajust */
+			/* X axis adjust */
 			if (err_x <= 4)
 				calib_x -= AXIS_ADJUST;
 			else if (err_x >= 60)
 				calib_x += AXIS_ADJUST;
 
-			/* Y axis ajust */
+			/* Y axis adjust */
 			if (err_y <= 4)
 				calib_y -= AXIS_ADJUST;
 			else if (err_y >= 60)
diff --git a/drivers/input/touchscreen/stmpe-ts.c b/drivers/input/touchscreen/stmpe-ts.c
index b204fdb2d22c6..2228842dfb494 100644
--- a/drivers/input/touchscreen/stmpe-ts.c
+++ b/drivers/input/touchscreen/stmpe-ts.c
@@ -107,7 +107,7 @@ static void stmpe_work(struct work_struct *work)
 
 	/*
 	 * touch_det sometimes get desasserted or just get stuck. This appears
-	 * to be a silicon bug, We still have to clearify this with the
+	 * to be a silicon bug, We still have to clarify this with the
 	 * manufacture. As a workaround We release the key anyway if the
 	 * touch_det keeps coming in after 4ms, while the FIFO contains no value
 	 * during the whole time.
@@ -140,7 +140,7 @@ static irqreturn_t stmpe_ts_handler(int irq, void *data)
 
 	/*
 	 * The FIFO sometimes just crashes and stops generating interrupts. This
-	 * appears to be a silicon bug. We still have to clearify this with
+	 * appears to be a silicon bug. We still have to clarify this with
 	 * the manufacture. As a workaround we disable the TSC while we are
 	 * collecting data and flush the FIFO after reading
 	 */
diff --git a/drivers/input/touchscreen/wm97xx-core.c b/drivers/input/touchscreen/wm97xx-core.c
index f01f6cc9b59fa..91384ad1aa40b 100644
--- a/drivers/input/touchscreen/wm97xx-core.c
+++ b/drivers/input/touchscreen/wm97xx-core.c
@@ -222,7 +222,7 @@ EXPORT_SYMBOL_GPL(wm97xx_set_gpio);
 
 /*
  * Codec GPIO pin configuration, this sets pin direction, polarity,
- * stickyness and wake up.
+ * stickiness and wake up.
  */
 void wm97xx_config_gpio(struct wm97xx *wm, u32 gpio, enum wm97xx_gpio_dir dir,
 		   enum wm97xx_gpio_pol pol, enum wm97xx_gpio_sticky sticky,
@@ -403,7 +403,7 @@ static int wm97xx_read_samples(struct wm97xx *wm)
 			* is actively working with the touchscreen we
 			* don't want to lose the quick response. So we
 			* will slowly increase sleep time after the
-			* pen is up and quicky restore it to ~one task
+			* pen is up and quickly restore it to ~one task
 			* switch when pen is down again.
 			*/
 			if (wm->ts_reader_interval < HZ / 10)

From 515ef92b4939fa51f9f1ee278618e2d419b0b8b0 Mon Sep 17 00:00:00 2001
From: Shen Lichuan <shenlichuan@vivo.com>
Date: Thu, 26 Sep 2024 15:55:15 +0800
Subject: [PATCH 0034/1530] Input: correct typos in multiple comments across
 misc drivers

Fixed some confusing typos that were currently identified witch codespell,
the details are as follows:

-in the code comments:
drivers/input/misc/drv2665.c:18: Contol ==> Control
drivers/input/misc/drv2667.c:19: Contol ==> Control
drivers/input/misc/ideapad_slidebar.c:26: meaningfull ==> meaningful
drivers/input/misc/ims-pcu.c:742: bootoloader ==> bootloader
drivers/input/misc/kxtj9.c:28: funtion ==> function
drivers/input/misc/soc_button_array.c:518: indentical ==> identical
drivers/input/misc/wistron_btns.c:274: satelite ==> satellite
drivers/input/misc/yealink.c:380: singe ==> single
drivers/input/misc/yealink.c:617: coresponding ==> corresponding

Signed-off-by: Shen Lichuan <shenlichuan@vivo.com>
Link: https://lore.kernel.org/r/20240926075515.10042-1-shenlichuan@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/drv2665.c          | 2 +-
 drivers/input/misc/drv2667.c          | 2 +-
 drivers/input/misc/ideapad_slidebar.c | 2 +-
 drivers/input/misc/ims-pcu.c          | 2 +-
 drivers/input/misc/kxtj9.c            | 2 +-
 drivers/input/misc/soc_button_array.c | 2 +-
 drivers/input/misc/wistron_btns.c     | 2 +-
 drivers/input/misc/yealink.c          | 4 ++--
 8 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/input/misc/drv2665.c b/drivers/input/misc/drv2665.c
index f98e4d7653077..59ad69912bfd5 100644
--- a/drivers/input/misc/drv2665.c
+++ b/drivers/input/misc/drv2665.c
@@ -15,7 +15,7 @@
 #include <linux/delay.h>
 #include <linux/regulator/consumer.h>
 
-/* Contol registers */
+/* Control registers */
 #define DRV2665_STATUS	0x00
 #define DRV2665_CTRL_1	0x01
 #define DRV2665_CTRL_2	0x02
diff --git a/drivers/input/misc/drv2667.c b/drivers/input/misc/drv2667.c
index ad49845374b9b..b53231d41b091 100644
--- a/drivers/input/misc/drv2667.c
+++ b/drivers/input/misc/drv2667.c
@@ -16,7 +16,7 @@
 #include <linux/delay.h>
 #include <linux/regulator/consumer.h>
 
-/* Contol registers */
+/* Control registers */
 #define DRV2667_STATUS	0x00
 #define DRV2667_CTRL_1	0x01
 #define DRV2667_CTRL_2	0x02
diff --git a/drivers/input/misc/ideapad_slidebar.c b/drivers/input/misc/ideapad_slidebar.c
index fa4e7f67d7136..7f1b3690b7e22 100644
--- a/drivers/input/misc/ideapad_slidebar.c
+++ b/drivers/input/misc/ideapad_slidebar.c
@@ -23,7 +23,7 @@
  *
  * The value is in byte range, however, I only figured out
  * how bits 0b10011001 work. Some other bits, probably,
- * are meaningfull too.
+ * are meaningful too.
  *
  * Possible states:
  *
diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c
index 058f3470b7ae2..f687e8832fd31 100644
--- a/drivers/input/misc/ims-pcu.c
+++ b/drivers/input/misc/ims-pcu.c
@@ -739,7 +739,7 @@ static int ims_pcu_switch_to_bootloader(struct ims_pcu *pcu)
 {
 	int error;
 
-	/* Execute jump to the bootoloader */
+	/* Execute jump to the bootloader */
 	error = ims_pcu_execute_command(pcu, JUMP_TO_BTLDR, NULL, 0);
 	if (error) {
 		dev_err(pcu->dev,
diff --git a/drivers/input/misc/kxtj9.c b/drivers/input/misc/kxtj9.c
index 837682cb2a7d3..2f301ebb2fb8c 100644
--- a/drivers/input/misc/kxtj9.c
+++ b/drivers/input/misc/kxtj9.c
@@ -25,7 +25,7 @@
 /* CONTROL REGISTER 1 BITS */
 #define PC1_OFF			0x7F
 #define PC1_ON			(1 << 7)
-/* Data ready funtion enable bit: set during probe if using irq mode */
+/* Data ready function enable bit: set during probe if using irq mode */
 #define DRDYE			(1 << 5)
 /* DATA CONTROL REGISTER BITS */
 #define ODR12_5F		0
diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c
index 5c5d407fe9650..e8f373715e506 100644
--- a/drivers/input/misc/soc_button_array.c
+++ b/drivers/input/misc/soc_button_array.c
@@ -515,7 +515,7 @@ static const struct soc_device_data soc_device_INT33D3 = {
 };
 
 /*
- * Button info for Microsoft Surface 3 (non pro), this is indentical to
+ * Button info for Microsoft Surface 3 (non pro), this is identical to
  * the PNP0C40 info except that the home button is active-high.
  *
  * The Surface 3 Pro also has a MSHW0028 ACPI device, but that uses a custom
diff --git a/drivers/input/misc/wistron_btns.c b/drivers/input/misc/wistron_btns.c
index 907b1a4e6633a..5c28ef4563dab 100644
--- a/drivers/input/misc/wistron_btns.c
+++ b/drivers/input/misc/wistron_btns.c
@@ -271,7 +271,7 @@ static struct key_entry keymap_fs_amilo_pro_v8210[] __initdata = {
 	{ KE_BLUETOOTH, 0x30 },                      /* Fn+F10 */
 	{ KE_KEY,       0x31, {KEY_MAIL} },          /* mail button */
 	{ KE_KEY,       0x36, {KEY_WWW} },           /* www button */
-	{ KE_WIFI,      0x78 },                      /* satelite dish button */
+	{ KE_WIFI,      0x78 },                      /* satellite dish button */
 	{ KE_END,       FE_WIFI_LED }
 };
 
diff --git a/drivers/input/misc/yealink.c b/drivers/input/misc/yealink.c
index 8866bf65d347b..08dc53ae1b3c9 100644
--- a/drivers/input/misc/yealink.c
+++ b/drivers/input/misc/yealink.c
@@ -377,7 +377,7 @@ static int yealink_do_idle_tasks(struct yealink_dev *yld)
 		if (len > sizeof(yld->ctl_data->data))
 			len = sizeof(yld->ctl_data->data);
 
-		/* Combine up to <len> consecutive LCD bytes in a singe request
+		/* Combine up to <len> consecutive LCD bytes in a single request
 		 */
 		yld->ctl_data->cmd	= CMD_LCD;
 		yld->ctl_data->offset	= cpu_to_be16(ix);
@@ -614,7 +614,7 @@ static ssize_t show_line3(struct device *dev, struct device_attribute *attr,
 	return show_line(dev, buf, LCD_LINE3_OFFSET, LCD_LINE4_OFFSET);
 }
 
-/* Writing to /sys/../lineX will set the coresponding LCD line.
+/* Writing to /sys/../lineX will set the corresponding LCD line.
  * - Excess characters are ignored.
  * - If less characters are written than allowed, the remaining digits are
  *   unchanged.

From a36d9f96d1cf7c0308bf091e810bec06ce492c3d Mon Sep 17 00:00:00 2001
From: Markus Elfring <elfring@users.sourceforge.net>
Date: Tue, 24 Sep 2024 14:28:35 +0200
Subject: [PATCH 0035/1530] remoteproc: k3: Call of_node_put(rmem_np) only once
 in three functions

An of_node_put(rmem_np) call was immediately used after a pointer check
for a of_reserved_mem_lookup() call in three function implementations.
Thus call such a function only once instead directly before the checks.

This issue was transformed by using the Coccinelle software.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Link: https://lore.kernel.org/r/c46b06f9-72b1-420b-9dce-a392b982140e@web.de
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/ti_k3_dsp_remoteproc.c | 6 ++----
 drivers/remoteproc/ti_k3_m4_remoteproc.c  | 6 ++----
 drivers/remoteproc/ti_k3_r5_remoteproc.c  | 3 +--
 3 files changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/remoteproc/ti_k3_dsp_remoteproc.c b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
index 8be3f631c1920..d08a3a98ada1c 100644
--- a/drivers/remoteproc/ti_k3_dsp_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
@@ -576,11 +576,9 @@ static int k3_dsp_reserved_mem_init(struct k3_dsp_rproc *kproc)
 			return -EINVAL;
 
 		rmem = of_reserved_mem_lookup(rmem_np);
-		if (!rmem) {
-			of_node_put(rmem_np);
-			return -EINVAL;
-		}
 		of_node_put(rmem_np);
+		if (!rmem)
+			return -EINVAL;
 
 		kproc->rmem[i].bus_addr = rmem->base;
 		/* 64-bit address regions currently not supported */
diff --git a/drivers/remoteproc/ti_k3_m4_remoteproc.c b/drivers/remoteproc/ti_k3_m4_remoteproc.c
index 09f0484a90e10..a16fb165fcedd 100644
--- a/drivers/remoteproc/ti_k3_m4_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_m4_remoteproc.c
@@ -433,11 +433,9 @@ static int k3_m4_reserved_mem_init(struct k3_m4_rproc *kproc)
 			return -EINVAL;
 
 		rmem = of_reserved_mem_lookup(rmem_np);
-		if (!rmem) {
-			of_node_put(rmem_np);
-			return -EINVAL;
-		}
 		of_node_put(rmem_np);
+		if (!rmem)
+			return -EINVAL;
 
 		kproc->rmem[i].bus_addr = rmem->base;
 		/* 64-bit address regions currently not supported */
diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c
index 747ee467da88c..d0ebdd5cfa70e 100644
--- a/drivers/remoteproc/ti_k3_r5_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c
@@ -1001,12 +1001,11 @@ static int k3_r5_reserved_mem_init(struct k3_r5_rproc *kproc)
 		}
 
 		rmem = of_reserved_mem_lookup(rmem_np);
+		of_node_put(rmem_np);
 		if (!rmem) {
-			of_node_put(rmem_np);
 			ret = -EINVAL;
 			goto unmap_rmem;
 		}
-		of_node_put(rmem_np);
 
 		kproc->rmem[i].bus_addr = rmem->base;
 		/*

From 8a8622b7c20658bf24b4d48dc53aaa893c37f482 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Mon, 12 Aug 2024 15:28:11 +0800
Subject: [PATCH 0036/1530] remoteproc: Use iommu_paging_domain_alloc()

An iommu domain is allocated in rproc_enable_iommu() and is attached to
rproc->dev.parent in the same function.

Use iommu_paging_domain_alloc() to make it explicit.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20240812072811.9737-1-baolu.lu@linux.intel.com
Acked-by: Beleswar Padhi <b-padhi@ti.com>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/remoteproc_core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index f276956f2c5ce..eb66f78ec8b77 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -109,10 +109,10 @@ static int rproc_enable_iommu(struct rproc *rproc)
 		return 0;
 	}
 
-	domain = iommu_domain_alloc(dev->bus);
-	if (!domain) {
+	domain = iommu_paging_domain_alloc(dev);
+	if (IS_ERR(domain)) {
 		dev_err(dev, "can't alloc iommu domain\n");
-		return -ENOMEM;
+		return PTR_ERR(domain);
 	}
 
 	iommu_set_fault_handler(domain, rproc_iommu_fault, rproc);

From b21a18f730e4b659be951a041eff682a60c0f4a0 Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@inria.fr>
Date: Mon, 30 Sep 2024 13:21:08 +0200
Subject: [PATCH 0037/1530] PCI: hotplug: Reorganize kerneldoc parameter names

Reorganize kerneldoc parameter names to match the parameter order in the
function header.

Problems identified using Coccinelle.

Link: https://lore.kernel.org/r/20240930112121.95324-23-Julia.Lawall@inria.fr
Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pci_hotplug_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c
index 058d5937d8a95..db09d4992e6e2 100644
--- a/drivers/pci/hotplug/pci_hotplug_core.c
+++ b/drivers/pci/hotplug/pci_hotplug_core.c
@@ -388,8 +388,8 @@ static struct hotplug_slot *get_slot_from_name(const char *name)
 
 /**
  * __pci_hp_register - register a hotplug_slot with the PCI hotplug subsystem
- * @bus: bus this slot is on
  * @slot: pointer to the &struct hotplug_slot to register
+ * @bus: bus this slot is on
  * @devnr: device number
  * @name: name registered with kobject core
  * @owner: caller module owner

From 43ee11adcb940204948ac0ca3a05d6178f0e8b08 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 30 Sep 2024 15:44:36 +0300
Subject: [PATCH 0038/1530] PCI: hotplug: Remove "Returns" kerneldoc from void
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

pci_hp_deregister() was converted to void by the commit 51bbf9bee34f ("PCI:
hotplug: Demidlayer registration with the core") but its kerneldoc still
describes the return value. pci_hp_del() and pci_hp_destroy() have been
void since they were introduced in that same commit.

Remove the return value description from the kerneldoc of those functions.

Link: https://lore.kernel.org/r/20240930124436.17908-1-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pci_hotplug_core.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c
index db09d4992e6e2..36236ac88fd56 100644
--- a/drivers/pci/hotplug/pci_hotplug_core.c
+++ b/drivers/pci/hotplug/pci_hotplug_core.c
@@ -498,8 +498,6 @@ EXPORT_SYMBOL_GPL(pci_hp_add);
  *
  * The @slot must have been registered with the pci hotplug subsystem
  * previously with a call to pci_hp_register().
- *
- * Returns 0 if successful, anything else for an error.
  */
 void pci_hp_deregister(struct hotplug_slot *slot)
 {
@@ -513,8 +511,6 @@ EXPORT_SYMBOL_GPL(pci_hp_deregister);
  * @slot: pointer to the &struct hotplug_slot to unpublish
  *
  * Remove a hotplug slot's sysfs interface.
- *
- * Returns 0 on success or a negative int on error.
  */
 void pci_hp_del(struct hotplug_slot *slot)
 {
@@ -545,8 +541,6 @@ EXPORT_SYMBOL_GPL(pci_hp_del);
  * the driver may no longer invoke hotplug_slot_name() to get the slot's
  * unique name.  The driver no longer needs to handle a ->reset_slot callback
  * from this point on.
- *
- * Returns 0 on success or a negative int on error.
  */
 void pci_hp_destroy(struct hotplug_slot *slot)
 {

From 9865f0a209fe78c7d924e10261c08fa7774e3e55 Mon Sep 17 00:00:00 2001
From: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Date: Sun, 29 Sep 2024 17:30:45 +0800
Subject: [PATCH 0039/1530] perf test: Use ARRAY_SIZE for array length

Use of macro ARRAY_SIZE to calculate array size minimizes
the redundant code and improves code reusability.

  ./tools/perf/tests/demangle-java-test.c:31:34-35: WARNING: Use ARRAY_SIZE.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=11173
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Link: https://lore.kernel.org/r/20240929093045.10136-1-jiapeng.chong@linux.alibaba.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/demangle-java-test.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/demangle-java-test.c b/tools/perf/tests/demangle-java-test.c
index 44d1be303b67a..93c94408bdc8f 100644
--- a/tools/perf/tests/demangle-java-test.c
+++ b/tools/perf/tests/demangle-java-test.c
@@ -2,6 +2,7 @@
 #include <string.h>
 #include <stdlib.h>
 #include <stdio.h>
+#include <linux/kernel.h>
 #include "tests.h"
 #include "session.h"
 #include "debug.h"
@@ -28,7 +29,7 @@ static int test__demangle_java(struct test_suite *test __maybe_unused, int subte
 		  "void java.lang.Object<init>()" },
 	};
 
-	for (i = 0; i < sizeof(test_cases) / sizeof(test_cases[0]); i++) {
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
 		buf = java_demangle_sym(test_cases[i].mangled, 0);
 		if (strcmp(buf, test_cases[i].demangled)) {
 			pr_debug("FAILED: %s: %s != %s\n", test_cases[i].mangled,

From f0cb9fa7a567d613eb23dd486ca89f8820f778bf Mon Sep 17 00:00:00 2001
From: Yicong Yang <yangyicong@hisilicon.com>
Date: Thu, 12 Sep 2024 14:39:03 +0800
Subject: [PATCH 0040/1530] perf vender events arm64: Use "Topdown" as topdown
 metric group name

HiSilicon HIP08 does support Topdown metrics but perf tool complains
when trying to count Topdown metrics:
[root@localhost tracing]# perf stat --topdown
Topdown requested but the topdown metric groups aren't present.
(See perf list the metric groups have names like TopdownL1)

It's because tool's using "Topdown" as the metric group name[1] rather
than "TopDown", so follow the convention. This is introduced by [2]
which allows to use json metrics to support --topdown function.

[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/perf/builtin-stat.c?h=v6.11-rc1#n1994
[2] commit 1647cd5b8802 ("perf stat: Implement --topdown using json metrics")

Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Cc: prime.zeng@hisilicon.com
Cc: hejunhao3@huawei.com
Cc: linuxarm@huawei.com
Cc: shameerali.kolothum.thodi@huawei.com
Link: https://lore.kernel.org/r/20240912063903.31460-1-yangyicong@huawei.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../arch/arm64/hisilicon/hip08/metrics.json   | 74 +++++++++----------
 1 file changed, 37 insertions(+), 37 deletions(-)

diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json
index 6463531b99410..b6a0d2de8534a 100644
--- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json
@@ -3,235 +3,235 @@
         "MetricExpr": "FETCH_BUBBLE / (4 * CPU_CYCLES)",
         "PublicDescription": "Frontend bound L1 topdown metric",
         "BriefDescription": "Frontend bound L1 topdown metric",
-        "DefaultMetricgroupName": "TopDownL1",
-        "MetricGroup": "Default;TopDownL1",
+        "DefaultMetricgroupName": "TopdownL1",
+        "MetricGroup": "Default;TopdownL1",
         "MetricName": "frontend_bound"
     },
     {
         "MetricExpr": "(INST_SPEC - INST_RETIRED) / (4 * CPU_CYCLES)",
         "PublicDescription": "Bad Speculation L1 topdown metric",
         "BriefDescription": "Bad Speculation L1 topdown metric",
-        "DefaultMetricgroupName": "TopDownL1",
-        "MetricGroup": "Default;TopDownL1",
+        "DefaultMetricgroupName": "TopdownL1",
+        "MetricGroup": "Default;TopdownL1",
         "MetricName": "bad_speculation"
     },
     {
         "MetricExpr": "INST_RETIRED / (CPU_CYCLES * 4)",
         "PublicDescription": "Retiring L1 topdown metric",
         "BriefDescription": "Retiring L1 topdown metric",
-        "DefaultMetricgroupName": "TopDownL1",
-        "MetricGroup": "Default;TopDownL1",
+        "DefaultMetricgroupName": "TopdownL1",
+        "MetricGroup": "Default;TopdownL1",
         "MetricName": "retiring"
     },
     {
         "MetricExpr": "1 - (frontend_bound + bad_speculation + retiring)",
         "PublicDescription": "Backend Bound L1 topdown metric",
         "BriefDescription": "Backend Bound L1 topdown metric",
-        "DefaultMetricgroupName": "TopDownL1",
-        "MetricGroup": "Default;TopDownL1",
+        "DefaultMetricgroupName": "TopdownL1",
+        "MetricGroup": "Default;TopdownL1",
         "MetricName": "backend_bound"
     },
     {
         "MetricExpr": "armv8_pmuv3_0@event\\=0x201d@ / CPU_CYCLES",
         "PublicDescription": "Fetch latency bound L2 topdown metric",
         "BriefDescription": "Fetch latency bound L2 topdown metric",
-        "MetricGroup": "TopDownL2",
+        "MetricGroup": "TopdownL2",
         "MetricName": "fetch_latency_bound"
     },
     {
         "MetricExpr": "frontend_bound - fetch_latency_bound",
         "PublicDescription": "Fetch bandwidth bound L2 topdown metric",
         "BriefDescription": "Fetch bandwidth bound L2 topdown metric",
-        "MetricGroup": "TopDownL2",
+        "MetricGroup": "TopdownL2",
         "MetricName": "fetch_bandwidth_bound"
     },
     {
         "MetricExpr": "(bad_speculation * BR_MIS_PRED) / (BR_MIS_PRED + armv8_pmuv3_0@event\\=0x2013@)",
         "PublicDescription": "Branch mispredicts L2 topdown metric",
         "BriefDescription": "Branch mispredicts L2 topdown metric",
-        "MetricGroup": "TopDownL2",
+        "MetricGroup": "TopdownL2",
         "MetricName": "branch_mispredicts"
     },
     {
         "MetricExpr": "bad_speculation - branch_mispredicts",
         "PublicDescription": "Machine clears L2 topdown metric",
         "BriefDescription": "Machine clears L2 topdown metric",
-        "MetricGroup": "TopDownL2",
+        "MetricGroup": "TopdownL2",
         "MetricName": "machine_clears"
     },
     {
         "MetricExpr": "(EXE_STALL_CYCLE - (MEM_STALL_ANYLOAD + armv8_pmuv3_0@event\\=0x7005@)) / CPU_CYCLES",
         "PublicDescription": "Core bound L2 topdown metric",
         "BriefDescription": "Core bound L2 topdown metric",
-        "MetricGroup": "TopDownL2",
+        "MetricGroup": "TopdownL2",
         "MetricName": "core_bound"
     },
     {
         "MetricExpr": "(MEM_STALL_ANYLOAD + armv8_pmuv3_0@event\\=0x7005@) / CPU_CYCLES",
         "PublicDescription": "Memory bound L2 topdown metric",
         "BriefDescription": "Memory bound L2 topdown metric",
-        "MetricGroup": "TopDownL2",
+        "MetricGroup": "TopdownL2",
         "MetricName": "memory_bound"
     },
     {
         "MetricExpr": "(((L2I_TLB - L2I_TLB_REFILL) * 15) + (L2I_TLB_REFILL * 100)) / CPU_CYCLES",
         "PublicDescription": "Idle by itlb miss L3 topdown metric",
         "BriefDescription": "Idle by itlb miss L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "idle_by_itlb_miss"
     },
     {
         "MetricExpr": "(((L2I_CACHE - L2I_CACHE_REFILL) * 15) + (L2I_CACHE_REFILL * 100)) / CPU_CYCLES",
         "PublicDescription": "Idle by icache miss L3 topdown metric",
         "BriefDescription": "Idle by icache miss L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "idle_by_icache_miss"
     },
     {
         "MetricExpr": "(BR_MIS_PRED * 5) / CPU_CYCLES",
         "PublicDescription": "BP misp flush L3 topdown metric",
         "BriefDescription": "BP misp flush L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "bp_misp_flush"
     },
     {
         "MetricExpr": "(armv8_pmuv3_0@event\\=0x2013@ * 5) / CPU_CYCLES",
         "PublicDescription": "OOO flush L3 topdown metric",
         "BriefDescription": "OOO flush L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "ooo_flush"
     },
     {
         "MetricExpr": "(armv8_pmuv3_0@event\\=0x1001@ * 5) / CPU_CYCLES",
         "PublicDescription": "Static predictor flush L3 topdown metric",
         "BriefDescription": "Static predictor flush L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "sp_flush"
     },
     {
         "MetricExpr": "armv8_pmuv3_0@event\\=0x1010@ / BR_MIS_PRED",
         "PublicDescription": "Indirect branch L3 topdown metric",
         "BriefDescription": "Indirect branch L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "indirect_branch"
     },
     {
         "MetricExpr": "(armv8_pmuv3_0@event\\=0x1013@ + armv8_pmuv3_0@event\\=0x1016@) / BR_MIS_PRED",
         "PublicDescription": "Push branch L3 topdown metric",
         "BriefDescription": "Push branch L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "push_branch"
     },
     {
         "MetricExpr": "armv8_pmuv3_0@event\\=0x100d@ / BR_MIS_PRED",
         "PublicDescription": "Pop branch L3 topdown metric",
         "BriefDescription": "Pop branch L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "pop_branch"
     },
     {
         "MetricExpr": "(BR_MIS_PRED - armv8_pmuv3_0@event\\=0x1010@ - armv8_pmuv3_0@event\\=0x1013@ - armv8_pmuv3_0@event\\=0x1016@ - armv8_pmuv3_0@event\\=0x100d@) / BR_MIS_PRED",
         "PublicDescription": "Other branch L3 topdown metric",
         "BriefDescription": "Other branch L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "other_branch"
     },
     {
         "MetricExpr": "armv8_pmuv3_0@event\\=0x2012@ / armv8_pmuv3_0@event\\=0x2013@",
         "PublicDescription": "Nuke flush L3 topdown metric",
         "BriefDescription": "Nuke flush L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "nuke_flush"
     },
     {
         "MetricExpr": "1 - nuke_flush",
         "PublicDescription": "Other flush L3 topdown metric",
         "BriefDescription": "Other flush L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "other_flush"
     },
     {
         "MetricExpr": "armv8_pmuv3_0@event\\=0x2010@ / CPU_CYCLES",
         "PublicDescription": "Sync stall L3 topdown metric",
         "BriefDescription": "Sync stall L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "sync_stall"
     },
     {
         "MetricExpr": "armv8_pmuv3_0@event\\=0x2004@ / CPU_CYCLES",
         "PublicDescription": "Rob stall L3 topdown metric",
         "BriefDescription": "Rob stall L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "rob_stall"
     },
     {
         "MetricExpr": "(armv8_pmuv3_0@event\\=0x2006@ + armv8_pmuv3_0@event\\=0x2007@ + armv8_pmuv3_0@event\\=0x2008@) / CPU_CYCLES",
         "PublicDescription": "Ptag stall L3 topdown metric",
         "BriefDescription": "Ptag stall L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "ptag_stall"
     },
     {
         "MetricExpr": "armv8_pmuv3_0@event\\=0x201e@ / CPU_CYCLES",
         "PublicDescription": "SaveOpQ stall L3 topdown metric",
         "BriefDescription": "SaveOpQ stall L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "saveopq_stall"
     },
     {
         "MetricExpr": "armv8_pmuv3_0@event\\=0x2005@ / CPU_CYCLES",
         "PublicDescription": "PC buffer stall L3 topdown metric",
         "BriefDescription": "PC buffer stall L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "pc_buffer_stall"
     },
     {
         "MetricExpr": "armv8_pmuv3_0@event\\=0x7002@ / CPU_CYCLES",
         "PublicDescription": "Divider L3 topdown metric",
         "BriefDescription": "Divider L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "divider"
     },
     {
         "MetricExpr": "armv8_pmuv3_0@event\\=0x7003@ / CPU_CYCLES",
         "PublicDescription": "FSU stall L3 topdown metric",
         "BriefDescription": "FSU stall L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "fsu_stall"
     },
     {
         "MetricExpr": "core_bound - divider - fsu_stall",
         "PublicDescription": "EXE ports util L3 topdown metric",
         "BriefDescription": "EXE ports util L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "exe_ports_util"
     },
     {
         "MetricExpr": "(MEM_STALL_ANYLOAD - MEM_STALL_L1MISS) / CPU_CYCLES",
         "PublicDescription": "L1 bound L3 topdown metric",
         "BriefDescription": "L1 bound L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "l1_bound"
     },
     {
         "MetricExpr": "(MEM_STALL_L1MISS - MEM_STALL_L2MISS) / CPU_CYCLES",
         "PublicDescription": "L2 bound L3 topdown metric",
         "BriefDescription": "L2 bound L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "l2_bound"
     },
     {
         "MetricExpr": "MEM_STALL_L2MISS / CPU_CYCLES",
         "PublicDescription": "Mem bound L3 topdown metric",
         "BriefDescription": "Mem bound L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "mem_bound"
     },
     {
         "MetricExpr": "armv8_pmuv3_0@event\\=0x7005@ / CPU_CYCLES",
         "PublicDescription": "Store bound L3 topdown metric",
         "BriefDescription": "Store bound L3 topdown metric",
-        "MetricGroup": "TopDownL3",
+        "MetricGroup": "TopdownL3",
         "MetricName": "store_bound"
     }
 ]

From 4d1b305dc8d74114abd544b0c11397ceb9ded528 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 19 Sep 2024 00:31:16 +0200
Subject: [PATCH 0041/1530] perf evsel: Reduce a variables scope

In __evsel__config_callchain avoid computing arch until code path that
uses it.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Dominique Martinet <asmadeus@codewreck.org>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Link: https://lore.kernel.org/r/20240918223116.127386-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/evsel.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index edfb376f06119..da0bada62140d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -859,7 +859,6 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
 {
 	bool function = evsel__is_function_event(evsel);
 	struct perf_event_attr *attr = &evsel->core.attr;
-	const char *arch = perf_env__arch(evsel__env(evsel));
 
 	evsel__set_sample_bit(evsel, CALLCHAIN);
 
@@ -890,6 +889,8 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
 
 	if (param->record_mode == CALLCHAIN_DWARF) {
 		if (!function) {
+			const char *arch = perf_env__arch(evsel__env(evsel));
+
 			evsel__set_sample_bit(evsel, REGS_USER);
 			evsel__set_sample_bit(evsel, STACK_USER);
 			if (opts->sample_user_regs &&

From 39820ced2aa1fb2453294909651dfc7dd6e6e028 Mon Sep 17 00:00:00 2001
From: Dapeng Mi <dapeng1.mi@linux.intel.com>
Date: Fri, 13 Sep 2024 08:47:07 +0000
Subject: [PATCH 0042/1530] perf x86/topdown: Complete topdown slots/metrics
 events check

It's not complete to check whether an event is a topdown slots or
topdown metrics event by only comparing the event name since user
may assign the event by RAW format, e.g.

perf stat -e '{instructions,cpu/r400/,cpu/r8300/}' sleep 1

 Performance counter stats for 'sleep 1':

     <not counted>      instructions
     <not counted>      cpu/r400/
   <not supported>      cpu/r8300/

       1.002917796 seconds time elapsed

       0.002955000 seconds user
       0.000000000 seconds sys

The RAW format slots and topdown-be-bound events are not recognized and
not regroup the events, and eventually cause error.

Thus add two helpers arch_is_topdown_slots()/arch_is_topdown_metrics()
to detect whether an event is topdown slots/metrics event by comparing
the event config directly, and use these two helpers to replace the
original event name comparisons.

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20240913084712.13861-2-dapeng1.mi@linux.intel.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/x86/util/evlist.c  |  8 ++---
 tools/perf/arch/x86/util/evsel.c   |  3 +-
 tools/perf/arch/x86/util/topdown.c | 48 +++++++++++++++++++++++++++++-
 tools/perf/arch/x86/util/topdown.h |  2 ++
 4 files changed, 55 insertions(+), 6 deletions(-)

diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index 3a4bf13b17593..044bc59482c88 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -10,14 +10,14 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 	if (topdown_sys_has_perf_metrics() &&
 	    (arch_evsel__must_be_in_group(lhs) || arch_evsel__must_be_in_group(rhs))) {
 		/* Ensure the topdown slots comes first. */
-		if (strcasestr(lhs->name, "slots") && !strcasestr(lhs->name, "uops_retired.slots"))
+		if (arch_is_topdown_slots(lhs))
 			return -1;
-		if (strcasestr(rhs->name, "slots") && !strcasestr(rhs->name, "uops_retired.slots"))
+		if (arch_is_topdown_slots(rhs))
 			return 1;
 		/* Followed by topdown events. */
-		if (strcasestr(lhs->name, "topdown") && !strcasestr(rhs->name, "topdown"))
+		if (arch_is_topdown_metrics(lhs) && !arch_is_topdown_metrics(rhs))
 			return -1;
-		if (!strcasestr(lhs->name, "topdown") && strcasestr(rhs->name, "topdown"))
+		if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs))
 			return 1;
 	}
 
diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
index cf7c116eeb8e4..3dd29ba2c23b0 100644
--- a/tools/perf/arch/x86/util/evsel.c
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -6,6 +6,7 @@
 #include "util/pmu.h"
 #include "util/pmus.h"
 #include "linux/string.h"
+#include "topdown.h"
 #include "evsel.h"
 #include "util/debug.h"
 #include "env.h"
@@ -65,7 +66,7 @@ bool arch_evsel__must_be_in_group(const struct evsel *evsel)
 	    strcasestr(evsel->name, "uops_retired.slots"))
 		return false;
 
-	return strcasestr(evsel->name, "topdown") || strcasestr(evsel->name, "slots");
+	return arch_is_topdown_metrics(evsel) || arch_is_topdown_slots(evsel);
 }
 
 int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c
index 3f9a267d4501b..49f25d67ed776 100644
--- a/tools/perf/arch/x86/util/topdown.c
+++ b/tools/perf/arch/x86/util/topdown.c
@@ -32,6 +32,52 @@ bool topdown_sys_has_perf_metrics(void)
 }
 
 #define TOPDOWN_SLOTS		0x0400
+bool arch_is_topdown_slots(const struct evsel *evsel)
+{
+	if (evsel->core.attr.config == TOPDOWN_SLOTS)
+		return true;
+
+	return false;
+}
+
+static int compare_topdown_event(void *vstate, struct pmu_event_info *info)
+{
+	int *config = vstate;
+	int event = 0;
+	int umask = 0;
+	char *str;
+
+	if (!strcasestr(info->name, "topdown"))
+		return 0;
+
+	str = strcasestr(info->str, "event=");
+	if (str)
+		sscanf(str, "event=%x", &event);
+
+	str = strcasestr(info->str, "umask=");
+	if (str)
+		sscanf(str, "umask=%x", &umask);
+
+	if (event == 0 && *config == (event | umask << 8))
+		return 1;
+
+	return 0;
+}
+
+bool arch_is_topdown_metrics(const struct evsel *evsel)
+{
+	struct perf_pmu *pmu = evsel__find_pmu(evsel);
+	int config = evsel->core.attr.config;
+
+	if (!pmu || !pmu->is_core)
+		return false;
+
+	if (perf_pmu__for_each_event(pmu, false, &config,
+				     compare_topdown_event))
+		return true;
+
+	return false;
+}
 
 /*
  * Check whether a topdown group supports sample-read.
@@ -44,7 +90,7 @@ bool arch_topdown_sample_read(struct evsel *leader)
 	if (!evsel__sys_has_perf_metrics(leader))
 		return false;
 
-	if (leader->core.attr.config == TOPDOWN_SLOTS)
+	if (arch_is_topdown_slots(leader))
 		return true;
 
 	return false;
diff --git a/tools/perf/arch/x86/util/topdown.h b/tools/perf/arch/x86/util/topdown.h
index 46bf9273e572f..1bae9b1822d71 100644
--- a/tools/perf/arch/x86/util/topdown.h
+++ b/tools/perf/arch/x86/util/topdown.h
@@ -3,5 +3,7 @@
 #define _TOPDOWN_H 1
 
 bool topdown_sys_has_perf_metrics(void);
+bool arch_is_topdown_slots(const struct evsel *evsel);
+bool arch_is_topdown_metrics(const struct evsel *evsel);
 
 #endif

From 1e53e9d1787babb1544eaec7c7fdcb78a4a20a13 Mon Sep 17 00:00:00 2001
From: Dapeng Mi <dapeng1.mi@linux.intel.com>
Date: Fri, 13 Sep 2024 08:47:08 +0000
Subject: [PATCH 0043/1530] perf x86/topdown: Correct leader selection with
 sample_read enabled

Addresses an issue where, in the absence of a topdown metrics event
within a sampling group, the slots event was incorrectly bypassed as
the sampling leader when sample_read was enabled.

perf record -e '{slots,branches}:S' -c 10000 -vv sleep 1

In this case, the slots event should be sampled as leader but the
branches event is sampled in fact like the verbose output shows.

perf_event_attr:
  type                             4 (cpu)
  size                             168
  config                           0x400 (slots)
  sample_type                      IP|TID|TIME|READ|CPU|IDENTIFIER
  read_format                      ID|GROUP|LOST
  disabled                         1
  sample_id_all                    1
  exclude_guest                    1
------------------------------------------------------------
sys_perf_event_open: pid -1  cpu 0  group_fd -1  flags 0x8 = 5
------------------------------------------------------------
perf_event_attr:
  type                             0 (PERF_TYPE_HARDWARE)
  size                             168
  config                           0x4 (PERF_COUNT_HW_BRANCH_INSTRUCTIONS)
  { sample_period, sample_freq }   10000
  sample_type                      IP|TID|TIME|READ|CPU|IDENTIFIER
  read_format                      ID|GROUP|LOST
  sample_id_all                    1
  exclude_guest                    1

The sample period of slots event instead of branches event is reset to
0.

This fix ensures the slots event remains the leader under these
conditions.

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20240913084712.13861-3-dapeng1.mi@linux.intel.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/x86/util/topdown.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c
index 49f25d67ed776..cb2c64928bc4b 100644
--- a/tools/perf/arch/x86/util/topdown.c
+++ b/tools/perf/arch/x86/util/topdown.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "api/fs/fs.h"
 #include "util/evsel.h"
+#include "util/evlist.h"
 #include "util/pmu.h"
 #include "util/pmus.h"
 #include "util/topdown.h"
@@ -87,11 +88,24 @@ bool arch_is_topdown_metrics(const struct evsel *evsel)
  */
 bool arch_topdown_sample_read(struct evsel *leader)
 {
+	struct evsel *evsel;
+
 	if (!evsel__sys_has_perf_metrics(leader))
 		return false;
 
-	if (arch_is_topdown_slots(leader))
-		return true;
+	if (!arch_is_topdown_slots(leader))
+		return false;
+
+	/*
+	 * If slots event as leader event but no topdown metric events
+	 * in group, slots event should still sample as leader.
+	 */
+	evlist__for_each_entry(leader->evlist, evsel) {
+		if (evsel->core.leader != leader->core.leader)
+			return false;
+		if (evsel != leader && arch_is_topdown_metrics(evsel))
+			return true;
+	}
 
 	return false;
 }

From 3b5edc0421e2598a0ae7f0adcd592017f37e3cdf Mon Sep 17 00:00:00 2001
From: Dapeng Mi <dapeng1.mi@linux.intel.com>
Date: Fri, 13 Sep 2024 08:47:09 +0000
Subject: [PATCH 0044/1530] perf x86/topdown: Don't move topdown metric events
 in group

when running below perf command, we say error is reported.

perf record -e "{slots,instructions,topdown-retiring}:S" -vv -C0 sleep 1

------------------------------------------------------------
perf_event_attr:
  type                             4 (cpu)
  size                             168
  config                           0x400 (slots)
  sample_type                      IP|TID|TIME|READ|CPU|PERIOD|IDENTIFIER
  read_format                      ID|GROUP|LOST
  disabled                         1
  sample_id_all                    1
  exclude_guest                    1
------------------------------------------------------------
sys_perf_event_open: pid -1  cpu 0  group_fd -1  flags 0x8 = 5
------------------------------------------------------------
perf_event_attr:
  type                             4 (cpu)
  size                             168
  config                           0x8000 (topdown-retiring)
  { sample_period, sample_freq }   4000
  sample_type                      IP|TID|TIME|READ|CPU|PERIOD|IDENTIFIER
  read_format                      ID|GROUP|LOST
  freq                             1
  sample_id_all                    1
  exclude_guest                    1
------------------------------------------------------------
sys_perf_event_open: pid -1  cpu 0  group_fd 5  flags 0x8
sys_perf_event_open failed, error -22

Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for
event (topdown-retiring).

The reason of error is that the events are regrouped and
topdown-retiring event is moved to closely after the slots event and
topdown-retiring event needs to do the sampling, but Intel PMU driver
doesn't support to sample topdown metrics events.

For topdown metrics events, it just requires to be in a group which has
slots event as leader. It doesn't require topdown metrics event must be
closely after slots event. Thus it's a overkill to move topdown metrics
event closely after slots event in events regrouping and furtherly cause
the above issue.

Thus don't move topdown metrics events forward if they are already in a
group.

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20240913084712.13861-4-dapeng1.mi@linux.intel.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/x86/util/evlist.c | 62 ++++++++++++++++++++++++++++++-
 1 file changed, 61 insertions(+), 1 deletion(-)

diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index 044bc59482c88..438e4639fa892 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -7,6 +7,61 @@
 
 int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 {
+	/*
+	 * Currently the following topdown events sequence are supported to
+	 * move and regroup correctly.
+	 *
+	 * a. all events in a group
+	 *    perf stat -e "{instructions,topdown-retiring,slots}" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *          15,066,240     slots
+	 *          1,899,760      instructions
+	 *          2,126,998      topdown-retiring
+	 * b. all events not in a group
+	 *    perf stat -e "instructions,topdown-retiring,slots" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *          2,045,561      instructions
+	 *          17,108,370     slots
+	 *          2,281,116      topdown-retiring
+	 * c. slots event in a group but topdown metrics events outside the group
+	 *    perf stat -e "{instructions,slots},topdown-retiring" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *         20,323,878      slots
+	 *          2,634,884      instructions
+	 *          3,028,656      topdown-retiring
+	 * d. slots event and topdown metrics events in two groups
+	 *    perf stat -e "{instructions,slots},{topdown-retiring}" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *         26,319,024      slots
+	 *          2,427,791      instructions
+	 *          2,683,508      topdown-retiring
+	 *
+	 * If slots event and topdown metrics events are not in same group, the
+	 * topdown metrics events must be first event after the slots event group,
+	 * otherwise topdown metrics events can't be regrouped correctly, e.g.
+	 *
+	 * a. perf stat -e "{instructions,slots},cycles,topdown-retiring" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *         17,923,134      slots
+	 *          2,154,855      instructions
+	 *          3,015,058      cycles
+	 *    <not supported>      topdown-retiring
+	 *
+	 * if slots event and topdown metrics events are in two groups, the group which
+	 * has topdown metrics events must contain only the topdown metrics event,
+	 * otherwise topdown metrics event can't be regrouped correctly as well, e.g.
+	 *
+	 * a. perf stat -e "{instructions,slots},{topdown-retiring,cycles}" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *    Error:
+	 *    The sys_perf_event_open() syscall returned with 22 (Invalid argument) for
+	 *    event (topdown-retiring)
+	 */
 	if (topdown_sys_has_perf_metrics() &&
 	    (arch_evsel__must_be_in_group(lhs) || arch_evsel__must_be_in_group(rhs))) {
 		/* Ensure the topdown slots comes first. */
@@ -17,7 +72,12 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 		/* Followed by topdown events. */
 		if (arch_is_topdown_metrics(lhs) && !arch_is_topdown_metrics(rhs))
 			return -1;
-		if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs))
+		/*
+		 * Move topdown events forward only when topdown events
+		 * are not in same group with previous event.
+		 */
+		if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs) &&
+		    lhs->core.leader != rhs->core.leader)
 			return 1;
 	}
 

From 387892723ad4044ff139ad7433e4dd24f7cfe303 Mon Sep 17 00:00:00 2001
From: Dapeng Mi <dapeng1.mi@linux.intel.com>
Date: Fri, 13 Sep 2024 08:47:10 +0000
Subject: [PATCH 0045/1530] perf tests: Add leader sampling test in record
 tests

Add leader sampling test to validate event counts are captured into
record and the count value is consistent.

Suggested-by: Kan Liang <kan.liang@linux.intel.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20240913084712.13861-5-dapeng1.mi@linux.intel.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/record.sh | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index 048078ee2eca5..45baf79106403 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -17,6 +17,7 @@ skip_test_missing_symbol ${testsym}
 
 err=0
 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+script_output=$(mktemp /tmp/__perf_test.perf.data.XXXXX.script)
 testprog="perf test -w thloop"
 cpu_pmu_dir="/sys/bus/event_source/devices/cpu*"
 br_cntr_file="/caps/branch_counter_nr"
@@ -228,6 +229,32 @@ test_cgroup() {
   echo "Cgroup sampling test [Success]"
 }
 
+test_leader_sampling() {
+  echo "Basic leader sampling test"
+  if ! perf record -o "${perfdata}" -e "{branches,branches}:Su" perf test -w brstack 2> /dev/null
+  then
+    echo "Leader sampling [Failed record]"
+    err=1
+    return
+  fi
+  index=0
+  perf script -i "${perfdata}" > $script_output
+  while IFS= read -r line
+  do
+    # Check if the two branches counts are equal in each record
+    branches=$(echo $line | awk '{for(i=1;i<=NF;i++) if($i=="branches:") print $(i-1)}')
+    if [ $(($index%2)) -ne 0 ] && [ ${branches}x != ${prev_branches}x ]
+    then
+      echo "Leader sampling [Failed inconsistent branches count]"
+      err=1
+      return
+    fi
+    index=$(($index+1))
+    prev_branches=$branches
+  done < $script_output
+  echo "Basic leader sampling test [Success]"
+}
+
 # raise the limit of file descriptors to minimum
 if [[ $default_fd_limit -lt $min_fd_limit ]]; then
        ulimit -Sn $min_fd_limit
@@ -239,6 +266,7 @@ test_system_wide
 test_workload
 test_branch_counter
 test_cgroup
+test_leader_sampling
 
 # restore the default value
 ulimit -Sn $default_fd_limit

From 0836aa60083a478cbc788f19fd2f389574a921bf Mon Sep 17 00:00:00 2001
From: Dapeng Mi <dapeng1.mi@linux.intel.com>
Date: Fri, 13 Sep 2024 08:47:11 +0000
Subject: [PATCH 0046/1530] perf tests: Add topdown events counting and
 sampling tests

Add counting and leader sampling tests to verify topdown events including
raw format can be reordered correctly.

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20240913084712.13861-6-dapeng1.mi@linux.intel.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/record.sh | 17 +++++++++++++++++
 tools/perf/tests/shell/stat.sh   |  6 ++++++
 2 files changed, 23 insertions(+)

diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index 45baf79106403..8d6366d96883e 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -255,6 +255,22 @@ test_leader_sampling() {
   echo "Basic leader sampling test [Success]"
 }
 
+test_topdown_leader_sampling() {
+  echo "Topdown leader sampling test"
+  if ! perf stat -e "{slots,topdown-retiring}" true 2> /dev/null
+  then
+    echo "Topdown leader sampling [Skipped event parsing failed]"
+    return
+  fi
+  if ! perf record -o "${perfdata}" -e "{instructions,slots,topdown-retiring}:S" true 2> /dev/null
+  then
+    echo "Topdown leader sampling [Failed topdown events not reordered correctly]"
+    err=1
+    return
+  fi
+  echo "Topdown leader sampling test [Success]"
+}
+
 # raise the limit of file descriptors to minimum
 if [[ $default_fd_limit -lt $min_fd_limit ]]; then
        ulimit -Sn $min_fd_limit
@@ -267,6 +283,7 @@ test_workload
 test_branch_counter
 test_cgroup
 test_leader_sampling
+test_topdown_leader_sampling
 
 # restore the default value
 ulimit -Sn $default_fd_limit
diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh
index 5a2ca2bcf94d1..b90a35906ee7d 100755
--- a/tools/perf/tests/shell/stat.sh
+++ b/tools/perf/tests/shell/stat.sh
@@ -79,6 +79,12 @@ test_topdown_groups() {
     err=1
     return
   fi
+  if perf stat -e '{instructions,r400,r8000}' true 2>&1 | grep -E -q "<not supported>"
+  then
+    echo "Topdown event group test [Failed raw format slots not reordered first]"
+    err=1
+    return
+  fi
   echo "Topdown event group test [Success]"
 }
 

From 80f192724e314ba860206e51bc1e3bc1ac7f58dd Mon Sep 17 00:00:00 2001
From: Dapeng Mi <dapeng1.mi@linux.intel.com>
Date: Fri, 13 Sep 2024 08:47:12 +0000
Subject: [PATCH 0047/1530] perf tests: Add more topdown events regroup tests

Add more test cases to cover all supported topdown events regroup cases.

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20240913084712.13861-7-dapeng1.mi@linux.intel.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/stat.sh | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh
index b90a35906ee7d..f25ef468b8fca 100755
--- a/tools/perf/tests/shell/stat.sh
+++ b/tools/perf/tests/shell/stat.sh
@@ -73,9 +73,27 @@ test_topdown_groups() {
     err=1
     return
   fi
-  if perf stat -e '{topdown-retiring,slots}' true 2>&1 | grep -E -q "<not supported>"
+  if perf stat -e 'instructions,topdown-retiring,slots' true 2>&1 | grep -E -q "<not supported>"
   then
-    echo "Topdown event group test [Failed slots not reordered first]"
+    echo "Topdown event group test [Failed slots not reordered first in no-group case]"
+    err=1
+    return
+  fi
+  if perf stat -e '{instructions,topdown-retiring,slots}' true 2>&1 | grep -E -q "<not supported>"
+  then
+    echo "Topdown event group test [Failed slots not reordered first in single group case]"
+    err=1
+    return
+  fi
+  if perf stat -e '{instructions,slots},topdown-retiring' true 2>&1 | grep -E -q "<not supported>"
+  then
+    echo "Topdown event group test [Failed topdown metrics event not move into slots group]"
+    err=1
+    return
+  fi
+  if perf stat -e '{instructions,slots},{topdown-retiring}' true 2>&1 | grep -E -q "<not supported>"
+  then
+    echo "Topdown event group test [Failed topdown metrics group not merge into slots group]"
     err=1
     return
   fi

From 217fa3961a5915a12e4ef6982e593e5215f8499c Mon Sep 17 00:00:00 2001
From: Zhang Zekun <zhangzekun11@huawei.com>
Date: Sat, 7 Sep 2024 16:07:01 +0800
Subject: [PATCH 0048/1530] OPP: Remove unused declarations in header file

The definition of _update_set_required_opps() has been removed since
commit e37440e7e2c2 ("OPP: Call dev_pm_opp_set_opp() for required
OPPs").

Besides, the definition of _put_opp_list_kref() has been removed since
commit 03758d60265c ("opp: Replace list_kref with a local counter").
Let's remove the empty declarations in header file.

Signed-off-by: Zhang Zekun <zhangzekun11@huawei.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/opp/opp.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h
index cff1fabd1ae36..882e32f121d33 100644
--- a/drivers/opp/opp.h
+++ b/drivers/opp/opp.h
@@ -262,9 +262,7 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *o
 int _opp_add_v1(struct opp_table *opp_table, struct device *dev, struct dev_pm_opp_data *data, bool dynamic);
 void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, int last_cpu);
 struct opp_table *_add_opp_table_indexed(struct device *dev, int index, bool getclk);
-void _put_opp_list_kref(struct opp_table *opp_table);
 void _required_opps_available(struct dev_pm_opp *opp, int count);
-void _update_set_required_opps(struct opp_table *opp_table);
 
 static inline bool lazy_linking_pending(struct opp_table *opp_table)
 {

From 87146254f8108f42b1e9f272dca1deef2540d234 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Mon, 30 Sep 2024 17:47:19 +0200
Subject: [PATCH 0049/1530] pinctrl: renesas: rza2: Mark GPIOs as used

GPIOs showed up as unclaimed in debugfs, so they could be muxed to
something else even though they were in use.  Mark GPIOs as claimed when
in use to avoid that.

Reported-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Link: https://lore.kernel.org/2862093f7701dcaf29f37c0b2f9268234168338f.1727711124.git.geert+renesas@glider.be
---
 drivers/pinctrl/renesas/pinctrl-rza2.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/pinctrl/renesas/pinctrl-rza2.c b/drivers/pinctrl/renesas/pinctrl-rza2.c
index af689d7c117f3..dd1f8c29d3e75 100644
--- a/drivers/pinctrl/renesas/pinctrl-rza2.c
+++ b/drivers/pinctrl/renesas/pinctrl-rza2.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/of.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/pinctrl/pinmux.h>
 #include <linux/platform_device.h>
 
@@ -229,6 +230,8 @@ static const char * const rza2_gpio_names[] = {
 static struct gpio_chip chip = {
 	.names = rza2_gpio_names,
 	.base = -1,
+	.request = pinctrl_gpio_request,
+	.free = pinctrl_gpio_free,
 	.get_direction = rza2_chip_get_direction,
 	.direction_input = rza2_chip_direction_input,
 	.direction_output = rza2_chip_direction_output,

From a8130323587cea11e7f15ca7803f1b138d6683d5 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Mon, 30 Sep 2024 21:14:43 +0200
Subject: [PATCH 0050/1530] pinctrl: renesas: rza1: Mark GPIOs as used

GPIOs showed up as unclaimed, so they could be muxed to something else
even though they were in use. Mark GPIOs as claimed to avoid that.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/20240930191523.7030-2-wsa+renesas@sang-engineering.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rza1.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/pinctrl/renesas/pinctrl-rza1.c b/drivers/pinctrl/renesas/pinctrl-rza1.c
index 6527872813dc5..b1058504e0bb3 100644
--- a/drivers/pinctrl/renesas/pinctrl-rza1.c
+++ b/drivers/pinctrl/renesas/pinctrl-rza1.c
@@ -19,6 +19,7 @@
 #include <linux/ioport.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/pinctrl/pinconf-generic.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/pinctrl/pinmux.h>
@@ -750,6 +751,11 @@ static int rza1_pin_mux_single(struct rza1_pinctrl *rza1_pctl,
 static int rza1_gpio_request(struct gpio_chip *chip, unsigned int gpio)
 {
 	struct rza1_port *port = gpiochip_get_data(chip);
+	int ret;
+
+	ret = pinctrl_gpio_request(chip, gpio);
+	if (ret)
+		return ret;
 
 	rza1_pin_reset(port, gpio);
 
@@ -771,6 +777,7 @@ static void rza1_gpio_free(struct gpio_chip *chip, unsigned int gpio)
 	struct rza1_port *port = gpiochip_get_data(chip);
 
 	rza1_pin_reset(port, gpio);
+	pinctrl_gpio_free(chip, gpio);
 }
 
 static int rza1_gpio_get_direction(struct gpio_chip *chip, unsigned int gpio)

From 53205a7903666d35709954d9fb7370a8150d5e0e Mon Sep 17 00:00:00 2001
From: Dhruva Gole <d-gole@ti.com>
Date: Thu, 19 Sep 2024 18:43:40 +0530
Subject: [PATCH 0051/1530] dt-bindings: opp: operating-points-v2-ti-cpu:
 Describe opp-supported-hw

It seems like we missed migrating the complete information from the old
DT binding where we had described what the opp-supported-hw is supposed
to describe. Hence, bring back the description from the previous binding
to the current one along with a bit more context on what the values are
supposed to be.

Fixes: e576a9a8603f ("dt-bindings: cpufreq: Convert ti-cpufreq to json schema")
Signed-off-by: Dhruva Gole <d-gole@ti.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 .../opp/operating-points-v2-ti-cpu.yaml       | 20 ++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/opp/operating-points-v2-ti-cpu.yaml b/Documentation/devicetree/bindings/opp/operating-points-v2-ti-cpu.yaml
index fd0c8d5c5f3e7..624d1f3f1382f 100644
--- a/Documentation/devicetree/bindings/opp/operating-points-v2-ti-cpu.yaml
+++ b/Documentation/devicetree/bindings/opp/operating-points-v2-ti-cpu.yaml
@@ -45,7 +45,25 @@ patternProperties:
       clock-latency-ns: true
       opp-hz: true
       opp-microvolt: true
-      opp-supported-hw: true
+      opp-supported-hw:
+        items:
+          items:
+            - description:
+                The revision of the SoC the OPP is supported by.
+                This can be easily obtained from the datasheet of the
+                part being ordered/used. For example, it will be 0x01 for SR1.0
+
+            - description:
+                The eFuse bits that indicate the particular OPP is available.
+                The device datasheet has a table talking about Device Speed Grades.
+                This table is to be sorted with only the unique elements of the
+                MAXIMUM OPERATING FREQUENCY starting from the first row which
+                tells the lowest OPP, to the highest. The corresponding bits
+                need to be set based on N elements of speed grade the device supports.
+                So, if there are 3 possible unique MAXIMUM OPERATING FREQUENCY
+                in the table, then BIT(0) | (1) | (2) will be set, which means
+                the value shall be 0x7.
+
       opp-suspend: true
       turbo-mode: true
 

From 8f04019d71cb870ca40960777b1b4720483cabac Mon Sep 17 00:00:00 2001
From: Shen Lichuan <shenlichuan@vivo.com>
Date: Mon, 30 Sep 2024 10:33:44 +0800
Subject: [PATCH 0052/1530] firewire: Correct some typos

Fixed some confusing typos that were currently identified with codespell,
the details are as follows:

drivers/firewire/core-topology.c:59: containted ==> contained
drivers/firewire/core.h:83: reenable ==> re-enable
drivers/firewire/ohci.c:1387: apppends ==> appends
drivers/firewire/ohci.c:2216: superceded ==> superseded
drivers/firewire/ohci.c:2617: litte ==> little

Signed-off-by: Shen Lichuan <shenlichuan@vivo.com>
Link: https://lore.kernel.org/r/20240930023344.7535-1-shenlichuan@vivo.com
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
---
 drivers/firewire/core-topology.c | 2 +-
 drivers/firewire/core.h          | 2 +-
 drivers/firewire/ohci.c          | 6 +++---
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c
index 6adadb11962e3..baba31933667a 100644
--- a/drivers/firewire/core-topology.c
+++ b/drivers/firewire/core-topology.c
@@ -56,7 +56,7 @@ static struct fw_node *fw_node_create(u32 sid, int port_count, int color)
  * two cases: either the path goes through this node, in which case
  * the hop count is the sum of the two biggest child depths plus 2.
  * Or it could be the case that the max hop path is entirely
- * containted in a child tree, in which case the max hop count is just
+ * contained in a child tree, in which case the max hop count is just
  * the max hop count of this child.
  */
 static void update_hop_count(struct fw_node *node)
diff --git a/drivers/firewire/core.h b/drivers/firewire/core.h
index 0ae2c84ecafed..9b298af1cac0b 100644
--- a/drivers/firewire/core.h
+++ b/drivers/firewire/core.h
@@ -80,7 +80,7 @@ struct fw_card_driver {
 	/*
 	 * Allow the specified node ID to do direct DMA out and in of
 	 * host memory.  The card will disable this for all node when
-	 * a bus reset happens, so driver need to reenable this after
+	 * a bus reset happens, so driver need to re-enable this after
 	 * bus reset.  Returns 0 on success, -ENODEV if the card
 	 * doesn't support this, -ESTALE if the generation doesn't
 	 * match.
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 7ee55c2804ded..4dbd203602233 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -1384,7 +1384,7 @@ struct driver_data {
 };
 
 /*
- * This function apppends a packet to the DMA queue for transmission.
+ * This function appends a packet to the DMA queue for transmission.
  * Must always be called with the ochi->lock held to ensure proper
  * generation handling and locking around packet queue manipulation.
  */
@@ -2213,7 +2213,7 @@ static irqreturn_t irq_handler(int irq, void *data)
 
 	if (unlikely(param_debug > 0)) {
 		dev_notice_ratelimited(ohci->card.device,
-				       "The debug parameter is superceded by tracepoints events, and deprecated.");
+				       "The debug parameter is superseded by tracepoints events, and deprecated.");
 	}
 
 	/*
@@ -2614,7 +2614,7 @@ static int ohci_set_config_rom(struct fw_card *card,
 	 * ConfigRomHeader and BusOptions doesn't honor the
 	 * noByteSwapData bit, so with a be32 config rom, the
 	 * controller will load be32 values in to these registers
-	 * during the atomic update, even on litte endian
+	 * during the atomic update, even on little endian
 	 * architectures.  The workaround we use is to put a 0 in the
 	 * header quadlet; 0 is endian agnostic and means that the
 	 * config rom isn't ready yet.  In the bus reset tasklet we

From 067d9fd7eed2bde170cba8ed12f49fb68c4e78ae Mon Sep 17 00:00:00 2001
From: Sai Krishna Potthuri <sai.krishna.potthuri@amd.com>
Date: Fri, 6 Sep 2024 16:31:11 +0530
Subject: [PATCH 0053/1530] dt-bindings: pinctrl: Add support for Xilinx Versal
 platform

Add Xilinx Versal compatible string and corresponding groups, function and
pins properties to support pin controller features on Versal platform.

Signed-off-by: Sai Krishna Potthuri <sai.krishna.potthuri@amd.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/20240906110113.3154327-2-sai.krishna.potthuri@amd.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/xlnx,versal-pinctrl.yaml | 278 ++++++++++++++++++
 1 file changed, 278 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/xlnx,versal-pinctrl.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/xlnx,versal-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/xlnx,versal-pinctrl.yaml
new file mode 100644
index 0000000000000..55ece6a8be5ef
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/xlnx,versal-pinctrl.yaml
@@ -0,0 +1,278 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/xlnx,versal-pinctrl.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Xilinx Versal Pinctrl
+
+maintainers:
+  - Sai Krishna Potthuri <sai.krishna.potthuri@amd.com>
+
+description: |
+  Please refer to pinctrl-bindings.txt in this directory for details of the
+  common pinctrl bindings used by client devices, including the meaning of the
+  phrase "pin configuration node".
+
+  Versal's pin configuration nodes act as a container for an arbitrary number of
+  subnodes. Each of these subnodes represents some desired configuration for a
+  pin, a group, or a list of pins or groups. This configuration can include the
+  mux function to select on those pin(s)/group(s), and various pin configuration
+  parameters, such as pull-up, slew rate, etc.
+
+  Each configuration node can consist of multiple nodes describing the pinmux and
+  pinconf options. Those nodes can be pinmux nodes or pinconf nodes.
+
+properties:
+  compatible:
+    const: xlnx,versal-pinctrl
+
+patternProperties:
+  '^(.*-)?(default|gpio-grp)$':
+    type: object
+    patternProperties:
+      '^mux':
+        type: object
+        description:
+          Pinctrl node's client devices use subnodes for pin muxes,
+          which in turn use below standard properties.
+        $ref: pinmux-node.yaml#
+
+        properties:
+          pins:
+            description:
+              List of pins to select (either this or "groups" must be specified)
+            $ref: "#/$defs/pins/properties/pins"
+
+          groups:
+            description:
+              List of groups to select (either this or "pins" must be
+              specified), available groups for this subnode.
+            anyOf:
+              - pattern: '^((LPD|PMC)_)MIO([0-9]|[1-6][0-9]|7[0-7])$'
+              - $ref: "#/$defs/pins/properties/groups"
+
+          function:
+            description:
+              Specify the alternative function to be configured for the
+              given pin groups.
+            enum: [spi0, spi0_ss, spi1, spi1_ss, can0, can1, i2c0, i2c1, i2c_pmc, ttc0_clk,
+                   ttc0_wav, ttc1_clk, ttc1_wav, ttc2_clk, ttc2_wav, ttc3_clk, ttc3_wav, wwdt0,
+                   wwdt1, sysmon_i2c0, sysmon_i2c0_alrt, uart0, uart0_ctrl, uart1, uart1_ctrl,
+                   gpio0, gpio1, gpio2, emio0, gem0, gem1, trace0, trace0_clk, mdio0, mdio1, gem_tsu0,
+                   pcie0, smap0, usb0, sd0, sd0_pc, sd0_cd, sd0_wp, sd1, sd1_pc, sd1_wp, sd1_cd,
+                   ospi0, ospi0_ss, qspi0, qspi0_fbclk, qspi0_ss, test_clk, test_scan, tamper_trigger]
+
+        required:
+          - function
+
+        oneOf:
+          - required: [ groups ]
+          - required: [ pins ]
+
+        additionalProperties: false
+
+      '^conf':
+        type: object
+        description:
+          Pinctrl node's client devices use subnodes for pin configurations,
+          which in turn use the standard properties below.
+        allOf:
+          - $ref: pincfg-node.yaml#
+          - $ref: "#/$defs/pins"
+
+    additionalProperties: false
+
+allOf:
+  - $ref: pinctrl.yaml#
+
+required:
+  - compatible
+
+additionalProperties: false
+
+$defs:
+  pins:
+    properties:
+      groups:
+        description:
+          List of pin groups to select in this subnode.
+        items:
+          enum: [spi0_0_grp, spi0_1_grp, spi0_2_grp, spi0_3_grp, spi0_4_grp, spi0_5_grp,
+                 spi0_ss_0_grp, spi0_ss_1_grp, spi0_ss_2_grp, spi0_ss_3_grp, spi0_ss_4_grp,
+                 spi0_ss_5_grp, spi0_ss_6_grp, spi0_ss_7_grp, spi0_ss_8_grp, spi0_ss_9_grp,
+                 spi0_ss_10_grp, spi0_ss_11_grp, spi0_ss_12_grp, spi0_ss_13_grp, spi0_ss_14_grp,
+                 spi0_ss_15_grp, spi0_ss_16_grp, spi0_ss_17_grp, spi1_0_grp, spi1_1_grp,
+                 spi1_2_grp, spi1_3_grp, spi1_4_grp, spi1_5_grp, spi1_ss_0_grp, spi1_ss_1_grp,
+                 spi1_ss_2_grp, spi1_ss_3_grp, spi1_ss_4_grp, spi1_ss_5_grp, spi1_ss_6_grp,
+                 spi1_ss_7_grp, spi1_ss_8_grp, spi1_ss_9_grp, spi1_ss_10_grp, spi1_ss_11_grp,
+                 spi1_ss_12_grp, spi1_ss_13_grp, spi1_ss_14_grp, spi1_ss_15_grp, spi1_ss_16_grp
+                 spi1_ss_17_grp, can0_0_grp, can0_1_grp, can0_2_grp, can0_3_grp, can0_4_grp,
+                 can0_5_grp, can0_6_grp, can0_7_grp, can0_8_grp, can0_9_grp, can0_10_grp,
+                 can0_11_grp, can0_12_grp, can0_13_grp, can0_14_grp, can0_15_grp, can0_16_grp,
+                 can0_17_grp, can1_0_grp, can1_1_grp, can1_2_grp, can1_3_grp, can1_4_grp,
+                 can1_5_grp, can1_6_grp, can1_7_grp, can1_8_grp, can1_9_grp, can1_10_grp,
+                 can1_11_grp, can1_12_grp, can1_13_grp, can1_14_grp, can1_15_grp, can1_16_grp,
+                 can1_17_grp, can1_18_grp, i2c0_0_grp, i2c0_1_grp, i2c0_2_grp, i2c0_3_grp,
+                 i2c0_4_grp, i2c0_5_grp, i2c0_6_grp, i2c0_7_grp, i2c0_8_grp, i2c0_9_grp,
+                 i2c0_10_grp, i2c0_11_grp, i2c0_12_grp, i2c0_13_grp, i2c0_14_grp, i2c0_15_grp,
+                 i2c0_16_grp, i2c0_17_grp, i2c1_0_grp, i2c1_1_grp, i2c1_2_grp, i2c1_3_grp,
+                 i2c1_4_grp, i2c1_5_grp, i2c1_6_grp, i2c1_7_grp, i2c1_8_grp, i2c1_9_grp,
+                 i2c1_10_grp, i2c1_11_grp, i2c1_12_grp, i2c1_13_grp, i2c1_14_grp, i2c1_15_grp,
+                 i2c1_16_grp, i2c1_17_grp, i2c1_18_grp, i2c_pmc_0_grp, i2c_pmc_1_grp,
+                 i2c_pmc_2_grp, i2c_pmc_3_grp, i2c_pmc_4_grp, i2c_pmc_5_grp, i2c_pmc_6_grp,
+                 i2c_pmc_7_grp, i2c_pmc_8_grp, i2c_pmc_9_grp, i2c_pmc_10_grp, i2c_pmc_11_grp,
+                 i2c_pmc_12_grp, ttc0_clk_0_grp, ttc0_clk_1_grp, ttc0_clk_2_grp, ttc0_clk_3_grp,
+                 ttc0_clk_4_grp, ttc0_clk_5_grp, ttc0_clk_6_grp, ttc0_clk_7_grp, ttc0_clk_8_grp,
+                 ttc0_wav_0_grp, ttc0_wav_1_grp, ttc0_wav_2_grp, ttc0_wav_3_grp, ttc0_wav_4_grp,
+                 ttc0_wav_5_grp, ttc0_wav_6_grp, ttc0_wav_7_grp, ttc0_wav_8_grp, ttc1_clk_0_grp,
+                 ttc1_clk_1_grp, ttc1_clk_2_grp, ttc1_clk_3_grp, ttc1_clk_4_grp, ttc1_clk_5_grp,
+                 ttc1_clk_6_grp, ttc1_clk_7_grp, ttc1_clk_8_grp, ttc1_wav_0_grp, ttc1_wav_1_grp,
+                 ttc1_wav_2_grp, ttc1_wav_3_grp, ttc1_wav_4_grp, ttc1_wav_5_grp, ttc1_wav_6_grp,
+                 ttc1_wav_7_grp, ttc1_wav_8_grp, ttc2_clk_0_grp, ttc2_clk_1_grp, ttc2_clk_2_grp,
+                 ttc2_clk_3_grp, ttc2_clk_4_grp, ttc2_clk_5_grp, ttc2_clk_6_grp, ttc2_clk_7_grp,
+                 ttc2_clk_8_grp, ttc2_wav_0_grp, ttc2_wav_1_grp, ttc2_wav_2_grp, ttc2_wav_3_grp,
+                 ttc2_wav_4_grp, ttc2_wav_5_grp, ttc2_wav_6_grp, ttc2_wav_7_grp, ttc2_wav_8_grp,
+                 ttc3_clk_0_grp, ttc3_clk_1_grp, ttc3_clk_2_grp, ttc3_clk_3_grp, ttc3_clk_4_grp,
+                 ttc3_clk_5_grp, ttc3_clk_6_grp, ttc3_clk_7_grp, ttc3_clk_8_grp, ttc3_wav_0_grp,
+                 ttc3_wav_1_grp, ttc3_wav_2_grp, ttc3_wav_3_grp, ttc3_wav_4_grp, ttc3_wav_5_grp,
+                 ttc3_wav_6_grp, ttc3_wav_7_grp, ttc3_wav_8_grp, wwdt0_0_grp, wwdt0_1_grp,
+                 wwdt0_2_grp, wwdt0_3_grp, wwdt0_4_grp, wwdt0_5_grp, wwdt1_0_grp, wwdt1_1_grp,
+                 wwdt1_2_grp, wwdt1_3_grp, wwdt1_4_grp, wwdt1_5_grp, sysmon_i2c0_0_grp,
+                 sysmon_i2c0_1_grp, sysmon_i2c0_2_grp, sysmon_i2c0_3_grp, sysmon_i2c0_4_grp,
+                 sysmon_i2c0_5_grp, sysmon_i2c0_6_grp, sysmon_i2c0_7_grp, sysmon_i2c0_8_grp,
+                 sysmon_i2c0_9_grp, sysmon_i2c0_10_grp, sysmon_i2c0_11_grp, sysmon_i2c0_12_grp,
+                 sysmon_i2c0_13_grp, sysmon_i2c0_14_grp, sysmon_i2c0_15_grp,
+                 sysmon_i2c0_16_grp, sysmon_i2c0_17_grp, sysmon_i2c0_alrt_0_grp,
+                 sysmon_i2c0_alrt_1_grp, sysmon_i2c0_alrt_2_grp, sysmon_i2c0_alrt_3_grp,
+                 sysmon_i2c0_alrt_4_grp, sysmon_i2c0_alrt_5_grp, sysmon_i2c0_alrt_6_grp,
+                 sysmon_i2c0_alrt_7_grp, sysmon_i2c0_alrt_8_grp, sysmon_i2c0_alrt_9_grp,
+                 sysmon_i2c0_alrt_10_grp, sysmon_i2c0_alrt_11_grp, sysmon_i2c0_alrt_12_grp,
+                 sysmon_i2c0_alrt_13_grp, sysmon_i2c0_alrt_14_grp, sysmon_i2c0_alrt_15_grp,
+                 sysmon_i2c0_alrt_16_grp, sysmon_i2c0_alrt_17_grp, uart0_0_grp, uart0_1_grp,
+                 uart0_2_grp, uart0_3_grp, uart0_4_grp, uart0_5_grp, uart0_6_grp, uart0_7_grp,
+                 uart0_8_grp, uart0_ctrl_0_grp, uart0_ctrl_1_grp, uart0_ctrl_2_grp,
+                 uart0_ctrl_3_grp, uart0_ctrl_4_grp, uart0_ctrl_5_grp, uart0_ctrl_6_grp,
+                 uart0_ctrl_7_grp, uart0_ctrl_8_grp, uart1_0_grp, uart1_1_grp, uart1_2_grp,
+                 uart1_3_grp, uart1_4_grp, uart1_5_grp, uart1_6_grp, uart1_7_grp, uart1_8_grp,
+                 uart1_ctrl_0_grp, uart1_ctrl_1_grp, uart1_ctrl_2_grp, uart1_ctrl_3_grp,
+                 uart1_ctrl_4_grp, uart1_ctrl_5_grp, uart1_ctrl_6_grp, uart1_ctrl_7_grp,
+                 uart1_ctrl_8_grp, gpio0_0_grp, gpio0_1_grp, gpio0_2_grp, gpio0_3_grp,
+                 gpio0_4_grp, gpio0_5_grp, gpio0_6_grp, gpio0_7_grp, gpio0_8_grp, gpio0_9_grp,
+                 gpio0_10_grp, gpio0_11_grp, gpio0_12_grp, gpio0_13_grp, gpio0_14_grp,
+                 gpio0_15_grp, gpio0_16_grp, gpio0_17_grp, gpio0_18_grp, gpio0_19_grp,
+                 gpio0_20_grp, gpio0_21_grp, gpio0_22_grp, gpio0_23_grp, gpio0_24_grp,
+                 gpio0_25_grp, gpio1_0_grp, gpio1_1_grp, gpio1_2_grp, gpio1_3_grp, gpio1_4_grp,
+                 gpio1_5_grp, gpio1_6_grp, gpio1_7_grp, gpio1_8_grp, gpio1_9_grp,
+                 gpio1_10_grp, gpio1_11_grp, gpio1_12_grp, gpio1_13_grp, gpio1_14_grp,
+                 gpio1_15_grp, gpio1_16_grp, gpio1_17_grp, gpio1_18_grp, gpio1_19_grp,
+                 gpio1_20_grp, gpio1_21_grp, gpio1_22_grp, gpio1_23_grp, gpio1_24_grp,
+                 gpio1_25_grp, gpio2_0_grp, gpio2_1_grp, gpio2_2_grp, gpio2_3_grp, gpio2_4_grp,
+                 gpio2_5_grp, gpio2_6_grp, gpio2_7_grp, gpio2_8_grp, gpio2_9_grp, gpio2_10_grp,
+                 gpio2_11_grp, gpio2_12_grp, gpio2_13_grp, gpio2_14_grp, gpio2_15_grp,
+                 gpio2_16_grp, gpio2_17_grp, gpio2_18_grp, gpio2_19_grp, gpio2_20_grp,
+                 gpio2_21_grp, gpio2_22_grp, gpio2_23_grp, gpio2_24_grp, gpio2_25_grp,
+                 emio0_0_grp, emio0_1_grp, emio0_2_grp, emio0_3_grp, emio0_4_grp, emio0_5_grp,
+                 emio0_6_grp, emio0_7_grp, emio0_8_grp, emio0_9_grp, emio0_10_grp,
+                 emio0_11_grp, emio0_12_grp, emio0_13_grp, emio0_14_grp, emio0_15_grp,
+                 emio0_16_grp, emio0_17_grp, emio0_18_grp, emio0_19_grp, emio0_20_grp,
+                 emio0_21_grp, emio0_22_grp, emio0_23_grp, emio0_24_grp, emio0_25_grp,
+                 emio0_26_grp, emio0_27_grp, emio0_28_grp, emio0_29_grp, emio0_30_grp,
+                 emio0_31_grp, emio0_32_grp, emio0_33_grp, emio0_34_grp, emio0_35_grp,
+                 emio0_36_grp, emio0_37_grp, emio0_38_grp, emio0_39_grp, emio0_40_grp,
+                 emio0_41_grp, emio0_42_grp, emio0_43_grp, emio0_44_grp, emio0_45_grp,
+                 emio0_46_grp, emio0_47_grp, emio0_48_grp, emio0_49_grp, emio0_50_grp,
+                 emio0_51_grp, emio0_52_grp, emio0_53_grp, emio0_54_grp, emio0_55_grp,
+                 emio0_56_grp, emio0_57_grp, emio0_58_grp, emio0_59_grp, emio0_60_grp,
+                 emio0_61_grp, emio0_62_grp, emio0_63_grp, emio0_64_grp, emio0_65_grp,
+                 emio0_66_grp, emio0_67_grp, emio0_68_grp, emio0_69_grp, emio0_70_grp,
+                 emio0_71_grp, emio0_72_grp, emio0_73_grp, emio0_74_grp, emio0_75_grp,
+                 emio0_76_grp, emio0_77_grp, gem0_0_grp, gem0_1_grp, gem1_0_grp, gem1_1_grp,
+                 trace0_0_grp, trace0_1_grp, trace0_2_grp, trace0_clk_0_grp, trace0_clk_1_grp,
+                 trace0_clk_2_grp, mdio0_0_grp, mdio0_1_grp, mdio1_0_grp, mdio1_1_grp,
+                 gem_tsu0_0_grp, gem_tsu0_1_grp, gem_tsu0_2_grp, gem_tsu0_3_grp, pcie0_0_grp,
+                 pcie0_1_grp, pcie0_2_grp, smap0_0_grp, usb0_0_grp, sd0_0_grp, sd0_1_grp,
+                 sd0_2_grp, sd0_3_grp, sd0_4_grp, sd0_5_grp, sd0_6_grp, sd0_7_grp, sd0_8_grp,
+                 sd0_9_grp, sd0_10_grp, sd0_11_grp, sd0_12_grp, sd0_13_grp, sd0_14_grp,
+                 sd0_15_grp, sd0_16_grp, sd0_17_grp, sd0_18_grp, sd0_19_grp, sd0_20_grp,
+                 sd0_21_grp, sd0_pc_0_grp, sd0_pc_1_grp, sd0_cd_0_grp, sd0_cd_1_grp,
+                 sd0_wp_0_grp, sd0_wp_1_grp, sd1_0_grp, sd1_1_grp, sd1_2_grp, sd1_3_grp,
+                 sd1_4_grp, sd1_5_grp, sd1_6_grp, sd1_7_grp, sd1_8_grp, sd1_9_grp, sd1_10_grp,
+                 sd1_11_grp, sd1_12_grp, sd1_13_grp, sd1_14_grp, sd1_15_grp, sd1_16_grp,
+                 sd1_17_grp, sd1_18_grp, sd1_19_grp, sd1_20_grp, sd1_21_grp, sd1_pc_0_grp,
+                 sd1_pc_1_grp, sd1_cd_0_grp, sd1_cd_1_grp, sd1_wp_0_grp, sd1_wp_1_grp,
+                 ospi0_0_grp, ospi0_ss_0_grp, qspi0_0_grp, qspi0_fbclk_0_grp, qspi0_ss_0_grp,
+                 test_clk_0_grp, test_scan_0_grp, tamper_trigger_0_grp]
+        minItems: 1
+        maxItems: 78
+
+      pins:
+        description:
+          List of pin names to select in this subnode.
+        items:
+          pattern: '^((LPD|PMC)_)MIO([0-9]|[1-6][0-9]|7[0-7])$'
+        minItems: 1
+        maxItems: 78
+
+      bias-pull-up: true
+      bias-pull-down: true
+      bias-disable: true
+      input-schmitt-enable: true
+      input-schmitt-disable: true
+      bias-high-impedance: true
+      low-power-enable: true
+      low-power-disable: true
+
+      slew-rate:
+        enum: [0, 1]
+
+      output-enable:
+        description:
+          This will internally disable the tri-state for MIO pins.
+
+      drive-strength:
+        description:
+          Selects the drive strength for MIO pins, in mA.
+        enum: [2, 4, 8, 12]
+
+      power-source:
+        enum: [0, 1]
+
+    oneOf:
+      - required: [ groups ]
+      - required: [ pins ]
+
+    additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/pinctrl/pinctrl-zynqmp.h>
+    pinctrl {
+      compatible = "xlnx,versal-pinctrl";
+
+      uart0-default {
+        mux {
+          groups = "uart0_4_grp", "uart0_5_grp";
+          function = "uart0";
+        };
+
+        conf {
+          groups = "uart0_4_grp";
+          slew-rate = <SLEW_RATE_SLOW>;
+          power-source = <IO_STANDARD_LVCMOS18>;
+        };
+
+        conf-rx {
+          pins = "PMC_MIO42";
+          bias-pull-up;
+        };
+
+        conf-tx {
+          pins = "PMC_MIO43";
+          bias-disable;
+          input-schmitt-disable;
+        };
+      };
+    };
+
+...

From 86b9ce0a8a6cf9397503920cd5412d207a93fae9 Mon Sep 17 00:00:00 2001
From: Sai Krishna Potthuri <sai.krishna.potthuri@amd.com>
Date: Fri, 6 Sep 2024 16:31:12 +0530
Subject: [PATCH 0054/1530] firmware: xilinx: Add Pinctrl Get Attribute ID

Add Pinctrl Get Attribute ID to the query ids list.

Signed-off-by: Sai Krishna Potthuri <sai.krishna.potthuri@amd.com>
Link: https://lore.kernel.org/20240906110113.3154327-3-sai.krishna.potthuri@amd.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/firmware/xlnx-zynqmp.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index d7d07afc0532d..3b4ce4ec5d3fc 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -238,6 +238,7 @@ enum pm_query_id {
 	PM_QID_PINCTRL_GET_PIN_GROUPS = 11,
 	PM_QID_CLOCK_GET_NUM_CLOCKS = 12,
 	PM_QID_CLOCK_GET_MAX_DIVISOR = 13,
+	PM_QID_PINCTRL_GET_ATTRIBUTES = 15,
 };
 
 enum rpu_oper_mode {

From 4c9e8da4e7a6ea6e2ba6626536d241a29fd7c871 Mon Sep 17 00:00:00 2001
From: Sai Krishna Potthuri <sai.krishna.potthuri@amd.com>
Date: Fri, 6 Sep 2024 16:31:13 +0530
Subject: [PATCH 0055/1530] pinctrl: pinctrl-zynqmp: Add support for Versal
 platform

Add Pinctrl support for Xilinx Versal platform.
Driver checks for firmware support to retrieve the Pin information, if it
is supported then proceed further otherwise it returns error saying
operation not supported. Latest Xilinx Platform Management Firmware must
be used to make use of the Pinctrl driver for Versal platform.

Signed-off-by: Sai Krishna Potthuri <sai.krishna.potthuri@amd.com>
Link: https://lore.kernel.org/20240906110113.3154327-4-sai.krishna.potthuri@amd.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-zynqmp.c | 97 ++++++++++++++++++++++++++++++--
 1 file changed, 92 insertions(+), 5 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-zynqmp.c b/drivers/pinctrl/pinctrl-zynqmp.c
index 3c6d56fdb8c96..2b9f8db49a153 100644
--- a/drivers/pinctrl/pinctrl-zynqmp.c
+++ b/drivers/pinctrl/pinctrl-zynqmp.c
@@ -10,6 +10,7 @@
 
 #include <dt-bindings/pinctrl/pinctrl-zynqmp.h>
 
+#include <linux/bitfield.h>
 #include <linux/bitmap.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -44,6 +45,12 @@
 #define DRIVE_STRENGTH_8MA	8
 #define DRIVE_STRENGTH_12MA	12
 
+#define VERSAL_LPD_PIN_PREFIX		"LPD_MIO"
+#define VERSAL_PMC_PIN_PREFIX		"PMC_MIO"
+
+#define VERSAL_PINCTRL_ATTR_NODETYPE_MASK	GENMASK(19, 14)
+#define VERSAL_PINCTRL_NODETYPE_LPD_MIO		BIT(0)
+
 /**
  * struct zynqmp_pmux_function - a pinmux function
  * @name:	Name of the pin mux function
@@ -93,6 +100,8 @@ struct zynqmp_pctrl_group {
 };
 
 static struct pinctrl_desc zynqmp_desc;
+static u32 family_code;
+static u32 sub_family_code;
 
 static int zynqmp_pctrl_get_groups_count(struct pinctrl_dev *pctldev)
 {
@@ -596,8 +605,12 @@ static int zynqmp_pinctrl_prepare_func_groups(struct device *dev, u32 fid,
 			if (!groups[resp[i]].name)
 				return -ENOMEM;
 
-			for (pin = 0; pin < groups[resp[i]].npins; pin++)
-				__set_bit(groups[resp[i]].pins[pin], used_pins);
+			for (pin = 0; pin < groups[resp[i]].npins; pin++) {
+				if (family_code == ZYNQMP_FAMILY_CODE)
+					__set_bit(groups[resp[i]].pins[pin], used_pins);
+				else
+					__set_bit((u8)groups[resp[i]].pins[pin] - 1, used_pins);
+			}
 		}
 	}
 done:
@@ -873,6 +886,70 @@ static int zynqmp_pinctrl_prepare_pin_desc(struct device *dev,
 	return 0;
 }
 
+static int versal_pinctrl_get_attributes(u32 pin_idx, u32 *response)
+{
+	struct zynqmp_pm_query_data qdata = {0};
+	u32 payload[PAYLOAD_ARG_CNT];
+	int ret;
+
+	qdata.qid = PM_QID_PINCTRL_GET_ATTRIBUTES;
+	qdata.arg1 = pin_idx;
+
+	ret = zynqmp_pm_query_data(qdata, payload);
+	if (ret)
+		return ret;
+
+	memcpy(response, &payload[1], sizeof(*response));
+
+	return 0;
+}
+
+static int versal_pinctrl_prepare_pin_desc(struct device *dev,
+					   const struct pinctrl_pin_desc **zynqmp_pins,
+					   unsigned int *npins)
+{
+	u32 lpd_mio_pins = 0, attr, nodetype;
+	struct pinctrl_pin_desc *pins, *pin;
+	int ret, i;
+
+	ret = zynqmp_pm_is_function_supported(PM_QUERY_DATA, PM_QID_PINCTRL_GET_ATTRIBUTES);
+	if (ret)
+		return ret;
+
+	ret = zynqmp_pinctrl_get_num_pins(npins);
+	if (ret)
+		return ret;
+
+	pins = devm_kzalloc(dev, sizeof(*pins) * *npins, GFP_KERNEL);
+	if (!pins)
+		return -ENOMEM;
+
+	for (i = 0; i < *npins; i++) {
+		ret = versal_pinctrl_get_attributes(i, &attr);
+		if (ret)
+			return ret;
+
+		pin = &pins[i];
+		pin->number = attr;
+		nodetype = FIELD_GET(VERSAL_PINCTRL_ATTR_NODETYPE_MASK, attr);
+		if (nodetype == VERSAL_PINCTRL_NODETYPE_LPD_MIO) {
+			pin->name = devm_kasprintf(dev, GFP_KERNEL, "%s%d",
+						   VERSAL_LPD_PIN_PREFIX, i);
+			lpd_mio_pins++;
+		} else {
+			pin->name = devm_kasprintf(dev, GFP_KERNEL, "%s%d",
+						   VERSAL_PMC_PIN_PREFIX, i - lpd_mio_pins);
+		}
+
+		if (!pin->name)
+			return -ENOMEM;
+	}
+
+	*zynqmp_pins = pins;
+
+	return 0;
+}
+
 static int zynqmp_pinctrl_probe(struct platform_device *pdev)
 {
 	struct zynqmp_pinctrl *pctrl;
@@ -882,9 +959,18 @@ static int zynqmp_pinctrl_probe(struct platform_device *pdev)
 	if (!pctrl)
 		return -ENOMEM;
 
-	ret = zynqmp_pinctrl_prepare_pin_desc(&pdev->dev,
-					      &zynqmp_desc.pins,
-					      &zynqmp_desc.npins);
+	ret = zynqmp_pm_get_family_info(&family_code, &sub_family_code);
+	if (ret < 0)
+		return ret;
+
+	if (family_code == ZYNQMP_FAMILY_CODE) {
+		ret = zynqmp_pinctrl_prepare_pin_desc(&pdev->dev, &zynqmp_desc.pins,
+						      &zynqmp_desc.npins);
+	} else {
+		ret = versal_pinctrl_prepare_pin_desc(&pdev->dev, &zynqmp_desc.pins,
+						      &zynqmp_desc.npins);
+	}
+
 	if (ret) {
 		dev_err(&pdev->dev, "pin desc prepare fail with %d\n", ret);
 		return ret;
@@ -907,6 +993,7 @@ static int zynqmp_pinctrl_probe(struct platform_device *pdev)
 
 static const struct of_device_id zynqmp_pinctrl_of_match[] = {
 	{ .compatible = "xlnx,zynqmp-pinctrl" },
+	{ .compatible = "xlnx,versal-pinctrl" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, zynqmp_pinctrl_of_match);

From c919ca8617dc347f1c3a9f411cd4bc93f5da42fe Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 4 Sep 2024 11:08:53 +0200
Subject: [PATCH 0056/1530] pinctrl: k210: Make (p)clk local to
 k210_fpioa_probe()

There were never any users of k210_fpioa_data.clk and
k210_fpioa_data.pclk outside k210_fpioa_probe().

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/77f543046d4d5c19206f829ddcf8e093d3e3f6da.1725440917.git.geert+renesas@glider.be
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-k210.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-k210.c b/drivers/pinctrl/pinctrl-k210.c
index 0f6b55fec31de..caf20215aaba5 100644
--- a/drivers/pinctrl/pinctrl-k210.c
+++ b/drivers/pinctrl/pinctrl-k210.c
@@ -96,8 +96,6 @@ struct k210_fpioa_data {
 	struct k210_fpioa __iomem *fpioa;
 	struct regmap *sysctl_map;
 	u32 power_offset;
-	struct clk *clk;
-	struct clk *pclk;
 };
 
 #define K210_PIN_NAME(i)	("IO_" #i)
@@ -925,6 +923,7 @@ static int k210_fpioa_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	struct k210_fpioa_data *pdata;
+	struct clk *clk, *pclk;
 
 	dev_info(dev, "K210 FPIOA pin controller\n");
 
@@ -939,13 +938,13 @@ static int k210_fpioa_probe(struct platform_device *pdev)
 	if (IS_ERR(pdata->fpioa))
 		return PTR_ERR(pdata->fpioa);
 
-	pdata->clk = devm_clk_get_enabled(dev, "ref");
-	if (IS_ERR(pdata->clk))
-		return PTR_ERR(pdata->clk);
+	clk = devm_clk_get_enabled(dev, "ref");
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
 
-	pdata->pclk = devm_clk_get_optional_enabled(dev, "pclk");
-	if (IS_ERR(pdata->pclk))
-		return PTR_ERR(pdata->pclk);
+	pclk = devm_clk_get_optional_enabled(dev, "pclk");
+	if (IS_ERR(pclk))
+		return PTR_ERR(pclk);
 
 	pdata->sysctl_map =
 		syscon_regmap_lookup_by_phandle_args(np,

From 88dbf374a5748c09e2a1eef3f3ad43cc73c6f69a Mon Sep 17 00:00:00 2001
From: Nikunj Kela <quic_nkela@quicinc.com>
Date: Thu, 5 Sep 2024 13:02:18 -0700
Subject: [PATCH 0057/1530] dt-bindings: pinctrl: Add SA8255p TLMM

Add compatible for TLMM block representing support on SA8255p.

SA8255p uses the same TLMM block as SA8775p however the ownership
of pins are split between Firmware VM and Linux VM on SA8255p. For
example, pins used by UART are owned and configured by Firmware VM
while pins used by ethernet are owned and configured by Linux VM.
Therefore, adding a sa8255p specific compatible to mark the difference.

Signed-off-by: Nikunj Kela <quic_nkela@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/20240905200218.3810712-1-quic_nkela@quicinc.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml    | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml
index e9abbf2c0689b..749dbc563ac50 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml
@@ -17,7 +17,13 @@ allOf:
 
 properties:
   compatible:
-    const: qcom,sa8775p-tlmm
+    oneOf:
+      - items:
+          - enum:
+              - qcom,sa8255p-tlmm
+          - const: qcom,sa8775p-tlmm
+      - items:
+          - const: qcom,sa8775p-tlmm
 
   reg:
     maxItems: 1

From 17d210018914024c97dfe08f7e7e49e65785b3a9 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Mon, 6 May 2024 12:23:53 +0200
Subject: [PATCH 0058/1530] ARM: imx: Allow user to disable pinctrl

Making pinctrl drivers and subsequently the pinctrl framework
user-controllable, allows building a kernel without this.
While in many (most) cases, this could make the system unbootable, it
does allow building smaller kernels for those situations where picntrl
is not needed.

One such situation is when building a kernel for NXP LS1021A systems,
which does not have run-time controllable pinctrl, so pinctrl framework
and drivers are 100% dead-weight.

Signed-off-by: Esben Haabendal <esben@geanix.com>
Acked-by: Shawn Guo <shawnguo@kernel.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/20240506-imx-pinctrl-optional-v2-1-bdff75085156@geanix.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 arch/arm/mach-imx/Kconfig         | 16 ----------------
 drivers/pinctrl/freescale/Kconfig | 15 +++++++++++++++
 2 files changed, 15 insertions(+), 16 deletions(-)

diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index ab767f0599295..e4fe059cd8614 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -6,7 +6,6 @@ menuconfig ARCH_MXC
 	select CLKSRC_IMX_GPT
 	select GENERIC_IRQ_CHIP
 	select GPIOLIB
-	select PINCTRL
 	select PM_OPP if PM
 	select SOC_BUS
 	select SRAM
@@ -49,7 +48,6 @@ config SOC_IMX31
 config SOC_IMX35
 	bool "i.MX35 support"
 	select MXC_AVIC
-	select PINCTRL_IMX35
 	help
 	  This enables support for Freescale i.MX35 processor
 
@@ -61,7 +59,6 @@ config SOC_IMX1
 	bool "i.MX1 support"
 	select CPU_ARM920T
 	select MXC_AVIC
-	select PINCTRL_IMX1
 	help
 	  This enables support for Freescale i.MX1 processor
 
@@ -73,7 +70,6 @@ config SOC_IMX25
 	bool "i.MX25 support"
 	select CPU_ARM926T
 	select MXC_AVIC
-	select PINCTRL_IMX25
 	help
 	  This enables support for Freescale i.MX25 processor
 
@@ -81,7 +77,6 @@ config SOC_IMX27
 	bool "i.MX27 support"
 	select CPU_ARM926T
 	select MXC_AVIC
-	select PINCTRL_IMX27
 	help
 	  This enables support for Freescale i.MX27 processor
 
@@ -98,7 +93,6 @@ config SOC_IMX5
 
 config SOC_IMX50
 	bool "i.MX50 support"
-	select PINCTRL_IMX50
 	select SOC_IMX5
 
 	help
@@ -106,14 +100,12 @@ config SOC_IMX50
 
 config SOC_IMX51
 	bool "i.MX51 support"
-	select PINCTRL_IMX51
 	select SOC_IMX5
 	help
 	  This enables support for Freescale i.MX51 processor
 
 config SOC_IMX53
 	bool "i.MX53 support"
-	select PINCTRL_IMX53
 	select SOC_IMX5
 
 	help
@@ -137,7 +129,6 @@ config SOC_IMX6Q
 	select ARM_ERRATA_775420
 	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_TWD
-	select PINCTRL_IMX6Q
 	select SOC_IMX6
 
 	help
@@ -147,7 +138,6 @@ config SOC_IMX6SL
 	bool "i.MX6 SoloLite support"
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_775420
-	select PINCTRL_IMX6SL
 	select SOC_IMX6
 
 	help
@@ -157,7 +147,6 @@ config SOC_IMX6SLL
 	bool "i.MX6 SoloLiteLite support"
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_775420
-	select PINCTRL_IMX6SLL
 	select SOC_IMX6
 
 	help
@@ -167,7 +156,6 @@ config SOC_IMX6SX
 	bool "i.MX6 SoloX support"
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_775420
-	select PINCTRL_IMX6SX
 	select SOC_IMX6
 
 	help
@@ -175,7 +163,6 @@ config SOC_IMX6SX
 
 config SOC_IMX6UL
 	bool "i.MX6 UltraLite support"
-	select PINCTRL_IMX6UL
 	select SOC_IMX6
 	select ARM_ERRATA_814220
 
@@ -211,7 +198,6 @@ config SOC_IMX7D_CM4
 
 config SOC_IMX7D
 	bool "i.MX7 Dual support"
-	select PINCTRL_IMX7D
 	select SOC_IMX7D_CA7 if ARCH_MULTI_V7
 	select SOC_IMX7D_CM4 if ARM_SINGLE_ARMV7M
 	select ARM_ERRATA_814220 if ARCH_MULTI_V7
@@ -221,7 +207,6 @@ config SOC_IMX7D
 config SOC_IMX7ULP
 	bool "i.MX7ULP support"
 	select CLKSRC_IMX_TPM
-	select PINCTRL_IMX7ULP
 	select SOC_IMX7D_CA7 if ARCH_MULTI_V7
 	select SOC_IMX7D_CM4 if ARM_SINGLE_ARMV7M
 	help
@@ -237,7 +222,6 @@ config SOC_IMXRT
 config SOC_VF610
 	bool "Vybrid Family VF610 support"
 	select ARM_GIC if ARCH_MULTI_V7
-	select PINCTRL_VF610
 
 	help
 	  This enables support for Freescale Vybrid VF610 processor.
diff --git a/drivers/pinctrl/freescale/Kconfig b/drivers/pinctrl/freescale/Kconfig
index 3b59d71890045..f3ad1049bc4a0 100644
--- a/drivers/pinctrl/freescale/Kconfig
+++ b/drivers/pinctrl/freescale/Kconfig
@@ -31,6 +31,7 @@ config PINCTRL_IMX1_CORE
 config PINCTRL_IMX1
 	bool "IMX1 pinctrl driver"
 	depends on SOC_IMX1
+	default SOC_IMX1
 	select PINCTRL_IMX1_CORE
 	help
 	  Say Y here to enable the imx1 pinctrl driver
@@ -38,6 +39,7 @@ config PINCTRL_IMX1
 config PINCTRL_IMX27
 	bool "IMX27 pinctrl driver"
 	depends on SOC_IMX27
+	default SOC_IMX27
 	select PINCTRL_IMX1_CORE
 	help
 	  Say Y here to enable the imx27 pinctrl driver
@@ -47,6 +49,7 @@ config PINCTRL_IMX25
 	bool "IMX25 pinctrl driver"
 	depends on OF
 	depends on SOC_IMX25
+	default SOC_IMX25
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx25 pinctrl driver
@@ -54,6 +57,7 @@ config PINCTRL_IMX25
 config PINCTRL_IMX35
 	bool "IMX35 pinctrl driver"
 	depends on SOC_IMX35
+	default SOC_IMX35
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx35 pinctrl driver
@@ -61,6 +65,7 @@ config PINCTRL_IMX35
 config PINCTRL_IMX50
 	bool "IMX50 pinctrl driver"
 	depends on SOC_IMX50
+	default SOC_IMX50
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx50 pinctrl driver
@@ -68,6 +73,7 @@ config PINCTRL_IMX50
 config PINCTRL_IMX51
 	bool "IMX51 pinctrl driver"
 	depends on SOC_IMX51
+	default SOC_IMX51
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx51 pinctrl driver
@@ -75,6 +81,7 @@ config PINCTRL_IMX51
 config PINCTRL_IMX53
 	bool "IMX53 pinctrl driver"
 	depends on SOC_IMX53
+	default SOC_IMX53
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx53 pinctrl driver
@@ -82,6 +89,7 @@ config PINCTRL_IMX53
 config PINCTRL_IMX6Q
 	bool "IMX6Q/DL pinctrl driver"
 	depends on SOC_IMX6Q
+	default SOC_IMX6Q
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx6q/dl pinctrl driver
@@ -89,6 +97,7 @@ config PINCTRL_IMX6Q
 config PINCTRL_IMX6SL
 	bool "IMX6SL pinctrl driver"
 	depends on SOC_IMX6SL
+	default SOC_IMX6SL
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx6sl pinctrl driver
@@ -96,6 +105,7 @@ config PINCTRL_IMX6SL
 config PINCTRL_IMX6SLL
 	bool "IMX6SLL pinctrl driver"
 	depends on SOC_IMX6SLL
+	default SOC_IMX6SLL
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx6sll pinctrl driver
@@ -103,6 +113,7 @@ config PINCTRL_IMX6SLL
 config PINCTRL_IMX6SX
 	bool "IMX6SX pinctrl driver"
 	depends on SOC_IMX6SX
+	default SOC_IMX6SX
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx6sx pinctrl driver
@@ -110,6 +121,7 @@ config PINCTRL_IMX6SX
 config PINCTRL_IMX6UL
 	bool "IMX6UL pinctrl driver"
 	depends on SOC_IMX6UL
+	default SOC_IMX6UL
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx6ul pinctrl driver
@@ -117,6 +129,7 @@ config PINCTRL_IMX6UL
 config PINCTRL_IMX7D
 	bool "IMX7D pinctrl driver"
 	depends on SOC_IMX7D
+	default SOC_IMX7D
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx7d pinctrl driver
@@ -124,6 +137,7 @@ config PINCTRL_IMX7D
 config PINCTRL_IMX7ULP
 	bool "IMX7ULP pinctrl driver"
 	depends on SOC_IMX7ULP
+	default SOC_IMX7ULP
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx7ulp pinctrl driver
@@ -212,6 +226,7 @@ config PINCTRL_IMX93
 config PINCTRL_VF610
 	bool "Freescale Vybrid VF610 pinctrl driver"
 	depends on SOC_VF610
+	default SOC_VF610
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the Freescale Vybrid VF610 pinctrl driver

From aea2dd7a6f9e8bd8a6e04fd6fb18f6e5884ba9e9 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Mon, 6 May 2024 12:23:54 +0200
Subject: [PATCH 0059/1530] pinctrl: freescale: Use CONFIG_SOC_IMXRT to guard
 i.MX RT1xxx drivers

This aligns with the use of SOC_IMX* as dependencies for all the other
mach-imx pinctrl drivers. Enabling i.MX RT pinctrl drivers for a kernel
with out i.MX RT SOC support is pointless.

Signed-off-by: Esben Haabendal <esben@geanix.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/20240506-imx-pinctrl-optional-v2-2-bdff75085156@geanix.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/freescale/Kconfig | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/freescale/Kconfig b/drivers/pinctrl/freescale/Kconfig
index f3ad1049bc4a0..a60f3cddc2198 100644
--- a/drivers/pinctrl/freescale/Kconfig
+++ b/drivers/pinctrl/freescale/Kconfig
@@ -204,7 +204,8 @@ config PINCTRL_IMX8ULP
 
 config PINCTRL_IMXRT1050
 	bool "IMXRT1050 pinctrl driver"
-	depends on ARCH_MXC
+	depends on SOC_IMXRT
+	default SOC_IMXRT
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imxrt1050 pinctrl driver
@@ -246,7 +247,7 @@ config PINCTRL_IMX28
 
 config PINCTRL_IMXRT1170
 	bool "IMXRT1170 pinctrl driver"
-	depends on ARCH_MXC
+	depends on SOC_IMXRT
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imxrt1170 pinctrl driver

From a55222b7a1327fabad71e1e61661077ab66bb98d Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Mon, 6 May 2024 12:23:55 +0200
Subject: [PATCH 0060/1530] pinctrl: freescale: enable use with COMPILE_TEST

Allow compile-testing of i.MX pinctrl drivers using CONFIG_COMPILE_TEST.

Signed-off-by: Esben Haabendal <esben@geanix.com>
Link: https://lore.kernel.org/20240506-imx-pinctrl-optional-v2-3-bdff75085156@geanix.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/freescale/Kconfig | 73 ++++++++++++++++++++-----------
 1 file changed, 47 insertions(+), 26 deletions(-)

diff --git a/drivers/pinctrl/freescale/Kconfig b/drivers/pinctrl/freescale/Kconfig
index a60f3cddc2198..4486f4a210684 100644
--- a/drivers/pinctrl/freescale/Kconfig
+++ b/drivers/pinctrl/freescale/Kconfig
@@ -30,7 +30,8 @@ config PINCTRL_IMX1_CORE
 
 config PINCTRL_IMX1
 	bool "IMX1 pinctrl driver"
-	depends on SOC_IMX1
+	depends on OF
+	depends on SOC_IMX1 || COMPILE_TEST
 	default SOC_IMX1
 	select PINCTRL_IMX1_CORE
 	help
@@ -38,7 +39,8 @@ config PINCTRL_IMX1
 
 config PINCTRL_IMX27
 	bool "IMX27 pinctrl driver"
-	depends on SOC_IMX27
+	depends on OF
+	depends on SOC_IMX27 || COMPILE_TEST
 	default SOC_IMX27
 	select PINCTRL_IMX1_CORE
 	help
@@ -48,7 +50,7 @@ config PINCTRL_IMX27
 config PINCTRL_IMX25
 	bool "IMX25 pinctrl driver"
 	depends on OF
-	depends on SOC_IMX25
+	depends on SOC_IMX25 || COMPILE_TEST
 	default SOC_IMX25
 	select PINCTRL_IMX
 	help
@@ -56,7 +58,8 @@ config PINCTRL_IMX25
 
 config PINCTRL_IMX35
 	bool "IMX35 pinctrl driver"
-	depends on SOC_IMX35
+	depends on OF
+	depends on SOC_IMX35 || COMPILE_TEST
 	default SOC_IMX35
 	select PINCTRL_IMX
 	help
@@ -64,7 +67,8 @@ config PINCTRL_IMX35
 
 config PINCTRL_IMX50
 	bool "IMX50 pinctrl driver"
-	depends on SOC_IMX50
+	depends on OF
+	depends on SOC_IMX50 || COMPILE_TEST
 	default SOC_IMX50
 	select PINCTRL_IMX
 	help
@@ -72,7 +76,8 @@ config PINCTRL_IMX50
 
 config PINCTRL_IMX51
 	bool "IMX51 pinctrl driver"
-	depends on SOC_IMX51
+	depends on OF
+	depends on SOC_IMX51 || COMPILE_TEST
 	default SOC_IMX51
 	select PINCTRL_IMX
 	help
@@ -80,7 +85,8 @@ config PINCTRL_IMX51
 
 config PINCTRL_IMX53
 	bool "IMX53 pinctrl driver"
-	depends on SOC_IMX53
+	depends on OF
+	depends on SOC_IMX53 || COMPILE_TEST
 	default SOC_IMX53
 	select PINCTRL_IMX
 	help
@@ -88,7 +94,8 @@ config PINCTRL_IMX53
 
 config PINCTRL_IMX6Q
 	bool "IMX6Q/DL pinctrl driver"
-	depends on SOC_IMX6Q
+	depends on OF
+	depends on SOC_IMX6Q || COMPILE_TEST
 	default SOC_IMX6Q
 	select PINCTRL_IMX
 	help
@@ -96,7 +103,8 @@ config PINCTRL_IMX6Q
 
 config PINCTRL_IMX6SL
 	bool "IMX6SL pinctrl driver"
-	depends on SOC_IMX6SL
+	depends on OF
+	depends on SOC_IMX6SL || COMPILE_TEST
 	default SOC_IMX6SL
 	select PINCTRL_IMX
 	help
@@ -104,7 +112,8 @@ config PINCTRL_IMX6SL
 
 config PINCTRL_IMX6SLL
 	bool "IMX6SLL pinctrl driver"
-	depends on SOC_IMX6SLL
+	depends on OF
+	depends on SOC_IMX6SLL || COMPILE_TEST
 	default SOC_IMX6SLL
 	select PINCTRL_IMX
 	help
@@ -112,7 +121,8 @@ config PINCTRL_IMX6SLL
 
 config PINCTRL_IMX6SX
 	bool "IMX6SX pinctrl driver"
-	depends on SOC_IMX6SX
+	depends on OF
+	depends on SOC_IMX6SX || COMPILE_TEST
 	default SOC_IMX6SX
 	select PINCTRL_IMX
 	help
@@ -120,7 +130,8 @@ config PINCTRL_IMX6SX
 
 config PINCTRL_IMX6UL
 	bool "IMX6UL pinctrl driver"
-	depends on SOC_IMX6UL
+	depends on OF
+	depends on SOC_IMX6UL || COMPILE_TEST
 	default SOC_IMX6UL
 	select PINCTRL_IMX
 	help
@@ -128,7 +139,8 @@ config PINCTRL_IMX6UL
 
 config PINCTRL_IMX7D
 	bool "IMX7D pinctrl driver"
-	depends on SOC_IMX7D
+	depends on OF
+	depends on SOC_IMX7D || COMPILE_TEST
 	default SOC_IMX7D
 	select PINCTRL_IMX
 	help
@@ -136,7 +148,8 @@ config PINCTRL_IMX7D
 
 config PINCTRL_IMX7ULP
 	bool "IMX7ULP pinctrl driver"
-	depends on SOC_IMX7ULP
+	depends on OF
+	depends on SOC_IMX7ULP || COMPILE_TEST
 	default SOC_IMX7ULP
 	select PINCTRL_IMX
 	help
@@ -145,7 +158,7 @@ config PINCTRL_IMX7ULP
 config PINCTRL_IMX8MM
 	tristate "IMX8MM pinctrl driver"
 	depends on OF
-	depends on SOC_IMX8M
+	depends on SOC_IMX8M || COMPILE_TEST
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx8mm pinctrl driver
@@ -153,7 +166,7 @@ config PINCTRL_IMX8MM
 config PINCTRL_IMX8MN
 	tristate "IMX8MN pinctrl driver"
 	depends on OF
-	depends on SOC_IMX8M
+	depends on SOC_IMX8M || COMPILE_TEST
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx8mn pinctrl driver
@@ -161,7 +174,7 @@ config PINCTRL_IMX8MN
 config PINCTRL_IMX8MP
 	tristate "IMX8MP pinctrl driver"
 	depends on OF
-	depends on SOC_IMX8M
+	depends on SOC_IMX8M || COMPILE_TEST
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx8mp pinctrl driver
@@ -169,42 +182,47 @@ config PINCTRL_IMX8MP
 config PINCTRL_IMX8MQ
 	tristate "IMX8MQ pinctrl driver"
 	depends on OF
-	depends on SOC_IMX8M
+	depends on SOC_IMX8M || COMPILE_TEST
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx8mq pinctrl driver
 
 config PINCTRL_IMX8QM
 	tristate "IMX8QM pinctrl driver"
-	depends on IMX_SCU && ARCH_MXC && ARM64
+	depends on OF
+	depends on (IMX_SCU && ARCH_MXC && ARM64) || COMPILE_TEST
 	select PINCTRL_IMX_SCU
 	help
 	  Say Y here to enable the imx8qm pinctrl driver
 
 config PINCTRL_IMX8QXP
 	tristate "IMX8QXP pinctrl driver"
-	depends on IMX_SCU && ARCH_MXC && ARM64
+	depends on OF
+	depends on (IMX_SCU && ARCH_MXC && ARM64) || COMPILE_TEST
 	select PINCTRL_IMX_SCU
 	help
 	  Say Y here to enable the imx8qxp pinctrl driver
 
 config PINCTRL_IMX8DXL
 	tristate "IMX8DXL pinctrl driver"
-	depends on IMX_SCU && ARCH_MXC && ARM64
+	depends on OF
+	depends on (IMX_SCU && ARCH_MXC && ARM64) || COMPILE_TEST
 	select PINCTRL_IMX_SCU
 	help
 	  Say Y here to enable the imx8dxl pinctrl driver
 
 config PINCTRL_IMX8ULP
 	tristate "IMX8ULP pinctrl driver"
-	depends on ARCH_MXC
+	depends on OF
+	depends on ARCH_MXC || COMPILE_TEST
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx8ulp pinctrl driver
 
 config PINCTRL_IMXRT1050
 	bool "IMXRT1050 pinctrl driver"
-	depends on SOC_IMXRT
+	depends on OF
+	depends on SOC_IMXRT || COMPILE_TEST
 	default SOC_IMXRT
 	select PINCTRL_IMX
 	help
@@ -219,14 +237,16 @@ config PINCTRL_IMX91
 
 config PINCTRL_IMX93
 	tristate "IMX93 pinctrl driver"
-	depends on ARCH_MXC
+	depends on OF
+	depends on ARCH_MXC || COMPILE_TEST
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imx93 pinctrl driver
 
 config PINCTRL_VF610
 	bool "Freescale Vybrid VF610 pinctrl driver"
-	depends on SOC_VF610
+	depends on OF
+	depends on SOC_VF610 || COMPILE_TEST
 	default SOC_VF610
 	select PINCTRL_IMX
 	help
@@ -247,7 +267,8 @@ config PINCTRL_IMX28
 
 config PINCTRL_IMXRT1170
 	bool "IMXRT1170 pinctrl driver"
-	depends on SOC_IMXRT
+	depends on OF
+	depends on SOC_IMXRT || COMPILE_TEST
 	select PINCTRL_IMX
 	help
 	  Say Y here to enable the imxrt1170 pinctrl driver

From 01be3ac0ab77d4ffcd425aee05dc81d5d10117e2 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Tue, 17 Sep 2024 14:45:40 +0200
Subject: [PATCH 0061/1530] dt-bindings: ocelot: document lan969x-pinctrl

Lan969x is going to reuse the existing Ocelot pinctrl driver - document
that by adding compatible strings for the different SKU's that we
support.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/20240917-lan969x-pinctrl-v2-1-ea02cbc56831@microchip.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/mscc,ocelot-pinctrl.yaml | 27 +++++++++++++------
 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/mscc,ocelot-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mscc,ocelot-pinctrl.yaml
index dbb3e1bd58c10..31bc30a817529 100644
--- a/Documentation/devicetree/bindings/pinctrl/mscc,ocelot-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/mscc,ocelot-pinctrl.yaml
@@ -12,14 +12,24 @@ maintainers:
 
 properties:
   compatible:
-    enum:
-      - microchip,lan966x-pinctrl
-      - microchip,sparx5-pinctrl
-      - mscc,jaguar2-pinctrl
-      - mscc,luton-pinctrl
-      - mscc,ocelot-pinctrl
-      - mscc,serval-pinctrl
-      - mscc,servalt-pinctrl
+    oneOf:
+      - enum:
+          - microchip,lan966x-pinctrl
+          - microchip,lan9691-pinctrl
+          - microchip,sparx5-pinctrl
+          - mscc,jaguar2-pinctrl
+          - mscc,luton-pinctrl
+          - mscc,ocelot-pinctrl
+          - mscc,serval-pinctrl
+          - mscc,servalt-pinctrl
+      - items:
+          - enum:
+              - microchip,lan9698-pinctrl
+              - microchip,lan9696-pinctrl
+              - microchip,lan9694-pinctrl
+              - microchip,lan9693-pinctrl
+              - microchip,lan9692-pinctrl
+          - const: microchip,lan9691-pinctrl
 
   reg:
     items:
@@ -85,6 +95,7 @@ allOf:
           contains:
             enum:
               - microchip,lan966x-pinctrl
+              - microchip,lan9691-pinctrl
               - microchip,sparx5-pinctrl
     then:
       properties:

From 4e778d2ca233a8b48558de30e6016a2c2a583738 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Tue, 17 Sep 2024 14:45:41 +0200
Subject: [PATCH 0062/1530] pinctrl: ocelot: add support for lan969x SoC
 pinctrl

This adds support for lan969x SoC pinctrl, reusing the existing ocelot
driver. There are 66 General Purpose I/O pins that are individually
configurable to multiple interfaces.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Link: https://lore.kernel.org/20240917-lan969x-pinctrl-v2-2-ea02cbc56831@microchip.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-ocelot.c | 203 +++++++++++++++++++++++++++++++
 1 file changed, 203 insertions(+)

diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c
index be9b8c0101670..13209adac6e60 100644
--- a/drivers/pinctrl/pinctrl-ocelot.c
+++ b/drivers/pinctrl/pinctrl-ocelot.c
@@ -57,6 +57,8 @@ enum {
 	FUNC_CAN1,
 	FUNC_CLKMON,
 	FUNC_NONE,
+	FUNC_FAN,
+	FUNC_FC,
 	FUNC_FC0_a,
 	FUNC_FC0_b,
 	FUNC_FC0_c,
@@ -71,6 +73,7 @@ enum {
 	FUNC_FC4_a,
 	FUNC_FC4_b,
 	FUNC_FC4_c,
+	FUNC_FC_SHRD,
 	FUNC_FC_SHRD0,
 	FUNC_FC_SHRD1,
 	FUNC_FC_SHRD2,
@@ -92,6 +95,7 @@ enum {
 	FUNC_FC_SHRD18,
 	FUNC_FC_SHRD19,
 	FUNC_FC_SHRD20,
+	FUNC_FUSA,
 	FUNC_GPIO,
 	FUNC_IB_TRG_a,
 	FUNC_IB_TRG_b,
@@ -108,6 +112,8 @@ enum {
 	FUNC_IRQ1,
 	FUNC_IRQ1_IN,
 	FUNC_IRQ1_OUT,
+	FUNC_IRQ3,
+	FUNC_IRQ4,
 	FUNC_EXT_IRQ,
 	FUNC_MIIM,
 	FUNC_MIIM_a,
@@ -115,12 +121,14 @@ enum {
 	FUNC_MIIM_c,
 	FUNC_MIIM_Sa,
 	FUNC_MIIM_Sb,
+	FUNC_MIIM_IRQ,
 	FUNC_OB_TRG,
 	FUNC_OB_TRG_a,
 	FUNC_OB_TRG_b,
 	FUNC_PHY_LED,
 	FUNC_PCI_WAKE,
 	FUNC_MD,
+	FUNC_PCIE_PERST,
 	FUNC_PTP0,
 	FUNC_PTP1,
 	FUNC_PTP2,
@@ -152,6 +160,7 @@ enum {
 	FUNC_SGPIO_b,
 	FUNC_SI,
 	FUNC_SI2,
+	FUNC_SYNCE,
 	FUNC_TACHO,
 	FUNC_TACHO_a,
 	FUNC_TACHO_b,
@@ -170,6 +179,10 @@ enum {
 	FUNC_USB_S_a,
 	FUNC_USB_S_b,
 	FUNC_USB_S_c,
+	FUNC_USB_POWER,
+	FUNC_USB2PHY_RST,
+	FUNC_USB_OVER_DETECT,
+	FUNC_USB_ULPI,
 	FUNC_PLL_STAT,
 	FUNC_EMMC,
 	FUNC_EMMC_SD,
@@ -184,6 +197,8 @@ static const char *const ocelot_function_names[] = {
 	[FUNC_CAN1]		= "can1",
 	[FUNC_CLKMON]		= "clkmon",
 	[FUNC_NONE]		= "none",
+	[FUNC_FAN]		= "fan",
+	[FUNC_FC]		= "fc",
 	[FUNC_FC0_a]		= "fc0_a",
 	[FUNC_FC0_b]		= "fc0_b",
 	[FUNC_FC0_c]		= "fc0_c",
@@ -198,6 +213,7 @@ static const char *const ocelot_function_names[] = {
 	[FUNC_FC4_a]		= "fc4_a",
 	[FUNC_FC4_b]		= "fc4_b",
 	[FUNC_FC4_c]		= "fc4_c",
+	[FUNC_FC_SHRD]		= "fc_shrd",
 	[FUNC_FC_SHRD0]		= "fc_shrd0",
 	[FUNC_FC_SHRD1]		= "fc_shrd1",
 	[FUNC_FC_SHRD2]		= "fc_shrd2",
@@ -219,6 +235,7 @@ static const char *const ocelot_function_names[] = {
 	[FUNC_FC_SHRD18]	= "fc_shrd18",
 	[FUNC_FC_SHRD19]	= "fc_shrd19",
 	[FUNC_FC_SHRD20]	= "fc_shrd20",
+	[FUNC_FUSA]		= "fusa",
 	[FUNC_GPIO]		= "gpio",
 	[FUNC_IB_TRG_a]		= "ib_trig_a",
 	[FUNC_IB_TRG_b]		= "ib_trig_b",
@@ -235,6 +252,8 @@ static const char *const ocelot_function_names[] = {
 	[FUNC_IRQ1]		= "irq1",
 	[FUNC_IRQ1_IN]		= "irq1_in",
 	[FUNC_IRQ1_OUT]		= "irq1_out",
+	[FUNC_IRQ3]		= "irq3",
+	[FUNC_IRQ4]		= "irq4",
 	[FUNC_EXT_IRQ]		= "ext_irq",
 	[FUNC_MIIM]		= "miim",
 	[FUNC_MIIM_a]		= "miim_a",
@@ -242,8 +261,10 @@ static const char *const ocelot_function_names[] = {
 	[FUNC_MIIM_c]		= "miim_c",
 	[FUNC_MIIM_Sa]		= "miim_slave_a",
 	[FUNC_MIIM_Sb]		= "miim_slave_b",
+	[FUNC_MIIM_IRQ]		= "miim_irq",
 	[FUNC_PHY_LED]		= "phy_led",
 	[FUNC_PCI_WAKE]		= "pci_wake",
+	[FUNC_PCIE_PERST]	= "pcie_perst",
 	[FUNC_MD]		= "md",
 	[FUNC_OB_TRG]		= "ob_trig",
 	[FUNC_OB_TRG_a]		= "ob_trig_a",
@@ -279,6 +300,7 @@ static const char *const ocelot_function_names[] = {
 	[FUNC_SGPIO_b]		= "sgpio_b",
 	[FUNC_SI]		= "si",
 	[FUNC_SI2]		= "si2",
+	[FUNC_SYNCE]		= "synce",
 	[FUNC_TACHO]		= "tacho",
 	[FUNC_TACHO_a]		= "tacho_a",
 	[FUNC_TACHO_b]		= "tacho_b",
@@ -294,6 +316,10 @@ static const char *const ocelot_function_names[] = {
 	[FUNC_USB_S_a]		= "usb_slave_a",
 	[FUNC_USB_S_b]		= "usb_slave_b",
 	[FUNC_USB_S_c]		= "usb_slave_c",
+	[FUNC_USB_POWER]	= "usb_power",
+	[FUNC_USB2PHY_RST]	= "usb2phy_rst",
+	[FUNC_USB_OVER_DETECT]	= "usb_over_detect",
+	[FUNC_USB_ULPI]		= "usb_ulpi",
 	[FUNC_UART]		= "uart",
 	[FUNC_UART2]		= "uart2",
 	[FUNC_UART3]		= "uart3",
@@ -1136,6 +1162,165 @@ static const struct pinctrl_pin_desc lan966x_pins[] = {
 	LAN966X_PIN(77),
 };
 
+#define LAN969X_P(p, f0, f1, f2, f3, f4, f5, f6, f7)           \
+static struct ocelot_pin_caps lan969x_pin_##p = {              \
+	.pin = p,                                              \
+	.functions = {                                         \
+		FUNC_##f0, FUNC_##f1, FUNC_##f2,               \
+		FUNC_##f3                                      \
+	},                                                     \
+	.a_functions = {                                       \
+		FUNC_##f4, FUNC_##f5, FUNC_##f6,               \
+		FUNC_##f7                                      \
+	},                                                     \
+}
+
+/* Pinmuxing table taken from data sheet */
+/*        Pin   FUNC0      FUNC1   FUNC2         FUNC3                  FUNC4     FUNC5      FUNC6        FUNC7 */
+LAN969X_P(0,    GPIO,      IRQ0,   FC_SHRD,      PCIE_PERST,            NONE,     NONE,      NONE,        R);
+LAN969X_P(1,    GPIO,      IRQ1,   FC_SHRD,       USB_POWER,            NONE,     NONE,      NONE,        R);
+LAN969X_P(2,    GPIO,        FC,      NONE,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(3,    GPIO,        FC,      NONE,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(4,    GPIO,        FC,      NONE,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(5,    GPIO,   SGPIO_a,      NONE,          CLKMON,            NONE,     NONE,      NONE,        R);
+LAN969X_P(6,    GPIO,   SGPIO_a,      NONE,          CLKMON,            NONE,     NONE,      NONE,        R);
+LAN969X_P(7,    GPIO,   SGPIO_a,      NONE,          CLKMON,            NONE,     NONE,      NONE,        R);
+LAN969X_P(8,    GPIO,   SGPIO_a,      NONE,          CLKMON,            NONE,     NONE,      NONE,        R);
+LAN969X_P(9,    GPIO,      MIIM,   MIIM_Sa,          CLKMON,            NONE,     NONE,      NONE,        R);
+LAN969X_P(10,   GPIO,      MIIM,   MIIM_Sa,          CLKMON,            NONE,     NONE,      NONE,        R);
+LAN969X_P(11,   GPIO,  MIIM_IRQ,   MIIM_Sa,          CLKMON,            NONE,     NONE,      NONE,        R);
+LAN969X_P(12,   GPIO,      IRQ3,   FC_SHRD,     USB2PHY_RST,            NONE,     NONE,      NONE,        R);
+LAN969X_P(13,   GPIO,      IRQ4,   FC_SHRD, USB_OVER_DETECT,            NONE,     NONE,      NONE,        R);
+LAN969X_P(14,   GPIO,   EMMC_SD,     QSPI1,              FC,            NONE,     NONE,      NONE,        R);
+LAN969X_P(15,   GPIO,   EMMC_SD,     QSPI1,              FC,            NONE,     NONE,      NONE,        R);
+LAN969X_P(16,   GPIO,   EMMC_SD,     QSPI1,              FC,            NONE,     NONE,      NONE,        R);
+LAN969X_P(17,   GPIO,   EMMC_SD,     QSPI1,       PTPSYNC_0,       USB_POWER,     NONE,      NONE,        R);
+LAN969X_P(18,   GPIO,   EMMC_SD,     QSPI1,       PTPSYNC_1,     USB2PHY_RST,     NONE,      NONE,        R);
+LAN969X_P(19,   GPIO,   EMMC_SD,     QSPI1,       PTPSYNC_2, USB_OVER_DETECT,     NONE,      NONE,        R);
+LAN969X_P(20,   GPIO,   EMMC_SD,      NONE,         FC_SHRD,            NONE,     NONE,      NONE,        R);
+LAN969X_P(21,   GPIO,   EMMC_SD,      NONE,         FC_SHRD,            NONE,     NONE,      NONE,        R);
+LAN969X_P(22,   GPIO,   EMMC_SD,      NONE,         FC_SHRD,            NONE,     NONE,      NONE,        R);
+LAN969X_P(23,   GPIO,   EMMC_SD,      NONE,         FC_SHRD,            NONE,     NONE,      NONE,        R);
+LAN969X_P(24,   GPIO,   EMMC_SD,      NONE,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(25,   GPIO,       FAN,      FUSA,          CAN0_a,           QSPI1,     NONE,      NONE,        R);
+LAN969X_P(26,   GPIO,       FAN,      FUSA,          CAN0_a,           QSPI1,     NONE,      NONE,        R);
+LAN969X_P(27,   GPIO,     SYNCE,        FC,            MIIM,           QSPI1,     NONE,      NONE,        R);
+LAN969X_P(28,   GPIO,     SYNCE,        FC,            MIIM,           QSPI1,     NONE,      NONE,        R);
+LAN969X_P(29,   GPIO,     SYNCE,        FC,        MIIM_IRQ,           QSPI1,     NONE,      NONE,        R);
+LAN969X_P(30,   GPIO, PTPSYNC_0,  USB_ULPI,         FC_SHRD,           QSPI1,     NONE,      NONE,        R);
+LAN969X_P(31,   GPIO, PTPSYNC_1,  USB_ULPI,         FC_SHRD,            NONE,     NONE,      NONE,        R);
+LAN969X_P(32,   GPIO, PTPSYNC_2,  USB_ULPI,         FC_SHRD,            NONE,     NONE,      NONE,        R);
+LAN969X_P(33,   GPIO,        SD,  USB_ULPI,         FC_SHRD,            NONE,     NONE,      NONE,        R);
+LAN969X_P(34,   GPIO,        SD,  USB_ULPI,            CAN1,         FC_SHRD,     NONE,      NONE,        R);
+LAN969X_P(35,   GPIO,        SD,  USB_ULPI,            CAN1,         FC_SHRD,     NONE,      NONE,        R);
+LAN969X_P(36,   GPIO,        SD,  USB_ULPI,      PCIE_PERST,         FC_SHRD,     NONE,      NONE,        R);
+LAN969X_P(37,   GPIO,        SD,  USB_ULPI,          CAN0_b,            NONE,     NONE,      NONE,        R);
+LAN969X_P(38,   GPIO,        SD,  USB_ULPI,          CAN0_b,            NONE,     NONE,      NONE,        R);
+LAN969X_P(39,   GPIO,        SD,  USB_ULPI,            MIIM,            NONE,     NONE,      NONE,        R);
+LAN969X_P(40,   GPIO,        SD,  USB_ULPI,            MIIM,            NONE,     NONE,      NONE,        R);
+LAN969X_P(41,   GPIO,        SD,  USB_ULPI,        MIIM_IRQ,            NONE,     NONE,      NONE,        R);
+LAN969X_P(42,   GPIO, PTPSYNC_3,      CAN1,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(43,   GPIO, PTPSYNC_4,      CAN1,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(44,   GPIO, PTPSYNC_5,    SFP_SD,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(45,   GPIO, PTPSYNC_6,    SFP_SD,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(46,   GPIO, PTPSYNC_7,    SFP_SD,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(47,   GPIO,      NONE,    SFP_SD,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(48,   GPIO,      NONE,    SFP_SD,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(49,   GPIO,      NONE,    SFP_SD,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(50,   GPIO,      NONE,    SFP_SD,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(51,   GPIO,      NONE,    SFP_SD,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(52,   GPIO,       FAN,    SFP_SD,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(53,   GPIO,       FAN,    SFP_SD,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(54,   GPIO,     SYNCE,        FC,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(55,   GPIO,     SYNCE,        FC,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(56,   GPIO,     SYNCE,        FC,            NONE,            NONE,     NONE,      NONE,        R);
+LAN969X_P(57,   GPIO,    SFP_SD,   FC_SHRD,             TWI,       PTPSYNC_3,     NONE,      NONE,        R);
+LAN969X_P(58,   GPIO,    SFP_SD,   FC_SHRD,             TWI,       PTPSYNC_4,     NONE,      NONE,        R);
+LAN969X_P(59,   GPIO,    SFP_SD,   FC_SHRD,             TWI,       PTPSYNC_5,     NONE,      NONE,        R);
+LAN969X_P(60,   GPIO,    SFP_SD,   FC_SHRD,             TWI,       PTPSYNC_6,     NONE,      NONE,        R);
+LAN969X_P(61,   GPIO,      MIIM,   FC_SHRD,             TWI,            NONE,     NONE,      NONE,        R);
+LAN969X_P(62,   GPIO,      MIIM,   FC_SHRD,             TWI,            NONE,     NONE,      NONE,        R);
+LAN969X_P(63,   GPIO,  MIIM_IRQ,   FC_SHRD,             TWI,            NONE,     NONE,      NONE,        R);
+LAN969X_P(64,   GPIO,        FC,   FC_SHRD,             TWI,            NONE,     NONE,      NONE,        R);
+LAN969X_P(65,   GPIO,        FC,   FC_SHRD,             TWI,            NONE,     NONE,      NONE,        R);
+LAN969X_P(66,   GPIO,        FC,   FC_SHRD,             TWI,            NONE,     NONE,      NONE,        R);
+
+#define LAN969X_PIN(n) {                                       \
+	.number = n,                                           \
+	.name = "GPIO_"#n,                                     \
+	.drv_data = &lan969x_pin_##n                           \
+}
+
+static const struct pinctrl_pin_desc lan969x_pins[] = {
+	LAN969X_PIN(0),
+	LAN969X_PIN(1),
+	LAN969X_PIN(2),
+	LAN969X_PIN(3),
+	LAN969X_PIN(4),
+	LAN969X_PIN(5),
+	LAN969X_PIN(6),
+	LAN969X_PIN(7),
+	LAN969X_PIN(8),
+	LAN969X_PIN(9),
+	LAN969X_PIN(10),
+	LAN969X_PIN(11),
+	LAN969X_PIN(12),
+	LAN969X_PIN(13),
+	LAN969X_PIN(14),
+	LAN969X_PIN(15),
+	LAN969X_PIN(16),
+	LAN969X_PIN(17),
+	LAN969X_PIN(18),
+	LAN969X_PIN(19),
+	LAN969X_PIN(20),
+	LAN969X_PIN(21),
+	LAN969X_PIN(22),
+	LAN969X_PIN(23),
+	LAN969X_PIN(24),
+	LAN969X_PIN(25),
+	LAN969X_PIN(26),
+	LAN969X_PIN(27),
+	LAN969X_PIN(28),
+	LAN969X_PIN(29),
+	LAN969X_PIN(30),
+	LAN969X_PIN(31),
+	LAN969X_PIN(32),
+	LAN969X_PIN(33),
+	LAN969X_PIN(34),
+	LAN969X_PIN(35),
+	LAN969X_PIN(36),
+	LAN969X_PIN(37),
+	LAN969X_PIN(38),
+	LAN969X_PIN(39),
+	LAN969X_PIN(40),
+	LAN969X_PIN(41),
+	LAN969X_PIN(42),
+	LAN969X_PIN(43),
+	LAN969X_PIN(44),
+	LAN969X_PIN(45),
+	LAN969X_PIN(46),
+	LAN969X_PIN(47),
+	LAN969X_PIN(48),
+	LAN969X_PIN(49),
+	LAN969X_PIN(50),
+	LAN969X_PIN(51),
+	LAN969X_PIN(52),
+	LAN969X_PIN(53),
+	LAN969X_PIN(54),
+	LAN969X_PIN(55),
+	LAN969X_PIN(56),
+	LAN969X_PIN(57),
+	LAN969X_PIN(58),
+	LAN969X_PIN(59),
+	LAN969X_PIN(60),
+	LAN969X_PIN(61),
+	LAN969X_PIN(62),
+	LAN969X_PIN(63),
+	LAN969X_PIN(64),
+	LAN969X_PIN(65),
+	LAN969X_PIN(66),
+};
+
 static int ocelot_get_functions_count(struct pinctrl_dev *pctldev)
 {
 	return ARRAY_SIZE(ocelot_function_names);
@@ -1682,6 +1867,23 @@ static struct ocelot_match_data lan966x_desc = {
 	},
 };
 
+static struct ocelot_match_data lan969x_desc = {
+	.desc = {
+		.name = "lan969x-pinctrl",
+		.pins = lan969x_pins,
+		.npins = ARRAY_SIZE(lan969x_pins),
+		.pctlops = &ocelot_pctl_ops,
+		.pmxops = &lan966x_pmx_ops,
+		.confops = &ocelot_confops,
+		.owner = THIS_MODULE,
+	},
+	.pincfg_data = {
+		.pd_bit = BIT(3),
+		.pu_bit = BIT(2),
+		.drive_bits = GENMASK(1, 0),
+	},
+};
+
 static int ocelot_create_group_func_map(struct device *dev,
 					struct ocelot_pinctrl *info)
 {
@@ -2014,6 +2216,7 @@ static const struct of_device_id ocelot_pinctrl_of_match[] = {
 	{ .compatible = "mscc,servalt-pinctrl", .data = &servalt_desc },
 	{ .compatible = "microchip,sparx5-pinctrl", .data = &sparx5_desc },
 	{ .compatible = "microchip,lan966x-pinctrl", .data = &lan966x_desc },
+	{ .compatible = "microchip,lan9691-pinctrl", .data = &lan969x_desc },
 	{},
 };
 MODULE_DEVICE_TABLE(of, ocelot_pinctrl_of_match);

From 137ca342ae2d6627496a871f5553ea023cfc77c0 Mon Sep 17 00:00:00 2001
From: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Date: Mon, 30 Sep 2024 12:50:51 -0700
Subject: [PATCH 0063/1530] dt-bindings: pinctrl: Add thead,th1520-pinctrl
 bindings

Add bindings for the pin controllers on the T-Head TH1520 RISC-V SoC.

Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Tested-by: Thomas Bonnefille <thomas.bonnefille@bootlin.com>
Signed-off-by: Emil Renner Berthing <emil.renner.berthing@canonical.com>
[dfustini: add thead,pad-group to select the pin controller instance]
Signed-off-by: Drew Fustini <dfustini@tenstorrent.com>
Link: https://lore.kernel.org/20240930-th1520-pinctrl-v3-1-32cea2bdbecb@tenstorrent.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../pinctrl/thead,th1520-pinctrl.yaml         | 176 ++++++++++++++++++
 MAINTAINERS                                   |   1 +
 2 files changed, 177 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/thead,th1520-pinctrl.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/thead,th1520-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/thead,th1520-pinctrl.yaml
new file mode 100644
index 0000000000000..21f86740a63d4
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/thead,th1520-pinctrl.yaml
@@ -0,0 +1,176 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/thead,th1520-pinctrl.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: T-Head TH1520 SoC pin controller
+
+maintainers:
+  - Emil Renner Berthing <emil.renner.berthing@canonical.com>
+
+description: |
+  Pinmux and pinconf controller in the T-Head TH1520 RISC-V SoC.
+
+  The TH1520 has 3 groups of pads each controlled from different memory ranges.
+  Confusingly the memory ranges are named
+    PADCTRL_AOSYS  -> PAD Group 1
+    PADCTRL1_APSYS -> PAD Group 2
+    PADCTRL0_APSYS -> PAD Group 3
+
+  Each pad can be muxed individually to up to 6 different functions. For most
+  pads only a few of those 6 configurations are valid though, and a few pads in
+  group 1 does not support muxing at all.
+
+  Pinconf is fairly regular except for a few pads in group 1 that either can't
+  be configured or has some special functions. The rest have configurable drive
+  strength, input enable, schmitt trigger, slew rate, pull-up and pull-down in
+  addition to a special strong pull up.
+
+  Certain pads in group 1 can be muxed to AUDIO_PA0 - AUDIO_PA30 functions and
+  are then meant to be used by the audio co-processor. Each such pad can then
+  be further muxed to either audio GPIO or one of 4 functions such as UART, I2C
+  and I2S. If the audio pad is muxed to one of the 4 functions then pinconf is
+  also configured in different registers. All of this is done from a different
+  AUDIO_IOCTRL memory range and is left to the audio co-processor for now.
+
+properties:
+  compatible:
+    enum:
+      - thead,th1520-pinctrl
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  thead,pad-group:
+    description: |
+      Select the pad group that is associated with the pin controller instance.
+
+        Base Address   Name           Group
+        0xFF_FFF4_A000 PADCTRL_AOSYS  1
+        0xFF_E7F3_C000 PADCTRL1_APSYS 2
+        0xFF_EC00_7000 PADCTRL0_APSYS 3
+
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [1, 2, 3]
+
+required:
+  - compatible
+  - reg
+  - clocks
+
+patternProperties:
+  '-[0-9]+$':
+    type: object
+    additionalProperties: false
+
+    patternProperties:
+      '-pins$':
+        type: object
+        allOf:
+          - $ref: /schemas/pinctrl/pincfg-node.yaml#
+          - $ref: /schemas/pinctrl/pinmux-node.yaml#
+
+        additionalProperties: false
+
+        description:
+          A pinctrl node should contain at least one subnode describing one
+          or more pads and their associated pinmux and pinconf settings.
+
+        properties:
+          pins:
+            description: List of pads that properties in the node apply to.
+
+          function:
+            enum: [ gpio, pwm, uart, ir, i2c, spi, qspi, sdio, audio, i2s,
+                    gmac0, gmac1, dpu0, dpu1, isp, hdmi, bootsel, debug,
+                    clock, jtag, iso7816, efuse, reset ]
+            description: The mux function to select for the given pins.
+
+          bias-disable: true
+
+          bias-pull-up:
+            oneOf:
+              - type: boolean
+                description: Enable the regular 48kOhm pull-up
+              - enum: [ 2100, 48000 ]
+                description: Enable the strong 2.1kOhm pull-up or regular 48kOhm pull-up
+
+          bias-pull-down:
+            oneOf:
+              - type: boolean
+              - const: 44000
+            description: Enable the regular 44kOhm pull-down
+
+          drive-strength:
+            enum: [ 1, 2, 3, 5, 7, 8, 10, 12, 13, 15, 16, 18, 20, 21, 23, 25 ]
+            description: Drive strength in mA
+
+          input-enable: true
+
+          input-disable: true
+
+          input-schmitt-enable: true
+
+          input-schmitt-disable: true
+
+          slew-rate:
+            maximum: 1
+
+        required:
+          - pins
+
+additionalProperties: false
+
+examples:
+  - |
+    padctrl0_apsys: pinctrl@ec007000 {
+        compatible = "thead,th1520-pinctrl";
+        reg = <0xec007000 0x1000>;
+        clocks = <&apb_clk>;
+        thead,pad-group = <3>;
+
+        uart0_pins: uart0-0 {
+            tx-pins {
+                pins = "UART0_TXD";
+                function = "uart";
+                bias-disable;
+                drive-strength = <3>;
+                input-disable;
+                input-schmitt-disable;
+                slew-rate = <0>;
+            };
+
+            rx-pins {
+                pins = "UART0_RXD";
+                function = "uart";
+                bias-disable;
+                drive-strength = <1>;
+                input-enable;
+                input-schmitt-enable;
+                slew-rate = <0>;
+            };
+        };
+    };
+
+    padctrl1_apsys: pinctrl@e7f3c000 {
+        compatible = "thead,th1520-pinctrl";
+        reg = <0xe7f3c000 0x1000>;
+        clocks = <&apb_clk>;
+        thead,pad-group = <2>;
+
+        i2c5_pins: i2c5-0 {
+            i2c-pins {
+                pins = "QSPI1_CSN0",    /* I2C5_SCL */
+                       "QSPI1_D0_MOSI"; /* I2C5_SDA */
+                function = "i2c";
+                bias-pull-up = <2100>;
+                drive-strength = <7>;
+                input-enable;
+                input-schmitt-enable;
+                slew-rate = <0>;
+            };
+        };
+    };
diff --git a/MAINTAINERS b/MAINTAINERS
index c27f3190737f8..dd74c9aa20091 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19942,6 +19942,7 @@ L:	linux-riscv@lists.infradead.org
 S:	Maintained
 T:	git https://github.com/pdp7/linux.git
 F:	Documentation/devicetree/bindings/clock/thead,th1520-clk-ap.yaml
+F:	Documentation/devicetree/bindings/pinctrl/thead,th1520-pinctrl.yaml
 F:	arch/riscv/boot/dts/thead/
 F:	drivers/clk/thead/clk-th1520-ap.c
 F:	include/dt-bindings/clock/thead,th1520-clk-ap.h

From bed5cd6f8a988389e987bcf5c1762ab7c53be317 Mon Sep 17 00:00:00 2001
From: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Date: Mon, 30 Sep 2024 12:50:52 -0700
Subject: [PATCH 0064/1530] pinctrl: Add driver for the T-Head TH1520 SoC

Add pinctrl driver for the T-Head TH1520 RISC-V SoC.

Tested-by: Thomas Bonnefille <thomas.bonnefille@bootlin.com>
Signed-off-by: Emil Renner Berthing <emil.renner.berthing@canonical.com>
[dfustini: use thead,pad-group to identify the pin controller instance]
Signed-off-by: Drew Fustini <dfustini@tenstorrent.com>
Link: https://lore.kernel.org/20240930-th1520-pinctrl-v3-2-32cea2bdbecb@tenstorrent.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 MAINTAINERS                      |   1 +
 drivers/pinctrl/Kconfig          |  13 +
 drivers/pinctrl/Makefile         |   1 +
 drivers/pinctrl/pinctrl-th1520.c | 907 +++++++++++++++++++++++++++++++
 4 files changed, 922 insertions(+)
 create mode 100644 drivers/pinctrl/pinctrl-th1520.c

diff --git a/MAINTAINERS b/MAINTAINERS
index dd74c9aa20091..67634f0ea30e1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19945,6 +19945,7 @@ F:	Documentation/devicetree/bindings/clock/thead,th1520-clk-ap.yaml
 F:	Documentation/devicetree/bindings/pinctrl/thead,th1520-pinctrl.yaml
 F:	arch/riscv/boot/dts/thead/
 F:	drivers/clk/thead/clk-th1520-ap.c
+F:	drivers/pinctrl/pinctrl-th1520.c
 F:	include/dt-bindings/clock/thead,th1520-clk-ap.h
 
 RNBD BLOCK DRIVERS
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index 354536de564b6..5bf58e138ce30 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -551,6 +551,19 @@ config PINCTRL_TPS6594
 	  This driver can also be built as a module
 	  called tps6594-pinctrl.
 
+config PINCTRL_TH1520
+	tristate "Pinctrl driver for the T-Head TH1520 SoC"
+	depends on ARCH_THEAD || COMPILE_TEST
+	select GENERIC_PINMUX_FUNCTIONS
+	select GENERIC_PINCONF
+	select PINMUX
+	help
+	  This is the driver for the pin controller blocks on the
+	  T-Head TH1520 SoC.
+
+	  This driver is needed for RISC-V development boards like
+	  the BeagleV Ahead and the LicheePi 4A.
+
 config PINCTRL_ZYNQ
 	bool "Pinctrl driver for Xilinx Zynq"
 	depends on ARCH_ZYNQ
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index 97823f52b972a..26180a616d139 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -54,6 +54,7 @@ obj-$(CONFIG_PINCTRL_STMFX) 	+= pinctrl-stmfx.o
 obj-$(CONFIG_PINCTRL_SX150X)	+= pinctrl-sx150x.o
 obj-$(CONFIG_PINCTRL_TB10X)	+= pinctrl-tb10x.o
 obj-$(CONFIG_PINCTRL_TPS6594)	+= pinctrl-tps6594.o
+obj-$(CONFIG_PINCTRL_TH1520)	+= pinctrl-th1520.o
 obj-$(CONFIG_PINCTRL_ZYNQMP)	+= pinctrl-zynqmp.o
 obj-$(CONFIG_PINCTRL_ZYNQ)	+= pinctrl-zynq.o
 
diff --git a/drivers/pinctrl/pinctrl-th1520.c b/drivers/pinctrl/pinctrl-th1520.c
new file mode 100644
index 0000000000000..1bb78b212fd50
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-th1520.c
@@ -0,0 +1,907 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Pinctrl driver for the T-Head TH1520 SoC
+ *
+ * Copyright (C) 2023 Emil Renner Berthing <emil.renner.berthing@canonical.com>
+ */
+
+#include <linux/array_size.h>
+#include <linux/bits.h>
+#include <linux/cleanup.h>
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinmux.h>
+
+#include "core.h"
+#include "pinmux.h"
+#include "pinconf.h"
+
+#define TH1520_PADCFG_IE	BIT(9)
+#define TH1520_PADCFG_SL	BIT(8)
+#define TH1520_PADCFG_ST	BIT(7)
+#define TH1520_PADCFG_SPU	BIT(6)
+#define TH1520_PADCFG_PS	BIT(5)
+#define TH1520_PADCFG_PE	BIT(4)
+#define TH1520_PADCFG_BIAS	(TH1520_PADCFG_SPU | TH1520_PADCFG_PS | TH1520_PADCFG_PE)
+#define TH1520_PADCFG_DS	GENMASK(3, 0)
+
+#define TH1520_PULL_DOWN_OHM	44000 /* typ. 44kOhm */
+#define TH1520_PULL_UP_OHM	48000 /* typ. 48kOhm */
+#define TH1520_PULL_STRONG_OHM	 2100 /* typ. 2.1kOhm */
+
+#define TH1520_PAD_NO_PADCFG	BIT(30)
+#define TH1520_PAD_MUXDATA	GENMASK(29, 0)
+
+struct th1520_pad_group {
+	const char *name;
+	const struct pinctrl_pin_desc *pins;
+	unsigned int npins;
+};
+
+struct th1520_pinctrl {
+	struct pinctrl_desc desc;
+	struct mutex mutex;	/* serialize adding functions */
+	raw_spinlock_t lock;	/* serialize register access */
+	void __iomem *base;
+	struct pinctrl_dev *pctl;
+};
+
+static void __iomem *th1520_padcfg(struct th1520_pinctrl *thp,
+				   unsigned int pin)
+{
+	return thp->base + 4 * (pin / 2);
+}
+
+static unsigned int th1520_padcfg_shift(unsigned int pin)
+{
+	return 16 * (pin & BIT(0));
+}
+
+static void __iomem *th1520_muxcfg(struct th1520_pinctrl *thp,
+				   unsigned int pin)
+{
+	return thp->base + 0x400 + 4 * (pin / 8);
+}
+
+static unsigned int th1520_muxcfg_shift(unsigned int pin)
+{
+	return 4 * (pin & GENMASK(2, 0));
+}
+
+enum th1520_muxtype {
+	TH1520_MUX_____,
+	TH1520_MUX_GPIO,
+	TH1520_MUX_PWM,
+	TH1520_MUX_UART,
+	TH1520_MUX_IR,
+	TH1520_MUX_I2C,
+	TH1520_MUX_SPI,
+	TH1520_MUX_QSPI,
+	TH1520_MUX_SDIO,
+	TH1520_MUX_AUD,
+	TH1520_MUX_I2S,
+	TH1520_MUX_MAC0,
+	TH1520_MUX_MAC1,
+	TH1520_MUX_DPU0,
+	TH1520_MUX_DPU1,
+	TH1520_MUX_ISP,
+	TH1520_MUX_HDMI,
+	TH1520_MUX_BSEL,
+	TH1520_MUX_DBG,
+	TH1520_MUX_CLK,
+	TH1520_MUX_JTAG,
+	TH1520_MUX_ISO,
+	TH1520_MUX_FUSE,
+	TH1520_MUX_RST,
+};
+
+static const char *const th1520_muxtype_string[] = {
+	[TH1520_MUX_GPIO] = "gpio",
+	[TH1520_MUX_PWM]  = "pwm",
+	[TH1520_MUX_UART] = "uart",
+	[TH1520_MUX_IR]   = "ir",
+	[TH1520_MUX_I2C]  = "i2c",
+	[TH1520_MUX_SPI]  = "spi",
+	[TH1520_MUX_QSPI] = "qspi",
+	[TH1520_MUX_SDIO] = "sdio",
+	[TH1520_MUX_AUD]  = "audio",
+	[TH1520_MUX_I2S]  = "i2s",
+	[TH1520_MUX_MAC0] = "gmac0",
+	[TH1520_MUX_MAC1] = "gmac1",
+	[TH1520_MUX_DPU0] = "dpu0",
+	[TH1520_MUX_DPU1] = "dpu1",
+	[TH1520_MUX_ISP]  = "isp",
+	[TH1520_MUX_HDMI] = "hdmi",
+	[TH1520_MUX_BSEL] = "bootsel",
+	[TH1520_MUX_DBG]  = "debug",
+	[TH1520_MUX_CLK]  = "clock",
+	[TH1520_MUX_JTAG] = "jtag",
+	[TH1520_MUX_ISO]  = "iso7816",
+	[TH1520_MUX_FUSE] = "efuse",
+	[TH1520_MUX_RST]  = "reset",
+};
+
+static enum th1520_muxtype th1520_muxtype_get(const char *str)
+{
+	enum th1520_muxtype mt;
+
+	for (mt = TH1520_MUX_GPIO; mt < ARRAY_SIZE(th1520_muxtype_string); mt++) {
+		if (!strcmp(str, th1520_muxtype_string[mt]))
+			return mt;
+	}
+	return TH1520_MUX_____;
+}
+
+#define TH1520_PAD(_nr, _name, m0, m1, m2, m3, m4, m5, _flags) \
+	{ .number = _nr, .name = #_name, .drv_data = (void *)((_flags) | \
+		(TH1520_MUX_##m0 <<  0) | (TH1520_MUX_##m1 <<  5) | (TH1520_MUX_##m2 << 10) | \
+		(TH1520_MUX_##m3 << 15) | (TH1520_MUX_##m4 << 20) | (TH1520_MUX_##m5 << 25)) }
+
+static const struct pinctrl_pin_desc th1520_group1_pins[] = {
+	TH1520_PAD(0,  OSC_CLK_IN,    ____, ____, ____, ____, ____, ____, TH1520_PAD_NO_PADCFG),
+	TH1520_PAD(1,  OSC_CLK_OUT,   ____, ____, ____, ____, ____, ____, TH1520_PAD_NO_PADCFG),
+	TH1520_PAD(2,  SYS_RST_N,     ____, ____, ____, ____, ____, ____, TH1520_PAD_NO_PADCFG),
+	TH1520_PAD(3,  RTC_CLK_IN,    ____, ____, ____, ____, ____, ____, TH1520_PAD_NO_PADCFG),
+	TH1520_PAD(4,  RTC_CLK_OUT,   ____, ____, ____, ____, ____, ____, TH1520_PAD_NO_PADCFG),
+	/* skip number 5 so we can calculate register offsets and shifts from the pin number */
+	TH1520_PAD(6,  TEST_MODE,     ____, ____, ____, ____, ____, ____, TH1520_PAD_NO_PADCFG),
+	TH1520_PAD(7,  DEBUG_MODE,    DBG,  ____, ____, GPIO, ____, ____, TH1520_PAD_NO_PADCFG),
+	TH1520_PAD(8,  POR_SEL,       ____, ____, ____, ____, ____, ____, TH1520_PAD_NO_PADCFG),
+	TH1520_PAD(9,  I2C_AON_SCL,   I2C,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(10, I2C_AON_SDA,   I2C,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(11, CPU_JTG_TCLK,  JTAG, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(12, CPU_JTG_TMS,   JTAG, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(13, CPU_JTG_TDI,   JTAG, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(14, CPU_JTG_TDO,   JTAG, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(15, CPU_JTG_TRST,  JTAG, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(16, AOGPIO_7,      CLK,  AUD,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(17, AOGPIO_8,      UART, AUD,  IR,   GPIO, ____, ____, 0),
+	TH1520_PAD(18, AOGPIO_9,      UART, AUD,  IR,   GPIO, ____, ____, 0),
+	TH1520_PAD(19, AOGPIO_10,     CLK,  AUD,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(20, AOGPIO_11,     GPIO, AUD,  ____, ____, ____, ____, 0),
+	TH1520_PAD(21, AOGPIO_12,     GPIO, AUD,  ____, ____, ____, ____, 0),
+	TH1520_PAD(22, AOGPIO_13,     GPIO, AUD,  ____, ____, ____, ____, 0),
+	TH1520_PAD(23, AOGPIO_14,     GPIO, AUD,  ____, ____, ____, ____, 0),
+	TH1520_PAD(24, AOGPIO_15,     GPIO, AUD,  ____, ____, ____, ____, 0),
+	TH1520_PAD(25, AUDIO_PA0,     AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(26, AUDIO_PA1,     AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(27, AUDIO_PA2,     AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(28, AUDIO_PA3,     AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(29, AUDIO_PA4,     AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(30, AUDIO_PA5,     AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(31, AUDIO_PA6,     AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(32, AUDIO_PA7,     AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(33, AUDIO_PA8,     AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(34, AUDIO_PA9,     AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(35, AUDIO_PA10,    AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(36, AUDIO_PA11,    AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(37, AUDIO_PA12,    AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(38, AUDIO_PA13,    AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(39, AUDIO_PA14,    AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(40, AUDIO_PA15,    AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(41, AUDIO_PA16,    AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(42, AUDIO_PA17,    AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(43, AUDIO_PA27,    AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(44, AUDIO_PA28,    AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(45, AUDIO_PA29,    AUD,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(46, AUDIO_PA30,    AUD,  RST,  ____, GPIO, ____, ____, 0),
+};
+
+static const struct pinctrl_pin_desc th1520_group2_pins[] = {
+	TH1520_PAD(0,  QSPI1_SCLK,    QSPI, ISO,  ____, GPIO, FUSE, ____, 0),
+	TH1520_PAD(1,  QSPI1_CSN0,    QSPI, ____, I2C,  GPIO, FUSE, ____, 0),
+	TH1520_PAD(2,  QSPI1_D0_MOSI, QSPI, ISO,  I2C,  GPIO, FUSE, ____, 0),
+	TH1520_PAD(3,  QSPI1_D1_MISO, QSPI, ISO,  ____, GPIO, FUSE, ____, 0),
+	TH1520_PAD(4,  QSPI1_D2_WP,   QSPI, ISO,  UART, GPIO, FUSE, ____, 0),
+	TH1520_PAD(5,  QSPI1_D3_HOLD, QSPI, ISO,  UART, GPIO, ____, ____, 0),
+	TH1520_PAD(6,  I2C0_SCL,      I2C,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(7,  I2C0_SDA,      I2C,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(8,  I2C1_SCL,      I2C,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(9,  I2C1_SDA,      I2C,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(10, UART1_TXD,     UART, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(11, UART1_RXD,     UART, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(12, UART4_TXD,     UART, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(13, UART4_RXD,     UART, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(14, UART4_CTSN,    UART, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(15, UART4_RTSN,    UART, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(16, UART3_TXD,     DBG,  UART, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(17, UART3_RXD,     DBG,  UART, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(18, GPIO0_18,      GPIO, I2C,  ____, ____, ____, ____, 0),
+	TH1520_PAD(19, GPIO0_19,      GPIO, I2C,  ____, ____, ____, ____, 0),
+	TH1520_PAD(20, GPIO0_20,      GPIO, UART, IR,   ____, ____, ____, 0),
+	TH1520_PAD(21, GPIO0_21,      GPIO, UART, IR,   ____, DPU0, DPU1, 0),
+	TH1520_PAD(22, GPIO0_22,      GPIO, JTAG, I2C,  ____, DPU0, DPU1, 0),
+	TH1520_PAD(23, GPIO0_23,      GPIO, JTAG, I2C,  ____, DPU0, DPU1, 0),
+	TH1520_PAD(24, GPIO0_24,      GPIO, JTAG, QSPI, ____, DPU0, DPU1, 0),
+	TH1520_PAD(25, GPIO0_25,      GPIO, JTAG, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(26, GPIO0_26,      GPIO, JTAG, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(27, GPIO0_27,      GPIO, ____, I2C,  ____, DPU0, DPU1, 0),
+	TH1520_PAD(28, GPIO0_28,      GPIO, ____, I2C,  ____, DPU0, DPU1, 0),
+	TH1520_PAD(29, GPIO0_29,      GPIO, ____, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(30, GPIO0_30,      GPIO, ____, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(31, GPIO0_31,      GPIO, ____, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(32, GPIO1_0,       GPIO, JTAG, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(33, GPIO1_1,       GPIO, JTAG, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(34, GPIO1_2,       GPIO, JTAG, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(35, GPIO1_3,       GPIO, JTAG, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(36, GPIO1_4,       GPIO, JTAG, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(37, GPIO1_5,       GPIO, ____, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(38, GPIO1_6,       GPIO, ____, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(39, GPIO1_7,       GPIO, QSPI, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(40, GPIO1_8,       GPIO, QSPI, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(41, GPIO1_9,       GPIO, QSPI, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(42, GPIO1_10,      GPIO, QSPI, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(43, GPIO1_11,      GPIO, QSPI, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(44, GPIO1_12,      GPIO, QSPI, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(45, GPIO1_13,      GPIO, UART, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(46, GPIO1_14,      GPIO, UART, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(47, GPIO1_15,      GPIO, UART, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(48, GPIO1_16,      GPIO, UART, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(49, CLK_OUT_0,     BSEL, CLK,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(50, CLK_OUT_1,     BSEL, CLK,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(51, CLK_OUT_2,     BSEL, CLK,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(52, CLK_OUT_3,     BSEL, CLK,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(53, GPIO1_21,      GPIO, ____, ISP,  ____, ____, ____, 0),
+	TH1520_PAD(54, GPIO1_22,      GPIO, ____, ISP,  ____, ____, ____, 0),
+	TH1520_PAD(55, GPIO1_23,      GPIO, ____, ISP,  ____, ____, ____, 0),
+	TH1520_PAD(56, GPIO1_24,      GPIO, ____, ISP,  ____, ____, ____, 0),
+	TH1520_PAD(57, GPIO1_25,      GPIO, ____, ISP,  ____, ____, ____, 0),
+	TH1520_PAD(58, GPIO1_26,      GPIO, ____, ISP,  ____, ____, ____, 0),
+	TH1520_PAD(59, GPIO1_27,      GPIO, ____, ISP,  ____, ____, ____, 0),
+	TH1520_PAD(60, GPIO1_28,      GPIO, ____, ISP,  ____, ____, ____, 0),
+	TH1520_PAD(61, GPIO1_29,      GPIO, ____, ISP,  ____, ____, ____, 0),
+	TH1520_PAD(62, GPIO1_30,      GPIO, ____, ISP,  ____, ____, ____, 0),
+};
+
+static const struct pinctrl_pin_desc th1520_group3_pins[] = {
+	TH1520_PAD(0,  UART0_TXD,     UART, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(1,  UART0_RXD,     UART, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(2,  QSPI0_SCLK,    QSPI, PWM,  I2S,  GPIO, ____, ____, 0),
+	TH1520_PAD(3,  QSPI0_CSN0,    QSPI, PWM,  I2S,  GPIO, ____, ____, 0),
+	TH1520_PAD(4,  QSPI0_CSN1,    QSPI, PWM,  I2S,  GPIO, ____, ____, 0),
+	TH1520_PAD(5,  QSPI0_D0_MOSI, QSPI, PWM,  I2S,  GPIO, ____, ____, 0),
+	TH1520_PAD(6,  QSPI0_D1_MISO, QSPI, PWM,  I2S,  GPIO, ____, ____, 0),
+	TH1520_PAD(7,  QSPI0_D2_WP,   QSPI, PWM,  I2S,  GPIO, ____, ____, 0),
+	TH1520_PAD(8,  QSPI1_D3_HOLD, QSPI, ____, I2S,  GPIO, ____, ____, 0),
+	TH1520_PAD(9,  I2C2_SCL,      I2C,  UART, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(10, I2C2_SDA,      I2C,  UART, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(11, I2C3_SCL,      I2C,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(12, I2C3_SDA,      I2C,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(13, GPIO2_13,      GPIO, SPI,  ____, ____, ____, ____, 0),
+	TH1520_PAD(14, SPI_SCLK,      SPI,  UART, IR,   GPIO, ____, ____, 0),
+	TH1520_PAD(15, SPI_CSN,       SPI,  UART, IR,   GPIO, ____, ____, 0),
+	TH1520_PAD(16, SPI_MOSI,      SPI,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(17, SPI_MISO,      SPI,  ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(18, GPIO2_18,      GPIO, MAC1, ____, ____, ____, ____, 0),
+	TH1520_PAD(19, GPIO2_19,      GPIO, MAC1, ____, ____, ____, ____, 0),
+	TH1520_PAD(20, GPIO2_20,      GPIO, MAC1, ____, ____, ____, ____, 0),
+	TH1520_PAD(21, GPIO2_21,      GPIO, MAC1, ____, ____, ____, ____, 0),
+	TH1520_PAD(22, GPIO2_22,      GPIO, MAC1, ____, ____, ____, ____, 0),
+	TH1520_PAD(23, GPIO2_23,      GPIO, MAC1, ____, ____, ____, ____, 0),
+	TH1520_PAD(24, GPIO2_24,      GPIO, MAC1, ____, ____, ____, ____, 0),
+	TH1520_PAD(25, GPIO2_25,      GPIO, MAC1, ____, ____, ____, ____, 0),
+	TH1520_PAD(26, SDIO0_WPRTN,   SDIO, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(27, SDIO0_DETN,    SDIO, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(28, SDIO1_WPRTN,   SDIO, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(29, SDIO1_DETN,    SDIO, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(30, GPIO2_30,      GPIO, MAC1, ____, ____, ____, ____, 0),
+	TH1520_PAD(31, GPIO2_31,      GPIO, MAC1, ____, ____, ____, ____, 0),
+	TH1520_PAD(32, GPIO3_0,       GPIO, MAC1, ____, ____, ____, ____, 0),
+	TH1520_PAD(33, GPIO3_1,       GPIO, MAC1, ____, ____, ____, ____, 0),
+	TH1520_PAD(34, GPIO3_2,       GPIO, PWM,  ____, ____, ____, ____, 0),
+	TH1520_PAD(35, GPIO3_3,       GPIO, PWM,  ____, ____, ____, ____, 0),
+	TH1520_PAD(36, HDMI_SCL,      HDMI, PWM,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(37, HDMI_SDA,      HDMI, PWM,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(38, HDMI_CEC,      HDMI, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(39, GMAC0_TX_CLK,  MAC0, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(40, GMAC0_RX_CLK,  MAC0, ____, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(41, GMAC0_TXEN,    MAC0, UART, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(42, GMAC0_TXD0,    MAC0, UART, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(43, GMAC0_TXD1,    MAC0, UART, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(44, GMAC0_TXD2,    MAC0, UART, ____, GPIO, ____, ____, 0),
+	TH1520_PAD(45, GMAC0_TXD3,    MAC0, I2C,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(46, GMAC0_RXDV,    MAC0, I2C,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(47, GMAC0_RXD0,    MAC0, I2C,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(48, GMAC0_RXD1,    MAC0, I2C,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(49, GMAC0_RXD2,    MAC0, SPI,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(50, GMAC0_RXD3,    MAC0, SPI,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(51, GMAC0_MDC,     MAC0, SPI,  MAC1, GPIO, ____, ____, 0),
+	TH1520_PAD(52, GMAC0_MDIO,    MAC0, SPI,  MAC1, GPIO, ____, ____, 0),
+	TH1520_PAD(53, GMAC0_COL,     MAC0, PWM,  ____, GPIO, ____, ____, 0),
+	TH1520_PAD(54, GMAC0_CRS,     MAC0, PWM,  ____, GPIO, ____, ____, 0),
+};
+
+static const struct th1520_pad_group th1520_group1 = {
+	.name = "th1520-group1",
+	.pins = th1520_group1_pins,
+	.npins = ARRAY_SIZE(th1520_group1_pins),
+};
+
+static const struct th1520_pad_group th1520_group2 = {
+	.name = "th1520-group2",
+	.pins = th1520_group2_pins,
+	.npins = ARRAY_SIZE(th1520_group2_pins),
+};
+
+static const struct th1520_pad_group th1520_group3 = {
+	.name = "th1520-group3",
+	.pins = th1520_group3_pins,
+	.npins = ARRAY_SIZE(th1520_group3_pins),
+};
+
+static int th1520_pinctrl_get_groups_count(struct pinctrl_dev *pctldev)
+{
+	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
+
+	return thp->desc.npins;
+}
+
+static const char *th1520_pinctrl_get_group_name(struct pinctrl_dev *pctldev,
+						 unsigned int gsel)
+{
+	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
+
+	return thp->desc.pins[gsel].name;
+}
+
+static int th1520_pinctrl_get_group_pins(struct pinctrl_dev *pctldev,
+					 unsigned int gsel,
+					 const unsigned int **pins,
+					 unsigned int *npins)
+{
+	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
+
+	*pins = &thp->desc.pins[gsel].number;
+	*npins = 1;
+	return 0;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static void th1520_pin_dbg_show(struct pinctrl_dev *pctldev,
+				struct seq_file *s, unsigned int pin)
+{
+	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
+	void __iomem *padcfg = th1520_padcfg(thp, pin);
+	void __iomem *muxcfg = th1520_muxcfg(thp, pin);
+	u32 pad;
+	u32 mux;
+
+	scoped_guard(raw_spinlock_irqsave, &thp->lock) {
+		pad = readl_relaxed(padcfg);
+		mux = readl_relaxed(muxcfg);
+	}
+
+	seq_printf(s, "[PADCFG_%03u:0x%x=0x%07x MUXCFG_%03u:0x%x=0x%08x]",
+		   1 + pin / 2, 0x000 + 4 * (pin / 2), pad,
+		   1 + pin / 8, 0x400 + 4 * (pin / 8), mux);
+}
+#else
+#define th1520_pin_dbg_show NULL
+#endif
+
+static void th1520_pinctrl_dt_free_map(struct pinctrl_dev *pctldev,
+				       struct pinctrl_map *map, unsigned int nmaps)
+{
+	unsigned long *seen = NULL;
+	unsigned int i;
+
+	for (i = 0; i < nmaps; i++) {
+		if (map[i].type == PIN_MAP_TYPE_CONFIGS_PIN &&
+		    map[i].data.configs.configs != seen) {
+			seen = map[i].data.configs.configs;
+			kfree(seen);
+		}
+	}
+
+	kfree(map);
+}
+
+static int th1520_pinctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
+					 struct device_node *np,
+					 struct pinctrl_map **maps,
+					 unsigned int *num_maps)
+{
+	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
+	struct device_node *child;
+	struct pinctrl_map *map;
+	unsigned long *configs;
+	unsigned int nconfigs;
+	unsigned int nmaps;
+	int ret;
+
+	nmaps = 0;
+	for_each_available_child_of_node(np, child) {
+		int npins = of_property_count_strings(child, "pins");
+
+		if (npins <= 0) {
+			of_node_put(child);
+			dev_err(thp->pctl->dev, "no pins selected for %pOFn.%pOFn\n",
+				np, child);
+			return -EINVAL;
+		}
+		nmaps += npins;
+		if (of_property_present(child, "function"))
+			nmaps += npins;
+	}
+
+	map = kcalloc(nmaps, sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+
+	nmaps = 0;
+	mutex_lock(&thp->mutex);
+	for_each_available_child_of_node(np, child) {
+		unsigned int rollback = nmaps;
+		enum th1520_muxtype muxtype;
+		struct property *prop;
+		const char *funcname;
+		const char **pgnames;
+		const char *pinname;
+		int npins;
+
+		ret = pinconf_generic_parse_dt_config(child, pctldev, &configs, &nconfigs);
+		if (ret) {
+			dev_err(thp->pctl->dev, "%pOFn.%pOFn: error parsing pin config\n",
+				np, child);
+			goto put_child;
+		}
+
+		if (!of_property_read_string(child, "function", &funcname)) {
+			muxtype = th1520_muxtype_get(funcname);
+			if (!muxtype) {
+				dev_err(thp->pctl->dev, "%pOFn.%pOFn: unknown function '%s'\n",
+					np, child, funcname);
+				ret = -EINVAL;
+				goto free_configs;
+			}
+
+			funcname = devm_kasprintf(thp->pctl->dev, GFP_KERNEL, "%pOFn.%pOFn",
+						  np, child);
+			if (!funcname) {
+				ret = -ENOMEM;
+				goto free_configs;
+			}
+
+			npins = of_property_count_strings(child, "pins");
+			pgnames = devm_kcalloc(thp->pctl->dev, npins, sizeof(*pgnames), GFP_KERNEL);
+			if (!pgnames) {
+				ret = -ENOMEM;
+				goto free_configs;
+			}
+		} else {
+			funcname = NULL;
+		}
+
+		npins = 0;
+		of_property_for_each_string(child, "pins", prop, pinname) {
+			unsigned int i;
+
+			for (i = 0; i < thp->desc.npins; i++) {
+				if (!strcmp(pinname, thp->desc.pins[i].name))
+					break;
+			}
+			if (i == thp->desc.npins) {
+				nmaps = rollback;
+				dev_err(thp->pctl->dev, "%pOFn.%pOFn: unknown pin '%s'\n",
+					np, child, pinname);
+				goto free_configs;
+			}
+
+			if (nconfigs) {
+				map[nmaps].type = PIN_MAP_TYPE_CONFIGS_PIN;
+				map[nmaps].data.configs.group_or_pin = thp->desc.pins[i].name;
+				map[nmaps].data.configs.configs = configs;
+				map[nmaps].data.configs.num_configs = nconfigs;
+				nmaps += 1;
+			}
+			if (funcname) {
+				pgnames[npins++] = thp->desc.pins[i].name;
+				map[nmaps].type = PIN_MAP_TYPE_MUX_GROUP;
+				map[nmaps].data.mux.function = funcname;
+				map[nmaps].data.mux.group = thp->desc.pins[i].name;
+				nmaps += 1;
+			}
+		}
+
+		if (funcname) {
+			ret = pinmux_generic_add_function(pctldev, funcname, pgnames,
+							  npins, (void *)muxtype);
+			if (ret < 0) {
+				dev_err(thp->pctl->dev, "error adding function %s\n", funcname);
+				goto put_child;
+			}
+		}
+	}
+
+	*maps = map;
+	*num_maps = nmaps;
+	mutex_unlock(&thp->mutex);
+	return 0;
+
+free_configs:
+	kfree(configs);
+put_child:
+	of_node_put(child);
+	th1520_pinctrl_dt_free_map(pctldev, map, nmaps);
+	mutex_unlock(&thp->mutex);
+	return ret;
+}
+
+static const struct pinctrl_ops th1520_pinctrl_ops = {
+	.get_groups_count = th1520_pinctrl_get_groups_count,
+	.get_group_name = th1520_pinctrl_get_group_name,
+	.get_group_pins = th1520_pinctrl_get_group_pins,
+	.pin_dbg_show = th1520_pin_dbg_show,
+	.dt_node_to_map = th1520_pinctrl_dt_node_to_map,
+	.dt_free_map = th1520_pinctrl_dt_free_map,
+};
+
+static const u8 th1520_drive_strength_in_ma[16] = {
+	1, 2, 3, 5, 7, 8, 10, 12, 13, 15, 16, 18, 20, 21, 23, 25,
+};
+
+static u16 th1520_drive_strength_from_ma(u32 arg)
+{
+	u16 ds;
+
+	for (ds = 0; ds < TH1520_PADCFG_DS; ds++) {
+		if (arg <= th1520_drive_strength_in_ma[ds])
+			return ds;
+	}
+	return TH1520_PADCFG_DS;
+}
+
+static int th1520_padcfg_rmw(struct th1520_pinctrl *thp, unsigned int pin,
+			     u32 mask, u32 value)
+{
+	void __iomem *padcfg = th1520_padcfg(thp, pin);
+	unsigned int shift = th1520_padcfg_shift(pin);
+	u32 tmp;
+
+	mask <<= shift;
+	value <<= shift;
+
+	scoped_guard(raw_spinlock_irqsave, &thp->lock) {
+		tmp = readl_relaxed(padcfg);
+		tmp = (tmp & ~mask) | value;
+		writel_relaxed(tmp, padcfg);
+	}
+	return 0;
+}
+
+static int th1520_pinconf_get(struct pinctrl_dev *pctldev,
+			      unsigned int pin, unsigned long *config)
+{
+	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
+	const struct pin_desc *desc = pin_desc_get(pctldev, pin);
+	bool enabled;
+	int param;
+	u32 value;
+	u32 arg;
+
+	if ((uintptr_t)desc->drv_data & TH1520_PAD_NO_PADCFG)
+		return -EOPNOTSUPP;
+
+	value = readl_relaxed(th1520_padcfg(thp, pin));
+	value = (value >> th1520_padcfg_shift(pin)) & GENMASK(9, 0);
+
+	param = pinconf_to_config_param(*config);
+	switch (param) {
+	case PIN_CONFIG_BIAS_DISABLE:
+		enabled = !(value & (TH1520_PADCFG_SPU | TH1520_PADCFG_PE));
+		arg = 0;
+		break;
+	case PIN_CONFIG_BIAS_PULL_DOWN:
+		enabled = (value & TH1520_PADCFG_BIAS) == TH1520_PADCFG_PE;
+		arg = enabled ? TH1520_PULL_DOWN_OHM : 0;
+		break;
+	case PIN_CONFIG_BIAS_PULL_UP:
+		if (value & TH1520_PADCFG_SPU) {
+			enabled = true;
+			arg = TH1520_PULL_STRONG_OHM;
+		} else if ((value & (TH1520_PADCFG_PE | TH1520_PADCFG_PS)) ==
+				    (TH1520_PADCFG_PE | TH1520_PADCFG_PS)) {
+			enabled = true;
+			arg = TH1520_PULL_UP_OHM;
+		} else {
+			enabled = false;
+			arg = 0;
+		}
+		break;
+	case PIN_CONFIG_DRIVE_STRENGTH:
+		enabled = true;
+		arg = th1520_drive_strength_in_ma[value & TH1520_PADCFG_DS];
+		break;
+	case PIN_CONFIG_INPUT_ENABLE:
+		enabled = value & TH1520_PADCFG_IE;
+		arg = enabled ? 1 : 0;
+		break;
+	case PIN_CONFIG_INPUT_SCHMITT_ENABLE:
+		enabled = value & TH1520_PADCFG_ST;
+		arg = enabled ? 1 : 0;
+		break;
+	case PIN_CONFIG_SLEW_RATE:
+		enabled = value & TH1520_PADCFG_SL;
+		arg = enabled ? 1 : 0;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	*config = pinconf_to_config_packed(param, arg);
+	return enabled ? 0 : -EINVAL;
+}
+
+static int th1520_pinconf_group_get(struct pinctrl_dev *pctldev,
+				    unsigned int gsel, unsigned long *config)
+{
+	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
+	unsigned int pin = thp->desc.pins[gsel].number;
+
+	return th1520_pinconf_get(pctldev, pin, config);
+}
+
+static int th1520_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
+			      unsigned long *configs, unsigned int num_configs)
+{
+	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
+	const struct pin_desc *desc = pin_desc_get(pctldev, pin);
+	unsigned int i;
+	u16 mask, value;
+
+	if ((uintptr_t)desc->drv_data & TH1520_PAD_NO_PADCFG)
+		return -EOPNOTSUPP;
+
+	mask = 0;
+	value = 0;
+	for (i = 0; i < num_configs; i++) {
+		int param = pinconf_to_config_param(configs[i]);
+		u32 arg = pinconf_to_config_argument(configs[i]);
+
+		switch (param) {
+		case PIN_CONFIG_BIAS_DISABLE:
+			mask |= TH1520_PADCFG_BIAS;
+			value &= ~TH1520_PADCFG_BIAS;
+			break;
+		case PIN_CONFIG_BIAS_PULL_DOWN:
+			if (arg == 0)
+				return -EOPNOTSUPP;
+			mask |= TH1520_PADCFG_BIAS;
+			value &= ~TH1520_PADCFG_BIAS;
+			value |= TH1520_PADCFG_PE;
+			break;
+		case PIN_CONFIG_BIAS_PULL_UP:
+			if (arg == 0)
+				return -EOPNOTSUPP;
+			mask |= TH1520_PADCFG_BIAS;
+			value &= ~TH1520_PADCFG_BIAS;
+			if (arg == TH1520_PULL_STRONG_OHM)
+				value |= TH1520_PADCFG_SPU;
+			else
+				value |= TH1520_PADCFG_PE | TH1520_PADCFG_PS;
+			break;
+		case PIN_CONFIG_DRIVE_STRENGTH:
+			mask |= TH1520_PADCFG_DS;
+			value &= ~TH1520_PADCFG_DS;
+			value |= th1520_drive_strength_from_ma(arg);
+			break;
+		case PIN_CONFIG_INPUT_ENABLE:
+			mask |= TH1520_PADCFG_IE;
+			if (arg)
+				value |= TH1520_PADCFG_IE;
+			else
+				value &= ~TH1520_PADCFG_IE;
+			break;
+		case PIN_CONFIG_INPUT_SCHMITT_ENABLE:
+			mask |= TH1520_PADCFG_ST;
+			if (arg)
+				value |= TH1520_PADCFG_ST;
+			else
+				value &= ~TH1520_PADCFG_ST;
+			break;
+		case PIN_CONFIG_SLEW_RATE:
+			mask |= TH1520_PADCFG_SL;
+			if (arg)
+				value |= TH1520_PADCFG_SL;
+			else
+				value &= ~TH1520_PADCFG_SL;
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return th1520_padcfg_rmw(thp, pin, mask, value);
+}
+
+static int th1520_pinconf_group_set(struct pinctrl_dev *pctldev,
+				    unsigned int gsel,
+				    unsigned long *configs,
+				    unsigned int num_configs)
+{
+	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
+	unsigned int pin = thp->desc.pins[gsel].number;
+
+	return th1520_pinconf_set(pctldev, pin, configs, num_configs);
+}
+
+#ifdef CONFIG_DEBUG_FS
+static void th1520_pinconf_dbg_show(struct pinctrl_dev *pctldev,
+				    struct seq_file *s, unsigned int pin)
+{
+	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
+	u32 value = readl_relaxed(th1520_padcfg(thp, pin));
+
+	value = (value >> th1520_padcfg_shift(pin)) & GENMASK(9, 0);
+
+	seq_printf(s, " [0x%03x]", value);
+}
+#else
+#define th1520_pinconf_dbg_show NULL
+#endif
+
+static const struct pinconf_ops th1520_pinconf_ops = {
+	.pin_config_get = th1520_pinconf_get,
+	.pin_config_group_get = th1520_pinconf_group_get,
+	.pin_config_set = th1520_pinconf_set,
+	.pin_config_group_set = th1520_pinconf_group_set,
+	.pin_config_dbg_show = th1520_pinconf_dbg_show,
+	.is_generic = true,
+};
+
+static int th1520_pinmux_set(struct th1520_pinctrl *thp, unsigned int pin,
+			     unsigned long muxdata, enum th1520_muxtype muxtype)
+{
+	void __iomem *muxcfg = th1520_muxcfg(thp, pin);
+	unsigned int shift = th1520_muxcfg_shift(pin);
+	u32 mask, value, tmp;
+
+	for (value = 0; muxdata; muxdata >>= 5, value++) {
+		if ((muxdata & GENMASK(4, 0)) == muxtype)
+			break;
+	}
+	if (!muxdata) {
+		dev_err(thp->pctl->dev, "invalid mux %s for pin %s\n",
+			th1520_muxtype_string[muxtype], pin_get_name(thp->pctl, pin));
+		return -EINVAL;
+	}
+
+	mask = GENMASK(3, 0) << shift;
+	value = value << shift;
+
+	scoped_guard(raw_spinlock_irqsave, &thp->lock) {
+		tmp = readl_relaxed(muxcfg);
+		tmp = (tmp & ~mask) | value;
+		writel_relaxed(tmp, muxcfg);
+	}
+	return 0;
+}
+
+static int th1520_pinmux_set_mux(struct pinctrl_dev *pctldev,
+				 unsigned int fsel, unsigned int gsel)
+{
+	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
+	const struct function_desc *func = pinmux_generic_get_function(pctldev, fsel);
+
+	return th1520_pinmux_set(thp, thp->desc.pins[gsel].number,
+				 (uintptr_t)thp->desc.pins[gsel].drv_data & TH1520_PAD_MUXDATA,
+				 (uintptr_t)func->data);
+}
+
+static int th1520_gpio_request_enable(struct pinctrl_dev *pctldev,
+				      struct pinctrl_gpio_range *range,
+				      unsigned int offset)
+{
+	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
+	const struct pin_desc *desc = pin_desc_get(pctldev, offset);
+
+	return th1520_pinmux_set(thp, offset,
+				 (uintptr_t)desc->drv_data & TH1520_PAD_MUXDATA,
+				 TH1520_MUX_GPIO);
+}
+
+static int th1520_gpio_set_direction(struct pinctrl_dev *pctldev,
+				     struct pinctrl_gpio_range *range,
+				     unsigned int offset, bool input)
+{
+	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
+
+	return th1520_padcfg_rmw(thp, offset, TH1520_PADCFG_IE,
+				 input ? TH1520_PADCFG_IE : 0);
+}
+
+static const struct pinmux_ops th1520_pinmux_ops = {
+	.get_functions_count = pinmux_generic_get_function_count,
+	.get_function_name = pinmux_generic_get_function_name,
+	.get_function_groups = pinmux_generic_get_function_groups,
+	.set_mux = th1520_pinmux_set_mux,
+	.gpio_request_enable = th1520_gpio_request_enable,
+	.gpio_set_direction = th1520_gpio_set_direction,
+	.strict = true,
+};
+
+static int th1520_pinctrl_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct th1520_pad_group *group;
+	struct device_node *np = dev->of_node;
+	struct th1520_pinctrl *thp;
+	struct clk *clk;
+	u32 pin_group;
+	int ret;
+
+	thp = devm_kzalloc(dev, sizeof(*thp), GFP_KERNEL);
+	if (!thp)
+		return -ENOMEM;
+
+	thp->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(thp->base))
+		return PTR_ERR(thp->base);
+
+	clk = devm_clk_get_enabled(dev, NULL);
+	if (IS_ERR(clk))
+		return dev_err_probe(dev, PTR_ERR(clk), "error getting clock\n");
+
+	ret = of_property_read_u32(np, "thead,pad-group", &pin_group);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to read the thead,pad-group property\n");
+
+	if (pin_group == 1)
+		group = &th1520_group1;
+	else if (pin_group == 2)
+		group = &th1520_group2;
+	else if (pin_group == 3)
+		group = &th1520_group3;
+	else
+		return dev_err_probe(dev, -EINVAL, "unit address did not match any pad group\n");
+
+	thp->desc.name = group->name;
+	thp->desc.pins = group->pins;
+	thp->desc.npins = group->npins;
+	thp->desc.pctlops = &th1520_pinctrl_ops;
+	thp->desc.pmxops = &th1520_pinmux_ops;
+	thp->desc.confops = &th1520_pinconf_ops;
+	thp->desc.owner = THIS_MODULE;
+	mutex_init(&thp->mutex);
+	raw_spin_lock_init(&thp->lock);
+
+	ret = devm_pinctrl_register_and_init(dev, &thp->desc, thp, &thp->pctl);
+	if (ret)
+		return dev_err_probe(dev, ret, "could not register pinctrl driver\n");
+
+	return pinctrl_enable(thp->pctl);
+}
+
+static const struct of_device_id th1520_pinctrl_of_match[] = {
+	{ .compatible = "thead,th1520-pinctrl"},
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, th1520_pinctrl_of_match);
+
+static struct platform_driver th1520_pinctrl_driver = {
+	.probe = th1520_pinctrl_probe,
+	.driver = {
+		.name = "pinctrl-th1520",
+		.of_match_table = th1520_pinctrl_of_match,
+	},
+};
+module_platform_driver(th1520_pinctrl_driver);
+
+MODULE_DESCRIPTION("Pinctrl driver for the T-Head TH1520 SoC");
+MODULE_AUTHOR("Emil Renner Berthing <emil.renner.berthing@canonical.com>");
+MODULE_LICENSE("GPL");

From b88752d3133b334fbad83a3d3fee5df9ad65e536 Mon Sep 17 00:00:00 2001
From: Sricharan Ramabadhran <quic_srichara@quicinc.com>
Date: Fri, 27 Sep 2024 12:22:38 +0530
Subject: [PATCH 0065/1530] dt-bindings: pinctrl: qcom: add IPQ5424 pinctrl

Add device tree bindings for IPQ5424 TLMM block.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Sricharan Ramabadhran <quic_srichara@quicinc.com>
Link: https://lore.kernel.org/20240927065244.3024604-4-quic_srichara@quicinc.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/qcom,ipq5424-tlmm.yaml   | 114 ++++++++++++++++++
 1 file changed, 114 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/qcom,ipq5424-tlmm.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq5424-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq5424-tlmm.yaml
new file mode 100644
index 0000000000000..5e64a232fc7a4
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq5424-tlmm.yaml
@@ -0,0 +1,114 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,ipq5424-tlmm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm IPQ5424 TLMM pin controller
+
+maintainers:
+  - Bjorn Andersson <andersson@kernel.org>
+
+description:
+  Top Level Mode Multiplexer pin controller in Qualcomm IPQ5424 SoC.
+
+allOf:
+  - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml#
+
+properties:
+  compatible:
+    const: qcom,ipq5424-tlmm
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  gpio-reserved-ranges:
+    minItems: 1
+    maxItems: 25
+
+  gpio-line-names:
+    maxItems: 50
+
+patternProperties:
+  "-state$":
+    oneOf:
+      - $ref: "#/$defs/qcom-ipq5424-tlmm-state"
+      - patternProperties:
+          "-pins$":
+            $ref: "#/$defs/qcom-ipq5424-tlmm-state"
+        additionalProperties: false
+
+$defs:
+  qcom-ipq5424-tlmm-state:
+    type: object
+    description:
+      Pinctrl node's client devices use subnodes for desired pin configuration.
+      Client device subnodes use below standard properties.
+    $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
+
+    properties:
+      pins:
+        description:
+          List of gpio pins affected by the properties specified in this
+          subnode.
+        items:
+          pattern: "^gpio([0-9]|[1-4][0-9])$"
+        minItems: 1
+        maxItems: 50
+
+      function:
+        description:
+          Specify the alternative function to be configured for the specified
+          pins.
+
+        enum: [ atest_char, atest_char0, atest_char1, atest_char2, atest_char3,
+                atest_tic, audio_pri, audio_pri0, audio_pri1, audio_sec,
+                audio_sec0, audio_sec1, core_voltage, cri_trng0, cri_trng1,
+                cri_trng2, cri_trng3, cxc_clk, cxc_data, dbg_out, gcc_plltest,
+                gcc_tlmm, gpio, i2c0_scl, i2c0_sda, i2c1_scl, i2c1_sda, i2c11,
+                mac0, mac1, mdc_mst, mdc_slv, mdio_mst, mdio_slv, pcie0_clk,
+                pcie0_wake, pcie1_clk, pcie1_wake, pcie2_clk, pcie2_wake,
+                pcie3_clk, pcie3_wake, pll_test, prng_rosc0, prng_rosc1,
+                prng_rosc2, prng_rosc3, PTA0_0, PTA0_1, PTA0_2, PTA10, PTA11,
+                pwm0, pwm1, pwm2, qdss_cti_trig_in_a0, qdss_cti_trig_out_a0,
+                qdss_cti_trig_in_a1, qdss_cti_trig_out_a1, qdss_cti_trig_in_b0,
+                qdss_cti_trig_out_b0, qdss_cti_trig_in_b1, qdss_cti_trig_out_b1,
+                qdss_traceclk_a, qdss_tracectl_a, qdss_tracedata_a, qspi_clk,
+                qspi_cs, qspi_data, resout, rx0, rx1, rx2, sdc_clk, sdc_cmd,
+                sdc_data, spi0, spi1, spi10, spi11, tsens_max, uart0, uart1,
+                wci_txd, wci_rxd, wsi_clk, wsi_data ]
+
+    required:
+      - pins
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    tlmm: pinctrl@1000000 {
+        compatible = "qcom,ipq5424-tlmm";
+        reg = <0x01000000 0x300000>;
+        gpio-controller;
+        #gpio-cells = <0x2>;
+        gpio-ranges = <&tlmm 0 0 50>;
+        interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
+        interrupt-controller;
+        #interrupt-cells = <0x2>;
+
+        uart1_pins: uart1-state {
+            pins = "gpio43", "gpio44";
+            function = "uart1";
+            drive-strength = <8>;
+            bias-pull-up;
+        };
+    };

From 968e671ebd2edac28e6f994e3705969d48af5199 Mon Sep 17 00:00:00 2001
From: Sricharan Ramabadhran <quic_srichara@quicinc.com>
Date: Fri, 27 Sep 2024 12:22:40 +0530
Subject: [PATCH 0066/1530] pinctrl: qcom: Introduce IPQ5424 TLMM driver

The IPQ5424 SoC comes with a TLMM block, like all other Qualcomm
platforms, so add a driver for it.

Co-developed-by: Varadarajan Narayanan <quic_varada@quicinc.com>
Signed-off-by: Varadarajan Narayanan <quic_varada@quicinc.com>
Signed-off-by: Sricharan Ramabadhran <quic_srichara@quicinc.com>
Link: https://lore.kernel.org/20240927065244.3024604-6-quic_srichara@quicinc.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/Kconfig.msm       |   9 +
 drivers/pinctrl/qcom/Makefile          |   1 +
 drivers/pinctrl/qcom/pinctrl-ipq5424.c | 792 +++++++++++++++++++++++++
 3 files changed, 802 insertions(+)
 create mode 100644 drivers/pinctrl/qcom/pinctrl-ipq5424.c

diff --git a/drivers/pinctrl/qcom/Kconfig.msm b/drivers/pinctrl/qcom/Kconfig.msm
index 8fe459d082ede..9738448f2a8a2 100644
--- a/drivers/pinctrl/qcom/Kconfig.msm
+++ b/drivers/pinctrl/qcom/Kconfig.msm
@@ -46,6 +46,15 @@ config PINCTRL_IPQ5332
 	  Qualcomm Technologies Inc TLMM block found on the Qualcomm
 	  Technologies Inc IPQ5332 platform.
 
+config PINCTRL_IPQ5424
+	tristate "Qualcomm Technologies, Inc. IPQ5424 pin controller driver"
+	depends on ARM64 || COMPILE_TEST
+	help
+	  This is the pinctrl, pinmux, pinconf and gpiolib driver for
+          the Qualcomm Technologies Inc. TLMM block found on the
+          Qualcomm Technologies Inc. IPQ5424 platform. Select this for
+          IPQ5424.
+
 config PINCTRL_IPQ8074
 	tristate "Qualcomm Technologies, Inc. IPQ8074 pin controller driver"
 	depends on ARM64 || COMPILE_TEST
diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile
index eb04297b63889..5b4712146db5a 100644
--- a/drivers/pinctrl/qcom/Makefile
+++ b/drivers/pinctrl/qcom/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_PINCTRL_IPQ4019)	+= pinctrl-ipq4019.o
 obj-$(CONFIG_PINCTRL_IPQ5018)	+= pinctrl-ipq5018.o
 obj-$(CONFIG_PINCTRL_IPQ8064)	+= pinctrl-ipq8064.o
 obj-$(CONFIG_PINCTRL_IPQ5332)	+= pinctrl-ipq5332.o
+obj-$(CONFIG_PINCTRL_IPQ5424)	+= pinctrl-ipq5424.o
 obj-$(CONFIG_PINCTRL_IPQ8074)	+= pinctrl-ipq8074.o
 obj-$(CONFIG_PINCTRL_IPQ6018)	+= pinctrl-ipq6018.o
 obj-$(CONFIG_PINCTRL_IPQ9574)	+= pinctrl-ipq9574.o
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq5424.c b/drivers/pinctrl/qcom/pinctrl-ipq5424.c
new file mode 100644
index 0000000000000..796299cd2e4ed
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-ipq5424.c
@@ -0,0 +1,792 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016-2018,2020 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-msm.h"
+
+#define REG_SIZE 0x1000
+#define PINGROUP(id, f1, f2, f3, f4, f5, f6, f7, f8, f9)	\
+	{					        \
+		.grp = PINCTRL_PINGROUP("gpio" #id,     \
+			gpio##id##_pins,                \
+			ARRAY_SIZE(gpio##id##_pins)),   \
+		.funcs = (int[]){			\
+			msm_mux_gpio, /* gpio mode */	\
+			msm_mux_##f1,			\
+			msm_mux_##f2,			\
+			msm_mux_##f3,			\
+			msm_mux_##f4,			\
+			msm_mux_##f5,			\
+			msm_mux_##f6,			\
+			msm_mux_##f7,			\
+			msm_mux_##f8,			\
+			msm_mux_##f9			\
+		},				        \
+		.nfuncs = 10,				\
+		.ctl_reg = REG_SIZE * id,	        \
+		.io_reg = 0x4 + REG_SIZE * id,		\
+		.intr_cfg_reg = 0x8 + REG_SIZE * id,	\
+		.intr_status_reg = 0xc + REG_SIZE * id,	\
+		.intr_target_reg = 0x8 + REG_SIZE * id,	\
+		.mux_bit = 2,			\
+		.pull_bit = 0,			\
+		.drv_bit = 6,			\
+		.oe_bit = 9,			\
+		.in_bit = 0,			\
+		.out_bit = 1,			\
+		.intr_enable_bit = 0,		\
+		.intr_status_bit = 0,		\
+		.intr_target_bit = 5,		\
+		.intr_target_kpss_val = 3,      \
+		.intr_raw_status_bit = 4,	\
+		.intr_polarity_bit = 1,		\
+		.intr_detection_bit = 2,	\
+		.intr_detection_width = 2,	\
+	}
+
+static const struct pinctrl_pin_desc ipq5424_pins[] = {
+	PINCTRL_PIN(0, "GPIO_0"),
+	PINCTRL_PIN(1, "GPIO_1"),
+	PINCTRL_PIN(2, "GPIO_2"),
+	PINCTRL_PIN(3, "GPIO_3"),
+	PINCTRL_PIN(4, "GPIO_4"),
+	PINCTRL_PIN(5, "GPIO_5"),
+	PINCTRL_PIN(6, "GPIO_6"),
+	PINCTRL_PIN(7, "GPIO_7"),
+	PINCTRL_PIN(8, "GPIO_8"),
+	PINCTRL_PIN(9, "GPIO_9"),
+	PINCTRL_PIN(10, "GPIO_10"),
+	PINCTRL_PIN(11, "GPIO_11"),
+	PINCTRL_PIN(12, "GPIO_12"),
+	PINCTRL_PIN(13, "GPIO_13"),
+	PINCTRL_PIN(14, "GPIO_14"),
+	PINCTRL_PIN(15, "GPIO_15"),
+	PINCTRL_PIN(16, "GPIO_16"),
+	PINCTRL_PIN(17, "GPIO_17"),
+	PINCTRL_PIN(18, "GPIO_18"),
+	PINCTRL_PIN(19, "GPIO_19"),
+	PINCTRL_PIN(20, "GPIO_20"),
+	PINCTRL_PIN(21, "GPIO_21"),
+	PINCTRL_PIN(22, "GPIO_22"),
+	PINCTRL_PIN(23, "GPIO_23"),
+	PINCTRL_PIN(24, "GPIO_24"),
+	PINCTRL_PIN(25, "GPIO_25"),
+	PINCTRL_PIN(26, "GPIO_26"),
+	PINCTRL_PIN(27, "GPIO_27"),
+	PINCTRL_PIN(28, "GPIO_28"),
+	PINCTRL_PIN(29, "GPIO_29"),
+	PINCTRL_PIN(30, "GPIO_30"),
+	PINCTRL_PIN(31, "GPIO_31"),
+	PINCTRL_PIN(32, "GPIO_32"),
+	PINCTRL_PIN(33, "GPIO_33"),
+	PINCTRL_PIN(34, "GPIO_34"),
+	PINCTRL_PIN(35, "GPIO_35"),
+	PINCTRL_PIN(36, "GPIO_36"),
+	PINCTRL_PIN(37, "GPIO_37"),
+	PINCTRL_PIN(38, "GPIO_38"),
+	PINCTRL_PIN(39, "GPIO_39"),
+	PINCTRL_PIN(40, "GPIO_40"),
+	PINCTRL_PIN(41, "GPIO_41"),
+	PINCTRL_PIN(42, "GPIO_42"),
+	PINCTRL_PIN(43, "GPIO_43"),
+	PINCTRL_PIN(44, "GPIO_44"),
+	PINCTRL_PIN(45, "GPIO_45"),
+	PINCTRL_PIN(46, "GPIO_46"),
+	PINCTRL_PIN(47, "GPIO_47"),
+	PINCTRL_PIN(48, "GPIO_48"),
+	PINCTRL_PIN(49, "GPIO_49"),
+};
+
+#define DECLARE_MSM_GPIO_PINS(pin) \
+	static const unsigned int gpio##pin##_pins[] = { pin }
+DECLARE_MSM_GPIO_PINS(0);
+DECLARE_MSM_GPIO_PINS(1);
+DECLARE_MSM_GPIO_PINS(2);
+DECLARE_MSM_GPIO_PINS(3);
+DECLARE_MSM_GPIO_PINS(4);
+DECLARE_MSM_GPIO_PINS(5);
+DECLARE_MSM_GPIO_PINS(6);
+DECLARE_MSM_GPIO_PINS(7);
+DECLARE_MSM_GPIO_PINS(8);
+DECLARE_MSM_GPIO_PINS(9);
+DECLARE_MSM_GPIO_PINS(10);
+DECLARE_MSM_GPIO_PINS(11);
+DECLARE_MSM_GPIO_PINS(12);
+DECLARE_MSM_GPIO_PINS(13);
+DECLARE_MSM_GPIO_PINS(14);
+DECLARE_MSM_GPIO_PINS(15);
+DECLARE_MSM_GPIO_PINS(16);
+DECLARE_MSM_GPIO_PINS(17);
+DECLARE_MSM_GPIO_PINS(18);
+DECLARE_MSM_GPIO_PINS(19);
+DECLARE_MSM_GPIO_PINS(20);
+DECLARE_MSM_GPIO_PINS(21);
+DECLARE_MSM_GPIO_PINS(22);
+DECLARE_MSM_GPIO_PINS(23);
+DECLARE_MSM_GPIO_PINS(24);
+DECLARE_MSM_GPIO_PINS(25);
+DECLARE_MSM_GPIO_PINS(26);
+DECLARE_MSM_GPIO_PINS(27);
+DECLARE_MSM_GPIO_PINS(28);
+DECLARE_MSM_GPIO_PINS(29);
+DECLARE_MSM_GPIO_PINS(30);
+DECLARE_MSM_GPIO_PINS(31);
+DECLARE_MSM_GPIO_PINS(32);
+DECLARE_MSM_GPIO_PINS(33);
+DECLARE_MSM_GPIO_PINS(34);
+DECLARE_MSM_GPIO_PINS(35);
+DECLARE_MSM_GPIO_PINS(36);
+DECLARE_MSM_GPIO_PINS(37);
+DECLARE_MSM_GPIO_PINS(38);
+DECLARE_MSM_GPIO_PINS(39);
+DECLARE_MSM_GPIO_PINS(40);
+DECLARE_MSM_GPIO_PINS(41);
+DECLARE_MSM_GPIO_PINS(42);
+DECLARE_MSM_GPIO_PINS(43);
+DECLARE_MSM_GPIO_PINS(44);
+DECLARE_MSM_GPIO_PINS(45);
+DECLARE_MSM_GPIO_PINS(46);
+DECLARE_MSM_GPIO_PINS(47);
+DECLARE_MSM_GPIO_PINS(48);
+DECLARE_MSM_GPIO_PINS(49);
+
+enum ipq5424_functions {
+	msm_mux_atest_char,
+	msm_mux_atest_char0,
+	msm_mux_atest_char1,
+	msm_mux_atest_char2,
+	msm_mux_atest_char3,
+	msm_mux_atest_tic,
+	msm_mux_audio_pri,
+	msm_mux_audio_pri0,
+	msm_mux_audio_pri1,
+	msm_mux_audio_sec,
+	msm_mux_audio_sec0,
+	msm_mux_audio_sec1,
+	msm_mux_core_voltage,
+	msm_mux_cri_trng0,
+	msm_mux_cri_trng1,
+	msm_mux_cri_trng2,
+	msm_mux_cri_trng3,
+	msm_mux_cxc_clk,
+	msm_mux_cxc_data,
+	msm_mux_dbg_out,
+	msm_mux_gcc_plltest,
+	msm_mux_gcc_tlmm,
+	msm_mux_gpio,
+	msm_mux_i2c0_scl,
+	msm_mux_i2c0_sda,
+	msm_mux_i2c1_scl,
+	msm_mux_i2c1_sda,
+	msm_mux_i2c11,
+	msm_mux_mac0,
+	msm_mux_mac1,
+	msm_mux_mdc_mst,
+	msm_mux_mdc_slv,
+	msm_mux_mdio_mst,
+	msm_mux_mdio_slv,
+	msm_mux_pcie0_clk,
+	msm_mux_pcie0_wake,
+	msm_mux_pcie1_clk,
+	msm_mux_pcie1_wake,
+	msm_mux_pcie2_clk,
+	msm_mux_pcie2_wake,
+	msm_mux_pcie3_clk,
+	msm_mux_pcie3_wake,
+	msm_mux_pll_test,
+	msm_mux_prng_rosc0,
+	msm_mux_prng_rosc1,
+	msm_mux_prng_rosc2,
+	msm_mux_prng_rosc3,
+	msm_mux_PTA0_0,
+	msm_mux_PTA0_1,
+	msm_mux_PTA0_2,
+	msm_mux_PTA10,
+	msm_mux_PTA11,
+	msm_mux_pwm0,
+	msm_mux_pwm1,
+	msm_mux_pwm2,
+	msm_mux_qdss_cti_trig_in_a0,
+	msm_mux_qdss_cti_trig_out_a0,
+	msm_mux_qdss_cti_trig_in_a1,
+	msm_mux_qdss_cti_trig_out_a1,
+	msm_mux_qdss_cti_trig_in_b0,
+	msm_mux_qdss_cti_trig_out_b0,
+	msm_mux_qdss_cti_trig_in_b1,
+	msm_mux_qdss_cti_trig_out_b1,
+	msm_mux_qdss_traceclk_a,
+	msm_mux_qdss_tracectl_a,
+	msm_mux_qdss_tracedata_a,
+	msm_mux_qspi_clk,
+	msm_mux_qspi_cs,
+	msm_mux_qspi_data,
+	msm_mux_resout,
+	msm_mux_rx0,
+	msm_mux_rx1,
+	msm_mux_rx2,
+	msm_mux_sdc_clk,
+	msm_mux_sdc_cmd,
+	msm_mux_sdc_data,
+	msm_mux_spi0,
+	msm_mux_spi1,
+	msm_mux_spi10,
+	msm_mux_spi11,
+	msm_mux_tsens_max,
+	msm_mux_uart0,
+	msm_mux_uart1,
+	msm_mux_wci_txd,
+	msm_mux_wci_rxd,
+	msm_mux_wsi_clk,
+	msm_mux_wsi_data,
+	msm_mux__,
+};
+
+static const char * const gpio_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7",
+	"gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14",
+	"gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21",
+	"gpio22", "gpio23", "gpio24", "gpio25", "gpio26", "gpio27", "gpio28",
+	"gpio29", "gpio30", "gpio31", "gpio32", "gpio33", "gpio34", "gpio35",
+	"gpio36", "gpio37", "gpio38", "gpio39", "gpio40", "gpio41", "gpio42",
+	"gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48", "gpio49",
+};
+
+static const char * const sdc_data_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3",
+};
+
+static const char * const qspi_data_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3",
+};
+
+static const char * const pwm2_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3",
+};
+
+static const char * const wci_txd_groups[] = {
+	"gpio0", "gpio1", "gpio8", "gpio10", "gpio11", "gpio40", "gpio41",
+};
+
+static const char * const wci_rxd_groups[] = {
+	"gpio0", "gpio1", "gpio8", "gpio10", "gpio11", "gpio40", "gpio41",
+};
+
+static const char * const sdc_cmd_groups[] = {
+	"gpio4",
+};
+
+static const char * const qspi_cs_groups[] = {
+	"gpio4",
+};
+
+static const char * const qdss_cti_trig_out_a1_groups[] = {
+	"gpio27",
+};
+
+static const char * const sdc_clk_groups[] = {
+	"gpio5",
+};
+
+static const char * const qspi_clk_groups[] = {
+	"gpio5",
+};
+
+static const char * const spi0_groups[] = {
+	"gpio6", "gpio7", "gpio8", "gpio9",
+};
+
+static const char * const pwm1_groups[] = {
+	"gpio6", "gpio7", "gpio8", "gpio9",
+};
+
+static const char * const cri_trng0_groups[] = {
+	"gpio6",
+};
+
+static const char * const qdss_tracedata_a_groups[] = {
+	"gpio6", "gpio7", "gpio8", "gpio9", "gpio10", "gpio11", "gpio12",
+	"gpio13", "gpio14", "gpio15", "gpio20", "gpio21", "gpio36", "gpio37",
+	"gpio38", "gpio39",
+};
+
+static const char * const cri_trng1_groups[] = {
+	"gpio7",
+};
+
+static const char * const cri_trng2_groups[] = {
+	"gpio8",
+};
+
+static const char * const cri_trng3_groups[] = {
+	"gpio9",
+};
+
+static const char * const uart0_groups[] = {
+	"gpio10", "gpio11", "gpio12", "gpio13",
+};
+
+static const char * const pwm0_groups[] = {
+	"gpio10", "gpio11", "gpio12", "gpio13",
+};
+
+static const char * const prng_rosc0_groups[] = {
+	"gpio12",
+};
+
+static const char * const prng_rosc1_groups[] = {
+	"gpio13",
+};
+
+static const char * const i2c0_scl_groups[] = {
+	"gpio14",
+};
+
+static const char * const tsens_max_groups[] = {
+	"gpio14",
+};
+
+static const char * const prng_rosc2_groups[] = {
+	"gpio14",
+};
+
+static const char * const i2c0_sda_groups[] = {
+	"gpio15",
+};
+
+static const char * const prng_rosc3_groups[] = {
+	"gpio15",
+};
+
+static const char * const core_voltage_groups[] = {
+	"gpio16", "gpio17",
+};
+
+static const char * const i2c1_scl_groups[] = {
+	"gpio16",
+};
+
+static const char * const i2c1_sda_groups[] = {
+	"gpio17",
+};
+
+static const char * const mdc_slv_groups[] = {
+	"gpio20",
+};
+
+static const char * const atest_char0_groups[] = {
+	"gpio20",
+};
+
+static const char * const mdio_slv_groups[] = {
+	"gpio21",
+};
+
+static const char * const atest_char1_groups[] = {
+	"gpio21",
+};
+
+static const char * const mdc_mst_groups[] = {
+	"gpio22",
+};
+
+static const char * const atest_char2_groups[] = {
+	"gpio22",
+};
+
+static const char * const mdio_mst_groups[] = {
+	"gpio23",
+};
+
+static const char * const atest_char3_groups[] = {
+	"gpio23",
+};
+
+static const char * const pcie0_clk_groups[] = {
+	"gpio24",
+};
+
+static const char * const PTA10_groups[] = {
+	"gpio24", "gpio26", "gpio27",
+};
+
+static const char * const mac0_groups[] = {
+	"gpio24", "gpio26",
+};
+
+static const char * const atest_char_groups[] = {
+	"gpio24",
+};
+
+static const char * const pcie0_wake_groups[] = {
+	"gpio26",
+};
+
+static const char * const pcie1_clk_groups[] = {
+	"gpio27",
+};
+
+static const char * const i2c11_groups[] = {
+	"gpio27", "gpio29",
+};
+
+static const char * const pcie1_wake_groups[] = {
+	"gpio29",
+};
+
+static const char * const pcie2_clk_groups[] = {
+	"gpio30",
+};
+
+static const char * const mac1_groups[] = {
+	"gpio30", "gpio32",
+};
+
+static const char * const pcie2_wake_groups[] = {
+	"gpio32",
+};
+
+static const char * const PTA11_groups[] = {
+	"gpio30", "gpio32", "gpio33",
+};
+
+static const char * const audio_pri0_groups[] = {
+	"gpio32", "gpio32",
+};
+
+static const char * const pcie3_clk_groups[] = {
+	"gpio33",
+};
+
+static const char * const audio_pri1_groups[] = {
+	"gpio33", "gpio33",
+};
+
+static const char * const pcie3_wake_groups[] = {
+	"gpio35",
+};
+
+static const char * const audio_sec1_groups[] = {
+	"gpio35", "gpio35",
+};
+
+static const char * const audio_pri_groups[] = {
+	"gpio36", "gpio37", "gpio38", "gpio39",
+};
+
+static const char * const spi1_groups[] = {
+	"gpio11", "gpio36", "gpio37", "gpio38", "gpio46",
+};
+
+static const char * const audio_sec0_groups[] = {
+	"gpio36", "gpio36",
+};
+
+static const char * const rx1_groups[] = {
+	"gpio38", "gpio46",
+};
+
+static const char * const pll_test_groups[] = {
+	"gpio38",
+};
+
+static const char * const dbg_out_groups[] = {
+	"gpio46",
+};
+
+static const char * const PTA0_0_groups[] = {
+	"gpio40",
+};
+
+static const char * const atest_tic_groups[] = {
+	"gpio40",
+};
+
+static const char * const PTA0_1_groups[] = {
+	"gpio41",
+};
+
+static const char * const cxc_data_groups[] = {
+	"gpio41",
+};
+
+static const char * const PTA0_2_groups[] = {
+	"gpio42",
+};
+
+static const char * const cxc_clk_groups[] = {
+	"gpio42",
+};
+
+static const char * const uart1_groups[] = {
+	"gpio43", "gpio44",
+};
+
+static const char * const audio_sec_groups[] = {
+	"gpio45", "gpio46", "gpio47", "gpio48",
+};
+
+static const char * const gcc_plltest_groups[] = {
+	"gpio43", "gpio45",
+};
+
+static const char * const gcc_tlmm_groups[] = {
+	"gpio44",
+};
+
+static const char * const qdss_cti_trig_out_b1_groups[] = {
+	"gpio33",
+};
+
+static const char * const rx0_groups[] = {
+	"gpio39", "gpio47",
+};
+
+static const char * const qdss_traceclk_a_groups[] = {
+	"gpio45",
+};
+
+static const char * const qdss_tracectl_a_groups[] = {
+	"gpio46",
+};
+
+static const char * const qdss_cti_trig_out_a0_groups[] = {
+	"gpio24",
+};
+
+static const char * const qdss_cti_trig_in_a0_groups[] = {
+	"gpio26",
+};
+
+static const char * const resout_groups[] = {
+	"gpio49",
+};
+
+static const char * const qdss_cti_trig_in_a1_groups[] = {
+	"gpio29",
+};
+
+static const char * const qdss_cti_trig_out_b0_groups[] = {
+	"gpio30",
+};
+
+static const char * const qdss_cti_trig_in_b0_groups[] = {
+	"gpio32",
+};
+
+static const char * const qdss_cti_trig_in_b1_groups[] = {
+	"gpio35",
+};
+
+static const char * const spi10_groups[] = {
+	"gpio45", "gpio47", "gpio48",
+};
+
+static const char * const spi11_groups[] = {
+	"gpio10", "gpio12", "gpio13",
+};
+
+static const char * const wsi_clk_groups[] = {
+	"gpio24", "gpio27",
+};
+
+static const char * const wsi_data_groups[] = {
+	"gpio26", "gpio29",
+};
+
+static const char * const rx2_groups[] = {
+	"gpio37", "gpio45",
+};
+
+static const struct pinfunction ipq5424_functions[] = {
+	MSM_PIN_FUNCTION(atest_char),
+	MSM_PIN_FUNCTION(atest_char0),
+	MSM_PIN_FUNCTION(atest_char1),
+	MSM_PIN_FUNCTION(atest_char2),
+	MSM_PIN_FUNCTION(atest_char3),
+	MSM_PIN_FUNCTION(atest_tic),
+	MSM_PIN_FUNCTION(audio_pri),
+	MSM_PIN_FUNCTION(audio_pri0),
+	MSM_PIN_FUNCTION(audio_pri1),
+	MSM_PIN_FUNCTION(audio_sec),
+	MSM_PIN_FUNCTION(audio_sec0),
+	MSM_PIN_FUNCTION(audio_sec1),
+	MSM_PIN_FUNCTION(core_voltage),
+	MSM_PIN_FUNCTION(cri_trng0),
+	MSM_PIN_FUNCTION(cri_trng1),
+	MSM_PIN_FUNCTION(cri_trng2),
+	MSM_PIN_FUNCTION(cri_trng3),
+	MSM_PIN_FUNCTION(cxc_clk),
+	MSM_PIN_FUNCTION(cxc_data),
+	MSM_PIN_FUNCTION(dbg_out),
+	MSM_PIN_FUNCTION(gcc_plltest),
+	MSM_PIN_FUNCTION(gcc_tlmm),
+	MSM_PIN_FUNCTION(gpio),
+	MSM_PIN_FUNCTION(i2c0_scl),
+	MSM_PIN_FUNCTION(i2c0_sda),
+	MSM_PIN_FUNCTION(i2c1_scl),
+	MSM_PIN_FUNCTION(i2c1_sda),
+	MSM_PIN_FUNCTION(i2c11),
+	MSM_PIN_FUNCTION(mac0),
+	MSM_PIN_FUNCTION(mac1),
+	MSM_PIN_FUNCTION(mdc_mst),
+	MSM_PIN_FUNCTION(mdc_slv),
+	MSM_PIN_FUNCTION(mdio_mst),
+	MSM_PIN_FUNCTION(mdio_slv),
+	MSM_PIN_FUNCTION(pcie0_clk),
+	MSM_PIN_FUNCTION(pcie0_wake),
+	MSM_PIN_FUNCTION(pcie1_clk),
+	MSM_PIN_FUNCTION(pcie1_wake),
+	MSM_PIN_FUNCTION(pcie2_clk),
+	MSM_PIN_FUNCTION(pcie2_wake),
+	MSM_PIN_FUNCTION(pcie3_clk),
+	MSM_PIN_FUNCTION(pcie3_wake),
+	MSM_PIN_FUNCTION(pll_test),
+	MSM_PIN_FUNCTION(prng_rosc0),
+	MSM_PIN_FUNCTION(prng_rosc1),
+	MSM_PIN_FUNCTION(prng_rosc2),
+	MSM_PIN_FUNCTION(prng_rosc3),
+	MSM_PIN_FUNCTION(PTA0_0),
+	MSM_PIN_FUNCTION(PTA0_1),
+	MSM_PIN_FUNCTION(PTA0_2),
+	MSM_PIN_FUNCTION(PTA10),
+	MSM_PIN_FUNCTION(PTA11),
+	MSM_PIN_FUNCTION(pwm0),
+	MSM_PIN_FUNCTION(pwm1),
+	MSM_PIN_FUNCTION(pwm2),
+	MSM_PIN_FUNCTION(qdss_cti_trig_in_a0),
+	MSM_PIN_FUNCTION(qdss_cti_trig_out_a0),
+	MSM_PIN_FUNCTION(qdss_cti_trig_in_a1),
+	MSM_PIN_FUNCTION(qdss_cti_trig_out_a1),
+	MSM_PIN_FUNCTION(qdss_cti_trig_in_b0),
+	MSM_PIN_FUNCTION(qdss_cti_trig_out_b0),
+	MSM_PIN_FUNCTION(qdss_cti_trig_in_b1),
+	MSM_PIN_FUNCTION(qdss_cti_trig_out_b1),
+	MSM_PIN_FUNCTION(qdss_traceclk_a),
+	MSM_PIN_FUNCTION(qdss_tracectl_a),
+	MSM_PIN_FUNCTION(qdss_tracedata_a),
+	MSM_PIN_FUNCTION(qspi_clk),
+	MSM_PIN_FUNCTION(qspi_cs),
+	MSM_PIN_FUNCTION(qspi_data),
+	MSM_PIN_FUNCTION(resout),
+	MSM_PIN_FUNCTION(rx0),
+	MSM_PIN_FUNCTION(rx1),
+	MSM_PIN_FUNCTION(rx2),
+	MSM_PIN_FUNCTION(sdc_clk),
+	MSM_PIN_FUNCTION(sdc_cmd),
+	MSM_PIN_FUNCTION(sdc_data),
+	MSM_PIN_FUNCTION(spi0),
+	MSM_PIN_FUNCTION(spi1),
+	MSM_PIN_FUNCTION(spi10),
+	MSM_PIN_FUNCTION(spi11),
+	MSM_PIN_FUNCTION(tsens_max),
+	MSM_PIN_FUNCTION(uart0),
+	MSM_PIN_FUNCTION(uart1),
+	MSM_PIN_FUNCTION(wci_txd),
+	MSM_PIN_FUNCTION(wci_rxd),
+	MSM_PIN_FUNCTION(wsi_clk),
+	MSM_PIN_FUNCTION(wsi_data),
+};
+
+static const struct msm_pingroup ipq5424_groups[] = {
+	PINGROUP(0, sdc_data, qspi_data, pwm2, wci_txd, wci_rxd, _, _, _, _),
+	PINGROUP(1, sdc_data, qspi_data, pwm2, wci_txd, wci_rxd, _, _, _, _),
+	PINGROUP(2, sdc_data, qspi_data, pwm2, _, _, _, _, _, _),
+	PINGROUP(3, sdc_data, qspi_data, pwm2, _, _, _, _, _, _),
+	PINGROUP(4, sdc_cmd, qspi_cs, _, _, _, _, _, _, _),
+	PINGROUP(5, sdc_clk, qspi_clk, _, _, _, _, _, _, _),
+	PINGROUP(6, spi0, pwm1, _, cri_trng0, qdss_tracedata_a, _, _, _, _),
+	PINGROUP(7, spi0, pwm1, _, cri_trng1, qdss_tracedata_a, _, _, _, _),
+	PINGROUP(8, spi0, pwm1, wci_txd, wci_rxd, _, cri_trng2, qdss_tracedata_a, _, _),
+	PINGROUP(9, spi0, pwm1, _, cri_trng3, qdss_tracedata_a, _, _, _, _),
+	PINGROUP(10, uart0, pwm0, spi11, _, wci_txd, wci_rxd, _, qdss_tracedata_a, _),
+	PINGROUP(11, uart0, pwm0, spi1, _, wci_txd, wci_rxd, _, qdss_tracedata_a, _),
+	PINGROUP(12, uart0, pwm0, spi11, _, prng_rosc0, qdss_tracedata_a, _, _, _),
+	PINGROUP(13, uart0, pwm0, spi11, _, prng_rosc1, qdss_tracedata_a, _, _, _),
+	PINGROUP(14, i2c0_scl, tsens_max, _, prng_rosc2, qdss_tracedata_a, _, _, _, _),
+	PINGROUP(15, i2c0_sda, _, prng_rosc3, qdss_tracedata_a, _, _, _, _, _),
+	PINGROUP(16, core_voltage, i2c1_scl, _, _, _, _, _, _, _),
+	PINGROUP(17, core_voltage, i2c1_sda, _, _, _, _, _, _, _),
+	PINGROUP(18, _, _, _, _, _, _, _, _, _),
+	PINGROUP(19, _, _, _, _, _, _, _, _, _),
+	PINGROUP(20, mdc_slv, atest_char0, _, qdss_tracedata_a, _, _, _, _, _),
+	PINGROUP(21, mdio_slv, atest_char1, _, qdss_tracedata_a, _, _, _, _, _),
+	PINGROUP(22, mdc_mst, atest_char2, _, _, _, _, _, _, _),
+	PINGROUP(23, mdio_mst, atest_char3, _, _, _, _, _, _, _),
+	PINGROUP(24, pcie0_clk, PTA10, mac0, _, wsi_clk, _, atest_char, qdss_cti_trig_out_a0, _),
+	PINGROUP(25, _, _, _, _, _, _, _, _, _),
+	PINGROUP(26, pcie0_wake, PTA10, mac0, _, wsi_data, _, qdss_cti_trig_in_a0, _, _),
+	PINGROUP(27, pcie1_clk, i2c11, PTA10, wsi_clk, qdss_cti_trig_out_a1, _, _, _, _),
+	PINGROUP(28, _, _, _, _, _, _, _, _, _),
+	PINGROUP(29, pcie1_wake, i2c11, wsi_data, qdss_cti_trig_in_a1, _, _, _, _, _),
+	PINGROUP(30, pcie2_clk, PTA11, mac1, qdss_cti_trig_out_b0, _, _, _, _, _),
+	PINGROUP(31, _, _, _, _, _, _, _, _, _),
+	PINGROUP(32, pcie2_wake, PTA11, mac1, audio_pri0, audio_pri0, qdss_cti_trig_in_b0, _, _, _),
+	PINGROUP(33, pcie3_clk, PTA11, audio_pri1, audio_pri1, qdss_cti_trig_out_b1, _, _, _, _),
+	PINGROUP(34, _, _, _, _, _, _, _, _, _),
+	PINGROUP(35, pcie3_wake, audio_sec1, audio_sec1, qdss_cti_trig_in_b1, _, _, _, _, _),
+	PINGROUP(36, audio_pri, spi1, audio_sec0, audio_sec0, qdss_tracedata_a, _, _, _, _),
+	PINGROUP(37, audio_pri, spi1, rx2, qdss_tracedata_a, _, _, _, _, _),
+	PINGROUP(38, audio_pri, spi1, pll_test, rx1, qdss_tracedata_a, _, _, _, _),
+	PINGROUP(39, audio_pri, rx0, _, qdss_tracedata_a, _, _, _, _, _),
+	PINGROUP(40, PTA0_0, wci_txd, wci_rxd, _, atest_tic, _, _, _, _),
+	PINGROUP(41, PTA0_1, wci_txd, wci_rxd, cxc_data, _, _, _, _, _),
+	PINGROUP(42, PTA0_2, cxc_clk, _, _, _, _, _, _, _),
+	PINGROUP(43, uart1, gcc_plltest, _, _, _, _, _, _, _),
+	PINGROUP(44, uart1, gcc_tlmm, _, _, _, _, _, _, _),
+	PINGROUP(45, spi10, rx2, audio_sec, gcc_plltest, _, qdss_traceclk_a, _, _, _),
+	PINGROUP(46, spi1, rx1, audio_sec, dbg_out, qdss_tracectl_a, _, _, _, _),
+	PINGROUP(47, spi10, rx0, audio_sec, _, _, _, _, _, _),
+	PINGROUP(48, spi10, audio_sec, _, _, _, _, _, _, _),
+	PINGROUP(49, resout, _, _, _, _, _, _, _, _),
+};
+
+static const struct msm_pinctrl_soc_data ipq5424_pinctrl = {
+	.pins = ipq5424_pins,
+	.npins = ARRAY_SIZE(ipq5424_pins),
+	.functions = ipq5424_functions,
+	.nfunctions = ARRAY_SIZE(ipq5424_functions),
+	.groups = ipq5424_groups,
+	.ngroups = ARRAY_SIZE(ipq5424_groups),
+	.ngpios = 50,
+};
+
+static int ipq5424_pinctrl_probe(struct platform_device *pdev)
+{
+	return msm_pinctrl_probe(pdev, &ipq5424_pinctrl);
+}
+
+static const struct of_device_id ipq5424_pinctrl_of_match[] = {
+	{ .compatible = "qcom,ipq5424-tlmm", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ipq5424_pinctrl_of_match);
+
+static struct platform_driver ipq5424_pinctrl_driver = {
+	.driver = {
+		.name = "ipq5424-tlmm",
+		.of_match_table = ipq5424_pinctrl_of_match,
+	},
+	.probe = ipq5424_pinctrl_probe,
+	.remove = msm_pinctrl_remove,
+};
+
+static int __init ipq5424_pinctrl_init(void)
+{
+	return platform_driver_register(&ipq5424_pinctrl_driver);
+}
+arch_initcall(ipq5424_pinctrl_init);
+
+static void __exit ipq5424_pinctrl_exit(void)
+{
+	platform_driver_unregister(&ipq5424_pinctrl_driver);
+}
+module_exit(ipq5424_pinctrl_exit);
+
+MODULE_DESCRIPTION("QTI IPQ5424 TLMM driver");
+MODULE_LICENSE("GPL");

From 561f3e9d21a16df0148f5f209bdc26db3d86632b Mon Sep 17 00:00:00 2001
From: Ze Huang <18771902331@163.com>
Date: Thu, 26 Sep 2024 23:57:43 +0800
Subject: [PATCH 0067/1530] dt-bindings: pinctrl: Add support for canaan,k230
 SoC

Add device tree binding details for Canaan K230 pinctrl device.

Signed-off-by: Ze Huang <18771902331@163.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/20240926-k230-pinctrl-v2-1-a9a36fba4b34@163.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/canaan,k230-pinctrl.yaml | 127 ++++++++++++++++++
 1 file changed, 127 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/canaan,k230-pinctrl.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/canaan,k230-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/canaan,k230-pinctrl.yaml
new file mode 100644
index 0000000000000..0b462eb6dfe16
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/canaan,k230-pinctrl.yaml
@@ -0,0 +1,127 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/canaan,k230-pinctrl.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Canaan Kendryte K230 Pin Controller
+
+maintainers:
+  - Ze Huang <18771902331@163.com>
+
+description:
+  The Canaan Kendryte K230 platform includes 64 IO pins, each capable of
+  multiplexing up to 5 different functions. Pin function configuration is
+  performed on a per-pin basis.
+
+properties:
+  compatible:
+    const: canaan,k230-pinctrl
+
+  reg:
+    maxItems: 1
+
+patternProperties:
+  '-pins$':
+    type: object
+    additionalProperties: false
+    description:
+      A pinctrl node should contain at least one subnode representing the
+      pinctrl groups available on the machine.
+
+    patternProperties:
+      '-cfg$':
+        type: object
+        allOf:
+          - $ref: /schemas/pinctrl/pincfg-node.yaml
+          - $ref: /schemas/pinctrl/pinmux-node.yaml
+        additionalProperties: false
+        description:
+          Each subnode will list the pins it needs, and how they should
+          be configured, with regard to muxer configuration, bias, input
+          enable/disable, input schmitt trigger, slew-rate enable/disable,
+          slew-rate, drive strength.
+
+        properties:
+          pinmux:
+            description:
+              The list of GPIOs and their mux settings that properties in
+              the node apply to. This should be set with the macro
+              'K230_PINMUX(pin, mode)'
+
+          bias-disable: true
+
+          bias-pull-up: true
+
+          bias-pull-down: true
+
+          drive-strength:
+            minimum: 0
+            maximum: 15
+
+          input-enable: true
+
+          output-enable: true
+
+          input-schmitt-enable: true
+
+          slew-rate:
+            description: |
+              slew rate control enable
+              0: disable
+              1: enable
+
+            enum: [0, 1]
+
+          power-source:
+            description: |
+              Specifies the power source voltage for the IO bank that the
+              pin belongs to. Each bank of IO pins operate at a specific,
+              fixed voltage levels. Incorrect voltage configuration can
+              damage the chip. The defined constants represent the
+              possible voltage configurations:
+
+              - K230_MSC_3V3 (value 0): 3.3V power supply
+              - K230_MSC_1V8 (value 1): 1.8V power supply
+
+              The following banks have the corresponding voltage
+              configurations:
+
+              - bank IO0 to IO1: Fixed at 1.8V
+              - bank IO2 to IO13: Fixed at 1.8V
+              - bank IO14 to IO25: Fixed at 1.8V
+              - bank IO26 to IO37: Fixed at 1.8V
+              - bank IO38 to IO49: Fixed at 1.8V
+              - bank IO50 to IO61: Fixed at 3.3V
+              - bank IO62 to IO63: Fixed at 1.8V
+
+            enum: [0, 1]
+
+        required:
+          - pinmux
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    pinctrl@91105000 {
+        compatible = "canaan,k230-pinctrl";
+        reg = <0x91105000 0x100>;
+
+        uart2-pins {
+            uart2-pins-cfg {
+                pinmux = <0x503>, /* uart2 txd */
+                         <0x603>; /* uart2 rxd */
+                slew-rate = <0>;
+                drive-strength = <4>;
+                power-source = <1>;
+                input-enable;
+                output-enable;
+                bias-disable;
+            };
+        };
+    };

From 545887eab6f6776a7477fe7e83860eab57138b03 Mon Sep 17 00:00:00 2001
From: Ze Huang <18771902331@163.com>
Date: Thu, 26 Sep 2024 23:57:44 +0800
Subject: [PATCH 0068/1530] pinctrl: canaan: Add support for k230 SoC

Configuration of the K230 is similar to that of the K210. However, in
K210, the 256 functions for each pin are shared, whereas in K230,
multiplex functions are different for every pin.

`drv_data` of `pinctrl_pin_desc` is pointing to currently activated
group, which is used to print the name of current function of pin in
`pin_dbg_show` and will be updated in `set_mux`, so they are not set
const.

Signed-off-by: Ze Huang <18771902331@163.com>
Link: https://lore.kernel.org/20240926-k230-pinctrl-v2-2-a9a36fba4b34@163.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/Kconfig        |  10 +
 drivers/pinctrl/Makefile       |   1 +
 drivers/pinctrl/pinctrl-k230.c | 643 +++++++++++++++++++++++++++++++++
 3 files changed, 654 insertions(+)
 create mode 100644 drivers/pinctrl/pinctrl-k230.c

diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index 5bf58e138ce30..a6acc27c9a83c 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -268,6 +268,16 @@ config PINCTRL_K210
 	  Add support for the Canaan Kendryte K210 RISC-V SOC Field
 	  Programmable IO Array (FPIOA) controller.
 
+config PINCTRL_K230
+	bool "Pinctrl driver for the Canaan Kendryte K230 SoC"
+	depends on OF
+	select GENERIC_PINCTRL_GROUPS
+	select GENERIC_PINMUX_FUNCTIONS
+	select GENERIC_PINCONF
+	select REGMAP_MMIO
+	help
+	  Add support for the Canaan Kendryte K230 RISC-V SOC pin controller.
+
 config PINCTRL_KEEMBAY
 	tristate "Pinctrl driver for Intel Keem Bay SoC"
 	depends on ARCH_KEEMBAY || (ARM64 && COMPILE_TEST)
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index 26180a616d139..efbe255fa8e1f 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_PINCTRL_EYEQ5)	+= pinctrl-eyeq5.o
 obj-$(CONFIG_PINCTRL_GEMINI)	+= pinctrl-gemini.o
 obj-$(CONFIG_PINCTRL_INGENIC)	+= pinctrl-ingenic.o
 obj-$(CONFIG_PINCTRL_K210)	+= pinctrl-k210.o
+obj-$(CONFIG_PINCTRL_K230)	+= pinctrl-k230.o
 obj-$(CONFIG_PINCTRL_KEEMBAY)	+= pinctrl-keembay.o
 obj-$(CONFIG_PINCTRL_LANTIQ)	+= pinctrl-lantiq.o
 obj-$(CONFIG_PINCTRL_FALCON)	+= pinctrl-falcon.o
diff --git a/drivers/pinctrl/pinctrl-k230.c b/drivers/pinctrl/pinctrl-k230.c
new file mode 100644
index 0000000000000..4266516886fce
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-k230.c
@@ -0,0 +1,643 @@
+// SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+/*
+ * Copyright (C) 2024 Canaan Bright Sight Co. Ltd
+ * Copyright (C) 2024 Ze Huang <18771902331@163.com>
+ */
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinmux.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/regmap.h>
+#include <linux/seq_file.h>
+
+#include "core.h"
+#include "pinconf.h"
+
+#define K230_NPINS 64
+
+#define K230_SHIFT_ST		(0)
+#define K230_SHIFT_DS		(1)
+#define K230_SHIFT_BIAS		(5)
+#define K230_SHIFT_PD		(5)
+#define K230_SHIFT_PU		(6)
+#define K230_SHIFT_OE		(7)
+#define K230_SHIFT_IE		(8)
+#define K230_SHIFT_MSC		(9)
+#define K230_SHIFT_SL		(10)
+#define K230_SHIFT_SEL		(11)
+
+#define K230_PC_ST		BIT(0)
+#define K230_PC_DS		GENMASK(4, 1)
+#define K230_PC_PD		BIT(5)
+#define K230_PC_PU		BIT(6)
+#define K230_PC_BIAS		GENMASK(6, 5)
+#define K230_PC_OE		BIT(7)
+#define K230_PC_IE		BIT(8)
+#define K230_PC_MSC		BIT(9)
+#define K230_PC_SL		BIT(10)
+#define K230_PC_SEL		GENMASK(13, 11)
+
+struct k230_pin_conf {
+	unsigned int		func;
+	unsigned long		*configs;
+	unsigned int		nconfigs;
+};
+
+struct k230_pin_group {
+	const char		*name;
+	unsigned int		*pins;
+	unsigned int		num_pins;
+
+	struct k230_pin_conf	*data;
+};
+
+struct k230_pmx_func {
+	const char		*name;
+	const char		**groups;
+	unsigned int		*group_idx;
+	unsigned int		ngroups;
+};
+
+struct k230_pinctrl {
+	struct pinctrl_desc	pctl;
+	struct pinctrl_dev	*pctl_dev;
+	struct regmap		*regmap_base;
+	void __iomem		*base;
+	struct k230_pin_group	*groups;
+	unsigned int		ngroups;
+	struct k230_pmx_func	*functions;
+	unsigned int		nfunctions;
+};
+
+static const struct regmap_config k230_regmap_config = {
+	.name		= "canaan,pinctrl",
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.max_register	= 0x100,
+	.reg_stride	= 4,
+};
+
+static int k230_get_groups_count(struct pinctrl_dev *pctldev)
+{
+	struct k230_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+
+	return info->ngroups;
+}
+
+static const char *k230_get_group_name(struct pinctrl_dev *pctldev,
+				       unsigned int selector)
+{
+	struct k230_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+
+	return info->groups[selector].name;
+}
+
+static int k230_get_group_pins(struct pinctrl_dev *pctldev,
+			       unsigned int selector,
+			       const unsigned int **pins,
+			       unsigned int *num_pins)
+{
+	struct k230_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+
+	if (selector >= info->ngroups)
+		return -EINVAL;
+
+	*pins = info->groups[selector].pins;
+	*num_pins = info->groups[selector].num_pins;
+
+	return 0;
+}
+
+static inline const struct k230_pmx_func *k230_name_to_funtion(
+		const struct k230_pinctrl *info, const char *name)
+{
+	unsigned int i;
+
+	for (i = 0; i < info->nfunctions; i++) {
+		if (!strcmp(info->functions[i].name, name))
+			return &info->functions[i];
+	}
+
+	return NULL;
+}
+
+static struct pinctrl_pin_desc k230_pins[] = {
+	PINCTRL_PIN(0,  "IO0"),  PINCTRL_PIN(1,  "IO1"),  PINCTRL_PIN(2,  "IO2"),
+	PINCTRL_PIN(3,  "IO3"),  PINCTRL_PIN(4,  "IO4"),  PINCTRL_PIN(5,  "IO5"),
+	PINCTRL_PIN(6,  "IO6"),  PINCTRL_PIN(7,  "IO7"),  PINCTRL_PIN(8,  "IO8"),
+	PINCTRL_PIN(9,  "IO9"),  PINCTRL_PIN(10, "IO10"), PINCTRL_PIN(11, "IO11"),
+	PINCTRL_PIN(12, "IO12"), PINCTRL_PIN(13, "IO13"), PINCTRL_PIN(14, "IO14"),
+	PINCTRL_PIN(15, "IO15"), PINCTRL_PIN(16, "IO16"), PINCTRL_PIN(17, "IO17"),
+	PINCTRL_PIN(18, "IO18"), PINCTRL_PIN(19, "IO19"), PINCTRL_PIN(20, "IO20"),
+	PINCTRL_PIN(21, "IO21"), PINCTRL_PIN(22, "IO22"), PINCTRL_PIN(23, "IO23"),
+	PINCTRL_PIN(24, "IO24"), PINCTRL_PIN(25, "IO25"), PINCTRL_PIN(26, "IO26"),
+	PINCTRL_PIN(27, "IO27"), PINCTRL_PIN(28, "IO28"), PINCTRL_PIN(29, "IO29"),
+	PINCTRL_PIN(30, "IO30"), PINCTRL_PIN(31, "IO31"), PINCTRL_PIN(32, "IO32"),
+	PINCTRL_PIN(33, "IO33"), PINCTRL_PIN(34, "IO34"), PINCTRL_PIN(35, "IO35"),
+	PINCTRL_PIN(36, "IO36"), PINCTRL_PIN(37, "IO37"), PINCTRL_PIN(38, "IO38"),
+	PINCTRL_PIN(39, "IO39"), PINCTRL_PIN(40, "IO40"), PINCTRL_PIN(41, "IO41"),
+	PINCTRL_PIN(42, "IO42"), PINCTRL_PIN(43, "IO43"), PINCTRL_PIN(44, "IO44"),
+	PINCTRL_PIN(45, "IO45"), PINCTRL_PIN(46, "IO46"), PINCTRL_PIN(47, "IO47"),
+	PINCTRL_PIN(48, "IO48"), PINCTRL_PIN(49, "IO49"), PINCTRL_PIN(50, "IO50"),
+	PINCTRL_PIN(51, "IO51"), PINCTRL_PIN(52, "IO52"), PINCTRL_PIN(53, "IO53"),
+	PINCTRL_PIN(54, "IO54"), PINCTRL_PIN(55, "IO55"), PINCTRL_PIN(56, "IO56"),
+	PINCTRL_PIN(57, "IO57"), PINCTRL_PIN(58, "IO58"), PINCTRL_PIN(59, "IO59"),
+	PINCTRL_PIN(60, "IO60"), PINCTRL_PIN(61, "IO61"), PINCTRL_PIN(62, "IO62"),
+	PINCTRL_PIN(63, "IO63")
+};
+
+static void k230_pinctrl_pin_dbg_show(struct pinctrl_dev *pctldev,
+				      struct seq_file *s, unsigned int offset)
+{
+	struct k230_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+	u32 val, mode, bias, drive, input, output, slew, schmitt, power;
+	struct k230_pin_group *grp = k230_pins[offset].drv_data;
+	static const char * const biasing[] = {
+			"pull none", "pull down", "pull up", "" };
+	static const char * const enable[] = {
+			"disable", "enable" };
+	static const char * const power_source[] = {
+			"3V3", "1V8" };
+
+	regmap_read(info->regmap_base, offset * 4, &val);
+
+	mode	= (val & K230_PC_SEL) >> K230_SHIFT_SEL;
+	drive	= (val & K230_PC_DS) >> K230_SHIFT_DS;
+	bias	= (val & K230_PC_BIAS) >> K230_SHIFT_BIAS;
+	input	= (val & K230_PC_IE) >> K230_SHIFT_IE;
+	output	= (val & K230_PC_OE) >> K230_SHIFT_OE;
+	slew	= (val & K230_PC_SL) >> K230_SHIFT_SL;
+	schmitt	= (val & K230_PC_ST) >> K230_SHIFT_ST;
+	power	= (val & K230_PC_MSC) >> K230_SHIFT_MSC;
+
+	seq_printf(s, "%s - strength %d - %s - %s - slewrate %s - schmitt %s - %s",
+		   grp ? grp->name : "unknown",
+		   drive,
+		   biasing[bias],
+		   input ? "input" : "output",
+		   enable[slew],
+		   enable[schmitt],
+		   power_source[power]);
+}
+
+static int k230_dt_node_to_map(struct pinctrl_dev *pctldev,
+			       struct device_node *np_config,
+			       struct pinctrl_map **map,
+			       unsigned int *num_maps)
+{
+	struct k230_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+	struct device *dev = info->pctl_dev->dev;
+	const struct k230_pmx_func *func;
+	const struct k230_pin_group *grp;
+	struct pinctrl_map *new_map;
+	int map_num, i, j, idx;
+	unsigned int grp_id;
+
+	func = k230_name_to_funtion(info, np_config->name);
+	if (!func) {
+		dev_err(dev, "function %s not found\n", np_config->name);
+		return -EINVAL;
+	}
+
+	map_num = 0;
+	for (i = 0; i < func->ngroups; ++i) {
+		grp_id = func->group_idx[i];
+		/* npins of config map plus a mux map */
+		map_num += info->groups[grp_id].num_pins + 1;
+	}
+
+	new_map = kcalloc(map_num, sizeof(*new_map), GFP_KERNEL);
+	if (!new_map)
+		return -ENOMEM;
+	*map = new_map;
+	*num_maps = map_num;
+
+	idx = 0;
+	for (i = 0; i < func->ngroups; ++i) {
+		grp_id = func->group_idx[i];
+		grp = &info->groups[grp_id];
+		new_map[idx].type = PIN_MAP_TYPE_MUX_GROUP;
+		new_map[idx].data.mux.group = grp->name;
+		new_map[idx].data.mux.function = np_config->name;
+		idx++;
+
+		for (j = 0; j < grp->num_pins; ++j) {
+			new_map[idx].type = PIN_MAP_TYPE_CONFIGS_PIN;
+			new_map[idx].data.configs.group_or_pin =
+				pin_get_name(pctldev, grp->pins[j]);
+			new_map[idx].data.configs.configs =
+				grp->data[j].configs;
+			new_map[idx].data.configs.num_configs =
+				grp->data[j].nconfigs;
+			idx++;
+		}
+	}
+
+	return 0;
+}
+
+static void k230_dt_free_map(struct pinctrl_dev *pctldev,
+			     struct pinctrl_map *map, unsigned int num_maps)
+{
+	kfree(map);
+}
+
+static const struct pinctrl_ops k230_pctrl_ops = {
+	.get_groups_count	= k230_get_groups_count,
+	.get_group_name		= k230_get_group_name,
+	.get_group_pins		= k230_get_group_pins,
+	.pin_dbg_show		= k230_pinctrl_pin_dbg_show,
+	.dt_node_to_map		= k230_dt_node_to_map,
+	.dt_free_map		= k230_dt_free_map,
+};
+
+static int k230_pinconf_get(struct pinctrl_dev *pctldev, unsigned int pin,
+			    unsigned long *config)
+{
+	struct k230_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+	enum pin_config_param param = pinconf_to_config_param(*config);
+	unsigned int val, arg;
+
+	regmap_read(info->regmap_base, pin * 4, &val);
+
+	switch (param) {
+	case PIN_CONFIG_INPUT_SCHMITT_ENABLE:
+		arg = (val & K230_PC_ST) ? 1 : 0;
+		break;
+	case PIN_CONFIG_DRIVE_STRENGTH:
+		arg = (val & K230_PC_DS) >> K230_SHIFT_DS;
+		break;
+	case PIN_CONFIG_BIAS_DISABLE:
+		arg = (val & K230_PC_BIAS) ? 0 : 1;
+		break;
+	case PIN_CONFIG_BIAS_PULL_DOWN:
+		arg = (val & K230_PC_PD) ? 1 : 0;
+		break;
+	case PIN_CONFIG_BIAS_PULL_UP:
+		arg = (val & K230_PC_PU) ? 1 : 0;
+		break;
+	case PIN_CONFIG_OUTPUT_ENABLE:
+		arg = (val & K230_PC_OE) ? 1 : 0;
+		break;
+	case PIN_CONFIG_INPUT_ENABLE:
+		arg = (val & K230_PC_IE) ? 1 : 0;
+		break;
+	case PIN_CONFIG_POWER_SOURCE:
+		arg = (val & K230_PC_MSC) ? 1 : 0;
+		break;
+	case PIN_CONFIG_SLEW_RATE:
+		arg = (val & K230_PC_SL) ? 1 : 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*config = pinconf_to_config_packed(param, arg);
+
+	return 0;
+}
+
+static int k230_pinconf_set_param(struct pinctrl_dev *pctldev, unsigned int pin,
+				  enum pin_config_param param, unsigned int arg)
+{
+	struct k230_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+	unsigned int val;
+
+	regmap_read(info->regmap_base, pin * 4, &val);
+
+	switch (param) {
+	case PIN_CONFIG_INPUT_SCHMITT_ENABLE:
+		if (arg)
+			val |= K230_PC_ST;
+		else
+			val &= ~K230_PC_ST;
+		break;
+	case PIN_CONFIG_DRIVE_STRENGTH:
+		val &= ~K230_PC_DS;
+		val |= (arg << K230_SHIFT_DS) & K230_PC_DS;
+		break;
+	case PIN_CONFIG_BIAS_DISABLE:
+		val &= ~K230_PC_BIAS;
+		break;
+	case PIN_CONFIG_BIAS_PULL_DOWN:
+		if (!arg)
+			return -EINVAL;
+		val |= K230_PC_PD;
+		break;
+	case PIN_CONFIG_BIAS_PULL_UP:
+		if (!arg)
+			return -EINVAL;
+		val |= K230_PC_PU;
+		break;
+	case PIN_CONFIG_OUTPUT_ENABLE:
+		if (!arg)
+			return -EINVAL;
+		val |= K230_PC_OE;
+		break;
+	case PIN_CONFIG_INPUT_ENABLE:
+		if (!arg)
+			return -EINVAL;
+		val |= K230_PC_IE;
+		break;
+	case PIN_CONFIG_POWER_SOURCE:
+		if (arg)
+			val |= K230_PC_MSC;
+		else
+			val &= ~K230_PC_MSC;
+		break;
+	case PIN_CONFIG_SLEW_RATE:
+		if (arg)
+			val |= K230_PC_SL;
+		else
+			val &= ~K230_PC_SL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	regmap_write(info->regmap_base, pin * 4, val);
+
+	return 0;
+}
+
+static int k230_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
+			    unsigned long *configs, unsigned int num_configs)
+{
+	struct k230_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+	struct device *dev = info->pctl_dev->dev;
+	enum pin_config_param param;
+	unsigned int arg, i;
+	int ret;
+
+	if (pin >= K230_NPINS) {
+		dev_err(dev, "pin number out of range\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < num_configs; i++) {
+		param = pinconf_to_config_param(configs[i]);
+		arg = pinconf_to_config_argument(configs[i]);
+		ret = k230_pinconf_set_param(pctldev, pin, param, arg);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void k230_pconf_dbg_show(struct pinctrl_dev *pctldev,
+				struct seq_file *s, unsigned int pin)
+{
+	struct k230_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+	unsigned int val;
+
+	regmap_read(info->regmap_base, pin * 4, &val);
+
+	seq_printf(s, " 0x%08x", val);
+}
+
+static const struct pinconf_ops k230_pinconf_ops = {
+	.is_generic		= true,
+	.pin_config_get		= k230_pinconf_get,
+	.pin_config_set		= k230_pinconf_set,
+	.pin_config_dbg_show	= k230_pconf_dbg_show,
+};
+
+static int k230_get_functions_count(struct pinctrl_dev *pctldev)
+{
+	struct k230_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+
+	return info->nfunctions;
+}
+
+static const char *k230_get_fname(struct pinctrl_dev *pctldev,
+				  unsigned int selector)
+{
+	struct k230_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+
+	return info->functions[selector].name;
+}
+
+static int k230_get_groups(struct pinctrl_dev *pctldev, unsigned int selector,
+			   const char * const **groups, unsigned int *num_groups)
+{
+	struct k230_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+
+	*groups = info->functions[selector].groups;
+	*num_groups = info->functions[selector].ngroups;
+
+	return 0;
+}
+
+static int k230_set_mux(struct pinctrl_dev *pctldev, unsigned int selector,
+			unsigned int group)
+{
+	struct k230_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+	const struct k230_pin_conf *data = info->groups[group].data;
+	struct k230_pin_group *grp = &info->groups[group];
+	const unsigned int *pins = grp->pins;
+	struct regmap *regmap;
+	unsigned int value, mask;
+	int cnt, reg;
+
+	regmap = info->regmap_base;
+
+	for (cnt = 0; cnt < grp->num_pins; cnt++) {
+		reg = pins[cnt] * 4;
+		value = data[cnt].func << K230_SHIFT_SEL;
+		mask = K230_PC_SEL;
+		regmap_update_bits(regmap, reg, mask, value);
+		k230_pins[pins[cnt]].drv_data = grp;
+	}
+
+	return 0;
+}
+
+static const struct pinmux_ops k230_pmxops = {
+	.get_functions_count	= k230_get_functions_count,
+	.get_function_name	= k230_get_fname,
+	.get_function_groups	= k230_get_groups,
+	.set_mux		= k230_set_mux,
+	.strict			= true,
+};
+
+static int k230_pinctrl_parse_groups(struct device_node *np,
+				     struct k230_pin_group *grp,
+				     struct k230_pinctrl *info,
+				     unsigned int index)
+{
+	struct device *dev = info->pctl_dev->dev;
+	const __be32 *list;
+	int size, i, ret;
+
+	grp->name = np->name;
+
+	list = of_get_property(np, "pinmux", &size);
+	size /= sizeof(*list);
+
+	grp->num_pins = size;
+	grp->pins = devm_kcalloc(dev, grp->num_pins, sizeof(*grp->pins),
+				 GFP_KERNEL);
+	grp->data = devm_kcalloc(dev, grp->num_pins, sizeof(*grp->data),
+				 GFP_KERNEL);
+	if (!grp->pins || !grp->data)
+		return -ENOMEM;
+
+	for (i = 0; i < size; i++) {
+		unsigned int mux_data = be32_to_cpu(*list++);
+
+		grp->pins[i] = (mux_data >> 8);
+		grp->data[i].func = (mux_data & 0xff);
+
+		ret = pinconf_generic_parse_dt_config(np, NULL,
+						      &grp->data[i].configs,
+						      &grp->data[i].nconfigs);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int k230_pinctrl_parse_functions(struct device_node *np,
+					struct k230_pinctrl *info,
+					unsigned int index)
+{
+	struct device *dev = info->pctl_dev->dev;
+	struct k230_pmx_func *func;
+	struct k230_pin_group *grp;
+	static unsigned int idx, i;
+	int ret;
+
+	func = &info->functions[index];
+
+	func->name = np->name;
+	func->ngroups = of_get_child_count(np);
+	if (func->ngroups <= 0)
+		return 0;
+
+	func->groups = devm_kcalloc(dev, func->ngroups,
+				    sizeof(*func->groups), GFP_KERNEL);
+	func->group_idx = devm_kcalloc(dev, func->ngroups,
+				       sizeof(*func->group_idx), GFP_KERNEL);
+	if (!func->groups || !func->group_idx)
+		return -ENOMEM;
+
+	i = 0;
+
+	for_each_child_of_node_scoped(np, child) {
+		func->groups[i] = child->name;
+		func->group_idx[i] = idx;
+		grp = &info->groups[idx];
+		idx++;
+		ret = k230_pinctrl_parse_groups(child, grp, info, i++);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void k230_pinctrl_child_count(struct k230_pinctrl *info,
+				     struct device_node *np)
+{
+	for_each_child_of_node_scoped(np, child) {
+		info->nfunctions++;
+		info->ngroups += of_get_child_count(child);
+	}
+}
+
+static int k230_pinctrl_parse_dt(struct platform_device *pdev,
+				 struct k230_pinctrl *info)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	unsigned int i;
+	int ret;
+
+	k230_pinctrl_child_count(info, np);
+
+	info->functions = devm_kcalloc(dev, info->nfunctions,
+				       sizeof(*info->functions), GFP_KERNEL);
+	info->groups = devm_kcalloc(dev, info->ngroups,
+				    sizeof(*info->groups), GFP_KERNEL);
+	if (!info->functions || !info->groups)
+		return -ENOMEM;
+
+	i = 0;
+
+	for_each_child_of_node_scoped(np, child) {
+		ret = k230_pinctrl_parse_functions(child, info, i++);
+		if (ret) {
+			dev_err(dev, "failed to parse function\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int k230_pinctrl_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct k230_pinctrl *info;
+	struct pinctrl_desc *pctl;
+
+	info = devm_kzalloc(dev, sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	pctl = &info->pctl;
+
+	pctl->name	= "k230-pinctrl";
+	pctl->owner	= THIS_MODULE;
+	pctl->pins	= k230_pins;
+	pctl->npins	= ARRAY_SIZE(k230_pins);
+	pctl->pctlops	= &k230_pctrl_ops;
+	pctl->pmxops	= &k230_pmxops;
+	pctl->confops	= &k230_pinconf_ops;
+
+	info->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(info->base))
+		return PTR_ERR(info->base);
+
+	info->regmap_base = devm_regmap_init_mmio(dev, info->base,
+						  &k230_regmap_config);
+	if (IS_ERR(info->regmap_base))
+		return dev_err_probe(dev, PTR_ERR(info->regmap_base),
+				     "failed to init regmap\n");
+
+	info->pctl_dev = devm_pinctrl_register(dev, pctl, info);
+	if (IS_ERR(info->pctl_dev))
+		return dev_err_probe(dev, PTR_ERR(info->pctl_dev),
+				     "devm_pinctrl_register failed\n");
+
+	k230_pinctrl_parse_dt(pdev, info);
+
+	return 0;
+}
+
+static const struct of_device_id k230_dt_ids[] = {
+	{ .compatible = "canaan,k230-pinctrl", },
+	{ /* sintenel */ }
+};
+MODULE_DEVICE_TABLE(of, k230_dt_ids);
+
+static struct platform_driver k230_pinctrl_driver = {
+	.probe = k230_pinctrl_probe,
+	.driver = {
+		.name = "k230-pinctrl",
+		.of_match_table = k230_dt_ids,
+	},
+};
+module_platform_driver(k230_pinctrl_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ze Huang <18771902331@163.com>");
+MODULE_DESCRIPTION("Canaan K230 pinctrl driver");

From b0c37572a6a4ce61fb5622b87db12f4079ad1826 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Wed, 11 Sep 2024 17:24:38 +0200
Subject: [PATCH 0069/1530] dt-bindings: pinctrl: amlogic,meson-pinctrl: lower
 gpio-line-names minItems for meson8b

The Amlogic Meson8b SoC has 83 CBUS GPIOs, thus lower the minItems
for gpio-line-names to account for it, fixing DTBs check on Meson8b
based boards.

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/20240911-topic-amlogic-arm32-upstream-bindings-fixes-meson-pinctrl-gpio-line-names-v1-1-4345ba336ea4@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/amlogic,meson8-pinctrl-cbus.yaml           | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/amlogic,meson8-pinctrl-cbus.yaml b/Documentation/devicetree/bindings/pinctrl/amlogic,meson8-pinctrl-cbus.yaml
index 412bbcc276f3b..c954761e01505 100644
--- a/Documentation/devicetree/bindings/pinctrl/amlogic,meson8-pinctrl-cbus.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/amlogic,meson8-pinctrl-cbus.yaml
@@ -46,7 +46,7 @@ patternProperties:
           - const: gpio
 
       gpio-line-names:
-        minItems: 86 # AXG
+        minItems: 83 # Meson8b
         maxItems: 120 # Meson8
 
 unevaluatedProperties:

From 55c487ea6084afa85753916fbbe40c3e658d9788 Mon Sep 17 00:00:00 2001
From: Lijuan Gao <quic_lijuang@quicinc.com>
Date: Fri, 20 Sep 2024 16:00:09 +0800
Subject: [PATCH 0070/1530] dt-bindings: pinctrl: document the QCS615 Top Level
 Mode Multiplexer

Document the Top Level Mode Multiplexer on the QCS615 Platform.
It concisely explains the pin multiplexing and configuration in
the device tree, and includes simple examples of typical device
tree snippets, making it easier for designers to configure and
manage chip pins.

Signed-off-by: Lijuan Gao <quic_lijuang@quicinc.com>
Link: https://lore.kernel.org/20240920-add_qcs615_pinctrl_driver-v2-1-e03c42a9d055@quicinc.com
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/qcom,qcs615-tlmm.yaml    | 124 ++++++++++++++++++
 1 file changed, 124 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/qcom,qcs615-tlmm.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,qcs615-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,qcs615-tlmm.yaml
new file mode 100644
index 0000000000000..1ce4b5df584ab
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,qcs615-tlmm.yaml
@@ -0,0 +1,124 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,qcs615-tlmm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Technologies, Inc. QCS615 TLMM block
+
+maintainers:
+  - Lijuan Gao <quic_lijuang@quicinc.com>
+
+description:
+  Top Level Mode Multiplexer pin controller in Qualcomm QCS615 SoC.
+
+allOf:
+  - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml#
+
+properties:
+  compatible:
+    const: qcom,qcs615-tlmm
+
+  reg:
+    maxItems: 3
+
+  reg-names:
+    items:
+      - const: east
+      - const: west
+      - const: south
+
+  interrupts:
+    maxItems: 1
+
+  gpio-reserved-ranges:
+    minItems: 1
+    maxItems: 62
+
+  gpio-line-names:
+    maxItems: 123
+
+patternProperties:
+  "-state$":
+    oneOf:
+      - $ref: "#/$defs/qcom-qcs615-tlmm-state"
+      - type: object
+        patternProperties:
+          "-pins$":
+            $ref: "#/$defs/qcom-qcs615-tlmm-state"
+        additionalProperties: false
+
+$defs:
+  qcom-qcs615-tlmm-state:
+    type: object
+    description:
+      Pinctrl node's client devices use subnodes for desired pin configuration.
+      Client device subnodes use below standard properties.
+    $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
+
+    properties:
+      pins:
+        description:
+          List of gpio pins affected by the properties specified in this
+          subnode.
+        items:
+          oneOf:
+            - pattern: "^gpio([0-9]|[1-9][0-9]|1[0-1][0-9]|12[0-2])$"
+            - enum: [ sdc1_clk, sdc1_cmd, sdc1_data, sdc1_rclk,
+                      sdc2_clk, sdc2_cmd, sdc2_data, ufs_reset ]
+        minItems: 1
+        maxItems: 36
+
+      function:
+        description:
+          Specify the alternative function to be configured for the specified
+          pins.
+        enum: [ gpio, adsp_ext, agera_pll, aoss_cti, atest_char, atest_tsens,
+                atest_usb, cam_mclk, cci_async, cci_i2c, cci_timer, copy_gp,
+                copy_phase, cri_trng, dbg_out_clk, ddr_bist, ddr_pxi, dp_hot,
+                edp_hot, edp_lcd, emac_gcc, emac_phy_intr, forced_usb, gcc_gp,
+                gp_pdm, gps_tx, hs0_mi2s, hs1_mi2s, jitter_bist, ldo_en,
+                ldo_update, m_voc, mclk1, mclk2, mdp_vsync, mdp_vsync0_out,
+                mdp_vsync1_out, mdp_vsync2_out, mdp_vsync3_out, mdp_vsync4_out,
+                mdp_vsync5_out, mi2s_1, mss_lte, nav_pps_in, nav_pps_out,
+                pa_indicator_or, pcie_clk_req, pcie_ep_rst, phase_flag, pll_bist,
+                pll_bypassnl, pll_reset_n, prng_rosc, qdss_cti, qdss_gpio,
+                qlink_enable, qlink_request, qspi, qup0, qup1, rgmii,
+                sd_write_protect, sp_cmu, ter_mi2s, tgu_ch, uim1, uim2, usb0_hs,
+                usb1_hs, usb_phy_ps, vfr_1, vsense_trigger_mirnat, wlan, wsa_clk,
+                wsa_data ]
+
+    required:
+      - pins
+
+required:
+  - compatible
+  - reg
+  - reg-names
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    tlmm: pinctrl@3000000 {
+        compatible = "qcom,qcs615-tlmm";
+        reg = <0x03100000 0x300000>,
+              <0x03500000 0x300000>,
+              <0x03c00000 0x300000>;
+        reg-names = "east", "west", "south";
+        interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
+        gpio-ranges = <&tlmm 0 0 123>;
+        gpio-controller;
+        #gpio-cells = <2>;
+        interrupt-controller;
+        #interrupt-cells = <2>;
+
+        qup3-uart2-state {
+            pins ="gpio16", "gpio17";
+            function = "qup0";
+        };
+    };
+...

From b698f36a9d4079b59af18be71ac95310fa241485 Mon Sep 17 00:00:00 2001
From: Lijuan Gao <quic_lijuang@quicinc.com>
Date: Fri, 20 Sep 2024 16:00:10 +0800
Subject: [PATCH 0071/1530] pinctrl: qcom: add the tlmm driver for QCS615
 platform

Add support for QCS615 TLMM configuration and control via the
pinctrl framework.

Signed-off-by: Lijuan Gao <quic_lijuang@quicinc.com>
Link: https://lore.kernel.org/20240920-add_qcs615_pinctrl_driver-v2-2-e03c42a9d055@quicinc.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/Kconfig.msm      |    7 +
 drivers/pinctrl/qcom/Makefile         |    1 +
 drivers/pinctrl/qcom/pinctrl-qcs615.c | 1107 +++++++++++++++++++++++++
 3 files changed, 1115 insertions(+)
 create mode 100644 drivers/pinctrl/qcom/pinctrl-qcs615.c

diff --git a/drivers/pinctrl/qcom/Kconfig.msm b/drivers/pinctrl/qcom/Kconfig.msm
index 9738448f2a8a2..c79f0c3c873da 100644
--- a/drivers/pinctrl/qcom/Kconfig.msm
+++ b/drivers/pinctrl/qcom/Kconfig.msm
@@ -191,6 +191,13 @@ config PINCTRL_QCS404
 	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
 	  TLMM block found in the Qualcomm QCS404 platform.
 
+config PINCTRL_QCS615
+	tristate "Qualcomm Technologies QCS615 pin controller driver"
+	depends on ARM64 || COMPILE_TEST
+	help
+	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
+	  TLMM block found on the Qualcomm QCS615 platform.
+
 config PINCTRL_QDF2XXX
 	tristate "Qualcomm Technologies QDF2xxx pin controller driver"
 	depends on ACPI
diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile
index 5b4712146db5a..715c3b5a636ad 100644
--- a/drivers/pinctrl/qcom/Makefile
+++ b/drivers/pinctrl/qcom/Makefile
@@ -24,6 +24,7 @@ obj-$(CONFIG_PINCTRL_MSM8996)   += pinctrl-msm8996.o
 obj-$(CONFIG_PINCTRL_MSM8998)   += pinctrl-msm8998.o
 obj-$(CONFIG_PINCTRL_QCM2290)	+= pinctrl-qcm2290.o
 obj-$(CONFIG_PINCTRL_QCS404)	+= pinctrl-qcs404.o
+obj-$(CONFIG_PINCTRL_QCS615)    += pinctrl-qcs615.o
 obj-$(CONFIG_PINCTRL_QDF2XXX)	+= pinctrl-qdf2xxx.o
 obj-$(CONFIG_PINCTRL_MDM9607)	+= pinctrl-mdm9607.o
 obj-$(CONFIG_PINCTRL_MDM9615)	+= pinctrl-mdm9615.o
diff --git a/drivers/pinctrl/qcom/pinctrl-qcs615.c b/drivers/pinctrl/qcom/pinctrl-qcs615.c
new file mode 100644
index 0000000000000..8380e22b2faa1
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-qcs615.c
@@ -0,0 +1,1107 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-msm.h"
+
+enum {
+	SOUTH,
+	EAST,
+	WEST
+};
+
+static const char * const qcs615_tiles[] = {
+	[SOUTH] = "south",
+	[EAST] = "east",
+	[WEST] = "west"
+};
+
+#define PINGROUP(id, _tile, f1, f2, f3, f4, f5, f6, f7, f8, f9)	\
+	{						\
+		.grp = PINCTRL_PINGROUP("gpio" #id,	\
+			gpio##id##_pins,		\
+			ARRAY_SIZE(gpio##id##_pins)),	\
+		.funcs = (int[]){			\
+			msm_mux_gpio, /* gpio mode */	\
+			msm_mux_##f1,			\
+			msm_mux_##f2,			\
+			msm_mux_##f3,			\
+			msm_mux_##f4,			\
+			msm_mux_##f5,			\
+			msm_mux_##f6,			\
+			msm_mux_##f7,			\
+			msm_mux_##f8,			\
+			msm_mux_##f9			\
+		},					\
+		.nfuncs = 10,				\
+		.ctl_reg = 0x1000 * id,		\
+		.io_reg = 0x1000 * id + 0x4,		\
+		.intr_cfg_reg = 0x1000 * id + 0x8,	\
+		.intr_status_reg = 0x1000 * id + 0xc,	\
+		.intr_target_reg = 0x1000 * id + 0x8,	\
+		.tile = _tile,			\
+		.mux_bit = 2,			\
+		.pull_bit = 0,			\
+		.drv_bit = 6,			\
+		.oe_bit = 9,			\
+		.in_bit = 0,			\
+		.out_bit = 1,			\
+		.intr_enable_bit = 0,		\
+		.intr_status_bit = 0,		\
+		.intr_target_bit = 5,		\
+		.intr_target_kpss_val = 3,	\
+		.intr_raw_status_bit = 4,	\
+		.intr_polarity_bit = 1,		\
+		.intr_detection_bit = 2,	\
+		.intr_detection_width = 2,	\
+	}
+
+#define SDC_QDSD_PINGROUP(pg_name, _tile, ctl, pull, drv)	\
+	{						\
+		.grp = PINCTRL_PINGROUP(#pg_name,	\
+			pg_name##_pins,			\
+			ARRAY_SIZE(pg_name##_pins)),	\
+		.ctl_reg = ctl,				\
+		.io_reg = 0,				\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.tile = _tile,				\
+		.mux_bit = -1,				\
+		.pull_bit = pull,			\
+		.drv_bit = drv,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = -1,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+#define UFS_RESET(pg_name, offset)			\
+	{						\
+		.grp = PINCTRL_PINGROUP(#pg_name,	\
+			pg_name##_pins,			\
+			ARRAY_SIZE(pg_name##_pins)),	\
+		.ctl_reg = offset,			\
+		.io_reg = offset + 0x4,			\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.tile = WEST,				\
+		.mux_bit = -1,				\
+		.pull_bit = 3,				\
+		.drv_bit = 0,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = 0,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+static const struct pinctrl_pin_desc qcs615_pins[] = {
+	PINCTRL_PIN(0, "GPIO_0"),
+	PINCTRL_PIN(1, "GPIO_1"),
+	PINCTRL_PIN(2, "GPIO_2"),
+	PINCTRL_PIN(3, "GPIO_3"),
+	PINCTRL_PIN(4, "GPIO_4"),
+	PINCTRL_PIN(5, "GPIO_5"),
+	PINCTRL_PIN(6, "GPIO_6"),
+	PINCTRL_PIN(7, "GPIO_7"),
+	PINCTRL_PIN(8, "GPIO_8"),
+	PINCTRL_PIN(9, "GPIO_9"),
+	PINCTRL_PIN(10, "GPIO_10"),
+	PINCTRL_PIN(11, "GPIO_11"),
+	PINCTRL_PIN(12, "GPIO_12"),
+	PINCTRL_PIN(13, "GPIO_13"),
+	PINCTRL_PIN(14, "GPIO_14"),
+	PINCTRL_PIN(15, "GPIO_15"),
+	PINCTRL_PIN(16, "GPIO_16"),
+	PINCTRL_PIN(17, "GPIO_17"),
+	PINCTRL_PIN(18, "GPIO_18"),
+	PINCTRL_PIN(19, "GPIO_19"),
+	PINCTRL_PIN(20, "GPIO_20"),
+	PINCTRL_PIN(21, "GPIO_21"),
+	PINCTRL_PIN(22, "GPIO_22"),
+	PINCTRL_PIN(23, "GPIO_23"),
+	PINCTRL_PIN(24, "GPIO_24"),
+	PINCTRL_PIN(25, "GPIO_25"),
+	PINCTRL_PIN(26, "GPIO_26"),
+	PINCTRL_PIN(27, "GPIO_27"),
+	PINCTRL_PIN(28, "GPIO_28"),
+	PINCTRL_PIN(29, "GPIO_29"),
+	PINCTRL_PIN(30, "GPIO_30"),
+	PINCTRL_PIN(31, "GPIO_31"),
+	PINCTRL_PIN(32, "GPIO_32"),
+	PINCTRL_PIN(33, "GPIO_33"),
+	PINCTRL_PIN(34, "GPIO_34"),
+	PINCTRL_PIN(35, "GPIO_35"),
+	PINCTRL_PIN(36, "GPIO_36"),
+	PINCTRL_PIN(37, "GPIO_37"),
+	PINCTRL_PIN(38, "GPIO_38"),
+	PINCTRL_PIN(39, "GPIO_39"),
+	PINCTRL_PIN(40, "GPIO_40"),
+	PINCTRL_PIN(41, "GPIO_41"),
+	PINCTRL_PIN(42, "GPIO_42"),
+	PINCTRL_PIN(43, "GPIO_43"),
+	PINCTRL_PIN(44, "GPIO_44"),
+	PINCTRL_PIN(45, "GPIO_45"),
+	PINCTRL_PIN(46, "GPIO_46"),
+	PINCTRL_PIN(47, "GPIO_47"),
+	PINCTRL_PIN(48, "GPIO_48"),
+	PINCTRL_PIN(49, "GPIO_49"),
+	PINCTRL_PIN(50, "GPIO_50"),
+	PINCTRL_PIN(51, "GPIO_51"),
+	PINCTRL_PIN(52, "GPIO_52"),
+	PINCTRL_PIN(53, "GPIO_53"),
+	PINCTRL_PIN(54, "GPIO_54"),
+	PINCTRL_PIN(55, "GPIO_55"),
+	PINCTRL_PIN(56, "GPIO_56"),
+	PINCTRL_PIN(57, "GPIO_57"),
+	PINCTRL_PIN(58, "GPIO_58"),
+	PINCTRL_PIN(59, "GPIO_59"),
+	PINCTRL_PIN(60, "GPIO_60"),
+	PINCTRL_PIN(61, "GPIO_61"),
+	PINCTRL_PIN(62, "GPIO_62"),
+	PINCTRL_PIN(63, "GPIO_63"),
+	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
+	PINCTRL_PIN(69, "GPIO_69"),
+	PINCTRL_PIN(70, "GPIO_70"),
+	PINCTRL_PIN(71, "GPIO_71"),
+	PINCTRL_PIN(72, "GPIO_72"),
+	PINCTRL_PIN(73, "GPIO_73"),
+	PINCTRL_PIN(74, "GPIO_74"),
+	PINCTRL_PIN(75, "GPIO_75"),
+	PINCTRL_PIN(76, "GPIO_76"),
+	PINCTRL_PIN(77, "GPIO_77"),
+	PINCTRL_PIN(78, "GPIO_78"),
+	PINCTRL_PIN(79, "GPIO_79"),
+	PINCTRL_PIN(80, "GPIO_80"),
+	PINCTRL_PIN(81, "GPIO_81"),
+	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
+	PINCTRL_PIN(86, "GPIO_86"),
+	PINCTRL_PIN(87, "GPIO_87"),
+	PINCTRL_PIN(88, "GPIO_88"),
+	PINCTRL_PIN(89, "GPIO_89"),
+	PINCTRL_PIN(90, "GPIO_90"),
+	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93"),
+	PINCTRL_PIN(94, "GPIO_94"),
+	PINCTRL_PIN(95, "GPIO_95"),
+	PINCTRL_PIN(96, "GPIO_96"),
+	PINCTRL_PIN(97, "GPIO_97"),
+	PINCTRL_PIN(98, "GPIO_98"),
+	PINCTRL_PIN(99, "GPIO_99"),
+	PINCTRL_PIN(100, "GPIO_100"),
+	PINCTRL_PIN(101, "GPIO_101"),
+	PINCTRL_PIN(102, "GPIO_102"),
+	PINCTRL_PIN(103, "GPIO_103"),
+	PINCTRL_PIN(104, "GPIO_104"),
+	PINCTRL_PIN(105, "GPIO_105"),
+	PINCTRL_PIN(106, "GPIO_106"),
+	PINCTRL_PIN(107, "GPIO_107"),
+	PINCTRL_PIN(108, "GPIO_108"),
+	PINCTRL_PIN(109, "GPIO_109"),
+	PINCTRL_PIN(110, "GPIO_110"),
+	PINCTRL_PIN(111, "GPIO_111"),
+	PINCTRL_PIN(112, "GPIO_112"),
+	PINCTRL_PIN(113, "GPIO_113"),
+	PINCTRL_PIN(114, "GPIO_114"),
+	PINCTRL_PIN(115, "GPIO_115"),
+	PINCTRL_PIN(116, "GPIO_116"),
+	PINCTRL_PIN(117, "GPIO_117"),
+	PINCTRL_PIN(118, "GPIO_118"),
+	PINCTRL_PIN(119, "GPIO_119"),
+	PINCTRL_PIN(120, "GPIO_120"),
+	PINCTRL_PIN(121, "GPIO_121"),
+	PINCTRL_PIN(122, "GPIO_122"),
+	PINCTRL_PIN(123, "UFS_RESET"),
+	PINCTRL_PIN(124, "SDC1_RCLK"),
+	PINCTRL_PIN(125, "SDC1_CLK"),
+	PINCTRL_PIN(126, "SDC1_CMD"),
+	PINCTRL_PIN(127, "SDC1_DATA"),
+	PINCTRL_PIN(128, "SDC2_CLK"),
+	PINCTRL_PIN(129, "SDC2_CMD"),
+	PINCTRL_PIN(130, "SDC2_DATA"),
+};
+
+#define DECLARE_MSM_GPIO_PINS(pin) \
+	static const unsigned int gpio##pin##_pins[] = { pin }
+DECLARE_MSM_GPIO_PINS(0);
+DECLARE_MSM_GPIO_PINS(1);
+DECLARE_MSM_GPIO_PINS(2);
+DECLARE_MSM_GPIO_PINS(3);
+DECLARE_MSM_GPIO_PINS(4);
+DECLARE_MSM_GPIO_PINS(5);
+DECLARE_MSM_GPIO_PINS(6);
+DECLARE_MSM_GPIO_PINS(7);
+DECLARE_MSM_GPIO_PINS(8);
+DECLARE_MSM_GPIO_PINS(9);
+DECLARE_MSM_GPIO_PINS(10);
+DECLARE_MSM_GPIO_PINS(11);
+DECLARE_MSM_GPIO_PINS(12);
+DECLARE_MSM_GPIO_PINS(13);
+DECLARE_MSM_GPIO_PINS(14);
+DECLARE_MSM_GPIO_PINS(15);
+DECLARE_MSM_GPIO_PINS(16);
+DECLARE_MSM_GPIO_PINS(17);
+DECLARE_MSM_GPIO_PINS(18);
+DECLARE_MSM_GPIO_PINS(19);
+DECLARE_MSM_GPIO_PINS(20);
+DECLARE_MSM_GPIO_PINS(21);
+DECLARE_MSM_GPIO_PINS(22);
+DECLARE_MSM_GPIO_PINS(23);
+DECLARE_MSM_GPIO_PINS(24);
+DECLARE_MSM_GPIO_PINS(25);
+DECLARE_MSM_GPIO_PINS(26);
+DECLARE_MSM_GPIO_PINS(27);
+DECLARE_MSM_GPIO_PINS(28);
+DECLARE_MSM_GPIO_PINS(29);
+DECLARE_MSM_GPIO_PINS(30);
+DECLARE_MSM_GPIO_PINS(31);
+DECLARE_MSM_GPIO_PINS(32);
+DECLARE_MSM_GPIO_PINS(33);
+DECLARE_MSM_GPIO_PINS(34);
+DECLARE_MSM_GPIO_PINS(35);
+DECLARE_MSM_GPIO_PINS(36);
+DECLARE_MSM_GPIO_PINS(37);
+DECLARE_MSM_GPIO_PINS(38);
+DECLARE_MSM_GPIO_PINS(39);
+DECLARE_MSM_GPIO_PINS(40);
+DECLARE_MSM_GPIO_PINS(41);
+DECLARE_MSM_GPIO_PINS(42);
+DECLARE_MSM_GPIO_PINS(43);
+DECLARE_MSM_GPIO_PINS(44);
+DECLARE_MSM_GPIO_PINS(45);
+DECLARE_MSM_GPIO_PINS(46);
+DECLARE_MSM_GPIO_PINS(47);
+DECLARE_MSM_GPIO_PINS(48);
+DECLARE_MSM_GPIO_PINS(49);
+DECLARE_MSM_GPIO_PINS(50);
+DECLARE_MSM_GPIO_PINS(51);
+DECLARE_MSM_GPIO_PINS(52);
+DECLARE_MSM_GPIO_PINS(53);
+DECLARE_MSM_GPIO_PINS(54);
+DECLARE_MSM_GPIO_PINS(55);
+DECLARE_MSM_GPIO_PINS(56);
+DECLARE_MSM_GPIO_PINS(57);
+DECLARE_MSM_GPIO_PINS(58);
+DECLARE_MSM_GPIO_PINS(59);
+DECLARE_MSM_GPIO_PINS(60);
+DECLARE_MSM_GPIO_PINS(61);
+DECLARE_MSM_GPIO_PINS(62);
+DECLARE_MSM_GPIO_PINS(63);
+DECLARE_MSM_GPIO_PINS(64);
+DECLARE_MSM_GPIO_PINS(65);
+DECLARE_MSM_GPIO_PINS(66);
+DECLARE_MSM_GPIO_PINS(67);
+DECLARE_MSM_GPIO_PINS(68);
+DECLARE_MSM_GPIO_PINS(69);
+DECLARE_MSM_GPIO_PINS(70);
+DECLARE_MSM_GPIO_PINS(71);
+DECLARE_MSM_GPIO_PINS(72);
+DECLARE_MSM_GPIO_PINS(73);
+DECLARE_MSM_GPIO_PINS(74);
+DECLARE_MSM_GPIO_PINS(75);
+DECLARE_MSM_GPIO_PINS(76);
+DECLARE_MSM_GPIO_PINS(77);
+DECLARE_MSM_GPIO_PINS(78);
+DECLARE_MSM_GPIO_PINS(79);
+DECLARE_MSM_GPIO_PINS(80);
+DECLARE_MSM_GPIO_PINS(81);
+DECLARE_MSM_GPIO_PINS(82);
+DECLARE_MSM_GPIO_PINS(83);
+DECLARE_MSM_GPIO_PINS(84);
+DECLARE_MSM_GPIO_PINS(85);
+DECLARE_MSM_GPIO_PINS(86);
+DECLARE_MSM_GPIO_PINS(87);
+DECLARE_MSM_GPIO_PINS(88);
+DECLARE_MSM_GPIO_PINS(89);
+DECLARE_MSM_GPIO_PINS(90);
+DECLARE_MSM_GPIO_PINS(91);
+DECLARE_MSM_GPIO_PINS(92);
+DECLARE_MSM_GPIO_PINS(93);
+DECLARE_MSM_GPIO_PINS(94);
+DECLARE_MSM_GPIO_PINS(95);
+DECLARE_MSM_GPIO_PINS(96);
+DECLARE_MSM_GPIO_PINS(97);
+DECLARE_MSM_GPIO_PINS(98);
+DECLARE_MSM_GPIO_PINS(99);
+DECLARE_MSM_GPIO_PINS(100);
+DECLARE_MSM_GPIO_PINS(101);
+DECLARE_MSM_GPIO_PINS(102);
+DECLARE_MSM_GPIO_PINS(103);
+DECLARE_MSM_GPIO_PINS(104);
+DECLARE_MSM_GPIO_PINS(105);
+DECLARE_MSM_GPIO_PINS(106);
+DECLARE_MSM_GPIO_PINS(107);
+DECLARE_MSM_GPIO_PINS(108);
+DECLARE_MSM_GPIO_PINS(109);
+DECLARE_MSM_GPIO_PINS(110);
+DECLARE_MSM_GPIO_PINS(111);
+DECLARE_MSM_GPIO_PINS(112);
+DECLARE_MSM_GPIO_PINS(113);
+DECLARE_MSM_GPIO_PINS(114);
+DECLARE_MSM_GPIO_PINS(115);
+DECLARE_MSM_GPIO_PINS(116);
+DECLARE_MSM_GPIO_PINS(117);
+DECLARE_MSM_GPIO_PINS(118);
+DECLARE_MSM_GPIO_PINS(119);
+DECLARE_MSM_GPIO_PINS(120);
+DECLARE_MSM_GPIO_PINS(121);
+DECLARE_MSM_GPIO_PINS(122);
+
+static const unsigned int ufs_reset_pins[] = { 123 };
+static const unsigned int sdc1_rclk_pins[] = { 124 };
+static const unsigned int sdc1_clk_pins[] = { 125 };
+static const unsigned int sdc1_cmd_pins[] = { 126 };
+static const unsigned int sdc1_data_pins[] = { 127 };
+static const unsigned int sdc2_clk_pins[] = { 128 };
+static const unsigned int sdc2_cmd_pins[] = { 129 };
+static const unsigned int sdc2_data_pins[] = { 130 };
+
+enum qcs615_functions {
+	msm_mux_gpio,
+	msm_mux_adsp_ext,
+	msm_mux_agera_pll,
+	msm_mux_aoss_cti,
+	msm_mux_atest_char,
+	msm_mux_atest_tsens,
+	msm_mux_atest_usb,
+	msm_mux_cam_mclk,
+	msm_mux_cci_async,
+	msm_mux_cci_i2c,
+	msm_mux_cci_timer,
+	msm_mux_copy_gp,
+	msm_mux_copy_phase,
+	msm_mux_cri_trng,
+	msm_mux_dbg_out_clk,
+	msm_mux_ddr_bist,
+	msm_mux_ddr_pxi,
+	msm_mux_dp_hot,
+	msm_mux_edp_hot,
+	msm_mux_edp_lcd,
+	msm_mux_emac_gcc,
+	msm_mux_emac_phy_intr,
+	msm_mux_forced_usb,
+	msm_mux_gcc_gp,
+	msm_mux_gp_pdm,
+	msm_mux_gps_tx,
+	msm_mux_hs0_mi2s,
+	msm_mux_hs1_mi2s,
+	msm_mux_jitter_bist,
+	msm_mux_ldo_en,
+	msm_mux_ldo_update,
+	msm_mux_m_voc,
+	msm_mux_mclk1,
+	msm_mux_mclk2,
+	msm_mux_mdp_vsync,
+	msm_mux_mdp_vsync0_out,
+	msm_mux_mdp_vsync1_out,
+	msm_mux_mdp_vsync2_out,
+	msm_mux_mdp_vsync3_out,
+	msm_mux_mdp_vsync4_out,
+	msm_mux_mdp_vsync5_out,
+	msm_mux_mi2s_1,
+	msm_mux_mss_lte,
+	msm_mux_nav_pps_in,
+	msm_mux_nav_pps_out,
+	msm_mux_pa_indicator_or,
+	msm_mux_pcie_clk_req,
+	msm_mux_pcie_ep_rst,
+	msm_mux_phase_flag,
+	msm_mux_pll_bist,
+	msm_mux_pll_bypassnl,
+	msm_mux_pll_reset_n,
+	msm_mux_prng_rosc,
+	msm_mux_qdss_cti,
+	msm_mux_qdss_gpio,
+	msm_mux_qlink_enable,
+	msm_mux_qlink_request,
+	msm_mux_qspi,
+	msm_mux_qup0,
+	msm_mux_qup1,
+	msm_mux_rgmii,
+	msm_mux_sd_write_protect,
+	msm_mux_sp_cmu,
+	msm_mux_ter_mi2s,
+	msm_mux_tgu_ch,
+	msm_mux_uim1,
+	msm_mux_uim2,
+	msm_mux_usb0_hs,
+	msm_mux_usb1_hs,
+	msm_mux_usb_phy_ps,
+	msm_mux_vfr_1,
+	msm_mux_vsense_trigger_mirnat,
+	msm_mux_wlan,
+	msm_mux_wsa_clk,
+	msm_mux_wsa_data,
+	msm_mux__,
+};
+
+static const char *const gpio_groups[] = {
+	"gpio0",   "gpio1",   "gpio2",   "gpio3",   "gpio4",   "gpio5",
+	"gpio6",   "gpio7",   "gpio8",   "gpio9",   "gpio10",  "gpio11",
+	"gpio12",  "gpio13",  "gpio14",  "gpio15",  "gpio16",  "gpio17",
+	"gpio18",  "gpio19",  "gpio20",  "gpio21",  "gpio22",  "gpio23",
+	"gpio24",  "gpio25",  "gpio26",  "gpio27",  "gpio28",  "gpio29",
+	"gpio30",  "gpio31",  "gpio32",  "gpio33",  "gpio34",  "gpio35",
+	"gpio36",  "gpio37",  "gpio38",  "gpio39",  "gpio40",  "gpio41",
+	"gpio42",  "gpio43",  "gpio44",  "gpio45",  "gpio46",  "gpio47",
+	"gpio48",  "gpio49",  "gpio50",  "gpio51",  "gpio52",  "gpio53",
+	"gpio54",  "gpio55",  "gpio56",  "gpio57",  "gpio58",  "gpio59",
+	"gpio60",  "gpio61",  "gpio62",  "gpio63",  "gpio64",  "gpio65",
+	"gpio66",  "gpio67",  "gpio68",  "gpio69",  "gpio70",  "gpio71",
+	"gpio72",  "gpio73",  "gpio74",  "gpio75",  "gpio76",  "gpio77",
+	"gpio78",  "gpio79",  "gpio80",  "gpio81",  "gpio82",  "gpio83",
+	"gpio84",  "gpio85",  "gpio86",  "gpio87",  "gpio88",  "gpio89",
+	"gpio90",  "gpio91",  "gpio92",  "gpio93",  "gpio94",  "gpio95",
+	"gpio96",  "gpio97",  "gpio98",  "gpio99",  "gpio100", "gpio101",
+	"gpio102", "gpio103", "gpio104", "gpio105", "gpio106", "gpio107",
+	"gpio108", "gpio109", "gpio110", "gpio111", "gpio112", "gpio113",
+	"gpio114", "gpio115", "gpio116", "gpio117", "gpio118", "gpio119",
+	"gpio120", "gpio121", "gpio122",
+};
+
+static const char *const adsp_ext_groups[] = {
+	"gpio118",
+};
+
+static const char *const agera_pll_groups[] = {
+	"gpio28",
+};
+
+static const char *const aoss_cti_groups[] = {
+	"gpio76",
+};
+
+static const char *const atest_char_groups[] = {
+	"gpio84",  "gpio85",  "gpio86",  "gpio87",
+	"gpio115", "gpio117", "gpio118", "gpio119",
+	"gpio120", "gpio121",
+};
+
+static const char *const atest_tsens_groups[] = {
+	"gpio7", "gpio29",
+};
+
+static const char *const atest_usb_groups[] = {
+	"gpio7",  "gpio10", "gpio11", "gpio54",
+	"gpio55", "gpio67", "gpio68", "gpio76",
+	"gpio75", "gpio77",
+};
+
+static const char *const cam_mclk_groups[] = {
+	"gpio28", "gpio29", "gpio30", "gpio31",
+};
+
+static const char *const cci_async_groups[] = {
+	"gpio26", "gpio41", "gpio42",
+};
+
+static const char *const cci_i2c_groups[] = {
+	"gpio32", "gpio33", "gpio34", "gpio35",
+};
+
+static const char *const cci_timer_groups[] = {
+	"gpio37", "gpio38", "gpio39", "gpio41",
+	"gpio42",
+};
+
+static const char *const copy_gp_groups[] = {
+	"gpio86",
+};
+
+static const char *const copy_phase_groups[] = {
+	"gpio103",
+};
+
+static const char *const cri_trng_groups[] = {
+	"gpio60", "gpio61", "gpio62",
+};
+
+static const char *const dbg_out_clk_groups[] = {
+	"gpio11",
+};
+
+static const char *const ddr_bist_groups[] = {
+	"gpio7", "gpio8", "gpio9", "gpio10",
+};
+
+static const char *const ddr_pxi_groups[] = {
+	"gpio6",  "gpio7",  "gpio10", "gpio11",
+	"gpio12", "gpio13", "gpio54", "gpio55",
+};
+
+static const char *const dp_hot_groups[] = {
+	"gpio102", "gpio103", "gpio104",
+};
+
+static const char *const edp_hot_groups[] = {
+	"gpio113",
+};
+
+static const char *const edp_lcd_groups[] = {
+	"gpio119",
+};
+
+static const char *const emac_gcc_groups[] = {
+	"gpio101", "gpio102",
+};
+
+static const char *const emac_phy_intr_groups[] = {
+	"gpio89",
+};
+
+static const char *const forced_usb_groups[] = {
+	"gpio43",
+};
+
+static const char *const gcc_gp_groups[] = {
+	"gpio21", "gpio22", "gpio57", "gpio58",
+	"gpio59", "gpio78",
+};
+
+static const char *const gp_pdm_groups[] = {
+	"gpio8", "gpio54", "gpio63", "gpio66",
+	"gpio79", "gpio95",
+};
+
+static const char *const gps_tx_groups[] = {
+	"gpio53", "gpio54", "gpio56", "gpio57",
+	"gpio59", "gpio60",
+};
+
+static const char *const hs0_mi2s_groups[] = {
+	"gpio36", "gpio37", "gpio38", "gpio39",
+};
+
+static const char *const hs1_mi2s_groups[] = {
+	"gpio24", "gpio25", "gpio26", "gpio27",
+};
+
+static const char *const jitter_bist_groups[] = {
+	"gpio12", "gpio26",
+};
+
+static const char *const ldo_en_groups[] = {
+	"gpio97",
+};
+
+static const char *const ldo_update_groups[] = {
+	"gpio98",
+};
+
+static const char *const m_voc_groups[] = {
+	"gpio120",
+};
+
+static const char *const mclk1_groups[] = {
+	"gpio121",
+};
+
+static const char *const mclk2_groups[] = {
+	"gpio122",
+};
+
+static const char *const mdp_vsync_groups[] = {
+	"gpio81", "gpio82", "gpio83", "gpio90",
+	"gpio97", "gpio98",
+};
+
+static const char *const mdp_vsync0_out_groups[] = {
+	"gpio90",
+};
+
+static const char *const mdp_vsync1_out_groups[] = {
+	"gpio90",
+};
+
+static const char *const mdp_vsync2_out_groups[] = {
+	"gpio90",
+};
+
+static const char *const mdp_vsync3_out_groups[] = {
+	"gpio90",
+};
+
+static const char *const mdp_vsync4_out_groups[] = {
+	"gpio90",
+};
+
+static const char *const mdp_vsync5_out_groups[] = {
+	"gpio90",
+};
+
+static const char *const mi2s_1_groups[] = {
+	"gpio108", "gpio109", "gpio110", "gpio111",
+};
+
+static const char *const mss_lte_groups[] = {
+	"gpio106", "gpio107",
+};
+
+static const char *const nav_pps_in_groups[] = {
+	"gpio53", "gpio56", "gpio57", "gpio59",
+	"gpio60",
+};
+
+static const char *const nav_pps_out_groups[] = {
+	"gpio53", "gpio56", "gpio57", "gpio59",
+	"gpio60",
+};
+
+static const char *const pa_indicator_or_groups[] = {
+	"gpio53",
+};
+
+static const char *const pcie_clk_req_groups[] = {
+	"gpio90",
+};
+
+static const char *const pcie_ep_rst_groups[] = {
+	"gpio89",
+};
+
+static const char *const phase_flag_groups[] = {
+	"gpio10",  "gpio18",  "gpio19",  "gpio20",
+	"gpio23",  "gpio24",  "gpio25",  "gpio38",
+	"gpio40",  "gpio41",  "gpio42",  "gpio43",
+	"gpio44",  "gpio45",  "gpio53",  "gpio54",
+	"gpio55",  "gpio67",  "gpio68",  "gpio75",
+	"gpio76",  "gpio77",  "gpio78",  "gpio79",
+	"gpio80",  "gpio82",  "gpio84",  "gpio92",
+	"gpio116", "gpio117", "gpio118", "gpio119",
+};
+
+static const char *const pll_bist_groups[] = {
+	"gpio27",
+};
+
+static const char *const pll_bypassnl_groups[] = {
+	"gpio13",
+};
+
+static const char *const pll_reset_n_groups[] = {
+	"gpio14",
+};
+
+static const char *const prng_rosc_groups[] = {
+	"gpio99", "gpio102",
+};
+
+static const char *const qdss_cti_groups[] = {
+	"gpio83",  "gpio96",  "gpio97",  "gpio98",
+	"gpio103", "gpio104", "gpio112", "gpio113",
+};
+
+static const char *const qdss_gpio_groups[] = {
+	"gpio0",   "gpio1",   "gpio2",   "gpio3",
+	"gpio6",   "gpio7",   "gpio8",   "gpio9",
+	"gpio14",  "gpio15",  "gpio20",  "gpio21",
+	"gpio28",  "gpio29",  "gpio30",  "gpio31",
+	"gpio32",  "gpio33",  "gpio34",  "gpio35",
+	"gpio44",  "gpio45",  "gpio46",  "gpio47",
+	"gpio81",  "gpio82",  "gpio92",  "gpio93",
+	"gpio94",  "gpio95",  "gpio108", "gpio109",
+	"gpio117", "gpio118", "gpio119", "gpio120",
+};
+
+static const char *const qlink_enable_groups[] = {
+	"gpio52",
+};
+
+static const char *const qlink_request_groups[] = {
+	"gpio51",
+};
+
+static const char *const qspi_groups[] = {
+	"gpio44", "gpio45", "gpio46", "gpio47",
+	"gpio48", "gpio49", "gpio50",
+};
+
+static const char *const qup0_groups[] = {
+	"gpio0",  "gpio1",  "gpio2",  "gpio3",
+	"gpio4",  "gpio5",  "gpio16", "gpio17",
+	"gpio18", "gpio19",
+};
+
+static const char *const qup1_groups[] = {
+	"gpio6",  "gpio7",  "gpio8",  "gpio9",
+	"gpio10", "gpio11", "gpio12", "gpio13",
+	"gpio14", "gpio15", "gpio20", "gpio21",
+	"gpio22", "gpio23",
+};
+
+static const char *const rgmii_groups[] = {
+	"gpio81",  "gpio82",  "gpio83",  "gpio91",
+	"gpio92",  "gpio93",  "gpio94",  "gpio95",
+	"gpio96",  "gpio97",  "gpio102", "gpio103",
+	"gpio112", "gpio113", "gpio114",
+};
+
+static const char *const sd_write_protect_groups[] = {
+	"gpio24",
+};
+
+static const char *const sp_cmu_groups[] = {
+	"gpio64",
+};
+
+static const char *const ter_mi2s_groups[] = {
+	"gpio115", "gpio116", "gpio117", "gpio118",
+};
+
+static const char *const tgu_ch_groups[] = {
+	"gpio89", "gpio90", "gpio91", "gpio92",
+};
+
+static const char *const uim1_groups[] = {
+	"gpio77", "gpio78", "gpio79", "gpio80",
+};
+
+static const char *const uim2_groups[] = {
+	"gpio73", "gpio74", "gpio75", "gpio76",
+};
+
+static const char *const usb0_hs_groups[] = {
+	"gpio88",
+};
+
+static const char *const usb1_hs_groups[] = {
+	"gpio89",
+};
+
+static const char *const usb_phy_ps_groups[] = {
+	"gpio104",
+};
+
+static const char *const vfr_1_groups[] = {
+	"gpio92",
+};
+
+static const char *const vsense_trigger_mirnat_groups[] = {
+	"gpio7",
+};
+
+static const char *const wlan_groups[] = {
+	"gpio16", "gpio17", "gpio47", "gpio48",
+};
+
+static const char *const wsa_clk_groups[] = {
+	"gpio111",
+};
+
+static const char *const wsa_data_groups[] = {
+	"gpio110",
+};
+
+static const struct pinfunction qcs615_functions[] = {
+	MSM_PIN_FUNCTION(gpio),
+	MSM_PIN_FUNCTION(adsp_ext),
+	MSM_PIN_FUNCTION(agera_pll),
+	MSM_PIN_FUNCTION(aoss_cti),
+	MSM_PIN_FUNCTION(atest_char),
+	MSM_PIN_FUNCTION(atest_tsens),
+	MSM_PIN_FUNCTION(atest_usb),
+	MSM_PIN_FUNCTION(cam_mclk),
+	MSM_PIN_FUNCTION(cci_async),
+	MSM_PIN_FUNCTION(cci_i2c),
+	MSM_PIN_FUNCTION(cci_timer),
+	MSM_PIN_FUNCTION(copy_gp),
+	MSM_PIN_FUNCTION(copy_phase),
+	MSM_PIN_FUNCTION(cri_trng),
+	MSM_PIN_FUNCTION(dbg_out_clk),
+	MSM_PIN_FUNCTION(ddr_bist),
+	MSM_PIN_FUNCTION(ddr_pxi),
+	MSM_PIN_FUNCTION(dp_hot),
+	MSM_PIN_FUNCTION(edp_hot),
+	MSM_PIN_FUNCTION(edp_lcd),
+	MSM_PIN_FUNCTION(emac_gcc),
+	MSM_PIN_FUNCTION(emac_phy_intr),
+	MSM_PIN_FUNCTION(forced_usb),
+	MSM_PIN_FUNCTION(gcc_gp),
+	MSM_PIN_FUNCTION(gp_pdm),
+	MSM_PIN_FUNCTION(gps_tx),
+	MSM_PIN_FUNCTION(hs0_mi2s),
+	MSM_PIN_FUNCTION(hs1_mi2s),
+	MSM_PIN_FUNCTION(jitter_bist),
+	MSM_PIN_FUNCTION(ldo_en),
+	MSM_PIN_FUNCTION(ldo_update),
+	MSM_PIN_FUNCTION(m_voc),
+	MSM_PIN_FUNCTION(mclk1),
+	MSM_PIN_FUNCTION(mclk2),
+	MSM_PIN_FUNCTION(mdp_vsync),
+	MSM_PIN_FUNCTION(mdp_vsync0_out),
+	MSM_PIN_FUNCTION(mdp_vsync1_out),
+	MSM_PIN_FUNCTION(mdp_vsync2_out),
+	MSM_PIN_FUNCTION(mdp_vsync3_out),
+	MSM_PIN_FUNCTION(mdp_vsync4_out),
+	MSM_PIN_FUNCTION(mdp_vsync5_out),
+	MSM_PIN_FUNCTION(mi2s_1),
+	MSM_PIN_FUNCTION(mss_lte),
+	MSM_PIN_FUNCTION(nav_pps_in),
+	MSM_PIN_FUNCTION(nav_pps_out),
+	MSM_PIN_FUNCTION(pa_indicator_or),
+	MSM_PIN_FUNCTION(pcie_clk_req),
+	MSM_PIN_FUNCTION(pcie_ep_rst),
+	MSM_PIN_FUNCTION(phase_flag),
+	MSM_PIN_FUNCTION(pll_bist),
+	MSM_PIN_FUNCTION(pll_bypassnl),
+	MSM_PIN_FUNCTION(pll_reset_n),
+	MSM_PIN_FUNCTION(prng_rosc),
+	MSM_PIN_FUNCTION(qdss_cti),
+	MSM_PIN_FUNCTION(qdss_gpio),
+	MSM_PIN_FUNCTION(qlink_enable),
+	MSM_PIN_FUNCTION(qlink_request),
+	MSM_PIN_FUNCTION(qspi),
+	MSM_PIN_FUNCTION(qup0),
+	MSM_PIN_FUNCTION(qup1),
+	MSM_PIN_FUNCTION(rgmii),
+	MSM_PIN_FUNCTION(sd_write_protect),
+	MSM_PIN_FUNCTION(sp_cmu),
+	MSM_PIN_FUNCTION(ter_mi2s),
+	MSM_PIN_FUNCTION(tgu_ch),
+	MSM_PIN_FUNCTION(uim1),
+	MSM_PIN_FUNCTION(uim2),
+	MSM_PIN_FUNCTION(usb0_hs),
+	MSM_PIN_FUNCTION(usb1_hs),
+	MSM_PIN_FUNCTION(usb_phy_ps),
+	MSM_PIN_FUNCTION(vfr_1),
+	MSM_PIN_FUNCTION(vsense_trigger_mirnat),
+	MSM_PIN_FUNCTION(wlan),
+	MSM_PIN_FUNCTION(wsa_clk),
+	MSM_PIN_FUNCTION(wsa_data),
+};
+
+/* Every pin is maintained as a single group, and missing or non-existing pin
+ * would be maintained as dummy group to synchronize pin group index with
+ * pin descriptor registered with pinctrl core.
+ * Clients would not be able to request these dummy pin groups.
+ */
+static const struct msm_pingroup qcs615_groups[] = {
+	[0] = PINGROUP(0, WEST, qup0, _, qdss_gpio, _, _, _, _, _, _),
+	[1] = PINGROUP(1, WEST, qup0, _, qdss_gpio, _, _, _, _, _, _),
+	[2] = PINGROUP(2, WEST, qup0, _, qdss_gpio, _, _, _, _, _, _),
+	[3] = PINGROUP(3, WEST, qup0, _, qdss_gpio, _, _, _, _, _, _),
+	[4] = PINGROUP(4, WEST, qup0, _, _, _, _, _, _, _, _),
+	[5] = PINGROUP(5, WEST, qup0, _, _, _, _, _, _, _, _),
+	[6] = PINGROUP(6, EAST, qup1, qdss_gpio, ddr_pxi, _, _, _, _, _, _),
+	[7] = PINGROUP(7, EAST, qup1, ddr_bist, qdss_gpio, atest_tsens,
+			vsense_trigger_mirnat, atest_usb, ddr_pxi, _, _),
+	[8] = PINGROUP(8, EAST, qup1, gp_pdm, ddr_bist, qdss_gpio, _, _, _, _, _),
+	[9] = PINGROUP(9, EAST, qup1, ddr_bist, qdss_gpio, _, _, _, _, _, _),
+	[10] = PINGROUP(10, EAST, qup1, ddr_bist, _, phase_flag, atest_usb, ddr_pxi, _, _, _),
+	[11] = PINGROUP(11, EAST, qup1, dbg_out_clk, atest_usb, ddr_pxi, _, _, _, _, _),
+	[12] = PINGROUP(12, EAST, qup1, jitter_bist, ddr_pxi, _, _, _, _, _, _),
+	[13] = PINGROUP(13, EAST, qup1, pll_bypassnl, _, ddr_pxi, _, _, _, _, _),
+	[14] = PINGROUP(14, EAST, qup1, pll_reset_n, _, qdss_gpio, _, _, _, _, _),
+	[15] = PINGROUP(15, EAST, qup1, qdss_gpio, _, _, _, _, _, _, _),
+	[16] = PINGROUP(16, WEST, qup0, _, wlan, _, _, _, _, _, _),
+	[17] = PINGROUP(17, WEST, qup0, _, wlan, _, _, _, _, _, _),
+	[18] = PINGROUP(18, WEST, qup0, _, phase_flag, _, _, _, _, _, _),
+	[19] = PINGROUP(19, WEST, qup0, _, phase_flag, _, _, _, _, _, _),
+	[20] = PINGROUP(20, SOUTH, qup1, _, phase_flag, qdss_gpio, _, _, _, _, _),
+	[21] = PINGROUP(21, SOUTH, qup1, gcc_gp, _, qdss_gpio, _, _, _, _, _),
+	[22] = PINGROUP(22, SOUTH, qup1, gcc_gp, _, _, _, _, _, _, _),
+	[23] = PINGROUP(23, SOUTH, qup1, _, phase_flag, _, _, _, _, _, _),
+	[24] = PINGROUP(24, EAST, hs1_mi2s, sd_write_protect, _, phase_flag, _, _, _, _, _),
+	[25] = PINGROUP(25, EAST, hs1_mi2s, _, phase_flag, _, _, _, _, _, _),
+	[26] = PINGROUP(26, EAST, cci_async, hs1_mi2s, jitter_bist, _, _, _, _, _, _),
+	[27] = PINGROUP(27, EAST, hs1_mi2s, pll_bist, _, _, _, _, _, _, _),
+	[28] = PINGROUP(28, EAST, cam_mclk, agera_pll, qdss_gpio, _, _, _, _, _, _),
+	[29] = PINGROUP(29, EAST, cam_mclk, _, qdss_gpio, atest_tsens, _, _, _, _, _),
+	[30] = PINGROUP(30, EAST, cam_mclk, qdss_gpio, _, _, _, _, _, _, _),
+	[31] = PINGROUP(31, EAST, cam_mclk, _, qdss_gpio, _, _, _, _, _, _),
+	[32] = PINGROUP(32, EAST, cci_i2c, _, qdss_gpio, _, _, _, _, _, _),
+	[33] = PINGROUP(33, EAST, cci_i2c, _, qdss_gpio, _, _, _, _, _, _),
+	[34] = PINGROUP(34, EAST, cci_i2c, _, qdss_gpio, _, _, _, _, _, _),
+	[35] = PINGROUP(35, EAST, cci_i2c, _, qdss_gpio, _, _, _, _, _, _),
+	[36] = PINGROUP(36, EAST, hs0_mi2s, _, _, _, _, _, _, _, _),
+	[37] = PINGROUP(37, EAST, cci_timer, hs0_mi2s, _, _, _, _, _, _, _),
+	[38] = PINGROUP(38, EAST, cci_timer, hs0_mi2s, _, phase_flag, _, _, _, _, _),
+	[39] = PINGROUP(39, EAST, cci_timer, hs0_mi2s, _, _, _, _, _, _, _),
+	[40] = PINGROUP(40, EAST, _, phase_flag, _, _, _, _, _, _, _),
+	[41] = PINGROUP(41, EAST, cci_async, cci_timer, _, phase_flag, _, _, _, _, _),
+	[42] = PINGROUP(42, EAST, cci_async, cci_timer, _, phase_flag, _, _, _, _, _),
+	[43] = PINGROUP(43, SOUTH, _, phase_flag, forced_usb, _, _, _, _, _, _),
+	[44] = PINGROUP(44, EAST, qspi, _, phase_flag, qdss_gpio, _, _, _, _, _),
+	[45] = PINGROUP(45, EAST, qspi, _, phase_flag, qdss_gpio, _, _, _, _, _),
+	[46] = PINGROUP(46, EAST, qspi, _, qdss_gpio, _, _, _, _, _, _),
+	[47] = PINGROUP(47, EAST, qspi, _, qdss_gpio, wlan, _, _, _, _, _),
+	[48] = PINGROUP(48, EAST, qspi, _, wlan, _, _, _, _, _, _),
+	[49] = PINGROUP(49, EAST, qspi, _, _, _, _, _, _, _, _),
+	[50] = PINGROUP(50, EAST, qspi, _, _, _, _, _, _, _, _),
+	[51] = PINGROUP(51, SOUTH, qlink_request, _, _, _, _, _, _, _, _),
+	[52] = PINGROUP(52, SOUTH, qlink_enable, _, _, _, _, _, _, _, _),
+	[53] = PINGROUP(53, SOUTH, pa_indicator_or, nav_pps_in, nav_pps_out, gps_tx, _,
+			phase_flag, _, _, _),
+	[54] = PINGROUP(54, SOUTH, _, gps_tx, gp_pdm, _, phase_flag, atest_usb, ddr_pxi, _, _),
+	[55] = PINGROUP(55, SOUTH, _, _, phase_flag, atest_usb, ddr_pxi, _, _, _, _),
+	[56] = PINGROUP(56, SOUTH, _, nav_pps_in, nav_pps_out, gps_tx, _, _, _, _, _),
+	[57] = PINGROUP(57, SOUTH, _, nav_pps_in, gps_tx, nav_pps_out, gcc_gp, _, _, _, _),
+	[58] = PINGROUP(58, SOUTH, _, gcc_gp, _, _, _, _, _, _, _),
+	[59] = PINGROUP(59, SOUTH, _, nav_pps_in, nav_pps_out, gps_tx, gcc_gp, _, _, _, _),
+	[60] = PINGROUP(60, SOUTH, _, nav_pps_in, nav_pps_out, gps_tx, cri_trng, _, _, _, _),
+	[61] = PINGROUP(61, SOUTH, _, cri_trng, _, _, _, _, _, _, _),
+	[62] = PINGROUP(62, SOUTH, _, cri_trng, _, _, _, _, _, _, _),
+	[63] = PINGROUP(63, SOUTH, _, _, gp_pdm, _, _, _, _, _, _),
+	[64] = PINGROUP(64, SOUTH, _, sp_cmu, _, _, _, _, _, _, _),
+	[65] = PINGROUP(65, SOUTH, _, _, _, _, _, _, _, _, _),
+	[66] = PINGROUP(66, SOUTH, _, gp_pdm, _, _, _, _, _, _, _),
+	[67] = PINGROUP(67, SOUTH, _, _, _, phase_flag, atest_usb, _, _, _, _),
+	[68] = PINGROUP(68, SOUTH, _, _, _, phase_flag, atest_usb, _, _, _, _),
+	[69] = PINGROUP(69, SOUTH, _, _, _, _, _, _, _, _, _),
+	[70] = PINGROUP(70, SOUTH, _, _, _, _, _, _, _, _, _),
+	[71] = PINGROUP(71, SOUTH, _, _, _, _, _, _, _, _, _),
+	[72] = PINGROUP(72, SOUTH, _, _, _, _, _, _, _, _, _),
+	[73] = PINGROUP(73, SOUTH, uim2, _, _, _, _, _, _, _, _),
+	[74] = PINGROUP(74, SOUTH, uim2, _, _, _, _, _, _, _, _),
+	[75] = PINGROUP(75, SOUTH, uim2, _, phase_flag, atest_usb, _, _, _, _, _),
+	[76] = PINGROUP(76, SOUTH, uim2, _, phase_flag, atest_usb, aoss_cti, _, _, _, _),
+	[77] = PINGROUP(77, SOUTH, uim1, _, phase_flag, atest_usb, _, _, _, _, _),
+	[78] = PINGROUP(78, SOUTH, uim1, gcc_gp, _, phase_flag, _, _, _, _, _),
+	[79] = PINGROUP(79, SOUTH, uim1, gp_pdm, _, phase_flag, _, _, _, _, _),
+	[80] = PINGROUP(80, SOUTH, uim1, _, phase_flag, _, _, _, _, _, _),
+	[81] = PINGROUP(81, WEST, rgmii, mdp_vsync, _, qdss_gpio, _, _, _, _, _),
+	[82] = PINGROUP(82, WEST, rgmii, mdp_vsync, _, phase_flag, qdss_gpio, _, _, _, _),
+	[83] = PINGROUP(83, WEST, rgmii, mdp_vsync, _, qdss_cti, _, _, _, _, _),
+	[84] = PINGROUP(84, SOUTH, _, phase_flag, atest_char, _, _, _, _, _, _),
+	[85] = PINGROUP(85, SOUTH, _, atest_char, _, _, _, _, _, _, _),
+	[86] = PINGROUP(86, SOUTH, copy_gp, _, atest_char, _, _, _, _, _, _),
+	[87] = PINGROUP(87, SOUTH, _, atest_char, _, _, _, _, _, _, _),
+	[88] = PINGROUP(88, WEST, _, usb0_hs, _, _, _, _, _, _, _),
+	[89] = PINGROUP(89, WEST, emac_phy_intr, pcie_ep_rst, tgu_ch, usb1_hs, _, _, _, _, _),
+	[90] = PINGROUP(90, WEST, mdp_vsync, mdp_vsync0_out, mdp_vsync1_out,
+			mdp_vsync2_out, mdp_vsync3_out, mdp_vsync4_out, mdp_vsync5_out,
+			pcie_clk_req, tgu_ch),
+	[91] = PINGROUP(91, WEST, rgmii, tgu_ch, _, _, _, _, _, _, _),
+	[92] = PINGROUP(92, WEST, rgmii, vfr_1, tgu_ch, _, phase_flag, qdss_gpio, _, _, _),
+	[93] = PINGROUP(93, WEST, rgmii, qdss_gpio, _, _, _, _, _, _, _),
+	[94] = PINGROUP(94, WEST, rgmii, qdss_gpio, _, _, _, _, _, _, _),
+	[95] = PINGROUP(95, WEST, rgmii, gp_pdm, qdss_gpio, _, _, _, _, _, _),
+	[96] = PINGROUP(96, WEST, rgmii, qdss_cti, _, _, _, _, _, _, _),
+	[97] = PINGROUP(97, WEST, rgmii, mdp_vsync, ldo_en, qdss_cti, _, _, _, _, _),
+	[98] = PINGROUP(98, WEST, mdp_vsync, ldo_update, qdss_cti, _, _, _, _, _, _),
+	[99] = PINGROUP(99, EAST, prng_rosc, _, _, _, _, _, _, _, _),
+	[100] = PINGROUP(100, WEST, _, _, _, _, _, _, _, _, _),
+	[101] = PINGROUP(101, WEST, emac_gcc, _, _, _, _, _, _, _, _),
+	[102] = PINGROUP(102, WEST, rgmii, dp_hot, emac_gcc, prng_rosc, _, _, _, _, _),
+	[103] = PINGROUP(103, WEST, rgmii, dp_hot, copy_phase, qdss_cti, _, _, _, _, _),
+	[104] = PINGROUP(104, WEST, usb_phy_ps, _, qdss_cti, dp_hot, _, _, _, _, _),
+	[105] = PINGROUP(105, SOUTH, _, _, _, _, _, _, _, _, _),
+	[106] = PINGROUP(106, EAST, mss_lte, _, _, _, _, _, _, _, _),
+	[107] = PINGROUP(107, EAST, mss_lte, _, _, _, _, _, _, _, _),
+	[108] = PINGROUP(108, SOUTH, mi2s_1, _, qdss_gpio, _, _, _, _, _, _),
+	[109] = PINGROUP(109, SOUTH, mi2s_1, _, qdss_gpio, _, _, _, _, _, _),
+	[110] = PINGROUP(110, SOUTH, wsa_data, mi2s_1, _, _, _, _, _, _, _),
+	[111] = PINGROUP(111, SOUTH, wsa_clk, mi2s_1, _, _, _, _, _, _, _),
+	[112] = PINGROUP(112, WEST, rgmii, _, qdss_cti, _, _, _, _, _, _),
+	[113] = PINGROUP(113, WEST, rgmii, edp_hot, _, qdss_cti, _, _, _, _, _),
+	[114] = PINGROUP(114, WEST, rgmii, _, _, _, _, _, _, _, _),
+	[115] = PINGROUP(115, SOUTH, ter_mi2s, atest_char, _, _, _, _, _, _, _),
+	[116] = PINGROUP(116, SOUTH, ter_mi2s, _, phase_flag, _, _, _, _, _, _),
+	[117] = PINGROUP(117, SOUTH, ter_mi2s, _, phase_flag, qdss_gpio, atest_char, _, _, _, _),
+	[118] = PINGROUP(118, SOUTH, ter_mi2s, adsp_ext, _, phase_flag, qdss_gpio, atest_char,
+			_, _, _),
+	[119] = PINGROUP(119, SOUTH, edp_lcd, _, phase_flag, qdss_gpio, atest_char, _, _, _, _),
+	[120] = PINGROUP(120, SOUTH, m_voc, qdss_gpio, atest_char, _, _, _, _, _, _),
+	[121] = PINGROUP(121, SOUTH, mclk1, atest_char, _, _, _, _, _, _, _),
+	[122] = PINGROUP(122, SOUTH, mclk2, _, _, _, _, _, _, _, _),
+	[123] = UFS_RESET(ufs_reset, 0x9f000),
+	[124] = SDC_QDSD_PINGROUP(sdc1_rclk, WEST, 0x9a000, 15, 0),
+	[125] = SDC_QDSD_PINGROUP(sdc1_clk, WEST, 0x9a000, 13, 6),
+	[126] = SDC_QDSD_PINGROUP(sdc1_cmd, WEST, 0x9a000, 11, 3),
+	[127] = SDC_QDSD_PINGROUP(sdc1_data, WEST, 0x9a000, 9, 0),
+	[128] = SDC_QDSD_PINGROUP(sdc2_clk, SOUTH, 0x98000, 14, 6),
+	[129] = SDC_QDSD_PINGROUP(sdc2_cmd, SOUTH, 0x98000, 11, 3),
+	[130] = SDC_QDSD_PINGROUP(sdc2_data, SOUTH, 0x98000, 9, 0),
+};
+
+static const struct msm_gpio_wakeirq_map qcs615_pdc_map[] = {
+	{ 1, 45 },    { 3, 31 },    { 7, 55 },    { 9, 110 },   { 11, 34 },
+	{ 13, 33 },   { 14, 35 },   { 17, 46 },   { 19, 48 },   { 21, 83 },
+	{ 22, 36 },   { 26, 38 },   { 35, 37 },   { 39, 125 },  { 41, 47 },
+	{ 47, 49 },   { 48, 51 },   { 50, 52 },   { 51, 123 },  { 55, 56 },
+	{ 56, 57 },   { 57, 58 },   { 60, 60 },   { 71, 54 },   { 80, 73 },
+	{ 81, 64 },   { 82, 50 },   { 83, 65 },   { 84, 92 },   { 85, 99 },
+	{ 86, 67 },   { 87, 84 },   { 88, 124 },  { 89, 122 },  { 90, 69 },
+	{ 92, 88 },   { 93, 75 },   { 94, 91 },   { 95, 72 },   { 96, 82 },
+	{ 97, 74 },   { 98, 95 },   { 99, 94 },   { 100, 100 }, { 101, 40 },
+	{ 102, 93 },  { 103, 77 },  { 104, 78 },  { 105, 96 },  { 107, 97 },
+	{ 108, 111 }, { 112, 112 }, { 113, 113 }, { 117, 85 },  { 118, 102 },
+	{ 119, 87 },  { 120, 114 }, { 121, 89 },  { 122, 90 },
+};
+
+static const struct msm_pinctrl_soc_data qcs615_tlmm = {
+	.pins = qcs615_pins,
+	.npins = ARRAY_SIZE(qcs615_pins),
+	.functions = qcs615_functions,
+	.nfunctions = ARRAY_SIZE(qcs615_functions),
+	.groups = qcs615_groups,
+	.ngroups = ARRAY_SIZE(qcs615_groups),
+	.ngpios = 123,
+	.tiles = qcs615_tiles,
+	.ntiles = ARRAY_SIZE(qcs615_tiles),
+	.wakeirq_map = qcs615_pdc_map,
+	.nwakeirq_map = ARRAY_SIZE(qcs615_pdc_map),
+};
+
+static const struct of_device_id qcs615_tlmm_of_match[] = {
+	{
+		.compatible = "qcom,qcs615-tlmm",
+	},
+	{},
+};
+
+static int qcs615_tlmm_probe(struct platform_device *pdev)
+{
+	return  msm_pinctrl_probe(pdev, &qcs615_tlmm);
+}
+
+static struct platform_driver qcs615_tlmm_driver = {
+	.driver = {
+		.name = "qcs615-tlmm",
+		.of_match_table = qcs615_tlmm_of_match,
+	},
+	.probe = qcs615_tlmm_probe,
+	.remove_new = msm_pinctrl_remove,
+};
+
+static int __init qcs615_tlmm_init(void)
+{
+	return platform_driver_register(&qcs615_tlmm_driver);
+}
+arch_initcall(qcs615_tlmm_init);
+
+static void __exit qcs615_tlmm_exit(void)
+{
+	platform_driver_unregister(&qcs615_tlmm_driver);
+}
+module_exit(qcs615_tlmm_exit);
+
+MODULE_DESCRIPTION("QTI QCS615 TLMM driver");
+MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(of, qcs615_tlmm_of_match);

From af8e4812288181f9a9af27b1df5da366bdcce740 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@baylibre.com>
Date: Fri, 20 Sep 2024 17:34:31 +0200
Subject: [PATCH 0072/1530] pinctrl: aw9523: Drop explicit initialization of
 struct i2c_device_id::driver_data to 0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These drivers don't use the driver_data member of struct i2c_device_id,
so don't explicitly initialize this member.

This prepares putting driver_data in an anonymous union which requires
either no initialization or named designators. But it's also a nice
cleanup on its own.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Link: https://lore.kernel.org/20240920153430.503212-13-u.kleine-koenig@baylibre.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-aw9523.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-aw9523.c b/drivers/pinctrl/pinctrl-aw9523.c
index b5e1c467625ba..d5cbc55eaecea 100644
--- a/drivers/pinctrl/pinctrl-aw9523.c
+++ b/drivers/pinctrl/pinctrl-aw9523.c
@@ -1053,7 +1053,7 @@ static void aw9523_remove(struct i2c_client *client)
 }
 
 static const struct i2c_device_id aw9523_i2c_id_table[] = {
-	{ "aw9523_i2c", 0 },
+	{ "aw9523_i2c" },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, aw9523_i2c_id_table);

From d1c7bf9cb31a8e3868c5eaf3ec05b79aba4d2e33 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Tue, 24 Sep 2024 17:39:18 +0200
Subject: [PATCH 0073/1530] pinctrl: sx150x: Use maple tree register cache

The sx150x driver uses a rbtree register cache with no obvious reason for
specifically preferring it. The maple tree register cache is based on a
more modern data structure and makes implementation decisions more suitable
for modern systems so let's switch the driver to use that. No functional
change.

Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/20240924-pinctl-sx150x-maple-v1-1-17dcfefefd17@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-sx150x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-sx150x.c b/drivers/pinctrl/pinctrl-sx150x.c
index fd0331a87cda2..ab87de319ad86 100644
--- a/drivers/pinctrl/pinctrl-sx150x.c
+++ b/drivers/pinctrl/pinctrl-sx150x.c
@@ -1105,7 +1105,7 @@ static const struct regmap_config sx150x_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 32,
 
-	.cache_type = REGCACHE_RBTREE,
+	.cache_type = REGCACHE_MAPLE,
 
 	.reg_read = sx150x_regmap_reg_read,
 	.reg_write = sx150x_regmap_reg_write,

From 724d52a3cd33774570c43cff06403b4cdda00abe Mon Sep 17 00:00:00 2001
From: Ivaylo Ivanov <ivo.ivanov.ivanov1@gmail.com>
Date: Fri, 20 Sep 2024 18:45:02 +0300
Subject: [PATCH 0074/1530] dt-bindings: pinctrl: samsung: Add compatible for
 Exynos8895 SoC

Add compatible for Exynos8895 SoC.

Signed-off-by: Ivaylo Ivanov <ivo.ivanov.ivanov1@gmail.com>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Link: https://lore.kernel.org/r/20240920154508.1618410-5-ivo.ivanov.ivanov1@gmail.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
index 242dd13c276b5..a2af2c88a3316 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
@@ -53,6 +53,7 @@ properties:
       - samsung,exynos7-pinctrl
       - samsung,exynos7885-pinctrl
       - samsung,exynos850-pinctrl
+      - samsung,exynos8895-pinctrl
       - samsung,exynosautov9-pinctrl
       - samsung,exynosautov920-pinctrl
       - tesla,fsd-pinctrl

From e2d58d1e1c61c1e1d4af400cc0ebcebf98efb49f Mon Sep 17 00:00:00 2001
From: Ivaylo Ivanov <ivo.ivanov.ivanov1@gmail.com>
Date: Fri, 20 Sep 2024 18:45:04 +0300
Subject: [PATCH 0075/1530] dt-bindings: pinctrl: samsung: add
 exynos8895-wakeup-eint compatible

Add a dedicated compatible for exynos8895.

Signed-off-by: Ivaylo Ivanov <ivo.ivanov.ivanov1@gmail.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20240920154508.1618410-7-ivo.ivanov.ivanov1@gmail.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml       | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
index 4dfb49b0e07f7..91516fedc872c 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
@@ -42,6 +42,7 @@ properties:
               - samsung,exynos5433-wakeup-eint
               - samsung,exynos7885-wakeup-eint
               - samsung,exynos850-wakeup-eint
+              - samsung,exynos8895-wakeup-eint
           - const: samsung,exynos7-wakeup-eint
       - items:
           - enum:

From eed2e79221e2b4a1d1469aa522f658889cd640ee Mon Sep 17 00:00:00 2001
From: Ivaylo Ivanov <ivo.ivanov.ivanov1@gmail.com>
Date: Fri, 20 Sep 2024 18:45:03 +0300
Subject: [PATCH 0076/1530] pinctrl: samsung: Add exynos8895 SoC pinctrl
 configuration

Add support for the pin-controller found on the Exynos8895 SoC
used in Samsung Galaxy S8 and S8 Plus phones.

It has a newly applied pinctrl register layer for FSYS0 with a
different bank type offset that consists of the following bit
fields:

CON: 4, DAT: 1, PUD: 2, DRV: 3, CONPDN: 2, PUDPDN: 2

Signed-off-by: Ivaylo Ivanov <ivo.ivanov.ivanov1@gmail.com>
Reviewed-by: Sam Protsenko <semen.protsenko@linaro.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20240920154508.1618410-6-ivo.ivanov.ivanov1@gmail.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../pinctrl/samsung/pinctrl-exynos-arm64.c    | 137 ++++++++++++++++++
 drivers/pinctrl/samsung/pinctrl-exynos.h      |  10 ++
 drivers/pinctrl/samsung/pinctrl-samsung.c     |   2 +
 drivers/pinctrl/samsung/pinctrl-samsung.h     |   1 +
 4 files changed, 150 insertions(+)

diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
index 5480e0884abec..c5df4f1bc600b 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
@@ -58,6 +58,15 @@ static const struct samsung_pin_bank_type exynos850_bank_type_alive = {
 	.reg_offset = { 0x00, 0x04, 0x08, 0x0c, },
 };
 
+/*
+ * Bank type for non-alive type. Bit fields:
+ * CON: 4, DAT: 1, PUD: 2, DRV: 3, CONPDN: 2, PUDPDN: 2
+ */
+static const struct samsung_pin_bank_type exynos8895_bank_type_off  = {
+	.fld_width = { 4, 1, 2, 3, 2, 2, },
+	.reg_offset = { 0x00, 0x04, 0x08, 0x0c, 0x10, 0x14, },
+};
+
 /* Pad retention control code for accessing PMU regmap */
 static atomic_t exynos_shared_retention_refcnt;
 
@@ -866,6 +875,134 @@ const struct samsung_pinctrl_of_match_data exynosautov920_of_data __initconst =
 	.num_ctrl	= ARRAY_SIZE(exynosautov920_pin_ctrl),
 };
 
+/* pin banks of exynos8895 pin-controller 0 (ALIVE) */
+static const struct samsung_pin_bank_data exynos8895_pin_banks0[] __initconst = {
+	EXYNOS_PIN_BANK_EINTW(8, 0x020, "gpa0", 0x00),
+	EXYNOS_PIN_BANK_EINTW(8, 0x040, "gpa1", 0x04),
+	EXYNOS_PIN_BANK_EINTW(8, 0x060, "gpa2", 0x08),
+	EXYNOS_PIN_BANK_EINTW(8, 0x080, "gpa3", 0x0c),
+	EXYNOS_PIN_BANK_EINTW(7, 0x0a0, "gpa4", 0x24),
+};
+
+/* pin banks of exynos8895 pin-controller 1 (ABOX) */
+static const struct samsung_pin_bank_data exynos8895_pin_banks1[] __initconst = {
+	EXYNOS_PIN_BANK_EINTG(8, 0x000, "gph0", 0x00),
+	EXYNOS_PIN_BANK_EINTG(7, 0x020, "gph1", 0x04),
+	EXYNOS_PIN_BANK_EINTG(4, 0x040, "gph3", 0x08),
+};
+
+/* pin banks of exynos8895 pin-controller 2 (VTS) */
+static const struct samsung_pin_bank_data exynos8895_pin_banks2[] __initconst = {
+	EXYNOS_PIN_BANK_EINTG(3, 0x000, "gph2", 0x00),
+};
+
+/* pin banks of exynos8895 pin-controller 3 (FSYS0) */
+static const struct samsung_pin_bank_data exynos8895_pin_banks3[] __initconst = {
+	EXYNOS8895_PIN_BANK_EINTG(3, 0x000, "gpi0", 0x00),
+	EXYNOS8895_PIN_BANK_EINTG(8, 0x020, "gpi1", 0x04),
+};
+
+/* pin banks of exynos8895 pin-controller 4 (FSYS1) */
+static const struct samsung_pin_bank_data exynos8895_pin_banks4[] __initconst = {
+	EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpj1", 0x00),
+	EXYNOS_PIN_BANK_EINTG(7, 0x020, "gpj0", 0x04),
+};
+
+/* pin banks of exynos8895 pin-controller 5 (BUSC) */
+static const struct samsung_pin_bank_data exynos8895_pin_banks5[] __initconst = {
+	EXYNOS_PIN_BANK_EINTG(2, 0x000, "gpb2", 0x00),
+};
+
+/* pin banks of exynos8895 pin-controller 6 (PERIC0) */
+static const struct samsung_pin_bank_data exynos8895_pin_banks6[] __initconst = {
+	EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpd0", 0x00),
+	EXYNOS_PIN_BANK_EINTG(8, 0x020, "gpd1", 0x04),
+	EXYNOS_PIN_BANK_EINTG(4, 0x040, "gpd2", 0x08),
+	EXYNOS_PIN_BANK_EINTG(5, 0x060, "gpd3", 0x0C),
+	EXYNOS_PIN_BANK_EINTG(4, 0x080, "gpb1", 0x10),
+	EXYNOS_PIN_BANK_EINTG(8, 0x0a0, "gpe7", 0x14),
+	EXYNOS_PIN_BANK_EINTG(8, 0x0c0, "gpf1", 0x18),
+};
+
+/* pin banks of exynos8895 pin-controller 7 (PERIC1) */
+static const struct samsung_pin_bank_data exynos8895_pin_banks7[] __initconst = {
+	EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpb0", 0x00),
+	EXYNOS_PIN_BANK_EINTG(5, 0x020, "gpc0", 0x04),
+	EXYNOS_PIN_BANK_EINTG(5, 0x040, "gpc1", 0x08),
+	EXYNOS_PIN_BANK_EINTG(8, 0x060, "gpc2", 0x0C),
+	EXYNOS_PIN_BANK_EINTG(8, 0x080, "gpc3", 0x10),
+	EXYNOS_PIN_BANK_EINTG(4, 0x0a0, "gpk0", 0x14),
+	EXYNOS_PIN_BANK_EINTG(8, 0x0c0, "gpe5", 0x18),
+	EXYNOS_PIN_BANK_EINTG(8, 0x0e0, "gpe6", 0x1C),
+	EXYNOS_PIN_BANK_EINTG(8, 0x100, "gpe2", 0x20),
+	EXYNOS_PIN_BANK_EINTG(8, 0x120, "gpe3", 0x24),
+	EXYNOS_PIN_BANK_EINTG(8, 0x140, "gpe4", 0x28),
+	EXYNOS_PIN_BANK_EINTG(4, 0x160, "gpf0", 0x2C),
+	EXYNOS_PIN_BANK_EINTG(8, 0x180, "gpe1", 0x30),
+	EXYNOS_PIN_BANK_EINTG(2, 0x1a0, "gpg0", 0x34),
+};
+
+static const struct samsung_pin_ctrl exynos8895_pin_ctrl[] __initconst = {
+	{
+		/* pin-controller instance 0 ALIVE data */
+		.pin_banks	= exynos8895_pin_banks0,
+		.nr_banks	= ARRAY_SIZE(exynos8895_pin_banks0),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.eint_wkup_init = exynos_eint_wkup_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 1 ABOX data */
+		.pin_banks	= exynos8895_pin_banks1,
+		.nr_banks	= ARRAY_SIZE(exynos8895_pin_banks1),
+	}, {
+		/* pin-controller instance 2 VTS data */
+		.pin_banks	= exynos8895_pin_banks2,
+		.nr_banks	= ARRAY_SIZE(exynos8895_pin_banks2),
+		.eint_gpio_init = exynos_eint_gpio_init,
+	}, {
+		/* pin-controller instance 3 FSYS0 data */
+		.pin_banks	= exynos8895_pin_banks3,
+		.nr_banks	= ARRAY_SIZE(exynos8895_pin_banks3),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 4 FSYS1 data */
+		.pin_banks	= exynos8895_pin_banks4,
+		.nr_banks	= ARRAY_SIZE(exynos8895_pin_banks4),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 5 BUSC data */
+		.pin_banks	= exynos8895_pin_banks5,
+		.nr_banks	= ARRAY_SIZE(exynos8895_pin_banks5),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 6 PERIC0 data */
+		.pin_banks	= exynos8895_pin_banks6,
+		.nr_banks	= ARRAY_SIZE(exynos8895_pin_banks6),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 7 PERIC1 data */
+		.pin_banks	= exynos8895_pin_banks7,
+		.nr_banks	= ARRAY_SIZE(exynos8895_pin_banks7),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	},
+};
+
+const struct samsung_pinctrl_of_match_data exynos8895_of_data __initconst = {
+	.ctrl		= exynos8895_pin_ctrl,
+	.num_ctrl	= ARRAY_SIZE(exynos8895_pin_ctrl),
+};
+
 /*
  * Pinctrl driver data for Tesla FSD SoC. FSD SoC includes three
  * gpio/pin-mux/pinconfig controllers.
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.h b/drivers/pinctrl/samsung/pinctrl-exynos.h
index 305cb1d31de49..7b7ff7ffeb56b 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.h
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.h
@@ -141,6 +141,16 @@
 		.name		= id				\
 	}
 
+#define EXYNOS8895_PIN_BANK_EINTG(pins, reg, id, offs)		\
+	{							\
+		.type		= &exynos8895_bank_type_off,	\
+		.pctl_offset	= reg,				\
+		.nr_pins	= pins,				\
+		.eint_type	= EINT_TYPE_GPIO,		\
+		.eint_offset	= offs,				\
+		.name		= id				\
+	}
+
 #define EXYNOSV920_PIN_BANK_EINTG(pins, reg, id, con_offs, mask_offs, pend_offs)	\
 	{							\
 		.type			= &exynos850_bank_type_off,	\
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index 675efa5d86a9a..86c7de109bca3 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -1477,6 +1477,8 @@ static const struct of_device_id samsung_pinctrl_dt_match[] = {
 		.data = &exynos7885_of_data },
 	{ .compatible = "samsung,exynos850-pinctrl",
 		.data = &exynos850_of_data },
+	{ .compatible = "samsung,exynos8895-pinctrl",
+		.data = &exynos8895_of_data },
 	{ .compatible = "samsung,exynosautov9-pinctrl",
 		.data = &exynosautov9_of_data },
 	{ .compatible = "samsung,exynosautov920-pinctrl",
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index a1e7377bd890b..dc930d620f554 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -384,6 +384,7 @@ extern const struct samsung_pinctrl_of_match_data exynos5433_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos7_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos7885_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos850_of_data;
+extern const struct samsung_pinctrl_of_match_data exynos8895_of_data;
 extern const struct samsung_pinctrl_of_match_data exynosautov9_of_data;
 extern const struct samsung_pinctrl_of_match_data exynosautov920_of_data;
 extern const struct samsung_pinctrl_of_match_data fsd_of_data;

From 38e2d33f134055ce377b69fe5ae181881d73d415 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Tue, 1 Oct 2024 14:27:23 -0700
Subject: [PATCH 0077/1530] pinctrl: aw9523: use enable for regulator

devm_regulator_get_enable_optional can be used to simplify the logic
here.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Link: https://lore.kernel.org/20241001212724.309320-2-rosenp@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-aw9523.c | 21 +++++----------------
 1 file changed, 5 insertions(+), 16 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-aw9523.c b/drivers/pinctrl/pinctrl-aw9523.c
index d5cbc55eaecea..e312a2c0e6d2f 100644
--- a/drivers/pinctrl/pinctrl-aw9523.c
+++ b/drivers/pinctrl/pinctrl-aw9523.c
@@ -80,7 +80,7 @@ struct aw9523 {
 	struct regmap *regmap;
 	struct mutex i2c_lock;
 	struct gpio_desc *reset_gpio;
-	struct regulator *vio_vreg;
+	int vio_vreg;
 	struct pinctrl_dev *pctl;
 	struct gpio_chip gpio;
 	struct aw9523_irq *irq;
@@ -972,16 +972,9 @@ static int aw9523_probe(struct i2c_client *client)
 	if (IS_ERR(awi->regmap))
 		return PTR_ERR(awi->regmap);
 
-	awi->vio_vreg = devm_regulator_get_optional(dev, "vio");
-	if (IS_ERR(awi->vio_vreg)) {
-		if (PTR_ERR(awi->vio_vreg) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
-		awi->vio_vreg = NULL;
-	} else {
-		ret = regulator_enable(awi->vio_vreg);
-		if (ret)
-			return ret;
-	}
+	awi->vio_vreg = devm_regulator_get_enable_optional(dev, "vio");
+	if (awi->vio_vreg && awi->vio_vreg != -ENODEV)
+		return awi->vio_vreg;
 
 	mutex_init(&awi->i2c_lock);
 	lockdep_set_subclass(&awi->i2c_lock, i2c_adapter_depth(client->adapter));
@@ -1025,8 +1018,6 @@ static int aw9523_probe(struct i2c_client *client)
 	return ret;
 
 err_disable_vregs:
-	if (awi->vio_vreg)
-		regulator_disable(awi->vio_vreg);
 	mutex_destroy(&awi->i2c_lock);
 	return ret;
 }
@@ -1041,9 +1032,7 @@ static void aw9523_remove(struct i2c_client *client)
 	 * set the pins to hardware defaults before removing the driver
 	 * to leave it in a clean, safe and predictable state.
 	 */
-	if (awi->vio_vreg) {
-		regulator_disable(awi->vio_vreg);
-	} else {
+	if (awi->vio_vreg == -ENODEV) {
 		mutex_lock(&awi->i2c_lock);
 		aw9523_hw_init(awi);
 		mutex_unlock(&awi->i2c_lock);

From 30e830b8b952e550344224546f8cd83c5c49a5bf Mon Sep 17 00:00:00 2001
From: Quentin Schulz <quentin.schulz@cherry.de>
Date: Wed, 2 Oct 2024 14:03:03 +0200
Subject: [PATCH 0078/1530] pinctrl: rockchip: improve error message for
 incorrect rockchip,pins property

If one improperly writes a rockchip,pins property, the pinctrl driver
basically just states that one in the myriad of pinctrl nodes is
improper but does not tell you which one.

Instead, let's print the full name of the Device Tree node that is
improper as well as provide more context on what the expected content
is.

Note that this should be rather unnecessary if one reads the output of
the dtbs_check as it would be highlighted as an error.

Signed-off-by: Quentin Schulz <quentin.schulz@cherry.de>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/20241002-pinctrl-rockchip-error-modulo-4-v1-1-4addb4e5732a@cherry.de
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-rockchip.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index 5c1bc4d5b662e..04e85a6037c93 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -3227,7 +3227,9 @@ static int rockchip_pinctrl_parse_groups(struct device_node *np,
 	/* we do not check return since it's safe node passed down */
 	size /= sizeof(*list);
 	if (!size || size % 4)
-		return dev_err_probe(dev, -EINVAL, "wrong pins number or pins and configs should be by 4\n");
+		return dev_err_probe(dev, -EINVAL,
+				     "%pOF: rockchip,pins: expected one or more of <bank pin mux CONFIG>, got %d args instead\n",
+				     np, size);
 
 	grp->npins = size / 4;
 

From 5efa23224bf573d4bceb51bc646dd67b6ccb83b5 Mon Sep 17 00:00:00 2001
From: Fei Shao <fshao@chromium.org>
Date: Wed, 25 Sep 2024 18:57:46 +0800
Subject: [PATCH 0079/1530] dt-bindings: PCI: mediatek-gen3: Allow exact number
 of clocks only

In MediaTek PCIe gen3 bindings, "clocks" accepts a range of 1-6 clocks
across all SoCs. But in practice, each SoC requires a particular number of
clocks as defined in "clock-names", and the length of "clocks" and
"clock-names" can be inconsistent with current bindings.

For example:

  - MT8188, MT8192 and MT8195 all require 6 clocks, while the bindings
    accept 4-6 clocks.

  - MT7986 requires 4 clocks, while the bindings accept 4-6 clocks.

Update minItems and maxItems properties for individual SoCs as needed to
only accept the correct number of clocks.

Fixes: c6abd0eadec6 ("dt-bindings: PCI: mediatek-gen3: Add support for Airoha EN7581")
Link: https://lore.kernel.org/r/20240925110044.3678055-3-fshao@chromium.org
Signed-off-by: Fei Shao <fshao@chromium.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 .../devicetree/bindings/pci/mediatek-pcie-gen3.yaml          | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/pci/mediatek-pcie-gen3.yaml b/Documentation/devicetree/bindings/pci/mediatek-pcie-gen3.yaml
index 898c1be2d6a43..f05aab2b1addc 100644
--- a/Documentation/devicetree/bindings/pci/mediatek-pcie-gen3.yaml
+++ b/Documentation/devicetree/bindings/pci/mediatek-pcie-gen3.yaml
@@ -149,7 +149,7 @@ allOf:
     then:
       properties:
         clocks:
-          minItems: 4
+          minItems: 6
 
         clock-names:
           items:
@@ -178,7 +178,7 @@ allOf:
     then:
       properties:
         clocks:
-          minItems: 4
+          minItems: 6
 
         clock-names:
           items:
@@ -207,6 +207,7 @@ allOf:
       properties:
         clocks:
           minItems: 4
+          maxItems: 4
 
         clock-names:
           items:

From 06783dc52057045edd9cfcdd8f90899d04bc8678 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 2 Oct 2024 16:18:36 +0200
Subject: [PATCH 0080/1530] pinctrl: imx1: Fix too generic defines

The "PC" define is colliding with the (apparently broadcased)
define for "program counter" on Loongarch, so let's rename all
these 2-letter defines so they don't collide with stuff.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202410020940.wGISlWfV-lkp@intel.com/
Fixes: a55222b7a132 ("pinctrl: freescale: enable use with COMPILE_TEST")
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/freescale/pinctrl-imx1.c | 228 +++++++++++------------
 1 file changed, 114 insertions(+), 114 deletions(-)

diff --git a/drivers/pinctrl/freescale/pinctrl-imx1.c b/drivers/pinctrl/freescale/pinctrl-imx1.c
index 1e2b0fe9ffd6f..bd39cadf1f34d 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx1.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx1.c
@@ -12,122 +12,122 @@
 #include "pinctrl-imx1.h"
 
 #define PAD_ID(port, pin)	((port) * 32 + (pin))
-#define PA	0
-#define PB	1
-#define PC	2
-#define PD	3
+#define IMX1_PA	0
+#define IMX1_PB	1
+#define IMX1_PC	2
+#define IMX1_PD	3
 
 enum imx1_pads {
-	MX1_PAD_A24		= PAD_ID(PA, 0),
-	MX1_PAD_TIN		= PAD_ID(PA, 1),
-	MX1_PAD_PWMO		= PAD_ID(PA, 2),
-	MX1_PAD_CSI_MCLK	= PAD_ID(PA, 3),
-	MX1_PAD_CSI_D0		= PAD_ID(PA, 4),
-	MX1_PAD_CSI_D1		= PAD_ID(PA, 5),
-	MX1_PAD_CSI_D2		= PAD_ID(PA, 6),
-	MX1_PAD_CSI_D3		= PAD_ID(PA, 7),
-	MX1_PAD_CSI_D4		= PAD_ID(PA, 8),
-	MX1_PAD_CSI_D5		= PAD_ID(PA, 9),
-	MX1_PAD_CSI_D6		= PAD_ID(PA, 10),
-	MX1_PAD_CSI_D7		= PAD_ID(PA, 11),
-	MX1_PAD_CSI_VSYNC	= PAD_ID(PA, 12),
-	MX1_PAD_CSI_HSYNC	= PAD_ID(PA, 13),
-	MX1_PAD_CSI_PIXCLK	= PAD_ID(PA, 14),
-	MX1_PAD_I2C_SDA		= PAD_ID(PA, 15),
-	MX1_PAD_I2C_SCL		= PAD_ID(PA, 16),
-	MX1_PAD_DTACK		= PAD_ID(PA, 17),
-	MX1_PAD_BCLK		= PAD_ID(PA, 18),
-	MX1_PAD_LBA		= PAD_ID(PA, 19),
-	MX1_PAD_ECB		= PAD_ID(PA, 20),
-	MX1_PAD_A0		= PAD_ID(PA, 21),
-	MX1_PAD_CS4		= PAD_ID(PA, 22),
-	MX1_PAD_CS5		= PAD_ID(PA, 23),
-	MX1_PAD_A16		= PAD_ID(PA, 24),
-	MX1_PAD_A17		= PAD_ID(PA, 25),
-	MX1_PAD_A18		= PAD_ID(PA, 26),
-	MX1_PAD_A19		= PAD_ID(PA, 27),
-	MX1_PAD_A20		= PAD_ID(PA, 28),
-	MX1_PAD_A21		= PAD_ID(PA, 29),
-	MX1_PAD_A22		= PAD_ID(PA, 30),
-	MX1_PAD_A23		= PAD_ID(PA, 31),
-	MX1_PAD_SD_DAT0		= PAD_ID(PB, 8),
-	MX1_PAD_SD_DAT1		= PAD_ID(PB, 9),
-	MX1_PAD_SD_DAT2		= PAD_ID(PB, 10),
-	MX1_PAD_SD_DAT3		= PAD_ID(PB, 11),
-	MX1_PAD_SD_SCLK		= PAD_ID(PB, 12),
-	MX1_PAD_SD_CMD		= PAD_ID(PB, 13),
-	MX1_PAD_SIM_SVEN	= PAD_ID(PB, 14),
-	MX1_PAD_SIM_PD		= PAD_ID(PB, 15),
-	MX1_PAD_SIM_TX		= PAD_ID(PB, 16),
-	MX1_PAD_SIM_RX		= PAD_ID(PB, 17),
-	MX1_PAD_SIM_RST		= PAD_ID(PB, 18),
-	MX1_PAD_SIM_CLK		= PAD_ID(PB, 19),
-	MX1_PAD_USBD_AFE	= PAD_ID(PB, 20),
-	MX1_PAD_USBD_OE		= PAD_ID(PB, 21),
-	MX1_PAD_USBD_RCV	= PAD_ID(PB, 22),
-	MX1_PAD_USBD_SUSPND	= PAD_ID(PB, 23),
-	MX1_PAD_USBD_VP		= PAD_ID(PB, 24),
-	MX1_PAD_USBD_VM		= PAD_ID(PB, 25),
-	MX1_PAD_USBD_VPO	= PAD_ID(PB, 26),
-	MX1_PAD_USBD_VMO	= PAD_ID(PB, 27),
-	MX1_PAD_UART2_CTS	= PAD_ID(PB, 28),
-	MX1_PAD_UART2_RTS	= PAD_ID(PB, 29),
-	MX1_PAD_UART2_TXD	= PAD_ID(PB, 30),
-	MX1_PAD_UART2_RXD	= PAD_ID(PB, 31),
-	MX1_PAD_SSI_RXFS	= PAD_ID(PC, 3),
-	MX1_PAD_SSI_RXCLK	= PAD_ID(PC, 4),
-	MX1_PAD_SSI_RXDAT	= PAD_ID(PC, 5),
-	MX1_PAD_SSI_TXDAT	= PAD_ID(PC, 6),
-	MX1_PAD_SSI_TXFS	= PAD_ID(PC, 7),
-	MX1_PAD_SSI_TXCLK	= PAD_ID(PC, 8),
-	MX1_PAD_UART1_CTS	= PAD_ID(PC, 9),
-	MX1_PAD_UART1_RTS	= PAD_ID(PC, 10),
-	MX1_PAD_UART1_TXD	= PAD_ID(PC, 11),
-	MX1_PAD_UART1_RXD	= PAD_ID(PC, 12),
-	MX1_PAD_SPI1_RDY	= PAD_ID(PC, 13),
-	MX1_PAD_SPI1_SCLK	= PAD_ID(PC, 14),
-	MX1_PAD_SPI1_SS		= PAD_ID(PC, 15),
-	MX1_PAD_SPI1_MISO	= PAD_ID(PC, 16),
-	MX1_PAD_SPI1_MOSI	= PAD_ID(PC, 17),
-	MX1_PAD_BT13		= PAD_ID(PC, 19),
-	MX1_PAD_BT12		= PAD_ID(PC, 20),
-	MX1_PAD_BT11		= PAD_ID(PC, 21),
-	MX1_PAD_BT10		= PAD_ID(PC, 22),
-	MX1_PAD_BT9		= PAD_ID(PC, 23),
-	MX1_PAD_BT8		= PAD_ID(PC, 24),
-	MX1_PAD_BT7		= PAD_ID(PC, 25),
-	MX1_PAD_BT6		= PAD_ID(PC, 26),
-	MX1_PAD_BT5		= PAD_ID(PC, 27),
-	MX1_PAD_BT4		= PAD_ID(PC, 28),
-	MX1_PAD_BT3		= PAD_ID(PC, 29),
-	MX1_PAD_BT2		= PAD_ID(PC, 30),
-	MX1_PAD_BT1		= PAD_ID(PC, 31),
-	MX1_PAD_LSCLK		= PAD_ID(PD, 6),
-	MX1_PAD_REV		= PAD_ID(PD, 7),
-	MX1_PAD_CLS		= PAD_ID(PD, 8),
-	MX1_PAD_PS		= PAD_ID(PD, 9),
-	MX1_PAD_SPL_SPR		= PAD_ID(PD, 10),
-	MX1_PAD_CONTRAST	= PAD_ID(PD, 11),
-	MX1_PAD_ACD_OE		= PAD_ID(PD, 12),
-	MX1_PAD_LP_HSYNC	= PAD_ID(PD, 13),
-	MX1_PAD_FLM_VSYNC	= PAD_ID(PD, 14),
-	MX1_PAD_LD0		= PAD_ID(PD, 15),
-	MX1_PAD_LD1		= PAD_ID(PD, 16),
-	MX1_PAD_LD2		= PAD_ID(PD, 17),
-	MX1_PAD_LD3		= PAD_ID(PD, 18),
-	MX1_PAD_LD4		= PAD_ID(PD, 19),
-	MX1_PAD_LD5		= PAD_ID(PD, 20),
-	MX1_PAD_LD6		= PAD_ID(PD, 21),
-	MX1_PAD_LD7		= PAD_ID(PD, 22),
-	MX1_PAD_LD8		= PAD_ID(PD, 23),
-	MX1_PAD_LD9		= PAD_ID(PD, 24),
-	MX1_PAD_LD10		= PAD_ID(PD, 25),
-	MX1_PAD_LD11		= PAD_ID(PD, 26),
-	MX1_PAD_LD12		= PAD_ID(PD, 27),
-	MX1_PAD_LD13		= PAD_ID(PD, 28),
-	MX1_PAD_LD14		= PAD_ID(PD, 29),
-	MX1_PAD_LD15		= PAD_ID(PD, 30),
-	MX1_PAD_TMR2OUT		= PAD_ID(PD, 31),
+	MX1_PAD_A24		= PAD_ID(IMX1_PA, 0),
+	MX1_PAD_TIN		= PAD_ID(IMX1_PA, 1),
+	MX1_PAD_PWMO		= PAD_ID(IMX1_PA, 2),
+	MX1_PAD_CSI_MCLK	= PAD_ID(IMX1_PA, 3),
+	MX1_PAD_CSI_D0		= PAD_ID(IMX1_PA, 4),
+	MX1_PAD_CSI_D1		= PAD_ID(IMX1_PA, 5),
+	MX1_PAD_CSI_D2		= PAD_ID(IMX1_PA, 6),
+	MX1_PAD_CSI_D3		= PAD_ID(IMX1_PA, 7),
+	MX1_PAD_CSI_D4		= PAD_ID(IMX1_PA, 8),
+	MX1_PAD_CSI_D5		= PAD_ID(IMX1_PA, 9),
+	MX1_PAD_CSI_D6		= PAD_ID(IMX1_PA, 10),
+	MX1_PAD_CSI_D7		= PAD_ID(IMX1_PA, 11),
+	MX1_PAD_CSI_VSYNC	= PAD_ID(IMX1_PA, 12),
+	MX1_PAD_CSI_HSYNC	= PAD_ID(IMX1_PA, 13),
+	MX1_PAD_CSI_PIXCLK	= PAD_ID(IMX1_PA, 14),
+	MX1_PAD_I2C_SDA		= PAD_ID(IMX1_PA, 15),
+	MX1_PAD_I2C_SCL		= PAD_ID(IMX1_PA, 16),
+	MX1_PAD_DTACK		= PAD_ID(IMX1_PA, 17),
+	MX1_PAD_BCLK		= PAD_ID(IMX1_PA, 18),
+	MX1_PAD_LBA		= PAD_ID(IMX1_PA, 19),
+	MX1_PAD_ECB		= PAD_ID(IMX1_PA, 20),
+	MX1_PAD_A0		= PAD_ID(IMX1_PA, 21),
+	MX1_PAD_CS4		= PAD_ID(IMX1_PA, 22),
+	MX1_PAD_CS5		= PAD_ID(IMX1_PA, 23),
+	MX1_PAD_A16		= PAD_ID(IMX1_PA, 24),
+	MX1_PAD_A17		= PAD_ID(IMX1_PA, 25),
+	MX1_PAD_A18		= PAD_ID(IMX1_PA, 26),
+	MX1_PAD_A19		= PAD_ID(IMX1_PA, 27),
+	MX1_PAD_A20		= PAD_ID(IMX1_PA, 28),
+	MX1_PAD_A21		= PAD_ID(IMX1_PA, 29),
+	MX1_PAD_A22		= PAD_ID(IMX1_PA, 30),
+	MX1_PAD_A23		= PAD_ID(IMX1_PA, 31),
+	MX1_PAD_SD_DAT0		= PAD_ID(IMX1_PB, 8),
+	MX1_PAD_SD_DAT1		= PAD_ID(IMX1_PB, 9),
+	MX1_PAD_SD_DAT2		= PAD_ID(IMX1_PB, 10),
+	MX1_PAD_SD_DAT3		= PAD_ID(IMX1_PB, 11),
+	MX1_PAD_SD_SCLK		= PAD_ID(IMX1_PB, 12),
+	MX1_PAD_SD_CMD		= PAD_ID(IMX1_PB, 13),
+	MX1_PAD_SIM_SVEN	= PAD_ID(IMX1_PB, 14),
+	MX1_PAD_SIM_PD		= PAD_ID(IMX1_PB, 15),
+	MX1_PAD_SIM_TX		= PAD_ID(IMX1_PB, 16),
+	MX1_PAD_SIM_RX		= PAD_ID(IMX1_PB, 17),
+	MX1_PAD_SIM_RST		= PAD_ID(IMX1_PB, 18),
+	MX1_PAD_SIM_CLK		= PAD_ID(IMX1_PB, 19),
+	MX1_PAD_USBD_AFE	= PAD_ID(IMX1_PB, 20),
+	MX1_PAD_USBD_OE		= PAD_ID(IMX1_PB, 21),
+	MX1_PAD_USBD_RCV	= PAD_ID(IMX1_PB, 22),
+	MX1_PAD_USBD_SUSPND	= PAD_ID(IMX1_PB, 23),
+	MX1_PAD_USBD_VP		= PAD_ID(IMX1_PB, 24),
+	MX1_PAD_USBD_VM		= PAD_ID(IMX1_PB, 25),
+	MX1_PAD_USBD_VPO	= PAD_ID(IMX1_PB, 26),
+	MX1_PAD_USBD_VMO	= PAD_ID(IMX1_PB, 27),
+	MX1_PAD_UART2_CTS	= PAD_ID(IMX1_PB, 28),
+	MX1_PAD_UART2_RTS	= PAD_ID(IMX1_PB, 29),
+	MX1_PAD_UART2_TXD	= PAD_ID(IMX1_PB, 30),
+	MX1_PAD_UART2_RXD	= PAD_ID(IMX1_PB, 31),
+	MX1_PAD_SSI_RXFS	= PAD_ID(IMX1_PC, 3),
+	MX1_PAD_SSI_RXCLK	= PAD_ID(IMX1_PC, 4),
+	MX1_PAD_SSI_RXDAT	= PAD_ID(IMX1_PC, 5),
+	MX1_PAD_SSI_TXDAT	= PAD_ID(IMX1_PC, 6),
+	MX1_PAD_SSI_TXFS	= PAD_ID(IMX1_PC, 7),
+	MX1_PAD_SSI_TXCLK	= PAD_ID(IMX1_PC, 8),
+	MX1_PAD_UART1_CTS	= PAD_ID(IMX1_PC, 9),
+	MX1_PAD_UART1_RTS	= PAD_ID(IMX1_PC, 10),
+	MX1_PAD_UART1_TXD	= PAD_ID(IMX1_PC, 11),
+	MX1_PAD_UART1_RXD	= PAD_ID(IMX1_PC, 12),
+	MX1_PAD_SPI1_RDY	= PAD_ID(IMX1_PC, 13),
+	MX1_PAD_SPI1_SCLK	= PAD_ID(IMX1_PC, 14),
+	MX1_PAD_SPI1_SS		= PAD_ID(IMX1_PC, 15),
+	MX1_PAD_SPI1_MISO	= PAD_ID(IMX1_PC, 16),
+	MX1_PAD_SPI1_MOSI	= PAD_ID(IMX1_PC, 17),
+	MX1_PAD_BT13		= PAD_ID(IMX1_PC, 19),
+	MX1_PAD_BT12		= PAD_ID(IMX1_PC, 20),
+	MX1_PAD_BT11		= PAD_ID(IMX1_PC, 21),
+	MX1_PAD_BT10		= PAD_ID(IMX1_PC, 22),
+	MX1_PAD_BT9		= PAD_ID(IMX1_PC, 23),
+	MX1_PAD_BT8		= PAD_ID(IMX1_PC, 24),
+	MX1_PAD_BT7		= PAD_ID(IMX1_PC, 25),
+	MX1_PAD_BT6		= PAD_ID(IMX1_PC, 26),
+	MX1_PAD_BT5		= PAD_ID(IMX1_PC, 27),
+	MX1_PAD_BT4		= PAD_ID(IMX1_PC, 28),
+	MX1_PAD_BT3		= PAD_ID(IMX1_PC, 29),
+	MX1_PAD_BT2		= PAD_ID(IMX1_PC, 30),
+	MX1_PAD_BT1		= PAD_ID(IMX1_PC, 31),
+	MX1_PAD_LSCLK		= PAD_ID(IMX1_PD, 6),
+	MX1_PAD_REV		= PAD_ID(IMX1_PD, 7),
+	MX1_PAD_CLS		= PAD_ID(IMX1_PD, 8),
+	MX1_PAD_PS		= PAD_ID(IMX1_PD, 9),
+	MX1_PAD_SPL_SPR		= PAD_ID(IMX1_PD, 10),
+	MX1_PAD_CONTRAST	= PAD_ID(IMX1_PD, 11),
+	MX1_PAD_ACD_OE		= PAD_ID(IMX1_PD, 12),
+	MX1_PAD_LP_HSYNC	= PAD_ID(IMX1_PD, 13),
+	MX1_PAD_FLM_VSYNC	= PAD_ID(IMX1_PD, 14),
+	MX1_PAD_LD0		= PAD_ID(IMX1_PD, 15),
+	MX1_PAD_LD1		= PAD_ID(IMX1_PD, 16),
+	MX1_PAD_LD2		= PAD_ID(IMX1_PD, 17),
+	MX1_PAD_LD3		= PAD_ID(IMX1_PD, 18),
+	MX1_PAD_LD4		= PAD_ID(IMX1_PD, 19),
+	MX1_PAD_LD5		= PAD_ID(IMX1_PD, 20),
+	MX1_PAD_LD6		= PAD_ID(IMX1_PD, 21),
+	MX1_PAD_LD7		= PAD_ID(IMX1_PD, 22),
+	MX1_PAD_LD8		= PAD_ID(IMX1_PD, 23),
+	MX1_PAD_LD9		= PAD_ID(IMX1_PD, 24),
+	MX1_PAD_LD10		= PAD_ID(IMX1_PD, 25),
+	MX1_PAD_LD11		= PAD_ID(IMX1_PD, 26),
+	MX1_PAD_LD12		= PAD_ID(IMX1_PD, 27),
+	MX1_PAD_LD13		= PAD_ID(IMX1_PD, 28),
+	MX1_PAD_LD14		= PAD_ID(IMX1_PD, 29),
+	MX1_PAD_LD15		= PAD_ID(IMX1_PD, 30),
+	MX1_PAD_TMR2OUT		= PAD_ID(IMX1_PD, 31),
 };
 
 /* Pad names for the pinmux subsystem */

From f69767a1ada3ac74be2e1ac0795a05e1d1384eff Mon Sep 17 00:00:00 2001
From: Wei Huang <wei.huang2@amd.com>
Date: Wed, 2 Oct 2024 11:59:50 -0500
Subject: [PATCH 0081/1530] PCI: Add TLP Processing Hints (TPH) support

Add support for PCIe TLP Processing Hints (TPH) support (see PCIe r6.2,
sec 6.17).

Add TPH register definitions in pci_regs.h, including the TPH Requester
capability register, TPH Requester control register, TPH Completer
capability, and the ST fields of MSI-X entry.

Introduce pcie_enable_tph() and pcie_disable_tph(), enabling drivers to
toggle TPH support and configure specific ST mode as needed. Also add a new
kernel parameter, "pci=notph", allowing users to disable TPH support across
the entire system.

Link: https://lore.kernel.org/r/20241002165954.128085-2-wei.huang2@amd.com
Co-developed-by: Jing Liu <jing2.liu@intel.com>
Co-developed-by: Paul Luse <paul.e.luse@linux.intel.com>
Co-developed-by: Eric Van Tassell <Eric.VanTassell@amd.com>
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Paul Luse <paul.e.luse@linux.intel.com>
Signed-off-by: Eric Van Tassell <Eric.VanTassell@amd.com>
Signed-off-by: Wei Huang <wei.huang2@amd.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Lukas Wunner <lukas@wunner.de>
---
 .../admin-guide/kernel-parameters.txt         |   4 +
 drivers/pci/Kconfig                           |   9 +
 drivers/pci/Makefile                          |   1 +
 drivers/pci/pci.c                             |   4 +
 drivers/pci/pci.h                             |  12 ++
 drivers/pci/probe.c                           |   1 +
 drivers/pci/tph.c                             | 197 ++++++++++++++++++
 include/linux/pci-tph.h                       |  21 ++
 include/linux/pci.h                           |   7 +
 include/uapi/linux/pci_regs.h                 |  37 +++-
 10 files changed, 285 insertions(+), 8 deletions(-)
 create mode 100644 drivers/pci/tph.c
 create mode 100644 include/linux/pci-tph.h

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 1518343bbe223..178995b07451f 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4678,6 +4678,10 @@
 		nomio		[S390] Do not use MIO instructions.
 		norid		[S390] ignore the RID field and force use of
 				one PCI domain per PCI function
+		notph		[PCIE] If the PCIE_TPH kernel config parameter
+				is enabled, this kernel boot option can be used
+				to disable PCIe TLP Processing Hints support
+				system-wide.
 
 	pcie_aspm=	[PCIE] Forcibly enable or ignore PCIe Active State Power
 			Management.
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 0d94e4a967d81..2f270e4414b31 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -173,6 +173,15 @@ config PCI_PASID
 
 	  If unsure, say N.
 
+config PCIE_TPH
+	bool "TLP Processing Hints"
+	help
+	  This option adds support for PCIe TLP Processing Hints (TPH).
+	  TPH allows endpoint devices to provide optimization hints, such as
+	  desired caching behavior, for requests that target memory space.
+	  These hints, called Steering Tags, can empower the system hardware
+	  to optimize the utilization of platform resources.
+
 config PCI_P2PDMA
 	bool "PCI peer-to-peer transfer support"
 	depends on ZONE_DEVICE
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 374c5c06d92f9..b2a100f2e24a3 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -36,6 +36,7 @@ obj-$(CONFIG_VGA_ARB)		+= vgaarb.o
 obj-$(CONFIG_PCI_DOE)		+= doe.o
 obj-$(CONFIG_PCI_DYNAMIC_OF_NODES) += of_property.o
 obj-$(CONFIG_PCI_NPEM)		+= npem.o
+obj-$(CONFIG_PCIE_TPH)		+= tph.o
 
 # Endpoint library must be initialized before its users
 obj-$(CONFIG_PCI_ENDPOINT)	+= endpoint/
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 7d85c04fbba2a..89dafecc869bd 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1828,6 +1828,7 @@ int pci_save_state(struct pci_dev *dev)
 	pci_save_dpc_state(dev);
 	pci_save_aer_state(dev);
 	pci_save_ptm_state(dev);
+	pci_save_tph_state(dev);
 	return pci_save_vc_state(dev);
 }
 EXPORT_SYMBOL(pci_save_state);
@@ -1933,6 +1934,7 @@ void pci_restore_state(struct pci_dev *dev)
 	pci_restore_rebar_state(dev);
 	pci_restore_dpc_state(dev);
 	pci_restore_ptm_state(dev);
+	pci_restore_tph_state(dev);
 
 	pci_aer_clear_status(dev);
 	pci_restore_aer_state(dev);
@@ -6896,6 +6898,8 @@ static int __init pci_setup(char *str)
 				pci_no_domains();
 			} else if (!strncmp(str, "noari", 5)) {
 				pcie_ari_disabled = true;
+			} else if (!strncmp(str, "notph", 5)) {
+				pci_no_tph();
 			} else if (!strncmp(str, "cbiosize=", 9)) {
 				pci_cardbus_io_size = memparse(str + 9, &str);
 			} else if (!strncmp(str, "cbmemsize=", 10)) {
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 14d00ce45bfa9..d89fdbf04f363 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -597,6 +597,18 @@ static inline int pci_iov_bus_range(struct pci_bus *bus)
 
 #endif /* CONFIG_PCI_IOV */
 
+#ifdef CONFIG_PCIE_TPH
+void pci_restore_tph_state(struct pci_dev *dev);
+void pci_save_tph_state(struct pci_dev *dev);
+void pci_no_tph(void);
+void pci_tph_init(struct pci_dev *dev);
+#else
+static inline void pci_restore_tph_state(struct pci_dev *dev) { }
+static inline void pci_save_tph_state(struct pci_dev *dev) { }
+static inline void pci_no_tph(void) { }
+static inline void pci_tph_init(struct pci_dev *dev) { }
+#endif
+
 #ifdef CONFIG_PCIE_PTM
 void pci_ptm_init(struct pci_dev *dev);
 void pci_save_ptm_state(struct pci_dev *dev);
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 4f68414c30860..b086d53a90485 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2495,6 +2495,7 @@ static void pci_init_capabilities(struct pci_dev *dev)
 	pci_dpc_init(dev);		/* Downstream Port Containment */
 	pci_rcec_init(dev);		/* Root Complex Event Collector */
 	pci_doe_init(dev);		/* Data Object Exchange */
+	pci_tph_init(dev);		/* TLP Processing Hints */
 
 	pcie_report_downtraining(dev);
 	pci_init_reset_methods(dev);
diff --git a/drivers/pci/tph.c b/drivers/pci/tph.c
new file mode 100644
index 0000000000000..4d6317cbf8a6d
--- /dev/null
+++ b/drivers/pci/tph.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * TPH (TLP Processing Hints) support
+ *
+ * Copyright (C) 2024 Advanced Micro Devices, Inc.
+ *     Eric Van Tassell <Eric.VanTassell@amd.com>
+ *     Wei Huang <wei.huang2@amd.com>
+ */
+#include <linux/pci.h>
+#include <linux/bitfield.h>
+#include <linux/pci-tph.h>
+
+#include "pci.h"
+
+/* System-wide TPH disabled */
+static bool pci_tph_disabled;
+
+static u8 get_st_modes(struct pci_dev *pdev)
+{
+	u32 reg;
+
+	pci_read_config_dword(pdev, pdev->tph_cap + PCI_TPH_CAP, &reg);
+	reg &= PCI_TPH_CAP_ST_NS | PCI_TPH_CAP_ST_IV | PCI_TPH_CAP_ST_DS;
+
+	return reg;
+}
+
+/* Return device's Root Port completer capability */
+static u8 get_rp_completer_type(struct pci_dev *pdev)
+{
+	struct pci_dev *rp;
+	u32 reg;
+	int ret;
+
+	rp = pcie_find_root_port(pdev);
+	if (!rp)
+		return 0;
+
+	ret = pcie_capability_read_dword(rp, PCI_EXP_DEVCAP2, &reg);
+	if (ret)
+		return 0;
+
+	return FIELD_GET(PCI_EXP_DEVCAP2_TPH_COMP_MASK, reg);
+}
+
+/**
+ * pcie_disable_tph - Turn off TPH support for device
+ * @pdev: PCI device
+ *
+ * Return: none
+ */
+void pcie_disable_tph(struct pci_dev *pdev)
+{
+	if (!pdev->tph_cap)
+		return;
+
+	if (!pdev->tph_enabled)
+		return;
+
+	pci_write_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, 0);
+
+	pdev->tph_mode = 0;
+	pdev->tph_req_type = 0;
+	pdev->tph_enabled = 0;
+}
+EXPORT_SYMBOL(pcie_disable_tph);
+
+/**
+ * pcie_enable_tph - Enable TPH support for device using a specific ST mode
+ * @pdev: PCI device
+ * @mode: ST mode to enable. Current supported modes include:
+ *
+ *   - PCI_TPH_ST_NS_MODE: NO ST Mode
+ *   - PCI_TPH_ST_IV_MODE: Interrupt Vector Mode
+ *   - PCI_TPH_ST_DS_MODE: Device Specific Mode
+ *
+ * Check whether the mode is actually supported by the device before enabling
+ * and return an error if not. Additionally determine what types of requests,
+ * TPH or extended TPH, can be issued by the device based on its TPH requester
+ * capability and the Root Port's completer capability.
+ *
+ * Return: 0 on success, otherwise negative value (-errno)
+ */
+int pcie_enable_tph(struct pci_dev *pdev, int mode)
+{
+	u32 reg;
+	u8 dev_modes;
+	u8 rp_req_type;
+
+	/* Honor "notph" kernel parameter */
+	if (pci_tph_disabled)
+		return -EINVAL;
+
+	if (!pdev->tph_cap)
+		return -EINVAL;
+
+	if (pdev->tph_enabled)
+		return -EBUSY;
+
+	/* Sanitize and check ST mode compatibility */
+	mode &= PCI_TPH_CTRL_MODE_SEL_MASK;
+	dev_modes = get_st_modes(pdev);
+	if (!((1 << mode) & dev_modes))
+		return -EINVAL;
+
+	pdev->tph_mode = mode;
+
+	/* Get req_type supported by device and its Root Port */
+	pci_read_config_dword(pdev, pdev->tph_cap + PCI_TPH_CAP, &reg);
+	if (FIELD_GET(PCI_TPH_CAP_EXT_TPH, reg))
+		pdev->tph_req_type = PCI_TPH_REQ_EXT_TPH;
+	else
+		pdev->tph_req_type = PCI_TPH_REQ_TPH_ONLY;
+
+	rp_req_type = get_rp_completer_type(pdev);
+
+	/* Final req_type is the smallest value of two */
+	pdev->tph_req_type = min(pdev->tph_req_type, rp_req_type);
+
+	if (pdev->tph_req_type == PCI_TPH_REQ_DISABLE)
+		return -EINVAL;
+
+	/* Write them into TPH control register */
+	pci_read_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, &reg);
+
+	reg &= ~PCI_TPH_CTRL_MODE_SEL_MASK;
+	reg |= FIELD_PREP(PCI_TPH_CTRL_MODE_SEL_MASK, pdev->tph_mode);
+
+	reg &= ~PCI_TPH_CTRL_REQ_EN_MASK;
+	reg |= FIELD_PREP(PCI_TPH_CTRL_REQ_EN_MASK, pdev->tph_req_type);
+
+	pci_write_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, reg);
+
+	pdev->tph_enabled = 1;
+
+	return 0;
+}
+EXPORT_SYMBOL(pcie_enable_tph);
+
+void pci_restore_tph_state(struct pci_dev *pdev)
+{
+	struct pci_cap_saved_state *save_state;
+	u32 *cap;
+
+	if (!pdev->tph_cap)
+		return;
+
+	if (!pdev->tph_enabled)
+		return;
+
+	save_state = pci_find_saved_ext_cap(pdev, PCI_EXT_CAP_ID_TPH);
+	if (!save_state)
+		return;
+
+	/* Restore control register and all ST entries */
+	cap = &save_state->cap.data[0];
+	pci_write_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, *cap++);
+}
+
+void pci_save_tph_state(struct pci_dev *pdev)
+{
+	struct pci_cap_saved_state *save_state;
+	u32 *cap;
+
+	if (!pdev->tph_cap)
+		return;
+
+	if (!pdev->tph_enabled)
+		return;
+
+	save_state = pci_find_saved_ext_cap(pdev, PCI_EXT_CAP_ID_TPH);
+	if (!save_state)
+		return;
+
+	/* Save control register */
+	cap = &save_state->cap.data[0];
+	pci_read_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, cap++);
+}
+
+void pci_no_tph(void)
+{
+	pci_tph_disabled = true;
+
+	pr_info("PCIe TPH is disabled\n");
+}
+
+void pci_tph_init(struct pci_dev *pdev)
+{
+	u32 save_size;
+
+	pdev->tph_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_TPH);
+	if (!pdev->tph_cap)
+		return;
+
+	save_size = sizeof(u32);
+	pci_add_ext_cap_save_buffer(pdev, PCI_EXT_CAP_ID_TPH, save_size);
+}
diff --git a/include/linux/pci-tph.h b/include/linux/pci-tph.h
new file mode 100644
index 0000000000000..58654a334ffba
--- /dev/null
+++ b/include/linux/pci-tph.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * TPH (TLP Processing Hints)
+ *
+ * Copyright (C) 2024 Advanced Micro Devices, Inc.
+ *     Eric Van Tassell <Eric.VanTassell@amd.com>
+ *     Wei Huang <wei.huang2@amd.com>
+ */
+#ifndef LINUX_PCI_TPH_H
+#define LINUX_PCI_TPH_H
+
+#ifdef CONFIG_PCIE_TPH
+void pcie_disable_tph(struct pci_dev *pdev);
+int pcie_enable_tph(struct pci_dev *pdev, int mode);
+#else
+static inline void pcie_disable_tph(struct pci_dev *pdev) { }
+static inline int pcie_enable_tph(struct pci_dev *pdev, int mode)
+{ return -EINVAL; }
+#endif
+
+#endif /* LINUX_PCI_TPH_H */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 573b4c4c2be61..8351d76b6e126 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -434,6 +434,7 @@ struct pci_dev {
 	unsigned int	ats_enabled:1;		/* Address Translation Svc */
 	unsigned int	pasid_enabled:1;	/* Process Address Space ID */
 	unsigned int	pri_enabled:1;		/* Page Request Interface */
+	unsigned int	tph_enabled:1;		/* TLP Processing Hints */
 	unsigned int	is_managed:1;		/* Managed via devres */
 	unsigned int	is_msi_managed:1;	/* MSI release via devres installed */
 	unsigned int	needs_freset:1;		/* Requires fundamental reset */
@@ -534,6 +535,12 @@ struct pci_dev {
 
 	/* These methods index pci_reset_fn_methods[] */
 	u8 reset_methods[PCI_NUM_RESET_METHODS]; /* In priority order */
+
+#ifdef CONFIG_PCIE_TPH
+	u16		tph_cap;	/* TPH capability offset */
+	u8		tph_mode;	/* TPH mode */
+	u8		tph_req_type;	/* TPH requester type */
+#endif
 };
 
 static inline struct pci_dev *pci_physfn(struct pci_dev *dev)
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 12323b3334a9c..155dea741615c 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -340,7 +340,8 @@
 #define PCI_MSIX_ENTRY_UPPER_ADDR	0x4  /* Message Upper Address */
 #define PCI_MSIX_ENTRY_DATA		0x8  /* Message Data */
 #define PCI_MSIX_ENTRY_VECTOR_CTRL	0xc  /* Vector Control */
-#define  PCI_MSIX_ENTRY_CTRL_MASKBIT	0x00000001
+#define  PCI_MSIX_ENTRY_CTRL_MASKBIT	0x00000001  /* Mask Bit */
+#define  PCI_MSIX_ENTRY_CTRL_ST		0xffff0000  /* Steering Tag */
 
 /* CompactPCI Hotswap Register */
 
@@ -659,6 +660,7 @@
 #define  PCI_EXP_DEVCAP2_ATOMIC_COMP64	0x00000100 /* 64b AtomicOp completion */
 #define  PCI_EXP_DEVCAP2_ATOMIC_COMP128	0x00000200 /* 128b AtomicOp completion */
 #define  PCI_EXP_DEVCAP2_LTR		0x00000800 /* Latency tolerance reporting */
+#define  PCI_EXP_DEVCAP2_TPH_COMP_MASK	0x00003000 /* TPH completer support */
 #define  PCI_EXP_DEVCAP2_OBFF_MASK	0x000c0000 /* OBFF support mechanism */
 #define  PCI_EXP_DEVCAP2_OBFF_MSG	0x00040000 /* New message signaling */
 #define  PCI_EXP_DEVCAP2_OBFF_WAKE	0x00080000 /* Re-use WAKE# for OBFF */
@@ -1023,15 +1025,34 @@
 #define  PCI_DPA_CAP_SUBSTATE_MASK	0x1F	/* # substates - 1 */
 #define PCI_DPA_BASE_SIZEOF	16	/* size with 0 substates */
 
+/* TPH Completer Support */
+#define PCI_EXP_DEVCAP2_TPH_COMP_NONE		0x0 /* None */
+#define PCI_EXP_DEVCAP2_TPH_COMP_TPH_ONLY	0x1 /* TPH only */
+#define PCI_EXP_DEVCAP2_TPH_COMP_EXT_TPH	0x3 /* TPH and Extended TPH */
+
 /* TPH Requester */
 #define PCI_TPH_CAP		4	/* capability register */
-#define  PCI_TPH_CAP_LOC_MASK	0x600	/* location mask */
-#define   PCI_TPH_LOC_NONE	0x000	/* no location */
-#define   PCI_TPH_LOC_CAP	0x200	/* in capability */
-#define   PCI_TPH_LOC_MSIX	0x400	/* in MSI-X */
-#define PCI_TPH_CAP_ST_MASK	0x07FF0000	/* ST table mask */
-#define PCI_TPH_CAP_ST_SHIFT	16	/* ST table shift */
-#define PCI_TPH_BASE_SIZEOF	0xc	/* size with no ST table */
+#define  PCI_TPH_CAP_ST_NS	0x00000001 /* No ST Mode Supported */
+#define  PCI_TPH_CAP_ST_IV	0x00000002 /* Interrupt Vector Mode Supported */
+#define  PCI_TPH_CAP_ST_DS	0x00000004 /* Device Specific Mode Supported */
+#define  PCI_TPH_CAP_EXT_TPH	0x00000100 /* Ext TPH Requester Supported */
+#define  PCI_TPH_CAP_LOC_MASK	0x00000600 /* ST Table Location */
+#define   PCI_TPH_LOC_NONE	0x00000000 /* Not present */
+#define   PCI_TPH_LOC_CAP	0x00000200 /* In capability */
+#define   PCI_TPH_LOC_MSIX	0x00000400 /* In MSI-X */
+#define  PCI_TPH_CAP_ST_MASK	0x07FF0000 /* ST Table Size */
+#define  PCI_TPH_CAP_ST_SHIFT	16	/* ST Table Size shift */
+#define PCI_TPH_BASE_SIZEOF	0xc	/* Size with no ST table */
+
+#define PCI_TPH_CTRL		8	/* control register */
+#define  PCI_TPH_CTRL_MODE_SEL_MASK	0x00000007 /* ST Mode Select */
+#define   PCI_TPH_ST_NS_MODE		0x0 /* No ST Mode */
+#define   PCI_TPH_ST_IV_MODE		0x1 /* Interrupt Vector Mode */
+#define   PCI_TPH_ST_DS_MODE		0x2 /* Device Specific Mode */
+#define  PCI_TPH_CTRL_REQ_EN_MASK	0x00000300 /* TPH Requester Enable */
+#define   PCI_TPH_REQ_DISABLE		0x0 /* No TPH requests allowed */
+#define   PCI_TPH_REQ_TPH_ONLY		0x1 /* TPH only requests allowed */
+#define   PCI_TPH_REQ_EXT_TPH		0x3 /* Extended TPH requests allowed */
 
 /* Downstream Port Containment */
 #define PCI_EXP_DPC_CAP			0x04	/* DPC Capability */

From d2e8a34876ce69b27f450eebfc550ab8e316f752 Mon Sep 17 00:00:00 2001
From: Wei Huang <wei.huang2@amd.com>
Date: Wed, 2 Oct 2024 11:59:51 -0500
Subject: [PATCH 0082/1530] PCI/TPH: Add Steering Tag support

Add pcie_tph_get_cpu_st() to allow a caller to retrieve Steering Tags for a
target memory associated with a specific CPU. The ST tag is retrieved by
invoking PCI ACPI "_DSM to Query Cache Locality TPH Features" method
(rev=0x7, func=0xF) of the device's Root Port device.

Add pcie_tph_set_st_entry() to update the device's Steering Tags. The tags
will be written into the device's MSI-X table or the ST table located in
the TPH Extended Capability space.

Co-developed-by: Eric Van Tassell <Eric.VanTassell@amd.com>
Link: https://lore.kernel.org/r/20241002165954.128085-3-wei.huang2@amd.com
Signed-off-by: Eric Van Tassell <Eric.VanTassell@amd.com>
Signed-off-by: Wei Huang <wei.huang2@amd.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
---
 drivers/pci/tph.c       | 352 +++++++++++++++++++++++++++++++++++++++-
 include/linux/pci-tph.h |  23 +++
 2 files changed, 374 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/tph.c b/drivers/pci/tph.c
index 4d6317cbf8a6d..1e604fbbda657 100644
--- a/drivers/pci/tph.c
+++ b/drivers/pci/tph.c
@@ -7,6 +7,8 @@
  *     Wei Huang <wei.huang2@amd.com>
  */
 #include <linux/pci.h>
+#include <linux/pci-acpi.h>
+#include <linux/msi.h>
 #include <linux/bitfield.h>
 #include <linux/pci-tph.h>
 
@@ -15,6 +17,134 @@
 /* System-wide TPH disabled */
 static bool pci_tph_disabled;
 
+#ifdef CONFIG_ACPI
+/*
+ * The st_info struct defines the Steering Tag (ST) info returned by the
+ * firmware PCI ACPI _DSM method (rev=0x7, func=0xF, "_DSM to Query Cache
+ * Locality TPH Features"), as specified in the approved ECN for PCI Firmware
+ * Spec and available at https://members.pcisig.com/wg/PCI-SIG/document/15470.
+ *
+ * @vm_st_valid:  8-bit ST for volatile memory is valid
+ * @vm_xst_valid: 16-bit extended ST for volatile memory is valid
+ * @vm_ph_ignore: 1 => PH was and will be ignored, 0 => PH should be supplied
+ * @vm_st:        8-bit ST for volatile mem
+ * @vm_xst:       16-bit extended ST for volatile mem
+ * @pm_st_valid:  8-bit ST for persistent memory is valid
+ * @pm_xst_valid: 16-bit extended ST for persistent memory is valid
+ * @pm_ph_ignore: 1 => PH was and will be ignored, 0 => PH should be supplied
+ * @pm_st:        8-bit ST for persistent mem
+ * @pm_xst:       16-bit extended ST for persistent mem
+ */
+union st_info {
+	struct {
+		u64 vm_st_valid : 1;
+		u64 vm_xst_valid : 1;
+		u64 vm_ph_ignore : 1;
+		u64 rsvd1 : 5;
+		u64 vm_st : 8;
+		u64 vm_xst : 16;
+		u64 pm_st_valid : 1;
+		u64 pm_xst_valid : 1;
+		u64 pm_ph_ignore : 1;
+		u64 rsvd2 : 5;
+		u64 pm_st : 8;
+		u64 pm_xst : 16;
+	};
+	u64 value;
+};
+
+static u16 tph_extract_tag(enum tph_mem_type mem_type, u8 req_type,
+			   union st_info *info)
+{
+	switch (req_type) {
+	case PCI_TPH_REQ_TPH_ONLY: /* 8-bit tag */
+		switch (mem_type) {
+		case TPH_MEM_TYPE_VM:
+			if (info->vm_st_valid)
+				return info->vm_st;
+			break;
+		case TPH_MEM_TYPE_PM:
+			if (info->pm_st_valid)
+				return info->pm_st;
+			break;
+		}
+		break;
+	case PCI_TPH_REQ_EXT_TPH: /* 16-bit tag */
+		switch (mem_type) {
+		case TPH_MEM_TYPE_VM:
+			if (info->vm_xst_valid)
+				return info->vm_xst;
+			break;
+		case TPH_MEM_TYPE_PM:
+			if (info->pm_xst_valid)
+				return info->pm_xst;
+			break;
+		}
+		break;
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
+#define TPH_ST_DSM_FUNC_INDEX	0xF
+static acpi_status tph_invoke_dsm(acpi_handle handle, u32 cpu_uid,
+				  union st_info *st_out)
+{
+	union acpi_object arg3[3], in_obj, *out_obj;
+
+	if (!acpi_check_dsm(handle, &pci_acpi_dsm_guid, 7,
+			    BIT(TPH_ST_DSM_FUNC_INDEX)))
+		return AE_ERROR;
+
+	/* DWORD: feature ID (0 for processor cache ST query) */
+	arg3[0].integer.type = ACPI_TYPE_INTEGER;
+	arg3[0].integer.value = 0;
+
+	/* DWORD: target UID */
+	arg3[1].integer.type = ACPI_TYPE_INTEGER;
+	arg3[1].integer.value = cpu_uid;
+
+	/* QWORD: properties, all 0's */
+	arg3[2].integer.type = ACPI_TYPE_INTEGER;
+	arg3[2].integer.value = 0;
+
+	in_obj.type = ACPI_TYPE_PACKAGE;
+	in_obj.package.count = ARRAY_SIZE(arg3);
+	in_obj.package.elements = arg3;
+
+	out_obj = acpi_evaluate_dsm(handle, &pci_acpi_dsm_guid, 7,
+				    TPH_ST_DSM_FUNC_INDEX, &in_obj);
+	if (!out_obj)
+		return AE_ERROR;
+
+	if (out_obj->type != ACPI_TYPE_BUFFER) {
+		ACPI_FREE(out_obj);
+		return AE_ERROR;
+	}
+
+	st_out->value = *((u64 *)(out_obj->buffer.pointer));
+
+	ACPI_FREE(out_obj);
+
+	return AE_OK;
+}
+#endif
+
+/* Update the TPH Requester Enable field of TPH Control Register */
+static void set_ctrl_reg_req_en(struct pci_dev *pdev, u8 req_type)
+{
+	u32 reg;
+
+	pci_read_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, &reg);
+
+	reg &= ~PCI_TPH_CTRL_REQ_EN_MASK;
+	reg |= FIELD_PREP(PCI_TPH_CTRL_REQ_EN_MASK, req_type);
+
+	pci_write_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, reg);
+}
+
 static u8 get_st_modes(struct pci_dev *pdev)
 {
 	u32 reg;
@@ -25,6 +155,37 @@ static u8 get_st_modes(struct pci_dev *pdev)
 	return reg;
 }
 
+static u32 get_st_table_loc(struct pci_dev *pdev)
+{
+	u32 reg;
+
+	pci_read_config_dword(pdev, pdev->tph_cap + PCI_TPH_CAP, &reg);
+
+	return FIELD_GET(PCI_TPH_CAP_LOC_MASK, reg);
+}
+
+/*
+ * Return the size of ST table. If ST table is not in TPH Requester Extended
+ * Capability space, return 0. Otherwise return the ST Table Size + 1.
+ */
+static u16 get_st_table_size(struct pci_dev *pdev)
+{
+	u32 reg;
+	u32 loc;
+
+	/* Check ST table location first */
+	loc = get_st_table_loc(pdev);
+
+	/* Convert loc to match with PCI_TPH_LOC_* defined in pci_regs.h */
+	loc = FIELD_PREP(PCI_TPH_CAP_LOC_MASK, loc);
+	if (loc != PCI_TPH_LOC_CAP)
+		return 0;
+
+	pci_read_config_dword(pdev, pdev->tph_cap + PCI_TPH_CAP, &reg);
+
+	return FIELD_GET(PCI_TPH_CAP_ST_MASK, reg) + 1;
+}
+
 /* Return device's Root Port completer capability */
 static u8 get_rp_completer_type(struct pci_dev *pdev)
 {
@@ -43,6 +204,171 @@ static u8 get_rp_completer_type(struct pci_dev *pdev)
 	return FIELD_GET(PCI_EXP_DEVCAP2_TPH_COMP_MASK, reg);
 }
 
+/* Write ST to MSI-X vector control reg - Return 0 if OK, otherwise -errno */
+static int write_tag_to_msix(struct pci_dev *pdev, int msix_idx, u16 tag)
+{
+#ifdef CONFIG_PCI_MSI
+	struct msi_desc *msi_desc = NULL;
+	void __iomem *vec_ctrl;
+	u32 val;
+	int err = 0;
+
+	msi_lock_descs(&pdev->dev);
+
+	/* Find the msi_desc entry with matching msix_idx */
+	msi_for_each_desc(msi_desc, &pdev->dev, MSI_DESC_ASSOCIATED) {
+		if (msi_desc->msi_index == msix_idx)
+			break;
+	}
+
+	if (!msi_desc) {
+		err = -ENXIO;
+		goto err_out;
+	}
+
+	/* Get the vector control register (offset 0xc) pointed by msix_idx */
+	vec_ctrl = pdev->msix_base + msix_idx * PCI_MSIX_ENTRY_SIZE;
+	vec_ctrl += PCI_MSIX_ENTRY_VECTOR_CTRL;
+
+	val = readl(vec_ctrl);
+	val &= ~PCI_MSIX_ENTRY_CTRL_ST;
+	val |= FIELD_PREP(PCI_MSIX_ENTRY_CTRL_ST, tag);
+	writel(val, vec_ctrl);
+
+	/* Read back to flush the update */
+	val = readl(vec_ctrl);
+
+err_out:
+	msi_unlock_descs(&pdev->dev);
+	return err;
+#else
+	return -ENODEV;
+#endif
+}
+
+/* Write tag to ST table - Return 0 if OK, otherwise -errno */
+static int write_tag_to_st_table(struct pci_dev *pdev, int index, u16 tag)
+{
+	int st_table_size;
+	int offset;
+
+	/* Check if index is out of bound */
+	st_table_size = get_st_table_size(pdev);
+	if (index >= st_table_size)
+		return -ENXIO;
+
+	offset = pdev->tph_cap + PCI_TPH_BASE_SIZEOF + index * sizeof(u16);
+
+	return pci_write_config_word(pdev, offset, tag);
+}
+
+/**
+ * pcie_tph_get_cpu_st() - Retrieve Steering Tag for a target memory associated
+ * with a specific CPU
+ * @pdev: PCI device
+ * @mem_type: target memory type (volatile or persistent RAM)
+ * @cpu_uid: associated CPU id
+ * @tag: Steering Tag to be returned
+ *
+ * Return the Steering Tag for a target memory that is associated with a
+ * specific CPU as indicated by cpu_uid.
+ *
+ * Return: 0 if success, otherwise negative value (-errno)
+ */
+int pcie_tph_get_cpu_st(struct pci_dev *pdev, enum tph_mem_type mem_type,
+			unsigned int cpu_uid, u16 *tag)
+{
+#ifdef CONFIG_ACPI
+	struct pci_dev *rp;
+	acpi_handle rp_acpi_handle;
+	union st_info info;
+
+	rp = pcie_find_root_port(pdev);
+	if (!rp || !rp->bus || !rp->bus->bridge)
+		return -ENODEV;
+
+	rp_acpi_handle = ACPI_HANDLE(rp->bus->bridge);
+
+	if (tph_invoke_dsm(rp_acpi_handle, cpu_uid, &info) != AE_OK) {
+		*tag = 0;
+		return -EINVAL;
+	}
+
+	*tag = tph_extract_tag(mem_type, pdev->tph_req_type, &info);
+
+	pci_dbg(pdev, "get steering tag: mem_type=%s, cpu_uid=%d, tag=%#04x\n",
+		(mem_type == TPH_MEM_TYPE_VM) ? "volatile" : "persistent",
+		cpu_uid, *tag);
+
+	return 0;
+#else
+	return -ENODEV;
+#endif
+}
+EXPORT_SYMBOL(pcie_tph_get_cpu_st);
+
+/**
+ * pcie_tph_set_st_entry() - Set Steering Tag in the ST table entry
+ * @pdev: PCI device
+ * @index: ST table entry index
+ * @tag: Steering Tag to be written
+ *
+ * Figure out the proper location of ST table, either in the MSI-X table or
+ * in the TPH Extended Capability space, and write the Steering Tag into
+ * the ST entry pointed by index.
+ *
+ * Return: 0 if success, otherwise negative value (-errno)
+ */
+int pcie_tph_set_st_entry(struct pci_dev *pdev, unsigned int index, u16 tag)
+{
+	u32 loc;
+	int err = 0;
+
+	if (!pdev->tph_cap)
+		return -EINVAL;
+
+	if (!pdev->tph_enabled)
+		return -EINVAL;
+
+	/* No need to write tag if device is in "No ST Mode" */
+	if (pdev->tph_mode == PCI_TPH_ST_NS_MODE)
+		return 0;
+
+	/*
+	 * Disable TPH before updating ST to avoid potential instability as
+	 * cautioned in PCIe r6.2, sec 6.17.3, "ST Modes of Operation"
+	 */
+	set_ctrl_reg_req_en(pdev, PCI_TPH_REQ_DISABLE);
+
+	loc = get_st_table_loc(pdev);
+	/* Convert loc to match with PCI_TPH_LOC_* */
+	loc = FIELD_PREP(PCI_TPH_CAP_LOC_MASK, loc);
+
+	switch (loc) {
+	case PCI_TPH_LOC_MSIX:
+		err = write_tag_to_msix(pdev, index, tag);
+		break;
+	case PCI_TPH_LOC_CAP:
+		err = write_tag_to_st_table(pdev, index, tag);
+		break;
+	default:
+		err = -EINVAL;
+	}
+
+	if (err) {
+		pcie_disable_tph(pdev);
+		return err;
+	}
+
+	set_ctrl_reg_req_en(pdev, pdev->tph_mode);
+
+	pci_dbg(pdev, "set steering tag: %s table, index=%d, tag=%#04x\n",
+		(loc == PCI_TPH_LOC_MSIX) ? "MSI-X" : "ST", index, tag);
+
+	return 0;
+}
+EXPORT_SYMBOL(pcie_tph_set_st_entry);
+
 /**
  * pcie_disable_tph - Turn off TPH support for device
  * @pdev: PCI device
@@ -140,6 +466,8 @@ EXPORT_SYMBOL(pcie_enable_tph);
 void pci_restore_tph_state(struct pci_dev *pdev)
 {
 	struct pci_cap_saved_state *save_state;
+	int num_entries, i, offset;
+	u16 *st_entry;
 	u32 *cap;
 
 	if (!pdev->tph_cap)
@@ -155,11 +483,21 @@ void pci_restore_tph_state(struct pci_dev *pdev)
 	/* Restore control register and all ST entries */
 	cap = &save_state->cap.data[0];
 	pci_write_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, *cap++);
+	st_entry = (u16 *)cap;
+	offset = PCI_TPH_BASE_SIZEOF;
+	num_entries = get_st_table_size(pdev);
+	for (i = 0; i < num_entries; i++) {
+		pci_write_config_word(pdev, pdev->tph_cap + offset,
+				      *st_entry++);
+		offset += sizeof(u16);
+	}
 }
 
 void pci_save_tph_state(struct pci_dev *pdev)
 {
 	struct pci_cap_saved_state *save_state;
+	int num_entries, i, offset;
+	u16 *st_entry;
 	u32 *cap;
 
 	if (!pdev->tph_cap)
@@ -175,6 +513,16 @@ void pci_save_tph_state(struct pci_dev *pdev)
 	/* Save control register */
 	cap = &save_state->cap.data[0];
 	pci_read_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, cap++);
+
+	/* Save all ST entries in extended capability structure */
+	st_entry = (u16 *)cap;
+	offset = PCI_TPH_BASE_SIZEOF;
+	num_entries = get_st_table_size(pdev);
+	for (i = 0; i < num_entries; i++) {
+		pci_read_config_word(pdev, pdev->tph_cap + offset,
+				     st_entry++);
+		offset += sizeof(u16);
+	}
 }
 
 void pci_no_tph(void)
@@ -186,12 +534,14 @@ void pci_no_tph(void)
 
 void pci_tph_init(struct pci_dev *pdev)
 {
+	int num_entries;
 	u32 save_size;
 
 	pdev->tph_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_TPH);
 	if (!pdev->tph_cap)
 		return;
 
-	save_size = sizeof(u32);
+	num_entries = get_st_table_size(pdev);
+	save_size = sizeof(u32) + num_entries * sizeof(u16);
 	pci_add_ext_cap_save_buffer(pdev, PCI_EXT_CAP_ID_TPH, save_size);
 }
diff --git a/include/linux/pci-tph.h b/include/linux/pci-tph.h
index 58654a334ffba..c3e806c13d646 100644
--- a/include/linux/pci-tph.h
+++ b/include/linux/pci-tph.h
@@ -9,10 +9,33 @@
 #ifndef LINUX_PCI_TPH_H
 #define LINUX_PCI_TPH_H
 
+/*
+ * According to the ECN for PCI Firmware Spec, Steering Tag can be different
+ * depending on the memory type: Volatile Memory or Persistent Memory. When a
+ * caller query about a target's Steering Tag, it must provide the target's
+ * tph_mem_type. ECN link: https://members.pcisig.com/wg/PCI-SIG/document/15470.
+ */
+enum tph_mem_type {
+	TPH_MEM_TYPE_VM,	/* volatile memory */
+	TPH_MEM_TYPE_PM		/* persistent memory */
+};
+
 #ifdef CONFIG_PCIE_TPH
+int pcie_tph_set_st_entry(struct pci_dev *pdev,
+			  unsigned int index, u16 tag);
+int pcie_tph_get_cpu_st(struct pci_dev *dev,
+			enum tph_mem_type mem_type,
+			unsigned int cpu_uid, u16 *tag);
 void pcie_disable_tph(struct pci_dev *pdev);
 int pcie_enable_tph(struct pci_dev *pdev, int mode);
 #else
+static inline int pcie_tph_set_st_entry(struct pci_dev *pdev,
+					unsigned int index, u16 tag)
+{ return -EINVAL; }
+static inline int pcie_tph_get_cpu_st(struct pci_dev *dev,
+				      enum tph_mem_type mem_type,
+				      unsigned int cpu_uid, u16 *tag)
+{ return -EINVAL; }
 static inline void pcie_disable_tph(struct pci_dev *pdev) { }
 static inline int pcie_enable_tph(struct pci_dev *pdev, int mode)
 { return -EINVAL; }

From 2985b1844f3f3447f2d938eff1ef6762592065a5 Mon Sep 17 00:00:00 2001
From: Todd Kjos <tkjos@google.com>
Date: Tue, 1 Oct 2024 23:11:47 +0000
Subject: [PATCH 0083/1530] PCI: Fix reset_method_store() memory leak

In reset_method_store(), a string is allocated via kstrndup() and assigned
to the local "options". options is then used in with strsep() to find
spaces:

  while ((name = strsep(&options, " ")) != NULL) {

If there are no remaining spaces, then options is set to NULL by strsep(),
so the subsequent kfree(options) doesn't free the memory allocated via
kstrndup().

Fix by using a separate tmp_options to iterate with strsep() so options is
preserved.

Link: https://lore.kernel.org/r/20241001231147.3583649-1-tkjos@google.com
Fixes: d88f521da3ef ("PCI: Allow userspace to query and set device reset mechanism")
Signed-off-by: Todd Kjos <tkjos@google.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 7d85c04fbba2a..0e6562ff3dcf8 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -5244,7 +5244,7 @@ static ssize_t reset_method_store(struct device *dev,
 				  const char *buf, size_t count)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	char *options, *name;
+	char *options, *tmp_options, *name;
 	int m, n;
 	u8 reset_methods[PCI_NUM_RESET_METHODS] = { 0 };
 
@@ -5264,7 +5264,8 @@ static ssize_t reset_method_store(struct device *dev,
 		return -ENOMEM;
 
 	n = 0;
-	while ((name = strsep(&options, " ")) != NULL) {
+	tmp_options = options;
+	while ((name = strsep(&tmp_options, " ")) != NULL) {
 		if (sysfs_streq(name, ""))
 			continue;
 

From 8d7f85e323ea402005fa83ddbdf5d00292d77098 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Mon, 30 Sep 2024 19:14:31 -0700
Subject: [PATCH 0084/1530] perf jevents: Don't stop at the first matched pmu
 when searching a events table

The "perf all PMU test" fails on a Coffee Lake machine.

The failure is caused by the below change in the commit e2641db83f18
("perf vendor events: Add/update skylake events/metrics").

+    {
+        "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles",
+        "Counter": "FIXED",
+        "EventCode": "0xff",
+        "EventName": "UNC_CLOCK.SOCKET",
+        "PerPkg": "1",
+        "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+        "Unit": "cbox_0"
     }

The other cbox events have the unit name "CBOX", while the fixed counter
has a unit name "cbox_0". So the events_table will maintain separate
entries for cbox and cbox_0.

The perf_pmus__print_pmu_events() calculates the total number of events,
allocate an aliases buffer, store all the events into the buffer, sort,
and print all the aliases one by one.

The problem is that the calculated total number of events doesn't match
the stored events in the aliases buffer.

The perf_pmu__num_events() is used to calculate the number of events. It
invokes the pmu_events_table__num_events() to go through the entire
events_table to find all events. Because of the
pmu_uncore_alias_match(), the suffix of uncore PMU will be ignored. So
the events for cbox and cbox_0 are all counted.

When storing events into the aliases buffer, the
perf_pmu__for_each_event() only process the events for cbox.

Since a bigger buffer was allocated, the last entry are all 0.
When printing all the aliases, null will be outputted, and trigger the
failure.

The mismatch was introduced from the commit e3edd6cf6399 ("perf
pmu-events: Reduce processed events by passing PMU"). The
pmu_events_table__for_each_event() stops immediately once a pmu is set.
But for uncore, especially this case, the method is wrong and mismatch
what perf does in the perf_pmu__num_events().

With the patch,
$ perf list pmu | grep -A 1 clock.socket
   unc_clock.socket
        [This 48-bit fixed counter counts the UCLK cycles. Unit: uncore_cbox_0
$ perf test "perf all PMU test"
  107: perf all PMU test                                               : Ok

Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/all/202407101021.2c8baddb-oliver.sang@intel.com/
Fixes: e3edd6cf6399 ("perf pmu-events: Reduce processed events by passing PMU")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20241001021431.814811-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/pmu-events/empty-pmu-events.c | 2 +-
 tools/perf/pmu-events/jevents.py         | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index c592079982fbd..873e9fb2041f0 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -380,7 +380,7 @@ int pmu_events_table__for_each_event(const struct pmu_events_table *table,
                         continue;
 
                 ret = pmu_events_table__for_each_event_pmu(table, table_pmu, fn, data);
-                if (pmu || ret)
+                if (ret)
                         return ret;
         }
         return 0;
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index bb0a5d92df4a1..d46a22fb5573d 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -930,7 +930,7 @@ def print_system_mapping_table() -> None:
                         continue;
 
                 ret = pmu_events_table__for_each_event_pmu(table, table_pmu, fn, data);
-                if (pmu || ret)
+                if (ret)
                         return ret;
         }
         return 0;

From 7f6ccb70e465bd8c9cf8973aee1c01224e4bdb3c Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 30 Sep 2024 22:23:24 -0700
Subject: [PATCH 0085/1530] perf stat: Fix affinity memory leaks on error path

Missed cleanup when an error occurs.

Fixes: 49de179577e7 ("perf stat: No need to setup affinities when starting a workload")
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20241001052327.7052-2-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-stat.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1521b6df26065..3e6b9f216e802 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -827,6 +827,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		}
 	}
 	affinity__cleanup(affinity);
+	affinity = NULL;
 
 	evlist__for_each_entry(evsel_list, counter) {
 		if (!counter->supported) {
@@ -965,6 +966,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	if (forks)
 		evlist__cancel_workload(evsel_list);
 
+	affinity__cleanup(affinity);
 	return err;
 }
 

From 1334ee91694c21777d2df1da20bc5d5a7022a1e5 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 30 Sep 2024 22:23:25 -0700
Subject: [PATCH 0086/1530] perf test: Fix memory leaks on event-times error
 paths

These error paths occur without sufficient permissions. Fix the memory
leaks to make leak sanitizer happier.

Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20241001052327.7052-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/event-times.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index e155f0e0e04d5..deefe5003bfc2 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -126,6 +126,7 @@ static int attach__cpu_disabled(struct evlist *evlist)
 	evsel->core.attr.disabled = 1;
 
 	err = evsel__open_per_cpu(evsel, cpus, -1);
+	perf_cpu_map__put(cpus);
 	if (err) {
 		if (err == -EACCES)
 			return TEST_SKIP;
@@ -134,7 +135,6 @@ static int attach__cpu_disabled(struct evlist *evlist)
 		return err;
 	}
 
-	perf_cpu_map__put(cpus);
 	return evsel__enable(evsel);
 }
 
@@ -153,10 +153,10 @@ static int attach__cpu_enabled(struct evlist *evlist)
 	}
 
 	err = evsel__open_per_cpu(evsel, cpus, -1);
+	perf_cpu_map__put(cpus);
 	if (err == -EACCES)
 		return TEST_SKIP;
 
-	perf_cpu_map__put(cpus);
 	return err ? TEST_FAIL : TEST_OK;
 }
 
@@ -188,6 +188,7 @@ static int test_times(int (attach)(struct evlist *),
 	err = attach(evlist);
 	if (err == TEST_SKIP) {
 		pr_debug("  SKIP  : not enough rights\n");
+		evlist__delete(evlist);
 		return err;
 	}
 

From 7457bcfcfb988a5600dca2433bbc4901ba49d123 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 30 Sep 2024 22:23:26 -0700
Subject: [PATCH 0087/1530] perf test: Skip not fail tp fields test when
 insufficient permissions

Clean up return value to be TEST_* rather than unspecific integer. Add
test case skip reason. Skip test if EACCES comes back from
evsel__newtp.

Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20241001052327.7052-4-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/evsel-tp-sched.c | 40 +++++++++++++++++++------------
 1 file changed, 25 insertions(+), 15 deletions(-)

diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index cf4da3d748c29..3da6a76eac385 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -36,33 +36,33 @@ static int test__perf_evsel__tp_sched_test(struct test_suite *test __maybe_unuse
 					   int subtest __maybe_unused)
 {
 	struct evsel *evsel = evsel__newtp("sched", "sched_switch");
-	int ret = 0;
+	int ret = TEST_OK;
 
 	if (IS_ERR(evsel)) {
 		pr_debug("evsel__newtp failed with %ld\n", PTR_ERR(evsel));
-		return -1;
+		return PTR_ERR(evsel) == -EACCES ? TEST_SKIP : TEST_FAIL;
 	}
 
 	if (evsel__test_field(evsel, "prev_comm", 16, false))
-		ret = -1;
+		ret = TEST_FAIL;
 
 	if (evsel__test_field(evsel, "prev_pid", 4, true))
-		ret = -1;
+		ret = TEST_FAIL;
 
 	if (evsel__test_field(evsel, "prev_prio", 4, true))
-		ret = -1;
+		ret = TEST_FAIL;
 
 	if (evsel__test_field(evsel, "prev_state", sizeof(long), true))
-		ret = -1;
+		ret = TEST_FAIL;
 
 	if (evsel__test_field(evsel, "next_comm", 16, false))
-		ret = -1;
+		ret = TEST_FAIL;
 
 	if (evsel__test_field(evsel, "next_pid", 4, true))
-		ret = -1;
+		ret = TEST_FAIL;
 
 	if (evsel__test_field(evsel, "next_prio", 4, true))
-		ret = -1;
+		ret = TEST_FAIL;
 
 	evsel__delete(evsel);
 
@@ -70,23 +70,33 @@ static int test__perf_evsel__tp_sched_test(struct test_suite *test __maybe_unuse
 
 	if (IS_ERR(evsel)) {
 		pr_debug("evsel__newtp failed with %ld\n", PTR_ERR(evsel));
-		return -1;
+		return TEST_FAIL;
 	}
 
 	if (evsel__test_field(evsel, "comm", 16, false))
-		ret = -1;
+		ret = TEST_FAIL;
 
 	if (evsel__test_field(evsel, "pid", 4, true))
-		ret = -1;
+		ret = TEST_FAIL;
 
 	if (evsel__test_field(evsel, "prio", 4, true))
-		ret = -1;
+		ret = TEST_FAIL;
 
 	if (evsel__test_field(evsel, "target_cpu", 4, true))
-		ret = -1;
+		ret = TEST_FAIL;
 
 	evsel__delete(evsel);
 	return ret;
 }
 
-DEFINE_SUITE("Parse sched tracepoints fields", perf_evsel__tp_sched_test);
+static struct test_case tests__perf_evsel__tp_sched_test[] = {
+	TEST_CASE_REASON("Parse sched tracepoints fields",
+			 perf_evsel__tp_sched_test,
+			 "permissions"),
+	{	.name = NULL, }
+};
+
+struct test_suite suite__perf_evsel__tp_sched_test = {
+	.desc = "Parse sched tracepoints fields",
+	.test_cases = tests__perf_evsel__tp_sched_test,
+};

From ad321b19d2bb6ed0380ad53a06972ea7f4e7d7b1 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 30 Sep 2024 22:23:27 -0700
Subject: [PATCH 0088/1530] perf test: Skip not fail syscall tp fields test
 when insufficient permissions

Clean up return value to be TEST_* rather than unspecific integer. Add
test case skip reason. Skip test if EACCES comes back from
evsel__newtp.

Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20241001052327.7052-5-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/openat-syscall-tp-fields.c | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 888df8eca9812..3943da441979c 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -40,7 +40,7 @@ static int test__syscall_openat_tp_fields(struct test_suite *test __maybe_unused
 	int flags = O_RDONLY | O_DIRECTORY;
 	struct evlist *evlist = evlist__new();
 	struct evsel *evsel;
-	int err = -1, i, nr_events = 0, nr_polls = 0;
+	int ret = TEST_FAIL, err, i, nr_events = 0, nr_polls = 0;
 	char sbuf[STRERR_BUFSIZE];
 
 	if (evlist == NULL) {
@@ -51,6 +51,7 @@ static int test__syscall_openat_tp_fields(struct test_suite *test __maybe_unused
 	evsel = evsel__newtp("syscalls", "sys_enter_openat");
 	if (IS_ERR(evsel)) {
 		pr_debug("%s: evsel__newtp\n", __func__);
+		ret = PTR_ERR(evsel) == -EACCES ? TEST_SKIP : TEST_FAIL;
 		goto out_delete_evlist;
 	}
 
@@ -138,11 +139,21 @@ static int test__syscall_openat_tp_fields(struct test_suite *test __maybe_unused
 		}
 	}
 out_ok:
-	err = 0;
+	ret = TEST_OK;
 out_delete_evlist:
 	evlist__delete(evlist);
 out:
-	return err;
+	return ret;
 }
 
-DEFINE_SUITE("syscalls:sys_enter_openat event fields", syscall_openat_tp_fields);
+static struct test_case tests__syscall_openat_tp_fields[] = {
+	TEST_CASE_REASON("syscalls:sys_enter_openat event fields",
+			 syscall_openat_tp_fields,
+			 "permissions"),
+	{	.name = NULL, }
+};
+
+struct test_suite suite__syscall_openat_tp_fields = {
+	.desc = "syscalls:sys_enter_openat event fields",
+	.test_cases = tests__syscall_openat_tp_fields,
+};

From 80c281fca252827facd05875b8d9d36d7aad0f8d Mon Sep 17 00:00:00 2001
From: Ben Gainey <ben.gainey@arm.com>
Date: Tue, 1 Oct 2024 13:15:04 +0100
Subject: [PATCH 0089/1530] tools/perf: Correctly calculate sample period for
 inherited SAMPLE_READ values

Sample period calculation in deliver_sample_value is updated to
calculate the per-thread period delta for events that are inherit +
PERF_SAMPLE_READ. When the sampling event has this configuration, the
read_format.id is used with the tid from the sample to lookup the
storage of the previously accumulated counter total before calculating
the delta. All existing valid configurations where read_format.value
represents some global value continue to use just the read_format.id to
locate the storage of the previously accumulated total.

perf_sample_id is modified to support tracking per-thread
values, along with the existing global per-id values. In the
per-thread case, values are stored in a hash by tid within the
perf_sample_id, and are dynamically allocated as the number is not known
ahead of time.

Signed-off-by: Ben Gainey <ben.gainey@arm.com>
Cc: james.clark@arm.com
Link: https://lore.kernel.org/r/20241001121505.1009685-2-ben.gainey@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/lib/perf/evsel.c                  | 48 +++++++++++++++++++
 tools/lib/perf/include/internal/evsel.h | 63 ++++++++++++++++++++++++-
 tools/perf/util/session.c               | 28 +++++++----
 3 files changed, 128 insertions(+), 11 deletions(-)

diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index c07160953224a..c475319e2e410 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -5,6 +5,7 @@
 #include <perf/evsel.h>
 #include <perf/cpumap.h>
 #include <perf/threadmap.h>
+#include <linux/hash.h>
 #include <linux/list.h>
 #include <internal/evsel.h>
 #include <linux/zalloc.h>
@@ -23,6 +24,7 @@ void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr,
 		      int idx)
 {
 	INIT_LIST_HEAD(&evsel->node);
+	INIT_LIST_HEAD(&evsel->per_stream_periods);
 	evsel->attr = *attr;
 	evsel->idx  = idx;
 	evsel->leader = evsel;
@@ -531,10 +533,56 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 
 void perf_evsel__free_id(struct perf_evsel *evsel)
 {
+	struct perf_sample_id_period *pos, *n;
+
 	xyarray__delete(evsel->sample_id);
 	evsel->sample_id = NULL;
 	zfree(&evsel->id);
 	evsel->ids = 0;
+
+	perf_evsel_for_each_per_thread_period_safe(evsel, n, pos) {
+		list_del_init(&pos->node);
+		free(pos);
+	}
+}
+
+bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel)
+{
+	return (evsel->attr.sample_type & PERF_SAMPLE_READ) &&
+		(evsel->attr.sample_type & PERF_SAMPLE_TID) &&
+		evsel->attr.inherit;
+}
+
+u64 *perf_sample_id__get_period_storage(struct perf_sample_id *sid, u32 tid, bool per_thread)
+{
+	struct hlist_head *head;
+	struct perf_sample_id_period *res;
+	int hash;
+
+	if (!per_thread)
+		return &sid->period;
+
+	hash = hash_32(tid, PERF_SAMPLE_ID__HLIST_BITS);
+	head = &sid->periods[hash];
+
+	hlist_for_each_entry(res, head, hnode)
+		if (res->tid == tid)
+			return &res->period;
+
+	if (sid->evsel == NULL)
+		return NULL;
+
+	res = zalloc(sizeof(struct perf_sample_id_period));
+	if (res == NULL)
+		return NULL;
+
+	INIT_LIST_HEAD(&res->node);
+	res->tid = tid;
+
+	list_add_tail(&res->node, &sid->evsel->per_stream_periods);
+	hlist_add_head(&res->hnode, &sid->periods[hash]);
+
+	return &res->period;
 }
 
 void perf_counts_values__scale(struct perf_counts_values *count,
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index 5cd220a61962e..ea78defa77d0b 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -11,6 +11,32 @@
 struct perf_thread_map;
 struct xyarray;
 
+/**
+ * The per-thread accumulated period storage node.
+ */
+struct perf_sample_id_period {
+	struct list_head	node;
+	struct hlist_node	hnode;
+	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
+	u64			period;
+	/* The TID that the values belongs to */
+	u32			tid;
+};
+
+/**
+ * perf_evsel_for_each_per_thread_period_safe - safely iterate thru all the
+ * per_stream_periods
+ * @evlist:perf_evsel instance to iterate
+ * @item: struct perf_sample_id_period iterator
+ * @tmp: struct perf_sample_id_period temp iterator
+ */
+#define perf_evsel_for_each_per_thread_period_safe(evsel, tmp, item) \
+	list_for_each_entry_safe(item, tmp, &(evsel)->per_stream_periods, node)
+
+
+#define PERF_SAMPLE_ID__HLIST_BITS 4
+#define PERF_SAMPLE_ID__HLIST_SIZE (1 << PERF_SAMPLE_ID__HLIST_BITS)
+
 /*
  * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
  * more than one entry in the evlist.
@@ -34,8 +60,32 @@ struct perf_sample_id {
 	pid_t			 machine_pid;
 	struct perf_cpu		 vcpu;
 
-	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
-	u64			 period;
+	/*
+	 * Per-thread, and global event counts are mutually exclusive:
+	 * Whilst it is possible to combine events into a group with differing
+	 * values of PERF_SAMPLE_READ, it is not valid to have inconsistent
+	 * values for `inherit`. Therefore it is not possible to have a
+	 * situation where a per-thread event is sampled as a global event;
+	 * all !inherit groups are global, and all groups where the sampling
+	 * event is inherit + PERF_SAMPLE_READ will be per-thread. Any event
+	 * that is part of such a group that is inherit but not PERF_SAMPLE_READ
+	 * will be read as per-thread. If such an event can also trigger a
+	 * sample (such as with sample_period > 0) then it will not cause
+	 * `read_format` to be included in its PERF_RECORD_SAMPLE, and
+	 * therefore will not expose the per-thread group members as global.
+	 */
+	union {
+		/*
+		 * Holds total ID period value for PERF_SAMPLE_READ processing
+		 * (when period is not per-thread).
+		 */
+		u64			period;
+		/*
+		 * Holds total ID period value for PERF_SAMPLE_READ processing
+		 * (when period is per-thread).
+		 */
+		struct hlist_head	periods[PERF_SAMPLE_ID__HLIST_SIZE];
+	};
 };
 
 struct perf_evsel {
@@ -58,6 +108,10 @@ struct perf_evsel {
 	u32			 ids;
 	struct perf_evsel	*leader;
 
+	/* For events where the read_format value is per-thread rather than
+	 * global, stores the per-thread cumulative period */
+	struct list_head	per_stream_periods;
+
 	/* parse modifier helper */
 	int			 nr_members;
 	/*
@@ -88,4 +142,9 @@ int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
 void perf_evsel__free_id(struct perf_evsel *evsel);
 
+bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel);
+
+u64 *perf_sample_id__get_period_storage(struct perf_sample_id *sid, u32 tid,
+					bool per_thread);
+
 #endif /* __LIBPERF_INTERNAL_EVSEL_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index dbaf07bf6c5fb..507e6cba95458 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1171,18 +1171,24 @@ static int deliver_sample_value(struct evlist *evlist,
 				union perf_event *event,
 				struct perf_sample *sample,
 				struct sample_read_value *v,
-				struct machine *machine)
+				struct machine *machine,
+				bool per_thread)
 {
 	struct perf_sample_id *sid = evlist__id2sid(evlist, v->id);
 	struct evsel *evsel;
+	u64 *storage = NULL;
 
 	if (sid) {
+		storage = perf_sample_id__get_period_storage(sid, sample->tid, per_thread);
+	}
+
+	if (storage) {
 		sample->id     = v->id;
-		sample->period = v->value - sid->period;
-		sid->period    = v->value;
+		sample->period = v->value - *storage;
+		*storage       = v->value;
 	}
 
-	if (!sid || sid->evsel == NULL) {
+	if (!storage || sid->evsel == NULL) {
 		++evlist->stats.nr_unknown_id;
 		return 0;
 	}
@@ -1203,17 +1209,19 @@ static int deliver_sample_group(struct evlist *evlist,
 				union  perf_event *event,
 				struct perf_sample *sample,
 				struct machine *machine,
-				u64 read_format)
+				u64 read_format,
+				bool per_thread)
 {
 	int ret = -EINVAL;
 	struct sample_read_value *v = sample->read.group.values;
 
 	if (tool->dont_split_sample_group)
-		return deliver_sample_value(evlist, tool, event, sample, v, machine);
+		return deliver_sample_value(evlist, tool, event, sample, v, machine,
+					    per_thread);
 
 	sample_read_group__for_each(v, sample->read.group.nr, read_format) {
 		ret = deliver_sample_value(evlist, tool, event, sample, v,
-					   machine);
+					   machine, per_thread);
 		if (ret)
 			break;
 	}
@@ -1228,6 +1236,7 @@ static int evlist__deliver_sample(struct evlist *evlist, const struct perf_tool
 	/* We know evsel != NULL. */
 	u64 sample_type = evsel->core.attr.sample_type;
 	u64 read_format = evsel->core.attr.read_format;
+	bool per_thread = perf_evsel__attr_has_per_thread_sample_period(&evsel->core);
 
 	/* Standard sample delivery. */
 	if (!(sample_type & PERF_SAMPLE_READ))
@@ -1236,10 +1245,11 @@ static int evlist__deliver_sample(struct evlist *evlist, const struct perf_tool
 	/* For PERF_SAMPLE_READ we have either single or group mode. */
 	if (read_format & PERF_FORMAT_GROUP)
 		return deliver_sample_group(evlist, tool, event, sample,
-					    machine, read_format);
+					    machine, read_format, per_thread);
 	else
 		return deliver_sample_value(evlist, tool, event, sample,
-					    &sample->read.one, machine);
+					    &sample->read.one, machine,
+					    per_thread);
 }
 
 static int machines__deliver_event(struct machines *machines,

From 90035d3cd876cb71f98868d44ee60f5c5aa5ad69 Mon Sep 17 00:00:00 2001
From: Ben Gainey <ben.gainey@arm.com>
Date: Tue, 1 Oct 2024 13:15:05 +0100
Subject: [PATCH 0090/1530] tools/perf: Allow inherit + PERF_SAMPLE_READ when
 opening events

The "perf record" tool will now default to this new mode if the user
specifies a sampling group when not in system-wide mode, and when
"--no-inherit" is not specified.

This change updates evsel to allow the combination of inherit
and PERF_SAMPLE_READ.

A fallback is implemented for kernel versions where this feature is not
supported.

Signed-off-by: Ben Gainey <ben.gainey@arm.com>
Cc: james.clark@arm.com
Link: https://lore.kernel.org/r/20241001121505.1009685-3-ben.gainey@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/attr/README                  |  2 +
 tools/perf/tests/attr/test-record-C0          |  2 +
 tools/perf/tests/attr/test-record-dummy-C0    |  2 +-
 .../tests/attr/test-record-group-sampling     |  3 +-
 .../tests/attr/test-record-group-sampling1    | 50 +++++++++++++++
 .../tests/attr/test-record-group-sampling2    | 61 +++++++++++++++++++
 tools/perf/tests/attr/test-record-group2      |  1 +
 tools/perf/tests/attr/test-record-group3      | 31 ++++++++++
 tools/perf/util/evsel.c                       | 21 ++++++-
 tools/perf/util/evsel.h                       |  1 +
 10 files changed, 169 insertions(+), 5 deletions(-)
 create mode 100644 tools/perf/tests/attr/test-record-group-sampling1
 create mode 100644 tools/perf/tests/attr/test-record-group-sampling2
 create mode 100644 tools/perf/tests/attr/test-record-group3

diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
index 4066fec7180a8..67c4ca76b85d5 100644
--- a/tools/perf/tests/attr/README
+++ b/tools/perf/tests/attr/README
@@ -51,6 +51,8 @@ Following tests are defined (with perf commands):
   perf record --call-graph fp kill              (test-record-graph-fp-aarch64)
   perf record -e '{cycles,instructions}' kill   (test-record-group1)
   perf record -e '{cycles/period=1/,instructions/period=2/}:S' kill (test-record-group2)
+  perf record -e '{cycles,cache-misses}:S' kill (test-record-group-sampling1)
+  perf record -c 10000 -e '{cycles,cache-misses}:S' kill (test-record-group-sampling2)
   perf record -D kill                           (test-record-no-delay)
   perf record -i kill                           (test-record-no-inherit)
   perf record -n kill                           (test-record-no-samples)
diff --git a/tools/perf/tests/attr/test-record-C0 b/tools/perf/tests/attr/test-record-C0
index 198e8429a1bf8..1049ac8b52f27 100644
--- a/tools/perf/tests/attr/test-record-C0
+++ b/tools/perf/tests/attr/test-record-C0
@@ -18,5 +18,7 @@ sample_type=65927
 mmap=0
 comm=0
 task=0
+inherit=0
 
 [event:system-wide-dummy]
+inherit=0
diff --git a/tools/perf/tests/attr/test-record-dummy-C0 b/tools/perf/tests/attr/test-record-dummy-C0
index 576ec48b3aafa..3050298bd6140 100644
--- a/tools/perf/tests/attr/test-record-dummy-C0
+++ b/tools/perf/tests/attr/test-record-dummy-C0
@@ -19,7 +19,7 @@ sample_period=4000
 sample_type=391
 read_format=4|20
 disabled=0
-inherit=1
+inherit=0
 pinned=0
 exclusive=0
 exclude_user=0
diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
index 97e7e64a38f07..86a940d7895d7 100644
--- a/tools/perf/tests/attr/test-record-group-sampling
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -2,6 +2,7 @@
 command = record
 args    = --no-bpf-event -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
 ret     = 1
+kernel_until = 6.12
 
 [event-1:base-record]
 fd=1
@@ -18,7 +19,7 @@ group_fd=1
 type=0
 config=3
 
-# default | PERF_SAMPLE_READ
+# default | PERF_SAMPLE_READ | PERF_SAMPLE_PERIOD
 sample_type=343
 
 # PERF_FORMAT_ID | PERF_FORMAT_GROUP  | PERF_FORMAT_LOST
diff --git a/tools/perf/tests/attr/test-record-group-sampling1 b/tools/perf/tests/attr/test-record-group-sampling1
new file mode 100644
index 0000000000000..4748ab7bf6843
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group-sampling1
@@ -0,0 +1,50 @@
+[config]
+command = record
+args    = --no-bpf-event -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+ret     = 1
+kernel_since = 6.12
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+
+# cycles
+type=0
+config=0
+
+# default | PERF_SAMPLE_READ | PERF_SAMPLE_PERIOD
+sample_type=343
+
+# PERF_FORMAT_ID | PERF_FORMAT_GROUP  | PERF_FORMAT_LOST | PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING
+read_format=28|31
+task=1
+mmap=1
+comm=1
+enable_on_exec=1
+disabled=1
+
+# inherit is enabled for group sampling
+inherit=1
+
+[event-2:base-record]
+fd=2
+group_fd=1
+
+# cache-misses
+type=0
+config=3
+
+# default | PERF_SAMPLE_READ | PERF_SAMPLE_PERIOD
+sample_type=343
+
+# PERF_FORMAT_ID | PERF_FORMAT_GROUP  | PERF_FORMAT_LOST | PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING
+read_format=28|31
+task=0
+mmap=0
+comm=0
+enable_on_exec=0
+disabled=0
+freq=0
+
+# inherit is enabled for group sampling
+inherit=1
diff --git a/tools/perf/tests/attr/test-record-group-sampling2 b/tools/perf/tests/attr/test-record-group-sampling2
new file mode 100644
index 0000000000000..e0432244a0eb7
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group-sampling2
@@ -0,0 +1,61 @@
+[config]
+command = record
+args    = --no-bpf-event -c 10000 -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+ret     = 1
+kernel_since = 6.12
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+
+# cycles
+type=0
+config=0
+
+# default | PERF_SAMPLE_READ
+sample_type=87
+
+# PERF_FORMAT_ID | PERF_FORMAT_GROUP  | PERF_FORMAT_LOST | PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING
+read_format=28|31
+task=1
+mmap=1
+comm=1
+enable_on_exec=1
+disabled=1
+
+# inherit is enabled for group sampling
+inherit=1
+
+# sampling disabled
+sample_freq=0
+sample_period=10000
+freq=0
+write_backward=0
+
+[event-2:base-record]
+fd=2
+group_fd=1
+
+# cache-misses
+type=0
+config=3
+
+# default | PERF_SAMPLE_READ
+sample_type=87
+
+# PERF_FORMAT_ID | PERF_FORMAT_GROUP  | PERF_FORMAT_LOST | PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING
+read_format=28|31
+task=0
+mmap=0
+comm=0
+enable_on_exec=0
+disabled=0
+
+# inherit is enabled for group sampling
+inherit=1
+
+# sampling disabled
+sample_freq=0
+sample_period=0
+freq=0
+write_backward=0
diff --git a/tools/perf/tests/attr/test-record-group2 b/tools/perf/tests/attr/test-record-group2
index cebdaa8e64e47..891d41a7bddf7 100644
--- a/tools/perf/tests/attr/test-record-group2
+++ b/tools/perf/tests/attr/test-record-group2
@@ -2,6 +2,7 @@
 command = record
 args    = --no-bpf-event -e '{cycles/period=1234000/,instructions/period=6789000/}:S' kill >/dev/null 2>&1
 ret     = 1
+kernel_until = 6.12
 
 [event-1:base-record]
 fd=1
diff --git a/tools/perf/tests/attr/test-record-group3 b/tools/perf/tests/attr/test-record-group3
new file mode 100644
index 0000000000000..249be884959ea
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group3
@@ -0,0 +1,31 @@
+[config]
+command = record
+args    = --no-bpf-event -e '{cycles/period=1234000/,instructions/period=6789000/}:S' kill >/dev/null 2>&1
+ret     = 1
+kernel_since = 6.12
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+config=0|1
+sample_period=1234000
+sample_type=87
+read_format=28|31
+disabled=1
+inherit=1
+freq=0
+
+[event-2:base-record]
+fd=2
+group_fd=1
+config=0|1
+sample_period=6789000
+sample_type=87
+read_format=28|31
+disabled=0
+inherit=1
+mmap=0
+comm=0
+freq=0
+enable_on_exec=0
+task=0
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index da0bada62140d..b221459439b88 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1148,7 +1148,7 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 	bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
 
 	attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
-	attr->inherit	    = !opts->no_inherit;
+	attr->inherit	    = target__has_cpu(&opts->target) ? 0 : !opts->no_inherit;
 	attr->write_backward = opts->overwrite ? 1 : 0;
 	attr->read_format   = PERF_FORMAT_LOST;
 
@@ -1170,7 +1170,15 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 		 */
 		if (leader->core.nr_members > 1) {
 			attr->read_format |= PERF_FORMAT_GROUP;
-			attr->inherit = 0;
+		}
+
+		/*
+		 * Inherit + SAMPLE_READ requires SAMPLE_TID in the read_format
+		 */
+		if (attr->inherit) {
+			evsel__set_sample_bit(evsel, TID);
+			evsel->core.attr.read_format |=
+				PERF_FORMAT_ID;
 		}
 	}
 
@@ -2104,6 +2112,8 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 
 static void evsel__disable_missing_features(struct evsel *evsel)
 {
+	if (perf_missing_features.inherit_sample_read)
+		evsel->core.attr.inherit = 0;
 	if (perf_missing_features.branch_counters)
 		evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_COUNTERS;
 	if (perf_missing_features.read_lost)
@@ -2159,7 +2169,12 @@ bool evsel__detect_missing_features(struct evsel *evsel)
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.branch_counters &&
+	if (!perf_missing_features.inherit_sample_read &&
+	    evsel->core.attr.inherit && (evsel->core.attr.sample_type & PERF_SAMPLE_READ)) {
+		perf_missing_features.inherit_sample_read = true;
+		pr_debug2("Using PERF_SAMPLE_READ / :S modifier is not compatible with inherit, falling back to no-inherit.\n");
+		return true;
+	} else if (!perf_missing_features.branch_counters &&
 	    (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS)) {
 		perf_missing_features.branch_counters = true;
 		pr_debug2("switching off branch counters support\n");
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 3e751ea769ac4..bd08d94d3f8ab 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -221,6 +221,7 @@ struct perf_missing_features {
 	bool weight_struct;
 	bool read_lost;
 	bool branch_counters;
+	bool inherit_sample_read;
 };
 
 extern struct perf_missing_features perf_missing_features;

From 5873de90315a13d211b1d50a1ba97f21a6f17516 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 1 Oct 2024 14:42:23 +0200
Subject: [PATCH 0091/1530] perf/test: perf test 86 fails on s390

Command perf test 86 fails on s390:
 # perf test -F 86
 ping 868299 [007] 28248.013596: probe_libc:inet_pton_1: (3ff95948020)
 3ff95948020 inet_pton+0x0 (inlined)
 3ff9595e6e7 text_to_binary_address+0x1007 (inlined)
 3ff9595e6e7 gaih_inet+0x1007 (inlined)
 FAIL: expected backtrace entry \
	 "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
	 got "3ff9595e6e7 gaih_inet+0x1007 (inlined)"
 86: probe libc's inet_pton & backtrace it with ping  : FAILED!
 #

The root cause is a new stack layout, two functions have been added
as seen below.

 # perf script | tac | grep -m1 '^ping' -B9 | tac
 ping  866856 [007] 25979.494921: probe_libc:inet_pton: (3ff8ec48020)
	     3ff8ec48020 inet_pton+0x0 (inlined)
 new -->     3ff8ec5e6e7 text_to_binary_address+0x1007 (inlined)
 new -->     3ff8ec5e6e7 gaih_inet+0x1007 (inlined)
	     3ff8ec5e6e7 getaddrinfo+0x1007 (/usr/lib64/libc.so.6)
	     2aa3fe04bf5 main+0xff5 (/usr/bin/ping)
	     3ff8eb34a5b __libc_start_call_main+0x8b (/usr/lib64/libc.so.6)
	     3ff8eb34b5d __libc_start_main@GLIBC_2.2+0xad (inlined)
	     2aa3fe06a1f [unknown] (/usr/bin/ping)

 #

The new functions in the call chain are:
 - text_to_binary_address()
 - gaih_inet().

Both functions are inlined and do not show up in the output
of the nm command:

  # nm -a /usr/lib64/libc.so.6 | \
	grep -E '(text_to_binary_address|gaih_inet)$'
  #

There is no possibility to add these 2 functions depending on their
existance in the C library.

Add text_to_binary_address() and gaih_inet() to the list of
expected functions in an compatible way and extend the regular
expression. On s390 the backtrace can now be

   Before                   After
   probe_libc:inet_pton     probe_libc:inet_pton
   inet_pton		    inet_pton
   getaddrinfo		    getaddrinfo | text_to_binary_address
   main			    main | gaih_inet

Output after:
 # perf test -F 86
 86: probe libc's inet_pton & backtrace it with ping  : Ok
 #

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Cc: agordeev@linux.ibm.com
Cc: gor@linux.ibm.com
Cc: hca@linux.ibm.com
Cc: sumanthk@linux.ibm.com
Link: https://lore.kernel.org/r/20241001124224.3370306-1-tmricht@linux.ibm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/record+probe_libc_inet_pton.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index f38c8ead0b03e..47a26f25db9fe 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -40,8 +40,8 @@ trace_libc_inet_pton_backtrace() {
 	case "$(uname -m)" in
 	s390x)
 		eventattr='call-graph=dwarf,max-stack=4'
-		echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
-		echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+		echo "((__GI_)?getaddrinfo|text_to_binary_address)\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "(gaih_inet|main)\+0x[[:xdigit:]]+[[:space:]]\(inlined|.*/bin/ping.*\)$" >> $expected
 		;;
 	ppc64|ppc64le)
 		eventattr='max-stack=4'

From d29d92df410e2fb523f640478b18f70c1823e55e Mon Sep 17 00:00:00 2001
From: Michael Petlan <mpetlan@redhat.com>
Date: Fri, 27 Sep 2024 17:19:26 +0200
Subject: [PATCH 0092/1530] perf trace: Keep exited threads for summary

Since 9ffa6c7512ca ("perf machine thread: Remove exited threads by
default") perf cleans exited threads up, but as said, sometimes they
are necessary to be kept. The mentioned commit does not cover all the
cases, we also need the information to construct the summary table in
perf-trace.

Before:
    # perf trace -s true

     Summary of events:

After:
    # perf trace -s -- true

     Summary of events:

     true (383382), 64 events, 91.4%

       syscall            calls  errors  total       min       avg       max       stddev
                                         (msec)    (msec)    (msec)    (msec)        (%)
       --------------- --------  ------ -------- --------- --------- ---------     ------
       mmap                   8      0     0.150     0.013     0.019     0.031     11.90%
       mprotect               3      0     0.045     0.014     0.015     0.017      6.47%
       openat                 2      0     0.014     0.006     0.007     0.007      9.73%
       munmap                 1      0     0.009     0.009     0.009     0.009      0.00%
       access                 1      1     0.009     0.009     0.009     0.009      0.00%
       pread64                4      0     0.006     0.001     0.001     0.002      4.53%
       fstat                  2      0     0.005     0.001     0.002     0.003     37.59%
       arch_prctl             2      1     0.003     0.001     0.002     0.002     25.91%
       read                   1      0     0.003     0.003     0.003     0.003      0.00%
       close                  2      0     0.003     0.001     0.001     0.001      3.86%
       brk                    1      0     0.002     0.002     0.002     0.002      0.00%
       rseq                   1      0     0.001     0.001     0.001     0.001      0.00%
       prlimit64              1      0     0.001     0.001     0.001     0.001      0.00%
       set_robust_list        1      0     0.001     0.001     0.001     0.001      0.00%
       set_tid_address        1      0     0.001     0.001     0.001     0.001      0.00%
       execve                 1      0     0.000     0.000     0.000     0.000      0.00%

[namhyung: simplified the condition]

Fixes: 9ffa6c7512ca ("perf machine thread: Remove exited threads by default")
Reported-by: Veronika Molnarova <vmolnaro@redhat.com>
Signed-off-by: Michael Petlan <mpetlan@redhat.com>
Link: https://lore.kernel.org/r/20240927151926.399474-1-mpetlan@redhat.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-trace.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f6e8475290739..0b30297b4ecb3 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -5449,6 +5449,10 @@ int cmd_trace(int argc, const char **argv)
 	if (trace.summary_only)
 		trace.summary = trace.summary_only;
 
+	/* Keep exited threads, otherwise information might be lost for summary */
+	if (trace.summary)
+		symbol_conf.keep_exited_threads = true;
+
 	if (output_name != NULL) {
 		err = trace__open_output(&trace, output_name);
 		if (err < 0) {

From ced20ea315fe8591093f19574ec32222c1ab71ba Mon Sep 17 00:00:00 2001
From: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Date: Tue, 24 Sep 2024 13:48:43 +0530
Subject: [PATCH 0093/1530] soundwire: amd: pass acp pci revision id as
 resource data

Pass ACP pci revision id as resource data and store it in amd SoundWire
manager private data structure. This field will be used to differentiate
ACP variants.

Signed-off-by: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Link: https://lore.kernel.org/r/20240924081846.1834612-2-Vijendar.Mukunda@amd.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/amd_init.c      | 1 +
 drivers/soundwire/amd_manager.c   | 1 +
 include/linux/soundwire/sdw_amd.h | 5 +++++
 3 files changed, 7 insertions(+)

diff --git a/drivers/soundwire/amd_init.c b/drivers/soundwire/amd_init.c
index db040f4350599..4f6e356e6bd24 100644
--- a/drivers/soundwire/amd_init.c
+++ b/drivers/soundwire/amd_init.c
@@ -121,6 +121,7 @@ static struct sdw_amd_ctx *sdw_amd_probe_controller(struct sdw_amd_res *res)
 
 		sdw_pdata[index].instance = index;
 		sdw_pdata[index].acp_sdw_lock = res->acp_lock;
+		sdw_pdata[index].acp_rev = res->acp_rev;
 		pdevinfo[index].name = "amd_sdw_manager";
 		pdevinfo[index].id = index;
 		pdevinfo[index].parent = res->parent;
diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c
index 0d01849c35861..4a1966fb01f6b 100644
--- a/drivers/soundwire/amd_manager.c
+++ b/drivers/soundwire/amd_manager.c
@@ -910,6 +910,7 @@ static int amd_sdw_manager_probe(struct platform_device *pdev)
 	amd_manager->mmio = amd_manager->acp_mmio +
 			    (amd_manager->instance * SDW_MANAGER_REG_OFFSET);
 	amd_manager->acp_sdw_lock = pdata->acp_sdw_lock;
+	amd_manager->acp_rev = pdata->acp_rev;
 	amd_manager->cols_index = sdw_find_col_index(AMD_SDW_DEFAULT_COLUMNS);
 	amd_manager->rows_index = sdw_find_row_index(AMD_SDW_DEFAULT_ROWS);
 	amd_manager->dev = dev;
diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h
index 28a4eb77717f9..e0abc59d4748b 100644
--- a/include/linux/soundwire/sdw_amd.h
+++ b/include/linux/soundwire/sdw_amd.h
@@ -30,6 +30,7 @@
 
 struct acp_sdw_pdata {
 	u16 instance;
+	u32 acp_rev;
 	/* mutex to protect acp common register access */
 	struct mutex *acp_sdw_lock;
 };
@@ -66,6 +67,7 @@ struct sdw_amd_dai_runtime {
  * @instance: SoundWire manager instance
  * @quirks: SoundWire manager quirks
  * @wake_en_mask: wake enable mask per SoundWire manager
+ * @acp_rev: acp pci device revision id
  * @clk_stopped: flag set to true when clock is stopped
  * @power_mode_mask: flag interprets amd SoundWire manager power mode
  * @dai_runtime_array: dai runtime array
@@ -94,6 +96,7 @@ struct amd_sdw_manager {
 	u32 quirks;
 	u32 wake_en_mask;
 	u32 power_mode_mask;
+	u32 acp_rev;
 	bool clk_stopped;
 
 	struct sdw_amd_dai_runtime **dai_runtime_array;
@@ -134,6 +137,7 @@ struct sdw_amd_ctx {
  * struct sdw_amd_res - Soundwire AMD global resource structure,
  * typically populated by the DSP driver/Legacy driver
  *
+ * @acp_rev: acp pci device revision id
  * @addr: acp pci device resource start address
  * @reg_range: ACP register range
  * @link_mask: bit-wise mask listing links selected by the DSP driver/
@@ -146,6 +150,7 @@ struct sdw_amd_ctx {
  * @acp_lock: mutex protecting acp common registers access
  */
 struct sdw_amd_res {
+	u32 acp_rev;
 	u32 addr;
 	u32 reg_range;
 	u32 link_mask;

From 7b54323dde29452dd06e6acd2701d9b489c9547d Mon Sep 17 00:00:00 2001
From: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Date: Tue, 24 Sep 2024 13:48:44 +0530
Subject: [PATCH 0094/1530] soundwire: amd: refactor existing code for acp 6.3
 platform

Refactor existing code by adding acp pci revision id coditional checks
for ACP 6.3 platform. Rename the macros and structure names with ACP63
tag.

Signed-off-by: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Link: https://lore.kernel.org/r/20240924081846.1834612-3-Vijendar.Mukunda@amd.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/amd_manager.c   | 98 ++++++++++++++++++++-----------
 drivers/soundwire/amd_manager.h   | 16 ++---
 include/linux/soundwire/sdw_amd.h |  1 +
 3 files changed, 72 insertions(+), 43 deletions(-)

diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c
index 4a1966fb01f6b..5a4bfaef65fb2 100644
--- a/drivers/soundwire/amd_manager.c
+++ b/drivers/soundwire/amd_manager.c
@@ -433,12 +433,18 @@ static int amd_sdw_port_params(struct sdw_bus *bus, struct sdw_port_params *p_pa
 	u32 frame_fmt_reg, dpn_frame_fmt;
 
 	dev_dbg(amd_manager->dev, "p_params->num:0x%x\n", p_params->num);
-	switch (amd_manager->instance) {
-	case ACP_SDW0:
-		frame_fmt_reg = sdw0_manager_dp_reg[p_params->num].frame_fmt_reg;
-		break;
-	case ACP_SDW1:
-		frame_fmt_reg = sdw1_manager_dp_reg[p_params->num].frame_fmt_reg;
+	switch (amd_manager->acp_rev) {
+	case ACP63_PCI_REV_ID:
+		switch (amd_manager->instance) {
+		case ACP_SDW0:
+			frame_fmt_reg = acp63_sdw0_dp_reg[p_params->num].frame_fmt_reg;
+			break;
+		case ACP_SDW1:
+			frame_fmt_reg = acp63_sdw1_dp_reg[p_params->num].frame_fmt_reg;
+			break;
+		default:
+			return -EINVAL;
+		}
 		break;
 	default:
 		return -EINVAL;
@@ -465,20 +471,28 @@ static int amd_sdw_transport_params(struct sdw_bus *bus,
 	u32 frame_fmt_reg, sample_int_reg, hctrl_dp0_reg;
 	u32 offset_reg, lane_ctrl_ch_en_reg;
 
-	switch (amd_manager->instance) {
-	case ACP_SDW0:
-		frame_fmt_reg = sdw0_manager_dp_reg[params->port_num].frame_fmt_reg;
-		sample_int_reg = sdw0_manager_dp_reg[params->port_num].sample_int_reg;
-		hctrl_dp0_reg = sdw0_manager_dp_reg[params->port_num].hctrl_dp0_reg;
-		offset_reg = sdw0_manager_dp_reg[params->port_num].offset_reg;
-		lane_ctrl_ch_en_reg = sdw0_manager_dp_reg[params->port_num].lane_ctrl_ch_en_reg;
-		break;
-	case ACP_SDW1:
-		frame_fmt_reg = sdw1_manager_dp_reg[params->port_num].frame_fmt_reg;
-		sample_int_reg = sdw1_manager_dp_reg[params->port_num].sample_int_reg;
-		hctrl_dp0_reg = sdw1_manager_dp_reg[params->port_num].hctrl_dp0_reg;
-		offset_reg = sdw1_manager_dp_reg[params->port_num].offset_reg;
-		lane_ctrl_ch_en_reg = sdw1_manager_dp_reg[params->port_num].lane_ctrl_ch_en_reg;
+	switch (amd_manager->acp_rev) {
+	case ACP63_PCI_REV_ID:
+		switch (amd_manager->instance) {
+		case ACP_SDW0:
+			frame_fmt_reg = acp63_sdw0_dp_reg[params->port_num].frame_fmt_reg;
+			sample_int_reg = acp63_sdw0_dp_reg[params->port_num].sample_int_reg;
+			hctrl_dp0_reg = acp63_sdw0_dp_reg[params->port_num].hctrl_dp0_reg;
+			offset_reg = acp63_sdw0_dp_reg[params->port_num].offset_reg;
+			lane_ctrl_ch_en_reg =
+					acp63_sdw0_dp_reg[params->port_num].lane_ctrl_ch_en_reg;
+			break;
+		case ACP_SDW1:
+			frame_fmt_reg = acp63_sdw1_dp_reg[params->port_num].frame_fmt_reg;
+			sample_int_reg = acp63_sdw1_dp_reg[params->port_num].sample_int_reg;
+			hctrl_dp0_reg = acp63_sdw1_dp_reg[params->port_num].hctrl_dp0_reg;
+			offset_reg = acp63_sdw1_dp_reg[params->port_num].offset_reg;
+			lane_ctrl_ch_en_reg =
+					acp63_sdw1_dp_reg[params->port_num].lane_ctrl_ch_en_reg;
+			break;
+		default:
+			return -EINVAL;
+		}
 		break;
 	default:
 		return -EINVAL;
@@ -520,12 +534,20 @@ static int amd_sdw_port_enable(struct sdw_bus *bus,
 	u32 dpn_ch_enable;
 	u32 lane_ctrl_ch_en_reg;
 
-	switch (amd_manager->instance) {
-	case ACP_SDW0:
-		lane_ctrl_ch_en_reg = sdw0_manager_dp_reg[enable_ch->port_num].lane_ctrl_ch_en_reg;
-		break;
-	case ACP_SDW1:
-		lane_ctrl_ch_en_reg = sdw1_manager_dp_reg[enable_ch->port_num].lane_ctrl_ch_en_reg;
+	switch (amd_manager->acp_rev) {
+	case ACP63_PCI_REV_ID:
+		switch (amd_manager->instance) {
+		case ACP_SDW0:
+			lane_ctrl_ch_en_reg =
+					acp63_sdw0_dp_reg[enable_ch->port_num].lane_ctrl_ch_en_reg;
+			break;
+		case ACP_SDW1:
+			lane_ctrl_ch_en_reg =
+					acp63_sdw1_dp_reg[enable_ch->port_num].lane_ctrl_ch_en_reg;
+			break;
+		default:
+			return -EINVAL;
+		}
 		break;
 	default:
 		return -EINVAL;
@@ -927,15 +949,21 @@ static int amd_sdw_manager_probe(struct platform_device *pdev)
 	 * information.
 	 */
 	amd_manager->bus.controller_id = 0;
-
-	switch (amd_manager->instance) {
-	case ACP_SDW0:
-		amd_manager->num_dout_ports = AMD_SDW0_MAX_TX_PORTS;
-		amd_manager->num_din_ports = AMD_SDW0_MAX_RX_PORTS;
-		break;
-	case ACP_SDW1:
-		amd_manager->num_dout_ports = AMD_SDW1_MAX_TX_PORTS;
-		amd_manager->num_din_ports = AMD_SDW1_MAX_RX_PORTS;
+	dev_dbg(dev, "acp_rev:0x%x\n", amd_manager->acp_rev);
+	switch (amd_manager->acp_rev) {
+	case ACP63_PCI_REV_ID:
+		switch (amd_manager->instance) {
+		case ACP_SDW0:
+			amd_manager->num_dout_ports = AMD_ACP63_SDW0_MAX_TX_PORTS;
+			amd_manager->num_din_ports = AMD_ACP63_SDW0_MAX_RX_PORTS;
+			break;
+		case ACP_SDW1:
+			amd_manager->num_dout_ports = AMD_ACP63_SDW1_MAX_TX_PORTS;
+			amd_manager->num_din_ports = AMD_ACP63_SDW1_MAX_RX_PORTS;
+			break;
+		default:
+			return -EINVAL;
+		}
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/soundwire/amd_manager.h b/drivers/soundwire/amd_manager.h
index 707065468e05a..cc2170e4521ed 100644
--- a/drivers/soundwire/amd_manager.h
+++ b/drivers/soundwire/amd_manager.h
@@ -155,12 +155,12 @@
 #define AMD_SDW_IRQ_MASK_8TO11		0x000c7777
 #define AMD_SDW_IRQ_ERROR_MASK		0xff
 #define AMD_SDW_MAX_FREQ_NUM		1
-#define AMD_SDW0_MAX_TX_PORTS		3
-#define AMD_SDW0_MAX_RX_PORTS		3
-#define AMD_SDW1_MAX_TX_PORTS		1
-#define AMD_SDW1_MAX_RX_PORTS		1
-#define AMD_SDW0_MAX_DAI		6
-#define AMD_SDW1_MAX_DAI		2
+#define AMD_ACP63_SDW0_MAX_TX_PORTS		3
+#define AMD_ACP63_SDW0_MAX_RX_PORTS		3
+#define AMD_ACP63_SDW1_MAX_TX_PORTS		1
+#define AMD_ACP63_SDW1_MAX_RX_PORTS		1
+#define AMD_ACP63_SDW0_MAX_DAI		6
+#define AMD_ACP63_SDW1_MAX_DAI		2
 #define AMD_SDW_SLAVE_0_ATTACHED	5
 #define AMD_SDW_SSP_COUNTER_VAL		3
 
@@ -222,7 +222,7 @@ struct sdw_manager_dp_reg {
  * in SoundWire DMA driver.
  */
 
-static struct sdw_manager_dp_reg sdw0_manager_dp_reg[AMD_SDW0_MAX_DAI] =  {
+static struct sdw_manager_dp_reg acp63_sdw0_dp_reg[AMD_ACP63_SDW0_MAX_DAI] =  {
 	{ACP_SW_AUDIO0_TX_FRAME_FORMAT, ACP_SW_AUDIO0_TX_SAMPLEINTERVAL, ACP_SW_AUDIO0_TX_HCTRL_DP0,
 	 ACP_SW_AUDIO0_TX_OFFSET_DP0, ACP_SW_AUDIO0_TX_CHANNEL_ENABLE_DP0},
 	{ACP_SW_AUDIO1_TX_FRAME_FORMAT, ACP_SW_AUDIO1_TX_SAMPLEINTERVAL, ACP_SW_AUDIO1_TX_HCTRL,
@@ -237,7 +237,7 @@ static struct sdw_manager_dp_reg sdw0_manager_dp_reg[AMD_SDW0_MAX_DAI] =  {
 	 ACP_SW_AUDIO2_RX_OFFSET, ACP_SW_AUDIO2_RX_CHANNEL_ENABLE_DP0},
 };
 
-static struct sdw_manager_dp_reg sdw1_manager_dp_reg[AMD_SDW1_MAX_DAI] =  {
+static struct sdw_manager_dp_reg acp63_sdw1_dp_reg[AMD_ACP63_SDW1_MAX_DAI] =  {
 	{ACP_SW_AUDIO1_TX_FRAME_FORMAT, ACP_SW_AUDIO1_TX_SAMPLEINTERVAL, ACP_SW_AUDIO1_TX_HCTRL,
 	 ACP_SW_AUDIO1_TX_OFFSET, ACP_SW_AUDIO1_TX_CHANNEL_ENABLE_DP0},
 	{ACP_SW_AUDIO1_RX_FRAME_FORMAT, ACP_SW_AUDIO1_RX_SAMPLEINTERVAL, ACP_SW_AUDIO1_RX_HCTRL,
diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h
index e0abc59d4748b..c9586f22c5a9b 100644
--- a/include/linux/soundwire/sdw_amd.h
+++ b/include/linux/soundwire/sdw_amd.h
@@ -27,6 +27,7 @@
 #define ACP_SDW0	0
 #define ACP_SDW1	1
 #define AMD_SDW_MAX_MANAGER_COUNT	2
+#define ACP63_PCI_REV_ID		0x63
 
 struct acp_sdw_pdata {
 	u16 instance;

From 1bb50ead592ceaf2b1572c7d08797b8b3229432e Mon Sep 17 00:00:00 2001
From: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Date: Tue, 24 Sep 2024 13:48:45 +0530
Subject: [PATCH 0095/1530] ASoC: SOF: amd: pass acp_rev as soundwire resource
 data

Pass acp_rev(ACP pci revision id) as soundwire resource data
for SoundWire controller probe function.

Signed-off-by: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Acked-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20240924081846.1834612-4-Vijendar.Mukunda@amd.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 sound/soc/sof/amd/acp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c
index d579c3849392c..f967e84987981 100644
--- a/sound/soc/sof/amd/acp.c
+++ b/sound/soc/sof/amd/acp.c
@@ -683,6 +683,7 @@ static int amd_sof_sdw_probe(struct snd_sof_dev *sdev)
 	sdw_res.count = acp_data->info.count;
 	sdw_res.link_mask = acp_data->info.link_mask;
 	sdw_res.mmio_base = sdev->bar[ACP_DSP_BAR];
+	sdw_res.acp_rev = acp_data->pci_rev;
 
 	ret = sdw_amd_probe(&sdw_res, &acp_data->sdw);
 	if (ret)

From 425f598ea69713b9e60f08e48a19be56b7bfddbc Mon Sep 17 00:00:00 2001
From: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Date: Tue, 24 Sep 2024 13:48:46 +0530
Subject: [PATCH 0096/1530] ASoC: amd: ps: pass acp pci revision id as
 soundwire resource data

Add acp_rev as structure member in acp pci driver private data structure
to store acp pci revision id and assign this variable to SoundWire resource
data acp_rev variable.

Signed-off-by: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Acked-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20240924081846.1834612-5-Vijendar.Mukunda@amd.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 sound/soc/amd/ps/acp63.h  | 2 ++
 sound/soc/amd/ps/pci-ps.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/sound/soc/amd/ps/acp63.h b/sound/soc/amd/ps/acp63.h
index 39208305dd6c3..e54eabaa4d3e1 100644
--- a/sound/soc/amd/ps/acp63.h
+++ b/sound/soc/amd/ps/acp63.h
@@ -231,6 +231,7 @@ struct sdw_dma_ring_buf_reg {
  * @sdw_en_stat: flag set to true when any one of the SoundWire manager instance is enabled
  * @addr: pci ioremap address
  * @reg_range: ACP reigister range
+ * @acp_rev: ACP PCI revision id
  * @sdw0-dma_intr_stat: DMA interrupt status array for SoundWire manager-SW0 instance
  * @sdw_dma_intr_stat: DMA interrupt status array for SoundWire manager-SW1 instance
  */
@@ -254,6 +255,7 @@ struct acp63_dev_data {
 	bool sdw_en_stat;
 	u32 addr;
 	u32 reg_range;
+	u32 acp_rev;
 	u16 sdw0_dma_intr_stat[ACP63_SDW0_DMA_MAX_STREAMS];
 	u16 sdw1_dma_intr_stat[ACP63_SDW1_DMA_MAX_STREAMS];
 };
diff --git a/sound/soc/amd/ps/pci-ps.c b/sound/soc/amd/ps/pci-ps.c
index c72d666d51bdf..0c3bb1da50975 100644
--- a/sound/soc/amd/ps/pci-ps.c
+++ b/sound/soc/amd/ps/pci-ps.c
@@ -267,6 +267,7 @@ static int amd_sdw_probe(struct device *dev)
 	sdw_res.acp_lock = &acp_data->acp_lock;
 	sdw_res.count = acp_data->info.count;
 	sdw_res.mmio_base = acp_data->acp63_base;
+	sdw_res.acp_rev = acp_data->acp_rev;
 	sdw_res.link_mask = acp_data->info.link_mask;
 	ret = sdw_amd_probe(&sdw_res, &acp_data->sdw);
 	if (ret)
@@ -576,6 +577,7 @@ static int snd_acp63_probe(struct pci_dev *pci,
 	}
 	adata->addr = addr;
 	adata->reg_range = ACP63_REG_END - ACP63_REG_START;
+	adata->acp_rev = pci->revision;
 	pci_set_master(pci);
 	pci_set_drvdata(pci, adata);
 	mutex_init(&adata->acp_lock);

From a54dc8c68a5b33ca00b8dcd3b87681aacfbfc9dc Mon Sep 17 00:00:00 2001
From: Shen Lichuan <shenlichuan@vivo.com>
Date: Wed, 25 Sep 2024 16:11:34 +0800
Subject: [PATCH 0097/1530] soundwire: Correct some typos in comments

Fixed some confusing spelling errors that were currently identified,
the details are as follows:

-in the code comments:
drivers/soundwire/bus.c:115: enumuration==> enumeration
drivers/soundwire/qcom.c:1176: wil ==> will
drivers/soundwire/sysfs_slave.c:218: highligh ==> highlight

Signed-off-by: Shen Lichuan <shenlichuan@vivo.com>
Link: https://lore.kernel.org/r/20240925081134.10248-1-shenlichuan@vivo.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/bus.c         | 2 +-
 drivers/soundwire/qcom.c        | 2 +-
 drivers/soundwire/sysfs_slave.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 263ca32f0c5c3..d1dc62c34f1cf 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -112,7 +112,7 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
 	/* Set higher order bits */
 	*bus->assigned = ~GENMASK(SDW_BROADCAST_DEV_NUM, SDW_ENUM_DEV_NUM);
 
-	/* Set enumuration device number and broadcast device number */
+	/* Set enumeration device number and broadcast device number */
 	set_bit(SDW_ENUM_DEV_NUM, bus->assigned);
 	set_bit(SDW_BROADCAST_DEV_NUM, bus->assigned);
 
diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c
index aed57002fd0e6..2b403b14066c1 100644
--- a/drivers/soundwire/qcom.c
+++ b/drivers/soundwire/qcom.c
@@ -1173,7 +1173,7 @@ static int qcom_swrm_stream_alloc_ports(struct qcom_swrm_ctrl *ctrl,
 	else
 		sconfig.direction = SDW_DATA_DIR_RX;
 
-	/* hw parameters wil be ignored as we only support PDM */
+	/* hw parameters will be ignored as we only support PDM */
 	sconfig.ch_count = 1;
 	sconfig.frame_rate = params_rate(params);
 	sconfig.type = stream->type;
diff --git a/drivers/soundwire/sysfs_slave.c b/drivers/soundwire/sysfs_slave.c
index f4259710dd0f7..c5c22d1708ec5 100644
--- a/drivers/soundwire/sysfs_slave.c
+++ b/drivers/soundwire/sysfs_slave.c
@@ -215,7 +215,7 @@ const struct attribute_group *sdw_attr_groups[] = {
 
 /*
  * the status is shown in capital letters for UNATTACHED and RESERVED
- * on purpose, to highligh users to the fact that these status values
+ * on purpose, to highlight users to the fact that these status values
  * are not expected.
  */
 static const char *const slave_status[] = {

From 093227bc53a023991ba04315f42839a22b613113 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 15:06:37 +0800
Subject: [PATCH 0098/1530] soundwire: mipi_disco: add MIPI-specific
 property_read_bool() helpers

The existing device/fwnode_property_read_bool() helpers only check if
the property is present.

The MIPI DisCo for SoundWire specification allows properties to be
exposed with a value of 'false'. Using the standard helpers to
retrieve the MIPI-defined properties causes all kinds of logical
inversions leading to loss of functionality - such as jack detection
in clock-stop mode broken when the device properties are read in
Realtek codec drivers.

This patch adds new MIPI/SoundWire helpers which first check if the
property is present, and then return the actual value extracted from
platform firmware.

Modifying the default property handling was considered as a possible
solution, but it could lead to other types of logical inversions
breaking 'working' setups. Andy Shevchenko also pointed out that DT
keeps values in the BE32 format, it's probably best to avoid
endianness complications.

The path of least resistance was chosen, with MIPI-specific helpers
which can be tested and with no side effects outside of the SoundWire
subsystem.

Closes: https://github.com/thesofproject/linux/issues/5129
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003070650.62787-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/mipi_disco.c | 50 ++++++++++++++++++++++++----------
 1 file changed, 35 insertions(+), 15 deletions(-)

diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c
index e5d9df26d4dc9..fdab3d4a1379b 100644
--- a/drivers/soundwire/mipi_disco.c
+++ b/drivers/soundwire/mipi_disco.c
@@ -23,6 +23,26 @@
 #include <linux/soundwire/sdw.h>
 #include "bus.h"
 
+static bool mipi_fwnode_property_read_bool(const struct fwnode_handle *fwnode,
+					   const char *propname)
+{
+	int ret;
+	u8 val;
+
+	if (!fwnode_property_present(fwnode, propname))
+		return false;
+	ret = fwnode_property_read_u8_array(fwnode, propname, &val, 1);
+	if (ret < 0)
+		return false;
+	return !!val;
+}
+
+static bool mipi_device_property_read_bool(const struct device *dev,
+					   const char *propname)
+{
+	return mipi_fwnode_property_read_bool(dev_fwnode(dev), propname);
+}
+
 /**
  * sdw_master_read_prop() - Read Master properties
  * @bus: SDW bus instance
@@ -48,11 +68,11 @@ int sdw_master_read_prop(struct sdw_bus *bus)
 		return -EIO;
 	}
 
-	if (fwnode_property_read_bool(link,
+	if (mipi_fwnode_property_read_bool(link,
 				      "mipi-sdw-clock-stop-mode0-supported"))
 		prop->clk_stop_modes |= BIT(SDW_CLK_STOP_MODE0);
 
-	if (fwnode_property_read_bool(link,
+	if (mipi_fwnode_property_read_bool(link,
 				      "mipi-sdw-clock-stop-mode1-supported"))
 		prop->clk_stop_modes |= BIT(SDW_CLK_STOP_MODE1);
 
@@ -114,7 +134,7 @@ int sdw_master_read_prop(struct sdw_bus *bus)
 	fwnode_property_read_u32(link, "mipi-sdw-default-frame-col-size",
 				 &prop->default_col);
 
-	prop->dynamic_frame =  fwnode_property_read_bool(link,
+	prop->dynamic_frame =  mipi_fwnode_property_read_bool(link,
 			"mipi-sdw-dynamic-frame-shape");
 
 	fwnode_property_read_u32(link, "mipi-sdw-command-error-threshold",
@@ -153,13 +173,13 @@ static int sdw_slave_read_dp0(struct sdw_slave *slave,
 				dp0->words, dp0->num_words);
 	}
 
-	dp0->BRA_flow_controlled = fwnode_property_read_bool(port,
+	dp0->BRA_flow_controlled = mipi_fwnode_property_read_bool(port,
 				"mipi-sdw-bra-flow-controlled");
 
-	dp0->simple_ch_prep_sm = fwnode_property_read_bool(port,
+	dp0->simple_ch_prep_sm = mipi_fwnode_property_read_bool(port,
 				"mipi-sdw-simplified-channel-prepare-sm");
 
-	dp0->imp_def_interrupts = fwnode_property_read_bool(port,
+	dp0->imp_def_interrupts = mipi_fwnode_property_read_bool(port,
 				"mipi-sdw-imp-def-dp0-interrupts-supported");
 
 	return 0;
@@ -220,7 +240,7 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave,
 					 "mipi-sdw-max-grouping-supported",
 					 &dpn[i].max_grouping);
 
-		dpn[i].simple_ch_prep_sm = fwnode_property_read_bool(node,
+		dpn[i].simple_ch_prep_sm = mipi_fwnode_property_read_bool(node,
 				"mipi-sdw-simplified-channelprepare-sm");
 
 		fwnode_property_read_u32(node,
@@ -278,7 +298,7 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave,
 		fwnode_property_read_u32(node, "mipi-sdw-max-async-buffer",
 					 &dpn[i].max_async_buffer);
 
-		dpn[i].block_pack_mode = fwnode_property_read_bool(node,
+		dpn[i].block_pack_mode = mipi_fwnode_property_read_bool(node,
 				"mipi-sdw-block-packing-mode");
 
 		fwnode_property_read_u32(node, "mipi-sdw-port-encoding-type",
@@ -308,19 +328,19 @@ int sdw_slave_read_prop(struct sdw_slave *slave)
 	device_property_read_u32(dev, "mipi-sdw-sw-interface-revision",
 				 &prop->mipi_revision);
 
-	prop->wake_capable = device_property_read_bool(dev,
+	prop->wake_capable = mipi_device_property_read_bool(dev,
 				"mipi-sdw-wake-up-unavailable");
 	prop->wake_capable = !prop->wake_capable;
 
-	prop->test_mode_capable = device_property_read_bool(dev,
+	prop->test_mode_capable = mipi_device_property_read_bool(dev,
 				"mipi-sdw-test-mode-supported");
 
 	prop->clk_stop_mode1 = false;
-	if (device_property_read_bool(dev,
+	if (mipi_device_property_read_bool(dev,
 				"mipi-sdw-clock-stop-mode1-supported"))
 		prop->clk_stop_mode1 = true;
 
-	prop->simple_clk_stop_capable = device_property_read_bool(dev,
+	prop->simple_clk_stop_capable = mipi_device_property_read_bool(dev,
 			"mipi-sdw-simplified-clockstopprepare-sm-supported");
 
 	device_property_read_u32(dev, "mipi-sdw-clockstopprepare-timeout",
@@ -333,13 +353,13 @@ int sdw_slave_read_prop(struct sdw_slave *slave)
 			"mipi-sdw-clockstopprepare-hard-reset-behavior",
 			&prop->reset_behave);
 
-	prop->high_PHY_capable = device_property_read_bool(dev,
+	prop->high_PHY_capable = mipi_device_property_read_bool(dev,
 			"mipi-sdw-highPHY-capable");
 
-	prop->paging_support = device_property_read_bool(dev,
+	prop->paging_support = mipi_device_property_read_bool(dev,
 			"mipi-sdw-paging-support");
 
-	prop->bank_delay_support = device_property_read_bool(dev,
+	prop->bank_delay_support = mipi_device_property_read_bool(dev,
 			"mipi-sdw-bank-delay-support");
 
 	device_property_read_u32(dev,

From 444d6824a4feca142b0a57095a2f1f1bda98e2ab Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 15:06:38 +0800
Subject: [PATCH 0099/1530] soundwire: optimize sdw_stream_runtime memory
 layout

pahole suggestion: swap position of 'm_rt_count'

before: pahole -C sdw_stream_runtime drivers/soundwire/soundwire-bus.ko
struct sdw_stream_runtime {
	const char  *              name;                 /*     0     8 */
	struct sdw_stream_params   params;               /*     8    12 */
	enum sdw_stream_state      state;                /*    20     4 */
	enum sdw_stream_type       type;                 /*    24     4 */

	/* XXX 4 bytes hole, try to pack */

	struct list_head           master_list;          /*    32    16 */
	int                        m_rt_count;           /*    48     4 */

	/* size: 56, cachelines: 1, members: 6 */
	/* sum members: 48, holes: 1, sum holes: 4 */
	/* padding: 4 */
	/* last cacheline: 56 bytes */
};

after: pahole --reorganize -C sdw_stream_runtime drivers/soundwire/soundwire-bus.ko
struct sdw_stream_runtime {
	const char  *              name;                 /*     0     8 */
	struct sdw_stream_params   params;               /*     8    12 */
	enum sdw_stream_state      state;                /*    20     4 */
	enum sdw_stream_type       type;                 /*    24     4 */
	int                        m_rt_count;           /*    28     4 */
	struct list_head           master_list;          /*    32    16 */

	/* size: 48, cachelines: 1, members: 6 */
	/* last cacheline: 48 bytes */
};   /* saved 8 bytes! */

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003070650.62787-3-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 5e0dd47a04124..a4fa451320305 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -820,15 +820,15 @@ struct sdw_master_port_ops {
 struct sdw_msg;
 
 /**
- * struct sdw_defer - SDW deffered message
- * @length: message length
+ * struct sdw_defer - SDW deferred message
  * @complete: message completion
  * @msg: SDW message
+ * @length: message length
  */
 struct sdw_defer {
+	struct sdw_msg *msg;
 	int length;
 	struct completion complete;
-	struct sdw_msg *msg;
 };
 
 /**
@@ -1010,18 +1010,18 @@ struct sdw_stream_params {
  * @params: Stream parameters
  * @state: Current state of the stream
  * @type: Stream type PCM or PDM
+ * @m_rt_count: Count of Master runtime(s) in this stream
  * @master_list: List of Master runtime(s) in this stream.
  * master_list can contain only one m_rt per Master instance
  * for a stream
- * @m_rt_count: Count of Master runtime(s) in this stream
  */
 struct sdw_stream_runtime {
 	const char *name;
 	struct sdw_stream_params params;
 	enum sdw_stream_state state;
 	enum sdw_stream_type type;
-	struct list_head master_list;
 	int m_rt_count;
+	struct list_head master_list;
 };
 
 struct sdw_stream_runtime *sdw_alloc_stream(const char *stream_name);

From 6cb2c156439430a7f9db2e1f71a7dccf1ca978bf Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 15:06:39 +0800
Subject: [PATCH 0100/1530] soundwire: optimize sdw_master_prop

Make pahole happy by moving pointers and u64 first instead of
interleaving them.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003070650.62787-4-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index a4fa451320305..2caea7345c3eb 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -406,13 +406,14 @@ struct sdw_slave_prop {
 
 /**
  * struct sdw_master_prop - Master properties
+ * @clk_gears: Clock gears supported
+ * @clk_freq: Clock frequencies supported, in Hz
+ * @quirks: bitmask identifying optional behavior beyond the scope of the MIPI specification
  * @revision: MIPI spec version of the implementation
  * @clk_stop_modes: Bitmap, bit N set when clock-stop-modeN supported
  * @max_clk_freq: Maximum Bus clock frequency, in Hz
  * @num_clk_gears: Number of clock gears supported
- * @clk_gears: Clock gears supported
  * @num_clk_freq: Number of clock frequencies supported, in Hz
- * @clk_freq: Clock frequencies supported, in Hz
  * @default_frame_rate: Controller default Frame rate, in Hz
  * @default_row: Number of rows
  * @default_col: Number of columns
@@ -421,24 +422,23 @@ struct sdw_slave_prop {
  * command
  * @mclk_freq: clock reference passed to SoundWire Master, in Hz.
  * @hw_disabled: if true, the Master is not functional, typically due to pin-mux
- * @quirks: bitmask identifying optional behavior beyond the scope of the MIPI specification
  */
 struct sdw_master_prop {
+	u32 *clk_gears;
+	u32 *clk_freq;
+	u64 quirks;
 	u32 revision;
 	u32 clk_stop_modes;
 	u32 max_clk_freq;
 	u32 num_clk_gears;
-	u32 *clk_gears;
 	u32 num_clk_freq;
-	u32 *clk_freq;
 	u32 default_frame_rate;
 	u32 default_row;
 	u32 default_col;
-	bool dynamic_frame;
 	u32 err_threshold;
 	u32 mclk_freq;
+	bool dynamic_frame;
 	bool hw_disabled;
-	u64 quirks;
 };
 
 /* Definitions for Master quirks */

From 0a323dad1c4e04048988cd04c60eaffd6ae61b1a Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 15:06:40 +0800
Subject: [PATCH 0101/1530] soundwire: optimize sdw_bus structure

The sdw_bus structure has seen multiple additions over the years. It's
one of the most used structures in this subsystem, so there's merit in
reshuffling the members a bit with 'pahole' to reduce holes and
structures across cache lines.

before:

struct sdw_bus {
	struct device *            dev;                  /*     0     8 */
	struct sdw_master_device * md;                   /*     8     8 */
	int                        controller_id;        /*    16     4 */
	unsigned int               link_id;              /*    20     4 */
	int                        id;                   /*    24     4 */

	/* XXX 4 bytes hole, try to pack */

	struct list_head           slaves;               /*    32    16 */
	long unsigned int          assigned[1];          /*    48     8 */
	struct mutex               bus_lock;             /*    56   160 */
	/* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */
	struct lock_class_key      bus_lock_key;         /*   216    16 */
	struct mutex               msg_lock;             /*   232   160 */
	/* --- cacheline 6 boundary (384 bytes) was 8 bytes ago --- */
	struct lock_class_key      msg_lock_key;         /*   392    16 */
	int                        (*compute_params)(struct sdw_bus *); /*   408     8 */
	const struct sdw_master_ops  * ops;              /*   416     8 */
	const struct sdw_master_port_ops  * port_ops;    /*   424     8 */
	struct sdw_bus_params      params;               /*   432    36 */

	/* XXX 4 bytes hole, try to pack */

	/* --- cacheline 7 boundary (448 bytes) was 24 bytes ago --- */
	struct sdw_master_prop     prop;                 /*   472    72 */

	/* XXX last struct has 6 bytes of padding */

	/* --- cacheline 8 boundary (512 bytes) was 32 bytes ago --- */
	void *                     vendor_specific_prop; /*   544     8 */
	struct list_head           m_rt_list;            /*   552    16 */
	struct dentry *            debugfs;              /*   568     8 */
	/* --- cacheline 9 boundary (576 bytes) --- */
	struct irq_chip            irq_chip;             /*   576   264 */
	/* --- cacheline 13 boundary (832 bytes) was 8 bytes ago --- */
	struct irq_domain *        domain;               /*   840     8 */
	struct sdw_defer           defer_msg;            /*   848   112 */
	/* --- cacheline 15 boundary (960 bytes) --- */
	unsigned int               clk_stop_timeout;     /*   960     4 */
	u32                        bank_switch_timeout;  /*   964     4 */
	bool                       multi_link;           /*   968     1 */

	/* XXX 3 bytes hole, try to pack */

	int                        hw_sync_min_links;    /*   972     4 */
	int                        stream_refcount;      /*   976     4 */

	/* size: 984, cachelines: 16, members: 27 */
	/* sum members: 969, holes: 3, sum holes: 11 */
	/* padding: 4 */
	/* paddings: 1, sum paddings: 6 */
	/* last cacheline: 24 bytes */
};

after:

struct sdw_bus {
	struct device *            dev;                  /*     0     8 */
	struct sdw_master_device * md;                   /*     8     8 */
	struct lock_class_key      bus_lock_key;         /*    16    16 */
	struct mutex               bus_lock;             /*    32   160 */
	/* --- cacheline 3 boundary (192 bytes) --- */
	struct list_head           slaves;               /*   192    16 */
	struct lock_class_key      msg_lock_key;         /*   208    16 */
	struct mutex               msg_lock;             /*   224   160 */
	/* --- cacheline 6 boundary (384 bytes) --- */
	struct list_head           m_rt_list;            /*   384    16 */
	struct sdw_defer           defer_msg;            /*   400   112 */
	/* --- cacheline 8 boundary (512 bytes) --- */
	struct sdw_bus_params      params;               /*   512    36 */
	int                        stream_refcount;      /*   548     4 */
	const struct sdw_master_ops  * ops;              /*   552     8 */
	const struct sdw_master_port_ops  * port_ops;    /*   560     8 */
	struct sdw_master_prop     prop;                 /*   568    72 */

	/* XXX last struct has 6 bytes of padding */

	/* --- cacheline 10 boundary (640 bytes) --- */
	void *                     vendor_specific_prop; /*   640     8 */
	int                        hw_sync_min_links;    /*   648     4 */
	int                        controller_id;        /*   652     4 */
	unsigned int               link_id;              /*   656     4 */
	int                        id;                   /*   660     4 */
	int                        (*compute_params)(struct sdw_bus *); /*   664     8 */
	long unsigned int          assigned[1];          /*   672     8 */
	unsigned int               clk_stop_timeout;     /*   680     4 */
	u32                        bank_switch_timeout;  /*   684     4 */
	struct irq_chip            irq_chip;             /*   688   264 */
	/* --- cacheline 14 boundary (896 bytes) was 56 bytes ago --- */
	struct irq_domain *        domain;               /*   952     8 */
	/* --- cacheline 15 boundary (960 bytes) --- */
	struct dentry *            debugfs;              /*   960     8 */
	bool                       multi_link;           /*   968     1 */

	/* size: 976, cachelines: 16, members: 27 */
	/* padding: 7 */
	/* paddings: 1, sum paddings: 6 */
	/* last cacheline: 16 bytes */
};

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003070650.62787-5-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 77 ++++++++++++++++++-----------------
 1 file changed, 40 insertions(+), 37 deletions(-)

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 2caea7345c3eb..6fcf122c18312 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -871,68 +871,71 @@ struct sdw_master_ops {
  * struct sdw_bus - SoundWire bus
  * @dev: Shortcut to &bus->md->dev to avoid changing the entire code.
  * @md: Master device
- * @controller_id: system-unique controller ID. If set to -1, the bus @id will be used.
- * @link_id: Link id number, can be 0 to N, unique for each Controller
- * @id: bus system-wide unique id
- * @slaves: list of Slaves on this bus
- * @assigned: Bitmap for Slave device numbers.
- * Bit set implies used number, bit clear implies unused number.
+ * @bus_lock_key: bus lock key associated to @bus_lock
  * @bus_lock: bus lock
+ * @slaves: list of Slaves on this bus
+ * @msg_lock_key: message lock key associated to @msg_lock
  * @msg_lock: message lock
- * @compute_params: points to Bus resource management implementation
- * @ops: Master callback ops
- * @port_ops: Master port callback ops
- * @params: Current bus parameters
- * @prop: Master properties
- * @vendor_specific_prop: pointer to non-standard properties
  * @m_rt_list: List of Master instance of all stream(s) running on Bus. This
  * is used to compute and program bus bandwidth, clock, frame shape,
  * transport and port parameters
- * @debugfs: Bus debugfs
- * @domain: IRQ domain
  * @defer_msg: Defer message
- * @clk_stop_timeout: Clock stop timeout computed
- * @bank_switch_timeout: Bank switch timeout computed
- * @multi_link: Store bus property that indicates if multi links
- * are supported. This flag is populated by drivers after reading
- * appropriate firmware (ACPI/DT).
+ * @params: Current bus parameters
+ * @stream_refcount: number of streams currently using this bus
+ * @ops: Master callback ops
+ * @port_ops: Master port callback ops
+ * @prop: Master properties
+ * @vendor_specific_prop: pointer to non-standard properties
  * @hw_sync_min_links: Number of links used by a stream above which
  * hardware-based synchronization is required. This value is only
  * meaningful if multi_link is set. If set to 1, hardware-based
  * synchronization will be used even if a stream only uses a single
  * SoundWire segment.
- * @stream_refcount: number of streams currently using this bus
+ * @controller_id: system-unique controller ID. If set to -1, the bus @id will be used.
+ * @link_id: Link id number, can be 0 to N, unique for each Controller
+ * @id: bus system-wide unique id
+ * @compute_params: points to Bus resource management implementation
+ * @assigned: Bitmap for Slave device numbers.
+ * Bit set implies used number, bit clear implies unused number.
+ * @clk_stop_timeout: Clock stop timeout computed
+ * @bank_switch_timeout: Bank switch timeout computed
+ * @domain: IRQ domain
+ * @irq_chip: IRQ chip
+ * @debugfs: Bus debugfs (optional)
+ * @multi_link: Store bus property that indicates if multi links
+ * are supported. This flag is populated by drivers after reading
+ * appropriate firmware (ACPI/DT).
  */
 struct sdw_bus {
 	struct device *dev;
 	struct sdw_master_device *md;
-	int controller_id;
-	unsigned int link_id;
-	int id;
-	struct list_head slaves;
-	DECLARE_BITMAP(assigned, SDW_MAX_DEVICES);
-	struct mutex bus_lock;
 	struct lock_class_key bus_lock_key;
-	struct mutex msg_lock;
+	struct mutex bus_lock;
+	struct list_head slaves;
 	struct lock_class_key msg_lock_key;
-	int (*compute_params)(struct sdw_bus *bus);
+	struct mutex msg_lock;
+	struct list_head m_rt_list;
+	struct sdw_defer defer_msg;
+	struct sdw_bus_params params;
+	int stream_refcount;
 	const struct sdw_master_ops *ops;
 	const struct sdw_master_port_ops *port_ops;
-	struct sdw_bus_params params;
 	struct sdw_master_prop prop;
 	void *vendor_specific_prop;
-	struct list_head m_rt_list;
+	int hw_sync_min_links;
+	int controller_id;
+	unsigned int link_id;
+	int id;
+	int (*compute_params)(struct sdw_bus *bus);
+	DECLARE_BITMAP(assigned, SDW_MAX_DEVICES);
+	unsigned int clk_stop_timeout;
+	u32 bank_switch_timeout;
+	struct irq_chip irq_chip;
+	struct irq_domain *domain;
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debugfs;
 #endif
-	struct irq_chip irq_chip;
-	struct irq_domain *domain;
-	struct sdw_defer defer_msg;
-	unsigned int clk_stop_timeout;
-	u32 bank_switch_timeout;
 	bool multi_link;
-	int hw_sync_min_links;
-	int stream_refcount;
 };
 
 int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,

From 1c758df5a83ea0c9b5055536336d8a586b5010b0 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 15:06:41 +0800
Subject: [PATCH 0102/1530] soundwire: optimize sdw_slave_prop

move pointers first, and move booleans together.

before:

struct sdw_slave_prop {
	u32                        mipi_revision;        /*     0     4 */
	bool                       wake_capable;         /*     4     1 */
	bool                       test_mode_capable;    /*     5     1 */
	bool                       clk_stop_mode1;       /*     6     1 */
	bool                       simple_clk_stop_capable; /*     7     1 */
	u32                        clk_stop_timeout;     /*     8     4 */
	u32                        ch_prep_timeout;      /*    12     4 */
	enum sdw_clk_stop_reset_behave reset_behave;     /*    16     4 */
	bool                       high_PHY_capable;     /*    20     1 */
	bool                       paging_support;       /*    21     1 */
	bool                       bank_delay_support;   /*    22     1 */

	/* XXX 1 byte hole, try to pack */

	enum sdw_p15_behave        p15_behave;           /*    24     4 */
	bool                       lane_control_support; /*    28     1 */

	/* XXX 3 bytes hole, try to pack */

	u32                        master_count;         /*    32     4 */
	u32                        source_ports;         /*    36     4 */
	u32                        sink_ports;           /*    40     4 */

	/* XXX 4 bytes hole, try to pack */

	struct sdw_dp0_prop *      dp0_prop;             /*    48     8 */
	struct sdw_dpn_prop *      src_dpn_prop;         /*    56     8 */
	/* --- cacheline 1 boundary (64 bytes) --- */
	struct sdw_dpn_prop *      sink_dpn_prop;        /*    64     8 */
	u8                         scp_int1_mask;        /*    72     1 */

	/* XXX 3 bytes hole, try to pack */

	u32                        quirks;               /*    76     4 */
	bool                       clock_reg_supported;  /*    80     1 */
	bool                       use_domain_irq;       /*    81     1 */

	/* size: 88, cachelines: 2, members: 23 */
	/* sum members: 71, holes: 4, sum holes: 11 */
	/* padding: 6 */
	/* last cacheline: 24 bytes */
};

after:

truct sdw_slave_prop {
	struct sdw_dp0_prop *      dp0_prop;             /*     0     8 */
	struct sdw_dpn_prop *      src_dpn_prop;         /*     8     8 */
	struct sdw_dpn_prop *      sink_dpn_prop;        /*    16     8 */
	u32                        mipi_revision;        /*    24     4 */
	bool                       wake_capable;         /*    28     1 */
	bool                       test_mode_capable;    /*    29     1 */
	bool                       clk_stop_mode1;       /*    30     1 */
	bool                       simple_clk_stop_capable; /*    31     1 */
	u32                        clk_stop_timeout;     /*    32     4 */
	u32                        ch_prep_timeout;      /*    36     4 */
	enum sdw_clk_stop_reset_behave reset_behave;     /*    40     4 */
	bool                       high_PHY_capable;     /*    44     1 */
	bool                       paging_support;       /*    45     1 */
	bool                       bank_delay_support;   /*    46     1 */
	bool                       lane_control_support; /*    47     1 */
	enum sdw_p15_behave        p15_behave;           /*    48     4 */
	u32                        master_count;         /*    52     4 */
	u32                        source_ports;         /*    56     4 */
	u32                        sink_ports;           /*    60     4 */
	/* --- cacheline 1 boundary (64 bytes) --- */
	u32                        quirks;               /*    64     4 */
	u8                         scp_int1_mask;        /*    68     1 */
	bool                       clock_reg_supported;  /*    69     1 */
	bool                       use_domain_irq;       /*    70     1 */

	/* size: 72, cachelines: 2, members: 23 */
	/* padding: 1 */
	/* last cacheline: 8 bytes */
};

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003070650.62787-6-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 6fcf122c18312..38db81f5bdb97 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -344,6 +344,9 @@ struct sdw_dpn_prop {
 
 /**
  * struct sdw_slave_prop - SoundWire Slave properties
+ * @dp0_prop: Data Port 0 properties
+ * @src_dpn_prop: Source Data Port N properties
+ * @sink_dpn_prop: Sink Data Port N properties
  * @mipi_revision: Spec version of the implementation
  * @wake_capable: Wake-up events are supported
  * @test_mode_capable: If test mode is supported
@@ -360,15 +363,12 @@ struct sdw_dpn_prop {
  * SCP_AddrPage2
  * @bank_delay_support: Slave implements bank delay/bridge support registers
  * SCP_BankDelay and SCP_NextFrame
+ * @lane_control_support: Slave supports lane control
  * @p15_behave: Slave behavior when the Master attempts a read to the Port15
  * alias
- * @lane_control_support: Slave supports lane control
  * @master_count: Number of Masters present on this Slave
  * @source_ports: Bitmap identifying source ports
  * @sink_ports: Bitmap identifying sink ports
- * @dp0_prop: Data Port 0 properties
- * @src_dpn_prop: Source Data Port N properties
- * @sink_dpn_prop: Sink Data Port N properties
  * @scp_int1_mask: SCP_INT1_MASK desired settings
  * @quirks: bitmask identifying deltas from the MIPI specification
  * @clock_reg_supported: the Peripheral implements the clock base and scale
@@ -377,6 +377,9 @@ struct sdw_dpn_prop {
  * @use_domain_irq: call actual IRQ handler on slave, as well as callback
  */
 struct sdw_slave_prop {
+	struct sdw_dp0_prop *dp0_prop;
+	struct sdw_dpn_prop *src_dpn_prop;
+	struct sdw_dpn_prop *sink_dpn_prop;
 	u32 mipi_revision;
 	bool wake_capable;
 	bool test_mode_capable;
@@ -388,16 +391,13 @@ struct sdw_slave_prop {
 	bool high_PHY_capable;
 	bool paging_support;
 	bool bank_delay_support;
-	enum sdw_p15_behave p15_behave;
 	bool lane_control_support;
+	enum sdw_p15_behave p15_behave;
 	u32 master_count;
 	u32 source_ports;
 	u32 sink_ports;
-	struct sdw_dp0_prop *dp0_prop;
-	struct sdw_dpn_prop *src_dpn_prop;
-	struct sdw_dpn_prop *sink_dpn_prop;
-	u8 scp_int1_mask;
 	u32 quirks;
+	u8 scp_int1_mask;
 	bool clock_reg_supported;
 	bool use_domain_irq;
 };

From 557e28f8b53243097162cf4d3e59bcee9fb9713b Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 15:06:42 +0800
Subject: [PATCH 0103/1530] soundwire: optimize sdw_dp0_prop

Move pointers and booleans.

Before:

struct sdw_dp0_prop {
	u32                        max_word;             /*     0     4 */
	u32                        min_word;             /*     4     4 */
	u32                        num_words;            /*     8     4 */

	/* XXX 4 bytes hole, try to pack */

	u32 *                      words;                /*    16     8 */
	bool                       BRA_flow_controlled;  /*    24     1 */
	bool                       simple_ch_prep_sm;    /*    25     1 */

	/* XXX 2 bytes hole, try to pack */

	u32                        ch_prep_timeout;      /*    28     4 */
	bool                       imp_def_interrupts;   /*    32     1 */

	/* size: 40, cachelines: 1, members: 8 */
	/* sum members: 27, holes: 2, sum holes: 6 */
	/* padding: 7 */
	/* last cacheline: 40 bytes */
};

after:

struct sdw_dp0_prop {
	u32 *                      words;                /*     0     8 */
	u32                        max_word;             /*     8     4 */
	u32                        min_word;             /*    12     4 */
	u32                        num_words;            /*    16     4 */
	u32                        ch_prep_timeout;      /*    20     4 */
	bool                       BRA_flow_controlled;  /*    24     1 */
	bool                       simple_ch_prep_sm;    /*    25     1 */
	bool                       imp_def_interrupts;   /*    26     1 */

	/* size: 32, cachelines: 1, members: 8 */
	/* padding: 5 */
	/* last cacheline: 32 bytes */
};

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003070650.62787-7-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 38db81f5bdb97..c72095137a35e 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -226,16 +226,16 @@ enum sdw_clk_stop_mode {
 
 /**
  * struct sdw_dp0_prop - DP0 properties
+ * @words: wordlengths supported
  * @max_word: Maximum number of bits in a Payload Channel Sample, 1 to 64
  * (inclusive)
  * @min_word: Minimum number of bits in a Payload Channel Sample, 1 to 64
  * (inclusive)
  * @num_words: number of wordlengths supported
- * @words: wordlengths supported
+ * @ch_prep_timeout: Port-specific timeout value, in milliseconds
  * @BRA_flow_controlled: Slave implementation results in an OK_NotReady
  * response
  * @simple_ch_prep_sm: If channel prepare sequence is required
- * @ch_prep_timeout: Port-specific timeout value, in milliseconds
  * @imp_def_interrupts: If set, each bit corresponds to support for
  * implementation-defined interrupts
  *
@@ -244,13 +244,13 @@ enum sdw_clk_stop_mode {
  * support
  */
 struct sdw_dp0_prop {
+	u32 *words;
 	u32 max_word;
 	u32 min_word;
 	u32 num_words;
-	u32 *words;
+	u32 ch_prep_timeout;
 	bool BRA_flow_controlled;
 	bool simple_ch_prep_sm;
-	u32 ch_prep_timeout;
 	bool imp_def_interrupts;
 };
 

From 9942f90bdcc035eb5f01d7343dac99bd805ef3ec Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 15:06:43 +0800
Subject: [PATCH 0104/1530] soundwire: optimize sdw_dpn_prop

before:
struct sdw_dpn_prop {
	u32                        num;                  /*     0     4 */
	u32                        max_word;             /*     4     4 */
	u32                        min_word;             /*     8     4 */
	u32                        num_words;            /*    12     4 */
	u32 *                      words;                /*    16     8 */
	enum sdw_dpn_type          type;                 /*    24     4 */
	u32                        max_grouping;         /*    28     4 */
	bool                       simple_ch_prep_sm;    /*    32     1 */

	/* XXX 3 bytes hole, try to pack */

	u32                        ch_prep_timeout;      /*    36     4 */
	u32                        imp_def_interrupts;   /*    40     4 */
	u32                        max_ch;               /*    44     4 */
	u32                        min_ch;               /*    48     4 */
	u32                        num_channels;         /*    52     4 */
	u32 *                      channels;             /*    56     8 */
	/* --- cacheline 1 boundary (64 bytes) --- */
	u32                        num_ch_combinations;  /*    64     4 */

	/* XXX 4 bytes hole, try to pack */

	u32 *                      ch_combinations;      /*    72     8 */
	u32                        modes;                /*    80     4 */
	u32                        max_async_buffer;     /*    84     4 */
	bool                       block_pack_mode;      /*    88     1 */
	bool                       read_only_wordlength; /*    89     1 */

	/* XXX 2 bytes hole, try to pack */

	u32                        port_encoding;        /*    92     4 */
	struct sdw_dpn_audio_mode * audio_modes;         /*    96     8 */

	/* size: 104, cachelines: 2, members: 22 */
	/* sum members: 95, holes: 3, sum holes: 9 */
	/* last cacheline: 40 bytes */
};

after:

struct sdw_dpn_prop {
	struct sdw_dpn_audio_mode * audio_modes;         /*     0     8 */
	u32                        num;                  /*     8     4 */
	u32                        max_word;             /*    12     4 */
	u32                        min_word;             /*    16     4 */
	u32                        num_words;            /*    20     4 */
	u32 *                      words;                /*    24     8 */
	enum sdw_dpn_type          type;                 /*    32     4 */
	u32                        max_grouping;         /*    36     4 */
	u32                        ch_prep_timeout;      /*    40     4 */
	u32                        imp_def_interrupts;   /*    44     4 */
	u32                        max_ch;               /*    48     4 */
	u32                        min_ch;               /*    52     4 */
	u32                        num_channels;         /*    56     4 */
	u32                        num_ch_combinations;  /*    60     4 */
	/* --- cacheline 1 boundary (64 bytes) --- */
	u32 *                      channels;             /*    64     8 */
	u32 *                      ch_combinations;      /*    72     8 */
	u32                        modes;                /*    80     4 */
	u32                        max_async_buffer;     /*    84     4 */
	u32                        port_encoding;        /*    88     4 */
	bool                       block_pack_mode;      /*    92     1 */
	bool                       read_only_wordlength; /*    93     1 */
	bool                       simple_ch_prep_sm;    /*    94     1 */

	/* size: 96, cachelines: 2, members: 22 */
	/* padding: 1 */
	/* last cacheline: 32 bytes */
};

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003070650.62787-8-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index c72095137a35e..cc0afb8af3332 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -288,6 +288,7 @@ struct sdw_dpn_audio_mode {
 
 /**
  * struct sdw_dpn_prop - Data Port DPn properties
+ * @audio_modes: Audio modes supported
  * @num: port number
  * @max_word: Maximum number of bits in a Payload Channel Sample, 1 to 64
  * (inclusive)
@@ -298,26 +299,26 @@ struct sdw_dpn_audio_mode {
  * @type: Data port type. Full, Simplified or Reduced
  * @max_grouping: Maximum number of samples that can be grouped together for
  * a full data port
- * @simple_ch_prep_sm: If the port supports simplified channel prepare state
- * machine
  * @ch_prep_timeout: Port-specific timeout value, in milliseconds
  * @imp_def_interrupts: If set, each bit corresponds to support for
  * implementation-defined interrupts
  * @max_ch: Maximum channels supported
  * @min_ch: Minimum channels supported
  * @num_channels: Number of discrete channels supported
- * @channels: Discrete channels supported
  * @num_ch_combinations: Number of channel combinations supported
+ * @channels: Discrete channels supported
  * @ch_combinations: Channel combinations supported
  * @modes: SDW mode supported
  * @max_async_buffer: Number of samples that this port can buffer in
  * asynchronous modes
+ * @port_encoding: Payload Channel Sample encoding schemes supported
  * @block_pack_mode: Type of block port mode supported
  * @read_only_wordlength: Read Only wordlength field in DPN_BlockCtrl1 register
- * @port_encoding: Payload Channel Sample encoding schemes supported
- * @audio_modes: Audio modes supported
+ * @simple_ch_prep_sm: If the port supports simplified channel prepare state
+ * machine
  */
 struct sdw_dpn_prop {
+	struct sdw_dpn_audio_mode *audio_modes;
 	u32 num;
 	u32 max_word;
 	u32 min_word;
@@ -325,21 +326,20 @@ struct sdw_dpn_prop {
 	u32 *words;
 	enum sdw_dpn_type type;
 	u32 max_grouping;
-	bool simple_ch_prep_sm;
 	u32 ch_prep_timeout;
 	u32 imp_def_interrupts;
 	u32 max_ch;
 	u32 min_ch;
 	u32 num_channels;
-	u32 *channels;
 	u32 num_ch_combinations;
+	u32 *channels;
 	u32 *ch_combinations;
 	u32 modes;
 	u32 max_async_buffer;
+	u32 port_encoding;
 	bool block_pack_mode;
 	bool read_only_wordlength;
-	u32 port_encoding;
-	struct sdw_dpn_audio_mode *audio_modes;
+	bool simple_ch_prep_sm;
 };
 
 /**

From 1ae4aa59d79399be0591c8d78c44e280406e2c34 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 15:06:44 +0800
Subject: [PATCH 0105/1530] soundwire: mipi-disco: remove DPn audio-modes

The concept of DPn audio-modes was never used by anyone, and was
removed from the DisCo for SoundWire 2.0 specification.

Remove the definitions and TODO.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003070650.62787-9-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/mipi_disco.c |  2 --
 include/linux/soundwire/sdw.h  | 34 ----------------------------------
 2 files changed, 36 deletions(-)

diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c
index fdab3d4a1379b..79cf8212f97ad 100644
--- a/drivers/soundwire/mipi_disco.c
+++ b/drivers/soundwire/mipi_disco.c
@@ -304,8 +304,6 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave,
 		fwnode_property_read_u32(node, "mipi-sdw-port-encoding-type",
 					 &dpn[i].port_encoding);
 
-		/* TODO: Read audio mode */
-
 		fwnode_handle_put(node);
 
 		i++;
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index cc0afb8af3332..66feaa79ecfc7 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -254,41 +254,8 @@ struct sdw_dp0_prop {
 	bool imp_def_interrupts;
 };
 
-/**
- * struct sdw_dpn_audio_mode - Audio mode properties for DPn
- * @bus_min_freq: Minimum bus frequency, in Hz
- * @bus_max_freq: Maximum bus frequency, in Hz
- * @bus_num_freq: Number of discrete frequencies supported
- * @bus_freq: Discrete bus frequencies, in Hz
- * @min_freq: Minimum sampling frequency, in Hz
- * @max_freq: Maximum sampling bus frequency, in Hz
- * @num_freq: Number of discrete sampling frequency supported
- * @freq: Discrete sampling frequencies, in Hz
- * @prep_ch_behave: Specifies the dependencies between Channel Prepare
- * sequence and bus clock configuration
- * If 0, Channel Prepare can happen at any Bus clock rate
- * If 1, Channel Prepare sequence shall happen only after Bus clock is
- * changed to a frequency supported by this mode or compatible modes
- * described by the next field
- * @glitchless: Bitmap describing possible glitchless transitions from this
- * Audio Mode to other Audio Modes
- */
-struct sdw_dpn_audio_mode {
-	u32 bus_min_freq;
-	u32 bus_max_freq;
-	u32 bus_num_freq;
-	u32 *bus_freq;
-	u32 max_freq;
-	u32 min_freq;
-	u32 num_freq;
-	u32 *freq;
-	u32 prep_ch_behave;
-	u32 glitchless;
-};
-
 /**
  * struct sdw_dpn_prop - Data Port DPn properties
- * @audio_modes: Audio modes supported
  * @num: port number
  * @max_word: Maximum number of bits in a Payload Channel Sample, 1 to 64
  * (inclusive)
@@ -318,7 +285,6 @@ struct sdw_dpn_audio_mode {
  * machine
  */
 struct sdw_dpn_prop {
-	struct sdw_dpn_audio_mode *audio_modes;
 	u32 num;
 	u32 max_word;
 	u32 min_word;

From a489afc105ed55f7537fb158e40d083ee57a698b Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 15:06:45 +0800
Subject: [PATCH 0106/1530] soundwire: mipi-disco: add error handling for
 property array read

The existing code assumes that there are no possible errors when using
fwnode_property_read_u32_array(), because fwnode_property_count_u32()
reads this array to determine its number of elements. We need to also
protect the second read to be completely bullet-proof.

Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003070650.62787-10-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/mipi_disco.c | 32 ++++++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)

diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c
index 79cf8212f97ad..99253f4c9a38c 100644
--- a/drivers/soundwire/mipi_disco.c
+++ b/drivers/soundwire/mipi_disco.c
@@ -52,7 +52,9 @@ int sdw_master_read_prop(struct sdw_bus *bus)
 	struct sdw_master_prop *prop = &bus->prop;
 	struct fwnode_handle *link;
 	char name[32];
-	int nval, i;
+	int nval;
+	int ret;
+	int i;
 
 	device_property_read_u32(bus->dev,
 				 "mipi-sdw-sw-interface-revision",
@@ -91,9 +93,11 @@ int sdw_master_read_prop(struct sdw_bus *bus)
 			return -ENOMEM;
 		}
 
-		fwnode_property_read_u32_array(link,
+		ret = fwnode_property_read_u32_array(link,
 				"mipi-sdw-clock-frequencies-supported",
 				prop->clk_freq, prop->num_clk_freq);
+		if (ret < 0)
+			return ret;
 	}
 
 	/*
@@ -119,10 +123,12 @@ int sdw_master_read_prop(struct sdw_bus *bus)
 			return -ENOMEM;
 		}
 
-		fwnode_property_read_u32_array(link,
+		ret = fwnode_property_read_u32_array(link,
 					       "mipi-sdw-supported-clock-gears",
 					       prop->clk_gears,
 					       prop->num_clk_gears);
+		if (ret < 0)
+			return ret;
 	}
 
 	fwnode_property_read_u32(link, "mipi-sdw-default-frame-rate",
@@ -151,6 +157,7 @@ static int sdw_slave_read_dp0(struct sdw_slave *slave,
 			      struct sdw_dp0_prop *dp0)
 {
 	int nval;
+	int ret;
 
 	fwnode_property_read_u32(port, "mipi-sdw-port-max-wordlength",
 				 &dp0->max_word);
@@ -168,9 +175,11 @@ static int sdw_slave_read_dp0(struct sdw_slave *slave,
 		if (!dp0->words)
 			return -ENOMEM;
 
-		fwnode_property_read_u32_array(port,
+		ret = fwnode_property_read_u32_array(port,
 				"mipi-sdw-port-wordlength-configs",
 				dp0->words, dp0->num_words);
+		if (ret < 0)
+			return ret;
 	}
 
 	dp0->BRA_flow_controlled = mipi_fwnode_property_read_bool(port,
@@ -191,9 +200,10 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave,
 {
 	struct fwnode_handle *node;
 	u32 bit, i = 0;
-	int nval;
 	unsigned long addr;
 	char name[40];
+	int nval;
+	int ret;
 
 	addr = ports;
 	/* valid ports are 1 to 14 so apply mask */
@@ -228,9 +238,11 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave,
 				return -ENOMEM;
 			}
 
-			fwnode_property_read_u32_array(node,
+			ret = fwnode_property_read_u32_array(node,
 					"mipi-sdw-port-wordlength-configs",
 					dpn[i].words, dpn[i].num_words);
+			if (ret < 0)
+				return ret;
 		}
 
 		fwnode_property_read_u32(node, "mipi-sdw-data-port-type",
@@ -269,9 +281,11 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave,
 				return -ENOMEM;
 			}
 
-			fwnode_property_read_u32_array(node,
+			ret = fwnode_property_read_u32_array(node,
 					"mipi-sdw-channel-number-list",
 					dpn[i].channels, dpn[i].num_channels);
+			if (ret < 0)
+				return ret;
 		}
 
 		nval = fwnode_property_count_u32(node, "mipi-sdw-channel-combination-list");
@@ -286,10 +300,12 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave,
 				return -ENOMEM;
 			}
 
-			fwnode_property_read_u32_array(node,
+			ret = fwnode_property_read_u32_array(node,
 					"mipi-sdw-channel-combination-list",
 					dpn[i].ch_combinations,
 					dpn[i].num_ch_combinations);
+			if (ret < 0)
+				return ret;
 		}
 
 		fwnode_property_read_u32(node,

From 89e95be18de16ed4942bb77b639118abcd085ce4 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 15:06:46 +0800
Subject: [PATCH 0107/1530] soundwire: mipi_disco: add support for clock-scales
 property

The DisCo for SoundWire 2.0 spec adds support for the
'mipi-sdw-supported-clock-scales' property, which is just a
rename. Add in a backwards-compatible manner.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003070650.62787-11-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/mipi_disco.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c
index 99253f4c9a38c..5f42d23bbc850 100644
--- a/drivers/soundwire/mipi_disco.c
+++ b/drivers/soundwire/mipi_disco.c
@@ -51,6 +51,7 @@ int sdw_master_read_prop(struct sdw_bus *bus)
 {
 	struct sdw_master_prop *prop = &bus->prop;
 	struct fwnode_handle *link;
+	const char *scales_prop;
 	char name[32];
 	int nval;
 	int ret;
@@ -112,7 +113,12 @@ int sdw_master_read_prop(struct sdw_bus *bus)
 		}
 	}
 
-	nval = fwnode_property_count_u32(link, "mipi-sdw-supported-clock-gears");
+	scales_prop = "mipi-sdw-supported-clock-scales";
+	nval = fwnode_property_count_u32(link, scales_prop);
+	if (nval == 0) {
+		scales_prop = "mipi-sdw-supported-clock-gears";
+		nval = fwnode_property_count_u32(link, scales_prop);
+	}
 	if (nval > 0) {
 		prop->num_clk_gears = nval;
 		prop->clk_gears = devm_kcalloc(bus->dev, prop->num_clk_gears,
@@ -124,7 +130,7 @@ int sdw_master_read_prop(struct sdw_bus *bus)
 		}
 
 		ret = fwnode_property_read_u32_array(link,
-					       "mipi-sdw-supported-clock-gears",
+					       scales_prop,
 					       prop->clk_gears,
 					       prop->num_clk_gears);
 		if (ret < 0)

From 4b230967c5506b1e55d4fd37722d87fb7aaa1ce7 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 15:06:47 +0800
Subject: [PATCH 0108/1530] soundwire: mipi-disco: add support for peripheral
 channelprepare timeout

The DisCo for SoundWire 2.0 spec renamed the
'mipi-sdw-slave-channelprepare-timeout', add support for the new
definition in backwards-compatible ways.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003070650.62787-12-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/mipi_disco.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c
index 5f42d23bbc850..6feba5631eae8 100644
--- a/drivers/soundwire/mipi_disco.c
+++ b/drivers/soundwire/mipi_disco.c
@@ -344,6 +344,7 @@ int sdw_slave_read_prop(struct sdw_slave *slave)
 	struct device *dev = &slave->dev;
 	struct fwnode_handle *port;
 	int nval;
+	int ret;
 
 	device_property_read_u32(dev, "mipi-sdw-sw-interface-revision",
 				 &prop->mipi_revision);
@@ -366,8 +367,11 @@ int sdw_slave_read_prop(struct sdw_slave *slave)
 	device_property_read_u32(dev, "mipi-sdw-clockstopprepare-timeout",
 				 &prop->clk_stop_timeout);
 
-	device_property_read_u32(dev, "mipi-sdw-slave-channelprepare-timeout",
-				 &prop->ch_prep_timeout);
+	ret = device_property_read_u32(dev, "mipi-sdw-peripheral-channelprepare-timeout",
+				       &prop->ch_prep_timeout);
+	if (ret < 0)
+		device_property_read_u32(dev, "mipi-sdw-slave-channelprepare-timeout",
+					 &prop->ch_prep_timeout);
 
 	device_property_read_u32(dev,
 			"mipi-sdw-clockstopprepare-hard-reset-behavior",

From 1ab88b57bbc2196545a510679e01b1f26158c39b Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 15:06:48 +0800
Subject: [PATCH 0109/1530] soundwire: mipi-disco: add comment on DP0-supported
 property

The DisCo for SoundWire 2.0 spec adds support for a new property, but
it's not very helpful. Add a comment to explain that it's
intentionally ignored.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003070650.62787-13-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/mipi_disco.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c
index 6feba5631eae8..d6eb63bf12525 100644
--- a/drivers/soundwire/mipi_disco.c
+++ b/drivers/soundwire/mipi_disco.c
@@ -398,7 +398,11 @@ int sdw_slave_read_prop(struct sdw_slave *slave)
 	device_property_read_u32(dev, "mipi-sdw-sink-port-list",
 				 &prop->sink_ports);
 
-	/* Read dp0 properties */
+	/*
+	 * Read dp0 properties - we don't rely on the 'mipi-sdw-dp-0-supported'
+	 * property since the 'mipi-sdw-dp0-subproperties' property is logically
+	 * equivalent.
+	 */
 	port = device_get_named_child_node(dev, "mipi-sdw-dp-0-subproperties");
 	if (!port) {
 		dev_dbg(dev, "DP0 node not found!!\n");

From 543bd28a3bfeff31f748ba83348b63313dd37ff9 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 15:06:49 +0800
Subject: [PATCH 0110/1530] soundwire: mipi-disco: add new properties from 2.0
 spec

The DisCo for SoundWire 2.0 spec adds support for new
'mipi-sdw-sdca-interrupt-register-list' and
'mipi-sdw-commit-register-supported'.

This patch only adds the definitions and property reads, but the use
of these properties will come at some point in the future when needed.

Note a slight conceptual disconnect between the MIPI DisCo definition
of a boolean property and the Linux implementation. The latter only
checks the presence of the property to set its value to 'true',
whereas the MIPI definitions allow for a property with a 'false'
value. This patch uses the new introduced mipi_device_property_read_bool()
to handle it.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003070650.62787-14-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/mipi_disco.c | 6 ++++++
 include/linux/soundwire/sdw.h  | 7 ++++++-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c
index d6eb63bf12525..36e734751225c 100644
--- a/drivers/soundwire/mipi_disco.c
+++ b/drivers/soundwire/mipi_disco.c
@@ -398,6 +398,12 @@ int sdw_slave_read_prop(struct sdw_slave *slave)
 	device_property_read_u32(dev, "mipi-sdw-sink-port-list",
 				 &prop->sink_ports);
 
+	device_property_read_u32(dev, "mipi-sdw-sdca-interrupt-register-list",
+				 &prop->sdca_interrupt_register_list);
+
+	prop->commit_register_supported = mipi_device_property_read_bool(dev,
+			"mipi-sdw-commit-register-supported");
+
 	/*
 	 * Read dp0 properties - we don't rely on the 'mipi-sdw-dp-0-supported'
 	 * property since the 'mipi-sdw-dp0-subproperties' property is logically
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 66feaa79ecfc7..952514f044f0d 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -335,8 +335,11 @@ struct sdw_dpn_prop {
  * @master_count: Number of Masters present on this Slave
  * @source_ports: Bitmap identifying source ports
  * @sink_ports: Bitmap identifying sink ports
- * @scp_int1_mask: SCP_INT1_MASK desired settings
  * @quirks: bitmask identifying deltas from the MIPI specification
+ * @sdca_interrupt_register_list: indicates which sets of SDCA interrupt status
+ * and masks are supported
+ * @commit_register_supported: is PCP_Commit register supported
+ * @scp_int1_mask: SCP_INT1_MASK desired settings
  * @clock_reg_supported: the Peripheral implements the clock base and scale
  * registers introduced with the SoundWire 1.2 specification. SDCA devices
  * do not need to set this boolean property as the registers are required.
@@ -363,6 +366,8 @@ struct sdw_slave_prop {
 	u32 source_ports;
 	u32 sink_ports;
 	u32 quirks;
+	u32 sdca_interrupt_register_list;
+	u8 commit_register_supported;
 	u8 scp_int1_mask;
 	bool clock_reg_supported;
 	bool use_domain_irq;

From 71b405b184449fffcb76ea0814104b71dfdb2aee Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 15:06:50 +0800
Subject: [PATCH 0111/1530] soundwire: mipi-disco: add support for DP0/DPn
 'lane-list' property

The SoundWire specification did not clearly require that ports could
use all Lanes. Some SoundWire/SDCA peripheral adopters added
restrictions on which lanes can be used by what port, and the DisCo
for SoundWire 2.1 specification added a 'lane-list' property to model
this hardware limitation.

When not specified, the ports can use all Lanes. Otherwise, the
'lane-list' indicates which Lanes can be used, sorted by order of
preference (most-preferred-first).

This patch only reads the properties, the use of this property will
come at a later time with multi-lane support.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003070650.62787-15-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/mipi_disco.c | 32 ++++++++++++++++++++++++++++++++
 include/linux/soundwire/sdw.h  |  8 ++++++++
 2 files changed, 40 insertions(+)

diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c
index 36e734751225c..9d59f486edbe0 100644
--- a/drivers/soundwire/mipi_disco.c
+++ b/drivers/soundwire/mipi_disco.c
@@ -197,6 +197,22 @@ static int sdw_slave_read_dp0(struct sdw_slave *slave,
 	dp0->imp_def_interrupts = mipi_fwnode_property_read_bool(port,
 				"mipi-sdw-imp-def-dp0-interrupts-supported");
 
+	nval = fwnode_property_count_u32(port, "mipi-sdw-lane-list");
+	if (nval > 0) {
+		dp0->num_lanes = nval;
+		dp0->lane_list = devm_kcalloc(&slave->dev,
+					      dp0->num_lanes, sizeof(*dp0->lane_list),
+					      GFP_KERNEL);
+		if (!dp0->lane_list)
+			return -ENOMEM;
+
+		ret = fwnode_property_read_u32_array(port,
+					       "mipi-sdw-lane-list",
+					       dp0->lane_list, dp0->num_lanes);
+		if (ret < 0)
+			return ret;
+	}
+
 	return 0;
 }
 
@@ -326,6 +342,22 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave,
 		fwnode_property_read_u32(node, "mipi-sdw-port-encoding-type",
 					 &dpn[i].port_encoding);
 
+		nval = fwnode_property_count_u32(node, "mipi-sdw-lane-list");
+		if (nval > 0) {
+			dpn[i].num_lanes = nval;
+			dpn[i].lane_list = devm_kcalloc(&slave->dev,
+							dpn[i].num_lanes, sizeof(*dpn[i].lane_list),
+							GFP_KERNEL);
+			if (!dpn[i].lane_list)
+				return -ENOMEM;
+
+			ret = fwnode_property_read_u32_array(node,
+						       "mipi-sdw-lane-list",
+						       dpn[i].lane_list, dpn[i].num_lanes);
+			if (ret < 0)
+				return ret;
+		}
+
 		fwnode_handle_put(node);
 
 		i++;
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 952514f044f0d..73f655334fe9c 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -238,6 +238,8 @@ enum sdw_clk_stop_mode {
  * @simple_ch_prep_sm: If channel prepare sequence is required
  * @imp_def_interrupts: If set, each bit corresponds to support for
  * implementation-defined interrupts
+ * @num_lanes: array size of @lane_list
+ * @lane_list: indicates which Lanes can be used by DP0
  *
  * The wordlengths are specified by Spec as max, min AND number of
  * discrete values, implementation can define based on the wordlengths they
@@ -252,6 +254,8 @@ struct sdw_dp0_prop {
 	bool BRA_flow_controlled;
 	bool simple_ch_prep_sm;
 	bool imp_def_interrupts;
+	int num_lanes;
+	u32 *lane_list;
 };
 
 /**
@@ -275,6 +279,8 @@ struct sdw_dp0_prop {
  * @num_ch_combinations: Number of channel combinations supported
  * @channels: Discrete channels supported
  * @ch_combinations: Channel combinations supported
+ * @lane_list: indicates which Lanes can be used by DPn
+ * @num_lanes: array size of @lane_list
  * @modes: SDW mode supported
  * @max_async_buffer: Number of samples that this port can buffer in
  * asynchronous modes
@@ -300,6 +306,8 @@ struct sdw_dpn_prop {
 	u32 num_ch_combinations;
 	u32 *channels;
 	u32 *ch_combinations;
+	u32 *lane_list;
+	int num_lanes;
 	u32 modes;
 	u32 max_async_buffer;
 	u32 port_encoding;

From 2f548325ae9d3b34eea98a2fe9160f1c246a6147 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Wed, 2 Oct 2024 22:42:30 +0200
Subject: [PATCH 0112/1530] Input: hideep - add missing dependency on
 REGMAP_I2C

hideep makes use of regmap_i2c, and it has to be selected within its
Kconfig entry to compile successfully.

Fixes: 842ff286166e ("Input: add support for HiDeep touchscreen")
Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20241002-input-hideep-select-remap-i2c-v1-1-6b0fa1dd5fc5@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index 1ac26fc2e3eb9..601fa7ec2e8a3 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -420,6 +420,7 @@ config TOUCHSCREEN_GOODIX_BERLIN_SPI
 config TOUCHSCREEN_HIDEEP
 	tristate "HiDeep Touch IC"
 	depends on I2C
+	select REGMAP_I2C
 	help
 	  Say Y here if you have a touchscreen using HiDeep.
 

From 334ababdd15ca13006741d27f71470cfa7be2542 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Wed, 2 Oct 2024 22:56:37 +0200
Subject: [PATCH 0113/1530] Input: hycon-hy46xx - add missing dependency on
 REGMAP_I2C

hideep makes use of regmap_i2c, and it has to be selected within its
Kconfig entry to compile successfully.

Fixes: aa2f62cf211a ("Input: add driver for the Hycon HY46XX touchpanel series")
Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20241002-input-hycon-hy46xx-select-remap-i2c-v1-1-08f6e83b268a@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index 601fa7ec2e8a3..1a03de7fcfa66 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -432,6 +432,7 @@ config TOUCHSCREEN_HIDEEP
 config TOUCHSCREEN_HYCON_HY46XX
 	tristate "Hycon hy46xx touchscreen support"
 	depends on I2C
+	select REGMAP_I2C
 	help
 	  Say Y here if you have a touchscreen using Hycon hy46xx
 

From d01240b22abf28ce32660c22458457f9b7f5dc1e Mon Sep 17 00:00:00 2001
From: clingfei <clf700383@gmail.com>
Date: Thu, 3 Oct 2024 10:33:07 +0800
Subject: [PATCH 0114/1530] pinctrl: thead1520: Fix Null pointer dereference

pinmux_generic_get_function may return NULL, and its retval is
dereferenced without check, which will cause a NULL pointer
dereference.

Signed-off-by: clingfei <clf700383@gmail.com>
Reviewed-by: Drew Fustini <dfustini@tenstorrent.com>
Link: https://lore.kernel.org/20241003023307.2138695-1-clf700383@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-th1520.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/pinctrl/pinctrl-th1520.c b/drivers/pinctrl/pinctrl-th1520.c
index 1bb78b212fd50..9331f44624809 100644
--- a/drivers/pinctrl/pinctrl-th1520.c
+++ b/drivers/pinctrl/pinctrl-th1520.c
@@ -798,6 +798,8 @@ static int th1520_pinmux_set_mux(struct pinctrl_dev *pctldev,
 	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
 	const struct function_desc *func = pinmux_generic_get_function(pctldev, fsel);
 
+	if (!func)
+		return -EINVAL;
 	return th1520_pinmux_set(thp, thp->desc.pins[gsel].number,
 				 (uintptr_t)thp->desc.pins[gsel].drv_data & TH1520_PAD_MUXDATA,
 				 (uintptr_t)func->data);

From 58414a31c5713afb5449fd74a26a843d34cc62e8 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Thu, 3 Oct 2024 11:23:09 +0200
Subject: [PATCH 0115/1530] pinctrl: freescale: fix COMPILE_TEST error with
 PINCTRL_IMX_SCU

When PINCTRL_IMX_SCU was selected by PINCTRL_IMX8DXL or PINCTRL_IMX8QM
combined with COMPILE_TEST on a non-arm platforms, the IMX_SCU
dependency could not be enabled.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202410031439.GyTSa0kX-lkp@intel.com/
Closes: https://lore.kernel.org/oe-kbuild-all/202410030852.q0Hukplf-lkp@intel.com/
Signed-off-by: Esben Haabendal <esben@geanix.com>
Link: https://lore.kernel.org/20241003-imx-pinctrl-compile-test-fix-v1-1-145ca1948cc3@geanix.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/freescale/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/freescale/Kconfig b/drivers/pinctrl/freescale/Kconfig
index 4486f4a210684..70acfbdd318b0 100644
--- a/drivers/pinctrl/freescale/Kconfig
+++ b/drivers/pinctrl/freescale/Kconfig
@@ -20,7 +20,7 @@ config PINCTRL_IMX_SCMI
 
 config PINCTRL_IMX_SCU
 	tristate
-	depends on IMX_SCU
+	depends on IMX_SCU || COMPILE_TEST
 	select PINCTRL_IMX
 
 config PINCTRL_IMX1_CORE

From c610e95f7769e52ae9f62eb3b5169ee3f7653905 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:26:03 -0700
Subject: [PATCH 0116/1530] Input: psmouse-smbus - use guard notation when
 acquiring mutex

This makes the code more compact and error handling more robust
by ensuring that mutexes are released in all code paths when control
leaves critical section.

Link: https://lore.kernel.org/r/ZsrAa9XcDvHeIs9T@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/psmouse-smbus.c | 28 ++++++++++------------------
 1 file changed, 10 insertions(+), 18 deletions(-)

diff --git a/drivers/input/mouse/psmouse-smbus.c b/drivers/input/mouse/psmouse-smbus.c
index 2a2459b1b4f2c..93420f07b7d07 100644
--- a/drivers/input/mouse/psmouse-smbus.c
+++ b/drivers/input/mouse/psmouse-smbus.c
@@ -35,7 +35,7 @@ static void psmouse_smbus_check_adapter(struct i2c_adapter *adapter)
 	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_HOST_NOTIFY))
 		return;
 
-	mutex_lock(&psmouse_smbus_mutex);
+	guard(mutex)(&psmouse_smbus_mutex);
 
 	list_for_each_entry(smbdev, &psmouse_smbus_list, node) {
 		if (smbdev->dead)
@@ -55,15 +55,13 @@ static void psmouse_smbus_check_adapter(struct i2c_adapter *adapter)
 			    "SMBus candidate adapter appeared, triggering rescan\n");
 		serio_rescan(smbdev->psmouse->ps2dev.serio);
 	}
-
-	mutex_unlock(&psmouse_smbus_mutex);
 }
 
 static void psmouse_smbus_detach_i2c_client(struct i2c_client *client)
 {
 	struct psmouse_smbus_dev *smbdev, *tmp;
 
-	mutex_lock(&psmouse_smbus_mutex);
+	guard(mutex)(&psmouse_smbus_mutex);
 
 	list_for_each_entry_safe(smbdev, tmp, &psmouse_smbus_list, node) {
 		if (smbdev->client != client)
@@ -85,8 +83,6 @@ static void psmouse_smbus_detach_i2c_client(struct i2c_client *client)
 			kfree(smbdev);
 		}
 	}
-
-	mutex_unlock(&psmouse_smbus_mutex);
 }
 
 static int psmouse_smbus_notifier_call(struct notifier_block *nb,
@@ -171,7 +167,7 @@ static void psmouse_smbus_disconnect(struct psmouse *psmouse)
 {
 	struct psmouse_smbus_dev *smbdev = psmouse->private;
 
-	mutex_lock(&psmouse_smbus_mutex);
+	guard(mutex)(&psmouse_smbus_mutex);
 
 	if (smbdev->dead) {
 		list_del(&smbdev->node);
@@ -186,8 +182,6 @@ static void psmouse_smbus_disconnect(struct psmouse *psmouse)
 		psmouse_smbus_schedule_remove(smbdev->client);
 	}
 
-	mutex_unlock(&psmouse_smbus_mutex);
-
 	psmouse->private = NULL;
 }
 
@@ -219,7 +213,7 @@ void psmouse_smbus_cleanup(struct psmouse *psmouse)
 {
 	struct psmouse_smbus_dev *smbdev, *tmp;
 
-	mutex_lock(&psmouse_smbus_mutex);
+	guard(mutex)(&psmouse_smbus_mutex);
 
 	list_for_each_entry_safe(smbdev, tmp, &psmouse_smbus_list, node) {
 		if (psmouse == smbdev->psmouse) {
@@ -227,8 +221,6 @@ void psmouse_smbus_cleanup(struct psmouse *psmouse)
 			kfree(smbdev);
 		}
 	}
-
-	mutex_unlock(&psmouse_smbus_mutex);
 }
 
 int psmouse_smbus_init(struct psmouse *psmouse,
@@ -267,9 +259,9 @@ int psmouse_smbus_init(struct psmouse *psmouse,
 	psmouse->disconnect = psmouse_smbus_disconnect;
 	psmouse->resync_time = 0;
 
-	mutex_lock(&psmouse_smbus_mutex);
-	list_add_tail(&smbdev->node, &psmouse_smbus_list);
-	mutex_unlock(&psmouse_smbus_mutex);
+	scoped_guard(mutex, &psmouse_smbus_mutex) {
+		list_add_tail(&smbdev->node, &psmouse_smbus_list);
+	}
 
 	/* Bind to already existing adapters right away */
 	error = i2c_for_each_dev(smbdev, psmouse_smbus_create_companion);
@@ -293,9 +285,9 @@ int psmouse_smbus_init(struct psmouse *psmouse,
 	smbdev->board.platform_data = NULL;
 
 	if (error < 0 || !leave_breadcrumbs) {
-		mutex_lock(&psmouse_smbus_mutex);
-		list_del(&smbdev->node);
-		mutex_unlock(&psmouse_smbus_mutex);
+		scoped_guard(mutex, &psmouse_smbus_mutex) {
+			list_del(&smbdev->node);
+		}
 
 		kfree(smbdev);
 	}

From 2e26a761619ed437b1e1b22c27eabdffb708c9f2 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:28:43 -0700
Subject: [PATCH 0117/1530] Input: elan_i2c - switch to using cleanup functions

Start using __free() and guard() primitives to simplify the code
and error handling. This makes the code more compact and error
handling more robust by ensuring that locks are released in all
code paths when control leaves critical section and all allocated
memory is freed.

Link: https://lore.kernel.org/r/ZsrBC7qDbOvAaI-W@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/elan_i2c_core.c | 228 ++++++++++++++--------------
 drivers/input/mouse/elan_i2c_i2c.c  |  14 +-
 2 files changed, 121 insertions(+), 121 deletions(-)

diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index ce96513b34f64..ef44bc027c306 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -541,7 +541,8 @@ static int elan_update_firmware(struct elan_tp_data *data,
 
 	dev_dbg(&client->dev, "Starting firmware update....\n");
 
-	disable_irq(client->irq);
+	guard(disable_irq)(&client->irq);
+
 	data->in_fw_update = true;
 
 	retval = __elan_update_firmware(data, fw);
@@ -555,7 +556,6 @@ static int elan_update_firmware(struct elan_tp_data *data,
 	}
 
 	data->in_fw_update = false;
-	enable_irq(client->irq);
 
 	return retval;
 }
@@ -621,8 +621,6 @@ static ssize_t elan_sysfs_update_fw(struct device *dev,
 				    const char *buf, size_t count)
 {
 	struct elan_tp_data *data = dev_get_drvdata(dev);
-	const struct firmware *fw;
-	char *fw_name;
 	int error;
 	const u8 *fw_signature;
 	static const u8 signature[] = {0xAA, 0x55, 0xCC, 0x33, 0xFF, 0xFF};
@@ -631,15 +629,16 @@ static ssize_t elan_sysfs_update_fw(struct device *dev,
 		return -EINVAL;
 
 	/* Look for a firmware with the product id appended. */
-	fw_name = kasprintf(GFP_KERNEL, ETP_FW_NAME, data->product_id);
+	const char *fw_name __free(kfree) =
+		kasprintf(GFP_KERNEL, ETP_FW_NAME, data->product_id);
 	if (!fw_name) {
 		dev_err(dev, "failed to allocate memory for firmware name\n");
 		return -ENOMEM;
 	}
 
 	dev_info(dev, "requesting fw '%s'\n", fw_name);
+	const struct firmware *fw __free(firmware) = NULL;
 	error = request_firmware(&fw, fw_name, dev);
-	kfree(fw_name);
 	if (error) {
 		dev_err(dev, "failed to request firmware: %d\n", error);
 		return error;
@@ -651,46 +650,36 @@ static ssize_t elan_sysfs_update_fw(struct device *dev,
 		dev_err(dev, "signature mismatch (expected %*ph, got %*ph)\n",
 			(int)sizeof(signature), signature,
 			(int)sizeof(signature), fw_signature);
-		error = -EBADF;
-		goto out_release_fw;
+		return -EBADF;
 	}
 
-	error = mutex_lock_interruptible(&data->sysfs_mutex);
-	if (error)
-		goto out_release_fw;
-
-	error = elan_update_firmware(data, fw);
-
-	mutex_unlock(&data->sysfs_mutex);
+	scoped_cond_guard(mutex_intr, return -EINTR, &data->sysfs_mutex) {
+		error = elan_update_firmware(data, fw);
+		if (error)
+			return error;
+	}
 
-out_release_fw:
-	release_firmware(fw);
-	return error ?: count;
+	return count;
 }
 
-static ssize_t calibrate_store(struct device *dev,
-			       struct device_attribute *attr,
-			       const char *buf, size_t count)
+static int elan_calibrate(struct elan_tp_data *data)
 {
-	struct i2c_client *client = to_i2c_client(dev);
-	struct elan_tp_data *data = i2c_get_clientdata(client);
+	struct i2c_client *client = data->client;
+	struct device *dev = &client->dev;
 	int tries = 20;
 	int retval;
 	int error;
 	u8 val[ETP_CALIBRATE_MAX_LEN];
 
-	retval = mutex_lock_interruptible(&data->sysfs_mutex);
-	if (retval)
-		return retval;
-
-	disable_irq(client->irq);
+	guard(disable_irq)(&client->irq);
 
 	data->mode |= ETP_ENABLE_CALIBRATE;
 	retval = data->ops->set_mode(client, data->mode);
 	if (retval) {
+		data->mode &= ~ETP_ENABLE_CALIBRATE;
 		dev_err(dev, "failed to enable calibration mode: %d\n",
 			retval);
-		goto out;
+		return retval;
 	}
 
 	retval = data->ops->calibrate(client);
@@ -728,10 +717,24 @@ static ssize_t calibrate_store(struct device *dev,
 		if (!retval)
 			retval = error;
 	}
-out:
-	enable_irq(client->irq);
-	mutex_unlock(&data->sysfs_mutex);
-	return retval ?: count;
+	return retval;
+}
+
+static ssize_t calibrate_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t count)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct elan_tp_data *data = i2c_get_clientdata(client);
+	int error;
+
+	scoped_cond_guard(mutex_intr, return -EINTR, &data->sysfs_mutex) {
+		error = elan_calibrate(data);
+		if (error)
+			return error;
+	}
+
+	return count;
 }
 
 static ssize_t elan_sysfs_read_mode(struct device *dev,
@@ -743,16 +746,11 @@ static ssize_t elan_sysfs_read_mode(struct device *dev,
 	int error;
 	enum tp_mode mode;
 
-	error = mutex_lock_interruptible(&data->sysfs_mutex);
-	if (error)
-		return error;
-
-	error = data->ops->iap_get_mode(data->client, &mode);
-
-	mutex_unlock(&data->sysfs_mutex);
-
-	if (error)
-		return error;
+	scoped_cond_guard(mutex_intr, return -EINTR, &data->sysfs_mutex) {
+		error = data->ops->iap_get_mode(data->client, &mode);
+		if (error)
+			return error;
+	}
 
 	return sysfs_emit(buf, "%d\n", (int)mode);
 }
@@ -783,44 +781,40 @@ static const struct attribute_group elan_sysfs_group = {
 	.attrs = elan_sysfs_entries,
 };
 
-static ssize_t acquire_store(struct device *dev, struct device_attribute *attr,
-			     const char *buf, size_t count)
+static int elan_acquire_baseline(struct elan_tp_data *data)
 {
-	struct i2c_client *client = to_i2c_client(dev);
-	struct elan_tp_data *data = i2c_get_clientdata(client);
-	int error;
+	struct i2c_client *client = data->client;
+	struct device *dev = &client->dev;
 	int retval;
+	int error;
 
-	retval = mutex_lock_interruptible(&data->sysfs_mutex);
-	if (retval)
-		return retval;
-
-	disable_irq(client->irq);
+	guard(disable_irq)(&client->irq);
 
 	data->baseline_ready = false;
 
 	data->mode |= ETP_ENABLE_CALIBRATE;
-	retval = data->ops->set_mode(data->client, data->mode);
+	retval = data->ops->set_mode(client, data->mode);
 	if (retval) {
+		data->mode &= ~ETP_ENABLE_CALIBRATE;
 		dev_err(dev, "Failed to enable calibration mode to get baseline: %d\n",
 			retval);
-		goto out;
+		return retval;
 	}
 
 	msleep(250);
 
-	retval = data->ops->get_baseline_data(data->client, true,
+	retval = data->ops->get_baseline_data(client, true,
 					      &data->max_baseline);
 	if (retval) {
-		dev_err(dev, "Failed to read max baseline form device: %d\n",
+		dev_err(dev, "Failed to read max baseline from device: %d\n",
 			retval);
 		goto out_disable_calibrate;
 	}
 
-	retval = data->ops->get_baseline_data(data->client, false,
+	retval = data->ops->get_baseline_data(client, false,
 					      &data->min_baseline);
 	if (retval) {
-		dev_err(dev, "Failed to read min baseline form device: %d\n",
+		dev_err(dev, "Failed to read min baseline from device: %d\n",
 			retval);
 		goto out_disable_calibrate;
 	}
@@ -829,17 +823,31 @@ static ssize_t acquire_store(struct device *dev, struct device_attribute *attr,
 
 out_disable_calibrate:
 	data->mode &= ~ETP_ENABLE_CALIBRATE;
-	error = data->ops->set_mode(data->client, data->mode);
+	error = data->ops->set_mode(client, data->mode);
 	if (error) {
 		dev_err(dev, "Failed to disable calibration mode after acquiring baseline: %d\n",
 			error);
 		if (!retval)
 			retval = error;
 	}
-out:
-	enable_irq(client->irq);
-	mutex_unlock(&data->sysfs_mutex);
-	return retval ?: count;
+
+	return retval;
+}
+
+static ssize_t acquire_store(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct elan_tp_data *data = i2c_get_clientdata(client);
+	int error;
+
+	scoped_cond_guard(mutex_intr, return -EINTR, &data->sysfs_mutex) {
+		error = elan_acquire_baseline(data);
+		if (error)
+			return error;
+	}
+
+	return count;
 }
 
 static ssize_t min_show(struct device *dev,
@@ -847,22 +855,15 @@ static ssize_t min_show(struct device *dev,
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct elan_tp_data *data = i2c_get_clientdata(client);
-	int retval;
 
-	retval = mutex_lock_interruptible(&data->sysfs_mutex);
-	if (retval)
-		return retval;
+	scoped_guard(mutex_intr, &data->sysfs_mutex) {
+		if (!data->baseline_ready)
+			return -ENODATA;
 
-	if (!data->baseline_ready) {
-		retval = -ENODATA;
-		goto out;
+		return sysfs_emit(buf, "%d", data->min_baseline);
 	}
 
-	retval = sysfs_emit(buf, "%d", data->min_baseline);
-
-out:
-	mutex_unlock(&data->sysfs_mutex);
-	return retval;
+	return -EINTR;
 }
 
 static ssize_t max_show(struct device *dev,
@@ -870,25 +871,17 @@ static ssize_t max_show(struct device *dev,
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct elan_tp_data *data = i2c_get_clientdata(client);
-	int retval;
 
-	retval = mutex_lock_interruptible(&data->sysfs_mutex);
-	if (retval)
-		return retval;
+	scoped_guard(mutex_intr, &data->sysfs_mutex) {
+		if (!data->baseline_ready)
+			return -ENODATA;
 
-	if (!data->baseline_ready) {
-		retval = -ENODATA;
-		goto out;
+		return sysfs_emit(buf, "%d", data->max_baseline);
 	}
 
-	retval = sysfs_emit(buf, "%d", data->max_baseline);
-
-out:
-	mutex_unlock(&data->sysfs_mutex);
-	return retval;
+	return -EINTR;
 }
 
-
 static DEVICE_ATTR_WO(acquire);
 static DEVICE_ATTR_RO(min);
 static DEVICE_ATTR_RO(max);
@@ -1323,43 +1316,54 @@ static int elan_probe(struct i2c_client *client)
 	return 0;
 }
 
+static int __elan_suspend(struct elan_tp_data *data)
+{
+	struct i2c_client *client = data->client;
+	int error;
+
+	if (device_may_wakeup(&client->dev))
+		return elan_sleep(data);
+
+	/* Touchpad is not a wakeup source */
+	error = elan_set_power(data, false);
+	if (error)
+		return error;
+
+	error = regulator_disable(data->vcc);
+	if (error) {
+		dev_err(&client->dev,
+			"failed to disable regulator when suspending: %d\n",
+			error);
+		/* Attempt to power the chip back up */
+		elan_set_power(data, true);
+		return error;
+	}
+
+	return 0;
+}
+
 static int elan_suspend(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct elan_tp_data *data = i2c_get_clientdata(client);
-	int ret;
+	int error;
 
 	/*
 	 * We are taking the mutex to make sure sysfs operations are
 	 * complete before we attempt to bring the device into low[er]
 	 * power mode.
 	 */
-	ret = mutex_lock_interruptible(&data->sysfs_mutex);
-	if (ret)
-		return ret;
-
-	disable_irq(client->irq);
+	scoped_cond_guard(mutex_intr, return -EINTR, &data->sysfs_mutex) {
+		disable_irq(client->irq);
 
-	if (device_may_wakeup(dev)) {
-		ret = elan_sleep(data);
-	} else {
-		ret = elan_set_power(data, false);
-		if (ret)
-			goto err;
-
-		ret = regulator_disable(data->vcc);
-		if (ret) {
-			dev_err(dev, "error %d disabling regulator\n", ret);
-			/* Attempt to power the chip back up */
-			elan_set_power(data, true);
+		error = __elan_suspend(data);
+		if (error) {
+			enable_irq(client->irq);
+			return error;
 		}
 	}
 
-err:
-	if (ret)
-		enable_irq(client->irq);
-	mutex_unlock(&data->sysfs_mutex);
-	return ret;
+	return 0;
 }
 
 static int elan_resume(struct device *dev)
diff --git a/drivers/input/mouse/elan_i2c_i2c.c b/drivers/input/mouse/elan_i2c_i2c.c
index 13dc097eb6c65..5ed13c8d976e1 100644
--- a/drivers/input/mouse/elan_i2c_i2c.c
+++ b/drivers/input/mouse/elan_i2c_i2c.c
@@ -628,12 +628,11 @@ static int elan_i2c_write_fw_block(struct i2c_client *client, u16 fw_page_size,
 				   const u8 *page, u16 checksum, int idx)
 {
 	struct device *dev = &client->dev;
-	u8 *page_store;
 	u8 val[3];
 	u16 result;
 	int ret, error;
 
-	page_store = kmalloc(fw_page_size + 4, GFP_KERNEL);
+	u8 *page_store __free(kfree) = kmalloc(fw_page_size + 4, GFP_KERNEL);
 	if (!page_store)
 		return -ENOMEM;
 
@@ -647,7 +646,7 @@ static int elan_i2c_write_fw_block(struct i2c_client *client, u16 fw_page_size,
 	if (ret != fw_page_size + 4) {
 		error = ret < 0 ? ret : -EIO;
 		dev_err(dev, "Failed to write page %d: %d\n", idx, error);
-		goto exit;
+		return error;
 	}
 
 	/* Wait for F/W to update one page ROM data. */
@@ -656,20 +655,17 @@ static int elan_i2c_write_fw_block(struct i2c_client *client, u16 fw_page_size,
 	error = elan_i2c_read_cmd(client, ETP_I2C_IAP_CTRL_CMD, val);
 	if (error) {
 		dev_err(dev, "Failed to read IAP write result: %d\n", error);
-		goto exit;
+		return error;
 	}
 
 	result = le16_to_cpup((__le16 *)val);
 	if (result & (ETP_FW_IAP_PAGE_ERR | ETP_FW_IAP_INTF_ERR)) {
 		dev_err(dev, "IAP reports failed write: %04hx\n",
 			result);
-		error = -EIO;
-		goto exit;
+		return -EIO;
 	}
 
-exit:
-	kfree(page_store);
-	return error;
+	return 0;
 }
 
 static int elan_i2c_finish_fw_update(struct i2c_client *client,

From 2e969e5b159d03026d524c334ddad5ddd4435fce Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:16:05 -0700
Subject: [PATCH 0118/1530] Input: adp5589-keys - use guard notation when
 acquiring mutex

This makes the code more compact and error handling more robust
by ensuring that mutexes are released in all code paths when control
leaves critical section.

Link: https://lore.kernel.org/r/20240825051627.2848495-2-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/adp5589-keys.c | 39 +++++++++++++--------------
 1 file changed, 18 insertions(+), 21 deletions(-)

diff --git a/drivers/input/keyboard/adp5589-keys.c b/drivers/input/keyboard/adp5589-keys.c
index 8996e00cd63a8..735d96b056d40 100644
--- a/drivers/input/keyboard/adp5589-keys.c
+++ b/drivers/input/keyboard/adp5589-keys.c
@@ -404,7 +404,7 @@ static void adp5589_gpio_set_value(struct gpio_chip *chip,
 	unsigned int bank = kpad->var->bank(kpad->gpiomap[off]);
 	unsigned int bit = kpad->var->bit(kpad->gpiomap[off]);
 
-	mutex_lock(&kpad->gpio_lock);
+	guard(mutex)(&kpad->gpio_lock);
 
 	if (val)
 		kpad->dat_out[bank] |= bit;
@@ -413,8 +413,6 @@ static void adp5589_gpio_set_value(struct gpio_chip *chip,
 
 	adp5589_write(kpad->client, kpad->var->reg(ADP5589_GPO_DATA_OUT_A) +
 		      bank, kpad->dat_out[bank]);
-
-	mutex_unlock(&kpad->gpio_lock);
 }
 
 static int adp5589_gpio_direction_input(struct gpio_chip *chip, unsigned off)
@@ -422,18 +420,13 @@ static int adp5589_gpio_direction_input(struct gpio_chip *chip, unsigned off)
 	struct adp5589_kpad *kpad = gpiochip_get_data(chip);
 	unsigned int bank = kpad->var->bank(kpad->gpiomap[off]);
 	unsigned int bit = kpad->var->bit(kpad->gpiomap[off]);
-	int ret;
 
-	mutex_lock(&kpad->gpio_lock);
+	guard(mutex)(&kpad->gpio_lock);
 
 	kpad->dir[bank] &= ~bit;
-	ret = adp5589_write(kpad->client,
-			    kpad->var->reg(ADP5589_GPIO_DIRECTION_A) + bank,
-			    kpad->dir[bank]);
-
-	mutex_unlock(&kpad->gpio_lock);
-
-	return ret;
+	return adp5589_write(kpad->client,
+			     kpad->var->reg(ADP5589_GPIO_DIRECTION_A) + bank,
+			     kpad->dir[bank]);
 }
 
 static int adp5589_gpio_direction_output(struct gpio_chip *chip,
@@ -442,9 +435,9 @@ static int adp5589_gpio_direction_output(struct gpio_chip *chip,
 	struct adp5589_kpad *kpad = gpiochip_get_data(chip);
 	unsigned int bank = kpad->var->bank(kpad->gpiomap[off]);
 	unsigned int bit = kpad->var->bit(kpad->gpiomap[off]);
-	int ret;
+	int error;
 
-	mutex_lock(&kpad->gpio_lock);
+	guard(mutex)(&kpad->gpio_lock);
 
 	kpad->dir[bank] |= bit;
 
@@ -453,15 +446,19 @@ static int adp5589_gpio_direction_output(struct gpio_chip *chip,
 	else
 		kpad->dat_out[bank] &= ~bit;
 
-	ret = adp5589_write(kpad->client, kpad->var->reg(ADP5589_GPO_DATA_OUT_A)
-			    + bank, kpad->dat_out[bank]);
-	ret |= adp5589_write(kpad->client,
-			     kpad->var->reg(ADP5589_GPIO_DIRECTION_A) + bank,
-			     kpad->dir[bank]);
+	error = adp5589_write(kpad->client,
+			      kpad->var->reg(ADP5589_GPO_DATA_OUT_A) + bank,
+			      kpad->dat_out[bank]);
+	if (error)
+		return error;
 
-	mutex_unlock(&kpad->gpio_lock);
+	error = adp5589_write(kpad->client,
+			      kpad->var->reg(ADP5589_GPIO_DIRECTION_A) + bank,
+			      kpad->dir[bank]);
+	if (error)
+		return error;
 
-	return ret;
+	return 0;
 }
 
 static int adp5589_build_gpiomap(struct adp5589_kpad *kpad,

From 932fc59b30eea5764aa4f1afc63521277258dd36 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:16:06 -0700
Subject: [PATCH 0119/1530] Input: applespi - use guard notation when acquiring
 spinlock

This makes the code more compact and error handling more robust
by ensuring that locks are released in all code paths when control
leaves critical section.

Link: https://lore.kernel.org/r/20240825051627.2848495-3-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/applespi.c | 72 ++++++++-----------------------
 1 file changed, 18 insertions(+), 54 deletions(-)

diff --git a/drivers/input/keyboard/applespi.c b/drivers/input/keyboard/applespi.c
index cf25177b48301..501ce8154786e 100644
--- a/drivers/input/keyboard/applespi.c
+++ b/drivers/input/keyboard/applespi.c
@@ -717,9 +717,7 @@ static int applespi_send_cmd_msg(struct applespi_data *applespi);
 static void applespi_msg_complete(struct applespi_data *applespi,
 				  bool is_write_msg, bool is_read_compl)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&applespi->cmd_msg_lock, flags);
+	guard(spinlock_irqsave)(&applespi->cmd_msg_lock);
 
 	if (is_read_compl)
 		applespi->read_active = false;
@@ -733,8 +731,6 @@ static void applespi_msg_complete(struct applespi_data *applespi,
 		applespi->cmd_msg_queued = 0;
 		applespi_send_cmd_msg(applespi);
 	}
-
-	spin_unlock_irqrestore(&applespi->cmd_msg_lock, flags);
 }
 
 static void applespi_async_write_complete(void *context)
@@ -888,33 +884,22 @@ static int applespi_send_cmd_msg(struct applespi_data *applespi)
 
 static void applespi_init(struct applespi_data *applespi, bool is_resume)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&applespi->cmd_msg_lock, flags);
+	guard(spinlock_irqsave)(&applespi->cmd_msg_lock);
 
 	if (is_resume)
 		applespi->want_mt_init_cmd = true;
 	else
 		applespi->want_tp_info_cmd = true;
 	applespi_send_cmd_msg(applespi);
-
-	spin_unlock_irqrestore(&applespi->cmd_msg_lock, flags);
 }
 
 static int applespi_set_capsl_led(struct applespi_data *applespi,
 				  bool capslock_on)
 {
-	unsigned long flags;
-	int sts;
-
-	spin_lock_irqsave(&applespi->cmd_msg_lock, flags);
+	guard(spinlock_irqsave)(&applespi->cmd_msg_lock);
 
 	applespi->want_cl_led_on = capslock_on;
-	sts = applespi_send_cmd_msg(applespi);
-
-	spin_unlock_irqrestore(&applespi->cmd_msg_lock, flags);
-
-	return sts;
+	return applespi_send_cmd_msg(applespi);
 }
 
 static void applespi_set_bl_level(struct led_classdev *led_cdev,
@@ -922,9 +907,8 @@ static void applespi_set_bl_level(struct led_classdev *led_cdev,
 {
 	struct applespi_data *applespi =
 		container_of(led_cdev, struct applespi_data, backlight_info);
-	unsigned long flags;
 
-	spin_lock_irqsave(&applespi->cmd_msg_lock, flags);
+	guard(spinlock_irqsave)(&applespi->cmd_msg_lock);
 
 	if (value == 0) {
 		applespi->want_bl_level = value;
@@ -940,8 +924,6 @@ static void applespi_set_bl_level(struct led_classdev *led_cdev,
 	}
 
 	applespi_send_cmd_msg(applespi);
-
-	spin_unlock_irqrestore(&applespi->cmd_msg_lock, flags);
 }
 
 static int applespi_event(struct input_dev *dev, unsigned int type,
@@ -1428,9 +1410,7 @@ static void applespi_got_data(struct applespi_data *applespi)
 	/* process packet header */
 	if (!applespi_verify_crc(applespi, applespi->rx_buffer,
 				 APPLESPI_PACKET_SIZE)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&applespi->cmd_msg_lock, flags);
+		guard(spinlock_irqsave)(&applespi->cmd_msg_lock);
 
 		if (applespi->drain) {
 			applespi->read_active = false;
@@ -1439,8 +1419,6 @@ static void applespi_got_data(struct applespi_data *applespi)
 			wake_up_all(&applespi->drain_complete);
 		}
 
-		spin_unlock_irqrestore(&applespi->cmd_msg_lock, flags);
-
 		return;
 	}
 
@@ -1573,11 +1551,10 @@ static u32 applespi_notify(acpi_handle gpe_device, u32 gpe, void *context)
 {
 	struct applespi_data *applespi = context;
 	int sts;
-	unsigned long flags;
 
 	trace_applespi_irq_received(ET_RD_IRQ, PT_READ);
 
-	spin_lock_irqsave(&applespi->cmd_msg_lock, flags);
+	guard(spinlock_irqsave)(&applespi->cmd_msg_lock);
 
 	if (!applespi->suspended) {
 		sts = applespi_async(applespi, &applespi->rd_m,
@@ -1590,8 +1567,6 @@ static u32 applespi_notify(acpi_handle gpe_device, u32 gpe, void *context)
 			applespi->read_active = true;
 	}
 
-	spin_unlock_irqrestore(&applespi->cmd_msg_lock, flags);
-
 	return ACPI_INTERRUPT_HANDLED;
 }
 
@@ -1819,29 +1794,21 @@ static int applespi_probe(struct spi_device *spi)
 
 static void applespi_drain_writes(struct applespi_data *applespi)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&applespi->cmd_msg_lock, flags);
+	guard(spinlock_irqsave)(&applespi->cmd_msg_lock);
 
 	applespi->drain = true;
 	wait_event_lock_irq(applespi->drain_complete, !applespi->write_active,
 			    applespi->cmd_msg_lock);
-
-	spin_unlock_irqrestore(&applespi->cmd_msg_lock, flags);
 }
 
 static void applespi_drain_reads(struct applespi_data *applespi)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&applespi->cmd_msg_lock, flags);
+	guard(spinlock_irqsave)(&applespi->cmd_msg_lock);
 
 	wait_event_lock_irq(applespi->drain_complete, !applespi->read_active,
 			    applespi->cmd_msg_lock);
 
 	applespi->suspended = true;
-
-	spin_unlock_irqrestore(&applespi->cmd_msg_lock, flags);
 }
 
 static void applespi_remove(struct spi_device *spi)
@@ -1908,21 +1875,18 @@ static int applespi_resume(struct device *dev)
 	struct spi_device *spi = to_spi_device(dev);
 	struct applespi_data *applespi = spi_get_drvdata(spi);
 	acpi_status acpi_sts;
-	unsigned long flags;
 
 	/* ensure our flags and state reflect a newly resumed device */
-	spin_lock_irqsave(&applespi->cmd_msg_lock, flags);
-
-	applespi->drain = false;
-	applespi->have_cl_led_on = false;
-	applespi->have_bl_level = 0;
-	applespi->cmd_msg_queued = 0;
-	applespi->read_active = false;
-	applespi->write_active = false;
-
-	applespi->suspended = false;
+	scoped_guard(spinlock_irqsave, &applespi->cmd_msg_lock) {
+		applespi->drain = false;
+		applespi->have_cl_led_on = false;
+		applespi->have_bl_level = 0;
+		applespi->cmd_msg_queued = 0;
+		applespi->read_active = false;
+		applespi->write_active = false;
 
-	spin_unlock_irqrestore(&applespi->cmd_msg_lock, flags);
+		applespi->suspended = false;
+	}
 
 	/* switch on the SPI interface */
 	applespi_enable_spi(applespi);

From 946a48090e71bd7915c159031cf24078a9403754 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:16:08 -0700
Subject: [PATCH 0120/1530] Input: ep93xx_keypad - use guard notation when
 acquiring mutex

This makes the code more compact and error handling more robust
by ensuring that mutexes are released in all code paths when control
leaves critical section.

Link: https://lore.kernel.org/r/20240825051627.2848495-5-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/ep93xx_keypad.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/input/keyboard/ep93xx_keypad.c b/drivers/input/keyboard/ep93xx_keypad.c
index 6b811d6bf6258..a8df957ef261b 100644
--- a/drivers/input/keyboard/ep93xx_keypad.c
+++ b/drivers/input/keyboard/ep93xx_keypad.c
@@ -184,15 +184,13 @@ static int ep93xx_keypad_suspend(struct device *dev)
 	struct ep93xx_keypad *keypad = platform_get_drvdata(pdev);
 	struct input_dev *input_dev = keypad->input_dev;
 
-	mutex_lock(&input_dev->mutex);
+	guard(mutex)(&input_dev->mutex);
 
 	if (keypad->enabled) {
 		clk_disable(keypad->clk);
 		keypad->enabled = false;
 	}
 
-	mutex_unlock(&input_dev->mutex);
-
 	return 0;
 }
 
@@ -202,7 +200,7 @@ static int ep93xx_keypad_resume(struct device *dev)
 	struct ep93xx_keypad *keypad = platform_get_drvdata(pdev);
 	struct input_dev *input_dev = keypad->input_dev;
 
-	mutex_lock(&input_dev->mutex);
+	guard(mutex)(&input_dev->mutex);
 
 	if (input_device_enabled(input_dev)) {
 		if (!keypad->enabled) {
@@ -212,8 +210,6 @@ static int ep93xx_keypad_resume(struct device *dev)
 		}
 	}
 
-	mutex_unlock(&input_dev->mutex);
-
 	return 0;
 }
 

From 2f39a9fc876e965d79a1ee097f06af87607b9fec Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:16:10 -0700
Subject: [PATCH 0121/1530] Input: imx_keypad - use guard notation when
 acquiring mutex

This makes the code more compact and error handling more robust
by ensuring that mutexes are released in all code paths when control
leaves critical section.

Link: https://lore.kernel.org/r/20240825051627.2848495-7-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/imx_keypad.c | 27 +++++++++++----------------
 1 file changed, 11 insertions(+), 16 deletions(-)

diff --git a/drivers/input/keyboard/imx_keypad.c b/drivers/input/keyboard/imx_keypad.c
index e15a93619e827..b92268ddfd842 100644
--- a/drivers/input/keyboard/imx_keypad.c
+++ b/drivers/input/keyboard/imx_keypad.c
@@ -521,13 +521,11 @@ static int __maybe_unused imx_kbd_noirq_suspend(struct device *dev)
 	struct input_dev *input_dev = kbd->input_dev;
 	unsigned short reg_val = readw(kbd->mmio_base + KPSR);
 
-	/* imx kbd can wake up system even clock is disabled */
-	mutex_lock(&input_dev->mutex);
-
-	if (input_device_enabled(input_dev))
-		clk_disable_unprepare(kbd->clk);
-
-	mutex_unlock(&input_dev->mutex);
+	scoped_guard(mutex, &input_dev->mutex) {
+		/* imx kbd can wake up system even clock is disabled */
+		if (input_device_enabled(input_dev))
+			clk_disable_unprepare(kbd->clk);
+	}
 
 	if (device_may_wakeup(&pdev->dev)) {
 		if (reg_val & KBD_STAT_KPKD)
@@ -547,23 +545,20 @@ static int __maybe_unused imx_kbd_noirq_resume(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct imx_keypad *kbd = platform_get_drvdata(pdev);
 	struct input_dev *input_dev = kbd->input_dev;
-	int ret = 0;
+	int error;
 
 	if (device_may_wakeup(&pdev->dev))
 		disable_irq_wake(kbd->irq);
 
-	mutex_lock(&input_dev->mutex);
+	guard(mutex)(&input_dev->mutex);
 
 	if (input_device_enabled(input_dev)) {
-		ret = clk_prepare_enable(kbd->clk);
-		if (ret)
-			goto err_clk;
+		error = clk_prepare_enable(kbd->clk);
+		if (error)
+			return error;
 	}
 
-err_clk:
-	mutex_unlock(&input_dev->mutex);
-
-	return ret;
+	return 0;
 }
 
 static const struct dev_pm_ops imx_kbd_pm_ops = {

From d1212ac94e8168eb6f8d317d59303c7752f615ff Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:16:11 -0700
Subject: [PATCH 0122/1530] Input: ipaq-micro-keys - use guard notation when
 acquiring mutex and spinlock

This makes the code more compact and error handling more robust
by ensuring that locks are released in all code paths when control
leaves critical section.

Link: https://lore.kernel.org/r/20240825051627.2848495-8-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/ipaq-micro-keys.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/input/keyboard/ipaq-micro-keys.c b/drivers/input/keyboard/ipaq-micro-keys.c
index 1d71dd79ffd28..58631bf7ce556 100644
--- a/drivers/input/keyboard/ipaq-micro-keys.c
+++ b/drivers/input/keyboard/ipaq-micro-keys.c
@@ -54,18 +54,18 @@ static void micro_key_receive(void *data, int len, unsigned char *msg)
 
 static void micro_key_start(struct ipaq_micro_keys *keys)
 {
-	spin_lock(&keys->micro->lock);
+	guard(spinlock)(&keys->micro->lock);
+
 	keys->micro->key = micro_key_receive;
 	keys->micro->key_data = keys;
-	spin_unlock(&keys->micro->lock);
 }
 
 static void micro_key_stop(struct ipaq_micro_keys *keys)
 {
-	spin_lock(&keys->micro->lock);
+	guard(spinlock)(&keys->micro->lock);
+
 	keys->micro->key = NULL;
 	keys->micro->key_data = NULL;
-	spin_unlock(&keys->micro->lock);
 }
 
 static int micro_key_open(struct input_dev *input)
@@ -141,13 +141,11 @@ static int micro_key_resume(struct device *dev)
 	struct ipaq_micro_keys *keys = dev_get_drvdata(dev);
 	struct input_dev *input = keys->input;
 
-	mutex_lock(&input->mutex);
+	guard(mutex)(&input->mutex);
 
 	if (input_device_enabled(input))
 		micro_key_start(keys);
 
-	mutex_unlock(&input->mutex);
-
 	return 0;
 }
 

From 02e4f823ce7838321b0c554ab000e1ceb5849c4e Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:16:13 -0700
Subject: [PATCH 0123/1530] Input: lm8323 - use guard notation when acquiring
 mutexes

This makes the code more compact and error handling more robust
by ensuring that mutexes are released in all code paths when control
leaves critical section.

Link: https://lore.kernel.org/r/20240825051627.2848495-10-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/lm8323.c | 49 +++++++++++++++------------------
 1 file changed, 22 insertions(+), 27 deletions(-)

diff --git a/drivers/input/keyboard/lm8323.c b/drivers/input/keyboard/lm8323.c
index cf67ba13477a4..e26bf29563446 100644
--- a/drivers/input/keyboard/lm8323.c
+++ b/drivers/input/keyboard/lm8323.c
@@ -350,11 +350,11 @@ static int lm8323_configure(struct lm8323_chip *lm)
 
 static void pwm_done(struct lm8323_pwm *pwm)
 {
-	mutex_lock(&pwm->lock);
+	guard(mutex)(&pwm->lock);
+
 	pwm->running = false;
 	if (pwm->desired_brightness != pwm->brightness)
 		schedule_work(&pwm->work);
-	mutex_unlock(&pwm->lock);
 }
 
 /*
@@ -367,7 +367,7 @@ static irqreturn_t lm8323_irq(int irq, void *_lm)
 	u8 ints;
 	int i;
 
-	mutex_lock(&lm->lock);
+	guard(mutex)(&lm->lock);
 
 	while ((lm8323_read(lm, LM8323_CMD_READ_INT, &ints, 1) == 1) && ints) {
 		if (likely(ints & INT_KEYPAD))
@@ -394,8 +394,6 @@ static irqreturn_t lm8323_irq(int irq, void *_lm)
 		}
 	}
 
-	mutex_unlock(&lm->lock);
-
 	return IRQ_HANDLED;
 }
 
@@ -445,7 +443,7 @@ static void lm8323_pwm_work(struct work_struct *work)
 	u16 pwm_cmds[3];
 	int num_cmds = 0;
 
-	mutex_lock(&pwm->lock);
+	guard(mutex)(&pwm->lock);
 
 	/*
 	 * Do nothing if we're already at the requested level,
@@ -454,7 +452,7 @@ static void lm8323_pwm_work(struct work_struct *work)
 	 * finishes.
 	 */
 	if (pwm->running || pwm->desired_brightness == pwm->brightness)
-		goto out;
+		return;
 
 	kill = (pwm->desired_brightness == 0);
 	up = (pwm->desired_brightness > pwm->brightness);
@@ -489,9 +487,6 @@ static void lm8323_pwm_work(struct work_struct *work)
 
 	lm8323_write_pwm(pwm, kill, num_cmds, pwm_cmds);
 	pwm->brightness = pwm->desired_brightness;
-
- out:
-	mutex_unlock(&pwm->lock);
 }
 
 static void lm8323_pwm_set_brightness(struct led_classdev *led_cdev,
@@ -500,9 +495,9 @@ static void lm8323_pwm_set_brightness(struct led_classdev *led_cdev,
 	struct lm8323_pwm *pwm = cdev_to_pwm(led_cdev);
 	struct lm8323_chip *lm = pwm->chip;
 
-	mutex_lock(&pwm->lock);
-	pwm->desired_brightness = brightness;
-	mutex_unlock(&pwm->lock);
+	scoped_guard(mutex, &pwm->lock) {
+		pwm->desired_brightness = brightness;
+	}
 
 	if (in_interrupt()) {
 		schedule_work(&pwm->work);
@@ -510,12 +505,12 @@ static void lm8323_pwm_set_brightness(struct led_classdev *led_cdev,
 		/*
 		 * Schedule PWM work as usual unless we are going into suspend
 		 */
-		mutex_lock(&lm->lock);
-		if (likely(!lm->pm_suspend))
-			schedule_work(&pwm->work);
-		else
-			lm8323_pwm_work(&pwm->work);
-		mutex_unlock(&lm->lock);
+		scoped_guard(mutex, &lm->lock) {
+			if (likely(!lm->pm_suspend))
+				schedule_work(&pwm->work);
+			else
+				lm8323_pwm_work(&pwm->work);
+		}
 	}
 }
 
@@ -608,9 +603,9 @@ static ssize_t lm8323_set_disable(struct device *dev,
 	if (ret)
 		return ret;
 
-	mutex_lock(&lm->lock);
+	guard(mutex)(&lm->lock);
+
 	lm->kp_enabled = !i;
-	mutex_unlock(&lm->lock);
 
 	return count;
 }
@@ -758,9 +753,9 @@ static int lm8323_suspend(struct device *dev)
 	irq_set_irq_wake(client->irq, 0);
 	disable_irq(client->irq);
 
-	mutex_lock(&lm->lock);
-	lm->pm_suspend = true;
-	mutex_unlock(&lm->lock);
+	scoped_guard(mutex, &lm->lock) {
+		lm->pm_suspend = true;
+	}
 
 	for (i = 0; i < 3; i++)
 		if (lm->pwm[i].enabled)
@@ -775,9 +770,9 @@ static int lm8323_resume(struct device *dev)
 	struct lm8323_chip *lm = i2c_get_clientdata(client);
 	int i;
 
-	mutex_lock(&lm->lock);
-	lm->pm_suspend = false;
-	mutex_unlock(&lm->lock);
+	scoped_guard(mutex, &lm->lock) {
+		lm->pm_suspend = false;
+	}
 
 	for (i = 0; i < 3; i++)
 		if (lm->pwm[i].enabled)

From e9495ead523f5d44d149c10ce30eba8e6f375ce5 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:16:14 -0700
Subject: [PATCH 0124/1530] Input: lpc32xx-keys - use guard notation when
 acquiring mutex

This makes the code more compact and error handling more robust
by ensuring that mutexes are released in all code paths when control
leaves critical section.

Link: https://lore.kernel.org/r/20240825051627.2848495-11-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/lpc32xx-keys.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/input/keyboard/lpc32xx-keys.c b/drivers/input/keyboard/lpc32xx-keys.c
index 423035be86fb8..2392e7ec3b191 100644
--- a/drivers/input/keyboard/lpc32xx-keys.c
+++ b/drivers/input/keyboard/lpc32xx-keys.c
@@ -262,7 +262,7 @@ static int lpc32xx_kscan_suspend(struct device *dev)
 	struct lpc32xx_kscan_drv *kscandat = platform_get_drvdata(pdev);
 	struct input_dev *input = kscandat->input;
 
-	mutex_lock(&input->mutex);
+	guard(mutex)(&input->mutex);
 
 	if (input_device_enabled(input)) {
 		/* Clear IRQ and disable clock */
@@ -270,7 +270,6 @@ static int lpc32xx_kscan_suspend(struct device *dev)
 		clk_disable_unprepare(kscandat->clk);
 	}
 
-	mutex_unlock(&input->mutex);
 	return 0;
 }
 
@@ -279,19 +278,20 @@ static int lpc32xx_kscan_resume(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct lpc32xx_kscan_drv *kscandat = platform_get_drvdata(pdev);
 	struct input_dev *input = kscandat->input;
-	int retval = 0;
+	int error;
 
-	mutex_lock(&input->mutex);
+	guard(mutex)(&input->mutex);
 
 	if (input_device_enabled(input)) {
 		/* Enable clock and clear IRQ */
-		retval = clk_prepare_enable(kscandat->clk);
-		if (retval == 0)
-			writel(1, LPC32XX_KS_IRQ(kscandat->kscan_base));
+		error = clk_prepare_enable(kscandat->clk);
+		if (error)
+			return error;
+
+		writel(1, LPC32XX_KS_IRQ(kscandat->kscan_base));
 	}
 
-	mutex_unlock(&input->mutex);
-	return retval;
+	return 0;
 }
 
 static DEFINE_SIMPLE_DEV_PM_OPS(lpc32xx_kscan_pm_ops, lpc32xx_kscan_suspend,

From 405b1762aef34e4bc8f39ce20ad27e2d336bbe27 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:16:15 -0700
Subject: [PATCH 0125/1530] Input: matrix_keypad - use guard notation when
 acquiring spinlock

This makes the code more compact and error handling more robust
by ensuring that locks are released in all code paths when control
leaves critical section.

Link: https://lore.kernel.org/r/20240825051627.2848495-12-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/matrix_keypad.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/input/keyboard/matrix_keypad.c b/drivers/input/keyboard/matrix_keypad.c
index 3c38bae576edd..a6bccb28d0794 100644
--- a/drivers/input/keyboard/matrix_keypad.c
+++ b/drivers/input/keyboard/matrix_keypad.c
@@ -158,18 +158,17 @@ static void matrix_keypad_scan(struct work_struct *work)
 	activate_all_cols(keypad, true);
 
 	/* Enable IRQs again */
-	spin_lock_irq(&keypad->lock);
-	keypad->scan_pending = false;
-	enable_row_irqs(keypad);
-	spin_unlock_irq(&keypad->lock);
+	scoped_guard(spinlock_irq, &keypad->lock) {
+		keypad->scan_pending = false;
+		enable_row_irqs(keypad);
+	}
 }
 
 static irqreturn_t matrix_keypad_interrupt(int irq, void *id)
 {
 	struct matrix_keypad *keypad = id;
-	unsigned long flags;
 
-	spin_lock_irqsave(&keypad->lock, flags);
+	guard(spinlock_irqsave)(&keypad->lock);
 
 	/*
 	 * See if another IRQ beaten us to it and scheduled the
@@ -185,7 +184,6 @@ static irqreturn_t matrix_keypad_interrupt(int irq, void *id)
 			      msecs_to_jiffies(keypad->debounce_ms));
 
 out:
-	spin_unlock_irqrestore(&keypad->lock, flags);
 	return IRQ_HANDLED;
 }
 
@@ -209,9 +207,9 @@ static void matrix_keypad_stop(struct input_dev *dev)
 {
 	struct matrix_keypad *keypad = input_get_drvdata(dev);
 
-	spin_lock_irq(&keypad->lock);
-	keypad->stopped = true;
-	spin_unlock_irq(&keypad->lock);
+	scoped_guard(spinlock_irq, &keypad->lock) {
+		keypad->stopped = true;
+	}
 
 	flush_delayed_work(&keypad->work);
 	/*

From a49e229319b1dd7007ede184884cefdf0da6df48 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:16:16 -0700
Subject: [PATCH 0126/1530] Input: omap4-keypad - use guard notation when
 acquiring mutex

This makes the code more compact and error handling more robust
by ensuring that mutexes are released in all code paths when control
leaves critical section.

Link: https://lore.kernel.org/r/20240825051627.2848495-13-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/omap4-keypad.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c
index 040b340995d89..935c2b27b81c2 100644
--- a/drivers/input/keyboard/omap4-keypad.c
+++ b/drivers/input/keyboard/omap4-keypad.c
@@ -144,7 +144,7 @@ static void omap4_keypad_scan_keys(struct omap4_keypad *keypad_data, u64 keys)
 {
 	u64 changed;
 
-	mutex_lock(&keypad_data->lock);
+	guard(mutex)(&keypad_data->lock);
 
 	changed = keys ^ keypad_data->keys;
 
@@ -158,8 +158,6 @@ static void omap4_keypad_scan_keys(struct omap4_keypad *keypad_data, u64 keys)
 	omap4_keypad_report_keys(keypad_data, changed & keys, true);
 
 	keypad_data->keys = keys;
-
-	mutex_unlock(&keypad_data->lock);
 }
 
 /* Interrupt handlers */

From 9e09354cb6f6858e3e54627c2e4f49d07bfae45e Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:16:17 -0700
Subject: [PATCH 0127/1530] Input: pmic8xxx-keypad - use guard notation when
 acquiring mutex

This makes the code more compact and error handling more robust
by ensuring that mutexes are released in all code paths when control
leaves critical section.

Link: https://lore.kernel.org/r/20240825051627.2848495-14-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/pmic8xxx-keypad.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/input/keyboard/pmic8xxx-keypad.c b/drivers/input/keyboard/pmic8xxx-keypad.c
index 26a005f9ace3b..35d1aa2a22a55 100644
--- a/drivers/input/keyboard/pmic8xxx-keypad.c
+++ b/drivers/input/keyboard/pmic8xxx-keypad.c
@@ -630,12 +630,10 @@ static int pmic8xxx_kp_suspend(struct device *dev)
 	if (device_may_wakeup(dev)) {
 		enable_irq_wake(kp->key_sense_irq);
 	} else {
-		mutex_lock(&input_dev->mutex);
+		guard(mutex)(&input_dev->mutex);
 
 		if (input_device_enabled(input_dev))
 			pmic8xxx_kp_disable(kp);
-
-		mutex_unlock(&input_dev->mutex);
 	}
 
 	return 0;
@@ -650,12 +648,10 @@ static int pmic8xxx_kp_resume(struct device *dev)
 	if (device_may_wakeup(dev)) {
 		disable_irq_wake(kp->key_sense_irq);
 	} else {
-		mutex_lock(&input_dev->mutex);
+		guard(mutex)(&input_dev->mutex);
 
 		if (input_device_enabled(input_dev))
 			pmic8xxx_kp_enable(kp);
-
-		mutex_unlock(&input_dev->mutex);
 	}
 
 	return 0;

From b8a3e18141659d72d1b5500e5bcc6b81f19477af Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:16:18 -0700
Subject: [PATCH 0128/1530] Input: pxa27x_keypad - use guard notation when
 acquiring mutex

This makes the code more compact and error handling more robust
by ensuring that mutexes are released in all code paths when control
leaves critical section.

Link: https://lore.kernel.org/r/20240825051627.2848495-15-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/pxa27x_keypad.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/input/keyboard/pxa27x_keypad.c b/drivers/input/keyboard/pxa27x_keypad.c
index 3724363d140e5..38ec619aa3590 100644
--- a/drivers/input/keyboard/pxa27x_keypad.c
+++ b/drivers/input/keyboard/pxa27x_keypad.c
@@ -682,7 +682,7 @@ static int pxa27x_keypad_resume(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct pxa27x_keypad *keypad = platform_get_drvdata(pdev);
 	struct input_dev *input_dev = keypad->input_dev;
-	int ret = 0;
+	int error;
 
 	/*
 	 * If the keypad is used as wake up source, the clock is not turned
@@ -691,19 +691,19 @@ static int pxa27x_keypad_resume(struct device *dev)
 	if (device_may_wakeup(&pdev->dev)) {
 		disable_irq_wake(keypad->irq);
 	} else {
-		mutex_lock(&input_dev->mutex);
+		guard(mutex)(&input_dev->mutex);
 
 		if (input_device_enabled(input_dev)) {
 			/* Enable unit clock */
-			ret = clk_prepare_enable(keypad->clk);
-			if (!ret)
-				pxa27x_keypad_config(keypad);
-		}
+			error = clk_prepare_enable(keypad->clk);
+			if (error)
+				return error;
 
-		mutex_unlock(&input_dev->mutex);
+			pxa27x_keypad_config(keypad);
+		}
 	}
 
-	return ret;
+	return 0;
 }
 
 static DEFINE_SIMPLE_DEV_PM_OPS(pxa27x_keypad_pm_ops,

From f0d822986988f364cb1f08620f28bafe232a6ecf Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:16:19 -0700
Subject: [PATCH 0129/1530] Input: spear-keyboard - use guard notation when
 acquiring mutex

This makes the code more compact and error handling more robust
by ensuring that mutexes are released in all code paths when control
leaves critical section.

Link: https://lore.kernel.org/r/20240825051627.2848495-16-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/spear-keyboard.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/input/keyboard/spear-keyboard.c b/drivers/input/keyboard/spear-keyboard.c
index 1df4feb8ba017..2d3f656e59dc5 100644
--- a/drivers/input/keyboard/spear-keyboard.c
+++ b/drivers/input/keyboard/spear-keyboard.c
@@ -274,7 +274,7 @@ static int spear_kbd_suspend(struct device *dev)
 	struct input_dev *input_dev = kbd->input;
 	unsigned int rate = 0, mode_ctl_reg, val;
 
-	mutex_lock(&input_dev->mutex);
+	guard(mutex)(&input_dev->mutex);
 
 	/* explicitly enable clock as we may program device */
 	clk_enable(kbd->clk);
@@ -315,8 +315,6 @@ static int spear_kbd_suspend(struct device *dev)
 	/* restore previous clk state */
 	clk_disable(kbd->clk);
 
-	mutex_unlock(&input_dev->mutex);
-
 	return 0;
 }
 
@@ -326,7 +324,7 @@ static int spear_kbd_resume(struct device *dev)
 	struct spear_kbd *kbd = platform_get_drvdata(pdev);
 	struct input_dev *input_dev = kbd->input;
 
-	mutex_lock(&input_dev->mutex);
+	guard(mutex)(&input_dev->mutex);
 
 	if (device_may_wakeup(&pdev->dev)) {
 		if (kbd->irq_wake_enabled) {
@@ -342,8 +340,6 @@ static int spear_kbd_resume(struct device *dev)
 	if (input_device_enabled(input_dev))
 		writel_relaxed(kbd->mode_ctl_reg, kbd->io_base + MODE_CTL_REG);
 
-	mutex_unlock(&input_dev->mutex);
-
 	return 0;
 }
 

From b18d9d75dd5996e73fd9dba196cc077f1977f410 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 24 Aug 2024 22:16:20 -0700
Subject: [PATCH 0130/1530] Input: st-keyscan - use guard notation when
 acquiring mutex

This makes the code more compact and error handling more robust
by ensuring that mutexes are released in all code paths when control
leaves critical section.

Link: https://lore.kernel.org/r/20240825051627.2848495-17-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/st-keyscan.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/drivers/input/keyboard/st-keyscan.c b/drivers/input/keyboard/st-keyscan.c
index 0d27324af809b..e53ef4c670e4b 100644
--- a/drivers/input/keyboard/st-keyscan.c
+++ b/drivers/input/keyboard/st-keyscan.c
@@ -216,14 +216,13 @@ static int keyscan_suspend(struct device *dev)
 	struct st_keyscan *keypad = platform_get_drvdata(pdev);
 	struct input_dev *input = keypad->input_dev;
 
-	mutex_lock(&input->mutex);
+	guard(mutex)(&input->mutex);
 
 	if (device_may_wakeup(dev))
 		enable_irq_wake(keypad->irq);
 	else if (input_device_enabled(input))
 		keyscan_stop(keypad);
 
-	mutex_unlock(&input->mutex);
 	return 0;
 }
 
@@ -232,17 +231,19 @@ static int keyscan_resume(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct st_keyscan *keypad = platform_get_drvdata(pdev);
 	struct input_dev *input = keypad->input_dev;
-	int retval = 0;
+	int error;
 
-	mutex_lock(&input->mutex);
+	guard(mutex)(&input->mutex);
 
-	if (device_may_wakeup(dev))
+	if (device_may_wakeup(dev)) {
 		disable_irq_wake(keypad->irq);
-	else if (input_device_enabled(input))
-		retval = keyscan_start(keypad);
+	} else if (input_device_enabled(input)) {
+		error = keyscan_start(keypad);
+		if (error)
+			return error;
+	}
 
-	mutex_unlock(&input->mutex);
-	return retval;
+	return 0;
 }
 
 static DEFINE_SIMPLE_DEV_PM_OPS(keyscan_dev_pm_ops,

From 556cac064c16f5f2eb17d442c1a78797ad2c962f Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:30:58 -0700
Subject: [PATCH 0131/1530] Input: db9 - use guard notation when acquiring
 mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240904043104.1030257-2-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/db9.c | 30 ++++++++++++++----------------
 1 file changed, 14 insertions(+), 16 deletions(-)

diff --git a/drivers/input/joystick/db9.c b/drivers/input/joystick/db9.c
index 6373d7aa739a8..a9f1946cf0d6f 100644
--- a/drivers/input/joystick/db9.c
+++ b/drivers/input/joystick/db9.c
@@ -505,24 +505,22 @@ static int db9_open(struct input_dev *dev)
 {
 	struct db9 *db9 = input_get_drvdata(dev);
 	struct parport *port = db9->pd->port;
-	int err;
 
-	err = mutex_lock_interruptible(&db9->mutex);
-	if (err)
-		return err;
-
-	if (!db9->used++) {
-		parport_claim(db9->pd);
-		parport_write_data(port, 0xff);
-		if (db9_modes[db9->mode].reverse) {
-			parport_data_reverse(port);
-			parport_write_control(port, DB9_NORMAL);
+	scoped_guard(mutex_intr, &db9->mutex) {
+		if (!db9->used++) {
+			parport_claim(db9->pd);
+			parport_write_data(port, 0xff);
+			if (db9_modes[db9->mode].reverse) {
+				parport_data_reverse(port);
+				parport_write_control(port, DB9_NORMAL);
+			}
+			mod_timer(&db9->timer, jiffies + DB9_REFRESH_TIME);
 		}
-		mod_timer(&db9->timer, jiffies + DB9_REFRESH_TIME);
+
+		return 0;
 	}
 
-	mutex_unlock(&db9->mutex);
-	return 0;
+	return -EINTR;
 }
 
 static void db9_close(struct input_dev *dev)
@@ -530,14 +528,14 @@ static void db9_close(struct input_dev *dev)
 	struct db9 *db9 = input_get_drvdata(dev);
 	struct parport *port = db9->pd->port;
 
-	mutex_lock(&db9->mutex);
+	guard(mutex)(&db9->mutex);
+
 	if (!--db9->used) {
 		del_timer_sync(&db9->timer);
 		parport_write_control(port, 0x00);
 		parport_data_forward(port);
 		parport_release(db9->pd);
 	}
-	mutex_unlock(&db9->mutex);
 }
 
 static void db9_attach(struct parport *pp)

From 60bf2f938980cb464dabab11d41eb37c49fe39ca Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:30:59 -0700
Subject: [PATCH 0132/1530] Input: gamecon - use guard notation when acquiring
 mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240904043104.1030257-3-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/gamecon.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/drivers/input/joystick/gamecon.c b/drivers/input/joystick/gamecon.c
index 2b553e2d838f2..b53cafd7a5ee1 100644
--- a/drivers/input/joystick/gamecon.c
+++ b/drivers/input/joystick/gamecon.c
@@ -765,33 +765,31 @@ static void gc_timer(struct timer_list *t)
 static int gc_open(struct input_dev *dev)
 {
 	struct gc *gc = input_get_drvdata(dev);
-	int err;
 
-	err = mutex_lock_interruptible(&gc->mutex);
-	if (err)
-		return err;
+	scoped_guard(mutex_intr, &gc->mutex) {
+		if (!gc->used++) {
+			parport_claim(gc->pd);
+			parport_write_control(gc->pd->port, 0x04);
+			mod_timer(&gc->timer, jiffies + GC_REFRESH_TIME);
+		}
 
-	if (!gc->used++) {
-		parport_claim(gc->pd);
-		parport_write_control(gc->pd->port, 0x04);
-		mod_timer(&gc->timer, jiffies + GC_REFRESH_TIME);
+		return 0;
 	}
 
-	mutex_unlock(&gc->mutex);
-	return 0;
+	return -EINTR;
 }
 
 static void gc_close(struct input_dev *dev)
 {
 	struct gc *gc = input_get_drvdata(dev);
 
-	mutex_lock(&gc->mutex);
+	guard(mutex)(&gc->mutex);
+
 	if (!--gc->used) {
 		del_timer_sync(&gc->timer);
 		parport_write_control(gc->pd->port, 0x00);
 		parport_release(gc->pd);
 	}
-	mutex_unlock(&gc->mutex);
 }
 
 static int gc_setup_pad(struct gc *gc, int idx, int pad_type)

From 63ade96711c7a0bb7226f3b029e800fafccd4b0b Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:31:00 -0700
Subject: [PATCH 0133/1530] Input: iforce - use guard notation when acquiring
 mutex and spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240904043104.1030257-4-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/iforce/iforce-ff.c     | 48 +++++++---------
 .../input/joystick/iforce/iforce-packets.c    | 57 ++++++++-----------
 drivers/input/joystick/iforce/iforce-serio.c  | 36 +++++-------
 drivers/input/joystick/iforce/iforce-usb.c    | 13 ++---
 4 files changed, 68 insertions(+), 86 deletions(-)

diff --git a/drivers/input/joystick/iforce/iforce-ff.c b/drivers/input/joystick/iforce/iforce-ff.c
index 95c0348843e6b..8c78cbe553c8c 100644
--- a/drivers/input/joystick/iforce/iforce-ff.c
+++ b/drivers/input/joystick/iforce/iforce-ff.c
@@ -21,14 +21,13 @@ static int make_magnitude_modifier(struct iforce* iforce,
 	unsigned char data[3];
 
 	if (!no_alloc) {
-		mutex_lock(&iforce->mem_mutex);
-		if (allocate_resource(&(iforce->device_memory), mod_chunk, 2,
-			iforce->device_memory.start, iforce->device_memory.end, 2L,
-			NULL, NULL)) {
-			mutex_unlock(&iforce->mem_mutex);
+		guard(mutex)(&iforce->mem_mutex);
+
+		if (allocate_resource(&iforce->device_memory, mod_chunk, 2,
+				      iforce->device_memory.start,
+				      iforce->device_memory.end,
+				      2L, NULL, NULL))
 			return -ENOSPC;
-		}
-		mutex_unlock(&iforce->mem_mutex);
 	}
 
 	data[0] = LO(mod_chunk->start);
@@ -54,14 +53,13 @@ static int make_period_modifier(struct iforce* iforce,
 	period = TIME_SCALE(period);
 
 	if (!no_alloc) {
-		mutex_lock(&iforce->mem_mutex);
-		if (allocate_resource(&(iforce->device_memory), mod_chunk, 0x0c,
-			iforce->device_memory.start, iforce->device_memory.end, 2L,
-			NULL, NULL)) {
-			mutex_unlock(&iforce->mem_mutex);
+		guard(mutex)(&iforce->mem_mutex);
+
+		if (allocate_resource(&iforce->device_memory, mod_chunk, 0x0c,
+				      iforce->device_memory.start,
+				      iforce->device_memory.end,
+				      2L, NULL, NULL))
 			return -ENOSPC;
-		}
-		mutex_unlock(&iforce->mem_mutex);
 	}
 
 	data[0] = LO(mod_chunk->start);
@@ -94,14 +92,13 @@ static int make_envelope_modifier(struct iforce* iforce,
 	fade_duration = TIME_SCALE(fade_duration);
 
 	if (!no_alloc) {
-		mutex_lock(&iforce->mem_mutex);
+		guard(mutex)(&iforce->mem_mutex);
+
 		if (allocate_resource(&(iforce->device_memory), mod_chunk, 0x0e,
-			iforce->device_memory.start, iforce->device_memory.end, 2L,
-			NULL, NULL)) {
-			mutex_unlock(&iforce->mem_mutex);
+				      iforce->device_memory.start,
+				      iforce->device_memory.end,
+				      2L, NULL, NULL))
 			return -ENOSPC;
-		}
-		mutex_unlock(&iforce->mem_mutex);
 	}
 
 	data[0] = LO(mod_chunk->start);
@@ -131,14 +128,13 @@ static int make_condition_modifier(struct iforce* iforce,
 	unsigned char data[10];
 
 	if (!no_alloc) {
-		mutex_lock(&iforce->mem_mutex);
+		guard(mutex)(&iforce->mem_mutex);
+
 		if (allocate_resource(&(iforce->device_memory), mod_chunk, 8,
-			iforce->device_memory.start, iforce->device_memory.end, 2L,
-			NULL, NULL)) {
-			mutex_unlock(&iforce->mem_mutex);
+				      iforce->device_memory.start,
+				      iforce->device_memory.end,
+				      2L, NULL, NULL))
 			return -ENOSPC;
-		}
-		mutex_unlock(&iforce->mem_mutex);
 	}
 
 	data[0] = LO(mod_chunk->start);
diff --git a/drivers/input/joystick/iforce/iforce-packets.c b/drivers/input/joystick/iforce/iforce-packets.c
index 763642c8cee9f..8c2531e2977c1 100644
--- a/drivers/input/joystick/iforce/iforce-packets.c
+++ b/drivers/input/joystick/iforce/iforce-packets.c
@@ -31,49 +31,42 @@ int iforce_send_packet(struct iforce *iforce, u16 cmd, unsigned char* data)
 	int c;
 	int empty;
 	int head, tail;
-	unsigned long flags;
 
 /*
  * Update head and tail of xmit buffer
  */
-	spin_lock_irqsave(&iforce->xmit_lock, flags);
-
-	head = iforce->xmit.head;
-	tail = iforce->xmit.tail;
-
-
-	if (CIRC_SPACE(head, tail, XMIT_SIZE) < n+2) {
-		dev_warn(&iforce->dev->dev,
-			 "not enough space in xmit buffer to send new packet\n");
-		spin_unlock_irqrestore(&iforce->xmit_lock, flags);
-		return -1;
-	}
+	scoped_guard(spinlock_irqsave, &iforce->xmit_lock) {
+		head = iforce->xmit.head;
+		tail = iforce->xmit.tail;
+
+		if (CIRC_SPACE(head, tail, XMIT_SIZE) < n + 2) {
+			dev_warn(&iforce->dev->dev,
+				 "not enough space in xmit buffer to send new packet\n");
+			return -1;
+		}
 
-	empty = head == tail;
-	XMIT_INC(iforce->xmit.head, n+2);
+		empty = head == tail;
+		XMIT_INC(iforce->xmit.head, n + 2);
 
 /*
  * Store packet in xmit buffer
  */
-	iforce->xmit.buf[head] = HI(cmd);
-	XMIT_INC(head, 1);
-	iforce->xmit.buf[head] = LO(cmd);
-	XMIT_INC(head, 1);
-
-	c = CIRC_SPACE_TO_END(head, tail, XMIT_SIZE);
-	if (n < c) c=n;
-
-	memcpy(&iforce->xmit.buf[head],
-	       data,
-	       c);
-	if (n != c) {
-		memcpy(&iforce->xmit.buf[0],
-		       data + c,
-		       n - c);
+		iforce->xmit.buf[head] = HI(cmd);
+		XMIT_INC(head, 1);
+		iforce->xmit.buf[head] = LO(cmd);
+		XMIT_INC(head, 1);
+
+		c = CIRC_SPACE_TO_END(head, tail, XMIT_SIZE);
+		if (n < c)
+			c = n;
+
+		memcpy(&iforce->xmit.buf[head], data, c);
+		if (n != c)
+			memcpy(&iforce->xmit.buf[0], data + c, n - c);
+
+		XMIT_INC(head, n);
 	}
-	XMIT_INC(head, n);
 
-	spin_unlock_irqrestore(&iforce->xmit_lock, flags);
 /*
  * If necessary, start the transmission
  */
diff --git a/drivers/input/joystick/iforce/iforce-serio.c b/drivers/input/joystick/iforce/iforce-serio.c
index 2380546d79782..75b85c46dfa41 100644
--- a/drivers/input/joystick/iforce/iforce-serio.c
+++ b/drivers/input/joystick/iforce/iforce-serio.c
@@ -28,45 +28,39 @@ static void iforce_serio_xmit(struct iforce *iforce)
 							 iforce);
 	unsigned char cs;
 	int i;
-	unsigned long flags;
 
 	if (test_and_set_bit(IFORCE_XMIT_RUNNING, iforce->xmit_flags)) {
 		set_bit(IFORCE_XMIT_AGAIN, iforce->xmit_flags);
 		return;
 	}
 
-	spin_lock_irqsave(&iforce->xmit_lock, flags);
+	guard(spinlock_irqsave)(&iforce->xmit_lock);
 
-again:
-	if (iforce->xmit.head == iforce->xmit.tail) {
-		iforce_clear_xmit_and_wake(iforce);
-		spin_unlock_irqrestore(&iforce->xmit_lock, flags);
-		return;
-	}
+	do {
+		if (iforce->xmit.head == iforce->xmit.tail)
+			break;
 
-	cs = 0x2b;
+		cs = 0x2b;
 
-	serio_write(iforce_serio->serio, 0x2b);
+		serio_write(iforce_serio->serio, 0x2b);
 
-	serio_write(iforce_serio->serio, iforce->xmit.buf[iforce->xmit.tail]);
-	cs ^= iforce->xmit.buf[iforce->xmit.tail];
-	XMIT_INC(iforce->xmit.tail, 1);
-
-	for (i=iforce->xmit.buf[iforce->xmit.tail]; i >= 0; --i) {
 		serio_write(iforce_serio->serio,
 			    iforce->xmit.buf[iforce->xmit.tail]);
 		cs ^= iforce->xmit.buf[iforce->xmit.tail];
 		XMIT_INC(iforce->xmit.tail, 1);
-	}
 
-	serio_write(iforce_serio->serio, cs);
+		for (i = iforce->xmit.buf[iforce->xmit.tail]; i >= 0; --i) {
+			serio_write(iforce_serio->serio,
+				    iforce->xmit.buf[iforce->xmit.tail]);
+			cs ^= iforce->xmit.buf[iforce->xmit.tail];
+			XMIT_INC(iforce->xmit.tail, 1);
+		}
 
-	if (test_and_clear_bit(IFORCE_XMIT_AGAIN, iforce->xmit_flags))
-		goto again;
+		serio_write(iforce_serio->serio, cs);
 
-	iforce_clear_xmit_and_wake(iforce);
+	} while (test_and_clear_bit(IFORCE_XMIT_AGAIN, iforce->xmit_flags));
 
-	spin_unlock_irqrestore(&iforce->xmit_lock, flags);
+	iforce_clear_xmit_and_wake(iforce);
 }
 
 static int iforce_serio_get_id(struct iforce *iforce, u8 id,
diff --git a/drivers/input/joystick/iforce/iforce-usb.c b/drivers/input/joystick/iforce/iforce-usb.c
index cba92bd590a8d..1f00f76b01745 100644
--- a/drivers/input/joystick/iforce/iforce-usb.c
+++ b/drivers/input/joystick/iforce/iforce-usb.c
@@ -25,13 +25,11 @@ static void __iforce_usb_xmit(struct iforce *iforce)
 	struct iforce_usb *iforce_usb = container_of(iforce, struct iforce_usb,
 						     iforce);
 	int n, c;
-	unsigned long flags;
 
-	spin_lock_irqsave(&iforce->xmit_lock, flags);
+	guard(spinlock_irqsave)(&iforce->xmit_lock);
 
 	if (iforce->xmit.head == iforce->xmit.tail) {
 		iforce_clear_xmit_and_wake(iforce);
-		spin_unlock_irqrestore(&iforce->xmit_lock, flags);
 		return;
 	}
 
@@ -45,7 +43,8 @@ static void __iforce_usb_xmit(struct iforce *iforce)
 
 	/* Copy rest of data then */
 	c = CIRC_CNT_TO_END(iforce->xmit.head, iforce->xmit.tail, XMIT_SIZE);
-	if (n < c) c=n;
+	if (n < c)
+		c = n;
 
 	memcpy(iforce_usb->out->transfer_buffer + 1,
 	       &iforce->xmit.buf[iforce->xmit.tail],
@@ -53,11 +52,12 @@ static void __iforce_usb_xmit(struct iforce *iforce)
 	if (n != c) {
 		memcpy(iforce_usb->out->transfer_buffer + 1 + c,
 		       &iforce->xmit.buf[0],
-		       n-c);
+		       n - c);
 	}
 	XMIT_INC(iforce->xmit.tail, n);
 
-	if ( (n=usb_submit_urb(iforce_usb->out, GFP_ATOMIC)) ) {
+	n=usb_submit_urb(iforce_usb->out, GFP_ATOMIC);
+	if (n) {
 		dev_warn(&iforce_usb->intf->dev,
 			 "usb_submit_urb failed %d\n", n);
 		iforce_clear_xmit_and_wake(iforce);
@@ -66,7 +66,6 @@ static void __iforce_usb_xmit(struct iforce *iforce)
 	/* The IFORCE_XMIT_RUNNING bit is not cleared here. That's intended.
 	 * As long as the urb completion handler is not called, the transmiting
 	 * is considered to be running */
-	spin_unlock_irqrestore(&iforce->xmit_lock, flags);
 }
 
 static void iforce_usb_xmit(struct iforce *iforce)

From d68ed9b580176d5df41072900afa164edc879282 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:31:01 -0700
Subject: [PATCH 0134/1530] Input: n64joy - use guard notation when acquiring
 mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240904043104.1030257-5-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/n64joy.c | 35 +++++++++++++++------------------
 1 file changed, 16 insertions(+), 19 deletions(-)

diff --git a/drivers/input/joystick/n64joy.c b/drivers/input/joystick/n64joy.c
index b0986d2195d68..c344dbc0c493e 100644
--- a/drivers/input/joystick/n64joy.c
+++ b/drivers/input/joystick/n64joy.c
@@ -191,35 +191,32 @@ static void n64joy_poll(struct timer_list *t)
 static int n64joy_open(struct input_dev *dev)
 {
 	struct n64joy_priv *priv = input_get_drvdata(dev);
-	int err;
-
-	err = mutex_lock_interruptible(&priv->n64joy_mutex);
-	if (err)
-		return err;
-
-	if (!priv->n64joy_opened) {
-		/*
-		 * We could use the vblank irq, but it's not important if
-		 * the poll point slightly changes.
-		 */
-		timer_setup(&priv->timer, n64joy_poll, 0);
-		mod_timer(&priv->timer, jiffies + msecs_to_jiffies(16));
-	}
 
-	priv->n64joy_opened++;
+	scoped_guard(mutex_intr, &priv->n64joy_mutex) {
+		if (!priv->n64joy_opened) {
+			/*
+			 * We could use the vblank irq, but it's not important
+			 * if the poll point slightly changes.
+			 */
+			timer_setup(&priv->timer, n64joy_poll, 0);
+			mod_timer(&priv->timer, jiffies + msecs_to_jiffies(16));
+		}
 
-	mutex_unlock(&priv->n64joy_mutex);
-	return err;
+		priv->n64joy_opened++;
+		return 0;
+	}
+
+	return -EINTR;
 }
 
 static void n64joy_close(struct input_dev *dev)
 {
 	struct n64joy_priv *priv = input_get_drvdata(dev);
 
-	mutex_lock(&priv->n64joy_mutex);
+	guard(mutex)(&priv->n64joy_mutex);
+
 	if (!--priv->n64joy_opened)
 		del_timer_sync(&priv->timer);
-	mutex_unlock(&priv->n64joy_mutex);
 }
 
 static const u64 __initconst scandata[] ____cacheline_aligned = {

From 10068a36b01dc25f598259ffd0562f474ae3ed94 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:31:02 -0700
Subject: [PATCH 0135/1530] Input: turbografx - use guard notation when
 acquiring mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240904043104.1030257-6-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/turbografx.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/drivers/input/joystick/turbografx.c b/drivers/input/joystick/turbografx.c
index 0a78dda3e0ea8..db696ba61a3bf 100644
--- a/drivers/input/joystick/turbografx.c
+++ b/drivers/input/joystick/turbografx.c
@@ -103,33 +103,31 @@ static void tgfx_timer(struct timer_list *t)
 static int tgfx_open(struct input_dev *dev)
 {
 	struct tgfx *tgfx = input_get_drvdata(dev);
-	int err;
 
-	err = mutex_lock_interruptible(&tgfx->sem);
-	if (err)
-		return err;
+	scoped_guard(mutex_intr, &tgfx->sem) {
+		if (!tgfx->used++) {
+			parport_claim(tgfx->pd);
+			parport_write_control(tgfx->pd->port, 0x04);
+			mod_timer(&tgfx->timer, jiffies + TGFX_REFRESH_TIME);
+		}
 
-	if (!tgfx->used++) {
-		parport_claim(tgfx->pd);
-		parport_write_control(tgfx->pd->port, 0x04);
-		mod_timer(&tgfx->timer, jiffies + TGFX_REFRESH_TIME);
+		return 0;
 	}
 
-	mutex_unlock(&tgfx->sem);
-	return 0;
+	return -EINTR;
 }
 
 static void tgfx_close(struct input_dev *dev)
 {
 	struct tgfx *tgfx = input_get_drvdata(dev);
 
-	mutex_lock(&tgfx->sem);
+	guard(mutex)(&tgfx->sem);
+
 	if (!--tgfx->used) {
 		del_timer_sync(&tgfx->timer);
 		parport_write_control(tgfx->pd->port, 0x00);
 		parport_release(tgfx->pd);
 	}
-	mutex_unlock(&tgfx->sem);
 }
 
 

From 45a81459722aa48de343910001355b0108b9c16b Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:31:03 -0700
Subject: [PATCH 0136/1530] Input: xpad - use guard notation when acquiring
 mutex and spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240904043104.1030257-7-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 99 ++++++++++++-----------------------
 1 file changed, 34 insertions(+), 65 deletions(-)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 4eda18f4f46e3..3e61df9272779 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -1289,9 +1289,8 @@ static void xpad_irq_out(struct urb *urb)
 	struct device *dev = &xpad->intf->dev;
 	int status = urb->status;
 	int error;
-	unsigned long flags;
 
-	spin_lock_irqsave(&xpad->odata_lock, flags);
+	guard(spinlock_irqsave)(&xpad->odata_lock);
 
 	switch (status) {
 	case 0:
@@ -1325,8 +1324,6 @@ static void xpad_irq_out(struct urb *urb)
 			xpad->irq_out_active = false;
 		}
 	}
-
-	spin_unlock_irqrestore(&xpad->odata_lock, flags);
 }
 
 static int xpad_init_output(struct usb_interface *intf, struct usb_xpad *xpad,
@@ -1391,10 +1388,8 @@ static int xpad_inquiry_pad_presence(struct usb_xpad *xpad)
 {
 	struct xpad_output_packet *packet =
 			&xpad->out_packets[XPAD_OUT_CMD_IDX];
-	unsigned long flags;
-	int retval;
 
-	spin_lock_irqsave(&xpad->odata_lock, flags);
+	guard(spinlock_irqsave)(&xpad->odata_lock);
 
 	packet->data[0] = 0x08;
 	packet->data[1] = 0x00;
@@ -1413,17 +1408,12 @@ static int xpad_inquiry_pad_presence(struct usb_xpad *xpad)
 
 	/* Reset the sequence so we send out presence first */
 	xpad->last_out_packet = -1;
-	retval = xpad_try_sending_next_out_packet(xpad);
-
-	spin_unlock_irqrestore(&xpad->odata_lock, flags);
-
-	return retval;
+	return xpad_try_sending_next_out_packet(xpad);
 }
 
 static int xpad_start_xbox_one(struct usb_xpad *xpad)
 {
-	unsigned long flags;
-	int retval;
+	int error;
 
 	if (usb_ifnum_to_if(xpad->udev, GIP_WIRED_INTF_AUDIO)) {
 		/*
@@ -1432,15 +1422,15 @@ static int xpad_start_xbox_one(struct usb_xpad *xpad)
 		 * Controller for Series X|S (0x20d6:0x200e) to report the
 		 * guide button.
 		 */
-		retval = usb_set_interface(xpad->udev,
-					   GIP_WIRED_INTF_AUDIO, 0);
-		if (retval)
+		error = usb_set_interface(xpad->udev,
+					  GIP_WIRED_INTF_AUDIO, 0);
+		if (error)
 			dev_warn(&xpad->dev->dev,
 				 "unable to disable audio interface: %d\n",
-				 retval);
+				 error);
 	}
 
-	spin_lock_irqsave(&xpad->odata_lock, flags);
+	guard(spinlock_irqsave)(&xpad->odata_lock);
 
 	/*
 	 * Begin the init sequence by attempting to send a packet.
@@ -1448,16 +1438,11 @@ static int xpad_start_xbox_one(struct usb_xpad *xpad)
 	 * sending any packets from the output ring.
 	 */
 	xpad->init_seq = 0;
-	retval = xpad_try_sending_next_out_packet(xpad);
-
-	spin_unlock_irqrestore(&xpad->odata_lock, flags);
-
-	return retval;
+	return xpad_try_sending_next_out_packet(xpad);
 }
 
 static void xpadone_ack_mode_report(struct usb_xpad *xpad, u8 seq_num)
 {
-	unsigned long flags;
 	struct xpad_output_packet *packet =
 			&xpad->out_packets[XPAD_OUT_CMD_IDX];
 	static const u8 mode_report_ack[] = {
@@ -1465,7 +1450,7 @@ static void xpadone_ack_mode_report(struct usb_xpad *xpad, u8 seq_num)
 		0x00, GIP_CMD_VIRTUAL_KEY, GIP_OPT_INTERNAL, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00
 	};
 
-	spin_lock_irqsave(&xpad->odata_lock, flags);
+	guard(spinlock_irqsave)(&xpad->odata_lock);
 
 	packet->len = sizeof(mode_report_ack);
 	memcpy(packet->data, mode_report_ack, packet->len);
@@ -1475,8 +1460,6 @@ static void xpadone_ack_mode_report(struct usb_xpad *xpad, u8 seq_num)
 	/* Reset the sequence so we send out the ack now */
 	xpad->last_out_packet = -1;
 	xpad_try_sending_next_out_packet(xpad);
-
-	spin_unlock_irqrestore(&xpad->odata_lock, flags);
 }
 
 #ifdef CONFIG_JOYSTICK_XPAD_FF
@@ -1486,8 +1469,6 @@ static int xpad_play_effect(struct input_dev *dev, void *data, struct ff_effect
 	struct xpad_output_packet *packet = &xpad->out_packets[XPAD_OUT_FF_IDX];
 	__u16 strong;
 	__u16 weak;
-	int retval;
-	unsigned long flags;
 
 	if (effect->type != FF_RUMBLE)
 		return 0;
@@ -1495,7 +1476,7 @@ static int xpad_play_effect(struct input_dev *dev, void *data, struct ff_effect
 	strong = effect->u.rumble.strong_magnitude;
 	weak = effect->u.rumble.weak_magnitude;
 
-	spin_lock_irqsave(&xpad->odata_lock, flags);
+	guard(spinlock_irqsave)(&xpad->odata_lock);
 
 	switch (xpad->xtype) {
 	case XTYPE_XBOX:
@@ -1561,15 +1542,10 @@ static int xpad_play_effect(struct input_dev *dev, void *data, struct ff_effect
 		dev_dbg(&xpad->dev->dev,
 			"%s - rumble command sent to unsupported xpad type: %d\n",
 			__func__, xpad->xtype);
-		retval = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
-	retval = xpad_try_sending_next_out_packet(xpad);
-
-out:
-	spin_unlock_irqrestore(&xpad->odata_lock, flags);
-	return retval;
+	return xpad_try_sending_next_out_packet(xpad);
 }
 
 static int xpad_init_ff(struct usb_xpad *xpad)
@@ -1622,11 +1598,10 @@ static void xpad_send_led_command(struct usb_xpad *xpad, int command)
 {
 	struct xpad_output_packet *packet =
 			&xpad->out_packets[XPAD_OUT_LED_IDX];
-	unsigned long flags;
 
 	command %= 16;
 
-	spin_lock_irqsave(&xpad->odata_lock, flags);
+	guard(spinlock_irqsave)(&xpad->odata_lock);
 
 	switch (xpad->xtype) {
 	case XTYPE_XBOX360:
@@ -1656,8 +1631,6 @@ static void xpad_send_led_command(struct usb_xpad *xpad, int command)
 	}
 
 	xpad_try_sending_next_out_packet(xpad);
-
-	spin_unlock_irqrestore(&xpad->odata_lock, flags);
 }
 
 /*
@@ -1782,11 +1755,10 @@ static void xpad_stop_input(struct usb_xpad *xpad)
 
 static void xpad360w_poweroff_controller(struct usb_xpad *xpad)
 {
-	unsigned long flags;
 	struct xpad_output_packet *packet =
 			&xpad->out_packets[XPAD_OUT_CMD_IDX];
 
-	spin_lock_irqsave(&xpad->odata_lock, flags);
+	guard(spinlock_irqsave)(&xpad->odata_lock);
 
 	packet->data[0] = 0x00;
 	packet->data[1] = 0x00;
@@ -1806,8 +1778,6 @@ static void xpad360w_poweroff_controller(struct usb_xpad *xpad)
 	/* Reset the sequence so we send out poweroff now */
 	xpad->last_out_packet = -1;
 	xpad_try_sending_next_out_packet(xpad);
-
-	spin_unlock_irqrestore(&xpad->odata_lock, flags);
 }
 
 static int xpad360w_start_input(struct usb_xpad *xpad)
@@ -2231,10 +2201,10 @@ static int xpad_suspend(struct usb_interface *intf, pm_message_t message)
 		if (auto_poweroff && xpad->pad_present)
 			xpad360w_poweroff_controller(xpad);
 	} else {
-		mutex_lock(&input->mutex);
+		guard(mutex)(&input->mutex);
+
 		if (input_device_enabled(input))
 			xpad_stop_input(xpad);
-		mutex_unlock(&input->mutex);
 	}
 
 	xpad_stop_output(xpad);
@@ -2246,26 +2216,25 @@ static int xpad_resume(struct usb_interface *intf)
 {
 	struct usb_xpad *xpad = usb_get_intfdata(intf);
 	struct input_dev *input = xpad->dev;
-	int retval = 0;
 
-	if (xpad->xtype == XTYPE_XBOX360W) {
-		retval = xpad360w_start_input(xpad);
-	} else {
-		mutex_lock(&input->mutex);
-		if (input_device_enabled(input)) {
-			retval = xpad_start_input(xpad);
-		} else if (xpad->xtype == XTYPE_XBOXONE) {
-			/*
-			 * Even if there are no users, we'll send Xbox One pads
-			 * the startup sequence so they don't sit there and
-			 * blink until somebody opens the input device again.
-			 */
-			retval = xpad_start_xbox_one(xpad);
-		}
-		mutex_unlock(&input->mutex);
+	if (xpad->xtype == XTYPE_XBOX360W)
+		return xpad360w_start_input(xpad);
+
+	guard(mutex)(&input->mutex);
+
+	if (input_device_enabled(input))
+		return xpad_start_input(xpad);
+
+	if (xpad->xtype == XTYPE_XBOXONE) {
+		/*
+		 * Even if there are no users, we'll send Xbox One pads
+		 * the startup sequence so they don't sit there and
+		 * blink until somebody opens the input device again.
+		 */
+		return xpad_start_xbox_one(xpad);
 	}
 
-	return retval;
+	return 0;
 }
 
 static struct usb_driver xpad_driver = {

From f9f37373ff02b64a46b266d25d680a061ed13a8d Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:42:21 -0700
Subject: [PATCH 0137/1530] Input: ad714x - use guard notation when acquiring
 mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044244.1042174-2-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/ad714x.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/input/misc/ad714x.c b/drivers/input/misc/ad714x.c
index 1acd8429c56c9..d106f37df6bcb 100644
--- a/drivers/input/misc/ad714x.c
+++ b/drivers/input/misc/ad714x.c
@@ -941,7 +941,7 @@ static irqreturn_t ad714x_interrupt_thread(int irq, void *data)
 	struct ad714x_chip *ad714x = data;
 	int i;
 
-	mutex_lock(&ad714x->mutex);
+	guard(mutex)(&ad714x->mutex);
 
 	ad714x->read(ad714x, STG_LOW_INT_STA_REG, &ad714x->l_state, 3);
 
@@ -954,8 +954,6 @@ static irqreturn_t ad714x_interrupt_thread(int irq, void *data)
 	for (i = 0; i < ad714x->hw->touchpad_num; i++)
 		ad714x_touchpad_state_machine(ad714x, i);
 
-	mutex_unlock(&ad714x->mutex);
-
 	return IRQ_HANDLED;
 }
 
@@ -1169,13 +1167,11 @@ static int ad714x_suspend(struct device *dev)
 
 	dev_dbg(ad714x->dev, "%s enter\n", __func__);
 
-	mutex_lock(&ad714x->mutex);
+	guard(mutex)(&ad714x->mutex);
 
 	data = ad714x->hw->sys_cfg_reg[AD714X_PWR_CTRL] | 0x3;
 	ad714x->write(ad714x, AD714X_PWR_CTRL, data);
 
-	mutex_unlock(&ad714x->mutex);
-
 	return 0;
 }
 
@@ -1184,7 +1180,7 @@ static int ad714x_resume(struct device *dev)
 	struct ad714x_chip *ad714x = dev_get_drvdata(dev);
 	dev_dbg(ad714x->dev, "%s enter\n", __func__);
 
-	mutex_lock(&ad714x->mutex);
+	guard(mutex)(&ad714x->mutex);
 
 	/* resume to non-shutdown mode */
 
@@ -1197,8 +1193,6 @@ static int ad714x_resume(struct device *dev)
 
 	ad714x->read(ad714x, STG_LOW_INT_STA_REG, &ad714x->l_state, 3);
 
-	mutex_unlock(&ad714x->mutex);
-
 	return 0;
 }
 

From 61bbcc9fa144433e6fc88e66f3d4463e10e556de Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:42:22 -0700
Subject: [PATCH 0138/1530] Input: ati_remote2 - use guard notation when
 acquiring mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044244.1042174-3-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/ati_remote2.c | 57 +++++++++++---------------------
 1 file changed, 19 insertions(+), 38 deletions(-)

diff --git a/drivers/input/misc/ati_remote2.c b/drivers/input/misc/ati_remote2.c
index 795f69edb4b27..e84649af801dd 100644
--- a/drivers/input/misc/ati_remote2.c
+++ b/drivers/input/misc/ati_remote2.c
@@ -244,29 +244,21 @@ static int ati_remote2_open(struct input_dev *idev)
 	if (r) {
 		dev_err(&ar2->intf[0]->dev,
 			"%s(): usb_autopm_get_interface() = %d\n", __func__, r);
-		goto fail1;
+		return r;
 	}
 
-	mutex_lock(&ati_remote2_mutex);
+	scoped_guard(mutex, &ati_remote2_mutex) {
+		if (!(ar2->flags & ATI_REMOTE2_SUSPENDED)) {
+			r = ati_remote2_submit_urbs(ar2);
+			if (r)
+				break;
+		}
 
-	if (!(ar2->flags & ATI_REMOTE2_SUSPENDED)) {
-		r = ati_remote2_submit_urbs(ar2);
-		if (r)
-			goto fail2;
+		ar2->flags |= ATI_REMOTE2_OPENED;
 	}
 
-	ar2->flags |= ATI_REMOTE2_OPENED;
-
-	mutex_unlock(&ati_remote2_mutex);
-
 	usb_autopm_put_interface(ar2->intf[0]);
 
-	return 0;
-
- fail2:
-	mutex_unlock(&ati_remote2_mutex);
-	usb_autopm_put_interface(ar2->intf[0]);
- fail1:
 	return r;
 }
 
@@ -276,14 +268,12 @@ static void ati_remote2_close(struct input_dev *idev)
 
 	dev_dbg(&ar2->intf[0]->dev, "%s()\n", __func__);
 
-	mutex_lock(&ati_remote2_mutex);
+	guard(mutex)(&ati_remote2_mutex);
 
 	if (!(ar2->flags & ATI_REMOTE2_SUSPENDED))
 		ati_remote2_kill_urbs(ar2);
 
 	ar2->flags &= ~ATI_REMOTE2_OPENED;
-
-	mutex_unlock(&ati_remote2_mutex);
 }
 
 static void ati_remote2_input_mouse(struct ati_remote2 *ar2)
@@ -713,16 +703,14 @@ static ssize_t ati_remote2_store_channel_mask(struct device *dev,
 		return r;
 	}
 
-	mutex_lock(&ati_remote2_mutex);
-
-	if (mask != ar2->channel_mask) {
-		r = ati_remote2_setup(ar2, mask);
-		if (!r)
-			ar2->channel_mask = mask;
+	scoped_guard(mutex, &ati_remote2_mutex) {
+		if (mask != ar2->channel_mask) {
+			r = ati_remote2_setup(ar2, mask);
+			if (!r)
+				ar2->channel_mask = mask;
+		}
 	}
 
-	mutex_unlock(&ati_remote2_mutex);
-
 	usb_autopm_put_interface(ar2->intf[0]);
 
 	return r ? r : count;
@@ -892,15 +880,13 @@ static int ati_remote2_suspend(struct usb_interface *interface,
 
 	dev_dbg(&ar2->intf[0]->dev, "%s()\n", __func__);
 
-	mutex_lock(&ati_remote2_mutex);
+	guard(mutex)(&ati_remote2_mutex);
 
 	if (ar2->flags & ATI_REMOTE2_OPENED)
 		ati_remote2_kill_urbs(ar2);
 
 	ar2->flags |= ATI_REMOTE2_SUSPENDED;
 
-	mutex_unlock(&ati_remote2_mutex);
-
 	return 0;
 }
 
@@ -917,7 +903,7 @@ static int ati_remote2_resume(struct usb_interface *interface)
 
 	dev_dbg(&ar2->intf[0]->dev, "%s()\n", __func__);
 
-	mutex_lock(&ati_remote2_mutex);
+	guard(mutex)(&ati_remote2_mutex);
 
 	if (ar2->flags & ATI_REMOTE2_OPENED)
 		r = ati_remote2_submit_urbs(ar2);
@@ -925,8 +911,6 @@ static int ati_remote2_resume(struct usb_interface *interface)
 	if (!r)
 		ar2->flags &= ~ATI_REMOTE2_SUSPENDED;
 
-	mutex_unlock(&ati_remote2_mutex);
-
 	return r;
 }
 
@@ -943,11 +927,11 @@ static int ati_remote2_reset_resume(struct usb_interface *interface)
 
 	dev_dbg(&ar2->intf[0]->dev, "%s()\n", __func__);
 
-	mutex_lock(&ati_remote2_mutex);
+	guard(mutex)(&ati_remote2_mutex);
 
 	r = ati_remote2_setup(ar2, ar2->channel_mask);
 	if (r)
-		goto out;
+		return r;
 
 	if (ar2->flags & ATI_REMOTE2_OPENED)
 		r = ati_remote2_submit_urbs(ar2);
@@ -955,9 +939,6 @@ static int ati_remote2_reset_resume(struct usb_interface *interface)
 	if (!r)
 		ar2->flags &= ~ATI_REMOTE2_SUSPENDED;
 
- out:
-	mutex_unlock(&ati_remote2_mutex);
-
 	return r;
 }
 

From d8a43a83633a4770f00ee77079fbb7a2218cea2a Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:42:23 -0700
Subject: [PATCH 0139/1530] Input: cm109 - use guard notation when acquiring
 mutex and spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044244.1042174-4-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/cm109.c | 167 ++++++++++++++++++-------------------
 1 file changed, 79 insertions(+), 88 deletions(-)

diff --git a/drivers/input/misc/cm109.c b/drivers/input/misc/cm109.c
index 728325a2d574a..0cfe5d4a573c6 100644
--- a/drivers/input/misc/cm109.c
+++ b/drivers/input/misc/cm109.c
@@ -355,6 +355,35 @@ static void cm109_submit_buzz_toggle(struct cm109_dev *dev)
 			__func__, error);
 }
 
+static void cm109_submit_ctl(struct cm109_dev *dev)
+{
+	int error;
+
+	guard(spinlock_irqsave)(&dev->ctl_submit_lock);
+
+	dev->irq_urb_pending = 0;
+
+	if (unlikely(dev->shutdown))
+		return;
+
+	if (dev->buzzer_state)
+		dev->ctl_data->byte[HID_OR0] |= BUZZER_ON;
+	else
+		dev->ctl_data->byte[HID_OR0] &= ~BUZZER_ON;
+
+	dev->ctl_data->byte[HID_OR1] = dev->keybit;
+	dev->ctl_data->byte[HID_OR2] = dev->keybit;
+
+	dev->buzzer_pending = 0;
+	dev->ctl_urb_pending = 1;
+
+	error = usb_submit_urb(dev->urb_ctl, GFP_ATOMIC);
+	if (error)
+		dev_err(&dev->intf->dev,
+			"%s: usb_submit_urb (urb_ctl) failed %d\n",
+			__func__, error);
+}
+
 /*
  * IRQ handler
  */
@@ -362,8 +391,6 @@ static void cm109_urb_irq_callback(struct urb *urb)
 {
 	struct cm109_dev *dev = urb->context;
 	const int status = urb->status;
-	int error;
-	unsigned long flags;
 
 	dev_dbg(&dev->intf->dev, "### URB IRQ: [0x%02x 0x%02x 0x%02x 0x%02x] keybit=0x%02x\n",
 	     dev->irq_data->byte[0],
@@ -401,32 +428,7 @@ static void cm109_urb_irq_callback(struct urb *urb)
 	}
 
  out:
-
-	spin_lock_irqsave(&dev->ctl_submit_lock, flags);
-
-	dev->irq_urb_pending = 0;
-
-	if (likely(!dev->shutdown)) {
-
-		if (dev->buzzer_state)
-			dev->ctl_data->byte[HID_OR0] |= BUZZER_ON;
-		else
-			dev->ctl_data->byte[HID_OR0] &= ~BUZZER_ON;
-
-		dev->ctl_data->byte[HID_OR1] = dev->keybit;
-		dev->ctl_data->byte[HID_OR2] = dev->keybit;
-
-		dev->buzzer_pending = 0;
-		dev->ctl_urb_pending = 1;
-
-		error = usb_submit_urb(dev->urb_ctl, GFP_ATOMIC);
-		if (error)
-			dev_err(&dev->intf->dev,
-				"%s: usb_submit_urb (urb_ctl) failed %d\n",
-				__func__, error);
-	}
-
-	spin_unlock_irqrestore(&dev->ctl_submit_lock, flags);
+	cm109_submit_ctl(dev);
 }
 
 static void cm109_urb_ctl_callback(struct urb *urb)
@@ -434,7 +436,6 @@ static void cm109_urb_ctl_callback(struct urb *urb)
 	struct cm109_dev *dev = urb->context;
 	const int status = urb->status;
 	int error;
-	unsigned long flags;
 
 	dev_dbg(&dev->intf->dev, "### URB CTL: [0x%02x 0x%02x 0x%02x 0x%02x]\n",
 	     dev->ctl_data->byte[0],
@@ -449,35 +450,31 @@ static void cm109_urb_ctl_callback(struct urb *urb)
 				    __func__, status);
 	}
 
-	spin_lock_irqsave(&dev->ctl_submit_lock, flags);
+	guard(spinlock_irqsave)(&dev->ctl_submit_lock);
 
 	dev->ctl_urb_pending = 0;
 
-	if (likely(!dev->shutdown)) {
-
-		if (dev->buzzer_pending || status) {
-			dev->buzzer_pending = 0;
-			dev->ctl_urb_pending = 1;
-			cm109_submit_buzz_toggle(dev);
-		} else if (likely(!dev->irq_urb_pending)) {
-			/* ask for key data */
-			dev->irq_urb_pending = 1;
-			error = usb_submit_urb(dev->urb_irq, GFP_ATOMIC);
-			if (error)
-				dev_err(&dev->intf->dev,
-					"%s: usb_submit_urb (urb_irq) failed %d\n",
-					__func__, error);
-		}
-	}
+	if (unlikely(dev->shutdown))
+		return;
 
-	spin_unlock_irqrestore(&dev->ctl_submit_lock, flags);
+	if (dev->buzzer_pending || status) {
+		dev->buzzer_pending = 0;
+		dev->ctl_urb_pending = 1;
+		cm109_submit_buzz_toggle(dev);
+	} else if (likely(!dev->irq_urb_pending)) {
+		/* ask for key data */
+		dev->irq_urb_pending = 1;
+		error = usb_submit_urb(dev->urb_irq, GFP_ATOMIC);
+		if (error)
+			dev_err(&dev->intf->dev,
+				"%s: usb_submit_urb (urb_irq) failed %d\n",
+				__func__, error);
+	}
 }
 
 static void cm109_toggle_buzzer_async(struct cm109_dev *dev)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&dev->ctl_submit_lock, flags);
+	guard(spinlock_irqsave)(&dev->ctl_submit_lock);
 
 	if (dev->ctl_urb_pending) {
 		/* URB completion will resubmit */
@@ -486,8 +483,6 @@ static void cm109_toggle_buzzer_async(struct cm109_dev *dev)
 		dev->ctl_urb_pending = 1;
 		cm109_submit_buzz_toggle(dev);
 	}
-
-	spin_unlock_irqrestore(&dev->ctl_submit_lock, flags);
 }
 
 static void cm109_toggle_buzzer_sync(struct cm109_dev *dev, int on)
@@ -556,32 +551,30 @@ static int cm109_input_open(struct input_dev *idev)
 		return error;
 	}
 
-	mutex_lock(&dev->pm_mutex);
-
-	dev->buzzer_state = 0;
-	dev->key_code = -1;	/* no keys pressed */
-	dev->keybit = 0xf;
+	scoped_guard(mutex, &dev->pm_mutex) {
+		dev->buzzer_state = 0;
+		dev->key_code = -1;	/* no keys pressed */
+		dev->keybit = 0xf;
 
-	/* issue INIT */
-	dev->ctl_data->byte[HID_OR0] = HID_OR_GPO_BUZ_SPDIF;
-	dev->ctl_data->byte[HID_OR1] = dev->keybit;
-	dev->ctl_data->byte[HID_OR2] = dev->keybit;
-	dev->ctl_data->byte[HID_OR3] = 0x00;
+		/* issue INIT */
+		dev->ctl_data->byte[HID_OR0] = HID_OR_GPO_BUZ_SPDIF;
+		dev->ctl_data->byte[HID_OR1] = dev->keybit;
+		dev->ctl_data->byte[HID_OR2] = dev->keybit;
+		dev->ctl_data->byte[HID_OR3] = 0x00;
 
-	dev->ctl_urb_pending = 1;
-	error = usb_submit_urb(dev->urb_ctl, GFP_KERNEL);
-	if (error) {
-		dev->ctl_urb_pending = 0;
-		dev_err(&dev->intf->dev, "%s: usb_submit_urb (urb_ctl) failed %d\n",
-			__func__, error);
-	} else {
-		dev->open = 1;
+		dev->ctl_urb_pending = 1;
+		error = usb_submit_urb(dev->urb_ctl, GFP_KERNEL);
+		if (!error) {
+			dev->open = 1;
+			return 0;
+		}
 	}
 
-	mutex_unlock(&dev->pm_mutex);
+	dev->ctl_urb_pending = 0;
+	usb_autopm_put_interface(dev->intf);
 
-	if (error)
-		usb_autopm_put_interface(dev->intf);
+	dev_err(&dev->intf->dev, "%s: usb_submit_urb (urb_ctl) failed %d\n",
+		__func__, error);
 
 	return error;
 }
@@ -590,17 +583,15 @@ static void cm109_input_close(struct input_dev *idev)
 {
 	struct cm109_dev *dev = input_get_drvdata(idev);
 
-	mutex_lock(&dev->pm_mutex);
-
-	/*
-	 * Once we are here event delivery is stopped so we
-	 * don't need to worry about someone starting buzzer
-	 * again
-	 */
-	cm109_stop_traffic(dev);
-	dev->open = 0;
-
-	mutex_unlock(&dev->pm_mutex);
+	scoped_guard(mutex, &dev->pm_mutex) {
+		/*
+		 * Once we are here event delivery is stopped so we
+		 * don't need to worry about someone starting buzzer
+		 * again
+		 */
+		cm109_stop_traffic(dev);
+		dev->open = 0;
+	}
 
 	usb_autopm_put_interface(dev->intf);
 }
@@ -823,9 +814,9 @@ static int cm109_usb_suspend(struct usb_interface *intf, pm_message_t message)
 
 	dev_info(&intf->dev, "cm109: usb_suspend (event=%d)\n", message.event);
 
-	mutex_lock(&dev->pm_mutex);
+	guard(mutex)(&dev->pm_mutex);
+
 	cm109_stop_traffic(dev);
-	mutex_unlock(&dev->pm_mutex);
 
 	return 0;
 }
@@ -836,9 +827,9 @@ static int cm109_usb_resume(struct usb_interface *intf)
 
 	dev_info(&intf->dev, "cm109: usb_resume\n");
 
-	mutex_lock(&dev->pm_mutex);
+	guard(mutex)(&dev->pm_mutex);
+
 	cm109_restore_state(dev);
-	mutex_unlock(&dev->pm_mutex);
 
 	return 0;
 }

From 0cc842d191b4f0ccf2a72795f49b5d9e28fcc91e Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:42:24 -0700
Subject: [PATCH 0140/1530] Input: cma3000_d0x - use guard notation when
 acquiring mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044244.1042174-5-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/cma3000_d0x.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/drivers/input/misc/cma3000_d0x.c b/drivers/input/misc/cma3000_d0x.c
index 0c68e924a1ccd..cfc12332bee14 100644
--- a/drivers/input/misc/cma3000_d0x.c
+++ b/drivers/input/misc/cma3000_d0x.c
@@ -217,15 +217,13 @@ static int cma3000_open(struct input_dev *input_dev)
 {
 	struct cma3000_accl_data *data = input_get_drvdata(input_dev);
 
-	mutex_lock(&data->mutex);
+	guard(mutex)(&data->mutex);
 
 	if (!data->suspended)
 		cma3000_poweron(data);
 
 	data->opened = true;
 
-	mutex_unlock(&data->mutex);
-
 	return 0;
 }
 
@@ -233,40 +231,34 @@ static void cma3000_close(struct input_dev *input_dev)
 {
 	struct cma3000_accl_data *data = input_get_drvdata(input_dev);
 
-	mutex_lock(&data->mutex);
+	guard(mutex)(&data->mutex);
 
 	if (!data->suspended)
 		cma3000_poweroff(data);
 
 	data->opened = false;
-
-	mutex_unlock(&data->mutex);
 }
 
 void cma3000_suspend(struct cma3000_accl_data *data)
 {
-	mutex_lock(&data->mutex);
+	guard(mutex)(&data->mutex);
 
 	if (!data->suspended && data->opened)
 		cma3000_poweroff(data);
 
 	data->suspended = true;
-
-	mutex_unlock(&data->mutex);
 }
 EXPORT_SYMBOL(cma3000_suspend);
 
 
 void cma3000_resume(struct cma3000_accl_data *data)
 {
-	mutex_lock(&data->mutex);
+	guard(mutex)(&data->mutex);
 
 	if (data->suspended && data->opened)
 		cma3000_poweron(data);
 
 	data->suspended = false;
-
-	mutex_unlock(&data->mutex);
 }
 EXPORT_SYMBOL(cma3000_resume);
 

From 1313f0ad814e816a96913deee1ac4fe776723cbc Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:42:25 -0700
Subject: [PATCH 0141/1530] Input: da7280 - use guard notation when acquiring
 mutex and spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044244.1042174-6-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/da7280.c | 26 ++++++++++++--------------
 1 file changed, 12 insertions(+), 14 deletions(-)

diff --git a/drivers/input/misc/da7280.c b/drivers/input/misc/da7280.c
index 1629b7ea4cbd4..e4a605c6af150 100644
--- a/drivers/input/misc/da7280.c
+++ b/drivers/input/misc/da7280.c
@@ -1263,39 +1263,37 @@ static int da7280_suspend(struct device *dev)
 {
 	struct da7280_haptic *haptics = dev_get_drvdata(dev);
 
-	mutex_lock(&haptics->input_dev->mutex);
+	guard(mutex)(&haptics->input_dev->mutex);
 
 	/*
 	 * Make sure no new requests will be submitted while device is
 	 * suspended.
 	 */
-	spin_lock_irq(&haptics->input_dev->event_lock);
-	haptics->suspended = true;
-	spin_unlock_irq(&haptics->input_dev->event_lock);
+	scoped_guard(spinlock_irq, &haptics->input_dev->event_lock) {
+		haptics->suspended = true;
+	}
 
 	da7280_haptic_stop(haptics);
 
-	mutex_unlock(&haptics->input_dev->mutex);
-
 	return 0;
 }
 
 static int da7280_resume(struct device *dev)
 {
 	struct da7280_haptic *haptics = dev_get_drvdata(dev);
-	int retval;
+	int error;
 
-	mutex_lock(&haptics->input_dev->mutex);
+	guard(mutex)(&haptics->input_dev->mutex);
 
-	retval = da7280_haptic_start(haptics);
-	if (!retval) {
-		spin_lock_irq(&haptics->input_dev->event_lock);
+	error = da7280_haptic_start(haptics);
+	if (error)
+		return error;
+
+	scoped_guard(spinlock_irq, &haptics->input_dev->event_lock) {
 		haptics->suspended = false;
-		spin_unlock_irq(&haptics->input_dev->event_lock);
 	}
 
-	mutex_unlock(&haptics->input_dev->mutex);
-	return retval;
+	return 0;
 }
 
 #ifdef CONFIG_OF

From 6bbf7efc40f7d43383bac63537a8d4e6253a2e98 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:42:26 -0700
Subject: [PATCH 0142/1530] Input: kxtj9 - use guard notation when acquiring
 mutex/disabling irq

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released and interrupts are
re-enabled in all code paths when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044244.1042174-7-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/kxtj9.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/input/misc/kxtj9.c b/drivers/input/misc/kxtj9.c
index 2f301ebb2fb8c..eb9788ea52155 100644
--- a/drivers/input/misc/kxtj9.c
+++ b/drivers/input/misc/kxtj9.c
@@ -314,9 +314,8 @@ static ssize_t kxtj9_set_poll(struct device *dev, struct device_attribute *attr,
 		return error;
 
 	/* Lock the device to prevent races with open/close (and itself) */
-	mutex_lock(&input_dev->mutex);
-
-	disable_irq(client->irq);
+	guard(mutex)(&input_dev->mutex);
+	guard(disable_irq)(&client->irq);
 
 	/*
 	 * Set current interval to the greater of the minimum interval or
@@ -326,9 +325,6 @@ static ssize_t kxtj9_set_poll(struct device *dev, struct device_attribute *attr,
 
 	kxtj9_update_odr(tj9, tj9->last_poll_interval);
 
-	enable_irq(client->irq);
-	mutex_unlock(&input_dev->mutex);
-
 	return count;
 }
 
@@ -504,12 +500,11 @@ static int kxtj9_suspend(struct device *dev)
 	struct kxtj9_data *tj9 = i2c_get_clientdata(client);
 	struct input_dev *input_dev = tj9->input_dev;
 
-	mutex_lock(&input_dev->mutex);
+	guard(mutex)(&input_dev->mutex);
 
 	if (input_device_enabled(input_dev))
 		kxtj9_disable(tj9);
 
-	mutex_unlock(&input_dev->mutex);
 	return 0;
 }
 
@@ -519,12 +514,11 @@ static int kxtj9_resume(struct device *dev)
 	struct kxtj9_data *tj9 = i2c_get_clientdata(client);
 	struct input_dev *input_dev = tj9->input_dev;
 
-	mutex_lock(&input_dev->mutex);
+	guard(mutex)(&input_dev->mutex);
 
 	if (input_device_enabled(input_dev))
 		kxtj9_enable(tj9);
 
-	mutex_unlock(&input_dev->mutex);
 	return 0;
 }
 

From 0a54609a890e808f9d7ad944a99a25b17153f65c Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:42:27 -0700
Subject: [PATCH 0143/1530] Input: drv260x - use guard notation when acquiring
 mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044244.1042174-8-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/drv260x.c | 50 +++++++++++++++++-------------------
 1 file changed, 24 insertions(+), 26 deletions(-)

diff --git a/drivers/input/misc/drv260x.c b/drivers/input/misc/drv260x.c
index 61b503835aa6d..96cd6a078c8ab 100644
--- a/drivers/input/misc/drv260x.c
+++ b/drivers/input/misc/drv260x.c
@@ -537,64 +537,62 @@ static int drv260x_probe(struct i2c_client *client)
 static int drv260x_suspend(struct device *dev)
 {
 	struct drv260x_data *haptics = dev_get_drvdata(dev);
-	int ret = 0;
+	int error;
 
-	mutex_lock(&haptics->input_dev->mutex);
+	guard(mutex)(&haptics->input_dev->mutex);
 
 	if (input_device_enabled(haptics->input_dev)) {
-		ret = regmap_update_bits(haptics->regmap,
-					 DRV260X_MODE,
-					 DRV260X_STANDBY_MASK,
-					 DRV260X_STANDBY);
-		if (ret) {
+		error = regmap_update_bits(haptics->regmap,
+					   DRV260X_MODE,
+					   DRV260X_STANDBY_MASK,
+					   DRV260X_STANDBY);
+		if (error) {
 			dev_err(dev, "Failed to set standby mode\n");
-			goto out;
+			return error;
 		}
 
 		gpiod_set_value(haptics->enable_gpio, 0);
 
-		ret = regulator_disable(haptics->regulator);
-		if (ret) {
+		error = regulator_disable(haptics->regulator);
+		if (error) {
 			dev_err(dev, "Failed to disable regulator\n");
 			regmap_update_bits(haptics->regmap,
 					   DRV260X_MODE,
 					   DRV260X_STANDBY_MASK, 0);
+			return error;
 		}
 	}
-out:
-	mutex_unlock(&haptics->input_dev->mutex);
-	return ret;
+
+	return 0;
 }
 
 static int drv260x_resume(struct device *dev)
 {
 	struct drv260x_data *haptics = dev_get_drvdata(dev);
-	int ret = 0;
+	int error;
 
-	mutex_lock(&haptics->input_dev->mutex);
+	guard(mutex)(&haptics->input_dev->mutex);
 
 	if (input_device_enabled(haptics->input_dev)) {
-		ret = regulator_enable(haptics->regulator);
-		if (ret) {
+		error = regulator_enable(haptics->regulator);
+		if (error) {
 			dev_err(dev, "Failed to enable regulator\n");
-			goto out;
+			return error;
 		}
 
-		ret = regmap_update_bits(haptics->regmap,
-					 DRV260X_MODE,
-					 DRV260X_STANDBY_MASK, 0);
-		if (ret) {
+		error = regmap_update_bits(haptics->regmap,
+					   DRV260X_MODE,
+					   DRV260X_STANDBY_MASK, 0);
+		if (error) {
 			dev_err(dev, "Failed to unset standby mode\n");
 			regulator_disable(haptics->regulator);
-			goto out;
+			return error;
 		}
 
 		gpiod_set_value(haptics->enable_gpio, 1);
 	}
 
-out:
-	mutex_unlock(&haptics->input_dev->mutex);
-	return ret;
+	return 0;
 }
 
 static DEFINE_SIMPLE_DEV_PM_OPS(drv260x_pm_ops, drv260x_suspend, drv260x_resume);

From cf3f3a08e10b366990ba8017406cbec257637805 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:42:28 -0700
Subject: [PATCH 0144/1530] Input: drv2665 - use guard notation when acquiring
 mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044244.1042174-9-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/drv2665.c | 44 +++++++++++++++++-------------------
 1 file changed, 21 insertions(+), 23 deletions(-)

diff --git a/drivers/input/misc/drv2665.c b/drivers/input/misc/drv2665.c
index 59ad69912bfd5..46842cb8ddd78 100644
--- a/drivers/input/misc/drv2665.c
+++ b/drivers/input/misc/drv2665.c
@@ -225,59 +225,57 @@ static int drv2665_probe(struct i2c_client *client)
 static int drv2665_suspend(struct device *dev)
 {
 	struct drv2665_data *haptics = dev_get_drvdata(dev);
-	int ret = 0;
+	int error;
 
-	mutex_lock(&haptics->input_dev->mutex);
+	guard(mutex)(&haptics->input_dev->mutex);
 
 	if (input_device_enabled(haptics->input_dev)) {
-		ret = regmap_update_bits(haptics->regmap, DRV2665_CTRL_2,
-					 DRV2665_STANDBY, DRV2665_STANDBY);
-		if (ret) {
+		error = regmap_update_bits(haptics->regmap, DRV2665_CTRL_2,
+					   DRV2665_STANDBY, DRV2665_STANDBY);
+		if (error) {
 			dev_err(dev, "Failed to set standby mode\n");
 			regulator_disable(haptics->regulator);
-			goto out;
+			return error;
 		}
 
-		ret = regulator_disable(haptics->regulator);
-		if (ret) {
+		error = regulator_disable(haptics->regulator);
+		if (error) {
 			dev_err(dev, "Failed to disable regulator\n");
 			regmap_update_bits(haptics->regmap,
 					   DRV2665_CTRL_2,
 					   DRV2665_STANDBY, 0);
+			return error;
 		}
 	}
-out:
-	mutex_unlock(&haptics->input_dev->mutex);
-	return ret;
+
+	return 0;
 }
 
 static int drv2665_resume(struct device *dev)
 {
 	struct drv2665_data *haptics = dev_get_drvdata(dev);
-	int ret = 0;
+	int error;
 
-	mutex_lock(&haptics->input_dev->mutex);
+	guard(mutex)(&haptics->input_dev->mutex);
 
 	if (input_device_enabled(haptics->input_dev)) {
-		ret = regulator_enable(haptics->regulator);
-		if (ret) {
+		error = regulator_enable(haptics->regulator);
+		if (error) {
 			dev_err(dev, "Failed to enable regulator\n");
-			goto out;
+			return error;
 		}
 
-		ret = regmap_update_bits(haptics->regmap, DRV2665_CTRL_2,
-					 DRV2665_STANDBY, 0);
-		if (ret) {
+		error = regmap_update_bits(haptics->regmap, DRV2665_CTRL_2,
+					   DRV2665_STANDBY, 0);
+		if (error) {
 			dev_err(dev, "Failed to unset standby mode\n");
 			regulator_disable(haptics->regulator);
-			goto out;
+			return error;
 		}
 
 	}
 
-out:
-	mutex_unlock(&haptics->input_dev->mutex);
-	return ret;
+	return 0;
 }
 
 static DEFINE_SIMPLE_DEV_PM_OPS(drv2665_pm_ops, drv2665_suspend, drv2665_resume);

From e5aee2d894fdff91c61d589c683c4a948e6d90b5 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:42:29 -0700
Subject: [PATCH 0145/1530] Input: drv2667 - use guard notation when acquiring
 mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044244.1042174-10-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/drv2667.c | 44 +++++++++++++++++-------------------
 1 file changed, 21 insertions(+), 23 deletions(-)

diff --git a/drivers/input/misc/drv2667.c b/drivers/input/misc/drv2667.c
index b53231d41b091..f952a24ec595b 100644
--- a/drivers/input/misc/drv2667.c
+++ b/drivers/input/misc/drv2667.c
@@ -402,59 +402,57 @@ static int drv2667_probe(struct i2c_client *client)
 static int drv2667_suspend(struct device *dev)
 {
 	struct drv2667_data *haptics = dev_get_drvdata(dev);
-	int ret = 0;
+	int error;
 
-	mutex_lock(&haptics->input_dev->mutex);
+	guard(mutex)(&haptics->input_dev->mutex);
 
 	if (input_device_enabled(haptics->input_dev)) {
-		ret = regmap_update_bits(haptics->regmap, DRV2667_CTRL_2,
-					 DRV2667_STANDBY, DRV2667_STANDBY);
-		if (ret) {
+		error = regmap_update_bits(haptics->regmap, DRV2667_CTRL_2,
+					   DRV2667_STANDBY, DRV2667_STANDBY);
+		if (error) {
 			dev_err(dev, "Failed to set standby mode\n");
 			regulator_disable(haptics->regulator);
-			goto out;
+			return error;
 		}
 
-		ret = regulator_disable(haptics->regulator);
-		if (ret) {
+		error = regulator_disable(haptics->regulator);
+		if (error) {
 			dev_err(dev, "Failed to disable regulator\n");
 			regmap_update_bits(haptics->regmap,
 					   DRV2667_CTRL_2,
 					   DRV2667_STANDBY, 0);
+			return error;
 		}
 	}
-out:
-	mutex_unlock(&haptics->input_dev->mutex);
-	return ret;
+
+	return 0;
 }
 
 static int drv2667_resume(struct device *dev)
 {
 	struct drv2667_data *haptics = dev_get_drvdata(dev);
-	int ret = 0;
+	int error;
 
-	mutex_lock(&haptics->input_dev->mutex);
+	guard(mutex)(&haptics->input_dev->mutex);
 
 	if (input_device_enabled(haptics->input_dev)) {
-		ret = regulator_enable(haptics->regulator);
-		if (ret) {
+		error = regulator_enable(haptics->regulator);
+		if (error) {
 			dev_err(dev, "Failed to enable regulator\n");
-			goto out;
+			return error;
 		}
 
-		ret = regmap_update_bits(haptics->regmap, DRV2667_CTRL_2,
-					 DRV2667_STANDBY, 0);
-		if (ret) {
+		error = regmap_update_bits(haptics->regmap, DRV2667_CTRL_2,
+					   DRV2667_STANDBY, 0);
+		if (error) {
 			dev_err(dev, "Failed to unset standby mode\n");
 			regulator_disable(haptics->regulator);
-			goto out;
+			return error;
 		}
 
 	}
 
-out:
-	mutex_unlock(&haptics->input_dev->mutex);
-	return ret;
+	return 0;
 }
 
 static DEFINE_SIMPLE_DEV_PM_OPS(drv2667_pm_ops, drv2667_suspend, drv2667_resume);

From 21f6b6b47c347e16e5ad95720ae7ebb99a72113c Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:42:30 -0700
Subject: [PATCH 0146/1530] Input: ideapad_slidebar - use guard notation when
 acquiring spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044244.1042174-11-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/ideapad_slidebar.c | 22 +++++-----------------
 1 file changed, 5 insertions(+), 17 deletions(-)

diff --git a/drivers/input/misc/ideapad_slidebar.c b/drivers/input/misc/ideapad_slidebar.c
index 7f1b3690b7e22..fea4a89607184 100644
--- a/drivers/input/misc/ideapad_slidebar.c
+++ b/drivers/input/misc/ideapad_slidebar.c
@@ -95,41 +95,29 @@ static struct platform_device *slidebar_platform_dev;
 
 static u8 slidebar_pos_get(void)
 {
-	u8 res;
-	unsigned long flags;
+	guard(spinlock_irqsave)(&io_lock);
 
-	spin_lock_irqsave(&io_lock, flags);
 	outb(0xf4, 0xff29);
 	outb(0xbf, 0xff2a);
-	res = inb(0xff2b);
-	spin_unlock_irqrestore(&io_lock, flags);
-
-	return res;
+	return inb(0xff2b);
 }
 
 static u8 slidebar_mode_get(void)
 {
-	u8 res;
-	unsigned long flags;
+	guard(spinlock_irqsave)(&io_lock);
 
-	spin_lock_irqsave(&io_lock, flags);
 	outb(0xf7, 0xff29);
 	outb(0x8b, 0xff2a);
-	res = inb(0xff2b);
-	spin_unlock_irqrestore(&io_lock, flags);
-
-	return res;
+	return inb(0xff2b);
 }
 
 static void slidebar_mode_set(u8 mode)
 {
-	unsigned long flags;
+	guard(spinlock_irqsave)(&io_lock);
 
-	spin_lock_irqsave(&io_lock, flags);
 	outb(0xf7, 0xff29);
 	outb(0x8b, 0xff2a);
 	outb(mode, 0xff2b);
-	spin_unlock_irqrestore(&io_lock, flags);
 }
 
 static bool slidebar_i8042_filter(unsigned char data, unsigned char str,

From 543429257d8884742127006eeb6a0ec543dd332f Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:47:33 -0700
Subject: [PATCH 0147/1530] Input: ibm-panel - use guard notation when
 acquiring spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Reviewed-by: Eddie James <eajames@linux.ibm.com>
Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044735.1047285-1-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/ibm-panel.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/input/misc/ibm-panel.c b/drivers/input/misc/ibm-panel.c
index 867ac7aa10d2c..aa48f62d7ea05 100644
--- a/drivers/input/misc/ibm-panel.c
+++ b/drivers/input/misc/ibm-panel.c
@@ -77,12 +77,11 @@ static void ibm_panel_process_command(struct ibm_panel *panel)
 static int ibm_panel_i2c_slave_cb(struct i2c_client *client,
 				  enum i2c_slave_event event, u8 *val)
 {
-	unsigned long flags;
 	struct ibm_panel *panel = i2c_get_clientdata(client);
 
 	dev_dbg(&panel->input->dev, "event: %u data: %02x\n", event, *val);
 
-	spin_lock_irqsave(&panel->lock, flags);
+	guard(spinlock_irqsave)(&panel->lock);
 
 	switch (event) {
 	case I2C_SLAVE_STOP:
@@ -114,8 +113,6 @@ static int ibm_panel_i2c_slave_cb(struct i2c_client *client,
 		break;
 	}
 
-	spin_unlock_irqrestore(&panel->lock, flags);
-
 	return 0;
 }
 

From d88460e48014a279b95e77ef24074c401f9d37c6 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:47:55 -0700
Subject: [PATCH 0148/1530] Input: iqs269a - use guard notation when acquiring
 mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Reviewed-by: Jeff LaBundy <jeff@labundy.com>
Link: https://lore.kernel.org/r/20240904044756.1047629-1-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/iqs269a.c | 46 +++++++++++++-----------------------
 1 file changed, 16 insertions(+), 30 deletions(-)

diff --git a/drivers/input/misc/iqs269a.c b/drivers/input/misc/iqs269a.c
index 843f8a3f3410d..c34d847fa4af5 100644
--- a/drivers/input/misc/iqs269a.c
+++ b/drivers/input/misc/iqs269a.c
@@ -365,7 +365,7 @@ static int iqs269_ati_mode_set(struct iqs269_private *iqs269,
 	if (mode > IQS269_CHx_ENG_A_ATI_MODE_MAX)
 		return -EINVAL;
 
-	mutex_lock(&iqs269->lock);
+	guard(mutex)(&iqs269->lock);
 
 	engine_a = be16_to_cpu(ch_reg[ch_num].engine_a);
 
@@ -375,8 +375,6 @@ static int iqs269_ati_mode_set(struct iqs269_private *iqs269,
 	ch_reg[ch_num].engine_a = cpu_to_be16(engine_a);
 	iqs269->ati_current = false;
 
-	mutex_unlock(&iqs269->lock);
-
 	return 0;
 }
 
@@ -389,9 +387,9 @@ static int iqs269_ati_mode_get(struct iqs269_private *iqs269,
 	if (ch_num >= IQS269_NUM_CH)
 		return -EINVAL;
 
-	mutex_lock(&iqs269->lock);
+	guard(mutex)(&iqs269->lock);
+
 	engine_a = be16_to_cpu(ch_reg[ch_num].engine_a);
-	mutex_unlock(&iqs269->lock);
 
 	engine_a &= IQS269_CHx_ENG_A_ATI_MODE_MASK;
 	*mode = (engine_a >> IQS269_CHx_ENG_A_ATI_MODE_SHIFT);
@@ -429,7 +427,7 @@ static int iqs269_ati_base_set(struct iqs269_private *iqs269,
 		return -EINVAL;
 	}
 
-	mutex_lock(&iqs269->lock);
+	guard(mutex)(&iqs269->lock);
 
 	engine_b = be16_to_cpu(ch_reg[ch_num].engine_b);
 
@@ -439,8 +437,6 @@ static int iqs269_ati_base_set(struct iqs269_private *iqs269,
 	ch_reg[ch_num].engine_b = cpu_to_be16(engine_b);
 	iqs269->ati_current = false;
 
-	mutex_unlock(&iqs269->lock);
-
 	return 0;
 }
 
@@ -453,9 +449,9 @@ static int iqs269_ati_base_get(struct iqs269_private *iqs269,
 	if (ch_num >= IQS269_NUM_CH)
 		return -EINVAL;
 
-	mutex_lock(&iqs269->lock);
+	guard(mutex)(&iqs269->lock);
+
 	engine_b = be16_to_cpu(ch_reg[ch_num].engine_b);
-	mutex_unlock(&iqs269->lock);
 
 	switch (engine_b & IQS269_CHx_ENG_B_ATI_BASE_MASK) {
 	case IQS269_CHx_ENG_B_ATI_BASE_75:
@@ -491,7 +487,7 @@ static int iqs269_ati_target_set(struct iqs269_private *iqs269,
 	if (target > IQS269_CHx_ENG_B_ATI_TARGET_MAX)
 		return -EINVAL;
 
-	mutex_lock(&iqs269->lock);
+	guard(mutex)(&iqs269->lock);
 
 	engine_b = be16_to_cpu(ch_reg[ch_num].engine_b);
 
@@ -501,8 +497,6 @@ static int iqs269_ati_target_set(struct iqs269_private *iqs269,
 	ch_reg[ch_num].engine_b = cpu_to_be16(engine_b);
 	iqs269->ati_current = false;
 
-	mutex_unlock(&iqs269->lock);
-
 	return 0;
 }
 
@@ -515,10 +509,9 @@ static int iqs269_ati_target_get(struct iqs269_private *iqs269,
 	if (ch_num >= IQS269_NUM_CH)
 		return -EINVAL;
 
-	mutex_lock(&iqs269->lock);
-	engine_b = be16_to_cpu(ch_reg[ch_num].engine_b);
-	mutex_unlock(&iqs269->lock);
+	guard(mutex)(&iqs269->lock);
 
+	engine_b = be16_to_cpu(ch_reg[ch_num].engine_b);
 	*target = (engine_b & IQS269_CHx_ENG_B_ATI_TARGET_MASK) * 32;
 
 	return 0;
@@ -1199,7 +1192,7 @@ static int iqs269_dev_init(struct iqs269_private *iqs269)
 {
 	int error;
 
-	mutex_lock(&iqs269->lock);
+	guard(mutex)(&iqs269->lock);
 
 	/*
 	 * Early revisions of silicon require the following workaround in order
@@ -1210,19 +1203,19 @@ static int iqs269_dev_init(struct iqs269_private *iqs269)
 		error = regmap_multi_reg_write(iqs269->regmap, iqs269_tws_init,
 					       ARRAY_SIZE(iqs269_tws_init));
 		if (error)
-			goto err_mutex;
+			return error;
 	}
 
 	error = regmap_update_bits(iqs269->regmap, IQS269_HALL_UI,
 				   IQS269_HALL_UI_ENABLE,
 				   iqs269->hall_enable ? ~0 : 0);
 	if (error)
-		goto err_mutex;
+		return error;
 
 	error = regmap_raw_write(iqs269->regmap, IQS269_SYS_SETTINGS,
 				 &iqs269->sys_reg, sizeof(iqs269->sys_reg));
 	if (error)
-		goto err_mutex;
+		return error;
 
 	/*
 	 * The following delay gives the device time to deassert its RDY output
@@ -1232,10 +1225,7 @@ static int iqs269_dev_init(struct iqs269_private *iqs269)
 
 	iqs269->ati_current = true;
 
-err_mutex:
-	mutex_unlock(&iqs269->lock);
-
-	return error;
+	return 0;
 }
 
 static int iqs269_input_init(struct iqs269_private *iqs269)
@@ -1580,13 +1570,11 @@ static ssize_t hall_enable_store(struct device *dev,
 	if (error)
 		return error;
 
-	mutex_lock(&iqs269->lock);
+	guard(mutex)(&iqs269->lock);
 
 	iqs269->hall_enable = val;
 	iqs269->ati_current = false;
 
-	mutex_unlock(&iqs269->lock);
-
 	return count;
 }
 
@@ -1643,13 +1631,11 @@ static ssize_t rx_enable_store(struct device *dev,
 	if (val > 0xFF)
 		return -EINVAL;
 
-	mutex_lock(&iqs269->lock);
+	guard(mutex)(&iqs269->lock);
 
 	ch_reg[iqs269->ch_num].rx_enable = val;
 	iqs269->ati_current = false;
 
-	mutex_unlock(&iqs269->lock);
-
 	return count;
 }
 

From 9a540b67a9c260ae55e7e93443a4413cccf5523d Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:48:05 -0700
Subject: [PATCH 0149/1530] Input: iqs269a - use cleanup facility for fwnodes

Use __free(fwnode_handle) cleanup facility to ensure that references to
acquired fwnodes are dropped at appropriate times automatically.

Reviewed-by: Jeff LaBundy <jeff@labundy.com>
Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044806.1047847-1-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/iqs269a.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/input/misc/iqs269a.c b/drivers/input/misc/iqs269a.c
index c34d847fa4af5..1851848e2cd38 100644
--- a/drivers/input/misc/iqs269a.c
+++ b/drivers/input/misc/iqs269a.c
@@ -550,7 +550,6 @@ static int iqs269_parse_chan(struct iqs269_private *iqs269,
 			     const struct fwnode_handle *ch_node)
 {
 	struct i2c_client *client = iqs269->client;
-	struct fwnode_handle *ev_node;
 	struct iqs269_ch_reg *ch_reg;
 	u16 engine_a, engine_b;
 	unsigned int reg, val;
@@ -727,8 +726,9 @@ static int iqs269_parse_chan(struct iqs269_private *iqs269,
 	}
 
 	for (i = 0; i < ARRAY_SIZE(iqs269_events); i++) {
-		ev_node = fwnode_get_named_child_node(ch_node,
-						      iqs269_events[i].name);
+		struct fwnode_handle *ev_node __free(fwnode_handle) =
+			fwnode_get_named_child_node(ch_node,
+						    iqs269_events[i].name);
 		if (!ev_node)
 			continue;
 
@@ -737,7 +737,6 @@ static int iqs269_parse_chan(struct iqs269_private *iqs269,
 				dev_err(&client->dev,
 					"Invalid channel %u threshold: %u\n",
 					reg, val);
-				fwnode_handle_put(ev_node);
 				return -EINVAL;
 			}
 
@@ -751,7 +750,6 @@ static int iqs269_parse_chan(struct iqs269_private *iqs269,
 				dev_err(&client->dev,
 					"Invalid channel %u hysteresis: %u\n",
 					reg, val);
-				fwnode_handle_put(ev_node);
 				return -EINVAL;
 			}
 
@@ -767,7 +765,6 @@ static int iqs269_parse_chan(struct iqs269_private *iqs269,
 		}
 
 		error = fwnode_property_read_u32(ev_node, "linux,code", &val);
-		fwnode_handle_put(ev_node);
 		if (error == -EINVAL) {
 			continue;
 		} else if (error) {

From 52776177d8b7ea4ffd71c6728d472f7aba8855c5 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:48:13 -0700
Subject: [PATCH 0150/1530] Input: iqs626a - use cleanup facility for fwnodes

Use __free(fwnode_handle) cleanup facility to ensure that references to
acquired fwnodes are dropped at appropriate times automatically.

Reviewed-by: Jeff LaBundy <jeff@labundy.com>
Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044814.1048062-1-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/iqs626a.c | 22 ++++++----------------
 1 file changed, 6 insertions(+), 16 deletions(-)

diff --git a/drivers/input/misc/iqs626a.c b/drivers/input/misc/iqs626a.c
index 0dab54d3a0603..7a6e6927f3312 100644
--- a/drivers/input/misc/iqs626a.c
+++ b/drivers/input/misc/iqs626a.c
@@ -462,7 +462,6 @@ iqs626_parse_events(struct iqs626_private *iqs626,
 {
 	struct iqs626_sys_reg *sys_reg = &iqs626->sys_reg;
 	struct i2c_client *client = iqs626->client;
-	struct fwnode_handle *ev_node;
 	const char *ev_name;
 	u8 *thresh, *hyst;
 	unsigned int val;
@@ -501,6 +500,7 @@ iqs626_parse_events(struct iqs626_private *iqs626,
 		if (!iqs626_channels[ch_id].events[i])
 			continue;
 
+		struct fwnode_handle *ev_node __free(fwnode_handle) = NULL;
 		if (ch_id == IQS626_CH_TP_2 || ch_id == IQS626_CH_TP_3) {
 			/*
 			 * Trackpad touch events are simply described under the
@@ -530,7 +530,6 @@ iqs626_parse_events(struct iqs626_private *iqs626,
 					dev_err(&client->dev,
 						"Invalid input type: %u\n",
 						val);
-					fwnode_handle_put(ev_node);
 					return -EINVAL;
 				}
 
@@ -545,7 +544,6 @@ iqs626_parse_events(struct iqs626_private *iqs626,
 				dev_err(&client->dev,
 					"Invalid %s channel hysteresis: %u\n",
 					fwnode_get_name(ch_node), val);
-				fwnode_handle_put(ev_node);
 				return -EINVAL;
 			}
 
@@ -566,7 +564,6 @@ iqs626_parse_events(struct iqs626_private *iqs626,
 				dev_err(&client->dev,
 					"Invalid %s channel threshold: %u\n",
 					fwnode_get_name(ch_node), val);
-				fwnode_handle_put(ev_node);
 				return -EINVAL;
 			}
 
@@ -575,8 +572,6 @@ iqs626_parse_events(struct iqs626_private *iqs626,
 			else
 				*(thresh + iqs626_events[i].th_offs) = val;
 		}
-
-		fwnode_handle_put(ev_node);
 	}
 
 	return 0;
@@ -774,12 +769,12 @@ static int iqs626_parse_trackpad(struct iqs626_private *iqs626,
 	for (i = 0; i < iqs626_channels[ch_id].num_ch; i++) {
 		u8 *ati_base = &sys_reg->tp_grp_reg.ch_reg_tp[i].ati_base;
 		u8 *thresh = &sys_reg->tp_grp_reg.ch_reg_tp[i].thresh;
-		struct fwnode_handle *tc_node;
 		char tc_name[10];
 
 		snprintf(tc_name, sizeof(tc_name), "channel-%d", i);
 
-		tc_node = fwnode_get_named_child_node(ch_node, tc_name);
+		struct fwnode_handle *tc_node __free(fwnode_handle) =
+				fwnode_get_named_child_node(ch_node, tc_name);
 		if (!tc_node)
 			continue;
 
@@ -790,7 +785,6 @@ static int iqs626_parse_trackpad(struct iqs626_private *iqs626,
 				dev_err(&client->dev,
 					"Invalid %s %s ATI base: %u\n",
 					fwnode_get_name(ch_node), tc_name, val);
-				fwnode_handle_put(tc_node);
 				return -EINVAL;
 			}
 
@@ -803,14 +797,11 @@ static int iqs626_parse_trackpad(struct iqs626_private *iqs626,
 				dev_err(&client->dev,
 					"Invalid %s %s threshold: %u\n",
 					fwnode_get_name(ch_node), tc_name, val);
-				fwnode_handle_put(tc_node);
 				return -EINVAL;
 			}
 
 			*thresh = val;
 		}
-
-		fwnode_handle_put(tc_node);
 	}
 
 	if (!fwnode_property_present(ch_node, "linux,keycodes"))
@@ -1233,7 +1224,6 @@ static int iqs626_parse_prop(struct iqs626_private *iqs626)
 {
 	struct iqs626_sys_reg *sys_reg = &iqs626->sys_reg;
 	struct i2c_client *client = iqs626->client;
-	struct fwnode_handle *ch_node;
 	unsigned int val;
 	int error, i;
 	u16 general;
@@ -1375,13 +1365,13 @@ static int iqs626_parse_prop(struct iqs626_private *iqs626)
 	sys_reg->active = 0;
 
 	for (i = 0; i < ARRAY_SIZE(iqs626_channels); i++) {
-		ch_node = device_get_named_child_node(&client->dev,
-						      iqs626_channels[i].name);
+		struct fwnode_handle *ch_node __free(fwnode_handle) =
+			device_get_named_child_node(&client->dev,
+						    iqs626_channels[i].name);
 		if (!ch_node)
 			continue;
 
 		error = iqs626_parse_channel(iqs626, ch_node, i);
-		fwnode_handle_put(ch_node);
 		if (error)
 			return error;
 

From 452e0adff26188fb13bfc862f665bdc684ce64fc Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:48:25 -0700
Subject: [PATCH 0151/1530] Input: iqs7222 - use cleanup facility for fwnodes

Use __free(fwnode_handle) cleanup facility to ensure that references to
acquired fwnodes are dropped at appropriate times automatically.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Reviewed-by: Jeff LaBundy <jeff@labundy.com>
Link: https://lore.kernel.org/r/20240904044825.1048256-1-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/iqs7222.c | 30 ++++++++++++++----------------
 1 file changed, 14 insertions(+), 16 deletions(-)

diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c
index 9ca5a743f19fe..d9b87606ff7a5 100644
--- a/drivers/input/misc/iqs7222.c
+++ b/drivers/input/misc/iqs7222.c
@@ -2385,9 +2385,9 @@ static int iqs7222_parse_chan(struct iqs7222_private *iqs7222,
 	for (i = 0; i < ARRAY_SIZE(iqs7222_kp_events); i++) {
 		const char *event_name = iqs7222_kp_events[i].name;
 		u16 event_enable = iqs7222_kp_events[i].enable;
-		struct fwnode_handle *event_node;
 
-		event_node = fwnode_get_named_child_node(chan_node, event_name);
+		struct fwnode_handle *event_node __free(fwnode_handle) =
+			fwnode_get_named_child_node(chan_node, event_name);
 		if (!event_node)
 			continue;
 
@@ -2408,7 +2408,6 @@ static int iqs7222_parse_chan(struct iqs7222_private *iqs7222,
 				dev_err(&client->dev,
 					"Invalid %s press timeout: %u\n",
 					fwnode_get_name(event_node), val);
-				fwnode_handle_put(event_node);
 				return -EINVAL;
 			}
 
@@ -2418,7 +2417,6 @@ static int iqs7222_parse_chan(struct iqs7222_private *iqs7222,
 			dev_err(&client->dev,
 				"Failed to read %s press timeout: %d\n",
 				fwnode_get_name(event_node), error);
-			fwnode_handle_put(event_node);
 			return error;
 		}
 
@@ -2429,7 +2427,6 @@ static int iqs7222_parse_chan(struct iqs7222_private *iqs7222,
 					    dev_desc->touch_link - (i ? 0 : 2),
 					    &iqs7222->kp_type[chan_index][i],
 					    &iqs7222->kp_code[chan_index][i]);
-		fwnode_handle_put(event_node);
 		if (error)
 			return error;
 
@@ -2604,10 +2601,10 @@ static int iqs7222_parse_sldr(struct iqs7222_private *iqs7222,
 
 	for (i = 0; i < ARRAY_SIZE(iqs7222_sl_events); i++) {
 		const char *event_name = iqs7222_sl_events[i].name;
-		struct fwnode_handle *event_node;
 		enum iqs7222_reg_key_id reg_key;
 
-		event_node = fwnode_get_named_child_node(sldr_node, event_name);
+		struct fwnode_handle *event_node __free(fwnode_handle) =
+			fwnode_get_named_child_node(sldr_node, event_name);
 		if (!event_node)
 			continue;
 
@@ -2639,7 +2636,6 @@ static int iqs7222_parse_sldr(struct iqs7222_private *iqs7222,
 					      : sldr_setup[4 + reg_offset],
 					    NULL,
 					    &iqs7222->sl_code[sldr_index][i]);
-		fwnode_handle_put(event_node);
 		if (error)
 			return error;
 
@@ -2742,9 +2738,9 @@ static int iqs7222_parse_tpad(struct iqs7222_private *iqs7222,
 
 	for (i = 0; i < ARRAY_SIZE(iqs7222_tp_events); i++) {
 		const char *event_name = iqs7222_tp_events[i].name;
-		struct fwnode_handle *event_node;
 
-		event_node = fwnode_get_named_child_node(tpad_node, event_name);
+		struct fwnode_handle *event_node __free(fwnode_handle) =
+			fwnode_get_named_child_node(tpad_node, event_name);
 		if (!event_node)
 			continue;
 
@@ -2760,7 +2756,6 @@ static int iqs7222_parse_tpad(struct iqs7222_private *iqs7222,
 					    iqs7222_tp_events[i].link, 1566,
 					    NULL,
 					    &iqs7222->tp_code[i]);
-		fwnode_handle_put(event_node);
 		if (error)
 			return error;
 
@@ -2818,9 +2813,9 @@ static int iqs7222_parse_reg_grp(struct iqs7222_private *iqs7222,
 				 int reg_grp_index)
 {
 	struct i2c_client *client = iqs7222->client;
-	struct fwnode_handle *reg_grp_node;
 	int error;
 
+	struct fwnode_handle *reg_grp_node __free(fwnode_handle) = NULL;
 	if (iqs7222_reg_grp_names[reg_grp]) {
 		char reg_grp_name[16];
 
@@ -2838,14 +2833,17 @@ static int iqs7222_parse_reg_grp(struct iqs7222_private *iqs7222,
 
 	error = iqs7222_parse_props(iqs7222, reg_grp_node, reg_grp_index,
 				    reg_grp, IQS7222_REG_KEY_NONE);
+	if (error)
+		return error;
 
-	if (!error && iqs7222_parse_extra[reg_grp])
+	if (iqs7222_parse_extra[reg_grp]) {
 		error = iqs7222_parse_extra[reg_grp](iqs7222, reg_grp_node,
 						     reg_grp_index);
+		if (error)
+			return error;
+	}
 
-	fwnode_handle_put(reg_grp_node);
-
-	return error;
+	return 0;
 }
 
 static int iqs7222_parse_all(struct iqs7222_private *iqs7222)

From 844111df52dc2d1f2da6c80d4b7e219d7b6e16f9 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:48:33 -0700
Subject: [PATCH 0152/1530] Input: max8997_haptic - use guard notation when
 acquiring mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044834.1048468-1-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/max8997_haptic.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/input/misc/max8997_haptic.c b/drivers/input/misc/max8997_haptic.c
index 11cac4b7dddc0..2853455daef2a 100644
--- a/drivers/input/misc/max8997_haptic.c
+++ b/drivers/input/misc/max8997_haptic.c
@@ -153,19 +153,19 @@ static void max8997_haptic_enable(struct max8997_haptic *chip)
 {
 	int error;
 
-	mutex_lock(&chip->mutex);
+	guard(mutex)(&chip->mutex);
 
 	error = max8997_haptic_set_duty_cycle(chip);
 	if (error) {
 		dev_err(chip->dev, "set_pwm_cycle failed, error: %d\n", error);
-		goto out;
+		return;
 	}
 
 	if (!chip->enabled) {
 		error = regulator_enable(chip->regulator);
 		if (error) {
 			dev_err(chip->dev, "Failed to enable regulator\n");
-			goto out;
+			return;
 		}
 		max8997_haptic_configure(chip);
 		if (chip->mode == MAX8997_EXTERNAL_MODE) {
@@ -173,19 +173,16 @@ static void max8997_haptic_enable(struct max8997_haptic *chip)
 			if (error) {
 				dev_err(chip->dev, "Failed to enable PWM\n");
 				regulator_disable(chip->regulator);
-				goto out;
+				return;
 			}
 		}
 		chip->enabled = true;
 	}
-
-out:
-	mutex_unlock(&chip->mutex);
 }
 
 static void max8997_haptic_disable(struct max8997_haptic *chip)
 {
-	mutex_lock(&chip->mutex);
+	guard(mutex)(&chip->mutex);
 
 	if (chip->enabled) {
 		chip->enabled = false;
@@ -194,8 +191,6 @@ static void max8997_haptic_disable(struct max8997_haptic *chip)
 			pwm_disable(chip->pwm);
 		regulator_disable(chip->regulator);
 	}
-
-	mutex_unlock(&chip->mutex);
 }
 
 static void max8997_haptic_play_effect_work(struct work_struct *work)

From 0e7b4bc31d171856fcb753f653e0f00855763bf3 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 13:59:18 -0700
Subject: [PATCH 0153/1530] Input: pegasus_notetaker - use guard notation when
 acquiring mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/ZtjKJsArLu3byTU6@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/tablet/pegasus_notetaker.c | 86 +++++++++++++-----------
 1 file changed, 48 insertions(+), 38 deletions(-)

diff --git a/drivers/input/tablet/pegasus_notetaker.c b/drivers/input/tablet/pegasus_notetaker.c
index a68da2988f9cd..8d6b71d597931 100644
--- a/drivers/input/tablet/pegasus_notetaker.c
+++ b/drivers/input/tablet/pegasus_notetaker.c
@@ -214,6 +214,28 @@ static void pegasus_init(struct work_struct *work)
 			error);
 }
 
+static int __pegasus_open(struct pegasus *pegasus)
+{
+	int error;
+
+	guard(mutex)(&pegasus->pm_mutex);
+
+	pegasus->irq->dev = pegasus->usbdev;
+	if (usb_submit_urb(pegasus->irq, GFP_KERNEL))
+		return -EIO;
+
+	error = pegasus_set_mode(pegasus, PEN_MODE_XY, NOTETAKER_LED_MOUSE);
+	if (error) {
+		usb_kill_urb(pegasus->irq);
+		cancel_work_sync(&pegasus->init);
+		return error;
+	}
+
+	pegasus->is_open = true;
+
+	return 0;
+}
+
 static int pegasus_open(struct input_dev *dev)
 {
 	struct pegasus *pegasus = input_get_drvdata(dev);
@@ -223,39 +245,25 @@ static int pegasus_open(struct input_dev *dev)
 	if (error)
 		return error;
 
-	mutex_lock(&pegasus->pm_mutex);
-	pegasus->irq->dev = pegasus->usbdev;
-	if (usb_submit_urb(pegasus->irq, GFP_KERNEL)) {
-		error = -EIO;
-		goto err_autopm_put;
+	error = __pegasus_open(pegasus);
+	if (error) {
+		usb_autopm_put_interface(pegasus->intf);
+		return error;
 	}
 
-	error = pegasus_set_mode(pegasus, PEN_MODE_XY, NOTETAKER_LED_MOUSE);
-	if (error)
-		goto err_kill_urb;
-
-	pegasus->is_open = true;
-	mutex_unlock(&pegasus->pm_mutex);
 	return 0;
-
-err_kill_urb:
-	usb_kill_urb(pegasus->irq);
-	cancel_work_sync(&pegasus->init);
-err_autopm_put:
-	mutex_unlock(&pegasus->pm_mutex);
-	usb_autopm_put_interface(pegasus->intf);
-	return error;
 }
 
 static void pegasus_close(struct input_dev *dev)
 {
 	struct pegasus *pegasus = input_get_drvdata(dev);
 
-	mutex_lock(&pegasus->pm_mutex);
-	usb_kill_urb(pegasus->irq);
-	cancel_work_sync(&pegasus->init);
-	pegasus->is_open = false;
-	mutex_unlock(&pegasus->pm_mutex);
+	scoped_guard(mutex, &pegasus->pm_mutex) {
+		usb_kill_urb(pegasus->irq);
+		cancel_work_sync(&pegasus->init);
+
+		pegasus->is_open = false;
+	}
 
 	usb_autopm_put_interface(pegasus->intf);
 }
@@ -411,10 +419,10 @@ static int pegasus_suspend(struct usb_interface *intf, pm_message_t message)
 {
 	struct pegasus *pegasus = usb_get_intfdata(intf);
 
-	mutex_lock(&pegasus->pm_mutex);
+	guard(mutex)(&pegasus->pm_mutex);
+
 	usb_kill_urb(pegasus->irq);
 	cancel_work_sync(&pegasus->init);
-	mutex_unlock(&pegasus->pm_mutex);
 
 	return 0;
 }
@@ -422,31 +430,33 @@ static int pegasus_suspend(struct usb_interface *intf, pm_message_t message)
 static int pegasus_resume(struct usb_interface *intf)
 {
 	struct pegasus *pegasus = usb_get_intfdata(intf);
-	int retval = 0;
 
-	mutex_lock(&pegasus->pm_mutex);
+	guard(mutex)(&pegasus->pm_mutex);
+
 	if (pegasus->is_open && usb_submit_urb(pegasus->irq, GFP_NOIO) < 0)
-		retval = -EIO;
-	mutex_unlock(&pegasus->pm_mutex);
+		return -EIO;
 
-	return retval;
+	return 0;
 }
 
 static int pegasus_reset_resume(struct usb_interface *intf)
 {
 	struct pegasus *pegasus = usb_get_intfdata(intf);
-	int retval = 0;
+	int error;
+
+	guard(mutex)(&pegasus->pm_mutex);
 
-	mutex_lock(&pegasus->pm_mutex);
 	if (pegasus->is_open) {
-		retval = pegasus_set_mode(pegasus, PEN_MODE_XY,
+		error = pegasus_set_mode(pegasus, PEN_MODE_XY,
 					  NOTETAKER_LED_MOUSE);
-		if (!retval && usb_submit_urb(pegasus->irq, GFP_NOIO) < 0)
-			retval = -EIO;
+		if (error)
+			return error;
+
+		if (usb_submit_urb(pegasus->irq, GFP_NOIO) < 0)
+			return -EIO;
 	}
-	mutex_unlock(&pegasus->pm_mutex);
 
-	return retval;
+	return 0;
 }
 
 static const struct usb_device_id pegasus_ids[] = {

From c6849218541d29a7725fd375b7095cb02df4b422 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:49:00 -0700
Subject: [PATCH 0154/1530] Input: powermate - use guard notation when
 acquiring spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044902.1049017-1-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/powermate.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/drivers/input/misc/powermate.c b/drivers/input/misc/powermate.c
index 4b039abffc4b8..ecb92ee5ebbc0 100644
--- a/drivers/input/misc/powermate.c
+++ b/drivers/input/misc/powermate.c
@@ -194,22 +194,18 @@ static void powermate_sync_state(struct powermate_device *pm)
 static void powermate_config_complete(struct urb *urb)
 {
 	struct powermate_device *pm = urb->context;
-	unsigned long flags;
 
 	if (urb->status)
 		printk(KERN_ERR "powermate: config urb returned %d\n", urb->status);
 
-	spin_lock_irqsave(&pm->lock, flags);
+	guard(spinlock_irqsave)(&pm->lock);
 	powermate_sync_state(pm);
-	spin_unlock_irqrestore(&pm->lock, flags);
 }
 
 /* Set the LED up as described and begin the sync with the hardware if required */
 static void powermate_pulse_led(struct powermate_device *pm, int static_brightness, int pulse_speed,
 				int pulse_table, int pulse_asleep, int pulse_awake)
 {
-	unsigned long flags;
-
 	if (pulse_speed < 0)
 		pulse_speed = 0;
 	if (pulse_table < 0)
@@ -222,8 +218,7 @@ static void powermate_pulse_led(struct powermate_device *pm, int static_brightne
 	pulse_asleep = !!pulse_asleep;
 	pulse_awake = !!pulse_awake;
 
-
-	spin_lock_irqsave(&pm->lock, flags);
+	guard(spinlock_irqsave)(&pm->lock);
 
 	/* mark state updates which are required */
 	if (static_brightness != pm->static_brightness) {
@@ -245,8 +240,6 @@ static void powermate_pulse_led(struct powermate_device *pm, int static_brightne
 	}
 
 	powermate_sync_state(pm);
-
-	spin_unlock_irqrestore(&pm->lock, flags);
 }
 
 /* Callback from the Input layer when an event arrives from userspace to configure the LED */

From 5bd3ade12109b276337ce85b950e09e09043e748 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:49:12 -0700
Subject: [PATCH 0155/1530] Input: pwm-beeper - use guard notation when
 acquiring spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044914.1049280-1-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/pwm-beeper.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/input/misc/pwm-beeper.c b/drivers/input/misc/pwm-beeper.c
index 5b9aedf4362f4..0e19e97d98ec2 100644
--- a/drivers/input/misc/pwm-beeper.c
+++ b/drivers/input/misc/pwm-beeper.c
@@ -203,9 +203,9 @@ static int pwm_beeper_suspend(struct device *dev)
 	 * beeper->suspended, but to ensure that pwm_beeper_event
 	 * does not re-submit work once flag is set.
 	 */
-	spin_lock_irq(&beeper->input->event_lock);
-	beeper->suspended = true;
-	spin_unlock_irq(&beeper->input->event_lock);
+	scoped_guard(spinlock_irq, &beeper->input->event_lock) {
+		beeper->suspended = true;
+	}
 
 	pwm_beeper_stop(beeper);
 
@@ -216,9 +216,9 @@ static int pwm_beeper_resume(struct device *dev)
 {
 	struct pwm_beeper *beeper = dev_get_drvdata(dev);
 
-	spin_lock_irq(&beeper->input->event_lock);
-	beeper->suspended = false;
-	spin_unlock_irq(&beeper->input->event_lock);
+	scoped_guard(spinlock_irq, &beeper->input->event_lock) {
+		beeper->suspended = false;
+	}
 
 	/* Let worker figure out if we should resume beeping */
 	schedule_work(&beeper->work);

From 2dc387620b85f2061fdcab172efdd9856999e987 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 13:55:07 -0700
Subject: [PATCH 0156/1530] Input: regulator-haptic - use guard notation when
 acquiring mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/ZtjJKxQRRzJE0aWZ@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/regulator-haptic.c | 24 ++++++++----------------
 1 file changed, 8 insertions(+), 16 deletions(-)

diff --git a/drivers/input/misc/regulator-haptic.c b/drivers/input/misc/regulator-haptic.c
index 02f73b7c04628..3666ba6d1f307 100644
--- a/drivers/input/misc/regulator-haptic.c
+++ b/drivers/input/misc/regulator-haptic.c
@@ -83,12 +83,10 @@ static void regulator_haptic_work(struct work_struct *work)
 	struct regulator_haptic *haptic = container_of(work,
 					struct regulator_haptic, work);
 
-	mutex_lock(&haptic->mutex);
+	guard(mutex)(&haptic->mutex);
 
 	if (!haptic->suspended)
 		regulator_haptic_set_voltage(haptic, haptic->magnitude);
-
-	mutex_unlock(&haptic->mutex);
 }
 
 static int regulator_haptic_play_effect(struct input_dev *input, void *data,
@@ -205,19 +203,15 @@ static int regulator_haptic_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct regulator_haptic *haptic = platform_get_drvdata(pdev);
-	int error;
 
-	error = mutex_lock_interruptible(&haptic->mutex);
-	if (error)
-		return error;
-
-	regulator_haptic_set_voltage(haptic, 0);
+	scoped_guard(mutex_intr, &haptic->mutex) {
+		regulator_haptic_set_voltage(haptic, 0);
+		haptic->suspended = true;
 
-	haptic->suspended = true;
-
-	mutex_unlock(&haptic->mutex);
+		return 0;
+	}
 
-	return 0;
+	return -EINTR;
 }
 
 static int regulator_haptic_resume(struct device *dev)
@@ -226,7 +220,7 @@ static int regulator_haptic_resume(struct device *dev)
 	struct regulator_haptic *haptic = platform_get_drvdata(pdev);
 	unsigned int magnitude;
 
-	mutex_lock(&haptic->mutex);
+	guard(mutex)(&haptic->mutex);
 
 	haptic->suspended = false;
 
@@ -234,8 +228,6 @@ static int regulator_haptic_resume(struct device *dev)
 	if (magnitude)
 		regulator_haptic_set_voltage(haptic, magnitude);
 
-	mutex_unlock(&haptic->mutex);
-
 	return 0;
 }
 

From 868d163aec12bf48fccbf15fd9cf06a55b744317 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:49:29 -0700
Subject: [PATCH 0157/1530] Input: rotary_encoder - use guard notation when
 acquiring mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044929.1049700-1-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/rotary_encoder.c | 23 ++++++++---------------
 1 file changed, 8 insertions(+), 15 deletions(-)

diff --git a/drivers/input/misc/rotary_encoder.c b/drivers/input/misc/rotary_encoder.c
index e94cab8133bec..f706e19974171 100644
--- a/drivers/input/misc/rotary_encoder.c
+++ b/drivers/input/misc/rotary_encoder.c
@@ -106,7 +106,7 @@ static irqreturn_t rotary_encoder_irq(int irq, void *dev_id)
 	struct rotary_encoder *encoder = dev_id;
 	unsigned int state;
 
-	mutex_lock(&encoder->access_mutex);
+	guard(mutex)(&encoder->access_mutex);
 
 	state = rotary_encoder_get_state(encoder);
 
@@ -129,8 +129,6 @@ static irqreturn_t rotary_encoder_irq(int irq, void *dev_id)
 		break;
 	}
 
-	mutex_unlock(&encoder->access_mutex);
-
 	return IRQ_HANDLED;
 }
 
@@ -139,7 +137,7 @@ static irqreturn_t rotary_encoder_half_period_irq(int irq, void *dev_id)
 	struct rotary_encoder *encoder = dev_id;
 	unsigned int state;
 
-	mutex_lock(&encoder->access_mutex);
+	guard(mutex)(&encoder->access_mutex);
 
 	state = rotary_encoder_get_state(encoder);
 
@@ -152,8 +150,6 @@ static irqreturn_t rotary_encoder_half_period_irq(int irq, void *dev_id)
 		}
 	}
 
-	mutex_unlock(&encoder->access_mutex);
-
 	return IRQ_HANDLED;
 }
 
@@ -162,22 +158,19 @@ static irqreturn_t rotary_encoder_quarter_period_irq(int irq, void *dev_id)
 	struct rotary_encoder *encoder = dev_id;
 	unsigned int state;
 
-	mutex_lock(&encoder->access_mutex);
+	guard(mutex)(&encoder->access_mutex);
 
 	state = rotary_encoder_get_state(encoder);
 
-	if ((encoder->last_stable + 1) % 4 == state)
+	if ((encoder->last_stable + 1) % 4 == state) {
 		encoder->dir = 1;
-	else if (encoder->last_stable == (state + 1) % 4)
+		rotary_encoder_report_event(encoder);
+	} else if (encoder->last_stable == (state + 1) % 4) {
 		encoder->dir = -1;
-	else
-		goto out;
-
-	rotary_encoder_report_event(encoder);
+		rotary_encoder_report_event(encoder);
+	}
 
-out:
 	encoder->last_stable = state;
-	mutex_unlock(&encoder->access_mutex);
 
 	return IRQ_HANDLED;
 }

From c03dfa7fdf7987d957acfc332d84720da6ed947a Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Sep 2024 21:49:37 -0700
Subject: [PATCH 0158/1530] Input: sparcspkr - use guard notation when
 acquiring spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240904044938.1049843-1-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/sparcspkr.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/input/misc/sparcspkr.c b/drivers/input/misc/sparcspkr.c
index 20020cbc0752b..5de59ae90c670 100644
--- a/drivers/input/misc/sparcspkr.c
+++ b/drivers/input/misc/sparcspkr.c
@@ -69,7 +69,6 @@ static int bbc_spkr_event(struct input_dev *dev, unsigned int type, unsigned int
 	struct sparcspkr_state *state = dev_get_drvdata(dev->dev.parent);
 	struct bbc_beep_info *info = &state->u.bbc;
 	unsigned int count = 0;
-	unsigned long flags;
 
 	if (type != EV_SND)
 		return -1;
@@ -85,7 +84,7 @@ static int bbc_spkr_event(struct input_dev *dev, unsigned int type, unsigned int
 
 	count = bbc_count_to_reg(info, count);
 
-	spin_lock_irqsave(&state->lock, flags);
+	guard(spinlock_irqsave)(&state->lock);
 
 	if (count) {
 		sbus_writeb(0x01,                 info->regs + 0);
@@ -97,8 +96,6 @@ static int bbc_spkr_event(struct input_dev *dev, unsigned int type, unsigned int
 		sbus_writeb(0x00,                 info->regs + 0);
 	}
 
-	spin_unlock_irqrestore(&state->lock, flags);
-
 	return 0;
 }
 
@@ -107,7 +104,6 @@ static int grover_spkr_event(struct input_dev *dev, unsigned int type, unsigned
 	struct sparcspkr_state *state = dev_get_drvdata(dev->dev.parent);
 	struct grover_beep_info *info = &state->u.grover;
 	unsigned int count = 0;
-	unsigned long flags;
 
 	if (type != EV_SND)
 		return -1;
@@ -121,7 +117,7 @@ static int grover_spkr_event(struct input_dev *dev, unsigned int type, unsigned
 	if (value > 20 && value < 32767)
 		count = 1193182 / value;
 
-	spin_lock_irqsave(&state->lock, flags);
+	guard(spinlock_irqsave)(&state->lock);
 
 	if (count) {
 		/* enable counter 2 */
@@ -136,8 +132,6 @@ static int grover_spkr_event(struct input_dev *dev, unsigned int type, unsigned
 		sbus_writeb(sbus_readb(info->enable_reg) & 0xFC, info->enable_reg);
 	}
 
-	spin_unlock_irqrestore(&state->lock, flags);
-
 	return 0;
 }
 

From f72751a73a6b6ad678d254335e031e4511282564 Mon Sep 17 00:00:00 2001
From: Veronika Molnarova <vmolnaro@redhat.com>
Date: Thu, 3 Oct 2024 14:51:36 +0200
Subject: [PATCH 0159/1530] perf test: Restore sample rate for perf_event_attr

Test "Setup struct perf_event_attr" consists of multiple test cases that
can affect the max sample rate value for perf events. Some test cases
check this value as it should not be lowered under the set minimum for
the given test. Currently, it is possible for the test cases to affect
each other as the previous tests can lower the sample rate, leading to
a possible failure of some of the future test cases as the value is not
restored at any point.

   # 10: Setup struct perf_event_attr:
    --- start ---
    test child forked, pid 104220
    Using CPUID 0x00000000413fd0c1
    running './tests/attr/test-record-C0'
    Current sample rate: 10000
    running './tests/attr/test-record-basic'
    Current sample rate: 900
    running './tests/attr/test-record-branch-any'
    Current sample rate: 600
    running './tests/attr/test-record-dummy-C0'
    Current sample rate: 600
    expected sample_period=4000, got 600
    FAILED './tests/attr/test-record-dummy-C0' - match failure

Restore the max sample rate value for perf events to a reasonable value
before each test case if its value was lowered too much to ensure the
same conditions for each test case.

   # 10: Setup struct perf_event_attr:
    --- start ---
    test child forked, pid 107222
    Using CPUID 0x00000000413fd0c1
    running './tests/attr/test-record-C0'
    Current sample rate: 10000
    running './tests/attr/test-record-basic'
    Current sample rate: 800
    running './tests/attr/test-record-branch-any'
    Current sample rate: 700
    unsupp  './tests/attr/test-record-branch-any'
    running './tests/attr/test-record-branch-filter-any'
    Current sample rate: 10000
    running './tests/attr/test-record-count'
    Current sample rate: 10000
    running './tests/attr/test-record-data'
    Current sample rate: 600
    running './tests/attr/test-record-dummy-C0'
    Current sample rate: 800
    running './tests/attr/test-record-freq'
    Current sample rate: 10000
    ...

Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Radostin Stoyanov <rstoyano@redhat.com>
Signed-off-by: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241003125136.15918-1-vmolnaro@redhat.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/attr.py | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
index e890c261ad269..3db9a7d78715f 100644
--- a/tools/perf/tests/attr.py
+++ b/tools/perf/tests/attr.py
@@ -246,6 +246,23 @@ def skip_test_arch(self, myarch):
                 return False
         return True
 
+    def restore_sample_rate(self, value=10000):
+        try:
+            # Check value of sample_rate
+            with open("/proc/sys/kernel/perf_event_max_sample_rate", "r") as fIn:
+                curr_value = fIn.readline()
+            # If too low restore to reasonable value
+            if not curr_value or int(curr_value) < int(value):
+                with open("/proc/sys/kernel/perf_event_max_sample_rate", "w") as fOut:
+                    fOut.write(str(value))
+
+        except IOError as e:
+            log.warning("couldn't restore sample_rate value: I/O error %s" % e)
+        except ValueError as e:
+            log.warning("couldn't restore sample_rate value: Value error %s" % e)
+        except TypeError as e:
+            log.warning("couldn't restore sample_rate value: Type error %s" % e)
+
     def load_events(self, path, events):
         parser_event = configparser.ConfigParser()
         parser_event.read(path)
@@ -283,6 +300,7 @@ def run_cmd(self, tempdir):
         if self.skip_test_kernel_until():
             raise Notest(self, "new kernel skip")
 
+        self.restore_sample_rate()
         cmd = "PERF_TEST_ATTR=%s %s %s -o %s/perf.data %s" % (tempdir,
               self.perf, self.command, tempdir, self.args)
         ret = os.WEXITSTATUS(os.system(cmd))

From f7ef062fe154a4249663ba87d8ffab47519033cf Mon Sep 17 00:00:00 2001
From: Yoshihiro Furudera <fj5100bi@fujitsu.com>
Date: Thu, 3 Oct 2024 00:24:04 +0000
Subject: [PATCH 0160/1530] perf list: update option desc in man page

There is a difference between the SYNOPSIS section of the help message
and the man page (tools/perf/Documentation/perf-list.txt) for the perf
list command. After checking, we found that the help message reflected
the latest specifications. Therefore, revised the SYNOPSIS section of
the man page to match the help message.

Signed-off-by: Yoshihiro Furudera <fj5100bi@fujitsu.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Liang
Link: https://lore.kernel.org/r/20241003002404.2592094-1-fj5100bi@fujitsu.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Documentation/perf-list.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index dea005410ec02..14621f39b375b 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -8,7 +8,7 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list' [--no-desc] [--long-desc]
+'perf list' [<options>]
             [hw|sw|cache|tracepoint|pmu|sdt|metric|metricgroup|event_glob]
 
 DESCRIPTION

From 3c87b3c85a5344098f239bf8fceee1db691e3a0c Mon Sep 17 00:00:00 2001
From: Sergio Paracuellos <sergio.paracuellos@gmail.com>
Date: Mon, 23 Sep 2024 08:57:06 +0200
Subject: [PATCH 0161/1530] PCI: controller: Switch back to struct
 platform_driver::remove()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 0edb555a65d1 ("platform: Make platform_driver::remove() return
void") .remove() is (again) the right callback to implement for platform
drivers.

Convert all PCI controller drivers to use .remove(), with the eventual goal
to drop struct platform_driver::remove_new(). As .remove() and .remove_new()
have the same prototypes, conversion is done by just changing the structure
member name in the driver initializer.

Link: https://lore.kernel.org/r/20240923065706.728769-1-sergio.paracuellos@gmail.com
Signed-off-by: Sergio Paracuellos <sergio.paracuellos@gmail.com>
[bhelgaas: add pcie-xilinx-nwl.c and tidy whitespace per Uwe Kleine-König:
https://lore.kernel.org/r/tdxrmmqyzcufupnwkdbg7lwgadizm7v3lxjirykijbml7x54ze@upbdzycdsilm]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/controller/cadence/pci-j721e.c   | 2 +-
 drivers/pci/controller/dwc/pci-exynos.c      | 2 +-
 drivers/pci/controller/dwc/pci-keystone.c    | 2 +-
 drivers/pci/controller/dwc/pcie-bt1.c        | 2 +-
 drivers/pci/controller/dwc/pcie-histb.c      | 2 +-
 drivers/pci/controller/dwc/pcie-intel-gw.c   | 2 +-
 drivers/pci/controller/dwc/pcie-kirin.c      | 2 +-
 drivers/pci/controller/dwc/pcie-qcom-ep.c    | 2 +-
 drivers/pci/controller/dwc/pcie-rcar-gen4.c  | 2 +-
 drivers/pci/controller/dwc/pcie-tegra194.c   | 2 +-
 drivers/pci/controller/pci-aardvark.c        | 2 +-
 drivers/pci/controller/pci-host-generic.c    | 2 +-
 drivers/pci/controller/pci-mvebu.c           | 2 +-
 drivers/pci/controller/pci-tegra.c           | 2 +-
 drivers/pci/controller/pci-xgene-msi.c       | 2 +-
 drivers/pci/controller/pcie-altera-msi.c     | 2 +-
 drivers/pci/controller/pcie-altera.c         | 6 +++---
 drivers/pci/controller/pcie-brcmstb.c        | 2 +-
 drivers/pci/controller/pcie-hisi-error.c     | 2 +-
 drivers/pci/controller/pcie-iproc-platform.c | 2 +-
 drivers/pci/controller/pcie-mediatek-gen3.c  | 2 +-
 drivers/pci/controller/pcie-mediatek.c       | 2 +-
 drivers/pci/controller/pcie-mt7621.c         | 2 +-
 drivers/pci/controller/pcie-rockchip-host.c  | 2 +-
 drivers/pci/controller/pcie-xilinx-nwl.c     | 2 +-
 drivers/pci/controller/plda/pcie-starfive.c  | 2 +-
 26 files changed, 28 insertions(+), 28 deletions(-)

diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c
index 284f2e0e4d261..ca24df2369769 100644
--- a/drivers/pci/controller/cadence/pci-j721e.c
+++ b/drivers/pci/controller/cadence/pci-j721e.c
@@ -712,7 +712,7 @@ static DEFINE_NOIRQ_DEV_PM_OPS(j721e_pcie_pm_ops,
 
 static struct platform_driver j721e_pcie_driver = {
 	.probe  = j721e_pcie_probe,
-	.remove_new = j721e_pcie_remove,
+	.remove = j721e_pcie_remove,
 	.driver = {
 		.name	= "j721e-pcie",
 		.of_match_table = of_j721e_pcie_match,
diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index fa45da28a218b..6a830166d37ff 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -383,7 +383,7 @@ static const struct of_device_id exynos_pcie_of_match[] = {
 
 static struct platform_driver exynos_pcie_driver = {
 	.probe		= exynos_pcie_probe,
-	.remove_new	= exynos_pcie_remove,
+	.remove		= exynos_pcie_remove,
 	.driver = {
 		.name	= "exynos-pcie",
 		.of_match_table = exynos_pcie_of_match,
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 2219b1a866faf..b82e13e65e1af 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -1363,7 +1363,7 @@ static void ks_pcie_remove(struct platform_device *pdev)
 
 static struct platform_driver ks_pcie_driver = {
 	.probe  = ks_pcie_probe,
-	.remove_new = ks_pcie_remove,
+	.remove = ks_pcie_remove,
 	.driver = {
 		.name	= "keystone-pcie",
 		.of_match_table = ks_pcie_of_match,
diff --git a/drivers/pci/controller/dwc/pcie-bt1.c b/drivers/pci/controller/dwc/pcie-bt1.c
index 76d0ddea80075..1340edc18d128 100644
--- a/drivers/pci/controller/dwc/pcie-bt1.c
+++ b/drivers/pci/controller/dwc/pcie-bt1.c
@@ -632,7 +632,7 @@ MODULE_DEVICE_TABLE(of, bt1_pcie_of_match);
 
 static struct platform_driver bt1_pcie_driver = {
 	.probe = bt1_pcie_probe,
-	.remove_new = bt1_pcie_remove,
+	.remove = bt1_pcie_remove,
 	.driver = {
 		.name	= "bt1-pcie",
 		.of_match_table = bt1_pcie_of_match,
diff --git a/drivers/pci/controller/dwc/pcie-histb.c b/drivers/pci/controller/dwc/pcie-histb.c
index 7a11c618b9d9c..615a0e3e6d7eb 100644
--- a/drivers/pci/controller/dwc/pcie-histb.c
+++ b/drivers/pci/controller/dwc/pcie-histb.c
@@ -439,7 +439,7 @@ MODULE_DEVICE_TABLE(of, histb_pcie_of_match);
 
 static struct platform_driver histb_pcie_platform_driver = {
 	.probe	= histb_pcie_probe,
-	.remove_new = histb_pcie_remove,
+	.remove = histb_pcie_remove,
 	.driver = {
 		.name = "histb-pcie",
 		.of_match_table = histb_pcie_of_match,
diff --git a/drivers/pci/controller/dwc/pcie-intel-gw.c b/drivers/pci/controller/dwc/pcie-intel-gw.c
index 676d2aba4fbde..9b53b8f6f268e 100644
--- a/drivers/pci/controller/dwc/pcie-intel-gw.c
+++ b/drivers/pci/controller/dwc/pcie-intel-gw.c
@@ -443,7 +443,7 @@ static const struct of_device_id of_intel_pcie_match[] = {
 
 static struct platform_driver intel_pcie_driver = {
 	.probe = intel_pcie_probe,
-	.remove_new = intel_pcie_remove,
+	.remove = intel_pcie_remove,
 	.driver = {
 		.name = "intel-gw-pcie",
 		.of_match_table = of_intel_pcie_match,
diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c
index 85a2c77b1835a..1b2088acb538b 100644
--- a/drivers/pci/controller/dwc/pcie-kirin.c
+++ b/drivers/pci/controller/dwc/pcie-kirin.c
@@ -769,7 +769,7 @@ static int kirin_pcie_probe(struct platform_device *pdev)
 
 static struct platform_driver kirin_pcie_driver = {
 	.probe			= kirin_pcie_probe,
-	.remove_new		= kirin_pcie_remove,
+	.remove			= kirin_pcie_remove,
 	.driver			= {
 		.name			= "kirin-pcie",
 		.of_match_table		= kirin_pcie_match,
diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
index e588fcc545893..d663c52064505 100644
--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
+++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
@@ -937,7 +937,7 @@ MODULE_DEVICE_TABLE(of, qcom_pcie_ep_match);
 
 static struct platform_driver qcom_pcie_ep_driver = {
 	.probe	= qcom_pcie_ep_probe,
-	.remove_new = qcom_pcie_ep_remove,
+	.remove = qcom_pcie_ep_remove,
 	.driver	= {
 		.name = "qcom-pcie-ep",
 		.of_match_table	= qcom_pcie_ep_match,
diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
index 3a5511c3f7d97..fc872dd35029c 100644
--- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c
+++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
@@ -775,7 +775,7 @@ static struct platform_driver rcar_gen4_pcie_driver = {
 		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
 	},
 	.probe = rcar_gen4_pcie_probe,
-	.remove_new = rcar_gen4_pcie_remove,
+	.remove = rcar_gen4_pcie_remove,
 };
 module_platform_driver(rcar_gen4_pcie_driver);
 
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index c1394f2ab63ff..f4bd7f5275cfb 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -2493,7 +2493,7 @@ static const struct dev_pm_ops tegra_pcie_dw_pm_ops = {
 
 static struct platform_driver tegra_pcie_dw_driver = {
 	.probe = tegra_pcie_dw_probe,
-	.remove_new = tegra_pcie_dw_remove,
+	.remove = tegra_pcie_dw_remove,
 	.shutdown = tegra_pcie_dw_shutdown,
 	.driver = {
 		.name	= "tegra194-pcie",
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index a598a98247ce9..a29796cce420a 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -1996,7 +1996,7 @@ static struct platform_driver advk_pcie_driver = {
 		.of_match_table = advk_pcie_of_match_table,
 	},
 	.probe = advk_pcie_probe,
-	.remove_new = advk_pcie_remove,
+	.remove = advk_pcie_remove,
 };
 module_platform_driver(advk_pcie_driver);
 
diff --git a/drivers/pci/controller/pci-host-generic.c b/drivers/pci/controller/pci-host-generic.c
index 5f06f94db7b17..4051b9b61dace 100644
--- a/drivers/pci/controller/pci-host-generic.c
+++ b/drivers/pci/controller/pci-host-generic.c
@@ -82,7 +82,7 @@ static struct platform_driver gen_pci_driver = {
 		.of_match_table = gen_pci_of_match,
 	},
 	.probe = pci_host_common_probe,
-	.remove_new = pci_host_common_remove,
+	.remove = pci_host_common_remove,
 };
 module_platform_driver(gen_pci_driver);
 
diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index 29fe09c99e7d9..46d3afe1d3081 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -1727,7 +1727,7 @@ static struct platform_driver mvebu_pcie_driver = {
 		.pm = &mvebu_pcie_pm_ops,
 	},
 	.probe = mvebu_pcie_probe,
-	.remove_new = mvebu_pcie_remove,
+	.remove = mvebu_pcie_remove,
 };
 module_platform_driver(mvebu_pcie_driver);
 
diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index d7517c3976e7f..1f0a872790e57 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -2800,6 +2800,6 @@ static struct platform_driver tegra_pcie_driver = {
 		.pm = &tegra_pcie_pm_ops,
 	},
 	.probe = tegra_pcie_probe,
-	.remove_new = tegra_pcie_remove,
+	.remove = tegra_pcie_remove,
 };
 module_platform_driver(tegra_pcie_driver);
diff --git a/drivers/pci/controller/pci-xgene-msi.c b/drivers/pci/controller/pci-xgene-msi.c
index 3ce38dfd0d29f..88c0977bc41a4 100644
--- a/drivers/pci/controller/pci-xgene-msi.c
+++ b/drivers/pci/controller/pci-xgene-msi.c
@@ -518,7 +518,7 @@ static struct platform_driver xgene_msi_driver = {
 		.of_match_table = xgene_msi_match_table,
 	},
 	.probe = xgene_msi_probe,
-	.remove_new = xgene_msi_remove,
+	.remove = xgene_msi_remove,
 };
 
 static int __init xgene_pcie_msi_init(void)
diff --git a/drivers/pci/controller/pcie-altera-msi.c b/drivers/pci/controller/pcie-altera-msi.c
index e36a6e158d23c..e1cee3c0575fb 100644
--- a/drivers/pci/controller/pcie-altera-msi.c
+++ b/drivers/pci/controller/pcie-altera-msi.c
@@ -267,7 +267,7 @@ static struct platform_driver altera_msi_driver = {
 		.of_match_table = altera_msi_of_match,
 	},
 	.probe = altera_msi_probe,
-	.remove_new = altera_msi_remove,
+	.remove = altera_msi_remove,
 };
 
 static int __init altera_msi_init(void)
diff --git a/drivers/pci/controller/pcie-altera.c b/drivers/pci/controller/pcie-altera.c
index 650b2dd81c482..eb55a7f8573a8 100644
--- a/drivers/pci/controller/pcie-altera.c
+++ b/drivers/pci/controller/pcie-altera.c
@@ -815,10 +815,10 @@ static void altera_pcie_remove(struct platform_device *pdev)
 }
 
 static struct platform_driver altera_pcie_driver = {
-	.probe		= altera_pcie_probe,
-	.remove_new	= altera_pcie_remove,
+	.probe = altera_pcie_probe,
+	.remove = altera_pcie_remove,
 	.driver = {
-		.name	= "altera-pcie",
+		.name = "altera-pcie",
 		.of_match_table = altera_pcie_of_match,
 	},
 };
diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c
index 9321280f6edba..e733a27dc8df8 100644
--- a/drivers/pci/controller/pcie-brcmstb.c
+++ b/drivers/pci/controller/pcie-brcmstb.c
@@ -1928,7 +1928,7 @@ static const struct dev_pm_ops brcm_pcie_pm_ops = {
 
 static struct platform_driver brcm_pcie_driver = {
 	.probe = brcm_pcie_probe,
-	.remove_new = brcm_pcie_remove,
+	.remove = brcm_pcie_remove,
 	.driver = {
 		.name = "brcm-pcie",
 		.of_match_table = brcm_pcie_match,
diff --git a/drivers/pci/controller/pcie-hisi-error.c b/drivers/pci/controller/pcie-hisi-error.c
index ad9d5ffcd9e34..aaf1ed2b6e597 100644
--- a/drivers/pci/controller/pcie-hisi-error.c
+++ b/drivers/pci/controller/pcie-hisi-error.c
@@ -317,7 +317,7 @@ static struct platform_driver hisi_pcie_error_handler_driver = {
 		.acpi_match_table = hisi_pcie_acpi_match,
 	},
 	.probe		= hisi_pcie_error_handler_probe,
-	.remove_new	= hisi_pcie_error_handler_remove,
+	.remove		= hisi_pcie_error_handler_remove,
 };
 module_platform_driver(hisi_pcie_error_handler_driver);
 
diff --git a/drivers/pci/controller/pcie-iproc-platform.c b/drivers/pci/controller/pcie-iproc-platform.c
index 4e6aa882a567a..0cb78c583c7ea 100644
--- a/drivers/pci/controller/pcie-iproc-platform.c
+++ b/drivers/pci/controller/pcie-iproc-platform.c
@@ -134,7 +134,7 @@ static struct platform_driver iproc_pltfm_pcie_driver = {
 		.of_match_table = of_match_ptr(iproc_pcie_of_match_table),
 	},
 	.probe = iproc_pltfm_pcie_probe,
-	.remove_new = iproc_pltfm_pcie_remove,
+	.remove = iproc_pltfm_pcie_remove,
 	.shutdown = iproc_pltfm_pcie_shutdown,
 };
 module_platform_driver(iproc_pltfm_pcie_driver);
diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c
index 66ce4b5d309bb..969f62e9cf01f 100644
--- a/drivers/pci/controller/pcie-mediatek-gen3.c
+++ b/drivers/pci/controller/pcie-mediatek-gen3.c
@@ -1225,7 +1225,7 @@ MODULE_DEVICE_TABLE(of, mtk_pcie_of_match);
 
 static struct platform_driver mtk_pcie_driver = {
 	.probe = mtk_pcie_probe,
-	.remove_new = mtk_pcie_remove,
+	.remove = mtk_pcie_remove,
 	.driver = {
 		.name = "mtk-pcie-gen3",
 		.of_match_table = mtk_pcie_of_match,
diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c
index 7f7d04c2ea573..3bcfc4e58ba24 100644
--- a/drivers/pci/controller/pcie-mediatek.c
+++ b/drivers/pci/controller/pcie-mediatek.c
@@ -1235,7 +1235,7 @@ MODULE_DEVICE_TABLE(of, mtk_pcie_ids);
 
 static struct platform_driver mtk_pcie_driver = {
 	.probe = mtk_pcie_probe,
-	.remove_new = mtk_pcie_remove,
+	.remove = mtk_pcie_remove,
 	.driver = {
 		.name = "mtk-pcie",
 		.of_match_table = mtk_pcie_ids,
diff --git a/drivers/pci/controller/pcie-mt7621.c b/drivers/pci/controller/pcie-mt7621.c
index 9b4754a45515f..776caa0b10115 100644
--- a/drivers/pci/controller/pcie-mt7621.c
+++ b/drivers/pci/controller/pcie-mt7621.c
@@ -541,7 +541,7 @@ MODULE_DEVICE_TABLE(of, mt7621_pcie_ids);
 
 static struct platform_driver mt7621_pcie_driver = {
 	.probe = mt7621_pcie_probe,
-	.remove_new = mt7621_pcie_remove,
+	.remove = mt7621_pcie_remove,
 	.driver = {
 		.name = "mt7621-pci",
 		.of_match_table = mt7621_pcie_ids,
diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c
index cbec711148253..06cdb68f09202 100644
--- a/drivers/pci/controller/pcie-rockchip-host.c
+++ b/drivers/pci/controller/pcie-rockchip-host.c
@@ -1050,7 +1050,7 @@ static struct platform_driver rockchip_pcie_driver = {
 		.pm = &rockchip_pcie_pm_ops,
 	},
 	.probe = rockchip_pcie_probe,
-	.remove_new = rockchip_pcie_remove,
+	.remove = rockchip_pcie_remove,
 };
 module_platform_driver(rockchip_pcie_driver);
 
diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c
index a8ae14474dd0a..8d6e2a89b067b 100644
--- a/drivers/pci/controller/pcie-xilinx-nwl.c
+++ b/drivers/pci/controller/pcie-xilinx-nwl.c
@@ -916,6 +916,6 @@ static struct platform_driver nwl_pcie_driver = {
 		.of_match_table = nwl_pcie_of_match,
 	},
 	.probe = nwl_pcie_probe,
-	.remove_new = nwl_pcie_remove,
+	.remove = nwl_pcie_remove,
 };
 builtin_platform_driver(nwl_pcie_driver);
diff --git a/drivers/pci/controller/plda/pcie-starfive.c b/drivers/pci/controller/plda/pcie-starfive.c
index c9933ecf68338..0567ec373a3ed 100644
--- a/drivers/pci/controller/plda/pcie-starfive.c
+++ b/drivers/pci/controller/plda/pcie-starfive.c
@@ -480,7 +480,7 @@ static struct platform_driver starfive_pcie_driver = {
 		.pm = pm_sleep_ptr(&starfive_pcie_pm_ops),
 	},
 	.probe = starfive_pcie_probe,
-	.remove_new = starfive_pcie_remove,
+	.remove = starfive_pcie_remove,
 };
 module_platform_driver(starfive_pcie_driver);
 

From 43d6961cdf1d0621c55638ed33554027978ae1fe Mon Sep 17 00:00:00 2001
From: Sergio Paracuellos <sergio.paracuellos@gmail.com>
Date: Fri, 27 Sep 2024 11:24:49 +0200
Subject: [PATCH 0162/1530] PCI: acpiphp_ampere_altra: Switch back to struct
 platform_driver::remove()

After commit 0edb555a65d1 ("platform: Make platform_driver::remove() return
void") .remove() is (again) the right callback to implement for platform
drivers.

Convert all PCI controller drivers to use .remove(), with the eventual goal
to drop struct platform_driver::remove_new(). As .remove() and
.remove_new() have the same prototypes, conversion is done by just changing
the structure member name in the driver initializer.

Link: https://lore.kernel.org/r/20240927092449.44628-1-sergio.paracuellos@gmail.com
Signed-off-by: Sergio Paracuellos <sergio.paracuellos@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/acpiphp_ampere_altra.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/hotplug/acpiphp_ampere_altra.c b/drivers/pci/hotplug/acpiphp_ampere_altra.c
index f5c9e741c1d41..70dbc0431fc69 100644
--- a/drivers/pci/hotplug/acpiphp_ampere_altra.c
+++ b/drivers/pci/hotplug/acpiphp_ampere_altra.c
@@ -119,7 +119,7 @@ static struct platform_driver altra_led_driver = {
 		.acpi_match_table = altra_led_ids,
 	},
 	.probe = altra_led_probe,
-	.remove_new = altra_led_remove,
+	.remove = altra_led_remove,
 };
 module_platform_driver(altra_led_driver);
 

From 0ca2c45404eed3b6bb80d3169bf672b09cf3a70d Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Thu, 3 Oct 2024 19:42:58 +0100
Subject: [PATCH 0163/1530] perf arm-spe: Define metadata header version 2

The first version's metadata header structure doesn't include a field to
indicate a header version, which is not friendly for extension.

Define the metadata version 2 format with a new header structure and
extend per CPU's metadata. In the meantime, the old metadata header will
still be supported for backward compatibility.

Signed-off-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Cc: Will Deacon <will@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Besar Wicaksono <bwicaksono@nvidia.com>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20241003184302.190806-2-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/arm64/util/arm-spe.c |  4 +--
 tools/perf/util/arm-spe.c            |  2 +-
 tools/perf/util/arm-spe.h            | 38 +++++++++++++++++++++++++++-
 3 files changed, 40 insertions(+), 4 deletions(-)

diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 59a85e6f3aa34..93c2590920711 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -41,7 +41,7 @@ static size_t
 arm_spe_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 		       struct evlist *evlist __maybe_unused)
 {
-	return ARM_SPE_AUXTRACE_PRIV_SIZE;
+	return ARM_SPE_AUXTRACE_V1_PRIV_SIZE;
 }
 
 static int arm_spe_info_fill(struct auxtrace_record *itr,
@@ -53,7 +53,7 @@ static int arm_spe_info_fill(struct auxtrace_record *itr,
 			container_of(itr, struct arm_spe_recording, itr);
 	struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
 
-	if (priv_size != ARM_SPE_AUXTRACE_PRIV_SIZE)
+	if (priv_size != ARM_SPE_AUXTRACE_V1_PRIV_SIZE)
 		return -EINVAL;
 
 	if (!session->evlist->core.nr_mmaps)
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 138ffc71b32dd..70989b1bae478 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -1262,7 +1262,7 @@ int arm_spe_process_auxtrace_info(union perf_event *event,
 				  struct perf_session *session)
 {
 	struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;
-	size_t min_sz = sizeof(u64) * ARM_SPE_AUXTRACE_PRIV_MAX;
+	size_t min_sz = ARM_SPE_AUXTRACE_V1_PRIV_SIZE;
 	struct perf_record_time_conv *tc = &session->time_conv;
 	const char *cpuid = perf_env__cpuid(session->evlist->env);
 	u64 midr = strtol(cpuid, NULL, 16);
diff --git a/tools/perf/util/arm-spe.h b/tools/perf/util/arm-spe.h
index 4f4900c18f3e2..390679a4af2fb 100644
--- a/tools/perf/util/arm-spe.h
+++ b/tools/perf/util/arm-spe.h
@@ -12,10 +12,46 @@
 enum {
 	ARM_SPE_PMU_TYPE,
 	ARM_SPE_PER_CPU_MMAPS,
+	ARM_SPE_AUXTRACE_V1_PRIV_MAX,
+};
+
+#define ARM_SPE_AUXTRACE_V1_PRIV_SIZE	\
+	(ARM_SPE_AUXTRACE_V1_PRIV_MAX * sizeof(u64))
+
+enum {
+	/*
+	 * The old metadata format (defined above) does not include a
+	 * field for version number. Version 1 is reserved and starts
+	 * from version 2.
+	 */
+	ARM_SPE_HEADER_VERSION,
+	/* Number of sizeof(u64) */
+	ARM_SPE_HEADER_SIZE,
+	/* PMU type shared by CPUs */
+	ARM_SPE_PMU_TYPE_V2,
+	/* Number of CPUs */
+	ARM_SPE_CPUS_NUM,
 	ARM_SPE_AUXTRACE_PRIV_MAX,
 };
 
-#define ARM_SPE_AUXTRACE_PRIV_SIZE (ARM_SPE_AUXTRACE_PRIV_MAX * sizeof(u64))
+enum {
+	/* Magic number */
+	ARM_SPE_MAGIC,
+	/* CPU logical number in system */
+	ARM_SPE_CPU,
+	/* Number of parameters */
+	ARM_SPE_CPU_NR_PARAMS,
+	/* CPU MIDR */
+	ARM_SPE_CPU_MIDR,
+	/* Associated PMU type */
+	ARM_SPE_CPU_PMU_TYPE,
+	/* Minimal interval */
+	ARM_SPE_CAP_MIN_IVAL,
+	ARM_SPE_CPU_PRIV_MAX,
+};
+
+#define ARM_SPE_HEADER_CURRENT_VERSION	2
+
 
 union perf_event;
 struct perf_session;

From 59715b1908b051fa3e4c0efb8a3724786d98bc48 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Thu, 3 Oct 2024 19:42:59 +0100
Subject: [PATCH 0164/1530] perf arm-spe: Calculate meta data size

The metadata is designed to contain a header and per CPU information.

The arm_spe_find_cpus() function is introduced to identify how many CPUs
support ARM SPE. Based on the CPU number, calculates the metadata size.

Signed-off-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Cc: Will Deacon <will@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Besar Wicaksono <bwicaksono@nvidia.com>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20241003184302.190806-3-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/arm64/util/arm-spe.c | 39 +++++++++++++++++++++++++---
 1 file changed, 36 insertions(+), 3 deletions(-)

diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 93c2590920711..cc927d88a6157 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -37,11 +37,44 @@ struct arm_spe_recording {
 	bool			*wrapped;
 };
 
+/*
+ * arm_spe_find_cpus() returns a new cpu map, and the caller should invoke
+ * perf_cpu_map__put() to release the map after use.
+ */
+static struct perf_cpu_map *arm_spe_find_cpus(struct evlist *evlist)
+{
+	struct perf_cpu_map *event_cpus = evlist->core.user_requested_cpus;
+	struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
+	struct perf_cpu_map *intersect_cpus;
+
+	/* cpu map is not "any" CPU , we have specific CPUs to work with */
+	if (!perf_cpu_map__has_any_cpu(event_cpus)) {
+		intersect_cpus = perf_cpu_map__intersect(event_cpus, online_cpus);
+		perf_cpu_map__put(online_cpus);
+	/* Event can be "any" CPU so count all CPUs. */
+	} else {
+		intersect_cpus = online_cpus;
+	}
+
+	return intersect_cpus;
+}
+
 static size_t
 arm_spe_info_priv_size(struct auxtrace_record *itr __maybe_unused,
-		       struct evlist *evlist __maybe_unused)
+		       struct evlist *evlist)
 {
-	return ARM_SPE_AUXTRACE_V1_PRIV_SIZE;
+	struct perf_cpu_map *cpu_map = arm_spe_find_cpus(evlist);
+	size_t size;
+
+	if (!cpu_map)
+		return 0;
+
+	size = ARM_SPE_AUXTRACE_PRIV_MAX +
+	       ARM_SPE_CPU_PRIV_MAX * perf_cpu_map__nr(cpu_map);
+	size *= sizeof(u64);
+
+	perf_cpu_map__put(cpu_map);
+	return size;
 }
 
 static int arm_spe_info_fill(struct auxtrace_record *itr,
@@ -53,7 +86,7 @@ static int arm_spe_info_fill(struct auxtrace_record *itr,
 			container_of(itr, struct arm_spe_recording, itr);
 	struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
 
-	if (priv_size != ARM_SPE_AUXTRACE_V1_PRIV_SIZE)
+	if (priv_size != arm_spe_info_priv_size(itr, session->evlist))
 		return -EINVAL;
 
 	if (!session->evlist->core.nr_mmaps)

From 703f344d0c4a3a006d3e1466d38ee6d8791acd87 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Thu, 3 Oct 2024 19:43:00 +0100
Subject: [PATCH 0165/1530] perf arm-spe: Save per CPU information in metadata

Save the Arm SPE information on a per-CPU basis. This approach is easier
in the decoding phase for retrieving metadata based on the CPU number of
every Arm SPE record.

Signed-off-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Cc: Will Deacon <will@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Besar Wicaksono <bwicaksono@nvidia.com>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20241003184302.190806-4-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/arm64/util/arm-spe.c | 83 +++++++++++++++++++++++++++-
 1 file changed, 81 insertions(+), 2 deletions(-)

diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index cc927d88a6157..7ccdea3cd461a 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -26,6 +26,8 @@
 #include "../../../util/arm-spe.h"
 #include <tools/libc_compat.h> // reallocarray
 
+#define ARM_SPE_CPU_MAGIC		0x1010101010101010ULL
+
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)
 
@@ -77,14 +79,70 @@ arm_spe_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 	return size;
 }
 
+static int arm_spe_save_cpu_header(struct auxtrace_record *itr,
+				   struct perf_cpu cpu, __u64 data[])
+{
+	struct arm_spe_recording *sper =
+			container_of(itr, struct arm_spe_recording, itr);
+	struct perf_pmu *pmu = NULL;
+	struct perf_pmu tmp_pmu;
+	char cpu_id_str[16];
+	char *cpuid = NULL;
+	u64 val;
+
+	snprintf(cpu_id_str, sizeof(cpu_id_str), "%d", cpu.cpu);
+	tmp_pmu.cpus = perf_cpu_map__new(cpu_id_str);
+	if (!tmp_pmu.cpus)
+		return -ENOMEM;
+
+	/* Read CPU MIDR */
+	cpuid = perf_pmu__getcpuid(&tmp_pmu);
+
+	/* The CPU map will not be used anymore, release it */
+	perf_cpu_map__put(tmp_pmu.cpus);
+
+	if (!cpuid)
+		return -ENOMEM;
+	val = strtol(cpuid, NULL, 16);
+
+	data[ARM_SPE_MAGIC] = ARM_SPE_CPU_MAGIC;
+	data[ARM_SPE_CPU] = cpu.cpu;
+	data[ARM_SPE_CPU_NR_PARAMS] = ARM_SPE_CPU_PRIV_MAX - ARM_SPE_CPU_MIDR;
+	data[ARM_SPE_CPU_MIDR] = val;
+
+	/* Find the associate Arm SPE PMU for the CPU */
+	if (perf_cpu_map__has(sper->arm_spe_pmu->cpus, cpu))
+		pmu = sper->arm_spe_pmu;
+
+	if (!pmu) {
+		/* No Arm SPE PMU is found */
+		data[ARM_SPE_CPU_PMU_TYPE] = ULLONG_MAX;
+		data[ARM_SPE_CAP_MIN_IVAL] = 0;
+	} else {
+		data[ARM_SPE_CPU_PMU_TYPE] = pmu->type;
+
+		if (perf_pmu__scan_file(pmu, "caps/min_interval", "%lu", &val) != 1)
+			val = 0;
+		data[ARM_SPE_CAP_MIN_IVAL] = val;
+	}
+
+	free(cpuid);
+	return ARM_SPE_CPU_PRIV_MAX;
+}
+
 static int arm_spe_info_fill(struct auxtrace_record *itr,
 			     struct perf_session *session,
 			     struct perf_record_auxtrace_info *auxtrace_info,
 			     size_t priv_size)
 {
+	int i, ret;
+	size_t offset;
 	struct arm_spe_recording *sper =
 			container_of(itr, struct arm_spe_recording, itr);
 	struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
+	struct perf_cpu_map *cpu_map;
+	struct perf_cpu cpu;
+	__u64 *data;
 
 	if (priv_size != arm_spe_info_priv_size(itr, session->evlist))
 		return -EINVAL;
@@ -92,10 +150,31 @@ static int arm_spe_info_fill(struct auxtrace_record *itr,
 	if (!session->evlist->core.nr_mmaps)
 		return -EINVAL;
 
+	cpu_map = arm_spe_find_cpus(session->evlist);
+	if (!cpu_map)
+		return -EINVAL;
+
 	auxtrace_info->type = PERF_AUXTRACE_ARM_SPE;
-	auxtrace_info->priv[ARM_SPE_PMU_TYPE] = arm_spe_pmu->type;
+	auxtrace_info->priv[ARM_SPE_HEADER_VERSION] = ARM_SPE_HEADER_CURRENT_VERSION;
+	auxtrace_info->priv[ARM_SPE_HEADER_SIZE] =
+		ARM_SPE_AUXTRACE_PRIV_MAX - ARM_SPE_HEADER_VERSION;
+	auxtrace_info->priv[ARM_SPE_PMU_TYPE_V2] = arm_spe_pmu->type;
+	auxtrace_info->priv[ARM_SPE_CPUS_NUM] = perf_cpu_map__nr(cpu_map);
+
+	offset = ARM_SPE_AUXTRACE_PRIV_MAX;
+	perf_cpu_map__for_each_cpu(cpu, i, cpu_map) {
+		assert(offset < priv_size);
+		data = &auxtrace_info->priv[offset];
+		ret = arm_spe_save_cpu_header(itr, cpu, data);
+		if (ret < 0)
+			goto out;
+		offset += ret;
+	}
 
-	return 0;
+	ret = 0;
+out:
+	perf_cpu_map__put(cpu_map);
+	return ret;
 }
 
 static void

From 7842a4b6ff698768ccdb13324c3902a069b5d5dd Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Thu, 3 Oct 2024 19:43:01 +0100
Subject: [PATCH 0166/1530] perf arm-spe: Support metadata version 2

This commit is to support metadata version 2 and at the meantime it is
backward compatible for version 1's format.

The metadata version 1 doesn't include the ARM_SPE_HEADER_VERSION field.
As version 1 is fixed with two u64 fields, by checking the metadata
size, it distinguishes the metadata is version 1 or version 2 (and any
new versions if later will have). For version 2, it reads out CPU number
and retrieves the metadata info for every CPU.

Signed-off-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Cc: Will Deacon <will@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Besar Wicaksono <bwicaksono@nvidia.com>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20241003184302.190806-5-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/arm-spe.c | 99 +++++++++++++++++++++++++++++++++++++--
 1 file changed, 95 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 70989b1bae478..8b2af1c7dc9b5 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -78,6 +78,10 @@ struct arm_spe {
 
 	unsigned long			num_events;
 	u8				use_ctx_pkt_for_pid;
+
+	u64				**metadata;
+	u64				metadata_ver;
+	u64				metadata_nr_cpu;
 };
 
 struct arm_spe_queue {
@@ -1016,6 +1020,73 @@ static int arm_spe_flush(struct perf_session *session __maybe_unused,
 	return 0;
 }
 
+static u64 *arm_spe__alloc_per_cpu_metadata(u64 *buf, int per_cpu_size)
+{
+	u64 *metadata;
+
+	metadata = zalloc(per_cpu_size);
+	if (!metadata)
+		return NULL;
+
+	memcpy(metadata, buf, per_cpu_size);
+	return metadata;
+}
+
+static void arm_spe__free_metadata(u64 **metadata, int nr_cpu)
+{
+	int i;
+
+	for (i = 0; i < nr_cpu; i++)
+		zfree(&metadata[i]);
+	free(metadata);
+}
+
+static u64 **arm_spe__alloc_metadata(struct perf_record_auxtrace_info *info,
+				     u64 *ver, int *nr_cpu)
+{
+	u64 *ptr = (u64 *)info->priv;
+	u64 metadata_size;
+	u64 **metadata = NULL;
+	int hdr_sz, per_cpu_sz, i;
+
+	metadata_size = info->header.size -
+		sizeof(struct perf_record_auxtrace_info);
+
+	/* Metadata version 1 */
+	if (metadata_size == ARM_SPE_AUXTRACE_V1_PRIV_SIZE) {
+		*ver = 1;
+		*nr_cpu = 0;
+		/* No per CPU metadata */
+		return NULL;
+	}
+
+	*ver = ptr[ARM_SPE_HEADER_VERSION];
+	hdr_sz = ptr[ARM_SPE_HEADER_SIZE];
+	*nr_cpu = ptr[ARM_SPE_CPUS_NUM];
+
+	metadata = calloc(*nr_cpu, sizeof(*metadata));
+	if (!metadata)
+		return NULL;
+
+	/* Locate the start address of per CPU metadata */
+	ptr += hdr_sz;
+	per_cpu_sz = (metadata_size - (hdr_sz * sizeof(u64))) / (*nr_cpu);
+
+	for (i = 0; i < *nr_cpu; i++) {
+		metadata[i] = arm_spe__alloc_per_cpu_metadata(ptr, per_cpu_sz);
+		if (!metadata[i])
+			goto err_per_cpu_metadata;
+
+		ptr += per_cpu_sz / sizeof(u64);
+	}
+
+	return metadata;
+
+err_per_cpu_metadata:
+	arm_spe__free_metadata(metadata, *nr_cpu);
+	return NULL;
+}
+
 static void arm_spe_free_queue(void *priv)
 {
 	struct arm_spe_queue *speq = priv;
@@ -1050,6 +1121,7 @@ static void arm_spe_free(struct perf_session *session)
 	auxtrace_heap__free(&spe->heap);
 	arm_spe_free_events(session);
 	session->auxtrace = NULL;
+	arm_spe__free_metadata(spe->metadata, spe->metadata_nr_cpu);
 	free(spe);
 }
 
@@ -1267,15 +1339,26 @@ int arm_spe_process_auxtrace_info(union perf_event *event,
 	const char *cpuid = perf_env__cpuid(session->evlist->env);
 	u64 midr = strtol(cpuid, NULL, 16);
 	struct arm_spe *spe;
-	int err;
+	u64 **metadata = NULL;
+	u64 metadata_ver;
+	int nr_cpu, err;
 
 	if (auxtrace_info->header.size < sizeof(struct perf_record_auxtrace_info) +
 					min_sz)
 		return -EINVAL;
 
+	metadata = arm_spe__alloc_metadata(auxtrace_info, &metadata_ver,
+					   &nr_cpu);
+	if (!metadata && metadata_ver != 1) {
+		pr_err("Failed to parse Arm SPE metadata.\n");
+		return -EINVAL;
+	}
+
 	spe = zalloc(sizeof(struct arm_spe));
-	if (!spe)
-		return -ENOMEM;
+	if (!spe) {
+		err = -ENOMEM;
+		goto err_free_metadata;
+	}
 
 	err = auxtrace_queues__init(&spe->queues);
 	if (err)
@@ -1284,8 +1367,14 @@ int arm_spe_process_auxtrace_info(union perf_event *event,
 	spe->session = session;
 	spe->machine = &session->machines.host; /* No kvm support */
 	spe->auxtrace_type = auxtrace_info->type;
-	spe->pmu_type = auxtrace_info->priv[ARM_SPE_PMU_TYPE];
+	if (metadata_ver == 1)
+		spe->pmu_type = auxtrace_info->priv[ARM_SPE_PMU_TYPE];
+	else
+		spe->pmu_type = auxtrace_info->priv[ARM_SPE_PMU_TYPE_V2];
 	spe->midr = midr;
+	spe->metadata = metadata;
+	spe->metadata_ver = metadata_ver;
+	spe->metadata_nr_cpu = nr_cpu;
 
 	spe->timeless_decoding = arm_spe__is_timeless_decoding(spe);
 
@@ -1346,5 +1435,7 @@ int arm_spe_process_auxtrace_info(union perf_event *event,
 	session->auxtrace = NULL;
 err_free:
 	free(spe);
+err_free_metadata:
+	arm_spe__free_metadata(metadata, nr_cpu);
 	return err;
 }

From e52abceb4b6c2723c7e49388e67a32ffb47bd90c Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Thu, 3 Oct 2024 19:43:02 +0100
Subject: [PATCH 0167/1530] perf arm-spe: Dump metadata with version 2

This commit dumps metadata with version 2. It dumps metadata for header
and per CPU data respectively in the arm_spe_print_info() function to
support metadata version 2 format.

After:

  0 0 0x3c0 [0x1b0]: PERF_RECORD_AUXTRACE_INFO type: 4
  Header version     :2
  Header size        :4
  PMU type v2        :13
  CPU number         :8
    Magic            :0x1010101010101010
    CPU #            :0
    Num of params    :3
    MIDR             :0x410fd801
    PMU Type         :-1
    Min Interval     :0
    Magic            :0x1010101010101010
    CPU #            :1
    Num of params    :3
    MIDR             :0x410fd801
    PMU Type         :-1
    Min Interval     :0
    Magic            :0x1010101010101010
    CPU #            :2
    Num of params    :3
    MIDR             :0x410fd870
    PMU Type         :13
    Min Interval     :1024
    Magic            :0x1010101010101010
    CPU #            :3
    Num of params    :3
    MIDR             :0x410fd870
    PMU Type         :13
    Min Interval     :1024
    Magic            :0x1010101010101010
    CPU #            :4
    Num of params    :3
    MIDR             :0x410fd870
    PMU Type         :13
    Min Interval     :1024
    Magic            :0x1010101010101010
    CPU #            :5
    Num of params    :3
    MIDR             :0x410fd870
    PMU Type         :13
    Min Interval     :1024
    Magic            :0x1010101010101010
    CPU #            :6
    Num of params    :3
    MIDR             :0x410fd850
    PMU Type         :-1
    Min Interval     :0
    Magic            :0x1010101010101010
    CPU #            :7
    Num of params    :3
    MIDR             :0x410fd850
    PMU Type         :-1
    Min Interval     :0

Signed-off-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Cc: Will Deacon <will@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Besar Wicaksono <bwicaksono@nvidia.com>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20241003184302.190806-6-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/arm-spe.c | 54 +++++++++++++++++++++++++++++++++++----
 1 file changed, 49 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 8b2af1c7dc9b5..13fd2c8afebdf 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -1133,16 +1133,60 @@ static bool arm_spe_evsel_is_auxtrace(struct perf_session *session,
 	return evsel->core.attr.type == spe->pmu_type;
 }
 
-static const char * const arm_spe_info_fmts[] = {
-	[ARM_SPE_PMU_TYPE]		= "  PMU Type           %"PRId64"\n",
+static const char * const metadata_hdr_v1_fmts[] = {
+	[ARM_SPE_PMU_TYPE]		= "  PMU Type           :%"PRId64"\n",
+	[ARM_SPE_PER_CPU_MMAPS]		= "  Per CPU mmaps      :%"PRId64"\n",
 };
 
-static void arm_spe_print_info(__u64 *arr)
+static const char * const metadata_hdr_fmts[] = {
+	[ARM_SPE_HEADER_VERSION]	= "  Header version     :%"PRId64"\n",
+	[ARM_SPE_HEADER_SIZE]		= "  Header size        :%"PRId64"\n",
+	[ARM_SPE_PMU_TYPE_V2]		= "  PMU type v2        :%"PRId64"\n",
+	[ARM_SPE_CPUS_NUM]		= "  CPU number         :%"PRId64"\n",
+};
+
+static const char * const metadata_per_cpu_fmts[] = {
+	[ARM_SPE_MAGIC]			= "    Magic            :0x%"PRIx64"\n",
+	[ARM_SPE_CPU]			= "    CPU #            :%"PRId64"\n",
+	[ARM_SPE_CPU_NR_PARAMS]		= "    Num of params    :%"PRId64"\n",
+	[ARM_SPE_CPU_MIDR]		= "    MIDR             :0x%"PRIx64"\n",
+	[ARM_SPE_CPU_PMU_TYPE]		= "    PMU Type         :%"PRId64"\n",
+	[ARM_SPE_CAP_MIN_IVAL]		= "    Min Interval     :%"PRId64"\n",
+};
+
+static void arm_spe_print_info(struct arm_spe *spe, __u64 *arr)
 {
+	unsigned int i, cpu, hdr_size, cpu_num, cpu_size;
+	const char * const *hdr_fmts;
+
 	if (!dump_trace)
 		return;
 
-	fprintf(stdout, arm_spe_info_fmts[ARM_SPE_PMU_TYPE], arr[ARM_SPE_PMU_TYPE]);
+	if (spe->metadata_ver == 1) {
+		cpu_num = 0;
+		hdr_size = ARM_SPE_AUXTRACE_V1_PRIV_MAX;
+		hdr_fmts = metadata_hdr_v1_fmts;
+	} else {
+		cpu_num = arr[ARM_SPE_CPUS_NUM];
+		hdr_size = arr[ARM_SPE_HEADER_SIZE];
+		hdr_fmts = metadata_hdr_fmts;
+	}
+
+	for (i = 0; i < hdr_size; i++)
+		fprintf(stdout, hdr_fmts[i], arr[i]);
+
+	arr += hdr_size;
+	for (cpu = 0; cpu < cpu_num; cpu++) {
+		/*
+		 * The parameters from ARM_SPE_MAGIC to ARM_SPE_CPU_NR_PARAMS
+		 * are fixed. The sequential parameter size is decided by the
+		 * field 'ARM_SPE_CPU_NR_PARAMS'.
+		 */
+		cpu_size = (ARM_SPE_CPU_NR_PARAMS + 1) + arr[ARM_SPE_CPU_NR_PARAMS];
+		for (i = 0; i < cpu_size; i++)
+			fprintf(stdout, metadata_per_cpu_fmts[i], arr[i]);
+		arr += cpu_size;
+	}
 }
 
 static void arm_spe_set_event_name(struct evlist *evlist, u64 id,
@@ -1407,7 +1451,7 @@ int arm_spe_process_auxtrace_info(union perf_event *event,
 	spe->auxtrace.evsel_is_auxtrace = arm_spe_evsel_is_auxtrace;
 	session->auxtrace = &spe->auxtrace;
 
-	arm_spe_print_info(&auxtrace_info->priv[0]);
+	arm_spe_print_info(spe, &auxtrace_info->priv[0]);
 
 	if (dump_trace)
 		return 0;

From 6bff76af9635411214ca44ea38fc2781e78064b6 Mon Sep 17 00:00:00 2001
From: Veronika Molnarova <vmolnaro@redhat.com>
Date: Mon, 11 Mar 2024 09:16:11 +0100
Subject: [PATCH 0168/1530] perf test attr: Add back missing topdown events

With the patch 0b6c5371c03c "Add missing topdown metrics events" eight
topdown metric events with numbers ranging from 0x8000 to 0x8700 were
added to the test since they were added as 'perf stat' default events.
Later the patch 951efb9976ce "Update no event/metric expectations" kept
only 4 of those events(0x8000-0x8300).

Currently, the topdown events with numbers 0x8400 to 0x8700 are missing
from the list of expected events resulting in a failure. Add back the
missing topdown events.

Fixes: 951efb9976ce ("perf test attr: Update no event/metric expectations")
Signed-off-by: Veronika Molnarova <vmolnaro@redhat.com>
Tested-by: Ian Rogers <irogers@google.com>
Cc: mpetlan@redhat.com
Link: https://lore.kernel.org/r/20240311081611.7835-1-vmolnaro@redhat.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/attr/test-stat-default    |  90 ++++++++++----
 tools/perf/tests/attr/test-stat-detailed-1 | 106 +++++++++++-----
 tools/perf/tests/attr/test-stat-detailed-2 | 130 ++++++++++++-------
 tools/perf/tests/attr/test-stat-detailed-3 | 138 ++++++++++++++-------
 4 files changed, 320 insertions(+), 144 deletions(-)

diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default
index a1e2da0a9a6dd..e47fb49446799 100644
--- a/tools/perf/tests/attr/test-stat-default
+++ b/tools/perf/tests/attr/test-stat-default
@@ -88,98 +88,142 @@ enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
+# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
 [event13:base-stat]
 fd=13
 group_fd=11
 type=4
-config=33280
+config=33024
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-be-bound (0x8300)
+# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
 [event14:base-stat]
 fd=14
 group_fd=11
 type=4
-config=33536
+config=33280
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
+# PERF_TYPE_RAW / topdown-be-bound (0x8300)
 [event15:base-stat]
 fd=15
 group_fd=11
 type=4
-config=33024
+config=33536
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING
+# PERF_TYPE_RAW / topdown-heavy-ops (0x8400)
 [event16:base-stat]
 fd=16
+group_fd=11
 type=4
-config=4109
+config=33792
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/
+# PERF_TYPE_RAW / topdown-br-mispredict (0x8500)
 [event17:base-stat]
 fd=17
+group_fd=11
 type=4
-config=17039629
+config=34048
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD
+# PERF_TYPE_RAW / topdown-fetch-lat (0x8600)
 [event18:base-stat]
 fd=18
+group_fd=11
 type=4
-config=60
+config=34304
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY
+# PERF_TYPE_RAW / topdown-mem-bound (0x8700)
 [event19:base-stat]
 fd=19
+group_fd=11
 type=4
-config=2097421
+config=34560
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK
+# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING
 [event20:base-stat]
 fd=20
 type=4
-config=316
+config=4109
 optional=1
 
-# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE
+# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/
 [event21:base-stat]
 fd=21
 type=4
-config=412
+config=17039629
 optional=1
 
-# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD
 [event22:base-stat]
 fd=22
 type=4
-config=572
+config=60
 optional=1
 
-# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS
+# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY
 [event23:base-stat]
 fd=23
 type=4
-config=706
+config=2097421
 optional=1
 
-# PERF_TYPE_RAW / UOPS_ISSUED.ANY
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK
 [event24:base-stat]
 fd=24
 type=4
+config=316
+optional=1
+
+# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE
+[event25:base-stat]
+fd=25
+type=4
+config=412
+optional=1
+
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE
+[event26:base-stat]
+fd=26
+type=4
+config=572
+optional=1
+
+# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS
+[event27:base-stat]
+fd=27
+type=4
+config=706
+optional=1
+
+# PERF_TYPE_RAW / UOPS_ISSUED.ANY
+[event28:base-stat]
+fd=28
+type=4
 config=270
 optional=1
diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1
index 1c52cb05c900d..3d500d3e0c5c8 100644
--- a/tools/perf/tests/attr/test-stat-detailed-1
+++ b/tools/perf/tests/attr/test-stat-detailed-1
@@ -90,99 +90,143 @@ enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
+# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
 [event13:base-stat]
 fd=13
 group_fd=11
 type=4
-config=33280
+config=33024
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-be-bound (0x8300)
+# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
 [event14:base-stat]
 fd=14
 group_fd=11
 type=4
-config=33536
+config=33280
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
+# PERF_TYPE_RAW / topdown-be-bound (0x8300)
 [event15:base-stat]
 fd=15
 group_fd=11
 type=4
-config=33024
+config=33536
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING
+# PERF_TYPE_RAW / topdown-heavy-ops (0x8400)
 [event16:base-stat]
 fd=16
+group_fd=11
 type=4
-config=4109
+config=33792
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/
+# PERF_TYPE_RAW / topdown-br-mispredict (0x8500)
 [event17:base-stat]
 fd=17
+group_fd=11
 type=4
-config=17039629
+config=34048
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD
+# PERF_TYPE_RAW / topdown-fetch-lat (0x8600)
 [event18:base-stat]
 fd=18
+group_fd=11
 type=4
-config=60
+config=34304
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY
+# PERF_TYPE_RAW / topdown-mem-bound (0x8700)
 [event19:base-stat]
 fd=19
+group_fd=11
 type=4
-config=2097421
+config=34560
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK
+# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING
 [event20:base-stat]
 fd=20
 type=4
-config=316
+config=4109
 optional=1
 
-# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE
+# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/
 [event21:base-stat]
 fd=21
 type=4
-config=412
+config=17039629
 optional=1
 
-# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD
 [event22:base-stat]
 fd=22
 type=4
-config=572
+config=60
 optional=1
 
-# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS
+# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY
 [event23:base-stat]
 fd=23
 type=4
-config=706
+config=2097421
 optional=1
 
-# PERF_TYPE_RAW / UOPS_ISSUED.ANY
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK
 [event24:base-stat]
 fd=24
 type=4
+config=316
+optional=1
+
+# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE
+[event25:base-stat]
+fd=25
+type=4
+config=412
+optional=1
+
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE
+[event26:base-stat]
+fd=26
+type=4
+config=572
+optional=1
+
+# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS
+[event27:base-stat]
+fd=27
+type=4
+config=706
+optional=1
+
+# PERF_TYPE_RAW / UOPS_ISSUED.ANY
+[event28:base-stat]
+fd=28
+type=4
 config=270
 optional=1
 
@@ -190,8 +234,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event25:base-stat]
-fd=25
+[event29:base-stat]
+fd=29
 type=3
 config=0
 optional=1
@@ -200,8 +244,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event26:base-stat]
-fd=26
+[event30:base-stat]
+fd=30
 type=3
 config=65536
 optional=1
@@ -210,8 +254,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event27:base-stat]
-fd=27
+[event31:base-stat]
+fd=31
 type=3
 config=2
 optional=1
@@ -220,8 +264,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event28:base-stat]
-fd=28
+[event32:base-stat]
+fd=32
 type=3
 config=65538
 optional=1
diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2
index 7e961d24a885a..01777a63752fe 100644
--- a/tools/perf/tests/attr/test-stat-detailed-2
+++ b/tools/perf/tests/attr/test-stat-detailed-2
@@ -90,99 +90,143 @@ enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
+# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
 [event13:base-stat]
 fd=13
 group_fd=11
 type=4
-config=33280
+config=33024
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-be-bound (0x8300)
+# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
 [event14:base-stat]
 fd=14
 group_fd=11
 type=4
-config=33536
+config=33280
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
+# PERF_TYPE_RAW / topdown-be-bound (0x8300)
 [event15:base-stat]
 fd=15
 group_fd=11
 type=4
-config=33024
+config=33536
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING
+# PERF_TYPE_RAW / topdown-heavy-ops (0x8400)
 [event16:base-stat]
 fd=16
+group_fd=11
 type=4
-config=4109
+config=33792
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/
+# PERF_TYPE_RAW / topdown-br-mispredict (0x8500)
 [event17:base-stat]
 fd=17
+group_fd=11
 type=4
-config=17039629
+config=34048
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD
+# PERF_TYPE_RAW / topdown-fetch-lat (0x8600)
 [event18:base-stat]
 fd=18
+group_fd=11
 type=4
-config=60
+config=34304
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY
+# PERF_TYPE_RAW / topdown-mem-bound (0x8700)
 [event19:base-stat]
 fd=19
+group_fd=11
 type=4
-config=2097421
+config=34560
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK
+# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING
 [event20:base-stat]
 fd=20
 type=4
-config=316
+config=4109
 optional=1
 
-# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE
+# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/
 [event21:base-stat]
 fd=21
 type=4
-config=412
+config=17039629
 optional=1
 
-# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD
 [event22:base-stat]
 fd=22
 type=4
-config=572
+config=60
 optional=1
 
-# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS
+# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY
 [event23:base-stat]
 fd=23
 type=4
-config=706
+config=2097421
 optional=1
 
-# PERF_TYPE_RAW / UOPS_ISSUED.ANY
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK
 [event24:base-stat]
 fd=24
 type=4
+config=316
+optional=1
+
+# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE
+[event25:base-stat]
+fd=25
+type=4
+config=412
+optional=1
+
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE
+[event26:base-stat]
+fd=26
+type=4
+config=572
+optional=1
+
+# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS
+[event27:base-stat]
+fd=27
+type=4
+config=706
+optional=1
+
+# PERF_TYPE_RAW / UOPS_ISSUED.ANY
+[event28:base-stat]
+fd=28
+type=4
 config=270
 optional=1
 
@@ -190,8 +234,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event25:base-stat]
-fd=25
+[event29:base-stat]
+fd=29
 type=3
 config=0
 optional=1
@@ -200,8 +244,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event26:base-stat]
-fd=26
+[event30:base-stat]
+fd=30
 type=3
 config=65536
 optional=1
@@ -210,8 +254,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event27:base-stat]
-fd=27
+[event31:base-stat]
+fd=31
 type=3
 config=2
 optional=1
@@ -220,8 +264,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event28:base-stat]
-fd=28
+[event32:base-stat]
+fd=32
 type=3
 config=65538
 optional=1
@@ -230,8 +274,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event29:base-stat]
-fd=29
+[event33:base-stat]
+fd=33
 type=3
 config=1
 optional=1
@@ -240,8 +284,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event30:base-stat]
-fd=30
+[event34:base-stat]
+fd=34
 type=3
 config=65537
 optional=1
@@ -250,8 +294,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event31:base-stat]
-fd=31
+[event35:base-stat]
+fd=35
 type=3
 config=3
 optional=1
@@ -260,8 +304,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event32:base-stat]
-fd=32
+[event36:base-stat]
+fd=36
 type=3
 config=65539
 optional=1
@@ -270,8 +314,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event33:base-stat]
-fd=33
+[event37:base-stat]
+fd=37
 type=3
 config=4
 optional=1
@@ -280,8 +324,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event34:base-stat]
-fd=34
+[event38:base-stat]
+fd=38
 type=3
 config=65540
 optional=1
diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3
index e50535f45977c..8400abd7e1e48 100644
--- a/tools/perf/tests/attr/test-stat-detailed-3
+++ b/tools/perf/tests/attr/test-stat-detailed-3
@@ -90,99 +90,143 @@ enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
+# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
 [event13:base-stat]
 fd=13
 group_fd=11
 type=4
-config=33280
+config=33024
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-be-bound (0x8300)
+# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
 [event14:base-stat]
 fd=14
 group_fd=11
 type=4
-config=33536
+config=33280
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
+# PERF_TYPE_RAW / topdown-be-bound (0x8300)
 [event15:base-stat]
 fd=15
 group_fd=11
 type=4
-config=33024
+config=33536
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING
+# PERF_TYPE_RAW / topdown-heavy-ops (0x8400)
 [event16:base-stat]
 fd=16
+group_fd=11
 type=4
-config=4109
+config=33792
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/
+# PERF_TYPE_RAW / topdown-br-mispredict (0x8500)
 [event17:base-stat]
 fd=17
+group_fd=11
 type=4
-config=17039629
+config=34048
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD
+# PERF_TYPE_RAW / topdown-fetch-lat (0x8600)
 [event18:base-stat]
 fd=18
+group_fd=11
 type=4
-config=60
+config=34304
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY
+# PERF_TYPE_RAW / topdown-mem-bound (0x8700)
 [event19:base-stat]
 fd=19
+group_fd=11
 type=4
-config=2097421
+config=34560
+disabled=0
+enable_on_exec=0
+read_format=15
 optional=1
 
-# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK
+# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING
 [event20:base-stat]
 fd=20
 type=4
-config=316
+config=4109
 optional=1
 
-# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE
+# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/
 [event21:base-stat]
 fd=21
 type=4
-config=412
+config=17039629
 optional=1
 
-# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD
 [event22:base-stat]
 fd=22
 type=4
-config=572
+config=60
 optional=1
 
-# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS
+# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY
 [event23:base-stat]
 fd=23
 type=4
-config=706
+config=2097421
 optional=1
 
-# PERF_TYPE_RAW / UOPS_ISSUED.ANY
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK
 [event24:base-stat]
 fd=24
 type=4
+config=316
+optional=1
+
+# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE
+[event25:base-stat]
+fd=25
+type=4
+config=412
+optional=1
+
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE
+[event26:base-stat]
+fd=26
+type=4
+config=572
+optional=1
+
+# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS
+[event27:base-stat]
+fd=27
+type=4
+config=706
+optional=1
+
+# PERF_TYPE_RAW / UOPS_ISSUED.ANY
+[event28:base-stat]
+fd=28
+type=4
 config=270
 optional=1
 
@@ -190,8 +234,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event25:base-stat]
-fd=25
+[event29:base-stat]
+fd=29
 type=3
 config=0
 optional=1
@@ -200,8 +244,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event26:base-stat]
-fd=26
+[event30:base-stat]
+fd=30
 type=3
 config=65536
 optional=1
@@ -210,8 +254,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event27:base-stat]
-fd=27
+[event31:base-stat]
+fd=31
 type=3
 config=2
 optional=1
@@ -220,8 +264,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event28:base-stat]
-fd=28
+[event32:base-stat]
+fd=32
 type=3
 config=65538
 optional=1
@@ -230,8 +274,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event29:base-stat]
-fd=29
+[event33:base-stat]
+fd=33
 type=3
 config=1
 optional=1
@@ -240,8 +284,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event30:base-stat]
-fd=30
+[event34:base-stat]
+fd=34
 type=3
 config=65537
 optional=1
@@ -250,8 +294,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event31:base-stat]
-fd=31
+[event35:base-stat]
+fd=35
 type=3
 config=3
 optional=1
@@ -260,8 +304,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event32:base-stat]
-fd=32
+[event36:base-stat]
+fd=36
 type=3
 config=65539
 optional=1
@@ -270,8 +314,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event33:base-stat]
-fd=33
+[event37:base-stat]
+fd=37
 type=3
 config=4
 optional=1
@@ -280,8 +324,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event34:base-stat]
-fd=34
+[event38:base-stat]
+fd=38
 type=3
 config=65540
 optional=1
@@ -290,8 +334,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_PREFETCH        <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event35:base-stat]
-fd=35
+[event39:base-stat]
+fd=39
 type=3
 config=512
 optional=1
@@ -300,8 +344,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_PREFETCH        <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event36:base-stat]
-fd=36
+[event40:base-stat]
+fd=40
 type=3
 config=66048
 optional=1

From c602a04b27ec80ada4b288967a09f213d5e05722 Mon Sep 17 00:00:00 2001
From: Xin Liu <quic_liuxin@quicinc.com>
Date: Wed, 11 Sep 2024 15:06:36 +0800
Subject: [PATCH 0169/1530] scsi: ufs: ufs: qcom: dt-bindings: Document the
 QCS8300 UFS Controller

Document the Universal Flash Storage(UFS) Controller on the Qualcomm
QCS8300 Platform.

Signed-off-by: Xin Liu <quic_liuxin@quicinc.com>
Signed-off-by: Jingyi Wang <quic_jingyw@quicinc.com>
Link: https://lore.kernel.org/r/20240911-qcs8300_ufs_binding-v2-1-68bb66d48730@quicinc.com
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Acked-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 Documentation/devicetree/bindings/ufs/qcom,ufs.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml b/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml
index 25a5edeea1645..cde334e3206b0 100644
--- a/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml
+++ b/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml
@@ -26,6 +26,7 @@ properties:
           - qcom,msm8994-ufshc
           - qcom,msm8996-ufshc
           - qcom,msm8998-ufshc
+          - qcom,qcs8300-ufshc
           - qcom,sa8775p-ufshc
           - qcom,sc7180-ufshc
           - qcom,sc7280-ufshc
@@ -146,6 +147,7 @@ allOf:
           contains:
             enum:
               - qcom,msm8998-ufshc
+              - qcom,qcs8300-ufshc
               - qcom,sa8775p-ufshc
               - qcom,sc7280-ufshc
               - qcom,sc8180x-ufshc

From 22fbabe82cea7af4127f089b7f3553cd75571d9a Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Thu, 12 Sep 2024 15:30:02 -0700
Subject: [PATCH 0170/1530] scsi: ufs: core: Improve the struct ufs_hba
 documentation

Make the role of the structure members related to UIC command processing
more clear.

Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20240912223019.3510966-2-bvanassche@acm.org
Reviewed-by: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 include/ufs/ufshcd.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index 3f68ae3e4330d..a95282b9f743f 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -877,9 +877,10 @@ enum ufshcd_mcq_opr {
  * @tmf_tag_set: TMF tag set.
  * @tmf_queue: Used to allocate TMF tags.
  * @tmf_rqs: array with pointers to TMF requests while these are in progress.
- * @active_uic_cmd: handle of active UIC command
- * @uic_cmd_mutex: mutex for UIC command
- * @uic_async_done: completion used during UIC processing
+ * @active_uic_cmd: pointer to active UIC command.
+ * @uic_cmd_mutex: mutex used for serializing UIC command processing.
+ * @uic_async_done: completion used to wait for power mode or hibernation state
+ *	changes.
  * @ufshcd_state: UFSHCD state
  * @eh_flags: Error handling flags
  * @intr_mask: Interrupt Mask Bits

From e31931d646d3bc2223d9a275bac9cdc4963c5bc1 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Thu, 12 Sep 2024 15:30:03 -0700
Subject: [PATCH 0171/1530] scsi: ufs: core: Make ufshcd_uic_cmd_compl() easier
 to read

Introduce a local variable for the expression hba->active_uic_cmd.
Remove superfluous parentheses. No functionality has been changed.

Reviewed-by: Bean Huo <beanhuo@micron.com>
Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20240912223019.3510966-3-bvanassche@acm.org
Reviewed-by: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 24a32e2fd75e4..8212e2d14256b 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -5477,31 +5477,30 @@ static bool ufshcd_is_auto_hibern8_error(struct ufs_hba *hba,
 static irqreturn_t ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status)
 {
 	irqreturn_t retval = IRQ_NONE;
+	struct uic_command *cmd;
 
 	spin_lock(hba->host->host_lock);
+	cmd = hba->active_uic_cmd;
 	if (ufshcd_is_auto_hibern8_error(hba, intr_status))
 		hba->errors |= (UFSHCD_UIC_HIBERN8_MASK & intr_status);
 
-	if ((intr_status & UIC_COMMAND_COMPL) && hba->active_uic_cmd) {
-		hba->active_uic_cmd->argument2 |=
-			ufshcd_get_uic_cmd_result(hba);
-		hba->active_uic_cmd->argument3 =
-			ufshcd_get_dme_attr_val(hba);
+	if (intr_status & UIC_COMMAND_COMPL && cmd) {
+		cmd->argument2 |= ufshcd_get_uic_cmd_result(hba);
+		cmd->argument3 = ufshcd_get_dme_attr_val(hba);
 		if (!hba->uic_async_done)
-			hba->active_uic_cmd->cmd_active = 0;
-		complete(&hba->active_uic_cmd->done);
+			cmd->cmd_active = 0;
+		complete(&cmd->done);
 		retval = IRQ_HANDLED;
 	}
 
-	if ((intr_status & UFSHCD_UIC_PWR_MASK) && hba->uic_async_done) {
-		hba->active_uic_cmd->cmd_active = 0;
+	if (intr_status & UFSHCD_UIC_PWR_MASK && hba->uic_async_done) {
+		cmd->cmd_active = 0;
 		complete(hba->uic_async_done);
 		retval = IRQ_HANDLED;
 	}
 
 	if (retval == IRQ_HANDLED)
-		ufshcd_add_uic_command_trace(hba, hba->active_uic_cmd,
-					     UFS_CMD_COMP);
+		ufshcd_add_uic_command_trace(hba, cmd, UFS_CMD_COMP);
 	spin_unlock(hba->host->host_lock);
 	return retval;
 }

From fcd8b0450a9acbf3f0e88d749a72ef932df97663 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Thu, 12 Sep 2024 15:30:04 -0700
Subject: [PATCH 0172/1530] scsi: ufs: core: Make ufshcd_uic_cmd_compl() easier
 to analyze

In ufshcd_uic_cmd_compl(), there is code that dereferences 'cmd' with
and without checking the 'cmd' pointer. This confuses static source code
analyzers like Coverity and sparse. Since none of the code in
ufshcd_uic_cmd_compl() can do anything useful if 'cmd' is NULL, move the
'cmd' test near the start of this function.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20240912223019.3510966-4-bvanassche@acm.org
Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Reviewed-by: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 8212e2d14256b..0c803b6f22219 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -5481,10 +5481,13 @@ static irqreturn_t ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status)
 
 	spin_lock(hba->host->host_lock);
 	cmd = hba->active_uic_cmd;
+	if (WARN_ON_ONCE(!cmd))
+		goto unlock;
+
 	if (ufshcd_is_auto_hibern8_error(hba, intr_status))
 		hba->errors |= (UFSHCD_UIC_HIBERN8_MASK & intr_status);
 
-	if (intr_status & UIC_COMMAND_COMPL && cmd) {
+	if (intr_status & UIC_COMMAND_COMPL) {
 		cmd->argument2 |= ufshcd_get_uic_cmd_result(hba);
 		cmd->argument3 = ufshcd_get_dme_attr_val(hba);
 		if (!hba->uic_async_done)
@@ -5501,7 +5504,10 @@ static irqreturn_t ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status)
 
 	if (retval == IRQ_HANDLED)
 		ufshcd_add_uic_command_trace(hba, cmd, UFS_CMD_COMP);
+
+unlock:
 	spin_unlock(hba->host->host_lock);
+
 	return retval;
 }
 

From b1e8c53749adb795bfb0bf4e2f7836e26684bb90 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Thu, 12 Sep 2024 15:30:05 -0700
Subject: [PATCH 0173/1530] scsi: ufs: core: Always initialize the UIC done
 completion

Simplify __ufshcd_send_uic_cmd() by always initializing the
uic_cmd::done completion. This is fine since the time required to
initialize a completion is small compared to the time required to
process an UIC command.

Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20240912223019.3510966-5-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 0c803b6f22219..d6528048c77f9 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -2551,13 +2551,11 @@ ufshcd_wait_for_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
  * __ufshcd_send_uic_cmd - Send UIC commands and retrieve the result
  * @hba: per adapter instance
  * @uic_cmd: UIC command
- * @completion: initialize the completion only if this is set to true
  *
  * Return: 0 only if success.
  */
 static int
-__ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd,
-		      bool completion)
+__ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
 {
 	lockdep_assert_held(&hba->uic_cmd_mutex);
 
@@ -2567,8 +2565,7 @@ __ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd,
 		return -EIO;
 	}
 
-	if (completion)
-		init_completion(&uic_cmd->done);
+	init_completion(&uic_cmd->done);
 
 	uic_cmd->cmd_active = 1;
 	ufshcd_dispatch_uic_cmd(hba, uic_cmd);
@@ -2594,7 +2591,7 @@ int ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
 	mutex_lock(&hba->uic_cmd_mutex);
 	ufshcd_add_delay_before_dme_cmd(hba);
 
-	ret = __ufshcd_send_uic_cmd(hba, uic_cmd, true);
+	ret = __ufshcd_send_uic_cmd(hba, uic_cmd);
 	if (!ret)
 		ret = ufshcd_wait_for_uic_cmd(hba, uic_cmd);
 
@@ -4289,7 +4286,7 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd)
 		reenable_intr = true;
 	}
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
-	ret = __ufshcd_send_uic_cmd(hba, cmd, false);
+	ret = __ufshcd_send_uic_cmd(hba, cmd);
 	if (ret) {
 		dev_err(hba->dev,
 			"pwr ctrl cmd 0x%x with mode 0x%x uic error %d\n",

From ab19e3154cc12fdf6c39b6e0a2ed518e45d9f876 Mon Sep 17 00:00:00 2001
From: Liao Chen <liaochen4@huawei.com>
Date: Sat, 21 Sep 2024 06:29:56 +0000
Subject: [PATCH 0174/1530] scsi: qedf: Remove dead code

If container_of() is used correctly, its result is never NULL. Remove the
code that depends on container_of() returning a NULL pointer.

Signed-off-by: Liao Chen <liaochen4@huawei.com>
Link: https://lore.kernel.org/r/20240921062956.2027563-1-liaochen4@huawei.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qedf/qedf_main.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index cf13148ba281c..df756f3eef3e8 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -4018,11 +4018,6 @@ void qedf_stag_change_work(struct work_struct *work)
 	struct qedf_ctx *qedf =
 	    container_of(work, struct qedf_ctx, stag_work.work);
 
-	if (!qedf) {
-		QEDF_ERR(&qedf->dbg_ctx, "qedf is NULL");
-		return;
-	}
-
 	if (test_bit(QEDF_IN_RECOVERY, &qedf->flags)) {
 		QEDF_ERR(&qedf->dbg_ctx,
 			 "Already is in recovery, hence not calling software context reset.\n");

From aa948b39ddc703ca6a0d0e1b1ab593767d67363c Mon Sep 17 00:00:00 2001
From: Liu Jing <liujing@cmss.chinamobile.com>
Date: Sat, 21 Sep 2024 18:45:37 +0800
Subject: [PATCH 0175/1530] scsi: bfa: Fix cacography in bfi.h file

Signed-off-by: Liu Jing <liujing@cmss.chinamobile.com>
Link: https://lore.kernel.org/r/20240921104537.14843-1-liujing@cmss.chinamobile.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/bfa/bfi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/bfa/bfi.h b/drivers/scsi/bfa/bfi.h
index 41e6b4dac056a..e1e0e967bcc3f 100644
--- a/drivers/scsi/bfa/bfi.h
+++ b/drivers/scsi/bfa/bfi.h
@@ -1148,7 +1148,7 @@ struct bfi_diag_dport_scn_testcomp_s {
 	u16	numbuffer; /* from switch  */
 	u8	subtest_status[DPORT_TEST_MAX];  /* 4 bytes */
 	u32	latency;   /* from switch  */
-	u32	distance;  /* from swtich unit in meters  */
+	u32	distance;  /* from switch unit in meters  */
 			/* Buffers required to saturate the link */
 	u16	frm_sz;	/* from switch for buf_reqd */
 	u8	rsvd[2];

From 5a66581a1af50b45bd4ced096201dfaac4d1ca83 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Fri, 20 Sep 2024 21:23:04 +0100
Subject: [PATCH 0176/1530] scsi: aacraid: Remove unused aac_check_health()

aac_check_health() has been unused since commit

  9473ddb2b037 ("scsi: aacraid: Use correct function to get ctrl health")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://lore.kernel.org/r/20240920202304.333108-1-linux@treblig.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/aacraid.h |   1 -
 drivers/scsi/aacraid/commsup.c | 121 ---------------------------------
 2 files changed, 122 deletions(-)

diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index 1d09d3ac6aa45..8c384c25dca17 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -2736,7 +2736,6 @@ unsigned int aac_intr_normal(struct aac_dev *dev, u32 Index,
 			int isAif, int isFastResponse,
 			struct hw_fib *aif_fib);
 int aac_reset_adapter(struct aac_dev *dev, int forced, u8 reset_type);
-int aac_check_health(struct aac_dev * dev);
 int aac_command_thread(void *data);
 int aac_close_fib_context(struct aac_dev * dev, struct aac_fib_context *fibctx);
 int aac_fib_adapter_complete(struct fib * fibptr, unsigned short size);
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 47287559c768f..ffef61c4aa015 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -1698,127 +1698,6 @@ int aac_reset_adapter(struct aac_dev *aac, int forced, u8 reset_type)
 	return retval;
 }
 
-int aac_check_health(struct aac_dev * aac)
-{
-	int BlinkLED;
-	unsigned long time_now, flagv = 0;
-	struct list_head * entry;
-
-	/* Extending the scope of fib_lock slightly to protect aac->in_reset */
-	if (spin_trylock_irqsave(&aac->fib_lock, flagv) == 0)
-		return 0;
-
-	if (aac->in_reset || !(BlinkLED = aac_adapter_check_health(aac))) {
-		spin_unlock_irqrestore(&aac->fib_lock, flagv);
-		return 0; /* OK */
-	}
-
-	aac->in_reset = 1;
-
-	/* Fake up an AIF:
-	 *	aac_aifcmd.command = AifCmdEventNotify = 1
-	 *	aac_aifcmd.seqnum = 0xFFFFFFFF
-	 *	aac_aifcmd.data[0] = AifEnExpEvent = 23
-	 *	aac_aifcmd.data[1] = AifExeFirmwarePanic = 3
-	 *	aac.aifcmd.data[2] = AifHighPriority = 3
-	 *	aac.aifcmd.data[3] = BlinkLED
-	 */
-
-	time_now = jiffies/HZ;
-	entry = aac->fib_list.next;
-
-	/*
-	 * For each Context that is on the
-	 * fibctxList, make a copy of the
-	 * fib, and then set the event to wake up the
-	 * thread that is waiting for it.
-	 */
-	while (entry != &aac->fib_list) {
-		/*
-		 * Extract the fibctx
-		 */
-		struct aac_fib_context *fibctx = list_entry(entry, struct aac_fib_context, next);
-		struct hw_fib * hw_fib;
-		struct fib * fib;
-		/*
-		 * Check if the queue is getting
-		 * backlogged
-		 */
-		if (fibctx->count > 20) {
-			/*
-			 * It's *not* jiffies folks,
-			 * but jiffies / HZ, so do not
-			 * panic ...
-			 */
-			u32 time_last = fibctx->jiffies;
-			/*
-			 * Has it been > 2 minutes
-			 * since the last read off
-			 * the queue?
-			 */
-			if ((time_now - time_last) > aif_timeout) {
-				entry = entry->next;
-				aac_close_fib_context(aac, fibctx);
-				continue;
-			}
-		}
-		/*
-		 * Warning: no sleep allowed while
-		 * holding spinlock
-		 */
-		hw_fib = kzalloc(sizeof(struct hw_fib), GFP_ATOMIC);
-		fib = kzalloc(sizeof(struct fib), GFP_ATOMIC);
-		if (fib && hw_fib) {
-			struct aac_aifcmd * aif;
-
-			fib->hw_fib_va = hw_fib;
-			fib->dev = aac;
-			aac_fib_init(fib);
-			fib->type = FSAFS_NTC_FIB_CONTEXT;
-			fib->size = sizeof (struct fib);
-			fib->data = hw_fib->data;
-			aif = (struct aac_aifcmd *)hw_fib->data;
-			aif->command = cpu_to_le32(AifCmdEventNotify);
-			aif->seqnum = cpu_to_le32(0xFFFFFFFF);
-			((__le32 *)aif->data)[0] = cpu_to_le32(AifEnExpEvent);
-			((__le32 *)aif->data)[1] = cpu_to_le32(AifExeFirmwarePanic);
-			((__le32 *)aif->data)[2] = cpu_to_le32(AifHighPriority);
-			((__le32 *)aif->data)[3] = cpu_to_le32(BlinkLED);
-
-			/*
-			 * Put the FIB onto the
-			 * fibctx's fibs
-			 */
-			list_add_tail(&fib->fiblink, &fibctx->fib_list);
-			fibctx->count++;
-			/*
-			 * Set the event to wake up the
-			 * thread that will waiting.
-			 */
-			complete(&fibctx->completion);
-		} else {
-			printk(KERN_WARNING "aifd: didn't allocate NewFib.\n");
-			kfree(fib);
-			kfree(hw_fib);
-		}
-		entry = entry->next;
-	}
-
-	spin_unlock_irqrestore(&aac->fib_lock, flagv);
-
-	if (BlinkLED < 0) {
-		printk(KERN_ERR "%s: Host adapter is dead (or got a PCI error) %d\n",
-				aac->name, BlinkLED);
-		goto out;
-	}
-
-	printk(KERN_ERR "%s: Host adapter BLINK LED 0x%x\n", aac->name, BlinkLED);
-
-out:
-	aac->in_reset = 0;
-	return BlinkLED;
-}
-
 static inline int is_safw_raid_volume(struct aac_dev *aac, int bus, int target)
 {
 	return bus == CONTAINER_CHANNEL && target < aac->maximum_num_containers;

From 0b1e535598d576e0727b2028a4e4e69f3e46596a Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Fri, 13 Sep 2024 18:01:16 +0100
Subject: [PATCH 0177/1530] scsi: aic7xxx: Remove unused aic7770_find_device()

'aic7770_find_device()' has been unused since 2005's
  commit dedd83108105 ("[SCSI] aic7xxx: remove Linux 2.4 ifdefs")

Remove it and the associated constant. (Whether anyone still has one of
these cards in use is another question, I've just build tested this).

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://lore.kernel.org/r/20240913170116.250996-1-linux@treblig.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aic7xxx/aic7770.c | 15 ---------------
 drivers/scsi/aic7xxx/aic7xxx.h |  2 --
 2 files changed, 17 deletions(-)

diff --git a/drivers/scsi/aic7xxx/aic7770.c b/drivers/scsi/aic7xxx/aic7770.c
index 176704b24e6ab..f1ce02cd569e3 100644
--- a/drivers/scsi/aic7xxx/aic7770.c
+++ b/drivers/scsi/aic7xxx/aic7770.c
@@ -99,21 +99,6 @@ struct aic7770_identity aic7770_ident_table[] =
 		ahc_aic7770_EISA_setup
 	}
 };
-const int ahc_num_aic7770_devs = ARRAY_SIZE(aic7770_ident_table);
-
-struct aic7770_identity *
-aic7770_find_device(uint32_t id)
-{
-	struct	aic7770_identity *entry;
-	int	i;
-
-	for (i = 0; i < ahc_num_aic7770_devs; i++) {
-		entry = &aic7770_ident_table[i];
-		if (entry->full_id == (id & entry->id_mask))
-			return (entry);
-	}
-	return (NULL);
-}
 
 int
 aic7770_config(struct ahc_softc *ahc, struct aic7770_identity *entry, u_int io)
diff --git a/drivers/scsi/aic7xxx/aic7xxx.h b/drivers/scsi/aic7xxx/aic7xxx.h
index 9bc755a0a2d38..20857c213c726 100644
--- a/drivers/scsi/aic7xxx/aic7xxx.h
+++ b/drivers/scsi/aic7xxx/aic7xxx.h
@@ -1119,7 +1119,6 @@ struct aic7770_identity {
 	ahc_device_setup_t	*setup;
 };
 extern struct aic7770_identity aic7770_ident_table[];
-extern const int ahc_num_aic7770_devs;
 
 #define AHC_EISA_SLOT_OFFSET	0xc00
 #define AHC_EISA_IOSIZE		0x100
@@ -1135,7 +1134,6 @@ int			 ahc_pci_test_register_access(struct ahc_softc *);
 void __maybe_unused	 ahc_pci_resume(struct ahc_softc *ahc);
 
 /*************************** EISA/VL Front End ********************************/
-struct aic7770_identity *aic7770_find_device(uint32_t);
 int			 aic7770_config(struct ahc_softc *ahc,
 					struct aic7770_identity *,
 					u_int port);

From 09822c231ae69e4ebc686ebe8b8cad02bcafea54 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 30 Sep 2024 13:13:47 -0700
Subject: [PATCH 0178/1530] scsi: mptfusion: Remove #ifndef __GENKSYMS__ /
 #endif

Except for preventing build errors, there shouldn't be any conditionals in
kernel drivers on __GENKSYMS__. Hence remove an #ifndef __GENKSYMS__ / #endif
pair from the MPT Fusion driver.

Cc: Sathya Prakash <sathya.prakash@broadcom.com>
Cc: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Cc: Suganath Prabu Subramani <suganath-prabu.subramani@broadcom.com>
Cc: MPT-FusionLinux.pdl@broadcom.com
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20240930201347.1837690-1-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/message/fusion/mptlan.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/message/fusion/mptlan.h b/drivers/message/fusion/mptlan.h
index a1ec7e84d6fe4..40b34f670065c 100644
--- a/drivers/message/fusion/mptlan.h
+++ b/drivers/message/fusion/mptlan.h
@@ -51,10 +51,7 @@
 #define LINUX_MPTLAN_H_INCLUDED
 /*****************************************************************************/
 
-#if !defined(__GENKSYMS__)
 #include <linux/module.h>
-#endif
-
 #include <linux/netdevice.h>
 #include <linux/errno.h>
 // #include <linux/etherdevice.h>

From 71ef4e6b05ae0a1b6bd8ba864815b01e041dfd10 Mon Sep 17 00:00:00 2001
From: Avri Altman <avri.altman@wdc.com>
Date: Thu, 19 Sep 2024 14:24:42 +0300
Subject: [PATCH 0179/1530] scsi: ufs: core: Do not open code read_poll_timeout

ufshcd_wait_for_register() practically does just that - replace with
read_poll_timeout.

Signed-off-by: Avri Altman <avri.altman@wdc.com>
Link: https://lore.kernel.org/r/20240919112442.48491-1-avri.altman@wdc.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 22 ++++++----------------
 1 file changed, 6 insertions(+), 16 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index d6528048c77f9..14a41d7c2d1af 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -739,25 +739,15 @@ EXPORT_SYMBOL_GPL(ufshcd_delay_us);
  * Return: -ETIMEDOUT on error, zero on success.
  */
 static int ufshcd_wait_for_register(struct ufs_hba *hba, u32 reg, u32 mask,
-				u32 val, unsigned long interval_us,
-				unsigned long timeout_ms)
+				    u32 val, unsigned long interval_us,
+				    unsigned long timeout_ms)
 {
-	int err = 0;
-	unsigned long timeout = jiffies + msecs_to_jiffies(timeout_ms);
-
-	/* ignore bits that we don't intend to wait on */
-	val = val & mask;
+	u32 v;
 
-	while ((ufshcd_readl(hba, reg) & mask) != val) {
-		usleep_range(interval_us, interval_us + 50);
-		if (time_after(jiffies, timeout)) {
-			if ((ufshcd_readl(hba, reg) & mask) != val)
-				err = -ETIMEDOUT;
-			break;
-		}
-	}
+	val &= mask; /* ignore bits that we don't intend to wait on */
 
-	return err;
+	return read_poll_timeout(ufshcd_readl, v, (v & mask) == val,
+				 interval_us, timeout_ms * 1000, false, hba, reg);
 }
 
 /**

From 43abe48d95fee8816f79e085ea9c86e4f65607e7 Mon Sep 17 00:00:00 2001
From: Avri Altman <avri.altman@wdc.com>
Date: Sat, 21 Sep 2024 09:23:06 +0300
Subject: [PATCH 0180/1530] scsi: ufs: core: Zero utp_upiu_req at the beginning
 of each command

This patch introduces a previously missing step: zeroing the 'utp_upiu_req'
structure at the beginning of each upiu transaction. This ensures that the
upiu request fields are properly initialized, preventing potential issues
caused by residual data from previous commands.

While at it, re-use some of the common initializations for query and
command upiu.

Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Avri Altman <avri.altman@wdc.com>
Link: https://lore.kernel.org/r/20240921062306.56019-1-avri.altman@wdc.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 36 ++++++++++++++++++++++--------------
 1 file changed, 22 insertions(+), 14 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 14a41d7c2d1af..9e6d008f4ea4a 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -2762,7 +2762,6 @@ void ufshcd_prepare_utp_scsi_cmd_upiu(struct ufshcd_lrb *lrbp, u8 upiu_flags)
 	ucd_req_ptr->sc.exp_data_transfer_len = cpu_to_be32(cmd->sdb.length);
 
 	cdb_len = min_t(unsigned short, cmd->cmd_len, UFS_CDB_SIZE);
-	memset(ucd_req_ptr->sc.cdb, 0, UFS_CDB_SIZE);
 	memcpy(ucd_req_ptr->sc.cdb, cmd->cmnd, cdb_len);
 
 	memset(lrbp->ucd_rsp_ptr, 0, sizeof(struct utp_upiu_rsp));
@@ -2865,6 +2864,26 @@ static void ufshcd_comp_scsi_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 	ufshcd_prepare_utp_scsi_cmd_upiu(lrbp, upiu_flags);
 }
 
+static void __ufshcd_setup_cmd(struct ufshcd_lrb *lrbp, struct scsi_cmnd *cmd, u8 lun, int tag)
+{
+	memset(lrbp->ucd_req_ptr, 0, sizeof(*lrbp->ucd_req_ptr));
+
+	lrbp->cmd = cmd;
+	lrbp->task_tag = tag;
+	lrbp->lun = lun;
+	ufshcd_prepare_lrbp_crypto(cmd ? scsi_cmd_to_rq(cmd) : NULL, lrbp);
+}
+
+static void ufshcd_setup_scsi_cmd(struct ufs_hba *hba, struct ufshcd_lrb *lrbp,
+				  struct scsi_cmnd *cmd, u8 lun, int tag)
+{
+	__ufshcd_setup_cmd(lrbp, cmd, lun, tag);
+	lrbp->intr_cmd = !ufshcd_is_intr_aggr_allowed(hba);
+	lrbp->req_abort_skip = false;
+
+	ufshcd_comp_scsi_upiu(hba, lrbp);
+}
+
 /**
  * ufshcd_upiu_wlun_to_scsi_wlun - maps UPIU W-LUN id to SCSI W-LUN ID
  * @upiu_wlun_id: UPIU W-LUN id
@@ -2998,16 +3017,8 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	ufshcd_hold(hba);
 
 	lrbp = &hba->lrb[tag];
-	lrbp->cmd = cmd;
-	lrbp->task_tag = tag;
-	lrbp->lun = ufshcd_scsi_to_upiu_lun(cmd->device->lun);
-	lrbp->intr_cmd = !ufshcd_is_intr_aggr_allowed(hba);
 
-	ufshcd_prepare_lrbp_crypto(scsi_cmd_to_rq(cmd), lrbp);
-
-	lrbp->req_abort_skip = false;
-
-	ufshcd_comp_scsi_upiu(hba, lrbp);
+	ufshcd_setup_scsi_cmd(hba, lrbp, cmd, ufshcd_scsi_to_upiu_lun(cmd->device->lun), tag);
 
 	err = ufshcd_map_sg(hba, lrbp);
 	if (err) {
@@ -3035,11 +3046,8 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 static void ufshcd_setup_dev_cmd(struct ufs_hba *hba, struct ufshcd_lrb *lrbp,
 			     enum dev_cmd_type cmd_type, u8 lun, int tag)
 {
-	lrbp->cmd = NULL;
-	lrbp->task_tag = tag;
-	lrbp->lun = lun;
+	__ufshcd_setup_cmd(lrbp, NULL, lun, tag);
 	lrbp->intr_cmd = true; /* No interrupt aggregation */
-	ufshcd_prepare_lrbp_crypto(NULL, lrbp);
 	hba->dev_cmd.type = cmd_type;
 }
 

From 94c4c5d78b0f7537354b2f1c0fd6e9dc18fe0699 Mon Sep 17 00:00:00 2001
From: Manish Pandey <quic_mapa@quicinc.com>
Date: Tue, 3 Sep 2024 18:45:46 +0530
Subject: [PATCH 0181/1530] scsi: ufs: ufs-qcom: Add fixup_dev_quirks vops

Add fixup_dev_quirk vops in QCOM UFS platforms and provide an initial
vendor-specific device quirk table to add UFS device specific quirks which
are enabled only for specified UFS devices.

 - Add DELAY_BEFORE_LPM quirk for Skhynix UFS devices to introduce a delay
   before VCC is powered off in QCOM platforms.

 - Add DELAY_AFTER_LPM quirk for Toshiba UFS devices to introduce a delay
   after the VCC power rail is turned off in QCOM platforms.

 - Move UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE quirk from
   ufs_qcom_apply_dev_quirks to ufs_qcom_dev_fixups.

Signed-off-by: Manish Pandey <quic_mapa@quicinc.com>
Link: https://lore.kernel.org/r/20240903131546.1141-1-quic_mapa@quicinc.com
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-qcom.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index ecdfff2456e31..a5a0646bb80a8 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -828,12 +828,28 @@ static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba)
 	if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME)
 		err = ufs_qcom_quirk_host_pa_saveconfigtime(hba);
 
-	if (hba->dev_info.wmanufacturerid == UFS_VENDOR_WDC)
-		hba->dev_quirks |= UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE;
-
 	return err;
 }
 
+/* UFS device-specific quirks */
+static struct ufs_dev_quirk ufs_qcom_dev_fixups[] = {
+	{ .wmanufacturerid = UFS_VENDOR_SKHYNIX,
+	  .model = UFS_ANY_MODEL,
+	  .quirk = UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM },
+	{ .wmanufacturerid = UFS_VENDOR_TOSHIBA,
+	  .model = UFS_ANY_MODEL,
+	  .quirk = UFS_DEVICE_QUIRK_DELAY_AFTER_LPM },
+	{ .wmanufacturerid = UFS_VENDOR_WDC,
+	  .model = UFS_ANY_MODEL,
+	  .quirk = UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE },
+	{}
+};
+
+static void ufs_qcom_fixup_dev_quirks(struct ufs_hba *hba)
+{
+	ufshcd_fixup_dev_quirks(hba, ufs_qcom_dev_fixups);
+}
+
 static u32 ufs_qcom_get_ufs_hci_version(struct ufs_hba *hba)
 {
 	return ufshci_version(2, 0);
@@ -1801,6 +1817,7 @@ static const struct ufs_hba_variant_ops ufs_hba_qcom_vops = {
 	.link_startup_notify    = ufs_qcom_link_startup_notify,
 	.pwr_change_notify	= ufs_qcom_pwr_change_notify,
 	.apply_dev_quirks	= ufs_qcom_apply_dev_quirks,
+	.fixup_dev_quirks       = ufs_qcom_fixup_dev_quirks,
 	.suspend		= ufs_qcom_suspend,
 	.resume			= ufs_qcom_resume,
 	.dbg_register_dump	= ufs_qcom_dump_dbg_regs,

From be86c553545eb5cb83434f9a67d766d0618c9705 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Tue, 1 Oct 2024 14:27:22 -0700
Subject: [PATCH 0182/1530] pinctrl: aw9523: add missing mutex_destroy

Otherwise the mutex remains after a failed kzalloc.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Link: https://lore.kernel.org/20241001212724.309320-1-rosenp@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-aw9523.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-aw9523.c b/drivers/pinctrl/pinctrl-aw9523.c
index e312a2c0e6d2f..f6df8d32225b4 100644
--- a/drivers/pinctrl/pinctrl-aw9523.c
+++ b/drivers/pinctrl/pinctrl-aw9523.c
@@ -980,8 +980,10 @@ static int aw9523_probe(struct i2c_client *client)
 	lockdep_set_subclass(&awi->i2c_lock, i2c_adapter_depth(client->adapter));
 
 	pdesc = devm_kzalloc(dev, sizeof(*pdesc), GFP_KERNEL);
-	if (!pdesc)
-		return -ENOMEM;
+	if (!pdesc) {
+		ret = -ENOMEM;
+		goto err_disable_vregs;
+	}
 
 	ret = aw9523_hw_init(awi);
 	if (ret)

From 7b2a96de50d04a45a021a3ba7531692e593ef64b Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Thu, 3 Oct 2024 14:47:46 -0700
Subject: [PATCH 0183/1530] pinctrl: aw9523: use devm_mutex_init

Simplifies probe by removing all gotos and removing mutex_destroy from
_remove.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Link: https://lore.kernel.org/20241003214746.146207-1-rosenp@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-aw9523.c | 36 ++++++++++++--------------------
 1 file changed, 13 insertions(+), 23 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-aw9523.c b/drivers/pinctrl/pinctrl-aw9523.c
index f6df8d32225b4..5cb24c1dcb0d0 100644
--- a/drivers/pinctrl/pinctrl-aw9523.c
+++ b/drivers/pinctrl/pinctrl-aw9523.c
@@ -976,18 +976,19 @@ static int aw9523_probe(struct i2c_client *client)
 	if (awi->vio_vreg && awi->vio_vreg != -ENODEV)
 		return awi->vio_vreg;
 
-	mutex_init(&awi->i2c_lock);
+	ret = devm_mutex_init(dev, &awi->i2c_lock);
+	if (ret)
+		return ret;
+
 	lockdep_set_subclass(&awi->i2c_lock, i2c_adapter_depth(client->adapter));
 
 	pdesc = devm_kzalloc(dev, sizeof(*pdesc), GFP_KERNEL);
-	if (!pdesc) {
-		ret = -ENOMEM;
-		goto err_disable_vregs;
-	}
+	if (!pdesc)
+		return -ENOMEM;
 
 	ret = aw9523_hw_init(awi);
 	if (ret)
-		goto err_disable_vregs;
+		return ret;
 
 	pdesc->name = dev_name(dev);
 	pdesc->owner = THIS_MODULE;
@@ -999,29 +1000,20 @@ static int aw9523_probe(struct i2c_client *client)
 
 	ret = aw9523_init_gpiochip(awi, pdesc->npins);
 	if (ret)
-		goto err_disable_vregs;
+		return ret;
 
 	if (client->irq) {
 		ret = aw9523_init_irq(awi, client->irq);
 		if (ret)
-			goto err_disable_vregs;
+			return ret;
 	}
 
 	awi->pctl = devm_pinctrl_register(dev, pdesc, awi);
-	if (IS_ERR(awi->pctl)) {
-		ret = dev_err_probe(dev, PTR_ERR(awi->pctl), "Cannot register pinctrl");
-		goto err_disable_vregs;
-	}
-
-	ret = devm_gpiochip_add_data(dev, &awi->gpio, awi);
-	if (ret)
-		goto err_disable_vregs;
+	if (IS_ERR(awi->pctl))
+		return dev_err_probe(dev, PTR_ERR(awi->pctl),
+				     "Cannot register pinctrl");
 
-	return ret;
-
-err_disable_vregs:
-	mutex_destroy(&awi->i2c_lock);
-	return ret;
+	return devm_gpiochip_add_data(dev, &awi->gpio, awi);
 }
 
 static void aw9523_remove(struct i2c_client *client)
@@ -1039,8 +1031,6 @@ static void aw9523_remove(struct i2c_client *client)
 		aw9523_hw_init(awi);
 		mutex_unlock(&awi->i2c_lock);
 	}
-
-	mutex_destroy(&awi->i2c_lock);
 }
 
 static const struct i2c_device_id aw9523_i2c_id_table[] = {

From f2256e344d5d97f33d4074d562823622db6d3d7c Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 3 Oct 2024 16:16:47 +0200
Subject: [PATCH 0184/1530] pinctrl: imx27: Fix too generic defines

The "PC" define is colliding with the (apparently broadcased)
define for "program counter" on Loongarch, so let's rename all
these 2-letter defines so they don't collide with stuff.

Fixes: a55222b7a132 ("pinctrl: freescale: enable use with COMPILE_TEST")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202410030214.dPrgmUqd-lkp@intel.com/
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/20241003-fix-imx27-pc-v1-1-0e78d1fc6175@linaro.org
---
 drivers/pinctrl/freescale/pinctrl-imx27.c | 350 +++++++++++-----------
 1 file changed, 175 insertions(+), 175 deletions(-)

diff --git a/drivers/pinctrl/freescale/pinctrl-imx27.c b/drivers/pinctrl/freescale/pinctrl-imx27.c
index 1738df4612351..afeb399572036 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx27.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx27.c
@@ -16,188 +16,188 @@
 #include "pinctrl-imx1.h"
 
 #define PAD_ID(port, pin) (port*32 + pin)
-#define PA 0
-#define PB 1
-#define PC 2
-#define PD 3
-#define PE 4
-#define PF 5
+#define MX27_PA 0
+#define MX27_PB 1
+#define MX27_PC 2
+#define MX27_PD 3
+#define MX27_PE 4
+#define MX27_PF 5
 
 enum imx27_pads {
-	MX27_PAD_USBH2_CLK = PAD_ID(PA, 0),
-	MX27_PAD_USBH2_DIR = PAD_ID(PA, 1),
-	MX27_PAD_USBH2_DATA7 = PAD_ID(PA, 2),
-	MX27_PAD_USBH2_NXT = PAD_ID(PA, 3),
-	MX27_PAD_USBH2_STP = PAD_ID(PA, 4),
-	MX27_PAD_LSCLK = PAD_ID(PA, 5),
-	MX27_PAD_LD0 = PAD_ID(PA, 6),
-	MX27_PAD_LD1 = PAD_ID(PA, 7),
-	MX27_PAD_LD2 = PAD_ID(PA, 8),
-	MX27_PAD_LD3 = PAD_ID(PA, 9),
-	MX27_PAD_LD4 = PAD_ID(PA, 10),
-	MX27_PAD_LD5 = PAD_ID(PA, 11),
-	MX27_PAD_LD6 = PAD_ID(PA, 12),
-	MX27_PAD_LD7 = PAD_ID(PA, 13),
-	MX27_PAD_LD8 = PAD_ID(PA, 14),
-	MX27_PAD_LD9 = PAD_ID(PA, 15),
-	MX27_PAD_LD10 = PAD_ID(PA, 16),
-	MX27_PAD_LD11 = PAD_ID(PA, 17),
-	MX27_PAD_LD12 = PAD_ID(PA, 18),
-	MX27_PAD_LD13 = PAD_ID(PA, 19),
-	MX27_PAD_LD14 = PAD_ID(PA, 20),
-	MX27_PAD_LD15 = PAD_ID(PA, 21),
-	MX27_PAD_LD16 = PAD_ID(PA, 22),
-	MX27_PAD_LD17 = PAD_ID(PA, 23),
-	MX27_PAD_REV = PAD_ID(PA, 24),
-	MX27_PAD_CLS = PAD_ID(PA, 25),
-	MX27_PAD_PS = PAD_ID(PA, 26),
-	MX27_PAD_SPL_SPR = PAD_ID(PA, 27),
-	MX27_PAD_HSYNC = PAD_ID(PA, 28),
-	MX27_PAD_VSYNC = PAD_ID(PA, 29),
-	MX27_PAD_CONTRAST = PAD_ID(PA, 30),
-	MX27_PAD_OE_ACD = PAD_ID(PA, 31),
+	MX27_PAD_USBH2_CLK = PAD_ID(MX27_PA, 0),
+	MX27_PAD_USBH2_DIR = PAD_ID(MX27_PA, 1),
+	MX27_PAD_USBH2_DATA7 = PAD_ID(MX27_PA, 2),
+	MX27_PAD_USBH2_NXT = PAD_ID(MX27_PA, 3),
+	MX27_PAD_USBH2_STP = PAD_ID(MX27_PA, 4),
+	MX27_PAD_LSCLK = PAD_ID(MX27_PA, 5),
+	MX27_PAD_LD0 = PAD_ID(MX27_PA, 6),
+	MX27_PAD_LD1 = PAD_ID(MX27_PA, 7),
+	MX27_PAD_LD2 = PAD_ID(MX27_PA, 8),
+	MX27_PAD_LD3 = PAD_ID(MX27_PA, 9),
+	MX27_PAD_LD4 = PAD_ID(MX27_PA, 10),
+	MX27_PAD_LD5 = PAD_ID(MX27_PA, 11),
+	MX27_PAD_LD6 = PAD_ID(MX27_PA, 12),
+	MX27_PAD_LD7 = PAD_ID(MX27_PA, 13),
+	MX27_PAD_LD8 = PAD_ID(MX27_PA, 14),
+	MX27_PAD_LD9 = PAD_ID(MX27_PA, 15),
+	MX27_PAD_LD10 = PAD_ID(MX27_PA, 16),
+	MX27_PAD_LD11 = PAD_ID(MX27_PA, 17),
+	MX27_PAD_LD12 = PAD_ID(MX27_PA, 18),
+	MX27_PAD_LD13 = PAD_ID(MX27_PA, 19),
+	MX27_PAD_LD14 = PAD_ID(MX27_PA, 20),
+	MX27_PAD_LD15 = PAD_ID(MX27_PA, 21),
+	MX27_PAD_LD16 = PAD_ID(MX27_PA, 22),
+	MX27_PAD_LD17 = PAD_ID(MX27_PA, 23),
+	MX27_PAD_REV = PAD_ID(MX27_PA, 24),
+	MX27_PAD_CLS = PAD_ID(MX27_PA, 25),
+	MX27_PAD_PS = PAD_ID(MX27_PA, 26),
+	MX27_PAD_SPL_SPR = PAD_ID(MX27_PA, 27),
+	MX27_PAD_HSYNC = PAD_ID(MX27_PA, 28),
+	MX27_PAD_VSYNC = PAD_ID(MX27_PA, 29),
+	MX27_PAD_CONTRAST = PAD_ID(MX27_PA, 30),
+	MX27_PAD_OE_ACD = PAD_ID(MX27_PA, 31),
 
-	MX27_PAD_SD2_D0 = PAD_ID(PB, 4),
-	MX27_PAD_SD2_D1 = PAD_ID(PB, 5),
-	MX27_PAD_SD2_D2 = PAD_ID(PB, 6),
-	MX27_PAD_SD2_D3 = PAD_ID(PB, 7),
-	MX27_PAD_SD2_CMD = PAD_ID(PB, 8),
-	MX27_PAD_SD2_CLK = PAD_ID(PB, 9),
-	MX27_PAD_CSI_D0 = PAD_ID(PB, 10),
-	MX27_PAD_CSI_D1 = PAD_ID(PB, 11),
-	MX27_PAD_CSI_D2 = PAD_ID(PB, 12),
-	MX27_PAD_CSI_D3 = PAD_ID(PB, 13),
-	MX27_PAD_CSI_D4 = PAD_ID(PB, 14),
-	MX27_PAD_CSI_MCLK = PAD_ID(PB, 15),
-	MX27_PAD_CSI_PIXCLK = PAD_ID(PB, 16),
-	MX27_PAD_CSI_D5 = PAD_ID(PB, 17),
-	MX27_PAD_CSI_D6 = PAD_ID(PB, 18),
-	MX27_PAD_CSI_D7 = PAD_ID(PB, 19),
-	MX27_PAD_CSI_VSYNC = PAD_ID(PB, 20),
-	MX27_PAD_CSI_HSYNC = PAD_ID(PB, 21),
-	MX27_PAD_USBH1_SUSP = PAD_ID(PB, 22),
-	MX27_PAD_USB_PWR = PAD_ID(PB, 23),
-	MX27_PAD_USB_OC_B = PAD_ID(PB, 24),
-	MX27_PAD_USBH1_RCV = PAD_ID(PB, 25),
-	MX27_PAD_USBH1_FS = PAD_ID(PB, 26),
-	MX27_PAD_USBH1_OE_B = PAD_ID(PB, 27),
-	MX27_PAD_USBH1_TXDM = PAD_ID(PB, 28),
-	MX27_PAD_USBH1_TXDP = PAD_ID(PB, 29),
-	MX27_PAD_USBH1_RXDM = PAD_ID(PB, 30),
-	MX27_PAD_USBH1_RXDP = PAD_ID(PB, 31),
+	MX27_PAD_SD2_D0 = PAD_ID(MX27_PB, 4),
+	MX27_PAD_SD2_D1 = PAD_ID(MX27_PB, 5),
+	MX27_PAD_SD2_D2 = PAD_ID(MX27_PB, 6),
+	MX27_PAD_SD2_D3 = PAD_ID(MX27_PB, 7),
+	MX27_PAD_SD2_CMD = PAD_ID(MX27_PB, 8),
+	MX27_PAD_SD2_CLK = PAD_ID(MX27_PB, 9),
+	MX27_PAD_CSI_D0 = PAD_ID(MX27_PB, 10),
+	MX27_PAD_CSI_D1 = PAD_ID(MX27_PB, 11),
+	MX27_PAD_CSI_D2 = PAD_ID(MX27_PB, 12),
+	MX27_PAD_CSI_D3 = PAD_ID(MX27_PB, 13),
+	MX27_PAD_CSI_D4 = PAD_ID(MX27_PB, 14),
+	MX27_PAD_CSI_MCLK = PAD_ID(MX27_PB, 15),
+	MX27_PAD_CSI_PIXCLK = PAD_ID(MX27_PB, 16),
+	MX27_PAD_CSI_D5 = PAD_ID(MX27_PB, 17),
+	MX27_PAD_CSI_D6 = PAD_ID(MX27_PB, 18),
+	MX27_PAD_CSI_D7 = PAD_ID(MX27_PB, 19),
+	MX27_PAD_CSI_VSYNC = PAD_ID(MX27_PB, 20),
+	MX27_PAD_CSI_HSYNC = PAD_ID(MX27_PB, 21),
+	MX27_PAD_USBH1_SUSP = PAD_ID(MX27_PB, 22),
+	MX27_PAD_USB_PWR = PAD_ID(MX27_PB, 23),
+	MX27_PAD_USB_OC_B = PAD_ID(MX27_PB, 24),
+	MX27_PAD_USBH1_RCV = PAD_ID(MX27_PB, 25),
+	MX27_PAD_USBH1_FS = PAD_ID(MX27_PB, 26),
+	MX27_PAD_USBH1_OE_B = PAD_ID(MX27_PB, 27),
+	MX27_PAD_USBH1_TXDM = PAD_ID(MX27_PB, 28),
+	MX27_PAD_USBH1_TXDP = PAD_ID(MX27_PB, 29),
+	MX27_PAD_USBH1_RXDM = PAD_ID(MX27_PB, 30),
+	MX27_PAD_USBH1_RXDP = PAD_ID(MX27_PB, 31),
 
-	MX27_PAD_I2C2_SDA = PAD_ID(PC, 5),
-	MX27_PAD_I2C2_SCL = PAD_ID(PC, 6),
-	MX27_PAD_USBOTG_DATA5 = PAD_ID(PC, 7),
-	MX27_PAD_USBOTG_DATA6 = PAD_ID(PC, 8),
-	MX27_PAD_USBOTG_DATA0 = PAD_ID(PC, 9),
-	MX27_PAD_USBOTG_DATA2 = PAD_ID(PC, 10),
-	MX27_PAD_USBOTG_DATA1 = PAD_ID(PC, 11),
-	MX27_PAD_USBOTG_DATA4 = PAD_ID(PC, 12),
-	MX27_PAD_USBOTG_DATA3 = PAD_ID(PC, 13),
-	MX27_PAD_TOUT = PAD_ID(PC, 14),
-	MX27_PAD_TIN = PAD_ID(PC, 15),
-	MX27_PAD_SSI4_FS = PAD_ID(PC, 16),
-	MX27_PAD_SSI4_RXDAT = PAD_ID(PC, 17),
-	MX27_PAD_SSI4_TXDAT = PAD_ID(PC, 18),
-	MX27_PAD_SSI4_CLK = PAD_ID(PC, 19),
-	MX27_PAD_SSI1_FS = PAD_ID(PC, 20),
-	MX27_PAD_SSI1_RXDAT = PAD_ID(PC, 21),
-	MX27_PAD_SSI1_TXDAT = PAD_ID(PC, 22),
-	MX27_PAD_SSI1_CLK = PAD_ID(PC, 23),
-	MX27_PAD_SSI2_FS = PAD_ID(PC, 24),
-	MX27_PAD_SSI2_RXDAT = PAD_ID(PC, 25),
-	MX27_PAD_SSI2_TXDAT = PAD_ID(PC, 26),
-	MX27_PAD_SSI2_CLK = PAD_ID(PC, 27),
-	MX27_PAD_SSI3_FS = PAD_ID(PC, 28),
-	MX27_PAD_SSI3_RXDAT = PAD_ID(PC, 29),
-	MX27_PAD_SSI3_TXDAT = PAD_ID(PC, 30),
-	MX27_PAD_SSI3_CLK = PAD_ID(PC, 31),
+	MX27_PAD_I2C2_SDA = PAD_ID(MX27_PC, 5),
+	MX27_PAD_I2C2_SCL = PAD_ID(MX27_PC, 6),
+	MX27_PAD_USBOTG_DATA5 = PAD_ID(MX27_PC, 7),
+	MX27_PAD_USBOTG_DATA6 = PAD_ID(MX27_PC, 8),
+	MX27_PAD_USBOTG_DATA0 = PAD_ID(MX27_PC, 9),
+	MX27_PAD_USBOTG_DATA2 = PAD_ID(MX27_PC, 10),
+	MX27_PAD_USBOTG_DATA1 = PAD_ID(MX27_PC, 11),
+	MX27_PAD_USBOTG_DATA4 = PAD_ID(MX27_PC, 12),
+	MX27_PAD_USBOTG_DATA3 = PAD_ID(MX27_PC, 13),
+	MX27_PAD_TOUT = PAD_ID(MX27_PC, 14),
+	MX27_PAD_TIN = PAD_ID(MX27_PC, 15),
+	MX27_PAD_SSI4_FS = PAD_ID(MX27_PC, 16),
+	MX27_PAD_SSI4_RXDAT = PAD_ID(MX27_PC, 17),
+	MX27_PAD_SSI4_TXDAT = PAD_ID(MX27_PC, 18),
+	MX27_PAD_SSI4_CLK = PAD_ID(MX27_PC, 19),
+	MX27_PAD_SSI1_FS = PAD_ID(MX27_PC, 20),
+	MX27_PAD_SSI1_RXDAT = PAD_ID(MX27_PC, 21),
+	MX27_PAD_SSI1_TXDAT = PAD_ID(MX27_PC, 22),
+	MX27_PAD_SSI1_CLK = PAD_ID(MX27_PC, 23),
+	MX27_PAD_SSI2_FS = PAD_ID(MX27_PC, 24),
+	MX27_PAD_SSI2_RXDAT = PAD_ID(MX27_PC, 25),
+	MX27_PAD_SSI2_TXDAT = PAD_ID(MX27_PC, 26),
+	MX27_PAD_SSI2_CLK = PAD_ID(MX27_PC, 27),
+	MX27_PAD_SSI3_FS = PAD_ID(MX27_PC, 28),
+	MX27_PAD_SSI3_RXDAT = PAD_ID(MX27_PC, 29),
+	MX27_PAD_SSI3_TXDAT = PAD_ID(MX27_PC, 30),
+	MX27_PAD_SSI3_CLK = PAD_ID(MX27_PC, 31),
 
-	MX27_PAD_SD3_CMD = PAD_ID(PD, 0),
-	MX27_PAD_SD3_CLK = PAD_ID(PD, 1),
-	MX27_PAD_ATA_DATA0 = PAD_ID(PD, 2),
-	MX27_PAD_ATA_DATA1 = PAD_ID(PD, 3),
-	MX27_PAD_ATA_DATA2 = PAD_ID(PD, 4),
-	MX27_PAD_ATA_DATA3 = PAD_ID(PD, 5),
-	MX27_PAD_ATA_DATA4 = PAD_ID(PD, 6),
-	MX27_PAD_ATA_DATA5 = PAD_ID(PD, 7),
-	MX27_PAD_ATA_DATA6 = PAD_ID(PD, 8),
-	MX27_PAD_ATA_DATA7 = PAD_ID(PD, 9),
-	MX27_PAD_ATA_DATA8 = PAD_ID(PD, 10),
-	MX27_PAD_ATA_DATA9 = PAD_ID(PD, 11),
-	MX27_PAD_ATA_DATA10 = PAD_ID(PD, 12),
-	MX27_PAD_ATA_DATA11 = PAD_ID(PD, 13),
-	MX27_PAD_ATA_DATA12 = PAD_ID(PD, 14),
-	MX27_PAD_ATA_DATA13 = PAD_ID(PD, 15),
-	MX27_PAD_ATA_DATA14 = PAD_ID(PD, 16),
-	MX27_PAD_I2C_DATA = PAD_ID(PD, 17),
-	MX27_PAD_I2C_CLK = PAD_ID(PD, 18),
-	MX27_PAD_CSPI2_SS2 = PAD_ID(PD, 19),
-	MX27_PAD_CSPI2_SS1 = PAD_ID(PD, 20),
-	MX27_PAD_CSPI2_SS0 = PAD_ID(PD, 21),
-	MX27_PAD_CSPI2_SCLK = PAD_ID(PD, 22),
-	MX27_PAD_CSPI2_MISO = PAD_ID(PD, 23),
-	MX27_PAD_CSPI2_MOSI = PAD_ID(PD, 24),
-	MX27_PAD_CSPI1_RDY = PAD_ID(PD, 25),
-	MX27_PAD_CSPI1_SS2 = PAD_ID(PD, 26),
-	MX27_PAD_CSPI1_SS1 = PAD_ID(PD, 27),
-	MX27_PAD_CSPI1_SS0 = PAD_ID(PD, 28),
-	MX27_PAD_CSPI1_SCLK = PAD_ID(PD, 29),
-	MX27_PAD_CSPI1_MISO = PAD_ID(PD, 30),
-	MX27_PAD_CSPI1_MOSI = PAD_ID(PD, 31),
+	MX27_PAD_SD3_CMD = PAD_ID(MX27_PD, 0),
+	MX27_PAD_SD3_CLK = PAD_ID(MX27_PD, 1),
+	MX27_PAD_ATA_DATA0 = PAD_ID(MX27_PD, 2),
+	MX27_PAD_ATA_DATA1 = PAD_ID(MX27_PD, 3),
+	MX27_PAD_ATA_DATA2 = PAD_ID(MX27_PD, 4),
+	MX27_PAD_ATA_DATA3 = PAD_ID(MX27_PD, 5),
+	MX27_PAD_ATA_DATA4 = PAD_ID(MX27_PD, 6),
+	MX27_PAD_ATA_DATA5 = PAD_ID(MX27_PD, 7),
+	MX27_PAD_ATA_DATA6 = PAD_ID(MX27_PD, 8),
+	MX27_PAD_ATA_DATA7 = PAD_ID(MX27_PD, 9),
+	MX27_PAD_ATA_DATA8 = PAD_ID(MX27_PD, 10),
+	MX27_PAD_ATA_DATA9 = PAD_ID(MX27_PD, 11),
+	MX27_PAD_ATA_DATA10 = PAD_ID(MX27_PD, 12),
+	MX27_PAD_ATA_DATA11 = PAD_ID(MX27_PD, 13),
+	MX27_PAD_ATA_DATA12 = PAD_ID(MX27_PD, 14),
+	MX27_PAD_ATA_DATA13 = PAD_ID(MX27_PD, 15),
+	MX27_PAD_ATA_DATA14 = PAD_ID(MX27_PD, 16),
+	MX27_PAD_I2C_DATA = PAD_ID(MX27_PD, 17),
+	MX27_PAD_I2C_CLK = PAD_ID(MX27_PD, 18),
+	MX27_PAD_CSPI2_SS2 = PAD_ID(MX27_PD, 19),
+	MX27_PAD_CSPI2_SS1 = PAD_ID(MX27_PD, 20),
+	MX27_PAD_CSPI2_SS0 = PAD_ID(MX27_PD, 21),
+	MX27_PAD_CSPI2_SCLK = PAD_ID(MX27_PD, 22),
+	MX27_PAD_CSPI2_MISO = PAD_ID(MX27_PD, 23),
+	MX27_PAD_CSPI2_MOSI = PAD_ID(MX27_PD, 24),
+	MX27_PAD_CSPI1_RDY = PAD_ID(MX27_PD, 25),
+	MX27_PAD_CSPI1_SS2 = PAD_ID(MX27_PD, 26),
+	MX27_PAD_CSPI1_SS1 = PAD_ID(MX27_PD, 27),
+	MX27_PAD_CSPI1_SS0 = PAD_ID(MX27_PD, 28),
+	MX27_PAD_CSPI1_SCLK = PAD_ID(MX27_PD, 29),
+	MX27_PAD_CSPI1_MISO = PAD_ID(MX27_PD, 30),
+	MX27_PAD_CSPI1_MOSI = PAD_ID(MX27_PD, 31),
 
-	MX27_PAD_USBOTG_NXT = PAD_ID(PE, 0),
-	MX27_PAD_USBOTG_STP = PAD_ID(PE, 1),
-	MX27_PAD_USBOTG_DIR = PAD_ID(PE, 2),
-	MX27_PAD_UART2_CTS = PAD_ID(PE, 3),
-	MX27_PAD_UART2_RTS = PAD_ID(PE, 4),
-	MX27_PAD_PWMO = PAD_ID(PE, 5),
-	MX27_PAD_UART2_TXD = PAD_ID(PE, 6),
-	MX27_PAD_UART2_RXD = PAD_ID(PE, 7),
-	MX27_PAD_UART3_TXD = PAD_ID(PE, 8),
-	MX27_PAD_UART3_RXD = PAD_ID(PE, 9),
-	MX27_PAD_UART3_CTS = PAD_ID(PE, 10),
-	MX27_PAD_UART3_RTS = PAD_ID(PE, 11),
-	MX27_PAD_UART1_TXD = PAD_ID(PE, 12),
-	MX27_PAD_UART1_RXD = PAD_ID(PE, 13),
-	MX27_PAD_UART1_CTS = PAD_ID(PE, 14),
-	MX27_PAD_UART1_RTS = PAD_ID(PE, 15),
-	MX27_PAD_RTCK = PAD_ID(PE, 16),
-	MX27_PAD_RESET_OUT_B = PAD_ID(PE, 17),
-	MX27_PAD_SD1_D0 = PAD_ID(PE, 18),
-	MX27_PAD_SD1_D1 = PAD_ID(PE, 19),
-	MX27_PAD_SD1_D2 = PAD_ID(PE, 20),
-	MX27_PAD_SD1_D3 = PAD_ID(PE, 21),
-	MX27_PAD_SD1_CMD = PAD_ID(PE, 22),
-	MX27_PAD_SD1_CLK = PAD_ID(PE, 23),
-	MX27_PAD_USBOTG_CLK = PAD_ID(PE, 24),
-	MX27_PAD_USBOTG_DATA7 = PAD_ID(PE, 25),
+	MX27_PAD_USBOTG_NXT = PAD_ID(MX27_PE, 0),
+	MX27_PAD_USBOTG_STP = PAD_ID(MX27_PE, 1),
+	MX27_PAD_USBOTG_DIR = PAD_ID(MX27_PE, 2),
+	MX27_PAD_UART2_CTS = PAD_ID(MX27_PE, 3),
+	MX27_PAD_UART2_RTS = PAD_ID(MX27_PE, 4),
+	MX27_PAD_PWMO = PAD_ID(MX27_PE, 5),
+	MX27_PAD_UART2_TXD = PAD_ID(MX27_PE, 6),
+	MX27_PAD_UART2_RXD = PAD_ID(MX27_PE, 7),
+	MX27_PAD_UART3_TXD = PAD_ID(MX27_PE, 8),
+	MX27_PAD_UART3_RXD = PAD_ID(MX27_PE, 9),
+	MX27_PAD_UART3_CTS = PAD_ID(MX27_PE, 10),
+	MX27_PAD_UART3_RTS = PAD_ID(MX27_PE, 11),
+	MX27_PAD_UART1_TXD = PAD_ID(MX27_PE, 12),
+	MX27_PAD_UART1_RXD = PAD_ID(MX27_PE, 13),
+	MX27_PAD_UART1_CTS = PAD_ID(MX27_PE, 14),
+	MX27_PAD_UART1_RTS = PAD_ID(MX27_PE, 15),
+	MX27_PAD_RTCK = PAD_ID(MX27_PE, 16),
+	MX27_PAD_RESET_OUT_B = PAD_ID(MX27_PE, 17),
+	MX27_PAD_SD1_D0 = PAD_ID(MX27_PE, 18),
+	MX27_PAD_SD1_D1 = PAD_ID(MX27_PE, 19),
+	MX27_PAD_SD1_D2 = PAD_ID(MX27_PE, 20),
+	MX27_PAD_SD1_D3 = PAD_ID(MX27_PE, 21),
+	MX27_PAD_SD1_CMD = PAD_ID(MX27_PE, 22),
+	MX27_PAD_SD1_CLK = PAD_ID(MX27_PE, 23),
+	MX27_PAD_USBOTG_CLK = PAD_ID(MX27_PE, 24),
+	MX27_PAD_USBOTG_DATA7 = PAD_ID(MX27_PE, 25),
 
-	MX27_PAD_NFRB = PAD_ID(PF, 0),
-	MX27_PAD_NFCLE = PAD_ID(PF, 1),
-	MX27_PAD_NFWP_B = PAD_ID(PF, 2),
-	MX27_PAD_NFCE_B = PAD_ID(PF, 3),
-	MX27_PAD_NFALE = PAD_ID(PF, 4),
-	MX27_PAD_NFRE_B = PAD_ID(PF, 5),
-	MX27_PAD_NFWE_B = PAD_ID(PF, 6),
-	MX27_PAD_PC_POE = PAD_ID(PF, 7),
-	MX27_PAD_PC_RW_B = PAD_ID(PF, 8),
-	MX27_PAD_IOIS16 = PAD_ID(PF, 9),
-	MX27_PAD_PC_RST = PAD_ID(PF, 10),
-	MX27_PAD_PC_BVD2 = PAD_ID(PF, 11),
-	MX27_PAD_PC_BVD1 = PAD_ID(PF, 12),
-	MX27_PAD_PC_VS2 = PAD_ID(PF, 13),
-	MX27_PAD_PC_VS1 = PAD_ID(PF, 14),
-	MX27_PAD_CLKO = PAD_ID(PF, 15),
-	MX27_PAD_PC_PWRON = PAD_ID(PF, 16),
-	MX27_PAD_PC_READY = PAD_ID(PF, 17),
-	MX27_PAD_PC_WAIT_B = PAD_ID(PF, 18),
-	MX27_PAD_PC_CD2_B = PAD_ID(PF, 19),
-	MX27_PAD_PC_CD1_B = PAD_ID(PF, 20),
-	MX27_PAD_CS4_B = PAD_ID(PF, 21),
-	MX27_PAD_CS5_B = PAD_ID(PF, 22),
-	MX27_PAD_ATA_DATA15 = PAD_ID(PF, 23),
+	MX27_PAD_NFRB = PAD_ID(MX27_PF, 0),
+	MX27_PAD_NFCLE = PAD_ID(MX27_PF, 1),
+	MX27_PAD_NFWP_B = PAD_ID(MX27_PF, 2),
+	MX27_PAD_NFCE_B = PAD_ID(MX27_PF, 3),
+	MX27_PAD_NFALE = PAD_ID(MX27_PF, 4),
+	MX27_PAD_NFRE_B = PAD_ID(MX27_PF, 5),
+	MX27_PAD_NFWE_B = PAD_ID(MX27_PF, 6),
+	MX27_PAD_PC_POE = PAD_ID(MX27_PF, 7),
+	MX27_PAD_PC_RW_B = PAD_ID(MX27_PF, 8),
+	MX27_PAD_IOIS16 = PAD_ID(MX27_PF, 9),
+	MX27_PAD_PC_RST = PAD_ID(MX27_PF, 10),
+	MX27_PAD_PC_BVD2 = PAD_ID(MX27_PF, 11),
+	MX27_PAD_PC_BVD1 = PAD_ID(MX27_PF, 12),
+	MX27_PAD_PC_VS2 = PAD_ID(MX27_PF, 13),
+	MX27_PAD_PC_VS1 = PAD_ID(MX27_PF, 14),
+	MX27_PAD_CLKO = PAD_ID(MX27_PF, 15),
+	MX27_PAD_PC_PWRON = PAD_ID(MX27_PF, 16),
+	MX27_PAD_PC_READY = PAD_ID(MX27_PF, 17),
+	MX27_PAD_PC_WAIT_B = PAD_ID(MX27_PF, 18),
+	MX27_PAD_PC_CD2_B = PAD_ID(MX27_PF, 19),
+	MX27_PAD_PC_CD1_B = PAD_ID(MX27_PF, 20),
+	MX27_PAD_CS4_B = PAD_ID(MX27_PF, 21),
+	MX27_PAD_CS5_B = PAD_ID(MX27_PF, 22),
+	MX27_PAD_ATA_DATA15 = PAD_ID(MX27_PF, 23),
 };
 
 /* Pad names for the pinmux subsystem */

From 2694868880705e8f6bb61b24b1b25adc42a4a217 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 3 Oct 2024 16:44:43 +0200
Subject: [PATCH 0185/1530] pinctrl: k230: Drop unused code

The build robot complains about unused code. Let's drop it,
this can be restored with simple git revert when needed.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202410021136.ie3cFM2w-lkp@intel.com/
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/20241003-k320-unused-v1-1-72e65bc2f27b@linaro.org
---
 drivers/pinctrl/pinctrl-k230.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-k230.c b/drivers/pinctrl/pinctrl-k230.c
index 4266516886fce..a9b4627b46b01 100644
--- a/drivers/pinctrl/pinctrl-k230.c
+++ b/drivers/pinctrl/pinctrl-k230.c
@@ -156,7 +156,7 @@ static void k230_pinctrl_pin_dbg_show(struct pinctrl_dev *pctldev,
 				      struct seq_file *s, unsigned int offset)
 {
 	struct k230_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
-	u32 val, mode, bias, drive, input, output, slew, schmitt, power;
+	u32 val, bias, drive, input, slew, schmitt, power;
 	struct k230_pin_group *grp = k230_pins[offset].drv_data;
 	static const char * const biasing[] = {
 			"pull none", "pull down", "pull up", "" };
@@ -167,11 +167,9 @@ static void k230_pinctrl_pin_dbg_show(struct pinctrl_dev *pctldev,
 
 	regmap_read(info->regmap_base, offset * 4, &val);
 
-	mode	= (val & K230_PC_SEL) >> K230_SHIFT_SEL;
 	drive	= (val & K230_PC_DS) >> K230_SHIFT_DS;
 	bias	= (val & K230_PC_BIAS) >> K230_SHIFT_BIAS;
 	input	= (val & K230_PC_IE) >> K230_SHIFT_IE;
-	output	= (val & K230_PC_OE) >> K230_SHIFT_OE;
 	slew	= (val & K230_PC_SL) >> K230_SHIFT_SL;
 	schmitt	= (val & K230_PC_ST) >> K230_SHIFT_ST;
 	power	= (val & K230_PC_MSC) >> K230_SHIFT_MSC;

From 0e45a09a1da0872786885c505467aab8fb29b5b4 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:06 -0700
Subject: [PATCH 0186/1530] Input: serio - define serio_pause_rx guard to pause
 and resume serio ports

serio_pause_rx() and serio_continue_rx() are usually used together to
temporarily stop receiving interrupts/data for a given serio port.
Define "serio_pause_rx" guard for this so that the port is always
resumed once critical section is over.

Example:

	scoped_guard(serio_pause_rx, elo->serio) {
		elo->expected_packet = toupper(packet[0]);
		init_completion(&elo->cmd_done);
	}

Link: https://lore.kernel.org/r/20240905041732.2034348-2-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 include/linux/serio.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/linux/serio.h b/include/linux/serio.h
index bf2191f253509..69a47674af653 100644
--- a/include/linux/serio.h
+++ b/include/linux/serio.h
@@ -6,6 +6,7 @@
 #define _SERIO_H
 
 
+#include <linux/cleanup.h>
 #include <linux/types.h>
 #include <linux/interrupt.h>
 #include <linux/list.h>
@@ -161,4 +162,6 @@ static inline void serio_continue_rx(struct serio *serio)
 	spin_unlock_irq(&serio->lock);
 }
 
+DEFINE_GUARD(serio_pause_rx, struct serio *, serio_pause_rx(_T), serio_continue_rx(_T))
+
 #endif

From 74c0b4c0ddf751578ce04e85075afbf7d6ef4229 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:07 -0700
Subject: [PATCH 0187/1530] Input: libps2 - use guard notation when temporarily
 pausing serio ports

Using guard notation makes the code more compact and error handling
more robust by ensuring that serio ports are resumed in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-3-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/libps2.c | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/drivers/input/serio/libps2.c b/drivers/input/serio/libps2.c
index 6d78a1fe00c1b..c22ea532276eb 100644
--- a/drivers/input/serio/libps2.c
+++ b/drivers/input/serio/libps2.c
@@ -108,13 +108,11 @@ int ps2_sendbyte(struct ps2dev *ps2dev, u8 byte, unsigned int timeout)
 {
 	int retval;
 
-	serio_pause_rx(ps2dev->serio);
+	guard(serio_pause_rx)(ps2dev->serio);
 
 	retval = ps2_do_sendbyte(ps2dev, byte, timeout, 1);
 	dev_dbg(&ps2dev->serio->dev, "%02x - %x\n", byte, ps2dev->nak);
 
-	serio_continue_rx(ps2dev->serio);
-
 	return retval;
 }
 EXPORT_SYMBOL(ps2_sendbyte);
@@ -162,10 +160,10 @@ void ps2_drain(struct ps2dev *ps2dev, size_t maxbytes, unsigned int timeout)
 
 	ps2_begin_command(ps2dev);
 
-	serio_pause_rx(ps2dev->serio);
-	ps2dev->flags = PS2_FLAG_CMD;
-	ps2dev->cmdcnt = maxbytes;
-	serio_continue_rx(ps2dev->serio);
+	scoped_guard(serio_pause_rx, ps2dev->serio) {
+		ps2dev->flags = PS2_FLAG_CMD;
+		ps2dev->cmdcnt = maxbytes;
+	}
 
 	wait_event_timeout(ps2dev->wait,
 			   !(ps2dev->flags & PS2_FLAG_CMD),
@@ -224,9 +222,9 @@ static int ps2_adjust_timeout(struct ps2dev *ps2dev,
 		 * use alternative probe to detect it.
 		 */
 		if (ps2dev->cmdbuf[1] == 0xaa) {
-			serio_pause_rx(ps2dev->serio);
-			ps2dev->flags = 0;
-			serio_continue_rx(ps2dev->serio);
+			scoped_guard(serio_pause_rx, ps2dev->serio)
+				ps2dev->flags = 0;
+
 			timeout = 0;
 		}
 
@@ -235,9 +233,9 @@ static int ps2_adjust_timeout(struct ps2dev *ps2dev,
 		 * won't be 2nd byte of ID response.
 		 */
 		if (!ps2_is_keyboard_id(ps2dev->cmdbuf[1])) {
-			serio_pause_rx(ps2dev->serio);
-			ps2dev->flags = ps2dev->cmdcnt = 0;
-			serio_continue_rx(ps2dev->serio);
+			scoped_guard(serio_pause_rx, ps2dev->serio)
+				ps2dev->flags = ps2dev->cmdcnt = 0;
+
 			timeout = 0;
 		}
 		break;
@@ -283,6 +281,10 @@ int __ps2_command(struct ps2dev *ps2dev, u8 *param, unsigned int command)
 
 	memcpy(send_param, param, send);
 
+	/*
+	 * Not using guard notation because we need to break critical
+	 * section below while waiting for the response.
+	 */
 	serio_pause_rx(ps2dev->serio);
 
 	ps2dev->cmdcnt = receive;

From ce18eefb6f50ead600126eeaf6eb4a105046103a Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:08 -0700
Subject: [PATCH 0188/1530] Input: alps - use guard notation when pausing serio
 port
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Using guard notation makes the code more compact and error handling
more robust by ensuring that serio ports are resumed in all code paths
when control leaves critical section.

Acked-by: Pali Rohár <pali@kernel.org>
Link: https://lore.kernel.org/r/20240905041732.2034348-4-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/alps.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 4e37fc3f1a9e9..0728b5c08f021 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -1585,7 +1585,7 @@ static void alps_flush_packet(struct timer_list *t)
 	struct alps_data *priv = from_timer(priv, t, timer);
 	struct psmouse *psmouse = priv->psmouse;
 
-	serio_pause_rx(psmouse->ps2dev.serio);
+	guard(serio_pause_rx)(psmouse->ps2dev.serio);
 
 	if (psmouse->pktcnt == psmouse->pktsize) {
 
@@ -1605,8 +1605,6 @@ static void alps_flush_packet(struct timer_list *t)
 		}
 		psmouse->pktcnt = 0;
 	}
-
-	serio_continue_rx(psmouse->ps2dev.serio);
 }
 
 static psmouse_ret_t alps_process_byte(struct psmouse *psmouse)

From bf46a2c73f867767afa378be5f00fa99d7f5c73c Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:09 -0700
Subject: [PATCH 0189/1530] Input: byd - use guard notation when pausing serio
 port

Using guard notation makes the code more compact and error handling
more robust by ensuring that serio ports are resumed in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-5-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/byd.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/input/mouse/byd.c b/drivers/input/mouse/byd.c
index 221a553f45cd8..654b38d249f32 100644
--- a/drivers/input/mouse/byd.c
+++ b/drivers/input/mouse/byd.c
@@ -254,13 +254,12 @@ static void byd_clear_touch(struct timer_list *t)
 	struct byd_data *priv = from_timer(priv, t, timer);
 	struct psmouse *psmouse = priv->psmouse;
 
-	serio_pause_rx(psmouse->ps2dev.serio);
+	guard(serio_pause_rx)(psmouse->ps2dev.serio);
+
 	priv->touch = false;
 
 	byd_report_input(psmouse);
 
-	serio_continue_rx(psmouse->ps2dev.serio);
-
 	/*
 	 * Move cursor back to center of pad when we lose touch - this
 	 * specifically improves user experience when moving cursor with one

From 5866065f5698557a3a15116c4e9436055185c4d2 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:10 -0700
Subject: [PATCH 0190/1530] Input: synaptics - use guard notation when pausing
 serio port

Using guard notation makes the code more compact and error handling
more robust by ensuring that serio ports are resumed in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-6-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/synaptics.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 380aa1614442f..2735f86c23cc8 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -650,9 +650,8 @@ static int synaptics_pt_start(struct serio *serio)
 	struct psmouse *parent = psmouse_from_serio(serio->parent);
 	struct synaptics_data *priv = parent->private;
 
-	serio_pause_rx(parent->ps2dev.serio);
+	guard(serio_pause_rx)(parent->ps2dev.serio);
 	priv->pt_port = serio;
-	serio_continue_rx(parent->ps2dev.serio);
 
 	return 0;
 }
@@ -662,9 +661,8 @@ static void synaptics_pt_stop(struct serio *serio)
 	struct psmouse *parent = psmouse_from_serio(serio->parent);
 	struct synaptics_data *priv = parent->private;
 
-	serio_pause_rx(parent->ps2dev.serio);
+	guard(serio_pause_rx)(parent->ps2dev.serio);
 	priv->pt_port = NULL;
-	serio_continue_rx(parent->ps2dev.serio);
 }
 
 static int synaptics_is_pt_packet(u8 *buf)

From 30cb2f6350c0f0e3f683fb3430541e6d1945468a Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:11 -0700
Subject: [PATCH 0191/1530] Input: atkbd - use guard notation when pausing
 serio port

Using guard notation makes the code more compact and error handling
more robust by ensuring that serio ports are resumed in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-7-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/atkbd.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index 5855d4fc6e6a4..ec94fcfa4cdeb 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -713,9 +713,9 @@ static int atkbd_event(struct input_dev *dev,
 
 static inline void atkbd_enable(struct atkbd *atkbd)
 {
-	serio_pause_rx(atkbd->ps2dev.serio);
+	guard(serio_pause_rx)(atkbd->ps2dev.serio);
+
 	atkbd->enabled = true;
-	serio_continue_rx(atkbd->ps2dev.serio);
 }
 
 /*
@@ -725,9 +725,9 @@ static inline void atkbd_enable(struct atkbd *atkbd)
 
 static inline void atkbd_disable(struct atkbd *atkbd)
 {
-	serio_pause_rx(atkbd->ps2dev.serio);
+	guard(serio_pause_rx)(atkbd->ps2dev.serio);
+
 	atkbd->enabled = false;
-	serio_continue_rx(atkbd->ps2dev.serio);
 }
 
 static int atkbd_activate(struct atkbd *atkbd)

From bc656ececfac95a9ff9a58cbfc3042228c18c857 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:12 -0700
Subject: [PATCH 0192/1530] Input: sunkbd - use guard notation when pausing
 serio port

Using guard notation makes the code more compact and error handling
more robust by ensuring that serio ports are resumed in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-8-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/sunkbd.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/input/keyboard/sunkbd.c b/drivers/input/keyboard/sunkbd.c
index 72fb46029710d..3299e1919b370 100644
--- a/drivers/input/keyboard/sunkbd.c
+++ b/drivers/input/keyboard/sunkbd.c
@@ -241,9 +241,8 @@ static void sunkbd_reinit(struct work_struct *work)
 
 static void sunkbd_enable(struct sunkbd *sunkbd, bool enable)
 {
-	serio_pause_rx(sunkbd->serio);
-	sunkbd->enabled = enable;
-	serio_continue_rx(sunkbd->serio);
+	scoped_guard(serio_pause_rx, sunkbd->serio)
+		sunkbd->enabled = enable;
 
 	if (!enable) {
 		wake_up_interruptible(&sunkbd->wait);

From 69a2229b05046eb42258b45df1f43248de8a3472 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:13 -0700
Subject: [PATCH 0193/1530] Input: synaptics-rmi4 - use guard notation when
 pausing serio port in F03

Using guard notation makes the code more compact and error handling
more robust by ensuring that serio ports are resumed in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-9-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/rmi4/rmi_f03.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/rmi4/rmi_f03.c b/drivers/input/rmi4/rmi_f03.c
index 1e11ea30d7bdb..e1157ff0f00af 100644
--- a/drivers/input/rmi4/rmi_f03.c
+++ b/drivers/input/rmi4/rmi_f03.c
@@ -61,14 +61,14 @@ void rmi_f03_commit_buttons(struct rmi_function *fn)
 	struct f03_data *f03 = dev_get_drvdata(&fn->dev);
 	struct serio *serio = f03->serio;
 
-	serio_pause_rx(serio);
+	guard(serio_pause_rx)(serio);
+
 	if (serio->drv) {
 		serio->drv->interrupt(serio, PSMOUSE_OOB_EXTRA_BTNS,
 				      SERIO_OOB_DATA);
 		serio->drv->interrupt(serio, f03->overwrite_buttons,
 				      SERIO_OOB_DATA);
 	}
-	serio_continue_rx(serio);
 }
 
 static int rmi_f03_pt_write(struct serio *id, unsigned char val)

From c91ae81e028f9aa363a38ef46ec5a6ca11a10f10 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:14 -0700
Subject: [PATCH 0194/1530] Input: elo - use guard notation when pausing serio
 port

Using guard notation makes the code more compact and error handling
more robust by ensuring that serio ports are resumed in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-10-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/elo.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/input/touchscreen/elo.c b/drivers/input/touchscreen/elo.c
index eb883db554205..ad209e6e82a64 100644
--- a/drivers/input/touchscreen/elo.c
+++ b/drivers/input/touchscreen/elo.c
@@ -225,10 +225,10 @@ static int elo_command_10(struct elo *elo, unsigned char *packet)
 
 	mutex_lock(&elo->cmd_mutex);
 
-	serio_pause_rx(elo->serio);
-	elo->expected_packet = toupper(packet[0]);
-	init_completion(&elo->cmd_done);
-	serio_continue_rx(elo->serio);
+	scoped_guard(serio_pause_rx, elo->serio) {
+		elo->expected_packet = toupper(packet[0]);
+		init_completion(&elo->cmd_done);
+	}
 
 	if (serio_write(elo->serio, ELO10_LEAD_BYTE))
 		goto out;

From 44f920069911437dbce84084de02b5cba4ba94f7 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:15 -0700
Subject: [PATCH 0195/1530] Input: gscps2 - use guard notation when acquiring
 spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-11-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/gscps2.c | 114 +++++++++++++++++++----------------
 1 file changed, 62 insertions(+), 52 deletions(-)

diff --git a/drivers/input/serio/gscps2.c b/drivers/input/serio/gscps2.c
index d94c01eb3fc97..cf0603d1a1139 100644
--- a/drivers/input/serio/gscps2.c
+++ b/drivers/input/serio/gscps2.c
@@ -145,7 +145,6 @@ static void gscps2_flush(struct gscps2port *ps2port)
 
 static inline int gscps2_writeb_output(struct gscps2port *ps2port, u8 data)
 {
-	unsigned long flags;
 	char __iomem *addr = ps2port->addr;
 
 	if (!wait_TBE(addr)) {
@@ -156,9 +155,8 @@ static inline int gscps2_writeb_output(struct gscps2port *ps2port, u8 data)
 	while (gscps2_readb_status(addr) & GSC_STAT_RBNE)
 		/* wait */;
 
-	spin_lock_irqsave(&ps2port->lock, flags);
-	writeb(data, addr+GSC_XMTDATA);
-	spin_unlock_irqrestore(&ps2port->lock, flags);
+	scoped_guard(spinlock_irqsave, &ps2port->lock)
+		writeb(data, addr+GSC_XMTDATA);
 
 	/* this is ugly, but due to timing of the port it seems to be necessary. */
 	mdelay(6);
@@ -177,19 +175,19 @@ static inline int gscps2_writeb_output(struct gscps2port *ps2port, u8 data)
 
 static void gscps2_enable(struct gscps2port *ps2port, int enable)
 {
-	unsigned long flags;
 	u8 data;
 
 	/* now enable/disable the port */
-	spin_lock_irqsave(&ps2port->lock, flags);
-	gscps2_flush(ps2port);
-	data = gscps2_readb_control(ps2port->addr);
-	if (enable)
-		data |= GSC_CTRL_ENBL;
-	else
-		data &= ~GSC_CTRL_ENBL;
-	gscps2_writeb_control(data, ps2port->addr);
-	spin_unlock_irqrestore(&ps2port->lock, flags);
+	scoped_guard(spinlock_irqsave, &ps2port->lock) {
+		gscps2_flush(ps2port);
+		data = gscps2_readb_control(ps2port->addr);
+		if (enable)
+			data |= GSC_CTRL_ENBL;
+		else
+			data &= ~GSC_CTRL_ENBL;
+		gscps2_writeb_control(data, ps2port->addr);
+	}
+
 	wait_TBE(ps2port->addr);
 	gscps2_flush(ps2port);
 }
@@ -203,15 +201,56 @@ static void gscps2_reset(struct gscps2port *ps2port)
 	unsigned long flags;
 
 	/* reset the interface */
-	spin_lock_irqsave(&ps2port->lock, flags);
+	guard(spinlock_irqsave)(&ps2port->lock);
 	gscps2_flush(ps2port);
 	writeb(0xff, ps2port->addr + GSC_RESET);
 	gscps2_flush(ps2port);
-	spin_unlock_irqrestore(&ps2port->lock, flags);
 }
 
 static LIST_HEAD(ps2port_list);
 
+static void gscps2_read_data(struct gscps2port *ps2port)
+{
+	u8 status;
+
+	do {
+		status = gscps2_readb_status(ps2port->addr);
+		if (!(status & GSC_STAT_RBNE))
+			break;
+
+		ps2port->buffer[ps2port->append].ste = status;
+		ps2port->buffer[ps2port->append].data =
+				gscps2_readb_input(ps2port->addr);
+	} while (true);
+}
+
+static bool gscps2_report_data(struct gscps2port *ps2port)
+{
+	unsigned int rxflags;
+	u8 data, status;
+
+	while (ps2port->act != ps2port->append) {
+		/*
+		 * Did new data arrived while we read existing data ?
+		 * If yes, exit now and let the new irq handler start
+		 * over again.
+		 */
+		if (gscps2_readb_status(ps2port->addr) & GSC_STAT_CMPINTR)
+			return true;
+
+		status = ps2port->buffer[ps2port->act].str;
+		data   = ps2port->buffer[ps2port->act].data;
+
+		ps2port->act = (ps2port->act + 1) & BUFFER_SIZE;
+		rxflags = ((status & GSC_STAT_TERR) ? SERIO_TIMEOUT : 0 ) |
+			  ((status & GSC_STAT_PERR) ? SERIO_PARITY  : 0 );
+
+		serio_interrupt(ps2port->port, data, rxflags);
+	}
+
+	return false;
+}
+
 /**
  * gscps2_interrupt() - Interruption service routine
  *
@@ -229,47 +268,18 @@ static irqreturn_t gscps2_interrupt(int irq, void *dev)
 	struct gscps2port *ps2port;
 
 	list_for_each_entry(ps2port, &ps2port_list, node) {
+		guard(spinlock_irqsave)(&ps2port->lock);
 
-	  unsigned long flags;
-	  spin_lock_irqsave(&ps2port->lock, flags);
-
-	  while ( (ps2port->buffer[ps2port->append].str =
-		   gscps2_readb_status(ps2port->addr)) & GSC_STAT_RBNE ) {
-		ps2port->buffer[ps2port->append].data =
-				gscps2_readb_input(ps2port->addr);
-		ps2port->append = ((ps2port->append+1) & BUFFER_SIZE);
-	  }
-
-	  spin_unlock_irqrestore(&ps2port->lock, flags);
-
+		gscps2_read_data(ps2port);
 	} /* list_for_each_entry */
 
 	/* all data was read from the ports - now report the data to upper layer */
-
 	list_for_each_entry(ps2port, &ps2port_list, node) {
-
-	  while (ps2port->act != ps2port->append) {
-
-	    unsigned int rxflags;
-	    u8 data, status;
-
-	    /* Did new data arrived while we read existing data ?
-	       If yes, exit now and let the new irq handler start over again */
-	    if (gscps2_readb_status(ps2port->addr) & GSC_STAT_CMPINTR)
-		return IRQ_HANDLED;
-
-	    status = ps2port->buffer[ps2port->act].str;
-	    data   = ps2port->buffer[ps2port->act].data;
-
-	    ps2port->act = ((ps2port->act+1) & BUFFER_SIZE);
-	    rxflags =	((status & GSC_STAT_TERR) ? SERIO_TIMEOUT : 0 ) |
-			((status & GSC_STAT_PERR) ? SERIO_PARITY  : 0 );
-
-	    serio_interrupt(ps2port->port, data, rxflags);
-
-	  } /* while() */
-
-	} /* list_for_each_entry */
+		if (gscps2_report_data(ps2port)) {
+			/* More data ready - break early to restart interrupt */
+			break;
+		}
+	}
 
 	return IRQ_HANDLED;
 }

From 79d01971fad360256167c4665907f1fe5ebd5e41 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:16 -0700
Subject: [PATCH 0196/1530] Input: hyperv-keyboard - use guard notation when
 acquiring spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-12-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/hyperv-keyboard.c | 38 +++++++++++++--------------
 1 file changed, 18 insertions(+), 20 deletions(-)

diff --git a/drivers/input/serio/hyperv-keyboard.c b/drivers/input/serio/hyperv-keyboard.c
index 31d9dacd2fd18..0ee7505427ace 100644
--- a/drivers/input/serio/hyperv-keyboard.c
+++ b/drivers/input/serio/hyperv-keyboard.c
@@ -102,7 +102,6 @@ static void hv_kbd_on_receive(struct hv_device *hv_dev,
 {
 	struct hv_kbd_dev *kbd_dev = hv_get_drvdata(hv_dev);
 	struct synth_kbd_keystroke *ks_msg;
-	unsigned long flags;
 	u32 msg_type = __le32_to_cpu(msg->header.type);
 	u32 info;
 	u16 scan_code;
@@ -147,21 +146,22 @@ static void hv_kbd_on_receive(struct hv_device *hv_dev,
 		/*
 		 * Inject the information through the serio interrupt.
 		 */
-		spin_lock_irqsave(&kbd_dev->lock, flags);
-		if (kbd_dev->started) {
-			if (info & IS_E0)
-				serio_interrupt(kbd_dev->hv_serio,
-						XTKBD_EMUL0, 0);
-			if (info & IS_E1)
-				serio_interrupt(kbd_dev->hv_serio,
-						XTKBD_EMUL1, 0);
-			scan_code = __le16_to_cpu(ks_msg->make_code);
-			if (info & IS_BREAK)
-				scan_code |= XTKBD_RELEASE;
+		scoped_guard(spinlock_irqsave, &kbd_dev->lock) {
+			if (kbd_dev->started) {
+				if (info & IS_E0)
+					serio_interrupt(kbd_dev->hv_serio,
+							XTKBD_EMUL0, 0);
+				if (info & IS_E1)
+					serio_interrupt(kbd_dev->hv_serio,
+							XTKBD_EMUL1, 0);
+				scan_code = __le16_to_cpu(ks_msg->make_code);
+				if (info & IS_BREAK)
+					scan_code |= XTKBD_RELEASE;
 
-			serio_interrupt(kbd_dev->hv_serio, scan_code, 0);
+				serio_interrupt(kbd_dev->hv_serio,
+						scan_code, 0);
+			}
 		}
-		spin_unlock_irqrestore(&kbd_dev->lock, flags);
 
 		/*
 		 * Only trigger a wakeup on key down, otherwise
@@ -292,11 +292,10 @@ static int hv_kbd_connect_to_vsp(struct hv_device *hv_dev)
 static int hv_kbd_start(struct serio *serio)
 {
 	struct hv_kbd_dev *kbd_dev = serio->port_data;
-	unsigned long flags;
 
-	spin_lock_irqsave(&kbd_dev->lock, flags);
+	guard(spinlock_irqsave)(&kbd_dev->lock);
+
 	kbd_dev->started = true;
-	spin_unlock_irqrestore(&kbd_dev->lock, flags);
 
 	return 0;
 }
@@ -304,11 +303,10 @@ static int hv_kbd_start(struct serio *serio)
 static void hv_kbd_stop(struct serio *serio)
 {
 	struct hv_kbd_dev *kbd_dev = serio->port_data;
-	unsigned long flags;
 
-	spin_lock_irqsave(&kbd_dev->lock, flags);
+	guard(spinlock_irqsave)(&kbd_dev->lock);
+
 	kbd_dev->started = false;
-	spin_unlock_irqrestore(&kbd_dev->lock, flags);
 }
 
 static int hv_kbd_probe(struct hv_device *hv_dev,

From c374a0cdab372c350ce9e2f8cb438d6175bac9f2 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:17 -0700
Subject: [PATCH 0197/1530] Input: i8042 - tease apart interrupt handler

In preparation to using guard notation when acquiring mutexes and
spinlocks factor out handling of active multiplexing mode from
i8042_interrupt().

Link: https://lore.kernel.org/r/20240905041732.2034348-13-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/i8042.c | 139 +++++++++++++++++++++---------------
 1 file changed, 83 insertions(+), 56 deletions(-)

diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index 8ec4872b44714..674cd155ec8fa 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -178,7 +178,7 @@ static unsigned char i8042_suppress_kbd_ack;
 static struct platform_device *i8042_platform_device;
 static struct notifier_block i8042_kbd_bind_notifier_block;
 
-static irqreturn_t i8042_interrupt(int irq, void *dev_id);
+static bool i8042_handle_data(int irq);
 static bool (*i8042_platform_filter)(unsigned char data, unsigned char str,
 				     struct serio *serio);
 
@@ -434,7 +434,7 @@ static void i8042_port_close(struct serio *serio)
 	 * See if there is any data appeared while we were messing with
 	 * port state.
 	 */
-	i8042_interrupt(0, NULL);
+	i8042_handle_data(0);
 }
 
 /*
@@ -518,12 +518,68 @@ static bool i8042_filter(unsigned char data, unsigned char str,
 }
 
 /*
- * i8042_interrupt() is the most important function in this driver -
- * it handles the interrupts from the i8042, and sends incoming bytes
- * to the upper layers.
+ * i8042_handle_mux() handles case when data is coming from one of
+ * the multiplexed ports. It would be simple if not for quirks with
+ * handling errors:
+ *
+ * When MUXERR condition is signalled the data register can only contain
+ * 0xfd, 0xfe or 0xff if implementation follows the spec. Unfortunately
+ * it is not always the case. Some KBCs also report 0xfc when there is
+ * nothing connected to the port while others sometimes get confused which
+ * port the data came from and signal error leaving the data intact. They
+ * _do not_ revert to legacy mode (actually I've never seen KBC reverting
+ * to legacy mode yet, when we see one we'll add proper handling).
+ * Anyway, we process 0xfc, 0xfd, 0xfe and 0xff as timeouts, and for the
+ * rest assume that the data came from the same serio last byte
+ * was transmitted (if transmission happened not too long ago).
  */
+static int i8042_handle_mux(u8 str, u8 *data, unsigned int *dfl)
+{
+	static unsigned long last_transmit;
+	static unsigned long last_port;
+	unsigned int mux_port;
+
+	mux_port = (str >> 6) & 3;
+	*dfl = 0;
+
+	if (str & I8042_STR_MUXERR) {
+		dbg("MUX error, status is %02x, data is %02x\n",
+		    str, *data);
+
+		switch (*data) {
+		default:
+			if (time_before(jiffies, last_transmit + HZ/10)) {
+				mux_port = last_port;
+				break;
+			}
+			fallthrough;	/* report timeout */
+		case 0xfc:
+		case 0xfd:
+		case 0xfe:
+			*dfl = SERIO_TIMEOUT;
+			*data = 0xfe;
+			break;
+		case 0xff:
+			*dfl = SERIO_PARITY;
+			*data = 0xfe;
+			break;
+		}
+	}
 
-static irqreturn_t i8042_interrupt(int irq, void *dev_id)
+	last_port = mux_port;
+	last_transmit = jiffies;
+
+	return I8042_MUX_PORT_NO + mux_port;
+}
+
+/*
+ * i8042_handle_data() is the most important function in this driver -
+ * it reads the data from the i8042, determines its destination serio
+ * port, and sends received byte to the upper layers.
+ *
+ * Returns true if there was data waiting, false otherwise.
+ */
+static bool i8042_handle_data(int irq)
 {
 	struct i8042_port *port;
 	struct serio *serio;
@@ -532,63 +588,24 @@ static irqreturn_t i8042_interrupt(int irq, void *dev_id)
 	unsigned int dfl;
 	unsigned int port_no;
 	bool filtered;
-	int ret = 1;
 
 	spin_lock_irqsave(&i8042_lock, flags);
 
 	str = i8042_read_status();
 	if (unlikely(~str & I8042_STR_OBF)) {
 		spin_unlock_irqrestore(&i8042_lock, flags);
-		if (irq)
-			dbg("Interrupt %d, without any data\n", irq);
-		ret = 0;
-		goto out;
+		return false;
 	}
 
 	data = i8042_read_data();
 
 	if (i8042_mux_present && (str & I8042_STR_AUXDATA)) {
-		static unsigned long last_transmit;
-		static unsigned char last_str;
-
-		dfl = 0;
-		if (str & I8042_STR_MUXERR) {
-			dbg("MUX error, status is %02x, data is %02x\n",
-			    str, data);
-/*
- * When MUXERR condition is signalled the data register can only contain
- * 0xfd, 0xfe or 0xff if implementation follows the spec. Unfortunately
- * it is not always the case. Some KBCs also report 0xfc when there is
- * nothing connected to the port while others sometimes get confused which
- * port the data came from and signal error leaving the data intact. They
- * _do not_ revert to legacy mode (actually I've never seen KBC reverting
- * to legacy mode yet, when we see one we'll add proper handling).
- * Anyway, we process 0xfc, 0xfd, 0xfe and 0xff as timeouts, and for the
- * rest assume that the data came from the same serio last byte
- * was transmitted (if transmission happened not too long ago).
- */
-
-			switch (data) {
-				default:
-					if (time_before(jiffies, last_transmit + HZ/10)) {
-						str = last_str;
-						break;
-					}
-					fallthrough;	/* report timeout */
-				case 0xfc:
-				case 0xfd:
-				case 0xfe: dfl = SERIO_TIMEOUT; data = 0xfe; break;
-				case 0xff: dfl = SERIO_PARITY;  data = 0xfe; break;
-			}
-		}
-
-		port_no = I8042_MUX_PORT_NO + ((str >> 6) & 3);
-		last_str = str;
-		last_transmit = jiffies;
+		port_no = i8042_handle_mux(str, &data, &dfl);
 	} else {
 
-		dfl = ((str & I8042_STR_PARITY) ? SERIO_PARITY : 0) |
-		      ((str & I8042_STR_TIMEOUT && !i8042_notimeout) ? SERIO_TIMEOUT : 0);
+		dfl = (str & I8042_STR_PARITY) ? SERIO_PARITY : 0;
+		if ((str & I8042_STR_TIMEOUT) && !i8042_notimeout)
+			dfl |= SERIO_TIMEOUT;
 
 		port_no = (str & I8042_STR_AUXDATA) ?
 				I8042_AUX_PORT_NO : I8042_KBD_PORT_NO;
@@ -609,8 +626,17 @@ static irqreturn_t i8042_interrupt(int irq, void *dev_id)
 	if (likely(serio && !filtered))
 		serio_interrupt(serio, data, dfl);
 
- out:
-	return IRQ_RETVAL(ret);
+	return true;
+}
+
+static irqreturn_t i8042_interrupt(int irq, void *dev_id)
+{
+	if (unlikely(!i8042_handle_data(irq))) {
+		dbg("Interrupt %d, without any data\n", irq);
+		return IRQ_NONE;
+	}
+
+	return IRQ_HANDLED;
 }
 
 /*
@@ -1216,13 +1242,14 @@ static int i8042_controller_resume(bool s2r_wants_reset)
 	if (i8042_mux_present) {
 		if (i8042_set_mux_mode(true, NULL) || i8042_enable_mux_ports())
 			pr_warn("failed to resume active multiplexor, mouse won't work\n");
-	} else if (i8042_ports[I8042_AUX_PORT_NO].serio)
+	} else if (i8042_ports[I8042_AUX_PORT_NO].serio) {
 		i8042_enable_aux_port();
+	}
 
 	if (i8042_ports[I8042_KBD_PORT_NO].serio)
 		i8042_enable_kbd_port();
 
-	i8042_interrupt(0, NULL);
+	i8042_handle_data(0);
 
 	return 0;
 }
@@ -1253,7 +1280,7 @@ static int i8042_pm_suspend(struct device *dev)
 static int i8042_pm_resume_noirq(struct device *dev)
 {
 	if (i8042_forcenorestore || !pm_resume_via_firmware())
-		i8042_interrupt(0, NULL);
+		i8042_handle_data(0);
 
 	return 0;
 }
@@ -1290,7 +1317,7 @@ static int i8042_pm_resume(struct device *dev)
 
 static int i8042_pm_thaw(struct device *dev)
 {
-	i8042_interrupt(0, NULL);
+	i8042_handle_data(0);
 
 	return 0;
 }

From 7dc406b736b9acf01379d2235d97bb4873b504e7 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:18 -0700
Subject: [PATCH 0198/1530] Input: i8042 - use guard notation when acquiring
 spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-14-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/i8042.c | 204 +++++++++++++++---------------------
 1 file changed, 82 insertions(+), 122 deletions(-)

diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index 674cd155ec8fa..86916fe3925fa 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -197,42 +197,26 @@ EXPORT_SYMBOL(i8042_unlock_chip);
 int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str,
 					struct serio *serio))
 {
-	unsigned long flags;
-	int ret = 0;
+	guard(spinlock_irqsave)(&i8042_lock);
 
-	spin_lock_irqsave(&i8042_lock, flags);
-
-	if (i8042_platform_filter) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (i8042_platform_filter)
+		return -EBUSY;
 
 	i8042_platform_filter = filter;
-
-out:
-	spin_unlock_irqrestore(&i8042_lock, flags);
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(i8042_install_filter);
 
 int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str,
 				       struct serio *port))
 {
-	unsigned long flags;
-	int ret = 0;
-
-	spin_lock_irqsave(&i8042_lock, flags);
+	guard(spinlock_irqsave)(&i8042_lock);
 
-	if (i8042_platform_filter != filter) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (i8042_platform_filter != filter)
+		return -EINVAL;
 
 	i8042_platform_filter = NULL;
-
-out:
-	spin_unlock_irqrestore(&i8042_lock, flags);
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(i8042_remove_filter);
 
@@ -271,28 +255,22 @@ static int i8042_wait_write(void)
 
 static int i8042_flush(void)
 {
-	unsigned long flags;
 	unsigned char data, str;
 	int count = 0;
-	int retval = 0;
 
-	spin_lock_irqsave(&i8042_lock, flags);
+	guard(spinlock_irqsave)(&i8042_lock);
 
 	while ((str = i8042_read_status()) & I8042_STR_OBF) {
-		if (count++ < I8042_BUFFER_SIZE) {
-			udelay(50);
-			data = i8042_read_data();
-			dbg("%02x <- i8042 (flush, %s)\n",
-			    data, str & I8042_STR_AUXDATA ? "aux" : "kbd");
-		} else {
-			retval = -EIO;
-			break;
-		}
-	}
+		if (count++ >= I8042_BUFFER_SIZE)
+			return -EIO;
 
-	spin_unlock_irqrestore(&i8042_lock, flags);
+		udelay(50);
+		data = i8042_read_data();
+		dbg("%02x <- i8042 (flush, %s)\n",
+		    data, str & I8042_STR_AUXDATA ? "aux" : "kbd");
+	}
 
-	return retval;
+	return 0;
 }
 
 /*
@@ -349,17 +327,12 @@ static int __i8042_command(unsigned char *param, int command)
 
 int i8042_command(unsigned char *param, int command)
 {
-	unsigned long flags;
-	int retval;
-
 	if (!i8042_present)
 		return -1;
 
-	spin_lock_irqsave(&i8042_lock, flags);
-	retval = __i8042_command(param, command);
-	spin_unlock_irqrestore(&i8042_lock, flags);
+	guard(spinlock_irqsave)(&i8042_lock);
 
-	return retval;
+	return __i8042_command(param, command);
 }
 EXPORT_SYMBOL(i8042_command);
 
@@ -369,19 +342,18 @@ EXPORT_SYMBOL(i8042_command);
 
 static int i8042_kbd_write(struct serio *port, unsigned char c)
 {
-	unsigned long flags;
-	int retval = 0;
+	int error;
 
-	spin_lock_irqsave(&i8042_lock, flags);
+	guard(spinlock_irqsave)(&i8042_lock);
 
-	if (!(retval = i8042_wait_write())) {
-		dbg("%02x -> i8042 (kbd-data)\n", c);
-		i8042_write_data(c);
-	}
+	error = i8042_wait_write();
+	if (error)
+		return error;
 
-	spin_unlock_irqrestore(&i8042_lock, flags);
+	dbg("%02x -> i8042 (kbd-data)\n", c);
+	i8042_write_data(c);
 
-	return retval;
+	return 0;
 }
 
 /*
@@ -460,9 +432,8 @@ static int i8042_start(struct serio *serio)
 		device_set_wakeup_enable(&serio->dev, true);
 	}
 
-	spin_lock_irq(&i8042_lock);
+	guard(spinlock_irq)(&i8042_lock);
 	port->exists = true;
-	spin_unlock_irq(&i8042_lock);
 
 	return 0;
 }
@@ -476,10 +447,10 @@ static void i8042_stop(struct serio *serio)
 {
 	struct i8042_port *port = serio->port_data;
 
-	spin_lock_irq(&i8042_lock);
-	port->exists = false;
-	port->serio = NULL;
-	spin_unlock_irq(&i8042_lock);
+	scoped_guard(spinlock_irq, &i8042_lock) {
+		port->exists = false;
+		port->serio = NULL;
+	}
 
 	/*
 	 * We need to make sure that interrupt handler finishes using
@@ -583,45 +554,41 @@ static bool i8042_handle_data(int irq)
 {
 	struct i8042_port *port;
 	struct serio *serio;
-	unsigned long flags;
 	unsigned char str, data;
 	unsigned int dfl;
 	unsigned int port_no;
 	bool filtered;
 
-	spin_lock_irqsave(&i8042_lock, flags);
-
-	str = i8042_read_status();
-	if (unlikely(~str & I8042_STR_OBF)) {
-		spin_unlock_irqrestore(&i8042_lock, flags);
-		return false;
-	}
-
-	data = i8042_read_data();
+	scoped_guard(spinlock_irqsave, &i8042_lock) {
+		str = i8042_read_status();
+		if (unlikely(~str & I8042_STR_OBF))
+			return false;
 
-	if (i8042_mux_present && (str & I8042_STR_AUXDATA)) {
-		port_no = i8042_handle_mux(str, &data, &dfl);
-	} else {
+		data = i8042_read_data();
 
-		dfl = (str & I8042_STR_PARITY) ? SERIO_PARITY : 0;
-		if ((str & I8042_STR_TIMEOUT) && !i8042_notimeout)
-			dfl |= SERIO_TIMEOUT;
+		if (i8042_mux_present && (str & I8042_STR_AUXDATA)) {
+			port_no = i8042_handle_mux(str, &data, &dfl);
+		} else {
 
-		port_no = (str & I8042_STR_AUXDATA) ?
-				I8042_AUX_PORT_NO : I8042_KBD_PORT_NO;
-	}
+			dfl = (str & I8042_STR_PARITY) ? SERIO_PARITY : 0;
+			if ((str & I8042_STR_TIMEOUT) && !i8042_notimeout)
+				dfl |= SERIO_TIMEOUT;
 
-	port = &i8042_ports[port_no];
-	serio = port->exists ? port->serio : NULL;
+			port_no = (str & I8042_STR_AUXDATA) ?
+					I8042_AUX_PORT_NO : I8042_KBD_PORT_NO;
+		}
 
-	filter_dbg(port->driver_bound, data, "<- i8042 (interrupt, %d, %d%s%s)\n",
-		   port_no, irq,
-		   dfl & SERIO_PARITY ? ", bad parity" : "",
-		   dfl & SERIO_TIMEOUT ? ", timeout" : "");
+		port = &i8042_ports[port_no];
+		serio = port->exists ? port->serio : NULL;
 
-	filtered = i8042_filter(data, str, serio);
+		filter_dbg(port->driver_bound,
+			   data, "<- i8042 (interrupt, %d, %d%s%s)\n",
+			   port_no, irq,
+			   dfl & SERIO_PARITY ? ", bad parity" : "",
+			   dfl & SERIO_TIMEOUT ? ", timeout" : "");
 
-	spin_unlock_irqrestore(&i8042_lock, flags);
+		filtered = i8042_filter(data, str, serio);
+	}
 
 	if (likely(serio && !filtered))
 		serio_interrupt(serio, data, dfl);
@@ -779,24 +746,22 @@ static bool i8042_irq_being_tested;
 
 static irqreturn_t i8042_aux_test_irq(int irq, void *dev_id)
 {
-	unsigned long flags;
 	unsigned char str, data;
-	int ret = 0;
 
-	spin_lock_irqsave(&i8042_lock, flags);
+	guard(spinlock_irqsave)(&i8042_lock);
+
 	str = i8042_read_status();
-	if (str & I8042_STR_OBF) {
-		data = i8042_read_data();
-		dbg("%02x <- i8042 (aux_test_irq, %s)\n",
-		    data, str & I8042_STR_AUXDATA ? "aux" : "kbd");
-		if (i8042_irq_being_tested &&
-		    data == 0xa5 && (str & I8042_STR_AUXDATA))
-			complete(&i8042_aux_irq_delivered);
-		ret = 1;
-	}
-	spin_unlock_irqrestore(&i8042_lock, flags);
+	if (!(str & I8042_STR_OBF))
+		return IRQ_NONE;
+
+	data = i8042_read_data();
+	dbg("%02x <- i8042 (aux_test_irq, %s)\n",
+	    data, str & I8042_STR_AUXDATA ? "aux" : "kbd");
+
+	if (i8042_irq_being_tested && data == 0xa5 && (str & I8042_STR_AUXDATA))
+		complete(&i8042_aux_irq_delivered);
 
-	return IRQ_RETVAL(ret);
+	return IRQ_HANDLED;
 }
 
 /*
@@ -837,7 +802,6 @@ static int i8042_check_aux(void)
 	int retval = -1;
 	bool irq_registered = false;
 	bool aux_loop_broken = false;
-	unsigned long flags;
 	unsigned char param;
 
 /*
@@ -921,18 +885,15 @@ static int i8042_check_aux(void)
 	if (i8042_enable_aux_port())
 		goto out;
 
-	spin_lock_irqsave(&i8042_lock, flags);
-
-	init_completion(&i8042_aux_irq_delivered);
-	i8042_irq_being_tested = true;
-
-	param = 0xa5;
-	retval = __i8042_command(&param, I8042_CMD_AUX_LOOP & 0xf0ff);
-
-	spin_unlock_irqrestore(&i8042_lock, flags);
+	scoped_guard(spinlock_irqsave, &i8042_lock) {
+		init_completion(&i8042_aux_irq_delivered);
+		i8042_irq_being_tested = true;
 
-	if (retval)
-		goto out;
+		param = 0xa5;
+		retval = __i8042_command(&param, I8042_CMD_AUX_LOOP & 0xf0ff);
+		if (retval)
+			goto out;
+	}
 
 	if (wait_for_completion_timeout(&i8042_aux_irq_delivered,
 					msecs_to_jiffies(250)) == 0) {
@@ -1020,7 +981,6 @@ static int i8042_controller_selftest(void)
 
 static int i8042_controller_init(void)
 {
-	unsigned long flags;
 	int n = 0;
 	unsigned char ctr[2];
 
@@ -1057,14 +1017,14 @@ static int i8042_controller_init(void)
  * Handle keylock.
  */
 
-	spin_lock_irqsave(&i8042_lock, flags);
-	if (~i8042_read_status() & I8042_STR_KEYLOCK) {
-		if (i8042_unlock)
-			i8042_ctr |= I8042_CTR_IGNKEYLOCK;
-		else
-			pr_warn("Warning: Keylock active\n");
+	scoped_guard(spinlock_irqsave, &i8042_lock) {
+		if (~i8042_read_status() & I8042_STR_KEYLOCK) {
+			if (i8042_unlock)
+				i8042_ctr |= I8042_CTR_IGNKEYLOCK;
+			else
+				pr_warn("Warning: Keylock active\n");
+		}
 	}
-	spin_unlock_irqrestore(&i8042_lock, flags);
 
 /*
  * If the chip is configured into nontranslated mode by the BIOS, don't

From 31b6b9a46d0af9c1ec7133e41302b3ef76016b04 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:19 -0700
Subject: [PATCH 0199/1530] Input: ps2-gpio - use guard notation when acquiring
 mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-15-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/ps2-gpio.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/serio/ps2-gpio.c b/drivers/input/serio/ps2-gpio.c
index 3a431395c4646..3e4ae2cc6552d 100644
--- a/drivers/input/serio/ps2-gpio.c
+++ b/drivers/input/serio/ps2-gpio.c
@@ -133,12 +133,12 @@ static int ps2_gpio_write(struct serio *serio, unsigned char val)
 	int ret = 0;
 
 	if (in_task()) {
-		mutex_lock(&drvdata->tx.mutex);
+		guard(mutex)(&drvdata->tx.mutex);
+
 		__ps2_gpio_write(serio, val);
 		if (!wait_for_completion_timeout(&drvdata->tx.complete,
 						 msecs_to_jiffies(10000)))
 			ret = SERIO_TIMEOUT;
-		mutex_unlock(&drvdata->tx.mutex);
 	} else {
 		__ps2_gpio_write(serio, val);
 	}

From 9d58ae181d0dbaf445a18079528b8e3b7f669f9b Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:20 -0700
Subject: [PATCH 0200/1530] Input: ps2mult - use guard notation when acquiring
 spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-16-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/ps2mult.c | 25 +++++++------------------
 1 file changed, 7 insertions(+), 18 deletions(-)

diff --git a/drivers/input/serio/ps2mult.c b/drivers/input/serio/ps2mult.c
index 937ecdea491d1..b96cee52fc52e 100644
--- a/drivers/input/serio/ps2mult.c
+++ b/drivers/input/serio/ps2mult.c
@@ -76,9 +76,8 @@ static int ps2mult_serio_write(struct serio *serio, unsigned char data)
 	struct ps2mult *psm = serio_get_drvdata(mx_port);
 	struct ps2mult_port *port = serio->port_data;
 	bool need_escape;
-	unsigned long flags;
 
-	spin_lock_irqsave(&psm->lock, flags);
+	guard(spinlock_irqsave)(&psm->lock);
 
 	if (psm->out_port != port)
 		ps2mult_select_port(psm, port);
@@ -93,8 +92,6 @@ static int ps2mult_serio_write(struct serio *serio, unsigned char data)
 
 	serio_write(mx_port, data);
 
-	spin_unlock_irqrestore(&psm->lock, flags);
-
 	return 0;
 }
 
@@ -102,11 +99,10 @@ static int ps2mult_serio_start(struct serio *serio)
 {
 	struct ps2mult *psm = serio_get_drvdata(serio->parent);
 	struct ps2mult_port *port = serio->port_data;
-	unsigned long flags;
 
-	spin_lock_irqsave(&psm->lock, flags);
+	guard(spinlock_irqsave)(&psm->lock);
+
 	port->registered = true;
-	spin_unlock_irqrestore(&psm->lock, flags);
 
 	return 0;
 }
@@ -115,11 +111,10 @@ static void ps2mult_serio_stop(struct serio *serio)
 {
 	struct ps2mult *psm = serio_get_drvdata(serio->parent);
 	struct ps2mult_port *port = serio->port_data;
-	unsigned long flags;
 
-	spin_lock_irqsave(&psm->lock, flags);
+	guard(spinlock_irqsave)(&psm->lock);
+
 	port->registered = false;
-	spin_unlock_irqrestore(&psm->lock, flags);
 }
 
 static int ps2mult_create_port(struct ps2mult *psm, int i)
@@ -148,16 +143,12 @@ static int ps2mult_create_port(struct ps2mult *psm, int i)
 
 static void ps2mult_reset(struct ps2mult *psm)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&psm->lock, flags);
+	guard(spinlock_irqsave)(&psm->lock);
 
 	serio_write(psm->mx_serio, PS2MULT_SESSION_END);
 	serio_write(psm->mx_serio, PS2MULT_SESSION_START);
 
 	ps2mult_select_port(psm, &psm->ports[PS2MULT_KBD_PORT]);
-
-	spin_unlock_irqrestore(&psm->lock, flags);
 }
 
 static int ps2mult_connect(struct serio *serio, struct serio_driver *drv)
@@ -234,11 +225,10 @@ static irqreturn_t ps2mult_interrupt(struct serio *serio,
 {
 	struct ps2mult *psm = serio_get_drvdata(serio);
 	struct ps2mult_port *in_port;
-	unsigned long flags;
 
 	dev_dbg(&serio->dev, "Received %02x flags %02x\n", data, dfl);
 
-	spin_lock_irqsave(&psm->lock, flags);
+	guard(spinlock_irqsave)(&psm->lock);
 
 	if (psm->escape) {
 		psm->escape = false;
@@ -285,7 +275,6 @@ static irqreturn_t ps2mult_interrupt(struct serio *serio,
 	}
 
  out:
-	spin_unlock_irqrestore(&psm->lock, flags);
 	return IRQ_HANDLED;
 }
 

From 424bc7e00a3495afb6ea85696b530b3f47bc24fb Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:21 -0700
Subject: [PATCH 0201/1530] Input: q40kbd - use guard notation when acquiring
 spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-17-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/q40kbd.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/input/serio/q40kbd.c b/drivers/input/serio/q40kbd.c
index cd4d5be946a36..cdd5c4ef9b365 100644
--- a/drivers/input/serio/q40kbd.c
+++ b/drivers/input/serio/q40kbd.c
@@ -39,17 +39,14 @@ struct q40kbd {
 static irqreturn_t q40kbd_interrupt(int irq, void *dev_id)
 {
 	struct q40kbd *q40kbd = dev_id;
-	unsigned long flags;
 
-	spin_lock_irqsave(&q40kbd->lock, flags);
+	guard(spinlock_irqsave)(&q40kbd->lock);
 
 	if (Q40_IRQ_KEYB_MASK & master_inb(INTERRUPT_REG))
 		serio_interrupt(q40kbd->port, master_inb(KEYCODE_REG), 0);
 
 	master_outb(-1, KEYBOARD_UNLOCK_REG);
 
-	spin_unlock_irqrestore(&q40kbd->lock, flags);
-
 	return IRQ_HANDLED;
 }
 
@@ -60,14 +57,11 @@ static irqreturn_t q40kbd_interrupt(int irq, void *dev_id)
 static void q40kbd_flush(struct q40kbd *q40kbd)
 {
 	int maxread = 100;
-	unsigned long flags;
 
-	spin_lock_irqsave(&q40kbd->lock, flags);
+	guard(spinlock_irqsave)(&q40kbd->lock);
 
 	while (maxread-- && (Q40_IRQ_KEYB_MASK & master_inb(INTERRUPT_REG)))
 		master_inb(KEYCODE_REG);
-
-	spin_unlock_irqrestore(&q40kbd->lock, flags);
 }
 
 static void q40kbd_stop(void)

From d8ea63cb4475f1e7ac2979d7181e2b9114c7f5b2 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:22 -0700
Subject: [PATCH 0202/1530] Input: sa1111ps2 - use guard notation when
 acquiring spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-18-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/sa1111ps2.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/input/serio/sa1111ps2.c b/drivers/input/serio/sa1111ps2.c
index 1311caf7dba4f..375c6f5f905c3 100644
--- a/drivers/input/serio/sa1111ps2.c
+++ b/drivers/input/serio/sa1111ps2.c
@@ -92,7 +92,8 @@ static irqreturn_t ps2_txint(int irq, void *dev_id)
 	struct ps2if *ps2if = dev_id;
 	unsigned int status;
 
-	spin_lock(&ps2if->lock);
+	guard(spinlock)(&ps2if->lock);
+
 	status = readl_relaxed(ps2if->base + PS2STAT);
 	if (ps2if->head == ps2if->tail) {
 		disable_irq_nosync(irq);
@@ -101,7 +102,6 @@ static irqreturn_t ps2_txint(int irq, void *dev_id)
 		writel_relaxed(ps2if->buf[ps2if->tail], ps2if->base + PS2DATA);
 		ps2if->tail = (ps2if->tail + 1) & (sizeof(ps2if->buf) - 1);
 	}
-	spin_unlock(&ps2if->lock);
 
 	return IRQ_HANDLED;
 }
@@ -113,10 +113,9 @@ static irqreturn_t ps2_txint(int irq, void *dev_id)
 static int ps2_write(struct serio *io, unsigned char val)
 {
 	struct ps2if *ps2if = io->port_data;
-	unsigned long flags;
 	unsigned int head;
 
-	spin_lock_irqsave(&ps2if->lock, flags);
+	guard(spinlock_irqsave)(&ps2if->lock);
 
 	/*
 	 * If the TX register is empty, we can go straight out.
@@ -133,7 +132,6 @@ static int ps2_write(struct serio *io, unsigned char val)
 		}
 	}
 
-	spin_unlock_irqrestore(&ps2if->lock, flags);
 	return 0;
 }
 

From f7d15dcc249e54aedcfc71dddb6418b0bb2b8531 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:23 -0700
Subject: [PATCH 0203/1530] Input: serport - use guard notation when acquiring
 spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-19-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/serport.c | 27 ++++++++-------------------
 1 file changed, 8 insertions(+), 19 deletions(-)

diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c
index 5a2b5404ffc21..74ac887961873 100644
--- a/drivers/input/serio/serport.c
+++ b/drivers/input/serio/serport.c
@@ -50,11 +50,9 @@ static int serport_serio_write(struct serio *serio, unsigned char data)
 static int serport_serio_open(struct serio *serio)
 {
 	struct serport *serport = serio->port_data;
-	unsigned long flags;
 
-	spin_lock_irqsave(&serport->lock, flags);
+	guard(spinlock_irqsave)(&serport->lock);
 	set_bit(SERPORT_ACTIVE, &serport->flags);
-	spin_unlock_irqrestore(&serport->lock, flags);
 
 	return 0;
 }
@@ -63,11 +61,9 @@ static int serport_serio_open(struct serio *serio)
 static void serport_serio_close(struct serio *serio)
 {
 	struct serport *serport = serio->port_data;
-	unsigned long flags;
 
-	spin_lock_irqsave(&serport->lock, flags);
+	guard(spinlock_irqsave)(&serport->lock);
 	clear_bit(SERPORT_ACTIVE, &serport->flags);
-	spin_unlock_irqrestore(&serport->lock, flags);
 }
 
 /*
@@ -118,14 +114,13 @@ static void serport_ldisc_receive(struct tty_struct *tty, const u8 *cp,
 				  const u8 *fp, size_t count)
 {
 	struct serport *serport = tty->disc_data;
-	unsigned long flags;
 	unsigned int ch_flags = 0;
 	int i;
 
-	spin_lock_irqsave(&serport->lock, flags);
+	guard(spinlock_irqsave)(&serport->lock);
 
 	if (!test_bit(SERPORT_ACTIVE, &serport->flags))
-		goto out;
+		return;
 
 	for (i = 0; i < count; i++) {
 		if (fp) {
@@ -146,9 +141,6 @@ static void serport_ldisc_receive(struct tty_struct *tty, const u8 *cp,
 
 		serio_interrupt(serport->serio, cp[i], ch_flags);
 	}
-
-out:
-	spin_unlock_irqrestore(&serport->lock, flags);
 }
 
 /*
@@ -246,11 +238,9 @@ static int serport_ldisc_compat_ioctl(struct tty_struct *tty,
 static void serport_ldisc_hangup(struct tty_struct *tty)
 {
 	struct serport *serport = tty->disc_data;
-	unsigned long flags;
 
-	spin_lock_irqsave(&serport->lock, flags);
-	set_bit(SERPORT_DEAD, &serport->flags);
-	spin_unlock_irqrestore(&serport->lock, flags);
+	scoped_guard(spinlock_irqsave, &serport->lock)
+		set_bit(SERPORT_DEAD, &serport->flags);
 
 	wake_up_interruptible(&serport->wait);
 }
@@ -258,12 +248,11 @@ static void serport_ldisc_hangup(struct tty_struct *tty)
 static void serport_ldisc_write_wakeup(struct tty_struct * tty)
 {
 	struct serport *serport = tty->disc_data;
-	unsigned long flags;
 
-	spin_lock_irqsave(&serport->lock, flags);
+	guard(spinlock_irqsave)(&serport->lock);
+
 	if (test_bit(SERPORT_ACTIVE, &serport->flags))
 		serio_drv_write_wakeup(serport->serio);
-	spin_unlock_irqrestore(&serport->lock, flags);
 }
 
 /*

From 924c5eeb17490136d9ec688b0926bbae27eb0a1f Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:24 -0700
Subject: [PATCH 0204/1530] Input: serio - use guard notation when acquiring
 mutexes and spinlocks

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-20-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/serio.c | 165 +++++++++++++++---------------------
 1 file changed, 66 insertions(+), 99 deletions(-)

diff --git a/drivers/input/serio/serio.c b/drivers/input/serio/serio.c
index 97d8eacb91127..4468018cef664 100644
--- a/drivers/input/serio/serio.c
+++ b/drivers/input/serio/serio.c
@@ -38,33 +38,27 @@ static void serio_attach_driver(struct serio_driver *drv);
 
 static int serio_connect_driver(struct serio *serio, struct serio_driver *drv)
 {
-	int retval;
-
-	mutex_lock(&serio->drv_mutex);
-	retval = drv->connect(serio, drv);
-	mutex_unlock(&serio->drv_mutex);
+	guard(mutex)(&serio->drv_mutex);
 
-	return retval;
+	return drv->connect(serio, drv);
 }
 
 static int serio_reconnect_driver(struct serio *serio)
 {
-	int retval = -1;
+	guard(mutex)(&serio->drv_mutex);
 
-	mutex_lock(&serio->drv_mutex);
 	if (serio->drv && serio->drv->reconnect)
-		retval = serio->drv->reconnect(serio);
-	mutex_unlock(&serio->drv_mutex);
+		return serio->drv->reconnect(serio);
 
-	return retval;
+	return -1;
 }
 
 static void serio_disconnect_driver(struct serio *serio)
 {
-	mutex_lock(&serio->drv_mutex);
+	guard(mutex)(&serio->drv_mutex);
+
 	if (serio->drv)
 		serio->drv->disconnect(serio);
-	mutex_unlock(&serio->drv_mutex);
 }
 
 static int serio_match_port(const struct serio_device_id *ids, struct serio *serio)
@@ -147,9 +141,8 @@ static LIST_HEAD(serio_event_list);
 static struct serio_event *serio_get_event(void)
 {
 	struct serio_event *event = NULL;
-	unsigned long flags;
 
-	spin_lock_irqsave(&serio_event_lock, flags);
+	guard(spinlock_irqsave)(&serio_event_lock);
 
 	if (!list_empty(&serio_event_list)) {
 		event = list_first_entry(&serio_event_list,
@@ -157,7 +150,6 @@ static struct serio_event *serio_get_event(void)
 		list_del_init(&event->node);
 	}
 
-	spin_unlock_irqrestore(&serio_event_lock, flags);
 	return event;
 }
 
@@ -171,9 +163,8 @@ static void serio_remove_duplicate_events(void *object,
 					  enum serio_event_type type)
 {
 	struct serio_event *e, *next;
-	unsigned long flags;
 
-	spin_lock_irqsave(&serio_event_lock, flags);
+	guard(spinlock_irqsave)(&serio_event_lock);
 
 	list_for_each_entry_safe(e, next, &serio_event_list, node) {
 		if (object == e->object) {
@@ -189,15 +180,13 @@ static void serio_remove_duplicate_events(void *object,
 			serio_free_event(e);
 		}
 	}
-
-	spin_unlock_irqrestore(&serio_event_lock, flags);
 }
 
 static void serio_handle_event(struct work_struct *work)
 {
 	struct serio_event *event;
 
-	mutex_lock(&serio_mutex);
+	guard(mutex)(&serio_mutex);
 
 	while ((event = serio_get_event())) {
 
@@ -228,8 +217,6 @@ static void serio_handle_event(struct work_struct *work)
 		serio_remove_duplicate_events(event->object, event->type);
 		serio_free_event(event);
 	}
-
-	mutex_unlock(&serio_mutex);
 }
 
 static DECLARE_WORK(serio_event_work, serio_handle_event);
@@ -237,11 +224,9 @@ static DECLARE_WORK(serio_event_work, serio_handle_event);
 static int serio_queue_event(void *object, struct module *owner,
 			     enum serio_event_type event_type)
 {
-	unsigned long flags;
 	struct serio_event *event;
-	int retval = 0;
 
-	spin_lock_irqsave(&serio_event_lock, flags);
+	guard(spinlock_irqsave)(&serio_event_lock);
 
 	/*
 	 * Scan event list for the other events for the same serio port,
@@ -253,7 +238,7 @@ static int serio_queue_event(void *object, struct module *owner,
 	list_for_each_entry_reverse(event, &serio_event_list, node) {
 		if (event->object == object) {
 			if (event->type == event_type)
-				goto out;
+				return 0;
 			break;
 		}
 	}
@@ -261,16 +246,14 @@ static int serio_queue_event(void *object, struct module *owner,
 	event = kmalloc(sizeof(*event), GFP_ATOMIC);
 	if (!event) {
 		pr_err("Not enough memory to queue event %d\n", event_type);
-		retval = -ENOMEM;
-		goto out;
+		return -ENOMEM;
 	}
 
 	if (!try_module_get(owner)) {
 		pr_warn("Can't get module reference, dropping event %d\n",
 			event_type);
 		kfree(event);
-		retval = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	event->type = event_type;
@@ -280,9 +263,7 @@ static int serio_queue_event(void *object, struct module *owner,
 	list_add_tail(&event->node, &serio_event_list);
 	queue_work(system_long_wq, &serio_event_work);
 
-out:
-	spin_unlock_irqrestore(&serio_event_lock, flags);
-	return retval;
+	return 0;
 }
 
 /*
@@ -292,9 +273,8 @@ static int serio_queue_event(void *object, struct module *owner,
 static void serio_remove_pending_events(void *object)
 {
 	struct serio_event *event, *next;
-	unsigned long flags;
 
-	spin_lock_irqsave(&serio_event_lock, flags);
+	guard(spinlock_irqsave)(&serio_event_lock);
 
 	list_for_each_entry_safe(event, next, &serio_event_list, node) {
 		if (event->object == object) {
@@ -302,8 +282,6 @@ static void serio_remove_pending_events(void *object)
 			serio_free_event(event);
 		}
 	}
-
-	spin_unlock_irqrestore(&serio_event_lock, flags);
 }
 
 /*
@@ -315,23 +293,19 @@ static void serio_remove_pending_events(void *object)
 static struct serio *serio_get_pending_child(struct serio *parent)
 {
 	struct serio_event *event;
-	struct serio *serio, *child = NULL;
-	unsigned long flags;
+	struct serio *serio;
 
-	spin_lock_irqsave(&serio_event_lock, flags);
+	guard(spinlock_irqsave)(&serio_event_lock);
 
 	list_for_each_entry(event, &serio_event_list, node) {
 		if (event->type == SERIO_REGISTER_PORT) {
 			serio = event->object;
-			if (serio->parent == parent) {
-				child = serio;
-				break;
-			}
+			if (serio->parent == parent)
+				return serio;
 		}
 	}
 
-	spin_unlock_irqrestore(&serio_event_lock, flags);
-	return child;
+	return NULL;
 }
 
 /*
@@ -382,29 +356,27 @@ static ssize_t drvctl_store(struct device *dev, struct device_attribute *attr, c
 	struct device_driver *drv;
 	int error;
 
-	error = mutex_lock_interruptible(&serio_mutex);
-	if (error)
-		return error;
-
-	if (!strncmp(buf, "none", count)) {
-		serio_disconnect_port(serio);
-	} else if (!strncmp(buf, "reconnect", count)) {
-		serio_reconnect_subtree(serio);
-	} else if (!strncmp(buf, "rescan", count)) {
-		serio_disconnect_port(serio);
-		serio_find_driver(serio);
-		serio_remove_duplicate_events(serio, SERIO_RESCAN_PORT);
-	} else if ((drv = driver_find(buf, &serio_bus)) != NULL) {
-		serio_disconnect_port(serio);
-		error = serio_bind_driver(serio, to_serio_driver(drv));
-		serio_remove_duplicate_events(serio, SERIO_RESCAN_PORT);
-	} else {
-		error = -EINVAL;
+	scoped_cond_guard(mutex_intr, return -EINTR, &serio_mutex) {
+		if (!strncmp(buf, "none", count)) {
+			serio_disconnect_port(serio);
+		} else if (!strncmp(buf, "reconnect", count)) {
+			serio_reconnect_subtree(serio);
+		} else if (!strncmp(buf, "rescan", count)) {
+			serio_disconnect_port(serio);
+			serio_find_driver(serio);
+			serio_remove_duplicate_events(serio, SERIO_RESCAN_PORT);
+		} else if ((drv = driver_find(buf, &serio_bus)) != NULL) {
+			serio_disconnect_port(serio);
+			error = serio_bind_driver(serio, to_serio_driver(drv));
+			serio_remove_duplicate_events(serio, SERIO_RESCAN_PORT);
+			if (error)
+				return error;
+		} else {
+			return -EINVAL;
+		}
 	}
 
-	mutex_unlock(&serio_mutex);
-
-	return error ? error : count;
+	return count;
 }
 
 static ssize_t serio_show_bind_mode(struct device *dev, struct device_attribute *attr, char *buf)
@@ -526,9 +498,9 @@ static void serio_add_port(struct serio *serio)
 	int error;
 
 	if (parent) {
-		serio_pause_rx(parent);
+		guard(serio_pause_rx)(parent);
+
 		list_add_tail(&serio->child_node, &parent->children);
-		serio_continue_rx(parent);
 	}
 
 	list_add_tail(&serio->node, &serio_list);
@@ -560,9 +532,9 @@ static void serio_destroy_port(struct serio *serio)
 		serio->stop(serio);
 
 	if (serio->parent) {
-		serio_pause_rx(serio->parent);
+		guard(serio_pause_rx)(serio->parent);
+
 		list_del_init(&serio->child_node);
-		serio_continue_rx(serio->parent);
 		serio->parent = NULL;
 	}
 
@@ -701,10 +673,10 @@ EXPORT_SYMBOL(__serio_register_port);
  */
 void serio_unregister_port(struct serio *serio)
 {
-	mutex_lock(&serio_mutex);
+	guard(mutex)(&serio_mutex);
+
 	serio_disconnect_port(serio);
 	serio_destroy_port(serio);
-	mutex_unlock(&serio_mutex);
 }
 EXPORT_SYMBOL(serio_unregister_port);
 
@@ -715,12 +687,12 @@ void serio_unregister_child_port(struct serio *serio)
 {
 	struct serio *s, *next;
 
-	mutex_lock(&serio_mutex);
+	guard(mutex)(&serio_mutex);
+
 	list_for_each_entry_safe(s, next, &serio->children, child_node) {
 		serio_disconnect_port(s);
 		serio_destroy_port(s);
 	}
-	mutex_unlock(&serio_mutex);
 }
 EXPORT_SYMBOL(serio_unregister_child_port);
 
@@ -784,10 +756,10 @@ static void serio_driver_remove(struct device *dev)
 
 static void serio_cleanup(struct serio *serio)
 {
-	mutex_lock(&serio->drv_mutex);
+	guard(mutex)(&serio->drv_mutex);
+
 	if (serio->drv && serio->drv->cleanup)
 		serio->drv->cleanup(serio);
-	mutex_unlock(&serio->drv_mutex);
 }
 
 static void serio_shutdown(struct device *dev)
@@ -850,7 +822,7 @@ void serio_unregister_driver(struct serio_driver *drv)
 {
 	struct serio *serio;
 
-	mutex_lock(&serio_mutex);
+	guard(mutex)(&serio_mutex);
 
 	drv->manual_bind = true;	/* so serio_find_driver ignores it */
 	serio_remove_pending_events(drv);
@@ -866,15 +838,14 @@ void serio_unregister_driver(struct serio_driver *drv)
 	}
 
 	driver_unregister(&drv->driver);
-	mutex_unlock(&serio_mutex);
 }
 EXPORT_SYMBOL(serio_unregister_driver);
 
 static void serio_set_drv(struct serio *serio, struct serio_driver *drv)
 {
-	serio_pause_rx(serio);
+	guard(serio_pause_rx)(serio);
+
 	serio->drv = drv;
-	serio_continue_rx(serio);
 }
 
 static int serio_bus_match(struct device *dev, const struct device_driver *drv)
@@ -935,14 +906,14 @@ static int serio_resume(struct device *dev)
 	struct serio *serio = to_serio_port(dev);
 	int error = -ENOENT;
 
-	mutex_lock(&serio->drv_mutex);
-	if (serio->drv && serio->drv->fast_reconnect) {
-		error = serio->drv->fast_reconnect(serio);
-		if (error && error != -ENOENT)
-			dev_warn(dev, "fast reconnect failed with error %d\n",
-				 error);
+	scoped_guard(mutex, &serio->drv_mutex) {
+		if (serio->drv && serio->drv->fast_reconnect) {
+			error = serio->drv->fast_reconnect(serio);
+			if (error && error != -ENOENT)
+				dev_warn(dev, "fast reconnect failed with error %d\n",
+					 error);
+		}
 	}
-	mutex_unlock(&serio->drv_mutex);
 
 	if (error) {
 		/*
@@ -989,21 +960,17 @@ EXPORT_SYMBOL(serio_close);
 irqreturn_t serio_interrupt(struct serio *serio,
 		unsigned char data, unsigned int dfl)
 {
-	unsigned long flags;
-	irqreturn_t ret = IRQ_NONE;
+	guard(spinlock_irqsave)(&serio->lock);
 
-	spin_lock_irqsave(&serio->lock, flags);
+	if (likely(serio->drv))
+		return serio->drv->interrupt(serio, data, dfl);
 
-        if (likely(serio->drv)) {
-                ret = serio->drv->interrupt(serio, data, dfl);
-	} else if (!dfl && device_is_registered(&serio->dev)) {
+	if (!dfl && device_is_registered(&serio->dev)) {
 		serio_rescan(serio);
-		ret = IRQ_HANDLED;
+		return IRQ_HANDLED;
 	}
 
-	spin_unlock_irqrestore(&serio->lock, flags);
-
-	return ret;
+	return IRQ_NONE;
 }
 EXPORT_SYMBOL(serio_interrupt);
 

From 5b53a9d40c4f83b44de8da06af9a9c9b3fb14988 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:25 -0700
Subject: [PATCH 0205/1530] Input: serio_raw - use guard notation for locks and
 other resources

Use guard notation when acquiring mutexes and spinlocks, and when
pausing and resuming serio port. Such guard notation makes the code
more compact and error handling more robust by ensuring that locks
are released in all code paths when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-21-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/serio_raw.c | 121 +++++++++++++-------------------
 1 file changed, 49 insertions(+), 72 deletions(-)

diff --git a/drivers/input/serio/serio_raw.c b/drivers/input/serio/serio_raw.c
index 0186d1b38f49f..aef8301313b2c 100644
--- a/drivers/input/serio/serio_raw.c
+++ b/drivers/input/serio/serio_raw.c
@@ -75,41 +75,31 @@ static int serio_raw_open(struct inode *inode, struct file *file)
 {
 	struct serio_raw *serio_raw;
 	struct serio_raw_client *client;
-	int retval;
 
-	retval = mutex_lock_interruptible(&serio_raw_mutex);
-	if (retval)
-		return retval;
+	scoped_guard(mutex_intr, &serio_raw_mutex) {
+		serio_raw = serio_raw_locate(iminor(inode));
+		if (!serio_raw)
+			return -ENODEV;
 
-	serio_raw = serio_raw_locate(iminor(inode));
-	if (!serio_raw) {
-		retval = -ENODEV;
-		goto out;
-	}
+		if (serio_raw->dead)
+			return -ENODEV;
 
-	if (serio_raw->dead) {
-		retval = -ENODEV;
-		goto out;
-	}
+		client = kzalloc(sizeof(*client), GFP_KERNEL);
+		if (!client)
+			return -ENOMEM;
 
-	client = kzalloc(sizeof(*client), GFP_KERNEL);
-	if (!client) {
-		retval = -ENOMEM;
-		goto out;
-	}
+		client->serio_raw = serio_raw;
+		file->private_data = client;
 
-	client->serio_raw = serio_raw;
-	file->private_data = client;
+		kref_get(&serio_raw->kref);
 
-	kref_get(&serio_raw->kref);
+		scoped_guard(serio_pause_rx, serio_raw->serio)
+			list_add_tail(&client->node, &serio_raw->client_list);
 
-	serio_pause_rx(serio_raw->serio);
-	list_add_tail(&client->node, &serio_raw->client_list);
-	serio_continue_rx(serio_raw->serio);
+		return 0;
+	}
 
-out:
-	mutex_unlock(&serio_raw_mutex);
-	return retval;
+	return -EINTR;
 }
 
 static void serio_raw_free(struct kref *kref)
@@ -126,9 +116,8 @@ static int serio_raw_release(struct inode *inode, struct file *file)
 	struct serio_raw_client *client = file->private_data;
 	struct serio_raw *serio_raw = client->serio_raw;
 
-	serio_pause_rx(serio_raw->serio);
-	list_del(&client->node);
-	serio_continue_rx(serio_raw->serio);
+	scoped_guard(serio_pause_rx, serio_raw->serio)
+		list_del(&client->node);
 
 	kfree(client);
 
@@ -139,19 +128,15 @@ static int serio_raw_release(struct inode *inode, struct file *file)
 
 static bool serio_raw_fetch_byte(struct serio_raw *serio_raw, char *c)
 {
-	bool empty;
+	guard(serio_pause_rx)(serio_raw->serio);
 
-	serio_pause_rx(serio_raw->serio);
-
-	empty = serio_raw->head == serio_raw->tail;
-	if (!empty) {
-		*c = serio_raw->queue[serio_raw->tail];
-		serio_raw->tail = (serio_raw->tail + 1) % SERIO_RAW_QUEUE_LEN;
-	}
+	if (serio_raw->head == serio_raw->tail)
+		return false; /* queue is empty */
 
-	serio_continue_rx(serio_raw->serio);
+	*c = serio_raw->queue[serio_raw->tail];
+	serio_raw->tail = (serio_raw->tail + 1) % SERIO_RAW_QUEUE_LEN;
 
-	return !empty;
+	return true;
 }
 
 static ssize_t serio_raw_read(struct file *file, char __user *buffer,
@@ -200,40 +185,32 @@ static ssize_t serio_raw_write(struct file *file, const char __user *buffer,
 {
 	struct serio_raw_client *client = file->private_data;
 	struct serio_raw *serio_raw = client->serio_raw;
-	int retval = 0;
+	int written;
 	unsigned char c;
 
-	retval = mutex_lock_interruptible(&serio_raw_mutex);
-	if (retval)
-		return retval;
+	scoped_guard(mutex_intr, &serio_raw_mutex) {
+		if (serio_raw->dead)
+			return -ENODEV;
 
-	if (serio_raw->dead) {
-		retval = -ENODEV;
-		goto out;
-	}
+		if (count > 32)
+			count = 32;
 
-	if (count > 32)
-		count = 32;
+		while (count--) {
+			if (get_user(c, buffer++))
+				return -EFAULT;
 
-	while (count--) {
-		if (get_user(c, buffer++)) {
-			retval = -EFAULT;
-			goto out;
-		}
+			if (serio_write(serio_raw->serio, c)) {
+				/* Either signal error or partial write */
+				return written ?: -EIO;
+			}
 
-		if (serio_write(serio_raw->serio, c)) {
-			/* Either signal error or partial write */
-			if (retval == 0)
-				retval = -EIO;
-			goto out;
+			written++;
 		}
 
-		retval++;
+		return written;
 	}
 
-out:
-	mutex_unlock(&serio_raw_mutex);
-	return retval;
+	return -EINTR;
 }
 
 static __poll_t serio_raw_poll(struct file *file, poll_table *wait)
@@ -379,10 +356,10 @@ static void serio_raw_hangup(struct serio_raw *serio_raw)
 {
 	struct serio_raw_client *client;
 
-	serio_pause_rx(serio_raw->serio);
-	list_for_each_entry(client, &serio_raw->client_list, node)
-		kill_fasync(&client->fasync, SIGIO, POLL_HUP);
-	serio_continue_rx(serio_raw->serio);
+	scoped_guard(serio_pause_rx, serio_raw->serio) {
+		list_for_each_entry(client, &serio_raw->client_list, node)
+			kill_fasync(&client->fasync, SIGIO, POLL_HUP);
+	}
 
 	wake_up_interruptible(&serio_raw->wait);
 }
@@ -394,10 +371,10 @@ static void serio_raw_disconnect(struct serio *serio)
 
 	misc_deregister(&serio_raw->dev);
 
-	mutex_lock(&serio_raw_mutex);
-	serio_raw->dead = true;
-	list_del_init(&serio_raw->node);
-	mutex_unlock(&serio_raw_mutex);
+	scoped_guard(mutex, &serio_raw_mutex) {
+		serio_raw->dead = true;
+		list_del_init(&serio_raw->node);
+	}
 
 	serio_raw_hangup(serio_raw);
 

From d49e7d08f08eb2c553a83b408894aad3cb8ccf5e Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:26 -0700
Subject: [PATCH 0206/1530] Input: serio-raw - fix potential serio port name
 truncation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When compiling with W=1 the following warnings are triggered:

drivers/input/serio/serio_raw.c: In function ‘serio_raw_connect’:
drivers/input/serio/serio_raw.c:303:28: error: ‘%ld’ directive output may be truncated writing between 1 and 11 bytes into a region of size 7 [-Werror=format-truncation=]
  303 |                  "serio_raw%ld", (long)atomic_inc_return(&serio_raw_no));

atomic_inc_return() returns an int, so there is no reason to cast it
to long and print as such. Fix the issue by removing the cast,
printing it as unsigned decimal, and expanding the name from 16 to 20
bytes to accommodate the largest possible port number.

Link: https://lore.kernel.org/r/20240905041732.2034348-22-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/serio_raw.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/serio/serio_raw.c b/drivers/input/serio/serio_raw.c
index aef8301313b2c..e058fef07f576 100644
--- a/drivers/input/serio/serio_raw.c
+++ b/drivers/input/serio/serio_raw.c
@@ -29,7 +29,7 @@ struct serio_raw {
 	unsigned char queue[SERIO_RAW_QUEUE_LEN];
 	unsigned int tail, head;
 
-	char name[16];
+	char name[20];
 	struct kref kref;
 	struct serio *serio;
 	struct miscdevice dev;
@@ -277,7 +277,7 @@ static int serio_raw_connect(struct serio *serio, struct serio_driver *drv)
 	}
 
 	snprintf(serio_raw->name, sizeof(serio_raw->name),
-		 "serio_raw%ld", (long)atomic_inc_return(&serio_raw_no));
+		 "serio_raw%u", atomic_inc_return(&serio_raw_no));
 	kref_init(&serio_raw->kref);
 	INIT_LIST_HEAD(&serio_raw->client_list);
 	init_waitqueue_head(&serio_raw->wait);

From 6ed8b7cfc04d11c54ed00c3893b4e5f9ab9bd36f Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:27 -0700
Subject: [PATCH 0207/1530] Input: sun4i-ps2 - use guard notation when
 acquiring spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-23-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/sun4i-ps2.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/input/serio/sun4i-ps2.c b/drivers/input/serio/sun4i-ps2.c
index 95cd8aaee65da..267214ca9b51e 100644
--- a/drivers/input/serio/sun4i-ps2.c
+++ b/drivers/input/serio/sun4i-ps2.c
@@ -101,7 +101,7 @@ static irqreturn_t sun4i_ps2_interrupt(int irq, void *dev_id)
 	unsigned int rxflags = 0;
 	u32 rval;
 
-	spin_lock(&drvdata->lock);
+	guard(spinlock)(&drvdata->lock);
 
 	/* Get the PS/2 interrupts and clear them */
 	intr_status  = readl(drvdata->reg_base + PS2_REG_LSTS);
@@ -134,8 +134,6 @@ static irqreturn_t sun4i_ps2_interrupt(int irq, void *dev_id)
 	writel(intr_status, drvdata->reg_base + PS2_REG_LSTS);
 	writel(fifo_status, drvdata->reg_base + PS2_REG_FSTS);
 
-	spin_unlock(&drvdata->lock);
-
 	return IRQ_HANDLED;
 }
 
@@ -146,7 +144,6 @@ static int sun4i_ps2_open(struct serio *serio)
 	u32 clk_scdf;
 	u32 clk_pcdf;
 	u32 rval;
-	unsigned long flags;
 
 	/* Set line control and enable interrupt */
 	rval = PS2_LCTL_STOPERREN | PS2_LCTL_ACKERREN
@@ -171,9 +168,8 @@ static int sun4i_ps2_open(struct serio *serio)
 	rval = PS2_GCTL_RESET | PS2_GCTL_INTEN | PS2_GCTL_MASTER
 		| PS2_GCTL_BUSEN;
 
-	spin_lock_irqsave(&drvdata->lock, flags);
+	guard(spinlock_irqsave)(&drvdata->lock);
 	writel(rval, drvdata->reg_base + PS2_REG_GCTL);
-	spin_unlock_irqrestore(&drvdata->lock, flags);
 
 	return 0;
 }

From 54f951736d88e1c405b305a01fc921bd31907631 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:28 -0700
Subject: [PATCH 0208/1530] Input: userio - switch to using cleanup functions

Use __free() and guard() primitives to simplify the code and error
handling.

Link: https://lore.kernel.org/r/20240905041732.2034348-24-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/userio.c | 141 +++++++++++++++++------------------
 1 file changed, 70 insertions(+), 71 deletions(-)

diff --git a/drivers/input/serio/userio.c b/drivers/input/serio/userio.c
index a88e2eee55c35..66c9838a1fa79 100644
--- a/drivers/input/serio/userio.c
+++ b/drivers/input/serio/userio.c
@@ -55,18 +55,15 @@ struct userio_device {
 static int userio_device_write(struct serio *id, unsigned char val)
 {
 	struct userio_device *userio = id->port_data;
-	unsigned long flags;
 
-	spin_lock_irqsave(&userio->buf_lock, flags);
+	scoped_guard(spinlock_irqsave, &userio->buf_lock) {
+		userio->buf[userio->head] = val;
+		userio->head = (userio->head + 1) % USERIO_BUFSIZE;
 
-	userio->buf[userio->head] = val;
-	userio->head = (userio->head + 1) % USERIO_BUFSIZE;
-
-	if (userio->head == userio->tail)
-		dev_warn(userio_misc.this_device,
-			 "Buffer overflowed, userio client isn't keeping up");
-
-	spin_unlock_irqrestore(&userio->buf_lock, flags);
+		if (userio->head == userio->tail)
+			dev_warn(userio_misc.this_device,
+				 "Buffer overflowed, userio client isn't keeping up");
+	}
 
 	wake_up_interruptible(&userio->waitq);
 
@@ -75,9 +72,8 @@ static int userio_device_write(struct serio *id, unsigned char val)
 
 static int userio_char_open(struct inode *inode, struct file *file)
 {
-	struct userio_device *userio;
-
-	userio = kzalloc(sizeof(*userio), GFP_KERNEL);
+	struct userio_device *userio __free(kfree) =
+			kzalloc(sizeof(*userio), GFP_KERNEL);
 	if (!userio)
 		return -ENOMEM;
 
@@ -86,15 +82,13 @@ static int userio_char_open(struct inode *inode, struct file *file)
 	init_waitqueue_head(&userio->waitq);
 
 	userio->serio = kzalloc(sizeof(*userio->serio), GFP_KERNEL);
-	if (!userio->serio) {
-		kfree(userio);
+	if (!userio->serio)
 		return -ENOMEM;
-	}
 
 	userio->serio->write = userio_device_write;
-	userio->serio->port_data = userio;
+	userio->serio->port_data = userio;;
 
-	file->private_data = userio;
+	file->private_data = no_free_ptr(userio);
 
 	return 0;
 }
@@ -118,14 +112,32 @@ static int userio_char_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static size_t userio_fetch_data(struct userio_device *userio, u8 *buf,
+				size_t count, size_t *copylen)
+{
+	size_t available, len;
+
+	guard(spinlock_irqsave)(&userio->buf_lock);
+
+	available = CIRC_CNT_TO_END(userio->head, userio->tail,
+				    USERIO_BUFSIZE);
+	len = min(available, count);
+	if (len) {
+		memcpy(buf, &userio->buf[userio->tail], len);
+		userio->tail = (userio->tail + len) % USERIO_BUFSIZE;
+	}
+
+	*copylen = len;
+	return available;
+}
+
 static ssize_t userio_char_read(struct file *file, char __user *user_buffer,
 				size_t count, loff_t *ppos)
 {
 	struct userio_device *userio = file->private_data;
 	int error;
-	size_t nonwrap_len, copylen;
-	unsigned char buf[USERIO_BUFSIZE];
-	unsigned long flags;
+	size_t available, copylen;
+	u8 buf[USERIO_BUFSIZE];
 
 	/*
 	 * By the time we get here, the data that was waiting might have
@@ -135,21 +147,8 @@ static ssize_t userio_char_read(struct file *file, char __user *user_buffer,
 	 * of course).
 	 */
 	for (;;) {
-		spin_lock_irqsave(&userio->buf_lock, flags);
-
-		nonwrap_len = CIRC_CNT_TO_END(userio->head,
-					      userio->tail,
-					      USERIO_BUFSIZE);
-		copylen = min(nonwrap_len, count);
-		if (copylen) {
-			memcpy(buf, &userio->buf[userio->tail], copylen);
-			userio->tail = (userio->tail + copylen) %
-							USERIO_BUFSIZE;
-		}
-
-		spin_unlock_irqrestore(&userio->buf_lock, flags);
-
-		if (nonwrap_len)
+		available = userio_fetch_data(userio, buf, count, &copylen);
+		if (available)
 			break;
 
 		/* buffer was/is empty */
@@ -176,40 +175,21 @@ static ssize_t userio_char_read(struct file *file, char __user *user_buffer,
 	return copylen;
 }
 
-static ssize_t userio_char_write(struct file *file, const char __user *buffer,
-				 size_t count, loff_t *ppos)
+static int userio_execute_cmd(struct userio_device *userio,
+			      const struct userio_cmd *cmd)
 {
-	struct userio_device *userio = file->private_data;
-	struct userio_cmd cmd;
-	int error;
-
-	if (count != sizeof(cmd)) {
-		dev_warn(userio_misc.this_device, "Invalid payload size\n");
-		return -EINVAL;
-	}
-
-	if (copy_from_user(&cmd, buffer, sizeof(cmd)))
-		return -EFAULT;
-
-	error = mutex_lock_interruptible(&userio->mutex);
-	if (error)
-		return error;
-
-	switch (cmd.type) {
+	switch (cmd->type) {
 	case USERIO_CMD_REGISTER:
 		if (!userio->serio->id.type) {
 			dev_warn(userio_misc.this_device,
 				 "No port type given on /dev/userio\n");
-
-			error = -EINVAL;
-			goto out;
+			return -EINVAL;
 		}
 
 		if (userio->running) {
 			dev_warn(userio_misc.this_device,
 				 "Begin command sent, but we're already running\n");
-			error = -EBUSY;
-			goto out;
+			return -EBUSY;
 		}
 
 		userio->running = true;
@@ -220,32 +200,51 @@ static ssize_t userio_char_write(struct file *file, const char __user *buffer,
 		if (userio->running) {
 			dev_warn(userio_misc.this_device,
 				 "Can't change port type on an already running userio instance\n");
-			error = -EBUSY;
-			goto out;
+			return -EBUSY;
 		}
 
-		userio->serio->id.type = cmd.data;
+		userio->serio->id.type = cmd->data;
 		break;
 
 	case USERIO_CMD_SEND_INTERRUPT:
 		if (!userio->running) {
 			dev_warn(userio_misc.this_device,
 				 "The device must be registered before sending interrupts\n");
-			error = -ENODEV;
-			goto out;
+			return -ENODEV;
 		}
 
-		serio_interrupt(userio->serio, cmd.data, 0);
+		serio_interrupt(userio->serio, cmd->data, 0);
 		break;
 
 	default:
-		error = -EOPNOTSUPP;
-		goto out;
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static ssize_t userio_char_write(struct file *file, const char __user *buffer,
+				 size_t count, loff_t *ppos)
+{
+	struct userio_device *userio = file->private_data;
+	struct userio_cmd cmd;
+	int error;
+
+	if (count != sizeof(cmd)) {
+		dev_warn(userio_misc.this_device, "Invalid payload size\n");
+		return -EINVAL;
+	}
+
+	if (copy_from_user(&cmd, buffer, sizeof(cmd)))
+		return -EFAULT;
+
+	scoped_cond_guard(mutex_intr, return -EINTR, &userio->mutex) {
+		error = userio_execute_cmd(userio, &cmd);
+		if (error)
+			return error;
 	}
 
-out:
-	mutex_unlock(&userio->mutex);
-	return error ?: count;
+	return count;
 }
 
 static __poll_t userio_char_poll(struct file *file, poll_table *wait)

From c6dcd360384e47fad0c6d228d70a1543192b895f Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 4 Sep 2024 21:17:29 -0700
Subject: [PATCH 0209/1530] Input: xilinx_ps2 - use guard notation when
 acquiring spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/20240905041732.2034348-25-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/xilinx_ps2.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/input/serio/xilinx_ps2.c b/drivers/input/serio/xilinx_ps2.c
index 1543267d02acd..0316760168e57 100644
--- a/drivers/input/serio/xilinx_ps2.c
+++ b/drivers/input/serio/xilinx_ps2.c
@@ -155,22 +155,17 @@ static irqreturn_t xps2_interrupt(int irq, void *dev_id)
 static int sxps2_write(struct serio *pserio, unsigned char c)
 {
 	struct xps2data *drvdata = pserio->port_data;
-	unsigned long flags;
 	u32 sr;
-	int status = -1;
 
-	spin_lock_irqsave(&drvdata->lock, flags);
+	guard(spinlock_irqsave)(&drvdata->lock);
 
 	/* If the PS/2 transmitter is empty send a byte of data */
 	sr = in_be32(drvdata->base_address + XPS2_STATUS_OFFSET);
-	if (!(sr & XPS2_STATUS_TX_FULL)) {
-		out_be32(drvdata->base_address + XPS2_TX_DATA_OFFSET, c);
-		status = 0;
-	}
+	if (sr & XPS2_STATUS_TX_FULL)
+		return -EAGAIN;
 
-	spin_unlock_irqrestore(&drvdata->lock, flags);
-
-	return status;
+	out_be32(drvdata->base_address + XPS2_TX_DATA_OFFSET, c);
+	return 0;
 }
 
 /**

From 1ec46bf0e48a46e181f5c8efb4732127e2fddeee Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Tue, 10 Sep 2024 09:01:33 +0800
Subject: [PATCH 0210/1530] Input: matrix_keypad - remove duplicated include

The header files consumer.h is included twice in matrix_keypad.c,
so one inclusion of each can be removed.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=10823
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Link: https://lore.kernel.org/r/20240910010133.44579-1-yang.lee@linux.alibaba.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/matrix_keypad.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/input/keyboard/matrix_keypad.c b/drivers/input/keyboard/matrix_keypad.c
index a6bccb28d0794..2a3b3bfc2878b 100644
--- a/drivers/input/keyboard/matrix_keypad.c
+++ b/drivers/input/keyboard/matrix_keypad.c
@@ -17,7 +17,6 @@
 #include <linux/jiffies.h>
 #include <linux/module.h>
 #include <linux/gpio.h>
-#include <linux/gpio/consumer.h>
 #include <linux/input/matrix_keypad.h>
 #include <linux/slab.h>
 #include <linux/of.h>

From 3ca258994b32c486b0ed59307ec31ee413524598 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 4 Oct 2024 18:22:40 +0300
Subject: [PATCH 0211/1530] PCI: Simplify pci_create_slot() logic
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Simplify pci_create_slot() by splitting an "if" statement into two parts.
In order to not duplicate error handling, add a new label to handle kobj
put.

Link: https://lore.kernel.org/r/20241004152240.7926-1-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/slot.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index 0f87cade10f74..9ac5a4f267949 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -244,12 +244,13 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
 	slot = get_slot(parent, slot_nr);
 	if (slot) {
 		if (hotplug) {
-			if ((err = slot->hotplug ? -EBUSY : 0)
-			     || (err = rename_slot(slot, name))) {
-				kobject_put(&slot->kobj);
-				slot = NULL;
-				goto err;
+			if (slot->hotplug) {
+				err = -EBUSY;
+				goto put_slot;
 			}
+			err = rename_slot(slot, name);
+			if (err)
+				goto put_slot;
 		}
 		goto out;
 	}
@@ -278,10 +279,8 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
 
 	err = kobject_init_and_add(&slot->kobj, &pci_slot_ktype, NULL,
 				   "%s", slot_name);
-	if (err) {
-		kobject_put(&slot->kobj);
-		goto err;
-	}
+	if (err)
+		goto put_slot;
 
 	down_read(&pci_bus_sem);
 	list_for_each_entry(dev, &parent->devices, bus_list)
@@ -296,6 +295,9 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
 	kfree(slot_name);
 	mutex_unlock(&pci_slot_mutex);
 	return slot;
+
+put_slot:
+	kobject_put(&slot->kobj);
 err:
 	slot = ERR_PTR(err);
 	goto out;

From 1b57747e978f920fb2affd1952ed913276019115 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 14 Aug 2024 01:10:54 -0700
Subject: [PATCH 0212/1530] riscv: Enable cbo.zero only when all harts support
 Zicboz

Currently, we enable cbo.zero for usermode on each hart that supports
the Zicboz extension. This means that the [ms]envcfg CSR value may
differ between harts. Other features, such as pointer masking and CFI,
require setting [ms]envcfg bits on a per-thread basis. The combination
of these two adds quite some complexity and overhead to context
switching, as we would need to maintain two separate masks for the
per-hart and per-thread bits. Andrew Jones, who originally added Zicboz
support, writes[1][2]:

  I've approached Zicboz the same way I would approach all
  extensions, which is to be per-hart. I'm not currently aware of
  a platform that is / will be composed of harts where some have
  Zicboz and others don't, but there's nothing stopping a platform
  like that from being built.

  So, how about we add code that confirms Zicboz is on all harts.
  If any hart does not have it, then we complain loudly and disable
  it on all the other harts. If it was just a hardware description
  bug, then it'll get fixed. If there's actually a platform which
  doesn't have Zicboz on all harts, then, when the issue is reported,
  we can decide to not support it, support it with defconfig, or
  support it under a Kconfig guard which must be enabled by the user.

Let's follow his suggested solution and require the extension to be
available on all harts, so the envcfg CSR value does not need to change
when a thread migrates between harts. Since we are doing this for all
extensions with fields in envcfg, the CSR itself only needs to be saved/
restored when it is present on all harts.

This should not be a regression as no known hardware has asymmetric
Zicboz support, but if anyone reports seeing the warning, we will
re-evaluate our solution.

Link: https://lore.kernel.org/linux-riscv/20240322-168f191eeb8479b2ea169a5e@orel/ [1]
Link: https://lore.kernel.org/linux-riscv/20240323-28943722feb57a41fb0ff488@orel/ [2]
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Deepak Gupta <debug@rivosinc.com>
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Tested-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20240814081126.956287-2-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/cpufeature.c | 7 ++++++-
 arch/riscv/kernel/suspend.c    | 4 ++--
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 3a8eeaa9310c3..e560a253e99bd 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -28,6 +28,8 @@
 
 #define NUM_ALPHA_EXTS ('z' - 'a' + 1)
 
+static bool any_cpu_has_zicboz;
+
 unsigned long elf_hwcap __read_mostly;
 
 /* Host ISA bitmap */
@@ -98,6 +100,7 @@ static int riscv_ext_zicboz_validate(const struct riscv_isa_ext_data *data,
 		pr_err("Zicboz disabled as cboz-block-size present, but is not a power-of-2\n");
 		return -EINVAL;
 	}
+	any_cpu_has_zicboz = true;
 	return 0;
 }
 
@@ -919,8 +922,10 @@ unsigned long riscv_get_elf_hwcap(void)
 
 void riscv_user_isa_enable(void)
 {
-	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ))
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICBOZ))
 		csr_set(CSR_ENVCFG, ENVCFG_CBZE);
+	else if (any_cpu_has_zicboz)
+		pr_warn_once("Zicboz disabled as it is unavailable on some harts\n");
 }
 
 #ifdef CONFIG_RISCV_ALTERNATIVE
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
index c8cec0cc5833c..9a8a0dc035b26 100644
--- a/arch/riscv/kernel/suspend.c
+++ b/arch/riscv/kernel/suspend.c
@@ -14,7 +14,7 @@
 
 void suspend_save_csrs(struct suspend_context *context)
 {
-	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG))
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_XLINUXENVCFG))
 		context->envcfg = csr_read(CSR_ENVCFG);
 	context->tvec = csr_read(CSR_TVEC);
 	context->ie = csr_read(CSR_IE);
@@ -37,7 +37,7 @@ void suspend_save_csrs(struct suspend_context *context)
 void suspend_restore_csrs(struct suspend_context *context)
 {
 	csr_write(CSR_SCRATCH, 0);
-	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG))
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_XLINUXENVCFG))
 		csr_write(CSR_ENVCFG, context->envcfg);
 	csr_write(CSR_TVEC, context->tvec);
 	csr_write(CSR_IE, context->ie);

From 5fc7355f01376e69964bb21b685025b042c37acc Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 14 Aug 2024 01:10:55 -0700
Subject: [PATCH 0213/1530] riscv: Add support for per-thread envcfg CSR values

Some bits in the [ms]envcfg CSR, such as the CFI state and pointer
masking mode, need to be controlled on a per-thread basis. Support this
by keeping a copy of the CSR value in struct thread_struct and writing
it during context switches. It is safe to discard the old CSR value
during the context switch because the CSR is modified only by software,
so the CSR will remain in sync with the copy in thread_struct.

Use ALTERNATIVE directly instead of riscv_has_extension_unlikely() to
minimize branchiness in the context switching code.

Since thread_struct is copied during fork(), setting the value for the
init task sets the default value for all other threads.

Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Deepak Gupta <debug@rivosinc.com>
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20240814081126.956287-3-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/processor.h | 1 +
 arch/riscv/include/asm/switch_to.h | 8 ++++++++
 arch/riscv/kernel/cpufeature.c     | 2 +-
 3 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index efa1b3519b238..c1a4925088353 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -102,6 +102,7 @@ struct thread_struct {
 	unsigned long s[12];	/* s[0]: frame pointer */
 	struct __riscv_d_ext_state fstate;
 	unsigned long bad_cause;
+	unsigned long envcfg;
 	u32 riscv_v_flags;
 	u32 vstate_ctrl;
 	struct __riscv_v_ext_state vstate;
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index 7594df37cc9ff..9685cd85e57cc 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -70,6 +70,13 @@ static __always_inline bool has_fpu(void) { return false; }
 #define __switch_to_fpu(__prev, __next) do { } while (0)
 #endif
 
+static inline void __switch_to_envcfg(struct task_struct *next)
+{
+	asm volatile (ALTERNATIVE("nop", "csrw " __stringify(CSR_ENVCFG) ", %0",
+				  0, RISCV_ISA_EXT_XLINUXENVCFG, 1)
+			:: "r" (next->thread.envcfg) : "memory");
+}
+
 extern struct task_struct *__switch_to(struct task_struct *,
 				       struct task_struct *);
 
@@ -103,6 +110,7 @@ do {							\
 		__switch_to_vector(__prev, __next);	\
 	if (switch_to_should_flush_icache(__next))	\
 		local_flush_icache_all();		\
+	__switch_to_envcfg(__next);			\
 	((last) = __switch_to(__prev, __next));		\
 } while (0)
 
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index e560a253e99bd..27bafc5dd62df 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -923,7 +923,7 @@ unsigned long riscv_get_elf_hwcap(void)
 void riscv_user_isa_enable(void)
 {
 	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICBOZ))
-		csr_set(CSR_ENVCFG, ENVCFG_CBZE);
+		current->thread.envcfg |= ENVCFG_CBZE;
 	else if (any_cpu_has_zicboz)
 		pr_warn_once("Zicboz disabled as it is unavailable on some harts\n");
 }

From 368546ebe7e74cb6e18f17768533ab7077392a8c Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 14 Aug 2024 01:10:56 -0700
Subject: [PATCH 0214/1530] riscv: Call riscv_user_isa_enable() only on the
 boot hart

Now that the [ms]envcfg CSR value is maintained per thread, not per
hart, riscv_user_isa_enable() only needs to be called once during boot,
to set the value for the init task. This also allows it to be marked as
__init.

Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Deepak Gupta <debug@rivosinc.com>
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20240814081126.956287-4-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/cpufeature.h | 2 +-
 arch/riscv/kernel/cpufeature.c      | 4 ++--
 arch/riscv/kernel/smpboot.c         | 2 --
 3 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 45f9c1171a486..ce9a995730c14 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -31,7 +31,7 @@ DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo);
 /* Per-cpu ISA extensions. */
 extern struct riscv_isainfo hart_isa[NR_CPUS];
 
-void riscv_user_isa_enable(void);
+void __init riscv_user_isa_enable(void);
 
 #define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size, _validate) {	\
 	.name = #_name,									\
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 27bafc5dd62df..b3a057c36996f 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -920,12 +920,12 @@ unsigned long riscv_get_elf_hwcap(void)
 	return hwcap;
 }
 
-void riscv_user_isa_enable(void)
+void __init riscv_user_isa_enable(void)
 {
 	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICBOZ))
 		current->thread.envcfg |= ENVCFG_CBZE;
 	else if (any_cpu_has_zicboz)
-		pr_warn_once("Zicboz disabled as it is unavailable on some harts\n");
+		pr_warn("Zicboz disabled as it is unavailable on some harts\n");
 }
 
 #ifdef CONFIG_RISCV_ALTERNATIVE
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 0f8f1c95ac38c..e36d20205bd7d 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -233,8 +233,6 @@ asmlinkage __visible void smp_callin(void)
 	numa_add_cpu(curr_cpuid);
 	set_cpu_online(curr_cpuid, true);
 
-	riscv_user_isa_enable();
-
 	/*
 	 * Remote cache and TLB flushes are ignored while the CPU is offline,
 	 * so flush them both right now just in case.

From d3712b35f3c694cb932f87194caafc714109ea08 Mon Sep 17 00:00:00 2001
From: Sam Edwards <cfsworks@gmail.com>
Date: Thu, 3 Oct 2024 20:41:31 -0700
Subject: [PATCH 0215/1530] phy: usb: update Broadcom driver table to use
 designated initializers

The Broadcom USB PHY driver contains a lookup table
(`reg_bits_map_tables`) to resolve register bitmaps unique to certain
versions of the USB PHY as found in various Broadcom chip families.
Historically, this table was just kept carefully in sync with the
"selector" enum every time the latter changed to ensure consistency.
However, a recent commit [1] introduced two new enumerators but did not
adjust the array for BCM4908, thus breaking the xHCI controller (and
boot process) on this platform and revealing the fragility of this
approach.

Since these arrays are a little sparse (many elements are zero) and the
position of the array elements is significant only insofar as they agree
with the enumerators, designated initializers are a better fit than
positional initializers here. Convert this table accordingly.

[1] 4536fe9640b6 ("phy: usb: suppress OC condition for 7439b2")

Signed-off-by: Sam Edwards <CFSworks@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Justin Chen <justin.chen@broadcom.com>
Link: https://lore.kernel.org/r/20241004034131.1363813-3-CFSworks@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/broadcom/phy-brcm-usb-init.c | 435 +++++++++++------------
 1 file changed, 215 insertions(+), 220 deletions(-)

diff --git a/drivers/phy/broadcom/phy-brcm-usb-init.c b/drivers/phy/broadcom/phy-brcm-usb-init.c
index 5ebb3a6161157..da23078878a9b 100644
--- a/drivers/phy/broadcom/phy-brcm-usb-init.c
+++ b/drivers/phy/broadcom/phy-brcm-usb-init.c
@@ -193,256 +193,251 @@ static const u32
 usb_reg_bits_map_table[BRCM_FAMILY_COUNT][USB_CTRL_SELECTOR_COUNT] = {
 	/* 3390B0 */
 	[BRCM_FAMILY_3390A0] = {
-		USB_CTRL_SETUP_SCB1_EN_MASK,
-		USB_CTRL_SETUP_SCB2_EN_MASK,
-		USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK,
-		USB_CTRL_SETUP_STRAP_IPP_SEL_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_MASK,
-		0, /* USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK */
-		0, /* USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK */
-		USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK,
-		USB_CTRL_USB_PM_USB_PWRDN_MASK,
-		0, /* USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IOC_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IPP_MASK */
-		USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK,
-		0, /* USB_CTRL_USB_PM_SOFT_RESET_MASK */
-		0, /* USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_MASK */
-		0, /* USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_MASK */
-		USB_CTRL_USB_PM_USB20_HC_RESETB_VAR_MASK,
-		ENDIAN_SETTINGS, /* USB_CTRL_SETUP ENDIAN bits */
+		[USB_CTRL_SETUP_SCB1_EN_SELECTOR] =
+			USB_CTRL_SETUP_SCB1_EN_MASK,
+		[USB_CTRL_SETUP_SCB2_EN_SELECTOR] =
+			USB_CTRL_SETUP_SCB2_EN_MASK,
+		[USB_CTRL_SETUP_SS_EHCI64BIT_EN_SELECTOR] =
+			USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK,
+		[USB_CTRL_SETUP_STRAP_IPP_SEL_SELECTOR] =
+			USB_CTRL_SETUP_STRAP_IPP_SEL_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT0_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT1_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_MASK,
+		[USB_CTRL_USB_PM_XHC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK,
+		[USB_CTRL_USB_PM_USB_PWRDN_SELECTOR] =
+			USB_CTRL_USB_PM_USB_PWRDN_MASK,
+		[USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_SELECTOR] =
+			USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK,
+		[USB_CTRL_USB_PM_USB20_HC_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_USB20_HC_RESETB_VAR_MASK,
+		[USB_CTRL_SETUP_ENDIAN_SELECTOR] = ENDIAN_SETTINGS,
 	},
 	/* 4908 */
 	[BRCM_FAMILY_4908] = {
-		0, /* USB_CTRL_SETUP_SCB1_EN_MASK */
-		0, /* USB_CTRL_SETUP_SCB2_EN_MASK */
-		0, /* USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK */
-		0, /* USB_CTRL_SETUP_STRAP_IPP_SEL_MASK */
-		0, /* USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK */
-		0, /* USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK */
-		0, /* USB_CTRL_SETUP_OC3_DISABLE_MASK */
-		0, /* USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK */
-		0, /* USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK */
-		USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK,
-		USB_CTRL_USB_PM_USB_PWRDN_MASK,
-		0, /* USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IOC_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IPP_MASK */
-		0, /* USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK */
-		0, /* USB_CTRL_USB_PM_SOFT_RESET_MASK */
-		0, /* USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_MASK */
-		0, /* USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_MASK */
-		0, /* USB_CTRL_USB_PM_USB20_HC_RESETB_VAR_MASK */
-		0, /* USB_CTRL_SETUP ENDIAN bits */
+		[USB_CTRL_USB_PM_XHC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK,
+		[USB_CTRL_USB_PM_USB_PWRDN_SELECTOR] =
+			USB_CTRL_USB_PM_USB_PWRDN_MASK,
 	},
 	/* 7250b0 */
 	[BRCM_FAMILY_7250B0] = {
-		USB_CTRL_SETUP_SCB1_EN_MASK,
-		USB_CTRL_SETUP_SCB2_EN_MASK,
-		USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK,
-		0, /* USB_CTRL_SETUP_STRAP_IPP_SEL_MASK */
-		USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_MASK,
-		USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK,
-		0, /* USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK */
-		USB_CTRL_USB_PM_XHC_SOFT_RESETB_VAR_MASK,
-		0, /* USB_CTRL_USB_PM_USB_PWRDN_MASK */
-		0, /* USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IOC_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IPP_MASK */
-		0, /* USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK */
-		0, /* USB_CTRL_USB_PM_SOFT_RESET_MASK */
-		0, /* USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_MASK */
-		0, /* USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_MASK */
-		USB_CTRL_USB_PM_USB20_HC_RESETB_MASK,
-		ENDIAN_SETTINGS, /* USB_CTRL_SETUP ENDIAN bits */
+		[USB_CTRL_SETUP_SCB1_EN_SELECTOR] =
+			USB_CTRL_SETUP_SCB1_EN_MASK,
+		[USB_CTRL_SETUP_SCB2_EN_SELECTOR] =
+			USB_CTRL_SETUP_SCB2_EN_MASK,
+		[USB_CTRL_SETUP_SS_EHCI64BIT_EN_SELECTOR] =
+			USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT0_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT1_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_MASK,
+		[USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_SELECTOR] =
+			USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK,
+		[USB_CTRL_USB_PM_XHC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_XHC_SOFT_RESETB_VAR_MASK,
+		[USB_CTRL_USB_PM_USB20_HC_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_USB20_HC_RESETB_MASK,
+		[USB_CTRL_SETUP_ENDIAN_SELECTOR] = ENDIAN_SETTINGS,
 	},
 	/* 7271a0 */
 	[BRCM_FAMILY_7271A0] = {
-		0, /* USB_CTRL_SETUP_SCB1_EN_MASK */
-		0, /* USB_CTRL_SETUP_SCB2_EN_MASK */
-		USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK,
-		USB_CTRL_SETUP_STRAP_IPP_SEL_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_MASK,
-		0, /* USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK */
-		USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK,
-		USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK,
-		USB_CTRL_USB_PM_USB_PWRDN_MASK,
-		0, /* USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IOC_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IPP_MASK */
-		USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK,
-		USB_CTRL_USB_PM_SOFT_RESET_MASK,
-		USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_MASK,
-		USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_MASK,
-		USB_CTRL_USB_PM_USB20_HC_RESETB_VAR_MASK,
-		ENDIAN_SETTINGS, /* USB_CTRL_SETUP ENDIAN bits */
+		[USB_CTRL_SETUP_SS_EHCI64BIT_EN_SELECTOR] =
+			USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK,
+		[USB_CTRL_SETUP_STRAP_IPP_SEL_SELECTOR] =
+			USB_CTRL_SETUP_STRAP_IPP_SEL_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT0_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT1_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_MASK,
+		[USB_CTRL_USB_PM_BDC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK,
+		[USB_CTRL_USB_PM_XHC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK,
+		[USB_CTRL_USB_PM_USB_PWRDN_SELECTOR] =
+			USB_CTRL_USB_PM_USB_PWRDN_MASK,
+		[USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_SELECTOR] =
+			USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK,
+		[USB_CTRL_USB_PM_SOFT_RESET_SELECTOR] =
+			USB_CTRL_USB_PM_SOFT_RESET_MASK,
+		[USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_SELECTOR] =
+			USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_MASK,
+		[USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_SELECTOR] =
+			USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_MASK,
+		[USB_CTRL_USB_PM_USB20_HC_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_USB20_HC_RESETB_VAR_MASK,
+		[USB_CTRL_SETUP_ENDIAN_SELECTOR] = ENDIAN_SETTINGS,
 	},
 	/* 7364a0 */
 	[BRCM_FAMILY_7364A0] = {
-		USB_CTRL_SETUP_SCB1_EN_MASK,
-		USB_CTRL_SETUP_SCB2_EN_MASK,
-		USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK,
-		0, /* USB_CTRL_SETUP_STRAP_IPP_SEL_MASK */
-		USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_MASK,
-		USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK,
-		0, /* USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK */
-		USB_CTRL_USB_PM_XHC_SOFT_RESETB_VAR_MASK,
-		0, /* USB_CTRL_USB_PM_USB_PWRDN_MASK */
-		0, /* USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IOC_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IPP_MASK */
-		0, /* USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK */
-		0, /* USB_CTRL_USB_PM_SOFT_RESET_MASK */
-		0, /* USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_MASK */
-		0, /* USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_MASK */
-		USB_CTRL_USB_PM_USB20_HC_RESETB_MASK,
-		ENDIAN_SETTINGS, /* USB_CTRL_SETUP ENDIAN bits */
+		[USB_CTRL_SETUP_SCB1_EN_SELECTOR] =
+			USB_CTRL_SETUP_SCB1_EN_MASK,
+		[USB_CTRL_SETUP_SCB2_EN_SELECTOR] =
+			USB_CTRL_SETUP_SCB2_EN_MASK,
+		[USB_CTRL_SETUP_SS_EHCI64BIT_EN_SELECTOR] =
+			USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT0_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT1_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_MASK,
+		[USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_SELECTOR] =
+			USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK,
+		[USB_CTRL_USB_PM_XHC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_XHC_SOFT_RESETB_VAR_MASK,
+		[USB_CTRL_USB_PM_USB20_HC_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_USB20_HC_RESETB_MASK,
+		[USB_CTRL_SETUP_ENDIAN_SELECTOR] = ENDIAN_SETTINGS,
 	},
 	/* 7366c0 */
 	[BRCM_FAMILY_7366C0] = {
-		USB_CTRL_SETUP_SCB1_EN_MASK,
-		USB_CTRL_SETUP_SCB2_EN_MASK,
-		USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK,
-		0, /* USB_CTRL_SETUP_STRAP_IPP_SEL_MASK */
-		USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_MASK,
-		0, /* USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK */
-		0, /* USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK */
-		USB_CTRL_USB_PM_XHC_SOFT_RESETB_VAR_MASK,
-		USB_CTRL_USB_PM_USB_PWRDN_MASK,
-		0, /* USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IOC_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IPP_MASK */
-		0, /* USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK */
-		0, /* USB_CTRL_USB_PM_SOFT_RESET_MASK */
-		0, /* USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_MASK */
-		0, /* USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_MASK */
-		USB_CTRL_USB_PM_USB20_HC_RESETB_MASK,
-		ENDIAN_SETTINGS, /* USB_CTRL_SETUP ENDIAN bits */
+		[USB_CTRL_SETUP_SCB1_EN_SELECTOR] =
+			USB_CTRL_SETUP_SCB1_EN_MASK,
+		[USB_CTRL_SETUP_SCB2_EN_SELECTOR] =
+			USB_CTRL_SETUP_SCB2_EN_MASK,
+		[USB_CTRL_SETUP_SS_EHCI64BIT_EN_SELECTOR] =
+			USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT0_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT1_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_MASK,
+		[USB_CTRL_USB_PM_XHC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_XHC_SOFT_RESETB_VAR_MASK,
+		[USB_CTRL_USB_PM_USB_PWRDN_SELECTOR] =
+			USB_CTRL_USB_PM_USB_PWRDN_MASK,
+		[USB_CTRL_USB_PM_USB20_HC_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_USB20_HC_RESETB_MASK,
+		[USB_CTRL_SETUP_ENDIAN_SELECTOR] = ENDIAN_SETTINGS,
 	},
 	/* 74371A0 */
 	[BRCM_FAMILY_74371A0] = {
-		USB_CTRL_SETUP_SCB1_EN_MASK,
-		USB_CTRL_SETUP_SCB2_EN_MASK,
-		USB_CTRL_SETUP_SS_EHCI64BIT_EN_VAR_MASK,
-		0, /* USB_CTRL_SETUP_STRAP_IPP_SEL_MASK */
-		0, /* USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK */
-		0, /* USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK */
-		0, /* USB_CTRL_SETUP_OC3_DISABLE_MASK */
-		USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK,
-		0, /* USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK */
-		0, /* USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK */
-		0, /* USB_CTRL_USB_PM_USB_PWRDN_MASK */
-		USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_MASK,
-		USB_CTRL_USB30_CTL1_USB3_IOC_MASK,
-		USB_CTRL_USB30_CTL1_USB3_IPP_MASK,
-		0, /* USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK */
-		0, /* USB_CTRL_USB_PM_SOFT_RESET_MASK */
-		0, /* USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_MASK */
-		0, /* USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_MASK */
-		0, /* USB_CTRL_USB_PM_USB20_HC_RESETB_MASK */
-		ENDIAN_SETTINGS, /* USB_CTRL_SETUP ENDIAN bits */
+		[USB_CTRL_SETUP_SCB1_EN_SELECTOR] =
+			USB_CTRL_SETUP_SCB1_EN_MASK,
+		[USB_CTRL_SETUP_SCB2_EN_SELECTOR] =
+			USB_CTRL_SETUP_SCB2_EN_MASK,
+		[USB_CTRL_SETUP_SS_EHCI64BIT_EN_SELECTOR] =
+			USB_CTRL_SETUP_SS_EHCI64BIT_EN_VAR_MASK,
+		[USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_SELECTOR] =
+			USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK,
+		[USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_MASK,
+		[USB_CTRL_USB30_CTL1_USB3_IOC_SELECTOR] =
+			USB_CTRL_USB30_CTL1_USB3_IOC_MASK,
+		[USB_CTRL_USB30_CTL1_USB3_IPP_SELECTOR] =
+			USB_CTRL_USB30_CTL1_USB3_IPP_MASK,
+		[USB_CTRL_SETUP_ENDIAN_SELECTOR] = ENDIAN_SETTINGS,
 	},
 	/* 7439B0 */
 	[BRCM_FAMILY_7439B0] = {
-		USB_CTRL_SETUP_SCB1_EN_MASK,
-		USB_CTRL_SETUP_SCB2_EN_MASK,
-		USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK,
-		USB_CTRL_SETUP_STRAP_IPP_SEL_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_MASK,
-		0, /* USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK */
-		USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK,
-		USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK,
-		USB_CTRL_USB_PM_USB_PWRDN_MASK,
-		0, /* USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IOC_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IPP_MASK */
-		USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK,
-		0, /* USB_CTRL_USB_PM_SOFT_RESET_MASK */
-		0, /* USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_MASK */
-		0, /* USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_MASK */
-		USB_CTRL_USB_PM_USB20_HC_RESETB_VAR_MASK,
-		ENDIAN_SETTINGS, /* USB_CTRL_SETUP ENDIAN bits */
+		[USB_CTRL_SETUP_SCB1_EN_SELECTOR] =
+			USB_CTRL_SETUP_SCB1_EN_MASK,
+		[USB_CTRL_SETUP_SCB2_EN_SELECTOR] =
+			USB_CTRL_SETUP_SCB2_EN_MASK,
+		[USB_CTRL_SETUP_SS_EHCI64BIT_EN_SELECTOR] =
+			USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK,
+		[USB_CTRL_SETUP_STRAP_IPP_SEL_SELECTOR] =
+			USB_CTRL_SETUP_STRAP_IPP_SEL_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT0_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT1_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_MASK,
+		[USB_CTRL_USB_PM_BDC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK,
+		[USB_CTRL_USB_PM_XHC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK,
+		[USB_CTRL_USB_PM_USB_PWRDN_SELECTOR] =
+			USB_CTRL_USB_PM_USB_PWRDN_MASK,
+		[USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_SELECTOR] =
+			USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK,
+		[USB_CTRL_USB_PM_USB20_HC_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_USB20_HC_RESETB_VAR_MASK,
+		[USB_CTRL_SETUP_ENDIAN_SELECTOR] = ENDIAN_SETTINGS,
 	},
 	/* 7445d0 */
 	[BRCM_FAMILY_7445D0] = {
-		USB_CTRL_SETUP_SCB1_EN_MASK,
-		USB_CTRL_SETUP_SCB2_EN_MASK,
-		USB_CTRL_SETUP_SS_EHCI64BIT_EN_VAR_MASK,
-		0, /* USB_CTRL_SETUP_STRAP_IPP_SEL_MASK */
-		USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_MASK,
-		USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK,
-		0, /* USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK */
-		0, /* USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK */
-		0, /* USB_CTRL_USB_PM_USB_PWRDN_MASK */
-		USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_MASK,
-		0, /* USB_CTRL_USB30_CTL1_USB3_IOC_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IPP_MASK */
-		0, /* USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK */
-		0, /* USB_CTRL_USB_PM_SOFT_RESET_MASK */
-		0, /* USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_MASK */
-		0, /* USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_MASK */
-		USB_CTRL_USB_PM_USB20_HC_RESETB_VAR_MASK,
-		ENDIAN_SETTINGS, /* USB_CTRL_SETUP ENDIAN bits */
+		[USB_CTRL_SETUP_SCB1_EN_SELECTOR] =
+			USB_CTRL_SETUP_SCB1_EN_MASK,
+		[USB_CTRL_SETUP_SCB2_EN_SELECTOR] =
+			USB_CTRL_SETUP_SCB2_EN_MASK,
+		[USB_CTRL_SETUP_SS_EHCI64BIT_EN_SELECTOR] =
+			USB_CTRL_SETUP_SS_EHCI64BIT_EN_VAR_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT0_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT1_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_MASK,
+		[USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_SELECTOR] =
+			USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK,
+		[USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_MASK,
+		[USB_CTRL_USB_PM_USB20_HC_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_USB20_HC_RESETB_VAR_MASK,
+		[USB_CTRL_SETUP_ENDIAN_SELECTOR] = ENDIAN_SETTINGS,
 	},
 	/* 7260a0 */
 	[BRCM_FAMILY_7260A0] = {
-		0, /* USB_CTRL_SETUP_SCB1_EN_MASK */
-		0, /* USB_CTRL_SETUP_SCB2_EN_MASK */
-		USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK,
-		USB_CTRL_SETUP_STRAP_IPP_SEL_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_MASK,
-		0, /* USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK */
-		USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK,
-		USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK,
-		USB_CTRL_USB_PM_USB_PWRDN_MASK,
-		0, /* USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IOC_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IPP_MASK */
-		USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK,
-		USB_CTRL_USB_PM_SOFT_RESET_MASK,
-		USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_MASK,
-		USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_MASK,
-		USB_CTRL_USB_PM_USB20_HC_RESETB_VAR_MASK,
-		ENDIAN_SETTINGS, /* USB_CTRL_SETUP ENDIAN bits */
+		[USB_CTRL_SETUP_SS_EHCI64BIT_EN_SELECTOR] =
+			USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK,
+		[USB_CTRL_SETUP_STRAP_IPP_SEL_SELECTOR] =
+			USB_CTRL_SETUP_STRAP_IPP_SEL_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT0_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT1_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_MASK,
+		[USB_CTRL_USB_PM_BDC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK,
+		[USB_CTRL_USB_PM_XHC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK,
+		[USB_CTRL_USB_PM_USB_PWRDN_SELECTOR] =
+			USB_CTRL_USB_PM_USB_PWRDN_MASK,
+		[USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_SELECTOR] =
+			USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK,
+		[USB_CTRL_USB_PM_SOFT_RESET_SELECTOR] =
+			USB_CTRL_USB_PM_SOFT_RESET_MASK,
+		[USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_SELECTOR] =
+			USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_MASK,
+		[USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_SELECTOR] =
+			USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_MASK,
+		[USB_CTRL_USB_PM_USB20_HC_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_USB20_HC_RESETB_VAR_MASK,
+		[USB_CTRL_SETUP_ENDIAN_SELECTOR] = ENDIAN_SETTINGS,
 	},
 	/* 7278a0 */
 	[BRCM_FAMILY_7278A0] = {
-		0, /* USB_CTRL_SETUP_SCB1_EN_MASK */
-		0, /* USB_CTRL_SETUP_SCB2_EN_MASK */
-		0, /*USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK */
-		USB_CTRL_SETUP_STRAP_IPP_SEL_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
-		USB_CTRL_SETUP_OC3_DISABLE_MASK,
-		0, /* USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK */
-		USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK,
-		USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK,
-		USB_CTRL_USB_PM_USB_PWRDN_MASK,
-		0, /* USB_CTRL_USB30_CTL1_XHC_SOFT_RESETB_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IOC_MASK */
-		0, /* USB_CTRL_USB30_CTL1_USB3_IPP_MASK */
-		USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK,
-		USB_CTRL_USB_PM_SOFT_RESET_MASK,
-		0, /* USB_CTRL_SETUP_CC_DRD_MODE_ENABLE_MASK */
-		0, /* USB_CTRL_SETUP_STRAP_CC_DRD_MODE_ENABLE_SEL_MASK */
-		0, /* USB_CTRL_USB_PM_USB20_HC_RESETB_MASK */
-		0, /* USB_CTRL_SETUP ENDIAN bits */
+		[USB_CTRL_SETUP_STRAP_IPP_SEL_SELECTOR] =
+			USB_CTRL_SETUP_STRAP_IPP_SEL_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT0_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_PORT1_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK,
+		[USB_CTRL_SETUP_OC3_DISABLE_SELECTOR] =
+			USB_CTRL_SETUP_OC3_DISABLE_MASK,
+		[USB_CTRL_USB_PM_BDC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK,
+		[USB_CTRL_USB_PM_XHC_SOFT_RESETB_SELECTOR] =
+			USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK,
+		[USB_CTRL_USB_PM_USB_PWRDN_SELECTOR] =
+			USB_CTRL_USB_PM_USB_PWRDN_MASK,
+		[USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_SELECTOR] =
+			USB_CTRL_USB_DEVICE_CTL1_PORT_MODE_MASK,
+		[USB_CTRL_USB_PM_SOFT_RESET_SELECTOR] =
+			USB_CTRL_USB_PM_SOFT_RESET_MASK,
 	},
 };
 

From 449d2a523a0c3ca8f4c993b8e37795c2aa174da6 Mon Sep 17 00:00:00 2001
From: Dragan Simic <dsimic@manjaro.org>
Date: Thu, 5 Sep 2024 10:28:22 +0200
Subject: [PATCH 0216/1530] phy: phy-rockchip-inno-usb2: Perform trivial code
 cleanups

Perform a few trivial code cleanups, e.g. to obey the reverse Christmas tree
rule, to avoid use of "{ ... }" code blocks where they aren't really needed,
or to avoid line wrapping by using the 100-column width better.

No intended functional changes are introduced by these code cleanups.

Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Dragan Simic <dsimic@manjaro.org>
Link: https://lore.kernel.org/r/adce7309f6fd9e1191c53bab552a8531d1a71216.1725524802.git.dsimic@manjaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/rockchip/phy-rockchip-inno-usb2.c | 26 +++++++------------
 1 file changed, 9 insertions(+), 17 deletions(-)

diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
index 4f71373ae6e1a..03b772200fed1 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
@@ -418,9 +418,9 @@ rockchip_usb2phy_clk480m_register(struct rockchip_usb2phy *rphy)
 
 static int rockchip_usb2phy_extcon_register(struct rockchip_usb2phy *rphy)
 {
-	int ret;
 	struct device_node *node = rphy->dev->of_node;
 	struct extcon_dev *edev;
+	int ret;
 
 	if (of_property_read_bool(node, "extcon")) {
 		edev = extcon_get_edev_by_phandle(rphy->dev, 0);
@@ -1327,7 +1327,7 @@ static int rockchip_usb2phy_probe(struct platform_device *pdev)
 	struct rockchip_usb2phy *rphy;
 	const struct rockchip_usb2phy_cfg *phy_cfgs;
 	unsigned int reg;
-	int index, ret;
+	int index = 0, ret;
 
 	rphy = devm_kzalloc(dev, sizeof(*rphy), GFP_KERNEL);
 	if (!rphy)
@@ -1339,9 +1339,7 @@ static int rockchip_usb2phy_probe(struct platform_device *pdev)
 			dev_err(dev, "failed to locate usbgrf\n");
 			return PTR_ERR(rphy->grf);
 		}
-	}
-
-	else {
+	} else {
 		rphy->grf = syscon_node_to_regmap(dev->parent->of_node);
 		if (IS_ERR(rphy->grf))
 			return PTR_ERR(rphy->grf);
@@ -1358,16 +1356,14 @@ static int rockchip_usb2phy_probe(struct platform_device *pdev)
 	}
 
 	if (of_property_read_u32_index(np, "reg", 0, &reg)) {
-		dev_err(dev, "the reg property is not assigned in %pOFn node\n",
-			np);
+		dev_err(dev, "the reg property is not assigned in %pOFn node\n", np);
 		return -EINVAL;
 	}
 
 	/* support address_cells=2 */
 	if (of_property_count_u32_elems(np, "reg") > 2 && reg == 0) {
 		if (of_property_read_u32_index(np, "reg", 1, &reg)) {
-			dev_err(dev, "the reg property is not assigned in %pOFn node\n",
-				np);
+			dev_err(dev, "the reg property is not assigned in %pOFn node\n", np);
 			return -EINVAL;
 		}
 	}
@@ -1386,8 +1382,7 @@ static int rockchip_usb2phy_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	/* find out a proper config which can be matched with dt. */
-	index = 0;
+	/* find a proper config that can be matched with the DT */
 	do {
 		if (phy_cfgs[index].reg == reg) {
 			rphy->phy_cfg = &phy_cfgs[index];
@@ -1407,10 +1402,9 @@ static int rockchip_usb2phy_probe(struct platform_device *pdev)
 		return PTR_ERR(rphy->phy_reset);
 
 	rphy->clk = devm_clk_get_optional_enabled(dev, "phyclk");
-	if (IS_ERR(rphy->clk)) {
+	if (IS_ERR(rphy->clk))
 		return dev_err_probe(&pdev->dev, PTR_ERR(rphy->clk),
 				     "failed to get phyclk\n");
-	}
 
 	ret = rockchip_usb2phy_clk480m_register(rphy);
 	if (ret) {
@@ -1446,13 +1440,11 @@ static int rockchip_usb2phy_probe(struct platform_device *pdev)
 
 		/* initialize otg/host port separately */
 		if (of_node_name_eq(child_np, "host-port")) {
-			ret = rockchip_usb2phy_host_port_init(rphy, rport,
-							      child_np);
+			ret = rockchip_usb2phy_host_port_init(rphy, rport, child_np);
 			if (ret)
 				goto put_child;
 		} else {
-			ret = rockchip_usb2phy_otg_port_init(rphy, rport,
-							     child_np);
+			ret = rockchip_usb2phy_otg_port_init(rphy, rport, child_np);
 			if (ret)
 				goto put_child;
 		}

From 595ad7a336bf21f9d111a033820cd95d70343bd1 Mon Sep 17 00:00:00 2001
From: Dragan Simic <dsimic@manjaro.org>
Date: Thu, 5 Sep 2024 10:28:23 +0200
Subject: [PATCH 0217/1530] phy: phy-rockchip-inno-usb2: Handle failed extcon
 allocation better

Return the actual error code upon failure to allocate extcon device, instead
of hardcoding -ENOMEM.  Use dev_err_probe() to also log appropriate messages,
which is fine because the containing function is used in the probe path.

Helped-by: Heiko Stubner <heiko@sntech.de>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Dragan Simic <dsimic@manjaro.org>
Link: https://lore.kernel.org/r/cc4995aa3e569be6bc23ca126b41fba82d50eeee.1725524802.git.dsimic@manjaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/rockchip/phy-rockchip-inno-usb2.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
index 03b772200fed1..cf6b67dd9f10c 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
@@ -435,7 +435,8 @@ static int rockchip_usb2phy_extcon_register(struct rockchip_usb2phy *rphy)
 						rockchip_usb2phy_extcon_cable);
 
 		if (IS_ERR(edev))
-			return -ENOMEM;
+			return dev_err_probe(rphy->dev, PTR_ERR(edev),
+					     "failed to allocate extcon device\n");
 
 		ret = devm_extcon_dev_register(rphy->dev, edev);
 		if (ret) {

From 40452520850683f6771094ca218ff206d1fcb022 Mon Sep 17 00:00:00 2001
From: Dragan Simic <dsimic@manjaro.org>
Date: Thu, 5 Sep 2024 10:28:24 +0200
Subject: [PATCH 0218/1530] phy: phy-rockchip-inno-usb2: Use dev_err_probe() in
 the probe path

Improve error handling in the probe path by using function dev_err_probe()
instead of function dev_err(), where appropriate.

Signed-off-by: Dragan Simic <dsimic@manjaro.org>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/r/d4ccd9fc278fb46ea868406bf77811ee507f0e4e.1725524803.git.dsimic@manjaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/rockchip/phy-rockchip-inno-usb2.c | 27 +++++++------------
 1 file changed, 10 insertions(+), 17 deletions(-)

diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
index cf6b67dd9f10c..6e5214862b8a3 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
@@ -424,11 +424,9 @@ static int rockchip_usb2phy_extcon_register(struct rockchip_usb2phy *rphy)
 
 	if (of_property_read_bool(node, "extcon")) {
 		edev = extcon_get_edev_by_phandle(rphy->dev, 0);
-		if (IS_ERR(edev)) {
-			if (PTR_ERR(edev) != -EPROBE_DEFER)
-				dev_err(rphy->dev, "Invalid or missing extcon\n");
-			return PTR_ERR(edev);
-		}
+		if (IS_ERR(edev))
+			return dev_err_probe(rphy->dev, PTR_ERR(edev),
+					     "invalid or missing extcon\n");
 	} else {
 		/* Initialize extcon device */
 		edev = devm_extcon_dev_allocate(rphy->dev,
@@ -439,10 +437,9 @@ static int rockchip_usb2phy_extcon_register(struct rockchip_usb2phy *rphy)
 					     "failed to allocate extcon device\n");
 
 		ret = devm_extcon_dev_register(rphy->dev, edev);
-		if (ret) {
-			dev_err(rphy->dev, "failed to register extcon device\n");
-			return ret;
-		}
+		if (ret)
+			return dev_err_probe(rphy->dev, ret,
+					     "failed to register extcon device\n");
 	}
 
 	rphy->edev = edev;
@@ -1408,10 +1405,8 @@ static int rockchip_usb2phy_probe(struct platform_device *pdev)
 				     "failed to get phyclk\n");
 
 	ret = rockchip_usb2phy_clk480m_register(rphy);
-	if (ret) {
-		dev_err(dev, "failed to register 480m output clock\n");
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to register 480m output clock\n");
 
 	if (rphy->phy_cfg->phy_tuning) {
 		ret = rphy->phy_cfg->phy_tuning(rphy);
@@ -1431,8 +1426,7 @@ static int rockchip_usb2phy_probe(struct platform_device *pdev)
 
 		phy = devm_phy_create(dev, child_np, &rockchip_usb2phy_ops);
 		if (IS_ERR(phy)) {
-			dev_err_probe(dev, PTR_ERR(phy), "failed to create phy\n");
-			ret = PTR_ERR(phy);
+			ret = dev_err_probe(dev, PTR_ERR(phy), "failed to create phy\n");
 			goto put_child;
 		}
 
@@ -1467,8 +1461,7 @@ static int rockchip_usb2phy_probe(struct platform_device *pdev)
 						"rockchip_usb2phy",
 						rphy);
 		if (ret) {
-			dev_err(rphy->dev,
-				"failed to request usb2phy irq handle\n");
+			dev_err_probe(rphy->dev, ret, "failed to request usb2phy irq handle\n");
 			goto put_child;
 		}
 	}

From d6c496f05e98c6d25ac73f23fd0075913620de56 Mon Sep 17 00:00:00 2001
From: Josua Mayer <josua@solid-run.com>
Date: Wed, 2 Oct 2024 17:04:40 +0300
Subject: [PATCH 0219/1530] phy: mvebu-cp110-utmi: support swapping d+/d- lanes
 by dts property

CP11x UTMI PHY supports swapping D+/D- signals via digital control
register 1.

Add support for the "swap-dx-lanes" device-tree property, which lists
the port-ids that should swap D+ and D-.
The property is evaluated in probe and applied before power-on
during mvebu_cp110_utmi_port_setup.

Signed-off-by: Josua Mayer <josua@solid-run.com>
Link: https://lore.kernel.org/r/20241002-mvebu-utmi-phy-v4-1-83783dc89b9d@solid-run.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/marvell/phy-mvebu-cp110-utmi.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/phy/marvell/phy-mvebu-cp110-utmi.c b/drivers/phy/marvell/phy-mvebu-cp110-utmi.c
index 4922a5f3327d5..59903f86b13f5 100644
--- a/drivers/phy/marvell/phy-mvebu-cp110-utmi.c
+++ b/drivers/phy/marvell/phy-mvebu-cp110-utmi.c
@@ -62,6 +62,8 @@
 #define   SQ_AMP_CAL_MASK			GENMASK(2, 0)
 #define   SQ_AMP_CAL_VAL			1
 #define   SQ_AMP_CAL_EN				BIT(3)
+#define UTMI_DIG_CTRL1_REG			0x20
+#define   SWAP_DPDM				BIT(15)
 #define UTMI_CTRL_STATUS0_REG			0x24
 #define   SUSPENDM				BIT(22)
 #define   TEST_SEL				BIT(25)
@@ -99,11 +101,13 @@ struct mvebu_cp110_utmi {
  * @priv: PHY driver data
  * @id: PHY port ID
  * @dr_mode: PHY connection: USB_DR_MODE_HOST or USB_DR_MODE_PERIPHERAL
+ * @swap_dx: whether to swap d+/d- signals
  */
 struct mvebu_cp110_utmi_port {
 	struct mvebu_cp110_utmi *priv;
 	u32 id;
 	enum usb_dr_mode dr_mode;
+	bool swap_dx;
 };
 
 static void mvebu_cp110_utmi_port_setup(struct mvebu_cp110_utmi_port *port)
@@ -159,6 +163,13 @@ static void mvebu_cp110_utmi_port_setup(struct mvebu_cp110_utmi_port *port)
 	reg &= ~(VDAT_MASK | VSRC_MASK);
 	reg |= (VDAT_VAL << VDAT_OFFSET) | (VSRC_VAL << VSRC_OFFSET);
 	writel(reg, PORT_REGS(port) + UTMI_CHGDTC_CTRL_REG);
+
+	/* Swap D+/D- */
+	reg = readl(PORT_REGS(port) + UTMI_DIG_CTRL1_REG);
+	reg &= ~(SWAP_DPDM);
+	if (port->swap_dx)
+		reg |= SWAP_DPDM;
+	writel(reg, PORT_REGS(port) + UTMI_DIG_CTRL1_REG);
 }
 
 static int mvebu_cp110_utmi_phy_power_off(struct phy *phy)
@@ -286,6 +297,7 @@ static int mvebu_cp110_utmi_phy_probe(struct platform_device *pdev)
 	struct phy_provider *provider;
 	struct device_node *child;
 	u32 usb_devices = 0;
+	u32 swap_dx = 0;
 
 	utmi = devm_kzalloc(dev, sizeof(*utmi), GFP_KERNEL);
 	if (!utmi)
@@ -345,6 +357,10 @@ static int mvebu_cp110_utmi_phy_probe(struct platform_device *pdev)
 			}
 		}
 
+		of_property_for_each_u32(dev->of_node, "swap-dx-lanes", swap_dx)
+			if (swap_dx == port_id)
+				port->swap_dx = 1;
+
 		/* Retrieve PHY capabilities */
 		utmi->ops = &mvebu_cp110_utmi_phy_ops;
 

From 8c7e955fac07ee11c76ddf2330587fe083fab1a2 Mon Sep 17 00:00:00 2001
From: Christian Bruel <christian.bruel@foss.st.com>
Date: Mon, 30 Sep 2024 19:08:43 +0200
Subject: [PATCH 0220/1530] dt-bindings: phy: Add STM32MP25 COMBOPHY bindings

Document the bindings for STM32 COMBOPHY interface, used to support
the PCIe and USB3 stm32mp25 drivers.
Following entries can be used to tune caracterisation parameters
 - st,output-micro-ohms and st,output-vswing-microvolt bindings entries
to tune the impedance and voltage swing using discrete simulation results
 - st,rx-equalizer register to set the internal rx equalizer filter value.

Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Christian Bruel <christian.bruel@foss.st.com>
Link: https://lore.kernel.org/r/20240930170847.948779-2-christian.bruel@foss.st.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../bindings/phy/st,stm32mp25-combophy.yaml   | 119 ++++++++++++++++++
 1 file changed, 119 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/phy/st,stm32mp25-combophy.yaml

diff --git a/Documentation/devicetree/bindings/phy/st,stm32mp25-combophy.yaml b/Documentation/devicetree/bindings/phy/st,stm32mp25-combophy.yaml
new file mode 100644
index 0000000000000..a2e82c0bb56b4
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/st,stm32mp25-combophy.yaml
@@ -0,0 +1,119 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/st,stm32mp25-combophy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: STMicroelectronics STM32MP25 USB3/PCIe COMBOPHY
+
+maintainers:
+  - Christian Bruel <christian.bruel@foss.st.com>
+
+description:
+  Single lane PHY shared (exclusive) between the USB3 and PCIe controllers.
+  Supports 5Gbit/s for USB3 and PCIe gen2 or 2.5Gbit/s for PCIe gen1.
+
+properties:
+  compatible:
+    const: st,stm32mp25-combophy
+
+  reg:
+    maxItems: 1
+
+  "#phy-cells":
+    const: 1
+
+  clocks:
+    minItems: 2
+    items:
+      - description: apb Bus clock mandatory to access registers.
+      - description: ker Internal RCC reference clock for USB3 or PCIe
+      - description: pad Optional on board clock input for PCIe only. Typically an
+                     external 100Mhz oscillator wired on dedicated CLKIN pad. Used as reference
+                     clock input instead of the ker
+
+  clock-names:
+    minItems: 2
+    items:
+      - const: apb
+      - const: ker
+      - const: pad
+
+  resets:
+    maxItems: 1
+
+  reset-names:
+    const: phy
+
+  power-domains:
+    maxItems: 1
+
+  wakeup-source: true
+
+  interrupts:
+    maxItems: 1
+    description: interrupt used for wakeup
+
+  access-controllers:
+    maxItems: 1
+    description: Phandle to the rifsc device to check access right.
+
+  st,ssc-on:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description:
+      A property whose presence indicates that the Spread Spectrum Clocking is active.
+
+  st,rx-equalizer:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 0
+    maximum: 7
+    default: 2
+    description:
+      A 3 bit value to tune the RX fixed equalizer setting for optimal eye compliance
+
+  st,output-micro-ohms:
+    minimum: 3999000
+    maximum: 6090000
+    default: 4968000
+    description:
+      A value property to tune the Single Ended Output Impedance, simulations results
+      at 25C for a VDDP=0.8V. The hardware accepts discrete values in this range.
+
+  st,output-vswing-microvolt:
+    minimum: 442000
+    maximum: 803000
+    default: 803000
+    description:
+      A value property in microvolt to tune the Single Ended Output Voltage Swing to change the
+      Vlo, Vhi for a VDDP = 0.8V. The hardware accepts discrete values in this range.
+
+required:
+  - compatible
+  - reg
+  - "#phy-cells"
+  - clocks
+  - clock-names
+  - resets
+  - reset-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/st,stm32mp25-rcc.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/reset/st,stm32mp25-rcc.h>
+
+    phy@480c0000 {
+        compatible = "st,stm32mp25-combophy";
+        reg = <0x480c0000 0x1000>;
+        #phy-cells = <1>;
+        clocks = <&rcc CK_BUS_USB3PCIEPHY>, <&rcc CK_KER_USB3PCIEPHY>;
+        clock-names = "apb", "ker";
+        resets = <&rcc USB3PCIEPHY_R>;
+        reset-names = "phy";
+        access-controllers = <&rifsc 67>;
+        power-domains = <&CLUSTER_PD>;
+        wakeup-source;
+        interrupts-extended = <&exti1 45 IRQ_TYPE_EDGE_FALLING>;
+    };

From 47e1bb6b4ba0987139ab790efa03c542ebc1b10d Mon Sep 17 00:00:00 2001
From: Christian Bruel <christian.bruel@foss.st.com>
Date: Mon, 30 Sep 2024 19:08:44 +0200
Subject: [PATCH 0221/1530] phy: stm32: Add support for STM32MP25 COMBOPHY.

Addition of the COMBOPHY driver found on STM32MP25 platforms

This single lane PHY is shared (exclusive) between the USB3 and PCIE
controllers.
Supports 5Gbit/s for PCIE gen2 or 2.5Gbit/s for PCIE gen1.

Supports wakeup-source capability to wakeup system using remote-wakeup
capable USB device

Signed-off-by: Christian Bruel <christian.bruel@foss.st.com>
Link: https://lore.kernel.org/r/20240930170847.948779-3-christian.bruel@foss.st.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/st/Kconfig              |  11 +
 drivers/phy/st/Makefile             |   1 +
 drivers/phy/st/phy-stm32-combophy.c | 598 ++++++++++++++++++++++++++++
 3 files changed, 610 insertions(+)
 create mode 100644 drivers/phy/st/phy-stm32-combophy.c

diff --git a/drivers/phy/st/Kconfig b/drivers/phy/st/Kconfig
index 3fc3d0781fb8a..304614b6dabfc 100644
--- a/drivers/phy/st/Kconfig
+++ b/drivers/phy/st/Kconfig
@@ -33,6 +33,17 @@ config PHY_STIH407_USB
 	  Enable this support to enable the picoPHY device used by USB2
 	  and USB3 controllers on STMicroelectronics STiH407 SoC families.
 
+config PHY_STM32_COMBOPHY
+	tristate "STMicroelectronics COMBOPHY driver for STM32MP25"
+	depends on ARCH_STM32 || COMPILE_TEST
+	select GENERIC_PHY
+	help
+	  Enable this to support the COMBOPHY device used by USB3 or PCIe
+	  controllers on STMicroelectronics STM32MP25 SoC.
+	  This driver controls the COMBOPHY block to generate the PCIe 100Mhz
+	  reference clock from either the external clock generator or HSE
+	  internal SoC clock source.
+
 config PHY_STM32_USBPHYC
 	tristate "STMicroelectronics STM32 USB HS PHY Controller driver"
 	depends on ARCH_STM32 || COMPILE_TEST
diff --git a/drivers/phy/st/Makefile b/drivers/phy/st/Makefile
index c862dd937b647..cb80e954ea9f0 100644
--- a/drivers/phy/st/Makefile
+++ b/drivers/phy/st/Makefile
@@ -3,4 +3,5 @@ obj-$(CONFIG_PHY_MIPHY28LP) 		+= phy-miphy28lp.o
 obj-$(CONFIG_PHY_ST_SPEAR1310_MIPHY)	+= phy-spear1310-miphy.o
 obj-$(CONFIG_PHY_ST_SPEAR1340_MIPHY)	+= phy-spear1340-miphy.o
 obj-$(CONFIG_PHY_STIH407_USB)		+= phy-stih407-usb.o
+obj-$(CONFIG_PHY_STM32_COMBOPHY)	+= phy-stm32-combophy.o
 obj-$(CONFIG_PHY_STM32_USBPHYC) 	+= phy-stm32-usbphyc.o
diff --git a/drivers/phy/st/phy-stm32-combophy.c b/drivers/phy/st/phy-stm32-combophy.c
new file mode 100644
index 0000000000000..e1e7083ccb5f4
--- /dev/null
+++ b/drivers/phy/st/phy-stm32-combophy.c
@@ -0,0 +1,598 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * STMicroelectronics COMBOPHY STM32MP25 Controller driver.
+ *
+ * Copyright (C) 2024 STMicroelectronics
+ * Author: Christian Bruel <christian.bruel@foss.st.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/mfd/syscon.h>
+#include <linux/platform_device.h>
+#include <linux/phy/phy.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include <linux/reset.h>
+#include <dt-bindings/phy/phy.h>
+
+#define SYSCFG_COMBOPHY_CR1 0x4c00
+#define SYSCFG_COMBOPHY_CR2 0x4c04
+#define SYSCFG_COMBOPHY_CR4 0x4c0c
+#define SYSCFG_COMBOPHY_CR5 0x4c10
+#define SYSCFG_COMBOPHY_SR  0x4c14
+#define SYSCFG_PCIEPRGCR    0x6080
+
+/* SYSCFG PCIEPRGCR */
+#define STM32MP25_PCIEPRGCR_EN	  BIT(0)
+#define STM32MP25_PCIEPRG_IMPCTRL_OHM     GENMASK(3, 1)
+#define STM32MP25_PCIEPRG_IMPCTRL_VSWING  GENMASK(5, 4)
+
+/* SYSCFG SYSCFG_COMBOPHY_SR */
+#define STM32MP25_PIPE0_PHYSTATUS BIT(1)
+
+/* SYSCFG CR1 */
+#define SYSCFG_COMBOPHY_CR1_REFUSEPAD BIT(0)
+#define SYSCFG_COMBOPHY_CR1_MPLLMULT GENMASK(7, 1)
+#define SYSCFG_COMBOPHY_CR1_REFCLKSEL GENMASK(16, 8)
+#define SYSCFG_COMBOPHY_CR1_REFCLKDIV2 BIT(17)
+#define SYSCFG_COMBOPHY_CR1_REFSSPEN BIT(18)
+#define SYSCFG_COMBOPHY_CR1_SSCEN BIT(19)
+
+/* SYSCFG CR4 */
+#define SYSCFG_COMBOPHY_CR4_RX0_EQ GENMASK(2, 0)
+
+#define MPLLMULT_19_2 (0x02u << 1)
+#define MPLLMULT_20   (0x7du << 1)
+#define MPLLMULT_24   (0x68u << 1)
+#define MPLLMULT_25   (0x64u << 1)
+#define MPLLMULT_26   (0x60u << 1)
+#define MPLLMULT_38_4 (0x41u << 1)
+#define MPLLMULT_48   (0x6cu << 1)
+#define MPLLMULT_50   (0x32u << 1)
+#define MPLLMULT_52   (0x30u << 1)
+#define MPLLMULT_100  (0x19u << 1)
+
+#define REFCLKSEL_0   0
+#define REFCLKSEL_1   (0x108u << 8)
+
+#define REFCLDIV_0    0
+
+/* SYSCFG CR2 */
+#define SYSCFG_COMBOPHY_CR2_MODESEL GENMASK(1, 0)
+#define SYSCFG_COMBOPHY_CR2_ISO_DIS BIT(15)
+
+#define COMBOPHY_MODESEL_PCIE 0
+#define COMBOPHY_MODESEL_USB  3
+
+/* SYSCFG CR5 */
+#define SYSCFG_COMBOPHY_CR5_COMMON_CLOCKS BIT(12)
+
+#define COMBOPHY_SUP_ANA_MPLL_LOOP_CTL 0xc0
+#define COMBOPHY_PROP_CNTRL GENMASK(7, 4)
+
+/* Required apb/ker clocks first, optional pad last. */
+static const char * const combophy_clks[] = {"apb", "ker", "pad"};
+#define APB_CLK 0
+#define KER_CLK 1
+#define PAD_CLK 2
+
+struct stm32_combophy {
+	struct phy *phy;
+	struct regmap *regmap;
+	struct device *dev;
+	void __iomem *base;
+	struct reset_control *phy_reset;
+	struct clk_bulk_data clks[ARRAY_SIZE(combophy_clks)];
+	int num_clks;
+	bool have_pad_clk;
+	unsigned int type;
+	bool is_init;
+	int irq_wakeup;
+};
+
+struct clk_impedance  {
+	u32 microohm;
+	u32 vswing[4];
+};
+
+/*
+ * lookup table to hold the settings needed for a ref clock frequency
+ * impedance, the offset is used to set the IMP_CTL and DE_EMP bit of the
+ * PRG_IMP_CTRL register. Use ordered discrete values in the table
+ */
+static const struct clk_impedance imp_lookup[] = {
+	{ 6090000, { 442000, 564000, 684000, 802000 } },
+	{ 5662000, { 528000, 621000, 712000, 803000 } },
+	{ 5292000, { 491000, 596000, 700000, 802000 } },
+	{ 4968000, { 558000, 640000, 722000, 803000 } },
+	{ 4684000, { 468000, 581000, 692000, 802000 } },
+	{ 4429000, { 554000, 613000, 717000, 803000 } },
+	{ 4204000, { 511000, 609000, 706000, 802000 } },
+	{ 3999000, { 571000, 648000, 726000, 803000 } }
+};
+
+static int stm32_impedance_tune(struct stm32_combophy *combophy)
+{
+	u8 imp_size = ARRAY_SIZE(imp_lookup);
+	u8 vswing_size = ARRAY_SIZE(imp_lookup[0].vswing);
+	u8 imp_of, vswing_of;
+	u32 max_imp = imp_lookup[0].microohm;
+	u32 min_imp = imp_lookup[imp_size - 1].microohm;
+	u32 max_vswing = imp_lookup[imp_size - 1].vswing[vswing_size - 1];
+	u32 min_vswing = imp_lookup[0].vswing[0];
+	u32 val;
+
+	if (!of_property_read_u32(combophy->dev->of_node, "st,output-micro-ohms", &val)) {
+		if (val < min_imp || val > max_imp) {
+			dev_err(combophy->dev, "Invalid value %u for output ohm\n", val);
+			return -EINVAL;
+		}
+
+		for (imp_of = 0; imp_of < ARRAY_SIZE(imp_lookup); imp_of++)
+			if (imp_lookup[imp_of].microohm <= val)
+				break;
+
+		dev_dbg(combophy->dev, "Set %u micro-ohms output impedance\n",
+			imp_lookup[imp_of].microohm);
+
+		regmap_update_bits(combophy->regmap, SYSCFG_PCIEPRGCR,
+				   STM32MP25_PCIEPRG_IMPCTRL_OHM,
+				   FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_OHM, imp_of));
+	} else {
+		regmap_read(combophy->regmap, SYSCFG_PCIEPRGCR, &val);
+		imp_of = FIELD_GET(STM32MP25_PCIEPRG_IMPCTRL_OHM, val);
+	}
+
+	if (!of_property_read_u32(combophy->dev->of_node, "st,output-vswing-microvolt", &val)) {
+		if (val < min_vswing || val > max_vswing) {
+			dev_err(combophy->dev, "Invalid value %u for output vswing\n", val);
+			return -EINVAL;
+		}
+
+		for (vswing_of = 0; vswing_of < ARRAY_SIZE(imp_lookup[imp_of].vswing); vswing_of++)
+			if (imp_lookup[imp_of].vswing[vswing_of] >= val)
+				break;
+
+		dev_dbg(combophy->dev, "Set %u microvolt swing\n",
+			 imp_lookup[imp_of].vswing[vswing_of]);
+
+		regmap_update_bits(combophy->regmap, SYSCFG_PCIEPRGCR,
+				   STM32MP25_PCIEPRG_IMPCTRL_VSWING,
+				   FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_VSWING, vswing_of));
+	}
+
+	return 0;
+}
+
+static int stm32_combophy_pll_init(struct stm32_combophy *combophy)
+{
+	int ret;
+	u32 refclksel, pllmult, propcntrl, val;
+	u32 clk_rate;
+	struct clk *clk;
+	u32 cr1_val = 0, cr1_mask = 0;
+
+	if (combophy->have_pad_clk)
+		clk = combophy->clks[PAD_CLK].clk;
+	else
+		clk = combophy->clks[KER_CLK].clk;
+
+	clk_rate = clk_get_rate(clk);
+
+	dev_dbg(combophy->dev, "%s pll init rate %d\n",
+		combophy->have_pad_clk ? "External" : "Ker", clk_rate);
+
+	if (combophy->type != PHY_TYPE_PCIE) {
+		cr1_mask |= SYSCFG_COMBOPHY_CR1_REFSSPEN;
+		cr1_val |= SYSCFG_COMBOPHY_CR1_REFSSPEN;
+	}
+
+	if (of_property_present(combophy->dev->of_node, "st,ssc-on")) {
+		dev_dbg(combophy->dev, "Enabling clock with SSC\n");
+		cr1_mask |= SYSCFG_COMBOPHY_CR1_SSCEN;
+		cr1_val |= SYSCFG_COMBOPHY_CR1_SSCEN;
+	}
+
+	switch (clk_rate) {
+	case 100000000:
+		pllmult = MPLLMULT_100;
+		refclksel = REFCLKSEL_0;
+		propcntrl = 0x8u << 4;
+		break;
+	case 19200000:
+		pllmult = MPLLMULT_19_2;
+		refclksel = REFCLKSEL_1;
+		propcntrl = 0x8u << 4;
+		break;
+	case 25000000:
+		pllmult = MPLLMULT_25;
+		refclksel = REFCLKSEL_0;
+		propcntrl = 0xeu << 4;
+		break;
+	case 24000000:
+		pllmult = MPLLMULT_24;
+		refclksel = REFCLKSEL_1;
+		propcntrl = 0xeu << 4;
+		break;
+	case 20000000:
+		pllmult = MPLLMULT_20;
+		refclksel = REFCLKSEL_0;
+		propcntrl = 0xeu << 4;
+		break;
+	default:
+		dev_err(combophy->dev, "Invalid rate 0x%x\n", clk_rate);
+		return -EINVAL;
+	};
+
+	cr1_mask |= SYSCFG_COMBOPHY_CR1_REFCLKDIV2;
+	cr1_val |= REFCLDIV_0;
+
+	cr1_mask |= SYSCFG_COMBOPHY_CR1_REFCLKSEL;
+	cr1_val |= refclksel;
+
+	cr1_mask |= SYSCFG_COMBOPHY_CR1_MPLLMULT;
+	cr1_val |= pllmult;
+
+	/*
+	 * vddcombophy is interconnected with vddcore. Isolation bit should be unset
+	 * before using the ComboPHY.
+	 */
+	regmap_update_bits(combophy->regmap, SYSCFG_COMBOPHY_CR2,
+			   SYSCFG_COMBOPHY_CR2_ISO_DIS, SYSCFG_COMBOPHY_CR2_ISO_DIS);
+
+	reset_control_assert(combophy->phy_reset);
+
+	if (combophy->type == PHY_TYPE_PCIE) {
+		ret = stm32_impedance_tune(combophy);
+		if (ret)
+			goto out_iso;
+
+		cr1_mask |= SYSCFG_COMBOPHY_CR1_REFUSEPAD;
+		cr1_val |= combophy->have_pad_clk ? SYSCFG_COMBOPHY_CR1_REFUSEPAD : 0;
+	}
+
+	if (!of_property_read_u32(combophy->dev->of_node, "st,rx-equalizer", &val)) {
+		dev_dbg(combophy->dev, "Set RX equalizer %u\n", val);
+		if (val > SYSCFG_COMBOPHY_CR4_RX0_EQ) {
+			dev_err(combophy->dev, "Invalid value %u for rx0 equalizer\n", val);
+			ret = -EINVAL;
+			goto out_iso;
+		}
+
+		regmap_update_bits(combophy->regmap, SYSCFG_COMBOPHY_CR4,
+			   SYSCFG_COMBOPHY_CR4_RX0_EQ, val);
+	}
+
+	regmap_update_bits(combophy->regmap, SYSCFG_COMBOPHY_CR1, cr1_mask, cr1_val);
+
+	/*
+	 * Force elasticity buffer to be tuned for the reference clock as
+	 * the separated clock model is not supported
+	 */
+	regmap_update_bits(combophy->regmap, SYSCFG_COMBOPHY_CR5,
+			   SYSCFG_COMBOPHY_CR5_COMMON_CLOCKS, SYSCFG_COMBOPHY_CR5_COMMON_CLOCKS);
+
+	reset_control_deassert(combophy->phy_reset);
+
+	ret = regmap_read_poll_timeout(combophy->regmap, SYSCFG_COMBOPHY_SR, val,
+				       !(val & STM32MP25_PIPE0_PHYSTATUS),
+				       10, 1000);
+	if (ret) {
+		dev_err(combophy->dev, "timeout, cannot lock PLL\n");
+		if (combophy->type == PHY_TYPE_PCIE && !combophy->have_pad_clk)
+			regmap_update_bits(combophy->regmap, SYSCFG_PCIEPRGCR,
+					   STM32MP25_PCIEPRGCR_EN, 0);
+
+		if (combophy->type != PHY_TYPE_PCIE)
+			regmap_update_bits(combophy->regmap, SYSCFG_COMBOPHY_CR1,
+					   SYSCFG_COMBOPHY_CR1_REFSSPEN, 0);
+
+		goto out;
+	}
+
+
+	if (combophy->type == PHY_TYPE_PCIE) {
+		if (!combophy->have_pad_clk)
+			regmap_update_bits(combophy->regmap, SYSCFG_PCIEPRGCR,
+					   STM32MP25_PCIEPRGCR_EN, STM32MP25_PCIEPRGCR_EN);
+
+		val = readl_relaxed(combophy->base + COMBOPHY_SUP_ANA_MPLL_LOOP_CTL);
+		val &= ~COMBOPHY_PROP_CNTRL;
+		val |= propcntrl;
+		writel_relaxed(val, combophy->base + COMBOPHY_SUP_ANA_MPLL_LOOP_CTL);
+	}
+
+	return 0;
+
+out_iso:
+	reset_control_deassert(combophy->phy_reset);
+
+out:
+	regmap_update_bits(combophy->regmap, SYSCFG_COMBOPHY_CR2,
+			   SYSCFG_COMBOPHY_CR2_ISO_DIS, 0);
+
+	return ret;
+}
+
+static struct phy *stm32_combophy_xlate(struct device *dev,
+					const struct of_phandle_args *args)
+{
+	struct stm32_combophy *combophy = dev_get_drvdata(dev);
+	unsigned int type;
+
+	if (args->args_count != 1) {
+		dev_err(dev, "invalid number of cells in 'phy' property\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	type = args->args[0];
+	if (type != PHY_TYPE_USB3 && type != PHY_TYPE_PCIE) {
+		dev_err(dev, "unsupported device type: %d\n", type);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (combophy->have_pad_clk && type != PHY_TYPE_PCIE) {
+		dev_err(dev, "Invalid use of clk_pad for USB3 mode\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	combophy->type = type;
+
+	return combophy->phy;
+}
+
+static int stm32_combophy_set_mode(struct stm32_combophy *combophy)
+{
+	int type = combophy->type;
+	u32 val;
+
+	switch (type) {
+	case PHY_TYPE_PCIE:
+		dev_dbg(combophy->dev, "setting PCIe ComboPHY\n");
+		val = COMBOPHY_MODESEL_PCIE;
+		break;
+	case PHY_TYPE_USB3:
+		dev_dbg(combophy->dev, "setting USB3 ComboPHY\n");
+		val = COMBOPHY_MODESEL_USB;
+		break;
+	default:
+		dev_err(combophy->dev, "Invalid PHY mode %d\n", type);
+		return -EINVAL;
+	}
+
+	return regmap_update_bits(combophy->regmap, SYSCFG_COMBOPHY_CR2,
+				  SYSCFG_COMBOPHY_CR2_MODESEL, val);
+}
+
+static int stm32_combophy_suspend_noirq(struct device *dev)
+{
+	struct stm32_combophy *combophy = dev_get_drvdata(dev);
+
+	/*
+	 * Clocks should be turned off since it is not needed for
+	 * wakeup capability. In case usb-remote wakeup is not enabled,
+	 * combo-phy is already turned off by HCD driver using exit callback
+	 */
+	if (combophy->is_init) {
+		clk_bulk_disable_unprepare(combophy->num_clks, combophy->clks);
+
+		/* since wakeup is enabled for ctrl */
+		enable_irq_wake(combophy->irq_wakeup);
+	}
+
+	return 0;
+}
+
+static int stm32_combophy_resume_noirq(struct device *dev)
+{
+	struct stm32_combophy *combophy = dev_get_drvdata(dev);
+	int ret;
+
+	/*
+	 * If clocks was turned off by suspend call for wakeup then needs
+	 * to be turned back ON in resume. In case usb-remote wakeup is not
+	 * enabled, clocks already turned ON by HCD driver using init callback
+	 */
+	if (combophy->is_init) {
+		/* since wakeup was enabled for ctrl */
+		disable_irq_wake(combophy->irq_wakeup);
+
+		ret = clk_bulk_prepare_enable(combophy->num_clks, combophy->clks);
+		if (ret) {
+			dev_err(dev, "can't enable clocks (%d)\n", ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int stm32_combophy_exit(struct phy *phy)
+{
+	struct stm32_combophy *combophy = phy_get_drvdata(phy);
+	struct device *dev = combophy->dev;
+
+	combophy->is_init = false;
+
+	if (combophy->type == PHY_TYPE_PCIE && !combophy->have_pad_clk)
+		regmap_update_bits(combophy->regmap, SYSCFG_PCIEPRGCR,
+				   STM32MP25_PCIEPRGCR_EN, 0);
+
+	if (combophy->type != PHY_TYPE_PCIE)
+		regmap_update_bits(combophy->regmap, SYSCFG_COMBOPHY_CR1,
+				   SYSCFG_COMBOPHY_CR1_REFSSPEN, 0);
+
+	regmap_update_bits(combophy->regmap, SYSCFG_COMBOPHY_CR2,
+			   SYSCFG_COMBOPHY_CR2_ISO_DIS, 0);
+
+	clk_bulk_disable_unprepare(combophy->num_clks, combophy->clks);
+
+	pm_runtime_put_noidle(dev);
+
+	return 0;
+}
+
+static int stm32_combophy_init(struct phy *phy)
+{
+	struct stm32_combophy *combophy = phy_get_drvdata(phy);
+	struct device *dev = combophy->dev;
+	int ret;
+
+	pm_runtime_get_noresume(dev);
+
+	ret = clk_bulk_prepare_enable(combophy->num_clks, combophy->clks);
+	if (ret) {
+		dev_err(dev, "can't enable clocks (%d)\n", ret);
+		pm_runtime_put_noidle(dev);
+		return ret;
+	}
+
+	ret = stm32_combophy_set_mode(combophy);
+	if (ret) {
+		dev_err(dev, "combophy mode not set\n");
+		clk_bulk_disable_unprepare(combophy->num_clks, combophy->clks);
+		pm_runtime_put_noidle(dev);
+		return ret;
+	}
+
+	ret = stm32_combophy_pll_init(combophy);
+	if (ret) {
+		clk_bulk_disable_unprepare(combophy->num_clks, combophy->clks);
+		pm_runtime_put_noidle(dev);
+		return ret;
+	}
+
+	pm_runtime_disable(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
+	combophy->is_init = true;
+
+	return ret;
+}
+
+static const struct phy_ops stm32_combophy_phy_data = {
+	.init = stm32_combophy_init,
+	.exit = stm32_combophy_exit,
+	.owner = THIS_MODULE
+};
+
+static irqreturn_t stm32_combophy_irq_wakeup_handler(int irq, void *dev_id)
+{
+	return IRQ_HANDLED;
+}
+
+static int stm32_combophy_get_clocks(struct stm32_combophy *combophy)
+{
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(combophy_clks); i++)
+		combophy->clks[i].id = combophy_clks[i];
+
+	combophy->num_clks = ARRAY_SIZE(combophy_clks) - 1;
+
+	ret = devm_clk_bulk_get(combophy->dev, combophy->num_clks, combophy->clks);
+	if (ret)
+		return ret;
+
+	ret = devm_clk_bulk_get_optional(combophy->dev, 1, combophy->clks + combophy->num_clks);
+	if (ret)
+		return ret;
+
+	if (combophy->clks[combophy->num_clks].clk != NULL) {
+		combophy->have_pad_clk = true;
+		combophy->num_clks++;
+	}
+
+	return 0;
+}
+
+static int stm32_combophy_probe(struct platform_device *pdev)
+{
+	struct stm32_combophy *combophy;
+	struct device *dev = &pdev->dev;
+	struct phy_provider *phy_provider;
+	int ret, irq;
+
+	combophy = devm_kzalloc(dev, sizeof(*combophy), GFP_KERNEL);
+	if (!combophy)
+		return -ENOMEM;
+
+	combophy->dev = dev;
+
+	dev_set_drvdata(dev, combophy);
+
+	combophy->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(combophy->base))
+		return PTR_ERR(combophy->base);
+
+	ret = stm32_combophy_get_clocks(combophy);
+	if (ret)
+		return ret;
+
+	combophy->phy_reset = devm_reset_control_get_exclusive(dev, "phy");
+	if (IS_ERR(combophy->phy_reset))
+		return dev_err_probe(dev, PTR_ERR(combophy->phy_reset),
+				     "Failed to get PHY reset\n");
+
+	combophy->regmap = syscon_regmap_lookup_by_compatible("st,stm32mp25-syscfg");
+	if (IS_ERR(combophy->regmap))
+		return dev_err_probe(dev, PTR_ERR(combophy->regmap),
+				     "No syscfg specified\n");
+
+	combophy->phy = devm_phy_create(dev, NULL, &stm32_combophy_phy_data);
+	if (IS_ERR(combophy->phy))
+		return dev_err_probe(dev, PTR_ERR(combophy->phy),
+				     "failed to create PCIe/USB3 ComboPHY\n");
+
+	if (device_property_read_bool(dev, "wakeup-source")) {
+		irq = platform_get_irq(pdev, 0);
+		if (irq < 0)
+			return dev_err_probe(dev, irq, "failed to get IRQ\n");
+		combophy->irq_wakeup = irq;
+
+		ret = devm_request_threaded_irq(dev, combophy->irq_wakeup, NULL,
+						stm32_combophy_irq_wakeup_handler, IRQF_ONESHOT,
+						NULL, NULL);
+		if (ret)
+			return dev_err_probe(dev, ret, "unable to request wake IRQ %d\n",
+						 combophy->irq_wakeup);
+	}
+
+	ret = devm_pm_runtime_enable(dev);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to enable pm runtime\n");
+
+	phy_set_drvdata(combophy->phy, combophy);
+
+	phy_provider = devm_of_phy_provider_register(dev, stm32_combophy_xlate);
+
+	return PTR_ERR_OR_ZERO(phy_provider);
+}
+
+static const struct dev_pm_ops stm32_combophy_pm_ops = {
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(stm32_combophy_suspend_noirq,
+				  stm32_combophy_resume_noirq)
+};
+
+static const struct of_device_id stm32_combophy_of_match[] = {
+	{ .compatible = "st,stm32mp25-combophy", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, stm32_combophy_of_match);
+
+static struct platform_driver stm32_combophy_driver = {
+	.probe = stm32_combophy_probe,
+	.driver = {
+		   .name = "stm32-combophy",
+		   .of_match_table = stm32_combophy_of_match,
+		   .pm = pm_sleep_ptr(&stm32_combophy_pm_ops)
+	}
+};
+
+module_platform_driver(stm32_combophy_driver);
+
+MODULE_AUTHOR("Christian Bruel <christian.bruel@foss.st.com>");
+MODULE_DESCRIPTION("STM32MP25 Combophy USB3/PCIe controller driver");
+MODULE_LICENSE("GPL");

From b6a713b92ebb9e7ee1495f009fd02a71e485184f Mon Sep 17 00:00:00 2001
From: Christian Bruel <christian.bruel@foss.st.com>
Date: Mon, 30 Sep 2024 19:08:45 +0200
Subject: [PATCH 0222/1530] MAINTAINERS: add entry for ST STM32MP25 COMBOPHY
 driver

Add myself as STM32MP25 COMBOPHY maintainer

Signed-off-by: Christian Bruel <christian.bruel@foss.st.com>
Link: https://lore.kernel.org/r/20240930170847.948779-4-christian.bruel@foss.st.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 MAINTAINERS | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index c27f3190737f8..8bf689ec63df9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22213,6 +22213,12 @@ F:	drivers/*/stm32-*timer*
 F:	drivers/pwm/pwm-stm32*
 F:	include/linux/*/stm32-*tim*
 
+STM32MP25 USB3/PCIE COMBOPHY DRIVER
+M:	Christian Bruel <christian.bruel@foss.st.com>
+S:	Maintained
+F:	Documentation/devicetree/bindings/phy/st,stm32mp25-combophy.yaml
+F:	drivers/phy/st/phy-stm32-combophy.c
+
 STMMAC ETHERNET DRIVER
 M:	Alexandre Torgue <alexandre.torgue@foss.st.com>
 M:	Jose Abreu <joabreu@synopsys.com>

From bbcc9e2bde693ec3fc6aab650abaf748eb9f38f9 Mon Sep 17 00:00:00 2001
From: Siddharth Vadapalli <s-vadapalli@ti.com>
Date: Mon, 30 Sep 2024 15:21:45 +0530
Subject: [PATCH 0223/1530] dt-bindings: phy: cadence-sierra: Allow PHY types
 QSGMII and SGMII

The Sierra SERDES can be configured for QSGMII and SGMII protocols. Hence,
update the bindings to treat "PHY_TYPE_QSGMII" and "PHY_TYPE_SGMII" as
valid values for the "cdns,phy-type" property.

Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20240930095145.3004053-1-s-vadapalli@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/phy/phy-cadence-sierra.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/phy/phy-cadence-sierra.yaml b/Documentation/devicetree/bindings/phy/phy-cadence-sierra.yaml
index 37f028f7a0955..137ac5703853d 100644
--- a/Documentation/devicetree/bindings/phy/phy-cadence-sierra.yaml
+++ b/Documentation/devicetree/bindings/phy/phy-cadence-sierra.yaml
@@ -96,7 +96,7 @@ patternProperties:
           Specifies the type of PHY for which the group of PHY lanes is used.
           Refer include/dt-bindings/phy/phy.h. Constants from the header should be used.
         $ref: /schemas/types.yaml#/definitions/uint32
-        enum: [2, 4]
+        enum: [2, 4, 8, 9]
 
       cdns,num-lanes:
         description:

From 38f022b0787b22feb9e34fce19a1f6cea1f951ed Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 25 Sep 2024 16:06:00 +0200
Subject: [PATCH 0224/1530] docs: rust: quick-start: add Ubuntu

Ubuntu has changed their maintenance model for Rust toolchains and is
now providing recent Rust releases in their releases, including both
LTS and non-LTS (interim) releases.

Therefore, add instructions to the Quick Start guide for Ubuntu, like
it is done for the other distributions.

Link: https://packages.ubuntu.com/search?keywords=rustc-1
Link: https://packages.ubuntu.com/search?keywords=bindgen-0
Cc: Zixing Liu <zixing.liu@canonical.com>
Cc: William Grant <wgrant@ubuntu.com>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20240925140600.275429-1-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Documentation/rust/quick-start.rst | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/Documentation/rust/quick-start.rst b/Documentation/rust/quick-start.rst
index 2d107982c87bb..4aa50e5fcb8c0 100644
--- a/Documentation/rust/quick-start.rst
+++ b/Documentation/rust/quick-start.rst
@@ -87,6 +87,23 @@ they should generally work out of the box, e.g.::
 	zypper install rust rust1.79-src rust-bindgen clang
 
 
+Ubuntu
+******
+
+Ubuntu LTS and non-LTS (interim) releases provide recent Rust releases and thus
+they should generally work out of the box, e.g.::
+
+	apt install rustc-1.80 rust-1.80-src bindgen-0.65 rustfmt-1.80 rust-1.80-clippy
+
+``RUST_LIB_SRC`` needs to be set when using the versioned packages, e.g.::
+
+	RUST_LIB_SRC=/usr/src/rustc-$(rustc-1.80 --version | cut -d' ' -f2)/library
+
+In addition, ``bindgen-0.65`` is available in newer releases (24.04 LTS and
+24.10), but it may not be available in older ones (20.04 LTS and 22.04 LTS),
+thus ``bindgen`` may need to be built manually (please see below).
+
+
 Requirements: Building
 ----------------------
 

From d407317076ce1ce5ec0882f08d619c0dd79a5fbf Mon Sep 17 00:00:00 2001
From: Nell Shamrell-Harrington <nells@linux.microsoft.com>
Date: Wed, 18 Sep 2024 21:20:52 +0000
Subject: [PATCH 0225/1530] rust: types: add examples for the `Either` type

We aim to have examples in all Rust types, thus add basic ones for the
`Either` type.

Suggested-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Nell Shamrell-Harrington <nells@linux.microsoft.com>
Tested-by: Dirk Behme <dirk.behme@de.bosch.com>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://rust-for-linux.zulipchat.com/#narrow/stream/291565/topic/x/near/467478085
Link: https://lore.kernel.org/r/20240918212052.8790-1-nells@linux.microsoft.com
[ Reworded slightly. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/types.rs | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index 9e7ca066355cd..e2f3ab11cfda2 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -461,6 +461,15 @@ impl<T: AlwaysRefCounted> Drop for ARef<T> {
 }
 
 /// A sum type that always holds either a value of type `L` or `R`.
+///
+/// # Examples
+///
+/// ```
+/// use kernel::types::Either;
+///
+/// let left_value: Either<i32, &str> = Either::Left(7);
+/// let right_value: Either<i32, &str> = Either::Right("right value");
+/// ```
 pub enum Either<L, R> {
     /// Constructs an instance of [`Either`] containing a value of type `L`.
     Left(L),

From 024f9676a6d236132119832a90fb9a1a9115b41a Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:29 +0200
Subject: [PATCH 0226/1530] rust: workqueue: remove unneeded
 ``#[allow(clippy::new_ret_no_self)]`

Perform the same clean commit b2516f7af9d2 ("rust: kernel: remove
`#[allow(clippy::new_ret_no_self)]`") did for a case that appeared in
workqueue in parallel in commit 7324b88975c5 ("rust: workqueue: add
helper for defining work_struct fields"):

    Clippy triggered a false positive on its `new_ret_no_self` lint
    when using the `pin_init!` macro. Since Rust 1.67.0, that does
    not happen anymore, since Clippy learnt to not warn about
    `-> impl Trait<Self>` [1][2].

    The kernel nowadays uses Rust 1.72.1, thus remove the `#[allow]`.

    Link: https://github.com/rust-lang/rust-clippy/issues/7344 [1]
    Link: https://github.com/rust-lang/rust-clippy/pull/9733 [2]

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-2-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/workqueue.rs | 1 -
 1 file changed, 1 deletion(-)

diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs
index 553a5cba2adcb..493288dc1de07 100644
--- a/rust/kernel/workqueue.rs
+++ b/rust/kernel/workqueue.rs
@@ -366,7 +366,6 @@ unsafe impl<T: ?Sized, const ID: u64> Sync for Work<T, ID> {}
 impl<T: ?Sized, const ID: u64> Work<T, ID> {
     /// Creates a new instance of [`Work`].
     #[inline]
-    #[allow(clippy::new_ret_no_self)]
     pub fn new(name: &'static CStr, key: &'static LockClassKey) -> impl PinInit<Self>
     where
         T: WorkItem<ID>,

From a135aa3d30d28f26eb28a0ff5d48b387b0e0755f Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:30 +0200
Subject: [PATCH 0227/1530] rust: sort global Rust flags

Sort the global Rust flags so that it is easier to follow along when we
have more, like this patch series does.

Reviewed-by: Trevor Gross <tmgross@umich.edu>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-3-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Makefile | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/Makefile b/Makefile
index c5493c0c0ca12..8e99f4a7e4060 100644
--- a/Makefile
+++ b/Makefile
@@ -446,18 +446,18 @@ KBUILD_USERLDFLAGS := $(USERLDFLAGS)
 export rust_common_flags := --edition=2021 \
 			    -Zbinary_dep_depinfo=y \
 			    -Astable_features \
-			    -Dunsafe_op_in_unsafe_fn \
 			    -Dnon_ascii_idents \
+			    -Dunsafe_op_in_unsafe_fn \
+			    -Wmissing_docs \
 			    -Wrust_2018_idioms \
 			    -Wunreachable_pub \
-			    -Wmissing_docs \
-			    -Wrustdoc::missing_crate_level_docs \
 			    -Wclippy::all \
+			    -Wclippy::dbg_macro \
 			    -Wclippy::mut_mut \
 			    -Wclippy::needless_bitwise_bool \
 			    -Wclippy::needless_continue \
 			    -Wclippy::no_mangle_with_rust_abi \
-			    -Wclippy::dbg_macro
+			    -Wrustdoc::missing_crate_level_docs
 
 KBUILD_HOSTCFLAGS   := $(KBUILD_USERHOSTCFLAGS) $(HOST_LFS_CFLAGS) \
 		       $(HOSTCFLAGS) -I $(srctree)/scripts/include

From 567cdff53e71de56ae67eaf4309db38778b7bcd3 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:31 +0200
Subject: [PATCH 0228/1530] rust: types: avoid repetition in `{As,From}Bytes`
 impls

In order to provide `// SAFETY` comments for every `unsafe impl`, we would
need to repeat them, which is not very useful and would be harder to read.

We could perhaps allow the lint (ideally within a small module), but we
can take the chance to avoid the repetition of the `impl`s themselves
too by using a small local macro, like in other places where we have
had to do this sort of thing.

Thus add the straightforward `impl_{from,as}bytes!` macros and use them
to implement `FromBytes`.

This, in turn, will allow us in the next patch to place a `// SAFETY`
comment that defers to the actual invocation of the macro.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-4-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/types.rs | 68 +++++++++++++++++++++++---------------------
 1 file changed, 35 insertions(+), 33 deletions(-)

diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index e2f3ab11cfda2..e00c14687eba7 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -490,21 +490,22 @@ pub enum Either<L, R> {
 /// All bit-patterns must be valid for this type. This type must not have interior mutability.
 pub unsafe trait FromBytes {}
 
-// SAFETY: All bit patterns are acceptable values of the types below.
-unsafe impl FromBytes for u8 {}
-unsafe impl FromBytes for u16 {}
-unsafe impl FromBytes for u32 {}
-unsafe impl FromBytes for u64 {}
-unsafe impl FromBytes for usize {}
-unsafe impl FromBytes for i8 {}
-unsafe impl FromBytes for i16 {}
-unsafe impl FromBytes for i32 {}
-unsafe impl FromBytes for i64 {}
-unsafe impl FromBytes for isize {}
-// SAFETY: If all bit patterns are acceptable for individual values in an array, then all bit
-// patterns are also acceptable for arrays of that type.
-unsafe impl<T: FromBytes> FromBytes for [T] {}
-unsafe impl<T: FromBytes, const N: usize> FromBytes for [T; N] {}
+macro_rules! impl_frombytes {
+    ($($({$($generics:tt)*})? $t:ty, )*) => {
+        $(unsafe impl$($($generics)*)? FromBytes for $t {})*
+    };
+}
+
+impl_frombytes! {
+    // SAFETY: All bit patterns are acceptable values of the types below.
+    u8, u16, u32, u64, usize,
+    i8, i16, i32, i64, isize,
+
+    // SAFETY: If all bit patterns are acceptable for individual values in an array, then all bit
+    // patterns are also acceptable for arrays of that type.
+    {<T: FromBytes>} [T],
+    {<T: FromBytes, const N: usize>} [T; N],
+}
 
 /// Types that can be viewed as an immutable slice of initialized bytes.
 ///
@@ -523,21 +524,22 @@ unsafe impl<T: FromBytes, const N: usize> FromBytes for [T; N] {}
 /// mutability.
 pub unsafe trait AsBytes {}
 
-// SAFETY: Instances of the following types have no uninitialized portions.
-unsafe impl AsBytes for u8 {}
-unsafe impl AsBytes for u16 {}
-unsafe impl AsBytes for u32 {}
-unsafe impl AsBytes for u64 {}
-unsafe impl AsBytes for usize {}
-unsafe impl AsBytes for i8 {}
-unsafe impl AsBytes for i16 {}
-unsafe impl AsBytes for i32 {}
-unsafe impl AsBytes for i64 {}
-unsafe impl AsBytes for isize {}
-unsafe impl AsBytes for bool {}
-unsafe impl AsBytes for char {}
-unsafe impl AsBytes for str {}
-// SAFETY: If individual values in an array have no uninitialized portions, then the array itself
-// does not have any uninitialized portions either.
-unsafe impl<T: AsBytes> AsBytes for [T] {}
-unsafe impl<T: AsBytes, const N: usize> AsBytes for [T; N] {}
+macro_rules! impl_asbytes {
+    ($($({$($generics:tt)*})? $t:ty, )*) => {
+        $(unsafe impl$($($generics)*)? AsBytes for $t {})*
+    };
+}
+
+impl_asbytes! {
+    // SAFETY: Instances of the following types have no uninitialized portions.
+    u8, u16, u32, u64, usize,
+    i8, i16, i32, i64, isize,
+    bool,
+    char,
+    str,
+
+    // SAFETY: If individual values in an array have no uninitialized portions, then the array
+    // itself does not have any uninitialized portions either.
+    {<T: AsBytes>} [T],
+    {<T: AsBytes, const N: usize>} [T; N],
+}

From db4f72c904cb116e2bf56afdd67fc5167a607a7b Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:32 +0200
Subject: [PATCH 0229/1530] rust: enable `clippy::undocumented_unsafe_blocks`
 lint

Checking that we are not missing any `// SAFETY` comments in our `unsafe`
blocks is something we have wanted to do for a long time, as well as
cleaning up the remaining cases that were not documented [1].

Back when Rust for Linux started, this was something that could have
been done via a script, like Rust's `tidy`. Soon after, in Rust 1.58.0,
Clippy implemented the `undocumented_unsafe_blocks` lint [2].

Even though the lint has a few false positives, e.g. in some cases where
attributes appear between the comment and the `unsafe` block [3], there
are workarounds and the lint seems quite usable already.

Thus enable the lint now.

We still have a few cases to clean up, so just allow those for the moment
by writing a `TODO` comment -- some of those may be good candidates for
new contributors.

Link: https://github.com/Rust-for-Linux/linux/issues/351 [1]
Link: https://rust-lang.github.io/rust-clippy/master/#/undocumented_unsafe_blocks [2]
Link: https://github.com/rust-lang/rust-clippy/issues/13189 [3]
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-5-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Makefile                       | 1 +
 mm/kasan/kasan_test_rust.rs    | 1 +
 rust/bindings/lib.rs           | 1 +
 rust/kernel/alloc/allocator.rs | 2 ++
 rust/kernel/error.rs           | 9 ++++++---
 rust/kernel/init.rs            | 5 +++++
 rust/kernel/init/__internal.rs | 2 ++
 rust/kernel/init/macros.rs     | 9 +++++++++
 rust/kernel/list.rs            | 1 +
 rust/kernel/print.rs           | 2 ++
 rust/kernel/str.rs             | 7 ++++---
 rust/kernel/sync/condvar.rs    | 2 +-
 rust/kernel/sync/lock.rs       | 6 +++---
 rust/kernel/types.rs           | 4 ++++
 rust/kernel/workqueue.rs       | 4 ++++
 rust/uapi/lib.rs               | 1 +
 16 files changed, 47 insertions(+), 10 deletions(-)

diff --git a/Makefile b/Makefile
index 8e99f4a7e4060..9730b4c3f029c 100644
--- a/Makefile
+++ b/Makefile
@@ -457,6 +457,7 @@ export rust_common_flags := --edition=2021 \
 			    -Wclippy::needless_bitwise_bool \
 			    -Wclippy::needless_continue \
 			    -Wclippy::no_mangle_with_rust_abi \
+			    -Wclippy::undocumented_unsafe_blocks \
 			    -Wrustdoc::missing_crate_level_docs
 
 KBUILD_HOSTCFLAGS   := $(KBUILD_USERHOSTCFLAGS) $(HOST_LFS_CFLAGS) \
diff --git a/mm/kasan/kasan_test_rust.rs b/mm/kasan/kasan_test_rust.rs
index caa7175964ef6..47bcf033dd4f0 100644
--- a/mm/kasan/kasan_test_rust.rs
+++ b/mm/kasan/kasan_test_rust.rs
@@ -17,5 +17,6 @@ pub extern "C" fn kasan_test_rust_uaf() -> u8 {
     }
     let ptr: *mut u8 = addr_of_mut!(v[2048]);
     drop(v);
+    // SAFETY: Incorrect, on purpose.
     unsafe { *ptr }
 }
diff --git a/rust/bindings/lib.rs b/rust/bindings/lib.rs
index 93a1a3fc97bc9..d6da3011281a9 100644
--- a/rust/bindings/lib.rs
+++ b/rust/bindings/lib.rs
@@ -25,6 +25,7 @@
 )]
 
 #[allow(dead_code)]
+#[allow(clippy::undocumented_unsafe_blocks)]
 mod bindings_raw {
     // Use glob import here to expose all helpers.
     // Symbols defined within the module will take precedence to the glob import.
diff --git a/rust/kernel/alloc/allocator.rs b/rust/kernel/alloc/allocator.rs
index e6ea601f38c6d..91216b36af693 100644
--- a/rust/kernel/alloc/allocator.rs
+++ b/rust/kernel/alloc/allocator.rs
@@ -31,6 +31,7 @@ pub(crate) unsafe fn krealloc_aligned(ptr: *mut u8, new_layout: Layout, flags: F
     unsafe { bindings::krealloc(ptr as *const core::ffi::c_void, size, flags.0) as *mut u8 }
 }
 
+// SAFETY: TODO.
 unsafe impl GlobalAlloc for KernelAllocator {
     unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
         // SAFETY: `ptr::null_mut()` is null and `layout` has a non-zero size by the function safety
@@ -39,6 +40,7 @@ unsafe impl GlobalAlloc for KernelAllocator {
     }
 
     unsafe fn dealloc(&self, ptr: *mut u8, _layout: Layout) {
+        // SAFETY: TODO.
         unsafe {
             bindings::kfree(ptr as *const core::ffi::c_void);
         }
diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs
index 6f1587a2524e8..639bc7572f901 100644
--- a/rust/kernel/error.rs
+++ b/rust/kernel/error.rs
@@ -171,9 +171,11 @@ impl fmt::Debug for Error {
         match self.name() {
             // Print out number if no name can be found.
             None => f.debug_tuple("Error").field(&-self.0).finish(),
-            // SAFETY: These strings are ASCII-only.
             Some(name) => f
-                .debug_tuple(unsafe { core::str::from_utf8_unchecked(name) })
+                .debug_tuple(
+                    // SAFETY: These strings are ASCII-only.
+                    unsafe { core::str::from_utf8_unchecked(name) },
+                )
                 .finish(),
         }
     }
@@ -277,6 +279,8 @@ pub(crate) fn from_err_ptr<T>(ptr: *mut T) -> Result<*mut T> {
     if unsafe { bindings::IS_ERR(const_ptr) } {
         // SAFETY: The FFI function does not deref the pointer.
         let err = unsafe { bindings::PTR_ERR(const_ptr) };
+
+        #[allow(clippy::unnecessary_cast)]
         // CAST: If `IS_ERR()` returns `true`,
         // then `PTR_ERR()` is guaranteed to return a
         // negative value greater-or-equal to `-bindings::MAX_ERRNO`,
@@ -286,7 +290,6 @@ pub(crate) fn from_err_ptr<T>(ptr: *mut T) -> Result<*mut T> {
         //
         // SAFETY: `IS_ERR()` ensures `err` is a
         // negative value greater-or-equal to `-bindings::MAX_ERRNO`.
-        #[allow(clippy::unnecessary_cast)]
         return Err(unsafe { Error::from_errno_unchecked(err as core::ffi::c_int) });
     }
     Ok(ptr)
diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs
index a17ac8762d8f9..08b9d695c2851 100644
--- a/rust/kernel/init.rs
+++ b/rust/kernel/init.rs
@@ -541,6 +541,7 @@ macro_rules! stack_try_pin_init {
 /// }
 /// pin_init!(&this in Buf {
 ///     buf: [0; 64],
+///     // SAFETY: TODO.
 ///     ptr: unsafe { addr_of_mut!((*this.as_ptr()).buf).cast() },
 ///     pin: PhantomPinned,
 /// });
@@ -875,6 +876,7 @@ pub unsafe trait PinInit<T: ?Sized, E = Infallible>: Sized {
     /// }
     ///
     /// let foo = pin_init!(Foo {
+    ///     // SAFETY: TODO.
     ///     raw <- unsafe {
     ///         Opaque::ffi_init(|s| {
     ///             init_foo(s);
@@ -1162,6 +1164,7 @@ where
 // SAFETY: Every type can be initialized by-value.
 unsafe impl<T, E> Init<T, E> for T {
     unsafe fn __init(self, slot: *mut T) -> Result<(), E> {
+        // SAFETY: TODO.
         unsafe { slot.write(self) };
         Ok(())
     }
@@ -1170,6 +1173,7 @@ unsafe impl<T, E> Init<T, E> for T {
 // SAFETY: Every type can be initialized by-value. `__pinned_init` calls `__init`.
 unsafe impl<T, E> PinInit<T, E> for T {
     unsafe fn __pinned_init(self, slot: *mut T) -> Result<(), E> {
+        // SAFETY: TODO.
         unsafe { self.__init(slot) }
     }
 }
@@ -1411,6 +1415,7 @@ pub fn zeroed<T: Zeroable>() -> impl Init<T> {
 
 macro_rules! impl_zeroable {
     ($($({$($generics:tt)*})? $t:ty, )*) => {
+        // SAFETY: Safety comments written in the macro invocation.
         $(unsafe impl$($($generics)*)? Zeroable for $t {})*
     };
 }
diff --git a/rust/kernel/init/__internal.rs b/rust/kernel/init/__internal.rs
index 13cefd37512f8..29f4fd00df3da 100644
--- a/rust/kernel/init/__internal.rs
+++ b/rust/kernel/init/__internal.rs
@@ -112,10 +112,12 @@ impl<T: ?Sized> Clone for AllData<T> {
 
 impl<T: ?Sized> Copy for AllData<T> {}
 
+// SAFETY: TODO.
 unsafe impl<T: ?Sized> InitData for AllData<T> {
     type Datee = T;
 }
 
+// SAFETY: TODO.
 unsafe impl<T: ?Sized> HasInitData for T {
     type InitData = AllData<T>;
 
diff --git a/rust/kernel/init/macros.rs b/rust/kernel/init/macros.rs
index 9a0c4650ef676..736fe0ce0cd9d 100644
--- a/rust/kernel/init/macros.rs
+++ b/rust/kernel/init/macros.rs
@@ -513,6 +513,7 @@ macro_rules! __pinned_drop {
             }
         ),
     ) => {
+        // SAFETY: TODO.
         unsafe $($impl_sig)* {
             // Inherit all attributes and the type/ident tokens for the signature.
             $(#[$($attr)*])*
@@ -872,6 +873,7 @@ macro_rules! __pin_data {
                 }
             }
 
+            // SAFETY: TODO.
             unsafe impl<$($impl_generics)*>
                 $crate::init::__internal::PinData for __ThePinData<$($ty_generics)*>
             where $($whr)*
@@ -997,6 +999,7 @@ macro_rules! __pin_data {
                     slot: *mut $p_type,
                     init: impl $crate::init::PinInit<$p_type, E>,
                 ) -> ::core::result::Result<(), E> {
+                    // SAFETY: TODO.
                     unsafe { $crate::init::PinInit::__pinned_init(init, slot) }
                 }
             )*
@@ -1007,6 +1010,7 @@ macro_rules! __pin_data {
                     slot: *mut $type,
                     init: impl $crate::init::Init<$type, E>,
                 ) -> ::core::result::Result<(), E> {
+                    // SAFETY: TODO.
                     unsafe { $crate::init::Init::__init(init, slot) }
                 }
             )*
@@ -1121,6 +1125,8 @@ macro_rules! __init_internal {
         // no possibility of returning without `unsafe`.
         struct __InitOk;
         // Get the data about fields from the supplied type.
+        //
+        // SAFETY: TODO.
         let data = unsafe {
             use $crate::init::__internal::$has_data;
             // Here we abuse `paste!` to retokenize `$t`. Declarative macros have some internal
@@ -1176,6 +1182,7 @@ macro_rules! __init_internal {
         let init = move |slot| -> ::core::result::Result<(), $err> {
             init(slot).map(|__InitOk| ())
         };
+        // SAFETY: TODO.
         let init = unsafe { $crate::init::$construct_closure::<_, $err>(init) };
         init
     }};
@@ -1324,6 +1331,8 @@ macro_rules! __init_internal {
         // Endpoint, nothing more to munch, create the initializer.
         // Since we are in the closure that is never called, this will never get executed.
         // We abuse `slot` to get the correct type inference here:
+        //
+        // SAFETY: TODO.
         unsafe {
             // Here we abuse `paste!` to retokenize `$t`. Declarative macros have some internal
             // information that is associated to already parsed fragments, so a path fragment
diff --git a/rust/kernel/list.rs b/rust/kernel/list.rs
index 5b4aec29eb675..fb93330f4af48 100644
--- a/rust/kernel/list.rs
+++ b/rust/kernel/list.rs
@@ -354,6 +354,7 @@ impl<T: ?Sized + ListItem<ID>, const ID: u64> List<T, ID> {
     ///
     /// `item` must not be in a different linked list (with the same id).
     pub unsafe fn remove(&mut self, item: &T) -> Option<ListArc<T, ID>> {
+        // SAFETY: TODO.
         let mut item = unsafe { ListLinks::fields(T::view_links(item)) };
         // SAFETY: The user provided a reference, and reference are never dangling.
         //
diff --git a/rust/kernel/print.rs b/rust/kernel/print.rs
index 508b0221256c9..fe53fc469c4f1 100644
--- a/rust/kernel/print.rs
+++ b/rust/kernel/print.rs
@@ -23,6 +23,7 @@ unsafe extern "C" fn rust_fmt_argument(
     use fmt::Write;
     // SAFETY: The C contract guarantees that `buf` is valid if it's less than `end`.
     let mut w = unsafe { RawFormatter::from_ptrs(buf.cast(), end.cast()) };
+    // SAFETY: TODO.
     let _ = w.write_fmt(unsafe { *(ptr as *const fmt::Arguments<'_>) });
     w.pos().cast()
 }
@@ -102,6 +103,7 @@ pub unsafe fn call_printk(
 ) {
     // `_printk` does not seem to fail in any path.
     #[cfg(CONFIG_PRINTK)]
+    // SAFETY: TODO.
     unsafe {
         bindings::_printk(
             format_string.as_ptr() as _,
diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
index bb8d4f41475b5..66d4527f6c6f0 100644
--- a/rust/kernel/str.rs
+++ b/rust/kernel/str.rs
@@ -162,10 +162,10 @@ impl CStr {
     /// Returns the length of this string with `NUL`.
     #[inline]
     pub const fn len_with_nul(&self) -> usize {
-        // SAFETY: This is one of the invariant of `CStr`.
-        // We add a `unreachable_unchecked` here to hint the optimizer that
-        // the value returned from this function is non-zero.
         if self.0.is_empty() {
+            // SAFETY: This is one of the invariant of `CStr`.
+            // We add a `unreachable_unchecked` here to hint the optimizer that
+            // the value returned from this function is non-zero.
             unsafe { core::hint::unreachable_unchecked() };
         }
         self.0.len()
@@ -301,6 +301,7 @@ impl CStr {
     /// ```
     #[inline]
     pub unsafe fn as_str_unchecked(&self) -> &str {
+        // SAFETY: TODO.
         unsafe { core::str::from_utf8_unchecked(self.as_bytes()) }
     }
 
diff --git a/rust/kernel/sync/condvar.rs b/rust/kernel/sync/condvar.rs
index 2b306afbe56d9..7e00048bf4b14 100644
--- a/rust/kernel/sync/condvar.rs
+++ b/rust/kernel/sync/condvar.rs
@@ -92,8 +92,8 @@ pub struct CondVar {
     _pin: PhantomPinned,
 }
 
-// SAFETY: `CondVar` only uses a `struct wait_queue_head`, which is safe to use on any thread.
 #[allow(clippy::non_send_fields_in_send_ty)]
+// SAFETY: `CondVar` only uses a `struct wait_queue_head`, which is safe to use on any thread.
 unsafe impl Send for CondVar {}
 
 // SAFETY: `CondVar` only uses a `struct wait_queue_head`, which is safe to use on multiple threads
diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs
index f6c34ca4d819f..07fcf2d8efc6c 100644
--- a/rust/kernel/sync/lock.rs
+++ b/rust/kernel/sync/lock.rs
@@ -150,9 +150,9 @@ impl<T: ?Sized, B: Backend> Guard<'_, T, B> {
         // SAFETY: The caller owns the lock, so it is safe to unlock it.
         unsafe { B::unlock(self.lock.state.get(), &self.state) };
 
-        // SAFETY: The lock was just unlocked above and is being relocked now.
-        let _relock =
-            ScopeGuard::new(|| unsafe { B::relock(self.lock.state.get(), &mut self.state) });
+        let _relock = ScopeGuard::new(||
+                // SAFETY: The lock was just unlocked above and is being relocked now.
+                unsafe { B::relock(self.lock.state.get(), &mut self.state) });
 
         cb()
     }
diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index e00c14687eba7..fd8e2b6039e04 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -410,6 +410,7 @@ impl<T: AlwaysRefCounted> ARef<T> {
     ///
     /// struct Empty {}
     ///
+    /// # // SAFETY: TODO.
     /// unsafe impl AlwaysRefCounted for Empty {
     ///     fn inc_ref(&self) {}
     ///     unsafe fn dec_ref(_obj: NonNull<Self>) {}
@@ -417,6 +418,7 @@ impl<T: AlwaysRefCounted> ARef<T> {
     ///
     /// let mut data = Empty {};
     /// let ptr = NonNull::<Empty>::new(&mut data as *mut _).unwrap();
+    /// # // SAFETY: TODO.
     /// let data_ref: ARef<Empty> = unsafe { ARef::from_raw(ptr) };
     /// let raw_ptr: NonNull<Empty> = ARef::into_raw(data_ref);
     ///
@@ -492,6 +494,7 @@ pub unsafe trait FromBytes {}
 
 macro_rules! impl_frombytes {
     ($($({$($generics:tt)*})? $t:ty, )*) => {
+        // SAFETY: Safety comments written in the macro invocation.
         $(unsafe impl$($($generics)*)? FromBytes for $t {})*
     };
 }
@@ -526,6 +529,7 @@ pub unsafe trait AsBytes {}
 
 macro_rules! impl_asbytes {
     ($($({$($generics:tt)*})? $t:ty, )*) => {
+        // SAFETY: Safety comments written in the macro invocation.
         $(unsafe impl$($($generics)*)? AsBytes for $t {})*
     };
 }
diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs
index 493288dc1de07..3b3f1dbe8192c 100644
--- a/rust/kernel/workqueue.rs
+++ b/rust/kernel/workqueue.rs
@@ -519,6 +519,7 @@ impl_has_work! {
     impl{T} HasWork<Self> for ClosureWork<T> { self.work }
 }
 
+// SAFETY: TODO.
 unsafe impl<T, const ID: u64> WorkItemPointer<ID> for Arc<T>
 where
     T: WorkItem<ID, Pointer = Self>,
@@ -536,6 +537,7 @@ where
     }
 }
 
+// SAFETY: TODO.
 unsafe impl<T, const ID: u64> RawWorkItem<ID> for Arc<T>
 where
     T: WorkItem<ID, Pointer = Self>,
@@ -564,6 +566,7 @@ where
     }
 }
 
+// SAFETY: TODO.
 unsafe impl<T, const ID: u64> WorkItemPointer<ID> for Pin<Box<T>>
 where
     T: WorkItem<ID, Pointer = Self>,
@@ -583,6 +586,7 @@ where
     }
 }
 
+// SAFETY: TODO.
 unsafe impl<T, const ID: u64> RawWorkItem<ID> for Pin<Box<T>>
 where
     T: WorkItem<ID, Pointer = Self>,
diff --git a/rust/uapi/lib.rs b/rust/uapi/lib.rs
index 80a00260e3e7a..fea2de330d193 100644
--- a/rust/uapi/lib.rs
+++ b/rust/uapi/lib.rs
@@ -14,6 +14,7 @@
 #![cfg_attr(test, allow(unsafe_op_in_unsafe_fn))]
 #![allow(
     clippy::all,
+    clippy::undocumented_unsafe_blocks,
     dead_code,
     missing_docs,
     non_camel_case_types,

From c28bfe76e4ba707775a205b0274710de7aa1e31c Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:33 +0200
Subject: [PATCH 0230/1530] rust: enable `clippy::unnecessary_safety_comment`
 lint

In Rust 1.67.0, Clippy added the `unnecessary_safety_comment` lint [1],
which is the "inverse" of `undocumented_unsafe_blocks`: it finds places
where safe code has a `// SAFETY` comment attached.

The lint currently finds 3 places where we had such mistakes, thus it
seems already quite useful.

Thus clean those and enable it.

Link: https://rust-lang.github.io/rust-clippy/master/index.html#/unnecessary_safety_comment [1]
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Reviewed-by: Vincenzo Palazzo <vincenzopalazzodev@gmail.com>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-6-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Makefile                 | 1 +
 rust/kernel/sync/arc.rs  | 2 +-
 rust/kernel/workqueue.rs | 4 ++--
 3 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/Makefile b/Makefile
index 9730b4c3f029c..203f66154c143 100644
--- a/Makefile
+++ b/Makefile
@@ -458,6 +458,7 @@ export rust_common_flags := --edition=2021 \
 			    -Wclippy::needless_continue \
 			    -Wclippy::no_mangle_with_rust_abi \
 			    -Wclippy::undocumented_unsafe_blocks \
+			    -Wclippy::unnecessary_safety_comment \
 			    -Wrustdoc::missing_crate_level_docs
 
 KBUILD_HOSTCFLAGS   := $(KBUILD_USERHOSTCFLAGS) $(HOST_LFS_CFLAGS) \
diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs
index 3021f30fd822f..84c7cbfb096dc 100644
--- a/rust/kernel/sync/arc.rs
+++ b/rust/kernel/sync/arc.rs
@@ -341,7 +341,7 @@ impl<T: 'static> ForeignOwnable for Arc<T> {
     }
 
     unsafe fn borrow<'a>(ptr: *const core::ffi::c_void) -> ArcBorrow<'a, T> {
-        // SAFETY: By the safety requirement of this function, we know that `ptr` came from
+        // By the safety requirement of this function, we know that `ptr` came from
         // a previous call to `Arc::into_foreign`.
         let inner = NonNull::new(ptr as *mut ArcInner<T>).unwrap();
 
diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs
index 3b3f1dbe8192c..10d2bc62e2cff 100644
--- a/rust/kernel/workqueue.rs
+++ b/rust/kernel/workqueue.rs
@@ -526,7 +526,7 @@ where
     T: HasWork<T, ID>,
 {
     unsafe extern "C" fn run(ptr: *mut bindings::work_struct) {
-        // SAFETY: The `__enqueue` method always uses a `work_struct` stored in a `Work<T, ID>`.
+        // The `__enqueue` method always uses a `work_struct` stored in a `Work<T, ID>`.
         let ptr = ptr as *mut Work<T, ID>;
         // SAFETY: This computes the pointer that `__enqueue` got from `Arc::into_raw`.
         let ptr = unsafe { T::work_container_of(ptr) };
@@ -573,7 +573,7 @@ where
     T: HasWork<T, ID>,
 {
     unsafe extern "C" fn run(ptr: *mut bindings::work_struct) {
-        // SAFETY: The `__enqueue` method always uses a `work_struct` stored in a `Work<T, ID>`.
+        // The `__enqueue` method always uses a `work_struct` stored in a `Work<T, ID>`.
         let ptr = ptr as *mut Work<T, ID>;
         // SAFETY: This computes the pointer that `__enqueue` got from `Arc::into_raw`.
         let ptr = unsafe { T::work_container_of(ptr) };

From 23f42dc054b3c550373eae0c9ae97f1ce1501e0a Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:34 +0200
Subject: [PATCH 0231/1530] rust: enable `clippy::unnecessary_safety_doc` lint

In Rust 1.67.0, Clippy added the `unnecessary_safety_doc` lint [1],
which is similar to `unnecessary_safety_comment`, but for `# Safety`
sections, i.e. safety preconditions in the documentation.

This is something that should not happen with our coding guidelines in
mind. Thus enable the lint to have it machine-checked.

Link: https://rust-lang.github.io/rust-clippy/master/index.html#/unnecessary_safety_doc [1]
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-7-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Makefile b/Makefile
index 203f66154c143..3476afc707886 100644
--- a/Makefile
+++ b/Makefile
@@ -459,6 +459,7 @@ export rust_common_flags := --edition=2021 \
 			    -Wclippy::no_mangle_with_rust_abi \
 			    -Wclippy::undocumented_unsafe_blocks \
 			    -Wclippy::unnecessary_safety_comment \
+			    -Wclippy::unnecessary_safety_doc \
 			    -Wrustdoc::missing_crate_level_docs
 
 KBUILD_HOSTCFLAGS   := $(KBUILD_USERHOSTCFLAGS) $(HOST_LFS_CFLAGS) \

From 3fcc23397628c2357dbe66df59644e09f72ac725 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:35 +0200
Subject: [PATCH 0232/1530] rust: enable `clippy::ignored_unit_patterns` lint

In Rust 1.73.0, Clippy introduced the `ignored_unit_patterns` lint [1]:

> Matching with `()` explicitly instead of `_` outlines the fact that
> the pattern contains no data. Also it would detect a type change
> that `_` would ignore.

There is only a single case that requires a change:

    error: matching over `()` is more explicit
       --> rust/kernel/types.rs:176:45
        |
    176 |         ScopeGuard::new_with_data((), move |_| cleanup())
        |                                             ^ help: use `()` instead of `_`: `()`
        |
        = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#ignored_unit_patterns
        = note: requested on the command line with `-D clippy::ignored-unit-patterns`

Thus clean it up and enable the lint -- no functional change intended.

Link: https://rust-lang.github.io/rust-clippy/master/index.html#/ignored_unit_patterns [1]
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-8-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Makefile             | 1 +
 rust/kernel/types.rs | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 3476afc707886..b0696cd0599c7 100644
--- a/Makefile
+++ b/Makefile
@@ -453,6 +453,7 @@ export rust_common_flags := --edition=2021 \
 			    -Wunreachable_pub \
 			    -Wclippy::all \
 			    -Wclippy::dbg_macro \
+			    -Wclippy::ignored_unit_patterns \
 			    -Wclippy::mut_mut \
 			    -Wclippy::needless_bitwise_bool \
 			    -Wclippy::needless_continue \
diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index fd8e2b6039e04..28d9e5ea3df45 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -225,7 +225,7 @@ impl<T, F: FnOnce(T)> ScopeGuard<T, F> {
 impl ScopeGuard<(), fn(())> {
     /// Creates a new guarded object with the given cleanup function.
     pub fn new(cleanup: impl FnOnce()) -> ScopeGuard<(), impl FnOnce(())> {
-        ScopeGuard::new_with_data((), move |_| cleanup())
+        ScopeGuard::new_with_data((), move |()| cleanup())
     }
 }
 

From bef83245f5ed434932aaf07f890142b576dc5d85 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:36 +0200
Subject: [PATCH 0233/1530] rust: enable `rustdoc::unescaped_backticks` lint

In Rust 1.71.0, `rustdoc` added the `unescaped_backticks` lint, which
detects what are typically typos in Markdown formatting regarding inline
code [1], e.g. from the Rust standard library:

    /// ... to `deref`/`deref_mut`` must ...

    /// ... use [`from_mut`]`. Specifically, ...

It does not seem to have almost any false positives, from the experience
of enabling it in the Rust standard library [2], which will be checked
starting with Rust 1.82.0. The maintainers also confirmed it is ready
to be used.

Thus enable it.

Link: https://doc.rust-lang.org/rustdoc/lints.html#unescaped_backticks [1]
Link: https://github.com/rust-lang/rust/pull/128307 [2]
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-9-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Makefile      | 3 ++-
 rust/Makefile | 5 ++++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index b0696cd0599c7..3d32c314dd666 100644
--- a/Makefile
+++ b/Makefile
@@ -461,7 +461,8 @@ export rust_common_flags := --edition=2021 \
 			    -Wclippy::undocumented_unsafe_blocks \
 			    -Wclippy::unnecessary_safety_comment \
 			    -Wclippy::unnecessary_safety_doc \
-			    -Wrustdoc::missing_crate_level_docs
+			    -Wrustdoc::missing_crate_level_docs \
+			    -Wrustdoc::unescaped_backticks
 
 KBUILD_HOSTCFLAGS   := $(KBUILD_USERHOSTCFLAGS) $(HOST_LFS_CFLAGS) \
 		       $(HOSTCFLAGS) -I $(srctree)/scripts/include
diff --git a/rust/Makefile b/rust/Makefile
index b5e0a73b78f3e..0856fd6bc6105 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -61,7 +61,7 @@ alloc-cfgs = \
 quiet_cmd_rustdoc = RUSTDOC $(if $(rustdoc_host),H, ) $<
       cmd_rustdoc = \
 	OBJTREE=$(abspath $(objtree)) \
-	$(RUSTDOC) $(if $(rustdoc_host),$(rust_common_flags),$(rust_flags)) \
+	$(RUSTDOC) $(filter-out $(skip_flags),$(if $(rustdoc_host),$(rust_common_flags),$(rust_flags))) \
 		$(rustc_target_flags) -L$(objtree)/$(obj) \
 		-Zunstable-options --generate-link-to-definition \
 		--output $(rustdoc_output) \
@@ -98,6 +98,9 @@ rustdoc-macros: private rustc_target_flags = --crate-type proc-macro \
 rustdoc-macros: $(src)/macros/lib.rs FORCE
 	+$(call if_changed,rustdoc)
 
+# Starting with Rust 1.82.0, skipping `-Wrustdoc::unescaped_backticks` should
+# not be needed -- see https://github.com/rust-lang/rust/pull/128307.
+rustdoc-core: private skip_flags = -Wrustdoc::unescaped_backticks
 rustdoc-core: private rustc_target_flags = $(core-cfgs)
 rustdoc-core: $(RUST_LIB_SRC)/core/src/lib.rs FORCE
 	+$(call if_changed,rustdoc)

From d5cc7ab0a0a99496de1bd933dac242699a417809 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:37 +0200
Subject: [PATCH 0234/1530] rust: init: remove unneeded
 `#[allow(clippy::disallowed_names)]`

These few cases, unlike others in the same file, did not need the `allow`.

Thus clean them up.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-10-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/init.rs | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs
index 08b9d695c2851..aec26a4decb1a 100644
--- a/rust/kernel/init.rs
+++ b/rust/kernel/init.rs
@@ -87,7 +87,6 @@
 //! To declare an init macro/function you just return an [`impl PinInit<T, E>`]:
 //!
 //! ```rust
-//! # #![allow(clippy::disallowed_names)]
 //! # use kernel::{sync::Mutex, new_mutex, init::PinInit, try_pin_init};
 //! #[pin_data]
 //! struct DriverData {
@@ -368,7 +367,6 @@ macro_rules! stack_try_pin_init {
 /// The syntax is almost identical to that of a normal `struct` initializer:
 ///
 /// ```rust
-/// # #![allow(clippy::disallowed_names)]
 /// # use kernel::{init, pin_init, macros::pin_data, init::*};
 /// # use core::pin::Pin;
 /// #[pin_data]
@@ -413,7 +411,6 @@ macro_rules! stack_try_pin_init {
 /// To create an initializer function, simply declare it like this:
 ///
 /// ```rust
-/// # #![allow(clippy::disallowed_names)]
 /// # use kernel::{init, pin_init, init::*};
 /// # use core::pin::Pin;
 /// # #[pin_data]
@@ -468,7 +465,6 @@ macro_rules! stack_try_pin_init {
 /// They can also easily embed it into their own `struct`s:
 ///
 /// ```rust
-/// # #![allow(clippy::disallowed_names)]
 /// # use kernel::{init, pin_init, macros::pin_data, init::*};
 /// # use core::pin::Pin;
 /// # #[pin_data]

From 5e7c9b84ad08cc7a41b2ddbbbaccb60057da3860 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:38 +0200
Subject: [PATCH 0235/1530] rust: sync: remove unneeded
 `#[allow(clippy::non_send_fields_in_send_ty)]`

Rust 1.58.0 (before Rust was merged into the kernel) made Clippy's
`non_send_fields_in_send_ty` lint part of the `suspicious` lint group for
a brief window of time [1] until the minor version 1.58.1 got released
a week after, where the lint was moved back to `nursery`.

By that time, we had already upgraded to that Rust version, and thus we
had `allow`ed the lint here for `CondVar`.

Nowadays, Clippy's `non_send_fields_in_send_ty` would still trigger here
if it were enabled.

Moreover, if enabled, `Lock<T, B>` and `Task` would also require an
`allow`. Therefore, it does not seem like someone is actually enabling it
(in, e.g., a custom flags build).

Finally, the lint does not appear to have had major improvements since
then [2].

Thus remove the `allow` since it is unneeded.

Link: https://github.com/rust-lang/rust/blob/master/RELEASES.md#version-1581-2022-01-20 [1]
Link: https://github.com/rust-lang/rust-clippy/issues/8045 [2]
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-11-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/sync/condvar.rs | 1 -
 1 file changed, 1 deletion(-)

diff --git a/rust/kernel/sync/condvar.rs b/rust/kernel/sync/condvar.rs
index 7e00048bf4b14..dec2e5ffc9193 100644
--- a/rust/kernel/sync/condvar.rs
+++ b/rust/kernel/sync/condvar.rs
@@ -92,7 +92,6 @@ pub struct CondVar {
     _pin: PhantomPinned,
 }
 
-#[allow(clippy::non_send_fields_in_send_ty)]
 // SAFETY: `CondVar` only uses a `struct wait_queue_head`, which is safe to use on any thread.
 unsafe impl Send for CondVar {}
 

From 7d56786edcbdf58b6367fd7f01d5861214ad1c95 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:39 +0200
Subject: [PATCH 0236/1530] rust: introduce `.clippy.toml`

Some Clippy lints can be configured/tweaked. We will use these knobs to
our advantage in later commits.

This is done via a configuration file, `.clippy.toml` [1]. The file is
currently unstable. This may be a problem in the future, but we can adapt
as needed. In addition, we proposed adding Clippy to the Rust CI's RFL
job [2], so we should be able to catch issues pre-merge.

Thus introduce the file.

Link: https://doc.rust-lang.org/clippy/configuration.html [1]
Link: https://github.com/rust-lang/rust/pull/128928 [2]
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-12-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 .clippy.toml | 1 +
 .gitignore   | 1 +
 MAINTAINERS  | 1 +
 Makefile     | 3 +++
 4 files changed, 6 insertions(+)
 create mode 100644 .clippy.toml

diff --git a/.clippy.toml b/.clippy.toml
new file mode 100644
index 0000000000000..f66554cd5c451
--- /dev/null
+++ b/.clippy.toml
@@ -0,0 +1 @@
+# SPDX-License-Identifier: GPL-2.0
diff --git a/.gitignore b/.gitignore
index 56972adb5031a..a61e4778d011c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -103,6 +103,7 @@ modules.order
 # We don't want to ignore the following even if they are dot-files
 #
 !.clang-format
+!.clippy.toml
 !.cocciconfig
 !.editorconfig
 !.get_maintainer.ignore
diff --git a/MAINTAINERS b/MAINTAINERS
index a097afd76ded4..3380b87dcbb98 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20222,6 +20222,7 @@ B:	https://github.com/Rust-for-Linux/linux/issues
 C:	zulip://rust-for-linux.zulipchat.com
 P:	https://rust-for-linux.com/contributing
 T:	git https://github.com/Rust-for-Linux/linux.git rust-next
+F:	.clippy.toml
 F:	Documentation/rust/
 F:	rust/
 F:	samples/rust/
diff --git a/Makefile b/Makefile
index 3d32c314dd666..2fe8c97e81bbb 100644
--- a/Makefile
+++ b/Makefile
@@ -587,6 +587,9 @@ endif
 # Allows the usage of unstable features in stable compilers.
 export RUSTC_BOOTSTRAP := 1
 
+# Allows finding `.clippy.toml` in out-of-srctree builds.
+export CLIPPY_CONF_DIR := $(srctree)
+
 export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE LD CC HOSTPKG_CONFIG
 export RUSTC RUSTDOC RUSTFMT RUSTC_OR_CLIPPY_QUIET RUSTC_OR_CLIPPY BINDGEN
 export HOSTRUSTC KBUILD_HOSTRUSTFLAGS

From 8577c9dca799bd74377f7c30015d8cdc53a53ca2 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:40 +0200
Subject: [PATCH 0237/1530] rust: replace `clippy::dbg_macro` with
 `disallowed_macros`

Back when we used Rust 1.60.0 (before Rust was merged in the kernel),
we added `-Wclippy::dbg_macro` to the compilation flags. This worked
great with our custom `dbg!` macro (vendored from `std`, but slightly
modified to use the kernel printing facilities).

However, in the very next version, 1.61.0, it stopped working [1] since
the lint started to use a Rust diagnostic item rather than a path to find
the `dbg!` macro [1]. This behavior remains until the current nightly
(1.83.0).

Therefore, currently, the `dbg_macro` is not doing anything, which
explains why we can invoke `dbg!` in samples/rust/rust_print.rs`, as well
as why changing the `#[allow()]`s to `#[expect()]`s in `std_vendor.rs`
doctests does not work since they are not fulfilled.

One possible workaround is using `rustc_attrs` like the standard library
does. However, this is intended to be internal, and we just started
supporting several Rust compiler versions, so it is best to avoid it.

Therefore, instead, use `disallowed_macros`. It is a stable lint and
is more flexible (in that we can provide different macros), although
its diagnostic message(s) are not as nice as the specialized one (yet),
and does not allow to set different lint levels per macro/path [2].

In turn, this requires allowing the (intentional) `dbg!` use in the
sample, as one would have expected.

Finally, in a single case, the `allow` is fixed to be an inner attribute,
since otherwise it was not being applied.

Link: https://github.com/rust-lang/rust-clippy/issues/11303 [1]
Link: https://github.com/rust-lang/rust-clippy/issues/11307 [2]
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-13-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 .clippy.toml               |  6 ++++++
 Makefile                   |  1 -
 rust/kernel/std_vendor.rs  | 10 +++++-----
 samples/rust/rust_print.rs |  1 +
 4 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/.clippy.toml b/.clippy.toml
index f66554cd5c451..ad9f804fb6771 100644
--- a/.clippy.toml
+++ b/.clippy.toml
@@ -1 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
+
+disallowed-macros = [
+    # The `clippy::dbg_macro` lint only works with `std::dbg!`, thus we simulate
+    # it here, see: https://github.com/rust-lang/rust-clippy/issues/11303.
+    { path = "kernel::dbg", reason = "the `dbg!` macro is intended as a debugging tool" },
+]
diff --git a/Makefile b/Makefile
index 2fe8c97e81bbb..a9e723cb05961 100644
--- a/Makefile
+++ b/Makefile
@@ -452,7 +452,6 @@ export rust_common_flags := --edition=2021 \
 			    -Wrust_2018_idioms \
 			    -Wunreachable_pub \
 			    -Wclippy::all \
-			    -Wclippy::dbg_macro \
 			    -Wclippy::ignored_unit_patterns \
 			    -Wclippy::mut_mut \
 			    -Wclippy::needless_bitwise_bool \
diff --git a/rust/kernel/std_vendor.rs b/rust/kernel/std_vendor.rs
index 67bf9d37ddb55..085b23312c652 100644
--- a/rust/kernel/std_vendor.rs
+++ b/rust/kernel/std_vendor.rs
@@ -14,7 +14,7 @@
 ///
 /// ```rust
 /// let a = 2;
-/// # #[allow(clippy::dbg_macro)]
+/// # #[allow(clippy::disallowed_macros)]
 /// let b = dbg!(a * 2) + 1;
 /// //      ^-- prints: [src/main.rs:2] a * 2 = 4
 /// assert_eq!(b, 5);
@@ -52,7 +52,7 @@
 /// With a method call:
 ///
 /// ```rust
-/// # #[allow(clippy::dbg_macro)]
+/// # #[allow(clippy::disallowed_macros)]
 /// fn foo(n: usize) {
 ///     if dbg!(n.checked_sub(4)).is_some() {
 ///         // ...
@@ -71,7 +71,7 @@
 /// Naive factorial implementation:
 ///
 /// ```rust
-/// # #[allow(clippy::dbg_macro)]
+/// # #[allow(clippy::disallowed_macros)]
 /// # {
 /// fn factorial(n: u32) -> u32 {
 ///     if dbg!(n <= 1) {
@@ -118,7 +118,7 @@
 /// a tuple (and return it, too):
 ///
 /// ```
-/// # #[allow(clippy::dbg_macro)]
+/// # #![allow(clippy::disallowed_macros)]
 /// assert_eq!(dbg!(1usize, 2u32), (1, 2));
 /// ```
 ///
@@ -127,7 +127,7 @@
 /// invocations. You can use a 1-tuple directly if you need one:
 ///
 /// ```
-/// # #[allow(clippy::dbg_macro)]
+/// # #[allow(clippy::disallowed_macros)]
 /// # {
 /// assert_eq!(1, dbg!(1u32,)); // trailing comma ignored
 /// assert_eq!((1,), dbg!((1u32,))); // 1-tuple
diff --git a/samples/rust/rust_print.rs b/samples/rust/rust_print.rs
index 6eabb0d79ea3a..ed1137ab20188 100644
--- a/samples/rust/rust_print.rs
+++ b/samples/rust/rust_print.rs
@@ -15,6 +15,7 @@ module! {
 
 struct RustPrint;
 
+#[allow(clippy::disallowed_macros)]
 fn arc_print() -> Result {
     use kernel::sync::*;
 

From 8333ff4d0799aafbe4275cddcbaf45e545e4efba Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:41 +0200
Subject: [PATCH 0238/1530] rust: rbtree: fix `SAFETY` comments that should be
 `# Safety` sections

The tag `SAFETY` is used for safety comments, i.e. `// SAFETY`, while a
`Safety` section is used for safety preconditions in code documentation,
i.e. `/// # Safety`.

Fix the three instances recently added in `rbtree` that Clippy would
have normally caught in a public item, so that we can enable checking
of private items in one of the following commits.

Fixes: 98c14e40e07a ("rust: rbtree: add cursor")
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-14-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/rbtree.rs | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/rust/kernel/rbtree.rs b/rust/kernel/rbtree.rs
index 25eb36fd1cdce..d03e4aa1f4812 100644
--- a/rust/kernel/rbtree.rs
+++ b/rust/kernel/rbtree.rs
@@ -884,7 +884,8 @@ impl<'a, K, V> Cursor<'a, K, V> {
         NonNull::new(neighbor)
     }
 
-    /// SAFETY:
+    /// # Safety
+    ///
     /// - `node` must be a valid pointer to a node in an [`RBTree`].
     /// - The caller has immutable access to `node` for the duration of 'b.
     unsafe fn to_key_value<'b>(node: NonNull<bindings::rb_node>) -> (&'b K, &'b V) {
@@ -894,7 +895,8 @@ impl<'a, K, V> Cursor<'a, K, V> {
         (k, unsafe { &*v })
     }
 
-    /// SAFETY:
+    /// # Safety
+    ///
     /// - `node` must be a valid pointer to a node in an [`RBTree`].
     /// - The caller has mutable access to `node` for the duration of 'b.
     unsafe fn to_key_value_mut<'b>(node: NonNull<bindings::rb_node>) -> (&'b K, &'b mut V) {
@@ -904,7 +906,8 @@ impl<'a, K, V> Cursor<'a, K, V> {
         (k, unsafe { &mut *v })
     }
 
-    /// SAFETY:
+    /// # Safety
+    ///
     /// - `node` must be a valid pointer to a node in an [`RBTree`].
     /// - The caller has immutable access to the key for the duration of 'b.
     unsafe fn to_key_value_raw<'b>(node: NonNull<bindings::rb_node>) -> (&'b K, *mut V) {

From 2f390cc589433dfcfedc307a141e103929a6fd4d Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:42 +0200
Subject: [PATCH 0239/1530] rust: provide proper code documentation titles

Rust 1.82.0's Clippy is introducing [1][2] a new warn-by-default lint,
`too_long_first_doc_paragraph` [3], which is intended to catch titles
of code documentation items that are too long (likely because no title
was provided and the item documentation starts with a paragraph).

This lint does not currently trigger anywhere, but it does detect a couple
cases if checking for private items gets enabled (which we will do in
the next commit):

    error: first doc comment paragraph is too long
      --> rust/kernel/init/__internal.rs:18:1
       |
    18 | / /// This is the module-internal type implementing `PinInit` and `Init`. It is unsafe to create this
    19 | | /// type, since the closure needs to fulfill the same safety requirement as the
    20 | | /// `__pinned_init`/`__init` functions.
       | |_
       |
       = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#too_long_first_doc_paragraph
       = note: `-D clippy::too-long-first-doc-paragraph` implied by `-D warnings`
       = help: to override `-D warnings` add `#[allow(clippy::too_long_first_doc_paragraph)]`

    error: first doc comment paragraph is too long
     --> rust/kernel/sync/arc/std_vendor.rs:3:1
      |
    3 | / //! The contents of this file come from the Rust standard library, hosted in
    4 | | //! the <https://github.com/rust-lang/rust> repository, licensed under
    5 | | //! "Apache-2.0 OR MIT" and adapted for kernel use. For copyright details,
    6 | | //! see <https://github.com/rust-lang/rust/blob/master/COPYRIGHT>.
      | |_
      |
      = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#too_long_first_doc_paragraph

Thus clean those two instances.

In addition, since we have a second `std_vendor.rs` file with a similar
header, do the same there too (even if that one does not trigger the lint,
because it is `doc(hidden)`).

Link: https://github.com/rust-lang/rust/pull/129531 [1]
Link: https://github.com/rust-lang/rust-clippy/pull/12993 [2]
Link: https://rust-lang.github.io/rust-clippy/master/index.html#/too_long_first_doc_paragraph [3]
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-15-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/init/__internal.rs     | 7 ++++---
 rust/kernel/std_vendor.rs          | 2 ++
 rust/kernel/sync/arc/std_vendor.rs | 2 ++
 3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/rust/kernel/init/__internal.rs b/rust/kernel/init/__internal.rs
index 29f4fd00df3da..163eb072f296e 100644
--- a/rust/kernel/init/__internal.rs
+++ b/rust/kernel/init/__internal.rs
@@ -15,9 +15,10 @@ use super::*;
 /// [this table]: https://doc.rust-lang.org/nomicon/phantom-data.html#table-of-phantomdata-patterns
 pub(super) type Invariant<T> = PhantomData<fn(*mut T) -> *mut T>;
 
-/// This is the module-internal type implementing `PinInit` and `Init`. It is unsafe to create this
-/// type, since the closure needs to fulfill the same safety requirement as the
-/// `__pinned_init`/`__init` functions.
+/// Module-internal type implementing `PinInit` and `Init`.
+///
+/// It is unsafe to create this type, since the closure needs to fulfill the same safety
+/// requirement as the `__pinned_init`/`__init` functions.
 pub(crate) struct InitClosure<F, T: ?Sized, E>(pub(crate) F, pub(crate) Invariant<(E, T)>);
 
 // SAFETY: While constructing the `InitClosure`, the user promised that it upholds the
diff --git a/rust/kernel/std_vendor.rs b/rust/kernel/std_vendor.rs
index 085b23312c652..d59e4cf4b252d 100644
--- a/rust/kernel/std_vendor.rs
+++ b/rust/kernel/std_vendor.rs
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: Apache-2.0 OR MIT
 
+//! Rust standard library vendored code.
+//!
 //! The contents of this file come from the Rust standard library, hosted in
 //! the <https://github.com/rust-lang/rust> repository, licensed under
 //! "Apache-2.0 OR MIT" and adapted for kernel use. For copyright details,
diff --git a/rust/kernel/sync/arc/std_vendor.rs b/rust/kernel/sync/arc/std_vendor.rs
index a66a0c2831b3e..11b3f4ecca5f7 100644
--- a/rust/kernel/sync/arc/std_vendor.rs
+++ b/rust/kernel/sync/arc/std_vendor.rs
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: Apache-2.0 OR MIT
 
+//! Rust standard library vendored code.
+//!
 //! The contents of this file come from the Rust standard library, hosted in
 //! the <https://github.com/rust-lang/rust> repository, licensed under
 //! "Apache-2.0 OR MIT" and adapted for kernel use. For copyright details,

From 624063b9ac97f40cadca32a896aafeb28b1220fd Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:43 +0200
Subject: [PATCH 0240/1530] rust: enable Clippy's `check-private-items`

In Rust 1.76.0, Clippy added the `check-private-items` lint configuration
option. When turned on (the default is off), it makes several lints
check private items as well.

In our case, it affects two lints we have enabled [1]:
`missing_safety_doc` and `unnecessary_safety_doc`.

It also seems to affect the new `too_long_first_doc_paragraph` lint [2],
even though the documentation does not mention it.

Thus allow the few instances remaining we currently hit and enable
the lint.

Link: https://doc.rust-lang.org/nightly/clippy/lint_configuration.html#check-private-items [1]
Link: https://rust-lang.github.io/rust-clippy/master/index.html#/too_long_first_doc_paragraph [2]
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-16-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 .clippy.toml                   | 2 ++
 rust/kernel/init.rs            | 1 +
 rust/kernel/init/__internal.rs | 2 ++
 rust/kernel/init/macros.rs     | 1 +
 rust/kernel/print.rs           | 1 +
 5 files changed, 7 insertions(+)

diff --git a/.clippy.toml b/.clippy.toml
index ad9f804fb6771..e4c4eef10b28c 100644
--- a/.clippy.toml
+++ b/.clippy.toml
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
+check-private-items = true
+
 disallowed-macros = [
     # The `clippy::dbg_macro` lint only works with `std::dbg!`, thus we simulate
     # it here, see: https://github.com/rust-lang/rust-clippy/issues/11303.
diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs
index aec26a4decb1a..10ec90a5f5d8d 100644
--- a/rust/kernel/init.rs
+++ b/rust/kernel/init.rs
@@ -125,6 +125,7 @@
 //! use core::{ptr::addr_of_mut, marker::PhantomPinned, pin::Pin};
 //! # mod bindings {
 //! #     #![allow(non_camel_case_types)]
+//! #     #![allow(clippy::missing_safety_doc)]
 //! #     pub struct foo;
 //! #     pub unsafe fn init_foo(_ptr: *mut foo) {}
 //! #     pub unsafe fn destroy_foo(_ptr: *mut foo) {}
diff --git a/rust/kernel/init/__internal.rs b/rust/kernel/init/__internal.rs
index 163eb072f296e..549ae227c2eac 100644
--- a/rust/kernel/init/__internal.rs
+++ b/rust/kernel/init/__internal.rs
@@ -54,6 +54,7 @@ where
 pub unsafe trait HasPinData {
     type PinData: PinData;
 
+    #[allow(clippy::missing_safety_doc)]
     unsafe fn __pin_data() -> Self::PinData;
 }
 
@@ -83,6 +84,7 @@ pub unsafe trait PinData: Copy {
 pub unsafe trait HasInitData {
     type InitData: InitData;
 
+    #[allow(clippy::missing_safety_doc)]
     unsafe fn __init_data() -> Self::InitData;
 }
 
diff --git a/rust/kernel/init/macros.rs b/rust/kernel/init/macros.rs
index 736fe0ce0cd9d..193d39886b1f3 100644
--- a/rust/kernel/init/macros.rs
+++ b/rust/kernel/init/macros.rs
@@ -989,6 +989,7 @@ macro_rules! __pin_data {
         //
         // The functions are `unsafe` to prevent accidentally calling them.
         #[allow(dead_code)]
+        #[allow(clippy::missing_safety_doc)]
         impl<$($impl_generics)*> $pin_data<$($ty_generics)*>
         where $($whr)*
         {
diff --git a/rust/kernel/print.rs b/rust/kernel/print.rs
index fe53fc469c4f1..45af17095a248 100644
--- a/rust/kernel/print.rs
+++ b/rust/kernel/print.rs
@@ -14,6 +14,7 @@ use core::{
 use crate::str::RawFormatter;
 
 // Called from `vsprintf` with format specifier `%pA`.
+#[allow(clippy::missing_safety_doc)]
 #[no_mangle]
 unsafe extern "C" fn rust_fmt_argument(
     buf: *mut c_char,

From 139d396572ec4ba6e8cc5c02f5c8d5d1139be4b7 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:44 +0200
Subject: [PATCH 0241/1530] Documentation: rust: add coding guidelines on lints

In the C side, disabling diagnostics locally, i.e. within the source code,
is rare (at least in the kernel). Sometimes warnings are manipulated
via the flags at the translation unit level, but that is about it.

In Rust, it is easier to change locally the "level" of lints
(e.g. allowing them locally). In turn, this means it is easier to
globally enable more lints that may trigger a few false positives here
and there that need to be allowed locally, but that generally can spot
issues or bugs.

Thus document this.

Reviewed-by: Trevor Gross <tmgross@umich.edu>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-17-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Documentation/rust/coding-guidelines.rst | 38 ++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/Documentation/rust/coding-guidelines.rst b/Documentation/rust/coding-guidelines.rst
index 329b070a1d473..6db0420f0ceaf 100644
--- a/Documentation/rust/coding-guidelines.rst
+++ b/Documentation/rust/coding-guidelines.rst
@@ -227,3 +227,41 @@ The equivalent in Rust may look like (ignoring documentation):
 That is, the equivalent of ``GPIO_LINE_DIRECTION_IN`` would be referred to as
 ``gpio::LineDirection::In``. In particular, it should not be named
 ``gpio::gpio_line_direction::GPIO_LINE_DIRECTION_IN``.
+
+
+Lints
+-----
+
+In Rust, it is possible to ``allow`` particular warnings (diagnostics, lints)
+locally, making the compiler ignore instances of a given warning within a given
+function, module, block, etc.
+
+It is similar to ``#pragma GCC diagnostic push`` + ``ignored`` + ``pop`` in C
+[#]_:
+
+.. code-block:: c
+
+	#pragma GCC diagnostic push
+	#pragma GCC diagnostic ignored "-Wunused-function"
+	static void f(void) {}
+	#pragma GCC diagnostic pop
+
+.. [#] In this particular case, the kernel's ``__{always,maybe}_unused``
+       attributes (C23's ``[[maybe_unused]]``) may be used; however, the example
+       is meant to reflect the equivalent lint in Rust discussed afterwards.
+
+But way less verbose:
+
+.. code-block:: rust
+
+	#[allow(dead_code)]
+	fn f() {}
+
+By that virtue, it makes it possible to comfortably enable more diagnostics by
+default (i.e. outside ``W=`` levels). In particular, those that may have some
+false positives but that are otherwise quite useful to keep enabled to catch
+potential mistakes.
+
+For more information about diagnostics in Rust, please see:
+
+	https://doc.rust-lang.org/stable/reference/attributes/diagnostics.html

From 1f9ed172545687e5c04c77490a45896be6d2e459 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:45 +0200
Subject: [PATCH 0242/1530] rust: start using the `#[expect(...)]` attribute

In Rust, it is possible to `allow` particular warnings (diagnostics,
lints) locally, making the compiler ignore instances of a given warning
within a given function, module, block, etc.

It is similar to `#pragma GCC diagnostic push` + `ignored` + `pop` in C:

    #pragma GCC diagnostic push
    #pragma GCC diagnostic ignored "-Wunused-function"
    static void f(void) {}
    #pragma GCC diagnostic pop

But way less verbose:

    #[allow(dead_code)]
    fn f() {}

By that virtue, it makes it possible to comfortably enable more
diagnostics by default (i.e. outside `W=` levels) that may have some
false positives but that are otherwise quite useful to keep enabled to
catch potential mistakes.

The `#[expect(...)]` attribute [1] takes this further, and makes the
compiler warn if the diagnostic was _not_ produced. For instance, the
following will ensure that, when `f()` is called somewhere, we will have
to remove the attribute:

    #[expect(dead_code)]
    fn f() {}

If we do not, we get a warning from the compiler:

    warning: this lint expectation is unfulfilled
     --> x.rs:3:10
      |
    3 | #[expect(dead_code)]
      |          ^^^^^^^^^
      |
      = note: `#[warn(unfulfilled_lint_expectations)]` on by default

This means that `expect`s do not get forgotten when they are not needed.

See the next commit for more details, nuances on its usage and
documentation on the feature.

The attribute requires the `lint_reasons` [2] unstable feature, but it
is becoming stable in 1.81.0 (to be released on 2024-09-05) and it has
already been useful to clean things up in this patch series, finding
cases where the `allow`s should not have been there.

Thus, enable `lint_reasons` and convert some of our `allow`s to `expect`s
where possible.

This feature was also an example of the ongoing collaboration between
Rust and the kernel -- we tested it in the kernel early on and found an
issue that was quickly resolved [3].

Cc: Fridtjof Stoldt <xfrednet@gmail.com>
Cc: Urgau <urgau@numericable.fr>
Link: https://rust-lang.github.io/rfcs/2383-lint-reasons.html#expect-lint-attribute [1]
Link: https://github.com/rust-lang/rust/issues/54503 [2]
Link: https://github.com/rust-lang/rust/issues/114557 [3]
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-18-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/error.rs           |  2 +-
 rust/kernel/init.rs            | 22 +++++++++++-----------
 rust/kernel/init/__internal.rs |  4 ++--
 rust/kernel/init/macros.rs     | 10 +++++-----
 rust/kernel/ioctl.rs           |  2 +-
 rust/kernel/lib.rs             |  1 +
 rust/kernel/list/arc_field.rs  |  2 +-
 rust/kernel/print.rs           |  4 ++--
 rust/kernel/std_vendor.rs      | 10 +++++-----
 samples/rust/rust_print.rs     |  2 +-
 scripts/Makefile.build         |  2 +-
 11 files changed, 31 insertions(+), 30 deletions(-)

diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs
index 639bc7572f901..a681acda87ce0 100644
--- a/rust/kernel/error.rs
+++ b/rust/kernel/error.rs
@@ -133,7 +133,7 @@ impl Error {
     }
 
     /// Returns the error encoded as a pointer.
-    #[allow(dead_code)]
+    #[expect(dead_code)]
     pub(crate) fn to_ptr<T>(self) -> *mut T {
         #[cfg_attr(target_pointer_width = "32", allow(clippy::useless_conversion))]
         // SAFETY: `self.0` is a valid error due to its invariant.
diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs
index 10ec90a5f5d8d..25057cbed40b5 100644
--- a/rust/kernel/init.rs
+++ b/rust/kernel/init.rs
@@ -35,7 +35,7 @@
 //! that you need to write `<-` instead of `:` for fields that you want to initialize in-place.
 //!
 //! ```rust
-//! # #![allow(clippy::disallowed_names)]
+//! # #![expect(clippy::disallowed_names)]
 //! use kernel::sync::{new_mutex, Mutex};
 //! # use core::pin::Pin;
 //! #[pin_data]
@@ -55,7 +55,7 @@
 //! (or just the stack) to actually initialize a `Foo`:
 //!
 //! ```rust
-//! # #![allow(clippy::disallowed_names)]
+//! # #![expect(clippy::disallowed_names)]
 //! # use kernel::sync::{new_mutex, Mutex};
 //! # use core::pin::Pin;
 //! # #[pin_data]
@@ -120,12 +120,12 @@
 //!   `slot` gets called.
 //!
 //! ```rust
-//! # #![allow(unreachable_pub, clippy::disallowed_names)]
+//! # #![expect(unreachable_pub, clippy::disallowed_names)]
 //! use kernel::{init, types::Opaque};
 //! use core::{ptr::addr_of_mut, marker::PhantomPinned, pin::Pin};
 //! # mod bindings {
-//! #     #![allow(non_camel_case_types)]
-//! #     #![allow(clippy::missing_safety_doc)]
+//! #     #![expect(non_camel_case_types)]
+//! #     #![expect(clippy::missing_safety_doc)]
 //! #     pub struct foo;
 //! #     pub unsafe fn init_foo(_ptr: *mut foo) {}
 //! #     pub unsafe fn destroy_foo(_ptr: *mut foo) {}
@@ -238,7 +238,7 @@ pub mod macros;
 /// # Examples
 ///
 /// ```rust
-/// # #![allow(clippy::disallowed_names)]
+/// # #![expect(clippy::disallowed_names)]
 /// # use kernel::{init, macros::pin_data, pin_init, stack_pin_init, init::*, sync::Mutex, new_mutex};
 /// # use core::pin::Pin;
 /// #[pin_data]
@@ -290,7 +290,7 @@ macro_rules! stack_pin_init {
 /// # Examples
 ///
 /// ```rust,ignore
-/// # #![allow(clippy::disallowed_names)]
+/// # #![expect(clippy::disallowed_names)]
 /// # use kernel::{init, pin_init, stack_try_pin_init, init::*, sync::Mutex, new_mutex};
 /// # use macros::pin_data;
 /// # use core::{alloc::AllocError, pin::Pin};
@@ -316,7 +316,7 @@ macro_rules! stack_pin_init {
 /// ```
 ///
 /// ```rust,ignore
-/// # #![allow(clippy::disallowed_names)]
+/// # #![expect(clippy::disallowed_names)]
 /// # use kernel::{init, pin_init, stack_try_pin_init, init::*, sync::Mutex, new_mutex};
 /// # use macros::pin_data;
 /// # use core::{alloc::AllocError, pin::Pin};
@@ -438,7 +438,7 @@ macro_rules! stack_try_pin_init {
 /// Users of `Foo` can now create it like this:
 ///
 /// ```rust
-/// # #![allow(clippy::disallowed_names)]
+/// # #![expect(clippy::disallowed_names)]
 /// # use kernel::{init, pin_init, macros::pin_data, init::*};
 /// # use core::pin::Pin;
 /// # #[pin_data]
@@ -852,7 +852,7 @@ pub unsafe trait PinInit<T: ?Sized, E = Infallible>: Sized {
     /// # Examples
     ///
     /// ```rust
-    /// # #![allow(clippy::disallowed_names)]
+    /// # #![expect(clippy::disallowed_names)]
     /// use kernel::{types::Opaque, init::pin_init_from_closure};
     /// #[repr(C)]
     /// struct RawFoo([u8; 16]);
@@ -964,7 +964,7 @@ pub unsafe trait Init<T: ?Sized, E = Infallible>: PinInit<T, E> {
     /// # Examples
     ///
     /// ```rust
-    /// # #![allow(clippy::disallowed_names)]
+    /// # #![expect(clippy::disallowed_names)]
     /// use kernel::{types::Opaque, init::{self, init_from_closure}};
     /// struct Foo {
     ///     buf: [u8; 1_000_000],
diff --git a/rust/kernel/init/__internal.rs b/rust/kernel/init/__internal.rs
index 549ae227c2eac..44431fba7aabf 100644
--- a/rust/kernel/init/__internal.rs
+++ b/rust/kernel/init/__internal.rs
@@ -54,7 +54,7 @@ where
 pub unsafe trait HasPinData {
     type PinData: PinData;
 
-    #[allow(clippy::missing_safety_doc)]
+    #[expect(clippy::missing_safety_doc)]
     unsafe fn __pin_data() -> Self::PinData;
 }
 
@@ -84,7 +84,7 @@ pub unsafe trait PinData: Copy {
 pub unsafe trait HasInitData {
     type InitData: InitData;
 
-    #[allow(clippy::missing_safety_doc)]
+    #[expect(clippy::missing_safety_doc)]
     unsafe fn __init_data() -> Self::InitData;
 }
 
diff --git a/rust/kernel/init/macros.rs b/rust/kernel/init/macros.rs
index 193d39886b1f3..1fd146a832416 100644
--- a/rust/kernel/init/macros.rs
+++ b/rust/kernel/init/macros.rs
@@ -182,13 +182,13 @@
 //!     // Normally `Drop` bounds do not have the correct semantics, but for this purpose they do
 //!     // (normally people want to know if a type has any kind of drop glue at all, here we want
 //!     // to know if it has any kind of custom drop glue, which is exactly what this bound does).
-//!     #[allow(drop_bounds)]
+//!     #[expect(drop_bounds)]
 //!     impl<T: ::core::ops::Drop> MustNotImplDrop for T {}
 //!     impl<T> MustNotImplDrop for Bar<T> {}
 //!     // Here comes a convenience check, if one implemented `PinnedDrop`, but forgot to add it to
 //!     // `#[pin_data]`, then this will error with the same mechanic as above, this is not needed
 //!     // for safety, but a good sanity check, since no normal code calls `PinnedDrop::drop`.
-//!     #[allow(non_camel_case_types)]
+//!     #[expect(non_camel_case_types)]
 //!     trait UselessPinnedDropImpl_you_need_to_specify_PinnedDrop {}
 //!     impl<
 //!         T: ::kernel::init::PinnedDrop,
@@ -925,14 +925,14 @@ macro_rules! __pin_data {
         // `Drop`. Additionally we will implement this trait for the struct leading to a conflict,
         // if it also implements `Drop`
         trait MustNotImplDrop {}
-        #[allow(drop_bounds)]
+        #[expect(drop_bounds)]
         impl<T: ::core::ops::Drop> MustNotImplDrop for T {}
         impl<$($impl_generics)*> MustNotImplDrop for $name<$($ty_generics)*>
         where $($whr)* {}
         // We also take care to prevent users from writing a useless `PinnedDrop` implementation.
         // They might implement `PinnedDrop` correctly for the struct, but forget to give
         // `PinnedDrop` as the parameter to `#[pin_data]`.
-        #[allow(non_camel_case_types)]
+        #[expect(non_camel_case_types)]
         trait UselessPinnedDropImpl_you_need_to_specify_PinnedDrop {}
         impl<T: $crate::init::PinnedDrop>
             UselessPinnedDropImpl_you_need_to_specify_PinnedDrop for T {}
@@ -989,7 +989,7 @@ macro_rules! __pin_data {
         //
         // The functions are `unsafe` to prevent accidentally calling them.
         #[allow(dead_code)]
-        #[allow(clippy::missing_safety_doc)]
+        #[expect(clippy::missing_safety_doc)]
         impl<$($impl_generics)*> $pin_data<$($ty_generics)*>
         where $($whr)*
         {
diff --git a/rust/kernel/ioctl.rs b/rust/kernel/ioctl.rs
index cfa7d080b5319..2fc7662339e54 100644
--- a/rust/kernel/ioctl.rs
+++ b/rust/kernel/ioctl.rs
@@ -4,7 +4,7 @@
 //!
 //! C header: [`include/asm-generic/ioctl.h`](srctree/include/asm-generic/ioctl.h)
 
-#![allow(non_snake_case)]
+#![expect(non_snake_case)]
 
 use crate::build_assert;
 
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index b5f4b3ce6b482..f329638fc5e06 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -14,6 +14,7 @@
 #![no_std]
 #![feature(coerce_unsized)]
 #![feature(dispatch_from_dyn)]
+#![feature(lint_reasons)]
 #![feature(new_uninit)]
 #![feature(receiver_trait)]
 #![feature(unsize)]
diff --git a/rust/kernel/list/arc_field.rs b/rust/kernel/list/arc_field.rs
index 2330f673427ab..c4b9dd5039826 100644
--- a/rust/kernel/list/arc_field.rs
+++ b/rust/kernel/list/arc_field.rs
@@ -56,7 +56,7 @@ impl<T, const ID: u64> ListArcField<T, ID> {
     ///
     /// The caller must have mutable access to the `ListArc<ID>` containing the struct with this
     /// field for the duration of the returned reference.
-    #[allow(clippy::mut_from_ref)]
+    #[expect(clippy::mut_from_ref)]
     pub unsafe fn assert_mut(&self) -> &mut T {
         // SAFETY: The caller has exclusive access to the `ListArc`, so they also have exclusive
         // access to this field.
diff --git a/rust/kernel/print.rs b/rust/kernel/print.rs
index 45af17095a248..a28077a7cb301 100644
--- a/rust/kernel/print.rs
+++ b/rust/kernel/print.rs
@@ -14,7 +14,7 @@ use core::{
 use crate::str::RawFormatter;
 
 // Called from `vsprintf` with format specifier `%pA`.
-#[allow(clippy::missing_safety_doc)]
+#[expect(clippy::missing_safety_doc)]
 #[no_mangle]
 unsafe extern "C" fn rust_fmt_argument(
     buf: *mut c_char,
@@ -140,7 +140,7 @@ pub fn call_printk_cont(args: fmt::Arguments<'_>) {
 #[doc(hidden)]
 #[cfg(not(testlib))]
 #[macro_export]
-#[allow(clippy::crate_in_macro_def)]
+#[expect(clippy::crate_in_macro_def)]
 macro_rules! print_macro (
     // The non-continuation cases (most of them, e.g. `INFO`).
     ($format_string:path, false, $($arg:tt)+) => (
diff --git a/rust/kernel/std_vendor.rs b/rust/kernel/std_vendor.rs
index d59e4cf4b252d..8b4872b48e977 100644
--- a/rust/kernel/std_vendor.rs
+++ b/rust/kernel/std_vendor.rs
@@ -16,7 +16,7 @@
 ///
 /// ```rust
 /// let a = 2;
-/// # #[allow(clippy::disallowed_macros)]
+/// # #[expect(clippy::disallowed_macros)]
 /// let b = dbg!(a * 2) + 1;
 /// //      ^-- prints: [src/main.rs:2] a * 2 = 4
 /// assert_eq!(b, 5);
@@ -54,7 +54,7 @@
 /// With a method call:
 ///
 /// ```rust
-/// # #[allow(clippy::disallowed_macros)]
+/// # #[expect(clippy::disallowed_macros)]
 /// fn foo(n: usize) {
 ///     if dbg!(n.checked_sub(4)).is_some() {
 ///         // ...
@@ -73,7 +73,7 @@
 /// Naive factorial implementation:
 ///
 /// ```rust
-/// # #[allow(clippy::disallowed_macros)]
+/// # #[expect(clippy::disallowed_macros)]
 /// # {
 /// fn factorial(n: u32) -> u32 {
 ///     if dbg!(n <= 1) {
@@ -120,7 +120,7 @@
 /// a tuple (and return it, too):
 ///
 /// ```
-/// # #![allow(clippy::disallowed_macros)]
+/// # #![expect(clippy::disallowed_macros)]
 /// assert_eq!(dbg!(1usize, 2u32), (1, 2));
 /// ```
 ///
@@ -129,7 +129,7 @@
 /// invocations. You can use a 1-tuple directly if you need one:
 ///
 /// ```
-/// # #[allow(clippy::disallowed_macros)]
+/// # #[expect(clippy::disallowed_macros)]
 /// # {
 /// assert_eq!(1, dbg!(1u32,)); // trailing comma ignored
 /// assert_eq!((1,), dbg!((1u32,))); // 1-tuple
diff --git a/samples/rust/rust_print.rs b/samples/rust/rust_print.rs
index ed1137ab20188..ba1606bdbd754 100644
--- a/samples/rust/rust_print.rs
+++ b/samples/rust/rust_print.rs
@@ -15,7 +15,7 @@ module! {
 
 struct RustPrint;
 
-#[allow(clippy::disallowed_macros)]
+#[expect(clippy::disallowed_macros)]
 fn arc_print() -> Result {
     use kernel::sync::*;
 
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 8f423a1faf507..0a9ea56db1002 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -248,7 +248,7 @@ $(obj)/%.lst: $(obj)/%.c FORCE
 # Compile Rust sources (.rs)
 # ---------------------------------------------------------------------------
 
-rust_allowed_features := new_uninit
+rust_allowed_features := lint_reasons,new_uninit
 
 # `--out-dir` is required to avoid temporaries being created by `rustc` in the
 # current working directory, which may be not accessible in the out-of-tree

From 04866494e936d041fd196d3a36aecd979e4ef078 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:46 +0200
Subject: [PATCH 0243/1530] Documentation: rust: discuss `#[expect(...)]` in
 the guidelines

Discuss `#[expect(...)]` in the Lints sections of the coding guidelines
document, which is an upcoming feature in Rust 1.81.0, and explain that
it is generally to be preferred over `allow` unless there is a reason
not to use it (e.g. conditional compilation being involved).

Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-19-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Documentation/rust/coding-guidelines.rst | 110 +++++++++++++++++++++++
 1 file changed, 110 insertions(+)

diff --git a/Documentation/rust/coding-guidelines.rst b/Documentation/rust/coding-guidelines.rst
index 6db0420f0ceaf..f7194f7124b07 100644
--- a/Documentation/rust/coding-guidelines.rst
+++ b/Documentation/rust/coding-guidelines.rst
@@ -262,6 +262,116 @@ default (i.e. outside ``W=`` levels). In particular, those that may have some
 false positives but that are otherwise quite useful to keep enabled to catch
 potential mistakes.
 
+On top of that, Rust provides the ``expect`` attribute which takes this further.
+It makes the compiler warn if the warning was not produced. For instance, the
+following will ensure that, when ``f()`` is called somewhere, we will have to
+remove the attribute:
+
+.. code-block:: rust
+
+	#[expect(dead_code)]
+	fn f() {}
+
+If we do not, we get a warning from the compiler::
+
+	warning: this lint expectation is unfulfilled
+	 --> x.rs:3:10
+	  |
+	3 | #[expect(dead_code)]
+	  |          ^^^^^^^^^
+	  |
+	  = note: `#[warn(unfulfilled_lint_expectations)]` on by default
+
+This means that ``expect``\ s do not get forgotten when they are not needed, which
+may happen in several situations, e.g.:
+
+- Temporary attributes added while developing.
+
+- Improvements in lints in the compiler, Clippy or custom tools which may
+  remove a false positive.
+
+- When the lint is not needed anymore because it was expected that it would be
+  removed at some point, such as the ``dead_code`` example above.
+
+It also increases the visibility of the remaining ``allow``\ s and reduces the
+chance of misapplying one.
+
+Thus prefer ``except`` over ``allow`` unless:
+
+- The lint attribute is intended to be temporary, e.g. while developing.
+
+- Conditional compilation triggers the warning in some cases but not others.
+
+  If there are only a few cases where the warning triggers (or does not
+  trigger) compared to the total number of cases, then one may consider using
+  a conditional ``expect`` (i.e. ``cfg_attr(..., expect(...))``). Otherwise,
+  it is likely simpler to just use ``allow``.
+
+- Inside macros, when the different invocations may create expanded code that
+  triggers the warning in some cases but not in others.
+
+- When code may trigger a warning for some architectures but not others, such
+  as an ``as`` cast to a C FFI type.
+
+As a more developed example, consider for instance this program:
+
+.. code-block:: rust
+
+	fn g() {}
+
+	fn main() {
+	    #[cfg(CONFIG_X)]
+	    g();
+	}
+
+Here, function ``g()`` is dead code if ``CONFIG_X`` is not set. Can we use
+``expect`` here?
+
+.. code-block:: rust
+
+	#[expect(dead_code)]
+	fn g() {}
+
+	fn main() {
+	    #[cfg(CONFIG_X)]
+	    g();
+	}
+
+This would emit a lint if ``CONFIG_X`` is set, since it is not dead code in that
+configuration. Therefore, in cases like this, we cannot use ``expect`` as-is.
+
+A simple possibility is using ``allow``:
+
+.. code-block:: rust
+
+	#[allow(dead_code)]
+	fn g() {}
+
+	fn main() {
+	    #[cfg(CONFIG_X)]
+	    g();
+	}
+
+An alternative would be using a conditional ``expect``:
+
+.. code-block:: rust
+
+	#[cfg_attr(not(CONFIG_X), expect(dead_code))]
+	fn g() {}
+
+	fn main() {
+	    #[cfg(CONFIG_X)]
+	    g();
+	}
+
+This would ensure that, if someone introduces another call to ``g()`` somewhere
+(e.g. unconditionally), then it would be spotted that it is not dead code
+anymore. However, the ``cfg_attr`` is more complex than a simple ``allow``.
+
+Therefore, it is likely that it is not worth using conditional ``expect``\ s when
+more than one or two configurations are involved or when the lint may be
+triggered due to non-local changes (such as ``dead_code``).
+
 For more information about diagnostics in Rust, please see:
 
 	https://doc.rust-lang.org/stable/reference/attributes/diagnostics.html

From 1c71ddb310ad04ccec70441c7f17089514e3bab8 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 4 Sep 2024 22:43:47 +0200
Subject: [PATCH 0244/1530] rust: std_vendor: simplify `{ .. macro! .. }` with
 inner attributes

It is cleaner to have a single inner attribute rather than needing
several hidden lines to wrap the macro invocations.

Thus simplify them.

Reviewed-by: Vincenzo Palazzo <vincenzopalazzodev@gmail.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Tested-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240904204347.168520-20-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/std_vendor.rs | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/rust/kernel/std_vendor.rs b/rust/kernel/std_vendor.rs
index 8b4872b48e977..8f27d447a7fca 100644
--- a/rust/kernel/std_vendor.rs
+++ b/rust/kernel/std_vendor.rs
@@ -73,8 +73,7 @@
 /// Naive factorial implementation:
 ///
 /// ```rust
-/// # #[expect(clippy::disallowed_macros)]
-/// # {
+/// # #![expect(clippy::disallowed_macros)]
 /// fn factorial(n: u32) -> u32 {
 ///     if dbg!(n <= 1) {
 ///         dbg!(1)
@@ -84,7 +83,6 @@
 /// }
 ///
 /// dbg!(factorial(4));
-/// # }
 /// ```
 ///
 /// This prints to the kernel log:
@@ -129,11 +127,9 @@
 /// invocations. You can use a 1-tuple directly if you need one:
 ///
 /// ```
-/// # #[expect(clippy::disallowed_macros)]
-/// # {
+/// # #![expect(clippy::disallowed_macros)]
 /// assert_eq!(1, dbg!(1u32,)); // trailing comma ignored
 /// assert_eq!((1,), dbg!((1u32,))); // 1-tuple
-/// # }
 /// ```
 ///
 /// [`std::dbg`]: https://doc.rust-lang.org/std/macro.dbg.html

From c95bbb59a9b22f9b838b15d28319185c1c884329 Mon Sep 17 00:00:00 2001
From: Gary Guo <gary@garyguo.net>
Date: Sun, 15 Sep 2024 14:26:31 +0100
Subject: [PATCH 0245/1530] rust: enable arbitrary_self_types and remove
 `Receiver`

The term "receiver" means that a type can be used as the type of `self`,
and thus enables method call syntax `foo.bar()` instead of
`Foo::bar(foo)`. Stable Rust as of today (1.81) enables a limited
selection of types (primitives and types in std, e.g. `Box` and `Arc`)
to be used as receivers, while custom types cannot.

We want the kernel `Arc` type to have the same functionality as the Rust
std `Arc`, so we use the `Receiver` trait (gated behind `receiver_trait`
unstable feature) to gain the functionality.

The `arbitrary_self_types` RFC [1] (tracking issue [2]) is accepted and
it will allow all types that implement a new `Receiver` trait (different
from today's unstable trait) to be used as receivers. This trait will be
automatically implemented for all `Deref` types, which include our `Arc`
type, so we no longer have to opt-in to be used as receiver. To prepare
us for the change, remove the `Receiver` implementation and the
associated feature. To still allow `Arc` and others to be used as method
receivers, turn on `arbitrary_self_types` feature instead.

This feature gate is introduced in 1.23.0. It used to enable both
`Deref` types and raw pointer types to be used as receivers, but the
latter is now split into a different feature gate in Rust 1.83 nightly.
We do not need receivers on raw pointers so this change would not affect
us and usage of `arbitrary_self_types` feature would work for all Rust
versions that we support (>=1.78).

Cc: Adrian Taylor <ade@hohum.me.uk>
Link: https://github.com/rust-lang/rfcs/pull/3519 [1]
Link: https://github.com/rust-lang/rust/issues/44874 [2]
Signed-off-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20240915132734.1653004-1-gary@garyguo.net
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/lib.rs      | 2 +-
 rust/kernel/list/arc.rs | 3 ---
 rust/kernel/sync/arc.rs | 6 ------
 scripts/Makefile.build  | 2 +-
 4 files changed, 2 insertions(+), 11 deletions(-)

diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index f329638fc5e06..3e4bd6e57bee5 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -12,11 +12,11 @@
 //! do so first instead of bypassing this crate.
 
 #![no_std]
+#![feature(arbitrary_self_types)]
 #![feature(coerce_unsized)]
 #![feature(dispatch_from_dyn)]
 #![feature(lint_reasons)]
 #![feature(new_uninit)]
-#![feature(receiver_trait)]
 #![feature(unsize)]
 
 // Ensure conditional compilation based on the kernel configuration works;
diff --git a/rust/kernel/list/arc.rs b/rust/kernel/list/arc.rs
index d801b9dc6291d..3483d8c232c4f 100644
--- a/rust/kernel/list/arc.rs
+++ b/rust/kernel/list/arc.rs
@@ -441,9 +441,6 @@ where
     }
 }
 
-// This is to allow [`ListArc`] (and variants) to be used as the type of `self`.
-impl<T, const ID: u64> core::ops::Receiver for ListArc<T, ID> where T: ListArcSafe<ID> + ?Sized {}
-
 // This is to allow coercion from `ListArc<T>` to `ListArc<U>` if `T` can be converted to the
 // dynamically-sized type (DST) `U`.
 impl<T, U, const ID: u64> core::ops::CoerceUnsized<ListArc<U, ID>> for ListArc<T, ID>
diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs
index 84c7cbfb096dc..9325cc5a16a4c 100644
--- a/rust/kernel/sync/arc.rs
+++ b/rust/kernel/sync/arc.rs
@@ -171,9 +171,6 @@ impl<T: ?Sized> ArcInner<T> {
     }
 }
 
-// This is to allow [`Arc`] (and variants) to be used as the type of `self`.
-impl<T: ?Sized> core::ops::Receiver for Arc<T> {}
-
 // This is to allow coercion from `Arc<T>` to `Arc<U>` if `T` can be converted to the
 // dynamically-sized type (DST) `U`.
 impl<T: ?Sized + Unsize<U>, U: ?Sized> core::ops::CoerceUnsized<Arc<U>> for Arc<T> {}
@@ -480,9 +477,6 @@ pub struct ArcBorrow<'a, T: ?Sized + 'a> {
     _p: PhantomData<&'a ()>,
 }
 
-// This is to allow [`ArcBorrow`] (and variants) to be used as the type of `self`.
-impl<T: ?Sized> core::ops::Receiver for ArcBorrow<'_, T> {}
-
 // This is to allow `ArcBorrow<U>` to be dispatched on when `ArcBorrow<T>` can be coerced into
 // `ArcBorrow<U>`.
 impl<T: ?Sized + Unsize<U>, U: ?Sized> core::ops::DispatchFromDyn<ArcBorrow<'_, U>>
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 0a9ea56db1002..64518c2f3d9c3 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -248,7 +248,7 @@ $(obj)/%.lst: $(obj)/%.c FORCE
 # Compile Rust sources (.rs)
 # ---------------------------------------------------------------------------
 
-rust_allowed_features := lint_reasons,new_uninit
+rust_allowed_features := arbitrary_self_types,lint_reasons,new_uninit
 
 # `--out-dir` is required to avoid temporaries being created by `rustc` in the
 # current working directory, which may be not accessible in the out-of-tree

From 5ed147473458f8c20f908a03227d8f5bb3cb8f7d Mon Sep 17 00:00:00 2001
From: Filipe Xavier <felipe_life@live.com>
Date: Fri, 13 Sep 2024 07:19:56 -0300
Subject: [PATCH 0246/1530] rust: error: make conversion functions public

Change visibility to public of functions in error.rs:
from_err_ptr, from_errno, from_result and to_ptr.
Additionally, remove dead_code annotations.

Link: https://github.com/Rust-for-Linux/linux/issues/1105
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Filipe Xavier <felipe_life@live.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/DM4PR14MB7276E6948E67B3B23D8EA847E9652@DM4PR14MB7276.namprd14.prod.outlook.com
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/error.rs | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs
index a681acda87ce0..2f1e4b783bfb3 100644
--- a/rust/kernel/error.rs
+++ b/rust/kernel/error.rs
@@ -95,7 +95,7 @@ impl Error {
     ///
     /// It is a bug to pass an out-of-range `errno`. `EINVAL` would
     /// be returned in such a case.
-    pub(crate) fn from_errno(errno: core::ffi::c_int) -> Error {
+    pub fn from_errno(errno: core::ffi::c_int) -> Error {
         if errno < -(bindings::MAX_ERRNO as i32) || errno >= 0 {
             // TODO: Make it a `WARN_ONCE` once available.
             crate::pr_warn!(
@@ -133,8 +133,7 @@ impl Error {
     }
 
     /// Returns the error encoded as a pointer.
-    #[expect(dead_code)]
-    pub(crate) fn to_ptr<T>(self) -> *mut T {
+    pub fn to_ptr<T>(self) -> *mut T {
         #[cfg_attr(target_pointer_width = "32", allow(clippy::useless_conversion))]
         // SAFETY: `self.0` is a valid error due to its invariant.
         unsafe {
@@ -270,9 +269,7 @@ pub fn to_result(err: core::ffi::c_int) -> Result {
 ///     from_err_ptr(unsafe { bindings::devm_platform_ioremap_resource(pdev.to_ptr(), index) })
 /// }
 /// ```
-// TODO: Remove `dead_code` marker once an in-kernel client is available.
-#[allow(dead_code)]
-pub(crate) fn from_err_ptr<T>(ptr: *mut T) -> Result<*mut T> {
+pub fn from_err_ptr<T>(ptr: *mut T) -> Result<*mut T> {
     // CAST: Casting a pointer to `*const core::ffi::c_void` is always valid.
     let const_ptr: *const core::ffi::c_void = ptr.cast();
     // SAFETY: The FFI function does not deref the pointer.
@@ -318,9 +315,7 @@ pub(crate) fn from_err_ptr<T>(ptr: *mut T) -> Result<*mut T> {
 ///     })
 /// }
 /// ```
-// TODO: Remove `dead_code` marker once an in-kernel client is available.
-#[allow(dead_code)]
-pub(crate) fn from_result<T, F>(f: F) -> T
+pub fn from_result<T, F>(f: F) -> T
 where
     T: From<i16>,
     F: FnOnce() -> Result<T>,

From e0020ba6cbcbfbaaa50c3d4b610c7caa36459624 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 2 Oct 2024 13:38:10 +0200
Subject: [PATCH 0247/1530] rust: add PidNamespace

The lifetime of `PidNamespace` is bound to `Task` and `struct pid`.

The `PidNamespace` of a `Task` doesn't ever change once the `Task` is
alive. A `unshare(CLONE_NEWPID)` or `setns(fd_pidns/pidfd, CLONE_NEWPID)`
will not have an effect on the calling `Task`'s pid namespace. It will
only effect the pid namespace of children created by the calling `Task`.
This invariant guarantees that after having acquired a reference to a
`Task`'s pid namespace it will remain unchanged.

When a task has exited and been reaped `release_task()` will be called.
This will set the `PidNamespace` of the task to `NULL`. So retrieving
the `PidNamespace` of a task that is dead will return `NULL`. Note, that
neither holding the RCU lock nor holding a referencing count to the
`Task` will prevent `release_task()` being called.

In order to retrieve the `PidNamespace` of a `Task` the
`task_active_pid_ns()` function can be used. There are two cases to
consider:

(1) retrieving the `PidNamespace` of the `current` task (2) retrieving
the `PidNamespace` of a non-`current` task

From system call context retrieving the `PidNamespace` for case (1) is
always safe and requires neither RCU locking nor a reference count to be
held. Retrieving the `PidNamespace` after `release_task()` for current
will return `NULL` but no codepath like that is exposed to Rust.

Retrieving the `PidNamespace` from system call context for (2) requires
RCU protection. Accessing `PidNamespace` outside of RCU protection
requires a reference count that must've been acquired while holding the
RCU lock. Note that accessing a non-`current` task means `NULL` can be
returned as the non-`current` task could have already passed through
`release_task()`.

To retrieve (1) the `current_pid_ns!()` macro should be used which
ensure that the returned `PidNamespace` cannot outlive the calling
scope. The associated `current_pid_ns()` function should not be called
directly as it could be abused to created an unbounded lifetime for
`PidNamespace`. The `current_pid_ns!()` macro allows Rust to handle the
common case of accessing `current`'s `PidNamespace` without RCU
protection and without having to acquire a reference count.

For (2) the `task_get_pid_ns()` method must be used. This will always
acquire a reference on `PidNamespace` and will return an `Option` to
force the caller to explicitly handle the case where `PidNamespace` is
`None`, something that tends to be forgotten when doing the equivalent
operation in `C`. Missing RCU primitives make it difficult to perform
operations that are otherwise safe without holding a reference count as
long as RCU protection is guaranteed. But it is not important currently.
But we do want it in the future.

Note for (2) the required RCU protection around calling
`task_active_pid_ns()` synchronizes against putting the last reference
of the associated `struct pid` of `task->thread_pid`. The `struct pid`
stored in that field is used to retrieve the `PidNamespace` of the
caller. When `release_task()` is called `task->thread_pid` will be
`NULL`ed and `put_pid()` on said `struct pid` will be delayed in
`free_pid()` via `call_rcu()` allowing everyone with an RCU protected
access to the `struct pid` acquired from `task->thread_pid` to finish.

Link: https://lore.kernel.org/r/20241002-brauner-rust-pid_namespace-v5-1-a90e70d44fde@kernel.org
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 rust/helpers/helpers.c       |   1 +
 rust/helpers/pid_namespace.c |  26 +++++++
 rust/kernel/lib.rs           |   1 +
 rust/kernel/pid_namespace.rs |  68 ++++++++++++++++++
 rust/kernel/task.rs          | 135 +++++++++++++++++++++++++++++++++--
 5 files changed, 225 insertions(+), 6 deletions(-)
 create mode 100644 rust/helpers/pid_namespace.c
 create mode 100644 rust/kernel/pid_namespace.rs

diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c
index 62022b18caf5e..d553ad9361ce1 100644
--- a/rust/helpers/helpers.c
+++ b/rust/helpers/helpers.c
@@ -17,6 +17,7 @@
 #include "kunit.c"
 #include "mutex.c"
 #include "page.c"
+#include "pid_namespace.c"
 #include "rbtree.c"
 #include "refcount.c"
 #include "security.c"
diff --git a/rust/helpers/pid_namespace.c b/rust/helpers/pid_namespace.c
new file mode 100644
index 0000000000000..f41482bdec9a7
--- /dev/null
+++ b/rust/helpers/pid_namespace.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/pid_namespace.h>
+#include <linux/cleanup.h>
+
+struct pid_namespace *rust_helper_get_pid_ns(struct pid_namespace *ns)
+{
+	return get_pid_ns(ns);
+}
+
+void rust_helper_put_pid_ns(struct pid_namespace *ns)
+{
+	put_pid_ns(ns);
+}
+
+/* Get a reference on a task's pid namespace. */
+struct pid_namespace *rust_helper_task_get_pid_ns(struct task_struct *task)
+{
+	struct pid_namespace *pid_ns;
+
+	guard(rcu)();
+	pid_ns = task_active_pid_ns(task);
+	if (pid_ns)
+		get_pid_ns(pid_ns);
+	return pid_ns;
+}
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 9843eedd42939..98219a5118c70 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -44,6 +44,7 @@ pub mod list;
 #[cfg(CONFIG_NET)]
 pub mod net;
 pub mod page;
+pub mod pid_namespace;
 pub mod prelude;
 pub mod print;
 pub mod rbtree;
diff --git a/rust/kernel/pid_namespace.rs b/rust/kernel/pid_namespace.rs
new file mode 100644
index 0000000000000..0e93808e4639b
--- /dev/null
+++ b/rust/kernel/pid_namespace.rs
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (c) 2024 Christian Brauner <brauner@kernel.org>
+
+//! Pid namespaces.
+//!
+//! C header: [`include/linux/pid_namespace.h`](srctree/include/linux/pid_namespace.h) and
+//! [`include/linux/pid.h`](srctree/include/linux/pid.h)
+
+use crate::{
+    bindings,
+    types::{AlwaysRefCounted, Opaque},
+};
+use core::ptr;
+
+/// Wraps the kernel's `struct pid_namespace`. Thread safe.
+///
+/// This structure represents the Rust abstraction for a C `struct pid_namespace`. This
+/// implementation abstracts the usage of an already existing C `struct pid_namespace` within Rust
+/// code that we get passed from the C side.
+#[repr(transparent)]
+pub struct PidNamespace {
+    inner: Opaque<bindings::pid_namespace>,
+}
+
+impl PidNamespace {
+    /// Returns a raw pointer to the inner C struct.
+    #[inline]
+    pub fn as_ptr(&self) -> *mut bindings::pid_namespace {
+        self.inner.get()
+    }
+
+    /// Creates a reference to a [`PidNamespace`] from a valid pointer.
+    ///
+    /// # Safety
+    ///
+    /// The caller must ensure that `ptr` is valid and remains valid for the lifetime of the
+    /// returned [`PidNamespace`] reference.
+    pub unsafe fn from_ptr<'a>(ptr: *const bindings::pid_namespace) -> &'a Self {
+        // SAFETY: The safety requirements guarantee the validity of the dereference, while the
+        // `PidNamespace` type being transparent makes the cast ok.
+        unsafe { &*ptr.cast() }
+    }
+}
+
+// SAFETY: Instances of `PidNamespace` are always reference-counted.
+unsafe impl AlwaysRefCounted for PidNamespace {
+    #[inline]
+    fn inc_ref(&self) {
+        // SAFETY: The existence of a shared reference means that the refcount is nonzero.
+        unsafe { bindings::get_pid_ns(self.as_ptr()) };
+    }
+
+    #[inline]
+    unsafe fn dec_ref(obj: ptr::NonNull<PidNamespace>) {
+        // SAFETY: The safety requirements guarantee that the refcount is non-zero.
+        unsafe { bindings::put_pid_ns(obj.cast().as_ptr()) }
+    }
+}
+
+// SAFETY:
+// - `PidNamespace::dec_ref` can be called from any thread.
+// - It is okay to send ownership of `PidNamespace` across thread boundaries.
+unsafe impl Send for PidNamespace {}
+
+// SAFETY: It's OK to access `PidNamespace` through shared references from other threads because
+// we're either accessing properties that don't change or that are properly synchronised by C code.
+unsafe impl Sync for PidNamespace {}
diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs
index 1a36a9f193685..4b8c59a82746d 100644
--- a/rust/kernel/task.rs
+++ b/rust/kernel/task.rs
@@ -6,7 +6,8 @@
 
 use crate::{
     bindings,
-    types::{NotThreadSafe, Opaque},
+    pid_namespace::PidNamespace,
+    types::{ARef, NotThreadSafe, Opaque},
 };
 use core::{
     cmp::{Eq, PartialEq},
@@ -36,6 +37,16 @@ macro_rules! current {
     };
 }
 
+/// Returns the currently running task's pid namespace.
+#[macro_export]
+macro_rules! current_pid_ns {
+    () => {
+        // SAFETY: Deref + addr-of below create a temporary `PidNamespaceRef` that cannot outlive
+        // the caller.
+        unsafe { &*$crate::task::Task::current_pid_ns() }
+    };
+}
+
 /// Wraps the kernel's `struct task_struct`.
 ///
 /// # Invariants
@@ -145,6 +156,97 @@ impl Task {
         }
     }
 
+    /// Returns a PidNamespace reference for the currently executing task's/thread's pid namespace.
+    ///
+    /// This function can be used to create an unbounded lifetime by e.g., storing the returned
+    /// PidNamespace in a global variable which would be a bug. So the recommended way to get the
+    /// current task's/thread's pid namespace is to use the [`current_pid_ns`] macro because it is
+    /// safe.
+    ///
+    /// # Safety
+    ///
+    /// Callers must ensure that the returned object doesn't outlive the current task/thread.
+    pub unsafe fn current_pid_ns() -> impl Deref<Target = PidNamespace> {
+        struct PidNamespaceRef<'a> {
+            task: &'a PidNamespace,
+            _not_send: NotThreadSafe,
+        }
+
+        impl Deref for PidNamespaceRef<'_> {
+            type Target = PidNamespace;
+
+            fn deref(&self) -> &Self::Target {
+                self.task
+            }
+        }
+
+        // The lifetime of `PidNamespace` is bound to `Task` and `struct pid`.
+        //
+        // The `PidNamespace` of a `Task` doesn't ever change once the `Task` is alive. A
+        // `unshare(CLONE_NEWPID)` or `setns(fd_pidns/pidfd, CLONE_NEWPID)` will not have an effect
+        // on the calling `Task`'s pid namespace. It will only effect the pid namespace of children
+        // created by the calling `Task`. This invariant guarantees that after having acquired a
+        // reference to a `Task`'s pid namespace it will remain unchanged.
+        //
+        // When a task has exited and been reaped `release_task()` will be called. This will set
+        // the `PidNamespace` of the task to `NULL`. So retrieving the `PidNamespace` of a task
+        // that is dead will return `NULL`. Note, that neither holding the RCU lock nor holding a
+        // referencing count to
+        // the `Task` will prevent `release_task()` being called.
+        //
+        // In order to retrieve the `PidNamespace` of a `Task` the `task_active_pid_ns()` function
+        // can be used. There are two cases to consider:
+        //
+        // (1) retrieving the `PidNamespace` of the `current` task
+        // (2) retrieving the `PidNamespace` of a non-`current` task
+        //
+        // From system call context retrieving the `PidNamespace` for case (1) is always safe and
+        // requires neither RCU locking nor a reference count to be held. Retrieving the
+        // `PidNamespace` after `release_task()` for current will return `NULL` but no codepath
+        // like that is exposed to Rust.
+        //
+        // Retrieving the `PidNamespace` from system call context for (2) requires RCU protection.
+        // Accessing `PidNamespace` outside of RCU protection requires a reference count that
+        // must've been acquired while holding the RCU lock. Note that accessing a non-`current`
+        // task means `NULL` can be returned as the non-`current` task could have already passed
+        // through `release_task()`.
+        //
+        // To retrieve (1) the `current_pid_ns!()` macro should be used which ensure that the
+        // returned `PidNamespace` cannot outlive the calling scope. The associated
+        // `current_pid_ns()` function should not be called directly as it could be abused to
+        // created an unbounded lifetime for `PidNamespace`. The `current_pid_ns!()` macro allows
+        // Rust to handle the common case of accessing `current`'s `PidNamespace` without RCU
+        // protection and without having to acquire a reference count.
+        //
+        // For (2) the `task_get_pid_ns()` method must be used. This will always acquire a
+        // reference on `PidNamespace` and will return an `Option` to force the caller to
+        // explicitly handle the case where `PidNamespace` is `None`, something that tends to be
+        // forgotten when doing the equivalent operation in `C`. Missing RCU primitives make it
+        // difficult to perform operations that are otherwise safe without holding a reference
+        // count as long as RCU protection is guaranteed. But it is not important currently. But we
+        // do want it in the future.
+        //
+        // Note for (2) the required RCU protection around calling `task_active_pid_ns()`
+        // synchronizes against putting the last reference of the associated `struct pid` of
+        // `task->thread_pid`. The `struct pid` stored in that field is used to retrieve the
+        // `PidNamespace` of the caller. When `release_task()` is called `task->thread_pid` will be
+        // `NULL`ed and `put_pid()` on said `struct pid` will be delayed in `free_pid()` via
+        // `call_rcu()` allowing everyone with an RCU protected access to the `struct pid` acquired
+        // from `task->thread_pid` to finish.
+        //
+        // SAFETY: The current task's pid namespace is valid as long as the current task is running.
+        let pidns = unsafe { bindings::task_active_pid_ns(Task::current_raw()) };
+        PidNamespaceRef {
+            // SAFETY: If the current thread is still running, the current task and its associated
+            // pid namespace are valid. `PidNamespaceRef` is not `Send`, so we know it cannot be
+            // transferred to another thread (where it could potentially outlive the current
+            // `Task`). The caller needs to ensure that the PidNamespaceRef doesn't outlive the
+            // current task/thread.
+            task: unsafe { PidNamespace::from_ptr(pidns) },
+            _not_send: NotThreadSafe,
+        }
+    }
+
     /// Returns the group leader of the given task.
     pub fn group_leader(&self) -> &Task {
         // SAFETY: By the type invariant, we know that `self.0` is a valid task. Valid tasks always
@@ -182,11 +284,32 @@ impl Task {
         unsafe { bindings::signal_pending(self.0.get()) != 0 }
     }
 
-    /// Returns the given task's pid in the current pid namespace.
-    pub fn pid_in_current_ns(&self) -> Pid {
-        // SAFETY: We know that `self.0.get()` is valid by the type invariant, and passing a null
-        // pointer as the namespace is correct for using the current namespace.
-        unsafe { bindings::task_tgid_nr_ns(self.0.get(), ptr::null_mut()) }
+    /// Returns task's pid namespace with elevated reference count
+    pub fn get_pid_ns(&self) -> Option<ARef<PidNamespace>> {
+        // SAFETY: By the type invariant, we know that `self.0` is valid.
+        let ptr = unsafe { bindings::task_get_pid_ns(self.0.get()) };
+        if ptr.is_null() {
+            None
+        } else {
+            // SAFETY: `ptr` is valid by the safety requirements of this function. And we own a
+            // reference count via `task_get_pid_ns()`.
+            // CAST: `Self` is a `repr(transparent)` wrapper around `bindings::pid_namespace`.
+            Some(unsafe { ARef::from_raw(ptr::NonNull::new_unchecked(ptr.cast::<PidNamespace>())) })
+        }
+    }
+
+    /// Returns the given task's pid in the provided pid namespace.
+    #[doc(alias = "task_tgid_nr_ns")]
+    pub fn tgid_nr_ns(&self, pidns: Option<&PidNamespace>) -> Pid {
+        let pidns = match pidns {
+            Some(pidns) => pidns.as_ptr(),
+            None => core::ptr::null_mut(),
+        };
+        // SAFETY: By the type invariant, we know that `self.0` is valid. We received a valid
+        // PidNamespace that we can use as a pointer or we received an empty PidNamespace and
+        // thus pass a null pointer. The underlying C function is safe to be used with NULL
+        // pointers.
+        unsafe { bindings::task_tgid_nr_ns(self.0.get(), pidns) }
     }
 
     /// Wakes up the task.

From 1d930d4bf8e68c2a7122a6d0899a99f0370c45b1 Mon Sep 17 00:00:00 2001
From: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Date: Mon, 30 Sep 2024 15:52:40 +0100
Subject: [PATCH 0248/1530] pinctrl: renesas: rzg2l: Remove
 RZG2L_TINT_IRQ_START_INDEX

The RZ/V2H(P) SoC has 16 IRQ interrupts, while every other SoC has 8,
and this affects the start index of TINT interrupts (1 + 16 = 17, rather
than 1 + 8 = 9).
Macro RZG2L_TINT_IRQ_START_INDEX cannot work anymore, replace it with a
new member within struct rzg2l_hwcfg.

Signed-off-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Link: https://lore.kernel.org/20240930145244.356565-2-fabrizio.castro.jz@renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rzg2l.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index 5a403915fed2c..cde0121878d1a 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -168,7 +168,6 @@
 #define RZG2L_PIN_ID_TO_PIN(id)		((id) % RZG2L_PINS_PER_PORT)
 
 #define RZG2L_TINT_MAX_INTERRUPT	32
-#define RZG2L_TINT_IRQ_START_INDEX	9
 #define RZG2L_PACK_HWIRQ(t, i)		(((t) << 16) | (i))
 
 /* Custom pinconf parameters */
@@ -247,6 +246,7 @@ enum rzg2l_iolh_index {
  * @iolh_groupb_ua: IOLH group B uA specific values
  * @iolh_groupc_ua: IOLH group C uA specific values
  * @iolh_groupb_oi: IOLH group B output impedance specific values
+ * @tint_start_index: the start index for the TINT interrupts
  * @drive_strength_ua: drive strength in uA is supported (otherwise mA is supported)
  * @func_base: base number for port function (see register PFC)
  * @oen_max_pin: the maximum pin number supporting output enable
@@ -258,6 +258,7 @@ struct rzg2l_hwcfg {
 	u16 iolh_groupb_ua[RZG2L_IOLH_IDX_MAX];
 	u16 iolh_groupc_ua[RZG2L_IOLH_IDX_MAX];
 	u16 iolh_groupb_oi[4];
+	u16 tint_start_index;
 	bool drive_strength_ua;
 	u8 func_base;
 	u8 oen_max_pin;
@@ -2379,7 +2380,7 @@ static int rzg2l_gpio_child_to_parent_hwirq(struct gpio_chip *gc,
 
 	rzg2l_gpio_irq_endisable(pctrl, child, true);
 	pctrl->hwirq[irq] = child;
-	irq += RZG2L_TINT_IRQ_START_INDEX;
+	irq += pctrl->data->hwcfg->tint_start_index;
 
 	/* All these interrupts are level high in the CPU */
 	*parent_type = IRQ_TYPE_LEVEL_HIGH;
@@ -3034,6 +3035,7 @@ static const struct rzg2l_hwcfg rzg2l_hwcfg = {
 		[RZG2L_IOLH_IDX_3V3] = 2000, 4000, 8000, 12000,
 	},
 	.iolh_groupb_oi = { 100, 66, 50, 33, },
+	.tint_start_index = 9,
 	.oen_max_pin = 0,
 };
 
@@ -3063,6 +3065,7 @@ static const struct rzg2l_hwcfg rzg3s_hwcfg = {
 		/* 3v3 power source */
 		[RZG2L_IOLH_IDX_3V3] = 4500, 5200, 5700, 6050,
 	},
+	.tint_start_index = 9,
 	.drive_strength_ua = true,
 	.func_base = 1,
 	.oen_max_pin = 1, /* Pin 1 of P0 and P7 is the maximum OEN pin. */
@@ -3073,6 +3076,7 @@ static const struct rzg2l_hwcfg rzv2h_hwcfg = {
 	.regs = {
 		.pwpr = 0x3c04,
 	},
+	.tint_start_index = 17,
 };
 
 static struct rzg2l_pinctrl_data r9a07g043_data = {

From 1737715a4c2c08f207c94cc1f3af3c5945318d29 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Thu, 3 Oct 2024 09:25:48 +0100
Subject: [PATCH 0249/1530] pinctrl: renesas: rzg2l: Fix missing return in
 rzg2l_pinctrl_register()

Fix the missing return statement in the error path of
rzg2l_pinctrl_register().

Fixes: f73f63b24491fa43 ("pinctrl: renesas: rzg2l: Use dev_err_probe()")
Reported-by: Nobuhiro Iwamatsu <nobuhiro1.iwamatsu@toshiba.co.jp>
Closes: https://lore.kernel.org/all/OS0PR01MB638837327E5487B71D88A70392712@OS0PR01MB6388.jpnprd01.prod.outlook.com/
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/20241003082550.33341-1-biju.das.jz@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rzg2l.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index cde0121878d1a..0a32d692628c4 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -2711,7 +2711,7 @@ static int rzg2l_pinctrl_register(struct rzg2l_pinctrl *pctrl)
 
 	ret = pinctrl_enable(pctrl->pctl);
 	if (ret)
-		dev_err_probe(pctrl->dev, ret, "pinctrl enable failed\n");
+		return dev_err_probe(pctrl->dev, ret, "pinctrl enable failed\n");
 
 	ret = rzg2l_gpio_register(pctrl);
 	if (ret)

From f07e2b681edd8d8ed25048b958fdcfb55abaf487 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 4 Oct 2024 13:36:56 +0100
Subject: [PATCH 0250/1530] dt-bindings: pinctrl: renesas,rzg2l-pinctrl: Allow
 schmitt and open drain properties

On the RZ/V2H(P) SoC one can configure the 'input-schmitt-{enable,disable}',
'drive-open-drain' and 'drive-push-pull' of multiplexed pins. Update the
binding documentation to include these properties.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/20241004123658.764557-2-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 .../devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml    | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml
index 56d90c8e1fa3f..a1805b6e3f635 100644
--- a/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml
@@ -119,6 +119,10 @@ additionalProperties:
         bias-disable: true
         bias-pull-down: true
         bias-pull-up: true
+        input-schmitt-enable: true
+        input-schmitt-disable: true
+        drive-open-drain: true
+        drive-push-pull: true
         renesas,output-impedance:
           description:
             Output impedance for pins on the RZ/V2H(P) SoC. The value provided by this

From 7027e36f55f663c2248e8a2d67b94e34cab0ac7f Mon Sep 17 00:00:00 2001
From: Drew Fustini <dfustini@tenstorrent.com>
Date: Tue, 8 Oct 2024 18:16:46 -0700
Subject: [PATCH 0251/1530] pinctrl: th1520: Fix return value for unknown pin
 error

Fix th1520_pinctrl_dt_node_to_map() to set the return value before
jumping to free_configs when an unknown pin error occurs.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202410022336.xyWlV0Tf-lkp@intel.com/
Signed-off-by: Drew Fustini <dfustini@tenstorrent.com>
Link: https://lore.kernel.org/20241008-th1520-pinctrl-fixes-v3-1-5b60db446a49@tenstorrent.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-th1520.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/pinctrl-th1520.c b/drivers/pinctrl/pinctrl-th1520.c
index 9331f44624809..265a75a78d5a4 100644
--- a/drivers/pinctrl/pinctrl-th1520.c
+++ b/drivers/pinctrl/pinctrl-th1520.c
@@ -499,6 +499,7 @@ static int th1520_pinctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
 				nmaps = rollback;
 				dev_err(thp->pctl->dev, "%pOFn.%pOFn: unknown pin '%s'\n",
 					np, child, pinname);
+				ret = -EINVAL;
 				goto free_configs;
 			}
 

From f3a3d006a443e3e39f97b4e71a8d134cda417109 Mon Sep 17 00:00:00 2001
From: Drew Fustini <dfustini@tenstorrent.com>
Date: Tue, 8 Oct 2024 18:16:47 -0700
Subject: [PATCH 0252/1530] pinctrl: th1520: Convert thp->mutex to guarded
 mutex

Convert th1520_pinctrl_dt_node_to_map() to use guarded mutex for
thp->mutex.

Suggested-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Drew Fustini <dfustini@tenstorrent.com>
Link: https://lore.kernel.org/20241008-th1520-pinctrl-fixes-v3-2-5b60db446a49@tenstorrent.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-th1520.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-th1520.c b/drivers/pinctrl/pinctrl-th1520.c
index 265a75a78d5a4..7ed3f82b93398 100644
--- a/drivers/pinctrl/pinctrl-th1520.c
+++ b/drivers/pinctrl/pinctrl-th1520.c
@@ -444,7 +444,7 @@ static int th1520_pinctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
 		return -ENOMEM;
 
 	nmaps = 0;
-	mutex_lock(&thp->mutex);
+	guard(mutex)(&thp->mutex);
 	for_each_available_child_of_node(np, child) {
 		unsigned int rollback = nmaps;
 		enum th1520_muxtype muxtype;
@@ -531,7 +531,6 @@ static int th1520_pinctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
 
 	*maps = map;
 	*num_maps = nmaps;
-	mutex_unlock(&thp->mutex);
 	return 0;
 
 free_configs:
@@ -539,7 +538,6 @@ static int th1520_pinctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
 put_child:
 	of_node_put(child);
 	th1520_pinctrl_dt_free_map(pctldev, map, nmaps);
-	mutex_unlock(&thp->mutex);
 	return ret;
 }
 

From 573cba282788c90b4ed01e21b9d3ba522fdcda17 Mon Sep 17 00:00:00 2001
From: Drew Fustini <dfustini@tenstorrent.com>
Date: Tue, 8 Oct 2024 18:16:48 -0700
Subject: [PATCH 0253/1530] pinctrl: th1520: Convert dt child node loop to
 scoped iterator

Convert th1520_pinctrl_dt_node_to_map() to use a scoped iterator with
for_each_available_child_of_node_scoped(). As a result, there is no need
to call of_node_put() anymore. The put_child label has been renamed to
free_map which is now a more accurate description.

Suggested-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Drew Fustini <dfustini@tenstorrent.com>
Link: https://lore.kernel.org/20241008-th1520-pinctrl-fixes-v3-3-5b60db446a49@tenstorrent.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-th1520.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-th1520.c b/drivers/pinctrl/pinctrl-th1520.c
index 7ed3f82b93398..c8d2ee6defa79 100644
--- a/drivers/pinctrl/pinctrl-th1520.c
+++ b/drivers/pinctrl/pinctrl-th1520.c
@@ -417,7 +417,6 @@ static int th1520_pinctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
 					 unsigned int *num_maps)
 {
 	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
-	struct device_node *child;
 	struct pinctrl_map *map;
 	unsigned long *configs;
 	unsigned int nconfigs;
@@ -425,11 +424,10 @@ static int th1520_pinctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
 	int ret;
 
 	nmaps = 0;
-	for_each_available_child_of_node(np, child) {
+	for_each_available_child_of_node_scoped(np, child) {
 		int npins = of_property_count_strings(child, "pins");
 
 		if (npins <= 0) {
-			of_node_put(child);
 			dev_err(thp->pctl->dev, "no pins selected for %pOFn.%pOFn\n",
 				np, child);
 			return -EINVAL;
@@ -445,7 +443,7 @@ static int th1520_pinctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
 
 	nmaps = 0;
 	guard(mutex)(&thp->mutex);
-	for_each_available_child_of_node(np, child) {
+	for_each_available_child_of_node_scoped(np, child) {
 		unsigned int rollback = nmaps;
 		enum th1520_muxtype muxtype;
 		struct property *prop;
@@ -458,7 +456,7 @@ static int th1520_pinctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
 		if (ret) {
 			dev_err(thp->pctl->dev, "%pOFn.%pOFn: error parsing pin config\n",
 				np, child);
-			goto put_child;
+			goto free_map;
 		}
 
 		if (!of_property_read_string(child, "function", &funcname)) {
@@ -524,7 +522,7 @@ static int th1520_pinctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
 							  npins, (void *)muxtype);
 			if (ret < 0) {
 				dev_err(thp->pctl->dev, "error adding function %s\n", funcname);
-				goto put_child;
+				goto free_map;
 			}
 		}
 	}
@@ -535,8 +533,7 @@ static int th1520_pinctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
 
 free_configs:
 	kfree(configs);
-put_child:
-	of_node_put(child);
+free_map:
 	th1520_pinctrl_dt_free_map(pctldev, map, nmaps);
 	return ret;
 }

From 07963c02067ffc04105a37ebc889392faee90164 Mon Sep 17 00:00:00 2001
From: Andrei Stefanescu <andrei.stefanescu@oss.nxp.com>
Date: Wed, 2 Oct 2024 16:59:18 +0300
Subject: [PATCH 0254/1530] pinctrl: s32: add missing pins definitions

Added definitions for some pins which were missing from the
S32G2 SIUL2 pinctrl driver. These pins are used by the JTAG,
PFE and LLCE hardware modules.

Reviewed-by: Matthias Brugger <mbrugger@suse.com>
Signed-off-by: Andrei Stefanescu <andrei.stefanescu@oss.nxp.com>
Link: https://lore.kernel.org/20241002135920.3647322-2-andrei.stefanescu@oss.nxp.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/nxp/pinctrl-s32g2.c | 52 +++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/drivers/pinctrl/nxp/pinctrl-s32g2.c b/drivers/pinctrl/nxp/pinctrl-s32g2.c
index 440ff18794249..c49d28793b696 100644
--- a/drivers/pinctrl/nxp/pinctrl-s32g2.c
+++ b/drivers/pinctrl/nxp/pinctrl-s32g2.c
@@ -216,6 +216,12 @@ enum s32_pins {
 	S32G_IMCR_CAN1_RXD = 631,
 	S32G_IMCR_CAN2_RXD = 632,
 	S32G_IMCR_CAN3_RXD = 633,
+
+	/* JTAG IMCRs */
+	S32G_IMCR_JTAG_TMS = 562,
+	S32G_IMCR_JTAG_TCK = 572,
+	S32G_IMCR_JTAG_TDI = 573,
+
 	/* GMAC0 */
 	S32G_IMCR_Ethernet_MDIO = 527,
 	S32G_IMCR_Ethernet_CRS = 526,
@@ -229,7 +235,21 @@ enum s32_pins {
 	S32G_IMCR_Ethernet_RX_DV = 530,
 	S32G_IMCR_Ethernet_TX_CLK = 538,
 	S32G_IMCR_Ethernet_REF_CLK = 535,
+
 	/* PFE EMAC 0 MII */
+	S32G_IMCR_PFE_EMAC_0_MDIO = 837,
+	S32G_IMCR_PFE_EMAC_0_CRS = 836,
+	S32G_IMCR_PFE_EMAC_0_COL = 835,
+	S32G_IMCR_PFE_EMAC_0_RX_D0 = 841,
+	S32G_IMCR_PFE_EMAC_0_RX_D1 = 842,
+	S32G_IMCR_PFE_EMAC_0_RX_D2 = 843,
+	S32G_IMCR_PFE_EMAC_0_RX_D3 = 844,
+	S32G_IMCR_PFE_EMAC_0_RX_ER = 840,
+	S32G_IMCR_PFE_EMAC_0_RX_CLK = 839,
+	S32G_IMCR_PFE_EMAC_0_RX_DV = 845,
+	S32G_IMCR_PFE_EMAC_0_TX_CLK = 846,
+	S32G_IMCR_PFE_EMAC_0_REF_CLK = 838,
+
 	/* PFE EMAC 1 MII */
 	S32G_IMCR_PFE_EMAC_1_MDIO = 857,
 	S32G_IMCR_PFE_EMAC_1_CRS = 856,
@@ -317,6 +337,13 @@ enum s32_pins {
 	S32G_IMCR_LLCE_CAN13_RXD = 758,
 	S32G_IMCR_LLCE_CAN14_RXD = 759,
 	S32G_IMCR_LLCE_CAN15_RXD = 760,
+	S32G_IMCR_LLCE_UART0_RXD = 790,
+	S32G_IMCR_LLCE_UART1_RXD = 791,
+	S32G_IMCR_LLCE_UART2_RXD = 792,
+	S32G_IMCR_LLCE_UART3_RXD = 793,
+	S32G_IMCR_LLCE_LPSPI2_PCS0 = 811,
+	S32G_IMCR_LLCE_LPSPI2_SCK = 816,
+	S32G_IMCR_LLCE_LPSPI2_SIN = 817,
 	S32G_IMCR_USB_CLK = 895,
 	S32G_IMCR_USB_DATA0 = 896,
 	S32G_IMCR_USB_DATA1 = 897,
@@ -503,6 +530,12 @@ static const struct pinctrl_pin_desc s32_pinctrl_pads_siul2[] = {
 	S32_PINCTRL_PIN(S32G_IMCR_USDHC_DAT7),
 	S32_PINCTRL_PIN(S32G_IMCR_USDHC_DQS),
 	S32_PINCTRL_PIN(S32G_IMCR_CAN0_RXD),
+
+	/* JTAG IMCRs */
+	S32_PINCTRL_PIN(S32G_IMCR_JTAG_TMS),
+	S32_PINCTRL_PIN(S32G_IMCR_JTAG_TCK),
+	S32_PINCTRL_PIN(S32G_IMCR_JTAG_TDI),
+
 	/* GMAC0 */
 	S32_PINCTRL_PIN(S32G_IMCR_Ethernet_MDIO),
 	S32_PINCTRL_PIN(S32G_IMCR_Ethernet_CRS),
@@ -638,6 +671,13 @@ static const struct pinctrl_pin_desc s32_pinctrl_pads_siul2[] = {
 	S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN13_RXD),
 	S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN14_RXD),
 	S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN15_RXD),
+	S32_PINCTRL_PIN(S32G_IMCR_LLCE_UART0_RXD),
+	S32_PINCTRL_PIN(S32G_IMCR_LLCE_UART1_RXD),
+	S32_PINCTRL_PIN(S32G_IMCR_LLCE_UART2_RXD),
+	S32_PINCTRL_PIN(S32G_IMCR_LLCE_UART3_RXD),
+	S32_PINCTRL_PIN(S32G_IMCR_LLCE_LPSPI2_PCS0),
+	S32_PINCTRL_PIN(S32G_IMCR_LLCE_LPSPI2_SCK),
+	S32_PINCTRL_PIN(S32G_IMCR_LLCE_LPSPI2_SIN),
 	S32_PINCTRL_PIN(S32G_IMCR_CAN1_RXD),
 	S32_PINCTRL_PIN(S32G_IMCR_CAN2_RXD),
 	S32_PINCTRL_PIN(S32G_IMCR_CAN3_RXD),
@@ -652,6 +692,18 @@ static const struct pinctrl_pin_desc s32_pinctrl_pads_siul2[] = {
 	S32_PINCTRL_PIN(S32G_IMCR_USB_DATA7),
 	S32_PINCTRL_PIN(S32G_IMCR_USB_DIR),
 	S32_PINCTRL_PIN(S32G_IMCR_USB_NXT),
+	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_0_MDIO),
+	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_0_CRS),
+	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_0_COL),
+	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_0_RX_D0),
+	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_0_RX_D1),
+	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_0_RX_D2),
+	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_0_RX_D3),
+	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_0_RX_ER),
+	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_0_RX_CLK),
+	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_0_RX_DV),
+	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_0_TX_CLK),
+	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_0_REF_CLK),
 	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_MDIO),
 	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_CRS),
 	S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_COL),

From 3c4e558787f233044052ffd255a44ff7127952ce Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sun, 29 Sep 2024 02:06:59 +0100
Subject: [PATCH 0255/1530] perf probe: Remove unused add_perf_probe_events

add_perf_probe_events has been unused since 2015's commit
b02137cc6550 ("perf probe: Move print logic into cmd_probe()")
which confusingly now uses perf_add_probe_events.

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20240929010659.430208-1-linux@treblig.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/probe-event.c | 18 ------------------
 tools/perf/util/probe-event.h |  1 -
 2 files changed, 19 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index a17c9b8a7a792..698a928753740 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -3705,24 +3705,6 @@ void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 	}
 }
 
-int add_perf_probe_events(struct perf_probe_event *pevs, int npevs)
-{
-	int ret;
-
-	ret = init_probe_symbol_maps(pevs->uprobes);
-	if (ret < 0)
-		return ret;
-
-	ret = convert_perf_probe_events(pevs, npevs);
-	if (ret == 0)
-		ret = apply_perf_probe_events(pevs, npevs);
-
-	cleanup_perf_probe_events(pevs, npevs);
-
-	exit_probe_symbol_maps();
-	return ret;
-}
-
 int del_perf_probe_events(struct strfilter *filter)
 {
 	int ret, ret2, ufd = -1, kfd = -1;
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 7e3b6c3d1f744..4850e52f274e4 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -159,7 +159,6 @@ void line_range__clear(struct line_range *lr);
 /* Initialize line range */
 int line_range__init(struct line_range *lr);
 
-int add_perf_probe_events(struct perf_probe_event *pevs, int npevs);
 int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs);
 int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs);
 int show_probe_trace_events(struct perf_probe_event *pevs, int npevs);

From 9f759d41b3ed8feb550473027e674edf46ce7b94 Mon Sep 17 00:00:00 2001
From: Thomas Falcon <thomas.falcon@intel.com>
Date: Mon, 7 Oct 2024 14:47:58 -0500
Subject: [PATCH 0256/1530] perf test x86: Fix typo in intel-pt-test

Change function name "is_hydrid" to "is_hybrid".

Signed-off-by: Thomas Falcon <thomas.falcon@intel.com>
Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Link: https://lore.kernel.org/r/20241007194758.78659-1-thomas.falcon@intel.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/x86/tests/intel-pt-test.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/arch/x86/tests/intel-pt-test.c b/tools/perf/arch/x86/tests/intel-pt-test.c
index 09d61fa736e36..b217ed67cd4e5 100644
--- a/tools/perf/arch/x86/tests/intel-pt-test.c
+++ b/tools/perf/arch/x86/tests/intel-pt-test.c
@@ -375,7 +375,7 @@ static int get_pt_caps(int cpu, struct pt_caps *caps)
 	return 0;
 }
 
-static bool is_hydrid(void)
+static bool is_hybrid(void)
 {
 	unsigned int eax, ebx, ecx, edx = 0;
 	bool result;
@@ -441,7 +441,7 @@ int test__intel_pt_hybrid_compat(struct test_suite *test, int subtest)
 	int ret = TEST_OK;
 	int cpu;
 
-	if (!is_hydrid()) {
+	if (!is_hybrid()) {
 		test->test_cases[subtest].skip_reason = "not hybrid";
 		return TEST_SKIP;
 	}

From 3566362dd4dc61f770e42045a92cc3f17df61df0 Mon Sep 17 00:00:00 2001
From: Deepak Thukral <iapain@gmail.com>
Date: Fri, 4 Oct 2024 14:56:16 +0200
Subject: [PATCH 0257/1530] rust: std_vendor: update dbg macro from Rust
 upstream

`dbg!` contains adapted code from Rust upstream. Compare the kernel
code with the Rust upstream one and update missing column numbers in
`dbg!` outputs.

Column numbers are not copied but adjusted for the kernel's examples.

Suggested-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1124
Signed-off-by: Deepak Thukral <iapain@gmail.com>
Link: https://lore.kernel.org/r/20241004125616.49886-1-iapain@gmail.com
[ Fixed typo and slightly reworded. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/std_vendor.rs | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/rust/kernel/std_vendor.rs b/rust/kernel/std_vendor.rs
index 8f27d447a7fca..279bd353687a7 100644
--- a/rust/kernel/std_vendor.rs
+++ b/rust/kernel/std_vendor.rs
@@ -18,7 +18,7 @@
 /// let a = 2;
 /// # #[expect(clippy::disallowed_macros)]
 /// let b = dbg!(a * 2) + 1;
-/// //      ^-- prints: [src/main.rs:2] a * 2 = 4
+/// //      ^-- prints: [src/main.rs:3:9] a * 2 = 4
 /// assert_eq!(b, 5);
 /// ```
 ///
@@ -67,7 +67,7 @@
 /// This prints to the kernel log:
 ///
 /// ```text,ignore
-/// [src/main.rs:4] n.checked_sub(4) = None
+/// [src/main.rs:3:8] n.checked_sub(4) = None
 /// ```
 ///
 /// Naive factorial implementation:
@@ -88,15 +88,15 @@
 /// This prints to the kernel log:
 ///
 /// ```text,ignore
-/// [src/main.rs:3] n <= 1 = false
-/// [src/main.rs:3] n <= 1 = false
-/// [src/main.rs:3] n <= 1 = false
-/// [src/main.rs:3] n <= 1 = true
-/// [src/main.rs:4] 1 = 1
-/// [src/main.rs:5] n * factorial(n - 1) = 2
-/// [src/main.rs:5] n * factorial(n - 1) = 6
-/// [src/main.rs:5] n * factorial(n - 1) = 24
-/// [src/main.rs:11] factorial(4) = 24
+/// [src/main.rs:3:8] n <= 1 = false
+/// [src/main.rs:3:8] n <= 1 = false
+/// [src/main.rs:3:8] n <= 1 = false
+/// [src/main.rs:3:8] n <= 1 = true
+/// [src/main.rs:4:9] 1 = 1
+/// [src/main.rs:5:9] n * factorial(n - 1) = 2
+/// [src/main.rs:5:9] n * factorial(n - 1) = 6
+/// [src/main.rs:5:9] n * factorial(n - 1) = 24
+/// [src/main.rs:11:1] factorial(4) = 24
 /// ```
 ///
 /// The `dbg!(..)` macro moves the input:

From f4c2c90bb7b4ae1812dbaca15d9637eecaac2c9f Mon Sep 17 00:00:00 2001
From: Filipe Xavier <felipe_life@live.com>
Date: Thu, 26 Sep 2024 17:50:37 -0300
Subject: [PATCH 0258/1530] rust: lock: add trylock method support for lock
 backend

Add a non-blocking trylock method to lock backend interface, mutex and
spinlock implementations. It includes a C helper for spin_trylock.

Rust Binder will use this method together with the new shrinker
abstractions to avoid deadlocks in the memory shrinker.

Link: https://lore.kernel.org/all/20240912-shrinker-v1-1-18b7f1253553@google.com
Signed-off-by: Filipe Xavier <felipe_life@live.com>
Reviewed-by: Fiona Behrens <me@kloenk.dev>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Link: https://lore.kernel.org/r/BL0PR02MB4914579914884B5D7473B3D6E96A2@BL0PR02MB4914.namprd02.prod.outlook.com
[ Slightly reworded. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/helpers/spinlock.c           |  5 +++++
 rust/kernel/sync/lock.rs          | 16 ++++++++++++++++
 rust/kernel/sync/lock/mutex.rs    | 11 +++++++++++
 rust/kernel/sync/lock/spinlock.rs | 11 +++++++++++
 4 files changed, 43 insertions(+)

diff --git a/rust/helpers/spinlock.c b/rust/helpers/spinlock.c
index acc1376b833c7..775ed4d549aef 100644
--- a/rust/helpers/spinlock.c
+++ b/rust/helpers/spinlock.c
@@ -22,3 +22,8 @@ void rust_helper_spin_unlock(spinlock_t *lock)
 {
 	spin_unlock(lock);
 }
+
+int rust_helper_spin_trylock(spinlock_t *lock)
+{
+	return spin_trylock(lock);
+}
diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs
index 07fcf2d8efc6c..90cc5416529bd 100644
--- a/rust/kernel/sync/lock.rs
+++ b/rust/kernel/sync/lock.rs
@@ -58,6 +58,13 @@ pub unsafe trait Backend {
     #[must_use]
     unsafe fn lock(ptr: *mut Self::State) -> Self::GuardState;
 
+    /// Tries to acquire the lock.
+    ///
+    /// # Safety
+    ///
+    /// Callers must ensure that [`Backend::init`] has been previously called.
+    unsafe fn try_lock(ptr: *mut Self::State) -> Option<Self::GuardState>;
+
     /// Releases the lock, giving up its ownership.
     ///
     /// # Safety
@@ -128,6 +135,15 @@ impl<T: ?Sized, B: Backend> Lock<T, B> {
         // SAFETY: The lock was just acquired.
         unsafe { Guard::new(self, state) }
     }
+
+    /// Tries to acquire the lock.
+    ///
+    /// Returns a guard that can be used to access the data protected by the lock if successful.
+    pub fn try_lock(&self) -> Option<Guard<'_, T, B>> {
+        // SAFETY: The constructor of the type calls `init`, so the existence of the object proves
+        // that `init` was called.
+        unsafe { B::try_lock(self.state.get()).map(|state| Guard::new(self, state)) }
+    }
 }
 
 /// A lock guard.
diff --git a/rust/kernel/sync/lock/mutex.rs b/rust/kernel/sync/lock/mutex.rs
index 30632070ee670..c4f3b6cbfe48d 100644
--- a/rust/kernel/sync/lock/mutex.rs
+++ b/rust/kernel/sync/lock/mutex.rs
@@ -115,4 +115,15 @@ unsafe impl super::Backend for MutexBackend {
         // caller is the owner of the mutex.
         unsafe { bindings::mutex_unlock(ptr) };
     }
+
+    unsafe fn try_lock(ptr: *mut Self::State) -> Option<Self::GuardState> {
+        // SAFETY: The `ptr` pointer is guaranteed to be valid and initialized before use.
+        let result = unsafe { bindings::mutex_trylock(ptr) };
+
+        if result != 0 {
+            Some(())
+        } else {
+            None
+        }
+    }
 }
diff --git a/rust/kernel/sync/lock/spinlock.rs b/rust/kernel/sync/lock/spinlock.rs
index ea5c5bc1ce12e..c900ae23db76f 100644
--- a/rust/kernel/sync/lock/spinlock.rs
+++ b/rust/kernel/sync/lock/spinlock.rs
@@ -114,4 +114,15 @@ unsafe impl super::Backend for SpinLockBackend {
         // caller is the owner of the spinlock.
         unsafe { bindings::spin_unlock(ptr) }
     }
+
+    unsafe fn try_lock(ptr: *mut Self::State) -> Option<Self::GuardState> {
+        // SAFETY: The `ptr` pointer is guaranteed to be valid and initialized before use.
+        let result = unsafe { bindings::spin_trylock(ptr) };
+
+        if result != 0 {
+            Some(())
+        } else {
+            None
+        }
+    }
 }

From e9759c5b9ea555d09f426c70c880e9522e9b0576 Mon Sep 17 00:00:00 2001
From: Filipe Xavier <felipe_life@live.com>
Date: Sat, 5 Oct 2024 19:51:23 +0000
Subject: [PATCH 0259/1530] rust: error: optimize error type to use nonzero

Optimize `Result<(), Error>` size by changing `Error` type to
`NonZero*` for niche optimization.

This reduces the space used by the `Result` type, as the `NonZero*`
type enables the compiler to apply more efficient memory layout.
For example, the `Result<(), Error>` changes size from 8 to 4 bytes.

Link: https://github.com/Rust-for-Linux/linux/issues/1120
Signed-off-by: Filipe Xavier <felipe_life@live.com>
Reviewed-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Fiona Behrens <me@kloenk.dev>
Link: https://lore.kernel.org/r/BL0PR02MB4914B9B088865CF237731207E9732@BL0PR02MB4914.namprd02.prod.outlook.com
[ Removed unneeded block around `match`, added backticks in panic
  message and added intra-doc link. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/error.rs | 37 ++++++++++++++++++++++++++++---------
 1 file changed, 28 insertions(+), 9 deletions(-)

diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs
index 2f1e4b783bfb3..be6509d5f4a4a 100644
--- a/rust/kernel/error.rs
+++ b/rust/kernel/error.rs
@@ -9,6 +9,7 @@ use crate::{alloc::AllocError, str::CStr};
 use alloc::alloc::LayoutError;
 
 use core::fmt;
+use core::num::NonZeroI32;
 use core::num::TryFromIntError;
 use core::str::Utf8Error;
 
@@ -20,7 +21,11 @@ pub mod code {
             $(
             #[doc = $doc]
             )*
-            pub const $err: super::Error = super::Error(-(crate::bindings::$err as i32));
+            pub const $err: super::Error =
+                match super::Error::try_from_errno(-(crate::bindings::$err as i32)) {
+                    Some(err) => err,
+                    None => panic!("Invalid errno in `declare_err!`"),
+                };
         };
     }
 
@@ -88,7 +93,7 @@ pub mod code {
 ///
 /// The value is a valid `errno` (i.e. `>= -MAX_ERRNO && < 0`).
 #[derive(Clone, Copy, PartialEq, Eq)]
-pub struct Error(core::ffi::c_int);
+pub struct Error(NonZeroI32);
 
 impl Error {
     /// Creates an [`Error`] from a kernel error code.
@@ -107,7 +112,20 @@ impl Error {
 
         // INVARIANT: The check above ensures the type invariant
         // will hold.
-        Error(errno)
+        // SAFETY: `errno` is checked above to be in a valid range.
+        unsafe { Error::from_errno_unchecked(errno) }
+    }
+
+    /// Creates an [`Error`] from a kernel error code.
+    ///
+    /// Returns [`None`] if `errno` is out-of-range.
+    const fn try_from_errno(errno: core::ffi::c_int) -> Option<Error> {
+        if errno < -(bindings::MAX_ERRNO as i32) || errno >= 0 {
+            return None;
+        }
+
+        // SAFETY: `errno` is checked above to be in a valid range.
+        Some(unsafe { Error::from_errno_unchecked(errno) })
     }
 
     /// Creates an [`Error`] from a kernel error code.
@@ -115,21 +133,22 @@ impl Error {
     /// # Safety
     ///
     /// `errno` must be within error code range (i.e. `>= -MAX_ERRNO && < 0`).
-    unsafe fn from_errno_unchecked(errno: core::ffi::c_int) -> Error {
+    const unsafe fn from_errno_unchecked(errno: core::ffi::c_int) -> Error {
         // INVARIANT: The contract ensures the type invariant
         // will hold.
-        Error(errno)
+        // SAFETY: The caller guarantees `errno` is non-zero.
+        Error(unsafe { NonZeroI32::new_unchecked(errno) })
     }
 
     /// Returns the kernel error code.
     pub fn to_errno(self) -> core::ffi::c_int {
-        self.0
+        self.0.get()
     }
 
     #[cfg(CONFIG_BLOCK)]
     pub(crate) fn to_blk_status(self) -> bindings::blk_status_t {
         // SAFETY: `self.0` is a valid error due to its invariant.
-        unsafe { bindings::errno_to_blk_status(self.0) }
+        unsafe { bindings::errno_to_blk_status(self.0.get()) }
     }
 
     /// Returns the error encoded as a pointer.
@@ -137,7 +156,7 @@ impl Error {
         #[cfg_attr(target_pointer_width = "32", allow(clippy::useless_conversion))]
         // SAFETY: `self.0` is a valid error due to its invariant.
         unsafe {
-            bindings::ERR_PTR(self.0.into()) as *mut _
+            bindings::ERR_PTR(self.0.get().into()) as *mut _
         }
     }
 
@@ -145,7 +164,7 @@ impl Error {
     #[cfg(not(testlib))]
     pub fn name(&self) -> Option<&'static CStr> {
         // SAFETY: Just an FFI call, there are no extra safety requirements.
-        let ptr = unsafe { bindings::errname(-self.0) };
+        let ptr = unsafe { bindings::errname(-self.0.get()) };
         if ptr.is_null() {
             None
         } else {

From ce1c54fdff7c4556b08f5b875a331d8952e8b6b7 Mon Sep 17 00:00:00 2001
From: Aliet Exposito Garcia <aliet.exposito@gmail.com>
Date: Wed, 18 Sep 2024 18:51:14 -0400
Subject: [PATCH 0260/1530] rust: kernel: move `FromBytes` and `AsBytes` traits
 to a new `transmute` module

Refactor the `FromBytes` and `AsBytes` traits from `types.rs` into a new
`transmute.rs` module:

 - Add `rust/kernel/transmute.rs` with the definitions of `FromBytes`
   and `AsBytes`.

 - Remove the same trait definitions from `rust/kernel/types.rs`.

 - Update `rust/kernel/uaccess.rs` to import `AsBytes` and `FromBytes`
   from `transmute.rs`.

The traits and their implementations remain unchanged.

Suggested-by: Benno Lossin <benno.lossin@proton.me>
Link: https://github.com/Rust-for-Linux/linux/issues/1117
Signed-off-by: Aliet Exposito Garcia <aliet.exposito@gmail.com>
Reviewed-by: Fiona Behrens <me@kloenk.dev>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Link: https://lore.kernel.org/r/20240918225115.2309224-2-aliet.exposito@gmail.com
[ Rebased on top of the lints series and slightly reworded. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/lib.rs       |  1 +
 rust/kernel/transmute.rs | 71 ++++++++++++++++++++++++++++++++++++++++
 rust/kernel/types.rs     | 68 --------------------------------------
 rust/kernel/uaccess.rs   |  2 +-
 4 files changed, 73 insertions(+), 69 deletions(-)
 create mode 100644 rust/kernel/transmute.rs

diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 3e4bd6e57bee5..dc37aef6a0085 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -54,6 +54,7 @@ pub mod str;
 pub mod sync;
 pub mod task;
 pub mod time;
+pub mod transmute;
 pub mod types;
 pub mod uaccess;
 pub mod workqueue;
diff --git a/rust/kernel/transmute.rs b/rust/kernel/transmute.rs
new file mode 100644
index 0000000000000..1c7d43771a37b
--- /dev/null
+++ b/rust/kernel/transmute.rs
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Traits for transmuting types.
+
+/// Types for which any bit pattern is valid.
+///
+/// Not all types are valid for all values. For example, a `bool` must be either zero or one, so
+/// reading arbitrary bytes into something that contains a `bool` is not okay.
+///
+/// It's okay for the type to have padding, as initializing those bytes has no effect.
+///
+/// # Safety
+///
+/// All bit-patterns must be valid for this type. This type must not have interior mutability.
+pub unsafe trait FromBytes {}
+
+macro_rules! impl_frombytes {
+    ($($({$($generics:tt)*})? $t:ty, )*) => {
+        // SAFETY: Safety comments written in the macro invocation.
+        $(unsafe impl$($($generics)*)? FromBytes for $t {})*
+    };
+}
+
+impl_frombytes! {
+    // SAFETY: All bit patterns are acceptable values of the types below.
+    u8, u16, u32, u64, usize,
+    i8, i16, i32, i64, isize,
+
+    // SAFETY: If all bit patterns are acceptable for individual values in an array, then all bit
+    // patterns are also acceptable for arrays of that type.
+    {<T: FromBytes>} [T],
+    {<T: FromBytes, const N: usize>} [T; N],
+}
+
+/// Types that can be viewed as an immutable slice of initialized bytes.
+///
+/// If a struct implements this trait, then it is okay to copy it byte-for-byte to userspace. This
+/// means that it should not have any padding, as padding bytes are uninitialized. Reading
+/// uninitialized memory is not just undefined behavior, it may even lead to leaking sensitive
+/// information on the stack to userspace.
+///
+/// The struct should also not hold kernel pointers, as kernel pointer addresses are also considered
+/// sensitive. However, leaking kernel pointers is not considered undefined behavior by Rust, so
+/// this is a correctness requirement, but not a safety requirement.
+///
+/// # Safety
+///
+/// Values of this type may not contain any uninitialized bytes. This type must not have interior
+/// mutability.
+pub unsafe trait AsBytes {}
+
+macro_rules! impl_asbytes {
+    ($($({$($generics:tt)*})? $t:ty, )*) => {
+        // SAFETY: Safety comments written in the macro invocation.
+        $(unsafe impl$($($generics)*)? AsBytes for $t {})*
+    };
+}
+
+impl_asbytes! {
+    // SAFETY: Instances of the following types have no uninitialized portions.
+    u8, u16, u32, u64, usize,
+    i8, i16, i32, i64, isize,
+    bool,
+    char,
+    str,
+
+    // SAFETY: If individual values in an array have no uninitialized portions, then the array
+    // itself does not have any uninitialized portions either.
+    {<T: AsBytes>} [T],
+    {<T: AsBytes, const N: usize>} [T; N],
+}
diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index 28d9e5ea3df45..085e8076f0788 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -479,71 +479,3 @@ pub enum Either<L, R> {
     /// Constructs an instance of [`Either`] containing a value of type `R`.
     Right(R),
 }
-
-/// Types for which any bit pattern is valid.
-///
-/// Not all types are valid for all values. For example, a `bool` must be either zero or one, so
-/// reading arbitrary bytes into something that contains a `bool` is not okay.
-///
-/// It's okay for the type to have padding, as initializing those bytes has no effect.
-///
-/// # Safety
-///
-/// All bit-patterns must be valid for this type. This type must not have interior mutability.
-pub unsafe trait FromBytes {}
-
-macro_rules! impl_frombytes {
-    ($($({$($generics:tt)*})? $t:ty, )*) => {
-        // SAFETY: Safety comments written in the macro invocation.
-        $(unsafe impl$($($generics)*)? FromBytes for $t {})*
-    };
-}
-
-impl_frombytes! {
-    // SAFETY: All bit patterns are acceptable values of the types below.
-    u8, u16, u32, u64, usize,
-    i8, i16, i32, i64, isize,
-
-    // SAFETY: If all bit patterns are acceptable for individual values in an array, then all bit
-    // patterns are also acceptable for arrays of that type.
-    {<T: FromBytes>} [T],
-    {<T: FromBytes, const N: usize>} [T; N],
-}
-
-/// Types that can be viewed as an immutable slice of initialized bytes.
-///
-/// If a struct implements this trait, then it is okay to copy it byte-for-byte to userspace. This
-/// means that it should not have any padding, as padding bytes are uninitialized. Reading
-/// uninitialized memory is not just undefined behavior, it may even lead to leaking sensitive
-/// information on the stack to userspace.
-///
-/// The struct should also not hold kernel pointers, as kernel pointer addresses are also considered
-/// sensitive. However, leaking kernel pointers is not considered undefined behavior by Rust, so
-/// this is a correctness requirement, but not a safety requirement.
-///
-/// # Safety
-///
-/// Values of this type may not contain any uninitialized bytes. This type must not have interior
-/// mutability.
-pub unsafe trait AsBytes {}
-
-macro_rules! impl_asbytes {
-    ($($({$($generics:tt)*})? $t:ty, )*) => {
-        // SAFETY: Safety comments written in the macro invocation.
-        $(unsafe impl$($($generics)*)? AsBytes for $t {})*
-    };
-}
-
-impl_asbytes! {
-    // SAFETY: Instances of the following types have no uninitialized portions.
-    u8, u16, u32, u64, usize,
-    i8, i16, i32, i64, isize,
-    bool,
-    char,
-    str,
-
-    // SAFETY: If individual values in an array have no uninitialized portions, then the array
-    // itself does not have any uninitialized portions either.
-    {<T: AsBytes>} [T],
-    {<T: AsBytes, const N: usize>} [T; N],
-}
diff --git a/rust/kernel/uaccess.rs b/rust/kernel/uaccess.rs
index e9347cff99ab2..0af243482eac9 100644
--- a/rust/kernel/uaccess.rs
+++ b/rust/kernel/uaccess.rs
@@ -9,7 +9,7 @@ use crate::{
     bindings,
     error::Result,
     prelude::*,
-    types::{AsBytes, FromBytes},
+    transmute::{AsBytes, FromBytes},
 };
 use alloc::vec::Vec;
 use core::ffi::{c_ulong, c_void};

From cbcb7edd099aee3f001c008fb8bbb1c0d2b7154c Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Fri, 4 Oct 2024 10:18:50 +0800
Subject: [PATCH 0261/1530] soundwire: intel_auxdevice: add kernel parameter
 for mclk divider

Add a kernel parameter to work-around discrepancies between hardware
and platform firmware, it's not unusual to see e.g. 38.4MHz listed in
_DSD properties as the SoundWire clock source, but the hardware may be
based on a 19.2 MHz mclk source.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241004021850.9758-1-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/admin-guide/kernel-parameters.rst |  1 +
 Documentation/admin-guide/kernel-parameters.txt |  4 ++++
 drivers/soundwire/intel_auxdevice.c             | 12 ++++++++++--
 3 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst
index fdea7c26ef804..a64130fd19bff 100644
--- a/Documentation/admin-guide/kernel-parameters.rst
+++ b/Documentation/admin-guide/kernel-parameters.rst
@@ -159,6 +159,7 @@ is applicable::
 	SCSI	Appropriate SCSI support is enabled.
 			A lot of drivers have their options described inside
 			the Documentation/scsi/ sub-directory.
+        SDW     SoundWire support is enabled.
 	SECURITY Different security models are enabled.
 	SELINUX SELinux support is enabled.
 	SERIAL	Serial support is enabled.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 1518343bbe223..d7aee9ed5a1d1 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6060,6 +6060,10 @@
 			non-zero "wait" parameter.  See weight_single
 			and weight_many.
 
+	sdw_mclk_divider=[SDW]
+			Specify the MCLK divider for Intel SoundWire buses in
+			case the BIOS does not provide the clock rate properly.
+
 	skew_tick=	[KNL,EARLY] Offset the periodic timer tick per cpu to mitigate
 			xtime_lock contention on larger systems, and/or RCU lock
 			contention on all systems with CONFIG_MAXSMP set.
diff --git a/drivers/soundwire/intel_auxdevice.c b/drivers/soundwire/intel_auxdevice.c
index ae689d5d1ab9e..599954d927529 100644
--- a/drivers/soundwire/intel_auxdevice.c
+++ b/drivers/soundwire/intel_auxdevice.c
@@ -41,6 +41,10 @@ static int md_flags;
 module_param_named(sdw_md_flags, md_flags, int, 0444);
 MODULE_PARM_DESC(sdw_md_flags, "SoundWire Intel Master device flags (0x0 all off)");
 
+static int mclk_divider;
+module_param_named(sdw_mclk_divider, mclk_divider, int, 0444);
+MODULE_PARM_DESC(sdw_mclk_divider, "SoundWire Intel mclk divider");
+
 struct wake_capable_part {
 	const u16 mfg_id;
 	const u16 part_id;
@@ -142,8 +146,12 @@ static int sdw_master_read_intel_prop(struct sdw_bus *bus)
 				 "intel-sdw-ip-clock",
 				 &prop->mclk_freq);
 
-	/* the values reported by BIOS are the 2x clock, not the bus clock */
-	prop->mclk_freq /= 2;
+	if (mclk_divider)
+		/* use kernel parameter for BIOS or board work-arounds */
+		prop->mclk_freq /= mclk_divider;
+	else
+		/* the values reported by BIOS are the 2x clock, not the bus clock */
+		prop->mclk_freq /= 2;
 
 	fwnode_property_read_u32(link,
 				 "intel-quirk-mask",

From 6124a4063b8083e4d973f60c09ddb7abdbabe57f Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 17:48:29 +0800
Subject: [PATCH 0262/1530] soundwire: cadence: add soft-reset on startup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Follow the recommended programming flows.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003094830.119673-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/cadence_master.c   | 25 +++++++++++++++++++++++++
 drivers/soundwire/cadence_master.h   |  1 +
 drivers/soundwire/intel_bus_common.c |  6 ++++++
 3 files changed, 32 insertions(+)

diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c
index 05652e983539b..7c8c977a923ad 100644
--- a/drivers/soundwire/cadence_master.c
+++ b/drivers/soundwire/cadence_master.c
@@ -1377,6 +1377,31 @@ static void cdns_init_clock_ctrl(struct sdw_cdns *cdns)
 	cdns_writel(cdns, CDNS_MCP_SSP_CTRL1, ssp_interval);
 }
 
+/**
+ * sdw_cdns_soft_reset() - Cadence soft-reset
+ * @cdns: Cadence instance
+ */
+int sdw_cdns_soft_reset(struct sdw_cdns *cdns)
+{
+	int ret;
+
+	cdns_updatel(cdns, CDNS_MCP_CONTROL, CDNS_MCP_CONTROL_SOFT_RST,
+		     CDNS_MCP_CONTROL_SOFT_RST);
+
+	ret = cdns_config_update(cdns);
+	if (ret < 0) {
+		dev_err(cdns->dev, "%s: config update failed\n", __func__);
+		return ret;
+	}
+
+	ret = cdns_set_wait(cdns, CDNS_MCP_CONTROL, CDNS_MCP_CONTROL_SOFT_RST, 0);
+	if (ret < 0)
+		dev_err(cdns->dev, "%s: Soft Reset timed out\n", __func__);
+
+	return ret;
+}
+EXPORT_SYMBOL(sdw_cdns_soft_reset);
+
 /**
  * sdw_cdns_init() - Cadence initialization
  * @cdns: Cadence instance
diff --git a/drivers/soundwire/cadence_master.h b/drivers/soundwire/cadence_master.h
index e1d7969ba48ae..c34fb050fe4f0 100644
--- a/drivers/soundwire/cadence_master.h
+++ b/drivers/soundwire/cadence_master.h
@@ -168,6 +168,7 @@ int sdw_cdns_probe(struct sdw_cdns *cdns);
 irqreturn_t sdw_cdns_irq(int irq, void *dev_id);
 irqreturn_t sdw_cdns_thread(int irq, void *dev_id);
 
+int sdw_cdns_soft_reset(struct sdw_cdns *cdns);
 int sdw_cdns_init(struct sdw_cdns *cdns);
 int sdw_cdns_pdi_init(struct sdw_cdns *cdns,
 		      struct sdw_cdns_stream_config config);
diff --git a/drivers/soundwire/intel_bus_common.c b/drivers/soundwire/intel_bus_common.c
index d3ff6c65b64c3..ad1f8ebdbfc9b 100644
--- a/drivers/soundwire/intel_bus_common.c
+++ b/drivers/soundwire/intel_bus_common.c
@@ -16,6 +16,12 @@ int intel_start_bus(struct sdw_intel *sdw)
 	struct sdw_bus *bus = &cdns->bus;
 	int ret;
 
+	ret = sdw_cdns_soft_reset(cdns);
+	if (ret < 0) {
+		dev_err(dev, "%s: unable to soft-reset Cadence IP: %d\n", __func__, ret);
+		return ret;
+	}
+
 	/*
 	 * follow recommended programming flows to avoid timeouts when
 	 * gsync is enabled

From 830f1aa53c0287eae667fa5f0a690bec34a10a3f Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 3 Oct 2024 17:48:30 +0800
Subject: [PATCH 0263/1530] soundwire: cadence: clear MCP BLOCK_WAKEUP in init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Follow recommended programming flows.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20241003094830.119673-3-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/cadence_master.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c
index 7c8c977a923ad..f367670ea991b 100644
--- a/drivers/soundwire/cadence_master.c
+++ b/drivers/soundwire/cadence_master.c
@@ -1425,6 +1425,11 @@ int sdw_cdns_init(struct sdw_cdns *cdns)
 	cdns_ip_updatel(cdns, CDNS_IP_MCP_CONTROL, CDNS_IP_MCP_CONTROL_CMD_ACCEPT,
 			CDNS_IP_MCP_CONTROL_CMD_ACCEPT);
 
+	/* disable wakeup */
+	cdns_ip_updatel(cdns, CDNS_IP_MCP_CONTROL,
+			CDNS_IP_MCP_CONTROL_BLOCK_WAKEUP,
+			0);
+
 	/* Configure mcp config */
 	val = cdns_readl(cdns, CDNS_MCP_CONFIG);
 

From 07d944b99c13c3e8bfbd7ee5d826cad722cc3591 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Thu, 10 Oct 2024 10:03:47 +0200
Subject: [PATCH 0264/1530] pinctrl: aw9523: fix kerneldoc for
 _aw9523_gpio_get_multiple()

The parameters' descriptions are wrong, drop the invalid ones and
document the ones that are missing the description.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Link: https://lore.kernel.org/20241010080347.7759-1-brgl@bgdev.pl
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-aw9523.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-aw9523.c b/drivers/pinctrl/pinctrl-aw9523.c
index 5cb24c1dcb0d0..9bf53de20be87 100644
--- a/drivers/pinctrl/pinctrl-aw9523.c
+++ b/drivers/pinctrl/pinctrl-aw9523.c
@@ -550,10 +550,10 @@ static int aw9523_gpio_get(struct gpio_chip *chip, unsigned int offset)
 
 /**
  * _aw9523_gpio_get_multiple - Get I/O state for an entire port
- * @regmap: Regmap structure
- * @pin: gpiolib pin number
+ * @awi: Controller data
  * @regbit: hw pin index, used to retrieve port number
  * @state: returned port I/O state
+ * @mask: lines to read values for
  *
  * Return: Zero for success or negative number for error
  */

From 2a85fc7044987d751f27d7f1e4423eebbcecc2c6 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Thu, 10 Oct 2024 10:04:32 +0200
Subject: [PATCH 0265/1530] pinctrl: zynqmp: drop excess struct member
 description

The 'node' member has never been part of this structure so drop its
description.

Fixes: 8b242ca700f8 ("pinctrl: Add Xilinx ZynqMP pinctrl driver support")
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Link: https://lore.kernel.org/20241010080432.7781-1-brgl@bgdev.pl
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-zynqmp.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-zynqmp.c b/drivers/pinctrl/pinctrl-zynqmp.c
index 2b9f8db49a153..fddf0fef4b13b 100644
--- a/drivers/pinctrl/pinctrl-zynqmp.c
+++ b/drivers/pinctrl/pinctrl-zynqmp.c
@@ -56,7 +56,6 @@
  * @name:	Name of the pin mux function
  * @groups:	List of pin groups for this function
  * @ngroups:	Number of entries in @groups
- * @node:	Firmware node matching with the function
  *
  * This structure holds information about pin control function
  * and function group names supporting that function.

From 9fb6fef0fb49124291837af1da5028f79d53f98e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 14 Jun 2024 13:06:03 +0300
Subject: [PATCH 0266/1530] resource: Add resource set range and size helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Setting the end address for a resource with a given size lacks a helper and
is therefore coded manually unlike the getter side which has a helper for
resource size calculation. Also, almost all callsites that calculate the
end address for a resource also set the start address right before it like
this:

  res->start = start_addr;
  res->end = res->start + size - 1;

Add resource_set_range(res, start_addr, size) that sets the start address
and calculates the end address to simplify this often repeated fragment.

Also add resource_set_size() for the cases where setting the start address
of the resource is not necessary but mention in its kerneldoc that
resource_set_range() is preferred when setting both addresses.

Link: https://lore.kernel.org/r/20240614100606.15830-2-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 include/linux/ioport.h | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 6e9fb667a1c5a..5385349f0b8a6 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -249,6 +249,38 @@ struct resource *lookup_resource(struct resource *root, resource_size_t start);
 int adjust_resource(struct resource *res, resource_size_t start,
 		    resource_size_t size);
 resource_size_t resource_alignment(struct resource *res);
+
+/**
+ * resource_set_size - Calculate resource end address from size and start
+ * @res: Resource descriptor
+ * @size: Size of the resource
+ *
+ * Calculate the end address for @res based on @size.
+ *
+ * Note: The start address of @res must be set when calling this function.
+ * Prefer resource_set_range() if setting both the start address and @size.
+ */
+static inline void resource_set_size(struct resource *res, resource_size_t size)
+{
+	res->end = res->start + size - 1;
+}
+
+/**
+ * resource_set_range - Set resource start and end addresses
+ * @res: Resource descriptor
+ * @start: Start address for the resource
+ * @size: Size of the resource
+ *
+ * Set @res start address and calculate the end address based on @size.
+ */
+static inline void resource_set_range(struct resource *res,
+				      resource_size_t start,
+				      resource_size_t size)
+{
+	res->start = start;
+	resource_set_size(res, size);
+}
+
 static inline resource_size_t resource_size(const struct resource *res)
 {
 	return res->end - res->start + 1;

From 783602c920e90023e6d38274d40e32979787d130 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 14 Jun 2024 13:06:04 +0300
Subject: [PATCH 0267/1530] PCI: Use resource_set_{range,size}() helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Convert open-coded resource size calculations to use
resource_set_{range,size}() helpers.

While at it, use SZ_* for size parameter where appropriate which makes the
intent of code more obvious.

Also, cast sizes to resource_size_t, not u64.

Link: https://lore.kernel.org/r/20240614100606.15830-3-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/controller/pci-tegra.c       |  2 +-
 drivers/pci/controller/pci-thunder-pem.c |  4 +--
 drivers/pci/ecam.c                       |  2 +-
 drivers/pci/iov.c                        |  6 ++--
 drivers/pci/pci.c                        |  3 +-
 drivers/pci/quirks.c                     | 20 ++++++--------
 drivers/pci/setup-bus.c                  | 35 ++++++++++--------------
 drivers/pci/setup-res.c                  |  7 ++---
 8 files changed, 34 insertions(+), 45 deletions(-)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index d7517c3976e7f..0471f2f7a6d13 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -1460,7 +1460,7 @@ static int tegra_pcie_get_resources(struct tegra_pcie *pcie)
 	pcie->cs = *res;
 
 	/* constrain configuration space to 4 KiB */
-	pcie->cs.end = pcie->cs.start + SZ_4K - 1;
+	resource_set_size(&pcie->cs, SZ_4K);
 
 	pcie->cfg = devm_ioremap_resource(dev, &pcie->cs);
 	if (IS_ERR(pcie->cfg)) {
diff --git a/drivers/pci/controller/pci-thunder-pem.c b/drivers/pci/controller/pci-thunder-pem.c
index 06a9855cb431c..f1bd5de67997c 100644
--- a/drivers/pci/controller/pci-thunder-pem.c
+++ b/drivers/pci/controller/pci-thunder-pem.c
@@ -400,9 +400,9 @@ static int thunder_pem_acpi_init(struct pci_config_window *cfg)
 		 * Reserve 64K size PEM specific resources. The full 16M range
 		 * size is required for thunder_pem_init() call.
 		 */
-		res_pem->end = res_pem->start + SZ_64K - 1;
+		resource_set_size(res_pem, SZ_64K);
 		thunder_pem_reserve_range(dev, root->segment, res_pem);
-		res_pem->end = res_pem->start + SZ_16M - 1;
+		resource_set_size(res_pem, SZ_16M);
 
 		/* Reserve PCI configuration space as well. */
 		thunder_pem_reserve_range(dev, root->segment, &cfg->res);
diff --git a/drivers/pci/ecam.c b/drivers/pci/ecam.c
index 1c40d2506aef3..260b7de2dbd57 100644
--- a/drivers/pci/ecam.c
+++ b/drivers/pci/ecam.c
@@ -55,7 +55,7 @@ struct pci_config_window *pci_ecam_create(struct device *dev,
 	bus_range_max = resource_size(cfgres) >> bus_shift;
 	if (bus_range > bus_range_max) {
 		bus_range = bus_range_max;
-		cfg->busr.end = busr->start + bus_range - 1;
+		resource_set_size(&cfg->busr, bus_range);
 		dev_warn(dev, "ECAM area %pR can only accommodate %pR (reduced from %pR desired)\n",
 			 cfgres, &cfg->busr, busr);
 	}
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index aaa33e8dc4c97..4be402fe9ab94 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -327,8 +327,8 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 		virtfn->resource[i].name = pci_name(virtfn);
 		virtfn->resource[i].flags = res->flags;
 		size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES);
-		virtfn->resource[i].start = res->start + size * id;
-		virtfn->resource[i].end = virtfn->resource[i].start + size - 1;
+		resource_set_range(&virtfn->resource[i],
+				   res->start + size * id, size);
 		rc = request_resource(res, &virtfn->resource[i]);
 		BUG_ON(rc);
 	}
@@ -804,7 +804,7 @@ static int sriov_init(struct pci_dev *dev, int pos)
 			goto failed;
 		}
 		iov->barsz[i] = resource_size(res);
-		res->end = res->start + resource_size(res) * total - 1;
+		resource_set_size(res, resource_size(res) * total);
 		pci_info(dev, "%s %pR: contains BAR %d for %d VFs\n",
 			 res_name, res, i, total);
 		i += bar64;
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 7d85c04fbba2a..25ced40738137 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -6649,8 +6649,7 @@ static void pci_request_resource_alignment(struct pci_dev *dev, int bar,
 	} else {
 		r->flags &= ~IORESOURCE_SIZEALIGN;
 		r->flags |= IORESOURCE_STARTALIGN;
-		r->start = align;
-		r->end = r->start + size - 1;
+		resource_set_range(r, align, size);
 	}
 	r->flags |= IORESOURCE_UNSET;
 }
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index dccb60c1d9cc3..e25476a766a73 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -29,6 +29,7 @@
 #include <linux/nvme.h>
 #include <linux/platform_data/x86/apple.h>
 #include <linux/pm_runtime.h>
+#include <linux/sizes.h>
 #include <linux/suspend.h>
 #include <linux/switchtec.h>
 #include "pci.h"
@@ -586,8 +587,7 @@ static void quirk_extend_bar_to_page(struct pci_dev *dev)
 		const char *r_name = pci_resource_name(dev, i);
 
 		if (r->flags & IORESOURCE_MEM && resource_size(r) < PAGE_SIZE) {
-			r->end = PAGE_SIZE - 1;
-			r->start = 0;
+			resource_set_range(r, 0, PAGE_SIZE);
 			r->flags |= IORESOURCE_UNSET;
 			pci_info(dev, "%s %pR: expanded to page size\n",
 				 r_name, r);
@@ -606,8 +606,7 @@ static void quirk_s3_64M(struct pci_dev *dev)
 
 	if ((r->start & 0x3ffffff) || r->end != r->start + 0x3ffffff) {
 		r->flags |= IORESOURCE_UNSET;
-		r->start = 0;
-		r->end = 0x3ffffff;
+		resource_set_range(r, 0, SZ_64M);
 	}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_S3,	PCI_DEVICE_ID_S3_868,		quirk_s3_64M);
@@ -1342,8 +1341,7 @@ static void quirk_dunord(struct pci_dev *dev)
 	struct resource *r = &dev->resource[1];
 
 	r->flags |= IORESOURCE_UNSET;
-	r->start = 0;
-	r->end = 0xffffff;
+	resource_set_range(r, 0, SZ_16M);
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_DUNORD,	PCI_DEVICE_ID_DUNORD_I3000,	quirk_dunord);
 
@@ -2340,8 +2338,7 @@ static void quirk_tc86c001_ide(struct pci_dev *dev)
 
 	if (r->start & 0x8) {
 		r->flags |= IORESOURCE_UNSET;
-		r->start = 0;
-		r->end = 0xf;
+		resource_set_range(r, 0, SZ_16);
 	}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TOSHIBA_2,
@@ -2369,8 +2366,7 @@ static void quirk_plx_pci9050(struct pci_dev *dev)
 			pci_info(dev, "Re-allocating PLX PCI 9050 BAR %u to length 256 to avoid bit 7 bug\n",
 				 bar);
 			r->flags |= IORESOURCE_UNSET;
-			r->start = 0;
-			r->end = 0xff;
+			resource_set_range(r, 0, SZ_256);
 		}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9050,
@@ -3522,13 +3518,13 @@ static void quirk_intel_ntb(struct pci_dev *dev)
 	if (rc)
 		return;
 
-	dev->resource[2].end = dev->resource[2].start + ((u64) 1 << val) - 1;
+	resource_set_size(&dev->resource[2], (resource_size_t)1 << val);
 
 	rc = pci_read_config_byte(dev, 0x00D1, &val);
 	if (rc)
 		return;
 
-	dev->resource[4].end = dev->resource[4].start + ((u64) 1 << val) - 1;
+	resource_set_size(&dev->resource[4], (resource_size_t)1 << val);
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0e08, quirk_intel_ntb);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0e0d, quirk_intel_ntb);
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 23082bc0ca37a..7293958ab234b 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -246,8 +246,7 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
 		add_size = add_res->add_size;
 		align = add_res->min_align;
 		if (!resource_size(res)) {
-			res->start = align;
-			res->end = res->start + add_size - 1;
+			resource_set_range(res, align, add_size);
 			if (pci_assign_resource(add_res->dev, idx))
 				reset_resource(res);
 		} else {
@@ -938,8 +937,7 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size,
 		return;
 	}
 
-	b_res->start = min_align;
-	b_res->end = b_res->start + size0 - 1;
+	resource_set_range(b_res, min_align, size0);
 	b_res->flags |= IORESOURCE_STARTALIGN;
 	if (bus->self && size1 > size0 && realloc_head) {
 		add_to_list(realloc_head, bus->self, b_res, size1-size0,
@@ -1202,8 +1200,7 @@ static void pci_bus_size_cardbus(struct pci_bus *bus,
 	 * Reserve some resources for CardBus.  We reserve a fixed amount
 	 * of bus space for CardBus bridges.
 	 */
-	b_res->start = pci_cardbus_io_size;
-	b_res->end = b_res->start + pci_cardbus_io_size - 1;
+	resource_set_range(b_res, pci_cardbus_io_size, pci_cardbus_io_size);
 	b_res->flags |= IORESOURCE_IO | IORESOURCE_STARTALIGN;
 	if (realloc_head) {
 		b_res->end -= pci_cardbus_io_size;
@@ -1215,8 +1212,7 @@ static void pci_bus_size_cardbus(struct pci_bus *bus,
 	b_res = &bridge->resource[PCI_CB_BRIDGE_IO_1_WINDOW];
 	if (b_res->parent)
 		goto handle_b_res_2;
-	b_res->start = pci_cardbus_io_size;
-	b_res->end = b_res->start + pci_cardbus_io_size - 1;
+	resource_set_range(b_res, pci_cardbus_io_size, pci_cardbus_io_size);
 	b_res->flags |= IORESOURCE_IO | IORESOURCE_STARTALIGN;
 	if (realloc_head) {
 		b_res->end -= pci_cardbus_io_size;
@@ -1249,8 +1245,8 @@ static void pci_bus_size_cardbus(struct pci_bus *bus,
 	 * Otherwise, allocate one region of twice the size.
 	 */
 	if (ctrl & PCI_CB_BRIDGE_CTL_PREFETCH_MEM0) {
-		b_res->start = pci_cardbus_mem_size;
-		b_res->end = b_res->start + pci_cardbus_mem_size - 1;
+		resource_set_range(b_res, pci_cardbus_mem_size,
+				   pci_cardbus_mem_size);
 		b_res->flags |= IORESOURCE_MEM | IORESOURCE_PREFETCH |
 				    IORESOURCE_STARTALIGN;
 		if (realloc_head) {
@@ -1267,8 +1263,7 @@ static void pci_bus_size_cardbus(struct pci_bus *bus,
 	b_res = &bridge->resource[PCI_CB_BRIDGE_MEM_1_WINDOW];
 	if (b_res->parent)
 		goto handle_done;
-	b_res->start = pci_cardbus_mem_size;
-	b_res->end = b_res->start + b_res_3_size - 1;
+	resource_set_range(b_res, pci_cardbus_mem_size, b_res_3_size);
 	b_res->flags |= IORESOURCE_MEM | IORESOURCE_STARTALIGN;
 	if (realloc_head) {
 		b_res->end -= b_res_3_size;
@@ -1847,7 +1842,7 @@ static void adjust_bridge_window(struct pci_dev *bridge, struct resource *res,
 		return;
 	}
 
-	res->end = res->start + new_size - 1;
+	resource_set_size(res, new_size);
 
 	/* If the resource is part of the add_list, remove it now */
 	if (add_list)
@@ -2010,8 +2005,8 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus,
 		 * what is available).
 		 */
 		align = pci_resource_alignment(dev, res);
-		io.end = align ? io.start + ALIGN_DOWN(io_per_b, align) - 1
-			       : io.start + io_per_b - 1;
+		resource_set_size(&io, align ? ALIGN_DOWN(io_per_b, align)
+					     : io_per_b);
 
 		/*
 		 * The x_per_b holds the extra resource space that can be
@@ -2023,15 +2018,15 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus,
 
 		res = &dev->resource[PCI_BRIDGE_MEM_WINDOW];
 		align = pci_resource_alignment(dev, res);
-		mmio.end = align ? mmio.start + ALIGN_DOWN(mmio_per_b, align) - 1
-				 : mmio.start + mmio_per_b - 1;
+		resource_set_size(&mmio, align ? ALIGN_DOWN(mmio_per_b, align)
+					       : mmio_per_b);
 		mmio.start -= resource_size(res);
 
 		res = &dev->resource[PCI_BRIDGE_PREF_MEM_WINDOW];
 		align = pci_resource_alignment(dev, res);
-		mmio_pref.end = align ? mmio_pref.start +
-					ALIGN_DOWN(mmio_pref_per_b, align) - 1
-				      : mmio_pref.start + mmio_pref_per_b - 1;
+		resource_set_size(&mmio_pref,
+				  align ? ALIGN_DOWN(mmio_pref_per_b, align)
+					: mmio_pref_per_b);
 		mmio_pref.start -= resource_size(res);
 
 		pci_bus_distribute_available_resources(b, add_list, io, mmio,
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index c6d933ddfd464..ca14576bf2bf2 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -211,8 +211,7 @@ static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev,
 
 	start = res->start;
 	end = res->end;
-	res->start = fw_addr;
-	res->end = res->start + size - 1;
+	resource_set_range(res, fw_addr, size);
 	res->flags &= ~IORESOURCE_UNSET;
 
 	root = pci_find_parent_resource(dev, res);
@@ -463,7 +462,7 @@ int pci_resize_resource(struct pci_dev *dev, int resno, int size)
 	if (ret)
 		return ret;
 
-	res->end = res->start + pci_rebar_size_to_bytes(size) - 1;
+	resource_set_size(res, pci_rebar_size_to_bytes(size));
 
 	/* Check if the new config works by trying to assign everything. */
 	if (dev->bus->self) {
@@ -475,7 +474,7 @@ int pci_resize_resource(struct pci_dev *dev, int resno, int size)
 
 error_resize:
 	pci_rebar_set_size(dev, resno, old);
-	res->end = res->start + pci_rebar_size_to_bytes(old) - 1;
+	resource_set_size(res, pci_rebar_size_to_bytes(old));
 	return ret;
 }
 EXPORT_SYMBOL(pci_resize_resource);

From 9d3faf229c06d953999e2aa6b6dbb57afd252f26 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 14 Jun 2024 13:06:05 +0300
Subject: [PATCH 0268/1530] PCI: Use align and resource helpers, and SZ_* in
 quirk_s3_64M()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use IS_ALIGNED(), resource_size(), and SZ_* defines in quirk_s3_64M().

Link: https://lore.kernel.org/r/20240614100606.15830-4-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/quirks.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index e25476a766a73..e85b89ca56017 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -12,6 +12,7 @@
  * file, where their drivers can use them.
  */
 
+#include <linux/align.h>
 #include <linux/bitfield.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
@@ -604,7 +605,7 @@ static void quirk_s3_64M(struct pci_dev *dev)
 {
 	struct resource *r = &dev->resource[0];
 
-	if ((r->start & 0x3ffffff) || r->end != r->start + 0x3ffffff) {
+	if (!IS_ALIGNED(r->start, SZ_64M) || resource_size(r) != SZ_64M) {
 		r->flags |= IORESOURCE_UNSET;
 		resource_set_range(r, 0, SZ_64M);
 	}

From e3bdd2dd3f618d0bb9f500aae17df2b4f726dca1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 14 Jun 2024 13:06:06 +0300
Subject: [PATCH 0269/1530] PCI: Add ALIGN_DOWN_IF_NONZERO() helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

pci_bus_distribute_available_resources() performs alignment in case of
non-zero alignment requirement on three occasions.

Add ALIGN_DOWN_IF_NONZERO() helper to avoid coding the non-zero check three
times.

Suggested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20240614100606.15830-5-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/setup-bus.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 7293958ab234b..27da27c59e899 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1894,6 +1894,9 @@ static void remove_dev_resources(struct pci_dev *dev, struct resource *io,
 	}
 }
 
+#define ALIGN_DOWN_IF_NONZERO(addr, align) \
+			((align) ? ALIGN_DOWN((addr), (align)) : (addr))
+
 /*
  * io, mmio and mmio_pref contain the total amount of bridge window space
  * available. This includes the minimal space needed to cover all the
@@ -2005,8 +2008,7 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus,
 		 * what is available).
 		 */
 		align = pci_resource_alignment(dev, res);
-		resource_set_size(&io, align ? ALIGN_DOWN(io_per_b, align)
-					     : io_per_b);
+		resource_set_size(&io, ALIGN_DOWN_IF_NONZERO(io_per_b, align));
 
 		/*
 		 * The x_per_b holds the extra resource space that can be
@@ -2018,15 +2020,14 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus,
 
 		res = &dev->resource[PCI_BRIDGE_MEM_WINDOW];
 		align = pci_resource_alignment(dev, res);
-		resource_set_size(&mmio, align ? ALIGN_DOWN(mmio_per_b, align)
-					       : mmio_per_b);
+		resource_set_size(&mmio,
+				  ALIGN_DOWN_IF_NONZERO(mmio_per_b,align));
 		mmio.start -= resource_size(res);
 
 		res = &dev->resource[PCI_BRIDGE_PREF_MEM_WINDOW];
 		align = pci_resource_alignment(dev, res);
 		resource_set_size(&mmio_pref,
-				  align ? ALIGN_DOWN(mmio_pref_per_b, align)
-					: mmio_pref_per_b);
+				  ALIGN_DOWN_IF_NONZERO(mmio_pref_per_b, align));
 		mmio_pref.start -= resource_size(res);
 
 		pci_bus_distribute_available_resources(b, add_list, io, mmio,

From c7c1bb78f3eec716bc35f58d74592331cc3281b2 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Wed, 9 Oct 2024 01:39:38 +0100
Subject: [PATCH 0270/1530] perf tools: Remove unused color_fwrite_lines

color_fwrite_lines() was added by 2009's commit
8fc0321f1ad0 ("perf_counter tools: Add color terminal output support")

but has never been used.

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20241009003938.254936-1-linux@treblig.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/color.c | 28 ----------------------------
 tools/perf/util/color.h |  1 -
 2 files changed, 29 deletions(-)

diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index bffbdd216a6a5..e51f0a676a228 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -93,34 +93,6 @@ int color_fprintf(FILE *fp, const char *color, const char *fmt, ...)
 	return r;
 }
 
-/*
- * This function splits the buffer by newlines and colors the lines individually.
- *
- * Returns 0 on success.
- */
-int color_fwrite_lines(FILE *fp, const char *color,
-		size_t count, const char *buf)
-{
-	if (!*color)
-		return fwrite(buf, count, 1, fp) != 1;
-
-	while (count) {
-		char *p = memchr(buf, '\n', count);
-
-		if (p != buf && (fputs(color, fp) < 0 ||
-				fwrite(buf, p ? (size_t)(p - buf) : count, 1, fp) != 1 ||
-				fputs(PERF_COLOR_RESET, fp) < 0))
-			return -1;
-		if (!p)
-			return 0;
-		if (fputc('\n', fp) < 0)
-			return -1;
-		count -= p + 1 - buf;
-		buf = p + 1;
-	}
-	return 0;
-}
-
 const char *get_percent_color(double percent)
 {
 	const char *color = PERF_COLOR_NORMAL;
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index 01f7bed21c9b2..aecf56dae73f5 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -39,7 +39,6 @@ int color_vsnprintf(char *bf, size_t size, const char *color,
 int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args);
 int color_fprintf(FILE *fp, const char *color, const char *fmt, ...);
 int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...);
-int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
 int value_color_snprintf(char *bf, size_t size, const char *fmt, double value);
 int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...);
 int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...);

From c051220d38463cfe8a248d204461beb3ed52b4ea Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 1 Oct 2024 20:20:04 -0700
Subject: [PATCH 0271/1530] perf pmu: Simplify an asprintf error message

Use ifs rather than ?: to avoid a large compound statement.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241002032016.333748-2-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/pmu.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 8993b5853687b..cb2eb2407de51 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1466,13 +1466,12 @@ static int pmu_config_term(const struct perf_pmu *pmu,
 		if (err) {
 			char *err_str;
 
-			parse_events_error__handle(err, term->err_val,
-				asprintf(&err_str,
-				    "value too big for format (%s), maximum is %llu",
-				    format->name, (unsigned long long)max_val) < 0
-				    ? strdup("value too big for format")
-				    : err_str,
-				    NULL);
+			if (asprintf(&err_str,
+				     "value too big for format (%s), maximum is %llu",
+				     format->name, (unsigned long long)max_val) < 0) {
+				err_str = strdup("value too big for format");
+			}
+			parse_events_error__handle(err, term->err_val, err_str, /*help=*/NULL);
 			return -EINVAL;
 		}
 		/*

From c798f72c7a67a4c089142d4b16c8b9587e6db5e6 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 1 Oct 2024 20:20:05 -0700
Subject: [PATCH 0272/1530] perf pmu: Allow hardcoded terms to be applied to
 attributes

Hard coded terms like "config=10" are skipped by perf_pmu__config
assuming they were already applied to a perf_event_attr by parse
event's config_attr function. When doing a reverse number to name
lookup in perf_pmu__name_from_config, as the hardcoded terms aren't
applied the config value is incorrect leading to misses or false
matches. Fix this by adding a parameter to have perf_pmu__config apply
hardcoded terms too (not just in parse event's config_term_common).

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241002032016.333748-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/x86/util/intel-pt.c |  3 +-
 tools/perf/tests/pmu.c              |  3 +-
 tools/perf/util/parse-events.c      |  4 ++-
 tools/perf/util/pmu.c               | 56 ++++++++++++++++++++++++-----
 tools/perf/util/pmu.h               |  4 ++-
 5 files changed, 58 insertions(+), 12 deletions(-)

diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index ea510a7486b14..8f235d8b67b62 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -75,7 +75,8 @@ static int intel_pt_parse_terms_with_default(const struct perf_pmu *pmu,
 		goto out_free;
 
 	attr.config = *config;
-	err = perf_pmu__config_terms(pmu, &attr, &terms, /*zero=*/true, /*err=*/NULL);
+	err = perf_pmu__config_terms(pmu, &attr, &terms, /*zero=*/true, /*apply_hardcoded=*/false,
+				     /*err=*/NULL);
 	if (err)
 		goto out_free;
 
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index be18506f6a242..6a681e3fb552d 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -176,7 +176,8 @@ static int test__pmu_format(struct test_suite *test __maybe_unused, int subtest
 	}
 
 	memset(&attr, 0, sizeof(attr));
-	ret = perf_pmu__config_terms(pmu, &attr, &terms, /*zero=*/false, /*err=*/NULL);
+	ret = perf_pmu__config_terms(pmu, &attr, &terms, /*zero=*/false,
+				     /*apply_hardcoded=*/false, /*err=*/NULL);
 	if (ret) {
 		pr_err("perf_pmu__config_terms failed");
 		goto err_out;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index e96cf13dc3961..6ae611e70fae3 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1546,7 +1546,9 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 		return -ENOMEM;
 	}
 
-	if (perf_pmu__config(pmu, &attr, &parsed_terms, parse_state->error)) {
+	/* Skip configuring hard coded terms that were applied by config_attr. */
+	if (perf_pmu__config(pmu, &attr, &parsed_terms, /*apply_hardcoded=*/false,
+			     parse_state->error)) {
 		free_config_terms(&config_terms);
 		parse_events_terms__exit(&parsed_terms);
 		return -EINVAL;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index cb2eb2407de51..a1c7e879cb2f9 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1366,7 +1366,8 @@ static int pmu_config_term(const struct perf_pmu *pmu,
 			   struct perf_event_attr *attr,
 			   struct parse_events_term *term,
 			   struct parse_events_terms *head_terms,
-			   bool zero, struct parse_events_error *err)
+			   bool zero, bool apply_hardcoded,
+			   struct parse_events_error *err)
 {
 	struct perf_pmu_format *format;
 	__u64 *vp;
@@ -1380,11 +1381,46 @@ static int pmu_config_term(const struct perf_pmu *pmu,
 		return 0;
 
 	/*
-	 * Hardcoded terms should be already in, so nothing
-	 * to be done for them.
+	 * Hardcoded terms are generally handled in event parsing, which
+	 * traditionally have had to handle not having a PMU. An alias may
+	 * have hard coded config values, optionally apply them below.
 	 */
-	if (parse_events__is_hardcoded_term(term))
+	if (parse_events__is_hardcoded_term(term)) {
+		/* Config terms set all bits in the config. */
+		DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
+
+		if (!apply_hardcoded)
+			return 0;
+
+		bitmap_fill(bits, PERF_PMU_FORMAT_BITS);
+
+		switch (term->type_term) {
+		case PARSE_EVENTS__TERM_TYPE_CONFIG:
+			assert(term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+			pmu_format_value(bits, term->val.num, &attr->config, zero);
+			break;
+		case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+			assert(term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+			pmu_format_value(bits, term->val.num, &attr->config1, zero);
+			break;
+		case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+			assert(term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+			pmu_format_value(bits, term->val.num, &attr->config2, zero);
+			break;
+		case PARSE_EVENTS__TERM_TYPE_CONFIG3:
+			assert(term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+			pmu_format_value(bits, term->val.num, &attr->config3, zero);
+			break;
+		case PARSE_EVENTS__TERM_TYPE_USER: /* Not hardcoded. */
+			return -EINVAL;
+		case PARSE_EVENTS__TERM_TYPE_NAME ... PARSE_EVENTS__TERM_TYPE_HARDWARE:
+			/* Skip non-config terms. */
+			break;
+		default:
+			break;
+		}
 		return 0;
+	}
 
 	format = pmu_find_format(&pmu->format, term->config);
 	if (!format) {
@@ -1487,12 +1523,13 @@ static int pmu_config_term(const struct perf_pmu *pmu,
 int perf_pmu__config_terms(const struct perf_pmu *pmu,
 			   struct perf_event_attr *attr,
 			   struct parse_events_terms *terms,
-			   bool zero, struct parse_events_error *err)
+			   bool zero, bool apply_hardcoded,
+			   struct parse_events_error *err)
 {
 	struct parse_events_term *term;
 
 	list_for_each_entry(term, &terms->terms, list) {
-		if (pmu_config_term(pmu, attr, term, terms, zero, err))
+		if (pmu_config_term(pmu, attr, term, terms, zero, apply_hardcoded, err))
 			return -EINVAL;
 	}
 
@@ -1506,6 +1543,7 @@ int perf_pmu__config_terms(const struct perf_pmu *pmu,
  */
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct parse_events_terms *head_terms,
+		     bool apply_hardcoded,
 		     struct parse_events_error *err)
 {
 	bool zero = !!pmu->perf_event_attr_init_default;
@@ -1514,7 +1552,7 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 	if (perf_pmu__is_fake(pmu))
 		return 0;
 
-	return perf_pmu__config_terms(pmu, attr, head_terms, zero, err);
+	return perf_pmu__config_terms(pmu, attr, head_terms, zero, apply_hardcoded, err);
 }
 
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
@@ -2283,7 +2321,9 @@ const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config)
 	pmu_add_cpu_aliases(pmu);
 	list_for_each_entry(event, &pmu->aliases, list) {
 		struct perf_event_attr attr = {.config = 0,};
-		int ret = perf_pmu__config(pmu, &attr, &event->terms, NULL);
+
+		int ret = perf_pmu__config(pmu, &attr, &event->terms, /*apply_hardcoded=*/true,
+					   /*err=*/NULL);
 
 		if (ret == 0 && config == attr.config)
 			return event->name;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index d352d53b8d55c..c70317d3fb040 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -206,11 +206,13 @@ typedef int (*pmu_format_callback)(void *state, const char *name, int config,
 void pmu_add_sys_aliases(struct perf_pmu *pmu);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct parse_events_terms *head_terms,
+		     bool apply_hardcoded,
 		     struct parse_events_error *error);
 int perf_pmu__config_terms(const struct perf_pmu *pmu,
 			   struct perf_event_attr *attr,
 			   struct parse_events_terms *terms,
-			   bool zero, struct parse_events_error *error);
+			   bool zero, bool apply_hardcoded,
+			   struct parse_events_error *error);
 __u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name);
 int perf_pmu__format_type(struct perf_pmu *pmu, const char *name);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_terms,

From d2f3ecb0ca2099d13bf8bf69219214c1425dc453 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 1 Oct 2024 20:20:06 -0700
Subject: [PATCH 0273/1530] perf parse-events: Expose/rename config_term_name

Expose config_term_name as parse_events__term_type_str so that PMUs not
in pmu.c may access it.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241002032016.333748-4-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/parse-events.c | 20 +++++++++++---------
 tools/perf/util/parse-events.h |  2 ++
 2 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 6ae611e70fae3..228ae469d44a0 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -800,7 +800,7 @@ static int check_type_val(struct parse_events_term *term,
 
 static bool config_term_shrinked;
 
-static const char *config_term_name(enum parse_events__term_type term_type)
+const char *parse_events__term_type_str(enum parse_events__term_type term_type)
 {
 	/*
 	 * Update according to parse-events.l
@@ -886,7 +886,7 @@ config_term_avail(enum parse_events__term_type term_type, struct parse_events_er
 
 		/* term_type is validated so indexing is safe */
 		if (asprintf(&err_str, "'%s' is not usable in 'perf stat'",
-			     config_term_name(term_type)) >= 0)
+			     parse_events__term_type_str(term_type)) >= 0)
 			parse_events_error__handle(err, -1, err_str, NULL);
 		return false;
 	}
@@ -1010,7 +1010,7 @@ do {									   \
 	case PARSE_EVENTS__TERM_TYPE_HARDWARE:
 	default:
 		parse_events_error__handle(err, term->err_term,
-					strdup(config_term_name(term->type_term)),
+					strdup(parse_events__term_type_str(term->type_term)),
 					parse_events_formats_error_string(NULL));
 		return -EINVAL;
 	}
@@ -1134,8 +1134,9 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	default:
 		if (err) {
 			parse_events_error__handle(err, term->err_term,
-						   strdup(config_term_name(term->type_term)),
-				strdup("valid terms: call-graph,stack-size\n"));
+					strdup(parse_events__term_type_str(term->type_term)),
+					strdup("valid terms: call-graph,stack-size\n")
+				);
 		}
 		return -EINVAL;
 	}
@@ -2582,7 +2583,7 @@ int parse_events_term__num(struct parse_events_term **term,
 	struct parse_events_term temp = {
 		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
 		.type_term = type_term,
-		.config    = config ? : strdup(config_term_name(type_term)),
+		.config    = config ? : strdup(parse_events__term_type_str(type_term)),
 		.no_value  = no_value,
 		.err_term  = loc_term ? loc_term->first_column : 0,
 		.err_val   = loc_val  ? loc_val->first_column  : 0,
@@ -2616,7 +2617,7 @@ int parse_events_term__term(struct parse_events_term **term,
 			    void *loc_term, void *loc_val)
 {
 	return parse_events_term__str(term, term_lhs, NULL,
-				      strdup(config_term_name(term_rhs)),
+				      strdup(parse_events__term_type_str(term_rhs)),
 				      loc_term, loc_val);
 }
 
@@ -2723,7 +2724,8 @@ int parse_events_terms__to_strbuf(const struct parse_events_terms *terms, struct
 				if (ret < 0)
 					return ret;
 			} else if ((unsigned int)term->type_term < __PARSE_EVENTS__TERM_TYPE_NR) {
-				ret = strbuf_addf(sb, "%s=", config_term_name(term->type_term));
+				ret = strbuf_addf(sb, "%s=",
+						  parse_events__term_type_str(term->type_term));
 				if (ret < 0)
 					return ret;
 			}
@@ -2743,7 +2745,7 @@ static void config_terms_list(char *buf, size_t buf_sz)
 
 	buf[0] = '\0';
 	for (i = 0; i < __PARSE_EVENTS__TERM_TYPE_NR; i++) {
-		const char *name = config_term_name(i);
+		const char *name = parse_events__term_type_str(i);
 
 		if (!config_term_avail(i, NULL))
 			continue;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 2b52f8d6aa29a..ac1feaaeb8d5d 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -168,6 +168,8 @@ struct parse_events_state {
 	bool			   wild_card_pmus;
 };
 
+const char *parse_events__term_type_str(enum parse_events__term_type term_type);
+
 bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
 			      const struct perf_pmu *pmu);
 void parse_events__shrink_config_terms(void);

From 240505b2d0adcdc8fd018117e88dc27b09734735 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 1 Oct 2024 20:20:07 -0700
Subject: [PATCH 0274/1530] perf tool_pmu: Factor tool events into their own
 PMU

Rather than treat tool events as a special kind of event, create a
tool only PMU where the events/aliases match the existing
duration_time, user_time and system_time events. Remove special
parsing and printing support for the tool events, but add function
calls for when PMU functions are called on a tool_pmu.

Move the tool PMU code in evsel into tool_pmu.c to better encapsulate
the tool event behavior in that file.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241002032016.333748-5-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-list.c      |  13 +-
 tools/perf/builtin-stat.c      |   1 +
 tools/perf/util/Build          |   1 +
 tools/perf/util/evsel.c        | 272 ++--------------------
 tools/perf/util/evsel.h        |  28 +--
 tools/perf/util/metricgroup.c  |   1 +
 tools/perf/util/parse-events.c |  39 ----
 tools/perf/util/parse-events.h |   3 -
 tools/perf/util/parse-events.l |  11 -
 tools/perf/util/parse-events.y |  16 --
 tools/perf/util/pmu.c          |  20 +-
 tools/perf/util/pmu.h          |   2 +
 tools/perf/util/pmus.c         |   9 +
 tools/perf/util/print-events.c |  36 +--
 tools/perf/util/print-events.h |   1 -
 tools/perf/util/stat-display.c |   6 +-
 tools/perf/util/stat-shadow.c  |   1 +
 tools/perf/util/tool_pmu.c     | 411 +++++++++++++++++++++++++++++++++
 tools/perf/util/tool_pmu.h     |  51 ++++
 19 files changed, 530 insertions(+), 392 deletions(-)
 create mode 100644 tools/perf/util/tool_pmu.c
 create mode 100644 tools/perf/util/tool_pmu.h

diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 65b8cba324be4..b8378ba18c282 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -19,6 +19,7 @@
 #include "util/string2.h"
 #include "util/strlist.h"
 #include "util/strbuf.h"
+#include "util/tool_pmu.h"
 #include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include <linux/zalloc.h>
@@ -614,9 +615,18 @@ int cmd_list(int argc, const char **argv)
 					event_symbols_hw, PERF_COUNT_HW_MAX);
 		else if (strcmp(argv[i], "sw") == 0 ||
 			 strcmp(argv[i], "software") == 0) {
+			char *old_pmu_glob = default_ps.pmu_glob;
+
 			print_symbol_events(&print_cb, ps, PERF_TYPE_SOFTWARE,
 					event_symbols_sw, PERF_COUNT_SW_MAX);
-			print_tool_events(&print_cb, ps);
+			default_ps.pmu_glob = strdup("tool");
+			if (!default_ps.pmu_glob) {
+				ret = -1;
+				goto out;
+			}
+			perf_pmus__print_pmu_events(&print_cb, ps);
+			zfree(&default_ps.pmu_glob);
+			default_ps.pmu_glob = old_pmu_glob;
 		} else if (strcmp(argv[i], "cache") == 0 ||
 			 strcmp(argv[i], "hwcache") == 0)
 			print_hwcache_events(&print_cb, ps);
@@ -664,7 +674,6 @@ int cmd_list(int argc, const char **argv)
 					event_symbols_hw, PERF_COUNT_HW_MAX);
 			print_symbol_events(&print_cb, ps, PERF_TYPE_SOFTWARE,
 					event_symbols_sw, PERF_COUNT_SW_MAX);
-			print_tool_events(&print_cb, ps);
 			print_hwcache_events(&print_cb, ps);
 			perf_pmus__print_pmu_events(&print_cb, ps);
 			print_tracepoint_events(&print_cb, ps);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 3e6b9f216e802..bc12975efad56 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -46,6 +46,7 @@
 #include "util/parse-events.h"
 #include "util/pmus.h"
 #include "util/pmu.h"
+#include "util/tool_pmu.h"
 #include "util/event.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index dc616292b2ddf..fa508e113dd0c 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -83,6 +83,7 @@ perf-util-y += pmu.o
 perf-util-y += pmus.o
 perf-util-y += pmu-flex.o
 perf-util-y += pmu-bison.o
+perf-util-y += tool_pmu.o
 perf-util-y += svghelper.o
 perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event-info.o
 perf-util-y += trace-event-scripting.o
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index b221459439b88..14a17f768f426 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -10,7 +10,6 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <linux/bitops.h>
-#include <api/io.h>
 #include <api/fs/fs.h>
 #include <api/fs/tracing_path.h>
 #include <linux/hw_breakpoint.h>
@@ -51,6 +50,7 @@
 #include "off_cpu.h"
 #include "pmu.h"
 #include "pmus.h"
+#include "tool_pmu.h"
 #include "rlimit.h"
 #include "../perf-sys.h"
 #include "util/parse-branch-options.h"
@@ -71,33 +71,6 @@ struct perf_missing_features perf_missing_features;
 
 static clockid_t clockid;
 
-static const char *const perf_tool_event__tool_names[PERF_TOOL_MAX] = {
-	NULL,
-	"duration_time",
-	"user_time",
-	"system_time",
-};
-
-const char *perf_tool_event__to_str(enum perf_tool_event ev)
-{
-	if (ev > PERF_TOOL_NONE && ev < PERF_TOOL_MAX)
-		return perf_tool_event__tool_names[ev];
-
-	return NULL;
-}
-
-enum perf_tool_event perf_tool_event__from_str(const char *str)
-{
-	int i;
-
-	perf_tool_event__for_each_event(i) {
-		if (!strcmp(str, perf_tool_event__tool_names[i]))
-			return i;
-	}
-	return PERF_TOOL_NONE;
-}
-
-
 static int evsel__no_extra_init(struct evsel *evsel __maybe_unused)
 {
 	return 0;
@@ -416,7 +389,6 @@ struct evsel *evsel__clone(struct evsel *orig)
 	evsel->core.leader = orig->core.leader;
 
 	evsel->max_events = orig->max_events;
-	evsel->tool_event = orig->tool_event;
 	free((char *)evsel->unit);
 	evsel->unit = strdup(orig->unit);
 	if (evsel->unit == NULL)
@@ -614,11 +586,6 @@ static int evsel__sw_name(struct evsel *evsel, char *bf, size_t size)
 	return r + evsel__add_modifiers(evsel, bf + r, size - r);
 }
 
-static int evsel__tool_name(enum perf_tool_event ev, char *bf, size_t size)
-{
-	return scnprintf(bf, size, "%s", perf_tool_event__to_str(ev));
-}
-
 static int __evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
 {
 	int r;
@@ -769,10 +736,7 @@ const char *evsel__name(struct evsel *evsel)
 		break;
 
 	case PERF_TYPE_SOFTWARE:
-		if (evsel__is_tool(evsel))
-			evsel__tool_name(evsel__tool_event(evsel), bf, sizeof(bf));
-		else
-			evsel__sw_name(evsel, bf, sizeof(bf));
+		evsel__sw_name(evsel, bf, sizeof(bf));
 		break;
 
 	case PERF_TYPE_TRACEPOINT:
@@ -783,6 +747,10 @@ const char *evsel__name(struct evsel *evsel)
 		evsel__bp_name(evsel, bf, sizeof(bf));
 		break;
 
+	case PERF_PMU_TYPE_TOOL:
+		scnprintf(bf, sizeof(bf), "%s", evsel__tool_pmu_event_name(evsel));
+		break;
+
 	default:
 		scnprintf(bf, sizeof(bf), "unknown attr type: %d",
 			  evsel->core.attr.type);
@@ -808,7 +776,7 @@ const char *evsel__metric_id(const struct evsel *evsel)
 		return evsel->metric_id;
 
 	if (evsel__is_tool(evsel))
-		return perf_tool_event__to_str(evsel__tool_event(evsel));
+		return evsel__tool_pmu_event_name(evsel);
 
 	return "unknown";
 }
@@ -1689,167 +1657,6 @@ static int evsel__read_group(struct evsel *leader, int cpu_map_idx, int thread)
 	return evsel__process_group_data(leader, cpu_map_idx, thread, data);
 }
 
-static bool read_until_char(struct io *io, char e)
-{
-	int c;
-
-	do {
-		c = io__get_char(io);
-		if (c == -1)
-			return false;
-	} while (c != e);
-	return true;
-}
-
-static int read_stat_field(int fd, struct perf_cpu cpu, int field, __u64 *val)
-{
-	char buf[256];
-	struct io io;
-	int i;
-
-	io__init(&io, fd, buf, sizeof(buf));
-
-	/* Skip lines to relevant CPU. */
-	for (i = -1; i < cpu.cpu; i++) {
-		if (!read_until_char(&io, '\n'))
-			return -EINVAL;
-	}
-	/* Skip to "cpu". */
-	if (io__get_char(&io) != 'c') return -EINVAL;
-	if (io__get_char(&io) != 'p') return -EINVAL;
-	if (io__get_char(&io) != 'u') return -EINVAL;
-
-	/* Skip N of cpuN. */
-	if (!read_until_char(&io, ' '))
-		return -EINVAL;
-
-	i = 1;
-	while (true) {
-		if (io__get_dec(&io, val) != ' ')
-			break;
-		if (field == i)
-			return 0;
-		i++;
-	}
-	return -EINVAL;
-}
-
-static int read_pid_stat_field(int fd, int field, __u64 *val)
-{
-	char buf[256];
-	struct io io;
-	int c, i;
-
-	io__init(&io, fd, buf, sizeof(buf));
-	if (io__get_dec(&io, val) != ' ')
-		return -EINVAL;
-	if (field == 1)
-		return 0;
-
-	/* Skip comm. */
-	if (io__get_char(&io) != '(' || !read_until_char(&io, ')'))
-		return -EINVAL;
-	if (field == 2)
-		return -EINVAL; /* String can't be returned. */
-
-	/* Skip state */
-	if (io__get_char(&io) != ' ' || io__get_char(&io) == -1)
-		return -EINVAL;
-	if (field == 3)
-		return -EINVAL; /* String can't be returned. */
-
-	/* Loop over numeric fields*/
-	if (io__get_char(&io) != ' ')
-		return -EINVAL;
-
-	i = 4;
-	while (true) {
-		c = io__get_dec(&io, val);
-		if (c == -1)
-			return -EINVAL;
-		if (c == -2) {
-			/* Assume a -ve was read */
-			c = io__get_dec(&io, val);
-			*val *= -1;
-		}
-		if (c != ' ')
-			return -EINVAL;
-		if (field == i)
-			return 0;
-		i++;
-	}
-	return -EINVAL;
-}
-
-static int evsel__read_tool(struct evsel *evsel, int cpu_map_idx, int thread)
-{
-	__u64 *start_time, cur_time, delta_start;
-	int fd, err = 0;
-	struct perf_counts_values *count;
-	bool adjust = false;
-
-	count = perf_counts(evsel->counts, cpu_map_idx, thread);
-
-	switch (evsel__tool_event(evsel)) {
-	case PERF_TOOL_DURATION_TIME:
-		/*
-		 * Pretend duration_time is only on the first CPU and thread, or
-		 * else aggregation will scale duration_time by the number of
-		 * CPUs/threads.
-		 */
-		start_time = &evsel->start_time;
-		if (cpu_map_idx == 0 && thread == 0)
-			cur_time = rdclock();
-		else
-			cur_time = *start_time;
-		break;
-	case PERF_TOOL_USER_TIME:
-	case PERF_TOOL_SYSTEM_TIME: {
-		bool system = evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME;
-
-		start_time = xyarray__entry(evsel->start_times, cpu_map_idx, thread);
-		fd = FD(evsel, cpu_map_idx, thread);
-		lseek(fd, SEEK_SET, 0);
-		if (evsel->pid_stat) {
-			/* The event exists solely on 1 CPU. */
-			if (cpu_map_idx == 0)
-				err = read_pid_stat_field(fd, system ? 15 : 14, &cur_time);
-			else
-				cur_time = 0;
-		} else {
-			/* The event is for all threads. */
-			if (thread == 0) {
-				struct perf_cpu cpu = perf_cpu_map__cpu(evsel->core.cpus,
-									cpu_map_idx);
-
-				err = read_stat_field(fd, cpu, system ? 3 : 1, &cur_time);
-			} else {
-				cur_time = 0;
-			}
-		}
-		adjust = true;
-		break;
-	}
-	case PERF_TOOL_NONE:
-	case PERF_TOOL_MAX:
-	default:
-		err = -EINVAL;
-	}
-	if (err)
-		return err;
-
-	delta_start = cur_time - *start_time;
-	if (adjust) {
-		__u64 ticks_per_sec = sysconf(_SC_CLK_TCK);
-
-		delta_start *= 1000000000 / ticks_per_sec;
-	}
-	count->val    = delta_start;
-	count->ena    = count->run = delta_start;
-	count->lost   = 0;
-	return 0;
-}
-
 bool __evsel__match(const struct evsel *evsel, u32 type, u64 config)
 {
 
@@ -2065,6 +1872,7 @@ static struct perf_thread_map *empty_thread_map;
 static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 		struct perf_thread_map *threads)
 {
+	int ret = 0;
 	int nthreads = perf_thread_map__nr(threads);
 
 	if ((perf_missing_features.write_backward && evsel->core.attr.write_backward) ||
@@ -2095,19 +1903,14 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 	    perf_evsel__alloc_fd(&evsel->core, perf_cpu_map__nr(cpus), nthreads) < 0)
 		return -ENOMEM;
 
-	if ((evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME ||
-	     evsel__tool_event(evsel) == PERF_TOOL_USER_TIME) &&
-	    !evsel->start_times) {
-		evsel->start_times = xyarray__new(perf_cpu_map__nr(cpus), nthreads, sizeof(__u64));
-		if (!evsel->start_times)
-			return -ENOMEM;
-	}
+	if (evsel__is_tool(evsel))
+		ret = evsel__tool_pmu_prepare_open(evsel, cpus, nthreads);
 
 	evsel->open_flags = PERF_FLAG_FD_CLOEXEC;
 	if (evsel->cgrp)
 		evsel->open_flags |= PERF_FLAG_PID_CGROUP;
 
-	return 0;
+	return ret;
 }
 
 static void evsel__disable_missing_features(struct evsel *evsel)
@@ -2292,13 +2095,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 	int pid = -1, err, old_errno;
 	enum rlimit_action set_rlimit = NO_CHANGE;
 
-	if (evsel__tool_event(evsel) == PERF_TOOL_DURATION_TIME) {
-		if (evsel->core.attr.sample_period) /* no sampling */
-			return -EINVAL;
-		evsel->start_time = rdclock();
-		return 0;
-	}
-
 	if (evsel__is_retire_lat(evsel))
 		return tpebs_start(evsel->evlist);
 
@@ -2323,6 +2119,12 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 	pr_debug3("Opening: %s\n", evsel__name(evsel));
 	display_attr(&evsel->core.attr);
 
+	if (evsel__is_tool(evsel)) {
+		return evsel__tool_pmu_open(evsel, threads,
+					    start_cpu_map_idx,
+					    end_cpu_map_idx);
+	}
+
 	for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) {
 
 		for (thread = 0; thread < nthreads; thread++) {
@@ -2334,46 +2136,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 			if (!evsel->cgrp && !evsel->core.system_wide)
 				pid = perf_thread_map__pid(threads, thread);
 
-			if (evsel__tool_event(evsel) == PERF_TOOL_USER_TIME ||
-			    evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME) {
-				bool system = evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME;
-				__u64 *start_time = NULL;
-
-				if (evsel->core.attr.sample_period) {
-					/* no sampling */
-					err = -EINVAL;
-					goto out_close;
-				}
-				if (pid > -1) {
-					char buf[64];
-
-					snprintf(buf, sizeof(buf), "/proc/%d/stat", pid);
-					fd = open(buf, O_RDONLY);
-					evsel->pid_stat = true;
-				} else {
-					fd = open("/proc/stat", O_RDONLY);
-				}
-				FD(evsel, idx, thread) = fd;
-				if (fd < 0) {
-					err = -errno;
-					goto out_close;
-				}
-				start_time = xyarray__entry(evsel->start_times, idx, thread);
-				if (pid > -1) {
-					err = read_pid_stat_field(fd, system ? 15 : 14,
-								  start_time);
-				} else {
-					struct perf_cpu cpu;
-
-					cpu = perf_cpu_map__cpu(evsel->core.cpus, idx);
-					err = read_stat_field(fd, cpu, system ? 3 : 1,
-							      start_time);
-				}
-				if (err)
-					goto out_close;
-				continue;
-			}
-
 			group_fd = get_group_fd(evsel, idx, thread);
 
 			if (group_fd == -2) {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index bd08d94d3f8ab..9fcaf417b2778 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -11,6 +11,7 @@
 #include <perf/evsel.h>
 #include "symbol_conf.h"
 #include "pmus.h"
+#include "pmu.h"
 
 struct bpf_object;
 struct cgroup;
@@ -22,25 +23,9 @@ struct target;
 struct hashmap;
 struct bperf_leader_bpf;
 struct bperf_follower_bpf;
-struct perf_pmu;
 
 typedef int (evsel__sb_cb_t)(union perf_event *event, void *data);
 
-enum perf_tool_event {
-	PERF_TOOL_NONE		= 0,
-	PERF_TOOL_DURATION_TIME = 1,
-	PERF_TOOL_USER_TIME = 2,
-	PERF_TOOL_SYSTEM_TIME = 3,
-
-	PERF_TOOL_MAX,
-};
-
-const char *perf_tool_event__to_str(enum perf_tool_event ev);
-enum perf_tool_event perf_tool_event__from_str(const char *str);
-
-#define perf_tool_event__for_each_event(ev)		\
-	for ((ev) = PERF_TOOL_DURATION_TIME; (ev) < PERF_TOOL_MAX; ev++)
-
 /** struct evsel - event selector
  *
  * @evlist - evlist this evsel is in, if it is in one.
@@ -82,7 +67,6 @@ struct evsel {
 		const char		*unit;
 		struct cgroup		*cgrp;
 		const char		*metric_id;
-		enum perf_tool_event	tool_event;
 		/* parse modifier helper */
 		int			exclude_GH;
 		int			sample_read;
@@ -321,21 +305,11 @@ const char *evsel__name(struct evsel *evsel);
 bool evsel__name_is(struct evsel *evsel, const char *name);
 const char *evsel__metric_id(const struct evsel *evsel);
 
-static inline bool evsel__is_tool(const struct evsel *evsel)
-{
-	return evsel->tool_event != PERF_TOOL_NONE;
-}
-
 static inline bool evsel__is_retire_lat(const struct evsel *evsel)
 {
 	return evsel->retire_lat;
 }
 
-static inline enum perf_tool_event evsel__tool_event(const struct evsel *evsel)
-{
-	return evsel->tool_event;
-}
-
 const char *evsel__group_name(struct evsel *evsel);
 int evsel__group_desc(struct evsel *evsel, char *buf, size_t size);
 
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 9c6fa6b4f628c..827bab455d5bc 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -14,6 +14,7 @@
 #include "pmus.h"
 #include "print-events.h"
 #include "smt.h"
+#include "tool_pmu.h"
 #include "expr.h"
 #include "rblist.h"
 #include <string.h>
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 228ae469d44a0..4507ae68198bd 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -301,38 +301,6 @@ static int add_event(struct list_head *list, int *idx,
 			   alternate_hw_config) ? 0 : -ENOMEM;
 }
 
-static int add_event_tool(struct list_head *list, int *idx,
-			  enum perf_tool_event tool_event)
-{
-	struct evsel *evsel;
-	struct perf_event_attr attr = {
-		.type = PERF_TYPE_SOFTWARE,
-		.config = PERF_COUNT_SW_DUMMY,
-	};
-	struct perf_cpu_map *cpu_list = NULL;
-
-	if (tool_event == PERF_TOOL_DURATION_TIME) {
-		/* Duration time is gathered globally, pretend it is only on CPU0. */
-		cpu_list = perf_cpu_map__new("0");
-	}
-	evsel = __add_event(list, idx, &attr, /*init_attr=*/true, /*name=*/NULL,
-			    /*metric_id=*/NULL, /*pmu=*/NULL,
-			    /*config_terms=*/NULL, /*auto_merge_stats=*/false,
-			    cpu_list,
-			    /*alternate_hw_config=*/PERF_COUNT_HW_MAX);
-	perf_cpu_map__put(cpu_list);
-	if (!evsel)
-		return -ENOMEM;
-	evsel->tool_event = tool_event;
-	if (tool_event == PERF_TOOL_DURATION_TIME
-	    || tool_event == PERF_TOOL_USER_TIME
-	    || tool_event == PERF_TOOL_SYSTEM_TIME) {
-		free((char *)evsel->unit);
-		evsel->unit = strdup("ns");
-	}
-	return 0;
-}
-
 /**
  * parse_aliases - search names for entries beginning or equalling str ignoring
  *                 case. If mutliple entries in names match str then the longest
@@ -1430,13 +1398,6 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 					type, /*extended_type=*/0, config, head_config);
 }
 
-int parse_events_add_tool(struct parse_events_state *parse_state,
-			  struct list_head *list,
-			  int tool_event)
-{
-	return add_event_tool(list, &parse_state->idx, tool_event);
-}
-
 static bool config_term_percore(struct list_head *config_terms)
 {
 	struct evsel_config_term *term;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index ac1feaaeb8d5d..3f4334ec62317 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -229,9 +229,6 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 			     u32 type, u64 config,
 			     const struct parse_events_terms *head_config,
 			     bool wildcard);
-int parse_events_add_tool(struct parse_events_state *parse_state,
-			  struct list_head *list,
-			  int tool_event);
 int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 			   struct parse_events_state *parse_state,
 			   struct parse_events_terms *parsed_terms);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 5a0bcd7f166ae..14e5bd856a187 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -121,14 +121,6 @@ static int sym(yyscan_t scanner, int type, int config)
 	return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
 }
 
-static int tool(yyscan_t scanner, enum perf_tool_event event)
-{
-	YYSTYPE *yylval = parse_events_get_lval(scanner);
-
-	yylval->num = event;
-	return PE_VALUE_SYM_TOOL;
-}
-
 static int term(yyscan_t scanner, enum parse_events__term_type type)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
@@ -404,9 +396,6 @@ cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU
 alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
-duration_time					{ return tool(yyscanner, PERF_TOOL_DURATION_TIME); }
-user_time						{ return tool(yyscanner, PERF_TOOL_USER_TIME); }
-system_time						{ return tool(yyscanner, PERF_TOOL_SYSTEM_TIME); }
 bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 cgroup-switches					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CGROUP_SWITCHES); }
 
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index dcf47fabdfdd7..f888cbb076d67 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -56,7 +56,6 @@ static void free_list_evsel(struct list_head* list_evsel)
 
 %token PE_START_EVENTS PE_START_TERMS
 %token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_TERM
-%token PE_VALUE_SYM_TOOL
 %token PE_EVENT_NAME
 %token PE_RAW PE_NAME
 %token PE_MODIFIER_EVENT PE_MODIFIER_BP PE_BP_COLON PE_BP_SLASH
@@ -68,7 +67,6 @@ static void free_list_evsel(struct list_head* list_evsel)
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
-%type <num> PE_VALUE_SYM_TOOL
 %type <mod> PE_MODIFIER_EVENT
 %type <term_type> PE_TERM
 %type <num> value_sym
@@ -350,20 +348,6 @@ value_sym sep_slash_slash_dc
 		PE_ABORT(err);
 	$$ = list;
 }
-|
-PE_VALUE_SYM_TOOL sep_slash_slash_dc
-{
-	struct list_head *list;
-	int err;
-
-	list = alloc_list();
-	if (!list)
-		YYNOMEM;
-	err = parse_events_add_tool(_parse_state, list, $1);
-	if (err)
-		YYNOMEM;
-	$$ = list;
-}
 
 event_legacy_cache:
 PE_LEGACY_CACHE opt_event_config
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index a1c7e879cb2f9..762942853351d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -19,6 +19,7 @@
 #include "evsel.h"
 #include "pmu.h"
 #include "pmus.h"
+#include "tool_pmu.h"
 #include <util/pmu-bison.h>
 #include <util/pmu-flex.h>
 #include "parse-events.h"
@@ -1548,6 +1549,9 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 {
 	bool zero = !!pmu->perf_event_attr_init_default;
 
+	if (perf_pmu__is_tool(pmu))
+		return tool_pmu__config_terms(attr, head_terms, err);
+
 	/* Fake PMU doesn't have proper terms so nothing to configure in attr. */
 	if (perf_pmu__is_fake(pmu))
 		return 0;
@@ -1660,8 +1664,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_
 	info->scale    = 0.0;
 	info->snapshot = false;
 
-	/* Fake PMU doesn't rewrite terms. */
-	if (perf_pmu__is_fake(pmu))
+	/* Tool/fake PMU doesn't rewrite terms. */
+	if (perf_pmu__is_tool(pmu) || perf_pmu__is_fake(pmu))
 		goto out;
 
 	list_for_each_entry_safe(term, h, &head_terms->terms, list) {
@@ -1831,6 +1835,8 @@ bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name)
 {
 	if (!name)
 		return false;
+	if (perf_pmu__is_tool(pmu))
+		return perf_tool_event__from_str(name) != PERF_TOOL_NONE;
 	if (perf_pmu__find_alias(pmu, name, /*load=*/ true) != NULL)
 		return true;
 	if (pmu->cpu_aliases_added || !pmu->events_table)
@@ -1842,6 +1848,9 @@ size_t perf_pmu__num_events(struct perf_pmu *pmu)
 {
 	size_t nr;
 
+	if (perf_pmu__is_tool(pmu))
+		return tool_pmu__num_events();
+
 	pmu_aliases_parse(pmu);
 	nr = pmu->sysfs_aliases + pmu->sys_json_aliases;
 
@@ -1902,6 +1911,9 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 	int ret = 0;
 	struct strbuf sb;
 
+	if (perf_pmu__is_tool(pmu))
+		return tool_pmu__for_each_event_cb(pmu, state, cb);
+
 	strbuf_init(&sb, /*hint=*/ 0);
 	pmu_aliases_parse(pmu);
 	pmu_add_cpu_aliases(pmu);
@@ -1990,6 +2002,7 @@ bool perf_pmu__is_software(const struct perf_pmu *pmu)
 	case PERF_TYPE_HW_CACHE:	return false;
 	case PERF_TYPE_RAW:		return false;
 	case PERF_TYPE_BREAKPOINT:	return true;
+	case PERF_PMU_TYPE_TOOL:	return true;
 	default: break;
 	}
 	for (size_t i = 0; i < ARRAY_SIZE(known_sw_pmus); i++) {
@@ -2317,6 +2330,9 @@ const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config)
 	if (!pmu)
 		return NULL;
 
+	if (perf_pmu__is_tool(pmu))
+		return perf_tool_event__to_str(config);
+
 	pmu_aliases_parse(pmu);
 	pmu_add_cpu_aliases(pmu);
 	list_for_each_entry(event, &pmu->aliases, list) {
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index c70317d3fb040..36fced2bf0651 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -37,6 +37,7 @@ struct perf_pmu_caps {
 };
 
 enum {
+	PERF_PMU_TYPE_TOOL = 0xFFFFFFFE,
 	PERF_PMU_TYPE_FAKE = 0xFFFFFFFF,
 };
 
@@ -282,6 +283,7 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
 void perf_pmu__delete(struct perf_pmu *pmu);
 struct perf_pmu *perf_pmus__find_core_pmu(void);
+
 const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config);
 bool perf_pmu__is_fake(const struct perf_pmu *pmu);
 
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index 52109af5f2f12..6e657c44de58e 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -15,6 +15,7 @@
 #include "evsel.h"
 #include "pmus.h"
 #include "pmu.h"
+#include "tool_pmu.h"
 #include "print-events.h"
 #include "strbuf.h"
 
@@ -200,6 +201,7 @@ static void pmu_read_sysfs(bool core_only)
 	int fd;
 	DIR *dir;
 	struct dirent *dent;
+	struct perf_pmu *tool_pmu;
 
 	if (read_sysfs_all_pmus || (core_only && read_sysfs_core_pmus))
 		return;
@@ -229,6 +231,10 @@ static void pmu_read_sysfs(bool core_only)
 			pr_err("Failure to set up any core PMUs\n");
 	}
 	list_sort(NULL, &core_pmus, pmus_cmp);
+	if (!core_only) {
+		tool_pmu = perf_pmus__tool_pmu();
+		list_add_tail(&tool_pmu->list, &other_pmus);
+	}
 	list_sort(NULL, &other_pmus, pmus_cmp);
 	if (!list_empty(&core_pmus)) {
 		read_sysfs_core_pmus = true;
@@ -584,6 +590,9 @@ void perf_pmus__print_raw_pmu_events(const struct print_callbacks *print_cb, voi
 		int len = pmu_name_len_no_suffix(pmu->name);
 		const char *desc = "(see 'man perf-list' or 'man perf-record' on how to encode it)";
 
+		if (perf_pmu__is_tool(pmu))
+			continue;
+
 		if (!pmu->is_core)
 			desc = NULL;
 
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index 81e0135cddf01..a786cbfb0ff56 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -29,6 +29,7 @@
 #include "tracepoint.h"
 #include "pfm.h"
 #include "thread_map.h"
+#include "tool_pmu.h"
 #include "util.h"
 
 #define MAX_NAME_LEN 100
@@ -43,21 +44,6 @@ static const char * const event_type_descriptors[] = {
 	"Hardware breakpoint",
 };
 
-static const struct event_symbol event_symbols_tool[PERF_TOOL_MAX] = {
-	[PERF_TOOL_DURATION_TIME] = {
-		.symbol = "duration_time",
-		.alias  = "",
-	},
-	[PERF_TOOL_USER_TIME] = {
-		.symbol = "user_time",
-		.alias  = "",
-	},
-	[PERF_TOOL_SYSTEM_TIME] = {
-		.symbol = "system_time",
-		.alias  = "",
-	},
-};
-
 /*
  * Print the events from <debugfs_mount_point>/tracing/events
  */
@@ -341,24 +327,6 @@ int print_hwcache_events(const struct print_callbacks *print_cb, void *print_sta
 	return 0;
 }
 
-void print_tool_events(const struct print_callbacks *print_cb, void *print_state)
-{
-	// Start at 1 because the first enum entry means no tool event.
-	for (int i = 1; i < PERF_TOOL_MAX; ++i) {
-		print_cb->print_event(print_state,
-				"tool",
-				/*pmu_name=*/NULL,
-				event_symbols_tool[i].symbol,
-				event_symbols_tool[i].alias,
-				/*scale_unit=*/NULL,
-				/*deprecated=*/false,
-				"Tool event",
-				/*desc=*/NULL,
-				/*long_desc=*/NULL,
-				/*encoding_desc=*/NULL);
-	}
-}
-
 void print_symbol_events(const struct print_callbacks *print_cb, void *print_state,
 			 unsigned int type, const struct event_symbol *syms,
 			 unsigned int max)
@@ -422,8 +390,6 @@ void print_events(const struct print_callbacks *print_cb, void *print_state)
 	print_symbol_events(print_cb, print_state, PERF_TYPE_SOFTWARE,
 			event_symbols_sw, PERF_COUNT_SW_MAX);
 
-	print_tool_events(print_cb, print_state);
-
 	print_hwcache_events(print_cb, print_state);
 
 	perf_pmus__print_pmu_events(print_cb, print_state);
diff --git a/tools/perf/util/print-events.h b/tools/perf/util/print-events.h
index bf4290bef0cd6..445efa1636c1b 100644
--- a/tools/perf/util/print-events.h
+++ b/tools/perf/util/print-events.h
@@ -36,7 +36,6 @@ void print_sdt_events(const struct print_callbacks *print_cb, void *print_state)
 void print_symbol_events(const struct print_callbacks *print_cb, void *print_state,
 			 unsigned int type, const struct event_symbol *syms,
 			 unsigned int max);
-void print_tool_events(const struct print_callbacks *print_cb, void *print_state);
 void print_tracepoint_events(const struct print_callbacks *print_cb, void *print_state);
 bool is_event_supported(u8 type, u64 config);
 
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 5402998881c44..ca85270678690 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -22,6 +22,7 @@
 #include "iostat.h"
 #include "pmu.h"
 #include "pmus.h"
+#include "tool_pmu.h"
 
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
@@ -982,7 +983,10 @@ static bool should_skip_zero_counter(struct perf_stat_config *config,
 	if (config->aggr_mode == AGGR_THREAD && config->system_wide)
 		return true;
 
-	/* Tool events have the software PMU but are only gathered on 1. */
+	/*
+	 * Many tool events are only gathered on the first index, skip other
+	 * zero values.
+	 */
 	if (evsel__is_tool(counter))
 		return true;
 
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 3ce756b8ede50..50f347217d84c 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -15,6 +15,7 @@
 #include <linux/zalloc.h>
 #include "iostat.h"
 #include "util/hashmap.h"
+#include "tool_pmu.h"
 
 struct stats walltime_nsecs_stats;
 struct rusage_stats ru_stats;
diff --git a/tools/perf/util/tool_pmu.c b/tools/perf/util/tool_pmu.c
new file mode 100644
index 0000000000000..f41fed39d70d8
--- /dev/null
+++ b/tools/perf/util/tool_pmu.c
@@ -0,0 +1,411 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "cgroup.h"
+#include "counts.h"
+#include "evsel.h"
+#include "pmu.h"
+#include "print-events.h"
+#include "time-utils.h"
+#include "tool_pmu.h"
+#include <api/io.h>
+#include <internal/threadmap.h>
+#include <perf/threadmap.h>
+#include <fcntl.h>
+#include <strings.h>
+
+static const char *const tool_pmu__event_names[PERF_TOOL_MAX] = {
+	NULL,
+	"duration_time",
+	"user_time",
+	"system_time",
+};
+
+
+const char *perf_tool_event__to_str(enum perf_tool_event ev)
+{
+	if (ev > PERF_TOOL_NONE && ev < PERF_TOOL_MAX)
+		return tool_pmu__event_names[ev];
+
+	return NULL;
+}
+
+enum perf_tool_event perf_tool_event__from_str(const char *str)
+{
+	int i;
+
+	perf_tool_event__for_each_event(i) {
+		if (!strcasecmp(str, tool_pmu__event_names[i]))
+			return i;
+	}
+	return PERF_TOOL_NONE;
+}
+
+static int tool_pmu__config_term(struct perf_event_attr *attr,
+				 struct parse_events_term *term,
+				 struct parse_events_error *err)
+{
+	if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER) {
+		enum perf_tool_event ev = perf_tool_event__from_str(term->config);
+
+		if (ev == PERF_TOOL_NONE)
+			goto err_out;
+
+		attr->config = ev;
+		return 0;
+	}
+err_out:
+	if (err) {
+		char *err_str;
+
+		parse_events_error__handle(err, term->err_val,
+					asprintf(&err_str,
+						"unexpected tool event term (%s) %s",
+						parse_events__term_type_str(term->type_term),
+						term->config) < 0
+					? strdup("unexpected tool event term")
+					: err_str,
+					NULL);
+	}
+	return -EINVAL;
+}
+
+int tool_pmu__config_terms(struct perf_event_attr *attr,
+			   struct parse_events_terms *terms,
+			   struct parse_events_error *err)
+{
+	struct parse_events_term *term;
+
+	list_for_each_entry(term, &terms->terms, list) {
+		if (tool_pmu__config_term(attr, term, err))
+			return -EINVAL;
+	}
+
+	return 0;
+
+}
+
+int tool_pmu__for_each_event_cb(struct perf_pmu *pmu, void *state, pmu_event_callback cb)
+{
+	struct pmu_event_info info = {
+		.pmu = pmu,
+		.event_type_desc = "Tool event",
+	};
+	int i;
+
+	perf_tool_event__for_each_event(i) {
+		int ret;
+
+		info.name = perf_tool_event__to_str(i);
+		info.alias = NULL;
+		info.scale_unit = NULL;
+		info.desc = NULL;
+		info.long_desc = NULL;
+		info.encoding_desc = NULL;
+		info.topic = NULL;
+		info.pmu_name = pmu->name;
+		info.deprecated = false;
+		ret = cb(state, &info);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+bool perf_pmu__is_tool(const struct perf_pmu *pmu)
+{
+	return pmu && pmu->type == PERF_PMU_TYPE_TOOL;
+}
+
+bool evsel__is_tool(const struct evsel *evsel)
+{
+	return perf_pmu__is_tool(evsel->pmu);
+}
+
+enum perf_tool_event evsel__tool_event(const struct evsel *evsel)
+{
+	if (!evsel__is_tool(evsel))
+		return PERF_TOOL_NONE;
+
+	return (enum perf_tool_event)evsel->core.attr.config;
+}
+
+const char *evsel__tool_pmu_event_name(const struct evsel *evsel)
+{
+	return perf_tool_event__to_str(evsel->core.attr.config);
+}
+
+static bool read_until_char(struct io *io, char e)
+{
+	int c;
+
+	do {
+		c = io__get_char(io);
+		if (c == -1)
+			return false;
+	} while (c != e);
+	return true;
+}
+
+static int read_stat_field(int fd, struct perf_cpu cpu, int field, __u64 *val)
+{
+	char buf[256];
+	struct io io;
+	int i;
+
+	io__init(&io, fd, buf, sizeof(buf));
+
+	/* Skip lines to relevant CPU. */
+	for (i = -1; i < cpu.cpu; i++) {
+		if (!read_until_char(&io, '\n'))
+			return -EINVAL;
+	}
+	/* Skip to "cpu". */
+	if (io__get_char(&io) != 'c') return -EINVAL;
+	if (io__get_char(&io) != 'p') return -EINVAL;
+	if (io__get_char(&io) != 'u') return -EINVAL;
+
+	/* Skip N of cpuN. */
+	if (!read_until_char(&io, ' '))
+		return -EINVAL;
+
+	i = 1;
+	while (true) {
+		if (io__get_dec(&io, val) != ' ')
+			break;
+		if (field == i)
+			return 0;
+		i++;
+	}
+	return -EINVAL;
+}
+
+static int read_pid_stat_field(int fd, int field, __u64 *val)
+{
+	char buf[256];
+	struct io io;
+	int c, i;
+
+	io__init(&io, fd, buf, sizeof(buf));
+	if (io__get_dec(&io, val) != ' ')
+		return -EINVAL;
+	if (field == 1)
+		return 0;
+
+	/* Skip comm. */
+	if (io__get_char(&io) != '(' || !read_until_char(&io, ')'))
+		return -EINVAL;
+	if (field == 2)
+		return -EINVAL; /* String can't be returned. */
+
+	/* Skip state */
+	if (io__get_char(&io) != ' ' || io__get_char(&io) == -1)
+		return -EINVAL;
+	if (field == 3)
+		return -EINVAL; /* String can't be returned. */
+
+	/* Loop over numeric fields*/
+	if (io__get_char(&io) != ' ')
+		return -EINVAL;
+
+	i = 4;
+	while (true) {
+		c = io__get_dec(&io, val);
+		if (c == -1)
+			return -EINVAL;
+		if (c == -2) {
+			/* Assume a -ve was read */
+			c = io__get_dec(&io, val);
+			*val *= -1;
+		}
+		if (c != ' ')
+			return -EINVAL;
+		if (field == i)
+			return 0;
+		i++;
+	}
+	return -EINVAL;
+}
+
+int evsel__tool_pmu_prepare_open(struct evsel *evsel,
+				 struct perf_cpu_map *cpus,
+				 int nthreads)
+{
+	if ((evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME ||
+	     evsel__tool_event(evsel) == PERF_TOOL_USER_TIME) &&
+	    !evsel->start_times) {
+		evsel->start_times = xyarray__new(perf_cpu_map__nr(cpus),
+						  nthreads,
+						  sizeof(__u64));
+		if (!evsel->start_times)
+			return -ENOMEM;
+	}
+	return 0;
+}
+
+#define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y))
+
+int evsel__tool_pmu_open(struct evsel *evsel,
+			 struct perf_thread_map *threads,
+			 int start_cpu_map_idx, int end_cpu_map_idx)
+{
+	enum perf_tool_event ev = evsel__tool_event(evsel);
+	int pid = -1, idx = 0, thread = 0, nthreads, err = 0, old_errno;
+
+	if (ev == PERF_TOOL_DURATION_TIME) {
+		if (evsel->core.attr.sample_period) /* no sampling */
+			return -EINVAL;
+		evsel->start_time = rdclock();
+		return 0;
+	}
+
+	if (evsel->cgrp)
+		pid = evsel->cgrp->fd;
+
+	nthreads = perf_thread_map__nr(threads);
+	for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) {
+		for (thread = 0; thread < nthreads; thread++) {
+			if (thread >= nthreads)
+				break;
+
+			if (!evsel->cgrp && !evsel->core.system_wide)
+				pid = perf_thread_map__pid(threads, thread);
+
+			if (ev == PERF_TOOL_USER_TIME || ev == PERF_TOOL_SYSTEM_TIME) {
+				bool system = ev == PERF_TOOL_SYSTEM_TIME;
+				__u64 *start_time = NULL;
+				int fd;
+
+				if (evsel->core.attr.sample_period) {
+					/* no sampling */
+					err = -EINVAL;
+					goto out_close;
+				}
+				if (pid > -1) {
+					char buf[64];
+
+					snprintf(buf, sizeof(buf), "/proc/%d/stat", pid);
+					fd = open(buf, O_RDONLY);
+					evsel->pid_stat = true;
+				} else {
+					fd = open("/proc/stat", O_RDONLY);
+				}
+				FD(evsel, idx, thread) = fd;
+				if (fd < 0) {
+					err = -errno;
+					goto out_close;
+				}
+				start_time = xyarray__entry(evsel->start_times, idx, thread);
+				if (pid > -1) {
+					err = read_pid_stat_field(fd, system ? 15 : 14,
+								  start_time);
+				} else {
+					struct perf_cpu cpu;
+
+					cpu = perf_cpu_map__cpu(evsel->core.cpus, idx);
+					err = read_stat_field(fd, cpu, system ? 3 : 1,
+							      start_time);
+				}
+				if (err)
+					goto out_close;
+			}
+
+		}
+	}
+	return 0;
+out_close:
+	if (err)
+		threads->err_thread = thread;
+
+	old_errno = errno;
+	do {
+		while (--thread >= 0) {
+			if (FD(evsel, idx, thread) >= 0)
+				close(FD(evsel, idx, thread));
+			FD(evsel, idx, thread) = -1;
+		}
+		thread = nthreads;
+	} while (--idx >= 0);
+	errno = old_errno;
+	return err;
+}
+
+int evsel__read_tool(struct evsel *evsel, int cpu_map_idx, int thread)
+{
+	__u64 *start_time, cur_time, delta_start;
+	int fd, err = 0;
+	struct perf_counts_values *count;
+	bool adjust = false;
+
+	count = perf_counts(evsel->counts, cpu_map_idx, thread);
+
+	switch (evsel__tool_event(evsel)) {
+	case PERF_TOOL_DURATION_TIME:
+		/*
+		 * Pretend duration_time is only on the first CPU and thread, or
+		 * else aggregation will scale duration_time by the number of
+		 * CPUs/threads.
+		 */
+		start_time = &evsel->start_time;
+		if (cpu_map_idx == 0 && thread == 0)
+			cur_time = rdclock();
+		else
+			cur_time = *start_time;
+		break;
+	case PERF_TOOL_USER_TIME:
+	case PERF_TOOL_SYSTEM_TIME: {
+		bool system = evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME;
+
+		start_time = xyarray__entry(evsel->start_times, cpu_map_idx, thread);
+		fd = FD(evsel, cpu_map_idx, thread);
+		lseek(fd, SEEK_SET, 0);
+		if (evsel->pid_stat) {
+			/* The event exists solely on 1 CPU. */
+			if (cpu_map_idx == 0)
+				err = read_pid_stat_field(fd, system ? 15 : 14, &cur_time);
+			else
+				cur_time = 0;
+		} else {
+			/* The event is for all threads. */
+			if (thread == 0) {
+				struct perf_cpu cpu = perf_cpu_map__cpu(evsel->core.cpus,
+									cpu_map_idx);
+
+				err = read_stat_field(fd, cpu, system ? 3 : 1, &cur_time);
+			} else {
+				cur_time = 0;
+			}
+		}
+		adjust = true;
+		break;
+	}
+	case PERF_TOOL_NONE:
+	case PERF_TOOL_MAX:
+	default:
+		err = -EINVAL;
+	}
+	if (err)
+		return err;
+
+	delta_start = cur_time - *start_time;
+	if (adjust) {
+		__u64 ticks_per_sec = sysconf(_SC_CLK_TCK);
+
+		delta_start *= 1000000000 / ticks_per_sec;
+	}
+	count->val    = delta_start;
+	count->ena    = count->run = delta_start;
+	count->lost   = 0;
+	return 0;
+}
+
+struct perf_pmu *perf_pmus__tool_pmu(void)
+{
+	static struct perf_pmu tool = {
+		.name = "tool",
+		.type = PERF_PMU_TYPE_TOOL,
+		.aliases = LIST_HEAD_INIT(tool.aliases),
+		.caps = LIST_HEAD_INIT(tool.caps),
+		.format = LIST_HEAD_INIT(tool.format),
+	};
+
+	return &tool;
+}
diff --git a/tools/perf/util/tool_pmu.h b/tools/perf/util/tool_pmu.h
new file mode 100644
index 0000000000000..05a4052c8b9d8
--- /dev/null
+++ b/tools/perf/util/tool_pmu.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TOOL_PMU_H
+#define __TOOL_PMU_H
+
+#include "pmu.h"
+
+struct evsel;
+struct perf_thread_map;
+struct print_callbacks;
+
+enum perf_tool_event {
+	PERF_TOOL_NONE = 0,
+	PERF_TOOL_DURATION_TIME = 1,
+	PERF_TOOL_USER_TIME = 2,
+	PERF_TOOL_SYSTEM_TIME = 3,
+
+	PERF_TOOL_MAX,
+};
+
+#define perf_tool_event__for_each_event(ev)				\
+	for ((ev) = PERF_TOOL_DURATION_TIME; (ev) < PERF_TOOL_MAX; ev++)
+
+static inline size_t tool_pmu__num_events(void)
+{
+	return PERF_TOOL_MAX - 1;
+}
+
+const char *perf_tool_event__to_str(enum perf_tool_event ev);
+enum perf_tool_event perf_tool_event__from_str(const char *str);
+int tool_pmu__config_terms(struct perf_event_attr *attr,
+			   struct parse_events_terms *terms,
+			   struct parse_events_error *err);
+int tool_pmu__for_each_event_cb(struct perf_pmu *pmu, void *state, pmu_event_callback cb);
+
+bool perf_pmu__is_tool(const struct perf_pmu *pmu);
+
+
+bool evsel__is_tool(const struct evsel *evsel);
+enum perf_tool_event evsel__tool_event(const struct evsel *evsel);
+const char *evsel__tool_pmu_event_name(const struct evsel *evsel);
+int evsel__tool_pmu_prepare_open(struct evsel *evsel,
+				 struct perf_cpu_map *cpus,
+				 int nthreads);
+int evsel__tool_pmu_open(struct evsel *evsel,
+			 struct perf_thread_map *threads,
+			 int start_cpu_map_idx, int end_cpu_map_idx);
+int evsel__read_tool(struct evsel *evsel, int cpu_map_idx, int thread);
+
+struct perf_pmu *perf_pmus__tool_pmu(void);
+
+#endif /* __TOOL_PMU_H */

From 0709a82c10bb98d0426dd289a6b8c143f61a8786 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 1 Oct 2024 20:20:08 -0700
Subject: [PATCH 0275/1530] perf tool_pmu: Rename enum perf_tool_event to
 tool_pmu_event

To better reflect the events listed are from the tool PMU. Rename the
enum values from PERF_TOOL_* to TOOL_PMU__EVENT_*.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241002032016.333748-6-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-stat.c     |  6 ++---
 tools/perf/util/evsel.c       |  4 ++--
 tools/perf/util/metricgroup.c | 12 +++++-----
 tools/perf/util/pmu.c         |  2 +-
 tools/perf/util/stat-shadow.c | 10 ++++----
 tools/perf/util/tool_pmu.c    | 44 +++++++++++++++++------------------
 tools/perf/util/tool_pmu.h    | 22 +++++++++---------
 7 files changed, 50 insertions(+), 50 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index bc12975efad56..b5e18853982cd 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -295,14 +295,14 @@ static int read_single_counter(struct evsel *counter, int cpu_map_idx, int threa
 	 * terminates. Use the wait4 values in that case.
 	 */
 	if (err && cpu_map_idx == 0 &&
-	    (evsel__tool_event(counter) == PERF_TOOL_USER_TIME ||
-	     evsel__tool_event(counter) == PERF_TOOL_SYSTEM_TIME)) {
+	    (evsel__tool_event(counter) == TOOL_PMU__EVENT_USER_TIME ||
+	     evsel__tool_event(counter) == TOOL_PMU__EVENT_SYSTEM_TIME)) {
 		u64 val, *start_time;
 		struct perf_counts_values *count =
 			perf_counts(counter->counts, cpu_map_idx, thread);
 
 		start_time = xyarray__entry(counter->start_times, cpu_map_idx, thread);
-		if (evsel__tool_event(counter) == PERF_TOOL_USER_TIME)
+		if (evsel__tool_event(counter) == TOOL_PMU__EVENT_USER_TIME)
 			val = ru_stats.ru_utime_usec_stat.mean;
 		else
 			val = ru_stats.ru_stime_usec_stat.mean;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 14a17f768f426..320310e333e64 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1476,8 +1476,8 @@ void evsel__exit(struct evsel *evsel)
 	evsel->per_pkg_mask = NULL;
 	zfree(&evsel->metric_events);
 	perf_evsel__object.fini(evsel);
-	if (evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME ||
-	    evsel__tool_event(evsel) == PERF_TOOL_USER_TIME)
+	if (evsel__tool_event(evsel) == TOOL_PMU__EVENT_SYSTEM_TIME ||
+	    evsel__tool_event(evsel) == TOOL_PMU__EVENT_USER_TIME)
 		xyarray__delete(evsel->start_times);
 }
 
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 827bab455d5bc..1250bf5050b09 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -674,20 +674,20 @@ static int metricgroup__build_event_string(struct strbuf *events,
 	struct hashmap_entry *cur;
 	size_t bkt;
 	bool no_group = true, has_tool_events = false;
-	bool tool_events[PERF_TOOL_MAX] = {false};
+	bool tool_events[TOOL_PMU__EVENT_MAX] = {false};
 	int ret = 0;
 
 #define RETURN_IF_NON_ZERO(x) do { if (x) return x; } while (0)
 
 	hashmap__for_each_entry(ctx->ids, cur, bkt) {
 		const char *sep, *rsep, *id = cur->pkey;
-		enum perf_tool_event ev;
+		enum tool_pmu_event ev;
 
 		pr_debug("found event %s\n", id);
 
 		/* Always move tool events outside of the group. */
 		ev = perf_tool_event__from_str(id);
-		if (ev != PERF_TOOL_NONE) {
+		if (ev != TOOL_PMU__EVENT_NONE) {
 			has_tool_events = true;
 			tool_events[ev] = true;
 			continue;
@@ -1375,7 +1375,7 @@ static void metricgroup__free_metrics(struct list_head *metric_list)
  *               to true if tool event is found.
  */
 static void find_tool_events(const struct list_head *metric_list,
-			     bool tool_events[PERF_TOOL_MAX])
+			     bool tool_events[TOOL_PMU__EVENT_MAX])
 {
 	struct metric *m;
 
@@ -1447,7 +1447,7 @@ static int build_combined_expr_ctx(const struct list_head *metric_list,
  */
 static int parse_ids(bool metric_no_merge, bool fake_pmu,
 		     struct expr_parse_ctx *ids, const char *modifier,
-		     bool group_events, const bool tool_events[PERF_TOOL_MAX],
+		     bool group_events, const bool tool_events[TOOL_PMU__EVENT_MAX],
 		     struct evlist **out_evlist)
 {
 	struct parse_events_error parse_error;
@@ -1536,7 +1536,7 @@ static int parse_groups(struct evlist *perf_evlist,
 	struct evlist *combined_evlist = NULL;
 	LIST_HEAD(metric_list);
 	struct metric *m;
-	bool tool_events[PERF_TOOL_MAX] = {false};
+	bool tool_events[TOOL_PMU__EVENT_MAX] = {false};
 	bool is_default = !strcmp(str, "Default");
 	int ret;
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 762942853351d..77e848ac5841b 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1836,7 +1836,7 @@ bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name)
 	if (!name)
 		return false;
 	if (perf_pmu__is_tool(pmu))
-		return perf_tool_event__from_str(name) != PERF_TOOL_NONE;
+		return perf_tool_event__from_str(name) != TOOL_PMU__EVENT_NONE;
 	if (perf_pmu__find_alias(pmu, name, /*load=*/ true) != NULL)
 		return true;
 	if (pmu->cpu_aliases_added || !pmu->events_table)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 50f347217d84c..b54afb56e3d67 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -382,22 +382,22 @@ static int prepare_metric(const struct metric_expr *mexp,
 			double scale;
 
 			switch (evsel__tool_event(metric_events[i])) {
-			case PERF_TOOL_DURATION_TIME:
+			case TOOL_PMU__EVENT_DURATION_TIME:
 				stats = &walltime_nsecs_stats;
 				scale = 1e-9;
 				break;
-			case PERF_TOOL_USER_TIME:
+			case TOOL_PMU__EVENT_USER_TIME:
 				stats = &ru_stats.ru_utime_usec_stat;
 				scale = 1e-6;
 				break;
-			case PERF_TOOL_SYSTEM_TIME:
+			case TOOL_PMU__EVENT_SYSTEM_TIME:
 				stats = &ru_stats.ru_stime_usec_stat;
 				scale = 1e-6;
 				break;
-			case PERF_TOOL_NONE:
+			case TOOL_PMU__EVENT_NONE:
 				pr_err("Invalid tool event 'none'");
 				abort();
-			case PERF_TOOL_MAX:
+			case TOOL_PMU__EVENT_MAX:
 				pr_err("Invalid tool event 'max'");
 				abort();
 			default:
diff --git a/tools/perf/util/tool_pmu.c b/tools/perf/util/tool_pmu.c
index f41fed39d70d8..ae0ca023f5ed5 100644
--- a/tools/perf/util/tool_pmu.c
+++ b/tools/perf/util/tool_pmu.c
@@ -12,7 +12,7 @@
 #include <fcntl.h>
 #include <strings.h>
 
-static const char *const tool_pmu__event_names[PERF_TOOL_MAX] = {
+static const char *const tool_pmu__event_names[TOOL_PMU__EVENT_MAX] = {
 	NULL,
 	"duration_time",
 	"user_time",
@@ -20,15 +20,15 @@ static const char *const tool_pmu__event_names[PERF_TOOL_MAX] = {
 };
 
 
-const char *perf_tool_event__to_str(enum perf_tool_event ev)
+const char *perf_tool_event__to_str(enum tool_pmu_event ev)
 {
-	if (ev > PERF_TOOL_NONE && ev < PERF_TOOL_MAX)
+	if (ev > TOOL_PMU__EVENT_NONE && ev < TOOL_PMU__EVENT_MAX)
 		return tool_pmu__event_names[ev];
 
 	return NULL;
 }
 
-enum perf_tool_event perf_tool_event__from_str(const char *str)
+enum tool_pmu_event perf_tool_event__from_str(const char *str)
 {
 	int i;
 
@@ -36,7 +36,7 @@ enum perf_tool_event perf_tool_event__from_str(const char *str)
 		if (!strcasecmp(str, tool_pmu__event_names[i]))
 			return i;
 	}
-	return PERF_TOOL_NONE;
+	return TOOL_PMU__EVENT_NONE;
 }
 
 static int tool_pmu__config_term(struct perf_event_attr *attr,
@@ -44,9 +44,9 @@ static int tool_pmu__config_term(struct perf_event_attr *attr,
 				 struct parse_events_error *err)
 {
 	if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER) {
-		enum perf_tool_event ev = perf_tool_event__from_str(term->config);
+		enum tool_pmu_event ev = perf_tool_event__from_str(term->config);
 
-		if (ev == PERF_TOOL_NONE)
+		if (ev == TOOL_PMU__EVENT_NONE)
 			goto err_out;
 
 		attr->config = ev;
@@ -120,12 +120,12 @@ bool evsel__is_tool(const struct evsel *evsel)
 	return perf_pmu__is_tool(evsel->pmu);
 }
 
-enum perf_tool_event evsel__tool_event(const struct evsel *evsel)
+enum tool_pmu_event evsel__tool_event(const struct evsel *evsel)
 {
 	if (!evsel__is_tool(evsel))
-		return PERF_TOOL_NONE;
+		return TOOL_PMU__EVENT_NONE;
 
-	return (enum perf_tool_event)evsel->core.attr.config;
+	return (enum tool_pmu_event)evsel->core.attr.config;
 }
 
 const char *evsel__tool_pmu_event_name(const struct evsel *evsel)
@@ -229,8 +229,8 @@ int evsel__tool_pmu_prepare_open(struct evsel *evsel,
 				 struct perf_cpu_map *cpus,
 				 int nthreads)
 {
-	if ((evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME ||
-	     evsel__tool_event(evsel) == PERF_TOOL_USER_TIME) &&
+	if ((evsel__tool_event(evsel) == TOOL_PMU__EVENT_SYSTEM_TIME ||
+	     evsel__tool_event(evsel) == TOOL_PMU__EVENT_USER_TIME) &&
 	    !evsel->start_times) {
 		evsel->start_times = xyarray__new(perf_cpu_map__nr(cpus),
 						  nthreads,
@@ -247,10 +247,10 @@ int evsel__tool_pmu_open(struct evsel *evsel,
 			 struct perf_thread_map *threads,
 			 int start_cpu_map_idx, int end_cpu_map_idx)
 {
-	enum perf_tool_event ev = evsel__tool_event(evsel);
+	enum tool_pmu_event ev = evsel__tool_event(evsel);
 	int pid = -1, idx = 0, thread = 0, nthreads, err = 0, old_errno;
 
-	if (ev == PERF_TOOL_DURATION_TIME) {
+	if (ev == TOOL_PMU__EVENT_DURATION_TIME) {
 		if (evsel->core.attr.sample_period) /* no sampling */
 			return -EINVAL;
 		evsel->start_time = rdclock();
@@ -269,8 +269,8 @@ int evsel__tool_pmu_open(struct evsel *evsel,
 			if (!evsel->cgrp && !evsel->core.system_wide)
 				pid = perf_thread_map__pid(threads, thread);
 
-			if (ev == PERF_TOOL_USER_TIME || ev == PERF_TOOL_SYSTEM_TIME) {
-				bool system = ev == PERF_TOOL_SYSTEM_TIME;
+			if (ev == TOOL_PMU__EVENT_USER_TIME || ev == TOOL_PMU__EVENT_SYSTEM_TIME) {
+				bool system = ev == TOOL_PMU__EVENT_SYSTEM_TIME;
 				__u64 *start_time = NULL;
 				int fd;
 
@@ -338,7 +338,7 @@ int evsel__read_tool(struct evsel *evsel, int cpu_map_idx, int thread)
 	count = perf_counts(evsel->counts, cpu_map_idx, thread);
 
 	switch (evsel__tool_event(evsel)) {
-	case PERF_TOOL_DURATION_TIME:
+	case TOOL_PMU__EVENT_DURATION_TIME:
 		/*
 		 * Pretend duration_time is only on the first CPU and thread, or
 		 * else aggregation will scale duration_time by the number of
@@ -350,9 +350,9 @@ int evsel__read_tool(struct evsel *evsel, int cpu_map_idx, int thread)
 		else
 			cur_time = *start_time;
 		break;
-	case PERF_TOOL_USER_TIME:
-	case PERF_TOOL_SYSTEM_TIME: {
-		bool system = evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME;
+	case TOOL_PMU__EVENT_USER_TIME:
+	case TOOL_PMU__EVENT_SYSTEM_TIME: {
+		bool system = evsel__tool_event(evsel) == TOOL_PMU__EVENT_SYSTEM_TIME;
 
 		start_time = xyarray__entry(evsel->start_times, cpu_map_idx, thread);
 		fd = FD(evsel, cpu_map_idx, thread);
@@ -377,8 +377,8 @@ int evsel__read_tool(struct evsel *evsel, int cpu_map_idx, int thread)
 		adjust = true;
 		break;
 	}
-	case PERF_TOOL_NONE:
-	case PERF_TOOL_MAX:
+	case TOOL_PMU__EVENT_NONE:
+	case TOOL_PMU__EVENT_MAX:
 	default:
 		err = -EINVAL;
 	}
diff --git a/tools/perf/util/tool_pmu.h b/tools/perf/util/tool_pmu.h
index 05a4052c8b9d8..b27a26133927b 100644
--- a/tools/perf/util/tool_pmu.h
+++ b/tools/perf/util/tool_pmu.h
@@ -8,25 +8,25 @@ struct evsel;
 struct perf_thread_map;
 struct print_callbacks;
 
-enum perf_tool_event {
-	PERF_TOOL_NONE = 0,
-	PERF_TOOL_DURATION_TIME = 1,
-	PERF_TOOL_USER_TIME = 2,
-	PERF_TOOL_SYSTEM_TIME = 3,
+enum tool_pmu_event {
+	TOOL_PMU__EVENT_NONE = 0,
+	TOOL_PMU__EVENT_DURATION_TIME = 1,
+	TOOL_PMU__EVENT_USER_TIME = 2,
+	TOOL_PMU__EVENT_SYSTEM_TIME = 3,
 
-	PERF_TOOL_MAX,
+	TOOL_PMU__EVENT_MAX,
 };
 
 #define perf_tool_event__for_each_event(ev)				\
-	for ((ev) = PERF_TOOL_DURATION_TIME; (ev) < PERF_TOOL_MAX; ev++)
+	for ((ev) = TOOL_PMU__EVENT_DURATION_TIME; (ev) < TOOL_PMU__EVENT_MAX; ev++)
 
 static inline size_t tool_pmu__num_events(void)
 {
-	return PERF_TOOL_MAX - 1;
+	return TOOL_PMU__EVENT_MAX - 1;
 }
 
-const char *perf_tool_event__to_str(enum perf_tool_event ev);
-enum perf_tool_event perf_tool_event__from_str(const char *str);
+const char *perf_tool_event__to_str(enum tool_pmu_event ev);
+enum tool_pmu_event perf_tool_event__from_str(const char *str);
 int tool_pmu__config_terms(struct perf_event_attr *attr,
 			   struct parse_events_terms *terms,
 			   struct parse_events_error *err);
@@ -36,7 +36,7 @@ bool perf_pmu__is_tool(const struct perf_pmu *pmu);
 
 
 bool evsel__is_tool(const struct evsel *evsel);
-enum perf_tool_event evsel__tool_event(const struct evsel *evsel);
+enum tool_pmu_event evsel__tool_event(const struct evsel *evsel);
 const char *evsel__tool_pmu_event_name(const struct evsel *evsel);
 int evsel__tool_pmu_prepare_open(struct evsel *evsel,
 				 struct perf_cpu_map *cpus,

From b8f1a1b0680c055bbe9f99e82e2e5b474621a1d6 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 1 Oct 2024 20:20:09 -0700
Subject: [PATCH 0276/1530] perf tool_pmu: Rename perf_tool_event__* to
 tool_pmu__*

Now the events are associated with the tool PMU, rename the functions
to reflect this.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241002032016.333748-7-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/evsel.c       |  2 +-
 tools/perf/util/metricgroup.c | 22 +++++++++++-----------
 tools/perf/util/pmu.c         |  4 ++--
 tools/perf/util/tool_pmu.c    | 16 ++++++++--------
 tools/perf/util/tool_pmu.h    |  8 ++++----
 5 files changed, 26 insertions(+), 26 deletions(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 320310e333e64..ed0d4d20e3576 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1678,7 +1678,7 @@ bool __evsel__match(const struct evsel *evsel, u32 type, u64 config)
 int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread)
 {
 	if (evsel__is_tool(evsel))
-		return evsel__read_tool(evsel, cpu_map_idx, thread);
+		return evsel__tool_pmu_read(evsel, cpu_map_idx, thread);
 
 	if (evsel__is_retire_lat(evsel))
 		return evsel__read_retire_lat(evsel, cpu_map_idx, thread);
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 1250bf5050b09..46920ebadfd1b 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -686,7 +686,7 @@ static int metricgroup__build_event_string(struct strbuf *events,
 		pr_debug("found event %s\n", id);
 
 		/* Always move tool events outside of the group. */
-		ev = perf_tool_event__from_str(id);
+		ev = tool_pmu__str_to_event(id);
 		if (ev != TOOL_PMU__EVENT_NONE) {
 			has_tool_events = true;
 			tool_events[ev] = true;
@@ -755,14 +755,14 @@ static int metricgroup__build_event_string(struct strbuf *events,
 	if (has_tool_events) {
 		int i;
 
-		perf_tool_event__for_each_event(i) {
+		tool_pmu__for_each_event(i) {
 			if (tool_events[i]) {
 				if (!no_group) {
 					ret = strbuf_addch(events, ',');
 					RETURN_IF_NON_ZERO(ret);
 				}
 				no_group = false;
-				ret = strbuf_addstr(events, perf_tool_event__to_str(i));
+				ret = strbuf_addstr(events, tool_pmu__event_to_str(i));
 				RETURN_IF_NON_ZERO(ret);
 			}
 		}
@@ -1148,14 +1148,14 @@ static int metric_list_cmp(void *priv __maybe_unused, const struct list_head *l,
 	int i, left_count, right_count;
 
 	left_count = hashmap__size(left->pctx->ids);
-	perf_tool_event__for_each_event(i) {
-		if (!expr__get_id(left->pctx, perf_tool_event__to_str(i), &data))
+	tool_pmu__for_each_event(i) {
+		if (!expr__get_id(left->pctx, tool_pmu__event_to_str(i), &data))
 			left_count--;
 	}
 
 	right_count = hashmap__size(right->pctx->ids);
-	perf_tool_event__for_each_event(i) {
-		if (!expr__get_id(right->pctx, perf_tool_event__to_str(i), &data))
+	tool_pmu__for_each_event(i) {
+		if (!expr__get_id(right->pctx, tool_pmu__event_to_str(i), &data))
 			right_count--;
 	}
 
@@ -1382,11 +1382,11 @@ static void find_tool_events(const struct list_head *metric_list,
 	list_for_each_entry(m, metric_list, nd) {
 		int i;
 
-		perf_tool_event__for_each_event(i) {
+		tool_pmu__for_each_event(i) {
 			struct expr_id_data *data;
 
 			if (!tool_events[i] &&
-			    !expr__get_id(m->pctx, perf_tool_event__to_str(i), &data))
+			    !expr__get_id(m->pctx, tool_pmu__event_to_str(i), &data))
 				tool_events[i] = true;
 		}
 	}
@@ -1472,9 +1472,9 @@ static int parse_ids(bool metric_no_merge, bool fake_pmu,
 		 *    event1 if #smt_on else 0
 		 * Add a tool event to avoid a parse error on an empty string.
 		 */
-		perf_tool_event__for_each_event(i) {
+		tool_pmu__for_each_event(i) {
 			if (tool_events[i]) {
-				char *tmp = strdup(perf_tool_event__to_str(i));
+				char *tmp = strdup(tool_pmu__event_to_str(i));
 
 				if (!tmp)
 					return -ENOMEM;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 77e848ac5841b..d3c7a1c4254c1 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1836,7 +1836,7 @@ bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name)
 	if (!name)
 		return false;
 	if (perf_pmu__is_tool(pmu))
-		return perf_tool_event__from_str(name) != TOOL_PMU__EVENT_NONE;
+		return tool_pmu__str_to_event(name) != TOOL_PMU__EVENT_NONE;
 	if (perf_pmu__find_alias(pmu, name, /*load=*/ true) != NULL)
 		return true;
 	if (pmu->cpu_aliases_added || !pmu->events_table)
@@ -2331,7 +2331,7 @@ const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config)
 		return NULL;
 
 	if (perf_pmu__is_tool(pmu))
-		return perf_tool_event__to_str(config);
+		return tool_pmu__event_to_str(config);
 
 	pmu_aliases_parse(pmu);
 	pmu_add_cpu_aliases(pmu);
diff --git a/tools/perf/util/tool_pmu.c b/tools/perf/util/tool_pmu.c
index ae0ca023f5ed5..2a1524dc2e31b 100644
--- a/tools/perf/util/tool_pmu.c
+++ b/tools/perf/util/tool_pmu.c
@@ -20,7 +20,7 @@ static const char *const tool_pmu__event_names[TOOL_PMU__EVENT_MAX] = {
 };
 
 
-const char *perf_tool_event__to_str(enum tool_pmu_event ev)
+const char *tool_pmu__event_to_str(enum tool_pmu_event ev)
 {
 	if (ev > TOOL_PMU__EVENT_NONE && ev < TOOL_PMU__EVENT_MAX)
 		return tool_pmu__event_names[ev];
@@ -28,11 +28,11 @@ const char *perf_tool_event__to_str(enum tool_pmu_event ev)
 	return NULL;
 }
 
-enum tool_pmu_event perf_tool_event__from_str(const char *str)
+enum tool_pmu_event tool_pmu__str_to_event(const char *str)
 {
 	int i;
 
-	perf_tool_event__for_each_event(i) {
+	tool_pmu__for_each_event(i) {
 		if (!strcasecmp(str, tool_pmu__event_names[i]))
 			return i;
 	}
@@ -44,7 +44,7 @@ static int tool_pmu__config_term(struct perf_event_attr *attr,
 				 struct parse_events_error *err)
 {
 	if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER) {
-		enum tool_pmu_event ev = perf_tool_event__from_str(term->config);
+		enum tool_pmu_event ev = tool_pmu__str_to_event(term->config);
 
 		if (ev == TOOL_PMU__EVENT_NONE)
 			goto err_out;
@@ -91,10 +91,10 @@ int tool_pmu__for_each_event_cb(struct perf_pmu *pmu, void *state, pmu_event_cal
 	};
 	int i;
 
-	perf_tool_event__for_each_event(i) {
+	tool_pmu__for_each_event(i) {
 		int ret;
 
-		info.name = perf_tool_event__to_str(i);
+		info.name = tool_pmu__event_to_str(i);
 		info.alias = NULL;
 		info.scale_unit = NULL;
 		info.desc = NULL;
@@ -130,7 +130,7 @@ enum tool_pmu_event evsel__tool_event(const struct evsel *evsel)
 
 const char *evsel__tool_pmu_event_name(const struct evsel *evsel)
 {
-	return perf_tool_event__to_str(evsel->core.attr.config);
+	return tool_pmu__event_to_str(evsel->core.attr.config);
 }
 
 static bool read_until_char(struct io *io, char e)
@@ -328,7 +328,7 @@ int evsel__tool_pmu_open(struct evsel *evsel,
 	return err;
 }
 
-int evsel__read_tool(struct evsel *evsel, int cpu_map_idx, int thread)
+int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread)
 {
 	__u64 *start_time, cur_time, delta_start;
 	int fd, err = 0;
diff --git a/tools/perf/util/tool_pmu.h b/tools/perf/util/tool_pmu.h
index b27a26133927b..b156645206c46 100644
--- a/tools/perf/util/tool_pmu.h
+++ b/tools/perf/util/tool_pmu.h
@@ -17,7 +17,7 @@ enum tool_pmu_event {
 	TOOL_PMU__EVENT_MAX,
 };
 
-#define perf_tool_event__for_each_event(ev)				\
+#define tool_pmu__for_each_event(ev)					\
 	for ((ev) = TOOL_PMU__EVENT_DURATION_TIME; (ev) < TOOL_PMU__EVENT_MAX; ev++)
 
 static inline size_t tool_pmu__num_events(void)
@@ -25,8 +25,8 @@ static inline size_t tool_pmu__num_events(void)
 	return TOOL_PMU__EVENT_MAX - 1;
 }
 
-const char *perf_tool_event__to_str(enum tool_pmu_event ev);
-enum tool_pmu_event perf_tool_event__from_str(const char *str);
+const char *tool_pmu__event_to_str(enum tool_pmu_event ev);
+enum tool_pmu_event tool_pmu__str_to_event(const char *str);
 int tool_pmu__config_terms(struct perf_event_attr *attr,
 			   struct parse_events_terms *terms,
 			   struct parse_events_error *err);
@@ -44,7 +44,7 @@ int evsel__tool_pmu_prepare_open(struct evsel *evsel,
 int evsel__tool_pmu_open(struct evsel *evsel,
 			 struct perf_thread_map *threads,
 			 int start_cpu_map_idx, int end_cpu_map_idx);
-int evsel__read_tool(struct evsel *evsel, int cpu_map_idx, int thread);
+int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread);
 
 struct perf_pmu *perf_pmus__tool_pmu(void);
 

From 069057239a676a82cce9330a81994129179dc817 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 1 Oct 2024 20:20:10 -0700
Subject: [PATCH 0277/1530] perf tool_pmu: Move expr literals to tool_pmu

Add the expr literals like "#smt_on" as tool events, this allows stat
events to give the values. On my laptop with hyperthreading enabled:

```
$ perf stat -e "has_pmem,num_cores,num_cpus,num_cpus_online,num_dies,num_packages,smt_on,system_tsc_freq" true

 Performance counter stats for 'true':

                 0      has_pmem
                 8      num_cores
                16      num_cpus
                16      num_cpus_online
                 1      num_dies
                 1      num_packages
                 1      smt_on
     2,496,000,000      system_tsc_freq

       0.001113637 seconds time elapsed

       0.001218000 seconds user
       0.000000000 seconds sys
```

And with hyperthreading disabled:
```
$ perf stat -e "has_pmem,num_cores,num_cpus,num_cpus_online,num_dies,num_packages,smt_on,system_tsc_freq" true

 Performance counter stats for 'true':

                 0      has_pmem
                 8      num_cores
                16      num_cpus
                 8      num_cpus_online
                 1      num_dies
                 1      num_packages
                 0      smt_on
     2,496,000,000      system_tsc_freq

       0.000802115 seconds time elapsed

       0.000000000 seconds user
       0.000806000 seconds sys
```

As zero matters for these values, in stat-display
should_skip_zero_counter only skip the zero value if it is not the
first aggregation index.

The tool event implementations are used in expr but not evaluated as
events for simplicity. Also core_wide isn't made a tool event as it
requires command line parameters.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241002032016.333748-8-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/arm64/util/pmu.c |   5 +-
 tools/perf/arch/x86/util/tsc.c   |  18 ++--
 tools/perf/util/expr.c           |  93 +++-----------------
 tools/perf/util/pmu.c            |   5 --
 tools/perf/util/pmu.h            |   1 -
 tools/perf/util/stat-display.c   |   8 +-
 tools/perf/util/stat-shadow.c    |  11 ++-
 tools/perf/util/tool_pmu.c       | 146 ++++++++++++++++++++++++++++++-
 tools/perf/util/tool_pmu.h       |  19 +++-
 tools/perf/util/tsc.h            |   2 +-
 10 files changed, 201 insertions(+), 107 deletions(-)

diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c
index 2a4eab2d160ee..a0964b191fcb9 100644
--- a/tools/perf/arch/arm64/util/pmu.c
+++ b/tools/perf/arch/arm64/util/pmu.c
@@ -5,6 +5,7 @@
 #include "../../../util/header.h"
 #include "../../../util/pmu.h"
 #include "../../../util/pmus.h"
+#include "../../../util/tool_pmu.h"
 #include <api/fs/fs.h>
 #include <math.h>
 
@@ -24,7 +25,7 @@ const struct pmu_metrics_table *pmu_metrics_table__find(void)
 	return NULL;
 }
 
-double perf_pmu__cpu_slots_per_cycle(void)
+u64 tool_pmu__cpu_slots_per_cycle(void)
 {
 	char path[PATH_MAX];
 	unsigned long long slots = 0;
@@ -41,5 +42,5 @@ double perf_pmu__cpu_slots_per_cycle(void)
 		filename__read_ull(path, &slots);
 	}
 
-	return slots ? (double)slots : NAN;
+	return slots;
 }
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index e2d6cfe21057b..3a439e4b12d28 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -24,9 +24,9 @@ u64 rdtsc(void)
  * ...
  * will return 3000000000.
  */
-static double cpuinfo_tsc_freq(void)
+static u64 cpuinfo_tsc_freq(void)
 {
-	double result = 0;
+	u64 result = 0;
 	FILE *cpuinfo;
 	char *line = NULL;
 	size_t len = 0;
@@ -34,20 +34,22 @@ static double cpuinfo_tsc_freq(void)
 	cpuinfo = fopen("/proc/cpuinfo", "r");
 	if (!cpuinfo) {
 		pr_err("Failed to read /proc/cpuinfo for TSC frequency\n");
-		return NAN;
+		return 0;
 	}
 	while (getline(&line, &len, cpuinfo) > 0) {
 		if (!strncmp(line, "model name", 10)) {
 			char *pos = strstr(line + 11, " @ ");
+			double float_result;
 
-			if (pos && sscanf(pos, " @ %lfGHz", &result) == 1) {
-				result *= 1000000000;
+			if (pos && sscanf(pos, " @ %lfGHz", &float_result) == 1) {
+				float_result *= 1000000000;
+				result = (u64)float_result;
 				goto out;
 			}
 		}
 	}
 out:
-	if (fpclassify(result) == FP_ZERO)
+	if (result == 0)
 		pr_err("Failed to find TSC frequency in /proc/cpuinfo\n");
 
 	free(line);
@@ -55,7 +57,7 @@ static double cpuinfo_tsc_freq(void)
 	return result;
 }
 
-double arch_get_tsc_freq(void)
+u64 arch_get_tsc_freq(void)
 {
 	unsigned int a, b, c, d, lvl;
 	static bool cached;
@@ -86,6 +88,6 @@ double arch_get_tsc_freq(void)
 		return tsc;
 	}
 
-	tsc = (double)c * (double)b / (double)a;
+	tsc = (u64)c * (u64)b / (u64)a;
 	return tsc;
 }
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index b2536a59c44e6..5e3732bc2fa52 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -5,25 +5,22 @@
 #include <stdlib.h>
 #include <string.h>
 #include "metricgroup.h"
-#include "cpumap.h"
-#include "cputopo.h"
 #include "debug.h"
 #include "evlist.h"
 #include "expr.h"
+#include "pmu.h"
+#include "smt.h"
+#include "tool_pmu.h"
 #include <util/expr-bison.h>
 #include <util/expr-flex.h>
 #include "util/hashmap.h"
 #include "util/header.h"
 #include "util/pmu.h"
-#include "smt.h"
-#include "tsc.h"
-#include <api/fs/fs.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <ctype.h>
 #include <math.h>
-#include "pmu.h"
 
 struct expr_id_data {
 	union {
@@ -393,90 +390,26 @@ double expr_id_data__source_count(const struct expr_id_data *data)
 	return data->val.source_count;
 }
 
-#if !defined(__i386__) && !defined(__x86_64__)
-double arch_get_tsc_freq(void)
-{
-	return 0.0;
-}
-#endif
-
-static double has_pmem(void)
-{
-	static bool has_pmem, cached;
-	const char *sysfs = sysfs__mountpoint();
-	char path[PATH_MAX];
-
-	if (!cached) {
-		snprintf(path, sizeof(path), "%s/firmware/acpi/tables/NFIT", sysfs);
-		has_pmem = access(path, F_OK) == 0;
-		cached = true;
-	}
-	return has_pmem ? 1.0 : 0.0;
-}
-
 double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx)
 {
-	const struct cpu_topology *topology;
 	double result = NAN;
+	enum tool_pmu_event ev = tool_pmu__str_to_event(literal + 1);
 
-	if (!strcmp("#num_cpus", literal)) {
-		result = cpu__max_present_cpu().cpu;
-		goto out;
-	}
-	if (!strcmp("#num_cpus_online", literal)) {
-		struct perf_cpu_map *online = cpu_map__online();
-
-		if (online)
-			result = perf_cpu_map__nr(online);
-		goto out;
-	}
+	if (ev != TOOL_PMU__EVENT_NONE) {
+		u64 count;
 
-	if (!strcasecmp("#system_tsc_freq", literal)) {
-		result = arch_get_tsc_freq();
-		goto out;
-	}
+		if (tool_pmu__read_event(ev, &count))
+			result = count;
+		else
+			pr_err("Failure to read '%s'", literal);
 
-	/*
-	 * Assume that topology strings are consistent, such as CPUs "0-1"
-	 * wouldn't be listed as "0,1", and so after deduplication the number of
-	 * these strings gives an indication of the number of packages, dies,
-	 * etc.
-	 */
-	if (!strcasecmp("#smt_on", literal)) {
-		result = smt_on() ? 1.0 : 0.0;
-		goto out;
-	}
-	if (!strcmp("#core_wide", literal)) {
+	} else if (!strcmp("#core_wide", literal)) {
 		result = core_wide(ctx->system_wide, ctx->user_requested_cpu_list)
 			? 1.0 : 0.0;
-		goto out;
-	}
-	if (!strcmp("#num_packages", literal)) {
-		topology = online_topology();
-		result = topology->package_cpus_lists;
-		goto out;
-	}
-	if (!strcmp("#num_dies", literal)) {
-		topology = online_topology();
-		result = topology->die_cpus_lists;
-		goto out;
-	}
-	if (!strcmp("#num_cores", literal)) {
-		topology = online_topology();
-		result = topology->core_cpus_lists;
-		goto out;
-	}
-	if (!strcmp("#slots", literal)) {
-		result = perf_pmu__cpu_slots_per_cycle();
-		goto out;
-	}
-	if (!strcmp("#has_pmem", literal)) {
-		result = has_pmem();
-		goto out;
+	} else {
+		pr_err("Unrecognized literal '%s'", literal);
 	}
 
-	pr_err("Unrecognized literal '%s'", literal);
-out:
 	pr_debug2("literal: %s = %f\n", literal, result);
 	return result;
 }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d3c7a1c4254c1..9228650a62d26 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -2254,11 +2254,6 @@ bool perf_pmu__match(const struct perf_pmu *pmu, const char *tok)
 		(need_fnmatch && !fnmatch(tok, name, 0));
 }
 
-double __weak perf_pmu__cpu_slots_per_cycle(void)
-{
-	return NAN;
-}
-
 int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size)
 {
 	const char *sysfs = sysfs__mountpoint();
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 36fced2bf0651..e400db9e9eb15 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -271,7 +271,6 @@ void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu);
 
 bool perf_pmu__match(const struct perf_pmu *pmu, const char *tok);
 
-double perf_pmu__cpu_slots_per_cycle(void);
 int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size);
 int perf_pmu__pathname_scnprintf(char *buf, size_t size,
 				 const char *pmu_name, const char *filename);
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index ca85270678690..ef0ca8cd802dd 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -987,8 +987,12 @@ static bool should_skip_zero_counter(struct perf_stat_config *config,
 	 * Many tool events are only gathered on the first index, skip other
 	 * zero values.
 	 */
-	if (evsel__is_tool(counter))
-		return true;
+	if (evsel__is_tool(counter)) {
+		struct aggr_cpu_id own_id =
+			config->aggr_get_id(config, (struct perf_cpu){ .cpu = 0 });
+
+		return !aggr_cpu_id__equal(id, &own_id);
+	}
 
 	/*
 	 * Skip value 0 when it's an uncore event and the given aggr id
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index b54afb56e3d67..6227de8480836 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -400,8 +400,17 @@ static int prepare_metric(const struct metric_expr *mexp,
 			case TOOL_PMU__EVENT_MAX:
 				pr_err("Invalid tool event 'max'");
 				abort();
+			case TOOL_PMU__EVENT_HAS_PMEM:
+			case TOOL_PMU__EVENT_NUM_CORES:
+			case TOOL_PMU__EVENT_NUM_CPUS:
+			case TOOL_PMU__EVENT_NUM_CPUS_ONLINE:
+			case TOOL_PMU__EVENT_NUM_DIES:
+			case TOOL_PMU__EVENT_NUM_PACKAGES:
+			case TOOL_PMU__EVENT_SLOTS:
+			case TOOL_PMU__EVENT_SMT_ON:
+			case TOOL_PMU__EVENT_SYSTEM_TSC_FREQ:
 			default:
-				pr_err("Unknown tool event '%s'", evsel__name(metric_events[i]));
+				pr_err("Unexpected tool event '%s'", evsel__name(metric_events[i]));
 				abort();
 			}
 			val = avg_stats(stats) * scale;
diff --git a/tools/perf/util/tool_pmu.c b/tools/perf/util/tool_pmu.c
index 2a1524dc2e31b..cfdc09dece1e5 100644
--- a/tools/perf/util/tool_pmu.c
+++ b/tools/perf/util/tool_pmu.c
@@ -1,11 +1,16 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include "cgroup.h"
 #include "counts.h"
+#include "cputopo.h"
 #include "evsel.h"
 #include "pmu.h"
 #include "print-events.h"
+#include "smt.h"
 #include "time-utils.h"
 #include "tool_pmu.h"
+#include "tsc.h"
+#include <api/fs/fs.h>
+#include <api/io.h>
 #include <api/io.h>
 #include <internal/threadmap.h>
 #include <perf/threadmap.h>
@@ -17,6 +22,15 @@ static const char *const tool_pmu__event_names[TOOL_PMU__EVENT_MAX] = {
 	"duration_time",
 	"user_time",
 	"system_time",
+	"has_pmem",
+	"num_cores",
+	"num_cpus",
+	"num_cpus_online",
+	"num_dies",
+	"num_packages",
+	"slots",
+	"smt_on",
+	"system_tsc_freq",
 };
 
 
@@ -33,8 +47,14 @@ enum tool_pmu_event tool_pmu__str_to_event(const char *str)
 	int i;
 
 	tool_pmu__for_each_event(i) {
-		if (!strcasecmp(str, tool_pmu__event_names[i]))
+		if (!strcasecmp(str, tool_pmu__event_names[i])) {
+#if !defined(__aarch64__)
+			/* The slots event should only appear on arm64. */
+			if (i == TOOL_PMU__EVENT_SLOTS)
+				return TOOL_PMU__EVENT_NONE;
+#endif
 			return i;
+		}
 	}
 	return TOOL_PMU__EVENT_NONE;
 }
@@ -250,6 +270,9 @@ int evsel__tool_pmu_open(struct evsel *evsel,
 	enum tool_pmu_event ev = evsel__tool_event(evsel);
 	int pid = -1, idx = 0, thread = 0, nthreads, err = 0, old_errno;
 
+	if (ev == TOOL_PMU__EVENT_NUM_CPUS)
+		return 0;
+
 	if (ev == TOOL_PMU__EVENT_DURATION_TIME) {
 		if (evsel->core.attr.sample_period) /* no sampling */
 			return -EINVAL;
@@ -328,16 +351,133 @@ int evsel__tool_pmu_open(struct evsel *evsel,
 	return err;
 }
 
+#if !defined(__i386__) && !defined(__x86_64__)
+u64 arch_get_tsc_freq(void)
+{
+	return 0;
+}
+#endif
+
+#if !defined(__aarch64__)
+u64 tool_pmu__cpu_slots_per_cycle(void)
+{
+	return 0;
+}
+#endif
+
+static bool has_pmem(void)
+{
+	static bool has_pmem, cached;
+	const char *sysfs = sysfs__mountpoint();
+	char path[PATH_MAX];
+
+	if (!cached) {
+		snprintf(path, sizeof(path), "%s/firmware/acpi/tables/NFIT", sysfs);
+		has_pmem = access(path, F_OK) == 0;
+		cached = true;
+	}
+	return has_pmem;
+}
+
+bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result)
+{
+	const struct cpu_topology *topology;
+
+	switch (ev) {
+	case TOOL_PMU__EVENT_HAS_PMEM:
+		*result = has_pmem() ? 1 : 0;
+		return true;
+
+	case TOOL_PMU__EVENT_NUM_CORES:
+		topology = online_topology();
+		*result = topology->core_cpus_lists;
+		return true;
+
+	case TOOL_PMU__EVENT_NUM_CPUS:
+		*result = cpu__max_present_cpu().cpu;
+		return true;
+
+	case TOOL_PMU__EVENT_NUM_CPUS_ONLINE: {
+		struct perf_cpu_map *online = cpu_map__online();
+
+		if (online) {
+			*result = perf_cpu_map__nr(online);
+			return true;
+		}
+		return false;
+	}
+	case TOOL_PMU__EVENT_NUM_DIES:
+		topology = online_topology();
+		*result = topology->die_cpus_lists;
+		return true;
+
+	case TOOL_PMU__EVENT_NUM_PACKAGES:
+		topology = online_topology();
+		*result = topology->package_cpus_lists;
+		return true;
+
+	case TOOL_PMU__EVENT_SLOTS:
+		*result = tool_pmu__cpu_slots_per_cycle();
+		return *result ? true : false;
+
+	case TOOL_PMU__EVENT_SMT_ON:
+		*result = smt_on() ? 1 : 0;
+		return true;
+
+	case TOOL_PMU__EVENT_SYSTEM_TSC_FREQ:
+		*result = arch_get_tsc_freq();
+		return true;
+
+	case TOOL_PMU__EVENT_NONE:
+	case TOOL_PMU__EVENT_DURATION_TIME:
+	case TOOL_PMU__EVENT_USER_TIME:
+	case TOOL_PMU__EVENT_SYSTEM_TIME:
+	case TOOL_PMU__EVENT_MAX:
+	default:
+		return false;
+	}
+}
+
 int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread)
 {
 	__u64 *start_time, cur_time, delta_start;
+	unsigned long val;
 	int fd, err = 0;
-	struct perf_counts_values *count;
+	struct perf_counts_values *count, *old_count = NULL;
 	bool adjust = false;
+	enum tool_pmu_event ev = evsel__tool_event(evsel);
 
 	count = perf_counts(evsel->counts, cpu_map_idx, thread);
 
-	switch (evsel__tool_event(evsel)) {
+	switch (ev) {
+	case TOOL_PMU__EVENT_HAS_PMEM:
+	case TOOL_PMU__EVENT_NUM_CORES:
+	case TOOL_PMU__EVENT_NUM_CPUS:
+	case TOOL_PMU__EVENT_NUM_CPUS_ONLINE:
+	case TOOL_PMU__EVENT_NUM_DIES:
+	case TOOL_PMU__EVENT_NUM_PACKAGES:
+	case TOOL_PMU__EVENT_SLOTS:
+	case TOOL_PMU__EVENT_SMT_ON:
+	case TOOL_PMU__EVENT_SYSTEM_TSC_FREQ:
+		if (evsel->prev_raw_counts)
+			old_count = perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
+		val = 0;
+		if (cpu_map_idx == 0 && thread == 0) {
+			if (!tool_pmu__read_event(ev, &val)) {
+				count->lost++;
+				val = 0;
+			}
+		}
+		if (old_count) {
+			count->val = old_count->val + val;
+			count->run = old_count->run + 1;
+			count->ena = old_count->ena + 1;
+		} else {
+			count->val = val;
+			count->run++;
+			count->ena++;
+		}
+		return 0;
 	case TOOL_PMU__EVENT_DURATION_TIME:
 		/*
 		 * Pretend duration_time is only on the first CPU and thread, or
diff --git a/tools/perf/util/tool_pmu.h b/tools/perf/util/tool_pmu.h
index b156645206c46..ecdf316525bbb 100644
--- a/tools/perf/util/tool_pmu.h
+++ b/tools/perf/util/tool_pmu.h
@@ -10,9 +10,18 @@ struct print_callbacks;
 
 enum tool_pmu_event {
 	TOOL_PMU__EVENT_NONE = 0,
-	TOOL_PMU__EVENT_DURATION_TIME = 1,
-	TOOL_PMU__EVENT_USER_TIME = 2,
-	TOOL_PMU__EVENT_SYSTEM_TIME = 3,
+	TOOL_PMU__EVENT_DURATION_TIME,
+	TOOL_PMU__EVENT_USER_TIME,
+	TOOL_PMU__EVENT_SYSTEM_TIME,
+	TOOL_PMU__EVENT_HAS_PMEM,
+	TOOL_PMU__EVENT_NUM_CORES,
+	TOOL_PMU__EVENT_NUM_CPUS,
+	TOOL_PMU__EVENT_NUM_CPUS_ONLINE,
+	TOOL_PMU__EVENT_NUM_DIES,
+	TOOL_PMU__EVENT_NUM_PACKAGES,
+	TOOL_PMU__EVENT_SLOTS,
+	TOOL_PMU__EVENT_SMT_ON,
+	TOOL_PMU__EVENT_SYSTEM_TSC_FREQ,
 
 	TOOL_PMU__EVENT_MAX,
 };
@@ -31,9 +40,11 @@ int tool_pmu__config_terms(struct perf_event_attr *attr,
 			   struct parse_events_terms *terms,
 			   struct parse_events_error *err);
 int tool_pmu__for_each_event_cb(struct perf_pmu *pmu, void *state, pmu_event_callback cb);
+bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result);
 
-bool perf_pmu__is_tool(const struct perf_pmu *pmu);
+u64 tool_pmu__cpu_slots_per_cycle(void);
 
+bool perf_pmu__is_tool(const struct perf_pmu *pmu);
 
 bool evsel__is_tool(const struct evsel *evsel);
 enum tool_pmu_event evsel__tool_event(const struct evsel *evsel);
diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h
index 88fd1c4c1cb8f..57ce8449647f7 100644
--- a/tools/perf/util/tsc.h
+++ b/tools/perf/util/tsc.h
@@ -25,7 +25,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
 u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
 u64 rdtsc(void);
-double arch_get_tsc_freq(void);
+u64 arch_get_tsc_freq(void);
 
 size_t perf_event__fprintf_time_conv(union perf_event *event, FILE *fp);
 

From c9b121b7fa5d99e87184d69d0852bf7f6a61179d Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 1 Oct 2024 20:20:11 -0700
Subject: [PATCH 0278/1530] perf jevents: Add tool event json under a common
 architecture

Introduce the notion of a common architecture/model that can be used
to find event tables for common PMUs like the tool PMU. By having tool
events be json standard PMU attribute configuration, descriptions,
etc. can be used and these routines are already optimized for things
like binary searching.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241002032016.333748-9-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../pmu-events/arch/common/common/tool.json   |  74 +++++++
 tools/perf/pmu-events/empty-pmu-events.c      | 208 +++++++++++-------
 tools/perf/pmu-events/jevents.py              |  16 +-
 3 files changed, 215 insertions(+), 83 deletions(-)
 create mode 100644 tools/perf/pmu-events/arch/common/common/tool.json

diff --git a/tools/perf/pmu-events/arch/common/common/tool.json b/tools/perf/pmu-events/arch/common/common/tool.json
new file mode 100644
index 0000000000000..12f2ef1813a63
--- /dev/null
+++ b/tools/perf/pmu-events/arch/common/common/tool.json
@@ -0,0 +1,74 @@
+[
+  {
+    "Unit": "tool",
+    "EventName": "duration_time",
+    "BriefDescription": "Wall clock interval time in nanoseconds",
+    "ConfigCode": "1"
+  },
+  {
+    "Unit": "tool",
+    "EventName": "user_time",
+    "BriefDescription": "User (non-kernel) time in nanoseconds",
+    "ConfigCode": "2"
+  },
+  {
+    "Unit": "tool",
+    "EventName": "system_time",
+    "BriefDescription": "System/kernel time in nanoseconds",
+    "ConfigCode": "3"
+  },
+  {
+    "Unit": "tool",
+    "EventName": "has_pmem",
+    "BriefDescription": "1 if persistent memory installed otherwise 0",
+    "ConfigCode": "4"
+  },
+  {
+    "Unit": "tool",
+    "EventName": "num_cores",
+    "BriefDescription": "Number of cores. A core consists of 1 or more thread, with each thread being associated with a logical Linux CPU",
+    "ConfigCode": "5"
+  },
+  {
+    "Unit": "tool",
+    "EventName": "num_cpus",
+    "BriefDescription": "Number of logical Linux CPUs. There may be multiple such CPUs on a core",
+    "ConfigCode": "6"
+  },
+  {
+    "Unit": "tool",
+    "EventName": "num_cpus_online",
+    "BriefDescription": "Number of online logical Linux CPUs. There may be multiple such CPUs on a core",
+    "ConfigCode": "7"
+  },
+  {
+    "Unit": "tool",
+    "EventName": "num_dies",
+    "BriefDescription": "Number of dies. Each die has 1 or more cores",
+    "ConfigCode": "8"
+  },
+  {
+    "Unit": "tool",
+    "EventName": "num_packages",
+    "BriefDescription": "Number of packages. Each package has 1 or more die",
+    "ConfigCode": "9"
+  },
+  {
+    "Unit": "tool",
+    "EventName": "slots",
+    "BriefDescription": "Number of functional units that in parallel can execute parts of an instruction",
+    "ConfigCode": "10"
+  },
+  {
+    "Unit": "tool",
+    "EventName": "smt_on",
+    "BriefDescription": "1 if simultaneous multithreading (aka hyperthreading) is enable otherwise 0",
+    "ConfigCode": "11"
+  },
+  {
+    "Unit": "tool",
+    "EventName": "system_tsc_freq",
+    "BriefDescription": "The amount a Time Stamp Counter (TSC) increases per second",
+    "ConfigCode": "12"
+  }
+]
diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index 873e9fb2041f0..2b7516946dedd 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -19,72 +19,109 @@ struct pmu_table_entry {
 };
 
 static const char *const big_c_string =
-/* offset=0 */ "default_core\000"
-/* offset=13 */ "bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000"
-/* offset=72 */ "bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000"
-/* offset=131 */ "l3_cache_rd\000cache\000L3 cache access, read\000event=0x40\000\00000\000Attributable Level 3 cache access, read\000"
-/* offset=226 */ "segment_reg_loads.any\000other\000Number of segment register loads\000event=6,period=200000,umask=0x80\000\00000\000\000"
-/* offset=325 */ "dispatch_blocked.any\000other\000Memory cluster signals to block micro-op dispatch for any reason\000event=9,period=200000,umask=0x20\000\00000\000\000"
-/* offset=455 */ "eist_trans\000other\000Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions\000event=0x3a,period=200000\000\00000\000\000"
-/* offset=570 */ "hisi_sccl,ddrc\000"
-/* offset=585 */ "uncore_hisi_ddrc.flux_wcmd\000uncore\000DDRC write commands\000event=2\000\00000\000DDRC write commands\000"
-/* offset=671 */ "uncore_cbox\000"
-/* offset=683 */ "unc_cbo_xsnp_response.miss_eviction\000uncore\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000event=0x22,umask=0x81\000\00000\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000"
-/* offset=914 */ "event-hyphen\000uncore\000UNC_CBO_HYPHEN\000event=0xe0\000\00000\000UNC_CBO_HYPHEN\000"
-/* offset=979 */ "event-two-hyph\000uncore\000UNC_CBO_TWO_HYPH\000event=0xc0\000\00000\000UNC_CBO_TWO_HYPH\000"
-/* offset=1050 */ "hisi_sccl,l3c\000"
-/* offset=1064 */ "uncore_hisi_l3c.rd_hit_cpipe\000uncore\000Total read hits\000event=7\000\00000\000Total read hits\000"
-/* offset=1144 */ "uncore_imc_free_running\000"
-/* offset=1168 */ "uncore_imc_free_running.cache_miss\000uncore\000Total cache misses\000event=0x12\000\00000\000Total cache misses\000"
-/* offset=1263 */ "uncore_imc\000"
-/* offset=1274 */ "uncore_imc.cache_hits\000uncore\000Total cache hits\000event=0x34\000\00000\000Total cache hits\000"
-/* offset=1352 */ "uncore_sys_ddr_pmu\000"
-/* offset=1371 */ "sys_ddr_pmu.write_cycles\000uncore\000ddr write-cycles event\000event=0x2b\000v8\00000\000\000"
-/* offset=1444 */ "uncore_sys_ccn_pmu\000"
-/* offset=1463 */ "sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000"
-/* offset=1537 */ "uncore_sys_cmn_pmu\000"
-/* offset=1556 */ "sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000"
-/* offset=1696 */ "CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000"
-/* offset=1718 */ "IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000"
-/* offset=1781 */ "Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000"
-/* offset=1947 */ "dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
-/* offset=2011 */ "icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
-/* offset=2078 */ "cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000"
-/* offset=2149 */ "DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000"
-/* offset=2243 */ "DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000"
-/* offset=2377 */ "DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000"
-/* offset=2441 */ "DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000"
-/* offset=2509 */ "DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000"
-/* offset=2579 */ "M1\000\000ipc + M2\000\000\000\000\000\000\000\00000"
-/* offset=2601 */ "M2\000\000ipc + M1\000\000\000\000\000\000\000\00000"
-/* offset=2623 */ "M3\000\0001 / M3\000\000\000\000\000\000\000\00000"
-/* offset=2643 */ "L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000"
+/* offset=0 */ "tool\000"
+/* offset=5 */ "duration_time\000tool\000Wall clock interval time in nanoseconds\000config=1\000\00000\000\000"
+/* offset=78 */ "user_time\000tool\000User (non-kernel) time in nanoseconds\000config=2\000\00000\000\000"
+/* offset=145 */ "system_time\000tool\000System/kernel time in nanoseconds\000config=3\000\00000\000\000"
+/* offset=210 */ "has_pmem\000tool\0001 if persistent memory installed otherwise 0\000config=4\000\00000\000\000"
+/* offset=283 */ "num_cores\000tool\000Number of cores. A core consists of 1 or more thread, with each thread being associated with a logical Linux CPU\000config=5\000\00000\000\000"
+/* offset=425 */ "num_cpus\000tool\000Number of logical Linux CPUs. There may be multiple such CPUs on a core\000config=6\000\00000\000\000"
+/* offset=525 */ "num_cpus_online\000tool\000Number of online logical Linux CPUs. There may be multiple such CPUs on a core\000config=7\000\00000\000\000"
+/* offset=639 */ "num_dies\000tool\000Number of dies. Each die has 1 or more cores\000config=8\000\00000\000\000"
+/* offset=712 */ "num_packages\000tool\000Number of packages. Each package has 1 or more die\000config=9\000\00000\000\000"
+/* offset=795 */ "slots\000tool\000Number of functional units that in parallel can execute parts of an instruction\000config=0xa\000\00000\000\000"
+/* offset=902 */ "smt_on\000tool\0001 if simultaneous multithreading (aka hyperthreading) is enable otherwise 0\000config=0xb\000\00000\000\000"
+/* offset=1006 */ "system_tsc_freq\000tool\000The amount a Time Stamp Counter (TSC) increases per second\000config=0xc\000\00000\000\000"
+/* offset=1102 */ "default_core\000"
+/* offset=1115 */ "bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000"
+/* offset=1174 */ "bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000"
+/* offset=1233 */ "l3_cache_rd\000cache\000L3 cache access, read\000event=0x40\000\00000\000Attributable Level 3 cache access, read\000"
+/* offset=1328 */ "segment_reg_loads.any\000other\000Number of segment register loads\000event=6,period=200000,umask=0x80\000\00000\000\000"
+/* offset=1427 */ "dispatch_blocked.any\000other\000Memory cluster signals to block micro-op dispatch for any reason\000event=9,period=200000,umask=0x20\000\00000\000\000"
+/* offset=1557 */ "eist_trans\000other\000Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions\000event=0x3a,period=200000\000\00000\000\000"
+/* offset=1672 */ "hisi_sccl,ddrc\000"
+/* offset=1687 */ "uncore_hisi_ddrc.flux_wcmd\000uncore\000DDRC write commands\000event=2\000\00000\000DDRC write commands\000"
+/* offset=1773 */ "uncore_cbox\000"
+/* offset=1785 */ "unc_cbo_xsnp_response.miss_eviction\000uncore\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000event=0x22,umask=0x81\000\00000\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000"
+/* offset=2016 */ "event-hyphen\000uncore\000UNC_CBO_HYPHEN\000event=0xe0\000\00000\000UNC_CBO_HYPHEN\000"
+/* offset=2081 */ "event-two-hyph\000uncore\000UNC_CBO_TWO_HYPH\000event=0xc0\000\00000\000UNC_CBO_TWO_HYPH\000"
+/* offset=2152 */ "hisi_sccl,l3c\000"
+/* offset=2166 */ "uncore_hisi_l3c.rd_hit_cpipe\000uncore\000Total read hits\000event=7\000\00000\000Total read hits\000"
+/* offset=2246 */ "uncore_imc_free_running\000"
+/* offset=2270 */ "uncore_imc_free_running.cache_miss\000uncore\000Total cache misses\000event=0x12\000\00000\000Total cache misses\000"
+/* offset=2365 */ "uncore_imc\000"
+/* offset=2376 */ "uncore_imc.cache_hits\000uncore\000Total cache hits\000event=0x34\000\00000\000Total cache hits\000"
+/* offset=2454 */ "uncore_sys_ddr_pmu\000"
+/* offset=2473 */ "sys_ddr_pmu.write_cycles\000uncore\000ddr write-cycles event\000event=0x2b\000v8\00000\000\000"
+/* offset=2546 */ "uncore_sys_ccn_pmu\000"
+/* offset=2565 */ "sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000"
+/* offset=2639 */ "uncore_sys_cmn_pmu\000"
+/* offset=2658 */ "sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000"
+/* offset=2798 */ "CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000"
+/* offset=2820 */ "IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000"
+/* offset=2883 */ "Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000"
+/* offset=3049 */ "dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
+/* offset=3113 */ "icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
+/* offset=3180 */ "cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000"
+/* offset=3251 */ "DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000"
+/* offset=3345 */ "DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000"
+/* offset=3479 */ "DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000"
+/* offset=3543 */ "DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000"
+/* offset=3611 */ "DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000"
+/* offset=3681 */ "M1\000\000ipc + M2\000\000\000\000\000\000\000\00000"
+/* offset=3703 */ "M2\000\000ipc + M1\000\000\000\000\000\000\000\00000"
+/* offset=3725 */ "M3\000\0001 / M3\000\000\000\000\000\000\000\00000"
+/* offset=3745 */ "L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000"
 ;
 
+static const struct compact_pmu_event pmu_events__common_tool[] = {
+{ 5 }, /* duration_time\000tool\000Wall clock interval time in nanoseconds\000config=1\000\00000\000\000 */
+{ 210 }, /* has_pmem\000tool\0001 if persistent memory installed otherwise 0\000config=4\000\00000\000\000 */
+{ 283 }, /* num_cores\000tool\000Number of cores. A core consists of 1 or more thread, with each thread being associated with a logical Linux CPU\000config=5\000\00000\000\000 */
+{ 425 }, /* num_cpus\000tool\000Number of logical Linux CPUs. There may be multiple such CPUs on a core\000config=6\000\00000\000\000 */
+{ 525 }, /* num_cpus_online\000tool\000Number of online logical Linux CPUs. There may be multiple such CPUs on a core\000config=7\000\00000\000\000 */
+{ 639 }, /* num_dies\000tool\000Number of dies. Each die has 1 or more cores\000config=8\000\00000\000\000 */
+{ 712 }, /* num_packages\000tool\000Number of packages. Each package has 1 or more die\000config=9\000\00000\000\000 */
+{ 795 }, /* slots\000tool\000Number of functional units that in parallel can execute parts of an instruction\000config=0xa\000\00000\000\000 */
+{ 902 }, /* smt_on\000tool\0001 if simultaneous multithreading (aka hyperthreading) is enable otherwise 0\000config=0xb\000\00000\000\000 */
+{ 145 }, /* system_time\000tool\000System/kernel time in nanoseconds\000config=3\000\00000\000\000 */
+{ 1006 }, /* system_tsc_freq\000tool\000The amount a Time Stamp Counter (TSC) increases per second\000config=0xc\000\00000\000\000 */
+{ 78 }, /* user_time\000tool\000User (non-kernel) time in nanoseconds\000config=2\000\00000\000\000 */
+
+};
+
+const struct pmu_table_entry pmu_events__common[] = {
+{
+     .entries = pmu_events__common_tool,
+     .num_entries = ARRAY_SIZE(pmu_events__common_tool),
+     .pmu_name = { 0 /* tool\000 */ },
+},
+};
+
 static const struct compact_pmu_event pmu_events__test_soc_cpu_default_core[] = {
-{ 13 }, /* bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000 */
-{ 72 }, /* bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000 */
-{ 325 }, /* dispatch_blocked.any\000other\000Memory cluster signals to block micro-op dispatch for any reason\000event=9,period=200000,umask=0x20\000\00000\000\000 */
-{ 455 }, /* eist_trans\000other\000Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions\000event=0x3a,period=200000\000\00000\000\000 */
-{ 131 }, /* l3_cache_rd\000cache\000L3 cache access, read\000event=0x40\000\00000\000Attributable Level 3 cache access, read\000 */
-{ 226 }, /* segment_reg_loads.any\000other\000Number of segment register loads\000event=6,period=200000,umask=0x80\000\00000\000\000 */
+{ 1115 }, /* bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000 */
+{ 1174 }, /* bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000 */
+{ 1427 }, /* dispatch_blocked.any\000other\000Memory cluster signals to block micro-op dispatch for any reason\000event=9,period=200000,umask=0x20\000\00000\000\000 */
+{ 1557 }, /* eist_trans\000other\000Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions\000event=0x3a,period=200000\000\00000\000\000 */
+{ 1233 }, /* l3_cache_rd\000cache\000L3 cache access, read\000event=0x40\000\00000\000Attributable Level 3 cache access, read\000 */
+{ 1328 }, /* segment_reg_loads.any\000other\000Number of segment register loads\000event=6,period=200000,umask=0x80\000\00000\000\000 */
 };
 static const struct compact_pmu_event pmu_events__test_soc_cpu_hisi_sccl_ddrc[] = {
-{ 585 }, /* uncore_hisi_ddrc.flux_wcmd\000uncore\000DDRC write commands\000event=2\000\00000\000DDRC write commands\000 */
+{ 1687 }, /* uncore_hisi_ddrc.flux_wcmd\000uncore\000DDRC write commands\000event=2\000\00000\000DDRC write commands\000 */
 };
 static const struct compact_pmu_event pmu_events__test_soc_cpu_hisi_sccl_l3c[] = {
-{ 1064 }, /* uncore_hisi_l3c.rd_hit_cpipe\000uncore\000Total read hits\000event=7\000\00000\000Total read hits\000 */
+{ 2166 }, /* uncore_hisi_l3c.rd_hit_cpipe\000uncore\000Total read hits\000event=7\000\00000\000Total read hits\000 */
 };
 static const struct compact_pmu_event pmu_events__test_soc_cpu_uncore_cbox[] = {
-{ 914 }, /* event-hyphen\000uncore\000UNC_CBO_HYPHEN\000event=0xe0\000\00000\000UNC_CBO_HYPHEN\000 */
-{ 979 }, /* event-two-hyph\000uncore\000UNC_CBO_TWO_HYPH\000event=0xc0\000\00000\000UNC_CBO_TWO_HYPH\000 */
-{ 683 }, /* unc_cbo_xsnp_response.miss_eviction\000uncore\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000event=0x22,umask=0x81\000\00000\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000 */
+{ 2016 }, /* event-hyphen\000uncore\000UNC_CBO_HYPHEN\000event=0xe0\000\00000\000UNC_CBO_HYPHEN\000 */
+{ 2081 }, /* event-two-hyph\000uncore\000UNC_CBO_TWO_HYPH\000event=0xc0\000\00000\000UNC_CBO_TWO_HYPH\000 */
+{ 1785 }, /* unc_cbo_xsnp_response.miss_eviction\000uncore\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000event=0x22,umask=0x81\000\00000\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000 */
 };
 static const struct compact_pmu_event pmu_events__test_soc_cpu_uncore_imc[] = {
-{ 1274 }, /* uncore_imc.cache_hits\000uncore\000Total cache hits\000event=0x34\000\00000\000Total cache hits\000 */
+{ 2376 }, /* uncore_imc.cache_hits\000uncore\000Total cache hits\000event=0x34\000\00000\000Total cache hits\000 */
 };
 static const struct compact_pmu_event pmu_events__test_soc_cpu_uncore_imc_free_running[] = {
-{ 1168 }, /* uncore_imc_free_running.cache_miss\000uncore\000Total cache misses\000event=0x12\000\00000\000Total cache misses\000 */
+{ 2270 }, /* uncore_imc_free_running.cache_miss\000uncore\000Total cache misses\000event=0x12\000\00000\000Total cache misses\000 */
 
 };
 
@@ -92,51 +129,51 @@ const struct pmu_table_entry pmu_events__test_soc_cpu[] = {
 {
      .entries = pmu_events__test_soc_cpu_default_core,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_default_core),
-     .pmu_name = { 0 /* default_core\000 */ },
+     .pmu_name = { 1102 /* default_core\000 */ },
 },
 {
      .entries = pmu_events__test_soc_cpu_hisi_sccl_ddrc,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_hisi_sccl_ddrc),
-     .pmu_name = { 570 /* hisi_sccl,ddrc\000 */ },
+     .pmu_name = { 1672 /* hisi_sccl,ddrc\000 */ },
 },
 {
      .entries = pmu_events__test_soc_cpu_hisi_sccl_l3c,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_hisi_sccl_l3c),
-     .pmu_name = { 1050 /* hisi_sccl,l3c\000 */ },
+     .pmu_name = { 2152 /* hisi_sccl,l3c\000 */ },
 },
 {
      .entries = pmu_events__test_soc_cpu_uncore_cbox,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_uncore_cbox),
-     .pmu_name = { 671 /* uncore_cbox\000 */ },
+     .pmu_name = { 1773 /* uncore_cbox\000 */ },
 },
 {
      .entries = pmu_events__test_soc_cpu_uncore_imc,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_uncore_imc),
-     .pmu_name = { 1263 /* uncore_imc\000 */ },
+     .pmu_name = { 2365 /* uncore_imc\000 */ },
 },
 {
      .entries = pmu_events__test_soc_cpu_uncore_imc_free_running,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_uncore_imc_free_running),
-     .pmu_name = { 1144 /* uncore_imc_free_running\000 */ },
+     .pmu_name = { 2246 /* uncore_imc_free_running\000 */ },
 },
 };
 
 static const struct compact_pmu_event pmu_metrics__test_soc_cpu_default_core[] = {
-{ 1696 }, /* CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000 */
-{ 2377 }, /* DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000 */
-{ 2149 }, /* DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000 */
-{ 2243 }, /* DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000 */
-{ 2441 }, /* DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
-{ 2509 }, /* DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
-{ 1781 }, /* Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000 */
-{ 1718 }, /* IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000 */
-{ 2643 }, /* L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000 */
-{ 2579 }, /* M1\000\000ipc + M2\000\000\000\000\000\000\000\00000 */
-{ 2601 }, /* M2\000\000ipc + M1\000\000\000\000\000\000\000\00000 */
-{ 2623 }, /* M3\000\0001 / M3\000\000\000\000\000\000\000\00000 */
-{ 2078 }, /* cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000 */
-{ 1947 }, /* dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
-{ 2011 }, /* icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
+{ 2798 }, /* CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000 */
+{ 3479 }, /* DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000 */
+{ 3251 }, /* DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000 */
+{ 3345 }, /* DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000 */
+{ 3543 }, /* DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
+{ 3611 }, /* DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
+{ 2883 }, /* Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000 */
+{ 2820 }, /* IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000 */
+{ 3745 }, /* L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000 */
+{ 3681 }, /* M1\000\000ipc + M2\000\000\000\000\000\000\000\00000 */
+{ 3703 }, /* M2\000\000ipc + M1\000\000\000\000\000\000\000\00000 */
+{ 3725 }, /* M3\000\0001 / M3\000\000\000\000\000\000\000\00000 */
+{ 3180 }, /* cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000 */
+{ 3049 }, /* dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
+{ 3113 }, /* icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
 
 };
 
@@ -144,18 +181,18 @@ const struct pmu_table_entry pmu_metrics__test_soc_cpu[] = {
 {
      .entries = pmu_metrics__test_soc_cpu_default_core,
      .num_entries = ARRAY_SIZE(pmu_metrics__test_soc_cpu_default_core),
-     .pmu_name = { 0 /* default_core\000 */ },
+     .pmu_name = { 1102 /* default_core\000 */ },
 },
 };
 
 static const struct compact_pmu_event pmu_events__test_soc_sys_uncore_sys_ccn_pmu[] = {
-{ 1463 }, /* sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000 */
+{ 2565 }, /* sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000 */
 };
 static const struct compact_pmu_event pmu_events__test_soc_sys_uncore_sys_cmn_pmu[] = {
-{ 1556 }, /* sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000 */
+{ 2658 }, /* sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000 */
 };
 static const struct compact_pmu_event pmu_events__test_soc_sys_uncore_sys_ddr_pmu[] = {
-{ 1371 }, /* sys_ddr_pmu.write_cycles\000uncore\000ddr write-cycles event\000event=0x2b\000v8\00000\000\000 */
+{ 2473 }, /* sys_ddr_pmu.write_cycles\000uncore\000ddr write-cycles event\000event=0x2b\000v8\00000\000\000 */
 
 };
 
@@ -163,17 +200,17 @@ const struct pmu_table_entry pmu_events__test_soc_sys[] = {
 {
      .entries = pmu_events__test_soc_sys_uncore_sys_ccn_pmu,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_sys_uncore_sys_ccn_pmu),
-     .pmu_name = { 1444 /* uncore_sys_ccn_pmu\000 */ },
+     .pmu_name = { 2546 /* uncore_sys_ccn_pmu\000 */ },
 },
 {
      .entries = pmu_events__test_soc_sys_uncore_sys_cmn_pmu,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_sys_uncore_sys_cmn_pmu),
-     .pmu_name = { 1537 /* uncore_sys_cmn_pmu\000 */ },
+     .pmu_name = { 2639 /* uncore_sys_cmn_pmu\000 */ },
 },
 {
      .entries = pmu_events__test_soc_sys_uncore_sys_ddr_pmu,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_sys_uncore_sys_ddr_pmu),
-     .pmu_name = { 1352 /* uncore_sys_ddr_pmu\000 */ },
+     .pmu_name = { 2454 /* uncore_sys_ddr_pmu\000 */ },
 },
 };
 
@@ -210,6 +247,15 @@ struct pmu_events_map {
  * table of PMU events.
  */
 const struct pmu_events_map pmu_events_map[] = {
+{
+	.arch = "common",
+	.cpuid = "common",
+	.event_table = {
+		.pmus = pmu_events__common,
+		.num_pmus = ARRAY_SIZE(pmu_events__common),
+	},
+	.metric_table = {},
+},
 {
 	.arch = "testarch",
 	.cpuid = "testcpu",
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index d46a22fb5573d..6e71b09dbc2ae 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -292,6 +292,7 @@ def unit_to_pmu(unit: str) -> Optional[str]:
           'cpu_atom': 'cpu_atom',
           'ali_drw': 'ali_drw',
           'arm_cmn': 'arm_cmn',
+          'tool': 'tool',
       }
       return table[unit] if unit in table else f'uncore_{unit.lower()}'
 
@@ -721,6 +722,17 @@ def print_mapping_table(archs: Sequence[str]) -> None:
 \t\t.num_pmus = ARRAY_SIZE(pmu_metrics__test_soc_cpu),
 \t}
 },
+""")
+    elif arch == 'common':
+      _args.output_file.write("""{
+\t.arch = "common",
+\t.cpuid = "common",
+\t.event_table = {
+\t\t.pmus = pmu_events__common,
+\t\t.num_pmus = ARRAY_SIZE(pmu_events__common),
+\t},
+\t.metric_table = {},
+},
 """)
     else:
       with open(f'{_args.starting_dir}/{arch}/mapfile.csv') as csvfile:
@@ -1241,7 +1253,7 @@ def ftw(path: str, parents: Sequence[str],
         if len(parents) == _args.model.split(',')[0].count('/'):
           # We're testing the correct directory.
           item_path = '/'.join(parents) + ('/' if len(parents) > 0 else '') + item.name
-          if 'test' not in item_path and item_path not in _args.model.split(','):
+          if 'test' not in item_path and 'common' not in item_path and item_path not in _args.model.split(','):
             continue
       action(parents, item)
       if item.is_dir():
@@ -1289,7 +1301,7 @@ def ftw(path: str, parents: Sequence[str],
   for item in os.scandir(_args.starting_dir):
     if not item.is_dir():
       continue
-    if item.name == _args.arch or _args.arch == 'all' or item.name == 'test':
+    if item.name == _args.arch or _args.arch == 'all' or item.name == 'test' or item.name == 'common':
       archs.append(item.name)
 
   if len(archs) < 2 and _args.arch != 'none':

From 609aa2667f67c1588d4e741110265f74b7713177 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 1 Oct 2024 20:20:12 -0700
Subject: [PATCH 0279/1530] perf tool_pmu: Switch to standard pmu functions and
 json descriptions

Use the regular PMU approaches with tool json events to reduce the
amount of special tool_pmu code - tool_pmu__config_terms and
tool_pmu__for_each_event_cb are removed. Some functions remain, like
tool_pmu__str_to_event, as conveniences to metricgroups. Add
tool_pmu__skip_event/tool_pmu__num_skip_events to handle the case that
tool json events shouldn't appear on certain architectures. This isn't
done in jevents.py due to complexity in the empty-pmu-events.c and
when all vendor json is built into the tool.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241002032016.333748-10-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/pmu.c      |  26 ++++-----
 tools/perf/util/pmus.c     |   4 +-
 tools/perf/util/tool_pmu.c | 109 +++++++++++--------------------------
 tools/perf/util/tool_pmu.h |  12 +---
 4 files changed, 46 insertions(+), 105 deletions(-)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 9228650a62d26..0789758598c07 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1549,9 +1549,6 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 {
 	bool zero = !!pmu->perf_event_attr_init_default;
 
-	if (perf_pmu__is_tool(pmu))
-		return tool_pmu__config_terms(attr, head_terms, err);
-
 	/* Fake PMU doesn't have proper terms so nothing to configure in attr. */
 	if (perf_pmu__is_fake(pmu))
 		return 0;
@@ -1664,8 +1661,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_
 	info->scale    = 0.0;
 	info->snapshot = false;
 
-	/* Tool/fake PMU doesn't rewrite terms. */
-	if (perf_pmu__is_tool(pmu) || perf_pmu__is_fake(pmu))
+	/* Fake PMU doesn't rewrite terms. */
+	if (perf_pmu__is_fake(pmu))
 		goto out;
 
 	list_for_each_entry_safe(term, h, &head_terms->terms, list) {
@@ -1835,8 +1832,8 @@ bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name)
 {
 	if (!name)
 		return false;
-	if (perf_pmu__is_tool(pmu))
-		return tool_pmu__str_to_event(name) != TOOL_PMU__EVENT_NONE;
+	if (perf_pmu__is_tool(pmu) && tool_pmu__skip_event(name))
+		return false;
 	if (perf_pmu__find_alias(pmu, name, /*load=*/ true) != NULL)
 		return true;
 	if (pmu->cpu_aliases_added || !pmu->events_table)
@@ -1848,9 +1845,6 @@ size_t perf_pmu__num_events(struct perf_pmu *pmu)
 {
 	size_t nr;
 
-	if (perf_pmu__is_tool(pmu))
-		return tool_pmu__num_events();
-
 	pmu_aliases_parse(pmu);
 	nr = pmu->sysfs_aliases + pmu->sys_json_aliases;
 
@@ -1861,6 +1855,9 @@ size_t perf_pmu__num_events(struct perf_pmu *pmu)
 	else
 		assert(pmu->cpu_json_aliases == 0);
 
+	if (perf_pmu__is_tool(pmu))
+		nr -= tool_pmu__num_skip_events();
+
 	return pmu->selectable ? nr + 1 : nr;
 }
 
@@ -1911,15 +1908,15 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 	int ret = 0;
 	struct strbuf sb;
 
-	if (perf_pmu__is_tool(pmu))
-		return tool_pmu__for_each_event_cb(pmu, state, cb);
-
 	strbuf_init(&sb, /*hint=*/ 0);
 	pmu_aliases_parse(pmu);
 	pmu_add_cpu_aliases(pmu);
 	list_for_each_entry(event, &pmu->aliases, list) {
 		size_t buf_used, pmu_name_len;
 
+		if (perf_pmu__is_tool(pmu) && tool_pmu__skip_event(event->name))
+			continue;
+
 		info.pmu_name = event->pmu_name ?: pmu->name;
 		pmu_name_len = pmu_deduped_name_len(pmu, info.pmu_name,
 						    skip_duplicate_pmus);
@@ -2325,9 +2322,6 @@ const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config)
 	if (!pmu)
 		return NULL;
 
-	if (perf_pmu__is_tool(pmu))
-		return tool_pmu__event_to_str(config);
-
 	pmu_aliases_parse(pmu);
 	pmu_add_cpu_aliases(pmu);
 	list_for_each_entry(event, &pmu->aliases, list) {
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index 6e657c44de58e..107de86c26373 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -440,6 +440,7 @@ static int perf_pmus__print_pmu_events__callback(void *vstate,
 		pr_err("Unexpected event %s/%s/\n", info->pmu->name, info->name);
 		return 1;
 	}
+	assert(info->pmu != NULL || info->name != NULL);
 	s = &state->aliases[state->index];
 	s->pmu = info->pmu;
 #define COPY_STR(str) s->str = info->str ? strdup(info->str) : NULL
@@ -590,9 +591,6 @@ void perf_pmus__print_raw_pmu_events(const struct print_callbacks *print_cb, voi
 		int len = pmu_name_len_no_suffix(pmu->name);
 		const char *desc = "(see 'man perf-list' or 'man perf-record' on how to encode it)";
 
-		if (perf_pmu__is_tool(pmu))
-			continue;
-
 		if (!pmu->is_core)
 			desc = NULL;
 
diff --git a/tools/perf/util/tool_pmu.c b/tools/perf/util/tool_pmu.c
index cfdc09dece1e5..ea9d50f025202 100644
--- a/tools/perf/util/tool_pmu.c
+++ b/tools/perf/util/tool_pmu.c
@@ -33,101 +33,54 @@ static const char *const tool_pmu__event_names[TOOL_PMU__EVENT_MAX] = {
 	"system_tsc_freq",
 };
 
-
-const char *tool_pmu__event_to_str(enum tool_pmu_event ev)
-{
-	if (ev > TOOL_PMU__EVENT_NONE && ev < TOOL_PMU__EVENT_MAX)
-		return tool_pmu__event_names[ev];
-
-	return NULL;
-}
-
-enum tool_pmu_event tool_pmu__str_to_event(const char *str)
+bool tool_pmu__skip_event(const char *name __maybe_unused)
 {
-	int i;
-
-	tool_pmu__for_each_event(i) {
-		if (!strcasecmp(str, tool_pmu__event_names[i])) {
 #if !defined(__aarch64__)
-			/* The slots event should only appear on arm64. */
-			if (i == TOOL_PMU__EVENT_SLOTS)
-				return TOOL_PMU__EVENT_NONE;
+	/* The slots event should only appear on arm64. */
+	if (strcasecmp(name, "slots") == 0)
+		return true;
 #endif
-			return i;
-		}
-	}
-	return TOOL_PMU__EVENT_NONE;
+#if !defined(__i386__) && !defined(__x86_64__)
+	/* The system_tsc_freq event should only appear on x86. */
+	if (strcasecmp(name, "system_tsc_freq") == 0)
+		return true;
+#endif
+	return false;
 }
 
-static int tool_pmu__config_term(struct perf_event_attr *attr,
-				 struct parse_events_term *term,
-				 struct parse_events_error *err)
+int tool_pmu__num_skip_events(void)
 {
-	if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER) {
-		enum tool_pmu_event ev = tool_pmu__str_to_event(term->config);
+	int num = 0;
 
-		if (ev == TOOL_PMU__EVENT_NONE)
-			goto err_out;
-
-		attr->config = ev;
-		return 0;
-	}
-err_out:
-	if (err) {
-		char *err_str;
-
-		parse_events_error__handle(err, term->err_val,
-					asprintf(&err_str,
-						"unexpected tool event term (%s) %s",
-						parse_events__term_type_str(term->type_term),
-						term->config) < 0
-					? strdup("unexpected tool event term")
-					: err_str,
-					NULL);
-	}
-	return -EINVAL;
+#if !defined(__aarch64__)
+	num++;
+#endif
+#if !defined(__i386__) && !defined(__x86_64__)
+	num++;
+#endif
+	return num;
 }
 
-int tool_pmu__config_terms(struct perf_event_attr *attr,
-			   struct parse_events_terms *terms,
-			   struct parse_events_error *err)
+const char *tool_pmu__event_to_str(enum tool_pmu_event ev)
 {
-	struct parse_events_term *term;
-
-	list_for_each_entry(term, &terms->terms, list) {
-		if (tool_pmu__config_term(attr, term, err))
-			return -EINVAL;
-	}
-
-	return 0;
+	if (ev > TOOL_PMU__EVENT_NONE && ev < TOOL_PMU__EVENT_MAX)
+		return tool_pmu__event_names[ev];
 
+	return NULL;
 }
 
-int tool_pmu__for_each_event_cb(struct perf_pmu *pmu, void *state, pmu_event_callback cb)
+enum tool_pmu_event tool_pmu__str_to_event(const char *str)
 {
-	struct pmu_event_info info = {
-		.pmu = pmu,
-		.event_type_desc = "Tool event",
-	};
 	int i;
 
+	if (tool_pmu__skip_event(str))
+		return TOOL_PMU__EVENT_NONE;
+
 	tool_pmu__for_each_event(i) {
-		int ret;
-
-		info.name = tool_pmu__event_to_str(i);
-		info.alias = NULL;
-		info.scale_unit = NULL;
-		info.desc = NULL;
-		info.long_desc = NULL;
-		info.encoding_desc = NULL;
-		info.topic = NULL;
-		info.pmu_name = pmu->name;
-		info.deprecated = false;
-		ret = cb(state, &info);
-		if (ret)
-			return ret;
+		if (!strcasecmp(str, tool_pmu__event_names[i]))
+			return i;
 	}
-	return 0;
+	return TOOL_PMU__EVENT_NONE;
 }
 
 bool perf_pmu__is_tool(const struct perf_pmu *pmu)
@@ -546,6 +499,8 @@ struct perf_pmu *perf_pmus__tool_pmu(void)
 		.caps = LIST_HEAD_INIT(tool.caps),
 		.format = LIST_HEAD_INIT(tool.format),
 	};
+	if (!tool.events_table)
+		tool.events_table = find_core_events_table("common", "common");
 
 	return &tool;
 }
diff --git a/tools/perf/util/tool_pmu.h b/tools/perf/util/tool_pmu.h
index ecdf316525bbb..a60184859080f 100644
--- a/tools/perf/util/tool_pmu.h
+++ b/tools/perf/util/tool_pmu.h
@@ -29,17 +29,11 @@ enum tool_pmu_event {
 #define tool_pmu__for_each_event(ev)					\
 	for ((ev) = TOOL_PMU__EVENT_DURATION_TIME; (ev) < TOOL_PMU__EVENT_MAX; ev++)
 
-static inline size_t tool_pmu__num_events(void)
-{
-	return TOOL_PMU__EVENT_MAX - 1;
-}
-
 const char *tool_pmu__event_to_str(enum tool_pmu_event ev);
 enum tool_pmu_event tool_pmu__str_to_event(const char *str);
-int tool_pmu__config_terms(struct perf_event_attr *attr,
-			   struct parse_events_terms *terms,
-			   struct parse_events_error *err);
-int tool_pmu__for_each_event_cb(struct perf_pmu *pmu, void *state, pmu_event_callback cb);
+bool tool_pmu__skip_event(const char *name);
+int tool_pmu__num_skip_events(void);
+
 bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result);
 
 u64 tool_pmu__cpu_slots_per_cycle(void);

From 8c25df7af322040fdf5041e912af7cc810b0f86d Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 1 Oct 2024 20:20:13 -0700
Subject: [PATCH 0280/1530] perf tests: Add tool PMU test

Ensure parsing with and without PMU creates events with the expected
config values. This ensures the tool.json doesn't get out of sync with
tool_pmu_event enum.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241002032016.333748-11-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/Build          |   1 +
 tools/perf/tests/builtin-test.c |   1 +
 tools/perf/tests/tests.h        |   1 +
 tools/perf/tests/tool_pmu.c     | 111 ++++++++++++++++++++++++++++++++
 4 files changed, 114 insertions(+)
 create mode 100644 tools/perf/tests/tool_pmu.c

diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 5671ee5300195..a771e49282471 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -67,6 +67,7 @@ perf-test-y += sigtrap.o
 perf-test-y += event_groups.o
 perf-test-y += symbols.o
 perf-test-y += util.o
+perf-test-y += tool_pmu.o
 
 ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc))
 perf-test-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 470a9709427dd..3b30f258c3959 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -73,6 +73,7 @@ static struct test_suite *generic_tests[] = {
 	&suite__PERF_RECORD,
 	&suite__pmu,
 	&suite__pmu_events,
+	&suite__tool_pmu,
 	&suite__dso_data,
 	&suite__perf_evsel__roundtrip_name_test,
 #ifdef HAVE_LIBTRACEEVENT
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 6ea2be86b7bf8..1ed76d4156b6a 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -83,6 +83,7 @@ DECLARE_SUITE(perf_evsel__tp_sched_test);
 DECLARE_SUITE(syscall_openat_tp_fields);
 DECLARE_SUITE(pmu);
 DECLARE_SUITE(pmu_events);
+DECLARE_SUITE(tool_pmu);
 DECLARE_SUITE(attr);
 DECLARE_SUITE(dso_data);
 DECLARE_SUITE(dso_data_cache);
diff --git a/tools/perf/tests/tool_pmu.c b/tools/perf/tests/tool_pmu.c
new file mode 100644
index 0000000000000..94d0dd8fd3cbb
--- /dev/null
+++ b/tools/perf/tests/tool_pmu.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+#include "debug.h"
+#include "evlist.h"
+#include "parse-events.h"
+#include "tests.h"
+#include "tool_pmu.h"
+
+static int do_test(enum tool_pmu_event ev, bool with_pmu)
+{
+	struct evlist *evlist = evlist__new();
+	struct evsel *evsel;
+	struct parse_events_error err;
+	int ret;
+	char str[128];
+	bool found = false;
+
+	if (!evlist) {
+		pr_err("evlist allocation failed\n");
+		return TEST_FAIL;
+	}
+
+	if (with_pmu)
+		snprintf(str, sizeof(str), "tool/%s/", tool_pmu__event_to_str(ev));
+	else
+		strncpy(str, tool_pmu__event_to_str(ev), sizeof(str));
+
+	parse_events_error__init(&err);
+	ret = parse_events(evlist, str, &err);
+	if (ret) {
+		evlist__delete(evlist);
+		if (tool_pmu__skip_event(tool_pmu__event_to_str(ev))) {
+			ret = TEST_OK;
+			goto out;
+		}
+
+		pr_debug("FAILED %s:%d failed to parse event '%s', err %d\n",
+			 __FILE__, __LINE__, str, ret);
+		parse_events_error__print(&err, str);
+		ret = TEST_FAIL;
+		goto out;
+	}
+
+	ret = TEST_OK;
+	if (with_pmu ? (evlist->core.nr_entries != 1) : (evlist->core.nr_entries < 1)) {
+		pr_debug("FAILED %s:%d Unexpected number of events for '%s' of %d\n",
+			 __FILE__, __LINE__, str, evlist->core.nr_entries);
+		ret = TEST_FAIL;
+		goto out;
+	}
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (perf_pmu__is_tool(evsel->pmu)) {
+			if (evsel->core.attr.config != ev) {
+				pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %d\n",
+					__FILE__, __LINE__, str, evsel->core.attr.config, ev);
+				ret = TEST_FAIL;
+				goto out;
+			}
+			found = true;
+		}
+	}
+
+	if (!found && !tool_pmu__skip_event(tool_pmu__event_to_str(ev))) {
+		pr_debug("FAILED %s:%d Didn't find tool event '%s' in parsed evsels\n",
+			 __FILE__, __LINE__, str);
+		ret = TEST_FAIL;
+	}
+
+out:
+	evlist__delete(evlist);
+	return ret;
+}
+
+static int test__tool_pmu_without_pmu(struct test_suite *test __maybe_unused,
+				      int subtest __maybe_unused)
+{
+	int i;
+
+	tool_pmu__for_each_event(i) {
+		int ret = do_test(i, /*with_pmu=*/false);
+
+		if (ret != TEST_OK)
+			return ret;
+	}
+	return TEST_OK;
+}
+
+static int test__tool_pmu_with_pmu(struct test_suite *test __maybe_unused,
+				   int subtest __maybe_unused)
+{
+	int i;
+
+	tool_pmu__for_each_event(i) {
+		int ret = do_test(i, /*with_pmu=*/true);
+
+		if (ret != TEST_OK)
+			return ret;
+	}
+	return TEST_OK;
+}
+
+static struct test_case tests__tool_pmu[] = {
+	TEST_CASE("Parsing without PMU name", tool_pmu_without_pmu),
+	TEST_CASE("Parsing with PMU name", tool_pmu_with_pmu),
+	{	.name = NULL, }
+};
+
+struct test_suite suite__tool_pmu = {
+	.desc = "Tool PMU",
+	.test_cases = tests__tool_pmu,
+};

From 48966a5a48cd48a499e7c431e09465ce0c092e38 Mon Sep 17 00:00:00 2001
From: Thomas Falcon <thomas.falcon@intel.com>
Date: Thu, 10 Oct 2024 13:40:46 -0500
Subject: [PATCH 0281/1530] perf report: Display columns Predicted/Abort/Cycles
 in --branch-history

The original commit message:

"
Use current sort mechanism but the real .se_cmp() just returns 0 so
that new columns "Predicted", "Abort" and "Cycles" are created in display
but actually these keys are not the sort keys.

For example:

Overhead  Source:Line   Symbol    Shared Object  Predicted  Abort  Cycles
........  ............  ........  .............  .........  .....  ......

  38.25%  div.c:45      [.] main  div            97.6%      0      3
"

Update missed commit from series "perf report: Show branch flags/cycles
in --branch-history callgraph view" to apply to current repository so that
new columns described above are visible.

Link to original series:
https://lore.kernel.org/lkml/1477876794-30749-1-git-send-email-yao.jin@linux.intel.com/

Reported-by: Dr. David Alan Gilbert <linux@treblig.org>
Suggested-by: Kan Liang <kan.liang@linux.intel.com>
Co-developed-by: Jin Yao <yao.jin@linux.intel.com>
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Thomas Falcon <thomas.falcon@intel.com>
Link: https://lore.kernel.org/r/20241010184046.203822-1-thomas.falcon@intel.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Documentation/perf-report.txt |   8 ++
 tools/perf/builtin-report.c              |   6 +-
 tools/perf/util/hist.c                   |   3 +
 tools/perf/util/hist.h                   |   3 +
 tools/perf/util/sort.c                   | 113 ++++++++++++++++++++++-
 tools/perf/util/sort.h                   |   3 +
 6 files changed, 134 insertions(+), 2 deletions(-)

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 7c66d81ab978c..87f8645194062 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -391,6 +391,14 @@ OPTIONS
 	This allows to examine the path the program took to each sample.
 	The data collection must have used -b (or -j) and -g.
 
+	Also show with some branch flags that can be:
+	- Predicted: display the average percentage of predicated branches.
+		     (predicated number / total number)
+	- Abort: display the number of tsx aborted branches.
+	- Cycles: cycles in basic block.
+
+	- iterations: display the average number of iterations in callchain list.
+
 --addr2line=<path>::
         Path to addr2line binary.
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 5dc17ffee27a2..36b344e39dd63 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1271,6 +1271,10 @@ static int process_attr(const struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
+#define CALLCHAIN_BRANCH_SORT_ORDER	\
+	"srcline,symbol,dso,callchain_branch_predicted," \
+	"callchain_branch_abort,callchain_branch_cycles"
+
 int cmd_report(int argc, const char **argv)
 {
 	struct perf_session *session;
@@ -1639,7 +1643,7 @@ int cmd_report(int argc, const char **argv)
 		symbol_conf.use_callchain = true;
 		callchain_register_param(&callchain_param);
 		if (sort_order == NULL)
-			sort_order = "srcline,symbol,dso";
+			sort_order = CALLCHAIN_BRANCH_SORT_ORDER;
 	}
 
 	if (report.mem_mode) {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index f387e85a00873..fff1345658016 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -218,6 +218,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	hists__new_col_len(hists, HISTC_LOCAL_P_STAGE_CYC, 13);
 	hists__new_col_len(hists, HISTC_GLOBAL_P_STAGE_CYC, 13);
 	hists__new_col_len(hists, HISTC_ADDR, BITS_PER_LONG / 4 + 2);
+	hists__new_col_len(hists, HISTC_CALLCHAIN_BRANCH_PREDICTED, 9);
+	hists__new_col_len(hists, HISTC_CALLCHAIN_BRANCH_ABORT, 5);
+	hists__new_col_len(hists, HISTC_CALLCHAIN_BRANCH_CYCLES, 6);
 
 	if (symbol_conf.nanosecs)
 		hists__new_col_len(hists, HISTC_TIME, 16);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 7d7ae94b4b31f..1131056924d9c 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -87,6 +87,9 @@ enum hist_column {
 	HISTC_TYPE_OFFSET,
 	HISTC_SYMBOL_OFFSET,
 	HISTC_TYPE_CACHELINE,
+	HISTC_CALLCHAIN_BRANCH_PREDICTED,
+	HISTC_CALLCHAIN_BRANCH_ABORT,
+	HISTC_CALLCHAIN_BRANCH_CYCLES,
 	HISTC_NR_COLS, /* Last entry */
 };
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 013020f33ece0..168c488f0178d 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -677,6 +677,102 @@ struct sort_entry sort_sym_ipc_null = {
 	.se_width_idx	= HISTC_SYMBOL_IPC,
 };
 
+/* --sort callchain_branch_predicted */
+
+static int64_t
+sort__callchain_branch_predicted_cmp(struct hist_entry *left __maybe_unused,
+				     struct hist_entry *right __maybe_unused)
+{
+	return 0;
+}
+
+static int hist_entry__callchain_branch_predicted_snprintf(
+	struct hist_entry *he, char *bf, size_t size, unsigned int width)
+{
+	u64 branch_count, predicted_count;
+	double percent = 0.0;
+	char str[32];
+
+	callchain_branch_counts(he->callchain, &branch_count,
+				&predicted_count, NULL, NULL);
+
+	if (branch_count)
+		percent = predicted_count * 100.0 / branch_count;
+
+	snprintf(str, sizeof(str), "%.1f%%", percent);
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, str);
+}
+
+struct sort_entry sort_callchain_branch_predicted = {
+	.se_header	= "Predicted",
+	.se_cmp		= sort__callchain_branch_predicted_cmp,
+	.se_snprintf	= hist_entry__callchain_branch_predicted_snprintf,
+	.se_width_idx	= HISTC_CALLCHAIN_BRANCH_PREDICTED,
+};
+
+/* --sort callchain_branch_abort */
+
+static int64_t
+sort__callchain_branch_abort_cmp(struct hist_entry *left __maybe_unused,
+				 struct hist_entry *right __maybe_unused)
+{
+	return 0;
+}
+
+static int hist_entry__callchain_branch_abort_snprintf(struct hist_entry *he,
+						       char *bf, size_t size,
+						       unsigned int width)
+{
+	u64 branch_count, abort_count;
+	char str[32];
+
+	callchain_branch_counts(he->callchain, &branch_count,
+				NULL, &abort_count, NULL);
+
+	snprintf(str, sizeof(str), "%" PRId64, abort_count);
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, str);
+}
+
+struct sort_entry sort_callchain_branch_abort = {
+	.se_header	= "Abort",
+	.se_cmp		= sort__callchain_branch_abort_cmp,
+	.se_snprintf	= hist_entry__callchain_branch_abort_snprintf,
+	.se_width_idx	= HISTC_CALLCHAIN_BRANCH_ABORT,
+};
+
+/* --sort callchain_branch_cycles */
+
+static int64_t
+sort__callchain_branch_cycles_cmp(struct hist_entry *left __maybe_unused,
+				  struct hist_entry *right __maybe_unused)
+{
+	return 0;
+}
+
+static int hist_entry__callchain_branch_cycles_snprintf(struct hist_entry *he,
+							char *bf, size_t size,
+							unsigned int width)
+{
+	u64 branch_count, cycles_count, cycles = 0;
+	char str[32];
+
+	callchain_branch_counts(he->callchain, &branch_count,
+				NULL, NULL, &cycles_count);
+
+	if (branch_count)
+		cycles = cycles_count / branch_count;
+
+	snprintf(str, sizeof(str), "%" PRId64 "", cycles);
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, str);
+}
+
+struct sort_entry sort_callchain_branch_cycles = {
+	.se_header	= "Cycles",
+	.se_cmp		= sort__callchain_branch_cycles_cmp,
+	.se_snprintf	= hist_entry__callchain_branch_cycles_snprintf,
+	.se_width_idx	= HISTC_CALLCHAIN_BRANCH_CYCLES,
+};
+
 /* --sort srcfile */
 
 static char no_srcfile[1];
@@ -2456,6 +2552,15 @@ static struct sort_dimension bstack_sort_dimensions[] = {
 	DIM(SORT_SYM_IPC, "ipc_lbr", sort_sym_ipc),
 	DIM(SORT_ADDR_FROM, "addr_from", sort_addr_from),
 	DIM(SORT_ADDR_TO, "addr_to", sort_addr_to),
+	DIM(SORT_CALLCHAIN_BRANCH_PREDICTED,
+		"callchain_branch_predicted",
+		sort_callchain_branch_predicted),
+	DIM(SORT_CALLCHAIN_BRANCH_ABORT,
+		"callchain_branch_abort",
+		sort_callchain_branch_abort),
+	DIM(SORT_CALLCHAIN_BRANCH_CYCLES,
+		"callchain_branch_cycles",
+		sort_callchain_branch_cycles)
 };
 
 #undef DIM
@@ -3484,7 +3589,13 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 		if (!sd->name || strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		if (sort__mode != SORT_MODE__BRANCH)
+		if ((sort__mode != SORT_MODE__BRANCH) &&
+			strncasecmp(tok, "callchain_branch_predicted",
+				    strlen(tok)) &&
+			strncasecmp(tok, "callchain_branch_abort",
+				    strlen(tok)) &&
+			strncasecmp(tok, "callchain_branch_cycles",
+				    strlen(tok)))
 			return -EINVAL;
 
 		if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 9ff68c6786e71..a8572574e1686 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -88,6 +88,9 @@ enum sort_type {
 	SORT_SYM_IPC,
 	SORT_ADDR_FROM,
 	SORT_ADDR_TO,
+	SORT_CALLCHAIN_BRANCH_PREDICTED,
+	SORT_CALLCHAIN_BRANCH_ABORT,
+	SORT_CALLCHAIN_BRANCH_CYCLES,
 
 	/* memory mode specific sort keys */
 	__SORT_MEMORY_MODE,

From 9e544d46a2d11a0cb8b30d8ad4409c59bc168ce2 Mon Sep 17 00:00:00 2001
From: Siddharth Vadapalli <s-vadapalli@ti.com>
Date: Thu, 10 Oct 2024 20:18:45 +0530
Subject: [PATCH 0282/1530] phy: ti: gmii-sel: Enable USXGMII mode for J7200

TI's J7200 SoC supports USXGMII mode with the CPSW5G instance's MAC Port1.
Add USXGMII mode to the extra_modes member of J7200's SoC data.

Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Link: https://lore.kernel.org/r/20241010144845.2555983-1-s-vadapalli@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/ti/phy-gmii-sel.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c
index 103b266fec771..e0ca59ae31531 100644
--- a/drivers/phy/ti/phy-gmii-sel.c
+++ b/drivers/phy/ti/phy-gmii-sel.c
@@ -230,7 +230,8 @@ static const
 struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw5g_soc_j7200 = {
 	.use_of_data = true,
 	.regfields = phy_gmii_sel_fields_am654,
-	.extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII),
+	.extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII) |
+		       BIT(PHY_INTERFACE_MODE_USXGMII),
 	.num_ports = 4,
 	.num_qsgmii_main_ports = 1,
 };

From 3624fa00ae76be6a93d46071db12bf9218090cb4 Mon Sep 17 00:00:00 2001
From: Krishna Kurapati <quic_kriskura@quicinc.com>
Date: Thu, 10 Oct 2024 01:23:45 +0530
Subject: [PATCH 0283/1530] dt-bindings: usb: qcom,dwc3: Add QCS8300 to USB
 DWC3 bindings

Update dt-bindings to add QCS8300 to USB DWC3 controller list.
The second controller of QCS8300 is High speed only capable and
doesn't have ss_phy_irq.

Signed-off-by: Krishna Kurapati <quic_kriskura@quicinc.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20241009195348.2649368-2-quic_kriskura@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/usb/qcom,dwc3.yaml | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
index 18758efb8d296..f7be056419307 100644
--- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
@@ -26,6 +26,7 @@ properties:
           - qcom,msm8998-dwc3
           - qcom,qcm2290-dwc3
           - qcom,qcs404-dwc3
+          - qcom,qcs8300-dwc3
           - qcom,qdu1000-dwc3
           - qcom,sa8775p-dwc3
           - qcom,sc7180-dwc3
@@ -201,6 +202,7 @@ allOf:
               - qcom,msm8953-dwc3
               - qcom,msm8996-dwc3
               - qcom,msm8998-dwc3
+              - qcom,qcs8300-dwc3
               - qcom,sa8775p-dwc3
               - qcom,sc7180-dwc3
               - qcom,sc7280-dwc3
@@ -465,6 +467,7 @@ allOf:
               - qcom,ipq4019-dwc3
               - qcom,ipq8064-dwc3
               - qcom,msm8994-dwc3
+              - qcom,qcs8300-dwc3
               - qcom,qdu1000-dwc3
               - qcom,sa8775p-dwc3
               - qcom,sc7180-dwc3
@@ -490,6 +493,7 @@ allOf:
           minItems: 4
           maxItems: 5
         interrupt-names:
+          minItems: 4
           items:
             - const: pwr_event
             - const: hs_phy_irq

From c5a3519eae7c491646a87c4861e91f1a1a9f461e Mon Sep 17 00:00:00 2001
From: Krishna Kurapati <quic_kriskura@quicinc.com>
Date: Thu, 10 Oct 2024 01:23:46 +0530
Subject: [PATCH 0284/1530] dt-bindings: phy: qcom,usb-snps-femto-v2: Add
 bindings for QCS8300

Update dt-bindings to add QCS8300 to USB2 SNPS Femto Phy list.

Signed-off-by: Krishna Kurapati <quic_kriskura@quicinc.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20241009195348.2649368-3-quic_kriskura@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml          | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml b/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml
index 519c2b403f66d..661759b250644 100644
--- a/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml
@@ -22,6 +22,7 @@ properties:
           - const: qcom,usb-snps-hs-5nm-phy
       - items:
           - enum:
+              - qcom,qcs8300-usb-hs-phy
               - qcom,qdu1000-usb-hs-phy
               - qcom,sc7280-usb-hs-phy
               - qcom,sc8180x-usb-hs-phy

From c2b174209bbb3341444c899f0a06f21eb953b1f0 Mon Sep 17 00:00:00 2001
From: Krishna Kurapati <quic_kriskura@quicinc.com>
Date: Thu, 10 Oct 2024 01:23:47 +0530
Subject: [PATCH 0285/1530] dt-bindings: phy: qcom,sc8280xp-qmp-usb3-uni: Add
 QCS8300 compatible

Update dt-bindings to add QCS8300 to QMP Uni Phy list.

Signed-off-by: Krishna Kurapati <quic_kriskura@quicinc.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20241009195348.2649368-4-quic_kriskura@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
index 0e0b6cae07bc7..baf5134ea3d8a 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
@@ -20,6 +20,7 @@ properties:
       - qcom,ipq8074-qmp-usb3-phy
       - qcom,ipq9574-qmp-usb3-phy
       - qcom,msm8996-qmp-usb3-phy
+      - qcom,qcs8300-qmp-usb3-uni-phy
       - qcom,qdu1000-qmp-usb3-uni-phy
       - qcom,sa8775p-qmp-usb3-uni-phy
       - qcom,sc8180x-qmp-usb3-uni-phy
@@ -111,6 +112,7 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,qcs8300-qmp-usb3-uni-phy
               - qcom,qdu1000-qmp-usb3-uni-phy
               - qcom,sa8775p-qmp-usb3-uni-phy
               - qcom,sc8180x-qmp-usb3-uni-phy

From 5ee213bdbc6c784c28fc9e2dbb5243906e1f8217 Mon Sep 17 00:00:00 2001
From: Krishna Kurapati <quic_kriskura@quicinc.com>
Date: Thu, 10 Oct 2024 01:23:48 +0530
Subject: [PATCH 0286/1530] phy: qcom: qmp: Add qmp configuration for QCS8300

Add qmp configuration for QCS8300. It is similar to SA8775P and
SC8280XP except for some Lane configuration settings specific to
QCS8300.

Signed-off-by: Krishna Kurapati <quic_kriskura@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20241009195348.2649368-5-quic_kriskura@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-usb.c | 65 +++++++++++++++++++++++++
 1 file changed, 65 insertions(+)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
index 2fd49355aa376..a8f90159395fa 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
@@ -871,6 +871,16 @@ static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_pcs_usb_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_RCVR_DTCT_DLY_U3_H, 0x00),
 };
 
+static const struct qmp_phy_init_tbl qcs8300_usb3_uniphy_tx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V5_TX_LANE_MODE_1, 0xa5),
+	QMP_PHY_INIT_CFG(QSERDES_V5_TX_LANE_MODE_2, 0xf2),
+	QMP_PHY_INIT_CFG(QSERDES_V5_TX_LANE_MODE_3, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V5_TX_LANE_MODE_4, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V5_TX_PI_QEC_CTRL, 0x21),
+	QMP_PHY_INIT_CFG(QSERDES_V5_TX_RES_CODE_LANE_OFFSET_TX, 0x10),
+	QMP_PHY_INIT_CFG(QSERDES_V5_TX_RES_CODE_LANE_OFFSET_RX, 0x0e),
+};
+
 static const struct qmp_phy_init_tbl sm8350_usb3_uniphy_tx_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V5_TX_LANE_MODE_1, 0xa5),
 	QMP_PHY_INIT_CFG(QSERDES_V5_TX_LANE_MODE_2, 0x82),
@@ -989,6 +999,40 @@ static const struct qmp_phy_init_tbl sc8280xp_usb3_uniphy_tx_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V5_TX_RES_CODE_LANE_OFFSET_RX, 0x0e),
 };
 
+static const struct qmp_phy_init_tbl qcs8300_usb3_uniphy_rx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_MODE_00_HIGH4, 0xec),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_MODE_00_HIGH3, 0xbd),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_MODE_00_HIGH2, 0x7f),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_MODE_00_HIGH, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_MODE_00_LOW, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_MODE_01_HIGH4, 0xa9),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_MODE_01_HIGH3, 0x7b),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_MODE_01_HIGH2, 0xe4),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_MODE_01_HIGH, 0x24),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_MODE_01_LOW, 0x64),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_PI_CONTROLS, 0x99),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_SB2_THRESH1, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_SB2_THRESH2, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_SB2_GAIN1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_SB2_GAIN2, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FASTLOCK_FO_GAIN, 0x2f),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FASTLOCK_COUNT_LOW, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FASTLOCK_COUNT_HIGH, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FO_GAIN, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_VGA_CAL_CNTRL1, 0x54),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_VGA_CAL_CNTRL2, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_EQU_ADAPTOR_CNTRL4, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1, 0x47),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_OFFSET_ADAPTOR_CNTRL2, 0x80),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_SIGDET_CNTRL, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_SIGDET_DEGLITCH_CNTRL, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_SO_GAIN, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_GM_CAL, 0x19),
+	QMP_PHY_INIT_CFG(QSERDES_V5_RX_SIGDET_ENABLES, 0x00),
+};
+
 static const struct qmp_phy_init_tbl sc8280xp_usb3_uniphy_rx_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_MODE_00_HIGH4, 0xdc),
 	QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_MODE_00_HIGH3, 0xbd),
@@ -1462,6 +1506,24 @@ static const struct qmp_phy_cfg sa8775p_usb3_uniphy_cfg = {
 	.regs			= qmp_v5_usb3phy_regs_layout,
 };
 
+static const struct qmp_phy_cfg qcs8300_usb3_uniphy_cfg = {
+	.offsets		= &qmp_usb_offsets_v5,
+
+	.serdes_tbl		= sc8280xp_usb3_uniphy_serdes_tbl,
+	.serdes_tbl_num		= ARRAY_SIZE(sc8280xp_usb3_uniphy_serdes_tbl),
+	.tx_tbl			= qcs8300_usb3_uniphy_tx_tbl,
+	.tx_tbl_num		= ARRAY_SIZE(qcs8300_usb3_uniphy_tx_tbl),
+	.rx_tbl			= qcs8300_usb3_uniphy_rx_tbl,
+	.rx_tbl_num		= ARRAY_SIZE(qcs8300_usb3_uniphy_rx_tbl),
+	.pcs_tbl		= sa8775p_usb3_uniphy_pcs_tbl,
+	.pcs_tbl_num		= ARRAY_SIZE(sa8775p_usb3_uniphy_pcs_tbl),
+	.pcs_usb_tbl		= sa8775p_usb3_uniphy_pcs_usb_tbl,
+	.pcs_usb_tbl_num	= ARRAY_SIZE(sa8775p_usb3_uniphy_pcs_usb_tbl),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= qmp_v5_usb3phy_regs_layout,
+};
+
 static const struct qmp_phy_cfg sc8280xp_usb3_uniphy_cfg = {
 	.offsets		= &qmp_usb_offsets_v5,
 
@@ -2246,6 +2308,9 @@ static const struct of_device_id qmp_usb_of_match_table[] = {
 	}, {
 		.compatible = "qcom,msm8996-qmp-usb3-phy",
 		.data = &msm8996_usb3phy_cfg,
+	}, {
+		.compatible = "qcom,qcs8300-qmp-usb3-uni-phy",
+		.data = &qcs8300_usb3_uniphy_cfg,
 	}, {
 		.compatible = "qcom,qdu1000-qmp-usb3-uni-phy",
 		.data = &qdu1000_usb3_uniphy_cfg,

From 11dad94b50263bbe87d015041c77be61c8c44161 Mon Sep 17 00:00:00 2001
From: Andrew Kreimer <algonell@gmail.com>
Date: Thu, 10 Oct 2024 12:13:55 +0300
Subject: [PATCH 0287/1530] phy: sun4i-usb: Fix a typo

Fix a typo in comments: wether -> whether.

Signed-off-by: Andrew Kreimer <algonell@gmail.com>
Acked-by: Chen-Yu Tsai <wens@csie.org>
Link: https://lore.kernel.org/r/20241010091355.8271-1-algonell@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/phy/phy-sun4i-usb.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/phy/phy-sun4i-usb.h b/include/linux/phy/phy-sun4i-usb.h
index 91eb755ee73ba..f3e7b13608e4d 100644
--- a/include/linux/phy/phy-sun4i-usb.h
+++ b/include/linux/phy/phy-sun4i-usb.h
@@ -11,7 +11,7 @@
 /**
  * sun4i_usb_phy_set_squelch_detect() - Enable/disable squelch detect
  * @phy: reference to a sun4i usb phy
- * @enabled: wether to enable or disable squelch detect
+ * @enabled: whether to enable or disable squelch detect
  */
 void sun4i_usb_phy_set_squelch_detect(struct phy *phy, bool enabled);
 

From ca35d5d24574c7f49c77860fb0a1e54b74ac9561 Mon Sep 17 00:00:00 2001
From: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Date: Fri, 11 Oct 2024 16:48:23 +0200
Subject: [PATCH 0288/1530] pinctrl: th1520: Fix pinconf return values

When Drew took over the pinctrl driver he must have changed
all the -ENOTSUPP returns into -EOPNOTSUPP. This subtle change
was most likely not spotted because it was never mentioned in the
changelog of the patchset, but it breaks all the places in the
pin control and GPIO frameworks where -ENOTSUPP is expected.

Fixes: bed5cd6f8a98 ("pinctrl: Add driver for the T-Head TH1520 SoC")
Signed-off-by: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Reviewed-by: Drew Fustini <dfustini@tenstorrent.com>
Tested-by: Drew Fustini <dfustini@tenstorrent.com>
Link: https://lore.kernel.org/20241011144826.381104-2-emil.renner.berthing@canonical.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-th1520.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-th1520.c b/drivers/pinctrl/pinctrl-th1520.c
index c8d2ee6defa79..03326df69668a 100644
--- a/drivers/pinctrl/pinctrl-th1520.c
+++ b/drivers/pinctrl/pinctrl-th1520.c
@@ -591,7 +591,7 @@ static int th1520_pinconf_get(struct pinctrl_dev *pctldev,
 	u32 arg;
 
 	if ((uintptr_t)desc->drv_data & TH1520_PAD_NO_PADCFG)
-		return -EOPNOTSUPP;
+		return -ENOTSUPP;
 
 	value = readl_relaxed(th1520_padcfg(thp, pin));
 	value = (value >> th1520_padcfg_shift(pin)) & GENMASK(9, 0);
@@ -636,7 +636,7 @@ static int th1520_pinconf_get(struct pinctrl_dev *pctldev,
 		arg = enabled ? 1 : 0;
 		break;
 	default:
-		return -EOPNOTSUPP;
+		return -ENOTSUPP;
 	}
 
 	*config = pinconf_to_config_packed(param, arg);
@@ -661,7 +661,7 @@ static int th1520_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 	u16 mask, value;
 
 	if ((uintptr_t)desc->drv_data & TH1520_PAD_NO_PADCFG)
-		return -EOPNOTSUPP;
+		return -ENOTSUPP;
 
 	mask = 0;
 	value = 0;
@@ -676,14 +676,14 @@ static int th1520_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 			break;
 		case PIN_CONFIG_BIAS_PULL_DOWN:
 			if (arg == 0)
-				return -EOPNOTSUPP;
+				return -ENOTSUPP;
 			mask |= TH1520_PADCFG_BIAS;
 			value &= ~TH1520_PADCFG_BIAS;
 			value |= TH1520_PADCFG_PE;
 			break;
 		case PIN_CONFIG_BIAS_PULL_UP:
 			if (arg == 0)
-				return -EOPNOTSUPP;
+				return -ENOTSUPP;
 			mask |= TH1520_PADCFG_BIAS;
 			value &= ~TH1520_PADCFG_BIAS;
 			if (arg == TH1520_PULL_STRONG_OHM)
@@ -718,7 +718,7 @@ static int th1520_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 				value &= ~TH1520_PADCFG_SL;
 			break;
 		default:
-			return -EOPNOTSUPP;
+			return -ENOTSUPP;
 		}
 	}
 

From d1e16e219901965e6c0715adb92750ed865fda43 Mon Sep 17 00:00:00 2001
From: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Date: Fri, 11 Oct 2024 16:48:24 +0200
Subject: [PATCH 0289/1530] pinctrl: th1520: Update pinmux tables

When Drew took over the pinctrl driver it seems like he didn't use the
git tree I pointed him at and thus missed some important fixes to the
tables describing valid pinmux settings.

The documentation has a nice overview table of these settings but
unfortunately it doesn't fully match the register descriptions, which
seem to be the correct version.

Fixes: bed5cd6f8a98 ("pinctrl: Add driver for the T-Head TH1520 SoC")
Signed-off-by: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Reviewed-by: Drew Fustini <dfustini@tenstorrent.com>
Tested-by: Drew Fustini <dfustini@tenstorrent.com>
Link: https://lore.kernel.org/20241011144826.381104-3-emil.renner.berthing@canonical.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-th1520.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-th1520.c b/drivers/pinctrl/pinctrl-th1520.c
index 03326df69668a..8bd40cb2f013c 100644
--- a/drivers/pinctrl/pinctrl-th1520.c
+++ b/drivers/pinctrl/pinctrl-th1520.c
@@ -221,9 +221,9 @@ static const struct pinctrl_pin_desc th1520_group2_pins[] = {
 	TH1520_PAD(15, UART4_RTSN,    UART, ____, ____, GPIO, ____, ____, 0),
 	TH1520_PAD(16, UART3_TXD,     DBG,  UART, ____, GPIO, ____, ____, 0),
 	TH1520_PAD(17, UART3_RXD,     DBG,  UART, ____, GPIO, ____, ____, 0),
-	TH1520_PAD(18, GPIO0_18,      GPIO, I2C,  ____, ____, ____, ____, 0),
-	TH1520_PAD(19, GPIO0_19,      GPIO, I2C,  ____, ____, ____, ____, 0),
-	TH1520_PAD(20, GPIO0_20,      GPIO, UART, IR,   ____, ____, ____, 0),
+	TH1520_PAD(18, GPIO0_18,      GPIO, I2C,  ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(19, GPIO0_19,      GPIO, I2C,  ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(20, GPIO0_20,      GPIO, UART, IR,   ____, DPU0, DPU1, 0),
 	TH1520_PAD(21, GPIO0_21,      GPIO, UART, IR,   ____, DPU0, DPU1, 0),
 	TH1520_PAD(22, GPIO0_22,      GPIO, JTAG, I2C,  ____, DPU0, DPU1, 0),
 	TH1520_PAD(23, GPIO0_23,      GPIO, JTAG, I2C,  ____, DPU0, DPU1, 0),
@@ -241,7 +241,7 @@ static const struct pinctrl_pin_desc th1520_group2_pins[] = {
 	TH1520_PAD(35, GPIO1_3,       GPIO, JTAG, ____, ____, DPU0, DPU1, 0),
 	TH1520_PAD(36, GPIO1_4,       GPIO, JTAG, ____, ____, DPU0, DPU1, 0),
 	TH1520_PAD(37, GPIO1_5,       GPIO, ____, ____, ____, DPU0, DPU1, 0),
-	TH1520_PAD(38, GPIO1_6,       GPIO, ____, ____, ____, DPU0, DPU1, 0),
+	TH1520_PAD(38, GPIO1_6,       GPIO, QSPI, ____, ____, DPU0, DPU1, 0),
 	TH1520_PAD(39, GPIO1_7,       GPIO, QSPI, ____, ____, DPU0, DPU1, 0),
 	TH1520_PAD(40, GPIO1_8,       GPIO, QSPI, ____, ____, DPU0, DPU1, 0),
 	TH1520_PAD(41, GPIO1_9,       GPIO, QSPI, ____, ____, DPU0, DPU1, 0),
@@ -256,11 +256,11 @@ static const struct pinctrl_pin_desc th1520_group2_pins[] = {
 	TH1520_PAD(50, CLK_OUT_1,     BSEL, CLK,  ____, GPIO, ____, ____, 0),
 	TH1520_PAD(51, CLK_OUT_2,     BSEL, CLK,  ____, GPIO, ____, ____, 0),
 	TH1520_PAD(52, CLK_OUT_3,     BSEL, CLK,  ____, GPIO, ____, ____, 0),
-	TH1520_PAD(53, GPIO1_21,      GPIO, ____, ISP,  ____, ____, ____, 0),
-	TH1520_PAD(54, GPIO1_22,      GPIO, ____, ISP,  ____, ____, ____, 0),
-	TH1520_PAD(55, GPIO1_23,      GPIO, ____, ISP,  ____, ____, ____, 0),
-	TH1520_PAD(56, GPIO1_24,      GPIO, ____, ISP,  ____, ____, ____, 0),
-	TH1520_PAD(57, GPIO1_25,      GPIO, ____, ISP,  ____, ____, ____, 0),
+	TH1520_PAD(53, GPIO1_21,      JTAG, ____, ISP,  GPIO, ____, ____, 0),
+	TH1520_PAD(54, GPIO1_22,      JTAG, ____, ISP,  GPIO, ____, ____, 0),
+	TH1520_PAD(55, GPIO1_23,      JTAG, ____, ISP,  GPIO, ____, ____, 0),
+	TH1520_PAD(56, GPIO1_24,      JTAG, ____, ISP,  GPIO, ____, ____, 0),
+	TH1520_PAD(57, GPIO1_25,      JTAG, ____, ISP,  GPIO, ____, ____, 0),
 	TH1520_PAD(58, GPIO1_26,      GPIO, ____, ISP,  ____, ____, ____, 0),
 	TH1520_PAD(59, GPIO1_27,      GPIO, ____, ISP,  ____, ____, ____, 0),
 	TH1520_PAD(60, GPIO1_28,      GPIO, ____, ISP,  ____, ____, ____, 0),

From 1fc30cd9277063bb797eeafe73a1f3faa6177492 Mon Sep 17 00:00:00 2001
From: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Date: Fri, 11 Oct 2024 16:48:25 +0200
Subject: [PATCH 0290/1530] pinctrl: th1520: Factor out casts

Limit the casts to get the mux data and flags from the driver data
pointer with each pin to two inline functions as requested by Andy
during review.

Signed-off-by: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Reviewed-by: Drew Fustini <dfustini@tenstorrent.com>
Tested-by: Drew Fustini <dfustini@tenstorrent.com>
Link: https://lore.kernel.org/20241011144826.381104-4-emil.renner.berthing@canonical.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-th1520.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-th1520.c b/drivers/pinctrl/pinctrl-th1520.c
index 8bd40cb2f013c..7474d8da32f90 100644
--- a/drivers/pinctrl/pinctrl-th1520.c
+++ b/drivers/pinctrl/pinctrl-th1520.c
@@ -152,6 +152,16 @@ static enum th1520_muxtype th1520_muxtype_get(const char *str)
 		(TH1520_MUX_##m0 <<  0) | (TH1520_MUX_##m1 <<  5) | (TH1520_MUX_##m2 << 10) | \
 		(TH1520_MUX_##m3 << 15) | (TH1520_MUX_##m4 << 20) | (TH1520_MUX_##m5 << 25)) }
 
+static unsigned long th1520_pad_muxdata(void *drv_data)
+{
+	return (uintptr_t)drv_data & TH1520_PAD_MUXDATA;
+}
+
+static bool th1520_pad_no_padcfg(void *drv_data)
+{
+	return (uintptr_t)drv_data & TH1520_PAD_NO_PADCFG;
+}
+
 static const struct pinctrl_pin_desc th1520_group1_pins[] = {
 	TH1520_PAD(0,  OSC_CLK_IN,    ____, ____, ____, ____, ____, ____, TH1520_PAD_NO_PADCFG),
 	TH1520_PAD(1,  OSC_CLK_OUT,   ____, ____, ____, ____, ____, ____, TH1520_PAD_NO_PADCFG),
@@ -590,7 +600,7 @@ static int th1520_pinconf_get(struct pinctrl_dev *pctldev,
 	u32 value;
 	u32 arg;
 
-	if ((uintptr_t)desc->drv_data & TH1520_PAD_NO_PADCFG)
+	if (th1520_pad_no_padcfg(desc->drv_data))
 		return -ENOTSUPP;
 
 	value = readl_relaxed(th1520_padcfg(thp, pin));
@@ -660,7 +670,7 @@ static int th1520_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 	unsigned int i;
 	u16 mask, value;
 
-	if ((uintptr_t)desc->drv_data & TH1520_PAD_NO_PADCFG)
+	if (th1520_pad_no_padcfg(desc->drv_data))
 		return -ENOTSUPP;
 
 	mask = 0;
@@ -793,12 +803,14 @@ static int th1520_pinmux_set_mux(struct pinctrl_dev *pctldev,
 {
 	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
 	const struct function_desc *func = pinmux_generic_get_function(pctldev, fsel);
+	enum th1520_muxtype muxtype = (uintptr_t)func->data;
 
 	if (!func)
 		return -EINVAL;
+
 	return th1520_pinmux_set(thp, thp->desc.pins[gsel].number,
-				 (uintptr_t)thp->desc.pins[gsel].drv_data & TH1520_PAD_MUXDATA,
-				 (uintptr_t)func->data);
+				 th1520_pad_muxdata(thp->desc.pins[gsel].drv_data),
+				 muxtype);
 }
 
 static int th1520_gpio_request_enable(struct pinctrl_dev *pctldev,
@@ -809,7 +821,7 @@ static int th1520_gpio_request_enable(struct pinctrl_dev *pctldev,
 	const struct pin_desc *desc = pin_desc_get(pctldev, offset);
 
 	return th1520_pinmux_set(thp, offset,
-				 (uintptr_t)desc->drv_data & TH1520_PAD_MUXDATA,
+				 th1520_pad_muxdata(desc->drv_data),
 				 TH1520_MUX_GPIO);
 }
 

From 1a075b1dcc14903ac56ec87d8cd6dfa06d54c013 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@baylibre.com>
Date: Mon, 7 Oct 2024 22:58:05 +0200
Subject: [PATCH 0291/1530] pinctrl: Switch back to struct
 platform_driver::remove()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 0edb555a65d1 ("platform: Make platform_driver::remove()
return void") .remove() is (again) the right callback to implement for
platform drivers.

Convert all platform drivers below drivers/pinctrl to use .remove(),
with the eventual goal to drop struct platform_driver::remove_new(). As
.remove() and .remove_new() have the same prototypes, conversion is done
by just changing the structure member name in the driver initializer.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Link: https://lore.kernel.org/20241007205803.444994-8-u.kleine-koenig@baylibre.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/cirrus/pinctrl-madera-core.c      | 2 +-
 drivers/pinctrl/intel/pinctrl-cherryview.c        | 2 +-
 drivers/pinctrl/nomadik/pinctrl-abx500.c          | 2 +-
 drivers/pinctrl/pinctrl-amd.c                     | 2 +-
 drivers/pinctrl/pinctrl-artpec6.c                 | 2 +-
 drivers/pinctrl/pinctrl-rockchip.c                | 2 +-
 drivers/pinctrl/pinctrl-single.c                  | 2 +-
 drivers/pinctrl/pinctrl-stmfx.c                   | 2 +-
 drivers/pinctrl/pinctrl-tb10x.c                   | 2 +-
 drivers/pinctrl/qcom/pinctrl-apq8064.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-apq8084.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-ipq4019.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-ipq5018.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-ipq5332.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-ipq6018.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-ipq8064.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-ipq8074.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-ipq9574.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-mdm9607.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-mdm9615.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-msm8226.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-msm8660.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-msm8909.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-msm8916.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-msm8953.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-msm8960.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-msm8976.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-msm8994.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-msm8996.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-msm8998.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-msm8x74.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-qcm2290.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-qcs404.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-qcs615.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-qdf2xxx.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-qdu1000.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-sa8775p.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-sc7180.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c   | 2 +-
 drivers/pinctrl/qcom/pinctrl-sc7280.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sc8180x.c            | 2 +-
 drivers/pinctrl/qcom/pinctrl-sc8280xp-lpass-lpi.c | 2 +-
 drivers/pinctrl/qcom/pinctrl-sc8280xp.c           | 2 +-
 drivers/pinctrl/qcom/pinctrl-sdm660.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sdm670.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sdm845.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sdx55.c              | 2 +-
 drivers/pinctrl/qcom/pinctrl-sdx65.c              | 2 +-
 drivers/pinctrl/qcom/pinctrl-sdx75.c              | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm4250-lpass-lpi.c   | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm4450.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm6115-lpass-lpi.c   | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm6115.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm6125.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm6350.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm6375.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm7150.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm8150.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c   | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm8250.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c   | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm8350.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm8450-lpass-lpi.c   | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm8450.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c   | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm8550.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c   | 2 +-
 drivers/pinctrl/qcom/pinctrl-sm8650.c             | 2 +-
 drivers/pinctrl/qcom/pinctrl-spmi-gpio.c          | 2 +-
 drivers/pinctrl/qcom/pinctrl-spmi-mpp.c           | 2 +-
 drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c          | 2 +-
 drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c           | 2 +-
 drivers/pinctrl/qcom/pinctrl-x1e80100.c           | 2 +-
 drivers/pinctrl/renesas/pinctrl-rzn1.c            | 2 +-
 drivers/pinctrl/sprd/pinctrl-sprd-sc9860.c        | 2 +-
 75 files changed, 75 insertions(+), 75 deletions(-)

diff --git a/drivers/pinctrl/cirrus/pinctrl-madera-core.c b/drivers/pinctrl/cirrus/pinctrl-madera-core.c
index 2932d7aba7255..73ec5b9beb49f 100644
--- a/drivers/pinctrl/cirrus/pinctrl-madera-core.c
+++ b/drivers/pinctrl/cirrus/pinctrl-madera-core.c
@@ -1091,7 +1091,7 @@ static void madera_pin_remove(struct platform_device *pdev)
 
 static struct platform_driver madera_pin_driver = {
 	.probe = madera_pin_probe,
-	.remove_new = madera_pin_remove,
+	.remove = madera_pin_remove,
 	.driver = {
 		.name = "madera-pinctrl",
 	},
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index 067b0d344f0e5..9f938718927bd 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1792,7 +1792,7 @@ MODULE_DEVICE_TABLE(acpi, chv_pinctrl_acpi_match);
 
 static struct platform_driver chv_pinctrl_driver = {
 	.probe = chv_pinctrl_probe,
-	.remove_new = chv_pinctrl_remove,
+	.remove = chv_pinctrl_remove,
 	.driver = {
 		.name = "cherryview-pinctrl",
 		.pm = pm_sleep_ptr(&chv_pinctrl_pm_ops),
diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c
index 68750b6f8e57a..4ce2e35a63733 100644
--- a/drivers/pinctrl/nomadik/pinctrl-abx500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c
@@ -1089,7 +1089,7 @@ static struct platform_driver abx500_gpio_driver = {
 		.of_match_table = abx500_gpio_match,
 	},
 	.probe = abx500_gpio_probe,
-	.remove_new = abx500_gpio_remove,
+	.remove = abx500_gpio_remove,
 };
 
 static int __init abx500_gpio_init(void)
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 7f66ec73199a9..b0fab262d534d 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -1204,7 +1204,7 @@ static struct platform_driver amd_gpio_driver = {
 #endif
 	},
 	.probe		= amd_gpio_probe,
-	.remove_new	= amd_gpio_remove,
+	.remove		= amd_gpio_remove,
 };
 
 module_platform_driver(amd_gpio_driver);
diff --git a/drivers/pinctrl/pinctrl-artpec6.c b/drivers/pinctrl/pinctrl-artpec6.c
index dd93f124e0a09..717f9592b28b5 100644
--- a/drivers/pinctrl/pinctrl-artpec6.c
+++ b/drivers/pinctrl/pinctrl-artpec6.c
@@ -988,7 +988,7 @@ static struct platform_driver artpec6_pmx_driver = {
 		.of_match_table = artpec6_pinctrl_match,
 	},
 	.probe = artpec6_pmx_probe,
-	.remove_new = artpec6_pmx_remove,
+	.remove = artpec6_pmx_remove,
 };
 
 static int __init artpec6_pmx_init(void)
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index 04e85a6037c93..36d4eaf0ebd15 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -4221,7 +4221,7 @@ static const struct of_device_id rockchip_pinctrl_dt_match[] = {
 
 static struct platform_driver rockchip_pinctrl_driver = {
 	.probe		= rockchip_pinctrl_probe,
-	.remove_new	= rockchip_pinctrl_remove,
+	.remove		= rockchip_pinctrl_remove,
 	.driver = {
 		.name	= "rockchip-pinctrl",
 		.pm = &rockchip_pinctrl_dev_pm_ops,
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index 2ec599e383e4b..8addb08d81a1d 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1981,7 +1981,7 @@ MODULE_DEVICE_TABLE(of, pcs_of_match);
 
 static struct platform_driver pcs_driver = {
 	.probe		= pcs_probe,
-	.remove_new	= pcs_remove,
+	.remove		= pcs_remove,
 	.driver = {
 		.name		= DRIVER_NAME,
 		.of_match_table	= pcs_of_match,
diff --git a/drivers/pinctrl/pinctrl-stmfx.c b/drivers/pinctrl/pinctrl-stmfx.c
index d2c5321dd025f..bfeb2edbeec5b 100644
--- a/drivers/pinctrl/pinctrl-stmfx.c
+++ b/drivers/pinctrl/pinctrl-stmfx.c
@@ -855,7 +855,7 @@ static struct platform_driver stmfx_pinctrl_driver = {
 		.pm = &stmfx_pinctrl_dev_pm_ops,
 	},
 	.probe = stmfx_pinctrl_probe,
-	.remove_new = stmfx_pinctrl_remove,
+	.remove = stmfx_pinctrl_remove,
 };
 module_platform_driver(stmfx_pinctrl_driver);
 
diff --git a/drivers/pinctrl/pinctrl-tb10x.c b/drivers/pinctrl/pinctrl-tb10x.c
index 4f98f72565f48..d6bb8f58978df 100644
--- a/drivers/pinctrl/pinctrl-tb10x.c
+++ b/drivers/pinctrl/pinctrl-tb10x.c
@@ -820,7 +820,7 @@ MODULE_DEVICE_TABLE(of, tb10x_pinctrl_dt_ids);
 
 static struct platform_driver tb10x_pinctrl_pdrv = {
 	.probe   = tb10x_pinctrl_probe,
-	.remove_new = tb10x_pinctrl_remove,
+	.remove  = tb10x_pinctrl_remove,
 	.driver  = {
 		.name  = "tb10x_pinctrl",
 		.of_match_table = of_match_ptr(tb10x_pinctrl_dt_ids),
diff --git a/drivers/pinctrl/qcom/pinctrl-apq8064.c b/drivers/pinctrl/qcom/pinctrl-apq8064.c
index a18df41622999..20c3b90250445 100644
--- a/drivers/pinctrl/qcom/pinctrl-apq8064.c
+++ b/drivers/pinctrl/qcom/pinctrl-apq8064.c
@@ -629,7 +629,7 @@ static struct platform_driver apq8064_pinctrl_driver = {
 		.of_match_table = apq8064_pinctrl_of_match,
 	},
 	.probe = apq8064_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init apq8064_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-apq8084.c b/drivers/pinctrl/qcom/pinctrl-apq8084.c
index afada80e52a23..3fc0a40762b63 100644
--- a/drivers/pinctrl/qcom/pinctrl-apq8084.c
+++ b/drivers/pinctrl/qcom/pinctrl-apq8084.c
@@ -1207,7 +1207,7 @@ static struct platform_driver apq8084_pinctrl_driver = {
 		.of_match_table = apq8084_pinctrl_of_match,
 	},
 	.probe = apq8084_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init apq8084_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq4019.c b/drivers/pinctrl/qcom/pinctrl-ipq4019.c
index cb13576ad6cfb..1f7944dd829d1 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq4019.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq4019.c
@@ -710,7 +710,7 @@ static struct platform_driver ipq4019_pinctrl_driver = {
 		.of_match_table = ipq4019_pinctrl_of_match,
 	},
 	.probe = ipq4019_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq4019_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq5018.c b/drivers/pinctrl/qcom/pinctrl-ipq5018.c
index 68f65b57003e9..e2951f81c3eeb 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq5018.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq5018.c
@@ -754,7 +754,7 @@ static struct platform_driver ipq5018_pinctrl_driver = {
 		.of_match_table = ipq5018_pinctrl_of_match,
 	},
 	.probe = ipq5018_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq5018_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq5332.c b/drivers/pinctrl/qcom/pinctrl-ipq5332.c
index 8821751189708..625f8014051f6 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq5332.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq5332.c
@@ -834,7 +834,7 @@ static struct platform_driver ipq5332_pinctrl_driver = {
 		.of_match_table = ipq5332_pinctrl_of_match,
 	},
 	.probe = ipq5332_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq5332_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq6018.c b/drivers/pinctrl/qcom/pinctrl-ipq6018.c
index ac330d8712b5c..0ad08647dbcdf 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq6018.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq6018.c
@@ -1080,7 +1080,7 @@ static struct platform_driver ipq6018_pinctrl_driver = {
 		.of_match_table = ipq6018_pinctrl_of_match,
 	},
 	.probe = ipq6018_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq6018_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq8064.c b/drivers/pinctrl/qcom/pinctrl-ipq8064.c
index e10e1bc4c9113..e2bb94e86aef6 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq8064.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq8064.c
@@ -631,7 +631,7 @@ static struct platform_driver ipq8064_pinctrl_driver = {
 		.of_match_table = ipq8064_pinctrl_of_match,
 	},
 	.probe = ipq8064_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq8064_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq8074.c b/drivers/pinctrl/qcom/pinctrl-ipq8074.c
index fee32c1d1d3e9..337f3a1c92c19 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq8074.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq8074.c
@@ -1041,7 +1041,7 @@ static struct platform_driver ipq8074_pinctrl_driver = {
 		.of_match_table = ipq8074_pinctrl_of_match,
 	},
 	.probe = ipq8074_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq8074_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq9574.c b/drivers/pinctrl/qcom/pinctrl-ipq9574.c
index 20ab59cb621bc..e2491617b2364 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq9574.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq9574.c
@@ -799,7 +799,7 @@ static struct platform_driver ipq9574_pinctrl_driver = {
 		.of_match_table = ipq9574_pinctrl_of_match,
 	},
 	.probe = ipq9574_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq9574_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-mdm9607.c b/drivers/pinctrl/qcom/pinctrl-mdm9607.c
index 415d24e16267d..e7cd3ef1cf3e8 100644
--- a/drivers/pinctrl/qcom/pinctrl-mdm9607.c
+++ b/drivers/pinctrl/qcom/pinctrl-mdm9607.c
@@ -1059,7 +1059,7 @@ static struct platform_driver mdm9607_pinctrl_driver = {
 		.of_match_table = mdm9607_pinctrl_of_match,
 	},
 	.probe = mdm9607_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init mdm9607_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-mdm9615.c b/drivers/pinctrl/qcom/pinctrl-mdm9615.c
index 3f2eafea0b246..0a2ae383d3d57 100644
--- a/drivers/pinctrl/qcom/pinctrl-mdm9615.c
+++ b/drivers/pinctrl/qcom/pinctrl-mdm9615.c
@@ -446,7 +446,7 @@ static struct platform_driver mdm9615_pinctrl_driver = {
 		.of_match_table = mdm9615_pinctrl_of_match,
 	},
 	.probe = mdm9615_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init mdm9615_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8226.c b/drivers/pinctrl/qcom/pinctrl-msm8226.c
index 40806c0650ef2..64fee70f1772c 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8226.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8226.c
@@ -654,7 +654,7 @@ static struct platform_driver msm8226_pinctrl_driver = {
 		.of_match_table = msm8226_pinctrl_of_match,
 	},
 	.probe = msm8226_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8226_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8660.c b/drivers/pinctrl/qcom/pinctrl-msm8660.c
index dba6d531b4a14..999a5f867eb50 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8660.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8660.c
@@ -981,7 +981,7 @@ static struct platform_driver msm8660_pinctrl_driver = {
 		.of_match_table = msm8660_pinctrl_of_match,
 	},
 	.probe = msm8660_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8660_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8909.c b/drivers/pinctrl/qcom/pinctrl-msm8909.c
index 14b17ba9f9061..756856d20d6b5 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8909.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8909.c
@@ -929,7 +929,7 @@ static struct platform_driver msm8909_pinctrl_driver = {
 		.of_match_table = msm8909_pinctrl_of_match,
 	},
 	.probe = msm8909_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8909_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8916.c b/drivers/pinctrl/qcom/pinctrl-msm8916.c
index 184dcf8422735..cea5c54f92fec 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8916.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8916.c
@@ -969,7 +969,7 @@ static struct platform_driver msm8916_pinctrl_driver = {
 		.of_match_table = msm8916_pinctrl_of_match,
 	},
 	.probe = msm8916_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8916_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8953.c b/drivers/pinctrl/qcom/pinctrl-msm8953.c
index c2253821ae8d3..998351bdfee13 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8953.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8953.c
@@ -1816,7 +1816,7 @@ static struct platform_driver msm8953_pinctrl_driver = {
 		.of_match_table = msm8953_pinctrl_of_match,
 	},
 	.probe = msm8953_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8953_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8960.c b/drivers/pinctrl/qcom/pinctrl-msm8960.c
index 6b9148d226e9b..ebe230b3b437c 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8960.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8960.c
@@ -1246,7 +1246,7 @@ static struct platform_driver msm8960_pinctrl_driver = {
 		.of_match_table = msm8960_pinctrl_of_match,
 	},
 	.probe = msm8960_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8960_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8976.c b/drivers/pinctrl/qcom/pinctrl-msm8976.c
index 9a951888e8a1b..c30d80e4e98ca 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8976.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8976.c
@@ -1096,7 +1096,7 @@ static struct platform_driver msm8976_pinctrl_driver = {
 		.of_match_table = msm8976_pinctrl_of_match,
 	},
 	.probe = msm8976_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8976_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8994.c b/drivers/pinctrl/qcom/pinctrl-msm8994.c
index 1ed1dd32d6c79..b1a6759ab4a5e 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8994.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8994.c
@@ -1343,7 +1343,7 @@ static struct platform_driver msm8994_pinctrl_driver = {
 		.of_match_table = msm8994_pinctrl_of_match,
 	},
 	.probe = msm8994_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8994_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8996.c b/drivers/pinctrl/qcom/pinctrl-msm8996.c
index 777c2a74036ed..1b5d80eaab83c 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8996.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8996.c
@@ -1920,7 +1920,7 @@ static struct platform_driver msm8996_pinctrl_driver = {
 		.of_match_table = msm8996_pinctrl_of_match,
 	},
 	.probe = msm8996_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8996_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8998.c b/drivers/pinctrl/qcom/pinctrl-msm8998.c
index 4aaf45e54f3a7..b7cbf32b3125a 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8998.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8998.c
@@ -1535,7 +1535,7 @@ static struct platform_driver msm8998_pinctrl_driver = {
 		.of_match_table = msm8998_pinctrl_of_match,
 	},
 	.probe = msm8998_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8998_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8x74.c b/drivers/pinctrl/qcom/pinctrl-msm8x74.c
index 750a8272ded7f..238c83f6ec4f4 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8x74.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8x74.c
@@ -1083,7 +1083,7 @@ static struct platform_driver msm8x74_pinctrl_driver = {
 		.of_match_table = msm8x74_pinctrl_of_match,
 	},
 	.probe = msm8x74_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8x74_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qcm2290.c b/drivers/pinctrl/qcom/pinctrl-qcm2290.c
index f5c1c427b44e9..ba699eac9ee8b 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcm2290.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcm2290.c
@@ -1113,7 +1113,7 @@ static struct platform_driver qcm2290_pinctrl_driver = {
 		.of_match_table = qcm2290_pinctrl_of_match,
 	},
 	.probe = qcm2290_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init qcm2290_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qcs404.c b/drivers/pinctrl/qcom/pinctrl-qcs404.c
index 9a875b7dc9989..ae7224012f8aa 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcs404.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcs404.c
@@ -1644,7 +1644,7 @@ static struct platform_driver qcs404_pinctrl_driver = {
 		.of_match_table = qcs404_pinctrl_of_match,
 	},
 	.probe = qcs404_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init qcs404_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qcs615.c b/drivers/pinctrl/qcom/pinctrl-qcs615.c
index 8380e22b2faa1..23015b055f6a9 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcs615.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcs615.c
@@ -1087,7 +1087,7 @@ static struct platform_driver qcs615_tlmm_driver = {
 		.of_match_table = qcs615_tlmm_of_match,
 	},
 	.probe = qcs615_tlmm_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init qcs615_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c b/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
index 4d2f6f495163b..b5808fcfb13cd 100644
--- a/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
+++ b/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
@@ -145,7 +145,7 @@ static struct platform_driver qdf2xxx_pinctrl_driver = {
 		.acpi_match_table = qdf2xxx_acpi_ids,
 	},
 	.probe = qdf2xxx_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init qdf2xxx_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qdu1000.c b/drivers/pinctrl/qcom/pinctrl-qdu1000.c
index da4f940bc8d4e..47bc529ef550d 100644
--- a/drivers/pinctrl/qcom/pinctrl-qdu1000.c
+++ b/drivers/pinctrl/qcom/pinctrl-qdu1000.c
@@ -1248,7 +1248,7 @@ static struct platform_driver qdu1000_tlmm_driver = {
 		.of_match_table = qdu1000_tlmm_of_match,
 	},
 	.probe = qdu1000_tlmm_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init qdu1000_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sa8775p.c b/drivers/pinctrl/qcom/pinctrl-sa8775p.c
index 5459c0c681a23..8fdea25d8d67e 100644
--- a/drivers/pinctrl/qcom/pinctrl-sa8775p.c
+++ b/drivers/pinctrl/qcom/pinctrl-sa8775p.c
@@ -1530,7 +1530,7 @@ static struct platform_driver sa8775p_pinctrl_driver = {
 		.of_match_table = sa8775p_pinctrl_of_match,
 	},
 	.probe = sa8775p_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sa8775p_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sc7180.c b/drivers/pinctrl/qcom/pinctrl-sc7180.c
index c27aaa599b917..6eb0c73791c0b 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc7180.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc7180.c
@@ -1159,7 +1159,7 @@ static struct platform_driver sc7180_pinctrl_driver = {
 		.of_match_table = sc7180_pinctrl_of_match,
 	},
 	.probe = sc7180_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sc7180_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c
index 6bb39812e1d8b..1161f0a91a002 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c
@@ -142,7 +142,7 @@ static struct platform_driver lpi_pinctrl_driver = {
 		   .of_match_table = lpi_pinctrl_of_match,
 	},
 	.probe = lpi_pinctrl_probe,
-	.remove_new = lpi_pinctrl_remove,
+	.remove = lpi_pinctrl_remove,
 };
 
 module_platform_driver(lpi_pinctrl_driver);
diff --git a/drivers/pinctrl/qcom/pinctrl-sc7280.c b/drivers/pinctrl/qcom/pinctrl-sc7280.c
index c2db663e396eb..0c10eeb60b55e 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc7280.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc7280.c
@@ -1505,7 +1505,7 @@ static struct platform_driver sc7280_pinctrl_driver = {
 		.of_match_table = sc7280_pinctrl_of_match,
 	},
 	.probe = sc7280_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sc7280_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sc8180x.c b/drivers/pinctrl/qcom/pinctrl-sc8180x.c
index cfa7c8be9770c..d6a79ad41a40a 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc8180x.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc8180x.c
@@ -1720,7 +1720,7 @@ static struct platform_driver sc8180x_pinctrl_driver = {
 		.acpi_match_table = sc8180x_pinctrl_acpi_match,
 	},
 	.probe = sc8180x_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sc8180x_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sc8280xp-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sc8280xp-lpass-lpi.c
index c0369baf33989..0e839b6aaaf4b 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc8280xp-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc8280xp-lpass-lpi.c
@@ -179,7 +179,7 @@ static struct platform_driver lpi_pinctrl_driver = {
 		   .of_match_table = lpi_pinctrl_of_match,
 	},
 	.probe = lpi_pinctrl_probe,
-	.remove_new = lpi_pinctrl_remove,
+	.remove = lpi_pinctrl_remove,
 };
 
 module_platform_driver(lpi_pinctrl_driver);
diff --git a/drivers/pinctrl/qcom/pinctrl-sc8280xp.c b/drivers/pinctrl/qcom/pinctrl-sc8280xp.c
index 4b1c49697698d..96f4fb5a5d297 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc8280xp.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc8280xp.c
@@ -1926,7 +1926,7 @@ static struct platform_driver sc8280xp_pinctrl_driver = {
 		.of_match_table = sc8280xp_pinctrl_of_match,
 	},
 	.probe = sc8280xp_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sc8280xp_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdm660.c b/drivers/pinctrl/qcom/pinctrl-sdm660.c
index b93837c00954a..907e4ffca5e7d 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdm660.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdm660.c
@@ -1442,7 +1442,7 @@ static struct platform_driver sdm660_pinctrl_driver = {
 		.of_match_table = sdm660_pinctrl_of_match,
 	},
 	.probe = sdm660_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sdm660_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdm670.c b/drivers/pinctrl/qcom/pinctrl-sdm670.c
index 894c042cb5249..c76183ba95e17 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdm670.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdm670.c
@@ -1337,7 +1337,7 @@ static struct platform_driver sdm670_pinctrl_driver = {
 		.of_match_table = sdm670_pinctrl_of_match,
 	},
 	.probe = sdm670_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sdm670_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdm845.c b/drivers/pinctrl/qcom/pinctrl-sdm845.c
index 3f3265e0018d6..cc05c415ed155 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdm845.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdm845.c
@@ -1351,7 +1351,7 @@ static struct platform_driver sdm845_pinctrl_driver = {
 		.acpi_match_table = ACPI_PTR(sdm845_pinctrl_acpi_match),
 	},
 	.probe = sdm845_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sdm845_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdx55.c b/drivers/pinctrl/qcom/pinctrl-sdx55.c
index c88b8bfcacb6a..8826db9d21d04 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdx55.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdx55.c
@@ -990,7 +990,7 @@ static struct platform_driver sdx55_pinctrl_driver = {
 		.of_match_table = sdx55_pinctrl_of_match,
 	},
 	.probe = sdx55_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sdx55_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdx65.c b/drivers/pinctrl/qcom/pinctrl-sdx65.c
index bd44ec0fcab43..f6f319c997fc7 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdx65.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdx65.c
@@ -939,7 +939,7 @@ static struct platform_driver sdx65_pinctrl_driver = {
 		.of_match_table = sdx65_pinctrl_of_match,
 	},
 	.probe = sdx65_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sdx65_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdx75.c b/drivers/pinctrl/qcom/pinctrl-sdx75.c
index 396f6fc779a2e..3cfe8c7f04df8 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdx75.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdx75.c
@@ -1124,7 +1124,7 @@ static struct platform_driver sdx75_pinctrl_driver = {
 		.of_match_table = sdx75_pinctrl_of_match,
 	},
 	.probe = sdx75_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sdx75_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm4250-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm4250-lpass-lpi.c
index 2d2c636a3e207..c0e178be9cfc3 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm4250-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm4250-lpass-lpi.c
@@ -227,7 +227,7 @@ static struct platform_driver lpi_pinctrl_driver = {
 		.of_match_table = lpi_pinctrl_of_match,
 	},
 	.probe = lpi_pinctrl_probe,
-	.remove_new = lpi_pinctrl_remove,
+	.remove = lpi_pinctrl_remove,
 };
 
 module_platform_driver(lpi_pinctrl_driver);
diff --git a/drivers/pinctrl/qcom/pinctrl-sm4450.c b/drivers/pinctrl/qcom/pinctrl-sm4450.c
index 27317b86d8359..622f20e6f6f85 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm4450.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm4450.c
@@ -994,7 +994,7 @@ static struct platform_driver sm4450_tlmm_driver = {
 		.of_match_table = sm4450_tlmm_of_match,
 	},
 	.probe = sm4450_tlmm_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 MODULE_DEVICE_TABLE(of, sm4450_tlmm_of_match);
 
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6115-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm6115-lpass-lpi.c
index 316d6fc69131b..b7d9186861a2f 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6115-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6115-lpass-lpi.c
@@ -147,7 +147,7 @@ static struct platform_driver lpi_pinctrl_driver = {
 		.of_match_table = lpi_pinctrl_of_match,
 	},
 	.probe = lpi_pinctrl_probe,
-	.remove_new = lpi_pinctrl_remove,
+	.remove = lpi_pinctrl_remove,
 };
 
 module_platform_driver(lpi_pinctrl_driver);
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6115.c b/drivers/pinctrl/qcom/pinctrl-sm6115.c
index 7ce04144b6ed3..4e91c75ad9524 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6115.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6115.c
@@ -907,7 +907,7 @@ static struct platform_driver sm6115_tlmm_driver = {
 		.of_match_table = sm6115_tlmm_of_match,
 	},
 	.probe = sm6115_tlmm_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm6115_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6125.c b/drivers/pinctrl/qcom/pinctrl-sm6125.c
index 65de34c307594..c188842047aae 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6125.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6125.c
@@ -1266,7 +1266,7 @@ static struct platform_driver sm6125_tlmm_driver = {
 		.of_match_table = sm6125_tlmm_of_match,
 	},
 	.probe = sm6125_tlmm_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm6125_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6350.c b/drivers/pinctrl/qcom/pinctrl-sm6350.c
index 4aeb1ba43ee3d..f3828c07b1345 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6350.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6350.c
@@ -1373,7 +1373,7 @@ static struct platform_driver sm6350_tlmm_driver = {
 		.of_match_table = sm6350_tlmm_of_match,
 	},
 	.probe = sm6350_tlmm_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm6350_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6375.c b/drivers/pinctrl/qcom/pinctrl-sm6375.c
index d86630d7125c2..c82c8516932ea 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6375.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6375.c
@@ -1516,7 +1516,7 @@ static struct platform_driver sm6375_tlmm_driver = {
 		.of_match_table = sm6375_tlmm_of_match,
 	},
 	.probe = sm6375_tlmm_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm6375_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm7150.c b/drivers/pinctrl/qcom/pinctrl-sm7150.c
index 095a1ca758490..3c7fd8af6635b 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm7150.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm7150.c
@@ -1255,7 +1255,7 @@ static struct platform_driver sm7150_tlmm_driver = {
 		.of_match_table = sm7150_tlmm_of_match,
 	},
 	.probe = sm7150_tlmm_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm7150_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8150.c b/drivers/pinctrl/qcom/pinctrl-sm8150.c
index f8f5bee74f1dc..01aea9c70b7a7 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8150.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8150.c
@@ -1542,7 +1542,7 @@ static struct platform_driver sm8150_pinctrl_driver = {
 		.of_match_table = sm8150_pinctrl_of_match,
 	},
 	.probe = sm8150_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm8150_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c
index 9791d9ba5087c..64494a86490e2 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c
@@ -140,7 +140,7 @@ static struct platform_driver lpi_pinctrl_driver = {
 		   .of_match_table = lpi_pinctrl_of_match,
 	},
 	.probe = lpi_pinctrl_probe,
-	.remove_new = lpi_pinctrl_remove,
+	.remove = lpi_pinctrl_remove,
 };
 
 module_platform_driver(lpi_pinctrl_driver);
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250.c b/drivers/pinctrl/qcom/pinctrl-sm8250.c
index 54fda77bf2968..e9961a49ff981 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8250.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8250.c
@@ -1351,7 +1351,7 @@ static struct platform_driver sm8250_pinctrl_driver = {
 		.of_match_table = sm8250_pinctrl_of_match,
 	},
 	.probe = sm8250_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm8250_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c
index 5b9a2cb216bd8..7b146b4acfdf4 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c
@@ -142,7 +142,7 @@ static struct platform_driver lpi_pinctrl_driver = {
 		   .of_match_table = lpi_pinctrl_of_match,
 	},
 	.probe = lpi_pinctrl_probe,
-	.remove_new = lpi_pinctrl_remove,
+	.remove = lpi_pinctrl_remove,
 };
 module_platform_driver(lpi_pinctrl_driver);
 
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8350.c b/drivers/pinctrl/qcom/pinctrl-sm8350.c
index ac7f2820f2cbf..9c69458bd9109 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8350.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8350.c
@@ -1642,7 +1642,7 @@ static struct platform_driver sm8350_tlmm_driver = {
 		.of_match_table = sm8350_tlmm_of_match,
 	},
 	.probe = sm8350_tlmm_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm8350_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8450-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8450-lpass-lpi.c
index a028cbb499472..439f6541622e9 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8450-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8450-lpass-lpi.c
@@ -208,7 +208,7 @@ static struct platform_driver lpi_pinctrl_driver = {
 		   .of_match_table = lpi_pinctrl_of_match,
 	},
 	.probe = lpi_pinctrl_probe,
-	.remove_new = lpi_pinctrl_remove,
+	.remove = lpi_pinctrl_remove,
 };
 
 module_platform_driver(lpi_pinctrl_driver);
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8450.c b/drivers/pinctrl/qcom/pinctrl-sm8450.c
index 6172867116952..d11bb1ee9e3d8 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8450.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8450.c
@@ -1677,7 +1677,7 @@ static struct platform_driver sm8450_tlmm_driver = {
 		.of_match_table = sm8450_tlmm_of_match,
 	},
 	.probe = sm8450_tlmm_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm8450_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c
index 852192b044e17..73065919c8c26 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c
@@ -216,7 +216,7 @@ static struct platform_driver lpi_pinctrl_driver = {
 		   .of_match_table = lpi_pinctrl_of_match,
 	},
 	.probe = lpi_pinctrl_probe,
-	.remove_new = lpi_pinctrl_remove,
+	.remove = lpi_pinctrl_remove,
 };
 
 module_platform_driver(lpi_pinctrl_driver);
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8550.c b/drivers/pinctrl/qcom/pinctrl-sm8550.c
index 9184e0183755d..3c847d9cb5d93 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8550.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8550.c
@@ -1762,7 +1762,7 @@ static struct platform_driver sm8550_tlmm_driver = {
 		.of_match_table = sm8550_tlmm_of_match,
 	},
 	.probe = sm8550_tlmm_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm8550_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c
index 04400c832327a..f9fcedf5a65d7 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c
@@ -223,7 +223,7 @@ static struct platform_driver lpi_pinctrl_driver = {
 		   .of_match_table = lpi_pinctrl_of_match,
 	},
 	.probe = lpi_pinctrl_probe,
-	.remove_new = lpi_pinctrl_remove,
+	.remove = lpi_pinctrl_remove,
 };
 
 module_platform_driver(lpi_pinctrl_driver);
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8650.c b/drivers/pinctrl/qcom/pinctrl-sm8650.c
index adaddd728662f..104708252d12a 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8650.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8650.c
@@ -1742,7 +1742,7 @@ static struct platform_driver sm8650_tlmm_driver = {
 		.of_match_table = sm8650_tlmm_of_match,
 	},
 	.probe = sm8650_tlmm_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm8650_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
index d2dd66769aa89..c33af2d667784 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
@@ -1268,7 +1268,7 @@ static struct platform_driver pmic_gpio_driver = {
 		   .of_match_table = pmic_gpio_of_match,
 	},
 	.probe	= pmic_gpio_probe,
-	.remove_new = pmic_gpio_remove,
+	.remove = pmic_gpio_remove,
 };
 
 module_platform_driver(pmic_gpio_driver);
diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
index d16ece90d926c..b5b3ac82f030b 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
@@ -1000,7 +1000,7 @@ static struct platform_driver pmic_mpp_driver = {
 		   .of_match_table = pmic_mpp_of_match,
 	},
 	.probe	= pmic_mpp_probe,
-	.remove_new = pmic_mpp_remove,
+	.remove = pmic_mpp_remove,
 };
 
 module_platform_driver(pmic_mpp_driver);
diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
index 9cd5247ea5742..b750ff4db4c3e 100644
--- a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
@@ -866,7 +866,7 @@ static struct platform_driver pm8xxx_gpio_driver = {
 		.of_match_table = pm8xxx_gpio_of_match,
 	},
 	.probe = pm8xxx_gpio_probe,
-	.remove_new = pm8xxx_gpio_remove,
+	.remove = pm8xxx_gpio_remove,
 };
 
 module_platform_driver(pm8xxx_gpio_driver);
diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
index 3aee6835a2de0..9b1039c08aa6d 100644
--- a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
+++ b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
@@ -949,7 +949,7 @@ static struct platform_driver pm8xxx_mpp_driver = {
 		.of_match_table = pm8xxx_mpp_of_match,
 	},
 	.probe = pm8xxx_mpp_probe,
-	.remove_new = pm8xxx_mpp_remove,
+	.remove = pm8xxx_mpp_remove,
 };
 
 module_platform_driver(pm8xxx_mpp_driver);
diff --git a/drivers/pinctrl/qcom/pinctrl-x1e80100.c b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
index abfcdd3da9e82..419cb8facb2f3 100644
--- a/drivers/pinctrl/qcom/pinctrl-x1e80100.c
+++ b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
@@ -1861,7 +1861,7 @@ static struct platform_driver x1e80100_pinctrl_driver = {
 		.of_match_table = x1e80100_pinctrl_of_match,
 	},
 	.probe = x1e80100_pinctrl_probe,
-	.remove_new = msm_pinctrl_remove,
+	.remove = msm_pinctrl_remove,
 };
 
 static int __init x1e80100_pinctrl_init(void)
diff --git a/drivers/pinctrl/renesas/pinctrl-rzn1.c b/drivers/pinctrl/renesas/pinctrl-rzn1.c
index 39af1fe79c846..d442d4f9981c9 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzn1.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzn1.c
@@ -925,7 +925,7 @@ MODULE_DEVICE_TABLE(of, rzn1_pinctrl_match);
 
 static struct platform_driver rzn1_pinctrl_driver = {
 	.probe	= rzn1_pinctrl_probe,
-	.remove_new = rzn1_pinctrl_remove,
+	.remove = rzn1_pinctrl_remove,
 	.driver	= {
 		.name		= "rzn1-pinctrl",
 		.of_match_table	= rzn1_pinctrl_match,
diff --git a/drivers/pinctrl/sprd/pinctrl-sprd-sc9860.c b/drivers/pinctrl/sprd/pinctrl-sprd-sc9860.c
index 9c3c39dc6550c..d14f382f2392c 100644
--- a/drivers/pinctrl/sprd/pinctrl-sprd-sc9860.c
+++ b/drivers/pinctrl/sprd/pinctrl-sprd-sc9860.c
@@ -943,7 +943,7 @@ static struct platform_driver sprd_pinctrl_driver = {
 		.of_match_table = sprd_pinctrl_of_match,
 	},
 	.probe = sprd_pinctrl_probe,
-	.remove_new = sprd_pinctrl_remove,
+	.remove = sprd_pinctrl_remove,
 	.shutdown = sprd_pinctrl_shutdown,
 };
 module_platform_driver(sprd_pinctrl_driver);

From d7eac9379f2198c4bd6a2e69eb8b38c82bb2fd5c Mon Sep 17 00:00:00 2001
From: Marc Ferland <marc.ferland@sonatest.com>
Date: Wed, 9 Oct 2024 11:12:49 -0400
Subject: [PATCH 0292/1530] pinctrl: amd: Fix two small typos

Found those two while reading the code:

EDGE_TRAGGER -> EDGE_TRIGGER
BOTH_EADGE -> BOTH_EDGES

No functional changes, compile tested only.

Signed-off-by: Marc Ferland <marc.ferland@sonatest.com>
Link: https://lore.kernel.org/20241009151249.2086702-1-marc.ferland@sonatest.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-amd.c | 2 +-
 drivers/pinctrl/pinctrl-amd.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index b0fab262d534d..fff6d4209ad57 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -506,7 +506,7 @@ static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	case IRQ_TYPE_EDGE_BOTH:
 		pin_reg &= ~BIT(LEVEL_TRIG_OFF);
 		pin_reg &= ~(ACTIVE_LEVEL_MASK << ACTIVE_LEVEL_OFF);
-		pin_reg |= BOTH_EADGE << ACTIVE_LEVEL_OFF;
+		pin_reg |= BOTH_EDGES << ACTIVE_LEVEL_OFF;
 		irq_set_handler_locked(d, handle_edge_irq);
 		break;
 
diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h
index cf59089f27763..667be49c3f48d 100644
--- a/drivers/pinctrl/pinctrl-amd.h
+++ b/drivers/pinctrl/pinctrl-amd.h
@@ -60,12 +60,12 @@
 #define DB_TYPE_PRESERVE_HIGH_GLITCH      0x2UL
 #define DB_TYPE_REMOVE_GLITCH             0x3UL
 
-#define EDGE_TRAGGER	0x0UL
+#define EDGE_TRIGGER	0x0UL
 #define LEVEL_TRIGGER	0x1UL
 
 #define ACTIVE_HIGH	0x0UL
 #define ACTIVE_LOW	0x1UL
-#define BOTH_EADGE	0x2UL
+#define BOTH_EDGES	0x2UL
 
 #define ENABLE_INTERRUPT	0x1UL
 #define DISABLE_INTERRUPT	0x0UL

From ca3c342fb3c76eee739a1cfc4ff59841722ebee7 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Sat, 12 Oct 2024 20:32:41 +0900
Subject: [PATCH 0293/1530] PCI: endpoint: Introduce
 pci_epc_function_is_valid()

Introduce the epc core helper function pci_epc_function_is_valid() to
verify that an epc pointer, a physical function number and a virtual
function number are all valid. This avoids repeating the code pattern:

if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions)
	return err;

if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no]))
	return err;

in many functions of the endpoint controller core code.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Link: https://lore.kernel.org/r/20241012113246.95634-2-dlemoal@kernel.org
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/endpoint/pci-epc-core.c | 79 +++++++++++------------------
 1 file changed, 31 insertions(+), 48 deletions(-)

diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index 17f0071092550..b854f1bab26f8 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -128,6 +128,18 @@ enum pci_barno pci_epc_get_next_free_bar(const struct pci_epc_features
 }
 EXPORT_SYMBOL_GPL(pci_epc_get_next_free_bar);
 
+static bool pci_epc_function_is_valid(struct pci_epc *epc,
+				      u8 func_no, u8 vfunc_no)
+{
+	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions)
+		return false;
+
+	if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no]))
+		return false;
+
+	return true;
+}
+
 /**
  * pci_epc_get_features() - get the features supported by EPC
  * @epc: the features supported by *this* EPC device will be returned
@@ -145,10 +157,7 @@ const struct pci_epc_features *pci_epc_get_features(struct pci_epc *epc,
 {
 	const struct pci_epc_features *epc_features;
 
-	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions)
-		return NULL;
-
-	if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no]))
+	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return NULL;
 
 	if (!epc->ops->get_features)
@@ -218,10 +227,7 @@ int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	int ret;
 
-	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions)
-		return -EINVAL;
-
-	if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no]))
+	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return -EINVAL;
 
 	if (!epc->ops->raise_irq)
@@ -262,10 +268,7 @@ int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	int ret;
 
-	if (IS_ERR_OR_NULL(epc))
-		return -EINVAL;
-
-	if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no]))
+	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return -EINVAL;
 
 	if (!epc->ops->map_msi_irq)
@@ -293,10 +296,7 @@ int pci_epc_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 {
 	int interrupt;
 
-	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions)
-		return 0;
-
-	if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no]))
+	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return 0;
 
 	if (!epc->ops->get_msi)
@@ -329,11 +329,10 @@ int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u8 interrupts)
 	int ret;
 	u8 encode_int;
 
-	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions ||
-	    interrupts < 1 || interrupts > 32)
+	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return -EINVAL;
 
-	if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no]))
+	if (interrupts < 1 || interrupts > 32)
 		return -EINVAL;
 
 	if (!epc->ops->set_msi)
@@ -361,10 +360,7 @@ int pci_epc_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 {
 	int interrupt;
 
-	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions)
-		return 0;
-
-	if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no]))
+	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return 0;
 
 	if (!epc->ops->get_msix)
@@ -397,11 +393,10 @@ int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	int ret;
 
-	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions ||
-	    interrupts < 1 || interrupts > 2048)
+	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return -EINVAL;
 
-	if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no]))
+	if (interrupts < 1 || interrupts > 2048)
 		return -EINVAL;
 
 	if (!epc->ops->set_msix)
@@ -428,10 +423,7 @@ EXPORT_SYMBOL_GPL(pci_epc_set_msix);
 void pci_epc_unmap_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			phys_addr_t phys_addr)
 {
-	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions)
-		return;
-
-	if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no]))
+	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return;
 
 	if (!epc->ops->unmap_addr)
@@ -459,10 +451,7 @@ int pci_epc_map_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	int ret;
 
-	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions)
-		return -EINVAL;
-
-	if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no]))
+	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return -EINVAL;
 
 	if (!epc->ops->map_addr)
@@ -489,12 +478,11 @@ EXPORT_SYMBOL_GPL(pci_epc_map_addr);
 void pci_epc_clear_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 		       struct pci_epf_bar *epf_bar)
 {
-	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions ||
-	    (epf_bar->barno == BAR_5 &&
-	     epf_bar->flags & PCI_BASE_ADDRESS_MEM_TYPE_64))
+	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return;
 
-	if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no]))
+	if (epf_bar->barno == BAR_5 &&
+	    epf_bar->flags & PCI_BASE_ADDRESS_MEM_TYPE_64)
 		return;
 
 	if (!epc->ops->clear_bar)
@@ -521,18 +509,16 @@ int pci_epc_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	int ret;
 	int flags = epf_bar->flags;
 
-	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions ||
-	    (epf_bar->barno == BAR_5 &&
-	     flags & PCI_BASE_ADDRESS_MEM_TYPE_64) ||
+	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
+		return -EINVAL;
+
+	if ((epf_bar->barno == BAR_5 && flags & PCI_BASE_ADDRESS_MEM_TYPE_64) ||
 	    (flags & PCI_BASE_ADDRESS_SPACE_IO &&
 	     flags & PCI_BASE_ADDRESS_IO_MASK) ||
 	    (upper_32_bits(epf_bar->size) &&
 	     !(flags & PCI_BASE_ADDRESS_MEM_TYPE_64)))
 		return -EINVAL;
 
-	if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no]))
-		return -EINVAL;
-
 	if (!epc->ops->set_bar)
 		return 0;
 
@@ -561,10 +547,7 @@ int pci_epc_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	int ret;
 
-	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions)
-		return -EINVAL;
-
-	if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no]))
+	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return -EINVAL;
 
 	/* Only Virtual Function #1 has deviceID */

From 2314c6ffe8113ac3c22c8112fa9623e30eec6c4a Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Sat, 12 Oct 2024 20:32:42 +0900
Subject: [PATCH 0294/1530] PCI: endpoint: Improve pci_epc_mem_alloc_addr()

There is no point in attempting to allocate memory from an endpoint
controller memory window if the requested size is larger than the memory
window size. Add a check to skip bitmap_find_free_region() calls for
such case. This check can be done without the mem->lock mutex held as
memory window sizes are constant and never modified at runtime.
Also change the final return to return NULL to simplify the code.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20241012113246.95634-3-dlemoal@kernel.org
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/endpoint/pci-epc-mem.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/endpoint/pci-epc-mem.c b/drivers/pci/endpoint/pci-epc-mem.c
index a9c028f58da17..218a60e945db6 100644
--- a/drivers/pci/endpoint/pci-epc-mem.c
+++ b/drivers/pci/endpoint/pci-epc-mem.c
@@ -178,7 +178,7 @@ EXPORT_SYMBOL_GPL(pci_epc_mem_exit);
 void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc,
 				     phys_addr_t *phys_addr, size_t size)
 {
-	void __iomem *virt_addr = NULL;
+	void __iomem *virt_addr;
 	struct pci_epc_mem *mem;
 	unsigned int page_shift;
 	size_t align_size;
@@ -188,10 +188,13 @@ void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc,
 
 	for (i = 0; i < epc->num_windows; i++) {
 		mem = epc->windows[i];
-		mutex_lock(&mem->lock);
+		if (size > mem->window.size)
+			continue;
+
 		align_size = ALIGN(size, mem->window.page_size);
 		order = pci_epc_mem_get_order(mem, align_size);
 
+		mutex_lock(&mem->lock);
 		pageno = bitmap_find_free_region(mem->bitmap, mem->pages,
 						 order);
 		if (pageno >= 0) {
@@ -211,7 +214,7 @@ void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc,
 		mutex_unlock(&mem->lock);
 	}
 
-	return virt_addr;
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(pci_epc_mem_alloc_addr);
 

From 86efc62d031307e53ad4011e0aa8898e029cef47 Mon Sep 17 00:00:00 2001
From: Gregory Price <gourry@gourry.net>
Date: Fri, 4 Oct 2024 12:28:28 -0400
Subject: [PATCH 0295/1530] PCI/DOE: Poll DOE Busy bit for up to 1 second in
 pci_doe_send_req()

During initial device probe, the PCI DOE busy bit for some CXL devices may
be left set for a longer period than expected by the current driver logic.
Despite local comments stating DOE Busy is unlikely to be detected, it
appears commonly specifically during boot when CXL devices are being
probed.

The symptom was messages like this:

  endpoint6: DOE failed -EBUSY

produced by cxl_cdat_get_length() or cxl_cdat_read_table().

This was observed on a single socket AMD platform with 2 CXL memory
expanders attached to the single socket. It was not the case that
concurrent accesses were being made, as validated by monitoring mailbox
commands on the device side.

This behavior has been observed with multiple CXL memory expanders from
different vendors - so it appears unrelated to the model.

In all observed tests, only a small period of the retry window is actually
used - typically only a handful of loop iterations.

Polling on the PCI DOE Busy Bit for (at max) one PCI DOE timeout interval
(1 second), resolves this issue cleanly.

Per PCIe r6.2 sec 6.30.3, the DOE Busy Bit being cleared does not raise an
interrupt, so polling is the best option in this scenario.

Subsequent code in doe_statemachine_work() and abort paths also wait for up
to 1 PCI DOE timeout interval, so this order of (potential) additional
delay is presumed acceptable.

Suggested-by: Lukas Wunner <lukas@wunner.de>
Link: https://lore.kernel.org/r/20241004162828.314-1-gourry@gourry.net
Signed-off-by: Gregory Price <gourry@gourry.net>
[bhelgaas: fix nits and add error message to commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Lukas Wunner <lukas@wunner.de>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/doe.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c
index 652d63df9d22e..7bd7892c52228 100644
--- a/drivers/pci/doe.c
+++ b/drivers/pci/doe.c
@@ -146,6 +146,7 @@ static int pci_doe_send_req(struct pci_doe_mb *doe_mb,
 {
 	struct pci_dev *pdev = doe_mb->pdev;
 	int offset = doe_mb->cap_offset;
+	unsigned long timeout_jiffies;
 	size_t length, remainder;
 	u32 val;
 	int i;
@@ -155,8 +156,19 @@ static int pci_doe_send_req(struct pci_doe_mb *doe_mb,
 	 * someone other than Linux (e.g. firmware) is using the mailbox. Note
 	 * it is expected that firmware and OS will negotiate access rights via
 	 * an, as yet to be defined, method.
+	 *
+	 * Wait up to one PCI_DOE_TIMEOUT period to allow the prior command to
+	 * finish. Otherwise, simply error out as unable to field the request.
+	 *
+	 * PCIe r6.2 sec 6.30.3 states no interrupt is raised when the DOE Busy
+	 * bit is cleared, so polling here is our best option for the moment.
 	 */
-	pci_read_config_dword(pdev, offset + PCI_DOE_STATUS, &val);
+	timeout_jiffies = jiffies + PCI_DOE_TIMEOUT;
+	do {
+		pci_read_config_dword(pdev, offset + PCI_DOE_STATUS, &val);
+	} while (FIELD_GET(PCI_DOE_STATUS_BUSY, val) &&
+		 !time_after(jiffies, timeout_jiffies));
+
 	if (FIELD_GET(PCI_DOE_STATUS_BUSY, val))
 		return -EBUSY;
 

From 9d75b70061917fbfe3247e2594879e5a14d3e24a Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 4 Oct 2024 13:36:57 +0100
Subject: [PATCH 0296/1530] pinctrl: renesas: rzg2l: Add support for
 enabling/disabling open-drain outputs

Add support for enabling and disabling open-drain outputs.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Link: https://lore.kernel.org/20241004123658.764557-3-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rzg2l.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index 0a32d692628c4..8fbb27248160b 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -139,6 +139,7 @@
 #define IEN(off)		(0x1800 + (off) * 8)
 #define PUPD(off)		(0x1C00 + (off) * 8)
 #define ISEL(off)		(0x2C00 + (off) * 8)
+#define NOD(off)		(0x3000 + (off) * 8)
 #define SD_CH(off, ch)		((off) + (ch) * 4)
 #define ETH_POC(off, ch)	((off) + (ch) * 4)
 #define QSPI			(0x3008)
@@ -160,6 +161,7 @@
 #define IOLH_MASK		0x03
 #define SR_MASK			0x01
 #define PUPD_MASK		0x03
+#define NOD_MASK		0x01
 
 #define PM_INPUT		0x1
 #define PM_OUTPUT		0x2
@@ -1338,6 +1340,18 @@ static int rzg2l_pinctrl_pinconf_get(struct pinctrl_dev *pctldev,
 		break;
 	}
 
+	case PIN_CONFIG_DRIVE_OPEN_DRAIN:
+	case PIN_CONFIG_DRIVE_PUSH_PULL:
+		if (!(cfg & PIN_CFG_NOD))
+			return -EINVAL;
+
+		arg = rzg2l_read_pin_config(pctrl, NOD(off), bit, NOD_MASK);
+		if (!arg && param != PIN_CONFIG_DRIVE_PUSH_PULL)
+			return -EINVAL;
+		if (arg && param != PIN_CONFIG_DRIVE_OPEN_DRAIN)
+			return -EINVAL;
+		break;
+
 	case RENESAS_RZV2H_PIN_CONFIG_OUTPUT_IMPEDANCE:
 		if (!(cfg & PIN_CFG_IOLH_RZV2H))
 			return -EINVAL;
@@ -1467,6 +1481,15 @@ static int rzg2l_pinctrl_pinconf_set(struct pinctrl_dev *pctldev,
 			rzg2l_rmw_pin_config(pctrl, IOLH(off), bit, IOLH_MASK, index);
 			break;
 
+		case PIN_CONFIG_DRIVE_OPEN_DRAIN:
+		case PIN_CONFIG_DRIVE_PUSH_PULL:
+			if (!(cfg & PIN_CFG_NOD))
+				return -EINVAL;
+
+			rzg2l_rmw_pin_config(pctrl, NOD(off), bit, NOD_MASK,
+					     param == PIN_CONFIG_DRIVE_OPEN_DRAIN ? 1 : 0);
+			break;
+
 		case RENESAS_RZV2H_PIN_CONFIG_OUTPUT_IMPEDANCE:
 			if (!(cfg & PIN_CFG_IOLH_RZV2H))
 				return -EINVAL;

From 725933a54f718af5362ec39971b2933d8bdf6994 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 4 Oct 2024 13:36:58 +0100
Subject: [PATCH 0297/1530] pinctrl: renesas: rzg2l: Add support for
 configuring schmitt-trigger

Add support for configuring the multiplexed pins as schmitt-trigger
inputs.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Link: https://lore.kernel.org/20241004123658.764557-4-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rzg2l.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index 8fbb27248160b..5eefbace7d912 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -140,6 +140,7 @@
 #define PUPD(off)		(0x1C00 + (off) * 8)
 #define ISEL(off)		(0x2C00 + (off) * 8)
 #define NOD(off)		(0x3000 + (off) * 8)
+#define SMT(off)		(0x3400 + (off) * 8)
 #define SD_CH(off, ch)		((off) + (ch) * 4)
 #define ETH_POC(off, ch)	((off) + (ch) * 4)
 #define QSPI			(0x3008)
@@ -162,6 +163,7 @@
 #define SR_MASK			0x01
 #define PUPD_MASK		0x03
 #define NOD_MASK		0x01
+#define SMT_MASK		0x01
 
 #define PM_INPUT		0x1
 #define PM_OUTPUT		0x2
@@ -1352,6 +1354,15 @@ static int rzg2l_pinctrl_pinconf_get(struct pinctrl_dev *pctldev,
 			return -EINVAL;
 		break;
 
+	case PIN_CONFIG_INPUT_SCHMITT_ENABLE:
+		if (!(cfg & PIN_CFG_SMT))
+			return -EINVAL;
+
+		arg = rzg2l_read_pin_config(pctrl, SMT(off), bit, SMT_MASK);
+		if (!arg)
+			return -EINVAL;
+		break;
+
 	case RENESAS_RZV2H_PIN_CONFIG_OUTPUT_IMPEDANCE:
 		if (!(cfg & PIN_CFG_IOLH_RZV2H))
 			return -EINVAL;
@@ -1490,6 +1501,13 @@ static int rzg2l_pinctrl_pinconf_set(struct pinctrl_dev *pctldev,
 					     param == PIN_CONFIG_DRIVE_OPEN_DRAIN ? 1 : 0);
 			break;
 
+		case PIN_CONFIG_INPUT_SCHMITT_ENABLE:
+			if (!(cfg & PIN_CFG_SMT))
+				return -EINVAL;
+
+			rzg2l_rmw_pin_config(pctrl, SMT(off), bit, SMT_MASK, arg);
+			break;
+
 		case RENESAS_RZV2H_PIN_CONFIG_OUTPUT_IMPEDANCE:
 			if (!(cfg & PIN_CFG_IOLH_RZV2H))
 				return -EINVAL;

From 5dcde519a067ac5c85c273e550dde1873e2199bf Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Thu, 10 Oct 2024 14:27:26 +0100
Subject: [PATCH 0298/1530] pinctrl: renesas: Select PINCTRL_RZG2L for
 RZ/V2H(P) SoC

Add explicit selection of the PINCTRL_RZG2L config option for the
RZ/V2H(P) (R9A09G057) SoC, ensuring pin control driver is enabled
for this SoC.

Fixes: 9bd95ac86e70 ("pinctrl: renesas: rzg2l: Add support for RZ/V2H SoC")
Reported-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/20241010132726.702658-1-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/renesas/Kconfig b/drivers/pinctrl/renesas/Kconfig
index 14bd55d647319..7f3f41c7fe54c 100644
--- a/drivers/pinctrl/renesas/Kconfig
+++ b/drivers/pinctrl/renesas/Kconfig
@@ -41,6 +41,7 @@ config PINCTRL_RENESAS
 	select PINCTRL_PFC_R8A779H0 if ARCH_R8A779H0
 	select PINCTRL_RZG2L if ARCH_RZG2L
 	select PINCTRL_RZV2M if ARCH_R9A09G011
+	select PINCTRL_RZG2L if ARCH_R9A09G057
 	select PINCTRL_PFC_SH7203 if CPU_SUBTYPE_SH7203
 	select PINCTRL_PFC_SH7264 if CPU_SUBTYPE_SH7264
 	select PINCTRL_PFC_SH7269 if CPU_SUBTYPE_SH7269

From b7a084ba4fbb8f416ce8d19c93a3a2bee63c9c89 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:05 +0200
Subject: [PATCH 0299/1530] rust: alloc: add `Allocator` trait

Add a kernel specific `Allocator` trait, that in contrast to the one in
Rust's core library doesn't require unstable features and supports GFP
flags.

Subsequent patches add the following trait implementors: `Kmalloc`,
`Vmalloc` and `KVmalloc`.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-2-dakr@kernel.org
[ Fixed typo. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc.rs | 101 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 101 insertions(+)

diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index 1966bd4070174..998779cc69769 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -11,6 +11,7 @@ pub mod vec_ext;
 /// Indicates an allocation error.
 #[derive(Copy, Clone, PartialEq, Eq, Debug)]
 pub struct AllocError;
+use core::{alloc::Layout, ptr::NonNull};
 
 /// Flags to be used when allocating memory.
 ///
@@ -86,3 +87,103 @@ pub mod flags {
     /// small allocations.
     pub const GFP_NOWAIT: Flags = Flags(bindings::GFP_NOWAIT);
 }
+
+/// The kernel's [`Allocator`] trait.
+///
+/// An implementation of [`Allocator`] can allocate, re-allocate and free memory buffers described
+/// via [`Layout`].
+///
+/// [`Allocator`] is designed to be implemented as a ZST; [`Allocator`] functions do not operate on
+/// an object instance.
+///
+/// In order to be able to support `#[derive(SmartPointer)]` later on, we need to avoid a design
+/// that requires an `Allocator` to be instantiated, hence its functions must not contain any kind
+/// of `self` parameter.
+///
+/// # Safety
+///
+/// - A memory allocation returned from an allocator must remain valid until it is explicitly freed.
+///
+/// - Any pointer to a valid memory allocation must be valid to be passed to any other [`Allocator`]
+///   function of the same type.
+///
+/// - Implementers must ensure that all trait functions abide by the guarantees documented in the
+///   `# Guarantees` sections.
+pub unsafe trait Allocator {
+    /// Allocate memory based on `layout` and `flags`.
+    ///
+    /// On success, returns a buffer represented as `NonNull<[u8]>` that satisfies the layout
+    /// constraints (i.e. minimum size and alignment as specified by `layout`).
+    ///
+    /// This function is equivalent to `realloc` when called with `None`.
+    ///
+    /// # Guarantees
+    ///
+    /// When the return value is `Ok(ptr)`, then `ptr` is
+    /// - valid for reads and writes for `layout.size()` bytes, until it is passed to
+    ///   [`Allocator::free`] or [`Allocator::realloc`],
+    /// - aligned to `layout.align()`,
+    ///
+    /// Additionally, `Flags` are honored as documented in
+    /// <https://docs.kernel.org/core-api/mm-api.html#mm-api-gfp-flags>.
+    fn alloc(layout: Layout, flags: Flags) -> Result<NonNull<[u8]>, AllocError> {
+        // SAFETY: Passing `None` to `realloc` is valid by its safety requirements and asks for a
+        // new memory allocation.
+        unsafe { Self::realloc(None, layout, Layout::new::<()>(), flags) }
+    }
+
+    /// Re-allocate an existing memory allocation to satisfy the requested `layout`.
+    ///
+    /// If the requested size is zero, `realloc` behaves equivalent to `free`.
+    ///
+    /// If the requested size is larger than the size of the existing allocation, a successful call
+    /// to `realloc` guarantees that the new or grown buffer has at least `Layout::size` bytes, but
+    /// may also be larger.
+    ///
+    /// If the requested size is smaller than the size of the existing allocation, `realloc` may or
+    /// may not shrink the buffer; this is implementation specific to the allocator.
+    ///
+    /// On allocation failure, the existing buffer, if any, remains valid.
+    ///
+    /// The buffer is represented as `NonNull<[u8]>`.
+    ///
+    /// # Safety
+    ///
+    /// - If `ptr == Some(p)`, then `p` must point to an existing and valid memory allocation
+    ///   created by this [`Allocator`]; if `old_layout` is zero-sized `p` does not need to be a
+    ///   pointer returned by this [`Allocator`].
+    /// - `ptr` is allowed to be `None`; in this case a new memory allocation is created and
+    ///   `old_layout` is ignored.
+    /// - `old_layout` must match the `Layout` the allocation has been created with.
+    ///
+    /// # Guarantees
+    ///
+    /// This function has the same guarantees as [`Allocator::alloc`]. When `ptr == Some(p)`, then
+    /// it additionally guarantees that:
+    /// - the contents of the memory pointed to by `p` are preserved up to the lesser of the new
+    ///   and old size, i.e. `ret_ptr[0..min(layout.size(), old_layout.size())] ==
+    ///   p[0..min(layout.size(), old_layout.size())]`.
+    /// - when the return value is `Err(AllocError)`, then `ptr` is still valid.
+    unsafe fn realloc(
+        ptr: Option<NonNull<u8>>,
+        layout: Layout,
+        old_layout: Layout,
+        flags: Flags,
+    ) -> Result<NonNull<[u8]>, AllocError>;
+
+    /// Free an existing memory allocation.
+    ///
+    /// # Safety
+    ///
+    /// - `ptr` must point to an existing and valid memory allocation created by this [`Allocator`];
+    ///   if `old_layout` is zero-sized `p` does not need to be a pointer returned by this
+    ///   [`Allocator`].
+    /// - `layout` must match the `Layout` the allocation has been created with.
+    /// - The memory allocation at `ptr` must never again be read from or written to.
+    unsafe fn free(ptr: NonNull<u8>, layout: Layout) {
+        // SAFETY: The caller guarantees that `ptr` points at a valid allocation created by this
+        // allocator. We are passing a `Layout` with the smallest possible alignment, so it is
+        // smaller than or equal to the alignment previously used with this allocation.
+        let _ = unsafe { Self::realloc(Some(ptr), Layout::new::<()>(), layout, Flags(0)) };
+    }
+}

From a654a6e09644266e38ac05415ef7737d299c4497 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:06 +0200
Subject: [PATCH 0300/1530] rust: alloc: separate `aligned_size` from
 `krealloc_aligned`

Separate `aligned_size` from `krealloc_aligned`.

Subsequent patches implement `Allocator` derivates, such as `Kmalloc`,
that require `aligned_size` and replace the original `krealloc_aligned`.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-3-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc/allocator.rs | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/rust/kernel/alloc/allocator.rs b/rust/kernel/alloc/allocator.rs
index 91216b36af693..765f72d5bc211 100644
--- a/rust/kernel/alloc/allocator.rs
+++ b/rust/kernel/alloc/allocator.rs
@@ -8,6 +8,17 @@ use core::ptr;
 
 struct KernelAllocator;
 
+/// Returns a proper size to alloc a new object aligned to `new_layout`'s alignment.
+fn aligned_size(new_layout: Layout) -> usize {
+    // Customized layouts from `Layout::from_size_align()` can have size < align, so pad first.
+    let layout = new_layout.pad_to_align();
+
+    // Note that `layout.size()` (after padding) is guaranteed to be a multiple of `layout.align()`
+    // which together with the slab guarantees means the `krealloc` will return a properly aligned
+    // object (see comments in `kmalloc()` for more information).
+    layout.size()
+}
+
 /// Calls `krealloc` with a proper size to alloc a new object aligned to `new_layout`'s alignment.
 ///
 /// # Safety
@@ -15,13 +26,7 @@ struct KernelAllocator;
 /// - `ptr` can be either null or a pointer which has been allocated by this allocator.
 /// - `new_layout` must have a non-zero size.
 pub(crate) unsafe fn krealloc_aligned(ptr: *mut u8, new_layout: Layout, flags: Flags) -> *mut u8 {
-    // Customized layouts from `Layout::from_size_align()` can have size < align, so pad first.
-    let layout = new_layout.pad_to_align();
-
-    // Note that `layout.size()` (after padding) is guaranteed to be a multiple of `layout.align()`
-    // which together with the slab guarantees means the `krealloc` will return a properly aligned
-    // object (see comments in `kmalloc()` for more information).
-    let size = layout.size();
+    let size = aligned_size(new_layout);
 
     // SAFETY:
     // - `ptr` is either null or a pointer returned from a previous `k{re}alloc()` by the

From 941e65531446c1eb5d573c5d30172117ebe96112 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:07 +0200
Subject: [PATCH 0301/1530] rust: alloc: rename `KernelAllocator` to `Kmalloc`

Subsequent patches implement `Vmalloc` and `KVmalloc` allocators, hence
align `KernelAllocator` to this naming scheme.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-4-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc/allocator.rs | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/rust/kernel/alloc/allocator.rs b/rust/kernel/alloc/allocator.rs
index 765f72d5bc211..3b1c735ba409f 100644
--- a/rust/kernel/alloc/allocator.rs
+++ b/rust/kernel/alloc/allocator.rs
@@ -6,7 +6,7 @@ use super::{flags::*, Flags};
 use core::alloc::{GlobalAlloc, Layout};
 use core::ptr;
 
-struct KernelAllocator;
+struct Kmalloc;
 
 /// Returns a proper size to alloc a new object aligned to `new_layout`'s alignment.
 fn aligned_size(new_layout: Layout) -> usize {
@@ -37,7 +37,7 @@ pub(crate) unsafe fn krealloc_aligned(ptr: *mut u8, new_layout: Layout, flags: F
 }
 
 // SAFETY: TODO.
-unsafe impl GlobalAlloc for KernelAllocator {
+unsafe impl GlobalAlloc for Kmalloc {
     unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
         // SAFETY: `ptr::null_mut()` is null and `layout` has a non-zero size by the function safety
         // requirement.
@@ -74,7 +74,7 @@ unsafe impl GlobalAlloc for KernelAllocator {
 }
 
 #[global_allocator]
-static ALLOCATOR: KernelAllocator = KernelAllocator;
+static ALLOCATOR: Kmalloc = Kmalloc;
 
 // See <https://github.com/rust-lang/rust/pull/86844>.
 #[no_mangle]

From d94d86cee1032bbf429d5bd0914b064e03b56f0e Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 13 Oct 2024 23:07:42 +0530
Subject: [PATCH 0302/1530] tools/perf/tests: Fix compilation error with
 strncpy in tests/tool_pmu
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

perf fails to compile on systems with GCC version11
as below:

In file included from /usr/include/string.h:519,
                 from /home/athir/perf-tools-next/tools/include/linux/bitmap.h:5,
                 from /home/athir/perf-tools-next/tools/perf/util/pmu.h:5,
                 from /home/athir/perf-tools-next/tools/perf/util/evsel.h:14,
                 from /home/athir/perf-tools-next/tools/perf/util/evlist.h:14,
                 from tests/tool_pmu.c:3:
In function ‘strncpy’,
    inlined from ‘do_test’ at tests/tool_pmu.c:25:3:
/usr/include/bits/string_fortified.h:95:10: error: ‘__builtin_strncpy’ specified bound 128 equals destination size [-Werror=stringop-truncation]
   95 |   return __builtin___strncpy_chk (__dest, __src, __len,
      |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   96 |                                   __glibc_objsize (__dest));
      |                                   ~~~~~~~~~~~~~~~~~~~~~~~~~

The compile error is from strncpy refernce in do_test:
	strncpy(str, tool_pmu__event_to_str(ev), sizeof(str));

This behaviour is not observed with GCC version 8, but observed
with GCC version 11 . This is message from gcc for detecting
truncation while using strncpu. Use snprintf instead of strncpy
here to be safe.

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: akanksha@linux.ibm.com
Cc: hbathini@linux.ibm.com
Cc: kjain@linux.ibm.com
Cc: maddy@linux.ibm.com
Cc: disgoel@linux.vnet.ibm.com
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20241013173742.71882-1-atrajeev@linux.vnet.ibm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/tool_pmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/tool_pmu.c b/tools/perf/tests/tool_pmu.c
index 94d0dd8fd3cbb..297cc8c555791 100644
--- a/tools/perf/tests/tool_pmu.c
+++ b/tools/perf/tests/tool_pmu.c
@@ -22,7 +22,7 @@ static int do_test(enum tool_pmu_event ev, bool with_pmu)
 	if (with_pmu)
 		snprintf(str, sizeof(str), "tool/%s/", tool_pmu__event_to_str(ev));
 	else
-		strncpy(str, tool_pmu__event_to_str(ev), sizeof(str));
+		snprintf(str, sizeof(str), "%s", tool_pmu__event_to_str(ev));
 
 	parse_events_error__init(&err);
 	ret = parse_events(evlist, str, &err);

From 9ea671d1b2d5962368b94b28507ae65f94c86fb3 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 13 Oct 2024 22:37:32 +0530
Subject: [PATCH 0303/1530] tools/perf/tests: Remove duplicate evlist__delete
 in tests/tool_pmu.c

The testcase for tool_pmu failed in powerpc as below:

 ./perf test -v "Parsing without PMU name"
  8: Tool PMU                                                        :
  8.1: Parsing without PMU name                                      : FAILED!

This happens when parse_events results in either skip or fail
of an event. Because the code invokes evlist__delete(evlist)
and "goto out".

	ret = parse_events(evlist, str, &err);
	if (ret) {
		 evlist__delete(evlist);

But in the "out" section also evlist__delete happens.

	out:
        evlist__delete(evlist);
        return ret;

Hence remove the duplicate evlist__delete from the first path
in the testcase

With the change:
	# ./perf test -v "Parsing without PMU name"
	  8: Tool PMU                                                        :
	  8.1: Parsing without PMU name                                      : Ok

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: akanksha@linux.ibm.com
Cc: hbathini@linux.ibm.com
Cc: kjain@linux.ibm.com
Cc: maddy@linux.ibm.com
Cc: disgoel@linux.vnet.ibm.com
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20241013170732.71339-1-atrajeev@linux.vnet.ibm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/tool_pmu.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/perf/tests/tool_pmu.c b/tools/perf/tests/tool_pmu.c
index 297cc8c555791..46896b485abf3 100644
--- a/tools/perf/tests/tool_pmu.c
+++ b/tools/perf/tests/tool_pmu.c
@@ -27,7 +27,6 @@ static int do_test(enum tool_pmu_event ev, bool with_pmu)
 	parse_events_error__init(&err);
 	ret = parse_events(evlist, str, &err);
 	if (ret) {
-		evlist__delete(evlist);
 		if (tool_pmu__skip_event(tool_pmu__event_to_str(ev))) {
 			ret = TEST_OK;
 			goto out;

From 1a3d6a9723d4dbdad41dad67b66a64d4a84c5f5c Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 14 Oct 2024 10:34:17 -0700
Subject: [PATCH 0304/1530] perf tools: Fix compiler error in util/tool_pmu.c

  util/tool_pmu.c: In function 'evsel__tool_pmu_read':
  util/tool_pmu.c:419:55: error: passing argument 2 of 'tool_pmu__read_event' from incompatible pointer type [-Werror=incompatible-pointer-types]
    419 |                         if (!tool_pmu__read_event(ev, &val)) {
        |                                                       ^~~~
        |                                                       |
        |                                                       long unsigned int *
  util/tool_pmu.c:335:56: note: expected 'u64 *' {aka 'long long unsigned int *'} but argument is of type 'long unsigned int *'
    335 | bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result)
        |                                                   ~~~~~^~~~~~

Link: https://lore.kernel.org/r/Zw1XIGML32VaxE0t@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/tool_pmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/tool_pmu.c b/tools/perf/util/tool_pmu.c
index ea9d50f025202..bd1cee643eb50 100644
--- a/tools/perf/util/tool_pmu.c
+++ b/tools/perf/util/tool_pmu.c
@@ -394,7 +394,7 @@ bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result)
 int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread)
 {
 	__u64 *start_time, cur_time, delta_start;
-	unsigned long val;
+	u64 val;
 	int fd, err = 0;
 	struct perf_counts_values *count, *old_count = NULL;
 	bool adjust = false;

From 209efec19c4c0cea17ff01d67c8fbd75a90fb854 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Mon, 7 Oct 2024 13:02:02 +0200
Subject: [PATCH 0305/1530] dt-bindings: dma: rz-dmac: Document RZ/A1H SoC

Document the Renesas RZ/A1H DMAC block. This one does not have clocks,
resets and power domains. Update the bindings accordingly. Introduce a
generic name in the header to make future additions easier.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20241007110200.43166-7-wsa+renesas@sang-engineering.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../bindings/dma/renesas,rz-dmac.yaml         | 29 +++++++++++++------
 1 file changed, 20 insertions(+), 9 deletions(-)

diff --git a/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml b/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
index ca24cf48769f6..b356251de5a82 100644
--- a/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
+++ b/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
@@ -4,18 +4,16 @@
 $id: http://devicetree.org/schemas/dma/renesas,rz-dmac.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Renesas RZ/{G2L,G2UL,V2L} DMA Controller
+title: Renesas RZ DMA Controller
 
 maintainers:
   - Biju Das <biju.das.jz@bp.renesas.com>
 
-allOf:
-  - $ref: dma-controller.yaml#
-
 properties:
   compatible:
     items:
       - enum:
+          - renesas,r7s72100-dmac # RZ/A1H
           - renesas,r9a07g043-dmac # RZ/G2UL and RZ/Five
           - renesas,r9a07g044-dmac # RZ/G2{L,LC}
           - renesas,r9a07g054-dmac # RZ/V2L
@@ -93,13 +91,26 @@ required:
   - reg
   - interrupts
   - interrupt-names
-  - clocks
-  - clock-names
   - '#dma-cells'
   - dma-channels
-  - power-domains
-  - resets
-  - reset-names
+
+allOf:
+  - $ref: dma-controller.yaml#
+
+  - if:
+      not:
+        properties:
+          compatible:
+            contains:
+              enum:
+                - renesas,r7s72100-dmac
+    then:
+      required:
+        - clocks
+        - clock-names
+        - power-domains
+        - resets
+        - reset-names
 
 additionalProperties: false
 

From 32172b3e3265833a367e41842fa8b7eaa0acae96 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Mon, 7 Oct 2024 13:02:03 +0200
Subject: [PATCH 0306/1530] dmaengine: sh: rz-dmac: add r7s72100 support

This SoC needs to make getting resets optional. Descriptions are
reworded to be more generic.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20241007110200.43166-8-wsa+renesas@sang-engineering.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/sh/Kconfig   | 8 ++++----
 drivers/dma/sh/rz-dmac.c | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/dma/sh/Kconfig b/drivers/dma/sh/Kconfig
index c0b2997ab7fd9..6ea5a880b4339 100644
--- a/drivers/dma/sh/Kconfig
+++ b/drivers/dma/sh/Kconfig
@@ -49,10 +49,10 @@ config RENESAS_USB_DMAC
 	  SoCs.
 
 config RZ_DMAC
-	tristate "Renesas RZ/{G2L,V2L} DMA Controller"
-	depends on ARCH_RZG2L || COMPILE_TEST
+	tristate "Renesas RZ DMA Controller"
+	depends on ARCH_R7S72100 || ARCH_RZG2L || COMPILE_TEST
 	select RENESAS_DMA
 	select DMA_VIRTUAL_CHANNELS
 	help
-	  This driver supports the general purpose DMA controller found in the
-	  Renesas RZ/{G2L,V2L} SoC variants.
+	  This driver supports the general purpose DMA controller typically
+	  found in the Renesas RZ SoC variants.
diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c
index 811389fc9cb82..03f3f99f0f4a6 100644
--- a/drivers/dma/sh/rz-dmac.c
+++ b/drivers/dma/sh/rz-dmac.c
@@ -893,7 +893,7 @@ static int rz_dmac_probe(struct platform_device *pdev)
 	/* Initialize the channels. */
 	INIT_LIST_HEAD(&dmac->engine.channels);
 
-	dmac->rstc = devm_reset_control_array_get_exclusive(&pdev->dev);
+	dmac->rstc = devm_reset_control_array_get_optional_exclusive(&pdev->dev);
 	if (IS_ERR(dmac->rstc))
 		return dev_err_probe(&pdev->dev, PTR_ERR(dmac->rstc),
 				     "failed to get resets\n");

From 6e3ea06240adfef7b46e2338dd824541c31de06d Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 7 Oct 2024 18:03:23 +0300
Subject: [PATCH 0307/1530] dmaengine: acpi: Drop unused
 devm_acpi_dma_controller_free()

After introduction a few years ago the devm_acpi_dma_controller_free()
was never used. Drop it.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20241007150436.2183575-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/driver-api/driver-model/devres.rst |  1 -
 drivers/dma/acpi-dma.c                           | 15 ---------------
 include/linux/acpi_dma.h                         |  4 ----
 3 files changed, 20 deletions(-)

diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index 5f2ee8d717b1d..f23dbe5d66067 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -459,7 +459,6 @@ SERDEV
 
 SLAVE DMA ENGINE
   devm_acpi_dma_controller_register()
-  devm_acpi_dma_controller_free()
 
 SPI
   devm_spi_alloc_master()
diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index a58a1600dd659..d5beb96ef510b 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -276,21 +276,6 @@ int devm_acpi_dma_controller_register(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(devm_acpi_dma_controller_register);
 
-/**
- * devm_acpi_dma_controller_free - resource managed acpi_dma_controller_free()
- * @dev:	device that is unregistering as DMA controller
- *
- * Unregister a DMA controller registered with
- * devm_acpi_dma_controller_register(). Normally this function will not need to
- * be called and the resource management code will ensure that the resource is
- * freed.
- */
-void devm_acpi_dma_controller_free(struct device *dev)
-{
-	WARN_ON(devres_release(dev, devm_acpi_dma_release, NULL, NULL));
-}
-EXPORT_SYMBOL_GPL(devm_acpi_dma_controller_free);
-
 /**
  * acpi_dma_update_dma_spec - prepare dma specifier to pass to translation function
  * @adma:	struct acpi_dma of DMA controller
diff --git a/include/linux/acpi_dma.h b/include/linux/acpi_dma.h
index 72cedb916a9c2..3ef1ec7a04cb7 100644
--- a/include/linux/acpi_dma.h
+++ b/include/linux/acpi_dma.h
@@ -65,7 +65,6 @@ int devm_acpi_dma_controller_register(struct device *dev,
 		struct dma_chan *(*acpi_dma_xlate)
 		(struct acpi_dma_spec *, struct acpi_dma *),
 		void *data);
-void devm_acpi_dma_controller_free(struct device *dev);
 
 struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev,
 						      size_t index);
@@ -94,9 +93,6 @@ static inline int devm_acpi_dma_controller_register(struct device *dev,
 {
 	return -ENODEV;
 }
-static inline void devm_acpi_dma_controller_free(struct device *dev)
-{
-}
 
 static inline struct dma_chan *acpi_dma_request_slave_chan_by_index(
 		struct device *dev, size_t index)

From c0fecce865535f77e7a8220175b126392dfe99dc Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 7 Oct 2024 18:03:24 +0300
Subject: [PATCH 0308/1530] dmaengine: acpi: Simplify
 devm_acpi_dma_controller_register()

Use devm_add_action_or_reset() instead of devres_alloc() and
devres_add(), which works the same. This will simplify the
code. There is no functional changes.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20241007150436.2183575-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/acpi-dma.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index d5beb96ef510b..f594ea265c76d 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -236,7 +236,7 @@ int acpi_dma_controller_free(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(acpi_dma_controller_free);
 
-static void devm_acpi_dma_release(struct device *dev, void *res)
+static void devm_acpi_dma_free(void *dev)
 {
 	acpi_dma_controller_free(dev);
 }
@@ -259,20 +259,13 @@ int devm_acpi_dma_controller_register(struct device *dev,
 		(struct acpi_dma_spec *, struct acpi_dma *),
 		void *data)
 {
-	void *res;
 	int ret;
 
-	res = devres_alloc(devm_acpi_dma_release, 0, GFP_KERNEL);
-	if (!res)
-		return -ENOMEM;
-
 	ret = acpi_dma_controller_register(dev, acpi_dma_xlate, data);
-	if (ret) {
-		devres_free(res);
+	if (ret)
 		return ret;
-	}
-	devres_add(dev, res);
-	return 0;
+
+	return devm_add_action_or_reset(dev, devm_acpi_dma_free, dev);
 }
 EXPORT_SYMBOL_GPL(devm_acpi_dma_controller_register);
 

From 662f045332addc961940e48eb920caa954abbf09 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 7 Oct 2024 18:03:25 +0300
Subject: [PATCH 0309/1530] dmaengine: acpi: Clean up headers

There is a few things done:
- include only the headers we are direct user of
- when pointer is in use, provide a forward declaration
- add missing headers
- sort alphabetically

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20241007150436.2183575-4-andriy.shevchenko@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/acpi-dma.c   | 13 ++++++++-----
 include/linux/acpi_dma.h |  5 +++--
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index f594ea265c76d..2abbe11e797e9 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -9,18 +9,21 @@
  *	    Mika Westerberg <mika.westerberg@linux.intel.com>
  */
 
+#include <linux/acpi.h>
+#include <linux/acpi_dma.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/err.h>
-#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/ioport.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
-#include <linux/slab.h>
-#include <linux/ioport.h>
-#include <linux/acpi.h>
-#include <linux/acpi_dma.h>
 #include <linux/property.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/types.h>
 
 static LIST_HEAD(acpi_dma_list);
 static DEFINE_MUTEX(acpi_dma_lock);
diff --git a/include/linux/acpi_dma.h b/include/linux/acpi_dma.h
index 3ef1ec7a04cb7..e748b28776022 100644
--- a/include/linux/acpi_dma.h
+++ b/include/linux/acpi_dma.h
@@ -11,10 +11,11 @@
 #ifndef __LINUX_ACPI_DMA_H
 #define __LINUX_ACPI_DMA_H
 
-#include <linux/list.h>
-#include <linux/device.h>
 #include <linux/err.h>
 #include <linux/dmaengine.h>
+#include <linux/types.h>
+
+struct device;
 
 /**
  * struct acpi_dma_spec - slave device DMA resources

From 0aa4523cdb9683e35af91ebdfae8d2fb4e6c3b8b Mon Sep 17 00:00:00 2001
From: Advait Dhamorikar <advaitdhamorikar@gmail.com>
Date: Sat, 5 Oct 2024 15:04:36 +0530
Subject: [PATCH 0310/1530] dmaengine: ep93xx: Fix unsigned compared against 0

An unsigned value can never be negative,
so this test will always evaluate the same way.
In ep93xx_dma_alloc_chan_resources: An unsigned dma_cfg.port's
value is checked against EP93XX_DMA_I2S1 which is 0.

Signed-off-by: Advait Dhamorikar <advaitdhamorikar@gmail.com>
Link: https://lore.kernel.org/r/20241005093436.27728-1-advaitdhamorikar@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/ep93xx_dma.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index 995427afe0773..6d7f6bd12d766 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -929,8 +929,7 @@ static int ep93xx_dma_alloc_chan_resources(struct dma_chan *chan)
 
 	/* Sanity check the channel parameters */
 	if (!edmac->edma->m2m) {
-		if (edmac->dma_cfg.port < EP93XX_DMA_I2S1 ||
-		    edmac->dma_cfg.port > EP93XX_DMA_IRDA)
+		if (edmac->dma_cfg.port > EP93XX_DMA_IRDA)
 			return -EINVAL;
 		if (edmac->dma_cfg.dir != ep93xx_dma_chan_direction(chan))
 			return -EINVAL;

From 76355c25e4f71ee4667ebaadd9faf8ec29d18f23 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@baylibre.com>
Date: Fri, 4 Oct 2024 08:22:27 +0200
Subject: [PATCH 0311/1530] dmaengine: Switch back to struct
 platform_driver::remove()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 0edb555a65d1 ("platform: Make platform_driver::remove()
return void") .remove() is (again) the right callback to implement for
platform drivers.

Convert all platform drivers below drivers/dma after the previous
conversion commits apart from the wireless drivers to use .remove(),
with the eventual goal to drop struct platform_driver::remove_new(). As
.remove() and .remove_new() have the same prototypes, conversion is done
by just changing the structure member name in the driver initializer.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Link: https://lore.kernel.org/r/20241004062227.187726-2-u.kleine-koenig@baylibre.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/altera-msgdma.c                    | 2 +-
 drivers/dma/amd/qdma/qdma.c                    | 2 +-
 drivers/dma/apple-admac.c                      | 2 +-
 drivers/dma/at_hdmac.c                         | 2 +-
 drivers/dma/at_xdmac.c                         | 2 +-
 drivers/dma/bcm-sba-raid.c                     | 2 +-
 drivers/dma/bcm2835-dma.c                      | 2 +-
 drivers/dma/bestcomm/bestcomm.c                | 2 +-
 drivers/dma/dma-jz4780.c                       | 2 +-
 drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c | 2 +-
 drivers/dma/dw/platform.c                      | 2 +-
 drivers/dma/fsl-edma-main.c                    | 2 +-
 drivers/dma/fsl-qdma.c                         | 2 +-
 drivers/dma/fsl_raid.c                         | 2 +-
 drivers/dma/fsldma.c                           | 2 +-
 drivers/dma/idma64.c                           | 2 +-
 drivers/dma/img-mdc-dma.c                      | 2 +-
 drivers/dma/imx-dma.c                          | 2 +-
 drivers/dma/imx-sdma.c                         | 2 +-
 drivers/dma/k3dma.c                            | 2 +-
 drivers/dma/ls2x-apb-dma.c                     | 2 +-
 drivers/dma/mcf-edma-main.c                    | 2 +-
 drivers/dma/mediatek/mtk-cqdma.c               | 2 +-
 drivers/dma/mediatek/mtk-hsdma.c               | 2 +-
 drivers/dma/mediatek/mtk-uart-apdma.c          | 2 +-
 drivers/dma/milbeaut-hdmac.c                   | 2 +-
 drivers/dma/milbeaut-xdmac.c                   | 2 +-
 drivers/dma/mmp_pdma.c                         | 2 +-
 drivers/dma/mmp_tdma.c                         | 2 +-
 drivers/dma/moxart-dma.c                       | 2 +-
 drivers/dma/mpc512x_dma.c                      | 2 +-
 drivers/dma/mv_xor_v2.c                        | 2 +-
 drivers/dma/nbpfaxi.c                          | 2 +-
 drivers/dma/owl-dma.c                          | 2 +-
 drivers/dma/ppc4xx/adma.c                      | 2 +-
 drivers/dma/pxa_dma.c                          | 2 +-
 drivers/dma/qcom/bam_dma.c                     | 2 +-
 drivers/dma/qcom/hidma.c                       | 2 +-
 drivers/dma/qcom/qcom_adm.c                    | 2 +-
 drivers/dma/sa11x0-dma.c                       | 2 +-
 drivers/dma/sf-pdma/sf-pdma.c                  | 2 +-
 drivers/dma/sh/rcar-dmac.c                     | 2 +-
 drivers/dma/sh/rz-dmac.c                       | 2 +-
 drivers/dma/sh/shdmac.c                        | 2 +-
 drivers/dma/sh/usb-dmac.c                      | 2 +-
 drivers/dma/sprd-dma.c                         | 2 +-
 drivers/dma/st_fdma.c                          | 2 +-
 drivers/dma/stm32/stm32-dma3.c                 | 2 +-
 drivers/dma/sun4i-dma.c                        | 2 +-
 drivers/dma/sun6i-dma.c                        | 2 +-
 drivers/dma/tegra186-gpc-dma.c                 | 2 +-
 drivers/dma/tegra20-apb-dma.c                  | 2 +-
 drivers/dma/tegra210-adma.c                    | 2 +-
 drivers/dma/ti/cppi41.c                        | 2 +-
 drivers/dma/ti/edma.c                          | 2 +-
 drivers/dma/ti/omap-dma.c                      | 2 +-
 drivers/dma/timb_dma.c                         | 2 +-
 drivers/dma/txx9dmac.c                         | 4 ++--
 drivers/dma/uniphier-mdmac.c                   | 2 +-
 drivers/dma/uniphier-xdmac.c                   | 2 +-
 drivers/dma/xgene-dma.c                        | 2 +-
 drivers/dma/xilinx/xdma.c                      | 2 +-
 drivers/dma/xilinx/xilinx_dma.c                | 2 +-
 drivers/dma/xilinx/xilinx_dpdma.c              | 2 +-
 drivers/dma/xilinx/zynqmp_dma.c                | 2 +-
 65 files changed, 66 insertions(+), 66 deletions(-)

diff --git a/drivers/dma/altera-msgdma.c b/drivers/dma/altera-msgdma.c
index e6a6566b309ee..a203fdd84950e 100644
--- a/drivers/dma/altera-msgdma.c
+++ b/drivers/dma/altera-msgdma.c
@@ -954,7 +954,7 @@ static struct platform_driver msgdma_driver = {
 		.of_match_table = of_match_ptr(msgdma_match),
 	},
 	.probe = msgdma_probe,
-	.remove_new = msgdma_remove,
+	.remove = msgdma_remove,
 };
 
 module_platform_driver(msgdma_driver);
diff --git a/drivers/dma/amd/qdma/qdma.c b/drivers/dma/amd/qdma/qdma.c
index b0a1f3ad851b1..6d9079458fe9c 100644
--- a/drivers/dma/amd/qdma/qdma.c
+++ b/drivers/dma/amd/qdma/qdma.c
@@ -1133,7 +1133,7 @@ static struct platform_driver amd_qdma_driver = {
 		.name = "amd-qdma",
 	},
 	.probe		= amd_qdma_probe,
-	.remove_new	= amd_qdma_remove,
+	.remove		= amd_qdma_remove,
 };
 
 module_platform_driver(amd_qdma_driver);
diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c
index 9588773dd2eb6..c499173d80b20 100644
--- a/drivers/dma/apple-admac.c
+++ b/drivers/dma/apple-admac.c
@@ -950,7 +950,7 @@ static struct platform_driver apple_admac_driver = {
 		.of_match_table = admac_of_match,
 	},
 	.probe = admac_probe,
-	.remove_new = admac_remove,
+	.remove = admac_remove,
 };
 module_platform_driver(apple_admac_driver);
 
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index baebddc740b0d..2d147712cbc69 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -2250,7 +2250,7 @@ static const struct dev_pm_ops __maybe_unused at_dma_dev_pm_ops = {
 };
 
 static struct platform_driver at_dma_driver = {
-	.remove_new	= at_dma_remove,
+	.remove		= at_dma_remove,
 	.shutdown	= at_dma_shutdown,
 	.id_table	= atdma_devtypes,
 	.driver = {
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 299396121e6dc..9c7b402200040 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -2476,7 +2476,7 @@ MODULE_DEVICE_TABLE(of, atmel_xdmac_dt_ids);
 
 static struct platform_driver at_xdmac_driver = {
 	.probe		= at_xdmac_probe,
-	.remove_new	= at_xdmac_remove,
+	.remove		= at_xdmac_remove,
 	.driver = {
 		.name		= "at_xdmac",
 		.of_match_table	= of_match_ptr(atmel_xdmac_dt_ids),
diff --git a/drivers/dma/bcm-sba-raid.c b/drivers/dma/bcm-sba-raid.c
index cfa6e1167a1fd..7f0e76439ce58 100644
--- a/drivers/dma/bcm-sba-raid.c
+++ b/drivers/dma/bcm-sba-raid.c
@@ -1756,7 +1756,7 @@ MODULE_DEVICE_TABLE(of, sba_of_match);
 
 static struct platform_driver sba_driver = {
 	.probe = sba_probe,
-	.remove_new = sba_remove,
+	.remove = sba_remove,
 	.driver = {
 		.name = "bcm-sba-raid",
 		.of_match_table = sba_of_match,
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index e1b92b4d7b056..7ba52dee40a96 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -1029,7 +1029,7 @@ static void bcm2835_dma_remove(struct platform_device *pdev)
 
 static struct platform_driver bcm2835_dma_driver = {
 	.probe	= bcm2835_dma_probe,
-	.remove_new = bcm2835_dma_remove,
+	.remove = bcm2835_dma_remove,
 	.driver = {
 		.name = "bcm2835-dma",
 		.of_match_table = of_match_ptr(bcm2835_dma_of_match),
diff --git a/drivers/dma/bestcomm/bestcomm.c b/drivers/dma/bestcomm/bestcomm.c
index 0bbaa7620bdd4..6c4d655ffe77f 100644
--- a/drivers/dma/bestcomm/bestcomm.c
+++ b/drivers/dma/bestcomm/bestcomm.c
@@ -486,7 +486,7 @@ MODULE_DEVICE_TABLE(of, mpc52xx_bcom_of_match);
 
 static struct platform_driver mpc52xx_bcom_of_platform_driver = {
 	.probe		= mpc52xx_bcom_probe,
-	.remove_new	= mpc52xx_bcom_remove,
+	.remove		= mpc52xx_bcom_remove,
 	.driver = {
 		.name = DRIVER_NAME,
 		.of_match_table = mpc52xx_bcom_of_match,
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index c9cfa341db510..100057603fd4e 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -1122,7 +1122,7 @@ MODULE_DEVICE_TABLE(of, jz4780_dma_dt_match);
 
 static struct platform_driver jz4780_dma_driver = {
 	.probe		= jz4780_dma_probe,
-	.remove_new	= jz4780_dma_remove,
+	.remove		= jz4780_dma_remove,
 	.driver	= {
 		.name	= "jz4780-dma",
 		.of_match_table = jz4780_dma_dt_match,
diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
index fffafa86d964e..b23536645ff7c 100644
--- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
+++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
@@ -1676,7 +1676,7 @@ MODULE_DEVICE_TABLE(of, dw_dma_of_id_table);
 
 static struct platform_driver dw_driver = {
 	.probe		= dw_probe,
-	.remove_new	= dw_remove,
+	.remove		= dw_remove,
 	.driver = {
 		.name	= KBUILD_MODNAME,
 		.of_match_table = dw_dma_of_id_table,
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index 47c58ad468cbc..2606cf9cd4299 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -191,7 +191,7 @@ static const struct dev_pm_ops dw_dev_pm_ops = {
 
 static struct platform_driver dw_driver = {
 	.probe		= dw_probe,
-	.remove_new	= dw_remove,
+	.remove		= dw_remove,
 	.shutdown       = dw_shutdown,
 	.driver = {
 		.name	= DRV_NAME,
diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index f9f1eda792546..60de1003193aa 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -740,7 +740,7 @@ static struct platform_driver fsl_edma_driver = {
 		.pm     = &fsl_edma_pm_ops,
 	},
 	.probe          = fsl_edma_probe,
-	.remove_new	= fsl_edma_remove,
+	.remove		= fsl_edma_remove,
 };
 
 static int __init fsl_edma_init(void)
diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index 5005e138fc239..823f5c6bc2e1a 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -1288,7 +1288,7 @@ static struct platform_driver fsl_qdma_driver = {
 		.of_match_table = fsl_qdma_dt_ids,
 	},
 	.probe          = fsl_qdma_probe,
-	.remove_new	= fsl_qdma_remove,
+	.remove		= fsl_qdma_remove,
 };
 
 module_platform_driver(fsl_qdma_driver);
diff --git a/drivers/dma/fsl_raid.c b/drivers/dma/fsl_raid.c
index 014ff523d5ec9..6aa97e258a557 100644
--- a/drivers/dma/fsl_raid.c
+++ b/drivers/dma/fsl_raid.c
@@ -886,7 +886,7 @@ static struct platform_driver fsl_re_driver = {
 		.of_match_table = fsl_re_ids,
 	},
 	.probe = fsl_re_probe,
-	.remove_new = fsl_re_remove,
+	.remove = fsl_re_remove,
 };
 
 module_platform_driver(fsl_re_driver);
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 18a6c4bf6275c..b5e7d18b97669 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -1404,7 +1404,7 @@ static struct platform_driver fsldma_of_driver = {
 #endif
 	},
 	.probe = fsldma_of_probe,
-	.remove_new = fsldma_of_remove,
+	.remove = fsldma_of_remove,
 };
 
 /*----------------------------------------------------------------------------*/
diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c
index 3c648308a54a3..d147353d47ab7 100644
--- a/drivers/dma/idma64.c
+++ b/drivers/dma/idma64.c
@@ -693,7 +693,7 @@ static const struct dev_pm_ops idma64_dev_pm_ops = {
 
 static struct platform_driver idma64_platform_driver = {
 	.probe		= idma64_platform_probe,
-	.remove_new	= idma64_platform_remove,
+	.remove		= idma64_platform_remove,
 	.driver = {
 		.name	= LPSS_IDMA64_DRIVER_NAME,
 		.pm	= &idma64_dev_pm_ops,
diff --git a/drivers/dma/img-mdc-dma.c b/drivers/dma/img-mdc-dma.c
index 0532dd2640dce..4127c1bdcca7c 100644
--- a/drivers/dma/img-mdc-dma.c
+++ b/drivers/dma/img-mdc-dma.c
@@ -1076,7 +1076,7 @@ static struct platform_driver mdc_dma_driver = {
 		.of_match_table = of_match_ptr(mdc_dma_of_match),
 	},
 	.probe = mdc_dma_probe,
-	.remove_new = mdc_dma_remove,
+	.remove = mdc_dma_remove,
 };
 module_platform_driver(mdc_dma_driver);
 
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index e913f0db99dad..a651e0995ce8d 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -1233,7 +1233,7 @@ static struct platform_driver imxdma_driver = {
 		.name	= "imx-dma",
 		.of_match_table = imx_dma_of_dev_id,
 	},
-	.remove_new	= imxdma_remove,
+	.remove		= imxdma_remove,
 };
 
 static int __init imxdma_module_init(void)
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 72299a08af441..3449006cd14b5 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -2440,7 +2440,7 @@ static struct platform_driver sdma_driver = {
 		.name	= "imx-sdma",
 		.of_match_table = sdma_dt_ids,
 	},
-	.remove_new	= sdma_remove,
+	.remove		= sdma_remove,
 	.probe		= sdma_probe,
 };
 
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index 5de8c21d41e7d..acc2983e28e0d 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -1028,7 +1028,7 @@ static struct platform_driver k3_pdma_driver = {
 		.of_match_table = k3_pdma_dt_ids,
 	},
 	.probe		= k3_dma_probe,
-	.remove_new	= k3_dma_remove,
+	.remove		= k3_dma_remove,
 };
 
 module_platform_driver(k3_pdma_driver);
diff --git a/drivers/dma/ls2x-apb-dma.c b/drivers/dma/ls2x-apb-dma.c
index 9652e86667224..2460cf9a44f5d 100644
--- a/drivers/dma/ls2x-apb-dma.c
+++ b/drivers/dma/ls2x-apb-dma.c
@@ -692,7 +692,7 @@ MODULE_DEVICE_TABLE(of, ls2x_dma_of_match_table);
 
 static struct platform_driver ls2x_dmac_driver = {
 	.probe		= ls2x_dma_probe,
-	.remove_new	= ls2x_dma_remove,
+	.remove		= ls2x_dma_remove,
 	.driver = {
 		.name	= "ls2x-apbdma",
 		.of_match_table	= ls2x_dma_of_match_table,
diff --git a/drivers/dma/mcf-edma-main.c b/drivers/dma/mcf-edma-main.c
index 0c5862bf26f8a..9e1c6400c77be 100644
--- a/drivers/dma/mcf-edma-main.c
+++ b/drivers/dma/mcf-edma-main.c
@@ -267,7 +267,7 @@ static struct platform_driver mcf_edma_driver = {
 		.name	= "mcf-edma",
 	},
 	.probe		= mcf_edma_probe,
-	.remove_new	= mcf_edma_remove,
+	.remove		= mcf_edma_remove,
 };
 
 bool mcf_edma_filter_fn(struct dma_chan *chan, void *param)
diff --git a/drivers/dma/mediatek/mtk-cqdma.c b/drivers/dma/mediatek/mtk-cqdma.c
index b69eabf12a24f..d5ddb4e30e715 100644
--- a/drivers/dma/mediatek/mtk-cqdma.c
+++ b/drivers/dma/mediatek/mtk-cqdma.c
@@ -922,7 +922,7 @@ static void mtk_cqdma_remove(struct platform_device *pdev)
 
 static struct platform_driver mtk_cqdma_driver = {
 	.probe = mtk_cqdma_probe,
-	.remove_new = mtk_cqdma_remove,
+	.remove = mtk_cqdma_remove,
 	.driver = {
 		.name           = KBUILD_MODNAME,
 		.of_match_table = mtk_cqdma_match,
diff --git a/drivers/dma/mediatek/mtk-hsdma.c b/drivers/dma/mediatek/mtk-hsdma.c
index 58c7961ab9ad1..fa77bb24a4307 100644
--- a/drivers/dma/mediatek/mtk-hsdma.c
+++ b/drivers/dma/mediatek/mtk-hsdma.c
@@ -1038,7 +1038,7 @@ static void mtk_hsdma_remove(struct platform_device *pdev)
 
 static struct platform_driver mtk_hsdma_driver = {
 	.probe		= mtk_hsdma_probe,
-	.remove_new	= mtk_hsdma_remove,
+	.remove		= mtk_hsdma_remove,
 	.driver = {
 		.name		= KBUILD_MODNAME,
 		.of_match_table	= mtk_hsdma_match,
diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c
index 1bdc1500be40f..08e15177427b9 100644
--- a/drivers/dma/mediatek/mtk-uart-apdma.c
+++ b/drivers/dma/mediatek/mtk-uart-apdma.c
@@ -637,7 +637,7 @@ static const struct dev_pm_ops mtk_uart_apdma_pm_ops = {
 
 static struct platform_driver mtk_uart_apdma_driver = {
 	.probe	= mtk_uart_apdma_probe,
-	.remove_new = mtk_uart_apdma_remove,
+	.remove = mtk_uart_apdma_remove,
 	.driver = {
 		.name		= KBUILD_MODNAME,
 		.pm		= &mtk_uart_apdma_pm_ops,
diff --git a/drivers/dma/milbeaut-hdmac.c b/drivers/dma/milbeaut-hdmac.c
index 7b41c670970a6..9a5ec247ed6d9 100644
--- a/drivers/dma/milbeaut-hdmac.c
+++ b/drivers/dma/milbeaut-hdmac.c
@@ -571,7 +571,7 @@ MODULE_DEVICE_TABLE(of, milbeaut_hdmac_match);
 
 static struct platform_driver milbeaut_hdmac_driver = {
 	.probe = milbeaut_hdmac_probe,
-	.remove_new = milbeaut_hdmac_remove,
+	.remove = milbeaut_hdmac_remove,
 	.driver = {
 		.name = "milbeaut-m10v-hdmac",
 		.of_match_table = milbeaut_hdmac_match,
diff --git a/drivers/dma/milbeaut-xdmac.c b/drivers/dma/milbeaut-xdmac.c
index 2cce529b448eb..58d4fd6df0bf4 100644
--- a/drivers/dma/milbeaut-xdmac.c
+++ b/drivers/dma/milbeaut-xdmac.c
@@ -409,7 +409,7 @@ MODULE_DEVICE_TABLE(of, milbeaut_xdmac_match);
 
 static struct platform_driver milbeaut_xdmac_driver = {
 	.probe = milbeaut_xdmac_probe,
-	.remove_new = milbeaut_xdmac_remove,
+	.remove = milbeaut_xdmac_remove,
 	.driver = {
 		.name = "milbeaut-m10v-xdmac",
 		.of_match_table = milbeaut_xdmac_match,
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
index 136fcaeff8dda..a95d31103d306 100644
--- a/drivers/dma/mmp_pdma.c
+++ b/drivers/dma/mmp_pdma.c
@@ -1137,7 +1137,7 @@ static struct platform_driver mmp_pdma_driver = {
 	},
 	.id_table	= mmp_pdma_id_table,
 	.probe		= mmp_pdma_probe,
-	.remove_new	= mmp_pdma_remove,
+	.remove		= mmp_pdma_remove,
 };
 
 module_platform_driver(mmp_pdma_driver);
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index b76fe99e11516..c8dc504510f1e 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -736,7 +736,7 @@ static struct platform_driver mmp_tdma_driver = {
 		.of_match_table = mmp_tdma_dt_ids,
 	},
 	.probe		= mmp_tdma_probe,
-	.remove_new	= mmp_tdma_remove,
+	.remove		= mmp_tdma_remove,
 };
 
 module_platform_driver(mmp_tdma_driver);
diff --git a/drivers/dma/moxart-dma.c b/drivers/dma/moxart-dma.c
index 66dc6d31b603d..de09e1ab77676 100644
--- a/drivers/dma/moxart-dma.c
+++ b/drivers/dma/moxart-dma.c
@@ -644,7 +644,7 @@ MODULE_DEVICE_TABLE(of, moxart_dma_match);
 
 static struct platform_driver moxart_driver = {
 	.probe	= moxart_probe,
-	.remove_new = moxart_remove,
+	.remove = moxart_remove,
 	.driver = {
 		.name		= "moxart-dma-engine",
 		.of_match_table	= moxart_dma_match,
diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c
index 68c247a46321c..bf131cb5db664 100644
--- a/drivers/dma/mpc512x_dma.c
+++ b/drivers/dma/mpc512x_dma.c
@@ -1110,7 +1110,7 @@ MODULE_DEVICE_TABLE(of, mpc_dma_match);
 
 static struct platform_driver mpc_dma_driver = {
 	.probe		= mpc_dma_probe,
-	.remove_new	= mpc_dma_remove,
+	.remove		= mpc_dma_remove,
 	.driver = {
 		.name = DRV_NAME,
 		.of_match_table	= mpc_dma_match,
diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c
index c8c67f4d982c0..d908143c77312 100644
--- a/drivers/dma/mv_xor_v2.c
+++ b/drivers/dma/mv_xor_v2.c
@@ -884,7 +884,7 @@ static struct platform_driver mv_xor_v2_driver = {
 	.probe		= mv_xor_v2_probe,
 	.suspend	= mv_xor_v2_suspend,
 	.resume		= mv_xor_v2_resume,
-	.remove_new	= mv_xor_v2_remove,
+	.remove		= mv_xor_v2_remove,
 	.driver		= {
 		.name	= "mv_xor_v2",
 		.of_match_table = of_match_ptr(mv_xor_v2_dt_ids),
diff --git a/drivers/dma/nbpfaxi.c b/drivers/dma/nbpfaxi.c
index 3b011a91d48ec..0d6324c4e2be0 100644
--- a/drivers/dma/nbpfaxi.c
+++ b/drivers/dma/nbpfaxi.c
@@ -1515,7 +1515,7 @@ static struct platform_driver nbpf_driver = {
 	},
 	.id_table = nbpf_ids,
 	.probe = nbpf_probe,
-	.remove_new = nbpf_remove,
+	.remove = nbpf_remove,
 };
 
 module_platform_driver(nbpf_driver);
diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c
index aa436f9e35718..57cec757d8f56 100644
--- a/drivers/dma/owl-dma.c
+++ b/drivers/dma/owl-dma.c
@@ -1252,7 +1252,7 @@ static void owl_dma_remove(struct platform_device *pdev)
 
 static struct platform_driver owl_dma_driver = {
 	.probe	= owl_dma_probe,
-	.remove_new = owl_dma_remove,
+	.remove = owl_dma_remove,
 	.driver = {
 		.name = "dma-owl",
 		.of_match_table = of_match_ptr(owl_dma_match),
diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c
index 7b78759ac734d..9d2a5a967a99c 100644
--- a/drivers/dma/ppc4xx/adma.c
+++ b/drivers/dma/ppc4xx/adma.c
@@ -4549,7 +4549,7 @@ MODULE_DEVICE_TABLE(of, ppc440spe_adma_of_match);
 
 static struct platform_driver ppc440spe_adma_driver = {
 	.probe = ppc440spe_adma_probe,
-	.remove_new = ppc440spe_adma_remove,
+	.remove = ppc440spe_adma_remove,
 	.driver = {
 		.name = "PPC440SP(E)-ADMA",
 		.of_match_table = ppc440spe_adma_of_match,
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index 31f8da810c055..e50cf3357e5ef 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -1442,7 +1442,7 @@ static struct platform_driver pxad_driver = {
 	},
 	.id_table	= pxad_id_table,
 	.probe		= pxad_probe,
-	.remove_new	= pxad_remove,
+	.remove		= pxad_remove,
 };
 
 static bool pxad_filter_fn(struct dma_chan *chan, void *param)
diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index d43a881e43b90..bbc3276992bb0 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -1469,7 +1469,7 @@ static const struct dev_pm_ops bam_dma_pm_ops = {
 
 static struct platform_driver bam_dma_driver = {
 	.probe = bam_dma_probe,
-	.remove_new = bam_dma_remove,
+	.remove = bam_dma_remove,
 	.driver = {
 		.name = "bam-dma-engine",
 		.pm = &bam_dma_pm_ops,
diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c
index 4d2cd8d9ec74a..c2b3e4452e715 100644
--- a/drivers/dma/qcom/hidma.c
+++ b/drivers/dma/qcom/hidma.c
@@ -948,7 +948,7 @@ MODULE_DEVICE_TABLE(acpi, hidma_acpi_ids);
 
 static struct platform_driver hidma_driver = {
 	.probe = hidma_probe,
-	.remove_new = hidma_remove,
+	.remove = hidma_remove,
 	.shutdown = hidma_shutdown,
 	.driver = {
 		   .name = "hidma",
diff --git a/drivers/dma/qcom/qcom_adm.c b/drivers/dma/qcom/qcom_adm.c
index c1db398adc84d..6be54fddcee18 100644
--- a/drivers/dma/qcom/qcom_adm.c
+++ b/drivers/dma/qcom/qcom_adm.c
@@ -937,7 +937,7 @@ MODULE_DEVICE_TABLE(of, adm_of_match);
 
 static struct platform_driver adm_dma_driver = {
 	.probe = adm_dma_probe,
-	.remove_new = adm_dma_remove,
+	.remove = adm_dma_remove,
 	.driver = {
 		.name = "adm-dma-engine",
 		.of_match_table = adm_of_match,
diff --git a/drivers/dma/sa11x0-dma.c b/drivers/dma/sa11x0-dma.c
index 01e656c69e6c1..dc1a9a05252ec 100644
--- a/drivers/dma/sa11x0-dma.c
+++ b/drivers/dma/sa11x0-dma.c
@@ -1079,7 +1079,7 @@ static struct platform_driver sa11x0_dma_driver = {
 		.pm	= &sa11x0_dma_pm_ops,
 	},
 	.probe		= sa11x0_dma_probe,
-	.remove_new	= sa11x0_dma_remove,
+	.remove		= sa11x0_dma_remove,
 };
 
 static int __init sa11x0_dma_init(void)
diff --git a/drivers/dma/sf-pdma/sf-pdma.c b/drivers/dma/sf-pdma/sf-pdma.c
index 428473611115d..15b1f4baf357d 100644
--- a/drivers/dma/sf-pdma/sf-pdma.c
+++ b/drivers/dma/sf-pdma/sf-pdma.c
@@ -633,7 +633,7 @@ MODULE_DEVICE_TABLE(of, sf_pdma_dt_ids);
 
 static struct platform_driver sf_pdma_driver = {
 	.probe		= sf_pdma_probe,
-	.remove_new	= sf_pdma_remove,
+	.remove		= sf_pdma_remove,
 	.driver		= {
 		.name	= "sf-pdma",
 		.of_match_table = sf_pdma_dt_ids,
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 1094a2f821649..2679c1f09faf0 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -2037,7 +2037,7 @@ static struct platform_driver rcar_dmac_driver = {
 		.of_match_table = rcar_dmac_of_ids,
 	},
 	.probe		= rcar_dmac_probe,
-	.remove_new	= rcar_dmac_remove,
+	.remove		= rcar_dmac_remove,
 	.shutdown	= rcar_dmac_shutdown,
 };
 
diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c
index 03f3f99f0f4a6..9235db5510266 100644
--- a/drivers/dma/sh/rz-dmac.c
+++ b/drivers/dma/sh/rz-dmac.c
@@ -1004,7 +1004,7 @@ static struct platform_driver rz_dmac_driver = {
 		.of_match_table = of_rz_dmac_match,
 	},
 	.probe		= rz_dmac_probe,
-	.remove_new	= rz_dmac_remove,
+	.remove		= rz_dmac_remove,
 };
 
 module_platform_driver(rz_dmac_driver);
diff --git a/drivers/dma/sh/shdmac.c b/drivers/dma/sh/shdmac.c
index 8ead0a1fd2371..093e449e19eee 100644
--- a/drivers/dma/sh/shdmac.c
+++ b/drivers/dma/sh/shdmac.c
@@ -906,7 +906,7 @@ static struct platform_driver sh_dmae_driver = {
 		.pm	= &sh_dmae_pm,
 		.name	= SH_DMAE_DRV_NAME,
 	},
-	.remove_new	= sh_dmae_remove,
+	.remove		= sh_dmae_remove,
 };
 
 static int __init sh_dmae_init(void)
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index f7cd0cad056c1..b2081a6126e6f 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -899,7 +899,7 @@ static struct platform_driver usb_dmac_driver = {
 		.of_match_table = usb_dmac_of_ids,
 	},
 	.probe		= usb_dmac_probe,
-	.remove_new	= usb_dmac_remove,
+	.remove		= usb_dmac_remove,
 	.shutdown	= usb_dmac_shutdown,
 };
 
diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c
index 3f54ff37c5e05..187a090463ced 100644
--- a/drivers/dma/sprd-dma.c
+++ b/drivers/dma/sprd-dma.c
@@ -1298,7 +1298,7 @@ static const struct dev_pm_ops sprd_dma_pm_ops = {
 
 static struct platform_driver sprd_dma_driver = {
 	.probe = sprd_dma_probe,
-	.remove_new = sprd_dma_remove,
+	.remove = sprd_dma_remove,
 	.driver = {
 		.name = "sprd-dma",
 		.of_match_table = sprd_dma_match,
diff --git a/drivers/dma/st_fdma.c b/drivers/dma/st_fdma.c
index 8880b5e336f8d..c65ee0c7bfbdb 100644
--- a/drivers/dma/st_fdma.c
+++ b/drivers/dma/st_fdma.c
@@ -858,7 +858,7 @@ static struct platform_driver st_fdma_platform_driver = {
 		.of_match_table = st_fdma_match,
 	},
 	.probe = st_fdma_probe,
-	.remove_new = st_fdma_remove,
+	.remove = st_fdma_remove,
 };
 module_platform_driver(st_fdma_platform_driver);
 
diff --git a/drivers/dma/stm32/stm32-dma3.c b/drivers/dma/stm32/stm32-dma3.c
index 0be6e944df6fd..b9470f783f989 100644
--- a/drivers/dma/stm32/stm32-dma3.c
+++ b/drivers/dma/stm32/stm32-dma3.c
@@ -1827,7 +1827,7 @@ static const struct dev_pm_ops stm32_dma3_pm_ops = {
 
 static struct platform_driver stm32_dma3_driver = {
 	.probe = stm32_dma3_probe,
-	.remove_new = stm32_dma3_remove,
+	.remove = stm32_dma3_remove,
 	.driver = {
 		.name = "stm32-dma3",
 		.of_match_table = stm32_dma3_of_match,
diff --git a/drivers/dma/sun4i-dma.c b/drivers/dma/sun4i-dma.c
index 2e7f9b07fdd29..f37cdf6f21796 100644
--- a/drivers/dma/sun4i-dma.c
+++ b/drivers/dma/sun4i-dma.c
@@ -1292,7 +1292,7 @@ MODULE_DEVICE_TABLE(of, sun4i_dma_match);
 
 static struct platform_driver sun4i_dma_driver = {
 	.probe	= sun4i_dma_probe,
-	.remove_new = sun4i_dma_remove,
+	.remove = sun4i_dma_remove,
 	.driver	= {
 		.name		= "sun4i-dma",
 		.of_match_table	= sun4i_dma_match,
diff --git a/drivers/dma/sun6i-dma.c b/drivers/dma/sun6i-dma.c
index 583bf49031cf2..95ecb12caaa5e 100644
--- a/drivers/dma/sun6i-dma.c
+++ b/drivers/dma/sun6i-dma.c
@@ -1488,7 +1488,7 @@ static void sun6i_dma_remove(struct platform_device *pdev)
 
 static struct platform_driver sun6i_dma_driver = {
 	.probe		= sun6i_dma_probe,
-	.remove_new	= sun6i_dma_remove,
+	.remove		= sun6i_dma_remove,
 	.driver = {
 		.name		= "sun6i-dma",
 		.of_match_table	= sun6i_dma_match,
diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c
index 3642508e88bb2..cacf3757adc2e 100644
--- a/drivers/dma/tegra186-gpc-dma.c
+++ b/drivers/dma/tegra186-gpc-dma.c
@@ -1532,7 +1532,7 @@ static struct platform_driver tegra_dma_driver = {
 		.of_match_table = tegra_dma_of_match,
 	},
 	.probe		= tegra_dma_probe,
-	.remove_new	= tegra_dma_remove,
+	.remove		= tegra_dma_remove,
 };
 
 module_platform_driver(tegra_dma_driver);
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index 7d1acda2d72b3..14a61e53a41b7 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -1675,7 +1675,7 @@ static struct platform_driver tegra_dmac_driver = {
 		.of_match_table = tegra_dma_of_match,
 	},
 	.probe		= tegra_dma_probe,
-	.remove_new	= tegra_dma_remove,
+	.remove		= tegra_dma_remove,
 };
 
 module_platform_driver(tegra_dmac_driver);
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index 24ad7077c53ba..2953008d42efa 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -1008,7 +1008,7 @@ static struct platform_driver tegra_admac_driver = {
 		.of_match_table = tegra_adma_of_match,
 	},
 	.probe		= tegra_adma_probe,
-	.remove_new	= tegra_adma_remove,
+	.remove		= tegra_adma_remove,
 };
 
 module_platform_driver(tegra_admac_driver);
diff --git a/drivers/dma/ti/cppi41.c b/drivers/dma/ti/cppi41.c
index a8bb70c2d1099..8d8c3d6038fcc 100644
--- a/drivers/dma/ti/cppi41.c
+++ b/drivers/dma/ti/cppi41.c
@@ -1243,7 +1243,7 @@ static const struct dev_pm_ops cppi41_pm_ops = {
 
 static struct platform_driver cpp41_dma_driver = {
 	.probe  = cppi41_dma_probe,
-	.remove_new = cppi41_dma_remove,
+	.remove = cppi41_dma_remove,
 	.driver = {
 		.name = "cppi41-dma-engine",
 		.pm = &cppi41_pm_ops,
diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index 5f8d2e93ff3fb..343e986e66e7c 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -2636,7 +2636,7 @@ static const struct dev_pm_ops edma_pm_ops = {
 
 static struct platform_driver edma_driver = {
 	.probe		= edma_probe,
-	.remove_new	= edma_remove,
+	.remove		= edma_remove,
 	.driver = {
 		.name	= "edma",
 		.pm	= &edma_pm_ops,
diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c
index 6ab9bfbdc4809..8c023c6e623a5 100644
--- a/drivers/dma/ti/omap-dma.c
+++ b/drivers/dma/ti/omap-dma.c
@@ -1915,7 +1915,7 @@ MODULE_DEVICE_TABLE(of, omap_dma_match);
 
 static struct platform_driver omap_dma_driver = {
 	.probe	= omap_dma_probe,
-	.remove_new = omap_dma_remove,
+	.remove = omap_dma_remove,
 	.driver = {
 		.name = "omap-dma-engine",
 		.of_match_table = omap_dma_match,
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index 7410025605e03..ecaf002558afc 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -761,7 +761,7 @@ static struct platform_driver td_driver = {
 		.name	= DRIVER_NAME,
 	},
 	.probe	= td_probe,
-	.remove_new = td_remove,
+	.remove = td_remove,
 };
 
 module_platform_driver(td_driver);
diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c
index 44ba377b4b5a5..35d5221683b28 100644
--- a/drivers/dma/txx9dmac.c
+++ b/drivers/dma/txx9dmac.c
@@ -1260,14 +1260,14 @@ static const struct dev_pm_ops txx9dmac_dev_pm_ops = {
 };
 
 static struct platform_driver txx9dmac_chan_driver = {
-	.remove_new	= txx9dmac_chan_remove,
+	.remove		= txx9dmac_chan_remove,
 	.driver = {
 		.name	= "txx9dmac-chan",
 	},
 };
 
 static struct platform_driver txx9dmac_driver = {
-	.remove_new	= txx9dmac_remove,
+	.remove		= txx9dmac_remove,
 	.shutdown	= txx9dmac_shutdown,
 	.driver = {
 		.name	= "txx9dmac",
diff --git a/drivers/dma/uniphier-mdmac.c b/drivers/dma/uniphier-mdmac.c
index ad7125f6e2ca8..7a99f86ecb5a0 100644
--- a/drivers/dma/uniphier-mdmac.c
+++ b/drivers/dma/uniphier-mdmac.c
@@ -493,7 +493,7 @@ MODULE_DEVICE_TABLE(of, uniphier_mdmac_match);
 
 static struct platform_driver uniphier_mdmac_driver = {
 	.probe = uniphier_mdmac_probe,
-	.remove_new = uniphier_mdmac_remove,
+	.remove = uniphier_mdmac_remove,
 	.driver = {
 		.name = "uniphier-mio-dmac",
 		.of_match_table = uniphier_mdmac_match,
diff --git a/drivers/dma/uniphier-xdmac.c b/drivers/dma/uniphier-xdmac.c
index 3ce2dc2ad9de4..ceeb6171c9d11 100644
--- a/drivers/dma/uniphier-xdmac.c
+++ b/drivers/dma/uniphier-xdmac.c
@@ -603,7 +603,7 @@ MODULE_DEVICE_TABLE(of, uniphier_xdmac_match);
 
 static struct platform_driver uniphier_xdmac_driver = {
 	.probe = uniphier_xdmac_probe,
-	.remove_new = uniphier_xdmac_remove,
+	.remove = uniphier_xdmac_remove,
 	.driver = {
 		.name = "uniphier-xdmac",
 		.of_match_table = uniphier_xdmac_match,
diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c
index 275848a9c4502..f64624ea44add 100644
--- a/drivers/dma/xgene-dma.c
+++ b/drivers/dma/xgene-dma.c
@@ -1815,7 +1815,7 @@ MODULE_DEVICE_TABLE(of, xgene_dma_of_match_ptr);
 
 static struct platform_driver xgene_dma_driver = {
 	.probe = xgene_dma_probe,
-	.remove_new = xgene_dma_remove,
+	.remove = xgene_dma_remove,
 	.driver = {
 		.name = "X-Gene-DMA",
 		.of_match_table = xgene_dma_of_match_ptr,
diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 718842fdaf98e..93772abc3b49f 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -1315,7 +1315,7 @@ static struct platform_driver xdma_driver = {
 	},
 	.id_table	= xdma_id_table,
 	.probe		= xdma_probe,
-	.remove_new	= xdma_remove,
+	.remove		= xdma_remove,
 };
 
 module_platform_driver(xdma_driver);
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 5eb51ae93e89d..1bdd57de87a6e 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -3271,7 +3271,7 @@ static struct platform_driver xilinx_vdma_driver = {
 		.of_match_table = xilinx_dma_of_ids,
 	},
 	.probe = xilinx_dma_probe,
-	.remove_new = xilinx_dma_remove,
+	.remove = xilinx_dma_remove,
 };
 
 module_platform_driver(xilinx_vdma_driver);
diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c
index be87764af9e83..ee5d9fdbfd7fa 100644
--- a/drivers/dma/xilinx/xilinx_dpdma.c
+++ b/drivers/dma/xilinx/xilinx_dpdma.c
@@ -1863,7 +1863,7 @@ MODULE_DEVICE_TABLE(of, xilinx_dpdma_of_match);
 
 static struct platform_driver xilinx_dpdma_driver = {
 	.probe			= xilinx_dpdma_probe,
-	.remove_new		= xilinx_dpdma_remove,
+	.remove			= xilinx_dpdma_remove,
 	.driver			= {
 		.name		= "xilinx-zynqmp-dpdma",
 		.of_match_table	= xilinx_dpdma_of_match,
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index 9ae46f1198fe6..3156eff5deb07 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -1192,7 +1192,7 @@ static struct platform_driver zynqmp_dma_driver = {
 		.pm = &zynqmp_dma_dev_pm_ops,
 	},
 	.probe = zynqmp_dma_probe,
-	.remove_new = zynqmp_dma_remove,
+	.remove = zynqmp_dma_remove,
 };
 
 module_platform_driver(zynqmp_dma_driver);

From 04042674b21a8dfa143abacf7b1ef5b25a58d86e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 9 Oct 2024 13:20:08 -0700
Subject: [PATCH 0312/1530] perf tools: Fix possible compiler warnings in
 hashmap
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The hashmap__for_each_entry[_safe] is accessing 'map' as if it's a
pointer.  But it does without parentheses so passing a static hash map
with an ampersand (like &slab_hash below) caused compiler warnings due
to unmatched types.

  In file included from util/bpf_lock_contention.c:5:
  util/bpf_lock_contention.c: In function ‘exit_slab_cache_iter’:
  linux/tools/perf/util/hashmap.h:169:32: error: invalid type argument of ‘->’ (have ‘struct hashmap’)
    169 |         for (bkt = 0; bkt < map->cap; bkt++)                                \
        |                                ^~
  util/bpf_lock_contention.c:105:9: note: in expansion of macro ‘hashmap__for_each_entry’
    105 |         hashmap__for_each_entry(&slab_hash, cur, bkt)
        |         ^~~~~~~~~~~~~~~~~~~~~~~
  /home/namhyung/project/linux/tools/perf/util/hashmap.h:170:31: error: invalid type argument of ‘->’ (have ‘struct hashmap’)
    170 |                 for (cur = map->buckets[bkt]; cur; cur = cur->next)
        |                               ^~
  util/bpf_lock_contention.c:105:9: note: in expansion of macro ‘hashmap__for_each_entry’
    105 |         hashmap__for_each_entry(&slab_hash, cur, bkt)
        |         ^~~~~~~~~~~~~~~~~~~~~~~

Cc: bpf@vger.kernel.org
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20241009202009.884884-1-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/hashmap.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h
index c12f8320e6682..0c4f155e8eb74 100644
--- a/tools/perf/util/hashmap.h
+++ b/tools/perf/util/hashmap.h
@@ -166,8 +166,8 @@ bool hashmap_find(const struct hashmap *map, long key, long *value);
  * @bkt: integer used as a bucket loop cursor
  */
 #define hashmap__for_each_entry(map, cur, bkt)				    \
-	for (bkt = 0; bkt < map->cap; bkt++)				    \
-		for (cur = map->buckets[bkt]; cur; cur = cur->next)
+	for (bkt = 0; bkt < (map)->cap; bkt++)				    \
+		for (cur = (map)->buckets[bkt]; cur; cur = cur->next)
 
 /*
  * hashmap__for_each_entry_safe - iterate over all entries in hashmap, safe
@@ -178,8 +178,8 @@ bool hashmap_find(const struct hashmap *map, long key, long *value);
  * @bkt: integer used as a bucket loop cursor
  */
 #define hashmap__for_each_entry_safe(map, cur, tmp, bkt)		    \
-	for (bkt = 0; bkt < map->cap; bkt++)				    \
-		for (cur = map->buckets[bkt];				    \
+	for (bkt = 0; bkt < (map)->cap; bkt++)				    \
+		for (cur = (map)->buckets[bkt];				    \
 		     cur && ({tmp = cur->next; true; });		    \
 		     cur = tmp)
 
@@ -190,19 +190,19 @@ bool hashmap_find(const struct hashmap *map, long key, long *value);
  * @key: key to iterate entries for
  */
 #define hashmap__for_each_key_entry(map, cur, _key)			    \
-	for (cur = map->buckets						    \
-		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+	for (cur = (map)->buckets					    \
+		     ? (map)->buckets[hash_bits((map)->hash_fn((_key), (map)->ctx), (map)->cap_bits)] \
 		     : NULL;						    \
 	     cur;							    \
 	     cur = cur->next)						    \
-		if (map->equal_fn(cur->key, (_key), map->ctx))
+		if ((map)->equal_fn(cur->key, (_key), (map)->ctx))
 
 #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key)		    \
-	for (cur = map->buckets						    \
-		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+	for (cur = (map)->buckets					    \
+		     ? (map)->buckets[hash_bits((map)->hash_fn((_key), (map)->ctx), (map)->cap_bits)] \
 		     : NULL;						    \
 	     cur && ({ tmp = cur->next; true; });			    \
 	     cur = tmp)							    \
-		if (map->equal_fn(cur->key, (_key), map->ctx))
+		if ((map)->equal_fn(cur->key, (_key), (map)->ctx))
 
 #endif /* __LIBBPF_HASHMAP_H */

From af3902bfc1b60941681a0db9db95d8fe3d5c785d Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 9 Oct 2024 13:20:09 -0700
Subject: [PATCH 0313/1530] perf tools: Remove unnecessary parentheses

The hashmap API used to require parentheses for the hashmap argument if
it's not a pointer type.  It's now fixed so let's drop the parentheses.

Link: https://lore.kernel.org/r/20241009202009.884884-2-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/threads.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/threads.c b/tools/perf/util/threads.c
index ff2b169e0085e..6ca0b178fb6c3 100644
--- a/tools/perf/util/threads.c
+++ b/tools/perf/util/threads.c
@@ -141,7 +141,7 @@ void threads__remove_all_threads(struct threads *threads)
 
 		down_write(&table->lock);
 		__threads_table_entry__set_last_match(table, NULL);
-		hashmap__for_each_entry_safe((&table->shard), cur, tmp, bkt) {
+		hashmap__for_each_entry_safe(&table->shard, cur, tmp, bkt) {
 			struct thread *old_value;
 
 			hashmap__delete(&table->shard, cur->key, /*old_key=*/NULL, &old_value);
@@ -175,7 +175,7 @@ int threads__for_each_thread(struct threads *threads,
 		size_t bkt;
 
 		down_read(&table->lock);
-		hashmap__for_each_entry((&table->shard), cur, bkt) {
+		hashmap__for_each_entry(&table->shard, cur, bkt) {
 			int rc = fn((struct thread *)cur->pvalue, data);
 
 			if (rc != 0) {

From cd912ab3b65445df7b95bbdd06ac29f823d4df98 Mon Sep 17 00:00:00 2001
From: Madadi Vineeth Reddy <vineethr@linux.ibm.com>
Date: Fri, 4 Oct 2024 22:37:56 +0530
Subject: [PATCH 0314/1530] perf sched timehist: Add pre-migration wait time
 option

pre-migration wait time is the time that a task unnecessarily spends
on the runqueue of a CPU but doesn't get switched-in there. In terms
of tracepoints, it is the time between sched:sched_wakeup and
sched:sched_migrate_task.

Let's say a task woke up on CPU2, then it got migrated to CPU4 and
then it's switched-in to CPU4. So, here pre-migration wait time is
time that it was waiting on runqueue of CPU2 after it is woken up.

The general pattern for pre-migration to occur is:
sched:sched_wakeup
sched:sched_migrate_task
sched:sched_switch

The sched:sched_waking event is used to capture the wakeup time,
as it aligns with the existing code and only introduces a negligible
time difference.

pre-migrations are generally not useful and it increases migrations.
This metric would be helpful in testing patches mainly related to wakeup
and load-balancer code paths as better wakeup logic would choose an
optimal CPU where task would be switched-in and thereby reducing pre-
migrations.

The sample output(s) when -P or --pre-migrations is used:
=================
           time    cpu  task name                       wait time  sch delay   run time  pre-mig time
                        [tid/pid]                          (msec)     (msec)     (msec)     (msec)
--------------- ------  ------------------------------  ---------  ---------  ---------  ---------
   38456.720806 [0001]  schbench[28634/28574]               4.917      4.768      1.004      0.000
   38456.720810 [0001]  rcu_preempt[18]                     3.919      0.003      0.004      0.000
   38456.721800 [0006]  schbench[28779/28574]              23.465     23.465      1.999      0.000
   38456.722800 [0002]  schbench[28773/28574]              60.371     60.237      3.955     60.197
   38456.722806 [0001]  schbench[28634/28574]               0.004      0.004      1.996      0.000
   38456.722811 [0001]  rcu_preempt[18]                     1.996      0.005      0.005      0.000
   38456.723800 [0000]  schbench[28833/28574]               4.000      4.000      3.999      0.000
   38456.723800 [0004]  schbench[28762/28574]              42.951     42.839      3.999     39.867
   38456.723802 [0007]  schbench[28812/28574]              43.947     43.817      3.999     40.866
   38456.723804 [0001]  schbench[28587/28574]               7.935      7.822      0.993      0.000

Signed-off-by: Madadi Vineeth Reddy <vineethr@linux.ibm.com>
Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
Link: https://lore.kernel.org/r/20241004170756.18064-1-vineethr@linux.ibm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Documentation/perf-sched.txt |  8 ++
 tools/perf/builtin-sched.c              | 98 +++++++++++++++----------
 2 files changed, 67 insertions(+), 39 deletions(-)

diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 3db64954a267a..6dbbddb6464d0 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -221,6 +221,14 @@ OPTIONS for 'perf sched timehist'
 	priorities are specified with -: 120-129. A combination of both can also be
 	provided: 0,120-129.
 
+-P::
+--pre-migrations::
+	Show pre-migration wait time. pre-migration wait time is the time spent
+	by a task waiting on a runqueue but not getting the chance to run there
+	and is migrated to a different runqueue where it is finally run. This
+	time between sched_wakeup and migrate_task is the pre-migration wait
+	time.
+
 OPTIONS for 'perf sched replay'
 ------------------------------
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index fdf979aaf2758..c053074b98b41 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -225,6 +225,7 @@ struct perf_sched {
 	bool		show_wakeups;
 	bool		show_next;
 	bool		show_migrations;
+	bool		pre_migrations;
 	bool		show_state;
 	bool		show_prio;
 	u64		skipped_samples;
@@ -244,7 +245,9 @@ struct thread_runtime {
 	u64 dt_iowait;      /* time between CPU access by iowait (off cpu) */
 	u64 dt_preempt;     /* time between CPU access by preempt (off cpu) */
 	u64 dt_delay;       /* time between wakeup and sched-in */
+	u64 dt_pre_mig;     /* time between migration and wakeup */
 	u64 ready_to_run;   /* time of wakeup */
+	u64 migrated;	    /* time when a thread is migrated */
 
 	struct stats run_stats;
 	u64 total_run_time;
@@ -252,6 +255,7 @@ struct thread_runtime {
 	u64 total_iowait_time;
 	u64 total_preempt_time;
 	u64 total_delay_time;
+	u64 total_pre_mig_time;
 
 	char last_state;
 
@@ -2073,14 +2077,15 @@ static void timehist_header(struct perf_sched *sched)
 		printf(" ");
 	}
 
-	if (sched->show_prio) {
-		printf(" %-*s  %-*s  %9s  %9s  %9s",
-		       comm_width, "task name", MAX_PRIO_STR_LEN, "prio",
-		       "wait time", "sch delay", "run time");
-	} else {
-		printf(" %-*s  %9s  %9s  %9s", comm_width,
-		       "task name", "wait time", "sch delay", "run time");
-	}
+	printf(" %-*s", comm_width, "task name");
+
+	if (sched->show_prio)
+		printf("  %-*s", MAX_PRIO_STR_LEN, "prio");
+
+	printf("  %9s  %9s  %9s", "wait time", "sch delay", "run time");
+
+	if (sched->pre_migrations)
+		printf("  %9s", "pre-mig time");
 
 	if (sched->show_state)
 		printf("  %s", "state");
@@ -2095,17 +2100,15 @@ static void timehist_header(struct perf_sched *sched)
 	if (sched->show_cpu_visual)
 		printf(" %*s ", ncpus, "");
 
-	if (sched->show_prio) {
-		printf(" %-*s  %-*s  %9s  %9s  %9s",
-		       comm_width, "[tid/pid]", MAX_PRIO_STR_LEN, "",
-		       "(msec)", "(msec)", "(msec)");
-	} else {
-		printf(" %-*s  %9s  %9s  %9s", comm_width,
-		       "[tid/pid]", "(msec)", "(msec)", "(msec)");
-	}
+	printf(" %-*s", comm_width, "[tid/pid]");
 
-	if (sched->show_state)
-		printf("  %5s", "");
+	if (sched->show_prio)
+		printf("  %-*s", MAX_PRIO_STR_LEN, "");
+
+	printf("  %9s  %9s  %9s", "(msec)", "(msec)", "(msec)");
+
+	if (sched->pre_migrations)
+		printf("  %9s", "(msec)");
 
 	printf("\n");
 
@@ -2117,15 +2120,15 @@ static void timehist_header(struct perf_sched *sched)
 	if (sched->show_cpu_visual)
 		printf(" %.*s ", ncpus, graph_dotted_line);
 
-	if (sched->show_prio) {
-		printf(" %.*s  %.*s  %.9s  %.9s  %.9s",
-		       comm_width, graph_dotted_line, MAX_PRIO_STR_LEN, graph_dotted_line,
-		       graph_dotted_line, graph_dotted_line, graph_dotted_line);
-	} else {
-		printf(" %.*s  %.9s  %.9s  %.9s", comm_width,
-		       graph_dotted_line, graph_dotted_line, graph_dotted_line,
-		       graph_dotted_line);
-	}
+	printf(" %.*s", comm_width, graph_dotted_line);
+
+	if (sched->show_prio)
+		printf("  %.*s", MAX_PRIO_STR_LEN, graph_dotted_line);
+
+	printf("  %.9s  %.9s  %.9s", graph_dotted_line, graph_dotted_line, graph_dotted_line);
+
+	if (sched->pre_migrations)
+		printf("  %.9s", graph_dotted_line);
 
 	if (sched->show_state)
 		printf("  %.5s", graph_dotted_line);
@@ -2180,6 +2183,8 @@ static void timehist_print_sample(struct perf_sched *sched,
 
 	print_sched_time(tr->dt_delay, 6);
 	print_sched_time(tr->dt_run, 6);
+	if (sched->pre_migrations)
+		print_sched_time(tr->dt_pre_mig, 6);
 
 	if (sched->show_state)
 		printf(" %5c ", thread__tid(thread) == 0 ? 'I' : state);
@@ -2217,18 +2222,21 @@ static void timehist_print_sample(struct perf_sched *sched,
  *    last_time = time of last sched change event for current task
  *                (i.e, time process was last scheduled out)
  * ready_to_run = time of wakeup for current task
+ *     migrated = time of task migration to another CPU
  *
- * -----|------------|------------|------------|------
- *    last         ready        tprev          t
+ * -----|-------------|-------------|-------------|-------------|-----
+ *    last         ready         migrated       tprev           t
  *    time         to run
  *
- *      |-------- dt_wait --------|
- *                   |- dt_delay -|-- dt_run --|
+ *      |---------------- dt_wait ----------------|
+ *                   |--------- dt_delay ---------|-- dt_run --|
+ *                   |- dt_pre_mig -|
  *
- *   dt_run = run time of current task
- *  dt_wait = time between last schedule out event for task and tprev
- *            represents time spent off the cpu
- * dt_delay = time between wakeup and schedule-in of task
+ *     dt_run = run time of current task
+ *    dt_wait = time between last schedule out event for task and tprev
+ *              represents time spent off the cpu
+ *   dt_delay = time between wakeup and schedule-in of task
+ * dt_pre_mig = time between wakeup and migration to another CPU
  */
 
 static void timehist_update_runtime_stats(struct thread_runtime *r,
@@ -2239,6 +2247,7 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
 	r->dt_iowait  = 0;
 	r->dt_preempt = 0;
 	r->dt_run     = 0;
+	r->dt_pre_mig = 0;
 
 	if (tprev) {
 		r->dt_run = t - tprev;
@@ -2247,6 +2256,9 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
 				pr_debug("time travel: wakeup time for task > previous sched_switch event\n");
 			else
 				r->dt_delay = tprev - r->ready_to_run;
+
+			if ((r->migrated > r->ready_to_run) && (r->migrated < tprev))
+				r->dt_pre_mig = r->migrated - r->ready_to_run;
 		}
 
 		if (r->last_time > tprev)
@@ -2270,6 +2282,7 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
 	r->total_sleep_time   += r->dt_sleep;
 	r->total_iowait_time  += r->dt_iowait;
 	r->total_preempt_time += r->dt_preempt;
+	r->total_pre_mig_time += r->dt_pre_mig;
 }
 
 static bool is_idle_sample(struct perf_sample *sample,
@@ -2683,9 +2696,13 @@ static int timehist_migrate_task_event(const struct perf_tool *tool,
 		return -1;
 
 	tr->migrations++;
+	tr->migrated = sample->time;
 
 	/* show migrations if requested */
-	timehist_print_migration_event(sched, evsel, sample, machine, thread);
+	if (sched->show_migrations) {
+		timehist_print_migration_event(sched, evsel, sample,
+							machine, thread);
+	}
 
 	return 0;
 }
@@ -2836,11 +2853,13 @@ static int timehist_sched_change_event(const struct perf_tool *tool,
 		/* last state is used to determine where to account wait time */
 		tr->last_state = state;
 
-		/* sched out event for task so reset ready to run time */
+		/* sched out event for task so reset ready to run time and migrated time */
 		if (state == 'R')
 			tr->ready_to_run = t;
 		else
 			tr->ready_to_run = 0;
+
+		tr->migrated = 0;
 	}
 
 	evsel__save_time(evsel, sample->time, sample->cpu);
@@ -3280,8 +3299,8 @@ static int perf_sched__timehist(struct perf_sched *sched)
 		goto out;
 	}
 
-	if (sched->show_migrations &&
-	    perf_session__set_tracepoints_handlers(session, migrate_handlers))
+	if ((sched->show_migrations || sched->pre_migrations) &&
+		perf_session__set_tracepoints_handlers(session, migrate_handlers))
 		goto out;
 
 	/* pre-allocate struct for per-CPU idle stats */
@@ -3823,6 +3842,7 @@ int cmd_sched(int argc, const char **argv)
 	OPT_BOOLEAN(0, "show-prio", &sched.show_prio, "Show task priority"),
 	OPT_STRING(0, "prio", &sched.prio_str, "prio",
 		   "analyze events only for given task priority(ies)"),
+	OPT_BOOLEAN('P', "pre-migrations", &sched.pre_migrations, "Show pre-migration wait time"),
 	OPT_PARENT(sched_options)
 	};
 

From 1afe05b0cf183035a77fdda1bc633aa5fb9daa43 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 8 Oct 2024 23:22:50 -0700
Subject: [PATCH 0315/1530] perf evsel: Fix missing inherit + sample read check

It should not clear the inherit bit simply because the kernel doesn't
support the sample read with it.  IOW the inherit bit should be kept
when the sample read is not requested for the event.

Fixes: 90035d3cd876cb71 ("tools/perf: Allow inherit + PERF_SAMPLE_READ when opening events")
Acked-by: Ben Gainey <ben.gainey@arm.com>
Link: https://lore.kernel.org/r/20241009062250.730192-1-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/evsel.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ed0d4d20e3576..e9e1f576d34dd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1915,7 +1915,8 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 
 static void evsel__disable_missing_features(struct evsel *evsel)
 {
-	if (perf_missing_features.inherit_sample_read)
+	if (perf_missing_features.inherit_sample_read && evsel->core.attr.inherit &&
+	    (evsel->core.attr.sample_type & PERF_SAMPLE_READ))
 		evsel->core.attr.inherit = 0;
 	if (perf_missing_features.branch_counters)
 		evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_COUNTERS;

From 0c383c0827ec73c0c349a2f1eef3e7b9c189fc52 Mon Sep 17 00:00:00 2001
From: Howard Chu <howardchu95@gmail.com>
Date: Thu, 10 Oct 2024 22:57:00 -0700
Subject: [PATCH 0316/1530] perf test: Delete unused Intel CQM test

As Ian Rogers <irogers@google.com> pointed out, intel-cqm.c is neither
used nor built. It was deleted in the following commit:

commit b24413180f56 ("License cleanup: add SPDX GPL-2.0 license identifier to files with no license")

However, it resurfaced soon after in the following commit:

commit 5c9295bfe6f5 ("perf tests: Remove Intel CQM perf test")

It should be deleted once and for all.

Suggested-by: Ian Rogers <irogers@google.com>
Signed-off-by: Howard Chu <howardchu95@gmail.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Reviewed-by: Matt Fleming <mfleming@cloudflare.com>
Link: https://lore.kernel.org/r/20241011055700.4142694-1-howardchu95@gmail.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/x86/tests/intel-cqm.c | 128 --------------------------
 1 file changed, 128 deletions(-)
 delete mode 100644 tools/perf/arch/x86/tests/intel-cqm.c

diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
deleted file mode 100644
index 360a082fc9280..0000000000000
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ /dev/null
@@ -1,128 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include "tests/tests.h"
-#include "cloexec.h"
-#include "debug.h"
-#include "evlist.h"
-#include "evsel.h"
-#include "arch-tests.h"
-#include <internal/lib.h> // page_size
-
-#include <signal.h>
-#include <sys/mman.h>
-#include <sys/wait.h>
-#include <errno.h>
-#include <string.h>
-
-static pid_t spawn(void)
-{
-	pid_t pid;
-
-	pid = fork();
-	if (pid)
-		return pid;
-
-	while(1)
-		sleep(5);
-	return 0;
-}
-
-/*
- * Create an event group that contains both a sampled hardware
- * (cpu-cycles) and software (intel_cqm/llc_occupancy/) event. We then
- * wait for the hardware perf counter to overflow and generate a PMI,
- * which triggers an event read for both of the events in the group.
- *
- * Since reading Intel CQM event counters requires sending SMP IPIs, the
- * CQM pmu needs to handle the above situation gracefully, and return
- * the last read counter value to avoid triggering a WARN_ON_ONCE() in
- * smp_call_function_many() caused by sending IPIs from NMI context.
- */
-int test__intel_cqm_count_nmi_context(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
-{
-	struct evlist *evlist = NULL;
-	struct evsel *evsel = NULL;
-	struct perf_event_attr pe;
-	int i, fd[2], flag, ret;
-	size_t mmap_len;
-	void *event;
-	pid_t pid;
-	int err = TEST_FAIL;
-
-	flag = perf_event_open_cloexec_flag();
-
-	evlist = evlist__new();
-	if (!evlist) {
-		pr_debug("evlist__new failed\n");
-		return TEST_FAIL;
-	}
-
-	ret = parse_event(evlist, "intel_cqm/llc_occupancy/");
-	if (ret) {
-		pr_debug("parse_events failed, is \"intel_cqm/llc_occupancy/\" available?\n");
-		err = TEST_SKIP;
-		goto out;
-	}
-
-	evsel = evlist__first(evlist);
-	if (!evsel) {
-		pr_debug("evlist__first failed\n");
-		goto out;
-	}
-
-	memset(&pe, 0, sizeof(pe));
-	pe.size = sizeof(pe);
-
-	pe.type = PERF_TYPE_HARDWARE;
-	pe.config = PERF_COUNT_HW_CPU_CYCLES;
-	pe.read_format = PERF_FORMAT_GROUP;
-
-	pe.sample_period = 128;
-	pe.sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_READ;
-
-	pid = spawn();
-
-	fd[0] = sys_perf_event_open(&pe, pid, -1, -1, flag);
-	if (fd[0] < 0) {
-		pr_debug("failed to open event\n");
-		goto out;
-	}
-
-	memset(&pe, 0, sizeof(pe));
-	pe.size = sizeof(pe);
-
-	pe.type = evsel->attr.type;
-	pe.config = evsel->attr.config;
-
-	fd[1] = sys_perf_event_open(&pe, pid, -1, fd[0], flag);
-	if (fd[1] < 0) {
-		pr_debug("failed to open event\n");
-		goto out;
-	}
-
-	/*
-	 * Pick a power-of-two number of pages + 1 for the meta-data
-	 * page (struct perf_event_mmap_page). See tools/perf/design.txt.
-	 */
-	mmap_len = page_size * 65;
-
-	event = mmap(NULL, mmap_len, PROT_READ, MAP_SHARED, fd[0], 0);
-	if (event == (void *)(-1)) {
-		pr_debug("failed to mmap %d\n", errno);
-		goto out;
-	}
-
-	sleep(1);
-
-	err = TEST_OK;
-
-	munmap(event, mmap_len);
-
-	for (i = 0; i < 2; i++)
-		close(fd[i]);
-
-	kill(pid, SIGKILL);
-	wait(NULL);
-out:
-	evlist__delete(evlist);
-	return err;
-}

From fb98fa3bf86893e53fac7bc951f503caf4a6eb23 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Thu, 3 Oct 2024 19:53:16 +0100
Subject: [PATCH 0317/1530] perf arm-spe: Rename
 arm_spe__synth_data_source_generic()

The arm_spe__synth_data_source_generic() function is invoked when the
tool detects that CPUs do not support data source packets and falls back
to synthesizing only the memory level.

Rename it to arm_spe__synth_memory_level() for better reflecting its
purpose.

Signed-off-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Link: https://lore.kernel.org/r/20241003185322.192357-2-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/arm-spe.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 13fd2c8afebdf..34e147e8a9636 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -496,8 +496,8 @@ static void arm_spe__synth_data_source_neoverse(const struct arm_spe_record *rec
 	}
 }
 
-static void arm_spe__synth_data_source_generic(const struct arm_spe_record *record,
-					       union perf_mem_data_src *data_src)
+static void arm_spe__synth_memory_level(const struct arm_spe_record *record,
+					union perf_mem_data_src *data_src)
 {
 	if (record->type & (ARM_SPE_LLC_ACCESS | ARM_SPE_LLC_MISS)) {
 		data_src->mem_lvl = PERF_MEM_LVL_L3;
@@ -534,7 +534,7 @@ static u64 arm_spe__synth_data_source(const struct arm_spe_record *record, u64 m
 	if (is_neoverse)
 		arm_spe__synth_data_source_neoverse(record, &data_src);
 	else
-		arm_spe__synth_data_source_generic(record, &data_src);
+		arm_spe__synth_memory_level(record, &data_src);
 
 	if (record->type & (ARM_SPE_TLB_ACCESS | ARM_SPE_TLB_MISS)) {
 		data_src.mem_dtlb = PERF_MEM_TLB_WK;

From 50b8f1d5bf4ad7f09ef8012ccf5f94f741df827b Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Thu, 3 Oct 2024 19:53:17 +0100
Subject: [PATCH 0318/1530] perf arm-spe: Rename the common data source
 encoding

The Neoverse CPUs follow the common data source encoding, and other
CPU variants can share the same format.

Rename the CPU list and data source definitions as common data source
names. This change prepares for appending more CPU variants.

Signed-off-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Link: https://lore.kernel.org/r/20241003185322.192357-3-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../util/arm-spe-decoder/arm-spe-decoder.h    | 18 ++++++------
 tools/perf/util/arm-spe.c                     | 28 +++++++++----------
 2 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
index 1443c28545a94..358c611eeddbb 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
@@ -56,15 +56,15 @@ enum arm_spe_op_type {
 	ARM_SPE_OP_BR_INDIRECT	= 1 << 17,
 };
 
-enum arm_spe_neoverse_data_source {
-	ARM_SPE_NV_L1D		 = 0x0,
-	ARM_SPE_NV_L2		 = 0x8,
-	ARM_SPE_NV_PEER_CORE	 = 0x9,
-	ARM_SPE_NV_LOCAL_CLUSTER = 0xa,
-	ARM_SPE_NV_SYS_CACHE	 = 0xb,
-	ARM_SPE_NV_PEER_CLUSTER	 = 0xc,
-	ARM_SPE_NV_REMOTE	 = 0xd,
-	ARM_SPE_NV_DRAM		 = 0xe,
+enum arm_spe_common_data_source {
+	ARM_SPE_COMMON_DS_L1D		= 0x0,
+	ARM_SPE_COMMON_DS_L2		= 0x8,
+	ARM_SPE_COMMON_DS_PEER_CORE	= 0x9,
+	ARM_SPE_COMMON_DS_LOCAL_CLUSTER = 0xa,
+	ARM_SPE_COMMON_DS_SYS_CACHE	= 0xb,
+	ARM_SPE_COMMON_DS_PEER_CLUSTER	= 0xc,
+	ARM_SPE_COMMON_DS_REMOTE	= 0xd,
+	ARM_SPE_COMMON_DS_DRAM		= 0xe,
 };
 
 struct arm_spe_record {
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 34e147e8a9636..b0e9eb6057c3b 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -413,15 +413,15 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,
 	return arm_spe_deliver_synth_event(spe, speq, event, &sample);
 }
 
-static const struct midr_range neoverse_spe[] = {
+static const struct midr_range common_ds_encoding_cpus[] = {
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),
 	{},
 };
 
-static void arm_spe__synth_data_source_neoverse(const struct arm_spe_record *record,
-						union perf_mem_data_src *data_src)
+static void arm_spe__synth_data_source_common(const struct arm_spe_record *record,
+					      union perf_mem_data_src *data_src)
 {
 	/*
 	 * Even though four levels of cache hierarchy are possible, no known
@@ -443,17 +443,17 @@ static void arm_spe__synth_data_source_neoverse(const struct arm_spe_record *rec
 	}
 
 	switch (record->source) {
-	case ARM_SPE_NV_L1D:
+	case ARM_SPE_COMMON_DS_L1D:
 		data_src->mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
 		data_src->mem_lvl_num = PERF_MEM_LVLNUM_L1;
 		data_src->mem_snoop = PERF_MEM_SNOOP_NONE;
 		break;
-	case ARM_SPE_NV_L2:
+	case ARM_SPE_COMMON_DS_L2:
 		data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT;
 		data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2;
 		data_src->mem_snoop = PERF_MEM_SNOOP_NONE;
 		break;
-	case ARM_SPE_NV_PEER_CORE:
+	case ARM_SPE_COMMON_DS_PEER_CORE:
 		data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT;
 		data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2;
 		data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
@@ -462,8 +462,8 @@ static void arm_spe__synth_data_source_neoverse(const struct arm_spe_record *rec
 	 * We don't know if this is L1, L2 but we do know it was a cache-2-cache
 	 * transfer, so set SNOOPX_PEER
 	 */
-	case ARM_SPE_NV_LOCAL_CLUSTER:
-	case ARM_SPE_NV_PEER_CLUSTER:
+	case ARM_SPE_COMMON_DS_LOCAL_CLUSTER:
+	case ARM_SPE_COMMON_DS_PEER_CLUSTER:
 		data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT;
 		data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3;
 		data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
@@ -471,7 +471,7 @@ static void arm_spe__synth_data_source_neoverse(const struct arm_spe_record *rec
 	/*
 	 * System cache is assumed to be L3
 	 */
-	case ARM_SPE_NV_SYS_CACHE:
+	case ARM_SPE_COMMON_DS_SYS_CACHE:
 		data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT;
 		data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3;
 		data_src->mem_snoop = PERF_MEM_SNOOP_HIT;
@@ -480,13 +480,13 @@ static void arm_spe__synth_data_source_neoverse(const struct arm_spe_record *rec
 	 * We don't know what level it hit in, except it came from the other
 	 * socket
 	 */
-	case ARM_SPE_NV_REMOTE:
+	case ARM_SPE_COMMON_DS_REMOTE:
 		data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1;
 		data_src->mem_lvl_num = PERF_MEM_LVLNUM_ANY_CACHE;
 		data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
 		data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
 		break;
-	case ARM_SPE_NV_DRAM:
+	case ARM_SPE_COMMON_DS_DRAM:
 		data_src->mem_lvl = PERF_MEM_LVL_LOC_RAM | PERF_MEM_LVL_HIT;
 		data_src->mem_lvl_num = PERF_MEM_LVLNUM_RAM;
 		data_src->mem_snoop = PERF_MEM_SNOOP_NONE;
@@ -522,7 +522,7 @@ static void arm_spe__synth_memory_level(const struct arm_spe_record *record,
 static u64 arm_spe__synth_data_source(const struct arm_spe_record *record, u64 midr)
 {
 	union perf_mem_data_src	data_src = { .mem_op = PERF_MEM_OP_NA };
-	bool is_neoverse = is_midr_in_range_list(midr, neoverse_spe);
+	bool is_common = is_midr_in_range_list(midr, common_ds_encoding_cpus);
 
 	if (record->op & ARM_SPE_OP_LD)
 		data_src.mem_op = PERF_MEM_OP_LOAD;
@@ -531,8 +531,8 @@ static u64 arm_spe__synth_data_source(const struct arm_spe_record *record, u64 m
 	else
 		return 0;
 
-	if (is_neoverse)
-		arm_spe__synth_data_source_neoverse(record, &data_src);
+	if (is_common)
+		arm_spe__synth_data_source_common(record, &data_src);
 	else
 		arm_spe__synth_memory_level(record, &data_src);
 

From 56ae663e7636f2ce180201f0f18d7736c319a43f Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Thu, 3 Oct 2024 19:53:18 +0100
Subject: [PATCH 0319/1530] perf arm-spe: Introduce arm_spe__is_homogeneous()

Introduce the arm_spe__is_homogeneous() function, it uses to check if
Arm SPE is homogeneous cross all CPUs.

Signed-off-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Link: https://lore.kernel.org/r/20241003185322.192357-4-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/arm-spe.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index b0e9eb6057c3b..587943b6bdb80 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -82,6 +82,7 @@ struct arm_spe {
 	u64				**metadata;
 	u64				metadata_ver;
 	u64				metadata_nr_cpu;
+	bool				is_homogeneous;
 };
 
 struct arm_spe_queue {
@@ -1374,6 +1375,30 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
 	return 0;
 }
 
+static bool arm_spe__is_homogeneous(u64 **metadata, int nr_cpu)
+{
+	u64 midr;
+	int i;
+
+	if (!nr_cpu)
+		return false;
+
+	for (i = 0; i < nr_cpu; i++) {
+		if (!metadata[i])
+			return false;
+
+		if (i == 0) {
+			midr = metadata[i][ARM_SPE_CPU_MIDR];
+			continue;
+		}
+
+		if (midr != metadata[i][ARM_SPE_CPU_MIDR])
+			return false;
+	}
+
+	return true;
+}
+
 int arm_spe_process_auxtrace_info(union perf_event *event,
 				  struct perf_session *session)
 {
@@ -1419,6 +1444,7 @@ int arm_spe_process_auxtrace_info(union perf_event *event,
 	spe->metadata = metadata;
 	spe->metadata_ver = metadata_ver;
 	spe->metadata_nr_cpu = nr_cpu;
+	spe->is_homogeneous = arm_spe__is_homogeneous(metadata, nr_cpu);
 
 	spe->timeless_decoding = arm_spe__is_timeless_decoding(spe);
 

From ba5e7169e5483a61899497e23fa18f7ef33aa827 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Thu, 3 Oct 2024 19:53:19 +0100
Subject: [PATCH 0320/1530] perf arm-spe: Use metadata to decide the data
 source feature

Use the info in the metadata to decide if the data source feature is
supported. The CPU MIDR must be in the CPU list for the common data
source encoding.

For the metadata version 1, it doesn't include info for MIDR. In this
case, due to absent info for making decision, print out warning to
remind users to upgrade tool and returns false.

Signed-off-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Link: https://lore.kernel.org/r/20241003185322.192357-5-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/arm-spe.c | 67 +++++++++++++++++++++++++++++++++++++--
 1 file changed, 64 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 587943b6bdb80..9221b2f66bbee 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -278,6 +278,20 @@ static int arm_spe_set_tid(struct arm_spe_queue *speq, pid_t tid)
 	return 0;
 }
 
+static u64 *arm_spe__get_metadata_by_cpu(struct arm_spe *spe, u64 cpu)
+{
+	u64 i;
+
+	if (!spe->metadata)
+		return NULL;
+
+	for (i = 0; i < spe->metadata_nr_cpu; i++)
+		if (spe->metadata[i][ARM_SPE_CPU] == cpu)
+			return spe->metadata[i];
+
+	return NULL;
+}
+
 static struct simd_flags arm_spe__synth_simd_flags(const struct arm_spe_record *record)
 {
 	struct simd_flags simd_flags = {};
@@ -520,10 +534,57 @@ static void arm_spe__synth_memory_level(const struct arm_spe_record *record,
 		data_src->mem_lvl |= PERF_MEM_LVL_REM_CCE1;
 }
 
-static u64 arm_spe__synth_data_source(const struct arm_spe_record *record, u64 midr)
+static bool arm_spe__is_common_ds_encoding(struct arm_spe_queue *speq)
+{
+	struct arm_spe *spe = speq->spe;
+	bool is_in_cpu_list;
+	u64 *metadata = NULL;
+	u64 midr = 0;
+
+	/*
+	 * Metadata version 1 doesn't contain any info for MIDR.
+	 * Simply return false in this case.
+	 */
+	if (spe->metadata_ver == 1) {
+		pr_warning_once("The data file contains metadata version 1, "
+				"which is absent the info for data source. "
+				"Please upgrade the tool to record data.\n");
+		return false;
+	}
+
+	/* CPU ID is -1 for per-thread mode */
+	if (speq->cpu < 0) {
+		/*
+		 * On the heterogeneous system, due to CPU ID is -1,
+		 * cannot confirm the data source packet is supported.
+		 */
+		if (!spe->is_homogeneous)
+			return false;
+
+		/* In homogeneous system, simply use CPU0's metadata */
+		if (spe->metadata)
+			metadata = spe->metadata[0];
+	} else {
+		metadata = arm_spe__get_metadata_by_cpu(spe, speq->cpu);
+	}
+
+	if (!metadata)
+		return false;
+
+	midr = metadata[ARM_SPE_CPU_MIDR];
+
+	is_in_cpu_list = is_midr_in_range_list(midr, common_ds_encoding_cpus);
+	if (is_in_cpu_list)
+		return true;
+	else
+		return false;
+}
+
+static u64 arm_spe__synth_data_source(struct arm_spe_queue *speq,
+				      const struct arm_spe_record *record)
 {
 	union perf_mem_data_src	data_src = { .mem_op = PERF_MEM_OP_NA };
-	bool is_common = is_midr_in_range_list(midr, common_ds_encoding_cpus);
+	bool is_common = arm_spe__is_common_ds_encoding(speq);
 
 	if (record->op & ARM_SPE_OP_LD)
 		data_src.mem_op = PERF_MEM_OP_LOAD;
@@ -556,7 +617,7 @@ static int arm_spe_sample(struct arm_spe_queue *speq)
 	u64 data_src;
 	int err;
 
-	data_src = arm_spe__synth_data_source(record, spe->midr);
+	data_src = arm_spe__synth_data_source(speq, record);
 
 	if (spe->sample_flc) {
 		if (record->type & ARM_SPE_L1D_MISS) {

From 6bcf54c89b3d8406433839f0e3b72c08b4a1caf3 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Thu, 3 Oct 2024 19:53:20 +0100
Subject: [PATCH 0321/1530] perf arm-spe: Remove the unused 'midr' field

The 'midr' field is replaced by the MIDR values stored in metadata (per
CPU wise). Remove the 'midr' field as it is no longer used.

Signed-off-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Link: https://lore.kernel.org/r/20241003185322.192357-6-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/arm-spe.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 9221b2f66bbee..485f60c323093 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -46,7 +46,6 @@ struct arm_spe {
 	struct perf_session		*session;
 	struct machine			*machine;
 	u32				pmu_type;
-	u64				midr;
 
 	struct perf_tsc_conversion	tc;
 
@@ -1466,8 +1465,6 @@ int arm_spe_process_auxtrace_info(union perf_event *event,
 	struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;
 	size_t min_sz = ARM_SPE_AUXTRACE_V1_PRIV_SIZE;
 	struct perf_record_time_conv *tc = &session->time_conv;
-	const char *cpuid = perf_env__cpuid(session->evlist->env);
-	u64 midr = strtol(cpuid, NULL, 16);
 	struct arm_spe *spe;
 	u64 **metadata = NULL;
 	u64 metadata_ver;
@@ -1501,7 +1498,6 @@ int arm_spe_process_auxtrace_info(union perf_event *event,
 		spe->pmu_type = auxtrace_info->priv[ARM_SPE_PMU_TYPE];
 	else
 		spe->pmu_type = auxtrace_info->priv[ARM_SPE_PMU_TYPE_V2];
-	spe->midr = midr;
 	spe->metadata = metadata;
 	spe->metadata_ver = metadata_ver;
 	spe->metadata_nr_cpu = nr_cpu;

From 041c0e5715a65a1b653283b853b4ca973780607a Mon Sep 17 00:00:00 2001
From: Besar Wicaksono <bwicaksono@nvidia.com>
Date: Thu, 3 Oct 2024 19:53:21 +0100
Subject: [PATCH 0322/1530] perf arm-spe: Add Neoverse-V2 to common data source
 encoding list

Add Neoverse-V2 MIDR to the common data source encoding range list.

Signed-off-by: Besar Wicaksono <bwicaksono@nvidia.com>
Reviewed-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: Leo Yan <leo.yan@linaro.org>
Reviewed-by: James Clark <james.clark@linaro.org>
Link: https://lore.kernel.org/r/20241003185322.192357-7-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/arm-spe.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 485f60c323093..5c34a9ae38629 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -431,6 +431,7 @@ static const struct midr_range common_ds_encoding_cpus[] = {
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),
+	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2),
 	{},
 };
 

From ea2ead4224fd3899f6dadd4c1fc526f32ec2246c Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Thu, 3 Oct 2024 19:53:22 +0100
Subject: [PATCH 0323/1530] perf arm-spe: Add Cortex CPUs to common data source
 encoding list

Add Cortex-A720, Cortex-A725, Cortex-X1C, Cortex-X3 and Cortex-X925 into
the common data source encoding list. For everyone of these CPUs, it
technical reference manual defines the data source packet as the common
encoding format.

Signed-off-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Link: https://lore.kernel.org/r/20241003185322.192357-8-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/arm-spe.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 5c34a9ae38629..c424e5b9a11d9 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -428,6 +428,11 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,
 }
 
 static const struct midr_range common_ds_encoding_cpus[] = {
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A720),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A725),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_X1C),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_X3),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_X925),
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),

From b19ee72722087c1d441193ce3b6b3d937ae16bf2 Mon Sep 17 00:00:00 2001
From: liuderong <liuderong@oppo.com>
Date: Wed, 18 Sep 2024 18:06:20 +0800
Subject: [PATCH 0324/1530] f2fs: introduce f2fs_get_section_mtime

When segs_per_sec is larger than 1, section may contain invalid segments,
mtime should be the average value of each valid blocks,
so introduce f2fs_get_section_mtime to
record the average mtime of all valid blocks in a section.

Signed-off-by: liuderong <liuderong@oppo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h    |  2 ++
 fs/f2fs/gc.c      | 17 ++++-------------
 fs/f2fs/segment.c | 35 ++++++++++++++++++++++++++++++-----
 fs/f2fs/segment.h |  2 ++
 4 files changed, 38 insertions(+), 18 deletions(-)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 33f5449dc22d5..60cf1e96a976d 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3783,6 +3783,8 @@ enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
 unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi);
 unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
 			unsigned int segno);
+unsigned long long f2fs_get_section_mtime(struct f2fs_sb_info *sbi,
+			unsigned int segno);
 
 #define DEF_FRAGMENT_SIZE	4
 #define MIN_FRAGMENT_SIZE	1
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 9322a7200e310..e40bdd12e36d1 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -361,20 +361,15 @@ static unsigned int check_bg_victims(struct f2fs_sb_info *sbi)
 static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
-	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
-	unsigned int start = GET_SEG_FROM_SEC(sbi, secno);
 	unsigned long long mtime = 0;
 	unsigned int vblocks;
 	unsigned char age = 0;
 	unsigned char u;
-	unsigned int i;
 	unsigned int usable_segs_per_sec = f2fs_usable_segs_in_sec(sbi);
 
-	for (i = 0; i < usable_segs_per_sec; i++)
-		mtime += get_seg_entry(sbi, start + i)->mtime;
+	mtime = f2fs_get_section_mtime(sbi, segno);
+	f2fs_bug_on(sbi, mtime == INVALID_MTIME);
 	vblocks = get_valid_blocks(sbi, segno, true);
-
-	mtime = div_u64(mtime, usable_segs_per_sec);
 	vblocks = div_u64(vblocks, usable_segs_per_sec);
 
 	u = BLKS_TO_SEGS(sbi, vblocks * 100);
@@ -519,10 +514,7 @@ static void add_victim_entry(struct f2fs_sb_info *sbi,
 				struct victim_sel_policy *p, unsigned int segno)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
-	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
-	unsigned int start = GET_SEG_FROM_SEC(sbi, secno);
 	unsigned long long mtime = 0;
-	unsigned int i;
 
 	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
 		if (p->gc_mode == GC_AT &&
@@ -530,9 +522,8 @@ static void add_victim_entry(struct f2fs_sb_info *sbi,
 			return;
 	}
 
-	for (i = 0; i < SEGS_PER_SEC(sbi); i++)
-		mtime += get_seg_entry(sbi, start + i)->mtime;
-	mtime = div_u64(mtime, SEGS_PER_SEC(sbi));
+	mtime = f2fs_get_section_mtime(sbi, segno);
+	f2fs_bug_on(sbi, mtime == INVALID_MTIME);
 
 	/* Handle if the system time has changed by the user */
 	if (mtime < sit_i->min_mtime)
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 1766254279d24..d91fbd1b27ba6 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -5430,6 +5430,35 @@ unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi)
 	return SEGS_PER_SEC(sbi);
 }
 
+unsigned long long f2fs_get_section_mtime(struct f2fs_sb_info *sbi,
+	unsigned int segno)
+{
+	unsigned int usable_segs_per_sec = f2fs_usable_segs_in_sec(sbi);
+	unsigned int secno = 0, start = 0;
+	unsigned int total_valid_blocks = 0;
+	unsigned long long mtime = 0;
+	unsigned int i = 0;
+
+	secno = GET_SEC_FROM_SEG(sbi, segno);
+	start = GET_SEG_FROM_SEC(sbi, secno);
+
+	if (!__is_large_section(sbi))
+		return get_seg_entry(sbi, start + i)->mtime;
+
+	for (i = 0; i < usable_segs_per_sec; i++) {
+		/* for large section, only check the mtime of valid segments */
+		struct seg_entry *se = get_seg_entry(sbi, start+i);
+
+		mtime += se->mtime * se->valid_blocks;
+		total_valid_blocks += se->valid_blocks;
+	}
+
+	if (total_valid_blocks == 0)
+		return INVALID_MTIME;
+
+	return div_u64(mtime, total_valid_blocks);
+}
+
 /*
  * Update min, max modified time for cost-benefit GC algorithm
  */
@@ -5443,13 +5472,9 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi)
 	sit_i->min_mtime = ULLONG_MAX;
 
 	for (segno = 0; segno < MAIN_SEGS(sbi); segno += SEGS_PER_SEC(sbi)) {
-		unsigned int i;
 		unsigned long long mtime = 0;
 
-		for (i = 0; i < SEGS_PER_SEC(sbi); i++)
-			mtime += get_seg_entry(sbi, segno + i)->mtime;
-
-		mtime = div_u64(mtime, SEGS_PER_SEC(sbi));
+		mtime = f2fs_get_section_mtime(sbi, segno);
 
 		if (sit_i->min_mtime > mtime)
 			sit_i->min_mtime = mtime;
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 71adb4a43bec5..e9cc73093417e 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -18,6 +18,8 @@
 #define F2FS_MIN_SEGMENTS	9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */
 #define F2FS_MIN_META_SEGMENTS	8 /* SB + 2 (CP + SIT + NAT) + SSA */
 
+#define INVALID_MTIME ULLONG_MAX /* no valid blocks in a segment/section */
+
 /* L: Logical segment # in volume, R: Relative segment # in main area */
 #define GET_L2R_SEGNO(free_i, segno)	((segno) - (free_i)->start_segno)
 #define GET_R2L_SEGNO(free_i, segno)	((segno) + (free_i)->start_segno)

From 527a4ded09b9266a5fb100e80e05b101b53053fd Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Mon, 7 Oct 2024 13:46:37 +0200
Subject: [PATCH 0325/1530] f2fs: Use struct_size() to improve f2fs_acl_clone()

Use struct_size() to calculate the number of bytes to allocate for a
cloned acl.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/acl.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 8bffdeccdbc3c..1fbc0607363bd 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -296,9 +296,8 @@ static struct posix_acl *f2fs_acl_clone(const struct posix_acl *acl,
 	struct posix_acl *clone = NULL;
 
 	if (acl) {
-		int size = sizeof(struct posix_acl) + acl->a_count *
-				sizeof(struct posix_acl_entry);
-		clone = kmemdup(acl, size, flags);
+		clone = kmemdup(acl, struct_size(acl, a_entries, acl->a_count),
+				flags);
 		if (clone)
 			refcount_set(&clone->a_refcount, 1);
 	}

From 26413ce18e85de3dda2cd3d72c3c3e8ab8f4f996 Mon Sep 17 00:00:00 2001
From: Qi Han <hanqi@vivo.com>
Date: Sun, 29 Sep 2024 02:00:10 -0600
Subject: [PATCH 0326/1530] f2fs: compress: fix inconsistent update of i_blocks
 in release_compress_blocks and reserve_compress_blocks

After release a file and subsequently reserve it, the FSCK flag is set
when the file is deleted, as shown in the following backtrace:

F2FS-fs (dm-48): Inconsistent i_blocks, ino:401231, iblocks:1448, sectors:1472
fs_rec_info_write_type+0x58/0x274
f2fs_rec_info_write+0x1c/0x2c
set_sbi_flag+0x74/0x98
dec_valid_block_count+0x150/0x190
f2fs_truncate_data_blocks_range+0x2d4/0x3cc
f2fs_do_truncate_blocks+0x2fc/0x5f0
f2fs_truncate_blocks+0x68/0x100
f2fs_truncate+0x80/0x128
f2fs_evict_inode+0x1a4/0x794
evict+0xd4/0x280
iput+0x238/0x284
do_unlinkat+0x1ac/0x298
__arm64_sys_unlinkat+0x48/0x68
invoke_syscall+0x58/0x11c

For clusters of the following type, i_blocks are decremented by 1 and
i_compr_blocks are incremented by 7 in release_compress_blocks, while
updates to i_blocks and i_compr_blocks are skipped in reserve_compress_blocks.

raw node:
D D D D D D D D
after compress:
C D D D D D D D
after reserve:
C D D D D D D D

Let's update i_blocks and i_compr_blocks properly in reserve_compress_blocks.

Fixes: eb8fbaa53374 ("f2fs: compress: fix to check unreleased compressed cluster")
Signed-off-by: Qi Han <hanqi@vivo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 321d8ffbab6e4..adc7d64a6f47d 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -3792,7 +3792,7 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count,
 		to_reserved = cluster_size - compr_blocks - reserved;
 
 		/* for the case all blocks in cluster were reserved */
-		if (to_reserved == 1) {
+		if (reserved && to_reserved == 1) {
 			dn->ofs_in_node += cluster_size;
 			goto next;
 		}

From d5c367ef8287fb4d235c46a2f8c8d68715f3a0ca Mon Sep 17 00:00:00 2001
From: Qi Han <hanqi@vivo.com>
Date: Wed, 18 Sep 2024 02:44:00 -0600
Subject: [PATCH 0327/1530] f2fs: fix f2fs_bug_on when uninstalling filesystem
 call f2fs_evict_inode.

creating a large files during checkpoint disable until it runs out of
space and then delete it, then remount to enable checkpoint again, and
then unmount the filesystem triggers the f2fs_bug_on as below:

------------[ cut here ]------------
kernel BUG at fs/f2fs/inode.c:896!
CPU: 2 UID: 0 PID: 1286 Comm: umount Not tainted 6.11.0-rc7-dirty #360
Oops: invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
RIP: 0010:f2fs_evict_inode+0x58c/0x610
Call Trace:
 __die_body+0x15/0x60
 die+0x33/0x50
 do_trap+0x10a/0x120
 f2fs_evict_inode+0x58c/0x610
 do_error_trap+0x60/0x80
 f2fs_evict_inode+0x58c/0x610
 exc_invalid_op+0x53/0x60
 f2fs_evict_inode+0x58c/0x610
 asm_exc_invalid_op+0x16/0x20
 f2fs_evict_inode+0x58c/0x610
 evict+0x101/0x260
 dispose_list+0x30/0x50
 evict_inodes+0x140/0x190
 generic_shutdown_super+0x2f/0x150
 kill_block_super+0x11/0x40
 kill_f2fs_super+0x7d/0x140
 deactivate_locked_super+0x2a/0x70
 cleanup_mnt+0xb3/0x140
 task_work_run+0x61/0x90

The root cause is: creating large files during disable checkpoint
period results in not enough free segments, so when writing back root
inode will failed in f2fs_enable_checkpoint. When umount the file
system after enabling checkpoint, the root inode is dirty in
f2fs_evict_inode function, which triggers BUG_ON. The steps to
reproduce are as follows:

dd if=/dev/zero of=f2fs.img bs=1M count=55
mount f2fs.img f2fs_dir -o checkpoint=disable:10%
dd if=/dev/zero of=big bs=1M count=50
sync
rm big
mount -o remount,checkpoint=enable f2fs_dir
umount f2fs_dir

Let's redirty inode when there is not free segments during checkpoint
is disable.

Signed-off-by: Qi Han <hanqi@vivo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/inode.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 1ed86df343a5d..10780e37fc7b6 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -775,8 +775,10 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 		!is_inode_flag_set(inode, FI_DIRTY_INODE))
 		return 0;
 
-	if (!f2fs_is_checkpoint_ready(sbi))
+	if (!f2fs_is_checkpoint_ready(sbi)) {
+		f2fs_mark_inode_dirty_sync(inode, true);
 		return -ENOSPC;
+	}
 
 	/*
 	 * We need to balance fs here to prevent from producing dirty node pages

From b7d0a97b28083084ebdd8e5c6bccd12e6ec18faa Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Sat, 12 Oct 2024 00:44:50 +0800
Subject: [PATCH 0328/1530] f2fs: fix null-ptr-deref in f2fs_submit_page_bio()

There's issue as follows when concurrently installing the f2fs.ko
module and mounting the f2fs file system:
KASAN: null-ptr-deref in range [0x0000000000000020-0x0000000000000027]
RIP: 0010:__bio_alloc+0x2fb/0x6c0 [f2fs]
Call Trace:
 <TASK>
 f2fs_submit_page_bio+0x126/0x8b0 [f2fs]
 __get_meta_page+0x1d4/0x920 [f2fs]
 get_checkpoint_version.constprop.0+0x2b/0x3c0 [f2fs]
 validate_checkpoint+0xac/0x290 [f2fs]
 f2fs_get_valid_checkpoint+0x207/0x950 [f2fs]
 f2fs_fill_super+0x1007/0x39b0 [f2fs]
 mount_bdev+0x183/0x250
 legacy_get_tree+0xf4/0x1e0
 vfs_get_tree+0x88/0x340
 do_new_mount+0x283/0x5e0
 path_mount+0x2b2/0x15b0
 __x64_sys_mount+0x1fe/0x270
 do_syscall_64+0x5f/0x170
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

Above issue happens as the biset of the f2fs file system is not
initialized before register "f2fs_fs_type".
To address above issue just register "f2fs_fs_type" at the last in
init_f2fs_fs(). Ensure that all f2fs file system resources are
initialized.

Fixes: f543805fcd60 ("f2fs: introduce private bioset")
Signed-off-by: Ye Bin <yebin10@huawei.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/super.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 87ab5696bd482..8d4ecb2e855e6 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -4991,9 +4991,6 @@ static int __init init_f2fs_fs(void)
 	err = f2fs_init_shrinker();
 	if (err)
 		goto free_sysfs;
-	err = register_filesystem(&f2fs_fs_type);
-	if (err)
-		goto free_shrinker;
 	f2fs_create_root_stats();
 	err = f2fs_init_post_read_processing();
 	if (err)
@@ -5016,7 +5013,12 @@ static int __init init_f2fs_fs(void)
 	err = f2fs_create_casefold_cache();
 	if (err)
 		goto free_compress_cache;
+	err = register_filesystem(&f2fs_fs_type);
+	if (err)
+		goto free_casefold_cache;
 	return 0;
+free_casefold_cache:
+	f2fs_destroy_casefold_cache();
 free_compress_cache:
 	f2fs_destroy_compress_cache();
 free_compress_mempool:
@@ -5031,8 +5033,6 @@ static int __init init_f2fs_fs(void)
 	f2fs_destroy_post_read_processing();
 free_root_stats:
 	f2fs_destroy_root_stats();
-	unregister_filesystem(&f2fs_fs_type);
-free_shrinker:
 	f2fs_exit_shrinker();
 free_sysfs:
 	f2fs_exit_sysfs();
@@ -5056,6 +5056,7 @@ static int __init init_f2fs_fs(void)
 
 static void __exit exit_f2fs_fs(void)
 {
+	unregister_filesystem(&f2fs_fs_type);
 	f2fs_destroy_casefold_cache();
 	f2fs_destroy_compress_cache();
 	f2fs_destroy_compress_mempool();
@@ -5064,7 +5065,6 @@ static void __exit exit_f2fs_fs(void)
 	f2fs_destroy_iostat_processing();
 	f2fs_destroy_post_read_processing();
 	f2fs_destroy_root_stats();
-	unregister_filesystem(&f2fs_fs_type);
 	f2fs_exit_shrinker();
 	f2fs_exit_sysfs();
 	f2fs_destroy_garbage_collection_cache();

From fe03acd4b165340d3ffe31d98b137c6f840a9bcf Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 11 Oct 2024 15:09:09 +0200
Subject: [PATCH 0329/1530] remoteproc: da8xx: Handle deferred probe

Don't pollute dmesg on deferred probe by using dev_err_probe().

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20241011-remote-proc-dev-err-probe-v1-1-5abb4fc61eca@linaro.org
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/da8xx_remoteproc.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/remoteproc/da8xx_remoteproc.c b/drivers/remoteproc/da8xx_remoteproc.c
index 8770d0cf1255f..f8121682ae9a2 100644
--- a/drivers/remoteproc/da8xx_remoteproc.c
+++ b/drivers/remoteproc/da8xx_remoteproc.c
@@ -265,11 +265,8 @@ static int da8xx_rproc_probe(struct platform_device *pdev)
 		return PTR_ERR(chipsig);
 
 	dsp_clk = devm_clk_get(dev, NULL);
-	if (IS_ERR(dsp_clk)) {
-		dev_err(dev, "clk_get error: %ld\n", PTR_ERR(dsp_clk));
-
-		return PTR_ERR(dsp_clk);
-	}
+	if (IS_ERR(dsp_clk))
+		return dev_err_probe(dev, PTR_ERR(dsp_clk), "clk_get error\n");
 
 	dsp_reset = devm_reset_control_get_exclusive(dev, NULL);
 	if (IS_ERR(dsp_reset)) {

From e1433706f3dea1adec9dcc91279fcbda9079bfb6 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 11 Oct 2024 15:09:10 +0200
Subject: [PATCH 0330/1530] remoteproc: da8xx: Simplify with dev_err_probe()

Use dev_err_probe() to make error and defer code handling simpler.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20241011-remote-proc-dev-err-probe-v1-2-5abb4fc61eca@linaro.org
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/da8xx_remoteproc.c | 22 ++++++----------------
 1 file changed, 6 insertions(+), 16 deletions(-)

diff --git a/drivers/remoteproc/da8xx_remoteproc.c b/drivers/remoteproc/da8xx_remoteproc.c
index f8121682ae9a2..7daaab8124e85 100644
--- a/drivers/remoteproc/da8xx_remoteproc.c
+++ b/drivers/remoteproc/da8xx_remoteproc.c
@@ -251,10 +251,8 @@ static int da8xx_rproc_probe(struct platform_device *pdev)
 		return irq;
 
 	irq_data = irq_get_irq_data(irq);
-	if (!irq_data) {
-		dev_err(dev, "irq_get_irq_data(%d): NULL\n", irq);
-		return -EINVAL;
-	}
+	if (!irq_data)
+		return dev_err_probe(dev, -EINVAL, "irq_get_irq_data(%d): NULL\n", irq);
 
 	bootreg = devm_platform_ioremap_resource_byname(pdev, "host1cfg");
 	if (IS_ERR(bootreg))
@@ -269,21 +267,13 @@ static int da8xx_rproc_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, PTR_ERR(dsp_clk), "clk_get error\n");
 
 	dsp_reset = devm_reset_control_get_exclusive(dev, NULL);
-	if (IS_ERR(dsp_reset)) {
-		if (PTR_ERR(dsp_reset) != -EPROBE_DEFER)
-			dev_err(dev, "unable to get reset control: %ld\n",
-				PTR_ERR(dsp_reset));
-
-		return PTR_ERR(dsp_reset);
-	}
+	if (IS_ERR(dsp_reset))
+		return dev_err_probe(dev, PTR_ERR(dsp_reset), "unable to get reset control\n");
 
 	if (dev->of_node) {
 		ret = of_reserved_mem_device_init(dev);
-		if (ret) {
-			dev_err(dev, "device does not have specific CMA pool: %d\n",
-				ret);
-			return ret;
-		}
+		if (ret)
+			return dev_err_probe(dev, ret, "device does not have specific CMA pool\n");
 	}
 
 	rproc = rproc_alloc(dev, "dsp", &da8xx_rproc_ops, da8xx_fw_name,

From fa9f7efe9ea9f6cb226fce315f241dd0ff670c92 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 11 Oct 2024 15:09:11 +0200
Subject: [PATCH 0331/1530] remoteproc: ti_k3_r5: Simplify with dev_err_probe()

Use dev_err_probe() to make error and defer code handling simpler.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20241011-remote-proc-dev-err-probe-v1-3-5abb4fc61eca@linaro.org
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/ti_k3_r5_remoteproc.c | 69 +++++++++---------------
 1 file changed, 24 insertions(+), 45 deletions(-)

diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c
index d0ebdd5cfa70e..5a2e0464e1b81 100644
--- a/drivers/remoteproc/ti_k3_r5_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c
@@ -1557,11 +1557,7 @@ static int k3_r5_core_of_init(struct platform_device *pdev)
 
 	core->ti_sci = devm_ti_sci_get_by_phandle(dev, "ti,sci");
 	if (IS_ERR(core->ti_sci)) {
-		ret = PTR_ERR(core->ti_sci);
-		if (ret != -EPROBE_DEFER) {
-			dev_err(dev, "failed to get ti-sci handle, ret = %d\n",
-				ret);
-		}
+		ret = dev_err_probe(dev, PTR_ERR(core->ti_sci), "failed to get ti-sci handle\n");
 		core->ti_sci = NULL;
 		goto err;
 	}
@@ -1577,18 +1573,14 @@ static int k3_r5_core_of_init(struct platform_device *pdev)
 		ret = PTR_ERR_OR_ZERO(core->reset);
 		if (!ret)
 			ret = -ENODEV;
-		if (ret != -EPROBE_DEFER) {
-			dev_err(dev, "failed to get reset handle, ret = %d\n",
-				ret);
-		}
+		dev_err_probe(dev, ret, "failed to get reset handle\n");
 		goto err;
 	}
 
 	core->tsp = ti_sci_proc_of_get_tsp(dev, core->ti_sci);
 	if (IS_ERR(core->tsp)) {
-		ret = PTR_ERR(core->tsp);
-		dev_err(dev, "failed to construct ti-sci proc control, ret = %d\n",
-			ret);
+		ret = dev_err_probe(dev, PTR_ERR(core->tsp),
+				    "failed to construct ti-sci proc control\n");
 		goto err;
 	}
 
@@ -1717,11 +1709,8 @@ static int k3_r5_probe(struct platform_device *pdev)
 	init_waitqueue_head(&cluster->core_transition);
 
 	ret = of_property_read_u32(np, "ti,cluster-mode", &cluster->mode);
-	if (ret < 0 && ret != -EINVAL) {
-		dev_err(dev, "invalid format for ti,cluster-mode, ret = %d\n",
-			ret);
-		return ret;
-	}
+	if (ret < 0 && ret != -EINVAL)
+		return dev_err_probe(dev, ret, "invalid format for ti,cluster-mode\n");
 
 	if (ret == -EINVAL) {
 		/*
@@ -1740,49 +1729,39 @@ static int k3_r5_probe(struct platform_device *pdev)
 	}
 
 	if  ((cluster->mode == CLUSTER_MODE_SINGLECPU && !data->single_cpu_mode) ||
-	     (cluster->mode == CLUSTER_MODE_SINGLECORE && !data->is_single_core)) {
-		dev_err(dev, "Cluster mode = %d is not supported on this SoC\n", cluster->mode);
-		return -EINVAL;
-	}
+	     (cluster->mode == CLUSTER_MODE_SINGLECORE && !data->is_single_core))
+		return dev_err_probe(dev, -EINVAL,
+				     "Cluster mode = %d is not supported on this SoC\n",
+				     cluster->mode);
 
 	num_cores = of_get_available_child_count(np);
-	if (num_cores != 2 && !data->is_single_core) {
-		dev_err(dev, "MCU cluster requires both R5F cores to be enabled but num_cores is set to = %d\n",
-			num_cores);
-		return -ENODEV;
-	}
+	if (num_cores != 2 && !data->is_single_core)
+		return dev_err_probe(dev, -ENODEV,
+				     "MCU cluster requires both R5F cores to be enabled but num_cores is set to = %d\n",
+				     num_cores);
 
-	if (num_cores != 1 && data->is_single_core) {
-		dev_err(dev, "SoC supports only single core R5 but num_cores is set to %d\n",
-			num_cores);
-		return -ENODEV;
-	}
+	if (num_cores != 1 && data->is_single_core)
+		return dev_err_probe(dev, -ENODEV,
+				     "SoC supports only single core R5 but num_cores is set to %d\n",
+				     num_cores);
 
 	platform_set_drvdata(pdev, cluster);
 
 	ret = devm_of_platform_populate(dev);
-	if (ret) {
-		dev_err(dev, "devm_of_platform_populate failed, ret = %d\n",
-			ret);
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(dev, ret, "devm_of_platform_populate failed\n");
 
 	ret = k3_r5_cluster_of_init(pdev);
-	if (ret) {
-		dev_err(dev, "k3_r5_cluster_of_init failed, ret = %d\n", ret);
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(dev, ret, "k3_r5_cluster_of_init failed\n");
 
 	ret = devm_add_action_or_reset(dev, k3_r5_cluster_of_exit, pdev);
 	if (ret)
 		return ret;
 
 	ret = k3_r5_cluster_rproc_init(pdev);
-	if (ret) {
-		dev_err(dev, "k3_r5_cluster_rproc_init failed, ret = %d\n",
-			ret);
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(dev, ret, "k3_r5_cluster_rproc_init failed\n");
 
 	ret = devm_add_action_or_reset(dev, k3_r5_cluster_rproc_exit, pdev);
 	if (ret)

From f5964cecd91fad55e732ded94bb7b9168ee0c294 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 11 Oct 2024 15:09:12 +0200
Subject: [PATCH 0332/1530] remoteproc: ti_k3_r5: Simplify with scoped for each
 OF child loop

Use scoped for_each_available_child_of_node_scoped() when iterating over
device nodes to make code a bit simpler.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20241011-remote-proc-dev-err-probe-v1-4-5abb4fc61eca@linaro.org
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/ti_k3_r5_remoteproc.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c
index 5a2e0464e1b81..2f996a962f557 100644
--- a/drivers/remoteproc/ti_k3_r5_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c
@@ -1650,16 +1650,14 @@ static int k3_r5_cluster_of_init(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev_of_node(dev);
 	struct platform_device *cpdev;
-	struct device_node *child;
 	struct k3_r5_core *core;
 	int ret;
 
-	for_each_available_child_of_node(np, child) {
+	for_each_available_child_of_node_scoped(np, child) {
 		cpdev = of_find_device_by_node(child);
 		if (!cpdev) {
 			ret = -ENODEV;
 			dev_err(dev, "could not get R5 core platform device\n");
-			of_node_put(child);
 			goto fail;
 		}
 
@@ -1668,7 +1666,6 @@ static int k3_r5_cluster_of_init(struct platform_device *pdev)
 			dev_err(dev, "k3_r5_core_of_init failed, ret = %d\n",
 				ret);
 			put_device(&cpdev->dev);
-			of_node_put(child);
 			goto fail;
 		}
 

From 2c19d0159944f3aef1c0ebbd9d7fc6c2523e4307 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@baylibre.com>
Date: Tue, 8 Oct 2024 11:00:10 +0200
Subject: [PATCH 0333/1530] Input: switch back to struct
 platform_driver::remove()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 0edb555a65d1 ("platform: Make platform_driver::remove()
return void") .remove() is (again) the right callback to implement for
platform drivers.

Convert all platform drivers below drivers/input/ to use .remove(), with
the eventual goal to drop struct platform_driver::remove_new(). As
.remove() and .remove_new() have the same prototypes, conversion is done
by just changing the structure member name in the driver initializer.

While touching these files, make indention of the struct initializer
consistent in a few drivers.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Link: https://lore.kernel.org/r/20241008090009.462836-2-u.kleine-koenig@baylibre.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/adp5520-keys.c        | 2 +-
 drivers/input/keyboard/cros_ec_keyb.c        | 2 +-
 drivers/input/keyboard/ep93xx_keypad.c       | 2 +-
 drivers/input/keyboard/iqs62x-keys.c         | 2 +-
 drivers/input/keyboard/omap-keypad.c         | 2 +-
 drivers/input/keyboard/omap4-keypad.c        | 2 +-
 drivers/input/keyboard/samsung-keypad.c      | 2 +-
 drivers/input/keyboard/sh_keysc.c            | 2 +-
 drivers/input/keyboard/stmpe-keypad.c        | 2 +-
 drivers/input/misc/88pm80x_onkey.c           | 2 +-
 drivers/input/misc/da9052_onkey.c            | 4 ++--
 drivers/input/misc/da9055_onkey.c            | 4 ++--
 drivers/input/misc/ideapad_slidebar.c        | 2 +-
 drivers/input/misc/m68kspkr.c                | 2 +-
 drivers/input/misc/max8997_haptic.c          | 2 +-
 drivers/input/misc/mc13783-pwrbutton.c       | 2 +-
 drivers/input/misc/palmas-pwrbutton.c        | 2 +-
 drivers/input/misc/pcap_keys.c               | 2 +-
 drivers/input/misc/pcf50633-input.c          | 2 +-
 drivers/input/misc/pcspkr.c                  | 2 +-
 drivers/input/misc/pm8941-pwrkey.c           | 2 +-
 drivers/input/misc/soc_button_array.c        | 2 +-
 drivers/input/misc/sparcspkr.c               | 4 ++--
 drivers/input/misc/tps65219-pwrbutton.c      | 2 +-
 drivers/input/misc/wistron_btns.c            | 2 +-
 drivers/input/misc/wm831x-on.c               | 2 +-
 drivers/input/mouse/amimouse.c               | 2 +-
 drivers/input/serio/altera_ps2.c             | 2 +-
 drivers/input/serio/ams_delta_serio.c        | 2 +-
 drivers/input/serio/apbps2.c                 | 2 +-
 drivers/input/serio/arc_ps2.c                | 2 +-
 drivers/input/serio/ct82c710.c               | 2 +-
 drivers/input/serio/i8042-sparcio.h          | 2 +-
 drivers/input/serio/i8042.c                  | 2 +-
 drivers/input/serio/ioc3kbd.c                | 2 +-
 drivers/input/serio/maceps2.c                | 2 +-
 drivers/input/serio/olpc_apsp.c              | 2 +-
 drivers/input/serio/ps2-gpio.c               | 2 +-
 drivers/input/serio/q40kbd.c                 | 2 +-
 drivers/input/serio/rpckbd.c                 | 2 +-
 drivers/input/serio/sun4i-ps2.c              | 2 +-
 drivers/input/serio/xilinx_ps2.c             | 2 +-
 drivers/input/touchscreen/da9052_tsi.c       | 2 +-
 drivers/input/touchscreen/mainstone-wm97xx.c | 2 +-
 drivers/input/touchscreen/mc13783_ts.c       | 2 +-
 drivers/input/touchscreen/pcap_ts.c          | 2 +-
 drivers/input/touchscreen/stmpe-ts.c         | 2 +-
 drivers/input/touchscreen/sun4i-ts.c         | 4 ++--
 drivers/input/touchscreen/ti_am335x_tsc.c    | 4 ++--
 drivers/input/touchscreen/wm831x-ts.c        | 2 +-
 drivers/input/touchscreen/wm97xx-core.c      | 2 +-
 51 files changed, 56 insertions(+), 56 deletions(-)

diff --git a/drivers/input/keyboard/adp5520-keys.c b/drivers/input/keyboard/adp5520-keys.c
index 10c248f0c1fcd..980d739e45b87 100644
--- a/drivers/input/keyboard/adp5520-keys.c
+++ b/drivers/input/keyboard/adp5520-keys.c
@@ -181,7 +181,7 @@ static struct platform_driver adp5520_keys_driver = {
 		.name	= "adp5520-keys",
 	},
 	.probe		= adp5520_keys_probe,
-	.remove_new	= adp5520_keys_remove,
+	.remove		= adp5520_keys_remove,
 };
 module_platform_driver(adp5520_keys_driver);
 
diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c
index 12eb9df180ee4..4219af6412128 100644
--- a/drivers/input/keyboard/cros_ec_keyb.c
+++ b/drivers/input/keyboard/cros_ec_keyb.c
@@ -770,7 +770,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(cros_ec_keyb_pm_ops, NULL, cros_ec_keyb_resume);
 
 static struct platform_driver cros_ec_keyb_driver = {
 	.probe = cros_ec_keyb_probe,
-	.remove_new = cros_ec_keyb_remove,
+	.remove = cros_ec_keyb_remove,
 	.driver = {
 		.name = "cros-ec-keyb",
 		.dev_groups = cros_ec_keyb_groups,
diff --git a/drivers/input/keyboard/ep93xx_keypad.c b/drivers/input/keyboard/ep93xx_keypad.c
index a8df957ef261b..144c73540d45c 100644
--- a/drivers/input/keyboard/ep93xx_keypad.c
+++ b/drivers/input/keyboard/ep93xx_keypad.c
@@ -315,7 +315,7 @@ static struct platform_driver ep93xx_keypad_driver = {
 		.pm	= pm_sleep_ptr(&ep93xx_keypad_pm_ops),
 	},
 	.probe		= ep93xx_keypad_probe,
-	.remove_new	= ep93xx_keypad_remove,
+	.remove		= ep93xx_keypad_remove,
 };
 module_platform_driver(ep93xx_keypad_driver);
 
diff --git a/drivers/input/keyboard/iqs62x-keys.c b/drivers/input/keyboard/iqs62x-keys.c
index 1315b0f0862fc..b086c7b28d5c1 100644
--- a/drivers/input/keyboard/iqs62x-keys.c
+++ b/drivers/input/keyboard/iqs62x-keys.c
@@ -323,7 +323,7 @@ static struct platform_driver iqs62x_keys_platform_driver = {
 		.name = "iqs62x-keys",
 	},
 	.probe = iqs62x_keys_probe,
-	.remove_new = iqs62x_keys_remove,
+	.remove = iqs62x_keys_remove,
 };
 module_platform_driver(iqs62x_keys_platform_driver);
 
diff --git a/drivers/input/keyboard/omap-keypad.c b/drivers/input/keyboard/omap-keypad.c
index 57587541110b6..33df8885b599e 100644
--- a/drivers/input/keyboard/omap-keypad.c
+++ b/drivers/input/keyboard/omap-keypad.c
@@ -290,7 +290,7 @@ static void omap_kp_remove(struct platform_device *pdev)
 
 static struct platform_driver omap_kp_driver = {
 	.probe		= omap_kp_probe,
-	.remove_new	= omap_kp_remove,
+	.remove		= omap_kp_remove,
 	.driver		= {
 		.name	= "omap-keypad",
 		.dev_groups = omap_kp_groups,
diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c
index 935c2b27b81c2..bffe89c0717ad 100644
--- a/drivers/input/keyboard/omap4-keypad.c
+++ b/drivers/input/keyboard/omap4-keypad.c
@@ -485,7 +485,7 @@ MODULE_DEVICE_TABLE(of, omap_keypad_dt_match);
 
 static struct platform_driver omap4_keypad_driver = {
 	.probe		= omap4_keypad_probe,
-	.remove_new	= omap4_keypad_remove,
+	.remove		= omap4_keypad_remove,
 	.driver		= {
 		.name	= "omap4-keypad",
 		.of_match_table = omap_keypad_dt_match,
diff --git a/drivers/input/keyboard/samsung-keypad.c b/drivers/input/keyboard/samsung-keypad.c
index e212eff7687c0..9f1049aa3048c 100644
--- a/drivers/input/keyboard/samsung-keypad.c
+++ b/drivers/input/keyboard/samsung-keypad.c
@@ -587,7 +587,7 @@ MODULE_DEVICE_TABLE(platform, samsung_keypad_driver_ids);
 
 static struct platform_driver samsung_keypad_driver = {
 	.probe		= samsung_keypad_probe,
-	.remove_new	= samsung_keypad_remove,
+	.remove		= samsung_keypad_remove,
 	.driver		= {
 		.name	= "samsung-keypad",
 		.of_match_table = of_match_ptr(samsung_keypad_dt_match),
diff --git a/drivers/input/keyboard/sh_keysc.c b/drivers/input/keyboard/sh_keysc.c
index 4ea4fd25c5d20..159f41eedd410 100644
--- a/drivers/input/keyboard/sh_keysc.c
+++ b/drivers/input/keyboard/sh_keysc.c
@@ -319,7 +319,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(sh_keysc_dev_pm_ops,
 
 static struct platform_driver sh_keysc_device_driver = {
 	.probe		= sh_keysc_probe,
-	.remove_new	= sh_keysc_remove,
+	.remove		= sh_keysc_remove,
 	.driver		= {
 		.name	= "sh_keysc",
 		.pm	= pm_sleep_ptr(&sh_keysc_dev_pm_ops),
diff --git a/drivers/input/keyboard/stmpe-keypad.c b/drivers/input/keyboard/stmpe-keypad.c
index ef2f440278943..0acded4fb9c9c 100644
--- a/drivers/input/keyboard/stmpe-keypad.c
+++ b/drivers/input/keyboard/stmpe-keypad.c
@@ -414,7 +414,7 @@ static void stmpe_keypad_remove(struct platform_device *pdev)
 static struct platform_driver stmpe_keypad_driver = {
 	.driver.name	= "stmpe-keypad",
 	.probe		= stmpe_keypad_probe,
-	.remove_new	= stmpe_keypad_remove,
+	.remove		= stmpe_keypad_remove,
 };
 module_platform_driver(stmpe_keypad_driver);
 
diff --git a/drivers/input/misc/88pm80x_onkey.c b/drivers/input/misc/88pm80x_onkey.c
index 6477a41c4bac3..9159b5fec129c 100644
--- a/drivers/input/misc/88pm80x_onkey.c
+++ b/drivers/input/misc/88pm80x_onkey.c
@@ -141,7 +141,7 @@ static struct platform_driver pm80x_onkey_driver = {
 		   .pm = &pm80x_onkey_pm_ops,
 		   },
 	.probe = pm80x_onkey_probe,
-	.remove_new = pm80x_onkey_remove,
+	.remove = pm80x_onkey_remove,
 };
 
 module_platform_driver(pm80x_onkey_driver);
diff --git a/drivers/input/misc/da9052_onkey.c b/drivers/input/misc/da9052_onkey.c
index 7a1122e1efb9c..cc23625019e34 100644
--- a/drivers/input/misc/da9052_onkey.c
+++ b/drivers/input/misc/da9052_onkey.c
@@ -140,8 +140,8 @@ static void da9052_onkey_remove(struct platform_device *pdev)
 
 static struct platform_driver da9052_onkey_driver = {
 	.probe	= da9052_onkey_probe,
-	.remove_new = da9052_onkey_remove,
-	.driver = {
+	.remove	= da9052_onkey_remove,
+	.driver	= {
 		.name	= "da9052-onkey",
 	},
 };
diff --git a/drivers/input/misc/da9055_onkey.c b/drivers/input/misc/da9055_onkey.c
index 871812f1b398e..3e4fc2f010119 100644
--- a/drivers/input/misc/da9055_onkey.c
+++ b/drivers/input/misc/da9055_onkey.c
@@ -145,8 +145,8 @@ static void da9055_onkey_remove(struct platform_device *pdev)
 
 static struct platform_driver da9055_onkey_driver = {
 	.probe	= da9055_onkey_probe,
-	.remove_new = da9055_onkey_remove,
-	.driver = {
+	.remove	= da9055_onkey_remove,
+	.driver	= {
 		.name	= "da9055-onkey",
 	},
 };
diff --git a/drivers/input/misc/ideapad_slidebar.c b/drivers/input/misc/ideapad_slidebar.c
index fea4a89607184..f6e5fc807b4df 100644
--- a/drivers/input/misc/ideapad_slidebar.c
+++ b/drivers/input/misc/ideapad_slidebar.c
@@ -255,7 +255,7 @@ static struct platform_driver slidebar_drv = {
 	.driver = {
 		.name = "ideapad_slidebar",
 	},
-	.remove_new = ideapad_remove,
+	.remove = ideapad_remove,
 };
 
 static int __init ideapad_dmi_check(const struct dmi_system_id *id)
diff --git a/drivers/input/misc/m68kspkr.c b/drivers/input/misc/m68kspkr.c
index 3fe0a85c45e00..0542334df6246 100644
--- a/drivers/input/misc/m68kspkr.c
+++ b/drivers/input/misc/m68kspkr.c
@@ -95,7 +95,7 @@ static struct platform_driver m68kspkr_platform_driver = {
 		.name	= "m68kspkr",
 	},
 	.probe		= m68kspkr_probe,
-	.remove_new	= m68kspkr_remove,
+	.remove		= m68kspkr_remove,
 	.shutdown	= m68kspkr_shutdown,
 };
 
diff --git a/drivers/input/misc/max8997_haptic.c b/drivers/input/misc/max8997_haptic.c
index 2853455daef2a..f97f341ee0bb2 100644
--- a/drivers/input/misc/max8997_haptic.c
+++ b/drivers/input/misc/max8997_haptic.c
@@ -384,7 +384,7 @@ static struct platform_driver max8997_haptic_driver = {
 		.pm	= pm_sleep_ptr(&max8997_haptic_pm_ops),
 	},
 	.probe		= max8997_haptic_probe,
-	.remove_new	= max8997_haptic_remove,
+	.remove		= max8997_haptic_remove,
 	.id_table	= max8997_haptic_id,
 };
 module_platform_driver(max8997_haptic_driver);
diff --git a/drivers/input/misc/mc13783-pwrbutton.c b/drivers/input/misc/mc13783-pwrbutton.c
index 1c8c939638f6c..1c7faa9b7afe0 100644
--- a/drivers/input/misc/mc13783-pwrbutton.c
+++ b/drivers/input/misc/mc13783-pwrbutton.c
@@ -253,7 +253,7 @@ static void mc13783_pwrbutton_remove(struct platform_device *pdev)
 
 static struct platform_driver mc13783_pwrbutton_driver = {
 	.probe		= mc13783_pwrbutton_probe,
-	.remove_new	= mc13783_pwrbutton_remove,
+	.remove		= mc13783_pwrbutton_remove,
 	.driver		= {
 		.name	= "mc13783-pwrbutton",
 	},
diff --git a/drivers/input/misc/palmas-pwrbutton.c b/drivers/input/misc/palmas-pwrbutton.c
index 06d5972e8e84d..39fc451c56e92 100644
--- a/drivers/input/misc/palmas-pwrbutton.c
+++ b/drivers/input/misc/palmas-pwrbutton.c
@@ -310,7 +310,7 @@ MODULE_DEVICE_TABLE(of, of_palmas_pwr_match);
 
 static struct platform_driver palmas_pwron_driver = {
 	.probe	= palmas_pwron_probe,
-	.remove_new = palmas_pwron_remove,
+	.remove	= palmas_pwron_remove,
 	.driver	= {
 		.name	= "palmas_pwrbutton",
 		.of_match_table = of_match_ptr(of_palmas_pwr_match),
diff --git a/drivers/input/misc/pcap_keys.c b/drivers/input/misc/pcap_keys.c
index f8954a2cab24d..fe43fd72ba7b0 100644
--- a/drivers/input/misc/pcap_keys.c
+++ b/drivers/input/misc/pcap_keys.c
@@ -112,7 +112,7 @@ static void pcap_keys_remove(struct platform_device *pdev)
 
 static struct platform_driver pcap_keys_device_driver = {
 	.probe		= pcap_keys_probe,
-	.remove_new	= pcap_keys_remove,
+	.remove		= pcap_keys_remove,
 	.driver		= {
 		.name	= "pcap-keys",
 	}
diff --git a/drivers/input/misc/pcf50633-input.c b/drivers/input/misc/pcf50633-input.c
index c5c5fe236c182..6d046e236ba69 100644
--- a/drivers/input/misc/pcf50633-input.c
+++ b/drivers/input/misc/pcf50633-input.c
@@ -103,7 +103,7 @@ static struct platform_driver pcf50633_input_driver = {
 		.name = "pcf50633-input",
 	},
 	.probe = pcf50633_input_probe,
-	.remove_new = pcf50633_input_remove,
+	.remove = pcf50633_input_remove,
 };
 module_platform_driver(pcf50633_input_driver);
 
diff --git a/drivers/input/misc/pcspkr.c b/drivers/input/misc/pcspkr.c
index 897854fd245f1..0467808402f24 100644
--- a/drivers/input/misc/pcspkr.c
+++ b/drivers/input/misc/pcspkr.c
@@ -127,7 +127,7 @@ static struct platform_driver pcspkr_platform_driver = {
 		.pm	= &pcspkr_pm_ops,
 	},
 	.probe		= pcspkr_probe,
-	.remove_new	= pcspkr_remove,
+	.remove		= pcspkr_remove,
 	.shutdown	= pcspkr_shutdown,
 };
 module_platform_driver(pcspkr_platform_driver);
diff --git a/drivers/input/misc/pm8941-pwrkey.c b/drivers/input/misc/pm8941-pwrkey.c
index bab710023d8f1..d0c46665e5270 100644
--- a/drivers/input/misc/pm8941-pwrkey.c
+++ b/drivers/input/misc/pm8941-pwrkey.c
@@ -465,7 +465,7 @@ MODULE_DEVICE_TABLE(of, pm8941_pwr_key_id_table);
 
 static struct platform_driver pm8941_pwrkey_driver = {
 	.probe = pm8941_pwrkey_probe,
-	.remove_new = pm8941_pwrkey_remove,
+	.remove = pm8941_pwrkey_remove,
 	.driver = {
 		.name = "pm8941-pwrkey",
 		.pm = pm_sleep_ptr(&pm8941_pwr_key_pm_ops),
diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c
index e8f373715e506..b8cad415c62ca 100644
--- a/drivers/input/misc/soc_button_array.c
+++ b/drivers/input/misc/soc_button_array.c
@@ -612,7 +612,7 @@ MODULE_DEVICE_TABLE(acpi, soc_button_acpi_match);
 
 static struct platform_driver soc_button_driver = {
 	.probe          = soc_button_probe,
-	.remove_new	= soc_button_remove,
+	.remove		= soc_button_remove,
 	.driver		= {
 		.name = KBUILD_MODNAME,
 		.acpi_match_table = ACPI_PTR(soc_button_acpi_match),
diff --git a/drivers/input/misc/sparcspkr.c b/drivers/input/misc/sparcspkr.c
index 5de59ae90c670..ff7b6291894a6 100644
--- a/drivers/input/misc/sparcspkr.c
+++ b/drivers/input/misc/sparcspkr.c
@@ -256,7 +256,7 @@ static struct platform_driver bbc_beep_driver = {
 		.of_match_table = bbc_beep_match,
 	},
 	.probe		= bbc_beep_probe,
-	.remove_new	= bbc_remove,
+	.remove		= bbc_remove,
 	.shutdown	= sparcspkr_shutdown,
 };
 
@@ -334,7 +334,7 @@ static struct platform_driver grover_beep_driver = {
 		.of_match_table = grover_beep_match,
 	},
 	.probe		= grover_beep_probe,
-	.remove_new	= grover_remove,
+	.remove		= grover_remove,
 	.shutdown	= sparcspkr_shutdown,
 };
 
diff --git a/drivers/input/misc/tps65219-pwrbutton.c b/drivers/input/misc/tps65219-pwrbutton.c
index eeb9f2334ab46..7a58bae4f1a03 100644
--- a/drivers/input/misc/tps65219-pwrbutton.c
+++ b/drivers/input/misc/tps65219-pwrbutton.c
@@ -137,7 +137,7 @@ MODULE_DEVICE_TABLE(platform, tps65219_pwrbtn_id_table);
 
 static struct platform_driver tps65219_pb_driver = {
 	.probe = tps65219_pb_probe,
-	.remove_new = tps65219_pb_remove,
+	.remove = tps65219_pb_remove,
 	.driver = {
 		.name = "tps65219_pwrbutton",
 	},
diff --git a/drivers/input/misc/wistron_btns.c b/drivers/input/misc/wistron_btns.c
index 5c28ef4563dab..69626e3bd0b3b 100644
--- a/drivers/input/misc/wistron_btns.c
+++ b/drivers/input/misc/wistron_btns.c
@@ -1334,7 +1334,7 @@ static struct platform_driver wistron_driver = {
 		.pm	= pm_sleep_ptr(&wistron_pm_ops),
 	},
 	.probe		= wistron_probe,
-	.remove_new	= wistron_remove,
+	.remove		= wistron_remove,
 };
 
 static int __init wb_module_init(void)
diff --git a/drivers/input/misc/wm831x-on.c b/drivers/input/misc/wm831x-on.c
index e4a06c73b72d9..18eb319bc6f75 100644
--- a/drivers/input/misc/wm831x-on.c
+++ b/drivers/input/misc/wm831x-on.c
@@ -134,7 +134,7 @@ static void wm831x_on_remove(struct platform_device *pdev)
 
 static struct platform_driver wm831x_on_driver = {
 	.probe		= wm831x_on_probe,
-	.remove_new	= wm831x_on_remove,
+	.remove		= wm831x_on_remove,
 	.driver		= {
 		.name	= "wm831x-on",
 	},
diff --git a/drivers/input/mouse/amimouse.c b/drivers/input/mouse/amimouse.c
index 2fbbaeb76d708..d203c2a6c438b 100644
--- a/drivers/input/mouse/amimouse.c
+++ b/drivers/input/mouse/amimouse.c
@@ -139,7 +139,7 @@ static void __exit amimouse_remove(struct platform_device *pdev)
  * triggering a section mismatch warning.
  */
 static struct platform_driver amimouse_driver __refdata = {
-	.remove_new = __exit_p(amimouse_remove),
+	.remove = __exit_p(amimouse_remove),
 	.driver   = {
 		.name	= "amiga-mouse",
 	},
diff --git a/drivers/input/serio/altera_ps2.c b/drivers/input/serio/altera_ps2.c
index 611eb9fe2d047..aa445b1941e93 100644
--- a/drivers/input/serio/altera_ps2.c
+++ b/drivers/input/serio/altera_ps2.c
@@ -146,7 +146,7 @@ MODULE_DEVICE_TABLE(of, altera_ps2_match);
  */
 static struct platform_driver altera_ps2_driver = {
 	.probe		= altera_ps2_probe,
-	.remove_new	= altera_ps2_remove,
+	.remove		= altera_ps2_remove,
 	.driver	= {
 		.name	= DRV_NAME,
 		.of_match_table = of_match_ptr(altera_ps2_match),
diff --git a/drivers/input/serio/ams_delta_serio.c b/drivers/input/serio/ams_delta_serio.c
index 0bd6ae1068099..81b3a053df810 100644
--- a/drivers/input/serio/ams_delta_serio.c
+++ b/drivers/input/serio/ams_delta_serio.c
@@ -182,7 +182,7 @@ static void ams_delta_serio_exit(struct platform_device *pdev)
 
 static struct platform_driver ams_delta_serio_driver = {
 	.probe	= ams_delta_serio_init,
-	.remove_new = ams_delta_serio_exit,
+	.remove	= ams_delta_serio_exit,
 	.driver	= {
 		.name	= DRIVER_NAME
 	},
diff --git a/drivers/input/serio/apbps2.c b/drivers/input/serio/apbps2.c
index 4015e75fcb903..b815337be2f43 100644
--- a/drivers/input/serio/apbps2.c
+++ b/drivers/input/serio/apbps2.c
@@ -208,7 +208,7 @@ static struct platform_driver apbps2_of_driver = {
 		.of_match_table = apbps2_of_match,
 	},
 	.probe = apbps2_of_probe,
-	.remove_new = apbps2_of_remove,
+	.remove = apbps2_of_remove,
 };
 
 module_platform_driver(apbps2_of_driver);
diff --git a/drivers/input/serio/arc_ps2.c b/drivers/input/serio/arc_ps2.c
index a9180a0058720..e991c72296c93 100644
--- a/drivers/input/serio/arc_ps2.c
+++ b/drivers/input/serio/arc_ps2.c
@@ -260,7 +260,7 @@ static struct platform_driver arc_ps2_driver = {
 		.of_match_table	= of_match_ptr(arc_ps2_match),
 	},
 	.probe	= arc_ps2_probe,
-	.remove_new = arc_ps2_remove,
+	.remove	= arc_ps2_remove,
 };
 
 module_platform_driver(arc_ps2_driver);
diff --git a/drivers/input/serio/ct82c710.c b/drivers/input/serio/ct82c710.c
index 6834440b37f66..053a15988c454 100644
--- a/drivers/input/serio/ct82c710.c
+++ b/drivers/input/serio/ct82c710.c
@@ -190,7 +190,7 @@ static struct platform_driver ct82c710_driver = {
 		.name	= "ct82c710",
 	},
 	.probe		= ct82c710_probe,
-	.remove_new	= ct82c710_remove,
+	.remove		= ct82c710_remove,
 };
 
 
diff --git a/drivers/input/serio/i8042-sparcio.h b/drivers/input/serio/i8042-sparcio.h
index c2fda54dc384f..b4a5fcaac09f6 100644
--- a/drivers/input/serio/i8042-sparcio.h
+++ b/drivers/input/serio/i8042-sparcio.h
@@ -101,7 +101,7 @@ static struct platform_driver sparc_i8042_driver = {
 		.of_match_table = sparc_i8042_match,
 	},
 	.probe		= sparc_i8042_probe,
-	.remove_new	= sparc_i8042_remove,
+	.remove		= sparc_i8042_remove,
 };
 
 static bool i8042_is_mr_coffee(void)
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index 86916fe3925fa..509330a278802 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -1590,7 +1590,7 @@ static struct platform_driver i8042_driver = {
 #endif
 	},
 	.probe		= i8042_probe,
-	.remove_new	= i8042_remove,
+	.remove		= i8042_remove,
 	.shutdown	= i8042_shutdown,
 };
 
diff --git a/drivers/input/serio/ioc3kbd.c b/drivers/input/serio/ioc3kbd.c
index 676b0bda3d720..d2c7ffb9a946b 100644
--- a/drivers/input/serio/ioc3kbd.c
+++ b/drivers/input/serio/ioc3kbd.c
@@ -208,7 +208,7 @@ MODULE_DEVICE_TABLE(platform, ioc3kbd_id_table);
 
 static struct platform_driver ioc3kbd_driver = {
 	.probe          = ioc3kbd_probe,
-	.remove_new     = ioc3kbd_remove,
+	.remove         = ioc3kbd_remove,
 	.id_table	= ioc3kbd_id_table,
 	.driver = {
 		.name = "ioc3-kbd",
diff --git a/drivers/input/serio/maceps2.c b/drivers/input/serio/maceps2.c
index 42ac1eb948662..3d28a5cddd611 100644
--- a/drivers/input/serio/maceps2.c
+++ b/drivers/input/serio/maceps2.c
@@ -159,7 +159,7 @@ static struct platform_driver maceps2_driver = {
 		.name	= "maceps2",
 	},
 	.probe		= maceps2_probe,
-	.remove_new	= maceps2_remove,
+	.remove		= maceps2_remove,
 };
 
 static int __init maceps2_init(void)
diff --git a/drivers/input/serio/olpc_apsp.c b/drivers/input/serio/olpc_apsp.c
index 0ad95e880cc20..a243248300216 100644
--- a/drivers/input/serio/olpc_apsp.c
+++ b/drivers/input/serio/olpc_apsp.c
@@ -256,7 +256,7 @@ MODULE_DEVICE_TABLE(of, olpc_apsp_dt_ids);
 
 static struct platform_driver olpc_apsp_driver = {
 	.probe		= olpc_apsp_probe,
-	.remove_new	= olpc_apsp_remove,
+	.remove		= olpc_apsp_remove,
 	.driver		= {
 		.name	= "olpc-apsp",
 		.of_match_table = olpc_apsp_dt_ids,
diff --git a/drivers/input/serio/ps2-gpio.c b/drivers/input/serio/ps2-gpio.c
index 3e4ae2cc6552d..93769910ce24e 100644
--- a/drivers/input/serio/ps2-gpio.c
+++ b/drivers/input/serio/ps2-gpio.c
@@ -491,7 +491,7 @@ MODULE_DEVICE_TABLE(of, ps2_gpio_match);
 
 static struct platform_driver ps2_gpio_driver = {
 	.probe		= ps2_gpio_probe,
-	.remove_new	= ps2_gpio_remove,
+	.remove		= ps2_gpio_remove,
 	.driver = {
 		.name = DRIVER_NAME,
 		.of_match_table = of_match_ptr(ps2_gpio_match),
diff --git a/drivers/input/serio/q40kbd.c b/drivers/input/serio/q40kbd.c
index cdd5c4ef9b365..ae55c4de092f9 100644
--- a/drivers/input/serio/q40kbd.c
+++ b/drivers/input/serio/q40kbd.c
@@ -160,7 +160,7 @@ static struct platform_driver q40kbd_driver = {
 	.driver		= {
 		.name	= "q40kbd",
 	},
-	.remove_new	= q40kbd_remove,
+	.remove		= q40kbd_remove,
 };
 
 module_platform_driver_probe(q40kbd_driver, q40kbd_probe);
diff --git a/drivers/input/serio/rpckbd.c b/drivers/input/serio/rpckbd.c
index e236bb7e10144..c65c552b0c45b 100644
--- a/drivers/input/serio/rpckbd.c
+++ b/drivers/input/serio/rpckbd.c
@@ -144,7 +144,7 @@ static void rpckbd_remove(struct platform_device *dev)
 
 static struct platform_driver rpckbd_driver = {
 	.probe		= rpckbd_probe,
-	.remove_new	= rpckbd_remove,
+	.remove		= rpckbd_remove,
 	.driver		= {
 		.name	= "kart",
 	},
diff --git a/drivers/input/serio/sun4i-ps2.c b/drivers/input/serio/sun4i-ps2.c
index 267214ca9b51e..524929ce1cae1 100644
--- a/drivers/input/serio/sun4i-ps2.c
+++ b/drivers/input/serio/sun4i-ps2.c
@@ -318,7 +318,7 @@ MODULE_DEVICE_TABLE(of, sun4i_ps2_match);
 
 static struct platform_driver sun4i_ps2_driver = {
 	.probe		= sun4i_ps2_probe,
-	.remove_new	= sun4i_ps2_remove,
+	.remove		= sun4i_ps2_remove,
 	.driver = {
 		.name = DRIVER_NAME,
 		.of_match_table = sun4i_ps2_match,
diff --git a/drivers/input/serio/xilinx_ps2.c b/drivers/input/serio/xilinx_ps2.c
index 0316760168e57..01433f0b48f16 100644
--- a/drivers/input/serio/xilinx_ps2.c
+++ b/drivers/input/serio/xilinx_ps2.c
@@ -353,7 +353,7 @@ static struct platform_driver xps2_of_driver = {
 		.of_match_table = xps2_of_match,
 	},
 	.probe		= xps2_of_probe,
-	.remove_new	= xps2_of_remove,
+	.remove		= xps2_of_remove,
 };
 module_platform_driver(xps2_of_driver);
 
diff --git a/drivers/input/touchscreen/da9052_tsi.c b/drivers/input/touchscreen/da9052_tsi.c
index 52e0e834e76fb..c2d3252f84668 100644
--- a/drivers/input/touchscreen/da9052_tsi.c
+++ b/drivers/input/touchscreen/da9052_tsi.c
@@ -326,7 +326,7 @@ static void da9052_ts_remove(struct platform_device *pdev)
 
 static struct platform_driver da9052_tsi_driver = {
 	.probe	= da9052_ts_probe,
-	.remove_new = da9052_ts_remove,
+	.remove	= da9052_ts_remove,
 	.driver	= {
 		.name	= "da9052-tsi",
 	},
diff --git a/drivers/input/touchscreen/mainstone-wm97xx.c b/drivers/input/touchscreen/mainstone-wm97xx.c
index bfbebe245040c..5abf164ae14c1 100644
--- a/drivers/input/touchscreen/mainstone-wm97xx.c
+++ b/drivers/input/touchscreen/mainstone-wm97xx.c
@@ -261,7 +261,7 @@ static void mainstone_wm97xx_remove(struct platform_device *pdev)
 
 static struct platform_driver mainstone_wm97xx_driver = {
 	.probe	= mainstone_wm97xx_probe,
-	.remove_new = mainstone_wm97xx_remove,
+	.remove	= mainstone_wm97xx_remove,
 	.driver	= {
 		.name	= "wm97xx-touch",
 	},
diff --git a/drivers/input/touchscreen/mc13783_ts.c b/drivers/input/touchscreen/mc13783_ts.c
index cbcd6e34efb7d..33635da850799 100644
--- a/drivers/input/touchscreen/mc13783_ts.c
+++ b/drivers/input/touchscreen/mc13783_ts.c
@@ -226,7 +226,7 @@ static void mc13783_ts_remove(struct platform_device *pdev)
 }
 
 static struct platform_driver mc13783_ts_driver = {
-	.remove_new	= mc13783_ts_remove,
+	.remove		= mc13783_ts_remove,
 	.driver		= {
 		.name	= MC13783_TS_NAME,
 	},
diff --git a/drivers/input/touchscreen/pcap_ts.c b/drivers/input/touchscreen/pcap_ts.c
index 821245019feaa..083206a3457b8 100644
--- a/drivers/input/touchscreen/pcap_ts.c
+++ b/drivers/input/touchscreen/pcap_ts.c
@@ -238,7 +238,7 @@ static const struct dev_pm_ops pcap_ts_pm_ops = {
 
 static struct platform_driver pcap_ts_driver = {
 	.probe		= pcap_ts_probe,
-	.remove_new	= pcap_ts_remove,
+	.remove		= pcap_ts_remove,
 	.driver		= {
 		.name	= "pcap-ts",
 		.pm	= PCAP_TS_PM_OPS,
diff --git a/drivers/input/touchscreen/stmpe-ts.c b/drivers/input/touchscreen/stmpe-ts.c
index 2228842dfb494..a94a1997f96b7 100644
--- a/drivers/input/touchscreen/stmpe-ts.c
+++ b/drivers/input/touchscreen/stmpe-ts.c
@@ -362,7 +362,7 @@ static struct platform_driver stmpe_ts_driver = {
 		.name = STMPE_TS_NAME,
 	},
 	.probe = stmpe_input_probe,
-	.remove_new = stmpe_ts_remove,
+	.remove = stmpe_ts_remove,
 };
 module_platform_driver(stmpe_ts_driver);
 
diff --git a/drivers/input/touchscreen/sun4i-ts.c b/drivers/input/touchscreen/sun4i-ts.c
index 92b2b840b4b7b..e8286060043ae 100644
--- a/drivers/input/touchscreen/sun4i-ts.c
+++ b/drivers/input/touchscreen/sun4i-ts.c
@@ -396,12 +396,12 @@ static const struct of_device_id sun4i_ts_of_match[] = {
 MODULE_DEVICE_TABLE(of, sun4i_ts_of_match);
 
 static struct platform_driver sun4i_ts_driver = {
-	.driver = {
+	.driver	= {
 		.name	= "sun4i-ts",
 		.of_match_table = sun4i_ts_of_match,
 	},
 	.probe	= sun4i_ts_probe,
-	.remove_new = sun4i_ts_remove,
+	.remove	= sun4i_ts_remove,
 };
 
 module_platform_driver(sun4i_ts_driver);
diff --git a/drivers/input/touchscreen/ti_am335x_tsc.c b/drivers/input/touchscreen/ti_am335x_tsc.c
index 294b7ceded272..93d659ff90aa9 100644
--- a/drivers/input/touchscreen/ti_am335x_tsc.c
+++ b/drivers/input/touchscreen/ti_am335x_tsc.c
@@ -550,9 +550,9 @@ MODULE_DEVICE_TABLE(of, ti_tsc_dt_ids);
 
 static struct platform_driver ti_tsc_driver = {
 	.probe	= titsc_probe,
-	.remove_new = titsc_remove,
+	.remove	= titsc_remove,
 	.driver	= {
-		.name   = "TI-am335x-tsc",
+		.name	= "TI-am335x-tsc",
 		.pm	= pm_sleep_ptr(&titsc_pm_ops),
 		.of_match_table = ti_tsc_dt_ids,
 	},
diff --git a/drivers/input/touchscreen/wm831x-ts.c b/drivers/input/touchscreen/wm831x-ts.c
index 9cee26b63341d..98f8ec408cad6 100644
--- a/drivers/input/touchscreen/wm831x-ts.c
+++ b/drivers/input/touchscreen/wm831x-ts.c
@@ -387,7 +387,7 @@ static struct platform_driver wm831x_ts_driver = {
 		.name = "wm831x-touch",
 	},
 	.probe = wm831x_ts_probe,
-	.remove_new = wm831x_ts_remove,
+	.remove = wm831x_ts_remove,
 };
 module_platform_driver(wm831x_ts_driver);
 
diff --git a/drivers/input/touchscreen/wm97xx-core.c b/drivers/input/touchscreen/wm97xx-core.c
index 91384ad1aa40b..b25771a8df2b3 100644
--- a/drivers/input/touchscreen/wm97xx-core.c
+++ b/drivers/input/touchscreen/wm97xx-core.c
@@ -876,7 +876,7 @@ static struct platform_driver wm97xx_mfd_driver = {
 		.pm =		pm_sleep_ptr(&wm97xx_pm_ops),
 	},
 	.probe =	wm97xx_mfd_probe,
-	.remove_new =	wm97xx_mfd_remove,
+	.remove =	wm97xx_mfd_remove,
 };
 
 static int __init wm97xx_init(void)

From 58797abed49d6b78c7af99b03b037f20c7ffb203 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:04:17 +0200
Subject: [PATCH 0334/1530] power: supply: core: constify
 power_supply_battery_info::resist_table
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The power supply core never modifies the resist table.
Reflect this in the API, so drivers can mark their static tables as
const.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20241005-power-supply-battery-const-v1-1-c1f721927048@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/power_supply_core.c | 4 ++--
 include/linux/power_supply.h             | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index 49534458a9f7d..a01703fa83c0d 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -798,7 +798,7 @@ int power_supply_get_battery_info(struct power_supply *psy,
 		goto out_ret_pointer;
 
 	info->resist_table_size = len / (2 * sizeof(__be32));
-	resist_table = info->resist_table = devm_kcalloc(&psy->dev,
+	info->resist_table = resist_table = devm_kcalloc(&psy->dev,
 							 info->resist_table_size,
 							 sizeof(*resist_table),
 							 GFP_KERNEL);
@@ -982,7 +982,7 @@ EXPORT_SYMBOL_GPL(power_supply_battery_info_get_prop);
  *
  * Return: the battery internal resistance percent
  */
-int power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table,
+int power_supply_temp2resist_simple(const struct power_supply_resistance_temp_table *table,
 				    int table_len, int temp)
 {
 	int i, high, low;
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index 910d407ebe632..9253411c105f2 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -752,7 +752,7 @@ struct power_supply_battery_info {
 	int temp_max;
 	struct power_supply_battery_ocv_table *ocv_table[POWER_SUPPLY_OCV_TEMP_MAX];
 	int ocv_table_size[POWER_SUPPLY_OCV_TEMP_MAX];
-	struct power_supply_resistance_temp_table *resist_table;
+	const struct power_supply_resistance_temp_table *resist_table;
 	int resist_table_size;
 	const struct power_supply_vbat_ri_table *vbat2ri_discharging;
 	int vbat2ri_discharging_size;
@@ -805,7 +805,7 @@ power_supply_find_ocv2cap_table(struct power_supply_battery_info *info,
 extern int power_supply_batinfo_ocv2cap(struct power_supply_battery_info *info,
 					int ocv, int temp);
 extern int
-power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table,
+power_supply_temp2resist_simple(const struct power_supply_resistance_temp_table *table,
 				int table_len, int temp);
 extern int power_supply_vbat2ri(struct power_supply_battery_info *info,
 				int vbat_uv, bool charging);

From 40d00fa5a8be87812a7acb6524eb3d8fd3ea42b9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:04:18 +0200
Subject: [PATCH 0335/1530] power: supply: ab8500: constify resistance table
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The power supply core now allows this constification.
Prevent accidental or malicious modification of the data.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20241005-power-supply-battery-const-v1-2-c1f721927048@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/ab8500_bmdata.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/power/supply/ab8500_bmdata.c b/drivers/power/supply/ab8500_bmdata.c
index 3e6ea22372b2d..2fcfbbef05038 100644
--- a/drivers/power/supply/ab8500_bmdata.c
+++ b/drivers/power/supply/ab8500_bmdata.c
@@ -48,7 +48,7 @@ static struct power_supply_battery_ocv_table ocv_cap_tbl[] = {
  * temperature values to work. Factory resistance is 300 mOhm and the
  * resistance values to the right are percentages of 300 mOhm.
  */
-static struct power_supply_resistance_temp_table temp_to_batres_tbl_thermistor[] = {
+static const struct power_supply_resistance_temp_table temp_to_batres_tbl_thermistor[] = {
 	{ .temp = 40, .resistance = 40 /* 120 mOhm */ },
 	{ .temp = 30, .resistance = 45 /* 135 mOhm */ },
 	{ .temp = 20, .resistance = 55 /* 165 mOhm */ },

From 27fde3aa4f924793966c8aa5b10506c41ce933e1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:04:19 +0200
Subject: [PATCH 0336/1530] power: supply: samsung-sdi-battery: constify
 resistance table
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The power supply core now allows this constification.
Prevent accidental or malicious modification of the data.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20241005-power-supply-battery-const-v1-3-c1f721927048@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/samsung-sdi-battery.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/power/supply/samsung-sdi-battery.c b/drivers/power/supply/samsung-sdi-battery.c
index b63fd2758c2f1..263592d625837 100644
--- a/drivers/power/supply/samsung-sdi-battery.c
+++ b/drivers/power/supply/samsung-sdi-battery.c
@@ -431,7 +431,7 @@ static const struct power_supply_vbat_ri_table samsung_vbat2res_charging_eb58515
  * temperature compensation tables so we just state 100% for every temperature.
  * If you have the datasheets, please provide these tables.
  */
-static struct power_supply_resistance_temp_table samsung_temp2res[] = {
+static const struct power_supply_resistance_temp_table samsung_temp2res[] = {
 	{ .temp = 50, .resistance = 100 },
 	{ .temp = 40, .resistance = 100 },
 	{ .temp = 30, .resistance = 100 },

From 840683c341907b37173e270798607a83462118f1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:04:20 +0200
Subject: [PATCH 0337/1530] power: supply: sc27xx: use const reference to ocv
 table
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The table is not modified, so constify the reference.
This enables a constification in the power supply core.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20241005-power-supply-battery-const-v1-4-c1f721927048@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/sc27xx_fuel_gauge.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/power/supply/sc27xx_fuel_gauge.c b/drivers/power/supply/sc27xx_fuel_gauge.c
index bd23c4d9fed43..426d423b935b5 100644
--- a/drivers/power/supply/sc27xx_fuel_gauge.c
+++ b/drivers/power/supply/sc27xx_fuel_gauge.c
@@ -992,7 +992,7 @@ static int sc27xx_fgu_calibration(struct sc27xx_fgu_data *data)
 static int sc27xx_fgu_hw_init(struct sc27xx_fgu_data *data)
 {
 	struct power_supply_battery_info *info;
-	struct power_supply_battery_ocv_table *table;
+	const struct power_supply_battery_ocv_table *table;
 	int ret, delta_clbcnt, alarm_adc;
 
 	ret = power_supply_get_battery_info(data->battery, &info);

From ce20d5b9e37099a035ab34d4d3f59e1744756385 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:04:21 +0200
Subject: [PATCH 0338/1530] power: supply: core: constify
 power_supply_battery_info::ocv_table
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The power supply core never modifies the ocv table.
Reflect this in the API, so drivers can mark their static tables as
const.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20241005-power-supply-battery-const-v1-5-c1f721927048@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/power_supply_core.c | 8 ++++----
 include/linux/power_supply.h             | 6 +++---
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index a01703fa83c0d..5aefba2ddcda1 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -777,7 +777,7 @@ int power_supply_get_battery_info(struct power_supply *psy,
 		tab_len = size / (2 * sizeof(__be32));
 		info->ocv_table_size[index] = tab_len;
 
-		table = info->ocv_table[index] =
+		info->ocv_table[index] = table =
 			devm_kcalloc(&psy->dev, tab_len, sizeof(*table), GFP_KERNEL);
 		if (!info->ocv_table[index]) {
 			power_supply_put_battery_info(psy, info);
@@ -1093,7 +1093,7 @@ EXPORT_SYMBOL_GPL(power_supply_get_maintenance_charging_setting);
  *
  * Return: the battery capacity.
  */
-int power_supply_ocv2cap_simple(struct power_supply_battery_ocv_table *table,
+int power_supply_ocv2cap_simple(const struct power_supply_battery_ocv_table *table,
 				int table_len, int ocv)
 {
 	int i, high, low;
@@ -1118,7 +1118,7 @@ int power_supply_ocv2cap_simple(struct power_supply_battery_ocv_table *table,
 }
 EXPORT_SYMBOL_GPL(power_supply_ocv2cap_simple);
 
-struct power_supply_battery_ocv_table *
+const struct power_supply_battery_ocv_table *
 power_supply_find_ocv2cap_table(struct power_supply_battery_info *info,
 				int temp, int *table_len)
 {
@@ -1149,7 +1149,7 @@ EXPORT_SYMBOL_GPL(power_supply_find_ocv2cap_table);
 int power_supply_batinfo_ocv2cap(struct power_supply_battery_info *info,
 				 int ocv, int temp)
 {
-	struct power_supply_battery_ocv_table *table;
+	const struct power_supply_battery_ocv_table *table;
 	int table_len;
 
 	table = power_supply_find_ocv2cap_table(info, temp, &table_len);
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index 9253411c105f2..4e29ec39c18f2 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -750,7 +750,7 @@ struct power_supply_battery_info {
 	int temp_alert_max;
 	int temp_min;
 	int temp_max;
-	struct power_supply_battery_ocv_table *ocv_table[POWER_SUPPLY_OCV_TEMP_MAX];
+	const struct power_supply_battery_ocv_table *ocv_table[POWER_SUPPLY_OCV_TEMP_MAX];
 	int ocv_table_size[POWER_SUPPLY_OCV_TEMP_MAX];
 	const struct power_supply_resistance_temp_table *resist_table;
 	int resist_table_size;
@@ -797,9 +797,9 @@ extern bool power_supply_battery_info_has_prop(struct power_supply_battery_info
 extern int power_supply_battery_info_get_prop(struct power_supply_battery_info *info,
 					      enum power_supply_property psp,
 					      union power_supply_propval *val);
-extern int power_supply_ocv2cap_simple(struct power_supply_battery_ocv_table *table,
+extern int power_supply_ocv2cap_simple(const struct power_supply_battery_ocv_table *table,
 				       int table_len, int ocv);
-extern struct power_supply_battery_ocv_table *
+extern const struct power_supply_battery_ocv_table *
 power_supply_find_ocv2cap_table(struct power_supply_battery_info *info,
 				int temp, int *table_len);
 extern int power_supply_batinfo_ocv2cap(struct power_supply_battery_info *info,

From b7b6bf444529c2ead9416e79d8dd8a2cb832cd24 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:04:22 +0200
Subject: [PATCH 0339/1530] power: supply: ab8500: constify ocv table
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The power supply core now allows this constification.
Prevent accidental or malicious modification of the data.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20241005-power-supply-battery-const-v1-6-c1f721927048@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/ab8500_bmdata.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/power/supply/ab8500_bmdata.c b/drivers/power/supply/ab8500_bmdata.c
index 2fcfbbef05038..19ed528528048 100644
--- a/drivers/power/supply/ab8500_bmdata.c
+++ b/drivers/power/supply/ab8500_bmdata.c
@@ -16,7 +16,7 @@
 /* Default: temperature hysteresis */
 #define AB8500_TEMP_HYSTERESIS	3
 
-static struct power_supply_battery_ocv_table ocv_cap_tbl[] = {
+static const struct power_supply_battery_ocv_table ocv_cap_tbl[] = {
 	{ .ocv = 4186000, .capacity = 100},
 	{ .ocv = 4163000, .capacity = 99},
 	{ .ocv = 4114000, .capacity = 95},

From b5289ba57a27a212acad14b81ec6597ce140e01d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:04:23 +0200
Subject: [PATCH 0340/1530] power: supply: samsung-sdi-battery: constify ocv
 table
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The power supply core now allows this constification.
Prevent accidental or malicious modification of the data.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20241005-power-supply-battery-const-v1-7-c1f721927048@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/samsung-sdi-battery.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/power/supply/samsung-sdi-battery.c b/drivers/power/supply/samsung-sdi-battery.c
index 263592d625837..33565002ee270 100644
--- a/drivers/power/supply/samsung-sdi-battery.c
+++ b/drivers/power/supply/samsung-sdi-battery.c
@@ -447,7 +447,7 @@ static const struct power_supply_resistance_temp_table samsung_temp2res[] = {
  * These must be sorted by falling OCV value.
  */
 
-static struct power_supply_battery_ocv_table samsung_ocv_cap_eb485159lu[] = {
+static const struct power_supply_battery_ocv_table samsung_ocv_cap_eb485159lu[] = {
 	{ .ocv = 4330000, .capacity = 100},
 	{ .ocv = 4320000, .capacity = 99},
 	{ .ocv = 4283000, .capacity = 95},
@@ -499,7 +499,7 @@ static struct power_supply_battery_ocv_table samsung_ocv_cap_eb485159lu[] = {
 };
 
 /* Same capacity table is used by eb-l1m7flu, eb425161la, eb425161lu */
-static struct power_supply_battery_ocv_table samsung_ocv_cap_1500mah[] = {
+static const struct power_supply_battery_ocv_table samsung_ocv_cap_1500mah[] = {
 	{ .ocv = 4328000, .capacity = 100},
 	{ .ocv = 4299000, .capacity = 99},
 	{ .ocv = 4281000, .capacity = 98},
@@ -540,7 +540,7 @@ static struct power_supply_battery_ocv_table samsung_ocv_cap_1500mah[] = {
 	{ .ocv = 3300000, .capacity = 0},
 };
 
-static struct power_supply_battery_ocv_table samsung_ocv_cap_eb535151vu[] = {
+static const struct power_supply_battery_ocv_table samsung_ocv_cap_eb535151vu[] = {
 	{ .ocv = 4178000, .capacity = 100},
 	{ .ocv = 4148000, .capacity = 99},
 	{ .ocv = 4105000, .capacity = 95},
@@ -572,7 +572,7 @@ static struct power_supply_battery_ocv_table samsung_ocv_cap_eb535151vu[] = {
 	{ .ocv = 3300000, .capacity = 0},
 };
 
-static struct power_supply_battery_ocv_table samsung_ocv_cap_eb585157lu[] = {
+static const struct power_supply_battery_ocv_table samsung_ocv_cap_eb585157lu[] = {
 	{ .ocv = 4320000, .capacity = 100},
 	{ .ocv = 4296000, .capacity = 99},
 	{ .ocv = 4283000, .capacity = 98},

From 49000fee9e639f62ba1f965ed2ae4c5ad18d19e2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:05:03 +0200
Subject: [PATCH 0341/1530] power: supply: core: add wakeup source inhibit by
 power_supply_config
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To inhibit wakeup users currently have to use dedicated functions to
register the power supply: {,devm_}power_supply_register_no_ws().
This is inconsistent to other runtime settings which can be configured
through struct power_supply_config.
It's also not obvious what _no_ws() is meant to mean.

Extend power_supply_config to also be able to inhibit the wakeup source.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Tzung-Bi Shih <tzungbi@kernel.org>
Link: https://lore.kernel.org/r/20241005-power-supply-no-wakeup-source-v1-1-1d62bf9bcb1d@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/power_supply_core.c | 3 +++
 include/linux/power_supply.h             | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index 5aefba2ddcda1..a2005e3c6f38d 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -1410,6 +1410,9 @@ __power_supply_register(struct device *parent,
 	if (rc)
 		goto device_add_failed;
 
+	if (cfg && cfg->no_wakeup_source)
+		ws = false;
+
 	rc = device_init_wakeup(dev, ws);
 	if (rc)
 		goto wakeup_init_failed;
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index 4e29ec39c18f2..9a64043798bd7 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -236,6 +236,8 @@ struct power_supply_config {
 
 	char **supplied_to;
 	size_t num_supplicants;
+
+	bool no_wakeup_source;
 };
 
 /* Description of power supply */

From 2de244e91ddf5cfcf7d88275ad2dbe7f0367e57e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:05:04 +0200
Subject: [PATCH 0342/1530] ACPI: battery: Register power supply with
 power_supply_register()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

power_supply_register_no_ws() is going to be removed.
Switch to the general registration API.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Tzung-Bi Shih <tzungbi@kernel.org>
Link: https://lore.kernel.org/r/20241005-power-supply-no-wakeup-source-v1-2-1d62bf9bcb1d@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/acpi/battery.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index f4599261cfc31..6d4a18fc2fcd4 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -847,6 +847,7 @@ static int sysfs_add_battery(struct acpi_battery *battery)
 	struct power_supply_config psy_cfg = {
 		.drv_data = battery,
 		.attr_grp = acpi_battery_groups,
+		.no_wakeup_source = true,
 	};
 	bool full_cap_broken = false;
 
@@ -882,7 +883,7 @@ static int sysfs_add_battery(struct acpi_battery *battery)
 	battery->bat_desc.type = POWER_SUPPLY_TYPE_BATTERY;
 	battery->bat_desc.get_property = acpi_battery_get_property;
 
-	battery->bat = power_supply_register_no_ws(&battery->device->dev,
+	battery->bat = power_supply_register(&battery->device->dev,
 				&battery->bat_desc, &psy_cfg);
 
 	if (IS_ERR(battery->bat)) {

From 8c3985bb4e78fb487621dce733fae387fce174a8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:05:05 +0200
Subject: [PATCH 0343/1530] power: supply: acer_a500_battery: register power
 supply with devm_power_supply_register()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

devm_power_supply_register_no_ws() is going to be removed.
Switch to the general registration API.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Tzung-Bi Shih <tzungbi@kernel.org>
Link: https://lore.kernel.org/r/20241005-power-supply-no-wakeup-source-v1-3-1d62bf9bcb1d@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/acer_a500_battery.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/power/supply/acer_a500_battery.c b/drivers/power/supply/acer_a500_battery.c
index ef5c419b1b7f2..58e7b2eac68f9 100644
--- a/drivers/power/supply/acer_a500_battery.c
+++ b/drivers/power/supply/acer_a500_battery.c
@@ -233,14 +233,15 @@ static int a500_battery_probe(struct platform_device *pdev)
 
 	psy_cfg.of_node = pdev->dev.parent->of_node;
 	psy_cfg.drv_data = bat;
+	psy_cfg.no_wakeup_source = true;
 
 	bat->regmap = dev_get_regmap(pdev->dev.parent, "KB930");
 	if (!bat->regmap)
 		return -EINVAL;
 
-	bat->psy = devm_power_supply_register_no_ws(&pdev->dev,
-						    &a500_battery_desc,
-						    &psy_cfg);
+	bat->psy = devm_power_supply_register(&pdev->dev,
+					      &a500_battery_desc,
+					      &psy_cfg);
 	if (IS_ERR(bat->psy))
 		return dev_err_probe(&pdev->dev, PTR_ERR(bat->psy),
 				     "failed to register battery\n");

From 1011646d4bd6c2eedb68d131ba7ddaf9ecd2aa9e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:05:06 +0200
Subject: [PATCH 0344/1530] power: supply: bq27xxx_battery: register power
 supply with power_supply_register()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

devm_power_supply_register_no_ws() is going to be removed.
Switch to the general registration API.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Tzung-Bi Shih <tzungbi@kernel.org>
Link: https://lore.kernel.org/r/20241005-power-supply-no-wakeup-source-v1-4-1d62bf9bcb1d@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/bq27xxx_battery.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index 750fda543308c..e47556ec3cfea 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -2131,6 +2131,7 @@ int bq27xxx_battery_setup(struct bq27xxx_device_info *di)
 	struct power_supply_config psy_cfg = {
 		.of_node = di->dev->of_node,
 		.drv_data = di,
+		.no_wakeup_source = true,
 	};
 	int ret;
 
@@ -2157,7 +2158,7 @@ int bq27xxx_battery_setup(struct bq27xxx_device_info *di)
 	psy_desc->get_property = bq27xxx_battery_get_property;
 	psy_desc->external_power_changed = bq27xxx_external_power_changed;
 
-	di->bat = devm_power_supply_register_no_ws(di->dev, psy_desc, &psy_cfg);
+	di->bat = devm_power_supply_register(di->dev, psy_desc, &psy_cfg);
 	if (IS_ERR(di->bat))
 		return dev_err_probe(di->dev, PTR_ERR(di->bat),
 				     "failed to register battery\n");

From e8d2dfa6d246b2b879287c79098a1960b3856533 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:05:07 +0200
Subject: [PATCH 0345/1530] power: supply: cros_usbpd-charger: register power
 supply with devm_power_supply_register()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

devm_power_supply_register_no_ws() is going to be removed.
Switch to the general registration API.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Acked-by: Tzung-Bi Shih <tzungbi@kernel.org>
Link: https://lore.kernel.org/r/20241005-power-supply-no-wakeup-source-v1-5-1d62bf9bcb1d@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/cros_usbpd-charger.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/power/supply/cros_usbpd-charger.c b/drivers/power/supply/cros_usbpd-charger.c
index bed3e2e9bfea9..47d3f58aa15ce 100644
--- a/drivers/power/supply/cros_usbpd-charger.c
+++ b/drivers/power/supply/cros_usbpd-charger.c
@@ -618,6 +618,7 @@ static int cros_usbpd_charger_probe(struct platform_device *pd)
 		psy_desc->external_power_changed =
 					cros_usbpd_charger_power_changed;
 		psy_cfg.drv_data = port;
+		psy_cfg.no_wakeup_source = true;
 
 		if (cros_usbpd_charger_port_is_dedicated(port)) {
 			sprintf(port->name, CHARGER_DEDICATED_DIR_NAME);
@@ -644,8 +645,7 @@ static int cros_usbpd_charger_probe(struct platform_device *pd)
 
 		psy_desc->name = port->name;
 
-		psy = devm_power_supply_register_no_ws(dev, psy_desc,
-						       &psy_cfg);
+		psy = devm_power_supply_register(dev, psy_desc, &psy_cfg);
 		if (IS_ERR(psy)) {
 			dev_err(dev, "Failed to register power supply\n");
 			continue;

From 705833305a7a68d6ff163626abd81735940b7751 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:05:08 +0200
Subject: [PATCH 0346/1530] power: supply: lenovo_yoga_c630_battery: register
 power supplies with power_supply_register()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

{,devm_}power_supply_register_no_ws() are going to be removed.
Switch to the general registration API.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Tzung-Bi Shih <tzungbi@kernel.org>
Link: https://lore.kernel.org/r/20241005-power-supply-no-wakeup-source-v1-6-1d62bf9bcb1d@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/lenovo_yoga_c630_battery.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/power/supply/lenovo_yoga_c630_battery.c b/drivers/power/supply/lenovo_yoga_c630_battery.c
index f98f65e00831a..7a6c8af9e8c24 100644
--- a/drivers/power/supply/lenovo_yoga_c630_battery.c
+++ b/drivers/power/supply/lenovo_yoga_c630_battery.c
@@ -368,11 +368,12 @@ static int yoga_c630_psy_register_bat_psy(struct yoga_c630_psy *ecbat)
 
 	bat_cfg.drv_data = ecbat;
 	bat_cfg.fwnode = ecbat->fwnode;
-	ecbat->bat_psy = power_supply_register_no_ws(ecbat->dev,
-						     ecbat->unit_mA ?
-						     &yoga_c630_psy_bat_psy_desc_mA :
-						     &yoga_c630_psy_bat_psy_desc_mWh,
-						     &bat_cfg);
+	bat_cfg.no_wakeup_source = true;
+	ecbat->bat_psy = power_supply_register(ecbat->dev,
+					       ecbat->unit_mA ?
+					       &yoga_c630_psy_bat_psy_desc_mA :
+					       &yoga_c630_psy_bat_psy_desc_mWh,
+					       &bat_cfg);
 	if (IS_ERR(ecbat->bat_psy)) {
 		dev_err(ecbat->dev, "failed to register battery supply\n");
 		return PTR_ERR(ecbat->bat_psy);
@@ -442,7 +443,8 @@ static int yoga_c630_psy_probe(struct auxiliary_device *adev,
 	adp_cfg.fwnode = ecbat->fwnode;
 	adp_cfg.supplied_to = (char **)&yoga_c630_psy_bat_psy_desc_mA.name;
 	adp_cfg.num_supplicants = 1;
-	ecbat->adp_psy = devm_power_supply_register_no_ws(dev, &yoga_c630_psy_adpt_psy_desc, &adp_cfg);
+	adp_cfg.no_wakeup_source = true;
+	ecbat->adp_psy = devm_power_supply_register(dev, &yoga_c630_psy_adpt_psy_desc, &adp_cfg);
 	if (IS_ERR(ecbat->adp_psy)) {
 		dev_err(dev, "failed to register AC adapter supply\n");
 		return PTR_ERR(ecbat->adp_psy);

From 79b9630e6fc80f225e1564b42cae154970f31136 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:05:09 +0200
Subject: [PATCH 0347/1530] power: supply: max77976_charger: register power
 supply with devm_power_supply_register()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

devm_power_supply_register_no_ws() is going to be removed.
Switch to the general registration API.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Reviewed-by: Tzung-Bi Shih <tzungbi@kernel.org>
Link: https://lore.kernel.org/r/20241005-power-supply-no-wakeup-source-v1-7-1d62bf9bcb1d@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/max77976_charger.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/power/supply/max77976_charger.c b/drivers/power/supply/max77976_charger.c
index d7e520da76886..e6fe68cebc32b 100644
--- a/drivers/power/supply/max77976_charger.c
+++ b/drivers/power/supply/max77976_charger.c
@@ -452,6 +452,7 @@ static int max77976_probe(struct i2c_client *client)
 
 	i2c_set_clientdata(client, chg);
 	psy_cfg.drv_data = chg;
+	psy_cfg.no_wakeup_source = true;
 	chg->client = client;
 
 	chg->regmap = devm_regmap_init_i2c(client, &max77976_regmap_config);
@@ -475,7 +476,7 @@ static int max77976_probe(struct i2c_client *client)
 	if (err)
 		return err;
 
-	psy = devm_power_supply_register_no_ws(dev, &max77976_psy_desc, &psy_cfg);
+	psy = devm_power_supply_register(dev, &max77976_psy_desc, &psy_cfg);
 	if (IS_ERR(psy))
 		return dev_err_probe(dev, PTR_ERR(psy), "cannot register\n");
 

From 85d319e14f301e1c68131b74c1dceabae73d1e81 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:05:10 +0200
Subject: [PATCH 0348/1530] power: supply: core: remove
 {,devm_}power_supply_register_no_ws()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The same functionality is available through
power_supply_config::no_wakeup_source, which is more idiomatic.
All users of the old API have been converted.

Also remove the argument "ws" from __power_supply_register(),
as it is now always "true".

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Tzung-Bi Shih <tzungbi@kernel.org>
Link: https://lore.kernel.org/r/20241005-power-supply-no-wakeup-source-v1-8-1d62bf9bcb1d@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/power_supply_core.c | 71 ++----------------------
 include/linux/power_supply.h             |  8 ---
 2 files changed, 4 insertions(+), 75 deletions(-)

diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index a2005e3c6f38d..f20b0fde98471 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -1342,8 +1342,7 @@ static void psy_unregister_thermal(struct power_supply *psy)
 static struct power_supply *__must_check
 __power_supply_register(struct device *parent,
 				   const struct power_supply_desc *desc,
-				   const struct power_supply_config *cfg,
-				   bool ws)
+				   const struct power_supply_config *cfg)
 {
 	struct device *dev;
 	struct power_supply *psy;
@@ -1410,10 +1409,7 @@ __power_supply_register(struct device *parent,
 	if (rc)
 		goto device_add_failed;
 
-	if (cfg && cfg->no_wakeup_source)
-		ws = false;
-
-	rc = device_init_wakeup(dev, ws);
+	rc = device_init_wakeup(dev, cfg ? !cfg->no_wakeup_source : true);
 	if (rc)
 		goto wakeup_init_failed;
 
@@ -1479,33 +1475,10 @@ struct power_supply *__must_check power_supply_register(struct device *parent,
 		const struct power_supply_desc *desc,
 		const struct power_supply_config *cfg)
 {
-	return __power_supply_register(parent, desc, cfg, true);
+	return __power_supply_register(parent, desc, cfg);
 }
 EXPORT_SYMBOL_GPL(power_supply_register);
 
-/**
- * power_supply_register_no_ws() - Register new non-waking-source power supply
- * @parent:	Device to be a parent of power supply's device, usually
- *		the device which probe function calls this
- * @desc:	Description of power supply, must be valid through whole
- *		lifetime of this power supply
- * @cfg:	Run-time specific configuration accessed during registering,
- *		may be NULL
- *
- * Return: A pointer to newly allocated power_supply on success
- * or ERR_PTR otherwise.
- * Use power_supply_unregister() on returned power_supply pointer to release
- * resources.
- */
-struct power_supply *__must_check
-power_supply_register_no_ws(struct device *parent,
-		const struct power_supply_desc *desc,
-		const struct power_supply_config *cfg)
-{
-	return __power_supply_register(parent, desc, cfg, false);
-}
-EXPORT_SYMBOL_GPL(power_supply_register_no_ws);
-
 static void devm_power_supply_release(struct device *dev, void *res)
 {
 	struct power_supply **psy = res;
@@ -1538,7 +1511,7 @@ devm_power_supply_register(struct device *parent,
 
 	if (!ptr)
 		return ERR_PTR(-ENOMEM);
-	psy = __power_supply_register(parent, desc, cfg, true);
+	psy = __power_supply_register(parent, desc, cfg);
 	if (IS_ERR(psy)) {
 		devres_free(ptr);
 	} else {
@@ -1549,42 +1522,6 @@ devm_power_supply_register(struct device *parent,
 }
 EXPORT_SYMBOL_GPL(devm_power_supply_register);
 
-/**
- * devm_power_supply_register_no_ws() - Register managed non-waking-source power supply
- * @parent:	Device to be a parent of power supply's device, usually
- *		the device which probe function calls this
- * @desc:	Description of power supply, must be valid through whole
- *		lifetime of this power supply
- * @cfg:	Run-time specific configuration accessed during registering,
- *		may be NULL
- *
- * Return: A pointer to newly allocated power_supply on success
- * or ERR_PTR otherwise.
- * The returned power_supply pointer will be automatically unregistered
- * on driver detach.
- */
-struct power_supply *__must_check
-devm_power_supply_register_no_ws(struct device *parent,
-		const struct power_supply_desc *desc,
-		const struct power_supply_config *cfg)
-{
-	struct power_supply **ptr, *psy;
-
-	ptr = devres_alloc(devm_power_supply_release, sizeof(*ptr), GFP_KERNEL);
-
-	if (!ptr)
-		return ERR_PTR(-ENOMEM);
-	psy = __power_supply_register(parent, desc, cfg, false);
-	if (IS_ERR(psy)) {
-		devres_free(ptr);
-	} else {
-		*ptr = psy;
-		devres_add(parent, ptr);
-	}
-	return psy;
-}
-EXPORT_SYMBOL_GPL(devm_power_supply_register_no_ws);
-
 /**
  * power_supply_unregister() - Remove this power supply from system
  * @psy:	Pointer to power supply to unregister
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index 9a64043798bd7..14eedefb3ac85 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -874,17 +874,9 @@ power_supply_register(struct device *parent,
 				 const struct power_supply_desc *desc,
 				 const struct power_supply_config *cfg);
 extern struct power_supply *__must_check
-power_supply_register_no_ws(struct device *parent,
-				 const struct power_supply_desc *desc,
-				 const struct power_supply_config *cfg);
-extern struct power_supply *__must_check
 devm_power_supply_register(struct device *parent,
 				 const struct power_supply_desc *desc,
 				 const struct power_supply_config *cfg);
-extern struct power_supply *__must_check
-devm_power_supply_register_no_ws(struct device *parent,
-				 const struct power_supply_desc *desc,
-				 const struct power_supply_config *cfg);
 extern void power_supply_unregister(struct power_supply *psy);
 extern int power_supply_powers(struct power_supply *psy, struct device *dev);
 

From f6da4553ff24a5d1c959c9627c965323adc3d307 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 17 Sep 2024 12:39:14 -0700
Subject: [PATCH 0349/1530] power: supply: core: Remove might_sleep() from
 power_supply_put()

The put_device() call in power_supply_put() may call
power_supply_dev_release(). The latter function does not sleep so
power_supply_put() doesn't sleep either. Hence, remove the might_sleep()
call from power_supply_put(). This patch suppresses false positive
complaints about calling a sleeping function from atomic context if
power_supply_put() is called from atomic context.

Cc: Kyle Tso <kyletso@google.com>
Cc: Krzysztof Kozlowski <krzk@kernel.org>
Fixes: 1a352462b537 ("power_supply: Add power_supply_put for decrementing device reference counter")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20240917193914.47566-1-bvanassche@acm.org
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/power_supply_core.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index f20b0fde98471..84b77fb499497 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -484,8 +484,6 @@ EXPORT_SYMBOL_GPL(power_supply_get_by_name);
  */
 void power_supply_put(struct power_supply *psy)
 {
-	might_sleep();
-
 	atomic_dec(&psy->use_cnt);
 	put_device(&psy->dev);
 }

From 570c2234d5d62d52be7e8e35169b96d98378a7ce Mon Sep 17 00:00:00 2001
From: Shen Lichuan <shenlichuan@vivo.com>
Date: Sat, 14 Sep 2024 16:54:15 +0800
Subject: [PATCH 0350/1530] power: supply: Correct multiple typos in comments

Fixed some spelling errors, the details are as follows:

-in the code comments:
	dettached->detached
	meausered->measured
	meausurement->measurement
	sholuld->should
	Tempreture->Temperature
	measuremnts->measurements
	detecing->detecting
	persent->percent
	Parallell->Parallel

Signed-off-by: Shen Lichuan <shenlichuan@vivo.com>
Link: https://lore.kernel.org/r/20240914085415.3886-1-shenlichuan@vivo.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/88pm860x_battery.c     | 4 ++--
 drivers/power/supply/ab8500_btemp.c         | 2 +-
 drivers/power/supply/charger-manager.c      | 2 +-
 drivers/power/supply/da9030_battery.c       | 4 ++--
 drivers/power/supply/max8925_power.c        | 2 +-
 drivers/power/supply/qcom_battmgr.c         | 2 +-
 drivers/power/supply/qcom_pmi8998_charger.c | 2 +-
 7 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/power/supply/88pm860x_battery.c b/drivers/power/supply/88pm860x_battery.c
index 34619c4d4eced..b7938fbb24a51 100644
--- a/drivers/power/supply/88pm860x_battery.c
+++ b/drivers/power/supply/88pm860x_battery.c
@@ -422,7 +422,7 @@ static irqreturn_t pm860x_batt_handler(int irq, void *data)
 		info->temp_type = PM860X_TEMP_TINT;
 	}
 	mutex_unlock(&info->lock);
-	/* clear ccnt since battery is attached or dettached */
+	/* clear ccnt since battery is attached or detached */
 	clear_ccnt(info, &ccnt_data);
 	return IRQ_HANDLED;
 }
@@ -566,7 +566,7 @@ static int measure_temp(struct pm860x_battery_info *info, int *data)
 		ret = measure_12bit_voltage(info, PM8607_GPADC1_MEAS1, data);
 		if (ret)
 			return ret;
-		/* meausered Vtbat(mV) / Ibias_current(11uA)*/
+		/* measured Vtbat(mV) / Ibias_current(11uA)*/
 		*data = (*data * 1000) / GPBIAS2_GPADC1_UA;
 
 		if (*data > TBAT_NEG_25D) {
diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c
index 56f136b2d071d..87c9b8e744b31 100644
--- a/drivers/power/supply/ab8500_btemp.c
+++ b/drivers/power/supply/ab8500_btemp.c
@@ -283,7 +283,7 @@ static void ab8500_btemp_periodic_work(struct work_struct *work)
 			dev_warn(di->dev, "failed to identify the battery\n");
 	}
 
-	/* Failover if a reading is erroneous, use last meausurement */
+	/* Failover if a reading is erroneous, use last measurement */
 	ret = thermal_zone_get_temp(di->tz, &bat_temp);
 	if (ret) {
 		dev_err(di->dev, "error reading temperature\n");
diff --git a/drivers/power/supply/charger-manager.c b/drivers/power/supply/charger-manager.c
index 96f0a7fbf1051..858e2b77ee5b0 100644
--- a/drivers/power/supply/charger-manager.c
+++ b/drivers/power/supply/charger-manager.c
@@ -221,7 +221,7 @@ static bool is_charging(struct charger_manager *cm)
 
 	/* If at least one of the charger is charging, return yes */
 	for (i = 0; cm->desc->psy_charger_stat[i]; i++) {
-		/* 1. The charger sholuld not be DISABLED */
+		/* 1. The charger should not be DISABLED */
 		if (cm->emergency_stop)
 			continue;
 		if (!cm->charger_enabled)
diff --git a/drivers/power/supply/da9030_battery.c b/drivers/power/supply/da9030_battery.c
index 04e0f4162d42b..b89604a8c0199 100644
--- a/drivers/power/supply/da9030_battery.c
+++ b/drivers/power/supply/da9030_battery.c
@@ -269,7 +269,7 @@ static void da9030_charger_check_state(struct da9030_charger *charger)
 		}
 		if (charger->adc.vchmax_res > charger->thresholds.vcharge_max ||
 		    charger->adc.vchmin_res < charger->thresholds.vcharge_min ||
-		    /* Tempreture readings are negative */
+		    /* Temperature readings are negative */
 		    charger->adc.tbat_res < charger->thresholds.tbat_high ||
 		    charger->adc.tbat_res > charger->thresholds.tbat_low) {
 			/* disable charger */
@@ -470,7 +470,7 @@ static int da9030_battery_charger_init(struct da9030_charger *charger)
 	if (ret)
 		return ret;
 
-	/* enable auto ADC measuremnts */
+	/* enable auto ADC measurements */
 	return da903x_write(charger->master, DA9030_ADC_AUTO_CONTROL,
 			    DA9030_ADC_TBAT_ENABLE | DA9030_ADC_VBAT_IN_TXON |
 			    DA9030_ADC_VCH_ENABLE | DA9030_ADC_ICH_ENABLE |
diff --git a/drivers/power/supply/max8925_power.c b/drivers/power/supply/max8925_power.c
index 621a006d52a96..fc24a6d3b63d8 100644
--- a/drivers/power/supply/max8925_power.c
+++ b/drivers/power/supply/max8925_power.c
@@ -73,7 +73,7 @@ struct max8925_power_info {
 	unsigned		usb_online:1;
 	unsigned		bat_online:1;
 	unsigned		chg_mode:2;
-	unsigned		batt_detect:1;	/* detecing MB by ID pin */
+	unsigned		batt_detect:1;	/* detecting MB by ID pin */
 	unsigned		topoff_threshold:2;
 	unsigned		fast_charge:3;
 	unsigned		no_temp_support:1;
diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c
index f0a64c00ddaae..47d29271ddf40 100644
--- a/drivers/power/supply/qcom_battmgr.c
+++ b/drivers/power/supply/qcom_battmgr.c
@@ -151,7 +151,7 @@ struct qcom_battmgr_message {
 			__le32 capacity_low;
 			__le32 capacity_warning;
 			__le32 cycle_count;
-			/* thousandth of persent */
+			/* thousandth of percent */
 			__le32 accuracy;
 			__le32 max_sample_time_ms;
 			__le32 min_sample_time_ms;
diff --git a/drivers/power/supply/qcom_pmi8998_charger.c b/drivers/power/supply/qcom_pmi8998_charger.c
index 81acbd8b2169c..3b4132376649e 100644
--- a/drivers/power/supply/qcom_pmi8998_charger.c
+++ b/drivers/power/supply/qcom_pmi8998_charger.c
@@ -832,7 +832,7 @@ static const struct smb2_register smb2_init_seq[] = {
 		  AUTO_RECHG_BIT | EN_ANALOG_DROP_IN_VBATT_BIT |
 		  CHARGER_INHIBIT_BIT,
 	  .val = CHARGER_INHIBIT_BIT },
-	/* STAT pin software override, match downstream. Parallell charging? */
+	/* STAT pin software override, match downstream. Parallel charging? */
 	{ .addr = STAT_CFG,
 	  .mask = STAT_SW_OVERRIDE_CFG_BIT,
 	  .val = STAT_SW_OVERRIDE_CFG_BIT },

From 24227455dd089b965e82cc5d2142c83f40529534 Mon Sep 17 00:00:00 2001
From: Andrew Kreimer <algonell@gmail.com>
Date: Thu, 12 Sep 2024 15:52:51 +0300
Subject: [PATCH 0351/1530] power: supply: Fix a typo

Fix a typo in comments.

Reported-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Kreimer <algonell@gmail.com>
Acked-by: Michael Hennerich <michael.hennerich@analog.com>
Link: https://lore.kernel.org/r/20240912125303.44118-1-algonell@gmail.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/adp5061.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/power/supply/adp5061.c b/drivers/power/supply/adp5061.c
index dac9875d993c9..458fd3024373f 100644
--- a/drivers/power/supply/adp5061.c
+++ b/drivers/power/supply/adp5061.c
@@ -590,7 +590,7 @@ static int adp5061_get_property(struct power_supply *psy,
 	case POWER_SUPPLY_PROP_VOLTAGE_AVG:
 		/*
 		 * This property is used to set the VWEAK threshold
-		 * bellow this value, weak charge mode is entered
+		 * below this value, weak charge mode is entered
 		 * above this value, fast chargerge mode is entered
 		 */
 		return adp5061_get_vweak_th(st, val);

From 8a799831fc63c988eec90d334fdd68ff5f2c7eb5 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:08 +0200
Subject: [PATCH 0352/1530] rust: alloc: implement `ReallocFunc`

`ReallocFunc` is an abstraction for the kernel's realloc derivates, such
as `krealloc`, `vrealloc` and `kvrealloc`.

All of the named functions share the same function signature and
implement the same semantics. The `ReallocFunc` abstractions provides a
generalized wrapper around those, to trivialize the implementation of
`Kmalloc`, `Vmalloc` and `KVmalloc` in subsequent patches.

Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-5-dakr@kernel.org
[ Added temporary `allow(dead_code)` for `dangling_from_layout` to clean
  warning in `rusttest` target as discussed in the list (but it is
  needed earlier, i.e. in this patch already). Added colon. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc.rs           |  9 +++++
 rust/kernel/alloc/allocator.rs | 70 ++++++++++++++++++++++++++++++++++
 2 files changed, 79 insertions(+)

diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index 998779cc69769..95d402feb6ffd 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -187,3 +187,12 @@ pub unsafe trait Allocator {
         let _ = unsafe { Self::realloc(Some(ptr), Layout::new::<()>(), layout, Flags(0)) };
     }
 }
+
+#[allow(dead_code)]
+/// Returns a properly aligned dangling pointer from the given `layout`.
+pub(crate) fn dangling_from_layout(layout: Layout) -> NonNull<u8> {
+    let ptr = layout.align() as *mut u8;
+
+    // SAFETY: `layout.align()` (and hence `ptr`) is guaranteed to be non-zero.
+    unsafe { NonNull::new_unchecked(ptr) }
+}
diff --git a/rust/kernel/alloc/allocator.rs b/rust/kernel/alloc/allocator.rs
index 3b1c735ba409f..9ed122401e8a4 100644
--- a/rust/kernel/alloc/allocator.rs
+++ b/rust/kernel/alloc/allocator.rs
@@ -1,10 +1,20 @@
 // SPDX-License-Identifier: GPL-2.0
 
 //! Allocator support.
+//!
+//! Documentation for the kernel's memory allocators can found in the "Memory Allocation Guide"
+//! linked below. For instance, this includes the concept of "get free page" (GFP) flags and the
+//! typical application of the different kernel allocators.
+//!
+//! Reference: <https://docs.kernel.org/core-api/memory-allocation.html>
 
 use super::{flags::*, Flags};
 use core::alloc::{GlobalAlloc, Layout};
 use core::ptr;
+use core::ptr::NonNull;
+
+use crate::alloc::AllocError;
+use crate::bindings;
 
 struct Kmalloc;
 
@@ -36,6 +46,66 @@ pub(crate) unsafe fn krealloc_aligned(ptr: *mut u8, new_layout: Layout, flags: F
     unsafe { bindings::krealloc(ptr as *const core::ffi::c_void, size, flags.0) as *mut u8 }
 }
 
+/// # Invariants
+///
+/// One of the following: `krealloc`, `vrealloc`, `kvrealloc`.
+struct ReallocFunc(
+    unsafe extern "C" fn(*const core::ffi::c_void, usize, u32) -> *mut core::ffi::c_void,
+);
+
+#[expect(dead_code)]
+impl ReallocFunc {
+    /// # Safety
+    ///
+    /// This method has the same safety requirements as [`Allocator::realloc`].
+    ///
+    /// # Guarantees
+    ///
+    /// This method has the same guarantees as `Allocator::realloc`. Additionally
+    /// - it accepts any pointer to a valid memory allocation allocated by this function.
+    /// - memory allocated by this function remains valid until it is passed to this function.
+    unsafe fn call(
+        &self,
+        ptr: Option<NonNull<u8>>,
+        layout: Layout,
+        old_layout: Layout,
+        flags: Flags,
+    ) -> Result<NonNull<[u8]>, AllocError> {
+        let size = aligned_size(layout);
+        let ptr = match ptr {
+            Some(ptr) => {
+                if old_layout.size() == 0 {
+                    ptr::null()
+                } else {
+                    ptr.as_ptr()
+                }
+            }
+            None => ptr::null(),
+        };
+
+        // SAFETY:
+        // - `self.0` is one of `krealloc`, `vrealloc`, `kvrealloc` and thus only requires that
+        //   `ptr` is NULL or valid.
+        // - `ptr` is either NULL or valid by the safety requirements of this function.
+        //
+        // GUARANTEE:
+        // - `self.0` is one of `krealloc`, `vrealloc`, `kvrealloc`.
+        // - Those functions provide the guarantees of this function.
+        let raw_ptr = unsafe {
+            // If `size == 0` and `ptr != NULL` the memory behind the pointer is freed.
+            self.0(ptr.cast(), size, flags.0).cast()
+        };
+
+        let ptr = if size == 0 {
+            crate::alloc::dangling_from_layout(layout)
+        } else {
+            NonNull::new(raw_ptr).ok_or(AllocError)?
+        };
+
+        Ok(NonNull::slice_from_raw_parts(ptr, size))
+    }
+}
+
 // SAFETY: TODO.
 unsafe impl GlobalAlloc for Kmalloc {
     unsafe fn alloc(&self, layout: Layout) -> *mut u8 {

From a87a36f0bf517dae22f3e3790b05c979070f776a Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:09 +0200
Subject: [PATCH 0353/1530] rust: alloc: make `allocator` module public

Subsequent patches implement allocators such as `Kmalloc`, `Vmalloc`,
`KVmalloc`; we need them to be available outside of the kernel crate as
well.

Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-6-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index 95d402feb6ffd..2203852c37121 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -4,7 +4,7 @@
 
 #[cfg(not(test))]
 #[cfg(not(testlib))]
-mod allocator;
+pub mod allocator;
 pub mod box_ext;
 pub mod vec_ext;
 

From a34822d1c4c93085f635b922441a017bd7e959b0 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:10 +0200
Subject: [PATCH 0354/1530] rust: alloc: implement `Allocator` for `Kmalloc`

Implement `Allocator` for `Kmalloc`, the kernel's default allocator,
typically used for objects smaller than page size.

All memory allocations made with `Kmalloc` end up in `krealloc()`.

It serves as allocator for the subsequently introduced types `KBox` and
`KVec`.

Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-7-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc/allocator.rs | 31 ++++++++++++++++++++++++++++---
 1 file changed, 28 insertions(+), 3 deletions(-)

diff --git a/rust/kernel/alloc/allocator.rs b/rust/kernel/alloc/allocator.rs
index 9ed122401e8a4..272c581e24a01 100644
--- a/rust/kernel/alloc/allocator.rs
+++ b/rust/kernel/alloc/allocator.rs
@@ -13,10 +13,16 @@ use core::alloc::{GlobalAlloc, Layout};
 use core::ptr;
 use core::ptr::NonNull;
 
-use crate::alloc::AllocError;
+use crate::alloc::{AllocError, Allocator};
 use crate::bindings;
 
-struct Kmalloc;
+/// The contiguous kernel allocator.
+///
+/// `Kmalloc` is typically used for physically contiguous allocations up to page size, but also
+/// supports larger allocations up to `bindings::KMALLOC_MAX_SIZE`, which is hardware specific.
+///
+/// For more details see [self].
+pub struct Kmalloc;
 
 /// Returns a proper size to alloc a new object aligned to `new_layout`'s alignment.
 fn aligned_size(new_layout: Layout) -> usize {
@@ -53,8 +59,10 @@ struct ReallocFunc(
     unsafe extern "C" fn(*const core::ffi::c_void, usize, u32) -> *mut core::ffi::c_void,
 );
 
-#[expect(dead_code)]
 impl ReallocFunc {
+    // INVARIANT: `krealloc` satisfies the type invariants.
+    const KREALLOC: Self = Self(bindings::krealloc);
+
     /// # Safety
     ///
     /// This method has the same safety requirements as [`Allocator::realloc`].
@@ -106,6 +114,23 @@ impl ReallocFunc {
     }
 }
 
+// SAFETY: `realloc` delegates to `ReallocFunc::call`, which guarantees that
+// - memory remains valid until it is explicitly freed,
+// - passing a pointer to a valid memory allocation is OK,
+// - `realloc` satisfies the guarantees, since `ReallocFunc::call` has the same.
+unsafe impl Allocator for Kmalloc {
+    #[inline]
+    unsafe fn realloc(
+        ptr: Option<NonNull<u8>>,
+        layout: Layout,
+        old_layout: Layout,
+        flags: Flags,
+    ) -> Result<NonNull<[u8]>, AllocError> {
+        // SAFETY: `ReallocFunc::call` has the same safety requirements as `Allocator::realloc`.
+        unsafe { ReallocFunc::KREALLOC.call(ptr, layout, old_layout, flags) }
+    }
+}
+
 // SAFETY: TODO.
 unsafe impl GlobalAlloc for Kmalloc {
     unsafe fn alloc(&self, layout: Layout) -> *mut u8 {

From 5a888c28e3b4ff6f54a53fca33951537d135e7f1 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:11 +0200
Subject: [PATCH 0355/1530] rust: alloc: add module `allocator_test`

`Allocator`s, such as `Kmalloc`, will be used by e.g. `Box` and `Vec` in
subsequent patches, and hence this dependency propagates throughout the
whole kernel.

Add the `allocator_test` module that provides an empty implementation
for all `Allocator`s in the kernel, such that we don't break the
`rusttest` make target in subsequent patches.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-8-dakr@kernel.org
[ Added missing `_old_layout` parameter as discussed. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc.rs                |  9 +++++++--
 rust/kernel/alloc/allocator_test.rs | 20 ++++++++++++++++++++
 2 files changed, 27 insertions(+), 2 deletions(-)
 create mode 100644 rust/kernel/alloc/allocator_test.rs

diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index 2203852c37121..b5605aab182d3 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -2,12 +2,17 @@
 
 //! Extensions to the [`alloc`] crate.
 
-#[cfg(not(test))]
-#[cfg(not(testlib))]
+#[cfg(not(any(test, testlib)))]
 pub mod allocator;
 pub mod box_ext;
 pub mod vec_ext;
 
+#[cfg(any(test, testlib))]
+pub mod allocator_test;
+
+#[cfg(any(test, testlib))]
+pub use self::allocator_test as allocator;
+
 /// Indicates an allocation error.
 #[derive(Copy, Clone, PartialEq, Eq, Debug)]
 pub struct AllocError;
diff --git a/rust/kernel/alloc/allocator_test.rs b/rust/kernel/alloc/allocator_test.rs
new file mode 100644
index 0000000000000..c5d325506f0c7
--- /dev/null
+++ b/rust/kernel/alloc/allocator_test.rs
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#![allow(missing_docs)]
+
+use super::{AllocError, Allocator, Flags};
+use core::alloc::Layout;
+use core::ptr::NonNull;
+
+pub struct Kmalloc;
+
+unsafe impl Allocator for Kmalloc {
+    unsafe fn realloc(
+        _ptr: Option<NonNull<u8>>,
+        _layout: Layout,
+        _old_layout: Layout,
+        _flags: Flags,
+    ) -> Result<NonNull<[u8]>, AllocError> {
+        panic!();
+    }
+}

From 61c004781d6b928443052e7a6cf84b35d4f61401 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:12 +0200
Subject: [PATCH 0356/1530] rust: alloc: implement `Vmalloc` allocator

Implement `Allocator` for `Vmalloc`, the kernel's virtually contiguous
allocator, typically used for larger objects, (much) larger than page
size.

All memory allocations made with `Vmalloc` end up in `vrealloc()`.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-9-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/helpers/helpers.c              |  1 +
 rust/helpers/vmalloc.c              |  9 +++++++
 rust/kernel/alloc/allocator.rs      | 37 +++++++++++++++++++++++++++++
 rust/kernel/alloc/allocator_test.rs |  1 +
 4 files changed, 48 insertions(+)
 create mode 100644 rust/helpers/vmalloc.c

diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c
index 30f40149f3a96..20a0c69d5cc7b 100644
--- a/rust/helpers/helpers.c
+++ b/rust/helpers/helpers.c
@@ -22,5 +22,6 @@
 #include "spinlock.c"
 #include "task.c"
 #include "uaccess.c"
+#include "vmalloc.c"
 #include "wait.c"
 #include "workqueue.c"
diff --git a/rust/helpers/vmalloc.c b/rust/helpers/vmalloc.c
new file mode 100644
index 0000000000000..80d34501bbc01
--- /dev/null
+++ b/rust/helpers/vmalloc.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/vmalloc.h>
+
+void * __must_check __realloc_size(2)
+rust_helper_vrealloc(const void *p, size_t size, gfp_t flags)
+{
+	return vrealloc(p, size, flags);
+}
diff --git a/rust/kernel/alloc/allocator.rs b/rust/kernel/alloc/allocator.rs
index 272c581e24a01..ee4c828cbd58b 100644
--- a/rust/kernel/alloc/allocator.rs
+++ b/rust/kernel/alloc/allocator.rs
@@ -15,6 +15,7 @@ use core::ptr::NonNull;
 
 use crate::alloc::{AllocError, Allocator};
 use crate::bindings;
+use crate::pr_warn;
 
 /// The contiguous kernel allocator.
 ///
@@ -24,6 +25,15 @@ use crate::bindings;
 /// For more details see [self].
 pub struct Kmalloc;
 
+/// The virtually contiguous kernel allocator.
+///
+/// `Vmalloc` allocates pages from the page level allocator and maps them into the contiguous kernel
+/// virtual space. It is typically used for large allocations. The memory allocated with this
+/// allocator is not physically contiguous.
+///
+/// For more details see [self].
+pub struct Vmalloc;
+
 /// Returns a proper size to alloc a new object aligned to `new_layout`'s alignment.
 fn aligned_size(new_layout: Layout) -> usize {
     // Customized layouts from `Layout::from_size_align()` can have size < align, so pad first.
@@ -63,6 +73,9 @@ impl ReallocFunc {
     // INVARIANT: `krealloc` satisfies the type invariants.
     const KREALLOC: Self = Self(bindings::krealloc);
 
+    // INVARIANT: `vrealloc` satisfies the type invariants.
+    const VREALLOC: Self = Self(bindings::vrealloc);
+
     /// # Safety
     ///
     /// This method has the same safety requirements as [`Allocator::realloc`].
@@ -168,6 +181,30 @@ unsafe impl GlobalAlloc for Kmalloc {
     }
 }
 
+// SAFETY: `realloc` delegates to `ReallocFunc::call`, which guarantees that
+// - memory remains valid until it is explicitly freed,
+// - passing a pointer to a valid memory allocation is OK,
+// - `realloc` satisfies the guarantees, since `ReallocFunc::call` has the same.
+unsafe impl Allocator for Vmalloc {
+    #[inline]
+    unsafe fn realloc(
+        ptr: Option<NonNull<u8>>,
+        layout: Layout,
+        old_layout: Layout,
+        flags: Flags,
+    ) -> Result<NonNull<[u8]>, AllocError> {
+        // TODO: Support alignments larger than PAGE_SIZE.
+        if layout.align() > bindings::PAGE_SIZE {
+            pr_warn!("Vmalloc does not support alignments larger than PAGE_SIZE yet.\n");
+            return Err(AllocError);
+        }
+
+        // SAFETY: If not `None`, `ptr` is guaranteed to point to valid memory, which was previously
+        // allocated with this `Allocator`.
+        unsafe { ReallocFunc::VREALLOC.call(ptr, layout, old_layout, flags) }
+    }
+}
+
 #[global_allocator]
 static ALLOCATOR: Kmalloc = Kmalloc;
 
diff --git a/rust/kernel/alloc/allocator_test.rs b/rust/kernel/alloc/allocator_test.rs
index c5d325506f0c7..32a1450c4d392 100644
--- a/rust/kernel/alloc/allocator_test.rs
+++ b/rust/kernel/alloc/allocator_test.rs
@@ -7,6 +7,7 @@ use core::alloc::Layout;
 use core::ptr::NonNull;
 
 pub struct Kmalloc;
+pub type Vmalloc = Kmalloc;
 
 unsafe impl Allocator for Kmalloc {
     unsafe fn realloc(

From 8362c2608ba1be635ffa22a256dfcfe51c6238cc Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:13 +0200
Subject: [PATCH 0357/1530] rust: alloc: implement `KVmalloc` allocator

Implement `Allocator` for `KVmalloc`, an `Allocator` that tries to
allocate memory with `kmalloc` first and, on failure, falls back to
`vmalloc`.

All memory allocations made with `KVmalloc` end up in
`kvrealloc_noprof()`; all frees in `kvfree()`.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-10-dakr@kernel.org
[ Reworded typo. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/helpers/slab.c                 |  6 +++++
 rust/kernel/alloc/allocator.rs      | 36 +++++++++++++++++++++++++++++
 rust/kernel/alloc/allocator_test.rs |  1 +
 3 files changed, 43 insertions(+)

diff --git a/rust/helpers/slab.c b/rust/helpers/slab.c
index f043e087f9d66..a842bfbddcba9 100644
--- a/rust/helpers/slab.c
+++ b/rust/helpers/slab.c
@@ -7,3 +7,9 @@ rust_helper_krealloc(const void *objp, size_t new_size, gfp_t flags)
 {
 	return krealloc(objp, new_size, flags);
 }
+
+void * __must_check __realloc_size(2)
+rust_helper_kvrealloc(const void *p, size_t size, gfp_t flags)
+{
+	return kvrealloc(p, size, flags);
+}
diff --git a/rust/kernel/alloc/allocator.rs b/rust/kernel/alloc/allocator.rs
index ee4c828cbd58b..f8a1f0feb25d2 100644
--- a/rust/kernel/alloc/allocator.rs
+++ b/rust/kernel/alloc/allocator.rs
@@ -34,6 +34,15 @@ pub struct Kmalloc;
 /// For more details see [self].
 pub struct Vmalloc;
 
+/// The kvmalloc kernel allocator.
+///
+/// `KVmalloc` attempts to allocate memory with `Kmalloc` first, but falls back to `Vmalloc` upon
+/// failure. This allocator is typically used when the size for the requested allocation is not
+/// known and may exceed the capabilities of `Kmalloc`.
+///
+/// For more details see [self].
+pub struct KVmalloc;
+
 /// Returns a proper size to alloc a new object aligned to `new_layout`'s alignment.
 fn aligned_size(new_layout: Layout) -> usize {
     // Customized layouts from `Layout::from_size_align()` can have size < align, so pad first.
@@ -76,6 +85,9 @@ impl ReallocFunc {
     // INVARIANT: `vrealloc` satisfies the type invariants.
     const VREALLOC: Self = Self(bindings::vrealloc);
 
+    // INVARIANT: `kvrealloc` satisfies the type invariants.
+    const KVREALLOC: Self = Self(bindings::kvrealloc);
+
     /// # Safety
     ///
     /// This method has the same safety requirements as [`Allocator::realloc`].
@@ -205,6 +217,30 @@ unsafe impl Allocator for Vmalloc {
     }
 }
 
+// SAFETY: `realloc` delegates to `ReallocFunc::call`, which guarantees that
+// - memory remains valid until it is explicitly freed,
+// - passing a pointer to a valid memory allocation is OK,
+// - `realloc` satisfies the guarantees, since `ReallocFunc::call` has the same.
+unsafe impl Allocator for KVmalloc {
+    #[inline]
+    unsafe fn realloc(
+        ptr: Option<NonNull<u8>>,
+        layout: Layout,
+        old_layout: Layout,
+        flags: Flags,
+    ) -> Result<NonNull<[u8]>, AllocError> {
+        // TODO: Support alignments larger than PAGE_SIZE.
+        if layout.align() > bindings::PAGE_SIZE {
+            pr_warn!("KVmalloc does not support alignments larger than PAGE_SIZE yet.\n");
+            return Err(AllocError);
+        }
+
+        // SAFETY: If not `None`, `ptr` is guaranteed to point to valid memory, which was previously
+        // allocated with this `Allocator`.
+        unsafe { ReallocFunc::KVREALLOC.call(ptr, layout, old_layout, flags) }
+    }
+}
+
 #[global_allocator]
 static ALLOCATOR: Kmalloc = Kmalloc;
 
diff --git a/rust/kernel/alloc/allocator_test.rs b/rust/kernel/alloc/allocator_test.rs
index 32a1450c4d392..bd0cbcd93e528 100644
--- a/rust/kernel/alloc/allocator_test.rs
+++ b/rust/kernel/alloc/allocator_test.rs
@@ -8,6 +8,7 @@ use core::ptr::NonNull;
 
 pub struct Kmalloc;
 pub type Vmalloc = Kmalloc;
+pub type KVmalloc = Kmalloc;
 
 unsafe impl Allocator for Kmalloc {
     unsafe fn realloc(

From 01b2196e5aac8af9343282d0044fa0d6b07d484c Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:14 +0200
Subject: [PATCH 0358/1530] rust: alloc: add __GFP_NOWARN to `Flags`

Some test cases in subsequent patches provoke allocation failures. Add
`__GFP_NOWARN` to enable test cases to silence unpleasant warnings.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-11-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/bindings/bindings_helper.h | 1 +
 rust/kernel/alloc.rs            | 5 +++++
 2 files changed, 6 insertions(+)

diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index ae82e9c941afa..a80783fcbe042 100644
--- a/rust/bindings/bindings_helper.h
+++ b/rust/bindings/bindings_helper.h
@@ -31,4 +31,5 @@ const gfp_t RUST_CONST_HELPER_GFP_KERNEL_ACCOUNT = GFP_KERNEL_ACCOUNT;
 const gfp_t RUST_CONST_HELPER_GFP_NOWAIT = GFP_NOWAIT;
 const gfp_t RUST_CONST_HELPER___GFP_ZERO = __GFP_ZERO;
 const gfp_t RUST_CONST_HELPER___GFP_HIGHMEM = ___GFP_HIGHMEM;
+const gfp_t RUST_CONST_HELPER___GFP_NOWARN = ___GFP_NOWARN;
 const blk_features_t RUST_CONST_HELPER_BLK_FEAT_ROTATIONAL = BLK_FEAT_ROTATIONAL;
diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index b5605aab182d3..8172106a1423e 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -91,6 +91,11 @@ pub mod flags {
     /// use any filesystem callback.  It is very likely to fail to allocate memory, even for very
     /// small allocations.
     pub const GFP_NOWAIT: Flags = Flags(bindings::GFP_NOWAIT);
+
+    /// Suppresses allocation failure reports.
+    ///
+    /// This is normally or'd with other flags.
+    pub const __GFP_NOWARN: Flags = Flags(bindings::__GFP_NOWARN);
 }
 
 /// The kernel's [`Allocator`] trait.

From c8cfa8d0c0b10be216861fe904ea68978b1dcc97 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:15 +0200
Subject: [PATCH 0359/1530] rust: alloc: implement kernel `Box`

`Box` provides the simplest way to allocate memory for a generic type
with one of the kernel's allocators, e.g. `Kmalloc`, `Vmalloc` or
`KVmalloc`.

In contrast to Rust's `Box` type, the kernel `Box` type considers the
kernel's GFP flags for all appropriate functions, always reports
allocation failures through `Result<_, AllocError>` and remains
independent from unstable features.

Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-12-dakr@kernel.org
[ Added backticks, fixed typos. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc.rs      |   6 +
 rust/kernel/alloc/kbox.rs | 456 ++++++++++++++++++++++++++++++++++++++
 rust/kernel/prelude.rs    |   2 +-
 3 files changed, 463 insertions(+), 1 deletion(-)
 create mode 100644 rust/kernel/alloc/kbox.rs

diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index 8172106a1423e..3628e16240a69 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -5,6 +5,7 @@
 #[cfg(not(any(test, testlib)))]
 pub mod allocator;
 pub mod box_ext;
+pub mod kbox;
 pub mod vec_ext;
 
 #[cfg(any(test, testlib))]
@@ -13,6 +14,11 @@ pub mod allocator_test;
 #[cfg(any(test, testlib))]
 pub use self::allocator_test as allocator;
 
+pub use self::kbox::Box;
+pub use self::kbox::KBox;
+pub use self::kbox::KVBox;
+pub use self::kbox::VBox;
+
 /// Indicates an allocation error.
 #[derive(Copy, Clone, PartialEq, Eq, Debug)]
 pub struct AllocError;
diff --git a/rust/kernel/alloc/kbox.rs b/rust/kernel/alloc/kbox.rs
new file mode 100644
index 0000000000000..d69c32496b86a
--- /dev/null
+++ b/rust/kernel/alloc/kbox.rs
@@ -0,0 +1,456 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Implementation of [`Box`].
+
+#[allow(unused_imports)] // Used in doc comments.
+use super::allocator::{KVmalloc, Kmalloc, Vmalloc};
+use super::{AllocError, Allocator, Flags};
+use core::alloc::Layout;
+use core::fmt;
+use core::marker::PhantomData;
+use core::mem::ManuallyDrop;
+use core::mem::MaybeUninit;
+use core::ops::{Deref, DerefMut};
+use core::pin::Pin;
+use core::ptr::NonNull;
+use core::result::Result;
+
+use crate::init::{InPlaceInit, InPlaceWrite, Init, PinInit};
+use crate::types::ForeignOwnable;
+
+/// The kernel's [`Box`] type -- a heap allocation for a single value of type `T`.
+///
+/// This is the kernel's version of the Rust stdlib's `Box`. There are several differences,
+/// for example no `noalias` attribute is emitted and partially moving out of a `Box` is not
+/// supported. There are also several API differences, e.g. `Box` always requires an [`Allocator`]
+/// implementation to be passed as generic, page [`Flags`] when allocating memory and all functions
+/// that may allocate memory are fallible.
+///
+/// `Box` works with any of the kernel's allocators, e.g. [`Kmalloc`], [`Vmalloc`] or [`KVmalloc`].
+/// There are aliases for `Box` with these allocators ([`KBox`], [`VBox`], [`KVBox`]).
+///
+/// When dropping a [`Box`], the value is also dropped and the heap memory is automatically freed.
+///
+/// # Examples
+///
+/// ```
+/// let b = KBox::<u64>::new(24_u64, GFP_KERNEL)?;
+///
+/// assert_eq!(*b, 24_u64);
+/// # Ok::<(), Error>(())
+/// ```
+///
+/// ```
+/// # use kernel::bindings;
+/// const SIZE: usize = bindings::KMALLOC_MAX_SIZE as usize + 1;
+/// struct Huge([u8; SIZE]);
+///
+/// assert!(KBox::<Huge>::new_uninit(GFP_KERNEL | __GFP_NOWARN).is_err());
+/// ```
+///
+/// ```
+/// # use kernel::bindings;
+/// const SIZE: usize = bindings::KMALLOC_MAX_SIZE as usize + 1;
+/// struct Huge([u8; SIZE]);
+///
+/// assert!(KVBox::<Huge>::new_uninit(GFP_KERNEL).is_ok());
+/// ```
+///
+/// # Invariants
+///
+/// `self.0` is always properly aligned and either points to memory allocated with `A` or, for
+/// zero-sized types, is a dangling, well aligned pointer.
+#[repr(transparent)]
+pub struct Box<T: ?Sized, A: Allocator>(NonNull<T>, PhantomData<A>);
+
+/// Type alias for [`Box`] with a [`Kmalloc`] allocator.
+///
+/// # Examples
+///
+/// ```
+/// let b = KBox::new(24_u64, GFP_KERNEL)?;
+///
+/// assert_eq!(*b, 24_u64);
+/// # Ok::<(), Error>(())
+/// ```
+pub type KBox<T> = Box<T, super::allocator::Kmalloc>;
+
+/// Type alias for [`Box`] with a [`Vmalloc`] allocator.
+///
+/// # Examples
+///
+/// ```
+/// let b = VBox::new(24_u64, GFP_KERNEL)?;
+///
+/// assert_eq!(*b, 24_u64);
+/// # Ok::<(), Error>(())
+/// ```
+pub type VBox<T> = Box<T, super::allocator::Vmalloc>;
+
+/// Type alias for [`Box`] with a [`KVmalloc`] allocator.
+///
+/// # Examples
+///
+/// ```
+/// let b = KVBox::new(24_u64, GFP_KERNEL)?;
+///
+/// assert_eq!(*b, 24_u64);
+/// # Ok::<(), Error>(())
+/// ```
+pub type KVBox<T> = Box<T, super::allocator::KVmalloc>;
+
+// SAFETY: `Box` is `Send` if `T` is `Send` because the `Box` owns a `T`.
+unsafe impl<T, A> Send for Box<T, A>
+where
+    T: Send + ?Sized,
+    A: Allocator,
+{
+}
+
+// SAFETY: `Box` is `Sync` if `T` is `Sync` because the `Box` owns a `T`.
+unsafe impl<T, A> Sync for Box<T, A>
+where
+    T: Sync + ?Sized,
+    A: Allocator,
+{
+}
+
+impl<T, A> Box<T, A>
+where
+    T: ?Sized,
+    A: Allocator,
+{
+    /// Creates a new `Box<T, A>` from a raw pointer.
+    ///
+    /// # Safety
+    ///
+    /// For non-ZSTs, `raw` must point at an allocation allocated with `A` that is sufficiently
+    /// aligned for and holds a valid `T`. The caller passes ownership of the allocation to the
+    /// `Box`.
+    ///
+    /// For ZSTs, `raw` must be a dangling, well aligned pointer.
+    #[inline]
+    pub const unsafe fn from_raw(raw: *mut T) -> Self {
+        // INVARIANT: Validity of `raw` is guaranteed by the safety preconditions of this function.
+        // SAFETY: By the safety preconditions of this function, `raw` is not a NULL pointer.
+        Self(unsafe { NonNull::new_unchecked(raw) }, PhantomData)
+    }
+
+    /// Consumes the `Box<T, A>` and returns a raw pointer.
+    ///
+    /// This will not run the destructor of `T` and for non-ZSTs the allocation will stay alive
+    /// indefinitely. Use [`Box::from_raw`] to recover the [`Box`], drop the value and free the
+    /// allocation, if any.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let x = KBox::new(24, GFP_KERNEL)?;
+    /// let ptr = KBox::into_raw(x);
+    /// // SAFETY: `ptr` comes from a previous call to `KBox::into_raw`.
+    /// let x = unsafe { KBox::from_raw(ptr) };
+    ///
+    /// assert_eq!(*x, 24);
+    /// # Ok::<(), Error>(())
+    /// ```
+    #[inline]
+    pub fn into_raw(b: Self) -> *mut T {
+        ManuallyDrop::new(b).0.as_ptr()
+    }
+
+    /// Consumes and leaks the `Box<T, A>` and returns a mutable reference.
+    ///
+    /// See [`Box::into_raw`] for more details.
+    #[inline]
+    pub fn leak<'a>(b: Self) -> &'a mut T {
+        // SAFETY: `Box::into_raw` always returns a properly aligned and dereferenceable pointer
+        // which points to an initialized instance of `T`.
+        unsafe { &mut *Box::into_raw(b) }
+    }
+}
+
+impl<T, A> Box<MaybeUninit<T>, A>
+where
+    A: Allocator,
+{
+    /// Converts a `Box<MaybeUninit<T>, A>` to a `Box<T, A>`.
+    ///
+    /// It is undefined behavior to call this function while the value inside of `b` is not yet
+    /// fully initialized.
+    ///
+    /// # Safety
+    ///
+    /// Callers must ensure that the value inside of `b` is in an initialized state.
+    pub unsafe fn assume_init(self) -> Box<T, A> {
+        let raw = Self::into_raw(self);
+
+        // SAFETY: `raw` comes from a previous call to `Box::into_raw`. By the safety requirements
+        // of this function, the value inside the `Box` is in an initialized state. Hence, it is
+        // safe to reconstruct the `Box` as `Box<T, A>`.
+        unsafe { Box::from_raw(raw.cast()) }
+    }
+
+    /// Writes the value and converts to `Box<T, A>`.
+    pub fn write(mut self, value: T) -> Box<T, A> {
+        (*self).write(value);
+
+        // SAFETY: We've just initialized `b`'s value.
+        unsafe { self.assume_init() }
+    }
+}
+
+impl<T, A> Box<T, A>
+where
+    A: Allocator,
+{
+    /// Creates a new `Box<T, A>` and initializes its contents with `x`.
+    ///
+    /// New memory is allocated with `A`. The allocation may fail, in which case an error is
+    /// returned. For ZSTs no memory is allocated.
+    pub fn new(x: T, flags: Flags) -> Result<Self, AllocError> {
+        let b = Self::new_uninit(flags)?;
+        Ok(Box::write(b, x))
+    }
+
+    /// Creates a new `Box<T, A>` with uninitialized contents.
+    ///
+    /// New memory is allocated with `A`. The allocation may fail, in which case an error is
+    /// returned. For ZSTs no memory is allocated.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let b = KBox::<u64>::new_uninit(GFP_KERNEL)?;
+    /// let b = KBox::write(b, 24);
+    ///
+    /// assert_eq!(*b, 24_u64);
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn new_uninit(flags: Flags) -> Result<Box<MaybeUninit<T>, A>, AllocError> {
+        let layout = Layout::new::<MaybeUninit<T>>();
+        let ptr = A::alloc(layout, flags)?;
+
+        // INVARIANT: `ptr` is either a dangling pointer or points to memory allocated with `A`,
+        // which is sufficient in size and alignment for storing a `T`.
+        Ok(Box(ptr.cast(), PhantomData))
+    }
+
+    /// Constructs a new `Pin<Box<T, A>>`. If `T` does not implement [`Unpin`], then `x` will be
+    /// pinned in memory and can't be moved.
+    #[inline]
+    pub fn pin(x: T, flags: Flags) -> Result<Pin<Box<T, A>>, AllocError>
+    where
+        A: 'static,
+    {
+        Ok(Self::new(x, flags)?.into())
+    }
+
+    /// Forgets the contents (does not run the destructor), but keeps the allocation.
+    fn forget_contents(this: Self) -> Box<MaybeUninit<T>, A> {
+        let ptr = Self::into_raw(this);
+
+        // SAFETY: `ptr` is valid, because it came from `Box::into_raw`.
+        unsafe { Box::from_raw(ptr.cast()) }
+    }
+
+    /// Drops the contents, but keeps the allocation.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let value = KBox::new([0; 32], GFP_KERNEL)?;
+    /// assert_eq!(*value, [0; 32]);
+    /// let value = KBox::drop_contents(value);
+    /// // Now we can re-use `value`:
+    /// let value = KBox::write(value, [1; 32]);
+    /// assert_eq!(*value, [1; 32]);
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn drop_contents(this: Self) -> Box<MaybeUninit<T>, A> {
+        let ptr = this.0.as_ptr();
+
+        // SAFETY: `ptr` is valid, because it came from `this`. After this call we never access the
+        // value stored in `this` again.
+        unsafe { core::ptr::drop_in_place(ptr) };
+
+        Self::forget_contents(this)
+    }
+
+    /// Moves the `Box`'s value out of the `Box` and consumes the `Box`.
+    pub fn into_inner(b: Self) -> T {
+        // SAFETY: By the type invariant `&*b` is valid for `read`.
+        let value = unsafe { core::ptr::read(&*b) };
+        let _ = Self::forget_contents(b);
+        value
+    }
+}
+
+impl<T, A> From<Box<T, A>> for Pin<Box<T, A>>
+where
+    T: ?Sized,
+    A: Allocator,
+{
+    /// Converts a `Box<T, A>` into a `Pin<Box<T, A>>`. If `T` does not implement [`Unpin`], then
+    /// `*b` will be pinned in memory and can't be moved.
+    ///
+    /// This moves `b` into `Pin` without moving `*b` or allocating and copying any memory.
+    fn from(b: Box<T, A>) -> Self {
+        // SAFETY: The value wrapped inside a `Pin<Box<T, A>>` cannot be moved or replaced as long
+        // as `T` does not implement `Unpin`.
+        unsafe { Pin::new_unchecked(b) }
+    }
+}
+
+impl<T, A> InPlaceWrite<T> for Box<MaybeUninit<T>, A>
+where
+    A: Allocator + 'static,
+{
+    type Initialized = Box<T, A>;
+
+    fn write_init<E>(mut self, init: impl Init<T, E>) -> Result<Self::Initialized, E> {
+        let slot = self.as_mut_ptr();
+        // SAFETY: When init errors/panics, slot will get deallocated but not dropped,
+        // slot is valid.
+        unsafe { init.__init(slot)? };
+        // SAFETY: All fields have been initialized.
+        Ok(unsafe { Box::assume_init(self) })
+    }
+
+    fn write_pin_init<E>(mut self, init: impl PinInit<T, E>) -> Result<Pin<Self::Initialized>, E> {
+        let slot = self.as_mut_ptr();
+        // SAFETY: When init errors/panics, slot will get deallocated but not dropped,
+        // slot is valid and will not be moved, because we pin it later.
+        unsafe { init.__pinned_init(slot)? };
+        // SAFETY: All fields have been initialized.
+        Ok(unsafe { Box::assume_init(self) }.into())
+    }
+}
+
+impl<T, A> InPlaceInit<T> for Box<T, A>
+where
+    A: Allocator + 'static,
+{
+    type PinnedSelf = Pin<Self>;
+
+    #[inline]
+    fn try_pin_init<E>(init: impl PinInit<T, E>, flags: Flags) -> Result<Pin<Self>, E>
+    where
+        E: From<AllocError>,
+    {
+        Box::<_, A>::new_uninit(flags)?.write_pin_init(init)
+    }
+
+    #[inline]
+    fn try_init<E>(init: impl Init<T, E>, flags: Flags) -> Result<Self, E>
+    where
+        E: From<AllocError>,
+    {
+        Box::<_, A>::new_uninit(flags)?.write_init(init)
+    }
+}
+
+impl<T: 'static, A> ForeignOwnable for Box<T, A>
+where
+    A: Allocator,
+{
+    type Borrowed<'a> = &'a T;
+
+    fn into_foreign(self) -> *const core::ffi::c_void {
+        Box::into_raw(self) as _
+    }
+
+    unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self {
+        // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous
+        // call to `Self::into_foreign`.
+        unsafe { Box::from_raw(ptr as _) }
+    }
+
+    unsafe fn borrow<'a>(ptr: *const core::ffi::c_void) -> &'a T {
+        // SAFETY: The safety requirements of this method ensure that the object remains alive and
+        // immutable for the duration of 'a.
+        unsafe { &*ptr.cast() }
+    }
+}
+
+impl<T: 'static, A> ForeignOwnable for Pin<Box<T, A>>
+where
+    A: Allocator,
+{
+    type Borrowed<'a> = Pin<&'a T>;
+
+    fn into_foreign(self) -> *const core::ffi::c_void {
+        // SAFETY: We are still treating the box as pinned.
+        Box::into_raw(unsafe { Pin::into_inner_unchecked(self) }) as _
+    }
+
+    unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self {
+        // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous
+        // call to `Self::into_foreign`.
+        unsafe { Pin::new_unchecked(Box::from_raw(ptr as _)) }
+    }
+
+    unsafe fn borrow<'a>(ptr: *const core::ffi::c_void) -> Pin<&'a T> {
+        // SAFETY: The safety requirements for this function ensure that the object is still alive,
+        // so it is safe to dereference the raw pointer.
+        // The safety requirements of `from_foreign` also ensure that the object remains alive for
+        // the lifetime of the returned value.
+        let r = unsafe { &*ptr.cast() };
+
+        // SAFETY: This pointer originates from a `Pin<Box<T>>`.
+        unsafe { Pin::new_unchecked(r) }
+    }
+}
+
+impl<T, A> Deref for Box<T, A>
+where
+    T: ?Sized,
+    A: Allocator,
+{
+    type Target = T;
+
+    fn deref(&self) -> &T {
+        // SAFETY: `self.0` is always properly aligned, dereferenceable and points to an initialized
+        // instance of `T`.
+        unsafe { self.0.as_ref() }
+    }
+}
+
+impl<T, A> DerefMut for Box<T, A>
+where
+    T: ?Sized,
+    A: Allocator,
+{
+    fn deref_mut(&mut self) -> &mut T {
+        // SAFETY: `self.0` is always properly aligned, dereferenceable and points to an initialized
+        // instance of `T`.
+        unsafe { self.0.as_mut() }
+    }
+}
+
+impl<T, A> fmt::Debug for Box<T, A>
+where
+    T: ?Sized + fmt::Debug,
+    A: Allocator,
+{
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        fmt::Debug::fmt(&**self, f)
+    }
+}
+
+impl<T, A> Drop for Box<T, A>
+where
+    T: ?Sized,
+    A: Allocator,
+{
+    fn drop(&mut self) {
+        let layout = Layout::for_value::<T>(self);
+
+        // SAFETY: The pointer in `self.0` is guaranteed to be valid by the type invariant.
+        unsafe { core::ptr::drop_in_place::<T>(self.deref_mut()) };
+
+        // SAFETY:
+        // - `self.0` was previously allocated with `A`.
+        // - `layout` is equal to the `Layout´ `self.0` was allocated with.
+        unsafe { A::free(self.0.cast(), layout) };
+    }
+}
diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs
index 4571daec0961b..a9210634a8c30 100644
--- a/rust/kernel/prelude.rs
+++ b/rust/kernel/prelude.rs
@@ -14,7 +14,7 @@
 #[doc(no_inline)]
 pub use core::pin::Pin;
 
-pub use crate::alloc::{box_ext::BoxExt, flags::*, vec_ext::VecExt};
+pub use crate::alloc::{box_ext::BoxExt, flags::*, vec_ext::VecExt, KBox, KVBox, VBox};
 
 #[doc(no_inline)]
 pub use alloc::{boxed::Box, vec::Vec};

From 8373147ce4961665c5700016b1c76299e962d077 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:16 +0200
Subject: [PATCH 0360/1530] rust: treewide: switch to our kernel `Box` type

Now that we got the kernel `Box` type in place, convert all existing
`Box` users to make use of it.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-13-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 drivers/block/rnull.rs            |  4 +--
 rust/kernel/init.rs               | 51 ++++++++++++++++---------------
 rust/kernel/init/__internal.rs    |  2 +-
 rust/kernel/rbtree.rs             | 49 ++++++++++++++++-------------
 rust/kernel/sync/arc.rs           | 17 +++++------
 rust/kernel/sync/condvar.rs       |  4 +--
 rust/kernel/sync/lock/mutex.rs    |  2 +-
 rust/kernel/sync/lock/spinlock.rs |  2 +-
 rust/kernel/workqueue.rs          | 20 ++++++------
 rust/macros/lib.rs                |  6 ++--
 10 files changed, 81 insertions(+), 76 deletions(-)

diff --git a/drivers/block/rnull.rs b/drivers/block/rnull.rs
index b0227cf9ddd38..5de7223beb4d5 100644
--- a/drivers/block/rnull.rs
+++ b/drivers/block/rnull.rs
@@ -32,7 +32,7 @@ module! {
 }
 
 struct NullBlkModule {
-    _disk: Pin<Box<Mutex<GenDisk<NullBlkDevice>>>>,
+    _disk: Pin<KBox<Mutex<GenDisk<NullBlkDevice>>>>,
 }
 
 impl kernel::Module for NullBlkModule {
@@ -47,7 +47,7 @@ impl kernel::Module for NullBlkModule {
             .rotational(false)
             .build(format_args!("rnullb{}", 0), tagset)?;
 
-        let disk = Box::pin_init(new_mutex!(disk, "nullb:disk"), flags::GFP_KERNEL)?;
+        let disk = KBox::pin_init(new_mutex!(disk, "nullb:disk"), flags::GFP_KERNEL)?;
 
         Ok(Self { _disk: disk })
     }
diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs
index 25057cbed40b5..c889f2640b56a 100644
--- a/rust/kernel/init.rs
+++ b/rust/kernel/init.rs
@@ -13,7 +13,7 @@
 //! To initialize a `struct` with an in-place constructor you will need two things:
 //! - an in-place constructor,
 //! - a memory location that can hold your `struct` (this can be the [stack], an [`Arc<T>`],
-//!   [`UniqueArc<T>`], [`Box<T>`] or any other smart pointer that implements [`InPlaceInit`]).
+//!   [`UniqueArc<T>`], [`KBox<T>`] or any other smart pointer that implements [`InPlaceInit`]).
 //!
 //! To get an in-place constructor there are generally three options:
 //! - directly creating an in-place constructor using the [`pin_init!`] macro,
@@ -68,7 +68,7 @@
 //! #     a <- new_mutex!(42, "Foo::a"),
 //! #     b: 24,
 //! # });
-//! let foo: Result<Pin<Box<Foo>>> = Box::pin_init(foo, GFP_KERNEL);
+//! let foo: Result<Pin<KBox<Foo>>> = KBox::pin_init(foo, GFP_KERNEL);
 //! ```
 //!
 //! For more information see the [`pin_init!`] macro.
@@ -92,14 +92,14 @@
 //! struct DriverData {
 //!     #[pin]
 //!     status: Mutex<i32>,
-//!     buffer: Box<[u8; 1_000_000]>,
+//!     buffer: KBox<[u8; 1_000_000]>,
 //! }
 //!
 //! impl DriverData {
 //!     fn new() -> impl PinInit<Self, Error> {
 //!         try_pin_init!(Self {
 //!             status <- new_mutex!(0, "DriverData::status"),
-//!             buffer: Box::init(kernel::init::zeroed(), GFP_KERNEL)?,
+//!             buffer: KBox::init(kernel::init::zeroed(), GFP_KERNEL)?,
 //!         })
 //!     }
 //! }
@@ -211,7 +211,7 @@
 //! [`pin_init!`]: crate::pin_init!
 
 use crate::{
-    alloc::{box_ext::BoxExt, AllocError, Flags},
+    alloc::{box_ext::BoxExt, AllocError, Flags, KBox},
     error::{self, Error},
     sync::Arc,
     sync::UniqueArc,
@@ -298,7 +298,7 @@ macro_rules! stack_pin_init {
 /// struct Foo {
 ///     #[pin]
 ///     a: Mutex<usize>,
-///     b: Box<Bar>,
+///     b: KBox<Bar>,
 /// }
 ///
 /// struct Bar {
@@ -307,7 +307,7 @@ macro_rules! stack_pin_init {
 ///
 /// stack_try_pin_init!(let foo: Result<Pin<&mut Foo>, AllocError> = pin_init!(Foo {
 ///     a <- new_mutex!(42),
-///     b: Box::new(Bar {
+///     b: KBox::new(Bar {
 ///         x: 64,
 ///     }, GFP_KERNEL)?,
 /// }));
@@ -324,7 +324,7 @@ macro_rules! stack_pin_init {
 /// struct Foo {
 ///     #[pin]
 ///     a: Mutex<usize>,
-///     b: Box<Bar>,
+///     b: KBox<Bar>,
 /// }
 ///
 /// struct Bar {
@@ -333,7 +333,7 @@ macro_rules! stack_pin_init {
 ///
 /// stack_try_pin_init!(let foo: Pin<&mut Foo> =? pin_init!(Foo {
 ///     a <- new_mutex!(42),
-///     b: Box::new(Bar {
+///     b: KBox::new(Bar {
 ///         x: 64,
 ///     }, GFP_KERNEL)?,
 /// }));
@@ -391,7 +391,7 @@ macro_rules! stack_try_pin_init {
 ///     },
 /// });
 /// # initializer }
-/// # Box::pin_init(demo(), GFP_KERNEL).unwrap();
+/// # KBox::pin_init(demo(), GFP_KERNEL).unwrap();
 /// ```
 ///
 /// Arbitrary Rust expressions can be used to set the value of a variable.
@@ -460,7 +460,7 @@ macro_rules! stack_try_pin_init {
 /// #         })
 /// #     }
 /// # }
-/// let foo = Box::pin_init(Foo::new(), GFP_KERNEL);
+/// let foo = KBox::pin_init(Foo::new(), GFP_KERNEL);
 /// ```
 ///
 /// They can also easily embed it into their own `struct`s:
@@ -592,7 +592,7 @@ macro_rules! pin_init {
 /// use kernel::{init::{self, PinInit}, error::Error};
 /// #[pin_data]
 /// struct BigBuf {
-///     big: Box<[u8; 1024 * 1024 * 1024]>,
+///     big: KBox<[u8; 1024 * 1024 * 1024]>,
 ///     small: [u8; 1024 * 1024],
 ///     ptr: *mut u8,
 /// }
@@ -600,7 +600,7 @@ macro_rules! pin_init {
 /// impl BigBuf {
 ///     fn new() -> impl PinInit<Self, Error> {
 ///         try_pin_init!(Self {
-///             big: Box::init(init::zeroed(), GFP_KERNEL)?,
+///             big: KBox::init(init::zeroed(), GFP_KERNEL)?,
 ///             small: [0; 1024 * 1024],
 ///             ptr: core::ptr::null_mut(),
 ///         }? Error)
@@ -692,16 +692,16 @@ macro_rules! init {
 /// # Examples
 ///
 /// ```rust
-/// use kernel::{init::{PinInit, zeroed}, error::Error};
+/// use kernel::{alloc::KBox, init::{PinInit, zeroed}, error::Error};
 /// struct BigBuf {
-///     big: Box<[u8; 1024 * 1024 * 1024]>,
+///     big: KBox<[u8; 1024 * 1024 * 1024]>,
 ///     small: [u8; 1024 * 1024],
 /// }
 ///
 /// impl BigBuf {
 ///     fn new() -> impl Init<Self, Error> {
 ///         try_init!(Self {
-///             big: Box::init(zeroed(), GFP_KERNEL)?,
+///             big: KBox::init(zeroed(), GFP_KERNEL)?,
 ///             small: [0; 1024 * 1024],
 ///         }? Error)
 ///     }
@@ -812,8 +812,8 @@ macro_rules! assert_pinned {
 /// A pin-initializer for the type `T`.
 ///
 /// To use this initializer, you will need a suitable memory location that can hold a `T`. This can
-/// be [`Box<T>`], [`Arc<T>`], [`UniqueArc<T>`] or even the stack (see [`stack_pin_init!`]). Use the
-/// [`InPlaceInit::pin_init`] function of a smart pointer like [`Arc<T>`] on this.
+/// be [`KBox<T>`], [`Arc<T>`], [`UniqueArc<T>`] or even the stack (see [`stack_pin_init!`]). Use
+/// the [`InPlaceInit::pin_init`] function of a smart pointer like [`Arc<T>`] on this.
 ///
 /// Also see the [module description](self).
 ///
@@ -893,7 +893,7 @@ pub unsafe trait PinInit<T: ?Sized, E = Infallible>: Sized {
 }
 
 /// An initializer returned by [`PinInit::pin_chain`].
-pub struct ChainPinInit<I, F, T: ?Sized, E>(I, F, __internal::Invariant<(E, Box<T>)>);
+pub struct ChainPinInit<I, F, T: ?Sized, E>(I, F, __internal::Invariant<(E, KBox<T>)>);
 
 // SAFETY: The `__pinned_init` function is implemented such that it
 // - returns `Ok(())` on successful initialization,
@@ -919,8 +919,8 @@ where
 /// An initializer for `T`.
 ///
 /// To use this initializer, you will need a suitable memory location that can hold a `T`. This can
-/// be [`Box<T>`], [`Arc<T>`], [`UniqueArc<T>`] or even the stack (see [`stack_pin_init!`]). Use the
-/// [`InPlaceInit::init`] function of a smart pointer like [`Arc<T>`] on this. Because
+/// be [`KBox<T>`], [`Arc<T>`], [`UniqueArc<T>`] or even the stack (see [`stack_pin_init!`]). Use
+/// the [`InPlaceInit::init`] function of a smart pointer like [`Arc<T>`] on this. Because
 /// [`PinInit<T, E>`] is a super trait, you can use every function that takes it as well.
 ///
 /// Also see the [module description](self).
@@ -992,7 +992,7 @@ pub unsafe trait Init<T: ?Sized, E = Infallible>: PinInit<T, E> {
 }
 
 /// An initializer returned by [`Init::chain`].
-pub struct ChainInit<I, F, T: ?Sized, E>(I, F, __internal::Invariant<(E, Box<T>)>);
+pub struct ChainInit<I, F, T: ?Sized, E>(I, F, __internal::Invariant<(E, KBox<T>)>);
 
 // SAFETY: The `__init` function is implemented such that it
 // - returns `Ok(())` on successful initialization,
@@ -1076,8 +1076,9 @@ pub fn uninit<T, E>() -> impl Init<MaybeUninit<T>, E> {
 /// # Examples
 ///
 /// ```rust
-/// use kernel::{error::Error, init::init_array_from_fn};
-/// let array: Box<[usize; 1_000]> = Box::init::<Error>(init_array_from_fn(|i| i), GFP_KERNEL).unwrap();
+/// use kernel::{alloc::KBox, error::Error, init::init_array_from_fn};
+/// let array: KBox<[usize; 1_000]> =
+///     KBox::init::<Error>(init_array_from_fn(|i| i), GFP_KERNEL).unwrap();
 /// assert_eq!(array.len(), 1_000);
 /// ```
 pub fn init_array_from_fn<I, const N: usize, T, E>(
@@ -1453,7 +1454,7 @@ impl_zeroable! {
     //
     // In this case we are allowed to use `T: ?Sized`, since all zeros is the `None` variant.
     {<T: ?Sized>} Option<NonNull<T>>,
-    {<T: ?Sized>} Option<Box<T>>,
+    {<T: ?Sized>} Option<KBox<T>>,
 
     // SAFETY: `null` pointer is valid.
     //
diff --git a/rust/kernel/init/__internal.rs b/rust/kernel/init/__internal.rs
index 44431fba7aabf..74329cc3262c0 100644
--- a/rust/kernel/init/__internal.rs
+++ b/rust/kernel/init/__internal.rs
@@ -105,7 +105,7 @@ pub unsafe trait InitData: Copy {
     }
 }
 
-pub struct AllData<T: ?Sized>(PhantomData<fn(Box<T>) -> Box<T>>);
+pub struct AllData<T: ?Sized>(PhantomData<fn(KBox<T>) -> KBox<T>>);
 
 impl<T: ?Sized> Clone for AllData<T> {
     fn clone(&self) -> Self {
diff --git a/rust/kernel/rbtree.rs b/rust/kernel/rbtree.rs
index d03e4aa1f4812..cb4415a122582 100644
--- a/rust/kernel/rbtree.rs
+++ b/rust/kernel/rbtree.rs
@@ -7,7 +7,6 @@
 //! Reference: <https://docs.kernel.org/core-api/rbtree.html>
 
 use crate::{alloc::Flags, bindings, container_of, error::Result, prelude::*};
-use alloc::boxed::Box;
 use core::{
     cmp::{Ord, Ordering},
     marker::PhantomData,
@@ -497,7 +496,7 @@ impl<K, V> Drop for RBTree<K, V> {
             // but it is not observable. The loop invariant is still maintained.
 
             // SAFETY: `this` is valid per the loop invariant.
-            unsafe { drop(Box::from_raw(this.cast_mut())) };
+            unsafe { drop(KBox::from_raw(this.cast_mut())) };
         }
     }
 }
@@ -764,7 +763,7 @@ impl<'a, K, V> Cursor<'a, K, V> {
         // point to the links field of `Node<K, V>` objects.
         let this = unsafe { container_of!(self.current.as_ptr(), Node<K, V>, links) }.cast_mut();
         // SAFETY: `this` is valid by the type invariants as described above.
-        let node = unsafe { Box::from_raw(this) };
+        let node = unsafe { KBox::from_raw(this) };
         let node = RBTreeNode { node };
         // SAFETY: The reference to the tree used to create the cursor outlives the cursor, so
         // the tree cannot change. By the tree invariant, all nodes are valid.
@@ -809,7 +808,7 @@ impl<'a, K, V> Cursor<'a, K, V> {
             // point to the links field of `Node<K, V>` objects.
             let this = unsafe { container_of!(neighbor, Node<K, V>, links) }.cast_mut();
             // SAFETY: `this` is valid by the type invariants as described above.
-            let node = unsafe { Box::from_raw(this) };
+            let node = unsafe { KBox::from_raw(this) };
             return Some(RBTreeNode { node });
         }
         None
@@ -1038,7 +1037,7 @@ impl<K, V> Iterator for IterRaw<K, V> {
 /// It contains the memory needed to hold a node that can be inserted into a red-black tree. One
 /// can be obtained by directly allocating it ([`RBTreeNodeReservation::new`]).
 pub struct RBTreeNodeReservation<K, V> {
-    node: Box<MaybeUninit<Node<K, V>>>,
+    node: KBox<MaybeUninit<Node<K, V>>>,
 }
 
 impl<K, V> RBTreeNodeReservation<K, V> {
@@ -1046,7 +1045,7 @@ impl<K, V> RBTreeNodeReservation<K, V> {
     /// call to [`RBTree::insert`].
     pub fn new(flags: Flags) -> Result<RBTreeNodeReservation<K, V>> {
         Ok(RBTreeNodeReservation {
-            node: <Box<_> as BoxExt<_>>::new_uninit(flags)?,
+            node: KBox::new_uninit(flags)?,
         })
     }
 }
@@ -1062,14 +1061,15 @@ impl<K, V> RBTreeNodeReservation<K, V> {
     /// Initialises a node reservation.
     ///
     /// It then becomes an [`RBTreeNode`] that can be inserted into a tree.
-    pub fn into_node(mut self, key: K, value: V) -> RBTreeNode<K, V> {
-        self.node.write(Node {
-            key,
-            value,
-            links: bindings::rb_node::default(),
-        });
-        // SAFETY: We just wrote to it.
-        let node = unsafe { self.node.assume_init() };
+    pub fn into_node(self, key: K, value: V) -> RBTreeNode<K, V> {
+        let node = KBox::write(
+            self.node,
+            Node {
+                key,
+                value,
+                links: bindings::rb_node::default(),
+            },
+        );
         RBTreeNode { node }
     }
 }
@@ -1079,7 +1079,7 @@ impl<K, V> RBTreeNodeReservation<K, V> {
 /// The node is fully initialised (with key and value) and can be inserted into a tree without any
 /// extra allocations or failure paths.
 pub struct RBTreeNode<K, V> {
-    node: Box<Node<K, V>>,
+    node: KBox<Node<K, V>>,
 }
 
 impl<K, V> RBTreeNode<K, V> {
@@ -1091,7 +1091,9 @@ impl<K, V> RBTreeNode<K, V> {
 
     /// Get the key and value from inside the node.
     pub fn to_key_value(self) -> (K, V) {
-        (self.node.key, self.node.value)
+        let node = KBox::into_inner(self.node);
+
+        (node.key, node.value)
     }
 }
 
@@ -1113,7 +1115,7 @@ impl<K, V> RBTreeNode<K, V> {
     /// may be freed (but only for the key/value; memory for the node itself is kept for reuse).
     pub fn into_reservation(self) -> RBTreeNodeReservation<K, V> {
         RBTreeNodeReservation {
-            node: Box::drop_contents(self.node),
+            node: KBox::drop_contents(self.node),
         }
     }
 }
@@ -1164,7 +1166,7 @@ impl<'a, K, V> RawVacantEntry<'a, K, V> {
     /// The `node` must have a key such that inserting it here does not break the ordering of this
     /// [`RBTree`].
     fn insert(self, node: RBTreeNode<K, V>) -> &'a mut V {
-        let node = Box::into_raw(node.node);
+        let node = KBox::into_raw(node.node);
 
         // SAFETY: `node` is valid at least until we call `Box::from_raw`, which only happens when
         // the node is removed or replaced.
@@ -1238,21 +1240,24 @@ impl<'a, K, V> OccupiedEntry<'a, K, V> {
             // SAFETY: The node was a node in the tree, but we removed it, so we can convert it
             // back into a box.
             node: unsafe {
-                Box::from_raw(container_of!(self.node_links, Node<K, V>, links).cast_mut())
+                KBox::from_raw(container_of!(self.node_links, Node<K, V>, links).cast_mut())
             },
         }
     }
 
     /// Takes the value of the entry out of the map, and returns it.
     pub fn remove(self) -> V {
-        self.remove_node().node.value
+        let rb_node = self.remove_node();
+        let node = KBox::into_inner(rb_node.node);
+
+        node.value
     }
 
     /// Swap the current node for the provided node.
     ///
     /// The key of both nodes must be equal.
     fn replace(self, node: RBTreeNode<K, V>) -> RBTreeNode<K, V> {
-        let node = Box::into_raw(node.node);
+        let node = KBox::into_raw(node.node);
 
         // SAFETY: `node` is valid at least until we call `Box::from_raw`, which only happens when
         // the node is removed or replaced.
@@ -1268,7 +1273,7 @@ impl<'a, K, V> OccupiedEntry<'a, K, V> {
         // - `self.node_ptr` produces a valid pointer to a node in the tree.
         // - Now that we removed this entry from the tree, we can convert the node to a box.
         let old_node =
-            unsafe { Box::from_raw(container_of!(self.node_links, Node<K, V>, links).cast_mut()) };
+            unsafe { KBox::from_raw(container_of!(self.node_links, Node<K, V>, links).cast_mut()) };
 
         RBTreeNode { node: old_node }
     }
diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs
index 9325cc5a16a4c..db9da352d588f 100644
--- a/rust/kernel/sync/arc.rs
+++ b/rust/kernel/sync/arc.rs
@@ -17,13 +17,12 @@
 //! [`Arc`]: https://doc.rust-lang.org/std/sync/struct.Arc.html
 
 use crate::{
-    alloc::{box_ext::BoxExt, AllocError, Flags},
+    alloc::{AllocError, Flags, KBox},
     bindings,
     init::{self, InPlaceInit, Init, PinInit},
     try_init,
     types::{ForeignOwnable, Opaque},
 };
-use alloc::boxed::Box;
 use core::{
     alloc::Layout,
     fmt,
@@ -201,11 +200,11 @@ impl<T> Arc<T> {
             data: contents,
         };
 
-        let inner = <Box<_> as BoxExt<_>>::new(value, flags)?;
+        let inner = KBox::new(value, flags)?;
 
         // SAFETY: We just created `inner` with a reference count of 1, which is owned by the new
         // `Arc` object.
-        Ok(unsafe { Self::from_inner(Box::leak(inner).into()) })
+        Ok(unsafe { Self::from_inner(KBox::leak(inner).into()) })
     }
 }
 
@@ -398,8 +397,8 @@ impl<T: ?Sized> Drop for Arc<T> {
         if is_zero {
             // The count reached zero, we must free the memory.
             //
-            // SAFETY: The pointer was initialised from the result of `Box::leak`.
-            unsafe { drop(Box::from_raw(self.ptr.as_ptr())) };
+            // SAFETY: The pointer was initialised from the result of `KBox::leak`.
+            unsafe { drop(KBox::from_raw(self.ptr.as_ptr())) };
         }
     }
 }
@@ -641,7 +640,7 @@ impl<T> UniqueArc<T> {
     /// Tries to allocate a new [`UniqueArc`] instance whose contents are not initialised yet.
     pub fn new_uninit(flags: Flags) -> Result<UniqueArc<MaybeUninit<T>>, AllocError> {
         // INVARIANT: The refcount is initialised to a non-zero value.
-        let inner = Box::try_init::<AllocError>(
+        let inner = KBox::try_init::<AllocError>(
             try_init!(ArcInner {
                 // SAFETY: There are no safety requirements for this FFI call.
                 refcount: Opaque::new(unsafe { bindings::REFCOUNT_INIT(1) }),
@@ -651,8 +650,8 @@ impl<T> UniqueArc<T> {
         )?;
         Ok(UniqueArc {
             // INVARIANT: The newly-created object has a refcount of 1.
-            // SAFETY: The pointer from the `Box` is valid.
-            inner: unsafe { Arc::from_inner(Box::leak(inner).into()) },
+            // SAFETY: The pointer from the `KBox` is valid.
+            inner: unsafe { Arc::from_inner(KBox::leak(inner).into()) },
         })
     }
 }
diff --git a/rust/kernel/sync/condvar.rs b/rust/kernel/sync/condvar.rs
index dec2e5ffc9193..a1a29c0bdb3aa 100644
--- a/rust/kernel/sync/condvar.rs
+++ b/rust/kernel/sync/condvar.rs
@@ -70,8 +70,8 @@ pub use new_condvar;
 /// }
 ///
 /// /// Allocates a new boxed `Example`.
-/// fn new_example() -> Result<Pin<Box<Example>>> {
-///     Box::pin_init(pin_init!(Example {
+/// fn new_example() -> Result<Pin<KBox<Example>>> {
+///     KBox::pin_init(pin_init!(Example {
 ///         value <- new_mutex!(0),
 ///         value_changed <- new_condvar!(),
 ///     }), GFP_KERNEL)
diff --git a/rust/kernel/sync/lock/mutex.rs b/rust/kernel/sync/lock/mutex.rs
index c4f3b6cbfe48d..9ce43ccb45158 100644
--- a/rust/kernel/sync/lock/mutex.rs
+++ b/rust/kernel/sync/lock/mutex.rs
@@ -58,7 +58,7 @@ pub use new_mutex;
 /// }
 ///
 /// // Allocate a boxed `Example`.
-/// let e = Box::pin_init(Example::new(), GFP_KERNEL)?;
+/// let e = KBox::pin_init(Example::new(), GFP_KERNEL)?;
 /// assert_eq!(e.c, 10);
 /// assert_eq!(e.d.lock().a, 20);
 /// assert_eq!(e.d.lock().b, 30);
diff --git a/rust/kernel/sync/lock/spinlock.rs b/rust/kernel/sync/lock/spinlock.rs
index c900ae23db76f..040dc16975a68 100644
--- a/rust/kernel/sync/lock/spinlock.rs
+++ b/rust/kernel/sync/lock/spinlock.rs
@@ -56,7 +56,7 @@ pub use new_spinlock;
 /// }
 ///
 /// // Allocate a boxed `Example`.
-/// let e = Box::pin_init(Example::new(), GFP_KERNEL)?;
+/// let e = KBox::pin_init(Example::new(), GFP_KERNEL)?;
 /// assert_eq!(e.c, 10);
 /// assert_eq!(e.d.lock().a, 20);
 /// assert_eq!(e.d.lock().b, 30);
diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs
index 10d2bc62e2cff..4d1d2062f6eba 100644
--- a/rust/kernel/workqueue.rs
+++ b/rust/kernel/workqueue.rs
@@ -216,7 +216,7 @@ impl Queue {
             func: Some(func),
         });
 
-        self.enqueue(Box::pin_init(init, flags).map_err(|_| AllocError)?);
+        self.enqueue(KBox::pin_init(init, flags).map_err(|_| AllocError)?);
         Ok(())
     }
 }
@@ -239,9 +239,9 @@ impl<T> ClosureWork<T> {
 }
 
 impl<T: FnOnce()> WorkItem for ClosureWork<T> {
-    type Pointer = Pin<Box<Self>>;
+    type Pointer = Pin<KBox<Self>>;
 
-    fn run(mut this: Pin<Box<Self>>) {
+    fn run(mut this: Pin<KBox<Self>>) {
         if let Some(func) = this.as_mut().project().take() {
             (func)()
         }
@@ -297,7 +297,7 @@ pub unsafe trait RawWorkItem<const ID: u64> {
 
 /// Defines the method that should be called directly when a work item is executed.
 ///
-/// This trait is implemented by `Pin<Box<T>>` and [`Arc<T>`], and is mainly intended to be
+/// This trait is implemented by `Pin<KBox<T>>` and [`Arc<T>`], and is mainly intended to be
 /// implemented for smart pointer types. For your own structs, you would implement [`WorkItem`]
 /// instead. The [`run`] method on this trait will usually just perform the appropriate
 /// `container_of` translation and then call into the [`run`][WorkItem::run] method from the
@@ -329,7 +329,7 @@ pub unsafe trait WorkItemPointer<const ID: u64>: RawWorkItem<ID> {
 /// This trait is used when the `work_struct` field is defined using the [`Work`] helper.
 pub trait WorkItem<const ID: u64 = 0> {
     /// The pointer type that this struct is wrapped in. This will typically be `Arc<Self>` or
-    /// `Pin<Box<Self>>`.
+    /// `Pin<KBox<Self>>`.
     type Pointer: WorkItemPointer<ID>;
 
     /// The method that should be called when this work item is executed.
@@ -567,7 +567,7 @@ where
 }
 
 // SAFETY: TODO.
-unsafe impl<T, const ID: u64> WorkItemPointer<ID> for Pin<Box<T>>
+unsafe impl<T, const ID: u64> WorkItemPointer<ID> for Pin<KBox<T>>
 where
     T: WorkItem<ID, Pointer = Self>,
     T: HasWork<T, ID>,
@@ -578,7 +578,7 @@ where
         // SAFETY: This computes the pointer that `__enqueue` got from `Arc::into_raw`.
         let ptr = unsafe { T::work_container_of(ptr) };
         // SAFETY: This pointer comes from `Arc::into_raw` and we've been given back ownership.
-        let boxed = unsafe { Box::from_raw(ptr) };
+        let boxed = unsafe { KBox::from_raw(ptr) };
         // SAFETY: The box was already pinned when it was enqueued.
         let pinned = unsafe { Pin::new_unchecked(boxed) };
 
@@ -587,7 +587,7 @@ where
 }
 
 // SAFETY: TODO.
-unsafe impl<T, const ID: u64> RawWorkItem<ID> for Pin<Box<T>>
+unsafe impl<T, const ID: u64> RawWorkItem<ID> for Pin<KBox<T>>
 where
     T: WorkItem<ID, Pointer = Self>,
     T: HasWork<T, ID>,
@@ -601,9 +601,9 @@ where
         // SAFETY: We're not going to move `self` or any of its fields, so its okay to temporarily
         // remove the `Pin` wrapper.
         let boxed = unsafe { Pin::into_inner_unchecked(self) };
-        let ptr = Box::into_raw(boxed);
+        let ptr = KBox::into_raw(boxed);
 
-        // SAFETY: Pointers into a `Box` point at a valid value.
+        // SAFETY: Pointers into a `KBox` point at a valid value.
         let work_ptr = unsafe { T::raw_get_work(ptr) };
         // SAFETY: `raw_get_work` returns a pointer to a valid value.
         let work_ptr = unsafe { Work::raw_get(work_ptr) };
diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
index a626b1145e5c4..ab93111a048c9 100644
--- a/rust/macros/lib.rs
+++ b/rust/macros/lib.rs
@@ -243,7 +243,7 @@ pub fn concat_idents(ts: TokenStream) -> TokenStream {
 /// struct DriverData {
 ///     #[pin]
 ///     queue: Mutex<Vec<Command>>,
-///     buf: Box<[u8; 1024 * 1024]>,
+///     buf: KBox<[u8; 1024 * 1024]>,
 /// }
 /// ```
 ///
@@ -252,7 +252,7 @@ pub fn concat_idents(ts: TokenStream) -> TokenStream {
 /// struct DriverData {
 ///     #[pin]
 ///     queue: Mutex<Vec<Command>>,
-///     buf: Box<[u8; 1024 * 1024]>,
+///     buf: KBox<[u8; 1024 * 1024]>,
 ///     raw_info: *mut Info,
 /// }
 ///
@@ -282,7 +282,7 @@ pub fn pin_data(inner: TokenStream, item: TokenStream) -> TokenStream {
 /// struct DriverData {
 ///     #[pin]
 ///     queue: Mutex<Vec<Command>>,
-///     buf: Box<[u8; 1024 * 1024]>,
+///     buf: KBox<[u8; 1024 * 1024]>,
 ///     raw_info: *mut Info,
 /// }
 ///

From e8c6ccdbcaaf31f26c0fffd4073edd0b0147cdc6 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:17 +0200
Subject: [PATCH 0361/1530] rust: alloc: remove extension of std's `Box`

Now that all existing `Box` users were moved to the kernel `Box` type,
remove the `BoxExt` extension and all other related extensions.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-14-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc.rs         |  1 -
 rust/kernel/alloc/box_ext.rs | 89 ------------------------------------
 rust/kernel/init.rs          | 46 +------------------
 rust/kernel/lib.rs           |  1 -
 rust/kernel/prelude.rs       |  4 +-
 rust/kernel/types.rs         | 50 --------------------
 6 files changed, 3 insertions(+), 188 deletions(-)
 delete mode 100644 rust/kernel/alloc/box_ext.rs

diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index 3628e16240a69..94f4de5e0cdc4 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -4,7 +4,6 @@
 
 #[cfg(not(any(test, testlib)))]
 pub mod allocator;
-pub mod box_ext;
 pub mod kbox;
 pub mod vec_ext;
 
diff --git a/rust/kernel/alloc/box_ext.rs b/rust/kernel/alloc/box_ext.rs
deleted file mode 100644
index 7009ad78d4e08..0000000000000
--- a/rust/kernel/alloc/box_ext.rs
+++ /dev/null
@@ -1,89 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-//! Extensions to [`Box`] for fallible allocations.
-
-use super::{AllocError, Flags};
-use alloc::boxed::Box;
-use core::{mem::MaybeUninit, ptr, result::Result};
-
-/// Extensions to [`Box`].
-pub trait BoxExt<T>: Sized {
-    /// Allocates a new box.
-    ///
-    /// The allocation may fail, in which case an error is returned.
-    fn new(x: T, flags: Flags) -> Result<Self, AllocError>;
-
-    /// Allocates a new uninitialised box.
-    ///
-    /// The allocation may fail, in which case an error is returned.
-    fn new_uninit(flags: Flags) -> Result<Box<MaybeUninit<T>>, AllocError>;
-
-    /// Drops the contents, but keeps the allocation.
-    ///
-    /// # Examples
-    ///
-    /// ```
-    /// use kernel::alloc::{flags, box_ext::BoxExt};
-    /// let value = Box::new([0; 32], flags::GFP_KERNEL)?;
-    /// assert_eq!(*value, [0; 32]);
-    /// let mut value = Box::drop_contents(value);
-    /// // Now we can re-use `value`:
-    /// value.write([1; 32]);
-    /// // SAFETY: We just wrote to it.
-    /// let value = unsafe { value.assume_init() };
-    /// assert_eq!(*value, [1; 32]);
-    /// # Ok::<(), Error>(())
-    /// ```
-    fn drop_contents(this: Self) -> Box<MaybeUninit<T>>;
-}
-
-impl<T> BoxExt<T> for Box<T> {
-    fn new(x: T, flags: Flags) -> Result<Self, AllocError> {
-        let mut b = <Self as BoxExt<_>>::new_uninit(flags)?;
-        b.write(x);
-        // SAFETY: We just wrote to it.
-        Ok(unsafe { b.assume_init() })
-    }
-
-    #[cfg(any(test, testlib))]
-    fn new_uninit(_flags: Flags) -> Result<Box<MaybeUninit<T>>, AllocError> {
-        Ok(Box::new_uninit())
-    }
-
-    #[cfg(not(any(test, testlib)))]
-    fn new_uninit(flags: Flags) -> Result<Box<MaybeUninit<T>>, AllocError> {
-        let ptr = if core::mem::size_of::<MaybeUninit<T>>() == 0 {
-            core::ptr::NonNull::<_>::dangling().as_ptr()
-        } else {
-            let layout = core::alloc::Layout::new::<MaybeUninit<T>>();
-
-            // SAFETY: Memory is being allocated (first arg is null). The only other source of
-            // safety issues is sleeping on atomic context, which is addressed by klint. Lastly,
-            // the type is not a SZT (checked above).
-            let ptr =
-                unsafe { super::allocator::krealloc_aligned(core::ptr::null_mut(), layout, flags) };
-            if ptr.is_null() {
-                return Err(AllocError);
-            }
-
-            ptr.cast::<MaybeUninit<T>>()
-        };
-
-        // SAFETY: For non-zero-sized types, we allocate above using the global allocator. For
-        // zero-sized types, we use `NonNull::dangling`.
-        Ok(unsafe { Box::from_raw(ptr) })
-    }
-
-    fn drop_contents(this: Self) -> Box<MaybeUninit<T>> {
-        let ptr = Box::into_raw(this);
-        // SAFETY: `ptr` is valid, because it came from `Box::into_raw`.
-        unsafe { ptr::drop_in_place(ptr) };
-
-        // CAST: `MaybeUninit<T>` is a transparent wrapper of `T`.
-        let ptr = ptr.cast::<MaybeUninit<T>>();
-
-        // SAFETY: `ptr` is valid for writes, because it came from `Box::into_raw` and it is valid for
-        // reads, since the pointer came from `Box::into_raw` and the type is `MaybeUninit<T>`.
-        unsafe { Box::from_raw(ptr) }
-    }
-}
diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs
index c889f2640b56a..c9919ba0b6836 100644
--- a/rust/kernel/init.rs
+++ b/rust/kernel/init.rs
@@ -211,13 +211,12 @@
 //! [`pin_init!`]: crate::pin_init!
 
 use crate::{
-    alloc::{box_ext::BoxExt, AllocError, Flags, KBox},
+    alloc::{AllocError, Flags, KBox},
     error::{self, Error},
     sync::Arc,
     sync::UniqueArc,
     types::{Opaque, ScopeGuard},
 };
-use alloc::boxed::Box;
 use core::{
     cell::UnsafeCell,
     convert::Infallible,
@@ -588,7 +587,6 @@ macro_rules! pin_init {
 /// # Examples
 ///
 /// ```rust
-/// # #![feature(new_uninit)]
 /// use kernel::{init::{self, PinInit}, error::Error};
 /// #[pin_data]
 /// struct BigBuf {
@@ -1245,26 +1243,6 @@ impl<T> InPlaceInit<T> for Arc<T> {
     }
 }
 
-impl<T> InPlaceInit<T> for Box<T> {
-    type PinnedSelf = Pin<Self>;
-
-    #[inline]
-    fn try_pin_init<E>(init: impl PinInit<T, E>, flags: Flags) -> Result<Self::PinnedSelf, E>
-    where
-        E: From<AllocError>,
-    {
-        <Box<_> as BoxExt<_>>::new_uninit(flags)?.write_pin_init(init)
-    }
-
-    #[inline]
-    fn try_init<E>(init: impl Init<T, E>, flags: Flags) -> Result<Self, E>
-    where
-        E: From<AllocError>,
-    {
-        <Box<_> as BoxExt<_>>::new_uninit(flags)?.write_init(init)
-    }
-}
-
 impl<T> InPlaceInit<T> for UniqueArc<T> {
     type PinnedSelf = Pin<Self>;
 
@@ -1301,28 +1279,6 @@ pub trait InPlaceWrite<T> {
     fn write_pin_init<E>(self, init: impl PinInit<T, E>) -> Result<Pin<Self::Initialized>, E>;
 }
 
-impl<T> InPlaceWrite<T> for Box<MaybeUninit<T>> {
-    type Initialized = Box<T>;
-
-    fn write_init<E>(mut self, init: impl Init<T, E>) -> Result<Self::Initialized, E> {
-        let slot = self.as_mut_ptr();
-        // SAFETY: When init errors/panics, slot will get deallocated but not dropped,
-        // slot is valid.
-        unsafe { init.__init(slot)? };
-        // SAFETY: All fields have been initialized.
-        Ok(unsafe { self.assume_init() })
-    }
-
-    fn write_pin_init<E>(mut self, init: impl PinInit<T, E>) -> Result<Pin<Self::Initialized>, E> {
-        let slot = self.as_mut_ptr();
-        // SAFETY: When init errors/panics, slot will get deallocated but not dropped,
-        // slot is valid and will not be moved, because we pin it later.
-        unsafe { init.__pinned_init(slot)? };
-        // SAFETY: All fields have been initialized.
-        Ok(unsafe { self.assume_init() }.into())
-    }
-}
-
 impl<T> InPlaceWrite<T> for UniqueArc<MaybeUninit<T>> {
     type Initialized = UniqueArc<T>;
 
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index dc37aef6a0085..34e9151db58d2 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -16,7 +16,6 @@
 #![feature(coerce_unsized)]
 #![feature(dispatch_from_dyn)]
 #![feature(lint_reasons)]
-#![feature(new_uninit)]
 #![feature(unsize)]
 
 // Ensure conditional compilation based on the kernel configuration works;
diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs
index a9210634a8c30..c1f8e5c832e2d 100644
--- a/rust/kernel/prelude.rs
+++ b/rust/kernel/prelude.rs
@@ -14,10 +14,10 @@
 #[doc(no_inline)]
 pub use core::pin::Pin;
 
-pub use crate::alloc::{box_ext::BoxExt, flags::*, vec_ext::VecExt, KBox, KVBox, VBox};
+pub use crate::alloc::{flags::*, vec_ext::VecExt, KBox, KVBox, VBox};
 
 #[doc(no_inline)]
-pub use alloc::{boxed::Box, vec::Vec};
+pub use alloc::vec::Vec;
 
 #[doc(no_inline)]
 pub use macros::{module, pin_data, pinned_drop, vtable, Zeroable};
diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index 085e8076f0788..34f1b31753df1 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -3,13 +3,11 @@
 //! Kernel types.
 
 use crate::init::{self, PinInit};
-use alloc::boxed::Box;
 use core::{
     cell::UnsafeCell,
     marker::{PhantomData, PhantomPinned},
     mem::{ManuallyDrop, MaybeUninit},
     ops::{Deref, DerefMut},
-    pin::Pin,
     ptr::NonNull,
 };
 
@@ -71,54 +69,6 @@ pub trait ForeignOwnable: Sized {
     }
 }
 
-impl<T: 'static> ForeignOwnable for Box<T> {
-    type Borrowed<'a> = &'a T;
-
-    fn into_foreign(self) -> *const core::ffi::c_void {
-        Box::into_raw(self) as _
-    }
-
-    unsafe fn borrow<'a>(ptr: *const core::ffi::c_void) -> &'a T {
-        // SAFETY: The safety requirements for this function ensure that the object is still alive,
-        // so it is safe to dereference the raw pointer.
-        // The safety requirements of `from_foreign` also ensure that the object remains alive for
-        // the lifetime of the returned value.
-        unsafe { &*ptr.cast() }
-    }
-
-    unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self {
-        // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous
-        // call to `Self::into_foreign`.
-        unsafe { Box::from_raw(ptr as _) }
-    }
-}
-
-impl<T: 'static> ForeignOwnable for Pin<Box<T>> {
-    type Borrowed<'a> = Pin<&'a T>;
-
-    fn into_foreign(self) -> *const core::ffi::c_void {
-        // SAFETY: We are still treating the box as pinned.
-        Box::into_raw(unsafe { Pin::into_inner_unchecked(self) }) as _
-    }
-
-    unsafe fn borrow<'a>(ptr: *const core::ffi::c_void) -> Pin<&'a T> {
-        // SAFETY: The safety requirements for this function ensure that the object is still alive,
-        // so it is safe to dereference the raw pointer.
-        // The safety requirements of `from_foreign` also ensure that the object remains alive for
-        // the lifetime of the returned value.
-        let r = unsafe { &*ptr.cast() };
-
-        // SAFETY: This pointer originates from a `Pin<Box<T>>`.
-        unsafe { Pin::new_unchecked(r) }
-    }
-
-    unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self {
-        // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous
-        // call to `Self::into_foreign`.
-        unsafe { Pin::new_unchecked(Box::from_raw(ptr as _)) }
-    }
-}
-
 impl ForeignOwnable for () {
     type Borrowed<'a> = ();
 

From e1044c2238f54ae5bd902cac6d12e48835df418b Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:18 +0200
Subject: [PATCH 0362/1530] rust: alloc: add `Box` to prelude

Now that we removed `BoxExt` and the corresponding includes in
prelude.rs, add the new kernel `Box` type instead.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-15-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/prelude.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs
index c1f8e5c832e2d..d5f2fe42d0932 100644
--- a/rust/kernel/prelude.rs
+++ b/rust/kernel/prelude.rs
@@ -14,7 +14,7 @@
 #[doc(no_inline)]
 pub use core::pin::Pin;
 
-pub use crate::alloc::{flags::*, vec_ext::VecExt, KBox, KVBox, VBox};
+pub use crate::alloc::{flags::*, vec_ext::VecExt, Box, KBox, KVBox, VBox};
 
 #[doc(no_inline)]
 pub use alloc::vec::Vec;

From 9e7bbfa182767f638ba61dba3518ff78da9f31ff Mon Sep 17 00:00:00 2001
From: Benno Lossin <benno.lossin@proton.me>
Date: Fri, 4 Oct 2024 17:41:19 +0200
Subject: [PATCH 0363/1530] rust: alloc: introduce `ArrayLayout`

When allocating memory for arrays using allocators, the `Layout::array`
function is typically used. It returns a result, since the given size
might be too big. However, `Vec` and its iterators store their allocated
capacity and thus they already did check that the size is not too big.

The `ArrayLayout` type provides this exact behavior, as it can be
infallibly converted into a `Layout`. Instead of a `usize` capacity,
`Vec` and other similar array-storing types can use `ArrayLayout`
instead.

Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Benno Lossin <benno.lossin@proton.me>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-16-dakr@kernel.org
[ Formatted a few comments. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc.rs        |  1 +
 rust/kernel/alloc/layout.rs | 91 +++++++++++++++++++++++++++++++++++++
 2 files changed, 92 insertions(+)
 create mode 100644 rust/kernel/alloc/layout.rs

diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index 94f4de5e0cdc4..c679d93b0523a 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -5,6 +5,7 @@
 #[cfg(not(any(test, testlib)))]
 pub mod allocator;
 pub mod kbox;
+pub mod layout;
 pub mod vec_ext;
 
 #[cfg(any(test, testlib))]
diff --git a/rust/kernel/alloc/layout.rs b/rust/kernel/alloc/layout.rs
new file mode 100644
index 0000000000000..7e0c2f46157b7
--- /dev/null
+++ b/rust/kernel/alloc/layout.rs
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Memory layout.
+//!
+//! Custom layout types extending or improving [`Layout`].
+
+use core::{alloc::Layout, marker::PhantomData};
+
+/// Error when constructing an [`ArrayLayout`].
+pub struct LayoutError;
+
+/// A layout for an array `[T; n]`.
+///
+/// # Invariants
+///
+/// - `len * size_of::<T>() <= isize::MAX`.
+pub struct ArrayLayout<T> {
+    len: usize,
+    _phantom: PhantomData<fn() -> T>,
+}
+
+impl<T> Clone for ArrayLayout<T> {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+impl<T> Copy for ArrayLayout<T> {}
+
+const ISIZE_MAX: usize = isize::MAX as usize;
+
+impl<T> ArrayLayout<T> {
+    /// Creates a new layout for `[T; 0]`.
+    pub const fn empty() -> Self {
+        // INVARIANT: `0 * size_of::<T>() <= isize::MAX`.
+        Self {
+            len: 0,
+            _phantom: PhantomData,
+        }
+    }
+
+    /// Creates a new layout for `[T; len]`.
+    ///
+    /// # Errors
+    ///
+    /// When `len * size_of::<T>()` overflows or when `len * size_of::<T>() > isize::MAX`.
+    pub const fn new(len: usize) -> Result<Self, LayoutError> {
+        match len.checked_mul(core::mem::size_of::<T>()) {
+            Some(len) if len <= ISIZE_MAX => {
+                // INVARIANT: We checked above that `len * size_of::<T>() <= isize::MAX`.
+                Ok(Self {
+                    len,
+                    _phantom: PhantomData,
+                })
+            }
+            _ => Err(LayoutError),
+        }
+    }
+
+    /// Creates a new layout for `[T; len]`.
+    ///
+    /// # Safety
+    ///
+    /// `len` must be a value, for which `len * size_of::<T>() <= isize::MAX` is true.
+    pub unsafe fn new_unchecked(len: usize) -> Self {
+        // INVARIANT: By the safety requirements of this function
+        // `len * size_of::<T>() <= isize::MAX`.
+        Self {
+            len,
+            _phantom: PhantomData,
+        }
+    }
+
+    /// Returns the number of array elements represented by this layout.
+    pub const fn len(&self) -> usize {
+        self.len
+    }
+
+    /// Returns `true` when no array elements are represented by this layout.
+    pub const fn is_empty(&self) -> bool {
+        self.len == 0
+    }
+}
+
+impl<T> From<ArrayLayout<T>> for Layout {
+    fn from(value: ArrayLayout<T>) -> Self {
+        let res = Layout::array::<T>(value.len);
+        // SAFETY: By the type invariant of `ArrayLayout` we have
+        // `len * size_of::<T>() <= isize::MAX` and thus the result must be `Ok`.
+        unsafe { res.unwrap_unchecked() }
+    }
+}

From 2aac4cd7dae3d7bb0e0ddec2561b2ee4cbe6c8f6 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:20 +0200
Subject: [PATCH 0364/1530] rust: alloc: implement kernel `Vec` type

`Vec` provides a contiguous growable array type with contents allocated
with the kernel's allocators (e.g. `Kmalloc`, `Vmalloc` or `KVmalloc`).

In contrast to Rust's stdlib `Vec` type, the kernel `Vec` type considers
the kernel's GFP flags for all appropriate functions, always reports
allocation failures through `Result<_, AllocError>` and remains
independent from unstable features.

[ This patch starts using a new unstable feature, `inline_const`, but
  it was stabilized in Rust 1.79.0, i.e. the next version after the
  minimum one, thus it will not be an issue. - Miguel ]

Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-17-dakr@kernel.org
[ Cleaned `rustdoc` unescaped backtick warning, added a couple more
  backticks elsewhere, fixed typos, sorted `feature`s, rewrapped
  documentation lines. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc.rs      |   6 +
 rust/kernel/alloc/kvec.rs | 648 ++++++++++++++++++++++++++++++++++++++
 rust/kernel/lib.rs        |   1 +
 rust/kernel/prelude.rs    |   2 +-
 4 files changed, 656 insertions(+), 1 deletion(-)
 create mode 100644 rust/kernel/alloc/kvec.rs

diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index c679d93b0523a..7f654b214ec24 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -5,6 +5,7 @@
 #[cfg(not(any(test, testlib)))]
 pub mod allocator;
 pub mod kbox;
+pub mod kvec;
 pub mod layout;
 pub mod vec_ext;
 
@@ -19,6 +20,11 @@ pub use self::kbox::KBox;
 pub use self::kbox::KVBox;
 pub use self::kbox::VBox;
 
+pub use self::kvec::KVVec;
+pub use self::kvec::KVec;
+pub use self::kvec::VVec;
+pub use self::kvec::Vec;
+
 /// Indicates an allocation error.
 #[derive(Copy, Clone, PartialEq, Eq, Debug)]
 pub struct AllocError;
diff --git a/rust/kernel/alloc/kvec.rs b/rust/kernel/alloc/kvec.rs
new file mode 100644
index 0000000000000..8a1d8f414955d
--- /dev/null
+++ b/rust/kernel/alloc/kvec.rs
@@ -0,0 +1,648 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Implementation of [`Vec`].
+
+use super::{
+    allocator::{KVmalloc, Kmalloc, Vmalloc},
+    layout::ArrayLayout,
+    AllocError, Allocator, Box, Flags,
+};
+use core::{
+    fmt,
+    marker::PhantomData,
+    mem::{ManuallyDrop, MaybeUninit},
+    ops::Deref,
+    ops::DerefMut,
+    ops::Index,
+    ops::IndexMut,
+    ptr,
+    ptr::NonNull,
+    slice,
+    slice::SliceIndex,
+};
+
+/// Create a [`KVec`] containing the arguments.
+///
+/// New memory is allocated with `GFP_KERNEL`.
+///
+/// # Examples
+///
+/// ```
+/// let mut v = kernel::kvec![];
+/// v.push(1, GFP_KERNEL)?;
+/// assert_eq!(v, [1]);
+///
+/// let mut v = kernel::kvec![1; 3]?;
+/// v.push(4, GFP_KERNEL)?;
+/// assert_eq!(v, [1, 1, 1, 4]);
+///
+/// let mut v = kernel::kvec![1, 2, 3]?;
+/// v.push(4, GFP_KERNEL)?;
+/// assert_eq!(v, [1, 2, 3, 4]);
+///
+/// # Ok::<(), Error>(())
+/// ```
+#[macro_export]
+macro_rules! kvec {
+    () => (
+        $crate::alloc::KVec::new()
+    );
+    ($elem:expr; $n:expr) => (
+        $crate::alloc::KVec::from_elem($elem, $n, GFP_KERNEL)
+    );
+    ($($x:expr),+ $(,)?) => (
+        match $crate::alloc::KBox::new_uninit(GFP_KERNEL) {
+            Ok(b) => Ok($crate::alloc::KVec::from($crate::alloc::KBox::write(b, [$($x),+]))),
+            Err(e) => Err(e),
+        }
+    );
+}
+
+/// The kernel's [`Vec`] type.
+///
+/// A contiguous growable array type with contents allocated with the kernel's allocators (e.g.
+/// [`Kmalloc`], [`Vmalloc`] or [`KVmalloc`]), written `Vec<T, A>`.
+///
+/// For non-zero-sized values, a [`Vec`] will use the given allocator `A` for its allocation. For
+/// the most common allocators the type aliases [`KVec`], [`VVec`] and [`KVVec`] exist.
+///
+/// For zero-sized types the [`Vec`]'s pointer must be `dangling_mut::<T>`; no memory is allocated.
+///
+/// Generally, [`Vec`] consists of a pointer that represents the vector's backing buffer, the
+/// capacity of the vector (the number of elements that currently fit into the vector), its length
+/// (the number of elements that are currently stored in the vector) and the `Allocator` type used
+/// to allocate (and free) the backing buffer.
+///
+/// A [`Vec`] can be deconstructed into and (re-)constructed from its previously named raw parts
+/// and manually modified.
+///
+/// [`Vec`]'s backing buffer gets, if required, automatically increased (re-allocated) when elements
+/// are added to the vector.
+///
+/// # Invariants
+///
+/// - `self.ptr` is always properly aligned and either points to memory allocated with `A` or, for
+///   zero-sized types, is a dangling, well aligned pointer.
+///
+/// - `self.len` always represents the exact number of elements stored in the vector.
+///
+/// - `self.layout` represents the absolute number of elements that can be stored within the vector
+///   without re-allocation. For ZSTs `self.layout`'s capacity is zero. However, it is legal for the
+///   backing buffer to be larger than `layout`.
+///
+/// - The `Allocator` type `A` of the vector is the exact same `Allocator` type the backing buffer
+///   was allocated with (and must be freed with).
+pub struct Vec<T, A: Allocator> {
+    ptr: NonNull<T>,
+    /// Represents the actual buffer size as `cap` times `size_of::<T>` bytes.
+    ///
+    /// Note: This isn't quite the same as `Self::capacity`, which in contrast returns the number of
+    /// elements we can still store without reallocating.
+    layout: ArrayLayout<T>,
+    len: usize,
+    _p: PhantomData<A>,
+}
+
+/// Type alias for [`Vec`] with a [`Kmalloc`] allocator.
+///
+/// # Examples
+///
+/// ```
+/// let mut v = KVec::new();
+/// v.push(1, GFP_KERNEL)?;
+/// assert_eq!(&v, &[1]);
+///
+/// # Ok::<(), Error>(())
+/// ```
+pub type KVec<T> = Vec<T, Kmalloc>;
+
+/// Type alias for [`Vec`] with a [`Vmalloc`] allocator.
+///
+/// # Examples
+///
+/// ```
+/// let mut v = VVec::new();
+/// v.push(1, GFP_KERNEL)?;
+/// assert_eq!(&v, &[1]);
+///
+/// # Ok::<(), Error>(())
+/// ```
+pub type VVec<T> = Vec<T, Vmalloc>;
+
+/// Type alias for [`Vec`] with a [`KVmalloc`] allocator.
+///
+/// # Examples
+///
+/// ```
+/// let mut v = KVVec::new();
+/// v.push(1, GFP_KERNEL)?;
+/// assert_eq!(&v, &[1]);
+///
+/// # Ok::<(), Error>(())
+/// ```
+pub type KVVec<T> = Vec<T, KVmalloc>;
+
+// SAFETY: `Vec` is `Send` if `T` is `Send` because `Vec` owns its elements.
+unsafe impl<T, A> Send for Vec<T, A>
+where
+    T: Send,
+    A: Allocator,
+{
+}
+
+// SAFETY: `Vec` is `Sync` if `T` is `Sync` because `Vec` owns its elements.
+unsafe impl<T, A> Sync for Vec<T, A>
+where
+    T: Sync,
+    A: Allocator,
+{
+}
+
+impl<T, A> Vec<T, A>
+where
+    A: Allocator,
+{
+    #[inline]
+    const fn is_zst() -> bool {
+        core::mem::size_of::<T>() == 0
+    }
+
+    /// Returns the number of elements that can be stored within the vector without allocating
+    /// additional memory.
+    pub fn capacity(&self) -> usize {
+        if const { Self::is_zst() } {
+            usize::MAX
+        } else {
+            self.layout.len()
+        }
+    }
+
+    /// Returns the number of elements stored within the vector.
+    #[inline]
+    pub fn len(&self) -> usize {
+        self.len
+    }
+
+    /// Forcefully sets `self.len` to `new_len`.
+    ///
+    /// # Safety
+    ///
+    /// - `new_len` must be less than or equal to [`Self::capacity`].
+    /// - If `new_len` is greater than `self.len`, all elements within the interval
+    ///   [`self.len`,`new_len`) must be initialized.
+    #[inline]
+    pub unsafe fn set_len(&mut self, new_len: usize) {
+        debug_assert!(new_len <= self.capacity());
+        self.len = new_len;
+    }
+
+    /// Returns a slice of the entire vector.
+    #[inline]
+    pub fn as_slice(&self) -> &[T] {
+        self
+    }
+
+    /// Returns a mutable slice of the entire vector.
+    #[inline]
+    pub fn as_mut_slice(&mut self) -> &mut [T] {
+        self
+    }
+
+    /// Returns a mutable raw pointer to the vector's backing buffer, or, if `T` is a ZST, a
+    /// dangling raw pointer.
+    #[inline]
+    pub fn as_mut_ptr(&mut self) -> *mut T {
+        self.ptr.as_ptr()
+    }
+
+    /// Returns a raw pointer to the vector's backing buffer, or, if `T` is a ZST, a dangling raw
+    /// pointer.
+    #[inline]
+    pub fn as_ptr(&self) -> *const T {
+        self.ptr.as_ptr()
+    }
+
+    /// Returns `true` if the vector contains no elements, `false` otherwise.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = KVec::new();
+    /// assert!(v.is_empty());
+    ///
+    /// v.push(1, GFP_KERNEL);
+    /// assert!(!v.is_empty());
+    /// ```
+    #[inline]
+    pub fn is_empty(&self) -> bool {
+        self.len() == 0
+    }
+
+    /// Creates a new, empty `Vec<T, A>`.
+    ///
+    /// This method does not allocate by itself.
+    #[inline]
+    pub const fn new() -> Self {
+        // INVARIANT: Since this is a new, empty `Vec` with no backing memory yet,
+        // - `ptr` is a properly aligned dangling pointer for type `T`,
+        // - `layout` is an empty `ArrayLayout` (zero capacity)
+        // - `len` is zero, since no elements can be or have been stored,
+        // - `A` is always valid.
+        Self {
+            ptr: NonNull::dangling(),
+            layout: ArrayLayout::empty(),
+            len: 0,
+            _p: PhantomData::<A>,
+        }
+    }
+
+    /// Returns a slice of `MaybeUninit<T>` for the remaining spare capacity of the vector.
+    pub fn spare_capacity_mut(&mut self) -> &mut [MaybeUninit<T>] {
+        // SAFETY:
+        // - `self.len` is smaller than `self.capacity` and hence, the resulting pointer is
+        //   guaranteed to be part of the same allocated object.
+        // - `self.len` can not overflow `isize`.
+        let ptr = unsafe { self.as_mut_ptr().add(self.len) } as *mut MaybeUninit<T>;
+
+        // SAFETY: The memory between `self.len` and `self.capacity` is guaranteed to be allocated
+        // and valid, but uninitialized.
+        unsafe { slice::from_raw_parts_mut(ptr, self.capacity() - self.len) }
+    }
+
+    /// Appends an element to the back of the [`Vec`] instance.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = KVec::new();
+    /// v.push(1, GFP_KERNEL)?;
+    /// assert_eq!(&v, &[1]);
+    ///
+    /// v.push(2, GFP_KERNEL)?;
+    /// assert_eq!(&v, &[1, 2]);
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn push(&mut self, v: T, flags: Flags) -> Result<(), AllocError> {
+        self.reserve(1, flags)?;
+
+        // SAFETY:
+        // - `self.len` is smaller than `self.capacity` and hence, the resulting pointer is
+        //   guaranteed to be part of the same allocated object.
+        // - `self.len` can not overflow `isize`.
+        let ptr = unsafe { self.as_mut_ptr().add(self.len) };
+
+        // SAFETY:
+        // - `ptr` is properly aligned and valid for writes.
+        unsafe { core::ptr::write(ptr, v) };
+
+        // SAFETY: We just initialised the first spare entry, so it is safe to increase the length
+        // by 1. We also know that the new length is <= capacity because of the previous call to
+        // `reserve` above.
+        unsafe { self.set_len(self.len() + 1) };
+        Ok(())
+    }
+
+    /// Creates a new [`Vec`] instance with at least the given capacity.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let v = KVec::<u32>::with_capacity(20, GFP_KERNEL)?;
+    ///
+    /// assert!(v.capacity() >= 20);
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn with_capacity(capacity: usize, flags: Flags) -> Result<Self, AllocError> {
+        let mut v = Vec::new();
+
+        v.reserve(capacity, flags)?;
+
+        Ok(v)
+    }
+
+    /// Creates a `Vec<T, A>` from a pointer, a length and a capacity using the allocator `A`.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = kernel::kvec![1, 2, 3]?;
+    /// v.reserve(1, GFP_KERNEL)?;
+    ///
+    /// let (mut ptr, mut len, cap) = v.into_raw_parts();
+    ///
+    /// // SAFETY: We've just reserved memory for another element.
+    /// unsafe { ptr.add(len).write(4) };
+    /// len += 1;
+    ///
+    /// // SAFETY: We only wrote an additional element at the end of the `KVec`'s buffer and
+    /// // correspondingly increased the length of the `KVec` by one. Otherwise, we construct it
+    /// // from the exact same raw parts.
+    /// let v = unsafe { KVec::from_raw_parts(ptr, len, cap) };
+    ///
+    /// assert_eq!(v, [1, 2, 3, 4]);
+    ///
+    /// # Ok::<(), Error>(())
+    /// ```
+    ///
+    /// # Safety
+    ///
+    /// If `T` is a ZST:
+    ///
+    /// - `ptr` must be a dangling, well aligned pointer.
+    ///
+    /// Otherwise:
+    ///
+    /// - `ptr` must have been allocated with the allocator `A`.
+    /// - `ptr` must satisfy or exceed the alignment requirements of `T`.
+    /// - `ptr` must point to memory with a size of at least `size_of::<T>() * capacity` bytes.
+    /// - The allocated size in bytes must not be larger than `isize::MAX`.
+    /// - `length` must be less than or equal to `capacity`.
+    /// - The first `length` elements must be initialized values of type `T`.
+    ///
+    /// It is also valid to create an empty `Vec` passing a dangling pointer for `ptr` and zero for
+    /// `cap` and `len`.
+    pub unsafe fn from_raw_parts(ptr: *mut T, length: usize, capacity: usize) -> Self {
+        let layout = if Self::is_zst() {
+            ArrayLayout::empty()
+        } else {
+            // SAFETY: By the safety requirements of this function, `capacity * size_of::<T>()` is
+            // smaller than `isize::MAX`.
+            unsafe { ArrayLayout::new_unchecked(capacity) }
+        };
+
+        // INVARIANT: For ZSTs, we store an empty `ArrayLayout`, all other type invariants are
+        // covered by the safety requirements of this function.
+        Self {
+            // SAFETY: By the safety requirements, `ptr` is either dangling or pointing to a valid
+            // memory allocation, allocated with `A`.
+            ptr: unsafe { NonNull::new_unchecked(ptr) },
+            layout,
+            len: length,
+            _p: PhantomData::<A>,
+        }
+    }
+
+    /// Consumes the `Vec<T, A>` and returns its raw components `pointer`, `length` and `capacity`.
+    ///
+    /// This will not run the destructor of the contained elements and for non-ZSTs the allocation
+    /// will stay alive indefinitely. Use [`Vec::from_raw_parts`] to recover the [`Vec`], drop the
+    /// elements and free the allocation, if any.
+    pub fn into_raw_parts(self) -> (*mut T, usize, usize) {
+        let mut me = ManuallyDrop::new(self);
+        let len = me.len();
+        let capacity = me.capacity();
+        let ptr = me.as_mut_ptr();
+        (ptr, len, capacity)
+    }
+
+    /// Ensures that the capacity exceeds the length by at least `additional` elements.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = KVec::new();
+    /// v.push(1, GFP_KERNEL)?;
+    ///
+    /// v.reserve(10, GFP_KERNEL)?;
+    /// let cap = v.capacity();
+    /// assert!(cap >= 10);
+    ///
+    /// v.reserve(10, GFP_KERNEL)?;
+    /// let new_cap = v.capacity();
+    /// assert_eq!(new_cap, cap);
+    ///
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn reserve(&mut self, additional: usize, flags: Flags) -> Result<(), AllocError> {
+        let len = self.len();
+        let cap = self.capacity();
+
+        if cap - len >= additional {
+            return Ok(());
+        }
+
+        if Self::is_zst() {
+            // The capacity is already `usize::MAX` for ZSTs, we can't go higher.
+            return Err(AllocError);
+        }
+
+        // We know that `cap <= isize::MAX` because of the type invariants of `Self`. So the
+        // multiplication by two won't overflow.
+        let new_cap = core::cmp::max(cap * 2, len.checked_add(additional).ok_or(AllocError)?);
+        let layout = ArrayLayout::new(new_cap).map_err(|_| AllocError)?;
+
+        // SAFETY:
+        // - `ptr` is valid because it's either `None` or comes from a previous call to
+        //   `A::realloc`.
+        // - `self.layout` matches the `ArrayLayout` of the preceding allocation.
+        let ptr = unsafe {
+            A::realloc(
+                Some(self.ptr.cast()),
+                layout.into(),
+                self.layout.into(),
+                flags,
+            )?
+        };
+
+        // INVARIANT:
+        // - `layout` is some `ArrayLayout::<T>`,
+        // - `ptr` has been created by `A::realloc` from `layout`.
+        self.ptr = ptr.cast();
+        self.layout = layout;
+
+        Ok(())
+    }
+}
+
+impl<T: Clone, A: Allocator> Vec<T, A> {
+    /// Extend the vector by `n` clones of `value`.
+    pub fn extend_with(&mut self, n: usize, value: T, flags: Flags) -> Result<(), AllocError> {
+        if n == 0 {
+            return Ok(());
+        }
+
+        self.reserve(n, flags)?;
+
+        let spare = self.spare_capacity_mut();
+
+        for item in spare.iter_mut().take(n - 1) {
+            item.write(value.clone());
+        }
+
+        // We can write the last element directly without cloning needlessly.
+        spare[n - 1].write(value);
+
+        // SAFETY:
+        // - `self.len() + n < self.capacity()` due to the call to reserve above,
+        // - the loop and the line above initialized the next `n` elements.
+        unsafe { self.set_len(self.len() + n) };
+
+        Ok(())
+    }
+
+    /// Pushes clones of the elements of slice into the [`Vec`] instance.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = KVec::new();
+    /// v.push(1, GFP_KERNEL)?;
+    ///
+    /// v.extend_from_slice(&[20, 30, 40], GFP_KERNEL)?;
+    /// assert_eq!(&v, &[1, 20, 30, 40]);
+    ///
+    /// v.extend_from_slice(&[50, 60], GFP_KERNEL)?;
+    /// assert_eq!(&v, &[1, 20, 30, 40, 50, 60]);
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn extend_from_slice(&mut self, other: &[T], flags: Flags) -> Result<(), AllocError> {
+        self.reserve(other.len(), flags)?;
+        for (slot, item) in core::iter::zip(self.spare_capacity_mut(), other) {
+            slot.write(item.clone());
+        }
+
+        // SAFETY:
+        // - `other.len()` spare entries have just been initialized, so it is safe to increase
+        //   the length by the same number.
+        // - `self.len() + other.len() <= self.capacity()` is guaranteed by the preceding `reserve`
+        //   call.
+        unsafe { self.set_len(self.len() + other.len()) };
+        Ok(())
+    }
+
+    /// Create a new `Vec<T, A>` and extend it by `n` clones of `value`.
+    pub fn from_elem(value: T, n: usize, flags: Flags) -> Result<Self, AllocError> {
+        let mut v = Self::with_capacity(n, flags)?;
+
+        v.extend_with(n, value, flags)?;
+
+        Ok(v)
+    }
+}
+
+impl<T, A> Drop for Vec<T, A>
+where
+    A: Allocator,
+{
+    fn drop(&mut self) {
+        // SAFETY: `self.as_mut_ptr` is guaranteed to be valid by the type invariant.
+        unsafe {
+            ptr::drop_in_place(core::ptr::slice_from_raw_parts_mut(
+                self.as_mut_ptr(),
+                self.len,
+            ))
+        };
+
+        // SAFETY:
+        // - `self.ptr` was previously allocated with `A`.
+        // - `self.layout` matches the `ArrayLayout` of the preceding allocation.
+        unsafe { A::free(self.ptr.cast(), self.layout.into()) };
+    }
+}
+
+impl<T, A, const N: usize> From<Box<[T; N], A>> for Vec<T, A>
+where
+    A: Allocator,
+{
+    fn from(b: Box<[T; N], A>) -> Vec<T, A> {
+        let len = b.len();
+        let ptr = Box::into_raw(b);
+
+        // SAFETY:
+        // - `b` has been allocated with `A`,
+        // - `ptr` fulfills the alignment requirements for `T`,
+        // - `ptr` points to memory with at least a size of `size_of::<T>() * len`,
+        // - all elements within `b` are initialized values of `T`,
+        // - `len` does not exceed `isize::MAX`.
+        unsafe { Vec::from_raw_parts(ptr as _, len, len) }
+    }
+}
+
+impl<T> Default for KVec<T> {
+    #[inline]
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl<T: fmt::Debug, A: Allocator> fmt::Debug for Vec<T, A> {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        fmt::Debug::fmt(&**self, f)
+    }
+}
+
+impl<T, A> Deref for Vec<T, A>
+where
+    A: Allocator,
+{
+    type Target = [T];
+
+    #[inline]
+    fn deref(&self) -> &[T] {
+        // SAFETY: The memory behind `self.as_ptr()` is guaranteed to contain `self.len`
+        // initialized elements of type `T`.
+        unsafe { slice::from_raw_parts(self.as_ptr(), self.len) }
+    }
+}
+
+impl<T, A> DerefMut for Vec<T, A>
+where
+    A: Allocator,
+{
+    #[inline]
+    fn deref_mut(&mut self) -> &mut [T] {
+        // SAFETY: The memory behind `self.as_ptr()` is guaranteed to contain `self.len`
+        // initialized elements of type `T`.
+        unsafe { slice::from_raw_parts_mut(self.as_mut_ptr(), self.len) }
+    }
+}
+
+impl<T: Eq, A> Eq for Vec<T, A> where A: Allocator {}
+
+impl<T, I: SliceIndex<[T]>, A> Index<I> for Vec<T, A>
+where
+    A: Allocator,
+{
+    type Output = I::Output;
+
+    #[inline]
+    fn index(&self, index: I) -> &Self::Output {
+        Index::index(&**self, index)
+    }
+}
+
+impl<T, I: SliceIndex<[T]>, A> IndexMut<I> for Vec<T, A>
+where
+    A: Allocator,
+{
+    #[inline]
+    fn index_mut(&mut self, index: I) -> &mut Self::Output {
+        IndexMut::index_mut(&mut **self, index)
+    }
+}
+
+macro_rules! impl_slice_eq {
+    ($([$($vars:tt)*] $lhs:ty, $rhs:ty,)*) => {
+        $(
+            impl<T, U, $($vars)*> PartialEq<$rhs> for $lhs
+            where
+                T: PartialEq<U>,
+            {
+                #[inline]
+                fn eq(&self, other: &$rhs) -> bool { self[..] == other[..] }
+            }
+        )*
+    }
+}
+
+impl_slice_eq! {
+    [A1: Allocator, A2: Allocator] Vec<T, A1>, Vec<U, A2>,
+    [A: Allocator] Vec<T, A>, &[U],
+    [A: Allocator] Vec<T, A>, &mut [U],
+    [A: Allocator] &[T], Vec<U, A>,
+    [A: Allocator] &mut [T], Vec<U, A>,
+    [A: Allocator] Vec<T, A>, [U],
+    [A: Allocator] [T], Vec<U, A>,
+    [A: Allocator, const N: usize] Vec<T, A>, [U; N],
+    [A: Allocator, const N: usize] Vec<T, A>, &[U; N],
+}
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 34e9151db58d2..620de74d128f9 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -15,6 +15,7 @@
 #![feature(arbitrary_self_types)]
 #![feature(coerce_unsized)]
 #![feature(dispatch_from_dyn)]
+#![feature(inline_const)]
 #![feature(lint_reasons)]
 #![feature(unsize)]
 
diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs
index d5f2fe42d0932..80223cdaa4850 100644
--- a/rust/kernel/prelude.rs
+++ b/rust/kernel/prelude.rs
@@ -14,7 +14,7 @@
 #[doc(no_inline)]
 pub use core::pin::Pin;
 
-pub use crate::alloc::{flags::*, vec_ext::VecExt, Box, KBox, KVBox, VBox};
+pub use crate::alloc::{flags::*, vec_ext::VecExt, Box, KBox, KVBox, KVVec, KVec, VBox, VVec};
 
 #[doc(no_inline)]
 pub use alloc::vec::Vec;

From 1d1d223aa3b37c34271aefc2706340d0843bfcb2 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:21 +0200
Subject: [PATCH 0365/1530] rust: alloc: implement `IntoIterator` for `Vec`

Implement `IntoIterator` for `Vec`, `Vec`'s `IntoIter` type, as well as
`Iterator` for `IntoIter`.

`Vec::into_iter` disassembles the `Vec` into its raw parts; additionally,
`IntoIter` keeps track of a separate pointer, which is incremented
correspondingly as the iterator advances, while the length, or the count
of elements, is decremented.

This also means that `IntoIter` takes the ownership of the backing
buffer and is responsible to drop the remaining elements and free the
backing buffer, if it's dropped.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-18-dakr@kernel.org
[ Fixed typos. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc.rs      |   1 +
 rust/kernel/alloc/kvec.rs | 170 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 171 insertions(+)

diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index 7f654b214ec24..86d2077a8e64f 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -20,6 +20,7 @@ pub use self::kbox::KBox;
 pub use self::kbox::KVBox;
 pub use self::kbox::VBox;
 
+pub use self::kvec::IntoIter;
 pub use self::kvec::KVVec;
 pub use self::kvec::KVec;
 pub use self::kvec::VVec;
diff --git a/rust/kernel/alloc/kvec.rs b/rust/kernel/alloc/kvec.rs
index 8a1d8f414955d..4ddc2ca6cd32d 100644
--- a/rust/kernel/alloc/kvec.rs
+++ b/rust/kernel/alloc/kvec.rs
@@ -646,3 +646,173 @@ impl_slice_eq! {
     [A: Allocator, const N: usize] Vec<T, A>, [U; N],
     [A: Allocator, const N: usize] Vec<T, A>, &[U; N],
 }
+
+impl<'a, T, A> IntoIterator for &'a Vec<T, A>
+where
+    A: Allocator,
+{
+    type Item = &'a T;
+    type IntoIter = slice::Iter<'a, T>;
+
+    fn into_iter(self) -> Self::IntoIter {
+        self.iter()
+    }
+}
+
+impl<'a, T, A: Allocator> IntoIterator for &'a mut Vec<T, A>
+where
+    A: Allocator,
+{
+    type Item = &'a mut T;
+    type IntoIter = slice::IterMut<'a, T>;
+
+    fn into_iter(self) -> Self::IntoIter {
+        self.iter_mut()
+    }
+}
+
+/// An [`Iterator`] implementation for [`Vec`] that moves elements out of a vector.
+///
+/// This structure is created by the [`Vec::into_iter`] method on [`Vec`] (provided by the
+/// [`IntoIterator`] trait).
+///
+/// # Examples
+///
+/// ```
+/// let v = kernel::kvec![0, 1, 2]?;
+/// let iter = v.into_iter();
+///
+/// # Ok::<(), Error>(())
+/// ```
+pub struct IntoIter<T, A: Allocator> {
+    ptr: *mut T,
+    buf: NonNull<T>,
+    len: usize,
+    layout: ArrayLayout<T>,
+    _p: PhantomData<A>,
+}
+
+impl<T, A> Iterator for IntoIter<T, A>
+where
+    A: Allocator,
+{
+    type Item = T;
+
+    /// # Examples
+    ///
+    /// ```
+    /// let v = kernel::kvec![1, 2, 3]?;
+    /// let mut it = v.into_iter();
+    ///
+    /// assert_eq!(it.next(), Some(1));
+    /// assert_eq!(it.next(), Some(2));
+    /// assert_eq!(it.next(), Some(3));
+    /// assert_eq!(it.next(), None);
+    ///
+    /// # Ok::<(), Error>(())
+    /// ```
+    fn next(&mut self) -> Option<T> {
+        if self.len == 0 {
+            return None;
+        }
+
+        let current = self.ptr;
+
+        // SAFETY: We can't overflow; decreasing `self.len` by one every time we advance `self.ptr`
+        // by one guarantees that.
+        unsafe { self.ptr = self.ptr.add(1) };
+
+        self.len -= 1;
+
+        // SAFETY: `current` is guaranteed to point at a valid element within the buffer.
+        Some(unsafe { current.read() })
+    }
+
+    /// # Examples
+    ///
+    /// ```
+    /// let v: KVec<u32> = kernel::kvec![1, 2, 3]?;
+    /// let mut iter = v.into_iter();
+    /// let size = iter.size_hint().0;
+    ///
+    /// iter.next();
+    /// assert_eq!(iter.size_hint().0, size - 1);
+    ///
+    /// iter.next();
+    /// assert_eq!(iter.size_hint().0, size - 2);
+    ///
+    /// iter.next();
+    /// assert_eq!(iter.size_hint().0, size - 3);
+    ///
+    /// # Ok::<(), Error>(())
+    /// ```
+    fn size_hint(&self) -> (usize, Option<usize>) {
+        (self.len, Some(self.len))
+    }
+}
+
+impl<T, A> Drop for IntoIter<T, A>
+where
+    A: Allocator,
+{
+    fn drop(&mut self) {
+        // SAFETY: `self.ptr` is guaranteed to be valid by the type invariant.
+        unsafe { ptr::drop_in_place(ptr::slice_from_raw_parts_mut(self.ptr, self.len)) };
+
+        // SAFETY:
+        // - `self.buf` was previously allocated with `A`.
+        // - `self.layout` matches the `ArrayLayout` of the preceding allocation.
+        unsafe { A::free(self.buf.cast(), self.layout.into()) };
+    }
+}
+
+impl<T, A> IntoIterator for Vec<T, A>
+where
+    A: Allocator,
+{
+    type Item = T;
+    type IntoIter = IntoIter<T, A>;
+
+    /// Consumes the `Vec<T, A>` and creates an `Iterator`, which moves each value out of the
+    /// vector (from start to end).
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let v = kernel::kvec![1, 2]?;
+    /// let mut v_iter = v.into_iter();
+    ///
+    /// let first_element: Option<u32> = v_iter.next();
+    ///
+    /// assert_eq!(first_element, Some(1));
+    /// assert_eq!(v_iter.next(), Some(2));
+    /// assert_eq!(v_iter.next(), None);
+    ///
+    /// # Ok::<(), Error>(())
+    /// ```
+    ///
+    /// ```
+    /// let v = kernel::kvec![];
+    /// let mut v_iter = v.into_iter();
+    ///
+    /// let first_element: Option<u32> = v_iter.next();
+    ///
+    /// assert_eq!(first_element, None);
+    ///
+    /// # Ok::<(), Error>(())
+    /// ```
+    #[inline]
+    fn into_iter(self) -> Self::IntoIter {
+        let buf = self.ptr;
+        let layout = self.layout;
+        let (ptr, len, _) = self.into_raw_parts();
+
+        IntoIter {
+            ptr,
+            buf,
+            len,
+            layout,
+            _p: PhantomData::<A>,
+        }
+    }
+}

From 93e602310f87b7b515b86a8f919cc0799387e5c3 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:22 +0200
Subject: [PATCH 0366/1530] rust: alloc: implement `collect` for `IntoIter`

Currently, we can't implement `FromIterator`. There are a couple of
issues with this trait in the kernel, namely:

  - Rust's specialization feature is unstable. This prevents us to
    optimize for the special case where `I::IntoIter` equals `Vec`'s
    `IntoIter` type.
  - We also can't use `I::IntoIter`'s type ID either to work around this,
    since `FromIterator` doesn't require this type to be `'static`.
  - `FromIterator::from_iter` does return `Self` instead of
    `Result<Self, AllocError>`, hence we can't properly handle allocation
    failures.
  - Neither `Iterator::collect` nor `FromIterator::from_iter` can handle
    additional allocation flags.

Instead, provide `IntoIter::collect`, such that we can at least convert
`IntoIter` into a `Vec` again.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-19-dakr@kernel.org
[ Added newline in documentation, changed case of section to be
  consistent with an existing one, fixed typo. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc/kvec.rs | 95 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 95 insertions(+)

diff --git a/rust/kernel/alloc/kvec.rs b/rust/kernel/alloc/kvec.rs
index 4ddc2ca6cd32d..ae9d072741ced 100644
--- a/rust/kernel/alloc/kvec.rs
+++ b/rust/kernel/alloc/kvec.rs
@@ -692,6 +692,101 @@ pub struct IntoIter<T, A: Allocator> {
     _p: PhantomData<A>,
 }
 
+impl<T, A> IntoIter<T, A>
+where
+    A: Allocator,
+{
+    fn into_raw_parts(self) -> (*mut T, NonNull<T>, usize, usize) {
+        let me = ManuallyDrop::new(self);
+        let ptr = me.ptr;
+        let buf = me.buf;
+        let len = me.len;
+        let cap = me.layout.len();
+        (ptr, buf, len, cap)
+    }
+
+    /// Same as `Iterator::collect` but specialized for `Vec`'s `IntoIter`.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let v = kernel::kvec![1, 2, 3]?;
+    /// let mut it = v.into_iter();
+    ///
+    /// assert_eq!(it.next(), Some(1));
+    ///
+    /// let v = it.collect(GFP_KERNEL);
+    /// assert_eq!(v, [2, 3]);
+    ///
+    /// # Ok::<(), Error>(())
+    /// ```
+    ///
+    /// # Implementation details
+    ///
+    /// Currently, we can't implement `FromIterator`. There are a couple of issues with this trait
+    /// in the kernel, namely:
+    ///
+    /// - Rust's specialization feature is unstable. This prevents us to optimize for the special
+    ///   case where `I::IntoIter` equals `Vec`'s `IntoIter` type.
+    /// - We also can't use `I::IntoIter`'s type ID either to work around this, since `FromIterator`
+    ///   doesn't require this type to be `'static`.
+    /// - `FromIterator::from_iter` does return `Self` instead of `Result<Self, AllocError>`, hence
+    ///   we can't properly handle allocation failures.
+    /// - Neither `Iterator::collect` nor `FromIterator::from_iter` can handle additional allocation
+    ///   flags.
+    ///
+    /// Instead, provide `IntoIter::collect`, such that we can at least convert a `IntoIter` into a
+    /// `Vec` again.
+    ///
+    /// Note that `IntoIter::collect` doesn't require `Flags`, since it re-uses the existing backing
+    /// buffer. However, this backing buffer may be shrunk to the actual count of elements.
+    pub fn collect(self, flags: Flags) -> Vec<T, A> {
+        let old_layout = self.layout;
+        let (mut ptr, buf, len, mut cap) = self.into_raw_parts();
+        let has_advanced = ptr != buf.as_ptr();
+
+        if has_advanced {
+            // Copy the contents we have advanced to at the beginning of the buffer.
+            //
+            // SAFETY:
+            // - `ptr` is valid for reads of `len * size_of::<T>()` bytes,
+            // - `buf.as_ptr()` is valid for writes of `len * size_of::<T>()` bytes,
+            // - `ptr` and `buf.as_ptr()` are not be subject to aliasing restrictions relative to
+            //   each other,
+            // - both `ptr` and `buf.ptr()` are properly aligned.
+            unsafe { ptr::copy(ptr, buf.as_ptr(), len) };
+            ptr = buf.as_ptr();
+
+            // SAFETY: `len` is guaranteed to be smaller than `self.layout.len()`.
+            let layout = unsafe { ArrayLayout::<T>::new_unchecked(len) };
+
+            // SAFETY: `buf` points to the start of the backing buffer and `len` is guaranteed to be
+            // smaller than `cap`. Depending on `alloc` this operation may shrink the buffer or leaves
+            // it as it is.
+            ptr = match unsafe {
+                A::realloc(Some(buf.cast()), layout.into(), old_layout.into(), flags)
+            } {
+                // If we fail to shrink, which likely can't even happen, continue with the existing
+                // buffer.
+                Err(_) => ptr,
+                Ok(ptr) => {
+                    cap = len;
+                    ptr.as_ptr().cast()
+                }
+            };
+        }
+
+        // SAFETY: If the iterator has been advanced, the advanced elements have been copied to
+        // the beginning of the buffer and `len` has been adjusted accordingly.
+        //
+        // - `ptr` is guaranteed to point to the start of the backing buffer.
+        // - `cap` is either the original capacity or, after shrinking the buffer, equal to `len`.
+        // - `alloc` is guaranteed to be unchanged since `into_iter` has been called on the original
+        //   `Vec`.
+        unsafe { Vec::from_raw_parts(ptr, len, cap) }
+    }
+}
+
 impl<T, A> Iterator for IntoIter<T, A>
 where
     A: Allocator,

From 58eff8e872bd04ccb3adcf99aec7334ffad06cfd Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:23 +0200
Subject: [PATCH 0367/1530] rust: treewide: switch to the kernel `Vec` type

Now that we got the kernel `Vec` in place, convert all existing `Vec`
users to make use of it.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-20-dakr@kernel.org
[ Converted `kasan_test_rust.rs` too, as discussed. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 mm/kasan/kasan_test_rust.rs   |  2 +-
 rust/kernel/str.rs            | 12 +++++-------
 rust/kernel/sync/locked_by.rs |  2 +-
 rust/kernel/types.rs          |  2 +-
 rust/kernel/uaccess.rs        | 17 +++++++----------
 rust/macros/lib.rs            |  6 +++---
 samples/rust/rust_minimal.rs  |  4 ++--
 7 files changed, 20 insertions(+), 25 deletions(-)

diff --git a/mm/kasan/kasan_test_rust.rs b/mm/kasan/kasan_test_rust.rs
index 47bcf033dd4f0..5b34edf30e724 100644
--- a/mm/kasan/kasan_test_rust.rs
+++ b/mm/kasan/kasan_test_rust.rs
@@ -11,7 +11,7 @@ use kernel::prelude::*;
 /// drop the vector, and touch it.
 #[no_mangle]
 pub extern "C" fn kasan_test_rust_uaf() -> u8 {
-    let mut v: Vec<u8> = Vec::new();
+    let mut v: KVec<u8> = KVec::new();
     for _ in 0..4096 {
         v.push(0x42, GFP_KERNEL).unwrap();
     }
diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
index 66d4527f6c6f0..6053bc7a98d19 100644
--- a/rust/kernel/str.rs
+++ b/rust/kernel/str.rs
@@ -2,8 +2,7 @@
 
 //! String representations.
 
-use crate::alloc::{flags::*, vec_ext::VecExt, AllocError};
-use alloc::vec::Vec;
+use crate::alloc::{flags::*, AllocError, KVec};
 use core::fmt::{self, Write};
 use core::ops::{self, Deref, DerefMut, Index};
 
@@ -791,7 +790,7 @@ impl fmt::Write for Formatter {
 /// assert_eq!(s.is_ok(), false);
 /// ```
 pub struct CString {
-    buf: Vec<u8>,
+    buf: KVec<u8>,
 }
 
 impl CString {
@@ -804,7 +803,7 @@ impl CString {
         let size = f.bytes_written();
 
         // Allocate a vector with the required number of bytes, and write to it.
-        let mut buf = <Vec<_> as VecExt<_>>::with_capacity(size, GFP_KERNEL)?;
+        let mut buf = KVec::with_capacity(size, GFP_KERNEL)?;
         // SAFETY: The buffer stored in `buf` is at least of size `size` and is valid for writes.
         let mut f = unsafe { Formatter::from_buffer(buf.as_mut_ptr(), size) };
         f.write_fmt(args)?;
@@ -851,10 +850,9 @@ impl<'a> TryFrom<&'a CStr> for CString {
     type Error = AllocError;
 
     fn try_from(cstr: &'a CStr) -> Result<CString, AllocError> {
-        let mut buf = Vec::new();
+        let mut buf = KVec::new();
 
-        <Vec<_> as VecExt<_>>::extend_from_slice(&mut buf, cstr.as_bytes_with_nul(), GFP_KERNEL)
-            .map_err(|_| AllocError)?;
+        buf.extend_from_slice(cstr.as_bytes_with_nul(), GFP_KERNEL)?;
 
         // INVARIANT: The `CStr` and `CString` types have the same invariants for
         // the string data, and we copied it over without changes.
diff --git a/rust/kernel/sync/locked_by.rs b/rust/kernel/sync/locked_by.rs
index ce2ee8d878658..a7b244675c2b9 100644
--- a/rust/kernel/sync/locked_by.rs
+++ b/rust/kernel/sync/locked_by.rs
@@ -43,7 +43,7 @@ use core::{cell::UnsafeCell, mem::size_of, ptr};
 /// struct InnerDirectory {
 ///     /// The sum of the bytes used by all files.
 ///     bytes_used: u64,
-///     _files: Vec<File>,
+///     _files: KVec<File>,
 /// }
 ///
 /// struct Directory {
diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index 34f1b31753df1..ced143600eb1b 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -135,7 +135,7 @@ impl ForeignOwnable for () {
 /// # use kernel::types::ScopeGuard;
 /// fn example3(arg: bool) -> Result {
 ///     let mut vec =
-///         ScopeGuard::new_with_data(Vec::new(), |v| pr_info!("vec had {} elements\n", v.len()));
+///         ScopeGuard::new_with_data(KVec::new(), |v| pr_info!("vec had {} elements\n", v.len()));
 ///
 ///     vec.push(10u8, GFP_KERNEL)?;
 ///     if arg {
diff --git a/rust/kernel/uaccess.rs b/rust/kernel/uaccess.rs
index 0af243482eac9..2c953ba53c771 100644
--- a/rust/kernel/uaccess.rs
+++ b/rust/kernel/uaccess.rs
@@ -11,7 +11,6 @@ use crate::{
     prelude::*,
     transmute::{AsBytes, FromBytes},
 };
-use alloc::vec::Vec;
 use core::ffi::{c_ulong, c_void};
 use core::mem::{size_of, MaybeUninit};
 
@@ -46,7 +45,6 @@ pub type UserPtr = usize;
 /// every byte in the region.
 ///
 /// ```no_run
-/// use alloc::vec::Vec;
 /// use core::ffi::c_void;
 /// use kernel::error::Result;
 /// use kernel::uaccess::{UserPtr, UserSlice};
@@ -54,7 +52,7 @@ pub type UserPtr = usize;
 /// fn bytes_add_one(uptr: UserPtr, len: usize) -> Result<()> {
 ///     let (read, mut write) = UserSlice::new(uptr, len).reader_writer();
 ///
-///     let mut buf = Vec::new();
+///     let mut buf = KVec::new();
 ///     read.read_all(&mut buf, GFP_KERNEL)?;
 ///
 ///     for b in &mut buf {
@@ -69,7 +67,6 @@ pub type UserPtr = usize;
 /// Example illustrating a TOCTOU (time-of-check to time-of-use) bug.
 ///
 /// ```no_run
-/// use alloc::vec::Vec;
 /// use core::ffi::c_void;
 /// use kernel::error::{code::EINVAL, Result};
 /// use kernel::uaccess::{UserPtr, UserSlice};
@@ -78,21 +75,21 @@ pub type UserPtr = usize;
 /// fn is_valid(uptr: UserPtr, len: usize) -> Result<bool> {
 ///     let read = UserSlice::new(uptr, len).reader();
 ///
-///     let mut buf = Vec::new();
+///     let mut buf = KVec::new();
 ///     read.read_all(&mut buf, GFP_KERNEL)?;
 ///
 ///     todo!()
 /// }
 ///
 /// /// Returns the bytes behind this user pointer if they are valid.
-/// fn get_bytes_if_valid(uptr: UserPtr, len: usize) -> Result<Vec<u8>> {
+/// fn get_bytes_if_valid(uptr: UserPtr, len: usize) -> Result<KVec<u8>> {
 ///     if !is_valid(uptr, len)? {
 ///         return Err(EINVAL);
 ///     }
 ///
 ///     let read = UserSlice::new(uptr, len).reader();
 ///
-///     let mut buf = Vec::new();
+///     let mut buf = KVec::new();
 ///     read.read_all(&mut buf, GFP_KERNEL)?;
 ///
 ///     // THIS IS A BUG! The bytes could have changed since we checked them.
@@ -130,7 +127,7 @@ impl UserSlice {
     /// Reads the entirety of the user slice, appending it to the end of the provided buffer.
     ///
     /// Fails with [`EFAULT`] if the read happens on a bad address.
-    pub fn read_all(self, buf: &mut Vec<u8>, flags: Flags) -> Result {
+    pub fn read_all(self, buf: &mut KVec<u8>, flags: Flags) -> Result {
         self.reader().read_all(buf, flags)
     }
 
@@ -291,9 +288,9 @@ impl UserSliceReader {
     /// Reads the entirety of the user slice, appending it to the end of the provided buffer.
     ///
     /// Fails with [`EFAULT`] if the read happens on a bad address.
-    pub fn read_all(mut self, buf: &mut Vec<u8>, flags: Flags) -> Result {
+    pub fn read_all(mut self, buf: &mut KVec<u8>, flags: Flags) -> Result {
         let len = self.length;
-        VecExt::<u8>::reserve(buf, len, flags)?;
+        buf.reserve(len, flags)?;
 
         // The call to `try_reserve` was successful, so the spare capacity is at least `len` bytes
         // long.
diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
index ab93111a048c9..8d4ac914b48bc 100644
--- a/rust/macros/lib.rs
+++ b/rust/macros/lib.rs
@@ -242,7 +242,7 @@ pub fn concat_idents(ts: TokenStream) -> TokenStream {
 /// #[pin_data]
 /// struct DriverData {
 ///     #[pin]
-///     queue: Mutex<Vec<Command>>,
+///     queue: Mutex<KVec<Command>>,
 ///     buf: KBox<[u8; 1024 * 1024]>,
 /// }
 /// ```
@@ -251,7 +251,7 @@ pub fn concat_idents(ts: TokenStream) -> TokenStream {
 /// #[pin_data(PinnedDrop)]
 /// struct DriverData {
 ///     #[pin]
-///     queue: Mutex<Vec<Command>>,
+///     queue: Mutex<KVec<Command>>,
 ///     buf: KBox<[u8; 1024 * 1024]>,
 ///     raw_info: *mut Info,
 /// }
@@ -281,7 +281,7 @@ pub fn pin_data(inner: TokenStream, item: TokenStream) -> TokenStream {
 /// #[pin_data(PinnedDrop)]
 /// struct DriverData {
 ///     #[pin]
-///     queue: Mutex<Vec<Command>>,
+///     queue: Mutex<KVec<Command>>,
 ///     buf: KBox<[u8; 1024 * 1024]>,
 ///     raw_info: *mut Info,
 /// }
diff --git a/samples/rust/rust_minimal.rs b/samples/rust/rust_minimal.rs
index 2a9eaab62d1ca..4aaf117bf8e3c 100644
--- a/samples/rust/rust_minimal.rs
+++ b/samples/rust/rust_minimal.rs
@@ -13,7 +13,7 @@ module! {
 }
 
 struct RustMinimal {
-    numbers: Vec<i32>,
+    numbers: KVec<i32>,
 }
 
 impl kernel::Module for RustMinimal {
@@ -21,7 +21,7 @@ impl kernel::Module for RustMinimal {
         pr_info!("Rust minimal sample (init)\n");
         pr_info!("Am I built-in? {}\n", !cfg!(MODULE));
 
-        let mut numbers = Vec::new();
+        let mut numbers = KVec::new();
         numbers.push(72, GFP_KERNEL)?;
         numbers.push(108, GFP_KERNEL)?;
         numbers.push(200, GFP_KERNEL)?;

From 405966efc789888c3e1a53cd09d2c2b338064438 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:24 +0200
Subject: [PATCH 0368/1530] rust: alloc: remove `VecExt` extension

Now that all existing `Vec` users were moved to the kernel `Vec` type,
remove the `VecExt` extension.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-21-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc.rs         |   1 -
 rust/kernel/alloc/vec_ext.rs | 185 -----------------------------------
 rust/kernel/prelude.rs       |   5 +-
 3 files changed, 1 insertion(+), 190 deletions(-)
 delete mode 100644 rust/kernel/alloc/vec_ext.rs

diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index 86d2077a8e64f..7fc2e404e594d 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -7,7 +7,6 @@ pub mod allocator;
 pub mod kbox;
 pub mod kvec;
 pub mod layout;
-pub mod vec_ext;
 
 #[cfg(any(test, testlib))]
 pub mod allocator_test;
diff --git a/rust/kernel/alloc/vec_ext.rs b/rust/kernel/alloc/vec_ext.rs
deleted file mode 100644
index 1297a4be32e8c..0000000000000
--- a/rust/kernel/alloc/vec_ext.rs
+++ /dev/null
@@ -1,185 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-//! Extensions to [`Vec`] for fallible allocations.
-
-use super::{AllocError, Flags};
-use alloc::vec::Vec;
-
-/// Extensions to [`Vec`].
-pub trait VecExt<T>: Sized {
-    /// Creates a new [`Vec`] instance with at least the given capacity.
-    ///
-    /// # Examples
-    ///
-    /// ```
-    /// let v = Vec::<u32>::with_capacity(20, GFP_KERNEL)?;
-    ///
-    /// assert!(v.capacity() >= 20);
-    /// # Ok::<(), Error>(())
-    /// ```
-    fn with_capacity(capacity: usize, flags: Flags) -> Result<Self, AllocError>;
-
-    /// Appends an element to the back of the [`Vec`] instance.
-    ///
-    /// # Examples
-    ///
-    /// ```
-    /// let mut v = Vec::new();
-    /// v.push(1, GFP_KERNEL)?;
-    /// assert_eq!(&v, &[1]);
-    ///
-    /// v.push(2, GFP_KERNEL)?;
-    /// assert_eq!(&v, &[1, 2]);
-    /// # Ok::<(), Error>(())
-    /// ```
-    fn push(&mut self, v: T, flags: Flags) -> Result<(), AllocError>;
-
-    /// Pushes clones of the elements of slice into the [`Vec`] instance.
-    ///
-    /// # Examples
-    ///
-    /// ```
-    /// let mut v = Vec::new();
-    /// v.push(1, GFP_KERNEL)?;
-    ///
-    /// v.extend_from_slice(&[20, 30, 40], GFP_KERNEL)?;
-    /// assert_eq!(&v, &[1, 20, 30, 40]);
-    ///
-    /// v.extend_from_slice(&[50, 60], GFP_KERNEL)?;
-    /// assert_eq!(&v, &[1, 20, 30, 40, 50, 60]);
-    /// # Ok::<(), Error>(())
-    /// ```
-    fn extend_from_slice(&mut self, other: &[T], flags: Flags) -> Result<(), AllocError>
-    where
-        T: Clone;
-
-    /// Ensures that the capacity exceeds the length by at least `additional` elements.
-    ///
-    /// # Examples
-    ///
-    /// ```
-    /// let mut v = Vec::new();
-    /// v.push(1, GFP_KERNEL)?;
-    ///
-    /// v.reserve(10, GFP_KERNEL)?;
-    /// let cap = v.capacity();
-    /// assert!(cap >= 10);
-    ///
-    /// v.reserve(10, GFP_KERNEL)?;
-    /// let new_cap = v.capacity();
-    /// assert_eq!(new_cap, cap);
-    ///
-    /// # Ok::<(), Error>(())
-    /// ```
-    fn reserve(&mut self, additional: usize, flags: Flags) -> Result<(), AllocError>;
-}
-
-impl<T> VecExt<T> for Vec<T> {
-    fn with_capacity(capacity: usize, flags: Flags) -> Result<Self, AllocError> {
-        let mut v = Vec::new();
-        <Self as VecExt<_>>::reserve(&mut v, capacity, flags)?;
-        Ok(v)
-    }
-
-    fn push(&mut self, v: T, flags: Flags) -> Result<(), AllocError> {
-        <Self as VecExt<_>>::reserve(self, 1, flags)?;
-        let s = self.spare_capacity_mut();
-        s[0].write(v);
-
-        // SAFETY: We just initialised the first spare entry, so it is safe to increase the length
-        // by 1. We also know that the new length is <= capacity because of the previous call to
-        // `reserve` above.
-        unsafe { self.set_len(self.len() + 1) };
-        Ok(())
-    }
-
-    fn extend_from_slice(&mut self, other: &[T], flags: Flags) -> Result<(), AllocError>
-    where
-        T: Clone,
-    {
-        <Self as VecExt<_>>::reserve(self, other.len(), flags)?;
-        for (slot, item) in core::iter::zip(self.spare_capacity_mut(), other) {
-            slot.write(item.clone());
-        }
-
-        // SAFETY: We just initialised the `other.len()` spare entries, so it is safe to increase
-        // the length by the same amount. We also know that the new length is <= capacity because
-        // of the previous call to `reserve` above.
-        unsafe { self.set_len(self.len() + other.len()) };
-        Ok(())
-    }
-
-    #[cfg(any(test, testlib))]
-    fn reserve(&mut self, additional: usize, _flags: Flags) -> Result<(), AllocError> {
-        Vec::reserve(self, additional);
-        Ok(())
-    }
-
-    #[cfg(not(any(test, testlib)))]
-    fn reserve(&mut self, additional: usize, flags: Flags) -> Result<(), AllocError> {
-        let len = self.len();
-        let cap = self.capacity();
-
-        if cap - len >= additional {
-            return Ok(());
-        }
-
-        if core::mem::size_of::<T>() == 0 {
-            // The capacity is already `usize::MAX` for SZTs, we can't go higher.
-            return Err(AllocError);
-        }
-
-        // We know cap is <= `isize::MAX` because `Layout::array` fails if the resulting byte size
-        // is greater than `isize::MAX`. So the multiplication by two won't overflow.
-        let new_cap = core::cmp::max(cap * 2, len.checked_add(additional).ok_or(AllocError)?);
-        let layout = core::alloc::Layout::array::<T>(new_cap).map_err(|_| AllocError)?;
-
-        let (old_ptr, len, cap) = destructure(self);
-
-        // We need to make sure that `ptr` is either NULL or comes from a previous call to
-        // `krealloc_aligned`. A `Vec<T>`'s `ptr` value is not guaranteed to be NULL and might be
-        // dangling after being created with `Vec::new`. Instead, we can rely on `Vec<T>`'s capacity
-        // to be zero if no memory has been allocated yet.
-        let ptr = if cap == 0 {
-            core::ptr::null_mut()
-        } else {
-            old_ptr
-        };
-
-        // SAFETY: `ptr` is valid because it's either NULL or comes from a previous call to
-        // `krealloc_aligned`. We also verified that the type is not a ZST.
-        let new_ptr = unsafe { super::allocator::krealloc_aligned(ptr.cast(), layout, flags) };
-        if new_ptr.is_null() {
-            // SAFETY: We are just rebuilding the existing `Vec` with no changes.
-            unsafe { rebuild(self, old_ptr, len, cap) };
-            Err(AllocError)
-        } else {
-            // SAFETY: `ptr` has been reallocated with the layout for `new_cap` elements. New cap
-            // is greater than `cap`, so it continues to be >= `len`.
-            unsafe { rebuild(self, new_ptr.cast::<T>(), len, new_cap) };
-            Ok(())
-        }
-    }
-}
-
-#[cfg(not(any(test, testlib)))]
-fn destructure<T>(v: &mut Vec<T>) -> (*mut T, usize, usize) {
-    let mut tmp = Vec::new();
-    core::mem::swap(&mut tmp, v);
-    let mut tmp = core::mem::ManuallyDrop::new(tmp);
-    let len = tmp.len();
-    let cap = tmp.capacity();
-    (tmp.as_mut_ptr(), len, cap)
-}
-
-/// Rebuilds a `Vec` from a pointer, length, and capacity.
-///
-/// # Safety
-///
-/// The same as [`Vec::from_raw_parts`].
-#[cfg(not(any(test, testlib)))]
-unsafe fn rebuild<T>(v: &mut Vec<T>, ptr: *mut T, len: usize, cap: usize) {
-    // SAFETY: The safety requirements from this function satisfy those of `from_raw_parts`.
-    let mut tmp = unsafe { Vec::from_raw_parts(ptr, len, cap) };
-    core::mem::swap(&mut tmp, v);
-}
diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs
index 80223cdaa4850..07daccf6ca8e7 100644
--- a/rust/kernel/prelude.rs
+++ b/rust/kernel/prelude.rs
@@ -14,10 +14,7 @@
 #[doc(no_inline)]
 pub use core::pin::Pin;
 
-pub use crate::alloc::{flags::*, vec_ext::VecExt, Box, KBox, KVBox, KVVec, KVec, VBox, VVec};
-
-#[doc(no_inline)]
-pub use alloc::vec::Vec;
+pub use crate::alloc::{flags::*, Box, KBox, KVBox, KVVec, KVec, VBox, VVec};
 
 #[doc(no_inline)]
 pub use macros::{module, pin_data, pinned_drop, vtable, Zeroable};

From 3145dc91c3c0ad945f06354385a6eb89d22becdb Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:25 +0200
Subject: [PATCH 0369/1530] rust: alloc: add `Vec` to prelude

Now that we removed `VecExt` and the corresponding includes in
prelude.rs, add the new kernel `Vec` type instead.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-22-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/prelude.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs
index 07daccf6ca8e7..8bdab9aa0d16b 100644
--- a/rust/kernel/prelude.rs
+++ b/rust/kernel/prelude.rs
@@ -14,7 +14,7 @@
 #[doc(no_inline)]
 pub use core::pin::Pin;
 
-pub use crate::alloc::{flags::*, Box, KBox, KVBox, KVVec, KVec, VBox, VVec};
+pub use crate::alloc::{flags::*, Box, KBox, KVBox, KVVec, KVec, VBox, VVec, Vec};
 
 #[doc(no_inline)]
 pub use macros::{module, pin_data, pinned_drop, vtable, Zeroable};

From 29a48d25ff53c183482dc88a99133a0fb5aa541a Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:26 +0200
Subject: [PATCH 0370/1530] rust: error: use `core::alloc::LayoutError`

Use `core::alloc::LayoutError` instead of `alloc::alloc::LayoutError` in
preparation to get rid of Rust's alloc crate.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-23-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/error.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs
index be6509d5f4a4a..aced2fe68b86b 100644
--- a/rust/kernel/error.rs
+++ b/rust/kernel/error.rs
@@ -6,7 +6,7 @@
 
 use crate::{alloc::AllocError, str::CStr};
 
-use alloc::alloc::LayoutError;
+use core::alloc::LayoutError;
 
 use core::fmt;
 use core::num::NonZeroI32;

From 4a28ab469ff01855eb819dfd94754d1792f03f2a Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:27 +0200
Subject: [PATCH 0371/1530] rust: error: check for config `test` in
 `Error::name`

Additional to `testlib` also check for `test` in `Error::name`. This is
required by a subsequent patch that (indirectly) uses `Error` in test
cases.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-24-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/error.rs | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs
index aced2fe68b86b..7cd3bbab52f20 100644
--- a/rust/kernel/error.rs
+++ b/rust/kernel/error.rs
@@ -161,7 +161,7 @@ impl Error {
     }
 
     /// Returns a string representing the error, if one exists.
-    #[cfg(not(testlib))]
+    #[cfg(not(any(test, testlib)))]
     pub fn name(&self) -> Option<&'static CStr> {
         // SAFETY: Just an FFI call, there are no extra safety requirements.
         let ptr = unsafe { bindings::errname(-self.0.get()) };
@@ -178,7 +178,7 @@ impl Error {
     /// When `testlib` is configured, this always returns `None` to avoid the dependency on a
     /// kernel function so that tests that use this (e.g., by calling [`Result::unwrap`]) can still
     /// run in userspace.
-    #[cfg(testlib)]
+    #[cfg(any(test, testlib))]
     pub fn name(&self) -> Option<&'static CStr> {
         None
     }

From 909037ce0369bc3f4fd31743fd2d8d7096f06002 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:28 +0200
Subject: [PATCH 0372/1530] rust: alloc: implement `contains` for `Flags`

Provide a simple helper function to check whether given flags do
contain one or multiple other flags.

This is used by a subsequent patch implementing the Cmalloc `Allocator`
to check for __GFP_ZERO.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-25-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc.rs | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index 7fc2e404e594d..049fca7a514d1 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -35,7 +35,7 @@ use core::{alloc::Layout, ptr::NonNull};
 /// They can be combined with the operators `|`, `&`, and `!`.
 ///
 /// Values can be used from the [`flags`] module.
-#[derive(Clone, Copy)]
+#[derive(Clone, Copy, PartialEq)]
 pub struct Flags(u32);
 
 impl Flags {
@@ -43,6 +43,11 @@ impl Flags {
     pub(crate) fn as_raw(self) -> u32 {
         self.0
     }
+
+    /// Check whether `flags` is contained in `self`.
+    pub fn contains(self, flags: Flags) -> bool {
+        (self & flags) == flags
+    }
 }
 
 impl core::ops::BitOr for Flags {

From dd09538fb4093176a818fcecd45114430cc5840f Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:29 +0200
Subject: [PATCH 0373/1530] rust: alloc: implement `Cmalloc` in module
 allocator_test

So far the kernel's `Box` and `Vec` types can't be used by userspace
test cases, since all users of those types (e.g. `CString`) use kernel
allocators for instantiation.

In order to allow userspace test cases to make use of such types as
well, implement the `Cmalloc` allocator within the allocator_test module
and type alias all kernel allocators to `Cmalloc`. The `Cmalloc`
allocator uses libc's `realloc()` function as allocator backend.

Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-26-dakr@kernel.org
[ Removed the temporary `allow(dead_code)` as discussed in the list and
  fixed typo, added backticks. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc.rs                |  1 -
 rust/kernel/alloc/allocator_test.rs | 89 ++++++++++++++++++++++++++---
 2 files changed, 81 insertions(+), 9 deletions(-)

diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index 049fca7a514d1..c6024afa37397 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -215,7 +215,6 @@ pub unsafe trait Allocator {
     }
 }
 
-#[allow(dead_code)]
 /// Returns a properly aligned dangling pointer from the given `layout`.
 pub(crate) fn dangling_from_layout(layout: Layout) -> NonNull<u8> {
     let ptr = layout.align() as *mut u8;
diff --git a/rust/kernel/alloc/allocator_test.rs b/rust/kernel/alloc/allocator_test.rs
index bd0cbcd93e528..54ca85964d4af 100644
--- a/rust/kernel/alloc/allocator_test.rs
+++ b/rust/kernel/alloc/allocator_test.rs
@@ -1,22 +1,95 @@
 // SPDX-License-Identifier: GPL-2.0
 
+//! So far the kernel's `Box` and `Vec` types can't be used by userspace test cases, since all users
+//! of those types (e.g. `CString`) use kernel allocators for instantiation.
+//!
+//! In order to allow userspace test cases to make use of such types as well, implement the
+//! `Cmalloc` allocator within the allocator_test module and type alias all kernel allocators to
+//! `Cmalloc`. The `Cmalloc` allocator uses libc's `realloc()` function as allocator backend.
+
 #![allow(missing_docs)]
 
-use super::{AllocError, Allocator, Flags};
+use super::{flags::*, AllocError, Allocator, Flags};
 use core::alloc::Layout;
+use core::cmp;
+use core::ptr;
 use core::ptr::NonNull;
 
-pub struct Kmalloc;
+/// The userspace allocator based on libc.
+pub struct Cmalloc;
+
+pub type Kmalloc = Cmalloc;
 pub type Vmalloc = Kmalloc;
 pub type KVmalloc = Kmalloc;
 
-unsafe impl Allocator for Kmalloc {
+extern "C" {
+    #[link_name = "aligned_alloc"]
+    fn libc_aligned_alloc(align: usize, size: usize) -> *mut core::ffi::c_void;
+
+    #[link_name = "free"]
+    fn libc_free(ptr: *mut core::ffi::c_void);
+}
+
+// SAFETY:
+// - memory remains valid until it is explicitly freed,
+// - passing a pointer to a valid memory allocation created by this `Allocator` is always OK,
+// - `realloc` provides the guarantees as provided in the `# Guarantees` section.
+unsafe impl Allocator for Cmalloc {
     unsafe fn realloc(
-        _ptr: Option<NonNull<u8>>,
-        _layout: Layout,
-        _old_layout: Layout,
-        _flags: Flags,
+        ptr: Option<NonNull<u8>>,
+        layout: Layout,
+        old_layout: Layout,
+        flags: Flags,
     ) -> Result<NonNull<[u8]>, AllocError> {
-        panic!();
+        let src = match ptr {
+            Some(src) => {
+                if old_layout.size() == 0 {
+                    ptr::null_mut()
+                } else {
+                    src.as_ptr()
+                }
+            }
+            None => ptr::null_mut(),
+        };
+
+        if layout.size() == 0 {
+            // SAFETY: `src` is either NULL or was previously allocated with this `Allocator`
+            unsafe { libc_free(src.cast()) };
+
+            return Ok(NonNull::slice_from_raw_parts(
+                crate::alloc::dangling_from_layout(layout),
+                0,
+            ));
+        }
+
+        // SAFETY: Returns either NULL or a pointer to a memory allocation that satisfies or
+        // exceeds the given size and alignment requirements.
+        let dst = unsafe { libc_aligned_alloc(layout.align(), layout.size()) } as *mut u8;
+        let dst = NonNull::new(dst).ok_or(AllocError)?;
+
+        if flags.contains(__GFP_ZERO) {
+            // SAFETY: The preceding calls to `libc_aligned_alloc` and `NonNull::new`
+            // guarantee that `dst` points to memory of at least `layout.size()` bytes.
+            unsafe { dst.as_ptr().write_bytes(0, layout.size()) };
+        }
+
+        if !src.is_null() {
+            // SAFETY:
+            // - `src` has previously been allocated with this `Allocator`; `dst` has just been
+            //   newly allocated, hence the memory regions do not overlap.
+            // - both` src` and `dst` are properly aligned and valid for reads and writes
+            unsafe {
+                ptr::copy_nonoverlapping(
+                    src,
+                    dst.as_ptr(),
+                    cmp::min(layout.size(), old_layout.size()),
+                )
+            };
+        }
+
+        // SAFETY: `src` is either NULL or was previously allocated with this `Allocator`
+        unsafe { libc_free(src.cast()) };
+
+        Ok(NonNull::slice_from_raw_parts(dst, layout.size()))
     }
 }

From eb6f92cd3f755c179204ea1f933b07cf992892fd Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:30 +0200
Subject: [PATCH 0374/1530] rust: str: test: replace `alloc::format`

The current implementation of tests in str.rs use `format!` to format
strings for comparison, which, internally, creates a new `String`.

In order to prepare for getting rid of Rust's alloc crate, we have to
cut this dependency. Instead, implement `format!` for `CString`.

Note that for userspace tests, `Kmalloc`, which is backing `CString`'s
memory, is just a type alias to `Cmalloc`.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-27-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/str.rs | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
index 6053bc7a98d19..aff6baa521d4a 100644
--- a/rust/kernel/str.rs
+++ b/rust/kernel/str.rs
@@ -524,7 +524,28 @@ macro_rules! c_str {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use alloc::format;
+
+    struct String(CString);
+
+    impl String {
+        fn from_fmt(args: fmt::Arguments<'_>) -> Self {
+            String(CString::try_from_fmt(args).unwrap())
+        }
+    }
+
+    impl Deref for String {
+        type Target = str;
+
+        fn deref(&self) -> &str {
+            self.0.to_str().unwrap()
+        }
+    }
+
+    macro_rules! format {
+        ($($f:tt)*) => ({
+            &*String::from_fmt(kernel::fmt!($($f)*))
+        })
+    }
 
     const ALL_ASCII_CHARS: &'static str =
         "\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\x09\\x0a\\x0b\\x0c\\x0d\\x0e\\x0f\

From 8ae740c3917ff92108df17236b3cf1b9a74bd359 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:31 +0200
Subject: [PATCH 0375/1530] rust: alloc: update module comment of alloc.rs

Before we remove Rust's alloc crate, rewrite the module comment in
alloc.rs to avoid a rustdoc warning.

Besides that, the module comment in alloc.rs isn't correct anymore,
we're no longer extending Rust's alloc crate.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-28-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index c6024afa37397..f2f7f3a53d298 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
-//! Extensions to the [`alloc`] crate.
+//! Implementation of the kernel's memory allocation infrastructure.
 
 #[cfg(not(any(test, testlib)))]
 pub mod allocator;

From 392e34b6bc22077ef63abf62387ea3e9f39418c1 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:32 +0200
Subject: [PATCH 0376/1530] kbuild: rust: remove the `alloc` crate and
 `GlobalAlloc`

Now that we have our own `Allocator`, `Box` and `Vec` types we can remove
Rust's `alloc` crate and the `new_uninit` unstable feature.

Also remove `Kmalloc`'s `GlobalAlloc` implementation -- we can't remove
this in a separate patch, since the `alloc` crate requires a
`#[global_allocator]` to set, that implements `GlobalAlloc`.

Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-29-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/Makefile                     | 43 +++++---------------
 rust/exports.c                    |  1 -
 rust/kernel/alloc/allocator.rs    | 65 +------------------------------
 scripts/Makefile.build            |  4 +-
 scripts/generate_rust_analyzer.py | 11 +-----
 5 files changed, 16 insertions(+), 108 deletions(-)

diff --git a/rust/Makefile b/rust/Makefile
index 0856fd6bc6105..3678e79317f12 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -15,8 +15,8 @@ always-$(CONFIG_RUST) += libmacros.so
 no-clean-files += libmacros.so
 
 always-$(CONFIG_RUST) += bindings/bindings_generated.rs bindings/bindings_helpers_generated.rs
-obj-$(CONFIG_RUST) += alloc.o bindings.o kernel.o
-always-$(CONFIG_RUST) += exports_alloc_generated.h exports_helpers_generated.h \
+obj-$(CONFIG_RUST) += bindings.o kernel.o
+always-$(CONFIG_RUST) += exports_helpers_generated.h \
     exports_bindings_generated.h exports_kernel_generated.h
 
 always-$(CONFIG_RUST) += uapi/uapi_generated.rs
@@ -53,11 +53,6 @@ endif
 core-cfgs = \
     --cfg no_fp_fmt_parse
 
-alloc-cfgs = \
-    --cfg no_global_oom_handling \
-    --cfg no_rc \
-    --cfg no_sync
-
 quiet_cmd_rustdoc = RUSTDOC $(if $(rustdoc_host),H, ) $<
       cmd_rustdoc = \
 	OBJTREE=$(abspath $(objtree)) \
@@ -81,7 +76,7 @@ quiet_cmd_rustdoc = RUSTDOC $(if $(rustdoc_host),H, ) $<
 # command-like flags to solve the issue. Meanwhile, we use the non-custom case
 # and then retouch the generated files.
 rustdoc: rustdoc-core rustdoc-macros rustdoc-compiler_builtins \
-    rustdoc-alloc rustdoc-kernel
+    rustdoc-kernel
 	$(Q)cp $(srctree)/Documentation/images/logo.svg $(rustdoc_output)/static.files/
 	$(Q)cp $(srctree)/Documentation/images/COPYING-logo $(rustdoc_output)/static.files/
 	$(Q)find $(rustdoc_output) -name '*.html' -type f -print0 | xargs -0 sed -Ei \
@@ -108,20 +103,11 @@ rustdoc-core: $(RUST_LIB_SRC)/core/src/lib.rs FORCE
 rustdoc-compiler_builtins: $(src)/compiler_builtins.rs rustdoc-core FORCE
 	+$(call if_changed,rustdoc)
 
-# We need to allow `rustdoc::broken_intra_doc_links` because some
-# `no_global_oom_handling` functions refer to non-`no_global_oom_handling`
-# functions. Ideally `rustdoc` would have a way to distinguish broken links
-# due to things that are "configured out" vs. entirely non-existing ones.
-rustdoc-alloc: private rustc_target_flags = $(alloc-cfgs) \
-    -Arustdoc::broken_intra_doc_links
-rustdoc-alloc: $(RUST_LIB_SRC)/alloc/src/lib.rs rustdoc-core rustdoc-compiler_builtins FORCE
-	+$(call if_changed,rustdoc)
-
-rustdoc-kernel: private rustc_target_flags = --extern alloc \
+rustdoc-kernel: private rustc_target_flags = \
     --extern build_error --extern macros=$(objtree)/$(obj)/libmacros.so \
     --extern bindings --extern uapi
 rustdoc-kernel: $(src)/kernel/lib.rs rustdoc-core rustdoc-macros \
-    rustdoc-compiler_builtins rustdoc-alloc $(obj)/libmacros.so \
+    rustdoc-compiler_builtins $(obj)/libmacros.so \
     $(obj)/bindings.o FORCE
 	+$(call if_changed,rustdoc)
 
@@ -165,7 +151,7 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $<
 	mkdir -p $(objtree)/$(obj)/test/doctests/kernel; \
 	OBJTREE=$(abspath $(objtree)) \
 	$(RUSTDOC) --test $(rust_flags) \
-		-L$(objtree)/$(obj) --extern alloc --extern kernel \
+		-L$(objtree)/$(obj) --extern kernel \
 		--extern build_error --extern macros \
 		--extern bindings --extern uapi \
 		--no-run --crate-name kernel -Zunstable-options \
@@ -201,7 +187,7 @@ rusttest-macros: $(src)/macros/lib.rs FORCE
 	+$(call if_changed,rustc_test)
 	+$(call if_changed,rustdoc_test)
 
-rusttest-kernel: private rustc_target_flags = --extern alloc \
+rusttest-kernel: private rustc_target_flags = \
     --extern build_error --extern macros --extern bindings --extern uapi
 rusttest-kernel: $(src)/kernel/lib.rs \
     rusttestlib-build_error rusttestlib-macros rusttestlib-bindings \
@@ -314,9 +300,6 @@ quiet_cmd_exports = EXPORTS $@
 $(obj)/exports_core_generated.h: $(obj)/core.o FORCE
 	$(call if_changed,exports)
 
-$(obj)/exports_alloc_generated.h: $(obj)/alloc.o FORCE
-	$(call if_changed,exports)
-
 # Even though Rust kernel modules should never use the bindings directly,
 # symbols from the `bindings` crate and the C helpers need to be exported
 # because Rust generics and inlined functions may not get their code generated
@@ -363,7 +346,7 @@ quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L
 
 rust-analyzer:
 	$(Q)$(srctree)/scripts/generate_rust_analyzer.py \
-		--cfgs='core=$(core-cfgs)' --cfgs='alloc=$(alloc-cfgs)' \
+		--cfgs='core=$(core-cfgs)' \
 		$(realpath $(srctree)) $(realpath $(objtree)) \
 		$(rustc_sysroot) $(RUST_LIB_SRC) $(KBUILD_EXTMOD) > \
 		$(if $(KBUILD_EXTMOD),$(extmod_prefix),$(objtree))/rust-project.json
@@ -401,12 +384,6 @@ $(obj)/compiler_builtins.o: private rustc_objcopy = -w -W '__*'
 $(obj)/compiler_builtins.o: $(src)/compiler_builtins.rs $(obj)/core.o FORCE
 	+$(call if_changed_rule,rustc_library)
 
-$(obj)/alloc.o: private skip_clippy = 1
-$(obj)/alloc.o: private skip_flags = -Wunreachable_pub
-$(obj)/alloc.o: private rustc_target_flags = $(alloc-cfgs)
-$(obj)/alloc.o: $(RUST_LIB_SRC)/alloc/src/lib.rs $(obj)/compiler_builtins.o FORCE
-	+$(call if_changed_rule,rustc_library)
-
 $(obj)/build_error.o: $(src)/build_error.rs $(obj)/compiler_builtins.o FORCE
 	+$(call if_changed_rule,rustc_library)
 
@@ -421,9 +398,9 @@ $(obj)/uapi.o: $(src)/uapi/lib.rs \
     $(obj)/uapi/uapi_generated.rs FORCE
 	+$(call if_changed_rule,rustc_library)
 
-$(obj)/kernel.o: private rustc_target_flags = --extern alloc \
+$(obj)/kernel.o: private rustc_target_flags = \
     --extern build_error --extern macros --extern bindings --extern uapi
-$(obj)/kernel.o: $(src)/kernel/lib.rs $(obj)/alloc.o $(obj)/build_error.o \
+$(obj)/kernel.o: $(src)/kernel/lib.rs $(obj)/build_error.o \
     $(obj)/libmacros.so $(obj)/bindings.o $(obj)/uapi.o FORCE
 	+$(call if_changed_rule,rustc_library)
 
diff --git a/rust/exports.c b/rust/exports.c
index e5695f3b45b7a..82a037381798d 100644
--- a/rust/exports.c
+++ b/rust/exports.c
@@ -16,7 +16,6 @@
 #define EXPORT_SYMBOL_RUST_GPL(sym) extern int sym; EXPORT_SYMBOL_GPL(sym)
 
 #include "exports_core_generated.h"
-#include "exports_alloc_generated.h"
 #include "exports_helpers_generated.h"
 #include "exports_bindings_generated.h"
 #include "exports_kernel_generated.h"
diff --git a/rust/kernel/alloc/allocator.rs b/rust/kernel/alloc/allocator.rs
index f8a1f0feb25d2..a041bbfdabecb 100644
--- a/rust/kernel/alloc/allocator.rs
+++ b/rust/kernel/alloc/allocator.rs
@@ -8,8 +8,8 @@
 //!
 //! Reference: <https://docs.kernel.org/core-api/memory-allocation.html>
 
-use super::{flags::*, Flags};
-use core::alloc::{GlobalAlloc, Layout};
+use super::Flags;
+use core::alloc::Layout;
 use core::ptr;
 use core::ptr::NonNull;
 
@@ -54,23 +54,6 @@ fn aligned_size(new_layout: Layout) -> usize {
     layout.size()
 }
 
-/// Calls `krealloc` with a proper size to alloc a new object aligned to `new_layout`'s alignment.
-///
-/// # Safety
-///
-/// - `ptr` can be either null or a pointer which has been allocated by this allocator.
-/// - `new_layout` must have a non-zero size.
-pub(crate) unsafe fn krealloc_aligned(ptr: *mut u8, new_layout: Layout, flags: Flags) -> *mut u8 {
-    let size = aligned_size(new_layout);
-
-    // SAFETY:
-    // - `ptr` is either null or a pointer returned from a previous `k{re}alloc()` by the
-    //   function safety requirement.
-    // - `size` is greater than 0 since it's from `layout.size()` (which cannot be zero according
-    //   to the function safety requirement)
-    unsafe { bindings::krealloc(ptr as *const core::ffi::c_void, size, flags.0) as *mut u8 }
-}
-
 /// # Invariants
 ///
 /// One of the following: `krealloc`, `vrealloc`, `kvrealloc`.
@@ -156,43 +139,6 @@ unsafe impl Allocator for Kmalloc {
     }
 }
 
-// SAFETY: TODO.
-unsafe impl GlobalAlloc for Kmalloc {
-    unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
-        // SAFETY: `ptr::null_mut()` is null and `layout` has a non-zero size by the function safety
-        // requirement.
-        unsafe { krealloc_aligned(ptr::null_mut(), layout, GFP_KERNEL) }
-    }
-
-    unsafe fn dealloc(&self, ptr: *mut u8, _layout: Layout) {
-        // SAFETY: TODO.
-        unsafe {
-            bindings::kfree(ptr as *const core::ffi::c_void);
-        }
-    }
-
-    unsafe fn realloc(&self, ptr: *mut u8, layout: Layout, new_size: usize) -> *mut u8 {
-        // SAFETY:
-        // - `new_size`, when rounded up to the nearest multiple of `layout.align()`, will not
-        //   overflow `isize` by the function safety requirement.
-        // - `layout.align()` is a proper alignment (i.e. not zero and must be a power of two).
-        let layout = unsafe { Layout::from_size_align_unchecked(new_size, layout.align()) };
-
-        // SAFETY:
-        // - `ptr` is either null or a pointer allocated by this allocator by the function safety
-        //   requirement.
-        // - the size of `layout` is not zero because `new_size` is not zero by the function safety
-        //   requirement.
-        unsafe { krealloc_aligned(ptr, layout, GFP_KERNEL) }
-    }
-
-    unsafe fn alloc_zeroed(&self, layout: Layout) -> *mut u8 {
-        // SAFETY: `ptr::null_mut()` is null and `layout` has a non-zero size by the function safety
-        // requirement.
-        unsafe { krealloc_aligned(ptr::null_mut(), layout, GFP_KERNEL | __GFP_ZERO) }
-    }
-}
-
 // SAFETY: `realloc` delegates to `ReallocFunc::call`, which guarantees that
 // - memory remains valid until it is explicitly freed,
 // - passing a pointer to a valid memory allocation is OK,
@@ -240,10 +186,3 @@ unsafe impl Allocator for KVmalloc {
         unsafe { ReallocFunc::KVREALLOC.call(ptr, layout, old_layout, flags) }
     }
 }
-
-#[global_allocator]
-static ALLOCATOR: Kmalloc = Kmalloc;
-
-// See <https://github.com/rust-lang/rust/pull/86844>.
-#[no_mangle]
-static __rust_no_alloc_shim_is_unstable: u8 = 0;
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 64518c2f3d9c3..2bba59e790b8a 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -248,7 +248,7 @@ $(obj)/%.lst: $(obj)/%.c FORCE
 # Compile Rust sources (.rs)
 # ---------------------------------------------------------------------------
 
-rust_allowed_features := arbitrary_self_types,lint_reasons,new_uninit
+rust_allowed_features := arbitrary_self_types,lint_reasons
 
 # `--out-dir` is required to avoid temporaries being created by `rustc` in the
 # current working directory, which may be not accessible in the out-of-tree
@@ -258,7 +258,7 @@ rust_common_cmd = \
 	-Zallow-features=$(rust_allowed_features) \
 	-Zcrate-attr=no_std \
 	-Zcrate-attr='feature($(rust_allowed_features))' \
-	-Zunstable-options --extern force:alloc --extern kernel \
+	-Zunstable-options --extern kernel \
 	--crate-type rlib -L $(objtree)/rust/ \
 	--crate-name $(basename $(notdir $@)) \
 	--sysroot=/dev/null \
diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py
index d2bc63cde8c6a..09e1d166d8d23 100755
--- a/scripts/generate_rust_analyzer.py
+++ b/scripts/generate_rust_analyzer.py
@@ -64,13 +64,6 @@ def append_crate(display_name, root_module, deps, cfg=[], is_workspace_member=Tr
         [],
     )
 
-    append_crate(
-        "alloc",
-        sysroot_src / "alloc" / "src" / "lib.rs",
-        ["core", "compiler_builtins"],
-        cfg=crates_cfgs.get("alloc", []),
-    )
-
     append_crate(
         "macros",
         srctree / "rust" / "macros" / "lib.rs",
@@ -96,7 +89,7 @@ def append_crate(display_name, root_module, deps, cfg=[], is_workspace_member=Tr
     append_crate(
         "kernel",
         srctree / "rust" / "kernel" / "lib.rs",
-        ["core", "alloc", "macros", "build_error", "bindings"],
+        ["core", "macros", "build_error", "bindings"],
         cfg=cfg,
     )
     crates[-1]["source"] = {
@@ -133,7 +126,7 @@ def is_root_crate(build_file, target):
             append_crate(
                 name,
                 path,
-                ["core", "alloc", "kernel"],
+                ["core", "kernel"],
                 cfg=cfg,
             )
 

From 6ce162a002657910104c7a07fb50017681bc476c Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 4 Oct 2024 17:41:33 +0200
Subject: [PATCH 0377/1530] MAINTAINERS: add entry for the Rust `alloc` module

Add maintainers entry for the Rust `alloc` module.

Currently, this includes the `Allocator` API itself, `Allocator`
implementations, such as `Kmalloc` or `Vmalloc`, as well as the kernel's
implementation of the primary memory allocation data structures, `Box`
and `Vec`.

Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20241004154149.93856-30-dakr@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 MAINTAINERS | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 3380b87dcbb98..b77f4495dcf42 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20230,6 +20230,13 @@ F:	scripts/*rust*
 F:	tools/testing/selftests/rust/
 K:	\b(?i:rust)\b
 
+RUST [ALLOC]
+M:	Danilo Krummrich <dakr@kernel.org>
+L:	rust-for-linux@vger.kernel.org
+S:	Maintained
+F:	rust/kernel/alloc.rs
+F:	rust/kernel/alloc/
+
 RXRPC SOCKETS (AF_RXRPC)
 M:	David Howells <dhowells@redhat.com>
 M:	Marc Dionne <marc.dionne@auristor.com>

From f3845d7d7145e325cf6512d2b7e805acd08ea291 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sun, 15 Sep 2024 13:56:29 +0100
Subject: [PATCH 0378/1530] scsi: bfa: Remove unused bfa_core code

bfa_get_pciids and bfa_cfg_get_min aren't called anywhere; remove them
together with the bfa_pciid_s used by bfa_get_pciids.

(Build tested, I don't have the card)

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://lore.kernel.org/r/20240915125633.25036-2-linux@treblig.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/bfa/bfa.h      | 10 ----------
 drivers/scsi/bfa/bfa_core.c | 35 -----------------------------------
 2 files changed, 45 deletions(-)

diff --git a/drivers/scsi/bfa/bfa.h b/drivers/scsi/bfa/bfa.h
index 4cb9249e583cc..a6b8c4ddea19d 100644
--- a/drivers/scsi/bfa/bfa.h
+++ b/drivers/scsi/bfa/bfa.h
@@ -138,14 +138,6 @@ bfa_reqq_winit(struct bfa_reqq_wait_s *wqe, void (*qresume) (void *cbarg),
 	} while (0)
 
 
-/*
- * PCI devices supported by the current BFA
- */
-struct bfa_pciid_s {
-	u16	device_id;
-	u16	vendor_id;
-};
-
 extern char     bfa_version[];
 
 struct bfa_iocfc_regs_s {
@@ -408,9 +400,7 @@ int bfa_iocfc_get_pbc_vports(struct bfa_s *bfa,
 	(((&(_bfa)->modules.dconf_mod)->min_cfg)		\
 	 ? BFA_LUNMASK_MINCFG : ((bfa_get_lun_mask(_bfa))->status))
 
-void bfa_get_pciids(struct bfa_pciid_s **pciids, int *npciids);
 void bfa_cfg_get_default(struct bfa_iocfc_cfg_s *cfg);
-void bfa_cfg_get_min(struct bfa_iocfc_cfg_s *cfg);
 void bfa_cfg_get_meminfo(struct bfa_iocfc_cfg_s *cfg,
 			struct bfa_meminfo_s *meminfo,
 			struct bfa_s *bfa);
diff --git a/drivers/scsi/bfa/bfa_core.c b/drivers/scsi/bfa/bfa_core.c
index 3438d0b8ba062..a99a101b95efe 100644
--- a/drivers/scsi/bfa/bfa_core.c
+++ b/drivers/scsi/bfa/bfa_core.c
@@ -1933,24 +1933,6 @@ bfa_comp_free(struct bfa_s *bfa, struct list_head *comp_q)
 	}
 }
 
-/*
- * Return the list of PCI vendor/device id lists supported by this
- * BFA instance.
- */
-void
-bfa_get_pciids(struct bfa_pciid_s **pciids, int *npciids)
-{
-	static struct bfa_pciid_s __pciids[] = {
-		{BFA_PCI_VENDOR_ID_BROCADE, BFA_PCI_DEVICE_ID_FC_8G2P},
-		{BFA_PCI_VENDOR_ID_BROCADE, BFA_PCI_DEVICE_ID_FC_8G1P},
-		{BFA_PCI_VENDOR_ID_BROCADE, BFA_PCI_DEVICE_ID_CT},
-		{BFA_PCI_VENDOR_ID_BROCADE, BFA_PCI_DEVICE_ID_CT_FC},
-	};
-
-	*npciids = ARRAY_SIZE(__pciids);
-	*pciids = __pciids;
-}
-
 /*
  * Use this function query the default struct bfa_iocfc_cfg_s value (compiled
  * into BFA layer). The OS driver can then turn back and overwrite entries that
@@ -1987,20 +1969,3 @@ bfa_cfg_get_default(struct bfa_iocfc_cfg_s *cfg)
 	cfg->drvcfg.delay_comp = BFA_FALSE;
 
 }
-
-void
-bfa_cfg_get_min(struct bfa_iocfc_cfg_s *cfg)
-{
-	bfa_cfg_get_default(cfg);
-	cfg->fwcfg.num_ioim_reqs   = BFA_IOIM_MIN;
-	cfg->fwcfg.num_tskim_reqs  = BFA_TSKIM_MIN;
-	cfg->fwcfg.num_fcxp_reqs   = BFA_FCXP_MIN;
-	cfg->fwcfg.num_uf_bufs     = BFA_UF_MIN;
-	cfg->fwcfg.num_rports      = BFA_RPORT_MIN;
-	cfg->fwcfg.num_fwtio_reqs = 0;
-
-	cfg->drvcfg.num_sgpgs      = BFA_SGPG_MIN;
-	cfg->drvcfg.num_reqq_elems = BFA_REQQ_NELEMS_MIN;
-	cfg->drvcfg.num_rspq_elems = BFA_RSPQ_NELEMS_MIN;
-	cfg->drvcfg.min_cfg	   = BFA_TRUE;
-}

From 0604cf11cd56179fa86baeb030d8862489d341e1 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sun, 15 Sep 2024 13:56:30 +0100
Subject: [PATCH 0379/1530] scsi: bfa: Remove unused bfa_svc code

These functions aren't called anywhere, remove them.

Build tested only.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://lore.kernel.org/r/20240915125633.25036-3-linux@treblig.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/bfa/bfa_modules.h |  1 -
 drivers/scsi/bfa/bfa_svc.c     | 72 ----------------------------------
 drivers/scsi/bfa/bfa_svc.h     |  5 ---
 3 files changed, 78 deletions(-)

diff --git a/drivers/scsi/bfa/bfa_modules.h b/drivers/scsi/bfa/bfa_modules.h
index 578e7678b056e..ed29ebda30da2 100644
--- a/drivers/scsi/bfa/bfa_modules.h
+++ b/drivers/scsi/bfa/bfa_modules.h
@@ -113,7 +113,6 @@ void bfa_sgpg_meminfo(struct bfa_iocfc_cfg_s *, struct bfa_meminfo_s *,
 		struct bfa_s *);
 void bfa_sgpg_attach(struct bfa_s *, void *bfad, struct bfa_iocfc_cfg_s *,
 		struct bfa_pcidev_s *);
-void bfa_uf_iocdisable(struct bfa_s *);
 void bfa_uf_meminfo(struct bfa_iocfc_cfg_s *, struct bfa_meminfo_s *,
 		struct bfa_s *);
 void bfa_uf_attach(struct bfa_s *, void *, struct bfa_iocfc_cfg_s *,
diff --git a/drivers/scsi/bfa/bfa_svc.c b/drivers/scsi/bfa/bfa_svc.c
index 9f33aa303b189..df33afaaa6735 100644
--- a/drivers/scsi/bfa/bfa_svc.c
+++ b/drivers/scsi/bfa/bfa_svc.c
@@ -913,14 +913,6 @@ bfa_fcxp_get_reqbuf(struct bfa_fcxp_s *fcxp)
 	return reqbuf;
 }
 
-u32
-bfa_fcxp_get_reqbufsz(struct bfa_fcxp_s *fcxp)
-{
-	struct bfa_fcxp_mod_s *mod = fcxp->fcxp_mod;
-
-	return mod->req_pld_sz;
-}
-
 /*
  * Get the internal response buffer pointer
  *
@@ -1023,21 +1015,6 @@ bfa_fcxp_send(struct bfa_fcxp_s *fcxp, struct bfa_rport_s *rport,
 	bfa_fcxp_queue(fcxp, send_req);
 }
 
-/*
- * Abort a BFA FCXP
- *
- * @param[in]	fcxp	BFA fcxp pointer
- *
- * @return		void
- */
-bfa_status_t
-bfa_fcxp_abort(struct bfa_fcxp_s *fcxp)
-{
-	bfa_trc(fcxp->fcxp_mod->bfa, fcxp->fcxp_tag);
-	WARN_ON(1);
-	return BFA_STATUS_OK;
-}
-
 void
 bfa_fcxp_req_rsp_alloc_wait(struct bfa_s *bfa, struct bfa_fcxp_wqe_s *wqe,
 	       bfa_fcxp_alloc_cbfn_t alloc_cbfn, void *alloc_cbarg,
@@ -3857,15 +3834,6 @@ bfa_fcport_clr_hardalpa(struct bfa_s *bfa)
 	return BFA_STATUS_OK;
 }
 
-bfa_boolean_t
-bfa_fcport_get_hardalpa(struct bfa_s *bfa, u8 *alpa)
-{
-	struct bfa_fcport_s *fcport = BFA_FCPORT_MOD(bfa);
-
-	*alpa = fcport->cfg.hardalpa;
-	return fcport->cfg.cfg_hardalpa;
-}
-
 u8
 bfa_fcport_get_myalpa(struct bfa_s *bfa)
 {
@@ -3923,17 +3891,6 @@ bfa_fcport_set_tx_bbcredit(struct bfa_s *bfa, u16 tx_bbcredit)
 /*
  * Get port attributes.
  */
-
-wwn_t
-bfa_fcport_get_wwn(struct bfa_s *bfa, bfa_boolean_t node)
-{
-	struct bfa_fcport_s *fcport = BFA_FCPORT_MOD(bfa);
-	if (node)
-		return fcport->nwwn;
-	else
-		return fcport->pwwn;
-}
-
 void
 bfa_fcport_get_attr(struct bfa_s *bfa, struct bfa_port_attr_s *attr)
 {
@@ -4105,18 +4062,6 @@ bfa_fcport_is_ratelim(struct bfa_s *bfa)
 
 }
 
-/*
- *	Enable/Disable FAA feature in port config
- */
-void
-bfa_fcport_cfg_faa(struct bfa_s *bfa, u8 state)
-{
-	struct bfa_fcport_s *fcport = BFA_FCPORT_MOD(bfa);
-
-	bfa_trc(bfa, state);
-	fcport->cfg.faa_state = state;
-}
-
 /*
  * Get default minimum ratelim speed
  */
@@ -5528,23 +5473,6 @@ uf_recv(struct bfa_s *bfa, struct bfi_uf_frm_rcvd_s *m)
 		bfa_cb_queue(bfa, &uf->hcb_qe, __bfa_cb_uf_recv, uf);
 }
 
-void
-bfa_uf_iocdisable(struct bfa_s *bfa)
-{
-	struct bfa_uf_mod_s *ufm = BFA_UF_MOD(bfa);
-	struct bfa_uf_s *uf;
-	struct list_head *qe, *qen;
-
-	/* Enqueue unused uf resources to free_q */
-	list_splice_tail_init(&ufm->uf_unused_q, &ufm->uf_free_q);
-
-	list_for_each_safe(qe, qen, &ufm->uf_posted_q) {
-		uf = (struct bfa_uf_s *) qe;
-		list_del(&uf->qe);
-		bfa_uf_put(ufm, uf);
-	}
-}
-
 void
 bfa_uf_start(struct bfa_s *bfa)
 {
diff --git a/drivers/scsi/bfa/bfa_svc.h b/drivers/scsi/bfa/bfa_svc.h
index 26eeee82bedc6..99a960a8a2dbb 100644
--- a/drivers/scsi/bfa/bfa_svc.h
+++ b/drivers/scsi/bfa/bfa_svc.h
@@ -587,14 +587,12 @@ bfa_status_t bfa_fcport_cfg_topology(struct bfa_s *bfa,
 enum bfa_port_topology bfa_fcport_get_topology(struct bfa_s *bfa);
 enum bfa_port_topology bfa_fcport_get_cfg_topology(struct bfa_s *bfa);
 bfa_status_t bfa_fcport_cfg_hardalpa(struct bfa_s *bfa, u8 alpa);
-bfa_boolean_t bfa_fcport_get_hardalpa(struct bfa_s *bfa, u8 *alpa);
 u8 bfa_fcport_get_myalpa(struct bfa_s *bfa);
 bfa_status_t bfa_fcport_clr_hardalpa(struct bfa_s *bfa);
 bfa_status_t bfa_fcport_cfg_maxfrsize(struct bfa_s *bfa, u16 maxsize);
 u16 bfa_fcport_get_maxfrsize(struct bfa_s *bfa);
 u8 bfa_fcport_get_rx_bbcredit(struct bfa_s *bfa);
 void bfa_fcport_get_attr(struct bfa_s *bfa, struct bfa_port_attr_s *attr);
-wwn_t bfa_fcport_get_wwn(struct bfa_s *bfa, bfa_boolean_t node);
 void bfa_fcport_event_register(struct bfa_s *bfa,
 			void (*event_cbfn) (void *cbarg,
 			enum bfa_port_linkstate event), void *event_cbarg);
@@ -619,7 +617,6 @@ bfa_boolean_t bfa_fcport_is_trunk_enabled(struct bfa_s *bfa);
 void bfa_fcport_dportenable(struct bfa_s *bfa);
 void bfa_fcport_dportdisable(struct bfa_s *bfa);
 bfa_status_t bfa_fcport_is_pbcdisabled(struct bfa_s *bfa);
-void bfa_fcport_cfg_faa(struct bfa_s *bfa, u8 state);
 bfa_status_t bfa_fcport_cfg_bbcr(struct bfa_s *bfa,
 			bfa_boolean_t on_off, u8 bb_scn);
 bfa_status_t bfa_fcport_get_bbcr_attr(struct bfa_s *bfa,
@@ -687,8 +684,6 @@ void bfa_fcxp_send(struct bfa_fcxp_s *fcxp, struct bfa_rport_s *rport,
 		   bfa_cb_fcxp_send_t cbfn,
 		   void *cbarg,
 		   u32 rsp_maxlen, u8 rsp_timeout);
-bfa_status_t bfa_fcxp_abort(struct bfa_fcxp_s *fcxp);
-u32 bfa_fcxp_get_reqbufsz(struct bfa_fcxp_s *fcxp);
 u32 bfa_fcxp_get_maxrsp(struct bfa_s *bfa);
 void bfa_fcxp_res_recfg(struct bfa_s *bfa, u16 num_fcxp_fw);
 

From b74448006a67debcd5299c9ab16b2e8ca748bee6 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sun, 15 Sep 2024 13:56:31 +0100
Subject: [PATCH 0380/1530] scsi: bfa: Remove unused bfa_ioc code

These functions aren't called anywhere, remove them.

Build tested only.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://lore.kernel.org/r/20240915125633.25036-4-linux@treblig.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/bfa/bfa_ioc.c | 21 ---------------------
 drivers/scsi/bfa/bfa_ioc.h |  2 --
 2 files changed, 23 deletions(-)

diff --git a/drivers/scsi/bfa/bfa_ioc.c b/drivers/scsi/bfa/bfa_ioc.c
index ea2f107f564cd..aa68d61a2d0d3 100644
--- a/drivers/scsi/bfa/bfa_ioc.c
+++ b/drivers/scsi/bfa/bfa_ioc.c
@@ -2254,33 +2254,12 @@ bfa_ioc_boot(struct bfa_ioc_s *ioc, u32 boot_type, u32 boot_env)
 	return status;
 }
 
-/*
- * Enable/disable IOC failure auto recovery.
- */
-void
-bfa_ioc_auto_recover(bfa_boolean_t auto_recover)
-{
-	bfa_auto_recover = auto_recover;
-}
-
-
-
 bfa_boolean_t
 bfa_ioc_is_operational(struct bfa_ioc_s *ioc)
 {
 	return bfa_fsm_cmp_state(ioc, bfa_ioc_sm_op);
 }
 
-bfa_boolean_t
-bfa_ioc_is_initialized(struct bfa_ioc_s *ioc)
-{
-	u32 r32 = bfa_ioc_get_cur_ioc_fwstate(ioc);
-
-	return ((r32 != BFI_IOC_UNINIT) &&
-		(r32 != BFI_IOC_INITING) &&
-		(r32 != BFI_IOC_MEMTEST));
-}
-
 bfa_boolean_t
 bfa_ioc_msgget(struct bfa_ioc_s *ioc, void *mbmsg)
 {
diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h
index 3ec10503caff9..d70332e9ad6d7 100644
--- a/drivers/scsi/bfa/bfa_ioc.h
+++ b/drivers/scsi/bfa/bfa_ioc.h
@@ -919,7 +919,6 @@ void bfa_ioc_ct2_poweron(struct bfa_ioc_s *ioc);
 
 void bfa_ioc_attach(struct bfa_ioc_s *ioc, void *bfa,
 		struct bfa_ioc_cbfn_s *cbfn, struct bfa_timer_mod_s *timer_mod);
-void bfa_ioc_auto_recover(bfa_boolean_t auto_recover);
 void bfa_ioc_detach(struct bfa_ioc_s *ioc);
 void bfa_ioc_suspend(struct bfa_ioc_s *ioc);
 void bfa_ioc_pci_init(struct bfa_ioc_s *ioc, struct bfa_pcidev_s *pcidev,
@@ -934,7 +933,6 @@ bfa_status_t bfa_ioc_boot(struct bfa_ioc_s *ioc, u32 boot_type,
 void bfa_ioc_isr(struct bfa_ioc_s *ioc, struct bfi_mbmsg_s *msg);
 void bfa_ioc_error_isr(struct bfa_ioc_s *ioc);
 bfa_boolean_t bfa_ioc_is_operational(struct bfa_ioc_s *ioc);
-bfa_boolean_t bfa_ioc_is_initialized(struct bfa_ioc_s *ioc);
 bfa_boolean_t bfa_ioc_is_disabled(struct bfa_ioc_s *ioc);
 bfa_boolean_t bfa_ioc_is_acq_addr(struct bfa_ioc_s *ioc);
 bfa_boolean_t bfa_ioc_fw_mismatch(struct bfa_ioc_s *ioc);

From 372dcc01616e41e06016044c330caed7117689cf Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sun, 15 Sep 2024 13:56:32 +0100
Subject: [PATCH 0381/1530] scsi: bfa: Remove unused bfa_fcs code

These functions aren't called anywhere, remove them.

Build tested only.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://lore.kernel.org/r/20240915125633.25036-5-linux@treblig.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/bfa/bfa_defs_fcs.h  |  22 -----
 drivers/scsi/bfa/bfa_fcs.h       |  12 ---
 drivers/scsi/bfa/bfa_fcs_lport.c | 142 -------------------------------
 drivers/scsi/bfa/bfa_fcs_rport.c |  36 --------
 4 files changed, 212 deletions(-)

diff --git a/drivers/scsi/bfa/bfa_defs_fcs.h b/drivers/scsi/bfa/bfa_defs_fcs.h
index 5e36620425ac7..760606062c660 100644
--- a/drivers/scsi/bfa/bfa_defs_fcs.h
+++ b/drivers/scsi/bfa/bfa_defs_fcs.h
@@ -124,28 +124,6 @@ enum bfa_lport_offline_reason {
 	BFA_LPORT_OFFLINE_FAB_LOGOUT,
 };
 
-/*
- * FCS lport info.
- */
-struct bfa_lport_info_s {
-	u8	 port_type;	/* bfa_lport_type_t : physical or
-	 * virtual */
-	u8	 port_state;	/* one of bfa_lport_state values */
-	u8	 offline_reason;	/* one of bfa_lport_offline_reason_t
-	 * values */
-	wwn_t	   port_wwn;
-	wwn_t	   node_wwn;
-
-	/*
-	 * following 4 feilds are valid for Physical Ports only
-	 */
-	u32	max_vports_supp;	/* Max supported vports */
-	u32	num_vports_inuse;	/* Num of in use vports */
-	u32	max_rports_supp;	/* Max supported rports */
-	u32	num_rports_inuse;	/* Num of doscovered rports */
-
-};
-
 /*
  * FCS port statistics
  */
diff --git a/drivers/scsi/bfa/bfa_fcs.h b/drivers/scsi/bfa/bfa_fcs.h
index 9788354b90da7..19903539a08dc 100644
--- a/drivers/scsi/bfa/bfa_fcs.h
+++ b/drivers/scsi/bfa/bfa_fcs.h
@@ -373,15 +373,11 @@ bfa_boolean_t   bfa_fcs_lport_is_online(struct bfa_fcs_lport_s *port);
 struct bfa_fcs_lport_s *bfa_fcs_get_base_port(struct bfa_fcs_s *fcs);
 void bfa_fcs_lport_get_rport_quals(struct bfa_fcs_lport_s *port,
 			struct bfa_rport_qualifier_s rport[], int *nrports);
-wwn_t bfa_fcs_lport_get_rport(struct bfa_fcs_lport_s *port, wwn_t wwn,
-			      int index, int nrports, bfa_boolean_t bwwn);
 
 struct bfa_fcs_lport_s *bfa_fcs_lookup_port(struct bfa_fcs_s *fcs,
 					    u16 vf_id, wwn_t lpwwn);
 
 void bfa_fcs_lport_set_symname(struct bfa_fcs_lport_s *port, char *symname);
-void bfa_fcs_lport_get_info(struct bfa_fcs_lport_s *port,
-			    struct bfa_lport_info_s *port_info);
 void bfa_fcs_lport_get_attr(struct bfa_fcs_lport_s *port,
 			    struct bfa_lport_attr_s *port_attr);
 void bfa_fcs_lport_get_stats(struct bfa_fcs_lport_s *fcs_port,
@@ -416,8 +412,6 @@ struct bfa_fcs_rport_s *bfa_fcs_lport_get_rport_by_old_pid(
 		struct bfa_fcs_lport_s *port, u32 pid);
 struct bfa_fcs_rport_s *bfa_fcs_lport_get_rport_by_pwwn(
 		struct bfa_fcs_lport_s *port, wwn_t pwwn);
-struct bfa_fcs_rport_s *bfa_fcs_lport_get_rport_by_nwwn(
-		struct bfa_fcs_lport_s *port, wwn_t nwwn);
 struct bfa_fcs_rport_s *bfa_fcs_lport_get_rport_by_qualifier(
 		struct bfa_fcs_lport_s *port, wwn_t pwwn, u32 pid);
 void            bfa_fcs_lport_add_rport(struct bfa_fcs_lport_s *port,
@@ -486,7 +480,6 @@ bfa_status_t bfa_fcs_pbc_vport_create(struct bfa_fcs_vport_s *vport,
 				      struct bfa_fcs_s *fcs, u16 vf_id,
 				      struct bfa_lport_cfg_s *port_cfg,
 				      struct bfad_vport_s *vport_drv);
-bfa_boolean_t bfa_fcs_is_pbc_vport(struct bfa_fcs_vport_s *vport);
 bfa_status_t bfa_fcs_vport_delete(struct bfa_fcs_vport_s *vport);
 bfa_status_t bfa_fcs_vport_start(struct bfa_fcs_vport_s *vport);
 bfa_status_t bfa_fcs_vport_stop(struct bfa_fcs_vport_s *vport);
@@ -494,7 +487,6 @@ void bfa_fcs_vport_get_attr(struct bfa_fcs_vport_s *vport,
 			    struct bfa_vport_attr_s *vport_attr);
 struct bfa_fcs_vport_s *bfa_fcs_vport_lookup(struct bfa_fcs_s *fcs,
 					     u16 vf_id, wwn_t vpwwn);
-void bfa_fcs_vport_cleanup(struct bfa_fcs_vport_s *vport);
 void bfa_fcs_vport_online(struct bfa_fcs_vport_s *vport);
 void bfa_fcs_vport_offline(struct bfa_fcs_vport_s *vport);
 void bfa_fcs_vport_delete_comp(struct bfa_fcs_vport_s *vport);
@@ -623,8 +615,6 @@ void bfa_fcs_rport_get_attr(struct bfa_fcs_rport_s *rport,
 			struct bfa_rport_attr_s *attr);
 struct bfa_fcs_rport_s *bfa_fcs_rport_lookup(struct bfa_fcs_lport_s *port,
 					     wwn_t rpwwn);
-struct bfa_fcs_rport_s *bfa_fcs_rport_lookup_by_nwwn(
-	struct bfa_fcs_lport_s *port, wwn_t rnwwn);
 void bfa_fcs_rport_set_del_timeout(u8 rport_tmo);
 void bfa_fcs_rport_set_max_logins(u32 max_logins);
 void bfa_fcs_rport_uf_recv(struct bfa_fcs_rport_s *rport,
@@ -633,8 +623,6 @@ void bfa_fcs_rport_scn(struct bfa_fcs_rport_s *rport);
 
 struct bfa_fcs_rport_s *bfa_fcs_rport_create(struct bfa_fcs_lport_s *port,
 	 u32 pid);
-void bfa_fcs_rport_start(struct bfa_fcs_lport_s *port, struct fchs_s *rx_fchs,
-			 struct fc_logi_s *plogi_rsp);
 void bfa_fcs_rport_plogi_create(struct bfa_fcs_lport_s *port,
 				struct fchs_s *rx_fchs,
 				struct fc_logi_s *plogi);
diff --git a/drivers/scsi/bfa/bfa_fcs_lport.c b/drivers/scsi/bfa/bfa_fcs_lport.c
index 966bf6cc6dd90..9a85f417018f9 100644
--- a/drivers/scsi/bfa/bfa_fcs_lport.c
+++ b/drivers/scsi/bfa/bfa_fcs_lport.c
@@ -937,25 +937,6 @@ bfa_fcs_lport_get_rport_by_pwwn(struct bfa_fcs_lport_s *port, wwn_t pwwn)
 	return NULL;
 }
 
-/*
- *   NWWN based Lookup for a R-Port in the Port R-Port Queue
- */
-struct bfa_fcs_rport_s *
-bfa_fcs_lport_get_rport_by_nwwn(struct bfa_fcs_lport_s *port, wwn_t nwwn)
-{
-	struct bfa_fcs_rport_s *rport;
-	struct list_head	*qe;
-
-	list_for_each(qe, &port->rport_q) {
-		rport = (struct bfa_fcs_rport_s *) qe;
-		if (wwn_is_equal(rport->nwwn, nwwn))
-			return rport;
-	}
-
-	bfa_trc(port->fcs, nwwn);
-	return NULL;
-}
-
 /*
  * PWWN & PID based Lookup for a R-Port in the Port R-Port Queue
  */
@@ -5645,54 +5626,6 @@ bfa_fcs_get_base_port(struct bfa_fcs_s *fcs)
 	return &fcs->fabric.bport;
 }
 
-wwn_t
-bfa_fcs_lport_get_rport(struct bfa_fcs_lport_s *port, wwn_t wwn, int index,
-		int nrports, bfa_boolean_t bwwn)
-{
-	struct list_head	*qh, *qe;
-	struct bfa_fcs_rport_s *rport = NULL;
-	int	i;
-	struct bfa_fcs_s	*fcs;
-
-	if (port == NULL || nrports == 0)
-		return (wwn_t) 0;
-
-	fcs = port->fcs;
-	bfa_trc(fcs, (u32) nrports);
-
-	i = 0;
-	qh = &port->rport_q;
-	qe = bfa_q_first(qh);
-
-	while ((qe != qh) && (i < nrports)) {
-		rport = (struct bfa_fcs_rport_s *) qe;
-		if (bfa_ntoh3b(rport->pid) > 0xFFF000) {
-			qe = bfa_q_next(qe);
-			bfa_trc(fcs, (u32) rport->pwwn);
-			bfa_trc(fcs, rport->pid);
-			bfa_trc(fcs, i);
-			continue;
-		}
-
-		if (bwwn) {
-			if (!memcmp(&wwn, &rport->pwwn, 8))
-				break;
-		} else {
-			if (i == index)
-				break;
-		}
-
-		i++;
-		qe = bfa_q_next(qe);
-	}
-
-	bfa_trc(fcs, i);
-	if (rport)
-		return rport->pwwn;
-	else
-		return (wwn_t) 0;
-}
-
 void
 bfa_fcs_lport_get_rport_quals(struct bfa_fcs_lport_s *port,
 		struct bfa_rport_qualifier_s rports[], int *nrports)
@@ -5823,54 +5756,6 @@ bfa_fcs_lookup_port(struct bfa_fcs_s *fcs, u16 vf_id, wwn_t lpwwn)
 	return NULL;
 }
 
-/*
- *  API corresponding to NPIV_VPORT_GETINFO.
- */
-void
-bfa_fcs_lport_get_info(struct bfa_fcs_lport_s *port,
-	 struct bfa_lport_info_s *port_info)
-{
-
-	bfa_trc(port->fcs, port->fabric->fabric_name);
-
-	if (port->vport == NULL) {
-		/*
-		 * This is a Physical port
-		 */
-		port_info->port_type = BFA_LPORT_TYPE_PHYSICAL;
-
-		/*
-		 * @todo : need to fix the state & reason
-		 */
-		port_info->port_state = 0;
-		port_info->offline_reason = 0;
-
-		port_info->port_wwn = bfa_fcs_lport_get_pwwn(port);
-		port_info->node_wwn = bfa_fcs_lport_get_nwwn(port);
-
-		port_info->max_vports_supp =
-			bfa_lps_get_max_vport(port->fcs->bfa);
-		port_info->num_vports_inuse =
-			port->fabric->num_vports;
-		port_info->max_rports_supp = BFA_FCS_MAX_RPORTS_SUPP;
-		port_info->num_rports_inuse = port->num_rports;
-	} else {
-		/*
-		 * This is a virtual port
-		 */
-		port_info->port_type = BFA_LPORT_TYPE_VIRTUAL;
-
-		/*
-		 * @todo : need to fix the state & reason
-		 */
-		port_info->port_state = 0;
-		port_info->offline_reason = 0;
-
-		port_info->port_wwn = bfa_fcs_lport_get_pwwn(port);
-		port_info->node_wwn = bfa_fcs_lport_get_nwwn(port);
-	}
-}
-
 void
 bfa_fcs_lport_get_stats(struct bfa_fcs_lport_s *fcs_port,
 	 struct bfa_lport_stats_s *port_stats)
@@ -6567,15 +6452,6 @@ bfa_fcs_vport_offline(struct bfa_fcs_vport_s *vport)
 	bfa_sm_send_event(vport, BFA_FCS_VPORT_SM_OFFLINE);
 }
 
-/*
- * Cleanup notification from fabric SM on link timer expiry.
- */
-void
-bfa_fcs_vport_cleanup(struct bfa_fcs_vport_s *vport)
-{
-	vport->vport_stats.fab_cleanup++;
-}
-
 /*
  * Stop notification from fabric SM. To be invoked from within FCS.
  */
@@ -6698,24 +6574,6 @@ bfa_fcs_pbc_vport_create(struct bfa_fcs_vport_s *vport, struct bfa_fcs_s *fcs,
 	return rc;
 }
 
-/*
- *	Use this function to findout if this is a pbc vport or not.
- *
- * @param[in] vport - pointer to bfa_fcs_vport_t.
- *
- * @returns None
- */
-bfa_boolean_t
-bfa_fcs_is_pbc_vport(struct bfa_fcs_vport_s *vport)
-{
-
-	if (vport && (vport->lport.port_cfg.preboot_vp == BFA_TRUE))
-		return BFA_TRUE;
-	else
-		return BFA_FALSE;
-
-}
-
 /*
  * Use this function initialize the vport.
  *
diff --git a/drivers/scsi/bfa/bfa_fcs_rport.c b/drivers/scsi/bfa/bfa_fcs_rport.c
index ce52a9c88ae63..d4bde9bbe75ba 100644
--- a/drivers/scsi/bfa/bfa_fcs_rport.c
+++ b/drivers/scsi/bfa/bfa_fcs_rport.c
@@ -2646,27 +2646,6 @@ bfa_fcs_rport_create_by_wwn(struct bfa_fcs_lport_s *port, wwn_t rpwwn)
 	bfa_sm_send_event(rport, RPSM_EVENT_ADDRESS_DISC);
 	return rport;
 }
-/*
- * Called by bport in private loop topology to indicate that a
- * rport has been discovered and plogi has been completed.
- *
- * @param[in] port	- base port or vport
- * @param[in] rpid	- remote port ID
- */
-void
-bfa_fcs_rport_start(struct bfa_fcs_lport_s *port, struct fchs_s *fchs,
-	 struct fc_logi_s *plogi)
-{
-	struct bfa_fcs_rport_s *rport;
-
-	rport = bfa_fcs_rport_alloc(port, WWN_NULL, fchs->s_id);
-	if (!rport)
-		return;
-
-	bfa_fcs_rport_update(rport, plogi);
-
-	bfa_sm_send_event(rport, RPSM_EVENT_PLOGI_COMP);
-}
 
 /*
  *	Called by bport/vport to handle PLOGI received from a new remote port.
@@ -3089,21 +3068,6 @@ bfa_fcs_rport_lookup(struct bfa_fcs_lport_s *port, wwn_t rpwwn)
 	return rport;
 }
 
-struct bfa_fcs_rport_s *
-bfa_fcs_rport_lookup_by_nwwn(struct bfa_fcs_lport_s *port, wwn_t rnwwn)
-{
-	struct bfa_fcs_rport_s *rport;
-
-	rport = bfa_fcs_lport_get_rport_by_nwwn(port, rnwwn);
-	if (rport == NULL) {
-		/*
-		 * TBD Error handling
-		 */
-	}
-
-	return rport;
-}
-
 /*
  * Remote port features (RPF) implementation.
  */

From 8d7cfe95217cae5ce8e0f6e35eef43a11dd33c48 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sun, 15 Sep 2024 13:56:33 +0100
Subject: [PATCH 0382/1530] scsi: bfa: Remove unused misc code

Some more unused functions that didn't group elsewhere.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://lore.kernel.org/r/20240915125633.25036-6-linux@treblig.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/bfa/bfa_fcpim.c |  9 ---------
 drivers/scsi/bfa/bfa_fcpim.h |  1 -
 drivers/scsi/bfa/bfad.c      | 20 --------------------
 drivers/scsi/bfa/bfad_drv.h  |  1 -
 4 files changed, 31 deletions(-)

diff --git a/drivers/scsi/bfa/bfa_fcpim.c b/drivers/scsi/bfa/bfa_fcpim.c
index 28ae4dc14dc9c..2518e36d70d35 100644
--- a/drivers/scsi/bfa/bfa_fcpim.c
+++ b/drivers/scsi/bfa/bfa_fcpim.c
@@ -3412,15 +3412,6 @@ bfa_tskim_iocdisable_ios(struct bfa_tskim_s *tskim)
 	}
 }
 
-/*
- * Notification on completions from related ioim.
- */
-void
-bfa_tskim_iodone(struct bfa_tskim_s *tskim)
-{
-	bfa_wc_down(&tskim->wc);
-}
-
 /*
  * Handle IOC h/w failure notification from itnim.
  */
diff --git a/drivers/scsi/bfa/bfa_fcpim.h b/drivers/scsi/bfa/bfa_fcpim.h
index 4499f84c2d812..64e4485b226e9 100644
--- a/drivers/scsi/bfa/bfa_fcpim.h
+++ b/drivers/scsi/bfa/bfa_fcpim.h
@@ -339,7 +339,6 @@ void	bfa_ioim_tov(struct bfa_ioim_s *ioim);
 
 void	bfa_tskim_attach(struct bfa_fcpim_s *fcpim);
 void	bfa_tskim_isr(struct bfa_s *bfa, struct bfi_msg_s *msg);
-void	bfa_tskim_iodone(struct bfa_tskim_s *tskim);
 void	bfa_tskim_iocdisable(struct bfa_tskim_s *tskim);
 void	bfa_tskim_cleanup(struct bfa_tskim_s *tskim);
 void	bfa_tskim_res_recfg(struct bfa_s *bfa, u16 num_tskim_fw);
diff --git a/drivers/scsi/bfa/bfad.c b/drivers/scsi/bfa/bfad.c
index 62cb7a864fd53..19675a6e0780d 100644
--- a/drivers/scsi/bfa/bfad.c
+++ b/drivers/scsi/bfa/bfad.c
@@ -842,26 +842,6 @@ bfad_drv_init(struct bfad_s *bfad)
 	return BFA_STATUS_OK;
 }
 
-void
-bfad_drv_uninit(struct bfad_s *bfad)
-{
-	unsigned long   flags;
-
-	spin_lock_irqsave(&bfad->bfad_lock, flags);
-	init_completion(&bfad->comp);
-	bfa_iocfc_stop(&bfad->bfa);
-	spin_unlock_irqrestore(&bfad->bfad_lock, flags);
-	wait_for_completion(&bfad->comp);
-
-	del_timer_sync(&bfad->hal_tmo);
-	bfa_isr_disable(&bfad->bfa);
-	bfa_detach(&bfad->bfa);
-	bfad_remove_intr(bfad);
-	bfad_hal_mem_release(bfad);
-
-	bfad->bfad_flags &= ~BFAD_DRV_INIT_DONE;
-}
-
 void
 bfad_drv_start(struct bfad_s *bfad)
 {
diff --git a/drivers/scsi/bfa/bfad_drv.h b/drivers/scsi/bfa/bfad_drv.h
index da42e3261237e..ce2ec51089472 100644
--- a/drivers/scsi/bfa/bfad_drv.h
+++ b/drivers/scsi/bfa/bfad_drv.h
@@ -312,7 +312,6 @@ void		bfad_bfa_tmo(struct timer_list *t);
 void		bfad_init_timer(struct bfad_s *bfad);
 int		bfad_pci_init(struct pci_dev *pdev, struct bfad_s *bfad);
 void		bfad_pci_uninit(struct pci_dev *pdev, struct bfad_s *bfad);
-void		bfad_drv_uninit(struct bfad_s *bfad);
 int		bfad_worker(void *ptr);
 void		bfad_debugfs_init(struct bfad_port_s *port);
 void		bfad_debugfs_exit(struct bfad_port_s *port);

From 60ba5da29a3afe1a6106203d34e02f90236b5dea Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 15 Oct 2024 15:11:13 +0000
Subject: [PATCH 0383/1530] pinctrl: th1520: add a CONFIG_OF dependency

When compile-testing without CONfIG_OF:

drivers/pinctrl/pinctrl-th1520.c: In function 'th1520_pinctrl_dt_node_to_map':
drivers/pinctrl/pinctrl-th1520.c:455:23: error: implicit declaration of function 'pinconf_generic_parse_dt_config'; did you mean 'pinconf_generic_dump_config'? [-Wimplicit-function-declaration]
  455 |                 ret = pinconf_generic_parse_dt_config(child, pctldev, &configs, &nconfigs);
      |                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
      |                       pinconf_generic_dump_config

Enforce this using Kconig dependencies.

Fixes: bed5cd6f8a98 ("pinctrl: Add driver for the T-Head TH1520 SoC")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Drew Fustini <drew@pdp7.com>
Link: https://lore.kernel.org/20241015151126.2401855-1-arnd@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index a6acc27c9a83c..3fab5ebeb2e07 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -564,6 +564,7 @@ config PINCTRL_TPS6594
 config PINCTRL_TH1520
 	tristate "Pinctrl driver for the T-Head TH1520 SoC"
 	depends on ARCH_THEAD || COMPILE_TEST
+	depends on OF
 	select GENERIC_PINMUX_FUNCTIONS
 	select GENERIC_PINCONF
 	select PINMUX

From 642490b50a7c90ca45bff5507f684c96f42e6756 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Tue, 15 Oct 2024 11:55:58 +0200
Subject: [PATCH 0384/1530] pinctrl: PINCTRL_K230 should depend on ARCH_CANAAN

The Canaan Kendryte K230 pin controller is only present on Canaan
Kendryte K230 SoCs.  Hence add a dependency on ARCH_CANAAN, to prevent
asking the user about this driver when configuring a kernel without
Canaan Kendryte series SoC platform support.

Fixes: 545887eab6f6776a ("pinctrl: canaan: Add support for k230 SoC")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/d70279ba02a67250203744b38314f4475b3c5671.1728986052.git.geert+renesas@glider.be
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index 3fab5ebeb2e07..f64126a8d9a93 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -271,6 +271,7 @@ config PINCTRL_K210
 config PINCTRL_K230
 	bool "Pinctrl driver for the Canaan Kendryte K230 SoC"
 	depends on OF
+	depends on ARCH_CANAAN || COMPILE_TEST
 	select GENERIC_PINCTRL_GROUPS
 	select GENERIC_PINMUX_FUNCTIONS
 	select GENERIC_PINCONF

From e6702e3919328b24757872cbf7f02c51894624d7 Mon Sep 17 00:00:00 2001
From: Yihang Li <liyihang9@huawei.com>
Date: Tue, 8 Oct 2024 10:18:10 +0800
Subject: [PATCH 0385/1530] scsi: hisi_sas: Adjust priority of registering and
 exiting debugfs for security

To be safe, we should register debugfs at the last stage of driver
initialization and then unregister debugfs at the first stage of driver
uninstallation.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Link: https://lore.kernel.org/r/20241008021822.2617339-2-liyihang9@huawei.com
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c  |  4 ++--
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 17 ++++++-----------
 2 files changed, 8 insertions(+), 13 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 6219807ce3b9e..d3dcc4918444c 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -2630,10 +2630,10 @@ static __init int hisi_sas_init(void)
 
 static __exit void hisi_sas_exit(void)
 {
-	sas_release_transport(hisi_sas_stt);
-
 	if (hisi_sas_debugfs_enable)
 		debugfs_remove(hisi_sas_debugfs_dir);
+
+	sas_release_transport(hisi_sas_stt);
 }
 
 module_init(hisi_sas_init);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 4cd3a3eab6f1c..63a7255d29945 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -4860,16 +4860,13 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 					    SHOST_DIX_GUARD_CRC);
 	}
 
-	if (hisi_sas_debugfs_enable)
-		debugfs_init_v3_hw(hisi_hba);
-
 	rc = interrupt_preinit_v3_hw(hisi_hba);
 	if (rc)
-		goto err_out_undo_debugfs;
+		goto err_out_free_host;
 
 	rc = scsi_add_host(shost, dev);
 	if (rc)
-		goto err_out_undo_debugfs;
+		goto err_out_free_host;
 
 	rc = sas_register_ha(sha);
 	if (rc)
@@ -4880,6 +4877,8 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_out_unregister_ha;
 
 	scsi_scan_host(shost);
+	if (hisi_sas_debugfs_enable)
+		debugfs_init_v3_hw(hisi_hba);
 
 	pm_runtime_set_autosuspend_delay(dev, 5000);
 	pm_runtime_use_autosuspend(dev);
@@ -4900,9 +4899,6 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	sas_unregister_ha(sha);
 err_out_remove_host:
 	scsi_remove_host(shost);
-err_out_undo_debugfs:
-	if (hisi_sas_debugfs_enable)
-		debugfs_exit_v3_hw(hisi_hba);
 err_out_free_host:
 	hisi_sas_free(hisi_hba);
 	scsi_host_put(shost);
@@ -4934,6 +4930,8 @@ static void hisi_sas_v3_remove(struct pci_dev *pdev)
 	struct Scsi_Host *shost = sha->shost;
 
 	pm_runtime_get_noresume(dev);
+	if (hisi_sas_debugfs_enable)
+		debugfs_exit_v3_hw(hisi_hba);
 
 	sas_unregister_ha(sha);
 	flush_workqueue(hisi_hba->wq);
@@ -4941,9 +4939,6 @@ static void hisi_sas_v3_remove(struct pci_dev *pdev)
 
 	hisi_sas_v3_destroy_irqs(pdev, hisi_hba);
 	hisi_sas_free(hisi_hba);
-	if (hisi_sas_debugfs_enable)
-		debugfs_exit_v3_hw(hisi_hba);
-
 	scsi_host_put(shost);
 }
 

From 436a97c5d2882c09f44d3255ac47f641860faeea Mon Sep 17 00:00:00 2001
From: Yihang Li <liyihang9@huawei.com>
Date: Tue, 8 Oct 2024 10:18:11 +0800
Subject: [PATCH 0386/1530] scsi: hisi_sas: Create trigger_dump at the end of
 the debugfs initialization

In the current debugfs initialization process, the interface
trigger_dump is created first, and then the dump directory is created to
store the register dump information.

The issue is that after the trigger_dump interface is created, users can
access the interface to trigger dump and call
debugfs_create_files_v3_hw().  In debugfs_create_files_v3_hw(), if
.debugfs_dump_dentry is NULL, the file for storing dump information is
created under /sys/kernel/debug, and the memory and information cannot
be released after the driver is uninstalled.

Therefore, the creation of the trigger_dump interface is placed at the
end of debugfs initialization.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Link: https://lore.kernel.org/r/20241008021822.2617339-3-liyihang9@huawei.com
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 63a7255d29945..980f28d7b87f2 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -4755,11 +4755,6 @@ static void debugfs_init_v3_hw(struct hisi_hba *hisi_hba)
 
 	hisi_hba->debugfs_dir = debugfs_create_dir(dev_name(dev),
 						   hisi_sas_debugfs_dir);
-	debugfs_create_file("trigger_dump", 0200,
-			    hisi_hba->debugfs_dir,
-			    hisi_hba,
-			    &debugfs_trigger_dump_v3_hw_fops);
-
 	/* create bist structures */
 	debugfs_bist_init_v3_hw(hisi_hba);
 
@@ -4768,6 +4763,10 @@ static void debugfs_init_v3_hw(struct hisi_hba *hisi_hba)
 
 	debugfs_phy_down_cnt_init_v3_hw(hisi_hba);
 	debugfs_fifo_init_v3_hw(hisi_hba);
+	debugfs_create_file("trigger_dump", 0200,
+			    hisi_hba->debugfs_dir,
+			    hisi_hba,
+			    &debugfs_trigger_dump_v3_hw_fops);
 }
 
 static int

From 2c335fa7e69c06d8932ae8bc0ec7145de2973cf5 Mon Sep 17 00:00:00 2001
From: Yihang Li <liyihang9@huawei.com>
Date: Tue, 8 Oct 2024 10:18:12 +0800
Subject: [PATCH 0387/1530] scsi: hisi_sas: Add firmware information check

For security purposes, after information is obtained through the FW,
check information to ensure data correctness.

 - In v1 and v2 hw, the maximum number of PHYs is 9, while in v3 it is 8.

 - In v2 and v3 hw, the maximum number of hardware queues is 16, while
   in v1 it is 32.

Also add some debug logs for failure.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Link: https://lore.kernel.org/r/20241008021822.2617339-4-liyihang9@huawei.com
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas.h       |  1 +
 drivers/scsi/hisi_sas/hisi_sas_main.c  |  5 +++++
 drivers/scsi/hisi_sas/hisi_sas_v1_hw.c | 18 ++++++++++++++++++
 drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 18 ++++++++++++++++++
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 20 ++++++++++++++++++++
 5 files changed, 62 insertions(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index d223f482488fc..a44768bceb9ab 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -307,6 +307,7 @@ enum {
 
 struct hisi_sas_hw {
 	int (*hw_init)(struct hisi_hba *hisi_hba);
+	int (*fw_info_check)(struct hisi_hba *hisi_hba);
 	int (*interrupt_preinit)(struct hisi_hba *hisi_hba);
 	void (*setup_itct)(struct hisi_hba *hisi_hba,
 			   struct hisi_sas_device *device);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index d3dcc4918444c..275d45a41b0be 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -2450,6 +2450,11 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
 	if (hisi_sas_get_fw_info(hisi_hba) < 0)
 		goto err_out;
 
+	if (hisi_hba->hw->fw_info_check) {
+		if (hisi_hba->hw->fw_info_check(hisi_hba))
+			goto err_out;
+	}
+
 	error = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (error) {
 		dev_err(dev, "No usable DMA addressing method\n");
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 71b5008c3552c..70bba55bc5d02 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -1734,6 +1734,23 @@ static struct attribute *host_v1_hw_attrs[] = {
 
 ATTRIBUTE_GROUPS(host_v1_hw);
 
+static int check_fw_info_v1_hw(struct hisi_hba *hisi_hba)
+{
+	struct device *dev = hisi_hba->dev;
+
+	if (hisi_hba->n_phy < 0 || hisi_hba->n_phy > 9) {
+		dev_err(dev, "invalid phy number from FW\n");
+		return -EINVAL;
+	}
+
+	if (hisi_hba->queue_count < 0 || hisi_hba->queue_count > 32) {
+		dev_err(dev, "invalid queue count from FW\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct scsi_host_template sht_v1_hw = {
 	LIBSAS_SHT_BASE_NO_SLAVE_INIT
 	.device_configure	= hisi_sas_device_configure,
@@ -1747,6 +1764,7 @@ static const struct scsi_host_template sht_v1_hw = {
 
 static const struct hisi_sas_hw hisi_sas_v1_hw = {
 	.hw_init = hisi_sas_v1_init,
+	.fw_info_check = check_fw_info_v1_hw,
 	.setup_itct = setup_itct_v1_hw,
 	.sl_notify_ssp = sl_notify_ssp_v1_hw,
 	.clear_itct = clear_itct_v1_hw,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 342d75f12051d..ab6668dc5b77c 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -3566,6 +3566,23 @@ static void map_queues_v2_hw(struct Scsi_Host *shost)
 	}
 }
 
+static int check_fw_info_v2_hw(struct hisi_hba *hisi_hba)
+{
+	struct device *dev = hisi_hba->dev;
+
+	if (hisi_hba->n_phy < 0 || hisi_hba->n_phy > 9) {
+		dev_err(dev, "invalid phy number from FW\n");
+		return -EINVAL;
+	}
+
+	if (hisi_hba->queue_count < 0 || hisi_hba->queue_count > 16) {
+		dev_err(dev, "invalid queue count from FW\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct scsi_host_template sht_v2_hw = {
 	LIBSAS_SHT_BASE_NO_SLAVE_INIT
 	.device_configure	= hisi_sas_device_configure,
@@ -3582,6 +3599,7 @@ static const struct scsi_host_template sht_v2_hw = {
 
 static const struct hisi_sas_hw hisi_sas_v2_hw = {
 	.hw_init = hisi_sas_v2_init,
+	.fw_info_check = check_fw_info_v2_hw,
 	.interrupt_preinit = hisi_sas_v2_interrupt_preinit,
 	.setup_itct = setup_itct_v2_hw,
 	.slot_index_alloc = slot_index_alloc_quirk_v2_hw,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 980f28d7b87f2..d48777fc4bd92 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -3371,6 +3371,23 @@ static const struct hisi_sas_hw hisi_sas_v3_hw = {
 	.debugfs_snapshot_regs = debugfs_snapshot_regs_v3_hw,
 };
 
+static int check_fw_info_v3_hw(struct hisi_hba *hisi_hba)
+{
+	struct device *dev = hisi_hba->dev;
+
+	if (hisi_hba->n_phy < 0 || hisi_hba->n_phy > 8) {
+		dev_err(dev, "invalid phy number from FW\n");
+		return -EINVAL;
+	}
+
+	if (hisi_hba->queue_count < 0 || hisi_hba->queue_count > 16) {
+		dev_err(dev, "invalid queue count from FW\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static struct Scsi_Host *
 hisi_sas_shost_alloc_pci(struct pci_dev *pdev)
 {
@@ -3401,6 +3418,9 @@ hisi_sas_shost_alloc_pci(struct pci_dev *pdev)
 	if (hisi_sas_get_fw_info(hisi_hba) < 0)
 		goto err_out;
 
+	if (check_fw_info_v3_hw(hisi_hba) < 0)
+		goto err_out;
+
 	if (experimental_iopoll_q_cnt < 0 ||
 		experimental_iopoll_q_cnt >= hisi_hba->queue_count)
 		dev_err(dev, "iopoll queue count %d cannot exceed or equal 16, using default 0\n",

From 08a07dc71d7fc6f58c35c4fc0bcede2811c5aa4c Mon Sep 17 00:00:00 2001
From: Yihang Li <liyihang9@huawei.com>
Date: Tue, 8 Oct 2024 10:18:13 +0800
Subject: [PATCH 0388/1530] scsi: hisi_sas: Enable all PHYs that are not
 disabled by user during controller reset

For the controller reset operation(such as FLR or clear nexus ha in SCSI
EH), we will disable all PHYs and then enable PHY based on the
hisi_hba->phy_state obtained in hisi_sas_controller_reset_prepare(). If
the device is removed before controller reset or the PHY is not attached
to any device in directly attached scenario, the corresponding bit of
phy_state is not set. After controller reset done, the PHY is disabled.
The device cannot be identified even if user reconnect the disk.

Therefore, for PHYs that are not disabled by user, hisi_sas_phy_enable()
needs to be executed even if the corresponding bit of phy_state is not
set.

Fixes: 89954f024c3a ("scsi: hisi_sas: Ensure all enabled PHYs up during controller reset")
Signed-off-by: Yihang Li <liyihang9@huawei.com>
Link: https://lore.kernel.org/r/20241008021822.2617339-5-liyihang9@huawei.com
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 275d45a41b0be..f3b0042ab67c5 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1545,10 +1545,16 @@ void hisi_sas_controller_reset_done(struct hisi_hba *hisi_hba)
 	/* Init and wait for PHYs to come up and all libsas event finished. */
 	for (phy_no = 0; phy_no < hisi_hba->n_phy; phy_no++) {
 		struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
+		struct asd_sas_phy *sas_phy = &phy->sas_phy;
 
-		if (!(hisi_hba->phy_state & BIT(phy_no)))
+		if (!sas_phy->phy->enabled)
 			continue;
 
+		if (!(hisi_hba->phy_state & BIT(phy_no))) {
+			hisi_sas_phy_enable(hisi_hba, phy_no, 1);
+			continue;
+		}
+
 		async_schedule_domain(hisi_sas_async_init_wait_phyup,
 				      phy, &async);
 	}

From 64359afb7068e9fd1b3ffcf7b0fefb63d1a2ccdf Mon Sep 17 00:00:00 2001
From: Yihang Li <liyihang9@huawei.com>
Date: Tue, 8 Oct 2024 10:18:14 +0800
Subject: [PATCH 0389/1530] scsi: hisi_sas: Reset PHY again if phyup timeout

In commit 89954f024c3a ("scsi: hisi_sas: Ensure all enabled PHYs up
during controller reset"), we enable PHYs in parallel through async
operations and wait for PHYs come up. However, for some directly
attached SATA disks, the PHY not come up after a timeout period and the
hardware is not ready.  At this time, we should get the latest PHY
hardware state, if the new PHY state is not ready but the old PHY state
is ready, call work HISI_PHYE_LINK_RESET to give it another chance to
phyup.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Link: https://lore.kernel.org/r/20241008021822.2617339-6-liyihang9@huawei.com
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index f3b0042ab67c5..93f9f13084fd2 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1384,6 +1384,7 @@ static void hisi_sas_refresh_port_id(struct hisi_hba *hisi_hba)
 
 static void hisi_sas_rescan_topology(struct hisi_hba *hisi_hba, u32 state)
 {
+	u32 new_state = hisi_hba->hw->get_phys_state(hisi_hba);
 	struct asd_sas_port *_sas_port = NULL;
 	int phy_no;
 
@@ -1397,7 +1398,7 @@ static void hisi_sas_rescan_topology(struct hisi_hba *hisi_hba, u32 state)
 			continue;
 
 		/* Report PHY state change to libsas */
-		if (state & BIT(phy_no)) {
+		if (new_state & BIT(phy_no)) {
 			if (do_port_check && sas_port && sas_port->port_dev) {
 				struct domain_device *dev = sas_port->port_dev;
 
@@ -1410,6 +1411,16 @@ static void hisi_sas_rescan_topology(struct hisi_hba *hisi_hba, u32 state)
 			}
 		} else {
 			hisi_sas_phy_down(hisi_hba, phy_no, 0, GFP_KERNEL);
+
+			/*
+			 * The new_state is not ready but old_state is ready,
+			 * the two possible causes:
+			 * 1. The connected device is removed
+			 * 2. Device exists but phyup timed out
+			 */
+			if (state & BIT(phy_no))
+				hisi_sas_notify_phy_event(phy,
+							  HISI_PHYE_LINK_RESET);
 		}
 	}
 }

From 4ca4ce000610d51c741ad81bffc79434421a0101 Mon Sep 17 00:00:00 2001
From: Yihang Li <liyihang9@huawei.com>
Date: Tue, 8 Oct 2024 10:18:15 +0800
Subject: [PATCH 0390/1530] scsi: hisi_sas: Check usage count only when the
 runtime PM status is RPM_SUSPENDING

Users can suspend the machine with 'echo disk > /sys/power/state', but
the suspend will fail because the SAS controller cannot be suspended:

[root@localhost ~]# echo freeze > /sys/power/state
-bash: echo: write error: Device or resource busy
[15104.142955] PM: suspend entry (s2idle)
...
[15104.283465] hisi_sas_v3_hw 0000:32:04.0: entering suspend state
[15104.283480] hisi_sas_v3_hw 0000:30:04.0: entering suspend state
[15104.283500] hisi_sas_v3_hw 0000:32:04.0: PM suspend: host status cannot be suspended
[15104.283508] hisi_sas_v3_hw 0000:30:04.0: PM suspend: host status cannot be suspended
[15104.283516] hisi_sas_v3_hw 0000:32:04.0: PM: pci_pm_suspend(): suspend_v3_hw+0x0/0x210 [hisi_sas_v3_hw] returns -16
[15104.283527] hisi_sas_v3_hw 0000:32:04.0: PM: dpm_run_callback(): pci_pm_suspend+0x0/0x1c0 returns -16
[15104.283524] hisi_sas_v3_hw 0000:30:04.0: PM: pci_pm_suspend(): suspend_v3_hw+0x0/0x210 [hisi_sas_v3_hw] returns -16
[15104.283533] hisi_sas_v3_hw 0000:32:04.0: PM: failed to suspend async: error -16
[15104.283536] hisi_sas_v3_hw 0000:30:04.0: PM: dpm_run_callback(): pci_pm_suspend+0x0/0x1c0 returns -16
[15104.283542] hisi_sas_v3_hw 0000:30:04.0: PM: failed to suspend async: error -16

The problem is that when the ->runtime_suspend() callback
suspend_v3_hw() is executing, the current runtime PM status is
RPM_ACTIVE and the usage count of the controller is not 0, so return
immediately.

To fix it, Check the device usage count only when the runtime PM status
is RPM_SUSPENDING.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Link: https://lore.kernel.org/r/20241008021822.2617339-7-liyihang9@huawei.com
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index d48777fc4bd92..9e65ad0e6ce0f 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -5048,7 +5048,8 @@ static int _suspend_v3_hw(struct device *device)
 	interrupt_disable_v3_hw(hisi_hba);
 
 #ifdef CONFIG_PM
-	if (atomic_read(&device->power.usage_count)) {
+	if ((device->power.runtime_status == RPM_SUSPENDING) &&
+	    atomic_read(&device->power.usage_count)) {
 		dev_err(dev, "PM suspend: host status cannot be suspended\n");
 		rc = -EBUSY;
 		goto err_out;

From 2233c4a0b948211743659b24c13d6bd059fa75fc Mon Sep 17 00:00:00 2001
From: Yihang Li <liyihang9@huawei.com>
Date: Tue, 8 Oct 2024 10:18:16 +0800
Subject: [PATCH 0391/1530] scsi: hisi_sas: Add cond_resched() for no forced
 preemption model

For no forced preemption model kernel, in the scenario where the
expander is connected to 12 high performance SAS SSDs, the following
call trace may occur:

[  214.409199][  C240] watchdog: BUG: soft lockup - CPU#240 stuck for 22s! [irq/149-hisi_sa:3211]
[  214.568533][  C240] pstate: 60400009 (nZCv daif +PAN -UAO -TCO BTYPE=--)
[  214.575224][  C240] pc : fput_many+0x8c/0xdc
[  214.579480][  C240] lr : fput+0x1c/0xf0
[  214.583302][  C240] sp : ffff80002de2b900
[  214.587298][  C240] x29: ffff80002de2b900 x28: ffff1082aa412000
[  214.593291][  C240] x27: ffff3062a0348c08 x26: ffff80003a9f6000
[  214.599284][  C240] x25: ffff1062bbac5c40 x24: 0000000000001000
[  214.605277][  C240] x23: 000000000000000a x22: 0000000000000001
[  214.611270][  C240] x21: 0000000000001000 x20: 0000000000000000
[  214.617262][  C240] x19: ffff3062a41ae580 x18: 0000000000010000
[  214.623255][  C240] x17: 0000000000000001 x16: ffffdb3a6efe5fc0
[  214.629248][  C240] x15: ffffffffffffffff x14: 0000000003ffffff
[  214.635241][  C240] x13: 000000000000ffff x12: 000000000000029c
[  214.641234][  C240] x11: 0000000000000006 x10: ffff80003a9f7fd0
[  214.647226][  C240] x9 : ffffdb3a6f0482fc x8 : 0000000000000001
[  214.653219][  C240] x7 : 0000000000000002 x6 : 0000000000000080
[  214.659212][  C240] x5 : ffff55480ee9b000 x4 : fffffde7f94c6554
[  214.665205][  C240] x3 : 0000000000000002 x2 : 0000000000000020
[  214.671198][  C240] x1 : 0000000000000021 x0 : ffff3062a41ae5b8
[  214.677191][  C240] Call trace:
[  214.680320][  C240]  fput_many+0x8c/0xdc
[  214.684230][  C240]  fput+0x1c/0xf0
[  214.687707][  C240]  aio_complete_rw+0xd8/0x1fc
[  214.692225][  C240]  blkdev_bio_end_io+0x98/0x140
[  214.696917][  C240]  bio_endio+0x160/0x1bc
[  214.701001][  C240]  blk_update_request+0x1c8/0x3bc
[  214.705867][  C240]  scsi_end_request+0x3c/0x1f0
[  214.710471][  C240]  scsi_io_completion+0x7c/0x1a0
[  214.715249][  C240]  scsi_finish_command+0x104/0x140
[  214.720200][  C240]  scsi_softirq_done+0x90/0x180
[  214.724892][  C240]  blk_mq_complete_request+0x5c/0x70
[  214.730016][  C240]  scsi_mq_done+0x48/0xac
[  214.734194][  C240]  sas_scsi_task_done+0xbc/0x16c [libsas]
[  214.739758][  C240]  slot_complete_v3_hw+0x260/0x760 [hisi_sas_v3_hw]
[  214.746185][  C240]  cq_thread_v3_hw+0xbc/0x190 [hisi_sas_v3_hw]
[  214.752179][  C240]  irq_thread_fn+0x34/0xa4
[  214.756435][  C240]  irq_thread+0xc4/0x130
[  214.760520][  C240]  kthread+0x108/0x13c
[  214.764430][  C240]  ret_from_fork+0x10/0x18

This is because in the hisi_sas driver, both the hardware interrupt
handler and the interrupt thread are executed on the same CPU. In the
performance test scenario, function irq_wait_for_interrupt() will always
return 0 if lots of interrupts occurs and the CPU will be continuously
consumed. As a result, the CPU cannot run the watchdog thread. When the
watchdog time exceeds the specified time, call trace occurs.

To fix it, add cond_resched() to execute the watchdog thread.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Link: https://lore.kernel.org/r/20241008021822.2617339-8-liyihang9@huawei.com
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 9e65ad0e6ce0f..e6fbbefe99597 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -2493,6 +2493,7 @@ static int complete_v3_hw(struct hisi_sas_cq *cq)
 	/* update rd_point */
 	cq->rd_point = rd_point;
 	hisi_sas_write32(hisi_hba, COMPL_Q_0_RD_PTR + (0x14 * queue), rd_point);
+	cond_resched();
 
 	return completed;
 }

From a220bffebabe7227b4dbb8f811bc64ecf25e017e Mon Sep 17 00:00:00 2001
From: Yihang Li <liyihang9@huawei.com>
Date: Tue, 8 Oct 2024 10:18:17 +0800
Subject: [PATCH 0392/1530] scsi: hisi_sas: Default enable interrupt coalescing

In the current interrupt reporting mode, each CQ entry reports an
interrupt. However, when there are a large number of I/O hardware
completion interrupts, the following issue may occur:

[ 4682.678657][  C129] irq 134: nobody cared (try booting with the "irqpoll" option)
[ 4682.708455][  C129] Call trace:
[ 4682.711589][  C129]  dump_backtrace+0x0/0x1e4
[ 4682.715934][  C129]  show_stack+0x20/0x2c
[ 4682.719933][  C129]  dump_stack+0xd8/0x140
[ 4682.724017][  C129]  __report_bad_irq+0x54/0x180
[ 4682.728625][  C129]  note_interrupt+0x1ec/0x2f0
[ 4682.733143][  C129]  handle_irq_event+0x118/0x1ac
[ 4682.737834][  C129]  handle_fasteoi_irq+0xc8/0x200
[ 4682.742613][  C129]  __handle_domain_irq+0x84/0xf0
[ 4682.747391][  C129]  gic_handle_irq+0x88/0x2c0
[ 4682.751822][  C129]  el1_irq+0xbc/0x140
[ 4682.755648][  C129]  _find_next_bit.constprop.0+0x20/0x94
[ 4682.761036][  C129]  cpumask_next+0x24/0x30
[ 4682.765208][  C129]  gic_ipi_send_mask+0x48/0x170
[ 4682.769900][  C129]  __ipi_send_mask+0x34/0x110
[ 4682.775720][  C129]  smp_cross_call+0x3c/0xcc
[ 4682.780064][  C129]  arch_send_call_function_single_ipi+0x38/0x44
[ 4682.786146][  C129]  send_call_function_single_ipi+0xd0/0xe0
[ 4682.791794][  C129]  generic_exec_single+0xb4/0x170
[ 4682.796659][  C129]  smp_call_function_single_async+0x2c/0x40
[ 4682.802395][  C129]  blk_mq_complete_request_remote.part.0+0xec/0x100
[ 4682.808822][  C129]  blk_mq_complete_request+0x30/0x70
[ 4682.813950][  C129]  scsi_mq_done+0x48/0xac
[ 4682.818128][  C129]  sas_scsi_task_done+0xb0/0x150 [libsas]
[ 4682.823692][  C129]  slot_complete_v3_hw+0x230/0x710 [hisi_sas_v3_hw]
[ 4682.830120][  C129]  cq_thread_v3_hw+0xbc/0x190 [hisi_sas_v3_hw]
[ 4682.836114][  C129]  irq_thread_fn+0x34/0xa4
[ 4682.840371][  C129]  irq_thread+0xc4/0x130
[ 4682.844455][  C129]  kthread+0x108/0x13c
[ 4682.848365][  C129]  ret_from_fork+0x10/0x18
[ 4682.852621][  C129] handlers:
[ 4682.855577][  C129] [<00000000949e52bf>] cq_interrupt_v3_hw [hisi_sas_v3_hw] threaded [<000000005d8e3b68>] cq_thread_v3_hw [hisi_sas_v3_hw]
[ 4682.868084][  C129] Disabling IRQ #134

When the IRQ management layer processes each hardware interrupt, if the
return value of the interrupt handler is IRQ_WAKE_THREAD, it will wake
up the handler thread for this interrupt action and set IRQTF_RUNTHREAD
flag, wait for the interrupt handling thread to clear the
IRQTF_RUNTHREAD flag after execution. Later in note_interrupt(), use
irq_count to count hardware interrupts and irqs_unhandled to count
interrupts for which no thread handler is responsible. When irq_count
reaches 100000 and irqs_unhandled reaches 99000, irq will be disabled.

In the performance test scenario, I/O completion hardware interrupts are
continuously and quickly generated. As a result, the interrupt
processing thread is cyclically called in irq_thread() and does not
exit, this affects the response of the interrupt thread to the hardware
interrupt and causes irqs_unhandled to grow to 99000. Finally, the irq
is disabled.

Therefore, default enable interrupt coalescing to reduce the generation
of hardware interrupts, this helps interrupt processing threads to stop
calling in irq_thread().

For interrupt coalescing, according to the actual performance test, set
the count of CQ entries to 10 and the interrupt coalescing timeout
period to 10us based on the actual performance test.

Before and after interrupt coalescing is enabled, the 4K read/write
performance is improved by about 3%, and the 256K read/write performance
is basically the same.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Link: https://lore.kernel.org/r/20241008021822.2617339-9-liyihang9@huawei.com
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index e6fbbefe99597..310c782b4926b 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -638,9 +638,11 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
 	hisi_sas_write32(hisi_hba, TRANS_LOCK_ICT_TIME, 0x4A817C80);
 	hisi_sas_write32(hisi_hba, HGC_SAS_TXFAIL_RETRY_CTRL, 0x108);
 	hisi_sas_write32(hisi_hba, CFG_AGING_TIME, 0x1);
-	hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x1);
-	hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME, 0x1);
-	hisi_sas_write32(hisi_hba, OQ_INT_COAL_CNT, 0x1);
+	hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x3);
+	/* configure the interrupt coalescing timeout period 10us */
+	hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME, 0xa);
+	/* configure the count of CQ entries 10 */
+	hisi_sas_write32(hisi_hba, OQ_INT_COAL_CNT, 0xa);
 	hisi_sas_write32(hisi_hba, CQ_INT_CONVERGE_EN,
 			 hisi_sas_intr_conv);
 	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 0xffff);
@@ -2797,14 +2799,15 @@ static void config_intr_coal_v3_hw(struct hisi_hba *hisi_hba)
 {
 	/* config those registers between enable and disable PHYs */
 	hisi_sas_stop_phys(hisi_hba);
+	hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x3);
 
 	if (hisi_hba->intr_coal_ticks == 0 ||
 	    hisi_hba->intr_coal_count == 0) {
-		hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x1);
-		hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME, 0x1);
-		hisi_sas_write32(hisi_hba, OQ_INT_COAL_CNT, 0x1);
+		/* configure the interrupt coalescing timeout period 10us */
+		hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME, 0xa);
+		/* configure the count of CQ entries 10 */
+		hisi_sas_write32(hisi_hba, OQ_INT_COAL_CNT, 0xa);
 	} else {
-		hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x3);
 		hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME,
 				 hisi_hba->intr_coal_ticks);
 		hisi_sas_write32(hisi_hba, OQ_INT_COAL_CNT,

From 90b24856b311e7e2f4f1629fb315ee50a4914aa5 Mon Sep 17 00:00:00 2001
From: Xingui Yang <yangxingui@huawei.com>
Date: Tue, 8 Oct 2024 10:18:18 +0800
Subject: [PATCH 0393/1530] scsi: hisi_sas: Update disk locked timeout to 7
 seconds

The SATA disk will be locked after the disk sends the DMA Setup frame
until all data frame transmission is completed. The
CFG_ICT_TIMER_STEP_TRSH register is used for sata disk to configure the
step size of the timer which records the time when the disk is
locked. The unit is 1us and the default step size is 150ms. If the disk
is locked for more than 7 timer steps, the io to be sent to the disk
will end abnormally.

The current timeout is only about 1 second, it is easy to trigger IO
abnormal end when the SATA hard disk returns data slowly. Adjust the
timeout to 7 seconds based on ERC time of most disks.

Signed-off-by: Xingui Yang <yangxingui@huawei.com>
Link: https://lore.kernel.org/r/20241008021822.2617339-10-liyihang9@huawei.com
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
Reviewed-by: Yihang Li <liyihang9@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 310c782b4926b..5c97c44630326 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -43,6 +43,7 @@
 #define CQ_INT_CONVERGE_EN		0xb0
 #define CFG_AGING_TIME			0xbc
 #define HGC_DFX_CFG2			0xc0
+#define CFG_ICT_TIMER_STEP_TRSH		0xc8
 #define CFG_ABT_SET_QUERY_IPTT	0xd4
 #define CFG_SET_ABORTED_IPTT_OFF	0
 #define CFG_SET_ABORTED_IPTT_MSK	(0xfff << CFG_SET_ABORTED_IPTT_OFF)
@@ -638,6 +639,7 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
 	hisi_sas_write32(hisi_hba, TRANS_LOCK_ICT_TIME, 0x4A817C80);
 	hisi_sas_write32(hisi_hba, HGC_SAS_TXFAIL_RETRY_CTRL, 0x108);
 	hisi_sas_write32(hisi_hba, CFG_AGING_TIME, 0x1);
+	hisi_sas_write32(hisi_hba, CFG_ICT_TIMER_STEP_TRSH, 0xf4240);
 	hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x3);
 	/* configure the interrupt coalescing timeout period 10us */
 	hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME, 0xa);

From 3c62791322e42d1afd65acfdb5b3a371bde21ede Mon Sep 17 00:00:00 2001
From: Xingui Yang <yangxingui@huawei.com>
Date: Tue, 8 Oct 2024 10:18:19 +0800
Subject: [PATCH 0394/1530] scsi: hisi_sas: Add time interval between two H2D
 FIS following soft reset spec

Spec says at least 5us between two H2D FIS when do soft reset, but be
generous and sleep for about 1ms.

Signed-off-by: Xingui Yang <yangxingui@huawei.com>
Link: https://lore.kernel.org/r/20241008021822.2617339-11-liyihang9@huawei.com
Reviewed-by: Yihang Li <liyihang9@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 93f9f13084fd2..53cb15f6714bd 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1321,6 +1321,7 @@ static int hisi_sas_softreset_ata_disk(struct domain_device *device)
 	}
 
 	if (rc == TMF_RESP_FUNC_COMPLETE) {
+		usleep_range(900, 1000);
 		ata_for_each_link(link, ap, EDGE) {
 			int pmp = sata_srst_pmp(link);
 

From 90f17e3431d9c643558c3c343407ee37783d5e43 Mon Sep 17 00:00:00 2001
From: Xingui Yang <yangxingui@huawei.com>
Date: Tue, 8 Oct 2024 10:18:20 +0800
Subject: [PATCH 0395/1530] scsi: hisi_sas: Update v3 hw STP_LINK_TIMER setting

At present, it is found that some SATA HDD disks may continue to return
the HOLD primitive for more than 500ms when they are busy writing data,
which is more likely to trigger an STP link timeout exception. Now
Modify STP link timer from 500ms to the maximum value of 1.048575s.

Signed-off-by: Xingui Yang <yangxingui@huawei.com>
Link: https://lore.kernel.org/r/20241008021822.2617339-12-liyihang9@huawei.com
Reviewed-by: Yihang Li <liyihang9@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 5c97c44630326..bc5c96320f5a5 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -686,7 +686,7 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
 		hisi_sas_phy_write32(hisi_hba, i, PHY_CTRL_RDY_MSK, 0x0);
 		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_DWS_RESET_MSK, 0x0);
 		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_OOB_RESTART_MSK, 0x1);
-		hisi_sas_phy_write32(hisi_hba, i, STP_LINK_TIMER, 0x7f7a120);
+		hisi_sas_phy_write32(hisi_hba, i, STP_LINK_TIMER, 0x7ffffff);
 		hisi_sas_phy_write32(hisi_hba, i, CON_CFG_DRIVER, 0x2a0a01);
 		hisi_sas_phy_write32(hisi_hba, i, SAS_EC_INT_COAL_TIME,
 				     0x30f4240);

From 9f564f15f88490b484e02442dc4c4b11640ea172 Mon Sep 17 00:00:00 2001
From: Yihang Li <liyihang9@huawei.com>
Date: Tue, 8 Oct 2024 10:18:21 +0800
Subject: [PATCH 0396/1530] scsi: hisi_sas: Create all dump files during
 debugfs initialization

For the current debugfs of hisi_sas, after user triggers dump, the
driver allocate memory space to save the register information and create
debugfs files to display the saved information. In this process, the
debugfs files created after each dump.

Therefore, when the dump is triggered while the driver is unbind, the
following hang occurs:

[67840.853907] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000a0
[67840.862947] Mem abort info:
[67840.865855]   ESR = 0x0000000096000004
[67840.869713]   EC = 0x25: DABT (current EL), IL = 32 bits
[67840.875125]   SET = 0, FnV = 0
[67840.878291]   EA = 0, S1PTW = 0
[67840.881545]   FSC = 0x04: level 0 translation fault
[67840.886528] Data abort info:
[67840.889524]   ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
[67840.895117]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[67840.900284]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[67840.905709] user pgtable: 4k pages, 48-bit VAs, pgdp=0000002803a1f000
[67840.912263] [00000000000000a0] pgd=0000000000000000, p4d=0000000000000000
[67840.919177] Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP
[67840.996435] pstate: 80400009 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[67841.003628] pc : down_write+0x30/0x98
[67841.007546] lr : start_creating.part.0+0x60/0x198
[67841.012495] sp : ffff8000b979ba20
[67841.016046] x29: ffff8000b979ba20 x28: 0000000000000010 x27: 0000000000024b40
[67841.023412] x26: 0000000000000012 x25: ffff20202b355ae8 x24: ffff20202b35a8c8
[67841.030779] x23: ffffa36877928208 x22: ffffa368b4972240 x21: ffff8000b979bb18
[67841.038147] x20: ffff00281dc1e3c0 x19: fffffffffffffffe x18: 0000000000000020
[67841.045515] x17: 0000000000000000 x16: ffffa368b128a530 x15: ffffffffffffffff
[67841.052888] x14: ffff8000b979bc18 x13: ffffffffffffffff x12: ffff8000b979bb18
[67841.060263] x11: 0000000000000000 x10: 0000000000000000 x9 : ffffa368b1289b18
[67841.067640] x8 : 0000000000000012 x7 : 0000000000000000 x6 : 00000000000003a9
[67841.075014] x5 : 0000000000000000 x4 : ffff002818c5cb00 x3 : 0000000000000001
[67841.082388] x2 : 0000000000000000 x1 : ffff002818c5cb00 x0 : 00000000000000a0
[67841.089759] Call trace:
[67841.092456]  down_write+0x30/0x98
[67841.096017]  start_creating.part.0+0x60/0x198
[67841.100613]  debugfs_create_dir+0x48/0x1f8
[67841.104950]  debugfs_create_files_v3_hw+0x88/0x348 [hisi_sas_v3_hw]
[67841.111447]  debugfs_snapshot_regs_v3_hw+0x708/0x798 [hisi_sas_v3_hw]
[67841.118111]  debugfs_trigger_dump_v3_hw_write+0x9c/0x120 [hisi_sas_v3_hw]
[67841.125115]  full_proxy_write+0x68/0xc8
[67841.129175]  vfs_write+0xd8/0x3f0
[67841.132708]  ksys_write+0x70/0x108
[67841.136317]  __arm64_sys_write+0x24/0x38
[67841.140440]  invoke_syscall+0x50/0x128
[67841.144385]  el0_svc_common.constprop.0+0xc8/0xf0
[67841.149273]  do_el0_svc+0x24/0x38
[67841.152773]  el0_svc+0x38/0xd8
[67841.156009]  el0t_64_sync_handler+0xc0/0xc8
[67841.160361]  el0t_64_sync+0x1a4/0x1a8
[67841.164189] Code: b9000882 d2800002 d2800023 f9800011 (c85ffc05)
[67841.170443] ---[ end trace 0000000000000000 ]---

To fix this issue, create all directories and files during debugfs
initialization. In this way, the driver only needs to allocate memory
space to save information each time the user triggers dumping.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Link: https://lore.kernel.org/r/20241008021822.2617339-13-liyihang9@huawei.com
Reviewed-by: Xingui Yang <yangxingui@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 99 ++++++++++++++++++++------
 1 file changed, 77 insertions(+), 22 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index bc5c96320f5a5..8250d44f0b3e9 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -3576,6 +3576,11 @@ debugfs_to_reg_name_v3_hw(int off, int base_off,
 	return NULL;
 }
 
+static bool debugfs_dump_is_generated_v3_hw(void *p)
+{
+	return p ? true : false;
+}
+
 static void debugfs_print_reg_v3_hw(u32 *regs_val, struct seq_file *s,
 				    const struct hisi_sas_debugfs_reg *reg)
 {
@@ -3601,6 +3606,9 @@ static int debugfs_global_v3_hw_show(struct seq_file *s, void *p)
 {
 	struct hisi_sas_debugfs_regs *global = s->private;
 
+	if (!debugfs_dump_is_generated_v3_hw(global->data))
+		return -EPERM;
+
 	debugfs_print_reg_v3_hw(global->data, s,
 				&debugfs_global_reg);
 
@@ -3612,6 +3620,9 @@ static int debugfs_axi_v3_hw_show(struct seq_file *s, void *p)
 {
 	struct hisi_sas_debugfs_regs *axi = s->private;
 
+	if (!debugfs_dump_is_generated_v3_hw(axi->data))
+		return -EPERM;
+
 	debugfs_print_reg_v3_hw(axi->data, s,
 				&debugfs_axi_reg);
 
@@ -3623,6 +3634,9 @@ static int debugfs_ras_v3_hw_show(struct seq_file *s, void *p)
 {
 	struct hisi_sas_debugfs_regs *ras = s->private;
 
+	if (!debugfs_dump_is_generated_v3_hw(ras->data))
+		return -EPERM;
+
 	debugfs_print_reg_v3_hw(ras->data, s,
 				&debugfs_ras_reg);
 
@@ -3635,6 +3649,9 @@ static int debugfs_port_v3_hw_show(struct seq_file *s, void *p)
 	struct hisi_sas_debugfs_port *port = s->private;
 	const struct hisi_sas_debugfs_reg *reg_port = &debugfs_port_reg;
 
+	if (!debugfs_dump_is_generated_v3_hw(port->data))
+		return -EPERM;
+
 	debugfs_print_reg_v3_hw(port->data, s, reg_port);
 
 	return 0;
@@ -3690,6 +3707,9 @@ static int debugfs_cq_v3_hw_show(struct seq_file *s, void *p)
 	struct hisi_sas_debugfs_cq *debugfs_cq = s->private;
 	int slot;
 
+	if (!debugfs_dump_is_generated_v3_hw(debugfs_cq->complete_hdr))
+		return -EPERM;
+
 	for (slot = 0; slot < HISI_SAS_QUEUE_SLOTS; slot++)
 		debugfs_cq_show_slot_v3_hw(s, slot, debugfs_cq);
 
@@ -3711,8 +3731,12 @@ static void debugfs_dq_show_slot_v3_hw(struct seq_file *s, int slot,
 
 static int debugfs_dq_v3_hw_show(struct seq_file *s, void *p)
 {
+	struct hisi_sas_debugfs_dq *debugfs_dq = s->private;
 	int slot;
 
+	if (!debugfs_dump_is_generated_v3_hw(debugfs_dq->hdr))
+		return -EPERM;
+
 	for (slot = 0; slot < HISI_SAS_QUEUE_SLOTS; slot++)
 		debugfs_dq_show_slot_v3_hw(s, slot, s->private);
 
@@ -3726,6 +3750,9 @@ static int debugfs_iost_v3_hw_show(struct seq_file *s, void *p)
 	struct hisi_sas_iost *iost = debugfs_iost->iost;
 	int i, max_command_entries = HISI_SAS_MAX_COMMANDS;
 
+	if (!debugfs_dump_is_generated_v3_hw(iost))
+		return -EPERM;
+
 	for (i = 0; i < max_command_entries; i++, iost++) {
 		__le64 *data = &iost->qw0;
 
@@ -3745,6 +3772,9 @@ static int debugfs_iost_cache_v3_hw_show(struct seq_file *s, void *p)
 	int i, tab_idx;
 	__le64 *iost;
 
+	if (!debugfs_dump_is_generated_v3_hw(iost_cache))
+		return -EPERM;
+
 	for (i = 0; i < HISI_SAS_IOST_ITCT_CACHE_NUM; i++, iost_cache++) {
 		/*
 		 * Data struct of IOST cache:
@@ -3768,6 +3798,9 @@ static int debugfs_itct_v3_hw_show(struct seq_file *s, void *p)
 	struct hisi_sas_debugfs_itct *debugfs_itct = s->private;
 	struct hisi_sas_itct *itct = debugfs_itct->itct;
 
+	if (!debugfs_dump_is_generated_v3_hw(itct))
+		return -EPERM;
+
 	for (i = 0; i < HISI_SAS_MAX_ITCT_ENTRIES; i++, itct++) {
 		__le64 *data = &itct->qw0;
 
@@ -3787,6 +3820,9 @@ static int debugfs_itct_cache_v3_hw_show(struct seq_file *s, void *p)
 	int i, tab_idx;
 	__le64 *itct;
 
+	if (!debugfs_dump_is_generated_v3_hw(itct_cache))
+		return -EPERM;
+
 	for (i = 0; i < HISI_SAS_IOST_ITCT_CACHE_NUM; i++, itct_cache++) {
 		/*
 		 * Data struct of ITCT cache:
@@ -3804,10 +3840,9 @@ static int debugfs_itct_cache_v3_hw_show(struct seq_file *s, void *p)
 }
 DEFINE_SHOW_ATTRIBUTE(debugfs_itct_cache_v3_hw);
 
-static void debugfs_create_files_v3_hw(struct hisi_hba *hisi_hba)
+static void debugfs_create_files_v3_hw(struct hisi_hba *hisi_hba, int index)
 {
 	u64 *debugfs_timestamp;
-	int dump_index = hisi_hba->debugfs_dump_index;
 	struct dentry *dump_dentry;
 	struct dentry *dentry;
 	char name[256];
@@ -3815,17 +3850,17 @@ static void debugfs_create_files_v3_hw(struct hisi_hba *hisi_hba)
 	int c;
 	int d;
 
-	snprintf(name, 256, "%d", dump_index);
+	snprintf(name, 256, "%d", index);
 
 	dump_dentry = debugfs_create_dir(name, hisi_hba->debugfs_dump_dentry);
 
-	debugfs_timestamp = &hisi_hba->debugfs_timestamp[dump_index];
+	debugfs_timestamp = &hisi_hba->debugfs_timestamp[index];
 
 	debugfs_create_u64("timestamp", 0400, dump_dentry,
 			   debugfs_timestamp);
 
 	debugfs_create_file("global", 0400, dump_dentry,
-			    &hisi_hba->debugfs_regs[dump_index][DEBUGFS_GLOBAL],
+			    &hisi_hba->debugfs_regs[index][DEBUGFS_GLOBAL],
 			    &debugfs_global_v3_hw_fops);
 
 	/* Create port dir and files */
@@ -3834,7 +3869,7 @@ static void debugfs_create_files_v3_hw(struct hisi_hba *hisi_hba)
 		snprintf(name, 256, "%d", p);
 
 		debugfs_create_file(name, 0400, dentry,
-				    &hisi_hba->debugfs_port_reg[dump_index][p],
+				    &hisi_hba->debugfs_port_reg[index][p],
 				    &debugfs_port_v3_hw_fops);
 	}
 
@@ -3844,7 +3879,7 @@ static void debugfs_create_files_v3_hw(struct hisi_hba *hisi_hba)
 		snprintf(name, 256, "%d", c);
 
 		debugfs_create_file(name, 0400, dentry,
-				    &hisi_hba->debugfs_cq[dump_index][c],
+				    &hisi_hba->debugfs_cq[index][c],
 				    &debugfs_cq_v3_hw_fops);
 	}
 
@@ -3854,32 +3889,32 @@ static void debugfs_create_files_v3_hw(struct hisi_hba *hisi_hba)
 		snprintf(name, 256, "%d", d);
 
 		debugfs_create_file(name, 0400, dentry,
-				    &hisi_hba->debugfs_dq[dump_index][d],
+				    &hisi_hba->debugfs_dq[index][d],
 				    &debugfs_dq_v3_hw_fops);
 	}
 
 	debugfs_create_file("iost", 0400, dump_dentry,
-			    &hisi_hba->debugfs_iost[dump_index],
+			    &hisi_hba->debugfs_iost[index],
 			    &debugfs_iost_v3_hw_fops);
 
 	debugfs_create_file("iost_cache", 0400, dump_dentry,
-			    &hisi_hba->debugfs_iost_cache[dump_index],
+			    &hisi_hba->debugfs_iost_cache[index],
 			    &debugfs_iost_cache_v3_hw_fops);
 
 	debugfs_create_file("itct", 0400, dump_dentry,
-			    &hisi_hba->debugfs_itct[dump_index],
+			    &hisi_hba->debugfs_itct[index],
 			    &debugfs_itct_v3_hw_fops);
 
 	debugfs_create_file("itct_cache", 0400, dump_dentry,
-			    &hisi_hba->debugfs_itct_cache[dump_index],
+			    &hisi_hba->debugfs_itct_cache[index],
 			    &debugfs_itct_cache_v3_hw_fops);
 
 	debugfs_create_file("axi", 0400, dump_dentry,
-			    &hisi_hba->debugfs_regs[dump_index][DEBUGFS_AXI],
+			    &hisi_hba->debugfs_regs[index][DEBUGFS_AXI],
 			    &debugfs_axi_v3_hw_fops);
 
 	debugfs_create_file("ras", 0400, dump_dentry,
-			    &hisi_hba->debugfs_regs[dump_index][DEBUGFS_RAS],
+			    &hisi_hba->debugfs_regs[index][DEBUGFS_RAS],
 			    &debugfs_ras_v3_hw_fops);
 }
 
@@ -4542,22 +4577,34 @@ static void debugfs_release_v3_hw(struct hisi_hba *hisi_hba, int dump_index)
 	int i;
 
 	devm_kfree(dev, hisi_hba->debugfs_iost_cache[dump_index].cache);
+	hisi_hba->debugfs_iost_cache[dump_index].cache = NULL;
 	devm_kfree(dev, hisi_hba->debugfs_itct_cache[dump_index].cache);
+	hisi_hba->debugfs_itct_cache[dump_index].cache = NULL;
 	devm_kfree(dev, hisi_hba->debugfs_iost[dump_index].iost);
+	hisi_hba->debugfs_iost[dump_index].iost = NULL;
 	devm_kfree(dev, hisi_hba->debugfs_itct[dump_index].itct);
+	hisi_hba->debugfs_itct[dump_index].itct = NULL;
 
-	for (i = 0; i < hisi_hba->queue_count; i++)
+	for (i = 0; i < hisi_hba->queue_count; i++) {
 		devm_kfree(dev, hisi_hba->debugfs_dq[dump_index][i].hdr);
+		hisi_hba->debugfs_dq[dump_index][i].hdr = NULL;
+	}
 
-	for (i = 0; i < hisi_hba->queue_count; i++)
+	for (i = 0; i < hisi_hba->queue_count; i++) {
 		devm_kfree(dev,
 			   hisi_hba->debugfs_cq[dump_index][i].complete_hdr);
+		hisi_hba->debugfs_cq[dump_index][i].complete_hdr = NULL;
+	}
 
-	for (i = 0; i < DEBUGFS_REGS_NUM; i++)
+	for (i = 0; i < DEBUGFS_REGS_NUM; i++) {
 		devm_kfree(dev, hisi_hba->debugfs_regs[dump_index][i].data);
+		hisi_hba->debugfs_regs[dump_index][i].data = NULL;
+	}
 
-	for (i = 0; i < hisi_hba->n_phy; i++)
+	for (i = 0; i < hisi_hba->n_phy; i++) {
 		devm_kfree(dev, hisi_hba->debugfs_port_reg[dump_index][i].data);
+		hisi_hba->debugfs_port_reg[dump_index][i].data = NULL;
+	}
 }
 
 static const struct hisi_sas_debugfs_reg *debugfs_reg_array_v3_hw[DEBUGFS_REGS_NUM] = {
@@ -4684,8 +4731,6 @@ static int debugfs_snapshot_regs_v3_hw(struct hisi_hba *hisi_hba)
 	debugfs_snapshot_itct_reg_v3_hw(hisi_hba);
 	debugfs_snapshot_iost_reg_v3_hw(hisi_hba);
 
-	debugfs_create_files_v3_hw(hisi_hba);
-
 	debugfs_snapshot_restore_v3_hw(hisi_hba);
 	hisi_hba->debugfs_dump_index++;
 
@@ -4769,6 +4814,17 @@ static void debugfs_bist_init_v3_hw(struct hisi_hba *hisi_hba)
 	hisi_hba->debugfs_bist_linkrate = SAS_LINK_RATE_1_5_GBPS;
 }
 
+static void debugfs_dump_init_v3_hw(struct hisi_hba *hisi_hba)
+{
+	int i;
+
+	hisi_hba->debugfs_dump_dentry =
+			debugfs_create_dir("dump", hisi_hba->debugfs_dir);
+
+	for (i = 0; i < hisi_sas_debugfs_dump_count; i++)
+		debugfs_create_files_v3_hw(hisi_hba, i);
+}
+
 static void debugfs_exit_v3_hw(struct hisi_hba *hisi_hba)
 {
 	debugfs_remove_recursive(hisi_hba->debugfs_dir);
@@ -4784,8 +4840,7 @@ static void debugfs_init_v3_hw(struct hisi_hba *hisi_hba)
 	/* create bist structures */
 	debugfs_bist_init_v3_hw(hisi_hba);
 
-	hisi_hba->debugfs_dump_dentry =
-			debugfs_create_dir("dump", hisi_hba->debugfs_dir);
+	debugfs_dump_init_v3_hw(hisi_hba);
 
 	debugfs_phy_down_cnt_init_v3_hw(hisi_hba);
 	debugfs_fifo_init_v3_hw(hisi_hba);

From cae668130c07f6873718b6f5b415d22e1008f2c9 Mon Sep 17 00:00:00 2001
From: Yihang Li <liyihang9@huawei.com>
Date: Tue, 8 Oct 2024 10:18:22 +0800
Subject: [PATCH 0397/1530] scsi: hisi_sas: Add latest_dump for the debugfs
 dump

Before that, after the user triggers the dump, the latest dump
information can be viewed in the directory with the maximum number in
the dump directory.

After this series patch, the driver creates all debugfs directories and
files during initialization. Therefore, users cannot know the directory
where the latest dump information is stored. So, add latest_dump file to
notify users where the latest dump information is stored.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Link: https://lore.kernel.org/r/20241008021822.2617339-14-liyihang9@huawei.com
Reviewed-by: Xingui Yang <yangxingui@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 8250d44f0b3e9..5db931663ae4e 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -4814,6 +4814,19 @@ static void debugfs_bist_init_v3_hw(struct hisi_hba *hisi_hba)
 	hisi_hba->debugfs_bist_linkrate = SAS_LINK_RATE_1_5_GBPS;
 }
 
+static int debugfs_dump_index_v3_hw_show(struct seq_file *s, void *p)
+{
+	int *debugfs_dump_index = s->private;
+
+	if (*debugfs_dump_index > 0)
+		seq_printf(s, "%d\n", *debugfs_dump_index - 1);
+	else
+		seq_puts(s, "dump not triggered\n");
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(debugfs_dump_index_v3_hw);
+
 static void debugfs_dump_init_v3_hw(struct hisi_hba *hisi_hba)
 {
 	int i;
@@ -4821,6 +4834,10 @@ static void debugfs_dump_init_v3_hw(struct hisi_hba *hisi_hba)
 	hisi_hba->debugfs_dump_dentry =
 			debugfs_create_dir("dump", hisi_hba->debugfs_dir);
 
+	debugfs_create_file("latest_dump", 0400, hisi_hba->debugfs_dump_dentry,
+			    &hisi_hba->debugfs_dump_index,
+			    &debugfs_dump_index_v3_hw_fops);
+
 	for (i = 0; i < hisi_sas_debugfs_dump_count; i++)
 		debugfs_create_files_v3_hw(hisi_hba, i);
 }

From ffb30875172eabff727e2896f097ccd4bb68723f Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 15 Oct 2024 08:58:47 +0200
Subject: [PATCH 0398/1530] dt-bindings: pinctrl: samsung: Fix interrupt
 constraint for variants with fallbacks

Commit 904140fa4553 ("dt-bindings: pinctrl: samsung: use Exynos7
fallbacks for newer wake-up controllers") added
samsung,exynos7-wakeup-eint fallback to some compatibles, so the
intention in the if:then: conditions was to handle the cases:

1. Single Exynos7 compatible or Exynos5433+Exynos7 or
   Exynos7885+Exynos7: only one interrupt

2. Exynos850+Exynos7: no interrupts

This was not implemented properly however and if:then: block matches
only single Exynos5433 or Exynos7885 compatibles, which do not exist in
DTS anymore, so basically is a no-op and no enforcement on number of
interrupts is made by the binding.

Fix the if:then: condition so interrupts in the Exynos5433 and
Exynos7885 wake-up pin controller will be properly constrained.

Fixes: 904140fa4553 ("dt-bindings: pinctrl: samsung: use Exynos7 fallbacks for newer wake-up controllers")
Cc: stable@vger.kernel.org
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20241015065848.29429-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../samsung,pinctrl-wakeup-interrupt.yaml     | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
index 91516fedc872c..49cb2b1a3d28d 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
@@ -92,14 +92,17 @@ allOf:
   - if:
       properties:
         compatible:
-          # Match without "contains", to skip newer variants which are still
-          # compatible with samsung,exynos7-wakeup-eint
-          enum:
-            - samsung,s5pv210-wakeup-eint
-            - samsung,exynos4210-wakeup-eint
-            - samsung,exynos5433-wakeup-eint
-            - samsung,exynos7-wakeup-eint
-            - samsung,exynos7885-wakeup-eint
+          oneOf:
+            # Match without "contains", to skip newer variants which are still
+            # compatible with samsung,exynos7-wakeup-eint
+            - enum:
+                - samsung,exynos4210-wakeup-eint
+                - samsung,exynos7-wakeup-eint
+                - samsung,s5pv210-wakeup-eint
+            - contains:
+                enum:
+                  - samsung,exynos5433-wakeup-eint
+                  - samsung,exynos7885-wakeup-eint
     then:
       properties:
         interrupts:

From e0f89ba1e04307a0060b354c40d29d008a3fef6e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 15 Oct 2024 08:58:48 +0200
Subject: [PATCH 0399/1530] dt-bindings: pinctrl: samsung: Add missing
 constraint for Exynos8895 interrupts

Expect only one interrupt on Exynos8895 wake-up pin controller.

Fixes: e2d58d1e1c61 ("dt-bindings: pinctrl: samsung: add exynos8895-wakeup-eint compatible")
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20241015065848.29429-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml       | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
index 49cb2b1a3d28d..b7c2692f0ac37 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
@@ -103,6 +103,7 @@ allOf:
                 enum:
                   - samsung,exynos5433-wakeup-eint
                   - samsung,exynos7885-wakeup-eint
+                  - samsung,exynos8895-wakeup-eint
     then:
       properties:
         interrupts:

From 5fb0ecf73e7ad59e7b3e4cd47a3d1a67eaa200af Mon Sep 17 00:00:00 2001
From: Drew Fustini <drew@pdp7.com>
Date: Mon, 14 Oct 2024 13:53:15 -0700
Subject: [PATCH 0400/1530] riscv: defconfig: enable gpio support for TH1520

Enable gpio-dwapb driver which is used by TH1520-based boards like the
BeagleV Ahead and the Sipeed LicheePi 4A.

Signed-off-by: Drew Fustini <drew@pdp7.com>
Link: https://lore.kernel.org/r/20241014205315.1349391-1-drew@pdp7.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/configs/defconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 2341393cfac1a..cfc887a7243d1 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -167,6 +167,7 @@ CONFIG_PINCTRL_SOPHGO_CV1800B=y
 CONFIG_PINCTRL_SOPHGO_CV1812H=y
 CONFIG_PINCTRL_SOPHGO_SG2000=y
 CONFIG_PINCTRL_SOPHGO_SG2002=y
+CONFIG_GPIO_DWAPB=y
 CONFIG_GPIO_SIFIVE=y
 CONFIG_POWER_RESET_GPIO_RESTART=y
 CONFIG_SENSORS_SFCTEMP=m

From 9c12b96ee244b9679629ac430c375a720bfec04b Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 7 Oct 2024 13:23:57 +0000
Subject: [PATCH 0401/1530] mailbox, remoteproc: k3-m4+: fix compile testing

The k3-m4 remoteproc driver was merged with incorrect dependencies.
Despite multiple people trying to fix this, the version 6.12-rc2
remains broken and causes a build failure with CONFIG_TI_SCI_PROTOCOL=m
when the driver is built-in.

arm-linux-gnueabi-ld: drivers/remoteproc/ti_k3_m4_remoteproc.o: in function `k3_m4_rproc_probe':
ti_k3_m4_remoteproc.c:(.text.k3_m4_rproc_probe+0x76): undefined reference to `devm_ti_sci_get_by_phandle'

Fix the dependency again to make it work in all configurations.
The 'select OMAP2PLUS_MBOX' no longer matches what the other drivers
dependencies. The link failure can be avoided with a simple 'depends
do, so turn that into the same 'depends' to ensure we get no circular
on TI_SCI_PROTOCOL', but the extra COMPILE_TEST alternative is what
we use elsehwere. On the other hand, building for OMAP2PLUS makes
no sense since the hardware only exists on K3.

Fixes: ebcf9008a895 ("remoteproc: k3-m4: Add a remoteproc driver for M4F subsystem")
Fixes: ba0c0cb56f22 ("remoteproc: k3-m4: use the proper dependencies")
Fixes: 54595f2807d2 ("mailbox, remoteproc: omap2+: fix compile testing")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20241007132441.2732215-1-arnd@kernel.org
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/Kconfig | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index 955e4e38477e6..62f8548fb46a5 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -341,9 +341,9 @@ config TI_K3_DSP_REMOTEPROC
 
 config TI_K3_M4_REMOTEPROC
 	tristate "TI K3 M4 remoteproc support"
-	depends on ARCH_OMAP2PLUS || ARCH_K3
-	select MAILBOX
-	select OMAP2PLUS_MBOX
+	depends on ARCH_K3 || COMPILE_TEST
+	depends on TI_SCI_PROTOCOL || (COMPILE_TEST && TI_SCI_PROTOCOL=n)
+	depends on OMAP2PLUS_MBOX
 	help
 	  Say m here to support TI's M4 remote processor subsystems
 	  on various TI K3 family of SoCs through the remote processor

From 1acd73edbbfef2c3c5b43cba4006a7797eca7050 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Tue, 15 Oct 2024 11:43:39 +0800
Subject: [PATCH 0402/1530] f2fs: fix to account dirty data in
 __get_secs_required()

It will trigger system panic w/ testcase in [1]:

------------[ cut here ]------------
kernel BUG at fs/f2fs/segment.c:2752!
RIP: 0010:new_curseg+0xc81/0x2110
Call Trace:
 f2fs_allocate_data_block+0x1c91/0x4540
 do_write_page+0x163/0xdf0
 f2fs_outplace_write_data+0x1aa/0x340
 f2fs_do_write_data_page+0x797/0x2280
 f2fs_write_single_data_page+0x16cd/0x2190
 f2fs_write_cache_pages+0x994/0x1c80
 f2fs_write_data_pages+0x9cc/0xea0
 do_writepages+0x194/0x7a0
 filemap_fdatawrite_wbc+0x12b/0x1a0
 __filemap_fdatawrite_range+0xbb/0xf0
 file_write_and_wait_range+0xa1/0x110
 f2fs_do_sync_file+0x26f/0x1c50
 f2fs_sync_file+0x12b/0x1d0
 vfs_fsync_range+0xfa/0x230
 do_fsync+0x3d/0x80
 __x64_sys_fsync+0x37/0x50
 x64_sys_call+0x1e88/0x20d0
 do_syscall_64+0x4b/0x110
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

The root cause is if checkpoint_disabling and lfs_mode are both on,
it will trigger OPU for all overwritten data, it may cost more free
segment than expected, so f2fs must account those data correctly to
calculate cosumed free segments later, and return ENOSPC earlier to
avoid run out of free segment during block allocation.

[1] https://lore.kernel.org/fstests/20241015025106.3203676-1-chao@kernel.org/

Fixes: 4354994f097d ("f2fs: checkpoint disabling")
Cc: Daniel Rosenberg <drosen@google.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/segment.h | 35 +++++++++++++++++++++++++----------
 1 file changed, 25 insertions(+), 10 deletions(-)

diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index e9cc73093417e..55a01da6c4be5 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -561,18 +561,21 @@ static inline int reserved_sections(struct f2fs_sb_info *sbi)
 }
 
 static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi,
-			unsigned int node_blocks, unsigned int dent_blocks)
+			unsigned int node_blocks, unsigned int data_blocks,
+			unsigned int dent_blocks)
 {
 
-	unsigned segno, left_blocks;
+	unsigned int segno, left_blocks, blocks;
 	int i;
 
-	/* check current node sections in the worst case. */
-	for (i = CURSEG_HOT_NODE; i <= CURSEG_COLD_NODE; i++) {
+	/* check current data/node sections in the worst case. */
+	for (i = CURSEG_HOT_DATA; i < NR_PERSISTENT_LOG; i++) {
 		segno = CURSEG_I(sbi, i)->segno;
 		left_blocks = CAP_BLKS_PER_SEC(sbi) -
 				get_ckpt_valid_blocks(sbi, segno, true);
-		if (node_blocks > left_blocks)
+
+		blocks = i <= CURSEG_COLD_DATA ? data_blocks : node_blocks;
+		if (blocks > left_blocks)
 			return false;
 	}
 
@@ -586,8 +589,9 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi,
 }
 
 /*
- * calculate needed sections for dirty node/dentry
- * and call has_curseg_enough_space
+ * calculate needed sections for dirty node/dentry and call
+ * has_curseg_enough_space, please note that, it needs to account
+ * dirty data as well in lfs mode when checkpoint is disabled.
  */
 static inline void __get_secs_required(struct f2fs_sb_info *sbi,
 		unsigned int *lower_p, unsigned int *upper_p, bool *curseg_p)
@@ -596,19 +600,30 @@ static inline void __get_secs_required(struct f2fs_sb_info *sbi,
 					get_pages(sbi, F2FS_DIRTY_DENTS) +
 					get_pages(sbi, F2FS_DIRTY_IMETA);
 	unsigned int total_dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS);
+	unsigned int total_data_blocks = 0;
 	unsigned int node_secs = total_node_blocks / CAP_BLKS_PER_SEC(sbi);
 	unsigned int dent_secs = total_dent_blocks / CAP_BLKS_PER_SEC(sbi);
+	unsigned int data_secs = 0;
 	unsigned int node_blocks = total_node_blocks % CAP_BLKS_PER_SEC(sbi);
 	unsigned int dent_blocks = total_dent_blocks % CAP_BLKS_PER_SEC(sbi);
+	unsigned int data_blocks = 0;
+
+	if (f2fs_lfs_mode(sbi) &&
+		unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+		total_data_blocks = get_pages(sbi, F2FS_DIRTY_DATA);
+		data_secs = total_data_blocks / CAP_BLKS_PER_SEC(sbi);
+		data_blocks = total_data_blocks % CAP_BLKS_PER_SEC(sbi);
+	}
 
 	if (lower_p)
-		*lower_p = node_secs + dent_secs;
+		*lower_p = node_secs + dent_secs + data_secs;
 	if (upper_p)
 		*upper_p = node_secs + dent_secs +
-			(node_blocks ? 1 : 0) + (dent_blocks ? 1 : 0);
+			(node_blocks ? 1 : 0) + (dent_blocks ? 1 : 0) +
+			(data_blocks ? 1 : 0);
 	if (curseg_p)
 		*curseg_p = has_curseg_enough_space(sbi,
-				node_blocks, dent_blocks);
+				node_blocks, data_blocks, dent_blocks);
 }
 
 static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,

From ce1dfe6d328966b75821c1f043a940eb2569768a Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Sat, 12 Oct 2024 20:32:43 +0900
Subject: [PATCH 0403/1530] PCI: endpoint: Introduce pci_epc_mem_map()/unmap()

Some endpoint controllers have requirements on the alignment of the
controller physical memory address that must be used to map a RC PCI
address region. For instance, the endpoint controller of the RK3399 SoC
uses at most the lower 20 bits of a physical memory address region as
the lower bits of a RC PCI address region. For mapping a PCI address
region of size bytes starting from pci_addr, the exact number of
address bits used is the number of address bits changing in the address
range [pci_addr..pci_addr + size - 1]. For this example, this creates
the following constraints:
1) The offset into the controller physical memory allocated for a
   mapping depends on the mapping size *and* the starting PCI address
   for the mapping.
2) A mapping size cannot exceed the controller windows size (1MB) minus
   the offset needed into the allocated physical memory, which can end
   up being a smaller size than the desired mapping size.

Handling these constraints independently of the controller being used
in an endpoint function driver is not possible with the current EPC
API as only the ->align field in struct pci_epc_features is provided
but used for BAR (inbound ATU mappings) mapping only. A new API is
needed for function drivers to discover mapping constraints and handle
non-static requirements based on the RC PCI address range to access.

Introduce the endpoint controller operation ->align_addr() to allow
the EPC core functions to obtain the size and the offset into a
controller address region that must be allocated and mapped to access
a RC PCI address region. The size of the mapping provided by the
align_addr() operation can then be used as the size argument for the
function pci_epc_mem_alloc_addr() and the offset into the allocated
controller memory provided can be used to correctly handle data
transfers. For endpoint controllers that have PCI address alignment
constraints, the align_addr() operation may indicate upon return an
effective PCI address mapping size that is smaller (but not 0) than the
requested PCI address region size.

The controller ->align_addr() operation is optional: controllers that
do not have any alignment constraints for mapping RC PCI address regions
do not need to implement this operation. For such controllers, it is
always assumed that the mapping size is equal to the requested size of
the PCI region and that the mapping offset is 0.

The function pci_epc_mem_map() is introduced to use this new controller
operation (if it is defined) to handle controller memory allocation and
mapping to a RC PCI address region in endpoint function drivers.

This function first uses the ->align_addr() controller operation to
determine the controller memory address size (and offset into) needed
for mapping an RC PCI address region. The result of this operation is
used to allocate a controller physical memory region using
pci_epc_mem_alloc_addr() and then to map that memory to the RC PCI
address space with pci_epc_map_addr().

Since ->align_addr() () may indicate that not all of a RC PCI address
region can be mapped, pci_epc_mem_map() may only partially map the RC
PCI address region specified. It is the responsibility of the caller
(an endpoint function driver) to handle such smaller mapping by
repeatedly using pci_epc_mem_map() over the desried PCI address range.

The counterpart of pci_epc_mem_map() to unmap and free a mapped
controller memory address region is pci_epc_mem_unmap().

Both functions operate using the new struct pci_epc_map data structure.
This new structure represents a mapping PCI address, mapping effective
size, the size of the controller memory needed for the mapping as well
as the physical and virtual CPU addresses of the mapping (phys_base and
virt_base fields). For convenience, the physical and virtual CPU
addresses within that mapping to use to access the target RC PCI address
region are also provided (phys_addr and virt_addr fields).

Endpoint function drivers can use struct pci_epc_map to access the
mapped RC PCI address region using the ->virt_addr and ->pci_size
fields.

Co-developed-by: Rick Wertenbroek <rick.wertenbroek@gmail.com>
Signed-off-by: Rick Wertenbroek <rick.wertenbroek@gmail.com>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20241012113246.95634-4-dlemoal@kernel.org
[mani: squashed the patch that changed phy_addr_t to u64]
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/endpoint/pci-epc-core.c | 103 ++++++++++++++++++++++++++++
 include/linux/pci-epc.h             |  38 ++++++++++
 2 files changed, 141 insertions(+)

diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index b854f1bab26f8..04a85d2f7e2a8 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -466,6 +466,109 @@ int pci_epc_map_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 }
 EXPORT_SYMBOL_GPL(pci_epc_map_addr);
 
+/**
+ * pci_epc_mem_map() - allocate and map a PCI address to a CPU address
+ * @epc: the EPC device on which the CPU address is to be allocated and mapped
+ * @func_no: the physical endpoint function number in the EPC device
+ * @vfunc_no: the virtual endpoint function number in the physical function
+ * @pci_addr: PCI address to which the CPU address should be mapped
+ * @pci_size: the number of bytes to map starting from @pci_addr
+ * @map: where to return the mapping information
+ *
+ * Allocate a controller memory address region and map it to a RC PCI address
+ * region, taking into account the controller physical address mapping
+ * constraints using the controller operation align_addr(). If this operation is
+ * not defined, we assume that there are no alignment constraints for the
+ * mapping.
+ *
+ * The effective size of the PCI address range mapped from @pci_addr is
+ * indicated by @map->pci_size. This size may be less than the requested
+ * @pci_size. The local virtual CPU address for the mapping is indicated by
+ * @map->virt_addr (@map->phys_addr indicates the physical address).
+ * The size and CPU address of the controller memory allocated and mapped are
+ * respectively indicated by @map->map_size and @map->virt_base (and
+ * @map->phys_base for the physical address of @map->virt_base).
+ *
+ * Returns 0 on success and a negative error code in case of error.
+ */
+int pci_epc_mem_map(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
+		    u64 pci_addr, size_t pci_size, struct pci_epc_map *map)
+{
+	size_t map_size = pci_size;
+	size_t map_offset = 0;
+	int ret;
+
+	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
+		return -EINVAL;
+
+	if (!pci_size || !map)
+		return -EINVAL;
+
+	/*
+	 * Align the PCI address to map. If the controller defines the
+	 * .align_addr() operation, use it to determine the PCI address to map
+	 * and the size of the mapping. Otherwise, assume that the controller
+	 * has no alignment constraint.
+	 */
+	memset(map, 0, sizeof(*map));
+	map->pci_addr = pci_addr;
+	if (epc->ops->align_addr)
+		map->map_pci_addr =
+			epc->ops->align_addr(epc, pci_addr,
+					     &map_size, &map_offset);
+	else
+		map->map_pci_addr = pci_addr;
+	map->map_size = map_size;
+	if (map->map_pci_addr + map->map_size < pci_addr + pci_size)
+		map->pci_size = map->map_pci_addr + map->map_size - pci_addr;
+	else
+		map->pci_size = pci_size;
+
+	map->virt_base = pci_epc_mem_alloc_addr(epc, &map->phys_base,
+						map->map_size);
+	if (!map->virt_base)
+		return -ENOMEM;
+
+	map->phys_addr = map->phys_base + map_offset;
+	map->virt_addr = map->virt_base + map_offset;
+
+	ret = pci_epc_map_addr(epc, func_no, vfunc_no, map->phys_base,
+			       map->map_pci_addr, map->map_size);
+	if (ret) {
+		pci_epc_mem_free_addr(epc, map->phys_base, map->virt_base,
+				      map->map_size);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_epc_mem_map);
+
+/**
+ * pci_epc_mem_unmap() - unmap and free a CPU address region
+ * @epc: the EPC device on which the CPU address is allocated and mapped
+ * @func_no: the physical endpoint function number in the EPC device
+ * @vfunc_no: the virtual endpoint function number in the physical function
+ * @map: the mapping information
+ *
+ * Unmap and free a CPU address region that was allocated and mapped with
+ * pci_epc_mem_map().
+ */
+void pci_epc_mem_unmap(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
+		       struct pci_epc_map *map)
+{
+	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
+		return;
+
+	if (!map || !map->virt_base)
+		return;
+
+	pci_epc_unmap_addr(epc, func_no, vfunc_no, map->phys_base);
+	pci_epc_mem_free_addr(epc, map->phys_base, map->virt_base,
+			      map->map_size);
+}
+EXPORT_SYMBOL_GPL(pci_epc_mem_unmap);
+
 /**
  * pci_epc_clear_bar() - reset the BAR
  * @epc: the EPC device for which the BAR has to be cleared
diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h
index 42ef06136bd1a..de8cc3658220b 100644
--- a/include/linux/pci-epc.h
+++ b/include/linux/pci-epc.h
@@ -32,11 +32,43 @@ pci_epc_interface_string(enum pci_epc_interface_type type)
 	}
 }
 
+/**
+ * struct pci_epc_map - information about EPC memory for mapping a RC PCI
+ *                      address range
+ * @pci_addr: start address of the RC PCI address range to map
+ * @pci_size: size of the RC PCI address range mapped from @pci_addr
+ * @map_pci_addr: RC PCI address used as the first address mapped (may be lower
+ *                than @pci_addr)
+ * @map_size: size of the controller memory needed for mapping the RC PCI address
+ *            range @pci_addr..@pci_addr+@pci_size
+ * @phys_base: base physical address of the allocated EPC memory for mapping the
+ *             RC PCI address range
+ * @phys_addr: physical address at which @pci_addr is mapped
+ * @virt_base: base virtual address of the allocated EPC memory for mapping the
+ *             RC PCI address range
+ * @virt_addr: virtual address at which @pci_addr is mapped
+ */
+struct pci_epc_map {
+	u64		pci_addr;
+	size_t		pci_size;
+
+	u64		map_pci_addr;
+	size_t		map_size;
+
+	phys_addr_t	phys_base;
+	phys_addr_t	phys_addr;
+	void __iomem	*virt_base;
+	void __iomem	*virt_addr;
+};
+
 /**
  * struct pci_epc_ops - set of function pointers for performing EPC operations
  * @write_header: ops to populate configuration space header
  * @set_bar: ops to configure the BAR
  * @clear_bar: ops to reset the BAR
+ * @align_addr: operation to get the mapping address, mapping size and offset
+ *		into a controller memory window needed to map an RC PCI address
+ *		region
  * @map_addr: ops to map CPU address to PCI address
  * @unmap_addr: ops to unmap CPU address and PCI address
  * @set_msi: ops to set the requested number of MSI interrupts in the MSI
@@ -61,6 +93,8 @@ struct pci_epc_ops {
 			   struct pci_epf_bar *epf_bar);
 	void	(*clear_bar)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			     struct pci_epf_bar *epf_bar);
+	u64	(*align_addr)(struct pci_epc *epc, u64 pci_addr, size_t *size,
+			      size_t *offset);
 	int	(*map_addr)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			    phys_addr_t addr, u64 pci_addr, size_t size);
 	void	(*unmap_addr)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
@@ -278,6 +312,10 @@ void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc,
 				     phys_addr_t *phys_addr, size_t size);
 void pci_epc_mem_free_addr(struct pci_epc *epc, phys_addr_t phys_addr,
 			   void __iomem *virt_addr, size_t size);
+int pci_epc_mem_map(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
+		    u64 pci_addr, size_t pci_size, struct pci_epc_map *map);
+void pci_epc_mem_unmap(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
+		       struct pci_epc_map *map);
 
 #else
 static inline void pci_epc_init_notify(struct pci_epc *epc)

From 6067ccf36fbc8a5e5a32f15b267e3dc6aa6e7eb4 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Sat, 12 Oct 2024 20:32:44 +0900
Subject: [PATCH 0404/1530] PCI: endpoint: Update documentation

Document the new functions pci_epc_mem_map() and pci_epc_mem_unmap().
Also add the documentation for the functions pci_epc_map_addr() and
pci_epc_unmap_addr() that were missing.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20241012113246.95634-5-dlemoal@kernel.org
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 Documentation/PCI/endpoint/pci-endpoint.rst | 29 +++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/Documentation/PCI/endpoint/pci-endpoint.rst b/Documentation/PCI/endpoint/pci-endpoint.rst
index 21507e3cc2385..35f82f2d45f5e 100644
--- a/Documentation/PCI/endpoint/pci-endpoint.rst
+++ b/Documentation/PCI/endpoint/pci-endpoint.rst
@@ -117,6 +117,35 @@ by the PCI endpoint function driver.
    The PCI endpoint function driver should use pci_epc_mem_free_addr() to
    free the memory space allocated using pci_epc_mem_alloc_addr().
 
+* pci_epc_map_addr()
+
+  A PCI endpoint function driver should use pci_epc_map_addr() to map to a RC
+  PCI address the CPU address of local memory obtained with
+  pci_epc_mem_alloc_addr().
+
+* pci_epc_unmap_addr()
+
+  A PCI endpoint function driver should use pci_epc_unmap_addr() to unmap the
+  CPU address of local memory mapped to a RC address with pci_epc_map_addr().
+
+* pci_epc_mem_map()
+
+  A PCI endpoint controller may impose constraints on the RC PCI addresses that
+  can be mapped. The function pci_epc_mem_map() allows endpoint function
+  drivers to allocate and map controller memory while handling such
+  constraints. This function will determine the size of the memory that must be
+  allocated with pci_epc_mem_alloc_addr() for successfully mapping a RC PCI
+  address range. This function will also indicate the size of the PCI address
+  range that was actually mapped, which can be less than the requested size, as
+  well as the offset into the allocated memory to use for accessing the mapped
+  RC PCI address range.
+
+* pci_epc_mem_unmap()
+
+  A PCI endpoint function driver can use pci_epc_mem_unmap() to unmap and free
+  controller memory that was allocated and mapped using pci_epc_mem_map().
+
+
 Other EPC APIs
 ~~~~~~~~~~~~~~
 

From 08cac1006bfcc35fe363055a40e05d5410cdf010 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Sat, 12 Oct 2024 20:32:45 +0900
Subject: [PATCH 0405/1530] PCI: endpoint: test: Use pci_epc_mem_map/unmap()

Modify the endpoint test driver to use the functions pci_epc_mem_map()
and pci_epc_mem_unmap() for the read, write and copy tests. For each
test case, the transfer (dma or mmio) are executed in a loop to ensure
that potentially partial mappings returned by pci_epc_mem_map() are
correctly handled.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20241012113246.95634-6-dlemoal@kernel.org
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/endpoint/functions/pci-epf-test.c | 372 +++++++++---------
 1 file changed, 193 insertions(+), 179 deletions(-)

diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 7c2ed6eae53ad..a73bc0771d358 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -317,91 +317,92 @@ static void pci_epf_test_print_rate(struct pci_epf_test *epf_test,
 static void pci_epf_test_copy(struct pci_epf_test *epf_test,
 			      struct pci_epf_test_reg *reg)
 {
-	int ret;
-	void __iomem *src_addr;
-	void __iomem *dst_addr;
-	phys_addr_t src_phys_addr;
-	phys_addr_t dst_phys_addr;
+	int ret = 0;
 	struct timespec64 start, end;
 	struct pci_epf *epf = epf_test->epf;
-	struct device *dev = &epf->dev;
 	struct pci_epc *epc = epf->epc;
+	struct device *dev = &epf->dev;
+	struct pci_epc_map src_map, dst_map;
+	u64 src_addr = reg->src_addr;
+	u64 dst_addr = reg->dst_addr;
+	size_t copy_size = reg->size;
+	ssize_t map_size = 0;
+	void *copy_buf = NULL, *buf;
 
-	src_addr = pci_epc_mem_alloc_addr(epc, &src_phys_addr, reg->size);
-	if (!src_addr) {
-		dev_err(dev, "Failed to allocate source address\n");
-		reg->status = STATUS_SRC_ADDR_INVALID;
-		ret = -ENOMEM;
-		goto err;
-	}
-
-	ret = pci_epc_map_addr(epc, epf->func_no, epf->vfunc_no, src_phys_addr,
-			       reg->src_addr, reg->size);
-	if (ret) {
-		dev_err(dev, "Failed to map source address\n");
-		reg->status = STATUS_SRC_ADDR_INVALID;
-		goto err_src_addr;
-	}
-
-	dst_addr = pci_epc_mem_alloc_addr(epc, &dst_phys_addr, reg->size);
-	if (!dst_addr) {
-		dev_err(dev, "Failed to allocate destination address\n");
-		reg->status = STATUS_DST_ADDR_INVALID;
-		ret = -ENOMEM;
-		goto err_src_map_addr;
-	}
-
-	ret = pci_epc_map_addr(epc, epf->func_no, epf->vfunc_no, dst_phys_addr,
-			       reg->dst_addr, reg->size);
-	if (ret) {
-		dev_err(dev, "Failed to map destination address\n");
-		reg->status = STATUS_DST_ADDR_INVALID;
-		goto err_dst_addr;
-	}
-
-	ktime_get_ts64(&start);
 	if (reg->flags & FLAG_USE_DMA) {
 		if (epf_test->dma_private) {
 			dev_err(dev, "Cannot transfer data using DMA\n");
 			ret = -EINVAL;
-			goto err_map_addr;
+			goto set_status;
 		}
-
-		ret = pci_epf_test_data_transfer(epf_test, dst_phys_addr,
-						 src_phys_addr, reg->size, 0,
-						 DMA_MEM_TO_MEM);
-		if (ret)
-			dev_err(dev, "Data transfer failed\n");
 	} else {
-		void *buf;
-
-		buf = kzalloc(reg->size, GFP_KERNEL);
-		if (!buf) {
+		copy_buf = kzalloc(copy_size, GFP_KERNEL);
+		if (!copy_buf) {
 			ret = -ENOMEM;
-			goto err_map_addr;
+			goto set_status;
 		}
-
-		memcpy_fromio(buf, src_addr, reg->size);
-		memcpy_toio(dst_addr, buf, reg->size);
-		kfree(buf);
+		buf = copy_buf;
 	}
-	ktime_get_ts64(&end);
-	pci_epf_test_print_rate(epf_test, "COPY", reg->size, &start, &end,
-				reg->flags & FLAG_USE_DMA);
 
-err_map_addr:
-	pci_epc_unmap_addr(epc, epf->func_no, epf->vfunc_no, dst_phys_addr);
+	while (copy_size) {
+		ret = pci_epc_mem_map(epc, epf->func_no, epf->vfunc_no,
+				      src_addr, copy_size, &src_map);
+		if (ret) {
+			dev_err(dev, "Failed to map source address\n");
+			reg->status = STATUS_SRC_ADDR_INVALID;
+			goto free_buf;
+		}
+
+		ret = pci_epc_mem_map(epf->epc, epf->func_no, epf->vfunc_no,
+					   dst_addr, copy_size, &dst_map);
+		if (ret) {
+			dev_err(dev, "Failed to map destination address\n");
+			reg->status = STATUS_DST_ADDR_INVALID;
+			pci_epc_mem_unmap(epc, epf->func_no, epf->vfunc_no,
+					  &src_map);
+			goto free_buf;
+		}
+
+		map_size = min_t(size_t, dst_map.pci_size, src_map.pci_size);
+
+		ktime_get_ts64(&start);
+		if (reg->flags & FLAG_USE_DMA) {
+			ret = pci_epf_test_data_transfer(epf_test,
+					dst_map.phys_addr, src_map.phys_addr,
+					map_size, 0, DMA_MEM_TO_MEM);
+			if (ret) {
+				dev_err(dev, "Data transfer failed\n");
+				goto unmap;
+			}
+		} else {
+			memcpy_fromio(buf, src_map.virt_addr, map_size);
+			memcpy_toio(dst_map.virt_addr, buf, map_size);
+			buf += map_size;
+		}
+		ktime_get_ts64(&end);
 
-err_dst_addr:
-	pci_epc_mem_free_addr(epc, dst_phys_addr, dst_addr, reg->size);
+		copy_size -= map_size;
+		src_addr += map_size;
+		dst_addr += map_size;
 
-err_src_map_addr:
-	pci_epc_unmap_addr(epc, epf->func_no, epf->vfunc_no, src_phys_addr);
+		pci_epc_mem_unmap(epc, epf->func_no, epf->vfunc_no, &dst_map);
+		pci_epc_mem_unmap(epc, epf->func_no, epf->vfunc_no, &src_map);
+		map_size = 0;
+	}
 
-err_src_addr:
-	pci_epc_mem_free_addr(epc, src_phys_addr, src_addr, reg->size);
+	pci_epf_test_print_rate(epf_test, "COPY", reg->size, &start,
+				&end, reg->flags & FLAG_USE_DMA);
 
-err:
+unmap:
+	if (map_size) {
+		pci_epc_mem_unmap(epc, epf->func_no, epf->vfunc_no, &dst_map);
+		pci_epc_mem_unmap(epc, epf->func_no, epf->vfunc_no, &src_map);
+	}
+
+free_buf:
+	kfree(copy_buf);
+
+set_status:
 	if (!ret)
 		reg->status |= STATUS_COPY_SUCCESS;
 	else
@@ -411,82 +412,89 @@ static void pci_epf_test_copy(struct pci_epf_test *epf_test,
 static void pci_epf_test_read(struct pci_epf_test *epf_test,
 			      struct pci_epf_test_reg *reg)
 {
-	int ret;
-	void __iomem *src_addr;
-	void *buf;
+	int ret = 0;
+	void *src_buf, *buf;
 	u32 crc32;
-	phys_addr_t phys_addr;
+	struct pci_epc_map map;
 	phys_addr_t dst_phys_addr;
 	struct timespec64 start, end;
 	struct pci_epf *epf = epf_test->epf;
-	struct device *dev = &epf->dev;
 	struct pci_epc *epc = epf->epc;
+	struct device *dev = &epf->dev;
 	struct device *dma_dev = epf->epc->dev.parent;
+	u64 src_addr = reg->src_addr;
+	size_t src_size = reg->size;
+	ssize_t map_size = 0;
 
-	src_addr = pci_epc_mem_alloc_addr(epc, &phys_addr, reg->size);
-	if (!src_addr) {
-		dev_err(dev, "Failed to allocate address\n");
-		reg->status = STATUS_SRC_ADDR_INVALID;
+	src_buf = kzalloc(src_size, GFP_KERNEL);
+	if (!src_buf) {
 		ret = -ENOMEM;
-		goto err;
+		goto set_status;
 	}
+	buf = src_buf;
 
-	ret = pci_epc_map_addr(epc, epf->func_no, epf->vfunc_no, phys_addr,
-			       reg->src_addr, reg->size);
-	if (ret) {
-		dev_err(dev, "Failed to map address\n");
-		reg->status = STATUS_SRC_ADDR_INVALID;
-		goto err_addr;
-	}
-
-	buf = kzalloc(reg->size, GFP_KERNEL);
-	if (!buf) {
-		ret = -ENOMEM;
-		goto err_map_addr;
-	}
+	while (src_size) {
+		ret = pci_epc_mem_map(epc, epf->func_no, epf->vfunc_no,
+					   src_addr, src_size, &map);
+		if (ret) {
+			dev_err(dev, "Failed to map address\n");
+			reg->status = STATUS_SRC_ADDR_INVALID;
+			goto free_buf;
+		}
 
-	if (reg->flags & FLAG_USE_DMA) {
-		dst_phys_addr = dma_map_single(dma_dev, buf, reg->size,
-					       DMA_FROM_DEVICE);
-		if (dma_mapping_error(dma_dev, dst_phys_addr)) {
-			dev_err(dev, "Failed to map destination buffer addr\n");
-			ret = -ENOMEM;
-			goto err_dma_map;
+		map_size = map.pci_size;
+		if (reg->flags & FLAG_USE_DMA) {
+			dst_phys_addr = dma_map_single(dma_dev, buf, map_size,
+						       DMA_FROM_DEVICE);
+			if (dma_mapping_error(dma_dev, dst_phys_addr)) {
+				dev_err(dev,
+					"Failed to map destination buffer addr\n");
+				ret = -ENOMEM;
+				goto unmap;
+			}
+
+			ktime_get_ts64(&start);
+			ret = pci_epf_test_data_transfer(epf_test,
+					dst_phys_addr, map.phys_addr,
+					map_size, src_addr, DMA_DEV_TO_MEM);
+			if (ret)
+				dev_err(dev, "Data transfer failed\n");
+			ktime_get_ts64(&end);
+
+			dma_unmap_single(dma_dev, dst_phys_addr, map_size,
+					 DMA_FROM_DEVICE);
+
+			if (ret)
+				goto unmap;
+		} else {
+			ktime_get_ts64(&start);
+			memcpy_fromio(buf, map.virt_addr, map_size);
+			ktime_get_ts64(&end);
 		}
 
-		ktime_get_ts64(&start);
-		ret = pci_epf_test_data_transfer(epf_test, dst_phys_addr,
-						 phys_addr, reg->size,
-						 reg->src_addr, DMA_DEV_TO_MEM);
-		if (ret)
-			dev_err(dev, "Data transfer failed\n");
-		ktime_get_ts64(&end);
+		src_size -= map_size;
+		src_addr += map_size;
+		buf += map_size;
 
-		dma_unmap_single(dma_dev, dst_phys_addr, reg->size,
-				 DMA_FROM_DEVICE);
-	} else {
-		ktime_get_ts64(&start);
-		memcpy_fromio(buf, src_addr, reg->size);
-		ktime_get_ts64(&end);
+		pci_epc_mem_unmap(epc, epf->func_no, epf->vfunc_no, &map);
+		map_size = 0;
 	}
 
-	pci_epf_test_print_rate(epf_test, "READ", reg->size, &start, &end,
-				reg->flags & FLAG_USE_DMA);
+	pci_epf_test_print_rate(epf_test, "READ", reg->size, &start,
+				&end, reg->flags & FLAG_USE_DMA);
 
-	crc32 = crc32_le(~0, buf, reg->size);
+	crc32 = crc32_le(~0, src_buf, reg->size);
 	if (crc32 != reg->checksum)
 		ret = -EIO;
 
-err_dma_map:
-	kfree(buf);
-
-err_map_addr:
-	pci_epc_unmap_addr(epc, epf->func_no, epf->vfunc_no, phys_addr);
+unmap:
+	if (map_size)
+		pci_epc_mem_unmap(epc, epf->func_no, epf->vfunc_no, &map);
 
-err_addr:
-	pci_epc_mem_free_addr(epc, phys_addr, src_addr, reg->size);
+free_buf:
+	kfree(src_buf);
 
-err:
+set_status:
 	if (!ret)
 		reg->status |= STATUS_READ_SUCCESS;
 	else
@@ -496,71 +504,79 @@ static void pci_epf_test_read(struct pci_epf_test *epf_test,
 static void pci_epf_test_write(struct pci_epf_test *epf_test,
 			       struct pci_epf_test_reg *reg)
 {
-	int ret;
-	void __iomem *dst_addr;
-	void *buf;
-	phys_addr_t phys_addr;
+	int ret = 0;
+	void *dst_buf, *buf;
+	struct pci_epc_map map;
 	phys_addr_t src_phys_addr;
 	struct timespec64 start, end;
 	struct pci_epf *epf = epf_test->epf;
-	struct device *dev = &epf->dev;
 	struct pci_epc *epc = epf->epc;
+	struct device *dev = &epf->dev;
 	struct device *dma_dev = epf->epc->dev.parent;
+	u64 dst_addr = reg->dst_addr;
+	size_t dst_size = reg->size;
+	ssize_t map_size = 0;
 
-	dst_addr = pci_epc_mem_alloc_addr(epc, &phys_addr, reg->size);
-	if (!dst_addr) {
-		dev_err(dev, "Failed to allocate address\n");
-		reg->status = STATUS_DST_ADDR_INVALID;
+	dst_buf = kzalloc(dst_size, GFP_KERNEL);
+	if (!dst_buf) {
 		ret = -ENOMEM;
-		goto err;
+		goto set_status;
 	}
+	get_random_bytes(dst_buf, dst_size);
+	reg->checksum = crc32_le(~0, dst_buf, dst_size);
+	buf = dst_buf;
 
-	ret = pci_epc_map_addr(epc, epf->func_no, epf->vfunc_no, phys_addr,
-			       reg->dst_addr, reg->size);
-	if (ret) {
-		dev_err(dev, "Failed to map address\n");
-		reg->status = STATUS_DST_ADDR_INVALID;
-		goto err_addr;
-	}
-
-	buf = kzalloc(reg->size, GFP_KERNEL);
-	if (!buf) {
-		ret = -ENOMEM;
-		goto err_map_addr;
-	}
-
-	get_random_bytes(buf, reg->size);
-	reg->checksum = crc32_le(~0, buf, reg->size);
-
-	if (reg->flags & FLAG_USE_DMA) {
-		src_phys_addr = dma_map_single(dma_dev, buf, reg->size,
-					       DMA_TO_DEVICE);
-		if (dma_mapping_error(dma_dev, src_phys_addr)) {
-			dev_err(dev, "Failed to map source buffer addr\n");
-			ret = -ENOMEM;
-			goto err_dma_map;
+	while (dst_size) {
+		ret = pci_epc_mem_map(epc, epf->func_no, epf->vfunc_no,
+					   dst_addr, dst_size, &map);
+		if (ret) {
+			dev_err(dev, "Failed to map address\n");
+			reg->status = STATUS_DST_ADDR_INVALID;
+			goto free_buf;
 		}
 
-		ktime_get_ts64(&start);
+		map_size = map.pci_size;
+		if (reg->flags & FLAG_USE_DMA) {
+			src_phys_addr = dma_map_single(dma_dev, buf, map_size,
+						       DMA_TO_DEVICE);
+			if (dma_mapping_error(dma_dev, src_phys_addr)) {
+				dev_err(dev,
+					"Failed to map source buffer addr\n");
+				ret = -ENOMEM;
+				goto unmap;
+			}
+
+			ktime_get_ts64(&start);
+
+			ret = pci_epf_test_data_transfer(epf_test,
+						map.phys_addr, src_phys_addr,
+						map_size, dst_addr,
+						DMA_MEM_TO_DEV);
+			if (ret)
+				dev_err(dev, "Data transfer failed\n");
+			ktime_get_ts64(&end);
+
+			dma_unmap_single(dma_dev, src_phys_addr, map_size,
+					 DMA_TO_DEVICE);
+
+			if (ret)
+				goto unmap;
+		} else {
+			ktime_get_ts64(&start);
+			memcpy_toio(map.virt_addr, buf, map_size);
+			ktime_get_ts64(&end);
+		}
 
-		ret = pci_epf_test_data_transfer(epf_test, phys_addr,
-						 src_phys_addr, reg->size,
-						 reg->dst_addr,
-						 DMA_MEM_TO_DEV);
-		if (ret)
-			dev_err(dev, "Data transfer failed\n");
-		ktime_get_ts64(&end);
+		dst_size -= map_size;
+		dst_addr += map_size;
+		buf += map_size;
 
-		dma_unmap_single(dma_dev, src_phys_addr, reg->size,
-				 DMA_TO_DEVICE);
-	} else {
-		ktime_get_ts64(&start);
-		memcpy_toio(dst_addr, buf, reg->size);
-		ktime_get_ts64(&end);
+		pci_epc_mem_unmap(epc, epf->func_no, epf->vfunc_no, &map);
+		map_size = 0;
 	}
 
-	pci_epf_test_print_rate(epf_test, "WRITE", reg->size, &start, &end,
-				reg->flags & FLAG_USE_DMA);
+	pci_epf_test_print_rate(epf_test, "WRITE", reg->size, &start,
+				&end, reg->flags & FLAG_USE_DMA);
 
 	/*
 	 * wait 1ms inorder for the write to complete. Without this delay L3
@@ -568,16 +584,14 @@ static void pci_epf_test_write(struct pci_epf_test *epf_test,
 	 */
 	usleep_range(1000, 2000);
 
-err_dma_map:
-	kfree(buf);
-
-err_map_addr:
-	pci_epc_unmap_addr(epc, epf->func_no, epf->vfunc_no, phys_addr);
+unmap:
+	if (map_size)
+		pci_epc_mem_unmap(epc, epf->func_no, epf->vfunc_no, &map);
 
-err_addr:
-	pci_epc_mem_free_addr(epc, phys_addr, dst_addr, reg->size);
+free_buf:
+	kfree(dst_buf);
 
-err:
+set_status:
 	if (!ret)
 		reg->status |= STATUS_WRITE_SUCCESS;
 	else

From 22c918258f90600665b44a9bc29d09d6f7837a6a Mon Sep 17 00:00:00 2001
From: Thomas Bonnefille <thomas.bonnefille@bootlin.com>
Date: Wed, 16 Oct 2024 12:11:42 +0200
Subject: [PATCH 0406/1530] pinctrl: sophgo: fix typo in tristate of SG2002

Fix typo in tristate definition of the SG2002 Pinctrl driver.

Signed-off-by: Thomas Bonnefille <thomas.bonnefille@bootlin.com>
Link: https://lore.kernel.org/20241016-typo-pinctrl-sg2002-v1-1-2bdacb2d41e3@bootlin.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/sophgo/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/sophgo/Kconfig b/drivers/pinctrl/sophgo/Kconfig
index b14792ee46fc3..c05f909a88389 100644
--- a/drivers/pinctrl/sophgo/Kconfig
+++ b/drivers/pinctrl/sophgo/Kconfig
@@ -43,7 +43,7 @@ config PINCTRL_SOPHGO_SG2000
 	  pinctrl-sg2000.
 
 config PINCTRL_SOPHGO_SG2002
-	tristate "Sophgo SG2000 SoC Pinctrl driver"
+	tristate "Sophgo SG2002 SoC Pinctrl driver"
 	depends on ARCH_SOPHGO || COMPILE_TEST
 	depends on OF
 	select PINCTRL_SOPHGO_CV18XX

From 05214b06ee832854bfae883de0522e3c48d4444b Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Wed, 16 Oct 2024 16:56:55 +0100
Subject: [PATCH 0407/1530] pinctrl: th1520: Fix potential null pointer
 dereference on func

The initialization of muxtype deferences pointer func before func
is sanity checked with a null pointer check, hence we have a null
pointer deference issue. Fix this by only deferencing func with
the assignment to muxtype after func has been null pointer checked.

Fixes: 1fc30cd92770 ("pinctrl: th1520: Factor out casts")
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reported-by: Kees Bakker <kees@ijzerbout.nl>
Acked-by: Drew Fustini <dfustini@tenstorrent.com>
Link: https://lore.kernel.org/20241016155655.334518-1-colin.i.king@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-th1520.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-th1520.c b/drivers/pinctrl/pinctrl-th1520.c
index 7474d8da32f90..e641bad6728cc 100644
--- a/drivers/pinctrl/pinctrl-th1520.c
+++ b/drivers/pinctrl/pinctrl-th1520.c
@@ -803,11 +803,12 @@ static int th1520_pinmux_set_mux(struct pinctrl_dev *pctldev,
 {
 	struct th1520_pinctrl *thp = pinctrl_dev_get_drvdata(pctldev);
 	const struct function_desc *func = pinmux_generic_get_function(pctldev, fsel);
-	enum th1520_muxtype muxtype = (uintptr_t)func->data;
+	enum th1520_muxtype muxtype;
 
 	if (!func)
 		return -EINVAL;
 
+	muxtype = (uintptr_t)func->data;
 	return th1520_pinmux_set(thp, thp->desc.pins[gsel].number,
 				 th1520_pad_muxdata(thp->desc.pins[gsel].drv_data),
 				 muxtype);

From 421aadd19a622852172ccc15ad4049201fd1f80b Mon Sep 17 00:00:00 2001
From: Andreas Kemnade <andreas@kemnade.info>
Date: Wed, 16 Oct 2024 10:03:12 +0200
Subject: [PATCH 0408/1530] dt-bindings: power: supply: Add TI TWL603X charger

Use a fallback compatible since for especially for generic
defensive setup of parameters, both 6030 and 6032 are the same and
U-Boot actually uses a generic 6030/32 function to enable the
charger.

Signed-off-by: Andreas Kemnade <andreas@kemnade.info>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20241016080314.222674-2-andreas@kemnade.info
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 .../power/supply/ti,twl6030-charger.yaml      | 48 +++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/power/supply/ti,twl6030-charger.yaml

diff --git a/Documentation/devicetree/bindings/power/supply/ti,twl6030-charger.yaml b/Documentation/devicetree/bindings/power/supply/ti,twl6030-charger.yaml
new file mode 100644
index 0000000000000..fc604d8a469df
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/supply/ti,twl6030-charger.yaml
@@ -0,0 +1,48 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/power/supply/ti,twl6030-charger.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: TWL6030/32 BCI (Battery Charger Interface)
+
+description:
+  The battery charger needs to be configured to do any charging besides of
+  precharging. The GPADC in the PMIC has to be used to get the related
+  voltages.
+
+maintainers:
+  - Andreas Kemnade <andreas@kemnade.info>
+
+allOf:
+  - $ref: power-supply.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - const: ti,twl6030-charger
+      - items:
+          - const: ti,twl6032-charger
+          - const: ti,twl6030-charger
+
+  interrupts:
+    items:
+      - description: Charger Control Interrupt
+      - description: Charger Fault Interrupt
+
+  io-channels:
+    items:
+      - description: VBUS Voltage Channel
+
+  io-channel-names:
+    items:
+      - const: vusb
+
+  monitored-battery: true
+
+required:
+  - compatible
+  - interrupts
+  - monitored-battery
+
+additionalProperties: false

From b45cdceba64d79a2538aeb36926fd9a065f0f753 Mon Sep 17 00:00:00 2001
From: Andreas Kemnade <andreas@kemnade.info>
Date: Wed, 16 Oct 2024 10:03:13 +0200
Subject: [PATCH 0409/1530] power: supply: initial support for TWL6030/32

Add a driver for the charger in the TWL6030/32. For now it does not report
much in sysfs but parameters are set up for USB, charging is enabled with
the specified parameters. It stops charging when full and also restarts
charging.
This prevents ending up in a system setup where you run out of battery
although a charger is plugged in after precharge completed.

Battery voltage behavior was checked via the GPADC.

Signed-off-by: Andreas Kemnade <andreas@kemnade.info>
Link: https://lore.kernel.org/r/20241016080314.222674-3-andreas@kemnade.info
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/Kconfig           |  10 +
 drivers/power/supply/Makefile          |   1 +
 drivers/power/supply/twl6030_charger.c | 581 +++++++++++++++++++++++++
 3 files changed, 592 insertions(+)
 create mode 100644 drivers/power/supply/twl6030_charger.c

diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig
index bcfa63fb9f1e2..9f2eef6787f7a 100644
--- a/drivers/power/supply/Kconfig
+++ b/drivers/power/supply/Kconfig
@@ -493,6 +493,16 @@ config CHARGER_TWL4030
 	help
 	  Say Y here to enable support for TWL4030 Battery Charge Interface.
 
+config CHARGER_TWL6030
+	tristate "OMAP TWL6030 BCI charger driver"
+	depends on IIO && TWL4030_CORE
+	help
+	  Say Y here to enable support for TWL6030/6032 Battery Charge
+	  Interface.
+
+	  This driver can be build as a module. If so, the module will be
+	  called twl6030_charger.
+
 config CHARGER_LP8727
 	tristate "TI/National Semiconductor LP8727 charger driver"
 	depends on I2C
diff --git a/drivers/power/supply/Makefile b/drivers/power/supply/Makefile
index 8dcb415453171..59c4a9f40d28a 100644
--- a/drivers/power/supply/Makefile
+++ b/drivers/power/supply/Makefile
@@ -69,6 +69,7 @@ obj-$(CONFIG_CHARGER_CPCAP)	+= cpcap-charger.o
 obj-$(CONFIG_CHARGER_ISP1704)	+= isp1704_charger.o
 obj-$(CONFIG_CHARGER_MAX8903)	+= max8903_charger.o
 obj-$(CONFIG_CHARGER_TWL4030)	+= twl4030_charger.o
+obj-$(CONFIG_CHARGER_TWL6030)	+= twl6030_charger.o
 obj-$(CONFIG_CHARGER_LP8727)	+= lp8727_charger.o
 obj-$(CONFIG_CHARGER_LP8788)	+= lp8788-charger.o
 obj-$(CONFIG_CHARGER_GPIO)	+= gpio-charger.o
diff --git a/drivers/power/supply/twl6030_charger.c b/drivers/power/supply/twl6030_charger.c
new file mode 100644
index 0000000000000..b4ec26ff257cc
--- /dev/null
+++ b/drivers/power/supply/twl6030_charger.c
@@ -0,0 +1,581 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * TWL6030 charger
+ *
+ * Copyright (C) 2024 Andreas Kemnade <andreas@kemnade.info>
+ *
+ * based on older 6030 driver found in a v3.0 vendor kernel
+ *
+ * based on twl4030_bci_battery.c by TI
+ * Copyright (C) 2008 Texas Instruments, Inc.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/bits.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/twl.h>
+#include <linux/power_supply.h>
+#include <linux/notifier.h>
+#include <linux/usb/otg.h>
+#include <linux/iio/consumer.h>
+#include <linux/devm-helpers.h>
+
+#define CONTROLLER_INT_MASK	0x00
+#define CONTROLLER_CTRL1	0x01
+#define CONTROLLER_WDG		0x02
+#define CONTROLLER_STAT1	0x03
+#define CHARGERUSB_INT_STATUS	0x04
+#define CHARGERUSB_INT_MASK	0x05
+#define CHARGERUSB_STATUS_INT1	0x06
+#define CHARGERUSB_STATUS_INT2	0x07
+#define CHARGERUSB_CTRL1	0x08
+#define CHARGERUSB_CTRL2	0x09
+#define CHARGERUSB_CTRL3	0x0A
+#define CHARGERUSB_STAT1	0x0B
+#define CHARGERUSB_VOREG	0x0C
+#define CHARGERUSB_VICHRG	0x0D
+#define CHARGERUSB_CINLIMIT	0x0E
+#define CHARGERUSB_CTRLLIMIT1	0x0F
+#define CHARGERUSB_CTRLLIMIT2	0x10
+#define ANTICOLLAPSE_CTRL1	0x11
+#define ANTICOLLAPSE_CTRL2	0x12
+
+/* TWL6032 registers 0xDA to 0xDE - TWL6032_MODULE_CHARGER */
+#define CONTROLLER_CTRL2	0x00
+#define CONTROLLER_VSEL_COMP	0x01
+#define CHARGERUSB_VSYSREG	0x02
+#define CHARGERUSB_VICHRG_PC	0x03
+#define LINEAR_CHRG_STS		0x04
+
+#define LINEAR_CHRG_STS_CRYSTL_OSC_OK	0x40
+#define LINEAR_CHRG_STS_END_OF_CHARGE	0x20
+#define LINEAR_CHRG_STS_VBATOV		0x10
+#define LINEAR_CHRG_STS_VSYSOV		0x08
+#define LINEAR_CHRG_STS_DPPM_STS	0x04
+#define LINEAR_CHRG_STS_CV_STS		0x02
+#define LINEAR_CHRG_STS_CC_STS		0x01
+
+#define FG_REG_00	0x00
+#define FG_REG_01	0x01
+#define FG_REG_02	0x02
+#define FG_REG_03	0x03
+#define FG_REG_04	0x04
+#define FG_REG_05	0x05
+#define FG_REG_06	0x06
+#define FG_REG_07	0x07
+#define FG_REG_08	0x08
+#define FG_REG_09	0x09
+#define FG_REG_10	0x0A
+#define FG_REG_11	0x0B
+
+/* CONTROLLER_INT_MASK */
+#define MVAC_FAULT		BIT(7)
+#define MAC_EOC			BIT(6)
+#define LINCH_GATED		BIT(5)
+#define MBAT_REMOVED		BIT(4)
+#define MFAULT_WDG		BIT(3)
+#define MBAT_TEMP		BIT(2)
+#define MVBUS_DET		BIT(1)
+#define MVAC_DET		BIT(0)
+
+/* CONTROLLER_CTRL1 */
+#define CONTROLLER_CTRL1_EN_LINCH	BIT(5)
+#define CONTROLLER_CTRL1_EN_CHARGER	BIT(4)
+#define CONTROLLER_CTRL1_SEL_CHARGER	BIT(3)
+
+/* CONTROLLER_STAT1 */
+#define CONTROLLER_STAT1_EXTCHRG_STATZ	BIT(7)
+#define CONTROLLER_STAT1_LINCH_GATED	BIT(6)
+#define CONTROLLER_STAT1_CHRG_DET_N	BIT(5)
+#define CONTROLLER_STAT1_FAULT_WDG	BIT(4)
+#define CONTROLLER_STAT1_VAC_DET	BIT(3)
+#define VAC_DET	BIT(3)
+#define CONTROLLER_STAT1_VBUS_DET	BIT(2)
+#define VBUS_DET	BIT(2)
+#define CONTROLLER_STAT1_BAT_REMOVED	BIT(1)
+#define CONTROLLER_STAT1_BAT_TEMP_OVRANGE BIT(0)
+
+/* CHARGERUSB_INT_STATUS */
+#define EN_LINCH		BIT(4)
+#define CURRENT_TERM_INT	BIT(3)
+#define CHARGERUSB_STAT		BIT(2)
+#define CHARGERUSB_THMREG	BIT(1)
+#define CHARGERUSB_FAULT	BIT(0)
+
+/* CHARGERUSB_INT_MASK */
+#define MASK_MCURRENT_TERM		BIT(3)
+#define MASK_MCHARGERUSB_STAT		BIT(2)
+#define MASK_MCHARGERUSB_THMREG		BIT(1)
+#define MASK_MCHARGERUSB_FAULT		BIT(0)
+
+/* CHARGERUSB_STATUS_INT1 */
+#define CHARGERUSB_STATUS_INT1_TMREG	BIT(7)
+#define CHARGERUSB_STATUS_INT1_NO_BAT	BIT(6)
+#define CHARGERUSB_STATUS_INT1_BST_OCP	BIT(5)
+#define CHARGERUSB_STATUS_INT1_TH_SHUTD	BIT(4)
+#define CHARGERUSB_STATUS_INT1_BAT_OVP	BIT(3)
+#define CHARGERUSB_STATUS_INT1_POOR_SRC	BIT(2)
+#define CHARGERUSB_STATUS_INT1_SLP_MODE	BIT(1)
+#define CHARGERUSB_STATUS_INT1_VBUS_OVP	BIT(0)
+
+/* CHARGERUSB_STATUS_INT2 */
+#define ICCLOOP		BIT(3)
+#define CURRENT_TERM	BIT(2)
+#define CHARGE_DONE	BIT(1)
+#define ANTICOLLAPSE	BIT(0)
+
+/* CHARGERUSB_CTRL1 */
+#define SUSPEND_BOOT	BIT(7)
+#define OPA_MODE	BIT(6)
+#define HZ_MODE		BIT(5)
+#define TERM		BIT(4)
+
+/* CHARGERUSB_CTRL2 */
+#define UA_TO_VITERM(x) (((x) / 50000 - 1) << 5)
+
+/* CHARGERUSB_CTRL3 */
+#define VBUSCHRG_LDO_OVRD	BIT(7)
+#define CHARGE_ONCE		BIT(6)
+#define BST_HW_PR_DIS		BIT(5)
+#define AUTOSUPPLY		BIT(3)
+#define BUCK_HSILIM		BIT(0)
+
+/* CHARGERUSB_VOREG */
+#define UV_TO_VOREG(x) (((x) - 3500000) / 20000)
+#define VOREG_TO_UV(x) (((x) & 0x3F) * 20000 + 3500000)
+#define CHARGERUSB_VOREG_3P52		0x01
+#define CHARGERUSB_VOREG_4P0		0x19
+#define CHARGERUSB_VOREG_4P2		0x23
+#define CHARGERUSB_VOREG_4P76		0x3F
+
+/* CHARGERUSB_VICHRG */
+/*
+ * might be inaccurate for < 500 mA, diffent scale might apply,
+ * either starting from 100 mA or 300 mA
+ */
+#define UA_TO_VICHRG(x) (((x) / 100000) - 1)
+#define VICHRG_TO_UA(x) (((x) & 0xf) * 100000 + 100000)
+
+/* CHARGERUSB_CINLIMIT */
+#define CHARGERUSB_CIN_LIMIT_100	0x1
+#define CHARGERUSB_CIN_LIMIT_300	0x5
+#define CHARGERUSB_CIN_LIMIT_500	0x9
+#define CHARGERUSB_CIN_LIMIT_NONE	0xF
+
+/* CHARGERUSB_CTRLLIMIT2 */
+#define CHARGERUSB_CTRLLIMIT2_1500	0x0E
+#define		LOCK_LIMIT		BIT(4)
+
+/* ANTICOLLAPSE_CTRL2 */
+#define BUCK_VTH_SHIFT			5
+
+/* FG_REG_00 */
+#define CC_ACTIVE_MODE_SHIFT	6
+#define CC_AUTOCLEAR		BIT(2)
+#define CC_CAL_EN		BIT(1)
+#define CC_PAUSE		BIT(0)
+
+#define REG_TOGGLE1		0x90
+#define REG_PWDNSTATUS1		0x93
+#define FGDITHS			BIT(7)
+#define FGDITHR			BIT(6)
+#define FGS			BIT(5)
+#define FGR			BIT(4)
+#define BBSPOR_CFG		0xE6
+#define	BB_CHG_EN		BIT(3)
+
+struct twl6030_charger_info {
+	struct device		*dev;
+	struct power_supply	*usb;
+	struct power_supply_battery_info *binfo;
+	struct work_struct	work;
+	int			irq_chg;
+	int			input_current_limit;
+	struct iio_channel	*channel_vusb;
+	struct delayed_work	charger_monitor;
+	bool			extended_current_range;
+};
+
+struct twl6030_charger_chip_data {
+	bool extended_current_range;
+};
+
+static int twl6030_charger_read(u8 reg, u8 *val)
+{
+	return twl_i2c_read_u8(TWL_MODULE_MAIN_CHARGE, val, reg);
+}
+
+static int twl6030_charger_write(u8 reg, u8 val)
+{
+	return twl_i2c_write_u8(TWL_MODULE_MAIN_CHARGE, val, reg);
+}
+
+static int twl6030_config_cinlimit_reg(struct twl6030_charger_info *charger,
+				       unsigned int ua)
+{
+	if (ua >= 50000 && ua <= 750000) {
+		ua = (ua - 50000) / 50000;
+	} else if ((ua > 750000) && (ua <= 1500000) && charger->extended_current_range) {
+		ua = ((ua % 100000) ? 0x30 : 0x20) + ((ua - 100000) / 100000);
+	} else {
+		if (ua < 50000) {
+			dev_err(charger->dev, "invalid input current limit\n");
+			return -EINVAL;
+		}
+		/* This is no current limit */
+		ua = 0x0F;
+	}
+
+	return twl6030_charger_write(CHARGERUSB_CINLIMIT, ua);
+}
+
+/*
+ * rewriting all stuff here, resets to extremely conservative defaults were
+ * seen under some circumstances, like charge voltage to 3.5V
+ */
+static int twl6030_enable_usb(struct twl6030_charger_info *charger)
+{
+	int ret;
+
+	ret = twl6030_charger_write(CHARGERUSB_VICHRG,
+				    UA_TO_VICHRG(charger->binfo->constant_charge_current_max_ua));
+	if (ret < 0)
+		return ret;
+
+	ret = twl6030_charger_write(CONTROLLER_WDG, 0xff);
+	if (ret < 0)
+		return ret;
+
+	charger->input_current_limit = 500000;
+	ret = twl6030_config_cinlimit_reg(charger, charger->input_current_limit);
+	if (ret < 0)
+		return ret;
+
+	ret = twl6030_charger_write(CHARGERUSB_CINLIMIT, CHARGERUSB_CIN_LIMIT_500);
+	if (ret < 0)
+		return ret;
+
+	ret = twl6030_charger_write(CHARGERUSB_VOREG,
+				    UV_TO_VOREG(charger->binfo->constant_charge_voltage_max_uv));
+	if (ret < 0)
+		return ret;
+
+	ret = twl6030_charger_write(CHARGERUSB_CTRL1, TERM);
+	if (ret < 0)
+		return ret;
+
+	if (charger->binfo->charge_term_current_ua != -EINVAL) {
+		ret = twl6030_charger_write(CHARGERUSB_CTRL2,
+					    UA_TO_VITERM(charger->binfo->charge_term_current_ua));
+		if (ret < 0)
+			return ret;
+	}
+
+	return twl6030_charger_write(CONTROLLER_CTRL1, CONTROLLER_CTRL1_EN_CHARGER);
+}
+
+static void twl6030_charger_wdg(struct work_struct *data)
+{
+	struct twl6030_charger_info *charger =
+		container_of(data, struct twl6030_charger_info,
+			     charger_monitor.work);
+
+	u8 val;
+	u8 int_stat;
+	u8 stat_int1;
+	u8 stat_int2;
+
+	twl6030_charger_read(CONTROLLER_STAT1, &val);
+	twl6030_charger_read(CHARGERUSB_INT_STATUS, &int_stat);
+	twl6030_charger_read(CHARGERUSB_STATUS_INT1, &stat_int1);
+	twl6030_charger_read(CHARGERUSB_STATUS_INT2, &stat_int2);
+	dev_dbg(charger->dev,
+		"wdg: stat1: %02x %s INT_STATUS %02x STATUS_INT1 %02x STATUS_INT2 %02x\n",
+		val, (val & VBUS_DET) ? "usb online" :  "usb offline",
+		int_stat, stat_int1, stat_int2);
+
+	twl6030_charger_write(CONTROLLER_WDG, 0xff);
+	schedule_delayed_work(&charger->charger_monitor,
+			      msecs_to_jiffies(10000));
+}
+
+static irqreturn_t twl6030_charger_interrupt(int irq, void *arg)
+{
+	struct twl6030_charger_info *charger = arg;
+	u8 val;
+	u8 int_stat;
+	u8 stat_int1;
+	u8 stat_int2;
+
+	if (twl6030_charger_read(CONTROLLER_STAT1, &val) < 0)
+		return IRQ_HANDLED;
+
+	if (twl6030_charger_read(CHARGERUSB_INT_STATUS, &int_stat) < 0)
+		return IRQ_HANDLED;
+
+	if (twl6030_charger_read(CHARGERUSB_STATUS_INT1, &stat_int1) < 0)
+		return IRQ_HANDLED;
+
+	if (twl6030_charger_read(CHARGERUSB_STATUS_INT2, &stat_int2) < 0)
+		return IRQ_HANDLED;
+
+	dev_dbg(charger->dev,
+		"charger irq: stat1: %02x %s INT_STATUS %02x STATUS_INT1 %02x STATUS_INT2 %02x\n",
+		val, (val & VBUS_DET) ? "usb online" :  "usb offline",
+		int_stat, stat_int1, stat_int2);
+	power_supply_changed(charger->usb);
+
+	if (val & VBUS_DET) {
+		if (twl6030_charger_read(CONTROLLER_CTRL1, &val) < 0)
+			return IRQ_HANDLED;
+
+		if (!(val & CONTROLLER_CTRL1_EN_CHARGER)) {
+			if (twl6030_enable_usb(charger) < 0)
+				return IRQ_HANDLED;
+
+			schedule_delayed_work(&charger->charger_monitor,
+					      msecs_to_jiffies(10000));
+		}
+	} else {
+		cancel_delayed_work(&charger->charger_monitor);
+	}
+	return IRQ_HANDLED;
+}
+
+static int twl6030_charger_usb_get_property(struct power_supply *psy,
+					    enum power_supply_property psp,
+					    union power_supply_propval *val)
+{
+	struct twl6030_charger_info *charger = power_supply_get_drvdata(psy);
+	int ret;
+	u8 stat1;
+	u8 intstat;
+
+	ret = twl6030_charger_read(CONTROLLER_STAT1, &stat1);
+	if (ret)
+		return ret;
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_STATUS:
+		if (!(stat1 & VBUS_DET)) {
+			val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING;
+			break;
+		}
+		ret = twl6030_charger_read(CHARGERUSB_STATUS_INT2, &intstat);
+		if (ret)
+			return ret;
+
+		if (intstat & CHARGE_DONE)
+			val->intval = POWER_SUPPLY_STATUS_FULL;
+		else if (intstat & CURRENT_TERM)
+			val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING;
+		else
+			val->intval = POWER_SUPPLY_STATUS_CHARGING;
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		if (!charger->channel_vusb)
+			return -ENODATA;
+
+		ret = iio_read_channel_processed_scale(charger->channel_vusb, &val->intval, 1000);
+		if (ret < 0)
+			return ret;
+
+		break;
+	case POWER_SUPPLY_PROP_ONLINE:
+		val->intval = !!(stat1 & VBUS_DET);
+		break;
+	case POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT:
+		val->intval = charger->input_current_limit;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int twl6030_charger_usb_set_property(struct power_supply *psy,
+					    enum power_supply_property psp,
+					    const union power_supply_propval *val)
+{
+	struct twl6030_charger_info *charger = power_supply_get_drvdata(psy);
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT:
+		charger->input_current_limit = val->intval;
+		return twl6030_config_cinlimit_reg(charger, charger->input_current_limit);
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int twl6030_charger_usb_property_is_writeable(struct power_supply *psy,
+						     enum power_supply_property psp)
+{
+	dev_info(&psy->dev, "is %d writeable?\n", (int)psp);
+	switch (psp) {
+	case POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static enum power_supply_property twl6030_charger_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT,
+};
+
+static const struct power_supply_desc twl6030_charger_usb_desc = {
+	.name		= "twl6030_usb",
+	.type		= POWER_SUPPLY_TYPE_USB,
+	.properties	= twl6030_charger_props,
+	.num_properties	= ARRAY_SIZE(twl6030_charger_props),
+	.get_property	= twl6030_charger_usb_get_property,
+	.set_property	= twl6030_charger_usb_set_property,
+	.property_is_writeable	= twl6030_charger_usb_property_is_writeable,
+};
+
+static int twl6030_charger_probe(struct platform_device *pdev)
+{
+	struct twl6030_charger_info *charger;
+	const struct twl6030_charger_chip_data *chip_data;
+	struct power_supply_config psy_cfg = {};
+	int ret;
+	u8 val;
+
+	charger = devm_kzalloc(&pdev->dev, sizeof(*charger), GFP_KERNEL);
+	if (!charger)
+		return -ENOMEM;
+
+	charger->dev = &pdev->dev;
+	charger->irq_chg = platform_get_irq(pdev, 0);
+
+	chip_data = device_get_match_data(&pdev->dev);
+	if (!chip_data)
+		return dev_err_probe(&pdev->dev, -EINVAL, "missing chip data\n");
+
+	charger->extended_current_range = chip_data->extended_current_range;
+	platform_set_drvdata(pdev, charger);
+	psy_cfg.drv_data = charger;
+	psy_cfg.fwnode = dev_fwnode(&pdev->dev);
+
+	charger->channel_vusb = devm_iio_channel_get(&pdev->dev, "vusb");
+	if (IS_ERR(charger->channel_vusb)) {
+		ret = PTR_ERR(charger->channel_vusb);
+		if (ret == -EPROBE_DEFER)
+			return ret;	/* iio not ready */
+		dev_warn(&pdev->dev, "could not request vusb iio channel (%d)",
+			 ret);
+		charger->channel_vusb = NULL;
+	}
+
+	charger->usb = devm_power_supply_register(&pdev->dev,
+						  &twl6030_charger_usb_desc,
+						  &psy_cfg);
+	if (IS_ERR(charger->usb))
+		return dev_err_probe(&pdev->dev, PTR_ERR(charger->usb),
+				     "Failed to register usb\n");
+
+	ret = power_supply_get_battery_info(charger->usb, &charger->binfo);
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "Failed to get battery info\n");
+
+	dev_info(&pdev->dev, "battery with vmax %d imax: %d\n",
+		 charger->binfo->constant_charge_voltage_max_uv,
+		 charger->binfo->constant_charge_current_max_ua);
+
+	if (charger->binfo->constant_charge_voltage_max_uv == -EINVAL) {
+		ret = twl6030_charger_read(CHARGERUSB_CTRLLIMIT1, &val);
+		if (ret < 0)
+			return ret;
+
+		charger->binfo->constant_charge_voltage_max_uv =
+			VOREG_TO_UV(val);
+	}
+
+	if (charger->binfo->constant_charge_voltage_max_uv > 4760000 ||
+	    charger->binfo->constant_charge_voltage_max_uv < 350000)
+		return dev_err_probe(&pdev->dev, -EINVAL,
+				     "Invalid charge voltage\n");
+
+	if (charger->binfo->constant_charge_current_max_ua == -EINVAL) {
+		ret = twl6030_charger_read(CHARGERUSB_CTRLLIMIT2, &val);
+		if (ret < 0)
+			return ret;
+
+		charger->binfo->constant_charge_current_max_ua = VICHRG_TO_UA(val);
+	}
+
+	if (charger->binfo->constant_charge_current_max_ua < 100000 ||
+	    charger->binfo->constant_charge_current_max_ua > 1500000) {
+		return dev_err_probe(&pdev->dev, -EINVAL,
+			 "Invalid charge current\n");
+	}
+
+	if ((charger->binfo->charge_term_current_ua != -EINVAL) &&
+	    (charger->binfo->charge_term_current_ua > 400000 ||
+	     charger->binfo->charge_term_current_ua < 50000)) {
+		return dev_err_probe(&pdev->dev, -EINVAL,
+			"Invalid charge termination current\n");
+	}
+
+	ret = devm_delayed_work_autocancel(&pdev->dev,
+					   &charger->charger_monitor,
+					   twl6030_charger_wdg);
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "Failed to register delayed work\n");
+
+	ret = devm_request_threaded_irq(&pdev->dev, charger->irq_chg, NULL,
+					twl6030_charger_interrupt,
+					IRQF_ONESHOT, pdev->name,
+					charger);
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "could not request irq %d\n",
+				     charger->irq_chg);
+
+	/* turing to charging to configure things */
+	twl6030_charger_write(CONTROLLER_CTRL1, 0);
+	twl6030_charger_interrupt(0, charger);
+
+	return 0;
+}
+
+static const struct twl6030_charger_chip_data twl6030_data = {
+	.extended_current_range = false,
+};
+
+static const struct twl6030_charger_chip_data twl6032_data = {
+	.extended_current_range = true,
+};
+
+static const struct of_device_id twl_charger_of_match[] = {
+	{.compatible = "ti,twl6030-charger", .data = &twl6030_data},
+	{.compatible = "ti,twl6032-charger", .data = &twl6032_data},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, twl_charger_of_match);
+
+static struct platform_driver twl6030_charger_driver = {
+	.probe = twl6030_charger_probe,
+	.driver	= {
+		.name	= "twl6030_charger",
+		.of_match_table = twl_charger_of_match,
+	},
+};
+module_platform_driver(twl6030_charger_driver);
+
+MODULE_DESCRIPTION("TWL6030 Battery Charger Interface driver");
+MODULE_LICENSE("GPL");

From e7af7d13316dc5e2293c4f777f71bd8331f5d7a5 Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Wed, 16 Oct 2024 11:59:43 +1300
Subject: [PATCH 0410/1530] dt-bindings: reset: syscon-reboot: Add reg property

The syscon-reboot binding used 'offset' for historical reasons. Having a
reg property is appropriate when these nodes are children of a MMIO bus.
Add a reg property and modify the constraints so that one of 'reg' or
'offset' is expected.

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20241015225948.3971924-2-chris.packham@alliedtelesis.co.nz
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 .../bindings/power/reset/syscon-reboot.yaml           | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/power/reset/syscon-reboot.yaml b/Documentation/devicetree/bindings/power/reset/syscon-reboot.yaml
index 75061124d9a8b..19d3093e6cd2f 100644
--- a/Documentation/devicetree/bindings/power/reset/syscon-reboot.yaml
+++ b/Documentation/devicetree/bindings/power/reset/syscon-reboot.yaml
@@ -31,6 +31,10 @@ properties:
     $ref: /schemas/types.yaml#/definitions/uint32
     description: Offset in the register map for the reboot register (in bytes).
 
+  reg:
+    maxItems: 1
+    description: Base address and size for the reboot register.
+
   regmap:
     $ref: /schemas/types.yaml#/definitions/phandle
     deprecated: true
@@ -45,9 +49,14 @@ properties:
   priority:
     default: 192
 
+oneOf:
+  - required:
+      - offset
+  - required:
+      - reg
+
 required:
   - compatible
-  - offset
 
 additionalProperties: false
 

From ce38cdc908557953604ffb0a91ef5ae3fbdf1c6b Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Wed, 16 Oct 2024 11:59:44 +1300
Subject: [PATCH 0411/1530] power: reset: syscon-reboot: Accept reg property

For historical reasons syscon-reboot has used an 'offset' property. As a
child on a MMIO bus having a 'reg' property is more appropriate. Accept
'reg' as an alternative to 'offset'.

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20241015225948.3971924-3-chris.packham@alliedtelesis.co.nz
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/syscon-reboot.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/power/reset/syscon-reboot.c b/drivers/power/reset/syscon-reboot.c
index 4d622c19bc486..d623d77e657e4 100644
--- a/drivers/power/reset/syscon-reboot.c
+++ b/drivers/power/reset/syscon-reboot.c
@@ -61,7 +61,8 @@ static int syscon_reboot_probe(struct platform_device *pdev)
 		priority = 192;
 
 	if (of_property_read_u32(pdev->dev.of_node, "offset", &ctx->offset))
-		return -EINVAL;
+		if (of_property_read_u32(pdev->dev.of_node, "reg", &ctx->offset))
+			return -EINVAL;
 
 	value_err = of_property_read_u32(pdev->dev.of_node, "value", &ctx->value);
 	mask_err = of_property_read_u32(pdev->dev.of_node, "mask", &ctx->mask);

From 42fd7cac57d6001974a0546e5eb50a430aa95b11 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 16 Oct 2024 09:04:13 -0700
Subject: [PATCH 0412/1530] perf tool_pmu: Remove duplicate io.h header

Remove duplicate inclusion of api/io.h.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202410131417.ynhvnEJb-lkp@intel.com/
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20241016160413.51587-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/tool_pmu.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/perf/util/tool_pmu.c b/tools/perf/util/tool_pmu.c
index bd1cee643eb50..4fb0975784794 100644
--- a/tools/perf/util/tool_pmu.c
+++ b/tools/perf/util/tool_pmu.c
@@ -11,7 +11,6 @@
 #include "tsc.h"
 #include <api/fs/fs.h>
 #include <api/io.h>
-#include <api/io.h>
 #include <internal/threadmap.h>
 #include <perf/threadmap.h>
 #include <fcntl.h>

From b68b5b36c790a82522623f9f1fd1c4e1f06aff2d Mon Sep 17 00:00:00 2001
From: Dapeng Mi <dapeng1.mi@linux.intel.com>
Date: Fri, 11 Oct 2024 11:02:06 +0000
Subject: [PATCH 0413/1530] perf x86/topdown: Make topdown metrics comparators
 be symmetric

The commit "3b5edc0421e2 (perf x86/topdown: Don't move topdown metric
 events in group)" modifies topdown metrics comparator to move topdown
metrics events which are not in same group with previous event. But it
just modifies the 2nd comparator and causes the comparators become
asymmetric.

Thus modify the 1st topdown metrics comparator and make the two
comparators be symmetric, and refine the comments as well.

Suggested-by: Ian Rogers <irogers@google.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20241011110207.1032235-1-dapeng1.mi@linux.intel.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/x86/util/evlist.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index 438e4639fa892..447a734e591c8 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -52,7 +52,7 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 	 *          3,015,058      cycles
 	 *    <not supported>      topdown-retiring
 	 *
-	 * if slots event and topdown metrics events are in two groups, the group which
+	 * If slots event and topdown metrics events are in two groups, the group which
 	 * has topdown metrics events must contain only the topdown metrics event,
 	 * otherwise topdown metrics event can't be regrouped correctly as well, e.g.
 	 *
@@ -69,13 +69,16 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 			return -1;
 		if (arch_is_topdown_slots(rhs))
 			return 1;
-		/* Followed by topdown events. */
-		if (arch_is_topdown_metrics(lhs) && !arch_is_topdown_metrics(rhs))
-			return -1;
+
 		/*
-		 * Move topdown events forward only when topdown events
-		 * are not in same group with previous event.
+		 * Move topdown metrics events forward only when topdown metrics
+		 * events are not in same group with previous slots event. If
+		 * topdown metrics events are already in same group with slots
+		 * event, do nothing.
 		 */
+		if (arch_is_topdown_metrics(lhs) && !arch_is_topdown_metrics(rhs) &&
+		    lhs->core.leader != rhs->core.leader)
+			return -1;
 		if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs) &&
 		    lhs->core.leader != rhs->core.leader)
 			return 1;

From fbc798316bef1b143e2cd0665cc6079529d6b0db Mon Sep 17 00:00:00 2001
From: Dapeng Mi <dapeng1.mi@linux.intel.com>
Date: Fri, 11 Oct 2024 11:02:07 +0000
Subject: [PATCH 0414/1530] perf x86/topdown: Refine helper
 arch_is_topdown_metrics()

Leverage the existed function perf_pmu__name_from_config() to check if
an event is topdown metrics event. perf_pmu__name_from_config() goes
through the defined formats and figures out the config of pre-defined
topdown events.

This avoids to figure out the config of topdown pre-defined events with
hard-coded format strings "event=" and "umask=" and provides more
flexibility.

Suggested-by: Ian Rogers <irogers@google.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20241011110207.1032235-2-dapeng1.mi@linux.intel.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/x86/util/topdown.c | 39 +++++++-----------------------
 1 file changed, 9 insertions(+), 30 deletions(-)

diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c
index cb2c64928bc4b..f63747d0abdf9 100644
--- a/tools/perf/arch/x86/util/topdown.c
+++ b/tools/perf/arch/x86/util/topdown.c
@@ -41,43 +41,22 @@ bool arch_is_topdown_slots(const struct evsel *evsel)
 	return false;
 }
 
-static int compare_topdown_event(void *vstate, struct pmu_event_info *info)
-{
-	int *config = vstate;
-	int event = 0;
-	int umask = 0;
-	char *str;
-
-	if (!strcasestr(info->name, "topdown"))
-		return 0;
-
-	str = strcasestr(info->str, "event=");
-	if (str)
-		sscanf(str, "event=%x", &event);
-
-	str = strcasestr(info->str, "umask=");
-	if (str)
-		sscanf(str, "umask=%x", &umask);
-
-	if (event == 0 && *config == (event | umask << 8))
-		return 1;
-
-	return 0;
-}
-
 bool arch_is_topdown_metrics(const struct evsel *evsel)
 {
-	struct perf_pmu *pmu = evsel__find_pmu(evsel);
 	int config = evsel->core.attr.config;
+	const char *name_from_config;
+	struct perf_pmu *pmu;
 
-	if (!pmu || !pmu->is_core)
+	/* All topdown events have an event code of 0. */
+	if ((config & 0xFF) != 0)
 		return false;
 
-	if (perf_pmu__for_each_event(pmu, false, &config,
-				     compare_topdown_event))
-		return true;
+	pmu = evsel__find_pmu(evsel);
+	if (!pmu || !pmu->is_core)
+		return false;
 
-	return false;
+	name_from_config = perf_pmu__name_from_config(pmu, config);
+	return name_from_config && strcasestr(name_from_config, "topdown");
 }
 
 /*

From 34f99d3b706a519e556841f405c224ca708b1f54 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Barnab=C3=A1s=20Cz=C3=A9m=C3=A1n?=
 <barnabas.czeman@mainlining.org>
Date: Wed, 16 Oct 2024 20:54:05 +0200
Subject: [PATCH 0415/1530] power: supply: bq27xxx: Fix registers of bq27426
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Correct bq27426 registers, according to technical reference manual
it does not have Design Capacity register so it is not register
compatible with bq27421.

Fixes: 5ef6a16033b47 ("power: supply: bq27xxx: Add support for BQ27426")
Signed-off-by: Barnabás Czémán <barnabas.czeman@mainlining.org>
Link: https://lore.kernel.org/r/20241016-fix_bq27426-v2-1-aa6c0f51a9f6@mainlining.org
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/bq27xxx_battery.c | 37 ++++++++++++++++++++++++--
 1 file changed, 35 insertions(+), 2 deletions(-)

diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index e47556ec3cfea..40c5ac7a11188 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -449,9 +449,29 @@ static u8
 		[BQ27XXX_REG_AP] = 0x18,
 		BQ27XXX_DM_REG_ROWS,
 	},
+	bq27426_regs[BQ27XXX_REG_MAX] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x02,
+		[BQ27XXX_REG_INT_TEMP] = 0x1e,
+		[BQ27XXX_REG_VOLT] = 0x04,
+		[BQ27XXX_REG_AI] = 0x10,
+		[BQ27XXX_REG_FLAGS] = 0x06,
+		[BQ27XXX_REG_TTE] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTF] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTES] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTECP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_NAC] = 0x08,
+		[BQ27XXX_REG_RC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x0e,
+		[BQ27XXX_REG_CYCT] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_AE] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_SOC] = 0x1c,
+		[BQ27XXX_REG_DCAP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_AP] = 0x18,
+		BQ27XXX_DM_REG_ROWS,
+	},
 #define bq27411_regs bq27421_regs
 #define bq27425_regs bq27421_regs
-#define bq27426_regs bq27421_regs
 #define bq27441_regs bq27421_regs
 #define bq27621_regs bq27421_regs
 	bq27z561_regs[BQ27XXX_REG_MAX] = {
@@ -769,10 +789,23 @@ static enum power_supply_property bq27421_props[] = {
 };
 #define bq27411_props bq27421_props
 #define bq27425_props bq27421_props
-#define bq27426_props bq27421_props
 #define bq27441_props bq27421_props
 #define bq27621_props bq27421_props
 
+static enum power_supply_property bq27426_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_NOW,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
 static enum power_supply_property bq27z561_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_PRESENT,

From bd3ee57b9d4c58edbf6f7bba071f6e508c7ff1c6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:06:15 +0200
Subject: [PATCH 0416/1530] power: supply: core: use device mutex wrappers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The mutex is an implementation detail of struct device.
Use the dedicated wrappers to access the field.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20241005-power-supply-cleanups-v1-1-45303b2d0a4d@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/power_supply_core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index 84b77fb499497..e0c87a08bc26d 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -152,7 +152,7 @@ static void power_supply_deferred_register_work(struct work_struct *work)
 						deferred_register_work.work);
 
 	if (psy->dev.parent) {
-		while (!mutex_trylock(&psy->dev.parent->mutex)) {
+		while (!device_trylock(psy->dev.parent)) {
 			if (psy->removing)
 				return;
 			msleep(10);
@@ -162,7 +162,7 @@ static void power_supply_deferred_register_work(struct work_struct *work)
 	power_supply_changed(psy);
 
 	if (psy->dev.parent)
-		mutex_unlock(&psy->dev.parent->mutex);
+		device_unlock(psy->dev.parent);
 }
 
 #ifdef CONFIG_OF

From cf70da29c4993bf23df68b67a82dfa3da8234e75 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:06:16 +0200
Subject: [PATCH 0417/1530] power: supply: core: unexport
 power_supply_property_is_writeable()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since commit ("power: supply: Drop use_cnt check from power_supply_property_is_writeable()"),
this function does not check use_cnt anymore, making it unsuitable for
general usage. As it is only used by the psy core anyways, remove it
from the public header and unexport it to avoid misusage.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20241005-power-supply-cleanups-v1-2-45303b2d0a4d@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/power_supply.h       | 3 +++
 drivers/power/supply/power_supply_core.c  | 1 -
 drivers/power/supply/power_supply_hwmon.c | 1 +
 include/linux/power_supply.h              | 2 --
 4 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/power/supply/power_supply.h b/drivers/power/supply/power_supply.h
index 3cbafc58bdad0..1bc57615ba68f 100644
--- a/drivers/power/supply/power_supply.h
+++ b/drivers/power/supply/power_supply.h
@@ -13,6 +13,9 @@ struct device;
 struct device_type;
 struct power_supply;
 
+extern int power_supply_property_is_writeable(struct power_supply *psy,
+					      enum power_supply_property psp);
+
 #ifdef CONFIG_SYSFS
 
 extern void power_supply_init_attrs(void);
diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index e0c87a08bc26d..16085eff00844 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -1231,7 +1231,6 @@ int power_supply_property_is_writeable(struct power_supply *psy,
 {
 	return psy->desc->property_is_writeable && psy->desc->property_is_writeable(psy, psp);
 }
-EXPORT_SYMBOL_GPL(power_supply_property_is_writeable);
 
 void power_supply_external_power_changed(struct power_supply *psy)
 {
diff --git a/drivers/power/supply/power_supply_hwmon.c b/drivers/power/supply/power_supply_hwmon.c
index 6fbbfb1c685e6..01be04903d7d2 100644
--- a/drivers/power/supply/power_supply_hwmon.c
+++ b/drivers/power/supply/power_supply_hwmon.c
@@ -7,6 +7,7 @@
 #include <linux/hwmon.h>
 #include <linux/power_supply.h>
 #include <linux/slab.h>
+#include "power_supply.h"
 
 struct power_supply_hwmon {
 	struct power_supply *psy;
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index 14eedefb3ac85..c1d6cb7f4c40e 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -865,8 +865,6 @@ static inline int power_supply_set_property(struct power_supply *psy,
 			    const union power_supply_propval *val)
 { return 0; }
 #endif
-extern int power_supply_property_is_writeable(struct power_supply *psy,
-					enum power_supply_property psp);
 extern void power_supply_external_power_changed(struct power_supply *psy);
 
 extern struct power_supply *__must_check

From 3120b5f218ca8e2b375d496e2ff3f4f861fbc013 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 5 Oct 2024 12:06:17 +0200
Subject: [PATCH 0418/1530] power: supply: core: mark attribute arrays as
 ro_after_init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The attribute arrays are only modified during the __init phase.
To protect them against intentional or accidental modification,
mark them as __ro_after_init.

To make sure no modifications are introduced, also mark the return
values of the accessors as const.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20241005-power-supply-cleanups-v1-3-45303b2d0a4d@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/power_supply.h       |  2 +-
 drivers/power/supply/power_supply_sysfs.c | 12 ++++++------
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/power/supply/power_supply.h b/drivers/power/supply/power_supply.h
index 1bc57615ba68f..4c558fb3db721 100644
--- a/drivers/power/supply/power_supply.h
+++ b/drivers/power/supply/power_supply.h
@@ -18,7 +18,7 @@ extern int power_supply_property_is_writeable(struct power_supply *psy,
 
 #ifdef CONFIG_SYSFS
 
-extern void power_supply_init_attrs(void);
+extern void __init power_supply_init_attrs(void);
 extern int power_supply_uevent(const struct device *dev, struct kobj_uevent_env *env);
 extern const struct attribute_group *power_supply_attr_groups[];
 
diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c
index 16b3c5880cd8c..571de43fcca98 100644
--- a/drivers/power/supply/power_supply_sysfs.c
+++ b/drivers/power/supply/power_supply_sysfs.c
@@ -142,7 +142,7 @@ static const char * const POWER_SUPPLY_CHARGE_BEHAVIOUR_TEXT[] = {
 	[POWER_SUPPLY_CHARGE_BEHAVIOUR_FORCE_DISCHARGE]	= "force-discharge",
 };
 
-static struct power_supply_attr power_supply_attrs[] = {
+static struct power_supply_attr power_supply_attrs[] __ro_after_init = {
 	/* Properties of type `int' */
 	POWER_SUPPLY_ENUM_ATTR(STATUS),
 	POWER_SUPPLY_ENUM_ATTR(CHARGE_TYPE),
@@ -225,9 +225,9 @@ static struct power_supply_attr power_supply_attrs[] = {
 #define POWER_SUPPLY_ATTR_CNT ARRAY_SIZE(power_supply_attrs)
 
 static struct attribute *
-__power_supply_attrs[POWER_SUPPLY_ATTR_CNT + 1];
+__power_supply_attrs[POWER_SUPPLY_ATTR_CNT + 1] __ro_after_init;
 
-static struct power_supply_attr *to_ps_attr(struct device_attribute *attr)
+static const struct power_supply_attr *to_ps_attr(struct device_attribute *attr)
 {
 	return container_of(attr, struct power_supply_attr, dev_attr);
 }
@@ -273,7 +273,7 @@ static ssize_t power_supply_show_property(struct device *dev,
 					  char *buf) {
 	ssize_t ret;
 	struct power_supply *psy = dev_get_drvdata(dev);
-	struct power_supply_attr *ps_attr = to_ps_attr(attr);
+	const struct power_supply_attr *ps_attr = to_ps_attr(attr);
 	enum power_supply_property psp = dev_attr_psp(attr);
 	union power_supply_propval value;
 
@@ -326,7 +326,7 @@ static ssize_t power_supply_store_property(struct device *dev,
 					   const char *buf, size_t count) {
 	ssize_t ret;
 	struct power_supply *psy = dev_get_drvdata(dev);
-	struct power_supply_attr *ps_attr = to_ps_attr(attr);
+	const struct power_supply_attr *ps_attr = to_ps_attr(attr);
 	enum power_supply_property psp = dev_attr_psp(attr);
 	union power_supply_propval value;
 
@@ -401,7 +401,7 @@ const struct attribute_group *power_supply_attr_groups[] = {
 	NULL
 };
 
-void power_supply_init_attrs(void)
+void __init power_supply_init_attrs(void)
 {
 	int i;
 

From 5d121065a6993e5ab4ccc0c9629241f256d11ad0 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Thu, 26 Sep 2024 16:37:26 -0500
Subject: [PATCH 0419/1530] dt-bindings: power/supply: qcom,pmi8998-charger:
 Drop incorrect "#interrupt-cells" from example

Enabling dtc interrupt_provider check reveals the example is missing
the "interrupt-controller" property as it is a dependency of
"#interrupt-cells". However, the PMIC parent node is not an interrupt
controller at all, so the "#interrupt-cells" is erroneous.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Link: https://lore.kernel.org/r/20240926213727.3064977-1-robh@kernel.org
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 .../devicetree/bindings/power/supply/qcom,pmi8998-charger.yaml   | 1 -
 1 file changed, 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/power/supply/qcom,pmi8998-charger.yaml b/Documentation/devicetree/bindings/power/supply/qcom,pmi8998-charger.yaml
index 277c47e048b65..a0f9d49ff8fb6 100644
--- a/Documentation/devicetree/bindings/power/supply/qcom,pmi8998-charger.yaml
+++ b/Documentation/devicetree/bindings/power/supply/qcom,pmi8998-charger.yaml
@@ -60,7 +60,6 @@ examples:
     pmic {
       #address-cells = <1>;
       #size-cells = <0>;
-      #interrupt-cells = <4>;
 
       charger@1000 {
         compatible = "qcom,pmi8998-charger";

From d10ff07dd2b933e3864c592ca932996b07bbf22a Mon Sep 17 00:00:00 2001
From: ChiYuan Huang <cy_huang@richtek.com>
Date: Wed, 25 Sep 2024 16:32:58 +0800
Subject: [PATCH 0420/1530] power: supply: rt9471: Fix wrong WDT function
 regfield declaration

Fix F_WDT and F_WDT_RST wrong regfield declaration.

Fixes: 4a1a5f6781d8 ("power: supply: rt9471: Add Richtek RT9471 charger driver")
Reported-by: Lucas Tsai <lucas_tsai@richtek.com>
Signed-off-by: ChiYuan Huang <cy_huang@richtek.com>
Link: https://lore.kernel.org/r/f862e23f220612f01fabb6d8e76cfaf63756c22b.1727252762.git.cy_huang@richtek.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/rt9471.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/power/supply/rt9471.c b/drivers/power/supply/rt9471.c
index c04af1ee89c67..730b252b49006 100644
--- a/drivers/power/supply/rt9471.c
+++ b/drivers/power/supply/rt9471.c
@@ -153,8 +153,8 @@ struct rt9471_chip {
 };
 
 static const struct reg_field rt9471_reg_fields[F_MAX_FIELDS] = {
-	[F_WDT]		= REG_FIELD(RT9471_REG_TOP, 0, 0),
-	[F_WDT_RST]	= REG_FIELD(RT9471_REG_TOP, 1, 1),
+	[F_WDT]		= REG_FIELD(RT9471_REG_TOP, 0, 1),
+	[F_WDT_RST]	= REG_FIELD(RT9471_REG_TOP, 2, 2),
 	[F_CHG_EN]	= REG_FIELD(RT9471_REG_FUNC, 0, 0),
 	[F_HZ]		= REG_FIELD(RT9471_REG_FUNC, 5, 5),
 	[F_BATFET_DIS]	= REG_FIELD(RT9471_REG_FUNC, 7, 7),

From c46a9ee5c6210682611d3d4276436c23a95e1996 Mon Sep 17 00:00:00 2001
From: ChiYuan Huang <cy_huang@richtek.com>
Date: Wed, 25 Sep 2024 16:32:59 +0800
Subject: [PATCH 0421/1530] power: supply: rt9471: Use IC status regfield to
 report real charger status

Use IC status regfield to rewrite the 'get_staus' function. The original
one cannot cover some special scenario like as charger OTG or JEITA case.

Fixes: 4a1a5f6781d8 ("power: supply: rt9471: Add Richtek RT9471 charger driver")
Reported-by: Lucas Tsai <lucas_tsai@richtek.com>
Signed-off-by: ChiYuan Huang <cy_huang@richtek.com>
Link: https://lore.kernel.org/r/67ba92bb4a9c51d9cafadab30b788a3a2c3048e1.1727252762.git.cy_huang@richtek.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/rt9471.c | 48 ++++++++++++++++++++++-------------
 1 file changed, 31 insertions(+), 17 deletions(-)

diff --git a/drivers/power/supply/rt9471.c b/drivers/power/supply/rt9471.c
index 730b252b49006..67b86ac91a21d 100644
--- a/drivers/power/supply/rt9471.c
+++ b/drivers/power/supply/rt9471.c
@@ -139,6 +139,19 @@ enum {
 	RT9471_PORTSTAT_DCP,
 };
 
+enum {
+	RT9471_ICSTAT_SLEEP = 0,
+	RT9471_ICSTAT_VBUSRDY,
+	RT9471_ICSTAT_TRICKLECHG,
+	RT9471_ICSTAT_PRECHG,
+	RT9471_ICSTAT_FASTCHG,
+	RT9471_ICSTAT_IEOC,
+	RT9471_ICSTAT_BGCHG,
+	RT9471_ICSTAT_CHGDONE,
+	RT9471_ICSTAT_CHGFAULT,
+	RT9471_ICSTAT_OTG = 15,
+};
+
 struct rt9471_chip {
 	struct device *dev;
 	struct regmap *regmap;
@@ -255,31 +268,32 @@ static int rt9471_get_ieoc(struct rt9471_chip *chip, int *microamp)
 
 static int rt9471_get_status(struct rt9471_chip *chip, int *status)
 {
-	unsigned int chg_ready, chg_done, fault_stat;
+	unsigned int ic_stat;
 	int ret;
 
-	ret = regmap_field_read(chip->rm_fields[F_ST_CHG_RDY], &chg_ready);
-	if (ret)
-		return ret;
-
-	ret = regmap_field_read(chip->rm_fields[F_ST_CHG_DONE], &chg_done);
+	ret = regmap_field_read(chip->rm_fields[F_IC_STAT], &ic_stat);
 	if (ret)
 		return ret;
 
-	ret = regmap_read(chip->regmap, RT9471_REG_STAT1, &fault_stat);
-	if (ret)
-		return ret;
-
-	fault_stat &= RT9471_CHGFAULT_MASK;
-
-	if (chg_ready && chg_done)
-		*status = POWER_SUPPLY_STATUS_FULL;
-	else if (chg_ready && fault_stat)
+	switch (ic_stat) {
+	case RT9471_ICSTAT_VBUSRDY:
+	case RT9471_ICSTAT_CHGFAULT:
 		*status = POWER_SUPPLY_STATUS_NOT_CHARGING;
-	else if (chg_ready && !fault_stat)
+		break;
+	case RT9471_ICSTAT_TRICKLECHG ... RT9471_ICSTAT_BGCHG:
 		*status = POWER_SUPPLY_STATUS_CHARGING;
-	else
+		break;
+	case RT9471_ICSTAT_CHGDONE:
+		*status = POWER_SUPPLY_STATUS_FULL;
+		break;
+	case RT9471_ICSTAT_SLEEP:
+	case RT9471_ICSTAT_OTG:
 		*status = POWER_SUPPLY_STATUS_DISCHARGING;
+		break;
+	default:
+		*status = POWER_SUPPLY_STATUS_UNKNOWN;
+		break;
+	}
 
 	return 0;
 }

From bded860c3110a45fe091f67b2fe6f3b2bb096165 Mon Sep 17 00:00:00 2001
From: Chris Morgan <macromorgan@hotmail.com>
Date: Thu, 26 Sep 2024 09:43:45 -0500
Subject: [PATCH 0422/1530] power: supply: rk817: stop updating info in suspend

The driver has a thread that checks the battery every 8 seconds. Stop
this thread during device suspend as while the device is suspended not
all values seem to be read correctly (such as battery voltage). The
resume function triggers the thread to start again.

Signed-off-by: Chris Morgan <macromorgan@hotmail.com>
Link: https://lore.kernel.org/r/20240926144346.94630-2-macroalpha82@gmail.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/rk817_charger.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/power/supply/rk817_charger.c b/drivers/power/supply/rk817_charger.c
index a3d377a32b497..d81fc7bd1cd2b 100644
--- a/drivers/power/supply/rk817_charger.c
+++ b/drivers/power/supply/rk817_charger.c
@@ -1202,6 +1202,15 @@ static int rk817_charger_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static int __maybe_unused rk817_suspend(struct device *dev)
+{
+	struct rk817_charger *charger = dev_get_drvdata(dev);
+
+	cancel_delayed_work_sync(&charger->work);
+
+	return 0;
+}
+
 static int __maybe_unused rk817_resume(struct device *dev)
 {
 
@@ -1213,7 +1222,7 @@ static int __maybe_unused rk817_resume(struct device *dev)
 	return 0;
 }
 
-static SIMPLE_DEV_PM_OPS(rk817_charger_pm, NULL, rk817_resume);
+static SIMPLE_DEV_PM_OPS(rk817_charger_pm, rk817_suspend, rk817_resume);
 
 static struct platform_driver rk817_charger_driver = {
 	.probe    = rk817_charger_probe,

From 1e5335d00707220b46c28ab09cd09a1837b84978 Mon Sep 17 00:00:00 2001
From: Chris Morgan <macromorgan@hotmail.com>
Date: Thu, 26 Sep 2024 09:43:46 -0500
Subject: [PATCH 0423/1530] power: supply: rk817: Update battery capacity
 calibration

The battery capacity calibration function continues to be a source of
bugs for end users, especially when coming out of suspend. This occurs
when the device has incorrect readings for voltage, and causes the
current code to set fully charged capacity incorrectly.

Add checks to ensure we don't attempt a capacity calibration when we
have invalid voltage values or no battery present, and remove the code
that attempts to automatically set the fully charged capacity in lieu of
making the value writeable. This way userspace is able to adjust the
fully charged capacity for a degraded battery.

Signed-off-by: Chris Morgan <macromorgan@hotmail.com>
Link: https://lore.kernel.org/r/20240926144346.94630-3-macroalpha82@gmail.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/rk817_charger.c | 101 +++++++++++++++------------
 1 file changed, 55 insertions(+), 46 deletions(-)

diff --git a/drivers/power/supply/rk817_charger.c b/drivers/power/supply/rk817_charger.c
index d81fc7bd1cd2b..958d375e1063a 100644
--- a/drivers/power/supply/rk817_charger.c
+++ b/drivers/power/supply/rk817_charger.c
@@ -240,9 +240,32 @@ static int rk817_record_battery_nvram_values(struct rk817_charger *charger)
 static int rk817_bat_calib_cap(struct rk817_charger *charger)
 {
 	struct rk808 *rk808 = charger->rk808;
-	int tmp, charge_now, charge_now_adc, volt_avg;
+	int charge_now, charge_now_adc;
 	u8 bulk_reg[4];
 
+	/* Don't do anything if there's no battery. */
+	if (!charger->battery_present)
+		return 0;
+
+	/*
+	 * When resuming from suspend, sometimes the voltage value would be
+	 * incorrect. BSP would simply wait two seconds and try reading the
+	 * values again. Do not do any sort of calibration activity when the
+	 * reported value is incorrect. The next scheduled update of battery
+	 * vaules should then return valid data and the driver can continue.
+	 * Use 2.7v as the sanity value because per the datasheet the PMIC
+	 * can in no way support a battery voltage lower than this. BSP only
+	 * checked for values too low, but I'm adding in a check for values
+	 * too high just in case; again the PMIC can in no way support
+	 * voltages above 4.45v, so this seems like a good value.
+	 */
+	if ((charger->volt_avg_uv < 2700000) || (charger->volt_avg_uv > 4450000)) {
+		dev_dbg(charger->dev,
+			"Battery voltage of %d is invalid, ignoring.\n",
+			charger->volt_avg_uv);
+		return -EINVAL;
+	}
+
 	/* Calibrate the soc and fcc on a fully charged battery */
 
 	if (charger->charge_status == CHARGE_FINISH && (!charger->soc_cal)) {
@@ -304,51 +327,6 @@ static int rk817_bat_calib_cap(struct rk817_charger *charger)
 		}
 	}
 
-	/*
-	 * Calibrate the fully charged capacity when we previously had a full
-	 * battery (soc_cal = 1) and are now empty (at or below minimum design
-	 * voltage). If our columb counter is still positive, subtract that
-	 * from our fcc value to get a calibrated fcc, and if our columb
-	 * counter is negative add that to our fcc (but not to exceed our
-	 * design capacity).
-	 */
-	regmap_bulk_read(charger->rk808->regmap, RK817_GAS_GAUGE_BAT_VOL_H,
-			 bulk_reg, 2);
-	tmp = get_unaligned_be16(bulk_reg);
-	volt_avg = (charger->voltage_k * tmp) + 1000 * charger->voltage_b;
-	if (volt_avg <= charger->bat_voltage_min_design_uv &&
-	    charger->soc_cal) {
-		regmap_bulk_read(rk808->regmap, RK817_GAS_GAUGE_Q_PRES_H3,
-				 bulk_reg, 4);
-		charge_now_adc = get_unaligned_be32(bulk_reg);
-		charge_now = ADC_TO_CHARGE_UAH(charge_now_adc,
-					       charger->res_div);
-		/*
-		 * Note, if charge_now is negative this will add it (what we
-		 * want) and if it's positive this will subtract (also what
-		 * we want).
-		 */
-		charger->fcc_mah = charger->fcc_mah - (charge_now / 1000);
-
-		dev_dbg(charger->dev,
-			"Recalibrating full charge capacity to %d uah\n",
-			charger->fcc_mah * 1000);
-	}
-
-	/*
-	 * Set the SOC to 0 if we are below the minimum system voltage.
-	 */
-	if (volt_avg <= charger->bat_voltage_min_design_uv) {
-		charger->soc = 0;
-		charge_now_adc = CHARGE_TO_ADC(0, charger->res_div);
-		put_unaligned_be32(charge_now_adc, bulk_reg);
-		regmap_bulk_write(rk808->regmap,
-				  RK817_GAS_GAUGE_Q_INIT_H3, bulk_reg, 4);
-		dev_warn(charger->dev,
-			 "Battery voltage %d below minimum voltage %d\n",
-			 volt_avg, charger->bat_voltage_min_design_uv);
-		}
-
 	rk817_record_battery_nvram_values(charger);
 
 	return 0;
@@ -648,6 +626,24 @@ static irqreturn_t rk817_plug_out_isr(int irq, void *cg)
 	return IRQ_HANDLED;
 }
 
+static int rk817_bat_set_prop(struct power_supply *ps,
+			      enum power_supply_property prop,
+			      const union power_supply_propval *val)
+{
+	struct rk817_charger *charger = power_supply_get_drvdata(ps);
+
+	switch (prop) {
+	case POWER_SUPPLY_PROP_CHARGE_FULL:
+		if ((val->intval < 500000) ||
+			(val->intval > charger->bat_charge_full_design_uah))
+			return -EINVAL;
+		charger->fcc_mah = val->intval / 1000;
+		return rk817_bat_calib_cap(charger);
+	default:
+		return -EINVAL;
+	}
+}
+
 static enum power_supply_property rk817_bat_props[] = {
 	POWER_SUPPLY_PROP_PRESENT,
 	POWER_SUPPLY_PROP_STATUS,
@@ -673,12 +669,25 @@ static enum power_supply_property rk817_chg_props[] = {
 	POWER_SUPPLY_PROP_VOLTAGE_AVG,
 };
 
+static int rk817_bat_prop_writeable(struct power_supply *psy,
+				    enum power_supply_property psp)
+{
+	switch (psp) {
+	case POWER_SUPPLY_PROP_CHARGE_FULL:
+		return 1;
+	default:
+		return 0;
+	}
+}
+
 static const struct power_supply_desc rk817_bat_desc = {
 	.name = "rk817-battery",
 	.type = POWER_SUPPLY_TYPE_BATTERY,
 	.properties = rk817_bat_props,
+	.property_is_writeable	= rk817_bat_prop_writeable,
 	.num_properties = ARRAY_SIZE(rk817_bat_props),
 	.get_property = rk817_bat_get_prop,
+	.set_property = rk817_bat_set_prop,
 };
 
 static const struct power_supply_desc rk817_chg_desc = {

From 5b653cb60275e1ad1a85f0d056a3084c4635623c Mon Sep 17 00:00:00 2001
From: Igor Belwon <igor.belwon@mentallysanemainliners.org>
Date: Wed, 16 Oct 2024 17:48:36 +0200
Subject: [PATCH 0424/1530] dt-bindings: pinctrl: samsung: Add
 exynos990-pinctrl compatible

Add a dedicated compatible for the exynos990-pinctrl node.

Signed-off-by: Igor Belwon <igor.belwon@mentallysanemainliners.org>
Link: https://lore.kernel.org/r/20241016154838.64515-2-igor.belwon@mentallysanemainliners.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
index a2af2c88a3316..7e6ef8249de6c 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
@@ -54,6 +54,7 @@ properties:
       - samsung,exynos7885-pinctrl
       - samsung,exynos850-pinctrl
       - samsung,exynos8895-pinctrl
+      - samsung,exynos990-pinctrl
       - samsung,exynosautov9-pinctrl
       - samsung,exynosautov920-pinctrl
       - tesla,fsd-pinctrl

From e690012f4f924f4ef4e105427b04ea3d496c6a38 Mon Sep 17 00:00:00 2001
From: Igor Belwon <igor.belwon@mentallysanemainliners.org>
Date: Wed, 16 Oct 2024 17:48:37 +0200
Subject: [PATCH 0425/1530] dt-bindings: pinctrl: samsung: Add
 exynos990-wakeup-eint compatible

Add a dedicated compatible for the exynos990-wakeup-eint node.
This SoC pin controller does not mux interrupts. It's compatible with
Exynos 850's node, while also being compatible with the Exynos7
fallback.

Signed-off-by: Igor Belwon <igor.belwon@mentallysanemainliners.org>
Link: https://lore.kernel.org/r/20241016154838.64515-3-igor.belwon@mentallysanemainliners.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml       | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
index b7c2692f0ac37..565cacadb6be7 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
@@ -47,6 +47,7 @@ properties:
       - items:
           - enum:
               - google,gs101-wakeup-eint
+              - samsung,exynos990-wakeup-eint
               - samsung,exynosautov9-wakeup-eint
           - const: samsung,exynos850-wakeup-eint
           - const: samsung,exynos7-wakeup-eint

From 2193074458dee3c4382c023740d86578db050bd8 Mon Sep 17 00:00:00 2001
From: Igor Belwon <igor.belwon@mentallysanemainliners.org>
Date: Wed, 16 Oct 2024 17:48:38 +0200
Subject: [PATCH 0426/1530] pinctrl: samsung: Add Exynos 990 SoC pinctrl
 configuration

Add SoC pinctrl configuration for the Exynos 990. The bank types
used are the same as Exynos 850, so we can reuse its macros.

Signed-off-by: Igor Belwon <igor.belwon@mentallysanemainliners.org>
Link: https://lore.kernel.org/r/20241016154838.64515-4-igor.belwon@mentallysanemainliners.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../pinctrl/samsung/pinctrl-exynos-arm64.c    | 140 ++++++++++++++++++
 drivers/pinctrl/samsung/pinctrl-samsung.c     |   2 +
 drivers/pinctrl/samsung/pinctrl-samsung.h     |   1 +
 3 files changed, 143 insertions(+)

diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
index c5df4f1bc600b..f07c26d374425 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
@@ -627,6 +627,146 @@ const struct samsung_pinctrl_of_match_data exynos850_of_data __initconst = {
 	.num_ctrl	= ARRAY_SIZE(exynos850_pin_ctrl),
 };
 
+/* pin banks of exynos990 pin-controller 0 (ALIVE) */
+static struct samsung_pin_bank_data exynos990_pin_banks0[] = {
+	/* Must start with EINTG banks, ordered by EINT group number. */
+	EXYNOS850_PIN_BANK_EINTW(8, 0x000, "gpa0", 0x00),
+	EXYNOS850_PIN_BANK_EINTW(8, 0x020, "gpa1", 0x04),
+	EXYNOS850_PIN_BANK_EINTW(8, 0x040, "gpa2", 0x08),
+	EXYNOS850_PIN_BANK_EINTW(8, 0x060, "gpa3", 0x0c),
+	EXYNOS850_PIN_BANK_EINTW(2, 0x080, "gpa4", 0x10),
+	EXYNOS850_PIN_BANK_EINTN(7, 0x0A0, "gpq0"),
+};
+
+/* pin banks of exynos990 pin-controller 1 (CMGP) */
+static struct samsung_pin_bank_data exynos990_pin_banks1[] = {
+	/* Must start with EINTG banks, ordered by EINT group number. */
+	EXYNOS850_PIN_BANK_EINTN(1, 0x000, "gpm0"),
+	EXYNOS850_PIN_BANK_EINTN(1, 0x020, "gpm1"),
+	EXYNOS850_PIN_BANK_EINTN(1, 0x040, "gpm2"),
+	EXYNOS850_PIN_BANK_EINTN(1, 0x060, "gpm3"),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x080, "gpm4", 0x00),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x0A0, "gpm5", 0x04),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x0C0, "gpm6", 0x08),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x0E0, "gpm7", 0x0c),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x100, "gpm8", 0x10),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x120, "gpm9", 0x14),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x140, "gpm10", 0x18),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x160, "gpm11", 0x1c),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x180, "gpm12", 0x20),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x1A0, "gpm13", 0x24),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x1C0, "gpm14", 0x28),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x1E0, "gpm15", 0x2c),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x200, "gpm16", 0x30),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x220, "gpm17", 0x34),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x240, "gpm18", 0x38),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x260, "gpm19", 0x3c),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x280, "gpm20", 0x40),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x2A0, "gpm21", 0x44),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x2C0, "gpm22", 0x48),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x2E0, "gpm23", 0x4c),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x300, "gpm24", 0x50),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x320, "gpm25", 0x54),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x340, "gpm26", 0x58),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x360, "gpm27", 0x5c),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x380, "gpm28", 0x60),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x3A0, "gpm29", 0x64),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x3C0, "gpm30", 0x68),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x3E0, "gpm31", 0x6c),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x400, "gpm32", 0x70),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x420, "gpm33", 0x74),
+
+};
+
+/* pin banks of exynos990 pin-controller 2 (HSI1) */
+static struct samsung_pin_bank_data exynos990_pin_banks2[] = {
+	/* Must start with EINTG banks, ordered by EINT group number. */
+	EXYNOS850_PIN_BANK_EINTG(4, 0x000, "gpf0", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(6, 0x020, "gpf1", 0x04),
+	EXYNOS850_PIN_BANK_EINTG(3, 0x040, "gpf2", 0x08),
+};
+
+/* pin banks of exynos990 pin-controller 3 (HSI2) */
+static struct samsung_pin_bank_data exynos990_pin_banks3[] = {
+	/* Must start with EINTG banks, ordered by EINT group number. */
+	EXYNOS850_PIN_BANK_EINTG(2, 0x000, "gpf3", 0x00),
+};
+
+/* pin banks of exynos990 pin-controller 4 (PERIC0) */
+static struct samsung_pin_bank_data exynos990_pin_banks4[] = {
+	/* Must start with EINTG banks, ordered by EINT group number. */
+	EXYNOS850_PIN_BANK_EINTG(8, 0x000, "gpp0", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x020, "gpp1", 0x04),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x040, "gpp2", 0x08),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x060, "gpp3", 0x0C),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x080, "gpp4", 0x10),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x0A0, "gpg0", 0x14),
+};
+
+/* pin banks of exynos990 pin-controller 5 (PERIC1) */
+static struct samsung_pin_bank_data exynos990_pin_banks5[] = {
+	/* Must start with EINTG banks, ordered by EINT group number. */
+	EXYNOS850_PIN_BANK_EINTG(8, 0x000, "gpp5", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x020, "gpp6", 0x04),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x040, "gpp7", 0x08),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x060, "gpp8", 0x0C),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x080, "gpp9", 0x10),
+	EXYNOS850_PIN_BANK_EINTG(6, 0x0A0, "gpc0", 0x14),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x0C0, "gpg1", 0x18),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x0E0, "gpb0", 0x1C),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x100, "gpb1", 0x20),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x120, "gpb2", 0x24),
+};
+
+/* pin banks of exynos990 pin-controller 6 (VTS) */
+static struct samsung_pin_bank_data exynos990_pin_banks6[] = {
+	/* Must start with EINTG banks, ordered by EINT group number. */
+	EXYNOS850_PIN_BANK_EINTG(7, 0x000, "gpv0", 0x00),
+};
+
+static const struct samsung_pin_ctrl exynos990_pin_ctrl[] __initconst = {
+	{
+		/* pin-controller instance 0 ALIVE data */
+		.pin_banks	= exynos990_pin_banks0,
+		.nr_banks	= ARRAY_SIZE(exynos990_pin_banks0),
+		.eint_wkup_init = exynos_eint_wkup_init,
+	}, {
+		/* pin-controller instance 1 CMGP data */
+		.pin_banks	= exynos990_pin_banks1,
+		.nr_banks	= ARRAY_SIZE(exynos990_pin_banks1),
+		.eint_wkup_init = exynos_eint_wkup_init,
+	}, {
+		/* pin-controller instance 2 HSI1 data */
+		.pin_banks	= exynos990_pin_banks2,
+		.nr_banks	= ARRAY_SIZE(exynos990_pin_banks2),
+		.eint_gpio_init = exynos_eint_gpio_init,
+	}, {
+		/* pin-controller instance 3 HSI2 data */
+		.pin_banks	= exynos990_pin_banks3,
+		.nr_banks	= ARRAY_SIZE(exynos990_pin_banks3),
+		.eint_gpio_init = exynos_eint_gpio_init,
+	}, {
+		/* pin-controller instance 4 PERIC0 data */
+		.pin_banks	= exynos990_pin_banks4,
+		.nr_banks	= ARRAY_SIZE(exynos990_pin_banks4),
+		.eint_gpio_init = exynos_eint_gpio_init,
+	}, {
+		/* pin-controller instance 5 PERIC1 data */
+		.pin_banks	= exynos990_pin_banks5,
+		.nr_banks	= ARRAY_SIZE(exynos990_pin_banks5),
+		.eint_gpio_init = exynos_eint_gpio_init,
+	}, {
+		/* pin-controller instance 6 VTS data */
+		.pin_banks	= exynos990_pin_banks6,
+		.nr_banks	= ARRAY_SIZE(exynos990_pin_banks6),
+	},
+};
+
+const struct samsung_pinctrl_of_match_data exynos990_of_data __initconst = {
+	.ctrl		= exynos990_pin_ctrl,
+	.num_ctrl	= ARRAY_SIZE(exynos990_pin_ctrl),
+};
+
 /* pin banks of exynosautov9 pin-controller 0 (ALIVE) */
 static const struct samsung_pin_bank_data exynosautov9_pin_banks0[] __initconst = {
 	EXYNOS850_PIN_BANK_EINTW(8, 0x000, "gpa0", 0x00),
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index 86c7de109bca3..42e40860841bc 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -1479,6 +1479,8 @@ static const struct of_device_id samsung_pinctrl_dt_match[] = {
 		.data = &exynos850_of_data },
 	{ .compatible = "samsung,exynos8895-pinctrl",
 		.data = &exynos8895_of_data },
+	{ .compatible = "samsung,exynos990-pinctrl",
+		.data = &exynos990_of_data },
 	{ .compatible = "samsung,exynosautov9-pinctrl",
 		.data = &exynosautov9_of_data },
 	{ .compatible = "samsung,exynosautov920-pinctrl",
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index dc930d620f554..615048f945243 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -385,6 +385,7 @@ extern const struct samsung_pinctrl_of_match_data exynos7_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos7885_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos850_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos8895_of_data;
+extern const struct samsung_pinctrl_of_match_data exynos990_of_data;
 extern const struct samsung_pinctrl_of_match_data exynosautov9_of_data;
 extern const struct samsung_pinctrl_of_match_data exynosautov920_of_data;
 extern const struct samsung_pinctrl_of_match_data fsd_of_data;

From 03b9d469e03d9ab1a991d8562e2d5e6c0e57558a Mon Sep 17 00:00:00 2001
From: Yijie Yang <quic_yijiyang@quicinc.com>
Date: Thu, 17 Oct 2024 17:52:38 +0800
Subject: [PATCH 0427/1530] dt-bindings: phy: describe the Qualcomm SGMII PHY

Describe the SGMII/SerDes PHY present on the qcs8300 platforms. Since
qcs8300 shares the same SerDes as sa8775p, so it fallback to the
compatible.

Signed-off-by: Yijie Yang <quic_yijiyang@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20241017-schema-v2-2-2320f68dc126@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../bindings/phy/qcom,sa8775p-dwmac-sgmii-phy.yaml         | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/phy/qcom,sa8775p-dwmac-sgmii-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sa8775p-dwmac-sgmii-phy.yaml
index b9107759b2a51..90fc8c039219c 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sa8775p-dwmac-sgmii-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sa8775p-dwmac-sgmii-phy.yaml
@@ -15,7 +15,12 @@ description:
 
 properties:
   compatible:
-    const: qcom,sa8775p-dwmac-sgmii-phy
+    oneOf:
+      - items:
+          - enum:
+              - qcom,qcs8300-dwmac-sgmii-phy
+          - const: qcom,sa8775p-dwmac-sgmii-phy
+      - const: qcom,sa8775p-dwmac-sgmii-phy
 
   reg:
     items:

From 6a612c86c8a5805c85fde359aa9c8aac6d5cba7a Mon Sep 17 00:00:00 2001
From: Sayali Lokhande <quic_sayalil@quicinc.com>
Date: Thu, 17 Oct 2024 12:22:57 +0800
Subject: [PATCH 0428/1530] dt-bindings: phy: Add QMP UFS PHY comptible for
 QCS615

Document the QMP UFS PHY compatible for Qualcomm QCS615 to support physical
layer functionality for UFS found on the SoC. Use fallback to indicate the
compatibility of the QMP UFS PHY on the QCS615 with that on the SM6115.

Signed-off-by: Sayali Lokhande <quic_sayalil@quicinc.com>
Co-developed-by: Xin Liu <quic_liuxin@quicinc.com>
Signed-off-by: Xin Liu <quic_liuxin@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20241017042300.872963-2-quic_liuxin@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../phy/qcom,sc8280xp-qmp-ufs-phy.yaml        | 45 ++++++++++---------
 1 file changed, 25 insertions(+), 20 deletions(-)

diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml
index f9cfbd0b2de6c..a93d64d1c55b4 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml
@@ -15,26 +15,31 @@ description:
 
 properties:
   compatible:
-    enum:
-      - qcom,msm8996-qmp-ufs-phy
-      - qcom,msm8998-qmp-ufs-phy
-      - qcom,sa8775p-qmp-ufs-phy
-      - qcom,sc7180-qmp-ufs-phy
-      - qcom,sc7280-qmp-ufs-phy
-      - qcom,sc8180x-qmp-ufs-phy
-      - qcom,sc8280xp-qmp-ufs-phy
-      - qcom,sdm845-qmp-ufs-phy
-      - qcom,sm6115-qmp-ufs-phy
-      - qcom,sm6125-qmp-ufs-phy
-      - qcom,sm6350-qmp-ufs-phy
-      - qcom,sm7150-qmp-ufs-phy
-      - qcom,sm8150-qmp-ufs-phy
-      - qcom,sm8250-qmp-ufs-phy
-      - qcom,sm8350-qmp-ufs-phy
-      - qcom,sm8450-qmp-ufs-phy
-      - qcom,sm8475-qmp-ufs-phy
-      - qcom,sm8550-qmp-ufs-phy
-      - qcom,sm8650-qmp-ufs-phy
+    oneOf:
+      - items:
+          - enum:
+              - qcom,qcs615-qmp-ufs-phy
+          - const: qcom,sm6115-qmp-ufs-phy
+      - enum:
+          - qcom,msm8996-qmp-ufs-phy
+          - qcom,msm8998-qmp-ufs-phy
+          - qcom,sa8775p-qmp-ufs-phy
+          - qcom,sc7180-qmp-ufs-phy
+          - qcom,sc7280-qmp-ufs-phy
+          - qcom,sc8180x-qmp-ufs-phy
+          - qcom,sc8280xp-qmp-ufs-phy
+          - qcom,sdm845-qmp-ufs-phy
+          - qcom,sm6115-qmp-ufs-phy
+          - qcom,sm6125-qmp-ufs-phy
+          - qcom,sm6350-qmp-ufs-phy
+          - qcom,sm7150-qmp-ufs-phy
+          - qcom,sm8150-qmp-ufs-phy
+          - qcom,sm8250-qmp-ufs-phy
+          - qcom,sm8350-qmp-ufs-phy
+          - qcom,sm8450-qmp-ufs-phy
+          - qcom,sm8475-qmp-ufs-phy
+          - qcom,sm8550-qmp-ufs-phy
+          - qcom,sm8650-qmp-ufs-phy
 
   reg:
     maxItems: 1

From 26fb23ce35e2d2233f810069ab11210851acbf54 Mon Sep 17 00:00:00 2001
From: Qiang Yu <quic_qianyu@quicinc.com>
Date: Wed, 16 Oct 2024 20:04:06 -0700
Subject: [PATCH 0429/1530] dt-bindings: phy: qcom,sc8280xp-qmp-pcie-phy:
 Document the X1E80100 QMP PCIe PHY Gen4 x8

PCIe 3rd instance of X1E80100 supports Gen 4 x8 which needs different
8 lane capable QMP PCIe PHY with hardware revision v6.30. Document Gen
4 x8 PHY as separate module.

Signed-off-by: Qiang Yu <quic_qianyu@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Acked-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20241017030412.265000-2-quic_qianyu@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml    | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
index dcf4fa55fbba5..680ec3113c2ba 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
@@ -41,6 +41,7 @@ properties:
       - qcom,x1e80100-qmp-gen3x2-pcie-phy
       - qcom,x1e80100-qmp-gen4x2-pcie-phy
       - qcom,x1e80100-qmp-gen4x4-pcie-phy
+      - qcom,x1e80100-qmp-gen4x8-pcie-phy
 
   reg:
     minItems: 1
@@ -172,6 +173,7 @@ allOf:
               - qcom,sc8280xp-qmp-gen3x2-pcie-phy
               - qcom,sc8280xp-qmp-gen3x4-pcie-phy
               - qcom,x1e80100-qmp-gen4x4-pcie-phy
+              - qcom,x1e80100-qmp-gen4x8-pcie-phy
     then:
       properties:
         clocks:
@@ -201,6 +203,7 @@ allOf:
               - qcom,sm8550-qmp-gen4x2-pcie-phy
               - qcom,sm8650-qmp-gen4x2-pcie-phy
               - qcom,x1e80100-qmp-gen4x2-pcie-phy
+              - qcom,x1e80100-qmp-gen4x8-pcie-phy
     then:
       properties:
         resets:

From e961ec81a39bc57119f165cf2e994fc29637fd97 Mon Sep 17 00:00:00 2001
From: Qiang Yu <quic_qianyu@quicinc.com>
Date: Wed, 16 Oct 2024 20:04:09 -0700
Subject: [PATCH 0430/1530] phy: qcom: qmp: Add phy register and clk setting
 for x1e80100 PCIe3

Currently driver supports only x4 lane based functionality using tx/rx and
tx2/rx2 pair of register sets. To support 8 lane functionality with PCIe3,
PCIe3 related QMP PHY provides additional programming which are available
as txz and rxz based register set. Hence add txz and rxz based registers
usage and programming sequences.

As soon as software programs the txz and rxz based register set, hardware
shall "broadcast" the same settings to the tx/rx pair of registers for all
the 8 lanes, which saves the effort of software programming them one by
one.

There might be some tx and/or rx registers on some lanes need minor tweaks,
program them after programming the txz and rxz reigster set.

In addition, x1e80100 uses QMP PHY ver 6.30 for PCIe Gen4 x8, hence add
two new header files to reflect the new register offsets.

Signed-off-by: Qiang Yu <quic_qianyu@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Konrad Dybcio <konradybcio@kernel.org>
Link: https://lore.kernel.org/r/20241017030412.265000-5-quic_qianyu@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-pcie.c      | 214 ++++++++++++++++++
 .../qualcomm/phy-qcom-qmp-pcs-pcie-v6_30.h    |  25 ++
 drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6_30.h |  19 ++
 3 files changed, 258 insertions(+)
 create mode 100644 drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6_30.h
 create mode 100644 drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6_30.h

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
index f71787fb4d7e9..e7e2d69b68d62 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
@@ -34,6 +34,8 @@
 #include "phy-qcom-qmp-pcs-pcie-v5_20.h"
 #include "phy-qcom-qmp-pcs-pcie-v6.h"
 #include "phy-qcom-qmp-pcs-pcie-v6_20.h"
+#include "phy-qcom-qmp-pcs-pcie-v6_30.h"
+#include "phy-qcom-qmp-pcs-v6_30.h"
 #include "phy-qcom-qmp-pcie-qhp.h"
 
 #define PHY_INIT_COMPLETE_TIMEOUT		10000
@@ -1344,6 +1346,154 @@ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_pcs_misc_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G4_FOM_EQ_CONFIG5, 0x8a),
 };
 
+static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x8_pcie_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE1, 0x26),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE1, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x0d),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x68),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE1, 0xab),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE1, 0xaa),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x12),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0xf8),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CORE_CLK_DIV_MODE0, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x0d),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x41),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0xab),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0xaa),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_HS_SWITCH_SEL_1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x62),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_POST_DIV_MUX, 0x40),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_BIAS_EN_CLK_BUFLR_EN, 0x1c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CLK_ENABLE1, 0x90),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYS_CLK_CTRL, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x46),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_CFG, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CLK_SELECT, 0x34),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_MISC_1, 0x88),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_MODE, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_VCO_DC_LEVEL_CTRL, 0x0f),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x8_pcie_ln_shrd_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RXCLK_DIV2_CTRL, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_SUMMER_CAL_SPD_MODE, 0x5b),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_DFE_DAC_ENABLE1, 0x88),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_TX_ADAPT_POST_THRESH1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_TX_ADAPT_POST_THRESH2, 0x0d),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MODE_RATE_0_1_B0, 0x12),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MODE_RATE_0_1_B1, 0x12),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MODE_RATE_0_1_B2, 0xdb),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MODE_RATE_0_1_B3, 0x9a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MODE_RATE_0_1_B4, 0x38),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MODE_RATE_0_1_B5, 0xb6),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MODE_RATE_0_1_B6, 0x64),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH1_RATE210, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH1_RATE3, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH2_RATE210, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH2_RATE3, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH3_RATE210, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH3_RATE3, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH4_RATE3, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH5_RATE3, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH6_RATE3, 0x1f),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x8_pcie_txz_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_TX_RES_CODE_LANE_OFFSET_TX, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_TX_RES_CODE_LANE_OFFSET_RX, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_TX_LANE_MODE_1, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_TX_LANE_MODE_2, 0x10),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_TX_LANE_MODE_3, 0x51),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_TX_TRAN_DRVR_EMP_EN, 0x34),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x8_pcie_rxz_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_FO_GAIN_RATE_2, 0x0c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_SO_GAIN_RATE_2, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_FO_GAIN_RATE_3, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_PI_CONTROLS, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_SO_ACC_DEFAULT_VAL_RATE3, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_IVCM_CAL_CTRL2, 0x80),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_IVCM_POSTCAL_OFFSET, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_BKUP_CTRL1, 0x15),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_3, 0x45),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_VGA_CAL_MAN_VAL, 0x0c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_VGA_CAL_CNTRL1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_GM_CAL, 0x0d),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_EQU_ADAPTOR_CNTRL4, 0x0b),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_SIGDET_ENABLES, 0x1c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_PHPRE_CTRL, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_Q_PI_INTRINSIC_BIAS_RATE32, 0x39),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B0, 0xd4),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B1, 0x23),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B2, 0x58),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B3, 0x9a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B4, 0x38),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B5, 0xb6),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B6, 0xee),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B0, 0x1c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B1, 0xe4),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B2, 0x60),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B3, 0xdf),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B4, 0x69),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B5, 0x76),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B6, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_TX_ADPT_CTRL, 0x10),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x8_pcie_rx_tbl[] = {
+	QMP_PHY_INIT_CFG_LANE(QSERDES_V6_20_RX_DFE_CTLE_POST_CAL_OFFSET, 0x3a, BIT(0)),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x8_pcie_pcs_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V6_30_PCS_LOCK_DETECT_CONFIG2, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V6_30_PCS_G3S2_PRE_GAIN, 0x2e),
+	QMP_PHY_INIT_CFG(QPHY_V6_30_PCS_RX_SIGDET_LVL, 0x99),
+	QMP_PHY_INIT_CFG(QPHY_V6_30_PCS_ALIGN_DETECT_CONFIG7, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V6_30_PCS_EQ_CONFIG4, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V6_30_PCS_EQ_CONFIG5, 0x22),
+	QMP_PHY_INIT_CFG(QPHY_V6_30_PCS_TX_RX_CONFIG, 0x04),
+	QMP_PHY_INIT_CFG(QPHY_V6_30_PCS_TX_RX_CONFIG2, 0x02),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x8_pcie_pcs_misc_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_30_PCS_ENDPOINT_REFCLK_DRIVE, 0xc1),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_30_PCS_OSC_DTCT_ACTIONS, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_30_PCS_EQ_CONFIG1, 0x16),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_30_PCS_G4_EQ_CONFIG5, 0x02),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_30_PCS_G4_PRE_GAIN, 0x2e),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_30_PCS_RX_MARGINING_CONFIG1, 0x03),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_30_PCS_RX_MARGINING_CONFIG3, 0x28),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_30_PCS_RX_MARGINING_CONFIG5, 0x18),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_30_PCS_G3_FOM_EQ_CONFIG5, 0x7a),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_30_PCS_G4_FOM_EQ_CONFIG5, 0x8a),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_30_PCS_G3_RXEQEVAL_TIME, 0x27),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_30_PCS_G4_RXEQEVAL_TIME, 0x27),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_30_PCS_TX_RX_CONFIG, 0xc0),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_30_PCS_POWER_STATE_CONFIG2, 0x1d),
+};
+
 static const struct qmp_phy_init_tbl sm8250_qmp_pcie_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V4_COM_SYSCLK_EN_SEL, 0x08),
 	QMP_PHY_INIT_CFG(QSERDES_V4_COM_CLK_SELECT, 0x34),
@@ -2582,6 +2732,8 @@ struct qmp_pcie_offsets {
 	u16 rx;
 	u16 tx2;
 	u16 rx2;
+	u16 txz;
+	u16 rxz;
 	u16 ln_shrd;
 };
 
@@ -2592,6 +2744,10 @@ struct qmp_phy_cfg_tbls {
 	int tx_num;
 	const struct qmp_phy_init_tbl *rx;
 	int rx_num;
+	const struct qmp_phy_init_tbl *txz;
+	int txz_num;
+	const struct qmp_phy_init_tbl *rxz;
+	int rxz_num;
 	const struct qmp_phy_init_tbl *pcs;
 	int pcs_num;
 	const struct qmp_phy_init_tbl *pcs_misc;
@@ -2659,6 +2815,8 @@ struct qmp_pcie {
 	void __iomem *rx;
 	void __iomem *tx2;
 	void __iomem *rx2;
+	void __iomem *txz;
+	void __iomem *rxz;
 	void __iomem *ln_shrd;
 
 	void __iomem *port_b;
@@ -2826,6 +2984,17 @@ static const struct qmp_pcie_offsets qmp_pcie_offsets_v6_20 = {
 	.ln_shrd	= 0x0e00,
 };
 
+static const struct qmp_pcie_offsets qmp_pcie_offsets_v6_30 = {
+	.serdes		= 0x8800,
+	.pcs		= 0x9000,
+	.pcs_misc	= 0x9800,
+	.tx		= 0x0000,
+	.rx		= 0x0200,
+	.txz		= 0xe000,
+	.rxz		= 0xe200,
+	.ln_shrd	= 0x8000,
+};
+
 static const struct qmp_phy_cfg ipq8074_pciephy_cfg = {
 	.lanes			= 1,
 
@@ -3704,6 +3873,38 @@ static const struct qmp_phy_cfg x1e80100_qmp_gen4x4_pciephy_cfg = {
 	.has_nocsr_reset	= true,
 };
 
+static const struct qmp_phy_cfg x1e80100_qmp_gen4x8_pciephy_cfg = {
+	.lanes = 8,
+
+	.offsets		= &qmp_pcie_offsets_v6_30,
+	.tbls = {
+		.serdes			= x1e80100_qmp_gen4x8_pcie_serdes_tbl,
+		.serdes_num		= ARRAY_SIZE(x1e80100_qmp_gen4x8_pcie_serdes_tbl),
+		.rx			= x1e80100_qmp_gen4x8_pcie_rx_tbl,
+		.rx_num			= ARRAY_SIZE(x1e80100_qmp_gen4x8_pcie_rx_tbl),
+		.txz			= x1e80100_qmp_gen4x8_pcie_txz_tbl,
+		.txz_num		= ARRAY_SIZE(x1e80100_qmp_gen4x8_pcie_txz_tbl),
+		.rxz			= x1e80100_qmp_gen4x8_pcie_rxz_tbl,
+		.rxz_num		= ARRAY_SIZE(x1e80100_qmp_gen4x8_pcie_rxz_tbl),
+		.pcs			= x1e80100_qmp_gen4x8_pcie_pcs_tbl,
+		.pcs_num		= ARRAY_SIZE(x1e80100_qmp_gen4x8_pcie_pcs_tbl),
+		.pcs_misc		= x1e80100_qmp_gen4x8_pcie_pcs_misc_tbl,
+		.pcs_misc_num		= ARRAY_SIZE(x1e80100_qmp_gen4x8_pcie_pcs_misc_tbl),
+		.ln_shrd		= x1e80100_qmp_gen4x8_pcie_ln_shrd_tbl,
+		.ln_shrd_num		= ARRAY_SIZE(x1e80100_qmp_gen4x8_pcie_ln_shrd_tbl),
+	},
+
+	.reset_list		= sdm845_pciephy_reset_l,
+	.num_resets		= ARRAY_SIZE(sdm845_pciephy_reset_l),
+	.vreg_list		= sm8550_qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(sm8550_qmp_phy_vreg_l),
+	.regs			= pciephy_v6_regs_layout,
+
+	.pwrdn_ctrl		= SW_PWRDN | REFCLK_DRV_DSBL,
+	.phy_status		= PHYSTATUS_4_20,
+	.has_nocsr_reset	= true,
+};
+
 static void qmp_pcie_init_port_b(struct qmp_pcie *qmp, const struct qmp_phy_cfg_tbls *tbls)
 {
 	const struct qmp_phy_cfg *cfg = qmp->cfg;
@@ -3751,6 +3952,13 @@ static void qmp_pcie_init_registers(struct qmp_pcie *qmp, const struct qmp_phy_c
 
 	qmp_configure(qmp->dev, serdes, tbls->serdes, tbls->serdes_num);
 
+	/*
+	 * Tx/Rx registers that require different settings than
+	 * txz/rxz must be programmed after txz/rxz.
+	 */
+	qmp_configure(qmp->dev, qmp->txz, tbls->txz, tbls->txz_num);
+	qmp_configure(qmp->dev, qmp->rxz, tbls->rxz, tbls->rxz_num);
+
 	qmp_configure_lane(qmp->dev, tx, tbls->tx, tbls->tx_num, 1);
 	qmp_configure_lane(qmp->dev, rx, tbls->rx, tbls->rx_num, 1);
 
@@ -4293,6 +4501,9 @@ static int qmp_pcie_parse_dt(struct qmp_pcie *qmp)
 			return PTR_ERR(qmp->port_b);
 	}
 
+	qmp->txz = base + offs->txz;
+	qmp->rxz = base + offs->rxz;
+
 	if (cfg->tbls.ln_shrd)
 		qmp->ln_shrd = base + offs->ln_shrd;
 
@@ -4478,6 +4689,9 @@ static const struct of_device_id qmp_pcie_of_match_table[] = {
 	}, {
 		.compatible = "qcom,x1e80100-qmp-gen4x4-pcie-phy",
 		.data = &x1e80100_qmp_gen4x4_pciephy_cfg,
+	}, {
+		.compatible = "qcom,x1e80100-qmp-gen4x8-pcie-phy",
+		.data = &x1e80100_qmp_gen4x8_pciephy_cfg,
 	},
 	{ },
 };
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6_30.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6_30.h
new file mode 100644
index 0000000000000..5a58ff197e6e0
--- /dev/null
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6_30.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Qualcomm Innovation Center. All rights reserved.
+ */
+
+#ifndef QCOM_PHY_QMP_PCS_PCIE_V6_30_H_
+#define QCOM_PHY_QMP_PCS_PCIE_V6_30_H_
+
+/* Only for QMP V6_30 PHY - PCIE have different offsets than V6 */
+#define QPHY_PCIE_V6_30_PCS_POWER_STATE_CONFIG2		0x014
+#define QPHY_PCIE_V6_30_PCS_TX_RX_CONFIG		0x020
+#define QPHY_PCIE_V6_30_PCS_ENDPOINT_REFCLK_DRIVE	0x024
+#define QPHY_PCIE_V6_30_PCS_OSC_DTCT_ACTIONS		0x098
+#define QPHY_PCIE_V6_30_PCS_EQ_CONFIG1			0x0a8
+#define QPHY_PCIE_V6_30_PCS_G3_RXEQEVAL_TIME		0x0f8
+#define QPHY_PCIE_V6_30_PCS_G4_RXEQEVAL_TIME		0x0fc
+#define QPHY_PCIE_V6_30_PCS_G4_EQ_CONFIG5		0x110
+#define QPHY_PCIE_V6_30_PCS_G4_PRE_GAIN			0x164
+#define QPHY_PCIE_V6_30_PCS_RX_MARGINING_CONFIG1	0x184
+#define QPHY_PCIE_V6_30_PCS_RX_MARGINING_CONFIG3	0x18c
+#define QPHY_PCIE_V6_30_PCS_RX_MARGINING_CONFIG5	0x194
+#define QPHY_PCIE_V6_30_PCS_G3_FOM_EQ_CONFIG5		0x1b4
+#define QPHY_PCIE_V6_30_PCS_G4_FOM_EQ_CONFIG5		0x1c8
+
+#endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6_30.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6_30.h
new file mode 100644
index 0000000000000..369120d88bc27
--- /dev/null
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6_30.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Qualcomm Innovation Center. All rights reserved.
+ */
+
+#ifndef QCOM_PHY_QMP_PCS_V6_30_H_
+#define QCOM_PHY_QMP_PCS_V6_30_H_
+
+/* Only for QMP V6_30 PHY - PCIe PCS registers */
+#define QPHY_V6_30_PCS_LOCK_DETECT_CONFIG2		0x0cc
+#define QPHY_V6_30_PCS_G3S2_PRE_GAIN			0x17c
+#define QPHY_V6_30_PCS_RX_SIGDET_LVL			0x194
+#define QPHY_V6_30_PCS_ALIGN_DETECT_CONFIG7		0x1dc
+#define QPHY_V6_30_PCS_TX_RX_CONFIG			0x1e0
+#define QPHY_V6_30_PCS_TX_RX_CONFIG2			0x1e4
+#define QPHY_V6_30_PCS_EQ_CONFIG4			0x1fc
+#define QPHY_V6_30_PCS_EQ_CONFIG5			0x200
+
+#endif

From e592a65584fce0852825156086cfa1d5ef4dc2b0 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Thu, 17 Oct 2024 12:06:57 +0800
Subject: [PATCH 0431/1530] phy: stm32: Remove unneeded semicolon

This patch removes an unneeded semicolon after a switch statement.

./drivers/phy/st/phy-stm32-combophy.c:226:2-3: Unneeded semicolon

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=11403
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Link: https://lore.kernel.org/r/20241017040657.33992-1-yang.lee@linux.alibaba.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/st/phy-stm32-combophy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/phy/st/phy-stm32-combophy.c b/drivers/phy/st/phy-stm32-combophy.c
index e1e7083ccb5f4..765bb34fe3589 100644
--- a/drivers/phy/st/phy-stm32-combophy.c
+++ b/drivers/phy/st/phy-stm32-combophy.c
@@ -223,7 +223,7 @@ static int stm32_combophy_pll_init(struct stm32_combophy *combophy)
 	default:
 		dev_err(combophy->dev, "Invalid rate 0x%x\n", clk_rate);
 		return -EINVAL;
-	};
+	}
 
 	cr1_mask |= SYSCFG_COMBOPHY_CR1_REFCLKDIV2;
 	cr1_val |= REFCLDIV_0;

From 86e2ed4e9a9680013ec9ab7c0428c9b8c5108efe Mon Sep 17 00:00:00 2001
From: Frank Wang <frank.wang@rock-chips.com>
Date: Wed, 16 Oct 2024 15:37:10 +0800
Subject: [PATCH 0432/1530] phy: rockchip: inno-usb2: convert clock management
 to bulk

Since some Rockchip SoCs (e.g RK3576) have more than one clock,
this converts the clock management from single to bulk method to
make the driver more flexible.

Signed-off-by: Frank Wang <frank.wang@rock-chips.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/r/20241016073713.14133-1-frawang.cn@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/rockchip/phy-rockchip-inno-usb2.c | 45 +++++++++++++++----
 1 file changed, 37 insertions(+), 8 deletions(-)

diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
index 6e5214862b8a3..f71266c27091e 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
@@ -229,9 +229,10 @@ struct rockchip_usb2phy_port {
  * @dev: pointer to device.
  * @grf: General Register Files regmap.
  * @usbgrf: USB General Register Files regmap.
- * @clk: clock struct of phy input clk.
+ * @clks: array of phy input clocks.
  * @clk480m: clock struct of phy output clk.
  * @clk480m_hw: clock struct of phy output clk management.
+ * @num_clks: number of phy input clocks.
  * @phy_reset: phy reset control.
  * @chg_state: states involved in USB charger detection.
  * @chg_type: USB charger types.
@@ -246,9 +247,10 @@ struct rockchip_usb2phy {
 	struct device	*dev;
 	struct regmap	*grf;
 	struct regmap	*usbgrf;
-	struct clk	*clk;
+	struct clk_bulk_data	*clks;
 	struct clk	*clk480m;
 	struct clk_hw	clk480m_hw;
+	int			num_clks;
 	struct reset_control	*phy_reset;
 	enum usb_chg_state	chg_state;
 	enum power_supply_type	chg_type;
@@ -310,6 +312,13 @@ static int rockchip_usb2phy_reset(struct rockchip_usb2phy *rphy)
 	return 0;
 }
 
+static void rockchip_usb2phy_clk_bulk_disable(void *data)
+{
+	struct rockchip_usb2phy *rphy = data;
+
+	clk_bulk_disable_unprepare(rphy->num_clks, rphy->clks);
+}
+
 static int rockchip_usb2phy_clk480m_prepare(struct clk_hw *hw)
 {
 	struct rockchip_usb2phy *rphy =
@@ -376,7 +385,9 @@ rockchip_usb2phy_clk480m_register(struct rockchip_usb2phy *rphy)
 {
 	struct device_node *node = rphy->dev->of_node;
 	struct clk_init_data init;
+	struct clk *refclk = NULL;
 	const char *clk_name;
+	int i;
 	int ret = 0;
 
 	init.flags = 0;
@@ -386,8 +397,15 @@ rockchip_usb2phy_clk480m_register(struct rockchip_usb2phy *rphy)
 	/* optional override of the clockname */
 	of_property_read_string(node, "clock-output-names", &init.name);
 
-	if (rphy->clk) {
-		clk_name = __clk_get_name(rphy->clk);
+	for (i = 0; i < rphy->num_clks; i++) {
+		if (!strncmp(rphy->clks[i].id, "phyclk", 6)) {
+			refclk = rphy->clks[i].clk;
+			break;
+		}
+	}
+
+	if (!IS_ERR(refclk)) {
+		clk_name = __clk_get_name(refclk);
 		init.parent_names = &clk_name;
 		init.num_parents = 1;
 	} else {
@@ -1399,15 +1417,26 @@ static int rockchip_usb2phy_probe(struct platform_device *pdev)
 	if (IS_ERR(rphy->phy_reset))
 		return PTR_ERR(rphy->phy_reset);
 
-	rphy->clk = devm_clk_get_optional_enabled(dev, "phyclk");
-	if (IS_ERR(rphy->clk))
-		return dev_err_probe(&pdev->dev, PTR_ERR(rphy->clk),
-				     "failed to get phyclk\n");
+	ret = devm_clk_bulk_get_all(dev, &rphy->clks);
+	if (ret == -EPROBE_DEFER)
+		return dev_err_probe(&pdev->dev, -EPROBE_DEFER,
+				     "failed to get phy clock\n");
+
+	/* Clocks are optional */
+	rphy->num_clks = ret < 0 ? 0 : ret;
 
 	ret = rockchip_usb2phy_clk480m_register(rphy);
 	if (ret)
 		return dev_err_probe(dev, ret, "failed to register 480m output clock\n");
 
+	ret = clk_bulk_prepare_enable(rphy->num_clks, rphy->clks);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to enable phy clock\n");
+
+	ret = devm_add_action_or_reset(dev, rockchip_usb2phy_clk_bulk_disable, rphy);
+	if (ret)
+		return ret;
+
 	if (rphy->phy_cfg->phy_tuning) {
 		ret = rphy->phy_cfg->phy_tuning(rphy);
 		if (ret)

From 0217f4aef0b07a57086baeed9c0ac05160435a45 Mon Sep 17 00:00:00 2001
From: Frank Wang <frank.wang@rock-chips.com>
Date: Wed, 16 Oct 2024 15:37:12 +0800
Subject: [PATCH 0433/1530] dt-bindings: phy: rockchip,inno-usb2phy: add rk3576

Add compatible for the USB2 phy in the Rockchip RK3576 SoC.

This change also refactor the clocks list as there are new clocks
adding used for the USB MMU in RK3576 SoC.

Signed-off-by: Frank Wang <frank.wang@rock-chips.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/r/20241016073713.14133-3-frawang.cn@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../bindings/phy/rockchip,inno-usb2phy.yaml   | 45 ++++++++++++++++++-
 1 file changed, 43 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/phy/rockchip,inno-usb2phy.yaml b/Documentation/devicetree/bindings/phy/rockchip,inno-usb2phy.yaml
index 5254413137c64..6a7ef556414ce 100644
--- a/Documentation/devicetree/bindings/phy/rockchip,inno-usb2phy.yaml
+++ b/Documentation/devicetree/bindings/phy/rockchip,inno-usb2phy.yaml
@@ -20,6 +20,7 @@ properties:
       - rockchip,rk3366-usb2phy
       - rockchip,rk3399-usb2phy
       - rockchip,rk3568-usb2phy
+      - rockchip,rk3576-usb2phy
       - rockchip,rk3588-usb2phy
       - rockchip,rv1108-usb2phy
 
@@ -34,10 +35,15 @@ properties:
     const: 0
 
   clocks:
-    maxItems: 1
+    minItems: 1
+    maxItems: 3
 
   clock-names:
-    const: phyclk
+    minItems: 1
+    items:
+      - const: phyclk
+      - const: aclk
+      - const: aclk_slv
 
   assigned-clocks:
     description:
@@ -172,6 +178,41 @@ allOf:
             - interrupts
             - interrupt-names
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - rockchip,px30-usb2phy
+              - rockchip,rk3128-usb2phy
+              - rockchip,rk3228-usb2phy
+              - rockchip,rk3308-usb2phy
+              - rockchip,rk3328-usb2phy
+              - rockchip,rk3366-usb2phy
+              - rockchip,rk3399-usb2phy
+              - rockchip,rk3568-usb2phy
+              - rockchip,rk3588-usb2phy
+              - rockchip,rv1108-usb2phy
+    then:
+      properties:
+        clocks:
+          maxItems: 1
+        clock-names:
+          maxItems: 1
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - rockchip,rk3576-usb2phy
+    then:
+      properties:
+        clocks:
+          minItems: 3
+        clock-names:
+          minItems: 3
+
 additionalProperties: false
 
 examples:

From 3d7de6e870ece5a32153382df9df6fb87613335e Mon Sep 17 00:00:00 2001
From: William Wu <william.wu@rock-chips.com>
Date: Wed, 16 Oct 2024 15:37:13 +0800
Subject: [PATCH 0434/1530] phy: rockchip: inno-usb2: Add usb2 phys support for
 rk3576

The RK3576 SoC has two independent USB2.0 PHYs, and each PHY has
one port. This adds device specific data for it.

Signed-off-by: William Wu <william.wu@rock-chips.com>
Signed-off-by: Frank Wang <frank.wang@rock-chips.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/r/20241016073713.14133-4-frawang.cn@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/rockchip/phy-rockchip-inno-usb2.c | 103 ++++++++++++++++++
 1 file changed, 103 insertions(+)

diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
index f71266c27091e..96f3d868a526f 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
@@ -1510,6 +1510,30 @@ static int rk3128_usb2phy_tuning(struct rockchip_usb2phy *rphy)
 				BIT(2) << BIT_WRITEABLE_SHIFT | 0);
 }
 
+static int rk3576_usb2phy_tuning(struct rockchip_usb2phy *rphy)
+{
+	int ret;
+	u32 reg = rphy->phy_cfg->reg;
+
+	/* Deassert SIDDQ to power on analog block */
+	ret = regmap_write(rphy->grf, reg + 0x0010, GENMASK(29, 29) | 0x0000);
+	if (ret)
+		return ret;
+
+	/* Do reset after exit IDDQ mode */
+	ret = rockchip_usb2phy_reset(rphy);
+	if (ret)
+		return ret;
+
+	/* HS DC Voltage Level Adjustment 4'b1001 : +5.89% */
+	ret |= regmap_write(rphy->grf, reg + 0x000c, GENMASK(27, 24) | 0x0900);
+
+	/* HS Transmitter Pre-Emphasis Current Control 2'b10 : 2x */
+	ret |= regmap_write(rphy->grf, reg + 0x0010, GENMASK(20, 19) | 0x0010);
+
+	return ret;
+}
+
 static int rk3588_usb2phy_tuning(struct rockchip_usb2phy *rphy)
 {
 	int ret;
@@ -1938,6 +1962,84 @@ static const struct rockchip_usb2phy_cfg rk3568_phy_cfgs[] = {
 	{ /* sentinel */ }
 };
 
+static const struct rockchip_usb2phy_cfg rk3576_phy_cfgs[] = {
+	{
+		.reg = 0x0,
+		.num_ports	= 1,
+		.phy_tuning	= rk3576_usb2phy_tuning,
+		.clkout_ctl	= { 0x0008, 0, 0, 1, 0 },
+		.port_cfgs	= {
+			[USB2PHY_PORT_OTG] = {
+				.phy_sus	= { 0x0000, 8, 0, 0, 0x1d1 },
+				.bvalid_det_en	= { 0x00c0, 1, 1, 0, 1 },
+				.bvalid_det_st	= { 0x00c4, 1, 1, 0, 1 },
+				.bvalid_det_clr = { 0x00c8, 1, 1, 0, 1 },
+				.ls_det_en	= { 0x00c0, 0, 0, 0, 1 },
+				.ls_det_st	= { 0x00c4, 0, 0, 0, 1 },
+				.ls_det_clr	= { 0x00c8, 0, 0, 0, 1 },
+				.disfall_en	= { 0x00c0, 6, 6, 0, 1 },
+				.disfall_st	= { 0x00c4, 6, 6, 0, 1 },
+				.disfall_clr	= { 0x00c8, 6, 6, 0, 1 },
+				.disrise_en	= { 0x00c0, 5, 5, 0, 1 },
+				.disrise_st	= { 0x00c4, 5, 5, 0, 1 },
+				.disrise_clr	= { 0x00c8, 5, 5, 0, 1 },
+				.utmi_avalid	= { 0x0080, 1, 1, 0, 1 },
+				.utmi_bvalid	= { 0x0080, 0, 0, 0, 1 },
+				.utmi_ls	= { 0x0080, 5, 4, 0, 1 },
+			}
+		},
+		.chg_det = {
+			.cp_det		= { 0x0080, 8, 8, 0, 1 },
+			.dcp_det	= { 0x0080, 8, 8, 0, 1 },
+			.dp_det		= { 0x0080, 9, 9, 1, 0 },
+			.idm_sink_en	= { 0x0010, 5, 5, 1, 0 },
+			.idp_sink_en	= { 0x0010, 5, 5, 0, 1 },
+			.idp_src_en	= { 0x0010, 14, 14, 0, 1 },
+			.rdm_pdwn_en	= { 0x0010, 14, 14, 0, 1 },
+			.vdm_src_en	= { 0x0010, 7, 6, 0, 3 },
+			.vdp_src_en	= { 0x0010, 7, 6, 0, 3 },
+		},
+	},
+	{
+		.reg = 0x2000,
+		.num_ports	= 1,
+		.phy_tuning	= rk3576_usb2phy_tuning,
+		.clkout_ctl	= { 0x2008, 0, 0, 1, 0 },
+		.port_cfgs	= {
+			[USB2PHY_PORT_OTG] = {
+				.phy_sus	= { 0x2000, 8, 0, 0, 0x1d1 },
+				.bvalid_det_en	= { 0x20c0, 1, 1, 0, 1 },
+				.bvalid_det_st	= { 0x20c4, 1, 1, 0, 1 },
+				.bvalid_det_clr = { 0x20c8, 1, 1, 0, 1 },
+				.ls_det_en	= { 0x20c0, 0, 0, 0, 1 },
+				.ls_det_st	= { 0x20c4, 0, 0, 0, 1 },
+				.ls_det_clr	= { 0x20c8, 0, 0, 0, 1 },
+				.disfall_en	= { 0x20c0, 6, 6, 0, 1 },
+				.disfall_st	= { 0x20c4, 6, 6, 0, 1 },
+				.disfall_clr	= { 0x20c8, 6, 6, 0, 1 },
+				.disrise_en	= { 0x20c0, 5, 5, 0, 1 },
+				.disrise_st	= { 0x20c4, 5, 5, 0, 1 },
+				.disrise_clr	= { 0x20c8, 5, 5, 0, 1 },
+				.utmi_avalid	= { 0x2080, 1, 1, 0, 1 },
+				.utmi_bvalid	= { 0x2080, 0, 0, 0, 1 },
+				.utmi_ls	= { 0x2080, 5, 4, 0, 1 },
+			}
+		},
+		.chg_det = {
+			.cp_det		= { 0x2080, 8, 8, 0, 1 },
+			.dcp_det	= { 0x2080, 8, 8, 0, 1 },
+			.dp_det		= { 0x2080, 9, 9, 1, 0 },
+			.idm_sink_en	= { 0x2010, 5, 5, 1, 0 },
+			.idp_sink_en	= { 0x2010, 5, 5, 0, 1 },
+			.idp_src_en	= { 0x2010, 14, 14, 0, 1 },
+			.rdm_pdwn_en	= { 0x2010, 14, 14, 0, 1 },
+			.vdm_src_en	= { 0x2010, 7, 6, 0, 3 },
+			.vdp_src_en	= { 0x2010, 7, 6, 0, 3 },
+		},
+	},
+	{ /* sentinel */ }
+};
+
 static const struct rockchip_usb2phy_cfg rk3588_phy_cfgs[] = {
 	{
 		.reg = 0x0000,
@@ -2109,6 +2211,7 @@ static const struct of_device_id rockchip_usb2phy_dt_match[] = {
 	{ .compatible = "rockchip,rk3366-usb2phy", .data = &rk3366_phy_cfgs },
 	{ .compatible = "rockchip,rk3399-usb2phy", .data = &rk3399_phy_cfgs },
 	{ .compatible = "rockchip,rk3568-usb2phy", .data = &rk3568_phy_cfgs },
+	{ .compatible = "rockchip,rk3576-usb2phy", .data = &rk3576_phy_cfgs },
 	{ .compatible = "rockchip,rk3588-usb2phy", .data = &rk3588_phy_cfgs },
 	{ .compatible = "rockchip,rv1108-usb2phy", .data = &rv1108_phy_cfgs },
 	{}

From 4a5a9e2577d61a4ee3e9788e0c2b0c1cbc5ba7b3 Mon Sep 17 00:00:00 2001
From: Adam Ford <aford173@gmail.com>
Date: Sat, 14 Sep 2024 06:27:45 -0500
Subject: [PATCH 0435/1530] phy: freescale: fsl-samsung-hdmi: Replace register
 defines with macro

There are 47 registers defined as PHY_REG_xx were xx goes from 00 to
47.  Simplify this by replacing them all with a macro which is passed
the register number to return the proper register offset.

Signed-off-by: Adam Ford <aford173@gmail.com>
Reviewed-by: Marco Felsch <m.felsch@pengutronix.de>
Reviewed-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Tested-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Reviewed-by: Dominique Martinet <dominique.martinet@atmark-techno.com>
Tested-by: Dominique Martinet <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/r/20240914112816.520224-2-aford173@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/freescale/phy-fsl-samsung-hdmi.c | 133 ++++++-------------
 1 file changed, 43 insertions(+), 90 deletions(-)

diff --git a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
index 9048cdc760c21..acea7008aefc5 100644
--- a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
+++ b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
@@ -14,76 +14,29 @@
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 
-#define PHY_REG_00		0x00
-#define PHY_REG_01		0x04
-#define PHY_REG_02		0x08
-#define PHY_REG_08		0x20
-#define PHY_REG_09		0x24
-#define PHY_REG_10		0x28
-#define PHY_REG_11		0x2c
-
-#define PHY_REG_12		0x30
-#define  REG12_CK_DIV_MASK	GENMASK(5, 4)
-
-#define PHY_REG_13		0x34
-#define  REG13_TG_CODE_LOW_MASK	GENMASK(7, 0)
-
-#define PHY_REG_14		0x38
-#define  REG14_TOL_MASK		GENMASK(7, 4)
-#define  REG14_RP_CODE_MASK	GENMASK(3, 1)
-#define  REG14_TG_CODE_HIGH_MASK	GENMASK(0, 0)
-
-#define PHY_REG_15		0x3c
-#define PHY_REG_16		0x40
-#define PHY_REG_17		0x44
-#define PHY_REG_18		0x48
-#define PHY_REG_19		0x4c
-#define PHY_REG_20		0x50
-
-#define PHY_REG_21		0x54
-#define  REG21_SEL_TX_CK_INV	BIT(7)
-#define  REG21_PMS_S_MASK	GENMASK(3, 0)
-
-#define PHY_REG_22		0x58
-#define PHY_REG_23		0x5c
-#define PHY_REG_24		0x60
-#define PHY_REG_25		0x64
-#define PHY_REG_26		0x68
-#define PHY_REG_27		0x6c
-#define PHY_REG_28		0x70
-#define PHY_REG_29		0x74
-#define PHY_REG_30		0x78
-#define PHY_REG_31		0x7c
-#define PHY_REG_32		0x80
+#define PHY_REG(reg)		(reg * 4)
 
+#define REG12_CK_DIV_MASK	GENMASK(5, 4)
+
+#define REG13_TG_CODE_LOW_MASK	GENMASK(7, 0)
+
+#define REG14_TOL_MASK		GENMASK(7, 4)
+#define REG14_RP_CODE_MASK	GENMASK(3, 1)
+#define REG14_TG_CODE_HIGH_MASK	GENMASK(0, 0)
+
+#define REG21_SEL_TX_CK_INV	BIT(7)
+#define REG21_PMS_S_MASK	GENMASK(3, 0)
 /*
  * REG33 does not match the ref manual. According to Sandor Yu from NXP,
  * "There is a doc issue on the i.MX8MP latest RM"
  * REG33 is being used per guidance from Sandor
  */
+#define REG33_MODE_SET_DONE	BIT(7)
+#define REG33_FIX_DA		BIT(1)
 
-#define PHY_REG_33		0x84
-#define  REG33_MODE_SET_DONE	BIT(7)
-#define  REG33_FIX_DA		BIT(1)
-
-#define PHY_REG_34		0x88
-#define  REG34_PHY_READY	BIT(7)
-#define  REG34_PLL_LOCK		BIT(6)
-#define  REG34_PHY_CLK_READY	BIT(5)
-
-#define PHY_REG_35		0x8c
-#define PHY_REG_36		0x90
-#define PHY_REG_37		0x94
-#define PHY_REG_38		0x98
-#define PHY_REG_39		0x9c
-#define PHY_REG_40		0xa0
-#define PHY_REG_41		0xa4
-#define PHY_REG_42		0xa8
-#define PHY_REG_43		0xac
-#define PHY_REG_44		0xb0
-#define PHY_REG_45		0xb4
-#define PHY_REG_46		0xb8
-#define PHY_REG_47		0xbc
+#define REG34_PHY_READY	BIT(7)
+#define REG34_PLL_LOCK		BIT(6)
+#define REG34_PHY_CLK_READY	BIT(5)
 
 #define PHY_PLL_DIV_REGS_NUM 6
 
@@ -369,29 +322,29 @@ struct reg_settings {
 };
 
 static const struct reg_settings common_phy_cfg[] = {
-	{ PHY_REG_00, 0x00 }, { PHY_REG_01, 0xd1 },
-	{ PHY_REG_08, 0x4f }, { PHY_REG_09, 0x30 },
-	{ PHY_REG_10, 0x33 }, { PHY_REG_11, 0x65 },
+	{ PHY_REG(0), 0x00 }, { PHY_REG(1), 0xd1 },
+	{ PHY_REG(8), 0x4f }, { PHY_REG(9), 0x30 },
+	{ PHY_REG(10), 0x33 }, { PHY_REG(11), 0x65 },
 	/* REG12 pixclk specific */
 	/* REG13 pixclk specific */
 	/* REG14 pixclk specific */
-	{ PHY_REG_15, 0x80 }, { PHY_REG_16, 0x6c },
-	{ PHY_REG_17, 0xf2 }, { PHY_REG_18, 0x67 },
-	{ PHY_REG_19, 0x00 }, { PHY_REG_20, 0x10 },
+	{ PHY_REG(15), 0x80 }, { PHY_REG(16), 0x6c },
+	{ PHY_REG(17), 0xf2 }, { PHY_REG(18), 0x67 },
+	{ PHY_REG(19), 0x00 }, { PHY_REG(20), 0x10 },
 	/* REG21 pixclk specific */
-	{ PHY_REG_22, 0x30 }, { PHY_REG_23, 0x32 },
-	{ PHY_REG_24, 0x60 }, { PHY_REG_25, 0x8f },
-	{ PHY_REG_26, 0x00 }, { PHY_REG_27, 0x00 },
-	{ PHY_REG_28, 0x08 }, { PHY_REG_29, 0x00 },
-	{ PHY_REG_30, 0x00 }, { PHY_REG_31, 0x00 },
-	{ PHY_REG_32, 0x00 }, { PHY_REG_33, 0x80 },
-	{ PHY_REG_34, 0x00 }, { PHY_REG_35, 0x00 },
-	{ PHY_REG_36, 0x00 }, { PHY_REG_37, 0x00 },
-	{ PHY_REG_38, 0x00 }, { PHY_REG_39, 0x00 },
-	{ PHY_REG_40, 0x00 }, { PHY_REG_41, 0xe0 },
-	{ PHY_REG_42, 0x83 }, { PHY_REG_43, 0x0f },
-	{ PHY_REG_44, 0x3E }, { PHY_REG_45, 0xf8 },
-	{ PHY_REG_46, 0x00 }, { PHY_REG_47, 0x00 }
+	{ PHY_REG(22), 0x30 }, { PHY_REG(23), 0x32 },
+	{ PHY_REG(24), 0x60 }, { PHY_REG(25), 0x8f },
+	{ PHY_REG(26), 0x00 }, { PHY_REG(27), 0x00 },
+	{ PHY_REG(28), 0x08 }, { PHY_REG(29), 0x00 },
+	{ PHY_REG(30), 0x00 }, { PHY_REG(31), 0x00 },
+	{ PHY_REG(32), 0x00 }, { PHY_REG(33), 0x80 },
+	{ PHY_REG(34), 0x00 }, { PHY_REG(35), 0x00 },
+	{ PHY_REG(36), 0x00 }, { PHY_REG(37), 0x00 },
+	{ PHY_REG(38), 0x00 }, { PHY_REG(39), 0x00 },
+	{ PHY_REG(40), 0x00 }, { PHY_REG(41), 0xe0 },
+	{ PHY_REG(42), 0x83 }, { PHY_REG(43), 0x0f },
+	{ PHY_REG(44), 0x3E }, { PHY_REG(45), 0xf8 },
+	{ PHY_REG(46), 0x00 }, { PHY_REG(47), 0x00 }
 };
 
 struct fsl_samsung_hdmi_phy {
@@ -442,7 +395,7 @@ fsl_samsung_hdmi_phy_configure_pixclk(struct fsl_samsung_hdmi_phy *phy,
 	}
 
 	writeb(REG21_SEL_TX_CK_INV | FIELD_PREP(REG21_PMS_S_MASK, div),
-	       phy->regs + PHY_REG_21);
+	       phy->regs + PHY_REG(21));
 }
 
 static void
@@ -469,7 +422,7 @@ fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy,
 		break;
 	}
 
-	writeb(FIELD_PREP(REG12_CK_DIV_MASK, ilog2(div)), phy->regs + PHY_REG_12);
+	writeb(FIELD_PREP(REG12_CK_DIV_MASK, ilog2(div)), phy->regs + PHY_REG(12));
 
 	/*
 	 * Calculation for the frequency lock detector target code (fld_tg_code)
@@ -489,11 +442,11 @@ fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy,
 
 	/* FLD_TOL and FLD_RP_CODE taken from downstream driver */
 	writeb(FIELD_PREP(REG13_TG_CODE_LOW_MASK, fld_tg_code),
-	       phy->regs + PHY_REG_13);
+	       phy->regs + PHY_REG(13));
 	writeb(FIELD_PREP(REG14_TOL_MASK, 2) |
 	       FIELD_PREP(REG14_RP_CODE_MASK, 2) |
 	       FIELD_PREP(REG14_TG_CODE_HIGH_MASK, fld_tg_code >> 8),
-	       phy->regs + PHY_REG_14);
+	       phy->regs + PHY_REG(14));
 }
 
 static int fsl_samsung_hdmi_phy_configure(struct fsl_samsung_hdmi_phy *phy,
@@ -503,7 +456,7 @@ static int fsl_samsung_hdmi_phy_configure(struct fsl_samsung_hdmi_phy *phy,
 	u8 val;
 
 	/* HDMI PHY init */
-	writeb(REG33_FIX_DA, phy->regs + PHY_REG_33);
+	writeb(REG33_FIX_DA, phy->regs + PHY_REG(33));
 
 	/* common PHY registers */
 	for (i = 0; i < ARRAY_SIZE(common_phy_cfg); i++)
@@ -511,14 +464,14 @@ static int fsl_samsung_hdmi_phy_configure(struct fsl_samsung_hdmi_phy *phy,
 
 	/* set individual PLL registers PHY_REG2 ... PHY_REG7 */
 	for (i = 0; i < PHY_PLL_DIV_REGS_NUM; i++)
-		writeb(cfg->pll_div_regs[i], phy->regs + PHY_REG_02 + i * 4);
+		writeb(cfg->pll_div_regs[i], phy->regs + PHY_REG(2) + i * 4);
 
 	fsl_samsung_hdmi_phy_configure_pixclk(phy, cfg);
 	fsl_samsung_hdmi_phy_configure_pll_lock_det(phy, cfg);
 
-	writeb(REG33_FIX_DA | REG33_MODE_SET_DONE, phy->regs + PHY_REG_33);
+	writeb(REG33_FIX_DA | REG33_MODE_SET_DONE, phy->regs + PHY_REG(33));
 
-	ret = readb_poll_timeout(phy->regs + PHY_REG_34, val,
+	ret = readb_poll_timeout(phy->regs + PHY_REG(34), val,
 				 val & REG34_PLL_LOCK, 50, 20000);
 	if (ret)
 		dev_err(phy->dev, "PLL failed to lock\n");

From 375ee44adb3640099508c5c0c01d86f0bdb16e97 Mon Sep 17 00:00:00 2001
From: Adam Ford <aford173@gmail.com>
Date: Sat, 14 Sep 2024 06:27:46 -0500
Subject: [PATCH 0436/1530] phy: freescale: fsl-samsung-hdmi: Simplify
 REG21_PMS_S_MASK lookup

The value of 'S' is writen to two places, PHY_REG3[7:4] and
PHY_REG21[3:0].  There is a lookup table which contains
the value of PHY_REG3.  Rather than using a switch statement
based on the pixel clock to search for the value of 'S' again,
just shift the contents of PHY_REG3[7:4] >> 4 and place the value
in PHY_REG21[3:0].  Doing this can eliminate an entire function.

Signed-off-by: Adam Ford <aford173@gmail.com>
Reviewed-by: Marco Felsch <m.felsch@pengutronix.de>
Reviewed-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Tested-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Reviewed-by: Dominique Martinet <dominique.martinet@atmark-techno.com>
Tested-by: Dominique Martinet <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/r/20240914112816.520224-3-aford173@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/freescale/phy-fsl-samsung-hdmi.c | 39 ++------------------
 1 file changed, 4 insertions(+), 35 deletions(-)

diff --git a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
index acea7008aefc5..4f6874226f9ab 100644
--- a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
+++ b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
@@ -364,40 +364,6 @@ to_fsl_samsung_hdmi_phy(struct clk_hw *hw)
 	return container_of(hw, struct fsl_samsung_hdmi_phy, hw);
 }
 
-static void
-fsl_samsung_hdmi_phy_configure_pixclk(struct fsl_samsung_hdmi_phy *phy,
-				      const struct phy_config *cfg)
-{
-	u8 div = 0x1;
-
-	switch (cfg->pixclk) {
-	case  22250000 ...  33750000:
-		div = 0xf;
-		break;
-	case  35000000 ...  40000000:
-		div = 0xb;
-		break;
-	case  43200000 ...  47500000:
-		div = 0x9;
-		break;
-	case  50349650 ...  63500000:
-		div = 0x7;
-		break;
-	case  67500000 ...  90000000:
-		div = 0x5;
-		break;
-	case  94000000 ... 148500000:
-		div = 0x3;
-		break;
-	case 154000000 ... 297000000:
-		div = 0x1;
-		break;
-	}
-
-	writeb(REG21_SEL_TX_CK_INV | FIELD_PREP(REG21_PMS_S_MASK, div),
-	       phy->regs + PHY_REG(21));
-}
-
 static void
 fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy,
 					    const struct phy_config *cfg)
@@ -466,7 +432,10 @@ static int fsl_samsung_hdmi_phy_configure(struct fsl_samsung_hdmi_phy *phy,
 	for (i = 0; i < PHY_PLL_DIV_REGS_NUM; i++)
 		writeb(cfg->pll_div_regs[i], phy->regs + PHY_REG(2) + i * 4);
 
-	fsl_samsung_hdmi_phy_configure_pixclk(phy, cfg);
+	/* High nibble of pll_div_regs[1] contains S which also gets written to REG21 */
+	writeb(REG21_SEL_TX_CK_INV | FIELD_PREP(REG21_PMS_S_MASK,
+	       cfg->pll_div_regs[1] >> 4), phy->regs + PHY_REG(21));
+
 	fsl_samsung_hdmi_phy_configure_pll_lock_det(phy, cfg);
 
 	writeb(REG33_FIX_DA | REG33_MODE_SET_DONE, phy->regs + PHY_REG(33));

From 1951dbb41d1dff7c135eed4fa1a6330df6971549 Mon Sep 17 00:00:00 2001
From: Adam Ford <aford173@gmail.com>
Date: Sat, 14 Sep 2024 06:27:47 -0500
Subject: [PATCH 0437/1530] phy: freescale: fsl-samsung-hdmi: Support dynamic
 integer

There is currently a look-up table for a variety of resolutions.
Since the phy has the ability to dynamically calculate the values
necessary to use the intger divider which should allow more
resolutions without having to update the look-up-table.

If the lookup table cannot find an exact match, fall back to the
dynamic calculator of the integer divider.

Previously, the value of P was hard-coded to 1, this required an
update to the phy_pll_cfg table to add in the extra value into the
table, so if the value of P is calculated to be something else
by the PMS calculator, the calculated_phy_pll_cfg structure
can be used instead without having to keep track of which method
was used.

Signed-off-by: Adam Ford <aford173@gmail.com>
Reviewed-by: Dominique Martinet <dominique.martinet@atmark-techno.com>
Tested-by: Dominique Martinet <dominique.martinet@atmark-techno.com>
Reviewed-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Link: https://lore.kernel.org/r/20240914112816.520224-4-aford173@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/freescale/phy-fsl-samsung-hdmi.c | 377 +++++++++++++------
 1 file changed, 270 insertions(+), 107 deletions(-)

diff --git a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
index 4f6874226f9ab..029de69fbeaf4 100644
--- a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
+++ b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
@@ -16,6 +16,8 @@
 
 #define PHY_REG(reg)		(reg * 4)
 
+#define REG01_PMS_P_MASK	GENMASK(3, 0)
+#define REG03_PMS_S_MASK	GENMASK(7, 4)
 #define REG12_CK_DIV_MASK	GENMASK(5, 4)
 
 #define REG13_TG_CODE_LOW_MASK	GENMASK(7, 0)
@@ -38,281 +40,296 @@
 #define REG34_PLL_LOCK		BIT(6)
 #define REG34_PHY_CLK_READY	BIT(5)
 
-#define PHY_PLL_DIV_REGS_NUM 6
+#ifndef MHZ
+#define MHZ	(1000UL * 1000UL)
+#endif
+
+#define PHY_PLL_DIV_REGS_NUM 7
 
 struct phy_config {
 	u32	pixclk;
 	u8	pll_div_regs[PHY_PLL_DIV_REGS_NUM];
 };
 
+/*
+ * The calculated_phy_pll_cfg only handles integer divider for PMS,
+ * meaning the last four entries will be fixed, but the first three will
+ * be calculated by the PMS calculator.
+ */
+static struct phy_config calculated_phy_pll_cfg = {
+	.pixclk = 0,
+	.pll_div_regs = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0x00 },
+};
+
+/* The lookup table contains values for which the fractional divder is used */
 static const struct phy_config phy_pll_cfg[] = {
 	{
 		.pixclk = 22250000,
-		.pll_div_regs = { 0x4b, 0xf1, 0x89, 0x88, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x4b, 0xf1, 0x89, 0x88, 0x80, 0x40 },
 	}, {
 		.pixclk = 23750000,
-		.pll_div_regs = { 0x50, 0xf1, 0x86, 0x85, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x50, 0xf1, 0x86, 0x85, 0x80, 0x40 },
 	}, {
 		.pixclk = 24000000,
-		.pll_div_regs = { 0x50, 0xf0, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x50, 0xf0, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 24024000,
-		.pll_div_regs = { 0x50, 0xf1, 0x99, 0x02, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x50, 0xf1, 0x99, 0x02, 0x80, 0x40 },
 	}, {
 		.pixclk = 25175000,
-		.pll_div_regs = { 0x54, 0xfc, 0xcc, 0x91, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x54, 0xfc, 0xcc, 0x91, 0x80, 0x40 },
 	}, {
 		.pixclk = 25200000,
-		.pll_div_regs = { 0x54, 0xf0, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x54, 0xf0, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 26750000,
-		.pll_div_regs = { 0x5a, 0xf2, 0x89, 0x88, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x5a, 0xf2, 0x89, 0x88, 0x80, 0x40 },
 	}, {
 		.pixclk = 27000000,
-		.pll_div_regs = { 0x5a, 0xf0, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x5a, 0xf0, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 27027000,
-		.pll_div_regs = { 0x5a, 0xf2, 0xfd, 0x0c, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x5a, 0xf2, 0xfd, 0x0c, 0x80, 0x40 },
 	}, {
 		.pixclk = 29500000,
-		.pll_div_regs = { 0x62, 0xf4, 0x95, 0x08, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x62, 0xf4, 0x95, 0x08, 0x80, 0x40 },
 	}, {
 		.pixclk = 30750000,
-		.pll_div_regs = { 0x66, 0xf4, 0x82, 0x01, 0x88, 0x45 },
+		.pll_div_regs = { 0xd1, 0x66, 0xf4, 0x82, 0x01, 0x88, 0x45 },
 	}, {
 		.pixclk = 30888000,
-		.pll_div_regs = { 0x66, 0xf4, 0x99, 0x18, 0x88, 0x45 },
+		.pll_div_regs = { 0xd1, 0x66, 0xf4, 0x99, 0x18, 0x88, 0x45 },
 	}, {
 		.pixclk = 33750000,
-		.pll_div_regs = { 0x70, 0xf4, 0x82, 0x01, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x70, 0xf4, 0x82, 0x01, 0x80, 0x40 },
 	}, {
 		.pixclk = 35000000,
-		.pll_div_regs = { 0x58, 0xb8, 0x8b, 0x88, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x58, 0xb8, 0x8b, 0x88, 0x80, 0x40 },
 	}, {
 		.pixclk = 36000000,
-		.pll_div_regs = { 0x5a, 0xb0, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x5a, 0xb0, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 36036000,
-		.pll_div_regs = { 0x5a, 0xb2, 0xfd, 0x0c, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x5a, 0xb2, 0xfd, 0x0c, 0x80, 0x40 },
 	}, {
 		.pixclk = 40000000,
-		.pll_div_regs = { 0x64, 0xb0, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x64, 0xb0, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 43200000,
-		.pll_div_regs = { 0x5a, 0x90, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x5a, 0x90, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 43243200,
-		.pll_div_regs = { 0x5a, 0x92, 0xfd, 0x0c, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x5a, 0x92, 0xfd, 0x0c, 0x80, 0x40 },
 	}, {
 		.pixclk = 44500000,
-		.pll_div_regs = { 0x5c, 0x92, 0x98, 0x11, 0x84, 0x41 },
+		.pll_div_regs = { 0xd1, 0x5c, 0x92, 0x98, 0x11, 0x84, 0x41 },
 	}, {
 		.pixclk = 47000000,
-		.pll_div_regs = { 0x62, 0x94, 0x95, 0x82, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x62, 0x94, 0x95, 0x82, 0x80, 0x40 },
 	}, {
 		.pixclk = 47500000,
-		.pll_div_regs = { 0x63, 0x96, 0xa1, 0x82, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x63, 0x96, 0xa1, 0x82, 0x80, 0x40 },
 	}, {
 		.pixclk = 50349650,
-		.pll_div_regs = { 0x54, 0x7c, 0xc3, 0x8f, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x54, 0x7c, 0xc3, 0x8f, 0x80, 0x40 },
 	}, {
 		.pixclk = 50400000,
-		.pll_div_regs = { 0x54, 0x70, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x54, 0x70, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 53250000,
-		.pll_div_regs = { 0x58, 0x72, 0x84, 0x03, 0x82, 0x41 },
+		.pll_div_regs = { 0xd1, 0x58, 0x72, 0x84, 0x03, 0x82, 0x41 },
 	}, {
 		.pixclk = 53500000,
-		.pll_div_regs = { 0x5a, 0x72, 0x89, 0x88, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x5a, 0x72, 0x89, 0x88, 0x80, 0x40 },
 	}, {
 		.pixclk = 54000000,
-		.pll_div_regs = { 0x5a, 0x70, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x5a, 0x70, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 54054000,
-		.pll_div_regs = { 0x5a, 0x72, 0xfd, 0x0c, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x5a, 0x72, 0xfd, 0x0c, 0x80, 0x40 },
 	}, {
 		.pixclk = 59000000,
-		.pll_div_regs = { 0x62, 0x74, 0x95, 0x08, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x62, 0x74, 0x95, 0x08, 0x80, 0x40 },
 	}, {
 		.pixclk = 59340659,
-		.pll_div_regs = { 0x62, 0x74, 0xdb, 0x52, 0x88, 0x47 },
+		.pll_div_regs = { 0xd1, 0x62, 0x74, 0xdb, 0x52, 0x88, 0x47 },
 	}, {
 		.pixclk = 59400000,
-		.pll_div_regs = { 0x63, 0x70, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x63, 0x70, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 61500000,
-		.pll_div_regs = { 0x66, 0x74, 0x82, 0x01, 0x88, 0x45 },
+		.pll_div_regs = { 0xd1, 0x66, 0x74, 0x82, 0x01, 0x88, 0x45 },
 	}, {
 		.pixclk = 63500000,
-		.pll_div_regs = { 0x69, 0x74, 0x89, 0x08, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x69, 0x74, 0x89, 0x08, 0x80, 0x40 },
 	}, {
 		.pixclk = 67500000,
-		.pll_div_regs = { 0x54, 0x52, 0x87, 0x03, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x54, 0x52, 0x87, 0x03, 0x80, 0x40 },
 	}, {
 		.pixclk = 70000000,
-		.pll_div_regs = { 0x58, 0x58, 0x8b, 0x88, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x58, 0x58, 0x8b, 0x88, 0x80, 0x40 },
 	}, {
 		.pixclk = 72000000,
-		.pll_div_regs = { 0x5a, 0x50, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x5a, 0x50, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 72072000,
-		.pll_div_regs = { 0x5a, 0x52, 0xfd, 0x0c, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x5a, 0x52, 0xfd, 0x0c, 0x80, 0x40 },
 	}, {
 		.pixclk = 74176000,
-		.pll_div_regs = { 0x5d, 0x58, 0xdb, 0xA2, 0x88, 0x41 },
+		.pll_div_regs = { 0xd1, 0x5d, 0x58, 0xdb, 0xA2, 0x88, 0x41 },
 	}, {
 		.pixclk = 74250000,
-		.pll_div_regs = { 0x5c, 0x52, 0x90, 0x0d, 0x84, 0x41 },
+		.pll_div_regs = { 0xd1, 0x5c, 0x52, 0x90, 0x0d, 0x84, 0x41 },
 	}, {
 		.pixclk = 78500000,
-		.pll_div_regs = { 0x62, 0x54, 0x87, 0x01, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x62, 0x54, 0x87, 0x01, 0x80, 0x40 },
 	}, {
 		.pixclk = 80000000,
-		.pll_div_regs = { 0x64, 0x50, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x64, 0x50, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 82000000,
-		.pll_div_regs = { 0x66, 0x54, 0x82, 0x01, 0x88, 0x45 },
+		.pll_div_regs = { 0xd1, 0x66, 0x54, 0x82, 0x01, 0x88, 0x45 },
 	}, {
 		.pixclk = 82500000,
-		.pll_div_regs = { 0x67, 0x54, 0x88, 0x01, 0x90, 0x49 },
+		.pll_div_regs = { 0xd1, 0x67, 0x54, 0x88, 0x01, 0x90, 0x49 },
 	}, {
 		.pixclk = 89000000,
-		.pll_div_regs = { 0x70, 0x54, 0x84, 0x83, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x70, 0x54, 0x84, 0x83, 0x80, 0x40 },
 	}, {
 		.pixclk = 90000000,
-		.pll_div_regs = { 0x70, 0x54, 0x82, 0x01, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x70, 0x54, 0x82, 0x01, 0x80, 0x40 },
 	}, {
 		.pixclk = 94000000,
-		.pll_div_regs = { 0x4e, 0x32, 0xa7, 0x10, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x4e, 0x32, 0xa7, 0x10, 0x80, 0x40 },
 	}, {
 		.pixclk = 95000000,
-		.pll_div_regs = { 0x50, 0x31, 0x86, 0x85, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x50, 0x31, 0x86, 0x85, 0x80, 0x40 },
 	}, {
 		.pixclk = 98901099,
-		.pll_div_regs = { 0x52, 0x3a, 0xdb, 0x4c, 0x88, 0x47 },
+		.pll_div_regs = { 0xd1, 0x52, 0x3a, 0xdb, 0x4c, 0x88, 0x47 },
 	}, {
 		.pixclk = 99000000,
-		.pll_div_regs = { 0x52, 0x32, 0x82, 0x01, 0x88, 0x47 },
+		.pll_div_regs = { 0xd1, 0x52, 0x32, 0x82, 0x01, 0x88, 0x47 },
 	}, {
 		.pixclk = 100699300,
-		.pll_div_regs = { 0x54, 0x3c, 0xc3, 0x8f, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x54, 0x3c, 0xc3, 0x8f, 0x80, 0x40 },
 	}, {
 		.pixclk = 100800000,
-		.pll_div_regs = { 0x54, 0x30, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x54, 0x30, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 102500000,
-		.pll_div_regs = { 0x55, 0x32, 0x8c, 0x05, 0x90, 0x4b },
+		.pll_div_regs = { 0xd1, 0x55, 0x32, 0x8c, 0x05, 0x90, 0x4b },
 	}, {
 		.pixclk = 104750000,
-		.pll_div_regs = { 0x57, 0x32, 0x98, 0x07, 0x90, 0x49 },
+		.pll_div_regs = { 0xd1, 0x57, 0x32, 0x98, 0x07, 0x90, 0x49 },
 	}, {
 		.pixclk = 106500000,
-		.pll_div_regs = { 0x58, 0x32, 0x84, 0x03, 0x82, 0x41 },
+		.pll_div_regs = { 0xd1, 0x58, 0x32, 0x84, 0x03, 0x82, 0x41 },
 	}, {
 		.pixclk = 107000000,
-		.pll_div_regs = { 0x5a, 0x32, 0x89, 0x88, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x5a, 0x32, 0x89, 0x88, 0x80, 0x40 },
 	}, {
 		.pixclk = 108000000,
-		.pll_div_regs = { 0x5a, 0x30, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x5a, 0x30, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 108108000,
-		.pll_div_regs = { 0x5a, 0x32, 0xfd, 0x0c, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x5a, 0x32, 0xfd, 0x0c, 0x80, 0x40 },
 	}, {
 		.pixclk = 118000000,
-		.pll_div_regs = { 0x62, 0x34, 0x95, 0x08, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x62, 0x34, 0x95, 0x08, 0x80, 0x40 },
 	}, {
 		.pixclk = 118800000,
-		.pll_div_regs = { 0x63, 0x30, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x63, 0x30, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 123000000,
-		.pll_div_regs = { 0x66, 0x34, 0x82, 0x01, 0x88, 0x45 },
+		.pll_div_regs = { 0xd1, 0x66, 0x34, 0x82, 0x01, 0x88, 0x45 },
 	}, {
 		.pixclk = 127000000,
-		.pll_div_regs = { 0x69, 0x34, 0x89, 0x08, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x69, 0x34, 0x89, 0x08, 0x80, 0x40 },
 	}, {
 		.pixclk = 135000000,
-		.pll_div_regs = { 0x70, 0x34, 0x82, 0x01, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x70, 0x34, 0x82, 0x01, 0x80, 0x40 },
 	}, {
 		.pixclk = 135580000,
-		.pll_div_regs = { 0x71, 0x39, 0xe9, 0x82, 0x9c, 0x5b },
+		.pll_div_regs = { 0xd1, 0x71, 0x39, 0xe9, 0x82, 0x9c, 0x5b },
 	}, {
 		.pixclk = 137520000,
-		.pll_div_regs = { 0x72, 0x38, 0x99, 0x10, 0x85, 0x41 },
+		.pll_div_regs = { 0xd1, 0x72, 0x38, 0x99, 0x10, 0x85, 0x41 },
 	}, {
 		.pixclk = 138750000,
-		.pll_div_regs = { 0x73, 0x35, 0x88, 0x05, 0x90, 0x4d },
+		.pll_div_regs = { 0xd1, 0x73, 0x35, 0x88, 0x05, 0x90, 0x4d },
 	}, {
 		.pixclk = 140000000,
-		.pll_div_regs = { 0x75, 0x36, 0xa7, 0x90, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x75, 0x36, 0xa7, 0x90, 0x80, 0x40 },
 	}, {
 		.pixclk = 144000000,
-		.pll_div_regs = { 0x78, 0x30, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x78, 0x30, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 148352000,
-		.pll_div_regs = { 0x7b, 0x35, 0xdb, 0x39, 0x90, 0x45 },
+		.pll_div_regs = { 0xd1, 0x7b, 0x35, 0xdb, 0x39, 0x90, 0x45 },
 	}, {
 		.pixclk = 148500000,
-		.pll_div_regs = { 0x7b, 0x35, 0x84, 0x03, 0x90, 0x45 },
+		.pll_div_regs = { 0xd1, 0x7b, 0x35, 0x84, 0x03, 0x90, 0x45 },
 	}, {
 		.pixclk = 154000000,
-		.pll_div_regs = { 0x40, 0x18, 0x83, 0x01, 0x00, 0x40 },
+		.pll_div_regs = { 0xd1, 0x40, 0x18, 0x83, 0x01, 0x00, 0x40 },
 	}, {
 		.pixclk = 157000000,
-		.pll_div_regs = { 0x41, 0x11, 0xa7, 0x14, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x41, 0x11, 0xa7, 0x14, 0x80, 0x40 },
 	}, {
 		.pixclk = 160000000,
-		.pll_div_regs = { 0x42, 0x12, 0xa1, 0x20, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x42, 0x12, 0xa1, 0x20, 0x80, 0x40 },
 	}, {
 		.pixclk = 162000000,
-		.pll_div_regs = { 0x43, 0x18, 0x8b, 0x08, 0x96, 0x55 },
+		.pll_div_regs = { 0xd1, 0x43, 0x18, 0x8b, 0x08, 0x96, 0x55 },
 	}, {
 		.pixclk = 164000000,
-		.pll_div_regs = { 0x45, 0x11, 0x83, 0x82, 0x90, 0x4b },
+		.pll_div_regs = { 0xd1, 0x45, 0x11, 0x83, 0x82, 0x90, 0x4b },
 	}, {
 		.pixclk = 165000000,
-		.pll_div_regs = { 0x45, 0x11, 0x84, 0x81, 0x90, 0x4b },
+		.pll_div_regs = { 0xd1, 0x45, 0x11, 0x84, 0x81, 0x90, 0x4b },
 	}, {
 		.pixclk = 180000000,
-		.pll_div_regs = { 0x4b, 0x10, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x4b, 0x10, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 185625000,
-		.pll_div_regs = { 0x4e, 0x12, 0x9a, 0x95, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x4e, 0x12, 0x9a, 0x95, 0x80, 0x40 },
 	}, {
 		.pixclk = 188000000,
-		.pll_div_regs = { 0x4e, 0x12, 0xa7, 0x10, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x4e, 0x12, 0xa7, 0x10, 0x80, 0x40 },
 	}, {
 		.pixclk = 198000000,
-		.pll_div_regs = { 0x52, 0x12, 0x82, 0x01, 0x88, 0x47 },
+		.pll_div_regs = { 0xd1, 0x52, 0x12, 0x82, 0x01, 0x88, 0x47 },
 	}, {
 		.pixclk = 205000000,
-		.pll_div_regs = { 0x55, 0x12, 0x8c, 0x05, 0x90, 0x4b },
+		.pll_div_regs = { 0xd1, 0x55, 0x12, 0x8c, 0x05, 0x90, 0x4b },
 	}, {
 		.pixclk = 209500000,
-		.pll_div_regs = { 0x57, 0x12, 0x98, 0x07, 0x90, 0x49 },
+		.pll_div_regs = { 0xd1, 0x57, 0x12, 0x98, 0x07, 0x90, 0x49 },
 	}, {
 		.pixclk = 213000000,
-		.pll_div_regs = { 0x58, 0x12, 0x84, 0x03, 0x82, 0x41 },
+		.pll_div_regs = { 0xd1, 0x58, 0x12, 0x84, 0x03, 0x82, 0x41 },
 	}, {
 		.pixclk = 216000000,
-		.pll_div_regs = { 0x5a, 0x10, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x5a, 0x10, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 216216000,
-		.pll_div_regs = { 0x5a, 0x12, 0xfd, 0x0c, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x5a, 0x12, 0xfd, 0x0c, 0x80, 0x40 },
 	}, {
 		.pixclk = 237600000,
-		.pll_div_regs = { 0x63, 0x10, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x63, 0x10, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 254000000,
-		.pll_div_regs = { 0x69, 0x14, 0x89, 0x08, 0x80, 0x40 },
+		.pll_div_regs = { 0xd1, 0x69, 0x14, 0x89, 0x08, 0x80, 0x40 },
 	}, {
 		.pixclk = 277500000,
-		.pll_div_regs = { 0x73, 0x15, 0x88, 0x05, 0x90, 0x4d },
+		.pll_div_regs = { 0xd1, 0x73, 0x15, 0x88, 0x05, 0x90, 0x4d },
 	}, {
 		.pixclk = 288000000,
-		.pll_div_regs = { 0x78, 0x10, 0x00, 0x00, 0x80, 0x00 },
+		.pll_div_regs = { 0xd1, 0x78, 0x10, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 297000000,
-		.pll_div_regs = { 0x7b, 0x15, 0x84, 0x03, 0x90, 0x45 },
+		.pll_div_regs = { 0xd1, 0x7b, 0x15, 0x84, 0x03, 0x90, 0x45 },
 	},
 };
 
@@ -322,7 +339,8 @@ struct reg_settings {
 };
 
 static const struct reg_settings common_phy_cfg[] = {
-	{ PHY_REG(0), 0x00 }, { PHY_REG(1), 0xd1 },
+	{ PHY_REG(0), 0x00 },
+	/* PHY_REG(1-7) pix clk specific */
 	{ PHY_REG(8), 0x4f }, { PHY_REG(9), 0x30 },
 	{ PHY_REG(10), 0x33 }, { PHY_REG(11), 0x65 },
 	/* REG12 pixclk specific */
@@ -415,6 +433,83 @@ fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy,
 	       phy->regs + PHY_REG(14));
 }
 
+static unsigned long fsl_samsung_hdmi_phy_find_pms(unsigned long fout, u8 *p, u16 *m, u8 *s)
+{
+	unsigned long best_freq = 0;
+	u32 min_delta = 0xffffffff;
+	u8 _p, best_p;
+	u16 _m, best_m;
+	u8 _s, best_s;
+
+	/*
+	 * Figure 13-78 of the reference manual states the PLL should be TMDS x 5
+	 * while the TMDS_CLKO should be the PLL / 5.  So to calculate the PLL,
+	 * take the pix clock x 5, then return the value of the PLL / 5.
+	 */
+	fout *= 5;
+
+	/* The ref manual states the values of 'P' range from 1 to 11 */
+	for (_p = 1; _p <= 11; ++_p) {
+		for (_s = 1; _s <= 16; ++_s) {
+			u64 tmp;
+			u32 delta;
+
+			/* s must be one or even */
+			if (_s > 1 && (_s & 0x01) == 1)
+				_s++;
+
+			/* _s cannot be 14 per the TRM */
+			if (_s == 14)
+				continue;
+
+			/*
+			 * TODO: Ref Manual doesn't state the range of _m
+			 * so this should be further refined if possible.
+			 * This range was set based on the original values
+			 * in the lookup table
+			 */
+			tmp = (u64)fout * (_p * _s);
+			do_div(tmp, 24 * MHZ);
+			_m = tmp;
+			if (_m < 0x30 || _m > 0x7b)
+				continue;
+
+			/*
+			 * Rev 2 of the Ref Manual states the
+			 * VCO can range between 750MHz and
+			 * 3GHz. The VCO is assumed to be
+			 * Fvco = (M * f_ref) / P,
+			 * where f_ref is 24MHz.
+			 */
+			tmp = (u64)_m * 24 * MHZ;
+			do_div(tmp, _p);
+			if (tmp < 750 * MHZ ||
+			    tmp > 3000 * MHZ)
+				continue;
+
+			/* Final frequency after post-divider */
+			do_div(tmp, _s);
+
+			delta = abs(fout - tmp);
+			if (delta < min_delta) {
+				best_p = _p;
+				best_s = _s;
+				best_m = _m;
+				min_delta = delta;
+				best_freq = tmp;
+			}
+		}
+	}
+
+	if (best_freq) {
+		*p = best_p;
+		*m = best_m;
+		*s = best_s;
+	}
+
+	return best_freq / 5;
+}
+
 static int fsl_samsung_hdmi_phy_configure(struct fsl_samsung_hdmi_phy *phy,
 					  const struct phy_config *cfg)
 {
@@ -428,13 +523,13 @@ static int fsl_samsung_hdmi_phy_configure(struct fsl_samsung_hdmi_phy *phy,
 	for (i = 0; i < ARRAY_SIZE(common_phy_cfg); i++)
 		writeb(common_phy_cfg[i].val, phy->regs + common_phy_cfg[i].reg);
 
-	/* set individual PLL registers PHY_REG2 ... PHY_REG7 */
+	/* set individual PLL registers PHY_REG1 ... PHY_REG7 */
 	for (i = 0; i < PHY_PLL_DIV_REGS_NUM; i++)
-		writeb(cfg->pll_div_regs[i], phy->regs + PHY_REG(2) + i * 4);
+		writeb(cfg->pll_div_regs[i], phy->regs + PHY_REG(1) + i * 4);
 
-	/* High nibble of pll_div_regs[1] contains S which also gets written to REG21 */
+	/* High nibble of PHY_REG3 and low nibble of PHY_REG21 both contain 'S' */
 	writeb(REG21_SEL_TX_CK_INV | FIELD_PREP(REG21_PMS_S_MASK,
-	       cfg->pll_div_regs[1] >> 4), phy->regs + PHY_REG(21));
+	       cfg->pll_div_regs[2] >> 4), phy->regs + PHY_REG(21));
 
 	fsl_samsung_hdmi_phy_configure_pll_lock_det(phy, cfg);
 
@@ -459,34 +554,102 @@ static unsigned long phy_clk_recalc_rate(struct clk_hw *hw,
 	return phy->cur_cfg->pixclk;
 }
 
-static long phy_clk_round_rate(struct clk_hw *hw,
-			       unsigned long rate, unsigned long *parent_rate)
+/* Helper function to lookup the available fractional-divider rate */
+static const struct phy_config *fsl_samsung_hdmi_phy_lookup_rate(unsigned long rate)
 {
 	int i;
 
+	/* Search the lookup table */
 	for (i = ARRAY_SIZE(phy_pll_cfg) - 1; i >= 0; i--)
 		if (phy_pll_cfg[i].pixclk <= rate)
-			return phy_pll_cfg[i].pixclk;
+			break;
+
+	return &phy_pll_cfg[i];
+}
+
+static void fsl_samsung_hdmi_calculate_phy(struct phy_config *cal_phy, unsigned long rate,
+				    u8 p, u16 m, u8 s)
+{
+	cal_phy->pixclk = rate;
+	cal_phy->pll_div_regs[0] = FIELD_PREP(REG01_PMS_P_MASK, p);
+	cal_phy->pll_div_regs[1] = m;
+	cal_phy->pll_div_regs[2] = FIELD_PREP(REG03_PMS_S_MASK, s-1);
+	/* pll_div_regs 3-6 are fixed and pre-defined already */
+}
+
+static long phy_clk_round_rate(struct clk_hw *hw,
+			       unsigned long rate, unsigned long *parent_rate)
+{
+	const struct phy_config *fract_div_phy;
+	u32 int_div_clk;
+	u16 m;
+	u8 p, s;
+
+	/* If the clock is out of range return error instead of searching */
+	if (rate > 297000000 || rate < 22250000)
+		return -EINVAL;
+
+	/* Search the fractional divider lookup table */
+	fract_div_phy = fsl_samsung_hdmi_phy_lookup_rate(rate);
 
-	return -EINVAL;
+	/* If the rate is an exact match, return that value */
+	if (rate == fract_div_phy->pixclk)
+		return fract_div_phy->pixclk;
+
+	/* If the exact match isn't found, calculate the integer divider */
+	int_div_clk = fsl_samsung_hdmi_phy_find_pms(rate, &p, &m, &s);
+
+	/* If the int_div_clk rate is an exact match, return that value */
+	if (int_div_clk == rate)
+		return int_div_clk;
+
+	/* If neither rate is an exact match, use the value from the LUT */
+	return fract_div_phy->pixclk;
+}
+
+static int phy_use_fract_div(struct fsl_samsung_hdmi_phy *phy, const struct phy_config *fract_div_phy)
+{
+	phy->cur_cfg = fract_div_phy;
+	dev_dbg(phy->dev, "fsl_samsung_hdmi_phy: using fractional divider rate = %u\n",
+		phy->cur_cfg->pixclk);
+	return fsl_samsung_hdmi_phy_configure(phy, phy->cur_cfg);
 }
 
 static int phy_clk_set_rate(struct clk_hw *hw,
 			    unsigned long rate, unsigned long parent_rate)
 {
 	struct fsl_samsung_hdmi_phy *phy = to_fsl_samsung_hdmi_phy(hw);
-	int i;
+	const struct phy_config *fract_div_phy;
+	u32 int_div_clk;
+	u16 m;
+	u8 p, s;
 
-	for (i = ARRAY_SIZE(phy_pll_cfg) - 1; i >= 0; i--)
-		if (phy_pll_cfg[i].pixclk <= rate)
-			break;
+	/* Search the fractional divider lookup table */
+	fract_div_phy = fsl_samsung_hdmi_phy_lookup_rate(rate);
 
-	if (i < 0)
-		return -EINVAL;
+	/* If the rate is an exact match, use that value */
+	if (fract_div_phy->pixclk == rate)
+		return phy_use_fract_div(phy, fract_div_phy);
 
-	phy->cur_cfg = &phy_pll_cfg[i];
+	/*
+	 * If the rate from the fractional divider is not exact, check the integer divider,
+	 * and use it if that value is an exact match.
+	 */
+	int_div_clk = fsl_samsung_hdmi_phy_find_pms(rate, &p, &m, &s);
+	if (int_div_clk == rate) {
+		dev_dbg(phy->dev, "fsl_samsung_hdmi_phy: integer divider rate = %u\n",
+				   int_div_clk);
+
+		fsl_samsung_hdmi_calculate_phy(&calculated_phy_pll_cfg, int_div_clk, p, m, s);
+		phy->cur_cfg  = &calculated_phy_pll_cfg;
+		return fsl_samsung_hdmi_phy_configure(phy, phy->cur_cfg);
+	}
 
-	return fsl_samsung_hdmi_phy_configure(phy, phy->cur_cfg);
+	/*
+	 * If neither the fractional divider nor the integer divider can find an exact value
+	 * fall back to using the fractional divider
+	 */
+	return phy_use_fract_div(phy, fract_div_phy);
 }
 
 static const struct clk_ops phy_clk_ops = {

From 058ea4a06704c6ad3032bdb3ead9ed3dc1f7fe6e Mon Sep 17 00:00:00 2001
From: Adam Ford <aford173@gmail.com>
Date: Sat, 14 Sep 2024 06:27:48 -0500
Subject: [PATCH 0438/1530] phy: freescale: fsl-samsung-hdmi: Use closest
 divider

Currently, if the clock values cannot be set to the exact rate,
the round_rate and set_rate functions use the closest value found in
the look-up-table.  In preparation of removing values from the LUT
that can be calculated evenly with the integer calculator, it's
necessary to ensure to check both the look-up-table and the integer
divider clock values to get the closest values to the requested
value.  It does this by measuring the difference between the
requested clock value and the closest value in both integer divider
calucator and the fractional clock look-up-table.

Which ever has the smallest difference between them is returned as
the closest rate.

Signed-off-by: Adam Ford <aford173@gmail.com>
Reviewed-by: Dominique Martinet <dominique.martinet@atmark-techno.com>
Tested-by: Dominique Martinet <dominique.martinet@atmark-techno.com>
Reviewed-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Link: https://lore.kernel.org/r/20240914112816.520224-5-aford173@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/freescale/phy-fsl-samsung-hdmi.c | 40 ++++++++++++++------
 1 file changed, 29 insertions(+), 11 deletions(-)

diff --git a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
index 029de69fbeaf4..381742e8b6188 100644
--- a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
+++ b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
@@ -577,6 +577,16 @@ static void fsl_samsung_hdmi_calculate_phy(struct phy_config *cal_phy, unsigned
 	/* pll_div_regs 3-6 are fixed and pre-defined already */
 }
 
+static u32 fsl_samsung_hdmi_phy_get_closest_rate(unsigned long rate,
+						 u32 int_div_clk, u32 frac_div_clk)
+{
+	/* Calculate the absolute value of the differences and return whichever is closest */
+	if (abs((long)rate - (long)int_div_clk) < abs((long)(rate - (long)frac_div_clk)))
+		return int_div_clk;
+
+	return frac_div_clk;
+}
+
 static long phy_clk_round_rate(struct clk_hw *hw,
 			       unsigned long rate, unsigned long *parent_rate)
 {
@@ -615,6 +625,15 @@ static int phy_use_fract_div(struct fsl_samsung_hdmi_phy *phy, const struct phy_
 	return fsl_samsung_hdmi_phy_configure(phy, phy->cur_cfg);
 }
 
+static int phy_use_integer_div(struct fsl_samsung_hdmi_phy *phy,
+			       const struct phy_config *int_div_clk)
+{
+	phy->cur_cfg  = &calculated_phy_pll_cfg;
+	dev_dbg(phy->dev, "fsl_samsung_hdmi_phy: integer divider rate = %u\n",
+		phy->cur_cfg->pixclk);
+	return fsl_samsung_hdmi_phy_configure(phy, phy->cur_cfg);
+}
+
 static int phy_clk_set_rate(struct clk_hw *hw,
 			    unsigned long rate, unsigned long parent_rate)
 {
@@ -636,20 +655,19 @@ static int phy_clk_set_rate(struct clk_hw *hw,
 	 * and use it if that value is an exact match.
 	 */
 	int_div_clk = fsl_samsung_hdmi_phy_find_pms(rate, &p, &m, &s);
-	if (int_div_clk == rate) {
-		dev_dbg(phy->dev, "fsl_samsung_hdmi_phy: integer divider rate = %u\n",
-				   int_div_clk);
-
-		fsl_samsung_hdmi_calculate_phy(&calculated_phy_pll_cfg, int_div_clk, p, m, s);
-		phy->cur_cfg  = &calculated_phy_pll_cfg;
-		return fsl_samsung_hdmi_phy_configure(phy, phy->cur_cfg);
-	}
+	fsl_samsung_hdmi_calculate_phy(&calculated_phy_pll_cfg, int_div_clk, p, m, s);
+	if (int_div_clk == rate)
+		return phy_use_integer_div(phy, &calculated_phy_pll_cfg);
 
 	/*
-	 * If neither the fractional divider nor the integer divider can find an exact value
-	 * fall back to using the fractional divider
+	 * Compare the difference between the integer clock and the fractional clock against
+	 * the desired clock and which whichever is closest.
 	 */
-	return phy_use_fract_div(phy, fract_div_phy);
+	if (fsl_samsung_hdmi_phy_get_closest_rate(rate, int_div_clk,
+						  fract_div_phy->pixclk) == fract_div_phy->pixclk)
+		return phy_use_fract_div(phy, fract_div_phy);
+	else
+		return phy_use_integer_div(phy, &calculated_phy_pll_cfg);
 }
 
 static const struct clk_ops phy_clk_ops = {

From 7588444551c65ddd37d6ee9e232bd944d2df2c8c Mon Sep 17 00:00:00 2001
From: Adam Ford <aford173@gmail.com>
Date: Sat, 14 Sep 2024 06:27:49 -0500
Subject: [PATCH 0439/1530] phy: freescale: fsl-samsung-hdmi: Remove
 unnecessary LUT entries

The lookup table contains entries which use the integer divider
instead of just the fractional divider. Since the set and round
functions check both the integer divider values and the LUT values,
it's no longer necessary to keep the integer divider values in the
lookup table, as can be dynamically calcuated.

Signed-off-by: Adam Ford <aford173@gmail.com>
Reviewed-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Tested-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Reviewed-by: Dominique Martinet <dominique.martinet@atmark-techno.com>
Tested-by: Dominique Martinet <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/r/20240914112816.520224-6-aford173@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/freescale/phy-fsl-samsung-hdmi.c | 83 +++-----------------
 1 file changed, 13 insertions(+), 70 deletions(-)

diff --git a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
index 381742e8b6188..a08c1bfa657c5 100644
--- a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
+++ b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
@@ -69,25 +69,16 @@ static const struct phy_config phy_pll_cfg[] = {
 	}, {
 		.pixclk = 23750000,
 		.pll_div_regs = { 0xd1, 0x50, 0xf1, 0x86, 0x85, 0x80, 0x40 },
-	}, {
-		.pixclk = 24000000,
-		.pll_div_regs = { 0xd1, 0x50, 0xf0, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 24024000,
 		.pll_div_regs = { 0xd1, 0x50, 0xf1, 0x99, 0x02, 0x80, 0x40 },
 	}, {
 		.pixclk = 25175000,
 		.pll_div_regs = { 0xd1, 0x54, 0xfc, 0xcc, 0x91, 0x80, 0x40 },
-	}, {
-		.pixclk = 25200000,
-		.pll_div_regs = { 0xd1, 0x54, 0xf0, 0x00, 0x00, 0x80, 0x00 },
-	}, {
+	},  {
 		.pixclk = 26750000,
 		.pll_div_regs = { 0xd1, 0x5a, 0xf2, 0x89, 0x88, 0x80, 0x40 },
-	}, {
-		.pixclk = 27000000,
-		.pll_div_regs = { 0xd1, 0x5a, 0xf0, 0x00, 0x00, 0x80, 0x00 },
-	}, {
+	},  {
 		.pixclk = 27027000,
 		.pll_div_regs = { 0xd1, 0x5a, 0xf2, 0xfd, 0x0c, 0x80, 0x40 },
 	}, {
@@ -105,18 +96,9 @@ static const struct phy_config phy_pll_cfg[] = {
 	}, {
 		.pixclk = 35000000,
 		.pll_div_regs = { 0xd1, 0x58, 0xb8, 0x8b, 0x88, 0x80, 0x40 },
-	}, {
-		.pixclk = 36000000,
-		.pll_div_regs = { 0xd1, 0x5a, 0xb0, 0x00, 0x00, 0x80, 0x00 },
-	}, {
+	},  {
 		.pixclk = 36036000,
 		.pll_div_regs = { 0xd1, 0x5a, 0xb2, 0xfd, 0x0c, 0x80, 0x40 },
-	}, {
-		.pixclk = 40000000,
-		.pll_div_regs = { 0xd1, 0x64, 0xb0, 0x00, 0x00, 0x80, 0x00 },
-	}, {
-		.pixclk = 43200000,
-		.pll_div_regs = { 0xd1, 0x5a, 0x90, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 43243200,
 		.pll_div_regs = { 0xd1, 0x5a, 0x92, 0xfd, 0x0c, 0x80, 0x40 },
@@ -132,19 +114,13 @@ static const struct phy_config phy_pll_cfg[] = {
 	}, {
 		.pixclk = 50349650,
 		.pll_div_regs = { 0xd1, 0x54, 0x7c, 0xc3, 0x8f, 0x80, 0x40 },
-	}, {
-		.pixclk = 50400000,
-		.pll_div_regs = { 0xd1, 0x54, 0x70, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 53250000,
 		.pll_div_regs = { 0xd1, 0x58, 0x72, 0x84, 0x03, 0x82, 0x41 },
 	}, {
 		.pixclk = 53500000,
 		.pll_div_regs = { 0xd1, 0x5a, 0x72, 0x89, 0x88, 0x80, 0x40 },
-	}, {
-		.pixclk = 54000000,
-		.pll_div_regs = { 0xd1, 0x5a, 0x70, 0x00, 0x00, 0x80, 0x00 },
-	}, {
+	},  {
 		.pixclk = 54054000,
 		.pll_div_regs = { 0xd1, 0x5a, 0x72, 0xfd, 0x0c, 0x80, 0x40 },
 	}, {
@@ -153,10 +129,7 @@ static const struct phy_config phy_pll_cfg[] = {
 	}, {
 		.pixclk = 59340659,
 		.pll_div_regs = { 0xd1, 0x62, 0x74, 0xdb, 0x52, 0x88, 0x47 },
-	}, {
-		.pixclk = 59400000,
-		.pll_div_regs = { 0xd1, 0x63, 0x70, 0x00, 0x00, 0x80, 0x00 },
-	}, {
+	},  {
 		.pixclk = 61500000,
 		.pll_div_regs = { 0xd1, 0x66, 0x74, 0x82, 0x01, 0x88, 0x45 },
 	}, {
@@ -168,10 +141,7 @@ static const struct phy_config phy_pll_cfg[] = {
 	}, {
 		.pixclk = 70000000,
 		.pll_div_regs = { 0xd1, 0x58, 0x58, 0x8b, 0x88, 0x80, 0x40 },
-	}, {
-		.pixclk = 72000000,
-		.pll_div_regs = { 0xd1, 0x5a, 0x50, 0x00, 0x00, 0x80, 0x00 },
-	}, {
+	},  {
 		.pixclk = 72072000,
 		.pll_div_regs = { 0xd1, 0x5a, 0x52, 0xfd, 0x0c, 0x80, 0x40 },
 	}, {
@@ -183,10 +153,7 @@ static const struct phy_config phy_pll_cfg[] = {
 	}, {
 		.pixclk = 78500000,
 		.pll_div_regs = { 0xd1, 0x62, 0x54, 0x87, 0x01, 0x80, 0x40 },
-	}, {
-		.pixclk = 80000000,
-		.pll_div_regs = { 0xd1, 0x64, 0x50, 0x00, 0x00, 0x80, 0x00 },
-	}, {
+	},  {
 		.pixclk = 82000000,
 		.pll_div_regs = { 0xd1, 0x66, 0x54, 0x82, 0x01, 0x88, 0x45 },
 	}, {
@@ -213,10 +180,7 @@ static const struct phy_config phy_pll_cfg[] = {
 	}, {
 		.pixclk = 100699300,
 		.pll_div_regs = { 0xd1, 0x54, 0x3c, 0xc3, 0x8f, 0x80, 0x40 },
-	}, {
-		.pixclk = 100800000,
-		.pll_div_regs = { 0xd1, 0x54, 0x30, 0x00, 0x00, 0x80, 0x00 },
-	}, {
+	},  {
 		.pixclk = 102500000,
 		.pll_div_regs = { 0xd1, 0x55, 0x32, 0x8c, 0x05, 0x90, 0x4b },
 	}, {
@@ -228,19 +192,13 @@ static const struct phy_config phy_pll_cfg[] = {
 	}, {
 		.pixclk = 107000000,
 		.pll_div_regs = { 0xd1, 0x5a, 0x32, 0x89, 0x88, 0x80, 0x40 },
-	}, {
-		.pixclk = 108000000,
-		.pll_div_regs = { 0xd1, 0x5a, 0x30, 0x00, 0x00, 0x80, 0x00 },
-	}, {
+	},  {
 		.pixclk = 108108000,
 		.pll_div_regs = { 0xd1, 0x5a, 0x32, 0xfd, 0x0c, 0x80, 0x40 },
 	}, {
 		.pixclk = 118000000,
 		.pll_div_regs = { 0xd1, 0x62, 0x34, 0x95, 0x08, 0x80, 0x40 },
-	}, {
-		.pixclk = 118800000,
-		.pll_div_regs = { 0xd1, 0x63, 0x30, 0x00, 0x00, 0x80, 0x00 },
-	}, {
+	},  {
 		.pixclk = 123000000,
 		.pll_div_regs = { 0xd1, 0x66, 0x34, 0x82, 0x01, 0x88, 0x45 },
 	}, {
@@ -261,10 +219,7 @@ static const struct phy_config phy_pll_cfg[] = {
 	}, {
 		.pixclk = 140000000,
 		.pll_div_regs = { 0xd1, 0x75, 0x36, 0xa7, 0x90, 0x80, 0x40 },
-	}, {
-		.pixclk = 144000000,
-		.pll_div_regs = { 0xd1, 0x78, 0x30, 0x00, 0x00, 0x80, 0x00 },
-	}, {
+	},  {
 		.pixclk = 148352000,
 		.pll_div_regs = { 0xd1, 0x7b, 0x35, 0xdb, 0x39, 0x90, 0x45 },
 	}, {
@@ -288,9 +243,6 @@ static const struct phy_config phy_pll_cfg[] = {
 	}, {
 		.pixclk = 165000000,
 		.pll_div_regs = { 0xd1, 0x45, 0x11, 0x84, 0x81, 0x90, 0x4b },
-	}, {
-		.pixclk = 180000000,
-		.pll_div_regs = { 0xd1, 0x4b, 0x10, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 185625000,
 		.pll_div_regs = { 0xd1, 0x4e, 0x12, 0x9a, 0x95, 0x80, 0x40 },
@@ -309,25 +261,16 @@ static const struct phy_config phy_pll_cfg[] = {
 	}, {
 		.pixclk = 213000000,
 		.pll_div_regs = { 0xd1, 0x58, 0x12, 0x84, 0x03, 0x82, 0x41 },
-	}, {
-		.pixclk = 216000000,
-		.pll_div_regs = { 0xd1, 0x5a, 0x10, 0x00, 0x00, 0x80, 0x00 },
 	}, {
 		.pixclk = 216216000,
 		.pll_div_regs = { 0xd1, 0x5a, 0x12, 0xfd, 0x0c, 0x80, 0x40 },
-	}, {
-		.pixclk = 237600000,
-		.pll_div_regs = { 0xd1, 0x63, 0x10, 0x00, 0x00, 0x80, 0x00 },
-	}, {
+	},  {
 		.pixclk = 254000000,
 		.pll_div_regs = { 0xd1, 0x69, 0x14, 0x89, 0x08, 0x80, 0x40 },
 	}, {
 		.pixclk = 277500000,
 		.pll_div_regs = { 0xd1, 0x73, 0x15, 0x88, 0x05, 0x90, 0x4d },
-	}, {
-		.pixclk = 288000000,
-		.pll_div_regs = { 0xd1, 0x78, 0x10, 0x00, 0x00, 0x80, 0x00 },
-	}, {
+	},  {
 		.pixclk = 297000000,
 		.pll_div_regs = { 0xd1, 0x7b, 0x15, 0x84, 0x03, 0x90, 0x45 },
 	},

From b3e804ab9aad465ba7285aa5daf83656d5efc59f Mon Sep 17 00:00:00 2001
From: Frank Wang <frank.wang@rock-chips.com>
Date: Mon, 14 Oct 2024 10:03:41 +0800
Subject: [PATCH 0440/1530] dt-bindings: phy: rockchip-usbdp: add rk3576

Add compatible for the USBDP phy in the Rockchip RK3576 SoC.

Signed-off-by: Frank Wang <frank.wang@rock-chips.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Reviewed-by: Dragan Simic <dsimic@manjaro.org>
Link: https://lore.kernel.org/r/20241014020342.15974-1-frawang.cn@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/phy/phy-rockchip-usbdp.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/phy/phy-rockchip-usbdp.yaml b/Documentation/devicetree/bindings/phy/phy-rockchip-usbdp.yaml
index 1f1f8863b80d0..b42f1272903d8 100644
--- a/Documentation/devicetree/bindings/phy/phy-rockchip-usbdp.yaml
+++ b/Documentation/devicetree/bindings/phy/phy-rockchip-usbdp.yaml
@@ -13,6 +13,7 @@ maintainers:
 properties:
   compatible:
     enum:
+      - rockchip,rk3576-usbdp-phy
       - rockchip,rk3588-usbdp-phy
 
   reg:

From a76de028c619dd18f89786805bcc7bb4d379ea9f Mon Sep 17 00:00:00 2001
From: Frank Wang <frank.wang@rock-chips.com>
Date: Mon, 14 Oct 2024 10:03:42 +0800
Subject: [PATCH 0441/1530] phy: rockchip: usbdp: add rk3576 device match data

This adds RK3576 device match data support.

Signed-off-by: Frank Wang <frank.wang@rock-chips.com>
Acked-by: Dragan Simic <dsimic@manjaro.org>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/r/20241014020342.15974-2-frawang.cn@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/rockchip/phy-rockchip-usbdp.c | 41 +++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/drivers/phy/rockchip/phy-rockchip-usbdp.c b/drivers/phy/rockchip/phy-rockchip-usbdp.c
index 2c51e5c62d3eb..5b1e8a3806ed4 100644
--- a/drivers/phy/rockchip/phy-rockchip-usbdp.c
+++ b/drivers/phy/rockchip/phy-rockchip-usbdp.c
@@ -1538,6 +1538,43 @@ static const char * const rk_udphy_rst_list[] = {
 	"init", "cmn", "lane", "pcs_apb", "pma_apb"
 };
 
+static const struct rk_udphy_cfg rk3576_udphy_cfgs = {
+	.num_phys = 1,
+	.phy_ids = { 0x2b010000 },
+	.num_rsts = ARRAY_SIZE(rk_udphy_rst_list),
+	.rst_list = rk_udphy_rst_list,
+	.grfcfg	= {
+		/* u2phy-grf */
+		.bvalid_phy_con		= RK_UDPHY_GEN_GRF_REG(0x0010, 1, 0, 0x2, 0x3),
+		.bvalid_grf_con		= RK_UDPHY_GEN_GRF_REG(0x0000, 15, 14, 0x1, 0x3),
+
+		/* usb-grf */
+		.usb3otg0_cfg		= RK_UDPHY_GEN_GRF_REG(0x0030, 15, 0, 0x1100, 0x0188),
+
+		/* usbdpphy-grf */
+		.low_pwrn		= RK_UDPHY_GEN_GRF_REG(0x0004, 13, 13, 0, 1),
+		.rx_lfps		= RK_UDPHY_GEN_GRF_REG(0x0004, 14, 14, 0, 1),
+	},
+	.vogrfcfg = {
+		{
+			.hpd_trigger	= RK_UDPHY_GEN_GRF_REG(0x0000, 11, 10, 1, 3),
+			.dp_lane_reg    = 0x0000,
+		},
+	},
+	.dp_tx_ctrl_cfg = {
+		rk3588_dp_tx_drv_ctrl_rbr_hbr_typec,
+		rk3588_dp_tx_drv_ctrl_rbr_hbr_typec,
+		rk3588_dp_tx_drv_ctrl_hbr2,
+		rk3588_dp_tx_drv_ctrl_hbr3,
+	},
+	.dp_tx_ctrl_cfg_typec = {
+		rk3588_dp_tx_drv_ctrl_rbr_hbr_typec,
+		rk3588_dp_tx_drv_ctrl_rbr_hbr_typec,
+		rk3588_dp_tx_drv_ctrl_hbr2,
+		rk3588_dp_tx_drv_ctrl_hbr3,
+	},
+};
+
 static const struct rk_udphy_cfg rk3588_udphy_cfgs = {
 	.num_phys = 2,
 	.phy_ids = {
@@ -1584,6 +1621,10 @@ static const struct rk_udphy_cfg rk3588_udphy_cfgs = {
 };
 
 static const struct of_device_id rk_udphy_dt_match[] = {
+	{
+		.compatible = "rockchip,rk3576-usbdp-phy",
+		.data = &rk3576_udphy_cfgs
+	},
 	{
 		.compatible = "rockchip,rk3588-usbdp-phy",
 		.data = &rk3588_udphy_cfgs

From 7adb3d221a4d6a4f5e0793c3bd35f1168934035c Mon Sep 17 00:00:00 2001
From: Soutrik Mukhopadhyay <quic_mukhopad@quicinc.com>
Date: Fri, 4 Oct 2024 16:00:42 +0530
Subject: [PATCH 0442/1530] dt-bindings: phy: Add eDP PHY compatible for
 sa8775p

Add compatible string for the supported eDP PHY on sa8775p platform.

Acked-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Soutrik Mukhopadhyay <quic_mukhopad@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20241004103046.22209-2-quic_mukhopad@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/phy/qcom,edp-phy.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/phy/qcom,edp-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,edp-phy.yaml
index 4e15d90d08b0e..293fb6a9b1c33 100644
--- a/Documentation/devicetree/bindings/phy/qcom,edp-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,edp-phy.yaml
@@ -17,6 +17,7 @@ description:
 properties:
   compatible:
     enum:
+      - qcom,sa8775p-edp-phy
       - qcom,sc7280-edp-phy
       - qcom,sc8180x-edp-phy
       - qcom,sc8280xp-dp-phy

From 913463587d528d766a8e12c7790995e273ec84fb Mon Sep 17 00:00:00 2001
From: Soutrik Mukhopadhyay <quic_mukhopad@quicinc.com>
Date: Fri, 4 Oct 2024 16:00:43 +0530
Subject: [PATCH 0443/1530] phy: qcom: edp: Introduce aux_cfg array for version
 specific aux settings

In order to support different HW versions, introduce aux_cfg array
to move v4 specific aux configuration settings.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Soutrik Mukhopadhyay <quic_mukhopad@quicinc.com>
Link: https://lore.kernel.org/r/20241004103046.22209-3-quic_mukhopad@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-edp.c | 41 ++++++++++++-----------------
 1 file changed, 17 insertions(+), 24 deletions(-)

diff --git a/drivers/phy/qualcomm/phy-qcom-edp.c b/drivers/phy/qualcomm/phy-qcom-edp.c
index da2b32fb5b451..2ecff164ec44f 100644
--- a/drivers/phy/qualcomm/phy-qcom-edp.c
+++ b/drivers/phy/qualcomm/phy-qcom-edp.c
@@ -32,16 +32,8 @@
 #define DP_PHY_PD_CTL                           0x001c
 #define DP_PHY_MODE                             0x0020
 
-#define DP_PHY_AUX_CFG0				0x0024
-#define DP_PHY_AUX_CFG1				0x0028
-#define DP_PHY_AUX_CFG2				0x002C
-#define DP_PHY_AUX_CFG3				0x0030
-#define DP_PHY_AUX_CFG4				0x0034
-#define DP_PHY_AUX_CFG5				0x0038
-#define DP_PHY_AUX_CFG6				0x003C
-#define DP_PHY_AUX_CFG7				0x0040
-#define DP_PHY_AUX_CFG8				0x0044
-#define DP_PHY_AUX_CFG9				0x0048
+#define DP_AUX_CFG_SIZE                         10
+#define DP_PHY_AUX_CFG(n)                       (0x24 + (0x04 * (n)))
 
 #define DP_PHY_AUX_INTERRUPT_MASK		0x0058
 
@@ -90,6 +82,7 @@ struct phy_ver_ops {
 
 struct qcom_edp_phy_cfg {
 	bool is_edp;
+	const u8 *aux_cfg;
 	const struct qcom_edp_swing_pre_emph_cfg *swing_pre_emph_cfg;
 	const struct phy_ver_ops *ver_ops;
 };
@@ -186,11 +179,15 @@ static const struct qcom_edp_swing_pre_emph_cfg edp_phy_swing_pre_emph_cfg = {
 	.pre_emphasis_hbr3_hbr2 = &edp_pre_emp_hbr2_hbr3,
 };
 
+static const u8 edp_phy_aux_cfg_v4[10] = {
+	0x00, 0x13, 0x24, 0x00, 0x0a, 0x26, 0x0a, 0x03, 0x37, 0x03
+};
+
 static int qcom_edp_phy_init(struct phy *phy)
 {
 	struct qcom_edp *edp = phy_get_drvdata(phy);
+	u8 aux_cfg[DP_AUX_CFG_SIZE];
 	int ret;
-	u8 cfg8;
 
 	ret = regulator_bulk_enable(ARRAY_SIZE(edp->supplies), edp->supplies);
 	if (ret)
@@ -200,6 +197,8 @@ static int qcom_edp_phy_init(struct phy *phy)
 	if (ret)
 		goto out_disable_supplies;
 
+	memcpy(aux_cfg, edp->cfg->aux_cfg, sizeof(aux_cfg));
+
 	writel(DP_PHY_PD_CTL_PWRDN | DP_PHY_PD_CTL_AUX_PWRDN |
 	       DP_PHY_PD_CTL_PLL_PWRDN | DP_PHY_PD_CTL_DP_CLAMP_EN,
 	       edp->edp + DP_PHY_PD_CTL);
@@ -222,22 +221,12 @@ static int qcom_edp_phy_init(struct phy *phy)
 	 * even needed.
 	 */
 	if (edp->cfg->swing_pre_emph_cfg && !edp->is_edp)
-		cfg8 = 0xb7;
-	else
-		cfg8 = 0x37;
+		aux_cfg[8] = 0xb7;
 
 	writel(0xfc, edp->edp + DP_PHY_MODE);
 
-	writel(0x00, edp->edp + DP_PHY_AUX_CFG0);
-	writel(0x13, edp->edp + DP_PHY_AUX_CFG1);
-	writel(0x24, edp->edp + DP_PHY_AUX_CFG2);
-	writel(0x00, edp->edp + DP_PHY_AUX_CFG3);
-	writel(0x0a, edp->edp + DP_PHY_AUX_CFG4);
-	writel(0x26, edp->edp + DP_PHY_AUX_CFG5);
-	writel(0x0a, edp->edp + DP_PHY_AUX_CFG6);
-	writel(0x03, edp->edp + DP_PHY_AUX_CFG7);
-	writel(cfg8, edp->edp + DP_PHY_AUX_CFG8);
-	writel(0x03, edp->edp + DP_PHY_AUX_CFG9);
+	for (int i = 0; i < DP_AUX_CFG_SIZE; i++)
+		writel(aux_cfg[i], edp->edp + DP_PHY_AUX_CFG(i));
 
 	writel(PHY_AUX_STOP_ERR_MASK | PHY_AUX_DEC_ERR_MASK |
 	       PHY_AUX_SYNC_ERR_MASK | PHY_AUX_ALIGN_ERR_MASK |
@@ -519,16 +508,19 @@ static const struct phy_ver_ops qcom_edp_phy_ops_v4 = {
 };
 
 static const struct qcom_edp_phy_cfg sc7280_dp_phy_cfg = {
+	.aux_cfg = edp_phy_aux_cfg_v4,
 	.ver_ops = &qcom_edp_phy_ops_v4,
 };
 
 static const struct qcom_edp_phy_cfg sc8280xp_dp_phy_cfg = {
+	.aux_cfg = edp_phy_aux_cfg_v4,
 	.swing_pre_emph_cfg = &dp_phy_swing_pre_emph_cfg,
 	.ver_ops = &qcom_edp_phy_ops_v4,
 };
 
 static const struct qcom_edp_phy_cfg sc8280xp_edp_phy_cfg = {
 	.is_edp = true,
+	.aux_cfg = edp_phy_aux_cfg_v4,
 	.swing_pre_emph_cfg = &edp_phy_swing_pre_emph_cfg,
 	.ver_ops = &qcom_edp_phy_ops_v4,
 };
@@ -707,6 +699,7 @@ static const struct phy_ver_ops qcom_edp_phy_ops_v6 = {
 };
 
 static struct qcom_edp_phy_cfg x1e80100_phy_cfg = {
+	.aux_cfg = edp_phy_aux_cfg_v4,
 	.swing_pre_emph_cfg = &dp_phy_swing_pre_emph_cfg,
 	.ver_ops = &qcom_edp_phy_ops_v6,
 };

From 3f12bf16213c30d8e645027efd94a19c13ee0253 Mon Sep 17 00:00:00 2001
From: Soutrik Mukhopadhyay <quic_mukhopad@quicinc.com>
Date: Fri, 4 Oct 2024 16:00:44 +0530
Subject: [PATCH 0444/1530] phy: qcom: edp: Add support for eDP PHY on SA8775P

Add support for eDP PHY v5 found on the Qualcomm SA8775P platform.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Soutrik Mukhopadhyay <quic_mukhopad@quicinc.com>
Link: https://lore.kernel.org/r/20241004103046.22209-4-quic_mukhopad@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-edp.c | 33 +++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/drivers/phy/qualcomm/phy-qcom-edp.c b/drivers/phy/qualcomm/phy-qcom-edp.c
index 2ecff164ec44f..f1b51018683d5 100644
--- a/drivers/phy/qualcomm/phy-qcom-edp.c
+++ b/drivers/phy/qualcomm/phy-qcom-edp.c
@@ -183,6 +183,31 @@ static const u8 edp_phy_aux_cfg_v4[10] = {
 	0x00, 0x13, 0x24, 0x00, 0x0a, 0x26, 0x0a, 0x03, 0x37, 0x03
 };
 
+static const u8 edp_pre_emp_hbr_rbr_v5[4][4] = {
+	{ 0x05, 0x11, 0x17, 0x1d },
+	{ 0x05, 0x11, 0x18, 0xff },
+	{ 0x06, 0x11, 0xff, 0xff },
+	{ 0x00, 0xff, 0xff, 0xff }
+};
+
+static const u8 edp_pre_emp_hbr2_hbr3_v5[4][4] = {
+	{ 0x0c, 0x15, 0x19, 0x1e },
+	{ 0x0b, 0x15, 0x19, 0xff },
+	{ 0x0e, 0x14, 0xff, 0xff },
+	{ 0x0d, 0xff, 0xff, 0xff }
+};
+
+static const struct qcom_edp_swing_pre_emph_cfg edp_phy_swing_pre_emph_cfg_v5 = {
+	.swing_hbr_rbr = &edp_swing_hbr_rbr,
+	.swing_hbr3_hbr2 = &edp_swing_hbr2_hbr3,
+	.pre_emphasis_hbr_rbr = &edp_pre_emp_hbr_rbr_v5,
+	.pre_emphasis_hbr3_hbr2 = &edp_pre_emp_hbr2_hbr3_v5,
+};
+
+static const u8 edp_phy_aux_cfg_v5[10] = {
+	0x00, 0x13, 0xa4, 0x00, 0x0a, 0x26, 0x0a, 0x03, 0x37, 0x03
+};
+
 static int qcom_edp_phy_init(struct phy *phy)
 {
 	struct qcom_edp *edp = phy_get_drvdata(phy);
@@ -507,6 +532,13 @@ static const struct phy_ver_ops qcom_edp_phy_ops_v4 = {
 	.com_configure_ssc	= qcom_edp_com_configure_ssc_v4,
 };
 
+static const struct qcom_edp_phy_cfg sa8775p_dp_phy_cfg = {
+	.is_edp = false,
+	.aux_cfg = edp_phy_aux_cfg_v5,
+	.swing_pre_emph_cfg = &edp_phy_swing_pre_emph_cfg_v5,
+	.ver_ops = &qcom_edp_phy_ops_v4,
+};
+
 static const struct qcom_edp_phy_cfg sc7280_dp_phy_cfg = {
 	.aux_cfg = edp_phy_aux_cfg_v4,
 	.ver_ops = &qcom_edp_phy_ops_v4,
@@ -1101,6 +1133,7 @@ static int qcom_edp_phy_probe(struct platform_device *pdev)
 }
 
 static const struct of_device_id qcom_edp_phy_match_table[] = {
+	{ .compatible = "qcom,sa8775p-edp-phy", .data = &sa8775p_dp_phy_cfg, },
 	{ .compatible = "qcom,sc7280-edp-phy", .data = &sc7280_dp_phy_cfg, },
 	{ .compatible = "qcom,sc8180x-edp-phy", .data = &sc7280_dp_phy_cfg, },
 	{ .compatible = "qcom,sc8280xp-dp-phy", .data = &sc8280xp_dp_phy_cfg, },

From 2ac03d0811b94c2397d5ec3c82a65a112aeab5b0 Mon Sep 17 00:00:00 2001
From: Macpaul Lin <macpaul.lin@mediatek.com>
Date: Sat, 12 Oct 2024 11:50:16 +0800
Subject: [PATCH 0445/1530] dt-bindings: phy: mediatek: tphy: add a property
 for power-domains

Include the MediaTek TPHY in a power domain.  Add the 'power-domains'
property in the Device Tree (DT) Schema and set 'maxItems: 1'.

Also, include a reminder in the description of the 'power-domains'
property.

Signed-off-by: Macpaul Lin <macpaul.lin@mediatek.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20241012035016.17667-1-macpaul.lin@mediatek.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/phy/mediatek,tphy.yaml         | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml b/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml
index 423b7c4e62f2a..6be3aa4557e55 100644
--- a/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml
+++ b/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml
@@ -125,6 +125,16 @@ properties:
     $ref: /schemas/types.yaml#/definitions/uint32
     default: 28
 
+  power-domains:
+    description:
+      The TPHY of MediaTek should exist within a power domain. The
+      developer should be aware that the hardware design of MediaTek TPHY
+      does not require the addition of MTCMOS. If the power to the TPHY
+      is turned off, it will impact other functions. From the current
+      perspective of USB hardware design, even if MTCMOS is added to the
+      TPHY, it should remain always on.
+    maxItems: 1
+
 # Required child node:
 patternProperties:
   "^(usb|pcie|sata)-phy@[0-9a-f]+$":

From 54234e3a69324c900715ccd8e0e17e7eb1bb47cd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@baylibre.com>
Date: Wed, 9 Oct 2024 08:53:07 +0200
Subject: [PATCH 0446/1530] phy: Switch back to struct
 platform_driver::remove()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 0edb555a65d1 ("platform: Make platform_driver::remove()
return void") .remove() is (again) the right callback to implement for
platform drivers.

Convert all platform drivers below drivers/phy/ to use .remove(), with
the eventual goal to drop struct platform_driver::remove_new(). As
.remove() and .remove_new() have the same prototypes, conversion is done
by just changing the structure member name in the driver initializer.

While touching these files, make indention of the struct initializer
consistent in several files.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Link: https://lore.kernel.org/r/20241009065307.504930-2-u.kleine-koenig@baylibre.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/allwinner/phy-sun4i-usb.c            |  8 ++++----
 drivers/phy/broadcom/phy-brcm-usb.c              |  2 +-
 drivers/phy/cadence/cdns-dphy.c                  |  2 +-
 drivers/phy/cadence/phy-cadence-sierra.c         |  2 +-
 drivers/phy/cadence/phy-cadence-torrent.c        |  4 ++--
 drivers/phy/freescale/phy-fsl-imx8qm-lvds-phy.c  |  6 +++---
 drivers/phy/freescale/phy-fsl-lynx-28g.c         |  6 +++---
 drivers/phy/freescale/phy-fsl-samsung-hdmi.c     |  4 ++--
 drivers/phy/intel/phy-intel-lgm-combo.c          |  2 +-
 drivers/phy/motorola/phy-cpcap-usb.c             |  2 +-
 drivers/phy/motorola/phy-mapphone-mdm6600.c      |  2 +-
 drivers/phy/phy-lgm-usb.c                        |  2 +-
 drivers/phy/qualcomm/phy-qcom-apq8064-sata.c     | 10 +++++-----
 drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c   |  2 +-
 drivers/phy/qualcomm/phy-qcom-ipq806x-sata.c     |  8 ++++----
 drivers/phy/realtek/phy-rtk-usb2.c               |  2 +-
 drivers/phy/realtek/phy-rtk-usb3.c               |  2 +-
 drivers/phy/renesas/phy-rcar-gen3-pcie.c         |  8 ++++----
 drivers/phy/renesas/phy-rcar-gen3-usb2.c         |  2 +-
 drivers/phy/renesas/phy-rcar-gen3-usb3.c         |  8 ++++----
 drivers/phy/renesas/r8a779f0-ether-serdes.c      |  2 +-
 drivers/phy/rockchip/phy-rockchip-inno-csidphy.c |  2 +-
 drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c |  2 +-
 drivers/phy/rockchip/phy-rockchip-inno-hdmi.c    |  4 ++--
 drivers/phy/rockchip/phy-rockchip-typec.c        |  2 +-
 drivers/phy/st/phy-stm32-usbphyc.c               |  2 +-
 drivers/phy/tegra/xusb.c                         |  2 +-
 drivers/phy/ti/phy-am654-serdes.c                |  2 +-
 drivers/phy/ti/phy-da8xx-usb.c                   |  4 ++--
 drivers/phy/ti/phy-dm816x-usb.c                  |  2 +-
 drivers/phy/ti/phy-j721e-wiz.c                   |  2 +-
 drivers/phy/ti/phy-omap-usb2.c                   |  2 +-
 drivers/phy/ti/phy-ti-pipe3.c                    |  2 +-
 drivers/phy/ti/phy-twl4030-usb.c                 |  2 +-
 drivers/phy/xilinx/phy-zynqmp.c                  |  2 +-
 35 files changed, 59 insertions(+), 59 deletions(-)

diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c
index b0f19e9506010..cd159a71b23c3 100644
--- a/drivers/phy/allwinner/phy-sun4i-usb.c
+++ b/drivers/phy/allwinner/phy-sun4i-usb.c
@@ -1049,11 +1049,11 @@ static const struct of_device_id sun4i_usb_phy_of_match[] = {
 MODULE_DEVICE_TABLE(of, sun4i_usb_phy_of_match);
 
 static struct platform_driver sun4i_usb_phy_driver = {
-	.probe	= sun4i_usb_phy_probe,
-	.remove_new = sun4i_usb_phy_remove,
+	.probe = sun4i_usb_phy_probe,
+	.remove = sun4i_usb_phy_remove,
 	.driver = {
-		.of_match_table	= sun4i_usb_phy_of_match,
-		.name  = "sun4i-usb-phy",
+		.of_match_table= sun4i_usb_phy_of_match,
+		.name = "sun4i-usb-phy",
 	}
 };
 module_platform_driver(sun4i_usb_phy_driver);
diff --git a/drivers/phy/broadcom/phy-brcm-usb.c b/drivers/phy/broadcom/phy-brcm-usb.c
index ad2eec0956016..6362ca5b7fb6b 100644
--- a/drivers/phy/broadcom/phy-brcm-usb.c
+++ b/drivers/phy/broadcom/phy-brcm-usb.c
@@ -667,7 +667,7 @@ MODULE_DEVICE_TABLE(of, brcm_usb_dt_ids);
 
 static struct platform_driver brcm_usb_driver = {
 	.probe		= brcm_usb_phy_probe,
-	.remove_new	= brcm_usb_phy_remove,
+	.remove		= brcm_usb_phy_remove,
 	.driver		= {
 		.name	= "brcmstb-usb-phy",
 		.pm = &brcm_usb_phy_pm_ops,
diff --git a/drivers/phy/cadence/cdns-dphy.c b/drivers/phy/cadence/cdns-dphy.c
index dddb66de6dba1..ed87a3970f834 100644
--- a/drivers/phy/cadence/cdns-dphy.c
+++ b/drivers/phy/cadence/cdns-dphy.c
@@ -472,7 +472,7 @@ MODULE_DEVICE_TABLE(of, cdns_dphy_of_match);
 
 static struct platform_driver cdns_dphy_platform_driver = {
 	.probe		= cdns_dphy_probe,
-	.remove_new	= cdns_dphy_remove,
+	.remove		= cdns_dphy_remove,
 	.driver		= {
 		.name		= "cdns-mipi-dphy",
 		.of_match_table	= cdns_dphy_of_match,
diff --git a/drivers/phy/cadence/phy-cadence-sierra.c b/drivers/phy/cadence/phy-cadence-sierra.c
index aeec6eb6be237..e739d9d51d5b8 100644
--- a/drivers/phy/cadence/phy-cadence-sierra.c
+++ b/drivers/phy/cadence/phy-cadence-sierra.c
@@ -2730,7 +2730,7 @@ MODULE_DEVICE_TABLE(of, cdns_sierra_id_table);
 
 static struct platform_driver cdns_sierra_driver = {
 	.probe		= cdns_sierra_phy_probe,
-	.remove_new	= cdns_sierra_phy_remove,
+	.remove		= cdns_sierra_phy_remove,
 	.driver		= {
 		.name	= "cdns-sierra-phy",
 		.of_match_table = cdns_sierra_id_table,
diff --git a/drivers/phy/cadence/phy-cadence-torrent.c b/drivers/phy/cadence/phy-cadence-torrent.c
index 8bbbbb87bb22e..a281c0dfae974 100644
--- a/drivers/phy/cadence/phy-cadence-torrent.c
+++ b/drivers/phy/cadence/phy-cadence-torrent.c
@@ -5440,8 +5440,8 @@ MODULE_DEVICE_TABLE(of, cdns_torrent_phy_of_match);
 
 static struct platform_driver cdns_torrent_phy_driver = {
 	.probe	= cdns_torrent_phy_probe,
-	.remove_new = cdns_torrent_phy_remove,
-	.driver = {
+	.remove	= cdns_torrent_phy_remove,
+	.driver	= {
 		.name	= "cdns-torrent-phy",
 		.of_match_table	= cdns_torrent_phy_of_match,
 		.pm	= pm_sleep_ptr(&cdns_torrent_phy_pm_ops),
diff --git a/drivers/phy/freescale/phy-fsl-imx8qm-lvds-phy.c b/drivers/phy/freescale/phy-fsl-imx8qm-lvds-phy.c
index 38388dd04bdc1..7aef2f59e8eb4 100644
--- a/drivers/phy/freescale/phy-fsl-imx8qm-lvds-phy.c
+++ b/drivers/phy/freescale/phy-fsl-imx8qm-lvds-phy.c
@@ -433,12 +433,12 @@ static const struct of_device_id mixel_lvds_phy_of_match[] = {
 MODULE_DEVICE_TABLE(of, mixel_lvds_phy_of_match);
 
 static struct platform_driver mixel_lvds_phy_driver = {
-	.probe	= mixel_lvds_phy_probe,
-	.remove_new = mixel_lvds_phy_remove,
+	.probe = mixel_lvds_phy_probe,
+	.remove = mixel_lvds_phy_remove,
 	.driver = {
 		.pm = &mixel_lvds_phy_pm_ops,
 		.name = "mixel-lvds-phy",
-		.of_match_table	= mixel_lvds_phy_of_match,
+		.of_match_table = mixel_lvds_phy_of_match,
 	}
 };
 module_platform_driver(mixel_lvds_phy_driver);
diff --git a/drivers/phy/freescale/phy-fsl-lynx-28g.c b/drivers/phy/freescale/phy-fsl-lynx-28g.c
index b86da8e9daa46..f7994e8983c8e 100644
--- a/drivers/phy/freescale/phy-fsl-lynx-28g.c
+++ b/drivers/phy/freescale/phy-fsl-lynx-28g.c
@@ -631,9 +631,9 @@ static const struct of_device_id lynx_28g_of_match_table[] = {
 MODULE_DEVICE_TABLE(of, lynx_28g_of_match_table);
 
 static struct platform_driver lynx_28g_driver = {
-	.probe	= lynx_28g_probe,
-	.remove_new = lynx_28g_remove,
-	.driver	= {
+	.probe = lynx_28g_probe,
+	.remove = lynx_28g_remove,
+	.driver = {
 		.name = "lynx-28g",
 		.of_match_table = lynx_28g_of_match_table,
 	},
diff --git a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
index a08c1bfa657c5..2c8038864357b 100644
--- a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
+++ b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
@@ -749,8 +749,8 @@ static const struct of_device_id fsl_samsung_hdmi_phy_of_match[] = {
 MODULE_DEVICE_TABLE(of, fsl_samsung_hdmi_phy_of_match);
 
 static struct platform_driver fsl_samsung_hdmi_phy_driver = {
-	.probe  = fsl_samsung_hdmi_phy_probe,
-	.remove_new = fsl_samsung_hdmi_phy_remove,
+	.probe = fsl_samsung_hdmi_phy_probe,
+	.remove = fsl_samsung_hdmi_phy_remove,
 	.driver = {
 		.name = "fsl-samsung-hdmi-phy",
 		.of_match_table = fsl_samsung_hdmi_phy_of_match,
diff --git a/drivers/phy/intel/phy-intel-lgm-combo.c b/drivers/phy/intel/phy-intel-lgm-combo.c
index f8e3054a9e597..9ee3cf61cdd00 100644
--- a/drivers/phy/intel/phy-intel-lgm-combo.c
+++ b/drivers/phy/intel/phy-intel-lgm-combo.c
@@ -605,7 +605,7 @@ static const struct of_device_id of_intel_cbphy_match[] = {
 
 static struct platform_driver intel_cbphy_driver = {
 	.probe = intel_cbphy_probe,
-	.remove_new = intel_cbphy_remove,
+	.remove = intel_cbphy_remove,
 	.driver = {
 		.name = "intel-combo-phy",
 		.of_match_table = of_intel_cbphy_match,
diff --git a/drivers/phy/motorola/phy-cpcap-usb.c b/drivers/phy/motorola/phy-cpcap-usb.c
index 7bbf729a7c90a..7cb020dd3423c 100644
--- a/drivers/phy/motorola/phy-cpcap-usb.c
+++ b/drivers/phy/motorola/phy-cpcap-usb.c
@@ -704,7 +704,7 @@ static void cpcap_usb_phy_remove(struct platform_device *pdev)
 
 static struct platform_driver cpcap_usb_phy_driver = {
 	.probe		= cpcap_usb_phy_probe,
-	.remove_new	= cpcap_usb_phy_remove,
+	.remove		= cpcap_usb_phy_remove,
 	.driver		= {
 		.name	= "cpcap-usb-phy",
 		.of_match_table = of_match_ptr(cpcap_usb_phy_id_table),
diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c
index 376d023a0aa90..152344e4f7e44 100644
--- a/drivers/phy/motorola/phy-mapphone-mdm6600.c
+++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c
@@ -655,7 +655,7 @@ static void phy_mdm6600_remove(struct platform_device *pdev)
 
 static struct platform_driver phy_mdm6600_driver = {
 	.probe = phy_mdm6600_probe,
-	.remove_new = phy_mdm6600_remove,
+	.remove = phy_mdm6600_remove,
 	.driver = {
 		.name = "phy-mapphone-mdm6600",
 		.pm = &phy_mdm6600_pm_ops,
diff --git a/drivers/phy/phy-lgm-usb.c b/drivers/phy/phy-lgm-usb.c
index 410729c7f513d..eb7c6fed20d34 100644
--- a/drivers/phy/phy-lgm-usb.c
+++ b/drivers/phy/phy-lgm-usb.c
@@ -271,7 +271,7 @@ static struct platform_driver lgm_phy_driver = {
 		.of_match_table = intel_usb_phy_dt_ids,
 	},
 	.probe = phy_probe,
-	.remove_new = phy_remove,
+	.remove = phy_remove,
 };
 
 module_platform_driver(lgm_phy_driver);
diff --git a/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c b/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c
index 3642a5d4f2f3b..cae290a6e19fc 100644
--- a/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c
+++ b/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c
@@ -257,12 +257,12 @@ static const struct of_device_id qcom_apq8064_sata_phy_of_match[] = {
 MODULE_DEVICE_TABLE(of, qcom_apq8064_sata_phy_of_match);
 
 static struct platform_driver qcom_apq8064_sata_phy_driver = {
-	.probe	= qcom_apq8064_sata_phy_probe,
-	.remove_new = qcom_apq8064_sata_phy_remove,
+	.probe = qcom_apq8064_sata_phy_probe,
+	.remove = qcom_apq8064_sata_phy_remove,
 	.driver = {
-		.name	= "qcom-apq8064-sata-phy",
-		.of_match_table	= qcom_apq8064_sata_phy_of_match,
-	}
+		.name = "qcom-apq8064-sata-phy",
+		.of_match_table = qcom_apq8064_sata_phy_of_match,
+	},
 };
 module_platform_driver(qcom_apq8064_sata_phy_driver);
 
diff --git a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
index 68cc8e24f3836..6bd1b3c75c779 100644
--- a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
+++ b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
@@ -294,7 +294,7 @@ MODULE_DEVICE_TABLE(of, eusb2_repeater_of_match_table);
 
 static struct platform_driver eusb2_repeater_driver = {
 	.probe		= eusb2_repeater_probe,
-	.remove_new	= eusb2_repeater_remove,
+	.remove		= eusb2_repeater_remove,
 	.driver = {
 		.name	= "qcom-eusb2-repeater",
 		.of_match_table = eusb2_repeater_of_match_table,
diff --git a/drivers/phy/qualcomm/phy-qcom-ipq806x-sata.c b/drivers/phy/qualcomm/phy-qcom-ipq806x-sata.c
index f0a72b82c770b..f5eb0bdac418b 100644
--- a/drivers/phy/qualcomm/phy-qcom-ipq806x-sata.c
+++ b/drivers/phy/qualcomm/phy-qcom-ipq806x-sata.c
@@ -184,11 +184,11 @@ static const struct of_device_id qcom_ipq806x_sata_phy_of_match[] = {
 MODULE_DEVICE_TABLE(of, qcom_ipq806x_sata_phy_of_match);
 
 static struct platform_driver qcom_ipq806x_sata_phy_driver = {
-	.probe	= qcom_ipq806x_sata_phy_probe,
-	.remove_new = qcom_ipq806x_sata_phy_remove,
+	.probe = qcom_ipq806x_sata_phy_probe,
+	.remove = qcom_ipq806x_sata_phy_remove,
 	.driver = {
-		.name	= "qcom-ipq806x-sata-phy",
-		.of_match_table	= qcom_ipq806x_sata_phy_of_match,
+		.name = "qcom-ipq806x-sata-phy",
+		.of_match_table = qcom_ipq806x_sata_phy_of_match,
 	}
 };
 module_platform_driver(qcom_ipq806x_sata_phy_driver);
diff --git a/drivers/phy/realtek/phy-rtk-usb2.c b/drivers/phy/realtek/phy-rtk-usb2.c
index e3ad7cea51099..c3e131a64131a 100644
--- a/drivers/phy/realtek/phy-rtk-usb2.c
+++ b/drivers/phy/realtek/phy-rtk-usb2.c
@@ -1298,7 +1298,7 @@ MODULE_DEVICE_TABLE(of, usbphy_rtk_dt_match);
 
 static struct platform_driver rtk_usb2phy_driver = {
 	.probe		= rtk_usb2phy_probe,
-	.remove_new	= rtk_usb2phy_remove,
+	.remove		= rtk_usb2phy_remove,
 	.driver		= {
 		.name	= "rtk-usb2phy",
 		.of_match_table = usbphy_rtk_dt_match,
diff --git a/drivers/phy/realtek/phy-rtk-usb3.c b/drivers/phy/realtek/phy-rtk-usb3.c
index dfcf4b921bba6..0cef29a7ddd95 100644
--- a/drivers/phy/realtek/phy-rtk-usb3.c
+++ b/drivers/phy/realtek/phy-rtk-usb3.c
@@ -734,7 +734,7 @@ MODULE_DEVICE_TABLE(of, usbphy_rtk_dt_match);
 
 static struct platform_driver rtk_usb3phy_driver = {
 	.probe		= rtk_usb3phy_probe,
-	.remove_new	= rtk_usb3phy_remove,
+	.remove		= rtk_usb3phy_remove,
 	.driver		= {
 		.name	= "rtk-usb3phy",
 		.of_match_table = usbphy_rtk_dt_match,
diff --git a/drivers/phy/renesas/phy-rcar-gen3-pcie.c b/drivers/phy/renesas/phy-rcar-gen3-pcie.c
index 0ce7e9c944447..feca4cb2ff4d1 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-pcie.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-pcie.c
@@ -132,11 +132,11 @@ static void rcar_gen3_phy_pcie_remove(struct platform_device *pdev)
 
 static struct platform_driver rcar_gen3_phy_driver = {
 	.driver = {
-		.name		= "phy_rcar_gen3_pcie",
-		.of_match_table	= rcar_gen3_phy_pcie_match_table,
+		.name = "phy_rcar_gen3_pcie",
+		.of_match_table = rcar_gen3_phy_pcie_match_table,
 	},
-	.probe	= rcar_gen3_phy_pcie_probe,
-	.remove_new = rcar_gen3_phy_pcie_remove,
+	.probe = rcar_gen3_phy_pcie_probe,
+	.remove = rcar_gen3_phy_pcie_remove,
 };
 
 module_platform_driver(rcar_gen3_phy_driver);
diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
index 58e1233051526..775f4f973a6cc 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
@@ -825,7 +825,7 @@ static struct platform_driver rcar_gen3_phy_usb2_driver = {
 		.of_match_table	= rcar_gen3_phy_usb2_match_table,
 	},
 	.probe	= rcar_gen3_phy_usb2_probe,
-	.remove_new = rcar_gen3_phy_usb2_remove,
+	.remove = rcar_gen3_phy_usb2_remove,
 };
 module_platform_driver(rcar_gen3_phy_usb2_driver);
 
diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb3.c b/drivers/phy/renesas/phy-rcar-gen3-usb3.c
index e2d630edd992d..5c267d148c90b 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb3.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb3.c
@@ -206,11 +206,11 @@ static void rcar_gen3_phy_usb3_remove(struct platform_device *pdev)
 
 static struct platform_driver rcar_gen3_phy_usb3_driver = {
 	.driver = {
-		.name		= "phy_rcar_gen3_usb3",
-		.of_match_table	= rcar_gen3_phy_usb3_match_table,
+		.name = "phy_rcar_gen3_usb3",
+		.of_match_table = rcar_gen3_phy_usb3_match_table,
 	},
-	.probe	= rcar_gen3_phy_usb3_probe,
-	.remove_new = rcar_gen3_phy_usb3_remove,
+	.probe = rcar_gen3_phy_usb3_probe,
+	.remove = rcar_gen3_phy_usb3_remove,
 };
 module_platform_driver(rcar_gen3_phy_usb3_driver);
 
diff --git a/drivers/phy/renesas/r8a779f0-ether-serdes.c b/drivers/phy/renesas/r8a779f0-ether-serdes.c
index f1f1da4a0b1fe..3b2d8cef75e52 100644
--- a/drivers/phy/renesas/r8a779f0-ether-serdes.c
+++ b/drivers/phy/renesas/r8a779f0-ether-serdes.c
@@ -404,7 +404,7 @@ static void r8a779f0_eth_serdes_remove(struct platform_device *pdev)
 
 static struct platform_driver r8a779f0_eth_serdes_driver_platform = {
 	.probe = r8a779f0_eth_serdes_probe,
-	.remove_new = r8a779f0_eth_serdes_remove,
+	.remove = r8a779f0_eth_serdes_remove,
 	.driver = {
 		.name = "r8a779f0_eth_serdes",
 		.of_match_table = r8a779f0_eth_serdes_of_table,
diff --git a/drivers/phy/rockchip/phy-rockchip-inno-csidphy.c b/drivers/phy/rockchip/phy-rockchip-inno-csidphy.c
index 98c92d6c482fe..2ab99e1d47ebe 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-csidphy.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-csidphy.c
@@ -472,7 +472,7 @@ static struct platform_driver rockchip_inno_csidphy_driver = {
 		.of_match_table = rockchip_inno_csidphy_match_id,
 	},
 	.probe = rockchip_inno_csidphy_probe,
-	.remove_new = rockchip_inno_csidphy_remove,
+	.remove = rockchip_inno_csidphy_remove,
 };
 
 module_platform_driver(rockchip_inno_csidphy_driver);
diff --git a/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c b/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c
index 6405943a26767..d5b1a4e2f7d34 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c
@@ -784,7 +784,7 @@ static struct platform_driver inno_dsidphy_driver = {
 		.of_match_table	= of_match_ptr(inno_dsidphy_of_match),
 	},
 	.probe = inno_dsidphy_probe,
-	.remove_new = inno_dsidphy_remove,
+	.remove = inno_dsidphy_remove,
 };
 module_platform_driver(inno_dsidphy_driver);
 
diff --git a/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c b/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c
index 053bd62e31ba7..8dcc2bb777b54 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c
@@ -1424,8 +1424,8 @@ static const struct of_device_id inno_hdmi_phy_of_match[] = {
 MODULE_DEVICE_TABLE(of, inno_hdmi_phy_of_match);
 
 static struct platform_driver inno_hdmi_phy_driver = {
-	.probe  = inno_hdmi_phy_probe,
-	.remove_new = inno_hdmi_phy_remove,
+	.probe = inno_hdmi_phy_probe,
+	.remove = inno_hdmi_phy_remove,
 	.driver = {
 		.name = "inno-hdmi-phy",
 		.of_match_table = inno_hdmi_phy_of_match,
diff --git a/drivers/phy/rockchip/phy-rockchip-typec.c b/drivers/phy/rockchip/phy-rockchip-typec.c
index 4efcb78b0ab18..122ae0fdc785e 100644
--- a/drivers/phy/rockchip/phy-rockchip-typec.c
+++ b/drivers/phy/rockchip/phy-rockchip-typec.c
@@ -1210,7 +1210,7 @@ MODULE_DEVICE_TABLE(of, rockchip_typec_phy_dt_ids);
 
 static struct platform_driver rockchip_typec_phy_driver = {
 	.probe		= rockchip_typec_phy_probe,
-	.remove_new	= rockchip_typec_phy_remove,
+	.remove		= rockchip_typec_phy_remove,
 	.driver		= {
 		.name	= "rockchip-typec-phy",
 		.of_match_table = rockchip_typec_phy_dt_ids,
diff --git a/drivers/phy/st/phy-stm32-usbphyc.c b/drivers/phy/st/phy-stm32-usbphyc.c
index 9dbe60dcf3190..b917cd413de73 100644
--- a/drivers/phy/st/phy-stm32-usbphyc.c
+++ b/drivers/phy/st/phy-stm32-usbphyc.c
@@ -812,7 +812,7 @@ MODULE_DEVICE_TABLE(of, stm32_usbphyc_of_match);
 
 static struct platform_driver stm32_usbphyc_driver = {
 	.probe = stm32_usbphyc_probe,
-	.remove_new = stm32_usbphyc_remove,
+	.remove = stm32_usbphyc_remove,
 	.driver = {
 		.of_match_table = stm32_usbphyc_of_match,
 		.name = "stm32-usbphyc",
diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c
index cfdb54b6070a4..480c1b5c56e25 100644
--- a/drivers/phy/tegra/xusb.c
+++ b/drivers/phy/tegra/xusb.c
@@ -1325,7 +1325,7 @@ static struct platform_driver tegra_xusb_padctl_driver = {
 		.pm = &tegra_xusb_padctl_pm_ops,
 	},
 	.probe = tegra_xusb_padctl_probe,
-	.remove_new = tegra_xusb_padctl_remove,
+	.remove = tegra_xusb_padctl_remove,
 };
 module_platform_driver(tegra_xusb_padctl_driver);
 
diff --git a/drivers/phy/ti/phy-am654-serdes.c b/drivers/phy/ti/phy-am654-serdes.c
index 3bf3aff4b1c74..431b223996e0a 100644
--- a/drivers/phy/ti/phy-am654-serdes.c
+++ b/drivers/phy/ti/phy-am654-serdes.c
@@ -837,7 +837,7 @@ static void serdes_am654_remove(struct platform_device *pdev)
 
 static struct platform_driver serdes_am654_driver = {
 	.probe		= serdes_am654_probe,
-	.remove_new	= serdes_am654_remove,
+	.remove		= serdes_am654_remove,
 	.driver		= {
 		.name	= "phy-am654",
 		.of_match_table = serdes_am654_id_table,
diff --git a/drivers/phy/ti/phy-da8xx-usb.c b/drivers/phy/ti/phy-da8xx-usb.c
index 68aa595b6ad8d..1d81a1e6ec6b6 100644
--- a/drivers/phy/ti/phy-da8xx-usb.c
+++ b/drivers/phy/ti/phy-da8xx-usb.c
@@ -277,11 +277,11 @@ MODULE_DEVICE_TABLE(of, da8xx_usb_phy_ids);
 
 static struct platform_driver da8xx_usb_phy_driver = {
 	.probe	= da8xx_usb_phy_probe,
-	.remove_new = da8xx_usb_phy_remove,
+	.remove	= da8xx_usb_phy_remove,
 	.driver	= {
 		.name	= "da8xx-usb-phy",
 		.pm	= &da8xx_usb_phy_pm_ops,
-		.of_match_table = da8xx_usb_phy_ids,
+		.of_match_table	= da8xx_usb_phy_ids,
 	},
 };
 
diff --git a/drivers/phy/ti/phy-dm816x-usb.c b/drivers/phy/ti/phy-dm816x-usb.c
index d5ae972a31fbc..e8f842d4e841b 100644
--- a/drivers/phy/ti/phy-dm816x-usb.c
+++ b/drivers/phy/ti/phy-dm816x-usb.c
@@ -259,7 +259,7 @@ static void dm816x_usb_phy_remove(struct platform_device *pdev)
 
 static struct platform_driver dm816x_usb_phy_driver = {
 	.probe		= dm816x_usb_phy_probe,
-	.remove_new	= dm816x_usb_phy_remove,
+	.remove		= dm816x_usb_phy_remove,
 	.driver		= {
 		.name	= "dm816x-usb-phy",
 		.pm	= &dm816x_usb_phy_pm_ops,
diff --git a/drivers/phy/ti/phy-j721e-wiz.c b/drivers/phy/ti/phy-j721e-wiz.c
index a6c0c5607ffd7..fd46dfe99c7f3 100644
--- a/drivers/phy/ti/phy-j721e-wiz.c
+++ b/drivers/phy/ti/phy-j721e-wiz.c
@@ -1685,7 +1685,7 @@ static DEFINE_NOIRQ_DEV_PM_OPS(wiz_pm_ops, NULL, wiz_resume_noirq);
 
 static struct platform_driver wiz_driver = {
 	.probe		= wiz_probe,
-	.remove_new	= wiz_remove,
+	.remove		= wiz_remove,
 	.driver		= {
 		.name	= "wiz",
 		.of_match_table = wiz_id_table,
diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c
index 78e19b128962a..c1a0ef979142c 100644
--- a/drivers/phy/ti/phy-omap-usb2.c
+++ b/drivers/phy/ti/phy-omap-usb2.c
@@ -511,7 +511,7 @@ static void omap_usb2_remove(struct platform_device *pdev)
 
 static struct platform_driver omap_usb2_driver = {
 	.probe		= omap_usb2_probe,
-	.remove_new	= omap_usb2_remove,
+	.remove		= omap_usb2_remove,
 	.driver		= {
 		.name	= "omap-usb2",
 		.of_match_table = omap_usb2_id_table,
diff --git a/drivers/phy/ti/phy-ti-pipe3.c b/drivers/phy/ti/phy-ti-pipe3.c
index 874c1a25ce36e..da2cbacb982c6 100644
--- a/drivers/phy/ti/phy-ti-pipe3.c
+++ b/drivers/phy/ti/phy-ti-pipe3.c
@@ -920,7 +920,7 @@ MODULE_DEVICE_TABLE(of, ti_pipe3_id_table);
 
 static struct platform_driver ti_pipe3_driver = {
 	.probe		= ti_pipe3_probe,
-	.remove_new	= ti_pipe3_remove,
+	.remove		= ti_pipe3_remove,
 	.driver		= {
 		.name	= "ti-pipe3",
 		.of_match_table = ti_pipe3_id_table,
diff --git a/drivers/phy/ti/phy-twl4030-usb.c b/drivers/phy/ti/phy-twl4030-usb.c
index 6b265992d988f..6f12b38cd894f 100644
--- a/drivers/phy/ti/phy-twl4030-usb.c
+++ b/drivers/phy/ti/phy-twl4030-usb.c
@@ -834,7 +834,7 @@ MODULE_DEVICE_TABLE(of, twl4030_usb_id_table);
 
 static struct platform_driver twl4030_usb_driver = {
 	.probe		= twl4030_usb_probe,
-	.remove_new	= twl4030_usb_remove,
+	.remove		= twl4030_usb_remove,
 	.driver		= {
 		.name	= "twl4030_usb",
 		.pm	= &twl4030_usb_pm_ops,
diff --git a/drivers/phy/xilinx/phy-zynqmp.c b/drivers/phy/xilinx/phy-zynqmp.c
index e6579002f1146..05a4a59f7c407 100644
--- a/drivers/phy/xilinx/phy-zynqmp.c
+++ b/drivers/phy/xilinx/phy-zynqmp.c
@@ -1071,7 +1071,7 @@ MODULE_DEVICE_TABLE(of, xpsgtr_of_match);
 
 static struct platform_driver xpsgtr_driver = {
 	.probe = xpsgtr_probe,
-	.remove_new = xpsgtr_remove,
+	.remove = xpsgtr_remove,
 	.driver = {
 		.name = "xilinx-psgtr",
 		.of_match_table	= xpsgtr_of_match,

From de30906910f8c2a91b236ff77d7dd5edfb14bb55 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko@sntech.de>
Date: Mon, 7 Oct 2024 18:27:32 +0200
Subject: [PATCH 0447/1530] dt-bindings: phy: rk3228-hdmi-phy: convert to yaml

Convert the binding to yaml and rename it according to its first
compatible instead of the unspecific rockchip-inno-hdmi naming.

Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20241007162732.2450168-1-heiko@sntech.de
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../bindings/phy/phy-rockchip-inno-hdmi.txt   | 43 --------
 .../phy/rockchip,rk3228-hdmi-phy.yaml         | 97 +++++++++++++++++++
 2 files changed, 97 insertions(+), 43 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/phy/phy-rockchip-inno-hdmi.txt
 create mode 100644 Documentation/devicetree/bindings/phy/rockchip,rk3228-hdmi-phy.yaml

diff --git a/Documentation/devicetree/bindings/phy/phy-rockchip-inno-hdmi.txt b/Documentation/devicetree/bindings/phy/phy-rockchip-inno-hdmi.txt
deleted file mode 100644
index 710cccd5ee56e..0000000000000
--- a/Documentation/devicetree/bindings/phy/phy-rockchip-inno-hdmi.txt
+++ /dev/null
@@ -1,43 +0,0 @@
-ROCKCHIP HDMI PHY WITH INNO IP BLOCK
-
-Required properties:
- - compatible : should be one of the listed compatibles:
-	* "rockchip,rk3228-hdmi-phy",
-	* "rockchip,rk3328-hdmi-phy";
- - reg : Address and length of the hdmi phy control register set
- - clocks : phandle + clock specifier for the phy clocks
- - clock-names : string, clock name, must contain "sysclk" for system
-	  control and register configuration, "refoclk" for crystal-
-	  oscillator reference PLL clock input and "refpclk" for pclk-
-	  based refeference PLL clock input.
- - #clock-cells: should be 0.
- - clock-output-names : shall be the name for the output clock.
- - interrupts : phandle + interrupt specified for the hdmiphy interrupt
- - #phy-cells : must be 0. See ./phy-bindings.txt for details.
-
-Optional properties for rk3328-hdmi-phy:
- - nvmem-cells = phandle + nvmem specifier for the cpu-version efuse
- - nvmem-cell-names : "cpu-version" to read the chip version, required
-	  for adjustment to some frequency settings
-
-Example:
-	hdmi_phy: hdmi-phy@12030000 {
-		compatible = "rockchip,rk3228-hdmi-phy";
-		reg = <0x12030000 0x10000>;
-		#phy-cells = <0>;
-		clocks = <&cru PCLK_HDMI_PHY>, <&xin24m>, <&cru DCLK_HDMIPHY>;
-		clock-names = "sysclk", "refoclk", "refpclk";
-		#clock-cells = <0>;
-		clock-output-names = "hdmi_phy";
-		status = "disabled";
-	};
-
-Then the PHY can be used in other nodes such as:
-
-	hdmi: hdmi@200a0000 {
-		compatible = "rockchip,rk3228-dw-hdmi";
-		...
-		phys = <&hdmi_phy>;
-		phy-names = "hdmi";
-		...
-	};
diff --git a/Documentation/devicetree/bindings/phy/rockchip,rk3228-hdmi-phy.yaml b/Documentation/devicetree/bindings/phy/rockchip,rk3228-hdmi-phy.yaml
new file mode 100644
index 0000000000000..ac15bf857ef99
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/rockchip,rk3228-hdmi-phy.yaml
@@ -0,0 +1,97 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/rockchip,rk3228-hdmi-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Rockchip HDMI PHY with Innosilicon IP block
+
+maintainers:
+  - Heiko Stuebner <heiko@sntech.de>
+
+properties:
+  compatible:
+    enum:
+      - rockchip,rk3228-hdmi-phy
+      - rockchip,rk3328-hdmi-phy
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 3
+
+  clock-names:
+    items:
+      - const: sysclk
+      - const: refoclk
+      - const: refpclk
+
+  clock-output-names:
+    description:
+      The hdmiphy output clock name, that gets fed back to the CRU.
+
+  "#clock-cells":
+    const: 0
+
+  interrupts:
+    maxItems: 1
+
+  nvmem-cells:
+    maxItems: 1
+    description: A phandle + nvmem specifier for the cpu-version efuse
+      for adjustment to some frequency settings, depending on cpu-version
+
+  nvmem-cell-names:
+    items:
+      - const: cpu-version
+
+  '#phy-cells':
+    const: 0
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - clock-output-names
+  - '#clock-cells'
+  - '#phy-cells'
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: rockchip,rk3228-hdmi-phy
+
+    then:
+      properties:
+        interrupts: false
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: rockchip,rk3328-hdmi-phy
+
+    then:
+      required:
+        - interrupts
+
+additionalProperties: false
+
+examples:
+  - |
+
+    #include <dt-bindings/clock/rk3228-cru.h>
+    hdmi_phy: phy@12030000 {
+      compatible = "rockchip,rk3228-hdmi-phy";
+      reg = <0x12030000 0x10000>;
+      #phy-cells = <0>;
+      clocks = <&cru PCLK_HDMI_PHY>, <&xin24m>, <&cru DCLK_HDMI_PHY>;
+      clock-names = "sysclk", "refoclk", "refpclk";
+      #clock-cells = <0>;
+
+      clock-output-names = "hdmi_phy";
+    };

From 76b4f2a5cec59e842de4b5989eb990a2ee8cedf3 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Thu, 26 Sep 2024 15:39:47 +0800
Subject: [PATCH 0448/1530] dt-bindings: phy: mxs-usb-phy: add imx8qxp
 compatible

Add "fsl,imx8qxp-usbphy" compatible.

Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20240926073951.783869-2-xu.yang_2@nxp.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/phy/fsl,mxs-usbphy.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/phy/fsl,mxs-usbphy.yaml b/Documentation/devicetree/bindings/phy/fsl,mxs-usbphy.yaml
index ce665a2779b79..d01b7d1870405 100644
--- a/Documentation/devicetree/bindings/phy/fsl,mxs-usbphy.yaml
+++ b/Documentation/devicetree/bindings/phy/fsl,mxs-usbphy.yaml
@@ -32,6 +32,7 @@ properties:
           - enum:
               - fsl,imx8dxl-usbphy
               - fsl,imx8qm-usbphy
+              - fsl,imx8qxp-usbphy
               - fsl,imx8ulp-usbphy
           - const: fsl,imx7ulp-usbphy
 

From 2df490e7374de8e940d353cfcafd3c91242841ea Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Fri, 30 Aug 2024 11:20:45 +0300
Subject: [PATCH 0449/1530] dt-bindings: phy: add NXP PTN3222 eUSB2 to USB2
 redriver

The NXP PTN3222 is the single-port eUSB2 to USB2 redriver that performs
translation between eUSB2 and USB2 signalling schemes. It supports all
three data rates: Low Speed, Full Speed and High Speed.

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Stephan Gerhold <stephan.gerhold@linaro.org>
Link: https://lore.kernel.org/r/20240830-nxp-ptn3222-v2-1-4c6d8535cf6c@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/phy/nxp,ptn3222.yaml  | 55 +++++++++++++++++++
 1 file changed, 55 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/phy/nxp,ptn3222.yaml

diff --git a/Documentation/devicetree/bindings/phy/nxp,ptn3222.yaml b/Documentation/devicetree/bindings/phy/nxp,ptn3222.yaml
new file mode 100644
index 0000000000000..acec5bb2391d7
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/nxp,ptn3222.yaml
@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/nxp,ptn3222.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NXP PTN3222 1-port eUSB2 to USB2 redriver
+
+maintainers:
+  - Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
+
+properties:
+  compatible:
+    enum:
+      - nxp,ptn3222
+
+  reg:
+    maxItems: 1
+
+  "#phy-cells":
+    const: 0
+
+  vdd1v8-supply:
+    description: power supply (1.8V)
+
+  vdd3v3-supply:
+    description: power supply (3.3V)
+
+  reset-gpios: true
+
+required:
+  - compatible
+  - reg
+  - '#phy-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        redriver@4f {
+            compatible = "nxp,ptn3222";
+            reg = <0x4f>;
+            #phy-cells = <0>;
+            vdd3v3-supply = <&vreg_3p3>;
+            vdd1v8-supply = <&vreg_1p8>;
+            reset-gpios = <&gpio_reset GPIO_ACTIVE_LOW>;
+        };
+    };
+...

From c9be539e11f0bf1665c03108d3b7881a5d67ae48 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Fri, 30 Aug 2024 11:20:46 +0300
Subject: [PATCH 0450/1530] phy: add NXP PTN3222 eUSB2 to USB2 redriver

The NXP PTN3222 is the single-port eUSB2 to USB2 redriver that performs
translation between eUSB2 and USB2 signalling schemes. It supports all
three data rates: Low Speed, Full Speed and High Speed.

The reset state enables autonegotiation of the PHY role and of the data
rate, so no additional programming is required.

Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Tested-by: Konrad Dybcio <konradybcio@kernel.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Stephan Gerhold <stephan.gerhold@linaro.org>
Tested-by: Stephan Gerhold <stephan.gerhold@linaro.org>
Link: https://lore.kernel.org/r/20240830-nxp-ptn3222-v2-2-4c6d8535cf6c@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/Kconfig           |  11 +++
 drivers/phy/Makefile          |   1 +
 drivers/phy/phy-nxp-ptn3222.c | 123 ++++++++++++++++++++++++++++++++++
 3 files changed, 135 insertions(+)
 create mode 100644 drivers/phy/phy-nxp-ptn3222.c

diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index f73abff416bed..8d58efe998ec5 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -82,6 +82,17 @@ config PHY_AIROHA_PCIE
 	  This driver create the basic PHY instance and provides initialize
 	  callback for PCIe GEN3 port.
 
+config PHY_NXP_PTN3222
+	tristate "NXP PTN3222 1-port eUSB2 to USB2 redriver"
+	depends on I2C
+	depends on OF
+	select GENERIC_PHY
+	help
+	  Enable this to support NXP PTN3222 1-port eUSB2 to USB2 Redriver.
+	  This redriver performs translation between eUSB2 and USB2 signalling
+	  schemes. It supports all three USB 2.0 data rates: Low Speed, Full
+	  Speed and High Speed.
+
 source "drivers/phy/allwinner/Kconfig"
 source "drivers/phy/amlogic/Kconfig"
 source "drivers/phy/broadcom/Kconfig"
diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
index ebc399560da4f..e281442acc752 100644
--- a/drivers/phy/Makefile
+++ b/drivers/phy/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_PHY_XGENE)			+= phy-xgene.o
 obj-$(CONFIG_PHY_PISTACHIO_USB)		+= phy-pistachio-usb.o
 obj-$(CONFIG_USB_LGM_PHY)		+= phy-lgm-usb.o
 obj-$(CONFIG_PHY_AIROHA_PCIE)		+= phy-airoha-pcie.o
+obj-$(CONFIG_PHY_NXP_PTN3222)		+= phy-nxp-ptn3222.o
 obj-y					+= allwinner/	\
 					   amlogic/	\
 					   broadcom/	\
diff --git a/drivers/phy/phy-nxp-ptn3222.c b/drivers/phy/phy-nxp-ptn3222.c
new file mode 100644
index 0000000000000..c6179d8701e61
--- /dev/null
+++ b/drivers/phy/phy-nxp-ptn3222.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2024, Linaro Limited
+ */
+
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/phy/phy.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+
+#define NUM_SUPPLIES 2
+
+struct ptn3222 {
+	struct i2c_client *client;
+	struct phy *phy;
+	struct gpio_desc *reset_gpio;
+	struct regulator_bulk_data *supplies;
+};
+
+static int ptn3222_init(struct phy *phy)
+{
+	struct ptn3222 *ptn3222 = phy_get_drvdata(phy);
+	int ret;
+
+	ret = regulator_bulk_enable(NUM_SUPPLIES, ptn3222->supplies);
+	if (ret)
+		return ret;
+
+	gpiod_set_value_cansleep(ptn3222->reset_gpio, 0);
+
+	return 0;
+}
+
+static int ptn3222_exit(struct phy *phy)
+{
+	struct ptn3222 *ptn3222 = phy_get_drvdata(phy);
+
+	gpiod_set_value_cansleep(ptn3222->reset_gpio, 1);
+
+	return regulator_bulk_disable(NUM_SUPPLIES, ptn3222->supplies);
+}
+
+static const struct phy_ops ptn3222_ops = {
+	.init		= ptn3222_init,
+	.exit		= ptn3222_exit,
+	.owner		= THIS_MODULE,
+};
+
+static const struct regulator_bulk_data ptn3222_supplies[NUM_SUPPLIES] = {
+	{
+		.supply = "vdd3v3",
+		.init_load_uA = 11000,
+	}, {
+		.supply = "vdd1v8",
+		.init_load_uA = 55000,
+	}
+};
+
+static int ptn3222_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct phy_provider *phy_provider;
+	struct ptn3222 *ptn3222;
+	int ret;
+
+	ptn3222 = devm_kzalloc(dev, sizeof(*ptn3222), GFP_KERNEL);
+	if (!ptn3222)
+		return -ENOMEM;
+
+	ptn3222->client = client;
+
+	ptn3222->reset_gpio = devm_gpiod_get_optional(dev, "reset",
+						      GPIOD_OUT_HIGH);
+	if (IS_ERR(ptn3222->reset_gpio))
+		return dev_err_probe(dev, PTR_ERR(ptn3222->reset_gpio),
+				     "unable to acquire reset gpio\n");
+
+	ret = devm_regulator_bulk_get_const(dev, NUM_SUPPLIES, ptn3222_supplies,
+					    &ptn3222->supplies);
+	if (ret)
+		return ret;
+
+	ptn3222->phy = devm_phy_create(dev, dev->of_node, &ptn3222_ops);
+	if (IS_ERR(ptn3222->phy)) {
+		dev_err(dev, "failed to create PHY: %d\n", ret);
+		return PTR_ERR(ptn3222->phy);
+	}
+
+	phy_set_drvdata(ptn3222->phy, ptn3222);
+
+	phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
+
+	return PTR_ERR_OR_ZERO(phy_provider);
+}
+
+static const struct i2c_device_id ptn3222_table[] = {
+	{ "ptn3222" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, ptn3222_table);
+
+static const struct of_device_id ptn3222_of_table[] = {
+	{ .compatible = "nxp,ptn3222" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ptn3222_of_table);
+
+static struct i2c_driver ptn3222_driver = {
+	.driver = {
+		.name = "ptn3222",
+		.of_match_table = ptn3222_of_table,
+	},
+	.probe = ptn3222_probe,
+	.id_table = ptn3222_table,
+};
+
+module_i2c_driver(ptn3222_driver);
+
+MODULE_DESCRIPTION("NXP PTN3222 eUSB2 Redriver driver");
+MODULE_LICENSE("GPL");

From f2dbca169790ea1e436ffdd9ef37d7c3a4401c46 Mon Sep 17 00:00:00 2001
From: Andy Yan <andy.yan@rock-chips.com>
Date: Fri, 20 Sep 2024 17:36:28 +0800
Subject: [PATCH 0451/1530] phy: phy-rockchip-samsung-hdptx: Don't request
 RST_PHY/RST_ROPLL/RST_LCPLL

RST_PHY/RST_ROPLL/RST_LCPLL are used for debug only on rk3588,
and they are not exported on rk3576, no need to request it in
driver.

Signed-off-by: Andy Yan <andy.yan@rock-chips.com>
Link: https://lore.kernel.org/r/20240920093629.7410-1-andyshrk@163.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../phy/rockchip/phy-rockchip-samsung-hdptx.c   | 17 +----------------
 1 file changed, 1 insertion(+), 16 deletions(-)

diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
index 9f084697dd05c..ceab9c71d3b53 100644
--- a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
+++ b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
@@ -256,13 +256,10 @@ struct ropll_config {
 };
 
 enum rk_hdptx_reset {
-	RST_PHY = 0,
-	RST_APB,
+	RST_APB = 0,
 	RST_INIT,
 	RST_CMN,
 	RST_LANE,
-	RST_ROPLL,
-	RST_LCPLL,
 	RST_MAX
 };
 
@@ -665,11 +662,6 @@ static void rk_hdptx_phy_disable(struct rk_hdptx_phy *hdptx)
 {
 	u32 val;
 
-	/* reset phy and apb, or phy locked flag may keep 1 */
-	reset_control_assert(hdptx->rsts[RST_PHY].rstc);
-	usleep_range(20, 30);
-	reset_control_deassert(hdptx->rsts[RST_PHY].rstc);
-
 	reset_control_assert(hdptx->rsts[RST_APB].rstc);
 	usleep_range(20, 30);
 	reset_control_deassert(hdptx->rsts[RST_APB].rstc);
@@ -792,10 +784,6 @@ static int rk_hdptx_ropll_tmds_cmn_config(struct rk_hdptx_phy *hdptx,
 
 	rk_hdptx_pre_power_up(hdptx);
 
-	reset_control_assert(hdptx->rsts[RST_ROPLL].rstc);
-	usleep_range(20, 30);
-	reset_control_deassert(hdptx->rsts[RST_ROPLL].rstc);
-
 	rk_hdptx_multi_reg_write(hdptx, rk_hdtpx_common_cmn_init_seq);
 	rk_hdptx_multi_reg_write(hdptx, rk_hdtpx_tmds_cmn_init_seq);
 
@@ -1098,13 +1086,10 @@ static int rk_hdptx_phy_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, PTR_ERR(hdptx->regmap),
 				     "Failed to init regmap\n");
 
-	hdptx->rsts[RST_PHY].id = "phy";
 	hdptx->rsts[RST_APB].id = "apb";
 	hdptx->rsts[RST_INIT].id = "init";
 	hdptx->rsts[RST_CMN].id = "cmn";
 	hdptx->rsts[RST_LANE].id = "lane";
-	hdptx->rsts[RST_ROPLL].id = "ropll";
-	hdptx->rsts[RST_LCPLL].id = "lcpll";
 
 	ret = devm_reset_control_bulk_get_exclusive(dev, RST_MAX, hdptx->rsts);
 	if (ret)

From 09a19fb75498985cbb598f1fa43a7d2416925c30 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 18 Sep 2024 15:32:52 +0200
Subject: [PATCH 0452/1530] phy: airoha: Fix REG_CSR_2L_PLL_CMN_RESERVE0 config
 in airoha_pcie_phy_init_clk_out()

Fix typo configuring REG_CSR_2L_PLL_CMN_RESERVE0 register in
airoha_pcie_phy_init_clk_out routine.

Fixes: d7d2818b9383 ("phy: airoha: Add PCIe PHY driver for EN7581 SoC.")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/r/20240918-airoha-en7581-phy-fixes-v1-1-8291729a87f8@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/phy-airoha-pcie.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/phy/phy-airoha-pcie.c b/drivers/phy/phy-airoha-pcie.c
index 1e410eb410580..4624aa9dd7127 100644
--- a/drivers/phy/phy-airoha-pcie.c
+++ b/drivers/phy/phy-airoha-pcie.c
@@ -459,7 +459,7 @@ static void airoha_pcie_phy_init_clk_out(struct airoha_pcie_phy *pcie_phy)
 	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_CLKTX1_OFFSET,
 				     CSR_2L_PXP_CLKTX1_SR);
 	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_PLL_CMN_RESERVE0,
-				       CSR_2L_PXP_PLL_RESERVE_MASK, 0xdd);
+				       CSR_2L_PXP_PLL_RESERVE_MASK, 0xd0d);
 }
 
 static void airoha_pcie_phy_init_csr_2l(struct airoha_pcie_phy *pcie_phy)

From f9c5d6369d3e8e36b7beb15e86b1ef0911ace85f Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 18 Sep 2024 15:32:53 +0200
Subject: [PATCH 0453/1530] phy: airoha: Fix REG_PCIE_PMA_TX_RESET config in
 airoha_pcie_phy_init_csr_2l()

Fix typos configuring REG_PCIE_PMA_TX_RESET register in
airoha_pcie_phy_init_csr_2l routine for lane0 and lane1

Fixes: d7d2818b9383 ("phy: airoha: Add PCIe PHY driver for EN7581 SoC.")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/r/20240918-airoha-en7581-phy-fixes-v1-2-8291729a87f8@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/phy-airoha-pcie.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/phy/phy-airoha-pcie.c b/drivers/phy/phy-airoha-pcie.c
index 4624aa9dd7127..9a7ce65f87f05 100644
--- a/drivers/phy/phy-airoha-pcie.c
+++ b/drivers/phy/phy-airoha-pcie.c
@@ -471,9 +471,9 @@ static void airoha_pcie_phy_init_csr_2l(struct airoha_pcie_phy *pcie_phy)
 				 PCIE_SW_XFI_RXPCS_RST | PCIE_SW_REF_RST |
 				 PCIE_SW_RX_RST);
 	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_TX_RESET,
-				 PCIE_TX_TOP_RST | REG_PCIE_PMA_TX_RESET);
+				 PCIE_TX_TOP_RST | PCIE_TX_CAL_RST);
 	airoha_phy_pma1_set_bits(pcie_phy, REG_PCIE_PMA_TX_RESET,
-				 PCIE_TX_TOP_RST | REG_PCIE_PMA_TX_RESET);
+				 PCIE_TX_TOP_RST | PCIE_TX_CAL_RST);
 }
 
 static void airoha_pcie_phy_init_rx(struct airoha_pcie_phy *pcie_phy)

From 6fd016c965d241673a2e62afbf9eeb4bcbfbbe45 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 18 Sep 2024 15:32:54 +0200
Subject: [PATCH 0454/1530] phy: airoha: Fix REG_CSR_2L_JCPLL_SDM_HREN config
 in airoha_pcie_phy_init_ssc_jcpll()

Fix typo configuring REG_CSR_2L_JCPLL_SDM_HREN register in
airoha_pcie_phy_init_ssc_jcpll routine.

Fixes: d7d2818b9383 ("phy: airoha: Add PCIe PHY driver for EN7581 SoC.")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/r/20240918-airoha-en7581-phy-fixes-v1-3-8291729a87f8@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/phy-airoha-pcie.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/phy/phy-airoha-pcie.c b/drivers/phy/phy-airoha-pcie.c
index 9a7ce65f87f05..56e9ade8a9fd3 100644
--- a/drivers/phy/phy-airoha-pcie.c
+++ b/drivers/phy/phy-airoha-pcie.c
@@ -802,7 +802,7 @@ static void airoha_pcie_phy_init_ssc_jcpll(struct airoha_pcie_phy *pcie_phy)
 	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_JCPLL_SDM_IFM,
 				   CSR_2L_PXP_JCPLL_SDM_IFM);
 	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_JCPLL_SDM_HREN,
-				   REG_CSR_2L_JCPLL_SDM_HREN);
+				   CSR_2L_PXP_JCPLL_SDM_HREN);
 	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_JCPLL_RST_DLY,
 				     CSR_2L_PXP_JCPLL_SDM_DI_EN);
 	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_JCPLL_SSC,

From e56272f2bb8314eb13b0eb0a4e8055831c700255 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 18 Sep 2024 15:32:55 +0200
Subject: [PATCH 0455/1530] phy: airoha: Fix REG_CSR_2L_RX{0,1}_REV0
 definitions

Fix the following register definitions for REG_CSR_2L_RX{0,1}_REV0
registers:
- CSR_2L_PXP_VOS_PNINV
- CSR_2L_PXP_FE_GAIN_NORMAL_MODE
- CSR_2L_PXP_FE_GAIN_TRAIN_MODE

Fixes: d7d2818b9383 ("phy: airoha: Add PCIe PHY driver for EN7581 SoC.")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/r/20240918-airoha-en7581-phy-fixes-v1-4-8291729a87f8@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/phy-airoha-pcie-regs.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/phy/phy-airoha-pcie-regs.h b/drivers/phy/phy-airoha-pcie-regs.h
index bb1f679ca1dfa..b938a7b468fee 100644
--- a/drivers/phy/phy-airoha-pcie-regs.h
+++ b/drivers/phy/phy-airoha-pcie-regs.h
@@ -197,9 +197,9 @@
 #define CSR_2L_PXP_TX1_MULTLANE_EN		BIT(0)
 
 #define REG_CSR_2L_RX0_REV0			0x00fc
-#define CSR_2L_PXP_VOS_PNINV			GENMASK(3, 2)
-#define CSR_2L_PXP_FE_GAIN_NORMAL_MODE		GENMASK(6, 4)
-#define CSR_2L_PXP_FE_GAIN_TRAIN_MODE		GENMASK(10, 8)
+#define CSR_2L_PXP_VOS_PNINV			GENMASK(19, 18)
+#define CSR_2L_PXP_FE_GAIN_NORMAL_MODE		GENMASK(22, 20)
+#define CSR_2L_PXP_FE_GAIN_TRAIN_MODE		GENMASK(26, 24)
 
 #define REG_CSR_2L_RX0_PHYCK_DIV		0x0100
 #define CSR_2L_PXP_RX0_PHYCK_SEL		GENMASK(9, 8)

From 26ac85e3adb4775df42d94b310276b06c0898d3d Mon Sep 17 00:00:00 2001
From: Ilya Orazov <ilordash02@gmail.com>
Date: Sun, 15 Sep 2024 17:18:31 +0300
Subject: [PATCH 0456/1530] dt-bindings: phy: ti,tcan104x-can: Document
 Microchip ATA6561

Microchip ATA6561 is High-Speed CAN Transceiver with Standby Mode.
It is pin-compatible with TI TCAN1042 and has a compatible programming
model, therefore use ti,tcan1042 as fallback compatible.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Ilya Orazov <ilordash02@gmail.com>
Link: https://lore.kernel.org/r/20240915141831.2809208-2-ilordash02@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/phy/ti,tcan104x-can.yaml    | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/phy/ti,tcan104x-can.yaml b/Documentation/devicetree/bindings/phy/ti,tcan104x-can.yaml
index 79dad3e89aa69..4a8c3829d85d3 100644
--- a/Documentation/devicetree/bindings/phy/ti,tcan104x-can.yaml
+++ b/Documentation/devicetree/bindings/phy/ti,tcan104x-can.yaml
@@ -14,10 +14,15 @@ properties:
     pattern: "^can-phy"
 
   compatible:
-    enum:
-      - nxp,tjr1443
-      - ti,tcan1042
-      - ti,tcan1043
+    oneOf:
+      - items:
+          - enum:
+              - microchip,ata6561
+          - const: ti,tcan1042
+      - enum:
+          - ti,tcan1042
+          - ti,tcan1043
+          - nxp,tjr1443
 
   '#phy-cells':
     const: 0

From 3662f82f16814636aaa152cdbd8db4b96984abea Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 15 Oct 2024 23:56:54 -0700
Subject: [PATCH 0457/1530] perf test: Speed up some tests using perf list

On my system, perf list is very slow to print the whole events.  I think
there's a performance issue in SDT and uprobes event listing.  I noticed
this issue while running perf test on x86 but it takes long to check
some CoreSight event which should be skipped quickly.

Anyway, some test uses perf list to check whether the required event is
available before running the test.  The perf list command can take an
argument to specify event class or (glob) pattern.  But glob pattern is
only to suppress output for unmatched ones after checking all events.

In this case, specifying event class is better to reduce the number of
events it checks and to avoid buggy subsystems entirely.

No functional changes intended.

Reviewed-by: James Clark <james.clark@linaro.org>
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Carsten Haitzler <carsten.haitzler@arm.com>
Cc: Leo Yan <leo.yan@arm.com>
Link: https://lore.kernel.org/r/20241016065654.269994-1-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/lib/coresight.sh             | 2 +-
 tools/perf/tests/shell/lock_contention.sh           | 2 +-
 tools/perf/tests/shell/record.sh                    | 2 +-
 tools/perf/tests/shell/test_arm_coresight.sh        | 2 +-
 tools/perf/tests/shell/test_arm_coresight_disasm.sh | 2 +-
 tools/perf/tests/shell/test_arm_spe.sh              | 2 +-
 tools/perf/tests/shell/test_arm_spe_fork.sh         | 2 +-
 tools/perf/tests/shell/test_intel_pt.sh             | 2 +-
 tools/perf/tests/shell/trace+probe_vfs_getname.sh   | 2 +-
 9 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/tools/perf/tests/shell/lib/coresight.sh b/tools/perf/tests/shell/lib/coresight.sh
index 11ed2c25ed912..184d62e7e5bdf 100644
--- a/tools/perf/tests/shell/lib/coresight.sh
+++ b/tools/perf/tests/shell/lib/coresight.sh
@@ -18,7 +18,7 @@ BIN="$DIR/$TEST"
 # If the test tool/binary does not exist and is executable then skip the test
 if ! test -x "$BIN"; then exit 2; fi
 # If CoreSight is not available, skip the test
-perf list cs_etm | grep -q cs_etm || exit 2
+perf list pmu | grep -q cs_etm || exit 2
 DATD="."
 # If the data dir env is set then make the data dir use that instead of ./
 if test -n "$PERF_TEST_CORESIGHT_DATADIR"; then
diff --git a/tools/perf/tests/shell/lock_contention.sh b/tools/perf/tests/shell/lock_contention.sh
index c1ec5762215ba..30d195d4c62f7 100755
--- a/tools/perf/tests/shell/lock_contention.sh
+++ b/tools/perf/tests/shell/lock_contention.sh
@@ -27,7 +27,7 @@ check() {
 		exit
 	fi
 
-	if ! perf list | grep -q lock:contention_begin; then
+	if ! perf list tracepoint | grep -q lock:contention_begin; then
 		echo "[Skip] No lock contention tracepoints"
 		err=2
 		exit
diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index 8d6366d96883e..3eee72242290d 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -94,7 +94,7 @@ test_per_thread() {
 
 test_register_capture() {
   echo "Register capture test"
-  if ! perf list | grep -q 'br_inst_retired.near_call'
+  if ! perf list pmu | grep -q 'br_inst_retired.near_call'
   then
     echo "Register capture test [Skipped missing event]"
     return
diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh
index 3302ea0b96723..6b8c4831eedc6 100755
--- a/tools/perf/tests/shell/test_arm_coresight.sh
+++ b/tools/perf/tests/shell/test_arm_coresight.sh
@@ -12,7 +12,7 @@
 glb_err=0
 
 skip_if_no_cs_etm_event() {
-	perf list | grep -q 'cs_etm//' && return 0
+	perf list pmu | grep -q 'cs_etm//' && return 0
 
 	# cs_etm event doesn't exist
 	return 2
diff --git a/tools/perf/tests/shell/test_arm_coresight_disasm.sh b/tools/perf/tests/shell/test_arm_coresight_disasm.sh
index af63e3757cb0a..dba086a40d846 100755
--- a/tools/perf/tests/shell/test_arm_coresight_disasm.sh
+++ b/tools/perf/tests/shell/test_arm_coresight_disasm.sh
@@ -8,7 +8,7 @@
 # the script. Test all 3 parts are working correctly by running the script.
 
 skip_if_no_cs_etm_event() {
-	perf list | grep -q 'cs_etm//' && return 0
+	perf list pmu | grep -q 'cs_etm//' && return 0
 
 	# cs_etm event doesn't exist
 	return 2
diff --git a/tools/perf/tests/shell/test_arm_spe.sh b/tools/perf/tests/shell/test_arm_spe.sh
index 03d5c7d12ee53..6c21fb1f10d8f 100755
--- a/tools/perf/tests/shell/test_arm_spe.sh
+++ b/tools/perf/tests/shell/test_arm_spe.sh
@@ -9,7 +9,7 @@
 # German Gomez <german.gomez@arm.com>, 2021
 
 skip_if_no_arm_spe_event() {
-	perf list | grep -E -q 'arm_spe_[0-9]+//' && return 0
+	perf list pmu | grep -E -q 'arm_spe_[0-9]+//' && return 0
 
 	# arm_spe event doesn't exist
 	return 2
diff --git a/tools/perf/tests/shell/test_arm_spe_fork.sh b/tools/perf/tests/shell/test_arm_spe_fork.sh
index 1a7e6a82d0e34..8efeef9fb9564 100755
--- a/tools/perf/tests/shell/test_arm_spe_fork.sh
+++ b/tools/perf/tests/shell/test_arm_spe_fork.sh
@@ -5,7 +5,7 @@
 # German Gomez <german.gomez@arm.com>, 2022
 
 skip_if_no_arm_spe_event() {
-	perf list | grep -E -q 'arm_spe_[0-9]+//' && return 0
+	perf list pmu | grep -E -q 'arm_spe_[0-9]+//' && return 0
 	return 2
 }
 
diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh
index 723ec501f99ab..bf9017b812aa6 100755
--- a/tools/perf/tests/shell/test_intel_pt.sh
+++ b/tools/perf/tests/shell/test_intel_pt.sh
@@ -5,7 +5,7 @@
 set -e
 
 # Skip if no Intel PT
-perf list | grep -q 'intel_pt//' || exit 2
+perf list pmu | grep -q 'intel_pt//' || exit 2
 
 shelldir=$(dirname "$0")
 # shellcheck source=lib/waiting.sh
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 3146a1eece078..97b4b9cd23784 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -19,7 +19,7 @@ skip_if_no_perf_trace || exit 2
 . "$(dirname $0)"/lib/probe_vfs_getname.sh
 
 trace_open_vfs_getname() {
-	evts="$(echo "$(perf list syscalls:sys_enter_open* 2>/dev/null | grep -E 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/')" | sed ':a;N;s:\n:,:g')"
+	evts="$(echo "$(perf list tracepoint 2>/dev/null | grep -E 'syscalls:sys_enter_open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/')" | sed ':a;N;s:\n:,:g')"
 	perf trace -e $evts touch $file 2>&1 | \
 	grep -E " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +\"?${file}\"?, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }

From d08e3f14e87259b9d63bf7eea7072d1bd61392ef Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Sat, 12 Oct 2024 21:47:23 +0100
Subject: [PATCH 0458/1530] perf probe: Use the MAX_EVENT_NAME_LEN macro

The MAX_EVENT_NAME_LEN macro has been defined in the kernel. Use the
same definition in the tool for more readable.

Signed-off-by: Leo Yan <leo.yan@arm.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20241012204725.928794-2-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/probe-event.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 698a928753740..83b5744da50c5 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -51,6 +51,9 @@
 
 #define PERFPROBE_GROUP "probe"
 
+/* Defined in kernel/trace/trace.h */
+#define MAX_EVENT_NAME_LEN	64
+
 bool probe_event_dry_run;	/* Dry run flag */
 struct probe_conf probe_conf = { .magic_num = DEFAULT_PROBE_MAGIC_NUM };
 
@@ -2841,7 +2844,7 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
 				       bool allow_suffix)
 {
 	const char *event, *group;
-	char buf[64];
+	char buf[MAX_EVENT_NAME_LEN];
 	int ret;
 
 	/* If probe_event or trace_event already have the name, reuse it */

From 6768faf9b70eec01c3c6d685b4f39049c561dbda Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Sat, 12 Oct 2024 21:47:24 +0100
Subject: [PATCH 0459/1530] perf probe: Check group string length

In the kernel, the probe group string length is limited up to
MAX_EVENT_NAME_LEN (including the NULL terminator).

Check for this limitation and report an error if it is exceeded.

Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Leo Yan <leo.yan@arm.com>
Link: https://lore.kernel.org/r/20241012204725.928794-3-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/probe-event.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 83b5744da50c5..2903341a43098 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2868,6 +2868,12 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
 	else
 		group = PERFPROBE_GROUP;
 
+	if (strlen(group) >= MAX_EVENT_NAME_LEN) {
+		pr_err("Probe group string='%s' is too long (>= %d bytes)\n",
+			group, MAX_EVENT_NAME_LEN);
+		return -ENOMEM;
+	}
+
 	/* Get an unused new event name */
 	ret = get_new_event_name(buf, sizeof(buf), event, namelist,
 				 tev->point.retprobe, allow_suffix);

From e34f6ac511be5347b270e42a7a23a4569ea74bc2 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Sat, 12 Oct 2024 21:47:25 +0100
Subject: [PATCH 0460/1530] perf probe: Improve log for long event name failure

If a symbol name is longer than the maximum event length (64 bytes), the
perf tool reports error:

  # perf probe -x test_cpp_mangle --add "this_is_a_very_very_long_print_data_abcdefghijklmnopqrstuvwxyz(int)"
    snprintf() failed: -7; the event name nbase='this_is_a_very_very_long_print_data_abcdefghijklmnopqrstuvwxyz(int)' is too long
    Error: Failed to add events.

An information is missed in the log that the symbol name and the event
name can be set separately. Especially, this is recommended for adding
probe for a long symbol.

This commit refines the log for reminding event syntax.

After:

  # perf probe -x test_cpp_mangle --add "this_is_a_very_very_long_print_data_abcdefghijklmnopqrstuvwxyz(int)"
    snprintf() failed: -7; the event name 'this_is_a_very_very_long_print_data_abcdefghijklmnopqrstuvwxyz(int)' is too long
      Hint: Set a shorter event with syntax "EVENT=PROBEDEF"
            EVENT: Event name (max length: 64 bytes).
      Error: Failed to add events.

Signed-off-by: Leo Yan <leo.yan@arm.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20241012204725.928794-4-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/probe-event.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 2903341a43098..2c8d94d09e86c 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2760,7 +2760,10 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 	/* Try no suffix number */
 	ret = e_snprintf(buf, len, "%s%s", nbase, ret_event ? "__return" : "");
 	if (ret < 0) {
-		pr_warning("snprintf() failed: %d; the event name nbase='%s' is too long\n", ret, nbase);
+		pr_warning("snprintf() failed: %d; the event name '%s' is too long\n"
+			   "  Hint: Set a shorter event with syntax \"EVENT=PROBEDEF\"\n"
+			   "        EVENT: Event name (max length: %d bytes).\n",
+			   ret, nbase, MAX_EVENT_NAME_LEN);
 		goto out;
 	}
 	if (!strlist__has_entry(namelist, buf))
@@ -2780,7 +2783,10 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 	for (i = 1; i < MAX_EVENT_INDEX; i++) {
 		ret = e_snprintf(buf, len, "%s_%d", nbase, i);
 		if (ret < 0) {
-			pr_debug("snprintf() failed: %d\n", ret);
+			pr_warning("Add suffix failed: %d; the event name '%s' is too long\n"
+				   "  Hint: Set a shorter event with syntax \"EVENT=PROBEDEF\"\n"
+				   "        EVENT: Event name (max length: %d bytes).\n",
+				   ret, nbase, MAX_EVENT_NAME_LEN);
 			goto out;
 		}
 		if (!strlist__has_entry(namelist, buf))

From 05a62936e6b14c005db3b0c9c7d8b93d825dd9ca Mon Sep 17 00:00:00 2001
From: Veronika Molnarova <vmolnaro@redhat.com>
Date: Thu, 10 Oct 2024 16:48:36 +0200
Subject: [PATCH 0461/1530] perf dso: Fix symtab_type for kmod compression

During the rework of the dso structure in patch ee756ef7491eafd an
increment was forgotten for the symtab_type in case the data for
the kernel module are compressed. This affects the probing of the
kernel modules, which fails if the data are not already cached.

Increment the value of the symtab_type to its compressed variant so the
data could be recovered successfully.

Fixes: ee756ef7491eafd7 ("perf dso: Add reference count checking and accessor functions")
Signed-off-by: Veronika Molnarova <vmolnaro@redhat.com>
Acked-by: Michael Petlan <mpetlan@redhat.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Michael Petlan <mpetlan@redhat.com>
Link: https://lore.kernel.org/r/20241010144836.16424-1-vmolnaro@redhat.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/machine.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index fad227b625d15..4f0ac998b0ccf 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1343,7 +1343,7 @@ static int maps__set_module_path(struct maps *maps, const char *path, struct kmo
 	 * we need to update the symtab_type if needed.
 	 */
 	if (m->comp && is_kmod_dso(dso)) {
-		dso__set_symtab_type(dso, dso__symtab_type(dso));
+		dso__set_symtab_type(dso, dso__symtab_type(dso)+1);
 		dso__set_comp(dso, m->comp);
 	}
 	map__put(map);

From 86f45d0f17d2f4d4857a8553673add9c71fb45aa Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Thu, 10 Oct 2024 20:21:06 +0530
Subject: [PATCH 0462/1530] tools/perf/pmu-events/powerpc: Add support for
 compat events in json

perf list picks the events supported for specific platform
from pmu-events/arch/powerpc/<platform>. Example power10 events
are in pmu-events/arch/powerpc/power10, power9 events are part
of pmu-events/arch/powerpc/power9. The decision of which
platform to pick is determined based on PVR value in powerpc.
The PVR value is matched from pmu-events/arch/powerpc/mapfile.csv

Example:

Format:
        PVR,Version,JSON/file/pathname,Type

0x004[bcd][[:xdigit:]]{4},1,power8,core
0x0066[[:xdigit:]]{4},1,power8,core
0x004e[[:xdigit:]]{4},1,power9,core
0x0080[[:xdigit:]]{4},1,power10,core
0x0082[[:xdigit:]]{4},1,power10,core

The code gets the PVR from system using get_cpuid_str function
in arch/powerpc/util/headers.c ( from SPRN_PVR ) and compares
with value from mapfile.csv

In case of compat mode, say when partition is booted in a power9
mode when the system is a power10, add an entry to pick the
ISA architected events from "pmu-events/arch/powerpc/compat".
Add json file generic-events.json which will contain these
events which is supported in compat mode.

Suggested-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Tested-by: Disha Goel <disgoel@linux.ibm.com>
Cc: akanksha@linux.ibm.com
Cc: hbathini@linux.ibm.com
Cc: kjain@linux.ibm.com
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20241010145107.51211-1-atrajeev@linux.vnet.ibm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../arch/powerpc/compat/generic-events.json   | 117 ++++++++++++++++++
 .../perf/pmu-events/arch/powerpc/mapfile.csv  |   1 +
 2 files changed, 118 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/powerpc/compat/generic-events.json

diff --git a/tools/perf/pmu-events/arch/powerpc/compat/generic-events.json b/tools/perf/pmu-events/arch/powerpc/compat/generic-events.json
new file mode 100644
index 0000000000000..6f5e8efcb098c
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/compat/generic-events.json
@@ -0,0 +1,117 @@
+[
+  {
+    "EventCode": "0x600F4",
+    "EventName": "PM_CYC",
+    "BriefDescription": "Processor cycles."
+  },
+  {
+    "EventCode": "0x100F2",
+    "EventName": "PM_CYC_INST_CMPL",
+    "BriefDescription": "1 or more ppc insts finished"
+  },
+  {
+    "EventCode": "0x100f4",
+    "EventName": "PM_FLOP_CMPL",
+    "BriefDescription": "Floating Point Operations Finished."
+  },
+  {
+    "EventCode": "0x100F6",
+    "EventName": "PM_L1_ITLB_MISS",
+    "BriefDescription": "Number of I-ERAT reloads."
+  },
+  {
+    "EventCode": "0x100F8",
+    "EventName": "PM_NO_INST_AVAIL",
+    "BriefDescription": "Number of cycles the ICT has no itags assigned to this thread."
+  },
+  {
+    "EventCode": "0x100fc",
+    "EventName": "PM_LD_CMPL",
+    "BriefDescription": "Load instruction completed."
+  },
+  {
+    "EventCode": "0x200F0",
+    "EventName": "PM_ST_CMPL",
+    "BriefDescription": "Stores completed from S2Q (2nd-level store queue)."
+  },
+  {
+    "EventCode": "0x200F2",
+    "EventName": "PM_INST_DISP",
+    "BriefDescription": "PowerPC instruction dispatched."
+  },
+  {
+    "EventCode": "0x200F4",
+    "EventName": "PM_RUN_CYC",
+    "BriefDescription": "Processor cycles gated by the run latch."
+  },
+  {
+    "EventCode": "0x200F6",
+    "EventName": "PM_L1_DTLB_RELOAD",
+    "BriefDescription": "DERAT Reloaded due to a DERAT miss."
+  },
+  {
+    "EventCode": "0x200FA",
+    "EventName": "PM_BR_TAKEN_CMPL",
+    "BriefDescription": "Branch Taken instruction completed."
+  },
+  {
+    "EventCode": "0x200FC",
+    "EventName": "PM_L1_ICACHE_MISS",
+    "BriefDescription": "Demand instruction cache miss."
+  },
+  {
+    "EventCode": "0x200FE",
+    "EventName": "PM_L1_RELOAD_FROM_MEM",
+    "BriefDescription": "L1 Dcache reload from memory"
+  },
+  {
+    "EventCode": "0x300F0",
+    "EventName": "PM_ST_MISS_L1",
+    "BriefDescription": "Store Missed L1"
+  },
+  {
+    "EventCode": "0x300FC",
+    "EventName": "PM_DTLB_MISS",
+    "BriefDescription": "Data PTEG reload"
+  },
+  {
+    "EventCode": "0x300FE",
+    "EventName": "PM_DATA_FROM_L3MISS",
+    "BriefDescription": "Demand LD - L3 Miss (not L2 hit and not L3 hit)"
+  },
+  {
+    "EventCode": "0x400F0",
+    "EventName": "PM_LD_MISS_L1",
+    "BriefDescription": "L1 Dcache load miss"
+  },
+  {
+    "EventCode": "0x400F2",
+    "EventName": "PM_CYC_INST_DISP",
+    "BriefDescription": "Cycle when instruction(s) dispatched."
+  },
+  {
+    "EventCode": "0x400F6",
+    "EventName": "PM_BR_MPRED_CMPL",
+    "BriefDescription": "A mispredicted branch completed. Includes direction and target."
+  },
+  {
+    "EventCode": "0x400FA",
+    "EventName": "PM_RUN_INST_CMPL",
+    "BriefDescription": "PowerPC instruction completed while the run latch is set."
+  },
+  {
+    "EventCode": "0x400FC",
+    "EventName": "PM_ITLB_MISS",
+    "BriefDescription": "Instruction TLB reload (after a miss), all page sizes. Includes only demand misses."
+  },
+  {
+    "EventCode": "0x400fe",
+    "EventName": "PM_LD_NOT_CACHED",
+    "BriefDescription": "Load data not cached."
+  },
+  {
+    "EventCode": "0x500fa",
+    "EventName": "PM_INST_CMPL",
+    "BriefDescription": "Instructions."
+  }
+]
diff --git a/tools/perf/pmu-events/arch/powerpc/mapfile.csv b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
index 4d5e9138d4cc2..cbd3cb443784f 100644
--- a/tools/perf/pmu-events/arch/powerpc/mapfile.csv
+++ b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
@@ -16,3 +16,4 @@
 0x004e[[:xdigit:]]{4},1,power9,core
 0x0080[[:xdigit:]]{4},1,power10,core
 0x0082[[:xdigit:]]{4},1,power10,core
+0x00ffffff,1,compat,core

From 54f9aa109245717df95d8dd2a1f42a3f42abdd3b Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Thu, 10 Oct 2024 20:21:07 +0530
Subject: [PATCH 0463/1530] tools/perf/powerpc/util: Add support to handle
 compatible mode PVR for perf json events

perf list picks the events supported for specific platform
from pmu-events/arch/powerpc/<platform>. Example power10 events
are in pmu-events/arch/powerpc/power10, power9 events are part
of pmu-events/arch/powerpc/power9. The decision of which
platform to pick is determined based on PVR value in powerpc.
The PVR value is matched from pmu-events/arch/powerpc/mapfile.csv

Example:

Format:
	PVR,Version,JSON/file/pathname,Type

0x004[bcd][[:xdigit:]]{4},1,power8,core
0x0066[[:xdigit:]]{4},1,power8,core
0x004e[[:xdigit:]]{4},1,power9,core
0x0080[[:xdigit:]]{4},1,power10,core
0x0082[[:xdigit:]]{4},1,power10,core

The code gets the PVR from system using get_cpuid_str function
in arch/powerpc/util/headers.c ( from SPRN_PVR ) and compares
with value from mapfile.csv
In case of compat mode, say when partition is booted in a power9
mode when the system is a power10, this picks incorrectly. Because
PVR will point to power10 where as it should pick events from power9
folder. To support generic events, add new folder
pmu-events/arch/powerpc/compat to contain the ISA architected events
which is supported in compat mode. Also return 0x00ffffff as pvr
when booted in compat mode. Based on this pvr value, json will
pick events from pmu-events/arch/powerpc/compat

Suggested-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Tested-by: Disha Goel<disgoel@linux.ibm.com>
Cc: akanksha@linux.ibm.com
Cc: hbathini@linux.ibm.com
Cc: kjain@linux.ibm.com
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20241010145107.51211-2-atrajeev@linux.vnet.ibm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/powerpc/util/header.c | 32 ++++++++++++++++++++++++++-
 1 file changed, 31 insertions(+), 1 deletion(-)

diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 6b00efd53638d..251cdbf58a4de 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -10,6 +10,18 @@
 #include "utils_header.h"
 #include "metricgroup.h"
 #include <api/fs/fs.h>
+#include <sys/auxv.h>
+
+static bool is_compat_mode(void)
+{
+	u64 base_platform = getauxval(AT_BASE_PLATFORM);
+	u64 platform = getauxval(AT_PLATFORM);
+
+	if (!strcmp((char *)platform, (char *)base_platform))
+		return false;
+
+	return true;
+}
 
 int
 get_cpuid(char *buffer, size_t sz)
@@ -33,8 +45,26 @@ char *
 get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 {
 	char *bufp;
+	unsigned long pvr;
+
+	/*
+	 * IBM Power System supports compatible mode. That is
+	 * Nth generation platform can support previous generation
+	 * OS in a mode called compatibile mode. For ex. LPAR can be
+	 * booted in a Power9 mode when the system is a Power10.
+	 *
+	 * In the compatible mode, care must be taken when generating
+	 * PVR value. When read, PVR will be of the AT_BASE_PLATFORM
+	 * To support generic events, return 0x00ffffff as pvr when
+	 * booted in compat mode. Based on this pvr value, json will
+	 * pick events from pmu-events/arch/powerpc/compat
+	 */
+	if (!is_compat_mode())
+		pvr = mfspr(SPRN_PVR);
+	else
+		pvr = 0x00ffffff;
 
-	if (asprintf(&bufp, "0x%.8lx", mfspr(SPRN_PVR)) < 0)
+	if (asprintf(&bufp, "0x%.8lx", pvr) < 0)
 		bufp = NULL;
 
 	return bufp;

From f8a23e3b79d6c622e1b329706cbd802bc88a058f Mon Sep 17 00:00:00 2001
From: Nick Hu <nick.hu@sifive.com>
Date: Wed, 14 Aug 2024 13:44:33 +0800
Subject: [PATCH 0464/1530] cpuidle: riscv-sbi: Move sbi_cpuidle_init to
 arch_initcall

Move the sbi_cpuidle_init to the arch_initcall to prevent the consumer
devices from being deferred.

Signed-off-by: Nick Hu <nick.hu@sifive.com>
Link: https://lore.kernel.org/lkml/CAKddAkAOUJSnM=Px-YO=U6pis_7mODHZbmYqcgEzXikriqYvXQ@mail.gmail.com/
Suggested-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20240814054434.3563453-2-nick.hu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 drivers/cpuidle/cpuidle-riscv-sbi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c
index a6e123dfe394d..98e7751dbfe8a 100644
--- a/drivers/cpuidle/cpuidle-riscv-sbi.c
+++ b/drivers/cpuidle/cpuidle-riscv-sbi.c
@@ -592,4 +592,4 @@ static int __init sbi_cpuidle_init(void)
 
 	return 0;
 }
-device_initcall(sbi_cpuidle_init);
+arch_initcall(sbi_cpuidle_init);

From 27b4d6aa29abe6c4f0b7695bc831fcc8d32267d9 Mon Sep 17 00:00:00 2001
From: Nick Hu <nick.hu@sifive.com>
Date: Wed, 14 Aug 2024 13:44:34 +0800
Subject: [PATCH 0465/1530] cpuidle: riscv-sbi: Add cpuidle_disabled() check

The consumer devices that inside the cpu/cluster power domain may register
the genpd notifier where their power domains point to the pd nodes under
'/cpus/power-domains'. If the cpuidle.off==1, the genpd notifier will fail
due to sbi_cpuidle_pd_allow_domain_state is not set. We also need the
sbi_cpuidle_cpuhp_up/down to invoke the callbacks. Therefore adding a
cpuidle_disabled() check before cpuidle_register() to address the issue.

Signed-off-by: Nick Hu <nick.hu@sifive.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20240814054434.3563453-3-nick.hu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 drivers/cpuidle/cpuidle-riscv-sbi.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c
index 98e7751dbfe8a..3c8a509288f3a 100644
--- a/drivers/cpuidle/cpuidle-riscv-sbi.c
+++ b/drivers/cpuidle/cpuidle-riscv-sbi.c
@@ -25,6 +25,7 @@
 #include <asm/smp.h>
 #include <asm/suspend.h>
 
+#include "cpuidle.h"
 #include "dt_idle_states.h"
 #include "dt_idle_genpd.h"
 
@@ -336,6 +337,9 @@ static int sbi_cpuidle_init_cpu(struct device *dev, int cpu)
 		return ret;
 	}
 
+	if (cpuidle_disabled())
+		return 0;
+
 	ret = cpuidle_register(drv, NULL);
 	if (ret)
 		goto deinit;
@@ -548,7 +552,10 @@ static int sbi_cpuidle_probe(struct platform_device *pdev)
 	/* Setup CPU hotplut notifiers */
 	sbi_idle_init_cpuhp();
 
-	pr_info("idle driver registered for all CPUs\n");
+	if (cpuidle_disabled())
+		pr_info("cpuidle is disabled\n");
+	else
+		pr_info("idle driver registered for all CPUs\n");
 
 	return 0;
 

From 1280f012e06e1555de47e3c3a9be898d8cbda5fb Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 16 Oct 2024 16:56:21 -0700
Subject: [PATCH 0466/1530] perf disasm: Fix capstone memory leak

The insn argument passed to cs_disasm needs freeing. To support
accurately having count, add an additional free_count variable.

Fixes: c5d60de1813a ("perf annotate: Add support to use libcapstone in powerpc")
Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Hemant Kumar <hemant@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20241016235622.52166-2-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/disasm.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index f05ba7739c1e9..2c8063660f2e8 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -1627,12 +1627,12 @@ static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
 	u64 start = map__rip_2objdump(map, sym->start);
 	u64 len;
 	u64 offset;
-	int i, count;
+	int i, count, free_count;
 	bool is_64bit = false;
 	bool needs_cs_close = false;
 	u8 *buf = NULL;
 	csh handle;
-	cs_insn *insn;
+	cs_insn *insn = NULL;
 	char disasm_buf[512];
 	struct disasm_line *dl;
 
@@ -1664,7 +1664,7 @@ static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
 
 	needs_cs_close = true;
 
-	count = cs_disasm(handle, buf, len, start, len, &insn);
+	free_count = count = cs_disasm(handle, buf, len, start, len, &insn);
 	for (i = 0, offset = 0; i < count; i++) {
 		int printed;
 
@@ -1702,8 +1702,11 @@ static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
 	}
 
 out:
-	if (needs_cs_close)
+	if (needs_cs_close) {
 		cs_close(&handle);
+		if (free_count > 0)
+			cs_free(insn, free_count);
+	}
 	free(buf);
 	return count < 0 ? count : 0;
 

From 4585038b8e186252141ef86e9f0d8e97f11dce8d Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 16 Oct 2024 16:56:22 -0700
Subject: [PATCH 0467/1530] perf probe: Fix libdw memory leak

Add missing dwarf_cfi_end to free memory associated with probe_finder
cfi_eh which is allocated and owned via a call to
dwarf_getcfi_elf. Confusingly cfi_dbg shouldn't be freed as its memory
is owned by the passed in debuginfo struct. Add comments to highlight
this.

This addresses leak sanitizer issues seen in:
tools/perf/tests/shell/test_uprobe_from_different_cu.sh

Fixes: 270bde1e76f4 ("perf probe: Search both .eh_frame and .debug_frame sections for probe location")
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Hemant Kumar <hemant@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20241016235622.52166-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/probe-finder.c | 4 ++++
 tools/perf/util/probe-finder.h | 4 ++--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 630e16c54ed5c..d6b902899940b 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1379,6 +1379,10 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 	if (ret >= 0 && tf.pf.skip_empty_arg)
 		ret = fill_empty_trace_arg(pev, tf.tevs, tf.ntevs);
 
+#if _ELFUTILS_PREREQ(0, 142)
+	dwarf_cfi_end(tf.pf.cfi_eh);
+#endif
+
 	if (ret < 0 || tf.ntevs == 0) {
 		for (i = 0; i < tf.ntevs; i++)
 			clear_probe_trace_event(&tf.tevs[i]);
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 3add5ff516e12..724db829b49e0 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -64,9 +64,9 @@ struct probe_finder {
 
 	/* For variable searching */
 #if _ELFUTILS_PREREQ(0, 142)
-	/* Call Frame Information from .eh_frame */
+	/* Call Frame Information from .eh_frame. Owned by this struct. */
 	Dwarf_CFI		*cfi_eh;
-	/* Call Frame Information from .debug_frame */
+	/* Call Frame Information from .debug_frame. Not owned. */
 	Dwarf_CFI		*cfi_dbg;
 #endif
 	Dwarf_Op		*fb_ops;	/* Frame base attribute */

From 58fc358a3e2d484697afbae86496fc5982f222f3 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 17 Oct 2024 10:53:50 -0700
Subject: [PATCH 0468/1530] perf color: Add printf format checking and resolve
 issues

Add printf format checking to vararg printf routines in
color.h. Resolve build errors/bugs that are found through this
checking.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20241017175356.783793-2-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-sched.c        | 2 +-
 tools/perf/builtin-trace.c        | 2 +-
 tools/perf/util/arm-spe.c         | 2 +-
 tools/perf/util/color.h           | 9 +++++----
 tools/perf/util/intel-bts.c       | 2 +-
 tools/perf/util/intel-pt.c        | 2 +-
 tools/perf/util/s390-cpumsf.c     | 2 +-
 tools/perf/util/s390-sample-raw.c | 8 ++++----
 8 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index c053074b98b41..7049c60ebf77c 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1743,7 +1743,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 	}
 
 	if (sched->map.comp && new_cpu)
-		color_fprintf(stdout, color, " (CPU %d)", this_cpu);
+		color_fprintf(stdout, color, " (CPU %d)", this_cpu.cpu);
 
 	if (proceed != 1) {
 		color_fprintf(stdout, color, "\n");
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 0b30297b4ecb3..748b061f8678d 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1873,7 +1873,7 @@ static int trace__process_event(struct trace *trace, struct machine *machine,
 	switch (event->header.type) {
 	case PERF_RECORD_LOST:
 		color_fprintf(trace->output, PERF_COLOR_RED,
-			      "LOST %" PRIu64 " events!\n", event->lost.lost);
+			      "LOST %" PRIu64 " events!\n", (u64)event->lost.lost);
 		ret = machine__process_lost_event(machine, event, sample);
 		break;
 	default:
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index c424e5b9a11d9..856cc36f33d79 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -122,7 +122,7 @@ static void arm_spe_dump(struct arm_spe *spe __maybe_unused,
 		else
 			pkt_len = 1;
 		printf(".");
-		color_fprintf(stdout, color, "  %08x: ", pos);
+		color_fprintf(stdout, color, "  %08zx: ", pos);
 		for (i = 0; i < pkt_len; i++)
 			color_fprintf(stdout, color, " %02x", buf[i]);
 		for (; i < 16; i++)
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index aecf56dae73f5..b2f37de305f63 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -2,6 +2,7 @@
 #ifndef __PERF_COLOR_H
 #define __PERF_COLOR_H
 
+#include <linux/compiler.h>
 #include <stdio.h>
 #include <stdarg.h>
 
@@ -37,11 +38,11 @@ int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
 int color_vsnprintf(char *bf, size_t size, const char *color,
 		    const char *fmt, va_list args);
 int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args);
-int color_fprintf(FILE *fp, const char *color, const char *fmt, ...);
-int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...);
+int color_fprintf(FILE *fp, const char *color, const char *fmt, ...) __printf(3, 4);
+int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...) __printf(4, 5);
 int value_color_snprintf(char *bf, size_t size, const char *fmt, double value);
-int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...);
-int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...);
+int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...) __printf(3, 4);
+int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...) __printf(3, 4);
 int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
 const char *get_percent_color(double percent);
 
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 27d9b5c9fec8b..3ea82d5e8d2ee 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -100,7 +100,7 @@ static void intel_bts_dump(struct intel_bts *bts __maybe_unused,
 		else
 			sz = len;
 		printf(".");
-		color_fprintf(stdout, color, "  %08x: ", pos);
+		color_fprintf(stdout, color, "  %08zx: ", pos);
 		for (i = 0; i < sz; i++)
 			color_fprintf(stdout, color, " %02x", buf[i]);
 		for (; i < br_sz; i++)
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index fd2597613f3dc..3fe67bf652b64 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -249,7 +249,7 @@ static void intel_pt_dump(struct intel_pt *pt __maybe_unused,
 		else
 			pkt_len = 1;
 		printf(".");
-		color_fprintf(stdout, color, "  %08x: ", pos);
+		color_fprintf(stdout, color, "  %08zx: ", pos);
 		for (i = 0; i < pkt_len; i++)
 			color_fprintf(stdout, color, " %02x", buf[i]);
 		for (; i < 16; i++)
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index 73846b73d0cf4..30638653ad2d6 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -345,7 +345,7 @@ static bool s390_cpumsf_trailer_show(const char *color, size_t pos,
 	}
 	color_fprintf(stdout, color, "    [%#08zx] Trailer %c%c%c bsdes:%d"
 		      " dsdes:%d Overflow:%lld Time:%#llx\n"
-		      "\t\tC:%d TOD:%#lx\n",
+		      "\t\tC:%d TOD:%#llx\n",
 		      pos,
 		      te->f ? 'F' : ' ',
 		      te->a ? 'A' : ' ',
diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
index 53383e97ec9d5..335217bb532b4 100644
--- a/tools/perf/util/s390-sample-raw.c
+++ b/tools/perf/util/s390-sample-raw.c
@@ -98,12 +98,12 @@ static void s390_cpumcfdg_dumptrail(const char *color, size_t offset,
 	te.res2 = be32_to_cpu(tep->res2);
 
 	color_fprintf(stdout, color, "    [%#08zx] Trailer:%c%c%c%c%c"
-		      " Cfvn:%d Csvn:%d Speed:%d TOD:%#llx\n",
+		      " Cfvn:%d Csvn:%d Speed:%d TOD:%#lx\n",
 		      offset, te.clock_base ? 'T' : ' ',
 		      te.speed ? 'S' : ' ', te.mtda ? 'M' : ' ',
 		      te.caca ? 'C' : ' ', te.lcda ? 'L' : ' ',
 		      te.cfvn, te.csvn, te.cpu_speed, te.timestamp);
-	color_fprintf(stdout, color, "\t\t1:%lx 2:%lx 3:%lx TOD-Base:%#llx"
+	color_fprintf(stdout, color, "\t\t1:%lx 2:%lx 3:%lx TOD-Base:%#lx"
 		      " Type:%x\n\n",
 		      te.progusage1, te.progusage2, te.progusage3,
 		      te.tod_base, te.mach_type);
@@ -205,7 +205,7 @@ static void s390_cpumcfdg_dump(struct perf_pmu *pmu, struct perf_sample *sample)
 			char *ev_name = get_counter_name(ce.set, i, pmu);
 
 			color_fprintf(stdout, color,
-				      "\tCounter:%03d %s Value:%#018lx\n", i,
+				      "\tCounter:%03zd %s Value:%#018"PRIx64"\n", i,
 				      ev_name ?: "<unknown>", be64_to_cpu(*p));
 			free(ev_name);
 		}
@@ -260,7 +260,7 @@ static void s390_pai_all_dump(struct evsel *evsel, struct perf_sample *sample)
 
 		ev_name = get_counter_name(evsel->core.attr.config,
 					   pai_data.event_nr, evsel->pmu);
-		color_fprintf(stdout, color, "\tCounter:%03d %s Value:%#018lx\n",
+		color_fprintf(stdout, color, "\tCounter:%03d %s Value:%#018"PRIx64"\n",
 			      pai_data.event_nr, ev_name ?: "<unknown>",
 			      pai_data.event_val);
 		free(ev_name);

From 9809b2b1f23d0b7e0c6154ee0e94445e584435d4 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 17 Oct 2024 10:53:51 -0700
Subject: [PATCH 0469/1530] perf stat: Fix/add parameter names for print_metric

The print_metric parameter names were rearranged, fix and add comments
in the stat-shadow callers to ensure they are correct.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20241017175356.783793-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/stat-shadow.c | 55 ++++++++++++++++++++---------------
 tools/perf/util/stat.h        |  6 ++--
 2 files changed, 36 insertions(+), 25 deletions(-)

diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 6227de8480836..512890d50b690 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -196,17 +196,21 @@ static void print_ratio(struct perf_stat_config *config,
 			const struct evsel *evsel, int aggr_idx,
 			double numerator, struct perf_stat_output_ctx *out,
 			enum stat_type denominator_type,
-			const double color_ratios[3], const char *unit)
+			const double color_ratios[3], const char *_unit)
 {
 	double denominator = find_stat(evsel, aggr_idx, denominator_type);
+	double ratio = 0;
+	const char *color = NULL;
+	const char *fmt = NULL;
+	const char *unit = NULL;
 
 	if (numerator && denominator) {
-		double ratio = numerator / denominator * 100.0;
-		const char *color = get_ratio_color(color_ratios, ratio);
-
-		out->print_metric(config, out->ctx, color, "%7.2f%%", unit, ratio);
-	} else
-		out->print_metric(config, out->ctx, NULL, NULL, unit, 0);
+		ratio = numerator / denominator * 100.0;
+		color = get_ratio_color(color_ratios, ratio);
+		fmt = "%7.2f%%";
+		unit = _unit;
+	}
+	out->print_metric(config, out->ctx, color, fmt, unit, ratio);
 }
 
 static void print_stalled_cycles_front(struct perf_stat_config *config,
@@ -320,14 +324,15 @@ static void print_instructions(struct perf_stat_config *config,
 				find_stat(evsel, aggr_idx, STAT_STALLED_CYCLES_BACK));
 
 	if (cycles) {
-		print_metric(config, ctxp, NULL, "%7.2f ", "insn per cycle",
-			instructions / cycles);
-	} else
-		print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
+		print_metric(config, ctxp, /*color=*/NULL, "%7.2f ", "insn per cycle",
+			     instructions / cycles);
+	} else {
+		print_metric(config, ctxp, /*color=*/NULL, /*fmt=*/NULL, "insn per cycle", 0);
+	}
 
 	if (max_stalled && instructions) {
 		out->new_line(config, ctxp);
-		print_metric(config, ctxp, NULL, "%7.2f ", "stalled cycles per insn",
+		print_metric(config, ctxp, /*color=*/NULL, "%7.2f ", "stalled cycles per insn",
 			max_stalled / instructions);
 	}
 }
@@ -342,9 +347,10 @@ static void print_cycles(struct perf_stat_config *config,
 	if (cycles && nsecs) {
 		double ratio = cycles / nsecs;
 
-		out->print_metric(config, out->ctx, NULL, "%8.3f", "GHz", ratio);
-	} else
-		out->print_metric(config, out->ctx, NULL, NULL, "GHz", 0);
+		out->print_metric(config, out->ctx, /*color=*/NULL, "%8.3f", "GHz", ratio);
+	} else {
+		out->print_metric(config, out->ctx, /*color=*/NULL, /*fmt=*/NULL, "GHz", 0);
+	}
 }
 
 static void print_nsecs(struct perf_stat_config *config,
@@ -357,10 +363,11 @@ static void print_nsecs(struct perf_stat_config *config,
 	double wall_time = avg_stats(&walltime_nsecs_stats);
 
 	if (wall_time) {
-		print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized",
+		print_metric(config, ctxp, /*color=*/NULL, "%8.3f", "CPUs utilized",
 			nsecs / (wall_time * evsel->scale));
-	} else
-		print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
+	} else {
+		print_metric(config, ctxp, /*color=*/NULL, /*fmt=*/NULL, "CPUs utilized", 0);
+	}
 }
 
 static int prepare_metric(const struct metric_expr *mexp,
@@ -542,12 +549,12 @@ static void generic_metric(struct perf_stat_config *config,
 					ratio);
 			}
 		} else {
-			print_metric(config, ctxp, color, /*unit=*/NULL,
+			print_metric(config, ctxp, color, /*fmt=*/NULL,
 				     out->force_header ?
 				     (metric_name ?: evsel->name) : "", 0);
 		}
 	} else {
-		print_metric(config, ctxp, color, /*unit=*/NULL,
+		print_metric(config, ctxp, color, /*fmt=*/NULL,
 			     out->force_header ?
 			     (metric_name ?: evsel->name) : "", 0);
 	}
@@ -718,9 +725,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 				if (unit != ' ')
 					snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
-				print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
-			} else
+				print_metric(config, ctxp, /*color=*/NULL, "%8.3f",
+					     unit_buf, ratio);
+			} else {
 				num = 0;
+			}
 		}
 	}
 
@@ -728,7 +737,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 						  &num, NULL, out, metric_events);
 
 	if (num == 0)
-		print_metric(config, ctxp, NULL, NULL, NULL, 0);
+		print_metric(config, ctxp, /*color=*/NULL, /*fmt=*/NULL, /*unit=*/NULL, 0);
 }
 
 /**
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index fd7a187551bd1..a5f3d7d001017 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -155,8 +155,10 @@ extern struct stats walltime_nsecs_stats;
 extern struct rusage_stats ru_stats;
 
 typedef void (*print_metric_t)(struct perf_stat_config *config,
-			       void *ctx, const char *color, const char *unit,
-			       const char *fmt, double val);
+			       void *ctx, const char *color,
+			       const char *fmt,
+			       const char *unit,
+			       double val);
 typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx);
 
 /* Used to print the display name of the Default metricgroup for now. */

From 1133e7f7dc53edcb26c0e07d345f7285c3246efa Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 17 Oct 2024 10:53:52 -0700
Subject: [PATCH 0470/1530] perf stat: Display "none" for NaN with metric only
 json

Return earlier for an empty unit case. If snprintf of the fmt doesn't
produce digits between vals and ends, as happens with NaN, make the
value "none" as happens in print_metric_end.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20241017175356.783793-4-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/stat-display.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index ef0ca8cd802dd..a137b377efa49 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -610,19 +610,22 @@ static void print_metric_only_json(struct perf_stat_config *config __maybe_unuse
 {
 	struct outstate *os = ctx;
 	FILE *out = os->fh;
-	char buf[64], *vals, *ends;
+	char buf[64], *ends;
 	char tbuf[1024];
+	const char *vals;
 
 	if (!valid_only_metric(unit))
 		return;
 	unit = fixunit(tbuf, os->evsel, unit);
+	if (!unit[0])
+		return;
 	snprintf(buf, sizeof(buf), fmt ?: "", val);
-	ends = vals = skip_spaces(buf);
+	vals = ends = skip_spaces(buf);
 	while (isdigit(*ends) || *ends == '.')
 		ends++;
 	*ends = 0;
-	if (!unit[0] || !vals[0])
-		return;
+	if (!vals[0])
+		vals = "none";
 	fprintf(out, "%s\"%s\" : \"%s\"", os->first ? "" : ", ", unit, vals);
 	os->first = false;
 }

From e1cc918b6cfd12064f9b085f4c5b059d183bd8c6 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 17 Oct 2024 10:53:53 -0700
Subject: [PATCH 0471/1530] perf stat: Drop metric-unit if unit is NULL

Avoid cases like:
```
$ perf stat -a -M topdownl1 -j -I 1000
...
{"interval" : 11.127757275, "counter-value" : "85715898.000000", "unit" : "", "event" : "IDQ.MITE_UOPS", "event-runtime" : 988376123, "pcnt-running" : 100.00, "metric-value" : "0.000000", "metric-unit" : "(null)"}
...
```

If there is no unit then drop the metric-value too as:
Suggested-by: Tim Chen <tim.c.chen@linux.intel.com>

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20241017175356.783793-5-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/stat-display.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index a137b377efa49..c6d33010ed22a 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -471,8 +471,8 @@ static void print_metric_json(struct perf_stat_config *config __maybe_unused,
 	struct outstate *os = ctx;
 	FILE *out = os->fh;
 
-	fprintf(out, "\"metric-value\" : \"%f\", ", val);
-	fprintf(out, "\"metric-unit\" : \"%s\"", unit);
+	if (unit)
+		fprintf(out, "\"metric-value\" : \"%f\", \"metric-unit\" : \"%s\"", val, unit);
 	if (!config->metric_only)
 		fprintf(out, "}");
 }

From 37b77ae954167f0ed1bf3dd610b319eeb43cf854 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 17 Oct 2024 10:53:54 -0700
Subject: [PATCH 0472/1530] perf stat: Change color to threshold in
 print_metric

Colors don't mean things in CSV and JSON output, switch to a threshold
enum value that the standard output can convert to a color. Updating
the CSV and JSON output will be later changes.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20241017175356.783793-6-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/x86/util/iostat.c |   2 +-
 tools/perf/builtin-script.c       |   6 +-
 tools/perf/util/stat-display.c    |  40 ++++++++----
 tools/perf/util/stat-shadow.c     | 105 +++++++++++++++---------------
 tools/perf/util/stat.h            |  12 +++-
 5 files changed, 97 insertions(+), 68 deletions(-)

diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c
index df7b5dfcc26a5..366b44d0bb7e5 100644
--- a/tools/perf/arch/x86/util/iostat.c
+++ b/tools/perf/arch/x86/util/iostat.c
@@ -444,7 +444,7 @@ void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel,
 		iostat_value = (count->val - prev_count_val) /
 			       ((double) count->run / count->ena);
 	}
-	out->print_metric(config, out->ctx, NULL, "%8.0f", iostat_metric,
+	out->print_metric(config, out->ctx, METRIC_THRESHOLD_UNKNOWN, "%8.0f", iostat_metric,
 			  iostat_value / (256 * 1024));
 }
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index a644787fa9e1d..8c5d5cecfba48 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2136,11 +2136,11 @@ struct metric_ctx {
 };
 
 static void script_print_metric(struct perf_stat_config *config __maybe_unused,
-				void *ctx, const char *color,
-			        const char *fmt,
-			        const char *unit, double val)
+				void *ctx, enum metric_threshold_classify thresh,
+				const char *fmt, const char *unit, double val)
 {
 	struct metric_ctx *mctx = ctx;
+	const char *color = metric_threshold_classify__color(thresh);
 
 	if (!fmt)
 		return;
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index c6d33010ed22a..5974aaead95f9 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -73,6 +73,19 @@ static const char *aggr_header_std[] = {
 	[AGGR_GLOBAL] 	=	""
 };
 
+const char *metric_threshold_classify__color(enum metric_threshold_classify thresh)
+{
+	const char * const colors[] = {
+		"", /* unknown */
+		PERF_COLOR_RED,     /* bad */
+		PERF_COLOR_MAGENTA, /* nearly bad */
+		PERF_COLOR_YELLOW,  /* less good */
+		PERF_COLOR_GREEN,   /* good */
+	};
+	static_assert(ARRAY_SIZE(colors) - 1  == METRIC_THRESHOLD_GOOD, "missing enum value");
+	return colors[thresh];
+}
+
 static void print_running_std(struct perf_stat_config *config, u64 run, u64 ena)
 {
 	if (run != ena)
@@ -405,13 +418,14 @@ static void do_new_line_std(struct perf_stat_config *config,
 }
 
 static void print_metric_std(struct perf_stat_config *config,
-			     void *ctx, const char *color, const char *fmt,
-			     const char *unit, double val)
+			     void *ctx, enum metric_threshold_classify thresh,
+			     const char *fmt, const char *unit, double val)
 {
 	struct outstate *os = ctx;
 	FILE *out = os->fh;
 	int n;
 	bool newline = os->newline;
+	const char *color = metric_threshold_classify__color(thresh);
 
 	os->newline = false;
 
@@ -443,7 +457,7 @@ static void new_line_csv(struct perf_stat_config *config, void *ctx)
 
 static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
 			     void *ctx,
-			     const char *color __maybe_unused,
+			     enum metric_threshold_classify thresh __maybe_unused,
 			     const char *fmt, const char *unit, double val)
 {
 	struct outstate *os = ctx;
@@ -464,7 +478,7 @@ static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
 
 static void print_metric_json(struct perf_stat_config *config __maybe_unused,
 			     void *ctx,
-			     const char *color __maybe_unused,
+			     enum metric_threshold_classify thresh __maybe_unused,
 			     const char *fmt __maybe_unused,
 			     const char *unit, double val)
 {
@@ -559,13 +573,14 @@ static const char *fixunit(char *buf, struct evsel *evsel,
 }
 
 static void print_metric_only(struct perf_stat_config *config,
-			      void *ctx, const char *color, const char *fmt,
-			      const char *unit, double val)
+			      void *ctx, enum metric_threshold_classify thresh,
+			      const char *fmt, const char *unit, double val)
 {
 	struct outstate *os = ctx;
 	FILE *out = os->fh;
 	char buf[1024], str[1024];
 	unsigned mlen = config->metric_only_len;
+	const char *color = metric_threshold_classify__color(thresh);
 
 	if (!valid_only_metric(unit))
 		return;
@@ -582,7 +597,8 @@ static void print_metric_only(struct perf_stat_config *config,
 }
 
 static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused,
-				  void *ctx, const char *color __maybe_unused,
+				  void *ctx,
+				  enum metric_threshold_classify thresh __maybe_unused,
 				  const char *fmt,
 				  const char *unit, double val)
 {
@@ -604,7 +620,8 @@ static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused
 }
 
 static void print_metric_only_json(struct perf_stat_config *config __maybe_unused,
-				  void *ctx, const char *color __maybe_unused,
+				  void *ctx,
+				  enum metric_threshold_classify thresh __maybe_unused,
 				  const char *fmt,
 				  const char *unit, double val)
 {
@@ -636,7 +653,8 @@ static void new_line_metric(struct perf_stat_config *config __maybe_unused,
 }
 
 static void print_metric_header(struct perf_stat_config *config,
-				void *ctx, const char *color __maybe_unused,
+				void *ctx,
+				enum metric_threshold_classify thresh __maybe_unused,
 				const char *fmt __maybe_unused,
 				const char *unit, double val __maybe_unused)
 {
@@ -810,7 +828,7 @@ static void printout(struct perf_stat_config *config, struct outstate *os,
 
 	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
 		if (config->metric_only) {
-			pm(config, os, NULL, "", "", 0);
+			pm(config, os, METRIC_THRESHOLD_UNKNOWN, "", "", 0);
 			return;
 		}
 
@@ -865,7 +883,7 @@ static void printout(struct perf_stat_config *config, struct outstate *os,
 			perf_stat__print_shadow_stats(config, counter, uval, aggr_idx,
 						      &out, &config->metric_events);
 	} else {
-		pm(config, os, /*color=*/NULL, /*format=*/NULL, /*unit=*/"", /*val=*/0);
+		pm(config, os, METRIC_THRESHOLD_UNKNOWN, /*format=*/NULL, /*unit=*/"", /*val=*/0);
 	}
 
 	if (!config->metric_only) {
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 512890d50b690..ada787947e163 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -137,18 +137,14 @@ static enum stat_type evsel__stat_type(struct evsel *evsel)
 	return STAT_NONE;
 }
 
-static const char *get_ratio_color(const double ratios[3], double val)
+static enum metric_threshold_classify get_ratio_thresh(const double ratios[3], double val)
 {
-	const char *color = PERF_COLOR_NORMAL;
+	assert(ratios[0] > ratios[1]);
+	assert(ratios[1] > ratios[2]);
 
-	if (val > ratios[0])
-		color = PERF_COLOR_RED;
-	else if (val > ratios[1])
-		color = PERF_COLOR_MAGENTA;
-	else if (val > ratios[2])
-		color = PERF_COLOR_YELLOW;
-
-	return color;
+	return val > ratios[1]
+		? (val > ratios[0] ? METRIC_THRESHOLD_BAD : METRIC_THRESHOLD_NEARLY_BAD)
+		: (val > ratios[2] ? METRIC_THRESHOLD_LESS_GOOD : METRIC_THRESHOLD_GOOD);
 }
 
 static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type type)
@@ -196,21 +192,21 @@ static void print_ratio(struct perf_stat_config *config,
 			const struct evsel *evsel, int aggr_idx,
 			double numerator, struct perf_stat_output_ctx *out,
 			enum stat_type denominator_type,
-			const double color_ratios[3], const char *_unit)
+			const double thresh_ratios[3], const char *_unit)
 {
 	double denominator = find_stat(evsel, aggr_idx, denominator_type);
 	double ratio = 0;
-	const char *color = NULL;
+	enum metric_threshold_classify thresh = METRIC_THRESHOLD_UNKNOWN;
 	const char *fmt = NULL;
 	const char *unit = NULL;
 
 	if (numerator && denominator) {
 		ratio = numerator / denominator * 100.0;
-		color = get_ratio_color(color_ratios, ratio);
+		thresh = get_ratio_thresh(thresh_ratios, ratio);
 		fmt = "%7.2f%%";
 		unit = _unit;
 	}
-	out->print_metric(config, out->ctx, color, fmt, unit, ratio);
+	out->print_metric(config, out->ctx, thresh, fmt, unit, ratio);
 }
 
 static void print_stalled_cycles_front(struct perf_stat_config *config,
@@ -218,9 +214,9 @@ static void print_stalled_cycles_front(struct perf_stat_config *config,
 				int aggr_idx, double stalled,
 				struct perf_stat_output_ctx *out)
 {
-	static const double color_ratios[3] = {50.0, 30.0, 10.0};
+	const double thresh_ratios[3] = {50.0, 30.0, 10.0};
 
-	print_ratio(config, evsel, aggr_idx, stalled, out, STAT_CYCLES, color_ratios,
+	print_ratio(config, evsel, aggr_idx, stalled, out, STAT_CYCLES, thresh_ratios,
 		    "frontend cycles idle");
 }
 
@@ -229,9 +225,9 @@ static void print_stalled_cycles_back(struct perf_stat_config *config,
 				int aggr_idx, double stalled,
 				struct perf_stat_output_ctx *out)
 {
-	static const double color_ratios[3] = {75.0, 50.0, 20.0};
+	const double thresh_ratios[3] = {75.0, 50.0, 20.0};
 
-	print_ratio(config, evsel, aggr_idx, stalled, out, STAT_CYCLES, color_ratios,
+	print_ratio(config, evsel, aggr_idx, stalled, out, STAT_CYCLES, thresh_ratios,
 		    "backend cycles idle");
 }
 
@@ -240,9 +236,9 @@ static void print_branch_miss(struct perf_stat_config *config,
 			int aggr_idx, double misses,
 			struct perf_stat_output_ctx *out)
 {
-	static const double color_ratios[3] = {20.0, 10.0, 5.0};
+	const double thresh_ratios[3] = {20.0, 10.0, 5.0};
 
-	print_ratio(config, evsel, aggr_idx, misses, out, STAT_BRANCHES, color_ratios,
+	print_ratio(config, evsel, aggr_idx, misses, out, STAT_BRANCHES, thresh_ratios,
 		    "of all branches");
 }
 
@@ -251,9 +247,9 @@ static void print_l1d_miss(struct perf_stat_config *config,
 			int aggr_idx, double misses,
 			struct perf_stat_output_ctx *out)
 {
-	static const double color_ratios[3] = {20.0, 10.0, 5.0};
+	const double thresh_ratios[3] = {20.0, 10.0, 5.0};
 
-	print_ratio(config, evsel, aggr_idx, misses, out, STAT_L1_DCACHE, color_ratios,
+	print_ratio(config, evsel, aggr_idx, misses, out, STAT_L1_DCACHE, thresh_ratios,
 		    "of all L1-dcache accesses");
 }
 
@@ -262,9 +258,9 @@ static void print_l1i_miss(struct perf_stat_config *config,
 			int aggr_idx, double misses,
 			struct perf_stat_output_ctx *out)
 {
-	static const double color_ratios[3] = {20.0, 10.0, 5.0};
+	const double thresh_ratios[3] = {20.0, 10.0, 5.0};
 
-	print_ratio(config, evsel, aggr_idx, misses, out, STAT_L1_ICACHE, color_ratios,
+	print_ratio(config, evsel, aggr_idx, misses, out, STAT_L1_ICACHE, thresh_ratios,
 		    "of all L1-icache accesses");
 }
 
@@ -273,9 +269,9 @@ static void print_ll_miss(struct perf_stat_config *config,
 			int aggr_idx, double misses,
 			struct perf_stat_output_ctx *out)
 {
-	static const double color_ratios[3] = {20.0, 10.0, 5.0};
+	const double thresh_ratios[3] = {20.0, 10.0, 5.0};
 
-	print_ratio(config, evsel, aggr_idx, misses, out, STAT_LL_CACHE, color_ratios,
+	print_ratio(config, evsel, aggr_idx, misses, out, STAT_LL_CACHE, thresh_ratios,
 		    "of all LL-cache accesses");
 }
 
@@ -284,9 +280,9 @@ static void print_dtlb_miss(struct perf_stat_config *config,
 			int aggr_idx, double misses,
 			struct perf_stat_output_ctx *out)
 {
-	static const double color_ratios[3] = {20.0, 10.0, 5.0};
+	const double thresh_ratios[3] = {20.0, 10.0, 5.0};
 
-	print_ratio(config, evsel, aggr_idx, misses, out, STAT_DTLB_CACHE, color_ratios,
+	print_ratio(config, evsel, aggr_idx, misses, out, STAT_DTLB_CACHE, thresh_ratios,
 		    "of all dTLB cache accesses");
 }
 
@@ -295,9 +291,9 @@ static void print_itlb_miss(struct perf_stat_config *config,
 			int aggr_idx, double misses,
 			struct perf_stat_output_ctx *out)
 {
-	static const double color_ratios[3] = {20.0, 10.0, 5.0};
+	const double thresh_ratios[3] = {20.0, 10.0, 5.0};
 
-	print_ratio(config, evsel, aggr_idx, misses, out, STAT_ITLB_CACHE, color_ratios,
+	print_ratio(config, evsel, aggr_idx, misses, out, STAT_ITLB_CACHE, thresh_ratios,
 		    "of all iTLB cache accesses");
 }
 
@@ -306,9 +302,9 @@ static void print_cache_miss(struct perf_stat_config *config,
 			int aggr_idx, double misses,
 			struct perf_stat_output_ctx *out)
 {
-	static const double color_ratios[3] = {20.0, 10.0, 5.0};
+	const double thresh_ratios[3] = {20.0, 10.0, 5.0};
 
-	print_ratio(config, evsel, aggr_idx, misses, out, STAT_CACHE_REFS, color_ratios,
+	print_ratio(config, evsel, aggr_idx, misses, out, STAT_CACHE_REFS, thresh_ratios,
 		    "of all cache refs");
 }
 
@@ -324,16 +320,16 @@ static void print_instructions(struct perf_stat_config *config,
 				find_stat(evsel, aggr_idx, STAT_STALLED_CYCLES_BACK));
 
 	if (cycles) {
-		print_metric(config, ctxp, /*color=*/NULL, "%7.2f ", "insn per cycle",
-			     instructions / cycles);
+		print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, "%7.2f ",
+			     "insn per cycle", instructions / cycles);
 	} else {
-		print_metric(config, ctxp, /*color=*/NULL, /*fmt=*/NULL, "insn per cycle", 0);
+		print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, /*fmt=*/NULL,
+			     "insn per cycle", 0);
 	}
-
 	if (max_stalled && instructions) {
 		out->new_line(config, ctxp);
-		print_metric(config, ctxp, /*color=*/NULL, "%7.2f ", "stalled cycles per insn",
-			max_stalled / instructions);
+		print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, "%7.2f ",
+			     "stalled cycles per insn", max_stalled / instructions);
 	}
 }
 
@@ -347,9 +343,11 @@ static void print_cycles(struct perf_stat_config *config,
 	if (cycles && nsecs) {
 		double ratio = cycles / nsecs;
 
-		out->print_metric(config, out->ctx, /*color=*/NULL, "%8.3f", "GHz", ratio);
+		out->print_metric(config, out->ctx, METRIC_THRESHOLD_UNKNOWN, "%8.3f",
+				  "GHz", ratio);
 	} else {
-		out->print_metric(config, out->ctx, /*color=*/NULL, /*fmt=*/NULL, "GHz", 0);
+		out->print_metric(config, out->ctx, METRIC_THRESHOLD_UNKNOWN, /*fmt=*/NULL,
+				  "GHz", 0);
 	}
 }
 
@@ -363,10 +361,11 @@ static void print_nsecs(struct perf_stat_config *config,
 	double wall_time = avg_stats(&walltime_nsecs_stats);
 
 	if (wall_time) {
-		print_metric(config, ctxp, /*color=*/NULL, "%8.3f", "CPUs utilized",
+		print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, "%8.3f", "CPUs utilized",
 			nsecs / (wall_time * evsel->scale));
 	} else {
-		print_metric(config, ctxp, /*color=*/NULL, /*fmt=*/NULL, "CPUs utilized", 0);
+		print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, /*fmt=*/NULL,
+			     "CPUs utilized", 0);
 	}
 }
 
@@ -500,7 +499,7 @@ static void generic_metric(struct perf_stat_config *config,
 	double ratio, scale, threshold;
 	int i;
 	void *ctxp = out->ctx;
-	const char *color = NULL;
+	enum metric_threshold_classify thresh = METRIC_THRESHOLD_UNKNOWN;
 
 	pctx = expr__ctx_new();
 	if (!pctx)
@@ -523,8 +522,8 @@ static void generic_metric(struct perf_stat_config *config,
 			if (metric_threshold &&
 			    expr__parse(&threshold, pctx, metric_threshold) == 0 &&
 			    !isnan(threshold)) {
-				color = fpclassify(threshold) == FP_ZERO
-					? PERF_COLOR_GREEN : PERF_COLOR_RED;
+				thresh = fpclassify(threshold) == FP_ZERO
+					? METRIC_THRESHOLD_GOOD : METRIC_THRESHOLD_BAD;
 			}
 
 			if (metric_unit && metric_name) {
@@ -539,22 +538,22 @@ static void generic_metric(struct perf_stat_config *config,
 					scnprintf(metric_bf, sizeof(metric_bf),
 					  "%s  %s", unit, metric_name);
 
-				print_metric(config, ctxp, color, "%8.1f",
+				print_metric(config, ctxp, thresh, "%8.1f",
 					     metric_bf, ratio);
 			} else {
-				print_metric(config, ctxp, color, "%8.2f",
+				print_metric(config, ctxp, thresh, "%8.2f",
 					metric_name ?
 					metric_name :
 					out->force_header ?  evsel->name : "",
 					ratio);
 			}
 		} else {
-			print_metric(config, ctxp, color, /*fmt=*/NULL,
+			print_metric(config, ctxp, thresh, /*fmt=*/NULL,
 				     out->force_header ?
 				     (metric_name ?: evsel->name) : "", 0);
 		}
 	} else {
-		print_metric(config, ctxp, color, /*fmt=*/NULL,
+		print_metric(config, ctxp, thresh, /*fmt=*/NULL,
 			     out->force_header ?
 			     (metric_name ?: evsel->name) : "", 0);
 	}
@@ -725,7 +724,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 				if (unit != ' ')
 					snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
-				print_metric(config, ctxp, /*color=*/NULL, "%8.3f",
+				print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, "%8.3f",
 					     unit_buf, ratio);
 			} else {
 				num = 0;
@@ -736,8 +735,10 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 	perf_stat__print_shadow_stats_metricgroup(config, evsel, aggr_idx,
 						  &num, NULL, out, metric_events);
 
-	if (num == 0)
-		print_metric(config, ctxp, /*color=*/NULL, /*fmt=*/NULL, /*unit=*/NULL, 0);
+	if (num == 0) {
+		print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN,
+			     /*fmt=*/NULL, /*unit=*/NULL, 0);
+	}
 }
 
 /**
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index a5f3d7d001017..6f8cff3cd39a4 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -154,8 +154,18 @@ struct evlist;
 extern struct stats walltime_nsecs_stats;
 extern struct rusage_stats ru_stats;
 
+enum metric_threshold_classify {
+	METRIC_THRESHOLD_UNKNOWN,
+	METRIC_THRESHOLD_BAD,
+	METRIC_THRESHOLD_NEARLY_BAD,
+	METRIC_THRESHOLD_LESS_GOOD,
+	METRIC_THRESHOLD_GOOD,
+};
+const char *metric_threshold_classify__color(enum metric_threshold_classify thresh);
+
 typedef void (*print_metric_t)(struct perf_stat_config *config,
-			       void *ctx, const char *color,
+			       void *ctx,
+			       enum metric_threshold_classify thresh,
 			       const char *fmt,
 			       const char *unit,
 			       double val);

From f9825601aa5e8f45a21ead5dd9b48e7f5119b3b0 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 17 Oct 2024 10:53:55 -0700
Subject: [PATCH 0473/1530] perf stat: Add metric-threshold to json output

When the threshold isn't unknown add a value to the json like:
"metric-threshold" : "good"

A more complete example:
```
$ perf stat -a -j -I 1000
{"interval" : 1.001089747, "counter-value" : "16045.281449", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 16045355135, "pcnt-running" : 100.00, "metric-value" : "16.045281", "metric-unit" : "CPUs utilized"}
{"interval" : 1.001089747, "counter-value" : "10003.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 16045314844, "pcnt-running" : 100.00, "metric-value" : "623.423156", "metric-unit" : "/sec"}
{"interval" : 1.001089747, "counter-value" : "328.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 16045321403, "pcnt-running" : 100.00, "metric-value" : "20.442147", "metric-unit" : "/sec"}
{"interval" : 1.001089747, "counter-value" : "20114.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 16045355927, "pcnt-running" : 100.00, "metric-value" : "1.253577", "metric-unit" : "K/sec"}
{"interval" : 1.001089747, "counter-value" : "4066679471.000000", "unit" : "", "event" : "instructions", "event-runtime" : 16045369123, "pcnt-running" : 100.00, "metric-value" : "1.628330", "metric-unit" : "insn per cycle"}
{"interval" : 1.001089747, "counter-value" : "2497454658.000000", "unit" : "", "event" : "cycles", "event-runtime" : 16045374810, "pcnt-running" : 100.00, "metric-value" : "0.155650", "metric-unit" : "GHz"}
{"interval" : 1.001089747, "counter-value" : "914974294.000000", "unit" : "", "event" : "branches", "event-runtime" : 16045379877, "pcnt-running" : 100.00, "metric-value" : "57.024509", "metric-unit" : "M/sec"}
{"interval" : 1.001089747, "counter-value" : "9237201.000000", "unit" : "", "event" : "branch-misses", "event-runtime" : 16045375017, "pcnt-running" : 100.00, "metric-value" : "1.009559", "metric-unit" : "of all branches", "metric-threshold" : "good"}
{"interval" : 1.001089747, "event-runtime" : 16045397172, "pcnt-running" : 100.00, "metricgroup" : "TopdownL1"}
{"interval" : 1.001089747, "metric-value" : "22.036686", "metric-unit" : "%  tma_backend_bound", "metric-threshold" : "bad"}
{"interval" : 1.001089747, "metric-value" : "7.610161", "metric-unit" : "%  tma_bad_speculation", "metric-threshold" : "good"}
{"interval" : 1.001089747, "metric-value" : "36.729687", "metric-unit" : "%  tma_frontend_bound", "metric-threshold" : "bad"}
{"interval" : 1.001089747, "metric-value" : "33.623465", "metric-unit" : "%  tma_retiring"}
...
```

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20241017175356.783793-7-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../tests/shell/lib/perf_json_output_lint.py  |  5 ++++-
 tools/perf/util/stat-display.c                | 22 +++++++++++++++++--
 2 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/shell/lib/perf_json_output_lint.py b/tools/perf/tests/shell/lib/perf_json_output_lint.py
index abc1fd7377822..8ddb855861319 100644
--- a/tools/perf/tests/shell/lib/perf_json_output_lint.py
+++ b/tools/perf/tests/shell/lib/perf_json_output_lint.py
@@ -57,6 +57,7 @@ def check_json_output(expected_items):
       'interval': lambda x: isfloat(x),
       'metric-unit': lambda x: True,
       'metric-value': lambda x: isfloat(x),
+      'metric-threshold': lambda x: x in ['unknown', 'good', 'less good', 'nearly bad', 'bad'],
       'metricgroup': lambda x: True,
       'node': lambda x: True,
       'pcnt-running': lambda x: isfloat(x),
@@ -68,13 +69,15 @@ def check_json_output(expected_items):
   for item in json.loads(input):
     if expected_items != -1:
       count = len(item)
-      if count != expected_items and count >= 1 and count <= 6 and 'metric-value' in item:
+      if count != expected_items and count >= 1 and count <= 7 and 'metric-value' in item:
         # Events that generate >1 metric may have isolated metric
         # values and possibly other prefixes like interval, core,
         # aggregate-number, or event-runtime/pcnt-running from multiplexing.
         pass
       elif count != expected_items and count >= 1 and count <= 5 and 'metricgroup' in item:
         pass
+      elif count == expected_items + 1 and 'metric-threshold' in item:
+          pass
       elif count != expected_items:
         raise RuntimeError(f'wrong number of fields. counted {count} expected {expected_items}'
                            f' in \'{item}\'')
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 5974aaead95f9..53dcdf07f5a21 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -86,6 +86,19 @@ const char *metric_threshold_classify__color(enum metric_threshold_classify thre
 	return colors[thresh];
 }
 
+static const char *metric_threshold_classify__str(enum metric_threshold_classify thresh)
+{
+	const char * const strs[] = {
+		"unknown",
+		"bad",
+		"nearly bad",
+		"less good",
+		"good",
+	};
+	static_assert(ARRAY_SIZE(strs) - 1  == METRIC_THRESHOLD_GOOD, "missing enum value");
+	return strs[thresh];
+}
+
 static void print_running_std(struct perf_stat_config *config, u64 run, u64 ena)
 {
 	if (run != ena)
@@ -478,15 +491,20 @@ static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
 
 static void print_metric_json(struct perf_stat_config *config __maybe_unused,
 			     void *ctx,
-			     enum metric_threshold_classify thresh __maybe_unused,
+			     enum metric_threshold_classify thresh,
 			     const char *fmt __maybe_unused,
 			     const char *unit, double val)
 {
 	struct outstate *os = ctx;
 	FILE *out = os->fh;
 
-	if (unit)
+	if (unit) {
 		fprintf(out, "\"metric-value\" : \"%f\", \"metric-unit\" : \"%s\"", val, unit);
+		if (thresh != METRIC_THRESHOLD_UNKNOWN) {
+			fprintf(out, ", \"metric-threshold\" : \"%s\"",
+				metric_threshold_classify__str(thresh));
+		}
+	}
 	if (!config->metric_only)
 		fprintf(out, "}");
 }

From 17df33fe22c71e0b07567e3c3c35c678b08e8689 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 17 Oct 2024 10:53:56 -0700
Subject: [PATCH 0474/1530] perf stat: Disable metric thresholds for CSV and
 JSON metric-only mode

These modes don't use the threshold, so don't compute it saving time
and potentially reducing events.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20241017175356.783793-8-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-stat.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b5e18853982cd..7639ecda6c05f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2561,6 +2561,14 @@ int cmd_stat(int argc, const char **argv)
 		goto out;
 	}
 
+	if (stat_config.csv_output || (stat_config.metric_only && stat_config.json_output)) {
+		/*
+		 * Current CSV and metric-only JSON output doesn't display the
+		 * metric threshold so don't compute it.
+		 */
+		stat_config.metric_no_threshold = true;
+	}
+
 	if (stat_config.walltime_run_table && stat_config.run_count <= 1) {
 		fprintf(stderr, "--table is only supported with -r\n");
 		parse_options_usage(stat_usage, stat_options, "r", 1);

From 314909f13cc12d47c468602c37dace512d225eeb Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Sat, 12 Oct 2024 15:14:32 +0100
Subject: [PATCH 0475/1530] perf probe: Correct demangled symbols in C++
 program

An issue can be observed when probe C++ demangled symbol with steps:

  # nm test_cpp_mangle | grep print_data
    0000000000000c94 t _GLOBAL__sub_I__Z10print_datai
    0000000000000afc T _Z10print_datai
    0000000000000b38 T _Z10print_dataR5Point

  # perf probe -x /home/niayan01/test_cpp_mangle -F --demangle
    ...
    print_data(Point&)
    print_data(int)
    ...

  # perf --debug verbose=3 probe -x test_cpp_mangle --add "test=print_data(int)"
    probe-definition(0): test=print_data(int)
    symbol:print_data(int) file:(null) line:0 offset:0 return:0 lazy:(null)
    0 arguments
    Open Debuginfo file: /home/niayan01/test_cpp_mangle
    Try to find probe point from debuginfo.
    Symbol print_data(int) address found : afc
    Matched function: print_data [2ccf]
    Probe point found: print_data+0
    Found 1 probe_trace_events.
    Opening /sys/kernel/tracing//uprobe_events write=1
    Opening /sys/kernel/tracing//README write=0
    Writing event: p:probe_test_cpp_mangle/test /home/niayan01/test_cpp_mangle:0xb38
    ...

When tried to probe symbol "print_data(int)", the log shows:

    Symbol print_data(int) address found : afc

The found address is 0xafc - which is right with verifying the output
result from nm. Afterwards when write event, the command uses offset
0xb38 in the last log, which is a wrong address.

The dwarf_diename() gets a common function name, in above case, it
returns string "print_data". As a result, the tool parses the offset
based on the common name. This leads to probe at the wrong symbol
"print_data(Point&)".

To fix the issue, use the die_get_linkage_name() function to retrieve
the distinct linkage name - this is the mangled name for the C++ case.
Based on this unique name, the tool can get a correct offset for
probing. Based on DWARF doc, it is possible the linkage name is missed
in the DIE, it rolls back to use dwarf_diename().

After:

  # perf --debug verbose=3 probe -x test_cpp_mangle --add "test=print_data(int)"
    probe-definition(0): test=print_data(int)
    symbol:print_data(int) file:(null) line:0 offset:0 return:0 lazy:(null)
    0 arguments
    Open Debuginfo file: /home/niayan01/test_cpp_mangle
    Try to find probe point from debuginfo.
    Symbol print_data(int) address found : afc
    Matched function: print_data [2d06]
    Probe point found: print_data+0
    Found 1 probe_trace_events.
    Opening /sys/kernel/tracing//uprobe_events write=1
    Opening /sys/kernel/tracing//README write=0
    Writing event: p:probe_test_cpp_mangle/test /home/niayan01/test_cpp_mangle:0xafc
    Added new event:
      probe_test_cpp_mangle:test (on print_data(int) in /home/niayan01/test_cpp_mangle)

    You can now use it in all perf tools, such as:

            perf record -e probe_test_cpp_mangle:test -aR sleep 1

  # perf --debug verbose=3 probe -x test_cpp_mangle --add "test2=print_data(Point&)"
    probe-definition(0): test2=print_data(Point&)
    symbol:print_data(Point&) file:(null) line:0 offset:0 return:0 lazy:(null)
    0 arguments
    Open Debuginfo file: /home/niayan01/test_cpp_mangle
    Try to find probe point from debuginfo.
    Symbol print_data(Point&) address found : b38
    Matched function: print_data [2ccf]
    Probe point found: print_data+0
    Found 1 probe_trace_events.
    Opening /sys/kernel/tracing//uprobe_events write=1
    Parsing probe_events: p:probe_test_cpp_mangle/test /home/niayan01/test_cpp_mangle:0x0000000000000afc
    Group:probe_test_cpp_mangle Event:test probe:p
    Opening /sys/kernel/tracing//README write=0
    Writing event: p:probe_test_cpp_mangle/test2 /home/niayan01/test_cpp_mangle:0xb38
    Added new event:
      probe_test_cpp_mangle:test2 (on print_data(Point&) in /home/niayan01/test_cpp_mangle)

    You can now use it in all perf tools, such as:

            perf record -e probe_test_cpp_mangle:test2 -aR sleep 1

Fixes: fb1587d869a3 ("perf probe: List probes with line number and file name")
Signed-off-by: Leo Yan <leo.yan@arm.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20241012141432.877894-1-leo.yan@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/probe-finder.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index d6b902899940b..a30f88ed03004 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1587,8 +1587,21 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr,
 
 	/* Find a corresponding function (name, baseline and baseaddr) */
 	if (die_find_realfunc(&cudie, (Dwarf_Addr)addr, &spdie)) {
-		/* Get function entry information */
-		func = basefunc = dwarf_diename(&spdie);
+		/*
+		 * Get function entry information.
+		 *
+		 * As described in the document DWARF Debugging Information
+		 * Format Version 5, section 2.22 Linkage Names, "mangled names,
+		 * are used in various ways, ... to distinguish multiple
+		 * entities that have the same name".
+		 *
+		 * Firstly try to get distinct linkage name, if fail then
+		 * rollback to get associated name in DIE.
+		 */
+		func = basefunc = die_get_linkage_name(&spdie);
+		if (!func)
+			func = basefunc = dwarf_diename(&spdie);
+
 		if (!func ||
 		    die_entrypc(&spdie, &baseaddr) != 0 ||
 		    dwarf_decl_line(&spdie, &baseline) != 0) {

From 8519e4f44c2af72214dc029f0334be068466e71f Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 14 Oct 2024 17:01:56 -0700
Subject: [PATCH 0476/1530] perf test: Add a shell wrapper for "Setup struct
 perf_event_attr"

The "Setup struct perf_event_attr" test in attr.c does a bunch of
directory finding to set up running a python test that in general is
more brittle than similar logic we have in shell tests. Add a shell
test that invokes and runs the tests in the python attr.py script.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: zhaimingbing <zhaimingbing@cmss.chinamobile.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241015000158.871828-2-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/attr.sh | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)
 create mode 100755 tools/perf/tests/shell/attr.sh

diff --git a/tools/perf/tests/shell/attr.sh b/tools/perf/tests/shell/attr.sh
new file mode 100755
index 0000000000000..e094f3baffb7c
--- /dev/null
+++ b/tools/perf/tests/shell/attr.sh
@@ -0,0 +1,22 @@
+#!/bin/bash
+# Perf attribute expectations test
+# SPDX-License-Identifier: GPL-2.0
+
+err=0
+
+cleanup() {
+  trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+  echo "Unexpected signal in ${FUNCNAME[1]}"
+  cleanup
+  exit 1
+}
+trap trap_cleanup EXIT TERM INT
+
+shelldir=$(dirname "$0")
+perf_path=$(which perf)
+python "${shelldir}"/../attr.py -d "${shelldir}"/../attr -v -p "$perf_path"
+cleanup
+exit $err

From 3a447031f5fc21c4e112a5ca52d091d1ef33aeb6 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 14 Oct 2024 17:01:57 -0700
Subject: [PATCH 0477/1530] perf test: Remove C test wrapper for attr.py

Remove the C wrapper now a shell script wrapper exists. Move
perf_event_attr dumping functions to evsel.c and reduce the scope of
variables/defines. Use fprintf to avoid snprintf complexities in
WRITE_ASS.

Add __SANE_USERSPACE_TYPES__ to evsel.c to fix format flag issues on
PowerPC triggered by moving attr.c functions to evsel.c.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: zhaimingbing <zhaimingbing@cmss.chinamobile.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241015000158.871828-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/perf.c               |   2 -
 tools/perf/tests/Build          |   1 -
 tools/perf/tests/attr.c         | 218 --------------------------------
 tools/perf/tests/builtin-test.c |   1 -
 tools/perf/util/evsel.c         | 127 ++++++++++++++++++-
 tools/perf/util/util.h          |   7 -
 6 files changed, 123 insertions(+), 233 deletions(-)
 delete mode 100644 tools/perf/tests/attr.c

diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 4def800f4089d..a2987f2cfe1a3 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -542,8 +542,6 @@ int main(int argc, const char **argv)
 	}
 	cmd = argv[0];
 
-	test_attr__init();
-
 	/*
 	 * We use PATH to find perf commands, but we prepend some higher
 	 * precedence paths: the "--exec-path" option, the PERF_EXEC_PATH
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index a771e49282471..03cbdf7c50a09 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -4,7 +4,6 @@ perf-test-y += builtin-test.o
 perf-test-y += tests-scripts.o
 perf-test-y += parse-events.o
 perf-test-y += dso-data.o
-perf-test-y += attr.o
 perf-test-y += vmlinux-kallsyms.o
 perf-test-$(CONFIG_LIBTRACEEVENT) += openat-syscall.o
 perf-test-$(CONFIG_LIBTRACEEVENT) += openat-syscall-all-cpus.o
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
deleted file mode 100644
index 97e1bdd6ec0e9..0000000000000
--- a/tools/perf/tests/attr.c
+++ /dev/null
@@ -1,218 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * The struct perf_event_attr test support.
- *
- * This test is embedded inside into perf directly and is governed
- * by the PERF_TEST_ATTR environment variable and hook inside
- * sys_perf_event_open function.
- *
- * The general idea is to store 'struct perf_event_attr' details for
- * each event created within single perf command. Each event details
- * are stored into separate text file. Once perf command is finished
- * these files can be checked for values we expect for command.
- *
- * Besides 'struct perf_event_attr' values we also store 'fd' and
- * 'group_fd' values to allow checking for groups created.
- *
- * This all is triggered by setting PERF_TEST_ATTR environment variable.
- * It must contain name of existing directory with access and write
- * permissions. All the event text files are stored there.
- */
-
-#include <debug.h>
-#include <errno.h>
-#include <inttypes.h>
-#include <stdlib.h>
-#include <stdio.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <sys/param.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <unistd.h>
-#include <subcmd/exec-cmd.h>
-#include "event.h"
-#include "util.h"
-#include "tests.h"
-#include "pmus.h"
-
-#define ENV "PERF_TEST_ATTR"
-
-static char *dir;
-static bool ready;
-
-void test_attr__init(void)
-{
-	dir = getenv(ENV);
-	test_attr__enabled = (dir != NULL);
-}
-
-#define BUFSIZE 1024
-
-#define __WRITE_ASS(str, fmt, data)					\
-do {									\
-	char buf[BUFSIZE];						\
-	size_t size;							\
-									\
-	size = snprintf(buf, BUFSIZE, #str "=%"fmt "\n", data);		\
-	if (1 != fwrite(buf, size, 1, file)) {				\
-		perror("test attr - failed to write event file");	\
-		fclose(file);						\
-		return -1;						\
-	}								\
-									\
-} while (0)
-
-#define WRITE_ASS(field, fmt) __WRITE_ASS(field, fmt, attr->field)
-
-static int store_event(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
-		       int fd, int group_fd, unsigned long flags)
-{
-	FILE *file;
-	char path[PATH_MAX];
-
-	if (!ready)
-		return 0;
-
-	snprintf(path, PATH_MAX, "%s/event-%d-%llu-%d", dir,
-		 attr->type, attr->config, fd);
-
-	file = fopen(path, "w+");
-	if (!file) {
-		perror("test attr - failed to open event file");
-		return -1;
-	}
-
-	if (fprintf(file, "[event-%d-%llu-%d]\n",
-		    attr->type, attr->config, fd) < 0) {
-		perror("test attr - failed to write event file");
-		fclose(file);
-		return -1;
-	}
-
-	/* syscall arguments */
-	__WRITE_ASS(fd,       "d", fd);
-	__WRITE_ASS(group_fd, "d", group_fd);
-	__WRITE_ASS(cpu,      "d", cpu.cpu);
-	__WRITE_ASS(pid,      "d", pid);
-	__WRITE_ASS(flags,   "lu", flags);
-
-	/* struct perf_event_attr */
-	WRITE_ASS(type,   PRIu32);
-	WRITE_ASS(size,   PRIu32);
-	WRITE_ASS(config,  "llu");
-	WRITE_ASS(sample_period, "llu");
-	WRITE_ASS(sample_type,   "llu");
-	WRITE_ASS(read_format,   "llu");
-	WRITE_ASS(disabled,       "d");
-	WRITE_ASS(inherit,        "d");
-	WRITE_ASS(pinned,         "d");
-	WRITE_ASS(exclusive,      "d");
-	WRITE_ASS(exclude_user,   "d");
-	WRITE_ASS(exclude_kernel, "d");
-	WRITE_ASS(exclude_hv,     "d");
-	WRITE_ASS(exclude_idle,   "d");
-	WRITE_ASS(mmap,           "d");
-	WRITE_ASS(comm,           "d");
-	WRITE_ASS(freq,           "d");
-	WRITE_ASS(inherit_stat,   "d");
-	WRITE_ASS(enable_on_exec, "d");
-	WRITE_ASS(task,           "d");
-	WRITE_ASS(watermark,      "d");
-	WRITE_ASS(precise_ip,     "d");
-	WRITE_ASS(mmap_data,      "d");
-	WRITE_ASS(sample_id_all,  "d");
-	WRITE_ASS(exclude_host,   "d");
-	WRITE_ASS(exclude_guest,  "d");
-	WRITE_ASS(exclude_callchain_kernel, "d");
-	WRITE_ASS(exclude_callchain_user, "d");
-	WRITE_ASS(mmap2,	  "d");
-	WRITE_ASS(comm_exec,	  "d");
-	WRITE_ASS(context_switch, "d");
-	WRITE_ASS(write_backward, "d");
-	WRITE_ASS(namespaces,	  "d");
-	WRITE_ASS(use_clockid,    "d");
-	WRITE_ASS(wakeup_events, PRIu32);
-	WRITE_ASS(bp_type, PRIu32);
-	WRITE_ASS(config1, "llu");
-	WRITE_ASS(config2, "llu");
-	WRITE_ASS(branch_sample_type, "llu");
-	WRITE_ASS(sample_regs_user,   "llu");
-	WRITE_ASS(sample_stack_user,  PRIu32);
-
-	fclose(file);
-	return 0;
-}
-
-void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
-		     int fd, int group_fd, unsigned long flags)
-{
-	int errno_saved = errno;
-
-	if ((fd != -1) && store_event(attr, pid, cpu, fd, group_fd, flags)) {
-		pr_err("test attr FAILED");
-		exit(128);
-	}
-
-	errno = errno_saved;
-}
-
-void test_attr__ready(void)
-{
-	if (unlikely(test_attr__enabled) && !ready)
-		ready = true;
-}
-
-static int run_dir(const char *d, const char *perf)
-{
-	char v[] = "-vvvvv";
-	int vcnt = min(verbose, (int) sizeof(v) - 1);
-	char cmd[3*PATH_MAX];
-
-	if (verbose > 0)
-		vcnt++;
-
-	scnprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s",
-		  d, d, perf, vcnt, v);
-
-	return system(cmd) ? TEST_FAIL : TEST_OK;
-}
-
-static int test__attr(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
-{
-	struct stat st;
-	char path_perf[PATH_MAX];
-	char path_dir[PATH_MAX];
-	char *exec_path;
-
-	if (perf_pmus__num_core_pmus() > 1) {
-		/*
-		 * TODO: Attribute tests hard code the PMU type. If there are >1
-		 * core PMU then each PMU will have a different type which
-		 * requires additional support.
-		 */
-		pr_debug("Skip test on hybrid systems");
-		return TEST_SKIP;
-	}
-
-	/* First try development tree tests. */
-	if (!lstat("./tests", &st))
-		return run_dir("./tests", "./perf");
-
-	exec_path = get_argv_exec_path();
-	if (exec_path == NULL)
-		return -1;
-
-	/* Then installed path. */
-	snprintf(path_dir,  PATH_MAX, "%s/tests", exec_path);
-	snprintf(path_perf, PATH_MAX, "%s/perf", BINDIR);
-	free(exec_path);
-
-	if (!lstat(path_dir, &st) &&
-	    !lstat(path_perf, &st))
-		return run_dir(path_dir, path_perf);
-
-	return TEST_SKIP;
-}
-
-DEFINE_SUITE("Setup struct perf_event_attr", attr);
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 3b30f258c3959..50533446e7478 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -80,7 +80,6 @@ static struct test_suite *generic_tests[] = {
 	&suite__perf_evsel__tp_sched_test,
 	&suite__syscall_openat_tp_fields,
 #endif
-	&suite__attr,
 	&suite__hists_link,
 	&suite__python_use,
 	&suite__bp_signal,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e9e1f576d34dd..14663ad14c531 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -5,6 +5,11 @@
  * Parts came from builtin-{top,stat,record}.c, see those files for further
  * copyright notes.
  */
+/*
+ * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select
+ * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu.
+ */
+#define __SANE_USERSPACE_TYPES__
 
 #include <byteswap.h>
 #include <errno.h>
@@ -76,7 +81,123 @@ static int evsel__no_extra_init(struct evsel *evsel __maybe_unused)
 	return 0;
 }
 
-void __weak test_attr__ready(void) { }
+static bool test_attr__enabled(void)
+{
+	static bool test_attr__enabled;
+	static bool test_attr__enabled_tested;
+
+	if (!test_attr__enabled_tested) {
+		char *dir = getenv("PERF_TEST_ATTR");
+
+		test_attr__enabled = (dir != NULL);
+		test_attr__enabled_tested = true;
+	}
+	return test_attr__enabled;
+}
+
+#define __WRITE_ASS(str, fmt, data)					\
+do {									\
+	if (fprintf(file, #str "=%"fmt "\n", data) < 0) {		\
+		perror("test attr - failed to write event file");	\
+		fclose(file);						\
+		return -1;						\
+	}								\
+} while (0)
+
+#define WRITE_ASS(field, fmt) __WRITE_ASS(field, fmt, attr->field)
+
+static int store_event(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
+		       int fd, int group_fd, unsigned long flags)
+{
+	FILE *file;
+	char path[PATH_MAX];
+	char *dir = getenv("PERF_TEST_ATTR");
+
+	snprintf(path, PATH_MAX, "%s/event-%d-%llu-%d", dir,
+		 attr->type, attr->config, fd);
+
+	file = fopen(path, "w+");
+	if (!file) {
+		perror("test attr - failed to open event file");
+		return -1;
+	}
+
+	if (fprintf(file, "[event-%d-%llu-%d]\n",
+		    attr->type, attr->config, fd) < 0) {
+		perror("test attr - failed to write event file");
+		fclose(file);
+		return -1;
+	}
+
+	/* syscall arguments */
+	__WRITE_ASS(fd,       "d", fd);
+	__WRITE_ASS(group_fd, "d", group_fd);
+	__WRITE_ASS(cpu,      "d", cpu.cpu);
+	__WRITE_ASS(pid,      "d", pid);
+	__WRITE_ASS(flags,   "lu", flags);
+
+	/* struct perf_event_attr */
+	WRITE_ASS(type,   PRIu32);
+	WRITE_ASS(size,   PRIu32);
+	WRITE_ASS(config,  "llu");
+	WRITE_ASS(sample_period, "llu");
+	WRITE_ASS(sample_type,   "llu");
+	WRITE_ASS(read_format,   "llu");
+	WRITE_ASS(disabled,       "d");
+	WRITE_ASS(inherit,        "d");
+	WRITE_ASS(pinned,         "d");
+	WRITE_ASS(exclusive,      "d");
+	WRITE_ASS(exclude_user,   "d");
+	WRITE_ASS(exclude_kernel, "d");
+	WRITE_ASS(exclude_hv,     "d");
+	WRITE_ASS(exclude_idle,   "d");
+	WRITE_ASS(mmap,           "d");
+	WRITE_ASS(comm,           "d");
+	WRITE_ASS(freq,           "d");
+	WRITE_ASS(inherit_stat,   "d");
+	WRITE_ASS(enable_on_exec, "d");
+	WRITE_ASS(task,           "d");
+	WRITE_ASS(watermark,      "d");
+	WRITE_ASS(precise_ip,     "d");
+	WRITE_ASS(mmap_data,      "d");
+	WRITE_ASS(sample_id_all,  "d");
+	WRITE_ASS(exclude_host,   "d");
+	WRITE_ASS(exclude_guest,  "d");
+	WRITE_ASS(exclude_callchain_kernel, "d");
+	WRITE_ASS(exclude_callchain_user, "d");
+	WRITE_ASS(mmap2,	  "d");
+	WRITE_ASS(comm_exec,	  "d");
+	WRITE_ASS(context_switch, "d");
+	WRITE_ASS(write_backward, "d");
+	WRITE_ASS(namespaces,	  "d");
+	WRITE_ASS(use_clockid,    "d");
+	WRITE_ASS(wakeup_events, PRIu32);
+	WRITE_ASS(bp_type, PRIu32);
+	WRITE_ASS(config1, "llu");
+	WRITE_ASS(config2, "llu");
+	WRITE_ASS(branch_sample_type, "llu");
+	WRITE_ASS(sample_regs_user,   "llu");
+	WRITE_ASS(sample_stack_user,  PRIu32);
+
+	fclose(file);
+	return 0;
+}
+
+#undef __WRITE_ASS
+#undef WRITE_ASS
+
+static void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
+		     int fd, int group_fd, unsigned long flags)
+{
+	int errno_saved = errno;
+
+	if ((fd != -1) && store_event(attr, pid, cpu, fd, group_fd, flags)) {
+		pr_err("test attr FAILED");
+		exit(128);
+	}
+
+	errno = errno_saved;
+}
 
 static void evsel__no_extra_fini(struct evsel *evsel __maybe_unused)
 {
@@ -2145,8 +2266,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 				goto out_close;
 			}
 
-			test_attr__ready();
-
 			/* Debug message used by test scripts */
 			pr_debug2_peo("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
 				pid, perf_cpu_map__cpu(cpus, idx).cpu, group_fd, evsel->open_flags);
@@ -2167,7 +2286,7 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 
 			bpf_counter__install_pe(evsel, idx, fd);
 
-			if (unlikely(test_attr__enabled)) {
+			if (unlikely(test_attr__enabled())) {
 				test_attr__open(&evsel->core.attr, pid,
 						perf_cpu_map__cpu(cpus, idx),
 						fd, group_fd, evsel->open_flags);
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 9966c21aaf048..14f2c70906be8 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -81,13 +81,6 @@ char *perf_exe(char *buf, int len);
 #endif
 #endif
 
-extern bool test_attr__enabled;
-void test_attr__ready(void);
-void test_attr__init(void);
-struct perf_event_attr;
-void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
-		     int fd, int group_fd, unsigned long flags);
-
 struct perf_debuginfod {
 	const char	*urls;
 	bool		 set;

From 8296aa0f28c2433f213fce18bad00a97965c052f Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 14 Oct 2024 17:01:58 -0700
Subject: [PATCH 0478/1530] perf test: Move attr files into shell directory
 where they are used

Now the attr tests are shell tests move the associated python and
configuration files. Update the installation build rules for the new
directories. Recycle the lib install rules for python files allowing
the explicit attr.py install line to be dropped.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: zhaimingbing <zhaimingbing@cmss.chinamobile.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241015000158.871828-4-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Makefile.perf                                     | 5 ++---
 tools/perf/tests/shell/attr.sh                               | 2 +-
 tools/perf/tests/{ => shell}/attr/README                     | 0
 tools/perf/tests/{ => shell}/attr/base-record                | 0
 tools/perf/tests/{ => shell}/attr/base-record-spe            | 0
 tools/perf/tests/{ => shell}/attr/base-stat                  | 0
 tools/perf/tests/{ => shell}/attr/system-wide-dummy          | 0
 tools/perf/tests/{ => shell}/attr/test-record-C0             | 0
 tools/perf/tests/{ => shell}/attr/test-record-basic          | 0
 tools/perf/tests/{ => shell}/attr/test-record-branch-any     | 0
 .../tests/{ => shell}/attr/test-record-branch-filter-any     | 0
 .../{ => shell}/attr/test-record-branch-filter-any_call      | 0
 .../tests/{ => shell}/attr/test-record-branch-filter-any_ret | 0
 .../perf/tests/{ => shell}/attr/test-record-branch-filter-hv | 0
 .../{ => shell}/attr/test-record-branch-filter-ind_call      | 0
 .../perf/tests/{ => shell}/attr/test-record-branch-filter-k  | 0
 .../perf/tests/{ => shell}/attr/test-record-branch-filter-u  | 0
 tools/perf/tests/{ => shell}/attr/test-record-count          | 0
 tools/perf/tests/{ => shell}/attr/test-record-data           | 0
 tools/perf/tests/{ => shell}/attr/test-record-dummy-C0       | 0
 tools/perf/tests/{ => shell}/attr/test-record-freq           | 0
 tools/perf/tests/{ => shell}/attr/test-record-graph-default  | 0
 .../tests/{ => shell}/attr/test-record-graph-default-aarch64 | 0
 tools/perf/tests/{ => shell}/attr/test-record-graph-dwarf    | 0
 tools/perf/tests/{ => shell}/attr/test-record-graph-fp       | 0
 .../perf/tests/{ => shell}/attr/test-record-graph-fp-aarch64 | 0
 tools/perf/tests/{ => shell}/attr/test-record-group-sampling | 0
 .../perf/tests/{ => shell}/attr/test-record-group-sampling1  | 0
 .../perf/tests/{ => shell}/attr/test-record-group-sampling2  | 0
 tools/perf/tests/{ => shell}/attr/test-record-group1         | 0
 tools/perf/tests/{ => shell}/attr/test-record-group2         | 0
 tools/perf/tests/{ => shell}/attr/test-record-group3         | 0
 tools/perf/tests/{ => shell}/attr/test-record-no-buffering   | 0
 tools/perf/tests/{ => shell}/attr/test-record-no-inherit     | 0
 tools/perf/tests/{ => shell}/attr/test-record-no-samples     | 0
 tools/perf/tests/{ => shell}/attr/test-record-period         | 0
 tools/perf/tests/{ => shell}/attr/test-record-pfm-period     | 0
 tools/perf/tests/{ => shell}/attr/test-record-raw            | 0
 tools/perf/tests/{ => shell}/attr/test-record-spe-period     | 0
 .../perf/tests/{ => shell}/attr/test-record-spe-period-term  | 0
 .../tests/{ => shell}/attr/test-record-spe-physical-address  | 0
 .../{ => shell}/attr/test-record-user-regs-no-sve-aarch64    | 0
 .../{ => shell}/attr/test-record-user-regs-old-sve-aarch64   | 0
 .../tests/{ => shell}/attr/test-record-user-regs-sve-aarch64 | 0
 tools/perf/tests/{ => shell}/attr/test-stat-C0               | 0
 tools/perf/tests/{ => shell}/attr/test-stat-basic            | 0
 tools/perf/tests/{ => shell}/attr/test-stat-default          | 0
 tools/perf/tests/{ => shell}/attr/test-stat-detailed-1       | 0
 tools/perf/tests/{ => shell}/attr/test-stat-detailed-2       | 0
 tools/perf/tests/{ => shell}/attr/test-stat-detailed-3       | 0
 tools/perf/tests/{ => shell}/attr/test-stat-group1           | 0
 tools/perf/tests/{ => shell}/attr/test-stat-no-inherit       | 0
 tools/perf/tests/{ => shell/lib}/attr.py                     | 0
 53 files changed, 3 insertions(+), 4 deletions(-)
 rename tools/perf/tests/{ => shell}/attr/README (100%)
 rename tools/perf/tests/{ => shell}/attr/base-record (100%)
 rename tools/perf/tests/{ => shell}/attr/base-record-spe (100%)
 rename tools/perf/tests/{ => shell}/attr/base-stat (100%)
 rename tools/perf/tests/{ => shell}/attr/system-wide-dummy (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-C0 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-basic (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-branch-any (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-branch-filter-any (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-branch-filter-any_call (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-branch-filter-any_ret (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-branch-filter-hv (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-branch-filter-ind_call (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-branch-filter-k (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-branch-filter-u (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-count (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-data (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-dummy-C0 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-freq (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-graph-default (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-graph-default-aarch64 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-graph-dwarf (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-graph-fp (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-graph-fp-aarch64 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-group-sampling (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-group-sampling1 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-group-sampling2 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-group1 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-group2 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-group3 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-no-buffering (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-no-inherit (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-no-samples (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-period (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-pfm-period (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-raw (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-spe-period (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-spe-period-term (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-spe-physical-address (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-user-regs-no-sve-aarch64 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-user-regs-old-sve-aarch64 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-record-user-regs-sve-aarch64 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-stat-C0 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-stat-basic (100%)
 rename tools/perf/tests/{ => shell}/attr/test-stat-default (100%)
 rename tools/perf/tests/{ => shell}/attr/test-stat-detailed-1 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-stat-detailed-2 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-stat-detailed-3 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-stat-group1 (100%)
 rename tools/perf/tests/{ => shell}/attr/test-stat-no-inherit (100%)
 rename tools/perf/tests/{ => shell/lib}/attr.py (100%)

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 9dd2e8d3f3c9b..105f734b68201 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1128,12 +1128,11 @@ endif
 install-tests: all install-gtk
 	$(call QUIET_INSTALL, tests) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
-		$(INSTALL) tests/attr.py -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) tests/pe-file.exe* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
-		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
-		$(INSTALL) tests/attr/* -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \
 		$(INSTALL) tests/shell/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/attr'; \
+		$(INSTALL) tests/shell/attr/* -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/attr'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
 		$(INSTALL) tests/shell/lib/*.sh -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
 		$(INSTALL) tests/shell/lib/*.py -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
diff --git a/tools/perf/tests/shell/attr.sh b/tools/perf/tests/shell/attr.sh
index e094f3baffb7c..5a4e43b2471de 100755
--- a/tools/perf/tests/shell/attr.sh
+++ b/tools/perf/tests/shell/attr.sh
@@ -17,6 +17,6 @@ trap trap_cleanup EXIT TERM INT
 
 shelldir=$(dirname "$0")
 perf_path=$(which perf)
-python "${shelldir}"/../attr.py -d "${shelldir}"/../attr -v -p "$perf_path"
+python "${shelldir}"/lib/attr.py -d "${shelldir}"/attr -v -p "$perf_path"
 cleanup
 exit $err
diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/shell/attr/README
similarity index 100%
rename from tools/perf/tests/attr/README
rename to tools/perf/tests/shell/attr/README
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/shell/attr/base-record
similarity index 100%
rename from tools/perf/tests/attr/base-record
rename to tools/perf/tests/shell/attr/base-record
diff --git a/tools/perf/tests/attr/base-record-spe b/tools/perf/tests/shell/attr/base-record-spe
similarity index 100%
rename from tools/perf/tests/attr/base-record-spe
rename to tools/perf/tests/shell/attr/base-record-spe
diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/shell/attr/base-stat
similarity index 100%
rename from tools/perf/tests/attr/base-stat
rename to tools/perf/tests/shell/attr/base-stat
diff --git a/tools/perf/tests/attr/system-wide-dummy b/tools/perf/tests/shell/attr/system-wide-dummy
similarity index 100%
rename from tools/perf/tests/attr/system-wide-dummy
rename to tools/perf/tests/shell/attr/system-wide-dummy
diff --git a/tools/perf/tests/attr/test-record-C0 b/tools/perf/tests/shell/attr/test-record-C0
similarity index 100%
rename from tools/perf/tests/attr/test-record-C0
rename to tools/perf/tests/shell/attr/test-record-C0
diff --git a/tools/perf/tests/attr/test-record-basic b/tools/perf/tests/shell/attr/test-record-basic
similarity index 100%
rename from tools/perf/tests/attr/test-record-basic
rename to tools/perf/tests/shell/attr/test-record-basic
diff --git a/tools/perf/tests/attr/test-record-branch-any b/tools/perf/tests/shell/attr/test-record-branch-any
similarity index 100%
rename from tools/perf/tests/attr/test-record-branch-any
rename to tools/perf/tests/shell/attr/test-record-branch-any
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any b/tools/perf/tests/shell/attr/test-record-branch-filter-any
similarity index 100%
rename from tools/perf/tests/attr/test-record-branch-filter-any
rename to tools/perf/tests/shell/attr/test-record-branch-filter-any
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_call b/tools/perf/tests/shell/attr/test-record-branch-filter-any_call
similarity index 100%
rename from tools/perf/tests/attr/test-record-branch-filter-any_call
rename to tools/perf/tests/shell/attr/test-record-branch-filter-any_call
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_ret b/tools/perf/tests/shell/attr/test-record-branch-filter-any_ret
similarity index 100%
rename from tools/perf/tests/attr/test-record-branch-filter-any_ret
rename to tools/perf/tests/shell/attr/test-record-branch-filter-any_ret
diff --git a/tools/perf/tests/attr/test-record-branch-filter-hv b/tools/perf/tests/shell/attr/test-record-branch-filter-hv
similarity index 100%
rename from tools/perf/tests/attr/test-record-branch-filter-hv
rename to tools/perf/tests/shell/attr/test-record-branch-filter-hv
diff --git a/tools/perf/tests/attr/test-record-branch-filter-ind_call b/tools/perf/tests/shell/attr/test-record-branch-filter-ind_call
similarity index 100%
rename from tools/perf/tests/attr/test-record-branch-filter-ind_call
rename to tools/perf/tests/shell/attr/test-record-branch-filter-ind_call
diff --git a/tools/perf/tests/attr/test-record-branch-filter-k b/tools/perf/tests/shell/attr/test-record-branch-filter-k
similarity index 100%
rename from tools/perf/tests/attr/test-record-branch-filter-k
rename to tools/perf/tests/shell/attr/test-record-branch-filter-k
diff --git a/tools/perf/tests/attr/test-record-branch-filter-u b/tools/perf/tests/shell/attr/test-record-branch-filter-u
similarity index 100%
rename from tools/perf/tests/attr/test-record-branch-filter-u
rename to tools/perf/tests/shell/attr/test-record-branch-filter-u
diff --git a/tools/perf/tests/attr/test-record-count b/tools/perf/tests/shell/attr/test-record-count
similarity index 100%
rename from tools/perf/tests/attr/test-record-count
rename to tools/perf/tests/shell/attr/test-record-count
diff --git a/tools/perf/tests/attr/test-record-data b/tools/perf/tests/shell/attr/test-record-data
similarity index 100%
rename from tools/perf/tests/attr/test-record-data
rename to tools/perf/tests/shell/attr/test-record-data
diff --git a/tools/perf/tests/attr/test-record-dummy-C0 b/tools/perf/tests/shell/attr/test-record-dummy-C0
similarity index 100%
rename from tools/perf/tests/attr/test-record-dummy-C0
rename to tools/perf/tests/shell/attr/test-record-dummy-C0
diff --git a/tools/perf/tests/attr/test-record-freq b/tools/perf/tests/shell/attr/test-record-freq
similarity index 100%
rename from tools/perf/tests/attr/test-record-freq
rename to tools/perf/tests/shell/attr/test-record-freq
diff --git a/tools/perf/tests/attr/test-record-graph-default b/tools/perf/tests/shell/attr/test-record-graph-default
similarity index 100%
rename from tools/perf/tests/attr/test-record-graph-default
rename to tools/perf/tests/shell/attr/test-record-graph-default
diff --git a/tools/perf/tests/attr/test-record-graph-default-aarch64 b/tools/perf/tests/shell/attr/test-record-graph-default-aarch64
similarity index 100%
rename from tools/perf/tests/attr/test-record-graph-default-aarch64
rename to tools/perf/tests/shell/attr/test-record-graph-default-aarch64
diff --git a/tools/perf/tests/attr/test-record-graph-dwarf b/tools/perf/tests/shell/attr/test-record-graph-dwarf
similarity index 100%
rename from tools/perf/tests/attr/test-record-graph-dwarf
rename to tools/perf/tests/shell/attr/test-record-graph-dwarf
diff --git a/tools/perf/tests/attr/test-record-graph-fp b/tools/perf/tests/shell/attr/test-record-graph-fp
similarity index 100%
rename from tools/perf/tests/attr/test-record-graph-fp
rename to tools/perf/tests/shell/attr/test-record-graph-fp
diff --git a/tools/perf/tests/attr/test-record-graph-fp-aarch64 b/tools/perf/tests/shell/attr/test-record-graph-fp-aarch64
similarity index 100%
rename from tools/perf/tests/attr/test-record-graph-fp-aarch64
rename to tools/perf/tests/shell/attr/test-record-graph-fp-aarch64
diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/shell/attr/test-record-group-sampling
similarity index 100%
rename from tools/perf/tests/attr/test-record-group-sampling
rename to tools/perf/tests/shell/attr/test-record-group-sampling
diff --git a/tools/perf/tests/attr/test-record-group-sampling1 b/tools/perf/tests/shell/attr/test-record-group-sampling1
similarity index 100%
rename from tools/perf/tests/attr/test-record-group-sampling1
rename to tools/perf/tests/shell/attr/test-record-group-sampling1
diff --git a/tools/perf/tests/attr/test-record-group-sampling2 b/tools/perf/tests/shell/attr/test-record-group-sampling2
similarity index 100%
rename from tools/perf/tests/attr/test-record-group-sampling2
rename to tools/perf/tests/shell/attr/test-record-group-sampling2
diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/shell/attr/test-record-group1
similarity index 100%
rename from tools/perf/tests/attr/test-record-group1
rename to tools/perf/tests/shell/attr/test-record-group1
diff --git a/tools/perf/tests/attr/test-record-group2 b/tools/perf/tests/shell/attr/test-record-group2
similarity index 100%
rename from tools/perf/tests/attr/test-record-group2
rename to tools/perf/tests/shell/attr/test-record-group2
diff --git a/tools/perf/tests/attr/test-record-group3 b/tools/perf/tests/shell/attr/test-record-group3
similarity index 100%
rename from tools/perf/tests/attr/test-record-group3
rename to tools/perf/tests/shell/attr/test-record-group3
diff --git a/tools/perf/tests/attr/test-record-no-buffering b/tools/perf/tests/shell/attr/test-record-no-buffering
similarity index 100%
rename from tools/perf/tests/attr/test-record-no-buffering
rename to tools/perf/tests/shell/attr/test-record-no-buffering
diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/shell/attr/test-record-no-inherit
similarity index 100%
rename from tools/perf/tests/attr/test-record-no-inherit
rename to tools/perf/tests/shell/attr/test-record-no-inherit
diff --git a/tools/perf/tests/attr/test-record-no-samples b/tools/perf/tests/shell/attr/test-record-no-samples
similarity index 100%
rename from tools/perf/tests/attr/test-record-no-samples
rename to tools/perf/tests/shell/attr/test-record-no-samples
diff --git a/tools/perf/tests/attr/test-record-period b/tools/perf/tests/shell/attr/test-record-period
similarity index 100%
rename from tools/perf/tests/attr/test-record-period
rename to tools/perf/tests/shell/attr/test-record-period
diff --git a/tools/perf/tests/attr/test-record-pfm-period b/tools/perf/tests/shell/attr/test-record-pfm-period
similarity index 100%
rename from tools/perf/tests/attr/test-record-pfm-period
rename to tools/perf/tests/shell/attr/test-record-pfm-period
diff --git a/tools/perf/tests/attr/test-record-raw b/tools/perf/tests/shell/attr/test-record-raw
similarity index 100%
rename from tools/perf/tests/attr/test-record-raw
rename to tools/perf/tests/shell/attr/test-record-raw
diff --git a/tools/perf/tests/attr/test-record-spe-period b/tools/perf/tests/shell/attr/test-record-spe-period
similarity index 100%
rename from tools/perf/tests/attr/test-record-spe-period
rename to tools/perf/tests/shell/attr/test-record-spe-period
diff --git a/tools/perf/tests/attr/test-record-spe-period-term b/tools/perf/tests/shell/attr/test-record-spe-period-term
similarity index 100%
rename from tools/perf/tests/attr/test-record-spe-period-term
rename to tools/perf/tests/shell/attr/test-record-spe-period-term
diff --git a/tools/perf/tests/attr/test-record-spe-physical-address b/tools/perf/tests/shell/attr/test-record-spe-physical-address
similarity index 100%
rename from tools/perf/tests/attr/test-record-spe-physical-address
rename to tools/perf/tests/shell/attr/test-record-spe-physical-address
diff --git a/tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64 b/tools/perf/tests/shell/attr/test-record-user-regs-no-sve-aarch64
similarity index 100%
rename from tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64
rename to tools/perf/tests/shell/attr/test-record-user-regs-no-sve-aarch64
diff --git a/tools/perf/tests/attr/test-record-user-regs-old-sve-aarch64 b/tools/perf/tests/shell/attr/test-record-user-regs-old-sve-aarch64
similarity index 100%
rename from tools/perf/tests/attr/test-record-user-regs-old-sve-aarch64
rename to tools/perf/tests/shell/attr/test-record-user-regs-old-sve-aarch64
diff --git a/tools/perf/tests/attr/test-record-user-regs-sve-aarch64 b/tools/perf/tests/shell/attr/test-record-user-regs-sve-aarch64
similarity index 100%
rename from tools/perf/tests/attr/test-record-user-regs-sve-aarch64
rename to tools/perf/tests/shell/attr/test-record-user-regs-sve-aarch64
diff --git a/tools/perf/tests/attr/test-stat-C0 b/tools/perf/tests/shell/attr/test-stat-C0
similarity index 100%
rename from tools/perf/tests/attr/test-stat-C0
rename to tools/perf/tests/shell/attr/test-stat-C0
diff --git a/tools/perf/tests/attr/test-stat-basic b/tools/perf/tests/shell/attr/test-stat-basic
similarity index 100%
rename from tools/perf/tests/attr/test-stat-basic
rename to tools/perf/tests/shell/attr/test-stat-basic
diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/shell/attr/test-stat-default
similarity index 100%
rename from tools/perf/tests/attr/test-stat-default
rename to tools/perf/tests/shell/attr/test-stat-default
diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/shell/attr/test-stat-detailed-1
similarity index 100%
rename from tools/perf/tests/attr/test-stat-detailed-1
rename to tools/perf/tests/shell/attr/test-stat-detailed-1
diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/shell/attr/test-stat-detailed-2
similarity index 100%
rename from tools/perf/tests/attr/test-stat-detailed-2
rename to tools/perf/tests/shell/attr/test-stat-detailed-2
diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/shell/attr/test-stat-detailed-3
similarity index 100%
rename from tools/perf/tests/attr/test-stat-detailed-3
rename to tools/perf/tests/shell/attr/test-stat-detailed-3
diff --git a/tools/perf/tests/attr/test-stat-group1 b/tools/perf/tests/shell/attr/test-stat-group1
similarity index 100%
rename from tools/perf/tests/attr/test-stat-group1
rename to tools/perf/tests/shell/attr/test-stat-group1
diff --git a/tools/perf/tests/attr/test-stat-no-inherit b/tools/perf/tests/shell/attr/test-stat-no-inherit
similarity index 100%
rename from tools/perf/tests/attr/test-stat-no-inherit
rename to tools/perf/tests/shell/attr/test-stat-no-inherit
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/shell/lib/attr.py
similarity index 100%
rename from tools/perf/tests/attr.py
rename to tools/perf/tests/shell/lib/attr.py

From 44fcc479a574a4055fb6aed1f786d39999466383 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Thu, 17 Oct 2024 06:37:33 +0200
Subject: [PATCH 0479/1530] power: supply: hwmon: move interface to private
 header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The interface of power_supply_hwmon.c is only meant to be used by the
psy core. Remove it from the public header file and use the private one
instead.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20241017-power-supply-cleanups-v2-1-cb0f5deab088@weissschuh.net
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/power_supply.h | 17 +++++++++++++++++
 include/linux/power_supply.h        | 13 -------------
 2 files changed, 17 insertions(+), 13 deletions(-)

diff --git a/drivers/power/supply/power_supply.h b/drivers/power/supply/power_supply.h
index 4c558fb3db721..7434a6f247750 100644
--- a/drivers/power/supply/power_supply.h
+++ b/drivers/power/supply/power_supply.h
@@ -44,3 +44,20 @@ static inline int power_supply_create_triggers(struct power_supply *psy)
 static inline void power_supply_remove_triggers(struct power_supply *psy) {}
 
 #endif /* CONFIG_LEDS_TRIGGERS */
+
+#ifdef CONFIG_POWER_SUPPLY_HWMON
+
+int power_supply_add_hwmon_sysfs(struct power_supply *psy);
+void power_supply_remove_hwmon_sysfs(struct power_supply *psy);
+
+#else
+
+static inline int power_supply_add_hwmon_sysfs(struct power_supply *psy)
+{
+	return 0;
+}
+
+static inline
+void power_supply_remove_hwmon_sysfs(struct power_supply *psy) {}
+
+#endif /* CONFIG_POWER_SUPPLY_HWMON */
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index c1d6cb7f4c40e..b98106e1a90f3 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -937,19 +937,6 @@ static inline bool power_supply_is_watt_property(enum power_supply_property psp)
 	return false;
 }
 
-#ifdef CONFIG_POWER_SUPPLY_HWMON
-int power_supply_add_hwmon_sysfs(struct power_supply *psy);
-void power_supply_remove_hwmon_sysfs(struct power_supply *psy);
-#else
-static inline int power_supply_add_hwmon_sysfs(struct power_supply *psy)
-{
-	return 0;
-}
-
-static inline
-void power_supply_remove_hwmon_sysfs(struct power_supply *psy) {}
-#endif
-
 #ifdef CONFIG_SYSFS
 ssize_t power_supply_charge_behaviour_show(struct device *dev,
 					   unsigned int available_behaviours,

From 0db357ef93281606936459de6fd9ee7cd2c14593 Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Wed, 16 Oct 2024 11:41:40 -0500
Subject: [PATCH 0480/1530] remoteproc: k3-dsp: Add compile testing support

This driver can be compile tested on non-K3 architectures as long
as TI_SCI_PROTOCOL is not compiled as a module. Enable this here
to improve this driver's build coverage.

Signed-off-by: Andrew Davis <afd@ti.com>
Link: https://lore.kernel.org/r/20241016164141.93401-2-afd@ti.com
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index 62f8548fb46a5..0ac1c8a6e4581 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -329,7 +329,8 @@ config STM32_RPROC
 
 config TI_K3_DSP_REMOTEPROC
 	tristate "TI K3 DSP remoteproc support"
-	depends on ARCH_K3
+	depends on ARCH_K3 || COMPILE_TEST
+	depends on TI_SCI_PROTOCOL || (COMPILE_TEST && TI_SCI_PROTOCOL=n)
 	depends on OMAP2PLUS_MBOX
 	help
 	  Say m here to support TI's C66x and C71x DSP remote processor

From be3e6529a8b90b1284a55117a4e23095ccbeaeaf Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Wed, 16 Oct 2024 11:41:41 -0500
Subject: [PATCH 0481/1530] remoteproc: k3-r5: Add compile testing support

This driver can be compile tested on non-K3 architectures as long
as TI_SCI_PROTOCOL is not compiled as a module. Enable this here
to improve this driver's build coverage.

Signed-off-by: Andrew Davis <afd@ti.com>
Link: https://lore.kernel.org/r/20241016164141.93401-3-afd@ti.com
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index 0ac1c8a6e4581..83962a114dc9f 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -355,7 +355,8 @@ config TI_K3_M4_REMOTEPROC
 
 config TI_K3_R5_REMOTEPROC
 	tristate "TI K3 R5 remoteproc support"
-	depends on ARCH_K3
+	depends on ARCH_K3 || COMPILE_TEST
+	depends on TI_SCI_PROTOCOL || (COMPILE_TEST && TI_SCI_PROTOCOL=n)
 	depends on OMAP2PLUS_MBOX
 	help
 	  Say m here to support TI's R5F remote processor subsystems

From 4bb21dbb6728fbe6cb7e2f7dc7e5388962c4125b Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Fri, 18 Oct 2024 12:31:51 +0200
Subject: [PATCH 0482/1530] mm: Use str_on_off() helper function in
 report_meminit()

Remove hard-coded strings by using the helper function str_on_off().

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Link: https://lore.kernel.org/r/20241018103150.96824-2-thorsten.blum@linux.dev
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
 mm/mm_init.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/mm_init.c b/mm/mm_init.c
index 4ba5607aaf194..253972926183c 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -2573,8 +2573,8 @@ static void __init report_meminit(void)
 		stack = "off";
 
 	pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n",
-		stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off",
-		want_init_on_free() ? "on" : "off");
+		stack, str_on_off(want_init_on_alloc(GFP_KERNEL)),
+		str_on_off(want_init_on_free()));
 	if (want_init_on_free())
 		pr_info("mem auto-init: clearing system memory may take some time...\n");
 }

From a9823dae4ccf70c388371e1e135fda0a3e08f4e6 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 16 Oct 2024 17:13:44 -0700
Subject: [PATCH 0483/1530] perf build: Fix LIBDW_DIR

Testing with a LIBDW_DIR showed that in Makefile.config the dwarf
feature tests need the LIBDW_DIR setting in the CFLAGS/LDFLAGS.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241017001354.56973-2-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Makefile.config | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 4ddb27a48eed2..c1c7c25887a72 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -162,8 +162,14 @@ ifeq ($(findstring -static,${LDFLAGS}),-static)
   # Must put -ldl after -lebl for dependency
   DWARFLIBS += -ldl
 endif
+FEATURE_CHECK_CFLAGS-dwarf := $(LIBDW_CFLAGS)
+FEATURE_CHECK_LDFLAGS-dwarf := $(LIBDW_LDFLAGS) $(DWARFLIBS)
 FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) $(DWARFLIBS)
+FEATURE_CHECK_CFLAGS-dwarf_getlocations := $(LIBDW_CFLAGS)
+FEATURE_CHECK_LDFLAGS-dwarf_getlocations := $(LIBDW_LDFLAGS) $(DWARFLIBS)
+FEATURE_CHECK_CFLAGS-dwarf_getcfi := $(LIBDW_CFLAGS)
+FEATURE_CHECK_LDFLAGS-dwarf_getcfi := $(LIBDW_LDFLAGS) $(DWARFLIBS)
 
 # for linking with debug library, run like:
 # make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/

From 54a1368567e8edd4f452085d89239b8b05d36856 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 16 Oct 2024 17:13:45 -0700
Subject: [PATCH 0484/1530] perf build: Rename NO_DWARF to NO_LIBDW

NO_DWARF could mean more than NO_LIBDW support, in particular no
libunwind support. Rename to be more intention revealing.

Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241017001354.56973-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Makefile.config         | 16 ++++++++--------
 tools/perf/Makefile.perf           |  2 +-
 tools/perf/arch/arm/Makefile       |  2 +-
 tools/perf/arch/arm64/Makefile     |  2 +-
 tools/perf/arch/csky/Makefile      |  2 +-
 tools/perf/arch/loongarch/Makefile |  2 +-
 tools/perf/arch/mips/Makefile      |  2 +-
 tools/perf/arch/powerpc/Makefile   |  2 +-
 tools/perf/arch/riscv/Makefile     |  2 +-
 tools/perf/arch/s390/Makefile      |  2 +-
 tools/perf/arch/sh/Makefile        |  2 +-
 tools/perf/arch/sparc/Makefile     |  2 +-
 tools/perf/arch/x86/Makefile       |  2 +-
 tools/perf/arch/xtensa/Makefile    |  2 +-
 tools/perf/builtin-probe.c         |  2 +-
 15 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index c1c7c25887a72..cc2cfc3aab405 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -432,7 +432,7 @@ ifeq ($(feature-file-handle), 1)
 endif
 
 ifdef NO_LIBELF
-  NO_DWARF := 1
+  NO_LIBDW := 1
   NO_LIBUNWIND := 1
   NO_LIBDW_DWARF_UNWIND := 1
   NO_LIBBPF := 1
@@ -474,9 +474,9 @@ else
       endif
     endif
     ifneq ($(feature-dwarf), 1)
-      ifndef NO_DWARF
+      ifndef NO_LIBDW
         $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev)
-        NO_DWARF := 1
+        NO_LIBDW := 1
       endif
     else
       ifneq ($(feature-dwarf_getlocations), 1)
@@ -499,7 +499,7 @@ ifeq ($(feature-libaio), 1)
   endif
 endif
 
-ifdef NO_DWARF
+ifdef NO_LIBDW
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
@@ -577,17 +577,17 @@ ifndef NO_LIBELF
     endif
   endif
 
-  ifndef NO_DWARF
+  ifndef NO_LIBDW
     ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
       $(warning DWARF register mappings have not been defined for architecture $(SRCARCH), DWARF support disabled)
-      NO_DWARF := 1
+      NO_LIBDW := 1
     else
       CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS)
       LDFLAGS += $(LIBDW_LDFLAGS)
       EXTLIBS += ${DWARFLIBS}
       $(call detected,CONFIG_DWARF)
     endif # PERF_HAVE_DWARF_REGS
-  endif # NO_DWARF
+  endif # NO_LIBDW
 
   ifndef NO_LIBBPF
     ifeq ($(feature-bpf), 1)
@@ -636,7 +636,7 @@ ifdef PERF_HAVE_JITDUMP
 endif
 
 ifeq ($(SRCARCH),powerpc)
-  ifndef NO_DWARF
+  ifndef NO_LIBDW
     CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
   endif
 endif
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 105f734b68201..b4dee7c20ed15 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -40,7 +40,7 @@ include ../scripts/utilities.mak
 #
 # Define EXTRA_PERFLIBS to pass extra libraries to PERFLIBS.
 #
-# Define NO_DWARF if you do not want debug-info analysis feature at all.
+# Define NO_LIBDW if you do not want debug-info analysis feature at all.
 #
 # Define WERROR=0 to disable treating any warnings as errors.
 #
diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile
index 1d88fdab13bf8..9b164d3795485 100644
--- a/tools/perf/arch/arm/Makefile
+++ b/tools/perf/arch/arm/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ifndef NO_DWARF
+ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 5735ed4479bb9..8a5ffbfe809fe 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-ifndef NO_DWARF
+ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/csky/Makefile b/tools/perf/arch/csky/Makefile
index 88c08eed9c7be..119b06a64bed4 100644
--- a/tools/perf/arch/csky/Makefile
+++ b/tools/perf/arch/csky/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ifndef NO_DWARF
+ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
diff --git a/tools/perf/arch/loongarch/Makefile b/tools/perf/arch/loongarch/Makefile
index c89d6bb6b184b..1cc5eb01f32b2 100644
--- a/tools/perf/arch/loongarch/Makefile
+++ b/tools/perf/arch/loongarch/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-ifndef NO_DWARF
+ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
diff --git a/tools/perf/arch/mips/Makefile b/tools/perf/arch/mips/Makefile
index cd0b011b3be5f..733f7b76f52de 100644
--- a/tools/perf/arch/mips/Makefile
+++ b/tools/perf/arch/mips/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-ifndef NO_DWARF
+ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
 
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index bf6d323574f66..7672d555f6cdb 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-ifndef NO_DWARF
+ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
 
diff --git a/tools/perf/arch/riscv/Makefile b/tools/perf/arch/riscv/Makefile
index 90c3c476a242c..4664a78a1afd4 100644
--- a/tools/perf/arch/riscv/Makefile
+++ b/tools/perf/arch/riscv/Makefile
@@ -1,4 +1,4 @@
-ifndef NO_DWARF
+ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile
index 56994e63b43ae..3f66e2ede3f7e 100644
--- a/tools/perf/arch/s390/Makefile
+++ b/tools/perf/arch/s390/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ifndef NO_DWARF
+ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
 HAVE_KVM_STAT_SUPPORT := 1
diff --git a/tools/perf/arch/sh/Makefile b/tools/perf/arch/sh/Makefile
index 88c08eed9c7be..119b06a64bed4 100644
--- a/tools/perf/arch/sh/Makefile
+++ b/tools/perf/arch/sh/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ifndef NO_DWARF
+ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
diff --git a/tools/perf/arch/sparc/Makefile b/tools/perf/arch/sparc/Makefile
index 4031db72ba71a..7741184894c81 100644
--- a/tools/perf/arch/sparc/Makefile
+++ b/tools/perf/arch/sparc/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ifndef NO_DWARF
+ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
 
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 67b4969a67383..9aa58acb55641 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-ifndef NO_DWARF
+ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
 HAVE_KVM_STAT_SUPPORT := 1
diff --git a/tools/perf/arch/xtensa/Makefile b/tools/perf/arch/xtensa/Makefile
index 88c08eed9c7be..119b06a64bed4 100644
--- a/tools/perf/arch/xtensa/Makefile
+++ b/tools/perf/arch/xtensa/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ifndef NO_DWARF
+ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 003a3bcebfdfc..91672bb3047c3 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -616,7 +616,7 @@ __cmd_probe(int argc, const char **argv)
 	set_option_flag(options, 'L', "line", PARSE_OPT_EXCLUSIVE);
 	set_option_flag(options, 'V', "vars", PARSE_OPT_EXCLUSIVE);
 #else
-# define set_nobuild(s, l, c) set_option_nobuild(options, s, l, "NO_DWARF=1", c)
+# define set_nobuild(s, l, c) set_option_nobuild(options, s, l, "NO_LIBDW=1", c)
 	set_nobuild('L', "line", false);
 	set_nobuild('V', "vars", false);
 	set_nobuild('\0', "externs", false);

From a6c55df973a8399d06d1bed676cb9ea4792e4e29 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 16 Oct 2024 17:13:46 -0700
Subject: [PATCH 0485/1530] perf build: Remove defined but never used variable

Previously NO_DWARF_UNWIND was part of conditional compilation but it
is now unused so remove.

Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241017001354.56973-4-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Makefile.config | 2 --
 1 file changed, 2 deletions(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index cc2cfc3aab405..dd5468b8b5de4 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -756,8 +756,6 @@ endif
 ifeq ($(dwarf-post-unwind),1)
   CFLAGS += -DHAVE_DWARF_UNWIND_SUPPORT
   $(call detected,CONFIG_DWARF_UNWIND)
-else
-  NO_DWARF_UNWIND := 1
 endif
 
 ifndef NO_LOCAL_LIBUNWIND

From 7c943261a1becfda44ac0468ca329e0f2bb95f2a Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 16 Oct 2024 17:13:47 -0700
Subject: [PATCH 0486/1530] perf build: Rename test-dwarf to test-libdw

Be more intention revealing that the dwarf test is actually testing
for libdw support.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241017001354.56973-5-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/build/Makefile.feature                     |  6 +++---
 tools/build/feature/Makefile                     | 16 ++++++++--------
 tools/build/feature/test-all.c                   |  6 +++---
 .../build/feature/{test-dwarf.c => test-libdw.c} |  0
 tools/perf/Makefile.config                       |  6 +++---
 5 files changed, 17 insertions(+), 17 deletions(-)
 rename tools/build/feature/{test-dwarf.c => test-libdw.c} (100%)

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index ffd117135094c..6025810cc3469 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -30,7 +30,7 @@ endef
 #
 FEATURE_TESTS_BASIC :=                  \
         backtrace                       \
-        dwarf                           \
+        libdw                           \
         dwarf_getlocations              \
         dwarf_getcfi                    \
         eventfd                         \
@@ -120,7 +120,7 @@ ifeq ($(FEATURE_TESTS),all)
 endif
 
 FEATURE_DISPLAY ?=              \
-         dwarf                  \
+         libdw                  \
          dwarf_getlocations     \
          glibc                  \
          libbfd                 \
@@ -233,7 +233,7 @@ endef
 
 #
 # generates feature value assignment for name, like:
-#   $(call feature_assign,dwarf) == feature-dwarf=1
+#   $(call feature_assign,libdw) == feature-libdw=1
 #
 feature_assign = feature-$(1)=$(feature-$(1))
 
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 1658596188bf8..7a1c028ce40b5 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -5,7 +5,7 @@ FILES=                                          \
          test-all.bin                           \
          test-backtrace.bin                     \
          test-bionic.bin                        \
-         test-dwarf.bin                         \
+         test-libdw.bin                         \
          test-dwarf_getlocations.bin            \
          test-dwarf_getcfi.bin                  \
          test-eventfd.bin                       \
@@ -168,9 +168,9 @@ $(OUTPUT)test-libopencsd.bin:
 	$(BUILD) # -lopencsd_c_api -lopencsd provided by
 		 # $(FEATURE_CHECK_LDFLAGS-libopencsd)
 
-DWARFLIBS := -ldw
+DWLIBS := -ldw
 ifeq ($(findstring -static,${LDFLAGS}),-static)
-  DWARFLIBS += -lelf -lz -llzma -lbz2 -lzstd
+  DWLIBS += -lelf -lz -llzma -lbz2 -lzstd
 
   LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw).0.0
   LIBDW_VERSION_1 := $(word 1, $(subst ., ,$(LIBDW_VERSION)))
@@ -179,21 +179,21 @@ ifeq ($(findstring -static,${LDFLAGS}),-static)
   # Elfutils merged libebl.a into libdw.a starting from version 0.177,
   # Link libebl.a only if libdw is older than this version.
   ifeq ($(shell test $(LIBDW_VERSION_2) -lt 177; echo $$?),0)
-    DWARFLIBS += -lebl
+    DWLIBS += -lebl
   endif
 
   # Must put -ldl after -lebl for dependency
   DWARFLIBS += -ldl
 endif
 
-$(OUTPUT)test-dwarf.bin:
-	$(BUILD) $(DWARFLIBS)
+$(OUTPUT)test-libdw.bin:
+	$(BUILD) $(DWLIBS)
 
 $(OUTPUT)test-dwarf_getlocations.bin:
-	$(BUILD) $(DWARFLIBS)
+	$(BUILD) $(DWLIBS)
 
 $(OUTPUT)test-dwarf_getcfi.bin:
-	$(BUILD) $(DWARFLIBS)
+	$(BUILD) $(DWLIBS)
 
 $(OUTPUT)test-libelf-getphdrnum.bin:
 	$(BUILD) -lelf
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 6f4bf386a3b5c..d60e072b6eca4 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -38,8 +38,8 @@
 # include "test-glibc.c"
 #undef main
 
-#define main main_test_dwarf
-# include "test-dwarf.c"
+#define main main_test_libdw
+# include "test-libdw.c"
 #undef main
 
 #define main main_test_dwarf_getlocations
@@ -187,7 +187,7 @@ int main(int argc, char *argv[])
 	main_test_get_current_dir_name();
 	main_test_gettid();
 	main_test_glibc();
-	main_test_dwarf();
+	main_test_libdw();
 	main_test_dwarf_getlocations();
 	main_test_eventfd();
 	main_test_libelf_getphdrnum();
diff --git a/tools/build/feature/test-dwarf.c b/tools/build/feature/test-libdw.c
similarity index 100%
rename from tools/build/feature/test-dwarf.c
rename to tools/build/feature/test-libdw.c
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index dd5468b8b5de4..f1e24c4ae1237 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -162,8 +162,8 @@ ifeq ($(findstring -static,${LDFLAGS}),-static)
   # Must put -ldl after -lebl for dependency
   DWARFLIBS += -ldl
 endif
-FEATURE_CHECK_CFLAGS-dwarf := $(LIBDW_CFLAGS)
-FEATURE_CHECK_LDFLAGS-dwarf := $(LIBDW_LDFLAGS) $(DWARFLIBS)
+FEATURE_CHECK_CFLAGS-libdw := $(LIBDW_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libdw := $(LIBDW_LDFLAGS) $(DWARFLIBS)
 FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) $(DWARFLIBS)
 FEATURE_CHECK_CFLAGS-dwarf_getlocations := $(LIBDW_CFLAGS)
@@ -473,7 +473,7 @@ else
         $(warning No libdw DWARF unwind found, Please install elfutils-devel/libdw-dev >= 0.158 and/or set LIBDW_DIR)
       endif
     endif
-    ifneq ($(feature-dwarf), 1)
+    ifneq ($(feature-libdw), 1)
       ifndef NO_LIBDW
         $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev)
         NO_LIBDW := 1

From 3034b48a4bc13effd3be03b44111b1cf0384bc13 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 16 Oct 2024 17:13:48 -0700
Subject: [PATCH 0487/1530] perf build: Combine libdw-dwarf-unwind into libdw
 feature tests

Support in libdw has been present for 10 years so let's simplify the
build logic with a single feature test.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241017001354.56973-6-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/build/Makefile.feature                  |  2 --
 tools/build/feature/Makefile                  |  4 ----
 tools/build/feature/test-all.c                |  5 -----
 tools/build/feature/test-libdw-dwarf-unwind.c | 14 --------------
 tools/build/feature/test-libdw.c              | 19 ++++++++++++++++++-
 tools/perf/Makefile.config                    |  8 --------
 6 files changed, 18 insertions(+), 34 deletions(-)
 delete mode 100644 tools/build/feature/test-libdw-dwarf-unwind.c

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 6025810cc3469..db3695ec5f838 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -60,7 +60,6 @@ FEATURE_TESTS_BASIC :=                  \
         reallocarray                    \
         stackprotector-all              \
         timerfd                         \
-        libdw-dwarf-unwind              \
         zlib                            \
         lzma                            \
         get_cpuid                       \
@@ -133,7 +132,6 @@ FEATURE_DISPLAY ?=              \
          libpython              \
          libcrypto              \
          libunwind              \
-         libdw-dwarf-unwind     \
          libcapstone            \
          llvm-perf              \
          zlib                   \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 7a1c028ce40b5..18f8fef5e8433 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -52,7 +52,6 @@ FILES=                                          \
          test-pthread-barrier.bin		\
          test-stackprotector-all.bin            \
          test-timerfd.bin                       \
-         test-libdw-dwarf-unwind.bin            \
          test-libbabeltrace.bin                 \
          test-libcapstone.bin			\
          test-compile-32.bin                    \
@@ -317,9 +316,6 @@ $(OUTPUT)test-backtrace.bin:
 $(OUTPUT)test-timerfd.bin:
 	$(BUILD)
 
-$(OUTPUT)test-libdw-dwarf-unwind.bin:
-	$(BUILD) # -ldw provided by $(FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind)
-
 $(OUTPUT)test-libbabeltrace.bin:
 	$(BUILD) # -lbabeltrace provided by $(FEATURE_CHECK_LDFLAGS-libbabeltrace)
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index d60e072b6eca4..863c825164330 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -98,10 +98,6 @@
 # include "test-stackprotector-all.c"
 #undef main
 
-#define main main_test_libdw_dwarf_unwind
-# include "test-libdw-dwarf-unwind.c"
-#undef main
-
 #define main main_test_zlib
 # include "test-zlib.c"
 #undef main
@@ -202,7 +198,6 @@ int main(int argc, char *argv[])
 	main_test_numa_num_possible_cpus();
 	main_test_timerfd();
 	main_test_stackprotector_all();
-	main_test_libdw_dwarf_unwind();
 	main_test_zlib();
 	main_test_pthread_attr_setaffinity_np();
 	main_test_pthread_barrier();
diff --git a/tools/build/feature/test-libdw-dwarf-unwind.c b/tools/build/feature/test-libdw-dwarf-unwind.c
deleted file mode 100644
index ed03d95056090..0000000000000
--- a/tools/build/feature/test-libdw-dwarf-unwind.c
+++ /dev/null
@@ -1,14 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <elfutils/libdwfl.h>
-
-int main(void)
-{
-	/*
-	 * This function is guarded via: __nonnull_attribute__ (1, 2).
-	 * Passing '1' as arguments value. This code is never executed,
-	 * only compiled.
-	 */
-	dwfl_thread_getframes((void *) 1, (void *) 1, NULL);
-	return 0;
-}
diff --git a/tools/build/feature/test-libdw.c b/tools/build/feature/test-libdw.c
index 8d474bd7371b2..793f4ac495140 100644
--- a/tools/build/feature/test-libdw.c
+++ b/tools/build/feature/test-libdw.c
@@ -1,11 +1,28 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <dwarf.h>
 #include <elfutils/libdw.h>
+#include <elfutils/libdwfl.h>
 #include <elfutils/version.h>
 
-int main(void)
+int test_libdw(void)
 {
 	Dwarf *dbg = dwarf_begin(0, DWARF_C_READ);
 
 	return (long)dbg;
 }
+
+int test_libdw_unwind(void)
+{
+	/*
+	 * This function is guarded via: __nonnull_attribute__ (1, 2).
+	 * Passing '1' as arguments value. This code is never executed,
+	 * only compiled.
+	 */
+	dwfl_thread_getframes((void *) 1, (void *) 1, NULL);
+	return 0;
+}
+
+int main(void)
+{
+	return test_libdw() + test_libdw_unwind();
+}
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index f1e24c4ae1237..fa59ecce44708 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -164,8 +164,6 @@ ifeq ($(findstring -static,${LDFLAGS}),-static)
 endif
 FEATURE_CHECK_CFLAGS-libdw := $(LIBDW_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libdw := $(LIBDW_LDFLAGS) $(DWARFLIBS)
-FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
-FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) $(DWARFLIBS)
 FEATURE_CHECK_CFLAGS-dwarf_getlocations := $(LIBDW_CFLAGS)
 FEATURE_CHECK_LDFLAGS-dwarf_getlocations := $(LIBDW_LDFLAGS) $(DWARFLIBS)
 FEATURE_CHECK_CFLAGS-dwarf_getcfi := $(LIBDW_CFLAGS)
@@ -467,12 +465,6 @@ else
       endif
     endif
   else
-    ifndef NO_LIBDW_DWARF_UNWIND
-      ifneq ($(feature-libdw-dwarf-unwind),1)
-        NO_LIBDW_DWARF_UNWIND := 1
-        $(warning No libdw DWARF unwind found, Please install elfutils-devel/libdw-dev >= 0.158 and/or set LIBDW_DIR)
-      endif
-    endif
     ifneq ($(feature-libdw), 1)
       ifndef NO_LIBDW
         $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev)

From 23580d7bb1f9a60bf60a26ce25615d18ca9b3e55 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 16 Oct 2024 17:13:49 -0700
Subject: [PATCH 0488/1530] perf build: Combine test-dwarf-getlocations into
 test-libdw

dwarf_getlocations support in libdw is more than 10 years old. Make
libdw imply dwarf_getlocations support and simplify build logic.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241017001354.56973-7-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/build/Makefile.feature                  |  2 --
 tools/build/feature/Makefile                  |  4 ----
 tools/build/feature/test-all.c                |  5 -----
 tools/build/feature/test-dwarf_getlocations.c | 13 -------------
 tools/build/feature/test-libdw.c              | 14 +++++++++++++-
 tools/perf/Makefile.config                    | 10 ++--------
 6 files changed, 15 insertions(+), 33 deletions(-)
 delete mode 100644 tools/build/feature/test-dwarf_getlocations.c

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index db3695ec5f838..cf6a967575eae 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -31,7 +31,6 @@ endef
 FEATURE_TESTS_BASIC :=                  \
         backtrace                       \
         libdw                           \
-        dwarf_getlocations              \
         dwarf_getcfi                    \
         eventfd                         \
         fortify-source                  \
@@ -120,7 +119,6 @@ endif
 
 FEATURE_DISPLAY ?=              \
          libdw                  \
-         dwarf_getlocations     \
          glibc                  \
          libbfd                 \
          libbfd-buildid		\
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 18f8fef5e8433..0af3e0255fedc 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -6,7 +6,6 @@ FILES=                                          \
          test-backtrace.bin                     \
          test-bionic.bin                        \
          test-libdw.bin                         \
-         test-dwarf_getlocations.bin            \
          test-dwarf_getcfi.bin                  \
          test-eventfd.bin                       \
          test-fortify-source.bin                \
@@ -188,9 +187,6 @@ endif
 $(OUTPUT)test-libdw.bin:
 	$(BUILD) $(DWLIBS)
 
-$(OUTPUT)test-dwarf_getlocations.bin:
-	$(BUILD) $(DWLIBS)
-
 $(OUTPUT)test-dwarf_getcfi.bin:
 	$(BUILD) $(DWLIBS)
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 863c825164330..59ef3d7fe6a4e 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -42,10 +42,6 @@
 # include "test-libdw.c"
 #undef main
 
-#define main main_test_dwarf_getlocations
-# include "test-dwarf_getlocations.c"
-#undef main
-
 #define main main_test_eventfd
 # include "test-eventfd.c"
 #undef main
@@ -184,7 +180,6 @@ int main(int argc, char *argv[])
 	main_test_gettid();
 	main_test_glibc();
 	main_test_libdw();
-	main_test_dwarf_getlocations();
 	main_test_eventfd();
 	main_test_libelf_getphdrnum();
 	main_test_libelf_gelf_getnote();
diff --git a/tools/build/feature/test-dwarf_getlocations.c b/tools/build/feature/test-dwarf_getlocations.c
deleted file mode 100644
index 78fb4a1fa68c3..0000000000000
--- a/tools/build/feature/test-dwarf_getlocations.c
+++ /dev/null
@@ -1,13 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <stdlib.h>
-#include <elfutils/libdw.h>
-
-int main(void)
-{
-	Dwarf_Addr base, start, end;
-	Dwarf_Attribute attr;
-	Dwarf_Op *op;
-        size_t nops;
-	ptrdiff_t offset = 0;
-        return (int)dwarf_getlocations(&attr, offset, &base, &start, &end, &op, &nops);
-}
diff --git a/tools/build/feature/test-libdw.c b/tools/build/feature/test-libdw.c
index 793f4ac495140..83ea5d5f235d7 100644
--- a/tools/build/feature/test-libdw.c
+++ b/tools/build/feature/test-libdw.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <stdlib.h>
 #include <dwarf.h>
 #include <elfutils/libdw.h>
 #include <elfutils/libdwfl.h>
@@ -22,7 +23,18 @@ int test_libdw_unwind(void)
 	return 0;
 }
 
+int test_libdw_getlocations(void)
+{
+	Dwarf_Addr base, start, end;
+	Dwarf_Attribute attr;
+	Dwarf_Op *op;
+	size_t nops;
+	ptrdiff_t offset = 0;
+
+	return (int)dwarf_getlocations(&attr, offset, &base, &start, &end, &op, &nops);
+}
+
 int main(void)
 {
-	return test_libdw() + test_libdw_unwind();
+	return test_libdw() + test_libdw_unwind() + test_libdw_getlocations();
 }
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index fa59ecce44708..fefa779041a08 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -164,8 +164,6 @@ ifeq ($(findstring -static,${LDFLAGS}),-static)
 endif
 FEATURE_CHECK_CFLAGS-libdw := $(LIBDW_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libdw := $(LIBDW_LDFLAGS) $(DWARFLIBS)
-FEATURE_CHECK_CFLAGS-dwarf_getlocations := $(LIBDW_CFLAGS)
-FEATURE_CHECK_LDFLAGS-dwarf_getlocations := $(LIBDW_LDFLAGS) $(DWARFLIBS)
 FEATURE_CHECK_CFLAGS-dwarf_getcfi := $(LIBDW_CFLAGS)
 FEATURE_CHECK_LDFLAGS-dwarf_getcfi := $(LIBDW_LDFLAGS) $(DWARFLIBS)
 
@@ -467,15 +465,11 @@ else
   else
     ifneq ($(feature-libdw), 1)
       ifndef NO_LIBDW
-        $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev)
+        $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.157, disables dwarf support. Please install new elfutils-devel/libdw-dev)
         NO_LIBDW := 1
       endif
     else
-      ifneq ($(feature-dwarf_getlocations), 1)
-        $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157)
-      else
-        CFLAGS += -DHAVE_DWARF_GETLOCATIONS_SUPPORT
-      endif # dwarf_getlocations
+      CFLAGS += -DHAVE_DWARF_GETLOCATIONS_SUPPORT
       ifneq ($(feature-dwarf_getcfi), 1)
         $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.142)
       else

From 26385fd237260f27befd49e25674baf3901050d4 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 16 Oct 2024 17:13:50 -0700
Subject: [PATCH 0489/1530] perf build: Combine test-dwarf-getcfi into
 test-libdw

dwarf_getcfi support in libdw is 15 years old. Make libdw imply
dwarf_getcfi support and simplify build logic.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241017001354.56973-8-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/build/Makefile.feature            |  1 -
 tools/build/feature/Makefile            |  4 ----
 tools/build/feature/test-dwarf_getcfi.c |  9 ---------
 tools/build/feature/test-libdw.c        | 10 +++++++++-
 tools/perf/Makefile.config              |  8 +-------
 5 files changed, 10 insertions(+), 22 deletions(-)
 delete mode 100644 tools/build/feature/test-dwarf_getcfi.c

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index cf6a967575eae..ef72aae3dd49b 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -31,7 +31,6 @@ endef
 FEATURE_TESTS_BASIC :=                  \
         backtrace                       \
         libdw                           \
-        dwarf_getcfi                    \
         eventfd                         \
         fortify-source                  \
         get_current_dir_name            \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 0af3e0255fedc..d28ad7672a270 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -6,7 +6,6 @@ FILES=                                          \
          test-backtrace.bin                     \
          test-bionic.bin                        \
          test-libdw.bin                         \
-         test-dwarf_getcfi.bin                  \
          test-eventfd.bin                       \
          test-fortify-source.bin                \
          test-get_current_dir_name.bin          \
@@ -187,9 +186,6 @@ endif
 $(OUTPUT)test-libdw.bin:
 	$(BUILD) $(DWLIBS)
 
-$(OUTPUT)test-dwarf_getcfi.bin:
-	$(BUILD) $(DWLIBS)
-
 $(OUTPUT)test-libelf-getphdrnum.bin:
 	$(BUILD) -lelf
 
diff --git a/tools/build/feature/test-dwarf_getcfi.c b/tools/build/feature/test-dwarf_getcfi.c
deleted file mode 100644
index 50e7d7cb7bdf9..0000000000000
--- a/tools/build/feature/test-dwarf_getcfi.c
+++ /dev/null
@@ -1,9 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <stdio.h>
-#include <elfutils/libdw.h>
-
-int main(void)
-{
-	Dwarf *dwarf = NULL;
-	return dwarf_getcfi(dwarf) == NULL;
-}
diff --git a/tools/build/feature/test-libdw.c b/tools/build/feature/test-libdw.c
index 83ea5d5f235d7..71c6f8e3b0eeb 100644
--- a/tools/build/feature/test-libdw.c
+++ b/tools/build/feature/test-libdw.c
@@ -34,7 +34,15 @@ int test_libdw_getlocations(void)
 	return (int)dwarf_getlocations(&attr, offset, &base, &start, &end, &op, &nops);
 }
 
+int test_libdw_getcfi(void)
+{
+	Dwarf *dwarf = NULL;
+
+	return dwarf_getcfi(dwarf) == NULL;
+}
+
 int main(void)
 {
-	return test_libdw() + test_libdw_unwind() + test_libdw_getlocations();
+	return test_libdw() + test_libdw_unwind() + test_libdw_getlocations() +
+	       test_libdw_getcfi();
 }
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index fefa779041a08..6378811f25686 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -164,8 +164,6 @@ ifeq ($(findstring -static,${LDFLAGS}),-static)
 endif
 FEATURE_CHECK_CFLAGS-libdw := $(LIBDW_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libdw := $(LIBDW_LDFLAGS) $(DWARFLIBS)
-FEATURE_CHECK_CFLAGS-dwarf_getcfi := $(LIBDW_CFLAGS)
-FEATURE_CHECK_LDFLAGS-dwarf_getcfi := $(LIBDW_LDFLAGS) $(DWARFLIBS)
 
 # for linking with debug library, run like:
 # make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/
@@ -470,11 +468,7 @@ else
       endif
     else
       CFLAGS += -DHAVE_DWARF_GETLOCATIONS_SUPPORT
-      ifneq ($(feature-dwarf_getcfi), 1)
-        $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.142)
-      else
-        CFLAGS += -DHAVE_DWARF_CFI_SUPPORT
-      endif # dwarf_getcfi
+      CFLAGS += -DHAVE_DWARF_CFI_SUPPORT
     endif # Dwarf support
   endif # libelf support
 endif # NO_LIBELF

From 91e81e988fc9c51f9f9f4cf6de74aa66a57b4361 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 16 Oct 2024 17:13:51 -0700
Subject: [PATCH 0490/1530] perf probe: Move elfutils support check to libdw
 check

The test _ELFUTILS_PREREQ(0, 142) is false for elfutils before
2009-06-13, but that is 15 years ago and very unlikely. Add a test to
test-libdw.c and assume the libdw version is at least 0.142 to
simplify the build logic.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241017001354.56973-9-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/build/feature/test-libdw.c | 10 +++++++++-
 tools/perf/util/probe-finder.c   |  2 --
 tools/perf/util/probe-finder.h   |  2 --
 3 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/tools/build/feature/test-libdw.c b/tools/build/feature/test-libdw.c
index 71c6f8e3b0eeb..2fb59479ab771 100644
--- a/tools/build/feature/test-libdw.c
+++ b/tools/build/feature/test-libdw.c
@@ -41,8 +41,16 @@ int test_libdw_getcfi(void)
 	return dwarf_getcfi(dwarf) == NULL;
 }
 
+int test_elfutils(void)
+{
+	Dwarf_CFI *cfi = NULL;
+
+	dwarf_cfi_end(cfi);
+	return 0;
+}
+
 int main(void)
 {
 	return test_libdw() + test_libdw_unwind() + test_libdw_getlocations() +
-	       test_libdw_getcfi();
+	       test_libdw_getcfi() + test_elfutils();
 }
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index a30f88ed03004..bb27a406b7c61 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1379,9 +1379,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 	if (ret >= 0 && tf.pf.skip_empty_arg)
 		ret = fill_empty_trace_arg(pev, tf.tevs, tf.ntevs);
 
-#if _ELFUTILS_PREREQ(0, 142)
 	dwarf_cfi_end(tf.pf.cfi_eh);
-#endif
 
 	if (ret < 0 || tf.ntevs == 0) {
 		for (i = 0; i < tf.ntevs; i++)
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 724db829b49e0..5ced3b058fd8c 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -63,12 +63,10 @@ struct probe_finder {
 	struct intlist		*lcache;	/* Line cache for lazy match */
 
 	/* For variable searching */
-#if _ELFUTILS_PREREQ(0, 142)
 	/* Call Frame Information from .eh_frame. Owned by this struct. */
 	Dwarf_CFI		*cfi_eh;
 	/* Call Frame Information from .debug_frame. Not owned. */
 	Dwarf_CFI		*cfi_dbg;
-#endif
 	Dwarf_Op		*fb_ops;	/* Frame base attribute */
 	unsigned int		machine;	/* Target machine arch */
 	struct perf_probe_arg	*pvar;		/* Current target variable */

From 5eb2242513072b9ad3d39ff13d771479554ae4aa Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 16 Oct 2024 17:13:52 -0700
Subject: [PATCH 0491/1530] perf libdw: Remove unnecessary defines

As HAVE_DWARF_GETLOCATIONS_SUPPORT and HAVE_DWARF_CFI_SUPPORT always
match HAVE_DWARF_SUPPORT remove the macros and use
HAVE_DWARF_SUPPORT. If building the file is guarded by CONFIG_DWARF
then remove all ifs.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241017001354.56973-10-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Documentation/perf-check.txt |  2 +-
 tools/perf/Makefile.config              |  3 --
 tools/perf/builtin-annotate.c           |  2 +-
 tools/perf/builtin-check.c              |  2 +-
 tools/perf/builtin-report.c             |  2 +-
 tools/perf/util/dwarf-aux.c             |  6 ---
 tools/perf/util/dwarf-aux.h             | 54 -------------------------
 tools/perf/util/probe-finder.c          |  4 --
 8 files changed, 4 insertions(+), 71 deletions(-)

diff --git a/tools/perf/Documentation/perf-check.txt b/tools/perf/Documentation/perf-check.txt
index 10f69fb6850bc..45101a8e4154e 100644
--- a/tools/perf/Documentation/perf-check.txt
+++ b/tools/perf/Documentation/perf-check.txt
@@ -48,7 +48,7 @@ feature::
                 bpf_skeletons           /  HAVE_BPF_SKEL
                 debuginfod              /  HAVE_DEBUGINFOD_SUPPORT
                 dwarf                   /  HAVE_DWARF_SUPPORT
-                dwarf_getlocations      /  HAVE_DWARF_GETLOCATIONS_SUPPORT
+                dwarf_getlocations      /  HAVE_DWARF_SUPPORT
                 dwarf-unwind            /  HAVE_DWARF_UNWIND_SUPPORT
                 auxtrace                /  HAVE_AUXTRACE_SUPPORT
                 libaudit                /  HAVE_LIBAUDIT_SUPPORT
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 6378811f25686..7dbcf8394f3dc 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -466,9 +466,6 @@ else
         $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.157, disables dwarf support. Please install new elfutils-devel/libdw-dev)
         NO_LIBDW := 1
       endif
-    else
-      CFLAGS += -DHAVE_DWARF_GETLOCATIONS_SUPPORT
-      CFLAGS += -DHAVE_DWARF_CFI_SUPPORT
     endif # Dwarf support
   endif # libelf support
 endif # NO_LIBELF
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 3dc6197ef3fa6..04af13eb4a4c9 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -840,7 +840,7 @@ int cmd_annotate(int argc, const char **argv)
 	}
 #endif
 
-#ifndef HAVE_DWARF_GETLOCATIONS_SUPPORT
+#ifndef HAVE_DWARF_SUPPORT
 	if (annotate.data_type) {
 		pr_err("Error: Data type profiling is disabled due to missing DWARF support\n");
 		return -ENOTSUP;
diff --git a/tools/perf/builtin-check.c b/tools/perf/builtin-check.c
index 0b76b6e42b781..18c0a815243b2 100644
--- a/tools/perf/builtin-check.c
+++ b/tools/perf/builtin-check.c
@@ -28,7 +28,7 @@ struct feature_status supported_features[] = {
 	FEATURE_STATUS("bpf_skeletons", HAVE_BPF_SKEL),
 	FEATURE_STATUS("debuginfod", HAVE_DEBUGINFOD_SUPPORT),
 	FEATURE_STATUS("dwarf", HAVE_DWARF_SUPPORT),
-	FEATURE_STATUS("dwarf_getlocations", HAVE_DWARF_GETLOCATIONS_SUPPORT),
+	FEATURE_STATUS("dwarf_getlocations", HAVE_DWARF_SUPPORT),
 	FEATURE_STATUS("dwarf-unwind", HAVE_DWARF_UNWIND_SUPPORT),
 	FEATURE_STATUS("auxtrace", HAVE_AUXTRACE_SUPPORT),
 	FEATURE_STATUS("libaudit", HAVE_LIBAUDIT_SUPPORT),
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 36b344e39dd63..2251aa61ea53d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1705,7 +1705,7 @@ int cmd_report(int argc, const char **argv)
 		report.data_type = true;
 		annotate_opts.annotate_src = false;
 
-#ifndef HAVE_DWARF_GETLOCATIONS_SUPPORT
+#ifndef HAVE_DWARF_SUPPORT
 		pr_err("Error: Data type profiling is disabled due to missing DWARF support\n");
 		goto error;
 #endif
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 92eb9c8dc3e52..559c953ca1727 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1182,7 +1182,6 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 	return ret < 0 ? ret : strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
 }
 
-#if defined(HAVE_DWARF_GETLOCATIONS_SUPPORT) || defined(HAVE_DWARF_CFI_SUPPORT)
 static int reg_from_dwarf_op(Dwarf_Op *op)
 {
 	switch (op->atom) {
@@ -1245,9 +1244,7 @@ static bool check_allowed_ops(Dwarf_Op *ops, size_t nops)
 	}
 	return true;
 }
-#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT || HAVE_DWARF_CFI_SUPPORT */
 
-#ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
 /**
  * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
  * @sp_die: a subprogram DIE
@@ -1697,9 +1694,7 @@ void die_collect_global_vars(Dwarf_Die *cu_die, struct die_var_type **var_types)
 
 	die_find_child(cu_die, __die_collect_global_vars_cb, (void *)var_types, &die_mem);
 }
-#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
-#ifdef HAVE_DWARF_CFI_SUPPORT
 /**
  * die_get_cfa - Get frame base information
  * @dwarf: a Dwarf info
@@ -1732,7 +1727,6 @@ int die_get_cfa(Dwarf *dwarf, u64 pc, int *preg, int *poffset)
 	}
 	return -1;
 }
-#endif /* HAVE_DWARF_CFI_SUPPORT */
 
 /*
  * die_has_loclist - Check if DW_AT_location of @vr_die is a location list
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index bd75058125693..892c8c5c23fc0 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -9,7 +9,6 @@
 #include <elfutils/libdw.h>
 #include <elfutils/libdwfl.h>
 #include <elfutils/version.h>
-#include <errno.h>
 
 struct strbuf;
 
@@ -157,8 +156,6 @@ Dwarf_Die *die_get_member_type(Dwarf_Die *type_die, int offset, Dwarf_Die *die_m
 /* Return type info where the pointer and offset point to */
 Dwarf_Die *die_deref_ptr_type(Dwarf_Die *ptr_die, int offset, Dwarf_Die *die_mem);
 
-#ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
-
 /* Get byte offset range of given variable DIE */
 int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf);
 
@@ -177,58 +174,7 @@ void die_collect_vars(Dwarf_Die *sc_die, struct die_var_type **var_types);
 /* Save all global variables in this CU */
 void die_collect_global_vars(Dwarf_Die *cu_die, struct die_var_type **var_types);
 
-#else /*  HAVE_DWARF_GETLOCATIONS_SUPPORT */
-
-static inline int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
-				    Dwarf_Die *vr_die __maybe_unused,
-				    struct strbuf *buf __maybe_unused)
-{
-	return -ENOTSUP;
-}
-
-static inline Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die __maybe_unused,
-						  Dwarf_Addr pc __maybe_unused,
-						  int reg __maybe_unused,
-						  int *poffset __maybe_unused,
-						  bool is_fbreg __maybe_unused,
-						  Dwarf_Die *die_mem __maybe_unused)
-{
-	return NULL;
-}
-
-static inline Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die __maybe_unused,
-						   Dwarf_Addr addr __maybe_unused,
-						   Dwarf_Die *die_mem __maybe_unused,
-						   int *offset __maybe_unused)
-{
-	return NULL;
-}
-
-static inline void die_collect_vars(Dwarf_Die *sc_die __maybe_unused,
-				    struct die_var_type **var_types __maybe_unused)
-{
-}
-
-static inline void die_collect_global_vars(Dwarf_Die *cu_die __maybe_unused,
-					   struct die_var_type **var_types __maybe_unused)
-{
-}
-
-#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
-
-#ifdef HAVE_DWARF_CFI_SUPPORT
-
 /* Get the frame base information from CFA */
 int die_get_cfa(Dwarf *dwarf, u64 pc, int *preg, int *poffset);
 
-#else /* HAVE_DWARF_CFI_SUPPORT */
-
-static inline int die_get_cfa(Dwarf *dwarf __maybe_unused, u64 pc __maybe_unused,
-			      int *preg __maybe_unused, int *poffset __maybe_unused)
-{
-	return -1;
-}
-
-#endif /* HAVE_DWARF_CFI_SUPPORT */
-
 #endif /* _DWARF_AUX_H */
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index bb27a406b7c61..18181017f5fd3 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -602,7 +602,6 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 	ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
 	if (ret <= 0 || nops == 0) {
 		pf->fb_ops = NULL;
-#ifdef HAVE_DWARF_CFI_SUPPORT
 	} else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
 		   (pf->cfi_eh != NULL || pf->cfi_dbg != NULL)) {
 		if ((dwarf_cfi_addrframe(pf->cfi_eh, pf->addr, &frame) != 0 &&
@@ -613,7 +612,6 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 			free(frame);
 			return -ENOENT;
 		}
-#endif /* HAVE_DWARF_CFI_SUPPORT */
 	}
 
 	/* Call finder's callback handler */
@@ -1138,7 +1136,6 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 
 	pf->machine = ehdr.e_machine;
 
-#ifdef HAVE_DWARF_CFI_SUPPORT
 	do {
 		GElf_Shdr shdr;
 
@@ -1148,7 +1145,6 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 
 		pf->cfi_dbg = dwarf_getcfi(dbg->dbg);
 	} while (0);
-#endif /* HAVE_DWARF_CFI_SUPPORT */
 
 	ret = debuginfo__find_probe_location(dbg, pf);
 	return ret;

From 8838abf6261444f7d8047c363f90cafbd2ff32c5 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 16 Oct 2024 17:13:53 -0700
Subject: [PATCH 0492/1530] perf build: Rename HAVE_DWARF_SUPPORT to
 HAVE_LIBDW_SUPPORT

In Makefile.config for unwinding the name dwarf implies either
libunwind or libdw. Make it clearer that HAVE_DWARF_SUPPORT is really
just defined when libdw is present by renaming to HAVE_LIBDW_SUPPORT.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241017001354.56973-11-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Documentation/perf-check.txt         |  6 +++---
 tools/perf/Makefile.config                      |  2 +-
 tools/perf/arch/powerpc/annotate/instructions.c |  4 ++--
 tools/perf/arch/x86/annotate/instructions.c     |  2 +-
 tools/perf/builtin-annotate.c                   |  2 +-
 tools/perf/builtin-check.c                      |  6 +++---
 tools/perf/builtin-probe.c                      | 12 ++++++------
 tools/perf/builtin-report.c                     |  4 ++--
 tools/perf/util/annotate-data.h                 |  8 ++++----
 tools/perf/util/debuginfo.h                     |  6 +++---
 tools/perf/util/disasm.c                        |  4 ++--
 tools/perf/util/disasm.h                        |  4 ++--
 tools/perf/util/genelf.c                        |  4 ++--
 tools/perf/util/genelf.h                        |  2 +-
 tools/perf/util/include/dwarf-regs.h            |  6 +++---
 tools/perf/util/probe-event.c                   |  4 ++--
 tools/perf/util/probe-finder.h                  |  4 ++--
 17 files changed, 40 insertions(+), 40 deletions(-)

diff --git a/tools/perf/Documentation/perf-check.txt b/tools/perf/Documentation/perf-check.txt
index 45101a8e4154e..31741499e7867 100644
--- a/tools/perf/Documentation/perf-check.txt
+++ b/tools/perf/Documentation/perf-check.txt
@@ -47,15 +47,15 @@ feature::
                 bpf                     /  HAVE_LIBBPF_SUPPORT
                 bpf_skeletons           /  HAVE_BPF_SKEL
                 debuginfod              /  HAVE_DEBUGINFOD_SUPPORT
-                dwarf                   /  HAVE_DWARF_SUPPORT
-                dwarf_getlocations      /  HAVE_DWARF_SUPPORT
+                dwarf                   /  HAVE_LIBDW_SUPPORT
+                dwarf_getlocations      /  HAVE_LIBDW_SUPPORT
                 dwarf-unwind            /  HAVE_DWARF_UNWIND_SUPPORT
                 auxtrace                /  HAVE_AUXTRACE_SUPPORT
                 libaudit                /  HAVE_LIBAUDIT_SUPPORT
                 libbfd                  /  HAVE_LIBBFD_SUPPORT
                 libcapstone             /  HAVE_LIBCAPSTONE_SUPPORT
                 libcrypto               /  HAVE_LIBCRYPTO_SUPPORT
-                libdw-dwarf-unwind      /  HAVE_DWARF_SUPPORT
+                libdw-dwarf-unwind      /  HAVE_LIBDW_SUPPORT
                 libelf                  /  HAVE_LIBELF_SUPPORT
                 libnuma                 /  HAVE_LIBNUMA_SUPPORT
                 libopencsd              /  HAVE_CSTRACE_SUPPORT
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 7dbcf8394f3dc..d0ad2919983c0 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -559,7 +559,7 @@ ifndef NO_LIBELF
       $(warning DWARF register mappings have not been defined for architecture $(SRCARCH), DWARF support disabled)
       NO_LIBDW := 1
     else
-      CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS)
+      CFLAGS += -DHAVE_LIBDW_SUPPORT $(LIBDW_CFLAGS)
       LDFLAGS += $(LIBDW_LDFLAGS)
       EXTLIBS += ${DWARFLIBS}
       $(call detected,CONFIG_DWARF)
diff --git a/tools/perf/arch/powerpc/annotate/instructions.c b/tools/perf/arch/powerpc/annotate/instructions.c
index ede9eeade0ab3..54478cf5cccc9 100644
--- a/tools/perf/arch/powerpc/annotate/instructions.c
+++ b/tools/perf/arch/powerpc/annotate/instructions.c
@@ -255,7 +255,7 @@ static struct ins_ops *check_ppc_insn(struct disasm_line *dl)
  * is moved to r31. update_insn_state_powerpc tracks these state
  * changes
  */
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 static void update_insn_state_powerpc(struct type_state *state,
 		struct data_loc_info *dloc, Dwarf_Die * cu_die __maybe_unused,
 		struct disasm_line *dl)
@@ -300,7 +300,7 @@ static void update_insn_state_powerpc(struct type_state *state,
 			insn_offset, src->reg1, dst->reg1);
 	pr_debug_type_name(&tsr->type, tsr->kind);
 }
-#endif /* HAVE_DWARF_SUPPORT */
+#endif /* HAVE_LIBDW_SUPPORT */
 
 static int powerpc__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 5caf5a17f03d8..c869abe3c31da 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -207,7 +207,7 @@ static int x86__annotate_init(struct arch *arch, char *cpuid)
 	return err;
 }
 
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 static void update_insn_state_x86(struct type_state *state,
 				  struct data_loc_info *dloc, Dwarf_Die *cu_die,
 				  struct disasm_line *dl)
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 04af13eb4a4c9..bb87e6e7687dc 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -840,7 +840,7 @@ int cmd_annotate(int argc, const char **argv)
 	}
 #endif
 
-#ifndef HAVE_DWARF_SUPPORT
+#ifndef HAVE_LIBDW_SUPPORT
 	if (annotate.data_type) {
 		pr_err("Error: Data type profiling is disabled due to missing DWARF support\n");
 		return -ENOTSUP;
diff --git a/tools/perf/builtin-check.c b/tools/perf/builtin-check.c
index 18c0a815243b2..2346536a5ee14 100644
--- a/tools/perf/builtin-check.c
+++ b/tools/perf/builtin-check.c
@@ -27,15 +27,15 @@ struct feature_status supported_features[] = {
 	FEATURE_STATUS("bpf", HAVE_LIBBPF_SUPPORT),
 	FEATURE_STATUS("bpf_skeletons", HAVE_BPF_SKEL),
 	FEATURE_STATUS("debuginfod", HAVE_DEBUGINFOD_SUPPORT),
-	FEATURE_STATUS("dwarf", HAVE_DWARF_SUPPORT),
-	FEATURE_STATUS("dwarf_getlocations", HAVE_DWARF_SUPPORT),
+	FEATURE_STATUS("dwarf", HAVE_LIBDW_SUPPORT),
+	FEATURE_STATUS("dwarf_getlocations", HAVE_LIBDW_SUPPORT),
 	FEATURE_STATUS("dwarf-unwind", HAVE_DWARF_UNWIND_SUPPORT),
 	FEATURE_STATUS("auxtrace", HAVE_AUXTRACE_SUPPORT),
 	FEATURE_STATUS("libaudit", HAVE_LIBAUDIT_SUPPORT),
 	FEATURE_STATUS("libbfd", HAVE_LIBBFD_SUPPORT),
 	FEATURE_STATUS("libcapstone", HAVE_LIBCAPSTONE_SUPPORT),
 	FEATURE_STATUS("libcrypto", HAVE_LIBCRYPTO_SUPPORT),
-	FEATURE_STATUS("libdw-dwarf-unwind", HAVE_DWARF_SUPPORT),
+	FEATURE_STATUS("libdw-dwarf-unwind", HAVE_LIBDW_SUPPORT),
 	FEATURE_STATUS("libelf", HAVE_LIBELF_SUPPORT),
 	FEATURE_STATUS("libnuma", HAVE_LIBNUMA_SUPPORT),
 	FEATURE_STATUS("libopencsd", HAVE_CSTRACE_SUPPORT),
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 91672bb3047c3..69800e4d9530b 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -229,7 +229,7 @@ static int opt_set_target_ns(const struct option *opt __maybe_unused,
 
 /* Command option callbacks */
 
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 static int opt_show_lines(const struct option *opt,
 			  const char *str, int unset __maybe_unused)
 {
@@ -505,7 +505,7 @@ static int perf_del_probe_events(struct strfilter *filter)
 	return ret;
 }
 
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 #define PROBEDEF_STR	\
 	"[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT [[NAME=]ARG ...]"
 #else
@@ -521,7 +521,7 @@ __cmd_probe(int argc, const char **argv)
 		"perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
 		"perf probe [<options>] --del '[GROUP:]EVENT' ...",
 		"perf probe --list [GROUP:]EVENT ...",
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 		"perf probe [<options>] --line 'LINEDESC'",
 		"perf probe [<options>] --vars 'PROBEPOINT'",
 #endif
@@ -545,7 +545,7 @@ __cmd_probe(int argc, const char **argv)
 		"\t\tFUNC:\tFunction name\n"
 		"\t\tOFF:\tOffset from function entry (in byte)\n"
 		"\t\t%return:\tPut the probe at function return\n"
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 		"\t\tSRC:\tSource code path\n"
 		"\t\tRL:\tRelative line number from function entry.\n"
 		"\t\tAL:\tAbsolute line number in file.\n"
@@ -612,7 +612,7 @@ __cmd_probe(int argc, const char **argv)
 	set_option_flag(options, 'd', "del", PARSE_OPT_EXCLUSIVE);
 	set_option_flag(options, 'D', "definition", PARSE_OPT_EXCLUSIVE);
 	set_option_flag(options, 'l', "list", PARSE_OPT_EXCLUSIVE);
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 	set_option_flag(options, 'L', "line", PARSE_OPT_EXCLUSIVE);
 	set_option_flag(options, 'V', "vars", PARSE_OPT_EXCLUSIVE);
 #else
@@ -694,7 +694,7 @@ __cmd_probe(int argc, const char **argv)
 		if (ret < 0)
 			pr_err_with_code("  Error: Failed to show functions.", ret);
 		return ret;
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 	case 'L':
 		ret = show_line_range(&params->line_range, params->target,
 				      params->nsi, params->uprobes);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 2251aa61ea53d..45304ee5537cb 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -455,7 +455,7 @@ static int report__setup_sample_type(struct report *rep)
 	if (!(evlist__combined_branch_type(session->evlist) & PERF_SAMPLE_BRANCH_ANY))
 		rep->nonany_branch_mode = true;
 
-#if !defined(HAVE_LIBUNWIND_SUPPORT) && !defined(HAVE_DWARF_SUPPORT)
+#if !defined(HAVE_LIBUNWIND_SUPPORT) && !defined(HAVE_LIBDW_SUPPORT)
 	if (dwarf_callchain_users) {
 		ui__warning("Please install libunwind or libdw "
 			    "development packages during the perf build.\n");
@@ -1705,7 +1705,7 @@ int cmd_report(int argc, const char **argv)
 		report.data_type = true;
 		annotate_opts.annotate_src = false;
 
-#ifndef HAVE_DWARF_SUPPORT
+#ifndef HAVE_LIBDW_SUPPORT
 		pr_err("Error: Data type profiling is disabled due to missing DWARF support\n");
 		goto error;
 #endif
diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
index 8ac0fd94a0ba4..98c80b2268dde 100644
--- a/tools/perf/util/annotate-data.h
+++ b/tools/perf/util/annotate-data.h
@@ -9,7 +9,7 @@
 #include "dwarf-regs.h"
 #include "annotate.h"
 
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 #include "debuginfo.h"
 #endif
 
@@ -165,7 +165,7 @@ struct annotated_data_stat {
 };
 extern struct annotated_data_stat ann_data_stat;
 
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 /*
  * Type information in a register, valid when @ok is true.
  * The @caller_saved registers are invalidated after a function call.
@@ -244,7 +244,7 @@ bool get_global_var_info(struct data_loc_info *dloc, u64 addr,
 				const char **var_name, int *var_offset);
 void pr_debug_type_name(Dwarf_Die *die, enum type_state_kind kind);
 
-#else /* HAVE_DWARF_SUPPORT */
+#else /* HAVE_LIBDW_SUPPORT */
 
 static inline struct annotated_data_type *
 find_data_type(struct data_loc_info *dloc __maybe_unused)
@@ -276,7 +276,7 @@ static inline int hist_entry__annotate_data_tty(struct hist_entry *he __maybe_un
 	return -1;
 }
 
-#endif /* HAVE_DWARF_SUPPORT */
+#endif /* HAVE_LIBDW_SUPPORT */
 
 #ifdef HAVE_SLANG_SUPPORT
 int hist_entry__annotate_data_tui(struct hist_entry *he, struct evsel *evsel,
diff --git a/tools/perf/util/debuginfo.h b/tools/perf/util/debuginfo.h
index ad6422c3f8ca3..a52d69932815c 100644
--- a/tools/perf/util/debuginfo.h
+++ b/tools/perf/util/debuginfo.h
@@ -5,7 +5,7 @@
 #include <errno.h>
 #include <linux/compiler.h>
 
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 
 #include "dwarf-aux.h"
 
@@ -25,7 +25,7 @@ void debuginfo__delete(struct debuginfo *dbg);
 int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
 			       bool adjust_offset);
 
-#else /* HAVE_DWARF_SUPPORT */
+#else /* HAVE_LIBDW_SUPPORT */
 
 /* dummy debug information structure */
 struct debuginfo {
@@ -49,7 +49,7 @@ static inline int debuginfo__get_text_offset(struct debuginfo *dbg __maybe_unuse
 	return -EINVAL;
 }
 
-#endif /* HAVE_DWARF_SUPPORT */
+#endif /* HAVE_LIBDW_SUPPORT */
 
 #ifdef HAVE_DEBUGINFOD_SUPPORT
 int get_source_from_debuginfod(const char *raw_path, const char *sbuild_id,
diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index 2c8063660f2e8..aef06a36bf40a 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -151,14 +151,14 @@ static struct arch architectures[] = {
 			.memory_ref_char = '(',
 			.imm_char = '$',
 		},
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 		.update_insn_state = update_insn_state_x86,
 #endif
 	},
 	{
 		.name = "powerpc",
 		.init = powerpc__annotate_init,
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 		.update_insn_state = update_insn_state_powerpc,
 #endif
 	},
diff --git a/tools/perf/util/disasm.h b/tools/perf/util/disasm.h
index f56beedeb9dad..486c269b29ba5 100644
--- a/tools/perf/util/disasm.h
+++ b/tools/perf/util/disasm.h
@@ -4,7 +4,7 @@
 
 #include "map_symbol.h"
 
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 #include "dwarf-aux.h"
 #endif
 
@@ -39,7 +39,7 @@ struct arch {
 		char memory_ref_char;
 		char imm_char;
 	} objdump;
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 	void		(*update_insn_state)(struct type_state *state,
 				struct data_loc_info *dloc, Dwarf_Die *cu_die,
 				struct disasm_line *dl);
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index c8f6bee1fa619..cdce7f173d00a 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -16,7 +16,7 @@
 #include <inttypes.h>
 #include <fcntl.h>
 #include <err.h>
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 #include <dwarf.h>
 #endif
 
@@ -499,7 +499,7 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym,
 	shdr->sh_size = sizeof(bnote);
 	shdr->sh_entsize = 0;
 
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 	if (debug && nr_debug_entries) {
 		retval = jit_add_debug_info(e, load_addr, debug, nr_debug_entries);
 		if (retval)
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index 4e2e4f40e134f..9f0b875d6548c 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -8,7 +8,7 @@
 int jit_write_elf(int fd, uint64_t code_addr, const char *sym,
 		  const void *code, int csize, void *debug, int nr_debug_entries,
 		  void *unwinding, uint64_t unwinding_header_size, uint64_t unwinding_size);
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 /* genelf_debug.c */
 int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries);
 #endif
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 75b28dcc8317d..29a7d0546b823 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -6,7 +6,7 @@
 #define DWARF_REG_PC  0xd3af9c /* random number */
 #define DWARF_REG_FB  0xd3affb /* random number */
 
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 const char *get_arch_regstr(unsigned int n);
 /*
  * get_dwarf_regstr - Returns ftrace register string from DWARF regnum
@@ -23,7 +23,7 @@ int get_arch_regnum(const char *name);
  */
 int get_dwarf_regnum(const char *name, unsigned int machine);
 
-#else /* HAVE_DWARF_SUPPORT */
+#else /* HAVE_LIBDW_SUPPORT */
 
 static inline int get_dwarf_regnum(const char *name __maybe_unused,
 				   unsigned int machine __maybe_unused)
@@ -32,7 +32,7 @@ static inline int get_dwarf_regnum(const char *name __maybe_unused,
 }
 #endif
 
-#if !defined(__powerpc__) || !defined(HAVE_DWARF_SUPPORT)
+#if !defined(__powerpc__) || !defined(HAVE_LIBDW_SUPPORT)
 static inline void get_powerpc_regs(u32 raw_insn __maybe_unused, int is_source __maybe_unused,
 		struct annotated_op_loc *op_loc __maybe_unused)
 {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 2c8d94d09e86c..a580aa2cd5120 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -345,7 +345,7 @@ static char *find_module_name(const char *module)
 	return mod_name;
 }
 
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 
 static int kernel_get_module_dso(const char *module, struct dso **pdso)
 {
@@ -1253,7 +1253,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	return ret;
 }
 
-#else	/* !HAVE_DWARF_SUPPORT */
+#else	/* !HAVE_LIBDW_SUPPORT */
 
 static void debuginfo_cache__exit(void)
 {
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 5ced3b058fd8c..dfcf8cdd9e8db 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -21,7 +21,7 @@ static inline int is_c_varname(const char *name)
 	return isalpha(name[0]) || name[0] == '_';
 }
 
-#ifdef HAVE_DWARF_SUPPORT
+#ifdef HAVE_LIBDW_SUPPORT
 
 #include "dwarf-aux.h"
 #include "debuginfo.h"
@@ -102,6 +102,6 @@ struct line_finder {
 	int			found;
 };
 
-#endif /* HAVE_DWARF_SUPPORT */
+#endif /* HAVE_LIBDW_SUPPORT */
 
 #endif /*_PROBE_FINDER_H */

From 5455d89bf3da85176606ff861f4178f6bea648ba Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 16 Oct 2024 17:13:54 -0700
Subject: [PATCH 0493/1530] perf build: Rename CONFIG_DWARF to CONFIG_LIBDW

In Makefile.config for unwinding the name dwarf implies either
libunwind or libdw. Make it clearer that CONFIG_DWARF is really just
defined when libdw is present by renaming to CONFIG_LIBDW.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241017001354.56973-12-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Makefile.config           |  2 +-
 tools/perf/arch/arm/util/Build       |  2 +-
 tools/perf/arch/arm64/util/Build     |  2 +-
 tools/perf/arch/csky/util/Build      |  2 +-
 tools/perf/arch/loongarch/util/Build |  2 +-
 tools/perf/arch/mips/util/Build      |  2 +-
 tools/perf/arch/powerpc/util/Build   |  4 ++--
 tools/perf/arch/riscv/util/Build     |  2 +-
 tools/perf/arch/s390/util/Build      |  2 +-
 tools/perf/arch/sh/util/Build        |  2 +-
 tools/perf/arch/sparc/util/Build     |  2 +-
 tools/perf/arch/x86/util/Build       |  2 +-
 tools/perf/arch/xtensa/util/Build    |  2 +-
 tools/perf/util/Build                | 12 ++++++------
 14 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index d0ad2919983c0..b93ed2b7623f9 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -562,7 +562,7 @@ ifndef NO_LIBELF
       CFLAGS += -DHAVE_LIBDW_SUPPORT $(LIBDW_CFLAGS)
       LDFLAGS += $(LIBDW_LDFLAGS)
       EXTLIBS += ${DWARFLIBS}
-      $(call detected,CONFIG_DWARF)
+      $(call detected,CONFIG_LIBDW)
     endif # PERF_HAVE_DWARF_REGS
   endif # NO_LIBDW
 
diff --git a/tools/perf/arch/arm/util/Build b/tools/perf/arch/arm/util/Build
index e6dd7cd79ebd0..e06fea1ea8ff7 100644
--- a/tools/perf/arch/arm/util/Build
+++ b/tools/perf/arch/arm/util/Build
@@ -1,6 +1,6 @@
 perf-util-y += perf_regs.o
 
-perf-util-$(CONFIG_DWARF) += dwarf-regs.o
+perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
 
 perf-util-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index 343ef7589a77a..4387a6d6a6c3b 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -4,7 +4,7 @@ perf-util-y += perf_regs.o
 perf-util-y += tsc.o
 perf-util-y += pmu.o
 perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o
-perf-util-$(CONFIG_DWARF)     += dwarf-regs.o
+perf-util-$(CONFIG_LIBDW)     += dwarf-regs.o
 perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
diff --git a/tools/perf/arch/csky/util/Build b/tools/perf/arch/csky/util/Build
index 99d83f41bf433..1325310cab6a4 100644
--- a/tools/perf/arch/csky/util/Build
+++ b/tools/perf/arch/csky/util/Build
@@ -1,4 +1,4 @@
 perf-util-y += perf_regs.o
 
-perf-util-$(CONFIG_DWARF) += dwarf-regs.o
+perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/arch/loongarch/util/Build b/tools/perf/arch/loongarch/util/Build
index b6b97de482333..06ff95394921c 100644
--- a/tools/perf/arch/loongarch/util/Build
+++ b/tools/perf/arch/loongarch/util/Build
@@ -1,7 +1,7 @@
 perf-util-y += header.o
 perf-util-y += perf_regs.o
 
-perf-util-$(CONFIG_DWARF)     += dwarf-regs.o
+perf-util-$(CONFIG_LIBDW)     += dwarf-regs.o
 perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o
diff --git a/tools/perf/arch/mips/util/Build b/tools/perf/arch/mips/util/Build
index e4644f1e68a03..b328109fc16c6 100644
--- a/tools/perf/arch/mips/util/Build
+++ b/tools/perf/arch/mips/util/Build
@@ -1,3 +1,3 @@
 perf-util-y += perf_regs.o
-perf-util-$(CONFIG_DWARF) += dwarf-regs.o
+perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
 perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 6c588ecdf3bd4..3d979480a1888 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -7,8 +7,8 @@ perf-util-y += sym-handling.o
 perf-util-y += evsel.o
 perf-util-y += event.o
 
-perf-util-$(CONFIG_DWARF) += dwarf-regs.o
-perf-util-$(CONFIG_DWARF) += skip-callchain-idx.o
+perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
+perf-util-$(CONFIG_LIBDW) += skip-callchain-idx.o
 
 perf-util-$(CONFIG_LIBUNWIND) += unwind-libunwind.o
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/arch/riscv/util/Build b/tools/perf/arch/riscv/util/Build
index f865cb0489ec6..8f93091b83457 100644
--- a/tools/perf/arch/riscv/util/Build
+++ b/tools/perf/arch/riscv/util/Build
@@ -2,5 +2,5 @@ perf-util-y += perf_regs.o
 perf-util-y += header.o
 
 perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o
-perf-util-$(CONFIG_DWARF) += dwarf-regs.o
+perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build
index 1ac830030ff3f..787410f99bb32 100644
--- a/tools/perf/arch/s390/util/Build
+++ b/tools/perf/arch/s390/util/Build
@@ -2,7 +2,7 @@ perf-util-y += header.o
 perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o
 perf-util-y += perf_regs.o
 
-perf-util-$(CONFIG_DWARF) += dwarf-regs.o
+perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
 perf-util-y += machine.o
diff --git a/tools/perf/arch/sh/util/Build b/tools/perf/arch/sh/util/Build
index 32f44fc4ab985..2337a0b710a24 100644
--- a/tools/perf/arch/sh/util/Build
+++ b/tools/perf/arch/sh/util/Build
@@ -1 +1 @@
-perf-util-$(CONFIG_DWARF) += dwarf-regs.o
+perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
diff --git a/tools/perf/arch/sparc/util/Build b/tools/perf/arch/sparc/util/Build
index 32f44fc4ab985..2337a0b710a24 100644
--- a/tools/perf/arch/sparc/util/Build
+++ b/tools/perf/arch/sparc/util/Build
@@ -1 +1 @@
-perf-util-$(CONFIG_DWARF) += dwarf-regs.o
+perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 2607ed5c42966..9705cda4f2400 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -12,7 +12,7 @@ perf-util-y += evsel.o
 perf-util-y += iostat.o
 perf-util-y += env.o
 
-perf-util-$(CONFIG_DWARF) += dwarf-regs.o
+perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
 perf-util-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
 
 perf-util-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
diff --git a/tools/perf/arch/xtensa/util/Build b/tools/perf/arch/xtensa/util/Build
index e813e618954b0..2d1a48696ad92 100644
--- a/tools/perf/arch/xtensa/util/Build
+++ b/tools/perf/arch/xtensa/util/Build
@@ -1 +1 @@
-perf-$(CONFIG_DWARF) += dwarf-regs.o
+perf-$(CONFIG_LIBDW) += dwarf-regs.o
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index fa508e113dd0c..1eedead5f2f28 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -200,11 +200,11 @@ ifndef CONFIG_SETNS
 perf-util-y += setns.o
 endif
 
-perf-util-$(CONFIG_DWARF) += probe-finder.o
-perf-util-$(CONFIG_DWARF) += dwarf-aux.o
-perf-util-$(CONFIG_DWARF) += dwarf-regs.o
-perf-util-$(CONFIG_DWARF) += debuginfo.o
-perf-util-$(CONFIG_DWARF) += annotate-data.o
+perf-util-$(CONFIG_LIBDW) += probe-finder.o
+perf-util-$(CONFIG_LIBDW) += dwarf-aux.o
+perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
+perf-util-$(CONFIG_LIBDW) += debuginfo.o
+perf-util-$(CONFIG_LIBDW) += annotate-data.o
 
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 perf-util-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind-local.o
@@ -235,7 +235,7 @@ perf-util-$(CONFIG_LIBLLVM) += llvm-c-helpers.o
 ifdef CONFIG_JITDUMP
 perf-util-$(CONFIG_LIBELF) += jitdump.o
 perf-util-$(CONFIG_LIBELF) += genelf.o
-perf-util-$(CONFIG_DWARF) += genelf_debug.o
+perf-util-$(CONFIG_LIBDW) += genelf_debug.o
 endif
 
 perf-util-y += perf-hooks.o

From 6eaa83ec229b1e99130456c4f6658430d509c76c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Thu, 17 Oct 2024 17:11:08 +0300
Subject: [PATCH 0494/1530] PCI: Remove unused PCI_SUBTRACTIVE_DECODE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

2fe2abf896c1 ("PCI: augment bus resource table with a list") added
PCI_SUBTRACTIVE_DECODE which is put into the struct pci_bus_resource flags
field but is never read. There seems to never have been users for it.

Remove both PCI_SUBTRACTIVE_DECODE and the flags field from the struct
pci_bus_resource.

Link: https://lore.kernel.org/r/20241017141111.44612-1-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 arch/s390/pci/pci_bus.c |  2 +-
 arch/x86/pci/fixup.c    |  2 +-
 drivers/pci/bus.c       |  4 +---
 drivers/pci/probe.c     |  5 ++---
 include/linux/pci.h     | 12 +-----------
 5 files changed, 6 insertions(+), 19 deletions(-)

diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c
index daa5d7450c7d3..5630af5deb8b9 100644
--- a/arch/s390/pci/pci_bus.c
+++ b/arch/s390/pci/pci_bus.c
@@ -53,7 +53,7 @@ static int zpci_bus_prepare_device(struct zpci_dev *zdev)
 		zpci_setup_bus_resources(zdev);
 		for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 			if (zdev->bars[i].res)
-				pci_bus_add_resource(zdev->zbus->bus, zdev->bars[i].res, 0);
+				pci_bus_add_resource(zdev->zbus->bus, zdev->bars[i].res);
 		}
 	}
 
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 98a9bb92d75c8..0681ecfe34300 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -757,7 +757,7 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev)
 		dev_info(&dev->dev, "adding root bus resource %pR (tainting kernel)\n",
 			 res);
 		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
-		pci_bus_add_resource(dev->bus, res, 0);
+		pci_bus_add_resource(dev->bus, res);
 	}
 
 	base = ((res->start >> 8) & AMD_141b_MMIO_BASE_MMIOBASE_MASK) |
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 55c8536860518..9cf6d0f3ab2be 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -46,8 +46,7 @@ void pci_free_resource_list(struct list_head *resources)
 }
 EXPORT_SYMBOL(pci_free_resource_list);
 
-void pci_bus_add_resource(struct pci_bus *bus, struct resource *res,
-			  unsigned int flags)
+void pci_bus_add_resource(struct pci_bus *bus, struct resource *res)
 {
 	struct pci_bus_resource *bus_res;
 
@@ -58,7 +57,6 @@ void pci_bus_add_resource(struct pci_bus *bus, struct resource *res,
 	}
 
 	bus_res->res = res;
-	bus_res->flags = flags;
 	list_add_tail(&bus_res->list, &bus->resources);
 }
 
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 4f68414c30860..4243b1e6ece26 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -546,8 +546,7 @@ void pci_read_bridge_bases(struct pci_bus *child)
 	if (dev->transparent) {
 		pci_bus_for_each_resource(child->parent, res) {
 			if (res && res->flags) {
-				pci_bus_add_resource(child, res,
-						     PCI_SUBTRACTIVE_DECODE);
+				pci_bus_add_resource(child, res);
 				pci_info(dev, "  bridge window %pR (subtractive decode)\n",
 					   res);
 			}
@@ -1032,7 +1031,7 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 		if (res->flags & IORESOURCE_BUS)
 			pci_bus_insert_busn_res(bus, bus->number, res->end);
 		else
-			pci_bus_add_resource(bus, res, 0);
+			pci_bus_add_resource(bus, res);
 
 		if (offset) {
 			if (resource_type(res) == IORESOURCE_IO)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 573b4c4c2be61..6a9cf80d0d4ba 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -633,18 +633,9 @@ int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge);
  * Use pci_bus_for_each_resource() to iterate through all the resources.
  */
 
-/*
- * PCI_SUBTRACTIVE_DECODE means the bridge forwards the window implicitly
- * and there's no way to program the bridge with the details of the window.
- * This does not apply to ACPI _CRS windows, even with the _DEC subtractive-
- * decode bit set, because they are explicit and can be programmed with _SRS.
- */
-#define PCI_SUBTRACTIVE_DECODE	0x1
-
 struct pci_bus_resource {
 	struct list_head	list;
 	struct resource		*res;
-	unsigned int		flags;
 };
 
 #define PCI_REGION_FLAG_MASK	0x0fU	/* These bits of resource flags tell us the PCI region flags */
@@ -1498,8 +1489,7 @@ void pci_add_resource(struct list_head *resources, struct resource *res);
 void pci_add_resource_offset(struct list_head *resources, struct resource *res,
 			     resource_size_t offset);
 void pci_free_resource_list(struct list_head *resources);
-void pci_bus_add_resource(struct pci_bus *bus, struct resource *res,
-			  unsigned int flags);
+void pci_bus_add_resource(struct pci_bus *bus, struct resource *res);
 struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n);
 void pci_bus_remove_resources(struct pci_bus *bus);
 void pci_bus_remove_resource(struct pci_bus *bus, struct resource *res);

From 469c9cb941480718db52876bbdb95a7a79b34889 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Thu, 17 Oct 2024 17:11:09 +0300
Subject: [PATCH 0495/1530] PCI: Move struct pci_bus_resource into bus.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The struct pci_bus_resource is only used in bus.c, so move it there.

Link: https://lore.kernel.org/r/20241017141111.44612-2-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/bus.c   | 12 ++++++++++++
 include/linux/pci.h | 12 ------------
 2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 9cf6d0f3ab2be..e0a2441be6d32 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -18,6 +18,18 @@
 
 #include "pci.h"
 
+/*
+ * The first PCI_BRIDGE_RESOURCE_NUM PCI bus resources (those that correspond
+ * to P2P or CardBus bridge windows) go in a table.  Additional ones (for
+ * buses below host bridges or subtractive decode bridges) go in the list.
+ * Use pci_bus_for_each_resource() to iterate through all the resources.
+ */
+
+struct pci_bus_resource {
+	struct list_head	list;
+	struct resource		*res;
+};
+
 void pci_add_resource_offset(struct list_head *resources, struct resource *res,
 			     resource_size_t offset)
 {
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 6a9cf80d0d4ba..5a9d849b28ef3 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -626,18 +626,6 @@ void pci_set_host_bridge_release(struct pci_host_bridge *bridge,
 
 int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge);
 
-/*
- * The first PCI_BRIDGE_RESOURCE_NUM PCI bus resources (those that correspond
- * to P2P or CardBus bridge windows) go in a table.  Additional ones (for
- * buses below host bridges or subtractive decode bridges) go in the list.
- * Use pci_bus_for_each_resource() to iterate through all the resources.
- */
-
-struct pci_bus_resource {
-	struct list_head	list;
-	struct resource		*res;
-};
-
 #define PCI_REGION_FLAG_MASK	0x0fU	/* These bits of resource flags tell us the PCI region flags */
 
 struct pci_bus {

From 32ec7b362d904c1e67f8e64524fb0b6c43d5c9c2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Thu, 17 Oct 2024 17:11:10 +0300
Subject: [PATCH 0496/1530] PCI: Simplify pci_read_bridge_bases() logic
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use reverse logic combined with return and continue to significantly
reduce indentation level in pci_read_bridge_bases().

Link: https://lore.kernel.org/r/20241017141111.44612-3-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/probe.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 4243b1e6ece26..f9524b90bdbcc 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -543,14 +543,15 @@ void pci_read_bridge_bases(struct pci_bus *child)
 	pci_read_bridge_mmio(child->self, child->resource[1], false);
 	pci_read_bridge_mmio_pref(child->self, child->resource[2], false);
 
-	if (dev->transparent) {
-		pci_bus_for_each_resource(child->parent, res) {
-			if (res && res->flags) {
-				pci_bus_add_resource(child, res);
-				pci_info(dev, "  bridge window %pR (subtractive decode)\n",
-					   res);
-			}
-		}
+	if (!dev->transparent)
+		return;
+
+	pci_bus_for_each_resource(child->parent, res) {
+		if (!res || !res->flags)
+			continue;
+
+		pci_bus_add_resource(child, res);
+		pci_info(dev, "  bridge window %pR (subtractive decode)\n", res);
 	}
 }
 

From 8d20a739f17a2de9e269db72330f5655d6545dd4 Mon Sep 17 00:00:00 2001
From: Jesse Taube <jesse@rivosinc.com>
Date: Thu, 17 Oct 2024 12:00:18 -0700
Subject: [PATCH 0497/1530] RISC-V: Check scalar unaligned access on all CPUs

Originally, the check_unaligned_access_emulated_all_cpus function
only checked the boot hart. This fixes the function to check all
harts.

Fixes: 71c54b3d169d ("riscv: report misaligned accesses emulation to hwprobe")
Signed-off-by: Jesse Taube <jesse@rivosinc.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20241017-jesse_unaligned_vector-v10-1-5b33500160f8@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/cpufeature.h  |  2 ++
 arch/riscv/kernel/traps_misaligned.c | 14 +++++++-------
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 45f9c1171a486..dfa5cdddd3671 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -8,6 +8,7 @@
 
 #include <linux/bitmap.h>
 #include <linux/jump_label.h>
+#include <linux/workqueue.h>
 #include <asm/hwcap.h>
 #include <asm/alternative-macros.h>
 #include <asm/errno.h>
@@ -60,6 +61,7 @@ void riscv_user_isa_enable(void);
 
 #if defined(CONFIG_RISCV_MISALIGNED)
 bool check_unaligned_access_emulated_all_cpus(void);
+void check_unaligned_access_emulated(struct work_struct *work __always_unused);
 void unaligned_emulation_finish(void);
 bool unaligned_ctl_available(void);
 DECLARE_PER_CPU(long, misaligned_access_speed);
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index d4fd8af7aaf5a..d076dde5ad204 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -526,11 +526,11 @@ int handle_misaligned_store(struct pt_regs *regs)
 	return 0;
 }
 
-static bool check_unaligned_access_emulated(int cpu)
+void check_unaligned_access_emulated(struct work_struct *work __always_unused)
 {
+	int cpu = smp_processor_id();
 	long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu);
 	unsigned long tmp_var, tmp_val;
-	bool misaligned_emu_detected;
 
 	*mas_ptr = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN;
 
@@ -538,19 +538,16 @@ static bool check_unaligned_access_emulated(int cpu)
 		"       "REG_L" %[tmp], 1(%[ptr])\n"
 		: [tmp] "=r" (tmp_val) : [ptr] "r" (&tmp_var) : "memory");
 
-	misaligned_emu_detected = (*mas_ptr == RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED);
 	/*
 	 * If unaligned_ctl is already set, this means that we detected that all
 	 * CPUS uses emulated misaligned access at boot time. If that changed
 	 * when hotplugging the new cpu, this is something we don't handle.
 	 */
-	if (unlikely(unaligned_ctl && !misaligned_emu_detected)) {
+	if (unlikely(unaligned_ctl && (*mas_ptr != RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED))) {
 		pr_crit("CPU misaligned accesses non homogeneous (expected all emulated)\n");
 		while (true)
 			cpu_relax();
 	}
-
-	return misaligned_emu_detected;
 }
 
 bool check_unaligned_access_emulated_all_cpus(void)
@@ -562,8 +559,11 @@ bool check_unaligned_access_emulated_all_cpus(void)
 	 * accesses emulated since tasks requesting such control can run on any
 	 * CPU.
 	 */
+	schedule_on_each_cpu(check_unaligned_access_emulated);
+
 	for_each_online_cpu(cpu)
-		if (!check_unaligned_access_emulated(cpu))
+		if (per_cpu(misaligned_access_speed, cpu)
+		    != RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED)
 			return false;
 
 	unaligned_ctl = true;

From 9c528b5f7927b857b40f3c46afbc869827af3c94 Mon Sep 17 00:00:00 2001
From: Jesse Taube <jesse@rivosinc.com>
Date: Thu, 17 Oct 2024 12:00:19 -0700
Subject: [PATCH 0498/1530] RISC-V: Scalar unaligned access emulated on hotplug
 CPUs

The check_unaligned_access_emulated() function should have been called
during CPU hotplug to ensure that if all CPUs had emulated unaligned
accesses, the new CPU also does.

This patch adds the call to check_unaligned_access_emulated() in
the hotplug path.

Fixes: 55e0bf49a0d0 ("RISC-V: Probe misaligned access speed in parallel")
Signed-off-by: Jesse Taube <jesse@rivosinc.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20241017-jesse_unaligned_vector-v10-2-5b33500160f8@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/unaligned_access_speed.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c
index 160628a2116de..f3508cc54f91a 100644
--- a/arch/riscv/kernel/unaligned_access_speed.c
+++ b/arch/riscv/kernel/unaligned_access_speed.c
@@ -191,6 +191,7 @@ static int riscv_online_cpu(unsigned int cpu)
 	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN)
 		goto exit;
 
+	check_unaligned_access_emulated(NULL);
 	buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
 	if (!buf) {
 		pr_warn("Allocation failure, not measuring misaligned performance\n");

From c05a62c92516d7679c819f8a5177cf84c8668954 Mon Sep 17 00:00:00 2001
From: Jesse Taube <jesse@rivosinc.com>
Date: Thu, 17 Oct 2024 12:00:20 -0700
Subject: [PATCH 0499/1530] RISC-V: Replace RISCV_MISALIGNED with
 RISCV_SCALAR_MISALIGNED

Replace RISCV_MISALIGNED with RISCV_SCALAR_MISALIGNED to allow
for the addition of RISCV_VECTOR_MISALIGNED in a later patch.

Signed-off-by: Jesse Taube <jesse@rivosinc.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Link: https://lore.kernel.org/r/20241017-jesse_unaligned_vector-v10-3-5b33500160f8@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig                    | 6 +++---
 arch/riscv/include/asm/cpufeature.h   | 2 +-
 arch/riscv/include/asm/entry-common.h | 2 +-
 arch/riscv/kernel/Makefile            | 4 ++--
 arch/riscv/kernel/fpu.S               | 4 ++--
 5 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 22dc5ea4196ce..fab7c6bc17298 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -784,7 +784,7 @@ config THREAD_SIZE_ORDER
 	  Specify the Pages of thread stack size (from 4KB to 64KB), which also
 	  affects irq stack size, which is equal to thread stack size.
 
-config RISCV_MISALIGNED
+config RISCV_SCALAR_MISALIGNED
 	bool
 	select SYSCTL_ARCH_UNALIGN_ALLOW
 	help
@@ -801,7 +801,7 @@ choice
 
 config RISCV_PROBE_UNALIGNED_ACCESS
 	bool "Probe for hardware unaligned access support"
-	select RISCV_MISALIGNED
+	select RISCV_SCALAR_MISALIGNED
 	help
 	  During boot, the kernel will run a series of tests to determine the
 	  speed of unaligned accesses. This probing will dynamically determine
@@ -812,7 +812,7 @@ config RISCV_PROBE_UNALIGNED_ACCESS
 
 config RISCV_EMULATED_UNALIGNED_ACCESS
 	bool "Emulate unaligned access where system support is missing"
-	select RISCV_MISALIGNED
+	select RISCV_SCALAR_MISALIGNED
 	help
 	  If unaligned memory accesses trap into the kernel as they are not
 	  supported by the system, the kernel will emulate the unaligned
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index dfa5cdddd3671..ccc6cf141c20e 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -59,7 +59,7 @@ void riscv_user_isa_enable(void);
 #define __RISCV_ISA_EXT_SUPERSET_VALIDATE(_name, _id, _sub_exts, _validate) \
 	_RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), _validate)
 
-#if defined(CONFIG_RISCV_MISALIGNED)
+#if defined(CONFIG_RISCV_SCALAR_MISALIGNED)
 bool check_unaligned_access_emulated_all_cpus(void);
 void check_unaligned_access_emulated(struct work_struct *work __always_unused);
 void unaligned_emulation_finish(void);
diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h
index 2293e535f8659..0a4e3544c877a 100644
--- a/arch/riscv/include/asm/entry-common.h
+++ b/arch/riscv/include/asm/entry-common.h
@@ -25,7 +25,7 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 void handle_page_fault(struct pt_regs *regs);
 void handle_break(struct pt_regs *regs);
 
-#ifdef CONFIG_RISCV_MISALIGNED
+#ifdef CONFIG_RISCV_SCALAR_MISALIGNED
 int handle_misaligned_load(struct pt_regs *regs);
 int handle_misaligned_store(struct pt_regs *regs);
 #else
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 7f88cc4931f5c..45624c5ea86c6 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -68,8 +68,8 @@ obj-y	+= probes/
 obj-y	+= tests/
 obj-$(CONFIG_MMU) += vdso.o vdso/
 
-obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
-obj-$(CONFIG_RISCV_MISALIGNED)	+= unaligned_access_speed.o
+obj-$(CONFIG_RISCV_SCALAR_MISALIGNED)	+= traps_misaligned.o
+obj-$(CONFIG_RISCV_SCALAR_MISALIGNED)	+= unaligned_access_speed.o
 obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)	+= copy-unaligned.o
 
 obj-$(CONFIG_FPU)		+= fpu.o
diff --git a/arch/riscv/kernel/fpu.S b/arch/riscv/kernel/fpu.S
index 327cf527dd7e1..f74f6b60e347f 100644
--- a/arch/riscv/kernel/fpu.S
+++ b/arch/riscv/kernel/fpu.S
@@ -170,7 +170,7 @@ SYM_FUNC_END(__fstate_restore)
 	__access_func(f31)
 
 
-#ifdef CONFIG_RISCV_MISALIGNED
+#ifdef CONFIG_RISCV_SCALAR_MISALIGNED
 
 /*
  * Disable compressed instructions set to keep a constant offset between FP
@@ -224,4 +224,4 @@ SYM_FUNC_START(get_f64_reg)
 	fp_access_epilogue
 SYM_FUNC_END(get_f64_reg)
 
-#endif /* CONFIG_RISCV_MISALIGNED */
+#endif /* CONFIG_RISCV_SCALAR_MISALIGNED */

From d1703dc7bc8ec7adb91f5ceaf1556ff1ed212858 Mon Sep 17 00:00:00 2001
From: Jesse Taube <jesse@rivosinc.com>
Date: Thu, 17 Oct 2024 12:00:21 -0700
Subject: [PATCH 0500/1530] RISC-V: Detect unaligned vector accesses supported

Run an unaligned vector access to test if the system supports
vector unaligned access. Add the result to a new key in hwprobe.
This is useful for usermode to know if vector misaligned accesses are
supported and if they are faster or slower than equivalent byte accesses.

Signed-off-by: Jesse Taube <jesse@rivosinc.com>
Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20241017-jesse_unaligned_vector-v10-4-5b33500160f8@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig                         |  36 ++++++
 arch/riscv/include/asm/cpufeature.h        |   8 +-
 arch/riscv/include/asm/entry-common.h      |  11 --
 arch/riscv/include/asm/hwprobe.h           |   2 +-
 arch/riscv/include/asm/vector.h            |   2 +
 arch/riscv/include/uapi/asm/hwprobe.h      |   5 +
 arch/riscv/kernel/Makefile                 |   4 +-
 arch/riscv/kernel/sys_hwprobe.c            |  35 ++++++
 arch/riscv/kernel/traps_misaligned.c       | 125 ++++++++++++++++++++-
 arch/riscv/kernel/unaligned_access_speed.c |  22 ++--
 arch/riscv/kernel/vector.c                 |   2 +-
 11 files changed, 222 insertions(+), 30 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index fab7c6bc17298..05f698a889777 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -784,12 +784,26 @@ config THREAD_SIZE_ORDER
 	  Specify the Pages of thread stack size (from 4KB to 64KB), which also
 	  affects irq stack size, which is equal to thread stack size.
 
+config RISCV_MISALIGNED
+	bool
+	help
+	  Embed support for detecting and emulating misaligned
+	  scalar or vector loads and stores.
+
 config RISCV_SCALAR_MISALIGNED
 	bool
+	select RISCV_MISALIGNED
 	select SYSCTL_ARCH_UNALIGN_ALLOW
 	help
 	  Embed support for emulating misaligned loads and stores.
 
+config RISCV_VECTOR_MISALIGNED
+	bool
+	select RISCV_MISALIGNED
+	depends on RISCV_ISA_V
+	help
+	  Enable detecting support for vector misaligned loads and stores.
+
 choice
 	prompt "Unaligned Accesses Support"
 	default RISCV_PROBE_UNALIGNED_ACCESS
@@ -841,6 +855,28 @@ config RISCV_EFFICIENT_UNALIGNED_ACCESS
 
 endchoice
 
+choice
+	prompt "Vector unaligned Accesses Support"
+	depends on RISCV_ISA_V
+	default RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
+	help
+	  This determines the level of support for vector unaligned accesses. This
+	  information is used by the kernel to perform optimizations. It is also
+	  exposed to user space via the hwprobe syscall. The hardware will be
+	  probed at boot by default.
+
+config RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
+	bool "Probe speed of vector unaligned accesses"
+	select RISCV_VECTOR_MISALIGNED
+	depends on RISCV_ISA_V
+	help
+	  During boot, the kernel will run a series of tests to determine the
+	  speed of vector unaligned accesses if they are supported. This probing
+	  will dynamically determine the speed of vector unaligned accesses on
+	  the underlying system if they are supported.
+
+endchoice
+
 source "arch/riscv/Kconfig.vendor"
 
 endmenu # "Platform type"
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index ccc6cf141c20e..85bf1bce51e65 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -59,8 +59,8 @@ void riscv_user_isa_enable(void);
 #define __RISCV_ISA_EXT_SUPERSET_VALIDATE(_name, _id, _sub_exts, _validate) \
 	_RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), _validate)
 
-#if defined(CONFIG_RISCV_SCALAR_MISALIGNED)
 bool check_unaligned_access_emulated_all_cpus(void);
+#if defined(CONFIG_RISCV_SCALAR_MISALIGNED)
 void check_unaligned_access_emulated(struct work_struct *work __always_unused);
 void unaligned_emulation_finish(void);
 bool unaligned_ctl_available(void);
@@ -72,6 +72,12 @@ static inline bool unaligned_ctl_available(void)
 }
 #endif
 
+bool check_vector_unaligned_access_emulated_all_cpus(void);
+#if defined(CONFIG_RISCV_VECTOR_MISALIGNED)
+void check_vector_unaligned_access_emulated(struct work_struct *work __always_unused);
+DECLARE_PER_CPU(long, vector_misaligned_access);
+#endif
+
 #if defined(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)
 DECLARE_STATIC_KEY_FALSE(fast_unaligned_access_speed_key);
 
diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h
index 0a4e3544c877a..7b32d2b08bb66 100644
--- a/arch/riscv/include/asm/entry-common.h
+++ b/arch/riscv/include/asm/entry-common.h
@@ -25,18 +25,7 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 void handle_page_fault(struct pt_regs *regs);
 void handle_break(struct pt_regs *regs);
 
-#ifdef CONFIG_RISCV_SCALAR_MISALIGNED
 int handle_misaligned_load(struct pt_regs *regs);
 int handle_misaligned_store(struct pt_regs *regs);
-#else
-static inline int handle_misaligned_load(struct pt_regs *regs)
-{
-	return -1;
-}
-static inline int handle_misaligned_store(struct pt_regs *regs)
-{
-	return -1;
-}
-#endif
 
 #endif /* _ASM_RISCV_ENTRY_COMMON_H */
diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h
index ffb9484531af7..1ce1df6d0ff3c 100644
--- a/arch/riscv/include/asm/hwprobe.h
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -8,7 +8,7 @@
 
 #include <uapi/asm/hwprobe.h>
 
-#define RISCV_HWPROBE_MAX_KEY 9
+#define RISCV_HWPROBE_MAX_KEY 10
 
 static inline bool riscv_hwprobe_key_is_valid(__s64 key)
 {
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index be7d309cca8a7..c7c023afbacd7 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -21,6 +21,7 @@
 
 extern unsigned long riscv_v_vsize;
 int riscv_v_setup_vsize(void);
+bool insn_is_vector(u32 insn_buf);
 bool riscv_v_first_use_handler(struct pt_regs *regs);
 void kernel_vector_begin(void);
 void kernel_vector_end(void);
@@ -268,6 +269,7 @@ struct pt_regs;
 
 static inline int riscv_v_setup_vsize(void) { return -EOPNOTSUPP; }
 static __always_inline bool has_vector(void) { return false; }
+static __always_inline bool insn_is_vector(u32 insn_buf) { return false; }
 static inline bool riscv_v_first_use_handler(struct pt_regs *regs) { return false; }
 static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; }
 static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; }
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 1e153cda57db8..34c88c15322c5 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -88,6 +88,11 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW		2
 #define		RISCV_HWPROBE_MISALIGNED_SCALAR_FAST		3
 #define		RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED	4
+#define RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF	10
+#define		RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN		0
+#define		RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW		2
+#define		RISCV_HWPROBE_MISALIGNED_VECTOR_FAST		3
+#define		RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED	4
 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
 
 /* Flags */
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 45624c5ea86c6..7f88cc4931f5c 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -68,8 +68,8 @@ obj-y	+= probes/
 obj-y	+= tests/
 obj-$(CONFIG_MMU) += vdso.o vdso/
 
-obj-$(CONFIG_RISCV_SCALAR_MISALIGNED)	+= traps_misaligned.o
-obj-$(CONFIG_RISCV_SCALAR_MISALIGNED)	+= unaligned_access_speed.o
+obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
+obj-$(CONFIG_RISCV_MISALIGNED)	+= unaligned_access_speed.o
 obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)	+= copy-unaligned.o
 
 obj-$(CONFIG_FPU)		+= fpu.o
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index cea0ca2bf2a25..6441baada36bc 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -201,6 +201,37 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus)
 }
 #endif
 
+#ifdef CONFIG_RISCV_VECTOR_MISALIGNED
+static u64 hwprobe_vec_misaligned(const struct cpumask *cpus)
+{
+	int cpu;
+	u64 perf = -1ULL;
+
+	/* Return if supported or not even if speed wasn't probed */
+	for_each_cpu(cpu, cpus) {
+		int this_perf = per_cpu(vector_misaligned_access, cpu);
+
+		if (perf == -1ULL)
+			perf = this_perf;
+
+		if (perf != this_perf) {
+			perf = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN;
+			break;
+		}
+	}
+
+	if (perf == -1ULL)
+		return RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN;
+
+	return perf;
+}
+#else
+static u64 hwprobe_vec_misaligned(const struct cpumask *cpus)
+{
+	return RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN;
+}
+#endif
+
 static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 			     const struct cpumask *cpus)
 {
@@ -229,6 +260,10 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 		pair->value = hwprobe_misaligned(cpus);
 		break;
 
+	case RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF:
+		pair->value = hwprobe_vec_misaligned(cpus);
+		break;
+
 	case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE:
 		pair->value = 0;
 		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index d076dde5ad204..ef59ecfc64cb5 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -16,6 +16,7 @@
 #include <asm/entry-common.h>
 #include <asm/hwprobe.h>
 #include <asm/cpufeature.h>
+#include <asm/vector.h>
 
 #define INSN_MATCH_LB			0x3
 #define INSN_MASK_LB			0x707f
@@ -322,12 +323,37 @@ union reg_data {
 	u64 data_u64;
 };
 
-static bool unaligned_ctl __read_mostly;
-
 /* sysctl hooks */
 int unaligned_enabled __read_mostly = 1;	/* Enabled by default */
 
-int handle_misaligned_load(struct pt_regs *regs)
+#ifdef CONFIG_RISCV_VECTOR_MISALIGNED
+static int handle_vector_misaligned_load(struct pt_regs *regs)
+{
+	unsigned long epc = regs->epc;
+	unsigned long insn;
+
+	if (get_insn(regs, epc, &insn))
+		return -1;
+
+	/* Only return 0 when in check_vector_unaligned_access_emulated */
+	if (*this_cpu_ptr(&vector_misaligned_access) == RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) {
+		*this_cpu_ptr(&vector_misaligned_access) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED;
+		regs->epc = epc + INSN_LEN(insn);
+		return 0;
+	}
+
+	/* If vector instruction we don't emulate it yet */
+	regs->epc = epc;
+	return -1;
+}
+#else
+static int handle_vector_misaligned_load(struct pt_regs *regs)
+{
+	return -1;
+}
+#endif
+
+static int handle_scalar_misaligned_load(struct pt_regs *regs)
 {
 	union reg_data val;
 	unsigned long epc = regs->epc;
@@ -435,7 +461,7 @@ int handle_misaligned_load(struct pt_regs *regs)
 	return 0;
 }
 
-int handle_misaligned_store(struct pt_regs *regs)
+static int handle_scalar_misaligned_store(struct pt_regs *regs)
 {
 	union reg_data val;
 	unsigned long epc = regs->epc;
@@ -526,6 +552,91 @@ int handle_misaligned_store(struct pt_regs *regs)
 	return 0;
 }
 
+int handle_misaligned_load(struct pt_regs *regs)
+{
+	unsigned long epc = regs->epc;
+	unsigned long insn;
+
+	if (IS_ENABLED(CONFIG_RISCV_VECTOR_MISALIGNED)) {
+		if (get_insn(regs, epc, &insn))
+			return -1;
+
+		if (insn_is_vector(insn))
+			return handle_vector_misaligned_load(regs);
+	}
+
+	if (IS_ENABLED(CONFIG_RISCV_SCALAR_MISALIGNED))
+		return handle_scalar_misaligned_load(regs);
+
+	return -1;
+}
+
+int handle_misaligned_store(struct pt_regs *regs)
+{
+	if (IS_ENABLED(CONFIG_RISCV_SCALAR_MISALIGNED))
+		return handle_scalar_misaligned_store(regs);
+
+	return -1;
+}
+
+#ifdef CONFIG_RISCV_VECTOR_MISALIGNED
+void check_vector_unaligned_access_emulated(struct work_struct *work __always_unused)
+{
+	long *mas_ptr = this_cpu_ptr(&vector_misaligned_access);
+	unsigned long tmp_var;
+
+	*mas_ptr = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN;
+
+	kernel_vector_begin();
+	/*
+	 * In pre-13.0.0 versions of GCC, vector registers cannot appear in
+	 * the clobber list. This inline asm clobbers v0, but since we do not
+	 * currently build the kernel with V enabled, the v0 clobber arg is not
+	 * needed (as the compiler will not emit vector code itself). If the kernel
+	 * is changed to build with V enabled, the clobber arg will need to be
+	 * added here.
+	 */
+	__asm__ __volatile__ (
+		".balign 4\n\t"
+		".option push\n\t"
+		".option arch, +zve32x\n\t"
+		"       vsetivli zero, 1, e16, m1, ta, ma\n\t"	// Vectors of 16b
+		"       vle16.v v0, (%[ptr])\n\t"		// Load bytes
+		".option pop\n\t"
+		: : [ptr] "r" ((u8 *)&tmp_var + 1));
+	kernel_vector_end();
+}
+
+bool check_vector_unaligned_access_emulated_all_cpus(void)
+{
+	int cpu;
+
+	if (!has_vector()) {
+		for_each_online_cpu(cpu)
+			per_cpu(vector_misaligned_access, cpu) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED;
+		return false;
+	}
+
+	schedule_on_each_cpu(check_vector_unaligned_access_emulated);
+
+	for_each_online_cpu(cpu)
+		if (per_cpu(vector_misaligned_access, cpu)
+		    == RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN)
+			return false;
+
+	return true;
+}
+#else
+bool check_vector_unaligned_access_emulated_all_cpus(void)
+{
+	return false;
+}
+#endif
+
+#ifdef CONFIG_RISCV_SCALAR_MISALIGNED
+
+static bool unaligned_ctl __read_mostly;
+
 void check_unaligned_access_emulated(struct work_struct *work __always_unused)
 {
 	int cpu = smp_processor_id();
@@ -574,3 +685,9 @@ bool unaligned_ctl_available(void)
 {
 	return unaligned_ctl;
 }
+#else
+bool check_unaligned_access_emulated_all_cpus(void)
+{
+	return false;
+}
+#endif
diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c
index f3508cc54f91a..0b8b5e17453a8 100644
--- a/arch/riscv/kernel/unaligned_access_speed.c
+++ b/arch/riscv/kernel/unaligned_access_speed.c
@@ -19,7 +19,8 @@
 #define MISALIGNED_BUFFER_ORDER get_order(MISALIGNED_BUFFER_SIZE)
 #define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80)
 
-DEFINE_PER_CPU(long, misaligned_access_speed);
+DEFINE_PER_CPU(long, misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN;
+DEFINE_PER_CPU(long, vector_misaligned_access) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED;
 
 #ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS
 static cpumask_t fast_misaligned_access;
@@ -260,23 +261,24 @@ static int check_unaligned_access_speed_all_cpus(void)
 	kfree(bufs);
 	return 0;
 }
+#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */
+static int check_unaligned_access_speed_all_cpus(void)
+{
+	return 0;
+}
+#endif
 
 static int check_unaligned_access_all_cpus(void)
 {
-	bool all_cpus_emulated = check_unaligned_access_emulated_all_cpus();
+	bool all_cpus_emulated;
+
+	all_cpus_emulated = check_unaligned_access_emulated_all_cpus();
+	check_vector_unaligned_access_emulated_all_cpus();
 
 	if (!all_cpus_emulated)
 		return check_unaligned_access_speed_all_cpus();
 
 	return 0;
 }
-#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */
-static int check_unaligned_access_all_cpus(void)
-{
-	check_unaligned_access_emulated_all_cpus();
-
-	return 0;
-}
-#endif
 
 arch_initcall(check_unaligned_access_all_cpus);
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 682b3feee4511..821818886fab0 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -66,7 +66,7 @@ void __init riscv_v_setup_ctx_cache(void)
 #endif
 }
 
-static bool insn_is_vector(u32 insn_buf)
+bool insn_is_vector(u32 insn_buf)
 {
 	u32 opcode = insn_buf & __INSN_OPCODE_MASK;
 	u32 width, csr;

From e7c9d66e313bc0f7cb185c4972c3c9383a0da70f Mon Sep 17 00:00:00 2001
From: Jesse Taube <jesse@rivosinc.com>
Date: Thu, 17 Oct 2024 12:00:22 -0700
Subject: [PATCH 0501/1530] RISC-V: Report vector unaligned access speed
 hwprobe

Detect if vector misaligned accesses are faster or slower than
equivalent vector byte accesses. This is useful for usermode to know
whether vector byte accesses or vector misaligned accesses have a better
bandwidth for operations like memcpy.

Signed-off-by: Jesse Taube <jesse@rivosinc.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20241017-jesse_unaligned_vector-v10-5-5b33500160f8@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig                         |  18 +++
 arch/riscv/kernel/Makefile                 |   3 +-
 arch/riscv/kernel/copy-unaligned.h         |   5 +
 arch/riscv/kernel/sys_hwprobe.c            |   6 +
 arch/riscv/kernel/unaligned_access_speed.c | 141 ++++++++++++++++++++-
 arch/riscv/kernel/vec-copy-unaligned.S     |  58 +++++++++
 6 files changed, 228 insertions(+), 3 deletions(-)
 create mode 100644 arch/riscv/kernel/vec-copy-unaligned.S

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 05f698a889777..d46394873afce 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -875,6 +875,24 @@ config RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
 	  will dynamically determine the speed of vector unaligned accesses on
 	  the underlying system if they are supported.
 
+config RISCV_SLOW_VECTOR_UNALIGNED_ACCESS
+	bool "Assume the system supports slow vector unaligned memory accesses"
+	depends on NONPORTABLE
+	help
+	  Assume that the system supports slow vector unaligned memory accesses. The
+	  kernel and userspace programs may not be able to run at all on systems
+	  that do not support unaligned memory accesses.
+
+config RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS
+	bool "Assume the system supports fast vector unaligned memory accesses"
+	depends on NONPORTABLE
+	help
+	  Assume that the system supports fast vector unaligned memory accesses. When
+	  enabled, this option improves the performance of the kernel on such
+	  systems. However, the kernel and userspace programs will run much more
+	  slowly, or will not be able to run at all, on systems that do not
+	  support efficient unaligned memory accesses.
+
 endchoice
 
 source "arch/riscv/Kconfig.vendor"
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 7f88cc4931f5c..30db92672ada5 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -70,7 +70,8 @@ obj-$(CONFIG_MMU) += vdso.o vdso/
 
 obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
 obj-$(CONFIG_RISCV_MISALIGNED)	+= unaligned_access_speed.o
-obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)	+= copy-unaligned.o
+obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)		+= copy-unaligned.o
+obj-$(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)	+= vec-copy-unaligned.o
 
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_FPU)		+= kernel_mode_fpu.o
diff --git a/arch/riscv/kernel/copy-unaligned.h b/arch/riscv/kernel/copy-unaligned.h
index e3d70d35b7081..85d4d11450cb6 100644
--- a/arch/riscv/kernel/copy-unaligned.h
+++ b/arch/riscv/kernel/copy-unaligned.h
@@ -10,4 +10,9 @@
 void __riscv_copy_words_unaligned(void *dst, const void *src, size_t size);
 void __riscv_copy_bytes_unaligned(void *dst, const void *src, size_t size);
 
+#ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
+void __riscv_copy_vec_words_unaligned(void *dst, const void *src, size_t size);
+void __riscv_copy_vec_bytes_unaligned(void *dst, const void *src, size_t size);
+#endif
+
 #endif /* __RISCV_KERNEL_COPY_UNALIGNED_H */
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index 6441baada36bc..6673278e84d58 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -228,6 +228,12 @@ static u64 hwprobe_vec_misaligned(const struct cpumask *cpus)
 #else
 static u64 hwprobe_vec_misaligned(const struct cpumask *cpus)
 {
+	if (IS_ENABLED(CONFIG_RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS))
+		return RISCV_HWPROBE_MISALIGNED_VECTOR_FAST;
+
+	if (IS_ENABLED(CONFIG_RISCV_SLOW_VECTOR_UNALIGNED_ACCESS))
+		return RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW;
+
 	return RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN;
 }
 #endif
diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c
index 0b8b5e17453a8..91f189cf16113 100644
--- a/arch/riscv/kernel/unaligned_access_speed.c
+++ b/arch/riscv/kernel/unaligned_access_speed.c
@@ -6,11 +6,13 @@
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/jump_label.h>
+#include <linux/kthread.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/types.h>
 #include <asm/cpufeature.h>
 #include <asm/hwprobe.h>
+#include <asm/vector.h>
 
 #include "copy-unaligned.h"
 
@@ -268,12 +270,147 @@ static int check_unaligned_access_speed_all_cpus(void)
 }
 #endif
 
+#ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
+static void check_vector_unaligned_access(struct work_struct *work __always_unused)
+{
+	int cpu = smp_processor_id();
+	u64 start_cycles, end_cycles;
+	u64 word_cycles;
+	u64 byte_cycles;
+	int ratio;
+	unsigned long start_jiffies, now;
+	struct page *page;
+	void *dst;
+	void *src;
+	long speed = RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW;
+
+	if (per_cpu(vector_misaligned_access, cpu) != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN)
+		return;
+
+	page = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
+	if (!page) {
+		pr_warn("Allocation failure, not measuring vector misaligned performance\n");
+		return;
+	}
+
+	/* Make an unaligned destination buffer. */
+	dst = (void *)((unsigned long)page_address(page) | 0x1);
+	/* Unalign src as well, but differently (off by 1 + 2 = 3). */
+	src = dst + (MISALIGNED_BUFFER_SIZE / 2);
+	src += 2;
+	word_cycles = -1ULL;
+
+	/* Do a warmup. */
+	kernel_vector_begin();
+	__riscv_copy_vec_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+
+	start_jiffies = jiffies;
+	while ((now = jiffies) == start_jiffies)
+		cpu_relax();
+
+	/*
+	 * For a fixed amount of time, repeatedly try the function, and take
+	 * the best time in cycles as the measurement.
+	 */
+	while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) {
+		start_cycles = get_cycles64();
+		/* Ensure the CSR read can't reorder WRT to the copy. */
+		mb();
+		__riscv_copy_vec_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+		/* Ensure the copy ends before the end time is snapped. */
+		mb();
+		end_cycles = get_cycles64();
+		if ((end_cycles - start_cycles) < word_cycles)
+			word_cycles = end_cycles - start_cycles;
+	}
+
+	byte_cycles = -1ULL;
+	__riscv_copy_vec_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+	start_jiffies = jiffies;
+	while ((now = jiffies) == start_jiffies)
+		cpu_relax();
+
+	while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) {
+		start_cycles = get_cycles64();
+		/* Ensure the CSR read can't reorder WRT to the copy. */
+		mb();
+		__riscv_copy_vec_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+		/* Ensure the copy ends before the end time is snapped. */
+		mb();
+		end_cycles = get_cycles64();
+		if ((end_cycles - start_cycles) < byte_cycles)
+			byte_cycles = end_cycles - start_cycles;
+	}
+
+	kernel_vector_end();
+
+	/* Don't divide by zero. */
+	if (!word_cycles || !byte_cycles) {
+		pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned vector access speed\n",
+			cpu);
+
+		return;
+	}
+
+	if (word_cycles < byte_cycles)
+		speed = RISCV_HWPROBE_MISALIGNED_VECTOR_FAST;
+
+	ratio = div_u64((byte_cycles * 100), word_cycles);
+	pr_info("cpu%d: Ratio of vector byte access time to vector unaligned word access is %d.%02d, unaligned accesses are %s\n",
+		cpu,
+		ratio / 100,
+		ratio % 100,
+		(speed ==  RISCV_HWPROBE_MISALIGNED_VECTOR_FAST) ? "fast" : "slow");
+
+	per_cpu(vector_misaligned_access, cpu) = speed;
+}
+
+static int riscv_online_cpu_vec(unsigned int cpu)
+{
+	if (!has_vector())
+		return 0;
+
+	if (per_cpu(vector_misaligned_access, cpu) != RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED)
+		return 0;
+
+	check_vector_unaligned_access_emulated(NULL);
+	check_vector_unaligned_access(NULL);
+	return 0;
+}
+
+/* Measure unaligned access speed on all CPUs present at boot in parallel. */
+static int vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
+{
+	schedule_on_each_cpu(check_vector_unaligned_access);
+
+	/*
+	 * Setup hotplug callbacks for any new CPUs that come online or go
+	 * offline.
+	 */
+	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
+				  riscv_online_cpu_vec, NULL);
+
+	return 0;
+}
+#else /* CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS */
+static int vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
+{
+	return 0;
+}
+#endif
+
 static int check_unaligned_access_all_cpus(void)
 {
-	bool all_cpus_emulated;
+	bool all_cpus_emulated, all_cpus_vec_unsupported;
 
 	all_cpus_emulated = check_unaligned_access_emulated_all_cpus();
-	check_vector_unaligned_access_emulated_all_cpus();
+	all_cpus_vec_unsupported = check_vector_unaligned_access_emulated_all_cpus();
+
+	if (!all_cpus_vec_unsupported &&
+	    IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) {
+		kthread_run(vec_check_unaligned_access_speed_all_cpus,
+			    NULL, "vec_check_unaligned_access_speed_all_cpus");
+	}
 
 	if (!all_cpus_emulated)
 		return check_unaligned_access_speed_all_cpus();
diff --git a/arch/riscv/kernel/vec-copy-unaligned.S b/arch/riscv/kernel/vec-copy-unaligned.S
new file mode 100644
index 0000000000000..d16f19f1b3b65
--- /dev/null
+++ b/arch/riscv/kernel/vec-copy-unaligned.S
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2024 Rivos Inc. */
+
+#include <linux/args.h>
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+	.text
+
+#define WORD_EEW 32
+
+#define WORD_SEW CONCATENATE(e, WORD_EEW)
+#define VEC_L CONCATENATE(vle, WORD_EEW).v
+#define VEC_S CONCATENATE(vle, WORD_EEW).v
+
+/* void __riscv_copy_vec_words_unaligned(void *, const void *, size_t) */
+/* Performs a memcpy without aligning buffers, using word loads and stores. */
+/* Note: The size is truncated to a multiple of WORD_EEW */
+SYM_FUNC_START(__riscv_copy_vec_words_unaligned)
+	andi  a4, a2, ~(WORD_EEW-1)
+	beqz  a4, 2f
+	add   a3, a1, a4
+	.option push
+	.option arch, +zve32x
+1:
+	vsetivli t0, 8, WORD_SEW, m8, ta, ma
+	VEC_L v0, (a1)
+	VEC_S v0, (a0)
+	addi  a0, a0, WORD_EEW
+	addi  a1, a1, WORD_EEW
+	bltu  a1, a3, 1b
+
+2:
+	.option pop
+	ret
+SYM_FUNC_END(__riscv_copy_vec_words_unaligned)
+
+/* void __riscv_copy_vec_bytes_unaligned(void *, const void *, size_t) */
+/* Performs a memcpy without aligning buffers, using only byte accesses. */
+/* Note: The size is truncated to a multiple of 8 */
+SYM_FUNC_START(__riscv_copy_vec_bytes_unaligned)
+	andi a4, a2, ~(8-1)
+	beqz a4, 2f
+	add  a3, a1, a4
+	.option push
+	.option arch, +zve32x
+1:
+	vsetivli t0, 8, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vse8.v v0, (a0)
+	addi a0, a0, 8
+	addi a1, a1, 8
+	bltu a1, a3, 1b
+
+2:
+	.option pop
+	ret
+SYM_FUNC_END(__riscv_copy_vec_bytes_unaligned)

From 40e09ebd791fe6b872df49c4ae859451977e1e64 Mon Sep 17 00:00:00 2001
From: Jesse Taube <jesse@rivosinc.com>
Date: Thu, 17 Oct 2024 12:00:23 -0700
Subject: [PATCH 0502/1530] RISC-V: hwprobe: Document unaligned vector perf key

Document key for reporting the speed of unaligned vector accesses.
The descriptions are the same as the scalar equivalent values.

Signed-off-by: Jesse Taube <jesse@rivosinc.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20241017-jesse_unaligned_vector-v10-6-5b33500160f8@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/hwprobe.rst | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 85b709257918a..ea4e0b9c73e74 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -274,3 +274,19 @@ The following keys are defined:
   represent the highest userspace virtual address usable.
 
 * :c:macro:`RISCV_HWPROBE_KEY_TIME_CSR_FREQ`: Frequency (in Hz) of `time CSR`.
+
+* :c:macro:`RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF`: An enum value describing the
+     performance of misaligned vector accesses on the selected set of processors.
+
+  * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN`: The performance of misaligned
+    vector accesses is unknown.
+
+  * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW`: 32-bit misaligned accesses using vector
+    registers are slower than the equivalent quantity of byte accesses via vector registers.
+    Misaligned accesses may be supported directly in hardware, or trapped and emulated by software.
+
+  * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_FAST`: 32-bit misaligned accesses using vector
+    registers are faster than the equivalent quantity of byte accesses via vector registers.
+
+  * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED`: Misaligned vector accesses are
+    not supported at all and will generate a misaligned address fault.

From 5b036cada481a7a3bf30d333298f6d83dfb19bed Mon Sep 17 00:00:00 2001
From: Guilherme Giacomo Simoes <trintaeoitogc@gmail.com>
Date: Mon, 14 Oct 2024 10:19:17 -0300
Subject: [PATCH 0503/1530] PCI: cpcihp: Remove unused struct
 cpci_hp_controller_ops.hardware_test

The 'hardware_test' field in struct cpci_hp_controller_ops is unused;
remove it to reduce resource consumption.

Link: https://lore.kernel.org/r/20241014131917.324667-1-trintaeoitogc@gmail.com
Signed-off-by: Guilherme Giacomo Simoes <trintaeoitogc@gmail.com>
[bhelgas: commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/cpci_hotplug.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pci/hotplug/cpci_hotplug.h b/drivers/pci/hotplug/cpci_hotplug.h
index 6d8970d8c3f29..03fa39ab0c884 100644
--- a/drivers/pci/hotplug/cpci_hotplug.h
+++ b/drivers/pci/hotplug/cpci_hotplug.h
@@ -44,7 +44,6 @@ struct cpci_hp_controller_ops {
 	int (*enable_irq)(void);
 	int (*disable_irq)(void);
 	int (*check_irq)(void *dev_id);
-	int (*hardware_test)(struct slot *slot, u32 value);
 	u8  (*get_power)(struct slot *slot);
 	int (*set_power)(struct slot *slot, int value);
 };

From 91a6296793591983f27db40f41daab53500ffc6e Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 12 Oct 2024 21:53:42 +0200
Subject: [PATCH 0504/1530] PCI: cpqphp: Remove unused struct ctrl_dbg.ctrl

'ctrl' is unused; remove it to save a few bytes when the structure is
allocated.

Link: https://lore.kernel.org/r/551d0cdaabcf69fcd09a565475c428e09c61e1a3.1728762751.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/cpqphp_sysfs.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pci/hotplug/cpqphp_sysfs.c b/drivers/pci/hotplug/cpqphp_sysfs.c
index fed1360ee9b18..6143ebf71f211 100644
--- a/drivers/pci/hotplug/cpqphp_sysfs.c
+++ b/drivers/pci/hotplug/cpqphp_sysfs.c
@@ -123,7 +123,6 @@ static int spew_debug_info(struct controller *ctrl, char *data, int size)
 struct ctrl_dbg {
 	int size;
 	char *data;
-	struct controller *ctrl;
 };
 
 #define MAX_OUTPUT	(4*PAGE_SIZE)

From 19f73e938df2b8edfa2e93e0280bd26fd4df5b92 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Thu, 17 Oct 2024 12:55:45 +0300
Subject: [PATCH 0505/1530] PCI: Improve pdev_sort_resources() warning message
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use pci_resource_name() helper in pdev_sort_resources() to print resources
in user-friendly format. Also replace the vague "bogus alignment" with a
more precise explanation of the problem.

Link: https://lore.kernel.org/r/20241017095545.1424-1-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Philipp Stanner <pstanner@redhat.com>
---
 drivers/pci/setup-bus.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 27da27c59e899..5e00cecf1f1af 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -134,6 +134,7 @@ static void pdev_sort_resources(struct pci_dev *dev, struct list_head *head)
 	int i;
 
 	pci_dev_for_each_resource(dev, r, i) {
+		const char *r_name = pci_resource_name(dev, i);
 		struct pci_dev_resource *dev_res, *tmp;
 		resource_size_t r_align;
 		struct list_head *n;
@@ -146,8 +147,8 @@ static void pdev_sort_resources(struct pci_dev *dev, struct list_head *head)
 
 		r_align = pci_resource_alignment(dev, r);
 		if (!r_align) {
-			pci_warn(dev, "BAR %d: %pR has bogus alignment\n",
-				 i, r);
+			pci_warn(dev, "%s %pR: alignment must not be zero\n",
+				 r_name, r);
 			continue;
 		}
 

From e2cb1db7daf8b7863aeec07bb574d3fae54518e6 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 18 Oct 2024 13:43:06 -0700
Subject: [PATCH 0506/1530] perf test: Update all metrics test like
 metricgroups test

Like in the metricgroup tests, it should check the permission first and
then skip relevant failures accordingly.

Also it needs to try again with the system wide flag properly.  On the
second round, check if the result has the metric name because other
failure cases are checked in the first round already.

Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20241018204306.741972-1-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/stat_all_metrics.sh | 87 ++++++++++++++++------
 1 file changed, 66 insertions(+), 21 deletions(-)

diff --git a/tools/perf/tests/shell/stat_all_metrics.sh b/tools/perf/tests/shell/stat_all_metrics.sh
index 54774525e18a7..73e9347e88a96 100755
--- a/tools/perf/tests/shell/stat_all_metrics.sh
+++ b/tools/perf/tests/shell/stat_all_metrics.sh
@@ -2,42 +2,87 @@
 # perf all metrics test
 # SPDX-License-Identifier: GPL-2.0
 
+ParanoidAndNotRoot()
+{
+  [ "$(id -u)" != 0 ] && [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt $1 ]
+}
+
+system_wide_flag="-a"
+if ParanoidAndNotRoot 0
+then
+  system_wide_flag=""
+fi
+
 err=0
 for m in $(perf list --raw-dump metrics); do
   echo "Testing $m"
-  result=$(perf stat -M "$m" true 2>&1)
-  if [[ "$result" =~ ${m:0:50} ]] || [[ "$result" =~ "<not supported>" ]]
+  result=$(perf stat -M "$m" $system_wide_flag -- sleep 0.01 2>&1)
+  result_err=$?
+  if [[ $result_err -gt 0 ]]
   then
-    continue
+    if [[ "$result" =~ \
+          "Access to performance monitoring and observability operations is limited" ]]
+    then
+      echo "Permission failure"
+      echo $result
+      if [[ $err -eq 0 ]]
+      then
+        err=2 # Skip
+      fi
+      continue
+    elif [[ "$result" =~ "in per-thread mode, enable system wide" ]]
+    then
+      echo "Permissions - need system wide mode"
+      echo $result
+      if [[ $err -eq 0 ]]
+      then
+        err=2 # Skip
+      fi
+      continue
+    elif [[ "$result" =~ "<not supported>" ]]
+    then
+      echo "Not supported events"
+      echo $result
+      if [[ $err -eq 0 ]]
+      then
+        err=2 # Skip
+      fi
+      continue
+    elif [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]]
+    then
+      echo "FP issues"
+      echo $result
+      if [[ $err -eq 0 ]]
+      then
+        err=2 # Skip
+      fi
+      continue
+    elif [[ "$result" =~ "PMM" ]]
+    then
+      echo "Optane memory issues"
+      echo $result
+      if [[ $err -eq 0 ]]
+      then
+        err=2 # Skip
+      fi
+      continue
+    fi
   fi
-  # Failed so try system wide.
-  result=$(perf stat -M "$m" -a sleep 0.01 2>&1)
+
   if [[ "$result" =~ ${m:0:50} ]]
   then
     continue
   fi
-  # Failed again, possibly the workload was too small so retry with something
-  # longer.
-  result=$(perf stat -M "$m" perf bench internals synthesize 2>&1)
+
+  # Failed, possibly the workload was too small so retry with something longer.
+  result=$(perf stat -M "$m" $system_wide_flag -- perf bench internals synthesize 2>&1)
   if [[ "$result" =~ ${m:0:50} ]]
   then
     continue
   fi
   echo "Metric '$m' not printed in:"
   echo "$result"
-  if [[ "$err" != "1" ]]
-  then
-    err=2
-    if [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]]
-    then
-      echo "Skip, not fail, for FP issues"
-    elif [[ "$result" =~ "PMM" ]]
-    then
-      echo "Skip, not fail, for Optane memory issues"
-    else
-      err=1
-    fi
-  fi
+  err=1
 done
 
 exit "$err"

From 21677f653f1a6b9a3796d3ed7406722d289ef781 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Fri, 18 Oct 2024 10:17:32 +0200
Subject: [PATCH 0507/1530] perf test: Fix perf test case 84 on s390

Perf test case 84 'perf pipe recording and injection test'
sometime fails on s390, especially on z/VM virtual machines.

This is caused by a very short run time of workload

  # perf test -w noploop

which runs for 1 second. Occasionally this is not long
enough and the perf report has no samples for symbol noploop.

Fix this and enlarge the runtime for the perf work load
to 3 seconds. This ensures the symbol noploop is always
present. Since only s390 is affected, make this loop
architecture dependend.

Output before:
 Inject -b build-ids test
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.195 MB - ]
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.277 MB - ]
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.195 MB - ]
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.160 MB
			 /tmp/perf.data.ELzRdq (4031 samples) ]
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.195 MB - ]
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.195 MB - ]
 Inject -b build-ids test [Success]

 Inject --buildid-all build-ids test
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.195 MB - ]
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.014 MB - ]
 Inject --buildid-all build-ids test [Failed - cannot find
				noploop function in pipe #2]

Output after:
Successful execution for over 10 times in a loop.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Suggested-by: Namhyung Kim <namhyung@kernel.org>
Cc: agordeev@linux.ibm.com
Cc: gor@linux.ibm.com
Cc: hca@linux.ibm.com
Link: https://lore.kernel.org/r/20241018081732.1391060-1-tmricht@linux.ibm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/pipe_test.sh | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/tests/shell/pipe_test.sh b/tools/perf/tests/shell/pipe_test.sh
index d4c8005ce9b96..e459aa99a9515 100755
--- a/tools/perf/tests/shell/pipe_test.sh
+++ b/tools/perf/tests/shell/pipe_test.sh
@@ -13,6 +13,7 @@ skip_test_missing_symbol ${sym}
 data=$(mktemp /tmp/perf.data.XXXXXX)
 data2=$(mktemp /tmp/perf.data2.XXXXXX)
 prog="perf test -w noploop"
+[ "$(uname -m)" = "s390x" ] && prog="$prog 3"
 err=0
 
 set -e

From f101a8e345c22a588132fda52055a16ec54e7621 Mon Sep 17 00:00:00 2001
From: Sandipan Das <sandipan.das@amd.com>
Date: Fri, 18 Oct 2024 15:01:03 +0530
Subject: [PATCH 0508/1530] perf vendor events amd: Add Zen 5 data fabric
 events

Add data fabric events taken from Section 2.1.16.2 "Performance
Measurement" in the Processor Programming Reference (PPR) for AMD Family
1Ah Model 02h Revision C1 Processors document available at the link
below.

This constitutes events which capture the flow of data beats at various
links and interfaces in the data fabric.

Link: https://bugzilla.kernel.org/attachment.cgi?id=307010
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: ananth.narayan@amd.com
Cc: ravi.bangoria@amd.com
Cc: eranian@google.com
Link: https://lore.kernel.org/r/198049e27366f3980e4991b95cec5eaac6d31d75.1729242778.git.sandipan.das@amd.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../arch/x86/amdzen5/data-fabric.json         | 1634 +++++++++++++++++
 1 file changed, 1634 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/x86/amdzen5/data-fabric.json

diff --git a/tools/perf/pmu-events/arch/x86/amdzen5/data-fabric.json b/tools/perf/pmu-events/arch/x86/amdzen5/data-fabric.json
new file mode 100644
index 0000000000000..fa06569d881d1
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/amdzen5/data-fabric.json
@@ -0,0 +1,1634 @@
+[
+  {
+    "EventName": "local_or_remote_socket_read_data_beats_dram_0",
+    "PublicDescription": "Read data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 0.",
+    "EventCode": "0x1f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_read_data_beats_dram_1",
+    "PublicDescription": "Read data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 1.",
+    "EventCode": "0x5f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_read_data_beats_dram_2",
+    "PublicDescription": "Read data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 2.",
+    "EventCode": "0x9f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_read_data_beats_dram_3",
+    "PublicDescription": "Read data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 3.",
+    "EventCode": "0xdf",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_read_data_beats_dram_4",
+    "PublicDescription": "Read data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 4.",
+    "EventCode": "0x11f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_read_data_beats_dram_5",
+    "PublicDescription": "Read data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 5.",
+    "EventCode": "0x15f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_read_data_beats_dram_6",
+    "PublicDescription": "Read data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 6.",
+    "EventCode": "0x19f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_read_data_beats_dram_7",
+    "PublicDescription": "Read data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 7.",
+    "EventCode": "0x1df",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_read_data_beats_dram_8",
+    "PublicDescription": "Read data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 8.",
+    "EventCode": "0x21f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_read_data_beats_dram_9",
+    "PublicDescription": "Read data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 9.",
+    "EventCode": "0x25f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_read_data_beats_dram_10",
+    "PublicDescription": "Read data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 10.",
+    "EventCode": "0x29f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_read_data_beats_dram_11",
+    "PublicDescription": "Read data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 11.",
+    "EventCode": "0x2df",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_write_data_beats_dram_0",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local socket and DRAM Channel 0.",
+    "EventCode": "0x1f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_write_data_beats_dram_1",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local socket and DRAM Channel 1.",
+    "EventCode": "0x5f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_write_data_beats_dram_2",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local socket and DRAM Channel 2.",
+    "EventCode": "0x9f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_write_data_beats_dram_3",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local socket and DRAM Channel 3.",
+    "EventCode": "0xdf",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_write_data_beats_dram_4",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local socket and DRAM Channel 4.",
+    "EventCode": "0x11f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_write_data_beats_dram_5",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local socket and DRAM Channel 5.",
+    "EventCode": "0x15f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_write_data_beats_dram_6",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local socket and DRAM Channel 6.",
+    "EventCode": "0x19f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_write_data_beats_dram_7",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local socket and DRAM Channel 7.",
+    "EventCode": "0x1df",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_write_data_beats_dram_8",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local socket and DRAM Channel 8.",
+    "EventCode": "0x21f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_write_data_beats_dram_9",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local socket and DRAM Channel 9.",
+    "EventCode": "0x25f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_write_data_beats_dram_10",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local socket and DRAM Channel 10.",
+    "EventCode": "0x29f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_write_data_beats_dram_11",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local socket and DRAM Channel 11.",
+    "EventCode": "0x2df",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_write_data_beats_dram_0",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between remote socket and DRAM Channel 0.",
+    "EventCode": "0x1f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_write_data_beats_dram_1",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between remote socket and DRAM Channel 1.",
+    "EventCode": "0x5f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_write_data_beats_dram_2",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between remote socket and DRAM Channel 2.",
+    "EventCode": "0x9f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_write_data_beats_dram_3",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between remote socket and DRAM Channel 3.",
+    "EventCode": "0xdf",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_write_data_beats_dram_4",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between remote socket and DRAM Channel 4.",
+    "EventCode": "0x11f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_write_data_beats_dram_5",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between remote socket and DRAM Channel 5.",
+    "EventCode": "0x15f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_write_data_beats_dram_6",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between remote socket and DRAM Channel 6.",
+    "EventCode": "0x19f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_write_data_beats_dram_7",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between remote socket and DRAM Channel 7.",
+    "EventCode": "0x1df",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_write_data_beats_dram_8",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between remote socket and DRAM Channel 8.",
+    "EventCode": "0x21f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_write_data_beats_dram_9",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between remote socket and DRAM Channel 9.",
+    "EventCode": "0x25f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_write_data_beats_dram_10",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between remote socket and DRAM Channel 10.",
+    "EventCode": "0x29f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_write_data_beats_dram_11",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between remote socket and DRAM Channel 11.",
+    "EventCode": "0x2df",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_write_data_beats_dram_0",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 0.",
+    "EventCode": "0x1f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_write_data_beats_dram_1",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 1.",
+    "EventCode": "0x5f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_write_data_beats_dram_2",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 2.",
+    "EventCode": "0x9f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_write_data_beats_dram_3",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 3.",
+    "EventCode": "0xdf",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_write_data_beats_dram_4",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 4.",
+    "EventCode": "0x11f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_write_data_beats_dram_5",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 5.",
+    "EventCode": "0x15f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_write_data_beats_dram_6",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 6.",
+    "EventCode": "0x19f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_write_data_beats_dram_7",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 7.",
+    "EventCode": "0x1df",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_write_data_beats_dram_8",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 8.",
+    "EventCode": "0x21f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_write_data_beats_dram_9",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 9.",
+    "EventCode": "0x25f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_write_data_beats_dram_10",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 10.",
+    "EventCode": "0x29f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_write_data_beats_dram_11",
+    "PublicDescription": "Write data beats (64 bytes) for transactions between local or remote socket and DRAM Channel 11.",
+    "EventCode": "0x2df",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_read_data_beats_io_0",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local socket and IO Root Complex 0.",
+    "EventCode": "0x81f",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_read_data_beats_io_1",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local socket and IO Root Complex 1.",
+    "EventCode": "0x85f",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_read_data_beats_io_2",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local socket and IO Root Complex 2.",
+    "EventCode": "0x89f",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_read_data_beats_io_3",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local socket and IO Root Complex 3.",
+    "EventCode": "0x8df",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_read_data_beats_io_4",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local socket and IO Root Complex 4.",
+    "EventCode": "0x91f",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_read_data_beats_io_5",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local socket and IO Root Complex 5.",
+    "EventCode": "0x95f",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_read_data_beats_io_6",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local socket and IO Root Complex 6.",
+    "EventCode": "0x99f",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_read_data_beats_io_7",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local socket and IO Root Complex 7.",
+    "EventCode": "0x9df",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_write_data_beats_io_0",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local socket and IO Root Complex 0.",
+    "EventCode": "0x81f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_write_data_beats_io_1",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local socket and IO Root Complex 1.",
+    "EventCode": "0x85f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_write_data_beats_io_2",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local socket and IO Root Complex 2.",
+    "EventCode": "0x89f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_write_data_beats_io_3",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local socket and IO Root Complex 3.",
+    "EventCode": "0x8df",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_write_data_beats_io_4",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local socket and IO Root Complex 4.",
+    "EventCode": "0x91f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_write_data_beats_io_5",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local socket and IO Root Complex 5.",
+    "EventCode": "0x95f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_write_data_beats_io_6",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local socket and IO Root Complex 6.",
+    "EventCode": "0x99f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_upstream_write_data_beats_io_7",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local socket and IO Root Complex 7.",
+    "EventCode": "0x9df",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_read_data_beats_io_0",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between remote socket and IO Root Complex 0.",
+    "EventCode": "0x81f",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_read_data_beats_io_1",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between remote socket and IO Root Complex 1.",
+    "EventCode": "0x85f",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_read_data_beats_io_2",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between remote socket and IO Root Complex 2.",
+    "EventCode": "0x89f",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_read_data_beats_io_3",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between remote socket and IO Root Complex 3.",
+    "EventCode": "0x8df",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_read_data_beats_io_4",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between remote socket and IO Root Complex 4.",
+    "EventCode": "0x91f",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_read_data_beats_io_5",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between remote socket and IO Root Complex 5.",
+    "EventCode": "0x95f",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_read_data_beats_io_6",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between remote socket and IO Root Complex 6.",
+    "EventCode": "0x99f",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_read_data_beats_io_7",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between remote socket and IO Root Complex 7.",
+    "EventCode": "0x9df",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_write_data_beats_io_0",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between remote socket and IO Root Complex 0.",
+    "EventCode": "0x81f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_write_data_beats_io_1",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between remote socket and IO Root Complex 1.",
+    "EventCode": "0x85f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_write_data_beats_io_2",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between remote socket and IO Root Complex 2.",
+    "EventCode": "0x89f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_write_data_beats_io_3",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between remote socket and IO Root Complex 3.",
+    "EventCode": "0x8df",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_write_data_beats_io_4",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between remote socket and IO Root Complex 4.",
+    "EventCode": "0x91f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_write_data_beats_io_5",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between remote socket and IO Root Complex 5.",
+    "EventCode": "0x95f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_write_data_beats_io_6",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between remote socket and IO Root Complex 6.",
+    "EventCode": "0x99f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_upstream_write_data_beats_io_7",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between remote socket and IO Root Complex 7.",
+    "EventCode": "0x9df",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_read_data_beats_io_0",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 0.",
+    "EventCode": "0x81f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_read_data_beats_io_1",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 1.",
+    "EventCode": "0x85f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_read_data_beats_io_2",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 2.",
+    "EventCode": "0x89f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_read_data_beats_io_3",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 3.",
+    "EventCode": "0x8df",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_read_data_beats_io_4",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 4.",
+    "EventCode": "0x91f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_read_data_beats_io_5",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 5.",
+    "EventCode": "0x95f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_read_data_beats_io_6",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 6.",
+    "EventCode": "0x99f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_read_data_beats_io_7",
+    "PublicDescription": "Upstream DMA read data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 7.",
+    "EventCode": "0x9df",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_write_data_beats_io_0",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 0.",
+    "EventCode": "0x81f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_write_data_beats_io_1",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 1.",
+    "EventCode": "0x85f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_write_data_beats_io_2",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 2.",
+    "EventCode": "0x89f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_write_data_beats_io_3",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 3.",
+    "EventCode": "0x8df",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_write_data_beats_io_4",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 4.",
+    "EventCode": "0x91f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_write_data_beats_io_5",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 5.",
+    "EventCode": "0x95f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_write_data_beats_io_6",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 6.",
+    "EventCode": "0x99f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_upstream_write_data_beats_io_7",
+    "PublicDescription": "Upstream DMA write data beats (64 bytes) for transactions between local or remote socket and IO Root Complex 7.",
+    "EventCode": "0x9df",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_0",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 0.",
+    "EventCode": "0x41e",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_1",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 1.",
+    "EventCode": "0x45e",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_2",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 2.",
+    "EventCode": "0x49e",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_3",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 3.",
+    "EventCode": "0x4de",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_4",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 4.",
+    "EventCode": "0x51e",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_5",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 5.",
+    "EventCode": "0x55e",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_6",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 6.",
+    "EventCode": "0x59e",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_7",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 7.",
+    "EventCode": "0x5de",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_8",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 8.",
+    "EventCode": "0x41f",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_9",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 9.",
+    "EventCode": "0x45f",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_10",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 10.",
+    "EventCode": "0x49f",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_11",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 11.",
+    "EventCode": "0x4df",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_12",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 12.",
+    "EventCode": "0x51f",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_13",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 13.",
+    "EventCode": "0x55f",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_14",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 14.",
+    "EventCode": "0x59f",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_cfi_15",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local socket and Core-to-Fabric Interface 15.",
+    "EventCode": "0x5df",
+    "UMask": "0x7fe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_0",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 0.",
+    "EventCode": "0x41e",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_1",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 1.",
+    "EventCode": "0x45e",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_2",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 2.",
+    "EventCode": "0x49e",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_3",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 3.",
+    "EventCode": "0x4de",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_4",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 4.",
+    "EventCode": "0x51e",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_5",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 5.",
+    "EventCode": "0x55e",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_6",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 6.",
+    "EventCode": "0x59e",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_7",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 7.",
+    "EventCode": "0x5de",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_8",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 8.",
+    "EventCode": "0x41f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_9",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 9.",
+    "EventCode": "0x45f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_10",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 10.",
+    "EventCode": "0x49f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_11",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 11.",
+    "EventCode": "0x4df",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_12",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 12.",
+    "EventCode": "0x51f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_13",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 13.",
+    "EventCode": "0x55f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_14",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 14.",
+    "EventCode": "0x59f",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_cfi_15",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and Core-to-Fabric Interface 15.",
+    "EventCode": "0x5df",
+    "UMask": "0x7ff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_0",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 0.",
+    "EventCode": "0x41e",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_1",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 1.",
+    "EventCode": "0x45e",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_2",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 2.",
+    "EventCode": "0x49e",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_3",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 3.",
+    "EventCode": "0x4de",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_4",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 4.",
+    "EventCode": "0x51e",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_5",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 5.",
+    "EventCode": "0x55e",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_6",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 6.",
+    "EventCode": "0x59e",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_7",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 7.",
+    "EventCode": "0x5de",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_8",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 8.",
+    "EventCode": "0x41f",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_9",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 9.",
+    "EventCode": "0x45f",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_10",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 10.",
+    "EventCode": "0x49f",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_11",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 11.",
+    "EventCode": "0x4df",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_12",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 12.",
+    "EventCode": "0x51f",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_13",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 13.",
+    "EventCode": "0x55f",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_14",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 14.",
+    "EventCode": "0x59f",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_inbound_data_beats_cfi_15",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between remote socket and Core-to-Fabric Interface 15.",
+    "EventCode": "0x5df",
+    "UMask": "0xbfe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_0",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 0.",
+    "EventCode": "0x41e",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_1",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 1.",
+    "EventCode": "0x45e",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_2",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 2.",
+    "EventCode": "0x49e",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_3",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 3.",
+    "EventCode": "0x4de",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_4",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 4.",
+    "EventCode": "0x51e",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_5",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 5.",
+    "EventCode": "0x55e",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_6",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 6.",
+    "EventCode": "0x59e",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_7",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 7.",
+    "EventCode": "0x5de",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_8",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 8.",
+    "EventCode": "0x41f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_9",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 9.",
+    "EventCode": "0x45f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_10",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 10.",
+    "EventCode": "0x49f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_11",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 11.",
+    "EventCode": "0x4df",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_12",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 12.",
+    "EventCode": "0x51f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_13",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 13.",
+    "EventCode": "0x55f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_14",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 14.",
+    "EventCode": "0x59f",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "remote_socket_outbound_data_beats_cfi_15",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between remote socket and Core-to-Fabric Interface 15.",
+    "EventCode": "0x5df",
+    "UMask": "0xbff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_0",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 0.",
+    "EventCode": "0x41e",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_1",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 1.",
+    "EventCode": "0x45e",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_2",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 2.",
+    "EventCode": "0x49e",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_3",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 3.",
+    "EventCode": "0x4de",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_4",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 4.",
+    "EventCode": "0x51e",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_5",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 5.",
+    "EventCode": "0x55e",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_6",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 6.",
+    "EventCode": "0x59e",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_7",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 7.",
+    "EventCode": "0x5de",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_8",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 8.",
+    "EventCode": "0x41f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_9",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 9.",
+    "EventCode": "0x45f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_10",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 10.",
+    "EventCode": "0x49f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_11",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 11.",
+    "EventCode": "0x4df",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_12",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 12.",
+    "EventCode": "0x51f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_13",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 13.",
+    "EventCode": "0x55f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_14",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 14.",
+    "EventCode": "0x59f",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_inbound_data_beats_cfi_15",
+    "PublicDescription": "Inbound data beats (32 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 15.",
+    "EventCode": "0x5df",
+    "UMask": "0xffe",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_0",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 0.",
+    "EventCode": "0x41e",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_1",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 1.",
+    "EventCode": "0x45e",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_2",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 2.",
+    "EventCode": "0x49e",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_3",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 3.",
+    "EventCode": "0x4de",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_4",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 4.",
+    "EventCode": "0x51e",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_5",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 5.",
+    "EventCode": "0x55e",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_6",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 6.",
+    "EventCode": "0x59e",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_7",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 7.",
+    "EventCode": "0x5de",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_8",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 8.",
+    "EventCode": "0x41f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_9",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 9.",
+    "EventCode": "0x45f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_10",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 10.",
+    "EventCode": "0x49f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_11",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 11.",
+    "EventCode": "0x4df",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_12",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 12.",
+    "EventCode": "0x51f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_13",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 13.",
+    "EventCode": "0x55f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_14",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 14.",
+    "EventCode": "0x59f",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_or_remote_socket_outbound_data_beats_cfi_15",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local or remote socket and Core-to-Fabric Interface 15.",
+    "EventCode": "0x5df",
+    "UMask": "0xfff",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_link_0",
+    "PublicDescription": "Inbound data beats (64 bytes) for transactions between local socket and remote socket over Cross-socket Link 0.",
+    "EventCode": "0xd5f",
+    "UMask": "0xf3f",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_link_1",
+    "PublicDescription": "Inbound data beats (64 bytes) for transactions between local socket and remote socket over Cross-socket Link 1.",
+    "EventCode": "0xd9f",
+    "UMask": "0xf3f",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_link_2",
+    "PublicDescription": "Inbound data beats (64 bytes) for transactions between local socket and remote socket over Cross-socket Link 2.",
+    "EventCode": "0xddf",
+    "UMask": "0xf3f",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_link_3",
+    "PublicDescription": "Inbound data beats (64 bytes) for transactions between local socket and remote socket over Cross-socket Link 3.",
+    "EventCode": "0xe1f",
+    "UMask": "0xf3f",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_link_4",
+    "PublicDescription": "Inbound data beats (64 bytes) for transactions between local socket and remote socket over Cross-socket Link 4.",
+    "EventCode": "0xe5f",
+    "UMask": "0xf3f",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_inbound_data_beats_link_5",
+    "PublicDescription": "Inbound data beats (64 bytes) for transactions between local socket and remote socket over Cross-socket Link 5.",
+    "EventCode": "0xe9f",
+    "UMask": "0xf3f",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_link_0",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and remote socket over Cross-socket Link 0.",
+    "EventCode": "0xd5f",
+    "UMask": "0xf3e",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_link_1",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and remote socket over Cross-socket Link 1.",
+    "EventCode": "0xd9f",
+    "UMask": "0xf3e",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_link_2",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and remote socket over Cross-socket Link 2.",
+    "EventCode": "0xddf",
+    "UMask": "0xf3e",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_link_3",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and remote socket over Cross-socket Link 3.",
+    "EventCode": "0xe1f",
+    "UMask": "0xf3e",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_link_4",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and remote socket over Cross-socket Link 4.",
+    "EventCode": "0xe5f",
+    "UMask": "0xf3e",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  },
+  {
+    "EventName": "local_socket_outbound_data_beats_link_5",
+    "PublicDescription": "Outbound data beats (64 bytes) for transactions between local socket and remote socket over Cross-socket Link 5.",
+    "EventCode": "0xe9f",
+    "UMask": "0xf3e",
+    "PerPkg": "1",
+    "Unit": "DFPMC"
+  }
+]

From 17aedce6e0ff80d5e210b7a773738877336f1ca5 Mon Sep 17 00:00:00 2001
From: Sandipan Das <sandipan.das@amd.com>
Date: Fri, 18 Oct 2024 15:01:04 +0530
Subject: [PATCH 0509/1530] perf vendor events amd: Add Zen 5 data fabric
 metrics

Add data fabric metrics taken from Section 2.1.16.2 "Performance
Measurement" in the Processor Programming Reference (PPR) for AMD Family
1Ah Model 02h Revision C1 Processors document available at the link
below.

The recommended metrics are sourced from Table 28 "Guidance for Common
Performance Statistics with Complex Event Selects". They capture data
bandwidth for various links and interfaces in the data fabric.

Link: https://bugzilla.kernel.org/attachment.cgi?id=307010
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: ananth.narayan@amd.com
Cc: ravi.bangoria@amd.com
Cc: eranian@google.com
Link: https://lore.kernel.org/r/e8757bb9f511907a52bc182de9395c5edec2fccf.1729242778.git.sandipan.das@amd.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../arch/x86/amdzen5/recommended.json         | 112 ++++++++++++++++++
 1 file changed, 112 insertions(+)

diff --git a/tools/perf/pmu-events/arch/x86/amdzen5/recommended.json b/tools/perf/pmu-events/arch/x86/amdzen5/recommended.json
index c97874039c1e7..635d57e3bc151 100644
--- a/tools/perf/pmu-events/arch/x86/amdzen5/recommended.json
+++ b/tools/perf/pmu-events/arch/x86/amdzen5/recommended.json
@@ -341,5 +341,117 @@
     "MetricGroup": "memory_controller",
     "PerPkg": "1",
     "ScaleUnit": "1per_memclk"
+  },
+  {
+    "MetricName": "dram_read_bandwidth_for_local_or_remote_socket",
+    "BriefDescription": "DRAM read data bandwidth for accesses in local or remote socket.",
+    "MetricExpr": "(local_or_remote_socket_read_data_beats_dram_0 + local_or_remote_socket_read_data_beats_dram_1 + local_or_remote_socket_read_data_beats_dram_2 + local_or_remote_socket_read_data_beats_dram_3 + local_or_remote_socket_read_data_beats_dram_4 + local_or_remote_socket_read_data_beats_dram_5 + local_or_remote_socket_read_data_beats_dram_6 + local_or_remote_socket_read_data_beats_dram_7 + local_or_remote_socket_read_data_beats_dram_8 + local_or_remote_socket_read_data_beats_dram_9 + local_or_remote_socket_read_data_beats_dram_10 + local_or_remote_socket_read_data_beats_dram_11) / duration_time",
+    "MetricGroup": "data_fabric",
+    "PerPkg": "1",
+    "ScaleUnit": "6.4e-5MB/s"
+  },
+  {
+    "MetricName": "dram_write_bandwidth_for_local_socket",
+    "BriefDescription": "DRAM write data bandwidth for accesses in local socket.",
+    "MetricExpr": "(local_socket_write_data_beats_dram_0 + local_socket_write_data_beats_dram_1 + local_socket_write_data_beats_dram_2 + local_socket_write_data_beats_dram_3 + local_socket_write_data_beats_dram_4 + local_socket_write_data_beats_dram_5 + local_socket_write_data_beats_dram_6 + local_socket_write_data_beats_dram_7 + local_socket_write_data_beats_dram_8 + local_socket_write_data_beats_dram_9 + local_socket_write_data_beats_dram_10 + local_socket_write_data_beats_dram_11) / duration_time",
+    "MetricGroup": "data_fabric",
+    "PerPkg": "1",
+    "ScaleUnit": "6.4e-5MB/s"
+  },
+  {
+    "MetricName": "dram_write_bandwidth_for_remote_socket",
+    "BriefDescription": "DRAM write data bandwidth for accesses in remote socket.",
+    "MetricExpr": "(remote_socket_write_data_beats_dram_0 + remote_socket_write_data_beats_dram_1 + remote_socket_write_data_beats_dram_2 + remote_socket_write_data_beats_dram_3 + remote_socket_write_data_beats_dram_4 + remote_socket_write_data_beats_dram_5 + remote_socket_write_data_beats_dram_6 + remote_socket_write_data_beats_dram_7 + remote_socket_write_data_beats_dram_8 + remote_socket_write_data_beats_dram_9 + remote_socket_write_data_beats_dram_10 + remote_socket_write_data_beats_dram_11) / duration_time",
+    "MetricGroup": "data_fabric",
+    "PerPkg": "1",
+    "ScaleUnit": "6.4e-5MB/s"
+  },
+  {
+    "MetricName": "dram_write_bandwidth_for_local_or_remote_socket",
+    "BriefDescription": "DRAM write data bandwidth for accesses in local or remote socket.",
+    "MetricExpr": "(local_or_remote_socket_write_data_beats_dram_0 + local_or_remote_socket_write_data_beats_dram_1 + local_or_remote_socket_write_data_beats_dram_2 + local_or_remote_socket_write_data_beats_dram_3 + local_or_remote_socket_write_data_beats_dram_4 + local_or_remote_socket_write_data_beats_dram_5 + local_or_remote_socket_write_data_beats_dram_6 + local_or_remote_socket_write_data_beats_dram_7 + local_or_remote_socket_write_data_beats_dram_8 + local_or_remote_socket_write_data_beats_dram_9 + local_or_remote_socket_write_data_beats_dram_10 + local_or_remote_socket_write_data_beats_dram_11) / duration_time",
+    "MetricGroup": "data_fabric",
+    "PerPkg": "1",
+    "ScaleUnit": "6.4e-5MB/s"
+  },
+  {
+    "MetricName": "upstream_dma_read_bandwidth_for_local_socket",
+    "BriefDescription": "Upstream DMA read data bandwidth for accesses in local socket.",
+    "MetricExpr": "(local_socket_upstream_read_data_beats_io_0 + local_socket_upstream_read_data_beats_io_1 + local_socket_upstream_read_data_beats_io_2 + local_socket_upstream_read_data_beats_io_3 + local_socket_upstream_read_data_beats_io_4 + local_socket_upstream_read_data_beats_io_5 + local_socket_upstream_read_data_beats_io_6 + local_socket_upstream_read_data_beats_io_7) / duration_time",
+    "MetricGroup": "data_fabric",
+    "PerPkg": "1",
+    "ScaleUnit": "6.4e-5MB/s"
+  },
+  {
+    "MetricName": "upstream_dma_write_bandwidth_for_local_socket",
+    "BriefDescription": "Upstream DMA write data bandwidth for accesses in local socket.",
+    "MetricExpr": "(local_socket_upstream_write_data_beats_io_0 + local_socket_upstream_write_data_beats_io_1 + local_socket_upstream_write_data_beats_io_2 + local_socket_upstream_write_data_beats_io_3 + local_socket_upstream_write_data_beats_io_4 + local_socket_upstream_write_data_beats_io_5 + local_socket_upstream_write_data_beats_io_6 + local_socket_upstream_write_data_beats_io_7) / duration_time",
+    "MetricGroup": "data_fabric",
+    "PerPkg": "1",
+    "ScaleUnit": "6.4e-5MB/s"
+  },
+  {
+    "MetricName": "upstream_dma_read_bandwidth_for_remote_socket",
+    "BriefDescription": "Upstream DMA read data bandwidth for accesses in remote socket.",
+    "MetricExpr": "(remote_socket_upstream_read_data_beats_io_0 + remote_socket_upstream_read_data_beats_io_1 + remote_socket_upstream_read_data_beats_io_2 + remote_socket_upstream_read_data_beats_io_3 + remote_socket_upstream_read_data_beats_io_4 + remote_socket_upstream_read_data_beats_io_5 + remote_socket_upstream_read_data_beats_io_6 + remote_socket_upstream_read_data_beats_io_7) / duration_time",
+    "MetricGroup": "data_fabric",
+    "PerPkg": "1",
+    "ScaleUnit": "6.4e-5MB/s"
+  },
+  {
+    "MetricName": "upstream_dma_write_bandwidth_for_remote_socket",
+    "BriefDescription": "Upstream DMA write data bandwidth for accesses in remote socket.",
+    "MetricExpr": "(remote_socket_upstream_write_data_beats_io_0 + remote_socket_upstream_write_data_beats_io_1 + remote_socket_upstream_write_data_beats_io_2 + remote_socket_upstream_write_data_beats_io_3 + remote_socket_upstream_write_data_beats_io_4 + remote_socket_upstream_write_data_beats_io_5 + remote_socket_upstream_write_data_beats_io_6 + remote_socket_upstream_write_data_beats_io_7) / duration_time",
+    "MetricGroup": "data_fabric",
+    "PerPkg": "1",
+    "ScaleUnit": "6.4e-5MB/s"
+  },
+  {
+    "MetricName": "core_inbound_data_bandwidth_for_local_socket",
+    "BriefDescription": "Core inbound data bandwidth for accesses in local socket.",
+    "MetricExpr": "(local_socket_inbound_data_beats_cfi_0 + local_socket_inbound_data_beats_cfi_1 + local_socket_inbound_data_beats_cfi_2 + local_socket_inbound_data_beats_cfi_3 + local_socket_inbound_data_beats_cfi_4 + local_socket_inbound_data_beats_cfi_5 + local_socket_inbound_data_beats_cfi_6 + local_socket_inbound_data_beats_cfi_7 + local_socket_inbound_data_beats_cfi_8 + local_socket_inbound_data_beats_cfi_9 + local_socket_inbound_data_beats_cfi_10 + local_socket_inbound_data_beats_cfi_11 + local_socket_inbound_data_beats_cfi_12 + local_socket_inbound_data_beats_cfi_13 + local_socket_inbound_data_beats_cfi_14 + local_socket_inbound_data_beats_cfi_15) / duration_time",
+    "MetricGroup": "data_fabric",
+    "PerPkg": "1",
+    "ScaleUnit": "3.2e-5MB/s"
+  },
+  {
+    "MetricName": "core_outbound_data_bandwidth_for_local_socket",
+    "BriefDescription": "Core outbound data bandwidth for accesses in local socket.",
+    "MetricExpr": "(local_socket_outbound_data_beats_cfi_0 + local_socket_outbound_data_beats_cfi_1 + local_socket_outbound_data_beats_cfi_2 + local_socket_outbound_data_beats_cfi_3 + local_socket_outbound_data_beats_cfi_4 + local_socket_outbound_data_beats_cfi_5 + local_socket_outbound_data_beats_cfi_6 + local_socket_outbound_data_beats_cfi_7 + local_socket_outbound_data_beats_cfi_8 + local_socket_outbound_data_beats_cfi_9 + local_socket_outbound_data_beats_cfi_10 + local_socket_outbound_data_beats_cfi_11 + local_socket_outbound_data_beats_cfi_12 + local_socket_outbound_data_beats_cfi_13 + local_socket_outbound_data_beats_cfi_14 + local_socket_outbound_data_beats_cfi_15) / duration_time",
+    "MetricGroup": "data_fabric",
+    "PerPkg": "1",
+    "ScaleUnit": "6.4e-5MB/s"
+  },
+  {
+    "MetricName": "core_inbound_data_bandwidth_for_remote_socket",
+    "BriefDescription": "Core inbound data bandwidth for accesses in remote socket.",
+    "MetricExpr": "(remote_socket_inbound_data_beats_cfi_0 + remote_socket_inbound_data_beats_cfi_1 + remote_socket_inbound_data_beats_cfi_2 + remote_socket_inbound_data_beats_cfi_3 + remote_socket_inbound_data_beats_cfi_4 + remote_socket_inbound_data_beats_cfi_5 + remote_socket_inbound_data_beats_cfi_6 + remote_socket_inbound_data_beats_cfi_7 + remote_socket_inbound_data_beats_cfi_8 + remote_socket_inbound_data_beats_cfi_9 + remote_socket_inbound_data_beats_cfi_10 + remote_socket_inbound_data_beats_cfi_11 + remote_socket_inbound_data_beats_cfi_12 + remote_socket_inbound_data_beats_cfi_13 + remote_socket_inbound_data_beats_cfi_14 + remote_socket_inbound_data_beats_cfi_15) / duration_time",
+    "MetricGroup": "data_fabric",
+    "PerPkg": "1",
+    "ScaleUnit": "3.2e-5MB/s"
+  },
+  {
+    "MetricName": "core_outbound_data_bandwidth_for_remote_socket",
+    "BriefDescription": "Core outbound data bandwidth for accesses in remote socket.",
+    "MetricExpr": "(remote_socket_outbound_data_beats_cfi_0 + remote_socket_outbound_data_beats_cfi_1 + remote_socket_outbound_data_beats_cfi_2 + remote_socket_outbound_data_beats_cfi_3 + remote_socket_outbound_data_beats_cfi_4 + remote_socket_outbound_data_beats_cfi_5 + remote_socket_outbound_data_beats_cfi_6 + remote_socket_outbound_data_beats_cfi_7 + remote_socket_outbound_data_beats_cfi_8 + remote_socket_outbound_data_beats_cfi_9 + remote_socket_outbound_data_beats_cfi_10 + remote_socket_outbound_data_beats_cfi_11 + remote_socket_outbound_data_beats_cfi_12 + remote_socket_outbound_data_beats_cfi_13 + remote_socket_outbound_data_beats_cfi_14 + remote_socket_outbound_data_beats_cfi_15) / duration_time",
+    "MetricGroup": "data_fabric",
+    "PerPkg": "1",
+    "ScaleUnit": "6.4e-5MB/s"
+  },
+  {
+    "MetricName": "cross_socket_inbound_data_bandwidth_for_local_socket",
+    "BriefDescription": "Inbound data bandwidth for accesses between local socket and remote socket.",
+    "MetricExpr": "(local_socket_inbound_data_beats_link_0 + local_socket_inbound_data_beats_link_1 + local_socket_inbound_data_beats_link_2 + local_socket_inbound_data_beats_link_3 + local_socket_inbound_data_beats_link_4 + local_socket_inbound_data_beats_link_5) / duration_time",
+    "MetricGroup": "data_fabric",
+    "PerPkg": "1",
+    "ScaleUnit": "6.4e-5MB/s"
+  },
+  {
+    "MetricName": "cross_socket_outbound_data_bandwidth_for_local_socket",
+    "BriefDescription": "Outbound data bandwidth for accesses between local socket and remote socket.",
+    "MetricExpr": "(local_socket_outbound_data_beats_link_0 + local_socket_outbound_data_beats_link_1 + local_socket_outbound_data_beats_link_2 + local_socket_outbound_data_beats_link_3 + local_socket_outbound_data_beats_link_4 + local_socket_outbound_data_beats_link_5) / duration_time",
+    "MetricGroup": "data_fabric",
+    "PerPkg": "1",
+    "ScaleUnit": "6.4e-5MB/s"
   }
 ]

From 46610ba41ef10b9570c5f5b12bde2f2eabb25bb5 Mon Sep 17 00:00:00 2001
From: Sandipan Das <sandipan.das@amd.com>
Date: Fri, 18 Oct 2024 15:01:05 +0530
Subject: [PATCH 0510/1530] perf vendor events amd: Update Zen 5 data cache
 fill events

For events that count data cache fills, some combinations of the unit
mask bits are useful for counting fills from local caches, DRAM or any
far sources. However, named events currently exist for PMCx044 (Any Data
Cache Fills) only. Add similar events for the following base events.
  * PMCx043 (Demand Data Cache Fills)
  * PMCx059 (Software Prefetch Data Cache Fills)
  * PMCx05A (Hardware Prefetch Data Cache Fills)

While at it, remove "ls_any_fills_from_sys.all_dram_io" since it is a
duplicate of "ls_any_fills_from_sys.dram_io_all".

Event descriptions can be found in Section 2.1.16.5.2 "Load/Store (LS)
Events" of the Processor Programming Reference (PPR) for AMD Family 1Ah
Model 02h Revision C1 Processors document available at the link below.

Link: https://bugzilla.kernel.org/attachment.cgi?id=307010
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: ananth.narayan@amd.com
Cc: ravi.bangoria@amd.com
Cc: eranian@google.com
Link: https://lore.kernel.org/r/e036e3c9fb962c939fa06c855b68e532ee609e01.1729242778.git.sandipan.das@amd.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../arch/x86/amdzen5/load-store.json          | 78 +++++++++++++++++--
 1 file changed, 72 insertions(+), 6 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/amdzen5/load-store.json b/tools/perf/pmu-events/arch/x86/amdzen5/load-store.json
index af2fdf1f55d64..ff6627a778057 100644
--- a/tools/perf/pmu-events/arch/x86/amdzen5/load-store.json
+++ b/tools/perf/pmu-events/arch/x86/amdzen5/load-store.json
@@ -96,6 +96,12 @@
     "BriefDescription": "Demand data cache fills from L3 cache or different L2 cache in the same CCX.",
     "UMask": "0x02"
   },
+  {
+    "EventName": "ls_dmnd_fills_from_sys.local_all",
+    "EventCode": "0x43",
+    "BriefDescription": "Demand data cache fills from local L2 cache, L3 cache or different L2 cache in the same CCX.",
+    "UMask": "0x03"
+  },
   {
     "EventName": "ls_dmnd_fills_from_sys.near_cache",
     "EventCode": "0x43",
@@ -114,12 +120,30 @@
     "BriefDescription": "Demand data cache fills from cache of another CCX when the address was in a different NUMA node.",
     "UMask": "0x10"
   },
+  {
+    "EventName": "ls_dmnd_fills_from_sys.remote_cache",
+    "EventCode": "0x43",
+    "BriefDescription": "Demand data cache fills from cache of another CCX when the address was in the same or a different NUMA node.",
+    "UMask": "0x14"
+  },
   {
     "EventName": "ls_dmnd_fills_from_sys.dram_io_far",
     "EventCode": "0x43",
     "BriefDescription": "Demand data cache fills from either DRAM or MMIO in a different NUMA node (same or different socket).",
     "UMask": "0x40"
   },
+  {
+    "EventName": "ls_dmnd_fills_from_sys.dram_io_all",
+    "EventCode": "0x43",
+    "BriefDescription": "Demand data cache fills from either DRAM or MMIO in the same or a different NUMA node (same or different socket).",
+    "UMask": "0x48"
+  },
+  {
+    "EventName": "ls_dmnd_fills_from_sys.far_all",
+    "EventCode": "0x43",
+    "BriefDescription": "Demand data cache fills from either cache of another CCX, DRAM or MMIO when the address was in a different NUMA node (same or different socket).",
+    "UMask": "0x50"
+  },
   {
     "EventName": "ls_dmnd_fills_from_sys.alternate_memories",
     "EventCode": "0x43",
@@ -192,12 +216,6 @@
     "BriefDescription": "Any data cache fills from either cache of another CCX, DRAM or MMIO when the address was in a different NUMA node (same or different socket).",
     "UMask": "0x50"
   },
-  {
-    "EventName": "ls_any_fills_from_sys.all_dram_io",
-    "EventCode": "0x44",
-    "BriefDescription": "Any data cache fills from either DRAM or MMIO in any NUMA node (same or different socket).",
-    "UMask": "0x48"
-  },
   {
     "EventName": "ls_any_fills_from_sys.alternate_memories",
     "EventCode": "0x44",
@@ -342,6 +360,12 @@
     "BriefDescription": "Software prefetch data cache fills from L3 cache or different L2 cache in the same CCX.",
     "UMask": "0x02"
   },
+  {
+    "EventName": "ls_sw_pf_dc_fills.local_all",
+    "EventCode": "0x59",
+    "BriefDescription": "Software prefetch data cache fills from local L2 cache, L3 cache or different L2 cache in the same CCX.",
+    "UMask": "0x03"
+  },
   {
     "EventName": "ls_sw_pf_dc_fills.near_cache",
     "EventCode": "0x59",
@@ -360,12 +384,30 @@
     "BriefDescription": "Software prefetch data cache fills from cache of another CCX in a different NUMA node.",
     "UMask": "0x10"
   },
+  {
+    "EventName": "ls_sw_pf_dc_fills.remote_cache",
+    "EventCode": "0x59",
+    "BriefDescription": "Software prefetch data cache fills from cache of another CCX when the address was in the same or a different NUMA node.",
+    "UMask": "0x14"
+  },
   {
     "EventName": "ls_sw_pf_dc_fills.dram_io_far",
     "EventCode": "0x59",
     "BriefDescription": "Software prefetch data cache fills from either DRAM or MMIO in a different NUMA node (same or different socket).",
     "UMask": "0x40"
   },
+  {
+    "EventName": "ls_sw_pf_dc_fills.dram_io_all",
+    "EventCode": "0x59",
+    "BriefDescription": "Software prefetch data cache fills from either DRAM or MMIO in the same or a different NUMA node (same or different socket).",
+    "UMask": "0x48"
+  },
+  {
+    "EventName": "ls_sw_pf_dc_fills.far_all",
+    "EventCode": "0x59",
+    "BriefDescription": "Software prefetch data cache fills from either cache of another CCX, DRAM or MMIO when the address was in a different NUMA node (same or different socket).",
+    "UMask": "0x50"
+  },
   {
     "EventName": "ls_sw_pf_dc_fills.alternate_memories",
     "EventCode": "0x59",
@@ -390,6 +432,12 @@
     "BriefDescription": "Hardware prefetch data cache fills from L3 cache or different L2 cache in the same CCX.",
     "UMask": "0x02"
   },
+  {
+    "EventName": "ls_hw_pf_dc_fills.local_all",
+    "EventCode": "0x5a",
+    "BriefDescription": "Hardware prefetch data cache fills from local L2 cache, L3 cache or different L2 cache in the same CCX.",
+    "UMask": "0x03"
+  },
   {
     "EventName": "ls_hw_pf_dc_fills.near_cache",
     "EventCode": "0x5a",
@@ -408,12 +456,30 @@
     "BriefDescription": "Hardware prefetch data cache fills from cache of another CCX when the address was in a different NUMA node.",
     "UMask": "0x10"
   },
+  {
+    "EventName": "ls_hw_pf_dc_fills.remote_cache",
+    "EventCode": "0x5a",
+    "BriefDescription": "Hardware prefetch data cache fills from cache of another CCX when the address was in the same or a different NUMA node.",
+    "UMask": "0x14"
+  },
   {
     "EventName": "ls_hw_pf_dc_fills.dram_io_far",
     "EventCode": "0x5a",
     "BriefDescription": "Hardware prefetch data cache fills from either DRAM or MMIO in a different NUMA node (same or different socket).",
     "UMask": "0x40"
   },
+  {
+    "EventName": "ls_hw_pf_dc_fills.dram_io_all",
+    "EventCode": "0x5a",
+    "BriefDescription": "Hardware prefetch data cache fills from either DRAM or MMIO in the same or a different NUMA node (same or different socket).",
+    "UMask": "0x48"
+  },
+  {
+    "EventName": "ls_hw_pf_dc_fills.far_all",
+    "EventCode": "0x5a",
+    "BriefDescription": "Hardware prefetch data cache fills from either cache of another CCX, DRAM or MMIO when the address was in a different NUMA node (same or different socket).",
+    "UMask": "0x50"
+  },
   {
     "EventName": "ls_hw_pf_dc_fills.alternate_memories",
     "EventCode": "0x5a",

From 97b7675640928a5de971f43034ba1f41e30001b7 Mon Sep 17 00:00:00 2001
From: Yixun Lan <dlan@gentoo.org>
Date: Wed, 16 Oct 2024 08:59:41 +0800
Subject: [PATCH 0511/1530] dt-bindings: pinctrl: spacemit: add support for K1
 SoC

Add dt-bindings for the pinctrl driver of SpacemiT's K1 SoC.

Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Yixun Lan <dlan@gentoo.org>
Link: https://lore.kernel.org/20241016-02-k1-pinctrl-v5-1-03d395222e4f@gentoo.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/spacemit,k1-pinctrl.yaml | 124 ++++++++++++++++++
 1 file changed, 124 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/spacemit,k1-pinctrl.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/spacemit,k1-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/spacemit,k1-pinctrl.yaml
new file mode 100644
index 0000000000000..b01ecd83b71b5
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/spacemit,k1-pinctrl.yaml
@@ -0,0 +1,124 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/spacemit,k1-pinctrl.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: SpacemiT K1 SoC Pin Controller
+
+maintainers:
+  - Yixun Lan <dlan@gentoo.org>
+
+properties:
+  compatible:
+    const: spacemit,k1-pinctrl
+
+  reg:
+    items:
+      - description: pinctrl io memory base
+
+patternProperties:
+  '-cfg$':
+    type: object
+    additionalProperties: false
+
+    description:
+      A pinctrl node should contain at least one subnode representing the
+      pinctrl groups available on the machine.
+
+    patternProperties:
+      '-pins$':
+        type: object
+        additionalProperties: false
+
+        description:
+          Each subnode will list the pins it needs, and how they should
+          be configured, with regard to muxer configuration, bias pull,
+          drive strength, input schmitt trigger, slew rate, power source.
+
+        allOf:
+          - $ref: pincfg-node.yaml#
+          - $ref: pinmux-node.yaml#
+
+        properties:
+          pinmux:
+            description:
+              The list of GPIOs and their mux settings that properties in the
+              node apply to. This should be set using the K1_PADCONF macro to
+              construct the value.
+
+          bias-disable: true
+
+          bias-pull-down: true
+
+          bias-pull-up:
+            description: |
+              typical value for selecting bias pull up or strong pull up.
+              0: normal bias pull up
+              1: strong bias pull up
+            enum: [ 0, 1 ]
+
+          drive-strength:
+            description: |
+              typical current when output high level.
+              1.8V output: 11, 21, 32, 42 (mA)
+              3.3V output: 7, 10, 13, 16, 19, 23, 26, 29 (mA)
+
+          input-schmitt:
+            description: |
+              typical threshold for schmitt trigger.
+              0: buffer mode
+              1: trigger mode
+              2, 3: trigger mode
+            $ref: /schemas/types.yaml#/definitions/uint32
+            enum: [ 0, 1, 2, 3 ]
+
+          power-source:
+            description: external power supplies at 1.8v or 3.3v.
+            enum: [ 1800, 3300 ]
+
+          slew-rate:
+            description: |
+              slew rate for output buffer.
+              0: disable it
+              1: enable it (via bundled value from drive strength)
+              2: slow speed 0
+              3: slow speed 1
+              4: medium speed
+              5: fast speed
+            enum: [ 0, 1, 2, 3, 4, 5 ]
+
+        required:
+          - pinmux
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #define K1_PADCONF(pin, func) (((pin) << 16) | (func))
+
+    soc {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        pinctrl@d401e000 {
+            compatible = "spacemit,k1-pinctrl";
+            reg = <0x0 0xd401e000 0x0 0x400>;
+
+            uart0_2_cfg: uart0-2-cfg {
+                uart0-2-pins {
+                    pinmux = <K1_PADCONF(68, 2)>,
+                             <K1_PADCONF(69, 2)>;
+
+                    bias-pull-up = <0>;
+                    drive-strength = <32>;
+                };
+            };
+        };
+    };
+
+...

From a83c29e1d145cca5240952100acd1cd60f25fb5f Mon Sep 17 00:00:00 2001
From: Yixun Lan <dlan@gentoo.org>
Date: Wed, 16 Oct 2024 08:59:42 +0800
Subject: [PATCH 0512/1530] pinctrl: spacemit: add support for SpacemiT K1 SoC

SpacemiT's K1 SoC has a pinctrl controller which use single register
to describe all functions, which include bias pull up/down(strong pull),
drive strength, schmitter trigger, slew rate, mux mode.

Signed-off-by: Yixun Lan <dlan@gentoo.org>
Link: https://lore.kernel.org/20241016-02-k1-pinctrl-v5-2-03d395222e4f@gentoo.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/Kconfig               |    1 +
 drivers/pinctrl/Makefile              |    1 +
 drivers/pinctrl/spacemit/Kconfig      |   17 +
 drivers/pinctrl/spacemit/Makefile     |    3 +
 drivers/pinctrl/spacemit/pinctrl-k1.c | 1051 +++++++++++++++++++++++++
 drivers/pinctrl/spacemit/pinctrl-k1.h |   40 +
 6 files changed, 1113 insertions(+)
 create mode 100644 drivers/pinctrl/spacemit/Kconfig
 create mode 100644 drivers/pinctrl/spacemit/Makefile
 create mode 100644 drivers/pinctrl/spacemit/pinctrl-k1.c
 create mode 100644 drivers/pinctrl/spacemit/pinctrl-k1.h

diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index f64126a8d9a93..95a8e2b9a614a 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -631,6 +631,7 @@ source "drivers/pinctrl/realtek/Kconfig"
 source "drivers/pinctrl/renesas/Kconfig"
 source "drivers/pinctrl/samsung/Kconfig"
 source "drivers/pinctrl/sophgo/Kconfig"
+source "drivers/pinctrl/spacemit/Kconfig"
 source "drivers/pinctrl/spear/Kconfig"
 source "drivers/pinctrl/sprd/Kconfig"
 source "drivers/pinctrl/starfive/Kconfig"
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index efbe255fa8e1f..fba1c56624c0d 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -78,6 +78,7 @@ obj-$(CONFIG_ARCH_REALTEK)      += realtek/
 obj-$(CONFIG_PINCTRL_RENESAS)	+= renesas/
 obj-$(CONFIG_PINCTRL_SAMSUNG)	+= samsung/
 obj-y				+= sophgo/
+obj-y				+= spacemit/
 obj-$(CONFIG_PINCTRL_SPEAR)	+= spear/
 obj-y				+= sprd/
 obj-$(CONFIG_SOC_STARFIVE)	+= starfive/
diff --git a/drivers/pinctrl/spacemit/Kconfig b/drivers/pinctrl/spacemit/Kconfig
new file mode 100644
index 0000000000000..168f8a5ffbb95
--- /dev/null
+++ b/drivers/pinctrl/spacemit/Kconfig
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Sophgo SoC PINCTRL drivers
+#
+
+config PINCTRL_SPACEMIT_K1
+	tristate "SpacemiT K1 SoC Pinctrl driver"
+	depends on ARCH_SPACEMIT || COMPILE_TEST
+	depends on OF
+	select GENERIC_PINCTRL_GROUPS
+	select GENERIC_PINMUX_FUNCTIONS
+	select GENERIC_PINCONF
+	help
+	  Say Y to select the pinctrl driver for K1 SoC.
+	  This pin controller allows selecting the mux function for
+	  each pin. This driver can also be built as a module called
+	  pinctrl-k1.
diff --git a/drivers/pinctrl/spacemit/Makefile b/drivers/pinctrl/spacemit/Makefile
new file mode 100644
index 0000000000000..fede1e80fe0ff
--- /dev/null
+++ b/drivers/pinctrl/spacemit/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_PINCTRL_SPACEMIT_K1)	+= pinctrl-k1.o
diff --git a/drivers/pinctrl/spacemit/pinctrl-k1.c b/drivers/pinctrl/spacemit/pinctrl-k1.c
new file mode 100644
index 0000000000000..c75ea27b23446
--- /dev/null
+++ b/drivers/pinctrl/spacemit/pinctrl-k1.c
@@ -0,0 +1,1051 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Yixun Lan <dlan@gentoo.org> */
+
+#include <linux/bits.h>
+#include <linux/cleanup.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/module.h>
+
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinmux.h>
+
+#include "../core.h"
+#include "../pinctrl-utils.h"
+#include "../pinconf.h"
+#include "../pinmux.h"
+#include "pinctrl-k1.h"
+
+/*
+ * +---------+----------+-----------+--------+--------+----------+--------+
+ * |   pull  |   drive  | schmitter |  slew  |  edge  |  strong  |   mux  |
+ * | up/down | strength |  trigger  |  rate  | detect |   pull   |  mode  |
+ * +---------+----------+-----------+--------+--------+----------+--------+
+ *   3 bits     3 bits     2 bits     1 bit    3 bits     1 bit    3 bits
+ */
+
+#define PAD_MUX			GENMASK(2, 0)
+#define PAD_STRONG_PULL		BIT(3)
+#define PAD_EDGE_RISE		BIT(4)
+#define PAD_EDGE_FALL		BIT(5)
+#define PAD_EDGE_CLEAR		BIT(6)
+#define PAD_SLEW_RATE		GENMASK(12, 11)
+#define PAD_SLEW_RATE_EN	BIT(7)
+#define PAD_SCHMITT		GENMASK(9, 8)
+#define PAD_DRIVE		GENMASK(12, 10)
+#define PAD_PULLDOWN		BIT(13)
+#define PAD_PULLUP		BIT(14)
+#define PAD_PULL_EN		BIT(15)
+
+struct spacemit_pin {
+	u16				pin;
+	u16				flags;
+	u8				gpiofunc;
+};
+
+struct spacemit_pinctrl {
+	struct device				*dev;
+	struct pinctrl_dev			*pctl_dev;
+	const struct spacemit_pinctrl_data	*data;
+	struct pinctrl_desc			pdesc;
+
+	struct mutex				mutex;
+	raw_spinlock_t				lock;
+
+	void __iomem				*regs;
+};
+
+struct spacemit_pinctrl_data {
+	const struct pinctrl_pin_desc   *pins;
+	const struct spacemit_pin	*data;
+	u16				npins;
+};
+
+struct spacemit_pin_mux_config {
+	const struct spacemit_pin	*pin;
+	u32				config;
+};
+
+struct spacemit_pin_drv_strength {
+	u8		val;
+	u32		mA;
+};
+
+/* map pin id to pinctrl register offset, refer MFPR definition */
+static unsigned int spacemit_pin_to_offset(unsigned int pin)
+{
+	unsigned int offset = 0;
+
+	switch (pin) {
+	case 0 ... 85:
+		offset = pin + 1;
+		break;
+	case 86 ... 92:
+		offset = pin + 37;
+		break;
+	case 93 ... 97:
+		offset = pin + 24;
+		break;
+	case 98:
+		offset = 93;
+		break;
+	case 99:
+		offset = 92;
+		break;
+	case 100:
+		offset = 91;
+		break;
+	case 101:
+		offset = 90;
+		break;
+	case 102:
+		offset = 95;
+		break;
+	case 103:
+		offset = 94;
+		break;
+	case 104 ... 110:
+		offset = pin + 6;
+		break;
+	case 111 ... 127:
+		offset = pin + 20;
+		break;
+	default:
+		break;
+	}
+
+	return offset << 2;
+}
+
+static inline void __iomem *spacemit_pin_to_reg(struct spacemit_pinctrl *pctrl,
+						unsigned int pin)
+{
+	return pctrl->regs + spacemit_pin_to_offset(pin);
+}
+
+static u16 spacemit_dt_get_pin(u32 value)
+{
+	return value >> 16;
+}
+
+static u16 spacemit_dt_get_pin_mux(u32 value)
+{
+	return value & GENMASK(15, 0);
+}
+
+static const struct spacemit_pin *spacemit_get_pin(struct spacemit_pinctrl *pctrl,
+						   unsigned long pin)
+{
+	const struct spacemit_pin *pdata = pctrl->data->data;
+	int i;
+
+	for (i = 0; i < pctrl->data->npins; i++) {
+		if (pin == pdata[i].pin)
+			return &pdata[i];
+	}
+
+	return NULL;
+}
+
+static inline enum spacemit_pin_io_type spacemit_to_pin_io_type(
+	const struct spacemit_pin *pin)
+{
+	return K1_PIN_GET_IO_TYPE(pin->flags);
+}
+
+/* External: IO voltage via external source, can be 1.8V or 3.3V */
+static const char * const io_type_desc[] = {
+	"None",
+	"Fixed/1V8",
+	"Fixed/3V3",
+	"External",
+};
+
+static void spacemit_pctrl_dbg_show(struct pinctrl_dev *pctldev,
+				    struct seq_file *seq, unsigned int pin)
+{
+	struct spacemit_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
+	const struct spacemit_pin *spin = spacemit_get_pin(pctrl, pin);
+	enum spacemit_pin_io_type type = spacemit_to_pin_io_type(spin);
+	void __iomem *reg;
+	u32 value;
+
+	seq_printf(seq, "offset: 0x%04x ", spacemit_pin_to_offset(pin));
+	seq_printf(seq, "type: %s ", io_type_desc[type]);
+
+	reg = spacemit_pin_to_reg(pctrl, pin);
+	value = readl(reg);
+	seq_printf(seq, "mux: %ld reg: 0x%04x", (value & PAD_MUX), value);
+}
+
+/* use IO high level output current as the table */
+static struct spacemit_pin_drv_strength spacemit_ds_1v8_tbl[4] = {
+	{ 0, 11 },
+	{ 2, 21 },
+	{ 4, 32 },
+	{ 6, 42 },
+};
+
+static struct spacemit_pin_drv_strength spacemit_ds_3v3_tbl[8] = {
+	{ 0,  7 },
+	{ 2, 10 },
+	{ 4, 13 },
+	{ 6, 16 },
+	{ 1, 19 },
+	{ 3, 23 },
+	{ 5, 26 },
+	{ 7, 29 },
+};
+
+static inline u8 spacemit_get_ds_value(struct spacemit_pin_drv_strength *tbl,
+				       u32 num, u32 mA)
+{
+	int i;
+
+	for (i = 0; i < num; i++)
+		if (mA <= tbl[i].mA)
+			return tbl[i].val;
+
+	return tbl[num - 1].val;
+}
+
+static inline u32 spacemit_get_ds_mA(struct spacemit_pin_drv_strength *tbl,
+				     u32 num, u32 val)
+{
+	int i;
+
+	for (i = 0; i < num; i++)
+		if (val == tbl[i].val)
+			return tbl[i].mA;
+
+	return 0;
+}
+
+static inline u8 spacemit_get_driver_strength(enum spacemit_pin_io_type type,
+					      u32 mA)
+{
+	switch (type) {
+	case IO_TYPE_1V8:
+		return spacemit_get_ds_value(spacemit_ds_1v8_tbl,
+					     ARRAY_SIZE(spacemit_ds_1v8_tbl),
+					     mA);
+	case IO_TYPE_3V3:
+		return spacemit_get_ds_value(spacemit_ds_3v3_tbl,
+					     ARRAY_SIZE(spacemit_ds_3v3_tbl),
+					     mA);
+	default:
+		return 0;
+	}
+}
+
+static inline u32 spacemit_get_drive_strength_mA(enum spacemit_pin_io_type type,
+						 u32 value)
+{
+	switch (type) {
+	case IO_TYPE_1V8:
+		return spacemit_get_ds_mA(spacemit_ds_1v8_tbl,
+					  ARRAY_SIZE(spacemit_ds_1v8_tbl),
+					  value & 0x6);
+	case IO_TYPE_3V3:
+		return spacemit_get_ds_mA(spacemit_ds_3v3_tbl,
+					  ARRAY_SIZE(spacemit_ds_3v3_tbl),
+					  value);
+	default:
+		return 0;
+	}
+}
+
+static int spacemit_pctrl_check_power(struct pinctrl_dev *pctldev,
+				      struct device_node *dn,
+				      struct spacemit_pin_mux_config *pinmuxs,
+				      int num_pins, const char *grpname)
+{
+	struct spacemit_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
+	struct device *dev = pctrl->dev;
+	enum spacemit_pin_io_type type;
+	u32 power = 0, i;
+
+	of_property_read_u32(dn, "power-source", &power);
+
+	for (i = 0; i < num_pins; i++) {
+		type = spacemit_to_pin_io_type(pinmuxs[i].pin);
+
+		if (type != IO_TYPE_EXTERNAL)
+			continue;
+
+		switch (power) {
+		case PIN_POWER_STATE_1V8:
+		case PIN_POWER_STATE_3V3:
+			break;
+		default:
+			dev_err(dev, "group %s has unsupported power\n",
+				grpname);
+			return -ENOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static int spacemit_pctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
+					 struct device_node *np,
+					 struct pinctrl_map **maps,
+					 unsigned int *num_maps)
+{
+	struct spacemit_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
+	struct device *dev = pctrl->dev;
+	struct device_node *child;
+	struct pinctrl_map *map;
+	const char **grpnames;
+	const char *grpname;
+	int ngroups = 0;
+	int nmaps = 0;
+	int ret;
+
+	for_each_available_child_of_node(np, child)
+		ngroups += 1;
+
+	grpnames = devm_kcalloc(dev, ngroups, sizeof(*grpnames), GFP_KERNEL);
+	if (!grpnames)
+		return -ENOMEM;
+
+	map = devm_kcalloc(dev, ngroups * 2, sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+
+	ngroups = 0;
+	guard(mutex)(&pctrl->mutex);
+	for_each_available_child_of_node_scoped(np, child) {
+		struct spacemit_pin_mux_config *pinmuxs;
+		unsigned int config, *pins;
+		int i, npins;
+
+		npins = of_property_count_u32_elems(child, "pinmux");
+
+		if (npins < 1) {
+			dev_err(dev, "invalid pinctrl group %pOFn.%pOFn\n",
+				np, child);
+			return -EINVAL;
+		}
+
+		grpname = devm_kasprintf(dev, GFP_KERNEL, "%pOFn.%pOFn",
+					 np, child);
+		if (!grpname)
+			return -ENOMEM;
+
+		grpnames[ngroups++] = grpname;
+
+		pins = devm_kcalloc(dev, npins, sizeof(*pins), GFP_KERNEL);
+		if (!pins)
+			return -ENOMEM;
+
+		pinmuxs = devm_kcalloc(dev, npins, sizeof(*pinmuxs), GFP_KERNEL);
+		if (!pinmuxs)
+			return -ENOMEM;
+
+		for (i = 0; i < npins; i++) {
+			ret = of_property_read_u32_index(child, "pinmux",
+							 i, &config);
+
+			if (ret)
+				return -EINVAL;
+
+			pins[i] = spacemit_dt_get_pin(config);
+			pinmuxs[i].config = config;
+			pinmuxs[i].pin = spacemit_get_pin(pctrl, pins[i]);
+
+			if (!pinmuxs[i].pin)
+				return dev_err_probe(dev, -ENODEV, "failed to get pin %d\n", pins[i]);
+		}
+
+		ret = spacemit_pctrl_check_power(pctldev, child, pinmuxs,
+						 npins, grpname);
+		if (ret < 0)
+			return ret;
+
+		map[nmaps].type = PIN_MAP_TYPE_MUX_GROUP;
+		map[nmaps].data.mux.function = np->name;
+		map[nmaps].data.mux.group = grpname;
+		nmaps += 1;
+
+		ret = pinctrl_generic_add_group(pctldev, grpname,
+						pins, npins, pinmuxs);
+		if (ret < 0)
+			return dev_err_probe(dev, ret, "failed to add group %s: %d\n", grpname, ret);
+
+		ret = pinconf_generic_parse_dt_config(child, pctldev,
+						      &map[nmaps].data.configs.configs,
+						      &map[nmaps].data.configs.num_configs);
+		if (ret)
+			return dev_err_probe(dev, ret, "failed to parse pin config of group %s\n",
+				grpname);
+
+		if (map[nmaps].data.configs.num_configs == 0)
+			continue;
+
+		map[nmaps].type = PIN_MAP_TYPE_CONFIGS_GROUP;
+		map[nmaps].data.configs.group_or_pin = grpname;
+		nmaps += 1;
+	}
+
+	ret = pinmux_generic_add_function(pctldev, np->name,
+					  grpnames, ngroups, NULL);
+	if (ret < 0) {
+		pinctrl_utils_free_map(pctldev, map, nmaps);
+		return dev_err_probe(dev, ret, "error adding function %s\n", np->name);
+	}
+
+	*maps = map;
+	*num_maps = nmaps;
+
+	return 0;
+}
+
+static const struct pinctrl_ops spacemit_pctrl_ops = {
+	.get_groups_count	= pinctrl_generic_get_group_count,
+	.get_group_name		= pinctrl_generic_get_group_name,
+	.get_group_pins		= pinctrl_generic_get_group_pins,
+	.pin_dbg_show		= spacemit_pctrl_dbg_show,
+	.dt_node_to_map		= spacemit_pctrl_dt_node_to_map,
+	.dt_free_map		= pinctrl_utils_free_map,
+};
+
+static int spacemit_pmx_set_mux(struct pinctrl_dev *pctldev,
+				unsigned int fsel, unsigned int gsel)
+{
+	struct spacemit_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
+	const struct group_desc *group;
+	const struct spacemit_pin_mux_config *configs;
+	unsigned int i, mux;
+	void __iomem *reg;
+
+	group = pinctrl_generic_get_group(pctldev, gsel);
+	if (!group)
+		return -EINVAL;
+
+	configs = group->data;
+
+	for (i = 0; i < group->grp.npins; i++) {
+		const struct spacemit_pin *spin = configs[i].pin;
+		u32 value = configs[i].config;
+
+		reg = spacemit_pin_to_reg(pctrl, spin->pin);
+		mux = spacemit_dt_get_pin_mux(value);
+
+		guard(raw_spinlock_irqsave)(&pctrl->lock);
+		value = readl_relaxed(reg) & ~PAD_MUX;
+		writel_relaxed(mux | value, reg);
+	}
+
+	return 0;
+}
+
+static int spacemit_request_gpio(struct pinctrl_dev *pctldev,
+				 struct pinctrl_gpio_range *range,
+				 unsigned int pin)
+{
+	struct spacemit_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
+	const struct spacemit_pin *spin = spacemit_get_pin(pctrl, pin);
+	void __iomem *reg;
+
+	reg = spacemit_pin_to_reg(pctrl, pin);
+	guard(raw_spinlock_irqsave)(&pctrl->lock);
+	writel_relaxed(spin->gpiofunc, reg);
+
+	return 0;
+}
+
+static const struct pinmux_ops spacemit_pmx_ops = {
+	.get_functions_count	= pinmux_generic_get_function_count,
+	.get_function_name	= pinmux_generic_get_function_name,
+	.get_function_groups	= pinmux_generic_get_function_groups,
+	.set_mux		= spacemit_pmx_set_mux,
+	.gpio_request_enable	= spacemit_request_gpio,
+	.strict			= true,
+};
+
+static int spacemit_pinconf_get(struct pinctrl_dev *pctldev,
+				unsigned int pin, unsigned long *config)
+{
+	struct spacemit_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
+	int param = pinconf_to_config_param(*config);
+	u32 value, arg = 0;
+
+	if (!pin)
+		return -EINVAL;
+
+	value = readl(spacemit_pin_to_reg(pctrl, pin));
+
+	switch (param) {
+	case PIN_CONFIG_SLEW_RATE:
+		if (FIELD_GET(PAD_SLEW_RATE_EN, value))
+			arg = FIELD_GET(PAD_SLEW_RATE, value) + 2;
+		else
+			arg = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*config = pinconf_to_config_packed(param, arg);
+
+	return 0;
+}
+
+#define ENABLE_DRV_STRENGTH	BIT(1)
+#define ENABLE_SLEW_RATE	BIT(2)
+static int spacemit_pinconf_generate_config(const struct spacemit_pin *spin,
+					    unsigned long *configs,
+					    unsigned int num_configs,
+					    u32 *value)
+{
+	enum spacemit_pin_io_type type;
+	int i, param;
+	u32 v = 0, voltage = 0, arg, val;
+	u32 flag = 0, drv_strength, slew_rate;
+
+	if (!spin)
+		return -EINVAL;
+
+	for (i = 0; i < num_configs; i++) {
+		param = pinconf_to_config_param(configs[i]);
+		arg = pinconf_to_config_argument(configs[i]);
+
+		switch (param) {
+		case PIN_CONFIG_BIAS_DISABLE:
+			v &= ~(PAD_PULL_EN | PAD_PULLDOWN | PAD_PULLUP);
+			v &= ~PAD_STRONG_PULL;
+			break;
+		case PIN_CONFIG_BIAS_PULL_DOWN:
+			v &= ~(PAD_PULLUP | PAD_STRONG_PULL);
+			v |= (PAD_PULL_EN | PAD_PULLDOWN);
+			break;
+		case PIN_CONFIG_BIAS_PULL_UP:
+			v &= ~PAD_PULLDOWN;
+			v |= (PAD_PULL_EN | PAD_PULLUP);
+
+			if (arg == 1)
+				v |= PAD_STRONG_PULL;
+			break;
+		case PIN_CONFIG_DRIVE_STRENGTH:
+			flag |= ENABLE_DRV_STRENGTH;
+			drv_strength = arg;
+			break;
+		case PIN_CONFIG_INPUT_SCHMITT:
+			v &= ~PAD_SCHMITT;
+			v |= FIELD_PREP(PAD_SCHMITT, arg);
+			break;
+		case PIN_CONFIG_POWER_SOURCE:
+			voltage = arg;
+			break;
+		case PIN_CONFIG_SLEW_RATE:
+			if (arg) {
+				flag |= ENABLE_SLEW_RATE;
+				v |= PAD_SLEW_RATE_EN;
+				slew_rate = arg;
+			} else {
+				v &= ~PAD_SLEW_RATE_EN;
+			}
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	if (flag & ENABLE_DRV_STRENGTH) {
+		type = spacemit_to_pin_io_type(spin);
+
+		/* fix external io type */
+		if (type == IO_TYPE_EXTERNAL) {
+			switch (voltage) {
+			case 1800:
+				type = IO_TYPE_1V8;
+				break;
+			case 3300:
+				type = IO_TYPE_3V3;
+				break;
+			default:
+				return -EINVAL;
+			}
+		}
+
+		val = spacemit_get_driver_strength(type, drv_strength);
+
+		v &= ~PAD_DRIVE;
+		v |= FIELD_PREP(PAD_DRIVE, val);
+	}
+
+	if (flag & ENABLE_SLEW_RATE) {
+		/* check, driver strength & slew rate */
+		if (flag & ENABLE_DRV_STRENGTH) {
+			val = FIELD_GET(PAD_SLEW_RATE, v) + 2;
+			if (slew_rate > 1 && slew_rate != val) {
+				pr_err("slew rate conflict with drive strength\n");
+				return -EINVAL;
+			}
+		} else {
+			v &= ~PAD_SLEW_RATE;
+			slew_rate = slew_rate > 1 ? (slew_rate - 2) : 0;
+			v |= FIELD_PREP(PAD_SLEW_RATE, slew_rate);
+		}
+	}
+
+	*value = v;
+
+	return 0;
+}
+
+static int spacemit_pin_set_config(struct spacemit_pinctrl *pctrl,
+				   unsigned int pin, u32 value)
+{
+	const struct spacemit_pin *spin = spacemit_get_pin(pctrl, pin);
+	void __iomem *reg;
+	unsigned int mux;
+
+	if (!pin)
+		return -EINVAL;
+
+	reg = spacemit_pin_to_reg(pctrl, spin->pin);
+
+	guard(raw_spinlock_irqsave)(&pctrl->lock);
+	mux = readl_relaxed(reg) & PAD_MUX;
+	writel_relaxed(mux | value, reg);
+
+	return 0;
+}
+
+static int spacemit_pinconf_set(struct pinctrl_dev *pctldev,
+				unsigned int pin, unsigned long *configs,
+				unsigned int num_configs)
+{
+	struct spacemit_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
+	const struct spacemit_pin *spin = spacemit_get_pin(pctrl, pin);
+	u32 value;
+
+	if (spacemit_pinconf_generate_config(spin, configs, num_configs, &value))
+		return -EINVAL;
+
+	return spacemit_pin_set_config(pctrl, pin, value);
+}
+
+static int spacemit_pinconf_group_set(struct pinctrl_dev *pctldev,
+				      unsigned int gsel,
+				      unsigned long *configs,
+				      unsigned int num_configs)
+{
+	struct spacemit_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
+	const struct spacemit_pin *spin;
+	const struct group_desc *group;
+	u32 value;
+	int i;
+
+	group = pinctrl_generic_get_group(pctldev, gsel);
+	if (!group)
+		return -EINVAL;
+
+	spin = spacemit_get_pin(pctrl, group->grp.pins[0]);
+	if (spacemit_pinconf_generate_config(spin, configs, num_configs, &value))
+		return -EINVAL;
+
+	for (i = 0; i < group->grp.npins; i++)
+		spacemit_pin_set_config(pctrl, group->grp.pins[i], value);
+
+	return 0;
+}
+
+static void spacemit_pinconf_dbg_pull(struct seq_file *seq, unsigned int value)
+{
+	u32 normal, strong;
+
+	if (!FIELD_GET(PAD_PULL_EN, value)) {
+		seq_puts(seq, ", bias pull disabled");
+		return;
+	}
+
+	if (FIELD_GET(PAD_PULLDOWN, value))
+		seq_puts(seq, ", bias pull down");
+
+	normal = FIELD_GET(PAD_PULLUP, value);
+	strong = FIELD_GET(PAD_STRONG_PULL, value);
+
+	if (normal && strong)
+		seq_puts(seq, ", bias strong pull up");
+	else if (normal)
+		seq_puts(seq, ", bias normal pull up");
+}
+
+static void spacemit_pinconf_dbg_show(struct pinctrl_dev *pctldev,
+				      struct seq_file *seq, unsigned int pin)
+{
+	struct spacemit_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
+	const struct spacemit_pin *spin = spacemit_get_pin(pctrl, pin);
+	enum spacemit_pin_io_type type = spacemit_to_pin_io_type(spin);
+	void __iomem *reg = spacemit_pin_to_reg(pctrl, pin);
+	u32 value, tmp, mA;
+
+	value = readl(reg);
+	spacemit_pinconf_dbg_pull(seq, value);
+
+	seq_printf(seq, ", io type (%s)", io_type_desc[type]);
+
+	tmp = FIELD_GET(PAD_DRIVE, value);
+	if (type == IO_TYPE_1V8 || type == IO_TYPE_3V3) {
+		mA = spacemit_get_drive_strength_mA(type, tmp);
+		seq_printf(seq, ", drive strength (%d mA)", mA);
+	}
+
+	/* drive strength depend on power source, so show all values */
+	if (type == IO_TYPE_EXTERNAL)
+		seq_printf(seq, ", drive strength (%d or %d mA)",
+			   spacemit_get_drive_strength_mA(IO_TYPE_1V8, tmp),
+			   spacemit_get_drive_strength_mA(IO_TYPE_3V3, tmp));
+
+	seq_printf(seq, ", register (0x%04x)\n", value);
+}
+
+static const struct pinconf_ops spacemit_pinconf_ops = {
+	.pin_config_get			= spacemit_pinconf_get,
+	.pin_config_set			= spacemit_pinconf_set,
+	.pin_config_group_set		= spacemit_pinconf_group_set,
+	.pin_config_dbg_show		= spacemit_pinconf_dbg_show,
+	.is_generic			= true,
+};
+
+static int spacemit_pinctrl_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct spacemit_pinctrl *pctrl;
+	const struct spacemit_pinctrl_data *pctrl_data;
+	int ret;
+
+	pctrl_data = device_get_match_data(dev);
+	if (!pctrl_data)
+		return -ENODEV;
+
+	if (pctrl_data->npins == 0)
+		return dev_err_probe(dev, -EINVAL, "invalid pin data\n");
+
+	pctrl = devm_kzalloc(dev, sizeof(*pctrl), GFP_KERNEL);
+	if (!pctrl)
+		return -ENOMEM;
+
+	pctrl->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(pctrl->regs))
+		return PTR_ERR(pctrl->regs);
+
+	pctrl->pdesc.name = dev_name(dev);
+	pctrl->pdesc.pins = pctrl_data->pins;
+	pctrl->pdesc.npins = pctrl_data->npins;
+	pctrl->pdesc.pctlops = &spacemit_pctrl_ops;
+	pctrl->pdesc.pmxops = &spacemit_pmx_ops;
+	pctrl->pdesc.confops = &spacemit_pinconf_ops;
+	pctrl->pdesc.owner = THIS_MODULE;
+
+	pctrl->data = pctrl_data;
+	pctrl->dev = dev;
+	raw_spin_lock_init(&pctrl->lock);
+	mutex_init(&pctrl->mutex);
+
+	platform_set_drvdata(pdev, pctrl);
+
+	ret = devm_pinctrl_register_and_init(dev, &pctrl->pdesc,
+					     pctrl, &pctrl->pctl_dev);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "fail to register pinctrl driver\n");
+
+	return pinctrl_enable(pctrl->pctl_dev);
+}
+
+static const struct pinctrl_pin_desc k1_pin_desc[] = {
+	PINCTRL_PIN(0, "GPIO_00"),
+	PINCTRL_PIN(1, "GPIO_01"),
+	PINCTRL_PIN(2, "GPIO_02"),
+	PINCTRL_PIN(3, "GPIO_03"),
+	PINCTRL_PIN(4, "GPIO_04"),
+	PINCTRL_PIN(5, "GPIO_05"),
+	PINCTRL_PIN(6, "GPIO_06"),
+	PINCTRL_PIN(7, "GPIO_07"),
+	PINCTRL_PIN(8, "GPIO_08"),
+	PINCTRL_PIN(9, "GPIO_09"),
+	PINCTRL_PIN(10, "GPIO_10"),
+	PINCTRL_PIN(11, "GPIO_11"),
+	PINCTRL_PIN(12, "GPIO_12"),
+	PINCTRL_PIN(13, "GPIO_13"),
+	PINCTRL_PIN(14, "GPIO_14"),
+	PINCTRL_PIN(15, "GPIO_15"),
+	PINCTRL_PIN(16, "GPIO_16"),
+	PINCTRL_PIN(17, "GPIO_17"),
+	PINCTRL_PIN(18, "GPIO_18"),
+	PINCTRL_PIN(19, "GPIO_19"),
+	PINCTRL_PIN(20, "GPIO_20"),
+	PINCTRL_PIN(21, "GPIO_21"),
+	PINCTRL_PIN(22, "GPIO_22"),
+	PINCTRL_PIN(23, "GPIO_23"),
+	PINCTRL_PIN(24, "GPIO_24"),
+	PINCTRL_PIN(25, "GPIO_25"),
+	PINCTRL_PIN(26, "GPIO_26"),
+	PINCTRL_PIN(27, "GPIO_27"),
+	PINCTRL_PIN(28, "GPIO_28"),
+	PINCTRL_PIN(29, "GPIO_29"),
+	PINCTRL_PIN(30, "GPIO_30"),
+	PINCTRL_PIN(31, "GPIO_31"),
+	PINCTRL_PIN(32, "GPIO_32"),
+	PINCTRL_PIN(33, "GPIO_33"),
+	PINCTRL_PIN(34, "GPIO_34"),
+	PINCTRL_PIN(35, "GPIO_35"),
+	PINCTRL_PIN(36, "GPIO_36"),
+	PINCTRL_PIN(37, "GPIO_37"),
+	PINCTRL_PIN(38, "GPIO_38"),
+	PINCTRL_PIN(39, "GPIO_39"),
+	PINCTRL_PIN(40, "GPIO_40"),
+	PINCTRL_PIN(41, "GPIO_41"),
+	PINCTRL_PIN(42, "GPIO_42"),
+	PINCTRL_PIN(43, "GPIO_43"),
+	PINCTRL_PIN(44, "GPIO_44"),
+	PINCTRL_PIN(45, "GPIO_45"),
+	PINCTRL_PIN(46, "GPIO_46"),
+	PINCTRL_PIN(47, "GPIO_47"),
+	PINCTRL_PIN(48, "GPIO_48"),
+	PINCTRL_PIN(49, "GPIO_49"),
+	PINCTRL_PIN(50, "GPIO_50"),
+	PINCTRL_PIN(51, "GPIO_51"),
+	PINCTRL_PIN(52, "GPIO_52"),
+	PINCTRL_PIN(53, "GPIO_53"),
+	PINCTRL_PIN(54, "GPIO_54"),
+	PINCTRL_PIN(55, "GPIO_55"),
+	PINCTRL_PIN(56, "GPIO_56"),
+	PINCTRL_PIN(57, "GPIO_57"),
+	PINCTRL_PIN(58, "GPIO_58"),
+	PINCTRL_PIN(59, "GPIO_59"),
+	PINCTRL_PIN(60, "GPIO_60"),
+	PINCTRL_PIN(61, "GPIO_61"),
+	PINCTRL_PIN(62, "GPIO_62"),
+	PINCTRL_PIN(63, "GPIO_63"),
+	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
+	PINCTRL_PIN(69, "GPIO_69"),
+	PINCTRL_PIN(70, "GPIO_70/PRI_DTI"),
+	PINCTRL_PIN(71, "GPIO_71/PRI_TMS"),
+	PINCTRL_PIN(72, "GPIO_72/PRI_TCK"),
+	PINCTRL_PIN(73, "GPIO_73/PRI_TDO"),
+	PINCTRL_PIN(74, "GPIO_74"),
+	PINCTRL_PIN(75, "GPIO_75"),
+	PINCTRL_PIN(76, "GPIO_76"),
+	PINCTRL_PIN(77, "GPIO_77"),
+	PINCTRL_PIN(78, "GPIO_78"),
+	PINCTRL_PIN(79, "GPIO_79"),
+	PINCTRL_PIN(80, "GPIO_80"),
+	PINCTRL_PIN(81, "GPIO_81"),
+	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
+	PINCTRL_PIN(86, "GPIO_86"),
+	PINCTRL_PIN(87, "GPIO_87"),
+	PINCTRL_PIN(88, "GPIO_88"),
+	PINCTRL_PIN(89, "GPIO_89"),
+	PINCTRL_PIN(90, "GPIO_90"),
+	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93/PWR_SCL"),
+	PINCTRL_PIN(94, "GPIO_94/PWR_SDA"),
+	PINCTRL_PIN(95, "GPIO_95/VCX0_EN"),
+	PINCTRL_PIN(96, "GPIO_96/DVL0"),
+	PINCTRL_PIN(97, "GPIO_97/DVL1"),
+	PINCTRL_PIN(98,  "GPIO_98/QSPI_DAT3"),
+	PINCTRL_PIN(99,  "GPIO_99/QSPI_DAT2"),
+	PINCTRL_PIN(100, "GPIO_100/QSPI_DAT1"),
+	PINCTRL_PIN(101, "GPIO_101/QSPI_DAT0"),
+	PINCTRL_PIN(102, "GPIO_102/QSPI_CLK"),
+	PINCTRL_PIN(103, "GPIO_103/QSPI_CS1"),
+	PINCTRL_PIN(104, "GPIO_104/MMC1_DAT3"),
+	PINCTRL_PIN(105, "GPIO_105/MMC1_DAT2"),
+	PINCTRL_PIN(106, "GPIO_106/MMC1_DAT1"),
+	PINCTRL_PIN(107, "GPIO_107/MMC1_DAT0"),
+	PINCTRL_PIN(108, "GPIO_108/MMC1_CMD"),
+	PINCTRL_PIN(109, "GPIO_109/MMC1_CLK"),
+	PINCTRL_PIN(110, "GPIO_110"),
+	PINCTRL_PIN(111, "GPIO_111"),
+	PINCTRL_PIN(112, "GPIO_112"),
+	PINCTRL_PIN(113, "GPIO_113"),
+	PINCTRL_PIN(114, "GPIO_114"),
+	PINCTRL_PIN(115, "GPIO_115"),
+	PINCTRL_PIN(116, "GPIO_116"),
+	PINCTRL_PIN(117, "GPIO_117"),
+	PINCTRL_PIN(118, "GPIO_118"),
+	PINCTRL_PIN(119, "GPIO_119"),
+	PINCTRL_PIN(120, "GPIO_120"),
+	PINCTRL_PIN(121, "GPIO_121"),
+	PINCTRL_PIN(122, "GPIO_122"),
+	PINCTRL_PIN(123, "GPIO_123"),
+	PINCTRL_PIN(124, "GPIO_124"),
+	PINCTRL_PIN(125, "GPIO_125"),
+	PINCTRL_PIN(126, "GPIO_126"),
+	PINCTRL_PIN(127, "GPIO_127"),
+};
+
+static const struct spacemit_pin k1_pin_data[ARRAY_SIZE(k1_pin_desc)] = {
+	K1_FUNC_PIN(0, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(1, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(2, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(3, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(4, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(5, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(6, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(7, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(8, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(9, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(10, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(11, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(12, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(13, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(14, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(15, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(16, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(17, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(18, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(19, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(20, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(21, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(22, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(23, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(24, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(25, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(26, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(27, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(28, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(29, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(30, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(31, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(32, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(33, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(34, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(35, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(36, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(37, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(38, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(39, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(40, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(41, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(42, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(43, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(44, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(45, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(46, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(47, 0, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(48, 0, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(49, 0, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(50, 0, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(51, 0, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(52, 0, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(53, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(54, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(55, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(56, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(57, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(58, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(59, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(60, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(61, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(62, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(63, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(64, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(65, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(66, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(67, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(68, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(69, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(70, 1, IO_TYPE_1V8),
+	K1_FUNC_PIN(71, 1, IO_TYPE_1V8),
+	K1_FUNC_PIN(72, 1, IO_TYPE_1V8),
+	K1_FUNC_PIN(73, 1, IO_TYPE_1V8),
+	K1_FUNC_PIN(74, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(75, 0, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(76, 0, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(77, 0, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(78, 0, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(79, 0, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(80, 0, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(81, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(82, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(83, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(84, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(85, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(86, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(87, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(88, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(89, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(90, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(91, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(92, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(93, 1, IO_TYPE_1V8),
+	K1_FUNC_PIN(94, 1, IO_TYPE_1V8),
+	K1_FUNC_PIN(95, 1, IO_TYPE_1V8),
+	K1_FUNC_PIN(96, 1, IO_TYPE_1V8),
+	K1_FUNC_PIN(97, 1, IO_TYPE_1V8),
+	K1_FUNC_PIN(98, 1, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(99, 1, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(100, 1, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(101, 1, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(102, 1, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(103, 1, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(104, 4, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(105, 4, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(106, 4, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(107, 4, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(108, 4, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(109, 4, IO_TYPE_EXTERNAL),
+	K1_FUNC_PIN(110, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(111, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(112, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(113, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(114, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(115, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(116, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(117, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(118, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(119, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(120, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(121, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(122, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(123, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(124, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(125, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(126, 0, IO_TYPE_1V8),
+	K1_FUNC_PIN(127, 0, IO_TYPE_1V8),
+};
+
+static const struct spacemit_pinctrl_data k1_pinctrl_data = {
+	.pins = k1_pin_desc,
+	.data = k1_pin_data,
+	.npins = ARRAY_SIZE(k1_pin_desc),
+};
+
+static const struct of_device_id k1_pinctrl_ids[] = {
+	{ .compatible = "spacemit,k1-pinctrl", .data = &k1_pinctrl_data },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, k1_pinctrl_ids);
+
+static struct platform_driver k1_pinctrl_driver = {
+	.probe	= spacemit_pinctrl_probe,
+	.driver	= {
+		.name			= "k1-pinctrl",
+		.suppress_bind_attrs	= true,
+		.of_match_table		= k1_pinctrl_ids,
+	},
+};
+module_platform_driver(k1_pinctrl_driver);
+
+MODULE_AUTHOR("Yixun Lan <dlan@gentoo.org>");
+MODULE_DESCRIPTION("Pinctrl driver for the SpacemiT K1 SoC");
+MODULE_LICENSE("GPL");
diff --git a/drivers/pinctrl/spacemit/pinctrl-k1.h b/drivers/pinctrl/spacemit/pinctrl-k1.h
new file mode 100644
index 0000000000000..16143fea469eb
--- /dev/null
+++ b/drivers/pinctrl/spacemit/pinctrl-k1.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2024 Yixun Lan <dlan@gentoo.org> */
+
+#ifndef _PINCTRL_SPACEMIT_K1_H
+#define _PINCTRL_SPACEMIT_K1_H
+
+#include <linux/bits.h>
+#include <linux/bitfield.h>
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
+#include <linux/platform_device.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinconf.h>
+
+enum spacemit_pin_io_type {
+	IO_TYPE_NONE = 0,
+	IO_TYPE_1V8,
+	IO_TYPE_3V3,
+	IO_TYPE_EXTERNAL,
+};
+
+#define PIN_POWER_STATE_1V8		1800
+#define PIN_POWER_STATE_3V3		3300
+
+#define K1_PIN_IO_TYPE		GENMASK(2, 1)
+
+#define K1_PIN_CAP_IO_TYPE(type)				\
+	FIELD_PREP_CONST(K1_PIN_IO_TYPE, type)
+#define K1_PIN_GET_IO_TYPE(val)					\
+	FIELD_GET(K1_PIN_IO_TYPE, val)
+
+#define K1_FUNC_PIN(_id, _gpiofunc, _io)			\
+	{							\
+		.pin		= (_id),			\
+		.gpiofunc	= (_gpiofunc),			\
+		.flags		= (K1_PIN_CAP_IO_TYPE(_io)),	\
+	}
+
+#endif /* _PINCTRL_SPACEMIT_K1_H */

From 335de24e5e774aa94ff9551b3194fe15f52ea1d9 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Wed, 22 Nov 2023 23:18:12 +0100
Subject: [PATCH 0513/1530] modules: Ensure 64-bit alignment on __ksymtab_*
 sections

On 64-bit architectures without CONFIG_HAVE_ARCH_PREL32_RELOCATIONS
(e.g. ppc64, ppc64le, parisc, s390x,...) the __KSYM_REF() macro stores
64-bit pointers into the __ksymtab* sections.
Make sure that those sections will be correctly aligned at module link time,
otherwise unaligned memory accesses may happen at runtime.

As per unaligned-memory-access [0] "unaligned memory accesses [...]
will not work correctly on certain platforms and will cause performance
problems on others", so fix this.

The __kcrctab* sections store 32-bit entities, so use ALIGN(4) for those.

Signed-off-by: Helge Deller <deller@gmx.de>
[mcgrof: added unaligned-memory-access justification]
Link: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/core-api/unaligned-memory-access.rst # [0]
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 scripts/module.lds.S | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/scripts/module.lds.S b/scripts/module.lds.S
index 3f43edef813cb..23f9912179cee 100644
--- a/scripts/module.lds.S
+++ b/scripts/module.lds.S
@@ -18,10 +18,10 @@ SECTIONS {
 		*(.export_symbol)
 	}
 
-	__ksymtab		0 : { *(SORT(___ksymtab+*)) }
-	__ksymtab_gpl		0 : { *(SORT(___ksymtab_gpl+*)) }
-	__kcrctab		0 : { *(SORT(___kcrctab+*)) }
-	__kcrctab_gpl		0 : { *(SORT(___kcrctab_gpl+*)) }
+	__ksymtab		0 : ALIGN(8) { *(SORT(___ksymtab+*)) }
+	__ksymtab_gpl		0 : ALIGN(8) { *(SORT(___ksymtab_gpl+*)) }
+	__kcrctab		0 : ALIGN(4) { *(SORT(___kcrctab+*)) }
+	__kcrctab_gpl		0 : ALIGN(4) { *(SORT(___kcrctab_gpl+*)) }
 
 	.ctors			0 : ALIGN(8) { *(SORT(.ctors.*)) *(.ctors) }
 	.init_array		0 : ALIGN(8) { *(SORT(.init_array.*)) *(.init_array) }

From 03ddd2f17e28fe0e53a702469b1b751d40f5efbb Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Wed, 22 Nov 2023 23:18:14 +0100
Subject: [PATCH 0514/1530] modules: Add missing entry for __ex_table

The entry for __ex_table was missing, which may make __ex_table
become 1- or 2-byte aligned in modules.
Add the entry to ensure it gets 32-bit aligned.

As per unaligned-memory-access [0] "unaligned memory accesses [...]
will not work correctly on certain platforms and will cause performance
problems on others", so fix this.

Signed-off-by: Helge Deller <deller@gmx.de>
[mcgrof: added unaligned-memory-access justification]
Link: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/core-api/unaligned-memory-access.rst # [0]
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 scripts/module.lds.S | 1 +
 1 file changed, 1 insertion(+)

diff --git a/scripts/module.lds.S b/scripts/module.lds.S
index 23f9912179cee..69b2423e27ab4 100644
--- a/scripts/module.lds.S
+++ b/scripts/module.lds.S
@@ -29,6 +29,7 @@ SECTIONS {
 	.altinstructions	0 : ALIGN(8) { KEEP(*(.altinstructions)) }
 	__bug_table		0 : ALIGN(8) { KEEP(*(__bug_table)) }
 	__jump_table		0 : ALIGN(8) { KEEP(*(__jump_table)) }
+	__ex_table		0 : ALIGN(4) { KEEP(*(__ex_table)) }
 
 	__patchable_function_entries : { *(__patchable_function_entries) }
 

From f43922162184f2bd54d87c1b5e97cf72d0dd1290 Mon Sep 17 00:00:00 2001
From: Matthew Maurer <mmaurer@google.com>
Date: Tue, 15 Oct 2024 23:16:35 +0000
Subject: [PATCH 0515/1530] module: Take const arg in validate_section_offset

`validate_section_offset` doesn't modify the info passed in. Make this
clear by adjusting the type signature.

Signed-off-by: Matthew Maurer <mmaurer@google.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 kernel/module/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index 49b9bca9de12f..1a2dd52147ba8 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1645,7 +1645,7 @@ bool __weak module_exit_section(const char *name)
 	return strstarts(name, ".exit");
 }
 
-static int validate_section_offset(struct load_info *info, Elf_Shdr *shdr)
+static int validate_section_offset(const struct load_info *info, Elf_Shdr *shdr)
 {
 #if defined(CONFIG_64BIT)
 	unsigned long long secend;

From 90f8f312db720dbabec7c6258ef580b50129cc21 Mon Sep 17 00:00:00 2001
From: Matthew Maurer <mmaurer@google.com>
Date: Tue, 15 Oct 2024 23:16:36 +0000
Subject: [PATCH 0516/1530] module: Factor out elf_validity_ehdr

Factor out verification of the ELF header and document what is checked.

Signed-off-by: Matthew Maurer <mmaurer@google.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 kernel/module/main.c | 70 +++++++++++++++++++++++++++++---------------
 1 file changed, 47 insertions(+), 23 deletions(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index 1a2dd52147ba8..59c977acfb44a 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1664,6 +1664,50 @@ static int validate_section_offset(const struct load_info *info, Elf_Shdr *shdr)
 	return 0;
 }
 
+/**
+ * elf_validity_ehdr() - Checks an ELF header for module validity
+ * @info: Load info containing the ELF header to check
+ *
+ * Checks whether an ELF header could belong to a valid module. Checks:
+ *
+ * * ELF header is within the data the user provided
+ * * ELF magic is present
+ * * It is relocatable (not final linked, not core file, etc.)
+ * * The header's machine type matches what the architecture expects.
+ * * Optional arch-specific hook for other properties
+ *   - module_elf_check_arch() is currently only used by PPC to check
+ *   ELF ABI version, but may be used by others in the future.
+ *
+ * Return: %0 if valid, %-ENOEXEC on failure.
+ */
+static int elf_validity_ehdr(const struct load_info *info)
+{
+	if (info->len < sizeof(*(info->hdr))) {
+		pr_err("Invalid ELF header len %lu\n", info->len);
+		return -ENOEXEC;
+	}
+	if (memcmp(info->hdr->e_ident, ELFMAG, SELFMAG) != 0) {
+		pr_err("Invalid ELF header magic: != %s\n", ELFMAG);
+		return -ENOEXEC;
+	}
+	if (info->hdr->e_type != ET_REL) {
+		pr_err("Invalid ELF header type: %u != %u\n",
+		       info->hdr->e_type, ET_REL);
+		return -ENOEXEC;
+	}
+	if (!elf_check_arch(info->hdr)) {
+		pr_err("Invalid architecture in ELF header: %u\n",
+		       info->hdr->e_machine);
+		return -ENOEXEC;
+	}
+	if (!module_elf_check_arch(info->hdr)) {
+		pr_err("Invalid module architecture in ELF header: %u\n",
+		       info->hdr->e_machine);
+		return -ENOEXEC;
+	}
+	return 0;
+}
+
 /*
  * Check userspace passed ELF module against our expectations, and cache
  * useful variables for further processing as we go.
@@ -1693,30 +1737,10 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 	unsigned int num_info_secs = 0, info_idx;
 	unsigned int num_sym_secs = 0, sym_idx;
 
-	if (info->len < sizeof(*(info->hdr))) {
-		pr_err("Invalid ELF header len %lu\n", info->len);
-		goto no_exec;
-	}
+	err = elf_validity_ehdr(info);
+	if (err < 0)
+		return err;
 
-	if (memcmp(info->hdr->e_ident, ELFMAG, SELFMAG) != 0) {
-		pr_err("Invalid ELF header magic: != %s\n", ELFMAG);
-		goto no_exec;
-	}
-	if (info->hdr->e_type != ET_REL) {
-		pr_err("Invalid ELF header type: %u != %u\n",
-		       info->hdr->e_type, ET_REL);
-		goto no_exec;
-	}
-	if (!elf_check_arch(info->hdr)) {
-		pr_err("Invalid architecture in ELF header: %u\n",
-		       info->hdr->e_machine);
-		goto no_exec;
-	}
-	if (!module_elf_check_arch(info->hdr)) {
-		pr_err("Invalid module architecture in ELF header: %u\n",
-		       info->hdr->e_machine);
-		goto no_exec;
-	}
 	if (info->hdr->e_shentsize != sizeof(Elf_Shdr)) {
 		pr_err("Invalid ELF section header size\n");
 		goto no_exec;

From c92aab819d56d51631f0484ed7af11d9d8ff4cb0 Mon Sep 17 00:00:00 2001
From: Matthew Maurer <mmaurer@google.com>
Date: Tue, 15 Oct 2024 23:16:37 +0000
Subject: [PATCH 0517/1530] module: Factor out elf_validity_cache_sechdrs

Factor out and document the validation of section headers.

Because we now validate all section offsets and lengths before accessing
them, we can remove the ad-hoc checks.

Signed-off-by: Matthew Maurer <mmaurer@google.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 kernel/module/main.c | 125 ++++++++++++++++++++++++++++---------------
 1 file changed, 82 insertions(+), 43 deletions(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index 59c977acfb44a..1f3a07ee59c6e 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1708,6 +1708,87 @@ static int elf_validity_ehdr(const struct load_info *info)
 	return 0;
 }
 
+/**
+ * elf_validity_cache_sechdrs() - Cache section headers if valid
+ * @info: Load info to compute section headers from
+ *
+ * Checks:
+ *
+ * * ELF header is valid (see elf_validity_ehdr())
+ * * Section headers are the size we expect
+ * * Section array fits in the user provided data
+ * * Section index 0 is NULL
+ * * Section contents are inbounds
+ *
+ * Then updates @info with a &load_info->sechdrs pointer if valid.
+ *
+ * Return: %0 if valid, negative error code if validation failed.
+ */
+static int elf_validity_cache_sechdrs(struct load_info *info)
+{
+	Elf_Shdr *sechdrs;
+	Elf_Shdr *shdr;
+	int i;
+	int err;
+
+	err = elf_validity_ehdr(info);
+	if (err < 0)
+		return err;
+
+	if (info->hdr->e_shentsize != sizeof(Elf_Shdr)) {
+		pr_err("Invalid ELF section header size\n");
+		return -ENOEXEC;
+	}
+
+	/*
+	 * e_shnum is 16 bits, and sizeof(Elf_Shdr) is
+	 * known and small. So e_shnum * sizeof(Elf_Shdr)
+	 * will not overflow unsigned long on any platform.
+	 */
+	if (info->hdr->e_shoff >= info->len
+	    || (info->hdr->e_shnum * sizeof(Elf_Shdr) >
+		info->len - info->hdr->e_shoff)) {
+		pr_err("Invalid ELF section header overflow\n");
+		return -ENOEXEC;
+	}
+
+	sechdrs = (void *)info->hdr + info->hdr->e_shoff;
+
+	/*
+	 * The code assumes that section 0 has a length of zero and
+	 * an addr of zero, so check for it.
+	 */
+	if (sechdrs[0].sh_type != SHT_NULL
+	    || sechdrs[0].sh_size != 0
+	    || sechdrs[0].sh_addr != 0) {
+		pr_err("ELF Spec violation: section 0 type(%d)!=SH_NULL or non-zero len or addr\n",
+		       sechdrs[0].sh_type);
+		return -ENOEXEC;
+	}
+
+	/* Validate contents are inbounds */
+	for (i = 1; i < info->hdr->e_shnum; i++) {
+		shdr = &sechdrs[i];
+		switch (shdr->sh_type) {
+		case SHT_NULL:
+		case SHT_NOBITS:
+			/* No contents, offset/size don't mean anything */
+			continue;
+		default:
+			err = validate_section_offset(info, shdr);
+			if (err < 0) {
+				pr_err("Invalid ELF section in module (section %u type %u)\n",
+				       i, shdr->sh_type);
+				return err;
+			}
+		}
+	}
+
+	info->sechdrs = sechdrs;
+
+	return 0;
+}
+
 /*
  * Check userspace passed ELF module against our expectations, and cache
  * useful variables for further processing as we go.
@@ -1737,29 +1818,10 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 	unsigned int num_info_secs = 0, info_idx;
 	unsigned int num_sym_secs = 0, sym_idx;
 
-	err = elf_validity_ehdr(info);
+	err = elf_validity_cache_sechdrs(info);
 	if (err < 0)
 		return err;
 
-	if (info->hdr->e_shentsize != sizeof(Elf_Shdr)) {
-		pr_err("Invalid ELF section header size\n");
-		goto no_exec;
-	}
-
-	/*
-	 * e_shnum is 16 bits, and sizeof(Elf_Shdr) is
-	 * known and small. So e_shnum * sizeof(Elf_Shdr)
-	 * will not overflow unsigned long on any platform.
-	 */
-	if (info->hdr->e_shoff >= info->len
-	    || (info->hdr->e_shnum * sizeof(Elf_Shdr) >
-		info->len - info->hdr->e_shoff)) {
-		pr_err("Invalid ELF section header overflow\n");
-		goto no_exec;
-	}
-
-	info->sechdrs = (void *)info->hdr + info->hdr->e_shoff;
-
 	/*
 	 * Verify if the section name table index is valid.
 	 */
@@ -1772,11 +1834,6 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 	}
 
 	strhdr = &info->sechdrs[info->hdr->e_shstrndx];
-	err = validate_section_offset(info, strhdr);
-	if (err < 0) {
-		pr_err("Invalid ELF section hdr(type %u)\n", strhdr->sh_type);
-		return err;
-	}
 
 	/*
 	 * The section name table must be NUL-terminated, as required
@@ -1793,18 +1850,6 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 		goto no_exec;
 	}
 
-	/*
-	 * The code assumes that section 0 has a length of zero and
-	 * an addr of zero, so check for it.
-	 */
-	if (info->sechdrs[0].sh_type != SHT_NULL
-	    || info->sechdrs[0].sh_size != 0
-	    || info->sechdrs[0].sh_addr != 0) {
-		pr_err("ELF Spec violation: section 0 type(%d)!=SH_NULL or non-zero len or addr\n",
-		       info->sechdrs[0].sh_type);
-		goto no_exec;
-	}
-
 	for (i = 1; i < info->hdr->e_shnum; i++) {
 		shdr = &info->sechdrs[i];
 		switch (shdr->sh_type) {
@@ -1823,12 +1868,6 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 			sym_idx = i;
 			fallthrough;
 		default:
-			err = validate_section_offset(info, shdr);
-			if (err < 0) {
-				pr_err("Invalid ELF section in module (section %u type %u)\n",
-					i, shdr->sh_type);
-				return err;
-			}
 			if (strcmp(info->secstrings + shdr->sh_name,
 				   ".gnu.linkonce.this_module") == 0) {
 				num_mod_secs++;

From 3c5700aeabd87e81d9153a7666b28d0e405c6c88 Mon Sep 17 00:00:00 2001
From: Matthew Maurer <mmaurer@google.com>
Date: Tue, 15 Oct 2024 23:16:38 +0000
Subject: [PATCH 0518/1530] module: Factor out elf_validity_cache_secstrings

Factor out the validation of section names.

There are two behavioral changes:

1. Previously, we did not validate non-SHF_ALLOC sections.
   This may have once been safe, as find_sec skips non-SHF_ALLOC
   sections, but find_any_sec, which will be used to load BTF if that is
   enabled, ignores the SHF_ALLOC flag. Since there's no need to support
   invalid section names, validate all of them, not just SHF_ALLOC
   sections.
2. Section names were validated *after* accessing them for the purposes
   of detecting ".modinfo" and ".gnu.linkonce.this_module". They are now
   checked prior to the access, which could avoid bad accesses with
   malformed modules.

Signed-off-by: Matthew Maurer <mmaurer@google.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 kernel/module/main.c | 106 ++++++++++++++++++++++++++++---------------
 1 file changed, 69 insertions(+), 37 deletions(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index 1f3a07ee59c6e..6a9159afca020 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1789,6 +1789,71 @@ static int elf_validity_cache_sechdrs(struct load_info *info)
 	return 0;
 }
 
+/**
+ * elf_validity_cache_secstrings() - Caches section names if valid
+ * @info: Load info to cache section names from. Must have valid sechdrs.
+ *
+ * Specifically checks:
+ *
+ * * Section name table index is inbounds of section headers
+ * * Section name table is not empty
+ * * Section name table is NUL terminated
+ * * All section name offsets are inbounds of the section
+ *
+ * Then updates @info with a &load_info->secstrings pointer if valid.
+ *
+ * Return: %0 if valid, negative error code if validation failed.
+ */
+static int elf_validity_cache_secstrings(struct load_info *info)
+{
+	Elf_Shdr *strhdr, *shdr;
+	char *secstrings;
+	int i;
+
+	/*
+	 * Verify if the section name table index is valid.
+	 */
+	if (info->hdr->e_shstrndx == SHN_UNDEF
+	    || info->hdr->e_shstrndx >= info->hdr->e_shnum) {
+		pr_err("Invalid ELF section name index: %d || e_shstrndx (%d) >= e_shnum (%d)\n",
+		       info->hdr->e_shstrndx, info->hdr->e_shstrndx,
+		       info->hdr->e_shnum);
+		return -ENOEXEC;
+	}
+
+	strhdr = &info->sechdrs[info->hdr->e_shstrndx];
+
+	/*
+	 * The section name table must be NUL-terminated, as required
+	 * by the spec. This makes strcmp and pr_* calls that access
+	 * strings in the section safe.
+	 */
+	secstrings = (void *)info->hdr + strhdr->sh_offset;
+	if (strhdr->sh_size == 0) {
+		pr_err("empty section name table\n");
+		return -ENOEXEC;
+	}
+	if (secstrings[strhdr->sh_size - 1] != '\0') {
+		pr_err("ELF Spec violation: section name table isn't null terminated\n");
+		return -ENOEXEC;
+	}
+
+	for (i = 0; i < info->hdr->e_shnum; i++) {
+		shdr = &info->sechdrs[i];
+		/* SHT_NULL means sh_name has an undefined value */
+		if (shdr->sh_type == SHT_NULL)
+			continue;
+		if (shdr->sh_name >= strhdr->sh_size) {
+			pr_err("Invalid ELF section name in module (section %u type %u)\n",
+			       i, shdr->sh_type);
+			return -ENOEXEC;
+		}
+	}
+
+	info->secstrings = secstrings;
+	return 0;
+}
+
 /*
  * Check userspace passed ELF module against our expectations, and cache
  * useful variables for further processing as we go.
@@ -1812,7 +1877,7 @@ static int elf_validity_cache_sechdrs(struct load_info *info)
 static int elf_validity_cache_copy(struct load_info *info, int flags)
 {
 	unsigned int i;
-	Elf_Shdr *shdr, *strhdr;
+	Elf_Shdr *shdr;
 	int err;
 	unsigned int num_mod_secs = 0, mod_idx;
 	unsigned int num_info_secs = 0, info_idx;
@@ -1821,34 +1886,9 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 	err = elf_validity_cache_sechdrs(info);
 	if (err < 0)
 		return err;
-
-	/*
-	 * Verify if the section name table index is valid.
-	 */
-	if (info->hdr->e_shstrndx == SHN_UNDEF
-	    || info->hdr->e_shstrndx >= info->hdr->e_shnum) {
-		pr_err("Invalid ELF section name index: %d || e_shstrndx (%d) >= e_shnum (%d)\n",
-		       info->hdr->e_shstrndx, info->hdr->e_shstrndx,
-		       info->hdr->e_shnum);
-		goto no_exec;
-	}
-
-	strhdr = &info->sechdrs[info->hdr->e_shstrndx];
-
-	/*
-	 * The section name table must be NUL-terminated, as required
-	 * by the spec. This makes strcmp and pr_* calls that access
-	 * strings in the section safe.
-	 */
-	info->secstrings = (void *)info->hdr + strhdr->sh_offset;
-	if (strhdr->sh_size == 0) {
-		pr_err("empty section name table\n");
-		goto no_exec;
-	}
-	if (info->secstrings[strhdr->sh_size - 1] != '\0') {
-		pr_err("ELF Spec violation: section name table isn't null terminated\n");
-		goto no_exec;
-	}
+	err = elf_validity_cache_secstrings(info);
+	if (err < 0)
+		return err;
 
 	for (i = 1; i < info->hdr->e_shnum; i++) {
 		shdr = &info->sechdrs[i];
@@ -1877,14 +1917,6 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 				num_info_secs++;
 				info_idx = i;
 			}
-
-			if (shdr->sh_flags & SHF_ALLOC) {
-				if (shdr->sh_name >= strhdr->sh_size) {
-					pr_err("Invalid ELF section name in module (section %u type %u)\n",
-					       i, shdr->sh_type);
-					return -ENOEXEC;
-				}
-			}
 			break;
 		}
 	}

From fbc0e4e482aac7f2b0d20f0a11f6d5eeda346fda Mon Sep 17 00:00:00 2001
From: Matthew Maurer <mmaurer@google.com>
Date: Tue, 15 Oct 2024 23:16:39 +0000
Subject: [PATCH 0519/1530] module: Factor out elf_validity_cache_index_info

Centralize .modinfo detection and property validation.

Signed-off-by: Matthew Maurer <mmaurer@google.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 kernel/module/main.c | 82 ++++++++++++++++++++++++++++++++++++--------
 1 file changed, 68 insertions(+), 14 deletions(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index 6a9159afca020..511d645ac577d 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -195,6 +195,38 @@ static unsigned int find_sec(const struct load_info *info, const char *name)
 	return 0;
 }
 
+/**
+ * find_any_unique_sec() - Find a unique section index by name
+ * @info: Load info for the module to scan
+ * @name: Name of the section we're looking for
+ *
+ * Locates a unique section by name. Ignores SHF_ALLOC.
+ *
+ * Return: Section index if found uniquely, zero if absent, negative count
+ *         of total instances if multiple were found.
+ */
+static int find_any_unique_sec(const struct load_info *info, const char *name)
+{
+	unsigned int idx;
+	unsigned int count = 0;
+	int i;
+
+	for (i = 1; i < info->hdr->e_shnum; i++) {
+		if (strcmp(info->secstrings + info->sechdrs[i].sh_name,
+			   name) == 0) {
+			count++;
+			idx = i;
+		}
+	}
+	if (count == 1) {
+		return idx;
+	} else if (count == 0) {
+		return 0;
+	} else {
+		return -count;
+	}
+}
+
 /* Find a module section, or NULL. */
 static void *section_addr(const struct load_info *info, const char *name)
 {
@@ -1854,6 +1886,39 @@ static int elf_validity_cache_secstrings(struct load_info *info)
 	return 0;
 }
 
+/**
+ * elf_validity_cache_index_info() - Validate and cache modinfo section
+ * @info: Load info to populate the modinfo index on.
+ *        Must have &load_info->sechdrs and &load_info->secstrings populated
+ *
+ * Checks that if there is a .modinfo section, it is unique.
+ * Then, it caches its index in &load_info->index.info.
+ * Finally, it tries to populate the name to improve error messages.
+ *
+ * Return: %0 if valid, %-ENOEXEC if multiple modinfo sections were found.
+ */
+static int elf_validity_cache_index_info(struct load_info *info)
+{
+	int info_idx;
+
+	info_idx = find_any_unique_sec(info, ".modinfo");
+
+	if (info_idx == 0)
+		/* Early return, no .modinfo */
+		return 0;
+
+	if (info_idx < 0) {
+		pr_err("Only one .modinfo section must exist.\n");
+		return -ENOEXEC;
+	}
+
+	info->index.info = info_idx;
+	/* Try to find a name early so we can log errors with a module name */
+	info->name = get_modinfo(info, "name");
+
+	return 0;
+}
+
 /*
  * Check userspace passed ELF module against our expectations, and cache
  * useful variables for further processing as we go.
@@ -1880,13 +1945,15 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 	Elf_Shdr *shdr;
 	int err;
 	unsigned int num_mod_secs = 0, mod_idx;
-	unsigned int num_info_secs = 0, info_idx;
 	unsigned int num_sym_secs = 0, sym_idx;
 
 	err = elf_validity_cache_sechdrs(info);
 	if (err < 0)
 		return err;
 	err = elf_validity_cache_secstrings(info);
+	if (err < 0)
+		return err;
+	err = elf_validity_cache_index_info(info);
 	if (err < 0)
 		return err;
 
@@ -1912,24 +1979,11 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 				   ".gnu.linkonce.this_module") == 0) {
 				num_mod_secs++;
 				mod_idx = i;
-			} else if (strcmp(info->secstrings + shdr->sh_name,
-				   ".modinfo") == 0) {
-				num_info_secs++;
-				info_idx = i;
 			}
 			break;
 		}
 	}
 
-	if (num_info_secs > 1) {
-		pr_err("Only one .modinfo section must exist.\n");
-		goto no_exec;
-	} else if (num_info_secs == 1) {
-		/* Try to find a name early so we can log errors with a module name */
-		info->index.info = info_idx;
-		info->name = get_modinfo(info, "name");
-	}
-
 	if (num_sym_secs != 1) {
 		pr_warn("%s: module has no symbols (stripped?)\n",
 			info->name ?: "(missing .modinfo section or name field)");

From 0be41a9367d1fbb16b4b57d81082341af114bad7 Mon Sep 17 00:00:00 2001
From: Matthew Maurer <mmaurer@google.com>
Date: Tue, 15 Oct 2024 23:16:40 +0000
Subject: [PATCH 0520/1530] module: Factor out elf_validity_cache_index_mod

Centralize .gnu.linkonce.this_module detection and property validation.

Signed-off-by: Matthew Maurer <mmaurer@google.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 kernel/module/main.c | 129 ++++++++++++++++++++++---------------------
 1 file changed, 67 insertions(+), 62 deletions(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index 511d645ac577d..ec638187ffcf8 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1919,6 +1919,68 @@ static int elf_validity_cache_index_info(struct load_info *info)
 	return 0;
 }
 
+/**
+ * elf_validity_cache_index_mod() - Validates and caches this_module section
+ * @info: Load info to cache this_module on.
+ *        Must have &load_info->sechdrs and &load_info->secstrings populated
+ *
+ * The ".gnu.linkonce.this_module" ELF section is special. It is what modpost
+ * uses to refer to __this_module and let's use rely on THIS_MODULE to point
+ * to &__this_module properly. The kernel's modpost declares it on each
+ * modules's *.mod.c file. If the struct module of the kernel changes a full
+ * kernel rebuild is required.
+ *
+ * We have a few expectations for this special section, this function
+ * validates all this for us:
+ *
+ * * The section has contents
+ * * The section is unique
+ * * We expect the kernel to always have to allocate it: SHF_ALLOC
+ * * The section size must match the kernel's run time's struct module
+ *   size
+ *
+ * If all checks pass, the index will be cached in &load_info->index.mod
+ *
+ * Return: %0 on validation success, %-ENOEXEC on failure
+ */
+static int elf_validity_cache_index_mod(struct load_info *info)
+{
+	Elf_Shdr *shdr;
+	int mod_idx;
+
+	mod_idx = find_any_unique_sec(info, ".gnu.linkonce.this_module");
+	if (mod_idx <= 0) {
+		pr_err("module %s: Exactly one .gnu.linkonce.this_module section must exist.\n",
+		       info->name ?: "(missing .modinfo section or name field)");
+		return -ENOEXEC;
+	}
+
+	shdr = &info->sechdrs[mod_idx];
+
+	if (shdr->sh_type == SHT_NOBITS) {
+		pr_err("module %s: .gnu.linkonce.this_module section must have a size set\n",
+		       info->name ?: "(missing .modinfo section or name field)");
+		return -ENOEXEC;
+	}
+
+	if (!(shdr->sh_flags & SHF_ALLOC)) {
+		pr_err("module %s: .gnu.linkonce.this_module must occupy memory during process execution\n",
+		       info->name ?: "(missing .modinfo section or name field)");
+		return -ENOEXEC;
+	}
+
+	if (shdr->sh_size != sizeof(struct module)) {
+		pr_err("module %s: .gnu.linkonce.this_module section size must match the kernel's built struct module size at run time\n",
+		       info->name ?: "(missing .modinfo section or name field)");
+		return -ENOEXEC;
+	}
+
+	info->index.mod = mod_idx;
+
+	return 0;
+}
+
+
 /*
  * Check userspace passed ELF module against our expectations, and cache
  * useful variables for further processing as we go.
@@ -1944,7 +2006,6 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 	unsigned int i;
 	Elf_Shdr *shdr;
 	int err;
-	unsigned int num_mod_secs = 0, mod_idx;
 	unsigned int num_sym_secs = 0, sym_idx;
 
 	err = elf_validity_cache_sechdrs(info);
@@ -1954,16 +2015,15 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 	if (err < 0)
 		return err;
 	err = elf_validity_cache_index_info(info);
+	if (err < 0)
+		return err;
+	err = elf_validity_cache_index_mod(info);
 	if (err < 0)
 		return err;
 
 	for (i = 1; i < info->hdr->e_shnum; i++) {
 		shdr = &info->sechdrs[i];
-		switch (shdr->sh_type) {
-		case SHT_NULL:
-		case SHT_NOBITS:
-			continue;
-		case SHT_SYMTAB:
+		if (shdr->sh_type == SHT_SYMTAB) {
 			if (shdr->sh_link == SHN_UNDEF
 			    || shdr->sh_link >= info->hdr->e_shnum) {
 				pr_err("Invalid ELF sh_link!=SHN_UNDEF(%d) or (sh_link(%d) >= hdr->e_shnum(%d)\n",
@@ -1973,14 +2033,6 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 			}
 			num_sym_secs++;
 			sym_idx = i;
-			fallthrough;
-		default:
-			if (strcmp(info->secstrings + shdr->sh_name,
-				   ".gnu.linkonce.this_module") == 0) {
-				num_mod_secs++;
-				mod_idx = i;
-			}
-			break;
 		}
 	}
 
@@ -1996,55 +2048,8 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 	info->index.str = shdr->sh_link;
 	info->strtab = (char *)info->hdr + info->sechdrs[info->index.str].sh_offset;
 
-	/*
-	 * The ".gnu.linkonce.this_module" ELF section is special. It is
-	 * what modpost uses to refer to __this_module and let's use rely
-	 * on THIS_MODULE to point to &__this_module properly. The kernel's
-	 * modpost declares it on each modules's *.mod.c file. If the struct
-	 * module of the kernel changes a full kernel rebuild is required.
-	 *
-	 * We have a few expectaions for this special section, the following
-	 * code validates all this for us:
-	 *
-	 *   o Only one section must exist
-	 *   o We expect the kernel to always have to allocate it: SHF_ALLOC
-	 *   o The section size must match the kernel's run time's struct module
-	 *     size
-	 */
-	if (num_mod_secs != 1) {
-		pr_err("module %s: Only one .gnu.linkonce.this_module section must exist.\n",
-		       info->name ?: "(missing .modinfo section or name field)");
-		goto no_exec;
-	}
-
-	shdr = &info->sechdrs[mod_idx];
-
-	/*
-	 * This is already implied on the switch above, however let's be
-	 * pedantic about it.
-	 */
-	if (shdr->sh_type == SHT_NOBITS) {
-		pr_err("module %s: .gnu.linkonce.this_module section must have a size set\n",
-		       info->name ?: "(missing .modinfo section or name field)");
-		goto no_exec;
-	}
-
-	if (!(shdr->sh_flags & SHF_ALLOC)) {
-		pr_err("module %s: .gnu.linkonce.this_module must occupy memory during process execution\n",
-		       info->name ?: "(missing .modinfo section or name field)");
-		goto no_exec;
-	}
-
-	if (shdr->sh_size != sizeof(struct module)) {
-		pr_err("module %s: .gnu.linkonce.this_module section size must match the kernel's built struct module size at run time\n",
-		       info->name ?: "(missing .modinfo section or name field)");
-		goto no_exec;
-	}
-
-	info->index.mod = mod_idx;
-
 	/* This is temporary: point mod into copy of data. */
-	info->mod = (void *)info->hdr + shdr->sh_offset;
+	info->mod = (void *)info->hdr + info->sechdrs[info->index.mod].sh_offset;
 
 	/*
 	 * If we didn't load the .modinfo 'name' field earlier, fall back to

From 9bd4982cf7d65f4c9e0793d5a8fda6ad838e8554 Mon Sep 17 00:00:00 2001
From: Matthew Maurer <mmaurer@google.com>
Date: Tue, 15 Oct 2024 23:16:41 +0000
Subject: [PATCH 0521/1530] module: Factor out elf_validity_cache_index_sym

Centralize symbol table detection and property validation.

Signed-off-by: Matthew Maurer <mmaurer@google.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 kernel/module/main.c | 73 ++++++++++++++++++++++++++------------------
 1 file changed, 44 insertions(+), 29 deletions(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index ec638187ffcf8..6be58b0a6468c 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1980,6 +1980,39 @@ static int elf_validity_cache_index_mod(struct load_info *info)
 	return 0;
 }
 
+/**
+ * elf_validity_cache_index_sym() - Validate and cache symtab index
+ * @info: Load info to cache symtab index in.
+ *        Must have &load_info->sechdrs and &load_info->secstrings populated.
+ *
+ * Checks that there is exactly one symbol table, then caches its index in
+ * &load_info->index.sym.
+ *
+ * Return: %0 if valid, %-ENOEXEC on failure.
+ */
+static int elf_validity_cache_index_sym(struct load_info *info)
+{
+	unsigned int sym_idx;
+	unsigned int num_sym_secs = 0;
+	int i;
+
+	for (i = 1; i < info->hdr->e_shnum; i++) {
+		if (info->sechdrs[i].sh_type == SHT_SYMTAB) {
+			num_sym_secs++;
+			sym_idx = i;
+		}
+	}
+
+	if (num_sym_secs != 1) {
+		pr_warn("%s: module has no symbols (stripped?)\n",
+			info->name ?: "(missing .modinfo section or name field)");
+		return -ENOEXEC;
+	}
+
+	info->index.sym = sym_idx;
+
+	return 0;
+}
 
 /*
  * Check userspace passed ELF module against our expectations, and cache
@@ -2003,10 +2036,8 @@ static int elf_validity_cache_index_mod(struct load_info *info)
  */
 static int elf_validity_cache_copy(struct load_info *info, int flags)
 {
-	unsigned int i;
-	Elf_Shdr *shdr;
 	int err;
-	unsigned int num_sym_secs = 0, sym_idx;
+	int str_idx;
 
 	err = elf_validity_cache_sechdrs(info);
 	if (err < 0)
@@ -2018,34 +2049,21 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 	if (err < 0)
 		return err;
 	err = elf_validity_cache_index_mod(info);
+	if (err < 0)
+		return err;
+	err = elf_validity_cache_index_sym(info);
 	if (err < 0)
 		return err;
 
-	for (i = 1; i < info->hdr->e_shnum; i++) {
-		shdr = &info->sechdrs[i];
-		if (shdr->sh_type == SHT_SYMTAB) {
-			if (shdr->sh_link == SHN_UNDEF
-			    || shdr->sh_link >= info->hdr->e_shnum) {
-				pr_err("Invalid ELF sh_link!=SHN_UNDEF(%d) or (sh_link(%d) >= hdr->e_shnum(%d)\n",
-				       shdr->sh_link, shdr->sh_link,
-				       info->hdr->e_shnum);
-				goto no_exec;
-			}
-			num_sym_secs++;
-			sym_idx = i;
-		}
-	}
-
-	if (num_sym_secs != 1) {
-		pr_warn("%s: module has no symbols (stripped?)\n",
-			info->name ?: "(missing .modinfo section or name field)");
-		goto no_exec;
+	str_idx = info->sechdrs[info->index.sym].sh_link;
+	if (str_idx == SHN_UNDEF || str_idx >= info->hdr->e_shnum) {
+		pr_err("Invalid ELF sh_link!=SHN_UNDEF(%d) or (sh_link(%d) >= hdr->e_shnum(%d)\n",
+				str_idx, str_idx, info->hdr->e_shnum);
+		return -ENOEXEC;
 	}
 
-	/* Sets internal symbols and strings. */
-	info->index.sym = sym_idx;
-	shdr = &info->sechdrs[sym_idx];
-	info->index.str = shdr->sh_link;
+	/* Sets internal strings. */
+	info->index.str = str_idx;
 	info->strtab = (char *)info->hdr + info->sechdrs[info->index.str].sh_offset;
 
 	/* This is temporary: point mod into copy of data. */
@@ -2066,9 +2084,6 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 	info->index.pcpu = find_pcpusec(info);
 
 	return 0;
-
-no_exec:
-	return -ENOEXEC;
 }
 
 #define COPY_CHUNK_SIZE (16*PAGE_SIZE)

From 0a9395334496d3be8bde491e46087540cb8f141d Mon Sep 17 00:00:00 2001
From: Matthew Maurer <mmaurer@google.com>
Date: Tue, 15 Oct 2024 23:16:42 +0000
Subject: [PATCH 0522/1530] module: Factor out elf_validity_cache_index_str

Pull out index validation for the symbol string section.

Note that this does not validate the *contents* of the string table,
only shape and presence of the section.

Signed-off-by: Matthew Maurer <mmaurer@google.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 kernel/module/main.c | 37 ++++++++++++++++++++++++++++---------
 1 file changed, 28 insertions(+), 9 deletions(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index 6be58b0a6468c..43140475aac00 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2014,6 +2014,31 @@ static int elf_validity_cache_index_sym(struct load_info *info)
 	return 0;
 }
 
+/**
+ * elf_validity_cache_index_str() - Validate and cache strtab index
+ * @info: Load info to cache strtab index in.
+ *        Must have &load_info->sechdrs and &load_info->secstrings populated.
+ *        Must have &load_info->index.sym populated.
+ *
+ * Looks at the symbol table's associated string table, makes sure it is
+ * in-bounds, and caches it.
+ *
+ * Return: %0 if valid, %-ENOEXEC on failure.
+ */
+static int elf_validity_cache_index_str(struct load_info *info)
+{
+	unsigned int str_idx = info->sechdrs[info->index.sym].sh_link;
+
+	if (str_idx == SHN_UNDEF || str_idx >= info->hdr->e_shnum) {
+		pr_err("Invalid ELF sh_link!=SHN_UNDEF(%d) or (sh_link(%d) >= hdr->e_shnum(%d)\n",
+		       str_idx, str_idx, info->hdr->e_shnum);
+		return -ENOEXEC;
+	}
+
+	info->index.str = str_idx;
+	return 0;
+}
+
 /*
  * Check userspace passed ELF module against our expectations, and cache
  * useful variables for further processing as we go.
@@ -2037,7 +2062,6 @@ static int elf_validity_cache_index_sym(struct load_info *info)
 static int elf_validity_cache_copy(struct load_info *info, int flags)
 {
 	int err;
-	int str_idx;
 
 	err = elf_validity_cache_sechdrs(info);
 	if (err < 0)
@@ -2054,16 +2078,11 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 	err = elf_validity_cache_index_sym(info);
 	if (err < 0)
 		return err;
-
-	str_idx = info->sechdrs[info->index.sym].sh_link;
-	if (str_idx == SHN_UNDEF || str_idx >= info->hdr->e_shnum) {
-		pr_err("Invalid ELF sh_link!=SHN_UNDEF(%d) or (sh_link(%d) >= hdr->e_shnum(%d)\n",
-				str_idx, str_idx, info->hdr->e_shnum);
-		return -ENOEXEC;
-	}
+	err = elf_validity_cache_index_str(info);
+	if (err < 0)
+		return err;
 
 	/* Sets internal strings. */
-	info->index.str = str_idx;
 	info->strtab = (char *)info->hdr + info->sechdrs[info->index.str].sh_offset;
 
 	/* This is temporary: point mod into copy of data. */

From f3f561218bb60afd6d3e3b26add39ff46de89c83 Mon Sep 17 00:00:00 2001
From: Matthew Maurer <mmaurer@google.com>
Date: Tue, 15 Oct 2024 23:16:43 +0000
Subject: [PATCH 0523/1530] module: Group section index calculations together

Group all the index detection together to make the parent function
easier to read.

Signed-off-by: Matthew Maurer <mmaurer@google.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 kernel/module/main.c | 68 +++++++++++++++++++++++++++++++++-----------
 1 file changed, 51 insertions(+), 17 deletions(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index 43140475aac00..e04a228c694a2 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2039,6 +2039,56 @@ static int elf_validity_cache_index_str(struct load_info *info)
 	return 0;
 }
 
+/**
+ * elf_validity_cache_index() - Resolve, validate, cache section indices
+ * @info:  Load info to read from and update.
+ *         &load_info->sechdrs and &load_info->secstrings must be populated.
+ * @flags: Load flags, relevant to suppress version loading, see
+ *         uapi/linux/module.h
+ *
+ * Populates &load_info->index, validating as it goes.
+ * See child functions for per-field validation:
+ *
+ * * elf_validity_cache_index_info()
+ * * elf_validity_cache_index_mod()
+ * * elf_validity_cache_index_sym()
+ * * elf_validity_cache_index_str()
+ *
+ * If versioning is not suppressed via flags, load the version index from
+ * a section called "__versions" with no validation.
+ *
+ * If CONFIG_SMP is enabled, load the percpu section by name with no
+ * validation.
+ *
+ * Return: 0 on success, negative error code if an index failed validation.
+ */
+static int elf_validity_cache_index(struct load_info *info, int flags)
+{
+	int err;
+
+	err = elf_validity_cache_index_info(info);
+	if (err < 0)
+		return err;
+	err = elf_validity_cache_index_mod(info);
+	if (err < 0)
+		return err;
+	err = elf_validity_cache_index_sym(info);
+	if (err < 0)
+		return err;
+	err = elf_validity_cache_index_str(info);
+	if (err < 0)
+		return err;
+
+	if (flags & MODULE_INIT_IGNORE_MODVERSIONS)
+		info->index.vers = 0; /* Pretend no __versions section! */
+	else
+		info->index.vers = find_sec(info, "__versions");
+
+	info->index.pcpu = find_pcpusec(info);
+
+	return 0;
+}
+
 /*
  * Check userspace passed ELF module against our expectations, and cache
  * useful variables for further processing as we go.
@@ -2069,16 +2119,7 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 	err = elf_validity_cache_secstrings(info);
 	if (err < 0)
 		return err;
-	err = elf_validity_cache_index_info(info);
-	if (err < 0)
-		return err;
-	err = elf_validity_cache_index_mod(info);
-	if (err < 0)
-		return err;
-	err = elf_validity_cache_index_sym(info);
-	if (err < 0)
-		return err;
-	err = elf_validity_cache_index_str(info);
+	err = elf_validity_cache_index(info, flags);
 	if (err < 0)
 		return err;
 
@@ -2095,13 +2136,6 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 	if (!info->name)
 		info->name = info->mod->name;
 
-	if (flags & MODULE_INIT_IGNORE_MODVERSIONS)
-		info->index.vers = 0; /* Pretend no __versions section! */
-	else
-		info->index.vers = find_sec(info, "__versions");
-
-	info->index.pcpu = find_pcpusec(info);
-
 	return 0;
 }
 

From 837031e052af32c747906238fb1feb87778e4fe0 Mon Sep 17 00:00:00 2001
From: Matthew Maurer <mmaurer@google.com>
Date: Tue, 15 Oct 2024 23:16:44 +0000
Subject: [PATCH 0524/1530] module: Factor out elf_validity_cache_strtab

This patch only moves the existing strtab population to a function.
Validation comes in a following patch, this is split out to make the new
validation checks more clearly separated.

Signed-off-by: Matthew Maurer <mmaurer@google.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 kernel/module/main.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index e04a228c694a2..c082d5d41a8d1 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2089,6 +2089,23 @@ static int elf_validity_cache_index(struct load_info *info, int flags)
 	return 0;
 }
 
+/**
+ * elf_validity_cache_strtab() - Cache symbol string table
+ * @info: Load info to read from and update.
+ *        Must have &load_info->sechdrs and &load_info->secstrings populated.
+ *        Must have &load_info->index populated.
+ *
+ * Return: 0 on success, negative error code if a check failed.
+ */
+static int elf_validity_cache_strtab(struct load_info *info)
+{
+	Elf_Shdr *str_shdr = &info->sechdrs[info->index.str];
+	char *strtab = (char *)info->hdr + str_shdr->sh_offset;
+
+	info->strtab = strtab;
+	return 0;
+}
+
 /*
  * Check userspace passed ELF module against our expectations, and cache
  * useful variables for further processing as we go.
@@ -2122,9 +2139,9 @@ static int elf_validity_cache_copy(struct load_info *info, int flags)
 	err = elf_validity_cache_index(info, flags);
 	if (err < 0)
 		return err;
-
-	/* Sets internal strings. */
-	info->strtab = (char *)info->hdr + info->sechdrs[info->index.str].sh_offset;
+	err = elf_validity_cache_strtab(info);
+	if (err < 0)
+		return err;
 
 	/* This is temporary: point mod into copy of data. */
 	info->mod = (void *)info->hdr + info->sechdrs[info->index.mod].sh_offset;

From d979e3dffa93c9284f244ef64f7a68042c2f8b80 Mon Sep 17 00:00:00 2001
From: Matthew Maurer <mmaurer@google.com>
Date: Tue, 15 Oct 2024 23:16:45 +0000
Subject: [PATCH 0525/1530] module: Additional validation in
 elf_validity_cache_strtab

Validate properties of the strtab that are depended on elsewhere, but
were previously unchecked:
* String table nonempty (offset 0 is valid)
* String table has a leading NUL (offset 0 corresponds to "")
* String table is NUL terminated (strfoo functions won't run out of the
  table while reading).
* All symbols names are inbounds of the string table.

Signed-off-by: Matthew Maurer <mmaurer@google.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 kernel/module/main.c | 38 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 37 insertions(+), 1 deletion(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index c082d5d41a8d1..b40b632f00a65 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2090,17 +2090,53 @@ static int elf_validity_cache_index(struct load_info *info, int flags)
 }
 
 /**
- * elf_validity_cache_strtab() - Cache symbol string table
+ * elf_validity_cache_strtab() - Validate and cache symbol string table
  * @info: Load info to read from and update.
  *        Must have &load_info->sechdrs and &load_info->secstrings populated.
  *        Must have &load_info->index populated.
  *
+ * Checks:
+ *
+ * * The string table is not empty.
+ * * The string table starts and ends with NUL (required by ELF spec).
+ * * Every &Elf_Sym->st_name offset in the symbol table is inbounds of the
+ *   string table.
+ *
+ * And caches the pointer as &load_info->strtab in @info.
+ *
  * Return: 0 on success, negative error code if a check failed.
  */
 static int elf_validity_cache_strtab(struct load_info *info)
 {
 	Elf_Shdr *str_shdr = &info->sechdrs[info->index.str];
+	Elf_Shdr *sym_shdr = &info->sechdrs[info->index.sym];
 	char *strtab = (char *)info->hdr + str_shdr->sh_offset;
+	Elf_Sym *syms = (void *)info->hdr + sym_shdr->sh_offset;
+	int i;
+
+	if (str_shdr->sh_size == 0) {
+		pr_err("empty symbol string table\n");
+		return -ENOEXEC;
+	}
+	if (strtab[0] != '\0') {
+		pr_err("symbol string table missing leading NUL\n");
+		return -ENOEXEC;
+	}
+	if (strtab[str_shdr->sh_size - 1] != '\0') {
+		pr_err("symbol string table isn't NUL terminated\n");
+		return -ENOEXEC;
+	}
+
+	/*
+	 * Now that we know strtab is correctly structured, check symbol
+	 * starts are inbounds before they're used later.
+	 */
+	for (i = 0; i < sym_shdr->sh_size / sizeof(*syms); i++) {
+		if (syms[i].st_name >= str_shdr->sh_size) {
+			pr_err("symbol name out of bounds in string table");
+			return -ENOEXEC;
+		}
+	}
 
 	info->strtab = strtab;
 	return 0;

From 2295cf87ed5a6da4564034e4f8ebcce0a0a021ed Mon Sep 17 00:00:00 2001
From: Matthew Maurer <mmaurer@google.com>
Date: Tue, 15 Oct 2024 23:16:46 +0000
Subject: [PATCH 0526/1530] module: Reformat struct for code style

Using commas to declare struct members makes adding new members to this
struct not as nice with patch management.

Test results linux-modules-kpd succeed [0].

Signed-off-by: Matthew Maurer <mmaurer@google.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
[mcgrof: add automated test results from kdevops using KPD ]
Link: https://github.com/linux-kdevops/linux-modules-kpd/actions/runs/11420095343 # [0]
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 kernel/module/internal.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/kernel/module/internal.h b/kernel/module/internal.h
index 2ebece8a789f5..daef2be839022 100644
--- a/kernel/module/internal.h
+++ b/kernel/module/internal.h
@@ -80,7 +80,12 @@ struct load_info {
 	unsigned int used_pages;
 #endif
 	struct {
-		unsigned int sym, str, mod, vers, info, pcpu;
+		unsigned int sym;
+		unsigned int str;
+		unsigned int mod;
+		unsigned int vers;
+		unsigned int info;
+		unsigned int pcpu;
 	} index;
 };
 

From 272167499ffac79d57d96b90d0458e0dad54488c Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 19 Oct 2024 14:07:42 -0700
Subject: [PATCH 0527/1530] Input: gscps2 - fix compilation error introduced
 with switch to guards

Change 44f920069911 ("Input: gscps2 - use guard notation when acquiring
spinlock") introduced typos resulting in compile errors noticed by the
kernel test robot. Fix them.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202410192242.GL0CoAbv-lkp@intel.com/
Fixes: 44f920069911 ("Input: gscps2 - use guard notation when acquiring spinlock")
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/gscps2.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/input/serio/gscps2.c b/drivers/input/serio/gscps2.c
index cf0603d1a1139..4fada5bc2a382 100644
--- a/drivers/input/serio/gscps2.c
+++ b/drivers/input/serio/gscps2.c
@@ -198,8 +198,6 @@ static void gscps2_enable(struct gscps2port *ps2port, int enable)
 
 static void gscps2_reset(struct gscps2port *ps2port)
 {
-	unsigned long flags;
-
 	/* reset the interface */
 	guard(spinlock_irqsave)(&ps2port->lock);
 	gscps2_flush(ps2port);
@@ -218,7 +216,7 @@ static void gscps2_read_data(struct gscps2port *ps2port)
 		if (!(status & GSC_STAT_RBNE))
 			break;
 
-		ps2port->buffer[ps2port->append].ste = status;
+		ps2port->buffer[ps2port->append].str = status;
 		ps2port->buffer[ps2port->append].data =
 				gscps2_readb_input(ps2port->addr);
 	} while (true);

From ac2b6ce67275a4c777622fda623ebbda320f47da Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Sat, 19 Oct 2024 20:59:02 -0700
Subject: [PATCH 0528/1530] Input: cap11xx - switch to
 for_each_child_of_node_scoped

Use the scoped variant of the macro to simplify the code and error
handling. This makes the error handling more robust by ensuring that
the child node is always freed.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20241010-input_automate_of_node_put-v1-1-ebc62138fbf8@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/cap11xx.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index b21ef9d6ff9d6..0c17cbaa3d27a 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -416,7 +416,7 @@ static int cap11xx_led_set(struct led_classdev *cdev,
 static int cap11xx_init_leds(struct device *dev,
 			     struct cap11xx_priv *priv, int num_leds)
 {
-	struct device_node *node = dev->of_node, *child;
+	struct device_node *node = dev->of_node;
 	struct cap11xx_led *led;
 	int cnt = of_get_child_count(node);
 	int error;
@@ -445,7 +445,7 @@ static int cap11xx_init_leds(struct device *dev,
 	if (error)
 		return error;
 
-	for_each_child_of_node(node, child) {
+	for_each_child_of_node_scoped(node, child) {
 		u32 reg;
 
 		led->cdev.name =
@@ -458,19 +458,15 @@ static int cap11xx_init_leds(struct device *dev,
 		led->cdev.brightness = LED_OFF;
 
 		error = of_property_read_u32(child, "reg", &reg);
-		if (error != 0 || reg >= num_leds) {
-			of_node_put(child);
+		if (error != 0 || reg >= num_leds)
 			return -EINVAL;
-		}
 
 		led->reg = reg;
 		led->priv = priv;
 
 		error = devm_led_classdev_register(dev, &led->cdev);
-		if (error) {
-			of_node_put(child);
+		if (error)
 			return error;
-		}
 
 		priv->num_leds++;
 		led++;

From 2e6980c16993d21ff6dc9c338a33920f10d22395 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Sat, 19 Oct 2024 20:59:49 -0700
Subject: [PATCH 0529/1530] Input: mtk-pmic-keys - switch to
 for_each_child_of_node_scoped

Use the scoped variant of the macro to simplify the code and error
handling. This makes the error handling more robust by ensuring that
the child node is always freed.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20241010-input_automate_of_node_put-v1-2-ebc62138fbf8@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/mtk-pmic-keys.c | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

diff --git a/drivers/input/keyboard/mtk-pmic-keys.c b/drivers/input/keyboard/mtk-pmic-keys.c
index 4364c3401ff1c..5ad6be9141603 100644
--- a/drivers/input/keyboard/mtk-pmic-keys.c
+++ b/drivers/input/keyboard/mtk-pmic-keys.c
@@ -307,7 +307,7 @@ static int mtk_pmic_keys_probe(struct platform_device *pdev)
 	int error, index = 0;
 	unsigned int keycount;
 	struct mt6397_chip *pmic_chip = dev_get_drvdata(pdev->dev.parent);
-	struct device_node *node = pdev->dev.of_node, *child;
+	struct device_node *node = pdev->dev.of_node;
 	static const char *const irqnames[] = { "powerkey", "homekey" };
 	static const char *const irqnames_r[] = { "powerkey_r", "homekey_r" };
 	struct mtk_pmic_keys *keys;
@@ -343,24 +343,20 @@ static int mtk_pmic_keys_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	for_each_child_of_node(node, child) {
+	for_each_child_of_node_scoped(node, child) {
 		keys->keys[index].regs = &mtk_pmic_regs->keys_regs[index];
 
 		keys->keys[index].irq =
 			platform_get_irq_byname(pdev, irqnames[index]);
-		if (keys->keys[index].irq < 0) {
-			of_node_put(child);
+		if (keys->keys[index].irq < 0)
 			return keys->keys[index].irq;
-		}
 
 		if (of_device_is_compatible(node, "mediatek,mt6358-keys")) {
 			keys->keys[index].irq_r = platform_get_irq_byname(pdev,
 									  irqnames_r[index]);
 
-			if (keys->keys[index].irq_r < 0) {
-				of_node_put(child);
+			if (keys->keys[index].irq_r < 0)
 				return keys->keys[index].irq_r;
-			}
 		}
 
 		error = of_property_read_u32(child,
@@ -369,7 +365,6 @@ static int mtk_pmic_keys_probe(struct platform_device *pdev)
 			dev_err(keys->dev,
 				"failed to read key:%d linux,keycode property: %d\n",
 				index, error);
-			of_node_put(child);
 			return error;
 		}
 
@@ -377,10 +372,8 @@ static int mtk_pmic_keys_probe(struct platform_device *pdev)
 			keys->keys[index].wakeup = true;
 
 		error = mtk_pmic_key_setup(keys, &keys->keys[index]);
-		if (error) {
-			of_node_put(child);
+		if (error)
 			return error;
-		}
 
 		index++;
 	}

From 0ec6f58b63ae17774b10aa41ee86b6a387b60038 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Sat, 19 Oct 2024 21:01:07 -0700
Subject: [PATCH 0530/1530] Input: sun4i-lradc-keys - switch to
 for_each_child_of_node_scoped

Use the scoped variant of the macro to simplify the code and error
handling. This makes the error handling more robust by ensuring that
the child node is always freed.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Reviewed-by: Andre Przywara <andre.przywara@arm.com>
Link: https://lore.kernel.org/r/20241010-input_automate_of_node_put-v1-3-ebc62138fbf8@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/sun4i-lradc-keys.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/input/keyboard/sun4i-lradc-keys.c b/drivers/input/keyboard/sun4i-lradc-keys.c
index f304cab0ebdb8..f1e269605f05a 100644
--- a/drivers/input/keyboard/sun4i-lradc-keys.c
+++ b/drivers/input/keyboard/sun4i-lradc-keys.c
@@ -202,7 +202,7 @@ static void sun4i_lradc_close(struct input_dev *dev)
 static int sun4i_lradc_load_dt_keymap(struct device *dev,
 				      struct sun4i_lradc_data *lradc)
 {
-	struct device_node *np, *pp;
+	struct device_node *np;
 	int i;
 	int error;
 
@@ -223,28 +223,25 @@ static int sun4i_lradc_load_dt_keymap(struct device *dev,
 		return -ENOMEM;
 
 	i = 0;
-	for_each_child_of_node(np, pp) {
+	for_each_child_of_node_scoped(np, pp) {
 		struct sun4i_lradc_keymap *map = &lradc->chan0_map[i];
 		u32 channel;
 
 		error = of_property_read_u32(pp, "channel", &channel);
 		if (error || channel != 0) {
 			dev_err(dev, "%pOFn: Inval channel prop\n", pp);
-			of_node_put(pp);
 			return -EINVAL;
 		}
 
 		error = of_property_read_u32(pp, "voltage", &map->voltage);
 		if (error) {
 			dev_err(dev, "%pOFn: Inval voltage prop\n", pp);
-			of_node_put(pp);
 			return -EINVAL;
 		}
 
 		error = of_property_read_u32(pp, "linux,code", &map->keycode);
 		if (error) {
 			dev_err(dev, "%pOFn: Inval linux,code prop\n", pp);
-			of_node_put(pp);
 			return -EINVAL;
 		}
 

From 0ba9d3a597c4446072f2a4326689b8858761c8f7 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Sat, 19 Oct 2024 21:07:19 -0700
Subject: [PATCH 0531/1530] Input: twl6040-vibra - use cleanup facility for
 device_node

Use the '__free(device_node)' macro to simplify the code and error
handling. This makes the error handling more robust by ensuring that the
device node is always freed.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20241010-input_automate_of_node_put-v1-4-ebc62138fbf8@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/twl6040-vibra.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/input/misc/twl6040-vibra.c b/drivers/input/misc/twl6040-vibra.c
index 78f0b63e5c200..afed9af65bf92 100644
--- a/drivers/input/misc/twl6040-vibra.c
+++ b/drivers/input/misc/twl6040-vibra.c
@@ -229,14 +229,13 @@ static DEFINE_SIMPLE_DEV_PM_OPS(twl6040_vibra_pm_ops,
 static int twl6040_vibra_probe(struct platform_device *pdev)
 {
 	struct device *twl6040_core_dev = pdev->dev.parent;
-	struct device_node *twl6040_core_node;
 	struct vibra_info *info;
 	int vddvibl_uV = 0;
 	int vddvibr_uV = 0;
 	int error;
 
-	twl6040_core_node = of_get_child_by_name(twl6040_core_dev->of_node,
-						 "vibra");
+	struct device_node *twl6040_core_node __free(device_node) =
+		of_get_child_by_name(twl6040_core_dev->of_node, "vibra");
 	if (!twl6040_core_node) {
 		dev_err(&pdev->dev, "parent of node is missing?\n");
 		return -EINVAL;
@@ -244,7 +243,6 @@ static int twl6040_vibra_probe(struct platform_device *pdev)
 
 	info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
 	if (!info) {
-		of_node_put(twl6040_core_node);
 		dev_err(&pdev->dev, "couldn't allocate memory\n");
 		return -ENOMEM;
 	}
@@ -264,8 +262,6 @@ static int twl6040_vibra_probe(struct platform_device *pdev)
 	of_property_read_u32(twl6040_core_node, "ti,vddvibl-uV", &vddvibl_uV);
 	of_property_read_u32(twl6040_core_node, "ti,vddvibr-uV", &vddvibr_uV);
 
-	of_node_put(twl6040_core_node);
-
 	if ((!info->vibldrv_res && !info->viblmotor_res) ||
 	    (!info->vibrdrv_res && !info->vibrmotor_res)) {
 		dev_err(info->dev, "invalid vibra driver/motor resistance\n");

From d3dcadd654aefadebe847da74059dce6cc506e6b Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Sat, 19 Oct 2024 21:07:41 -0700
Subject: [PATCH 0532/1530] Input: twl4030-vibra - use cleanup facility for
 device_node

Use the '__free(device_node)' macro to simplify the code by
automatically freeing the device node.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20241010-input_automate_of_node_put-v1-5-ebc62138fbf8@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/twl4030-vibra.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/input/misc/twl4030-vibra.c b/drivers/input/misc/twl4030-vibra.c
index 101548b35ee31..5fa7d4a7da363 100644
--- a/drivers/input/misc/twl4030-vibra.c
+++ b/drivers/input/misc/twl4030-vibra.c
@@ -165,15 +165,10 @@ static DEFINE_SIMPLE_DEV_PM_OPS(twl4030_vibra_pm_ops,
 
 static bool twl4030_vibra_check_coexist(struct device_node *parent)
 {
-	struct device_node *node;
+	struct device_node *node __free(device_node) =
+		of_get_child_by_name(parent, "codec");
 
-	node = of_get_child_by_name(parent, "codec");
-	if (node) {
-		of_node_put(node);
-		return true;
-	}
-
-	return false;
+	return node != NULL;
 }
 
 static int twl4030_vibra_probe(struct platform_device *pdev)

From 8dee1ddafa2f66c32d14af8e138e70ae7ace0292 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Sat, 19 Oct 2024 21:14:57 -0700
Subject: [PATCH 0533/1530] Input: 88pm860x - use cleanup facility for
 device_node

Use the '__free(device_node)' macro to simplify the code and error
handling. This makes the code more robust by ensuring that the device
node is always freed.

Drop the first assignment to 'pdev->dev.parent->of_node', as it was only
a shortcut, and tie 'np' to its usage as a child node.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20241010-input_automate_of_node_put-v1-7-ebc62138fbf8@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/88pm860x-ts.c | 20 +++++++-------------
 1 file changed, 7 insertions(+), 13 deletions(-)

diff --git a/drivers/input/touchscreen/88pm860x-ts.c b/drivers/input/touchscreen/88pm860x-ts.c
index 81a3ea4b9a3dd..0468ce2b216f6 100644
--- a/drivers/input/touchscreen/88pm860x-ts.c
+++ b/drivers/input/touchscreen/88pm860x-ts.c
@@ -117,13 +117,14 @@ static int pm860x_touch_dt_init(struct platform_device *pdev,
 					  struct pm860x_chip *chip,
 					  int *res_x)
 {
-	struct device_node *np = pdev->dev.parent->of_node;
 	struct i2c_client *i2c = (chip->id == CHIP_PM8607) ? chip->client \
 				 : chip->companion;
 	int data, n, ret;
-	if (!np)
+	if (!pdev->dev.parent->of_node)
 		return -ENODEV;
-	np = of_get_child_by_name(np, "touch");
+
+	struct device_node *np __free(device_node) =
+		of_get_child_by_name(pdev->dev.parent->of_node, "touch");
 	if (!np) {
 		dev_err(&pdev->dev, "Can't find touch node\n");
 		return -EINVAL;
@@ -141,13 +142,13 @@ static int pm860x_touch_dt_init(struct platform_device *pdev,
 	if (data) {
 		ret = pm860x_reg_write(i2c, PM8607_GPADC_MISC1, data);
 		if (ret < 0)
-			goto err_put_node;
+			return -EINVAL;
 	}
 	/* set tsi prebias time */
 	if (!of_property_read_u32(np, "marvell,88pm860x-tsi-prebias", &data)) {
 		ret = pm860x_reg_write(i2c, PM8607_TSI_PREBIAS, data);
 		if (ret < 0)
-			goto err_put_node;
+			return -EINVAL;
 	}
 	/* set prebias & prechg time of pen detect */
 	data = 0;
@@ -158,18 +159,11 @@ static int pm860x_touch_dt_init(struct platform_device *pdev,
 	if (data) {
 		ret = pm860x_reg_write(i2c, PM8607_PD_PREBIAS, data);
 		if (ret < 0)
-			goto err_put_node;
+			return -EINVAL;
 	}
 	of_property_read_u32(np, "marvell,88pm860x-resistor-X", res_x);
 
-	of_node_put(np);
-
 	return 0;
-
-err_put_node:
-	of_node_put(np);
-
-	return -EINVAL;
 }
 #else
 #define pm860x_touch_dt_init(x, y, z)	(-1)

From 6243376d6a969fb4fa654a685599ec09b872bd20 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Sat, 19 Oct 2024 21:15:41 -0700
Subject: [PATCH 0534/1530] Input: i8042 - use cleanup facility for device_node

Use the '__free(device_node)' macro to automatically free the device
node, removing the need for explicit calls to 'of_node_put()' to
decrement its refcount.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20241010-input_automate_of_node_put-v1-8-ebc62138fbf8@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/i8042-sparcio.h | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/input/serio/i8042-sparcio.h b/drivers/input/serio/i8042-sparcio.h
index b4a5fcaac09f6..0f97158fd14e6 100644
--- a/drivers/input/serio/i8042-sparcio.h
+++ b/drivers/input/serio/i8042-sparcio.h
@@ -106,18 +106,10 @@ static struct platform_driver sparc_i8042_driver = {
 
 static bool i8042_is_mr_coffee(void)
 {
-	struct device_node *root;
-	const char *name;
-	bool is_mr_coffee;
+	struct device_node *root __free(device_node) = of_find_node_by_path("/");
+	const char *name = of_get_property(root, "name", NULL);
 
-	root = of_find_node_by_path("/");
-
-	name = of_get_property(root, "name", NULL);
-	is_mr_coffee = name && !strcmp(name, "SUNW,JavaStation-1");
-
-	of_node_put(root);
-
-	return is_mr_coffee;
+	return name && !strcmp(name, "SUNW,JavaStation-1");
 }
 
 static int __init i8042_platform_init(void)

From cd63c67be6094825ff06b2649c6d9b33cb38a1b9 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Sat, 19 Oct 2024 21:18:30 -0700
Subject: [PATCH 0535/1530] Input: raspberrypi-ts - use cleanup facility for
 device_node

Use the '__free(device_node)' macro to automatically free the device
node, removing the need for explicit calls to 'of_node_put()' to
decrement its refcount.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20241010-input_automate_of_node_put-v1-9-ebc62138fbf8@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/raspberrypi-ts.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/input/touchscreen/raspberrypi-ts.c b/drivers/input/touchscreen/raspberrypi-ts.c
index 45c575df994e0..841d39a449b37 100644
--- a/drivers/input/touchscreen/raspberrypi-ts.c
+++ b/drivers/input/touchscreen/raspberrypi-ts.c
@@ -122,20 +122,18 @@ static int rpi_ts_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	struct input_dev *input;
-	struct device_node *fw_node;
 	struct rpi_firmware *fw;
 	struct rpi_ts *ts;
 	u32 touchbuf;
 	int error;
 
-	fw_node = of_get_parent(np);
+	struct device_node *fw_node __free(device_node) = of_get_parent(np);
 	if (!fw_node) {
 		dev_err(dev, "Missing firmware node\n");
 		return -ENOENT;
 	}
 
 	fw = devm_rpi_firmware_get(&pdev->dev, fw_node);
-	of_node_put(fw_node);
 	if (!fw)
 		return -EPROBE_DEFER;
 

From 00850d7b542aa4a8240cf977d43dc6d2158e48d7 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Sat, 19 Oct 2024 21:18:57 -0700
Subject: [PATCH 0536/1530] Input: ts4800-ts - use cleanup facility for
 device_node

Use the '__free(device_node)' macro to automatically free the device
node, removing the need for explicit calls to 'of_node_put()' to
decrement its refcount.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20241010-input_automate_of_node_put-v1-10-ebc62138fbf8@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/ts4800-ts.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/input/touchscreen/ts4800-ts.c b/drivers/input/touchscreen/ts4800-ts.c
index 6cf66aadc10ed..98422d1e80d6d 100644
--- a/drivers/input/touchscreen/ts4800-ts.c
+++ b/drivers/input/touchscreen/ts4800-ts.c
@@ -110,18 +110,17 @@ static int ts4800_parse_dt(struct platform_device *pdev,
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
-	struct device_node *syscon_np;
 	u32 reg, bit;
 	int error;
 
-	syscon_np = of_parse_phandle(np, "syscon", 0);
+	struct device_node *syscon_np __free(device_node) =
+		of_parse_phandle(np, "syscon", 0);
 	if (!syscon_np) {
 		dev_err(dev, "no syscon property\n");
 		return -ENODEV;
 	}
 
 	ts->regmap = syscon_node_to_regmap(syscon_np);
-	of_node_put(syscon_np);
 	if (IS_ERR(ts->regmap)) {
 		dev_err(dev, "cannot get parent's regmap\n");
 		return PTR_ERR(ts->regmap);

From c408dd81678bb0a957eae96962c913c242e069f7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20B=C3=B6hler?= <witcher@wiredspace.de>
Date: Sat, 19 Oct 2024 10:22:46 +0200
Subject: [PATCH 0537/1530] drm/panic: avoid reimplementing Iterator::find
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rust's standard library's `std::iter::Iterator` trait provides a function
`find` that finds the first element that satisfies a predicate.
The function `Version::from_segments` is doing the same thing but is
implementing the same logic itself.

Clippy complains about this in the `manual_find` lint:

    error: manual implementation of `Iterator::find`
       --> drivers/gpu/drm/drm_panic_qr.rs:212:9
        |
    212 | /         for v in (1..=40).map(|k| Version(k)) {
    213 | |             if v.max_data() * 8 >= segments.iter().map(|s| s.total_size_bits(v)).sum() {
    214 | |                 return Some(v);
    215 | |             }
    216 | |         }
    217 | |         None
        | |____________^ help: replace with an iterator: `(1..=40).map(|k| Version(k)).find(|&v| v.max_data() * 8 >= segments.iter().map(|s| s.total_size_bits(v)).sum())`
        |
        = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#manual_find
        = note: `-D clippy::manual-find` implied by `-D warnings`
        = help: to override `-D warnings` add `#[allow(clippy::manual_find)]`

Use `Iterator::find` instead to make the intention clearer.

At the same time, clean up the redundant closure that Clippy warns
about too:

    error: redundant closure
    --> drivers/gpu/drm/drm_panic_qr.rs:212:31
        |
    212 |         for v in (1..=40).map(|k| Version(k)) {
        |                               ^^^^^^^^^^^^^^ help: replace the closure with the function itself: `Version`
        |
        = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#redundant_closure
        = note: `-D clippy::redundant-closure` implied by `-D warnings`
        = help: to override `-D warnings` add `#[allow(clippy::redundant_closure)]`

Fixes: cb5164ac43d0 ("drm/panic: Add a QR code panic screen")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1123
Signed-off-by: Thomas Böhler <witcher@wiredspace.de>
Reviewed-by: Jocelyn Falempe <jfalempe@redhat.com>
Link: https://lore.kernel.org/r/20241019084048.22336-2-witcher@wiredspace.de
[ Reworded to mention the redundant closure cleanup too. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 drivers/gpu/drm/drm_panic_qr.rs | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs
index 1ef56cb07dfbd..76decf49e6785 100644
--- a/drivers/gpu/drm/drm_panic_qr.rs
+++ b/drivers/gpu/drm/drm_panic_qr.rs
@@ -209,12 +209,9 @@ const FORMAT_INFOS_QR_L: [u16; 8] = [
 impl Version {
     /// Returns the smallest QR version than can hold these segments.
     fn from_segments(segments: &[&Segment<'_>]) -> Option<Version> {
-        for v in (1..=40).map(|k| Version(k)) {
-            if v.max_data() * 8 >= segments.iter().map(|s| s.total_size_bits(v)).sum() {
-                return Some(v);
-            }
-        }
-        None
+        (1..=40)
+            .map(Version)
+            .find(|&v| v.max_data() * 8 >= segments.iter().map(|s| s.total_size_bits(v)).sum())
     }
 
     fn width(&self) -> u8 {

From 7b6de57e0b2d1e62becfa3aac063c4c58d2c2c42 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20B=C3=B6hler?= <witcher@wiredspace.de>
Date: Sat, 19 Oct 2024 10:22:47 +0200
Subject: [PATCH 0538/1530] drm/panic: remove unnecessary borrow in
 alignment_pattern
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The function `alignment_pattern` returns a static reference to a `u8`
slice. The borrow of the returned element in `ALIGNMENT_PATTERNS` is
already a reference as defined in the array definition above so this
borrow is unnecessary and removed by the compiler. Clippy notes this in
`needless_borrow`:

    error: this expression creates a reference which is immediately dereferenced by the compiler
       --> drivers/gpu/drm/drm_panic_qr.rs:245:9
        |
    245 |         &ALIGNMENT_PATTERNS[self.0 - 1]
        |         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ help: change this to: `ALIGNMENT_PATTERNS[self.0 - 1]`
        |
        = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#needless_borrow
        = note: `-D clippy::needless-borrow` implied by `-D warnings`
        = help: to override `-D warnings` add `#[allow(clippy::needless_borrow)]`

Remove the unnecessary borrow.

Fixes: cb5164ac43d0 ("drm/panic: Add a QR code panic screen")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1123
Signed-off-by: Thomas Böhler <witcher@wiredspace.de>
Reviewed-by: Jocelyn Falempe <jfalempe@redhat.com>
Link: https://lore.kernel.org/r/20241019084048.22336-3-witcher@wiredspace.de
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 drivers/gpu/drm/drm_panic_qr.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs
index 76decf49e6785..7adfaa3d62222 100644
--- a/drivers/gpu/drm/drm_panic_qr.rs
+++ b/drivers/gpu/drm/drm_panic_qr.rs
@@ -239,7 +239,7 @@ impl Version {
     }
 
     fn alignment_pattern(&self) -> &'static [u8] {
-        &ALIGNMENT_PATTERNS[self.0 - 1]
+        ALIGNMENT_PATTERNS[self.0 - 1]
     }
 
     fn poly(&self) -> &'static [u8] {

From ae75c40117b53ae3d91dfc9d0bf06984a079f044 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20B=C3=B6hler?= <witcher@wiredspace.de>
Date: Sat, 19 Oct 2024 10:22:48 +0200
Subject: [PATCH 0539/1530] drm/panic: prefer eliding lifetimes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Eliding lifetimes when possible instead of specifying them directly is
both shorter and easier to read. Clippy notes this in the
`needless_lifetimes` lint:

    error: the following explicit lifetimes could be elided: 'b
       --> drivers/gpu/drm/drm_panic_qr.rs:479:16
        |
    479 |     fn new<'a, 'b>(segments: &[&Segment<'b>], data: &'a mut [u8]) -> Option<EncodedMsg<'a>> {
        |                ^^                       ^^
        |
        = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#needless_lifetimes
        = note: `-D clippy::needless-lifetimes` implied by `-D warnings`
        = help: to override `-D warnings` add `#[allow(clippy::needless_lifetimes)]`
    help: elide the lifetimes
        |
    479 -     fn new<'a, 'b>(segments: &[&Segment<'b>], data: &'a mut [u8]) -> Option<EncodedMsg<'a>> {
    479 +     fn new<'a>(segments: &[&Segment<'_>], data: &'a mut [u8]) -> Option<EncodedMsg<'a>> {
        |

Remove the explicit lifetime annotation in favour of an elided lifetime.

Fixes: cb5164ac43d0 ("drm/panic: Add a QR code panic screen")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1123
Signed-off-by: Thomas Böhler <witcher@wiredspace.de>
Reviewed-by: Jocelyn Falempe <jfalempe@redhat.com>
Link: https://lore.kernel.org/r/20241019084048.22336-4-witcher@wiredspace.de
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 drivers/gpu/drm/drm_panic_qr.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs
index 7adfaa3d62222..767a8eb0acec9 100644
--- a/drivers/gpu/drm/drm_panic_qr.rs
+++ b/drivers/gpu/drm/drm_panic_qr.rs
@@ -476,7 +476,7 @@ struct EncodedMsg<'a> {
 /// Data to be put in the QR code, with correct segment encoding, padding, and
 /// Error Code Correction.
 impl EncodedMsg<'_> {
-    fn new<'a, 'b>(segments: &[&Segment<'b>], data: &'a mut [u8]) -> Option<EncodedMsg<'a>> {
+    fn new<'a>(segments: &[&Segment<'_>], data: &'a mut [u8]) -> Option<EncodedMsg<'a>> {
         let version = Version::from_segments(segments)?;
         let ec_size = version.ec_size();
         let g1_blocks = version.g1_blocks();

From da13129a3f2a75d49469e1d6f7dcefac2d11d205 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20B=C3=B6hler?= <witcher@wiredspace.de>
Date: Sat, 19 Oct 2024 10:22:49 +0200
Subject: [PATCH 0540/1530] drm/panic: remove redundant field when assigning
 value
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rust allows initializing fields of a struct without specifying the
attribute that is assigned if the variable has the same name. In this
instance this is done for all other attributes of the struct except for
`data`. Clippy notes the redundant field name:

    error: redundant field names in struct initialization
    --> drivers/gpu/drm/drm_panic_qr.rs:495:13
        |
    495 |             data: data,
        |             ^^^^^^^^^^ help: replace it with: `data`
        |
        = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#redundant_field_names
        = note: `-D clippy::redundant-field-names` implied by `-D warnings`
        = help: to override `-D warnings` add `#[allow(clippy::redundant_field_names)]`

Remove the redundant `data` in the assignment to be consistent.

Fixes: cb5164ac43d0 ("drm/panic: Add a QR code panic screen")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1123
Signed-off-by: Thomas Böhler <witcher@wiredspace.de>
Reviewed-by: Jocelyn Falempe <jfalempe@redhat.com>
Link: https://lore.kernel.org/r/20241019084048.22336-5-witcher@wiredspace.de
[ Reworded to add Clippy warning like it is done in the rest of the
  series. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 drivers/gpu/drm/drm_panic_qr.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs
index 767a8eb0acec9..5b2386a515fa6 100644
--- a/drivers/gpu/drm/drm_panic_qr.rs
+++ b/drivers/gpu/drm/drm_panic_qr.rs
@@ -489,7 +489,7 @@ impl EncodedMsg<'_> {
         data.fill(0);
 
         let mut em = EncodedMsg {
-            data: data,
+            data,
             ec_size,
             g1_blocks,
             g2_blocks,

From 5bb698e6fc514ddd9e23b6649b29a0934d8d8586 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20B=C3=B6hler?= <witcher@wiredspace.de>
Date: Sat, 19 Oct 2024 10:22:50 +0200
Subject: [PATCH 0541/1530] drm/panic: correctly indent continuation of line in
 list item
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It is common practice in Rust to indent the next line the same amount of
space as the previous one if both belong to the same list item. Clippy
checks for this with the lint `doc_lazy_continuation`.

    error: doc list item without indentation
    --> drivers/gpu/drm/drm_panic_qr.rs:979:5
        |
    979 | /// conversion to numeric segments.
        |     ^
        |
        = help: if this is supposed to be its own paragraph, add a blank line
        = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#doc_lazy_continuation
        = note: `-D clippy::doc-lazy-continuation` implied by `-D warnings`
        = help: to override `-D warnings` add `#[allow(clippy::doc_lazy_continuation)]`
    help: indent this line
        |
    979 | ///   conversion to numeric segments.
        |     ++

Indent the offending line by 2 more spaces to remove this Clippy error.

Fixes: cb5164ac43d0 ("drm/panic: Add a QR code panic screen")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1123
Signed-off-by: Thomas Böhler <witcher@wiredspace.de>
Reviewed-by: Jocelyn Falempe <jfalempe@redhat.com>
Link: https://lore.kernel.org/r/20241019084048.22336-6-witcher@wiredspace.de
[ Reworded to indent Clippy's message. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 drivers/gpu/drm/drm_panic_qr.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs
index 5b2386a515fa6..58c46f366f761 100644
--- a/drivers/gpu/drm/drm_panic_qr.rs
+++ b/drivers/gpu/drm/drm_panic_qr.rs
@@ -976,7 +976,7 @@ pub unsafe extern "C" fn drm_panic_qr_generate(
 /// * `url_len`: Length of the URL.
 ///
 /// * If `url_len` > 0, remove the 2 segments header/length and also count the
-/// conversion to numeric segments.
+///   conversion to numeric segments.
 /// * If `url_len` = 0, only removes 3 bytes for 1 binary segment.
 #[no_mangle]
 pub extern "C" fn drm_panic_qr_max_data_size(version: u8, url_len: usize) -> usize {

From 27aef8a52e4b7f120ce47cd638d9d83065b759d2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20B=C3=B6hler?= <witcher@wiredspace.de>
Date: Sat, 19 Oct 2024 10:22:51 +0200
Subject: [PATCH 0542/1530] drm/panic: allow verbose boolean for clarity
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Clippy complains about a non-minimal boolean expression with
`nonminimal_bool`:

    error: this boolean expression can be simplified
       --> drivers/gpu/drm/drm_panic_qr.rs:722:9
        |
    722 |         (x < 8 && y < 8) || (x < 8 && y >= end) || (x >= end && y < 8)
        |         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
        |
        = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#nonminimal_bool
        = note: `-D clippy::nonminimal-bool` implied by `-D warnings`
        = help: to override `-D warnings` add `#[allow(clippy::nonminimal_bool)]`
    help: try
        |
    722 |         !(x >= 8 || y >= 8 && y < end) || (x >= end && y < 8)
        |         ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    722 |         (y >= end || y < 8) && x < 8 || (x >= end && y < 8)
        |         ~~~~~~~~~~~~~~~~~~~~~~~~~~~~

While this can be useful in a lot of cases, it isn't here because the
line expresses clearly what the intention is. Simplifying the expression
means losing clarity, so opt-out of this lint for the offending line.

Fixes: cb5164ac43d0 ("drm/panic: Add a QR code panic screen")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1123
Signed-off-by: Thomas Böhler <witcher@wiredspace.de>
Reviewed-by: Jocelyn Falempe <jfalempe@redhat.com>
Link: https://lore.kernel.org/r/20241019084048.22336-7-witcher@wiredspace.de
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 drivers/gpu/drm/drm_panic_qr.rs | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs
index 58c46f366f761..2d4e367f0fcd3 100644
--- a/drivers/gpu/drm/drm_panic_qr.rs
+++ b/drivers/gpu/drm/drm_panic_qr.rs
@@ -719,7 +719,10 @@ impl QrImage<'_> {
 
     fn is_finder(&self, x: u8, y: u8) -> bool {
         let end = self.width - 8;
-        (x < 8 && y < 8) || (x < 8 && y >= end) || (x >= end && y < 8)
+        #[expect(clippy::nonminimal_bool)]
+        {
+            (x < 8 && y < 8) || (x < 8 && y >= end) || (x >= end && y < 8)
+        }
     }
 
     // Alignment pattern: 5x5 squares in a grid.

From 06b919e3fedf4798a1f0f60e0b67caa192f724a7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20B=C3=B6hler?= <witcher@wiredspace.de>
Date: Sat, 19 Oct 2024 10:22:52 +0200
Subject: [PATCH 0543/1530] drm/panic: allow verbose version check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Clippy warns about a reimplementation of `RangeInclusive::contains`:

    error: manual `!RangeInclusive::contains` implementation
       --> drivers/gpu/drm/drm_panic_qr.rs:986:8
        |
    986 |     if version < 1 || version > 40 {
        |        ^^^^^^^^^^^^^^^^^^^^^^^^^^^ help: use: `!(1..=40).contains(&version)`
        |
        = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#manual_range_contains
        = note: `-D clippy::manual-range-contains` implied by `-D warnings`
        = help: to override `-D warnings` add `#[allow(clippy::manual_range_contains)]`

Ignore this and keep the current implementation as that makes it easier
to read.

Fixes: cb5164ac43d0 ("drm/panic: Add a QR code panic screen")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1123
Signed-off-by: Thomas Böhler <witcher@wiredspace.de>
Reviewed-by: Jocelyn Falempe <jfalempe@redhat.com>
Link: https://lore.kernel.org/r/20241019084048.22336-8-witcher@wiredspace.de
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 drivers/gpu/drm/drm_panic_qr.rs | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs
index 2d4e367f0fcd3..09500cddc009b 100644
--- a/drivers/gpu/drm/drm_panic_qr.rs
+++ b/drivers/gpu/drm/drm_panic_qr.rs
@@ -983,6 +983,7 @@ pub unsafe extern "C" fn drm_panic_qr_generate(
 /// * If `url_len` = 0, only removes 3 bytes for 1 binary segment.
 #[no_mangle]
 pub extern "C" fn drm_panic_qr_max_data_size(version: u8, url_len: usize) -> usize {
+    #[expect(clippy::manual_range_contains)]
     if version < 1 || version > 40 {
         return 0;
     }

From d0c3a7aa814c091843ccca467c02078db9da4e1e Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Mon, 21 Oct 2024 00:04:05 -0700
Subject: [PATCH 0544/1530] Input: serio_raw - fix uninitialized variable bug

Recent conversion of the driver to use guard notation for locks and
other resources introduced a bug: "written" variable that is supposed to
hold number of bytes successfully written was not initialized.

Fix it by initializing the variable with 0.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202410201730.ItNhUTIv-lkp@intel.com/
Fixes: 5b53a9d40c4f ("Input: serio_raw - use guard notation for locks and other resources")
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/serio_raw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/serio/serio_raw.c b/drivers/input/serio/serio_raw.c
index e058fef07f576..4d63950889860 100644
--- a/drivers/input/serio/serio_raw.c
+++ b/drivers/input/serio/serio_raw.c
@@ -185,7 +185,7 @@ static ssize_t serio_raw_write(struct file *file, const char __user *buffer,
 {
 	struct serio_raw_client *client = file->private_data;
 	struct serio_raw *serio_raw = client->serio_raw;
-	int written;
+	int written = 0;
 	unsigned char c;
 
 	scoped_guard(mutex_intr, &serio_raw_mutex) {

From 6951ec3f6ea9a814a1b7f6c932a9ed663e53412d Mon Sep 17 00:00:00 2001
From: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Date: Tue, 8 Oct 2024 09:41:37 +0200
Subject: [PATCH 0545/1530] dt-bindings: input: mediatek,pmic-keys: Add
 compatible for MT6359 keys

Add a compatible for the keys found on the MT6359 PMIC.

Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Macpaul Lin <macpaul.lin@mediatek.com>
Link: https://lore.kernel.org/r/20241008074137.20269-1-angelogioacchino.delregno@collabora.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml b/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml
index 70567d92c746e..bba55a81e6cc7 100644
--- a/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml
+++ b/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml
@@ -28,6 +28,7 @@ properties:
       - mediatek,mt6331-keys
       - mediatek,mt6357-keys
       - mediatek,mt6358-keys
+      - mediatek,mt6359-keys
       - mediatek,mt6397-keys
 
   power-off-time-sec: true

From 83bce34420eaf91506957703bf9a31d8581ed6cb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@baylibre.com>
Date: Thu, 10 Oct 2024 22:36:24 +0200
Subject: [PATCH 0546/1530] power: Switch back to struct
 platform_driver::remove()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 0edb555a65d1 ("platform: Make platform_driver::remove()
return void") .remove() is (again) the right callback to implement for
platform drivers.

Convert all platform drivers below drivers/power/ to use .remove(), with
the eventual goal to drop struct platform_driver::remove_new(). As
.remove() and .remove_new() have the same prototypes, conversion is done
by just changing the structure member name in the driver initializer.

While touching these files, make indention of the struct initializer
consistent in several files.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Link: https://lore.kernel.org/r/20241010203622.839625-6-u.kleine-koenig@baylibre.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/at91-poweroff.c       | 2 +-
 drivers/power/reset/at91-reset.c          | 2 +-
 drivers/power/reset/at91-sama5d2_shdwc.c  | 2 +-
 drivers/power/reset/ltc2952-poweroff.c    | 2 +-
 drivers/power/reset/qnap-poweroff.c       | 2 +-
 drivers/power/supply/ab8500_btemp.c       | 2 +-
 drivers/power/supply/ab8500_chargalg.c    | 2 +-
 drivers/power/supply/ab8500_charger.c     | 2 +-
 drivers/power/supply/ab8500_fg.c          | 2 +-
 drivers/power/supply/acer_a500_battery.c  | 2 +-
 drivers/power/supply/act8945a_charger.c   | 2 +-
 drivers/power/supply/charger-manager.c    | 2 +-
 drivers/power/supply/cpcap-battery.c      | 2 +-
 drivers/power/supply/cpcap-charger.c      | 2 +-
 drivers/power/supply/da9030_battery.c     | 2 +-
 drivers/power/supply/da9052-battery.c     | 2 +-
 drivers/power/supply/da9150-charger.c     | 2 +-
 drivers/power/supply/ipaq_micro_battery.c | 2 +-
 drivers/power/supply/isp1704_charger.c    | 2 +-
 drivers/power/supply/lp8788-charger.c     | 2 +-
 drivers/power/supply/max14577_charger.c   | 2 +-
 drivers/power/supply/max77650-charger.c   | 2 +-
 drivers/power/supply/max77693_charger.c   | 2 +-
 drivers/power/supply/max8925_power.c      | 2 +-
 drivers/power/supply/pcf50633-charger.c   | 2 +-
 drivers/power/supply/qcom_smbb.c          | 8 ++++----
 drivers/power/supply/sc2731_charger.c     | 2 +-
 drivers/power/supply/tps65090-charger.c   | 2 +-
 drivers/power/supply/tps65217_charger.c   | 2 +-
 drivers/power/supply/twl4030_charger.c    | 2 +-
 drivers/power/supply/wm831x_power.c       | 2 +-
 drivers/power/supply/wm8350_power.c       | 2 +-
 drivers/power/supply/wm97xx_battery.c     | 2 +-
 33 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/drivers/power/reset/at91-poweroff.c b/drivers/power/reset/at91-poweroff.c
index 93eece0278652..7bc779055cf3f 100644
--- a/drivers/power/reset/at91-poweroff.c
+++ b/drivers/power/reset/at91-poweroff.c
@@ -223,7 +223,7 @@ MODULE_DEVICE_TABLE(of, at91_poweroff_of_match);
 
 static struct platform_driver at91_poweroff_driver = {
 	.probe = at91_poweroff_probe,
-	.remove_new = at91_poweroff_remove,
+	.remove = at91_poweroff_remove,
 	.driver = {
 		.name = "at91-poweroff",
 		.of_match_table = at91_poweroff_of_match,
diff --git a/drivers/power/reset/at91-reset.c b/drivers/power/reset/at91-reset.c
index 16512654295f5..036b18a1f90f8 100644
--- a/drivers/power/reset/at91-reset.c
+++ b/drivers/power/reset/at91-reset.c
@@ -427,7 +427,7 @@ static void at91_reset_remove(struct platform_device *pdev)
 
 static struct platform_driver at91_reset_driver = {
 	.probe = at91_reset_probe,
-	.remove_new = at91_reset_remove,
+	.remove = at91_reset_remove,
 	.driver = {
 		.name = "at91-reset",
 		.of_match_table = at91_reset_of_match,
diff --git a/drivers/power/reset/at91-sama5d2_shdwc.c b/drivers/power/reset/at91-sama5d2_shdwc.c
index 959ce0dbe91d1..edb0df86aff45 100644
--- a/drivers/power/reset/at91-sama5d2_shdwc.c
+++ b/drivers/power/reset/at91-sama5d2_shdwc.c
@@ -441,7 +441,7 @@ static void at91_shdwc_remove(struct platform_device *pdev)
 
 static struct platform_driver at91_shdwc_driver = {
 	.probe = at91_shdwc_probe,
-	.remove_new = at91_shdwc_remove,
+	.remove = at91_shdwc_remove,
 	.driver = {
 		.name = "at91-shdwc",
 		.of_match_table = at91_shdwc_of_match,
diff --git a/drivers/power/reset/ltc2952-poweroff.c b/drivers/power/reset/ltc2952-poweroff.c
index fa25fbd539343..1a6fc8d38e206 100644
--- a/drivers/power/reset/ltc2952-poweroff.c
+++ b/drivers/power/reset/ltc2952-poweroff.c
@@ -305,7 +305,7 @@ MODULE_DEVICE_TABLE(of, of_ltc2952_poweroff_match);
 
 static struct platform_driver ltc2952_poweroff_driver = {
 	.probe = ltc2952_poweroff_probe,
-	.remove_new = ltc2952_poweroff_remove,
+	.remove = ltc2952_poweroff_remove,
 	.driver = {
 		.name = "ltc2952-poweroff",
 		.of_match_table = of_ltc2952_poweroff_match,
diff --git a/drivers/power/reset/qnap-poweroff.c b/drivers/power/reset/qnap-poweroff.c
index e0f2ff6b147c1..f7d8fc935d519 100644
--- a/drivers/power/reset/qnap-poweroff.c
+++ b/drivers/power/reset/qnap-poweroff.c
@@ -118,7 +118,7 @@ static void qnap_power_off_remove(struct platform_device *pdev)
 
 static struct platform_driver qnap_power_off_driver = {
 	.probe	= qnap_power_off_probe,
-	.remove_new = qnap_power_off_remove,
+	.remove	= qnap_power_off_remove,
 	.driver	= {
 		.name	= "qnap_power_off",
 		.of_match_table = of_match_ptr(qnap_power_off_of_match_table),
diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c
index 87c9b8e744b31..37039e28fc4bd 100644
--- a/drivers/power/supply/ab8500_btemp.c
+++ b/drivers/power/supply/ab8500_btemp.c
@@ -818,7 +818,7 @@ MODULE_DEVICE_TABLE(of, ab8500_btemp_match);
 
 struct platform_driver ab8500_btemp_driver = {
 	.probe = ab8500_btemp_probe,
-	.remove_new = ab8500_btemp_remove,
+	.remove = ab8500_btemp_remove,
 	.driver = {
 		.name = "ab8500-btemp",
 		.of_match_table = ab8500_btemp_match,
diff --git a/drivers/power/supply/ab8500_chargalg.c b/drivers/power/supply/ab8500_chargalg.c
index 854491ad3ecd5..14e1b448bd39b 100644
--- a/drivers/power/supply/ab8500_chargalg.c
+++ b/drivers/power/supply/ab8500_chargalg.c
@@ -1837,7 +1837,7 @@ static const struct of_device_id ab8500_chargalg_match[] = {
 
 struct platform_driver ab8500_chargalg_driver = {
 	.probe = ab8500_chargalg_probe,
-	.remove_new = ab8500_chargalg_remove,
+	.remove = ab8500_chargalg_remove,
 	.driver = {
 		.name = "ab8500_chargalg",
 		.of_match_table = ab8500_chargalg_match,
diff --git a/drivers/power/supply/ab8500_charger.c b/drivers/power/supply/ab8500_charger.c
index 93181ebfb3247..cece8d6753ac1 100644
--- a/drivers/power/supply/ab8500_charger.c
+++ b/drivers/power/supply/ab8500_charger.c
@@ -3711,7 +3711,7 @@ MODULE_DEVICE_TABLE(of, ab8500_charger_match);
 
 static struct platform_driver ab8500_charger_driver = {
 	.probe = ab8500_charger_probe,
-	.remove_new = ab8500_charger_remove,
+	.remove = ab8500_charger_remove,
 	.driver = {
 		.name = "ab8500-charger",
 		.of_match_table = ab8500_charger_match,
diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c
index a71903b1bf781..78871a2143de3 100644
--- a/drivers/power/supply/ab8500_fg.c
+++ b/drivers/power/supply/ab8500_fg.c
@@ -3242,7 +3242,7 @@ MODULE_DEVICE_TABLE(of, ab8500_fg_match);
 
 struct platform_driver ab8500_fg_driver = {
 	.probe = ab8500_fg_probe,
-	.remove_new = ab8500_fg_remove,
+	.remove = ab8500_fg_remove,
 	.driver = {
 		.name = "ab8500-fg",
 		.of_match_table = ab8500_fg_match,
diff --git a/drivers/power/supply/acer_a500_battery.c b/drivers/power/supply/acer_a500_battery.c
index 58e7b2eac68f9..39d85b11a13c2 100644
--- a/drivers/power/supply/acer_a500_battery.c
+++ b/drivers/power/supply/acer_a500_battery.c
@@ -286,7 +286,7 @@ static struct platform_driver a500_battery_driver = {
 		.pm = &a500_battery_pm_ops,
 	},
 	.probe = a500_battery_probe,
-	.remove_new = a500_battery_remove,
+	.remove = a500_battery_remove,
 };
 module_platform_driver(a500_battery_driver);
 
diff --git a/drivers/power/supply/act8945a_charger.c b/drivers/power/supply/act8945a_charger.c
index 51122bfbf196c..b2b82f97a4712 100644
--- a/drivers/power/supply/act8945a_charger.c
+++ b/drivers/power/supply/act8945a_charger.c
@@ -651,7 +651,7 @@ static struct platform_driver act8945a_charger_driver = {
 		.name = "act8945a-charger",
 	},
 	.probe	= act8945a_charger_probe,
-	.remove_new = act8945a_charger_remove,
+	.remove	= act8945a_charger_remove,
 };
 module_platform_driver(act8945a_charger_driver);
 
diff --git a/drivers/power/supply/charger-manager.c b/drivers/power/supply/charger-manager.c
index 858e2b77ee5b0..9a1ba051e62fb 100644
--- a/drivers/power/supply/charger-manager.c
+++ b/drivers/power/supply/charger-manager.c
@@ -1740,7 +1740,7 @@ static struct platform_driver charger_manager_driver = {
 		.of_match_table = charger_manager_match,
 	},
 	.probe = charger_manager_probe,
-	.remove_new = charger_manager_remove,
+	.remove = charger_manager_remove,
 	.id_table = charger_manager_id,
 };
 
diff --git a/drivers/power/supply/cpcap-battery.c b/drivers/power/supply/cpcap-battery.c
index 30ec76cdf34b0..813037c00ded5 100644
--- a/drivers/power/supply/cpcap-battery.c
+++ b/drivers/power/supply/cpcap-battery.c
@@ -1169,7 +1169,7 @@ static struct platform_driver cpcap_battery_driver = {
 		.of_match_table = of_match_ptr(cpcap_battery_id_table),
 	},
 	.probe	= cpcap_battery_probe,
-	.remove_new = cpcap_battery_remove,
+	.remove	= cpcap_battery_remove,
 };
 module_platform_driver(cpcap_battery_driver);
 
diff --git a/drivers/power/supply/cpcap-charger.c b/drivers/power/supply/cpcap-charger.c
index 91e7292d86bb7..7781b45a67a7d 100644
--- a/drivers/power/supply/cpcap-charger.c
+++ b/drivers/power/supply/cpcap-charger.c
@@ -969,7 +969,7 @@ static struct platform_driver cpcap_charger_driver = {
 		.of_match_table = cpcap_charger_id_table,
 	},
 	.shutdown = cpcap_charger_shutdown,
-	.remove_new = cpcap_charger_remove,
+	.remove = cpcap_charger_remove,
 };
 module_platform_driver(cpcap_charger_driver);
 
diff --git a/drivers/power/supply/da9030_battery.c b/drivers/power/supply/da9030_battery.c
index b89604a8c0199..34328f5d556e2 100644
--- a/drivers/power/supply/da9030_battery.c
+++ b/drivers/power/supply/da9030_battery.c
@@ -571,7 +571,7 @@ static struct platform_driver da903x_battery_driver = {
 		.name	= "da903x-battery",
 	},
 	.probe = da9030_battery_probe,
-	.remove_new = da9030_battery_remove,
+	.remove = da9030_battery_remove,
 };
 
 module_platform_driver(da903x_battery_driver);
diff --git a/drivers/power/supply/da9052-battery.c b/drivers/power/supply/da9052-battery.c
index 0d84c42c624e0..6f17e2fa1a28e 100644
--- a/drivers/power/supply/da9052-battery.c
+++ b/drivers/power/supply/da9052-battery.c
@@ -648,7 +648,7 @@ static void da9052_bat_remove(struct platform_device *pdev)
 
 static struct platform_driver da9052_bat_driver = {
 	.probe = da9052_bat_probe,
-	.remove_new = da9052_bat_remove,
+	.remove = da9052_bat_remove,
 	.driver = {
 		.name = "da9052-bat",
 	},
diff --git a/drivers/power/supply/da9150-charger.c b/drivers/power/supply/da9150-charger.c
index b13cecd84f589..27f36ef5b88dc 100644
--- a/drivers/power/supply/da9150-charger.c
+++ b/drivers/power/supply/da9150-charger.c
@@ -636,7 +636,7 @@ static struct platform_driver da9150_charger_driver = {
 		.name = "da9150-charger",
 	},
 	.probe = da9150_charger_probe,
-	.remove_new = da9150_charger_remove,
+	.remove = da9150_charger_remove,
 };
 
 module_platform_driver(da9150_charger_driver);
diff --git a/drivers/power/supply/ipaq_micro_battery.c b/drivers/power/supply/ipaq_micro_battery.c
index 66cc649f702af..7e0568a5353f1 100644
--- a/drivers/power/supply/ipaq_micro_battery.c
+++ b/drivers/power/supply/ipaq_micro_battery.c
@@ -302,7 +302,7 @@ static struct platform_driver micro_batt_device_driver = {
 		.pm	= &micro_batt_dev_pm_ops,
 	},
 	.probe		= micro_batt_probe,
-	.remove_new	= micro_batt_remove,
+	.remove		= micro_batt_remove,
 };
 module_platform_driver(micro_batt_device_driver);
 
diff --git a/drivers/power/supply/isp1704_charger.c b/drivers/power/supply/isp1704_charger.c
index 860d8614c98fd..237912a922724 100644
--- a/drivers/power/supply/isp1704_charger.c
+++ b/drivers/power/supply/isp1704_charger.c
@@ -501,7 +501,7 @@ static struct platform_driver isp1704_charger_driver = {
 		.of_match_table = of_match_ptr(omap_isp1704_of_match),
 	},
 	.probe = isp1704_charger_probe,
-	.remove_new = isp1704_charger_remove,
+	.remove = isp1704_charger_remove,
 };
 
 module_platform_driver(isp1704_charger_driver);
diff --git a/drivers/power/supply/lp8788-charger.c b/drivers/power/supply/lp8788-charger.c
index 72b170b4ac46a..f0a680c155c48 100644
--- a/drivers/power/supply/lp8788-charger.c
+++ b/drivers/power/supply/lp8788-charger.c
@@ -716,7 +716,7 @@ static void lp8788_charger_remove(struct platform_device *pdev)
 
 static struct platform_driver lp8788_charger_driver = {
 	.probe = lp8788_charger_probe,
-	.remove_new = lp8788_charger_remove,
+	.remove = lp8788_charger_remove,
 	.driver = {
 		.name = LP8788_DEV_CHARGER,
 	},
diff --git a/drivers/power/supply/max14577_charger.c b/drivers/power/supply/max14577_charger.c
index b28c04157709a..1cef2f860b5fc 100644
--- a/drivers/power/supply/max14577_charger.c
+++ b/drivers/power/supply/max14577_charger.c
@@ -634,7 +634,7 @@ static struct platform_driver max14577_charger_driver = {
 		.of_match_table = of_max14577_charger_dt_match,
 	},
 	.probe		= max14577_charger_probe,
-	.remove_new	= max14577_charger_remove,
+	.remove		= max14577_charger_remove,
 	.id_table	= max14577_charger_id,
 };
 module_platform_driver(max14577_charger_driver);
diff --git a/drivers/power/supply/max77650-charger.c b/drivers/power/supply/max77650-charger.c
index 818e13c613e35..5f58c0c24b4d6 100644
--- a/drivers/power/supply/max77650-charger.c
+++ b/drivers/power/supply/max77650-charger.c
@@ -364,7 +364,7 @@ static struct platform_driver max77650_charger_driver = {
 		.of_match_table = max77650_charger_of_match,
 	},
 	.probe = max77650_charger_probe,
-	.remove_new = max77650_charger_remove,
+	.remove = max77650_charger_remove,
 };
 module_platform_driver(max77650_charger_driver);
 
diff --git a/drivers/power/supply/max77693_charger.c b/drivers/power/supply/max77693_charger.c
index 4caac142c4285..cdea35c0d1de1 100644
--- a/drivers/power/supply/max77693_charger.c
+++ b/drivers/power/supply/max77693_charger.c
@@ -798,7 +798,7 @@ static struct platform_driver max77693_charger_driver = {
 		.name	= "max77693-charger",
 	},
 	.probe		= max77693_charger_probe,
-	.remove_new	= max77693_charger_remove,
+	.remove		= max77693_charger_remove,
 	.id_table	= max77693_charger_id,
 };
 module_platform_driver(max77693_charger_driver);
diff --git a/drivers/power/supply/max8925_power.c b/drivers/power/supply/max8925_power.c
index fc24a6d3b63d8..d753145de3bb3 100644
--- a/drivers/power/supply/max8925_power.c
+++ b/drivers/power/supply/max8925_power.c
@@ -563,7 +563,7 @@ static void max8925_power_remove(struct platform_device *pdev)
 
 static struct platform_driver max8925_power_driver = {
 	.probe	= max8925_power_probe,
-	.remove_new = max8925_power_remove,
+	.remove	= max8925_power_remove,
 	.driver	= {
 		.name	= "max8925-power",
 	},
diff --git a/drivers/power/supply/pcf50633-charger.c b/drivers/power/supply/pcf50633-charger.c
index 0e980522fee51..0136bc87b105e 100644
--- a/drivers/power/supply/pcf50633-charger.c
+++ b/drivers/power/supply/pcf50633-charger.c
@@ -455,7 +455,7 @@ static struct platform_driver pcf50633_mbc_driver = {
 		.name = "pcf50633-mbc",
 	},
 	.probe = pcf50633_mbc_probe,
-	.remove_new = pcf50633_mbc_remove,
+	.remove = pcf50633_mbc_remove,
 };
 
 module_platform_driver(pcf50633_mbc_driver);
diff --git a/drivers/power/supply/qcom_smbb.c b/drivers/power/supply/qcom_smbb.c
index 4e57762e27bad..a79563f6ff7a0 100644
--- a/drivers/power/supply/qcom_smbb.c
+++ b/drivers/power/supply/qcom_smbb.c
@@ -1017,10 +1017,10 @@ static const struct of_device_id smbb_charger_id_table[] = {
 MODULE_DEVICE_TABLE(of, smbb_charger_id_table);
 
 static struct platform_driver smbb_charger_driver = {
-	.probe	  = smbb_charger_probe,
-	.remove_new	 = smbb_charger_remove,
-	.driver	 = {
-		.name   = "qcom-smbb",
+	.probe = smbb_charger_probe,
+	.remove = smbb_charger_remove,
+	.driver = {
+		.name = "qcom-smbb",
 		.of_match_table = smbb_charger_id_table,
 	},
 };
diff --git a/drivers/power/supply/sc2731_charger.c b/drivers/power/supply/sc2731_charger.c
index b3d8b1ca97da7..50d5157af9277 100644
--- a/drivers/power/supply/sc2731_charger.c
+++ b/drivers/power/supply/sc2731_charger.c
@@ -530,7 +530,7 @@ static struct platform_driver sc2731_charger_driver = {
 		.of_match_table = sc2731_charger_of_match,
 	},
 	.probe = sc2731_charger_probe,
-	.remove_new = sc2731_charger_remove,
+	.remove = sc2731_charger_remove,
 };
 
 module_platform_driver(sc2731_charger_driver);
diff --git a/drivers/power/supply/tps65090-charger.c b/drivers/power/supply/tps65090-charger.c
index d41595764caa5..d65193e410a62 100644
--- a/drivers/power/supply/tps65090-charger.c
+++ b/drivers/power/supply/tps65090-charger.c
@@ -343,7 +343,7 @@ static struct platform_driver tps65090_charger_driver = {
 		.of_match_table = of_tps65090_charger_match,
 	},
 	.probe	= tps65090_charger_probe,
-	.remove_new = tps65090_charger_remove,
+	.remove = tps65090_charger_remove,
 };
 module_platform_driver(tps65090_charger_driver);
 
diff --git a/drivers/power/supply/tps65217_charger.c b/drivers/power/supply/tps65217_charger.c
index 2382749a2f531..6fff44e1ecac8 100644
--- a/drivers/power/supply/tps65217_charger.c
+++ b/drivers/power/supply/tps65217_charger.c
@@ -269,7 +269,7 @@ MODULE_DEVICE_TABLE(of, tps65217_charger_match_table);
 
 static struct platform_driver tps65217_charger_driver = {
 	.probe	= tps65217_charger_probe,
-	.remove_new = tps65217_charger_remove,
+	.remove	= tps65217_charger_remove,
 	.driver	= {
 		.name	= "tps65217-charger",
 		.of_match_table = of_match_ptr(tps65217_charger_match_table),
diff --git a/drivers/power/supply/twl4030_charger.c b/drivers/power/supply/twl4030_charger.c
index f3f1a0862e935..9dcb5457bef41 100644
--- a/drivers/power/supply/twl4030_charger.c
+++ b/drivers/power/supply/twl4030_charger.c
@@ -1133,7 +1133,7 @@ MODULE_DEVICE_TABLE(of, twl_bci_of_match);
 
 static struct platform_driver twl4030_bci_driver = {
 	.probe = twl4030_bci_probe,
-	.remove_new = twl4030_bci_remove,
+	.remove = twl4030_bci_remove,
 	.driver	= {
 		.name	= "twl4030_bci",
 		.of_match_table = of_match_ptr(twl_bci_of_match),
diff --git a/drivers/power/supply/wm831x_power.c b/drivers/power/supply/wm831x_power.c
index d56e499ac59fb..538055b29decb 100644
--- a/drivers/power/supply/wm831x_power.c
+++ b/drivers/power/supply/wm831x_power.c
@@ -720,7 +720,7 @@ static void wm831x_power_remove(struct platform_device *pdev)
 
 static struct platform_driver wm831x_power_driver = {
 	.probe = wm831x_power_probe,
-	.remove_new = wm831x_power_remove,
+	.remove = wm831x_power_remove,
 	.driver = {
 		.name = "wm831x-power",
 	},
diff --git a/drivers/power/supply/wm8350_power.c b/drivers/power/supply/wm8350_power.c
index 3f79ab6f6abf1..b0eb6e0ce8bcf 100644
--- a/drivers/power/supply/wm8350_power.c
+++ b/drivers/power/supply/wm8350_power.c
@@ -577,7 +577,7 @@ static void wm8350_power_remove(struct platform_device *pdev)
 
 static struct platform_driver wm8350_power_driver = {
 	.probe = wm8350_power_probe,
-	.remove_new = wm8350_power_remove,
+	.remove = wm8350_power_remove,
 	.driver = {
 		.name = "wm8350-power",
 	},
diff --git a/drivers/power/supply/wm97xx_battery.c b/drivers/power/supply/wm97xx_battery.c
index 1cc38d1437d91..b3b0c37a9dd2d 100644
--- a/drivers/power/supply/wm97xx_battery.c
+++ b/drivers/power/supply/wm97xx_battery.c
@@ -265,7 +265,7 @@ static struct platform_driver wm97xx_bat_driver = {
 #endif
 	},
 	.probe		= wm97xx_bat_probe,
-	.remove_new	= wm97xx_bat_remove,
+	.remove		= wm97xx_bat_remove,
 };
 
 module_platform_driver(wm97xx_bat_driver);

From 54c5dc52143e5b335b698f4e8810efa1f00787bf Mon Sep 17 00:00:00 2001
From: Tamir Duberstein <tamird@gmail.com>
Date: Wed, 9 Oct 2024 12:23:58 -0400
Subject: [PATCH 0547/1530] rust: exports: improve grammar in commentary

Commit e26fa546042a ("rust: kbuild: auto generate helper exports")
added an errant "the" where one was not needed; remove it.

Signed-off-by: Tamir Duberstein <tamird@gmail.com>
Reviewed-by: Dirk Behme <dirk.behme@gmail.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Link: https://lore.kernel.org/r/20241009162358.27735-1-tamird@gmail.com
[ Reworded title. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/exports.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/rust/exports.c b/rust/exports.c
index 82a037381798d..587f0e776aba5 100644
--- a/rust/exports.c
+++ b/rust/exports.c
@@ -3,9 +3,9 @@
  * A hack to export Rust symbols for loadable modules without having to redo
  * the entire `include/linux/export.h` logic in Rust.
  *
- * This requires the Rust's new/future `v0` mangling scheme because the default
- * one ("legacy") uses invalid characters for C identifiers (thus we cannot use
- * the `EXPORT_SYMBOL_*` macros).
+ * This requires Rust's new/future `v0` mangling scheme because the default one
+ * ("legacy") uses invalid characters for C identifiers (thus we cannot use the
+ * `EXPORT_SYMBOL_*` macros).
  *
  * All symbols are exported as GPL-only to guarantee no GPL-only feature is
  * accidentally exposed.

From d4d7c05f9656fd8e14c6977a54986264eb296ec8 Mon Sep 17 00:00:00 2001
From: Tamir Duberstein <tamird@gmail.com>
Date: Wed, 9 Oct 2024 12:25:30 -0400
Subject: [PATCH 0548/1530] rust: helpers: remove unnecessary header includes

Commit e26fa546042a ("rust: kbuild: auto generate helper exports")
removed the need for these by automatically generating the exports; it
removed the explicit uses of `EXPORT_SYMBOL_GPL` but didn't remove the
`#include <linux/export.h>`s.

Signed-off-by: Tamir Duberstein <tamird@gmail.com>
Reviewed-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Link: https://lore.kernel.org/r/20241009162553.27845-2-tamird@gmail.com
[ Reworded title. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/helpers/build_bug.c | 1 -
 rust/helpers/err.c       | 1 -
 rust/helpers/kunit.c     | 1 -
 rust/helpers/mutex.c     | 1 -
 rust/helpers/refcount.c  | 1 -
 rust/helpers/signal.c    | 1 -
 rust/helpers/spinlock.c  | 1 -
 rust/helpers/task.c      | 1 -
 rust/helpers/wait.c      | 1 -
 rust/helpers/workqueue.c | 1 -
 10 files changed, 10 deletions(-)

diff --git a/rust/helpers/build_bug.c b/rust/helpers/build_bug.c
index e994f7b5928c0..44e5794880373 100644
--- a/rust/helpers/build_bug.c
+++ b/rust/helpers/build_bug.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/export.h>
 #include <linux/errname.h>
 
 const char *rust_helper_errname(int err)
diff --git a/rust/helpers/err.c b/rust/helpers/err.c
index be3d45ef78a25..544c7cb866328 100644
--- a/rust/helpers/err.c
+++ b/rust/helpers/err.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/err.h>
-#include <linux/export.h>
 
 __force void *rust_helper_ERR_PTR(long err)
 {
diff --git a/rust/helpers/kunit.c b/rust/helpers/kunit.c
index 9d725067eb3bc..b85a4d394c118 100644
--- a/rust/helpers/kunit.c
+++ b/rust/helpers/kunit.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <kunit/test-bug.h>
-#include <linux/export.h>
 
 struct kunit *rust_helper_kunit_get_current_test(void)
 {
diff --git a/rust/helpers/mutex.c b/rust/helpers/mutex.c
index a17ca8cdb50ca..7e00680958ef1 100644
--- a/rust/helpers/mutex.c
+++ b/rust/helpers/mutex.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/export.h>
 #include <linux/mutex.h>
 
 void rust_helper_mutex_lock(struct mutex *lock)
diff --git a/rust/helpers/refcount.c b/rust/helpers/refcount.c
index f47afc148ec36..d6adbd2e45a18 100644
--- a/rust/helpers/refcount.c
+++ b/rust/helpers/refcount.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/export.h>
 #include <linux/refcount.h>
 
 refcount_t rust_helper_REFCOUNT_INIT(int n)
diff --git a/rust/helpers/signal.c b/rust/helpers/signal.c
index 63c407f80c26b..1a6bbe9438e28 100644
--- a/rust/helpers/signal.c
+++ b/rust/helpers/signal.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/export.h>
 #include <linux/sched/signal.h>
 
 int rust_helper_signal_pending(struct task_struct *t)
diff --git a/rust/helpers/spinlock.c b/rust/helpers/spinlock.c
index 775ed4d549aef..b7b0945e8b3cb 100644
--- a/rust/helpers/spinlock.c
+++ b/rust/helpers/spinlock.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/export.h>
 #include <linux/spinlock.h>
 
 void rust_helper___spin_lock_init(spinlock_t *lock, const char *name,
diff --git a/rust/helpers/task.c b/rust/helpers/task.c
index 7ac789232d11c..190fdb2c8e2f4 100644
--- a/rust/helpers/task.c
+++ b/rust/helpers/task.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/export.h>
 #include <linux/sched/task.h>
 
 struct task_struct *rust_helper_get_current(void)
diff --git a/rust/helpers/wait.c b/rust/helpers/wait.c
index c7336bbf27507..ae48e33d9da3b 100644
--- a/rust/helpers/wait.c
+++ b/rust/helpers/wait.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/export.h>
 #include <linux/wait.h>
 
 void rust_helper_init_wait(struct wait_queue_entry *wq_entry)
diff --git a/rust/helpers/workqueue.c b/rust/helpers/workqueue.c
index f59427acc3237..b2b82753509bf 100644
--- a/rust/helpers/workqueue.c
+++ b/rust/helpers/workqueue.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/export.h>
 #include <linux/workqueue.h>
 
 void rust_helper_init_work_with_key(struct work_struct *work, work_func_t func,

From e7a614cc8847f469370ea29604be966ee16f07e9 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Thu, 17 Oct 2024 21:11:49 +0300
Subject: [PATCH 0549/1530] dt-bindings: dma: qcom,gpi: Add SAR2130P compatible

Document compatible for GPI DMA controller on SAR2130P platform.

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20241017-sar2130p-dma-v1-1-e6aa6789f116@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/dma/qcom,gpi.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
index 4df4e61895d21..4ad56a409b9ca 100644
--- a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
+++ b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
@@ -26,6 +26,7 @@ properties:
           - enum:
               - qcom,qcm2290-gpi-dma
               - qcom,qdu1000-gpi-dma
+              - qcom,sar2130p-gpi-dma
               - qcom,sc7280-gpi-dma
               - qcom,sdx75-gpi-dma
               - qcom,sm6115-gpi-dma

From 3e482e2840546a3ff725d5adf8d0779ac1c3cf4f Mon Sep 17 00:00:00 2001
From: Fenghua Yu <fenghua.yu@intel.com>
Date: Fri, 18 Oct 2024 14:37:25 -0700
Subject: [PATCH 0550/1530] dmaengine: idxd: Move DSA/IAA device IDs to IDXD
 driver

Since the DSA/IAA device IDs are only used by the IDXD driver, there is
no need to define them as public IDs. Move their definitions to the IDXD
driver to limit their scope. This change helps reduce unnecessary
exposure of the device IDs in the global space, making the codebase
cleaner and better encapsulated.

There is no functional change.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: https://lore.kernel.org/r/20241018213725.4167413-1-fenghua.yu@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/registers.h | 4 ++++
 include/linux/pci_ids.h      | 3 ---
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h
index e16dbf9ab324c..c426511f21048 100644
--- a/drivers/dma/idxd/registers.h
+++ b/drivers/dma/idxd/registers.h
@@ -6,6 +6,10 @@
 #include <uapi/linux/idxd.h>
 
 /* PCI Config */
+#define PCI_DEVICE_ID_INTEL_DSA_GNRD	0x11fb
+#define PCI_DEVICE_ID_INTEL_DSA_DMR	0x1212
+#define PCI_DEVICE_ID_INTEL_IAA_DMR	0x1216
+
 #define DEVICE_VERSION_1		0x100
 #define DEVICE_VERSION_2		0x200
 
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 4cf6aaed5f35d..e4bddb9277956 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2709,9 +2709,6 @@
 #define PCI_DEVICE_ID_INTEL_82815_MC	0x1130
 #define PCI_DEVICE_ID_INTEL_82815_CGC	0x1132
 #define PCI_DEVICE_ID_INTEL_SST_TNG	0x119a
-#define PCI_DEVICE_ID_INTEL_DSA_GNRD	0x11fb
-#define PCI_DEVICE_ID_INTEL_DSA_DMR	0x1212
-#define PCI_DEVICE_ID_INTEL_IAA_DMR	0x1216
 #define PCI_DEVICE_ID_INTEL_82092AA_0	0x1221
 #define PCI_DEVICE_ID_INTEL_82437	0x122d
 #define PCI_DEVICE_ID_INTEL_82371FB_0	0x122e

From 689f05586e7ea620c8fc1066c067809e52ffc2f3 Mon Sep 17 00:00:00 2001
From: Amelie Delaunay <amelie.delaunay@foss.st.com>
Date: Wed, 16 Oct 2024 14:39:53 +0200
Subject: [PATCH 0551/1530] dt-bindings: dma: stm32-dma3: prevent
 packing/unpacking mode

When source data width/burst and destination data width/burst are
different, data are packed or unpacked in DMA3 channel FIFO.
Data are pushed out from DMA3 channel FIFO when the destination burst
length (= data width * burst) is reached.
If the channel is stopped before the transfer end, and if some bytes are
packed/unpacked in the DMA3 channel FIFO, these bytes are lost.
Indeed, DMA3 channel FIFO has no flush capability, only reset.
To avoid potential bytes lost, pack/unpack must be prevented by setting
memory data width/burst equal to peripheral data width/burst.
Memory accesses will be penalized. But it is the only way to avoid bytes
lost.

Some devices (e.g. cyclic RX like UART) need this, so add the possibility
to prevent pack/unpack feature, by setting bit 16 of the 'DMA transfer
requirements' bit mask.

Acked-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Amelie Delaunay <amelie.delaunay@foss.st.com>
Link: https://lore.kernel.org/r/20241016-dma3-mp25-updates-v3-1-8311fe6f228d@foss.st.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/dma/stm32/st,stm32-dma3.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/dma/stm32/st,stm32-dma3.yaml b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dma3.yaml
index 7fdc44b2e6467..5484848735f8a 100644
--- a/Documentation/devicetree/bindings/dma/stm32/st,stm32-dma3.yaml
+++ b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dma3.yaml
@@ -96,6 +96,9 @@ properties:
                including the update of the LLI if any
           0x3: at channel level, the transfer complete event is generated at the
                end of the last LLI
+        -bit 16: Prevent packing/unpacking mode
+          0x0: pack/unpack enabled when source data width/burst != destination data width/burst
+          0x1: memory data width/burst forced to peripheral data width/burst to prevent pack/unpack
 
 required:
   - compatible

From 12eb621e1abff65d89aeb4c92a4f3436225971d0 Mon Sep 17 00:00:00 2001
From: Amelie Delaunay <amelie.delaunay@foss.st.com>
Date: Wed, 16 Oct 2024 14:39:54 +0200
Subject: [PATCH 0552/1530] dmaengine: stm32-dma3: prevent pack/unpack thanks
 to DT configuration

When source data width/burst and destination data width/burst are
different, data are packed or unpacked in DMA3 channel FIFO, using
CxTR1.PAM.
Data are pushed out from DMA3 channel FIFO when the destination burst
length (= data width * burst) is reached.
If the transfer is stopped before CxBR1.BNDT = 0, and if some bytes are
packed/unpacked in the DMA3 channel FIFO, these bytes are lost.
Indeed, DMA3 channel FIFO has no flush capability, only reset.
To avoid potential bytes lost, pack/unpack must be prevented by setting
memory data width/burst equal to peripheral data width/burst.
Memory accesses will be penalized. But it is the only way to avoid bytes
lost.

Prevent pack/unpack feature can be activated by setting bit 16 of DMA3
Transfer requirements bitfield (tr_conf) in device tree.

Signed-off-by: Amelie Delaunay <amelie.delaunay@foss.st.com>
Link: https://lore.kernel.org/r/20241016-dma3-mp25-updates-v3-2-8311fe6f228d@foss.st.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/stm32/stm32-dma3.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/dma/stm32/stm32-dma3.c b/drivers/dma/stm32/stm32-dma3.c
index b9470f783f989..f793eecd2c27c 100644
--- a/drivers/dma/stm32/stm32-dma3.c
+++ b/drivers/dma/stm32/stm32-dma3.c
@@ -221,6 +221,7 @@ enum stm32_dma3_port_data_width {
 #define STM32_DMA3_DT_BREQ		BIT(8) /* CTR2_BREQ */
 #define STM32_DMA3_DT_PFREQ		BIT(9) /* CTR2_PFREQ */
 #define STM32_DMA3_DT_TCEM		GENMASK(13, 12) /* CTR2_TCEM */
+#define STM32_DMA3_DT_NOPACK		BIT(16) /* CTR1_PAM */
 
 /* struct stm32_dma3_chan .config_set bitfield */
 #define STM32_DMA3_CFG_SET_DT		BIT(0)
@@ -622,6 +623,10 @@ static int stm32_dma3_chan_prep_hw(struct stm32_dma3_chan *chan, enum dma_transf
 		/* Set source (memory) data width and burst */
 		sdw = stm32_dma3_get_max_dw(chan->max_burst, sap_max_dw, len, src_addr);
 		sbl_max = stm32_dma3_get_max_burst(len, sdw, chan->max_burst);
+		if (!!FIELD_GET(STM32_DMA3_DT_NOPACK, tr_conf)) {
+			sdw = ddw;
+			sbl_max = dbl_max;
+		}
 
 		_ctr1 |= FIELD_PREP(CTR1_SDW_LOG2, ilog2(sdw));
 		_ctr1 |= FIELD_PREP(CTR1_SBL_1, sbl_max - 1);
@@ -652,6 +657,11 @@ static int stm32_dma3_chan_prep_hw(struct stm32_dma3_chan *chan, enum dma_transf
 		/* Set destination (memory) data width and burst */
 		ddw = stm32_dma3_get_max_dw(chan->max_burst, dap_max_dw, len, dst_addr);
 		dbl_max = stm32_dma3_get_max_burst(len, ddw, chan->max_burst);
+		if (!!FIELD_GET(STM32_DMA3_DT_NOPACK, tr_conf) ||
+		    ((_ctr2 & CTR2_PFREQ) && ddw > sdw)) { /* Packing to wider ddw not supported */
+			ddw = sdw;
+			dbl_max = sbl_max;
+		}
 
 		_ctr1 |= FIELD_PREP(CTR1_SDW_LOG2, ilog2(sdw));
 		_ctr1 |= FIELD_PREP(CTR1_SBL_1, sbl_max - 1);

From cb467c451163bacad4cbb7540ce7d731946f13f9 Mon Sep 17 00:00:00 2001
From: Amelie Delaunay <amelie.delaunay@foss.st.com>
Date: Wed, 16 Oct 2024 14:39:55 +0200
Subject: [PATCH 0553/1530] dmaengine: stm32-dma3: refactor HW linked-list to
 optimize memory accesses

Current behavior splits the buffer/sg in n * STM32_DMA3_MAX_BLOCK_SIZE + 1
for the remainder without optimization.

New behavior splits the buffer/sg in n * STM32_DMA3_MAX_BLOCK_SIZE + 1 for
(x * chan->max_burst) + 1 for the remainder.
Depending on channel FIFO size, optimal double-word (word if only 8-byte
FIFO size) bursts can be programmed before managing the very last remainder
with lower data width.
In case of _prep_slave_sg, and depending on the channel Transfer Complete
event configuration, the user is warned about the refactored linked-list,
not having the same items count than the initial sg_list. This warning is
shown only if the configuration is successful.

Signed-off-by: Amelie Delaunay <amelie.delaunay@foss.st.com>
Link: https://lore.kernel.org/r/20241016-dma3-mp25-updates-v3-3-8311fe6f228d@foss.st.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/stm32/stm32-dma3.c | 40 ++++++++++++++++++++++++++++------
 1 file changed, 33 insertions(+), 7 deletions(-)

diff --git a/drivers/dma/stm32/stm32-dma3.c b/drivers/dma/stm32/stm32-dma3.c
index f793eecd2c27c..1d961f5935f93 100644
--- a/drivers/dma/stm32/stm32-dma3.c
+++ b/drivers/dma/stm32/stm32-dma3.c
@@ -1126,6 +1126,25 @@ static void stm32_dma3_free_chan_resources(struct dma_chan *c)
 	chan->config_set = 0;
 }
 
+static u32 stm32_dma3_get_ll_count(struct stm32_dma3_chan *chan, size_t len)
+{
+	u32 count;
+
+	count = len / STM32_DMA3_MAX_BLOCK_SIZE;
+	len -= (len / STM32_DMA3_MAX_BLOCK_SIZE) * STM32_DMA3_MAX_BLOCK_SIZE;
+
+	if (len >= chan->max_burst) {
+		count += 1; /* len < STM32_DMA3_MAX_BLOCK_SIZE here, so it fits in one item */
+		len -= (len / chan->max_burst) * chan->max_burst;
+	}
+
+	/* Unaligned remainder fits in one extra item */
+	if (len > 0)
+		count += 1;
+
+	return count;
+}
+
 static void stm32_dma3_init_chan_config_for_memcpy(struct stm32_dma3_chan *chan,
 						   dma_addr_t dst, dma_addr_t src)
 {
@@ -1161,7 +1180,7 @@ static struct dma_async_tx_descriptor *stm32_dma3_prep_dma_memcpy(struct dma_cha
 	size_t next_size, offset;
 	u32 count, i, ctr1, ctr2;
 
-	count = DIV_ROUND_UP(len, STM32_DMA3_MAX_BLOCK_SIZE);
+	count = stm32_dma3_get_ll_count(chan, len);
 
 	swdesc = stm32_dma3_chan_desc_alloc(chan, count);
 	if (!swdesc)
@@ -1177,6 +1196,9 @@ static struct dma_async_tx_descriptor *stm32_dma3_prep_dma_memcpy(struct dma_cha
 		remaining = len - offset;
 		next_size = min_t(size_t, remaining, STM32_DMA3_MAX_BLOCK_SIZE);
 
+		if (next_size < STM32_DMA3_MAX_BLOCK_SIZE && next_size >= chan->max_burst)
+			next_size = chan->max_burst * (remaining / chan->max_burst);
+
 		ret = stm32_dma3_chan_prep_hw(chan, DMA_MEM_TO_MEM, &swdesc->ccr, &ctr1, &ctr2,
 					      src + offset, dst + offset, next_size);
 		if (ret)
@@ -1215,12 +1237,9 @@ static struct dma_async_tx_descriptor *stm32_dma3_prep_slave_sg(struct dma_chan
 	u32 i, j, count, ctr1, ctr2;
 	int ret;
 
-	count = sg_len;
-	for_each_sg(sgl, sg, sg_len, i) {
-		len = sg_dma_len(sg);
-		if (len > STM32_DMA3_MAX_BLOCK_SIZE)
-			count += DIV_ROUND_UP(len, STM32_DMA3_MAX_BLOCK_SIZE) - 1;
-	}
+	count = 0;
+	for_each_sg(sgl, sg, sg_len, i)
+		count += stm32_dma3_get_ll_count(chan, sg_dma_len(sg));
 
 	swdesc = stm32_dma3_chan_desc_alloc(chan, count);
 	if (!swdesc)
@@ -1237,6 +1256,9 @@ static struct dma_async_tx_descriptor *stm32_dma3_prep_slave_sg(struct dma_chan
 		do {
 			size_t chunk = min_t(size_t, len, STM32_DMA3_MAX_BLOCK_SIZE);
 
+			if (chunk < STM32_DMA3_MAX_BLOCK_SIZE && chunk >= chan->max_burst)
+				chunk = chan->max_burst * (len / chan->max_burst);
+
 			if (dir == DMA_MEM_TO_DEV) {
 				src = sg_addr;
 				dst = dev_addr;
@@ -1269,6 +1291,10 @@ static struct dma_async_tx_descriptor *stm32_dma3_prep_slave_sg(struct dma_chan
 		} while (len);
 	}
 
+	if (count != sg_len && chan->tcem != CTR2_TCEM_CHANNEL)
+		dev_warn(chan2dev(chan), "Linked-list refactored, %d items instead of %d\n",
+			 count, sg_len);
+
 	/* Enable Error interrupts */
 	swdesc->ccr |= CCR_USEIE | CCR_ULEIE | CCR_DTEIE;
 	/* Enable Transfer state interrupts */

From e18a9830233e739ae7045700232c53b4cb2e98eb Mon Sep 17 00:00:00 2001
From: Amelie Delaunay <amelie.delaunay@foss.st.com>
Date: Wed, 16 Oct 2024 14:39:56 +0200
Subject: [PATCH 0554/1530] dt-bindings: dma: stm32-dma3: prevent additional
 transfers

Some devices require a single transfer. For example, reading FMC ECC status
registers does not support multiple transfers.
Add the possibility to prevent additional transfers, by setting bit 17 of
the 'DMA transfer requirements' bit mask.

Signed-off-by: Amelie Delaunay <amelie.delaunay@foss.st.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20241016-dma3-mp25-updates-v3-4-8311fe6f228d@foss.st.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/dma/stm32/st,stm32-dma3.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/dma/stm32/st,stm32-dma3.yaml b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dma3.yaml
index 5484848735f8a..36f9fe860eb99 100644
--- a/Documentation/devicetree/bindings/dma/stm32/st,stm32-dma3.yaml
+++ b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dma3.yaml
@@ -99,6 +99,9 @@ properties:
         -bit 16: Prevent packing/unpacking mode
           0x0: pack/unpack enabled when source data width/burst != destination data width/burst
           0x1: memory data width/burst forced to peripheral data width/burst to prevent pack/unpack
+        -bit 17: Prevent additional transfers due to linked-list refactoring
+          0x0: don't prevent additional transfers for optimal performance
+          0x1: prevent additional transfer to accommodate user constraints such as single transfer
 
 required:
   - compatible

From 2ff0fb9474eefa7149c199fb3f79e54355a6c184 Mon Sep 17 00:00:00 2001
From: Amelie Delaunay <amelie.delaunay@foss.st.com>
Date: Wed, 16 Oct 2024 14:39:57 +0200
Subject: [PATCH 0555/1530] dmaengine: stm32-dma3: prevent LL refactoring
 thanks to DT configuration

stm32-dma3 driver refactors the linked-list in order to address the memory
with the highest possible data width.
It means that it can introduce up to 2 linked-list items. One with a
transfer length multiple of channel maximum burst length and so with the
highest possible data width. And an extra one with the latest bytes, with
lower data width.
Some devices (e.g. FMC ECC) don't support having several transfers instead
of only one.
So add the possibility to prevent linked-list refactoring, when bit 17 of
the 'DMA transfer requirements' bit mask is set in device tree.
When NOPACK feature is used (bit 16 pf the 'DMA transfer requirements' bit
mask in device tree), linked-list refactoring can be avoided, since the
memory data width and burst will be aligned with the device ones.

Signed-off-by: Amelie Delaunay <amelie.delaunay@foss.st.com>
Link: https://lore.kernel.org/r/20241016-dma3-mp25-updates-v3-5-8311fe6f228d@foss.st.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/stm32/stm32-dma3.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/dma/stm32/stm32-dma3.c b/drivers/dma/stm32/stm32-dma3.c
index 1d961f5935f93..fc874fec729df 100644
--- a/drivers/dma/stm32/stm32-dma3.c
+++ b/drivers/dma/stm32/stm32-dma3.c
@@ -222,6 +222,7 @@ enum stm32_dma3_port_data_width {
 #define STM32_DMA3_DT_PFREQ		BIT(9) /* CTR2_PFREQ */
 #define STM32_DMA3_DT_TCEM		GENMASK(13, 12) /* CTR2_TCEM */
 #define STM32_DMA3_DT_NOPACK		BIT(16) /* CTR1_PAM */
+#define STM32_DMA3_DT_NOREFACT		BIT(17)
 
 /* struct stm32_dma3_chan .config_set bitfield */
 #define STM32_DMA3_CFG_SET_DT		BIT(0)
@@ -1126,10 +1127,13 @@ static void stm32_dma3_free_chan_resources(struct dma_chan *c)
 	chan->config_set = 0;
 }
 
-static u32 stm32_dma3_get_ll_count(struct stm32_dma3_chan *chan, size_t len)
+static u32 stm32_dma3_get_ll_count(struct stm32_dma3_chan *chan, size_t len, bool prevent_refactor)
 {
 	u32 count;
 
+	if (prevent_refactor)
+		return DIV_ROUND_UP(len, STM32_DMA3_MAX_BLOCK_SIZE);
+
 	count = len / STM32_DMA3_MAX_BLOCK_SIZE;
 	len -= (len / STM32_DMA3_MAX_BLOCK_SIZE) * STM32_DMA3_MAX_BLOCK_SIZE;
 
@@ -1179,8 +1183,10 @@ static struct dma_async_tx_descriptor *stm32_dma3_prep_dma_memcpy(struct dma_cha
 	struct stm32_dma3_swdesc *swdesc;
 	size_t next_size, offset;
 	u32 count, i, ctr1, ctr2;
+	bool prevent_refactor = !!FIELD_GET(STM32_DMA3_DT_NOPACK, chan->dt_config.tr_conf) ||
+				!!FIELD_GET(STM32_DMA3_DT_NOREFACT, chan->dt_config.tr_conf);
 
-	count = stm32_dma3_get_ll_count(chan, len);
+	count = stm32_dma3_get_ll_count(chan, len, prevent_refactor);
 
 	swdesc = stm32_dma3_chan_desc_alloc(chan, count);
 	if (!swdesc)
@@ -1196,7 +1202,8 @@ static struct dma_async_tx_descriptor *stm32_dma3_prep_dma_memcpy(struct dma_cha
 		remaining = len - offset;
 		next_size = min_t(size_t, remaining, STM32_DMA3_MAX_BLOCK_SIZE);
 
-		if (next_size < STM32_DMA3_MAX_BLOCK_SIZE && next_size >= chan->max_burst)
+		if (!prevent_refactor &&
+		    (next_size < STM32_DMA3_MAX_BLOCK_SIZE && next_size >= chan->max_burst))
 			next_size = chan->max_burst * (remaining / chan->max_burst);
 
 		ret = stm32_dma3_chan_prep_hw(chan, DMA_MEM_TO_MEM, &swdesc->ccr, &ctr1, &ctr2,
@@ -1235,11 +1242,13 @@ static struct dma_async_tx_descriptor *stm32_dma3_prep_slave_sg(struct dma_chan
 	size_t len;
 	dma_addr_t sg_addr, dev_addr, src, dst;
 	u32 i, j, count, ctr1, ctr2;
+	bool prevent_refactor = !!FIELD_GET(STM32_DMA3_DT_NOPACK, chan->dt_config.tr_conf) ||
+				!!FIELD_GET(STM32_DMA3_DT_NOREFACT, chan->dt_config.tr_conf);
 	int ret;
 
 	count = 0;
 	for_each_sg(sgl, sg, sg_len, i)
-		count += stm32_dma3_get_ll_count(chan, sg_dma_len(sg));
+		count += stm32_dma3_get_ll_count(chan, sg_dma_len(sg), prevent_refactor);
 
 	swdesc = stm32_dma3_chan_desc_alloc(chan, count);
 	if (!swdesc)
@@ -1256,7 +1265,8 @@ static struct dma_async_tx_descriptor *stm32_dma3_prep_slave_sg(struct dma_chan
 		do {
 			size_t chunk = min_t(size_t, len, STM32_DMA3_MAX_BLOCK_SIZE);
 
-			if (chunk < STM32_DMA3_MAX_BLOCK_SIZE && chunk >= chan->max_burst)
+			if (!prevent_refactor &&
+			    (chunk < STM32_DMA3_MAX_BLOCK_SIZE && chunk >= chan->max_burst))
 				chunk = chan->max_burst * (len / chan->max_burst);
 
 			if (dir == DMA_MEM_TO_DEV) {

From e713468e7c104a0598a7ec31ab7ec0bec94a174d Mon Sep 17 00:00:00 2001
From: Amelie Delaunay <amelie.delaunay@foss.st.com>
Date: Wed, 16 Oct 2024 14:39:58 +0200
Subject: [PATCH 0556/1530] dmaengine: stm32-dma3: clamp AXI burst using match
 data

STM32 DMA3 can be interconnected with AXI3 or AXI4 busses. In case it is
interconnected with AXI3, the maximum burst length supported by AXI3
protocol is 16 beats, which is lower than the maximum burst length
supported by STM32 DMA3. So the programmed burst has to be shortened when
AXI port is used.
Introduce struct stm32_dma3_pdata to specify the specific configurations
(e.g. AXI maximum burst length) required by the SoC, so implied by the SoC
specific compatible.

Signed-off-by: Amelie Delaunay <amelie.delaunay@foss.st.com>
Link: https://lore.kernel.org/r/20241016-dma3-mp25-updates-v3-6-8311fe6f228d@foss.st.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/stm32/stm32-dma3.c | 59 ++++++++++++++++++++++++++--------
 1 file changed, 46 insertions(+), 13 deletions(-)

diff --git a/drivers/dma/stm32/stm32-dma3.c b/drivers/dma/stm32/stm32-dma3.c
index fc874fec729df..0c6c4258b1956 100644
--- a/drivers/dma/stm32/stm32-dma3.c
+++ b/drivers/dma/stm32/stm32-dma3.c
@@ -230,6 +230,8 @@ enum stm32_dma3_port_data_width {
 #define STM32_DMA3_CFG_SET_BOTH		(STM32_DMA3_CFG_SET_DT | STM32_DMA3_CFG_SET_DMA)
 
 #define STM32_DMA3_MAX_BLOCK_SIZE	ALIGN_DOWN(CBR1_BNDT, 64)
+#define STM32_DMA3_MAX_BURST_LEN	(1 + min_t(u32, FIELD_MAX(CTR1_SBL_1), \
+							FIELD_MAX(CTR1_DBL_1)))
 #define port_is_ahb(maxdw)		({ typeof(maxdw) (_maxdw) = (maxdw); \
 					   ((_maxdw) != DW_INVALID) && ((_maxdw) == DW_32); })
 #define port_is_axi(maxdw)		({ typeof(maxdw) (_maxdw) = (maxdw); \
@@ -295,6 +297,10 @@ struct stm32_dma3_chan {
 	u32 dma_status;
 };
 
+struct stm32_dma3_pdata {
+	u32 axi_max_burst_len;
+};
+
 struct stm32_dma3_ddata {
 	struct dma_device dma_dev;
 	void __iomem *base;
@@ -303,6 +309,7 @@ struct stm32_dma3_ddata {
 	u32 dma_channels;
 	u32 dma_requests;
 	enum stm32_dma3_port_data_width ports_max_dw[2];
+	u32 axi_max_burst_len;
 };
 
 static inline struct stm32_dma3_ddata *to_stm32_dma3_ddata(struct stm32_dma3_chan *chan)
@@ -535,7 +542,8 @@ static enum dma_slave_buswidth stm32_dma3_get_max_dw(u32 chan_max_burst,
 	return 1 << __ffs(len | addr | max_dw);
 }
 
-static u32 stm32_dma3_get_max_burst(u32 len, enum dma_slave_buswidth dw, u32 chan_max_burst)
+static u32 stm32_dma3_get_max_burst(u32 len, enum dma_slave_buswidth dw,
+				    u32 chan_max_burst, u32 bus_max_burst)
 {
 	u32 max_burst = chan_max_burst ? chan_max_burst / dw : 1;
 
@@ -546,8 +554,9 @@ static u32 stm32_dma3_get_max_burst(u32 len, enum dma_slave_buswidth dw, u32 cha
 	/*
 	 * HW doesn't modify the burst if burst size <= half of the fifo size.
 	 * If len is not a multiple of burst size, last burst is shortened by HW.
+	 * Take care of maximum burst supported on interconnect bus.
 	 */
-	return max_burst;
+	return min_t(u32, max_burst, bus_max_burst);
 }
 
 static int stm32_dma3_chan_prep_hw(struct stm32_dma3_chan *chan, enum dma_transfer_direction dir,
@@ -556,6 +565,7 @@ static int stm32_dma3_chan_prep_hw(struct stm32_dma3_chan *chan, enum dma_transf
 {
 	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
 	struct dma_device dma_device = ddata->dma_dev;
+	u32 src_max_burst = STM32_DMA3_MAX_BURST_LEN, dst_max_burst = STM32_DMA3_MAX_BURST_LEN;
 	u32 sdw, ddw, sbl_max, dbl_max, tcem, init_dw, init_bl_max;
 	u32 _ctr1 = 0, _ctr2 = 0;
 	u32 ch_conf = chan->dt_config.ch_conf;
@@ -596,10 +606,14 @@ static int stm32_dma3_chan_prep_hw(struct stm32_dma3_chan *chan, enum dma_transf
 		_ctr1 |= CTR1_SINC;
 	if (sap)
 		_ctr1 |= CTR1_SAP;
+	if (port_is_axi(sap_max_dw)) /* AXI - apply axi maximum burst limitation */
+		src_max_burst = ddata->axi_max_burst_len;
 	if (FIELD_GET(STM32_DMA3_DT_DINC, tr_conf))
 		_ctr1 |= CTR1_DINC;
 	if (dap)
 		_ctr1 |= CTR1_DAP;
+	if (port_is_axi(dap_max_dw)) /* AXI - apply axi maximum burst limitation */
+		dst_max_burst = ddata->axi_max_burst_len;
 
 	_ctr2 |= FIELD_PREP(CTR2_REQSEL, chan->dt_config.req_line) & ~CTR2_SWREQ;
 	if (FIELD_GET(STM32_DMA3_DT_BREQ, tr_conf))
@@ -619,11 +633,12 @@ static int stm32_dma3_chan_prep_hw(struct stm32_dma3_chan *chan, enum dma_transf
 		/* Set destination (device) data width and burst */
 		ddw = min_t(u32, ddw, stm32_dma3_get_max_dw(chan->max_burst, dap_max_dw,
 							    len, dst_addr));
-		dbl_max = min_t(u32, dbl_max, stm32_dma3_get_max_burst(len, ddw, chan->max_burst));
+		dbl_max = min_t(u32, dbl_max, stm32_dma3_get_max_burst(len, ddw, chan->max_burst,
+								       dst_max_burst));
 
 		/* Set source (memory) data width and burst */
 		sdw = stm32_dma3_get_max_dw(chan->max_burst, sap_max_dw, len, src_addr);
-		sbl_max = stm32_dma3_get_max_burst(len, sdw, chan->max_burst);
+		sbl_max = stm32_dma3_get_max_burst(len, sdw, chan->max_burst, src_max_burst);
 		if (!!FIELD_GET(STM32_DMA3_DT_NOPACK, tr_conf)) {
 			sdw = ddw;
 			sbl_max = dbl_max;
@@ -653,11 +668,12 @@ static int stm32_dma3_chan_prep_hw(struct stm32_dma3_chan *chan, enum dma_transf
 		/* Set source (device) data width and burst */
 		sdw = min_t(u32, sdw, stm32_dma3_get_max_dw(chan->max_burst, sap_max_dw,
 							    len, src_addr));
-		sbl_max = min_t(u32, sbl_max, stm32_dma3_get_max_burst(len, sdw, chan->max_burst));
+		sbl_max = min_t(u32, sbl_max, stm32_dma3_get_max_burst(len, sdw, chan->max_burst,
+								       src_max_burst));
 
 		/* Set destination (memory) data width and burst */
 		ddw = stm32_dma3_get_max_dw(chan->max_burst, dap_max_dw, len, dst_addr);
-		dbl_max = stm32_dma3_get_max_burst(len, ddw, chan->max_burst);
+		dbl_max = stm32_dma3_get_max_burst(len, ddw, chan->max_burst, dst_max_burst);
 		if (!!FIELD_GET(STM32_DMA3_DT_NOPACK, tr_conf) ||
 		    ((_ctr2 & CTR2_PFREQ) && ddw > sdw)) { /* Packing to wider ddw not supported */
 			ddw = sdw;
@@ -689,22 +705,24 @@ static int stm32_dma3_chan_prep_hw(struct stm32_dma3_chan *chan, enum dma_transf
 		init_dw = sdw;
 		init_bl_max = sbl_max;
 		sdw = stm32_dma3_get_max_dw(chan->max_burst, sap_max_dw, len, src_addr);
-		sbl_max = stm32_dma3_get_max_burst(len, sdw, chan->max_burst);
+		sbl_max = stm32_dma3_get_max_burst(len, sdw, chan->max_burst, src_max_burst);
 		if (chan->config_set & STM32_DMA3_CFG_SET_DMA) {
 			sdw = min_t(u32, init_dw, sdw);
-			sbl_max = min_t(u32, init_bl_max,
-					stm32_dma3_get_max_burst(len, sdw, chan->max_burst));
+			sbl_max = min_t(u32, init_bl_max, stm32_dma3_get_max_burst(len, sdw,
+										   chan->max_burst,
+										   src_max_burst));
 		}
 
 		/* Set destination (memory) data width and burst */
 		init_dw = ddw;
 		init_bl_max = dbl_max;
 		ddw = stm32_dma3_get_max_dw(chan->max_burst, dap_max_dw, len, dst_addr);
-		dbl_max = stm32_dma3_get_max_burst(len, ddw, chan->max_burst);
+		dbl_max = stm32_dma3_get_max_burst(len, ddw, chan->max_burst, dst_max_burst);
 		if (chan->config_set & STM32_DMA3_CFG_SET_DMA) {
 			ddw = min_t(u32, init_dw, ddw);
-			dbl_max = min_t(u32, init_bl_max,
-					stm32_dma3_get_max_burst(len, ddw, chan->max_burst));
+			dbl_max = min_t(u32, init_bl_max, stm32_dma3_get_max_burst(len, ddw,
+										   chan->max_burst,
+										   dst_max_burst));
 		}
 
 		_ctr1 |= FIELD_PREP(CTR1_SDW_LOG2, ilog2(sdw));
@@ -1647,8 +1665,12 @@ static u32 stm32_dma3_check_rif(struct stm32_dma3_ddata *ddata)
 	return chan_reserved;
 }
 
+static struct stm32_dma3_pdata stm32mp25_pdata = {
+	.axi_max_burst_len = 16,
+};
+
 static const struct of_device_id stm32_dma3_of_match[] = {
-	{ .compatible = "st,stm32mp25-dma3", },
+	{ .compatible = "st,stm32mp25-dma3", .data = &stm32mp25_pdata, },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, stm32_dma3_of_match);
@@ -1656,6 +1678,7 @@ MODULE_DEVICE_TABLE(of, stm32_dma3_of_match);
 static int stm32_dma3_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
+	const struct stm32_dma3_pdata *pdata;
 	struct stm32_dma3_ddata *ddata;
 	struct reset_control *reset;
 	struct stm32_dma3_chan *chan;
@@ -1750,6 +1773,16 @@ static int stm32_dma3_probe(struct platform_device *pdev)
 	else /* Dual master ports */
 		ddata->ports_max_dw[1] = FIELD_GET(G_M1_DATA_WIDTH_ENC, hwcfgr);
 
+	/* axi_max_burst_len is optional, if not defined, use STM32_DMA3_MAX_BURST_LEN  */
+	ddata->axi_max_burst_len = STM32_DMA3_MAX_BURST_LEN;
+	pdata = device_get_match_data(&pdev->dev);
+	if (pdata && pdata->axi_max_burst_len) {
+		ddata->axi_max_burst_len = min_t(u32, pdata->axi_max_burst_len,
+						 STM32_DMA3_MAX_BURST_LEN);
+		dev_dbg(&pdev->dev, "Burst is limited to %u beats through AXI port\n",
+			ddata->axi_max_burst_len);
+	}
+
 	ddata->chans = devm_kcalloc(&pdev->dev, ddata->dma_channels, sizeof(*ddata->chans),
 				    GFP_KERNEL);
 	if (!ddata->chans) {

From 39d283d146922a266e8196e7fd29b31feff528be Mon Sep 17 00:00:00 2001
From: Yan Zhen <yanzhen@vivo.com>
Date: Wed, 18 Sep 2024 11:41:14 +0800
Subject: [PATCH 0557/1530] dmaengine: fix typo in the comment

Correctly spelled comments make it easier for the reader to understand
the code.

Replace 'enngine' with 'engine' in the comment &
replace 'trascatioin' with 'transaction' in the comment &
replace 'descripter' with 'descriptor' in the comment &
replace 'descritpor' with 'descriptor' in the comment &
replace 'rgisters' with 'registers' in the comment.

Signed-off-by: Yan Zhen <yanzhen@vivo.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20240918034114.860132-1-yanzhen@vivo.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/mv_xor_v2.c         | 2 +-
 drivers/dma/sf-pdma/sf-pdma.c   | 2 +-
 drivers/dma/sh/shdma-base.c     | 2 +-
 drivers/dma/sh/usb-dmac.c       | 2 +-
 drivers/dma/xilinx/zynqmp_dma.c | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c
index d908143c77312..cad4d4fb51ac3 100644
--- a/drivers/dma/mv_xor_v2.c
+++ b/drivers/dma/mv_xor_v2.c
@@ -635,7 +635,7 @@ static int mv_xor_v2_descq_init(struct mv_xor_v2_device *xor_dev)
 	writel(MV_XOR_V2_DESC_NUM,
 	       xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_SIZE_OFF);
 
-	/* write the DESQ address to the DMA enngine*/
+	/* write the DESQ address to the DMA engine*/
 	writel(lower_32_bits(xor_dev->hw_desq),
 	       xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_BALR_OFF);
 	writel(upper_32_bits(xor_dev->hw_desq),
diff --git a/drivers/dma/sf-pdma/sf-pdma.c b/drivers/dma/sf-pdma/sf-pdma.c
index 15b1f4baf357d..7ad3c29be1467 100644
--- a/drivers/dma/sf-pdma/sf-pdma.c
+++ b/drivers/dma/sf-pdma/sf-pdma.c
@@ -354,7 +354,7 @@ static irqreturn_t sf_pdma_done_isr(int irq, void *dev_id)
 	if (!residue) {
 		tasklet_hi_schedule(&chan->done_tasklet);
 	} else {
-		/* submit next trascatioin if possible */
+		/* submit next transaction if possible */
 		struct sf_pdma_desc *desc = chan->desc;
 
 		desc->src_addr += desc->xfer_size - residue;
diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c
index 588c5f409a808..fdd41e1c22636 100644
--- a/drivers/dma/sh/shdma-base.c
+++ b/drivers/dma/sh/shdma-base.c
@@ -961,7 +961,7 @@ void shdma_chan_probe(struct shdma_dev *sdev,
 
 	spin_lock_init(&schan->chan_lock);
 
-	/* Init descripter manage list */
+	/* Init descriptor manage list */
 	INIT_LIST_HEAD(&schan->ld_queue);
 	INIT_LIST_HEAD(&schan->ld_free);
 
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index b2081a6126e6f..7e2b6c97fa2f9 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -301,7 +301,7 @@ static struct usb_dmac_desc *usb_dmac_desc_get(struct usb_dmac_chan *chan,
 	struct usb_dmac_desc *desc = NULL;
 	unsigned long flags;
 
-	/* Get a freed descritpor */
+	/* Get a freed descriptor */
 	spin_lock_irqsave(&chan->vc.lock, flags);
 	list_for_each_entry(desc, &chan->desc_freed, node) {
 		if (sg_len <= desc->sg_allocated_len) {
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index 3156eff5deb07..d05fc5fcc77dc 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -366,7 +366,7 @@ static void zynqmp_dma_init(struct zynqmp_dma_chan *chan)
 	}
 	writel(val, chan->regs + ZYNQMP_DMA_DATA_ATTR);
 
-	/* Clearing the interrupt account rgisters */
+	/* Clearing the interrupt account registers */
 	val = readl(chan->regs + ZYNQMP_DMA_IRQ_SRC_ACCT);
 	val = readl(chan->regs + ZYNQMP_DMA_IRQ_DST_ACCT);
 

From 7655ec4d0de0a822364ecdeec239a2562fa9d96f Mon Sep 17 00:00:00 2001
From: Pierre-Henry Moussay <pierre-henry.moussay@microchip.com>
Date: Mon, 30 Sep 2024 10:54:38 +0100
Subject: [PATCH 0558/1530] dt-bindings: dma: sifive pdma: Add PIC64GX to
 compatibles

PIC64GX is compatible as out of order DMA capable, just like the MPFS
version, therefore we add it with microchip,mpfs-pdma as a fallback

Signed-off-by: Pierre-Henry Moussay <pierre-henry.moussay@microchip.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20240930095449.1813195-10-pierre-henry.moussay@microchip.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../bindings/dma/sifive,fu540-c000-pdma.yaml      | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml b/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
index 3b22183a1a379..609e38901434a 100644
--- a/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
+++ b/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
@@ -27,11 +27,16 @@ allOf:
 
 properties:
   compatible:
-    items:
-      - enum:
-          - microchip,mpfs-pdma
-          - sifive,fu540-c000-pdma
-      - const: sifive,pdma0
+    oneOf:
+      - items:
+          - const: microchip,pic64gx-pdma
+          - const: microchip,mpfs-pdma
+          - const: sifive,pdma0
+      - items:
+          - enum:
+              - microchip,mpfs-pdma
+              - sifive,fu540-c000-pdma
+          - const: sifive,pdma0
     description:
       Should be "sifive,<chip>-pdma" and "sifive,pdma<version>".
       Supported compatible strings are -

From 8e1e94619bd37915323a199ceed39ed5904e7fa6 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Thu, 17 Oct 2024 20:42:56 +0300
Subject: [PATCH 0559/1530] dt-bindings: phy: qcom: snps-eusb2: Add SAR2130P
 compatible

Document the Synopsys eUSB2 PHY on the SAR2130P platform by using
the SM8550 as fallback.

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20241017-sar2130p-eusb2-v1-1-1cedd674ec64@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml
index b82f7f5731ed4..142b3c8839d62 100644
--- a/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml
@@ -17,6 +17,7 @@ properties:
     oneOf:
       - items:
           - enum:
+              - qcom,sar2130p-snps-eusb2-phy
               - qcom,sdx75-snps-eusb2-phy
               - qcom,sm8650-snps-eusb2-phy
               - qcom,x1e80100-snps-eusb2-phy

From 30c280bc8e4555d55d7de7b85983990356c1e8e9 Mon Sep 17 00:00:00 2001
From: Xin Liu <quic_liuxin@quicinc.com>
Date: Fri, 18 Oct 2024 13:57:50 +0800
Subject: [PATCH 0560/1530] dt-bindings: phy: Add QMP UFS PHY compatible for
 QCS8300

Document the QMP UFS PHY compatible for Qualcomm QCS8300 to support
physical layer functionality for UFS found on the SoC. Use fallback to
indicate the compatibility of the QMP UFS PHY on the QCS8300 with that
on the SA8775P.

Signed-off-by: Xin Liu <quic_liuxin@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Jingyi Wang <quic_jingyw@quicinc.com>
Link: https://lore.kernel.org/r/20241018-qcs8300_ufs_phy_binding-v4-1-261c7c5fb8ff@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml    | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml
index a93d64d1c55b4..72bed2933b034 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml
@@ -20,6 +20,10 @@ properties:
           - enum:
               - qcom,qcs615-qmp-ufs-phy
           - const: qcom,sm6115-qmp-ufs-phy
+      - items:
+          - enum:
+              - qcom,qcs8300-qmp-ufs-phy
+          - const: qcom,sa8775p-qmp-ufs-phy
       - enum:
           - qcom,msm8996-qmp-ufs-phy
           - qcom,msm8998-qmp-ufs-phy

From c3639d423d76c935b58827296a124e8f13d79b4b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <rafal@milecki.pl>
Date: Fri, 13 Sep 2024 06:45:56 +0200
Subject: [PATCH 0561/1530] dt-bindings: phy: bcm-ns-usb2-phy: drop deprecated
 variant
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The old binding variant (the one covering whole DMU block) was
deprecated 3 years ago. Linux kernel was warning when using it for
similar amount of time.

There aren't any known Northstar devices with bootloader providing DT to
operating system. Actually OpenWrt seems to be the only project using
this binding and it always appends DTB to kernel. It has switched to the
non-deprecated binding years ago.

Given there is close to zero chance this breaks anyone's setup it should
more than safe to drop this binding variant after 3 years.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20240913044557.28315-1-zajec5@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../bindings/phy/bcm-ns-usb2-phy.yaml         | 19 +++----------------
 1 file changed, 3 insertions(+), 16 deletions(-)

diff --git a/Documentation/devicetree/bindings/phy/bcm-ns-usb2-phy.yaml b/Documentation/devicetree/bindings/phy/bcm-ns-usb2-phy.yaml
index 426101530a21e..d72c02ab55ae8 100644
--- a/Documentation/devicetree/bindings/phy/bcm-ns-usb2-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/bcm-ns-usb2-phy.yaml
@@ -18,16 +18,8 @@ properties:
     const: brcm,ns-usb2-phy
 
   reg:
-    anyOf:
-      - maxItems: 1
-        description: PHY control register
-      - maxItems: 1
-        description: iomem address range of DMU (Device Management Unit)
-        deprecated: true
-
-  reg-names:
-    items:
-      - const: dmu
+    maxItems: 1
+    description: PHY control register
 
   brcm,syscon-clkset:
     description: phandle to syscon for clkset register
@@ -50,12 +42,7 @@ required:
   - clocks
   - clock-names
   - "#phy-cells"
-
-oneOf:
-  - required:
-      - brcm,syscon-clkset
-  - required:
-      - reg-names
+  - brcm,syscon-clkset
 
 additionalProperties: false
 

From 0175a673e478eed99a86fc094e7d91ed2f3d5a34 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <rafal@milecki.pl>
Date: Fri, 13 Sep 2024 06:45:57 +0200
Subject: [PATCH 0562/1530] phy: bcm-ns-usb2: drop support for old binding
 variant
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The old binding was incorrectly designed and ended up being deprecated 3
years ago. Finally it has been dropped so relevant code it not needed
anymore.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Link: https://lore.kernel.org/r/20240913044557.28315-2-zajec5@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/broadcom/phy-bcm-ns-usb2.c | 54 +++++++-------------------
 1 file changed, 15 insertions(+), 39 deletions(-)

diff --git a/drivers/phy/broadcom/phy-bcm-ns-usb2.c b/drivers/phy/broadcom/phy-bcm-ns-usb2.c
index 5213c75b6da6a..c5d35031b3983 100644
--- a/drivers/phy/broadcom/phy-bcm-ns-usb2.c
+++ b/drivers/phy/broadcom/phy-bcm-ns-usb2.c
@@ -24,9 +24,6 @@ struct bcm_ns_usb2 {
 	struct phy *phy;
 	struct regmap *clkset;
 	void __iomem *base;
-
-	/* Deprecated binding */
-	void __iomem *dmu;
 };
 
 static int bcm_ns_usb2_phy_init(struct phy *phy)
@@ -49,10 +46,7 @@ static int bcm_ns_usb2_phy_init(struct phy *phy)
 		goto err_clk_off;
 	}
 
-	if (usb2->base)
-		usb2ctl = readl(usb2->base);
-	else
-		usb2ctl = readl(usb2->dmu + BCMA_DMU_CRU_USB2_CONTROL);
+	usb2ctl = readl(usb2->base);
 
 	if (usb2ctl & BCMA_DMU_CRU_USB2_CONTROL_USB_PLL_PDIV_MASK) {
 		usb_pll_pdiv = usb2ctl;
@@ -66,24 +60,16 @@ static int bcm_ns_usb2_phy_init(struct phy *phy)
 	usb_pll_ndiv = (1920000000 * usb_pll_pdiv) / ref_clk_rate;
 
 	/* Unlock DMU PLL settings with some magic value */
-	if (usb2->clkset)
-		regmap_write(usb2->clkset, 0, 0x0000ea68);
-	else
-		writel(0x0000ea68, usb2->dmu + BCMA_DMU_CRU_CLKSET_KEY);
+	regmap_write(usb2->clkset, 0, 0x0000ea68);
 
 	/* Write USB 2.0 PLL control setting */
 	usb2ctl &= ~BCMA_DMU_CRU_USB2_CONTROL_USB_PLL_NDIV_MASK;
 	usb2ctl |= usb_pll_ndiv << BCMA_DMU_CRU_USB2_CONTROL_USB_PLL_NDIV_SHIFT;
-	if (usb2->base)
-		writel(usb2ctl, usb2->base);
-	else
-		writel(usb2ctl, usb2->dmu + BCMA_DMU_CRU_USB2_CONTROL);
+
+	writel(usb2ctl, usb2->base);
 
 	/* Lock DMU PLL settings */
-	if (usb2->clkset)
-		regmap_write(usb2->clkset, 0, 0x00000000);
-	else
-		writel(0x00000000, usb2->dmu + BCMA_DMU_CRU_CLKSET_KEY);
+	regmap_write(usb2->clkset, 0, 0x00000000);
 
 err_clk_off:
 	clk_disable_unprepare(usb2->ref_clk);
@@ -107,27 +93,17 @@ static int bcm_ns_usb2_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	usb2->dev = dev;
 
-	if (of_property_present(dev->of_node, "brcm,syscon-clkset")) {
-		usb2->base = devm_platform_ioremap_resource(pdev, 0);
-		if (IS_ERR(usb2->base)) {
-			dev_err(dev, "Failed to map control reg\n");
-			return PTR_ERR(usb2->base);
-		}
-
-		usb2->clkset = syscon_regmap_lookup_by_phandle(dev->of_node,
-							       "brcm,syscon-clkset");
-		if (IS_ERR(usb2->clkset)) {
-			dev_err(dev, "Failed to lookup clkset regmap\n");
-			return PTR_ERR(usb2->clkset);
-		}
-	} else {
-		usb2->dmu = devm_platform_ioremap_resource_byname(pdev, "dmu");
-		if (IS_ERR(usb2->dmu)) {
-			dev_err(dev, "Failed to map DMU regs\n");
-			return PTR_ERR(usb2->dmu);
-		}
+	usb2->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(usb2->base)) {
+		dev_err(dev, "Failed to map control reg\n");
+		return PTR_ERR(usb2->base);
+	}
 
-		dev_warn(dev, "using deprecated DT binding\n");
+	usb2->clkset = syscon_regmap_lookup_by_phandle(dev->of_node,
+						       "brcm,syscon-clkset");
+	if (IS_ERR(usb2->clkset)) {
+		dev_err(dev, "Failed to lookup clkset regmap\n");
+		return PTR_ERR(usb2->clkset);
 	}
 
 	usb2->ref_clk = devm_clk_get(dev, "phy-ref-clk");

From d41bb5e00ec7ac2905ab115ed4bbf971aa593704 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 9 Sep 2024 17:14:41 +0200
Subject: [PATCH 0563/1530] phy: sparx5-serdes: add support for private match
 data

In order to reuse the existing Sparx5 SERDES driver for lan969x, we add
support for private match data, with initial fields for the iomap and
imap_size.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Link: https://lore.kernel.org/r/20240909-sparx5-lan969x-serdes-driver-v2-1-d695bcb57b84@microchip.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/microchip/sparx5_serdes.c | 16 +++++++++++++---
 drivers/phy/microchip/sparx5_serdes.h |  6 ++++++
 2 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/drivers/phy/microchip/sparx5_serdes.c b/drivers/phy/microchip/sparx5_serdes.c
index 7cb85029fab39..5427e8627a787 100644
--- a/drivers/phy/microchip/sparx5_serdes.c
+++ b/drivers/phy/microchip/sparx5_serdes.c
@@ -2507,6 +2507,11 @@ static struct sparx5_serdes_io_resource sparx5_serdes_iomap[] =  {
 	{ TARGET_SD_LANE_25G + 7, 0x5c8000 }, /* 0x610dd0000: sd_lane_25g_32 */
 };
 
+static const struct sparx5_serdes_match_data sparx5_desc = {
+	.iomap = sparx5_serdes_iomap,
+	.iomap_size = ARRAY_SIZE(sparx5_serdes_iomap),
+};
+
 /* Client lookup function, uses serdes index */
 static struct phy *sparx5_serdes_xlate(struct device *dev,
 				     const struct of_phandle_args *args)
@@ -2555,6 +2560,10 @@ static int sparx5_serdes_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, priv);
 	priv->dev = &pdev->dev;
 
+	priv->data = device_get_match_data(priv->dev);
+	if (!priv->data)
+		return -EINVAL;
+
 	/* Get coreclock */
 	clk = devm_clk_get(priv->dev, NULL);
 	if (IS_ERR(clk)) {
@@ -2579,8 +2588,9 @@ static int sparx5_serdes_probe(struct platform_device *pdev)
 			iores->name);
 		return -ENOMEM;
 	}
-	for (idx = 0; idx < ARRAY_SIZE(sparx5_serdes_iomap); idx++) {
-		struct sparx5_serdes_io_resource *iomap = &sparx5_serdes_iomap[idx];
+	for (idx = 0; idx < priv->data->iomap_size; idx++) {
+		const struct sparx5_serdes_io_resource *iomap =
+			&priv->data->iomap[idx];
 
 		priv->regs[iomap->id] = iomem + iomap->offset;
 	}
@@ -2599,7 +2609,7 @@ static int sparx5_serdes_probe(struct platform_device *pdev)
 }
 
 static const struct of_device_id sparx5_serdes_match[] = {
-	{ .compatible = "microchip,sparx5-serdes" },
+	{ .compatible = "microchip,sparx5-serdes", .data = &sparx5_desc },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, sparx5_serdes_match);
diff --git a/drivers/phy/microchip/sparx5_serdes.h b/drivers/phy/microchip/sparx5_serdes.h
index 13f94a29225a4..128f8c53172f1 100644
--- a/drivers/phy/microchip/sparx5_serdes.h
+++ b/drivers/phy/microchip/sparx5_serdes.h
@@ -26,11 +26,17 @@ enum sparx5_serdes_mode {
 	SPX5_SD_MODE_SFI,
 };
 
+struct sparx5_serdes_match_data {
+	const struct sparx5_serdes_io_resource *iomap;
+	int iomap_size;
+};
+
 struct sparx5_serdes_private {
 	struct device *dev;
 	void __iomem *regs[NUM_TARGETS];
 	struct phy *phys[SPX5_SERDES_MAX];
 	unsigned long coreclock;
+	const struct sparx5_serdes_match_data *data;
 };
 
 struct sparx5_serdes_macro {

From 8e65baf8ccc1fdc72645db15a10bd69209cccfb8 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 9 Sep 2024 17:14:42 +0200
Subject: [PATCH 0564/1530] phy: sparx5-serdes: add constants to match data

We need to handle a few different constants that differ for Sparx5 and
lan969x. Add a new struct: sparx5_serdes_consts for this purpose. We
populate it with an initial field for the number of SERDES'es: sd_max.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Link: https://lore.kernel.org/r/20240909-sparx5-lan969x-serdes-driver-v2-2-d695bcb57b84@microchip.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/microchip/sparx5_serdes.c | 7 +++++--
 drivers/phy/microchip/sparx5_serdes.h | 5 +++++
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/phy/microchip/sparx5_serdes.c b/drivers/phy/microchip/sparx5_serdes.c
index 5427e8627a787..c3ed028fc74e3 100644
--- a/drivers/phy/microchip/sparx5_serdes.c
+++ b/drivers/phy/microchip/sparx5_serdes.c
@@ -2510,6 +2510,9 @@ static struct sparx5_serdes_io_resource sparx5_serdes_iomap[] =  {
 static const struct sparx5_serdes_match_data sparx5_desc = {
 	.iomap = sparx5_serdes_iomap,
 	.iomap_size = ARRAY_SIZE(sparx5_serdes_iomap),
+	.consts = {
+		.sd_max       = 33,
+	},
 };
 
 /* Client lookup function, uses serdes index */
@@ -2526,7 +2529,7 @@ static struct phy *sparx5_serdes_xlate(struct device *dev,
 	sidx = args->args[0];
 
 	/* Check validity: ERR_PTR(-ENODEV) if not valid */
-	for (idx = 0; idx < SPX5_SERDES_MAX; idx++) {
+	for (idx = 0; idx < priv->data->consts.sd_max; idx++) {
 		struct sparx5_serdes_macro *macro =
 			phy_get_drvdata(priv->phys[idx]);
 
@@ -2594,7 +2597,7 @@ static int sparx5_serdes_probe(struct platform_device *pdev)
 
 		priv->regs[iomap->id] = iomem + iomap->offset;
 	}
-	for (idx = 0; idx < SPX5_SERDES_MAX; idx++) {
+	for (idx = 0; idx < priv->data->consts.sd_max; idx++) {
 		err = sparx5_phy_create(priv, idx, &priv->phys[idx]);
 		if (err)
 			return err;
diff --git a/drivers/phy/microchip/sparx5_serdes.h b/drivers/phy/microchip/sparx5_serdes.h
index 128f8c53172f1..8c27cfde4938a 100644
--- a/drivers/phy/microchip/sparx5_serdes.h
+++ b/drivers/phy/microchip/sparx5_serdes.h
@@ -26,7 +26,12 @@ enum sparx5_serdes_mode {
 	SPX5_SD_MODE_SFI,
 };
 
+struct sparx5_serdes_consts {
+	int sd_max;
+};
+
 struct sparx5_serdes_match_data {
+	const struct sparx5_serdes_consts consts;
 	const struct sparx5_serdes_io_resource *iomap;
 	int iomap_size;
 };

From 5206ba966d0b053bcd15e4fcba17284201ca6199 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 9 Sep 2024 17:14:43 +0200
Subject: [PATCH 0565/1530] phy: sparx5-serdes: add constant for the number of
 CMU's

The number of CMU's differ for Sparx5 and lan969x, so add a new field:
cmu_max and use it throughout.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Link: https://lore.kernel.org/r/20240909-sparx5-lan969x-serdes-driver-v2-3-d695bcb57b84@microchip.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/microchip/sparx5_serdes.c | 5 ++---
 drivers/phy/microchip/sparx5_serdes.h | 1 +
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/phy/microchip/sparx5_serdes.c b/drivers/phy/microchip/sparx5_serdes.c
index c3ed028fc74e3..9c91545dd8e17 100644
--- a/drivers/phy/microchip/sparx5_serdes.c
+++ b/drivers/phy/microchip/sparx5_serdes.c
@@ -21,8 +21,6 @@
 
 #include "sparx5_serdes.h"
 
-#define SPX5_CMU_MAX          14
-
 #define SPX5_SERDES_10G_START 13
 #define SPX5_SERDES_25G_START 25
 #define SPX5_SERDES_6G10G_CNT SPX5_SERDES_25G_START
@@ -1101,7 +1099,7 @@ static void sparx5_serdes_cmu_power_off(struct sparx5_serdes_private *priv)
 	int i;
 
 	/* Power down each CMU */
-	for (i = 0; i < SPX5_CMU_MAX; i++) {
+	for (i = 0; i < priv->data->consts.cmu_max; i++) {
 		cmu_inst = sdx5_inst_get(priv, TARGET_SD_CMU, i);
 		cmu_cfg_inst = sdx5_inst_get(priv, TARGET_SD_CMU_CFG, i);
 
@@ -2512,6 +2510,7 @@ static const struct sparx5_serdes_match_data sparx5_desc = {
 	.iomap_size = ARRAY_SIZE(sparx5_serdes_iomap),
 	.consts = {
 		.sd_max       = 33,
+		.cmu_max      = 14,
 	},
 };
 
diff --git a/drivers/phy/microchip/sparx5_serdes.h b/drivers/phy/microchip/sparx5_serdes.h
index 8c27cfde4938a..87c44bbaf3683 100644
--- a/drivers/phy/microchip/sparx5_serdes.h
+++ b/drivers/phy/microchip/sparx5_serdes.h
@@ -28,6 +28,7 @@ enum sparx5_serdes_mode {
 
 struct sparx5_serdes_consts {
 	int sd_max;
+	int cmu_max;
 };
 
 struct sparx5_serdes_match_data {

From d61d42a91e322f73b8c68e22347469306b280008 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 9 Sep 2024 17:14:44 +0200
Subject: [PATCH 0566/1530] phy: sparx5-serdes: add ops to match data

We need to handle code differently in a few places. Add a struct:
sparx5_serdes_ops for this purpose, and populate it a with function to
set the SERDES type.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Link: https://lore.kernel.org/r/20240909-sparx5-lan969x-serdes-driver-v2-4-d695bcb57b84@microchip.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/microchip/sparx5_serdes.c | 29 ++++++++++++++++++---------
 drivers/phy/microchip/sparx5_serdes.h | 27 +++++++++++++++----------
 2 files changed, 35 insertions(+), 21 deletions(-)

diff --git a/drivers/phy/microchip/sparx5_serdes.c b/drivers/phy/microchip/sparx5_serdes.c
index 9c91545dd8e17..b1376a142b147 100644
--- a/drivers/phy/microchip/sparx5_serdes.c
+++ b/drivers/phy/microchip/sparx5_serdes.c
@@ -2373,6 +2373,20 @@ static const struct phy_ops sparx5_serdes_ops = {
 	.owner		= THIS_MODULE,
 };
 
+static void sparx5_serdes_type_set(struct sparx5_serdes_macro *macro, int sidx)
+{
+	if (sidx < SPX5_SERDES_10G_START) {
+		macro->serdestype = SPX5_SDT_6G;
+		macro->stpidx = macro->sidx;
+	} else if (sidx < SPX5_SERDES_25G_START) {
+		macro->serdestype = SPX5_SDT_10G;
+		macro->stpidx = macro->sidx - SPX5_SERDES_10G_START;
+	} else {
+		macro->serdestype = SPX5_SDT_25G;
+		macro->stpidx = macro->sidx - SPX5_SERDES_25G_START;
+	}
+}
+
 static int sparx5_phy_create(struct sparx5_serdes_private *priv,
 			   int idx, struct phy **phy)
 {
@@ -2389,16 +2403,8 @@ static int sparx5_phy_create(struct sparx5_serdes_private *priv,
 	macro->sidx = idx;
 	macro->priv = priv;
 	macro->speed = SPEED_UNKNOWN;
-	if (idx < SPX5_SERDES_10G_START) {
-		macro->serdestype = SPX5_SDT_6G;
-		macro->stpidx = macro->sidx;
-	} else if (idx < SPX5_SERDES_25G_START) {
-		macro->serdestype = SPX5_SDT_10G;
-		macro->stpidx = macro->sidx - SPX5_SERDES_10G_START;
-	} else {
-		macro->serdestype = SPX5_SDT_25G;
-		macro->stpidx = macro->sidx - SPX5_SERDES_25G_START;
-	}
+
+	priv->data->ops.serdes_type_set(macro, idx);
 
 	phy_set_drvdata(*phy, macro);
 
@@ -2512,6 +2518,9 @@ static const struct sparx5_serdes_match_data sparx5_desc = {
 		.sd_max       = 33,
 		.cmu_max      = 14,
 	},
+	.ops = {
+		.serdes_type_set      = &sparx5_serdes_type_set,
+	},
 };
 
 /* Client lookup function, uses serdes index */
diff --git a/drivers/phy/microchip/sparx5_serdes.h b/drivers/phy/microchip/sparx5_serdes.h
index 87c44bbaf3683..785c7fe0bbebe 100644
--- a/drivers/phy/microchip/sparx5_serdes.h
+++ b/drivers/phy/microchip/sparx5_serdes.h
@@ -26,13 +26,29 @@ enum sparx5_serdes_mode {
 	SPX5_SD_MODE_SFI,
 };
 
+struct sparx5_serdes_macro {
+	struct sparx5_serdes_private *priv;
+	u32 sidx;
+	u32 stpidx;
+	enum sparx5_serdes_type serdestype;
+	enum sparx5_serdes_mode serdesmode;
+	phy_interface_t portmode;
+	int speed;
+	enum phy_media media;
+};
+
 struct sparx5_serdes_consts {
 	int sd_max;
 	int cmu_max;
 };
 
+struct sparx5_serdes_ops {
+	void (*serdes_type_set)(struct sparx5_serdes_macro *macro, int sidx);
+};
+
 struct sparx5_serdes_match_data {
 	const struct sparx5_serdes_consts consts;
+	const struct sparx5_serdes_ops ops;
 	const struct sparx5_serdes_io_resource *iomap;
 	int iomap_size;
 };
@@ -45,17 +61,6 @@ struct sparx5_serdes_private {
 	const struct sparx5_serdes_match_data *data;
 };
 
-struct sparx5_serdes_macro {
-	struct sparx5_serdes_private *priv;
-	u32 sidx;
-	u32 stpidx;
-	enum sparx5_serdes_type serdestype;
-	enum sparx5_serdes_mode serdesmode;
-	phy_interface_t portmode;
-	int speed;
-	enum phy_media media;
-};
-
 /* Read, Write and modify registers content.
  * The register definition macros start at the id
  */

From f16df057837e06d16b5e5f978d79d80d70784b80 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 9 Sep 2024 17:14:45 +0200
Subject: [PATCH 0567/1530] phy: sparx5-serdes: add function for getting the
 CMU index

The SERDES to CMU mapping is different on Sparx5 and lan969x. Therefore
create a function for getting the CMU index on Sparx5.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Link: https://lore.kernel.org/r/20240909-sparx5-lan969x-serdes-driver-v2-5-d695bcb57b84@microchip.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/microchip/sparx5_serdes.c | 11 ++---------
 drivers/phy/microchip/sparx5_serdes.h |  9 +++++++++
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/phy/microchip/sparx5_serdes.c b/drivers/phy/microchip/sparx5_serdes.c
index b1376a142b147..5b918a2716dd1 100644
--- a/drivers/phy/microchip/sparx5_serdes.c
+++ b/drivers/phy/microchip/sparx5_serdes.c
@@ -28,14 +28,6 @@
 /* Optimal power settings from GUC */
 #define SPX5_SERDES_QUIET_MODE_VAL 0x01ef4e0c
 
-enum sparx5_10g28cmu_mode {
-	SPX5_SD10G28_CMU_MAIN = 0,
-	SPX5_SD10G28_CMU_AUX1 = 1,
-	SPX5_SD10G28_CMU_AUX2 = 3,
-	SPX5_SD10G28_CMU_NONE = 4,
-	SPX5_SD10G28_CMU_MAX,
-};
-
 enum sparx5_sd25g28_mode_preset_type {
 	SPX5_SD25G28_MODE_PRESET_25000,
 	SPX5_SD25G28_MODE_PRESET_10000,
@@ -1648,7 +1640,7 @@ static int sparx5_sd10g28_apply_params(struct sparx5_serdes_macro *macro,
 	if (params->skip_cmu_cfg)
 		return 0;
 
-	cmu_idx = sparx5_serdes_cmu_get(params->cmu_sel, lane_index);
+	cmu_idx = priv->data->ops.serdes_cmu_get(params->cmu_sel, macro->sidx);
 	err = sparx5_cmu_cfg(priv, cmu_idx);
 	if (err)
 		return err;
@@ -2520,6 +2512,7 @@ static const struct sparx5_serdes_match_data sparx5_desc = {
 	},
 	.ops = {
 		.serdes_type_set      = &sparx5_serdes_type_set,
+		.serdes_cmu_get       = &sparx5_serdes_cmu_get,
 	},
 };
 
diff --git a/drivers/phy/microchip/sparx5_serdes.h b/drivers/phy/microchip/sparx5_serdes.h
index 785c7fe0bbebe..a7e92c1330e92 100644
--- a/drivers/phy/microchip/sparx5_serdes.h
+++ b/drivers/phy/microchip/sparx5_serdes.h
@@ -26,6 +26,14 @@ enum sparx5_serdes_mode {
 	SPX5_SD_MODE_SFI,
 };
 
+enum sparx5_10g28cmu_mode {
+	SPX5_SD10G28_CMU_MAIN = 0,
+	SPX5_SD10G28_CMU_AUX1 = 1,
+	SPX5_SD10G28_CMU_AUX2 = 3,
+	SPX5_SD10G28_CMU_NONE = 4,
+	SPX5_SD10G28_CMU_MAX,
+};
+
 struct sparx5_serdes_macro {
 	struct sparx5_serdes_private *priv;
 	u32 sidx;
@@ -44,6 +52,7 @@ struct sparx5_serdes_consts {
 
 struct sparx5_serdes_ops {
 	void (*serdes_type_set)(struct sparx5_serdes_macro *macro, int sidx);
+	int (*serdes_cmu_get)(enum sparx5_10g28cmu_mode mode, int sd_index);
 };
 
 struct sparx5_serdes_match_data {

From c8e4c8b7ea47cb9044c190e6148e994c8e04a34a Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 9 Sep 2024 17:14:46 +0200
Subject: [PATCH 0568/1530] phy: sparx5-serdes: add indirection layer to
 register macros

The register macros are used to read and write to the SERDES registers.
The registers are largely the same on Sparx5 and lan969x, however some
register target sizes differ. Therefore we introduce a new indirection
to the register macros. The target sizes are looked up, using a mapping
table (sparx5_serdes_tsize) that maps the register target to the
register target size.

With this addition, we can reuse all the existing macros for lan969x.

Also the autogenerated macros are now formatted slightly different, to
adhere to a 80 character limit.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Link: https://lore.kernel.org/r/20240909-sparx5-lan969x-serdes-driver-v2-6-d695bcb57b84@microchip.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/microchip/sparx5_serdes.c      |  14 +
 drivers/phy/microchip/sparx5_serdes.h      |   1 +
 drivers/phy/microchip/sparx5_serdes_regs.h | 746 ++++++++++++++-------
 3 files changed, 507 insertions(+), 254 deletions(-)

diff --git a/drivers/phy/microchip/sparx5_serdes.c b/drivers/phy/microchip/sparx5_serdes.c
index 5b918a2716dd1..8a716bfaa0231 100644
--- a/drivers/phy/microchip/sparx5_serdes.c
+++ b/drivers/phy/microchip/sparx5_serdes.c
@@ -28,6 +28,17 @@
 /* Optimal power settings from GUC */
 #define SPX5_SERDES_QUIET_MODE_VAL 0x01ef4e0c
 
+/* Register target sizes */
+const unsigned int sparx5_serdes_tsize[TSIZE_LAST] = {
+	[TC_SD10G_LANE] = 12,
+	[TC_SD_CMU] = 14,
+	[TC_SD_CMU_CFG] = 14,
+	[TC_SD_LANE] = 25,
+};
+
+/* Pointer to the register target size table */
+const unsigned int *tsize;
+
 enum sparx5_sd25g28_mode_preset_type {
 	SPX5_SD25G28_MODE_PRESET_25000,
 	SPX5_SD25G28_MODE_PRESET_10000,
@@ -2506,6 +2517,7 @@ static struct sparx5_serdes_io_resource sparx5_serdes_iomap[] =  {
 static const struct sparx5_serdes_match_data sparx5_desc = {
 	.iomap = sparx5_serdes_iomap,
 	.iomap_size = ARRAY_SIZE(sparx5_serdes_iomap),
+	.tsize = sparx5_serdes_tsize,
 	.consts = {
 		.sd_max       = 33,
 		.cmu_max      = 14,
@@ -2568,6 +2580,8 @@ static int sparx5_serdes_probe(struct platform_device *pdev)
 	if (!priv->data)
 		return -EINVAL;
 
+	tsize = priv->data->tsize;
+
 	/* Get coreclock */
 	clk = devm_clk_get(priv->dev, NULL);
 	if (IS_ERR(clk)) {
diff --git a/drivers/phy/microchip/sparx5_serdes.h b/drivers/phy/microchip/sparx5_serdes.h
index a7e92c1330e92..50900bf06c4c7 100644
--- a/drivers/phy/microchip/sparx5_serdes.h
+++ b/drivers/phy/microchip/sparx5_serdes.h
@@ -60,6 +60,7 @@ struct sparx5_serdes_match_data {
 	const struct sparx5_serdes_ops ops;
 	const struct sparx5_serdes_io_resource *iomap;
 	int iomap_size;
+	const unsigned int *tsize;
 };
 
 struct sparx5_serdes_private {
diff --git a/drivers/phy/microchip/sparx5_serdes_regs.h b/drivers/phy/microchip/sparx5_serdes_regs.h
index d0543fd3dc94d..11c4fdc593fad 100644
--- a/drivers/phy/microchip/sparx5_serdes_regs.h
+++ b/drivers/phy/microchip/sparx5_serdes_regs.h
@@ -1,11 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0+
  * Microchip Sparx5 SerDes driver
  *
- * Copyright (c) 2020 Microchip Technology Inc.
+ * Copyright (c) 2024 Microchip Technology Inc.
  */
 
-/* This file is autogenerated by cml-utils 2020-11-16 13:11:27 +0100.
- * Commit ID: 13bdf073131d8bf40c54901df6988ae4e9c8f29f
+/* This file is autogenerated by cml-utils 2023-04-13 15:02:00 +0200.
+ * Commit ID: 5ac560288d46048f872ecdb8add53717f1efc0e1
  */
 
 #ifndef _SPARX5_SERDES_REGS_H_
@@ -26,10 +26,25 @@ enum sparx5_serdes_target {
 	NUM_TARGETS = 332
 };
 
+enum sparx5_serdes_tsize_enum {
+	TC_SD10G_LANE,
+	TC_SD_CMU,
+	TC_SD_CMU_CFG,
+	TC_SD_LANE,
+	TSIZE_LAST,
+};
+
+/* sparx5_serdes.c */
+extern const unsigned int *tsize;
+
+#define TSIZE(o) tsize[o]
+
 #define __REG(...)    __VA_ARGS__
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_01 */
-#define SD10G_LANE_LANE_01(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 4, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_01 */
+#define SD10G_LANE_LANE_01(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 4, 0,  \
+	      1, 4)
 
 #define SD10G_LANE_LANE_01_CFG_PMA_TX_CK_BITWIDTH_2_0 GENMASK(2, 0)
 #define SD10G_LANE_LANE_01_CFG_PMA_TX_CK_BITWIDTH_2_0_SET(x)\
@@ -49,8 +64,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_01_CFG_RXDET_STR_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_01_CFG_RXDET_STR, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_02 */
-#define SD10G_LANE_LANE_02(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 8, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_02 */
+#define SD10G_LANE_LANE_02(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 8, 0,  \
+	      1, 4)
 
 #define SD10G_LANE_LANE_02_CFG_EN_ADV            BIT(0)
 #define SD10G_LANE_LANE_02_CFG_EN_ADV_SET(x)\
@@ -82,8 +99,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_02_CFG_TAP_ADV_3_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_02_CFG_TAP_ADV_3_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_03 */
-#define SD10G_LANE_LANE_03(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 12, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_03 */
+#define SD10G_LANE_LANE_03(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 12, 0, \
+	      1, 4)
 
 #define SD10G_LANE_LANE_03_CFG_TAP_MAIN          BIT(0)
 #define SD10G_LANE_LANE_03_CFG_TAP_MAIN_SET(x)\
@@ -91,8 +110,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_03_CFG_TAP_MAIN_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_03_CFG_TAP_MAIN, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_04 */
-#define SD10G_LANE_LANE_04(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 16, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_04 */
+#define SD10G_LANE_LANE_04(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 16, 0, \
+	      1, 4)
 
 #define SD10G_LANE_LANE_04_CFG_TAP_DLY_4_0       GENMASK(4, 0)
 #define SD10G_LANE_LANE_04_CFG_TAP_DLY_4_0_SET(x)\
@@ -100,8 +121,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_04_CFG_TAP_DLY_4_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_04_CFG_TAP_DLY_4_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_06 */
-#define SD10G_LANE_LANE_06(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 24, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_06 */
+#define SD10G_LANE_LANE_06(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 24, 0, \
+	      1, 4)
 
 #define SD10G_LANE_LANE_06_CFG_PD_DRIVER         BIT(0)
 #define SD10G_LANE_LANE_06_CFG_PD_DRIVER_SET(x)\
@@ -139,8 +162,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_06_CFG_EN_PREEMPH_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_06_CFG_EN_PREEMPH, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_0B */
-#define SD10G_LANE_LANE_0B(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 44, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_0B */
+#define SD10G_LANE_LANE_0B(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 44, 0, \
+	      1, 4)
 
 #define SD10G_LANE_LANE_0B_CFG_EQ_RES_3_0        GENMASK(3, 0)
 #define SD10G_LANE_LANE_0B_CFG_EQ_RES_3_0_SET(x)\
@@ -172,8 +197,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_0B_CFG_RESETB_OSCAL_SQ_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_0B_CFG_RESETB_OSCAL_SQ, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_0C */
-#define SD10G_LANE_LANE_0C(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 48, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_0C */
+#define SD10G_LANE_LANE_0C(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 48, 0, \
+	      1, 4)
 
 #define SD10G_LANE_LANE_0C_CFG_OSCAL_AFE         BIT(0)
 #define SD10G_LANE_LANE_0C_CFG_OSCAL_AFE_SET(x)\
@@ -223,8 +250,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_0C_CFG_RX_PCIE_GEN12_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_0C_CFG_RX_PCIE_GEN12, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_0D */
-#define SD10G_LANE_LANE_0D(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 52, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_0D */
+#define SD10G_LANE_LANE_0D(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 52, 0, \
+	      1, 4)
 
 #define SD10G_LANE_LANE_0D_CFG_CTLE_M_THR_1_0    GENMASK(1, 0)
 #define SD10G_LANE_LANE_0D_CFG_CTLE_M_THR_1_0_SET(x)\
@@ -238,8 +267,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_0D_CFG_EQR_BYP_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_0D_CFG_EQR_BYP, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_0E */
-#define SD10G_LANE_LANE_0E(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 56, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_0E */
+#define SD10G_LANE_LANE_0E(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 56, 0, \
+	      1, 4)
 
 #define SD10G_LANE_LANE_0E_CFG_EQC_FORCE_3_0     GENMASK(3, 0)
 #define SD10G_LANE_LANE_0E_CFG_EQC_FORCE_3_0_SET(x)\
@@ -265,8 +296,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_0E_CFG_SUM_SETCM_EN_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_0E_CFG_SUM_SETCM_EN, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_0F */
-#define SD10G_LANE_LANE_0F(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 60, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_0F */
+#define SD10G_LANE_LANE_0F(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 60, 0, \
+	      1, 4)
 
 #define SD10G_LANE_LANE_0F_R_CDR_M_GEN1_7_0      GENMASK(7, 0)
 #define SD10G_LANE_LANE_0F_R_CDR_M_GEN1_7_0_SET(x)\
@@ -274,8 +307,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_0F_R_CDR_M_GEN1_7_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_0F_R_CDR_M_GEN1_7_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_13 */
-#define SD10G_LANE_LANE_13(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 76, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_13 */
+#define SD10G_LANE_LANE_13(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 76, 0, \
+	      1, 4)
 
 #define SD10G_LANE_LANE_13_CFG_DCDR_PD           BIT(0)
 #define SD10G_LANE_LANE_13_CFG_DCDR_PD_SET(x)\
@@ -295,8 +330,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_13_CFG_CDRCK_EN_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_13_CFG_CDRCK_EN, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_14 */
-#define SD10G_LANE_LANE_14(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 80, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_14 */
+#define SD10G_LANE_LANE_14(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 80, 0, \
+	      1, 4)
 
 #define SD10G_LANE_LANE_14_CFG_PI_EXT_DAC_7_0    GENMASK(7, 0)
 #define SD10G_LANE_LANE_14_CFG_PI_EXT_DAC_7_0_SET(x)\
@@ -304,8 +341,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_14_CFG_PI_EXT_DAC_7_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_14_CFG_PI_EXT_DAC_7_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_15 */
-#define SD10G_LANE_LANE_15(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 84, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_15 */
+#define SD10G_LANE_LANE_15(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 84, 0, \
+	      1, 4)
 
 #define SD10G_LANE_LANE_15_CFG_PI_EXT_DAC_15_8   GENMASK(7, 0)
 #define SD10G_LANE_LANE_15_CFG_PI_EXT_DAC_15_8_SET(x)\
@@ -313,8 +352,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_15_CFG_PI_EXT_DAC_15_8_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_15_CFG_PI_EXT_DAC_15_8, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_16 */
-#define SD10G_LANE_LANE_16(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 88, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_16 */
+#define SD10G_LANE_LANE_16(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 88, 0, \
+	      1, 4)
 
 #define SD10G_LANE_LANE_16_CFG_PI_EXT_DAC_23_16  GENMASK(7, 0)
 #define SD10G_LANE_LANE_16_CFG_PI_EXT_DAC_23_16_SET(x)\
@@ -322,8 +363,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_16_CFG_PI_EXT_DAC_23_16_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_16_CFG_PI_EXT_DAC_23_16, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_1A */
-#define SD10G_LANE_LANE_1A(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 104, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_1A */
+#define SD10G_LANE_LANE_1A(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 104, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_1A_CFG_PI_R_SCAN_EN      BIT(0)
 #define SD10G_LANE_LANE_1A_CFG_PI_R_SCAN_EN_SET(x)\
@@ -355,8 +398,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_1A_CFG_PI_FLOOP_STEPS_1_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_1A_CFG_PI_FLOOP_STEPS_1_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_22 */
-#define SD10G_LANE_LANE_22(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 136, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_22 */
+#define SD10G_LANE_LANE_22(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 136, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_22_CFG_DFETAP_EN_5_1     GENMASK(4, 0)
 #define SD10G_LANE_LANE_22_CFG_DFETAP_EN_5_1_SET(x)\
@@ -364,8 +409,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_22_CFG_DFETAP_EN_5_1_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_22_CFG_DFETAP_EN_5_1, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_23 */
-#define SD10G_LANE_LANE_23(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 140, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_23 */
+#define SD10G_LANE_LANE_23(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 140, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_23_CFG_DFE_PD            BIT(0)
 #define SD10G_LANE_LANE_23_CFG_DFE_PD_SET(x)\
@@ -397,8 +444,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_23_CFG_DFEDIG_M_2_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_23_CFG_DFEDIG_M_2_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_24 */
-#define SD10G_LANE_LANE_24(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 144, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_24 */
+#define SD10G_LANE_LANE_24(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 144, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_24_CFG_PI_BW_GEN1_3_0    GENMASK(3, 0)
 #define SD10G_LANE_LANE_24_CFG_PI_BW_GEN1_3_0_SET(x)\
@@ -412,8 +461,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_24_CFG_PI_BW_GEN2_3_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_24_CFG_PI_BW_GEN2_3_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_26 */
-#define SD10G_LANE_LANE_26(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 152, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_26 */
+#define SD10G_LANE_LANE_26(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 152, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_26_CFG_ISCAN_EXT_DAC_7_0 GENMASK(7, 0)
 #define SD10G_LANE_LANE_26_CFG_ISCAN_EXT_DAC_7_0_SET(x)\
@@ -421,8 +472,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_26_CFG_ISCAN_EXT_DAC_7_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_26_CFG_ISCAN_EXT_DAC_7_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_2F */
-#define SD10G_LANE_LANE_2F(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 188, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_2F */
+#define SD10G_LANE_LANE_2F(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 188, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_2F_CFG_VGA_CP_2_0        GENMASK(2, 0)
 #define SD10G_LANE_LANE_2F_CFG_VGA_CP_2_0_SET(x)\
@@ -436,8 +489,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_2F_CFG_VGA_CTRL_3_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_2F_CFG_VGA_CTRL_3_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_30 */
-#define SD10G_LANE_LANE_30(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 192, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_30 */
+#define SD10G_LANE_LANE_30(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 192, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_30_CFG_SUMMER_EN         BIT(0)
 #define SD10G_LANE_LANE_30_CFG_SUMMER_EN_SET(x)\
@@ -451,8 +506,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_30_CFG_RXDIV_SEL_2_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_30_CFG_RXDIV_SEL_2_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_31 */
-#define SD10G_LANE_LANE_31(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 196, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_31 */
+#define SD10G_LANE_LANE_31(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 196, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_31_CFG_PI_RSTN           BIT(0)
 #define SD10G_LANE_LANE_31_CFG_PI_RSTN_SET(x)\
@@ -490,8 +547,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_31_CFG_R50_EN_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_31_CFG_R50_EN, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_32 */
-#define SD10G_LANE_LANE_32(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 200, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_32 */
+#define SD10G_LANE_LANE_32(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 200, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_32_CFG_ITX_IPCLK_BASE_1_0 GENMASK(1, 0)
 #define SD10G_LANE_LANE_32_CFG_ITX_IPCLK_BASE_1_0_SET(x)\
@@ -505,8 +564,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_32_CFG_ITX_IPCML_BASE_1_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_32_CFG_ITX_IPCML_BASE_1_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_33 */
-#define SD10G_LANE_LANE_33(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 204, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_33 */
+#define SD10G_LANE_LANE_33(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 204, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_33_CFG_ITX_IPDRIVER_BASE_2_0 GENMASK(2, 0)
 #define SD10G_LANE_LANE_33_CFG_ITX_IPDRIVER_BASE_2_0_SET(x)\
@@ -520,8 +581,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_33_CFG_ITX_IPPREEMP_BASE_1_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_33_CFG_ITX_IPPREEMP_BASE_1_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_35 */
-#define SD10G_LANE_LANE_35(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 212, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_35 */
+#define SD10G_LANE_LANE_35(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 212, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_35_CFG_TXRATE_1_0        GENMASK(1, 0)
 #define SD10G_LANE_LANE_35_CFG_TXRATE_1_0_SET(x)\
@@ -535,8 +598,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_35_CFG_RXRATE_1_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_35_CFG_RXRATE_1_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_36 */
-#define SD10G_LANE_LANE_36(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 216, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_36 */
+#define SD10G_LANE_LANE_36(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 216, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_36_CFG_PREDRV_SLEWRATE_1_0 GENMASK(1, 0)
 #define SD10G_LANE_LANE_36_CFG_PREDRV_SLEWRATE_1_0_SET(x)\
@@ -568,8 +633,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_36_CFG_PRBS_SETB_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_36_CFG_PRBS_SETB, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_37 */
-#define SD10G_LANE_LANE_37(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 220, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_37 */
+#define SD10G_LANE_LANE_37(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 220, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_37_CFG_RXDET_COMP_PD     BIT(0)
 #define SD10G_LANE_LANE_37_CFG_RXDET_COMP_PD_SET(x)\
@@ -595,8 +662,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_37_CFG_IP_PRE_BASE_1_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_37_CFG_IP_PRE_BASE_1_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_39 */
-#define SD10G_LANE_LANE_39(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 228, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_39 */
+#define SD10G_LANE_LANE_39(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 228, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_39_CFG_RXFILT_Y_2_0      GENMASK(2, 0)
 #define SD10G_LANE_LANE_39_CFG_RXFILT_Y_2_0_SET(x)\
@@ -610,8 +679,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_39_CFG_RX_SSC_LH_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_39_CFG_RX_SSC_LH, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_3A */
-#define SD10G_LANE_LANE_3A(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 232, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_3A */
+#define SD10G_LANE_LANE_3A(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 232, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_3A_CFG_MP_MIN_3_0        GENMASK(3, 0)
 #define SD10G_LANE_LANE_3A_CFG_MP_MIN_3_0_SET(x)\
@@ -625,8 +696,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_3A_CFG_MP_MAX_3_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_3A_CFG_MP_MAX_3_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_3C */
-#define SD10G_LANE_LANE_3C(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 240, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_3C */
+#define SD10G_LANE_LANE_3C(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 240, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_3C_CFG_DIS_ACC           BIT(0)
 #define SD10G_LANE_LANE_3C_CFG_DIS_ACC_SET(x)\
@@ -640,8 +713,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_3C_CFG_DIS_2NDORDER_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_3C_CFG_DIS_2NDORDER, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_40 */
-#define SD10G_LANE_LANE_40(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 256, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_40 */
+#define SD10G_LANE_LANE_40(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 256, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_40_CFG_LANE_RESERVE_7_0  GENMASK(7, 0)
 #define SD10G_LANE_LANE_40_CFG_LANE_RESERVE_7_0_SET(x)\
@@ -649,8 +724,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_40_CFG_LANE_RESERVE_7_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_40_CFG_LANE_RESERVE_7_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_41 */
-#define SD10G_LANE_LANE_41(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 260, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_41 */
+#define SD10G_LANE_LANE_41(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 260, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_41_CFG_LANE_RESERVE_15_8 GENMASK(7, 0)
 #define SD10G_LANE_LANE_41_CFG_LANE_RESERVE_15_8_SET(x)\
@@ -658,8 +735,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_41_CFG_LANE_RESERVE_15_8_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_41_CFG_LANE_RESERVE_15_8, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_0:LANE_42 */
-#define SD10G_LANE_LANE_42(t)     __REG(TARGET_SD10G_LANE, t, 12, 0, 0, 1, 288, 264, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_0:LANE_42 */
+#define SD10G_LANE_LANE_42(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 0, 0, 1, 288, 264, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_42_CFG_CDR_KF_GEN1_2_0   GENMASK(2, 0)
 #define SD10G_LANE_LANE_42_CFG_CDR_KF_GEN1_2_0_SET(x)\
@@ -673,8 +752,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_42_CFG_CDR_KF_GEN2_2_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_42_CFG_CDR_KF_GEN2_2_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_1:LANE_48 */
-#define SD10G_LANE_LANE_48(t)     __REG(TARGET_SD10G_LANE, t, 12, 288, 0, 1, 40, 0, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_1:LANE_48 */
+#define SD10G_LANE_LANE_48(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 288, 0, 1, 40, 0, 0, \
+	      1, 4)
 
 #define SD10G_LANE_LANE_48_CFG_ALOS_THR_3_0      GENMASK(3, 0)
 #define SD10G_LANE_LANE_48_CFG_ALOS_THR_3_0_SET(x)\
@@ -694,8 +775,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_48_CFG_CLK_ENQ_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_48_CFG_CLK_ENQ, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_1:LANE_50 */
-#define SD10G_LANE_LANE_50(t)     __REG(TARGET_SD10G_LANE, t, 12, 288, 0, 1, 40, 32, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_1:LANE_50 */
+#define SD10G_LANE_LANE_50(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 288, 0, 1, 40, 32, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_50_CFG_SSC_PI_STEP_1_0   GENMASK(1, 0)
 #define SD10G_LANE_LANE_50_CFG_SSC_PI_STEP_1_0_SET(x)\
@@ -727,8 +810,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_50_CFG_JT_EN_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_50_CFG_JT_EN, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_2:LANE_52 */
-#define SD10G_LANE_LANE_52(t)     __REG(TARGET_SD10G_LANE, t, 12, 328, 0, 1, 24, 0, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_2:LANE_52 */
+#define SD10G_LANE_LANE_52(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 328, 0, 1, 24, 0, 0, \
+	      1, 4)
 
 #define SD10G_LANE_LANE_52_CFG_IBIAS_TUNE_RESERVE_5_0 GENMASK(5, 0)
 #define SD10G_LANE_LANE_52_CFG_IBIAS_TUNE_RESERVE_5_0_SET(x)\
@@ -736,8 +821,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_52_CFG_IBIAS_TUNE_RESERVE_5_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_52_CFG_IBIAS_TUNE_RESERVE_5_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_4:LANE_83 */
-#define SD10G_LANE_LANE_83(t)     __REG(TARGET_SD10G_LANE, t, 12, 464, 0, 1, 112, 60, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_4:LANE_83 */
+#define SD10G_LANE_LANE_83(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 464, 0, 1, 112, 60,  \
+	      0, 1, 4)
 
 #define SD10G_LANE_LANE_83_R_TX_BIT_REVERSE      BIT(0)
 #define SD10G_LANE_LANE_83_R_TX_BIT_REVERSE_SET(x)\
@@ -781,8 +868,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_83_R_CTLE_RSTN_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_83_R_CTLE_RSTN, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_5:LANE_93 */
-#define SD10G_LANE_LANE_93(t)     __REG(TARGET_SD10G_LANE, t, 12, 576, 0, 1, 64, 12, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_5:LANE_93 */
+#define SD10G_LANE_LANE_93(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 576, 0, 1, 64, 12, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_93_R_RXEI_FIFO_RST_EN    BIT(0)
 #define SD10G_LANE_LANE_93_R_RXEI_FIFO_RST_EN_SET(x)\
@@ -832,8 +921,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_93_R_RX_PCIE_GEN12_FROM_HWT_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_93_R_RX_PCIE_GEN12_FROM_HWT, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_5:LANE_94 */
-#define SD10G_LANE_LANE_94(t)     __REG(TARGET_SD10G_LANE, t, 12, 576, 0, 1, 64, 16, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_5:LANE_94 */
+#define SD10G_LANE_LANE_94(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 576, 0, 1, 64, 16, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_94_R_DWIDTHCTRL_2_0      GENMASK(2, 0)
 #define SD10G_LANE_LANE_94_R_DWIDTHCTRL_2_0_SET(x)\
@@ -865,8 +956,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_94_R_SWING_REG_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_94_R_SWING_REG, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_5:LANE_9E */
-#define SD10G_LANE_LANE_9E(t)     __REG(TARGET_SD10G_LANE, t, 12, 576, 0, 1, 64, 56, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_5:LANE_9E */
+#define SD10G_LANE_LANE_9E(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 576, 0, 1, 64, 56, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_9E_R_RXEQ_REG            BIT(0)
 #define SD10G_LANE_LANE_9E_R_RXEQ_REG_SET(x)\
@@ -886,8 +979,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_9E_R_EN_AUTO_CDR_RSTN_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_9E_R_EN_AUTO_CDR_RSTN, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_6:LANE_A1 */
-#define SD10G_LANE_LANE_A1(t)     __REG(TARGET_SD10G_LANE, t, 12, 640, 0, 1, 128, 4, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_6:LANE_A1 */
+#define SD10G_LANE_LANE_A1(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 640, 0, 1, 128, 4, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_A1_R_PMA_TXCK_DIV_SEL_1_0 GENMASK(1, 0)
 #define SD10G_LANE_LANE_A1_R_PMA_TXCK_DIV_SEL_1_0_SET(x)\
@@ -919,8 +1014,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_A1_R_PCLK_GATING_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_A1_R_PCLK_GATING, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_6:LANE_A2 */
-#define SD10G_LANE_LANE_A2(t)     __REG(TARGET_SD10G_LANE, t, 12, 640, 0, 1, 128, 8, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_6:LANE_A2 */
+#define SD10G_LANE_LANE_A2(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 640, 0, 1, 128, 8, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_A2_R_PCS2PMA_PHYMODE_4_0 GENMASK(4, 0)
 #define SD10G_LANE_LANE_A2_R_PCS2PMA_PHYMODE_4_0_SET(x)\
@@ -928,8 +1025,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_A2_R_PCS2PMA_PHYMODE_4_0_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_A2_R_PCS2PMA_PHYMODE_4_0, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_8:LANE_DF */
-#define SD10G_LANE_LANE_DF(t)     __REG(TARGET_SD10G_LANE, t, 12, 832, 0, 1, 84, 60, 0, 1, 4)
+/* SD10G_LANE_TARGET:LANE_GRP_8:LANE_DF */
+#define SD10G_LANE_LANE_DF(t)                                                  \
+	__REG(TARGET_SD10G_LANE, t, TSIZE(TC_SD10G_LANE), 832, 0, 1, 84, 60, 0,\
+	      1, 4)
 
 #define SD10G_LANE_LANE_DF_LOL_UDL               BIT(0)
 #define SD10G_LANE_LANE_DF_LOL_UDL_SET(x)\
@@ -955,8 +1054,10 @@ enum sparx5_serdes_target {
 #define SD10G_LANE_LANE_DF_SQUELCH_GET(x)\
 	FIELD_GET(SD10G_LANE_LANE_DF_SQUELCH, x)
 
-/*      SD25G_TARGET:CMU_GRP_0:CMU_09 */
-#define SD25G_LANE_CMU_09(t)      __REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 36, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_0:CMU_09 */
+#define SD25G_LANE_CMU_09(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 36, 0, 1, 4)
 
 #define SD25G_LANE_CMU_09_CFG_REFCK_TERM_EN      BIT(0)
 #define SD25G_LANE_CMU_09_CFG_REFCK_TERM_EN_SET(x)\
@@ -988,8 +1089,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_09_CFG_PLL_TP_SEL_1_0_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_09_CFG_PLL_TP_SEL_1_0, x)
 
-/*      SD25G_TARGET:CMU_GRP_0:CMU_0B */
-#define SD25G_LANE_CMU_0B(t)      __REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 44, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_0:CMU_0B */
+#define SD25G_LANE_CMU_0B(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 44, 0, 1, 4)
 
 #define SD25G_LANE_CMU_0B_CFG_FORCE_RX_FILT      BIT(0)
 #define SD25G_LANE_CMU_0B_CFG_FORCE_RX_FILT_SET(x)\
@@ -1039,8 +1142,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_0B_CFG_RST_TREE_PD_MAN_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_0B_CFG_RST_TREE_PD_MAN, x)
 
-/*      SD25G_TARGET:CMU_GRP_0:CMU_0C */
-#define SD25G_LANE_CMU_0C(t)      __REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 48, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_0:CMU_0C */
+#define SD25G_LANE_CMU_0C(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 48, 0, 1, 4)
 
 #define SD25G_LANE_CMU_0C_CFG_PLL_LOL_SET        BIT(0)
 #define SD25G_LANE_CMU_0C_CFG_PLL_LOL_SET_SET(x)\
@@ -1072,8 +1177,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_0C_CFG_VCO_DIV_MODE_1_0_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_0C_CFG_VCO_DIV_MODE_1_0, x)
 
-/*      SD25G_TARGET:CMU_GRP_0:CMU_0D */
-#define SD25G_LANE_CMU_0D(t)      __REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 52, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_0:CMU_0D */
+#define SD25G_LANE_CMU_0D(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 52, 0, 1, 4)
 
 #define SD25G_LANE_CMU_0D_CFG_CK_TREE_PD         BIT(0)
 #define SD25G_LANE_CMU_0D_CFG_CK_TREE_PD_SET(x)\
@@ -1105,8 +1212,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_0D_CFG_PRE_DIVSEL_1_0_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_0D_CFG_PRE_DIVSEL_1_0, x)
 
-/*      SD25G_TARGET:CMU_GRP_0:CMU_0E */
-#define SD25G_LANE_CMU_0E(t)      __REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 56, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_0:CMU_0E */
+#define SD25G_LANE_CMU_0E(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 56, 0, 1, 4)
 
 #define SD25G_LANE_CMU_0E_CFG_SEL_DIV_3_0        GENMASK(3, 0)
 #define SD25G_LANE_CMU_0E_CFG_SEL_DIV_3_0_SET(x)\
@@ -1120,8 +1229,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_0E_CFG_PMAA_CENTR_CK_PD_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_0E_CFG_PMAA_CENTR_CK_PD, x)
 
-/*      SD25G_TARGET:CMU_GRP_0:CMU_13 */
-#define SD25G_LANE_CMU_13(t)      __REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 76, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_0:CMU_13 */
+#define SD25G_LANE_CMU_13(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 76, 0, 1, 4)
 
 #define SD25G_LANE_CMU_13_CFG_PLL_RESERVE_3_0    GENMASK(3, 0)
 #define SD25G_LANE_CMU_13_CFG_PLL_RESERVE_3_0_SET(x)\
@@ -1135,8 +1246,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_13_CFG_JT_EN_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_13_CFG_JT_EN, x)
 
-/*      SD25G_TARGET:CMU_GRP_0:CMU_18 */
-#define SD25G_LANE_CMU_18(t)      __REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 96, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_0:CMU_18 */
+#define SD25G_LANE_CMU_18(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 96, 0, 1, 4)
 
 #define SD25G_LANE_CMU_18_R_PLL_RSTN             BIT(0)
 #define SD25G_LANE_CMU_18_R_PLL_RSTN_SET(x)\
@@ -1162,8 +1275,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_18_R_PLL_TP_SEL_1_0_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_18_R_PLL_TP_SEL_1_0, x)
 
-/*      SD25G_TARGET:CMU_GRP_0:CMU_19 */
-#define SD25G_LANE_CMU_19(t)      __REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 100, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_0:CMU_19 */
+#define SD25G_LANE_CMU_19(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 100, 0, 1, 4)
 
 #define SD25G_LANE_CMU_19_R_CK_RESETB            BIT(0)
 #define SD25G_LANE_CMU_19_R_CK_RESETB_SET(x)\
@@ -1177,8 +1292,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_19_R_PLL_DLOL_EN_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_19_R_PLL_DLOL_EN, x)
 
-/*      SD25G_TARGET:CMU_GRP_0:CMU_1A */
-#define SD25G_LANE_CMU_1A(t)      __REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 104, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_0:CMU_1A */
+#define SD25G_LANE_CMU_1A(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 0, 0, 1, 132, 104, 0, 1, 4)
 
 #define SD25G_LANE_CMU_1A_R_DWIDTHCTRL_2_0       GENMASK(2, 0)
 #define SD25G_LANE_CMU_1A_R_DWIDTHCTRL_2_0_SET(x)\
@@ -1204,8 +1321,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_1A_R_REG_MANUAL_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_1A_R_REG_MANUAL, x)
 
-/*      SD25G_TARGET:CMU_GRP_1:CMU_2A */
-#define SD25G_LANE_CMU_2A(t)      __REG(TARGET_SD25G_LANE, t, 8, 132, 0, 1, 124, 36, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_1:CMU_2A */
+#define SD25G_LANE_CMU_2A(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 132, 0, 1, 124, 36, 0, 1, 4)
 
 #define SD25G_LANE_CMU_2A_R_DBG_SEL_1_0          GENMASK(1, 0)
 #define SD25G_LANE_CMU_2A_R_DBG_SEL_1_0_SET(x)\
@@ -1225,8 +1344,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_2A_R_DBG_LOL_STATUS_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_2A_R_DBG_LOL_STATUS, x)
 
-/*      SD25G_TARGET:CMU_GRP_1:CMU_30 */
-#define SD25G_LANE_CMU_30(t)      __REG(TARGET_SD25G_LANE, t, 8, 132, 0, 1, 124, 60, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_1:CMU_30 */
+#define SD25G_LANE_CMU_30(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 132, 0, 1, 124, 60, 0, 1, 4)
 
 #define SD25G_LANE_CMU_30_R_TXFIFO_CK_DIV_PMAD_2_0 GENMASK(2, 0)
 #define SD25G_LANE_CMU_30_R_TXFIFO_CK_DIV_PMAD_2_0_SET(x)\
@@ -1240,8 +1361,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_30_R_RXFIFO_CK_DIV_PMAD_2_0_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_30_R_RXFIFO_CK_DIV_PMAD_2_0, x)
 
-/*      SD25G_TARGET:CMU_GRP_1:CMU_31 */
-#define SD25G_LANE_CMU_31(t)      __REG(TARGET_SD25G_LANE, t, 8, 132, 0, 1, 124, 64, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_1:CMU_31 */
+#define SD25G_LANE_CMU_31(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 132, 0, 1, 124, 64, 0, 1, 4)
 
 #define SD25G_LANE_CMU_31_CFG_COMMON_RESERVE_7_0 GENMASK(7, 0)
 #define SD25G_LANE_CMU_31_CFG_COMMON_RESERVE_7_0_SET(x)\
@@ -1249,8 +1372,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_31_CFG_COMMON_RESERVE_7_0_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_31_CFG_COMMON_RESERVE_7_0, x)
 
-/*      SD25G_TARGET:CMU_GRP_2:CMU_40 */
-#define SD25G_LANE_CMU_40(t)      __REG(TARGET_SD25G_LANE, t, 8, 256, 0, 1, 512, 0, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_2:CMU_40 */
+#define SD25G_LANE_CMU_40(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 256, 0, 1, 512, 0, 0, 1, 4)
 
 #define SD25G_LANE_CMU_40_L0_CFG_CKSKEW_CTRL     BIT(0)
 #define SD25G_LANE_CMU_40_L0_CFG_CKSKEW_CTRL_SET(x)\
@@ -1288,8 +1413,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_40_L0_CFG_TXCAL_RST_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_40_L0_CFG_TXCAL_RST, x)
 
-/*      SD25G_TARGET:CMU_GRP_2:CMU_45 */
-#define SD25G_LANE_CMU_45(t)      __REG(TARGET_SD25G_LANE, t, 8, 256, 0, 1, 512, 20, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_2:CMU_45 */
+#define SD25G_LANE_CMU_45(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 256, 0, 1, 512, 20, 0, 1, 4)
 
 #define SD25G_LANE_CMU_45_L0_CFG_TX_RESERVE_7_0  GENMASK(7, 0)
 #define SD25G_LANE_CMU_45_L0_CFG_TX_RESERVE_7_0_SET(x)\
@@ -1297,8 +1424,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_45_L0_CFG_TX_RESERVE_7_0_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_45_L0_CFG_TX_RESERVE_7_0, x)
 
-/*      SD25G_TARGET:CMU_GRP_2:CMU_46 */
-#define SD25G_LANE_CMU_46(t)      __REG(TARGET_SD25G_LANE, t, 8, 256, 0, 1, 512, 24, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_2:CMU_46 */
+#define SD25G_LANE_CMU_46(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 256, 0, 1, 512, 24, 0, 1, 4)
 
 #define SD25G_LANE_CMU_46_L0_CFG_TX_RESERVE_15_8 GENMASK(7, 0)
 #define SD25G_LANE_CMU_46_L0_CFG_TX_RESERVE_15_8_SET(x)\
@@ -1306,8 +1435,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_46_L0_CFG_TX_RESERVE_15_8_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_46_L0_CFG_TX_RESERVE_15_8, x)
 
-/*      SD25G_TARGET:CMU_GRP_3:CMU_C0 */
-#define SD25G_LANE_CMU_C0(t)      __REG(TARGET_SD25G_LANE, t, 8, 768, 0, 1, 252, 0, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_3:CMU_C0 */
+#define SD25G_LANE_CMU_C0(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 768, 0, 1, 252, 0, 0, 1, 4)
 
 #define SD25G_LANE_CMU_C0_READ_VCO_CTUNE_3_0     GENMASK(3, 0)
 #define SD25G_LANE_CMU_C0_READ_VCO_CTUNE_3_0_SET(x)\
@@ -1321,8 +1452,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_C0_PLL_LOL_UDL_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_C0_PLL_LOL_UDL, x)
 
-/*      SD25G_TARGET:CMU_GRP_4:CMU_FF */
-#define SD25G_LANE_CMU_FF(t)      __REG(TARGET_SD25G_LANE, t, 8, 1020, 0, 1, 4, 0, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:CMU_GRP_4:CMU_FF */
+#define SD25G_LANE_CMU_FF(t)                                                   \
+	__REG(TARGET_SD25G_LANE, t, 8, 1020, 0, 1, 4, 0, 0, 1, 4)
 
 #define SD25G_LANE_CMU_FF_REGISTER_TABLE_INDEX   GENMASK(7, 0)
 #define SD25G_LANE_CMU_FF_REGISTER_TABLE_INDEX_SET(x)\
@@ -1330,8 +1463,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_CMU_FF_REGISTER_TABLE_INDEX_GET(x)\
 	FIELD_GET(SD25G_LANE_CMU_FF_REGISTER_TABLE_INDEX, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_00 */
-#define SD25G_LANE_LANE_00(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 0, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_00 */
+#define SD25G_LANE_LANE_00(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 0, 0, 1, 4)
 
 #define SD25G_LANE_LANE_00_LN_CFG_ITX_VC_DRIVER_3_0 GENMASK(3, 0)
 #define SD25G_LANE_LANE_00_LN_CFG_ITX_VC_DRIVER_3_0_SET(x)\
@@ -1345,8 +1480,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_00_LN_CFG_ITX_IPCML_BASE_1_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_00_LN_CFG_ITX_IPCML_BASE_1_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_01 */
-#define SD25G_LANE_LANE_01(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 4, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_01 */
+#define SD25G_LANE_LANE_01(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 4, 0, 1, 4)
 
 #define SD25G_LANE_LANE_01_LN_CFG_ITX_IPDRIVER_BASE_2_0 GENMASK(2, 0)
 #define SD25G_LANE_LANE_01_LN_CFG_ITX_IPDRIVER_BASE_2_0_SET(x)\
@@ -1360,8 +1497,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_01_LN_CFG_TX_PREDIV_1_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_01_LN_CFG_TX_PREDIV_1_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_03 */
-#define SD25G_LANE_LANE_03(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 12, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_03 */
+#define SD25G_LANE_LANE_03(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 12, 0, 1, 4)
 
 #define SD25G_LANE_LANE_03_LN_CFG_TAP_DLY_4_0    GENMASK(4, 0)
 #define SD25G_LANE_LANE_03_LN_CFG_TAP_DLY_4_0_SET(x)\
@@ -1369,8 +1508,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_03_LN_CFG_TAP_DLY_4_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_03_LN_CFG_TAP_DLY_4_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_04 */
-#define SD25G_LANE_LANE_04(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 16, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_04 */
+#define SD25G_LANE_LANE_04(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 16, 0, 1, 4)
 
 #define SD25G_LANE_LANE_04_LN_CFG_TX2RX_LP_EN    BIT(0)
 #define SD25G_LANE_LANE_04_LN_CFG_TX2RX_LP_EN_SET(x)\
@@ -1408,8 +1549,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_04_LN_CFG_TAP_MAIN_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_04_LN_CFG_TAP_MAIN, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_05 */
-#define SD25G_LANE_LANE_05(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 20, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_05 */
+#define SD25G_LANE_LANE_05(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 20, 0, 1, 4)
 
 #define SD25G_LANE_LANE_05_LN_CFG_TAP_DLY2_3_0   GENMASK(3, 0)
 #define SD25G_LANE_LANE_05_LN_CFG_TAP_DLY2_3_0_SET(x)\
@@ -1423,8 +1566,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_05_LN_CFG_BW_1_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_05_LN_CFG_BW_1_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_06 */
-#define SD25G_LANE_LANE_06(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 24, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_06 */
+#define SD25G_LANE_LANE_06(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 24, 0, 1, 4)
 
 #define SD25G_LANE_LANE_06_LN_CFG_EN_MAIN        BIT(0)
 #define SD25G_LANE_LANE_06_LN_CFG_EN_MAIN_SET(x)\
@@ -1438,8 +1583,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_06_LN_CFG_TAP_ADV_3_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_06_LN_CFG_TAP_ADV_3_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_07 */
-#define SD25G_LANE_LANE_07(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 28, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_07 */
+#define SD25G_LANE_LANE_07(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 28, 0, 1, 4)
 
 #define SD25G_LANE_LANE_07_LN_CFG_EN_ADV         BIT(0)
 #define SD25G_LANE_LANE_07_LN_CFG_EN_ADV_SET(x)\
@@ -1459,8 +1606,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_07_LN_CFG_EN_DLY_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_07_LN_CFG_EN_DLY, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_09 */
-#define SD25G_LANE_LANE_09(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 36, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_09 */
+#define SD25G_LANE_LANE_09(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 36, 0, 1, 4)
 
 #define SD25G_LANE_LANE_09_LN_CFG_TXCAL_VALID_SEL_3_0 GENMASK(3, 0)
 #define SD25G_LANE_LANE_09_LN_CFG_TXCAL_VALID_SEL_3_0_SET(x)\
@@ -1468,8 +1617,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_09_LN_CFG_TXCAL_VALID_SEL_3_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_09_LN_CFG_TXCAL_VALID_SEL_3_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_0A */
-#define SD25G_LANE_LANE_0A(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 40, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_0A */
+#define SD25G_LANE_LANE_0A(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 40, 0, 1, 4)
 
 #define SD25G_LANE_LANE_0A_LN_CFG_TXCAL_SHIFT_CODE_5_0 GENMASK(5, 0)
 #define SD25G_LANE_LANE_0A_LN_CFG_TXCAL_SHIFT_CODE_5_0_SET(x)\
@@ -1477,8 +1628,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_0A_LN_CFG_TXCAL_SHIFT_CODE_5_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_0A_LN_CFG_TXCAL_SHIFT_CODE_5_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_0B */
-#define SD25G_LANE_LANE_0B(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 44, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_0B */
+#define SD25G_LANE_LANE_0B(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 44, 0, 1, 4)
 
 #define SD25G_LANE_LANE_0B_LN_CFG_TXCAL_MAN_EN   BIT(0)
 #define SD25G_LANE_LANE_0B_LN_CFG_TXCAL_MAN_EN_SET(x)\
@@ -1498,8 +1651,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_0B_LN_CFG_QUAD_MAN_1_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_0B_LN_CFG_QUAD_MAN_1_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_0C */
-#define SD25G_LANE_LANE_0C(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 48, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_0C */
+#define SD25G_LANE_LANE_0C(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 48, 0, 1, 4)
 
 #define SD25G_LANE_LANE_0C_LN_CFG_PMA_TX_CK_BITWIDTH_2_0 GENMASK(2, 0)
 #define SD25G_LANE_LANE_0C_LN_CFG_PMA_TX_CK_BITWIDTH_2_0_SET(x)\
@@ -1519,8 +1674,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_0C_LN_CFG_RXTERM_PD_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_0C_LN_CFG_RXTERM_PD, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_0D */
-#define SD25G_LANE_LANE_0D(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 52, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_0D */
+#define SD25G_LANE_LANE_0D(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 52, 0, 1, 4)
 
 #define SD25G_LANE_LANE_0D_LN_CFG_RXTERM_2_0     GENMASK(2, 0)
 #define SD25G_LANE_LANE_0D_LN_CFG_RXTERM_2_0_SET(x)\
@@ -1552,8 +1709,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_0D_LN_CFG_DFECK_EN_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_0D_LN_CFG_DFECK_EN, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_0E */
-#define SD25G_LANE_LANE_0E(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 56, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_0E */
+#define SD25G_LANE_LANE_0E(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 56, 0, 1, 4)
 
 #define SD25G_LANE_LANE_0E_LN_CFG_ISCAN_EN       BIT(0)
 #define SD25G_LANE_LANE_0E_LN_CFG_ISCAN_EN_SET(x)\
@@ -1579,8 +1738,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_0E_LN_CFG_DFEDIG_M_2_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_0E_LN_CFG_DFEDIG_M_2_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_0F */
-#define SD25G_LANE_LANE_0F(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 60, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_0F */
+#define SD25G_LANE_LANE_0F(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 60, 0, 1, 4)
 
 #define SD25G_LANE_LANE_0F_LN_CFG_DFETAP_EN_5_1  GENMASK(4, 0)
 #define SD25G_LANE_LANE_0F_LN_CFG_DFETAP_EN_5_1_SET(x)\
@@ -1588,8 +1749,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_0F_LN_CFG_DFETAP_EN_5_1_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_0F_LN_CFG_DFETAP_EN_5_1, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_18 */
-#define SD25G_LANE_LANE_18(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 96, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_18 */
+#define SD25G_LANE_LANE_18(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 96, 0, 1, 4)
 
 #define SD25G_LANE_LANE_18_LN_CFG_CDRCK_EN       BIT(0)
 #define SD25G_LANE_LANE_18_LN_CFG_CDRCK_EN_SET(x)\
@@ -1621,8 +1784,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_18_LN_CFG_RXDIV_SEL_2_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_18_LN_CFG_RXDIV_SEL_2_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_19 */
-#define SD25G_LANE_LANE_19(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 100, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_19 */
+#define SD25G_LANE_LANE_19(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 100, 0, 1, 4)
 
 #define SD25G_LANE_LANE_19_LN_CFG_DCDR_PD        BIT(0)
 #define SD25G_LANE_LANE_19_LN_CFG_DCDR_PD_SET(x)\
@@ -1672,8 +1837,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_19_LN_CFG_PD_CTLE_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_19_LN_CFG_PD_CTLE, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_1A */
-#define SD25G_LANE_LANE_1A(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 104, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_1A */
+#define SD25G_LANE_LANE_1A(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 104, 0, 1, 4)
 
 #define SD25G_LANE_LANE_1A_LN_CFG_CTLE_TP_EN     BIT(0)
 #define SD25G_LANE_LANE_1A_LN_CFG_CTLE_TP_EN_SET(x)\
@@ -1687,8 +1854,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_1A_LN_CFG_CDR_KF_2_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_1A_LN_CFG_CDR_KF_2_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_1B */
-#define SD25G_LANE_LANE_1B(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 108, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_1B */
+#define SD25G_LANE_LANE_1B(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 108, 0, 1, 4)
 
 #define SD25G_LANE_LANE_1B_LN_CFG_CDR_M_7_0      GENMASK(7, 0)
 #define SD25G_LANE_LANE_1B_LN_CFG_CDR_M_7_0_SET(x)\
@@ -1696,8 +1865,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_1B_LN_CFG_CDR_M_7_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_1B_LN_CFG_CDR_M_7_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_1C */
-#define SD25G_LANE_LANE_1C(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 112, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_1C */
+#define SD25G_LANE_LANE_1C(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 112, 0, 1, 4)
 
 #define SD25G_LANE_LANE_1C_LN_CFG_CDR_RSTN       BIT(0)
 #define SD25G_LANE_LANE_1C_LN_CFG_CDR_RSTN_SET(x)\
@@ -1723,8 +1894,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_1C_LN_CFG_EQC_FORCE_3_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_1C_LN_CFG_EQC_FORCE_3_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_1D */
-#define SD25G_LANE_LANE_1D(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 116, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_1D */
+#define SD25G_LANE_LANE_1D(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 116, 0, 1, 4)
 
 #define SD25G_LANE_LANE_1D_LN_CFG_ISCAN_EXT_OVR  BIT(0)
 #define SD25G_LANE_LANE_1D_LN_CFG_ISCAN_EXT_OVR_SET(x)\
@@ -1774,8 +1947,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_1D_LN_CFG_PI_HOLD_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_1D_LN_CFG_PI_HOLD, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_1E */
-#define SD25G_LANE_LANE_1E(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 120, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_1E */
+#define SD25G_LANE_LANE_1E(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 120, 0, 1, 4)
 
 #define SD25G_LANE_LANE_1E_LN_CFG_PI_STEPS_1_0   GENMASK(1, 0)
 #define SD25G_LANE_LANE_1E_LN_CFG_PI_STEPS_1_0_SET(x)\
@@ -1807,8 +1982,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_1E_LN_CFG_PMAD_CK_PD_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_1E_LN_CFG_PMAD_CK_PD, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_21 */
-#define SD25G_LANE_LANE_21(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 132, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_21 */
+#define SD25G_LANE_LANE_21(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 132, 0, 1, 4)
 
 #define SD25G_LANE_LANE_21_LN_CFG_VGA_CTRL_BYP_4_0 GENMASK(4, 0)
 #define SD25G_LANE_LANE_21_LN_CFG_VGA_CTRL_BYP_4_0_SET(x)\
@@ -1816,8 +1993,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_21_LN_CFG_VGA_CTRL_BYP_4_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_21_LN_CFG_VGA_CTRL_BYP_4_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_22 */
-#define SD25G_LANE_LANE_22(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 136, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_22 */
+#define SD25G_LANE_LANE_22(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 136, 0, 1, 4)
 
 #define SD25G_LANE_LANE_22_LN_CFG_EQR_FORCE_3_0  GENMASK(3, 0)
 #define SD25G_LANE_LANE_22_LN_CFG_EQR_FORCE_3_0_SET(x)\
@@ -1825,8 +2004,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_22_LN_CFG_EQR_FORCE_3_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_22_LN_CFG_EQR_FORCE_3_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_25 */
-#define SD25G_LANE_LANE_25(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 148, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_25 */
+#define SD25G_LANE_LANE_25(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 148, 0, 1, 4)
 
 #define SD25G_LANE_LANE_25_LN_CFG_INIT_POS_ISCAN_6_0 GENMASK(6, 0)
 #define SD25G_LANE_LANE_25_LN_CFG_INIT_POS_ISCAN_6_0_SET(x)\
@@ -1834,8 +2015,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_25_LN_CFG_INIT_POS_ISCAN_6_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_25_LN_CFG_INIT_POS_ISCAN_6_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_26 */
-#define SD25G_LANE_LANE_26(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 152, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_26 */
+#define SD25G_LANE_LANE_26(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 152, 0, 1, 4)
 
 #define SD25G_LANE_LANE_26_LN_CFG_INIT_POS_IPI_6_0 GENMASK(6, 0)
 #define SD25G_LANE_LANE_26_LN_CFG_INIT_POS_IPI_6_0_SET(x)\
@@ -1843,8 +2026,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_26_LN_CFG_INIT_POS_IPI_6_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_26_LN_CFG_INIT_POS_IPI_6_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_28 */
-#define SD25G_LANE_LANE_28(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 160, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_28 */
+#define SD25G_LANE_LANE_28(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 160, 0, 1, 4)
 
 #define SD25G_LANE_LANE_28_LN_CFG_ISCAN_MODE_EN  BIT(0)
 #define SD25G_LANE_LANE_28_LN_CFG_ISCAN_MODE_EN_SET(x)\
@@ -1870,8 +2055,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_28_LN_CFG_RX_SUBRATE_2_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_28_LN_CFG_RX_SUBRATE_2_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_2B */
-#define SD25G_LANE_LANE_2B(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 172, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_2B */
+#define SD25G_LANE_LANE_2B(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 172, 0, 1, 4)
 
 #define SD25G_LANE_LANE_2B_LN_CFG_PI_BW_3_0      GENMASK(3, 0)
 #define SD25G_LANE_LANE_2B_LN_CFG_PI_BW_3_0_SET(x)\
@@ -1891,8 +2078,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_2B_LN_CFG_RSTN_TXDUPU_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_2B_LN_CFG_RSTN_TXDUPU, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_2C */
-#define SD25G_LANE_LANE_2C(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 176, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_2C */
+#define SD25G_LANE_LANE_2C(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 176, 0, 1, 4)
 
 #define SD25G_LANE_LANE_2C_LN_CFG_TX_SUBRATE_2_0 GENMASK(2, 0)
 #define SD25G_LANE_LANE_2C_LN_CFG_TX_SUBRATE_2_0_SET(x)\
@@ -1906,8 +2095,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_2C_LN_CFG_DIS_2NDORDER_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_2C_LN_CFG_DIS_2NDORDER, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_2D */
-#define SD25G_LANE_LANE_2D(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 180, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_2D */
+#define SD25G_LANE_LANE_2D(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 180, 0, 1, 4)
 
 #define SD25G_LANE_LANE_2D_LN_CFG_ALOS_THR_2_0   GENMASK(2, 0)
 #define SD25G_LANE_LANE_2D_LN_CFG_ALOS_THR_2_0_SET(x)\
@@ -1921,8 +2112,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_2D_LN_CFG_SAT_CNTSEL_2_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_2D_LN_CFG_SAT_CNTSEL_2_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_2E */
-#define SD25G_LANE_LANE_2E(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 184, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_2E */
+#define SD25G_LANE_LANE_2E(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 184, 0, 1, 4)
 
 #define SD25G_LANE_LANE_2E_LN_CFG_EN_FAST_ISCAN  BIT(0)
 #define SD25G_LANE_LANE_2E_LN_CFG_EN_FAST_ISCAN_SET(x)\
@@ -1972,8 +2165,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_2E_LN_CFG_CTLE_RSTN_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_2E_LN_CFG_CTLE_RSTN, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_40 */
-#define SD25G_LANE_LANE_40(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 256, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_40 */
+#define SD25G_LANE_LANE_40(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 256, 0, 1, 4)
 
 #define SD25G_LANE_LANE_40_LN_R_TX_BIT_REVERSE   BIT(0)
 #define SD25G_LANE_LANE_40_LN_R_TX_BIT_REVERSE_SET(x)\
@@ -2017,8 +2212,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_40_LN_R_CTLE_RSTN_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_40_LN_R_CTLE_RSTN, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_42 */
-#define SD25G_LANE_LANE_42(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 264, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_42 */
+#define SD25G_LANE_LANE_42(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 264, 0, 1, 4)
 
 #define SD25G_LANE_LANE_42_LN_CFG_TX_RESERVE_7_0 GENMASK(7, 0)
 #define SD25G_LANE_LANE_42_LN_CFG_TX_RESERVE_7_0_SET(x)\
@@ -2026,8 +2223,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_42_LN_CFG_TX_RESERVE_7_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_42_LN_CFG_TX_RESERVE_7_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_43 */
-#define SD25G_LANE_LANE_43(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 268, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_43 */
+#define SD25G_LANE_LANE_43(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 268, 0, 1, 4)
 
 #define SD25G_LANE_LANE_43_LN_CFG_TX_RESERVE_15_8 GENMASK(7, 0)
 #define SD25G_LANE_LANE_43_LN_CFG_TX_RESERVE_15_8_SET(x)\
@@ -2035,8 +2234,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_43_LN_CFG_TX_RESERVE_15_8_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_43_LN_CFG_TX_RESERVE_15_8, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_44 */
-#define SD25G_LANE_LANE_44(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 272, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_44 */
+#define SD25G_LANE_LANE_44(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 272, 0, 1, 4)
 
 #define SD25G_LANE_LANE_44_LN_CFG_RX_RESERVE_7_0 GENMASK(7, 0)
 #define SD25G_LANE_LANE_44_LN_CFG_RX_RESERVE_7_0_SET(x)\
@@ -2044,8 +2245,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_44_LN_CFG_RX_RESERVE_7_0_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_44_LN_CFG_RX_RESERVE_7_0, x)
 
-/*      SD25G_TARGET:LANE_GRP_0:LANE_45 */
-#define SD25G_LANE_LANE_45(t)     __REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 276, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_0:LANE_45 */
+#define SD25G_LANE_LANE_45(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1024, 0, 1, 768, 276, 0, 1, 4)
 
 #define SD25G_LANE_LANE_45_LN_CFG_RX_RESERVE_15_8 GENMASK(7, 0)
 #define SD25G_LANE_LANE_45_LN_CFG_RX_RESERVE_15_8_SET(x)\
@@ -2053,8 +2256,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_45_LN_CFG_RX_RESERVE_15_8_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_45_LN_CFG_RX_RESERVE_15_8, x)
 
-/*      SD25G_TARGET:LANE_GRP_1:LANE_DE */
-#define SD25G_LANE_LANE_DE(t)     __REG(TARGET_SD25G_LANE, t, 8, 1792, 0, 1, 128, 120, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_TARGET:LANE_GRP_1:LANE_DE */
+#define SD25G_LANE_LANE_DE(t)                                                  \
+	__REG(TARGET_SD25G_LANE, t, 8, 1792, 0, 1, 128, 120, 0, 1, 4)
 
 #define SD25G_LANE_LANE_DE_LN_LOL_UDL            BIT(0)
 #define SD25G_LANE_LANE_DE_LN_LOL_UDL_SET(x)\
@@ -2080,8 +2285,10 @@ enum sparx5_serdes_target {
 #define SD25G_LANE_LANE_DE_LN_PMA_RXEI_GET(x)\
 	FIELD_GET(SD25G_LANE_LANE_DE_LN_PMA_RXEI, x)
 
-/*      SD10G_LANE_TARGET:LANE_GRP_8:LANE_DF */
-#define SD6G_LANE_LANE_DF(t)      __REG(TARGET_SD6G_LANE, t, 13, 832, 0, 1, 84, 60, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD10G_LANE_TARGET:LANE_GRP_8:LANE_DF */
+#define SD6G_LANE_LANE_DF(t)                                                   \
+	__REG(TARGET_SD6G_LANE, t, 13, 832, 0, 1, 84, 60, 0, 1, 4)
 
 #define SD6G_LANE_LANE_DF_LOL_UDL                BIT(0)
 #define SD6G_LANE_LANE_DF_LOL_UDL_SET(x)\
@@ -2107,8 +2314,9 @@ enum sparx5_serdes_target {
 #define SD6G_LANE_LANE_DF_SQUELCH_GET(x)\
 	FIELD_GET(SD6G_LANE_LANE_DF_SQUELCH, x)
 
-/*      SD10G_CMU_TARGET:CMU_GRP_0:CMU_00 */
-#define SD_CMU_CMU_00(t)          __REG(TARGET_SD_CMU, t, 14, 0, 0, 1, 20, 0, 0, 1, 4)
+/* SD10G_CMU_TARGET:CMU_GRP_0:CMU_00 */
+#define SD_CMU_CMU_00(t)                                                       \
+	__REG(TARGET_SD_CMU, t, TSIZE(TC_SD_CMU), 0, 0, 1, 20, 0, 0, 1, 4)
 
 #define SD_CMU_CMU_00_R_HWT_SIMULATION_MODE      BIT(0)
 #define SD_CMU_CMU_00_R_HWT_SIMULATION_MODE_SET(x)\
@@ -2134,8 +2342,9 @@ enum sparx5_serdes_target {
 #define SD_CMU_CMU_00_CFG_PLL_TP_SEL_1_0_GET(x)\
 	FIELD_GET(SD_CMU_CMU_00_CFG_PLL_TP_SEL_1_0, x)
 
-/*      SD10G_CMU_TARGET:CMU_GRP_1:CMU_05 */
-#define SD_CMU_CMU_05(t)          __REG(TARGET_SD_CMU, t, 14, 20, 0, 1, 72, 0, 0, 1, 4)
+/* SD10G_CMU_TARGET:CMU_GRP_1:CMU_05 */
+#define SD_CMU_CMU_05(t)                                                       \
+	__REG(TARGET_SD_CMU, t, TSIZE(TC_SD_CMU), 20, 0, 1, 72, 0, 0, 1, 4)
 
 #define SD_CMU_CMU_05_CFG_REFCK_TERM_EN          BIT(0)
 #define SD_CMU_CMU_05_CFG_REFCK_TERM_EN_SET(x)\
@@ -2149,9 +2358,9 @@ enum sparx5_serdes_target {
 #define SD_CMU_CMU_05_CFG_BIAS_TP_SEL_1_0_GET(x)\
 	FIELD_GET(SD_CMU_CMU_05_CFG_BIAS_TP_SEL_1_0, x)
 
-/*      SD10G_CMU_TARGET:CMU_GRP_1:CMU_06 */
-#define SD_CMU_CMU_06(t) \
-	__REG(TARGET_SD_CMU, t, 14, 20, 0, 1, 72, 4, 0, 1, 4)
+/* SD10G_CMU_TARGET:CMU_GRP_1:CMU_06 */
+#define SD_CMU_CMU_06(t)                                                       \
+	__REG(TARGET_SD_CMU, t, TSIZE(TC_SD_CMU), 20, 0, 1, 72, 4, 0, 1, 4)
 
 #define SD_CMU_CMU_06_CFG_DISLOS                 BIT(0)
 #define SD_CMU_CMU_06_CFG_DISLOS_SET(x)\
@@ -2201,9 +2410,9 @@ enum sparx5_serdes_target {
 #define SD_CMU_CMU_06_CFG_VCO_CAL_BYP_GET(x)\
 	FIELD_GET(SD_CMU_CMU_06_CFG_VCO_CAL_BYP, x)
 
-/*      SD10G_CMU_TARGET:CMU_GRP_1:CMU_08 */
-#define SD_CMU_CMU_08(t) \
-	__REG(TARGET_SD_CMU, t, 14, 20, 0, 1, 72, 12, 0, 1, 4)
+/* SD10G_CMU_TARGET:CMU_GRP_1:CMU_08 */
+#define SD_CMU_CMU_08(t)                                                       \
+	__REG(TARGET_SD_CMU, t, TSIZE(TC_SD_CMU), 20, 0, 1, 72, 12, 0, 1, 4)
 
 #define SD_CMU_CMU_08_CFG_VFILT2PAD              BIT(0)
 #define SD_CMU_CMU_08_CFG_VFILT2PAD_SET(x)\
@@ -2235,8 +2444,9 @@ enum sparx5_serdes_target {
 #define SD_CMU_CMU_08_CFG_RST_TREE_PD_MAN_EN_GET(x)\
 	FIELD_GET(SD_CMU_CMU_08_CFG_RST_TREE_PD_MAN_EN, x)
 
-/*      SD10G_CMU_TARGET:CMU_GRP_1:CMU_09 */
-#define SD_CMU_CMU_09(t)          __REG(TARGET_SD_CMU, t, 14, 20, 0, 1, 72, 16, 0, 1, 4)
+/* SD10G_CMU_TARGET:CMU_GRP_1:CMU_09 */
+#define SD_CMU_CMU_09(t)                                                       \
+	__REG(TARGET_SD_CMU, t, TSIZE(TC_SD_CMU), 20, 0, 1, 72, 16, 0, 1, 4)
 
 #define SD_CMU_CMU_09_CFG_EN_TX_CK_UP            BIT(0)
 #define SD_CMU_CMU_09_CFG_EN_TX_CK_UP_SET(x)\
@@ -2262,8 +2472,9 @@ enum sparx5_serdes_target {
 #define SD_CMU_CMU_09_CFG_SW_10G_GET(x)\
 	FIELD_GET(SD_CMU_CMU_09_CFG_SW_10G, x)
 
-/*      SD10G_CMU_TARGET:CMU_GRP_1:CMU_0D */
-#define SD_CMU_CMU_0D(t)          __REG(TARGET_SD_CMU, t, 14, 20, 0, 1, 72, 32, 0, 1, 4)
+/* SD10G_CMU_TARGET:CMU_GRP_1:CMU_0D */
+#define SD_CMU_CMU_0D(t)                                                       \
+	__REG(TARGET_SD_CMU, t, TSIZE(TC_SD_CMU), 20, 0, 1, 72, 32, 0, 1, 4)
 
 #define SD_CMU_CMU_0D_CFG_PD_DIV64               BIT(0)
 #define SD_CMU_CMU_0D_CFG_PD_DIV64_SET(x)\
@@ -2295,8 +2506,9 @@ enum sparx5_serdes_target {
 #define SD_CMU_CMU_0D_CFG_REFCK_PD_GET(x)\
 	FIELD_GET(SD_CMU_CMU_0D_CFG_REFCK_PD, x)
 
-/*      SD10G_CMU_TARGET:CMU_GRP_3:CMU_1B */
-#define SD_CMU_CMU_1B(t)          __REG(TARGET_SD_CMU, t, 14, 104, 0, 1, 20, 4, 0, 1, 4)
+/* SD10G_CMU_TARGET:CMU_GRP_3:CMU_1B */
+#define SD_CMU_CMU_1B(t)                                                       \
+	__REG(TARGET_SD_CMU, t, TSIZE(TC_SD_CMU), 104, 0, 1, 20, 4, 0, 1, 4)
 
 #define SD_CMU_CMU_1B_CFG_RESERVE_7_0            GENMASK(7, 0)
 #define SD_CMU_CMU_1B_CFG_RESERVE_7_0_SET(x)\
@@ -2304,8 +2516,9 @@ enum sparx5_serdes_target {
 #define SD_CMU_CMU_1B_CFG_RESERVE_7_0_GET(x)\
 	FIELD_GET(SD_CMU_CMU_1B_CFG_RESERVE_7_0, x)
 
-/*      SD10G_CMU_TARGET:CMU_GRP_4:CMU_1F */
-#define SD_CMU_CMU_1F(t)          __REG(TARGET_SD_CMU, t, 14, 124, 0, 1, 68, 0, 0, 1, 4)
+/* SD10G_CMU_TARGET:CMU_GRP_4:CMU_1F */
+#define SD_CMU_CMU_1F(t)                                                       \
+	__REG(TARGET_SD_CMU, t, TSIZE(TC_SD_CMU), 124, 0, 1, 68, 0, 0, 1, 4)
 
 #define SD_CMU_CMU_1F_CFG_BIAS_DN_EN             BIT(0)
 #define SD_CMU_CMU_1F_CFG_BIAS_DN_EN_SET(x)\
@@ -2331,8 +2544,9 @@ enum sparx5_serdes_target {
 #define SD_CMU_CMU_1F_CFG_VTUNE_SEL_GET(x)\
 	FIELD_GET(SD_CMU_CMU_1F_CFG_VTUNE_SEL, x)
 
-/*      SD10G_CMU_TARGET:CMU_GRP_5:CMU_30 */
-#define SD_CMU_CMU_30(t)          __REG(TARGET_SD_CMU, t, 14, 192, 0, 1, 72, 0, 0, 1, 4)
+/* SD10G_CMU_TARGET:CMU_GRP_5:CMU_30 */
+#define SD_CMU_CMU_30(t)                                                       \
+	__REG(TARGET_SD_CMU, t, TSIZE(TC_SD_CMU), 192, 0, 1, 72, 0, 0, 1, 4)
 
 #define SD_CMU_CMU_30_R_PLL_DLOL_EN              BIT(0)
 #define SD_CMU_CMU_30_R_PLL_DLOL_EN_SET(x)\
@@ -2340,8 +2554,9 @@ enum sparx5_serdes_target {
 #define SD_CMU_CMU_30_R_PLL_DLOL_EN_GET(x)\
 	FIELD_GET(SD_CMU_CMU_30_R_PLL_DLOL_EN, x)
 
-/*      SD10G_CMU_TARGET:CMU_GRP_6:CMU_44 */
-#define SD_CMU_CMU_44(t)          __REG(TARGET_SD_CMU, t, 14, 264, 0, 1, 632, 8, 0, 1, 4)
+/* SD10G_CMU_TARGET:CMU_GRP_6:CMU_44 */
+#define SD_CMU_CMU_44(t)                                                       \
+	__REG(TARGET_SD_CMU, t, TSIZE(TC_SD_CMU), 264, 0, 1, 632, 8, 0, 1, 4)
 
 #define SD_CMU_CMU_44_R_PLL_RSTN                 BIT(0)
 #define SD_CMU_CMU_44_R_PLL_RSTN_SET(x)\
@@ -2355,8 +2570,9 @@ enum sparx5_serdes_target {
 #define SD_CMU_CMU_44_R_CK_RESETB_GET(x)\
 	FIELD_GET(SD_CMU_CMU_44_R_CK_RESETB, x)
 
-/*      SD10G_CMU_TARGET:CMU_GRP_6:CMU_45 */
-#define SD_CMU_CMU_45(t)          __REG(TARGET_SD_CMU, t, 14, 264, 0, 1, 632, 12, 0, 1, 4)
+/* SD10G_CMU_TARGET:CMU_GRP_6:CMU_45 */
+#define SD_CMU_CMU_45(t)                                                       \
+	__REG(TARGET_SD_CMU, t, TSIZE(TC_SD_CMU), 264, 0, 1, 632, 12, 0, 1, 4)
 
 #define SD_CMU_CMU_45_R_EN_RATECHG_CTRL          BIT(0)
 #define SD_CMU_CMU_45_R_EN_RATECHG_CTRL_SET(x)\
@@ -2406,8 +2622,9 @@ enum sparx5_serdes_target {
 #define SD_CMU_CMU_45_R_AUTO_RST_TREE_PD_MAN_GET(x)\
 	FIELD_GET(SD_CMU_CMU_45_R_AUTO_RST_TREE_PD_MAN, x)
 
-/*      SD10G_CMU_TARGET:CMU_GRP_6:CMU_47 */
-#define SD_CMU_CMU_47(t)          __REG(TARGET_SD_CMU, t, 14, 264, 0, 1, 632, 20, 0, 1, 4)
+/* SD10G_CMU_TARGET:CMU_GRP_6:CMU_47 */
+#define SD_CMU_CMU_47(t)                                                       \
+	__REG(TARGET_SD_CMU, t, TSIZE(TC_SD_CMU), 264, 0, 1, 632, 20, 0, 1, 4)
 
 #define SD_CMU_CMU_47_R_PCS2PMA_PHYMODE_4_0      GENMASK(4, 0)
 #define SD_CMU_CMU_47_R_PCS2PMA_PHYMODE_4_0_SET(x)\
@@ -2415,8 +2632,9 @@ enum sparx5_serdes_target {
 #define SD_CMU_CMU_47_R_PCS2PMA_PHYMODE_4_0_GET(x)\
 	FIELD_GET(SD_CMU_CMU_47_R_PCS2PMA_PHYMODE_4_0, x)
 
-/*      SD10G_CMU_TARGET:CMU_GRP_7:CMU_E0 */
-#define SD_CMU_CMU_E0(t)          __REG(TARGET_SD_CMU, t, 14, 896, 0, 1, 8, 0, 0, 1, 4)
+/* SD10G_CMU_TARGET:CMU_GRP_7:CMU_E0 */
+#define SD_CMU_CMU_E0(t)                                                       \
+	__REG(TARGET_SD_CMU, t, TSIZE(TC_SD_CMU), 896, 0, 1, 8, 0, 0, 1, 4)
 
 #define SD_CMU_CMU_E0_READ_VCO_CTUNE_3_0         GENMASK(3, 0)
 #define SD_CMU_CMU_E0_READ_VCO_CTUNE_3_0_SET(x)\
@@ -2430,8 +2648,10 @@ enum sparx5_serdes_target {
 #define SD_CMU_CMU_E0_PLL_LOL_UDL_GET(x)\
 	FIELD_GET(SD_CMU_CMU_E0_PLL_LOL_UDL, x)
 
-/*      SD_CMU_TARGET:SD_CMU_CFG:SD_CMU_CFG */
-#define SD_CMU_CFG_SD_CMU_CFG(t)  __REG(TARGET_SD_CMU_CFG, t, 14, 0, 0, 1, 8, 0, 0, 1, 4)
+/* SD_CMU_TARGET:SD_CMU_CFG:SD_CMU_CFG */
+#define SD_CMU_CFG_SD_CMU_CFG(t)                                               \
+	__REG(TARGET_SD_CMU_CFG, t, TSIZE(TC_SD_CMU_CFG), 0, 0, 1, 8, 0, 0, 1, \
+	      4)
 
 #define SD_CMU_CFG_SD_CMU_CFG_CMU_RST            BIT(0)
 #define SD_CMU_CFG_SD_CMU_CFG_CMU_RST_SET(x)\
@@ -2445,8 +2665,9 @@ enum sparx5_serdes_target {
 #define SD_CMU_CFG_SD_CMU_CFG_EXT_CFG_RST_GET(x)\
 	FIELD_GET(SD_CMU_CFG_SD_CMU_CFG_EXT_CFG_RST, x)
 
-/*      SD_LANE_TARGET:SD_RESET:SD_SER_RST */
-#define SD_LANE_SD_SER_RST(t)     __REG(TARGET_SD_LANE, t, 25, 0, 0, 1, 8, 0, 0, 1, 4)
+/* SD_LANE_TARGET:SD_RESET:SD_SER_RST */
+#define SD_LANE_SD_SER_RST(t)                                                  \
+	__REG(TARGET_SD_LANE, t, TSIZE(TC_SD_LANE), 0, 0, 1, 8, 0, 0, 1, 4)
 
 #define SD_LANE_SD_SER_RST_SER_RST               BIT(0)
 #define SD_LANE_SD_SER_RST_SER_RST_SET(x)\
@@ -2454,8 +2675,9 @@ enum sparx5_serdes_target {
 #define SD_LANE_SD_SER_RST_SER_RST_GET(x)\
 	FIELD_GET(SD_LANE_SD_SER_RST_SER_RST, x)
 
-/*      SD_LANE_TARGET:SD_RESET:SD_DES_RST */
-#define SD_LANE_SD_DES_RST(t)     __REG(TARGET_SD_LANE, t, 25, 0, 0, 1, 8, 4, 0, 1, 4)
+/* SD_LANE_TARGET:SD_RESET:SD_DES_RST */
+#define SD_LANE_SD_DES_RST(t)                                                  \
+	__REG(TARGET_SD_LANE, t, TSIZE(TC_SD_LANE), 0, 0, 1, 8, 4, 0, 1, 4)
 
 #define SD_LANE_SD_DES_RST_DES_RST               BIT(0)
 #define SD_LANE_SD_DES_RST_DES_RST_SET(x)\
@@ -2463,8 +2685,9 @@ enum sparx5_serdes_target {
 #define SD_LANE_SD_DES_RST_DES_RST_GET(x)\
 	FIELD_GET(SD_LANE_SD_DES_RST_DES_RST, x)
 
-/*      SD_LANE_TARGET:SD_LANE_CFG_STAT:SD_LANE_CFG */
-#define SD_LANE_SD_LANE_CFG(t)    __REG(TARGET_SD_LANE, t, 25, 8, 0, 1, 8, 0, 0, 1, 4)
+/* SD_LANE_TARGET:SD_LANE_CFG_STAT:SD_LANE_CFG */
+#define SD_LANE_SD_LANE_CFG(t)                                                 \
+	__REG(TARGET_SD_LANE, t, TSIZE(TC_SD_LANE), 8, 0, 1, 8, 0, 0, 1, 4)
 
 #define SD_LANE_SD_LANE_CFG_MACRO_RST            BIT(0)
 #define SD_LANE_SD_LANE_CFG_MACRO_RST_SET(x)\
@@ -2508,8 +2731,9 @@ enum sparx5_serdes_target {
 #define SD_LANE_SD_LANE_CFG_LANE_RX_RST_GET(x)\
 	FIELD_GET(SD_LANE_SD_LANE_CFG_LANE_RX_RST, x)
 
-/*      SD_LANE_TARGET:SD_LANE_CFG_STAT:SD_LANE_STAT */
-#define SD_LANE_SD_LANE_STAT(t)   __REG(TARGET_SD_LANE, t, 25, 8, 0, 1, 8, 4, 0, 1, 4)
+/* SD_LANE_TARGET:SD_LANE_CFG_STAT:SD_LANE_STAT */
+#define SD_LANE_SD_LANE_STAT(t)                                                \
+	__REG(TARGET_SD_LANE, t, TSIZE(TC_SD_LANE), 8, 0, 1, 8, 4, 0, 1, 4)
 
 #define SD_LANE_SD_LANE_STAT_PMA_RST_DONE        BIT(0)
 #define SD_LANE_SD_LANE_STAT_PMA_RST_DONE_SET(x)\
@@ -2529,9 +2753,9 @@ enum sparx5_serdes_target {
 #define SD_LANE_SD_LANE_STAT_DBG_OBS_GET(x)\
 	FIELD_GET(SD_LANE_SD_LANE_STAT_DBG_OBS, x)
 
-/*      SD_LANE_TARGET:SD_PWR_CFG:QUIET_MODE_6G */
-#define SD_LANE_QUIET_MODE_6G(t) \
-	__REG(TARGET_SD_LANE, t, 25, 24, 0, 1, 8, 4, 0, 1, 4)
+/* SD_LANE_TARGET:SD_PWR_CFG:QUIET_MODE_6G */
+#define SD_LANE_QUIET_MODE_6G(t)                                               \
+	__REG(TARGET_SD_LANE, t, TSIZE(TC_SD_LANE), 24, 0, 1, 8, 4, 0, 1, 4)
 
 #define SD_LANE_QUIET_MODE_6G_QUIET_MODE         GENMASK(24, 0)
 #define SD_LANE_QUIET_MODE_6G_QUIET_MODE_SET(x)\
@@ -2539,8 +2763,9 @@ enum sparx5_serdes_target {
 #define SD_LANE_QUIET_MODE_6G_QUIET_MODE_GET(x)\
 	FIELD_GET(SD_LANE_QUIET_MODE_6G_QUIET_MODE, x)
 
-/*      SD_LANE_TARGET:CFG_STAT_FX100:MISC */
-#define SD_LANE_MISC(t)           __REG(TARGET_SD_LANE, t, 25, 56, 0, 1, 56, 0, 0, 1, 4)
+/* SD_LANE_TARGET:CFG_STAT_FX100:MISC */
+#define SD_LANE_MISC(t)                                                        \
+	__REG(TARGET_SD_LANE, t, TSIZE(TC_SD_LANE), 56, 0, 1, 56, 0, 0, 1, 4)
 
 #define SD_LANE_MISC_SD_125_RST_DIS              BIT(0)
 #define SD_LANE_MISC_SD_125_RST_DIS_SET(x)\
@@ -2560,14 +2785,16 @@ enum sparx5_serdes_target {
 #define SD_LANE_MISC_MUX_ENA_GET(x)\
 	FIELD_GET(SD_LANE_MISC_MUX_ENA, x)
 
+/* SPARX5 ONLY */
 #define SD_LANE_MISC_CORE_CLK_FREQ               GENMASK(5, 4)
 #define SD_LANE_MISC_CORE_CLK_FREQ_SET(x)\
 	FIELD_PREP(SD_LANE_MISC_CORE_CLK_FREQ, x)
 #define SD_LANE_MISC_CORE_CLK_FREQ_GET(x)\
 	FIELD_GET(SD_LANE_MISC_CORE_CLK_FREQ, x)
 
-/*      SD_LANE_TARGET:CFG_STAT_FX100:M_STAT_MISC */
-#define SD_LANE_M_STAT_MISC(t)    __REG(TARGET_SD_LANE, t, 25, 56, 0, 1, 56, 36, 0, 1, 4)
+/* SD_LANE_TARGET:CFG_STAT_FX100:M_STAT_MISC */
+#define SD_LANE_M_STAT_MISC(t)                                                 \
+	__REG(TARGET_SD_LANE, t, TSIZE(TC_SD_LANE), 56, 0, 1, 56, 36, 0, 1, 4)
 
 #define SD_LANE_M_STAT_MISC_M_RIS_EDGE_PTR_ADJ_SUM GENMASK(21, 0)
 #define SD_LANE_M_STAT_MISC_M_RIS_EDGE_PTR_ADJ_SUM_SET(x)\
@@ -2581,8 +2808,10 @@ enum sparx5_serdes_target {
 #define SD_LANE_M_STAT_MISC_M_LOCK_CNT_GET(x)\
 	FIELD_GET(SD_LANE_M_STAT_MISC_M_LOCK_CNT, x)
 
-/*      SD25G_CFG_TARGET:SD_RESET:SD_SER_RST */
-#define SD_LANE_25G_SD_SER_RST(t) __REG(TARGET_SD_LANE_25G, t, 8, 0, 0, 1, 8, 0, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_CFG_TARGET:SD_RESET:SD_SER_RST */
+#define SD_LANE_25G_SD_SER_RST(t)                                              \
+	__REG(TARGET_SD_LANE_25G, t, 8, 0, 0, 1, 8, 0, 0, 1, 4)
 
 #define SD_LANE_25G_SD_SER_RST_SER_RST           BIT(0)
 #define SD_LANE_25G_SD_SER_RST_SER_RST_SET(x)\
@@ -2590,8 +2819,10 @@ enum sparx5_serdes_target {
 #define SD_LANE_25G_SD_SER_RST_SER_RST_GET(x)\
 	FIELD_GET(SD_LANE_25G_SD_SER_RST_SER_RST, x)
 
-/*      SD25G_CFG_TARGET:SD_RESET:SD_DES_RST */
-#define SD_LANE_25G_SD_DES_RST(t) __REG(TARGET_SD_LANE_25G, t, 8, 0, 0, 1, 8, 4, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_CFG_TARGET:SD_RESET:SD_DES_RST */
+#define SD_LANE_25G_SD_DES_RST(t)                                              \
+	__REG(TARGET_SD_LANE_25G, t, 8, 0, 0, 1, 8, 4, 0, 1, 4)
 
 #define SD_LANE_25G_SD_DES_RST_DES_RST           BIT(0)
 #define SD_LANE_25G_SD_DES_RST_DES_RST_SET(x)\
@@ -2599,8 +2830,10 @@ enum sparx5_serdes_target {
 #define SD_LANE_25G_SD_DES_RST_DES_RST_GET(x)\
 	FIELD_GET(SD_LANE_25G_SD_DES_RST_DES_RST, x)
 
-/*      SD25G_CFG_TARGET:SD_LANE_CFG_STAT:SD_LANE_CFG */
-#define SD_LANE_25G_SD_LANE_CFG(t) __REG(TARGET_SD_LANE_25G, t, 8, 8, 0, 1, 12, 0, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_CFG_TARGET:SD_LANE_CFG_STAT:SD_LANE_CFG */
+#define SD_LANE_25G_SD_LANE_CFG(t)                                             \
+	__REG(TARGET_SD_LANE_25G, t, 8, 8, 0, 1, 12, 0, 0, 1, 4)
 
 #define SD_LANE_25G_SD_LANE_CFG_MACRO_RST        BIT(0)
 #define SD_LANE_25G_SD_LANE_CFG_MACRO_RST_SET(x)\
@@ -2698,8 +2931,10 @@ enum sparx5_serdes_target {
 #define SD_LANE_25G_SD_LANE_CFG_PCS2PMA_TXMARGIN_GET(x)\
 	FIELD_GET(SD_LANE_25G_SD_LANE_CFG_PCS2PMA_TXMARGIN, x)
 
-/*      SD25G_CFG_TARGET:SD_LANE_CFG_STAT:SD_LANE_CFG2 */
-#define SD_LANE_25G_SD_LANE_CFG2(t) __REG(TARGET_SD_LANE_25G, t, 8, 8, 0, 1, 12, 4, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_CFG_TARGET:SD_LANE_CFG_STAT:SD_LANE_CFG2 */
+#define SD_LANE_25G_SD_LANE_CFG2(t)                                            \
+	__REG(TARGET_SD_LANE_25G, t, 8, 8, 0, 1, 12, 4, 0, 1, 4)
 
 #define SD_LANE_25G_SD_LANE_CFG2_DATA_WIDTH_SEL  GENMASK(2, 0)
 #define SD_LANE_25G_SD_LANE_CFG2_DATA_WIDTH_SEL_SET(x)\
@@ -2767,8 +3002,10 @@ enum sparx5_serdes_target {
 #define SD_LANE_25G_SD_LANE_CFG2_RXRATE_SEL_GET(x)\
 	FIELD_GET(SD_LANE_25G_SD_LANE_CFG2_RXRATE_SEL, x)
 
-/*      SD25G_CFG_TARGET:SD_LANE_CFG_STAT:SD_LANE_STAT */
-#define SD_LANE_25G_SD_LANE_STAT(t) __REG(TARGET_SD_LANE_25G, t, 8, 8, 0, 1, 12, 8, 0, 1, 4)
+/* SPARX5 ONLY */
+/* SD25G_CFG_TARGET:SD_LANE_CFG_STAT:SD_LANE_STAT */
+#define SD_LANE_25G_SD_LANE_STAT(t)                                            \
+	__REG(TARGET_SD_LANE_25G, t, 8, 8, 0, 1, 12, 8, 0, 1, 4)
 
 #define SD_LANE_25G_SD_LANE_STAT_PMA_RST_DONE    BIT(0)
 #define SD_LANE_25G_SD_LANE_STAT_PMA_RST_DONE_SET(x)\
@@ -2788,8 +3025,9 @@ enum sparx5_serdes_target {
 #define SD_LANE_25G_SD_LANE_STAT_DBG_OBS_GET(x)\
 	FIELD_GET(SD_LANE_25G_SD_LANE_STAT_DBG_OBS, x)
 
-/*      SD25G_CFG_TARGET:SD_PWR_CFG:QUIET_MODE_6G */
-#define SD_LANE_25G_QUIET_MODE_6G(t) \
+/* SPARX5 ONLY */
+/* SD25G_CFG_TARGET:SD_PWR_CFG:QUIET_MODE_6G */
+#define SD_LANE_25G_QUIET_MODE_6G(t)                                           \
 	__REG(TARGET_SD_LANE_25G, t, 8, 28, 0, 1, 8, 4, 0, 1, 4)
 
 #define SD_LANE_25G_QUIET_MODE_6G_QUIET_MODE     GENMASK(24, 0)

From 6158a32b431bc93f35aff03c9889417a7643da9a Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 9 Sep 2024 17:14:47 +0200
Subject: [PATCH 0569/1530] phy: sparx5-serdes: add support for branching on
 chip type

In preparation for lan969x, add a way to branch out on code that is to
be executed on either Sparx5 or lan969x.  Initially, this is required to
branch out when checking the SERDES types and SERDES speeds, since the
handling of these differ on the two platforms. This will also be used by
the lan969x driver introduced in a subsequent patch.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Link: https://lore.kernel.org/r/20240909-sparx5-lan969x-serdes-driver-v2-7-d695bcb57b84@microchip.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/microchip/sparx5_serdes.c | 29 +++++++++++++++++----------
 drivers/phy/microchip/sparx5_serdes.h |  5 +++++
 2 files changed, 23 insertions(+), 11 deletions(-)

diff --git a/drivers/phy/microchip/sparx5_serdes.c b/drivers/phy/microchip/sparx5_serdes.c
index 8a716bfaa0231..05fdf225ff43f 100644
--- a/drivers/phy/microchip/sparx5_serdes.c
+++ b/drivers/phy/microchip/sparx5_serdes.c
@@ -2298,10 +2298,12 @@ static int sparx5_serdes_set_speed(struct phy *phy, int speed)
 {
 	struct sparx5_serdes_macro *macro = phy_get_drvdata(phy);
 
-	if (macro->sidx < SPX5_SERDES_10G_START && speed > SPEED_5000)
-		return -EINVAL;
-	if (macro->sidx < SPX5_SERDES_25G_START && speed > SPEED_10000)
-		return -EINVAL;
+	if (macro->priv->data->type == SPX5_TARGET_SPARX5) {
+		if (macro->sidx < SPX5_SERDES_10G_START && speed > SPEED_5000)
+			return -EINVAL;
+		if (macro->sidx < SPX5_SERDES_25G_START && speed > SPEED_10000)
+			return -EINVAL;
+	}
 	if (speed != macro->speed) {
 		macro->speed = speed;
 		if (macro->serdesmode != SPX5_SD_MODE_NONE)
@@ -2338,11 +2340,14 @@ static int sparx5_serdes_validate(struct phy *phy, enum phy_mode mode,
 	if (macro->speed == 0)
 		return -EINVAL;
 
-	if (macro->sidx < SPX5_SERDES_10G_START && macro->speed > SPEED_5000)
-		return -EINVAL;
-	if (macro->sidx < SPX5_SERDES_25G_START && macro->speed > SPEED_10000)
-		return -EINVAL;
-
+	if (macro->priv->data->type == SPX5_TARGET_SPARX5) {
+		if (macro->sidx < SPX5_SERDES_10G_START &&
+		    macro->speed > SPEED_5000)
+			return -EINVAL;
+		if (macro->sidx < SPX5_SERDES_25G_START &&
+		    macro->speed > SPEED_10000)
+			return -EINVAL;
+	}
 	switch (submode) {
 	case PHY_INTERFACE_MODE_1000BASEX:
 		if (macro->speed != SPEED_100 && /* This is for 100BASE-FX */
@@ -2515,6 +2520,7 @@ static struct sparx5_serdes_io_resource sparx5_serdes_iomap[] =  {
 };
 
 static const struct sparx5_serdes_match_data sparx5_desc = {
+	.type = SPX5_TARGET_SPARX5,
 	.iomap = sparx5_serdes_iomap,
 	.iomap_size = ARRAY_SIZE(sparx5_serdes_iomap),
 	.tsize = sparx5_serdes_tsize,
@@ -2618,8 +2624,9 @@ static int sparx5_serdes_probe(struct platform_device *pdev)
 			return err;
 	}
 
-	/* Power down all CMUs by default */
-	sparx5_serdes_cmu_power_off(priv);
+	/* Power down all CMU's by default */
+	if (priv->data->type == SPX5_TARGET_SPARX5)
+		sparx5_serdes_cmu_power_off(priv);
 
 	provider = devm_of_phy_provider_register(priv->dev, sparx5_serdes_xlate);
 
diff --git a/drivers/phy/microchip/sparx5_serdes.h b/drivers/phy/microchip/sparx5_serdes.h
index 50900bf06c4c7..1beaa3d05a5d5 100644
--- a/drivers/phy/microchip/sparx5_serdes.h
+++ b/drivers/phy/microchip/sparx5_serdes.h
@@ -34,6 +34,10 @@ enum sparx5_10g28cmu_mode {
 	SPX5_SD10G28_CMU_MAX,
 };
 
+enum sparx5_target {
+	SPX5_TARGET_SPARX5,
+};
+
 struct sparx5_serdes_macro {
 	struct sparx5_serdes_private *priv;
 	u32 sidx;
@@ -56,6 +60,7 @@ struct sparx5_serdes_ops {
 };
 
 struct sparx5_serdes_match_data {
+	enum sparx5_target type;
 	const struct sparx5_serdes_consts consts;
 	const struct sparx5_serdes_ops ops;
 	const struct sparx5_serdes_io_resource *iomap;

From c5699055472ead216c38236476c62bf43fcc3ca3 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 9 Sep 2024 17:14:48 +0200
Subject: [PATCH 0570/1530] dt-bindings: phy: sparx5: document lan969x

Lan969x is going to reuse the existing Sparx5 SERDES driver - document
that by adding compatible strings for the different SKU's that we
support, and a short description of the SERDES types and data rates
supported.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20240909-sparx5-lan969x-serdes-driver-v2-8-d695bcb57b84@microchip.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../bindings/phy/microchip,sparx5-serdes.yaml   | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/phy/microchip,sparx5-serdes.yaml b/Documentation/devicetree/bindings/phy/microchip,sparx5-serdes.yaml
index bdbdb3bbddbea..fa0b02916dacf 100644
--- a/Documentation/devicetree/bindings/phy/microchip,sparx5-serdes.yaml
+++ b/Documentation/devicetree/bindings/phy/microchip,sparx5-serdes.yaml
@@ -8,6 +8,7 @@ title: Microchip Sparx5 Serdes controller
 
 maintainers:
   - Steen Hegelund <steen.hegelund@microchip.com>
+  - Daniel Machon <daniel.machon@microchip.com>
 
 description: |
   The Sparx5 SERDES interfaces share the same basic functionality, but
@@ -62,12 +63,26 @@ description: |
   * 10.3125 Gbps (10GBASE-R/10GBASE-KR/USXGMII)
   * 25.78125 Gbps (25GBASE-KR/25GBASE-CR/25GBASE-SR/25GBASE-LR/25GBASE-ER)
 
+  lan969x has ten SERDES10G interfaces that share the same features, operating
+  modes and data rates as the equivalent Sparx5 SERDES10G interfaces.
+
 properties:
   $nodename:
     pattern: "^serdes@[0-9a-f]+$"
 
   compatible:
-    const: microchip,sparx5-serdes
+    oneOf:
+      - enum:
+          - microchip,sparx5-serdes
+          - microchip,lan9691-serdes
+      - items:
+          - enum:
+              - microchip,lan9698-serdes
+              - microchip,lan9696-serdes
+              - microchip,lan9694-serdes
+              - microchip,lan9693-serdes
+              - microchip,lan9692-serdes
+          - const: microchip,lan9691-serdes
 
   reg:
     minItems: 1

From c0a0a7aec1b142e116c61f3d3facc8c80e97bbff Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 9 Sep 2024 17:14:49 +0200
Subject: [PATCH 0571/1530] phy: lan969x-serdes: add support for lan969x serdes
 driver

Add support for lan969x SERDES driver. Lan969x has ten 10G SERDES'es
which share the same features and data rates as the Sparx5 SERDES'es.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Link: https://lore.kernel.org/r/20240909-sparx5-lan969x-serdes-driver-v2-9-d695bcb57b84@microchip.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/microchip/sparx5_serdes.c | 88 +++++++++++++++++++++++++++
 drivers/phy/microchip/sparx5_serdes.h |  2 +
 2 files changed, 90 insertions(+)

diff --git a/drivers/phy/microchip/sparx5_serdes.c b/drivers/phy/microchip/sparx5_serdes.c
index 05fdf225ff43f..320cf5b50a8cc 100644
--- a/drivers/phy/microchip/sparx5_serdes.c
+++ b/drivers/phy/microchip/sparx5_serdes.c
@@ -25,6 +25,8 @@
 #define SPX5_SERDES_25G_START 25
 #define SPX5_SERDES_6G10G_CNT SPX5_SERDES_25G_START
 
+#define LAN969X_SERDES_10G_CNT 10
+
 /* Optimal power settings from GUC */
 #define SPX5_SERDES_QUIET_MODE_VAL 0x01ef4e0c
 
@@ -36,6 +38,13 @@ const unsigned int sparx5_serdes_tsize[TSIZE_LAST] = {
 	[TC_SD_LANE] = 25,
 };
 
+const unsigned int lan969x_serdes_tsize[TSIZE_LAST] = {
+	[TC_SD10G_LANE] = 10,
+	[TC_SD_CMU] = 6,
+	[TC_SD_CMU_CFG] = 6,
+	[TC_SD_LANE] = 10,
+};
+
 /* Pointer to the register target size table */
 const unsigned int *tsize;
 
@@ -1096,6 +1105,24 @@ static int sparx5_serdes_cmu_get(enum sparx5_10g28cmu_mode mode, int sd_index)
 	return sparx5_serdes_cmu_map[mode][sd_index];
 }
 
+/* Map of 6G/10G serdes mode and index to CMU index. */
+static const int
+lan969x_serdes_cmu_map[SPX5_SD10G28_CMU_MAX][LAN969X_SERDES_10G_CNT] = {
+	[SPX5_SD10G28_CMU_MAIN] = { 2, 2, 2, 2, 2,
+				    2, 2, 2, 5, 5 },
+	[SPX5_SD10G28_CMU_AUX1] = { 0, 0, 3, 3, 3,
+				    3, 3, 3, 3, 3 },
+	[SPX5_SD10G28_CMU_AUX2] = { 1, 1, 1, 1, 4,
+				    4, 4, 4, 4, 4 },
+	[SPX5_SD10G28_CMU_NONE] = { 1, 1, 1, 1, 4,
+				    4, 4, 4, 4, 4 },
+};
+
+static int lan969x_serdes_cmu_get(enum sparx5_10g28cmu_mode mode, int sd_index)
+{
+	return lan969x_serdes_cmu_map[mode][sd_index];
+}
+
 static void sparx5_serdes_cmu_power_off(struct sparx5_serdes_private *priv)
 {
 	void __iomem *cmu_inst, *cmu_cfg_inst;
@@ -2184,6 +2211,10 @@ static int sparx5_serdes_clock_config(struct sparx5_serdes_macro *macro)
 {
 	struct sparx5_serdes_private *priv = macro->priv;
 
+	/* Clock is auto-detected in 100Base-FX mode on lan969x */
+	if (priv->data->type == SPX5_TARGET_LAN969X)
+		return 0;
+
 	if (macro->serdesmode == SPX5_SD_MODE_100FX) {
 		u32 freq = priv->coreclock == 250000000 ? 2 :
 			priv->coreclock == 500000000 ? 1 : 0;
@@ -2395,6 +2426,12 @@ static void sparx5_serdes_type_set(struct sparx5_serdes_macro *macro, int sidx)
 	}
 }
 
+static void lan969x_serdes_type_set(struct sparx5_serdes_macro *macro, int sidx)
+{
+	macro->serdestype = SPX5_SDT_10G;
+	macro->stpidx = macro->sidx;
+}
+
 static int sparx5_phy_create(struct sparx5_serdes_private *priv,
 			   int idx, struct phy **phy)
 {
@@ -2519,6 +2556,41 @@ static struct sparx5_serdes_io_resource sparx5_serdes_iomap[] =  {
 	{ TARGET_SD_LANE_25G + 7, 0x5c8000 }, /* 0x610dd0000: sd_lane_25g_32 */
 };
 
+static const struct sparx5_serdes_io_resource lan969x_serdes_iomap[] =  {
+	{ TARGET_SD_CMU,               0x0     }, /* 0xe3410000 */
+	{ TARGET_SD_CMU +  1,          0x8000  }, /* 0xe3418000 */
+	{ TARGET_SD_CMU +  2,          0x10000 }, /* 0xe3420000 */
+	{ TARGET_SD_CMU +  3,          0x18000 }, /* 0xe3428000 */
+	{ TARGET_SD_CMU +  4,          0x20000 }, /* 0xe3430000 */
+	{ TARGET_SD_CMU +  5,          0x28000 }, /* 0xe3438000 */
+	{ TARGET_SD_CMU_CFG,           0x30000 }, /* 0xe3440000 */
+	{ TARGET_SD_CMU_CFG +  1,      0x38000 }, /* 0xe3448000 */
+	{ TARGET_SD_CMU_CFG +  2,      0x40000 }, /* 0xe3450000 */
+	{ TARGET_SD_CMU_CFG +  3,      0x48000 }, /* 0xe3458000 */
+	{ TARGET_SD_CMU_CFG +  4,      0x50000 }, /* 0xe3460000 */
+	{ TARGET_SD_CMU_CFG +  5,      0x58000 }, /* 0xe3468000 */
+	{ TARGET_SD10G_LANE,           0x60000 }, /* 0xe3470000 */
+	{ TARGET_SD10G_LANE +  1,      0x68000 }, /* 0xe3478000 */
+	{ TARGET_SD10G_LANE +  2,      0x70000 }, /* 0xe3480000 */
+	{ TARGET_SD10G_LANE +  3,      0x78000 }, /* 0xe3488000 */
+	{ TARGET_SD10G_LANE +  4,      0x80000 }, /* 0xe3490000 */
+	{ TARGET_SD10G_LANE +  5,      0x88000 }, /* 0xe3498000 */
+	{ TARGET_SD10G_LANE +  6,      0x90000 }, /* 0xe34a0000 */
+	{ TARGET_SD10G_LANE +  7,      0x98000 }, /* 0xe34a8000 */
+	{ TARGET_SD10G_LANE +  8,      0xa0000 }, /* 0xe34b0000 */
+	{ TARGET_SD10G_LANE +  9,      0xa8000 }, /* 0xe34b8000 */
+	{ TARGET_SD_LANE,             0x100000 }, /* 0xe3510000 */
+	{ TARGET_SD_LANE +  1,        0x108000 }, /* 0xe3518000 */
+	{ TARGET_SD_LANE +  2,        0x110000 }, /* 0xe3520000 */
+	{ TARGET_SD_LANE +  3,        0x118000 }, /* 0xe3528000 */
+	{ TARGET_SD_LANE +  4,        0x120000 }, /* 0xe3530000 */
+	{ TARGET_SD_LANE +  5,        0x128000 }, /* 0xe3538000 */
+	{ TARGET_SD_LANE +  6,        0x130000 }, /* 0xe3540000 */
+	{ TARGET_SD_LANE +  7,        0x138000 }, /* 0xe3548000 */
+	{ TARGET_SD_LANE +  8,        0x140000 }, /* 0xe3550000 */
+	{ TARGET_SD_LANE +  9,        0x148000 }, /* 0xe3558000 */
+};
+
 static const struct sparx5_serdes_match_data sparx5_desc = {
 	.type = SPX5_TARGET_SPARX5,
 	.iomap = sparx5_serdes_iomap,
@@ -2534,6 +2606,21 @@ static const struct sparx5_serdes_match_data sparx5_desc = {
 	},
 };
 
+static const struct sparx5_serdes_match_data lan969x_desc = {
+	.type = SPX5_TARGET_LAN969X,
+	.iomap = lan969x_serdes_iomap,
+	.iomap_size = ARRAY_SIZE(lan969x_serdes_iomap),
+	.tsize = lan969x_serdes_tsize,
+	.consts = {
+		.sd_max       = 10,
+		.cmu_max      = 6,
+	},
+	.ops = {
+		.serdes_type_set      = &lan969x_serdes_type_set,
+		.serdes_cmu_get       = &lan969x_serdes_cmu_get,
+	}
+};
+
 /* Client lookup function, uses serdes index */
 static struct phy *sparx5_serdes_xlate(struct device *dev,
 				     const struct of_phandle_args *args)
@@ -2635,6 +2722,7 @@ static int sparx5_serdes_probe(struct platform_device *pdev)
 
 static const struct of_device_id sparx5_serdes_match[] = {
 	{ .compatible = "microchip,sparx5-serdes", .data = &sparx5_desc },
+	{ .compatible = "microchip,lan9691-serdes", .data = &lan969x_desc },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, sparx5_serdes_match);
diff --git a/drivers/phy/microchip/sparx5_serdes.h b/drivers/phy/microchip/sparx5_serdes.h
index 1beaa3d05a5d5..d7093d0b09c0c 100644
--- a/drivers/phy/microchip/sparx5_serdes.h
+++ b/drivers/phy/microchip/sparx5_serdes.h
@@ -36,6 +36,8 @@ enum sparx5_10g28cmu_mode {
 
 enum sparx5_target {
 	SPX5_TARGET_SPARX5,
+	SPX5_TARGET_LAN969X,
+
 };
 
 struct sparx5_serdes_macro {

From 6e86292f212cf121cafe881c18381b5972b18d4f Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Wed, 16 Oct 2024 11:34:25 +0000
Subject: [PATCH 0572/1530] rust: page: add Rust version of PAGE_ALIGN

This is a useful for helper for working with indices into buffers that
consist of several pages. I forgot to include it when I added PAGE_SIZE
and PAGE_MASK for the same purpose in commit fc6e66f4696b ("rust: add
abstraction for `struct page`").

Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20241016-page-align-v2-1-e0afe85fc4b4@google.com
[ Added intra-doc links, formatted comment and replaced "Brackets" with
  "Parentheses" as discussed in the list. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/page.rs | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/rust/kernel/page.rs b/rust/kernel/page.rs
index 208a006d587c1..fdac6c375fe46 100644
--- a/rust/kernel/page.rs
+++ b/rust/kernel/page.rs
@@ -20,6 +20,16 @@ pub const PAGE_SIZE: usize = bindings::PAGE_SIZE;
 /// A bitmask that gives the page containing a given address.
 pub const PAGE_MASK: usize = !(PAGE_SIZE - 1);
 
+/// Round up the given number to the next multiple of [`PAGE_SIZE`].
+///
+/// It is incorrect to pass an address where the next multiple of [`PAGE_SIZE`] doesn't fit in a
+/// [`usize`].
+pub const fn page_align(addr: usize) -> usize {
+    // Parentheses around `PAGE_SIZE - 1` to avoid triggering overflow sanitizers in the wrong
+    // cases.
+    (addr + (PAGE_SIZE - 1)) & PAGE_MASK
+}
+
 /// A pointer to a page that owns the page allocation.
 ///
 /// # Invariants

From 8b55dc8610acf816a66373be53ca6e3bbe2d313a Mon Sep 17 00:00:00 2001
From: Yutaro Ohno <yutaro.ono.418@gmail.com>
Date: Mon, 21 Oct 2024 11:58:47 +0900
Subject: [PATCH 0573/1530] rust: kernel: fix THIS_MODULE header path in
 ThisModule doc comment

The doc comment for `ThisModule` incorrectly states the C header file
for `THIS_MODULE` as `include/linux/export.h`, while the correct path is
`include/linux/init.h`. This is because `THIS_MODULE` was moved in
commit 5b20755b7780 ("init: move THIS_MODULE from <linux/export.h> to
<linux/init.h>").

Update the doc comment for `ThisModule` to reflect the correct header
file path for `THIS_MODULE`.

Fixes: 5b20755b7780 ("init: move THIS_MODULE from <linux/export.h> to <linux/init.h>")
Signed-off-by: Yutaro Ohno <yutaro.ono.418@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/ZxXDZwxWgoEiIYkj@ohnotp
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/lib.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 620de74d128f9..b62451f64f6ed 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -85,7 +85,7 @@ pub trait Module: Sized + Sync + Send {
 
 /// Equivalent to `THIS_MODULE` in the C API.
 ///
-/// C header: [`include/linux/export.h`](srctree/include/linux/export.h)
+/// C header: [`include/linux/init.h`](srctree/include/linux/init.h)
 pub struct ThisModule(*mut bindings::module);
 
 // SAFETY: `THIS_MODULE` may be used from all threads within a module.

From 15541c9263ce34ff95a06bc68f45d9bc5c990bcd Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Sat, 19 Oct 2024 09:22:08 +0200
Subject: [PATCH 0574/1530] rust: macros: fix documentation of the paste! macro

One of the example in this section uses a curious mix of the constant
and function declaration syntaxes; fix it.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Fixes: 823d4737d4c2 ("rust: macros: add `paste!` proc macro")
Link: https://lore.kernel.org/r/20241019072208.1016707-1-pbonzini@redhat.com
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/macros/lib.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
index 8d4ac914b48bc..939ae00b723a6 100644
--- a/rust/macros/lib.rs
+++ b/rust/macros/lib.rs
@@ -359,7 +359,7 @@ pub fn pinned_drop(args: TokenStream, input: TokenStream) -> TokenStream {
 /// macro_rules! pub_no_prefix {
 ///     ($prefix:ident, $($newname:ident),+) => {
 ///         kernel::macros::paste! {
-///             $(pub(crate) const fn [<$newname:lower:span>]: u32 = [<$prefix $newname:span>];)+
+///             $(pub(crate) const fn [<$newname:lower:span>]() -> u32 { [<$prefix $newname:span>] })+
 ///         }
 ///     };
 /// }

From 32f4a76b8e7cedec9f9aedbfc43626536bba8350 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <quic_kdybcio@quicinc.com>
Date: Tue, 3 Sep 2024 13:13:10 +0200
Subject: [PATCH 0575/1530] phy: qcom: qmp: Fix lecacy-legacy typo

Introduced in Commit b3982f2144e1 ("phy: qcom-qmp-combo: restructure
PHY creation"). No functional changes.

Signed-off-by: Konrad Dybcio <quic_kdybcio@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20240903-topic-qmp_typo-v1-1-781e81799992@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-combo.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
index a8adc3214bfe7..0198dc21ae56f 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
@@ -3483,7 +3483,7 @@ static int qmp_combo_typec_switch_register(struct qmp_combo *qmp)
 }
 #endif
 
-static int qmp_combo_parse_dt_lecacy_dp(struct qmp_combo *qmp, struct device_node *np)
+static int qmp_combo_parse_dt_legacy_dp(struct qmp_combo *qmp, struct device_node *np)
 {
 	struct device *dev = qmp->dev;
 
@@ -3510,7 +3510,7 @@ static int qmp_combo_parse_dt_lecacy_dp(struct qmp_combo *qmp, struct device_nod
 	return 0;
 }
 
-static int qmp_combo_parse_dt_lecacy_usb(struct qmp_combo *qmp, struct device_node *np)
+static int qmp_combo_parse_dt_legacy_usb(struct qmp_combo *qmp, struct device_node *np)
 {
 	const struct qmp_phy_cfg *cfg = qmp->cfg;
 	struct device *dev = qmp->dev;
@@ -3576,11 +3576,11 @@ static int qmp_combo_parse_dt_legacy(struct qmp_combo *qmp, struct device_node *
 	if (IS_ERR(qmp->dp_serdes))
 		return PTR_ERR(qmp->dp_serdes);
 
-	ret = qmp_combo_parse_dt_lecacy_usb(qmp, usb_np);
+	ret = qmp_combo_parse_dt_legacy_usb(qmp, usb_np);
 	if (ret)
 		return ret;
 
-	ret = qmp_combo_parse_dt_lecacy_dp(qmp, dp_np);
+	ret = qmp_combo_parse_dt_legacy_dp(qmp, dp_np);
 	if (ret)
 		return ret;
 

From 48d0fd2b903e397c2a9621ab35f3d8877f61aee4 Mon Sep 17 00:00:00 2001
From: Wei Huang <wei.huang2@amd.com>
Date: Wed, 2 Oct 2024 11:59:52 -0500
Subject: [PATCH 0576/1530] PCI/TPH: Add TPH documentation

Add a document for the TPH feature, including description of "notph" kernel
parameter and the API interface.

Co-developed-by: Eric Van Tassell <Eric.VanTassell@amd.com>
Link: https://lore.kernel.org/r/20241002165954.128085-4-wei.huang2@amd.com
Signed-off-by: Eric Van Tassell <Eric.VanTassell@amd.com>
Signed-off-by: Wei Huang <wei.huang2@amd.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
---
 Documentation/PCI/index.rst          |   1 +
 Documentation/PCI/tph.rst            | 132 +++++++++++++++++++++++++++
 Documentation/driver-api/pci/pci.rst |   3 +
 3 files changed, 136 insertions(+)
 create mode 100644 Documentation/PCI/tph.rst

diff --git a/Documentation/PCI/index.rst b/Documentation/PCI/index.rst
index e73f84aebde3b..5e7c4e6e726bb 100644
--- a/Documentation/PCI/index.rst
+++ b/Documentation/PCI/index.rst
@@ -18,3 +18,4 @@ PCI Bus Subsystem
    pcieaer-howto
    endpoint/index
    boot-interrupts
+   tph
diff --git a/Documentation/PCI/tph.rst b/Documentation/PCI/tph.rst
new file mode 100644
index 0000000000000..e8993be64fd64
--- /dev/null
+++ b/Documentation/PCI/tph.rst
@@ -0,0 +1,132 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+
+===========
+TPH Support
+===========
+
+:Copyright: 2024 Advanced Micro Devices, Inc.
+:Authors: - Eric van Tassell <eric.vantassell@amd.com>
+          - Wei Huang <wei.huang2@amd.com>
+
+
+Overview
+========
+
+TPH (TLP Processing Hints) is a PCIe feature that allows endpoint devices
+to provide optimization hints for requests that target memory space.
+These hints, in a format called Steering Tags (STs), are embedded in the
+requester's TLP headers, enabling the system hardware, such as the Root
+Complex, to better manage platform resources for these requests.
+
+For example, on platforms with TPH-based direct data cache injection
+support, an endpoint device can include appropriate STs in its DMA
+traffic to specify which cache the data should be written to. This allows
+the CPU core to have a higher probability of getting data from cache,
+potentially improving performance and reducing latency in data
+processing.
+
+
+How to Use TPH
+==============
+
+TPH is presented as an optional extended capability in PCIe. The Linux
+kernel handles TPH discovery during boot, but it is up to the device
+driver to request TPH enablement if it is to be utilized. Once enabled,
+the driver uses the provided API to obtain the Steering Tag for the
+target memory and to program the ST into the device's ST table.
+
+Enable TPH support in Linux
+---------------------------
+
+To support TPH, the kernel must be built with the CONFIG_PCIE_TPH option
+enabled.
+
+Manage TPH
+----------
+
+To enable TPH for a device, use the following function::
+
+  int pcie_enable_tph(struct pci_dev *pdev, int mode);
+
+This function enables TPH support for device with a specific ST mode.
+Current supported modes include:
+
+  * PCI_TPH_ST_NS_MODE - NO ST Mode
+  * PCI_TPH_ST_IV_MODE - Interrupt Vector Mode
+  * PCI_TPH_ST_DS_MODE - Device Specific Mode
+
+`pcie_enable_tph()` checks whether the requested mode is actually
+supported by the device before enabling. The device driver can figure out
+which TPH mode is supported and can be properly enabled based on the
+return value of `pcie_enable_tph()`.
+
+To disable TPH, use the following function::
+
+  void pcie_disable_tph(struct pci_dev *pdev);
+
+Manage ST
+---------
+
+Steering Tags are platform specific. PCIe spec does not specify where STs
+are from. Instead PCI Firmware Specification defines an ACPI _DSM method
+(see the `Revised _DSM for Cache Locality TPH Features ECN
+<https://members.pcisig.com/wg/PCI-SIG/document/15470>`_) for retrieving
+STs for a target memory of various properties. This method is what is
+supported in this implementation.
+
+To retrieve a Steering Tag for a target memory associated with a specific
+CPU, use the following function::
+
+  int pcie_tph_get_cpu_st(struct pci_dev *pdev, enum tph_mem_type type,
+                          unsigned int cpu_uid, u16 *tag);
+
+The `type` argument is used to specify the memory type, either volatile
+or persistent, of the target memory. The `cpu_uid` argument specifies the
+CPU where the memory is associated to.
+
+After the ST value is retrieved, the device driver can use the following
+function to write the ST into the device::
+
+  int pcie_tph_set_st_entry(struct pci_dev *pdev, unsigned int index,
+                            u16 tag);
+
+The `index` argument is the ST table entry index the ST tag will be
+written into. `pcie_tph_set_st_entry()` will figure out the proper
+location of ST table, either in the MSI-X table or in the TPH Extended
+Capability space, and write the Steering Tag into the ST entry pointed by
+the `index` argument.
+
+It is completely up to the driver to decide how to use these TPH
+functions. For example a network device driver can use the TPH APIs above
+to update the Steering Tag when interrupt affinity of a RX/TX queue has
+been changed. Here is a sample code for IRQ affinity notifier:
+
+.. code-block:: c
+
+    static void irq_affinity_notified(struct irq_affinity_notify *notify,
+                                      const cpumask_t *mask)
+    {
+         struct drv_irq *irq;
+         unsigned int cpu_id;
+         u16 tag;
+
+         irq = container_of(notify, struct drv_irq, affinity_notify);
+         cpumask_copy(irq->cpu_mask, mask);
+
+         /* Pick a right CPU as the target - here is just an example */
+         cpu_id = cpumask_first(irq->cpu_mask);
+
+         if (pcie_tph_get_cpu_st(irq->pdev, TPH_MEM_TYPE_VM, cpu_id,
+                                 &tag))
+             return;
+
+         if (pcie_tph_set_st_entry(irq->pdev, irq->msix_nr, tag))
+             return;
+    }
+
+Disable TPH system-wide
+-----------------------
+
+There is a kernel command line option available to control TPH feature:
+    * "notph": TPH will be disabled for all endpoint devices.
diff --git a/Documentation/driver-api/pci/pci.rst b/Documentation/driver-api/pci/pci.rst
index aa40b1cc243b8..59d86e8271986 100644
--- a/Documentation/driver-api/pci/pci.rst
+++ b/Documentation/driver-api/pci/pci.rst
@@ -46,6 +46,9 @@ PCI Support Library
 .. kernel-doc:: drivers/pci/pci-sysfs.c
    :internal:
 
+.. kernel-doc:: drivers/pci/tph.c
+   :export:
+
 PCI Hotplug Support Library
 ---------------------------
 

From 18b63d63cd0148fef02c6c3f33a596ad7ee97a9a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sat, 19 Oct 2024 23:18:40 -0300
Subject: [PATCH 0577/1530] perf test: Introduce workloads__for_each()

And use it in run_workload().

Testing it:

  root@x1:~# perf trace -e *landlock* perf test -w landlock
       0.000 ( 0.015 ms): :1274331/1274331 landlock_add_rule(ruleset_fd: 11, rule_type: LANDLOCK_RULE_PATH_BENEATH, rule_attr: 0x7ffd3fea55e0, flags: 45) = -1 EINVAL (Invalid argument)
       0.018 ( 0.003 ms): :1274331/1274331 landlock_add_rule(ruleset_fd: 11, rule_type: LANDLOCK_RULE_NET_PORT, rule_attr: 0x7ffd3fea55f0, flags: 45) = -1 EINVAL (Invalid argument)
  root@x1:~# perf test -w bla
  No workload found: bla
  root@x1:~#

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Clark Williams <williams@redhat.com>
Link: https://lore.kernel.org/r/20241020021842.1752770-2-acme@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/builtin-test.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 50533446e7478..b47d53764d815 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -155,6 +155,9 @@ static struct test_workload *workloads[] = {
 	&workload__landlock,
 };
 
+#define workloads__for_each(workload) \
+	for (unsigned i = 0; i < ARRAY_SIZE(workloads) && ({ workload = workloads[i]; 1; }); i++)
+
 static int num_subtests(const struct test_suite *t)
 {
 	int num;
@@ -504,11 +507,9 @@ static int perf_test__list(int argc, const char **argv)
 
 static int run_workload(const char *work, int argc, const char **argv)
 {
-	unsigned int i = 0;
 	struct test_workload *twl;
 
-	for (i = 0; i < ARRAY_SIZE(workloads); i++) {
-		twl = workloads[i];
+	workloads__for_each(twl) {
 		if (!strcmp(twl->name, work))
 			return twl->func(argc, argv);
 	}

From 13c138308d15cb194db53d0f24a4dd9de37193f3 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sat, 19 Oct 2024 23:18:41 -0300
Subject: [PATCH 0578/1530] perf test: Introduce --list-workloads to list the
 available workloads

Using it:

  $ perf test -w noplop
  No workload found: noplop
  $
  $ perf test -w
   Error: switch `w' requires a value
   Usage: perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]

      -w, --workload <work>
                            workload to run for testing, use '--list-workloads' to list the available ones.
  $
  $ perf test --list-workloads
  noploop
  thloop
  leafloop
  sqrtloop
  brstack
  datasym
  landlock
  $

Would be good at some point to have a description in 'struct test_workload'.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Clark Williams <williams@redhat.com>
Link: https://lore.kernel.org/r/20241020021842.1752770-3-acme@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/builtin-test.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index b47d53764d815..7d27e30d9b2db 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -505,6 +505,17 @@ static int perf_test__list(int argc, const char **argv)
 	return 0;
 }
 
+static int workloads__fprintf_list(FILE *fp)
+{
+	struct test_workload *twl;
+	int printed = 0;
+
+	workloads__for_each(twl)
+		printed += fprintf(fp, "%s\n", twl->name);
+
+	return printed;
+}
+
 static int run_workload(const char *work, int argc, const char **argv)
 {
 	struct test_workload *twl;
@@ -535,6 +546,7 @@ int cmd_test(int argc, const char **argv)
 	};
 	const char *skip = NULL;
 	const char *workload = NULL;
+	bool list_workloads = false;
 	const struct option test_options[] = {
 	OPT_STRING('s', "skip", &skip, "tests", "tests to skip"),
 	OPT_INCR('v', "verbose", &verbose,
@@ -544,7 +556,8 @@ int cmd_test(int argc, const char **argv)
 	OPT_BOOLEAN('p', "parallel", &parallel, "Run the tests in parallel"),
 	OPT_BOOLEAN('S', "sequential", &sequential,
 		    "Run the tests one after another rather than in parallel"),
-	OPT_STRING('w', "workload", &workload, "work", "workload to run for testing"),
+	OPT_STRING('w', "workload", &workload, "work", "workload to run for testing, use '--list-workloads' to list the available ones."),
+	OPT_BOOLEAN(0, "list-workloads", &list_workloads, "List the available builtin workloads to use with -w/--workload"),
 	OPT_STRING(0, "dso", &dso_to_test, "dso", "dso to test"),
 	OPT_STRING(0, "objdump", &test_objdump_path, "path",
 		   "objdump binary to use for disassembly and annotations"),
@@ -570,6 +583,11 @@ int cmd_test(int argc, const char **argv)
 	if (workload)
 		return run_workload(workload, argc, argv);
 
+	if (list_workloads) {
+		workloads__fprintf_list(stdout);
+		return 0;
+	}
+
 	if (dont_fork)
 		sequential = true;
 	else if (parallel)

From 915a377627f7ad91983377f68c3096b3594961a4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sat, 19 Oct 2024 23:18:42 -0300
Subject: [PATCH 0579/1530] perf test: Document the -w/--workload option

Wasn't documented so far, mention that it is mostly used in the shell
regression tests.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Clark Williams <williams@redhat.com>
Link: https://lore.kernel.org/r/20241020021842.1752770-4-acme@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Documentation/perf-test.txt | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt
index 9acb8d1f65889..efcdec528a8f7 100644
--- a/tools/perf/Documentation/perf-test.txt
+++ b/tools/perf/Documentation/perf-test.txt
@@ -48,3 +48,20 @@ OPTIONS
 
 --dso::
 	Specify a DSO for the "Symbols" test.
+
+-w::
+--workload=::
+	Run a built-in workload, to list them use '--list-workloads', current ones include:
+	noploop, thloop, leafloop, sqrtloop, brstack, datasym and landlock.
+
+	Used with the shell script regression tests.
+
+	Some accept an extra parameter:
+
+		seconds: leafloop, noploop, sqrtloop, thloop
+		nrloops: brstack
+
+	The datasym and landlock workloads don't accept any.
+
+--list-workloads::
+	List the available workloads to use with -w/--workload.

From 3e2d4df574fc6bbd00b422f2f1ce5c1ac251feae Mon Sep 17 00:00:00 2001
From: Brian Geffon <bgeffon@google.com>
Date: Wed, 16 Oct 2024 15:00:09 -0400
Subject: [PATCH 0580/1530] perf tools: sched-pipe bench: add (-n) nonblocking
 benchmark

The -n mode will benchmark pipes in a non-blocking mode using
epoll_wait.

This specific mode was added to demonstrate the broken sync nature
of epoll: https://lore.kernel.org/lkml/20240426-zupfen-jahrzehnt-5be786bcdf04@brauner

Signed-off-by: Brian Geffon <bgeffon@google.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: https://lore.kernel.org/r/20241016190009.866615-1-bgeffon@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/bench/sched-pipe.c | 43 +++++++++++++++++++++++++++++------
 1 file changed, 36 insertions(+), 7 deletions(-)

diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 3af6d3c55aba1..e2562677df964 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -23,6 +23,7 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <assert.h>
+#include <sys/epoll.h>
 #include <sys/time.h>
 #include <sys/types.h>
 #include <sys/syscall.h>
@@ -34,6 +35,8 @@ struct thread_data {
 	int			nr;
 	int			pipe_read;
 	int			pipe_write;
+	struct epoll_event      epoll_ev;
+	int			epoll_fd;
 	bool			cgroup_failed;
 	pthread_t		pthread;
 };
@@ -44,6 +47,7 @@ static	int			loops = LOOPS_DEFAULT;
 /* Use processes by default: */
 static bool			threaded;
 
+static bool			nonblocking;
 static char			*cgrp_names[2];
 static struct cgroup		*cgrps[2];
 
@@ -81,6 +85,7 @@ static int parse_two_cgroups(const struct option *opt __maybe_unused,
 }
 
 static const struct option options[] = {
+	OPT_BOOLEAN('n', "nonblocking",	&nonblocking,	"Use non-blocking operations"),
 	OPT_INTEGER('l', "loop",	&loops,		"Specify number of loops"),
 	OPT_BOOLEAN('T', "threaded",	&threaded,	"Specify threads/process based task setup"),
 	OPT_CALLBACK('G', "cgroups", NULL, "SEND,RECV",
@@ -165,11 +170,25 @@ static void exit_cgroup(int nr)
 	free(cgrp_names[nr]);
 }
 
+static inline int read_pipe(struct thread_data *td)
+{
+	int ret, m;
+retry:
+	if (nonblocking) {
+		ret = epoll_wait(td->epoll_fd, &td->epoll_ev, 1, -1);
+		if (ret < 0)
+			return ret;
+	}
+	ret = read(td->pipe_read, &m, sizeof(int));
+	if (nonblocking && ret < 0 && errno == EWOULDBLOCK)
+		goto retry;
+	return ret;
+}
+
 static void *worker_thread(void *__tdata)
 {
 	struct thread_data *td = __tdata;
-	int m = 0, i;
-	int ret;
+	int i, ret, m = 0;
 
 	ret = enter_cgroup(td->nr);
 	if (ret < 0) {
@@ -177,16 +196,23 @@ static void *worker_thread(void *__tdata)
 		return NULL;
 	}
 
+	if (nonblocking) {
+		td->epoll_ev.events = EPOLLIN;
+		td->epoll_fd = epoll_create(1);
+		BUG_ON(td->epoll_fd < 0);
+		BUG_ON(epoll_ctl(td->epoll_fd, EPOLL_CTL_ADD, td->pipe_read, &td->epoll_ev) < 0);
+	}
+
 	for (i = 0; i < loops; i++) {
 		if (!td->nr) {
-			ret = read(td->pipe_read, &m, sizeof(int));
+			ret = read_pipe(td);
 			BUG_ON(ret != sizeof(int));
 			ret = write(td->pipe_write, &m, sizeof(int));
 			BUG_ON(ret != sizeof(int));
 		} else {
 			ret = write(td->pipe_write, &m, sizeof(int));
 			BUG_ON(ret != sizeof(int));
-			ret = read(td->pipe_read, &m, sizeof(int));
+			ret = read_pipe(td);
 			BUG_ON(ret != sizeof(int));
 		}
 	}
@@ -209,13 +235,16 @@ int bench_sched_pipe(int argc, const char **argv)
 	 * discarding returned value of read(), write()
 	 * causes error in building environment for perf
 	 */
-	int __maybe_unused ret, wait_stat;
+	int __maybe_unused ret, wait_stat, flags = 0;
 	pid_t pid, retpid __maybe_unused;
 
 	argc = parse_options(argc, argv, options, bench_sched_pipe_usage, 0);
 
-	BUG_ON(pipe(pipe_1));
-	BUG_ON(pipe(pipe_2));
+	if (nonblocking)
+		flags |= O_NONBLOCK;
+
+	BUG_ON(pipe2(pipe_1, flags));
+	BUG_ON(pipe2(pipe_2, flags));
 
 	gettimeofday(&start, NULL);
 

From f9417fcfca3c5e30a0b961e7250fab92cfa5d123 Mon Sep 17 00:00:00 2001
From: Qianqiang Liu <qianqiang.liu@163.com>
Date: Mon, 21 Oct 2024 22:58:01 +0200
Subject: [PATCH 0581/1530] KMSAN: uninit-value in inode_go_dump (5)

When mounting of a corrupted disk image fails, the error message printed
can reference uninitialized inode fields.  To prevent that from happening,
always initialize those fields.

Reported-by: syzbot+aa0730b0a42646eb1359@syzkaller.appspotmail.com
Signed-off-by: Qianqiang Liu <qianqiang.liu@163.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/super.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index e22c1edc32b39..b9cef63c78717 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1537,11 +1537,13 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb)
 	if (!ip)
 		return NULL;
 	ip->i_no_addr = 0;
+	ip->i_no_formal_ino = 0;
 	ip->i_flags = 0;
 	ip->i_gl = NULL;
 	gfs2_holder_mark_uninitialized(&ip->i_iopen_gh);
 	memset(&ip->i_res, 0, sizeof(ip->i_res));
 	RB_CLEAR_NODE(&ip->i_res.rs_node);
+	ip->i_diskflags = 0;
 	ip->i_rahead = 0;
 	return &ip->i_inode;
 }

From 5778535972e2c1eb69e698803a610b43e50cb036 Mon Sep 17 00:00:00 2001
From: Jingyi Wang <quic_jingyw@quicinc.com>
Date: Fri, 18 Oct 2024 11:19:31 +0800
Subject: [PATCH 0582/1530] dt-bindings: pinctrl: describe qcs8300-tlmm

Add DT bindings for the TLMM controller on QCS8300 platforms.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Jingyi Wang <quic_jingyw@quicinc.com>
Link: https://lore.kernel.org/20241018-qcs8300_tlmm-v3-1-8b8d3957cf1a@quicinc.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/qcom,qcs8300-tlmm.yaml   | 118 ++++++++++++++++++
 1 file changed, 118 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/qcom,qcs8300-tlmm.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,qcs8300-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,qcs8300-tlmm.yaml
new file mode 100644
index 0000000000000..bb0d7132886a1
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,qcs8300-tlmm.yaml
@@ -0,0 +1,118 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,qcs8300-tlmm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Technologies, Inc. QCS8300 TLMM block
+
+maintainers:
+  - Jingyi Wang <quic_jingyw@quicinc.com>
+
+description: |
+  Top Level Mode Multiplexer pin controller in Qualcomm QCS8300 SoC.
+
+allOf:
+  - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml#
+
+properties:
+  compatible:
+    const: qcom,qcs8300-tlmm
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  gpio-reserved-ranges:
+    minItems: 1
+    maxItems: 67
+
+  gpio-line-names:
+    maxItems: 133
+
+patternProperties:
+  "-state$":
+    oneOf:
+      - $ref: "#/$defs/qcom-qcs8300-tlmm-state"
+      - patternProperties:
+          "-pins$":
+            $ref: "#/$defs/qcom-qcs8300-tlmm-state"
+        additionalProperties: false
+
+$defs:
+  qcom-qcs8300-tlmm-state:
+    type: object
+    description:
+      Pinctrl node's client devices use subnodes for desired pin configuration.
+      Client device subnodes use below standard properties.
+    $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
+
+    properties:
+      pins:
+        description:
+          List of gpio pins affected by the properties specified in this
+          subnode.
+        items:
+          oneOf:
+            - pattern: "^gpio([0-9]|[1-9][0-9]|1[0-2][0-9]|13[0-2])$"
+            - enum: [ ufs_reset, sdc1_rclk, sdc1_clk, sdc1_cmd, sdc1_data ]
+        minItems: 1
+        maxItems: 36
+
+      function:
+        description:
+          Specify the alternative function to be configured for the specified
+          pins.
+
+        enum: [ aoss_cti, atest_char, atest_usb2, audio_ref, cam_mclk,
+                cci_async, cci_i2c_scl, cci_i2c_sda, cci_timer, cri_trng,
+                dbg_out, ddr_bist, ddr_pxi0, ddr_pxi1, ddr_pxi2, ddr_pxi3,
+                edp0_hot, edp0_lcd, edp1_lcd, egpio, emac0_mcg0, emac0_mcg1,
+                emac0_mcg2, emac0_mcg3, emac0_mdc, emac0_mdio, emac0_ptp_aux,
+                emac0_ptp_pps, gcc_gp1, gcc_gp2, gcc_gp3, gcc_gp4, gcc_gp5,
+                gpio, hs0_mi2s, hs1_mi2s, hs2_mi2s, ibi_i3c, jitter_bist,
+                mdp0_vsync0, mdp0_vsync1, mdp0_vsync3, mdp0_vsync6, mdp0_vsync7,
+                mdp_vsync, mi2s1_data0, mi2s1_data1, mi2s1_sck, mi2s1_ws,
+                mi2s2_data0, mi2s2_data1, mi2s2_sck, mi2s2_ws, mi2s_mclk0,
+                mi2s_mclk1, pcie0_clkreq, pcie1_clkreq, phase_flag, pll_bist,
+                pll_clk, prng_rosc0, prng_rosc1, prng_rosc2, prng_rosc3,
+                qdss_cti, qdss_gpio, qup0_se0, qup0_se1, qup0_se2, qup0_se3,
+                qup0_se4, qup0_se5, qup0_se6, qup0_se7, qup1_se0, qup1_se1,
+                qup1_se2, qup1_se3, qup1_se4, qup1_se5, qup1_se6, qup1_se7,
+                qup2_se0, sailss_emac0, sailss_ospi, sail_top, sgmii_phy,
+                tb_trig, tgu_ch0, tgu_ch1, tgu_ch2, tgu_ch3, tsense_pwm1,
+                tsense_pwm2, tsense_pwm3, tsense_pwm4, usb2phy_ac,
+                vsense_trigger ]
+
+    required:
+      - pins
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    tlmm: pinctrl@f100000 {
+        compatible = "qcom,qcs8300-tlmm";
+        reg = <0x0f100000 0x300000>;
+        interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
+        gpio-controller;
+        #gpio-cells = <2>;
+        gpio-ranges = <&tlmm 0 0 133>;
+        interrupt-controller;
+        #interrupt-cells = <2>;
+
+        qup-uart7-state {
+            pins = "gpio43", "gpio44";
+            function = "qup0_se7";
+        };
+    };
+...

From 0c4cd2cc87c848848c23e0d82e40c4bff8f458c3 Mon Sep 17 00:00:00 2001
From: Jingyi Wang <quic_jingyw@quicinc.com>
Date: Fri, 18 Oct 2024 11:19:32 +0800
Subject: [PATCH 0583/1530] pinctrl: qcom: add the tlmm driver for QCS8300
 platforms

Add support for QCS8300 TLMM configuration and control via the
pinctrl framework.

Signed-off-by: Jingyi Wang <quic_jingyw@quicinc.com>
Link: https://lore.kernel.org/20241018-qcs8300_tlmm-v3-2-8b8d3957cf1a@quicinc.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/Kconfig.msm       |    7 +
 drivers/pinctrl/qcom/Makefile          |    1 +
 drivers/pinctrl/qcom/pinctrl-qcs8300.c | 1246 ++++++++++++++++++++++++
 3 files changed, 1254 insertions(+)
 create mode 100644 drivers/pinctrl/qcom/pinctrl-qcs8300.c

diff --git a/drivers/pinctrl/qcom/Kconfig.msm b/drivers/pinctrl/qcom/Kconfig.msm
index c79f0c3c873da..c5d67539f5c91 100644
--- a/drivers/pinctrl/qcom/Kconfig.msm
+++ b/drivers/pinctrl/qcom/Kconfig.msm
@@ -198,6 +198,13 @@ config PINCTRL_QCS615
 	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
 	  TLMM block found on the Qualcomm QCS615 platform.
 
+config PINCTRL_QCS8300
+	tristate "Qualcomm Technologies QCS8300 pin controller driver"
+	depends on ARM64 || COMPILE_TEST
+	help
+	  This is the pinctrl, pinmux and pinconf driver for the Qualcomm
+	  TLMM block found on the Qualcomm QCS8300 platform.
+
 config PINCTRL_QDF2XXX
 	tristate "Qualcomm Technologies QDF2xxx pin controller driver"
 	depends on ACPI
diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile
index 715c3b5a636ad..7c8385e69e90f 100644
--- a/drivers/pinctrl/qcom/Makefile
+++ b/drivers/pinctrl/qcom/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_PINCTRL_MSM8998)   += pinctrl-msm8998.o
 obj-$(CONFIG_PINCTRL_QCM2290)	+= pinctrl-qcm2290.o
 obj-$(CONFIG_PINCTRL_QCS404)	+= pinctrl-qcs404.o
 obj-$(CONFIG_PINCTRL_QCS615)    += pinctrl-qcs615.o
+obj-$(CONFIG_PINCTRL_QCS8300)	+= pinctrl-qcs8300.o
 obj-$(CONFIG_PINCTRL_QDF2XXX)	+= pinctrl-qdf2xxx.o
 obj-$(CONFIG_PINCTRL_MDM9607)	+= pinctrl-mdm9607.o
 obj-$(CONFIG_PINCTRL_MDM9615)	+= pinctrl-mdm9615.o
diff --git a/drivers/pinctrl/qcom/pinctrl-qcs8300.c b/drivers/pinctrl/qcom/pinctrl-qcs8300.c
new file mode 100644
index 0000000000000..ba6de944a859a
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-qcs8300.c
@@ -0,0 +1,1246 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-msm.h"
+
+#define REG_SIZE 0x1000
+#define PINGROUP(id, f1, f2, f3, f4, f5, f6, f7, f8, f9, f10, f11)\
+	{						\
+		.grp = PINCTRL_PINGROUP("gpio" #id,	\
+			gpio##id##_pins,		\
+			ARRAY_SIZE(gpio##id##_pins)),	\
+		.funcs = (int[]){			\
+			msm_mux_gpio, /* gpio mode */	\
+			msm_mux_##f1,			\
+			msm_mux_##f2,			\
+			msm_mux_##f3,			\
+			msm_mux_##f4,			\
+			msm_mux_##f5,			\
+			msm_mux_##f6,			\
+			msm_mux_##f7,			\
+			msm_mux_##f8,			\
+			msm_mux_##f9,			\
+			msm_mux_##f10,			\
+			msm_mux_##f11 /* egpio mode */	\
+		},					\
+		.nfuncs = 12,				\
+		.ctl_reg = REG_SIZE * id,		\
+		.io_reg = 0x4 + REG_SIZE * id,		\
+		.intr_cfg_reg = 0x8 + REG_SIZE * id,	\
+		.intr_status_reg = 0xc + REG_SIZE * id,	\
+		.intr_target_reg = 0x8 + REG_SIZE * id,	\
+		.mux_bit = 2,			\
+		.pull_bit = 0,			\
+		.drv_bit = 6,			\
+		.egpio_enable = 12,		\
+		.egpio_present = 11,		\
+		.oe_bit = 9,			\
+		.in_bit = 0,			\
+		.out_bit = 1,			\
+		.intr_enable_bit = 0,		\
+		.intr_status_bit = 0,		\
+		.intr_target_bit = 5,		\
+		.intr_target_kpss_val = 3,	\
+		.intr_raw_status_bit = 4,	\
+		.intr_polarity_bit = 1,		\
+		.intr_detection_bit = 2,	\
+		.intr_detection_width = 2,	\
+	}
+
+#define SDC_QDSD_PINGROUP(pg_name, ctl, pull, drv)	\
+	{						\
+		.grp = PINCTRL_PINGROUP(#pg_name,	\
+			pg_name##_pins,			\
+			ARRAY_SIZE(pg_name##_pins)),	\
+		.ctl_reg = ctl,				\
+		.io_reg = 0,				\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = pull,			\
+		.drv_bit = drv,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = -1,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+#define UFS_RESET(pg_name, offset)			\
+	{						\
+		.grp = PINCTRL_PINGROUP(#pg_name,	\
+			pg_name##_pins,			\
+			ARRAY_SIZE(pg_name##_pins)),	\
+		.ctl_reg = offset,			\
+		.io_reg = offset + 0x4,			\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = 3,				\
+		.drv_bit = 0,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = 0,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+#define QUP_I3C(qup_mode, qup_offset)			\
+	{						\
+		.mode = qup_mode,			\
+		.offset = qup_offset,			\
+	}
+
+#define QUP_I3C_6_MODE_OFFSET	0xaf000
+#define QUP_I3C_7_MODE_OFFSET	0xb0000
+#define QUP_I3C_13_MODE_OFFSET	0xb1000
+#define QUP_I3C_14_MODE_OFFSET	0xb2000
+
+static const struct pinctrl_pin_desc qcs8300_pins[] = {
+	PINCTRL_PIN(0, "GPIO_0"),
+	PINCTRL_PIN(1, "GPIO_1"),
+	PINCTRL_PIN(2, "GPIO_2"),
+	PINCTRL_PIN(3, "GPIO_3"),
+	PINCTRL_PIN(4, "GPIO_4"),
+	PINCTRL_PIN(5, "GPIO_5"),
+	PINCTRL_PIN(6, "GPIO_6"),
+	PINCTRL_PIN(7, "GPIO_7"),
+	PINCTRL_PIN(8, "GPIO_8"),
+	PINCTRL_PIN(9, "GPIO_9"),
+	PINCTRL_PIN(10, "GPIO_10"),
+	PINCTRL_PIN(11, "GPIO_11"),
+	PINCTRL_PIN(12, "GPIO_12"),
+	PINCTRL_PIN(13, "GPIO_13"),
+	PINCTRL_PIN(14, "GPIO_14"),
+	PINCTRL_PIN(15, "GPIO_15"),
+	PINCTRL_PIN(16, "GPIO_16"),
+	PINCTRL_PIN(17, "GPIO_17"),
+	PINCTRL_PIN(18, "GPIO_18"),
+	PINCTRL_PIN(19, "GPIO_19"),
+	PINCTRL_PIN(20, "GPIO_20"),
+	PINCTRL_PIN(21, "GPIO_21"),
+	PINCTRL_PIN(22, "GPIO_22"),
+	PINCTRL_PIN(23, "GPIO_23"),
+	PINCTRL_PIN(24, "GPIO_24"),
+	PINCTRL_PIN(25, "GPIO_25"),
+	PINCTRL_PIN(26, "GPIO_26"),
+	PINCTRL_PIN(27, "GPIO_27"),
+	PINCTRL_PIN(28, "GPIO_28"),
+	PINCTRL_PIN(29, "GPIO_29"),
+	PINCTRL_PIN(30, "GPIO_30"),
+	PINCTRL_PIN(31, "GPIO_31"),
+	PINCTRL_PIN(32, "GPIO_32"),
+	PINCTRL_PIN(33, "GPIO_33"),
+	PINCTRL_PIN(34, "GPIO_34"),
+	PINCTRL_PIN(35, "GPIO_35"),
+	PINCTRL_PIN(36, "GPIO_36"),
+	PINCTRL_PIN(37, "GPIO_37"),
+	PINCTRL_PIN(38, "GPIO_38"),
+	PINCTRL_PIN(39, "GPIO_39"),
+	PINCTRL_PIN(40, "GPIO_40"),
+	PINCTRL_PIN(41, "GPIO_41"),
+	PINCTRL_PIN(42, "GPIO_42"),
+	PINCTRL_PIN(43, "GPIO_43"),
+	PINCTRL_PIN(44, "GPIO_44"),
+	PINCTRL_PIN(45, "GPIO_45"),
+	PINCTRL_PIN(46, "GPIO_46"),
+	PINCTRL_PIN(47, "GPIO_47"),
+	PINCTRL_PIN(48, "GPIO_48"),
+	PINCTRL_PIN(49, "GPIO_49"),
+	PINCTRL_PIN(50, "GPIO_50"),
+	PINCTRL_PIN(51, "GPIO_51"),
+	PINCTRL_PIN(52, "GPIO_52"),
+	PINCTRL_PIN(53, "GPIO_53"),
+	PINCTRL_PIN(54, "GPIO_54"),
+	PINCTRL_PIN(55, "GPIO_55"),
+	PINCTRL_PIN(56, "GPIO_56"),
+	PINCTRL_PIN(57, "GPIO_57"),
+	PINCTRL_PIN(58, "GPIO_58"),
+	PINCTRL_PIN(59, "GPIO_59"),
+	PINCTRL_PIN(60, "GPIO_60"),
+	PINCTRL_PIN(61, "GPIO_61"),
+	PINCTRL_PIN(62, "GPIO_62"),
+	PINCTRL_PIN(63, "GPIO_63"),
+	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
+	PINCTRL_PIN(69, "GPIO_69"),
+	PINCTRL_PIN(70, "GPIO_70"),
+	PINCTRL_PIN(71, "GPIO_71"),
+	PINCTRL_PIN(72, "GPIO_72"),
+	PINCTRL_PIN(73, "GPIO_73"),
+	PINCTRL_PIN(74, "GPIO_74"),
+	PINCTRL_PIN(75, "GPIO_75"),
+	PINCTRL_PIN(76, "GPIO_76"),
+	PINCTRL_PIN(77, "GPIO_77"),
+	PINCTRL_PIN(78, "GPIO_78"),
+	PINCTRL_PIN(79, "GPIO_79"),
+	PINCTRL_PIN(80, "GPIO_80"),
+	PINCTRL_PIN(81, "GPIO_81"),
+	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
+	PINCTRL_PIN(86, "GPIO_86"),
+	PINCTRL_PIN(87, "GPIO_87"),
+	PINCTRL_PIN(88, "GPIO_88"),
+	PINCTRL_PIN(89, "GPIO_89"),
+	PINCTRL_PIN(90, "GPIO_90"),
+	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93"),
+	PINCTRL_PIN(94, "GPIO_94"),
+	PINCTRL_PIN(95, "GPIO_95"),
+	PINCTRL_PIN(96, "GPIO_96"),
+	PINCTRL_PIN(97, "GPIO_97"),
+	PINCTRL_PIN(98, "GPIO_98"),
+	PINCTRL_PIN(99, "GPIO_99"),
+	PINCTRL_PIN(100, "GPIO_100"),
+	PINCTRL_PIN(101, "GPIO_101"),
+	PINCTRL_PIN(102, "GPIO_102"),
+	PINCTRL_PIN(103, "GPIO_103"),
+	PINCTRL_PIN(104, "GPIO_104"),
+	PINCTRL_PIN(105, "GPIO_105"),
+	PINCTRL_PIN(106, "GPIO_106"),
+	PINCTRL_PIN(107, "GPIO_107"),
+	PINCTRL_PIN(108, "GPIO_108"),
+	PINCTRL_PIN(109, "GPIO_109"),
+	PINCTRL_PIN(110, "GPIO_110"),
+	PINCTRL_PIN(111, "GPIO_111"),
+	PINCTRL_PIN(112, "GPIO_112"),
+	PINCTRL_PIN(113, "GPIO_113"),
+	PINCTRL_PIN(114, "GPIO_114"),
+	PINCTRL_PIN(115, "GPIO_115"),
+	PINCTRL_PIN(116, "GPIO_116"),
+	PINCTRL_PIN(117, "GPIO_117"),
+	PINCTRL_PIN(118, "GPIO_118"),
+	PINCTRL_PIN(119, "GPIO_119"),
+	PINCTRL_PIN(120, "GPIO_120"),
+	PINCTRL_PIN(121, "GPIO_121"),
+	PINCTRL_PIN(122, "GPIO_122"),
+	PINCTRL_PIN(123, "GPIO_123"),
+	PINCTRL_PIN(124, "GPIO_124"),
+	PINCTRL_PIN(125, "GPIO_125"),
+	PINCTRL_PIN(126, "GPIO_126"),
+	PINCTRL_PIN(127, "GPIO_127"),
+	PINCTRL_PIN(128, "GPIO_128"),
+	PINCTRL_PIN(129, "GPIO_129"),
+	PINCTRL_PIN(130, "GPIO_130"),
+	PINCTRL_PIN(131, "GPIO_131"),
+	PINCTRL_PIN(132, "GPIO_132"),
+	PINCTRL_PIN(133, "UFS_RESET"),
+	PINCTRL_PIN(134, "SDC1_RCLK"),
+	PINCTRL_PIN(135, "SDC1_CLK"),
+	PINCTRL_PIN(136, "SDC1_CMD"),
+	PINCTRL_PIN(137, "SDC1_DATA"),
+};
+
+#define DECLARE_MSM_GPIO_PINS(pin) \
+	static const unsigned int gpio##pin##_pins[] = { pin }
+DECLARE_MSM_GPIO_PINS(0);
+DECLARE_MSM_GPIO_PINS(1);
+DECLARE_MSM_GPIO_PINS(2);
+DECLARE_MSM_GPIO_PINS(3);
+DECLARE_MSM_GPIO_PINS(4);
+DECLARE_MSM_GPIO_PINS(5);
+DECLARE_MSM_GPIO_PINS(6);
+DECLARE_MSM_GPIO_PINS(7);
+DECLARE_MSM_GPIO_PINS(8);
+DECLARE_MSM_GPIO_PINS(9);
+DECLARE_MSM_GPIO_PINS(10);
+DECLARE_MSM_GPIO_PINS(11);
+DECLARE_MSM_GPIO_PINS(12);
+DECLARE_MSM_GPIO_PINS(13);
+DECLARE_MSM_GPIO_PINS(14);
+DECLARE_MSM_GPIO_PINS(15);
+DECLARE_MSM_GPIO_PINS(16);
+DECLARE_MSM_GPIO_PINS(17);
+DECLARE_MSM_GPIO_PINS(18);
+DECLARE_MSM_GPIO_PINS(19);
+DECLARE_MSM_GPIO_PINS(20);
+DECLARE_MSM_GPIO_PINS(21);
+DECLARE_MSM_GPIO_PINS(22);
+DECLARE_MSM_GPIO_PINS(23);
+DECLARE_MSM_GPIO_PINS(24);
+DECLARE_MSM_GPIO_PINS(25);
+DECLARE_MSM_GPIO_PINS(26);
+DECLARE_MSM_GPIO_PINS(27);
+DECLARE_MSM_GPIO_PINS(28);
+DECLARE_MSM_GPIO_PINS(29);
+DECLARE_MSM_GPIO_PINS(30);
+DECLARE_MSM_GPIO_PINS(31);
+DECLARE_MSM_GPIO_PINS(32);
+DECLARE_MSM_GPIO_PINS(33);
+DECLARE_MSM_GPIO_PINS(34);
+DECLARE_MSM_GPIO_PINS(35);
+DECLARE_MSM_GPIO_PINS(36);
+DECLARE_MSM_GPIO_PINS(37);
+DECLARE_MSM_GPIO_PINS(38);
+DECLARE_MSM_GPIO_PINS(39);
+DECLARE_MSM_GPIO_PINS(40);
+DECLARE_MSM_GPIO_PINS(41);
+DECLARE_MSM_GPIO_PINS(42);
+DECLARE_MSM_GPIO_PINS(43);
+DECLARE_MSM_GPIO_PINS(44);
+DECLARE_MSM_GPIO_PINS(45);
+DECLARE_MSM_GPIO_PINS(46);
+DECLARE_MSM_GPIO_PINS(47);
+DECLARE_MSM_GPIO_PINS(48);
+DECLARE_MSM_GPIO_PINS(49);
+DECLARE_MSM_GPIO_PINS(50);
+DECLARE_MSM_GPIO_PINS(51);
+DECLARE_MSM_GPIO_PINS(52);
+DECLARE_MSM_GPIO_PINS(53);
+DECLARE_MSM_GPIO_PINS(54);
+DECLARE_MSM_GPIO_PINS(55);
+DECLARE_MSM_GPIO_PINS(56);
+DECLARE_MSM_GPIO_PINS(57);
+DECLARE_MSM_GPIO_PINS(58);
+DECLARE_MSM_GPIO_PINS(59);
+DECLARE_MSM_GPIO_PINS(60);
+DECLARE_MSM_GPIO_PINS(61);
+DECLARE_MSM_GPIO_PINS(62);
+DECLARE_MSM_GPIO_PINS(63);
+DECLARE_MSM_GPIO_PINS(64);
+DECLARE_MSM_GPIO_PINS(65);
+DECLARE_MSM_GPIO_PINS(66);
+DECLARE_MSM_GPIO_PINS(67);
+DECLARE_MSM_GPIO_PINS(68);
+DECLARE_MSM_GPIO_PINS(69);
+DECLARE_MSM_GPIO_PINS(70);
+DECLARE_MSM_GPIO_PINS(71);
+DECLARE_MSM_GPIO_PINS(72);
+DECLARE_MSM_GPIO_PINS(73);
+DECLARE_MSM_GPIO_PINS(74);
+DECLARE_MSM_GPIO_PINS(75);
+DECLARE_MSM_GPIO_PINS(76);
+DECLARE_MSM_GPIO_PINS(77);
+DECLARE_MSM_GPIO_PINS(78);
+DECLARE_MSM_GPIO_PINS(79);
+DECLARE_MSM_GPIO_PINS(80);
+DECLARE_MSM_GPIO_PINS(81);
+DECLARE_MSM_GPIO_PINS(82);
+DECLARE_MSM_GPIO_PINS(83);
+DECLARE_MSM_GPIO_PINS(84);
+DECLARE_MSM_GPIO_PINS(85);
+DECLARE_MSM_GPIO_PINS(86);
+DECLARE_MSM_GPIO_PINS(87);
+DECLARE_MSM_GPIO_PINS(88);
+DECLARE_MSM_GPIO_PINS(89);
+DECLARE_MSM_GPIO_PINS(90);
+DECLARE_MSM_GPIO_PINS(91);
+DECLARE_MSM_GPIO_PINS(92);
+DECLARE_MSM_GPIO_PINS(93);
+DECLARE_MSM_GPIO_PINS(94);
+DECLARE_MSM_GPIO_PINS(95);
+DECLARE_MSM_GPIO_PINS(96);
+DECLARE_MSM_GPIO_PINS(97);
+DECLARE_MSM_GPIO_PINS(98);
+DECLARE_MSM_GPIO_PINS(99);
+DECLARE_MSM_GPIO_PINS(100);
+DECLARE_MSM_GPIO_PINS(101);
+DECLARE_MSM_GPIO_PINS(102);
+DECLARE_MSM_GPIO_PINS(103);
+DECLARE_MSM_GPIO_PINS(104);
+DECLARE_MSM_GPIO_PINS(105);
+DECLARE_MSM_GPIO_PINS(106);
+DECLARE_MSM_GPIO_PINS(107);
+DECLARE_MSM_GPIO_PINS(108);
+DECLARE_MSM_GPIO_PINS(109);
+DECLARE_MSM_GPIO_PINS(110);
+DECLARE_MSM_GPIO_PINS(111);
+DECLARE_MSM_GPIO_PINS(112);
+DECLARE_MSM_GPIO_PINS(113);
+DECLARE_MSM_GPIO_PINS(114);
+DECLARE_MSM_GPIO_PINS(115);
+DECLARE_MSM_GPIO_PINS(116);
+DECLARE_MSM_GPIO_PINS(117);
+DECLARE_MSM_GPIO_PINS(118);
+DECLARE_MSM_GPIO_PINS(119);
+DECLARE_MSM_GPIO_PINS(120);
+DECLARE_MSM_GPIO_PINS(121);
+DECLARE_MSM_GPIO_PINS(122);
+DECLARE_MSM_GPIO_PINS(123);
+DECLARE_MSM_GPIO_PINS(124);
+DECLARE_MSM_GPIO_PINS(125);
+DECLARE_MSM_GPIO_PINS(126);
+DECLARE_MSM_GPIO_PINS(127);
+DECLARE_MSM_GPIO_PINS(128);
+DECLARE_MSM_GPIO_PINS(129);
+DECLARE_MSM_GPIO_PINS(130);
+DECLARE_MSM_GPIO_PINS(131);
+DECLARE_MSM_GPIO_PINS(132);
+
+static const unsigned int ufs_reset_pins[] = { 133 };
+static const unsigned int sdc1_rclk_pins[] = { 134 };
+static const unsigned int sdc1_clk_pins[]  = { 135 };
+static const unsigned int sdc1_cmd_pins[]  = { 136 };
+static const unsigned int sdc1_data_pins[] = { 137 };
+
+enum qcs8300_functions {
+	msm_mux_gpio,
+	msm_mux_aoss_cti,
+	msm_mux_atest_char,
+	msm_mux_atest_usb2,
+	msm_mux_audio_ref,
+	msm_mux_cam_mclk,
+	msm_mux_cci_async,
+	msm_mux_cci_i2c_scl,
+	msm_mux_cci_i2c_sda,
+	msm_mux_cci_timer,
+	msm_mux_cri_trng,
+	msm_mux_dbg_out,
+	msm_mux_ddr_bist,
+	msm_mux_ddr_pxi0,
+	msm_mux_ddr_pxi1,
+	msm_mux_ddr_pxi2,
+	msm_mux_ddr_pxi3,
+	msm_mux_edp0_hot,
+	msm_mux_edp0_lcd,
+	msm_mux_edp1_lcd,
+	msm_mux_egpio,
+	msm_mux_emac0_mcg0,
+	msm_mux_emac0_mcg1,
+	msm_mux_emac0_mcg2,
+	msm_mux_emac0_mcg3,
+	msm_mux_emac0_mdc,
+	msm_mux_emac0_mdio,
+	msm_mux_emac0_ptp_aux,
+	msm_mux_emac0_ptp_pps,
+	msm_mux_gcc_gp1,
+	msm_mux_gcc_gp2,
+	msm_mux_gcc_gp3,
+	msm_mux_gcc_gp4,
+	msm_mux_gcc_gp5,
+	msm_mux_hs0_mi2s,
+	msm_mux_hs1_mi2s,
+	msm_mux_hs2_mi2s,
+	msm_mux_ibi_i3c,
+	msm_mux_jitter_bist,
+	msm_mux_mdp0_vsync0,
+	msm_mux_mdp0_vsync1,
+	msm_mux_mdp0_vsync3,
+	msm_mux_mdp0_vsync6,
+	msm_mux_mdp0_vsync7,
+	msm_mux_mdp_vsync,
+	msm_mux_mi2s1_data0,
+	msm_mux_mi2s1_data1,
+	msm_mux_mi2s1_sck,
+	msm_mux_mi2s1_ws,
+	msm_mux_mi2s2_data0,
+	msm_mux_mi2s2_data1,
+	msm_mux_mi2s2_sck,
+	msm_mux_mi2s2_ws,
+	msm_mux_mi2s_mclk0,
+	msm_mux_mi2s_mclk1,
+	msm_mux_pcie0_clkreq,
+	msm_mux_pcie1_clkreq,
+	msm_mux_phase_flag,
+	msm_mux_pll_bist,
+	msm_mux_pll_clk,
+	msm_mux_prng_rosc0,
+	msm_mux_prng_rosc1,
+	msm_mux_prng_rosc2,
+	msm_mux_prng_rosc3,
+	msm_mux_qdss_cti,
+	msm_mux_qdss_gpio,
+	msm_mux_qup0_se0,
+	msm_mux_qup0_se1,
+	msm_mux_qup0_se2,
+	msm_mux_qup0_se3,
+	msm_mux_qup0_se4,
+	msm_mux_qup0_se5,
+	msm_mux_qup0_se6,
+	msm_mux_qup0_se7,
+	msm_mux_qup1_se0,
+	msm_mux_qup1_se1,
+	msm_mux_qup1_se2,
+	msm_mux_qup1_se3,
+	msm_mux_qup1_se4,
+	msm_mux_qup1_se5,
+	msm_mux_qup1_se6,
+	msm_mux_qup1_se7,
+	msm_mux_qup2_se0,
+	msm_mux_sailss_emac0,
+	msm_mux_sailss_ospi,
+	msm_mux_sgmii_phy,
+	msm_mux_tb_trig,
+	msm_mux_tgu_ch0,
+	msm_mux_tgu_ch1,
+	msm_mux_tgu_ch2,
+	msm_mux_tgu_ch3,
+	msm_mux_tsense_pwm1,
+	msm_mux_tsense_pwm2,
+	msm_mux_tsense_pwm3,
+	msm_mux_tsense_pwm4,
+	msm_mux_usb2phy_ac,
+	msm_mux_vsense_trigger,
+	msm_mux__,
+};
+
+static const char * const gpio_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7",
+	"gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14",
+	"gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21",
+	"gpio22", "gpio23", "gpio24", "gpio25", "gpio26", "gpio27", "gpio28",
+	"gpio29", "gpio30", "gpio31", "gpio32", "gpio33", "gpio34", "gpio35",
+	"gpio36", "gpio37", "gpio38", "gpio39", "gpio40", "gpio41", "gpio42",
+	"gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48", "gpio49",
+	"gpio50", "gpio51", "gpio52", "gpio53", "gpio54", "gpio55", "gpio56",
+	"gpio57", "gpio58", "gpio59", "gpio60", "gpio61", "gpio62", "gpio63",
+	"gpio64", "gpio65", "gpio66", "gpio67", "gpio68", "gpio69", "gpio70",
+	"gpio71", "gpio72", "gpio73", "gpio74", "gpio75", "gpio76", "gpio77",
+	"gpio78", "gpio79", "gpio80", "gpio81", "gpio82", "gpio83", "gpio84",
+	"gpio85", "gpio86", "gpio87", "gpio88", "gpio89", "gpio90", "gpio91",
+	"gpio92", "gpio93", "gpio94", "gpio95", "gpio96", "gpio97", "gpio98",
+	"gpio99", "gpio100", "gpio101", "gpio102", "gpio103", "gpio104",
+	"gpio105", "gpio106", "gpio107", "gpio108", "gpio109", "gpio110",
+	"gpio111", "gpio112", "gpio113", "gpio114", "gpio115", "gpio116",
+	"gpio117", "gpio118", "gpio119", "gpio120", "gpio121", "gpio122",
+	"gpio123", "gpio124", "gpio125", "gpio126", "gpio127", "gpio128",
+	"gpio129", "gpio130", "gpio131", "gpio132",
+};
+
+static const char *const aoss_cti_groups[] = {
+	"gpio37", "gpio38", "gpio39", "gpio40",
+};
+
+static const char * const atest_char_groups[] = {
+	"gpio66", "gpio70", "gpio71", "gpio72", "gpio93",
+};
+
+static const char * const atest_usb2_groups[] = {
+	"gpio63", "gpio83", "gpio92", "gpio74", "gpio84", "gpio87", "gpio67",
+	"gpio75", "gpio85", "gpio65", "gpio68", "gpio80", "gpio64", "gpio69",
+	"gpio81",
+};
+
+static const char * const audio_ref_groups[] = {
+	"gpio105",
+};
+
+static const char * const cam_mclk_groups[] = {
+	"gpio67", "gpio68", "gpio69",
+};
+
+static const char * const cci_async_groups[] = {
+	"gpio63", "gpio64", "gpio65", "gpio29", "gpio30", "gpio31",
+};
+
+static const char * const cci_i2c_scl_groups[] = {
+	"gpio58", "gpio30", "gpio60", "gpio32", "gpio62", "gpio55",
+};
+
+static const char * const cci_i2c_sda_groups[] = {
+	"gpio57", "gpio29", "gpio59", "gpio31", "gpio61", "gpio54",
+};
+
+static const char *const cci_timer_groups[] = {
+	"gpio63", "gpio64", "gpio65", "gpio49", "gpio50", "gpio19",
+	"gpio20", "gpio21", "gpio22", "gpio23",
+};
+
+static const char *const cri_trng_groups[] = {
+	"gpio92", "gpio90", "gpio91",
+};
+
+static const char *const dbg_out_groups[] = {
+	"gpio75",
+};
+
+static const char * const ddr_bist_groups[] = {
+	"gpio53", "gpio54", "gpio55", "gpio56",
+};
+
+static const char *const ddr_pxi0_groups[] = {
+	"gpio68", "gpio69",
+};
+
+static const char *const ddr_pxi1_groups[] = {
+	"gpio49", "gpio50",
+};
+
+static const char *const ddr_pxi2_groups[] = {
+	"gpio52", "gpio83",
+};
+
+static const char *const ddr_pxi3_groups[] = {
+	"gpio80", "gpio81",
+};
+
+static const char *const edp0_hot_groups[] = {
+	"gpio94",
+};
+
+static const char *const edp0_lcd_groups[] = {
+	"gpio48",
+};
+
+static const char *const edp1_lcd_groups[] = {
+	"gpio49",
+};
+
+static const char *const egpio_groups[] = {
+	"gpio110", "gpio111", "gpio112", "gpio113", "gpio114", "gpio115",
+	"gpio116", "gpio117", "gpio118", "gpio119", "gpio120", "gpio121",
+	"gpio122", "gpio123", "gpio124", "gpio125", "gpio126", "gpio127",
+	"gpio128", "gpio129", "gpio130", "gpio131", "gpio132",
+};
+
+static const char *const emac0_mcg0_groups[] = {
+	"gpio10",
+};
+
+static const char *const emac0_mcg1_groups[] = {
+	"gpio11",
+};
+
+static const char *const emac0_mcg2_groups[] = {
+	"gpio24",
+};
+
+static const char *const emac0_mcg3_groups[] = {
+	"gpio79",
+};
+
+static const char *const emac0_mdc_groups[] = {
+	"gpio5",
+};
+
+static const char *const emac0_mdio_groups[] = {
+	"gpio6",
+};
+
+static const char * const emac0_ptp_aux_groups[] = {
+	"gpio24", "gpio31", "gpio32", "gpio79",
+};
+
+static const char * const emac0_ptp_pps_groups[] = {
+	"gpio24", "gpio29", "gpio30", "gpio79",
+};
+
+static const char *const gcc_gp1_groups[] = {
+	"gpio35", "gpio84",
+};
+
+static const char *const gcc_gp2_groups[] = {
+	"gpio36", "gpio81",
+};
+
+static const char *const gcc_gp3_groups[] = {
+	"gpio69", "gpio82",
+};
+
+static const char *const gcc_gp4_groups[] = {
+	"gpio68", "gpio83",
+};
+
+static const char *const gcc_gp5_groups[] = {
+	"gpio76", "gpio77",
+};
+
+static const char * const hs0_mi2s_groups[] = {
+	"gpio106", "gpio107", "gpio108", "gpio109",
+};
+
+static const char * const hs1_mi2s_groups[] = {
+	"gpio45", "gpio46", "gpio47", "gpio48",
+};
+
+static const char * const hs2_mi2s_groups[] = {
+	"gpio49", "gpio50", "gpio51", "gpio52",
+};
+
+static const char * const ibi_i3c_groups[] = {
+	"gpio17", "gpio18", "gpio19", "gpio20", "gpio37", "gpio38",
+	"gpio39", "gpio40",
+};
+
+static const char *const jitter_bist_groups[] = {
+	"gpio97",
+};
+
+static const char *const mdp0_vsync0_groups[] = {
+	"gpio89",
+};
+
+static const char *const mdp0_vsync1_groups[] = {
+	"gpio90",
+};
+
+static const char *const mdp0_vsync3_groups[] = {
+	"gpio91",
+};
+
+static const char *const mdp0_vsync6_groups[] = {
+	"gpio80",
+};
+
+static const char *const mdp0_vsync7_groups[] = {
+	"gpio81",
+};
+
+static const char *const mdp_vsync_groups[] = {
+	"gpio42", "gpio52", "gpio32",
+};
+
+static const char *const mi2s1_data0_groups[] = {
+	"gpio100",
+};
+
+static const char *const mi2s1_data1_groups[] = {
+	"gpio101",
+};
+
+static const char *const mi2s1_sck_groups[] = {
+	"gpio98",
+};
+
+static const char *const mi2s1_ws_groups[] = {
+	"gpio99",
+};
+
+static const char *const mi2s2_data0_groups[] = {
+	"gpio104",
+};
+
+static const char *const mi2s2_data1_groups[] = {
+	"gpio105",
+};
+
+static const char *const mi2s2_sck_groups[] = {
+	"gpio102",
+};
+
+static const char *const mi2s2_ws_groups[] = {
+	"gpio103",
+};
+
+static const char *const mi2s_mclk0_groups[] = {
+	"gpio97",
+};
+
+static const char *const mi2s_mclk1_groups[] = {
+	"gpio109",
+};
+
+static const char *const pcie0_clkreq_groups[] = {
+	"gpio1",
+};
+
+static const char *const pcie1_clkreq_groups[] = {
+	"gpio22",
+};
+
+static const char *const phase_flag_groups[] = {
+	"gpio66", "gpio56", "gpio118", "gpio117", "gpio116",
+	"gpio3", "gpio114", "gpio113", "gpio112", "gpio111",
+	"gpio110", "gpio28", "gpio55", "gpio108", "gpio107",
+	"gpio106", "gpio105", "gpio104", "gpio103", "gpio102",
+	"gpio101", "gpio100", "gpio99", "gpio125", "gpio98",
+	"gpio54", "gpio25", "gpio26", "gpio122", "gpio121",
+	"gpio120", "gpio9",
+};
+
+static const char *const pll_bist_groups[] = {
+	"gpio107",
+};
+
+static const char *const pll_clk_groups[] = {
+	"gpio74",
+};
+
+static const char *const prng_rosc0_groups[] = {
+	"gpio57",
+};
+
+static const char *const prng_rosc1_groups[] = {
+	"gpio58",
+};
+
+static const char *const prng_rosc2_groups[] = {
+	"gpio59",
+};
+
+static const char *const prng_rosc3_groups[] = {
+	"gpio60",
+};
+
+static const char *const qdss_cti_groups[] = {
+	"gpio4", "gpio5", "gpio23", "gpio24", "gpio49", "gpio50",
+	"gpio51", "gpio52",
+};
+
+static const char *const qdss_gpio_groups[] = {
+	"gpio57", "gpio58", "gpio97", "gpio106",
+	"gpio59", "gpio107", "gpio60", "gpio108",
+	"gpio36", "gpio100", "gpio61", "gpio101",
+	"gpio62", "gpio102", "gpio33", "gpio103",
+	"gpio34", "gpio104", "gpio75", "gpio105",
+	"gpio72", "gpio109", "gpio71", "gpio110",
+	"gpio70", "gpio111", "gpio63", "gpio112",
+	"gpio64", "gpio113", "gpio65", "gpio114",
+	"gpio73", "gpio98", "gpio74", "gpio99",
+};
+
+static const char *const qup0_se0_groups[] = {
+	"gpio17", "gpio18", "gpio19", "gpio20",
+};
+
+static const char *const qup0_se1_groups[] = {
+	"gpio19", "gpio20", "gpio17", "gpio18",
+};
+
+static const char *const qup0_se2_groups[] = {
+	"gpio33", "gpio34", "gpio35", "gpio36",
+};
+
+static const char *const qup0_se3_groups[] = {
+	"gpio25", "gpio26", "gpio27", "gpio28",
+};
+
+static const char *const qup0_se4_groups[] = {
+	"gpio29", "gpio30", "gpio31", "gpio32",
+};
+
+static const char *const qup0_se5_groups[] = {
+	"gpio21", "gpio22", "gpio23", "gpio24",
+};
+
+static const char *const qup0_se6_groups[] = {
+	"gpio80", "gpio81", "gpio82", "gpio83",
+};
+
+static const char *const qup0_se7_groups[] = {
+	"gpio43", "gpio44", "gpio43", "gpio44",
+};
+
+static const char *const qup1_se0_groups[] = {
+	"gpio37", "gpio38", "gpio39", "gpio40",
+};
+
+static const char *const qup1_se1_groups[] = {
+	"gpio39", "gpio40", "gpio37", "gpio38",
+};
+
+static const char *const qup1_se2_groups[] = {
+	"gpio84", "gpio85", "gpio86", "gpio87", "gpio88",
+};
+
+static const char *const qup1_se3_groups[] = {
+	"gpio41", "gpio42", "gpio41", "gpio42",
+};
+
+static const char *const qup1_se4_groups[] = {
+	"gpio45", "gpio46", "gpio47", "gpio48",
+};
+
+static const char *const qup1_se5_groups[] = {
+	"gpio49", "gpio50", "gpio51", "gpio52",
+};
+
+static const char *const qup1_se6_groups[] = {
+	"gpio89", "gpio90", "gpio91", "gpio92",
+};
+
+static const char *const qup1_se7_groups[] = {
+	"gpio91", "gpio92", "gpio89", "gpio90",
+};
+
+static const char *const qup2_se0_groups[] = {
+	"gpio10", "gpio11", "gpio12", "gpio13",
+	"gpio14", "gpio15", "gpio16",
+};
+
+static const char *const sailss_emac0_groups[] = {
+	"gpio15", "gpio16",
+};
+
+static const char *const sailss_ospi_groups[] = {
+	"gpio15", "gpio16",
+};
+
+static const char *const sgmii_phy_groups[] = {
+	"gpio4",
+};
+
+static const char *const tb_trig_groups[] = {
+	"gpio14",
+};
+
+static const char *const tgu_ch0_groups[] = {
+	"gpio43",
+};
+
+static const char *const tgu_ch1_groups[] = {
+	"gpio44",
+};
+
+static const char *const tgu_ch2_groups[] = {
+	"gpio29",
+};
+
+static const char *const tgu_ch3_groups[] = {
+	"gpio30",
+};
+
+static const char *const tsense_pwm1_groups[] = {
+	"gpio79",
+};
+
+static const char *const tsense_pwm2_groups[] = {
+	"gpio78",
+};
+
+static const char *const tsense_pwm3_groups[] = {
+	"gpio77",
+};
+
+static const char *const tsense_pwm4_groups[] = {
+	"gpio76",
+};
+
+static const char *const usb2phy_ac_groups[] = {
+	"gpio7", "gpio8",
+};
+
+static const char *const vsense_trigger_groups[] = {
+	"gpio67",
+};
+
+static const struct pinfunction qcs8300_functions[] = {
+	MSM_PIN_FUNCTION(gpio),
+	MSM_PIN_FUNCTION(aoss_cti),
+	MSM_PIN_FUNCTION(atest_char),
+	MSM_PIN_FUNCTION(atest_usb2),
+	MSM_PIN_FUNCTION(audio_ref),
+	MSM_PIN_FUNCTION(cam_mclk),
+	MSM_PIN_FUNCTION(cci_async),
+	MSM_PIN_FUNCTION(cci_i2c_scl),
+	MSM_PIN_FUNCTION(cci_i2c_sda),
+	MSM_PIN_FUNCTION(cci_timer),
+	MSM_PIN_FUNCTION(cri_trng),
+	MSM_PIN_FUNCTION(dbg_out),
+	MSM_PIN_FUNCTION(ddr_bist),
+	MSM_PIN_FUNCTION(ddr_pxi0),
+	MSM_PIN_FUNCTION(ddr_pxi1),
+	MSM_PIN_FUNCTION(ddr_pxi2),
+	MSM_PIN_FUNCTION(ddr_pxi3),
+	MSM_PIN_FUNCTION(edp0_hot),
+	MSM_PIN_FUNCTION(edp0_lcd),
+	MSM_PIN_FUNCTION(edp1_lcd),
+	MSM_PIN_FUNCTION(egpio),
+	MSM_PIN_FUNCTION(emac0_mcg0),
+	MSM_PIN_FUNCTION(emac0_mcg1),
+	MSM_PIN_FUNCTION(emac0_mcg2),
+	MSM_PIN_FUNCTION(emac0_mcg3),
+	MSM_PIN_FUNCTION(emac0_mdc),
+	MSM_PIN_FUNCTION(emac0_mdio),
+	MSM_PIN_FUNCTION(emac0_ptp_aux),
+	MSM_PIN_FUNCTION(emac0_ptp_pps),
+	MSM_PIN_FUNCTION(gcc_gp1),
+	MSM_PIN_FUNCTION(gcc_gp2),
+	MSM_PIN_FUNCTION(gcc_gp3),
+	MSM_PIN_FUNCTION(gcc_gp4),
+	MSM_PIN_FUNCTION(gcc_gp5),
+	MSM_PIN_FUNCTION(hs0_mi2s),
+	MSM_PIN_FUNCTION(hs1_mi2s),
+	MSM_PIN_FUNCTION(hs2_mi2s),
+	MSM_PIN_FUNCTION(ibi_i3c),
+	MSM_PIN_FUNCTION(jitter_bist),
+	MSM_PIN_FUNCTION(mdp0_vsync0),
+	MSM_PIN_FUNCTION(mdp0_vsync1),
+	MSM_PIN_FUNCTION(mdp0_vsync3),
+	MSM_PIN_FUNCTION(mdp0_vsync6),
+	MSM_PIN_FUNCTION(mdp0_vsync7),
+	MSM_PIN_FUNCTION(mdp_vsync),
+	MSM_PIN_FUNCTION(mi2s1_data0),
+	MSM_PIN_FUNCTION(mi2s1_data1),
+	MSM_PIN_FUNCTION(mi2s1_sck),
+	MSM_PIN_FUNCTION(mi2s1_ws),
+	MSM_PIN_FUNCTION(mi2s2_data0),
+	MSM_PIN_FUNCTION(mi2s2_data1),
+	MSM_PIN_FUNCTION(mi2s2_sck),
+	MSM_PIN_FUNCTION(mi2s2_ws),
+	MSM_PIN_FUNCTION(mi2s_mclk0),
+	MSM_PIN_FUNCTION(mi2s_mclk1),
+	MSM_PIN_FUNCTION(pcie0_clkreq),
+	MSM_PIN_FUNCTION(pcie1_clkreq),
+	MSM_PIN_FUNCTION(phase_flag),
+	MSM_PIN_FUNCTION(pll_bist),
+	MSM_PIN_FUNCTION(pll_clk),
+	MSM_PIN_FUNCTION(prng_rosc0),
+	MSM_PIN_FUNCTION(prng_rosc1),
+	MSM_PIN_FUNCTION(prng_rosc2),
+	MSM_PIN_FUNCTION(prng_rosc3),
+	MSM_PIN_FUNCTION(qdss_cti),
+	MSM_PIN_FUNCTION(qdss_gpio),
+	MSM_PIN_FUNCTION(qup0_se0),
+	MSM_PIN_FUNCTION(qup0_se1),
+	MSM_PIN_FUNCTION(qup0_se2),
+	MSM_PIN_FUNCTION(qup0_se3),
+	MSM_PIN_FUNCTION(qup0_se4),
+	MSM_PIN_FUNCTION(qup0_se5),
+	MSM_PIN_FUNCTION(qup0_se6),
+	MSM_PIN_FUNCTION(qup0_se7),
+	MSM_PIN_FUNCTION(qup1_se0),
+	MSM_PIN_FUNCTION(qup1_se1),
+	MSM_PIN_FUNCTION(qup1_se2),
+	MSM_PIN_FUNCTION(qup1_se3),
+	MSM_PIN_FUNCTION(qup1_se4),
+	MSM_PIN_FUNCTION(qup1_se5),
+	MSM_PIN_FUNCTION(qup1_se6),
+	MSM_PIN_FUNCTION(qup1_se7),
+	MSM_PIN_FUNCTION(qup2_se0),
+	MSM_PIN_FUNCTION(sailss_emac0),
+	MSM_PIN_FUNCTION(sailss_ospi),
+	MSM_PIN_FUNCTION(sgmii_phy),
+	MSM_PIN_FUNCTION(tb_trig),
+	MSM_PIN_FUNCTION(tgu_ch0),
+	MSM_PIN_FUNCTION(tgu_ch1),
+	MSM_PIN_FUNCTION(tgu_ch2),
+	MSM_PIN_FUNCTION(tgu_ch3),
+	MSM_PIN_FUNCTION(tsense_pwm1),
+	MSM_PIN_FUNCTION(tsense_pwm2),
+	MSM_PIN_FUNCTION(tsense_pwm3),
+	MSM_PIN_FUNCTION(tsense_pwm4),
+	MSM_PIN_FUNCTION(usb2phy_ac),
+	MSM_PIN_FUNCTION(vsense_trigger),
+};
+
+/*
+ * Every pin is maintained as a single group, and missing or non-existing pin
+ * would be maintained as dummy group to synchronize pin group index with
+ * pin descriptor registered with pinctrl core.
+ * Clients would not be able to request these dummy pin groups.
+ */
+static const struct msm_pingroup qcs8300_groups[] = {
+	[0] = PINGROUP(0, _, _, _, _, _, _, _, _, _, _, _),
+	[1] = PINGROUP(1, pcie0_clkreq, _, _, _, _, _, _, _, _, _, _),
+	[2] = PINGROUP(2, _, _, _, _, _, _, _, _, _, _, _),
+	[3] = PINGROUP(3, phase_flag, _, _, _, _, _, _, _, _, _, _),
+	[4] = PINGROUP(4, sgmii_phy, qdss_cti, _, _, _, _, _, _, _, _, _),
+	[5] = PINGROUP(5, emac0_mdc, qdss_cti, _, _, _, _, _, _, _, _, _),
+	[6] = PINGROUP(6, emac0_mdio, _, _, _, _, _, _, _, _, _, _),
+	[7] = PINGROUP(7, usb2phy_ac, _, _, _, _, _, _, _, _, _, _),
+	[8] = PINGROUP(8, usb2phy_ac, _, _, _, _, _, _, _, _, _, _),
+	[9] = PINGROUP(9, phase_flag, _, _, _, _, _, _, _, _, _, _),
+	[10] = PINGROUP(10, qup2_se0, emac0_mcg0, _, _, _, _, _, _, _, _, _),
+	[11] = PINGROUP(11, qup2_se0, emac0_mcg1, _, _, _, _, _, _, _, _, _),
+	[12] = PINGROUP(12, qup2_se0, _, _, _, _, _, _, _, _, _, _),
+	[13] = PINGROUP(13, qup2_se0, _, _, _, _, _, _, _, _, _, _),
+	[14] = PINGROUP(14, qup2_se0, tb_trig, _, _, _, _, _, _, _, _, _),
+	[15] = PINGROUP(15, qup2_se0, _, sailss_ospi, sailss_emac0, _, _, _, _, _, _, _),
+	[16] = PINGROUP(16, qup2_se0, _, _, sailss_ospi, sailss_emac0, _, _, _, _, _, _),
+	[17] = PINGROUP(17, qup0_se0, qup0_se1, ibi_i3c, _, _, _, _, _, _, _, _),
+	[18] = PINGROUP(18, qup0_se0, qup0_se1, ibi_i3c, _, _, _, _, _, _, _, _),
+	[19] = PINGROUP(19, qup0_se1, qup0_se0, cci_timer, ibi_i3c, _, _, _, _, _, _, _),
+	[20] = PINGROUP(20, qup0_se1, qup0_se0, cci_timer, ibi_i3c, _, _, _, _, _, _, _),
+	[21] = PINGROUP(21, qup0_se5, cci_timer, _, _, _, _, _, _, _, _, _),
+	[22] = PINGROUP(22, pcie1_clkreq, qup0_se5, cci_timer, _, _, _, _, _, _, _, _),
+	[23] = PINGROUP(23, qup0_se5, cci_timer, qdss_cti, _, _, _, _, _, _, _, _),
+	[24] = PINGROUP(24, qup0_se5, emac0_ptp_aux, emac0_ptp_pps, qdss_cti,
+			emac0_mcg2, _, _, _, _, _, _),
+	[25] = PINGROUP(25, qup0_se3, phase_flag, _, _, _, _, _, _, _, _, _),
+	[26] = PINGROUP(26, qup0_se3, phase_flag, _, _, _, _, _, _, _, _, _),
+	[27] = PINGROUP(27, qup0_se3, _, _, _, _, _, _, _, _, _, _),
+	[28] = PINGROUP(28, qup0_se3, phase_flag, _, _, _, _, _, _, _, _, _),
+	[29] = PINGROUP(29, qup0_se4, cci_i2c_sda, cci_async, emac0_ptp_pps,
+			tgu_ch2, _, _, _, _, _, _),
+	[30] = PINGROUP(30, qup0_se4, cci_i2c_scl, cci_async, emac0_ptp_pps,
+			tgu_ch3, _, _, _, _, _, _),
+	[31] = PINGROUP(31, qup0_se4, cci_i2c_sda, cci_async, emac0_ptp_aux, _, _, _, _, _, _, _),
+	[32] = PINGROUP(32, qup0_se4, cci_i2c_scl, emac0_ptp_aux, mdp_vsync, _, _, _, _, _, _, _),
+	[33] = PINGROUP(33, qup0_se2, qdss_gpio, _, _, _, _, _, _, _, _, _),
+	[34] = PINGROUP(34, qup0_se2, qdss_gpio, _, _, _, _, _, _, _, _, _),
+	[35] = PINGROUP(35, qup0_se2, gcc_gp1, _, _, _, _, _, _, _, _, _),
+	[36] = PINGROUP(36, qup0_se2, gcc_gp2, qdss_gpio, _, _, _, _, _, _, _, _),
+	[37] = PINGROUP(37, qup1_se0, ibi_i3c, qup1_se1, aoss_cti, _, _, _, _, _, _, _),
+	[38] = PINGROUP(38, qup1_se0, ibi_i3c, qup1_se1, aoss_cti, _, _, _, _, _, _, _),
+	[39] = PINGROUP(39, qup1_se1, ibi_i3c, qup1_se0, aoss_cti, _, _, _, _, _, _, _),
+	[40] = PINGROUP(40, qup1_se1, ibi_i3c, qup1_se0, aoss_cti, _, _, _, _, _, _, _),
+	[41] = PINGROUP(41, qup1_se3, _, _, _, _, _, _, _, _, _, _),
+	[42] = PINGROUP(42, qup1_se3, _, mdp_vsync, _, _, _, _, _, _, _, _),
+	[43] = PINGROUP(43, qup0_se7, _, tgu_ch0, _, _, _, _, _, _, _, _),
+	[44] = PINGROUP(44, qup0_se7, _, tgu_ch1, _, _, _, _, _, _, _, _),
+	[45] = PINGROUP(45, qup1_se4, hs1_mi2s, _, _, _, _, _, _, _, _, _),
+	[46] = PINGROUP(46, qup1_se4, hs1_mi2s, _, _, _, _, _, _, _, _, _),
+	[47] = PINGROUP(47, qup1_se4, hs1_mi2s, _, _, _, _, _, _, _, _, _),
+	[48] = PINGROUP(48, qup1_se4, hs1_mi2s, edp0_lcd, _, _, _, _, _, _, _, _),
+	[49] = PINGROUP(49, qup1_se5, hs2_mi2s, cci_timer, qdss_cti, edp1_lcd,
+			ddr_pxi1, _, _, _, _, _),
+	[50] = PINGROUP(50, qup1_se5, hs2_mi2s, cci_timer, qdss_cti, _, ddr_pxi1, _, _, _, _, _),
+	[51] = PINGROUP(51, qup1_se5, hs2_mi2s, qdss_cti, _, _, _, _, _, _, _, _),
+	[52] = PINGROUP(52, qup1_se5, hs2_mi2s, qdss_cti, mdp_vsync, ddr_pxi2, _, _, _, _, _, _),
+	[53] = PINGROUP(53, ddr_bist, _, _, _, _, _, _, _, _, _, _),
+	[54] = PINGROUP(54, cci_i2c_sda, phase_flag, ddr_bist, _, _, _, _, _, _, _, _),
+	[55] = PINGROUP(55, cci_i2c_scl, phase_flag, ddr_bist, _, _, _, _, _, _, _, _),
+	[56] = PINGROUP(56, phase_flag, ddr_bist, _, _, _, _, _, _, _, _, _),
+	[57] = PINGROUP(57, cci_i2c_sda, prng_rosc0, qdss_gpio, _, _, _, _, _, _, _, _),
+	[58] = PINGROUP(58, cci_i2c_scl, prng_rosc1, qdss_gpio, _, _, _, _, _, _, _, _),
+	[59] = PINGROUP(59, cci_i2c_sda, prng_rosc2, qdss_gpio, _, _, _, _, _, _, _, _),
+	[60] = PINGROUP(60, cci_i2c_scl, prng_rosc3, qdss_gpio, _, _, _, _, _, _, _, _),
+	[61] = PINGROUP(61, cci_i2c_sda, qdss_gpio, _, _, _, _, _, _, _, _, _),
+	[62] = PINGROUP(62, cci_i2c_scl, qdss_gpio, _, _, _, _, _, _, _, _, _),
+	[63] = PINGROUP(63, cci_timer, cci_async, qdss_gpio, atest_usb2, _, _, _, _, _, _, _),
+	[64] = PINGROUP(64, cci_timer, cci_async, qdss_gpio, atest_usb2, _, _, _, _, _, _, _),
+	[65] = PINGROUP(65, cci_timer, cci_async, qdss_gpio, atest_usb2, _, _, _, _, _, _, _),
+	[66] = PINGROUP(66, phase_flag, _, atest_char, _, _, _, _, _, _, _, _),
+	[67] = PINGROUP(67, cam_mclk, vsense_trigger, atest_usb2, _, _, _, _, _, _, _, _),
+	[68] = PINGROUP(68, cam_mclk, gcc_gp4, atest_usb2, ddr_pxi0, _, _, _, _, _, _, _),
+	[69] = PINGROUP(69, cam_mclk, gcc_gp3, atest_usb2, ddr_pxi0, _, _, _, _, _, _, _),
+	[70] = PINGROUP(70, qdss_gpio, atest_char, _, _, _, _, _, _, _, _, _),
+	[71] = PINGROUP(71, qdss_gpio, atest_char, _, _, _, _, _, _, _, _, _),
+	[72] = PINGROUP(72, qdss_gpio, atest_char, _, _, _, _, _, _, _, _, _),
+	[73] = PINGROUP(73, _, qdss_gpio, _, _, _, _, _, _, _, _, _),
+	[74] = PINGROUP(74, pll_clk, qdss_gpio, atest_usb2, _, _, _, _, _, _, _, _),
+	[75] = PINGROUP(75, _, dbg_out, qdss_gpio, atest_usb2, _, _, _, _, _, _, _),
+	[76] = PINGROUP(76, gcc_gp5, tsense_pwm4, _, _, _, _, _, _, _, _, _),
+	[77] = PINGROUP(77, gcc_gp5, tsense_pwm3, _, _, _, _, _, _, _, _, _),
+	[78] = PINGROUP(78, tsense_pwm2, _, _, _, _, _, _, _, _, _, _),
+	[79] = PINGROUP(79, emac0_ptp_aux, emac0_ptp_pps, emac0_mcg3, _,
+			tsense_pwm1, _, _, _, _, _, _),
+	[80] = PINGROUP(80, qup0_se6, mdp0_vsync6, _, atest_usb2, ddr_pxi3, _, _, _, _, _, _),
+	[81] = PINGROUP(81, qup0_se6, mdp0_vsync7, gcc_gp2, _, atest_usb2, ddr_pxi3, _, _, _, _, _),
+	[82] = PINGROUP(82, qup0_se6, gcc_gp3, _, _, _, _, _, _, _, _, _),
+	[83] = PINGROUP(83, qup0_se6, gcc_gp4, _, atest_usb2, ddr_pxi2, _, _, _, _, _, _),
+	[84] = PINGROUP(84, qup1_se2, gcc_gp1, _, atest_usb2, _, _, _, _, _, _, _),
+	[85] = PINGROUP(85, qup1_se2, _, atest_usb2, _, _, _, _, _, _, _, _),
+	[86] = PINGROUP(86, qup1_se2, _, _, _, _, _, _, _, _, _, _),
+	[87] = PINGROUP(87, qup1_se2, _, atest_usb2, _, _, _, _, _, _, _, _),
+	[88] = PINGROUP(88, qup1_se2, _, _, _, _, _, _, _, _, _, _),
+	[89] = PINGROUP(89, qup1_se6, qup1_se7, mdp0_vsync0, _, _, _, _, _, _, _, _),
+	[90] = PINGROUP(90, qup1_se6, qup1_se7, mdp0_vsync1, cri_trng, _, _, _, _, _, _, _),
+	[91] = PINGROUP(91, qup1_se7, qup1_se6, mdp0_vsync3, cri_trng, _, _, _, _, _, _, _),
+	[92] = PINGROUP(92, qup1_se7, qup1_se6, cri_trng, _, atest_usb2, _, _, _, _, _, _),
+	[93] = PINGROUP(93, atest_char, _, _, _, _, _, _, _, _, _, _),
+	[94] = PINGROUP(94, edp0_hot, _, _, _, _, _, _, _, _, _, _),
+	[95] = PINGROUP(95, _, _, _, _, _, _, _, _, _, _, _),
+	[96] = PINGROUP(96, _, _, _, _, _, _, _, _, _, _, _),
+	[97] = PINGROUP(97, mi2s_mclk0, jitter_bist, qdss_gpio, _, _, _, _, _, _, _, _),
+	[98] = PINGROUP(98, mi2s1_sck, phase_flag, _, qdss_gpio, _, _, _, _, _, _, _),
+	[99] = PINGROUP(99, mi2s1_ws, phase_flag, _, qdss_gpio, _, _, _, _, _, _, _),
+	[100] = PINGROUP(100, mi2s1_data0, phase_flag, _, qdss_gpio, _, _, _, _, _, _, _),
+	[101] = PINGROUP(101, mi2s1_data1, phase_flag, _, qdss_gpio, _, _, _, _, _, _, _),
+	[102] = PINGROUP(102, mi2s2_sck, phase_flag, _, qdss_gpio, _, _, _, _, _, _, _),
+	[103] = PINGROUP(103, mi2s2_ws, phase_flag, _, qdss_gpio, _, _, _, _, _, _, _),
+	[104] = PINGROUP(104, mi2s2_data0, phase_flag, _, qdss_gpio, _, _, _, _, _, _, _),
+	[105] = PINGROUP(105, mi2s2_data1, audio_ref, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[106] = PINGROUP(106, hs0_mi2s, phase_flag, _, qdss_gpio, _, _, _, _, _, _, _),
+	[107] = PINGROUP(107, hs0_mi2s, pll_bist, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[108] = PINGROUP(108, hs0_mi2s, phase_flag, _, qdss_gpio, _, _, _, _, _, _, _),
+	[109] = PINGROUP(109, hs0_mi2s, mi2s_mclk1, qdss_gpio, _, _, _, _, _, _, _, _),
+	[110] = PINGROUP(110, phase_flag, _, qdss_gpio, _, _, _, _, _, _, _, egpio),
+	[111] = PINGROUP(111, phase_flag, _, qdss_gpio, _, _, _, _, _, _, _, egpio),
+	[112] = PINGROUP(112, phase_flag, _, qdss_gpio, _, _, _, _, _, _, _, egpio),
+	[113] = PINGROUP(113, phase_flag, _, qdss_gpio, _, _, _, _, _, _, _, egpio),
+	[114] = PINGROUP(114, phase_flag, _, qdss_gpio, _, _, _, _, _, _, _, egpio),
+	[115] = PINGROUP(115, _, _, _, _, _, _, _, _, _, _, egpio),
+	[116] = PINGROUP(116, phase_flag, _, _, _, _, _, _, _, _, _, egpio),
+	[117] = PINGROUP(117, phase_flag, _, _, _, _, _, _, _, _, _, egpio),
+	[118] = PINGROUP(118, phase_flag, _, _, _, _, _, _, _, _, _, egpio),
+	[119] = PINGROUP(119, _, _, _, _, _, _, _, _, _, _, egpio),
+	[120] = PINGROUP(120, phase_flag, _, _, _, _, _, _, _, _, _, egpio),
+	[121] = PINGROUP(121, phase_flag, _, _, _, _, _, _, _, _, _, egpio),
+	[122] = PINGROUP(122, phase_flag, _, _, _, _, _, _, _, _, _, egpio),
+	[123] = PINGROUP(123, _, _, _, _, _, _, _, _, _, _, egpio),
+	[124] = PINGROUP(124, _, _, _, _, _, _, _, _, _, _, egpio),
+	[125] = PINGROUP(125, phase_flag, _, _, _, _, _, _, _, _, _, egpio),
+	[126] = PINGROUP(126, _, _, _, _, _, _, _, _, _, _, egpio),
+	[127] = PINGROUP(127, _, _, _, _, _, _, _, _, _, _, egpio),
+	[128] = PINGROUP(128, _, _, _, _, _, _, _, _, _, _, egpio),
+	[129] = PINGROUP(129, _, _, _, _, _, _, _, _, _, _, egpio),
+	[130] = PINGROUP(130, _, _, _, _, _, _, _, _, _, _, egpio),
+	[131] = PINGROUP(131, _, _, _, _, _, _, _, _, _, _, egpio),
+	[132] = PINGROUP(132, _, _, _, _, _, _, _, _, _, _, egpio),
+	[133] = UFS_RESET(ufs_reset, 0x92000),
+	[134] = SDC_QDSD_PINGROUP(sdc1_rclk, 0x89000, 15, 0),
+	[135] = SDC_QDSD_PINGROUP(sdc1_clk, 0x89000, 13, 6),
+	[136] = SDC_QDSD_PINGROUP(sdc1_cmd, 0x89000, 11, 3),
+	[137] = SDC_QDSD_PINGROUP(sdc1_data, 0x89000, 9, 0),
+};
+
+static const struct msm_gpio_wakeirq_map qcs8300_pdc_map[] = {
+	{ 0, 169 },   { 1, 174 },   { 2, 221 },   { 3, 176 },   { 4, 171 },
+	{ 9, 198 },   { 10, 187 },  { 11, 188 },  { 13, 211 },  { 16, 203 },
+	{ 17, 213 },  { 18, 209 },  { 19, 201 },  { 20, 230 },  { 21, 231 },
+	{ 22, 175 },  { 23, 170 },  { 24, 232 },  { 28, 235 },  { 29, 216 },
+	{ 31, 208 },  { 32, 200 },  { 36, 212 },  { 37, 177 },  { 38, 178 },
+	{ 39, 184 },  { 40, 185 },  { 42, 186 },  { 44, 194 },  { 45, 173 },
+	{ 48, 195 },  { 51, 215 },  { 52, 197 },  { 53, 192 },  { 56, 193 },
+	{ 66, 238 },  { 67, 172 },  { 68, 182 },  { 69, 179 },  { 70, 181 },
+	{ 71, 202 },  { 72, 183 },  { 73, 189 },  { 74, 196 },  { 75, 190 },
+	{ 76, 191 },  { 77, 204 },  { 78, 206 },  { 79, 207 },  { 83, 214 },
+	{ 84, 205 },  { 87, 237 },  { 89, 225 },  { 90, 217 },  { 91, 218 },
+	{ 92, 226 },  { 93, 227 },  { 94, 228 },  { 95, 236 },  { 97, 199 },
+	{ 98, 229 },  { 99, 180 },  { 100, 220 }, { 101, 239 }, { 102, 219 },
+	{ 103, 233 }, { 104, 234 }, { 105, 223 }, { 129, 210 }, { 130, 222 },
+};
+
+static const struct msm_pinctrl_soc_data qcs8300_pinctrl = {
+	.pins = qcs8300_pins,
+	.npins = ARRAY_SIZE(qcs8300_pins),
+	.functions = qcs8300_functions,
+	.nfunctions = ARRAY_SIZE(qcs8300_functions),
+	.groups = qcs8300_groups,
+	.ngroups = ARRAY_SIZE(qcs8300_groups),
+	.ngpios = 133,
+	.wakeirq_map = qcs8300_pdc_map,
+	.nwakeirq_map = ARRAY_SIZE(qcs8300_pdc_map),
+	.egpio_func = 11,
+};
+
+static int qcs8300_pinctrl_probe(struct platform_device *pdev)
+{
+	return msm_pinctrl_probe(pdev, &qcs8300_pinctrl);
+}
+
+static const struct of_device_id qcs8300_pinctrl_of_match[] = {
+	{ .compatible = "qcom,qcs8300-tlmm", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, qcs8300_pinctrl_of_match);
+
+static struct platform_driver qcs8300_pinctrl_driver = {
+	.driver = {
+		.name = "qcs8300-tlmm",
+		.of_match_table = qcs8300_pinctrl_of_match,
+	},
+	.probe = qcs8300_pinctrl_probe,
+	.remove = msm_pinctrl_remove,
+};
+
+static int __init qcs8300_pinctrl_init(void)
+{
+	return platform_driver_register(&qcs8300_pinctrl_driver);
+}
+arch_initcall(qcs8300_pinctrl_init);
+
+static void __exit qcs8300_pinctrl_exit(void)
+{
+	platform_driver_unregister(&qcs8300_pinctrl_driver);
+}
+module_exit(qcs8300_pinctrl_exit);
+
+MODULE_DESCRIPTION("QTI QCS8300 pinctrl driver");
+MODULE_LICENSE("GPL");

From e89768f63f49fd7a31ebc1699cd209549f27611e Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Fri, 18 Oct 2024 11:42:39 +0300
Subject: [PATCH 0584/1530] dt-bindings: pinctrl : qcom: document SAR2130P TLMM

Add bindings for the pin controller (TLMM) present on the
Qualcomm SAR2130P platform.

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/20241018-sar2130p-tlmm-v2-1-11a1d09a6e5f@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/qcom,sar2130p-tlmm.yaml  | 138 ++++++++++++++++++
 1 file changed, 138 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/qcom,sar2130p-tlmm.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sar2130p-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sar2130p-tlmm.yaml
new file mode 100644
index 0000000000000..b388380b1ce02
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sar2130p-tlmm.yaml
@@ -0,0 +1,138 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,sar2130p-tlmm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Technologies, Inc. SAR2130P TLMM block
+
+maintainers:
+  - Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
+
+description:
+  Top Level Mode Multiplexer pin controller in Qualcomm SAR2130P SoC.
+
+allOf:
+  - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml#
+
+properties:
+  compatible:
+    const: qcom,sar2130p-tlmm
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  gpio-reserved-ranges:
+    minItems: 1
+    maxItems: 78
+
+  gpio-line-names:
+    maxItems: 156
+
+patternProperties:
+  "-state$":
+    oneOf:
+      - $ref: "#/$defs/qcom-sar2130p-tlmm-state"
+      - patternProperties:
+          "-pins$":
+            $ref: "#/$defs/qcom-sar2130p-tlmm-state"
+        additionalProperties: false
+
+$defs:
+  qcom-sar2130p-tlmm-state:
+    type: object
+    description:
+      Pinctrl node's client devices use subnodes for desired pin configuration.
+      Client device subnodes use below standard properties.
+    $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
+
+    properties:
+      pins:
+        description:
+          List of gpio pins affected by the properties specified in this
+          subnode.
+        items:
+          oneOf:
+            - pattern: "^gpio([0-9]|[1-9][0-9]|1[0-4][0-9]|15[0-5])$"
+            - enum: [ sdc1_clk, sdc1_cmd, sdc1_data, sdc1_rclk ]
+        minItems: 1
+        maxItems: 36
+
+      function:
+        description:
+          Specify the alternative function to be configured for the specified
+          pins.
+        enum: [ aoss_cti, atest_char, atest_char0, atest_char1, atest_char2,
+                atest_char3, atest_usb0, atest_usb00, atest_usb01, atest_usb02,
+                atest_usb03, audio_ref, cam_mclk, cci_async, cci_i2c,
+                cci_timer0, cci_timer1, cci_timer2, cci_timer3, cci_timer4,
+                cri_trng, cri_trng0, cri_trng1, dbg_out, ddr_bist, ddr_pxi0,
+                ddr_pxi1, ddr_pxi2, ddr_pxi3, dp0_hot, ext_mclk0, ext_mclk1,
+                gcc_gp1, gcc_gp2, gcc_gp3, gpio, host2wlan_sol, i2s0_data0,
+                i2s0_data1, i2s0_sck, i2s0_ws, ibi_i3c, jitter_bist, mdp_vsync,
+                mdp_vsync0, mdp_vsync1, mdp_vsync2, mdp_vsync3, pcie0_clkreqn,
+                pcie1_clkreqn, phase_flag0, phase_flag1, phase_flag10,
+                phase_flag11, phase_flag12, phase_flag13, phase_flag14,
+                phase_flag15, phase_flag16, phase_flag17, phase_flag18,
+                phase_flag19, phase_flag2, phase_flag20, phase_flag21,
+                phase_flag22, phase_flag23, phase_flag24, phase_flag25,
+                phase_flag26, phase_flag27, phase_flag28, phase_flag29,
+                phase_flag3, phase_flag30, phase_flag31, phase_flag4,
+                phase_flag5, phase_flag6, phase_flag7, phase_flag8,
+                phase_flag9, pll_bist, pll_clk, prng_rosc0, prng_rosc1,
+                prng_rosc2, prng_rosc3, qdss_cti, qdss_gpio, qdss_gpio0,
+                qdss_gpio1, qdss_gpio10, qdss_gpio11, qdss_gpio12, qdss_gpio13,
+                qdss_gpio14, qdss_gpio15, qdss_gpio2, qdss_gpio3, qdss_gpio4,
+                qdss_gpio5, qdss_gpio6, qdss_gpio7, qdss_gpio8, qdss_gpio9,
+                qspi0, qspi1, qspi2, qspi3, qspi_clk, qspi_cs0, qspi_cs1, qup0,
+                qup1, qup2, qup3, qup4, qup5, qup6, qup7, qup8, qup9, qup10,
+                qup11, tb_trig, tgu_ch0, tgu_ch1, tgu_ch2, tgu_ch3,
+                tmess_prng0, tmess_prng1, tmess_prng2, tmess_prng3,
+                tsense_pwm1, tsense_pwm2, usb0_phy, vsense_trigger ]
+
+    required:
+      - pins
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    pinctrl@f100000 {
+        compatible = "qcom,sar2130p-tlmm";
+        reg = <0x0f100000 0x300000>;
+        gpio-controller;
+        #gpio-cells = <2>;
+        gpio-ranges = <&tlmm 0 0 156>;
+        interrupt-controller;
+        #interrupt-cells = <2>;
+        interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
+
+        gpio-wo-state {
+            pins = "gpio1";
+            function = "gpio";
+        };
+
+        uart-w-state {
+            rx-pins {
+                pins = "gpio26";
+                function = "qup7";
+                bias-pull-up;
+            };
+
+            tx-pins {
+                pins = "gpio27";
+                function = "qup7";
+                bias-disable;
+            };
+        };
+    };
+...

From 11138a5caa2bc396d74b7996460b6ff353eb1fd0 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Fri, 18 Oct 2024 11:42:40 +0300
Subject: [PATCH 0585/1530] pinctrl: qcom: add support for TLMM on SAR2130P

Add driver for the pincontrol device as present on the Qualcomm
SAR2130P platform. This is based on the msm-5.10 tree, tag
KERNEL.PLATFORM.1.0.r4-00400-NEO.0.

Co-developed-by: Mayank Grover <groverm@codeaurora.org>
Signed-off-by: Mayank Grover <groverm@codeaurora.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/20241018-sar2130p-tlmm-v2-2-11a1d09a6e5f@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/Kconfig.msm        |    8 +
 drivers/pinctrl/qcom/Makefile           |    1 +
 drivers/pinctrl/qcom/pinctrl-sar2130p.c | 1505 +++++++++++++++++++++++
 3 files changed, 1514 insertions(+)
 create mode 100644 drivers/pinctrl/qcom/pinctrl-sar2130p.c

diff --git a/drivers/pinctrl/qcom/Kconfig.msm b/drivers/pinctrl/qcom/Kconfig.msm
index c5d67539f5c91..38d44052d3c91 100644
--- a/drivers/pinctrl/qcom/Kconfig.msm
+++ b/drivers/pinctrl/qcom/Kconfig.msm
@@ -227,6 +227,14 @@ config PINCTRL_SA8775P
 	  This is the pinctrl, pinmux and pinconf driver for the Qualcomm
 	  TLMM block found on the Qualcomm SA8775P platforms.
 
+config PINCTRL_SAR2130P
+	tristate "Qualcomm Technologies Inc SAR2130P pin controller driver"
+	depends on ARM64 || COMPILE_TEST
+	help
+	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
+	  Qualcomm Technologies Inc TLMM block found on the Qualcomm
+	  Technologies Inc SAR2130P platform.
+
 config PINCTRL_SC7180
 	tristate "Qualcomm Technologies Inc SC7180 pin controller driver"
 	depends on ARM64 || COMPILE_TEST
diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile
index 7c8385e69e90f..51bf41c343803 100644
--- a/drivers/pinctrl/qcom/Makefile
+++ b/drivers/pinctrl/qcom/Makefile
@@ -35,6 +35,7 @@ obj-$(CONFIG_PINCTRL_QCOM_SSBI_PMIC) += pinctrl-ssbi-gpio.o
 obj-$(CONFIG_PINCTRL_QCOM_SSBI_PMIC) += pinctrl-ssbi-mpp.o
 obj-$(CONFIG_PINCTRL_QDU1000)	+= pinctrl-qdu1000.o
 obj-$(CONFIG_PINCTRL_SA8775P)	+= pinctrl-sa8775p.o
+obj-$(CONFIG_PINCTRL_SAR2130P)	+= pinctrl-sar2130p.o
 obj-$(CONFIG_PINCTRL_SC7180)	+= pinctrl-sc7180.o
 obj-$(CONFIG_PINCTRL_SC7280)	+= pinctrl-sc7280.o
 obj-$(CONFIG_PINCTRL_SC7280_LPASS_LPI) += pinctrl-sc7280-lpass-lpi.o
diff --git a/drivers/pinctrl/qcom/pinctrl-sar2130p.c b/drivers/pinctrl/qcom/pinctrl-sar2130p.c
new file mode 100644
index 0000000000000..19a2e37826c7b
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-sar2130p.c
@@ -0,0 +1,1505 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020-2021, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021, Linaro Limited
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-msm.h"
+
+#define REG_SIZE 0x1000
+
+#define PINGROUP(id, f1, f2, f3, f4, f5, f6, f7, f8, f9)	\
+	{						\
+		.grp = PINCTRL_PINGROUP("gpio" #id,	\
+			gpio##id##_pins,		\
+			ARRAY_SIZE(gpio##id##_pins)),	\
+		.funcs = (int[]){			\
+			msm_mux_gpio, /* gpio mode */	\
+			msm_mux_##f1,			\
+			msm_mux_##f2,			\
+			msm_mux_##f3,			\
+			msm_mux_##f4,			\
+			msm_mux_##f5,			\
+			msm_mux_##f6,			\
+			msm_mux_##f7,			\
+			msm_mux_##f8,			\
+			msm_mux_##f9			\
+		},					\
+		.nfuncs = 10,				\
+		.ctl_reg = REG_SIZE * id,		\
+		.io_reg = 0x4 + REG_SIZE * id,		\
+		.intr_cfg_reg = 0x8 + REG_SIZE * id,	\
+		.intr_status_reg = 0xc + REG_SIZE * id,	\
+		.intr_target_reg = 0x8 + REG_SIZE * id,	\
+		.mux_bit = 2,			\
+		.pull_bit = 0,			\
+		.drv_bit = 6,			\
+		.egpio_enable = 12,		\
+		.egpio_present = 11,		\
+		.oe_bit = 9,			\
+		.in_bit = 0,			\
+		.out_bit = 1,			\
+		.intr_enable_bit = 0,		\
+		.intr_status_bit = 0,		\
+		.intr_target_bit = 5,		\
+		.intr_target_kpss_val = 4,	\
+		.intr_raw_status_bit = 4,	\
+		.intr_polarity_bit = 1,		\
+		.intr_detection_bit = 2,	\
+		.intr_detection_width = 2,	\
+	}
+
+#define SDC_QDSD_PINGROUP(pg_name, ctl, pull, drv)	\
+	{						\
+		.grp = PINCTRL_PINGROUP(#pg_name,	\
+			pg_name##_pins,			\
+			ARRAY_SIZE(pg_name##_pins)),	\
+		.ctl_reg = ctl,				\
+		.io_reg = 0,				\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = pull,			\
+		.drv_bit = drv,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = -1,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+static const struct pinctrl_pin_desc sar2130p_pins[] = {
+	PINCTRL_PIN(0, "GPIO_0"),
+	PINCTRL_PIN(1, "GPIO_1"),
+	PINCTRL_PIN(2, "GPIO_2"),
+	PINCTRL_PIN(3, "GPIO_3"),
+	PINCTRL_PIN(4, "GPIO_4"),
+	PINCTRL_PIN(5, "GPIO_5"),
+	PINCTRL_PIN(6, "GPIO_6"),
+	PINCTRL_PIN(7, "GPIO_7"),
+	PINCTRL_PIN(8, "GPIO_8"),
+	PINCTRL_PIN(9, "GPIO_9"),
+	PINCTRL_PIN(10, "GPIO_10"),
+	PINCTRL_PIN(11, "GPIO_11"),
+	PINCTRL_PIN(12, "GPIO_12"),
+	PINCTRL_PIN(13, "GPIO_13"),
+	PINCTRL_PIN(14, "GPIO_14"),
+	PINCTRL_PIN(15, "GPIO_15"),
+	PINCTRL_PIN(16, "GPIO_16"),
+	PINCTRL_PIN(17, "GPIO_17"),
+	PINCTRL_PIN(18, "GPIO_18"),
+	PINCTRL_PIN(19, "GPIO_19"),
+	PINCTRL_PIN(20, "GPIO_20"),
+	PINCTRL_PIN(21, "GPIO_21"),
+	PINCTRL_PIN(22, "GPIO_22"),
+	PINCTRL_PIN(23, "GPIO_23"),
+	PINCTRL_PIN(24, "GPIO_24"),
+	PINCTRL_PIN(25, "GPIO_25"),
+	PINCTRL_PIN(26, "GPIO_26"),
+	PINCTRL_PIN(27, "GPIO_27"),
+	PINCTRL_PIN(28, "GPIO_28"),
+	PINCTRL_PIN(29, "GPIO_29"),
+	PINCTRL_PIN(30, "GPIO_30"),
+	PINCTRL_PIN(31, "GPIO_31"),
+	PINCTRL_PIN(32, "GPIO_32"),
+	PINCTRL_PIN(33, "GPIO_33"),
+	PINCTRL_PIN(34, "GPIO_34"),
+	PINCTRL_PIN(35, "GPIO_35"),
+	PINCTRL_PIN(36, "GPIO_36"),
+	PINCTRL_PIN(37, "GPIO_37"),
+	PINCTRL_PIN(38, "GPIO_38"),
+	PINCTRL_PIN(39, "GPIO_39"),
+	PINCTRL_PIN(40, "GPIO_40"),
+	PINCTRL_PIN(41, "GPIO_41"),
+	PINCTRL_PIN(42, "GPIO_42"),
+	PINCTRL_PIN(43, "GPIO_43"),
+	PINCTRL_PIN(44, "GPIO_44"),
+	PINCTRL_PIN(45, "GPIO_45"),
+	PINCTRL_PIN(46, "GPIO_46"),
+	PINCTRL_PIN(47, "GPIO_47"),
+	PINCTRL_PIN(48, "GPIO_48"),
+	PINCTRL_PIN(49, "GPIO_49"),
+	PINCTRL_PIN(50, "GPIO_50"),
+	PINCTRL_PIN(51, "GPIO_51"),
+	PINCTRL_PIN(52, "GPIO_52"),
+	PINCTRL_PIN(53, "GPIO_53"),
+	PINCTRL_PIN(54, "GPIO_54"),
+	PINCTRL_PIN(55, "GPIO_55"),
+	PINCTRL_PIN(56, "GPIO_56"),
+	PINCTRL_PIN(57, "GPIO_57"),
+	PINCTRL_PIN(58, "GPIO_58"),
+	PINCTRL_PIN(59, "GPIO_59"),
+	PINCTRL_PIN(60, "GPIO_60"),
+	PINCTRL_PIN(61, "GPIO_61"),
+	PINCTRL_PIN(62, "GPIO_62"),
+	PINCTRL_PIN(63, "GPIO_63"),
+	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
+	PINCTRL_PIN(69, "GPIO_69"),
+	PINCTRL_PIN(70, "GPIO_70"),
+	PINCTRL_PIN(71, "GPIO_71"),
+	PINCTRL_PIN(72, "GPIO_72"),
+	PINCTRL_PIN(73, "GPIO_73"),
+	PINCTRL_PIN(74, "GPIO_74"),
+	PINCTRL_PIN(75, "GPIO_75"),
+	PINCTRL_PIN(76, "GPIO_76"),
+	PINCTRL_PIN(77, "GPIO_77"),
+	PINCTRL_PIN(78, "GPIO_78"),
+	PINCTRL_PIN(79, "GPIO_79"),
+	PINCTRL_PIN(80, "GPIO_80"),
+	PINCTRL_PIN(81, "GPIO_81"),
+	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
+	PINCTRL_PIN(86, "GPIO_86"),
+	PINCTRL_PIN(87, "GPIO_87"),
+	PINCTRL_PIN(88, "GPIO_88"),
+	PINCTRL_PIN(89, "GPIO_89"),
+	PINCTRL_PIN(90, "GPIO_90"),
+	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93"),
+	PINCTRL_PIN(94, "GPIO_94"),
+	PINCTRL_PIN(95, "GPIO_95"),
+	PINCTRL_PIN(96, "GPIO_96"),
+	PINCTRL_PIN(97, "GPIO_97"),
+	PINCTRL_PIN(98, "GPIO_98"),
+	PINCTRL_PIN(99, "GPIO_99"),
+	PINCTRL_PIN(100, "GPIO_100"),
+	PINCTRL_PIN(101, "GPIO_101"),
+	PINCTRL_PIN(102, "GPIO_102"),
+	PINCTRL_PIN(103, "GPIO_103"),
+	PINCTRL_PIN(104, "GPIO_104"),
+	PINCTRL_PIN(105, "GPIO_105"),
+	PINCTRL_PIN(106, "GPIO_106"),
+	PINCTRL_PIN(107, "GPIO_107"),
+	PINCTRL_PIN(108, "GPIO_108"),
+	PINCTRL_PIN(109, "GPIO_109"),
+	PINCTRL_PIN(110, "GPIO_110"),
+	PINCTRL_PIN(111, "GPIO_111"),
+	PINCTRL_PIN(112, "GPIO_112"),
+	PINCTRL_PIN(113, "GPIO_113"),
+	PINCTRL_PIN(114, "GPIO_114"),
+	PINCTRL_PIN(115, "GPIO_115"),
+	PINCTRL_PIN(116, "GPIO_116"),
+	PINCTRL_PIN(117, "GPIO_117"),
+	PINCTRL_PIN(118, "GPIO_118"),
+	PINCTRL_PIN(119, "GPIO_119"),
+	PINCTRL_PIN(120, "GPIO_120"),
+	PINCTRL_PIN(121, "GPIO_121"),
+	PINCTRL_PIN(122, "GPIO_122"),
+	PINCTRL_PIN(123, "GPIO_123"),
+	PINCTRL_PIN(124, "GPIO_124"),
+	PINCTRL_PIN(125, "GPIO_125"),
+	PINCTRL_PIN(126, "GPIO_126"),
+	PINCTRL_PIN(127, "GPIO_127"),
+	PINCTRL_PIN(128, "GPIO_128"),
+	PINCTRL_PIN(129, "GPIO_129"),
+	PINCTRL_PIN(130, "GPIO_130"),
+	PINCTRL_PIN(131, "GPIO_131"),
+	PINCTRL_PIN(132, "GPIO_132"),
+	PINCTRL_PIN(133, "GPIO_133"),
+	PINCTRL_PIN(134, "GPIO_134"),
+	PINCTRL_PIN(135, "GPIO_135"),
+	PINCTRL_PIN(136, "GPIO_136"),
+	PINCTRL_PIN(137, "GPIO_137"),
+	PINCTRL_PIN(138, "GPIO_138"),
+	PINCTRL_PIN(139, "GPIO_139"),
+	PINCTRL_PIN(140, "GPIO_140"),
+	PINCTRL_PIN(141, "GPIO_141"),
+	PINCTRL_PIN(142, "GPIO_142"),
+	PINCTRL_PIN(143, "GPIO_143"),
+	PINCTRL_PIN(144, "GPIO_144"),
+	PINCTRL_PIN(145, "GPIO_145"),
+	PINCTRL_PIN(146, "GPIO_146"),
+	PINCTRL_PIN(147, "GPIO_147"),
+	PINCTRL_PIN(148, "GPIO_148"),
+	PINCTRL_PIN(149, "GPIO_149"),
+	PINCTRL_PIN(150, "GPIO_150"),
+	PINCTRL_PIN(151, "GPIO_151"),
+	PINCTRL_PIN(152, "GPIO_152"),
+	PINCTRL_PIN(153, "GPIO_153"),
+	PINCTRL_PIN(154, "GPIO_154"),
+	PINCTRL_PIN(155, "GPIO_155"),
+	PINCTRL_PIN(156, "SDC1_RCLK"),
+	PINCTRL_PIN(157, "SDC1_CLK"),
+	PINCTRL_PIN(158, "SDC1_CMD"),
+	PINCTRL_PIN(159, "SDC1_DATA"),
+};
+
+#define DECLARE_MSM_GPIO_PINS(pin) \
+	static const unsigned int gpio##pin##_pins[] = { pin }
+DECLARE_MSM_GPIO_PINS(0);
+DECLARE_MSM_GPIO_PINS(1);
+DECLARE_MSM_GPIO_PINS(2);
+DECLARE_MSM_GPIO_PINS(3);
+DECLARE_MSM_GPIO_PINS(4);
+DECLARE_MSM_GPIO_PINS(5);
+DECLARE_MSM_GPIO_PINS(6);
+DECLARE_MSM_GPIO_PINS(7);
+DECLARE_MSM_GPIO_PINS(8);
+DECLARE_MSM_GPIO_PINS(9);
+DECLARE_MSM_GPIO_PINS(10);
+DECLARE_MSM_GPIO_PINS(11);
+DECLARE_MSM_GPIO_PINS(12);
+DECLARE_MSM_GPIO_PINS(13);
+DECLARE_MSM_GPIO_PINS(14);
+DECLARE_MSM_GPIO_PINS(15);
+DECLARE_MSM_GPIO_PINS(16);
+DECLARE_MSM_GPIO_PINS(17);
+DECLARE_MSM_GPIO_PINS(18);
+DECLARE_MSM_GPIO_PINS(19);
+DECLARE_MSM_GPIO_PINS(20);
+DECLARE_MSM_GPIO_PINS(21);
+DECLARE_MSM_GPIO_PINS(22);
+DECLARE_MSM_GPIO_PINS(23);
+DECLARE_MSM_GPIO_PINS(24);
+DECLARE_MSM_GPIO_PINS(25);
+DECLARE_MSM_GPIO_PINS(26);
+DECLARE_MSM_GPIO_PINS(27);
+DECLARE_MSM_GPIO_PINS(28);
+DECLARE_MSM_GPIO_PINS(29);
+DECLARE_MSM_GPIO_PINS(30);
+DECLARE_MSM_GPIO_PINS(31);
+DECLARE_MSM_GPIO_PINS(32);
+DECLARE_MSM_GPIO_PINS(33);
+DECLARE_MSM_GPIO_PINS(34);
+DECLARE_MSM_GPIO_PINS(35);
+DECLARE_MSM_GPIO_PINS(36);
+DECLARE_MSM_GPIO_PINS(37);
+DECLARE_MSM_GPIO_PINS(38);
+DECLARE_MSM_GPIO_PINS(39);
+DECLARE_MSM_GPIO_PINS(40);
+DECLARE_MSM_GPIO_PINS(41);
+DECLARE_MSM_GPIO_PINS(42);
+DECLARE_MSM_GPIO_PINS(43);
+DECLARE_MSM_GPIO_PINS(44);
+DECLARE_MSM_GPIO_PINS(45);
+DECLARE_MSM_GPIO_PINS(46);
+DECLARE_MSM_GPIO_PINS(47);
+DECLARE_MSM_GPIO_PINS(48);
+DECLARE_MSM_GPIO_PINS(49);
+DECLARE_MSM_GPIO_PINS(50);
+DECLARE_MSM_GPIO_PINS(51);
+DECLARE_MSM_GPIO_PINS(52);
+DECLARE_MSM_GPIO_PINS(53);
+DECLARE_MSM_GPIO_PINS(54);
+DECLARE_MSM_GPIO_PINS(55);
+DECLARE_MSM_GPIO_PINS(56);
+DECLARE_MSM_GPIO_PINS(57);
+DECLARE_MSM_GPIO_PINS(58);
+DECLARE_MSM_GPIO_PINS(59);
+DECLARE_MSM_GPIO_PINS(60);
+DECLARE_MSM_GPIO_PINS(61);
+DECLARE_MSM_GPIO_PINS(62);
+DECLARE_MSM_GPIO_PINS(63);
+DECLARE_MSM_GPIO_PINS(64);
+DECLARE_MSM_GPIO_PINS(65);
+DECLARE_MSM_GPIO_PINS(66);
+DECLARE_MSM_GPIO_PINS(67);
+DECLARE_MSM_GPIO_PINS(68);
+DECLARE_MSM_GPIO_PINS(69);
+DECLARE_MSM_GPIO_PINS(70);
+DECLARE_MSM_GPIO_PINS(71);
+DECLARE_MSM_GPIO_PINS(72);
+DECLARE_MSM_GPIO_PINS(73);
+DECLARE_MSM_GPIO_PINS(74);
+DECLARE_MSM_GPIO_PINS(75);
+DECLARE_MSM_GPIO_PINS(76);
+DECLARE_MSM_GPIO_PINS(77);
+DECLARE_MSM_GPIO_PINS(78);
+DECLARE_MSM_GPIO_PINS(79);
+DECLARE_MSM_GPIO_PINS(80);
+DECLARE_MSM_GPIO_PINS(81);
+DECLARE_MSM_GPIO_PINS(82);
+DECLARE_MSM_GPIO_PINS(83);
+DECLARE_MSM_GPIO_PINS(84);
+DECLARE_MSM_GPIO_PINS(85);
+DECLARE_MSM_GPIO_PINS(86);
+DECLARE_MSM_GPIO_PINS(87);
+DECLARE_MSM_GPIO_PINS(88);
+DECLARE_MSM_GPIO_PINS(89);
+DECLARE_MSM_GPIO_PINS(90);
+DECLARE_MSM_GPIO_PINS(91);
+DECLARE_MSM_GPIO_PINS(92);
+DECLARE_MSM_GPIO_PINS(93);
+DECLARE_MSM_GPIO_PINS(94);
+DECLARE_MSM_GPIO_PINS(95);
+DECLARE_MSM_GPIO_PINS(96);
+DECLARE_MSM_GPIO_PINS(97);
+DECLARE_MSM_GPIO_PINS(98);
+DECLARE_MSM_GPIO_PINS(99);
+DECLARE_MSM_GPIO_PINS(100);
+DECLARE_MSM_GPIO_PINS(101);
+DECLARE_MSM_GPIO_PINS(102);
+DECLARE_MSM_GPIO_PINS(103);
+DECLARE_MSM_GPIO_PINS(104);
+DECLARE_MSM_GPIO_PINS(105);
+DECLARE_MSM_GPIO_PINS(106);
+DECLARE_MSM_GPIO_PINS(107);
+DECLARE_MSM_GPIO_PINS(108);
+DECLARE_MSM_GPIO_PINS(109);
+DECLARE_MSM_GPIO_PINS(110);
+DECLARE_MSM_GPIO_PINS(111);
+DECLARE_MSM_GPIO_PINS(112);
+DECLARE_MSM_GPIO_PINS(113);
+DECLARE_MSM_GPIO_PINS(114);
+DECLARE_MSM_GPIO_PINS(115);
+DECLARE_MSM_GPIO_PINS(116);
+DECLARE_MSM_GPIO_PINS(117);
+DECLARE_MSM_GPIO_PINS(118);
+DECLARE_MSM_GPIO_PINS(119);
+DECLARE_MSM_GPIO_PINS(120);
+DECLARE_MSM_GPIO_PINS(121);
+DECLARE_MSM_GPIO_PINS(122);
+DECLARE_MSM_GPIO_PINS(123);
+DECLARE_MSM_GPIO_PINS(124);
+DECLARE_MSM_GPIO_PINS(125);
+DECLARE_MSM_GPIO_PINS(126);
+DECLARE_MSM_GPIO_PINS(127);
+DECLARE_MSM_GPIO_PINS(128);
+DECLARE_MSM_GPIO_PINS(129);
+DECLARE_MSM_GPIO_PINS(130);
+DECLARE_MSM_GPIO_PINS(131);
+DECLARE_MSM_GPIO_PINS(132);
+DECLARE_MSM_GPIO_PINS(133);
+DECLARE_MSM_GPIO_PINS(134);
+DECLARE_MSM_GPIO_PINS(135);
+DECLARE_MSM_GPIO_PINS(136);
+DECLARE_MSM_GPIO_PINS(137);
+DECLARE_MSM_GPIO_PINS(138);
+DECLARE_MSM_GPIO_PINS(139);
+DECLARE_MSM_GPIO_PINS(140);
+DECLARE_MSM_GPIO_PINS(141);
+DECLARE_MSM_GPIO_PINS(142);
+DECLARE_MSM_GPIO_PINS(143);
+DECLARE_MSM_GPIO_PINS(144);
+DECLARE_MSM_GPIO_PINS(145);
+DECLARE_MSM_GPIO_PINS(146);
+DECLARE_MSM_GPIO_PINS(147);
+DECLARE_MSM_GPIO_PINS(148);
+DECLARE_MSM_GPIO_PINS(149);
+DECLARE_MSM_GPIO_PINS(150);
+DECLARE_MSM_GPIO_PINS(151);
+DECLARE_MSM_GPIO_PINS(152);
+DECLARE_MSM_GPIO_PINS(153);
+DECLARE_MSM_GPIO_PINS(154);
+DECLARE_MSM_GPIO_PINS(155);
+
+static const unsigned int sdc1_rclk_pins[] = { 156 };
+static const unsigned int sdc1_clk_pins[] = { 157 };
+static const unsigned int sdc1_cmd_pins[] = { 158 };
+static const unsigned int sdc1_data_pins[] = { 159 };
+
+enum sar2130p_functions {
+	msm_mux_gpio,
+	msm_mux_aoss_cti,
+	msm_mux_atest_char,
+	msm_mux_atest_char0,
+	msm_mux_atest_char1,
+	msm_mux_atest_char2,
+	msm_mux_atest_char3,
+	msm_mux_atest_usb0,
+	msm_mux_atest_usb00,
+	msm_mux_atest_usb01,
+	msm_mux_atest_usb02,
+	msm_mux_atest_usb03,
+	msm_mux_audio_ref,
+	msm_mux_cam_mclk,
+	msm_mux_cci_async,
+	msm_mux_cci_i2c,
+	msm_mux_cci_timer0,
+	msm_mux_cci_timer1,
+	msm_mux_cci_timer2,
+	msm_mux_cci_timer3,
+	msm_mux_cci_timer4,
+	msm_mux_cri_trng,
+	msm_mux_cri_trng0,
+	msm_mux_cri_trng1,
+	msm_mux_dbg_out,
+	msm_mux_ddr_bist,
+	msm_mux_ddr_pxi0,
+	msm_mux_ddr_pxi1,
+	msm_mux_ddr_pxi2,
+	msm_mux_ddr_pxi3,
+	msm_mux_dp0_hot,
+	msm_mux_ext_mclk0,
+	msm_mux_ext_mclk1,
+	msm_mux_gcc_gp1,
+	msm_mux_gcc_gp2,
+	msm_mux_gcc_gp3,
+	msm_mux_host2wlan_sol,
+	msm_mux_i2s0_data0,
+	msm_mux_i2s0_data1,
+	msm_mux_i2s0_sck,
+	msm_mux_i2s0_ws,
+	msm_mux_ibi_i3c,
+	msm_mux_jitter_bist,
+	msm_mux_mdp_vsync,
+	msm_mux_mdp_vsync0,
+	msm_mux_mdp_vsync1,
+	msm_mux_mdp_vsync2,
+	msm_mux_mdp_vsync3,
+	msm_mux_pcie0_clkreqn,
+	msm_mux_pcie1_clkreqn,
+	msm_mux_phase_flag0,
+	msm_mux_phase_flag1,
+	msm_mux_phase_flag10,
+	msm_mux_phase_flag11,
+	msm_mux_phase_flag12,
+	msm_mux_phase_flag13,
+	msm_mux_phase_flag14,
+	msm_mux_phase_flag15,
+	msm_mux_phase_flag16,
+	msm_mux_phase_flag17,
+	msm_mux_phase_flag18,
+	msm_mux_phase_flag19,
+	msm_mux_phase_flag2,
+	msm_mux_phase_flag20,
+	msm_mux_phase_flag21,
+	msm_mux_phase_flag22,
+	msm_mux_phase_flag23,
+	msm_mux_phase_flag24,
+	msm_mux_phase_flag25,
+	msm_mux_phase_flag26,
+	msm_mux_phase_flag27,
+	msm_mux_phase_flag28,
+	msm_mux_phase_flag29,
+	msm_mux_phase_flag3,
+	msm_mux_phase_flag30,
+	msm_mux_phase_flag31,
+	msm_mux_phase_flag4,
+	msm_mux_phase_flag5,
+	msm_mux_phase_flag6,
+	msm_mux_phase_flag7,
+	msm_mux_phase_flag8,
+	msm_mux_phase_flag9,
+	msm_mux_pll_bist,
+	msm_mux_pll_clk,
+	msm_mux_prng_rosc0,
+	msm_mux_prng_rosc1,
+	msm_mux_prng_rosc2,
+	msm_mux_prng_rosc3,
+	msm_mux_qdss_cti,
+	msm_mux_qdss_gpio,
+	msm_mux_qdss_gpio0,
+	msm_mux_qdss_gpio1,
+	msm_mux_qdss_gpio10,
+	msm_mux_qdss_gpio11,
+	msm_mux_qdss_gpio12,
+	msm_mux_qdss_gpio13,
+	msm_mux_qdss_gpio14,
+	msm_mux_qdss_gpio15,
+	msm_mux_qdss_gpio2,
+	msm_mux_qdss_gpio3,
+	msm_mux_qdss_gpio4,
+	msm_mux_qdss_gpio5,
+	msm_mux_qdss_gpio6,
+	msm_mux_qdss_gpio7,
+	msm_mux_qdss_gpio8,
+	msm_mux_qdss_gpio9,
+	msm_mux_qspi0,
+	msm_mux_qspi1,
+	msm_mux_qspi2,
+	msm_mux_qspi3,
+	msm_mux_qspi_clk,
+	msm_mux_qspi_cs0,
+	msm_mux_qspi_cs1,
+	msm_mux_qup0,
+	msm_mux_qup1,
+	msm_mux_qup2,
+	msm_mux_qup3,
+	msm_mux_qup4,
+	msm_mux_qup5,
+	msm_mux_qup6,
+	msm_mux_qup7,
+	msm_mux_qup8,
+	msm_mux_qup9,
+	msm_mux_qup10,
+	msm_mux_qup11,
+	msm_mux_tb_trig,
+	msm_mux_tgu_ch0,
+	msm_mux_tgu_ch1,
+	msm_mux_tgu_ch2,
+	msm_mux_tgu_ch3,
+	msm_mux_tmess_prng0,
+	msm_mux_tmess_prng1,
+	msm_mux_tmess_prng2,
+	msm_mux_tmess_prng3,
+	msm_mux_tsense_pwm1,
+	msm_mux_tsense_pwm2,
+	msm_mux_usb0_phy,
+	msm_mux_vsense_trigger,
+	msm_mux__,
+};
+
+static const char * const gpio_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7",
+	"gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14",
+	"gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21",
+	"gpio22", "gpio23", "gpio24", "gpio25", "gpio26", "gpio27", "gpio28",
+	"gpio29", "gpio30", "gpio31", "gpio32", "gpio33", "gpio34", "gpio35",
+	"gpio36", "gpio37", "gpio38", "gpio39", "gpio40", "gpio41", "gpio42",
+	"gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48", "gpio49",
+	"gpio50", "gpio51", "gpio52", "gpio53", "gpio54", "gpio55", "gpio56",
+	"gpio57", "gpio58", "gpio59", "gpio60", "gpio61", "gpio62", "gpio63",
+	"gpio64", "gpio65", "gpio66", "gpio67", "gpio68", "gpio69", "gpio70",
+	"gpio71", "gpio72", "gpio73", "gpio74", "gpio75", "gpio76", "gpio77",
+	"gpio78", "gpio79", "gpio80", "gpio81", "gpio82", "gpio83", "gpio84",
+	"gpio85", "gpio86", "gpio87", "gpio88", "gpio89", "gpio90", "gpio91",
+	"gpio92", "gpio93", "gpio94", "gpio95", "gpio96", "gpio97", "gpio98",
+	"gpio99", "gpio100", "gpio101", "gpio102", "gpio103", "gpio104",
+	"gpio105", "gpio106", "gpio107", "gpio108", "gpio109", "gpio110",
+	"gpio111", "gpio112", "gpio113", "gpio114", "gpio115", "gpio116",
+	"gpio117", "gpio118", "gpio119", "gpio120", "gpio121", "gpio122",
+	"gpio123", "gpio124", "gpio125", "gpio126", "gpio127", "gpio128",
+	"gpio129", "gpio130", "gpio131", "gpio132", "gpio133", "gpio134",
+	"gpio135", "gpio136", "gpio137", "gpio138", "gpio139", "gpio140",
+	"gpio141", "gpio142", "gpio143", "gpio144", "gpio145", "gpio146",
+	"gpio147", "gpio148", "gpio149", "gpio150", "gpio151", "gpio152",
+	"gpio153", "gpio154", "gpio155",
+};
+
+static const char * const aoss_cti_groups[] = {
+	"gpio20", "gpio21", "gpio22", "gpio23",
+};
+
+static const char * const atest_char_groups[] = {
+	"gpio45",
+};
+
+static const char * const atest_char0_groups[] = {
+	"gpio90",
+};
+
+static const char * const atest_char1_groups[] = {
+	"gpio89",
+};
+
+static const char * const atest_char2_groups[] = {
+	"gpio88",
+};
+
+static const char * const atest_char3_groups[] = {
+	"gpio87",
+};
+
+static const char * const atest_usb0_groups[] = {
+	"gpio26",
+};
+
+static const char * const atest_usb00_groups[] = {
+	"gpio110",
+};
+
+static const char * const atest_usb01_groups[] = {
+	"gpio109",
+};
+
+static const char * const atest_usb02_groups[] = {
+	"gpio27",
+};
+
+static const char * const atest_usb03_groups[] = {
+	"gpio60",
+};
+
+static const char * const audio_ref_groups[] = {
+	"gpio103",
+};
+
+static const char * const cam_mclk_groups[] = {
+	"gpio69", "gpio70", "gpio71", "gpio72", "gpio73", "gpio74", "gpio75",
+	"gpio76",
+};
+
+static const char * const cci_async_groups[] = {
+	"gpio80", "gpio81", "gpio82",
+};
+
+static const char * const cci_i2c_groups[] = {
+	"gpio67", "gpio68", "gpio78", "gpio79", "gpio80", "gpio81", "gpio83",
+	"gpio84", "gpio85", "gpio86", "gpio87", "gpio88", "gpio89", "gpio90",
+	"gpio91", "gpio92",
+};
+
+static const char * const cci_timer0_groups[] = {
+	"gpio77",
+};
+
+static const char * const cci_timer1_groups[] = {
+	"gpio78",
+};
+
+static const char * const cci_timer2_groups[] = {
+	"gpio79",
+};
+
+static const char * const cci_timer3_groups[] = {
+	"gpio80",
+};
+
+static const char * const cci_timer4_groups[] = {
+	"gpio81",
+};
+
+static const char * const cri_trng_groups[] = {
+	"gpio60",
+};
+
+static const char * const cri_trng0_groups[] = {
+	"gpio70",
+};
+
+static const char * const cri_trng1_groups[] = {
+	"gpio71",
+};
+
+static const char * const dbg_out_groups[] = {
+	"gpio59",
+};
+
+static const char * const ddr_bist_groups[] = {
+	"gpio4", "gpio5", "gpio100", "gpio103",
+};
+
+static const char * const ddr_pxi0_groups[] = {
+	"gpio56", "gpio57",
+};
+
+static const char * const ddr_pxi1_groups[] = {
+	"gpio41", "gpio45",
+};
+
+static const char * const ddr_pxi2_groups[] = {
+	"gpio48", "gpio55",
+};
+
+static const char * const ddr_pxi3_groups[] = {
+	"gpio46", "gpio47",
+};
+
+static const char * const dp0_hot_groups[] = {
+	"gpio35", "gpio103",
+};
+
+static const char * const ext_mclk0_groups[] = {
+	"gpio104",
+};
+
+static const char * const ext_mclk1_groups[] = {
+	"gpio103",
+};
+
+static const char * const gcc_gp1_groups[] = {
+	"gpio129", "gpio132",
+};
+
+static const char * const gcc_gp2_groups[] = {
+	"gpio130", "gpio135",
+};
+
+static const char * const gcc_gp3_groups[] = {
+	"gpio131", "gpio136",
+};
+
+static const char * const host2wlan_sol_groups[] = {
+	"gpio111",
+};
+
+static const char * const i2s0_data0_groups[] = {
+	"gpio106",
+};
+
+static const char * const i2s0_data1_groups[] = {
+	"gpio107",
+};
+
+static const char * const i2s0_sck_groups[] = {
+	"gpio105",
+};
+
+static const char * const i2s0_ws_groups[] = {
+	"gpio108",
+};
+
+static const char * const ibi_i3c_groups[] = {
+	"gpio0", "gpio1", "gpio91", "gpio92",
+};
+
+static const char * const jitter_bist_groups[] = {
+	"gpio0",
+};
+
+static const char * const mdp_vsync_groups[] = {
+	"gpio12", "gpio13", "gpio41", "gpio49", "gpio50",
+};
+
+static const char * const mdp_vsync0_groups[] = {
+	"gpio49",
+};
+
+static const char * const mdp_vsync1_groups[] = {
+	"gpio49",
+};
+
+static const char * const mdp_vsync2_groups[] = {
+	"gpio50",
+};
+
+static const char * const mdp_vsync3_groups[] = {
+	"gpio50",
+};
+
+static const char * const pcie0_clkreqn_groups[] = {
+	"gpio56",
+};
+
+static const char * const pcie1_clkreqn_groups[] = {
+	"gpio59",
+};
+
+static const char * const phase_flag0_groups[] = {
+	"gpio133",
+};
+
+static const char * const phase_flag1_groups[] = {
+	"gpio128",
+};
+
+static const char * const phase_flag10_groups[] = {
+	"gpio94",
+};
+
+static const char * const phase_flag11_groups[] = {
+	"gpio93",
+};
+
+static const char * const phase_flag12_groups[] = {
+	"gpio134",
+};
+
+static const char * const phase_flag13_groups[] = {
+	"gpio139",
+};
+
+static const char * const phase_flag14_groups[] = {
+	"gpio138",
+};
+
+static const char * const phase_flag15_groups[] = {
+	"gpio137",
+};
+
+static const char * const phase_flag16_groups[] = {
+	"gpio62",
+};
+
+static const char * const phase_flag17_groups[] = {
+	"gpio61",
+};
+
+static const char * const phase_flag18_groups[] = {
+	"gpio41",
+};
+
+static const char * const phase_flag19_groups[] = {
+	"gpio23",
+};
+
+static const char * const phase_flag2_groups[] = {
+	"gpio127",
+};
+
+static const char * const phase_flag20_groups[] = {
+	"gpio22",
+};
+
+static const char * const phase_flag21_groups[] = {
+	"gpio21",
+};
+
+static const char * const phase_flag22_groups[] = {
+	"gpio19",
+};
+
+static const char * const phase_flag23_groups[] = {
+	"gpio18",
+};
+
+static const char * const phase_flag24_groups[] = {
+	"gpio17",
+};
+
+static const char * const phase_flag25_groups[] = {
+	"gpio16",
+};
+
+static const char * const phase_flag26_groups[] = {
+	"gpio13",
+};
+
+static const char * const phase_flag27_groups[] = {
+	"gpio12",
+};
+
+static const char * const phase_flag28_groups[] = {
+	"gpio3",
+};
+
+static const char * const phase_flag29_groups[] = {
+	"gpio2",
+};
+
+static const char * const phase_flag3_groups[] = {
+	"gpio126",
+};
+
+static const char * const phase_flag30_groups[] = {
+	"gpio149",
+};
+
+static const char * const phase_flag31_groups[] = {
+	"gpio148",
+};
+
+static const char * const phase_flag4_groups[] = {
+	"gpio151",
+};
+
+static const char * const phase_flag5_groups[] = {
+	"gpio150",
+};
+
+static const char * const phase_flag6_groups[] = {
+	"gpio98",
+};
+
+static const char * const phase_flag7_groups[] = {
+	"gpio97",
+};
+
+static const char * const phase_flag8_groups[] = {
+	"gpio96",
+};
+
+static const char * const phase_flag9_groups[] = {
+	"gpio95",
+};
+
+static const char * const pll_bist_groups[] = {
+	"gpio8",
+};
+
+static const char * const pll_clk_groups[] = {
+	"gpio54",
+};
+
+static const char * const prng_rosc0_groups[] = {
+	"gpio72",
+};
+
+static const char * const prng_rosc1_groups[] = {
+	"gpio73",
+};
+
+static const char * const prng_rosc2_groups[] = {
+	"gpio74",
+};
+
+static const char * const prng_rosc3_groups[] = {
+	"gpio75",
+};
+
+static const char * const qdss_cti_groups[] = {
+	"gpio28", "gpio29", "gpio36", "gpio37", "gpio38", "gpio38", "gpio47",
+	"gpio48", "gpio53", "gpio53", "gpio105", "gpio106", "gpio154",
+	"gpio155",
+};
+
+static const char * const qdss_gpio_groups[] = {
+	"gpio89", "gpio90", "gpio109", "gpio110",
+};
+
+static const char * const qdss_gpio0_groups[] = {
+	"gpio24", "gpio65",
+};
+
+static const char * const qdss_gpio1_groups[] = {
+	"gpio25", "gpio66",
+};
+
+static const char * const qdss_gpio10_groups[] = {
+	"gpio63", "gpio83",
+};
+
+static const char * const qdss_gpio11_groups[] = {
+	"gpio64", "gpio84",
+};
+
+static const char * const qdss_gpio12_groups[] = {
+	"gpio39", "gpio85",
+};
+
+static const char * const qdss_gpio13_groups[] = {
+	"gpio10", "gpio86",
+};
+
+static const char * const qdss_gpio14_groups[] = {
+	"gpio45", "gpio87",
+};
+
+static const char * const qdss_gpio15_groups[] = {
+	"gpio11", "gpio88",
+};
+
+static const char * const qdss_gpio2_groups[] = {
+	"gpio26", "gpio67",
+};
+
+static const char * const qdss_gpio3_groups[] = {
+	"gpio27", "gpio68",
+};
+
+static const char * const qdss_gpio4_groups[] = {
+	"gpio30", "gpio77",
+};
+
+static const char * const qdss_gpio5_groups[] = {
+	"gpio31", "gpio78",
+};
+
+static const char * const qdss_gpio6_groups[] = {
+	"gpio4", "gpio79",
+};
+
+static const char * const qdss_gpio7_groups[] = {
+	"gpio5", "gpio80",
+};
+
+static const char * const qdss_gpio8_groups[] = {
+	"gpio6", "gpio81",
+};
+
+static const char * const qdss_gpio9_groups[] = {
+	"gpio7", "gpio82",
+};
+
+static const char * const qspi0_groups[] = {
+	"gpio32",
+};
+
+static const char * const qspi1_groups[] = {
+	"gpio33",
+};
+
+static const char * const qspi2_groups[] = {
+	"gpio36",
+};
+
+static const char * const qspi3_groups[] = {
+	"gpio37",
+};
+
+static const char * const qspi_clk_groups[] = {
+	"gpio34",
+};
+
+static const char * const qspi_cs0_groups[] = {
+	"gpio35",
+};
+
+static const char * const qspi_cs1_groups[] = {
+	"gpio38",
+};
+
+static const char * const qup0_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3", "gpio93",
+};
+
+static const char * const qup1_groups[] = {
+	"gpio2", "gpio3", "gpio61", "gpio62",
+};
+
+static const char * const qup2_groups[] = {
+	"gpio12", "gpio13", "gpio22", "gpio23",
+};
+
+static const char * const qup3_groups[] = {
+	"gpio16", "gpio17", "gpio18", "gpio19", "gpio41",
+};
+
+static const char * const qup4_groups[] = {
+	"gpio20", "gpio21", "gpio22", "gpio23", "gpio94",
+};
+
+static const char * const qup5_groups[] = {
+	"gpio95", "gpio96", "gpio97", "gpio98",
+};
+
+static const char * const qup6_groups[] = {
+	"gpio63", "gpio64", "gpio91", "gpio92",
+};
+
+static const char * const qup7_groups[] = {
+	"gpio24", "gpio25", "gpio26", "gpio27",
+};
+
+static const char * const qup8_groups[] = {
+	"gpio8", "gpio9", "gpio10", "gpio11",
+};
+
+static const char * const qup9_groups[] = {
+	"gpio34", "gpio35", "gpio109", "gpio110",
+};
+
+static const char * const qup10_groups[] = {
+	"gpio4", "gpio5", "gpio6", "gpio7",
+};
+
+static const char * const qup11_groups[] = {
+	"gpio14", "gpio15", "gpio28", "gpio30",
+};
+
+static const char * const tb_trig_groups[] = {
+	"gpio69",
+};
+
+static const char * const tgu_ch0_groups[] = {
+	"gpio20",
+};
+
+static const char * const tgu_ch1_groups[] = {
+	"gpio21",
+};
+
+static const char * const tgu_ch2_groups[] = {
+	"gpio22",
+};
+
+static const char * const tgu_ch3_groups[] = {
+	"gpio23",
+};
+
+static const char * const tmess_prng0_groups[] = {
+	"gpio80",
+};
+
+static const char * const tmess_prng1_groups[] = {
+	"gpio79",
+};
+
+static const char * const tmess_prng2_groups[] = {
+	"gpio83",
+};
+
+static const char * const tmess_prng3_groups[] = {
+	"gpio81",
+};
+
+static const char * const tsense_pwm1_groups[] = {
+	"gpio86",
+};
+
+static const char * const tsense_pwm2_groups[] = {
+	"gpio86",
+};
+
+static const char * const usb0_phy_groups[] = {
+	"gpio100",
+};
+
+static const char * const vsense_trigger_groups[] = {
+	"gpio36",
+};
+
+static const struct pinfunction sar2130p_functions[] = {
+	MSM_PIN_FUNCTION(gpio),
+	MSM_PIN_FUNCTION(qup0),
+	MSM_PIN_FUNCTION(ibi_i3c),
+	MSM_PIN_FUNCTION(jitter_bist),
+	MSM_PIN_FUNCTION(qup1),
+	MSM_PIN_FUNCTION(phase_flag29),
+	MSM_PIN_FUNCTION(phase_flag28),
+	MSM_PIN_FUNCTION(qup10),
+	MSM_PIN_FUNCTION(ddr_bist),
+	MSM_PIN_FUNCTION(qdss_gpio6),
+	MSM_PIN_FUNCTION(qdss_gpio7),
+	MSM_PIN_FUNCTION(qdss_gpio8),
+	MSM_PIN_FUNCTION(qdss_gpio9),
+	MSM_PIN_FUNCTION(qup8),
+	MSM_PIN_FUNCTION(pll_bist),
+	MSM_PIN_FUNCTION(qdss_gpio13),
+	MSM_PIN_FUNCTION(qdss_gpio15),
+	MSM_PIN_FUNCTION(qup2),
+	MSM_PIN_FUNCTION(mdp_vsync),
+	MSM_PIN_FUNCTION(phase_flag27),
+	MSM_PIN_FUNCTION(phase_flag26),
+	MSM_PIN_FUNCTION(qup11),
+	MSM_PIN_FUNCTION(qup3),
+	MSM_PIN_FUNCTION(phase_flag25),
+	MSM_PIN_FUNCTION(phase_flag24),
+	MSM_PIN_FUNCTION(phase_flag23),
+	MSM_PIN_FUNCTION(phase_flag22),
+	MSM_PIN_FUNCTION(qup4),
+	MSM_PIN_FUNCTION(aoss_cti),
+	MSM_PIN_FUNCTION(tgu_ch0),
+	MSM_PIN_FUNCTION(phase_flag21),
+	MSM_PIN_FUNCTION(tgu_ch1),
+	MSM_PIN_FUNCTION(phase_flag20),
+	MSM_PIN_FUNCTION(tgu_ch2),
+	MSM_PIN_FUNCTION(phase_flag19),
+	MSM_PIN_FUNCTION(tgu_ch3),
+	MSM_PIN_FUNCTION(qup7),
+	MSM_PIN_FUNCTION(qdss_gpio0),
+	MSM_PIN_FUNCTION(qdss_gpio1),
+	MSM_PIN_FUNCTION(qdss_gpio2),
+	MSM_PIN_FUNCTION(atest_usb0),
+	MSM_PIN_FUNCTION(qdss_gpio3),
+	MSM_PIN_FUNCTION(atest_usb02),
+	MSM_PIN_FUNCTION(qdss_cti),
+	MSM_PIN_FUNCTION(qdss_gpio4),
+	MSM_PIN_FUNCTION(qdss_gpio5),
+	MSM_PIN_FUNCTION(qspi0),
+	MSM_PIN_FUNCTION(qspi1),
+	MSM_PIN_FUNCTION(qspi_clk),
+	MSM_PIN_FUNCTION(qup9),
+	MSM_PIN_FUNCTION(qspi_cs0),
+	MSM_PIN_FUNCTION(dp0_hot),
+	MSM_PIN_FUNCTION(qspi2),
+	MSM_PIN_FUNCTION(vsense_trigger),
+	MSM_PIN_FUNCTION(qspi3),
+	MSM_PIN_FUNCTION(qspi_cs1),
+	MSM_PIN_FUNCTION(qdss_gpio12),
+	MSM_PIN_FUNCTION(phase_flag18),
+	MSM_PIN_FUNCTION(ddr_pxi1),
+	MSM_PIN_FUNCTION(qdss_gpio14),
+	MSM_PIN_FUNCTION(atest_char),
+	MSM_PIN_FUNCTION(ddr_pxi3),
+	MSM_PIN_FUNCTION(ddr_pxi2),
+	MSM_PIN_FUNCTION(mdp_vsync0),
+	MSM_PIN_FUNCTION(mdp_vsync1),
+	MSM_PIN_FUNCTION(mdp_vsync2),
+	MSM_PIN_FUNCTION(mdp_vsync3),
+	MSM_PIN_FUNCTION(pll_clk),
+	MSM_PIN_FUNCTION(pcie0_clkreqn),
+	MSM_PIN_FUNCTION(ddr_pxi0),
+	MSM_PIN_FUNCTION(pcie1_clkreqn),
+	MSM_PIN_FUNCTION(dbg_out),
+	MSM_PIN_FUNCTION(cri_trng),
+	MSM_PIN_FUNCTION(atest_usb03),
+	MSM_PIN_FUNCTION(phase_flag17),
+	MSM_PIN_FUNCTION(phase_flag16),
+	MSM_PIN_FUNCTION(qup6),
+	MSM_PIN_FUNCTION(qdss_gpio10),
+	MSM_PIN_FUNCTION(qdss_gpio11),
+	MSM_PIN_FUNCTION(cci_i2c),
+	MSM_PIN_FUNCTION(cam_mclk),
+	MSM_PIN_FUNCTION(tb_trig),
+	MSM_PIN_FUNCTION(cri_trng0),
+	MSM_PIN_FUNCTION(cri_trng1),
+	MSM_PIN_FUNCTION(prng_rosc0),
+	MSM_PIN_FUNCTION(prng_rosc1),
+	MSM_PIN_FUNCTION(prng_rosc2),
+	MSM_PIN_FUNCTION(prng_rosc3),
+	MSM_PIN_FUNCTION(cci_timer0),
+	MSM_PIN_FUNCTION(cci_timer1),
+	MSM_PIN_FUNCTION(cci_timer2),
+	MSM_PIN_FUNCTION(tmess_prng1),
+	MSM_PIN_FUNCTION(cci_timer3),
+	MSM_PIN_FUNCTION(cci_async),
+	MSM_PIN_FUNCTION(tmess_prng0),
+	MSM_PIN_FUNCTION(cci_timer4),
+	MSM_PIN_FUNCTION(tmess_prng3),
+	MSM_PIN_FUNCTION(tmess_prng2),
+	MSM_PIN_FUNCTION(tsense_pwm1),
+	MSM_PIN_FUNCTION(tsense_pwm2),
+	MSM_PIN_FUNCTION(atest_char3),
+	MSM_PIN_FUNCTION(atest_char2),
+	MSM_PIN_FUNCTION(qdss_gpio),
+	MSM_PIN_FUNCTION(atest_char1),
+	MSM_PIN_FUNCTION(atest_char0),
+	MSM_PIN_FUNCTION(phase_flag11),
+	MSM_PIN_FUNCTION(phase_flag10),
+	MSM_PIN_FUNCTION(qup5),
+	MSM_PIN_FUNCTION(phase_flag9),
+	MSM_PIN_FUNCTION(phase_flag8),
+	MSM_PIN_FUNCTION(phase_flag7),
+	MSM_PIN_FUNCTION(phase_flag6),
+	MSM_PIN_FUNCTION(usb0_phy),
+	MSM_PIN_FUNCTION(ext_mclk1),
+	MSM_PIN_FUNCTION(audio_ref),
+	MSM_PIN_FUNCTION(ext_mclk0),
+	MSM_PIN_FUNCTION(i2s0_sck),
+	MSM_PIN_FUNCTION(i2s0_data0),
+	MSM_PIN_FUNCTION(i2s0_data1),
+	MSM_PIN_FUNCTION(i2s0_ws),
+	MSM_PIN_FUNCTION(atest_usb01),
+	MSM_PIN_FUNCTION(atest_usb00),
+	MSM_PIN_FUNCTION(host2wlan_sol),
+	MSM_PIN_FUNCTION(phase_flag3),
+	MSM_PIN_FUNCTION(phase_flag2),
+	MSM_PIN_FUNCTION(phase_flag1),
+	MSM_PIN_FUNCTION(gcc_gp1),
+	MSM_PIN_FUNCTION(gcc_gp2),
+	MSM_PIN_FUNCTION(gcc_gp3),
+	MSM_PIN_FUNCTION(phase_flag0),
+	MSM_PIN_FUNCTION(phase_flag12),
+	MSM_PIN_FUNCTION(phase_flag15),
+	MSM_PIN_FUNCTION(phase_flag14),
+	MSM_PIN_FUNCTION(phase_flag13),
+	MSM_PIN_FUNCTION(phase_flag31),
+	MSM_PIN_FUNCTION(phase_flag30),
+	MSM_PIN_FUNCTION(phase_flag5),
+	MSM_PIN_FUNCTION(phase_flag4),
+};
+
+/* Every pin is maintained as a single group, and missing or non-existing pin
+ * would be maintained as dummy group to synchronize pin group index with
+ * pin descriptor registered with pinctrl core.
+ * Clients would not be able to request these dummy pin groups.
+ */
+static const struct msm_pingroup sar2130p_groups[] = {
+	[0] = PINGROUP(0, qup0, ibi_i3c, jitter_bist, _, _, _, _, _, _),
+	[1] = PINGROUP(1, qup0, ibi_i3c, _, _, _, _, _, _, _),
+	[2] = PINGROUP(2, qup0, qup1, phase_flag29, _, _, _, _, _, _),
+	[3] = PINGROUP(3, qup0, qup1, phase_flag28, _, _, _, _, _, _),
+	[4] = PINGROUP(4, qup10, ddr_bist, qdss_gpio6, _, _, _, _, _, _),
+	[5] = PINGROUP(5, qup10, ddr_bist, qdss_gpio7, _, _, _, _, _, _),
+	[6] = PINGROUP(6, qup10, qdss_gpio8, _, _, _, _, _, _, _),
+	[7] = PINGROUP(7, qup10, qdss_gpio9, _, _, _, _, _, _, _),
+	[8] = PINGROUP(8, qup8, pll_bist, _, _, _, _, _, _, _),
+	[9] = PINGROUP(9, qup8, _, _, _, _, _, _, _, _),
+	[10] = PINGROUP(10, qup8, qdss_gpio13, _, _, _, _, _, _, _),
+	[11] = PINGROUP(11, qup8, qdss_gpio15, _, _, _, _, _, _, _),
+	[12] = PINGROUP(12, qup2, mdp_vsync, phase_flag27, _, _, _, _, _, _),
+	[13] = PINGROUP(13, qup2, mdp_vsync, phase_flag26, _, _, _, _, _, _),
+	[14] = PINGROUP(14, qup11, _, _, _, _, _, _, _, _),
+	[15] = PINGROUP(15, qup11, _, _, _, _, _, _, _, _),
+	[16] = PINGROUP(16, qup3, phase_flag25, _, _, _, _, _, _, _),
+	[17] = PINGROUP(17, qup3, phase_flag24, _, _, _, _, _, _, _),
+	[18] = PINGROUP(18, qup3, phase_flag23, _, _, _, _, _, _, _),
+	[19] = PINGROUP(19, qup3, phase_flag22, _, _, _, _, _, _, _),
+	[20] = PINGROUP(20, qup4, aoss_cti, tgu_ch0, _, _, _, _, _, _),
+	[21] = PINGROUP(21, qup4, aoss_cti, phase_flag21, tgu_ch1, _, _, _, _, _),
+	[22] = PINGROUP(22, qup4, qup2, aoss_cti, phase_flag20, tgu_ch2, _, _, _, _),
+	[23] = PINGROUP(23, qup4, qup2, aoss_cti, phase_flag19, tgu_ch3, _, _, _, _),
+	[24] = PINGROUP(24, qup7, qdss_gpio0, _, _, _, _, _, _, _),
+	[25] = PINGROUP(25, qup7, qdss_gpio1, _, _, _, _, _, _, _),
+	[26] = PINGROUP(26, qup7, qdss_gpio2, atest_usb0, _, _, _, _, _, _),
+	[27] = PINGROUP(27, qup7, qdss_gpio3, atest_usb02, _, _, _, _, _, _),
+	[28] = PINGROUP(28, qup11, qdss_cti, _, _, _, _, _, _, _),
+	[29] = PINGROUP(29, qdss_cti, _, _, _, _, _, _, _, _),
+	[30] = PINGROUP(30, qup11, qdss_gpio4, _, _, _, _, _, _, _),
+	[31] = PINGROUP(31, qdss_gpio5, _, _, _, _, _, _, _, _),
+	[32] = PINGROUP(32, qspi0, _, _, _, _, _, _, _, _),
+	[33] = PINGROUP(33, qspi1, _, _, _, _, _, _, _, _),
+	[34] = PINGROUP(34, qspi_clk, qup9, _, _, _, _, _, _, _),
+	[35] = PINGROUP(35, qspi_cs0, qup9, dp0_hot, _, _, _, _, _, _),
+	[36] = PINGROUP(36, qspi2, qdss_cti, vsense_trigger, _, _, _, _, _, _),
+	[37] = PINGROUP(37, qspi3, qdss_cti, _, _, _, _, _, _, _),
+	[38] = PINGROUP(38, qspi_cs1, qdss_cti, qdss_cti, _, _, _, _, _, _),
+	[39] = PINGROUP(39, qdss_gpio12, _, _, _, _, _, _, _, _),
+	[40] = PINGROUP(40, _, _, _, _, _, _, _, _, _),
+	[41] = PINGROUP(41, qup3, mdp_vsync, phase_flag18, _, ddr_pxi1, _, _, _, _),
+	[42] = PINGROUP(42, _, _, _, _, _, _, _, _, _),
+	[43] = PINGROUP(43, _, _, _, _, _, _, _, _, _),
+	[44] = PINGROUP(44, _, _, _, _, _, _, _, _, _),
+	[45] = PINGROUP(45, qdss_gpio14, ddr_pxi1, atest_char, _, _, _, _, _, _),
+	[46] = PINGROUP(46, ddr_pxi3, _, _, _, _, _, _, _, _),
+	[47] = PINGROUP(47, qdss_cti, ddr_pxi3, _, _, _, _, _, _, _),
+	[48] = PINGROUP(48, qdss_cti, ddr_pxi2, _, _, _, _, _, _, _),
+	[49] = PINGROUP(49, mdp_vsync, mdp_vsync0, mdp_vsync1, _, _, _, _, _, _),
+	[50] = PINGROUP(50, mdp_vsync, mdp_vsync2, mdp_vsync3, _, _, _, _, _, _),
+	[51] = PINGROUP(51, _, _, _, _, _, _, _, _, _),
+	[52] = PINGROUP(52, _, _, _, _, _, _, _, _, _),
+	[53] = PINGROUP(53, qdss_cti, qdss_cti, _, _, _, _, _, _, _),
+	[54] = PINGROUP(54, pll_clk, _, _, _, _, _, _, _, _),
+	[55] = PINGROUP(55, _, ddr_pxi2, _, _, _, _, _, _, _),
+	[56] = PINGROUP(56, pcie0_clkreqn, _, ddr_pxi0, _, _, _, _, _, _),
+	[57] = PINGROUP(57, ddr_pxi0, _, _, _, _, _, _, _, _),
+	[58] = PINGROUP(58, _, _, _, _, _, _, _, _, _),
+	[59] = PINGROUP(59, pcie1_clkreqn, dbg_out, _, _, _, _, _, _, _),
+	[60] = PINGROUP(60, cri_trng, atest_usb03, _, _, _, _, _, _, _),
+	[61] = PINGROUP(61, qup1, phase_flag17, _, _, _, _, _, _, _),
+	[62] = PINGROUP(62, qup1, phase_flag16, _, _, _, _, _, _, _),
+	[63] = PINGROUP(63, qup6, qdss_gpio10, _, _, _, _, _, _, _),
+	[64] = PINGROUP(64, qup6, qdss_gpio11, _, _, _, _, _, _, _),
+	[65] = PINGROUP(65, qdss_gpio0, _, _, _, _, _, _, _, _),
+	[66] = PINGROUP(66, qdss_gpio1, _, _, _, _, _, _, _, _),
+	[67] = PINGROUP(67, cci_i2c, qdss_gpio2, _, _, _, _, _, _, _),
+	[68] = PINGROUP(68, cci_i2c, qdss_gpio3, _, _, _, _, _, _, _),
+	[69] = PINGROUP(69, cam_mclk, tb_trig, _, _, _, _, _, _, _),
+	[70] = PINGROUP(70, cam_mclk, cri_trng0, _, _, _, _, _, _, _),
+	[71] = PINGROUP(71, cam_mclk, cri_trng1, _, _, _, _, _, _, _),
+	[72] = PINGROUP(72, cam_mclk, prng_rosc0, _, _, _, _, _, _, _),
+	[73] = PINGROUP(73, cam_mclk, prng_rosc1, _, _, _, _, _, _, _),
+	[74] = PINGROUP(74, cam_mclk, prng_rosc2, _, _, _, _, _, _, _),
+	[75] = PINGROUP(75, cam_mclk, prng_rosc3, _, _, _, _, _, _, _),
+	[76] = PINGROUP(76, cam_mclk, _, _, _, _, _, _, _, _),
+	[77] = PINGROUP(77, cci_timer0, qdss_gpio4, _, _, _, _, _, _, _),
+	[78] = PINGROUP(78, cci_timer1, cci_i2c, qdss_gpio5, _, _, _, _, _, _),
+	[79] = PINGROUP(79, cci_timer2, cci_i2c, tmess_prng1, qdss_gpio6, _, _, _, _, _),
+	[80] = PINGROUP(80, cci_timer3, cci_i2c, cci_async, tmess_prng0, qdss_gpio7, _, _, _, _),
+	[81] = PINGROUP(81, cci_timer4, cci_i2c, cci_async, tmess_prng3, qdss_gpio8, _, _, _, _),
+	[82] = PINGROUP(82, cci_async, qdss_gpio9, _, _, _, _, _, _, _),
+	[83] = PINGROUP(83, cci_i2c, tmess_prng2, qdss_gpio10, _, _, _, _, _, _),
+	[84] = PINGROUP(84, cci_i2c, qdss_gpio11, _, _, _, _, _, _, _),
+	[85] = PINGROUP(85, cci_i2c, qdss_gpio12, _, _, _, _, _, _, _),
+	[86] = PINGROUP(86, cci_i2c, qdss_gpio13, tsense_pwm1, tsense_pwm2, _, _, _, _, _),
+	[87] = PINGROUP(87, cci_i2c, qdss_gpio14, atest_char3, _, _, _, _, _, _),
+	[88] = PINGROUP(88, cci_i2c, qdss_gpio15, atest_char2, _, _, _, _, _, _),
+	[89] = PINGROUP(89, cci_i2c, qdss_gpio, atest_char1, _, _, _, _, _, _),
+	[90] = PINGROUP(90, cci_i2c, qdss_gpio, atest_char0, _, _, _, _, _, _),
+	[91] = PINGROUP(91, cci_i2c, qup6, ibi_i3c, _, _, _, _, _, _),
+	[92] = PINGROUP(92, cci_i2c, qup6, ibi_i3c, _, _, _, _, _, _),
+	[93] = PINGROUP(93, qup0, phase_flag11, _, _, _, _, _, _, _),
+	[94] = PINGROUP(94, qup4, phase_flag10, _, _, _, _, _, _, _),
+	[95] = PINGROUP(95, qup5, phase_flag9, _, _, _, _, _, _, _),
+	[96] = PINGROUP(96, qup5, phase_flag8, _, _, _, _, _, _, _),
+	[97] = PINGROUP(97, qup5, phase_flag7, _, _, _, _, _, _, _),
+	[98] = PINGROUP(98, qup5, phase_flag6, _, _, _, _, _, _, _),
+	[99] = PINGROUP(99, _, _, _, _, _, _, _, _, _),
+	[100] = PINGROUP(100, usb0_phy, ddr_bist, _, _, _, _, _, _, _),
+	[101] = PINGROUP(101, _, _, _, _, _, _, _, _, _),
+	[102] = PINGROUP(102, _, _, _, _, _, _, _, _, _),
+	[103] = PINGROUP(103, ext_mclk1, audio_ref, dp0_hot, ddr_bist, _, _, _, _, _),
+	[104] = PINGROUP(104, ext_mclk0, _, _, _, _, _, _, _, _),
+	[105] = PINGROUP(105, i2s0_sck, _, qdss_cti, _, _, _, _, _, _),
+	[106] = PINGROUP(106, i2s0_data0, _, qdss_cti, _, _, _, _, _, _),
+	[107] = PINGROUP(107, i2s0_data1, _, _, _, _, _, _, _, _),
+	[108] = PINGROUP(108, i2s0_ws, _, _, _, _, _, _, _, _),
+	[109] = PINGROUP(109, qup9, qdss_gpio, atest_usb01, _, _, _, _, _, _),
+	[110] = PINGROUP(110, qup9, qdss_gpio, atest_usb00, _, _, _, _, _, _),
+	[111] = PINGROUP(111, host2wlan_sol, _, _, _, _, _, _, _, _),
+	[112] = PINGROUP(112, _, _, _, _, _, _, _, _, _),
+	[113] = PINGROUP(113, _, _, _, _, _, _, _, _, _),
+	[114] = PINGROUP(114, _, _, _, _, _, _, _, _, _),
+	[115] = PINGROUP(115, _, _, _, _, _, _, _, _, _),
+	[116] = PINGROUP(116, _, _, _, _, _, _, _, _, _),
+	[117] = PINGROUP(117, _, _, _, _, _, _, _, _, _),
+	[118] = PINGROUP(118, _, _, _, _, _, _, _, _, _),
+	[119] = PINGROUP(119, _, _, _, _, _, _, _, _, _),
+	[120] = PINGROUP(120, _, _, _, _, _, _, _, _, _),
+	[121] = PINGROUP(121, _, _, _, _, _, _, _, _, _),
+	[122] = PINGROUP(122, _, _, _, _, _, _, _, _, _),
+	[123] = PINGROUP(123, _, _, _, _, _, _, _, _, _),
+	[124] = PINGROUP(124, _, _, _, _, _, _, _, _, _),
+	[125] = PINGROUP(125, _, _, _, _, _, _, _, _, _),
+	[126] = PINGROUP(126, phase_flag3, _, _, _, _, _, _, _, _),
+	[127] = PINGROUP(127, phase_flag2, _, _, _, _, _, _, _, _),
+	[128] = PINGROUP(128, phase_flag1, _, _, _, _, _, _, _, _),
+	[129] = PINGROUP(129, gcc_gp1, _, _, _, _, _, _, _, _),
+	[130] = PINGROUP(130, gcc_gp2, _, _, _, _, _, _, _, _),
+	[131] = PINGROUP(131, gcc_gp3, _, _, _, _, _, _, _, _),
+	[132] = PINGROUP(132, gcc_gp1, _, _, _, _, _, _, _, _),
+	[133] = PINGROUP(133, phase_flag0, _, _, _, _, _, _, _, _),
+	[134] = PINGROUP(134, phase_flag12, _, _, _, _, _, _, _, _),
+	[135] = PINGROUP(135, gcc_gp2, _, _, _, _, _, _, _, _),
+	[136] = PINGROUP(136, gcc_gp3, _, _, _, _, _, _, _, _),
+	[137] = PINGROUP(137, phase_flag15, _, _, _, _, _, _, _, _),
+	[138] = PINGROUP(138, phase_flag14, _, _, _, _, _, _, _, _),
+	[139] = PINGROUP(139, phase_flag13, _, _, _, _, _, _, _, _),
+	[140] = PINGROUP(140, _, _, _, _, _, _, _, _, _),
+	[141] = PINGROUP(141, _, _, _, _, _, _, _, _, _),
+	[142] = PINGROUP(142, _, _, _, _, _, _, _, _, _),
+	[143] = PINGROUP(143, _, _, _, _, _, _, _, _, _),
+	[144] = PINGROUP(144, _, _, _, _, _, _, _, _, _),
+	[145] = PINGROUP(145, _, _, _, _, _, _, _, _, _),
+	[146] = PINGROUP(146, _, _, _, _, _, _, _, _, _),
+	[147] = PINGROUP(147, _, _, _, _, _, _, _, _, _),
+	[148] = PINGROUP(148, phase_flag31, _, _, _, _, _, _, _, _),
+	[149] = PINGROUP(149, phase_flag30, _, _, _, _, _, _, _, _),
+	[150] = PINGROUP(150, phase_flag5, _, _, _, _, _, _, _, _),
+	[151] = PINGROUP(151, phase_flag4, _, _, _, _, _, _, _, _),
+	[152] = PINGROUP(152, _, _, _, _, _, _, _, _, _),
+	[153] = PINGROUP(153, _, _, _, _, _, _, _, _, _),
+	[154] = PINGROUP(154, qdss_cti, _, _, _, _, _, _, _, _),
+	[155] = PINGROUP(155, qdss_cti, _, _, _, _, _, _, _, _),
+	[156] = SDC_QDSD_PINGROUP(sdc1_rclk, 0xa1000, 0, 0),
+	[157] = SDC_QDSD_PINGROUP(sdc1_clk, 0xa0000, 13, 6),
+	[158] = SDC_QDSD_PINGROUP(sdc1_cmd, 0xa0000, 11, 3),
+	[159] = SDC_QDSD_PINGROUP(sdc1_data, 0xa0000, 9, 0),
+};
+
+static const struct msm_gpio_wakeirq_map sar2130p_pdc_map[] = {
+	{ 0, 50 }, { 3, 68 }, { 6, 88 }, { 7, 55 }, { 10, 66 }, { 11, 96 },
+	{ 12, 48 }, { 13, 49 }, { 15, 62 }, { 18, 57 }, { 19, 59 }, { 23, 51 },
+	{ 27, 74 }, { 28, 67 }, { 29, 84 }, { 30, 58 }, { 31, 94 }, { 32, 60 },
+	{ 33, 61 }, { 35, 69 }, { 37, 70 }, { 38, 64 }, { 39, 65 }, { 40, 63 },
+	{ 41, 92 }, { 42, 82 }, { 44, 83 }, { 45, 43 }, { 46, 72 }, { 47, 45 },
+	{ 48, 44 }, { 49, 71 }, { 50, 87 }, { 53, 77 }, { 54, 78 },
+	{ 55, 106 }, { 56, 79 }, { 57, 80 }, { 58, 107 }, { 59, 81 },
+	{ 60, 89 }, { 61, 54 }, { 62, 73 }, { 63, 93 }, { 64, 86 }, { 65, 75 },
+	{ 67, 42 }, { 68, 76 }, { 76, 116 }, { 77, 12 }, { 83, 13 },
+	{ 91, 90 }, { 94, 95 }, { 95, 91 }, { 98, 47 }, { 100, 85 },
+	{ 101, 52 }, { 102, 53 }, { 103, 97 }, { 104, 98 }, { 105, 99 },
+	{ 106, 100 }, { 107, 101 }, { 108, 102 }, { 109, 103 }, { 111, 104 },
+	{ 113, 46 }, { 114, 56 }, { 115, 108 }, { 116, 109 }, { 117, 110 },
+	{ 118, 111 }, { 121, 112 }, { 122, 113 }, { 124, 114 }, { 127, 115 },
+	{ 132, 118 }, { 134, 119 }, { 135, 120 }, { 136, 121 }, { 139, 122 },
+	{ 140, 123 }, { 141, 124 }, { 143, 128 }, { 144, 129 }, { 145, 130 },
+	{ 146, 131 }, { 148, 132 }, { 150, 133 }, { 151, 134 }, { 153, 135 },
+	{ 155, 137 },
+};
+
+static const struct msm_pinctrl_soc_data sar2130p_tlmm = {
+	.pins = sar2130p_pins,
+	.npins = ARRAY_SIZE(sar2130p_pins),
+	.functions = sar2130p_functions,
+	.nfunctions = ARRAY_SIZE(sar2130p_functions),
+	.groups = sar2130p_groups,
+	.ngroups = ARRAY_SIZE(sar2130p_groups),
+	.ngpios = 156,
+	.wakeirq_map = sar2130p_pdc_map,
+	.nwakeirq_map = ARRAY_SIZE(sar2130p_pdc_map),
+};
+
+static int sar2130p_tlmm_probe(struct platform_device *pdev)
+{
+	return msm_pinctrl_probe(pdev, &sar2130p_tlmm);
+}
+
+static const struct of_device_id sar2130p_tlmm_of_match[] = {
+	{ .compatible = "qcom,sar2130p-tlmm", .data = &sar2130p_tlmm},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, sar2130p_tlmm_of_match);
+
+static struct platform_driver sar2130p_tlmm_driver = {
+	.driver = {
+		.name = "sar2130p-tlmm",
+		.of_match_table = sar2130p_tlmm_of_match,
+	},
+	.probe = sar2130p_tlmm_probe,
+	.remove = msm_pinctrl_remove,
+};
+
+static int __init sar2130p_tlmm_init(void)
+{
+	return platform_driver_register(&sar2130p_tlmm_driver);
+}
+arch_initcall(sar2130p_tlmm_init);
+
+static void __exit sar2130p_tlmm_exit(void)
+{
+	platform_driver_unregister(&sar2130p_tlmm_driver);
+}
+module_exit(sar2130p_tlmm_exit);
+
+MODULE_DESCRIPTION("QTI SAR2130P TLMM driver");
+MODULE_LICENSE("GPL");

From e2226dbc4a4919d9c8bd9293299b532090bdf020 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Tue, 22 Oct 2024 12:11:37 +0300
Subject: [PATCH 0586/1530] PCI: cpqphp: Fix PCIBIOS_* return value confusion
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Code in and related to PCI_RefinedAccessConfig() has three types of return
type confusion:

 - PCI_RefinedAccessConfig() tests pci_bus_read_config_dword() return value
   against -1.

 - PCI_RefinedAccessConfig() returns both -1 and PCIBIOS_* return codes.

 - Callers of PCI_RefinedAccessConfig() only test for -1.

Make PCI_RefinedAccessConfig() return PCIBIOS_* codes consistently and
adapt callers accordingly.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Link: https://lore.kernel.org/r/20241022091140.3504-2-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/cpqphp_pci.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/pci/hotplug/cpqphp_pci.c b/drivers/pci/hotplug/cpqphp_pci.c
index 718bc6cf12cb3..974c7db3265b5 100644
--- a/drivers/pci/hotplug/cpqphp_pci.c
+++ b/drivers/pci/hotplug/cpqphp_pci.c
@@ -135,11 +135,13 @@ int cpqhp_unconfigure_device(struct pci_func *func)
 static int PCI_RefinedAccessConfig(struct pci_bus *bus, unsigned int devfn, u8 offset, u32 *value)
 {
 	u32 vendID = 0;
+	int ret;
 
-	if (pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, &vendID) == -1)
-		return -1;
+	ret = pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, &vendID);
+	if (ret != PCIBIOS_SUCCESSFUL)
+		return PCIBIOS_DEVICE_NOT_FOUND;
 	if (PCI_POSSIBLE_ERROR(vendID))
-		return -1;
+		return PCIBIOS_DEVICE_NOT_FOUND;
 	return pci_bus_read_config_dword(bus, devfn, offset, value);
 }
 
@@ -202,13 +204,15 @@ static int PCI_ScanBusForNonBridge(struct controller *ctrl, u8 bus_num, u8 *dev_
 {
 	u16 tdevice;
 	u32 work;
+	int ret;
 	u8 tbus;
 
 	ctrl->pci_bus->number = bus_num;
 
 	for (tdevice = 0; tdevice < 0xFF; tdevice++) {
 		/* Scan for access first */
-		if (PCI_RefinedAccessConfig(ctrl->pci_bus, tdevice, 0x08, &work) == -1)
+		ret = PCI_RefinedAccessConfig(ctrl->pci_bus, tdevice, 0x08, &work);
+		if (ret)
 			continue;
 		dbg("Looking for nonbridge bus_num %d dev_num %d\n", bus_num, tdevice);
 		/* Yep we got one. Not a bridge ? */
@@ -220,7 +224,8 @@ static int PCI_ScanBusForNonBridge(struct controller *ctrl, u8 bus_num, u8 *dev_
 	}
 	for (tdevice = 0; tdevice < 0xFF; tdevice++) {
 		/* Scan for access first */
-		if (PCI_RefinedAccessConfig(ctrl->pci_bus, tdevice, 0x08, &work) == -1)
+		ret = PCI_RefinedAccessConfig(ctrl->pci_bus, tdevice, 0x08, &work);
+		if (ret)
 			continue;
 		dbg("Looking for bridge bus_num %d dev_num %d\n", bus_num, tdevice);
 		/* Yep we got one. bridge ? */

From 752430d1d33ed69653a6e8dbdf01f83cdf5be574 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Tue, 22 Oct 2024 12:11:38 +0300
Subject: [PATCH 0587/1530] PCI: cpqphp: Use pci_bus_read_dev_vendor_id() to
 detect presence
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The intent of the first part in PCI_RefinedAccessConfig() is to read Vendor
ID register and detect presence of the device that way.

Remove PCI_RefinedAccessConfig() (which was not named very helpfully to
begin with) and replace the call with pci_bus_read_dev_vendor_id() + read
config because it makes the logic more obvious at the caller side.

Link: https://lore.kernel.org/r/20241022091140.3504-3-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/cpqphp_pci.c | 22 ++++++----------------
 1 file changed, 6 insertions(+), 16 deletions(-)

diff --git a/drivers/pci/hotplug/cpqphp_pci.c b/drivers/pci/hotplug/cpqphp_pci.c
index 974c7db3265b5..7844007dbc862 100644
--- a/drivers/pci/hotplug/cpqphp_pci.c
+++ b/drivers/pci/hotplug/cpqphp_pci.c
@@ -132,20 +132,6 @@ int cpqhp_unconfigure_device(struct pci_func *func)
 	return 0;
 }
 
-static int PCI_RefinedAccessConfig(struct pci_bus *bus, unsigned int devfn, u8 offset, u32 *value)
-{
-	u32 vendID = 0;
-	int ret;
-
-	ret = pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, &vendID);
-	if (ret != PCIBIOS_SUCCESSFUL)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-	if (PCI_POSSIBLE_ERROR(vendID))
-		return PCIBIOS_DEVICE_NOT_FOUND;
-	return pci_bus_read_config_dword(bus, devfn, offset, value);
-}
-
-
 /*
  * cpqhp_set_irq
  *
@@ -211,7 +197,9 @@ static int PCI_ScanBusForNonBridge(struct controller *ctrl, u8 bus_num, u8 *dev_
 
 	for (tdevice = 0; tdevice < 0xFF; tdevice++) {
 		/* Scan for access first */
-		ret = PCI_RefinedAccessConfig(ctrl->pci_bus, tdevice, 0x08, &work);
+		if (!pci_bus_read_dev_vendor_id(ctrl->pci_bus, tdevice, &work, 0))
+			continue;
+		ret = pci_bus_read_config_dword(ctrl->pci_bus, tdevice, 0x08, &work);
 		if (ret)
 			continue;
 		dbg("Looking for nonbridge bus_num %d dev_num %d\n", bus_num, tdevice);
@@ -224,7 +212,9 @@ static int PCI_ScanBusForNonBridge(struct controller *ctrl, u8 bus_num, u8 *dev_
 	}
 	for (tdevice = 0; tdevice < 0xFF; tdevice++) {
 		/* Scan for access first */
-		ret = PCI_RefinedAccessConfig(ctrl->pci_bus, tdevice, 0x08, &work);
+		if (!pci_bus_read_dev_vendor_id(ctrl->pci_bus, tdevice, &work, 0))
+			continue;
+		ret = pci_bus_read_config_dword(ctrl->pci_bus, tdevice, 0x08, &work);
 		if (ret)
 			continue;
 		dbg("Looking for bridge bus_num %d dev_num %d\n", bus_num, tdevice);

From de2cdf110a39a660e810979e480761fed9842436 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Tue, 22 Oct 2024 12:11:39 +0300
Subject: [PATCH 0588/1530] PCI: cpqphp: Use define to read class/revision
 dword
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace literal 0x08 with PCI_CLASS_REVISION.

Link: https://lore.kernel.org/r/20241022091140.3504-4-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/cpqphp_pci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/hotplug/cpqphp_pci.c b/drivers/pci/hotplug/cpqphp_pci.c
index 7844007dbc862..558866c15e03c 100644
--- a/drivers/pci/hotplug/cpqphp_pci.c
+++ b/drivers/pci/hotplug/cpqphp_pci.c
@@ -199,7 +199,7 @@ static int PCI_ScanBusForNonBridge(struct controller *ctrl, u8 bus_num, u8 *dev_
 		/* Scan for access first */
 		if (!pci_bus_read_dev_vendor_id(ctrl->pci_bus, tdevice, &work, 0))
 			continue;
-		ret = pci_bus_read_config_dword(ctrl->pci_bus, tdevice, 0x08, &work);
+		ret = pci_bus_read_config_dword(ctrl->pci_bus, tdevice, PCI_CLASS_REVISION, &work);
 		if (ret)
 			continue;
 		dbg("Looking for nonbridge bus_num %d dev_num %d\n", bus_num, tdevice);
@@ -214,7 +214,7 @@ static int PCI_ScanBusForNonBridge(struct controller *ctrl, u8 bus_num, u8 *dev_
 		/* Scan for access first */
 		if (!pci_bus_read_dev_vendor_id(ctrl->pci_bus, tdevice, &work, 0))
 			continue;
-		ret = pci_bus_read_config_dword(ctrl->pci_bus, tdevice, 0x08, &work);
+		ret = pci_bus_read_config_dword(ctrl->pci_bus, tdevice, PCI_CLASS_REVISION, &work);
 		if (ret)
 			continue;
 		dbg("Looking for bridge bus_num %d dev_num %d\n", bus_num, tdevice);

From 5a02413a4586a7cfa10b7380377138e66db9df4b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Tue, 22 Oct 2024 12:11:40 +0300
Subject: [PATCH 0589/1530] PCI: cpqphp: Simplify PCI_ScanBusForNonBridge()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PCI_ScanBusForNonBridge() has two loops, one to search for non-bridges and
a second to look for bridges. The second loop has hints in a debug print it
should do recursion for buses underneath the bridge, but no recursion is
attempted.

Since the second loop is quite useless in its current form, just eliminate
it. This code hasn't been touched for very long time so either it's unused
or the missing parts are not important enough for anyone to attempt to add
them.

Leave only a warning print and comment about the missing recursion for the
unlikely case that somebody comes across the lack of functionality. In any
case, search whether an endpoint exists downstream of a bridge sounds
generic enough to belong to core so if the functionality is to be extended
it should probably be moved into PCI core.

Link: https://lore.kernel.org/r/20241022091140.3504-5-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/cpqphp_pci.c | 34 ++++++++++++++------------------
 1 file changed, 15 insertions(+), 19 deletions(-)

diff --git a/drivers/pci/hotplug/cpqphp_pci.c b/drivers/pci/hotplug/cpqphp_pci.c
index 558866c15e03c..ef7534a3ca40f 100644
--- a/drivers/pci/hotplug/cpqphp_pci.c
+++ b/drivers/pci/hotplug/cpqphp_pci.c
@@ -12,8 +12,11 @@
  *
  */
 
+#define pr_fmt(fmt) "cpqphp: " fmt
+
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/printk.h>
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/workqueue.h>
@@ -190,8 +193,7 @@ static int PCI_ScanBusForNonBridge(struct controller *ctrl, u8 bus_num, u8 *dev_
 {
 	u16 tdevice;
 	u32 work;
-	int ret;
-	u8 tbus;
+	int ret = -1;
 
 	ctrl->pci_bus->number = bus_num;
 
@@ -208,26 +210,20 @@ static int PCI_ScanBusForNonBridge(struct controller *ctrl, u8 bus_num, u8 *dev_
 			*dev_num = tdevice;
 			dbg("found it !\n");
 			return 0;
-		}
-	}
-	for (tdevice = 0; tdevice < 0xFF; tdevice++) {
-		/* Scan for access first */
-		if (!pci_bus_read_dev_vendor_id(ctrl->pci_bus, tdevice, &work, 0))
-			continue;
-		ret = pci_bus_read_config_dword(ctrl->pci_bus, tdevice, PCI_CLASS_REVISION, &work);
-		if (ret)
-			continue;
-		dbg("Looking for bridge bus_num %d dev_num %d\n", bus_num, tdevice);
-		/* Yep we got one. bridge ? */
-		if ((work >> 8) == PCI_TO_PCI_BRIDGE_CLASS) {
-			pci_bus_read_config_byte(ctrl->pci_bus, PCI_DEVFN(tdevice, 0), PCI_SECONDARY_BUS, &tbus);
-			/* XXX: no recursion, wtf? */
-			dbg("Recurse on bus_num %d tdevice %d\n", tbus, tdevice);
-			return 0;
+		} else {
+			/*
+			 * XXX: Code whose debug printout indicated
+			 * recursion to buses underneath bridges might be
+			 * necessary was removed because it never did
+			 * any recursion.
+			 */
+			ret = 0;
+			pr_warn("missing feature: bridge scan recursion not implemented\n");
 		}
 	}
 
-	return -1;
+
+	return ret;
 }
 
 

From bb6e7cb11d97ce1957894d30d13bfad3e8bfefe9 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 15 Oct 2024 23:23:51 -0700
Subject: [PATCH 0590/1530] perf tools: Add fallback for exclude_guest

Commit 7b100989b4f6bce70 ("perf evlist: Remove __evlist__add_default")
changed to parse "cycles:P" event instead of creating a new cycles
event for perf record.  But it also changed the way how modifiers are
handled so it doesn't set the exclude_guest bit by default.

It seems Apple M1 PMU requires exclude_guest set and returns EOPNOTSUPP
if not.  Let's add a fallback so that it can work with default events.

Also update perf stat hybrid tests to handle possible u or H modifiers.

Reviewed-by: Ian Rogers <irogers@google.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Cc: James Clark <james.clark@arm.com>
Cc: Atish Patra <atishp@atishpatra.org>
Cc: Mingwei Zhang <mizhang@google.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20241016062359.264929-2-namhyung@kernel.org
Fixes: 7b100989b4f6bce70 ("perf evlist: Remove __evlist__add_default")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-stat.c      | 18 +++++++++++++++---
 tools/perf/tests/shell/stat.sh |  2 +-
 tools/perf/util/evsel.c        | 21 +++++++++++++++++++++
 3 files changed, 37 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7639ecda6c05f..c12158d99353d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -640,8 +640,7 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
 	 * (behavior changed with commit b0a873e).
 	 */
 	if (errno == EINVAL || errno == ENOSYS ||
-	    errno == ENOENT || errno == EOPNOTSUPP ||
-	    errno == ENXIO) {
+	    errno == ENOENT || errno == ENXIO) {
 		if (verbose > 0)
 			ui__warning("%s event is not supported by the kernel.\n",
 				    evsel__name(counter));
@@ -659,7 +658,7 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
 		if (verbose > 0)
 			ui__warning("%s\n", msg);
 		return COUNTER_RETRY;
-	} else if (target__has_per_thread(&target) &&
+	} else if (target__has_per_thread(&target) && errno != EOPNOTSUPP &&
 		   evsel_list->core.threads &&
 		   evsel_list->core.threads->err_thread != -1) {
 		/*
@@ -680,6 +679,19 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
 		return COUNTER_SKIP;
 	}
 
+	if (errno == EOPNOTSUPP) {
+		if (verbose > 0) {
+			ui__warning("%s event is not supported by the kernel.\n",
+				    evsel__name(counter));
+		}
+		counter->supported = false;
+		counter->errored = true;
+
+		if ((evsel__leader(counter) != counter) ||
+		    !(counter->core.leader->nr_members > 1))
+			return COUNTER_SKIP;
+	}
+
 	evsel__open_strerror(counter, &target, errno, msg, sizeof(msg));
 	ui__error("%s\n", msg);
 
diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh
index f25ef468b8fca..7a8adf81e4b39 100755
--- a/tools/perf/tests/shell/stat.sh
+++ b/tools/perf/tests/shell/stat.sh
@@ -185,7 +185,7 @@ test_hybrid() {
   fi
 
   # Run default Perf stat
-  cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/|  cycles  " | wc -l)
+  cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/[uH]*|  cycles[:uH]*  " -c)
 
   if [ "$pmus" -ne "$cycles_events" ]
   then
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 14663ad14c531..8fb31f0b48b8d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -3156,6 +3156,27 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err,
 		evsel->core.attr.exclude_kernel = 1;
 		evsel->core.attr.exclude_hv     = 1;
 
+		return true;
+	} else if (err == EOPNOTSUPP && !evsel->core.attr.exclude_guest &&
+		   !evsel->exclude_GH) {
+		const char *name = evsel__name(evsel);
+		char *new_name;
+		const char *sep = ":";
+
+		/* Is there already the separator in the name. */
+		if (strchr(name, '/') ||
+		    (strchr(name, ':') && !evsel->is_libpfm_event))
+			sep = "";
+
+		if (asprintf(&new_name, "%s%sH", name, sep) < 0)
+			return false;
+
+		free(evsel->name);
+		evsel->name = new_name;
+		/* Apple M1 requires exclude_guest */
+		scnprintf(msg, msgsize, "trying to fall back to excluding guest samples");
+		evsel->core.attr.exclude_guest = 1;
+
 		return true;
 	}
 

From 35c8d21371e9b342dbd91a8e9b1abaabaec95d41 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 15 Oct 2024 23:23:52 -0700
Subject: [PATCH 0591/1530] perf tools: Don't set attr.exclude_guest by default

The exclude_guest in the event attribute is to limit profiling in the
host environment.  But I'm not sure why we want to set it by default
cause we don't care about it in most cases and I feel like it just
makes new PMU implementation complicated.

Of course it's useful for perf kvm command so I added the
exclude_GH_default variable to preserve the old behavior for perf kvm
and other commands like perf record and stat won't set the exclude bit.
This is helpful for AMD IBS case since having exclude_guest bit will
clear new feature bit due to the missing feature check logic.

  $ sysctl kernel.perf_event_paranoid
  kernel.perf_event_paranoid = 0

  $ perf record -W -e ibs_op// -vv true 2>&1 | grep switching
  switching off PERF_FORMAT_LOST support
  switching off weight struct support
  switching off bpf_event
  switching off ksymbol
  switching off cloexec flag
  switching off mmap2
  switching off exclude_guest, exclude_host

Intestingly, I found it sets the exclude_bit if "u" modifier is used.
I don't know why but it's neither intuitive nor consistent.  Let's
remove the bit there too.

Reviewed-by: Ian Rogers <irogers@google.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Cc: James Clark <james.clark@arm.com>
Cc: Atish Patra <atishp@atishpatra.org>
Cc: Mingwei Zhang <mizhang@google.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20241016062359.264929-3-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-kvm.c                       |  1 +
 tools/perf/tests/parse-events.c                | 18 +++++++++---------
 .../perf/tests/shell/attr/test-record-dummy-C0 |  2 +-
 tools/perf/util/parse-events.c                 |  2 +-
 tools/perf/util/util.c                         | 10 ++++++++--
 tools/perf/util/util.h                         |  3 +++
 6 files changed, 23 insertions(+), 13 deletions(-)

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 55ea17c5ff02a..099ce3ebf67ce 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -2147,6 +2147,7 @@ int cmd_kvm(int argc, const char **argv)
 						"buildid-list", "stat", NULL };
 	const char *kvm_usage[] = { NULL, NULL };
 
+	exclude_GH_default = true;
 	perf_host  = 0;
 	perf_guest = 1;
 
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 78e999f03d2d7..727683f249f66 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -932,7 +932,7 @@ static int test__group2(struct evlist *evlist)
 			TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 			TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 			TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
-			TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
+			TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 			TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 			TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 			TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
@@ -947,7 +947,7 @@ static int test__group2(struct evlist *evlist)
 			TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 			TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 			TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
-			TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
+			TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 			TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 			TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 			if (evsel__has_leader(evsel, leader))
@@ -1072,7 +1072,7 @@ static int test__group3(struct evlist *evlist __maybe_unused)
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
-		TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
+		TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 		TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 		TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 		TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
@@ -1222,7 +1222,7 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
-		TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
+		TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 		TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 		TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 		TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
@@ -1437,7 +1437,7 @@ static int test__leader_sample1(struct evlist *evlist)
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
-		TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
+		TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 		TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 		TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 		TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
@@ -1453,7 +1453,7 @@ static int test__leader_sample1(struct evlist *evlist)
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
-		TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
+		TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 		TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 		TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 		TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
@@ -1468,7 +1468,7 @@ static int test__leader_sample1(struct evlist *evlist)
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
-		TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
+		TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 		TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 		TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 		TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
@@ -1497,7 +1497,7 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused)
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
-		TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
+		TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 		TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 		TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 		TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
@@ -1513,7 +1513,7 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused)
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
-		TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
+		TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 		TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 		TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 		TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
diff --git a/tools/perf/tests/shell/attr/test-record-dummy-C0 b/tools/perf/tests/shell/attr/test-record-dummy-C0
index 3050298bd6140..91499405fff4d 100644
--- a/tools/perf/tests/shell/attr/test-record-dummy-C0
+++ b/tools/perf/tests/shell/attr/test-record-dummy-C0
@@ -37,7 +37,7 @@ precise_ip=0
 mmap_data=0
 sample_id_all=1
 exclude_host=0
-exclude_guest=1
+exclude_guest=0
 exclude_callchain_kernel=0
 exclude_callchain_user=0
 mmap2=1
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4507ae68198bd..687125570f563 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1740,7 +1740,7 @@ static int parse_events__modifier_list(struct parse_events_state *parse_state,
 		if (mod.user) {
 			if (!exclude)
 				exclude = eu = ek = eh = 1;
-			if (!exclude_GH && !perf_guest)
+			if (!exclude_GH && !perf_guest && exclude_GH_default)
 				eG = 1;
 			eu = 0;
 		}
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 9d55a13787ce3..280c86d61d8a7 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -78,17 +78,23 @@ bool sysctl__nmi_watchdog_enabled(void)
 
 bool test_attr__enabled;
 
+bool exclude_GH_default;
+
 bool perf_host  = true;
 bool perf_guest = false;
 
 void event_attr_init(struct perf_event_attr *attr)
 {
+	/* to capture ABI version */
+	attr->size = sizeof(*attr);
+
+	if (!exclude_GH_default)
+		return;
+
 	if (!perf_host)
 		attr->exclude_host  = 1;
 	if (!perf_guest)
 		attr->exclude_guest = 1;
-	/* to capture ABI version */
-	attr->size = sizeof(*attr);
 }
 
 int mkdir_p(char *path, mode_t mode)
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 14f2c70906be8..2359362885eaf 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -21,6 +21,9 @@ extern const char perf_more_info_string[];
 
 extern const char *input_name;
 
+/* This will control if perf_{host,guest} will set attr.exclude_{host,guest}. */
+extern bool exclude_GH_default;
+
 extern bool perf_host;
 extern bool perf_guest;
 

From d9e0970f77b92b0e2afff5e4a9e379bc9885df56 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 15 Oct 2024 23:23:53 -0700
Subject: [PATCH 0592/1530] perf tools: Simplify evsel__add_modifier()

Since it doesn't set the exclude_guest, no need to special handle the
bit and simply show only if one of host or guest bit is set.  Now the
default event name might not have :H prefix anymore so change the
dlfilter test not to compare the ":" at the end.

Reviewed-by: Ian Rogers <irogers@google.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Cc: James Clark <james.clark@arm.com>
Cc: Atish Patra <atishp@atishpatra.org>
Cc: Mingwei Zhang <mizhang@google.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20241016062359.264929-4-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/dlfilters/dlfilter-test-api-v0.c | 2 +-
 tools/perf/dlfilters/dlfilter-test-api-v2.c | 2 +-
 tools/perf/util/evsel.c                     | 5 +----
 3 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/tools/perf/dlfilters/dlfilter-test-api-v0.c b/tools/perf/dlfilters/dlfilter-test-api-v0.c
index 4083b1abeaabe..4ca2d7b2ea6c8 100644
--- a/tools/perf/dlfilters/dlfilter-test-api-v0.c
+++ b/tools/perf/dlfilters/dlfilter-test-api-v0.c
@@ -220,7 +220,7 @@ static int check_sample(struct filter_data *d, const struct perf_dlfilter_sample
 	CHECK_SAMPLE(raw_callchain_nr);
 	CHECK(!sample->raw_callchain);
 
-#define EVENT_NAME "branches:"
+#define EVENT_NAME "branches"
 	CHECK(!strncmp(sample->event, EVENT_NAME, strlen(EVENT_NAME)));
 
 	return 0;
diff --git a/tools/perf/dlfilters/dlfilter-test-api-v2.c b/tools/perf/dlfilters/dlfilter-test-api-v2.c
index 32ff619e881ca..00d73a16c4fda 100644
--- a/tools/perf/dlfilters/dlfilter-test-api-v2.c
+++ b/tools/perf/dlfilters/dlfilter-test-api-v2.c
@@ -235,7 +235,7 @@ static int check_sample(struct filter_data *d, const struct perf_dlfilter_sample
 	CHECK_SAMPLE(raw_callchain_nr);
 	CHECK(!sample->raw_callchain);
 
-#define EVENT_NAME "branches:"
+#define EVENT_NAME "branches"
 	CHECK(!strncmp(sample->event, EVENT_NAME, strlen(EVENT_NAME)));
 
 	return 0;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 8fb31f0b48b8d..7f98f9d3394a7 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -638,7 +638,6 @@ static int evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)
 {
 	int colon = 0, r = 0;
 	struct perf_event_attr *attr = &evsel->core.attr;
-	bool exclude_guest_default = false;
 
 #define MOD_PRINT(context, mod)	do {					\
 		if (!attr->exclude_##context) {				\
@@ -650,17 +649,15 @@ static int evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)
 		MOD_PRINT(kernel, 'k');
 		MOD_PRINT(user, 'u');
 		MOD_PRINT(hv, 'h');
-		exclude_guest_default = true;
 	}
 
 	if (attr->precise_ip) {
 		if (!colon)
 			colon = ++r;
 		r += scnprintf(bf + r, size - r, "%.*s", attr->precise_ip, "ppp");
-		exclude_guest_default = true;
 	}
 
-	if (attr->exclude_host || attr->exclude_guest == exclude_guest_default) {
+	if (attr->exclude_host || attr->exclude_guest) {
 		MOD_PRINT(host, 'H');
 		MOD_PRINT(guest, 'G');
 	}

From 88bc63d00eb6defb661b9fd79957660b4dfa4b50 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 15 Oct 2024 23:23:54 -0700
Subject: [PATCH 0593/1530] perf tools: Do not set exclude_guest for precise_ip

It seems perf sets the exclude_guest bit because of Intel PEBS
implementation which uses a virtual address.  IIUC now kernel disables
PEBS when it goes to the guest mode regardless of this bit so we don't
need to set it explicitly.  At least for the other archs/vendors.

I found the commit 1342798cc13e set the exclude_guest for precise_ip
in the tool and the commit 20b279ddb38c added kernel side enforcement
which was reverted by commit a706d965dcfd later.

Actually it doesn't set the exclude_guest for the default event
(cycles:P) already.

  $ grep -m1 vendor /proc/cpuinfo
  vendor_id	: GenuineIntel

  $ perf record -e cycles:P true
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.002 MB perf.data (9 samples) ]

  $ perf evlist -v | tr ',' '\n' | grep -e exclude -e precise
   precise_ip: 3

But having lower 'p' modifier set the bit for some reason.

  $ perf record -e cycles:pp true
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.002 MB perf.data (9 samples) ]

  $ perf evlist -v | tr ',' '\n' | grep -e exclude -e precise
   precise_ip: 2
   exclude_guest: 1

Actually AMD IBS suffers from this because it doesn't support excludes
and having this bit effectively disables new features in the current
implementation (due to the missing feature check).

  $ grep -m1 vendor /proc/cpuinfo
  vendor_id	: AuthenticAMD

  $ perf record -W -e cycles:p -vv true 2>&1 | grep switching
  switching off PERF_FORMAT_LOST support
  switching off weight struct support
  switching off bpf_event
  switching off ksymbol
  switching off cloexec flag
  switching off mmap2
  switching off exclude_guest, exclude_host

By not setting exclude_guest, we can fix this inconsistency and the
troubles.

Reviewed-by: Ian Rogers <irogers@google.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Cc: James Clark <james.clark@arm.com>
Cc: Atish Patra <atishp@atishpatra.org>
Cc: Mingwei Zhang <mizhang@google.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20241016062359.264929-5-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/parse-events.c | 12 ++++--------
 tools/perf/util/parse-events.c  |  4 ----
 2 files changed, 4 insertions(+), 12 deletions(-)

diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 727683f249f66..82a19674a38f7 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -898,8 +898,7 @@ static int test__group1(struct evlist *evlist)
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
-		/* use of precise requires exclude_guest */
-		TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
+		TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 		TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 		TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip == 2);
 		TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
@@ -1016,9 +1015,8 @@ static int test__group3(struct evlist *evlist __maybe_unused)
 				TEST_ASSERT_VAL("wrong exclude_kernel",
 						!evsel->core.attr.exclude_kernel);
 				TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
-				/* use of precise requires exclude_guest */
 				TEST_ASSERT_VAL("wrong exclude guest",
-						evsel->core.attr.exclude_guest);
+						!evsel->core.attr.exclude_guest);
 				TEST_ASSERT_VAL("wrong exclude host",
 						!evsel->core.attr.exclude_host);
 				TEST_ASSERT_VAL("wrong precise_ip",
@@ -1103,8 +1101,7 @@ static int test__group4(struct evlist *evlist __maybe_unused)
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
-		/* use of precise requires exclude_guest */
-		TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
+		TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 		TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 		TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip == 1);
 		TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
@@ -1122,8 +1119,7 @@ static int test__group4(struct evlist *evlist __maybe_unused)
 		TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
-		/* use of precise requires exclude_guest */
-		TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
+		TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 		TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 		TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip == 2);
 		TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 687125570f563..afeb8d815bbff 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1733,10 +1733,6 @@ static int parse_events__modifier_list(struct parse_events_state *parse_state,
 		int exclude = eu | ek | eh;
 		int exclude_GH = group ? evsel->exclude_GH : 0;
 
-		if (mod.precise) {
-			/* use of precise requires exclude_guest */
-			eG = 1;
-		}
 		if (mod.user) {
 			if (!exclude)
 				exclude = eu = ek = eh = 1;

From 3b193a57baf15c468e4f86cebc694ca4fe18301b Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 15 Oct 2024 23:23:55 -0700
Subject: [PATCH 0594/1530] perf tools: Detect missing kernel features properly

The evsel__detect_missing_features() is to check if the attributes of
the evsel is supported or not.  But it checks the attribute based on the
given evsel, it might miss something if the attr doesn't have the bit or
give incorrect results if the event is special.

Also it maintains the order of the feature that was added to the kernel
which means it can assume older features should be supported once it
detects the current feature is working.  To minimized the confusion and
to accurately check the kernel features, I think it's better to use a
software event and go through all the features at once.

Also make the function static since it's only used in evsel.c.

Reviewed-by: James Clark <james.clark@linaro.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Cc: James Clark <james.clark@arm.com>
Cc: Atish Patra <atishp@atishpatra.org>
Cc: Mingwei Zhang <mizhang@google.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20241016062359.264929-6-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/evsel.c | 403 ++++++++++++++++++++++++++++++----------
 tools/perf/util/evsel.h |   1 -
 tools/perf/util/pmu.h   |   4 +
 3 files changed, 307 insertions(+), 101 deletions(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7f98f9d3394a7..9d976acf08dd9 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -24,6 +24,7 @@
 #include <linux/zalloc.h>
 #include <sys/ioctl.h>
 #include <sys/resource.h>
+#include <sys/syscall.h>
 #include <sys/types.h>
 #include <dirent.h>
 #include <stdlib.h>
@@ -2085,125 +2086,327 @@ int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 	return err;
 }
 
-bool evsel__detect_missing_features(struct evsel *evsel)
+static bool has_attr_feature(struct perf_event_attr *attr, unsigned long flags)
 {
+	int fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, /*cpu=*/-1,
+			 /*group_fd=*/-1, flags);
+	close(fd);
+
+	if (fd < 0) {
+		attr->exclude_kernel = 1;
+
+		fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, /*cpu=*/-1,
+			     /*group_fd=*/-1, flags);
+		close(fd);
+	}
+
+	if (fd < 0) {
+		attr->exclude_hv = 1;
+
+		fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, /*cpu=*/-1,
+			     /*group_fd=*/-1, flags);
+		close(fd);
+	}
+
+	if (fd < 0) {
+		attr->exclude_guest = 1;
+
+		fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, /*cpu=*/-1,
+			     /*group_fd=*/-1, flags);
+		close(fd);
+	}
+
+	attr->exclude_kernel = 0;
+	attr->exclude_guest = 0;
+	attr->exclude_hv = 0;
+
+	return fd >= 0;
+}
+
+static void evsel__detect_missing_pmu_features(struct evsel *evsel)
+{
+	struct perf_event_attr attr = {
+		.type = evsel->core.attr.type,
+		.config = evsel->core.attr.config,
+		.disabled = 1,
+	};
+	struct perf_pmu *pmu = evsel->pmu;
+	int old_errno;
+
+	old_errno = errno;
+
+	if (pmu == NULL)
+		pmu = evsel->pmu = evsel__find_pmu(evsel);
+
+	if (pmu == NULL || pmu->missing_features.checked)
+		goto out;
+
 	/*
 	 * Must probe features in the order they were added to the
-	 * perf_event_attr interface.
+	 * perf_event_attr interface.  These are PMU specific limitation
+	 * so we can detect with the given hardware event and stop on the
+	 * first one succeeded.
 	 */
-	if (!perf_missing_features.inherit_sample_read &&
-	    evsel->core.attr.inherit && (evsel->core.attr.sample_type & PERF_SAMPLE_READ)) {
-		perf_missing_features.inherit_sample_read = true;
-		pr_debug2("Using PERF_SAMPLE_READ / :S modifier is not compatible with inherit, falling back to no-inherit.\n");
-		return true;
-	} else if (!perf_missing_features.branch_counters &&
-	    (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS)) {
-		perf_missing_features.branch_counters = true;
-		pr_debug2("switching off branch counters support\n");
+
+	/* Please add new feature detection here. */
+
+	attr.exclude_guest = 1;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	pmu->missing_features.exclude_guest = true;
+	pr_debug2("switching off exclude_guest for PMU %s\n", pmu->name);
+
+found:
+	pmu->missing_features.checked = true;
+out:
+	errno = old_errno;
+}
+
+static void evsel__detect_missing_brstack_features(struct evsel *evsel)
+{
+	static bool detection_done = false;
+	struct perf_event_attr attr = {
+		.type = evsel->core.attr.type,
+		.config = evsel->core.attr.config,
+		.disabled = 1,
+		.sample_type = PERF_SAMPLE_BRANCH_STACK,
+		.sample_period = 1000,
+	};
+	int old_errno;
+
+	if (detection_done)
+		return;
+
+	old_errno = errno;
+
+	/*
+	 * Must probe features in the order they were added to the
+	 * perf_event_attr interface.  These are PMU specific limitation
+	 * so we can detect with the given hardware event and stop on the
+	 * first one succeeded.
+	 */
+
+	/* Please add new feature detection here. */
+
+	attr.branch_sample_type = PERF_SAMPLE_BRANCH_COUNTERS;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.branch_counters = true;
+	pr_debug2("switching off branch counters support\n");
+
+	attr.branch_sample_type = PERF_SAMPLE_BRANCH_HW_INDEX;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.branch_hw_idx = true;
+	pr_debug2("switching off branch HW index support\n");
+
+	attr.branch_sample_type = PERF_SAMPLE_BRANCH_NO_CYCLES | PERF_SAMPLE_BRANCH_NO_FLAGS;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.lbr_flags = true;
+	pr_debug2_peo("switching off branch sample type no (cycles/flags)\n");
+
+found:
+	detection_done = true;
+	errno = old_errno;
+}
+
+static bool evsel__detect_missing_features(struct evsel *evsel)
+{
+	static bool detection_done = false;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_TASK_CLOCK,
+		.disabled = 1,
+	};
+	int old_errno;
+
+	evsel__detect_missing_pmu_features(evsel);
+
+	if (evsel__has_br_stack(evsel))
+		evsel__detect_missing_brstack_features(evsel);
+
+	if (detection_done)
+		goto check;
+
+	old_errno = errno;
+
+	/*
+	 * Must probe features in the order they were added to the
+	 * perf_event_attr interface.  These are kernel core limitation
+	 * not PMU-specific so we can detect with a software event and
+	 * stop on the first one succeeded.
+	 */
+
+	/* Please add new feature detection here. */
+
+	attr.inherit = true;
+	attr.sample_type = PERF_SAMPLE_READ;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.inherit_sample_read = true;
+	pr_debug2("Using PERF_SAMPLE_READ / :S modifier is not compatible with inherit, falling back to no-inherit.\n");
+	attr.inherit = false;
+	attr.sample_type = 0;
+
+	attr.read_format = PERF_FORMAT_LOST;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.read_lost = true;
+	pr_debug2("switching off PERF_FORMAT_LOST support\n");
+	attr.read_format = 0;
+
+	attr.sample_type = PERF_SAMPLE_WEIGHT_STRUCT;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.weight_struct = true;
+	pr_debug2("switching off weight struct support\n");
+	attr.sample_type = 0;
+
+	attr.sample_type = PERF_SAMPLE_CODE_PAGE_SIZE;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.code_page_size = true;
+	pr_debug2_peo("Kernel has no PERF_SAMPLE_CODE_PAGE_SIZE support\n");
+	attr.sample_type = 0;
+
+	attr.sample_type = PERF_SAMPLE_DATA_PAGE_SIZE;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.data_page_size = true;
+	pr_debug2_peo("Kernel has no PERF_SAMPLE_DATA_PAGE_SIZE support\n");
+	attr.sample_type = 0;
+
+	attr.cgroup = 1;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.cgroup = true;
+	pr_debug2_peo("Kernel has no cgroup sampling support\n");
+	attr.cgroup = 0;
+
+	attr.aux_output = 1;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.aux_output = true;
+	pr_debug2_peo("Kernel has no attr.aux_output support\n");
+	attr.aux_output = 0;
+
+	attr.bpf_event = 1;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.bpf = true;
+	pr_debug2_peo("switching off bpf_event\n");
+	attr.bpf_event = 0;
+
+	attr.ksymbol = 1;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.ksymbol = true;
+	pr_debug2_peo("switching off ksymbol\n");
+	attr.ksymbol = 0;
+
+	attr.write_backward = 1;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.write_backward = true;
+	pr_debug2_peo("switching off write_backward\n");
+	attr.write_backward = 0;
+
+	attr.use_clockid = 1;
+	attr.clockid = CLOCK_MONOTONIC;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.clockid = true;
+	pr_debug2_peo("switching off clockid\n");
+	attr.use_clockid = 0;
+	attr.clockid = 0;
+
+	if (has_attr_feature(&attr, /*flags=*/PERF_FLAG_FD_CLOEXEC))
+		goto found;
+	perf_missing_features.cloexec = true;
+	pr_debug2_peo("switching off cloexec flag\n");
+
+	attr.mmap2 = 1;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.mmap2 = true;
+	pr_debug2_peo("switching off mmap2\n");
+	attr.mmap2 = 0;
+
+	/* set this unconditionally? */
+	perf_missing_features.sample_id_all = true;
+	pr_debug2_peo("switching off sample_id_all\n");
+
+	attr.inherit = 1;
+	attr.read_format = PERF_FORMAT_GROUP;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.group_read = true;
+	pr_debug2_peo("switching off group read\n");
+	attr.inherit = 0;
+	attr.read_format = 0;
+
+found:
+	detection_done = true;
+	errno = old_errno;
+
+check:
+	if (evsel->core.attr.inherit &&
+	    (evsel->core.attr.sample_type & PERF_SAMPLE_READ) &&
+	    perf_missing_features.inherit_sample_read)
 		return true;
-	} else if (!perf_missing_features.read_lost &&
-	    (evsel->core.attr.read_format & PERF_FORMAT_LOST)) {
-		perf_missing_features.read_lost = true;
-		pr_debug2("switching off PERF_FORMAT_LOST support\n");
+
+	if ((evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS) &&
+	    perf_missing_features.branch_counters)
 		return true;
-	} else if (!perf_missing_features.weight_struct &&
-	    (evsel->core.attr.sample_type & PERF_SAMPLE_WEIGHT_STRUCT)) {
-		perf_missing_features.weight_struct = true;
-		pr_debug2("switching off weight struct support\n");
+
+	if ((evsel->core.attr.read_format & PERF_FORMAT_LOST) &&
+	    perf_missing_features.read_lost)
 		return true;
-	} else if (!perf_missing_features.code_page_size &&
-	    (evsel->core.attr.sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)) {
-		perf_missing_features.code_page_size = true;
-		pr_debug2_peo("Kernel has no PERF_SAMPLE_CODE_PAGE_SIZE support, bailing out\n");
-		return false;
-	} else if (!perf_missing_features.data_page_size &&
-	    (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)) {
-		perf_missing_features.data_page_size = true;
-		pr_debug2_peo("Kernel has no PERF_SAMPLE_DATA_PAGE_SIZE support, bailing out\n");
-		return false;
-	} else if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) {
-		perf_missing_features.cgroup = true;
-		pr_debug2_peo("Kernel has no cgroup sampling support, bailing out\n");
-		return false;
-	} else if (!perf_missing_features.branch_hw_idx &&
-	    (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX)) {
-		perf_missing_features.branch_hw_idx = true;
-		pr_debug2("switching off branch HW index support\n");
+
+	if ((evsel->core.attr.sample_type & PERF_SAMPLE_WEIGHT_STRUCT) &&
+	    perf_missing_features.weight_struct)
 		return true;
-	} else if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
-		perf_missing_features.aux_output = true;
-		pr_debug2_peo("Kernel has no attr.aux_output support, bailing out\n");
-		return false;
-	} else if (!perf_missing_features.bpf && evsel->core.attr.bpf_event) {
-		perf_missing_features.bpf = true;
-		pr_debug2_peo("switching off bpf_event\n");
+
+	if (evsel->core.attr.use_clockid && evsel->core.attr.clockid != CLOCK_MONOTONIC &&
+	    !perf_missing_features.clockid) {
+		perf_missing_features.clockid_wrong = true;
 		return true;
-	} else if (!perf_missing_features.ksymbol && evsel->core.attr.ksymbol) {
-		perf_missing_features.ksymbol = true;
-		pr_debug2_peo("switching off ksymbol\n");
+	}
+
+	if (evsel->core.attr.use_clockid && perf_missing_features.clockid)
 		return true;
-	} else if (!perf_missing_features.write_backward && evsel->core.attr.write_backward) {
-		perf_missing_features.write_backward = true;
-		pr_debug2_peo("switching off write_backward\n");
-		return false;
-	} else if (!perf_missing_features.clockid_wrong && evsel->core.attr.use_clockid) {
-		perf_missing_features.clockid_wrong = true;
-		pr_debug2_peo("switching off clockid\n");
+
+	if ((evsel->open_flags & PERF_FLAG_FD_CLOEXEC) &&
+	    perf_missing_features.cloexec)
 		return true;
-	} else if (!perf_missing_features.clockid && evsel->core.attr.use_clockid) {
-		perf_missing_features.clockid = true;
-		pr_debug2_peo("switching off use_clockid\n");
+
+	if (evsel->core.attr.mmap2 && perf_missing_features.mmap2)
 		return true;
-	} else if (!perf_missing_features.cloexec && (evsel->open_flags & PERF_FLAG_FD_CLOEXEC)) {
-		perf_missing_features.cloexec = true;
-		pr_debug2_peo("switching off cloexec flag\n");
+
+	if ((evsel->core.attr.branch_sample_type & (PERF_SAMPLE_BRANCH_NO_FLAGS |
+						    PERF_SAMPLE_BRANCH_NO_CYCLES)) &&
+	    perf_missing_features.lbr_flags)
 		return true;
-	} else if (!perf_missing_features.mmap2 && evsel->core.attr.mmap2) {
-		perf_missing_features.mmap2 = true;
-		pr_debug2_peo("switching off mmap2\n");
+
+	if (evsel->core.attr.inherit && (evsel->core.attr.read_format & PERF_FORMAT_GROUP) &&
+	    perf_missing_features.group_read)
 		return true;
-	} else if (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host) {
-		if (evsel->pmu == NULL)
-			evsel->pmu = evsel__find_pmu(evsel);
-
-		if (evsel->pmu)
-			evsel->pmu->missing_features.exclude_guest = true;
-		else {
-			/* we cannot find PMU, disable attrs now */
-			evsel->core.attr.exclude_host = false;
-			evsel->core.attr.exclude_guest = false;
-		}
 
-		if (evsel->exclude_GH) {
-			pr_debug2_peo("PMU has no exclude_host/guest support, bailing out\n");
-			return false;
-		}
-		if (!perf_missing_features.exclude_guest) {
-			perf_missing_features.exclude_guest = true;
-			pr_debug2_peo("switching off exclude_guest, exclude_host\n");
-		}
+	if (evsel->core.attr.ksymbol && perf_missing_features.ksymbol)
 		return true;
-	} else if (!perf_missing_features.sample_id_all) {
-		perf_missing_features.sample_id_all = true;
-		pr_debug2_peo("switching off sample_id_all\n");
+
+	if (evsel->core.attr.bpf_event && perf_missing_features.bpf)
 		return true;
-	} else if (!perf_missing_features.lbr_flags &&
-			(evsel->core.attr.branch_sample_type &
-			 (PERF_SAMPLE_BRANCH_NO_CYCLES |
-			  PERF_SAMPLE_BRANCH_NO_FLAGS))) {
-		perf_missing_features.lbr_flags = true;
-		pr_debug2_peo("switching off branch sample type no (cycles/flags)\n");
+
+	if ((evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX) &&
+	    perf_missing_features.branch_hw_idx)
 		return true;
-	} else if (!perf_missing_features.group_read &&
-		    evsel->core.attr.inherit &&
-		   (evsel->core.attr.read_format & PERF_FORMAT_GROUP) &&
-		   evsel__is_group_leader(evsel)) {
-		perf_missing_features.group_read = true;
-		pr_debug2_peo("switching off group read\n");
+
+	if (evsel->core.attr.sample_id_all && perf_missing_features.sample_id_all)
 		return true;
-	} else {
-		return false;
-	}
+
+	return false;
 }
 
 static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 9fcaf417b2778..04934a7af1745 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -343,7 +343,6 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
 void evsel__close(struct evsel *evsel);
 int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 		struct perf_thread_map *threads);
-bool evsel__detect_missing_features(struct evsel *evsel);
 
 bool evsel__precise_ip_fallback(struct evsel *evsel);
 
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index e400db9e9eb15..b86b3c3685a23 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -170,6 +170,10 @@ struct perf_pmu {
 		 * exclude_host.
 		 */
 		bool exclude_guest;
+		/**
+		 * @checked: Are the missing features checked?
+		 */
+		bool checked;
 	} missing_features;
 
 	/**

From 28398ce1726e5dfa74f6305dd842e0fb7e332ef1 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 15 Oct 2024 23:23:56 -0700
Subject: [PATCH 0595/1530] perf tools: Move x86__is_amd_cpu() to util/env.c

It can be called from non-x86 platform so let's move it to the general
util directory.  Also add a new helper perf_env__is_x86_amd_cpu() so
that it can be called with an existing perf_env as well.

Reviewed-by: James Clark <james.clark@linaro.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Cc: James Clark <james.clark@arm.com>
Cc: Atish Patra <atishp@atishpatra.org>
Cc: Mingwei Zhang <mizhang@google.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20241016062359.264929-7-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/x86/util/Build |  1 -
 tools/perf/arch/x86/util/env.c | 19 -------------------
 tools/perf/arch/x86/util/env.h |  7 -------
 tools/perf/arch/x86/util/pmu.c |  2 +-
 tools/perf/util/env.c          | 23 +++++++++++++++++++++++
 tools/perf/util/env.h          |  4 ++++
 6 files changed, 28 insertions(+), 28 deletions(-)
 delete mode 100644 tools/perf/arch/x86/util/env.c
 delete mode 100644 tools/perf/arch/x86/util/env.h

diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 9705cda4f2400..bc56a8e70f347 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -10,7 +10,6 @@ perf-util-y += evlist.o
 perf-util-y += mem-events.o
 perf-util-y += evsel.o
 perf-util-y += iostat.o
-perf-util-y += env.o
 
 perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
 perf-util-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
diff --git a/tools/perf/arch/x86/util/env.c b/tools/perf/arch/x86/util/env.c
deleted file mode 100644
index 3e537ffb1353a..0000000000000
--- a/tools/perf/arch/x86/util/env.c
+++ /dev/null
@@ -1,19 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include "linux/string.h"
-#include "util/env.h"
-#include "env.h"
-
-bool x86__is_amd_cpu(void)
-{
-	struct perf_env env = { .total_mem = 0, };
-	static int is_amd; /* 0: Uninitialized, 1: Yes, -1: No */
-
-	if (is_amd)
-		goto ret;
-
-	perf_env__cpuid(&env);
-	is_amd = env.cpuid && strstarts(env.cpuid, "AuthenticAMD") ? 1 : -1;
-	perf_env__exit(&env);
-ret:
-	return is_amd >= 1 ? true : false;
-}
diff --git a/tools/perf/arch/x86/util/env.h b/tools/perf/arch/x86/util/env.h
deleted file mode 100644
index d78f080b6b3f8..0000000000000
--- a/tools/perf/arch/x86/util/env.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _X86_ENV_H
-#define _X86_ENV_H
-
-bool x86__is_amd_cpu(void);
-
-#endif /* _X86_ENV_H */
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index c3d89d6ba1bf0..e0060dac2a9f9 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -16,7 +16,7 @@
 #include "../../../util/fncache.h"
 #include "../../../util/pmus.h"
 #include "mem-events.h"
-#include "env.h"
+#include "util/env.h"
 
 void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused)
 {
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 1edbccfc3281d..ccb4640266428 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -5,6 +5,7 @@
 #include "util/header.h"
 #include "linux/compiler.h"
 #include <linux/ctype.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 #include "cgroup.h"
 #include <errno.h>
@@ -639,3 +640,25 @@ void perf_env__find_br_cntr_info(struct perf_env *env,
 					     env->pmu_caps->br_cntr_width;
 	}
 }
+
+bool perf_env__is_x86_amd_cpu(struct perf_env *env)
+{
+	static int is_amd; /* 0: Uninitialized, 1: Yes, -1: No */
+
+	if (is_amd == 0)
+		is_amd = env->cpuid && strstarts(env->cpuid, "AuthenticAMD") ? 1 : -1;
+
+	return is_amd >= 1 ? true : false;
+}
+
+bool x86__is_amd_cpu(void)
+{
+	struct perf_env env = { .total_mem = 0, };
+	bool is_amd;
+
+	perf_env__cpuid(&env);
+	is_amd = perf_env__is_x86_amd_cpu(&env);
+	perf_env__exit(&env);
+
+	return is_amd;
+}
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 51b36c36019be..ae604c4edbb7e 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -195,4 +195,8 @@ bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name);
 void perf_env__find_br_cntr_info(struct perf_env *env,
 				 unsigned int *nr,
 				 unsigned int *width);
+
+bool x86__is_amd_cpu(void);
+bool perf_env__is_x86_amd_cpu(struct perf_env *env);
+
 #endif /* __PERF_ENV_H */

From af954f76eea56453713ae657f6812d4063f9bc57 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 15 Oct 2024 23:23:57 -0700
Subject: [PATCH 0596/1530] perf tools: Check fallback error and order

The perf_event_open might fail due to various reasons, so blindly
reducing precise_ip level might not be the best way to deal with it.

It seems the kernel return -EOPNOTSUPP when PMU doesn't support the
given precise level.  Let's try again with the correct error code.

This caused a problem on AMD, as it stops on precise_ip of 2 for IBS but
user events with exclude_kernel=1 cannot make progress.  Let's add the
evsel__handle_error_quirks() to this case specially.  I plan to work on
the kernel side to improve this situation but it'd still need some
special handling for IBS.

Reviewed-by: James Clark <james.clark@linaro.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Cc: James Clark <james.clark@arm.com>
Cc: Atish Patra <atishp@atishpatra.org>
Cc: Mingwei Zhang <mizhang@google.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20241016062359.264929-8-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/evsel.c | 38 +++++++++++++++++++++++++++++---------
 1 file changed, 29 insertions(+), 9 deletions(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 9d976acf08dd9..f780e30aa259f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2143,9 +2143,9 @@ static void evsel__detect_missing_pmu_features(struct evsel *evsel)
 
 	/*
 	 * Must probe features in the order they were added to the
-	 * perf_event_attr interface.  These are PMU specific limitation
-	 * so we can detect with the given hardware event and stop on the
-	 * first one succeeded.
+	 * perf_event_attr interface.  These are kernel core limitation but
+	 * specific to PMUs with branch stack.  So we can detect with the given
+	 * hardware event and stop on the first one succeeded.
 	 */
 
 	/* Please add new feature detection here. */
@@ -2409,6 +2409,25 @@ static bool evsel__detect_missing_features(struct evsel *evsel)
 	return false;
 }
 
+static bool evsel__handle_error_quirks(struct evsel *evsel, int error)
+{
+	/*
+	 * AMD core PMU tries to forward events with precise_ip to IBS PMU
+	 * implicitly.  But IBS PMU has more restrictions so it can fail with
+	 * supported event attributes.  Let's forward it back to the core PMU
+	 * by clearing precise_ip only if it's from precise_max (:P).
+	 */
+	if ((error == -EINVAL || error == -ENOENT) && x86__is_amd_cpu() &&
+	    evsel->core.attr.precise_ip && evsel->precise_max) {
+		evsel->core.attr.precise_ip = 0;
+		pr_debug2_peo("removing precise_ip on AMD\n");
+		display_attr(&evsel->core.attr);
+		return true;
+	}
+
+	return false;
+}
+
 static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 		struct perf_thread_map *threads,
 		int start_cpu_map_idx, int end_cpu_map_idx)
@@ -2527,9 +2546,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 	return 0;
 
 try_fallback:
-	if (evsel__precise_ip_fallback(evsel))
-		goto retry_open;
-
 	if (evsel__ignore_missing_thread(evsel, perf_cpu_map__nr(cpus),
 					 idx, threads, thread, err)) {
 		/* We just removed 1 thread, so lower the upper nthreads limit. */
@@ -2546,11 +2562,15 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 	if (err == -EMFILE && rlimit__increase_nofile(&set_rlimit))
 		goto retry_open;
 
-	if (err != -EINVAL || idx > 0 || thread > 0)
-		goto out_close;
+	if (err == -EOPNOTSUPP && evsel__precise_ip_fallback(evsel))
+		goto retry_open;
 
-	if (evsel__detect_missing_features(evsel))
+	if (err == -EINVAL && evsel__detect_missing_features(evsel))
 		goto fallback_missing_features;
+
+	if (evsel__handle_error_quirks(evsel, err))
+		goto retry_open;
+
 out_close:
 	if (err)
 		threads->err_thread = thread;

From 634d36f82517eb5c6a9b9ec7fe3ba19dbbcb7809 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 15 Oct 2024 23:23:58 -0700
Subject: [PATCH 0597/1530] perf record: Just use "cycles:P" as the default
 event

The fallback logic can add ":u" modifier if needed.

Reviewed-by: Ian Rogers <irogers@google.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Cc: James Clark <james.clark@arm.com>
Cc: Atish Patra <atishp@atishpatra.org>
Cc: Mingwei Zhang <mizhang@google.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20241016062359.264929-9-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-record.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index adbaf80b398c1..f832524729211 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -4157,9 +4157,7 @@ int cmd_record(int argc, const char **argv)
 		record.opts.tail_synthesize = true;
 
 	if (rec->evlist->core.nr_entries == 0) {
-		bool can_profile_kernel = perf_event_paranoid_check(1);
-
-		err = parse_event(rec->evlist, can_profile_kernel ? "cycles:P" : "cycles:Pu");
+		err = parse_event(rec->evlist, "cycles:P");
 		if (err)
 			goto out;
 	}

From 36fae9f93e5f00eb3e410784ce99a4d7503aa12e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 15 Oct 2024 23:23:59 -0700
Subject: [PATCH 0598/1530] perf test: Add precise_max subtest to the perf
 record shell test

It's a very simply test just to run with cycles:P and instructions:P
events.

Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: James Clark <james.clark@arm.com>
Cc: Atish Patra <atishp@atishpatra.org>
Cc: Mingwei Zhang <mizhang@google.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20241016062359.264929-10-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/record.sh | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index 3eee72242290d..f0e79200b9813 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -271,6 +271,30 @@ test_topdown_leader_sampling() {
   echo "Topdown leader sampling test [Success]"
 }
 
+test_precise_max() {
+  echo "precise_max attribute test"
+  if ! perf stat -e "cycles,instructions" true 2> /dev/null
+  then
+    echo "precise_max attribute [Skipped no hardware events]"
+    return
+  fi
+  # Just to make sure it doesn't fail
+  if ! perf record -o "${perfdata}" -e "cycles:P" true 2> /dev/null
+  then
+    echo "precise_max attribute [Failed cycles:P event]"
+    err=1
+    return
+  fi
+  # On AMD, cycles and instructions events are treated differently
+  if ! perf record -o "${perfdata}" -e "instructions:P" true 2> /dev/null
+  then
+    echo "precise_max attribute [Failed instructions:P event]"
+    err=1
+    return
+  fi
+  echo "precise_max attribute test [Success]"
+}
+
 # raise the limit of file descriptors to minimum
 if [[ $default_fd_limit -lt $min_fd_limit ]]; then
        ulimit -Sn $min_fd_limit
@@ -284,6 +308,7 @@ test_branch_counter
 test_cgroup
 test_leader_sampling
 test_topdown_leader_sampling
+test_precise_max
 
 # restore the default value
 ulimit -Sn $default_fd_limit

From 28e848386b92645f93b9f2fdba5882c3ca7fb3e2 Mon Sep 17 00:00:00 2001
From: Francesco Zardi <frazar00@gmail.com>
Date: Tue, 3 Sep 2024 19:30:29 +0200
Subject: [PATCH 0599/1530] rust: block: fix formatting of
 `kernel::block::mq::request` module

Fix several issues with rustdoc formatting for the
`kernel::block::mq::Request` module, in particular:

  - An ordered list not rendering correctly, fixed by using numbers
    prefixes instead of letters.

  - Code snippets formatted as regular text, fixed by wrapping the
    code with `back-ticks`.

  - References to types missing intra-doc links, fixed by wrapping the
    types with [square brackets].

Reported-by: Miguel Ojeda <ojeda@kernel.org>
Closes: https://github.com/Rust-for-Linux/linux/issues/1108
Signed-off-by: Francesco Zardi <frazar00@gmail.com>
Acked-by: Andreas Hindborg <a.hindborg@kernel.org>
Fixes: 3253aba3408a ("rust: block: introduce `kernel::block::mq` module")
Link: https://lore.kernel.org/r/20240903173027.16732-3-frazar00@gmail.com
[ Added an extra intra-doc link. Took the chance to add some periods
  for consistency. Reworded slightly. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/block/mq/request.rs | 67 +++++++++++++++++++--------------
 1 file changed, 38 insertions(+), 29 deletions(-)

diff --git a/rust/kernel/block/mq/request.rs b/rust/kernel/block/mq/request.rs
index a0e22827f3f4e..7943f43b95753 100644
--- a/rust/kernel/block/mq/request.rs
+++ b/rust/kernel/block/mq/request.rs
@@ -16,50 +16,55 @@ use core::{
     sync::atomic::{AtomicU64, Ordering},
 };
 
-/// A wrapper around a blk-mq `struct request`. This represents an IO request.
+/// A wrapper around a blk-mq [`struct request`]. This represents an IO request.
 ///
 /// # Implementation details
 ///
 /// There are four states for a request that the Rust bindings care about:
 ///
-/// A) Request is owned by block layer (refcount 0)
-/// B) Request is owned by driver but with zero `ARef`s in existence
-///    (refcount 1)
-/// C) Request is owned by driver with exactly one `ARef` in existence
-///    (refcount 2)
-/// D) Request is owned by driver with more than one `ARef` in existence
-///    (refcount > 2)
+/// 1. Request is owned by block layer (refcount 0).
+/// 2. Request is owned by driver but with zero [`ARef`]s in existence
+///    (refcount 1).
+/// 3. Request is owned by driver with exactly one [`ARef`] in existence
+///    (refcount 2).
+/// 4. Request is owned by driver with more than one [`ARef`] in existence
+///    (refcount > 2).
 ///
 ///
-/// We need to track A and B to ensure we fail tag to request conversions for
+/// We need to track 1 and 2 to ensure we fail tag to request conversions for
 /// requests that are not owned by the driver.
 ///
-/// We need to track C and D to ensure that it is safe to end the request and hand
+/// We need to track 3 and 4 to ensure that it is safe to end the request and hand
 /// back ownership to the block layer.
 ///
 /// The states are tracked through the private `refcount` field of
 /// `RequestDataWrapper`. This structure lives in the private data area of the C
-/// `struct request`.
+/// [`struct request`].
 ///
 /// # Invariants
 ///
-/// * `self.0` is a valid `struct request` created by the C portion of the kernel.
+/// * `self.0` is a valid [`struct request`] created by the C portion of the
+///   kernel.
 /// * The private data area associated with this request must be an initialized
 ///   and valid `RequestDataWrapper<T>`.
 /// * `self` is reference counted by atomic modification of
-///   self.wrapper_ref().refcount().
+///   `self.wrapper_ref().refcount()`.
+///
+/// [`struct request`]: srctree/include/linux/blk-mq.h
 ///
 #[repr(transparent)]
 pub struct Request<T: Operations>(Opaque<bindings::request>, PhantomData<T>);
 
 impl<T: Operations> Request<T> {
-    /// Create an `ARef<Request>` from a `struct request` pointer.
+    /// Create an [`ARef<Request>`] from a [`struct request`] pointer.
     ///
     /// # Safety
     ///
     /// * The caller must own a refcount on `ptr` that is transferred to the
-    ///   returned `ARef`.
-    /// * The type invariants for `Request` must hold for the pointee of `ptr`.
+    ///   returned [`ARef`].
+    /// * The type invariants for [`Request`] must hold for the pointee of `ptr`.
+    ///
+    /// [`struct request`]: srctree/include/linux/blk-mq.h
     pub(crate) unsafe fn aref_from_raw(ptr: *mut bindings::request) -> ARef<Self> {
         // INVARIANT: By the safety requirements of this function, invariants are upheld.
         // SAFETY: By the safety requirement of this function, we own a
@@ -84,12 +89,14 @@ impl<T: Operations> Request<T> {
     }
 
     /// Try to take exclusive ownership of `this` by dropping the refcount to 0.
-    /// This fails if `this` is not the only `ARef` pointing to the underlying
-    /// `Request`.
+    /// This fails if `this` is not the only [`ARef`] pointing to the underlying
+    /// [`Request`].
     ///
-    /// If the operation is successful, `Ok` is returned with a pointer to the
-    /// C `struct request`. If the operation fails, `this` is returned in the
-    /// `Err` variant.
+    /// If the operation is successful, [`Ok`] is returned with a pointer to the
+    /// C [`struct request`]. If the operation fails, `this` is returned in the
+    /// [`Err`] variant.
+    ///
+    /// [`struct request`]: srctree/include/linux/blk-mq.h
     fn try_set_end(this: ARef<Self>) -> Result<*mut bindings::request, ARef<Self>> {
         // We can race with `TagSet::tag_to_rq`
         if let Err(_old) = this.wrapper_ref().refcount().compare_exchange(
@@ -109,7 +116,7 @@ impl<T: Operations> Request<T> {
 
     /// Notify the block layer that the request has been completed without errors.
     ///
-    /// This function will return `Err` if `this` is not the only `ARef`
+    /// This function will return [`Err`] if `this` is not the only [`ARef`]
     /// referencing the request.
     pub fn end_ok(this: ARef<Self>) -> Result<(), ARef<Self>> {
         let request_ptr = Self::try_set_end(this)?;
@@ -123,13 +130,13 @@ impl<T: Operations> Request<T> {
         Ok(())
     }
 
-    /// Return a pointer to the `RequestDataWrapper` stored in the private area
+    /// Return a pointer to the [`RequestDataWrapper`] stored in the private area
     /// of the request structure.
     ///
     /// # Safety
     ///
     /// - `this` must point to a valid allocation of size at least size of
-    ///   `Self` plus size of `RequestDataWrapper`.
+    ///   [`Self`] plus size of [`RequestDataWrapper`].
     pub(crate) unsafe fn wrapper_ptr(this: *mut Self) -> NonNull<RequestDataWrapper> {
         let request_ptr = this.cast::<bindings::request>();
         // SAFETY: By safety requirements for this function, `this` is a
@@ -141,7 +148,7 @@ impl<T: Operations> Request<T> {
         unsafe { NonNull::new_unchecked(wrapper_ptr) }
     }
 
-    /// Return a reference to the `RequestDataWrapper` stored in the private
+    /// Return a reference to the [`RequestDataWrapper`] stored in the private
     /// area of the request structure.
     pub(crate) fn wrapper_ref(&self) -> &RequestDataWrapper {
         // SAFETY: By type invariant, `self.0` is a valid allocation. Further,
@@ -152,13 +159,15 @@ impl<T: Operations> Request<T> {
     }
 }
 
-/// A wrapper around data stored in the private area of the C `struct request`.
+/// A wrapper around data stored in the private area of the C [`struct request`].
+///
+/// [`struct request`]: srctree/include/linux/blk-mq.h
 pub(crate) struct RequestDataWrapper {
     /// The Rust request refcount has the following states:
     ///
     /// - 0: The request is owned by C block layer.
-    /// - 1: The request is owned by Rust abstractions but there are no ARef references to it.
-    /// - 2+: There are `ARef` references to the request.
+    /// - 1: The request is owned by Rust abstractions but there are no [`ARef`] references to it.
+    /// - 2+: There are [`ARef`] references to the request.
     refcount: AtomicU64,
 }
 
@@ -204,7 +213,7 @@ fn atomic_relaxed_op_return(target: &AtomicU64, op: impl Fn(u64) -> u64) -> u64
 }
 
 /// Store the result of `op(target.load)` in `target` if `target.load() !=
-/// pred`, returning true if the target was updated.
+/// pred`, returning [`true`] if the target was updated.
 fn atomic_relaxed_op_unless(target: &AtomicU64, op: impl Fn(u64) -> u64, pred: u64) -> bool {
     target
         .fetch_update(Ordering::Relaxed, Ordering::Relaxed, |x| {

From ddefcd779eb7ef931e47fb41a0da288286d6a431 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Mon, 21 Oct 2024 22:28:23 +0200
Subject: [PATCH 0600/1530] Input: sparcspkr - use device managed memory for
 'state'

Use devm_kzalloc() in bbc_bee_probe() and grover_beep_probe() to
automatically free 'state' when the device is removed. Drop the
kfree(state) calls from the probe error paths and the remove functions
accordingly.

Suggested-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20241021-input_automate_of_node_put-v3-1-cc73f636e1bc@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/sparcspkr.c | 41 ++++++++++++----------------------
 1 file changed, 14 insertions(+), 27 deletions(-)

diff --git a/drivers/input/misc/sparcspkr.c b/drivers/input/misc/sparcspkr.c
index ff7b6291894a6..e484d79b55975 100644
--- a/drivers/input/misc/sparcspkr.c
+++ b/drivers/input/misc/sparcspkr.c
@@ -183,46 +183,39 @@ static int bbc_beep_probe(struct platform_device *op)
 	struct sparcspkr_state *state;
 	struct bbc_beep_info *info;
 	struct device_node *dp;
-	int err = -ENOMEM;
+	int err;
 
-	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	state = devm_kzalloc(&op->dev, sizeof(*state), GFP_KERNEL);
 	if (!state)
-		goto out_err;
+		return -ENOMEM;
 
 	state->name = "Sparc BBC Speaker";
 	state->event = bbc_spkr_event;
 	spin_lock_init(&state->lock);
 
 	dp = of_find_node_by_path("/");
-	err = -ENODEV;
 	if (!dp)
-		goto out_free;
+		return -ENODEV;
 
 	info = &state->u.bbc;
 	info->clock_freq = of_getintprop_default(dp, "clock-frequency", 0);
 	of_node_put(dp);
 	if (!info->clock_freq)
-		goto out_free;
+		return -ENODEV;
 
 	info->regs = of_ioremap(&op->resource[0], 0, 6, "bbc beep");
 	if (!info->regs)
-		goto out_free;
+		return -ENODEV;
 
 	platform_set_drvdata(op, state);
 
 	err = sparcspkr_probe(&op->dev);
-	if (err)
-		goto out_clear_drvdata;
+	if (err) {
+		of_iounmap(&op->resource[0], info->regs, 6);
+		return err;
+	}
 
 	return 0;
-
-out_clear_drvdata:
-	of_iounmap(&op->resource[0], info->regs, 6);
-
-out_free:
-	kfree(state);
-out_err:
-	return err;
 }
 
 static void bbc_remove(struct platform_device *op)
@@ -237,8 +230,6 @@ static void bbc_remove(struct platform_device *op)
 	input_unregister_device(input_dev);
 
 	of_iounmap(&op->resource[0], info->regs, 6);
-
-	kfree(state);
 }
 
 static const struct of_device_id bbc_beep_match[] = {
@@ -266,9 +257,9 @@ static int grover_beep_probe(struct platform_device *op)
 	struct grover_beep_info *info;
 	int err = -ENOMEM;
 
-	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	state = devm_kzalloc(&op->dev, sizeof(*state), GFP_KERNEL);
 	if (!state)
-		goto out_err;
+		return err;
 
 	state->name = "Sparc Grover Speaker";
 	state->event = grover_spkr_event;
@@ -277,7 +268,7 @@ static int grover_beep_probe(struct platform_device *op)
 	info = &state->u.grover;
 	info->freq_regs = of_ioremap(&op->resource[2], 0, 2, "grover beep freq");
 	if (!info->freq_regs)
-		goto out_free;
+		return err;
 
 	info->enable_reg = of_ioremap(&op->resource[3], 0, 1, "grover beep enable");
 	if (!info->enable_reg)
@@ -296,9 +287,7 @@ static int grover_beep_probe(struct platform_device *op)
 
 out_unmap_freq_regs:
 	of_iounmap(&op->resource[2], info->freq_regs, 2);
-out_free:
-	kfree(state);
-out_err:
+
 	return err;
 }
 
@@ -315,8 +304,6 @@ static void grover_remove(struct platform_device *op)
 
 	of_iounmap(&op->resource[3], info->enable_reg, 1);
 	of_iounmap(&op->resource[2], info->freq_regs, 2);
-
-	kfree(state);
 }
 
 static const struct of_device_id grover_beep_match[] = {

From 20d1278d4bb5fbb7021314c573c69d8fa3e33de1 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Mon, 21 Oct 2024 22:28:24 +0200
Subject: [PATCH 0601/1530] Input: sparcspkr - use cleanup facility for
 device_node

Use the 'free(device_node)' macro to simplify the code by automatically
freeing the device node, which removes the need for explicit calls to
'of_node_put()'.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Link: https://lore.kernel.org/r/20241021-input_automate_of_node_put-v3-2-cc73f636e1bc@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/sparcspkr.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/input/misc/sparcspkr.c b/drivers/input/misc/sparcspkr.c
index e484d79b55975..8d7303fc13bce 100644
--- a/drivers/input/misc/sparcspkr.c
+++ b/drivers/input/misc/sparcspkr.c
@@ -182,7 +182,6 @@ static int bbc_beep_probe(struct platform_device *op)
 {
 	struct sparcspkr_state *state;
 	struct bbc_beep_info *info;
-	struct device_node *dp;
 	int err;
 
 	state = devm_kzalloc(&op->dev, sizeof(*state), GFP_KERNEL);
@@ -193,13 +192,12 @@ static int bbc_beep_probe(struct platform_device *op)
 	state->event = bbc_spkr_event;
 	spin_lock_init(&state->lock);
 
-	dp = of_find_node_by_path("/");
+	struct device_node *dp __free(device_node) = of_find_node_by_path("/");
 	if (!dp)
 		return -ENODEV;
 
 	info = &state->u.bbc;
 	info->clock_freq = of_getintprop_default(dp, "clock-frequency", 0);
-	of_node_put(dp);
 	if (!info->clock_freq)
 		return -ENODEV;
 

From 92a22842ecd804d7ac456f8862f4b5f618cc53c3 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Tue, 22 Oct 2024 14:40:56 +0800
Subject: [PATCH 0602/1530] Input: userio - remove unneeded semicolon

Remove a redundant semicolon from the code.

./drivers/input/serio/userio.c:89:35-36: Unneeded semicolon

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=11431
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Link: https://lore.kernel.org/r/20241022064056.112575-1-yang.lee@linux.alibaba.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/userio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/serio/userio.c b/drivers/input/serio/userio.c
index 66c9838a1fa79..a54ddb2758b6f 100644
--- a/drivers/input/serio/userio.c
+++ b/drivers/input/serio/userio.c
@@ -86,7 +86,7 @@ static int userio_char_open(struct inode *inode, struct file *file)
 		return -ENOMEM;
 
 	userio->serio->write = userio_device_write;
-	userio->serio->port_data = userio;;
+	userio->serio->port_data = userio;
 
 	file->private_data = no_free_ptr(userio);
 

From 7447990137bf06b2aeecad9c6081e01a9f47f2aa Mon Sep 17 00:00:00 2001
From: Ajay Agarwal <ajayagarwal@google.com>
Date: Mon, 7 Oct 2024 08:59:17 +0530
Subject: [PATCH 0603/1530] PCI/ASPM: Disable L1 before disabling L1 PM
 Substates

PCIe r6.2, sec 5.5.4, requires that:

  If setting either or both of the enable bits for ASPM L1 PM Substates,
  both ports must be configured as described in this section while ASPM L1
  is disabled.

Previously, pcie_config_aspm_l1ss() assumed that "setting enable bits"
meant "setting them to 1", and it configured L1SS as follows:

  - Clear L1SS enable bits
  - Disable L1
  - Configure L1SS enable bits as required
  - Enable L1 if required

With this sequence, when disabling L1SS on an ARM A-core with a Synopsys
DesignWare PCIe core, the CPU occasionally hangs when reading
PCI_L1SS_CTL1, leading to a reboot when the CPU watchdog expires.

Move the L1 disable to the caller (pcie_config_aspm_link(), where L1 was
already enabled) so L1 is always disabled while updating the L1SS bits:

  - Disable L1
  - Clear L1SS enable bits
  - Configure L1SS enable bits as required
  - Enable L1 if required

Change pcie_aspm_cap_init() similarly.

Link: https://lore.kernel.org/r/20241007032917.872262-1-ajayagarwal@google.com
Signed-off-by: Ajay Agarwal <ajayagarwal@google.com>
[bhelgaas: comments, commit log, compute L1SS setting before config access]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/aspm.c | 92 ++++++++++++++++++++++-------------------
 1 file changed, 50 insertions(+), 42 deletions(-)

diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index cee2365e54b8b..e943691bc9317 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -805,6 +805,15 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 	pcie_capability_read_word(parent, PCI_EXP_LNKCTL, &parent_lnkctl);
 	pcie_capability_read_word(child, PCI_EXP_LNKCTL, &child_lnkctl);
 
+	/* Disable L0s/L1 before updating L1SS config */
+	if (FIELD_GET(PCI_EXP_LNKCTL_ASPMC, child_lnkctl) ||
+	    FIELD_GET(PCI_EXP_LNKCTL_ASPMC, parent_lnkctl)) {
+		pcie_capability_write_word(child, PCI_EXP_LNKCTL,
+					   child_lnkctl & ~PCI_EXP_LNKCTL_ASPMC);
+		pcie_capability_write_word(parent, PCI_EXP_LNKCTL,
+					   parent_lnkctl & ~PCI_EXP_LNKCTL_ASPMC);
+	}
+
 	/*
 	 * Setup L0s state
 	 *
@@ -829,6 +838,13 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 
 	aspm_l1ss_init(link);
 
+	/* Restore L0s/L1 if they were enabled */
+	if (FIELD_GET(PCI_EXP_LNKCTL_ASPMC, child_lnkctl) ||
+	    FIELD_GET(PCI_EXP_LNKCTL_ASPMC, parent_lnkctl)) {
+		pcie_capability_write_word(parent, PCI_EXP_LNKCTL, parent_lnkctl);
+		pcie_capability_write_word(child, PCI_EXP_LNKCTL, child_lnkctl);
+	}
+
 	/* Save default state */
 	link->aspm_default = link->aspm_enabled;
 
@@ -845,25 +861,28 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 	}
 }
 
-/* Configure the ASPM L1 substates */
+/* Configure the ASPM L1 substates. Caller must disable L1 first. */
 static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 {
-	u32 val, enable_req;
+	u32 val;
 	struct pci_dev *child = link->downstream, *parent = link->pdev;
 
-	enable_req = (link->aspm_enabled ^ state) & state;
+	val = 0;
+	if (state & PCIE_LINK_STATE_L1_1)
+		val |= PCI_L1SS_CTL1_ASPM_L1_1;
+	if (state & PCIE_LINK_STATE_L1_2)
+		val |= PCI_L1SS_CTL1_ASPM_L1_2;
+	if (state & PCIE_LINK_STATE_L1_1_PCIPM)
+		val |= PCI_L1SS_CTL1_PCIPM_L1_1;
+	if (state & PCIE_LINK_STATE_L1_2_PCIPM)
+		val |= PCI_L1SS_CTL1_PCIPM_L1_2;
 
 	/*
-	 * Here are the rules specified in the PCIe spec for enabling L1SS:
-	 * - When enabling L1.x, enable bit at parent first, then at child
-	 * - When disabling L1.x, disable bit at child first, then at parent
-	 * - When enabling ASPM L1.x, need to disable L1
-	 *   (at child followed by parent).
-	 * - The ASPM/PCIPM L1.2 must be disabled while programming timing
+	 * PCIe r6.2, sec 5.5.4, rules for enabling L1 PM Substates:
+	 * - Clear L1.x enable bits at child first, then at parent
+	 * - Set L1.x enable bits at parent first, then at child
+	 * - ASPM/PCIPM L1.2 must be disabled while programming timing
 	 *   parameters
-	 *
-	 * To keep it simple, disable all L1SS bits first, and later enable
-	 * what is needed.
 	 */
 
 	/* Disable all L1 substates */
@@ -871,26 +890,6 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 				       PCI_L1SS_CTL1_L1SS_MASK, 0);
 	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
 				       PCI_L1SS_CTL1_L1SS_MASK, 0);
-	/*
-	 * If needed, disable L1, and it gets enabled later
-	 * in pcie_config_aspm_link().
-	 */
-	if (enable_req & (PCIE_LINK_STATE_L1_1 | PCIE_LINK_STATE_L1_2)) {
-		pcie_capability_clear_word(child, PCI_EXP_LNKCTL,
-					   PCI_EXP_LNKCTL_ASPM_L1);
-		pcie_capability_clear_word(parent, PCI_EXP_LNKCTL,
-					   PCI_EXP_LNKCTL_ASPM_L1);
-	}
-
-	val = 0;
-	if (state & PCIE_LINK_STATE_L1_1)
-		val |= PCI_L1SS_CTL1_ASPM_L1_1;
-	if (state & PCIE_LINK_STATE_L1_2)
-		val |= PCI_L1SS_CTL1_ASPM_L1_2;
-	if (state & PCIE_LINK_STATE_L1_1_PCIPM)
-		val |= PCI_L1SS_CTL1_PCIPM_L1_1;
-	if (state & PCIE_LINK_STATE_L1_2_PCIPM)
-		val |= PCI_L1SS_CTL1_PCIPM_L1_2;
 
 	/* Enable what we need to enable */
 	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
@@ -937,21 +936,30 @@ static void pcie_config_aspm_link(struct pcie_link_state *link, u32 state)
 		dwstream |= PCI_EXP_LNKCTL_ASPM_L1;
 	}
 
+	/*
+	 * Per PCIe r6.2, sec 5.5.4, setting either or both of the enable
+	 * bits for ASPM L1 PM Substates must be done while ASPM L1 is
+	 * disabled. Disable L1 here and apply new configuration after L1SS
+	 * configuration has been completed.
+	 *
+	 * Per sec 7.5.3.7, when disabling ASPM L1, software must disable
+	 * it in the Downstream component prior to disabling it in the
+	 * Upstream component, and ASPM L1 must be enabled in the Upstream
+	 * component prior to enabling it in the Downstream component.
+	 *
+	 * Sec 7.5.3.7 also recommends programming the same ASPM Control
+	 * value for all functions of a multi-function device.
+	 */
+	list_for_each_entry(child, &linkbus->devices, bus_list)
+		pcie_config_aspm_dev(child, 0);
+	pcie_config_aspm_dev(parent, 0);
+
 	if (link->aspm_capable & PCIE_LINK_STATE_L1SS)
 		pcie_config_aspm_l1ss(link, state);
 
-	/*
-	 * Spec 2.0 suggests all functions should be configured the
-	 * same setting for ASPM. Enabling ASPM L1 should be done in
-	 * upstream component first and then downstream, and vice
-	 * versa for disabling ASPM L1. Spec doesn't mention L0S.
-	 */
-	if (state & PCIE_LINK_STATE_L1)
-		pcie_config_aspm_dev(parent, upstream);
+	pcie_config_aspm_dev(parent, upstream);
 	list_for_each_entry(child, &linkbus->devices, bus_list)
 		pcie_config_aspm_dev(child, dwstream);
-	if (!(state & PCIE_LINK_STATE_L1))
-		pcie_config_aspm_dev(parent, upstream);
 
 	link->aspm_enabled = state;
 

From 8974f34de2ef173470a596a4dee22f4922583d1b Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Tue, 24 Sep 2024 14:42:41 +0800
Subject: [PATCH 0604/1530] dmaengine: loongson2-apb: Rename the prefix ls2x to
 loongson2

Since commit e06c43231214 ("dmaengine: Loongson1: Add Loongson-1 APB DMA
driver"), the Loongson-1 dma controller was added.

Unfortunately their naming has not been standardized, as CPUs belonging
to the same Loongson family, we expect to standardize the naming for
ease of understanding.

Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Link: https://lore.kernel.org/r/20240924064241.2414629-1-zhoubinbin@loongson.cn
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 MAINTAINERS                                   |  4 +--
 arch/loongarch/configs/loongson3_defconfig    |  2 +-
 drivers/dma/Kconfig                           | 28 +++++++++----------
 drivers/dma/Makefile                          |  2 +-
 .../{ls2x-apb-dma.c => loongson2-apb-dma.c}   |  4 +--
 5 files changed, 20 insertions(+), 20 deletions(-)
 rename drivers/dma/{ls2x-apb-dma.c => loongson2-apb-dma.c} (99%)

diff --git a/MAINTAINERS b/MAINTAINERS
index c27f3190737f8..c5cda5ad4022f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13369,12 +13369,12 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/gpio/loongson,ls-gpio.yaml
 F:	drivers/gpio/gpio-loongson-64bit.c
 
-LOONGSON LS2X APB DMA DRIVER
+LOONGSON-2 APB DMA DRIVER
 M:	Binbin Zhou <zhoubinbin@loongson.cn>
 L:	dmaengine@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml
-F:	drivers/dma/ls2x-apb-dma.c
+F:	drivers/dma/loongson2-apb-dma.c
 
 LOONGSON LS2X I2C DRIVER
 M:	Binbin Zhou <zhoubinbin@loongson.cn>
diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index 75b366407a60a..6dfedda930a24 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -775,7 +775,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_EFI=y
 CONFIG_RTC_DRV_LOONGSON=y
 CONFIG_DMADEVICES=y
-CONFIG_LS2X_APB_DMA=y
+CONFIG_LOONGSON2_APB_DMA=y
 CONFIG_UDMABUF=y
 CONFIG_DMABUF_HEAPS=y
 CONFIG_DMABUF_HEAPS_SYSTEM=y
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index d9ec1e69e4283..e994d6e0779e0 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -378,6 +378,20 @@ config LOONGSON1_APB_DMA
 	  This selects support for the APB DMA controller in Loongson1 SoCs,
 	  which is required by Loongson1 NAND and audio support.
 
+config LOONGSON2_APB_DMA
+	tristate "Loongson2 APB DMA support"
+	depends on LOONGARCH || COMPILE_TEST
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support for the Loongson2 APB DMA controller driver. The
+	  DMA controller is having single DMA channel which can be
+	  configured for different peripherals like audio, nand, sdio
+	  etc which is in APB bus.
+
+	  This DMA controller transfers data from memory to peripheral fifo.
+	  It does not support memory to memory data transfer.
+
 config LPC18XX_DMAMUX
 	bool "NXP LPC18xx/43xx DMA MUX for PL080"
 	depends on ARCH_LPC18XX || COMPILE_TEST
@@ -396,20 +410,6 @@ config LPC32XX_DMAMUX
 	  Support for PL080 multiplexed DMA request lines on
 	  LPC32XX platrofm.
 
-config LS2X_APB_DMA
-	tristate "Loongson LS2X APB DMA support"
-	depends on LOONGARCH || COMPILE_TEST
-	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
-	help
-	  Support for the Loongson LS2X APB DMA controller driver. The
-	  DMA controller is having single DMA channel which can be
-	  configured for different peripherals like audio, nand, sdio
-	  etc which is in APB bus.
-
-	  This DMA controller transfers data from memory to peripheral fifo.
-	  It does not support memory to memory data transfer.
-
 config MCF_EDMA
 	tristate "Freescale eDMA engine support, ColdFire mcf5441x SoCs"
 	depends on M5441x || (COMPILE_TEST && FSL_EDMA=n)
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index ad6a03c052ec4..5b2a52f4f2ee9 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -50,9 +50,9 @@ obj-$(CONFIG_INTEL_IOATDMA) += ioat/
 obj-y += idxd/
 obj-$(CONFIG_K3_DMA) += k3dma.o
 obj-$(CONFIG_LOONGSON1_APB_DMA) += loongson1-apb-dma.o
+obj-$(CONFIG_LOONGSON2_APB_DMA) += loongson2-apb-dma.o
 obj-$(CONFIG_LPC18XX_DMAMUX) += lpc18xx-dmamux.o
 obj-$(CONFIG_LPC32XX_DMAMUX) += lpc32xx-dmamux.o
-obj-$(CONFIG_LS2X_APB_DMA) += ls2x-apb-dma.o
 obj-$(CONFIG_MILBEAUT_HDMAC) += milbeaut-hdmac.o
 obj-$(CONFIG_MILBEAUT_XDMAC) += milbeaut-xdmac.o
 obj-$(CONFIG_MMP_PDMA) += mmp_pdma.o
diff --git a/drivers/dma/ls2x-apb-dma.c b/drivers/dma/loongson2-apb-dma.c
similarity index 99%
rename from drivers/dma/ls2x-apb-dma.c
rename to drivers/dma/loongson2-apb-dma.c
index 2460cf9a44f5d..367ed34ce4da5 100644
--- a/drivers/dma/ls2x-apb-dma.c
+++ b/drivers/dma/loongson2-apb-dma.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Driver for the Loongson LS2X APB DMA Controller
+ * Driver for the Loongson-2 APB DMA Controller
  *
  * Copyright (C) 2017-2023 Loongson Corporation
  */
@@ -700,6 +700,6 @@ static struct platform_driver ls2x_dmac_driver = {
 };
 module_platform_driver(ls2x_dmac_driver);
 
-MODULE_DESCRIPTION("Loongson LS2X APB DMA Controller driver");
+MODULE_DESCRIPTION("Loongson-2 APB DMA Controller driver");
 MODULE_AUTHOR("Loongson Technology Corporation Limited");
 MODULE_LICENSE("GPL");

From b509b5e59793ce21f9dff0cc11d970a63a9cc48e Mon Sep 17 00:00:00 2001
From: Jean Delvare <jdelvare@suse.de>
Date: Tue, 22 Oct 2024 13:40:17 +0200
Subject: [PATCH 0605/1530] pinctrl: imx-scmi: Drop obsolete dependency on
 COMPILE_TEST

Since commit 0166dc11be91 ("of: make CONFIG_OF user selectable"), OF
can be enabled on all architectures. Therefore depending on
COMPILE_TEST as an alternative is no longer needed.

As ARM_SCMI_PROTOCOL already depends on COMPILE_TEST, we also don't
need to add COMPILE_TEST as an alternative dependency for it.

Signed-off-by: Jean Delvare <jdelvare@suse.de>
Link: https://lore.kernel.org/20241022134017.172411db@endymion.delvare
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/freescale/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/freescale/Kconfig b/drivers/pinctrl/freescale/Kconfig
index 70acfbdd318b0..4c420b21b804d 100644
--- a/drivers/pinctrl/freescale/Kconfig
+++ b/drivers/pinctrl/freescale/Kconfig
@@ -9,7 +9,7 @@ config PINCTRL_IMX
 
 config PINCTRL_IMX_SCMI
 	tristate "i.MX95 pinctrl driver using SCMI protocol interface"
-	depends on ARM_SCMI_PROTOCOL && OF || COMPILE_TEST
+	depends on ARM_SCMI_PROTOCOL && OF
 	select PINMUX
 	select GENERIC_PINCONF
 	select GENERIC_PINCTRL_GROUPS

From 56c9d1a033d628b7abac88a5e19c9a5111b01302 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Thu, 17 Oct 2024 23:11:18 +0200
Subject: [PATCH 0606/1530] dt-bindings: pinctrl: fsl,imx6ul-pinctrl: Convert
 i.MX35/5x/6 to YAML

The IOMUXC controller description is almost identical on i.MX35/5x/6 SoCs,
except for the configuration bits which differ across SoCs. Rename the
fsl,imx6ul-pinctrl.yaml to fsl,imx35-pinctrl.yaml, fill in compatible
strings for the other SoCs and fill in the various bits into desciption.
This way, i.MX35/5x/6 series SoCs can all be converted to DT schema.
Remove the old text DT bindings description.

Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Marek Vasut <marex@denx.de>
Link: https://lore.kernel.org/20241017211241.170861-1-marex@denx.de
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/fsl,imx35-pinctrl.txt    | 33 -------
 ...ul-pinctrl.yaml => fsl,imx35-pinctrl.yaml} | 88 ++++++++++++++++---
 .../bindings/pinctrl/fsl,imx50-pinctrl.txt    | 32 -------
 .../bindings/pinctrl/fsl,imx51-pinctrl.txt    | 32 -------
 .../bindings/pinctrl/fsl,imx53-pinctrl.txt    | 32 -------
 .../bindings/pinctrl/fsl,imx6dl-pinctrl.txt   | 38 --------
 .../bindings/pinctrl/fsl,imx6q-pinctrl.txt    | 38 --------
 .../bindings/pinctrl/fsl,imx6sl-pinctrl.txt   | 39 --------
 .../bindings/pinctrl/fsl,imx6sll-pinctrl.txt  | 40 ---------
 .../bindings/pinctrl/fsl,imx6sx-pinctrl.txt   | 36 --------
 10 files changed, 78 insertions(+), 330 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/pinctrl/fsl,imx35-pinctrl.txt
 rename Documentation/devicetree/bindings/pinctrl/{fsl,imx6ul-pinctrl.yaml => fsl,imx35-pinctrl.yaml} (50%)
 delete mode 100644 Documentation/devicetree/bindings/pinctrl/fsl,imx50-pinctrl.txt
 delete mode 100644 Documentation/devicetree/bindings/pinctrl/fsl,imx51-pinctrl.txt
 delete mode 100644 Documentation/devicetree/bindings/pinctrl/fsl,imx53-pinctrl.txt
 delete mode 100644 Documentation/devicetree/bindings/pinctrl/fsl,imx6dl-pinctrl.txt
 delete mode 100644 Documentation/devicetree/bindings/pinctrl/fsl,imx6q-pinctrl.txt
 delete mode 100644 Documentation/devicetree/bindings/pinctrl/fsl,imx6sl-pinctrl.txt
 delete mode 100644 Documentation/devicetree/bindings/pinctrl/fsl,imx6sll-pinctrl.txt
 delete mode 100644 Documentation/devicetree/bindings/pinctrl/fsl,imx6sx-pinctrl.txt

diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx35-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx35-pinctrl.txt
deleted file mode 100644
index c083dfd25db93..0000000000000
--- a/Documentation/devicetree/bindings/pinctrl/fsl,imx35-pinctrl.txt
+++ /dev/null
@@ -1,33 +0,0 @@
-* Freescale IMX35 IOMUX Controller
-
-Please refer to fsl,imx-pinctrl.txt in this directory for common binding part
-and usage.
-
-Required properties:
-- compatible: "fsl,imx35-iomuxc"
-- fsl,pins: two integers array, represents a group of pins mux and config
-  setting. The format is fsl,pins = <PIN_FUNC_ID CONFIG>, PIN_FUNC_ID is a
-  pin working on a specific function, CONFIG is the pad setting value like
-  pull-up for this pin. Please refer to imx35 datasheet for the valid pad
-  config settings.
-
-CONFIG bits definition:
-PAD_CTL_DRIVE_VOLAGAGE_18	(1 << 13)
-PAD_CTL_DRIVE_VOLAGAGE_33	(0 << 13)
-PAD_CTL_HYS			(1 << 8)
-PAD_CTL_PKE			(1 << 7)
-PAD_CTL_PUE			(1 << 6)
-PAD_CTL_PUS_100K_DOWN		(0 << 4)
-PAD_CTL_PUS_47K_UP		(1 << 4)
-PAD_CTL_PUS_100K_UP		(2 << 4)
-PAD_CTL_PUS_22K_UP		(3 << 4)
-PAD_CTL_ODE_CMOS		(0 << 3)
-PAD_CTL_ODE_OPENDRAIN		(1 << 3)
-PAD_CTL_DSE_NOMINAL		(0 << 1)
-PAD_CTL_DSE_HIGH		(1 << 1)
-PAD_CTL_DSE_MAX			(2 << 1)
-PAD_CTL_SRE_FAST		(1 << 0)
-PAD_CTL_SRE_SLOW		(0 << 0)
-
-Refer to imx35-pinfunc.h in device tree source folder for all available
-imx35 PIN_FUNC_ID.
diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx6ul-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/fsl,imx35-pinctrl.yaml
similarity index 50%
rename from Documentation/devicetree/bindings/pinctrl/fsl,imx6ul-pinctrl.yaml
rename to Documentation/devicetree/bindings/pinctrl/fsl,imx35-pinctrl.yaml
index 906b264a9e3cd..265c43ab76f4c 100644
--- a/Documentation/devicetree/bindings/pinctrl/fsl,imx6ul-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/fsl,imx35-pinctrl.yaml
@@ -1,10 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/pinctrl/fsl,imx6ul-pinctrl.yaml#
+$id: http://devicetree.org/schemas/pinctrl/fsl,imx35-pinctrl.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Freescale IMX6UL IOMUX Controller
+title: Freescale IMX35/IMX5x/IMX6 IOMUX Controller
 
 maintainers:
   - Dong Aisheng <aisheng.dong@nxp.com>
@@ -18,9 +18,21 @@ allOf:
 
 properties:
   compatible:
-    enum:
-      - fsl,imx6ul-iomuxc
-      - fsl,imx6ull-iomuxc-snvs
+    oneOf:
+      - enum:
+          - fsl,imx35-iomuxc
+          - fsl,imx51-iomuxc
+          - fsl,imx53-iomuxc
+          - fsl,imx6dl-iomuxc
+          - fsl,imx6q-iomuxc
+          - fsl,imx6sl-iomuxc
+          - fsl,imx6sll-iomuxc
+          - fsl,imx6sx-iomuxc
+          - fsl,imx6ul-iomuxc
+          - fsl,imx6ull-iomuxc-snvs
+      - items:
+          - const: fsl,imx50-iomuxc
+          - const: fsl,imx53-iomuxc
 
   reg:
     maxItems: 1
@@ -39,9 +51,9 @@ patternProperties:
           each entry consists of 6 integers and represents the mux and config
           setting for one pin. The first 5 integers <mux_reg conf_reg input_reg
           mux_val input_val> are specified using a PIN_FUNC_ID macro, which can
-          be found in <arch/arm/boot/dts/imx6ul-pinfunc.h>. The last integer
+          be found in <arch/arm/boot/dts/nxp/imx/imx*-pinfunc.h>. The last integer
           CONFIG is the pad setting value like pull-up on this pin. Please
-          refer to i.MX6UL Reference Manual for detailed CONFIG settings.
+          refer to matching i.MX Reference Manual for detailed CONFIG settings.
         $ref: /schemas/types.yaml#/definitions/uint32-matrix
         items:
           items:
@@ -56,7 +68,41 @@ patternProperties:
             - description: |
                 "input_val" indicates the select input value to be applied.
             - description: |
-                "pad_setting" indicates the pad configuration value to be applied:
+                "pad_setting" indicates the pad configuration value to be applied.
+                Common i.MX35
+                  PAD_CTL_DRIVE_VOLAGAGE_18       (1 << 13)
+                  PAD_CTL_DRIVE_VOLAGAGE_33       (0 << 13)
+                  PAD_CTL_HYS                     (1 << 8)
+                  PAD_CTL_PKE                     (1 << 7)
+                  PAD_CTL_PUE                     (1 << 6)
+                  PAD_CTL_PUS_100K_DOWN           (0 << 4)
+                  PAD_CTL_PUS_47K_UP              (1 << 4)
+                  PAD_CTL_PUS_100K_UP             (2 << 4)
+                  PAD_CTL_PUS_22K_UP              (3 << 4)
+                  PAD_CTL_ODE_CMOS                (0 << 3)
+                  PAD_CTL_ODE_OPENDRAIN           (1 << 3)
+                  PAD_CTL_DSE_NOMINAL             (0 << 1)
+                  PAD_CTL_DSE_HIGH                (1 << 1)
+                  PAD_CTL_DSE_MAX                 (2 << 1)
+                  PAD_CTL_SRE_FAST                (1 << 0)
+                  PAD_CTL_SRE_SLOW                (0 << 0)
+                Common i.MX50/i.MX51/i.MX53 bits
+                  PAD_CTL_HVE                     (1 << 13)
+                  PAD_CTL_HYS                     (1 << 8)
+                  PAD_CTL_PKE                     (1 << 7)
+                  PAD_CTL_PUE                     (1 << 6)
+                  PAD_CTL_PUS_100K_DOWN           (0 << 4)
+                  PAD_CTL_PUS_47K_UP              (1 << 4)
+                  PAD_CTL_PUS_100K_UP             (2 << 4)
+                  PAD_CTL_PUS_22K_UP              (3 << 4)
+                  PAD_CTL_ODE                     (1 << 3)
+                  PAD_CTL_DSE_LOW                 (0 << 1)
+                  PAD_CTL_DSE_MED                 (1 << 1)
+                  PAD_CTL_DSE_HIGH                (2 << 1)
+                  PAD_CTL_DSE_MAX                 (3 << 1)
+                  PAD_CTL_SRE_FAST                (1 << 0)
+                  PAD_CTL_SRE_SLOW                (0 << 0)
+                Common i.MX6 bits
                   PAD_CTL_HYS                     (1 << 16)
                   PAD_CTL_PUS_100K_DOWN           (0 << 14)
                   PAD_CTL_PUS_47K_UP              (1 << 14)
@@ -69,6 +115,11 @@ patternProperties:
                   PAD_CTL_SPEED_MED               (1 << 6)
                   PAD_CTL_SPEED_HIGH              (3 << 6)
                   PAD_CTL_DSE_DISABLE             (0 << 3)
+                  PAD_CTL_SRE_FAST                (1 << 0)
+                  PAD_CTL_SRE_SLOW                (0 << 0)
+                i.MX6SL/MX6SLL specific bits
+                  PAD_CTL_LVE                     (1 << 22) (MX6SL/SLL only)
+                i.MX6SLL/i.MX6SX/i.MX6UL/i.MX6ULL specific bits
                   PAD_CTL_DSE_260ohm              (1 << 3)
                   PAD_CTL_DSE_130ohm              (2 << 3)
                   PAD_CTL_DSE_87ohm               (3 << 3)
@@ -76,8 +127,14 @@ patternProperties:
                   PAD_CTL_DSE_52ohm               (5 << 3)
                   PAD_CTL_DSE_43ohm               (6 << 3)
                   PAD_CTL_DSE_37ohm               (7 << 3)
-                  PAD_CTL_SRE_FAST                (1 << 0)
-                  PAD_CTL_SRE_SLOW                (0 << 0)
+                i.MX6DL/i.MX6Q/i.MX6SL specific bits
+                  PAD_CTL_DSE_240ohm              (1 << 3)
+                  PAD_CTL_DSE_120ohm              (2 << 3)
+                  PAD_CTL_DSE_80ohm               (3 << 3)
+                  PAD_CTL_DSE_60ohm               (4 << 3)
+                  PAD_CTL_DSE_48ohm               (5 << 3)
+                  PAD_CTL_DSE_40ohm               (6 << 3)
+                  PAD_CTL_DSE_34ohm               (7 << 3)
 
     required:
       - fsl,pins
@@ -114,3 +171,14 @@ examples:
         >;
       };
     };
+  - |
+    iomuxc_mx6q: pinctrl@20e0000 {
+        compatible = "fsl,imx6q-iomuxc";
+        reg = <0x20e0000 0x4000>;
+
+        pinctrl_uart4: uart4grp {
+            fsl,pins =
+                <0x288 0x658 0x000 0x3 0x0	0x140>,
+                <0x28c 0x65c 0x938 0x3 0x3	0x140>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx50-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx50-pinctrl.txt
deleted file mode 100644
index 6da01d619d33e..0000000000000
--- a/Documentation/devicetree/bindings/pinctrl/fsl,imx50-pinctrl.txt
+++ /dev/null
@@ -1,32 +0,0 @@
-* Freescale IMX50 IOMUX Controller
-
-Please refer to fsl,imx-pinctrl.txt in this directory for common binding part
-and usage.
-
-Required properties:
-- compatible: "fsl,imx50-iomuxc"
-- fsl,pins: two integers array, represents a group of pins mux and config
-  setting. The format is fsl,pins = <PIN_FUNC_ID CONFIG>, PIN_FUNC_ID is a
-  pin working on a specific function, CONFIG is the pad setting value like
-  pull-up for this pin. Please refer to imx50 datasheet for the valid pad
-  config settings.
-
-CONFIG bits definition:
-PAD_CTL_HVE			(1 << 13)
-PAD_CTL_HYS			(1 << 8)
-PAD_CTL_PKE			(1 << 7)
-PAD_CTL_PUE			(1 << 6)
-PAD_CTL_PUS_100K_DOWN		(0 << 4)
-PAD_CTL_PUS_47K_UP		(1 << 4)
-PAD_CTL_PUS_100K_UP		(2 << 4)
-PAD_CTL_PUS_22K_UP		(3 << 4)
-PAD_CTL_ODE			(1 << 3)
-PAD_CTL_DSE_LOW			(0 << 1)
-PAD_CTL_DSE_MED			(1 << 1)
-PAD_CTL_DSE_HIGH		(2 << 1)
-PAD_CTL_DSE_MAX			(3 << 1)
-PAD_CTL_SRE_FAST		(1 << 0)
-PAD_CTL_SRE_SLOW		(0 << 0)
-
-Refer to imx50-pinfunc.h in device tree source folder for all available
-imx50 PIN_FUNC_ID.
diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx51-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx51-pinctrl.txt
deleted file mode 100644
index 4d1408fcc99cf..0000000000000
--- a/Documentation/devicetree/bindings/pinctrl/fsl,imx51-pinctrl.txt
+++ /dev/null
@@ -1,32 +0,0 @@
-* Freescale IMX51 IOMUX Controller
-
-Please refer to fsl,imx-pinctrl.txt in this directory for common binding part
-and usage.
-
-Required properties:
-- compatible: "fsl,imx51-iomuxc"
-- fsl,pins: two integers array, represents a group of pins mux and config
-  setting. The format is fsl,pins = <PIN_FUNC_ID CONFIG>, PIN_FUNC_ID is a
-  pin working on a specific function, CONFIG is the pad setting value like
-  pull-up for this pin. Please refer to imx51 datasheet for the valid pad
-  config settings.
-
-CONFIG bits definition:
-PAD_CTL_HVE			(1 << 13)
-PAD_CTL_HYS			(1 << 8)
-PAD_CTL_PKE			(1 << 7)
-PAD_CTL_PUE			(1 << 6)
-PAD_CTL_PUS_100K_DOWN		(0 << 4)
-PAD_CTL_PUS_47K_UP		(1 << 4)
-PAD_CTL_PUS_100K_UP		(2 << 4)
-PAD_CTL_PUS_22K_UP		(3 << 4)
-PAD_CTL_ODE			(1 << 3)
-PAD_CTL_DSE_LOW			(0 << 1)
-PAD_CTL_DSE_MED			(1 << 1)
-PAD_CTL_DSE_HIGH		(2 << 1)
-PAD_CTL_DSE_MAX			(3 << 1)
-PAD_CTL_SRE_FAST		(1 << 0)
-PAD_CTL_SRE_SLOW		(0 << 0)
-
-Refer to imx51-pinfunc.h in device tree source folder for all available
-imx51 PIN_FUNC_ID.
diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx53-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx53-pinctrl.txt
deleted file mode 100644
index 25dcb77cfaf74..0000000000000
--- a/Documentation/devicetree/bindings/pinctrl/fsl,imx53-pinctrl.txt
+++ /dev/null
@@ -1,32 +0,0 @@
-* Freescale IMX53 IOMUX Controller
-
-Please refer to fsl,imx-pinctrl.txt in this directory for common binding part
-and usage.
-
-Required properties:
-- compatible: "fsl,imx53-iomuxc"
-- fsl,pins: two integers array, represents a group of pins mux and config
-  setting. The format is fsl,pins = <PIN_FUNC_ID CONFIG>, PIN_FUNC_ID is a
-  pin working on a specific function, CONFIG is the pad setting value like
-  pull-up for this pin. Please refer to imx53 datasheet for the valid pad
-  config settings.
-
-CONFIG bits definition:
-PAD_CTL_HVE			(1 << 13)
-PAD_CTL_HYS			(1 << 8)
-PAD_CTL_PKE			(1 << 7)
-PAD_CTL_PUE			(1 << 6)
-PAD_CTL_PUS_100K_DOWN		(0 << 4)
-PAD_CTL_PUS_47K_UP		(1 << 4)
-PAD_CTL_PUS_100K_UP		(2 << 4)
-PAD_CTL_PUS_22K_UP		(3 << 4)
-PAD_CTL_ODE			(1 << 3)
-PAD_CTL_DSE_LOW			(0 << 1)
-PAD_CTL_DSE_MED			(1 << 1)
-PAD_CTL_DSE_HIGH		(2 << 1)
-PAD_CTL_DSE_MAX			(3 << 1)
-PAD_CTL_SRE_FAST		(1 << 0)
-PAD_CTL_SRE_SLOW		(0 << 0)
-
-Refer to imx53-pinfunc.h in device tree source folder for all available
-imx53 PIN_FUNC_ID.
diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx6dl-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx6dl-pinctrl.txt
deleted file mode 100644
index 0ac5bee875056..0000000000000
--- a/Documentation/devicetree/bindings/pinctrl/fsl,imx6dl-pinctrl.txt
+++ /dev/null
@@ -1,38 +0,0 @@
-* Freescale IMX6 DualLite/Solo IOMUX Controller
-
-Please refer to fsl,imx-pinctrl.txt in this directory for common binding part
-and usage.
-
-Required properties:
-- compatible: "fsl,imx6dl-iomuxc"
-- fsl,pins: two integers array, represents a group of pins mux and config
-  setting. The format is fsl,pins = <PIN_FUNC_ID CONFIG>, PIN_FUNC_ID is a
-  pin working on a specific function, CONFIG is the pad setting value like
-  pull-up for this pin. Please refer to imx6dl datasheet for the valid pad
-  config settings.
-
-CONFIG bits definition:
-PAD_CTL_HYS                     (1 << 16)
-PAD_CTL_PUS_100K_DOWN           (0 << 14)
-PAD_CTL_PUS_47K_UP              (1 << 14)
-PAD_CTL_PUS_100K_UP             (2 << 14)
-PAD_CTL_PUS_22K_UP              (3 << 14)
-PAD_CTL_PUE                     (1 << 13)
-PAD_CTL_PKE                     (1 << 12)
-PAD_CTL_ODE                     (1 << 11)
-PAD_CTL_SPEED_LOW               (1 << 6)
-PAD_CTL_SPEED_MED               (2 << 6)
-PAD_CTL_SPEED_HIGH              (3 << 6)
-PAD_CTL_DSE_DISABLE             (0 << 3)
-PAD_CTL_DSE_240ohm              (1 << 3)
-PAD_CTL_DSE_120ohm              (2 << 3)
-PAD_CTL_DSE_80ohm               (3 << 3)
-PAD_CTL_DSE_60ohm               (4 << 3)
-PAD_CTL_DSE_48ohm               (5 << 3)
-PAD_CTL_DSE_40ohm               (6 << 3)
-PAD_CTL_DSE_34ohm               (7 << 3)
-PAD_CTL_SRE_FAST                (1 << 0)
-PAD_CTL_SRE_SLOW                (0 << 0)
-
-Refer to imx6dl-pinfunc.h in device tree source folder for all available
-imx6dl PIN_FUNC_ID.
diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx6q-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx6q-pinctrl.txt
deleted file mode 100644
index 546610cf2ae71..0000000000000
--- a/Documentation/devicetree/bindings/pinctrl/fsl,imx6q-pinctrl.txt
+++ /dev/null
@@ -1,38 +0,0 @@
-* Freescale IMX6Q IOMUX Controller
-
-Please refer to fsl,imx-pinctrl.txt in this directory for common binding part
-and usage.
-
-Required properties:
-- compatible: "fsl,imx6q-iomuxc"
-- fsl,pins: two integers array, represents a group of pins mux and config
-  setting. The format is fsl,pins = <PIN_FUNC_ID CONFIG>, PIN_FUNC_ID is a
-  pin working on a specific function, CONFIG is the pad setting value like
-  pull-up for this pin. Please refer to imx6q datasheet for the valid pad
-  config settings.
-
-CONFIG bits definition:
-PAD_CTL_HYS                     (1 << 16)
-PAD_CTL_PUS_100K_DOWN           (0 << 14)
-PAD_CTL_PUS_47K_UP              (1 << 14)
-PAD_CTL_PUS_100K_UP             (2 << 14)
-PAD_CTL_PUS_22K_UP              (3 << 14)
-PAD_CTL_PUE                     (1 << 13)
-PAD_CTL_PKE                     (1 << 12)
-PAD_CTL_ODE                     (1 << 11)
-PAD_CTL_SPEED_LOW               (1 << 6)
-PAD_CTL_SPEED_MED               (2 << 6)
-PAD_CTL_SPEED_HIGH              (3 << 6)
-PAD_CTL_DSE_DISABLE             (0 << 3)
-PAD_CTL_DSE_240ohm              (1 << 3)
-PAD_CTL_DSE_120ohm              (2 << 3)
-PAD_CTL_DSE_80ohm               (3 << 3)
-PAD_CTL_DSE_60ohm               (4 << 3)
-PAD_CTL_DSE_48ohm               (5 << 3)
-PAD_CTL_DSE_40ohm               (6 << 3)
-PAD_CTL_DSE_34ohm               (7 << 3)
-PAD_CTL_SRE_FAST                (1 << 0)
-PAD_CTL_SRE_SLOW                (0 << 0)
-
-Refer to imx6q-pinfunc.h in device tree source folder for all available
-imx6q PIN_FUNC_ID.
diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx6sl-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx6sl-pinctrl.txt
deleted file mode 100644
index e5f6d1f065a42..0000000000000
--- a/Documentation/devicetree/bindings/pinctrl/fsl,imx6sl-pinctrl.txt
+++ /dev/null
@@ -1,39 +0,0 @@
-* Freescale IMX6 SoloLite IOMUX Controller
-
-Please refer to fsl,imx-pinctrl.txt in this directory for common binding part
-and usage.
-
-Required properties:
-- compatible: "fsl,imx6sl-iomuxc"
-- fsl,pins: two integers array, represents a group of pins mux and config
-  setting. The format is fsl,pins = <PIN_FUNC_ID CONFIG>, PIN_FUNC_ID is a
-  pin working on a specific function, CONFIG is the pad setting value like
-  pull-up for this pin. Please refer to imx6sl datasheet for the valid pad
-  config settings.
-
-CONFIG bits definition:
-PAD_CTL_LVE                     (1 << 22)
-PAD_CTL_HYS                     (1 << 16)
-PAD_CTL_PUS_100K_DOWN           (0 << 14)
-PAD_CTL_PUS_47K_UP              (1 << 14)
-PAD_CTL_PUS_100K_UP             (2 << 14)
-PAD_CTL_PUS_22K_UP              (3 << 14)
-PAD_CTL_PUE                     (1 << 13)
-PAD_CTL_PKE                     (1 << 12)
-PAD_CTL_ODE                     (1 << 11)
-PAD_CTL_SPEED_LOW               (1 << 6)
-PAD_CTL_SPEED_MED               (2 << 6)
-PAD_CTL_SPEED_HIGH              (3 << 6)
-PAD_CTL_DSE_DISABLE             (0 << 3)
-PAD_CTL_DSE_240ohm              (1 << 3)
-PAD_CTL_DSE_120ohm              (2 << 3)
-PAD_CTL_DSE_80ohm               (3 << 3)
-PAD_CTL_DSE_60ohm               (4 << 3)
-PAD_CTL_DSE_48ohm               (5 << 3)
-PAD_CTL_DSE_40ohm               (6 << 3)
-PAD_CTL_DSE_34ohm               (7 << 3)
-PAD_CTL_SRE_FAST                (1 << 0)
-PAD_CTL_SRE_SLOW                (0 << 0)
-
-Refer to imx6sl-pinfunc.h in device tree source folder for all available
-imx6sl PIN_FUNC_ID.
diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx6sll-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx6sll-pinctrl.txt
deleted file mode 100644
index 175e8939a3018..0000000000000
--- a/Documentation/devicetree/bindings/pinctrl/fsl,imx6sll-pinctrl.txt
+++ /dev/null
@@ -1,40 +0,0 @@
-* Freescale i.MX6 SLL IOMUX Controller
-
-Please refer to fsl,imx-pinctrl.txt in this directory for common binding part
-and usage.
-
-Required properties:
-- compatible: "fsl,imx6sll-iomuxc"
-- fsl,pins: each entry consists of 6 integers and represents the mux and config
-  setting for one pin.  The first 5 integers <mux_reg conf_reg input_reg mux_val
-  input_val> are specified using a PIN_FUNC_ID macro, which can be found in
-  imx6sll-pinfunc.h under device tree source folder.  The last integer CONFIG is
-  the pad setting value like pull-up on this pin.  Please refer to i.MX6SLL
-  Reference Manual for detailed CONFIG settings.
-
-CONFIG bits definition:
-PAD_CTL_LVE			(1 << 22)
-PAD_CTL_HYS                     (1 << 16)
-PAD_CTL_PUS_100K_DOWN           (0 << 14)
-PAD_CTL_PUS_47K_UP              (1 << 14)
-PAD_CTL_PUS_100K_UP             (2 << 14)
-PAD_CTL_PUS_22K_UP              (3 << 14)
-PAD_CTL_PUE                     (1 << 13)
-PAD_CTL_PKE                     (1 << 12)
-PAD_CTL_ODE                     (1 << 11)
-PAD_CTL_SPEED_LOW               (0 << 6)
-PAD_CTL_SPEED_MED               (1 << 6)
-PAD_CTL_SPEED_HIGH              (3 << 6)
-PAD_CTL_DSE_DISABLE             (0 << 3)
-PAD_CTL_DSE_260ohm              (1 << 3)
-PAD_CTL_DSE_130ohm              (2 << 3)
-PAD_CTL_DSE_87ohm               (3 << 3)
-PAD_CTL_DSE_65ohm               (4 << 3)
-PAD_CTL_DSE_52ohm               (5 << 3)
-PAD_CTL_DSE_43ohm               (6 << 3)
-PAD_CTL_DSE_37ohm               (7 << 3)
-PAD_CTL_SRE_FAST                (1 << 0)
-PAD_CTL_SRE_SLOW                (0 << 0)
-
-Refer to imx6sll-pinfunc.h in device tree source folder for all available
-imx6sll PIN_FUNC_ID.
diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx6sx-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx6sx-pinctrl.txt
deleted file mode 100644
index b1b595220f1bd..0000000000000
--- a/Documentation/devicetree/bindings/pinctrl/fsl,imx6sx-pinctrl.txt
+++ /dev/null
@@ -1,36 +0,0 @@
-* Freescale i.MX6 SoloX IOMUX Controller
-
-Please refer to fsl,imx-pinctrl.txt in this directory for common binding part
-and usage.
-
-Required properties:
-- compatible: "fsl,imx6sx-iomuxc"
-- fsl,pins: each entry consists of 6 integers and represents the mux and config
-  setting for one pin.  The first 5 integers <mux_reg conf_reg input_reg mux_val
-  input_val> are specified using a PIN_FUNC_ID macro, which can be found in
-  imx6sx-pinfunc.h under device tree source folder.  The last integer CONFIG is
-  the pad setting value like pull-up on this pin.  Please refer to i.MX6 SoloX
-  Reference Manual for detailed CONFIG settings.
-
-CONFIG bits definition:
-PAD_CTL_HYS                     (1 << 16)
-PAD_CTL_PUS_100K_DOWN           (0 << 14)
-PAD_CTL_PUS_47K_UP              (1 << 14)
-PAD_CTL_PUS_100K_UP             (2 << 14)
-PAD_CTL_PUS_22K_UP              (3 << 14)
-PAD_CTL_PUE                     (1 << 13)
-PAD_CTL_PKE                     (1 << 12)
-PAD_CTL_ODE                     (1 << 11)
-PAD_CTL_SPEED_LOW               (0 << 6)
-PAD_CTL_SPEED_MED               (1 << 6)
-PAD_CTL_SPEED_HIGH              (3 << 6)
-PAD_CTL_DSE_DISABLE             (0 << 3)
-PAD_CTL_DSE_260ohm              (1 << 3)
-PAD_CTL_DSE_130ohm              (2 << 3)
-PAD_CTL_DSE_87ohm               (3 << 3)
-PAD_CTL_DSE_65ohm               (4 << 3)
-PAD_CTL_DSE_52ohm               (5 << 3)
-PAD_CTL_DSE_43ohm               (6 << 3)
-PAD_CTL_DSE_37ohm               (7 << 3)
-PAD_CTL_SRE_FAST                (1 << 0)
-PAD_CTL_SRE_SLOW                (0 << 0)

From 5a3e85c3c397c781393ea5fb2f45b1f60f8a4e6e Mon Sep 17 00:00:00 2001
From: Mukesh Ojha <quic_mojha@quicinc.com>
Date: Tue, 15 Oct 2024 00:59:30 +0530
Subject: [PATCH 0607/1530] pinmux: Use sequential access to access
 desc->pinmux data

When two client of the same gpio call pinctrl_select_state() for the
same functionality, we are seeing NULL pointer issue while accessing
desc->mux_owner.

Let's say two processes A, B executing in pin_request() for the same pin
and process A updates the desc->mux_usecount but not yet updated the
desc->mux_owner while process B see the desc->mux_usecount which got
updated by A path and further executes strcmp and while accessing
desc->mux_owner it crashes with NULL pointer.

Serialize the access to mux related setting with a mutex lock.

	cpu0 (process A)			cpu1(process B)

pinctrl_select_state() {		  pinctrl_select_state() {
  pin_request() {				pin_request() {
  ...
						 ....
    } else {
         desc->mux_usecount++;
    						desc->mux_usecount && strcmp(desc->mux_owner, owner)) {

         if (desc->mux_usecount > 1)
               return 0;
         desc->mux_owner = owner;

  }						}

Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com>
Link: https://lore.kernel.org/20241014192930.1539673-1-quic_mojha@quicinc.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/core.c   |   3 +
 drivers/pinctrl/core.h   |   1 +
 drivers/pinctrl/pinmux.c | 173 ++++++++++++++++++++++-----------------
 3 files changed, 100 insertions(+), 77 deletions(-)

diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 4061890a17483..b3eec63c00ba0 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -220,6 +220,9 @@ static int pinctrl_register_one_pin(struct pinctrl_dev *pctldev,
 
 	/* Set owner */
 	pindesc->pctldev = pctldev;
+#ifdef CONFIG_PINMUX
+	mutex_init(&pindesc->mux_lock);
+#endif
 
 	/* Copy basic pin info */
 	if (pin->name) {
diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h
index 4e07707d2435b..d6c24978e7081 100644
--- a/drivers/pinctrl/core.h
+++ b/drivers/pinctrl/core.h
@@ -177,6 +177,7 @@ struct pin_desc {
 	const char *mux_owner;
 	const struct pinctrl_setting_mux *mux_setting;
 	const char *gpio_owner;
+	struct mutex mux_lock;
 #endif
 };
 
diff --git a/drivers/pinctrl/pinmux.c b/drivers/pinctrl/pinmux.c
index 02033ea1c6438..0743190da59e8 100644
--- a/drivers/pinctrl/pinmux.c
+++ b/drivers/pinctrl/pinmux.c
@@ -14,6 +14,7 @@
 
 #include <linux/array_size.h>
 #include <linux/ctype.h>
+#include <linux/cleanup.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/err.h>
@@ -93,6 +94,7 @@ bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned int pin)
 	if (!desc || !ops)
 		return true;
 
+	guard(mutex)(&desc->mux_lock);
 	if (ops->strict && desc->mux_usecount)
 		return false;
 
@@ -127,29 +129,31 @@ static int pin_request(struct pinctrl_dev *pctldev,
 	dev_dbg(pctldev->dev, "request pin %d (%s) for %s\n",
 		pin, desc->name, owner);
 
-	if ((!gpio_range || ops->strict) &&
-	    desc->mux_usecount && strcmp(desc->mux_owner, owner)) {
-		dev_err(pctldev->dev,
-			"pin %s already requested by %s; cannot claim for %s\n",
-			desc->name, desc->mux_owner, owner);
-		goto out;
-	}
+	scoped_guard(mutex, &desc->mux_lock) {
+		if ((!gpio_range || ops->strict) &&
+		    desc->mux_usecount && strcmp(desc->mux_owner, owner)) {
+			dev_err(pctldev->dev,
+				"pin %s already requested by %s; cannot claim for %s\n",
+				desc->name, desc->mux_owner, owner);
+			goto out;
+		}
 
-	if ((gpio_range || ops->strict) && desc->gpio_owner) {
-		dev_err(pctldev->dev,
-			"pin %s already requested by %s; cannot claim for %s\n",
-			desc->name, desc->gpio_owner, owner);
-		goto out;
-	}
+		if ((gpio_range || ops->strict) && desc->gpio_owner) {
+			dev_err(pctldev->dev,
+				"pin %s already requested by %s; cannot claim for %s\n",
+				desc->name, desc->gpio_owner, owner);
+			goto out;
+		}
 
-	if (gpio_range) {
-		desc->gpio_owner = owner;
-	} else {
-		desc->mux_usecount++;
-		if (desc->mux_usecount > 1)
-			return 0;
+		if (gpio_range) {
+			desc->gpio_owner = owner;
+		} else {
+			desc->mux_usecount++;
+			if (desc->mux_usecount > 1)
+				return 0;
 
-		desc->mux_owner = owner;
+			desc->mux_owner = owner;
+		}
 	}
 
 	/* Let each pin increase references to this module */
@@ -178,12 +182,14 @@ static int pin_request(struct pinctrl_dev *pctldev,
 
 out_free_pin:
 	if (status) {
-		if (gpio_range) {
-			desc->gpio_owner = NULL;
-		} else {
-			desc->mux_usecount--;
-			if (!desc->mux_usecount)
-				desc->mux_owner = NULL;
+		scoped_guard(mutex, &desc->mux_lock) {
+			if (gpio_range) {
+				desc->gpio_owner = NULL;
+			} else {
+				desc->mux_usecount--;
+				if (!desc->mux_usecount)
+					desc->mux_owner = NULL;
+			}
 		}
 	}
 out:
@@ -219,15 +225,17 @@ static const char *pin_free(struct pinctrl_dev *pctldev, int pin,
 		return NULL;
 	}
 
-	if (!gpio_range) {
-		/*
-		 * A pin should not be freed more times than allocated.
-		 */
-		if (WARN_ON(!desc->mux_usecount))
-			return NULL;
-		desc->mux_usecount--;
-		if (desc->mux_usecount)
-			return NULL;
+	scoped_guard(mutex, &desc->mux_lock) {
+		if (!gpio_range) {
+			/*
+			 * A pin should not be freed more times than allocated.
+			 */
+			if (WARN_ON(!desc->mux_usecount))
+				return NULL;
+			desc->mux_usecount--;
+			if (desc->mux_usecount)
+				return NULL;
+		}
 	}
 
 	/*
@@ -239,13 +247,15 @@ static const char *pin_free(struct pinctrl_dev *pctldev, int pin,
 	else if (ops->free)
 		ops->free(pctldev, pin);
 
-	if (gpio_range) {
-		owner = desc->gpio_owner;
-		desc->gpio_owner = NULL;
-	} else {
-		owner = desc->mux_owner;
-		desc->mux_owner = NULL;
-		desc->mux_setting = NULL;
+	scoped_guard(mutex, &desc->mux_lock) {
+		if (gpio_range) {
+			owner = desc->gpio_owner;
+			desc->gpio_owner = NULL;
+		} else {
+			owner = desc->mux_owner;
+			desc->mux_owner = NULL;
+			desc->mux_setting = NULL;
+		}
 	}
 
 	module_put(pctldev->owner);
@@ -458,7 +468,8 @@ int pinmux_enable_setting(const struct pinctrl_setting *setting)
 				 pins[i]);
 			continue;
 		}
-		desc->mux_setting = &(setting->data.mux);
+		scoped_guard(mutex, &desc->mux_lock)
+			desc->mux_setting = &(setting->data.mux);
 	}
 
 	ret = ops->set_mux(pctldev, setting->data.mux.func,
@@ -472,8 +483,10 @@ int pinmux_enable_setting(const struct pinctrl_setting *setting)
 err_set_mux:
 	for (i = 0; i < num_pins; i++) {
 		desc = pin_desc_get(pctldev, pins[i]);
-		if (desc)
-			desc->mux_setting = NULL;
+		if (desc) {
+			scoped_guard(mutex, &desc->mux_lock)
+				desc->mux_setting = NULL;
+		}
 	}
 err_pin_request:
 	/* On error release all taken pins */
@@ -492,6 +505,7 @@ void pinmux_disable_setting(const struct pinctrl_setting *setting)
 	unsigned int num_pins = 0;
 	int i;
 	struct pin_desc *desc;
+	bool is_equal;
 
 	if (pctlops->get_group_pins)
 		ret = pctlops->get_group_pins(pctldev, setting->data.mux.group,
@@ -517,7 +531,10 @@ void pinmux_disable_setting(const struct pinctrl_setting *setting)
 				 pins[i]);
 			continue;
 		}
-		if (desc->mux_setting == &(setting->data.mux)) {
+		scoped_guard(mutex, &desc->mux_lock)
+			is_equal = (desc->mux_setting == &(setting->data.mux));
+
+		if (is_equal) {
 			pin_free(pctldev, pins[i], NULL);
 		} else {
 			const char *gname;
@@ -608,40 +625,42 @@ static int pinmux_pins_show(struct seq_file *s, void *what)
 		if (desc == NULL)
 			continue;
 
-		if (desc->mux_owner &&
-		    !strcmp(desc->mux_owner, pinctrl_dev_get_name(pctldev)))
-			is_hog = true;
-
-		if (pmxops->strict) {
-			if (desc->mux_owner)
-				seq_printf(s, "pin %d (%s): device %s%s",
-					   pin, desc->name, desc->mux_owner,
+		scoped_guard(mutex, &desc->mux_lock) {
+			if (desc->mux_owner &&
+			    !strcmp(desc->mux_owner, pinctrl_dev_get_name(pctldev)))
+				is_hog = true;
+
+			if (pmxops->strict) {
+				if (desc->mux_owner)
+					seq_printf(s, "pin %d (%s): device %s%s",
+						   pin, desc->name, desc->mux_owner,
+						   is_hog ? " (HOG)" : "");
+				else if (desc->gpio_owner)
+					seq_printf(s, "pin %d (%s): GPIO %s",
+						   pin, desc->name, desc->gpio_owner);
+				else
+					seq_printf(s, "pin %d (%s): UNCLAIMED",
+						   pin, desc->name);
+			} else {
+				/* For non-strict controllers */
+				seq_printf(s, "pin %d (%s): %s %s%s", pin, desc->name,
+					   desc->mux_owner ? desc->mux_owner
+					   : "(MUX UNCLAIMED)",
+					   desc->gpio_owner ? desc->gpio_owner
+					   : "(GPIO UNCLAIMED)",
 					   is_hog ? " (HOG)" : "");
-			else if (desc->gpio_owner)
-				seq_printf(s, "pin %d (%s): GPIO %s",
-					   pin, desc->name, desc->gpio_owner);
+			}
+
+			/* If mux: print function+group claiming the pin */
+			if (desc->mux_setting)
+				seq_printf(s, " function %s group %s\n",
+					   pmxops->get_function_name(pctldev,
+						desc->mux_setting->func),
+					   pctlops->get_group_name(pctldev,
+						desc->mux_setting->group));
 			else
-				seq_printf(s, "pin %d (%s): UNCLAIMED",
-					   pin, desc->name);
-		} else {
-			/* For non-strict controllers */
-			seq_printf(s, "pin %d (%s): %s %s%s", pin, desc->name,
-				   desc->mux_owner ? desc->mux_owner
-				   : "(MUX UNCLAIMED)",
-				   desc->gpio_owner ? desc->gpio_owner
-				   : "(GPIO UNCLAIMED)",
-				   is_hog ? " (HOG)" : "");
+				seq_putc(s, '\n');
 		}
-
-		/* If mux: print function+group claiming the pin */
-		if (desc->mux_setting)
-			seq_printf(s, " function %s group %s\n",
-				   pmxops->get_function_name(pctldev,
-					desc->mux_setting->func),
-				   pctlops->get_group_name(pctldev,
-					desc->mux_setting->group));
-		else
-			seq_putc(s, '\n');
 	}
 
 	mutex_unlock(&pctldev->mutex);

From fad610b987132868e3410c530871086552ce6155 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 18 Oct 2024 17:47:47 +0300
Subject: [PATCH 0608/1530] Documentation PCI: Reformat RMW ops documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extract the list of RMW protected PCIe Capability registers into a
bullet list to make them easier to pick up on a glance. An upcoming
change is going to add one more register among them so it will be much
cleaner to have them as bullets.

Link: https://lore.kernel.org/r/20241018144755.7875-2-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Lukas Wunner <lukas@wunner.de>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/PCI/pciebus-howto.rst | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/Documentation/PCI/pciebus-howto.rst b/Documentation/PCI/pciebus-howto.rst
index f344452651e1f..e48d01422efc2 100644
--- a/Documentation/PCI/pciebus-howto.rst
+++ b/Documentation/PCI/pciebus-howto.rst
@@ -217,8 +217,11 @@ capability structure except the PCI Express capability structure,
 that is shared between many drivers including the service drivers.
 RMW Capability accessors (pcie_capability_clear_and_set_word(),
 pcie_capability_set_word(), and pcie_capability_clear_word()) protect
-a selected set of PCI Express Capability Registers (Link Control
-Register and Root Control Register). Any change to those registers
-should be performed using RMW accessors to avoid problems due to
-concurrent updates. For the up-to-date list of protected registers,
-see pcie_capability_clear_and_set_word().
+a selected set of PCI Express Capability Registers:
+
+* Link Control Register
+* Root Control Register
+
+Any change to those registers should be performed using RMW accessors to
+avoid problems due to concurrent updates. For the up-to-date list of
+protected registers, see pcie_capability_clear_and_set_word().

From 04af8a399fa40310f831b4f1dc9f757085f41983 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 18 Oct 2024 17:47:48 +0300
Subject: [PATCH 0609/1530] PCI: Protect Link Control 2 Register with RMW
 locking
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PCIe Bandwidth Controller performs RMW accesses the Link Control 2
Register which can occur concurrently to other sources of Link Control 2
Register writes. Therefore, add Link Control 2 Register among the PCI
Express Capability Registers that need RMW locking.

Link: https://lore.kernel.org/r/20241018144755.7875-3-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Lukas Wunner <lukas@wunner.de>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/PCI/pciebus-howto.rst | 1 +
 include/linux/pci.h                 | 1 +
 2 files changed, 2 insertions(+)

diff --git a/Documentation/PCI/pciebus-howto.rst b/Documentation/PCI/pciebus-howto.rst
index e48d01422efc2..375d9ce171f62 100644
--- a/Documentation/PCI/pciebus-howto.rst
+++ b/Documentation/PCI/pciebus-howto.rst
@@ -221,6 +221,7 @@ a selected set of PCI Express Capability Registers:
 
 * Link Control Register
 * Root Control Register
+* Link Control 2 Register
 
 Any change to those registers should be performed using RMW accessors to
 avoid problems due to concurrent updates. For the up-to-date list of
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 573b4c4c2be61..be5ed534c39cf 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1274,6 +1274,7 @@ static inline int pcie_capability_clear_and_set_word(struct pci_dev *dev,
 {
 	switch (pos) {
 	case PCI_EXP_LNKCTL:
+	case PCI_EXP_LNKCTL2:
 	case PCI_EXP_RTCTL:
 		return pcie_capability_clear_and_set_word_locked(dev, pos,
 								 clear, set);

From b4e0e9a1e30059f4523c9b6a1f8045ad89b5db8a Mon Sep 17 00:00:00 2001
From: Li Huafei <lihuafei1@huawei.com>
Date: Sat, 19 Oct 2024 23:41:55 +0800
Subject: [PATCH 0610/1530] perf disasm: Use disasm_line__free() to properly
 free disasm_line

The structure disasm_line contains members that require dynamically
allocated memory and need to be freed correctly using
disasm_line__free().

This patch fixes the incorrect release in
symbol__disassemble_capstone().

Fixes: 6d17edc113de ("perf annotate: Use libcapstone to disassemble")
Signed-off-by: Li Huafei <lihuafei1@huawei.com>
Tested-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: sesse@google.com
Cc: kjain@linux.ibm.com
Link: https://lore.kernel.org/r/20241019154157.282038-1-lihuafei1@huawei.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/disasm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index aef06a36bf40a..053b1f9ccc71e 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -1720,7 +1720,7 @@ static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
 		 */
 		list_for_each_entry_safe(dl, tmp, &notes->src->source, al.node) {
 			list_del(&dl->al.node);
-			free(dl);
+			disasm_line__free(dl);
 		}
 	}
 	count = -1;

From 908d50e50ef91713ae94bc8988db87def6b6fec3 Mon Sep 17 00:00:00 2001
From: Li Huafei <lihuafei1@huawei.com>
Date: Sat, 19 Oct 2024 23:41:56 +0800
Subject: [PATCH 0611/1530] perf disasm: Use disasm_line__free() to properly
 free disasm_line

symbol__disassemble_capstone_powerpc() goto the 'err' label when it
failed in the loop that created disasm_line, and then used free()
directly to free disasm_line. Since the structure disasm_line contains
members that allocate memory dynamically, this can result in a memory
leak. In fact, we can simply break the loop when it fails in the middle
of the loop, and disasm_line__free() will then be called to properly
free the created line. Other error paths do not need to consider freeing
disasm_line.

Fixes: c5d60de1813a ("perf annotate: Add support to use libcapstone in powerpc")
Signed-off-by: Li Huafei <lihuafei1@huawei.com>
Tested-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: sesse@google.com
Cc: kjain@linux.ibm.com
Link: https://lore.kernel.org/r/20241019154157.282038-2-lihuafei1@huawei.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/disasm.c | 14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index 053b1f9ccc71e..5fdd5afc5c2fa 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -1573,7 +1573,7 @@ static int symbol__disassemble_capstone_powerpc(char *filename, struct symbol *s
 
 		dl = disasm_line__new(args);
 		if (dl == NULL)
-			goto err;
+			break;
 
 		annotation_line__add(&dl->al, &notes->src->source);
 
@@ -1603,18 +1603,6 @@ static int symbol__disassemble_capstone_powerpc(char *filename, struct symbol *s
 err:
 	if (fd >= 0)
 		close(fd);
-	if (needs_cs_close) {
-		struct disasm_line *tmp;
-
-		/*
-		 * It probably failed in the middle of the above loop.
-		 * Release any resources it might add.
-		 */
-		list_for_each_entry_safe(dl, tmp, &notes->src->source, al.node) {
-			list_del(&dl->al.node);
-			free(dl);
-		}
-	}
 	count = -1;
 	goto out;
 }

From 150dab31d5609f896fbfaa06b442ca314da79858 Mon Sep 17 00:00:00 2001
From: Li Huafei <lihuafei1@huawei.com>
Date: Sat, 19 Oct 2024 23:41:57 +0800
Subject: [PATCH 0612/1530] perf disasm: Fix not cleaning up disasm_line in
 symbol__disassemble_raw()

In symbol__disassemble_raw(), the created disasm_line should be
discarded before returning an error. When creating disasm_line fails,
break the loop and then release the created lines.

Fixes: 0b971e6bf1c3 ("perf annotate: Add support to capture and parse raw instruction in powerpc using dso__data_read_offset utility")
Signed-off-by: Li Huafei <lihuafei1@huawei.com>
Tested-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: sesse@google.com
Cc: kjain@linux.ibm.com
Link: https://lore.kernel.org/r/20241019154157.282038-3-lihuafei1@huawei.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/disasm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index 5fdd5afc5c2fa..bd98fec903f73 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -1773,7 +1773,7 @@ static int symbol__disassemble_raw(char *filename, struct symbol *sym,
 		sprintf(args->line, "%x", line[i]);
 		dl = disasm_line__new(args);
 		if (dl == NULL)
-			goto err;
+			break;
 
 		annotation_line__add(&dl->al, &notes->src->source);
 		offset += 4;

From 718c4069896cabba5c39b637cbb7205927f16ae0 Mon Sep 17 00:00:00 2001
From: Dirk Behme <dirk.behme@de.bosch.com>
Date: Wed, 2 Oct 2024 07:03:01 +0200
Subject: [PATCH 0613/1530] rust: types: extend `Opaque` documentation

Update the `Opaque` documentation and add an example as proposed by
Miguel Ojeda in [1]. The documentation update is mainly taken from
Benno Lossin's description [2].

Cc: Nell Shamrell-Harrington <nells@linux.microsoft.com>
Suggested-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://rust-for-linux.zulipchat.com/#narrow/stream/291565/topic/x/near/467478085 [1]
Link: https://rust-for-linux.zulipchat.com/#narrow/stream/291565/topic/x/near/470498289 [2]
Co-developed-by: Benno Lossin <benno.lossin@proton.me>
Signed-off-by: Benno Lossin <benno.lossin@proton.me>
Signed-off-by: Dirk Behme <dirk.behme@de.bosch.com>
Link: https://lore.kernel.org/r/20241002050301.1927545-1-dirk.behme@de.bosch.com
[ Used `expect`. Rewrapped docs. Added intra-doc link. Formatted
  example. Reworded to fix tag typo/order. Fixed `&mut` formatting
  as discussed. Added Benno's SOB and CDB as discussed. Shortened
  links. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/types.rs | 53 +++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 52 insertions(+), 1 deletion(-)

diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index ced143600eb1b..fae80814fa1c5 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -206,7 +206,58 @@ impl<T, F: FnOnce(T)> Drop for ScopeGuard<T, F> {
 
 /// Stores an opaque value.
 ///
-/// This is meant to be used with FFI objects that are never interpreted by Rust code.
+/// `Opaque<T>` is meant to be used with FFI objects that are never interpreted by Rust code.
+///
+/// It is used to wrap structs from the C side, like for example `Opaque<bindings::mutex>`.
+/// It gets rid of all the usual assumptions that Rust has for a value:
+///
+/// * The value is allowed to be uninitialized (for example have invalid bit patterns: `3` for a
+///   [`bool`]).
+/// * The value is allowed to be mutated, when a `&Opaque<T>` exists on the Rust side.
+/// * No uniqueness for mutable references: it is fine to have multiple `&mut Opaque<T>` point to
+///   the same value.
+/// * The value is not allowed to be shared with other threads (i.e. it is `!Sync`).
+///
+/// This has to be used for all values that the C side has access to, because it can't be ensured
+/// that the C side is adhering to the usual constraints that Rust needs.
+///
+/// Using `Opaque<T>` allows to continue to use references on the Rust side even for values shared
+/// with C.
+///
+/// # Examples
+///
+/// ```
+/// # #![expect(unreachable_pub, clippy::disallowed_names)]
+/// use kernel::types::Opaque;
+/// # // Emulate a C struct binding which is from C, maybe uninitialized or not, only the C side
+/// # // knows.
+/// # mod bindings {
+/// #     pub struct Foo {
+/// #         pub val: u8,
+/// #     }
+/// # }
+///
+/// // `foo.val` is assumed to be handled on the C side, so we use `Opaque` to wrap it.
+/// pub struct Foo {
+///     foo: Opaque<bindings::Foo>,
+/// }
+///
+/// impl Foo {
+///     pub fn get_val(&self) -> u8 {
+///         let ptr = Opaque::get(&self.foo);
+///
+///         // SAFETY: `Self` is valid from C side.
+///         unsafe { (*ptr).val }
+///     }
+/// }
+///
+/// // Create an instance of `Foo` with the `Opaque` wrapper.
+/// let foo = Foo {
+///     foo: Opaque::new(bindings::Foo { val: 0xdb }),
+/// };
+///
+/// assert_eq!(foo.get_val(), 0xdb);
+/// ```
 #[repr(transparent)]
 pub struct Opaque<T> {
     value: UnsafeCell<MaybeUninit<T>>,

From 84b4a51fce4ccc6605113ed8af41a3d91609a756 Mon Sep 17 00:00:00 2001
From: Luis Chamberlain <mcgrof@kernel.org>
Date: Mon, 21 Oct 2024 12:11:44 -0700
Subject: [PATCH 0614/1530] selftests: add new kallsyms selftests

We lack find_symbol() selftests, so add one. This let's us stress test
improvements easily on find_symbol() or optimizations. It also inherently
allows us to test the limits of kallsyms on Linux today.

We test a pathalogical use case for kallsyms by introducing modules
which are automatically written for us with a larger number of symbols.
We have 4 kallsyms test modules:

A: has KALLSYSMS_NUMSYMS exported symbols
B: uses one of A's symbols
C: adds KALLSYMS_SCALE_FACTOR * KALLSYSMS_NUMSYMS exported
D: adds 2 * the symbols than C

By using anything much larger than KALLSYSMS_NUMSYMS as 10,000 and
KALLSYMS_SCALE_FACTOR of 8 we segfault today. So we're capped at
around 160000 symbols somehow today. We can inpsect that issue at
our leasure later, but for now the real value to this test is that
this will easily allow us to test improvements on find_symbol().

We want to enable this test on allyesmodconfig builds so we can't
use this combination, so instead just use a safe value for now and
be informative on the Kconfig symbol documentation about where our
thresholds are for testers. We default then to KALLSYSMS_NUMSYMS of
just 100 and KALLSYMS_SCALE_FACTOR of 8.

On x86_64 we can use perf, for other architectures we just use 'time'
and allow for customizations. For example a future enhancements could
be done for parisc to check for unaligned accesses which triggers a
special special exception handler assembler code inside the kernel.
The negative impact on performance is so large on parisc that it
keeps track of its accesses on /proc/cpuinfo as UAH:

IRQ:       CPU0       CPU1
3:       1332          0         SuperIO  ttyS0
7:    1270013          0         SuperIO  pata_ns87415
64:  320023012  320021431             CPU  timer
65:   17080507   20624423             CPU  IPI
UAH:   10948640      58104   Unaligned access handler traps

While at it, this tidies up lib/ test modules to allow us to have
a new directory for them. The amount of test modules under lib/
is insane.

This should also hopefully showcase how to start doing basic
self module writing code, which may be more useful for more complex
cases later in the future.

Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 lib/Kconfig.debug                             | 105 ++++++++++++++
 lib/Makefile                                  |   1 +
 lib/tests/Makefile                            |   1 +
 lib/tests/module/.gitignore                   |   4 +
 lib/tests/module/Makefile                     |  15 ++
 lib/tests/module/gen_test_kallsyms.sh         | 128 ++++++++++++++++++
 tools/testing/selftests/module/Makefile       |  12 ++
 tools/testing/selftests/module/config         |   3 +
 tools/testing/selftests/module/find_symbol.sh |  81 +++++++++++
 9 files changed, 350 insertions(+)
 create mode 100644 lib/tests/Makefile
 create mode 100644 lib/tests/module/.gitignore
 create mode 100644 lib/tests/module/Makefile
 create mode 100755 lib/tests/module/gen_test_kallsyms.sh
 create mode 100644 tools/testing/selftests/module/Makefile
 create mode 100644 tools/testing/selftests/module/config
 create mode 100755 tools/testing/selftests/module/find_symbol.sh

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 7315f643817ae..b5929721fc639 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2903,6 +2903,111 @@ config TEST_KMOD
 
 	  If unsure, say N.
 
+config TEST_RUNTIME
+	bool
+
+config TEST_RUNTIME_MODULE
+	bool
+
+config TEST_KALLSYMS
+	tristate "module kallsyms find_symbol() test"
+	depends on m
+	select TEST_RUNTIME
+	select TEST_RUNTIME_MODULE
+	select TEST_KALLSYMS_A
+	select TEST_KALLSYMS_B
+	select TEST_KALLSYMS_C
+	select TEST_KALLSYMS_D
+	help
+	  This allows us to stress test find_symbol() through the kallsyms
+	  used to place symbols on the kernel ELF kallsyms and modules kallsyms
+	  where we place kernel symbols such as exported symbols.
+
+	  We have four test modules:
+
+	  A: has KALLSYSMS_NUMSYMS exported symbols
+	  B: uses one of A's symbols
+	  C: adds KALLSYMS_SCALE_FACTOR * KALLSYSMS_NUMSYMS exported
+	  D: adds 2 * the symbols than C
+
+	  We stress test find_symbol() through two means:
+
+	  1) Upon load of B it will trigger simplify_symbols() to look for the
+	  one symbol it uses from the module A with tons of symbols. This is an
+	  indirect way for us to have B call resolve_symbol_wait() upon module
+	  load. This will eventually call find_symbol() which will eventually
+	  try to find the symbols used with find_exported_symbol_in_section().
+	  find_exported_symbol_in_section() uses bsearch() so a binary search
+	  for each symbol. Binary search will at worst be O(log(n)) so the
+	  larger TEST_MODULE_KALLSYSMS the worse the search.
+
+	  2) The selftests should load C first, before B. Upon B's load towards
+	  the end right before we call module B's init routine we get
+	  complete_formation() called on the module. That will first check
+	  for duplicate symbols with the call to verify_exported_symbols().
+	  That is when we'll force iteration on module C's insane symbol list.
+	  Since it has 10 * KALLSYMS_NUMSYMS it means we can first test
+	  just loading B without C. The amount of time it takes to load C Vs
+	  B can give us an idea of the impact growth of the symbol space and
+	  give us projection. Module A only uses one symbol from B so to allow
+	  this scaling in module C to be proportional, if it used more symbols
+	  then the first test would be doing more and increasing just the
+	  search space would be slightly different. The last module, module D
+	  will just increase the search space by twice the number of symbols in
+	  C so to allow for full projects.
+
+	  tools/testing/selftests/module/find_symbol.sh
+
+	  The current defaults will incur a build delay of about 7 minutes
+	  on an x86_64 with only 8 cores. Enable this only if you want to
+	  stress test find_symbol() with thousands of symbols. At the same
+	  time this is also useful to test building modules with thousands of
+	  symbols, and if BTF is enabled this also stress tests adding BTF
+	  information for each module. Currently enabling many more symbols
+	  will segfault the build system.
+
+	  If unsure, say N.
+
+if TEST_KALLSYMS
+
+config TEST_KALLSYMS_A
+	tristate
+	depends on m
+
+config TEST_KALLSYMS_B
+	tristate
+	depends on m
+
+config TEST_KALLSYMS_C
+	tristate
+	depends on m
+
+config TEST_KALLSYMS_D
+	tristate
+	depends on m
+
+config TEST_KALLSYMS_NUMSYMS
+	int "test kallsyms number of symbols"
+	default 100
+	help
+	  The number of symbols to create on TEST_KALLSYMS_A, only one of which
+	  module TEST_KALLSYMS_B will use. This also will be used
+	  for how many symbols TEST_KALLSYMS_C will have, scaled up by
+	  TEST_KALLSYMS_SCALE_FACTOR. Note that setting this to 10,000 will
+	  trigger a segfault today, don't use anything close to it unless
+	  you are aware that this should not be used for automated build tests.
+
+config TEST_KALLSYMS_SCALE_FACTOR
+	int "test kallsyms scale factor"
+	default 8
+	help
+	  How many more unusued symbols will TEST_KALLSYSMS_C have than
+	  TEST_KALLSYMS_A. If 8, then module C will have 8 * syms
+	  than module A. Then TEST_KALLSYMS_D will have double the amount
+	  of symbols than C so to allow projections.
+
+endif # TEST_KALLSYMS
+
 config TEST_DEBUG_VIRTUAL
 	tristate "Test CONFIG_DEBUG_VIRTUAL feature"
 	depends on DEBUG_VIRTUAL
diff --git a/lib/Makefile b/lib/Makefile
index 773adf88af416..ae720c7eb996b 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -96,6 +96,7 @@ obj-$(CONFIG_TEST_XARRAY) += test_xarray.o
 obj-$(CONFIG_TEST_MAPLE_TREE) += test_maple_tree.o
 obj-$(CONFIG_TEST_PARMAN) += test_parman.o
 obj-$(CONFIG_TEST_KMOD) += test_kmod.o
+obj-$(CONFIG_TEST_RUNTIME) += tests/
 obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o
 obj-$(CONFIG_TEST_MEMCAT_P) += test_memcat_p.o
 obj-$(CONFIG_TEST_OBJAGG) += test_objagg.o
diff --git a/lib/tests/Makefile b/lib/tests/Makefile
new file mode 100644
index 0000000000000..8e4f42cb9c54f
--- /dev/null
+++ b/lib/tests/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_TEST_RUNTIME_MODULE)		+= module/
diff --git a/lib/tests/module/.gitignore b/lib/tests/module/.gitignore
new file mode 100644
index 0000000000000..8be7891b250fe
--- /dev/null
+++ b/lib/tests/module/.gitignore
@@ -0,0 +1,4 @@
+test_kallsyms_a.c
+test_kallsyms_b.c
+test_kallsyms_c.c
+test_kallsyms_d.c
diff --git a/lib/tests/module/Makefile b/lib/tests/module/Makefile
new file mode 100644
index 0000000000000..af5c27b996cb1
--- /dev/null
+++ b/lib/tests/module/Makefile
@@ -0,0 +1,15 @@
+obj-$(CONFIG_TEST_KALLSYMS_A) += test_kallsyms_a.o
+obj-$(CONFIG_TEST_KALLSYMS_B) += test_kallsyms_b.o
+obj-$(CONFIG_TEST_KALLSYMS_C) += test_kallsyms_c.o
+obj-$(CONFIG_TEST_KALLSYMS_D) += test_kallsyms_d.o
+
+$(obj)/%.c: FORCE
+	@$(kecho) "  GEN     $@"
+	$(Q)$(srctree)/lib/tests/module/gen_test_kallsyms.sh $@\
+		$(CONFIG_TEST_KALLSYMS_NUMSYMS) \
+		$(CONFIG_TEST_KALLSYMS_SCALE_FACTOR)
+
+clean-files += test_kallsyms_a.c
+clean-files += test_kallsyms_b.c
+clean-files += test_kallsyms_c.c
+clean-files += test_kallsyms_d.c
diff --git a/lib/tests/module/gen_test_kallsyms.sh b/lib/tests/module/gen_test_kallsyms.sh
new file mode 100755
index 0000000000000..e85f10dc11bdf
--- /dev/null
+++ b/lib/tests/module/gen_test_kallsyms.sh
@@ -0,0 +1,128 @@
+#!/bin/bash
+
+TARGET=$(basename $1)
+DIR=lib/tests/module
+TARGET="$DIR/$TARGET"
+NUM_SYMS=$2
+SCALE_FACTOR=$3
+TEST_TYPE=$(echo $TARGET | sed -e 's|lib/tests/module/test_kallsyms_||g')
+TEST_TYPE=$(echo $TEST_TYPE | sed -e 's|.c||g')
+
+gen_template_module_header()
+{
+	cat <<____END_MODULE
+// SPDX-License-Identifier: GPL-2.0-or-later OR copyleft-next-0.3.1
+/*
+ * Copyright (C) 2023 Luis Chamberlain <mcgrof@kernel.org>
+ *
+ * Automatically generated code for testing, do not edit manually.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+
+____END_MODULE
+}
+
+gen_num_syms()
+{
+	PREFIX=$1
+	NUM=$2
+	for i in $(seq 1 $NUM); do
+		printf "int auto_test_%s_%010d = 0xff;\n" $PREFIX $i
+		printf "EXPORT_SYMBOL_GPL(auto_test_%s_%010d);\n" $PREFIX $i
+	done
+	echo
+}
+
+gen_template_module_data_a()
+{
+	gen_num_syms a $1
+	cat <<____END_MODULE
+static int auto_runtime_test(void)
+{
+	return 0;
+}
+
+____END_MODULE
+}
+
+gen_template_module_data_b()
+{
+	printf "\nextern int auto_test_a_%010d;\n\n" 28
+	echo "static int auto_runtime_test(void)"
+	echo "{"
+	printf "\nreturn auto_test_a_%010d;\n" 28
+	echo "}"
+}
+
+gen_template_module_data_c()
+{
+	gen_num_syms c $1
+	cat <<____END_MODULE
+static int auto_runtime_test(void)
+{
+	return 0;
+}
+
+____END_MODULE
+}
+
+gen_template_module_data_d()
+{
+	gen_num_syms d $1
+	cat <<____END_MODULE
+static int auto_runtime_test(void)
+{
+	return 0;
+}
+
+____END_MODULE
+}
+
+gen_template_module_exit()
+{
+	cat <<____END_MODULE
+static int __init auto_test_module_init(void)
+{
+	return auto_runtime_test();
+}
+module_init(auto_test_module_init);
+
+static void __exit auto_test_module_exit(void)
+{
+}
+module_exit(auto_test_module_exit);
+
+MODULE_AUTHOR("Luis Chamberlain <mcgrof@kernel.org>");
+MODULE_LICENSE("GPL");
+____END_MODULE
+}
+
+case $TEST_TYPE in
+	a)
+		gen_template_module_header > $TARGET
+		gen_template_module_data_a $NUM_SYMS >> $TARGET
+		gen_template_module_exit >> $TARGET
+		;;
+	b)
+		gen_template_module_header > $TARGET
+		gen_template_module_data_b >> $TARGET
+		gen_template_module_exit >> $TARGET
+		;;
+	c)
+		gen_template_module_header > $TARGET
+		gen_template_module_data_c $((NUM_SYMS * SCALE_FACTOR)) >> $TARGET
+		gen_template_module_exit >> $TARGET
+		;;
+	d)
+		gen_template_module_header > $TARGET
+		gen_template_module_data_d $((NUM_SYMS * SCALE_FACTOR * 2)) >> $TARGET
+		gen_template_module_exit >> $TARGET
+		;;
+	*)
+		;;
+esac
diff --git a/tools/testing/selftests/module/Makefile b/tools/testing/selftests/module/Makefile
new file mode 100644
index 0000000000000..6132d7ddb08b0
--- /dev/null
+++ b/tools/testing/selftests/module/Makefile
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Makefile for module loading selftests
+
+# No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
+all:
+
+TEST_PROGS := find_symbol.sh
+
+include ../lib.mk
+
+# Nothing to clean up.
+clean:
diff --git a/tools/testing/selftests/module/config b/tools/testing/selftests/module/config
new file mode 100644
index 0000000000000..b0c206b1ad47d
--- /dev/null
+++ b/tools/testing/selftests/module/config
@@ -0,0 +1,3 @@
+CONFIG_TEST_RUNTIME=y
+CONFIG_TEST_RUNTIME_MODULE=y
+CONFIG_TEST_KALLSYMS=m
diff --git a/tools/testing/selftests/module/find_symbol.sh b/tools/testing/selftests/module/find_symbol.sh
new file mode 100755
index 0000000000000..140364d3c49fc
--- /dev/null
+++ b/tools/testing/selftests/module/find_symbol.sh
@@ -0,0 +1,81 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-or-later OR copyleft-next-0.3.1
+# Copyright (C) 2023 Luis Chamberlain <mcgrof@kernel.org>
+#
+# This is a stress test script for kallsyms through find_symbol()
+
+set -e
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+test_reqs()
+{
+	if ! which modprobe 2> /dev/null > /dev/null; then
+		echo "$0: You need modprobe installed" >&2
+		exit $ksft_skip
+	fi
+
+	if ! which kmod 2> /dev/null > /dev/null; then
+		echo "$0: You need kmod installed" >&2
+		exit $ksft_skip
+	fi
+
+	if ! which perf 2> /dev/null > /dev/null; then
+		echo "$0: You need perf installed" >&2
+		exit $ksft_skip
+	fi
+
+	uid=$(id -u)
+	if [ $uid -ne 0 ]; then
+		echo $msg must be run as root >&2
+		exit $ksft_skip
+	fi
+}
+
+load_mod()
+{
+	local STATS="-e duration_time"
+	STATS="$STATS -e user_time"
+	STATS="$STATS -e system_time"
+	STATS="$STATS -e page-faults"
+	local MOD=$1
+
+	local ARCH="$(uname -m)"
+	case "${ARCH}" in
+	x86_64)
+		perf stat $STATS $MODPROBE test_kallsyms_b
+		;;
+	*)
+		time $MODPROBE test_kallsyms_b
+		exit 1
+		;;
+	esac
+}
+
+remove_all()
+{
+	$MODPROBE -r test_kallsyms_b
+	for i in a b c d; do
+		$MODPROBE -r test_kallsyms_$i
+	done
+}
+test_reqs
+
+MODPROBE=$(</proc/sys/kernel/modprobe)
+
+remove_all
+load_mod test_kallsyms_b
+remove_all
+
+# Now pollute the namespace
+$MODPROBE test_kallsyms_c
+load_mod test_kallsyms_b
+
+# Now pollute the namespace with twice the number of symbols than the last time
+remove_all
+$MODPROBE test_kallsyms_c
+$MODPROBE test_kallsyms_d
+load_mod test_kallsyms_b
+
+exit 0

From c6898d66fd198cd458734da40e414361f295de6a Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 16 Oct 2024 10:36:25 +0200
Subject: [PATCH 0615/1530] riscv: Check that vdso does not contain any dynamic
 relocations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Like other architectures, use the common cmd_vdso_check to make sure of
that.

Reviewed-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Vladimir Isaev <vladimir.isaev@syntacore.com>
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Guo Ren <guoren@kernel.org>
Link: https://lore.kernel.org/r/20241016083625.136311-3-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/vdso/Makefile | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 3f1c4b2d0b064..9a1b555e87331 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -45,7 +45,7 @@ $(obj)/vdso.o: $(obj)/vdso.so
 
 # link rule for the .so file, .lds has to be first
 $(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
-	$(call if_changed,vdsold)
+	$(call if_changed,vdsold_and_check)
 LDFLAGS_vdso.so.dbg = -shared -soname=linux-vdso.so.1 \
 	--build-id=sha1 --hash-style=both --eh-frame-hdr
 
@@ -65,7 +65,8 @@ include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
 # actual build commands
 # The DSO images are built using a special linker script
 # Make sure only to export the intended __vdso_xxx symbol offsets.
-quiet_cmd_vdsold = VDSOLD  $@
-      cmd_vdsold = $(LD) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \
+quiet_cmd_vdsold_and_check = VDSOLD  $@
+      cmd_vdsold_and_check = $(LD) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \
                    $(OBJCOPY) $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \
-                   rm $@.tmp
+                   rm $@.tmp && \
+                   $(cmd_vdso_check)

From 8727163a1ae304b5b4ac5952f593936ab9024d37 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 16 Oct 2024 13:27:42 -0700
Subject: [PATCH 0616/1530] dt-bindings: riscv: Add pointer masking ISA
 extensions

The RISC-V Pointer Masking specification defines three extensions:
Smmpm, Smnpm, and Ssnpm. Document the behavior of these extensions as
following the ratified version 1.0 of the specification.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20241016202814.4061541-2-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 .../devicetree/bindings/riscv/extensions.yaml  | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index 2cf2026cff574..28bf1daa1d276 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -128,6 +128,18 @@ properties:
             changes to interrupts as frozen at commit ccbddab ("Merge pull
             request #42 from riscv/jhauser-2023-RC4") of riscv-aia.
 
+        - const: smmpm
+          description: |
+            The standard Smmpm extension for M-mode pointer masking as
+            ratified at commit d70011dde6c2 ("Update to ratified state")
+            of riscv-j-extension.
+
+        - const: smnpm
+          description: |
+            The standard Smnpm extension for next-mode pointer masking as
+            ratified at commit d70011dde6c2 ("Update to ratified state")
+            of riscv-j-extension.
+
         - const: smstateen
           description: |
             The standard Smstateen extension for controlling access to CSRs
@@ -147,6 +159,12 @@ properties:
             and mode-based filtering as ratified at commit 01d1df0 ("Add ability
             to manually trigger workflow. (#2)") of riscv-count-overflow.
 
+        - const: ssnpm
+          description: |
+            The standard Ssnpm extension for next-mode pointer masking as
+            ratified at commit d70011dde6c2 ("Update to ratified state")
+            of riscv-j-extension.
+
         - const: sstc
           description: |
             The standard Sstc supervisor-level extension for time compare as

From 2e6f6ea452aa9fa9f150520fdecf6bda31954db4 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 16 Oct 2024 13:27:43 -0700
Subject: [PATCH 0617/1530] riscv: Add ISA extension parsing for pointer
 masking

The RISC-V Pointer Masking specification defines three extensions:
Smmpm, Smnpm, and Ssnpm. Add support for parsing each of them. The
specific extension which provides pointer masking support to userspace
(Supm) depends on the kernel's privilege mode, so provide a macro to
abstract this selection.

Smmpm implies the existence of the mseccfg CSR. As it is the only user
of this CSR so far, there is no need for an Xlinuxmseccfg extension.

Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20241016202814.4061541-3-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/hwcap.h | 5 +++++
 arch/riscv/kernel/cpufeature.c | 3 +++
 2 files changed, 8 insertions(+)

diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 46d9de54179ed..8608883da4539 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -93,6 +93,9 @@
 #define RISCV_ISA_EXT_ZCMOP		84
 #define RISCV_ISA_EXT_ZAWRS		85
 #define RISCV_ISA_EXT_SVVPTC		86
+#define RISCV_ISA_EXT_SMMPM		87
+#define RISCV_ISA_EXT_SMNPM		88
+#define RISCV_ISA_EXT_SSNPM		89
 
 #define RISCV_ISA_EXT_XLINUXENVCFG	127
 
@@ -101,8 +104,10 @@
 
 #ifdef CONFIG_RISCV_M_MODE
 #define RISCV_ISA_EXT_SxAIA		RISCV_ISA_EXT_SMAIA
+#define RISCV_ISA_EXT_SUPM		RISCV_ISA_EXT_SMNPM
 #else
 #define RISCV_ISA_EXT_SxAIA		RISCV_ISA_EXT_SSAIA
+#define RISCV_ISA_EXT_SUPM		RISCV_ISA_EXT_SSNPM
 #endif
 
 #endif /* _ASM_RISCV_HWCAP_H */
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index b3a057c36996f..94596bca464ee 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -377,9 +377,12 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_BUNDLE(zvksg, riscv_zvksg_bundled_exts),
 	__RISCV_ISA_EXT_DATA(zvkt, RISCV_ISA_EXT_ZVKT),
 	__RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA),
+	__RISCV_ISA_EXT_DATA(smmpm, RISCV_ISA_EXT_SMMPM),
+	__RISCV_ISA_EXT_SUPERSET(smnpm, RISCV_ISA_EXT_SMNPM, riscv_xlinuxenvcfg_exts),
 	__RISCV_ISA_EXT_DATA(smstateen, RISCV_ISA_EXT_SMSTATEEN),
 	__RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA),
 	__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
+	__RISCV_ISA_EXT_SUPERSET(ssnpm, RISCV_ISA_EXT_SSNPM, riscv_xlinuxenvcfg_exts),
 	__RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC),
 	__RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
 	__RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT),

From 29eedc7d1587f42f33ae209be45c89c424ee9c00 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 16 Oct 2024 13:27:44 -0700
Subject: [PATCH 0618/1530] riscv: Add CSR definitions for pointer masking

Pointer masking is controlled via a two-bit PMM field, which appears in
various CSRs depending on which extensions are implemented. Smmpm adds
the field to mseccfg; Smnpm adds the field to menvcfg; Ssnpm adds the
field to senvcfg. If the H extension is implemented, Ssnpm also defines
henvcfg.PMM and hstatus.HUPMM.

Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20241016202814.4061541-4-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/csr.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 25966995da04e..fe5d4eb9adea1 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -119,6 +119,10 @@
 
 /* HSTATUS flags */
 #ifdef CONFIG_64BIT
+#define HSTATUS_HUPMM		_AC(0x3000000000000, UL)
+#define HSTATUS_HUPMM_PMLEN_0	_AC(0x0000000000000, UL)
+#define HSTATUS_HUPMM_PMLEN_7	_AC(0x2000000000000, UL)
+#define HSTATUS_HUPMM_PMLEN_16	_AC(0x3000000000000, UL)
 #define HSTATUS_VSXL		_AC(0x300000000, UL)
 #define HSTATUS_VSXL_SHIFT	32
 #endif
@@ -195,6 +199,10 @@
 /* xENVCFG flags */
 #define ENVCFG_STCE			(_AC(1, ULL) << 63)
 #define ENVCFG_PBMTE			(_AC(1, ULL) << 62)
+#define ENVCFG_PMM			(_AC(0x3, ULL) << 32)
+#define ENVCFG_PMM_PMLEN_0		(_AC(0x0, ULL) << 32)
+#define ENVCFG_PMM_PMLEN_7		(_AC(0x2, ULL) << 32)
+#define ENVCFG_PMM_PMLEN_16		(_AC(0x3, ULL) << 32)
 #define ENVCFG_CBZE			(_AC(1, UL) << 7)
 #define ENVCFG_CBCFE			(_AC(1, UL) << 6)
 #define ENVCFG_CBIE_SHIFT		4
@@ -216,6 +224,12 @@
 #define SMSTATEEN0_SSTATEEN0_SHIFT	63
 #define SMSTATEEN0_SSTATEEN0		(_ULL(1) << SMSTATEEN0_SSTATEEN0_SHIFT)
 
+/* mseccfg bits */
+#define MSECCFG_PMM			ENVCFG_PMM
+#define MSECCFG_PMM_PMLEN_0		ENVCFG_PMM_PMLEN_0
+#define MSECCFG_PMM_PMLEN_7		ENVCFG_PMM_PMLEN_7
+#define MSECCFG_PMM_PMLEN_16		ENVCFG_PMM_PMLEN_16
+
 /* symbolic CSR names: */
 #define CSR_CYCLE		0xc00
 #define CSR_TIME		0xc01
@@ -382,6 +396,8 @@
 #define CSR_MIP			0x344
 #define CSR_PMPCFG0		0x3a0
 #define CSR_PMPADDR0		0x3b0
+#define CSR_MSECCFG		0x747
+#define CSR_MSECCFGH		0x757
 #define CSR_MVENDORID		0xf11
 #define CSR_MARCHID		0xf12
 #define CSR_MIMPID		0xf13

From 09d6775f503b393d0457c7126aa43208e1724004 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 16 Oct 2024 13:27:45 -0700
Subject: [PATCH 0619/1530] riscv: Add support for userspace pointer masking

RISC-V supports pointer masking with a variable number of tag bits
(which is called "PMLEN" in the specification) and which is configured
at the next higher privilege level.

Wire up the PR_SET_TAGGED_ADDR_CTRL and PR_GET_TAGGED_ADDR_CTRL prctls
so userspace can request a lower bound on the number of tag bits and
determine the actual number of tag bits. As with arm64's
PR_TAGGED_ADDR_ENABLE, the pointer masking configuration is
thread-scoped, inherited on clone() and fork() and cleared on execve().

Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Tested-by: Charlie Jenkins <charlie@rivosinc.com>
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20241016202814.4061541-5-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/uabi.rst  | 12 ++++
 arch/riscv/Kconfig                 | 11 ++++
 arch/riscv/include/asm/processor.h |  8 +++
 arch/riscv/include/asm/switch_to.h | 11 ++++
 arch/riscv/kernel/process.c        | 91 ++++++++++++++++++++++++++++++
 include/uapi/linux/prctl.h         |  5 +-
 6 files changed, 137 insertions(+), 1 deletion(-)

diff --git a/Documentation/arch/riscv/uabi.rst b/Documentation/arch/riscv/uabi.rst
index 2b420bab0527a..ddb8359a46ed5 100644
--- a/Documentation/arch/riscv/uabi.rst
+++ b/Documentation/arch/riscv/uabi.rst
@@ -68,3 +68,15 @@ Misaligned accesses
 Misaligned scalar accesses are supported in userspace, but they may perform
 poorly.  Misaligned vector accesses are only supported if the Zicclsm extension
 is supported.
+
+Pointer masking
+---------------
+
+Support for pointer masking in userspace (the Supm extension) is provided via
+the ``PR_SET_TAGGED_ADDR_CTRL`` and ``PR_GET_TAGGED_ADDR_CTRL`` ``prctl()``
+operations. Pointer masking is disabled by default. To enable it, userspace
+must call ``PR_SET_TAGGED_ADDR_CTRL`` with the ``PR_PMLEN`` field set to the
+number of mask/tag bits needed by the application. ``PR_PMLEN`` is interpreted
+as a lower bound; if the kernel is unable to satisfy the request, the
+``PR_SET_TAGGED_ADDR_CTRL`` operation will fail. The actual number of tag bits
+is returned in ``PR_PMLEN`` by the ``PR_GET_TAGGED_ADDR_CTRL`` operation.
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 22dc5ea4196ce..0ef449465378e 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -531,6 +531,17 @@ config RISCV_ISA_C
 
 	  If you don't know what to do here, say Y.
 
+config RISCV_ISA_SUPM
+	bool "Supm extension for userspace pointer masking"
+	depends on 64BIT
+	default y
+	help
+	  Add support for pointer masking in userspace (Supm) when the
+	  underlying hardware extension (Smnpm or Ssnpm) is detected at boot.
+
+	  If this option is disabled, userspace will be unable to use
+	  the prctl(PR_{SET,GET}_TAGGED_ADDR_CTRL) API.
+
 config RISCV_ISA_SVNAPOT
 	bool "Svnapot extension support for supervisor mode NAPOT pages"
 	depends on 64BIT && MMU
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index c1a4925088353..5f56eb9d114a9 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -178,6 +178,14 @@ extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);
 #define RISCV_SET_ICACHE_FLUSH_CTX(arg1, arg2)	riscv_set_icache_flush_ctx(arg1, arg2)
 extern int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long per_thread);
 
+#ifdef CONFIG_RISCV_ISA_SUPM
+/* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */
+long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg);
+long get_tagged_addr_ctrl(struct task_struct *task);
+#define SET_TAGGED_ADDR_CTRL(arg)	set_tagged_addr_ctrl(current, arg)
+#define GET_TAGGED_ADDR_CTRL()		get_tagged_addr_ctrl(current)
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_RISCV_PROCESSOR_H */
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index 9685cd85e57cc..94e33216b2d94 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -70,6 +70,17 @@ static __always_inline bool has_fpu(void) { return false; }
 #define __switch_to_fpu(__prev, __next) do { } while (0)
 #endif
 
+static inline void envcfg_update_bits(struct task_struct *task,
+				      unsigned long mask, unsigned long val)
+{
+	unsigned long envcfg;
+
+	envcfg = (task->thread.envcfg & ~mask) | val;
+	task->thread.envcfg = envcfg;
+	if (task == current)
+		csr_write(CSR_ENVCFG, envcfg);
+}
+
 static inline void __switch_to_envcfg(struct task_struct *next)
 {
 	asm volatile (ALTERNATIVE("nop", "csrw " __stringify(CSR_ENVCFG) ", %0",
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index e3142d8a6e284..200d2ed64dfee 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -7,6 +7,7 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/bitfield.h>
 #include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
@@ -180,6 +181,10 @@ void flush_thread(void)
 	memset(&current->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
 	clear_tsk_thread_flag(current, TIF_RISCV_V_DEFER_RESTORE);
 #endif
+#ifdef CONFIG_RISCV_ISA_SUPM
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
+		envcfg_update_bits(current, ENVCFG_PMM, ENVCFG_PMM_PMLEN_0);
+#endif
 }
 
 void arch_release_task_struct(struct task_struct *tsk)
@@ -242,3 +247,89 @@ void __init arch_task_cache_init(void)
 {
 	riscv_v_setup_ctx_cache();
 }
+
+#ifdef CONFIG_RISCV_ISA_SUPM
+enum {
+	PMLEN_0 = 0,
+	PMLEN_7 = 7,
+	PMLEN_16 = 16,
+};
+
+static bool have_user_pmlen_7;
+static bool have_user_pmlen_16;
+
+long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
+{
+	unsigned long valid_mask = PR_PMLEN_MASK;
+	struct thread_info *ti = task_thread_info(task);
+	unsigned long pmm;
+	u8 pmlen;
+
+	if (is_compat_thread(ti))
+		return -EINVAL;
+
+	if (arg & ~valid_mask)
+		return -EINVAL;
+
+	/*
+	 * Prefer the smallest PMLEN that satisfies the user's request,
+	 * in case choosing a larger PMLEN has a performance impact.
+	 */
+	pmlen = FIELD_GET(PR_PMLEN_MASK, arg);
+	if (pmlen == PMLEN_0)
+		pmm = ENVCFG_PMM_PMLEN_0;
+	else if (pmlen <= PMLEN_7 && have_user_pmlen_7)
+		pmm = ENVCFG_PMM_PMLEN_7;
+	else if (pmlen <= PMLEN_16 && have_user_pmlen_16)
+		pmm = ENVCFG_PMM_PMLEN_16;
+	else
+		return -EINVAL;
+
+	envcfg_update_bits(task, ENVCFG_PMM, pmm);
+
+	return 0;
+}
+
+long get_tagged_addr_ctrl(struct task_struct *task)
+{
+	struct thread_info *ti = task_thread_info(task);
+	long ret = 0;
+
+	if (is_compat_thread(ti))
+		return -EINVAL;
+
+	switch (task->thread.envcfg & ENVCFG_PMM) {
+	case ENVCFG_PMM_PMLEN_7:
+		ret = FIELD_PREP(PR_PMLEN_MASK, PMLEN_7);
+		break;
+	case ENVCFG_PMM_PMLEN_16:
+		ret = FIELD_PREP(PR_PMLEN_MASK, PMLEN_16);
+		break;
+	}
+
+	return ret;
+}
+
+static bool try_to_set_pmm(unsigned long value)
+{
+	csr_set(CSR_ENVCFG, value);
+	return (csr_read_clear(CSR_ENVCFG, ENVCFG_PMM) & ENVCFG_PMM) == value;
+}
+
+static int __init tagged_addr_init(void)
+{
+	if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
+		return 0;
+
+	/*
+	 * envcfg.PMM is a WARL field. Detect which values are supported.
+	 * Assume the supported PMLEN values are the same on all harts.
+	 */
+	csr_clear(CSR_ENVCFG, ENVCFG_PMM);
+	have_user_pmlen_7 = try_to_set_pmm(ENVCFG_PMM_PMLEN_7);
+	have_user_pmlen_16 = try_to_set_pmm(ENVCFG_PMM_PMLEN_16);
+
+	return 0;
+}
+core_initcall(tagged_addr_init);
+#endif	/* CONFIG_RISCV_ISA_SUPM */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 35791791a879b..cefd656ebf439 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -230,7 +230,7 @@ struct prctl_mm_map {
 # define PR_PAC_APDBKEY			(1UL << 3)
 # define PR_PAC_APGAKEY			(1UL << 4)
 
-/* Tagged user address controls for arm64 */
+/* Tagged user address controls for arm64 and RISC-V */
 #define PR_SET_TAGGED_ADDR_CTRL		55
 #define PR_GET_TAGGED_ADDR_CTRL		56
 # define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
@@ -244,6 +244,9 @@ struct prctl_mm_map {
 # define PR_MTE_TAG_MASK		(0xffffUL << PR_MTE_TAG_SHIFT)
 /* Unused; kept only for source compatibility */
 # define PR_MTE_TCF_SHIFT		1
+/* RISC-V pointer masking tag length */
+# define PR_PMLEN_SHIFT			24
+# define PR_PMLEN_MASK			(0x7fUL << PR_PMLEN_SHIFT)
 
 /* Control reclaim behavior when allocating memory */
 #define PR_SET_IO_FLUSHER		57

From 2e1743085887ba3f553c2bb472a75a3ff744b242 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 16 Oct 2024 13:27:46 -0700
Subject: [PATCH 0620/1530] riscv: Add support for the tagged address ABI

When pointer masking is enabled for userspace, the kernel can accept
tagged pointers as arguments to some system calls. Allow this by
untagging the pointers in access_ok() and the uaccess routines. The
uaccess routines must peform untagging in software because U-mode and
S-mode have entirely separate pointer masking configurations. In fact,
hardware may not even implement pointer masking for S-mode.

Since the number of tag bits is variable, untagged_addr_remote() needs
to know what PMLEN to use for the remote mm. Therefore, the pointer
masking mode must be the same for all threads sharing an mm. Enforce
this with a lock flag in the mm context, as x86 does for LAM. The flag
gets reset in init_new_context() during fork(), as the new mm is no
longer multithreaded.

Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Tested-by: Charlie Jenkins <charlie@rivosinc.com>
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20241016202814.4061541-6-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/uabi.rst    |  4 ++
 arch/riscv/include/asm/mmu.h         |  7 +++
 arch/riscv/include/asm/mmu_context.h | 13 +++++
 arch/riscv/include/asm/uaccess.h     | 43 ++++++++++++++--
 arch/riscv/kernel/process.c          | 73 ++++++++++++++++++++++++++--
 5 files changed, 130 insertions(+), 10 deletions(-)

diff --git a/Documentation/arch/riscv/uabi.rst b/Documentation/arch/riscv/uabi.rst
index ddb8359a46ed5..243e40062e34e 100644
--- a/Documentation/arch/riscv/uabi.rst
+++ b/Documentation/arch/riscv/uabi.rst
@@ -80,3 +80,7 @@ number of mask/tag bits needed by the application. ``PR_PMLEN`` is interpreted
 as a lower bound; if the kernel is unable to satisfy the request, the
 ``PR_SET_TAGGED_ADDR_CTRL`` operation will fail. The actual number of tag bits
 is returned in ``PR_PMLEN`` by the ``PR_GET_TAGGED_ADDR_CTRL`` operation.
+
+Additionally, when pointer masking is enabled (``PR_PMLEN`` is greater than 0),
+a tagged address ABI is supported, with the same interface and behavior as
+documented for AArch64 (Documentation/arch/arm64/tagged-address-abi.rst).
diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
index c9e03e9da3dc9..1cc90465d75b1 100644
--- a/arch/riscv/include/asm/mmu.h
+++ b/arch/riscv/include/asm/mmu.h
@@ -25,9 +25,16 @@ typedef struct {
 #ifdef CONFIG_BINFMT_ELF_FDPIC
 	unsigned long exec_fdpic_loadmap;
 	unsigned long interp_fdpic_loadmap;
+#endif
+	unsigned long flags;
+#ifdef CONFIG_RISCV_ISA_SUPM
+	u8 pmlen;
 #endif
 } mm_context_t;
 
+/* Lock the pointer masking mode because this mm is multithreaded */
+#define MM_CONTEXT_LOCK_PMLEN	0
+
 #define cntx2asid(cntx)		((cntx) & SATP_ASID_MASK)
 #define cntx2version(cntx)	((cntx) & ~SATP_ASID_MASK)
 
diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
index 7030837adc1a2..8c4bc49a3a0f5 100644
--- a/arch/riscv/include/asm/mmu_context.h
+++ b/arch/riscv/include/asm/mmu_context.h
@@ -20,6 +20,9 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 static inline void activate_mm(struct mm_struct *prev,
 			       struct mm_struct *next)
 {
+#ifdef CONFIG_RISCV_ISA_SUPM
+	next->context.pmlen = 0;
+#endif
 	switch_mm(prev, next, NULL);
 }
 
@@ -30,11 +33,21 @@ static inline int init_new_context(struct task_struct *tsk,
 #ifdef CONFIG_MMU
 	atomic_long_set(&mm->context.id, 0);
 #endif
+	if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM))
+		clear_bit(MM_CONTEXT_LOCK_PMLEN, &mm->context.flags);
 	return 0;
 }
 
 DECLARE_STATIC_KEY_FALSE(use_asid_allocator);
 
+#ifdef CONFIG_RISCV_ISA_SUPM
+#define mm_untag_mask mm_untag_mask
+static inline unsigned long mm_untag_mask(struct mm_struct *mm)
+{
+	return -1UL >> mm->context.pmlen;
+}
+#endif
+
 #include <asm-generic/mmu_context.h>
 
 #endif /* _ASM_RISCV_MMU_CONTEXT_H */
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 72ec1d9bd3f31..fee56b0c80586 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -9,8 +9,41 @@
 #define _ASM_RISCV_UACCESS_H
 
 #include <asm/asm-extable.h>
+#include <asm/cpufeature.h>
 #include <asm/pgtable.h>		/* for TASK_SIZE */
 
+#ifdef CONFIG_RISCV_ISA_SUPM
+static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, unsigned long addr)
+{
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) {
+		u8 pmlen = mm->context.pmlen;
+
+		/* Virtual addresses are sign-extended; physical addresses are zero-extended. */
+		if (IS_ENABLED(CONFIG_MMU))
+			return (long)(addr << pmlen) >> pmlen;
+		else
+			return (addr << pmlen) >> pmlen;
+	}
+
+	return addr;
+}
+
+#define untagged_addr(addr) ({							\
+	unsigned long __addr = (__force unsigned long)(addr);			\
+	(__force __typeof__(addr))__untagged_addr_remote(current->mm, __addr);	\
+})
+
+#define untagged_addr_remote(mm, addr) ({					\
+	unsigned long __addr = (__force unsigned long)(addr);			\
+	mmap_assert_locked(mm);							\
+	(__force __typeof__(addr))__untagged_addr_remote(mm, __addr);		\
+})
+
+#define access_ok(addr, size) likely(__access_ok(untagged_addr(addr), size))
+#else
+#define untagged_addr(addr) (addr)
+#endif
+
 /*
  * User space memory access functions
  */
@@ -130,7 +163,7 @@ do {								\
  */
 #define __get_user(x, ptr)					\
 ({								\
-	const __typeof__(*(ptr)) __user *__gu_ptr = (ptr);	\
+	const __typeof__(*(ptr)) __user *__gu_ptr = untagged_addr(ptr); \
 	long __gu_err = 0;					\
 								\
 	__chk_user_ptr(__gu_ptr);				\
@@ -246,7 +279,7 @@ do {								\
  */
 #define __put_user(x, ptr)					\
 ({								\
-	__typeof__(*(ptr)) __user *__gu_ptr = (ptr);		\
+	__typeof__(*(ptr)) __user *__gu_ptr = untagged_addr(ptr); \
 	__typeof__(*__gu_ptr) __val = (x);			\
 	long __pu_err = 0;					\
 								\
@@ -293,13 +326,13 @@ unsigned long __must_check __asm_copy_from_user(void *to,
 static inline unsigned long
 raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	return __asm_copy_from_user(to, from, n);
+	return __asm_copy_from_user(to, untagged_addr(from), n);
 }
 
 static inline unsigned long
 raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	return __asm_copy_to_user(to, from, n);
+	return __asm_copy_to_user(untagged_addr(to), from, n);
 }
 
 extern long strncpy_from_user(char *dest, const char __user *src, long count);
@@ -314,7 +347,7 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
 {
 	might_fault();
 	return access_ok(to, n) ?
-		__clear_user(to, n) : n;
+		__clear_user(untagged_addr(to), n) : n;
 }
 
 #define __get_kernel_nofault(dst, src, type, err_label)			\
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 200d2ed64dfee..58b6482c2bf66 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -213,6 +213,10 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 
+	/* Ensure all threads in this mm have the same pointer masking mode. */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM) && p->mm && (clone_flags & CLONE_VM))
+		set_bit(MM_CONTEXT_LOCK_PMLEN, &p->mm->context.flags);
+
 	memset(&p->thread.s, 0, sizeof(p->thread.s));
 
 	/* p->thread holds context to be restored by __switch_to() */
@@ -258,10 +262,16 @@ enum {
 static bool have_user_pmlen_7;
 static bool have_user_pmlen_16;
 
+/*
+ * Control the relaxed ABI allowing tagged user addresses into the kernel.
+ */
+static unsigned int tagged_addr_disabled;
+
 long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
 {
-	unsigned long valid_mask = PR_PMLEN_MASK;
+	unsigned long valid_mask = PR_PMLEN_MASK | PR_TAGGED_ADDR_ENABLE;
 	struct thread_info *ti = task_thread_info(task);
+	struct mm_struct *mm = task->mm;
 	unsigned long pmm;
 	u8 pmlen;
 
@@ -276,16 +286,41 @@ long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
 	 * in case choosing a larger PMLEN has a performance impact.
 	 */
 	pmlen = FIELD_GET(PR_PMLEN_MASK, arg);
-	if (pmlen == PMLEN_0)
+	if (pmlen == PMLEN_0) {
 		pmm = ENVCFG_PMM_PMLEN_0;
-	else if (pmlen <= PMLEN_7 && have_user_pmlen_7)
+	} else if (pmlen <= PMLEN_7 && have_user_pmlen_7) {
+		pmlen = PMLEN_7;
 		pmm = ENVCFG_PMM_PMLEN_7;
-	else if (pmlen <= PMLEN_16 && have_user_pmlen_16)
+	} else if (pmlen <= PMLEN_16 && have_user_pmlen_16) {
+		pmlen = PMLEN_16;
 		pmm = ENVCFG_PMM_PMLEN_16;
-	else
+	} else {
 		return -EINVAL;
+	}
+
+	/*
+	 * Do not allow the enabling of the tagged address ABI if globally
+	 * disabled via sysctl abi.tagged_addr_disabled, if pointer masking
+	 * is disabled for userspace.
+	 */
+	if (arg & PR_TAGGED_ADDR_ENABLE && (tagged_addr_disabled || !pmlen))
+		return -EINVAL;
+
+	if (!(arg & PR_TAGGED_ADDR_ENABLE))
+		pmlen = PMLEN_0;
+
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	if (test_bit(MM_CONTEXT_LOCK_PMLEN, &mm->context.flags) && mm->context.pmlen != pmlen) {
+		mmap_write_unlock(mm);
+		return -EBUSY;
+	}
 
 	envcfg_update_bits(task, ENVCFG_PMM, pmm);
+	mm->context.pmlen = pmlen;
+
+	mmap_write_unlock(mm);
 
 	return 0;
 }
@@ -298,6 +333,10 @@ long get_tagged_addr_ctrl(struct task_struct *task)
 	if (is_compat_thread(ti))
 		return -EINVAL;
 
+	/*
+	 * The mm context's pmlen is set only when the tagged address ABI is
+	 * enabled, so the effective PMLEN must be extracted from envcfg.PMM.
+	 */
 	switch (task->thread.envcfg & ENVCFG_PMM) {
 	case ENVCFG_PMM_PMLEN_7:
 		ret = FIELD_PREP(PR_PMLEN_MASK, PMLEN_7);
@@ -307,6 +346,9 @@ long get_tagged_addr_ctrl(struct task_struct *task)
 		break;
 	}
 
+	if (task->mm->context.pmlen)
+		ret |= PR_TAGGED_ADDR_ENABLE;
+
 	return ret;
 }
 
@@ -316,6 +358,24 @@ static bool try_to_set_pmm(unsigned long value)
 	return (csr_read_clear(CSR_ENVCFG, ENVCFG_PMM) & ENVCFG_PMM) == value;
 }
 
+/*
+ * Global sysctl to disable the tagged user addresses support. This control
+ * only prevents the tagged address ABI enabling via prctl() and does not
+ * disable it for tasks that already opted in to the relaxed ABI.
+ */
+
+static struct ctl_table tagged_addr_sysctl_table[] = {
+	{
+		.procname	= "tagged_addr_disabled",
+		.mode		= 0644,
+		.data		= &tagged_addr_disabled,
+		.maxlen		= sizeof(int),
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+};
+
 static int __init tagged_addr_init(void)
 {
 	if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
@@ -329,6 +389,9 @@ static int __init tagged_addr_init(void)
 	have_user_pmlen_7 = try_to_set_pmm(ENVCFG_PMM_PMLEN_7);
 	have_user_pmlen_16 = try_to_set_pmm(ENVCFG_PMM_PMLEN_16);
 
+	if (!register_sysctl("abi", tagged_addr_sysctl_table))
+		return -EINVAL;
+
 	return 0;
 }
 core_initcall(tagged_addr_init);

From 78844482a1c939a972681842f8ee2a8ddb202441 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 16 Oct 2024 13:27:47 -0700
Subject: [PATCH 0621/1530] riscv: Allow ptrace control of the tagged address
 ABI

This allows a tracer to control the ABI of the tracee, as on arm64.

Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20241016202814.4061541-7-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/ptrace.c | 42 ++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/elf.h   |  1 +
 2 files changed, 43 insertions(+)

diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 92731ff8c79ad..ea67e9fb7a583 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -28,6 +28,9 @@ enum riscv_regset {
 #ifdef CONFIG_RISCV_ISA_V
 	REGSET_V,
 #endif
+#ifdef CONFIG_RISCV_ISA_SUPM
+	REGSET_TAGGED_ADDR_CTRL,
+#endif
 };
 
 static int riscv_gpr_get(struct task_struct *target,
@@ -152,6 +155,35 @@ static int riscv_vr_set(struct task_struct *target,
 }
 #endif
 
+#ifdef CONFIG_RISCV_ISA_SUPM
+static int tagged_addr_ctrl_get(struct task_struct *target,
+				const struct user_regset *regset,
+				struct membuf to)
+{
+	long ctrl = get_tagged_addr_ctrl(target);
+
+	if (IS_ERR_VALUE(ctrl))
+		return ctrl;
+
+	return membuf_write(&to, &ctrl, sizeof(ctrl));
+}
+
+static int tagged_addr_ctrl_set(struct task_struct *target,
+				const struct user_regset *regset,
+				unsigned int pos, unsigned int count,
+				const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+	long ctrl;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1);
+	if (ret)
+		return ret;
+
+	return set_tagged_addr_ctrl(target, ctrl);
+}
+#endif
+
 static const struct user_regset riscv_user_regset[] = {
 	[REGSET_X] = {
 		.core_note_type = NT_PRSTATUS,
@@ -182,6 +214,16 @@ static const struct user_regset riscv_user_regset[] = {
 		.set = riscv_vr_set,
 	},
 #endif
+#ifdef CONFIG_RISCV_ISA_SUPM
+	[REGSET_TAGGED_ADDR_CTRL] = {
+		.core_note_type = NT_RISCV_TAGGED_ADDR_CTRL,
+		.n = 1,
+		.size = sizeof(long),
+		.align = sizeof(long),
+		.regset_get = tagged_addr_ctrl_get,
+		.set = tagged_addr_ctrl_set,
+	},
+#endif
 };
 
 static const struct user_regset_view riscv_user_native_view = {
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index b9935988da5cf..a920cf8934dc8 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -450,6 +450,7 @@ typedef struct elf64_shdr {
 #define NT_MIPS_MSA	0x802		/* MIPS SIMD registers */
 #define NT_RISCV_CSR	0x900		/* RISC-V Control and Status Registers */
 #define NT_RISCV_VECTOR	0x901		/* RISC-V vector registers */
+#define NT_RISCV_TAGGED_ADDR_CTRL 0x902	/* RISC-V tagged address control (prctl()) */
 #define NT_LOONGARCH_CPUCFG	0xa00	/* LoongArch CPU config registers */
 #define NT_LOONGARCH_CSR	0xa01	/* LoongArch control and status registers */
 #define NT_LOONGARCH_LSX	0xa02	/* LoongArch Loongson SIMD Extension registers */

From 7470b5afd150e683c7aef03961d0c4c6f500de3b Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 16 Oct 2024 13:27:48 -0700
Subject: [PATCH 0622/1530] riscv: selftests: Add a pointer masking test

This test covers the behavior of the PR_SET_TAGGED_ADDR_CTRL and
PR_GET_TAGGED_ADDR_CTRL prctl() operations, their effects on the
userspace ABI, and their effects on the system call ABI.

Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Tested-by: Charlie Jenkins <charlie@rivosinc.com>
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20241016202814.4061541-8-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 tools/testing/selftests/riscv/Makefile        |   2 +-
 tools/testing/selftests/riscv/abi/.gitignore  |   1 +
 tools/testing/selftests/riscv/abi/Makefile    |  10 +
 .../selftests/riscv/abi/pointer_masking.c     | 332 ++++++++++++++++++
 4 files changed, 344 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/riscv/abi/.gitignore
 create mode 100644 tools/testing/selftests/riscv/abi/Makefile
 create mode 100644 tools/testing/selftests/riscv/abi/pointer_masking.c

diff --git a/tools/testing/selftests/riscv/Makefile b/tools/testing/selftests/riscv/Makefile
index 7ce03d832b647..099b8c1f46f89 100644
--- a/tools/testing/selftests/riscv/Makefile
+++ b/tools/testing/selftests/riscv/Makefile
@@ -5,7 +5,7 @@
 ARCH ?= $(shell uname -m 2>/dev/null || echo not)
 
 ifneq (,$(filter $(ARCH),riscv))
-RISCV_SUBTARGETS ?= hwprobe vector mm sigreturn
+RISCV_SUBTARGETS ?= abi hwprobe mm sigreturn vector
 else
 RISCV_SUBTARGETS :=
 endif
diff --git a/tools/testing/selftests/riscv/abi/.gitignore b/tools/testing/selftests/riscv/abi/.gitignore
new file mode 100644
index 0000000000000..b38358f91c4d2
--- /dev/null
+++ b/tools/testing/selftests/riscv/abi/.gitignore
@@ -0,0 +1 @@
+pointer_masking
diff --git a/tools/testing/selftests/riscv/abi/Makefile b/tools/testing/selftests/riscv/abi/Makefile
new file mode 100644
index 0000000000000..ed82ff9c664e7
--- /dev/null
+++ b/tools/testing/selftests/riscv/abi/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+
+CFLAGS += -I$(top_srcdir)/tools/include
+
+TEST_GEN_PROGS := pointer_masking
+
+include ../../lib.mk
+
+$(OUTPUT)/pointer_masking: pointer_masking.c
+	$(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^
diff --git a/tools/testing/selftests/riscv/abi/pointer_masking.c b/tools/testing/selftests/riscv/abi/pointer_masking.c
new file mode 100644
index 0000000000000..dee41b7ee3e32
--- /dev/null
+++ b/tools/testing/selftests/riscv/abi/pointer_masking.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <errno.h>
+#include <fcntl.h>
+#include <setjmp.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "../../kselftest.h"
+
+#ifndef PR_PMLEN_SHIFT
+#define PR_PMLEN_SHIFT			24
+#endif
+#ifndef PR_PMLEN_MASK
+#define PR_PMLEN_MASK			(0x7fUL << PR_PMLEN_SHIFT)
+#endif
+
+static int dev_zero;
+
+static int pipefd[2];
+
+static sigjmp_buf jmpbuf;
+
+static void sigsegv_handler(int sig)
+{
+	siglongjmp(jmpbuf, 1);
+}
+
+static int min_pmlen;
+static int max_pmlen;
+
+static inline bool valid_pmlen(int pmlen)
+{
+	return pmlen == 0 || pmlen == 7 || pmlen == 16;
+}
+
+static void test_pmlen(void)
+{
+	ksft_print_msg("Testing available PMLEN values\n");
+
+	for (int request = 0; request <= 16; request++) {
+		int pmlen, ret;
+
+		ret = prctl(PR_SET_TAGGED_ADDR_CTRL, request << PR_PMLEN_SHIFT, 0, 0, 0);
+		if (ret)
+			goto pr_set_error;
+
+		ret = prctl(PR_GET_TAGGED_ADDR_CTRL, 0, 0, 0, 0);
+		ksft_test_result(ret >= 0, "PMLEN=%d PR_GET_TAGGED_ADDR_CTRL\n", request);
+		if (ret < 0)
+			goto pr_get_error;
+
+		pmlen = (ret & PR_PMLEN_MASK) >> PR_PMLEN_SHIFT;
+		ksft_test_result(pmlen >= request, "PMLEN=%d constraint\n", request);
+		ksft_test_result(valid_pmlen(pmlen), "PMLEN=%d validity\n", request);
+
+		if (min_pmlen == 0)
+			min_pmlen = pmlen;
+		if (max_pmlen < pmlen)
+			max_pmlen = pmlen;
+
+		continue;
+
+pr_set_error:
+		ksft_test_result_skip("PMLEN=%d PR_GET_TAGGED_ADDR_CTRL\n", request);
+pr_get_error:
+		ksft_test_result_skip("PMLEN=%d constraint\n", request);
+		ksft_test_result_skip("PMLEN=%d validity\n", request);
+	}
+
+	if (max_pmlen == 0)
+		ksft_exit_fail_msg("Failed to enable pointer masking\n");
+}
+
+static int set_tagged_addr_ctrl(int pmlen, bool tagged_addr_abi)
+{
+	int arg, ret;
+
+	arg = pmlen << PR_PMLEN_SHIFT | tagged_addr_abi;
+	ret = prctl(PR_SET_TAGGED_ADDR_CTRL, arg, 0, 0, 0);
+	if (!ret) {
+		ret = prctl(PR_GET_TAGGED_ADDR_CTRL, 0, 0, 0, 0);
+		if (ret == arg)
+			return 0;
+	}
+
+	return ret < 0 ? -errno : -ENODATA;
+}
+
+static void test_dereference_pmlen(int pmlen)
+{
+	static volatile int i;
+	volatile int *p;
+	int ret;
+
+	ret = set_tagged_addr_ctrl(pmlen, false);
+	if (ret)
+		return ksft_test_result_error("PMLEN=%d setup (%d)\n", pmlen, ret);
+
+	i = pmlen;
+
+	if (pmlen) {
+		p = (volatile int *)((uintptr_t)&i | 1UL << (__riscv_xlen - pmlen));
+
+		/* These dereferences should succeed. */
+		if (sigsetjmp(jmpbuf, 1))
+			return ksft_test_result_fail("PMLEN=%d valid tag\n", pmlen);
+		if (*p != pmlen)
+			return ksft_test_result_fail("PMLEN=%d bad value\n", pmlen);
+		++*p;
+	}
+
+	p = (volatile int *)((uintptr_t)&i | 1UL << (__riscv_xlen - pmlen - 1));
+
+	/* These dereferences should raise SIGSEGV. */
+	if (sigsetjmp(jmpbuf, 1))
+		return ksft_test_result_pass("PMLEN=%d dereference\n", pmlen);
+	++*p;
+	ksft_test_result_fail("PMLEN=%d invalid tag\n", pmlen);
+}
+
+static void test_dereference(void)
+{
+	ksft_print_msg("Testing userspace pointer dereference\n");
+
+	signal(SIGSEGV, sigsegv_handler);
+
+	test_dereference_pmlen(0);
+	test_dereference_pmlen(min_pmlen);
+	test_dereference_pmlen(max_pmlen);
+
+	signal(SIGSEGV, SIG_DFL);
+}
+
+static void execve_child_sigsegv_handler(int sig)
+{
+	exit(42);
+}
+
+static int execve_child(void)
+{
+	static volatile int i;
+	volatile int *p = (volatile int *)((uintptr_t)&i | 1UL << (__riscv_xlen - 7));
+
+	signal(SIGSEGV, execve_child_sigsegv_handler);
+
+	/* This dereference should raise SIGSEGV. */
+	return *p;
+}
+
+static void test_fork_exec(void)
+{
+	int ret, status;
+
+	ksft_print_msg("Testing fork/exec behavior\n");
+
+	ret = set_tagged_addr_ctrl(min_pmlen, false);
+	if (ret)
+		return ksft_test_result_error("setup (%d)\n", ret);
+
+	if (fork()) {
+		wait(&status);
+		ksft_test_result(WIFEXITED(status) && WEXITSTATUS(status) == 42,
+				 "dereference after fork\n");
+	} else {
+		static volatile int i = 42;
+		volatile int *p;
+
+		p = (volatile int *)((uintptr_t)&i | 1UL << (__riscv_xlen - min_pmlen));
+
+		/* This dereference should succeed. */
+		exit(*p);
+	}
+
+	if (fork()) {
+		wait(&status);
+		ksft_test_result(WIFEXITED(status) && WEXITSTATUS(status) == 42,
+				 "dereference after fork+exec\n");
+	} else {
+		/* Will call execve_child(). */
+		execve("/proc/self/exe", (char *const []) { "", NULL }, NULL);
+	}
+}
+
+static void test_tagged_addr_abi_sysctl(void)
+{
+	char value;
+	int fd;
+
+	ksft_print_msg("Testing tagged address ABI sysctl\n");
+
+	fd = open("/proc/sys/abi/tagged_addr_disabled", O_WRONLY);
+	if (fd < 0) {
+		ksft_test_result_skip("failed to open sysctl file\n");
+		ksft_test_result_skip("failed to open sysctl file\n");
+		return;
+	}
+
+	value = '1';
+	pwrite(fd, &value, 1, 0);
+	ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL,
+			 "sysctl disabled\n");
+
+	value = '0';
+	pwrite(fd, &value, 1, 0);
+	ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0,
+			 "sysctl enabled\n");
+
+	set_tagged_addr_ctrl(0, false);
+
+	close(fd);
+}
+
+static void test_tagged_addr_abi_pmlen(int pmlen)
+{
+	int i, *p, ret;
+
+	i = ~pmlen;
+
+	if (pmlen) {
+		p = (int *)((uintptr_t)&i | 1UL << (__riscv_xlen - pmlen));
+
+		ret = set_tagged_addr_ctrl(pmlen, false);
+		if (ret)
+			return ksft_test_result_error("PMLEN=%d ABI disabled setup (%d)\n",
+						      pmlen, ret);
+
+		ret = write(pipefd[1], p, sizeof(*p));
+		if (ret >= 0 || errno != EFAULT)
+			return ksft_test_result_fail("PMLEN=%d ABI disabled write\n", pmlen);
+
+		ret = read(dev_zero, p, sizeof(*p));
+		if (ret >= 0 || errno != EFAULT)
+			return ksft_test_result_fail("PMLEN=%d ABI disabled read\n", pmlen);
+
+		if (i != ~pmlen)
+			return ksft_test_result_fail("PMLEN=%d ABI disabled value\n", pmlen);
+
+		ret = set_tagged_addr_ctrl(pmlen, true);
+		if (ret)
+			return ksft_test_result_error("PMLEN=%d ABI enabled setup (%d)\n",
+						      pmlen, ret);
+
+		ret = write(pipefd[1], p, sizeof(*p));
+		if (ret != sizeof(*p))
+			return ksft_test_result_fail("PMLEN=%d ABI enabled write\n", pmlen);
+
+		ret = read(dev_zero, p, sizeof(*p));
+		if (ret != sizeof(*p))
+			return ksft_test_result_fail("PMLEN=%d ABI enabled read\n", pmlen);
+
+		if (i)
+			return ksft_test_result_fail("PMLEN=%d ABI enabled value\n", pmlen);
+
+		i = ~pmlen;
+	} else {
+		/* The tagged address ABI cannot be enabled when PMLEN == 0. */
+		ret = set_tagged_addr_ctrl(pmlen, true);
+		if (ret != -EINVAL)
+			return ksft_test_result_error("PMLEN=%d ABI setup (%d)\n",
+						      pmlen, ret);
+	}
+
+	p = (int *)((uintptr_t)&i | 1UL << (__riscv_xlen - pmlen - 1));
+
+	ret = write(pipefd[1], p, sizeof(*p));
+	if (ret >= 0 || errno != EFAULT)
+		return ksft_test_result_fail("PMLEN=%d invalid tag write (%d)\n", pmlen, errno);
+
+	ret = read(dev_zero, p, sizeof(*p));
+	if (ret >= 0 || errno != EFAULT)
+		return ksft_test_result_fail("PMLEN=%d invalid tag read\n", pmlen);
+
+	if (i != ~pmlen)
+		return ksft_test_result_fail("PMLEN=%d invalid tag value\n", pmlen);
+
+	ksft_test_result_pass("PMLEN=%d tagged address ABI\n", pmlen);
+}
+
+static void test_tagged_addr_abi(void)
+{
+	ksft_print_msg("Testing tagged address ABI\n");
+
+	test_tagged_addr_abi_pmlen(0);
+	test_tagged_addr_abi_pmlen(min_pmlen);
+	test_tagged_addr_abi_pmlen(max_pmlen);
+}
+
+static struct test_info {
+	unsigned int nr_tests;
+	void (*test_fn)(void);
+} tests[] = {
+	{ .nr_tests = 17 * 3, test_pmlen },
+	{ .nr_tests = 3, test_dereference },
+	{ .nr_tests = 2, test_fork_exec },
+	{ .nr_tests = 2, test_tagged_addr_abi_sysctl },
+	{ .nr_tests = 3, test_tagged_addr_abi },
+};
+
+int main(int argc, char **argv)
+{
+	unsigned int plan = 0;
+	int ret;
+
+	/* Check if this is the child process after execve(). */
+	if (!argv[0][0])
+		return execve_child();
+
+	dev_zero = open("/dev/zero", O_RDWR);
+	if (dev_zero < 0)
+		return 1;
+
+	/* Write to a pipe so the kernel must dereference the buffer pointer. */
+	ret = pipe(pipefd);
+	if (ret)
+		return 1;
+
+	ksft_print_header();
+
+	for (int i = 0; i < ARRAY_SIZE(tests); i++)
+		plan += tests[i].nr_tests;
+
+	ksft_set_plan(plan);
+
+	for (int i = 0; i < ARRAY_SIZE(tests); i++)
+		tests[i].test_fn();
+
+	ksft_finished();
+}

From 3c2e0aff7b4f03fbc11b7d63c8db5b94a48978cf Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 16 Oct 2024 13:27:49 -0700
Subject: [PATCH 0623/1530] riscv: hwprobe: Export the Supm ISA extension

Supm is a virtual ISA extension defined in the RISC-V Pointer Masking
specification, which indicates that pointer masking is available in
U-mode. It can be provided by either Smnpm or Ssnpm, depending on which
mode the kernel runs in. Userspace should not care about this
distinction, so export Supm instead of either underlying extension.

Hide the extension if the kernel was compiled without support for the
pointer masking prctl() interface.

Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20241016202814.4061541-9-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/hwprobe.rst  | 3 +++
 arch/riscv/include/uapi/asm/hwprobe.h | 1 +
 arch/riscv/kernel/sys_hwprobe.c       | 3 +++
 3 files changed, 7 insertions(+)

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 85b709257918a..b9aec2e5bbd44 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -239,6 +239,9 @@ The following keys are defined:
        ratified in commit 98918c844281 ("Merge pull request #1217 from
        riscv/zawrs") of riscv-isa-manual.
 
+  * :c:macro:`RISCV_HWPROBE_EXT_SUPM`: The Supm extension is supported as
+       defined in version 1.0 of the RISC-V Pointer Masking extensions.
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: Deprecated.  Returns similar values to
      :c:macro:`RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF`, but the key was
      mistakenly classified as a bitmask rather than a value.
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 1e153cda57db8..868ff41b93d62 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -72,6 +72,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZCF		(1ULL << 46)
 #define		RISCV_HWPROBE_EXT_ZCMOP		(1ULL << 47)
 #define		RISCV_HWPROBE_EXT_ZAWRS		(1ULL << 48)
+#define		RISCV_HWPROBE_EXT_SUPM		(1ULL << 49)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index cea0ca2bf2a25..0ac78e9f7c941 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -150,6 +150,9 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 			EXT_KEY(ZFH);
 			EXT_KEY(ZFHMIN);
 		}
+
+		if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM))
+			EXT_KEY(SUPM);
 #undef EXT_KEY
 	}
 

From 1851e7836212c76bebb6944bb1541ddcccbea535 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 16 Oct 2024 13:27:50 -0700
Subject: [PATCH 0624/1530] RISC-V: KVM: Allow Smnpm and Ssnpm extensions for
 guests

The interface for controlling pointer masking in VS-mode is henvcfg.PMM,
which is part of the Ssnpm extension, even though pointer masking in
HS-mode is provided by the Smnpm extension. As a result, emulating Smnpm
in the guest requires (only) Ssnpm on the host.

The guest configures Smnpm through the SBI Firmware Features extension,
which KVM does not yet implement, so currently the ISA extension has no
visible effect on the guest, and thus it cannot be disabled. Ssnpm is
configured using the senvcfg CSR within the guest, so that extension
cannot be hidden from the guest without intercepting writes to the CSR.

Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20241016202814.4061541-10-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/uapi/asm/kvm.h | 2 ++
 arch/riscv/kvm/vcpu_onereg.c      | 4 ++++
 2 files changed, 6 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index e97db3296456e..4f24201376b17 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -175,6 +175,8 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_ZCF,
 	KVM_RISCV_ISA_EXT_ZCMOP,
 	KVM_RISCV_ISA_EXT_ZAWRS,
+	KVM_RISCV_ISA_EXT_SMNPM,
+	KVM_RISCV_ISA_EXT_SSNPM,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index b319c4c13c54c..5b68490ad9b75 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -34,9 +34,11 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	[KVM_RISCV_ISA_EXT_M] = RISCV_ISA_EXT_m,
 	[KVM_RISCV_ISA_EXT_V] = RISCV_ISA_EXT_v,
 	/* Multi letter extensions (alphabetically sorted) */
+	[KVM_RISCV_ISA_EXT_SMNPM] = RISCV_ISA_EXT_SSNPM,
 	KVM_ISA_EXT_ARR(SMSTATEEN),
 	KVM_ISA_EXT_ARR(SSAIA),
 	KVM_ISA_EXT_ARR(SSCOFPMF),
+	KVM_ISA_EXT_ARR(SSNPM),
 	KVM_ISA_EXT_ARR(SSTC),
 	KVM_ISA_EXT_ARR(SVINVAL),
 	KVM_ISA_EXT_ARR(SVNAPOT),
@@ -127,8 +129,10 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_C:
 	case KVM_RISCV_ISA_EXT_I:
 	case KVM_RISCV_ISA_EXT_M:
+	case KVM_RISCV_ISA_EXT_SMNPM:
 	/* There is not architectural config bit to disable sscofpmf completely */
 	case KVM_RISCV_ISA_EXT_SSCOFPMF:
+	case KVM_RISCV_ISA_EXT_SSNPM:
 	case KVM_RISCV_ISA_EXT_SSTC:
 	case KVM_RISCV_ISA_EXT_SVINVAL:
 	case KVM_RISCV_ISA_EXT_SVNAPOT:

From 036a1407b4d49790ca5b35436d02de62212bc790 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 16 Oct 2024 13:27:51 -0700
Subject: [PATCH 0625/1530] KVM: riscv: selftests: Add Smnpm and Ssnpm to
 get-reg-list test

Add testing for the pointer masking extensions exposed to KVM guests.

Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20241016202814.4061541-11-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 tools/testing/selftests/kvm/riscv/get-reg-list.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 8e34f7fa44e94..54ab484d00006 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -41,9 +41,11 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_I:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_M:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_V:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SMNPM:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SMSTATEEN:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSAIA:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSCOFPMF:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSNPM:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSTC:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVINVAL:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVNAPOT:
@@ -414,9 +416,11 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
 		KVM_ISA_EXT_ARR(I),
 		KVM_ISA_EXT_ARR(M),
 		KVM_ISA_EXT_ARR(V),
+		KVM_ISA_EXT_ARR(SMNPM),
 		KVM_ISA_EXT_ARR(SMSTATEEN),
 		KVM_ISA_EXT_ARR(SSAIA),
 		KVM_ISA_EXT_ARR(SSCOFPMF),
+		KVM_ISA_EXT_ARR(SSNPM),
 		KVM_ISA_EXT_ARR(SSTC),
 		KVM_ISA_EXT_ARR(SVINVAL),
 		KVM_ISA_EXT_ARR(SVNAPOT),
@@ -946,8 +950,10 @@ KVM_ISA_EXT_SUBLIST_CONFIG(aia, AIA);
 KVM_ISA_EXT_SUBLIST_CONFIG(fp_f, FP_F);
 KVM_ISA_EXT_SUBLIST_CONFIG(fp_d, FP_D);
 KVM_ISA_EXT_SIMPLE_CONFIG(h, H);
+KVM_ISA_EXT_SIMPLE_CONFIG(smnpm, SMNPM);
 KVM_ISA_EXT_SUBLIST_CONFIG(smstateen, SMSTATEEN);
 KVM_ISA_EXT_SIMPLE_CONFIG(sscofpmf, SSCOFPMF);
+KVM_ISA_EXT_SIMPLE_CONFIG(ssnpm, SSNPM);
 KVM_ISA_EXT_SIMPLE_CONFIG(sstc, SSTC);
 KVM_ISA_EXT_SIMPLE_CONFIG(svinval, SVINVAL);
 KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT);
@@ -1009,8 +1015,10 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_fp_f,
 	&config_fp_d,
 	&config_h,
+	&config_smnpm,
 	&config_smstateen,
 	&config_sscofpmf,
+	&config_ssnpm,
 	&config_sstc,
 	&config_svinval,
 	&config_svnapot,

From b4badee88cd3af8b31f93ca1469f499ddabd01c5 Mon Sep 17 00:00:00 2001
From: Zeng Heng <zengheng4@huawei.com>
Date: Wed, 23 Oct 2024 14:21:05 -0700
Subject: [PATCH 0626/1530] Input: imagis - fix warning regarding
 'imagis_3038_data' being unused
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following compilation warnings:
drivers/input/touchscreen/imagis.c:422:39: warning: ‘imagis_3038c_data’
defined but not used [-Wunused-const-variable=]
  422 | static const struct imagis_properties imagis_3038c_data = {
drivers/input/touchscreen/imagis.c:415:39: warning: ‘imagis_3038b_data’
defined but not used [-Wunused-const-variable=]
  415 | static const struct imagis_properties imagis_3038b_data = {
drivers/input/touchscreen/imagis.c:407:39: warning: ‘imagis_3038_data’
defined but not used [-Wunused-const-variable=]
  407 | static const struct imagis_properties imagis_3038_data = {
drivers/input/touchscreen/imagis.c:398:39: warning: ‘imagis_3032c_data’
defined but not used [-Wunused-const-variable=]
  398 | static const struct imagis_properties imagis_3032c_data = {

Only define the variables 'imagis_303*_data' when the CONFIG_OF
is enabled.

Fixes: 1e48ee99f603 ("Input: imagis - add supports for Imagis IST3038")
Signed-off-by: Zeng Heng <zengheng4@huawei.com>
Acked-by: Markuss Broks <markuss.broks@gmail.com>
Link: https://lore.kernel.org/r/20241023094831.1680214-1-zengheng4@huawei.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/imagis.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/touchscreen/imagis.c b/drivers/input/touchscreen/imagis.c
index aeabf8d057ded..abeae9102323c 100644
--- a/drivers/input/touchscreen/imagis.c
+++ b/drivers/input/touchscreen/imagis.c
@@ -395,6 +395,7 @@ static int imagis_resume(struct device *dev)
 
 static DEFINE_SIMPLE_DEV_PM_OPS(imagis_pm_ops, imagis_suspend, imagis_resume);
 
+#ifdef CONFIG_OF
 static const struct imagis_properties imagis_3032c_data = {
 	.interrupt_msg_cmd = IST3038C_REG_INTR_MESSAGE,
 	.touch_coord_cmd = IST3038C_REG_TOUCH_COORD,
@@ -427,7 +428,6 @@ static const struct imagis_properties imagis_3038c_data = {
 	.protocol_b = true,
 };
 
-#ifdef CONFIG_OF
 static const struct of_device_id imagis_of_match[] = {
 	{ .compatible = "imagis,ist3032c", .data = &imagis_3032c_data },
 	{ .compatible = "imagis,ist3038", .data = &imagis_3038_data },

From f407af78c8d3b6035f81152b15ad67063f42514e Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Thu, 17 Oct 2024 12:39:37 +0100
Subject: [PATCH 0627/1530] pinctrl: renesas: rzg2l: Use
 gpiochip_populate_parent_fwspec_twocell helper

Because rzg2l_gpio_populate_parent_fwspec() and
gpiochip_populate_parent_fwspec_twocell() are identical.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/20241017113942.139712-3-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rzg2l.c | 17 +----------------
 1 file changed, 1 insertion(+), 16 deletions(-)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index 5eefbace7d912..8ffb9430a1342 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -2433,21 +2433,6 @@ static int rzg2l_gpio_child_to_parent_hwirq(struct gpio_chip *gc,
 	return ret;
 }
 
-static int rzg2l_gpio_populate_parent_fwspec(struct gpio_chip *chip,
-					     union gpio_irq_fwspec *gfwspec,
-					     unsigned int parent_hwirq,
-					     unsigned int parent_type)
-{
-	struct irq_fwspec *fwspec = &gfwspec->fwspec;
-
-	fwspec->fwnode = chip->irq.parent_domain->fwnode;
-	fwspec->param_count = 2;
-	fwspec->param[0] = parent_hwirq;
-	fwspec->param[1] = parent_type;
-
-	return 0;
-}
-
 static void rzg2l_gpio_irq_restore(struct rzg2l_pinctrl *pctrl)
 {
 	struct irq_domain *domain = pctrl->gpio_chip.irq.domain;
@@ -2649,7 +2634,7 @@ static int rzg2l_gpio_register(struct rzg2l_pinctrl *pctrl)
 	girq->fwnode = dev_fwnode(pctrl->dev);
 	girq->parent_domain = parent_domain;
 	girq->child_to_parent_hwirq = rzg2l_gpio_child_to_parent_hwirq;
-	girq->populate_parent_alloc_arg = rzg2l_gpio_populate_parent_fwspec;
+	girq->populate_parent_alloc_arg = gpiochip_populate_parent_fwspec_twocell;
 	girq->child_irq_domain_ops.free = rzg2l_gpio_irq_domain_free;
 	girq->init_valid_mask = rzg2l_init_irq_valid_mask;
 

From 1aad42abae6b9ec104bec5d0ae496f2dc248dd28 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 22 Oct 2024 08:42:45 +0200
Subject: [PATCH 0628/1530] dt-bindings: pinctrl:
 qcom,sm8650-lpass-lpi-pinctrl: Add SM8750

Document compatible for Qualcomm SM8750 SoC LPASS TLMM pin controller,
fully compatible with previous SM8650 generation (same amount of pins
and functions).

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/20241022064245.22983-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml     | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml
index db72143623018..e90a5274647df 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml
@@ -16,7 +16,11 @@ description:
 
 properties:
   compatible:
-    const: qcom,sm8650-lpass-lpi-pinctrl
+    oneOf:
+      - const: qcom,sm8650-lpass-lpi-pinctrl
+      - items:
+          - const: qcom,sm8750-lpass-lpi-pinctrl
+          - const: qcom,sm8650-lpass-lpi-pinctrl
 
   reg:
     items:

From 2b3933b1e0a0a4b758fbc164bb31db0c113a7e2c Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Mon, 23 Sep 2024 10:13:11 -0700
Subject: [PATCH 0629/1530] fuse: enable dynamic configuration of fuse max
 pages limit (FUSE_MAX_MAX_PAGES)

Introduce the capability to dynamically configure the max pages limit
(FUSE_MAX_MAX_PAGES) through a sysctl. This allows system administrators
to dynamically set the maximum number of pages that can be used for
servicing requests in fuse.

Previously, this is gated by FUSE_MAX_MAX_PAGES which is statically set
to 256 pages. One result of this is that the buffer size for a write
request is limited to 1 MiB on a 4k-page system.

The default value for this sysctl is the original limit (256 pages).

$ sysctl -a | grep max_pages_limit
fs.fuse.max_pages_limit = 256

$ sysctl -n fs.fuse.max_pages_limit
256

$ echo 1024 | sudo tee /proc/sys/fs/fuse/max_pages_limit
1024

$ sysctl -n fs.fuse.max_pages_limit
1024

$ echo 65536 | sudo tee /proc/sys/fs/fuse/max_pages_limit
tee: /proc/sys/fs/fuse/max_pages_limit: Invalid argument

$ echo 0 | sudo tee /proc/sys/fs/fuse/max_pages_limit
tee: /proc/sys/fs/fuse/max_pages_limit: Invalid argument

$ echo 65535 | sudo tee /proc/sys/fs/fuse/max_pages_limit
65535

$ sysctl -n fs.fuse.max_pages_limit
65535

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Sweet Tea Dorminy <sweettea-kernel@dorminy.me>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 Documentation/admin-guide/sysctl/fs.rst | 10 +++++++
 fs/fuse/Makefile                        |  1 +
 fs/fuse/fuse_i.h                        | 14 +++++++--
 fs/fuse/inode.c                         | 11 ++++++-
 fs/fuse/ioctl.c                         |  4 ++-
 fs/fuse/sysctl.c                        | 40 +++++++++++++++++++++++++
 6 files changed, 75 insertions(+), 5 deletions(-)
 create mode 100644 fs/fuse/sysctl.c

diff --git a/Documentation/admin-guide/sysctl/fs.rst b/Documentation/admin-guide/sysctl/fs.rst
index 47499a1742bd4..fa25d7e718b37 100644
--- a/Documentation/admin-guide/sysctl/fs.rst
+++ b/Documentation/admin-guide/sysctl/fs.rst
@@ -332,3 +332,13 @@ Each "watch" costs roughly 90 bytes on a 32-bit kernel, and roughly 160 bytes
 on a 64-bit one.
 The current default value for ``max_user_watches`` is 4% of the
 available low memory, divided by the "watch" cost in bytes.
+
+5. /proc/sys/fs/fuse - Configuration options for FUSE filesystems
+=====================================================================
+
+This directory contains the following configuration options for FUSE
+filesystems:
+
+``/proc/sys/fs/fuse/max_pages_limit`` is a read/write file for
+setting/getting the maximum number of pages that can be used for servicing
+requests in FUSE.
diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile
index ce0ff7a9007b9..2c372180d631e 100644
--- a/fs/fuse/Makefile
+++ b/fs/fuse/Makefile
@@ -14,5 +14,6 @@ fuse-y := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o ioctl.o
 fuse-y += iomode.o
 fuse-$(CONFIG_FUSE_DAX) += dax.o
 fuse-$(CONFIG_FUSE_PASSTHROUGH) += passthrough.o
+fuse-$(CONFIG_SYSCTL) += sysctl.o
 
 virtiofs-y := virtio_fs.o
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index e6cc3d552b138..7ff00bae4a845 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -35,9 +35,6 @@
 /** Default max number of pages that can be used in a single read request */
 #define FUSE_DEFAULT_MAX_PAGES_PER_REQ 32
 
-/** Maximum of max_pages received in init_out */
-#define FUSE_MAX_MAX_PAGES 256
-
 /** Bias for fi->writectr, meaning new writepages must not be sent */
 #define FUSE_NOWRITE INT_MIN
 
@@ -47,6 +44,9 @@
 /** Number of dentries for each connection in the control filesystem */
 #define FUSE_CTL_NUM_DENTRIES 5
 
+/** Maximum of max_pages received in init_out */
+extern unsigned int fuse_max_pages_limit;
+
 /** List of active connections */
 extern struct list_head fuse_conn_list;
 
@@ -1480,4 +1480,12 @@ ssize_t fuse_passthrough_splice_write(struct pipe_inode_info *pipe,
 				      size_t len, unsigned int flags);
 ssize_t fuse_passthrough_mmap(struct file *file, struct vm_area_struct *vma);
 
+#ifdef CONFIG_SYSCTL
+extern int fuse_sysctl_register(void);
+extern void fuse_sysctl_unregister(void);
+#else
+#define fuse_sysctl_register()		(0)
+#define fuse_sysctl_unregister()	do { } while (0)
+#endif /* CONFIG_SYSCTL */
+
 #endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index fd3321e29a3e5..f1779ff3f8d19 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -35,6 +35,8 @@ DEFINE_MUTEX(fuse_mutex);
 
 static int set_global_limit(const char *val, const struct kernel_param *kp);
 
+unsigned int fuse_max_pages_limit = 256;
+
 unsigned max_user_bgreq;
 module_param_call(max_user_bgreq, set_global_limit, param_get_uint,
 		  &max_user_bgreq, 0644);
@@ -944,7 +946,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
 	fc->pid_ns = get_pid_ns(task_active_pid_ns(current));
 	fc->user_ns = get_user_ns(user_ns);
 	fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ;
-	fc->max_pages_limit = FUSE_MAX_MAX_PAGES;
+	fc->max_pages_limit = fuse_max_pages_limit;
 
 	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
 		fuse_backing_files_init(fc);
@@ -2063,8 +2065,14 @@ static int __init fuse_fs_init(void)
 	if (err)
 		goto out3;
 
+	err = fuse_sysctl_register();
+	if (err)
+		goto out4;
+
 	return 0;
 
+ out4:
+	unregister_filesystem(&fuse_fs_type);
  out3:
 	unregister_fuseblk();
  out2:
@@ -2075,6 +2083,7 @@ static int __init fuse_fs_init(void)
 
 static void fuse_fs_cleanup(void)
 {
+	fuse_sysctl_unregister();
 	unregister_filesystem(&fuse_fs_type);
 	unregister_fuseblk();
 
diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c
index 572ce8a82ceb9..a6c8ee5516351 100644
--- a/fs/fuse/ioctl.c
+++ b/fs/fuse/ioctl.c
@@ -10,6 +10,8 @@
 #include <linux/fileattr.h>
 #include <linux/fsverity.h>
 
+#define FUSE_VERITY_ENABLE_ARG_MAX_PAGES 256
+
 static ssize_t fuse_send_ioctl(struct fuse_mount *fm, struct fuse_args *args,
 			       struct fuse_ioctl_out *outarg)
 {
@@ -140,7 +142,7 @@ static int fuse_setup_enable_verity(unsigned long arg, struct iovec *iov,
 {
 	struct fsverity_enable_arg enable;
 	struct fsverity_enable_arg __user *uarg = (void __user *)arg;
-	const __u32 max_buffer_len = FUSE_MAX_MAX_PAGES * PAGE_SIZE;
+	const __u32 max_buffer_len = FUSE_VERITY_ENABLE_ARG_MAX_PAGES * PAGE_SIZE;
 
 	if (copy_from_user(&enable, uarg, sizeof(enable)))
 		return -EFAULT;
diff --git a/fs/fuse/sysctl.c b/fs/fuse/sysctl.c
new file mode 100644
index 0000000000000..b272bb333005a
--- /dev/null
+++ b/fs/fuse/sysctl.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/fs/fuse/fuse_sysctl.c
+ *
+ * Sysctl interface to fuse parameters
+ */
+#include <linux/sysctl.h>
+
+#include "fuse_i.h"
+
+static struct ctl_table_header *fuse_table_header;
+
+/* Bound by fuse_init_out max_pages, which is a u16 */
+static unsigned int sysctl_fuse_max_pages_limit = 65535;
+
+static struct ctl_table fuse_sysctl_table[] = {
+	{
+		.procname	= "max_pages_limit",
+		.data		= &fuse_max_pages_limit,
+		.maxlen		= sizeof(fuse_max_pages_limit),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= &sysctl_fuse_max_pages_limit,
+	},
+};
+
+int fuse_sysctl_register(void)
+{
+	fuse_table_header = register_sysctl("fs/fuse", fuse_sysctl_table);
+	if (!fuse_table_header)
+		return -ENOMEM;
+	return 0;
+}
+
+void fuse_sysctl_unregister(void)
+{
+	unregister_sysctl_table(fuse_table_header);
+	fuse_table_header = NULL;
+}

From cc23d537e56153560bb2f88fd826675a5a8c6af6 Mon Sep 17 00:00:00 2001
From: yangyun <yangyun50@huawei.com>
Date: Mon, 26 Aug 2024 21:06:12 +0800
Subject: [PATCH 0630/1530] fuse: remove useless IOCB_DIRECT in
 fuse_direct_read/write_iter

Commit 23c94e1cdcbf ("fuse: Switch to using async direct IO
for FOPEN_DIRECT_IO") gave the async direct IO code path in the
fuse_direct_read_iter() and fuse_direct_write_iter(). But since
these two functions are only called under FOPEN_DIRECT_IO is set,
it seems that we can also use the async direct IO even the flag
IOCB_DIRECT is not set to enjoy the async direct IO method. Also
move the definition of fuse_io_priv to where it is used in fuse_
direct_write_iter.

Signed-off-by: yangyun <yangyun50@huawei.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index dafdf766b1d53..5d240d8f1d5a4 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1650,7 +1650,7 @@ static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	ssize_t res;
 
-	if (!is_sync_kiocb(iocb) && iocb->ki_flags & IOCB_DIRECT) {
+	if (!is_sync_kiocb(iocb)) {
 		res = fuse_direct_IO(iocb, to);
 	} else {
 		struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb);
@@ -1664,7 +1664,6 @@ static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to)
 static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
-	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb);
 	ssize_t res;
 	bool exclusive;
 
@@ -1672,9 +1671,11 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	res = generic_write_checks(iocb, from);
 	if (res > 0) {
 		task_io_account_write(res);
-		if (!is_sync_kiocb(iocb) && iocb->ki_flags & IOCB_DIRECT) {
+		if (!is_sync_kiocb(iocb)) {
 			res = fuse_direct_IO(iocb, from);
 		} else {
+			struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb);
+
 			res = fuse_direct_io(&io, from, &iocb->ki_pos,
 					     FUSE_DIO_WRITE);
 			fuse_write_update_attr(inode, iocb->ki_pos, res);

From 41748675c0bf252b3c5f600a95830f0936d366c1 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Sat, 31 Aug 2024 17:37:49 +0800
Subject: [PATCH 0631/1530] virtiofs: use pages instead of pointer for kernel
 direct IO

When trying to insert a 10MB kernel module kept in a virtio-fs with cache
disabled, the following warning was reported:

  ------------[ cut here ]------------
  WARNING: CPU: 1 PID: 404 at mm/page_alloc.c:4551 ......
  Modules linked in:
  CPU: 1 PID: 404 Comm: insmod Not tainted 6.9.0-rc5+ #123
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) ......
  RIP: 0010:__alloc_pages+0x2bf/0x380
  ......
  Call Trace:
   <TASK>
   ? __warn+0x8e/0x150
   ? __alloc_pages+0x2bf/0x380
   __kmalloc_large_node+0x86/0x160
   __kmalloc+0x33c/0x480
   virtio_fs_enqueue_req+0x240/0x6d0
   virtio_fs_wake_pending_and_unlock+0x7f/0x190
   queue_request_and_unlock+0x55/0x60
   fuse_simple_request+0x152/0x2b0
   fuse_direct_io+0x5d2/0x8c0
   fuse_file_read_iter+0x121/0x160
   __kernel_read+0x151/0x2d0
   kernel_read+0x45/0x50
   kernel_read_file+0x1a9/0x2a0
   init_module_from_file+0x6a/0xe0
   idempotent_init_module+0x175/0x230
   __x64_sys_finit_module+0x5d/0xb0
   x64_sys_call+0x1c3/0x9e0
   do_syscall_64+0x3d/0xc0
   entry_SYSCALL_64_after_hwframe+0x4b/0x53
   ......
   </TASK>
  ---[ end trace 0000000000000000 ]---

The warning is triggered as follows:

1) syscall finit_module() handles the module insertion and it invokes
kernel_read_file() to read the content of the module first.

2) kernel_read_file() allocates a 10MB buffer by using vmalloc() and
passes it to kernel_read(). kernel_read() constructs a kvec iter by
using iov_iter_kvec() and passes it to fuse_file_read_iter().

3) virtio-fs disables the cache, so fuse_file_read_iter() invokes
fuse_direct_io(). As for now, the maximal read size for kvec iter is
only limited by fc->max_read. For virtio-fs, max_read is UINT_MAX, so
fuse_direct_io() doesn't split the 10MB buffer. It saves the address and
the size of the 10MB-sized buffer in out_args[0] of a fuse request and
passes the fuse request to virtio_fs_wake_pending_and_unlock().

4) virtio_fs_wake_pending_and_unlock() uses virtio_fs_enqueue_req() to
queue the request. Because virtiofs need DMA-able address, so
virtio_fs_enqueue_req() uses kmalloc() to allocate a bounce buffer for
all fuse args, copies these args into the bounce buffer and passed the
physical address of the bounce buffer to virtiofsd. The total length of
these fuse args for the passed fuse request is about 10MB, so
copy_args_to_argbuf() invokes kmalloc() with a 10MB size parameter and
it triggers the warning in __alloc_pages():

	if (WARN_ON_ONCE_GFP(order > MAX_PAGE_ORDER, gfp))
		return NULL;

5) virtio_fs_enqueue_req() will retry the memory allocation in a
kworker, but it won't help, because kmalloc() will always return NULL
due to the abnormal size and finit_module() will hang forever.

A feasible solution is to limit the value of max_read for virtio-fs, so
the length passed to kmalloc() will be limited. However it will affect
the maximal read size for normal read. And for virtio-fs write initiated
from kernel, it has the similar problem but now there is no way to limit
fc->max_write in kernel.

So instead of limiting both the values of max_read and max_write in
kernel, introducing use_pages_for_kvec_io in fuse_conn and setting it as
true in virtiofs. When use_pages_for_kvec_io is enabled, fuse will use
pages instead of pointer to pass the KVEC_IO data.

After switching to pages for KVEC_IO data, these pages will be used for
DMA through virtio-fs. If these pages are backed by vmalloc(),
{flush|invalidate}_kernel_vmap_range() are necessary to flush or
invalidate the cache before the DMA operation. So add two new fields in
fuse_args_pages to record the base address of vmalloc area and the
condition indicating whether invalidation is needed. Perform the flush
in fuse_get_user_pages() for write operations and the invalidation in
fuse_release_user_pages() for read operations.

It may seem necessary to introduce another field in fuse_conn to
indicate that these KVEC_IO pages are used for DMA, However, considering
that virtio-fs is currently the only user of use_pages_for_kvec_io, just
reuse use_pages_for_kvec_io to indicate that these pages will be used
for DMA.

Fixes: a62a8ef9d97d ("virtio-fs: add virtiofs filesystem")
Signed-off-by: Hou Tao <houtao1@huawei.com>
Tested-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c      | 62 +++++++++++++++++++++++++++++++--------------
 fs/fuse/fuse_i.h    |  6 +++++
 fs/fuse/virtio_fs.c |  1 +
 3 files changed, 50 insertions(+), 19 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 5d240d8f1d5a4..1943945c7370c 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -645,7 +645,7 @@ void fuse_read_args_fill(struct fuse_io_args *ia, struct file *file, loff_t pos,
 	args->out_args[0].size = count;
 }
 
-static void fuse_release_user_pages(struct fuse_args_pages *ap,
+static void fuse_release_user_pages(struct fuse_args_pages *ap, ssize_t nres,
 				    bool should_dirty)
 {
 	unsigned int i;
@@ -656,6 +656,9 @@ static void fuse_release_user_pages(struct fuse_args_pages *ap,
 		if (ap->args.is_pinned)
 			unpin_user_page(ap->pages[i]);
 	}
+
+	if (nres > 0 && ap->args.invalidate_vmap)
+		invalidate_kernel_vmap_range(ap->args.vmap_base, nres);
 }
 
 static void fuse_io_release(struct kref *kref)
@@ -754,25 +757,29 @@ static void fuse_aio_complete_req(struct fuse_mount *fm, struct fuse_args *args,
 	struct fuse_io_args *ia = container_of(args, typeof(*ia), ap.args);
 	struct fuse_io_priv *io = ia->io;
 	ssize_t pos = -1;
-
-	fuse_release_user_pages(&ia->ap, io->should_dirty);
+	size_t nres;
 
 	if (err) {
 		/* Nothing */
 	} else if (io->write) {
 		if (ia->write.out.size > ia->write.in.size) {
 			err = -EIO;
-		} else if (ia->write.in.size != ia->write.out.size) {
-			pos = ia->write.in.offset - io->offset +
-				ia->write.out.size;
+		} else {
+			nres = ia->write.out.size;
+			if (ia->write.in.size != ia->write.out.size)
+				pos = ia->write.in.offset - io->offset +
+				      ia->write.out.size;
 		}
 	} else {
 		u32 outsize = args->out_args[0].size;
 
+		nres = outsize;
 		if (ia->read.in.size != outsize)
 			pos = ia->read.in.offset - io->offset + outsize;
 	}
 
+	fuse_release_user_pages(&ia->ap, err ?: nres, io->should_dirty);
+
 	fuse_aio_complete(io, err, pos);
 	fuse_io_free(ia);
 }
@@ -1468,24 +1475,37 @@ static inline size_t fuse_get_frag_size(const struct iov_iter *ii,
 
 static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
 			       size_t *nbytesp, int write,
-			       unsigned int max_pages)
+			       unsigned int max_pages,
+			       bool use_pages_for_kvec_io)
 {
+	bool flush_or_invalidate = false;
 	size_t nbytes = 0;  /* # bytes already packed in req */
 	ssize_t ret = 0;
 
-	/* Special case for kernel I/O: can copy directly into the buffer */
+	/* Special case for kernel I/O: can copy directly into the buffer.
+	 * However if the implementation of fuse_conn requires pages instead of
+	 * pointer (e.g., virtio-fs), use iov_iter_extract_pages() instead.
+	 */
 	if (iov_iter_is_kvec(ii)) {
-		unsigned long user_addr = fuse_get_user_addr(ii);
-		size_t frag_size = fuse_get_frag_size(ii, *nbytesp);
+		void *user_addr = (void *)fuse_get_user_addr(ii);
 
-		if (write)
-			ap->args.in_args[1].value = (void *) user_addr;
-		else
-			ap->args.out_args[0].value = (void *) user_addr;
+		if (!use_pages_for_kvec_io) {
+			size_t frag_size = fuse_get_frag_size(ii, *nbytesp);
 
-		iov_iter_advance(ii, frag_size);
-		*nbytesp = frag_size;
-		return 0;
+			if (write)
+				ap->args.in_args[1].value = user_addr;
+			else
+				ap->args.out_args[0].value = user_addr;
+
+			iov_iter_advance(ii, frag_size);
+			*nbytesp = frag_size;
+			return 0;
+		}
+
+		if (is_vmalloc_addr(user_addr)) {
+			ap->args.vmap_base = user_addr;
+			flush_or_invalidate = true;
+		}
 	}
 
 	while (nbytes < *nbytesp && ap->num_pages < max_pages) {
@@ -1514,6 +1534,10 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
 			(PAGE_SIZE - ret) & (PAGE_SIZE - 1);
 	}
 
+	if (write && flush_or_invalidate)
+		flush_kernel_vmap_range(ap->args.vmap_base, nbytes);
+
+	ap->args.invalidate_vmap = !write && flush_or_invalidate;
 	ap->args.is_pinned = iov_iter_extract_will_pin(ii);
 	ap->args.user_pages = true;
 	if (write)
@@ -1582,7 +1606,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 		size_t nbytes = min(count, nmax);
 
 		err = fuse_get_user_pages(&ia->ap, iter, &nbytes, write,
-					  max_pages);
+					  max_pages, fc->use_pages_for_kvec_io);
 		if (err && !nbytes)
 			break;
 
@@ -1596,7 +1620,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 		}
 
 		if (!io->async || nres < 0) {
-			fuse_release_user_pages(&ia->ap, io->should_dirty);
+			fuse_release_user_pages(&ia->ap, nres, io->should_dirty);
 			fuse_io_free(ia);
 		}
 		ia = NULL;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 7ff00bae4a845..671daa4d07adb 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -309,9 +309,12 @@ struct fuse_args {
 	bool may_block:1;
 	bool is_ext:1;
 	bool is_pinned:1;
+	bool invalidate_vmap:1;
 	struct fuse_in_arg in_args[3];
 	struct fuse_arg out_args[2];
 	void (*end)(struct fuse_mount *fm, struct fuse_args *args, int error);
+	/* Used for kvec iter backed by vmalloc address */
+	void *vmap_base;
 };
 
 struct fuse_args_pages {
@@ -857,6 +860,9 @@ struct fuse_conn {
 	/** Passthrough support for read/write IO */
 	unsigned int passthrough:1;
 
+	/* Use pages instead of pointer for kernel I/O */
+	unsigned int use_pages_for_kvec_io:1;
+
 	/** Maximum stack depth for passthrough backing files */
 	int max_stack_depth;
 
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 6404a189e9890..d220e28e755fe 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -1691,6 +1691,7 @@ static int virtio_fs_get_tree(struct fs_context *fsc)
 	fc->delete_stale = true;
 	fc->auto_submounts = true;
 	fc->sync_fs = true;
+	fc->use_pages_for_kvec_io = true;
 
 	/* Tell FUSE to split requests that exceed the virtqueue's size */
 	fc->max_pages_limit = min_t(unsigned int, fc->max_pages_limit,

From 86b74eb5a11e878151eb429c3810f1dcda090b8c Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Sat, 31 Aug 2024 17:37:50 +0800
Subject: [PATCH 0632/1530] virtiofs: use GFP_NOFS when enqueuing request
 through kworker

When invoking virtio_fs_enqueue_req() through kworker, both the
allocation of the sg array and the bounce buffer still use GFP_ATOMIC.
Considering the size of the sg array may be greater than PAGE_SIZE, use
GFP_NOFS instead of GFP_ATOMIC to lower the possibility of memory
allocation failure and to avoid unnecessarily depleting the atomic
reserves. GFP_NOFS is not passed to virtio_fs_enqueue_req() directly,
GFP_KERNEL and memalloc_nofs_{save|restore} helpers are used instead.

It may seem OK to pass GFP_NOFS to virtio_fs_enqueue_req() as well when
queuing the request for the first time, but this is not the case. The
reason is that fuse_request_queue_background() may call
->queue_request_and_unlock() while holding fc->bg_lock, which is a
spin-lock. Therefore, still use GFP_ATOMIC for it.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Reviewed-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/virtio_fs.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index d220e28e755fe..f685278919292 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -97,7 +97,8 @@ struct virtio_fs_req_work {
 };
 
 static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
-				 struct fuse_req *req, bool in_flight);
+				 struct fuse_req *req, bool in_flight,
+				 gfp_t gfp);
 
 static const struct constant_table dax_param_enums[] = {
 	{"always",	FUSE_DAX_ALWAYS },
@@ -575,6 +576,8 @@ static void virtio_fs_request_dispatch_work(struct work_struct *work)
 
 	/* Dispatch pending requests */
 	while (1) {
+		unsigned int flags;
+
 		spin_lock(&fsvq->lock);
 		req = list_first_entry_or_null(&fsvq->queued_reqs,
 					       struct fuse_req, list);
@@ -585,7 +588,9 @@ static void virtio_fs_request_dispatch_work(struct work_struct *work)
 		list_del_init(&req->list);
 		spin_unlock(&fsvq->lock);
 
-		ret = virtio_fs_enqueue_req(fsvq, req, true);
+		flags = memalloc_nofs_save();
+		ret = virtio_fs_enqueue_req(fsvq, req, true, GFP_KERNEL);
+		memalloc_nofs_restore(flags);
 		if (ret < 0) {
 			if (ret == -ENOSPC) {
 				spin_lock(&fsvq->lock);
@@ -686,7 +691,7 @@ static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
 }
 
 /* Allocate and copy args into req->argbuf */
-static int copy_args_to_argbuf(struct fuse_req *req)
+static int copy_args_to_argbuf(struct fuse_req *req, gfp_t gfp)
 {
 	struct fuse_args *args = req->args;
 	unsigned int offset = 0;
@@ -700,7 +705,7 @@ static int copy_args_to_argbuf(struct fuse_req *req)
 	len = fuse_len_args(num_in, (struct fuse_arg *) args->in_args) +
 	      fuse_len_args(num_out, args->out_args);
 
-	req->argbuf = kmalloc(len, GFP_ATOMIC);
+	req->argbuf = kmalloc(len, gfp);
 	if (!req->argbuf)
 		return -ENOMEM;
 
@@ -1366,7 +1371,8 @@ static unsigned int sg_init_fuse_args(struct scatterlist *sg,
 
 /* Add a request to a virtqueue and kick the device */
 static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
-				 struct fuse_req *req, bool in_flight)
+				 struct fuse_req *req, bool in_flight,
+				 gfp_t gfp)
 {
 	/* requests need at least 4 elements */
 	struct scatterlist *stack_sgs[6];
@@ -1387,8 +1393,8 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
 	/* Does the sglist fit on the stack? */
 	total_sgs = sg_count_fuse_req(req);
 	if (total_sgs > ARRAY_SIZE(stack_sgs)) {
-		sgs = kmalloc_array(total_sgs, sizeof(sgs[0]), GFP_ATOMIC);
-		sg = kmalloc_array(total_sgs, sizeof(sg[0]), GFP_ATOMIC);
+		sgs = kmalloc_array(total_sgs, sizeof(sgs[0]), gfp);
+		sg = kmalloc_array(total_sgs, sizeof(sg[0]), gfp);
 		if (!sgs || !sg) {
 			ret = -ENOMEM;
 			goto out;
@@ -1396,7 +1402,7 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
 	}
 
 	/* Use a bounce buffer since stack args cannot be mapped */
-	ret = copy_args_to_argbuf(req);
+	ret = copy_args_to_argbuf(req, gfp);
 	if (ret < 0)
 		goto out;
 
@@ -1490,7 +1496,7 @@ static void virtio_fs_send_req(struct fuse_iqueue *fiq, struct fuse_req *req)
 		 queue_id);
 
 	fsvq = &fs->vqs[queue_id];
-	ret = virtio_fs_enqueue_req(fsvq, req, false);
+	ret = virtio_fs_enqueue_req(fsvq, req, false, GFP_ATOMIC);
 	if (ret < 0) {
 		if (ret == -ENOSPC) {
 			/*

From aaa32429da09a9afa0f54a197733d757334ed169 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 30 Sep 2024 09:45:09 -0400
Subject: [PATCH 0633/1530] fuse: use fuse_range_is_writeback() instead of
 iterating pages

fuse_send_readpages() waits for writeback on each page.  This can be
replaced by a single call to fuse_range_is_writeback().

[SzM: split this off from "fuse: convert readahead to use folios"]

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 1943945c7370c..f495ddd9e9ad9 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -992,12 +992,17 @@ static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
 static void fuse_readahead(struct readahead_control *rac)
 {
 	struct inode *inode = rac->mapping->host;
+	struct fuse_inode *fi = get_fuse_inode(inode);
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	unsigned int i, max_pages, nr_pages = 0;
+	pgoff_t first = readahead_index(rac);
+	pgoff_t last = first + readahead_count(rac) - 1;
 
 	if (fuse_is_bad(inode))
 		return;
 
+	wait_event(fi->page_waitq, !fuse_range_is_writeback(inode, first, last));
+
 	max_pages = min_t(unsigned int, fc->max_pages,
 			fc->max_read / PAGE_SIZE);
 
@@ -1024,8 +1029,6 @@ static void fuse_readahead(struct readahead_control *rac)
 		ap = &ia->ap;
 		nr_pages = __readahead_batch(rac, ap->pages, nr_pages);
 		for (i = 0; i < nr_pages; i++) {
-			fuse_wait_on_page_writeback(inode,
-						    readahead_index(rac) + i);
 			ap->descs[i].length = PAGE_SIZE;
 		}
 		ap->num_pages = nr_pages;

From 3eab9d7bc2f4ae7f3f9c9c7852ff61600df79856 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 30 Sep 2024 09:45:09 -0400
Subject: [PATCH 0634/1530] fuse: convert readahead to use folios

Currently we're using the __readahead_batch() helper which populates our
fuse_args_pages->pages array with pages.  Convert this to use the newer
folio based pattern which is to call readahead_folio() to get the next
folio in the read ahead batch.  I've updated the code to use things like
folio_size() and to take into account larger folio sizes, but this is
purely to make that eventual work easier to do, we currently will not
get large folios so this is more future proofing than actual support.

[SzM: remove check for readahead_folio() won't return NULL (at least for
now) so remove ugly assign in conditional.]

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c | 36 +++++++++++++++++++++++-------------
 1 file changed, 23 insertions(+), 13 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index f495ddd9e9ad9..2e7ecbf8e4278 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -945,7 +945,6 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
 		struct folio *folio = page_folio(ap->pages[i]);
 
 		folio_end_read(folio, !err);
-		folio_put(folio);
 	}
 	if (ia->ff)
 		fuse_file_put(ia->ff, false);
@@ -994,7 +993,7 @@ static void fuse_readahead(struct readahead_control *rac)
 	struct inode *inode = rac->mapping->host;
 	struct fuse_inode *fi = get_fuse_inode(inode);
 	struct fuse_conn *fc = get_fuse_conn(inode);
-	unsigned int i, max_pages, nr_pages = 0;
+	unsigned int max_pages, nr_pages;
 	pgoff_t first = readahead_index(rac);
 	pgoff_t last = first + readahead_count(rac) - 1;
 
@@ -1006,9 +1005,22 @@ static void fuse_readahead(struct readahead_control *rac)
 	max_pages = min_t(unsigned int, fc->max_pages,
 			fc->max_read / PAGE_SIZE);
 
-	for (;;) {
+	/*
+	 * This is only accurate the first time through, since readahead_folio()
+	 * doesn't update readahead_count() from the previous folio until the
+	 * next call.  Grab nr_pages here so we know how many pages we're going
+	 * to have to process.  This means that we will exit here with
+	 * readahead_count() == folio_nr_pages(last_folio), but we will have
+	 * consumed all of the folios, and read_pages() will call
+	 * readahead_folio() again which will clean up the rac.
+	 */
+	nr_pages = readahead_count(rac);
+
+	while (nr_pages) {
 		struct fuse_io_args *ia;
 		struct fuse_args_pages *ap;
+		struct folio *folio;
+		unsigned cur_pages = min(max_pages, nr_pages);
 
 		if (fc->num_background >= fc->congestion_threshold &&
 		    rac->ra->async_size >= readahead_count(rac))
@@ -1018,21 +1030,19 @@ static void fuse_readahead(struct readahead_control *rac)
 			 */
 			break;
 
-		nr_pages = readahead_count(rac) - nr_pages;
-		if (nr_pages > max_pages)
-			nr_pages = max_pages;
-		if (nr_pages == 0)
-			break;
-		ia = fuse_io_alloc(NULL, nr_pages);
+		ia = fuse_io_alloc(NULL, cur_pages);
 		if (!ia)
 			return;
 		ap = &ia->ap;
-		nr_pages = __readahead_batch(rac, ap->pages, nr_pages);
-		for (i = 0; i < nr_pages; i++) {
-			ap->descs[i].length = PAGE_SIZE;
+
+		while (ap->num_pages < cur_pages) {
+			folio = readahead_folio(rac);
+			ap->pages[ap->num_pages] = &folio->page;
+			ap->descs[ap->num_pages].length = folio_size(folio);
+			ap->num_pages++;
 		}
-		ap->num_pages = nr_pages;
 		fuse_send_readpages(ia, rac->file);
+		nr_pages -= cur_pages;
 	}
 }
 

From 785d06afc840922cced0c4e90f99209210dd6bd9 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 30 Sep 2024 09:45:10 -0400
Subject: [PATCH 0635/1530] fuse: convert fuse_send_write_pages to use folios

Convert this to grab the folio from the fuse_args_pages and use the
appropriate folio related functions.

Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 2e7ecbf8e4278..be6d07751ee5e 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1175,23 +1175,23 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia,
 	offset = ap->descs[0].offset;
 	count = ia->write.out.size;
 	for (i = 0; i < ap->num_pages; i++) {
-		struct page *page = ap->pages[i];
+		struct folio *folio = page_folio(ap->pages[i]);
 
 		if (err) {
-			ClearPageUptodate(page);
+			folio_clear_uptodate(folio);
 		} else {
-			if (count >= PAGE_SIZE - offset)
-				count -= PAGE_SIZE - offset;
+			if (count >= folio_size(folio) - offset)
+				count -= folio_size(folio) - offset;
 			else {
 				if (short_write)
-					ClearPageUptodate(page);
+					folio_clear_uptodate(folio);
 				count = 0;
 			}
 			offset = 0;
 		}
 		if (ia->write.page_locked && (i == ap->num_pages - 1))
-			unlock_page(page);
-		put_page(page);
+			folio_unlock(folio);
+		folio_put(folio);
 	}
 
 	return err;

From 9bafbe7ae01321eb1345daf0975355f890c975cf Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 30 Sep 2024 09:45:11 -0400
Subject: [PATCH 0636/1530] fuse: convert fuse_fill_write_pages to use folios

Convert this to grab the folio directly, and update all the helpers to
use the folio related functions.

Reviewed-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index be6d07751ee5e..3e9a88af917c8 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1213,7 +1213,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 
 	do {
 		size_t tmp;
-		struct page *page;
+		struct folio *folio;
 		pgoff_t index = pos >> PAGE_SHIFT;
 		size_t bytes = min_t(size_t, PAGE_SIZE - offset,
 				     iov_iter_count(ii));
@@ -1225,25 +1225,27 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 		if (fault_in_iov_iter_readable(ii, bytes))
 			break;
 
-		err = -ENOMEM;
-		page = grab_cache_page_write_begin(mapping, index);
-		if (!page)
+		folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
+					    mapping_gfp_mask(mapping));
+		if (IS_ERR(folio)) {
+			err = PTR_ERR(folio);
 			break;
+		}
 
 		if (mapping_writably_mapped(mapping))
-			flush_dcache_page(page);
+			flush_dcache_folio(folio);
 
-		tmp = copy_page_from_iter_atomic(page, offset, bytes, ii);
-		flush_dcache_page(page);
+		tmp = copy_folio_from_iter_atomic(folio, offset, bytes, ii);
+		flush_dcache_folio(folio);
 
 		if (!tmp) {
-			unlock_page(page);
-			put_page(page);
+			folio_unlock(folio);
+			folio_put(folio);
 			goto again;
 		}
 
 		err = 0;
-		ap->pages[ap->num_pages] = page;
+		ap->pages[ap->num_pages] = &folio->page;
 		ap->descs[ap->num_pages].length = tmp;
 		ap->num_pages++;
 
@@ -1255,10 +1257,10 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 
 		/* If we copied full page, mark it uptodate */
 		if (tmp == PAGE_SIZE)
-			SetPageUptodate(page);
+			folio_mark_uptodate(folio);
 
-		if (PageUptodate(page)) {
-			unlock_page(page);
+		if (folio_test_uptodate(folio)) {
+			folio_unlock(folio);
 		} else {
 			ia->write.page_locked = true;
 			break;

From 184b6eb3645ad9e0e5ea8a1ac9e6a4fd501a4b45 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 30 Sep 2024 09:45:12 -0400
Subject: [PATCH 0637/1530] fuse: convert fuse_page_mkwrite to use folios

Convert this to grab the folio directly, and update all the helpers to
use the folio related functions.

Reviewed-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 3e9a88af917c8..add051e4ad308 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -483,6 +483,16 @@ static void fuse_wait_on_page_writeback(struct inode *inode, pgoff_t index)
 	wait_event(fi->page_waitq, !fuse_page_is_writeback(inode, index));
 }
 
+static void fuse_wait_on_folio_writeback(struct inode *inode,
+					 struct folio *folio)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	pgoff_t last = folio_next_index(folio) - 1;
+
+	wait_event(fi->page_waitq,
+		   !fuse_range_is_writeback(inode, folio_index(folio), last));
+}
+
 /*
  * Wait for all pending writepages on the inode to finish.
  *
@@ -2558,17 +2568,17 @@ static void fuse_vma_close(struct vm_area_struct *vma)
  */
 static vm_fault_t fuse_page_mkwrite(struct vm_fault *vmf)
 {
-	struct page *page = vmf->page;
+	struct folio *folio = page_folio(vmf->page);
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 
 	file_update_time(vmf->vma->vm_file);
-	lock_page(page);
-	if (page->mapping != inode->i_mapping) {
-		unlock_page(page);
+	folio_lock(folio);
+	if (folio->mapping != inode->i_mapping) {
+		folio_unlock(folio);
 		return VM_FAULT_NOPAGE;
 	}
 
-	fuse_wait_on_page_writeback(inode, page->index);
+	fuse_wait_on_folio_writeback(inode, folio);
 	return VM_FAULT_LOCKED;
 }
 

From e6befec5e901e06dd6c7c456a4e20d2529efb014 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 30 Sep 2024 09:45:13 -0400
Subject: [PATCH 0638/1530] fuse: use kiocb_modified in buffered write path

This combines the file_remove_privs() and file_update_time() call into
one call.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Bernd Schubert <bschubert@ddn.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index add051e4ad308..5ae8784efe024 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1462,11 +1462,7 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 	task_io_account_write(count);
 
-	err = file_remove_privs(file);
-	if (err)
-		goto out;
-
-	err = file_update_time(file);
+	err = kiocb_modified(iocb);
 	if (err)
 		goto out;
 

From 65fe891d9005a41de2fccfd5ced3c0bf6f1e3bcd Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 30 Sep 2024 09:45:14 -0400
Subject: [PATCH 0639/1530] fuse: convert fuse_do_readpage to use folios

Now that the buffered write path is using folios, convert
fuse_do_readpage() to take a folio instead of a page, update it to use
the appropriate folio helpers, and update the callers to pass in the
folio directly instead of a page.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 5ae8784efe024..efb5e5ccbe337 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -865,12 +865,13 @@ static void fuse_short_read(struct inode *inode, u64 attr_ver, size_t num_read,
 	}
 }
 
-static int fuse_do_readpage(struct file *file, struct page *page)
+static int fuse_do_readfolio(struct file *file, struct folio *folio)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 	struct fuse_mount *fm = get_fuse_mount(inode);
-	loff_t pos = page_offset(page);
+	loff_t pos = folio_pos(folio);
 	struct fuse_page_desc desc = { .length = PAGE_SIZE };
+	struct page *page = &folio->page;
 	struct fuse_io_args ia = {
 		.ap.args.page_zeroing = true,
 		.ap.args.out_pages = true,
@@ -882,11 +883,11 @@ static int fuse_do_readpage(struct file *file, struct page *page)
 	u64 attr_ver;
 
 	/*
-	 * Page writeback can extend beyond the lifetime of the
-	 * page-cache page, so make sure we read a properly synced
-	 * page.
+	 * With the temporary pages that are used to complete writeback, we can
+	 * have writeback that extends beyond the lifetime of the folio.  So
+	 * make sure we read a properly synced folio.
 	 */
-	fuse_wait_on_page_writeback(inode, page->index);
+	fuse_wait_on_folio_writeback(inode, folio);
 
 	attr_ver = fuse_get_attr_version(fm->fc);
 
@@ -904,25 +905,24 @@ static int fuse_do_readpage(struct file *file, struct page *page)
 	if (res < desc.length)
 		fuse_short_read(inode, attr_ver, res, &ia.ap);
 
-	SetPageUptodate(page);
+	folio_mark_uptodate(folio);
 
 	return 0;
 }
 
 static int fuse_read_folio(struct file *file, struct folio *folio)
 {
-	struct page *page = &folio->page;
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 	int err;
 
 	err = -EIO;
 	if (fuse_is_bad(inode))
 		goto out;
 
-	err = fuse_do_readpage(file, page);
+	err = fuse_do_readfolio(file, folio);
 	fuse_invalidate_atime(inode);
  out:
-	unlock_page(page);
+	folio_unlock(folio);
 	return err;
 }
 
@@ -2475,7 +2475,7 @@ static int fuse_write_begin(struct file *file, struct address_space *mapping,
 			folio_zero_segment(folio, 0, off);
 		goto success;
 	}
-	err = fuse_do_readpage(file, &folio->page);
+	err = fuse_do_readfolio(file, folio);
 	if (err)
 		goto cleanup;
 success:

From 6930b8dac19ee86282222ea1cb559ee0602e4877 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 30 Sep 2024 09:45:15 -0400
Subject: [PATCH 0640/1530] fuse: convert fuse_writepage_need_send to take a
 folio

fuse_writepage_need_send is called by fuse_writepages_fill() which
already has a folio.  Change fuse_writepage_need_send() to take a folio
instead, add a helper to check if the folio range is under writeback and
use this, as well as the appropriate folio helpers in the rest of the
function.  Update fuse_writepage_need_send() to pass in the folio
directly.

Reviewed-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index efb5e5ccbe337..d4b5d46f7bceb 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -483,14 +483,19 @@ static void fuse_wait_on_page_writeback(struct inode *inode, pgoff_t index)
 	wait_event(fi->page_waitq, !fuse_page_is_writeback(inode, index));
 }
 
+static inline bool fuse_folio_is_writeback(struct inode *inode,
+					   struct folio *folio)
+{
+	pgoff_t last = folio_next_index(folio) - 1;
+	return fuse_range_is_writeback(inode, folio_index(folio), last);
+}
+
 static void fuse_wait_on_folio_writeback(struct inode *inode,
 					 struct folio *folio)
 {
 	struct fuse_inode *fi = get_fuse_inode(inode);
-	pgoff_t last = folio_next_index(folio) - 1;
 
-	wait_event(fi->page_waitq,
-		   !fuse_range_is_writeback(inode, folio_index(folio), last));
+	wait_event(fi->page_waitq, !fuse_folio_is_writeback(inode, folio));
 }
 
 /*
@@ -2288,7 +2293,7 @@ static bool fuse_writepage_add(struct fuse_writepage_args *new_wpa,
 	return false;
 }
 
-static bool fuse_writepage_need_send(struct fuse_conn *fc, struct page *page,
+static bool fuse_writepage_need_send(struct fuse_conn *fc, struct folio *folio,
 				     struct fuse_args_pages *ap,
 				     struct fuse_fill_wb_data *data)
 {
@@ -2300,7 +2305,7 @@ static bool fuse_writepage_need_send(struct fuse_conn *fc, struct page *page,
 	 * the pages are faulted with get_user_pages(), and then after the read
 	 * completed.
 	 */
-	if (fuse_page_is_writeback(data->inode, page->index))
+	if (fuse_folio_is_writeback(data->inode, folio))
 		return true;
 
 	/* Reached max pages */
@@ -2312,7 +2317,7 @@ static bool fuse_writepage_need_send(struct fuse_conn *fc, struct page *page,
 		return true;
 
 	/* Discontinuity */
-	if (data->orig_pages[ap->num_pages - 1]->index + 1 != page->index)
+	if (data->orig_pages[ap->num_pages - 1]->index + 1 != folio_index(folio))
 		return true;
 
 	/* Need to grow the pages array?  If so, did the expansion fail? */
@@ -2341,7 +2346,7 @@ static int fuse_writepages_fill(struct folio *folio,
 			goto out_unlock;
 	}
 
-	if (wpa && fuse_writepage_need_send(fc, &folio->page, ap, data)) {
+	if (wpa && fuse_writepage_need_send(fc, folio, ap, data)) {
 		fuse_writepages_send(data);
 		data->wpa = NULL;
 	}

From 949d67ac2eff129f1dbe2d6dc69f51f4f64281f2 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 30 Sep 2024 09:45:16 -0400
Subject: [PATCH 0641/1530] fuse: use the folio based vmstat helpers

In order to make it easier to switch to folios in the fuse_args_pages
update the places where we update the vmstat counters for writeback to
use the folio related helpers.  On the inc side this is easy as we
already have the folio, on the dec side we have to page_folio() the
pages for now.

Reviewed-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index d4b5d46f7bceb..ce67af163c9ae 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1820,12 +1820,12 @@ static void fuse_writepage_free(struct fuse_writepage_args *wpa)
 	kfree(wpa);
 }
 
-static void fuse_writepage_finish_stat(struct inode *inode, struct page *page)
+static void fuse_writepage_finish_stat(struct inode *inode, struct folio *folio)
 {
 	struct backing_dev_info *bdi = inode_to_bdi(inode);
 
 	dec_wb_stat(&bdi->wb, WB_WRITEBACK);
-	dec_node_page_state(page, NR_WRITEBACK_TEMP);
+	node_stat_sub_folio(folio, NR_WRITEBACK_TEMP);
 	wb_writeout_inc(&bdi->wb);
 }
 
@@ -1837,7 +1837,7 @@ static void fuse_writepage_finish(struct fuse_writepage_args *wpa)
 	int i;
 
 	for (i = 0; i < ap->num_pages; i++)
-		fuse_writepage_finish_stat(inode, ap->pages[i]);
+		fuse_writepage_finish_stat(inode, page_folio(ap->pages[i]));
 
 	wake_up(&fi->page_waitq);
 }
@@ -1892,7 +1892,8 @@ __acquires(fi->lock)
 	for (aux = wpa->next; aux; aux = next) {
 		next = aux->next;
 		aux->next = NULL;
-		fuse_writepage_finish_stat(aux->inode, aux->ia.ap.pages[0]);
+		fuse_writepage_finish_stat(aux->inode,
+					   page_folio(aux->ia.ap.pages[0]));
 		fuse_writepage_free(aux);
 	}
 
@@ -2112,7 +2113,7 @@ static void fuse_writepage_args_page_fill(struct fuse_writepage_args *wpa, struc
 	ap->descs[page_index].length = PAGE_SIZE;
 
 	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
-	inc_node_page_state(&tmp_folio->page, NR_WRITEBACK_TEMP);
+	node_stat_add_folio(tmp_folio, NR_WRITEBACK_TEMP);
 }
 
 static struct fuse_writepage_args *fuse_writepage_args_setup(struct folio *folio,
@@ -2286,7 +2287,8 @@ static bool fuse_writepage_add(struct fuse_writepage_args *new_wpa,
 	spin_unlock(&fi->lock);
 
 	if (tmp) {
-		fuse_writepage_finish_stat(new_wpa->inode, new_ap->pages[0]);
+		fuse_writepage_finish_stat(new_wpa->inode,
+					   page_folio(new_ap->pages[0]));
 		fuse_writepage_free(new_wpa);
 	}
 

From 71e10dc2f561b1f7cef5152a865813339e96d575 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 30 Sep 2024 09:45:17 -0400
Subject: [PATCH 0642/1530] fuse: convert fuse_retrieve to use folios

We're just looking for pages in a mapping, use a folio and the folio
lookup function directly instead of using the page helper.

Reviewed-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dev.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 1f64ae6d7a69e..a332cb7999672 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1756,15 +1756,15 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 	index = outarg->offset >> PAGE_SHIFT;
 
 	while (num && ap->num_pages < num_pages) {
-		struct page *page;
+		struct folio *folio;
 		unsigned int this_num;
 
-		page = find_get_page(mapping, index);
-		if (!page)
+		folio = filemap_get_folio(mapping, index);
+		if (IS_ERR(folio))
 			break;
 
 		this_num = min_t(unsigned, num, PAGE_SIZE - offset);
-		ap->pages[ap->num_pages] = page;
+		ap->pages[ap->num_pages] = &folio->page;
 		ap->descs[ap->num_pages].offset = offset;
 		ap->descs[ap->num_pages].length = this_num;
 		ap->num_pages++;

From 8807f117be9d15088003e63bfaf0533355371ee8 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 30 Sep 2024 09:45:18 -0400
Subject: [PATCH 0643/1530] fuse: convert fuse_notify_store to use folios

This function creates pages in an inode and copies data into them,
update the function to use a folio instead of a page, and use the
appropriate folio helpers.

[SzM: use filemap_grab_folio()]

[Hau Tao: The third argument of folio_zero_range() should be the length to
be zeroed, not the total length. Fix it by using folio_zero_segment()
instead in fuse_notify_store()]

Reviewed-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dev.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index a332cb7999672..e25804097ffbc 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1654,24 +1654,25 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
 
 	num = outarg.size;
 	while (num) {
+		struct folio *folio;
 		struct page *page;
 		unsigned int this_num;
 
-		err = -ENOMEM;
-		page = find_or_create_page(mapping, index,
-					   mapping_gfp_mask(mapping));
-		if (!page)
+		folio = filemap_grab_folio(mapping, index);
+		err = PTR_ERR(folio);
+		if (IS_ERR(folio))
 			goto out_iput;
 
-		this_num = min_t(unsigned, num, PAGE_SIZE - offset);
+		page = &folio->page;
+		this_num = min_t(unsigned, num, folio_size(folio) - offset);
 		err = fuse_copy_page(cs, &page, offset, this_num, 0);
-		if (!PageUptodate(page) && !err && offset == 0 &&
-		    (this_num == PAGE_SIZE || file_size == end)) {
-			zero_user_segment(page, this_num, PAGE_SIZE);
-			SetPageUptodate(page);
+		if (!folio_test_uptodate(folio) && !err && offset == 0 &&
+		    (this_num == folio_size(folio) || file_size == end)) {
+			folio_zero_segment(folio, this_num, folio_size(folio));
+			folio_mark_uptodate(folio);
 		}
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 
 		if (err)
 			goto out_iput;

From 10c58d7eea443c6961135a7f16f9fa03bf8e5823 Mon Sep 17 00:00:00 2001
From: SEO HOYOUNG <hy50.seo@samsung.com>
Date: Thu, 10 Oct 2024 16:52:28 +0900
Subject: [PATCH 0644/1530] scsi: ufs: core: check asymmetric connected lanes

Performance problems may occur if there is a problem with the asymmetric
connected lane such as h/w failure.  Currently, only check connected
lane for rx/tx is checked if it is not 0.  But it should also be checked
if it is asymmetrically connected.

Signed-off-by: SEO HOYOUNG <hy50.seo@samsung.com>
Link: https://lore.kernel.org/r/e82b4b65b5f6501a687c624dd06e5c362e160f32.1728544727.git.hy50.seo@samsung.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 9e6d008f4ea4a..945253eb590ee 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -4535,6 +4535,14 @@ static int ufshcd_get_max_pwr_mode(struct ufs_hba *hba)
 		return -EINVAL;
 	}
 
+	if (pwr_info->lane_rx != pwr_info->lane_tx) {
+		dev_err(hba->dev, "%s: asymmetric connected lanes. rx=%d, tx=%d\n",
+			__func__,
+				pwr_info->lane_rx,
+				pwr_info->lane_tx);
+		return -EINVAL;
+	}
+
 	/*
 	 * First, get the maximum gears of HS speed.
 	 * If a zero value, it means there is no HSGEAR capability.

From 6c1143bb5d122ec542b10288bfca183788c547e8 Mon Sep 17 00:00:00 2001
From: Avri Altman <avri.altman@wdc.com>
Date: Wed, 16 Oct 2024 13:21:41 +0300
Subject: [PATCH 0645/1530] scsi: ufs: core: Use ufshcd_wait_for_register() in
 HCE init

The current so called "inner loop" in ufshcd_hba_execute_hce() is open
coding ufshcd_wait_for_register(). Replace it by
ufshcd_wait_for_register().  This is a code simplification - no
functional change.

Signed-off-by: Avri Altman <avri.altman@wdc.com>
Link: https://lore.kernel.org/r/20241016102141.441382-1-avri.altman@wdc.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 67 ++++++++++++++++++---------------------
 1 file changed, 30 insertions(+), 37 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 945253eb590ee..f2b3e7e45ea29 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -4826,51 +4826,44 @@ EXPORT_SYMBOL_GPL(ufshcd_hba_stop);
  */
 static int ufshcd_hba_execute_hce(struct ufs_hba *hba)
 {
-	int retry_outer = 3;
-	int retry_inner;
+	int retry;
 
-start:
-	if (ufshcd_is_hba_active(hba))
-		/* change controller state to "reset state" */
-		ufshcd_hba_stop(hba);
+	for (retry = 3; retry > 0; retry--) {
+		if (ufshcd_is_hba_active(hba))
+			/* change controller state to "reset state" */
+			ufshcd_hba_stop(hba);
 
-	/* UniPro link is disabled at this point */
-	ufshcd_set_link_off(hba);
+		/* UniPro link is disabled at this point */
+		ufshcd_set_link_off(hba);
 
-	ufshcd_vops_hce_enable_notify(hba, PRE_CHANGE);
+		ufshcd_vops_hce_enable_notify(hba, PRE_CHANGE);
 
-	/* start controller initialization sequence */
-	ufshcd_hba_start(hba);
+		/* start controller initialization sequence */
+		ufshcd_hba_start(hba);
 
-	/*
-	 * To initialize a UFS host controller HCE bit must be set to 1.
-	 * During initialization the HCE bit value changes from 1->0->1.
-	 * When the host controller completes initialization sequence
-	 * it sets the value of HCE bit to 1. The same HCE bit is read back
-	 * to check if the controller has completed initialization sequence.
-	 * So without this delay the value HCE = 1, set in the previous
-	 * instruction might be read back.
-	 * This delay can be changed based on the controller.
-	 */
-	ufshcd_delay_us(hba->vps->hba_enable_delay_us, 100);
+		/*
+		 * To initialize a UFS host controller HCE bit must be set to 1.
+		 * During initialization the HCE bit value changes from 1->0->1.
+		 * When the host controller completes initialization sequence
+		 * it sets the value of HCE bit to 1. The same HCE bit is read back
+		 * to check if the controller has completed initialization sequence.
+		 * So without this delay the value HCE = 1, set in the previous
+		 * instruction might be read back.
+		 * This delay can be changed based on the controller.
+		 */
+		ufshcd_delay_us(hba->vps->hba_enable_delay_us, 100);
 
-	/* wait for the host controller to complete initialization */
-	retry_inner = 50;
-	while (!ufshcd_is_hba_active(hba)) {
-		if (retry_inner) {
-			retry_inner--;
-		} else {
-			dev_err(hba->dev,
-				"Controller enable failed\n");
-			if (retry_outer) {
-				retry_outer--;
-				goto start;
-			}
-			return -EIO;
-		}
-		usleep_range(1000, 1100);
+		/* wait for the host controller to complete initialization */
+		if (!ufshcd_wait_for_register(hba, REG_CONTROLLER_ENABLE, CONTROLLER_ENABLE,
+					      CONTROLLER_ENABLE, 1000, 50))
+			break;
+
+		dev_err(hba->dev, "Enabling the controller failed\n");
 	}
 
+	if (!retry)
+		return -EIO;
+
 	/* enable UIC related interrupts */
 	ufshcd_enable_intr(hba, UFSHCD_UIC_MASK);
 

From 78bc671bd1501e2f6c571e063301a4fdc5db53b2 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Fri, 18 Oct 2024 12:47:39 -0700
Subject: [PATCH 0646/1530] scsi: ufs: core: Make DMA mask configuration more
 flexible

Replace UFSHCD_QUIRK_BROKEN_64BIT_ADDRESS with
ufs_hba_variant_ops::set_dma_mask.  Update the Renesas driver
accordingly.  This patch enables supporting other configurations than
32-bit or 64-bit DMA addresses, e.g. 36-bit DMA addresses.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241018194753.775074-1-bvanassche@acm.org
Reviewed-by: Avri Altman <Avri.Altman@wdc.com>
Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c      | 4 ++--
 drivers/ufs/host/ufs-renesas.c | 9 ++++++++-
 include/ufs/ufshcd.h           | 9 +++------
 3 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index f2b3e7e45ea29..2877e487637d0 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -2401,8 +2401,6 @@ static inline int ufshcd_hba_capabilities(struct ufs_hba *hba)
 	int err;
 
 	hba->capabilities = ufshcd_readl(hba, REG_CONTROLLER_CAPABILITIES);
-	if (hba->quirks & UFSHCD_QUIRK_BROKEN_64BIT_ADDRESS)
-		hba->capabilities &= ~MASK_64_ADDRESSING_SUPPORT;
 
 	/* nutrs and nutmrs are 0 based values */
 	hba->nutrs = (hba->capabilities & MASK_TRANSFER_REQUESTS_SLOTS_SDB) + 1;
@@ -10315,6 +10313,8 @@ EXPORT_SYMBOL_GPL(ufshcd_dealloc_host);
  */
 static int ufshcd_set_dma_mask(struct ufs_hba *hba)
 {
+	if (hba->vops && hba->vops->set_dma_mask)
+		return hba->vops->set_dma_mask(hba);
 	if (hba->capabilities & MASK_64_ADDRESSING_SUPPORT) {
 		if (!dma_set_mask_and_coherent(hba->dev, DMA_BIT_MASK(64)))
 			return 0;
diff --git a/drivers/ufs/host/ufs-renesas.c b/drivers/ufs/host/ufs-renesas.c
index 8711e5cbc9680..3ff97112e1f6d 100644
--- a/drivers/ufs/host/ufs-renesas.c
+++ b/drivers/ufs/host/ufs-renesas.c
@@ -7,6 +7,7 @@
 
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/iopoll.h>
 #include <linux/kernel.h>
@@ -364,14 +365,20 @@ static int ufs_renesas_init(struct ufs_hba *hba)
 		return -ENOMEM;
 	ufshcd_set_variant(hba, priv);
 
-	hba->quirks |= UFSHCD_QUIRK_BROKEN_64BIT_ADDRESS | UFSHCD_QUIRK_HIBERN_FASTAUTO;
+	hba->quirks |= UFSHCD_QUIRK_HIBERN_FASTAUTO;
 
 	return 0;
 }
 
+static int ufs_renesas_set_dma_mask(struct ufs_hba *hba)
+{
+	return dma_set_mask_and_coherent(hba->dev, DMA_BIT_MASK(32));
+}
+
 static const struct ufs_hba_variant_ops ufs_renesas_vops = {
 	.name		= "renesas",
 	.init		= ufs_renesas_init,
+	.set_dma_mask	= ufs_renesas_set_dma_mask,
 	.setup_clocks	= ufs_renesas_setup_clocks,
 	.hce_enable_notify = ufs_renesas_hce_enable_notify,
 	.dbg_register_dump = ufs_renesas_dbg_register_dump,
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index a95282b9f743f..a2d600ff4372c 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -299,6 +299,8 @@ struct ufs_pwr_mode_info {
  * @max_num_rtt: maximum RTT supported by the host
  * @init: called when the driver is initialized
  * @exit: called to cleanup everything done in init
+ * @set_dma_mask: For setting another DMA mask than indicated by the 64AS
+ *	capability bit.
  * @get_ufs_hci_version: called to get UFS HCI version
  * @clk_scale_notify: notifies that clks are scaled up/down
  * @setup_clocks: called before touching any of the controller registers
@@ -341,6 +343,7 @@ struct ufs_hba_variant_ops {
 	int	(*init)(struct ufs_hba *);
 	void    (*exit)(struct ufs_hba *);
 	u32	(*get_ufs_hci_version)(struct ufs_hba *);
+	int	(*set_dma_mask)(struct ufs_hba *);
 	int	(*clk_scale_notify)(struct ufs_hba *, bool,
 				    enum ufs_notify_change_status);
 	int	(*setup_clocks)(struct ufs_hba *, bool,
@@ -623,12 +626,6 @@ enum ufshcd_quirks {
 	 */
 	UFSHCD_QUIRK_SKIP_PH_CONFIGURATION		= 1 << 16,
 
-	/*
-	 * This quirk needs to be enabled if the host controller has
-	 * 64-bit addressing supported capability but it doesn't work.
-	 */
-	UFSHCD_QUIRK_BROKEN_64BIT_ADDRESS		= 1 << 17,
-
 	/*
 	 * This quirk needs to be enabled if the host controller has
 	 * auto-hibernate capability but it's FASTAUTO only.

From a085e03758b87ee5aea45de27c811576574d795b Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 22 Oct 2024 12:30:57 -0700
Subject: [PATCH 0647/1530] scsi: ufs: core: Move the ufshcd_mcq_enable_esi()
 definition

Move the ufshcd_mcq_enable_esi() definition such that it occurs
immediately before the ufshcd_mcq_config_esi() definition.

Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241022193130.2733293-2-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufs-mcq.c | 14 +++++++-------
 include/ufs/ufshcd.h       |  2 +-
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index 5891cdacd0b3c..57ced1729b73c 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -417,13 +417,6 @@ void ufshcd_mcq_make_queues_operational(struct ufs_hba *hba)
 }
 EXPORT_SYMBOL_GPL(ufshcd_mcq_make_queues_operational);
 
-void ufshcd_mcq_enable_esi(struct ufs_hba *hba)
-{
-	ufshcd_writel(hba, ufshcd_readl(hba, REG_UFS_MEM_CFG) | 0x2,
-		      REG_UFS_MEM_CFG);
-}
-EXPORT_SYMBOL_GPL(ufshcd_mcq_enable_esi);
-
 void ufshcd_mcq_enable(struct ufs_hba *hba)
 {
 	ufshcd_rmwl(hba, MCQ_MODE_SELECT, MCQ_MODE_SELECT, REG_UFS_MEM_CFG);
@@ -437,6 +430,13 @@ void ufshcd_mcq_disable(struct ufs_hba *hba)
 	hba->mcq_enabled = false;
 }
 
+void ufshcd_mcq_enable_esi(struct ufs_hba *hba)
+{
+	ufshcd_writel(hba, ufshcd_readl(hba, REG_UFS_MEM_CFG) | 0x2,
+		      REG_UFS_MEM_CFG);
+}
+EXPORT_SYMBOL_GPL(ufshcd_mcq_enable_esi);
+
 void ufshcd_mcq_config_esi(struct ufs_hba *hba, struct msi_msg *msg)
 {
 	ufshcd_writel(hba, msg->address_lo, REG_UFS_ESILBA);
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index a2d600ff4372c..d2dad221c12b5 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -1318,8 +1318,8 @@ void ufshcd_mcq_write_cqis(struct ufs_hba *hba, u32 val, int i);
 unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba,
 					 struct ufs_hw_queue *hwq);
 void ufshcd_mcq_make_queues_operational(struct ufs_hba *hba);
-void ufshcd_mcq_enable_esi(struct ufs_hba *hba);
 void ufshcd_mcq_enable(struct ufs_hba *hba);
+void ufshcd_mcq_enable_esi(struct ufs_hba *hba);
 void ufshcd_mcq_config_esi(struct ufs_hba *hba, struct msi_msg *msg);
 
 int ufshcd_opp_config_clks(struct device *dev, struct opp_table *opp_table,

From 7df89440d0ec47a4d91c5d664a6fa33931800913 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 22 Oct 2024 12:30:58 -0700
Subject: [PATCH 0648/1530] scsi: ufs: core: Remove goto statements from
 ufshcd_try_to_abort_task()

The only statement that follows the 'out:' label in
ufshcd_try_to_abort_task() is a return-statement. Simplify this function
by changing 'goto out' statements into return statements.

Reviewed-by: Avri Altman <avri.altman@wdc.com>
Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241022193130.2733293-3-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 2877e487637d0..ac69e6426d396 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -7485,7 +7485,7 @@ static void ufshcd_set_req_abort_skip(struct ufs_hba *hba, unsigned long bitmap)
 int ufshcd_try_to_abort_task(struct ufs_hba *hba, int tag)
 {
 	struct ufshcd_lrb *lrbp = &hba->lrb[tag];
-	int err = 0;
+	int err;
 	int poll_cnt;
 	u8 resp = 0xF;
 	u32 reg;
@@ -7515,7 +7515,7 @@ int ufshcd_try_to_abort_task(struct ufs_hba *hba, int tag)
 				/* command completed already */
 				dev_err(hba->dev, "%s: cmd at tag=%d is cleared.\n",
 					__func__, tag);
-				goto out;
+				return 0;
 			}
 
 			/* Single Doorbell Mode */
@@ -7528,21 +7528,17 @@ int ufshcd_try_to_abort_task(struct ufs_hba *hba, int tag)
 			/* command completed already */
 			dev_err(hba->dev, "%s: cmd at tag %d successfully cleared from DB.\n",
 				__func__, tag);
-			goto out;
+			return 0;
 		} else {
 			dev_err(hba->dev,
 				"%s: no response from device. tag = %d, err %d\n",
 				__func__, tag, err);
-			if (!err)
-				err = resp; /* service response error */
-			goto out;
+			return err ? : resp;
 		}
 	}
 
-	if (!poll_cnt) {
-		err = -EBUSY;
-		goto out;
-	}
+	if (!poll_cnt)
+		return -EBUSY;
 
 	err = ufshcd_issue_tm_cmd(hba, lrbp->lun, lrbp->task_tag,
 			UFS_ABORT_TASK, &resp);
@@ -7552,7 +7548,7 @@ int ufshcd_try_to_abort_task(struct ufs_hba *hba, int tag)
 			dev_err(hba->dev, "%s: issued. tag = %d, err %d\n",
 				__func__, tag, err);
 		}
-		goto out;
+		return err;
 	}
 
 	err = ufshcd_clear_cmd(hba, tag);
@@ -7560,7 +7556,6 @@ int ufshcd_try_to_abort_task(struct ufs_hba *hba, int tag)
 		dev_err(hba->dev, "%s: Failed clearing cmd at tag %d, err %d\n",
 			__func__, tag, err);
 
-out:
 	return err;
 }
 

From 9a5f6c09d0fa5a7b2139a745368e0ef77dece34b Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 22 Oct 2024 12:30:59 -0700
Subject: [PATCH 0649/1530] scsi: ufs: core: Simplify
 ufshcd_try_to_abort_task()

The MCQ code is also valid for legacy mode. Hence, remove the legacy
mode code and retain the MCQ code. Since it is not an error if a command
completes while ufshcd_try_to_abort_task() is in progress, use
dev_info() instead of dev_err() to report this.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241022193130.2733293-4-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 32 ++++++++------------------------
 1 file changed, 8 insertions(+), 24 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index ac69e6426d396..86e745b7e6bb5 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -7488,7 +7488,6 @@ int ufshcd_try_to_abort_task(struct ufs_hba *hba, int tag)
 	int err;
 	int poll_cnt;
 	u8 resp = 0xF;
-	u32 reg;
 
 	for (poll_cnt = 100; poll_cnt; poll_cnt--) {
 		err = ufshcd_issue_tm_cmd(hba, lrbp->lun, lrbp->task_tag,
@@ -7503,32 +7502,17 @@ int ufshcd_try_to_abort_task(struct ufs_hba *hba, int tag)
 			 * cmd not pending in the device, check if it is
 			 * in transition.
 			 */
-			dev_err(hba->dev, "%s: cmd at tag %d not pending in the device.\n",
+			dev_info(
+				hba->dev,
+				"%s: cmd with tag %d not pending in the device.\n",
 				__func__, tag);
-			if (hba->mcq_enabled) {
-				/* MCQ mode */
-				if (ufshcd_cmd_inflight(lrbp->cmd)) {
-					/* sleep for max. 200us same delay as in SDB mode */
-					usleep_range(100, 200);
-					continue;
-				}
-				/* command completed already */
-				dev_err(hba->dev, "%s: cmd at tag=%d is cleared.\n",
-					__func__, tag);
+			if (!ufshcd_cmd_inflight(lrbp->cmd)) {
+				dev_info(hba->dev,
+					 "%s: cmd with tag=%d completed.\n",
+					 __func__, tag);
 				return 0;
 			}
-
-			/* Single Doorbell Mode */
-			reg = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
-			if (reg & (1 << tag)) {
-				/* sleep for max. 200us to stabilize */
-				usleep_range(100, 200);
-				continue;
-			}
-			/* command completed already */
-			dev_err(hba->dev, "%s: cmd at tag %d successfully cleared from DB.\n",
-				__func__, tag);
-			return 0;
+			usleep_range(100, 200);
 		} else {
 			dev_err(hba->dev,
 				"%s: no response from device. tag = %d, err %d\n",

From b5d9da58a05172ec08301e06932338ade6d55f82 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 22 Oct 2024 12:31:00 -0700
Subject: [PATCH 0650/1530] scsi: ufs: core: Simplify
 ufshcd_exception_event_handler()

The ufshcd_scsi_block_requests() and ufshcd_scsi_unblock_requests()
calls were introduced in ufshcd_exception_event_handler() to prevent
that querying the exception event information would time out. Commit
10fe5888a40e ("scsi: ufs: increase the scsi query response timeout")
increased the timeout for querying exception information from 30 ms to
1.5 s and thereby eliminated the risk that a timeout would happen.
Hence, the calls to block and unblock SCSI requests are superfluous.
Remove these calls.

Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Tested-by: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241022193130.2733293-5-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 86e745b7e6bb5..656a09cd48e49 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -6194,12 +6194,11 @@ static void ufshcd_exception_event_handler(struct work_struct *work)
 	u32 status = 0;
 	hba = container_of(work, struct ufs_hba, eeh_work);
 
-	ufshcd_scsi_block_requests(hba);
 	err = ufshcd_get_ee_status(hba, &status);
 	if (err) {
 		dev_err(hba->dev, "%s: failed to get exception status %d\n",
 				__func__, err);
-		goto out;
+		return;
 	}
 
 	trace_ufshcd_exception_event(dev_name(hba->dev), status);
@@ -6211,8 +6210,6 @@ static void ufshcd_exception_event_handler(struct work_struct *work)
 		ufshcd_temp_exception_event_handler(hba, status);
 
 	ufs_debugfs_exception_event(hba, status);
-out:
-	ufshcd_scsi_unblock_requests(hba);
 }
 
 /* Complete requests that have door-bell cleared */

From 2a36646012fc58e6262435ff5d2c8c97456c253f Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 22 Oct 2024 12:31:01 -0700
Subject: [PATCH 0651/1530] scsi: ufs: core: Simplify
 ufshcd_err_handling_prepare()

Use blk_mq_quiesce_tagset() instead of ufshcd_scsi_block_requests() and
blk_mq_wait_quiesce_done(). Since this patch removes the last callers of
ufshcd_scsi_block_requests() and ufshcd_scsi_unblock_requests(), remove
these functions.

Reviewed-by: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241022193130.2733293-6-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 19 +++----------------
 include/ufs/ufshcd.h      |  2 --
 2 files changed, 3 insertions(+), 18 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 656a09cd48e49..c156c47875283 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -349,18 +349,6 @@ static void ufshcd_configure_wb(struct ufs_hba *hba)
 		ufshcd_wb_toggle_buf_flush(hba, true);
 }
 
-static void ufshcd_scsi_unblock_requests(struct ufs_hba *hba)
-{
-	if (atomic_dec_and_test(&hba->scsi_block_reqs_cnt))
-		scsi_unblock_requests(hba->host);
-}
-
-static void ufshcd_scsi_block_requests(struct ufs_hba *hba)
-{
-	if (atomic_inc_return(&hba->scsi_block_reqs_cnt) == 1)
-		scsi_block_requests(hba->host);
-}
-
 static void ufshcd_add_cmd_upiu_trace(struct ufs_hba *hba, unsigned int tag,
 				      enum ufs_trace_str_t str_t)
 {
@@ -6375,15 +6363,14 @@ static void ufshcd_err_handling_prepare(struct ufs_hba *hba)
 			ufshcd_suspend_clkscaling(hba);
 		ufshcd_clk_scaling_allow(hba, false);
 	}
-	ufshcd_scsi_block_requests(hba);
 	/* Wait for ongoing ufshcd_queuecommand() calls to finish. */
-	blk_mq_wait_quiesce_done(&hba->host->tag_set);
+	blk_mq_quiesce_tagset(&hba->host->tag_set);
 	cancel_work_sync(&hba->eeh_work);
 }
 
 static void ufshcd_err_handling_unprepare(struct ufs_hba *hba)
 {
-	ufshcd_scsi_unblock_requests(hba);
+	blk_mq_unquiesce_tagset(&hba->host->tag_set);
 	ufshcd_release(hba);
 	if (ufshcd_is_clkscaling_supported(hba))
 		ufshcd_clk_scaling_suspend(hba, false);
@@ -10558,7 +10545,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 
 	/* Hold auto suspend until async scan completes */
 	pm_runtime_get_sync(dev);
-	atomic_set(&hba->scsi_block_reqs_cnt, 0);
+
 	/*
 	 * We are assuming that device wasn't put in sleep/power-down
 	 * state exclusively during the boot stage before kernel.
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index d2dad221c12b5..9ea2a7411bb58 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -925,7 +925,6 @@ enum ufshcd_mcq_opr {
  * @wb_mutex: used to serialize devfreq and sysfs write booster toggling
  * @clk_scaling_lock: used to serialize device commands and clock scaling
  * @desc_size: descriptor sizes reported by device
- * @scsi_block_reqs_cnt: reference counting for scsi block requests
  * @bsg_dev: struct device associated with the BSG queue
  * @bsg_queue: BSG queue associated with the UFS controller
  * @rpm_dev_flush_recheck_work: used to suspend from RPM (runtime power
@@ -1086,7 +1085,6 @@ struct ufs_hba {
 
 	struct mutex wb_mutex;
 	struct rw_semaphore clk_scaling_lock;
-	atomic_t scsi_block_reqs_cnt;
 
 	struct device		bsg_dev;
 	struct request_queue	*bsg_queue;

From 2c73fb138da587597c2b02e72dcbeae18af60f4e Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 22 Oct 2024 12:31:02 -0700
Subject: [PATCH 0652/1530] scsi: ufs: core: Improve ufshcd_mcq_sq_cleanup()

From the UFSHCI specification: "CleanUp Command Return Code (RTC): host
controller sets this return code to provide more details of the cleanup
process. It is valid only when CUS is 1." Hence, do not read RTC if the
CUS bitfield is zero.

Cc: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Fixes: 8d7290348992 ("scsi: ufs: mcq: Add supporting functions for MCQ abort")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241022193130.2733293-7-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufs-mcq.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index 57ced1729b73c..9884005005605 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -572,14 +572,18 @@ int ufshcd_mcq_sq_cleanup(struct ufs_hba *hba, int task_tag)
 	/* SQRTCy.ICU = 1 */
 	writel(SQ_ICU, opr_sqd_base + REG_SQRTC);
 
-	/* Poll SQRTSy.CUS = 1. Return result from SQRTSy.RTC */
+	/* Wait until SQRTSy.CUS = 1. Report SQRTSy.RTC. */
 	reg = opr_sqd_base + REG_SQRTS;
 	err = read_poll_timeout(readl, val, val & SQ_CUS, 20,
 				MCQ_POLL_US, false, reg);
 	if (err)
-		dev_err(hba->dev, "%s: failed. hwq=%d, tag=%d err=%ld\n",
-			__func__, id, task_tag,
-			FIELD_GET(SQ_ICU_ERR_CODE_MASK, readl(reg)));
+		dev_err(hba->dev, "%s: failed. hwq=%d, tag=%d err=%d\n",
+			__func__, id, task_tag, err);
+	else
+		dev_info(hba->dev,
+			 "%s, hwq %d: cleanup return code (RTC) %ld\n",
+			 __func__, id,
+			 FIELD_GET(SQ_ICU_ERR_CODE_MASK, readl(reg)));
 
 	if (ufshcd_mcq_sq_start(hba, hwq))
 		err = -ETIMEDOUT;

From 2b314e182caabd32f656ddba22432a7749572013 Mon Sep 17 00:00:00 2001
From: Avri Altman <avri.altman@wdc.com>
Date: Thu, 24 Oct 2024 10:50:31 +0300
Subject: [PATCH 0653/1530] scsi: ufs: core: Remove redundant host_lock calls
 around UTMRLDBR

There is no need to serialize single read/write calls to the host
controller registers. Remove the redundant host_lock calls that protect
access to the task management doorbell register: UTMRLDBR.

Signed-off-by: Avri Altman <avri.altman@wdc.com>
Link: https://lore.kernel.org/r/20241024075033.562562-2-avri.altman@wdc.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index c156c47875283..5827575204fae 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -1233,11 +1233,13 @@ static bool ufshcd_is_devfreq_scaling_required(struct ufs_hba *hba,
 static u32 ufshcd_pending_cmds(struct ufs_hba *hba)
 {
 	const struct scsi_device *sdev;
+	unsigned long flags;
 	u32 pending = 0;
 
-	lockdep_assert_held(hba->host->host_lock);
+	spin_lock_irqsave(hba->host->host_lock, flags);
 	__shost_for_each_device(sdev, hba->host)
 		pending += sbitmap_weight(&sdev->budget_map);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
 	return pending;
 }
@@ -1251,7 +1253,6 @@ static u32 ufshcd_pending_cmds(struct ufs_hba *hba)
 static int ufshcd_wait_for_doorbell_clr(struct ufs_hba *hba,
 					u64 wait_timeout_us)
 {
-	unsigned long flags;
 	int ret = 0;
 	u32 tm_doorbell;
 	u32 tr_pending;
@@ -1259,7 +1260,6 @@ static int ufshcd_wait_for_doorbell_clr(struct ufs_hba *hba,
 	ktime_t start;
 
 	ufshcd_hold(hba);
-	spin_lock_irqsave(hba->host->host_lock, flags);
 	/*
 	 * Wait for all the outstanding tasks/transfer requests.
 	 * Verify by checking the doorbell registers are clear.
@@ -1280,7 +1280,6 @@ static int ufshcd_wait_for_doorbell_clr(struct ufs_hba *hba,
 			break;
 		}
 
-		spin_unlock_irqrestore(hba->host->host_lock, flags);
 		io_schedule_timeout(msecs_to_jiffies(20));
 		if (ktime_to_us(ktime_sub(ktime_get(), start)) >
 		    wait_timeout_us) {
@@ -1292,7 +1291,6 @@ static int ufshcd_wait_for_doorbell_clr(struct ufs_hba *hba,
 			 */
 			do_last_check = true;
 		}
-		spin_lock_irqsave(hba->host->host_lock, flags);
 	} while (tm_doorbell || tr_pending);
 
 	if (timeout) {
@@ -1302,7 +1300,6 @@ static int ufshcd_wait_for_doorbell_clr(struct ufs_hba *hba,
 		ret = -EBUSY;
 	}
 out:
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	ufshcd_release(hba);
 	return ret;
 }
@@ -7048,12 +7045,13 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba,
 	memcpy(hba->utmrdl_base_addr + task_tag, treq, sizeof(*treq));
 	ufshcd_vops_setup_task_mgmt(hba, task_tag, tm_function);
 
-	/* send command to the controller */
 	__set_bit(task_tag, &hba->outstanding_tasks);
-	ufshcd_writel(hba, 1 << task_tag, REG_UTP_TASK_REQ_DOOR_BELL);
 
 	spin_unlock_irqrestore(host->host_lock, flags);
 
+	/* send command to the controller */
+	ufshcd_writel(hba, 1 << task_tag, REG_UTP_TASK_REQ_DOOR_BELL);
+
 	ufshcd_add_tm_upiu_trace(hba, task_tag, UFS_TM_SEND);
 
 	/* wait until the task management command is completed */

From 5824e18b3db468e6eb5e9ef226eed80db26f581a Mon Sep 17 00:00:00 2001
From: Avri Altman <avri.altman@wdc.com>
Date: Thu, 24 Oct 2024 10:50:32 +0300
Subject: [PATCH 0654/1530] scsi: ufs: core: Remove redundant host_lock calls
 around UTMRLCLR

There is no need to serialize single read/write calls to the host
controller registers. Remove the redundant host_lock calls that protect
access to the task management request List cLear register: UTMRLCLR.

Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Avri Altman <avri.altman@wdc.com>
Link: https://lore.kernel.org/r/20241024075033.562562-3-avri.altman@wdc.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 5827575204fae..f6e84a3bfcf47 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -6995,14 +6995,11 @@ static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag)
 {
 	int err = 0;
 	u32 mask = 1 << tag;
-	unsigned long flags;
 
 	if (!test_bit(tag, &hba->outstanding_tasks))
 		goto out;
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
 	ufshcd_utmrl_clear(hba, tag);
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
 	/* poll for max. 1 sec to clear door bell register by h/w */
 	err = ufshcd_wait_for_register(hba,

From 2a330f16ad305935c965dd84b727771c52701642 Mon Sep 17 00:00:00 2001
From: Avri Altman <avri.altman@wdc.com>
Date: Thu, 24 Oct 2024 10:50:33 +0300
Subject: [PATCH 0655/1530] scsi: ufs: core: Remove redundant host_lock calls
 around UTRLCLR.

There is no need to serialize single read/write calls to the host
controller registers. Remove the redundant host_lock calls that protect
access to the request list cLear register: UTRLCLR.

Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Avri Altman <avri.altman@wdc.com>
Link: https://lore.kernel.org/r/20241024075033.562562-4-avri.altman@wdc.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index f6e84a3bfcf47..9458ecc1c10e3 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -3062,7 +3062,6 @@ bool ufshcd_cmd_inflight(struct scsi_cmnd *cmd)
 static int ufshcd_clear_cmd(struct ufs_hba *hba, u32 task_tag)
 {
 	u32 mask;
-	unsigned long flags;
 	int err;
 
 	if (hba->mcq_enabled) {
@@ -3082,9 +3081,7 @@ static int ufshcd_clear_cmd(struct ufs_hba *hba, u32 task_tag)
 	mask = 1U << task_tag;
 
 	/* clear outstanding transaction before retry */
-	spin_lock_irqsave(hba->host->host_lock, flags);
 	ufshcd_utrl_clear(hba, mask);
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
 	/*
 	 * wait for h/w to clear corresponding bit in door-bell.

From 17a973970397b3452fde2c93bc1ee051e7a8c79b Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 16 Oct 2024 13:11:57 -0700
Subject: [PATCH 0656/1530] scsi: ufs: core: Introduce ufshcd_add_scsi_host()

Move the code for adding a SCSI host and also the code for managing TMF
tags from ufshcd_init() into a new function called
ufshcd_add_scsi_host(). This patch prepares for combining the two
scsi_add_host() calls into a single call. No functionality has been
changed.

Reviewed-by: Avri Altman <avri.altman@wdc.com>
Reviewed-by: Bean Huo <beanhuo@micron.com>
Reviewed-by: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241016201249.2256266-2-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 96 ++++++++++++++++++++++++---------------
 1 file changed, 59 insertions(+), 37 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 9458ecc1c10e3..7660d35464086 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -10333,6 +10333,62 @@ static const struct blk_mq_ops ufshcd_tmf_ops = {
 	.queue_rq = ufshcd_queue_tmf,
 };
 
+static int ufshcd_add_scsi_host(struct ufs_hba *hba)
+{
+	int err;
+
+	if (!is_mcq_supported(hba)) {
+		if (!hba->lsdb_sup) {
+			dev_err(hba->dev,
+				"%s: failed to initialize (legacy doorbell mode not supported)\n",
+				__func__);
+			return -EINVAL;
+		}
+		err = scsi_add_host(hba->host, hba->dev);
+		if (err) {
+			dev_err(hba->dev, "scsi_add_host failed\n");
+			return err;
+		}
+		hba->scsi_host_added = true;
+	}
+
+	hba->tmf_tag_set = (struct blk_mq_tag_set) {
+		.nr_hw_queues	= 1,
+		.queue_depth	= hba->nutmrs,
+		.ops		= &ufshcd_tmf_ops,
+		.flags		= BLK_MQ_F_NO_SCHED,
+	};
+	err = blk_mq_alloc_tag_set(&hba->tmf_tag_set);
+	if (err < 0)
+		goto remove_scsi_host;
+	hba->tmf_queue = blk_mq_alloc_queue(&hba->tmf_tag_set, NULL, NULL);
+	if (IS_ERR(hba->tmf_queue)) {
+		err = PTR_ERR(hba->tmf_queue);
+		goto free_tmf_tag_set;
+	}
+	hba->tmf_rqs = devm_kcalloc(hba->dev, hba->nutmrs,
+				    sizeof(*hba->tmf_rqs), GFP_KERNEL);
+	if (!hba->tmf_rqs) {
+		err = -ENOMEM;
+		goto free_tmf_queue;
+	}
+
+	return 0;
+
+free_tmf_queue:
+	blk_mq_destroy_queue(hba->tmf_queue);
+	blk_put_queue(hba->tmf_queue);
+
+free_tmf_tag_set:
+	blk_mq_free_tag_set(&hba->tmf_tag_set);
+
+remove_scsi_host:
+	if (hba->scsi_host_added)
+		scsi_remove_host(hba->host);
+
+	return err;
+}
+
 /**
  * ufshcd_init - Driver initialization routine
  * @hba: per-adapter instance
@@ -10464,41 +10520,9 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 		hba->is_irq_enabled = true;
 	}
 
-	if (!is_mcq_supported(hba)) {
-		if (!hba->lsdb_sup) {
-			dev_err(hba->dev, "%s: failed to initialize (legacy doorbell mode not supported)\n",
-				__func__);
-			err = -EINVAL;
-			goto out_disable;
-		}
-		err = scsi_add_host(host, hba->dev);
-		if (err) {
-			dev_err(hba->dev, "scsi_add_host failed\n");
-			goto out_disable;
-		}
-		hba->scsi_host_added = true;
-	}
-
-	hba->tmf_tag_set = (struct blk_mq_tag_set) {
-		.nr_hw_queues	= 1,
-		.queue_depth	= hba->nutmrs,
-		.ops		= &ufshcd_tmf_ops,
-		.flags		= BLK_MQ_F_NO_SCHED,
-	};
-	err = blk_mq_alloc_tag_set(&hba->tmf_tag_set);
-	if (err < 0)
-		goto out_remove_scsi_host;
-	hba->tmf_queue = blk_mq_alloc_queue(&hba->tmf_tag_set, NULL, NULL);
-	if (IS_ERR(hba->tmf_queue)) {
-		err = PTR_ERR(hba->tmf_queue);
-		goto free_tmf_tag_set;
-	}
-	hba->tmf_rqs = devm_kcalloc(hba->dev, hba->nutmrs,
-				    sizeof(*hba->tmf_rqs), GFP_KERNEL);
-	if (!hba->tmf_rqs) {
-		err = -ENOMEM;
-		goto free_tmf_queue;
-	}
+	err = ufshcd_add_scsi_host(hba);
+	if (err)
+		goto out_disable;
 
 	/* Reset the attached device */
 	ufshcd_device_reset(hba);
@@ -10556,9 +10580,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 free_tmf_queue:
 	blk_mq_destroy_queue(hba->tmf_queue);
 	blk_put_queue(hba->tmf_queue);
-free_tmf_tag_set:
 	blk_mq_free_tag_set(&hba->tmf_tag_set);
-out_remove_scsi_host:
 	if (hba->scsi_host_added)
 		scsi_remove_host(hba->host);
 out_disable:

From 3192d28ec6608ace67e85753da2504c11a4fdb16 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 16 Oct 2024 13:11:58 -0700
Subject: [PATCH 0657/1530] scsi: ufs: core: Introduce
 ufshcd_post_device_init()

Prepare for inlining one ufshcd_device_init() call by introducing the
new function ufshcd_post_device_init(). No functionality has been
changed.

Reviewed-by: Avri Altman <avri.altman@wdc.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241016201249.2256266-3-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 62 ++++++++++++++++++++++-----------------
 1 file changed, 35 insertions(+), 27 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 7660d35464086..72f041338788c 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -8686,6 +8686,40 @@ static void ufshcd_config_mcq(struct ufs_hba *hba)
 		 hba->nutrs);
 }
 
+static int ufshcd_post_device_init(struct ufs_hba *hba)
+{
+	int ret;
+
+	ufshcd_tune_unipro_params(hba);
+
+	/* UFS device is also active now */
+	ufshcd_set_ufs_dev_active(hba);
+	ufshcd_force_reset_auto_bkops(hba);
+
+	ufshcd_set_timestamp_attr(hba);
+	schedule_delayed_work(&hba->ufs_rtc_update_work,
+			      msecs_to_jiffies(UFS_RTC_UPDATE_INTERVAL_MS));
+
+	if (!hba->max_pwr_info.is_valid)
+		return 0;
+
+	/*
+	 * Set the right value to bRefClkFreq before attempting to
+	 * switch to HS gears.
+	 */
+	if (hba->dev_ref_clk_freq != REF_CLK_FREQ_INVAL)
+		ufshcd_set_dev_ref_clk(hba);
+	/* Gear up to HS gear. */
+	ret = ufshcd_config_pwr_mode(hba, &hba->max_pwr_info.info);
+	if (ret) {
+		dev_err(hba->dev, "%s: Failed setting power mode, err = %d\n",
+			__func__, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
 static int ufshcd_device_init(struct ufs_hba *hba, bool init_dev_params)
 {
 	int ret;
@@ -8755,33 +8789,7 @@ static int ufshcd_device_init(struct ufs_hba *hba, bool init_dev_params)
 		}
 	}
 
-	ufshcd_tune_unipro_params(hba);
-
-	/* UFS device is also active now */
-	ufshcd_set_ufs_dev_active(hba);
-	ufshcd_force_reset_auto_bkops(hba);
-
-	ufshcd_set_timestamp_attr(hba);
-	schedule_delayed_work(&hba->ufs_rtc_update_work,
-			      msecs_to_jiffies(UFS_RTC_UPDATE_INTERVAL_MS));
-
-	/* Gear up to HS gear if supported */
-	if (hba->max_pwr_info.is_valid) {
-		/*
-		 * Set the right value to bRefClkFreq before attempting to
-		 * switch to HS gears.
-		 */
-		if (hba->dev_ref_clk_freq != REF_CLK_FREQ_INVAL)
-			ufshcd_set_dev_ref_clk(hba);
-		ret = ufshcd_config_pwr_mode(hba, &hba->max_pwr_info.info);
-		if (ret) {
-			dev_err(hba->dev, "%s: Failed setting power mode, err = %d\n",
-					__func__, ret);
-			return ret;
-		}
-	}
-
-	return 0;
+	return ufshcd_post_device_init(hba);
 }
 
 /**

From 7702c7f64f2df3e299ae26059e448bf4f08b867a Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 16 Oct 2024 13:11:59 -0700
Subject: [PATCH 0658/1530] scsi: ufs: core: Call ufshcd_add_scsi_host() later

Call ufshcd_add_scsi_host() after host controller initialization has
completed. This is safe because no code between the old and new
ufshcd_add_scsi_host() call site depends on the scsi_add_host() call.

Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Bean Huo <beanhuo@micron.com>
Reviewed-by: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241016201249.2256266-4-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 72f041338788c..4fe2339b1deb8 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -10528,10 +10528,6 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 		hba->is_irq_enabled = true;
 	}
 
-	err = ufshcd_add_scsi_host(hba);
-	if (err)
-		goto out_disable;
-
 	/* Reset the attached device */
 	ufshcd_device_reset(hba);
 
@@ -10543,7 +10539,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 		dev_err(hba->dev, "Host controller enable failed\n");
 		ufshcd_print_evt_hist(hba);
 		ufshcd_print_host_state(hba);
-		goto free_tmf_queue;
+		goto out_disable;
 	}
 
 	/*
@@ -10578,6 +10574,10 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	 */
 	ufshcd_set_ufs_dev_active(hba);
 
+	err = ufshcd_add_scsi_host(hba);
+	if (err)
+		goto out_disable;
+
 	async_schedule(ufshcd_async_scan, hba);
 	ufs_sysfs_add_nodes(hba->dev);
 
@@ -10585,12 +10585,6 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	ufshcd_pm_qos_init(hba);
 	return 0;
 
-free_tmf_queue:
-	blk_mq_destroy_queue(hba->tmf_queue);
-	blk_put_queue(hba->tmf_queue);
-	blk_mq_free_tag_set(&hba->tmf_tag_set);
-	if (hba->scsi_host_added)
-		scsi_remove_host(hba->host);
 out_disable:
 	hba->is_irq_enabled = false;
 	ufshcd_hba_exit(hba);

From 18ec23b60822fb52ae1f1f3a08df29289458b087 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 16 Oct 2024 13:12:00 -0700
Subject: [PATCH 0659/1530] scsi: ufs: core: Introduce
 ufshcd_process_probe_result()

Prepare for moving a ufshcd_device_init() call from inside
ufshcd_probe_hba() into the ufshcd_probe_hba() callers by introducing
the function ufshcd_process_probe_result(). No functionality has been
changed.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241016201249.2256266-5-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 35 ++++++++++++++++++++++++-----------
 1 file changed, 24 insertions(+), 11 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 4fe2339b1deb8..67ee6fba6f2a7 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -7638,6 +7638,29 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 	return err;
 }
 
+/**
+ * ufshcd_process_probe_result - Process the ufshcd_probe_hba() result.
+ * @hba: UFS host controller instance.
+ * @probe_start: time when the ufshcd_probe_hba() call started.
+ * @ret: ufshcd_probe_hba() return value.
+ */
+static void ufshcd_process_probe_result(struct ufs_hba *hba,
+					ktime_t probe_start, int ret)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	if (ret)
+		hba->ufshcd_state = UFSHCD_STATE_ERROR;
+	else if (hba->ufshcd_state == UFSHCD_STATE_RESET)
+		hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	trace_ufshcd_init(dev_name(hba->dev), ret,
+			  ktime_to_us(ktime_sub(ktime_get(), probe_start)),
+			  hba->curr_dev_pwr_mode, hba->uic_link_state);
+}
+
 /**
  * ufshcd_host_reset_and_restore - reset and restore host controller
  * @hba: per-adapter instance
@@ -8804,7 +8827,6 @@ static int ufshcd_device_init(struct ufs_hba *hba, bool init_dev_params)
 static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params)
 {
 	ktime_t start = ktime_get();
-	unsigned long flags;
 	int ret;
 
 	ret = ufshcd_device_init(hba, init_dev_params);
@@ -8850,16 +8872,7 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params)
 	ufshcd_configure_auto_hibern8(hba);
 
 out:
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	if (ret)
-		hba->ufshcd_state = UFSHCD_STATE_ERROR;
-	else if (hba->ufshcd_state == UFSHCD_STATE_RESET)
-		hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
-
-	trace_ufshcd_init(dev_name(hba->dev), ret,
-		ktime_to_us(ktime_sub(ktime_get(), start)),
-		hba->curr_dev_pwr_mode, hba->uic_link_state);
+	ufshcd_process_probe_result(hba, start, ret);
 	return ret;
 }
 

From 0936001322646a15d7091f61232e5ded9bf1883f Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 16 Oct 2024 13:12:01 -0700
Subject: [PATCH 0660/1530] scsi: ufs: core: Convert a comment into an explicit
 check

The comment /* UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH is set */ is
only correct if ufshcd_device_init() is only called by
ufshcd_probe_hba().  Convert the comment into an explicit check. This
patch prepares for moving the ufshcd_device_init() calls.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241016201249.2256266-6-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 67ee6fba6f2a7..2ed1e5391152d 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -8805,8 +8805,9 @@ static int ufshcd_device_init(struct ufs_hba *hba, bool init_dev_params)
 				return ret;
 			}
 			hba->scsi_host_added = true;
-		} else if (is_mcq_supported(hba)) {
-			/* UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH is set */
+		} else if (is_mcq_supported(hba) &&
+			   hba->quirks &
+				   UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH) {
 			ufshcd_config_mcq(hba);
 			ufshcd_mcq_enable(hba);
 		}

From 639e2043b58998b3950ab90413c1b726945058bf Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 16 Oct 2024 13:12:02 -0700
Subject: [PATCH 0661/1530] scsi: ufs: core: Move the ufshcd_device_init()
 calls

Move the ufshcd_device_init() and ufshcd_process_hba_result() calls to
the ufshcd_probe_hba() callers. This change refactors the code without
modifying the behavior of the UFSHCI driver. This change prepares for
moving one ufshcd_device_init() call into ufshcd_init().

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241016201249.2256266-7-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 2ed1e5391152d..1c9ffa1c3670d 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -298,6 +298,7 @@ static int ufshcd_reset_and_restore(struct ufs_hba *hba);
 static int ufshcd_eh_host_reset_handler(struct scsi_cmnd *cmd);
 static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag);
 static void ufshcd_hba_exit(struct ufs_hba *hba);
+static int ufshcd_device_init(struct ufs_hba *hba, bool init_dev_params);
 static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params);
 static int ufshcd_setup_clocks(struct ufs_hba *hba, bool on);
 static inline void ufshcd_add_delay_before_dme_cmd(struct ufs_hba *hba);
@@ -7690,8 +7691,14 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba)
 	err = ufshcd_hba_enable(hba);
 
 	/* Establish the link again and restore the device */
-	if (!err)
-		err = ufshcd_probe_hba(hba, false);
+	if (!err) {
+		ktime_t probe_start = ktime_get();
+
+		err = ufshcd_device_init(hba, /*init_dev_params=*/false);
+		if (!err)
+			err = ufshcd_probe_hba(hba, false);
+		ufshcd_process_probe_result(hba, probe_start, err);
+	}
 
 	if (err)
 		dev_err(hba->dev, "%s: Host init failed %d\n", __func__, err);
@@ -8827,13 +8834,8 @@ static int ufshcd_device_init(struct ufs_hba *hba, bool init_dev_params)
  */
 static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params)
 {
-	ktime_t start = ktime_get();
 	int ret;
 
-	ret = ufshcd_device_init(hba, init_dev_params);
-	if (ret)
-		goto out;
-
 	if (!hba->pm_op_in_progress &&
 	    (hba->quirks & UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH)) {
 		/* Reset the device and controller before doing reinit */
@@ -8846,13 +8848,13 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params)
 			dev_err(hba->dev, "Host controller enable failed\n");
 			ufshcd_print_evt_hist(hba);
 			ufshcd_print_host_state(hba);
-			goto out;
+			return ret;
 		}
 
 		/* Reinit the device */
 		ret = ufshcd_device_init(hba, init_dev_params);
 		if (ret)
-			goto out;
+			return ret;
 	}
 
 	ufshcd_print_pwr_info(hba);
@@ -8872,9 +8874,7 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params)
 		ufshcd_write_ee_control(hba);
 	ufshcd_configure_auto_hibern8(hba);
 
-out:
-	ufshcd_process_probe_result(hba, start, ret);
-	return ret;
+	return 0;
 }
 
 /**
@@ -8885,11 +8885,16 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params)
 static void ufshcd_async_scan(void *data, async_cookie_t cookie)
 {
 	struct ufs_hba *hba = (struct ufs_hba *)data;
+	ktime_t probe_start;
 	int ret;
 
 	down(&hba->host_sem);
 	/* Initialize hba, detect and initialize UFS device */
-	ret = ufshcd_probe_hba(hba, true);
+	probe_start = ktime_get();
+	ret = ufshcd_device_init(hba, /*init_dev_params=*/true);
+	if (ret == 0)
+		ret = ufshcd_probe_hba(hba, true);
+	ufshcd_process_probe_result(hba, probe_start, ret);
 	up(&hba->host_sem);
 	if (ret)
 		goto out;

From 69f5eb78d4b0cc978fe83dd2bfea1b67547290bf Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 16 Oct 2024 13:12:03 -0700
Subject: [PATCH 0662/1530] scsi: ufs: core: Move the ufshcd_device_init(hba,
 true) call

ufshcd_async_scan() is called (asynchronously) only by ufshcd_init().
Move the ufshcd_device_init(hba, true) call from ufshcd_async_scan()
into ufshcd_init(). This patch prepares for moving both scsi_add_host()
calls into ufshcd_add_scsi_host(). Calling ufshcd_device_init() from
ufshcd_init() without holding hba->host_sem is safe. This is safe
because hba->host_sem serializes core code and sysfs callbacks. The
ufshcd_device_init() call is moved before the scsi_add_host() call and
hence happens before any SCSI sysfs attributes are created.

Since ufshcd_device_init() may call scsi_add_host(), only call
scsi_add_host() from ufshcd_add_scsi_host() if the SCSI host has not yet
been added by ufshcd_device_init().

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241016201249.2256266-8-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 1c9ffa1c3670d..0f69653510cc2 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -8891,9 +8891,7 @@ static void ufshcd_async_scan(void *data, async_cookie_t cookie)
 	down(&hba->host_sem);
 	/* Initialize hba, detect and initialize UFS device */
 	probe_start = ktime_get();
-	ret = ufshcd_device_init(hba, /*init_dev_params=*/true);
-	if (ret == 0)
-		ret = ufshcd_probe_hba(hba, true);
+	ret = ufshcd_probe_hba(hba, true);
 	ufshcd_process_probe_result(hba, probe_start, ret);
 	up(&hba->host_sem);
 	if (ret)
@@ -10364,7 +10362,8 @@ static int ufshcd_add_scsi_host(struct ufs_hba *hba)
 {
 	int err;
 
-	if (!is_mcq_supported(hba)) {
+	if (!hba->scsi_host_added) {
+		WARN_ON_ONCE(is_mcq_supported(hba));
 		if (!hba->lsdb_sup) {
 			dev_err(hba->dev,
 				"%s: failed to initialize (legacy doorbell mode not supported)\n",
@@ -10593,6 +10592,11 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	 */
 	ufshcd_set_ufs_dev_active(hba);
 
+	/* Initialize hba, detect and initialize UFS device */
+	err = ufshcd_device_init(hba, /*init_dev_params=*/true);
+	if (err)
+		goto out_disable;
+
 	err = ufshcd_add_scsi_host(hba);
 	if (err)
 		goto out_disable;

From a390e6677f4119e3b9e6364ac2c5cbe3ef1321a2 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 16 Oct 2024 13:12:04 -0700
Subject: [PATCH 0663/1530] scsi: ufs: core: Expand the ufshcd_device_init(hba,
 true) call

Expand the ufshcd_device_init(hba, true) call and remove all code that
depends on init_dev_params == false. This change prepares for combining
the two scsi_add_host() calls.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241016201249.2256266-9-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 56 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 55 insertions(+), 1 deletion(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 0f69653510cc2..239e826f4b498 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -10593,7 +10593,61 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	ufshcd_set_ufs_dev_active(hba);
 
 	/* Initialize hba, detect and initialize UFS device */
-	err = ufshcd_device_init(hba, /*init_dev_params=*/true);
+	ktime_t probe_start = ktime_get();
+
+	hba->ufshcd_state = UFSHCD_STATE_RESET;
+
+	err = ufshcd_link_startup(hba);
+	if (err)
+		goto out_disable;
+
+	if (hba->quirks & UFSHCD_QUIRK_SKIP_PH_CONFIGURATION)
+		goto initialized;
+
+	/* Debug counters initialization */
+	ufshcd_clear_dbg_ufs_stats(hba);
+
+	/* UniPro link is active now */
+	ufshcd_set_link_active(hba);
+
+	/* Verify device initialization by sending NOP OUT UPIU */
+	err = ufshcd_verify_dev_init(hba);
+	if (err)
+		goto out_disable;
+
+	/* Initiate UFS initialization, and waiting until completion */
+	err = ufshcd_complete_dev_init(hba);
+	if (err)
+		goto out_disable;
+
+	err = ufshcd_device_params_init(hba);
+	if (err)
+		goto out_disable;
+
+	if (is_mcq_supported(hba)) {
+		ufshcd_mcq_enable(hba);
+		err = ufshcd_alloc_mcq(hba);
+		if (!err) {
+			ufshcd_config_mcq(hba);
+		} else {
+			/* Continue with SDB mode */
+			ufshcd_mcq_disable(hba);
+			use_mcq_mode = false;
+			dev_err(hba->dev, "MCQ mode is disabled, err=%d\n",
+				err);
+		}
+		err = scsi_add_host(host, hba->dev);
+		if (err) {
+			dev_err(hba->dev, "scsi_add_host failed\n");
+			goto out_disable;
+		}
+		hba->scsi_host_added = true;
+	}
+
+	err = ufshcd_post_device_init(hba);
+
+initialized:
+	ufshcd_process_probe_result(hba, probe_start, err);
 	if (err)
 		goto out_disable;
 

From b6195d02b914ddfddb50e3ceb6b66928ebf0fdb8 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 16 Oct 2024 13:12:05 -0700
Subject: [PATCH 0664/1530] scsi: ufs: core: Remove code that is no longer
 needed

Previous changes guarantee that hba->scsi_host_added is true before
ufshcd_device_init() is called. Hence, remove the code from
ufshcd_device_init() that depends on hba->scsi_host_added being false.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241016201249.2256266-10-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 26 ++++----------------------
 1 file changed, 4 insertions(+), 22 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 239e826f4b498..4103b1c9c388d 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -8753,7 +8753,8 @@ static int ufshcd_post_device_init(struct ufs_hba *hba)
 static int ufshcd_device_init(struct ufs_hba *hba, bool init_dev_params)
 {
 	int ret;
-	struct Scsi_Host *host = hba->host;
+
+	WARN_ON_ONCE(!hba->scsi_host_added);
 
 	hba->ufshcd_state = UFSHCD_STATE_RESET;
 
@@ -8794,27 +8795,8 @@ static int ufshcd_device_init(struct ufs_hba *hba, bool init_dev_params)
 		ret = ufshcd_device_params_init(hba);
 		if (ret)
 			return ret;
-		if (is_mcq_supported(hba) && !hba->scsi_host_added) {
-			ufshcd_mcq_enable(hba);
-			ret = ufshcd_alloc_mcq(hba);
-			if (!ret) {
-				ufshcd_config_mcq(hba);
-			} else {
-				/* Continue with SDB mode */
-				ufshcd_mcq_disable(hba);
-				use_mcq_mode = false;
-				dev_err(hba->dev, "MCQ mode is disabled, err=%d\n",
-					 ret);
-			}
-			ret = scsi_add_host(host, hba->dev);
-			if (ret) {
-				dev_err(hba->dev, "scsi_add_host failed\n");
-				return ret;
-			}
-			hba->scsi_host_added = true;
-		} else if (is_mcq_supported(hba) &&
-			   hba->quirks &
-				   UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH) {
+		if (is_mcq_supported(hba) &&
+		    hba->quirks & UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH) {
 			ufshcd_config_mcq(hba);
 			ufshcd_mcq_enable(hba);
 		}

From 72e979225ed2e9427396e317d33050bcf50ad899 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 16 Oct 2024 13:12:06 -0700
Subject: [PATCH 0665/1530] scsi: ufs: core: Move the MCQ scsi_add_host() call

Whether or not MCQ is used, call scsi_add_host() from
ufshcd_add_scsi_host().  For MCQ this patch swaps the order of the
scsi_add_host() and UFS device initialization. This patch prepares for
combining the two scsi_add_host() calls.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241016201249.2256266-11-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 41 ++++++++++++++++++---------------------
 1 file changed, 19 insertions(+), 22 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 4103b1c9c388d..fd2783623a897 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -10344,8 +10344,25 @@ static int ufshcd_add_scsi_host(struct ufs_hba *hba)
 {
 	int err;
 
-	if (!hba->scsi_host_added) {
-		WARN_ON_ONCE(is_mcq_supported(hba));
+	if (is_mcq_supported(hba)) {
+		ufshcd_mcq_enable(hba);
+		err = ufshcd_alloc_mcq(hba);
+		if (!err) {
+			ufshcd_config_mcq(hba);
+		} else {
+			/* Continue with SDB mode */
+			ufshcd_mcq_disable(hba);
+			use_mcq_mode = false;
+			dev_err(hba->dev, "MCQ mode is disabled, err=%d\n",
+				err);
+		}
+		err = scsi_add_host(hba->host, hba->dev);
+		if (err) {
+			dev_err(hba->dev, "scsi_add_host failed\n");
+			return err;
+		}
+		hba->scsi_host_added = true;
+	} else {
 		if (!hba->lsdb_sup) {
 			dev_err(hba->dev,
 				"%s: failed to initialize (legacy doorbell mode not supported)\n",
@@ -10606,26 +10623,6 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	if (err)
 		goto out_disable;
 
-	if (is_mcq_supported(hba)) {
-		ufshcd_mcq_enable(hba);
-		err = ufshcd_alloc_mcq(hba);
-		if (!err) {
-			ufshcd_config_mcq(hba);
-		} else {
-			/* Continue with SDB mode */
-			ufshcd_mcq_disable(hba);
-			use_mcq_mode = false;
-			dev_err(hba->dev, "MCQ mode is disabled, err=%d\n",
-				err);
-		}
-		err = scsi_add_host(host, hba->dev);
-		if (err) {
-			dev_err(hba->dev, "scsi_add_host failed\n");
-			goto out_disable;
-		}
-		hba->scsi_host_added = true;
-	}
-
 	err = ufshcd_post_device_init(hba);
 
 initialized:

From b92e5937e3523b0b7d41373681256bec78d7e134 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 16 Oct 2024 13:12:07 -0700
Subject: [PATCH 0666/1530] scsi: ufs: core: Move code out of an if-statement

The previous patch in this series introduced identical code in both
branches of an if-statement. Move that code outside the if-statement.

Reviewed-by: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241016201249.2256266-12-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 32 +++++++++++++-------------------
 1 file changed, 13 insertions(+), 19 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index fd2783623a897..099373a25017c 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -10356,26 +10356,20 @@ static int ufshcd_add_scsi_host(struct ufs_hba *hba)
 			dev_err(hba->dev, "MCQ mode is disabled, err=%d\n",
 				err);
 		}
-		err = scsi_add_host(hba->host, hba->dev);
-		if (err) {
-			dev_err(hba->dev, "scsi_add_host failed\n");
-			return err;
-		}
-		hba->scsi_host_added = true;
-	} else {
-		if (!hba->lsdb_sup) {
-			dev_err(hba->dev,
-				"%s: failed to initialize (legacy doorbell mode not supported)\n",
-				__func__);
-			return -EINVAL;
-		}
-		err = scsi_add_host(hba->host, hba->dev);
-		if (err) {
-			dev_err(hba->dev, "scsi_add_host failed\n");
-			return err;
-		}
-		hba->scsi_host_added = true;
 	}
+	if (!is_mcq_supported(hba) && !hba->lsdb_sup) {
+		dev_err(hba->dev,
+			"%s: failed to initialize (legacy doorbell mode not supported)\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	err = scsi_add_host(hba->host, hba->dev);
+	if (err) {
+		dev_err(hba->dev, "scsi_add_host failed\n");
+		return err;
+	}
+	hba->scsi_host_added = true;
 
 	hba->tmf_tag_set = (struct blk_mq_tag_set) {
 		.nr_hw_queues	= 1,

From 12dd12821f1eb2755643914df2cc900c5e8c9d12 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Fri, 4 Oct 2024 23:10:00 +0900
Subject: [PATCH 0667/1530] PCI: dwc: endpoint: Clear outbound address on unmap
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Clear the address mapped (outbound_addr array) in dw_pcie_ep_unmap_addr(),
to ensure that dw_pcie_find_index() does not match an ATU index that was
already unmapped.

This is in addition to clearing the ATU index bit in ob_window_map.

Link: https://lore.kernel.org/linux-pci/20241004141000.5080-1-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
[kwilczynski: commit log]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/dwc/pcie-designware-ep.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 43ba5c6738df1..b07ace7dc92ed 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -280,6 +280,7 @@ static void dw_pcie_ep_unmap_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	if (ret < 0)
 		return;
 
+	ep->outbound_addr[atu_index] = 0;
 	dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_OB, atu_index);
 	clear_bit(atu_index, ep->ob_window_map);
 }

From 47c3309d58b5e6fd3fc425253491c1ce014538c0 Mon Sep 17 00:00:00 2001
From: Markuss Broks <markuss.broks@gmail.com>
Date: Sat, 26 Oct 2024 23:32:34 +0300
Subject: [PATCH 0668/1530] dt-bindings: pinctrl: samsung: Add compatible for
 Exynos9810 SoC

Add a compatible for Samsung Exynos9810 pinctrl block to the schema.
Exynos9810 has 9 total pin banks and it's similar to other Samsung
SoC pinctrl blocks.

Co-developed-by: Maksym Holovach <nergzd@nergzd723.xyz>
Signed-off-by: Maksym Holovach <nergzd@nergzd723.xyz>
Signed-off-by: Markuss Broks <markuss.broks@gmail.com>
Link: https://lore.kernel.org/r/20241026-exynos9810-v3-3-b89de9441ea8@gmail.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
index 7e6ef8249de6c..5296a9e4faaec 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
@@ -54,6 +54,7 @@ properties:
       - samsung,exynos7885-pinctrl
       - samsung,exynos850-pinctrl
       - samsung,exynos8895-pinctrl
+      - samsung,exynos9810-pinctrl
       - samsung,exynos990-pinctrl
       - samsung,exynosautov9-pinctrl
       - samsung,exynosautov920-pinctrl

From e830431e0ad0501c2e6dcb3c65dabc053e3ce5e4 Mon Sep 17 00:00:00 2001
From: Markuss Broks <markuss.broks@gmail.com>
Date: Sat, 26 Oct 2024 23:32:35 +0300
Subject: [PATCH 0669/1530] dt-bindings: pinctrl: samsung: Add compatible for
 exynos9810-wakeup-eint

Add the compatible for Samsung Exynos9810 pinctrl eint block
to the schema. It is compatible with Exynos850 EINT controller,
and doesn't have a dedicated IRQ line.

Co-developed-by: Maksym Holovach <nergzd@nergzd723.xyz>
Signed-off-by: Maksym Holovach <nergzd@nergzd723.xyz>
Signed-off-by: Markuss Broks <markuss.broks@gmail.com>
Link: https://lore.kernel.org/r/20241026-exynos9810-v3-4-b89de9441ea8@gmail.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml       | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
index 565cacadb6be7..68ed714eb0a17 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
@@ -47,6 +47,7 @@ properties:
       - items:
           - enum:
               - google,gs101-wakeup-eint
+              - samsung,exynos9810-wakeup-eint
               - samsung,exynos990-wakeup-eint
               - samsung,exynosautov9-wakeup-eint
           - const: samsung,exynos850-wakeup-eint

From 6d2dbd4cec8939ad2b813b8052eb12406db528d7 Mon Sep 17 00:00:00 2001
From: Markuss Broks <markuss.broks@gmail.com>
Date: Sat, 26 Oct 2024 23:32:39 +0300
Subject: [PATCH 0670/1530] pinctrl: samsung: Add Exynos9810 SoC specific data

Add Samsung Exynos9810 SoC specific data to enable pinctrl
support for platforms based on Exynos9810.

Co-developed-by: Maksym Holovach <nergzd@nergzd723.xyz>
Signed-off-by: Maksym Holovach <nergzd@nergzd723.xyz>
Signed-off-by: Markuss Broks <markuss.broks@gmail.com>
Link: https://lore.kernel.org/r/20241026-exynos9810-v3-8-b89de9441ea8@gmail.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../pinctrl/samsung/pinctrl-exynos-arm64.c    | 154 ++++++++++++++++++
 drivers/pinctrl/samsung/pinctrl-samsung.c     |   2 +
 drivers/pinctrl/samsung/pinctrl-samsung.h     |   1 +
 3 files changed, 157 insertions(+)

diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
index f07c26d374425..3ea7106ce5eae 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
@@ -767,6 +767,160 @@ const struct samsung_pinctrl_of_match_data exynos990_of_data __initconst = {
 	.num_ctrl	= ARRAY_SIZE(exynos990_pin_ctrl),
 };
 
+/* pin banks of exynos9810 pin-controller 0 (ALIVE) */
+static const struct samsung_pin_bank_data exynos9810_pin_banks0[] __initconst = {
+	EXYNOS850_PIN_BANK_EINTN(6, 0x000, "etc1"),
+	EXYNOS850_PIN_BANK_EINTW(8, 0x020, "gpa0", 0x00),
+	EXYNOS850_PIN_BANK_EINTW(8, 0x040, "gpa1", 0x04),
+	EXYNOS850_PIN_BANK_EINTW(8, 0x060, "gpa2", 0x08),
+	EXYNOS850_PIN_BANK_EINTW(8, 0x080, "gpa3", 0x0c),
+	EXYNOS850_PIN_BANK_EINTN(6, 0x0A0, "gpq0"),
+	EXYNOS850_PIN_BANK_EINTW(2, 0x0C0, "gpa4", 0x10),
+};
+
+/* pin banks of exynos9810 pin-controller 1 (AUD) */
+static const struct samsung_pin_bank_data exynos9810_pin_banks1[] __initconst = {
+	EXYNOS850_PIN_BANK_EINTG(5, 0x000, "gpb0", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x020, "gpb1", 0x04),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x040, "gpb2", 0x08),
+};
+
+/* pin banks of exynos9810 pin-controller 2 (CHUB) */
+static const struct samsung_pin_bank_data exynos9810_pin_banks2[] __initconst = {
+	EXYNOS850_PIN_BANK_EINTG(8, 0x000, "gph0", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(5, 0x020, "gph1", 0x04),
+};
+
+/* pin banks of exynos9810 pin-controller 3 (CMGP) */
+static const struct samsung_pin_bank_data exynos9810_pin_banks3[] __initconst = {
+	EXYNOS850_PIN_BANK_EINTW(1, 0x000, "gpm0", 0x00),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x020, "gpm1", 0x04),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x040, "gpm2", 0x08),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x060, "gpm3", 0x0C),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x080, "gpm4", 0x10),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x0A0, "gpm5", 0x14),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x0C0, "gpm6", 0x18),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x0E0, "gpm7", 0x1C),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x100, "gpm10", 0x20),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x120, "gpm11", 0x24),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x140, "gpm12", 0x28),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x160, "gpm13", 0x2C),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x180, "gpm14", 0x30),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x1A0, "gpm15", 0x34),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x1C0, "gpm16", 0x38),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x1E0, "gpm17", 0x3C),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x200, "gpm40", 0x40),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x220, "gpm41", 0x44),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x240, "gpm42", 0x48),
+	EXYNOS850_PIN_BANK_EINTW(1, 0x260, "gpm43", 0x4C),
+};
+
+/* pin banks of exynos9810 pin-controller 4 (FSYS0) */
+static const struct samsung_pin_bank_data exynos9810_pin_banks4[] __initconst = {
+	EXYNOS850_PIN_BANK_EINTG(2, 0x000, "gpf0", 0x00),
+};
+
+/* pin banks of exynos9810 pin-controller 5 (FSYS1) */
+static const struct samsung_pin_bank_data exynos9810_pin_banks5[] __initconst = {
+	EXYNOS850_PIN_BANK_EINTG(7, 0x000, "gpf1", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(6, 0x020, "gpf2", 0x04),
+};
+
+/* pin banks of exynos9810 pin-controller 6 (PERIC0) */
+static const struct samsung_pin_bank_data exynos9810_pin_banks6[] __initconst = {
+	EXYNOS850_PIN_BANK_EINTG(8, 0x000, "gpp0", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x020, "gpp1", 0x04),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x040, "gpp2", 0x08),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x060, "gpp3", 0x0C),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x080, "gpg0", 0x10),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x0A0, "gpg1", 0x14),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x0C0, "gpg2", 0x18),
+};
+
+/* pin banks of exynos9810 pin-controller 7 (PERIC1) */
+static const struct samsung_pin_bank_data exynos9810_pin_banks7[] __initconst = {
+	EXYNOS850_PIN_BANK_EINTG(8, 0x000, "gpp4", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x020, "gpp5", 0x04),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x040, "gpp6", 0x08),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x060, "gpc0", 0x0C),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x080, "gpc1", 0x10),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x0A0, "gpd0", 0x14),
+	EXYNOS850_PIN_BANK_EINTG(7, 0x0C0, "gpg3", 0x18),
+};
+
+/* pin banks of exynos9810 pin-controller 8 (VTS) */
+static const struct samsung_pin_bank_data exynos9810_pin_banks8[] __initconst = {
+	EXYNOS850_PIN_BANK_EINTG(3, 0x000, "gpt0", 0x00),
+};
+
+static const struct samsung_pin_ctrl exynos9810_pin_ctrl[] __initconst = {
+	{
+		/* pin-controller instance 0 ALIVE data */
+		.pin_banks      = exynos9810_pin_banks0,
+		.nr_banks       = ARRAY_SIZE(exynos9810_pin_banks0),
+		.eint_wkup_init = exynos_eint_wkup_init,
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend        = exynos_pinctrl_suspend,
+		.resume         = exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 1 AUD data */
+		.pin_banks      = exynos9810_pin_banks1,
+		.nr_banks       = ARRAY_SIZE(exynos9810_pin_banks1),
+	}, {
+		/* pin-controller instance 2 CHUB data */
+		.pin_banks      = exynos9810_pin_banks2,
+		.nr_banks       = ARRAY_SIZE(exynos9810_pin_banks2),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend        = exynos_pinctrl_suspend,
+		.resume         = exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 3 CMGP data */
+		.pin_banks      = exynos9810_pin_banks3,
+		.nr_banks       = ARRAY_SIZE(exynos9810_pin_banks3),
+		.eint_wkup_init = exynos_eint_wkup_init,
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend        = exynos_pinctrl_suspend,
+		.resume         = exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 4 FSYS0 data */
+		.pin_banks      = exynos9810_pin_banks4,
+		.nr_banks       = ARRAY_SIZE(exynos9810_pin_banks4),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend        = exynos_pinctrl_suspend,
+		.resume         = exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 5 FSYS1 data */
+		.pin_banks      = exynos9810_pin_banks5,
+		.nr_banks       = ARRAY_SIZE(exynos9810_pin_banks5),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend        = exynos_pinctrl_suspend,
+		.resume         = exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 6 PERIC0 data */
+		.pin_banks      = exynos9810_pin_banks6,
+		.nr_banks       = ARRAY_SIZE(exynos9810_pin_banks6),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend        = exynos_pinctrl_suspend,
+		.resume         = exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 7 PERIC1 data */
+		.pin_banks      = exynos9810_pin_banks7,
+		.nr_banks       = ARRAY_SIZE(exynos9810_pin_banks7),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend        = exynos_pinctrl_suspend,
+		.resume         = exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 8 VTS data */
+		.pin_banks      = exynos9810_pin_banks8,
+		.nr_banks       = ARRAY_SIZE(exynos9810_pin_banks8),
+	},
+};
+
+const struct samsung_pinctrl_of_match_data exynos9810_of_data __initconst = {
+	.ctrl		= exynos9810_pin_ctrl,
+	.num_ctrl	= ARRAY_SIZE(exynos9810_pin_ctrl),
+};
+
 /* pin banks of exynosautov9 pin-controller 0 (ALIVE) */
 static const struct samsung_pin_bank_data exynosautov9_pin_banks0[] __initconst = {
 	EXYNOS850_PIN_BANK_EINTW(8, 0x000, "gpa0", 0x00),
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index 42e40860841bc..bbedd980ec672 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -1479,6 +1479,8 @@ static const struct of_device_id samsung_pinctrl_dt_match[] = {
 		.data = &exynos850_of_data },
 	{ .compatible = "samsung,exynos8895-pinctrl",
 		.data = &exynos8895_of_data },
+	{ .compatible = "samsung,exynos9810-pinctrl",
+		.data = &exynos9810_of_data },
 	{ .compatible = "samsung,exynos990-pinctrl",
 		.data = &exynos990_of_data },
 	{ .compatible = "samsung,exynosautov9-pinctrl",
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index 615048f945243..bb0689d52ea0b 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -385,6 +385,7 @@ extern const struct samsung_pinctrl_of_match_data exynos7_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos7885_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos850_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos8895_of_data;
+extern const struct samsung_pinctrl_of_match_data exynos9810_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos990_of_data;
 extern const struct samsung_pinctrl_of_match_data exynosautov9_of_data;
 extern const struct samsung_pinctrl_of_match_data exynosautov920_of_data;

From 98b7beba1ee6fb4ee755812e6c06cfc9084e7430 Mon Sep 17 00:00:00 2001
From: Hua Su <suhua.tanke@gmail.com>
Date: Mon, 21 Oct 2024 13:11:51 +0800
Subject: [PATCH 0671/1530] memblock: uniformly initialize all reserved pages
 to MIGRATE_MOVABLE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently when CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set, the reserved
pages are initialized to MIGRATE_MOVABLE by default in memmap_init.

Reserved memory mainly store the metadata of struct page. When
HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=Y and hugepages are allocated,
the HVO will remap the vmemmap virtual address range to the page which
vmemmap_reuse is mapped to. The pages previously mapping the range will
be freed to the buddy system.

Before this patch:
when CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set, the freed memory was
placed on the Movable list;
When CONFIG_DEFERRED_STRUCT_PAGE_INIT=Y, the freed memory was placed on
the Unmovable list.

After this patch, the freed memory is placed on the Movable list
regardless of whether CONFIG_DEFERRED_STRUCT_PAGE_INIT is set.

Eg:
Tested on a virtual machine(1000GB):
Intel(R) Xeon(R) Platinum 8358P CPU

After vm start:
echo 500000 > /proc/sys/vm/nr_hugepages
cat /proc/meminfo | grep -i huge
HugePages_Total:   500000
HugePages_Free:    500000
HugePages_Rsvd:        0
HugePages_Surp:        0
Hugepagesize:       2048 kB
Hugetlb:        1024000000 kB

cat /proc/pagetypeinfo
before：
Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
…
Node    0, zone   Normal, type    Unmovable     51      2      1     28     53     35     35     43     40     69   3852
Node    0, zone   Normal, type      Movable   6485   4610    666    202    200    185    208     87     54      2    240
Node    0, zone   Normal, type  Reclaimable      2      2      1     23     13      1      2      1      0      1      0
Node    0, zone   Normal, type   HighAtomic      0      0      0      0      0      0      0      0      0      0      0
Node    0, zone   Normal, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
Unmovable ≈ 15GB

after：
Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
…
Node    0, zone   Normal, type    Unmovable      0      1      1      0      0      0      0      1      1      1      0
Node    0, zone   Normal, type      Movable   1563   4107   1119    189    256    368    286    132    109      4   3841
Node    0, zone   Normal, type  Reclaimable      2      2      1     23     13      1      2      1      0      1      0
Node    0, zone   Normal, type   HighAtomic      0      0      0      0      0      0      0      0      0      0      0
Node    0, zone   Normal, type      Isolate      0      0      0      0      0      0      0      0      0      0      0

Signed-off-by: Hua Su <suhua.tanke@gmail.com>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Link: https://lore.kernel.org/r/20241021051151.4664-1-suhua.tanke@gmail.com
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
 mm/mm_init.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/mm_init.c b/mm/mm_init.c
index 253972926183c..38ce5f45090e0 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -723,6 +723,9 @@ static void __meminit init_reserved_page(unsigned long pfn, int nid)
 			break;
 	}
 	__init_single_page(pfn_to_page(pfn), pfn, zid, nid);
+
+	if (pageblock_aligned(pfn))
+		set_pageblock_migratetype(pfn_to_page(pfn), MIGRATE_MOVABLE);
 }
 #else
 static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {}

From b7688fcde3cfdd8489421b8eeeb908733316d638 Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Mon, 28 Oct 2024 10:44:42 +0100
Subject: [PATCH 0672/1530] firewire: ohci: Replace deprecated PCI functions

pcim_iomap_regions() and pcim_iomap_table() have been deprecated in
commit e354bb84a4c1 ("PCI: Deprecate pcim_iomap_table(),
pcim_iomap_regions_request_all()").

Replace these functions with pcim_iomap_region().

Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Link: https://lore.kernel.org/r/20241028094440.19115-3-pstanner@redhat.com
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
---
 drivers/firewire/ohci.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 4dbd203602233..c02aed11b5902 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -3726,12 +3726,11 @@ static int pci_probe(struct pci_dev *dev,
 		return -ENXIO;
 	}
 
-	err = pcim_iomap_regions(dev, 1 << 0, ohci_driver_name);
-	if (err) {
+	ohci->registers = pcim_iomap_region(dev, 0, ohci_driver_name);
+	if (IS_ERR(ohci->registers)) {
 		ohci_err(ohci, "request and map MMIO resource unavailable\n");
 		return -ENXIO;
 	}
-	ohci->registers = pcim_iomap_table(dev)[0];
 
 	for (i = 0; i < ARRAY_SIZE(ohci_quirks); i++)
 		if ((ohci_quirks[i].vendor == dev->vendor) &&

From 3ad8d3ec6d87b16cdd336aa065d8e150096a192b Mon Sep 17 00:00:00 2001
From: Himanshu Bhavani <himanshu.bhavani@siliconsignals.io>
Date: Mon, 28 Oct 2024 12:09:11 +0530
Subject: [PATCH 0673/1530] dt-bindings: pinctrl: convert pinctrl-mcp23s08.txt
 to yaml format

YAML binding file provides the conversion of the original text-based
binding for the pinctrl-mcp23s08 to microchip,mcp23s08.yaml.

following compatible strings using the deprecated mcp prefix have been
removed from this binding:

- mcp,mcp23s08
- mcp,mcp23s17
- mcp,mcp23008
- mcp,mcp23017

Signed-off-by: Himanshu Bhavani <himanshu.bhavani@siliconsignals.io>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/20241028063939.6276-1-himanshu.bhavani@siliconsignals.io
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/microchip,mcp23s08.yaml  | 161 ++++++++++++++++++
 .../bindings/pinctrl/pinctrl-mcp23s08.txt     | 148 ----------------
 2 files changed, 161 insertions(+), 148 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/microchip,mcp23s08.yaml
 delete mode 100644 Documentation/devicetree/bindings/pinctrl/pinctrl-mcp23s08.txt

diff --git a/Documentation/devicetree/bindings/pinctrl/microchip,mcp23s08.yaml b/Documentation/devicetree/bindings/pinctrl/microchip,mcp23s08.yaml
new file mode 100644
index 0000000000000..e07f4723de177
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/microchip,mcp23s08.yaml
@@ -0,0 +1,161 @@
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/microchip,mcp23s08.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Microchip I/O expander with serial interface (I2C/SPI)
+
+maintainers:
+  - Himanshu Bhavani <himanshu.bhavani@siliconsignals.io>
+
+description:
+  Microchip MCP23008, MCP23017, MCP23S08, MCP23S17, MCP23S18 GPIO expander
+  chips.These chips provide 8 or 16 GPIO pins with either I2C or SPI interface.
+
+allOf:
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
+
+properties:
+  compatible:
+    enum:
+      - microchip,mcp23s08
+      - microchip,mcp23s17
+      - microchip,mcp23s18
+      - microchip,mcp23008
+      - microchip,mcp23017
+      - microchip,mcp23018
+
+  reg:
+    maxItems: 1
+
+  gpio-controller: true
+
+  '#gpio-cells':
+    const: 2
+
+  interrupt-controller: true
+
+  '#interrupt-cells':
+    const: 2
+
+  interrupts:
+    maxItems: 1
+
+  reset-gpios:
+    description: GPIO specifier for active-low reset pin.
+    maxItems: 1
+
+  microchip,spi-present-mask:
+    description:
+      Multiple SPI chips can share the same SPI chipselect. Set a bit in
+      bit0-7 in this mask to 1 if there is a chip connected with the
+      corresponding spi address set. For example if you have a chip with
+      address 3 connected, you have to set bit3 to 1, which is 0x08. mcp23s08
+      chip variant only supports bits 0-3. It is not possible to mix mcp23s08
+      and mcp23s17 on the same chipselect. Set at least one bit to 1 for SPI
+      chips.
+    $ref: /schemas/types.yaml#/definitions/uint8
+
+  microchip,irq-mirror:
+    type: boolean
+    description:
+      Sets the mirror flag in the IOCON register. Devices with two interrupt
+      outputs (these are the devices ending with 17 and those that have 16 IOs)
+      have two IO banks IO 0-7 form bank 1 and IO 8-15 are bank 2. These chips
+      have two different interrupt outputs One for bank 1 and another for
+      bank 2. If irq-mirror is set, both interrupts are generated regardless of
+      the bank that an input change occurred on. If it is not set,the interrupt
+      are only generated for the bank they belong to.
+
+  microchip,irq-active-high:
+    type: boolean
+    description:
+      Sets the INTPOL flag in the IOCON register.This configures the IRQ output
+      polarity as active high.
+
+  drive-open-drain:
+    type: boolean
+    description:
+      Sets the ODR flag in the IOCON register. This configures the IRQ output as
+      open drain active low.
+
+  pinmux:
+    type: object
+    properties:
+      pins:
+        description:
+          The list of GPIO pins controlled by this node. Each pin name
+          corresponds to a physical pin on the GPIO expander.
+        items:
+          pattern: '^gpio([0-9]|[1][0-5])$'
+        maxItems: 16
+
+      bias-pull-up:
+        type: boolean
+        description:
+          Configures pull-up resistors for the GPIO pins. Absence of this
+          property will leave the configuration in its default state.
+
+    required:
+      - pins
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - gpio-controller
+  - '#gpio-cells'
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/gpio/gpio.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        gpio@21 {
+            compatible = "microchip,mcp23017";
+            reg = <0x21>;
+            gpio-controller;
+            #gpio-cells = <2>;
+
+            interrupt-parent = <&gpio1>;
+            interrupts = <17 IRQ_TYPE_LEVEL_LOW>;
+            interrupt-controller;
+            #interrupt-cells = <2>;
+
+            microchip,irq-mirror;
+            pinctrl-names = "default";
+            pinctrl-0 = <&pinctrl_i2c_gpio0>, <&gpiopullups>;
+            reset-gpios = <&gpio6 15 GPIO_ACTIVE_LOW>;
+
+            gpiopullups: pinmux {
+                pins = "gpio0", "gpio1", "gpio2", "gpio3",
+                       "gpio4", "gpio5", "gpio6", "gpio7",
+                       "gpio8", "gpio9", "gpio10", "gpio11",
+                       "gpio12", "gpio13", "gpio14", "gpio15";
+                bias-pull-up;
+            };
+        };
+    };
+
+  - |
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        gpio@0 {
+            compatible = "microchip,mcp23s17";
+            reg = <0>;
+            gpio-controller;
+            #gpio-cells = <2>;
+            spi-max-frequency = <1000000>;
+            microchip,spi-present-mask = /bits/ 8 <0x01>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-mcp23s08.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-mcp23s08.txt
deleted file mode 100644
index 2fa5edac7a35a..0000000000000
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-mcp23s08.txt
+++ /dev/null
@@ -1,148 +0,0 @@
-Microchip MCP2308/MCP23S08/MCP23017/MCP23S17 driver for
-8-/16-bit I/O expander with serial interface (I2C/SPI)
-
-Required properties:
-- compatible : Should be
-    - "mcp,mcp23s08" (DEPRECATED) for  8 GPIO SPI version
-    - "mcp,mcp23s17" (DEPRECATED) for 16 GPIO SPI version
-    - "mcp,mcp23008" (DEPRECATED) for  8 GPIO I2C version or
-    - "mcp,mcp23017" (DEPRECATED) for 16 GPIO I2C version of the chip
-
-    - "microchip,mcp23s08" for  8 GPIO SPI version
-    - "microchip,mcp23s17" for 16 GPIO SPI version
-    - "microchip,mcp23s18" for 16 GPIO SPI version
-    - "microchip,mcp23008" for  8 GPIO I2C version or
-    - "microchip,mcp23017" for 16 GPIO I2C version of the chip
-    - "microchip,mcp23018" for 16 GPIO I2C version
-    NOTE: Do not use the old mcp prefix any more. It is deprecated and will be
-    removed.
-- #gpio-cells : Should be two.
-  - first cell is the pin number
-  - second cell is used to specify flags as described in
-    'Documentation/devicetree/bindings/gpio/gpio.txt'. Allowed values defined by
-    'include/dt-bindings/gpio/gpio.h' (e.g. GPIO_ACTIVE_LOW).
-- gpio-controller : Marks the device node as a GPIO controller.
-- reg : For an address on its bus. I2C uses this a the I2C address of the chip.
-        SPI uses this to specify the chipselect line which the chip is
-        connected to. The driver and the SPI variant of the chip support
-        multiple chips on the same chipselect. Have a look at
-        microchip,spi-present-mask below.
-
-Required device specific properties (only for SPI chips):
-- mcp,spi-present-mask (DEPRECATED)
-- microchip,spi-present-mask : This is a present flag, that makes only sense for SPI
-        chips - as the name suggests. Multiple SPI chips can share the same
-        SPI chipselect. Set a bit in bit0-7 in this mask to 1 if there is a
-        chip connected with the corresponding spi address set. For example if
-        you have a chip with address 3 connected, you have to set bit3 to 1,
-        which is 0x08. mcp23s08 chip variant only supports bits 0-3. It is not
-        possible to mix mcp23s08 and mcp23s17 on the same chipselect. Set at
-        least one bit to 1 for SPI chips.
-    NOTE: Do not use the old mcp prefix any more. It is deprecated and will be
-    removed.
-- spi-max-frequency = The maximum frequency this chip is able to handle
-
-Optional properties:
-- #interrupt-cells : Should be two.
-  - first cell is the pin number
-  - second cell is used to specify flags.
-- interrupt-controller: Marks the device node as a interrupt controller.
-- drive-open-drain: Sets the ODR flag in the IOCON register. This configures
-        the IRQ output as open drain active low.
-- reset-gpios: Corresponds to the active-low RESET# pin for the chip
-
-Optional device specific properties:
-- microchip,irq-mirror: Sets the mirror flag in the IOCON register. Devices
-        with two interrupt outputs (these are the devices ending with 17 and
-        those that have 16 IOs) have two IO banks: IO 0-7 form bank 1 and
-        IO 8-15 are bank 2. These chips have two different interrupt outputs:
-        One for bank 1 and another for bank 2. If irq-mirror is set, both
-        interrupts are generated regardless of the bank that an input change
-        occurred on. If it is not set, the interrupt are only generated for the
-        bank they belong to.
-        On devices with only one interrupt output this property is useless.
-- microchip,irq-active-high: Sets the INTPOL flag in the IOCON register. This
-        configures the IRQ output polarity as active high.
-
-Example I2C (with interrupt):
-gpiom1: gpio@20 {
-        compatible = "microchip,mcp23017";
-        gpio-controller;
-        #gpio-cells = <2>;
-        reg = <0x20>;
-
-        interrupt-parent = <&gpio1>;
-        interrupts = <17 IRQ_TYPE_LEVEL_LOW>;
-        interrupt-controller;
-        #interrupt-cells=<2>;
-        microchip,irq-mirror;
-};
-
-Example SPI:
-gpiom1: gpio@0 {
-        compatible = "microchip,mcp23s17";
-        gpio-controller;
-        #gpio-cells = <2>;
-        microchip,spi-present-mask = <0x01>;
-        reg = <0>;
-        spi-max-frequency = <1000000>;
-};
-
-Pull-up configuration
-=====================
-
-If pins are used as output, they can also be configured with pull-ups. This is
-done with pinctrl.
-
-Please refer file <devicetree/bindings/pinctrl/pinctrl-bindings.txt>
-for details of the common pinctrl bindings used by client devices,
-including the meaning of the phrase "pin configuration node".
-
-Optional Pinmux properties:
---------------------------
-Following properties are required if default setting of pins are required
-at boot.
-- pinctrl-names: A pinctrl state named per <pinctrl-bindings.txt>.
-- pinctrl[0...n]: Properties to contain the phandle for pinctrl states per
-		<pinctrl-bindings.txt>.
-
-The pin configurations are defined as child of the pinctrl states node. Each
-sub-node have following properties:
-
-Required properties:
-------------------
-- pins: List of pins. Valid values of pins properties are:
-		      gpio0 ... gpio7 for the devices with 8 GPIO pins and
-		      gpio0 ... gpio15 for the devices with 16 GPIO pins.
-
-Optional properties:
--------------------
-The following optional property is defined in the pinmux DT binding document
-<pinctrl-bindings.txt>. Absence of this property will leave the configuration
-in its default state.
-	bias-pull-up
-
-Example with pinctrl to pull-up output pins:
-gpio21: gpio@21 {
-	compatible = "microchip,mcp23017";
-	gpio-controller;
-	#gpio-cells = <0x2>;
-	reg = <0x21>;
-	interrupt-parent = <&socgpio>;
-	interrupts = <0x17 0x8>;
-	interrupt-names = "mcp23017@21 irq";
-	interrupt-controller;
-	#interrupt-cells = <0x2>;
-	microchip,irq-mirror;
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2cgpio0irq>, <&gpio21pullups>;
-	reset-gpios = <&gpio6 15 GPIO_ACTIVE_LOW>;
-
-	gpio21pullups: pinmux {
-		pins =	"gpio0", "gpio1", "gpio2", "gpio3",
-			"gpio4", "gpio5", "gpio6", "gpio7",
-			"gpio8", "gpio9", "gpio10", "gpio11",
-			"gpio12", "gpio13", "gpio14", "gpio15";
-		bias-pull-up;
-	};
-};

From 5a18e2be454f51c7f698d47d8b2cf3b92a5a3ec1 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 23 Oct 2024 11:39:47 +0300
Subject: [PATCH 0674/1530] pinctrl: spacemit: fix double free of map

The map pointer is freed by pinctrl_utils_free_map().  It must not be a
devm_ pointer or it leads to a double free when the device is unloaded.

This is similar to a couple bugs Harshit Mogalapalli fixed earlier in
commits 3fd976afe974 ("pinctrl: nuvoton: fix a double free in
ma35_pinctrl_dt_node_to_map_func()") and 4575962aeed6 ("pinctrl: sophgo:
fix double free in cv1800_pctrl_dt_node_to_map()").

Fixes: a83c29e1d145 ("pinctrl: spacemit: add support for SpacemiT K1 SoC")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Acked-by: Yixun Lan <dlan@gentoo.org>
Link: https://lore.kernel.org/4b5f1306-dc01-4edc-96d3-b232b930ddf2@stanley.mountain
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/spacemit/pinctrl-k1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/spacemit/pinctrl-k1.c b/drivers/pinctrl/spacemit/pinctrl-k1.c
index c75ea27b23446..a32579d736130 100644
--- a/drivers/pinctrl/spacemit/pinctrl-k1.c
+++ b/drivers/pinctrl/spacemit/pinctrl-k1.c
@@ -314,7 +314,7 @@ static int spacemit_pctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
 	if (!grpnames)
 		return -ENOMEM;
 
-	map = devm_kcalloc(dev, ngroups * 2, sizeof(*map), GFP_KERNEL);
+	map = kcalloc(ngroups * 2, sizeof(*map), GFP_KERNEL);
 	if (!map)
 		return -ENOMEM;
 

From c34b20622e4f8da23503ca953b7aa23dc3c45659 Mon Sep 17 00:00:00 2001
From: Billy Tsai <billy_tsai@aspeedtech.com>
Date: Wed, 23 Oct 2024 18:44:06 +0800
Subject: [PATCH 0675/1530] pinctrl: aspeed-g6: Support drive-strength for
 GPIOF/G

Add drive strength configuration support for GPIO F and G groups.

Signed-off-by: Billy Tsai <billy_tsai@aspeedtech.com>
Reviewed-by: Andrew Jeffery <andrew@codeconstruct.com.au>
Link: https://lore.kernel.org/20241023104406.4083460-1-billy_tsai@aspeedtech.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c
index 6ecc656abc44f..5a7cd0a886876 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c
@@ -2607,6 +2607,10 @@ static struct aspeed_pin_config aspeed_g6_configs[] = {
 	{ PIN_CONFIG_DRIVE_STRENGTH, { AB8, AB8 }, SCU454, GENMASK(27, 26)},
 	/* LAD0 */
 	{ PIN_CONFIG_DRIVE_STRENGTH, { AB7, AB7 }, SCU454, GENMASK(25, 24)},
+	/* GPIOF */
+	{ PIN_CONFIG_DRIVE_STRENGTH, { D22, A23 }, SCU458, GENMASK(9, 8)},
+	/* GPIOG */
+	{ PIN_CONFIG_DRIVE_STRENGTH, { E21, B21 }, SCU458, GENMASK(11, 10)},
 
 	/* MAC3 */
 	{ PIN_CONFIG_POWER_SOURCE,   { H24, E26 }, SCU458, BIT_MASK(4)},

From 5ce42b5de461c3154f61a023b191dd6b77ee66c0 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 25 Oct 2024 12:21:00 -0700
Subject: [PATCH 0676/1530] tools subcmd: Add non-waitpid
 check_if_command_finished()

Using waitpid can cause stdout/stderr of the child process to be
lost. Use Linux's /prod/<pid>/status file to determine if the process
has reached the zombie state. Use the 'status' file rather than 'stat'
to avoid issues around skipping the process name.

Tested-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Ilya Leoshkevich <iii@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241025192109.132482-2-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/lib/subcmd/run-command.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/tools/lib/subcmd/run-command.c b/tools/lib/subcmd/run-command.c
index 4e3a557a2f374..0a764c25c384f 100644
--- a/tools/lib/subcmd/run-command.c
+++ b/tools/lib/subcmd/run-command.c
@@ -2,6 +2,7 @@
 #include <unistd.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <ctype.h>
 #include <fcntl.h>
 #include <string.h>
 #include <linux/string.h>
@@ -217,8 +218,40 @@ static int wait_or_whine(struct child_process *cmd, bool block)
 
 int check_if_command_finished(struct child_process *cmd)
 {
+#ifdef __linux__
+	char filename[FILENAME_MAX + 12];
+	char status_line[256];
+	FILE *status_file;
+
+	/*
+	 * Check by reading /proc/<pid>/status as calling waitpid causes
+	 * stdout/stderr to be closed and data lost.
+	 */
+	sprintf(filename, "/proc/%d/status", cmd->pid);
+	status_file = fopen(filename, "r");
+	if (status_file == NULL) {
+		/* Open failed assume finish_command was called. */
+		return true;
+	}
+	while (fgets(status_line, sizeof(status_line), status_file) != NULL) {
+		char *p;
+
+		if (strncmp(status_line, "State:", 6))
+			continue;
+
+		fclose(status_file);
+		p = status_line + 6;
+		while (isspace(*p))
+			p++;
+		return *p == 'Z' ? 1 : 0;
+	}
+	/* Read failed assume finish_command was called. */
+	fclose(status_file);
+	return 1;
+#else
 	wait_or_whine(cmd, /*block=*/false);
 	return cmd->finished;
+#endif
 }
 
 int finish_command(struct child_process *cmd)

From 0e036dcad4e62b89f8df3e41402babb9345521af Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 25 Oct 2024 12:21:01 -0700
Subject: [PATCH 0677/1530] perf test: Display number of active running tests

Before polling or sleeping to wait for a test to complete, print out
": Running (<num> active)" where the number of active tests is
determined by iterating over the tests and seeing which return false
for check_if_command_finished. The line erasing and printing out only
occur if the number of runnings tests changes to avoid the line
flickering excessively. Knowing tests are running allows a user to
know a test is running and in parallel mode how many of the tests are
waiting to complete. If color mode is disabled then avoid displaying
the "Running" message as deleting the line isn't reliable.

Tested-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Ilya Leoshkevich <iii@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241025192109.132482-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/builtin-test.c | 93 ++++++++++++++++++++++-----------
 tools/perf/util/color.h         |  1 +
 2 files changed, 63 insertions(+), 31 deletions(-)

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 7d27e30d9b2db..57d2e9e03fbce 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -245,7 +245,10 @@ static int run_test_child(struct child_process *process)
 	return -err;
 }
 
-static int print_test_result(struct test_suite *t, int i, int subtest, int result, int width)
+#define TEST_RUNNING -3
+
+static int print_test_result(struct test_suite *t, int i, int subtest, int result, int width,
+			     int running)
 {
 	if (has_subtests(t)) {
 		int subw = width > 2 ? width - 2 : width;
@@ -255,6 +258,9 @@ static int print_test_result(struct test_suite *t, int i, int subtest, int resul
 		pr_info("%3d: %-*s:", i + 1, width, test_description(t, subtest));
 
 	switch (result) {
+	case TEST_RUNNING:
+		color_fprintf(stderr, PERF_COLOR_YELLOW, " Running (%d active)\n", running);
+		break;
 	case TEST_OK:
 		pr_info(" Ok\n");
 		break;
@@ -276,14 +282,17 @@ static int print_test_result(struct test_suite *t, int i, int subtest, int resul
 	return 0;
 }
 
-static int finish_test(struct child_test *child_test, int width)
+static int finish_test(struct child_test **child_tests, int running_test, int child_test_num,
+		       int width)
 {
+	struct child_test *child_test = child_tests[running_test];
 	struct test_suite *t = child_test->test;
 	int i = child_test->test_num;
 	int subi = child_test->subtest;
 	int err = child_test->process.err;
-	bool err_done = err <= 0;
+	bool err_done = false;
 	struct strbuf err_output = STRBUF_INIT;
+	int last_running = -1;
 	int ret;
 
 	/*
@@ -297,7 +306,7 @@ static int finish_test(struct child_test *child_test, int width)
 	 * Busy loop reading from the child's stdout/stderr that are set to be
 	 * non-blocking until EOF.
 	 */
-	if (!err_done)
+	if (err > 0)
 		fcntl(err, F_SETFL, O_NONBLOCK);
 	if (verbose > 1) {
 		if (has_subtests(t))
@@ -311,38 +320,60 @@ static int finish_test(struct child_test *child_test, int width)
 			  .events = POLLIN | POLLERR | POLLHUP | POLLNVAL,
 			},
 		};
-		char buf[512];
-		ssize_t len;
-
-		/* Poll to avoid excessive spinning, timeout set for 100ms. */
-		poll(pfds, ARRAY_SIZE(pfds), /*timeout=*/100);
-		if (!err_done && pfds[0].revents) {
-			errno = 0;
-			len = read(err, buf, sizeof(buf) - 1);
-
-			if (len <= 0) {
-				err_done = errno != EAGAIN;
-			} else {
-				buf[len] = '\0';
-				if (verbose > 1)
-					fprintf(stdout, "%s", buf);
-				else
+		if (perf_use_color_default) {
+			int running = 0;
+
+			for (int y = running_test; y < child_test_num; y++) {
+				if (check_if_command_finished(&child_tests[y]->process) == 0)
+					running++;
+			}
+			if (running != last_running) {
+				if (last_running != -1) {
+					/*
+					 * Erase "Running (.. active)" line
+					 * printed before poll/sleep.
+					 */
+					fprintf(debug_file(), PERF_COLOR_DELETE_LINE);
+				}
+				print_test_result(t, i, subi, TEST_RUNNING, width, running);
+				last_running = running;
+			}
+		}
+
+		err_done = true;
+		if (err <= 0) {
+			/* No child stderr to poll, sleep for 10ms for child to complete. */
+			usleep(10 * 1000);
+		} else {
+			/* Poll to avoid excessive spinning, timeout set for 100ms. */
+			poll(pfds, ARRAY_SIZE(pfds), /*timeout=*/100);
+			if (pfds[0].revents) {
+				char buf[512];
+				ssize_t len;
+
+				len = read(err, buf, sizeof(buf) - 1);
+
+				if (len > 0) {
+					err_done = false;
+					buf[len] = '\0';
 					strbuf_addstr(&err_output, buf);
+				}
 			}
 		}
+		if (err_done)
+			err_done = check_if_command_finished(&child_test->process);
+	}
+	if (perf_use_color_default && last_running != -1) {
+		/* Erase "Running (.. active)" line printed before poll/sleep. */
+		fprintf(debug_file(), PERF_COLOR_DELETE_LINE);
 	}
 	/* Clean up child process. */
 	ret = finish_command(&child_test->process);
-	if (verbose == 1 && ret == TEST_FAIL) {
-		/* Add header for test that was skipped above. */
-		if (has_subtests(t))
-			pr_info("%3d.%1d: %s:\n", i + 1, subi + 1, test_description(t, subi));
-		else
-			pr_info("%3d: %s:\n", i + 1, test_description(t, -1));
+	if (verbose > 1 || (verbose == 1 && ret == TEST_FAIL))
 		fprintf(stderr, "%s", err_output.buf);
-	}
+
 	strbuf_release(&err_output);
-	print_test_result(t, i, subi, ret, width);
+	print_test_result(t, i, subi, ret, width, /*running=*/0);
 	if (err > 0)
 		close(err);
 	return 0;
@@ -358,7 +389,7 @@ static int start_test(struct test_suite *test, int i, int subi, struct child_tes
 		pr_debug("--- start ---\n");
 		err = test_function(test, subi)(test, subi);
 		pr_debug("---- end ----\n");
-		print_test_result(test, i, subi, err, width);
+		print_test_result(test, i, subi, err, width, /*running=*/0);
 		return 0;
 	}
 
@@ -383,7 +414,7 @@ static int start_test(struct test_suite *test, int i, int subi, struct child_tes
 	err = start_command(&(*child)->process);
 	if (err || !sequential)
 		return  err;
-	return finish_test(*child, width);
+	return finish_test(child, /*running_test=*/0, /*child_test_num=*/1, width);
 }
 
 #define for_each_test(j, k, t)					\
@@ -468,7 +499,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 	}
 	for (i = 0; i < child_test_num; i++) {
 		if (!sequential) {
-			int ret  = finish_test(child_tests[i], width);
+			int ret  = finish_test(child_tests, i, child_test_num, width);
 
 			if (ret)
 				return ret;
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index b2f37de305f63..9a7248dbe2d74 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -23,6 +23,7 @@
 #define MIN_GREEN	0.5
 #define MIN_RED		5.0
 
+#define PERF_COLOR_DELETE_LINE	"\033[A\33[2K\r"
 /*
  * This variable stores the value of color.ui
  */

From d50318fe00d176c5ee5de9092ca092bee05a9eb6 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 25 Oct 2024 12:21:02 -0700
Subject: [PATCH 0678/1530] perf test: Reduce scope of parallel variable

The variable duplicates sequential but is only used for command line
argument processing. Reduce scope to make the behavior clearer.

Tested-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Ilya Leoshkevich <iii@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241025192109.132482-4-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/builtin-test.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 57d2e9e03fbce..0e8f877f4b1f0 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -41,9 +41,6 @@
 static bool dont_fork;
 /* Don't fork the tests in parallel and wait for their completion. */
 static bool sequential = true;
-/* Do it in parallel, lacks infrastructure to avoid running tests that clash for resources,
- * So leave it as the developers choice to enable while working on the needed infra */
-static bool parallel;
 const char *dso_to_test;
 const char *test_objdump_path = "objdump";
 
@@ -578,6 +575,12 @@ int cmd_test(int argc, const char **argv)
 	const char *skip = NULL;
 	const char *workload = NULL;
 	bool list_workloads = false;
+	/*
+	 * Run tests in parallel, lacks infrastructure to avoid running tests
+	 * that clash for resources, So leave it as the developers choice to
+	 * enable while working on the needed infra.
+	 */
+	bool parallel = false;
 	const struct option test_options[] = {
 	OPT_STRING('s', "skip", &skip, "tests", "tests to skip"),
 	OPT_INCR('v', "verbose", &verbose,

From 2c66343927eebe799324410f1ca9cde79e71dbe4 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 25 Oct 2024 12:21:03 -0700
Subject: [PATCH 0679/1530] perf test: Avoid list test blocking on writing to
 stdout

Python's json.tool will output the input json to stdout. Redirect to
/dev/null to avoid blocking on stdout writes.

Tested-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Ilya Leoshkevich <iii@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241025192109.132482-5-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/list.sh | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/list.sh b/tools/perf/tests/shell/list.sh
index 8a868ae64560e..76a9846cff223 100755
--- a/tools/perf/tests/shell/list.sh
+++ b/tools/perf/tests/shell/list.sh
@@ -24,8 +24,11 @@ trap trap_cleanup EXIT TERM INT
 
 test_list_json() {
   echo "Json output test"
+  # Generate perf list json output into list_output file.
   perf list -j -o "${list_output}"
-  $PYTHON -m json.tool "${list_output}"
+  # Validate the json using python, redirect the json copy to /dev/null as
+  # otherwise the test may block writing to stdout.
+  $PYTHON -m json.tool "${list_output}" /dev/null
   echo "Json output test [Success]"
 }
 

From 2532be3d219d8819e59dc52a5ead4696b8354a82 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 25 Oct 2024 12:21:04 -0700
Subject: [PATCH 0680/1530] perf test: Tag parallel failing shell tests with
 "(exclusive)"

Some shell tests compete for resources and so can't run with other
tests, tag such tests.  The "(exclusive)" stems from shared/exclusive
to describe how the tests run as if holding a lock.

For ARM/coresight tests:
Suggested-by: James Clark <james.clark@linaro.org>

Additional failing tests:
Suggested-by: Namhyung Kim <namhyung@kernel.org>

Tested-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Ilya Leoshkevich <iii@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241025192109.132482-6-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/coresight/asm_pure_loop.sh            | 2 +-
 tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh     | 2 +-
 tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh | 2 +-
 tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh  | 2 +-
 tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh    | 2 +-
 tools/perf/tests/shell/perftool-testsuite_report.sh          | 2 +-
 tools/perf/tests/shell/probe_vfs_getname.sh                  | 2 +-
 tools/perf/tests/shell/record+script_probe_vfs_getname.sh    | 2 +-
 tools/perf/tests/shell/record.sh                             | 2 +-
 tools/perf/tests/shell/record_lbr.sh                         | 2 +-
 tools/perf/tests/shell/record_offcpu.sh                      | 2 +-
 tools/perf/tests/shell/stat_all_pmu.sh                       | 2 +-
 tools/perf/tests/shell/stat_bpf_counters.sh                  | 2 +-
 tools/perf/tests/shell/test_arm_coresight.sh                 | 2 +-
 tools/perf/tests/shell/test_arm_coresight_disasm.sh          | 2 +-
 tools/perf/tests/shell/test_arm_spe.sh                       | 2 +-
 tools/perf/tests/shell/test_data_symbol.sh                   | 2 +-
 tools/perf/tests/shell/test_intel_pt.sh                      | 2 +-
 tools/perf/tests/shell/test_stat_intel_tpebs.sh              | 2 +-
 tools/perf/tests/shell/trace+probe_vfs_getname.sh            | 2 +-
 20 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/tools/perf/tests/shell/coresight/asm_pure_loop.sh b/tools/perf/tests/shell/coresight/asm_pure_loop.sh
index 2d65defb7e0f1..c63bc8c73e262 100755
--- a/tools/perf/tests/shell/coresight/asm_pure_loop.sh
+++ b/tools/perf/tests/shell/coresight/asm_pure_loop.sh
@@ -1,5 +1,5 @@
 #!/bin/sh -e
-# CoreSight / ASM Pure Loop
+# CoreSight / ASM Pure Loop (exclusive)
 
 # SPDX-License-Identifier: GPL-2.0
 # Carsten Haitzler <carsten.haitzler@arm.com>, 2021
diff --git a/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh b/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh
index ddcc9bb850f5f..8e29630957c8d 100755
--- a/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh
+++ b/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh
@@ -1,5 +1,5 @@
 #!/bin/sh -e
-# CoreSight / Memcpy 16k 10 Threads
+# CoreSight / Memcpy 16k 10 Threads (exclusive)
 
 # SPDX-License-Identifier: GPL-2.0
 # Carsten Haitzler <carsten.haitzler@arm.com>, 2021
diff --git a/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh b/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh
index 2ce5e139b2fdd..0c4c82a1c8e15 100755
--- a/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh
+++ b/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh
@@ -1,5 +1,5 @@
 #!/bin/sh -e
-# CoreSight / Thread Loop 10 Threads - Check TID
+# CoreSight / Thread Loop 10 Threads - Check TID (exclusive)
 
 # SPDX-License-Identifier: GPL-2.0
 # Carsten Haitzler <carsten.haitzler@arm.com>, 2021
diff --git a/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh b/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh
index 3ad9498753d7b..d3aea9fc6ced9 100755
--- a/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh
+++ b/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh
@@ -1,5 +1,5 @@
 #!/bin/sh -e
-# CoreSight / Thread Loop 2 Threads - Check TID
+# CoreSight / Thread Loop 2 Threads - Check TID (exclusive)
 
 # SPDX-License-Identifier: GPL-2.0
 # Carsten Haitzler <carsten.haitzler@arm.com>, 2021
diff --git a/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh b/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh
index 4fbb4a29aad3f..7429d3a2ae436 100755
--- a/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh
+++ b/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh
@@ -1,5 +1,5 @@
 #!/bin/sh -e
-# CoreSight / Unroll Loop Thread 10
+# CoreSight / Unroll Loop Thread 10 (exclusive)
 
 # SPDX-License-Identifier: GPL-2.0
 # Carsten Haitzler <carsten.haitzler@arm.com>, 2021
diff --git a/tools/perf/tests/shell/perftool-testsuite_report.sh b/tools/perf/tests/shell/perftool-testsuite_report.sh
index 973012ce92a76..a8cf75b4e77ec 100755
--- a/tools/perf/tests/shell/perftool-testsuite_report.sh
+++ b/tools/perf/tests/shell/perftool-testsuite_report.sh
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perftool-testsuite_report
+# perftool-testsuite_report (exclusive)
 # SPDX-License-Identifier: GPL-2.0
 
 test -d "$(dirname "$0")/base_report" || exit 2
diff --git a/tools/perf/tests/shell/probe_vfs_getname.sh b/tools/perf/tests/shell/probe_vfs_getname.sh
index 554e12e83c55f..0c5aacc446b3e 100755
--- a/tools/perf/tests/shell/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/probe_vfs_getname.sh
@@ -1,5 +1,5 @@
 #!/bin/sh
-# Add vfs_getname probe to get syscall args filenames
+# Add vfs_getname probe to get syscall args filenames (exclusive)
 
 # SPDX-License-Identifier: GPL-2.0
 # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
diff --git a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
index 9a61928e3c9aa..5940fdc1df37c 100755
--- a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
@@ -1,5 +1,5 @@
 #!/bin/sh
-# Use vfs_getname probe to get syscall args filenames
+# Use vfs_getname probe to get syscall args filenames (exclusive)
 
 # Uses the 'perf test shell' library to add probe:vfs_getname to the system
 # then use it with 'perf record' using 'touch' to write to a temp file, then
diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index f0e79200b9813..85d512f5a1263 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf record tests
+# perf record tests (exclusive)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e
diff --git a/tools/perf/tests/shell/record_lbr.sh b/tools/perf/tests/shell/record_lbr.sh
index 32314641217e6..8d750ee631f87 100755
--- a/tools/perf/tests/shell/record_lbr.sh
+++ b/tools/perf/tests/shell/record_lbr.sh
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf record LBR tests
+# perf record LBR tests (exclusive)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e
diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh
index 67c925f3a15aa..678947fe69eed 100755
--- a/tools/perf/tests/shell/record_offcpu.sh
+++ b/tools/perf/tests/shell/record_offcpu.sh
@@ -1,5 +1,5 @@
 #!/bin/sh
-# perf record offcpu profiling tests
+# perf record offcpu profiling tests (exclusive)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e
diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh
index 42456d89c5da3..8b148b300be11 100755
--- a/tools/perf/tests/shell/stat_all_pmu.sh
+++ b/tools/perf/tests/shell/stat_all_pmu.sh
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf all PMU test
+# perf all PMU test (exclusive)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e
diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
index f250b7d6f773f..a038c1b1a706a 100755
--- a/tools/perf/tests/shell/stat_bpf_counters.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters.sh
@@ -1,5 +1,5 @@
 #!/bin/sh
-# perf stat --bpf-counters test
+# perf stat --bpf-counters test (exclusive)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e
diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh
index 6b8c4831eedc6..573af9235b725 100755
--- a/tools/perf/tests/shell/test_arm_coresight.sh
+++ b/tools/perf/tests/shell/test_arm_coresight.sh
@@ -1,5 +1,5 @@
 #!/bin/sh
-# Check Arm CoreSight trace data recording and synthesized samples
+# Check Arm CoreSight trace data recording and synthesized samples (exclusive)
 
 # Uses the 'perf record' to record trace data with Arm CoreSight sinks;
 # then verify if there have any branch samples and instruction samples
diff --git a/tools/perf/tests/shell/test_arm_coresight_disasm.sh b/tools/perf/tests/shell/test_arm_coresight_disasm.sh
index dba086a40d846..be2d26303f94b 100755
--- a/tools/perf/tests/shell/test_arm_coresight_disasm.sh
+++ b/tools/perf/tests/shell/test_arm_coresight_disasm.sh
@@ -1,5 +1,5 @@
 #!/bin/sh
-# Check Arm CoreSight disassembly script completes without errors
+# Check Arm CoreSight disassembly script completes without errors (exclusive)
 # SPDX-License-Identifier: GPL-2.0
 
 # The disassembly script reconstructs ranges of instructions and gives these to objdump to
diff --git a/tools/perf/tests/shell/test_arm_spe.sh b/tools/perf/tests/shell/test_arm_spe.sh
index 6c21fb1f10d8f..3258368634f79 100755
--- a/tools/perf/tests/shell/test_arm_spe.sh
+++ b/tools/perf/tests/shell/test_arm_spe.sh
@@ -1,5 +1,5 @@
 #!/bin/sh
-# Check Arm SPE trace data recording and synthesized samples
+# Check Arm SPE trace data recording and synthesized samples (exclusive)
 
 # Uses the 'perf record' to record trace data of Arm SPE events;
 # then verify if any SPE event samples are generated by SPE with
diff --git a/tools/perf/tests/shell/test_data_symbol.sh b/tools/perf/tests/shell/test_data_symbol.sh
index 3dfa91832aa87..c86da02350596 100755
--- a/tools/perf/tests/shell/test_data_symbol.sh
+++ b/tools/perf/tests/shell/test_data_symbol.sh
@@ -1,5 +1,5 @@
 #!/bin/bash
-# Test data symbol
+# Test data symbol (exclusive)
 
 # SPDX-License-Identifier: GPL-2.0
 # Leo Yan <leo.yan@linaro.org>, 2022
diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh
index bf9017b812aa6..e6f0070975f66 100755
--- a/tools/perf/tests/shell/test_intel_pt.sh
+++ b/tools/perf/tests/shell/test_intel_pt.sh
@@ -1,5 +1,5 @@
 #!/bin/sh
-# Miscellaneous Intel PT testing
+# Miscellaneous Intel PT testing (exclusive)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e
diff --git a/tools/perf/tests/shell/test_stat_intel_tpebs.sh b/tools/perf/tests/shell/test_stat_intel_tpebs.sh
index 9a11f42d153ca..f95fc64bf0a7b 100755
--- a/tools/perf/tests/shell/test_stat_intel_tpebs.sh
+++ b/tools/perf/tests/shell/test_stat_intel_tpebs.sh
@@ -1,5 +1,5 @@
 #!/bin/bash
-# test Intel TPEBS counting mode
+# test Intel TPEBS counting mode (exclusive)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 97b4b9cd23784..708a13f006353 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -1,5 +1,5 @@
 #!/bin/sh
-# Check open filename arg using perf trace + vfs_getname
+# Check open filename arg using perf trace + vfs_getname (exclusive)
 
 # Uses the 'perf test shell' library to add probe:vfs_getname to the system
 # then use it with 'perf trace' using 'touch' to write to a temp file, then

From a6fffc60940a903ebcd70d44f047277ba5188225 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 25 Oct 2024 12:21:05 -0700
Subject: [PATCH 0681/1530] perf test: Add a signal handler around running a
 test

Add a signal handler around running a test. If a signal occurs during
the test a siglongjmp unwinds the stack and output is flushed. The
global run_test_jmp_buf is either unique per forked child or not
shared during sequential execution.

Tested-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Ilya Leoshkevich <iii@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241025192109.132482-7-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/builtin-test.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 0e8f877f4b1f0..8a720ddb03963 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -8,6 +8,7 @@
 #include <errno.h>
 #include <poll.h>
 #include <unistd.h>
+#include <setjmp.h>
 #include <string.h>
 #include <stdlib.h>
 #include <sys/types.h>
@@ -229,16 +230,41 @@ struct child_test {
 	int subtest;
 };
 
+static jmp_buf run_test_jmp_buf;
+
+static void child_test_sig_handler(int sig)
+{
+	siglongjmp(run_test_jmp_buf, sig);
+}
+
 static int run_test_child(struct child_process *process)
 {
-	struct child_test *child = container_of(process, struct child_test, process);
+	const int signals[] = {
+		SIGABRT, SIGBUS, SIGFPE, SIGILL, SIGINT, SIGPIPE, SIGQUIT, SIGSEGV, SIGTERM,
+	};
+	static struct child_test *child;
 	int err;
 
+	err = sigsetjmp(run_test_jmp_buf, 1);
+	if (err) {
+		fprintf(stderr, "\n---- unexpected signal (%d) ----\n", err);
+		err = err > 0 ? -err : -1;
+		goto err_out;
+	}
+
+	child = container_of(process, struct child_test, process);
+	for (size_t i = 0; i < ARRAY_SIZE(signals); i++)
+		signal(signals[i], child_test_sig_handler);
+
 	pr_debug("--- start ---\n");
 	pr_debug("test child forked, pid %d\n", getpid());
 	err = test_function(child->test, child->subtest)(child->test, child->subtest);
 	pr_debug("---- end(%d) ----\n", err);
+
+err_out:
 	fflush(NULL);
+	for (size_t i = 0; i < ARRAY_SIZE(signals); i++)
+		signal(signals[i], SIG_DFL);
 	return -err;
 }
 

From 79e72f384d733f78cb07a9649a5ea52b78898a30 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 25 Oct 2024 12:21:06 -0700
Subject: [PATCH 0682/1530] perf test: Run parallel tests in two passes

In pass 1 run all tests that succeed when run in parallel. In pass 2
sequentially run all remaining tests that are flagged as
"exclusive". Sequential and dont_fork tests keep to run in pass 1.
Read the exclusive flag from the shell test descriptions, but remove
from display to avoid >100 characters. Add error handling to finish
tests if starting a later test fails. Mark the task-exit test as
exclusive due to issues reported-by James Clark.

Tested-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Ilya Leoshkevich <iii@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241025192109.132482-8-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/builtin-test.c  | 157 +++++++++++++++++++------------
 tools/perf/tests/task-exit.c     |   9 +-
 tools/perf/tests/tests-scripts.c |   7 +-
 tools/perf/tests/tests.h         |   9 ++
 4 files changed, 121 insertions(+), 61 deletions(-)

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 8a720ddb03963..b997d0a68ca24 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -199,6 +199,14 @@ static test_fnptr test_function(const struct test_suite *t, int subtest)
 	return t->test_cases[subtest].run_case;
 }
 
+static bool test_exclusive(const struct test_suite *t, int subtest)
+{
+	if (subtest <= 0)
+		return t->test_cases[0].exclusive;
+
+	return t->test_cases[subtest].exclusive;
+}
+
 static bool perf_test__matches(const char *desc, int curr, int argc, const char *argv[])
 {
 	int i;
@@ -242,7 +250,7 @@ static int run_test_child(struct child_process *process)
 	const int signals[] = {
 		SIGABRT, SIGBUS, SIGFPE, SIGILL, SIGINT, SIGPIPE, SIGQUIT, SIGSEGV, SIGTERM,
 	};
-	static struct child_test *child;
+	struct child_test *child = container_of(process, struct child_test, process);
 	int err;
 
 	err = sigsetjmp(run_test_jmp_buf, 1);
@@ -252,7 +260,6 @@ static int run_test_child(struct child_process *process)
 		goto err_out;
 	}
 
-	child = container_of(process, struct child_test, process);
 	for (size_t i = 0; i < ARRAY_SIZE(signals); i++)
 		signal(signals[i], child_test_sig_handler);
 
@@ -305,19 +312,25 @@ static int print_test_result(struct test_suite *t, int i, int subtest, int resul
 	return 0;
 }
 
-static int finish_test(struct child_test **child_tests, int running_test, int child_test_num,
-		       int width)
+static void finish_test(struct child_test **child_tests, int running_test, int child_test_num,
+		int width)
 {
 	struct child_test *child_test = child_tests[running_test];
-	struct test_suite *t = child_test->test;
-	int i = child_test->test_num;
-	int subi = child_test->subtest;
-	int err = child_test->process.err;
+	struct test_suite *t;
+	int i, subi, err;
 	bool err_done = false;
 	struct strbuf err_output = STRBUF_INIT;
 	int last_running = -1;
 	int ret;
 
+	if (child_test == NULL) {
+		/* Test wasn't started. */
+		return;
+	}
+	t = child_test->test;
+	i = child_test->test_num;
+	subi = child_test->subtest;
+	err = child_test->process.err;
 	/*
 	 * For test suites with subtests, display the suite name ahead of the
 	 * sub test names.
@@ -347,6 +360,8 @@ static int finish_test(struct child_test **child_tests, int running_test, int ch
 			int running = 0;
 
 			for (int y = running_test; y < child_test_num; y++) {
+				if (child_tests[y] == NULL)
+					continue;
 				if (check_if_command_finished(&child_tests[y]->process) == 0)
 					running++;
 			}
@@ -399,23 +414,32 @@ static int finish_test(struct child_test **child_tests, int running_test, int ch
 	print_test_result(t, i, subi, ret, width, /*running=*/0);
 	if (err > 0)
 		close(err);
-	return 0;
+	zfree(&child_tests[running_test]);
 }
 
 static int start_test(struct test_suite *test, int i, int subi, struct child_test **child,
-		      int width)
+		int width, int pass)
 {
 	int err;
 
 	*child = NULL;
 	if (dont_fork) {
-		pr_debug("--- start ---\n");
-		err = test_function(test, subi)(test, subi);
-		pr_debug("---- end ----\n");
-		print_test_result(test, i, subi, err, width, /*running=*/0);
+		if (pass == 1) {
+			pr_debug("--- start ---\n");
+			err = test_function(test, subi)(test, subi);
+			pr_debug("---- end ----\n");
+			print_test_result(test, i, subi, err, width, /*running=*/0);
+		}
+		return 0;
+	}
+	if (pass == 1 && !sequential && test_exclusive(test, subi)) {
+		/* When parallel, skip exclusive tests on the first pass. */
+		return 0;
+	}
+	if (pass != 1 && (sequential || !test_exclusive(test, subi))) {
+		/* Sequential and non-exclusive tests were run on the first pass. */
 		return 0;
 	}
-
 	*child = zalloc(sizeof(**child));
 	if (!*child)
 		return -ENOMEM;
@@ -434,10 +458,14 @@ static int start_test(struct test_suite *test, int i, int subi, struct child_tes
 		(*child)->process.err = -1;
 	}
 	(*child)->process.no_exec_cmd = run_test_child;
-	err = start_command(&(*child)->process);
-	if (err || !sequential)
-		return  err;
-	return finish_test(child, /*running_test=*/0, /*child_test_num=*/1, width);
+	if (sequential || pass == 2) {
+		err = start_command(&(*child)->process);
+		if (err)
+			return err;
+		finish_test(child, /*running_test=*/0, /*child_test_num=*/1, width);
+		return 0;
+	}
+	return start_command(&(*child)->process);
 }
 
 #define for_each_test(j, k, t)					\
@@ -447,12 +475,11 @@ static int start_test(struct test_suite *test, int i, int subi, struct child_tes
 static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 {
 	struct test_suite *t;
-	unsigned int j, k;
-	int i = 0;
 	int width = 0;
+	unsigned int j, k;
 	size_t num_tests = 0;
 	struct child_test **child_tests;
-	int child_test_num = 0;
+	int err = 0;
 
 	for_each_test(j, k, t) {
 		int len = strlen(test_description(t, -1));
@@ -475,62 +502,73 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 	if (!child_tests)
 		return -ENOMEM;
 
-	for_each_test(j, k, t) {
-		int curr = i++;
-
-		if (!perf_test__matches(test_description(t, -1), curr, argc, argv)) {
-			bool skip = true;
+	/*
+	 * In parallel mode pass 1 runs non-exclusive tests in parallel, pass 2
+	 * runs the exclusive tests sequentially. In other modes all tests are
+	 * run in pass 1.
+	 */
+	for (int pass = 1; pass <= 2; pass++) {
+		int child_test_num = 0;
+		int i = 0;
+
+		for_each_test(j, k, t) {
+			int curr = i++;
+
+			if (!perf_test__matches(test_description(t, -1), curr, argc, argv)) {
+				/*
+				 * Test suite shouldn't be run based on
+				 * description. See if subtest should.
+				 */
+				bool skip = true;
+
+				for (int subi = 0, subn = num_subtests(t); subi < subn; subi++) {
+					if (perf_test__matches(test_description(t, subi),
+								curr, argc, argv))
+						skip = false;
+				}
 
-			for (int subi = 0, subn = num_subtests(t); subi < subn; subi++) {
-				if (perf_test__matches(test_description(t, subi),
-							curr, argc, argv))
-					skip = false;
+				if (skip)
+					continue;
 			}
 
-			if (skip)
+			if (intlist__find(skiplist, i)) {
+				pr_info("%3d: %-*s:", curr + 1, width, test_description(t, -1));
+				color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n");
 				continue;
-		}
-
-		if (intlist__find(skiplist, i)) {
-			pr_info("%3d: %-*s:", curr + 1, width, test_description(t, -1));
-			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n");
-			continue;
-		}
-
-		if (!has_subtests(t)) {
-			int err = start_test(t, curr, -1, &child_tests[child_test_num++], width);
+			}
 
-			if (err) {
-				/* TODO: if !sequential waitpid the already forked children. */
-				free(child_tests);
-				return err;
+			if (!has_subtests(t)) {
+				err = start_test(t, curr, -1, &child_tests[child_test_num++],
+						 width, pass);
+				if (err)
+					goto err_out;
+				continue;
 			}
-		} else {
 			for (int subi = 0, subn = num_subtests(t); subi < subn; subi++) {
-				int err;
-
 				if (!perf_test__matches(test_description(t, subi),
 							curr, argc, argv))
 					continue;
 
 				err = start_test(t, curr, subi, &child_tests[child_test_num++],
-						 width);
+						 width, pass);
 				if (err)
-					return err;
+					goto err_out;
 			}
 		}
-	}
-	for (i = 0; i < child_test_num; i++) {
 		if (!sequential) {
-			int ret  = finish_test(child_tests, i, child_test_num, width);
-
-			if (ret)
-				return ret;
+			/* Parallel mode starts tests but doesn't finish them. Do that now. */
+			for (size_t x = 0; x < num_tests; x++)
+				finish_test(child_tests, x, num_tests, width);
 		}
-		free(child_tests[i]);
+	}
+err_out:
+	if (err) {
+		pr_err("Internal test harness failure. Completing any started tests:\n:");
+		for (size_t x = 0; x < num_tests; x++)
+			finish_test(child_tests, x, num_tests, width);
 	}
 	free(child_tests);
-	return 0;
+	return err;
 }
 
 static int perf_test__list(int argc, const char **argv)
@@ -656,6 +694,7 @@ int cmd_test(int argc, const char **argv)
 	symbol_conf.priv_size = sizeof(int);
 	symbol_conf.try_vmlinux_path = true;
 
+
 	if (symbol__init(NULL) < 0)
 		return -1;
 
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index d33d0952025cf..8e328bbd509dc 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -152,4 +152,11 @@ static int test__task_exit(struct test_suite *test __maybe_unused, int subtest _
 	return err;
 }
 
-DEFINE_SUITE("Number of exit events of a simple workload", task_exit);
+struct test_case tests__task_exit[] = {
+	TEST_CASE_EXCLUSIVE("Number of exit events of a simple workload", task_exit),
+	{	.name = NULL, }
+};
+struct test_suite suite__task_exit = {
+	.desc = "Number of exit events of a simple workload",
+	.test_cases = tests__task_exit,
+};
diff --git a/tools/perf/tests/tests-scripts.c b/tools/perf/tests/tests-scripts.c
index ed114b0442936..cf3ae0c1d8717 100644
--- a/tools/perf/tests/tests-scripts.c
+++ b/tools/perf/tests/tests-scripts.c
@@ -175,6 +175,7 @@ static void append_script(int dir_fd, const char *name, char *desc,
 	struct test_suite *test_suite, **result_tmp;
 	struct test_case *tests;
 	size_t len;
+	char *exclusive;
 
 	snprintf(link, sizeof(link), "/proc/%d/fd/%d", getpid(), dir_fd);
 	len = readlink(link, filename, sizeof(filename));
@@ -191,9 +192,13 @@ static void append_script(int dir_fd, const char *name, char *desc,
 		return;
 	}
 	tests[0].name = strdup_check(name);
+	exclusive = strstr(desc, " (exclusive)");
+	if (exclusive != NULL) {
+		tests[0].exclusive = true;
+		exclusive[0] = '\0';
+	}
 	tests[0].desc = strdup_check(desc);
 	tests[0].run_case = shell_test__run;
-
 	test_suite = zalloc(sizeof(*test_suite));
 	if (!test_suite) {
 		pr_err("Out of memory while building script test suite list\n");
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 1ed76d4156b6a..af284dd47e5c7 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -36,6 +36,7 @@ struct test_case {
 	const char *desc;
 	const char *skip_reason;
 	test_fnptr run_case;
+	bool exclusive;
 };
 
 struct test_suite {
@@ -62,6 +63,14 @@ struct test_suite {
 		.skip_reason = _reason,			\
 	}
 
+#define TEST_CASE_EXCLUSIVE(description, _name)		\
+	{						\
+		.name = #_name,				\
+		.desc = description,			\
+		.run_case = test__##_name,		\
+		.exclusive = true,			\
+	}
+
 #define DEFINE_SUITE(description, _name)		\
 	struct test_case tests__##_name[] = {           \
 		TEST_CASE(description, _name),		\

From 94d1a913bdc423073d5f58fcd8caaf7ee9f57ebc Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 25 Oct 2024 12:21:07 -0700
Subject: [PATCH 0683/1530] perf test: Make parallel testing the default

Now C tests can have the "exclusive" flag to run without other tests,
and shell tests can add "(exclusive)" to their description, run tests
in parallel by default. Tests which flake when run in parallel can be
marked exclusive to resolve the problem.

Non-scientifically, the reduction on `perf test` execution time is
from 8m35.890s to 3m55.115s on a Tigerlake laptop. So the tests
complete in less than half the time.

Tested-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Ilya Leoshkevich <iii@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241025192109.132482-9-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/builtin-test.c | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index b997d0a68ca24..a0a678facc458 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -40,8 +40,8 @@
  * making them easier to debug.
  */
 static bool dont_fork;
-/* Don't fork the tests in parallel and wait for their completion. */
-static bool sequential = true;
+/* Fork the tests in parallel and wait for their completion. */
+static bool sequential;
 const char *dso_to_test;
 const char *test_objdump_path = "objdump";
 
@@ -639,19 +639,12 @@ int cmd_test(int argc, const char **argv)
 	const char *skip = NULL;
 	const char *workload = NULL;
 	bool list_workloads = false;
-	/*
-	 * Run tests in parallel, lacks infrastructure to avoid running tests
-	 * that clash for resources, So leave it as the developers choice to
-	 * enable while working on the needed infra.
-	 */
-	bool parallel = false;
 	const struct option test_options[] = {
 	OPT_STRING('s', "skip", &skip, "tests", "tests to skip"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('F', "dont-fork", &dont_fork,
 		    "Do not fork for testcase"),
-	OPT_BOOLEAN('p', "parallel", &parallel, "Run the tests in parallel"),
 	OPT_BOOLEAN('S', "sequential", &sequential,
 		    "Run the tests one after another rather than in parallel"),
 	OPT_STRING('w', "workload", &workload, "work", "workload to run for testing, use '--list-workloads' to list the available ones."),
@@ -688,8 +681,6 @@ int cmd_test(int argc, const char **argv)
 
 	if (dont_fork)
 		sequential = true;
-	else if (parallel)
-		sequential = false;
 
 	symbol_conf.priv_size = sizeof(int);
 	symbol_conf.try_vmlinux_path = true;

From 553d5efeb341f2f814f937e0658ed7d22f625662 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 25 Oct 2024 12:21:08 -0700
Subject: [PATCH 0684/1530] perf test: Add a signal handler to kill forked
 child processes

If the `perf test` process is killed the child tests continue running
and may run indefinitely. Propagate SIGINT (ctrl-C) and SIGTERM (kill)
signals to the running child processes so that they terminate when the
parent is killed.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Ilya Leoshkevich <iii@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241025192109.132482-10-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/builtin-test.c | 37 ++++++++++++++++++++++++++++++---
 1 file changed, 34 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index a0a678facc458..2f880f48cdc56 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -472,13 +472,22 @@ static int start_test(struct test_suite *test, int i, int subi, struct child_tes
 	for (j = 0, k = 0; j < ARRAY_SIZE(tests); j++, k = 0)	\
 		while ((t = tests[j][k++]) != NULL)
 
+/* State outside of __cmd_test for the sake of the signal handler. */
+
+static size_t num_tests;
+static struct child_test **child_tests;
+static jmp_buf cmd_test_jmp_buf;
+
+static void cmd_test_sig_handler(int sig)
+{
+	siglongjmp(cmd_test_jmp_buf, sig);
+}
+
 static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 {
 	struct test_suite *t;
-	int width = 0;
+	static int width = 0;
 	unsigned int j, k;
-	size_t num_tests = 0;
-	struct child_test **child_tests;
 	int err = 0;
 
 	for_each_test(j, k, t) {
@@ -502,6 +511,26 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 	if (!child_tests)
 		return -ENOMEM;
 
+	err = sigsetjmp(cmd_test_jmp_buf, 1);
+	if (err) {
+		pr_err("\nSignal (%d) while running tests.\nTerminating tests with the same signal\n",
+		       err);
+		for (size_t x = 0; x < num_tests; x++) {
+			struct child_test *child_test = child_tests[x];
+
+			if (!child_test)
+				continue;
+
+			pr_debug3("Killing %d pid %d\n",
+				  child_test->test_num + 1,
+				  child_test->process.pid);
+			kill(child_test->process.pid, err);
+		}
+		goto err_out;
+	}
+	signal(SIGINT, cmd_test_sig_handler);
+	signal(SIGTERM, cmd_test_sig_handler);
+
 	/*
 	 * In parallel mode pass 1 runs non-exclusive tests in parallel, pass 2
 	 * runs the exclusive tests sequentially. In other modes all tests are
@@ -562,6 +591,8 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 		}
 	}
 err_out:
+	signal(SIGINT, SIG_DFL);
+	signal(SIGTERM, SIG_DFL);
 	if (err) {
 		pr_err("Internal test harness failure. Completing any started tests:\n:");
 		for (size_t x = 0; x < num_tests; x++)

From 7449a4d674cc14f8e689cecf7354748706d00f30 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 25 Oct 2024 12:21:09 -0700
Subject: [PATCH 0685/1530] perf test: Sort tests placing exclusive tests last

This allows a uniform test numbering even though two passes are used
to execute them.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Ilya Leoshkevich <iii@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241025192109.132482-11-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/builtin-test.c | 125 +++++++++++++++++++++-----------
 1 file changed, 84 insertions(+), 41 deletions(-)

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 2f880f48cdc56..d2cabaa8ad922 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -137,12 +137,6 @@ static struct test_suite *generic_tests[] = {
 	NULL,
 };
 
-static struct test_suite **tests[] = {
-	generic_tests,
-	arch_tests,
-	NULL, /* shell tests created at runtime. */
-};
-
 static struct test_workload *workloads[] = {
 	&workload__noploop,
 	&workload__thloop,
@@ -468,10 +462,6 @@ static int start_test(struct test_suite *test, int i, int subi, struct child_tes
 	return start_command(&(*child)->process);
 }
 
-#define for_each_test(j, k, t)					\
-	for (j = 0, k = 0; j < ARRAY_SIZE(tests); j++, k = 0)	\
-		while ((t = tests[j][k++]) != NULL)
-
 /* State outside of __cmd_test for the sake of the signal handler. */
 
 static size_t num_tests;
@@ -483,22 +473,21 @@ static void cmd_test_sig_handler(int sig)
 	siglongjmp(cmd_test_jmp_buf, sig);
 }
 
-static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
+static int __cmd_test(struct test_suite **suites, int argc, const char *argv[],
+		      struct intlist *skiplist)
 {
-	struct test_suite *t;
 	static int width = 0;
-	unsigned int j, k;
 	int err = 0;
 
-	for_each_test(j, k, t) {
-		int len = strlen(test_description(t, -1));
+	for (struct test_suite **t = suites; *t; t++) {
+		int len = strlen(test_description(*t, -1));
 
 		if (width < len)
 			width = len;
 
-		if (has_subtests(t)) {
-			for (int subi = 0, subn = num_subtests(t); subi < subn; subi++) {
-				len = strlen(test_description(t, subi));
+		if (has_subtests(*t)) {
+			for (int subi = 0, subn = num_subtests(*t); subi < subn; subi++) {
+				len = strlen(test_description(*t, subi));
 				if (width < len)
 					width = len;
 				num_tests++;
@@ -540,18 +529,18 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 		int child_test_num = 0;
 		int i = 0;
 
-		for_each_test(j, k, t) {
+		for (struct test_suite **t = suites; *t; t++) {
 			int curr = i++;
 
-			if (!perf_test__matches(test_description(t, -1), curr, argc, argv)) {
+			if (!perf_test__matches(test_description(*t, -1), curr, argc, argv)) {
 				/*
 				 * Test suite shouldn't be run based on
 				 * description. See if subtest should.
 				 */
 				bool skip = true;
 
-				for (int subi = 0, subn = num_subtests(t); subi < subn; subi++) {
-					if (perf_test__matches(test_description(t, subi),
+				for (int subi = 0, subn = num_subtests(*t); subi < subn; subi++) {
+					if (perf_test__matches(test_description(*t, subi),
 								curr, argc, argv))
 						skip = false;
 				}
@@ -561,24 +550,24 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 			}
 
 			if (intlist__find(skiplist, i)) {
-				pr_info("%3d: %-*s:", curr + 1, width, test_description(t, -1));
+				pr_info("%3d: %-*s:", curr + 1, width, test_description(*t, -1));
 				color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n");
 				continue;
 			}
 
-			if (!has_subtests(t)) {
-				err = start_test(t, curr, -1, &child_tests[child_test_num++],
+			if (!has_subtests(*t)) {
+				err = start_test(*t, curr, -1, &child_tests[child_test_num++],
 						 width, pass);
 				if (err)
 					goto err_out;
 				continue;
 			}
-			for (int subi = 0, subn = num_subtests(t); subi < subn; subi++) {
-				if (!perf_test__matches(test_description(t, subi),
+			for (int subi = 0, subn = num_subtests(*t); subi < subn; subi++) {
+				if (!perf_test__matches(test_description(*t, subi),
 							curr, argc, argv))
 					continue;
 
-				err = start_test(t, curr, subi, &child_tests[child_test_num++],
+				err = start_test(*t, curr, subi, &child_tests[child_test_num++],
 						 width, pass);
 				if (err)
 					goto err_out;
@@ -602,27 +591,25 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 	return err;
 }
 
-static int perf_test__list(int argc, const char **argv)
+static int perf_test__list(struct test_suite **suites, int argc, const char **argv)
 {
-	unsigned int j, k;
-	struct test_suite *t;
 	int i = 0;
 
-	for_each_test(j, k, t) {
+	for (struct test_suite **t = suites; *t; t++) {
 		int curr = i++;
 
-		if (!perf_test__matches(test_description(t, -1), curr, argc, argv))
+		if (!perf_test__matches(test_description(*t, -1), curr, argc, argv))
 			continue;
 
-		pr_info("%3d: %s\n", i, test_description(t, -1));
+		pr_info("%3d: %s\n", i, test_description(*t, -1));
 
-		if (has_subtests(t)) {
-			int subn = num_subtests(t);
+		if (has_subtests(*t)) {
+			int subn = num_subtests(*t);
 			int subi;
 
 			for (subi = 0; subi < subn; subi++)
 				pr_info("%3d:%1d: %s\n", i, subi + 1,
-					test_description(t, subi));
+					test_description(*t, subi));
 		}
 	}
 	return 0;
@@ -661,6 +648,55 @@ static int perf_test__config(const char *var, const char *value,
 	return 0;
 }
 
+static struct test_suite **build_suites(void)
+{
+	/*
+	 * TODO: suites is static to avoid needing to clean up the scripts tests
+	 * for leak sanitizer.
+	 */
+	static struct test_suite **suites[] = {
+		generic_tests,
+		arch_tests,
+		NULL,
+	};
+	struct test_suite **result;
+	struct test_suite *t;
+	size_t n = 0, num_suites = 0;
+
+	if (suites[2] == NULL)
+		suites[2] = create_script_test_suites();
+
+#define for_each_test(t)						\
+	for (size_t i = 0, j = 0; i < ARRAY_SIZE(suites); i++, j = 0)	\
+		while ((t = suites[i][j++]) != NULL)
+
+	for_each_test(t)
+		num_suites++;
+
+	result = calloc(num_suites + 1, sizeof(struct test_suite *));
+
+	for (int pass = 1; pass <= 2; pass++) {
+		for_each_test(t) {
+			bool exclusive = false;
+
+			if (!has_subtests(t)) {
+				exclusive = test_exclusive(t, -1);
+			} else {
+				for (int subi = 0, subn = num_subtests(t); subi < subn; subi++) {
+					if (test_exclusive(t, subi)) {
+						exclusive = true;
+						break;
+					}
+				}
+			}
+			if ((!exclusive && pass == 1) || (exclusive && pass == 2))
+				result[n++] = t;
+		}
+	}
+	return result;
+#undef for_each_test
+}
+
 int cmd_test(int argc, const char **argv)
 {
 	const char *test_usage[] = {
@@ -688,6 +724,7 @@ int cmd_test(int argc, const char **argv)
 	const char * const test_subcommands[] = { "list", NULL };
 	struct intlist *skiplist = NULL;
         int ret = hists__init();
+	struct test_suite **suites;
 
         if (ret < 0)
                 return ret;
@@ -697,10 +734,13 @@ int cmd_test(int argc, const char **argv)
 	/* Unbuffered output */
 	setvbuf(stdout, NULL, _IONBF, 0);
 
-	tests[2] = create_script_test_suites();
 	argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0);
-	if (argc >= 1 && !strcmp(argv[0], "list"))
-		return perf_test__list(argc - 1, argv + 1);
+	if (argc >= 1 && !strcmp(argv[0], "list")) {
+		suites = build_suites();
+		ret = perf_test__list(suites, argc - 1, argv + 1);
+		free(suites);
+		return ret;
+	}
 
 	if (workload)
 		return run_workload(workload, argc, argv);
@@ -728,5 +768,8 @@ int cmd_test(int argc, const char **argv)
 	 */
 	rlimit__bump_memlock();
 
-	return __cmd_test(argc, argv, skiplist);
+	suites = build_suites();
+	ret = __cmd_test(suites, argc, argv, skiplist);
+	free(suites);
+	return ret;
 }

From e3b2949e3fa2fd8c19cd5fbb0424d38f70a70e9c Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Tue, 24 Sep 2024 14:12:51 +0800
Subject: [PATCH 0686/1530] perf vendor events arm64: Add i.MX91 DDR
 Performance Monitor metrics

Add JSON metrics for i.MX91 DDR Performance Monitor.

Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: festevam@gmail.com
Cc: conor+dt@kernel.org
Cc: krzk+dt@kernel.org
Cc: robh@kernel.org
Cc: shawnguo@kernel.org
Cc: will@kernel.org
Cc: james.clark@linaro.org
Cc: mike.leach@linaro.org
Cc: leo.yan@linux.dev
Cc: linux-arm-kernel@lists.infradead.org
Cc: imx@lists.linux.dev
Cc: Frank.li@nxp.com
Cc: john.g.garry@oracle.com
Cc: kernel@pengutronix.de
Cc: s.hauer@pengutronix.de
Cc: devicetree@vger.kernel.org
Link: https://lore.kernel.org/r/20240924061251.3387850-3-xu.yang_2@nxp.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../arch/arm64/freescale/imx91/sys/ddrc.json  |  9 +++++++
 .../arm64/freescale/imx91/sys/metrics.json    | 26 +++++++++++++++++++
 2 files changed, 35 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/arm64/freescale/imx91/sys/ddrc.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/freescale/imx91/sys/metrics.json

diff --git a/tools/perf/pmu-events/arch/arm64/freescale/imx91/sys/ddrc.json b/tools/perf/pmu-events/arch/arm64/freescale/imx91/sys/ddrc.json
new file mode 100644
index 0000000000000..74ac12660a294
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/freescale/imx91/sys/ddrc.json
@@ -0,0 +1,9 @@
+[
+   {
+           "BriefDescription": "ddr cycles event",
+           "EventCode": "0x00",
+           "EventName": "imx91_ddr.cycles",
+           "Unit": "imx9_ddr",
+           "Compat": "imx91"
+   }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/freescale/imx91/sys/metrics.json b/tools/perf/pmu-events/arch/arm64/freescale/imx91/sys/metrics.json
new file mode 100644
index 0000000000000..f0c5911eb2d0c
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/freescale/imx91/sys/metrics.json
@@ -0,0 +1,26 @@
+[
+   {
+	    "BriefDescription": "bandwidth usage for lpddr4 evk board",
+	    "MetricName": "imx91_bandwidth_usage.lpddr4",
+	    "MetricExpr": "(((( imx9_ddr0@ddrc_pm_0@ ) * 2 * 8 ) + (( imx9_ddr0@ddrc_pm_3@ + imx9_ddr0@ddrc_pm_5@ + imx9_ddr0@ddrc_pm_7@ + imx9_ddr0@ddrc_pm_9@ - imx9_ddr0@ddrc_pm_2@ - imx9_ddr0@ddrc_pm_4@ - imx9_ddr0@ddrc_pm_6@ - imx9_ddr0@ddrc_pm_8@ ) * 32 )) / duration_time) / (2400 * 1000000 * 2)",
+	    "ScaleUnit": "1e2%",
+	    "Unit": "imx9_ddr",
+	    "Compat": "imx91"
+   },
+   {
+	    "BriefDescription": "bytes all masters read from ddr",
+	    "MetricName": "imx91_ddr_read.all",
+	    "MetricExpr": "( imx9_ddr0@ddrc_pm_0@ ) * 2 * 8",
+	    "ScaleUnit": "9.765625e-4KB",
+	    "Unit": "imx9_ddr",
+	    "Compat": "imx91"
+   },
+   {
+	    "BriefDescription": "bytes all masters write to ddr",
+	    "MetricName": "imx91_ddr_write.all",
+	    "MetricExpr": "( imx9_ddr0@ddrc_pm_3@ + imx9_ddr0@ddrc_pm_5@ + imx9_ddr0@ddrc_pm_7@ + imx9_ddr0@ddrc_pm_9@ - imx9_ddr0@ddrc_pm_2@ - imx9_ddr0@ddrc_pm_4@ - imx9_ddr0@ddrc_pm_6@ - imx9_ddr0@ddrc_pm_8@ ) * 32",
+	    "ScaleUnit": "9.765625e-4KB",
+	    "Unit": "imx9_ddr",
+	    "Compat": "imx91"
+   }
+]

From af0847537031c0c7cc0a168776ac21e29fa74c5c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 28 Oct 2024 16:29:54 +0000
Subject: [PATCH 0687/1530] selftests: kallsyms: add MODULE_DESCRIPTION

The newly added test script creates modules that are lacking
a description line in order to build cleanly:

WARNING: modpost: missing MODULE_DESCRIPTION() in lib/tests/module/test_kallsyms_a.o
WARNING: modpost: missing MODULE_DESCRIPTION() in lib/tests/module/test_kallsyms_b.o
WARNING: modpost: missing MODULE_DESCRIPTION() in lib/tests/module/test_kallsyms_c.o
WARNING: modpost: missing MODULE_DESCRIPTION() in lib/tests/module/test_kallsyms_d.o

Fixes: 84b4a51fce4c ("selftests: add new kallsyms selftests")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 lib/tests/module/gen_test_kallsyms.sh | 1 +
 1 file changed, 1 insertion(+)

diff --git a/lib/tests/module/gen_test_kallsyms.sh b/lib/tests/module/gen_test_kallsyms.sh
index e85f10dc11bdf..ae5966f1f904e 100755
--- a/lib/tests/module/gen_test_kallsyms.sh
+++ b/lib/tests/module/gen_test_kallsyms.sh
@@ -99,6 +99,7 @@ module_exit(auto_test_module_exit);
 
 MODULE_AUTHOR("Luis Chamberlain <mcgrof@kernel.org>");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Test module for kallsyms");
 ____END_MODULE
 }
 

From fb5eda0dfe2256b468fc4e95207a4df88457274f Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Wed, 11 Sep 2024 14:45:31 +0800
Subject: [PATCH 0688/1530] mm/kasan: Don't store metadata inside kmalloc
 object when slub_debug_orig_size is on

For a kmalloc object, when both kasan and slub redzone sanity check
are enabled, they could both manipulate its data space like storing
kasan free meta data and setting up kmalloc redzone, and may affect
accuracy of that object's 'orig_size'.

As an accurate 'orig_size' will be needed by some function like
krealloc() soon, save kasan's free meta data in slub's metadata area
instead of inside object when 'orig_size' is enabled.

This will make it easier to maintain/understand the code. Size wise,
when these two options are both enabled, the slub meta data space is
already huge, and this just slightly increase the overall size.

Signed-off-by: Feng Tang <feng.tang@intel.com>
Acked-by: Andrey Konovalov <andreyknvl@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/kasan/generic.c |  7 +++++--
 mm/slab.h          |  6 ++++++
 mm/slub.c          | 17 -----------------
 3 files changed, 11 insertions(+), 19 deletions(-)

diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index 6310a180278b6..8b9e348113b13 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -392,9 +392,12 @@ void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
 	 * 1. Object is SLAB_TYPESAFE_BY_RCU, which means that it can
 	 *    be touched after it was freed, or
 	 * 2. Object has a constructor, which means it's expected to
-	 *    retain its content until the next allocation.
+	 *    retain its content until the next allocation, or
+	 * 3. It is from a kmalloc cache which enables the debug option
+	 *    to store original size.
 	 */
-	if ((cache->flags & SLAB_TYPESAFE_BY_RCU) || cache->ctor) {
+	if ((cache->flags & SLAB_TYPESAFE_BY_RCU) || cache->ctor ||
+	     slub_debug_orig_size(cache)) {
 		cache->kasan_info.free_meta_offset = *size;
 		*size += sizeof(struct kasan_free_meta);
 		goto free_meta_added;
diff --git a/mm/slab.h b/mm/slab.h
index 6c6fe6d630ce3..2985670194857 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -695,6 +695,12 @@ void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab)
 void __check_heap_object(const void *ptr, unsigned long n,
 			 const struct slab *slab, bool to_user);
 
+static inline bool slub_debug_orig_size(struct kmem_cache *s)
+{
+	return (kmem_cache_debug_flags(s, SLAB_STORE_USER) &&
+			(s->flags & SLAB_KMALLOC));
+}
+
 #ifdef CONFIG_SLUB_DEBUG
 void skip_orig_size_check(struct kmem_cache *s, const void *object);
 #endif
diff --git a/mm/slub.c b/mm/slub.c
index 5b832512044e3..83579b6375788 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -230,12 +230,6 @@ static inline bool kmem_cache_debug(struct kmem_cache *s)
 	return kmem_cache_debug_flags(s, SLAB_DEBUG_FLAGS);
 }
 
-static inline bool slub_debug_orig_size(struct kmem_cache *s)
-{
-	return (kmem_cache_debug_flags(s, SLAB_STORE_USER) &&
-			(s->flags & SLAB_KMALLOC));
-}
-
 void *fixup_red_left(struct kmem_cache *s, void *p)
 {
 	if (kmem_cache_debug_flags(s, SLAB_RED_ZONE))
@@ -760,21 +754,10 @@ static inline void set_orig_size(struct kmem_cache *s,
 				void *object, unsigned int orig_size)
 {
 	void *p = kasan_reset_tag(object);
-	unsigned int kasan_meta_size;
 
 	if (!slub_debug_orig_size(s))
 		return;
 
-	/*
-	 * KASAN can save its free meta data inside of the object at offset 0.
-	 * If this meta data size is larger than 'orig_size', it will overlap
-	 * the data redzone in [orig_size+1, object_size]. Thus, we adjust
-	 * 'orig_size' to be as at least as big as KASAN's meta data.
-	 */
-	kasan_meta_size = kasan_metadata_size(s, true);
-	if (kasan_meta_size > orig_size)
-		orig_size = kasan_meta_size;
-
 	p += get_info_end(s);
 	p += sizeof(struct track) * 2;
 

From 1e4df1859ec2d09fdfe184e7a92a476f01f64e34 Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Wed, 11 Sep 2024 14:45:33 +0800
Subject: [PATCH 0689/1530] mm/slub: Move krealloc() and related code to slub.c

This is a preparation for the following refactoring of krealloc(),
for more efficient function calling as it will call some internal
functions defined in slub.c.

Signed-off-by: Feng Tang <feng.tang@intel.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slab_common.c | 84 ------------------------------------------------
 mm/slub.c        | 84 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 84 insertions(+), 84 deletions(-)

diff --git a/mm/slab_common.c b/mm/slab_common.c
index 552b92dfdac77..f1f90491df03a 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1190,90 +1190,6 @@ module_init(slab_proc_init);
 
 #endif /* CONFIG_SLUB_DEBUG */
 
-static __always_inline __realloc_size(2) void *
-__do_krealloc(const void *p, size_t new_size, gfp_t flags)
-{
-	void *ret;
-	size_t ks;
-
-	/* Check for double-free before calling ksize. */
-	if (likely(!ZERO_OR_NULL_PTR(p))) {
-		if (!kasan_check_byte(p))
-			return NULL;
-		ks = ksize(p);
-	} else
-		ks = 0;
-
-	/* If the object still fits, repoison it precisely. */
-	if (ks >= new_size) {
-		/* Zero out spare memory. */
-		if (want_init_on_alloc(flags)) {
-			kasan_disable_current();
-			memset(kasan_reset_tag(p) + new_size, 0, ks - new_size);
-			kasan_enable_current();
-		}
-
-		p = kasan_krealloc((void *)p, new_size, flags);
-		return (void *)p;
-	}
-
-	ret = kmalloc_node_track_caller_noprof(new_size, flags, NUMA_NO_NODE, _RET_IP_);
-	if (ret && p) {
-		/* Disable KASAN checks as the object's redzone is accessed. */
-		kasan_disable_current();
-		memcpy(ret, kasan_reset_tag(p), ks);
-		kasan_enable_current();
-	}
-
-	return ret;
-}
-
-/**
- * krealloc - reallocate memory. The contents will remain unchanged.
- * @p: object to reallocate memory for.
- * @new_size: how many bytes of memory are required.
- * @flags: the type of memory to allocate.
- *
- * If @p is %NULL, krealloc() behaves exactly like kmalloc().  If @new_size
- * is 0 and @p is not a %NULL pointer, the object pointed to is freed.
- *
- * If __GFP_ZERO logic is requested, callers must ensure that, starting with the
- * initial memory allocation, every subsequent call to this API for the same
- * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that
- * __GFP_ZERO is not fully honored by this API.
- *
- * This is the case, since krealloc() only knows about the bucket size of an
- * allocation (but not the exact size it was allocated with) and hence
- * implements the following semantics for shrinking and growing buffers with
- * __GFP_ZERO.
- *
- *         new             bucket
- * 0       size             size
- * |--------|----------------|
- * |  keep  |      zero      |
- *
- * In any case, the contents of the object pointed to are preserved up to the
- * lesser of the new and old sizes.
- *
- * Return: pointer to the allocated memory or %NULL in case of error
- */
-void *krealloc_noprof(const void *p, size_t new_size, gfp_t flags)
-{
-	void *ret;
-
-	if (unlikely(!new_size)) {
-		kfree(p);
-		return ZERO_SIZE_PTR;
-	}
-
-	ret = __do_krealloc(p, new_size, flags);
-	if (ret && kasan_reset_tag(p) != kasan_reset_tag(ret))
-		kfree(p);
-
-	return ret;
-}
-EXPORT_SYMBOL(krealloc_noprof);
-
 /**
  * kfree_sensitive - Clear sensitive information in memory before freeing
  * @p: object to free memory of
diff --git a/mm/slub.c b/mm/slub.c
index 83579b6375788..2ccb016c7f998 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4711,6 +4711,90 @@ void kfree(const void *object)
 }
 EXPORT_SYMBOL(kfree);
 
+static __always_inline __realloc_size(2) void *
+__do_krealloc(const void *p, size_t new_size, gfp_t flags)
+{
+	void *ret;
+	size_t ks;
+
+	/* Check for double-free before calling ksize. */
+	if (likely(!ZERO_OR_NULL_PTR(p))) {
+		if (!kasan_check_byte(p))
+			return NULL;
+		ks = ksize(p);
+	} else
+		ks = 0;
+
+	/* If the object still fits, repoison it precisely. */
+	if (ks >= new_size) {
+		/* Zero out spare memory. */
+		if (want_init_on_alloc(flags)) {
+			kasan_disable_current();
+			memset(kasan_reset_tag(p) + new_size, 0, ks - new_size);
+			kasan_enable_current();
+		}
+
+		p = kasan_krealloc((void *)p, new_size, flags);
+		return (void *)p;
+	}
+
+	ret = kmalloc_node_track_caller_noprof(new_size, flags, NUMA_NO_NODE, _RET_IP_);
+	if (ret && p) {
+		/* Disable KASAN checks as the object's redzone is accessed. */
+		kasan_disable_current();
+		memcpy(ret, kasan_reset_tag(p), ks);
+		kasan_enable_current();
+	}
+
+	return ret;
+}
+
+/**
+ * krealloc - reallocate memory. The contents will remain unchanged.
+ * @p: object to reallocate memory for.
+ * @new_size: how many bytes of memory are required.
+ * @flags: the type of memory to allocate.
+ *
+ * If @p is %NULL, krealloc() behaves exactly like kmalloc().  If @new_size
+ * is 0 and @p is not a %NULL pointer, the object pointed to is freed.
+ *
+ * If __GFP_ZERO logic is requested, callers must ensure that, starting with the
+ * initial memory allocation, every subsequent call to this API for the same
+ * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that
+ * __GFP_ZERO is not fully honored by this API.
+ *
+ * This is the case, since krealloc() only knows about the bucket size of an
+ * allocation (but not the exact size it was allocated with) and hence
+ * implements the following semantics for shrinking and growing buffers with
+ * __GFP_ZERO.
+ *
+ *         new             bucket
+ * 0       size             size
+ * |--------|----------------|
+ * |  keep  |      zero      |
+ *
+ * In any case, the contents of the object pointed to are preserved up to the
+ * lesser of the new and old sizes.
+ *
+ * Return: pointer to the allocated memory or %NULL in case of error
+ */
+void *krealloc_noprof(const void *p, size_t new_size, gfp_t flags)
+{
+	void *ret;
+
+	if (unlikely(!new_size)) {
+		kfree(p);
+		return ZERO_SIZE_PTR;
+	}
+
+	ret = __do_krealloc(p, new_size, flags);
+	if (ret && kasan_reset_tag(p) != kasan_reset_tag(ret))
+		kfree(p);
+
+	return ret;
+}
+EXPORT_SYMBOL(krealloc_noprof);
+
 struct detached_freelist {
 	struct slab *slab;
 	void *tail;

From b4b797d87745f79e1d3c945dc0db4093c9ae9904 Mon Sep 17 00:00:00 2001
From: Zhen Lei <thunder.leizhen@huawei.com>
Date: Wed, 9 Oct 2024 11:54:55 +0800
Subject: [PATCH 0690/1530] mm/slab: remove duplicate check in create_cache()

The WARN_ON() check in static function create_cache() is done by its only
parent __kmem_cache_create_args() before calling it.
	if (... ||
	    WARN_ON(... ||
		    object_size - args->usersize < args->useroffset))
		args->usersize = args->useroffset = 0;
	...
	s = create_cache(cache_name, object_size, args, flags);

Therefore, the WARN_ON() check in create_cache() can be safely removed.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slab_common.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/mm/slab_common.c b/mm/slab_common.c
index f1f90491df03a..9e22d1266f6a2 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -222,9 +222,6 @@ static struct kmem_cache *create_cache(const char *name,
 	struct kmem_cache *s;
 	int err;
 
-	if (WARN_ON(args->useroffset + args->usersize > object_size))
-		args->useroffset = args->usersize = 0;
-
 	/* If a custom freelist pointer is requested make sure it's sane. */
 	err = -EINVAL;
 	if (args->use_freeptr_offset &&

From b6da940130579769a42605b2c7f529b6f14ef1f8 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Wed, 9 Oct 2024 16:29:37 +0200
Subject: [PATCH 0691/1530] mm, slab: add kerneldocs for common SLAB_ flags

We have many SLAB_ flags but many are used only internally, by kunit
tests or debugging subsystems cooperating with slab, or are set
according to slab_debug boot parameter.

Create kerneldocs for the commonly used flags that may be passed to
kmem_cache_create(). SLAB_TYPESAFE_BY_RCU already had a detailed
description, so turn it to a kerneldoc. Add some details for
SLAB_ACCOUNT, SLAB_RECLAIM_ACCOUNT and SLAB_HWCACHE_ALIGN. Reference
them from the __kmem_cache_create_args() kerneldoc.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 include/linux/slab.h | 60 ++++++++++++++++++++++++++++++--------------
 mm/slab_common.c     | 14 ++++++++++-
 2 files changed, 54 insertions(+), 20 deletions(-)

diff --git a/include/linux/slab.h b/include/linux/slab.h
index b35e2db7eb0ec..49e9fb93e8646 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -77,7 +77,17 @@ enum _slab_flag_bits {
 #define SLAB_POISON		__SLAB_FLAG_BIT(_SLAB_POISON)
 /* Indicate a kmalloc slab */
 #define SLAB_KMALLOC		__SLAB_FLAG_BIT(_SLAB_KMALLOC)
-/* Align objs on cache lines */
+/**
+ * define SLAB_HWCACHE_ALIGN - Align objects on cache line boundaries.
+ *
+ * Sufficiently large objects are aligned on cache line boundary. For object
+ * size smaller than a half of cache line size, the alignment is on the half of
+ * cache line size. In general, if object size is smaller than 1/2^n of cache
+ * line size, the alignment is adjusted to 1/2^n.
+ *
+ * If explicit alignment is also requested by the respective
+ * &struct kmem_cache_args field, the greater of both is alignments is applied.
+ */
 #define SLAB_HWCACHE_ALIGN	__SLAB_FLAG_BIT(_SLAB_HWCACHE_ALIGN)
 /* Use GFP_DMA memory */
 #define SLAB_CACHE_DMA		__SLAB_FLAG_BIT(_SLAB_CACHE_DMA)
@@ -87,8 +97,8 @@ enum _slab_flag_bits {
 #define SLAB_STORE_USER		__SLAB_FLAG_BIT(_SLAB_STORE_USER)
 /* Panic if kmem_cache_create() fails */
 #define SLAB_PANIC		__SLAB_FLAG_BIT(_SLAB_PANIC)
-/*
- * SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS!
+/**
+ * define SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS!
  *
  * This delays freeing the SLAB page by a grace period, it does _NOT_
  * delay object freeing. This means that if you do kmem_cache_free()
@@ -99,20 +109,22 @@ enum _slab_flag_bits {
  * stays valid, the trick to using this is relying on an independent
  * object validation pass. Something like:
  *
- * begin:
- *  rcu_read_lock();
- *  obj = lockless_lookup(key);
- *  if (obj) {
- *    if (!try_get_ref(obj)) // might fail for free objects
- *      rcu_read_unlock();
- *      goto begin;
+ * ::
+ *
+ *  begin:
+ *   rcu_read_lock();
+ *   obj = lockless_lookup(key);
+ *   if (obj) {
+ *     if (!try_get_ref(obj)) // might fail for free objects
+ *       rcu_read_unlock();
+ *       goto begin;
  *
- *    if (obj->key != key) { // not the object we expected
- *      put_ref(obj);
- *      rcu_read_unlock();
- *      goto begin;
- *    }
- *  }
+ *     if (obj->key != key) { // not the object we expected
+ *       put_ref(obj);
+ *       rcu_read_unlock();
+ *       goto begin;
+ *     }
+ *   }
  *  rcu_read_unlock();
  *
  * This is useful if we need to approach a kernel structure obliquely,
@@ -137,7 +149,6 @@ enum _slab_flag_bits {
  *
  * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU.
  */
-/* Defer freeing slabs to RCU */
 #define SLAB_TYPESAFE_BY_RCU	__SLAB_FLAG_BIT(_SLAB_TYPESAFE_BY_RCU)
 /* Trace allocations and frees */
 #define SLAB_TRACE		__SLAB_FLAG_BIT(_SLAB_TRACE)
@@ -170,7 +181,12 @@ enum _slab_flag_bits {
 #else
 # define SLAB_FAILSLAB		__SLAB_FLAG_UNUSED
 #endif
-/* Account to memcg */
+/**
+ * define SLAB_ACCOUNT - Account allocations to memcg.
+ *
+ * All object allocations from this cache will be memcg accounted, regardless of
+ * __GFP_ACCOUNT being or not being passed to individual allocations.
+ */
 #ifdef CONFIG_MEMCG
 # define SLAB_ACCOUNT		__SLAB_FLAG_BIT(_SLAB_ACCOUNT)
 #else
@@ -197,7 +213,13 @@ enum _slab_flag_bits {
 #endif
 
 /* The following flags affect the page allocator grouping pages by mobility */
-/* Objects are reclaimable */
+/**
+ * define SLAB_RECLAIM_ACCOUNT - Objects are reclaimable.
+ *
+ * Use this flag for caches that have an associated shrinker. As a result, slab
+ * pages are allocated with __GFP_RECLAIMABLE, which affects grouping pages by
+ * mobility, and are accounted in SReclaimable counter in /proc/meminfo
+ */
 #ifndef CONFIG_SLUB_TINY
 #define SLAB_RECLAIM_ACCOUNT	__SLAB_FLAG_BIT(_SLAB_RECLAIM_ACCOUNT)
 #else
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 9e22d1266f6a2..62878edb0a81a 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -254,11 +254,23 @@ static struct kmem_cache *create_cache(const char *name,
  * @object_size: The size of objects to be created in this cache.
  * @args: Additional arguments for the cache creation (see
  *        &struct kmem_cache_args).
- * @flags: See %SLAB_* flags for an explanation of individual @flags.
+ * @flags: See the desriptions of individual flags. The common ones are listed
+ *         in the description below.
  *
  * Not to be called directly, use the kmem_cache_create() wrapper with the same
  * parameters.
  *
+ * Commonly used @flags:
+ *
+ * &SLAB_ACCOUNT - Account allocations to memcg.
+ *
+ * &SLAB_HWCACHE_ALIGN - Align objects on cache line boundaries.
+ *
+ * &SLAB_RECLAIM_ACCOUNT - Objects are reclaimable.
+ *
+ * &SLAB_TYPESAFE_BY_RCU - Slab page (not individual objects) freeing delayed
+ * by a grace period - see the full description before using.
+ *
  * Context: Cannot be called within a interrupt, but can be interrupted.
  *
  * Return: a pointer to the cache on success, NULL on failure.

From f7c80fad6c2b64cf73361772dbd30493879e85f4 Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@gentwo.org>
Date: Tue, 1 Oct 2024 12:08:06 -0700
Subject: [PATCH 0692/1530] SLUB: Add support for per object memory policies

The old SLAB allocator used to support memory policies on a per
allocation bases. In SLUB the memory policies are applied on a
per page frame / folio bases. Doing so avoids having to check memory
policies in critical code paths for kmalloc and friends.

This worked on general well on Intel/AMD/PowerPC because the
interconnect technology is mature and can minimize the latencies
through intelligent caching even if a small object is not
placed optimally.

However, on ARM we have an emergence of new NUMA interconnect
technology based more on embedded devices. Caching of remote content
can currently be ineffective using the standard building blocks / mesh
available on that platform. Such architectures benefit if each slab
object is individually placed according to memory policies
and other restrictions.

This patch adds another kernel parameter

    slab_strict_numa

If that is set then a static branch is activated that will cause
the hotpaths of the allocator to evaluate the current memory
allocation policy. Each object will be properly placed by
paying the price of extra processing and SLUB will no longer
defer to the page allocator to apply memory policies at the
folio level.

This patch improves performance of memcached running
on Ampere Altra 2P system (ARM Neoverse N1 processor)
by 3.6% due to accurate placement of small kernel objects.

Tested-by: Huang Shijie <shijie@os.amperecomputing.com>
Signed-off-by: Christoph Lameter (Ampere) <cl@gentwo.org>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 .../admin-guide/kernel-parameters.txt         | 10 +++++
 Documentation/mm/slub.rst                     |  9 ++++
 mm/slub.c                                     | 43 +++++++++++++++++++
 3 files changed, 62 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 1518343bbe223..9be54e9a55d32 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6147,6 +6147,16 @@
 			For more information see Documentation/mm/slub.rst.
 			(slub_nomerge legacy name also accepted for now)
 
+	slab_strict_numa	[MM]
+			Support memory policies on a per object level
+			in the slab allocator. The default is for memory
+			policies to be applied at the folio level when
+			a new folio is needed or a partial folio is
+			retrieved from the lists. Increases overhead
+			in the slab fastpaths but gains more accurate
+			NUMA kernel object placement which helps with slow
+			interconnects in NUMA systems.
+
 	slram=		[HW,MTD]
 
 	smart2=		[HW]
diff --git a/Documentation/mm/slub.rst b/Documentation/mm/slub.rst
index 60d350d08362b..84ca1dc94e5ee 100644
--- a/Documentation/mm/slub.rst
+++ b/Documentation/mm/slub.rst
@@ -175,6 +175,15 @@ can be influenced by kernel parameters:
 	``slab_max_order`` to 0, what cause minimum possible order of
 	slabs allocation.
 
+``slab_strict_numa``
+        Enables the application of memory policies on each
+        allocation. This results in more accurate placement of
+        objects which may result in the reduction of accesses
+        to remote nodes. The default is to only apply memory
+        policies at the folio level when a new folio is acquired
+        or a folio is retrieved from the lists. Enabling this
+        option reduces the fastpath performance of the slab allocator.
+
 SLUB Debug output
 =================
 
diff --git a/mm/slub.c b/mm/slub.c
index 5b832512044e3..d4b1680ef17a4 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -218,6 +218,10 @@ DEFINE_STATIC_KEY_FALSE(slub_debug_enabled);
 #endif
 #endif		/* CONFIG_SLUB_DEBUG */
 
+#ifdef CONFIG_NUMA
+static DEFINE_STATIC_KEY_FALSE(strict_numa);
+#endif
+
 /* Structure holding parameters for get_partial() call chain */
 struct partial_context {
 	gfp_t flags;
@@ -3956,6 +3960,28 @@ static __always_inline void *__slab_alloc_node(struct kmem_cache *s,
 	object = c->freelist;
 	slab = c->slab;
 
+#ifdef CONFIG_NUMA
+	if (static_branch_unlikely(&strict_numa) &&
+			node == NUMA_NO_NODE) {
+
+		struct mempolicy *mpol = current->mempolicy;
+
+		if (mpol) {
+			/*
+			 * Special BIND rule support. If existing slab
+			 * is in permitted set then do not redirect
+			 * to a particular node.
+			 * Otherwise we apply the memory policy to get
+			 * the node we need to allocate on.
+			 */
+			if (mpol->mode != MPOL_BIND || !slab ||
+					!node_isset(slab_nid(slab), mpol->nodes))
+
+				node = mempolicy_slab_node();
+		}
+	}
+#endif
+
 	if (!USE_LOCKLESS_FAST_PATH() ||
 	    unlikely(!object || !slab || !node_match(slab, node))) {
 		object = __slab_alloc(s, gfpflags, node, addr, c, orig_size);
@@ -5602,6 +5628,23 @@ static int __init setup_slub_min_objects(char *str)
 __setup("slab_min_objects=", setup_slub_min_objects);
 __setup_param("slub_min_objects=", slub_min_objects, setup_slub_min_objects, 0);
 
+#ifdef CONFIG_NUMA
+static int __init setup_slab_strict_numa(char *str)
+{
+	if (nr_node_ids > 1) {
+		static_branch_enable(&strict_numa);
+		pr_info("SLUB: Strict NUMA enabled.\n");
+	} else {
+		pr_warn("slab_strict_numa parameter set on non NUMA system.\n");
+	}
+
+	return 1;
+}
+
+__setup("slab_strict_numa", setup_slab_strict_numa);
+#endif
+
+
 #ifdef CONFIG_HARDENED_USERCOPY
 /*
  * Rejects incorrectly sized objects and objects that are to be copied

From 06cbc5e45317c0521709f85c9046f3fbc57382c2 Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Mon, 21 Oct 2024 15:45:55 -0500
Subject: [PATCH 0693/1530] remoteproc: k3-r5: Use IO memset to clear TCMs

While it should be safe to use normal memset() on these memories as they
are mapped as Normal Non-Cached, using the memset_io() provides stronger
guarantees on access alignment and fixes a sparse check warning. Switch
to memset_io() here.

Signed-off-by: Andrew Davis <afd@ti.com>
Link: https://lore.kernel.org/r/20241021204557.929823-1-afd@ti.com
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/ti_k3_r5_remoteproc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c
index 2f996a962f557..e1fe85e5eba6a 100644
--- a/drivers/remoteproc/ti_k3_r5_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c
@@ -487,10 +487,10 @@ static int k3_r5_rproc_prepare(struct rproc *rproc)
 	 * can be effective on all TCM addresses.
 	 */
 	dev_dbg(dev, "zeroing out ATCM memory\n");
-	memset(core->mem[0].cpu_addr, 0x00, core->mem[0].size);
+	memset_io(core->mem[0].cpu_addr, 0x00, core->mem[0].size);
 
 	dev_dbg(dev, "zeroing out BTCM memory\n");
-	memset(core->mem[1].cpu_addr, 0x00, core->mem[1].size);
+	memset_io(core->mem[1].cpu_addr, 0x00, core->mem[1].size);
 
 	return 0;
 }

From 760c69af2cc4c93aa6a58f50f637816657850099 Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Mon, 21 Oct 2024 15:45:56 -0500
Subject: [PATCH 0694/1530] remoteproc: k3-r5: Force cast from iomem address
 space

These memory regions are mapped as Normal Non-Cached which on
does not have the normal IO address space limitations and so this
cast is safe. Add '__force' to explicitly specify that the cast is
intentional to remove a sparse check warning.

Signed-off-by: Andrew Davis <afd@ti.com>
Link: https://lore.kernel.org/r/20241021204557.929823-2-afd@ti.com
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/ti_k3_r5_remoteproc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c
index e1fe85e5eba6a..6560b7954027f 100644
--- a/drivers/remoteproc/ti_k3_r5_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c
@@ -717,7 +717,7 @@ static struct resource_table *k3_r5_get_loaded_rsc_table(struct rproc *rproc,
 	 * the hard-coded value suffices to support the IPC-only mode.
 	 */
 	*rsc_table_sz = 256;
-	return (struct resource_table *)kproc->rmem[0].cpu_addr;
+	return (__force struct resource_table *)kproc->rmem[0].cpu_addr;
 }
 
 /*

From 3a8c30e88cfb96d6f7aaa1626446147f7fe1aff3 Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Mon, 21 Oct 2024 15:45:57 -0500
Subject: [PATCH 0695/1530] remoteproc: k3-dsp: Force cast from iomem address
 space

These memory regions are mapped as Normal Non-Cached which on
does not have the normal IO address space limitations and so this
cast is safe. Add '__force' to explicitly specify that the cast is
intentional to remove a sparse check warning.

Signed-off-by: Andrew Davis <afd@ti.com>
Link: https://lore.kernel.org/r/20241021204557.929823-3-afd@ti.com
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/ti_k3_dsp_remoteproc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/remoteproc/ti_k3_dsp_remoteproc.c b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
index d08a3a98ada1c..ffb46c64170ac 100644
--- a/drivers/remoteproc/ti_k3_dsp_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
@@ -403,7 +403,7 @@ static struct resource_table *k3_dsp_get_loaded_rsc_table(struct rproc *rproc,
 	 * the hard-coded value suffices to support the IPC-only mode.
 	 */
 	*rsc_table_sz = 256;
-	return (struct resource_table *)kproc->rmem[0].cpu_addr;
+	return (__force struct resource_table *)kproc->rmem[0].cpu_addr;
 }
 
 /*

From ad64a7c4a49d30c5d909a35e2c7882d3870ddafc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@baylibre.com>
Date: Fri, 25 Oct 2024 15:13:41 +0200
Subject: [PATCH 0696/1530] remoteproc: Switch back to struct
 platform_driver::remove()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 0edb555a65d1 ("platform: Make platform_driver::remove()
return void") .remove() is (again) the right callback to implement for
platform drivers.

Convert all platform drivers below drivers/remoteproc to use .remove(),
with the eventual goal to drop struct platform_driver::remove_new(). As
.remove() and .remove_new() have the same prototypes, conversion is done
by just changing the structure member name in the driver initializer.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Link: https://lore.kernel.org/r/20241025131340.258233-2-u.kleine-koenig@baylibre.com
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/da8xx_remoteproc.c     | 2 +-
 drivers/remoteproc/imx_dsp_rproc.c        | 2 +-
 drivers/remoteproc/imx_rproc.c            | 2 +-
 drivers/remoteproc/keystone_remoteproc.c  | 2 +-
 drivers/remoteproc/meson_mx_ao_arc.c      | 2 +-
 drivers/remoteproc/mtk_scp.c              | 2 +-
 drivers/remoteproc/pru_rproc.c            | 2 +-
 drivers/remoteproc/qcom_q6v5_adsp.c       | 2 +-
 drivers/remoteproc/qcom_q6v5_mss.c        | 2 +-
 drivers/remoteproc/qcom_q6v5_pas.c        | 2 +-
 drivers/remoteproc/qcom_q6v5_wcss.c       | 2 +-
 drivers/remoteproc/qcom_wcnss.c           | 2 +-
 drivers/remoteproc/rcar_rproc.c           | 2 +-
 drivers/remoteproc/remoteproc_virtio.c    | 2 +-
 drivers/remoteproc/st_remoteproc.c        | 2 +-
 drivers/remoteproc/stm32_rproc.c          | 2 +-
 drivers/remoteproc/ti_k3_dsp_remoteproc.c | 2 +-
 drivers/remoteproc/wkup_m3_rproc.c        | 2 +-
 18 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/drivers/remoteproc/da8xx_remoteproc.c b/drivers/remoteproc/da8xx_remoteproc.c
index 7daaab8124e85..93031f0867d10 100644
--- a/drivers/remoteproc/da8xx_remoteproc.c
+++ b/drivers/remoteproc/da8xx_remoteproc.c
@@ -365,7 +365,7 @@ MODULE_DEVICE_TABLE(of, davinci_rproc_of_match);
 
 static struct platform_driver da8xx_rproc_driver = {
 	.probe = da8xx_rproc_probe,
-	.remove_new = da8xx_rproc_remove,
+	.remove = da8xx_rproc_remove,
 	.driver = {
 		.name = "davinci-rproc",
 		.of_match_table = of_match_ptr(davinci_rproc_of_match),
diff --git a/drivers/remoteproc/imx_dsp_rproc.c b/drivers/remoteproc/imx_dsp_rproc.c
index 376187ad5754c..ea5024919c2ff 100644
--- a/drivers/remoteproc/imx_dsp_rproc.c
+++ b/drivers/remoteproc/imx_dsp_rproc.c
@@ -1258,7 +1258,7 @@ MODULE_DEVICE_TABLE(of, imx_dsp_rproc_of_match);
 
 static struct platform_driver imx_dsp_rproc_driver = {
 	.probe = imx_dsp_rproc_probe,
-	.remove_new = imx_dsp_rproc_remove,
+	.remove = imx_dsp_rproc_remove,
 	.driver = {
 		.name = "imx-dsp-rproc",
 		.of_match_table = imx_dsp_rproc_of_match,
diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c
index 800015ff7ff92..74299af1d7f10 100644
--- a/drivers/remoteproc/imx_rproc.c
+++ b/drivers/remoteproc/imx_rproc.c
@@ -1198,7 +1198,7 @@ MODULE_DEVICE_TABLE(of, imx_rproc_of_match);
 
 static struct platform_driver imx_rproc_driver = {
 	.probe = imx_rproc_probe,
-	.remove_new = imx_rproc_remove,
+	.remove = imx_rproc_remove,
 	.driver = {
 		.name = "imx-rproc",
 		.of_match_table = imx_rproc_of_match,
diff --git a/drivers/remoteproc/keystone_remoteproc.c b/drivers/remoteproc/keystone_remoteproc.c
index 8f0f7a4cfef26..6e54093d17323 100644
--- a/drivers/remoteproc/keystone_remoteproc.c
+++ b/drivers/remoteproc/keystone_remoteproc.c
@@ -490,7 +490,7 @@ MODULE_DEVICE_TABLE(of, keystone_rproc_of_match);
 
 static struct platform_driver keystone_rproc_driver = {
 	.probe	= keystone_rproc_probe,
-	.remove_new = keystone_rproc_remove,
+	.remove = keystone_rproc_remove,
 	.driver	= {
 		.name = "keystone-rproc",
 		.of_match_table = keystone_rproc_of_match,
diff --git a/drivers/remoteproc/meson_mx_ao_arc.c b/drivers/remoteproc/meson_mx_ao_arc.c
index f6744b5383230..7dfdf11b00368 100644
--- a/drivers/remoteproc/meson_mx_ao_arc.c
+++ b/drivers/remoteproc/meson_mx_ao_arc.c
@@ -246,7 +246,7 @@ MODULE_DEVICE_TABLE(of, meson_mx_ao_arc_rproc_match);
 
 static struct platform_driver meson_mx_ao_arc_rproc_driver = {
 	.probe = meson_mx_ao_arc_rproc_probe,
-	.remove_new = meson_mx_ao_arc_rproc_remove,
+	.remove = meson_mx_ao_arc_rproc_remove,
 	.driver = {
 		.name = "meson-mx-ao-arc-rproc",
 		.of_match_table = meson_mx_ao_arc_rproc_match,
diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c
index e744c07507eed..0f4a7065d0bd9 100644
--- a/drivers/remoteproc/mtk_scp.c
+++ b/drivers/remoteproc/mtk_scp.c
@@ -1521,7 +1521,7 @@ MODULE_DEVICE_TABLE(of, mtk_scp_of_match);
 
 static struct platform_driver mtk_scp_driver = {
 	.probe = scp_probe,
-	.remove_new = scp_remove,
+	.remove = scp_remove,
 	.driver = {
 		.name = "mtk-scp",
 		.of_match_table = mtk_scp_of_match,
diff --git a/drivers/remoteproc/pru_rproc.c b/drivers/remoteproc/pru_rproc.c
index 327f0c7ee3d6b..1656574b73175 100644
--- a/drivers/remoteproc/pru_rproc.c
+++ b/drivers/remoteproc/pru_rproc.c
@@ -1132,7 +1132,7 @@ static struct platform_driver pru_rproc_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe  = pru_rproc_probe,
-	.remove_new = pru_rproc_remove,
+	.remove = pru_rproc_remove,
 };
 module_platform_driver(pru_rproc_driver);
 
diff --git a/drivers/remoteproc/qcom_q6v5_adsp.c b/drivers/remoteproc/qcom_q6v5_adsp.c
index 572dcb0f055b7..cbd9a914880ba 100644
--- a/drivers/remoteproc/qcom_q6v5_adsp.c
+++ b/drivers/remoteproc/qcom_q6v5_adsp.c
@@ -840,7 +840,7 @@ MODULE_DEVICE_TABLE(of, adsp_of_match);
 
 static struct platform_driver adsp_pil_driver = {
 	.probe = adsp_probe,
-	.remove_new = adsp_remove,
+	.remove = adsp_remove,
 	.driver = {
 		.name = "qcom_q6v5_adsp",
 		.of_match_table = adsp_of_match,
diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c
index 2a42215ce8e07..103368d11a96e 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -2533,7 +2533,7 @@ MODULE_DEVICE_TABLE(of, q6v5_of_match);
 
 static struct platform_driver q6v5_driver = {
 	.probe = q6v5_probe,
-	.remove_new = q6v5_remove,
+	.remove = q6v5_remove,
 	.driver = {
 		.name = "qcom-q6v5-mss",
 		.of_match_table = q6v5_of_match,
diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
index ef82835e98a4e..297ef0c69054d 100644
--- a/drivers/remoteproc/qcom_q6v5_pas.c
+++ b/drivers/remoteproc/qcom_q6v5_pas.c
@@ -1477,7 +1477,7 @@ MODULE_DEVICE_TABLE(of, adsp_of_match);
 
 static struct platform_driver adsp_driver = {
 	.probe = adsp_probe,
-	.remove_new = adsp_remove,
+	.remove = adsp_remove,
 	.driver = {
 		.name = "qcom_q6v5_pas",
 		.of_match_table = adsp_of_match,
diff --git a/drivers/remoteproc/qcom_q6v5_wcss.c b/drivers/remoteproc/qcom_q6v5_wcss.c
index e913dabae9924..810441f43396f 100644
--- a/drivers/remoteproc/qcom_q6v5_wcss.c
+++ b/drivers/remoteproc/qcom_q6v5_wcss.c
@@ -1111,7 +1111,7 @@ MODULE_DEVICE_TABLE(of, q6v5_wcss_of_match);
 
 static struct platform_driver q6v5_wcss_driver = {
 	.probe = q6v5_wcss_probe,
-	.remove_new = q6v5_wcss_remove,
+	.remove = q6v5_wcss_remove,
 	.driver = {
 		.name = "qcom-q6v5-wcss-pil",
 		.of_match_table = q6v5_wcss_of_match,
diff --git a/drivers/remoteproc/qcom_wcnss.c b/drivers/remoteproc/qcom_wcnss.c
index a7bb9da27029d..5b5664603eed2 100644
--- a/drivers/remoteproc/qcom_wcnss.c
+++ b/drivers/remoteproc/qcom_wcnss.c
@@ -682,7 +682,7 @@ MODULE_DEVICE_TABLE(of, wcnss_of_match);
 
 static struct platform_driver wcnss_driver = {
 	.probe = wcnss_probe,
-	.remove_new = wcnss_remove,
+	.remove = wcnss_remove,
 	.driver = {
 		.name = "qcom-wcnss-pil",
 		.of_match_table = wcnss_of_match,
diff --git a/drivers/remoteproc/rcar_rproc.c b/drivers/remoteproc/rcar_rproc.c
index cc17e8421f65b..921d853594f42 100644
--- a/drivers/remoteproc/rcar_rproc.c
+++ b/drivers/remoteproc/rcar_rproc.c
@@ -214,7 +214,7 @@ MODULE_DEVICE_TABLE(of, rcar_rproc_of_match);
 
 static struct platform_driver rcar_rproc_driver = {
 	.probe = rcar_rproc_probe,
-	.remove_new = rcar_rproc_remove,
+	.remove = rcar_rproc_remove,
 	.driver = {
 		.name = "rcar-rproc",
 		.of_match_table = rcar_rproc_of_match,
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index d3f39009b28ed..25a655f33ec0e 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -593,7 +593,7 @@ static void rproc_virtio_remove(struct platform_device *pdev)
 /* Platform driver */
 static struct platform_driver rproc_virtio_driver = {
 	.probe		= rproc_virtio_probe,
-	.remove_new	= rproc_virtio_remove,
+	.remove		= rproc_virtio_remove,
 	.driver		= {
 		.name	= "rproc-virtio",
 	},
diff --git a/drivers/remoteproc/st_remoteproc.c b/drivers/remoteproc/st_remoteproc.c
index 1340be9d01101..5df99bae7131a 100644
--- a/drivers/remoteproc/st_remoteproc.c
+++ b/drivers/remoteproc/st_remoteproc.c
@@ -457,7 +457,7 @@ static void st_rproc_remove(struct platform_device *pdev)
 
 static struct platform_driver st_rproc_driver = {
 	.probe = st_rproc_probe,
-	.remove_new = st_rproc_remove,
+	.remove = st_rproc_remove,
 	.driver = {
 		.name = "st-rproc",
 		.of_match_table = of_match_ptr(st_rproc_match),
diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c
index 8c7f7950b80ee..b02b36a3f5156 100644
--- a/drivers/remoteproc/stm32_rproc.c
+++ b/drivers/remoteproc/stm32_rproc.c
@@ -946,7 +946,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(stm32_rproc_pm_ops,
 
 static struct platform_driver stm32_rproc_driver = {
 	.probe = stm32_rproc_probe,
-	.remove_new = stm32_rproc_remove,
+	.remove = stm32_rproc_remove,
 	.driver = {
 		.name = "stm32-rproc",
 		.pm = pm_ptr(&stm32_rproc_pm_ops),
diff --git a/drivers/remoteproc/ti_k3_dsp_remoteproc.c b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
index ffb46c64170ac..a695890254ff7 100644
--- a/drivers/remoteproc/ti_k3_dsp_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
@@ -791,7 +791,7 @@ MODULE_DEVICE_TABLE(of, k3_dsp_of_match);
 
 static struct platform_driver k3_dsp_rproc_driver = {
 	.probe	= k3_dsp_rproc_probe,
-	.remove_new = k3_dsp_rproc_remove,
+	.remove = k3_dsp_rproc_remove,
 	.driver	= {
 		.name = "k3-dsp-rproc",
 		.of_match_table = k3_dsp_of_match,
diff --git a/drivers/remoteproc/wkup_m3_rproc.c b/drivers/remoteproc/wkup_m3_rproc.c
index 36a55f7ffa64d..d8be21e717212 100644
--- a/drivers/remoteproc/wkup_m3_rproc.c
+++ b/drivers/remoteproc/wkup_m3_rproc.c
@@ -251,7 +251,7 @@ static const struct dev_pm_ops wkup_m3_rproc_pm_ops = {
 
 static struct platform_driver wkup_m3_rproc_driver = {
 	.probe = wkup_m3_rproc_probe,
-	.remove_new = wkup_m3_rproc_remove,
+	.remove = wkup_m3_rproc_remove,
 	.driver = {
 		.name = "wkup_m3_rproc",
 		.of_match_table = wkup_m3_rproc_of_match,

From 19966d792b9e6b055aeb2f0e573b4d4573d5e15b Mon Sep 17 00:00:00 2001
From: Graham Woodward <graham.woodward@arm.com>
Date: Fri, 25 Oct 2024 15:30:06 +0100
Subject: [PATCH 0697/1530] perf arm-spe: Set sample.addr to target address for
 instruction sample

For an instruction sample, assign the target address to the field
'to_ip'.
If it is a non-branch record, to_ip will be 0, presenting a non-valid
target address.

Signed-off-by: Graham Woodward <graham.woodward@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: nd@arm.com
Cc: mike.leach@linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20241025143009.25419-2-graham.woodward@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/arm-spe.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 856cc36f33d79..49b7638073600 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -418,7 +418,7 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,
 
 	sample.id = spe_events_id;
 	sample.stream_id = spe_events_id;
-	sample.addr = record->virt_addr;
+	sample.addr = record->to_ip;
 	sample.phys_addr = record->phys_addr;
 	sample.data_src = data_src;
 	sample.period = spe->instructions_sample_period;

From c1b67c85108f99af0a80aa9e59a2b94ad95428d7 Mon Sep 17 00:00:00 2001
From: Graham Woodward <graham.woodward@arm.com>
Date: Fri, 25 Oct 2024 15:30:07 +0100
Subject: [PATCH 0698/1530] perf arm-spe: Use ARM_SPE_OP_BRANCH_ERET when
 synthesizing branches

Instead of checking the type for just branch misses, we can instead
check for the OP_BRANCH_ERET and synthesise branches as well as
branch misses.

Signed-off-by: Graham Woodward <graham.woodward@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: nd@arm.com
Cc: mike.leach@linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20241025143009.25419-3-graham.woodward@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/arm-spe.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 49b7638073600..e60e21d247355 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -68,7 +68,7 @@ struct arm_spe {
 	u64				llc_access_id;
 	u64				tlb_miss_id;
 	u64				tlb_access_id;
-	u64				branch_miss_id;
+	u64				branch_id;
 	u64				remote_access_id;
 	u64				memory_id;
 	u64				instructions_id;
@@ -672,8 +672,8 @@ static int arm_spe_sample(struct arm_spe_queue *speq)
 		}
 	}
 
-	if (spe->sample_branch && (record->type & ARM_SPE_BRANCH_MISS)) {
-		err = arm_spe__synth_branch_sample(speq, spe->branch_miss_id);
+	if (spe->sample_branch && (record->op & ARM_SPE_OP_BRANCH_ERET)) {
+		err = arm_spe__synth_branch_sample(speq, spe->branch_id);
 		if (err)
 			return err;
 	}
@@ -1385,12 +1385,12 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
 	if (spe->synth_opts.branches) {
 		spe->sample_branch = true;
 
-		/* Branch miss */
+		/* Branch */
 		err = perf_session__deliver_synth_attr_event(session, &attr, id);
 		if (err)
 			return err;
-		spe->branch_miss_id = id;
-		arm_spe_set_event_name(evlist, id, "branch-miss");
+		spe->branch_id = id;
+		arm_spe_set_event_name(evlist, id, "branch");
 		id += 1;
 	}
 

From edff8dad3f9a483259140fb814586b39da430a38 Mon Sep 17 00:00:00 2001
From: Graham Woodward <graham.woodward@arm.com>
Date: Fri, 25 Oct 2024 15:30:08 +0100
Subject: [PATCH 0699/1530] perf arm-spe: Correctly set sample flags

Set flags on all synthesized instruction and branch samples.

Signed-off-by: Graham Woodward <graham.woodward@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: nd@arm.com
Cc: mike.leach@linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20241025143009.25419-4-graham.woodward@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-script.c |  1 +
 tools/perf/util/arm-spe.c   | 17 +++++++++++++++++
 tools/perf/util/event.h     |  1 +
 3 files changed, 19 insertions(+)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 8c5d5cecfba48..6b6d4472db6e6 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1728,6 +1728,7 @@ static struct {
 	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "tr end"},
 	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMENTRY, "vmentry"},
 	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMEXIT, "vmexit"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_BRANCH_MISS, "br miss"},
 	{0, NULL}
 };
 
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index e60e21d247355..a291a412f6a14 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -100,6 +100,7 @@ struct arm_spe_queue {
 	u64				timestamp;
 	struct thread			*thread;
 	u64				period_instructions;
+	u32				flags;
 };
 
 static void arm_spe_dump(struct arm_spe *spe __maybe_unused,
@@ -394,6 +395,7 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq,
 	sample.stream_id = spe_events_id;
 	sample.addr = record->to_ip;
 	sample.weight = record->latency;
+	sample.flags = speq->flags;
 
 	return arm_spe_deliver_synth_event(spe, speq, event, &sample);
 }
@@ -423,6 +425,7 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,
 	sample.data_src = data_src;
 	sample.period = spe->instructions_sample_period;
 	sample.weight = record->latency;
+	sample.flags = speq->flags;
 
 	return arm_spe_deliver_synth_event(spe, speq, event, &sample);
 }
@@ -440,6 +443,19 @@ static const struct midr_range common_ds_encoding_cpus[] = {
 	{},
 };
 
+static void arm_spe__sample_flags(struct arm_spe_queue *speq)
+{
+	const struct arm_spe_record *record = &speq->decoder->record;
+
+	speq->flags = 0;
+	if (record->op & ARM_SPE_OP_BRANCH_ERET) {
+		speq->flags = PERF_IP_FLAG_BRANCH;
+
+		if (record->type & ARM_SPE_BRANCH_MISS)
+			speq->flags |= PERF_IP_FLAG_BRANCH_MISS;
+	}
+}
+
 static void arm_spe__synth_data_source_common(const struct arm_spe_record *record,
 					      union perf_mem_data_src *data_src)
 {
@@ -622,6 +638,7 @@ static int arm_spe_sample(struct arm_spe_queue *speq)
 	u64 data_src;
 	int err;
 
+	arm_spe__sample_flags(speq);
 	data_src = arm_spe__synth_data_source(speq, record);
 
 	if (spe->sample_flc) {
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index f8742e6230a5a..2744c54f404e7 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -66,6 +66,7 @@ enum {
 	PERF_IP_FLAG_VMEXIT		= 1ULL << 12,
 	PERF_IP_FLAG_INTR_DISABLE	= 1ULL << 13,
 	PERF_IP_FLAG_INTR_TOGGLE	= 1ULL << 14,
+	PERF_IP_FLAG_BRANCH_MISS	= 1ULL << 15,
 };
 
 #define PERF_IP_FLAG_CHARS "bcrosyiABExghDt"

From 35f5aa9ccc83f4a4171cdb6ba023e514e2b2ecff Mon Sep 17 00:00:00 2001
From: Graham Woodward <graham.woodward@arm.com>
Date: Fri, 25 Oct 2024 15:30:09 +0100
Subject: [PATCH 0700/1530] perf arm-spe: Update --itrace help text

The --itrace help now needs updating to reflect that
the --itrace=b argument sythesises branches as well
as branch misses.

Signed-off-by: Graham Woodward <graham.woodward@arm.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: nd@arm.com
Cc: mike.leach@linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20241025143009.25419-5-graham.woodward@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Documentation/itrace.txt       | 2 +-
 tools/perf/Documentation/perf-arm-spe.txt | 2 +-
 tools/perf/util/auxtrace.h                | 3 +--
 3 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index 19cc179be9a78..40476b227f8d6 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -1,6 +1,6 @@
 		i	synthesize instructions events
 		y	synthesize cycles events
-		b	synthesize branches events (branch misses for Arm SPE)
+		b	synthesize branches events
 		c	synthesize branches events (calls only)
 		r	synthesize branches events (returns only)
 		x	synthesize transactions events
diff --git a/tools/perf/Documentation/perf-arm-spe.txt b/tools/perf/Documentation/perf-arm-spe.txt
index 0a3eda482307a..de2b0b479249e 100644
--- a/tools/perf/Documentation/perf-arm-spe.txt
+++ b/tools/perf/Documentation/perf-arm-spe.txt
@@ -187,7 +187,7 @@ groups:
   7 llc-access
   2 tlb-miss
   1K tlb-access
-  36 branch-miss
+  36 branch
   0 remote-access
   900 memory
 
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index a1895a4f530be..dddaf4f3ffeda 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -75,7 +75,6 @@ enum itrace_period_type {
  *          (not fully accurate, since CYC packets are only emitted
  *          together with other events, such as branches)
  * @branches: whether to synthesize 'branches' events
- *            (branch misses only for Arm SPE)
  * @transactions: whether to synthesize events for transactions
  * @ptwrites: whether to synthesize events for ptwrites
  * @pwr_events: whether to synthesize power events
@@ -650,7 +649,7 @@ bool auxtrace__evsel_is_auxtrace(struct perf_session *session,
 #define ITRACE_HELP \
 "				i[period]:    		synthesize instructions events\n" \
 "				y[period]:    		synthesize cycles events (same period as i)\n" \
-"				b:	    		synthesize branches events (branch misses for Arm SPE)\n" \
+"				b:	    		synthesize branches events\n" \
 "				c:	    		synthesize branches events (calls only)\n"	\
 "				r:	    		synthesize branches events (returns only)\n" \
 "				x:	    		synthesize transactions events\n"		\

From 54afc56db221c831479dd1b59eb0657c078355d1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@kernel.org>
Date: Mon, 28 Oct 2024 18:31:28 -0300
Subject: [PATCH 0701/1530] perf probe: Fix retrieval of source files from a
 debuginfod server

When perf is linked with libdebuginfod:

  root@number:~# ldd ~/bin/perf | grep debuginfod
	libdebuginfod.so.1 => /lib64/libdebuginfod.so.1 (0x00007ff5c3930000)
  root@number:~# perf check feature debuginfod
            debuginfod: [ on  ]  # HAVE_DEBUGINFOD_SUPPORT
  root@number:~#

And we don't have a debuginfo package installed for the binary we're
trying to use, vmlinux in this case as we didn't specify any using 'perf
probe -x', it will use the build for the running kernel:

  root@number:~# perf buildid-list -k
  38e927fd7799d50dbc4d99ec5e3f781b6105a6a9
  root@number:~#

And communicate with a debuginfo server, be it configured in a
~/.perfconfig file, excerpt from the 'perf config' man page:

       buildid-cache.*
           buildid-cache.debuginfod=URLs Specify debuginfod URLs to be
	   used when retrieving perf.data binaries, it follows the same
	   syntax as the DEBUGINFOD_URLS variable, like:

               buildid-cache.debuginfod=http://192.168.122.174:8002

Or via the DEBUGINFOD_URLS env var, as distros like fedora do by
default:

  root@number:~# echo $DEBUGINFOD_URLS
  https://debuginfod.fedoraproject.org/
  root@number:~#

To pick and cache just what is needed, instead of requiring the manual
installation of the entire kernel-debuginfo package, which is really
large.

It will, in this example, use the following cache files, deleted
before/after this patch just to test the whole process:

  root@number:~# rm -f /root/.cache/debuginfod_client/38e927fd7799d50dbc4d99ec5e3f781b6105a6a9/source-a1414a5d-#usr#src#debug#kernel-6.11.4#linux-6.11.4-201.fc40.x86_64#net#ipv4#icmp.c
  root@number:~# rm -f /root/.cache/debuginfod_client/38e927fd7799d50dbc4d99ec5e3f781b6105a6a9/debuginfo

Before this patch:

  root@number:~# perf probe -L icmp_rcv
  Failed to find source file path.
    Error: Failed to show lines.
  root@number:~#

This is because 'perf probe' was using just the relative file name, in
this case "net/ipv4/icmp.c", that is where the 'icmp_rcv' function is
located, if we add it and comply with the debuginfo_find_source()
function man page, it contacts the server, finds the necessary files,
cache them locally and all works:

  root@number:~# perf probe -L icmp_rcv | head
  <icmp_rcv@/root/.cache/debuginfod_client/38e927fd7799d50dbc4d99ec5e3f781b6105a6a9/source-a1414a5d-#usr#src#debug#kernel-6.11.4#linux-6.11.4-201.fc40.x86_64#net#ipv4#icmp.c:0>
        0  int icmp_rcv(struct sk_buff *skb)
           {
        2  	enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
           	struct rtable *rt = skb_rtable(skb);
           	struct net *net = dev_net(rt->dst.dev);
           	struct icmphdr *icmph;

           	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
        8  		struct sec_path *sp = skb_sec_path(skb);
  root@number:~#

Acked-by: Frank Ch. Eigler <fche@redhat.com>
Cc: Aaron Merey <amerey@redhat.com>
Cc: Francesco Nigro <fnigro@redhat.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: https://lore.kernel.org/r/ZyACsIFUETsr7-09@x1
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/probe-finder.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 18181017f5fd3..c2ca94e29aca3 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1874,7 +1874,11 @@ int find_source_path(const char *raw_path, const char *sbuild_id,
 	const char *prefix = symbol_conf.source_prefix;
 
 	if (sbuild_id && !prefix) {
-		if (!get_source_from_debuginfod(raw_path, sbuild_id, new_path))
+		char prefixed_raw_path[PATH_MAX];
+
+		path__join(prefixed_raw_path, sizeof(prefixed_raw_path), comp_dir, raw_path);
+
+		if (!get_source_from_debuginfod(prefixed_raw_path, sbuild_id, new_path))
 			return 0;
 	}
 

From e2adb96f53c0fd323d1aeb2a441c55aa7554bb1e Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 23 Oct 2024 01:20:01 +0200
Subject: [PATCH 0702/1530] dt-bindings: arm: airoha: Add the chip-scu node for
 EN7581 SoC

This patch adds the chip-scu document bindings for EN7581 SoC.
The airoha chip-scu block provides a configuration interface for clock,
io-muxing and other functionalities used by multiple controllers (e.g.
clock, pinctrl, ecc.) on EN7581 SoC.

Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/20241023-en7581-pinctrl-v9-1-afb0cbcab0ec@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/arm/airoha,en7581-chip-scu.yaml  | 42 +++++++++++++++++++
 1 file changed, 42 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/arm/airoha,en7581-chip-scu.yaml

diff --git a/Documentation/devicetree/bindings/arm/airoha,en7581-chip-scu.yaml b/Documentation/devicetree/bindings/arm/airoha,en7581-chip-scu.yaml
new file mode 100644
index 0000000000000..67c449d804c22
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/airoha,en7581-chip-scu.yaml
@@ -0,0 +1,42 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/arm/airoha,en7581-chip-scu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Airoha Chip SCU Controller for EN7581 SoC
+
+maintainers:
+  - Lorenzo Bianconi <lorenzo@kernel.org>
+
+description:
+  The airoha chip-scu block provides a configuration interface for clock,
+  io-muxing and other functionalities used by multiple controllers (e.g. clock,
+  pinctrl, ecc) on EN7581 SoC.
+
+properties:
+  compatible:
+    items:
+      - enum:
+          - airoha,en7581-chip-scu
+      - const: syscon
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    soc {
+      #address-cells = <2>;
+      #size-cells = <2>;
+      syscon@1fa20000 {
+        compatible = "airoha,en7581-chip-scu", "syscon";
+        reg = <0x0 0x1fa20000 0x0 0x388>;
+      };
+    };

From d0c15cb96b74606b18721dc11637cf494703a617 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 23 Oct 2024 01:20:02 +0200
Subject: [PATCH 0703/1530] dt-bindings: pinctrl: airoha: Add EN7581 pinctrl

Introduce device-tree binding documentation for Airoha EN7581 pinctrl
controller.

Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/20241023-en7581-pinctrl-v9-2-afb0cbcab0ec@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../pinctrl/airoha,en7581-pinctrl.yaml        | 400 ++++++++++++++++++
 1 file changed, 400 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/airoha,en7581-pinctrl.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/airoha,en7581-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/airoha,en7581-pinctrl.yaml
new file mode 100644
index 0000000000000..b2601d698dcd4
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/airoha,en7581-pinctrl.yaml
@@ -0,0 +1,400 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/airoha,en7581-pinctrl.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Airoha EN7581 Pin Controller
+
+maintainers:
+  - Lorenzo Bianconi <lorenzo@kernel.org>
+
+description:
+  The Airoha's EN7581 Pin controller is used to control SoC pins.
+
+properties:
+  compatible:
+    const: airoha,en7581-pinctrl
+
+  interrupts:
+    maxItems: 1
+
+  gpio-controller: true
+
+  '#gpio-cells':
+    const: 2
+
+  interrupt-controller: true
+
+  '#interrupt-cells':
+    const: 2
+
+allOf:
+  - $ref: pinctrl.yaml#
+
+required:
+  - compatible
+  - interrupts
+  - gpio-controller
+  - "#gpio-cells"
+  - interrupt-controller
+  - "#interrupt-cells"
+
+patternProperties:
+  '-pins$':
+    type: object
+
+    patternProperties:
+      '^mux(-|$)':
+        type: object
+
+        description:
+          pinmux configuration nodes.
+
+        $ref: /schemas/pinctrl/pinmux-node.yaml
+
+        properties:
+          function:
+            description:
+              A string containing the name of the function to mux to the group.
+            enum: [pon, tod_1pps, sipo, mdio, uart, i2c, jtag, pcm, spi,
+                   pcm_spi, i2s, emmc, pnand, pcie_reset, pwm, phy1_led0,
+                   phy2_led0, phy3_led0, phy4_led0, phy1_led1, phy2_led1,
+                   phy3_led1, phy4_led1]
+
+          groups:
+            description:
+              An array of strings. Each string contains the name of a group.
+
+        required:
+          - function
+          - groups
+
+        allOf:
+          - if:
+              properties:
+                function:
+                  const: pon
+            then:
+              properties:
+                groups:
+                  enum: [pon]
+          - if:
+              properties:
+                function:
+                  const: tod_1pps
+            then:
+              properties:
+                groups:
+                  enum: [pon_tod_1pps, gsw_tod_1pps]
+          - if:
+              properties:
+                function:
+                  const: sipo
+            then:
+              properties:
+                groups:
+                  enum: [sipo, sipo_rclk]
+          - if:
+              properties:
+                function:
+                  const: mdio
+            then:
+              properties:
+                groups:
+                  enum: [mdio]
+          - if:
+              properties:
+                function:
+                  const: uart
+            then:
+              properties:
+                groups:
+                  items:
+                    enum: [uart2, uart2_cts_rts, hsuart, hsuart_cts_rts,
+                           uart4, uart5]
+                  maxItems: 2
+          - if:
+              properties:
+                function:
+                  const: i2c
+            then:
+              properties:
+                groups:
+                  enum: [i2c1]
+          - if:
+              properties:
+                function:
+                  const: jtag
+            then:
+              properties:
+                groups:
+                  enum: [jtag_udi, jtag_dfd]
+          - if:
+              properties:
+                function:
+                  const: pcm
+            then:
+              properties:
+                groups:
+                  enum: [pcm1, pcm2]
+          - if:
+              properties:
+                function:
+                  const: spi
+            then:
+              properties:
+                groups:
+                  items:
+                    enum: [spi_quad, spi_cs1]
+                  maxItems: 2
+          - if:
+              properties:
+                function:
+                  const: pcm_spi
+            then:
+              properties:
+                groups:
+                  items:
+                    enum: [pcm_spi, pcm_spi_int, pcm_spi_rst, pcm_spi_cs1,
+                           pcm_spi_cs2_p156, pcm_spi_cs2_p128, pcm_spi_cs3,
+                           pcm_spi_cs4]
+                  maxItems: 7
+          - if:
+              properties:
+                function:
+                  const: i2c
+            then:
+              properties:
+                groups:
+                  enum: [i2s]
+          - if:
+              properties:
+                function:
+                  const: emmc
+            then:
+              properties:
+                groups:
+                  enum: [emmc]
+          - if:
+              properties:
+                function:
+                  const: pnand
+            then:
+              properties:
+                groups:
+                  enum: [pnand]
+          - if:
+              properties:
+                function:
+                  const: pcie_reset
+            then:
+              properties:
+                groups:
+                  enum: [pcie_reset0, pcie_reset1, pcie_reset2]
+          - if:
+              properties:
+                function:
+                  const: pwm
+            then:
+              properties:
+                groups:
+                  enum: [gpio0, gpio1, gpio2, gpio3, gpio4, gpio5, gpio6,
+                         gpio7, gpio8, gpio9, gpio10, gpio11, gpio12, gpio13,
+                         gpio14, gpio15, gpio16, gpio17, gpio18, gpio19,
+                         gpio20, gpio21, gpio22, gpio23, gpio24, gpio25,
+                         gpio26, gpio27, gpio28, gpio29, gpio30, gpio31,
+                         gpio36, gpio37, gpio38, gpio39, gpio40, gpio41,
+                         gpio42, gpio43, gpio44, gpio45, gpio46, gpio47]
+          - if:
+              properties:
+                function:
+                  const: phy1_led0
+            then:
+              properties:
+                groups:
+                  enum: [gpio33, gpio34, gpio35, gpio42]
+          - if:
+              properties:
+                function:
+                  const: phy2_led0
+            then:
+              properties:
+                groups:
+                  enum: [gpio33, gpio34, gpio35, gpio42]
+          - if:
+              properties:
+                function:
+                  const: phy3_led0
+            then:
+              properties:
+                groups:
+                  enum: [gpio33, gpio34, gpio35, gpio42]
+          - if:
+              properties:
+                function:
+                  const: phy4_led0
+            then:
+              properties:
+                groups:
+                  enum: [gpio33, gpio34, gpio35, gpio42]
+          - if:
+              properties:
+                function:
+                  const: phy1_led1
+            then:
+              properties:
+                groups:
+                  enum: [gpio43, gpio44, gpio45, gpio46]
+          - if:
+              properties:
+                function:
+                  const: phy2_led1
+            then:
+              properties:
+                groups:
+                  enum: [gpio43, gpio44, gpio45, gpio46]
+          - if:
+              properties:
+                function:
+                  const: phy3_led1
+            then:
+              properties:
+                groups:
+                  enum: [gpio43, gpio44, gpio45, gpio46]
+          - if:
+              properties:
+                function:
+                  const: phy4_led1
+            then:
+              properties:
+                groups:
+                  enum: [gpio43, gpio44, gpio45, gpio46]
+
+        additionalProperties: false
+
+      '^conf(-|$)':
+        type: object
+
+        description:
+          pinconf configuration nodes.
+
+        $ref: /schemas/pinctrl/pincfg-node.yaml
+
+        properties:
+          pins:
+            description:
+              An array of strings. Each string contains the name of a pin.
+            items:
+              enum: [uart1_txd, uart1_rxd, i2c_scl, i2c_sda, spi_cs0, spi_clk,
+                     spi_mosi, spi_miso, gpio0, gpio1, gpio2, gpio3, gpio4,
+                     gpio5, gpio6, gpio7, gpio8, gpio9, gpio10, gpio11, gpio12,
+                     gpio13, gpio14, gpio15, gpio16, gpio17, gpio18, gpio19,
+                     gpio20, gpio21, gpio22, gpio23, gpio24, gpio25, gpio26,
+                     gpio27, gpio28, gpio29, gpio30, gpio31, gpio32, gpio33,
+                     gpio34, gpio35, gpio36, gpio37, gpio38, gpio39, gpio40,
+                     gpio41, gpio42, gpio43, gpio44, gpio45, gpio46,
+                     pcie_reset0, pcie_reset1, pcie_reset2]
+            minItems: 1
+            maxItems: 58
+
+          bias-disable: true
+
+          bias-pull-up: true
+
+          bias-pull-down: true
+
+          input-enable: true
+
+          output-enable: true
+
+          output-low: true
+
+          output-high: true
+
+          drive-open-drain: true
+
+          drive-strength:
+            description:
+              Selects the drive strength for MIO pins, in mA.
+            enum: [2, 4, 6, 8]
+
+        required:
+          - pins
+
+        additionalProperties: false
+
+    additionalProperties: false
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    pinctrl {
+      compatible = "airoha,en7581-pinctrl";
+
+      interrupt-parent = <&gic>;
+      interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
+
+      gpio-controller;
+      #gpio-cells = <2>;
+
+      interrupt-controller;
+      #interrupt-cells = <2>;
+
+      pcie1-rst-pins {
+        conf {
+          pins = "pcie_reset1";
+          drive-open-drain = <1>;
+        };
+      };
+
+      pwm-pins {
+        mux {
+          function = "pwm";
+          groups = "gpio18";
+        };
+      };
+
+      spi-pins {
+        mux {
+          function = "spi";
+          groups = "spi_quad", "spi_cs1";
+        };
+      };
+
+      uart2-pins {
+        mux {
+          function = "uart";
+          groups = "uart2", "uart2_cts_rts";
+        };
+      };
+
+      uar5-pins {
+        mux {
+          function = "uart";
+          groups = "uart5";
+        };
+      };
+
+      mmc-pins {
+        mux {
+          function = "emmc";
+          groups = "emmc";
+        };
+      };
+
+      mdio-pins {
+        mux {
+          function = "mdio";
+          groups = "mdio";
+        };
+
+        conf {
+          pins = "gpio2";
+          output-enable;
+        };
+      };
+    };

From a24663432fe1dfe1ab4db020cb94942258c1ed24 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 23 Oct 2024 01:20:03 +0200
Subject: [PATCH 0704/1530] dt-bindings: pwm: airoha: Add EN7581 pwm
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce device-tree binding documentation for Airoha EN7581 pwm
controller.

Co-developed-by: Christian Marangi <ansuelsmth@gmail.com>
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Acked-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Link: https://lore.kernel.org/20241023-en7581-pinctrl-v9-3-afb0cbcab0ec@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pwm/airoha,en7581-pwm.yaml       | 34 +++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pwm/airoha,en7581-pwm.yaml

diff --git a/Documentation/devicetree/bindings/pwm/airoha,en7581-pwm.yaml b/Documentation/devicetree/bindings/pwm/airoha,en7581-pwm.yaml
new file mode 100644
index 0000000000000..f36387572a978
--- /dev/null
+++ b/Documentation/devicetree/bindings/pwm/airoha,en7581-pwm.yaml
@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pwm/airoha,en7581-pwm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Airoha EN7581 PWM Controller
+
+maintainers:
+  - Lorenzo Bianconi <lorenzo@kernel.org>
+
+allOf:
+  - $ref: pwm.yaml#
+
+properties:
+  compatible:
+    const: airoha,en7581-pwm
+
+  "#pwm-cells":
+    const: 3
+
+required:
+  - compatible
+  - "#pwm-cells"
+
+additionalProperties: false
+
+examples:
+  - |
+    pwm {
+      compatible = "airoha,en7581-pwm";
+
+      #pwm-cells = <3>;
+    };

From 50dedb1eb1e6755ccab55f6140916c2d192be765 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Wed, 23 Oct 2024 01:20:04 +0200
Subject: [PATCH 0705/1530] dt-bindings: mfd: Add support for Airoha EN7581
 GPIO System Controller

Add support for Airoha EN7581 GPIO System Controller which provide a
register map for controlling the GPIO, pinctrl and PWM of the SoC via
dedicated pinctrl and pwm child nodes.

Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/20241023-en7581-pinctrl-v9-4-afb0cbcab0ec@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../mfd/airoha,en7581-gpio-sysctl.yaml        | 90 +++++++++++++++++++
 1 file changed, 90 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/mfd/airoha,en7581-gpio-sysctl.yaml

diff --git a/Documentation/devicetree/bindings/mfd/airoha,en7581-gpio-sysctl.yaml b/Documentation/devicetree/bindings/mfd/airoha,en7581-gpio-sysctl.yaml
new file mode 100644
index 0000000000000..4a81ed82ef34d
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/airoha,en7581-gpio-sysctl.yaml
@@ -0,0 +1,90 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/mfd/airoha,en7581-gpio-sysctl.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Airoha EN7581 GPIO System Controller
+
+maintainers:
+  - Christian Marangi <ansuelsmth@gmail.com>
+  - Lorenzo Bianconi <lorenzo@kernel.org>
+
+description:
+  Airoha EN7581 SoC GPIO system controller which provided a register map
+  for controlling the GPIO, pins and PWM of the SoC.
+
+properties:
+  compatible:
+    items:
+      - const: airoha,en7581-gpio-sysctl
+      - const: syscon
+      - const: simple-mfd
+
+  reg:
+    maxItems: 1
+
+  pinctrl:
+    type: object
+    $ref: /schemas/pinctrl/airoha,en7581-pinctrl.yaml
+    description:
+      Child node definition for EN7581 Pin controller
+
+  pwm:
+    type: object
+    $ref: /schemas/pwm/airoha,en7581-pwm.yaml
+    description:
+      Child node definition for EN7581 PWM controller
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    system-controller@1fbf0200 {
+      compatible = "airoha,en7581-gpio-sysctl", "syscon", "simple-mfd";
+      reg = <0x1fbf0200 0xc0>;
+
+      pinctrl {
+        compatible = "airoha,en7581-pinctrl";
+
+        interrupt-parent = <&gic>;
+        interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
+
+        gpio-controller;
+        #gpio-cells = <2>;
+
+        interrupt-controller;
+        #interrupt-cells = <2>;
+
+        mmc-pins {
+          mux {
+            function = "emmc";
+            groups = "emmc";
+          };
+        };
+
+        mdio-pins {
+          mux {
+            function = "mdio";
+            groups = "mdio";
+          };
+
+          conf {
+            pins = "gpio2";
+            output-enable;
+          };
+        };
+      };
+
+      pwm {
+        compatible = "airoha,en7581-pwm";
+
+        #pwm-cells = <3>;
+      };
+    };

From 1c8ace2d0725c1c8d5012f8a56c5fb31805aad27 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 23 Oct 2024 01:20:05 +0200
Subject: [PATCH 0706/1530] pinctrl: airoha: Add support for EN7581 SoC

Introduce pinctrl driver for EN7581 SoC. Current EN7581 pinctrl driver
supports the following functionalities:
- pin multiplexing
- pin pull-up, pull-down, open-drain, current strength,
  {input,output}_enable, output_{low,high}
- gpio controller
- irq controller

Tested-by: Benjamin Larsson <benjamin.larsson@genexis.eu>
Co-developed-by: Benjamin Larsson <benjamin.larsson@genexis.eu>
Signed-off-by: Benjamin Larsson <benjamin.larsson@genexis.eu>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/20241023-en7581-pinctrl-v9-5-afb0cbcab0ec@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 MAINTAINERS                               |    7 +
 drivers/pinctrl/mediatek/Kconfig          |   17 +-
 drivers/pinctrl/mediatek/Makefile         |    1 +
 drivers/pinctrl/mediatek/pinctrl-airoha.c | 2970 +++++++++++++++++++++
 4 files changed, 2994 insertions(+), 1 deletion(-)
 create mode 100644 drivers/pinctrl/mediatek/pinctrl-airoha.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 67634f0ea30e1..38ccb620cc249 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18232,6 +18232,13 @@ F:	drivers/pinctrl/
 F:	include/dt-bindings/pinctrl/
 F:	include/linux/pinctrl/
 
+PIN CONTROLLER - AIROHA
+M:	Lorenzo Bianconi <lorenzo@kernel.org>
+L:	linux-mediatek@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	Documentation/devicetree/bindings/pinctrl/airoha,en7581-pinctrl.yaml
+F:	drivers/pinctrl/mediatek/pinctrl-airoha.c
+
 PIN CONTROLLER - AMD
 M:	Basavaraj Natikar <Basavaraj.Natikar@amd.com>
 M:	Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
diff --git a/drivers/pinctrl/mediatek/Kconfig b/drivers/pinctrl/mediatek/Kconfig
index 7af287252834a..a417a031659c6 100644
--- a/drivers/pinctrl/mediatek/Kconfig
+++ b/drivers/pinctrl/mediatek/Kconfig
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 menu "MediaTek pinctrl drivers"
-	depends on ARCH_MEDIATEK || RALINK || COMPILE_TEST
+	depends on ARCH_MEDIATEK || ARCH_AIROHA || RALINK || COMPILE_TEST
 
 config EINT_MTK
 	tristate "MediaTek External Interrupt Support"
@@ -126,6 +126,21 @@ config PINCTRL_MT8127
 	select PINCTRL_MTK
 
 # For ARMv8 SoCs
+config PINCTRL_AIROHA
+	tristate "Airoha EN7581 pin control"
+	depends on OF
+	depends on ARM64 || COMPILE_TEST
+	select PINMUX
+	select GENERIC_PINCONF
+	select GENERIC_PINCTRL_GROUPS
+	select GENERIC_PINMUX_FUNCTIONS
+	select GPIOLIB
+	select GPIOLIB_IRQCHIP
+	select REGMAP_MMIO
+	help
+	  Say yes here to support pin controller and gpio driver
+	  on Airoha EN7581 SoC.
+
 config PINCTRL_MT2712
 	bool "MediaTek MT2712 pin control"
 	depends on OF
diff --git a/drivers/pinctrl/mediatek/Makefile b/drivers/pinctrl/mediatek/Makefile
index 680f7e8526e00..1405d434218ea 100644
--- a/drivers/pinctrl/mediatek/Makefile
+++ b/drivers/pinctrl/mediatek/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_PINCTRL_MTK_MOORE)		+= pinctrl-moore.o
 obj-$(CONFIG_PINCTRL_MTK_PARIS)		+= pinctrl-paris.o
 
 # SoC Drivers
+obj-$(CONFIG_PINCTRL_AIROHA)		+= pinctrl-airoha.o
 obj-$(CONFIG_PINCTRL_MT7620)		+= pinctrl-mt7620.o
 obj-$(CONFIG_PINCTRL_MT7621)		+= pinctrl-mt7621.o
 obj-$(CONFIG_PINCTRL_MT76X8)		+= pinctrl-mt76x8.o
diff --git a/drivers/pinctrl/mediatek/pinctrl-airoha.c b/drivers/pinctrl/mediatek/pinctrl-airoha.c
new file mode 100644
index 0000000000000..7692e6d9b8710
--- /dev/null
+++ b/drivers/pinctrl/mediatek/pinctrl-airoha.c
@@ -0,0 +1,2970 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ * Author: Benjamin Larsson <benjamin.larsson@genexis.eu>
+ * Author: Markus Gothe <markus.gothe@genexis.eu>
+ */
+
+#include <dt-bindings/pinctrl/mt65xx.h>
+#include <linux/bits.h>
+#include <linux/cleanup.h>
+#include <linux/gpio/driver.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinmux.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include "../core.h"
+#include "../pinconf.h"
+#include "../pinmux.h"
+
+#define PINCTRL_PIN_GROUP(id)						\
+	PINCTRL_PINGROUP(#id, id##_pins, ARRAY_SIZE(id##_pins))
+
+#define PINCTRL_FUNC_DESC(id)						\
+	{								\
+		.desc = {						\
+			.func = {					\
+				.name = #id,				\
+				.groups = id##_groups,			\
+				.ngroups = ARRAY_SIZE(id##_groups),	\
+			}						\
+		},							\
+		.groups = id##_func_group,				\
+		.group_size = ARRAY_SIZE(id##_func_group),		\
+	}
+
+#define PINCTRL_CONF_DESC(p, offset, mask)				\
+	{								\
+		.pin = p,						\
+		.reg = { offset, mask },				\
+	}
+
+/* MUX */
+#define REG_GPIO_2ND_I2C_MODE			0x0214
+#define GPIO_MDC_IO_MASTER_MODE_MODE		BIT(14)
+#define GPIO_I2C_MASTER_MODE_MODE		BIT(13)
+#define GPIO_I2S_MODE_MASK			BIT(12)
+#define GPIO_I2C_SLAVE_MODE_MODE		BIT(11)
+#define GPIO_LAN3_LED1_MODE_MASK		BIT(10)
+#define GPIO_LAN3_LED0_MODE_MASK		BIT(9)
+#define GPIO_LAN2_LED1_MODE_MASK		BIT(8)
+#define GPIO_LAN2_LED0_MODE_MASK		BIT(7)
+#define GPIO_LAN1_LED1_MODE_MASK		BIT(6)
+#define GPIO_LAN1_LED0_MODE_MASK		BIT(5)
+#define GPIO_LAN0_LED1_MODE_MASK		BIT(4)
+#define GPIO_LAN0_LED0_MODE_MASK		BIT(3)
+#define PON_TOD_1PPS_MODE_MASK			BIT(2)
+#define GSW_TOD_1PPS_MODE_MASK			BIT(1)
+#define GPIO_2ND_I2C_MODE_MASK			BIT(0)
+
+#define REG_GPIO_SPI_CS1_MODE			0x0218
+#define GPIO_PCM_SPI_CS4_MODE_MASK		BIT(21)
+#define GPIO_PCM_SPI_CS3_MODE_MASK		BIT(20)
+#define GPIO_PCM_SPI_CS2_MODE_P156_MASK		BIT(19)
+#define GPIO_PCM_SPI_CS2_MODE_P128_MASK		BIT(18)
+#define GPIO_PCM_SPI_CS1_MODE_MASK		BIT(17)
+#define GPIO_PCM_SPI_MODE_MASK			BIT(16)
+#define GPIO_PCM2_MODE_MASK			BIT(13)
+#define GPIO_PCM1_MODE_MASK			BIT(12)
+#define GPIO_PCM_INT_MODE_MASK			BIT(9)
+#define GPIO_PCM_RESET_MODE_MASK		BIT(8)
+#define GPIO_SPI_QUAD_MODE_MASK			BIT(4)
+#define GPIO_SPI_CS4_MODE_MASK			BIT(3)
+#define GPIO_SPI_CS3_MODE_MASK			BIT(2)
+#define GPIO_SPI_CS2_MODE_MASK			BIT(1)
+#define GPIO_SPI_CS1_MODE_MASK			BIT(0)
+
+#define REG_GPIO_PON_MODE			0x021c
+#define GPIO_PARALLEL_NAND_MODE_MASK		BIT(14)
+#define GPIO_SGMII_MDIO_MODE_MASK		BIT(13)
+#define GPIO_PCIE_RESET2_MASK			BIT(12)
+#define SIPO_RCLK_MODE_MASK			BIT(11)
+#define GPIO_PCIE_RESET1_MASK			BIT(10)
+#define GPIO_PCIE_RESET0_MASK			BIT(9)
+#define GPIO_UART5_MODE_MASK			BIT(8)
+#define GPIO_UART4_MODE_MASK			BIT(7)
+#define GPIO_HSUART_CTS_RTS_MODE_MASK		BIT(6)
+#define GPIO_HSUART_MODE_MASK			BIT(5)
+#define GPIO_UART2_CTS_RTS_MODE_MASK		BIT(4)
+#define GPIO_UART2_MODE_MASK			BIT(3)
+#define GPIO_SIPO_MODE_MASK			BIT(2)
+#define GPIO_EMMC_MODE_MASK			BIT(1)
+#define GPIO_PON_MODE_MASK			BIT(0)
+
+#define REG_NPU_UART_EN				0x0224
+#define JTAG_UDI_EN_MASK			BIT(4)
+#define JTAG_DFD_EN_MASK			BIT(3)
+
+/* LED MAP */
+#define REG_LAN_LED0_MAPPING			0x027c
+#define REG_LAN_LED1_MAPPING			0x0280
+
+#define LAN4_LED_MAPPING_MASK			GENMASK(18, 16)
+#define LAN4_PHY4_LED_MAP			BIT(18)
+#define LAN4_PHY2_LED_MAP			BIT(17)
+#define LAN4_PHY1_LED_MAP			BIT(16)
+#define LAN4_PHY0_LED_MAP			0
+#define LAN4_PHY3_LED_MAP			GENMASK(17, 16)
+
+#define LAN3_LED_MAPPING_MASK			GENMASK(14, 12)
+#define LAN3_PHY4_LED_MAP			BIT(14)
+#define LAN3_PHY2_LED_MAP			BIT(13)
+#define LAN3_PHY1_LED_MAP			BIT(12)
+#define LAN3_PHY0_LED_MAP			0
+#define LAN3_PHY3_LED_MAP			GENMASK(13, 12)
+
+#define LAN2_LED_MAPPING_MASK			GENMASK(10, 8)
+#define LAN2_PHY4_LED_MAP			BIT(12)
+#define LAN2_PHY2_LED_MAP			BIT(11)
+#define LAN2_PHY1_LED_MAP			BIT(10)
+#define LAN2_PHY0_LED_MAP			0
+#define LAN2_PHY3_LED_MAP			GENMASK(11, 10)
+
+#define LAN1_LED_MAPPING_MASK			GENMASK(6, 4)
+#define LAN1_PHY4_LED_MAP			BIT(6)
+#define LAN1_PHY2_LED_MAP			BIT(5)
+#define LAN1_PHY1_LED_MAP			BIT(4)
+#define LAN1_PHY0_LED_MAP			0
+#define LAN1_PHY3_LED_MAP			GENMASK(5, 4)
+
+#define LAN0_LED_MAPPING_MASK			GENMASK(2, 0)
+#define LAN0_PHY4_LED_MAP			BIT(3)
+#define LAN0_PHY2_LED_MAP			BIT(2)
+#define LAN0_PHY1_LED_MAP			BIT(1)
+#define LAN0_PHY0_LED_MAP			0
+#define LAN0_PHY3_LED_MAP			GENMASK(2, 1)
+
+/* CONF */
+#define REG_I2C_SDA_E2				0x001c
+#define SPI_MISO_E2_MASK			BIT(14)
+#define SPI_MOSI_E2_MASK			BIT(13)
+#define SPI_CLK_E2_MASK				BIT(12)
+#define SPI_CS0_E2_MASK				BIT(11)
+#define PCIE2_RESET_E2_MASK			BIT(10)
+#define PCIE1_RESET_E2_MASK			BIT(9)
+#define PCIE0_RESET_E2_MASK			BIT(8)
+#define UART1_RXD_E2_MASK			BIT(3)
+#define UART1_TXD_E2_MASK			BIT(2)
+#define I2C_SCL_E2_MASK				BIT(1)
+#define I2C_SDA_E2_MASK				BIT(0)
+
+#define REG_I2C_SDA_E4				0x0020
+#define SPI_MISO_E4_MASK			BIT(14)
+#define SPI_MOSI_E4_MASK			BIT(13)
+#define SPI_CLK_E4_MASK				BIT(12)
+#define SPI_CS0_E4_MASK				BIT(11)
+#define PCIE2_RESET_E4_MASK			BIT(10)
+#define PCIE1_RESET_E4_MASK			BIT(9)
+#define PCIE0_RESET_E4_MASK			BIT(8)
+#define UART1_RXD_E4_MASK			BIT(3)
+#define UART1_TXD_E4_MASK			BIT(2)
+#define I2C_SCL_E4_MASK				BIT(1)
+#define I2C_SDA_E4_MASK				BIT(0)
+
+#define REG_GPIO_L_E2				0x0024
+#define REG_GPIO_L_E4				0x0028
+#define REG_GPIO_H_E2				0x002c
+#define REG_GPIO_H_E4				0x0030
+
+#define REG_I2C_SDA_PU				0x0044
+#define SPI_MISO_PU_MASK			BIT(14)
+#define SPI_MOSI_PU_MASK			BIT(13)
+#define SPI_CLK_PU_MASK				BIT(12)
+#define SPI_CS0_PU_MASK				BIT(11)
+#define PCIE2_RESET_PU_MASK			BIT(10)
+#define PCIE1_RESET_PU_MASK			BIT(9)
+#define PCIE0_RESET_PU_MASK			BIT(8)
+#define UART1_RXD_PU_MASK			BIT(3)
+#define UART1_TXD_PU_MASK			BIT(2)
+#define I2C_SCL_PU_MASK				BIT(1)
+#define I2C_SDA_PU_MASK				BIT(0)
+
+#define REG_I2C_SDA_PD				0x0048
+#define SPI_MISO_PD_MASK			BIT(14)
+#define SPI_MOSI_PD_MASK			BIT(13)
+#define SPI_CLK_PD_MASK				BIT(12)
+#define SPI_CS0_PD_MASK				BIT(11)
+#define PCIE2_RESET_PD_MASK			BIT(10)
+#define PCIE1_RESET_PD_MASK			BIT(9)
+#define PCIE0_RESET_PD_MASK			BIT(8)
+#define UART1_RXD_PD_MASK			BIT(3)
+#define UART1_TXD_PD_MASK			BIT(2)
+#define I2C_SCL_PD_MASK				BIT(1)
+#define I2C_SDA_PD_MASK				BIT(0)
+
+#define REG_GPIO_L_PU				0x004c
+#define REG_GPIO_L_PD				0x0050
+#define REG_GPIO_H_PU				0x0054
+#define REG_GPIO_H_PD				0x0058
+
+#define REG_PCIE_RESET_OD			0x018c
+#define PCIE2_RESET_OD_MASK			BIT(2)
+#define PCIE1_RESET_OD_MASK			BIT(1)
+#define PCIE0_RESET_OD_MASK			BIT(0)
+
+/* GPIOs */
+#define REG_GPIO_CTRL				0x0000
+#define REG_GPIO_DATA				0x0004
+#define REG_GPIO_INT				0x0008
+#define REG_GPIO_INT_EDGE			0x000c
+#define REG_GPIO_INT_LEVEL			0x0010
+#define REG_GPIO_OE				0x0014
+#define REG_GPIO_CTRL1				0x0020
+
+/* PWM MODE CONF */
+#define REG_GPIO_FLASH_MODE_CFG			0x0034
+#define GPIO15_FLASH_MODE_CFG			BIT(15)
+#define GPIO14_FLASH_MODE_CFG			BIT(14)
+#define GPIO13_FLASH_MODE_CFG			BIT(13)
+#define GPIO12_FLASH_MODE_CFG			BIT(12)
+#define GPIO11_FLASH_MODE_CFG			BIT(11)
+#define GPIO10_FLASH_MODE_CFG			BIT(10)
+#define GPIO9_FLASH_MODE_CFG			BIT(9)
+#define GPIO8_FLASH_MODE_CFG			BIT(8)
+#define GPIO7_FLASH_MODE_CFG			BIT(7)
+#define GPIO6_FLASH_MODE_CFG			BIT(6)
+#define GPIO5_FLASH_MODE_CFG			BIT(5)
+#define GPIO4_FLASH_MODE_CFG			BIT(4)
+#define GPIO3_FLASH_MODE_CFG			BIT(3)
+#define GPIO2_FLASH_MODE_CFG			BIT(2)
+#define GPIO1_FLASH_MODE_CFG			BIT(1)
+#define GPIO0_FLASH_MODE_CFG			BIT(0)
+
+#define REG_GPIO_CTRL2				0x0060
+#define REG_GPIO_CTRL3				0x0064
+
+/* PWM MODE CONF EXT */
+#define REG_GPIO_FLASH_MODE_CFG_EXT		0x0068
+#define GPIO51_FLASH_MODE_CFG			BIT(31)
+#define GPIO50_FLASH_MODE_CFG			BIT(30)
+#define GPIO49_FLASH_MODE_CFG			BIT(29)
+#define GPIO48_FLASH_MODE_CFG			BIT(28)
+#define GPIO47_FLASH_MODE_CFG			BIT(27)
+#define GPIO46_FLASH_MODE_CFG			BIT(26)
+#define GPIO45_FLASH_MODE_CFG			BIT(25)
+#define GPIO44_FLASH_MODE_CFG			BIT(24)
+#define GPIO43_FLASH_MODE_CFG			BIT(23)
+#define GPIO42_FLASH_MODE_CFG			BIT(22)
+#define GPIO41_FLASH_MODE_CFG			BIT(21)
+#define GPIO40_FLASH_MODE_CFG			BIT(20)
+#define GPIO39_FLASH_MODE_CFG			BIT(19)
+#define GPIO38_FLASH_MODE_CFG			BIT(18)
+#define GPIO37_FLASH_MODE_CFG			BIT(17)
+#define GPIO36_FLASH_MODE_CFG			BIT(16)
+#define GPIO31_FLASH_MODE_CFG			BIT(15)
+#define GPIO30_FLASH_MODE_CFG			BIT(14)
+#define GPIO29_FLASH_MODE_CFG			BIT(13)
+#define GPIO28_FLASH_MODE_CFG			BIT(12)
+#define GPIO27_FLASH_MODE_CFG			BIT(11)
+#define GPIO26_FLASH_MODE_CFG			BIT(10)
+#define GPIO25_FLASH_MODE_CFG			BIT(9)
+#define GPIO24_FLASH_MODE_CFG			BIT(8)
+#define GPIO23_FLASH_MODE_CFG			BIT(7)
+#define GPIO22_FLASH_MODE_CFG			BIT(6)
+#define GPIO21_FLASH_MODE_CFG			BIT(5)
+#define GPIO20_FLASH_MODE_CFG			BIT(4)
+#define GPIO19_FLASH_MODE_CFG			BIT(3)
+#define GPIO18_FLASH_MODE_CFG			BIT(2)
+#define GPIO17_FLASH_MODE_CFG			BIT(1)
+#define GPIO16_FLASH_MODE_CFG			BIT(0)
+
+#define REG_GPIO_DATA1				0x0070
+#define REG_GPIO_OE1				0x0078
+#define REG_GPIO_INT1				0x007c
+#define REG_GPIO_INT_EDGE1			0x0080
+#define REG_GPIO_INT_EDGE2			0x0084
+#define REG_GPIO_INT_EDGE3			0x0088
+#define REG_GPIO_INT_LEVEL1			0x008c
+#define REG_GPIO_INT_LEVEL2			0x0090
+#define REG_GPIO_INT_LEVEL3			0x0094
+
+#define AIROHA_NUM_PINS				64
+#define AIROHA_PIN_BANK_SIZE			(AIROHA_NUM_PINS / 2)
+#define AIROHA_REG_GPIOCTRL_NUM_PIN		(AIROHA_NUM_PINS / 4)
+
+static const u32 gpio_data_regs[] = {
+	REG_GPIO_DATA,
+	REG_GPIO_DATA1
+};
+
+static const u32 gpio_out_regs[] = {
+	REG_GPIO_OE,
+	REG_GPIO_OE1
+};
+
+static const u32 gpio_dir_regs[] = {
+	REG_GPIO_CTRL,
+	REG_GPIO_CTRL1,
+	REG_GPIO_CTRL2,
+	REG_GPIO_CTRL3
+};
+
+static const u32 irq_status_regs[] = {
+	REG_GPIO_INT,
+	REG_GPIO_INT1
+};
+
+static const u32 irq_level_regs[] = {
+	REG_GPIO_INT_LEVEL,
+	REG_GPIO_INT_LEVEL1,
+	REG_GPIO_INT_LEVEL2,
+	REG_GPIO_INT_LEVEL3
+};
+
+static const u32 irq_edge_regs[] = {
+	REG_GPIO_INT_EDGE,
+	REG_GPIO_INT_EDGE1,
+	REG_GPIO_INT_EDGE2,
+	REG_GPIO_INT_EDGE3
+};
+
+struct airoha_pinctrl_reg {
+	u32 offset;
+	u32 mask;
+};
+
+enum airoha_pinctrl_mux_func {
+	AIROHA_FUNC_MUX,
+	AIROHA_FUNC_PWM_MUX,
+	AIROHA_FUNC_PWM_EXT_MUX,
+};
+
+struct airoha_pinctrl_func_group {
+	const char *name;
+	struct {
+		enum airoha_pinctrl_mux_func mux;
+		u32 offset;
+		u32 mask;
+		u32 val;
+	} regmap[2];
+	int regmap_size;
+};
+
+struct airoha_pinctrl_func {
+	const struct function_desc desc;
+	const struct airoha_pinctrl_func_group *groups;
+	u8 group_size;
+};
+
+struct airoha_pinctrl_conf {
+	u32 pin;
+	struct airoha_pinctrl_reg reg;
+};
+
+struct airoha_pinctrl_gpiochip {
+	struct gpio_chip chip;
+
+	/* gpio */
+	const u32 *data;
+	const u32 *dir;
+	const u32 *out;
+	/* irq */
+	const u32 *status;
+	const u32 *level;
+	const u32 *edge;
+
+	u32 irq_type[AIROHA_NUM_PINS];
+};
+
+struct airoha_pinctrl {
+	struct pinctrl_dev *ctrl;
+
+	struct regmap *chip_scu;
+	struct regmap *regmap;
+
+	struct airoha_pinctrl_gpiochip gpiochip;
+};
+
+static struct pinctrl_pin_desc airoha_pinctrl_pins[] = {
+	PINCTRL_PIN(0, "uart1_txd"),
+	PINCTRL_PIN(1, "uart1_rxd"),
+	PINCTRL_PIN(2, "i2c_scl"),
+	PINCTRL_PIN(3, "i2c_sda"),
+	PINCTRL_PIN(4, "spi_cs0"),
+	PINCTRL_PIN(5, "spi_clk"),
+	PINCTRL_PIN(6, "spi_mosi"),
+	PINCTRL_PIN(7, "spi_miso"),
+	PINCTRL_PIN(13, "gpio0"),
+	PINCTRL_PIN(14, "gpio1"),
+	PINCTRL_PIN(15, "gpio2"),
+	PINCTRL_PIN(16, "gpio3"),
+	PINCTRL_PIN(17, "gpio4"),
+	PINCTRL_PIN(18, "gpio5"),
+	PINCTRL_PIN(19, "gpio6"),
+	PINCTRL_PIN(20, "gpio7"),
+	PINCTRL_PIN(21, "gpio8"),
+	PINCTRL_PIN(22, "gpio9"),
+	PINCTRL_PIN(23, "gpio10"),
+	PINCTRL_PIN(24, "gpio11"),
+	PINCTRL_PIN(25, "gpio12"),
+	PINCTRL_PIN(26, "gpio13"),
+	PINCTRL_PIN(27, "gpio14"),
+	PINCTRL_PIN(28, "gpio15"),
+	PINCTRL_PIN(29, "gpio16"),
+	PINCTRL_PIN(30, "gpio17"),
+	PINCTRL_PIN(31, "gpio18"),
+	PINCTRL_PIN(32, "gpio19"),
+	PINCTRL_PIN(33, "gpio20"),
+	PINCTRL_PIN(34, "gpio21"),
+	PINCTRL_PIN(35, "gpio22"),
+	PINCTRL_PIN(36, "gpio23"),
+	PINCTRL_PIN(37, "gpio24"),
+	PINCTRL_PIN(38, "gpio25"),
+	PINCTRL_PIN(39, "gpio26"),
+	PINCTRL_PIN(40, "gpio27"),
+	PINCTRL_PIN(41, "gpio28"),
+	PINCTRL_PIN(42, "gpio29"),
+	PINCTRL_PIN(43, "gpio30"),
+	PINCTRL_PIN(44, "gpio31"),
+	PINCTRL_PIN(45, "gpio32"),
+	PINCTRL_PIN(46, "gpio33"),
+	PINCTRL_PIN(47, "gpio34"),
+	PINCTRL_PIN(48, "gpio35"),
+	PINCTRL_PIN(49, "gpio36"),
+	PINCTRL_PIN(50, "gpio37"),
+	PINCTRL_PIN(51, "gpio38"),
+	PINCTRL_PIN(52, "gpio39"),
+	PINCTRL_PIN(53, "gpio40"),
+	PINCTRL_PIN(54, "gpio41"),
+	PINCTRL_PIN(55, "gpio42"),
+	PINCTRL_PIN(56, "gpio43"),
+	PINCTRL_PIN(57, "gpio44"),
+	PINCTRL_PIN(58, "gpio45"),
+	PINCTRL_PIN(59, "gpio46"),
+	PINCTRL_PIN(61, "pcie_reset0"),
+	PINCTRL_PIN(62, "pcie_reset1"),
+	PINCTRL_PIN(63, "pcie_reset2"),
+};
+
+static const int pon_pins[] = { 49, 50, 51, 52, 53, 54 };
+static const int pon_tod_1pps_pins[] = { 46 };
+static const int gsw_tod_1pps_pins[] = { 46 };
+static const int sipo_pins[] = { 16, 17 };
+static const int sipo_rclk_pins[] = { 16, 17, 43 };
+static const int mdio_pins[] = { 14, 15 };
+static const int uart2_pins[] = { 48, 55 };
+static const int uart2_cts_rts_pins[] = { 46, 47 };
+static const int hsuart_pins[] = { 28, 29 };
+static const int hsuart_cts_rts_pins[] = { 26, 27 };
+static const int uart4_pins[] = { 38, 39 };
+static const int uart5_pins[] = { 18, 19 };
+static const int i2c0_pins[] = { 2, 3 };
+static const int i2c1_pins[] = { 14, 15 };
+static const int jtag_udi_pins[] = { 16, 17, 18, 19, 20 };
+static const int jtag_dfd_pins[] = { 16, 17, 18, 19, 20 };
+static const int i2s_pins[] = { 26, 27, 28, 29 };
+static const int pcm1_pins[] = { 22, 23, 24, 25 };
+static const int pcm2_pins[] = { 18, 19, 20, 21 };
+static const int spi_quad_pins[] = { 32, 33 };
+static const int spi_pins[] = { 4, 5, 6, 7 };
+static const int spi_cs1_pins[] = { 34 };
+static const int pcm_spi_pins[] = { 18, 19, 20, 21, 22, 23, 24, 25 };
+static const int pcm_spi_int_pins[] = { 14 };
+static const int pcm_spi_rst_pins[] = { 15 };
+static const int pcm_spi_cs1_pins[] = { 43 };
+static const int pcm_spi_cs2_pins[] = { 40 };
+static const int pcm_spi_cs2_p128_pins[] = { 40 };
+static const int pcm_spi_cs2_p156_pins[] = { 40 };
+static const int pcm_spi_cs3_pins[] = { 41 };
+static const int pcm_spi_cs4_pins[] = { 42 };
+static const int emmc_pins[] = { 4, 5, 6, 30, 31, 32, 33, 34, 35, 36, 37 };
+static const int pnand_pins[] = { 4, 5, 6, 7, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42 };
+static const int gpio0_pins[] = { 13 };
+static const int gpio1_pins[] = { 14 };
+static const int gpio2_pins[] = { 15 };
+static const int gpio3_pins[] = { 16 };
+static const int gpio4_pins[] = { 17 };
+static const int gpio5_pins[] = { 18 };
+static const int gpio6_pins[] = { 19 };
+static const int gpio7_pins[] = { 20 };
+static const int gpio8_pins[] = { 21 };
+static const int gpio9_pins[] = { 22 };
+static const int gpio10_pins[] = { 23 };
+static const int gpio11_pins[] = { 24 };
+static const int gpio12_pins[] = { 25 };
+static const int gpio13_pins[] = { 26 };
+static const int gpio14_pins[] = { 27 };
+static const int gpio15_pins[] = { 28 };
+static const int gpio16_pins[] = { 29 };
+static const int gpio17_pins[] = { 30 };
+static const int gpio18_pins[] = { 31 };
+static const int gpio19_pins[] = { 32 };
+static const int gpio20_pins[] = { 33 };
+static const int gpio21_pins[] = { 34 };
+static const int gpio22_pins[] = { 35 };
+static const int gpio23_pins[] = { 36 };
+static const int gpio24_pins[] = { 37 };
+static const int gpio25_pins[] = { 38 };
+static const int gpio26_pins[] = { 39 };
+static const int gpio27_pins[] = { 40 };
+static const int gpio28_pins[] = { 41 };
+static const int gpio29_pins[] = { 42 };
+static const int gpio30_pins[] = { 43 };
+static const int gpio31_pins[] = { 44 };
+static const int gpio33_pins[] = { 46 };
+static const int gpio34_pins[] = { 47 };
+static const int gpio35_pins[] = { 48 };
+static const int gpio36_pins[] = { 49 };
+static const int gpio37_pins[] = { 50 };
+static const int gpio38_pins[] = { 51 };
+static const int gpio39_pins[] = { 52 };
+static const int gpio40_pins[] = { 53 };
+static const int gpio41_pins[] = { 54 };
+static const int gpio42_pins[] = { 55 };
+static const int gpio43_pins[] = { 56 };
+static const int gpio44_pins[] = { 57 };
+static const int gpio45_pins[] = { 58 };
+static const int gpio46_pins[] = { 59 };
+static const int pcie_reset0_pins[] = { 61 };
+static const int pcie_reset1_pins[] = { 62 };
+static const int pcie_reset2_pins[] = { 63 };
+
+static const struct pingroup airoha_pinctrl_groups[] = {
+	PINCTRL_PIN_GROUP(pon),
+	PINCTRL_PIN_GROUP(pon_tod_1pps),
+	PINCTRL_PIN_GROUP(gsw_tod_1pps),
+	PINCTRL_PIN_GROUP(sipo),
+	PINCTRL_PIN_GROUP(sipo_rclk),
+	PINCTRL_PIN_GROUP(mdio),
+	PINCTRL_PIN_GROUP(uart2),
+	PINCTRL_PIN_GROUP(uart2_cts_rts),
+	PINCTRL_PIN_GROUP(hsuart),
+	PINCTRL_PIN_GROUP(hsuart_cts_rts),
+	PINCTRL_PIN_GROUP(uart4),
+	PINCTRL_PIN_GROUP(uart5),
+	PINCTRL_PIN_GROUP(i2c0),
+	PINCTRL_PIN_GROUP(i2c1),
+	PINCTRL_PIN_GROUP(jtag_udi),
+	PINCTRL_PIN_GROUP(jtag_dfd),
+	PINCTRL_PIN_GROUP(i2s),
+	PINCTRL_PIN_GROUP(pcm1),
+	PINCTRL_PIN_GROUP(pcm2),
+	PINCTRL_PIN_GROUP(spi),
+	PINCTRL_PIN_GROUP(spi_quad),
+	PINCTRL_PIN_GROUP(spi_cs1),
+	PINCTRL_PIN_GROUP(pcm_spi),
+	PINCTRL_PIN_GROUP(pcm_spi_int),
+	PINCTRL_PIN_GROUP(pcm_spi_rst),
+	PINCTRL_PIN_GROUP(pcm_spi_cs1),
+	PINCTRL_PIN_GROUP(pcm_spi_cs2_p128),
+	PINCTRL_PIN_GROUP(pcm_spi_cs2_p156),
+	PINCTRL_PIN_GROUP(pcm_spi_cs2),
+	PINCTRL_PIN_GROUP(pcm_spi_cs3),
+	PINCTRL_PIN_GROUP(pcm_spi_cs4),
+	PINCTRL_PIN_GROUP(emmc),
+	PINCTRL_PIN_GROUP(pnand),
+	PINCTRL_PIN_GROUP(gpio0),
+	PINCTRL_PIN_GROUP(gpio1),
+	PINCTRL_PIN_GROUP(gpio2),
+	PINCTRL_PIN_GROUP(gpio3),
+	PINCTRL_PIN_GROUP(gpio4),
+	PINCTRL_PIN_GROUP(gpio5),
+	PINCTRL_PIN_GROUP(gpio6),
+	PINCTRL_PIN_GROUP(gpio7),
+	PINCTRL_PIN_GROUP(gpio8),
+	PINCTRL_PIN_GROUP(gpio9),
+	PINCTRL_PIN_GROUP(gpio10),
+	PINCTRL_PIN_GROUP(gpio11),
+	PINCTRL_PIN_GROUP(gpio12),
+	PINCTRL_PIN_GROUP(gpio13),
+	PINCTRL_PIN_GROUP(gpio14),
+	PINCTRL_PIN_GROUP(gpio15),
+	PINCTRL_PIN_GROUP(gpio16),
+	PINCTRL_PIN_GROUP(gpio17),
+	PINCTRL_PIN_GROUP(gpio18),
+	PINCTRL_PIN_GROUP(gpio19),
+	PINCTRL_PIN_GROUP(gpio20),
+	PINCTRL_PIN_GROUP(gpio21),
+	PINCTRL_PIN_GROUP(gpio22),
+	PINCTRL_PIN_GROUP(gpio23),
+	PINCTRL_PIN_GROUP(gpio24),
+	PINCTRL_PIN_GROUP(gpio25),
+	PINCTRL_PIN_GROUP(gpio26),
+	PINCTRL_PIN_GROUP(gpio27),
+	PINCTRL_PIN_GROUP(gpio28),
+	PINCTRL_PIN_GROUP(gpio29),
+	PINCTRL_PIN_GROUP(gpio30),
+	PINCTRL_PIN_GROUP(gpio31),
+	PINCTRL_PIN_GROUP(gpio33),
+	PINCTRL_PIN_GROUP(gpio34),
+	PINCTRL_PIN_GROUP(gpio35),
+	PINCTRL_PIN_GROUP(gpio36),
+	PINCTRL_PIN_GROUP(gpio37),
+	PINCTRL_PIN_GROUP(gpio38),
+	PINCTRL_PIN_GROUP(gpio39),
+	PINCTRL_PIN_GROUP(gpio40),
+	PINCTRL_PIN_GROUP(gpio41),
+	PINCTRL_PIN_GROUP(gpio42),
+	PINCTRL_PIN_GROUP(gpio43),
+	PINCTRL_PIN_GROUP(gpio44),
+	PINCTRL_PIN_GROUP(gpio45),
+	PINCTRL_PIN_GROUP(gpio46),
+	PINCTRL_PIN_GROUP(pcie_reset0),
+	PINCTRL_PIN_GROUP(pcie_reset1),
+	PINCTRL_PIN_GROUP(pcie_reset2),
+};
+
+static const char *const pon_groups[] = { "pon" };
+static const char *const tod_1pps_groups[] = { "pon_tod_1pps", "gsw_tod_1pps" };
+static const char *const sipo_groups[] = { "sipo", "sipo_rclk" };
+static const char *const mdio_groups[] = { "mdio" };
+static const char *const uart_groups[] = { "uart2", "uart2_cts_rts", "hsuart",
+					   "hsuart_cts_rts", "uart4",
+					   "uart5" };
+static const char *const i2c_groups[] = { "i2c1" };
+static const char *const jtag_groups[] = { "jtag_udi", "jtag_dfd" };
+static const char *const pcm_groups[] = { "pcm1", "pcm2" };
+static const char *const spi_groups[] = { "spi_quad", "spi_cs1" };
+static const char *const pcm_spi_groups[] = { "pcm_spi", "pcm_spi_int",
+					      "pcm_spi_rst", "pcm_spi_cs1",
+					      "pcm_spi_cs2_p156",
+					      "pcm_spi_cs2_p128",
+					      "pcm_spi_cs3", "pcm_spi_cs4" };
+static const char *const i2s_groups[] = { "i2s" };
+static const char *const emmc_groups[] = { "emmc" };
+static const char *const pnand_groups[] = { "pnand" };
+static const char *const pcie_reset_groups[] = { "pcie_reset0", "pcie_reset1",
+						 "pcie_reset2" };
+static const char *const pwm_groups[] = { "gpio0", "gpio1",
+					  "gpio2", "gpio3",
+					  "gpio4", "gpio5",
+					  "gpio6", "gpio7",
+					  "gpio8", "gpio9",
+					  "gpio10", "gpio11",
+					  "gpio12", "gpio13",
+					  "gpio14", "gpio15",
+					  "gpio16", "gpio17",
+					  "gpio18", "gpio19",
+					  "gpio20", "gpio21",
+					  "gpio22", "gpio23",
+					  "gpio24", "gpio25",
+					  "gpio26", "gpio27",
+					  "gpio28", "gpio29",
+					  "gpio30", "gpio31",
+					  "gpio36", "gpio37",
+					  "gpio38", "gpio39",
+					  "gpio40", "gpio41",
+					  "gpio42", "gpio43",
+					  "gpio44", "gpio45",
+					  "gpio46", "gpio47" };
+static const char *const phy1_led0_groups[] = { "gpio33", "gpio34",
+						"gpio35", "gpio42" };
+static const char *const phy2_led0_groups[] = { "gpio33", "gpio34",
+						"gpio35", "gpio42" };
+static const char *const phy3_led0_groups[] = { "gpio33", "gpio34",
+						"gpio35", "gpio42" };
+static const char *const phy4_led0_groups[] = { "gpio33", "gpio34",
+						"gpio35", "gpio42" };
+static const char *const phy1_led1_groups[] = { "gpio43", "gpio44",
+						"gpio45", "gpio46" };
+static const char *const phy2_led1_groups[] = { "gpio43", "gpio44",
+						"gpio45", "gpio46" };
+static const char *const phy3_led1_groups[] = { "gpio43", "gpio44",
+						"gpio45", "gpio46" };
+static const char *const phy4_led1_groups[] = { "gpio43", "gpio44",
+						"gpio45", "gpio46" };
+
+static const struct airoha_pinctrl_func_group pon_func_group[] = {
+	{
+		.name = "pon",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_PON_MODE_MASK,
+			GPIO_PON_MODE_MASK
+		},
+		.regmap_size = 1,
+	},
+};
+
+static const struct airoha_pinctrl_func_group tod_1pps_func_group[] = {
+	{
+		.name = "pon_tod_1pps",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			PON_TOD_1PPS_MODE_MASK,
+			PON_TOD_1PPS_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gsw_tod_1pps",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GSW_TOD_1PPS_MODE_MASK,
+			GSW_TOD_1PPS_MODE_MASK
+		},
+		.regmap_size = 1,
+	},
+};
+
+static const struct airoha_pinctrl_func_group sipo_func_group[] = {
+	{
+		.name = "sipo",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_SIPO_MODE_MASK | SIPO_RCLK_MODE_MASK,
+			GPIO_SIPO_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "sipo_rclk",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_SIPO_MODE_MASK | SIPO_RCLK_MODE_MASK,
+			GPIO_SIPO_MODE_MASK | SIPO_RCLK_MODE_MASK
+		},
+		.regmap_size = 1,
+	},
+};
+
+static const struct airoha_pinctrl_func_group mdio_func_group[] = {
+	{
+		.name = "mdio",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_SGMII_MDIO_MODE_MASK,
+			GPIO_SGMII_MDIO_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_MDC_IO_MASTER_MODE_MODE,
+			GPIO_MDC_IO_MASTER_MODE_MODE
+		},
+		.regmap_size = 2,
+	},
+};
+
+static const struct airoha_pinctrl_func_group uart_func_group[] = {
+	{
+		.name = "uart2",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_UART2_MODE_MASK,
+			GPIO_UART2_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "uart2_cts_rts",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_UART2_MODE_MASK | GPIO_UART2_CTS_RTS_MODE_MASK,
+			GPIO_UART2_MODE_MASK | GPIO_UART2_CTS_RTS_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "hsuart",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_HSUART_MODE_MASK | GPIO_HSUART_CTS_RTS_MODE_MASK,
+			GPIO_HSUART_MODE_MASK
+		},
+		.regmap_size = 1,
+	},
+	{
+		.name = "hsuart_cts_rts",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_HSUART_MODE_MASK | GPIO_HSUART_CTS_RTS_MODE_MASK,
+			GPIO_HSUART_MODE_MASK | GPIO_HSUART_CTS_RTS_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "uart4",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_UART4_MODE_MASK,
+			GPIO_UART4_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "uart5",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_UART5_MODE_MASK,
+			GPIO_UART5_MODE_MASK
+		},
+		.regmap_size = 1,
+	},
+};
+
+static const struct airoha_pinctrl_func_group i2c_func_group[] = {
+	{
+		.name = "i2c1",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_2ND_I2C_MODE_MASK,
+			GPIO_2ND_I2C_MODE_MASK
+		},
+		.regmap_size = 1,
+	},
+};
+
+static const struct airoha_pinctrl_func_group jtag_func_group[] = {
+	{
+		.name = "jtag_udi",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_NPU_UART_EN,
+			JTAG_UDI_EN_MASK,
+			JTAG_UDI_EN_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "jtag_dfd",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_NPU_UART_EN,
+			JTAG_DFD_EN_MASK,
+			JTAG_DFD_EN_MASK
+		},
+		.regmap_size = 1,
+	},
+};
+
+static const struct airoha_pinctrl_func_group pcm_func_group[] = {
+	{
+		.name = "pcm1",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_PCM1_MODE_MASK,
+			GPIO_PCM1_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "pcm2",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_PCM2_MODE_MASK,
+			GPIO_PCM2_MODE_MASK
+		},
+		.regmap_size = 1,
+	},
+};
+
+static const struct airoha_pinctrl_func_group spi_func_group[] = {
+	{
+		.name = "spi_quad",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_SPI_QUAD_MODE_MASK,
+			GPIO_SPI_QUAD_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "spi_cs1",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_SPI_CS1_MODE_MASK,
+			GPIO_SPI_CS1_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "spi_cs2",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_SPI_CS2_MODE_MASK,
+			GPIO_SPI_CS2_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "spi_cs3",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_SPI_CS3_MODE_MASK,
+			GPIO_SPI_CS3_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "spi_cs4",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_SPI_CS4_MODE_MASK,
+			GPIO_SPI_CS4_MODE_MASK
+		},
+		.regmap_size = 1,
+	},
+};
+
+static const struct airoha_pinctrl_func_group pcm_spi_func_group[] = {
+	{
+		.name = "pcm_spi",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_PCM_SPI_MODE_MASK,
+			GPIO_PCM_SPI_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "pcm_spi_int",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_PCM_INT_MODE_MASK,
+			GPIO_PCM_INT_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "pcm_spi_rst",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_PCM_RESET_MODE_MASK,
+			GPIO_PCM_RESET_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "pcm_spi_cs1",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_PCM_SPI_CS1_MODE_MASK,
+			GPIO_PCM_SPI_CS1_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "pcm_spi_cs2_p128",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_PCM_SPI_CS2_MODE_P128_MASK,
+			GPIO_PCM_SPI_CS2_MODE_P128_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "pcm_spi_cs2_p156",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_PCM_SPI_CS2_MODE_P156_MASK,
+			GPIO_PCM_SPI_CS2_MODE_P156_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "pcm_spi_cs3",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_PCM_SPI_CS3_MODE_MASK,
+			GPIO_PCM_SPI_CS3_MODE_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "pcm_spi_cs4",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_SPI_CS1_MODE,
+			GPIO_PCM_SPI_CS4_MODE_MASK,
+			GPIO_PCM_SPI_CS4_MODE_MASK
+		},
+		.regmap_size = 1,
+	},
+};
+
+static const struct airoha_pinctrl_func_group i2s_func_group[] = {
+	{
+		.name = "i2s",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_I2S_MODE_MASK,
+			GPIO_I2S_MODE_MASK
+		},
+		.regmap_size = 1,
+	},
+};
+
+static const struct airoha_pinctrl_func_group emmc_func_group[] = {
+	{
+		.name = "emmc",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_EMMC_MODE_MASK,
+			GPIO_EMMC_MODE_MASK
+		},
+		.regmap_size = 1,
+	},
+};
+
+static const struct airoha_pinctrl_func_group pnand_func_group[] = {
+	{
+		.name = "pnand",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_PARALLEL_NAND_MODE_MASK,
+			GPIO_PARALLEL_NAND_MODE_MASK
+		},
+		.regmap_size = 1,
+	},
+};
+
+static const struct airoha_pinctrl_func_group pcie_reset_func_group[] = {
+	{
+		.name = "pcie_reset0",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_PCIE_RESET0_MASK,
+			GPIO_PCIE_RESET0_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "pcie_reset1",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_PCIE_RESET1_MASK,
+			GPIO_PCIE_RESET1_MASK
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "pcie_reset2",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_PON_MODE,
+			GPIO_PCIE_RESET2_MASK,
+			GPIO_PCIE_RESET2_MASK
+		},
+		.regmap_size = 1,
+	},
+};
+
+/* PWM */
+static const struct airoha_pinctrl_func_group pwm_func_group[] = {
+	{
+		.name = "gpio0",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO0_FLASH_MODE_CFG,
+			GPIO0_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio1",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO1_FLASH_MODE_CFG,
+			GPIO1_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio2",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO2_FLASH_MODE_CFG,
+			GPIO2_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio3",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO3_FLASH_MODE_CFG,
+			GPIO3_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio4",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO4_FLASH_MODE_CFG,
+			GPIO4_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio5",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO5_FLASH_MODE_CFG,
+			GPIO5_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio6",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO6_FLASH_MODE_CFG,
+			GPIO6_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio7",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO7_FLASH_MODE_CFG,
+			GPIO7_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio8",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO8_FLASH_MODE_CFG,
+			GPIO8_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio9",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO9_FLASH_MODE_CFG,
+			GPIO9_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio10",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO10_FLASH_MODE_CFG,
+			GPIO10_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio11",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO11_FLASH_MODE_CFG,
+			GPIO11_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio12",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO12_FLASH_MODE_CFG,
+			GPIO12_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio13",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO13_FLASH_MODE_CFG,
+			GPIO13_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio14",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO14_FLASH_MODE_CFG,
+			GPIO14_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio15",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_MUX,
+			REG_GPIO_FLASH_MODE_CFG,
+			GPIO15_FLASH_MODE_CFG,
+			GPIO15_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio16",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO16_FLASH_MODE_CFG,
+			GPIO16_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio17",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO17_FLASH_MODE_CFG,
+			GPIO17_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio18",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO18_FLASH_MODE_CFG,
+			GPIO18_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio19",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO19_FLASH_MODE_CFG,
+			GPIO19_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio20",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO20_FLASH_MODE_CFG,
+			GPIO20_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio21",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO21_FLASH_MODE_CFG,
+			GPIO21_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio22",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO22_FLASH_MODE_CFG,
+			GPIO22_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio23",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO23_FLASH_MODE_CFG,
+			GPIO23_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio24",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO24_FLASH_MODE_CFG,
+			GPIO24_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio25",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO25_FLASH_MODE_CFG,
+			GPIO25_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio26",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO26_FLASH_MODE_CFG,
+			GPIO26_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio27",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO27_FLASH_MODE_CFG,
+			GPIO27_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio28",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO28_FLASH_MODE_CFG,
+			GPIO28_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio29",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO29_FLASH_MODE_CFG,
+			GPIO29_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio30",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO30_FLASH_MODE_CFG,
+			GPIO30_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio31",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO31_FLASH_MODE_CFG,
+			GPIO31_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio36",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO36_FLASH_MODE_CFG,
+			GPIO36_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio37",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO37_FLASH_MODE_CFG,
+			GPIO37_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio38",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO38_FLASH_MODE_CFG,
+			GPIO38_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio39",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO39_FLASH_MODE_CFG,
+			GPIO39_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio40",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO40_FLASH_MODE_CFG,
+			GPIO40_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio41",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO41_FLASH_MODE_CFG,
+			GPIO41_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio42",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO42_FLASH_MODE_CFG,
+			GPIO42_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio43",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO43_FLASH_MODE_CFG,
+			GPIO43_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio44",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO44_FLASH_MODE_CFG,
+			GPIO44_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio45",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO45_FLASH_MODE_CFG,
+			GPIO45_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio46",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO46_FLASH_MODE_CFG,
+			GPIO46_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	}, {
+		.name = "gpio47",
+		.regmap[0] = {
+			AIROHA_FUNC_PWM_EXT_MUX,
+			REG_GPIO_FLASH_MODE_CFG_EXT,
+			GPIO47_FLASH_MODE_CFG,
+			GPIO47_FLASH_MODE_CFG
+		},
+		.regmap_size = 1,
+	},
+};
+
+static const struct airoha_pinctrl_func_group phy1_led0_func_group[] = {
+	{
+		.name = "gpio33",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN0_LED0_MODE_MASK,
+			GPIO_LAN0_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY1_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio34",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN1_LED0_MODE_MASK,
+			GPIO_LAN1_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY1_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio35",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN2_LED0_MODE_MASK,
+			GPIO_LAN2_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY1_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio42",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN3_LED0_MODE_MASK,
+			GPIO_LAN3_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN4_LED_MAPPING_MASK,
+			LAN4_PHY1_LED_MAP
+		},
+		.regmap_size = 2,
+	},
+};
+
+static const struct airoha_pinctrl_func_group phy2_led0_func_group[] = {
+	{
+		.name = "gpio33",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN0_LED0_MODE_MASK,
+			GPIO_LAN0_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY2_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio34",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN1_LED0_MODE_MASK,
+			GPIO_LAN1_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY2_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio35",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN2_LED0_MODE_MASK,
+			GPIO_LAN2_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY2_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio42",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN3_LED0_MODE_MASK,
+			GPIO_LAN3_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN4_LED_MAPPING_MASK,
+			LAN4_PHY2_LED_MAP
+		},
+		.regmap_size = 2,
+	},
+};
+
+static const struct airoha_pinctrl_func_group phy3_led0_func_group[] = {
+	{
+		.name = "gpio33",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN0_LED0_MODE_MASK,
+			GPIO_LAN0_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY3_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio34",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN1_LED0_MODE_MASK,
+			GPIO_LAN1_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY3_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio35",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN2_LED0_MODE_MASK,
+			GPIO_LAN2_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY3_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio42",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN3_LED0_MODE_MASK,
+			GPIO_LAN3_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN4_LED_MAPPING_MASK,
+			LAN4_PHY3_LED_MAP
+		},
+		.regmap_size = 2,
+	},
+};
+
+static const struct airoha_pinctrl_func_group phy4_led0_func_group[] = {
+	{
+		.name = "gpio33",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN0_LED0_MODE_MASK,
+			GPIO_LAN0_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY4_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio34",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN1_LED0_MODE_MASK,
+			GPIO_LAN1_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY4_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio35",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN2_LED0_MODE_MASK,
+			GPIO_LAN2_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY4_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio42",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN3_LED0_MODE_MASK,
+			GPIO_LAN3_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED0_MAPPING,
+			LAN4_LED_MAPPING_MASK,
+			LAN4_PHY4_LED_MAP
+		},
+		.regmap_size = 2,
+	},
+};
+
+static const struct airoha_pinctrl_func_group phy1_led1_func_group[] = {
+	{
+		.name = "gpio43",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN0_LED1_MODE_MASK,
+			GPIO_LAN0_LED1_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY1_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio44",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN1_LED1_MODE_MASK,
+			GPIO_LAN1_LED1_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY1_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio45",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN2_LED1_MODE_MASK,
+			GPIO_LAN2_LED1_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY1_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio46",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN3_LED0_MODE_MASK,
+			GPIO_LAN3_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN4_LED_MAPPING_MASK,
+			LAN4_PHY1_LED_MAP
+		},
+		.regmap_size = 2,
+	},
+};
+
+static const struct airoha_pinctrl_func_group phy2_led1_func_group[] = {
+	{
+		.name = "gpio43",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN0_LED1_MODE_MASK,
+			GPIO_LAN0_LED1_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY2_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio44",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN1_LED1_MODE_MASK,
+			GPIO_LAN1_LED1_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY2_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio45",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN2_LED1_MODE_MASK,
+			GPIO_LAN2_LED1_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY2_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio46",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN3_LED0_MODE_MASK,
+			GPIO_LAN3_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN4_LED_MAPPING_MASK,
+			LAN4_PHY2_LED_MAP
+		},
+		.regmap_size = 2,
+	},
+};
+
+static const struct airoha_pinctrl_func_group phy3_led1_func_group[] = {
+	{
+		.name = "gpio43",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN0_LED1_MODE_MASK,
+			GPIO_LAN0_LED1_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY3_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio44",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN1_LED1_MODE_MASK,
+			GPIO_LAN1_LED1_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY3_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio45",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN2_LED1_MODE_MASK,
+			GPIO_LAN2_LED1_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY3_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio46",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN3_LED0_MODE_MASK,
+			GPIO_LAN3_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN4_LED_MAPPING_MASK,
+			LAN4_PHY3_LED_MAP
+		},
+		.regmap_size = 2,
+	},
+};
+
+static const struct airoha_pinctrl_func_group phy4_led1_func_group[] = {
+	{
+		.name = "gpio43",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN0_LED1_MODE_MASK,
+			GPIO_LAN0_LED1_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY4_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio44",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN1_LED1_MODE_MASK,
+			GPIO_LAN1_LED1_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY4_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio45",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN2_LED1_MODE_MASK,
+			GPIO_LAN2_LED1_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY4_LED_MAP
+		},
+		.regmap_size = 2,
+	}, {
+		.name = "gpio46",
+		.regmap[0] = {
+			AIROHA_FUNC_MUX,
+			REG_GPIO_2ND_I2C_MODE,
+			GPIO_LAN3_LED0_MODE_MASK,
+			GPIO_LAN3_LED0_MODE_MASK
+		},
+		.regmap[1] = {
+			AIROHA_FUNC_MUX,
+			REG_LAN_LED1_MAPPING,
+			LAN4_LED_MAPPING_MASK,
+			LAN4_PHY4_LED_MAP
+		},
+		.regmap_size = 2,
+	},
+};
+
+static const struct airoha_pinctrl_func airoha_pinctrl_funcs[] = {
+	PINCTRL_FUNC_DESC(pon),
+	PINCTRL_FUNC_DESC(tod_1pps),
+	PINCTRL_FUNC_DESC(sipo),
+	PINCTRL_FUNC_DESC(mdio),
+	PINCTRL_FUNC_DESC(uart),
+	PINCTRL_FUNC_DESC(i2c),
+	PINCTRL_FUNC_DESC(jtag),
+	PINCTRL_FUNC_DESC(pcm),
+	PINCTRL_FUNC_DESC(spi),
+	PINCTRL_FUNC_DESC(pcm_spi),
+	PINCTRL_FUNC_DESC(i2s),
+	PINCTRL_FUNC_DESC(emmc),
+	PINCTRL_FUNC_DESC(pnand),
+	PINCTRL_FUNC_DESC(pcie_reset),
+	PINCTRL_FUNC_DESC(pwm),
+	PINCTRL_FUNC_DESC(phy1_led0),
+	PINCTRL_FUNC_DESC(phy2_led0),
+	PINCTRL_FUNC_DESC(phy3_led0),
+	PINCTRL_FUNC_DESC(phy4_led0),
+	PINCTRL_FUNC_DESC(phy1_led1),
+	PINCTRL_FUNC_DESC(phy2_led1),
+	PINCTRL_FUNC_DESC(phy3_led1),
+	PINCTRL_FUNC_DESC(phy4_led1),
+};
+
+static const struct airoha_pinctrl_conf airoha_pinctrl_pullup_conf[] = {
+	PINCTRL_CONF_DESC(0, REG_I2C_SDA_PU, UART1_TXD_PU_MASK),
+	PINCTRL_CONF_DESC(1, REG_I2C_SDA_PU, UART1_RXD_PU_MASK),
+	PINCTRL_CONF_DESC(2, REG_I2C_SDA_PU, I2C_SDA_PU_MASK),
+	PINCTRL_CONF_DESC(3, REG_I2C_SDA_PU, I2C_SCL_PU_MASK),
+	PINCTRL_CONF_DESC(4, REG_I2C_SDA_PU, SPI_CS0_PU_MASK),
+	PINCTRL_CONF_DESC(5, REG_I2C_SDA_PU, SPI_CLK_PU_MASK),
+	PINCTRL_CONF_DESC(6, REG_I2C_SDA_PU, SPI_MOSI_PU_MASK),
+	PINCTRL_CONF_DESC(7, REG_I2C_SDA_PU, SPI_MISO_PU_MASK),
+	PINCTRL_CONF_DESC(13, REG_GPIO_L_PU, BIT(0)),
+	PINCTRL_CONF_DESC(14, REG_GPIO_L_PU, BIT(1)),
+	PINCTRL_CONF_DESC(15, REG_GPIO_L_PU, BIT(2)),
+	PINCTRL_CONF_DESC(16, REG_GPIO_L_PU, BIT(3)),
+	PINCTRL_CONF_DESC(17, REG_GPIO_L_PU, BIT(4)),
+	PINCTRL_CONF_DESC(18, REG_GPIO_L_PU, BIT(5)),
+	PINCTRL_CONF_DESC(19, REG_GPIO_L_PU, BIT(6)),
+	PINCTRL_CONF_DESC(20, REG_GPIO_L_PU, BIT(7)),
+	PINCTRL_CONF_DESC(21, REG_GPIO_L_PU, BIT(8)),
+	PINCTRL_CONF_DESC(22, REG_GPIO_L_PU, BIT(9)),
+	PINCTRL_CONF_DESC(23, REG_GPIO_L_PU, BIT(10)),
+	PINCTRL_CONF_DESC(24, REG_GPIO_L_PU, BIT(11)),
+	PINCTRL_CONF_DESC(25, REG_GPIO_L_PU, BIT(12)),
+	PINCTRL_CONF_DESC(26, REG_GPIO_L_PU, BIT(13)),
+	PINCTRL_CONF_DESC(27, REG_GPIO_L_PU, BIT(14)),
+	PINCTRL_CONF_DESC(28, REG_GPIO_L_PU, BIT(15)),
+	PINCTRL_CONF_DESC(29, REG_GPIO_L_PU, BIT(16)),
+	PINCTRL_CONF_DESC(30, REG_GPIO_L_PU, BIT(17)),
+	PINCTRL_CONF_DESC(31, REG_GPIO_L_PU, BIT(18)),
+	PINCTRL_CONF_DESC(32, REG_GPIO_L_PU, BIT(18)),
+	PINCTRL_CONF_DESC(33, REG_GPIO_L_PU, BIT(20)),
+	PINCTRL_CONF_DESC(34, REG_GPIO_L_PU, BIT(21)),
+	PINCTRL_CONF_DESC(35, REG_GPIO_L_PU, BIT(22)),
+	PINCTRL_CONF_DESC(36, REG_GPIO_L_PU, BIT(23)),
+	PINCTRL_CONF_DESC(37, REG_GPIO_L_PU, BIT(24)),
+	PINCTRL_CONF_DESC(38, REG_GPIO_L_PU, BIT(25)),
+	PINCTRL_CONF_DESC(39, REG_GPIO_L_PU, BIT(26)),
+	PINCTRL_CONF_DESC(40, REG_GPIO_L_PU, BIT(27)),
+	PINCTRL_CONF_DESC(41, REG_GPIO_L_PU, BIT(28)),
+	PINCTRL_CONF_DESC(42, REG_GPIO_L_PU, BIT(29)),
+	PINCTRL_CONF_DESC(43, REG_GPIO_L_PU, BIT(30)),
+	PINCTRL_CONF_DESC(44, REG_GPIO_L_PU, BIT(31)),
+	PINCTRL_CONF_DESC(45, REG_GPIO_H_PU, BIT(0)),
+	PINCTRL_CONF_DESC(46, REG_GPIO_H_PU, BIT(1)),
+	PINCTRL_CONF_DESC(47, REG_GPIO_H_PU, BIT(2)),
+	PINCTRL_CONF_DESC(48, REG_GPIO_H_PU, BIT(3)),
+	PINCTRL_CONF_DESC(49, REG_GPIO_H_PU, BIT(4)),
+	PINCTRL_CONF_DESC(50, REG_GPIO_H_PU, BIT(5)),
+	PINCTRL_CONF_DESC(51, REG_GPIO_H_PU, BIT(6)),
+	PINCTRL_CONF_DESC(52, REG_GPIO_H_PU, BIT(7)),
+	PINCTRL_CONF_DESC(53, REG_GPIO_H_PU, BIT(8)),
+	PINCTRL_CONF_DESC(54, REG_GPIO_H_PU, BIT(9)),
+	PINCTRL_CONF_DESC(55, REG_GPIO_H_PU, BIT(10)),
+	PINCTRL_CONF_DESC(56, REG_GPIO_H_PU, BIT(11)),
+	PINCTRL_CONF_DESC(57, REG_GPIO_H_PU, BIT(12)),
+	PINCTRL_CONF_DESC(58, REG_GPIO_H_PU, BIT(13)),
+	PINCTRL_CONF_DESC(59, REG_GPIO_H_PU, BIT(14)),
+	PINCTRL_CONF_DESC(61, REG_I2C_SDA_PU, PCIE0_RESET_PU_MASK),
+	PINCTRL_CONF_DESC(62, REG_I2C_SDA_PU, PCIE1_RESET_PU_MASK),
+	PINCTRL_CONF_DESC(63, REG_I2C_SDA_PU, PCIE2_RESET_PU_MASK),
+};
+
+static const struct airoha_pinctrl_conf airoha_pinctrl_pulldown_conf[] = {
+	PINCTRL_CONF_DESC(0, REG_I2C_SDA_PD, UART1_TXD_PD_MASK),
+	PINCTRL_CONF_DESC(1, REG_I2C_SDA_PD, UART1_RXD_PD_MASK),
+	PINCTRL_CONF_DESC(2, REG_I2C_SDA_PD, I2C_SDA_PD_MASK),
+	PINCTRL_CONF_DESC(3, REG_I2C_SDA_PD, I2C_SCL_PD_MASK),
+	PINCTRL_CONF_DESC(4, REG_I2C_SDA_PD, SPI_CS0_PD_MASK),
+	PINCTRL_CONF_DESC(5, REG_I2C_SDA_PD, SPI_CLK_PD_MASK),
+	PINCTRL_CONF_DESC(6, REG_I2C_SDA_PD, SPI_MOSI_PD_MASK),
+	PINCTRL_CONF_DESC(7, REG_I2C_SDA_PD, SPI_MISO_PD_MASK),
+	PINCTRL_CONF_DESC(13, REG_GPIO_L_PD, BIT(0)),
+	PINCTRL_CONF_DESC(14, REG_GPIO_L_PD, BIT(1)),
+	PINCTRL_CONF_DESC(15, REG_GPIO_L_PD, BIT(2)),
+	PINCTRL_CONF_DESC(16, REG_GPIO_L_PD, BIT(3)),
+	PINCTRL_CONF_DESC(17, REG_GPIO_L_PD, BIT(4)),
+	PINCTRL_CONF_DESC(18, REG_GPIO_L_PD, BIT(5)),
+	PINCTRL_CONF_DESC(19, REG_GPIO_L_PD, BIT(6)),
+	PINCTRL_CONF_DESC(20, REG_GPIO_L_PD, BIT(7)),
+	PINCTRL_CONF_DESC(21, REG_GPIO_L_PD, BIT(8)),
+	PINCTRL_CONF_DESC(22, REG_GPIO_L_PD, BIT(9)),
+	PINCTRL_CONF_DESC(23, REG_GPIO_L_PD, BIT(10)),
+	PINCTRL_CONF_DESC(24, REG_GPIO_L_PD, BIT(11)),
+	PINCTRL_CONF_DESC(25, REG_GPIO_L_PD, BIT(12)),
+	PINCTRL_CONF_DESC(26, REG_GPIO_L_PD, BIT(13)),
+	PINCTRL_CONF_DESC(27, REG_GPIO_L_PD, BIT(14)),
+	PINCTRL_CONF_DESC(28, REG_GPIO_L_PD, BIT(15)),
+	PINCTRL_CONF_DESC(29, REG_GPIO_L_PD, BIT(16)),
+	PINCTRL_CONF_DESC(30, REG_GPIO_L_PD, BIT(17)),
+	PINCTRL_CONF_DESC(31, REG_GPIO_L_PD, BIT(18)),
+	PINCTRL_CONF_DESC(32, REG_GPIO_L_PD, BIT(18)),
+	PINCTRL_CONF_DESC(33, REG_GPIO_L_PD, BIT(20)),
+	PINCTRL_CONF_DESC(34, REG_GPIO_L_PD, BIT(21)),
+	PINCTRL_CONF_DESC(35, REG_GPIO_L_PD, BIT(22)),
+	PINCTRL_CONF_DESC(36, REG_GPIO_L_PD, BIT(23)),
+	PINCTRL_CONF_DESC(37, REG_GPIO_L_PD, BIT(24)),
+	PINCTRL_CONF_DESC(38, REG_GPIO_L_PD, BIT(25)),
+	PINCTRL_CONF_DESC(39, REG_GPIO_L_PD, BIT(26)),
+	PINCTRL_CONF_DESC(40, REG_GPIO_L_PD, BIT(27)),
+	PINCTRL_CONF_DESC(41, REG_GPIO_L_PD, BIT(28)),
+	PINCTRL_CONF_DESC(42, REG_GPIO_L_PD, BIT(29)),
+	PINCTRL_CONF_DESC(43, REG_GPIO_L_PD, BIT(30)),
+	PINCTRL_CONF_DESC(44, REG_GPIO_L_PD, BIT(31)),
+	PINCTRL_CONF_DESC(45, REG_GPIO_H_PD, BIT(0)),
+	PINCTRL_CONF_DESC(46, REG_GPIO_H_PD, BIT(1)),
+	PINCTRL_CONF_DESC(47, REG_GPIO_H_PD, BIT(2)),
+	PINCTRL_CONF_DESC(48, REG_GPIO_H_PD, BIT(3)),
+	PINCTRL_CONF_DESC(49, REG_GPIO_H_PD, BIT(4)),
+	PINCTRL_CONF_DESC(50, REG_GPIO_H_PD, BIT(5)),
+	PINCTRL_CONF_DESC(51, REG_GPIO_H_PD, BIT(6)),
+	PINCTRL_CONF_DESC(52, REG_GPIO_H_PD, BIT(7)),
+	PINCTRL_CONF_DESC(53, REG_GPIO_H_PD, BIT(8)),
+	PINCTRL_CONF_DESC(54, REG_GPIO_H_PD, BIT(9)),
+	PINCTRL_CONF_DESC(55, REG_GPIO_H_PD, BIT(10)),
+	PINCTRL_CONF_DESC(56, REG_GPIO_H_PD, BIT(11)),
+	PINCTRL_CONF_DESC(57, REG_GPIO_H_PD, BIT(12)),
+	PINCTRL_CONF_DESC(58, REG_GPIO_H_PD, BIT(13)),
+	PINCTRL_CONF_DESC(59, REG_GPIO_H_PD, BIT(14)),
+	PINCTRL_CONF_DESC(61, REG_I2C_SDA_PD, PCIE0_RESET_PD_MASK),
+	PINCTRL_CONF_DESC(62, REG_I2C_SDA_PD, PCIE1_RESET_PD_MASK),
+	PINCTRL_CONF_DESC(63, REG_I2C_SDA_PD, PCIE2_RESET_PD_MASK),
+};
+
+static const struct airoha_pinctrl_conf airoha_pinctrl_drive_e2_conf[] = {
+	PINCTRL_CONF_DESC(0, REG_I2C_SDA_E2, UART1_TXD_E2_MASK),
+	PINCTRL_CONF_DESC(1, REG_I2C_SDA_E2, UART1_RXD_E2_MASK),
+	PINCTRL_CONF_DESC(2, REG_I2C_SDA_E2, I2C_SDA_E2_MASK),
+	PINCTRL_CONF_DESC(3, REG_I2C_SDA_E2, I2C_SCL_E2_MASK),
+	PINCTRL_CONF_DESC(4, REG_I2C_SDA_E2, SPI_CS0_E2_MASK),
+	PINCTRL_CONF_DESC(5, REG_I2C_SDA_E2, SPI_CLK_E2_MASK),
+	PINCTRL_CONF_DESC(6, REG_I2C_SDA_E2, SPI_MOSI_E2_MASK),
+	PINCTRL_CONF_DESC(7, REG_I2C_SDA_E2, SPI_MISO_E2_MASK),
+	PINCTRL_CONF_DESC(13, REG_GPIO_L_E2, BIT(0)),
+	PINCTRL_CONF_DESC(14, REG_GPIO_L_E2, BIT(1)),
+	PINCTRL_CONF_DESC(15, REG_GPIO_L_E2, BIT(2)),
+	PINCTRL_CONF_DESC(16, REG_GPIO_L_E2, BIT(3)),
+	PINCTRL_CONF_DESC(17, REG_GPIO_L_E2, BIT(4)),
+	PINCTRL_CONF_DESC(18, REG_GPIO_L_E2, BIT(5)),
+	PINCTRL_CONF_DESC(19, REG_GPIO_L_E2, BIT(6)),
+	PINCTRL_CONF_DESC(20, REG_GPIO_L_E2, BIT(7)),
+	PINCTRL_CONF_DESC(21, REG_GPIO_L_E2, BIT(8)),
+	PINCTRL_CONF_DESC(22, REG_GPIO_L_E2, BIT(9)),
+	PINCTRL_CONF_DESC(23, REG_GPIO_L_E2, BIT(10)),
+	PINCTRL_CONF_DESC(24, REG_GPIO_L_E2, BIT(11)),
+	PINCTRL_CONF_DESC(25, REG_GPIO_L_E2, BIT(12)),
+	PINCTRL_CONF_DESC(26, REG_GPIO_L_E2, BIT(13)),
+	PINCTRL_CONF_DESC(27, REG_GPIO_L_E2, BIT(14)),
+	PINCTRL_CONF_DESC(28, REG_GPIO_L_E2, BIT(15)),
+	PINCTRL_CONF_DESC(29, REG_GPIO_L_E2, BIT(16)),
+	PINCTRL_CONF_DESC(30, REG_GPIO_L_E2, BIT(17)),
+	PINCTRL_CONF_DESC(31, REG_GPIO_L_E2, BIT(18)),
+	PINCTRL_CONF_DESC(32, REG_GPIO_L_E2, BIT(18)),
+	PINCTRL_CONF_DESC(33, REG_GPIO_L_E2, BIT(20)),
+	PINCTRL_CONF_DESC(34, REG_GPIO_L_E2, BIT(21)),
+	PINCTRL_CONF_DESC(35, REG_GPIO_L_E2, BIT(22)),
+	PINCTRL_CONF_DESC(36, REG_GPIO_L_E2, BIT(23)),
+	PINCTRL_CONF_DESC(37, REG_GPIO_L_E2, BIT(24)),
+	PINCTRL_CONF_DESC(38, REG_GPIO_L_E2, BIT(25)),
+	PINCTRL_CONF_DESC(39, REG_GPIO_L_E2, BIT(26)),
+	PINCTRL_CONF_DESC(40, REG_GPIO_L_E2, BIT(27)),
+	PINCTRL_CONF_DESC(41, REG_GPIO_L_E2, BIT(28)),
+	PINCTRL_CONF_DESC(42, REG_GPIO_L_E2, BIT(29)),
+	PINCTRL_CONF_DESC(43, REG_GPIO_L_E2, BIT(30)),
+	PINCTRL_CONF_DESC(44, REG_GPIO_L_E2, BIT(31)),
+	PINCTRL_CONF_DESC(45, REG_GPIO_H_E2, BIT(0)),
+	PINCTRL_CONF_DESC(46, REG_GPIO_H_E2, BIT(1)),
+	PINCTRL_CONF_DESC(47, REG_GPIO_H_E2, BIT(2)),
+	PINCTRL_CONF_DESC(48, REG_GPIO_H_E2, BIT(3)),
+	PINCTRL_CONF_DESC(49, REG_GPIO_H_E2, BIT(4)),
+	PINCTRL_CONF_DESC(50, REG_GPIO_H_E2, BIT(5)),
+	PINCTRL_CONF_DESC(51, REG_GPIO_H_E2, BIT(6)),
+	PINCTRL_CONF_DESC(52, REG_GPIO_H_E2, BIT(7)),
+	PINCTRL_CONF_DESC(53, REG_GPIO_H_E2, BIT(8)),
+	PINCTRL_CONF_DESC(54, REG_GPIO_H_E2, BIT(9)),
+	PINCTRL_CONF_DESC(55, REG_GPIO_H_E2, BIT(10)),
+	PINCTRL_CONF_DESC(56, REG_GPIO_H_E2, BIT(11)),
+	PINCTRL_CONF_DESC(57, REG_GPIO_H_E2, BIT(12)),
+	PINCTRL_CONF_DESC(58, REG_GPIO_H_E2, BIT(13)),
+	PINCTRL_CONF_DESC(59, REG_GPIO_H_E2, BIT(14)),
+	PINCTRL_CONF_DESC(61, REG_I2C_SDA_E2, PCIE0_RESET_E2_MASK),
+	PINCTRL_CONF_DESC(62, REG_I2C_SDA_E2, PCIE1_RESET_E2_MASK),
+	PINCTRL_CONF_DESC(63, REG_I2C_SDA_E2, PCIE2_RESET_E2_MASK),
+};
+
+static const struct airoha_pinctrl_conf airoha_pinctrl_drive_e4_conf[] = {
+	PINCTRL_CONF_DESC(0, REG_I2C_SDA_E4, UART1_TXD_E4_MASK),
+	PINCTRL_CONF_DESC(1, REG_I2C_SDA_E4, UART1_RXD_E4_MASK),
+	PINCTRL_CONF_DESC(2, REG_I2C_SDA_E4, I2C_SDA_E4_MASK),
+	PINCTRL_CONF_DESC(3, REG_I2C_SDA_E4, I2C_SCL_E4_MASK),
+	PINCTRL_CONF_DESC(4, REG_I2C_SDA_E4, SPI_CS0_E4_MASK),
+	PINCTRL_CONF_DESC(5, REG_I2C_SDA_E4, SPI_CLK_E4_MASK),
+	PINCTRL_CONF_DESC(6, REG_I2C_SDA_E4, SPI_MOSI_E4_MASK),
+	PINCTRL_CONF_DESC(7, REG_I2C_SDA_E4, SPI_MISO_E4_MASK),
+	PINCTRL_CONF_DESC(13, REG_GPIO_L_E4, BIT(0)),
+	PINCTRL_CONF_DESC(14, REG_GPIO_L_E4, BIT(1)),
+	PINCTRL_CONF_DESC(15, REG_GPIO_L_E4, BIT(2)),
+	PINCTRL_CONF_DESC(16, REG_GPIO_L_E4, BIT(3)),
+	PINCTRL_CONF_DESC(17, REG_GPIO_L_E4, BIT(4)),
+	PINCTRL_CONF_DESC(18, REG_GPIO_L_E4, BIT(5)),
+	PINCTRL_CONF_DESC(19, REG_GPIO_L_E4, BIT(6)),
+	PINCTRL_CONF_DESC(20, REG_GPIO_L_E4, BIT(7)),
+	PINCTRL_CONF_DESC(21, REG_GPIO_L_E4, BIT(8)),
+	PINCTRL_CONF_DESC(22, REG_GPIO_L_E4, BIT(9)),
+	PINCTRL_CONF_DESC(23, REG_GPIO_L_E4, BIT(10)),
+	PINCTRL_CONF_DESC(24, REG_GPIO_L_E4, BIT(11)),
+	PINCTRL_CONF_DESC(25, REG_GPIO_L_E4, BIT(12)),
+	PINCTRL_CONF_DESC(26, REG_GPIO_L_E4, BIT(13)),
+	PINCTRL_CONF_DESC(27, REG_GPIO_L_E4, BIT(14)),
+	PINCTRL_CONF_DESC(28, REG_GPIO_L_E4, BIT(15)),
+	PINCTRL_CONF_DESC(29, REG_GPIO_L_E4, BIT(16)),
+	PINCTRL_CONF_DESC(30, REG_GPIO_L_E4, BIT(17)),
+	PINCTRL_CONF_DESC(31, REG_GPIO_L_E4, BIT(18)),
+	PINCTRL_CONF_DESC(32, REG_GPIO_L_E4, BIT(18)),
+	PINCTRL_CONF_DESC(33, REG_GPIO_L_E4, BIT(20)),
+	PINCTRL_CONF_DESC(34, REG_GPIO_L_E4, BIT(21)),
+	PINCTRL_CONF_DESC(35, REG_GPIO_L_E4, BIT(22)),
+	PINCTRL_CONF_DESC(36, REG_GPIO_L_E4, BIT(23)),
+	PINCTRL_CONF_DESC(37, REG_GPIO_L_E4, BIT(24)),
+	PINCTRL_CONF_DESC(38, REG_GPIO_L_E4, BIT(25)),
+	PINCTRL_CONF_DESC(39, REG_GPIO_L_E4, BIT(26)),
+	PINCTRL_CONF_DESC(40, REG_GPIO_L_E4, BIT(27)),
+	PINCTRL_CONF_DESC(41, REG_GPIO_L_E4, BIT(28)),
+	PINCTRL_CONF_DESC(42, REG_GPIO_L_E4, BIT(29)),
+	PINCTRL_CONF_DESC(43, REG_GPIO_L_E4, BIT(30)),
+	PINCTRL_CONF_DESC(44, REG_GPIO_L_E4, BIT(31)),
+	PINCTRL_CONF_DESC(45, REG_GPIO_H_E4, BIT(0)),
+	PINCTRL_CONF_DESC(46, REG_GPIO_H_E4, BIT(1)),
+	PINCTRL_CONF_DESC(47, REG_GPIO_H_E4, BIT(2)),
+	PINCTRL_CONF_DESC(48, REG_GPIO_H_E4, BIT(3)),
+	PINCTRL_CONF_DESC(49, REG_GPIO_H_E4, BIT(4)),
+	PINCTRL_CONF_DESC(50, REG_GPIO_H_E4, BIT(5)),
+	PINCTRL_CONF_DESC(51, REG_GPIO_H_E4, BIT(6)),
+	PINCTRL_CONF_DESC(52, REG_GPIO_H_E4, BIT(7)),
+	PINCTRL_CONF_DESC(53, REG_GPIO_H_E4, BIT(8)),
+	PINCTRL_CONF_DESC(54, REG_GPIO_H_E4, BIT(9)),
+	PINCTRL_CONF_DESC(55, REG_GPIO_H_E4, BIT(10)),
+	PINCTRL_CONF_DESC(56, REG_GPIO_H_E4, BIT(11)),
+	PINCTRL_CONF_DESC(57, REG_GPIO_H_E4, BIT(12)),
+	PINCTRL_CONF_DESC(58, REG_GPIO_H_E4, BIT(13)),
+	PINCTRL_CONF_DESC(59, REG_GPIO_H_E4, BIT(14)),
+	PINCTRL_CONF_DESC(61, REG_I2C_SDA_E4, PCIE0_RESET_E4_MASK),
+	PINCTRL_CONF_DESC(62, REG_I2C_SDA_E4, PCIE1_RESET_E4_MASK),
+	PINCTRL_CONF_DESC(63, REG_I2C_SDA_E4, PCIE2_RESET_E4_MASK),
+};
+
+static const struct airoha_pinctrl_conf airoha_pinctrl_pcie_rst_od_conf[] = {
+	PINCTRL_CONF_DESC(61, REG_PCIE_RESET_OD, PCIE0_RESET_OD_MASK),
+	PINCTRL_CONF_DESC(62, REG_PCIE_RESET_OD, PCIE1_RESET_OD_MASK),
+	PINCTRL_CONF_DESC(63, REG_PCIE_RESET_OD, PCIE2_RESET_OD_MASK),
+};
+
+static int airoha_convert_pin_to_reg_offset(struct pinctrl_dev *pctrl_dev,
+					    struct pinctrl_gpio_range *range,
+					    int pin)
+{
+	if (!range)
+		range = pinctrl_find_gpio_range_from_pin_nolock(pctrl_dev,
+								pin);
+	if (!range)
+		return -EINVAL;
+
+	return pin - range->pin_base;
+}
+
+/* gpio callbacks */
+static void airoha_gpio_set(struct gpio_chip *chip, unsigned int gpio,
+			    int value)
+{
+	struct airoha_pinctrl *pinctrl = gpiochip_get_data(chip);
+	u32 offset = gpio % AIROHA_PIN_BANK_SIZE;
+	u8 index = gpio / AIROHA_PIN_BANK_SIZE;
+
+	regmap_update_bits(pinctrl->regmap, pinctrl->gpiochip.data[index],
+			   BIT(offset), value ? BIT(offset) : 0);
+}
+
+static int airoha_gpio_get(struct gpio_chip *chip, unsigned int gpio)
+{
+	struct airoha_pinctrl *pinctrl = gpiochip_get_data(chip);
+	u32 val, pin = gpio % AIROHA_PIN_BANK_SIZE;
+	u8 index = gpio / AIROHA_PIN_BANK_SIZE;
+	int err;
+
+	err = regmap_read(pinctrl->regmap,
+			  pinctrl->gpiochip.data[index], &val);
+
+	return err ? err : !!(val & BIT(pin));
+}
+
+static int airoha_gpio_direction_output(struct gpio_chip *chip,
+					unsigned int gpio, int value)
+{
+	int err;
+
+	err = pinctrl_gpio_direction_output(chip, gpio);
+	if (err)
+		return err;
+
+	airoha_gpio_set(chip, gpio, value);
+
+	return 0;
+}
+
+/* irq callbacks */
+static void airoha_irq_unmask(struct irq_data *data)
+{
+	u8 offset = data->hwirq % AIROHA_REG_GPIOCTRL_NUM_PIN;
+	u8 index = data->hwirq / AIROHA_REG_GPIOCTRL_NUM_PIN;
+	u32 mask = GENMASK(2 * offset + 1, 2 * offset);
+	struct airoha_pinctrl_gpiochip *gpiochip;
+	struct airoha_pinctrl *pinctrl;
+	u32 val = BIT(2 * offset);
+
+	gpiochip = irq_data_get_irq_chip_data(data);
+	if (WARN_ON_ONCE(data->hwirq >= ARRAY_SIZE(gpiochip->irq_type)))
+		return;
+
+	pinctrl = container_of(gpiochip, struct airoha_pinctrl, gpiochip);
+	switch (gpiochip->irq_type[data->hwirq]) {
+	case IRQ_TYPE_LEVEL_LOW:
+		val = val << 1;
+		fallthrough;
+	case IRQ_TYPE_LEVEL_HIGH:
+		regmap_update_bits(pinctrl->regmap, gpiochip->level[index],
+				   mask, val);
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		val = val << 1;
+		fallthrough;
+	case IRQ_TYPE_EDGE_RISING:
+		regmap_update_bits(pinctrl->regmap, gpiochip->edge[index],
+				   mask, val);
+		break;
+	case IRQ_TYPE_EDGE_BOTH:
+		regmap_set_bits(pinctrl->regmap, gpiochip->edge[index], mask);
+		break;
+	default:
+		break;
+	}
+}
+
+static void airoha_irq_mask(struct irq_data *data)
+{
+	u8 offset = data->hwirq % AIROHA_REG_GPIOCTRL_NUM_PIN;
+	u8 index = data->hwirq / AIROHA_REG_GPIOCTRL_NUM_PIN;
+	u32 mask = GENMASK(2 * offset + 1, 2 * offset);
+	struct airoha_pinctrl_gpiochip *gpiochip;
+	struct airoha_pinctrl *pinctrl;
+
+	gpiochip = irq_data_get_irq_chip_data(data);
+	pinctrl = container_of(gpiochip, struct airoha_pinctrl, gpiochip);
+
+	regmap_clear_bits(pinctrl->regmap, gpiochip->level[index], mask);
+	regmap_clear_bits(pinctrl->regmap, gpiochip->edge[index], mask);
+}
+
+static int airoha_irq_type(struct irq_data *data, unsigned int type)
+{
+	struct airoha_pinctrl_gpiochip *gpiochip;
+
+	gpiochip = irq_data_get_irq_chip_data(data);
+	if (data->hwirq >= ARRAY_SIZE(gpiochip->irq_type))
+		return -EINVAL;
+
+	if (type == IRQ_TYPE_PROBE) {
+		if (gpiochip->irq_type[data->hwirq])
+			return 0;
+
+		type = IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING;
+	}
+	gpiochip->irq_type[data->hwirq] = type & IRQ_TYPE_SENSE_MASK;
+
+	return 0;
+}
+
+static irqreturn_t airoha_irq_handler(int irq, void *data)
+{
+	struct airoha_pinctrl *pinctrl = data;
+	bool handled = false;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(irq_status_regs); i++) {
+		struct gpio_irq_chip *girq = &pinctrl->gpiochip.chip.irq;
+		u32 status;
+		int irq;
+
+		if (regmap_read(pinctrl->regmap, pinctrl->gpiochip.status[i],
+				&status))
+			continue;
+
+		for_each_set_bit(irq, (unsigned long *)&status,
+				 AIROHA_PIN_BANK_SIZE) {
+			u32 offset = irq + i * AIROHA_PIN_BANK_SIZE;
+
+			generic_handle_irq(irq_find_mapping(girq->domain,
+							    offset));
+			regmap_write(pinctrl->regmap,
+				     pinctrl->gpiochip.status[i], BIT(irq));
+		}
+		handled |= !!status;
+	}
+
+	return handled ? IRQ_HANDLED : IRQ_NONE;
+}
+
+static const struct irq_chip airoha_gpio_irq_chip = {
+	.name = "airoha-gpio-irq",
+	.irq_unmask = airoha_irq_unmask,
+	.irq_mask = airoha_irq_mask,
+	.irq_mask_ack = airoha_irq_mask,
+	.irq_set_type = airoha_irq_type,
+	.flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_IMMUTABLE,
+};
+
+static int airoha_pinctrl_add_gpiochip(struct airoha_pinctrl *pinctrl,
+				       struct platform_device *pdev)
+{
+	struct airoha_pinctrl_gpiochip *chip = &pinctrl->gpiochip;
+	struct gpio_chip *gc = &chip->chip;
+	struct gpio_irq_chip *girq = &gc->irq;
+	struct device *dev = &pdev->dev;
+	int irq, err;
+
+	chip->data = gpio_data_regs;
+	chip->dir = gpio_dir_regs;
+	chip->out = gpio_out_regs;
+	chip->status = irq_status_regs;
+	chip->level = irq_level_regs;
+	chip->edge = irq_edge_regs;
+
+	gc->parent = dev;
+	gc->label = dev_name(dev);
+	gc->request = gpiochip_generic_request;
+	gc->free = gpiochip_generic_free;
+	gc->direction_input = pinctrl_gpio_direction_input;
+	gc->direction_output = airoha_gpio_direction_output;
+	gc->set = airoha_gpio_set;
+	gc->get = airoha_gpio_get;
+	gc->base = -1;
+	gc->ngpio = AIROHA_NUM_PINS;
+
+	girq->default_type = IRQ_TYPE_NONE;
+	girq->handler = handle_simple_irq;
+	gpio_irq_chip_set_chip(girq, &airoha_gpio_irq_chip);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	err = devm_request_irq(dev, irq, airoha_irq_handler, IRQF_SHARED,
+			       dev_name(dev), pinctrl);
+	if (err) {
+		dev_err(dev, "error requesting irq %d: %d\n", irq, err);
+		return err;
+	}
+
+	return devm_gpiochip_add_data(dev, gc, pinctrl);
+}
+
+/* pinmux callbacks */
+static int airoha_pinmux_set_mux(struct pinctrl_dev *pctrl_dev,
+				 unsigned int selector,
+				 unsigned int group)
+{
+	struct airoha_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctrl_dev);
+	const struct airoha_pinctrl_func *func;
+	struct function_desc *desc;
+	struct group_desc *grp;
+	int i;
+
+	desc = pinmux_generic_get_function(pctrl_dev, selector);
+	if (!desc)
+		return -EINVAL;
+
+	grp = pinctrl_generic_get_group(pctrl_dev, group);
+	if (!grp)
+		return -EINVAL;
+
+	dev_dbg(pctrl_dev->dev, "enable function %s group %s\n",
+		desc->func.name, grp->grp.name);
+
+	func = desc->data;
+	for (i = 0; i < func->group_size; i++) {
+		const struct airoha_pinctrl_func_group *group;
+		int j;
+
+		group = &func->groups[i];
+		if (strcmp(group->name, grp->grp.name))
+			continue;
+
+		for (j = 0; j < group->regmap_size; j++) {
+			switch (group->regmap[j].mux) {
+			case AIROHA_FUNC_PWM_EXT_MUX:
+			case AIROHA_FUNC_PWM_MUX:
+				regmap_update_bits(pinctrl->regmap,
+						   group->regmap[j].offset,
+						   group->regmap[j].mask,
+						   group->regmap[j].val);
+				break;
+			default:
+				regmap_update_bits(pinctrl->chip_scu,
+						   group->regmap[j].offset,
+						   group->regmap[j].mask,
+						   group->regmap[j].val);
+				break;
+			}
+		}
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int airoha_pinmux_set_direction(struct pinctrl_dev *pctrl_dev,
+				       struct pinctrl_gpio_range *range,
+				       unsigned int p, bool input)
+{
+	struct airoha_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctrl_dev);
+	u32 mask, index;
+	int err, pin;
+
+	pin = airoha_convert_pin_to_reg_offset(pctrl_dev, range, p);
+	if (pin < 0)
+		return pin;
+
+	/* set output enable */
+	mask = BIT(pin % AIROHA_PIN_BANK_SIZE);
+	index = pin / AIROHA_PIN_BANK_SIZE;
+	err = regmap_update_bits(pinctrl->regmap, pinctrl->gpiochip.out[index],
+				 mask, !input ? mask : 0);
+	if (err)
+		return err;
+
+	/* set direction */
+	mask = BIT(2 * (pin % AIROHA_REG_GPIOCTRL_NUM_PIN));
+	index = pin / AIROHA_REG_GPIOCTRL_NUM_PIN;
+	return regmap_update_bits(pinctrl->regmap,
+				  pinctrl->gpiochip.dir[index], mask,
+				  !input ? mask : 0);
+}
+
+static const struct pinmux_ops airoha_pmxops = {
+	.get_functions_count = pinmux_generic_get_function_count,
+	.get_function_name = pinmux_generic_get_function_name,
+	.get_function_groups = pinmux_generic_get_function_groups,
+	.gpio_set_direction = airoha_pinmux_set_direction,
+	.set_mux = airoha_pinmux_set_mux,
+	.strict = true,
+};
+
+/* pinconf callbacks */
+static const struct airoha_pinctrl_reg *
+airoha_pinctrl_get_conf_reg(const struct airoha_pinctrl_conf *conf,
+			    int conf_size, int pin)
+{
+	int i;
+
+	for (i = 0; i < conf_size; i++) {
+		if (conf[i].pin == pin)
+			return &conf[i].reg;
+	}
+
+	return NULL;
+}
+
+static int airoha_pinctrl_get_conf(struct airoha_pinctrl *pinctrl,
+				   const struct airoha_pinctrl_conf *conf,
+				   int conf_size, int pin, u32 *val)
+{
+	const struct airoha_pinctrl_reg *reg;
+
+	reg = airoha_pinctrl_get_conf_reg(conf, conf_size, pin);
+	if (!reg)
+		return -EINVAL;
+
+	if (regmap_read(pinctrl->chip_scu, reg->offset, val))
+		return -EINVAL;
+
+	*val = (*val & reg->mask) >> __ffs(reg->mask);
+
+	return 0;
+}
+
+static int airoha_pinctrl_set_conf(struct airoha_pinctrl *pinctrl,
+				   const struct airoha_pinctrl_conf *conf,
+				   int conf_size, int pin, u32 val)
+{
+	const struct airoha_pinctrl_reg *reg = NULL;
+
+	reg = airoha_pinctrl_get_conf_reg(conf, conf_size, pin);
+	if (!reg)
+		return -EINVAL;
+
+
+	if (regmap_update_bits(pinctrl->chip_scu, reg->offset, reg->mask,
+			       val << __ffs(reg->mask)))
+		return -EINVAL;
+
+	return 0;
+}
+
+#define airoha_pinctrl_get_pullup_conf(pinctrl, pin, val)			\
+	airoha_pinctrl_get_conf((pinctrl), airoha_pinctrl_pullup_conf,		\
+				ARRAY_SIZE(airoha_pinctrl_pullup_conf),		\
+				(pin), (val))
+#define airoha_pinctrl_get_pulldown_conf(pinctrl, pin, val)			\
+	airoha_pinctrl_get_conf((pinctrl), airoha_pinctrl_pulldown_conf,	\
+				ARRAY_SIZE(airoha_pinctrl_pulldown_conf),	\
+				(pin), (val))
+#define airoha_pinctrl_get_drive_e2_conf(pinctrl, pin, val)			\
+	airoha_pinctrl_get_conf((pinctrl), airoha_pinctrl_drive_e2_conf,	\
+				ARRAY_SIZE(airoha_pinctrl_drive_e2_conf),	\
+				(pin), (val))
+#define airoha_pinctrl_get_drive_e4_conf(pinctrl, pin, val)			\
+	airoha_pinctrl_get_conf((pinctrl), airoha_pinctrl_drive_e4_conf,	\
+				ARRAY_SIZE(airoha_pinctrl_drive_e4_conf),	\
+				(pin), (val))
+#define airoha_pinctrl_get_pcie_rst_od_conf(pinctrl, pin, val)			\
+	airoha_pinctrl_get_conf((pinctrl), airoha_pinctrl_pcie_rst_od_conf,	\
+				ARRAY_SIZE(airoha_pinctrl_pcie_rst_od_conf),	\
+				(pin), (val))
+#define airoha_pinctrl_set_pullup_conf(pinctrl, pin, val)			\
+	airoha_pinctrl_set_conf((pinctrl), airoha_pinctrl_pullup_conf,		\
+				ARRAY_SIZE(airoha_pinctrl_pullup_conf),		\
+				(pin), (val))
+#define airoha_pinctrl_set_pulldown_conf(pinctrl, pin, val)			\
+	airoha_pinctrl_set_conf((pinctrl), airoha_pinctrl_pulldown_conf,	\
+				ARRAY_SIZE(airoha_pinctrl_pulldown_conf),	\
+				(pin), (val))
+#define airoha_pinctrl_set_drive_e2_conf(pinctrl, pin, val)			\
+	airoha_pinctrl_set_conf((pinctrl), airoha_pinctrl_drive_e2_conf,	\
+				ARRAY_SIZE(airoha_pinctrl_drive_e2_conf),	\
+				(pin), (val))
+#define airoha_pinctrl_set_drive_e4_conf(pinctrl, pin, val)			\
+	airoha_pinctrl_set_conf((pinctrl), airoha_pinctrl_drive_e4_conf,	\
+				ARRAY_SIZE(airoha_pinctrl_drive_e4_conf),	\
+				(pin), (val))
+#define airoha_pinctrl_set_pcie_rst_od_conf(pinctrl, pin, val)			\
+	airoha_pinctrl_set_conf((pinctrl), airoha_pinctrl_pcie_rst_od_conf,	\
+				ARRAY_SIZE(airoha_pinctrl_pcie_rst_od_conf),	\
+				(pin), (val))
+
+static int airoha_pinconf_get_direction(struct pinctrl_dev *pctrl_dev, u32 p)
+{
+	struct airoha_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctrl_dev);
+	u32 val, mask;
+	int err, pin;
+	u8 index;
+
+	pin = airoha_convert_pin_to_reg_offset(pctrl_dev, NULL, p);
+	if (pin < 0)
+		return pin;
+
+	index = pin / AIROHA_REG_GPIOCTRL_NUM_PIN;
+	err = regmap_read(pinctrl->regmap, pinctrl->gpiochip.dir[index], &val);
+	if (err)
+		return err;
+
+	mask = BIT(2 * (pin % AIROHA_REG_GPIOCTRL_NUM_PIN));
+	return val & mask ? PIN_CONFIG_OUTPUT_ENABLE : PIN_CONFIG_INPUT_ENABLE;
+}
+
+static int airoha_pinconf_get(struct pinctrl_dev *pctrl_dev,
+			      unsigned int pin, unsigned long *config)
+{
+	struct airoha_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctrl_dev);
+	enum pin_config_param param = pinconf_to_config_param(*config);
+	u32 arg;
+
+	switch (param) {
+	case PIN_CONFIG_BIAS_PULL_DOWN:
+	case PIN_CONFIG_BIAS_DISABLE:
+	case PIN_CONFIG_BIAS_PULL_UP: {
+		u32 pull_up, pull_down;
+
+		if (airoha_pinctrl_get_pullup_conf(pinctrl, pin, &pull_up) ||
+		    airoha_pinctrl_get_pulldown_conf(pinctrl, pin, &pull_down))
+			return -EINVAL;
+
+		if (param == PIN_CONFIG_BIAS_PULL_UP &&
+		    !(pull_up && !pull_down))
+			return -EINVAL;
+		else if (param == PIN_CONFIG_BIAS_PULL_DOWN &&
+			 !(pull_down && !pull_up))
+			return -EINVAL;
+		else if (pull_up || pull_down)
+			return -EINVAL;
+
+		arg = 1;
+		break;
+	}
+	case PIN_CONFIG_DRIVE_STRENGTH: {
+		u32 e2, e4;
+
+		if (airoha_pinctrl_get_drive_e2_conf(pinctrl, pin, &e2) ||
+		    airoha_pinctrl_get_drive_e4_conf(pinctrl, pin, &e4))
+			return -EINVAL;
+
+		arg = e4 << 1 | e2;
+		break;
+	}
+	case PIN_CONFIG_DRIVE_OPEN_DRAIN:
+		if (airoha_pinctrl_get_pcie_rst_od_conf(pinctrl, pin, &arg))
+			return -EINVAL;
+		break;
+	case PIN_CONFIG_OUTPUT_ENABLE:
+	case PIN_CONFIG_INPUT_ENABLE:
+		arg = airoha_pinconf_get_direction(pctrl_dev, pin);
+		if (arg != param)
+			return -EINVAL;
+
+		arg = 1;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	*config = pinconf_to_config_packed(param, arg);
+
+	return 0;
+}
+
+static int airoha_pinconf_set_pin_value(struct pinctrl_dev *pctrl_dev,
+					unsigned int p, bool value)
+{
+	struct airoha_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctrl_dev);
+	int pin;
+
+	pin = airoha_convert_pin_to_reg_offset(pctrl_dev, NULL, p);
+	if (pin < 0)
+		return pin;
+
+	airoha_gpio_set(&pinctrl->gpiochip.chip, pin, value);
+
+	return 0;
+}
+
+static int airoha_pinconf_set(struct pinctrl_dev *pctrl_dev,
+			      unsigned int pin, unsigned long *configs,
+			      unsigned int num_configs)
+{
+	struct airoha_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctrl_dev);
+	int i;
+
+	for (i = 0; i < num_configs; i++) {
+		u32 param = pinconf_to_config_param(configs[i]);
+		u32 arg = pinconf_to_config_argument(configs[i]);
+
+		switch (param) {
+		case PIN_CONFIG_BIAS_DISABLE:
+			airoha_pinctrl_set_pulldown_conf(pinctrl, pin, 0);
+			airoha_pinctrl_set_pullup_conf(pinctrl, pin, 0);
+			break;
+		case PIN_CONFIG_BIAS_PULL_UP:
+			airoha_pinctrl_set_pulldown_conf(pinctrl, pin, 0);
+			airoha_pinctrl_set_pullup_conf(pinctrl, pin, 1);
+			break;
+		case PIN_CONFIG_BIAS_PULL_DOWN:
+			airoha_pinctrl_set_pulldown_conf(pinctrl, pin, 1);
+			airoha_pinctrl_set_pullup_conf(pinctrl, pin, 0);
+			break;
+		case PIN_CONFIG_DRIVE_STRENGTH: {
+			u32 e2 = 0, e4 = 0;
+
+			switch (arg) {
+			case MTK_DRIVE_2mA:
+				break;
+			case MTK_DRIVE_4mA:
+				e2 = 1;
+				break;
+			case MTK_DRIVE_6mA:
+				e4 = 1;
+				break;
+			case MTK_DRIVE_8mA:
+				e2 = 1;
+				e4 = 1;
+				break;
+			default:
+				return -EINVAL;
+			}
+
+			airoha_pinctrl_set_drive_e2_conf(pinctrl, pin, e2);
+			airoha_pinctrl_set_drive_e4_conf(pinctrl, pin, e4);
+			break;
+		}
+		case PIN_CONFIG_DRIVE_OPEN_DRAIN:
+			airoha_pinctrl_set_pcie_rst_od_conf(pinctrl, pin, !!arg);
+			break;
+		case PIN_CONFIG_OUTPUT_ENABLE:
+		case PIN_CONFIG_INPUT_ENABLE:
+		case PIN_CONFIG_OUTPUT: {
+			bool input = param == PIN_CONFIG_INPUT_ENABLE;
+			int err;
+
+			err = airoha_pinmux_set_direction(pctrl_dev, NULL, pin,
+							  input);
+			if (err)
+				return err;
+
+			if (param == PIN_CONFIG_OUTPUT) {
+				err = airoha_pinconf_set_pin_value(pctrl_dev,
+								   pin, !!arg);
+				if (err)
+					return err;
+			}
+			break;
+		}
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static int airoha_pinconf_group_get(struct pinctrl_dev *pctrl_dev,
+				    unsigned int group, unsigned long *config)
+{
+	u32 cur_config = 0;
+	int i;
+
+	for (i = 0; i < airoha_pinctrl_groups[group].npins; i++) {
+		if (airoha_pinconf_get(pctrl_dev,
+				       airoha_pinctrl_groups[group].pins[i],
+				       config))
+			return -EOPNOTSUPP;
+
+		if (i && cur_config != *config)
+			return -EOPNOTSUPP;
+
+		cur_config = *config;
+	}
+
+	return 0;
+}
+
+static int airoha_pinconf_group_set(struct pinctrl_dev *pctrl_dev,
+				    unsigned int group, unsigned long *configs,
+				    unsigned int num_configs)
+{
+	int i;
+
+	for (i = 0; i < airoha_pinctrl_groups[group].npins; i++) {
+		int err;
+
+		err = airoha_pinconf_set(pctrl_dev,
+					 airoha_pinctrl_groups[group].pins[i],
+					 configs, num_configs);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static const struct pinconf_ops airoha_confops = {
+	.is_generic = true,
+	.pin_config_get = airoha_pinconf_get,
+	.pin_config_set = airoha_pinconf_set,
+	.pin_config_group_get = airoha_pinconf_group_get,
+	.pin_config_group_set = airoha_pinconf_group_set,
+	.pin_config_config_dbg_show = pinconf_generic_dump_config,
+};
+
+static const struct pinctrl_ops airoha_pctlops = {
+	.get_groups_count = pinctrl_generic_get_group_count,
+	.get_group_name = pinctrl_generic_get_group_name,
+	.get_group_pins = pinctrl_generic_get_group_pins,
+	.dt_node_to_map = pinconf_generic_dt_node_to_map_all,
+	.dt_free_map = pinconf_generic_dt_free_map,
+};
+
+static struct pinctrl_desc airoha_pinctrl_desc = {
+	.name = KBUILD_MODNAME,
+	.owner = THIS_MODULE,
+	.pctlops = &airoha_pctlops,
+	.pmxops = &airoha_pmxops,
+	.confops = &airoha_confops,
+	.pins = airoha_pinctrl_pins,
+	.npins = ARRAY_SIZE(airoha_pinctrl_pins),
+};
+
+static int airoha_pinctrl_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct airoha_pinctrl *pinctrl;
+	struct regmap *map;
+	int err, i;
+
+	pinctrl = devm_kzalloc(dev, sizeof(*pinctrl), GFP_KERNEL);
+	if (!pinctrl)
+		return -ENOMEM;
+
+	pinctrl->regmap = device_node_to_regmap(dev->parent->of_node);
+	if (IS_ERR(pinctrl->regmap))
+		return PTR_ERR(pinctrl->regmap);
+
+	map = syscon_regmap_lookup_by_compatible("airoha,en7581-chip-scu");
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	pinctrl->chip_scu = map;
+
+	err = devm_pinctrl_register_and_init(dev, &airoha_pinctrl_desc,
+					     pinctrl, &pinctrl->ctrl);
+	if (err)
+		return err;
+
+	/* build pin groups */
+	for (i = 0; i < ARRAY_SIZE(airoha_pinctrl_groups); i++) {
+		const struct pingroup *grp = &airoha_pinctrl_groups[i];
+
+		err = pinctrl_generic_add_group(pinctrl->ctrl, grp->name,
+						grp->pins, grp->npins,
+						(void *)grp);
+		if (err < 0) {
+			dev_err(&pdev->dev, "Failed to register group %s\n",
+				grp->name);
+			return err;
+		}
+	}
+
+	/* build functions */
+	for (i = 0; i < ARRAY_SIZE(airoha_pinctrl_funcs); i++) {
+		const struct airoha_pinctrl_func *func;
+
+		func = &airoha_pinctrl_funcs[i];
+		err = pinmux_generic_add_function(pinctrl->ctrl,
+						  func->desc.func.name,
+						  func->desc.func.groups,
+						  func->desc.func.ngroups,
+						  (void *)func);
+		if (err < 0) {
+			dev_err(dev, "Failed to register function %s\n",
+				func->desc.func.name);
+			return err;
+		}
+	}
+
+	err = pinctrl_enable(pinctrl->ctrl);
+	if (err)
+		return err;
+
+	/* build gpio-chip */
+	return airoha_pinctrl_add_gpiochip(pinctrl, pdev);
+}
+
+static const struct of_device_id airoha_pinctrl_of_match[] = {
+	{ .compatible = "airoha,en7581-pinctrl" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, airoha_pinctrl_of_match);
+
+static struct platform_driver airoha_pinctrl_driver = {
+	.probe = airoha_pinctrl_probe,
+	.driver = {
+		.name = "pinctrl-airoha",
+		.of_match_table = airoha_pinctrl_of_match,
+	},
+};
+module_platform_driver(airoha_pinctrl_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_AUTHOR("Benjamin Larsson <benjamin.larsson@genexis.eu>");
+MODULE_AUTHOR("Markus Gothe <markus.gothe@genexis.eu>");
+MODULE_DESCRIPTION("Pinctrl driver for Airoha SoC");

From bbee049d8ee21f33ef68d02b16763ae7e5bf9025 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 28 Sep 2024 11:52:46 +0200
Subject: [PATCH 0707/1530] kvm/vfio: Constify struct kvm_device_ops

'struct kvm_device_ops' is not modified in this driver.

Constifying this structure moves some data to a read-only section, so
increases overall security, especially when the structure holds some
function pointers.

On a x86_64, with allmodconfig:
Before:
======
   text	   data	    bss	    dec	    hex	filename
   2605	    169	     16	   2790	    ae6	virt/kvm/vfio.o

After:
=====
   text	   data	    bss	    dec	    hex	filename
   2685	     89	     16	   2790	    ae6	virt/kvm/vfio.o

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/e7361a1bb7defbb0f7056b884e83f8d75ac9fe21.1727517084.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 virt/kvm/vfio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index 388ae471d2584..e72a6a1d5a200 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -353,7 +353,7 @@ static void kvm_vfio_release(struct kvm_device *dev)
 
 static int kvm_vfio_create(struct kvm_device *dev, u32 type);
 
-static struct kvm_device_ops kvm_vfio_ops = {
+static const struct kvm_device_ops kvm_vfio_ops = {
 	.name = "kvm-vfio",
 	.create = kvm_vfio_create,
 	.release = kvm_vfio_release,

From 12cd88a9116acf79416a39adcd8bb1337ae7cee1 Mon Sep 17 00:00:00 2001
From: Ankit Agrawal <ankita@nvidia.com>
Date: Sun, 13 Oct 2024 07:52:16 +0000
Subject: [PATCH 0708/1530] vfio/nvgrace-gpu: Add a new GH200 SKU to the devid
 table

NVIDIA is planning to productize a new Grace Hopper superchip
SKU with device ID 0x2348.

Add the SKU devid to nvgrace_gpu_vfio_pci_table.

Signed-off-by: Ankit Agrawal <ankita@nvidia.com>
Link: https://lore.kernel.org/r/20241013075216.19229-1-ankita@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/nvgrace-gpu/main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c
index a7fd018aa5483..a467085038f0c 100644
--- a/drivers/vfio/pci/nvgrace-gpu/main.c
+++ b/drivers/vfio/pci/nvgrace-gpu/main.c
@@ -866,6 +866,8 @@ static const struct pci_device_id nvgrace_gpu_vfio_pci_table[] = {
 	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2342) },
 	/* GH200 480GB */
 	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2345) },
+	/* GH200 SKU */
+	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2348) },
 	{}
 };
 

From 9283b7392570421c22a6c8058614f5b76a46b81c Mon Sep 17 00:00:00 2001
From: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Date: Mon, 21 Oct 2024 13:37:53 +0100
Subject: [PATCH 0709/1530] vfio/qat: fix overflow check in
 qat_vf_resume_write()

The unsigned variable `size_t len` is cast to the signed type `loff_t`
when passed to the function check_add_overflow(). This function considers
the type of the destination, which is of type loff_t (signed),
potentially leading to an overflow. This issue is similar to the one
described in the link below.

Remove the cast.

Note that even if check_add_overflow() is bypassed, by setting `len` to
a value that is greater than LONG_MAX (which is considered as a negative
value after the cast), the function copy_from_user(), invoked a few lines
later, will not perform any copy and return `len` as (len > INT_MAX)
causing qat_vf_resume_write() to fail with -EFAULT.

Fixes: bb208810b1ab ("vfio/qat: Add vfio_pci driver for Intel QAT SR-IOV VF devices")
CC: stable@vger.kernel.org # 6.10+
Link: https://lore.kernel.org/all/138bd2e2-ede8-4bcc-aa7b-f3d9de167a37@moroto.mountain
Reported-by: Zijie Zhao <zzjas98@gmail.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Xin Zeng <xin.zeng@intel.com>
Link: https://lore.kernel.org/r/20241021123843.42979-1-giovanni.cabiddu@intel.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/qat/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/qat/main.c b/drivers/vfio/pci/qat/main.c
index be3644ced17be..c78cb6de93906 100644
--- a/drivers/vfio/pci/qat/main.c
+++ b/drivers/vfio/pci/qat/main.c
@@ -304,7 +304,7 @@ static ssize_t qat_vf_resume_write(struct file *filp, const char __user *buf,
 	offs = &filp->f_pos;
 
 	if (*offs < 0 ||
-	    check_add_overflow((loff_t)len, *offs, &end))
+	    check_add_overflow(len, *offs, &end))
 		return -EOVERFLOW;
 
 	if (end > mig_dev->state_size)

From d9d959c36bec59f11c0eb6b5308729e3c4901b5e Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 30 Oct 2024 12:27:34 +0100
Subject: [PATCH 0710/1530] PCI: Make pcim_request_all_regions() a public
 function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In order to remove the deprecated function
pcim_iomap_regions_request_all(), a few drivers need an interface to
request all BARs a PCI device offers.

Make pcim_request_all_regions() a public interface.

Link: https://lore.kernel.org/r/20241030112743.104395-2-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/pci/devres.c | 3 ++-
 include/linux/pci.h  | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c
index b133967faef84..2a64da5c91fb9 100644
--- a/drivers/pci/devres.c
+++ b/drivers/pci/devres.c
@@ -939,7 +939,7 @@ static void pcim_release_all_regions(struct pci_dev *pdev)
  * desired, release individual regions with pcim_release_region() or all of
  * them at once with pcim_release_all_regions().
  */
-static int pcim_request_all_regions(struct pci_dev *pdev, const char *name)
+int pcim_request_all_regions(struct pci_dev *pdev, const char *name)
 {
 	int ret;
 	int bar;
@@ -957,6 +957,7 @@ static int pcim_request_all_regions(struct pci_dev *pdev, const char *name)
 
 	return ret;
 }
+EXPORT_SYMBOL(pcim_request_all_regions);
 
 /**
  * pcim_iomap_regions_request_all - Request all BARs and iomap specified ones
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 573b4c4c2be61..3b151c8331e59 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2293,6 +2293,7 @@ static inline void pci_fixup_device(enum pci_fixup_pass pass,
 				    struct pci_dev *dev) { }
 #endif
 
+int pcim_request_all_regions(struct pci_dev *pdev, const char *name);
 void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen);
 void __iomem *pcim_iomap_region(struct pci_dev *pdev, int bar,
 				const char *name);

From bdcddd0cdc39dab62813bad760905f69918d7a85 Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 30 Oct 2024 12:27:35 +0100
Subject: [PATCH 0711/1530] ata: ahci: Replace deprecated PCI functions

pcim_iomap_regions_request_all() and pcim_iomap_table() have been
deprecated by the PCI subsystem in commit e354bb84a4c1 ("PCI: Deprecate
pcim_iomap_table(), pcim_iomap_regions_request_all()").

Replace these functions with their successors, pcim_iomap() and
pcim_request_all_regions().

Link: https://lore.kernel.org/r/20241030112743.104395-3-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Damien Le Moal <dlemoal@kernel.org>
---
 drivers/ata/acard-ahci.c | 6 ++++--
 drivers/ata/ahci.c       | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c
index 547f563417057..3999305b53560 100644
--- a/drivers/ata/acard-ahci.c
+++ b/drivers/ata/acard-ahci.c
@@ -370,7 +370,7 @@ static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id
 	/* AHCI controllers often implement SFF compatible interface.
 	 * Grab all PCI BARs just in case.
 	 */
-	rc = pcim_iomap_regions_request_all(pdev, 1 << AHCI_PCI_BAR, DRV_NAME);
+	rc = pcim_request_all_regions(pdev, DRV_NAME);
 	if (rc == -EBUSY)
 		pcim_pin_device(pdev);
 	if (rc)
@@ -386,7 +386,9 @@ static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id
 	if (!(hpriv->flags & AHCI_HFLAG_NO_MSI))
 		pci_enable_msi(pdev);
 
-	hpriv->mmio = pcim_iomap_table(pdev)[AHCI_PCI_BAR];
+	hpriv->mmio = pcim_iomap(pdev, AHCI_PCI_BAR, 0);
+	if (!hpriv->mmio)
+		return -ENOMEM;
 
 	/* save initial config */
 	ahci_save_initial_config(&pdev->dev, hpriv);
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 45f63b09828a1..2043dfb52ae8c 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1869,7 +1869,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* AHCI controllers often implement SFF compatible interface.
 	 * Grab all PCI BARs just in case.
 	 */
-	rc = pcim_iomap_regions_request_all(pdev, 1 << ahci_pci_bar, DRV_NAME);
+	rc = pcim_request_all_regions(pdev, DRV_NAME);
 	if (rc == -EBUSY)
 		pcim_pin_device(pdev);
 	if (rc)
@@ -1893,7 +1893,9 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ahci_sb600_enable_64bit(pdev))
 		hpriv->flags &= ~AHCI_HFLAG_32BIT_ONLY;
 
-	hpriv->mmio = pcim_iomap_table(pdev)[ahci_pci_bar];
+	hpriv->mmio = pcim_iomap(pdev, ahci_pci_bar, 0);
+	if (!hpriv->mmio)
+		return -ENOMEM;
 
 	/* detect remapped nvme devices */
 	ahci_remap_check(pdev, ahci_pci_bar, hpriv);

From 86d17afd1a9fbb57b56035a86936f9cc7817674e Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 30 Oct 2024 12:27:36 +0100
Subject: [PATCH 0712/1530] crypto: qat - replace deprecated PCI functions

pcim_iomap_table() and pcim_iomap_regions_request_all() have been
deprecated by the PCI subsystem in commit e354bb84a4c1 ("PCI: Deprecate
pcim_iomap_table(), pcim_iomap_regions_request_all()").

Replace these functions with their successors, pcim_iomap() and
pcim_request_all_regions().

Link: https://lore.kernel.org/r/20241030112743.104395-4-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
---
 drivers/crypto/intel/qat/qat_420xx/adf_drv.c | 11 ++++++++---
 drivers/crypto/intel/qat/qat_4xxx/adf_drv.c  | 11 ++++++++---
 2 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/crypto/intel/qat/qat_420xx/adf_drv.c b/drivers/crypto/intel/qat/qat_420xx/adf_drv.c
index f49818a13013a..788a11cdb34b5 100644
--- a/drivers/crypto/intel/qat/qat_420xx/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_420xx/adf_drv.c
@@ -129,16 +129,21 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Find and map all the device's BARS */
 	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM) & ADF_GEN4_BAR_MASK;
 
-	ret = pcim_iomap_regions_request_all(pdev, bar_mask, pci_name(pdev));
+	ret = pcim_request_all_regions(pdev, pci_name(pdev));
 	if (ret) {
-		dev_err(&pdev->dev, "Failed to map pci regions.\n");
+		dev_err(&pdev->dev, "Failed to request PCI regions.\n");
 		goto out_err;
 	}
 
 	i = 0;
 	for_each_set_bit(bar_nr, &bar_mask, PCI_STD_NUM_BARS) {
 		bar = &accel_pci_dev->pci_bars[i++];
-		bar->virt_addr = pcim_iomap_table(pdev)[bar_nr];
+		bar->virt_addr = pcim_iomap(pdev, bar_nr, 0);
+		if (!bar->virt_addr) {
+			dev_err(&pdev->dev, "Failed to ioremap PCI region.\n");
+			ret = -ENOMEM;
+			goto out_err;
+		}
 	}
 
 	pci_set_master(pdev);
diff --git a/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c b/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c
index 659905e459503..115eabfd1f6ba 100644
--- a/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c
@@ -131,16 +131,21 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Find and map all the device's BARS */
 	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM) & ADF_GEN4_BAR_MASK;
 
-	ret = pcim_iomap_regions_request_all(pdev, bar_mask, pci_name(pdev));
+	ret = pcim_request_all_regions(pdev, pci_name(pdev));
 	if (ret) {
-		dev_err(&pdev->dev, "Failed to map pci regions.\n");
+		dev_err(&pdev->dev, "Failed to request PCI regions.\n");
 		goto out_err;
 	}
 
 	i = 0;
 	for_each_set_bit(bar_nr, &bar_mask, PCI_STD_NUM_BARS) {
 		bar = &accel_pci_dev->pci_bars[i++];
-		bar->virt_addr = pcim_iomap_table(pdev)[bar_nr];
+		bar->virt_addr = pcim_iomap(pdev, bar_nr, 0);
+		if (!bar->virt_addr) {
+			dev_err(&pdev->dev, "Failed to ioremap PCI region.\n");
+			ret = -ENOMEM;
+			goto out_err;
+		}
 	}
 
 	pci_set_master(pdev);

From cf43d998fd9b0dbfafecdfeaae0b70c2862b810a Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 30 Oct 2024 12:27:37 +0100
Subject: [PATCH 0713/1530] crypto: marvell - replace deprecated PCI functions

pcim_iomap_table() and pcim_iomap_regions_request_all() have been
deprecated by the PCI subsystem in commit e354bb84a4c1 ("PCI: Deprecate
pcim_iomap_table(), pcim_iomap_regions_request_all()").

Replace these functions with their successors, pcim_iomap() and
pcim_request_all_regions().

Link: https://lore.kernel.org/r/20241030112743.104395-5-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Bharat Bhushan <bbhushan2@marvell.com>
---
 drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c | 14 +++++++++-----
 drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c | 13 +++++++++----
 2 files changed, 18 insertions(+), 9 deletions(-)

diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c
index 400e36d9908f4..94d0e73e42de1 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c
@@ -739,18 +739,22 @@ static int otx2_cptpf_probe(struct pci_dev *pdev,
 		dev_err(dev, "Unable to get usable DMA configuration\n");
 		goto clear_drvdata;
 	}
-	/* Map PF's configuration registers */
-	err = pcim_iomap_regions_request_all(pdev, 1 << PCI_PF_REG_BAR_NUM,
-					     OTX2_CPT_DRV_NAME);
+	err = pcim_request_all_regions(pdev, OTX2_CPT_DRV_NAME);
 	if (err) {
-		dev_err(dev, "Couldn't get PCI resources 0x%x\n", err);
+		dev_err(dev, "Couldn't request PCI resources 0x%x\n", err);
 		goto clear_drvdata;
 	}
 	pci_set_master(pdev);
 	pci_set_drvdata(pdev, cptpf);
 	cptpf->pdev = pdev;
 
-	cptpf->reg_base = pcim_iomap_table(pdev)[PCI_PF_REG_BAR_NUM];
+	/* Map PF's configuration registers */
+	cptpf->reg_base = pcim_iomap(pdev, PCI_PF_REG_BAR_NUM, 0);
+	if (!cptpf->reg_base) {
+		err = -ENOMEM;
+		dev_err(dev, "Couldn't ioremap PCI resource 0x%x\n", err);
+		goto clear_drvdata;
+	}
 
 	/* Check if AF driver is up, otherwise defer probe */
 	err = cpt_is_pf_usable(cptpf);
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c
index 527d34cc258b4..d0b6ee901f620 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c
@@ -358,9 +358,8 @@ static int otx2_cptvf_probe(struct pci_dev *pdev,
 		dev_err(dev, "Unable to get usable DMA configuration\n");
 		goto clear_drvdata;
 	}
-	/* Map VF's configuration registers */
-	ret = pcim_iomap_regions_request_all(pdev, 1 << PCI_PF_REG_BAR_NUM,
-					     OTX2_CPTVF_DRV_NAME);
+
+	ret = pcim_request_all_regions(pdev, OTX2_CPTVF_DRV_NAME);
 	if (ret) {
 		dev_err(dev, "Couldn't get PCI resources 0x%x\n", ret);
 		goto clear_drvdata;
@@ -369,7 +368,13 @@ static int otx2_cptvf_probe(struct pci_dev *pdev,
 	pci_set_drvdata(pdev, cptvf);
 	cptvf->pdev = pdev;
 
-	cptvf->reg_base = pcim_iomap_table(pdev)[PCI_PF_REG_BAR_NUM];
+	/* Map VF's configuration registers */
+	cptvf->reg_base = pcim_iomap(pdev, PCI_PF_REG_BAR_NUM, 0);
+	if (!cptvf->reg_base) {
+		ret = -ENOMEM;
+		dev_err(dev, "Couldn't ioremap PCI resource 0x%x\n", ret);
+		goto clear_drvdata;
+	}
 
 	otx2_cpt_set_hw_caps(pdev, &cptvf->cap_flag);
 

From abbc299c71aa1ff118c48b392d1235122884c85a Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 30 Oct 2024 12:27:38 +0100
Subject: [PATCH 0714/1530] intel_th: pci: Replace deprecated PCI functions

pcim_iomap_table() and pcim_iomap_regions_request_all() have been
deprecated by the PCI subsystem in commit e354bb84a4c1 ("PCI: Deprecate
pcim_iomap_table(), pcim_iomap_regions_request_all()").

Replace these functions with their successors, pcim_iomap() and
pcim_request_all_regions().

Link: https://lore.kernel.org/r/20241030112743.104395-6-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
---
 drivers/hwtracing/intel_th/pci.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 0d7b9839e5b66..e9d8d28e055f3 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -23,7 +23,6 @@ enum {
 	TH_PCI_RTIT_BAR		= 4,
 };
 
-#define BAR_MASK (BIT(TH_PCI_CONFIG_BAR) | BIT(TH_PCI_STH_SW_BAR))
 
 #define PCI_REG_NPKDSC	0x80
 #define NPKDSC_TSACT	BIT(5)
@@ -83,10 +82,16 @@ static int intel_th_pci_probe(struct pci_dev *pdev,
 	if (err)
 		return err;
 
-	err = pcim_iomap_regions_request_all(pdev, BAR_MASK, DRIVER_NAME);
+	err = pcim_request_all_regions(pdev, DRIVER_NAME);
 	if (err)
 		return err;
 
+	if (!pcim_iomap(pdev, TH_PCI_CONFIG_BAR, 0))
+		return -ENOMEM;
+
+	if (!pcim_iomap(pdev, TH_PCI_STH_SW_BAR, 0))
+		return -ENOMEM;
+
 	if (pdev->resource[TH_PCI_RTIT_BAR].start) {
 		resource[TH_MMIO_RTIT] = pdev->resource[TH_PCI_RTIT_BAR];
 		r++;

From 3dd6ed25a90cf3fa0e414afe8c42d28de4a05928 Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 30 Oct 2024 12:27:39 +0100
Subject: [PATCH 0715/1530] wifi: iwlwifi: replace deprecated PCI functions

pcim_iomap_table() and pcim_iomap_regions_request_all() have been
deprecated by the PCI subsystem in commit e354bb84a4c1 ("PCI: Deprecate
pcim_iomap_table(), pcim_iomap_regions_request_all()").

Replace these functions with their successors, pcim_iomap() and
pcim_request_all_regions().

Link: https://lore.kernel.org/r/20241030112743.104395-7-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Kalle Valo <kvalo@kernel.org>
---
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 3b9943eb69341..4839dcb199c45 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -3533,7 +3533,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 	struct iwl_trans_pcie *trans_pcie, **priv;
 	struct iwl_trans *trans;
 	int ret, addr_size;
-	void __iomem * const *table;
 	u32 bar0;
 
 	/* reassign our BAR 0 if invalid due to possible runtime PM races */
@@ -3659,22 +3658,15 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 		}
 	}
 
-	ret = pcim_iomap_regions_request_all(pdev, BIT(0), DRV_NAME);
+	ret = pcim_request_all_regions(pdev, DRV_NAME);
 	if (ret) {
-		dev_err(&pdev->dev, "pcim_iomap_regions_request_all failed\n");
+		dev_err(&pdev->dev, "Requesting all PCI BARs failed.\n");
 		goto out_no_pci;
 	}
 
-	table = pcim_iomap_table(pdev);
-	if (!table) {
-		dev_err(&pdev->dev, "pcim_iomap_table failed\n");
-		ret = -ENOMEM;
-		goto out_no_pci;
-	}
-
-	trans_pcie->hw_base = table[0];
+	trans_pcie->hw_base = pcim_iomap(pdev, 0, 0);
 	if (!trans_pcie->hw_base) {
-		dev_err(&pdev->dev, "couldn't find IO mem in first BAR\n");
+		dev_err(&pdev->dev, "Could not ioremap PCI BAR 0.\n");
 		ret = -ENODEV;
 		goto out_no_pci;
 	}

From 5915997a8eb4b8a8e8aa3b0fe6cb85265822c2ba Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 30 Oct 2024 12:27:40 +0100
Subject: [PATCH 0716/1530] ntb: idt: Replace deprecated PCI functions

pcim_iomap_table() and pcim_iomap_regions_request_all() have been
deprecated by the PCI subsystem in commit e354bb84a4c1 ("PCI: Deprecate
pcim_iomap_table(), pcim_iomap_regions_request_all()").

Replace these functions with their successors, pcim_iomap() and
pcim_request_all_regions().

Link: https://lore.kernel.org/r/20241030112743.104395-8-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Serge Semin <fancer.lancer@gmail.com>
---
 drivers/ntb/hw/idt/ntb_hw_idt.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/ntb/hw/idt/ntb_hw_idt.c b/drivers/ntb/hw/idt/ntb_hw_idt.c
index 6fc9dfe824747..544d8a4d2af59 100644
--- a/drivers/ntb/hw/idt/ntb_hw_idt.c
+++ b/drivers/ntb/hw/idt/ntb_hw_idt.c
@@ -2671,15 +2671,20 @@ static int idt_init_pci(struct idt_ntb_dev *ndev)
 	 */
 	pci_set_master(pdev);
 
-	/* Request all BARs resources and map BAR0 only */
-	ret = pcim_iomap_regions_request_all(pdev, 1, NTB_NAME);
+	/* Request all BARs resources */
+	ret = pcim_request_all_regions(pdev, NTB_NAME);
 	if (ret != 0) {
 		dev_err(&pdev->dev, "Failed to request resources\n");
 		goto err_clear_master;
 	}
 
-	/* Retrieve virtual address of BAR0 - PCI configuration space */
-	ndev->cfgspc = pcim_iomap_table(pdev)[0];
+	/* ioremap BAR0 - PCI configuration space */
+	ndev->cfgspc = pcim_iomap(pdev, 0, 0);
+	if (!ndev->cfgspc) {
+		dev_err(&pdev->dev, "Failed to ioremap BAR 0\n");
+		ret = -ENOMEM;
+		goto err_clear_master;
+	}
 
 	/* Put the IDT driver data pointer to the PCI-device private pointer */
 	pci_set_drvdata(pdev, ndev);

From 55285d8fa2a17c25ae5f4b76df26f2823631baae Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 30 Oct 2024 12:27:41 +0100
Subject: [PATCH 0717/1530] serial: rp2: Replace deprecated PCI functions

pcim_iomap_table() and pcim_iomap_regions_request_all() have been
deprecated by the PCI subsystem in commit e354bb84a4c1 ("PCI: Deprecate
pcim_iomap_table(), pcim_iomap_regions_request_all()").

Replace these functions with their successors, pcim_iomap() and
pcim_request_all_regions().

Link: https://lore.kernel.org/r/20241030112743.104395-9-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
---
 drivers/tty/serial/rp2.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serial/rp2.c b/drivers/tty/serial/rp2.c
index 8bab2aedc4991..6d99a02dd439d 100644
--- a/drivers/tty/serial/rp2.c
+++ b/drivers/tty/serial/rp2.c
@@ -698,7 +698,6 @@ static int rp2_probe(struct pci_dev *pdev,
 	const struct firmware *fw;
 	struct rp2_card *card;
 	struct rp2_uart_port *ports;
-	void __iomem * const *bars;
 	int rc;
 
 	card = devm_kzalloc(&pdev->dev, sizeof(*card), GFP_KERNEL);
@@ -711,13 +710,16 @@ static int rp2_probe(struct pci_dev *pdev,
 	if (rc)
 		return rc;
 
-	rc = pcim_iomap_regions_request_all(pdev, 0x03, DRV_NAME);
+	rc = pcim_request_all_regions(pdev, DRV_NAME);
 	if (rc)
 		return rc;
 
-	bars = pcim_iomap_table(pdev);
-	card->bar0 = bars[0];
-	card->bar1 = bars[1];
+	card->bar0 = pcim_iomap(pdev, 0, 0);
+	if (!card->bar0)
+		return -ENOMEM;
+	card->bar1 = pcim_iomap(pdev, 1, 0);
+	if (!card->bar1)
+		return -ENOMEM;
 	card->pdev = pdev;
 
 	rp2_decode_cap(id, &card->n_ports, &card->smpte);

From bfeb07b8aea64db7538cafd65ee2bf8a810aa2e8 Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 30 Oct 2024 12:27:42 +0100
Subject: [PATCH 0718/1530] ALSA: korg1212: Replace deprecated PCI functions

pcim_iomap_table() and pcim_iomap_regions_request_all() have been
deprecated by the PCI subsystem in commit e354bb84a4c1 ("PCI: Deprecate
pcim_iomap_table(), pcim_iomap_regions_request_all()").

Replace these functions with their successors, pcim_iomap() and
pcim_request_all_regions().

Link: https://lore.kernel.org/r/20241030112743.104395-10-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/korg1212/korg1212.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/sound/pci/korg1212/korg1212.c b/sound/pci/korg1212/korg1212.c
index e62fb1ad6d77c..49b71082c4859 100644
--- a/sound/pci/korg1212/korg1212.c
+++ b/sound/pci/korg1212/korg1212.c
@@ -2108,7 +2108,7 @@ static int snd_korg1212_create(struct snd_card *card, struct pci_dev *pci)
         for (i=0; i<kAudioChannels; i++)
                 korg1212->volumePhase[i] = 0;
 
-	err = pcim_iomap_regions_request_all(pci, 1 << 0, "korg1212");
+	err = pcim_request_all_regions(pci, "korg1212");
 	if (err < 0)
 		return err;
 
@@ -2130,7 +2130,9 @@ static int snd_korg1212_create(struct snd_card *card, struct pci_dev *pci)
 		   korg1212->iomem2, iomem2_size,
 		   stateName[korg1212->cardState]);
 
-	korg1212->iobase = pcim_iomap_table(pci)[0];
+	korg1212->iobase = pcim_iomap(pci, 0, 0);
+	if (!korg1212->iobase)
+		return -ENOMEM;
 
 	err = devm_request_irq(&pci->dev, pci->irq, snd_korg1212_interrupt,
                           IRQF_SHARED,

From 6d9c59212523e719a63575222f1cd1b0aca3da4f Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 30 Oct 2024 12:27:43 +0100
Subject: [PATCH 0719/1530] PCI: Remove pcim_iomap_regions_request_all()

pcim_iomap_regions_request_all() have been deprecated in
commit e354bb84a4c1 ("PCI: Deprecate pcim_iomap_table(),
pcim_iomap_regions_request_all()").

All users of this function have been ported to other interfaces by now.

Remove pcim_iomap_regions_request_all().

Link: https://lore.kernel.org/r/20241030112743.104395-11-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
---
 .../driver-api/driver-model/devres.rst        |  1 -
 drivers/pci/devres.c                          | 56 -------------------
 include/linux/pci.h                           |  2 -
 3 files changed, 59 deletions(-)

diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index 5f2ee8d717b1d..3a30cf4f6c0d6 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -394,7 +394,6 @@ PCI
   pcim_enable_device()		: after success, some PCI ops become managed
   pcim_iomap()			: do iomap() on a single BAR
   pcim_iomap_regions()		: do request_region() and iomap() on multiple BARs
-  pcim_iomap_regions_request_all() : do request_region() on all and iomap() on multiple BARs
   pcim_iomap_table()		: array of mapped addresses indexed by BAR
   pcim_iounmap()		: do iounmap() on a single BAR
   pcim_iounmap_regions()	: do iounmap() and release_region() on multiple BARs
diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c
index 2a64da5c91fb9..319a477a2135b 100644
--- a/drivers/pci/devres.c
+++ b/drivers/pci/devres.c
@@ -959,62 +959,6 @@ int pcim_request_all_regions(struct pci_dev *pdev, const char *name)
 }
 EXPORT_SYMBOL(pcim_request_all_regions);
 
-/**
- * pcim_iomap_regions_request_all - Request all BARs and iomap specified ones
- *			(DEPRECATED)
- * @pdev: PCI device to map IO resources for
- * @mask: Mask of BARs to iomap
- * @name: Name associated with the requests
- *
- * Returns: 0 on success, negative error code on failure.
- *
- * Request all PCI BARs and iomap regions specified by @mask.
- *
- * To release these resources manually, call pcim_release_region() for the
- * regions and pcim_iounmap() for the mappings.
- *
- * This function is DEPRECATED. Don't use it in new code. Instead, use one
- * of the pcim_* region request functions in combination with a pcim_*
- * mapping function.
- */
-int pcim_iomap_regions_request_all(struct pci_dev *pdev, int mask,
-				   const char *name)
-{
-	int bar;
-	int ret;
-	void __iomem **legacy_iomap_table;
-
-	ret = pcim_request_all_regions(pdev, name);
-	if (ret != 0)
-		return ret;
-
-	for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
-		if (!mask_contains_bar(mask, bar))
-			continue;
-		if (!pcim_iomap(pdev, bar, 0))
-			goto err;
-	}
-
-	return 0;
-
-err:
-	/*
-	 * If bar is larger than 0, then pcim_iomap() above has most likely
-	 * failed because of -EINVAL. If it is equal 0, most likely the table
-	 * couldn't be created, indicating -ENOMEM.
-	 */
-	ret = bar > 0 ? -EINVAL : -ENOMEM;
-	legacy_iomap_table = (void __iomem **)pcim_iomap_table(pdev);
-
-	while (--bar >= 0)
-		pcim_iounmap(pdev, legacy_iomap_table[bar]);
-
-	pcim_release_all_regions(pdev);
-
-	return ret;
-}
-EXPORT_SYMBOL(pcim_iomap_regions_request_all);
-
 /**
  * pcim_iounmap_regions - Unmap and release PCI BARs
  * @pdev: PCI device to map IO resources for
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 3b151c8331e59..b59197635c5c5 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2301,8 +2301,6 @@ void pcim_iounmap(struct pci_dev *pdev, void __iomem *addr);
 void __iomem * const *pcim_iomap_table(struct pci_dev *pdev);
 int pcim_request_region(struct pci_dev *pdev, int bar, const char *name);
 int pcim_iomap_regions(struct pci_dev *pdev, int mask, const char *name);
-int pcim_iomap_regions_request_all(struct pci_dev *pdev, int mask,
-				   const char *name);
 void pcim_iounmap_regions(struct pci_dev *pdev, int mask);
 void __iomem *pcim_iomap_range(struct pci_dev *pdev, int bar,
 				unsigned long offset, unsigned long len);

From 4a6afd60733c75369680f4a40c82b7c8528f4a7a Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 16 Oct 2024 11:49:04 +0200
Subject: [PATCH 0720/1530] PCI: Make pcim_iounmap_region() a public function

The function pcim_iounmap_regions() is problematic because it uses a
bitmask mechanism to release / iounmap multiple BARs at once. It, thus,
prevents getting rid of the problematic iomap table mechanism which was
deprecated in commit e354bb84a4c1 ("PCI: Deprecate pcim_iomap_table(),
pcim_iomap_regions_request_all()").

pcim_iounmap_region() does not have that problem. Make it public as the
successor of pcim_iounmap_regions().

Link: https://lore.kernel.org/r/20241016094911.24818-3-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/devres.c | 3 ++-
 include/linux/pci.h  | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c
index 319a477a2135b..fc50d2456aed6 100644
--- a/drivers/pci/devres.c
+++ b/drivers/pci/devres.c
@@ -773,7 +773,7 @@ EXPORT_SYMBOL(pcim_iomap_region);
  * Unmap a BAR and release its region manually. Only pass BARs that were
  * previously mapped by pcim_iomap_region().
  */
-static void pcim_iounmap_region(struct pci_dev *pdev, int bar)
+void pcim_iounmap_region(struct pci_dev *pdev, int bar)
 {
 	struct pcim_addr_devres res_searched;
 
@@ -784,6 +784,7 @@ static void pcim_iounmap_region(struct pci_dev *pdev, int bar)
 	devres_release(&pdev->dev, pcim_addr_resource_release,
 			pcim_addr_resources_match, &res_searched);
 }
+EXPORT_SYMBOL(pcim_iounmap_region);
 
 /**
  * pcim_iomap_regions - Request and iomap PCI BARs (DEPRECATED)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index b59197635c5c5..b8d248c136ba3 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2297,6 +2297,7 @@ int pcim_request_all_regions(struct pci_dev *pdev, const char *name);
 void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen);
 void __iomem *pcim_iomap_region(struct pci_dev *pdev, int bar,
 				const char *name);
+void pcim_iounmap_region(struct pci_dev *pdev, int bar);
 void pcim_iounmap(struct pci_dev *pdev, void __iomem *addr);
 void __iomem * const *pcim_iomap_table(struct pci_dev *pdev);
 int pcim_request_region(struct pci_dev *pdev, int bar, const char *name);

From c7acef99642b763ba585f4a43af999fcdbcc3dc4 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 10 Oct 2024 19:10:34 +0200
Subject: [PATCH 0721/1530] PCI: Fix use-after-free of slot->bus on hot remove

Dennis reports a boot crash on recent Lenovo laptops with a USB4 dock.

Since commit 0fc70886569c ("thunderbolt: Reset USB4 v2 host router") and
commit 59a54c5f3dbd ("thunderbolt: Reset topology created by the boot
firmware"), USB4 v2 and v1 Host Routers are reset on probe of the
thunderbolt driver.

The reset clears the Presence Detect State and Data Link Layer Link Active
bits at the USB4 Host Router's Root Port and thus causes hot removal of the
dock.

The crash occurs when pciehp is unbound from one of the dock's Downstream
Ports:  pciehp creates a pci_slot on bind and destroys it on unbind.  The
pci_slot contains a pointer to the pci_bus below the Downstream Port, but
a reference on that pci_bus is never acquired.  The pci_bus is destroyed
before the pci_slot, so a use-after-free ensues when pci_slot_release()
accesses slot->bus.

In principle this should not happen because pci_stop_bus_device() unbinds
pciehp (and therefore destroys the pci_slot) before the pci_bus is
destroyed by pci_remove_bus_device().

However the stacktrace provided by Dennis shows that pciehp is unbound from
pci_remove_bus_device() instead of pci_stop_bus_device().  To understand
the significance of this, one needs to know that the PCI core uses a two
step process to remove a portion of the hierarchy:  It first unbinds all
drivers in the sub-hierarchy in pci_stop_bus_device() and then actually
removes the devices in pci_remove_bus_device().  There is no precaution to
prevent driver binding in-between pci_stop_bus_device() and
pci_remove_bus_device().

In Dennis' case, it seems removal of the hierarchy by pciehp races with
driver binding by pci_bus_add_devices().  pciehp is bound to the
Downstream Port after pci_stop_bus_device() has run, so it is unbound by
pci_remove_bus_device() instead of pci_stop_bus_device().  Because the
pci_bus has already been destroyed at that point, accesses to it result in
a use-after-free.

One might conclude that driver binding needs to be prevented after
pci_stop_bus_device() has run.  However it seems risky that pci_slot points
to pci_bus without holding a reference.  Solely relying on correct ordering
of driver unbind versus pci_bus destruction is certainly not defensive
programming.

If pci_slot has a need to access data in pci_bus, it ought to acquire a
reference.  Amend pci_create_slot() accordingly.  Dennis reports that the
crash is not reproducible with this change.

Abridged stacktrace:

  pcieport 0000:00:07.0: PME: Signaling with IRQ 156
  pcieport 0000:00:07.0: pciehp: Slot #12 AttnBtn- PwrCtrl- MRL- AttnInd- PwrInd- HotPlug+ Surprise+ Interlock- NoCompl+ IbPresDis- LLActRep+
  pci_bus 0000:20: dev 00, created physical slot 12
  pcieport 0000:00:07.0: pciehp: Slot(12): Card not present
  ...
  pcieport 0000:21:02.0: pciehp: pcie_disable_notification: SLOTCTRL d8 write cmd 0
  Oops: general protection fault, probably for non-canonical address 0x6b6b6b6b6b6b6b6b: 0000 [#1] PREEMPT SMP NOPTI
  CPU: 13 UID: 0 PID: 134 Comm: irq/156-pciehp Not tainted 6.11.0-devel+ #1
  RIP: 0010:dev_driver_string+0x12/0x40
  pci_destroy_slot
  pciehp_remove
  pcie_port_remove_service
  device_release_driver_internal
  bus_remove_device
  device_del
  device_unregister
  remove_iter
  device_for_each_child
  pcie_portdrv_remove
  pci_device_remove
  device_release_driver_internal
  bus_remove_device
  device_del
  pci_remove_bus_device (recursive invocation)
  pci_remove_bus_device
  pciehp_unconfigure_device
  pciehp_disable_slot
  pciehp_handle_presence_or_link_change
  pciehp_ist

Link: https://lore.kernel.org/r/4bfd4c0e976c1776cd08e76603903b338cf25729.1728579288.git.lukas@wunner.de
Reported-by: Dennis Wassenberg <Dennis.Wassenberg@secunet.com>
Closes: https://lore.kernel.org/r/6de4b45ff2b32dd91a805ec02ec8ec73ef411bf6.camel@secunet.com/
Tested-by: Dennis Wassenberg <Dennis.Wassenberg@secunet.com>
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: stable@vger.kernel.org
---
 drivers/pci/slot.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index 0f87cade10f74..ed645c7a4e4b4 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -79,6 +79,7 @@ static void pci_slot_release(struct kobject *kobj)
 	up_read(&pci_bus_sem);
 
 	list_del(&slot->list);
+	pci_bus_put(slot->bus);
 
 	kfree(slot);
 }
@@ -261,7 +262,7 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
 		goto err;
 	}
 
-	slot->bus = parent;
+	slot->bus = pci_bus_get(parent);
 	slot->number = slot_nr;
 
 	slot->kobj.kset = pci_slots_kset;
@@ -269,6 +270,7 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
 	slot_name = make_slot_name(name);
 	if (!slot_name) {
 		err = -ENOMEM;
+		pci_bus_put(slot->bus);
 		kfree(slot);
 		goto err;
 	}

From e1325e19d2256c4724fb465c547333af424e5de5 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Thu, 24 Oct 2024 18:47:08 -0700
Subject: [PATCH 0722/1530] Input: omap-keypad - use guard notation when
 acquiring mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/Zxr4nF-igbrmgq85@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/omap-keypad.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/input/keyboard/omap-keypad.c b/drivers/input/keyboard/omap-keypad.c
index 33df8885b599e..9e13f3f70a81c 100644
--- a/drivers/input/keyboard/omap-keypad.c
+++ b/drivers/input/keyboard/omap-keypad.c
@@ -156,15 +156,15 @@ static ssize_t omap_kp_enable_store(struct device *dev, struct device_attribute
 	if ((state != 1) && (state != 0))
 		return -EINVAL;
 
-	mutex_lock(&kp_enable_mutex);
-	if (state != kp_enable) {
-		if (state)
-			enable_irq(omap_kp->irq);
-		else
-			disable_irq(omap_kp->irq);
-		kp_enable = state;
+	scoped_guard(mutex, &kp_enable_mutex) {
+		if (state != kp_enable) {
+			if (state)
+				enable_irq(omap_kp->irq);
+			else
+				disable_irq(omap_kp->irq);
+			kp_enable = state;
+		}
 	}
-	mutex_unlock(&kp_enable_mutex);
 
 	return strnlen(buf, count);
 }

From 8c0d1202bad3aa6e40fb078dc08158f0bb4e03e2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn@rivosinc.com>
Date: Thu, 24 Oct 2024 12:03:51 -0700
Subject: [PATCH 0723/1530] perf, riscv: Wire up perf trace support for RISC-V
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

RISC-V does not currently support perf trace, since the system call
table is not generated.

Perform the copy/paste exercise, wiring up RISC-V system call table
generation.

Signed-off-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: linux-riscv@lists.infradead.org
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Link: https://lore.kernel.org/r/20241024190353.46737-1-bjorn@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Makefile.config                    |  6 ++-
 tools/perf/arch/riscv/Makefile                | 22 +++++++++
 .../arch/riscv/entry/syscalls/mksyscalltbl    | 47 +++++++++++++++++++
 tools/perf/util/syscalltbl.c                  |  4 ++
 4 files changed, 78 insertions(+), 1 deletion(-)
 create mode 100755 tools/perf/arch/riscv/entry/syscalls/mksyscalltbl

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index b93ed2b7623f9..854f84e802562 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -31,7 +31,7 @@ $(call detected_var,SRCARCH)
 ifneq ($(NO_SYSCALL_TABLE),1)
   NO_SYSCALL_TABLE := 1
 
-  ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 powerpc arm64 s390 mips loongarch))
+  ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 powerpc arm64 s390 mips loongarch riscv))
     NO_SYSCALL_TABLE := 0
   endif
 
@@ -83,6 +83,10 @@ ifeq ($(ARCH),mips)
   LIBUNWIND_LIBS = -lunwind -lunwind-mips
 endif
 
+ifeq ($(ARCH),riscv)
+  CFLAGS += -I$(OUTPUT)arch/riscv/include/generated
+endif
+
 # So far there's only x86 and arm libdw unwind support merged in perf.
 # Disable it on all other architectures in case libdw unwind
 # support is detected in system. Add supported architectures
diff --git a/tools/perf/arch/riscv/Makefile b/tools/perf/arch/riscv/Makefile
index 4664a78a1afd4..00573af87a681 100644
--- a/tools/perf/arch/riscv/Makefile
+++ b/tools/perf/arch/riscv/Makefile
@@ -4,3 +4,25 @@ endif
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 PERF_HAVE_JITDUMP := 1
 HAVE_KVM_STAT_SUPPORT := 1
+
+#
+# Syscall table generation for perf
+#
+
+out    := $(OUTPUT)arch/riscv/include/generated/asm
+header := $(out)/syscalls.c
+incpath := $(srctree)/tools
+sysdef := $(srctree)/tools/arch/riscv/include/uapi/asm/unistd.h
+sysprf := $(srctree)/tools/perf/arch/riscv/entry/syscalls/
+systbl := $(sysprf)/mksyscalltbl
+
+# Create output directory if not already present
+$(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header): $(sysdef) $(systbl)
+	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@
+
+clean::
+	$(call QUIET_CLEAN, riscv) $(RM) $(header)
+
+archheaders: $(header)
diff --git a/tools/perf/arch/riscv/entry/syscalls/mksyscalltbl b/tools/perf/arch/riscv/entry/syscalls/mksyscalltbl
new file mode 100755
index 0000000000000..c59f5e852b977
--- /dev/null
+++ b/tools/perf/arch/riscv/entry/syscalls/mksyscalltbl
@@ -0,0 +1,47 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table for perf. Derived from
+# powerpc script.
+#
+# Copyright IBM Corp. 2017
+# Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
+# Changed by: Kim Phillips <kim.phillips@arm.com>
+# Changed by: Björn Töpel <bjorn@rivosinc.com>
+
+gcc=$1
+hostcc=$2
+incpath=$3
+input=$4
+
+if ! test -r $input; then
+	echo "Could not read input file" >&2
+	exit 1
+fi
+
+create_sc_table()
+{
+	local sc nr max_nr
+
+	while read sc nr; do
+		printf "%s\n" "	[$nr] = \"$sc\","
+		max_nr=$nr
+	done
+
+	echo "#define SYSCALLTBL_RISCV_MAX_ID $max_nr"
+}
+
+create_table()
+{
+	echo "#include \"$input\""
+	echo "static const char *const syscalltbl_riscv[] = {"
+	create_sc_table
+	echo "};"
+}
+
+$gcc -E -dM -x c -I $incpath/include/uapi $input \
+	|awk '$2 ~ "__NR" && $3 !~ "__NR3264_" {
+		sub("^#define __NR(3264)?_", "");
+		print | "sort -k2 -n"}' \
+	|create_table
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 7c15dec6900d8..349986f6e5f5b 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -46,6 +46,10 @@ static const char *const *syscalltbl_native = syscalltbl_mips_n64;
 #include <asm/syscalls.c>
 const int syscalltbl_native_max_id = SYSCALLTBL_LOONGARCH_MAX_ID;
 static const char *const *syscalltbl_native = syscalltbl_loongarch;
+#elif defined(__riscv)
+#include <asm/syscalls.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_RISCV_MAX_ID;
+static const char *const *syscalltbl_native = syscalltbl_riscv;
 #endif
 
 struct syscall {

From 064d569e20e82c065b1dec9d20c29c7087bb1a00 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@kernel.org>
Date: Tue, 29 Oct 2024 16:29:02 -0300
Subject: [PATCH 0724/1530] perf ftrace latency: Fix unit on histogram first
 entry when using --use-nsec

The use_nsec arg wasn't being taken into account when printing the first
histogram entry, fix it:

  root@number:~# perf ftrace latency --use-nsec -T switch_mm_irqs_off -a sleep 2
  #   DURATION     |      COUNT | GRAPH                                          |
       0 - 1    us |          0 |                                                |
       1 - 2    ns |          0 |                                                |
       2 - 4    ns |          0 |                                                |
       4 - 8    ns |          0 |                                                |
       8 - 16   ns |          0 |                                                |
      16 - 32   ns |          0 |                                                |
      32 - 64   ns |        125 |                                                |
      64 - 128  ns |        335 |                                                |
     128 - 256  ns |       2155 | ####                                           |
     256 - 512  ns |       9996 | ###################                            |
     512 - 1024 ns |       4958 | #########                                      |
       1 - 2    us |       4636 | #########                                      |
       2 - 4    us |       1053 | ##                                             |
       4 - 8    us |         15 |                                                |
       8 - 16   us |          1 |                                                |
      16 - 32   us |          0 |                                                |
      32 - 64   us |          0 |                                                |
      64 - 128  us |          0 |                                                |
     128 - 256  us |          0 |                                                |
     256 - 512  us |          0 |                                                |
     512 - 1024 us |          0 |                                                |
       1 - ...  ms |          0 |                                                |
  root@number:~#

After:

  root@number:~# perf ftrace latency --use-nsec -T switch_mm_irqs_off -a sleep 2
  #   DURATION     |      COUNT | GRAPH                                          |
       0 - 1    ns |          0 |                                                |
       1 - 2    ns |          0 |                                                |
       2 - 4    ns |          0 |                                                |
       4 - 8    ns |          0 |                                                |
       8 - 16   ns |          0 |                                                |
      16 - 32   ns |          0 |                                                |
      32 - 64   ns |         19 |                                                |
      64 - 128  ns |         94 |                                                |
     128 - 256  ns |       2191 | ####                                           |
     256 - 512  ns |       9719 | ####################                           |
     512 - 1024 ns |       5330 | ###########                                    |
       1 - 2    us |       4104 | ########                                       |
       2 - 4    us |        807 | #                                              |
       4 - 8    us |          9 |                                                |
       8 - 16   us |          0 |                                                |
      16 - 32   us |          0 |                                                |
      32 - 64   us |          0 |                                                |
      64 - 128  us |          0 |                                                |
     128 - 256  us |          0 |                                                |
     256 - 512  us |          0 |                                                |
     512 - 1024 us |          0 |                                                |
       1 - ...  ms |          0 |                                                |
  root@number:~#

Fixes: 84005bb6148618cc ("perf ftrace latency: Add -n/--use-nsec option")
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Gabriele Monaco <gmonaco@redhat.com>
Link: https://lore.kernel.org/r/ZyE3frB-hMXHCnMO@x1
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-ftrace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index abcdc49b7a987..272d3c70810e7 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -815,7 +815,7 @@ static void display_histogram(int buckets[], bool use_nsec)
 
 	bar_len = buckets[0] * bar_total / total;
 	printf("  %4d - %-4d %s | %10d | %.*s%*s |\n",
-	       0, 1, "us", buckets[0], bar_len, bar, bar_total - bar_len, "");
+	       0, 1, use_nsec ? "ns" : "us", buckets[0], bar_len, bar, bar_total - bar_len, "");
 
 	for (i = 1; i < NUM_BUCKET - 1; i++) {
 		int start = (1 << (i - 1));

From ba993e5ada1ddce7a71140dc85ef65bc2cd981bc Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Tue, 29 Oct 2024 14:37:33 +0000
Subject: [PATCH 0725/1530] perf arm-spe: Use old behavior when opening old SPE
 files

Since the linked commit, we stopped interpreting data source if the
perf.data file doesn't have the new metadata version. This means that
perf c2c will show no samples in this case.

Keep the old behavior so old files can be opened, but also still show
the new warning that updating might improve the decoding.

Also re-write the warning to be more concise and specific to a user.

Fixes: ba5e7169e548 ("perf arm-spe: Use metadata to decide the data source feature")
Signed-off-by: James Clark <james.clark@linaro.org>
Reviewed-by: Leo Yan <leo.yan@arm.com>
Cc: Julio.Suarez@arm.com
Cc: Kiel.Friedt@arm.com
Cc: Ryan.Roberts@arm.com
Cc: Will Deacon <will@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Besar Wicaksono <bwicaksono@nvidia.com>
Cc: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20241029143734.291638-1-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/arm-spe.c | 50 +++++++++++++++++++--------------------
 1 file changed, 24 insertions(+), 26 deletions(-)

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index a291a412f6a14..dbf13f47879c0 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -562,37 +562,35 @@ static bool arm_spe__is_common_ds_encoding(struct arm_spe_queue *speq)
 	u64 *metadata = NULL;
 	u64 midr = 0;
 
-	/*
-	 * Metadata version 1 doesn't contain any info for MIDR.
-	 * Simply return false in this case.
-	 */
+	/* Metadata version 1 assumes all CPUs are the same (old behavior) */
 	if (spe->metadata_ver == 1) {
-		pr_warning_once("The data file contains metadata version 1, "
-				"which is absent the info for data source. "
-				"Please upgrade the tool to record data.\n");
-		return false;
-	}
-
-	/* CPU ID is -1 for per-thread mode */
-	if (speq->cpu < 0) {
-		/*
-		 * On the heterogeneous system, due to CPU ID is -1,
-		 * cannot confirm the data source packet is supported.
-		 */
-		if (!spe->is_homogeneous)
-			return false;
+		const char *cpuid;
 
-		/* In homogeneous system, simply use CPU0's metadata */
-		if (spe->metadata)
-			metadata = spe->metadata[0];
+		pr_warning_once("Old SPE metadata, re-record to improve decode accuracy\n");
+		cpuid = perf_env__cpuid(spe->session->evlist->env);
+		midr = strtol(cpuid, NULL, 16);
 	} else {
-		metadata = arm_spe__get_metadata_by_cpu(spe, speq->cpu);
-	}
+		/* CPU ID is -1 for per-thread mode */
+		if (speq->cpu < 0) {
+			/*
+			 * On the heterogeneous system, due to CPU ID is -1,
+			 * cannot confirm the data source packet is supported.
+			 */
+			if (!spe->is_homogeneous)
+				return false;
+
+			/* In homogeneous system, simply use CPU0's metadata */
+			if (spe->metadata)
+				metadata = spe->metadata[0];
+		} else {
+			metadata = arm_spe__get_metadata_by_cpu(spe, speq->cpu);
+		}
 
-	if (!metadata)
-		return false;
+		if (!metadata)
+			return false;
 
-	midr = metadata[ARM_SPE_CPU_MIDR];
+		midr = metadata[ARM_SPE_CPU_MIDR];
+	}
 
 	is_in_cpu_list = is_midr_in_range_list(midr, common_ds_encoding_cpus);
 	if (is_in_cpu_list)

From 16aed0a6520ba01b7d22c32e193fc1ec674f92d4 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Mon, 21 Oct 2024 11:45:06 -0400
Subject: [PATCH 0726/1530] i3c: master: Replace hard code 2 with macro
 I3C_ADDR_SLOT_STATUS_BITS

Replace the hardcoded value 2, which indicates 2 bits for I3C address
status, with the predefined macro I3C_ADDR_SLOT_STATUS_BITS.

Improve maintainability and extensibility of the code.

Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20241021-i3c_dts_assign-v8-1-4098b8bde01e@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master.c       | 4 ++--
 include/linux/i3c/master.h | 4 +++-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index 6f3eb710a75d6..dcf8d23c5941a 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -348,7 +348,7 @@ static enum i3c_addr_slot_status
 i3c_bus_get_addr_slot_status(struct i3c_bus *bus, u16 addr)
 {
 	unsigned long status;
-	int bitpos = addr * 2;
+	int bitpos = addr * I3C_ADDR_SLOT_STATUS_BITS;
 
 	if (addr > I2C_MAX_ADDR)
 		return I3C_ADDR_SLOT_RSVD;
@@ -362,7 +362,7 @@ i3c_bus_get_addr_slot_status(struct i3c_bus *bus, u16 addr)
 static void i3c_bus_set_addr_slot_status(struct i3c_bus *bus, u16 addr,
 					 enum i3c_addr_slot_status status)
 {
-	int bitpos = addr * 2;
+	int bitpos = addr * I3C_ADDR_SLOT_STATUS_BITS;
 	unsigned long *ptr;
 
 	if (addr > I2C_MAX_ADDR)
diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index 2a1ed05d5782a..2100547b2d8d2 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -313,6 +313,8 @@ enum i3c_addr_slot_status {
 	I3C_ADDR_SLOT_STATUS_MASK = 3,
 };
 
+#define I3C_ADDR_SLOT_STATUS_BITS 2
+
 /**
  * struct i3c_bus - I3C bus object
  * @cur_master: I3C master currently driving the bus. Since I3C is multi-master
@@ -354,7 +356,7 @@ enum i3c_addr_slot_status {
 struct i3c_bus {
 	struct i3c_dev_desc *cur_master;
 	int id;
-	unsigned long addrslots[((I2C_MAX_ADDR + 1) * 2) / BITS_PER_LONG];
+	unsigned long addrslots[((I2C_MAX_ADDR + 1) * I3C_ADDR_SLOT_STATUS_BITS) / BITS_PER_LONG];
 	enum i3c_bus_mode mode;
 	struct {
 		unsigned long i3c;

From 2f552fa280590e61bd3dbe66a7b54b99caa642a4 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Mon, 21 Oct 2024 11:45:07 -0400
Subject: [PATCH 0727/1530] i3c: master: Extend address status bit to 4 and add
 I3C_ADDR_SLOT_EXT_DESIRED
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extend the address status bit to 4 and introduce the
I3C_ADDR_SLOT_EXT_DESIRED macro to indicate that a device prefers a
specific address. This is generally set by the 'assigned-address' in the
device tree source (dts) file.

 ┌────┬─────────────┬───┬─────────┬───┐
 │S/Sr│ 7'h7E RnW=0 │ACK│ ENTDAA  │ T ├────┐
 └────┴─────────────┴───┴─────────┴───┘    │
 ┌─────────────────────────────────────────┘
 │  ┌──┬─────────────┬───┬─────────────────┬────────────────┬───┬─────────┐
 └─►│Sr│7'h7E RnW=1  │ACK│48bit UID BCR DCR│Assign 7bit Addr│PAR│ ACK/NACK│
    └──┴─────────────┴───┴─────────────────┴────────────────┴───┴─────────┘

Some master controllers (such as HCI) need to prepare the entire above
transaction before sending it out to the I3C bus. This means that a 7-bit
dynamic address needs to be allocated before knowing the target device's
UID information.

However, some I3C targets may request specific addresses (called as
"init_dyn_addr"), which is typically specified by the DT-'s
assigned-address property. Lower addresses having higher IBI priority. If
it is available, i3c_bus_get_free_addr() preferably return a free address
that is not in the list of desired addresses (called as "init_dyn_addr").
This allows the device with the "init_dyn_addr" to switch to its
"init_dyn_addr" when it hot-joins the I3C bus. Otherwise, if the
"init_dyn_addr" is already in use by another I3C device, the target device
will not be able to switch to its desired address.

If the previous step fails, fallback returning one of the remaining
unassigned address, regardless of its state in the desired list.

Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20241021-i3c_dts_assign-v8-2-4098b8bde01e@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master.c       | 65 +++++++++++++++++++++++++++++++-------
 include/linux/i3c/master.h |  7 ++--
 2 files changed, 59 insertions(+), 13 deletions(-)

diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index dcf8d23c5941a..1bf9cb138f77f 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -345,7 +345,7 @@ const struct bus_type i3c_bus_type = {
 EXPORT_SYMBOL_GPL(i3c_bus_type);
 
 static enum i3c_addr_slot_status
-i3c_bus_get_addr_slot_status(struct i3c_bus *bus, u16 addr)
+i3c_bus_get_addr_slot_status_mask(struct i3c_bus *bus, u16 addr, u32 mask)
 {
 	unsigned long status;
 	int bitpos = addr * I3C_ADDR_SLOT_STATUS_BITS;
@@ -356,11 +356,17 @@ i3c_bus_get_addr_slot_status(struct i3c_bus *bus, u16 addr)
 	status = bus->addrslots[bitpos / BITS_PER_LONG];
 	status >>= bitpos % BITS_PER_LONG;
 
-	return status & I3C_ADDR_SLOT_STATUS_MASK;
+	return status & mask;
 }
 
-static void i3c_bus_set_addr_slot_status(struct i3c_bus *bus, u16 addr,
-					 enum i3c_addr_slot_status status)
+static enum i3c_addr_slot_status
+i3c_bus_get_addr_slot_status(struct i3c_bus *bus, u16 addr)
+{
+	return i3c_bus_get_addr_slot_status_mask(bus, addr, I3C_ADDR_SLOT_STATUS_MASK);
+}
+
+static void i3c_bus_set_addr_slot_status_mask(struct i3c_bus *bus, u16 addr,
+					      enum i3c_addr_slot_status status, u32 mask)
 {
 	int bitpos = addr * I3C_ADDR_SLOT_STATUS_BITS;
 	unsigned long *ptr;
@@ -369,9 +375,14 @@ static void i3c_bus_set_addr_slot_status(struct i3c_bus *bus, u16 addr,
 		return;
 
 	ptr = bus->addrslots + (bitpos / BITS_PER_LONG);
-	*ptr &= ~((unsigned long)I3C_ADDR_SLOT_STATUS_MASK <<
-						(bitpos % BITS_PER_LONG));
-	*ptr |= (unsigned long)status << (bitpos % BITS_PER_LONG);
+	*ptr &= ~((unsigned long)mask << (bitpos % BITS_PER_LONG));
+	*ptr |= ((unsigned long)status & mask) << (bitpos % BITS_PER_LONG);
+}
+
+static void i3c_bus_set_addr_slot_status(struct i3c_bus *bus, u16 addr,
+					 enum i3c_addr_slot_status status)
+{
+	i3c_bus_set_addr_slot_status_mask(bus, addr, status, I3C_ADDR_SLOT_STATUS_MASK);
 }
 
 static bool i3c_bus_dev_addr_is_avail(struct i3c_bus *bus, u8 addr)
@@ -383,13 +394,44 @@ static bool i3c_bus_dev_addr_is_avail(struct i3c_bus *bus, u8 addr)
 	return status == I3C_ADDR_SLOT_FREE;
 }
 
+/*
+ * ┌────┬─────────────┬───┬─────────┬───┐
+ * │S/Sr│ 7'h7E RnW=0 │ACK│ ENTDAA  │ T ├────┐
+ * └────┴─────────────┴───┴─────────┴───┘    │
+ * ┌─────────────────────────────────────────┘
+ * │  ┌──┬─────────────┬───┬─────────────────┬────────────────┬───┬─────────┐
+ * └─►│Sr│7'h7E RnW=1  │ACK│48bit UID BCR DCR│Assign 7bit Addr│PAR│ ACK/NACK│
+ *    └──┴─────────────┴───┴─────────────────┴────────────────┴───┴─────────┘
+ * Some master controllers (such as HCI) need to prepare the entire above transaction before
+ * sending it out to the I3C bus. This means that a 7-bit dynamic address needs to be allocated
+ * before knowing the target device's UID information.
+ *
+ * However, some I3C targets may request specific addresses (called as "init_dyn_addr"), which is
+ * typically specified by the DT-'s assigned-address property. Lower addresses having higher IBI
+ * priority. If it is available, i3c_bus_get_free_addr() preferably return a free address that is
+ * not in the list of desired addresses (called as "init_dyn_addr"). This allows the device with
+ * the "init_dyn_addr" to switch to its "init_dyn_addr" when it hot-joins the I3C bus. Otherwise,
+ * if the "init_dyn_addr" is already in use by another I3C device, the target device will not be
+ * able to switch to its desired address.
+ *
+ * If the previous step fails, fallback returning one of the remaining unassigned address,
+ * regardless of its state in the desired list.
+ */
 static int i3c_bus_get_free_addr(struct i3c_bus *bus, u8 start_addr)
 {
 	enum i3c_addr_slot_status status;
 	u8 addr;
 
 	for (addr = start_addr; addr < I3C_MAX_ADDR; addr++) {
-		status = i3c_bus_get_addr_slot_status(bus, addr);
+		status = i3c_bus_get_addr_slot_status_mask(bus, addr,
+							   I3C_ADDR_SLOT_EXT_STATUS_MASK);
+		if (status == I3C_ADDR_SLOT_FREE)
+			return addr;
+	}
+
+	for (addr = start_addr; addr < I3C_MAX_ADDR; addr++) {
+		status = i3c_bus_get_addr_slot_status_mask(bus, addr,
+							   I3C_ADDR_SLOT_STATUS_MASK);
 		if (status == I3C_ADDR_SLOT_FREE)
 			return addr;
 	}
@@ -1918,9 +1960,10 @@ static int i3c_master_bus_init(struct i3c_master_controller *master)
 			goto err_rstdaa;
 		}
 
-		i3c_bus_set_addr_slot_status(&master->bus,
-					     i3cboardinfo->init_dyn_addr,
-					     I3C_ADDR_SLOT_I3C_DEV);
+		i3c_bus_set_addr_slot_status_mask(&master->bus,
+						  i3cboardinfo->init_dyn_addr,
+						  I3C_ADDR_SLOT_I3C_DEV | I3C_ADDR_SLOT_EXT_DESIRED,
+						  I3C_ADDR_SLOT_EXT_STATUS_MASK);
 
 		/*
 		 * Only try to create/attach devices that have a static
diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index 2100547b2d8d2..6e5328c6c6afd 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -298,7 +298,8 @@ enum i3c_open_drain_speed {
  * @I3C_ADDR_SLOT_I2C_DEV: address is assigned to an I2C device
  * @I3C_ADDR_SLOT_I3C_DEV: address is assigned to an I3C device
  * @I3C_ADDR_SLOT_STATUS_MASK: address slot mask
- *
+ * @I3C_ADDR_SLOT_EXT_DESIRED: the bitmask represents addresses that are preferred by some devices,
+ *			       such as the "assigned-address" property in a device tree source.
  * On an I3C bus, addresses are assigned dynamically, and we need to know which
  * addresses are free to use and which ones are already assigned.
  *
@@ -311,9 +312,11 @@ enum i3c_addr_slot_status {
 	I3C_ADDR_SLOT_I2C_DEV,
 	I3C_ADDR_SLOT_I3C_DEV,
 	I3C_ADDR_SLOT_STATUS_MASK = 3,
+	I3C_ADDR_SLOT_EXT_STATUS_MASK = 7,
+	I3C_ADDR_SLOT_EXT_DESIRED = BIT(2),
 };
 
-#define I3C_ADDR_SLOT_STATUS_BITS 2
+#define I3C_ADDR_SLOT_STATUS_BITS 4
 
 /**
  * struct i3c_bus - I3C bus object

From 851bd21cdb55e727ab29280bc9f6b678164f802a Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Mon, 21 Oct 2024 11:45:08 -0400
Subject: [PATCH 0728/1530] i3c: master: Fix dynamic address leak when
 'assigned-address' is present

If the DTS contains 'assigned-address', a dynamic address leak occurs
during hotjoin events.

Assume a device have assigned-address 0xb.
  - Device issue Hotjoin
  - Call i3c_master_do_daa()
  - Call driver xxx_do_daa()
  - Call i3c_master_get_free_addr() to get dynamic address 0x9
  - i3c_master_add_i3c_dev_locked(0x9)
  -     expected_dyn_addr  = newdev->boardinfo->init_dyn_addr (0xb);
  -     i3c_master_reattach_i3c_dev(newdev(0xb), old_dyn_addr(0x9));
  -         if (dev->info.dyn_addr != old_dyn_addr &&
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 0xb != 0x9 -> TRUE
                (!dev->boardinfo ||
                 ^^^^^^^^^^^^^^^ ->  FALSE
                 dev->info.dyn_addr != dev->boardinfo->init_dyn_addr)) {
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                 0xb != 0xb      ->  FALSE
                 ...
                 i3c_bus_set_addr_slot_status(&master->bus, old_dyn_addr,
                                                     I3C_ADDR_SLOT_FREE);
		 ^^^
                 This will be skipped. So old_dyn_addr never free
            }

  - i3c_master_get_free_addr() will return increased sequence number.

Remove dev->info.dyn_addr != dev->boardinfo->init_dyn_addr condition check.
dev->info.dyn_addr should be checked before calling this function because
i3c_master_setnewda_locked() has already been called and the target device
has already accepted dyn_addr. It is too late to check if dyn_addr is free
in i3c_master_reattach_i3c_dev().

Add check to ensure expected_dyn_addr is free before
i3c_master_setnewda_locked().

Fixes: cc3a392d69b6 ("i3c: master: fix for SETDASA and DAA process")
Cc: stable@kernel.org
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20241021-i3c_dts_assign-v8-3-4098b8bde01e@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index 1bf9cb138f77f..5a089be7e0728 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -1548,16 +1548,9 @@ static int i3c_master_reattach_i3c_dev(struct i3c_dev_desc *dev,
 				       u8 old_dyn_addr)
 {
 	struct i3c_master_controller *master = i3c_dev_get_master(dev);
-	enum i3c_addr_slot_status status;
 	int ret;
 
-	if (dev->info.dyn_addr != old_dyn_addr &&
-	    (!dev->boardinfo ||
-	     dev->info.dyn_addr != dev->boardinfo->init_dyn_addr)) {
-		status = i3c_bus_get_addr_slot_status(&master->bus,
-						      dev->info.dyn_addr);
-		if (status != I3C_ADDR_SLOT_FREE)
-			return -EBUSY;
+	if (dev->info.dyn_addr != old_dyn_addr) {
 		i3c_bus_set_addr_slot_status(&master->bus,
 					     dev->info.dyn_addr,
 					     I3C_ADDR_SLOT_I3C_DEV);
@@ -1960,9 +1953,10 @@ static int i3c_master_bus_init(struct i3c_master_controller *master)
 			goto err_rstdaa;
 		}
 
+		/* Do not mark as occupied until real device exist in bus */
 		i3c_bus_set_addr_slot_status_mask(&master->bus,
 						  i3cboardinfo->init_dyn_addr,
-						  I3C_ADDR_SLOT_I3C_DEV | I3C_ADDR_SLOT_EXT_DESIRED,
+						  I3C_ADDR_SLOT_EXT_DESIRED,
 						  I3C_ADDR_SLOT_EXT_STATUS_MASK);
 
 		/*
@@ -2126,7 +2120,8 @@ int i3c_master_add_i3c_dev_locked(struct i3c_master_controller *master,
 	else
 		expected_dyn_addr = newdev->info.dyn_addr;
 
-	if (newdev->info.dyn_addr != expected_dyn_addr) {
+	if (newdev->info.dyn_addr != expected_dyn_addr &&
+	    i3c_bus_get_addr_slot_status(&master->bus, expected_dyn_addr) == I3C_ADDR_SLOT_FREE) {
 		/*
 		 * Try to apply the expected dynamic address. If it fails, keep
 		 * the address assigned by the master.

From 3c6684a15010822a83f312d6b9d4714c36f0f7e2 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Wed, 2 Oct 2024 10:50:33 -0400
Subject: [PATCH 0729/1530] i3c: master: svc: use repeat start when IBI WIN
 happens

There is a possibility of an IBI WIN occurring when addressing issues, even
when sending CCC commands. Most of the time, returning -EAGAIN is
acceptable, but the case below becomes highly complex.

When a Hotjoin event occurs:
- i3c_master_do_daa()
  - i3c_master_add_i3c_dev_locked()
    - A dynamic address (e.g., 0x9) is already set during DAA.
    - i3c_master_getpid_locked()
      - Another device issues HJ or IBI here. Returning -EAGAIN causes
        failure in adding the new device. However, the dynamic address(0x9)
        has already been assigned to this device. If another device issues
        HJ, it will get this address 0x9 again, causing two devices on the
        bus to use the same dynamic address 0x9.
      - Attempting to send RSTDAA when the first device fails at
        i3c_master_getpid_locked() could also fail when sending RSTDAA for
        the same reason.

According to the I3C spec, address arbitration only happens at START, never
at REPEAT start. Using repeat start when an IBI WIN occurs simplifies this
case, as i3c_master_getpid_locked() will not return an error when another
device tries to send HJ or IBI.

Acked-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20241002-svc-i3c-hj-v6-1-7e6e1d3569ae@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/svc-i3c-master.c | 36 ++++++++++++++---------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index a7bfc678153e6..7cd3ce2643f1a 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -1163,6 +1163,24 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 		if (ret)
 			goto emit_stop;
 
+		/*
+		 * According to I3C spec ver 1.1.1, 5.1.2.2.3 Consequence of Controller Starting a
+		 * Frame with I3C Target Address.
+		 *
+		 * The I3C Controller normally should start a Frame, the Address may be arbitrated,
+		 * and so the Controller shall monitor to see whether an In-Band Interrupt request,
+		 * a Controller Role Request (i.e., Secondary Controller requests to become the
+		 * Active Controller), or a Hot-Join Request has been made.
+		 *
+		 * If missed IBIWON check, the wrong data will be return. When IBIWON happen, issue
+		 * repeat start. Address arbitrate only happen at START, never happen at REPEAT
+		 * start.
+		 */
+		if (SVC_I3C_MSTATUS_IBIWON(reg)) {
+			writel(SVC_I3C_MINT_IBIWON, master->regs + SVC_I3C_MSTATUS);
+			continue;
+		}
+
 		if (readl(master->regs + SVC_I3C_MERRWARN) & SVC_I3C_MERRWARN_NACK) {
 			/*
 			 * According to I3C Spec 1.1.1, 11-Jun-2021, section: 5.1.2.2.3.
@@ -1196,24 +1214,6 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 		}
 	}
 
-	/*
-	 * According to I3C spec ver 1.1.1, 5.1.2.2.3 Consequence of Controller Starting a Frame
-	 * with I3C Target Address.
-	 *
-	 * The I3C Controller normally should start a Frame, the Address may be arbitrated, and so
-	 * the Controller shall monitor to see whether an In-Band Interrupt request, a Controller
-	 * Role Request (i.e., Secondary Controller requests to become the Active Controller), or
-	 * a Hot-Join Request has been made.
-	 *
-	 * If missed IBIWON check, the wrong data will be return. When IBIWON happen, return failure
-	 * and yield the above events handler.
-	 */
-	if (SVC_I3C_MSTATUS_IBIWON(reg)) {
-		ret = -EAGAIN;
-		*actual_len = 0;
-		goto emit_stop;
-	}
-
 	if (rnw)
 		ret = svc_i3c_master_read(master, in, xfer_len);
 	else

From e22405a812a11e5b01bfbb18c5277dd3e69ba589 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Wed, 2 Oct 2024 10:50:34 -0400
Subject: [PATCH 0730/1530] i3c: master: svc: manually emit NACK/ACK for
 hotjoin

When the address is arbitrated at send address, the hardware can auto-send
NACK if it is an IBI. However, manual emission of NACK/ACK is needed for
hot join or controller request events.

Add help function svc_i3c_master_handle_ibi_won() to check event type and
send out NACK if the event is not an IBI.

Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20241002-svc-i3c-hj-v6-2-7e6e1d3569ae@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/svc-i3c-master.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index 7cd3ce2643f1a..c35a228f0c2f4 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -409,6 +409,24 @@ static void svc_i3c_master_nack_ibi(struct svc_i3c_master *master)
 	       master->regs + SVC_I3C_MCTRL);
 }
 
+static int svc_i3c_master_handle_ibi_won(struct svc_i3c_master *master, u32 mstatus)
+{
+	u32 ibitype;
+
+	ibitype = SVC_I3C_MSTATUS_IBITYPE(mstatus);
+
+	writel(SVC_I3C_MINT_IBIWON, master->regs + SVC_I3C_MSTATUS);
+
+	/* Hardware can't auto emit NACK for hot join and master request */
+	switch (ibitype) {
+	case SVC_I3C_MSTATUS_IBITYPE_HOT_JOIN:
+	case SVC_I3C_MSTATUS_IBITYPE_MASTER_REQUEST:
+		svc_i3c_master_nack_ibi(master);
+	}
+
+	return 0;
+}
+
 static void svc_i3c_master_ibi_work(struct work_struct *work)
 {
 	struct svc_i3c_master *master = container_of(work, struct svc_i3c_master, ibi_work);
@@ -1177,7 +1195,7 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 		 * start.
 		 */
 		if (SVC_I3C_MSTATUS_IBIWON(reg)) {
-			writel(SVC_I3C_MINT_IBIWON, master->regs + SVC_I3C_MSTATUS);
+			svc_i3c_master_handle_ibi_won(master, reg);
 			continue;
 		}
 

From 6a12f56f7392cfdd2f31ef9a090ccadadae548e8 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Wed, 2 Oct 2024 10:50:35 -0400
Subject: [PATCH 0731/1530] i3c: master: svc: need check IBIWON for dynamic
 address assignment

When sending REQUEST_PROC_DAA, emit START and address 7E. Address
arbitration may occur at this time if other devices trigger HJ, IBI, or
CR events.

When IBIWON happen during a REQUEST_PROC_DAA, NACK the IBI request then
send a repeated start to continue current dynamic address assignment.

Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20241002-svc-i3c-hj-v6-3-7e6e1d3569ae@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/svc-i3c-master.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index c35a228f0c2f4..5df0ec02d73ce 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -872,6 +872,9 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master,
 	int ret, i;
 
 	while (true) {
+		/* clean SVC_I3C_MINT_IBIWON w1c bits */
+		writel(SVC_I3C_MINT_IBIWON, master->regs + SVC_I3C_MSTATUS);
+
 		/* SVC_I3C_MCTRL_REQUEST_PROC_DAA have two mode, ENTER DAA or PROCESS DAA.
 		 *
 		 * ENTER DAA:
@@ -923,6 +926,9 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master,
 			ret = svc_i3c_master_readb(master, data, 2);
 			if (ret)
 				break;
+		} else if (SVC_I3C_MSTATUS_IBIWON(reg)) {
+			svc_i3c_master_handle_ibi_won(master, reg);
+			continue;
 		} else if (SVC_I3C_MSTATUS_MCTRLDONE(reg)) {
 			if (SVC_I3C_MSTATUS_STATE_IDLE(reg) &&
 			    SVC_I3C_MSTATUS_COMPLETE(reg)) {

From f36f6624cbacb31d25d2cc11dfb1e74cd2a3996e Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Wed, 2 Oct 2024 10:50:36 -0400
Subject: [PATCH 0732/1530] i3c: master: svc: use spin_lock_irqsave at
 svc_i3c_master_ibi_work()

According to I3C spec ver 1.1, 09-Jun-2021, section 5.1.2.5:

The I3C Controller shall hold SCL low while the Bus is in ACK/NACK Phase of
I3C/I2C transfer. But maximum stall time is 100us. The IRQs have to be
disabled to prevent schedule during the whole I3C transaction, otherwise,
the I3C bus timeout may happen if any irq or schedule happen during
transaction.

Replace mutex with spin_lock_irqsave() to avoid stalling SCL more than
100us.

Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20241002-svc-i3c-hj-v6-4-7e6e1d3569ae@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/svc-i3c-master.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index 5df0ec02d73ce..ed3f1bfbea37a 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -436,7 +436,16 @@ static void svc_i3c_master_ibi_work(struct work_struct *work)
 	u32 status, val;
 	int ret;
 
-	mutex_lock(&master->lock);
+	/*
+	 * According to I3C spec ver 1.1, 09-Jun-2021, section 5.1.2.5:
+	 *
+	 * The I3C Controller shall hold SCL low while the Bus is in ACK/NACK Phase of I3C/I2C
+	 * transfer. But maximum stall time is 100us. The IRQs have to be disabled to prevent
+	 * schedule during the whole I3C transaction, otherwise, the I3C bus timeout may happen if
+	 * any irq or schedule happen during transaction.
+	 */
+	guard(spinlock_irqsave)(&master->xferqueue.lock);
+
 	/*
 	 * IBIWON may be set before SVC_I3C_MCTRL_REQUEST_AUTO_IBI, causing
 	 * readl_relaxed_poll_timeout() to return immediately. Consequently,
@@ -456,8 +465,8 @@ static void svc_i3c_master_ibi_work(struct work_struct *work)
 	       master->regs + SVC_I3C_MCTRL);
 
 	/* Wait for IBIWON, should take approximately 100us */
-	ret = readl_relaxed_poll_timeout(master->regs + SVC_I3C_MSTATUS, val,
-					 SVC_I3C_MSTATUS_IBIWON(val), 0, 1000);
+	ret = readl_relaxed_poll_timeout_atomic(master->regs + SVC_I3C_MSTATUS, val,
+					 SVC_I3C_MSTATUS_IBIWON(val), 0, 100);
 	if (ret) {
 		dev_err(master->dev, "Timeout when polling for IBIWON\n");
 		svc_i3c_master_emit_stop(master);
@@ -529,7 +538,6 @@ static void svc_i3c_master_ibi_work(struct work_struct *work)
 
 reenable_ibis:
 	svc_i3c_master_enable_interrupts(master, SVC_I3C_MINT_SLVSTART);
-	mutex_unlock(&master->lock);
 }
 
 static irqreturn_t svc_i3c_master_irq_handler(int irq, void *dev_id)

From 3ca529194e292a9a9548951ed20cfd6f0c98c94d Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Wed, 2 Oct 2024 10:50:37 -0400
Subject: [PATCH 0733/1530] i3c: master: svc: wait for Manual ACK/NACK Done
 before next step

Wait for the controller to complete emitting ACK/NACK, otherwise the next
command may be omitted by the hardware.

Add a "command done" check in svc_i3c_master_nack(ack)_ibi() and change the
return type to int to flag possible timeouts.

Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20241002-svc-i3c-hj-v6-5-7e6e1d3569ae@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/svc-i3c-master.c | 29 +++++++++++++++++++++++------
 1 file changed, 23 insertions(+), 6 deletions(-)

diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index ed3f1bfbea37a..7ef7e50b4b916 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -388,10 +388,11 @@ static int svc_i3c_master_handle_ibi(struct svc_i3c_master *master,
 	return 0;
 }
 
-static void svc_i3c_master_ack_ibi(struct svc_i3c_master *master,
+static int svc_i3c_master_ack_ibi(struct svc_i3c_master *master,
 				   bool mandatory_byte)
 {
 	unsigned int ibi_ack_nack;
+	u32 reg;
 
 	ibi_ack_nack = SVC_I3C_MCTRL_REQUEST_IBI_ACKNACK;
 	if (mandatory_byte)
@@ -400,18 +401,30 @@ static void svc_i3c_master_ack_ibi(struct svc_i3c_master *master,
 		ibi_ack_nack |= SVC_I3C_MCTRL_IBIRESP_ACK_WITHOUT_BYTE;
 
 	writel(ibi_ack_nack, master->regs + SVC_I3C_MCTRL);
+
+	return readl_poll_timeout_atomic(master->regs + SVC_I3C_MSTATUS, reg,
+					 SVC_I3C_MSTATUS_MCTRLDONE(reg), 1, 1000);
+
 }
 
-static void svc_i3c_master_nack_ibi(struct svc_i3c_master *master)
+static int svc_i3c_master_nack_ibi(struct svc_i3c_master *master)
 {
+	int ret;
+	u32 reg;
+
 	writel(SVC_I3C_MCTRL_REQUEST_IBI_ACKNACK |
 	       SVC_I3C_MCTRL_IBIRESP_NACK,
 	       master->regs + SVC_I3C_MCTRL);
+
+	ret = readl_poll_timeout_atomic(master->regs + SVC_I3C_MSTATUS, reg,
+					SVC_I3C_MSTATUS_MCTRLDONE(reg), 1, 1000);
+	return ret;
 }
 
 static int svc_i3c_master_handle_ibi_won(struct svc_i3c_master *master, u32 mstatus)
 {
 	u32 ibitype;
+	int ret = 0;
 
 	ibitype = SVC_I3C_MSTATUS_IBITYPE(mstatus);
 
@@ -421,10 +434,10 @@ static int svc_i3c_master_handle_ibi_won(struct svc_i3c_master *master, u32 msta
 	switch (ibitype) {
 	case SVC_I3C_MSTATUS_IBITYPE_HOT_JOIN:
 	case SVC_I3C_MSTATUS_IBITYPE_MASTER_REQUEST:
-		svc_i3c_master_nack_ibi(master);
+		ret = svc_i3c_master_nack_ibi(master);
 	}
 
-	return 0;
+	return ret;
 }
 
 static void svc_i3c_master_ibi_work(struct work_struct *work)
@@ -935,7 +948,9 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master,
 			if (ret)
 				break;
 		} else if (SVC_I3C_MSTATUS_IBIWON(reg)) {
-			svc_i3c_master_handle_ibi_won(master, reg);
+			ret = svc_i3c_master_handle_ibi_won(master, reg);
+			if (ret)
+				break;
 			continue;
 		} else if (SVC_I3C_MSTATUS_MCTRLDONE(reg)) {
 			if (SVC_I3C_MSTATUS_STATE_IDLE(reg) &&
@@ -1209,7 +1224,9 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 		 * start.
 		 */
 		if (SVC_I3C_MSTATUS_IBIWON(reg)) {
-			svc_i3c_master_handle_ibi_won(master, reg);
+			ret = svc_i3c_master_handle_ibi_won(master, reg);
+			if (ret)
+				goto emit_stop;
 			continue;
 		}
 

From 3b2ac810d86eb96e882db80a3320a3848b133208 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Wed, 2 Oct 2024 10:50:38 -0400
Subject: [PATCH 0734/1530] i3c: master: svc: fix possible assignment of the
 same address to two devices

svc_i3c_master_do_daa() {
    ...
    for (i = 0; i < dev_nb; i++) {
        ret = i3c_master_add_i3c_dev_locked(m, addrs[i]);
        if (ret)
            goto rpm_out;
    }
}

If two devices (A and B) are detected in DAA and address 0xa is assigned to
device A and 0xb to device B, a failure in i3c_master_add_i3c_dev_locked()
for device A (addr: 0xa) could prevent device B (addr: 0xb) from being
registered on the bus. The I3C stack might still consider 0xb a free
address. If a subsequent Hotjoin occurs, 0xb might be assigned to Device A,
causing both devices A and B to use the same address 0xb, violating the I3C
specification.

The return value for i3c_master_add_i3c_dev_locked() should not be checked
because subsequent steps will scan the entire I3C bus, independent of
whether i3c_master_add_i3c_dev_locked() returns success.

If device A registration fails, there is still a chance to register device
B. i3c_master_add_i3c_dev_locked() can reset DAA if a failure occurs while
retrieving device information.

Cc: stable@kernel.org
Fixes: 317bacf960a4 ("i3c: master: add enable(disable) hot join in sys entry")
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20241002-svc-i3c-hj-v6-6-7e6e1d3569ae@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/svc-i3c-master.c | 27 +++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)

diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index 7ef7e50b4b916..e9c8e340d861b 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -1103,12 +1103,27 @@ static int svc_i3c_master_do_daa(struct i3c_master_controller *m)
 	if (ret)
 		goto rpm_out;
 
-	/* Register all devices who participated to the core */
-	for (i = 0; i < dev_nb; i++) {
-		ret = i3c_master_add_i3c_dev_locked(m, addrs[i]);
-		if (ret)
-			goto rpm_out;
-	}
+	/*
+	 * Register all devices who participated to the core
+	 *
+	 * If two devices (A and B) are detected in DAA and address 0xa is assigned to
+	 * device A and 0xb to device B, a failure in i3c_master_add_i3c_dev_locked()
+	 * for device A (addr: 0xa) could prevent device B (addr: 0xb) from being
+	 * registered on the bus. The I3C stack might still consider 0xb a free
+	 * address. If a subsequent Hotjoin occurs, 0xb might be assigned to Device A,
+	 * causing both devices A and B to use the same address 0xb, violating the I3C
+	 * specification.
+	 *
+	 * The return value for i3c_master_add_i3c_dev_locked() should not be checked
+	 * because subsequent steps will scan the entire I3C bus, independent of
+	 * whether i3c_master_add_i3c_dev_locked() returns success.
+	 *
+	 * If device A registration fails, there is still a chance to register device
+	 * B. i3c_master_add_i3c_dev_locked() can reset DAA if a failure occurs while
+	 * retrieving device information.
+	 */
+	for (i = 0; i < dev_nb; i++)
+		i3c_master_add_i3c_dev_locked(m, addrs[i]);
 
 	/* Configure IBI auto-rules */
 	ret = svc_i3c_update_ibirules(master);

From 36faa04ce3d9c962b4b29d285ad07ca29e2988e4 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Tue, 1 Oct 2024 12:22:32 -0400
Subject: [PATCH 0735/1530] i3c: master: Remove
 i3c_dev_disable_ibi_locked(olddev) on device hotjoin

When a new device hotjoins, a new dynamic address is assigned.
i3c_master_add_i3c_dev_locked() identifies that the device was previously
attached to the bus and locates the olddev.

i3c_master_add_i3c_dev_locked()
{
    ...
    olddev = i3c_master_search_i3c_dev_duplicate(newdev);
    ...
    if (olddev) {
        ...
        i3c_dev_disable_ibi_locked(olddev);
        ^^^^^^
        The olddev should not receive any commands on the i3c bus as it
        does not exist and has been assigned a new address. This will
        result in NACK or timeout. So remove it.
    }

    i3c_dev_free_ibi_locked(olddev);
    ^^^^^^^^
    This function internally calls i3c_dev_disable_ibi_locked() function
    causing to send DISEC command with old Address.

    The olddev should not receive any commands on the i3c bus as it
    does not exist and has been assigned a new address. This will
    result in NACK or timeout. So, update the olddev->ibi->enabled
    flag to false to avoid DISEC with OldAddr.
}

Include part of Ravindra Yashvant Shinde's work:
https://lore.kernel.org/linux-i3c/20240820151917.3904956-1-ravindra.yashvant.shinde@nxp.com/T/#u

Fixes: 317bacf960a4 ("i3c: master: add enable(disable) hot join in sys entry")
Co-developed-by: Ravindra Yashvant Shinde <ravindra.yashvant.shinde@nxp.com>
Signed-off-by: Ravindra Yashvant Shinde <ravindra.yashvant.shinde@nxp.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20241001162232.223724-1-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index 5a089be7e0728..a1d25c830efff 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -2088,11 +2088,16 @@ int i3c_master_add_i3c_dev_locked(struct i3c_master_controller *master,
 			ibireq.max_payload_len = olddev->ibi->max_payload_len;
 			ibireq.num_slots = olddev->ibi->num_slots;
 
-			if (olddev->ibi->enabled) {
+			if (olddev->ibi->enabled)
 				enable_ibi = true;
-				i3c_dev_disable_ibi_locked(olddev);
-			}
-
+			/*
+			 * The olddev should not receive any commands on the
+			 * i3c bus as it does not exist and has been assigned
+			 * a new address. This will result in NACK or timeout.
+			 * So, update the olddev->ibi->enabled flag to false
+			 * to avoid DISEC with OldAddr.
+			 */
+			olddev->ibi->enabled = false;
 			i3c_dev_free_ibi_locked(olddev);
 		}
 		mutex_unlock(&olddev->ibi_lock);

From 3082990592f7c6d7510a9133afa46e31bbe26533 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Tue, 1 Oct 2024 12:26:08 -0400
Subject: [PATCH 0736/1530] i3c: master: Fix miss free init_dyn_addr at
 i3c_master_put_i3c_addrs()

if (dev->boardinfo && dev->boardinfo->init_dyn_addr)
                                      ^^^ here check "init_dyn_addr"
	i3c_bus_set_addr_slot_status(&master->bus, dev->info.dyn_addr, ...)
						             ^^^^
							free "dyn_addr"
Fix copy/paste error "dyn_addr" by replacing it with "init_dyn_addr".

Cc: stable@kernel.org
Fixes: 3a379bbcea0a ("i3c: Add core I3C infrastructure")
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20241001162608.224039-1-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index a1d25c830efff..770908cff2434 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -1459,7 +1459,7 @@ static void i3c_master_put_i3c_addrs(struct i3c_dev_desc *dev)
 					     I3C_ADDR_SLOT_FREE);
 
 	if (dev->boardinfo && dev->boardinfo->init_dyn_addr)
-		i3c_bus_set_addr_slot_status(&master->bus, dev->info.dyn_addr,
+		i3c_bus_set_addr_slot_status(&master->bus, dev->boardinfo->init_dyn_addr,
 					     I3C_ADDR_SLOT_FREE);
 }
 

From 6ca2738174e4ee44edb2ab2d86ce74f015a0cc32 Mon Sep 17 00:00:00 2001
From: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Date: Fri, 20 Sep 2024 17:44:31 +0300
Subject: [PATCH 0737/1530] i3c: mipi-i3c-hci: Mask ring interrupts before ring
 stop request

Bus cleanup path in DMA mode may trigger a RING_OP_STAT interrupt when
the ring is being stopped. Depending on timing between ring stop request
completion, interrupt handler removal and code execution this may lead
to a NULL pointer dereference in hci_dma_irq_handler() if it gets to run
after the io_data pointer is set to NULL in hci_dma_cleanup().

Prevent this my masking the ring interrupts before ring stop request.

Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Link: https://lore.kernel.org/r/20240920144432.62370-2-jarkko.nikula@linux.intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/dma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index a918e96b21fdd..13adc58400942 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -159,10 +159,10 @@ static void hci_dma_cleanup(struct i3c_hci *hci)
 	for (i = 0; i < rings->total; i++) {
 		rh = &rings->headers[i];
 
+		rh_reg_write(INTR_SIGNAL_ENABLE, 0);
 		rh_reg_write(RING_CONTROL, 0);
 		rh_reg_write(CR_SETUP, 0);
 		rh_reg_write(IBI_SETUP, 0);
-		rh_reg_write(INTR_SIGNAL_ENABLE, 0);
 
 		if (rh->xfer)
 			dma_free_coherent(&hci->master.dev,

From 45357c9b37bb069dfa4941449de5839c02801a15 Mon Sep 17 00:00:00 2001
From: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Date: Fri, 20 Sep 2024 17:44:32 +0300
Subject: [PATCH 0738/1530] i3c: mipi-i3c-hci: Handle interrupts according to
 current specifications

Current MIPI I3C HCI specification versions pre-1.0, 1.0. 1.1 and 1.2
don't have cascaded interrupt bits for the PIO and DMA (ring headers) in
the INTR_STATUS register as implemented currently in the code. Instead
bits 9:0 are marked as reserved with unspecified reset value.

To my understanding they were planned to be introduced in the version 2
and the original commit 9ad9a52cce28 ("i3c/master: introduce the
mipi-i3c-hci driver") was coding ahead according to a draft. With
remarks though.

This is causing that the DMA handler is not called until at least one
reserved bit 7:0 is set in the INTR_STATUS.

Since it looks that idea was dropped in later official versions and to
make able to handle DMA interrupts on an HW that is implemented
according to current specifications call assigned PIO or DMA IO handler
unconditionally.

While doing so remove cascaded interrupt bit definitions and the mask
argument passed to the handler functions.

Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Link: https://lore.kernel.org/r/20240920144432.62370-3-jarkko.nikula@linux.intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c | 16 +++-------------
 drivers/i3c/master/mipi-i3c-hci/dma.c  |  8 ++------
 drivers/i3c/master/mipi-i3c-hci/hci.h  |  2 +-
 drivers/i3c/master/mipi-i3c-hci/pio.c  |  2 +-
 4 files changed, 7 insertions(+), 21 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index a82c47c9986d3..b190401c89c99 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -80,8 +80,6 @@
 #define INTR_HC_CMD_SEQ_UFLOW_STAT	BIT(12)	/* Cmd Sequence Underflow */
 #define INTR_HC_RESET_CANCEL		BIT(11)	/* HC Cancelled Reset */
 #define INTR_HC_INTERNAL_ERR		BIT(10)	/* HC Internal Error */
-#define INTR_HC_PIO			BIT(8)	/* cascaded PIO interrupt */
-#define INTR_HC_RINGS			GENMASK(7, 0)
 
 #define DAT_SECTION			0x30	/* Device Address Table */
 #define DAT_ENTRY_SIZE			GENMASK(31, 28)
@@ -597,9 +595,6 @@ static irqreturn_t i3c_hci_irq_handler(int irq, void *dev_id)
 
 	if (val) {
 		reg_write(INTR_STATUS, val);
-	} else {
-		/* v1.0 does not have PIO cascaded notification bits */
-		val |= INTR_HC_PIO;
 	}
 
 	if (val & INTR_HC_RESET_CANCEL) {
@@ -610,14 +605,9 @@ static irqreturn_t i3c_hci_irq_handler(int irq, void *dev_id)
 		dev_err(&hci->master.dev, "Host Controller Internal Error\n");
 		val &= ~INTR_HC_INTERNAL_ERR;
 	}
-	if (val & INTR_HC_PIO) {
-		hci->io->irq_handler(hci, 0);
-		val &= ~INTR_HC_PIO;
-	}
-	if (val & INTR_HC_RINGS) {
-		hci->io->irq_handler(hci, val & INTR_HC_RINGS);
-		val &= ~INTR_HC_RINGS;
-	}
+
+	hci->io->irq_handler(hci);
+
 	if (val)
 		dev_err(&hci->master.dev, "unexpected INTR_STATUS %#x\n", val);
 	else
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index 13adc58400942..e8e56a8d20573 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -733,20 +733,16 @@ static void hci_dma_process_ibi(struct i3c_hci *hci, struct hci_rh_data *rh)
 	rh_reg_write(CHUNK_CONTROL, rh_reg_read(CHUNK_CONTROL) + ibi_chunks);
 }
 
-static bool hci_dma_irq_handler(struct i3c_hci *hci, unsigned int mask)
+static bool hci_dma_irq_handler(struct i3c_hci *hci)
 {
 	struct hci_rings_data *rings = hci->io_data;
 	unsigned int i;
 	bool handled = false;
 
-	for (i = 0; mask && i < rings->total; i++) {
+	for (i = 0; i < rings->total; i++) {
 		struct hci_rh_data *rh;
 		u32 status;
 
-		if (!(mask & BIT(i)))
-			continue;
-		mask &= ~BIT(i);
-
 		rh = &rings->headers[i];
 		status = rh_reg_read(INTR_STATUS);
 		DBG("rh%d status: %#x", i, status);
diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h
index aaa47ac473814..69ea1d10414b8 100644
--- a/drivers/i3c/master/mipi-i3c-hci/hci.h
+++ b/drivers/i3c/master/mipi-i3c-hci/hci.h
@@ -115,7 +115,7 @@ static inline void hci_free_xfer(struct hci_xfer *xfer, unsigned int n)
 
 /* This abstracts PIO vs DMA operations */
 struct hci_io_ops {
-	bool (*irq_handler)(struct i3c_hci *hci, unsigned int mask);
+	bool (*irq_handler)(struct i3c_hci *hci);
 	int (*queue_xfer)(struct i3c_hci *hci, struct hci_xfer *xfer, int n);
 	bool (*dequeue_xfer)(struct i3c_hci *hci, struct hci_xfer *xfer, int n);
 	int (*request_ibi)(struct i3c_hci *hci, struct i3c_dev_desc *dev,
diff --git a/drivers/i3c/master/mipi-i3c-hci/pio.c b/drivers/i3c/master/mipi-i3c-hci/pio.c
index d0272aa93599c..2fc71e6969111 100644
--- a/drivers/i3c/master/mipi-i3c-hci/pio.c
+++ b/drivers/i3c/master/mipi-i3c-hci/pio.c
@@ -979,7 +979,7 @@ static void hci_pio_recycle_ibi_slot(struct i3c_hci *hci,
 	i3c_generic_ibi_recycle_slot(dev_ibi->pool, slot);
 }
 
-static bool hci_pio_irq_handler(struct i3c_hci *hci, unsigned int unused)
+static bool hci_pio_irq_handler(struct i3c_hci *hci)
 {
 	struct hci_pio_data *pio = hci->io_data;
 	u32 status;

From 18599e93e4e814ce146186026c6abf83c14d5798 Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Mon, 30 Sep 2024 17:19:13 +0800
Subject: [PATCH 0739/1530] i3c: master: svc: Fix pm_runtime_set_suspended()
 with runtime pm enabled

It is not valid to call pm_runtime_set_suspended() for devices
with runtime PM enabled because it returns -EAGAIN if it is enabled
already and working. So, call pm_runtime_disable() before to fix it.

Cc: stable@vger.kernel.org # v5.17
Fixes: 05be23ef78f7 ("i3c: master: svc: add runtime pm support")
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Link: https://lore.kernel.org/r/20240930091913.2545510-1-ruanjinjie@huawei.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/svc-i3c-master.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index e9c8e340d861b..c53f2b27662f4 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -1891,8 +1891,8 @@ static int svc_i3c_master_probe(struct platform_device *pdev)
 rpm_disable:
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
 	pm_runtime_put_noidle(&pdev->dev);
-	pm_runtime_set_suspended(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+	pm_runtime_set_suspended(&pdev->dev);
 
 err_disable_clks:
 	svc_i3c_master_unprepare_clks(master);

From 6babe00ccd34fc65b78ef8b99754e32b4385f23d Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Wed, 16 Oct 2024 16:13:37 +0800
Subject: [PATCH 0740/1530] f2fs: fix to do sanity check on node blkaddr in
 truncate_node()

syzbot reports a f2fs bug as below:

------------[ cut here ]------------
kernel BUG at fs/f2fs/segment.c:2534!
RIP: 0010:f2fs_invalidate_blocks+0x35f/0x370 fs/f2fs/segment.c:2534
Call Trace:
 truncate_node+0x1ae/0x8c0 fs/f2fs/node.c:909
 f2fs_remove_inode_page+0x5c2/0x870 fs/f2fs/node.c:1288
 f2fs_evict_inode+0x879/0x15c0 fs/f2fs/inode.c:856
 evict+0x4e8/0x9b0 fs/inode.c:723
 f2fs_handle_failed_inode+0x271/0x2e0 fs/f2fs/inode.c:986
 f2fs_create+0x357/0x530 fs/f2fs/namei.c:394
 lookup_open fs/namei.c:3595 [inline]
 open_last_lookups fs/namei.c:3694 [inline]
 path_openat+0x1c03/0x3590 fs/namei.c:3930
 do_filp_open+0x235/0x490 fs/namei.c:3960
 do_sys_openat2+0x13e/0x1d0 fs/open.c:1415
 do_sys_open fs/open.c:1430 [inline]
 __do_sys_openat fs/open.c:1446 [inline]
 __se_sys_openat fs/open.c:1441 [inline]
 __x64_sys_openat+0x247/0x2a0 fs/open.c:1441
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0010:f2fs_invalidate_blocks+0x35f/0x370 fs/f2fs/segment.c:2534

The root cause is: on a fuzzed image, blkaddr in nat entry may be
corrupted, then it will cause system panic when using it in
f2fs_invalidate_blocks(), to avoid this, let's add sanity check on
nat blkaddr in truncate_node().

Reported-by: syzbot+33379ce4ac76acf7d0c7@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-f2fs-devel/0000000000009a6cd706224ca720@google.com/
Cc: stable@vger.kernel.org
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/node.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 59b13ff243fa8..af36c6d6542b8 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -905,6 +905,16 @@ static int truncate_node(struct dnode_of_data *dn)
 	if (err)
 		return err;
 
+	if (ni.blk_addr != NEW_ADDR &&
+		!f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC_ENHANCE)) {
+		f2fs_err_ratelimited(sbi,
+			"nat entry is corrupted, run fsck to fix it, ino:%u, "
+			"nid:%u, blkaddr:%u", ni.ino, ni.nid, ni.blk_addr);
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		f2fs_handle_error(sbi, ERROR_INCONSISTENT_NAT);
+		return -EFSCORRUPTED;
+	}
+
 	/* Deallocate node address */
 	f2fs_invalidate_blocks(sbi, ni.blk_addr);
 	dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino);

From 2d56b4e39192fb9693284ce8aa3416b517d785b7 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Wed, 16 Oct 2024 16:24:20 +0800
Subject: [PATCH 0741/1530] f2fs: multidevice: add stats in debugfs

This patch adds per-device stats in debugfs, the examples
are as below:

mkfs.f2fs -f -c /dev/vdc /dev/vdb
mount /dev/vdb /mnt/f2fs/
cat /sys/kernel/debug/f2fs/status

Multidevice stats:
  [seg:      inuse    dirty     full     free  prefree]
  #0             5        0        0     4007        0
  #1             1        0        0     8191        0

mkfs.f2fs -f -s 2 -c /dev/vdc /dev/vdb
mount /dev/vdb /mnt/f2fs
cat /sys/kernel/debug/f2fs/status

Multidevice stats:
  [seg:      inuse    dirty     full     free  prefree] [sec:      inuse    dirty     full     free  prefree]
  #0             5        0        0     4005        0                 5        0        0     2000        0
  #1             1        0        0     8191        0                 1        0        0     4095        0

Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/debug.c | 107 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/f2fs/f2fs.h  |  14 +++++++
 2 files changed, 121 insertions(+)

diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 546b8ba912613..278c8855ac0a2 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -60,6 +60,70 @@ void f2fs_update_sit_info(struct f2fs_sb_info *sbi)
 }
 
 #ifdef CONFIG_DEBUG_FS
+static void update_multidevice_stats(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_stat_info *si = F2FS_STAT(sbi);
+	struct f2fs_dev_stats *dev_stats = si->dev_stats;
+	int i, j;
+
+	if (!f2fs_is_multi_device(sbi))
+		return;
+
+	memset(dev_stats, 0, sizeof(struct f2fs_dev_stats) * sbi->s_ndevs);
+	for (i = 0; i < sbi->s_ndevs; i++) {
+		unsigned int start_segno, end_segno;
+		block_t start_blk, end_blk;
+
+		if (i == 0) {
+			start_blk = MAIN_BLKADDR(sbi);
+			end_blk = FDEV(i).end_blk + 1 - SEG0_BLKADDR(sbi);
+		} else {
+			start_blk = FDEV(i).start_blk;
+			end_blk = FDEV(i).end_blk + 1;
+		}
+
+		start_segno = GET_SEGNO(sbi, start_blk);
+		end_segno = GET_SEGNO(sbi, end_blk);
+
+		for (j = start_segno; j < end_segno; j++) {
+			unsigned int seg_blks, sec_blks;
+
+			seg_blks = get_seg_entry(sbi, j)->valid_blocks;
+
+			/* update segment stats */
+			if (IS_CURSEG(sbi, j))
+				dev_stats[i].devstats[0][DEVSTAT_INUSE]++;
+			else if (seg_blks == BLKS_PER_SEG(sbi))
+				dev_stats[i].devstats[0][DEVSTAT_FULL]++;
+			else if (seg_blks != 0)
+				dev_stats[i].devstats[0][DEVSTAT_DIRTY]++;
+			else if (!test_bit(j, FREE_I(sbi)->free_segmap))
+				dev_stats[i].devstats[0][DEVSTAT_FREE]++;
+			else
+				dev_stats[i].devstats[0][DEVSTAT_PREFREE]++;
+
+			if (!__is_large_section(sbi) ||
+				(j % SEGS_PER_SEC(sbi)) != 0)
+				continue;
+
+			sec_blks = get_sec_entry(sbi, j)->valid_blocks;
+
+			/* update section stats */
+			if (IS_CURSEC(sbi, GET_SEC_FROM_SEG(sbi, j)))
+				dev_stats[i].devstats[1][DEVSTAT_INUSE]++;
+			else if (sec_blks == BLKS_PER_SEC(sbi))
+				dev_stats[i].devstats[1][DEVSTAT_FULL]++;
+			else if (sec_blks != 0)
+				dev_stats[i].devstats[1][DEVSTAT_DIRTY]++;
+			else if (!test_bit(GET_SEC_FROM_SEG(sbi, j),
+					FREE_I(sbi)->free_secmap))
+				dev_stats[i].devstats[1][DEVSTAT_FREE]++;
+			else
+				dev_stats[i].devstats[1][DEVSTAT_PREFREE]++;
+		}
+	}
+}
+
 static void update_general_status(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_stat_info *si = F2FS_STAT(sbi);
@@ -214,6 +278,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 		si->valid_blks[type] += blks;
 	}
 
+	update_multidevice_stats(sbi);
+
 	for (i = 0; i < MAX_CALL_TYPE; i++)
 		si->cp_call_count[i] = atomic_read(&sbi->cp_call_count[i]);
 
@@ -498,6 +564,36 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->dirty_count);
 		seq_printf(s, "  - Prefree: %d\n  - Free: %d (%d)\n\n",
 			   si->prefree_count, si->free_segs, si->free_secs);
+		if (f2fs_is_multi_device(sbi)) {
+			seq_puts(s, "Multidevice stats:\n");
+			seq_printf(s, "  [seg:   %8s %8s %8s %8s %8s]",
+					"inuse", "dirty", "full", "free", "prefree");
+			if (__is_large_section(sbi))
+				seq_printf(s, " [sec:   %8s %8s %8s %8s %8s]\n",
+					"inuse", "dirty", "full", "free", "prefree");
+			else
+				seq_puts(s, "\n");
+
+			for (i = 0; i < sbi->s_ndevs; i++) {
+				seq_printf(s, "  #%-2d     %8u %8u %8u %8u %8u", i,
+					si->dev_stats[i].devstats[0][DEVSTAT_INUSE],
+					si->dev_stats[i].devstats[0][DEVSTAT_DIRTY],
+					si->dev_stats[i].devstats[0][DEVSTAT_FULL],
+					si->dev_stats[i].devstats[0][DEVSTAT_FREE],
+					si->dev_stats[i].devstats[0][DEVSTAT_PREFREE]);
+				if (!__is_large_section(sbi)) {
+					seq_puts(s, "\n");
+					continue;
+				}
+				seq_printf(s, "          %8u %8u %8u %8u %8u\n",
+					si->dev_stats[i].devstats[1][DEVSTAT_INUSE],
+					si->dev_stats[i].devstats[1][DEVSTAT_DIRTY],
+					si->dev_stats[i].devstats[1][DEVSTAT_FULL],
+					si->dev_stats[i].devstats[1][DEVSTAT_FREE],
+					si->dev_stats[i].devstats[1][DEVSTAT_PREFREE]);
+			}
+			seq_puts(s, "\n");
+		}
 		seq_printf(s, "CP calls: %d (BG: %d)\n",
 			   si->cp_call_count[TOTAL_CALL],
 			   si->cp_call_count[BACKGROUND]);
@@ -665,6 +761,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct f2fs_stat_info *si;
+	struct f2fs_dev_stats *dev_stats;
 	unsigned long flags;
 	int i;
 
@@ -672,6 +769,15 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 	if (!si)
 		return -ENOMEM;
 
+	dev_stats = f2fs_kzalloc(sbi, sizeof(struct f2fs_dev_stats) *
+						sbi->s_ndevs, GFP_KERNEL);
+	if (!dev_stats) {
+		kfree(si);
+		return -ENOMEM;
+	}
+
+	si->dev_stats = dev_stats;
+
 	si->all_area_segs = le32_to_cpu(raw_super->segment_count);
 	si->sit_area_segs = le32_to_cpu(raw_super->segment_count_sit);
 	si->nat_area_segs = le32_to_cpu(raw_super->segment_count_nat);
@@ -724,6 +830,7 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
 	list_del(&si->stat_list);
 	raw_spin_unlock_irqrestore(&f2fs_stat_lock, flags);
 
+	kfree(si->dev_stats);
 	kfree(si);
 }
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 60cf1e96a976d..dd47dbf6d9e68 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3937,6 +3937,19 @@ void f2fs_destroy_recovery_cache(void);
  * debug.c
  */
 #ifdef CONFIG_F2FS_STAT_FS
+enum {
+	DEVSTAT_INUSE,
+	DEVSTAT_DIRTY,
+	DEVSTAT_FULL,
+	DEVSTAT_FREE,
+	DEVSTAT_PREFREE,
+	DEVSTAT_MAX,
+};
+
+struct f2fs_dev_stats {
+	unsigned int devstats[2][DEVSTAT_MAX];		/* 0: segs, 1: secs */
+};
+
 struct f2fs_stat_info {
 	struct list_head stat_list;
 	struct f2fs_sb_info *sbi;
@@ -4000,6 +4013,7 @@ struct f2fs_stat_info {
 	unsigned int block_count[2];
 	unsigned int inplace_count;
 	unsigned long long base_mem, cache_mem, page_mem;
+	struct f2fs_dev_stats *dev_stats;
 };
 
 static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)

From fa08972bcb7baaf5f1f4fdf251dc08bdd3ab1cf0 Mon Sep 17 00:00:00 2001
From: Daeho Jeong <daehojeong@google.com>
Date: Tue, 15 Oct 2024 09:54:27 -0700
Subject: [PATCH 0742/1530] f2fs: decrease spare area for pinned files for
 zoned devices

Now we reclaim too much space before allocating pinned space for zoned
devices.

Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/file.c    | 3 ++-
 fs/f2fs/gc.h      | 1 +
 fs/f2fs/segment.c | 3 ++-
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index adc7d64a6f47d..348ef73bf8dd3 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1790,7 +1790,8 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset,
 
 		map.m_len = sec_blks;
 next_alloc:
-		if (has_not_enough_free_secs(sbi, 0,
+		if (has_not_enough_free_secs(sbi, 0, f2fs_sb_has_blkzoned(sbi) ?
+			ZONED_PIN_SEC_REQUIRED_COUNT :
 			GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) {
 			f2fs_down_write(&sbi->gc_lock);
 			stat_inc_gc_call_count(sbi, FOREGROUND);
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index 2914b678bf8fb..5c1eaf55e1277 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -35,6 +35,7 @@
 #define LIMIT_BOOST_ZONED_GC	25 /* percentage over total user space of boosted gc for zoned devices */
 #define DEF_MIGRATION_WINDOW_GRANULARITY_ZONED	3
 #define BOOST_GC_MULTIPLE	5
+#define ZONED_PIN_SEC_REQUIRED_COUNT	1
 
 #define DEF_GC_FAILED_PINNED_FILES	2048
 #define MAX_GC_FAILED_PINNED_FILES	USHRT_MAX
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index d91fbd1b27ba6..859d70bbc5e70 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -3237,7 +3237,8 @@ int f2fs_allocate_pinning_section(struct f2fs_sb_info *sbi)
 
 	if (f2fs_sb_has_blkzoned(sbi) && err == -EAGAIN && gc_required) {
 		f2fs_down_write(&sbi->gc_lock);
-		err = f2fs_gc_range(sbi, 0, GET_SEGNO(sbi, FDEV(0).end_blk), true, 1);
+		err = f2fs_gc_range(sbi, 0, GET_SEGNO(sbi, FDEV(0).end_blk),
+				true, ZONED_PIN_SEC_REQUIRED_COUNT);
 		f2fs_up_write(&sbi->gc_lock);
 
 		gc_required = false;

From 128d333f0dff2fbe41c546581c6f151e9d68cd4c Mon Sep 17 00:00:00 2001
From: Daeho Jeong <daehojeong@google.com>
Date: Thu, 17 Oct 2024 10:31:53 -0700
Subject: [PATCH 0743/1530] f2fs: introduce device aliasing file

F2FS should understand how the device aliasing file works and support
deleting the file after use. A device aliasing file can be created by
mkfs.f2fs tool and it can map the whole device with an extent, not
using node blocks. The file space should be pinned and normally used for
read-only usages.

Signed-off-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 Documentation/filesystems/f2fs.rst | 44 +++++++++++++++++++++++++++++
 fs/f2fs/data.c                     |  5 ++++
 fs/f2fs/extent_cache.c             | 45 +++++++++++++++++++++++++++++-
 fs/f2fs/f2fs.h                     |  5 ++++
 fs/f2fs/file.c                     | 45 +++++++++++++++++++++++++++---
 fs/f2fs/inode.c                    | 19 ++++++++++++-
 fs/f2fs/super.c                    |  4 +++
 fs/f2fs/sysfs.c                    |  2 ++
 include/uapi/linux/f2fs.h          |  1 +
 9 files changed, 164 insertions(+), 6 deletions(-)

diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst
index 68a0885fb5e69..fb7d2ee022bc0 100644
--- a/Documentation/filesystems/f2fs.rst
+++ b/Documentation/filesystems/f2fs.rst
@@ -943,3 +943,47 @@ NVMe Zoned Namespace devices
   can start before the zone-capacity and span across zone-capacity boundary.
   Such spanning segments are also considered as usable segments. All blocks
   past the zone-capacity are considered unusable in these segments.
+
+Device aliasing feature
+-----------------------
+
+f2fs can utilize a special file called a "device aliasing file." This file allows
+the entire storage device to be mapped with a single, large extent, not using
+the usual f2fs node structures. This mapped area is pinned and primarily intended
+for holding the space.
+
+Essentially, this mechanism allows a portion of the f2fs area to be temporarily
+reserved and used by another filesystem or for different purposes. Once that
+external usage is complete, the device aliasing file can be deleted, releasing
+the reserved space back to F2FS for its own use.
+
+<use-case>
+
+# ls /dev/vd*
+/dev/vdb (32GB) /dev/vdc (32GB)
+# mkfs.ext4 /dev/vdc
+# mkfs.f2fs -c /dev/vdc@vdc.file /dev/vdb
+# mount /dev/vdb /mnt/f2fs
+# ls -l /mnt/f2fs
+vdc.file
+# df -h
+/dev/vdb                            64G   33G   32G  52% /mnt/f2fs
+
+# mount -o loop /dev/vdc /mnt/ext4
+# df -h
+/dev/vdb                            64G   33G   32G  52% /mnt/f2fs
+/dev/loop7                          32G   24K   30G   1% /mnt/ext4
+# umount /mnt/ext4
+
+# f2fs_io getflags /mnt/f2fs/vdc.file
+get a flag on /mnt/f2fs/vdc.file ret=0, flags=nocow(pinned),immutable
+# f2fs_io setflags noimmutable /mnt/f2fs/vdc.file
+get a flag on noimmutable ret=0, flags=800010
+set a flag on /mnt/f2fs/vdc.file ret=0, flags=noimmutable
+# rm /mnt/f2fs/vdc.file
+# df -h
+/dev/vdb                            64G  753M   64G   2% /mnt/f2fs
+
+So, the key idea is, user can do any file operations on /dev/vdc, and
+reclaim the space after the use, while the space is counted as /data.
+That doesn't require modifying partition size and filesystem format.
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 94f7b084f6016..90fa8ab851943 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -3441,6 +3441,11 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
 
 	if (!f2fs_lookup_read_extent_cache_block(inode, index,
 						 &dn.data_blkaddr)) {
+		if (IS_DEVICE_ALIASING(inode)) {
+			err = -ENODATA;
+			goto out;
+		}
+
 		if (locked) {
 			err = f2fs_reserve_block(&dn, index);
 			goto out;
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 62ac440d94168..019c1f7b7fa53 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -24,6 +24,7 @@ bool sanity_check_extent_cache(struct inode *inode, struct page *ipage)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_extent *i_ext = &F2FS_INODE(ipage)->i_ext;
 	struct extent_info ei;
+	int devi;
 
 	get_read_extent_info(&ei, i_ext);
 
@@ -38,7 +39,36 @@ bool sanity_check_extent_cache(struct inode *inode, struct page *ipage)
 			  ei.blk, ei.fofs, ei.len);
 		return false;
 	}
-	return true;
+
+	if (!IS_DEVICE_ALIASING(inode))
+		return true;
+
+	for (devi = 0; devi < sbi->s_ndevs; devi++) {
+		if (FDEV(devi).start_blk != ei.blk ||
+				FDEV(devi).end_blk != ei.blk + ei.len - 1)
+			continue;
+
+		if (devi == 0) {
+			f2fs_warn(sbi,
+			    "%s: inode (ino=%lx) is an alias of meta device",
+			    __func__, inode->i_ino);
+			return false;
+		}
+
+		if (bdev_is_zoned(FDEV(devi).bdev)) {
+			f2fs_warn(sbi,
+			    "%s: device alias inode (ino=%lx)'s extent info "
+			    "[%u, %u, %u] maps to zoned block device",
+			    __func__, inode->i_ino, ei.blk, ei.fofs, ei.len);
+			return false;
+		}
+		return true;
+	}
+
+	f2fs_warn(sbi, "%s: device alias inode (ino=%lx)'s extent info "
+			"[%u, %u, %u] is inconsistent w/ any devices",
+			__func__, inode->i_ino, ei.blk, ei.fofs, ei.len);
+	return false;
 }
 
 static void __set_extent_info(struct extent_info *ei,
@@ -76,6 +106,9 @@ static bool __init_may_extent_tree(struct inode *inode, enum extent_type type)
 
 static bool __may_extent_tree(struct inode *inode, enum extent_type type)
 {
+	if (IS_DEVICE_ALIASING(inode) && type == EX_READ)
+		return true;
+
 	/*
 	 * for recovered files during mount do not create extents
 	 * if shrinker is not registered.
@@ -401,6 +434,11 @@ void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage)
 	if (atomic_read(&et->node_cnt) || !ei.len)
 		goto skip;
 
+	if (IS_DEVICE_ALIASING(inode)) {
+		et->largest = ei;
+		goto skip;
+	}
+
 	en = __attach_extent_node(sbi, et, &ei, NULL,
 				&et->root.rb_root.rb_node, true);
 	if (en) {
@@ -463,6 +501,11 @@ static bool __lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 		goto out;
 	}
 
+	if (IS_DEVICE_ALIASING(inode)) {
+		ret = false;
+		goto out;
+	}
+
 	en = __lookup_extent_node(&et->root, et->cached_en, pgofs);
 	if (!en)
 		goto out;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index dd47dbf6d9e68..f3ef4dc509921 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -213,6 +213,7 @@ struct f2fs_mount_info {
 #define F2FS_FEATURE_CASEFOLD			0x00001000
 #define F2FS_FEATURE_COMPRESSION		0x00002000
 #define F2FS_FEATURE_RO				0x00004000
+#define F2FS_FEATURE_DEVICE_ALIAS		0x00008000
 
 #define __F2FS_HAS_FEATURE(raw_super, mask)				\
 	((raw_super->feature & cpu_to_le32(mask)) != 0)
@@ -3046,6 +3047,7 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
 #define F2FS_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
 #define F2FS_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
 #define F2FS_CASEFOLD_FL		0x40000000 /* Casefolded file */
+#define F2FS_DEVICE_ALIAS_FL		0x80000000 /* File for aliasing a device */
 
 #define F2FS_QUOTA_DEFAULT_FL		(F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL)
 
@@ -3061,6 +3063,8 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
 /* Flags that are appropriate for non-directories/regular files. */
 #define F2FS_OTHER_FLMASK	(F2FS_NODUMP_FL | F2FS_NOATIME_FL)
 
+#define IS_DEVICE_ALIASING(inode)	(F2FS_I(inode)->i_flags & F2FS_DEVICE_ALIAS_FL)
+
 static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
 {
 	if (S_ISDIR(mode))
@@ -4526,6 +4530,7 @@ F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
 F2FS_FEATURE_FUNCS(casefold, CASEFOLD);
 F2FS_FEATURE_FUNCS(compression, COMPRESSION);
 F2FS_FEATURE_FUNCS(readonly, RO);
+F2FS_FEATURE_FUNCS(device_alias, DEVICE_ALIAS);
 
 #ifdef CONFIG_BLK_DEV_ZONED
 static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 348ef73bf8dd3..75a8b22da664d 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -725,6 +725,11 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
 
 	trace_f2fs_truncate_blocks_enter(inode, from);
 
+	if (IS_DEVICE_ALIASING(inode) && from) {
+		err = -EINVAL;
+		goto out_err;
+	}
+
 	free_from = (pgoff_t)F2FS_BLK_ALIGN(from);
 
 	if (free_from >= max_file_blocks(inode))
@@ -739,6 +744,21 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
 		goto out;
 	}
 
+	if (IS_DEVICE_ALIASING(inode)) {
+		struct extent_tree *et = F2FS_I(inode)->extent_tree[EX_READ];
+		struct extent_info ei = et->largest;
+		unsigned int i;
+
+		for (i = 0; i < ei.len; i++)
+			f2fs_invalidate_blocks(sbi, ei.blk + i);
+
+		dec_valid_block_count(sbi, inode, ei.len);
+		f2fs_update_time(sbi, REQ_TIME);
+
+		f2fs_put_page(ipage, 1);
+		goto out;
+	}
+
 	if (f2fs_has_inline_data(inode)) {
 		f2fs_truncate_inline_inode(inode, ipage, from);
 		f2fs_put_page(ipage, 1);
@@ -774,7 +794,7 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
 	/* lastly zero out the first data page */
 	if (!err)
 		err = truncate_partial_data_page(inode, from, truncate_page);
-
+out_err:
 	trace_f2fs_truncate_blocks_exit(inode, err);
 	return err;
 }
@@ -992,7 +1012,8 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		return -EPERM;
 
 	if ((attr->ia_valid & ATTR_SIZE)) {
-		if (!f2fs_is_compress_backend_ready(inode))
+		if (!f2fs_is_compress_backend_ready(inode) ||
+				IS_DEVICE_ALIASING(inode))
 			return -EOPNOTSUPP;
 		if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED) &&
 			!IS_ALIGNED(attr->ia_size,
@@ -1861,7 +1882,7 @@ static long f2fs_fallocate(struct file *file, int mode,
 		return -EIO;
 	if (!f2fs_is_checkpoint_ready(F2FS_I_SB(inode)))
 		return -ENOSPC;
-	if (!f2fs_is_compress_backend_ready(inode))
+	if (!f2fs_is_compress_backend_ready(inode) || IS_DEVICE_ALIASING(inode))
 		return -EOPNOTSUPP;
 
 	/* f2fs only support ->fallocate for regular file */
@@ -3297,6 +3318,9 @@ int f2fs_pin_file_control(struct inode *inode, bool inc)
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
+	if (IS_DEVICE_ALIASING(inode))
+		return -EINVAL;
+
 	if (fi->i_gc_failures >= sbi->gc_pin_file_threshold) {
 		f2fs_warn(sbi, "%s: Enable GC = ino %lx after %x GC trials",
 			  __func__, inode->i_ino, fi->i_gc_failures);
@@ -3327,6 +3351,9 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
 	if (f2fs_readonly(sbi->sb))
 		return -EROFS;
 
+	if (!pin && IS_DEVICE_ALIASING(inode))
+		return -EOPNOTSUPP;
+
 	ret = mnt_want_write_file(filp);
 	if (ret)
 		return ret;
@@ -3392,6 +3419,12 @@ static int f2fs_ioc_get_pin_file(struct file *filp, unsigned long arg)
 	return put_user(pin, (u32 __user *)arg);
 }
 
+static int f2fs_ioc_get_dev_alias_file(struct file *filp, unsigned long arg)
+{
+	return put_user(IS_DEVICE_ALIASING(file_inode(filp)) ? 1 : 0,
+			(u32 __user *)arg);
+}
+
 int f2fs_precache_extents(struct inode *inode)
 {
 	struct f2fs_inode_info *fi = F2FS_I(inode);
@@ -4491,6 +4524,8 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return f2fs_ioc_decompress_file(filp);
 	case F2FS_IOC_COMPRESS_FILE:
 		return f2fs_ioc_compress_file(filp);
+	case F2FS_IOC_GET_DEV_ALIAS_FILE:
+		return f2fs_ioc_get_dev_alias_file(filp, arg);
 	default:
 		return -ENOTTY;
 	}
@@ -4766,7 +4801,8 @@ static int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *iter,
 	else
 		return 0;
 
-	map.m_may_create = true;
+	if (!IS_DEVICE_ALIASING(inode))
+		map.m_may_create = true;
 	if (dio) {
 		map.m_seg_type = f2fs_rw_hint_to_seg_type(sbi,
 						inode->i_write_hint);
@@ -5203,6 +5239,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case F2FS_IOC_SET_COMPRESS_OPTION:
 	case F2FS_IOC_DECOMPRESS_FILE:
 	case F2FS_IOC_COMPRESS_FILE:
+	case F2FS_IOC_GET_DEV_ALIAS_FILE:
 		break;
 	default:
 		return -ENOIOCTLCMD;
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 10780e37fc7b6..282fd320bdb35 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -372,6 +372,19 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 		return false;
 	}
 
+	if (IS_DEVICE_ALIASING(inode)) {
+		if (!f2fs_sb_has_device_alias(sbi)) {
+			f2fs_warn(sbi, "%s: inode (ino=%lx) has device alias flag, but the feature is off",
+				  __func__, inode->i_ino);
+			return false;
+		}
+		if (!f2fs_is_pinned_file(inode)) {
+			f2fs_warn(sbi, "%s: inode (ino=%lx) has device alias flag, but is not pinned",
+				  __func__, inode->i_ino);
+			return false;
+		}
+	}
+
 	return true;
 }
 
@@ -825,7 +838,8 @@ void f2fs_evict_inode(struct inode *inode)
 	f2fs_bug_on(sbi, get_dirty_pages(inode));
 	f2fs_remove_dirty_inode(inode);
 
-	f2fs_destroy_extent_tree(inode);
+	if (!IS_DEVICE_ALIASING(inode))
+		f2fs_destroy_extent_tree(inode);
 
 	if (inode->i_nlink || is_bad_inode(inode))
 		goto no_delete;
@@ -881,6 +895,9 @@ void f2fs_evict_inode(struct inode *inode)
 		goto retry;
 	}
 
+	if (IS_DEVICE_ALIASING(inode))
+		f2fs_destroy_extent_tree(inode);
+
 	if (err) {
 		f2fs_update_inode_page(inode);
 		if (dquot_initialize_needed(inode))
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 8d4ecb2e855e6..aa14c8fce7d9f 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -834,6 +834,10 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 			set_opt(sbi, READ_EXTENT_CACHE);
 			break;
 		case Opt_noextent_cache:
+			if (F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_DEVICE_ALIAS)) {
+				f2fs_err(sbi, "device aliasing requires extent cache");
+				return -EINVAL;
+			}
 			clear_opt(sbi, READ_EXTENT_CACHE);
 			break;
 		case Opt_noinline_data:
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index c56e8c8739352..e51304bc65eae 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -1313,6 +1313,7 @@ F2FS_SB_FEATURE_RO_ATTR(sb_checksum, SB_CHKSUM);
 F2FS_SB_FEATURE_RO_ATTR(casefold, CASEFOLD);
 F2FS_SB_FEATURE_RO_ATTR(compression, COMPRESSION);
 F2FS_SB_FEATURE_RO_ATTR(readonly, RO);
+F2FS_SB_FEATURE_RO_ATTR(device_alias, DEVICE_ALIAS);
 
 static struct attribute *f2fs_sb_feat_attrs[] = {
 	ATTR_LIST(sb_encryption),
@@ -1329,6 +1330,7 @@ static struct attribute *f2fs_sb_feat_attrs[] = {
 	ATTR_LIST(sb_casefold),
 	ATTR_LIST(sb_compression),
 	ATTR_LIST(sb_readonly),
+	ATTR_LIST(sb_device_alias),
 	NULL,
 };
 ATTRIBUTE_GROUPS(f2fs_sb_feat);
diff --git a/include/uapi/linux/f2fs.h b/include/uapi/linux/f2fs.h
index 955d440be1046..f7aaf8d23e20c 100644
--- a/include/uapi/linux/f2fs.h
+++ b/include/uapi/linux/f2fs.h
@@ -43,6 +43,7 @@
 #define F2FS_IOC_DECOMPRESS_FILE	_IO(F2FS_IOCTL_MAGIC, 23)
 #define F2FS_IOC_COMPRESS_FILE		_IO(F2FS_IOCTL_MAGIC, 24)
 #define F2FS_IOC_START_ATOMIC_REPLACE	_IO(F2FS_IOCTL_MAGIC, 25)
+#define F2FS_IOC_GET_DEV_ALIAS_FILE	_IOR(F2FS_IOCTL_MAGIC, 26, __u32)
 
 /*
  * should be same as XFS_IOC_GOINGDOWN.

From 5bc5aae843128aefb1c55d769d057c92dd8a32c9 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Fri, 18 Oct 2024 14:26:36 +0800
Subject: [PATCH 0744/1530] f2fs: zone: introduce first_zoned_segno in
 f2fs_sb_info

first_zoned_segno() returns a fixed value, let's cache it in
structure f2fs_sb_info to avoid redundant calculation.

Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h    |  1 +
 fs/f2fs/segment.c |  4 ++--
 fs/f2fs/segment.h | 10 ----------
 fs/f2fs/super.c   | 13 +++++++++++++
 4 files changed, 16 insertions(+), 12 deletions(-)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index f3ef4dc509921..3c6f3cce57790 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1759,6 +1759,7 @@ struct f2fs_sb_info {
 	unsigned int dirty_device;		/* for checkpoint data flush */
 	spinlock_t dev_lock;			/* protect dirty_device */
 	bool aligned_blksize;			/* all devices has the same logical blksize */
+	unsigned int first_zoned_segno;		/* first zoned segno */
 
 	/* For write statistics */
 	u64 sectors_written_start;
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 859d70bbc5e70..216762a10e5a6 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -2711,7 +2711,7 @@ static int get_new_segment(struct f2fs_sb_info *sbi,
 		if (sbi->blkzone_alloc_policy == BLKZONE_ALLOC_PRIOR_CONV || pinning)
 			segno = 0;
 		else
-			segno = max(first_zoned_segno(sbi), *newseg);
+			segno = max(sbi->first_zoned_segno, *newseg);
 		hint = GET_SEC_FROM_SEG(sbi, segno);
 	}
 #endif
@@ -2723,7 +2723,7 @@ static int get_new_segment(struct f2fs_sb_info *sbi,
 	if (secno >= MAIN_SECS(sbi) && f2fs_sb_has_blkzoned(sbi)) {
 		/* Write only to sequential zones */
 		if (sbi->blkzone_alloc_policy == BLKZONE_ALLOC_ONLY_SEQ) {
-			hint = GET_SEC_FROM_SEG(sbi, first_zoned_segno(sbi));
+			hint = GET_SEC_FROM_SEG(sbi, sbi->first_zoned_segno);
 			secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint);
 		} else
 			secno = find_first_zero_bit(free_i->free_secmap,
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 55a01da6c4be5..8bf09fb67841c 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -974,13 +974,3 @@ static inline void wake_up_discard_thread(struct f2fs_sb_info *sbi, bool force)
 	dcc->discard_wake = true;
 	wake_up_interruptible_all(&dcc->discard_wait_queue);
 }
-
-static inline unsigned int first_zoned_segno(struct f2fs_sb_info *sbi)
-{
-	int devi;
-
-	for (devi = 0; devi < sbi->s_ndevs; devi++)
-		if (bdev_is_zoned(FDEV(devi).bdev))
-			return GET_SEGNO(sbi, FDEV(devi).start_blk);
-	return 0;
-}
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index aa14c8fce7d9f..80a53dbf1c38c 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -4221,6 +4221,16 @@ static void f2fs_record_error_work(struct work_struct *work)
 	f2fs_record_stop_reason(sbi);
 }
 
+static inline unsigned int get_first_zoned_segno(struct f2fs_sb_info *sbi)
+{
+	int devi;
+
+	for (devi = 0; devi < sbi->s_ndevs; devi++)
+		if (bdev_is_zoned(FDEV(devi).bdev))
+			return GET_SEGNO(sbi, FDEV(devi).start_blk);
+	return 0;
+}
+
 static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
@@ -4621,6 +4631,9 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	/* For write statistics */
 	sbi->sectors_written_start = f2fs_get_sectors_written(sbi);
 
+	/* get segno of first zoned block device */
+	sbi->first_zoned_segno = get_first_zoned_segno(sbi);
+
 	/* Read accumulated write IO statistics if exists */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
 	if (__exist_node_summaries(sbi))

From c3af1f13476ec23fd99c98d060a89be28c1e8871 Mon Sep 17 00:00:00 2001
From: LongPing Wei <weilongping@oppo.com>
Date: Mon, 21 Oct 2024 10:31:47 +0800
Subject: [PATCH 0745/1530] f2fs: fix the wrong f2fs_bug_on condition in
 f2fs_do_replace_block

This f2fs_bug_on was introduced by commit 2c1905042c8c ("f2fs: check
segment type in __f2fs_replace_block") when there were only 6 curseg types.
After commit d0b9e42ab615 ("f2fs: introduce inmem curseg") was introduced,
the condition should be changed to checking curseg->seg_type.

Fixes: d0b9e42ab615 ("f2fs: introduce inmem curseg")
Signed-off-by: LongPing Wei <weilongping@oppo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/segment.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 216762a10e5a6..96e7abaf42c81 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -3978,8 +3978,8 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 		}
 	}
 
-	f2fs_bug_on(sbi, !IS_DATASEG(type));
 	curseg = CURSEG_I(sbi, type);
+	f2fs_bug_on(sbi, !IS_DATASEG(curseg->seg_type));
 
 	mutex_lock(&curseg->curseg_mutex);
 	down_write(&sit_i->sentry_lock);

From 43563069e1c1df417d2eed6eca8a22fc6b04691d Mon Sep 17 00:00:00 2001
From: Yongpeng Yang <yangyongpeng1@oppo.com>
Date: Mon, 21 Oct 2024 12:48:01 +0800
Subject: [PATCH 0746/1530] f2fs: check curseg->inited before write_sum_page in
 change_curseg

In the __f2fs_init_atgc_curseg->get_atssr_segment calling,
curseg->segno is NULL_SEGNO, indicating that there is no summary
block that needs to be written.

Fixes: 093749e296e2 ("f2fs: support age threshold based garbage collection")
Signed-off-by: Yongpeng Yang <yangyongpeng1@oppo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/segment.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 96e7abaf42c81..bda7156a2d9d9 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -2926,7 +2926,8 @@ static int change_curseg(struct f2fs_sb_info *sbi, int type)
 	struct f2fs_summary_block *sum_node;
 	struct page *sum_page;
 
-	write_sum_page(sbi, curseg->sum_blk, GET_SUM_BLOCK(sbi, curseg->segno));
+	if (curseg->inited)
+		write_sum_page(sbi, curseg->sum_blk, GET_SUM_BLOCK(sbi, curseg->segno));
 
 	__set_test_and_inuse(sbi, new_segno);
 

From 84b5bb8bf0f6a78c232a20c2eecdbb8112ac2703 Mon Sep 17 00:00:00 2001
From: Qi Han <hanqi@vivo.com>
Date: Fri, 25 Oct 2024 03:18:23 -0600
Subject: [PATCH 0747/1530] f2fs: modify f2fs_is_checkpoint_ready logic to
 allow more data to be written with the CP disable

When the free segment is used up during CP disable, many write or
ioctl operations will get ENOSPC error codes, even if there are
still many blocks available. We can reproduce it in the following
steps:

dd if=/dev/zero of=f2fs.img bs=1M count=65
mkfs.f2fs -f f2fs.img
mount f2fs.img f2fs_dir -o checkpoint=disable:10%
cd f2fs_dir
i=1 ; while [[ $i -lt 50 ]] ; do (file_name=./2M_file$i ; dd \
if=/dev/random of=$file_name bs=1M count=2); i=$((i+1)); done
sync
i=1 ; while [[ $i -lt 50 ]] ; do (file_name=./2M_file$i ; truncate \
-s 1K $file_name); i=$((i+1)); done
sync
dd if=/dev/zero of=./file bs=1M count=20

In f2fs_need_SSR() function, it is allowed to use SSR to allocate
blocks when CP is disabled, so in f2fs_is_checkpoint_ready function,
can we judge the number of invalid blocks when free segment is not
enough, and return ENOSPC only if the number of invalid blocks is
also not enough.

Signed-off-by: Qi Han <hanqi@vivo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/segment.h | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 8bf09fb67841c..0f706cfc754a0 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -654,12 +654,30 @@ static inline bool has_enough_free_secs(struct f2fs_sb_info *sbi,
 	return !has_not_enough_free_secs(sbi, freed, needed);
 }
 
+static inline bool has_enough_free_blks(struct f2fs_sb_info *sbi)
+{
+	unsigned int total_free_blocks = 0;
+	unsigned int avail_user_block_count;
+
+	spin_lock(&sbi->stat_lock);
+
+	avail_user_block_count = get_available_block_count(sbi, NULL, true);
+	total_free_blocks = avail_user_block_count - (unsigned int)valid_user_blocks(sbi);
+
+	spin_unlock(&sbi->stat_lock);
+
+	return total_free_blocks > 0;
+}
+
 static inline bool f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi)
 {
 	if (likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
 		return true;
 	if (likely(has_enough_free_secs(sbi, 0, 0)))
 		return true;
+	if (!f2fs_lfs_mode(sbi) &&
+		likely(has_enough_free_blks(sbi)))
+		return true;
 	return false;
 }
 

From e63ce120b41ac5a904758a0231d43c6b328cd8fa Mon Sep 17 00:00:00 2001
From: Andrew Kreimer <algonell@gmail.com>
Date: Sun, 27 Oct 2024 16:06:08 +0200
Subject: [PATCH 0748/1530] f2fs: fix typos

Fix typos: datas -> data.

Via codespell.

Signed-off-by: Andrew Kreimer <algonell@gmail.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/debug.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 278c8855ac0a2..468828288a4a8 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -694,9 +694,9 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->ndirty_node, si->node_pages);
 		seq_printf(s, "  - dents: %4d in dirs:%4d (%4d)\n",
 			   si->ndirty_dent, si->ndirty_dirs, si->ndirty_all);
-		seq_printf(s, "  - datas: %4d in files:%4d\n",
+		seq_printf(s, "  - data: %4d in files:%4d\n",
 			   si->ndirty_data, si->ndirty_files);
-		seq_printf(s, "  - quota datas: %4d in quota files:%4d\n",
+		seq_printf(s, "  - quota data: %4d in quota files:%4d\n",
 			   si->ndirty_qdata, si->nquota_files);
 		seq_printf(s, "  - meta: %4d in %4d\n",
 			   si->ndirty_meta, si->meta_pages);

From 0c3a38a4b442893f8baca72e44a2a27d52d6cc75 Mon Sep 17 00:00:00 2001
From: Zeng Heng <zengheng4@huawei.com>
Date: Wed, 23 Oct 2024 17:48:50 +0800
Subject: [PATCH 0749/1530] f2fs: Fix not used variable 'index'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following compilation warning:
fs/f2fs/data.c:2391:10: warning: variable ‘index’ set but not used
[-Wunused-but-set-variable]
 2391 |  pgoff_t index;

Only define and set the variable index when the CONFIG_F2FS_FS_COMPRESSION
is enabled.

Fixes: db92e6c729d8 ("f2fs: convert f2fs_mpage_readpages() to use folio")
Signed-off-by: Zeng Heng <zengheng4@huawei.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 90fa8ab851943..306b86b0595d1 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2385,10 +2385,10 @@ static int f2fs_mpage_readpages(struct inode *inode,
 		.nr_cpages = 0,
 	};
 	pgoff_t nc_cluster_idx = NULL_CLUSTER;
+	pgoff_t index;
 #endif
 	unsigned nr_pages = rac ? readahead_count(rac) : 1;
 	unsigned max_nr_pages = nr_pages;
-	pgoff_t index;
 	int ret = 0;
 
 	map.m_pblk = 0;
@@ -2406,9 +2406,9 @@ static int f2fs_mpage_readpages(struct inode *inode,
 			prefetchw(&folio->flags);
 		}
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
 		index = folio_index(folio);
 
-#ifdef CONFIG_F2FS_FS_COMPRESSION
 		if (!f2fs_compressed_file(inode))
 			goto read_single_page;
 

From f10a890308a7cd8794e21f646f09827c6cb4bf5d Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Tue, 22 Oct 2024 16:36:23 +0800
Subject: [PATCH 0750/1530] f2fs: fix to avoid potential deadlock in
 f2fs_record_stop_reason()

syzbot reports deadlock issue of f2fs as below:

======================================================
WARNING: possible circular locking dependency detected
6.12.0-rc3-syzkaller-00087-gc964ced77262 #0 Not tainted
------------------------------------------------------
kswapd0/79 is trying to acquire lock:
ffff888011824088 (&sbi->sb_lock){++++}-{3:3}, at: f2fs_down_write fs/f2fs/f2fs.h:2199 [inline]
ffff888011824088 (&sbi->sb_lock){++++}-{3:3}, at: f2fs_record_stop_reason+0x52/0x1d0 fs/f2fs/super.c:4068

but task is already holding lock:
ffff88804bd92610 (sb_internal#2){.+.+}-{0:0}, at: f2fs_evict_inode+0x662/0x15c0 fs/f2fs/inode.c:842

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #2 (sb_internal#2){.+.+}-{0:0}:
       lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5825
       percpu_down_read include/linux/percpu-rwsem.h:51 [inline]
       __sb_start_write include/linux/fs.h:1716 [inline]
       sb_start_intwrite+0x4d/0x1c0 include/linux/fs.h:1899
       f2fs_evict_inode+0x662/0x15c0 fs/f2fs/inode.c:842
       evict+0x4e8/0x9b0 fs/inode.c:725
       f2fs_evict_inode+0x1a4/0x15c0 fs/f2fs/inode.c:807
       evict+0x4e8/0x9b0 fs/inode.c:725
       dispose_list fs/inode.c:774 [inline]
       prune_icache_sb+0x239/0x2f0 fs/inode.c:963
       super_cache_scan+0x38c/0x4b0 fs/super.c:223
       do_shrink_slab+0x701/0x1160 mm/shrinker.c:435
       shrink_slab+0x1093/0x14d0 mm/shrinker.c:662
       shrink_one+0x43b/0x850 mm/vmscan.c:4818
       shrink_many mm/vmscan.c:4879 [inline]
       lru_gen_shrink_node mm/vmscan.c:4957 [inline]
       shrink_node+0x3799/0x3de0 mm/vmscan.c:5937
       kswapd_shrink_node mm/vmscan.c:6765 [inline]
       balance_pgdat mm/vmscan.c:6957 [inline]
       kswapd+0x1ca3/0x3700 mm/vmscan.c:7226
       kthread+0x2f0/0x390 kernel/kthread.c:389
       ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147
       ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244

-> #1 (fs_reclaim){+.+.}-{0:0}:
       lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5825
       __fs_reclaim_acquire mm/page_alloc.c:3834 [inline]
       fs_reclaim_acquire+0x88/0x130 mm/page_alloc.c:3848
       might_alloc include/linux/sched/mm.h:318 [inline]
       prepare_alloc_pages+0x147/0x5b0 mm/page_alloc.c:4493
       __alloc_pages_noprof+0x16f/0x710 mm/page_alloc.c:4722
       alloc_pages_mpol_noprof+0x3e8/0x680 mm/mempolicy.c:2265
       alloc_pages_noprof mm/mempolicy.c:2345 [inline]
       folio_alloc_noprof+0x128/0x180 mm/mempolicy.c:2352
       filemap_alloc_folio_noprof+0xdf/0x500 mm/filemap.c:1010
       do_read_cache_folio+0x2eb/0x850 mm/filemap.c:3787
       read_mapping_folio include/linux/pagemap.h:1011 [inline]
       f2fs_commit_super+0x3c0/0x7d0 fs/f2fs/super.c:4032
       f2fs_record_stop_reason+0x13b/0x1d0 fs/f2fs/super.c:4079
       f2fs_handle_critical_error+0x2ac/0x5c0 fs/f2fs/super.c:4174
       f2fs_write_inode+0x35f/0x4d0 fs/f2fs/inode.c:785
       write_inode fs/fs-writeback.c:1503 [inline]
       __writeback_single_inode+0x711/0x10d0 fs/fs-writeback.c:1723
       writeback_single_inode+0x1f3/0x660 fs/fs-writeback.c:1779
       sync_inode_metadata+0xc4/0x120 fs/fs-writeback.c:2849
       f2fs_release_file+0xa8/0x100 fs/f2fs/file.c:1941
       __fput+0x23f/0x880 fs/file_table.c:431
       task_work_run+0x24f/0x310 kernel/task_work.c:228
       resume_user_mode_work include/linux/resume_user_mode.h:50 [inline]
       exit_to_user_mode_loop kernel/entry/common.c:114 [inline]
       exit_to_user_mode_prepare include/linux/entry-common.h:328 [inline]
       __syscall_exit_to_user_mode_work kernel/entry/common.c:207 [inline]
       syscall_exit_to_user_mode+0x168/0x370 kernel/entry/common.c:218
       do_syscall_64+0x100/0x230 arch/x86/entry/common.c:89
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

-> #0 (&sbi->sb_lock){++++}-{3:3}:
       check_prev_add kernel/locking/lockdep.c:3161 [inline]
       check_prevs_add kernel/locking/lockdep.c:3280 [inline]
       validate_chain+0x18ef/0x5920 kernel/locking/lockdep.c:3904
       __lock_acquire+0x1384/0x2050 kernel/locking/lockdep.c:5202
       lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5825
       down_write+0x99/0x220 kernel/locking/rwsem.c:1577
       f2fs_down_write fs/f2fs/f2fs.h:2199 [inline]
       f2fs_record_stop_reason+0x52/0x1d0 fs/f2fs/super.c:4068
       f2fs_handle_critical_error+0x2ac/0x5c0 fs/f2fs/super.c:4174
       f2fs_evict_inode+0xa61/0x15c0 fs/f2fs/inode.c:883
       evict+0x4e8/0x9b0 fs/inode.c:725
       f2fs_evict_inode+0x1a4/0x15c0 fs/f2fs/inode.c:807
       evict+0x4e8/0x9b0 fs/inode.c:725
       dispose_list fs/inode.c:774 [inline]
       prune_icache_sb+0x239/0x2f0 fs/inode.c:963
       super_cache_scan+0x38c/0x4b0 fs/super.c:223
       do_shrink_slab+0x701/0x1160 mm/shrinker.c:435
       shrink_slab+0x1093/0x14d0 mm/shrinker.c:662
       shrink_one+0x43b/0x850 mm/vmscan.c:4818
       shrink_many mm/vmscan.c:4879 [inline]
       lru_gen_shrink_node mm/vmscan.c:4957 [inline]
       shrink_node+0x3799/0x3de0 mm/vmscan.c:5937
       kswapd_shrink_node mm/vmscan.c:6765 [inline]
       balance_pgdat mm/vmscan.c:6957 [inline]
       kswapd+0x1ca3/0x3700 mm/vmscan.c:7226
       kthread+0x2f0/0x390 kernel/kthread.c:389
       ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147
       ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244

other info that might help us debug this:

Chain exists of:
  &sbi->sb_lock --> fs_reclaim --> sb_internal#2

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  rlock(sb_internal#2);
                               lock(fs_reclaim);
                               lock(sb_internal#2);
  lock(&sbi->sb_lock);

Root cause is there will be potential deadlock in between
below tasks:

Thread A				Kswapd
- f2fs_ioc_commit_atomic_write
 - mnt_want_write_file -- down_read lock A
					- balance_pgdat
					 - __fs_reclaim_acquire  -- lock B
					  - shrink_node
					   - prune_icache_sb
					    - dispose_list
					     - f2fs_evict_inode
					      - sb_start_intwrite  -- down_read lock A
 - f2fs_do_sync_file
  - f2fs_write_inode
   - f2fs_handle_critical_error
    - f2fs_record_stop_reason
     - f2fs_commit_super
      - read_mapping_folio
       - filemap_alloc_folio_noprof
        - fs_reclaim_acquire  -- lock B

Both threads try to acquire read lock of lock A, then its upcoming write
lock grabber will trigger deadlock.

Let's always create an asynchronous task in f2fs_handle_critical_error()
rather than calling f2fs_record_stop_reason() synchronously to avoid
this potential deadlock issue.

Fixes: b62e71be2110 ("f2fs: support errors=remount-ro|continue|panic mountoption")
Reported-by: syzbot+be4a9983e95a5e25c8d3@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/6704d667.050a0220.1e4d62.0081.GAE@google.com
Signed-off-by: Chao Yu <chao@kernel.org>
Reviewed-by: Daejun Park <daejun7.park@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/checkpoint.c |  2 +-
 fs/f2fs/f2fs.h       |  3 +--
 fs/f2fs/super.c      | 13 +++++++------
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 7f76460b721f2..efda9a0229816 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -32,7 +32,7 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io,
 	f2fs_build_fault_attr(sbi, 0, 0);
 	if (!end_io)
 		f2fs_flush_merged_writes(sbi);
-	f2fs_handle_critical_error(sbi, reason, end_io);
+	f2fs_handle_critical_error(sbi, reason);
 }
 
 /*
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 3c6f3cce57790..0ac5536277710 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3637,8 +3637,7 @@ int f2fs_quota_sync(struct super_block *sb, int type);
 loff_t max_file_blocks(struct inode *inode);
 void f2fs_quota_off_umount(struct super_block *sb);
 void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag);
-void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason,
-							bool irq_context);
+void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason);
 void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error);
 void f2fs_handle_error_async(struct f2fs_sb_info *sbi, unsigned char error);
 int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 80a53dbf1c38c..49519439b770f 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -4159,8 +4159,7 @@ static bool system_going_down(void)
 		|| system_state == SYSTEM_RESTART;
 }
 
-void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason,
-							bool irq_context)
+void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason)
 {
 	struct super_block *sb = sbi->sb;
 	bool shutdown = reason == STOP_CP_REASON_SHUTDOWN;
@@ -4172,10 +4171,12 @@ void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason,
 	if (!f2fs_hw_is_readonly(sbi)) {
 		save_stop_reason(sbi, reason);
 
-		if (irq_context && !shutdown)
-			schedule_work(&sbi->s_error_work);
-		else
-			f2fs_record_stop_reason(sbi);
+		/*
+		 * always create an asynchronous task to record stop_reason
+		 * in order to avoid potential deadlock when running into
+		 * f2fs_record_stop_reason() synchronously.
+		 */
+		schedule_work(&sbi->s_error_work);
 	}
 
 	/*

From 9395fb09e897dcd96f601715e63018fc5c69cf03 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Tue, 22 Oct 2024 10:01:49 +0800
Subject: [PATCH 0751/1530] f2fs: fix to parse temperature correctly in
 f2fs_get_segment_temp()

In __get_segment_type(), __get_segment_type_6() may return
CURSEG_COLD_DATA_PINNED or CURSEG_ALL_DATA_ATGC log type, but
following f2fs_get_segment_temp() can only handle persistent
log type, fix it.

Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h    |  5 +++--
 fs/f2fs/file.c    |  4 ++--
 fs/f2fs/segment.c | 33 +++++++++++++++++++++++++--------
 fs/f2fs/segment.h |  4 ----
 4 files changed, 30 insertions(+), 16 deletions(-)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 0ac5536277710..c13812dc7d3b5 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1019,7 +1019,7 @@ static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode,
 #define NR_CURSEG_PERSIST_TYPE	(NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE)
 #define NR_CURSEG_TYPE		(NR_CURSEG_INMEM_TYPE + NR_CURSEG_PERSIST_TYPE)
 
-enum {
+enum log_type {
 	CURSEG_HOT_DATA	= 0,	/* directory entry blocks */
 	CURSEG_WARM_DATA,	/* data blocks */
 	CURSEG_COLD_DATA,	/* multimedia or GCed data blocks */
@@ -3758,7 +3758,8 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
 			block_t old_addr, block_t new_addr,
 			unsigned char version, bool recover_curseg,
 			bool recover_newaddr);
-int f2fs_get_segment_temp(int seg_type);
+enum temp_type f2fs_get_segment_temp(struct f2fs_sb_info *sbi,
+						enum log_type seg_type);
 int f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 			block_t old_blkaddr, block_t *new_blkaddr,
 			struct f2fs_summary *sum, int type,
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 75a8b22da664d..0e7a0195eca8f 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -4858,8 +4858,8 @@ static void f2fs_dio_write_submit_io(const struct iomap_iter *iter,
 {
 	struct inode *inode = iter->inode;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	int seg_type = f2fs_rw_hint_to_seg_type(sbi, inode->i_write_hint);
-	enum temp_type temp = f2fs_get_segment_temp(seg_type);
+	enum log_type type = f2fs_rw_hint_to_seg_type(sbi, inode->i_write_hint);
+	enum temp_type temp = f2fs_get_segment_temp(sbi, type);
 
 	bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi, DATA, temp);
 	submit_bio(bio);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index bda7156a2d9d9..d8a0c50b8dfc1 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -3583,18 +3583,35 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 	}
 }
 
-int f2fs_get_segment_temp(int seg_type)
+enum temp_type f2fs_get_segment_temp(struct f2fs_sb_info *sbi,
+						enum log_type type)
 {
-	if (IS_HOT(seg_type))
-		return HOT;
-	else if (IS_WARM(seg_type))
-		return WARM;
-	return COLD;
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	enum temp_type temp = COLD;
+
+	switch (curseg->seg_type) {
+	case CURSEG_HOT_NODE:
+	case CURSEG_HOT_DATA:
+		temp = HOT;
+		break;
+	case CURSEG_WARM_NODE:
+	case CURSEG_WARM_DATA:
+		temp = WARM;
+		break;
+	case CURSEG_COLD_NODE:
+	case CURSEG_COLD_DATA:
+		temp = COLD;
+		break;
+	default:
+		f2fs_bug_on(sbi, 1);
+	}
+
+	return temp;
 }
 
 static int __get_segment_type(struct f2fs_io_info *fio)
 {
-	int type = 0;
+	enum log_type type = CURSEG_HOT_DATA;
 
 	switch (F2FS_OPTION(fio->sbi).active_logs) {
 	case 2:
@@ -3610,7 +3627,7 @@ static int __get_segment_type(struct f2fs_io_info *fio)
 		f2fs_bug_on(fio->sbi, true);
 	}
 
-	fio->temp = f2fs_get_segment_temp(type);
+	fio->temp = f2fs_get_segment_temp(fio->sbi, type);
 
 	return type;
 }
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 0f706cfc754a0..d440fdb83ca4b 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -34,10 +34,6 @@ static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi,
 	f2fs_bug_on(sbi, seg_type >= NR_PERSISTENT_LOG);
 }
 
-#define IS_HOT(t)	((t) == CURSEG_HOT_NODE || (t) == CURSEG_HOT_DATA)
-#define IS_WARM(t)	((t) == CURSEG_WARM_NODE || (t) == CURSEG_WARM_DATA)
-#define IS_COLD(t)	((t) == CURSEG_COLD_NODE || (t) == CURSEG_COLD_DATA)
-
 #define IS_CURSEG(sbi, seg)						\
 	(((seg) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) ||	\
 	 ((seg) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) ||	\

From 296b8cb34e65fa93382cf919be5a056f719c9a26 Mon Sep 17 00:00:00 2001
From: Zhiguo Niu <zhiguo.niu@unisoc.com>
Date: Tue, 29 Oct 2024 11:12:49 +0800
Subject: [PATCH 0752/1530] f2fs: fix to avoid use GC_AT when setting gc_mode
 as GC_URGENT_LOW or GC_URGENT_MID

If gc_mode is set to GC_URGENT_LOW or GC_URGENT_MID, cost benefit GC
approach should be used, but if ATGC is enabled at the same time,
Age-threshold approach will be selected, which can only do amount of
GC and it is much less than the numbers of CB approach.

some traces:
  f2fs_gc-254:48-396     [007] ..... 2311600.684028: f2fs_gc_begin: dev = (254,48), gc_type = Background GC, no_background_GC = 0, nr_free_secs = 0, nodes = 1053, dents = 2, imeta = 18, free_sec:44898, free_seg:44898, rsv_seg:239, prefree_seg:0
  f2fs_gc-254:48-396     [007] ..... 2311600.684527: f2fs_get_victim: dev = (254,48), type = No TYPE, policy = (Background GC, LFS-mode, Age-threshold), victim = 10, cost = 4294364975, ofs_unit = 1, pre_victim_secno = -1, prefree = 0, free = 44898
  f2fs_gc-254:48-396     [007] ..... 2311600.714835: f2fs_gc_end: dev = (254,48), ret = 0, seg_freed = 0, sec_freed = 0, nodes = 1562, dents = 2, imeta = 18, free_sec:44898, free_seg:44898, rsv_seg:239, prefree_seg:0
  f2fs_gc-254:48-396     [007] ..... 2311600.714843: f2fs_background_gc: dev = (254,48), wait_ms = 50, prefree = 0, free = 44898
  f2fs_gc-254:48-396     [007] ..... 2311600.771785: f2fs_gc_begin: dev = (254,48), gc_type = Background GC, no_background_GC = 0, nr_free_secs = 0, nodes = 1562, dents = 2, imeta = 18, free_sec:44898, free_seg:44898, rsv_seg:239, prefree_seg:
  f2fs_gc-254:48-396     [007] ..... 2311600.772275: f2fs_gc_end: dev = (254,48), ret = -61, seg_freed = 0, sec_freed = 0, nodes = 1562, dents = 2, imeta = 18, free_sec:44898, free_seg:44898, rsv_seg:239, prefree_seg:0

Fixes: 0e5e81114de1 ("f2fs: add GC_URGENT_LOW mode in gc_urgent")
Fixes: d98af5f45520 ("f2fs: introduce gc_urgent_mid mode")
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 Documentation/ABI/testing/sysfs-fs-f2fs | 7 +++++--
 fs/f2fs/gc.c                            | 2 ++
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index fdedf1ea944ba..513296bb6f297 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -311,10 +311,13 @@ Description:	Do background GC aggressively when set. Set to 0 by default.
 		GC approach and turns SSR mode on.
 		gc urgent low(2): lowers the bar of checking I/O idling in
 		order to process outstanding discard commands and GC a
-		little bit aggressively. uses cost benefit GC approach.
+		little bit aggressively. always uses cost benefit GC approach,
+		and will override age-threshold GC approach if ATGC is enabled
+		at the same time.
 		gc urgent mid(3): does GC forcibly in a period of given
 		gc_urgent_sleep_time and executes a mid level of I/O idling check.
-		uses cost benefit GC approach.
+		always uses cost benefit GC approach, and will override
+		age-threshold GC approach if ATGC is enabled at the same time.
 
 What:		/sys/fs/f2fs/<disk>/gc_urgent_sleep_time
 Date:		August 2017
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index e40bdd12e36d1..3e1b6d2ff3a73 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -257,6 +257,8 @@ static int select_gc_type(struct f2fs_sb_info *sbi, int gc_type)
 
 	switch (sbi->gc_mode) {
 	case GC_IDLE_CB:
+	case GC_URGENT_LOW:
+	case GC_URGENT_MID:
 		gc_mode = GC_CB;
 		break;
 	case GC_IDLE_GREEDY:

From cffaa0976fcc941a618951b56745a817befa8f91 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Tue, 29 Oct 2024 08:57:03 +0800
Subject: [PATCH 0753/1530] f2fs: clean up opened code w/ {get,set}_nid()

Just cleanup, no logic change.

Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/node.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index af36c6d6542b8..7d904f2bd5b6c 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1066,7 +1066,7 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
 	int i;
 	int idx = depth - 2;
 
-	nid[0] = le32_to_cpu(ri->i_nid[offset[0] - NODE_DIR1_BLOCK]);
+	nid[0] = get_nid(dn->inode_page, offset[0], true);
 	if (!nid[0])
 		return 0;
 
@@ -1177,7 +1177,7 @@ int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from)
 
 skip_partial:
 	while (cont) {
-		dn.nid = le32_to_cpu(ri->i_nid[offset[0] - NODE_DIR1_BLOCK]);
+		dn.nid = get_nid(page, offset[0], true);
 		switch (offset[0]) {
 		case NODE_DIR1_BLOCK:
 		case NODE_DIR2_BLOCK:
@@ -1209,13 +1209,10 @@ int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from)
 		}
 		if (err < 0)
 			goto fail;
-		if (offset[1] == 0 &&
-				ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) {
+		if (offset[1] == 0 && get_nid(page, offset[0], true)) {
 			lock_page(page);
 			BUG_ON(page->mapping != NODE_MAPPING(sbi));
-			f2fs_wait_on_page_writeback(page, NODE, true, true);
-			ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0;
-			set_page_dirty(page);
+			set_nid(page, offset[0], 0, true);
 			unlock_page(page);
 		}
 		offset[1] = 0;

From 1df2bc3c8252261860787a02f61797a914b99163 Mon Sep 17 00:00:00 2001
From: LongPing Wei <weilongping@oppo.com>
Date: Tue, 29 Oct 2024 18:49:07 +0800
Subject: [PATCH 0754/1530] f2fs: clean up the unused variable
 additional_reserved_segments

additional_reserved_segments was introduced by
commit 300a842937fb ("f2fs: fix to reserve space for IO align feature"),
and its initialization was deleted by
commit 87161a2b0aed ("f2fs: deprecate io_bits").

Signed-off-by: LongPing Wei <weilongping@oppo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h    | 1 -
 fs/f2fs/segment.h | 3 +--
 fs/f2fs/sysfs.c   | 4 +---
 3 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index c13812dc7d3b5..119706dbaefa9 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1064,7 +1064,6 @@ struct f2fs_sm_info {
 	unsigned int segment_count;	/* total # of segments */
 	unsigned int main_segments;	/* # of segments in main area */
 	unsigned int reserved_segments;	/* # of reserved segments */
-	unsigned int additional_reserved_segments;/* reserved segs for IO align feature */
 	unsigned int ovp_segments;	/* # of overprovision segments */
 
 	/* a threshold to reclaim prefree segments */
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index d440fdb83ca4b..943be4f1d6d2d 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -522,8 +522,7 @@ static inline unsigned int free_segments(struct f2fs_sb_info *sbi)
 
 static inline unsigned int reserved_segments(struct f2fs_sb_info *sbi)
 {
-	return SM_I(sbi)->reserved_segments +
-			SM_I(sbi)->additional_reserved_segments;
+	return SM_I(sbi)->reserved_segments;
 }
 
 static inline unsigned int free_sections(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index e51304bc65eae..bdbf24db667bb 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -501,9 +501,7 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
 	if (a->struct_type == RESERVED_BLOCKS) {
 		spin_lock(&sbi->stat_lock);
 		if (t > (unsigned long)(sbi->user_block_count -
-				F2FS_OPTION(sbi).root_reserved_blocks -
-				SEGS_TO_BLKS(sbi,
-				SM_I(sbi)->additional_reserved_segments))) {
+				F2FS_OPTION(sbi).root_reserved_blocks)) {
 			spin_unlock(&sbi->stat_lock);
 			return -EINVAL;
 		}

From 51d3d952c5084393d89cce0b951bb5f18eb97bb1 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Wed, 30 Oct 2024 16:17:01 +0800
Subject: [PATCH 0755/1530] f2fs: fix to convert log type to segment data type
 correctly

This patch introduces a new helper log_type_to_seg_type() to convert
log type to segment data type, and uses it to clean up opened codes
in build_curseg(), and also it fixes to convert log type before use
in do_write_page().

Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/segment.c | 36 ++++++++++++++++++++++++++++--------
 1 file changed, 28 insertions(+), 8 deletions(-)

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index d8a0c50b8dfc1..edf2a74207b35 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -3812,10 +3812,35 @@ void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino,
 	}
 }
 
+static int log_type_to_seg_type(enum log_type type)
+{
+	int seg_type = CURSEG_COLD_DATA;
+
+	switch (type) {
+	case CURSEG_HOT_DATA:
+	case CURSEG_WARM_DATA:
+	case CURSEG_COLD_DATA:
+	case CURSEG_HOT_NODE:
+	case CURSEG_WARM_NODE:
+	case CURSEG_COLD_NODE:
+		seg_type = (int)type;
+		break;
+	case CURSEG_COLD_DATA_PINNED:
+	case CURSEG_ALL_DATA_ATGC:
+		seg_type = CURSEG_COLD_DATA;
+		break;
+	default:
+		break;
+	}
+	return seg_type;
+}
+
 static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
-	int type = __get_segment_type(fio);
-	bool keep_order = (f2fs_lfs_mode(fio->sbi) && type == CURSEG_COLD_DATA);
+	enum log_type type = __get_segment_type(fio);
+	int seg_type = log_type_to_seg_type(type);
+	bool keep_order = (f2fs_lfs_mode(fio->sbi) &&
+				seg_type == CURSEG_COLD_DATA);
 
 	if (keep_order)
 		f2fs_down_read(&fio->sbi->io_order_lock);
@@ -4797,12 +4822,7 @@ static int build_curseg(struct f2fs_sb_info *sbi)
 				sizeof(struct f2fs_journal), GFP_KERNEL);
 		if (!array[i].journal)
 			return -ENOMEM;
-		if (i < NR_PERSISTENT_LOG)
-			array[i].seg_type = CURSEG_HOT_DATA + i;
-		else if (i == CURSEG_COLD_DATA_PINNED)
-			array[i].seg_type = CURSEG_COLD_DATA;
-		else if (i == CURSEG_ALL_DATA_ATGC)
-			array[i].seg_type = CURSEG_COLD_DATA;
+		array[i].seg_type = log_type_to_seg_type(i);
 		reset_curseg_fields(&array[i]);
 	}
 	return restore_curseg_summaries(sbi);

From 744e66cb8779fcbdbe20b0ec3235ef1ee9815261 Mon Sep 17 00:00:00 2001
From: Zhiguo Niu <zhiguo.niu@unisoc.com>
Date: Thu, 31 Oct 2024 13:59:52 +0800
Subject: [PATCH 0756/1530] f2fs: remove redundant atomic file check in
 defragment

f2fs_is_atomic_file(inode) is checked in f2fs_defragment_range,
so remove the redundant checking in f2fs_ioc_defragment.

Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 0e7a0195eca8f..b619f7e556406 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -2883,7 +2883,7 @@ static int f2fs_ioc_defragment(struct file *filp, unsigned long arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!S_ISREG(inode->i_mode) || f2fs_is_atomic_file(inode))
+	if (!S_ISREG(inode->i_mode))
 		return -EINVAL;
 
 	if (f2fs_readonly(sbi->sb))

From e2705dd3d16d1000f1fd8193d82447065de8c899 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Tue, 8 Oct 2024 10:48:15 +0300
Subject: [PATCH 0757/1530] fs/ntfs3: Fix warning in ni_fiemap

Use local runs_tree instead of cached. This way excludes rw_semaphore lock.

Reported-by: syzbot+1c25748a40fe79b8a119@syzkaller.appspotmail.com
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/attrib.c  |   9 ++--
 fs/ntfs3/frecord.c | 103 +++++++--------------------------------------
 fs/ntfs3/ntfs_fs.h |   3 +-
 3 files changed, 21 insertions(+), 94 deletions(-)

diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
index 0763202d00c99..8d789b017fa9b 100644
--- a/fs/ntfs3/attrib.c
+++ b/fs/ntfs3/attrib.c
@@ -977,7 +977,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 
 	/* Check for compressed frame. */
 	err = attr_is_frame_compressed(ni, attr_b, vcn >> NTFS_LZNT_CUNIT,
-				       &hint);
+				       &hint, run);
 	if (err)
 		goto out;
 
@@ -1521,16 +1521,16 @@ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr,
  * attr_is_frame_compressed - Used to detect compressed frame.
  *
  * attr - base (primary) attribute segment.
+ * run  - run to use, usually == &ni->file.run.
  * Only base segments contains valid 'attr->nres.c_unit'
  */
 int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr,
-			     CLST frame, CLST *clst_data)
+			     CLST frame, CLST *clst_data, struct runs_tree *run)
 {
 	int err;
 	u32 clst_frame;
 	CLST clen, lcn, vcn, alen, slen, vcn_next;
 	size_t idx;
-	struct runs_tree *run;
 
 	*clst_data = 0;
 
@@ -1542,7 +1542,6 @@ int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr,
 
 	clst_frame = 1u << attr->nres.c_unit;
 	vcn = frame * clst_frame;
-	run = &ni->file.run;
 
 	if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) {
 		err = attr_load_runs_vcn(ni, attr->type, attr_name(attr),
@@ -1678,7 +1677,7 @@ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size,
 	if (err)
 		goto out;
 
-	err = attr_is_frame_compressed(ni, attr_b, frame, &clst_data);
+	err = attr_is_frame_compressed(ni, attr_b, frame, &clst_data, run);
 	if (err)
 		goto out;
 
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 41c7ffad27901..c33e818b3164c 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -1900,46 +1900,6 @@ enum REPARSE_SIGN ni_parse_reparse(struct ntfs_inode *ni, struct ATTRIB *attr,
 	return REPARSE_LINK;
 }
 
-/*
- * fiemap_fill_next_extent_k - a copy of fiemap_fill_next_extent
- * but it uses 'fe_k' instead of fieinfo->fi_extents_start
- */
-static int fiemap_fill_next_extent_k(struct fiemap_extent_info *fieinfo,
-				     struct fiemap_extent *fe_k, u64 logical,
-				     u64 phys, u64 len, u32 flags)
-{
-	struct fiemap_extent extent;
-
-	/* only count the extents */
-	if (fieinfo->fi_extents_max == 0) {
-		fieinfo->fi_extents_mapped++;
-		return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
-	}
-
-	if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
-		return 1;
-
-	if (flags & FIEMAP_EXTENT_DELALLOC)
-		flags |= FIEMAP_EXTENT_UNKNOWN;
-	if (flags & FIEMAP_EXTENT_DATA_ENCRYPTED)
-		flags |= FIEMAP_EXTENT_ENCODED;
-	if (flags & (FIEMAP_EXTENT_DATA_TAIL | FIEMAP_EXTENT_DATA_INLINE))
-		flags |= FIEMAP_EXTENT_NOT_ALIGNED;
-
-	memset(&extent, 0, sizeof(extent));
-	extent.fe_logical = logical;
-	extent.fe_physical = phys;
-	extent.fe_length = len;
-	extent.fe_flags = flags;
-
-	memcpy(fe_k + fieinfo->fi_extents_mapped, &extent, sizeof(extent));
-
-	fieinfo->fi_extents_mapped++;
-	if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
-		return 1;
-	return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
-}
-
 /*
  * ni_fiemap - Helper for file_fiemap().
  *
@@ -1950,11 +1910,9 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
 	      __u64 vbo, __u64 len)
 {
 	int err = 0;
-	struct fiemap_extent *fe_k = NULL;
 	struct ntfs_sb_info *sbi = ni->mi.sbi;
 	u8 cluster_bits = sbi->cluster_bits;
-	struct runs_tree *run;
-	struct rw_semaphore *run_lock;
+	struct runs_tree run;
 	struct ATTRIB *attr;
 	CLST vcn = vbo >> cluster_bits;
 	CLST lcn, clen;
@@ -1965,13 +1923,11 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
 	u32 flags;
 	bool ok;
 
+	run_init(&run);
 	if (S_ISDIR(ni->vfs_inode.i_mode)) {
-		run = &ni->dir.alloc_run;
 		attr = ni_find_attr(ni, NULL, NULL, ATTR_ALLOC, I30_NAME,
 				    ARRAY_SIZE(I30_NAME), NULL, NULL);
-		run_lock = &ni->dir.run_lock;
 	} else {
-		run = &ni->file.run;
 		attr = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL,
 				    NULL);
 		if (!attr) {
@@ -1986,7 +1942,6 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
 				"fiemap is not supported for compressed file (cp -r)");
 			goto out;
 		}
-		run_lock = &ni->file.run_lock;
 	}
 
 	if (!attr || !attr->non_res) {
@@ -1998,51 +1953,33 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
 		goto out;
 	}
 
-	/*
-	 * To avoid lock problems replace pointer to user memory by pointer to kernel memory.
-	 */
-	fe_k = kmalloc_array(fieinfo->fi_extents_max,
-			     sizeof(struct fiemap_extent),
-			     GFP_NOFS | __GFP_ZERO);
-	if (!fe_k) {
-		err = -ENOMEM;
-		goto out;
-	}
-
 	end = vbo + len;
 	alloc_size = le64_to_cpu(attr->nres.alloc_size);
 	if (end > alloc_size)
 		end = alloc_size;
 
-	down_read(run_lock);
 
 	while (vbo < end) {
 		if (idx == -1) {
-			ok = run_lookup_entry(run, vcn, &lcn, &clen, &idx);
+			ok = run_lookup_entry(&run, vcn, &lcn, &clen, &idx);
 		} else {
 			CLST vcn_next = vcn;
 
-			ok = run_get_entry(run, ++idx, &vcn, &lcn, &clen) &&
+			ok = run_get_entry(&run, ++idx, &vcn, &lcn, &clen) &&
 			     vcn == vcn_next;
 			if (!ok)
 				vcn = vcn_next;
 		}
 
 		if (!ok) {
-			up_read(run_lock);
-			down_write(run_lock);
-
 			err = attr_load_runs_vcn(ni, attr->type,
 						 attr_name(attr),
-						 attr->name_len, run, vcn);
-
-			up_write(run_lock);
-			down_read(run_lock);
+						 attr->name_len, &run, vcn);
 
 			if (err)
 				break;
 
-			ok = run_lookup_entry(run, vcn, &lcn, &clen, &idx);
+			ok = run_lookup_entry(&run, vcn, &lcn, &clen, &idx);
 
 			if (!ok) {
 				err = -EINVAL;
@@ -2067,8 +2004,9 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
 		} else if (is_attr_compressed(attr)) {
 			CLST clst_data;
 
-			err = attr_is_frame_compressed(
-				ni, attr, vcn >> attr->nres.c_unit, &clst_data);
+			err = attr_is_frame_compressed(ni, attr,
+						       vcn >> attr->nres.c_unit,
+						       &clst_data, &run);
 			if (err)
 				break;
 			if (clst_data < NTFS_LZNT_CLUSTERS)
@@ -2097,8 +2035,8 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
 			if (vbo + dlen >= end)
 				flags |= FIEMAP_EXTENT_LAST;
 
-			err = fiemap_fill_next_extent_k(fieinfo, fe_k, vbo, lbo,
-							dlen, flags);
+			err = fiemap_fill_next_extent(fieinfo, vbo, lbo, dlen,
+						      flags);
 
 			if (err < 0)
 				break;
@@ -2119,8 +2057,7 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
 		if (vbo + bytes >= end)
 			flags |= FIEMAP_EXTENT_LAST;
 
-		err = fiemap_fill_next_extent_k(fieinfo, fe_k, vbo, lbo, bytes,
-						flags);
+		err = fiemap_fill_next_extent(fieinfo, vbo, lbo, bytes, flags);
 		if (err < 0)
 			break;
 		if (err == 1) {
@@ -2131,19 +2068,8 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
 		vbo += bytes;
 	}
 
-	up_read(run_lock);
-
-	/*
-	 * Copy to user memory out of lock
-	 */
-	if (copy_to_user(fieinfo->fi_extents_start, fe_k,
-			 fieinfo->fi_extents_max *
-				 sizeof(struct fiemap_extent))) {
-		err = -EFAULT;
-	}
-
 out:
-	kfree(fe_k);
+	run_close(&run);
 	return err;
 }
 
@@ -2672,7 +2598,8 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages,
 		down_write(&ni->file.run_lock);
 		run_truncate_around(run, le64_to_cpu(attr->nres.svcn));
 		frame = frame_vbo >> (cluster_bits + NTFS_LZNT_CUNIT);
-		err = attr_is_frame_compressed(ni, attr, frame, &clst_data);
+		err = attr_is_frame_compressed(ni, attr, frame, &clst_data,
+					       run);
 		up_write(&ni->file.run_lock);
 		if (err)
 			goto out1;
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 26e1e1379c04e..cd8e8374bb5a0 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -446,7 +446,8 @@ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr,
 			struct runs_tree *run, u64 frame, u64 frames,
 			u8 frame_bits, u32 *ondisk_size, u64 *vbo_data);
 int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr,
-			     CLST frame, CLST *clst_data);
+			     CLST frame, CLST *clst_data,
+			     struct runs_tree *run);
 int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size,
 			u64 new_valid);
 int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes);

From 5fc982fe7eca9d0cf7b25832450ebd4f7c8e1c36 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Thu, 10 Oct 2024 20:09:24 +0300
Subject: [PATCH 0758/1530] fs/ntfs3: Fix case when unmarked clusters intersect
 with zone

Reported-by: syzbot+7f3761b790fa41d0f3d5@syzkaller.appspotmail.com
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/run.c | 40 ++++++++++++++++++++++++++++++----------
 1 file changed, 30 insertions(+), 10 deletions(-)

diff --git a/fs/ntfs3/run.c b/fs/ntfs3/run.c
index 58e988cd80490..48566dff0dc92 100644
--- a/fs/ntfs3/run.c
+++ b/fs/ntfs3/run.c
@@ -1055,8 +1055,8 @@ int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino,
 {
 	int ret, err;
 	CLST next_vcn, lcn, len;
-	size_t index;
-	bool ok;
+	size_t index, done;
+	bool ok, zone;
 	struct wnd_bitmap *wnd;
 
 	ret = run_unpack(run, sbi, ino, svcn, evcn, vcn, run_buf, run_buf_size);
@@ -1087,8 +1087,9 @@ int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino,
 			continue;
 
 		down_read_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS);
+		zone = max(wnd->zone_bit, lcn) < min(wnd->zone_end, lcn + len);
 		/* Check for free blocks. */
-		ok = wnd_is_used(wnd, lcn, len);
+		ok = !zone && wnd_is_used(wnd, lcn, len);
 		up_read(&wnd->rw_lock);
 		if (ok)
 			continue;
@@ -1096,14 +1097,33 @@ int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino,
 		/* Looks like volume is corrupted. */
 		ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
 
-		if (down_write_trylock(&wnd->rw_lock)) {
-			/* Mark all zero bits as used in range [lcn, lcn+len). */
-			size_t done;
-			err = wnd_set_used_safe(wnd, lcn, len, &done);
-			up_write(&wnd->rw_lock);
-			if (err)
-				return err;
+		if (!down_write_trylock(&wnd->rw_lock))
+			continue;
+
+		if (zone) {
+			/*
+			 * Range [lcn, lcn + len) intersects with zone.
+			 * To avoid complex with zone just turn it off.
+			 */
+			wnd_zone_set(wnd, 0, 0);
+		}
+
+		/* Mark all zero bits as used in range [lcn, lcn+len). */
+		err = wnd_set_used_safe(wnd, lcn, len, &done);
+		if (zone) {
+			/* Restore zone. Lock mft run. */
+			struct rw_semaphore *lock;
+			lock = is_mounted(sbi) ? &sbi->mft.ni->file.run_lock :
+						 NULL;
+			if (lock)
+				down_read(lock);
+			ntfs_refresh_zone(sbi);
+			if (lock)
+				up_read(lock);
 		}
+		up_write(&wnd->rw_lock);
+		if (err)
+			return err;
 	}
 
 	return ret;

From 045fff619312fb013540c80cff18aab3c33048ab Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 1 Nov 2024 10:39:36 +0300
Subject: [PATCH 0759/1530] fs/ntfs3: Equivalent transition from page to folio

If using the proposed function folio_zero_range(), should one switch
from 'start + end' to 'start + length,' or use folio_zero_segment()

Fixes: 1da86618bdce ("fs: Convert aops->write_begin to take a folio")
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index e370eaf9bfe2e..f704ceef95394 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -222,7 +222,7 @@ static int ntfs_extend_initialized_size(struct file *file,
 		if (err)
 			goto out;
 
-		folio_zero_range(folio, zerofrom, folio_size(folio));
+		folio_zero_range(folio, zerofrom, folio_size(folio) - zerofrom);
 
 		err = ntfs_write_end(file, mapping, pos, len, len, folio, NULL);
 		if (err < 0)

From a8f659ce14f8f734894227ba2c5ca78c8451501e Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Mon, 21 Oct 2024 14:49:01 +0300
Subject: [PATCH 0760/1530] fs/ntfs3: Add more checks in mi_enum_attr (part 2)

Add offset check before access to attr->non_res field as mentioned in [1].

[1] https://lore.kernel.org/ntfs3/20241010110005.42792-1-llfamsec@gmail.com/

Suggested-by: lei lu <llfamsec@gmail.com>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/record.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c
index f810f0419d25e..61d53d39f3b9f 100644
--- a/fs/ntfs3/record.c
+++ b/fs/ntfs3/record.c
@@ -212,7 +212,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
 			return NULL;
 
 		if (off >= used || off < MFTRECORD_FIXUP_OFFSET_1 ||
-		    !IS_ALIGNED(off, 4)) {
+		    !IS_ALIGNED(off, 8)) {
 			return NULL;
 		}
 
@@ -236,8 +236,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
 		off += asize;
 	}
 
-	/* Can we use the first field (attr->type). */
-	/* NOTE: this code also checks attr->size availability. */
+	/*
+	 * Can we use the first fields:
+	 * attr->type,
+	 * attr->size
+	 */
 	if (off + 8 > used) {
 		static_assert(ALIGN(sizeof(enum ATTR_TYPE), 8) == 8);
 		return NULL;
@@ -259,10 +262,17 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
 
 	asize = le32_to_cpu(attr->size);
 
+	if (!IS_ALIGNED(asize, 8))
+		return NULL;
+
 	/* Check overflow and boundary. */
 	if (off + asize < off || off + asize > used)
 		return NULL;
 
+	/* Can we use the field attr->non_res. */
+	if (off + 9 > used)
+		return NULL;
+
 	/* Check size of attribute. */
 	if (!attr->non_res) {
 		/* Check resident fields. */

From db1d2b4cc9c654d18dd17c65a14de2da78bdf998 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Mon, 14 Oct 2024 13:52:42 +0300
Subject: [PATCH 0761/1530] fs/ntfs3: Add check in ntfs_extend_initialized_size

Check arguments again after lock.

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/file.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index f704ceef95394..0063e2351aa9f 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -182,13 +182,15 @@ static int ntfs_extend_initialized_size(struct file *file,
 	loff_t pos = valid;
 	int err;
 
+	if (valid >= new_valid)
+		return 0;
+
 	if (is_resident(ni)) {
 		ni->i_valid = new_valid;
 		return 0;
 	}
 
 	WARN_ON(is_compressed(ni));
-	WARN_ON(valid >= new_valid);
 
 	for (;;) {
 		u32 zerofrom, len;

From 678c1901af51f324be211dcd94351a8d64b2cad0 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 11 Oct 2024 21:36:36 +0300
Subject: [PATCH 0762/1530] fs/ntfs3: Switch to folio to release resources

As part of the process of switching from page to folio.

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/file.c | 28 +++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 0063e2351aa9f..3f96a11804c90 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -989,6 +989,7 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 	u64 frame_vbo;
 	pgoff_t index;
 	bool frame_uptodate;
+	struct folio *folio;
 
 	if (frame_size < PAGE_SIZE) {
 		/*
@@ -1043,8 +1044,9 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 			if (err) {
 				for (ip = 0; ip < pages_per_frame; ip++) {
 					page = pages[ip];
-					unlock_page(page);
-					put_page(page);
+					folio = page_folio(page);
+					folio_unlock(folio);
+					folio_put(folio);
 				}
 				goto out;
 			}
@@ -1054,9 +1056,10 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 		off = offset_in_page(valid);
 		for (; ip < pages_per_frame; ip++, off = 0) {
 			page = pages[ip];
+			folio = page_folio(page);
 			zero_user_segment(page, off, PAGE_SIZE);
 			flush_dcache_page(page);
-			SetPageUptodate(page);
+			folio_mark_uptodate(folio);
 		}
 
 		ni_lock(ni);
@@ -1065,9 +1068,10 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 
 		for (ip = 0; ip < pages_per_frame; ip++) {
 			page = pages[ip];
-			SetPageUptodate(page);
-			unlock_page(page);
-			put_page(page);
+			folio = page_folio(page);
+			folio_mark_uptodate(folio);
+			folio_unlock(folio);
+			folio_put(folio);
 		}
 
 		if (err)
@@ -1109,8 +1113,9 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 					for (ip = 0; ip < pages_per_frame;
 					     ip++) {
 						page = pages[ip];
-						unlock_page(page);
-						put_page(page);
+						folio = page_folio(page);
+						folio_unlock(folio);
+						folio_put(folio);
 					}
 					goto out;
 				}
@@ -1151,9 +1156,10 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 		for (ip = 0; ip < pages_per_frame; ip++) {
 			page = pages[ip];
 			ClearPageDirty(page);
-			SetPageUptodate(page);
-			unlock_page(page);
-			put_page(page);
+			folio = page_folio(page);
+			folio_mark_uptodate(folio);
+			folio_unlock(folio);
+			folio_put(folio);
 		}
 
 		if (err)

From bac89bb33d91cdd75092e15cf59fe6be34571142 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Thu, 10 Oct 2024 20:06:59 +0300
Subject: [PATCH 0763/1530] fs/ntfs3: Accumulated refactoring changes

Changes made to improve readability and debuggability.

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/bitmap.c  | 62 +++++++++++++---------------------------------
 fs/ntfs3/frecord.c |  1 -
 fs/ntfs3/fsntfs.c  |  2 +-
 fs/ntfs3/run.c     |  6 ++---
 4 files changed, 21 insertions(+), 50 deletions(-)

diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c
index cf4fe21a50399..04107b9507170 100644
--- a/fs/ntfs3/bitmap.c
+++ b/fs/ntfs3/bitmap.c
@@ -710,20 +710,17 @@ int wnd_set_free(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 {
 	int err = 0;
 	struct super_block *sb = wnd->sb;
-	size_t bits0 = bits;
 	u32 wbits = 8 * sb->s_blocksize;
 	size_t iw = bit >> (sb->s_blocksize_bits + 3);
 	u32 wbit = bit & (wbits - 1);
 	struct buffer_head *bh;
+	u32 op;
 
-	while (iw < wnd->nwnd && bits) {
-		u32 tail, op;
-
+	for (; iw < wnd->nwnd && bits; iw++, bit += op, bits -= op, wbit = 0) {
 		if (iw + 1 == wnd->nwnd)
 			wbits = wnd->bits_last;
 
-		tail = wbits - wbit;
-		op = min_t(u32, tail, bits);
+		op = min_t(u32, wbits - wbit, bits);
 
 		bh = wnd_map(wnd, iw);
 		if (IS_ERR(bh)) {
@@ -736,20 +733,15 @@ int wnd_set_free(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 		ntfs_bitmap_clear_le(bh->b_data, wbit, op);
 
 		wnd->free_bits[iw] += op;
+		wnd->total_zeroes += op;
 
 		set_buffer_uptodate(bh);
 		mark_buffer_dirty(bh);
 		unlock_buffer(bh);
 		put_bh(bh);
 
-		wnd->total_zeroes += op;
-		bits -= op;
-		wbit = 0;
-		iw += 1;
+		wnd_add_free_ext(wnd, bit, op, false);
 	}
-
-	wnd_add_free_ext(wnd, bit, bits0, false);
-
 	return err;
 }
 
@@ -760,20 +752,17 @@ int wnd_set_used(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 {
 	int err = 0;
 	struct super_block *sb = wnd->sb;
-	size_t bits0 = bits;
 	size_t iw = bit >> (sb->s_blocksize_bits + 3);
 	u32 wbits = 8 * sb->s_blocksize;
 	u32 wbit = bit & (wbits - 1);
 	struct buffer_head *bh;
+	u32 op;
 
-	while (iw < wnd->nwnd && bits) {
-		u32 tail, op;
-
+	for (; iw < wnd->nwnd && bits; iw++, bit += op, bits -= op, wbit = 0) {
 		if (unlikely(iw + 1 == wnd->nwnd))
 			wbits = wnd->bits_last;
 
-		tail = wbits - wbit;
-		op = min_t(u32, tail, bits);
+		op = min_t(u32, wbits - wbit, bits);
 
 		bh = wnd_map(wnd, iw);
 		if (IS_ERR(bh)) {
@@ -785,21 +774,16 @@ int wnd_set_used(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 
 		ntfs_bitmap_set_le(bh->b_data, wbit, op);
 		wnd->free_bits[iw] -= op;
+		wnd->total_zeroes -= op;
 
 		set_buffer_uptodate(bh);
 		mark_buffer_dirty(bh);
 		unlock_buffer(bh);
 		put_bh(bh);
 
-		wnd->total_zeroes -= op;
-		bits -= op;
-		wbit = 0;
-		iw += 1;
+		if (!RB_EMPTY_ROOT(&wnd->start_tree))
+			wnd_remove_free_ext(wnd, bit, op);
 	}
-
-	if (!RB_EMPTY_ROOT(&wnd->start_tree))
-		wnd_remove_free_ext(wnd, bit, bits0);
-
 	return err;
 }
 
@@ -852,15 +836,13 @@ static bool wnd_is_free_hlp(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 	size_t iw = bit >> (sb->s_blocksize_bits + 3);
 	u32 wbits = 8 * sb->s_blocksize;
 	u32 wbit = bit & (wbits - 1);
+	u32 op;
 
-	while (iw < wnd->nwnd && bits) {
-		u32 tail, op;
-
+	for (; iw < wnd->nwnd && bits; iw++, bits -= op, wbit = 0) {
 		if (unlikely(iw + 1 == wnd->nwnd))
 			wbits = wnd->bits_last;
 
-		tail = wbits - wbit;
-		op = min_t(u32, tail, bits);
+		op = min_t(u32, wbits - wbit, bits);
 
 		if (wbits != wnd->free_bits[iw]) {
 			bool ret;
@@ -875,10 +857,6 @@ static bool wnd_is_free_hlp(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 			if (!ret)
 				return false;
 		}
-
-		bits -= op;
-		wbit = 0;
-		iw += 1;
 	}
 
 	return true;
@@ -928,6 +906,7 @@ bool wnd_is_used(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 	size_t iw = bit >> (sb->s_blocksize_bits + 3);
 	u32 wbits = 8 * sb->s_blocksize;
 	u32 wbit = bit & (wbits - 1);
+	u32 op;
 	size_t end;
 	struct rb_node *n;
 	struct e_node *e;
@@ -945,14 +924,11 @@ bool wnd_is_used(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 		return false;
 
 use_wnd:
-	while (iw < wnd->nwnd && bits) {
-		u32 tail, op;
-
+	for (; iw < wnd->nwnd && bits; iw++, bits -= op, wbit = 0) {
 		if (unlikely(iw + 1 == wnd->nwnd))
 			wbits = wnd->bits_last;
 
-		tail = wbits - wbit;
-		op = min_t(u32, tail, bits);
+		op = min_t(u32, wbits - wbit, bits);
 
 		if (wnd->free_bits[iw]) {
 			bool ret;
@@ -966,10 +942,6 @@ bool wnd_is_used(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 			if (!ret)
 				goto out;
 		}
-
-		bits -= op;
-		wbit = 0;
-		iw += 1;
 	}
 	ret = true;
 
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index c33e818b3164c..8b39d0ce5f289 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -1958,7 +1958,6 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
 	if (end > alloc_size)
 		end = alloc_size;
 
-
 	while (vbo < end) {
 		if (idx == -1) {
 			ok = run_lookup_entry(&run, vcn, &lcn, &clen, &idx);
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index 0fa636038b4e4..03471bc9371cd 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -2699,4 +2699,4 @@ int ntfs_set_label(struct ntfs_sb_info *sbi, u8 *label, int len)
 out:
 	__putname(uni);
 	return err;
-}
\ No newline at end of file
+}
diff --git a/fs/ntfs3/run.c b/fs/ntfs3/run.c
index 48566dff0dc92..6e86d66197ef2 100644
--- a/fs/ntfs3/run.c
+++ b/fs/ntfs3/run.c
@@ -1112,9 +1112,9 @@ int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino,
 		err = wnd_set_used_safe(wnd, lcn, len, &done);
 		if (zone) {
 			/* Restore zone. Lock mft run. */
-			struct rw_semaphore *lock;
-			lock = is_mounted(sbi) ? &sbi->mft.ni->file.run_lock :
-						 NULL;
+			struct rw_semaphore *lock =
+				is_mounted(sbi) ? &sbi->mft.ni->file.run_lock :
+						  NULL;
 			if (lock)
 				down_read(lock);
 			ntfs_refresh_zone(sbi);

From b2c261fa8629dff2bd1143fa790797a773ace102 Mon Sep 17 00:00:00 2001
From: "Ethan D. Twardy" <ethan.twardy@gmail.com>
Date: Thu, 4 Jul 2024 09:55:42 -0500
Subject: [PATCH 0764/1530] rust: kbuild: expand rusttest target for macros

Previously, the rusttest target for the macros crate did not specify
the dependencies necessary to run the rustdoc tests. These tests rely on
the kernel crate, so add the dependencies.

Signed-off-by: Ethan D. Twardy <ethan.twardy@gmail.com>
Link: https://github.com/Rust-for-Linux/linux/issues/1076
Link: https://lore.kernel.org/r/20240704145607.17732-2-ethan.twardy@gmail.com
[ Rebased (`alloc` is gone nowadays, sysroot handling is simpler) and
  simplified (reused `rustdoc_test` rule instead of adding a new one,
  no need for `rustdoc-compiler_builtins`, removed unneeded `macros`
  explicit path). Made `vtable` example fail (avoiding to increase
  the complexity in the `rusttest` target). Removed unstable
  `-Zproc-macro-backtrace` option. Reworded accordingly. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/Makefile      | 17 +++++++++++++----
 rust/macros/lib.rs |  2 +-
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/rust/Makefile b/rust/Makefile
index 3678e79317f12..7fb05a797f7a9 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -129,6 +129,14 @@ rusttestlib-macros: private rustc_test_library_proc = yes
 rusttestlib-macros: $(src)/macros/lib.rs FORCE
 	+$(call if_changed,rustc_test_library)
 
+rusttestlib-kernel: private rustc_target_flags = \
+    --extern build_error --extern macros \
+    --extern bindings --extern uapi
+rusttestlib-kernel: $(src)/kernel/lib.rs \
+    rusttestlib-bindings rusttestlib-uapi rusttestlib-build_error \
+    $(obj)/libmacros.so $(obj)/bindings.o FORCE
+	+$(call if_changed,rustc_test_library)
+
 rusttestlib-bindings: $(src)/bindings/lib.rs FORCE
 	+$(call if_changed,rustc_test_library)
 
@@ -181,19 +189,20 @@ quiet_cmd_rustc_test = RUSTC T  $<
 
 rusttest: rusttest-macros rusttest-kernel
 
-rusttest-macros: private rustc_target_flags = --extern proc_macro
+rusttest-macros: private rustc_target_flags = --extern proc_macro \
+	--extern macros --extern kernel
 rusttest-macros: private rustdoc_test_target_flags = --crate-type proc-macro
-rusttest-macros: $(src)/macros/lib.rs FORCE
+rusttest-macros: $(src)/macros/lib.rs \
+    rusttestlib-macros rusttestlib-kernel FORCE
 	+$(call if_changed,rustc_test)
 	+$(call if_changed,rustdoc_test)
 
 rusttest-kernel: private rustc_target_flags = \
     --extern build_error --extern macros --extern bindings --extern uapi
-rusttest-kernel: $(src)/kernel/lib.rs \
+rusttest-kernel: $(src)/kernel/lib.rs rusttestlib-kernel \
     rusttestlib-build_error rusttestlib-macros rusttestlib-bindings \
     rusttestlib-uapi FORCE
 	+$(call if_changed,rustc_test)
-	+$(call if_changed,rustc_test_library)
 
 ifdef CONFIG_CC_IS_CLANG
 bindgen_c_flags = $(c_flags)
diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
index 939ae00b723a6..b16402a16acd4 100644
--- a/rust/macros/lib.rs
+++ b/rust/macros/lib.rs
@@ -132,7 +132,7 @@ pub fn module(ts: TokenStream) -> TokenStream {
 /// calls to this function at compile time:
 ///
 /// ```compile_fail
-/// # use kernel::error::VTABLE_DEFAULT_ERROR;
+/// # // Intentionally missing `use`s to simplify `rusttest`.
 /// kernel::build_error(VTABLE_DEFAULT_ERROR)
 /// ```
 ///

From 8d3f50795ac2857b0c2fd43558e078650d58d750 Mon Sep 17 00:00:00 2001
From: "Ethan D. Twardy" <ethan.twardy@gmail.com>
Date: Thu, 4 Jul 2024 09:55:43 -0500
Subject: [PATCH 0765/1530] rust: enable macros::module! tests

Previously, these tests were ignored due to a missing necessary dependency
on the `kernel` crate. Enable the tests, and update them: for both,
add the parameter to `init()`; for the first one, remove the use of a
kernel parameter mechanism that was never merged.

Signed-off-by: Ethan D. Twardy <ethan.twardy@gmail.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://github.com/Rust-for-Linux/linux/issues/1076
Link: https://lore.kernel.org/r/20240704145607.17732-3-ethan.twardy@gmail.com
[ Rebased (moved the `export` to the `rustdoc_test` rule, enable the
  firmware example too). Removed `export` for `RUST_MODFILE`. Removed
  unneeded `rust` language in examples, as well as `#[macro_use]`
  `extern`s. Reworded accordingly. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/Makefile      |  1 +
 rust/macros/lib.rs | 25 ++++++++++---------------
 2 files changed, 11 insertions(+), 15 deletions(-)

diff --git a/rust/Makefile b/rust/Makefile
index 7fb05a797f7a9..6daaa4dc21dbc 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -145,6 +145,7 @@ rusttestlib-uapi: $(src)/uapi/lib.rs FORCE
 
 quiet_cmd_rustdoc_test = RUSTDOC T $<
       cmd_rustdoc_test = \
+	RUST_MODFILE=test.rs \
 	OBJTREE=$(abspath $(objtree)) \
 	$(RUSTDOC) --test $(rust_common_flags) \
 		@$(objtree)/include/generated/rustc_cfg \
diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
index b16402a16acd4..114a5f7fc645c 100644
--- a/rust/macros/lib.rs
+++ b/rust/macros/lib.rs
@@ -30,7 +30,7 @@ use proc_macro::TokenStream;
 ///
 /// # Examples
 ///
-/// ```ignore
+/// ```
 /// use kernel::prelude::*;
 ///
 /// module!{
@@ -42,22 +42,16 @@ use proc_macro::TokenStream;
 ///     alias: ["alternate_module_name"],
 /// }
 ///
-/// struct MyModule;
+/// struct MyModule(i32);
 ///
 /// impl kernel::Module for MyModule {
-///     fn init() -> Result<Self> {
-///         // If the parameter is writeable, then the kparam lock must be
-///         // taken to read the parameter:
-///         {
-///             let lock = THIS_MODULE.kernel_param_lock();
-///             pr_info!("i32 param is:  {}\n", writeable_i32.read(&lock));
-///         }
-///         // If the parameter is read only, it can be read without locking
-///         // the kernel parameters:
-///         pr_info!("i32 param is:  {}\n", my_i32.read());
-///         Ok(Self)
+///     fn init(_module: &'static ThisModule) -> Result<Self> {
+///         let foo: i32 = 42;
+///         pr_info!("I contain:  {}\n", foo);
+///         Ok(Self(foo))
 ///     }
 /// }
+/// # fn main() {}
 /// ```
 ///
 /// ## Firmware
@@ -69,7 +63,7 @@ use proc_macro::TokenStream;
 /// build an initramfs uses this information to put the firmware files into
 /// the initramfs image.
 ///
-/// ```ignore
+/// ```
 /// use kernel::prelude::*;
 ///
 /// module!{
@@ -84,10 +78,11 @@ use proc_macro::TokenStream;
 /// struct MyDeviceDriverModule;
 ///
 /// impl kernel::Module for MyDeviceDriverModule {
-///     fn init() -> Result<Self> {
+///     fn init(_module: &'static ThisModule) -> Result<Self> {
 ///         Ok(Self)
 ///     }
 /// }
+/// # fn main() {}
 /// ```
 ///
 /// # Supported argument types

From 7e06561fcd9636b6483c5fcd8fe935475f4944f8 Mon Sep 17 00:00:00 2001
From: "Ethan D. Twardy" <ethan.twardy@gmail.com>
Date: Thu, 4 Jul 2024 09:55:44 -0500
Subject: [PATCH 0766/1530] rust: macros: enable paste! use from macro_rules!

According to the rustdoc for the proc_macro crate[1], tokens captured
from a "macro variable" (e.g. from within macro_rules!) may be delimited
by invisible tokens and be contained within a proc_macro::Group.

Previously, this scenario was not handled by macros::paste, which caused
a proc-macro panic when the corresponding tests are enabled. Enable the
tests, and handle this case by making macros::paste::concat recursive.

Link: https://doc.rust-lang.org/stable/proc_macro/enum.Delimiter.html [1]
Signed-off-by: Ethan D. Twardy <ethan.twardy@gmail.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://github.com/Rust-for-Linux/linux/issues/1076
Link: https://lore.kernel.org/r/20240704145607.17732-4-ethan.twardy@gmail.com
[ Rebased (one fix was already applied) and reworded. Remove unneeded
  `rust` as language in examples. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/macros/lib.rs   | 42 ++++++++++++++++++++++++++++++++++--------
 rust/macros/paste.rs | 15 ++++++++++++---
 2 files changed, 46 insertions(+), 11 deletions(-)

diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
index 114a5f7fc645c..83a041570e1ee 100644
--- a/rust/macros/lib.rs
+++ b/rust/macros/lib.rs
@@ -304,12 +304,25 @@ pub fn pinned_drop(args: TokenStream, input: TokenStream) -> TokenStream {
 ///
 /// # Example
 ///
-/// ```ignore
-/// use kernel::macro::paste;
-///
+/// ```
+/// # const binder_driver_return_protocol_BR_OK: u32 = 0;
+/// # const binder_driver_return_protocol_BR_ERROR: u32 = 1;
+/// # const binder_driver_return_protocol_BR_TRANSACTION: u32 = 2;
+/// # const binder_driver_return_protocol_BR_REPLY: u32 = 3;
+/// # const binder_driver_return_protocol_BR_DEAD_REPLY: u32 = 4;
+/// # const binder_driver_return_protocol_BR_TRANSACTION_COMPLETE: u32 = 5;
+/// # const binder_driver_return_protocol_BR_INCREFS: u32 = 6;
+/// # const binder_driver_return_protocol_BR_ACQUIRE: u32 = 7;
+/// # const binder_driver_return_protocol_BR_RELEASE: u32 = 8;
+/// # const binder_driver_return_protocol_BR_DECREFS: u32 = 9;
+/// # const binder_driver_return_protocol_BR_NOOP: u32 = 10;
+/// # const binder_driver_return_protocol_BR_SPAWN_LOOPER: u32 = 11;
+/// # const binder_driver_return_protocol_BR_DEAD_BINDER: u32 = 12;
+/// # const binder_driver_return_protocol_BR_CLEAR_DEATH_NOTIFICATION_DONE: u32 = 13;
+/// # const binder_driver_return_protocol_BR_FAILED_REPLY: u32 = 14;
 /// macro_rules! pub_no_prefix {
 ///     ($prefix:ident, $($newname:ident),+) => {
-///         paste! {
+///         kernel::macros::paste! {
 ///             $(pub(crate) const $newname: u32 = [<$prefix $newname>];)+
 ///         }
 ///     };
@@ -348,9 +361,22 @@ pub fn pinned_drop(args: TokenStream, input: TokenStream) -> TokenStream {
 /// * `lower`: change the identifier to lower case.
 /// * `upper`: change the identifier to upper case.
 ///
-/// ```ignore
-/// use kernel::macro::paste;
-///
+/// ```
+/// # const binder_driver_return_protocol_BR_OK: u32 = 0;
+/// # const binder_driver_return_protocol_BR_ERROR: u32 = 1;
+/// # const binder_driver_return_protocol_BR_TRANSACTION: u32 = 2;
+/// # const binder_driver_return_protocol_BR_REPLY: u32 = 3;
+/// # const binder_driver_return_protocol_BR_DEAD_REPLY: u32 = 4;
+/// # const binder_driver_return_protocol_BR_TRANSACTION_COMPLETE: u32 = 5;
+/// # const binder_driver_return_protocol_BR_INCREFS: u32 = 6;
+/// # const binder_driver_return_protocol_BR_ACQUIRE: u32 = 7;
+/// # const binder_driver_return_protocol_BR_RELEASE: u32 = 8;
+/// # const binder_driver_return_protocol_BR_DECREFS: u32 = 9;
+/// # const binder_driver_return_protocol_BR_NOOP: u32 = 10;
+/// # const binder_driver_return_protocol_BR_SPAWN_LOOPER: u32 = 11;
+/// # const binder_driver_return_protocol_BR_DEAD_BINDER: u32 = 12;
+/// # const binder_driver_return_protocol_BR_CLEAR_DEATH_NOTIFICATION_DONE: u32 = 13;
+/// # const binder_driver_return_protocol_BR_FAILED_REPLY: u32 = 14;
 /// macro_rules! pub_no_prefix {
 ///     ($prefix:ident, $($newname:ident),+) => {
 ///         kernel::macros::paste! {
@@ -385,7 +411,7 @@ pub fn pinned_drop(args: TokenStream, input: TokenStream) -> TokenStream {
 ///
 /// Literals can also be concatenated with other identifiers:
 ///
-/// ```ignore
+/// ```
 /// macro_rules! create_numbered_fn {
 ///     ($name:literal, $val:literal) => {
 ///         kernel::macros::paste! {
diff --git a/rust/macros/paste.rs b/rust/macros/paste.rs
index f40d42b35b586..6529a387673fb 100644
--- a/rust/macros/paste.rs
+++ b/rust/macros/paste.rs
@@ -2,7 +2,7 @@
 
 use proc_macro::{Delimiter, Group, Ident, Spacing, Span, TokenTree};
 
-fn concat(tokens: &[TokenTree], group_span: Span) -> TokenTree {
+fn concat_helper(tokens: &[TokenTree]) -> Vec<(String, Span)> {
     let mut tokens = tokens.iter();
     let mut segments = Vec::new();
     let mut span = None;
@@ -46,12 +46,21 @@ fn concat(tokens: &[TokenTree], group_span: Span) -> TokenTree {
                 };
                 segments.push((value, sp));
             }
-            _ => panic!("unexpected token in paste segments"),
+            Some(TokenTree::Group(group)) if group.delimiter() == Delimiter::None => {
+                let tokens = group.stream().into_iter().collect::<Vec<TokenTree>>();
+                segments.append(&mut concat_helper(tokens.as_slice()));
+            }
+            token => panic!("unexpected token in paste segments: {:?}", token),
         };
     }
 
+    segments
+}
+
+fn concat(tokens: &[TokenTree], group_span: Span) -> TokenTree {
+    let segments = concat_helper(tokens);
     let pasted: String = segments.into_iter().map(|x| x.0).collect();
-    TokenTree::Ident(Ident::new(&pasted, span.unwrap_or(group_span)))
+    TokenTree::Ident(Ident::new(&pasted, group_span))
 }
 
 pub(crate) fn expand(tokens: &mut Vec<TokenTree>) {

From ae7851c29747fa3765ecb722fe722117a346f988 Mon Sep 17 00:00:00 2001
From: "Ethan D. Twardy" <ethan.twardy@gmail.com>
Date: Thu, 4 Jul 2024 09:55:45 -0500
Subject: [PATCH 0767/1530] rust: macros: enable the rest of the tests

Now that the rusttest target for the macros crate is compiled with the
kernel crate as a dependency, the rest of the rustdoc tests can be
enabled.

Signed-off-by: Ethan D. Twardy <ethan.twardy@gmail.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://github.com/Rust-for-Linux/linux/issues/1076
Link: https://lore.kernel.org/r/20240704145607.17732-5-ethan.twardy@gmail.com
[ Rebased (use `K{Box,Vec}` instead, enable `lint_reasons` feature).
  Remove unneeded `rust` as language in examples, as well as
  `#[macro_use]` `extern`s. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/macros/lib.rs | 59 +++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 50 insertions(+), 9 deletions(-)

diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
index 83a041570e1ee..4ab94e44adfe3 100644
--- a/rust/macros/lib.rs
+++ b/rust/macros/lib.rs
@@ -137,7 +137,7 @@ pub fn module(ts: TokenStream) -> TokenStream {
 ///
 /// # Examples
 ///
-/// ```ignore
+/// ```
 /// use kernel::error::VTABLE_DEFAULT_ERROR;
 /// use kernel::prelude::*;
 ///
@@ -182,12 +182,27 @@ pub fn vtable(attr: TokenStream, ts: TokenStream) -> TokenStream {
 ///
 /// # Examples
 ///
-/// ```ignore
-/// use kernel::macro::concat_idents;
+/// ```
+/// # const binder_driver_return_protocol_BR_OK: u32 = 0;
+/// # const binder_driver_return_protocol_BR_ERROR: u32 = 1;
+/// # const binder_driver_return_protocol_BR_TRANSACTION: u32 = 2;
+/// # const binder_driver_return_protocol_BR_REPLY: u32 = 3;
+/// # const binder_driver_return_protocol_BR_DEAD_REPLY: u32 = 4;
+/// # const binder_driver_return_protocol_BR_TRANSACTION_COMPLETE: u32 = 5;
+/// # const binder_driver_return_protocol_BR_INCREFS: u32 = 6;
+/// # const binder_driver_return_protocol_BR_ACQUIRE: u32 = 7;
+/// # const binder_driver_return_protocol_BR_RELEASE: u32 = 8;
+/// # const binder_driver_return_protocol_BR_DECREFS: u32 = 9;
+/// # const binder_driver_return_protocol_BR_NOOP: u32 = 10;
+/// # const binder_driver_return_protocol_BR_SPAWN_LOOPER: u32 = 11;
+/// # const binder_driver_return_protocol_BR_DEAD_BINDER: u32 = 12;
+/// # const binder_driver_return_protocol_BR_CLEAR_DEATH_NOTIFICATION_DONE: u32 = 13;
+/// # const binder_driver_return_protocol_BR_FAILED_REPLY: u32 = 14;
+/// use kernel::macros::concat_idents;
 ///
 /// macro_rules! pub_no_prefix {
 ///     ($prefix:ident, $($newname:ident),+) => {
-///         $(pub(crate) const $newname: u32 = kernel::macros::concat_idents!($prefix, $newname);)+
+///         $(pub(crate) const $newname: u32 = concat_idents!($prefix, $newname);)+
 ///     };
 /// }
 ///
@@ -233,7 +248,11 @@ pub fn concat_idents(ts: TokenStream) -> TokenStream {
 ///
 /// # Examples
 ///
-/// ```rust,ignore
+/// ```
+/// # #![feature(lint_reasons)]
+/// # use kernel::prelude::*;
+/// # use std::{sync::Mutex, process::Command};
+/// # use kernel::macros::pin_data;
 /// #[pin_data]
 /// struct DriverData {
 ///     #[pin]
@@ -242,7 +261,17 @@ pub fn concat_idents(ts: TokenStream) -> TokenStream {
 /// }
 /// ```
 ///
-/// ```rust,ignore
+/// ```
+/// # #![feature(lint_reasons)]
+/// # use kernel::prelude::*;
+/// # use std::{sync::Mutex, process::Command};
+/// # use core::pin::Pin;
+/// # pub struct Info;
+/// # mod bindings {
+/// #     pub unsafe fn destroy_info(_ptr: *mut super::Info) {}
+/// # }
+/// use kernel::macros::{pin_data, pinned_drop};
+///
 /// #[pin_data(PinnedDrop)]
 /// struct DriverData {
 ///     #[pin]
@@ -257,6 +286,7 @@ pub fn concat_idents(ts: TokenStream) -> TokenStream {
 ///         unsafe { bindings::destroy_info(self.raw_info) };
 ///     }
 /// }
+/// # fn main() {}
 /// ```
 ///
 /// [`pin_init!`]: ../kernel/macro.pin_init.html
@@ -272,13 +302,22 @@ pub fn pin_data(inner: TokenStream, item: TokenStream) -> TokenStream {
 ///
 /// # Examples
 ///
-/// ```rust,ignore
+/// ```
+/// # #![feature(lint_reasons)]
+/// # use kernel::prelude::*;
+/// # use macros::{pin_data, pinned_drop};
+/// # use std::{sync::Mutex, process::Command};
+/// # use core::pin::Pin;
+/// # mod bindings {
+/// #     pub struct Info;
+/// #     pub unsafe fn destroy_info(_ptr: *mut Info) {}
+/// # }
 /// #[pin_data(PinnedDrop)]
 /// struct DriverData {
 ///     #[pin]
 ///     queue: Mutex<KVec<Command>>,
 ///     buf: KBox<[u8; 1024 * 1024]>,
-///     raw_info: *mut Info,
+///     raw_info: *mut bindings::Info,
 /// }
 ///
 /// #[pinned_drop]
@@ -439,7 +478,9 @@ pub fn paste(input: TokenStream) -> TokenStream {
 ///
 /// # Examples
 ///
-/// ```rust,ignore
+/// ```
+/// use kernel::macros::Zeroable;
+///
 /// #[derive(Zeroable)]
 /// pub struct DriverData {
 ///     id: i64,

From 07dc3a6de33098b0dd2ab73ef43fe721abed4825 Mon Sep 17 00:00:00 2001
From: Tengda Wu <wutengda@huaweicloud.com>
Date: Mon, 21 Oct 2024 11:02:00 +0000
Subject: [PATCH 0768/1530] perf stat: Support inherit events during fork() for
 bperf

bperf has a nice ability to share PMUs, but it still does not support
inherit events during fork(), resulting in some deviations in its stat
results compared with perf.

perf stat result:
$ ./perf stat -e cycles,instructions -- ./perf test -w sqrtloop
   Performance counter stats for './perf test -w sqrtloop':

       2,316,038,116      cycles
       2,859,350,725      instructions

         1.009603637 seconds time elapsed

         1.004196000 seconds user
         0.003950000 seconds sys

bperf stat result:
$ ./perf stat --bpf-counters -e cycles,instructions -- \
      ./perf test -w sqrtloop

   Performance counter stats for './perf test -w sqrtloop':

          18,762,093      cycles
          23,487,766      instructions

         1.008913769 seconds time elapsed

         1.003248000 seconds user
         0.004069000 seconds sys

In order to support event inheritance, two new bpf programs are added
to monitor the fork and exit of tasks respectively. When a task is
created, add it to the filter map to enable counting, and reuse the
`accum_key` of its parent task to count together with the parent task.
When a task exits, remove it from the filter map to disable counting.

After support:
$ ./perf stat --bpf-counters -e cycles,instructions -- \
      ./perf test -w sqrtloop

 Performance counter stats for './perf test -w sqrtloop':

     2,316,252,189      cycles
     2,859,946,547      instructions

       1.009422314 seconds time elapsed

       1.003597000 seconds user
       0.004270000 seconds sys

Signed-off-by: Tengda Wu <wutengda@huaweicloud.com>
Cc: song@kernel.org
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20241021110201.325617-2-wutengda@huaweicloud.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-stat.c                     |  1 +
 tools/perf/util/bpf_counter.c                 | 35 +++++--
 tools/perf/util/bpf_skel/bperf_follower.bpf.c | 98 +++++++++++++++++--
 tools/perf/util/bpf_skel/bperf_u.h            |  5 +
 tools/perf/util/target.h                      |  1 +
 5 files changed, 126 insertions(+), 14 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index c12158d99353d..fdf5172646a59 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2641,6 +2641,7 @@ int cmd_stat(int argc, const char **argv)
 	} else if (big_num_opt == 0) /* User passed --no-big-num */
 		stat_config.big_num = false;
 
+	target.inherit = !stat_config.no_inherit;
 	err = target__validate(&target);
 	if (err) {
 		target__strerror(&target, err, errbuf, BUFSIZ);
diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c
index 7a8af60e0f515..73fcafbffc6a6 100644
--- a/tools/perf/util/bpf_counter.c
+++ b/tools/perf/util/bpf_counter.c
@@ -394,6 +394,7 @@ static int bperf_check_target(struct evsel *evsel,
 }
 
 static	struct perf_cpu_map *all_cpu_map;
+static __u32 filter_entry_cnt;
 
 static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd,
 				       struct perf_event_attr_map_entry *entry)
@@ -444,12 +445,32 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd,
 	return err;
 }
 
+static int bperf_attach_follower_program(struct bperf_follower_bpf *skel,
+					 enum bperf_filter_type filter_type,
+					 bool inherit)
+{
+	struct bpf_link *link;
+	int err = 0;
+
+	if ((filter_type == BPERF_FILTER_PID ||
+	    filter_type == BPERF_FILTER_TGID) && inherit)
+		/* attach all follower bpf progs to enable event inheritance */
+		err = bperf_follower_bpf__attach(skel);
+	else {
+		link = bpf_program__attach(skel->progs.fexit_XXX);
+		if (IS_ERR(link))
+			err = PTR_ERR(link);
+	}
+
+	return err;
+}
+
 static int bperf__load(struct evsel *evsel, struct target *target)
 {
 	struct perf_event_attr_map_entry entry = {0xffffffff, 0xffffffff};
 	int attr_map_fd, diff_map_fd = -1, err;
 	enum bperf_filter_type filter_type;
-	__u32 filter_entry_cnt, i;
+	__u32 i;
 
 	if (bperf_check_target(evsel, target, &filter_type, &filter_entry_cnt))
 		return -1;
@@ -529,9 +550,6 @@ static int bperf__load(struct evsel *evsel, struct target *target)
 	/* set up reading map */
 	bpf_map__set_max_entries(evsel->follower_skel->maps.accum_readings,
 				 filter_entry_cnt);
-	/* set up follower filter based on target */
-	bpf_map__set_max_entries(evsel->follower_skel->maps.filter,
-				 filter_entry_cnt);
 	err = bperf_follower_bpf__load(evsel->follower_skel);
 	if (err) {
 		pr_err("Failed to load follower skeleton\n");
@@ -543,6 +561,7 @@ static int bperf__load(struct evsel *evsel, struct target *target)
 	for (i = 0; i < filter_entry_cnt; i++) {
 		int filter_map_fd;
 		__u32 key;
+		struct bperf_filter_value fval = { i, 0 };
 
 		if (filter_type == BPERF_FILTER_PID ||
 		    filter_type == BPERF_FILTER_TGID)
@@ -553,12 +572,14 @@ static int bperf__load(struct evsel *evsel, struct target *target)
 			break;
 
 		filter_map_fd = bpf_map__fd(evsel->follower_skel->maps.filter);
-		bpf_map_update_elem(filter_map_fd, &key, &i, BPF_ANY);
+		bpf_map_update_elem(filter_map_fd, &key, &fval, BPF_ANY);
 	}
 
 	evsel->follower_skel->bss->type = filter_type;
+	evsel->follower_skel->bss->inherit = target->inherit;
 
-	err = bperf_follower_bpf__attach(evsel->follower_skel);
+	err = bperf_attach_follower_program(evsel->follower_skel, filter_type,
+					    target->inherit);
 
 out:
 	if (err && evsel->bperf_leader_link_fd >= 0)
@@ -623,7 +644,7 @@ static int bperf__read(struct evsel *evsel)
 	bperf_sync_counters(evsel);
 	reading_map_fd = bpf_map__fd(skel->maps.accum_readings);
 
-	for (i = 0; i < bpf_map__max_entries(skel->maps.accum_readings); i++) {
+	for (i = 0; i < filter_entry_cnt; i++) {
 		struct perf_cpu entry;
 		__u32 cpu;
 
diff --git a/tools/perf/util/bpf_skel/bperf_follower.bpf.c b/tools/perf/util/bpf_skel/bperf_follower.bpf.c
index f193998530d43..0595063139a3d 100644
--- a/tools/perf/util/bpf_skel/bperf_follower.bpf.c
+++ b/tools/perf/util/bpf_skel/bperf_follower.bpf.c
@@ -5,6 +5,8 @@
 #include <bpf/bpf_tracing.h>
 #include "bperf_u.h"
 
+#define MAX_ENTRIES 102400
+
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
 	__uint(key_size, sizeof(__u32));
@@ -22,25 +24,29 @@ struct {
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
 	__uint(key_size, sizeof(__u32));
-	__uint(value_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bperf_filter_value));
+	__uint(max_entries, MAX_ENTRIES);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
 } filter SEC(".maps");
 
 enum bperf_filter_type type = 0;
 int enabled = 0;
+int inherit;
 
 SEC("fexit/XXX")
 int BPF_PROG(fexit_XXX)
 {
 	struct bpf_perf_event_value *diff_val, *accum_val;
 	__u32 filter_key, zero = 0;
-	__u32 *accum_key;
+	__u32 accum_key;
+	struct bperf_filter_value *fval;
 
 	if (!enabled)
 		return 0;
 
 	switch (type) {
 	case BPERF_FILTER_GLOBAL:
-		accum_key = &zero;
+		accum_key = zero;
 		goto do_add;
 	case BPERF_FILTER_CPU:
 		filter_key = bpf_get_smp_processor_id();
@@ -49,22 +55,34 @@ int BPF_PROG(fexit_XXX)
 		filter_key = bpf_get_current_pid_tgid() & 0xffffffff;
 		break;
 	case BPERF_FILTER_TGID:
-		filter_key = bpf_get_current_pid_tgid() >> 32;
+		/* Use pid as the filter_key to exclude new task counts
+		 * when inherit is disabled. Don't worry about the existing
+		 * children in TGID losing their counts, bpf_counter has
+		 * already added them to the filter map via perf_thread_map
+		 * before this bpf prog runs.
+		 */
+		filter_key = inherit ?
+			     bpf_get_current_pid_tgid() >> 32 :
+			     bpf_get_current_pid_tgid() & 0xffffffff;
 		break;
 	default:
 		return 0;
 	}
 
-	accum_key = bpf_map_lookup_elem(&filter, &filter_key);
-	if (!accum_key)
+	fval = bpf_map_lookup_elem(&filter, &filter_key);
+	if (!fval)
 		return 0;
 
+	accum_key = fval->accum_key;
+	if (fval->exited)
+		bpf_map_delete_elem(&filter, &filter_key);
+
 do_add:
 	diff_val = bpf_map_lookup_elem(&diff_readings, &zero);
 	if (!diff_val)
 		return 0;
 
-	accum_val = bpf_map_lookup_elem(&accum_readings, accum_key);
+	accum_val = bpf_map_lookup_elem(&accum_readings, &accum_key);
 	if (!accum_val)
 		return 0;
 
@@ -75,4 +93,70 @@ int BPF_PROG(fexit_XXX)
 	return 0;
 }
 
+/* The program is only used for PID or TGID filter types. */
+SEC("tp_btf/task_newtask")
+int BPF_PROG(on_newtask, struct task_struct *task, __u64 clone_flags)
+{
+	__u32 parent_key, child_key;
+	struct bperf_filter_value *parent_fval;
+	struct bperf_filter_value child_fval = { 0 };
+
+	if (!enabled)
+		return 0;
+
+	switch (type) {
+	case BPERF_FILTER_PID:
+		parent_key = bpf_get_current_pid_tgid() & 0xffffffff;
+		child_key = task->pid;
+		break;
+	case BPERF_FILTER_TGID:
+		parent_key = bpf_get_current_pid_tgid() >> 32;
+		child_key = task->tgid;
+		if (child_key == parent_key)
+			return 0;
+		break;
+	default:
+		return 0;
+	}
+
+	/* Check if the current task is one of the target tasks to be counted */
+	parent_fval = bpf_map_lookup_elem(&filter, &parent_key);
+	if (!parent_fval)
+		return 0;
+
+	/* Start counting for the new task by adding it into filter map,
+	 * inherit the accum key of its parent task so that they can be
+	 * counted together.
+	 */
+	child_fval.accum_key = parent_fval->accum_key;
+	child_fval.exited = 0;
+	bpf_map_update_elem(&filter, &child_key, &child_fval, BPF_NOEXIST);
+
+	return 0;
+}
+
+/* The program is only used for PID or TGID filter types. */
+SEC("tp_btf/sched_process_exit")
+int BPF_PROG(on_exittask, struct task_struct *task)
+{
+	__u32 pid;
+	struct bperf_filter_value *fval;
+
+	if (!enabled)
+		return 0;
+
+	/* Stop counting for this task by removing it from filter map.
+	 * For TGID type, if the pid can be found in the map, it means that
+	 * this pid belongs to the leader task. After the task exits, the
+	 * tgid of its child tasks (if any) will be 1, so the pid can be
+	 * safely removed.
+	 */
+	pid = task->pid;
+	fval = bpf_map_lookup_elem(&filter, &pid);
+	if (fval)
+		fval->exited = 1;
+
+	return 0;
+}
+
 char LICENSE[] SEC("license") = "Dual BSD/GPL";
diff --git a/tools/perf/util/bpf_skel/bperf_u.h b/tools/perf/util/bpf_skel/bperf_u.h
index 1ce0c2c905c11..4a4a753980bef 100644
--- a/tools/perf/util/bpf_skel/bperf_u.h
+++ b/tools/perf/util/bpf_skel/bperf_u.h
@@ -11,4 +11,9 @@ enum bperf_filter_type {
 	BPERF_FILTER_TGID,
 };
 
+struct bperf_filter_value {
+	__u32 accum_key;
+	__u8 exited;
+};
+
 #endif /* __BPERF_STAT_U_H */
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index d582cae8e1051..2ee2cc30340f0 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -17,6 +17,7 @@ struct target {
 	bool	     default_per_cpu;
 	bool	     per_thread;
 	bool	     use_bpf;
+	bool	     inherit;
 	int	     initial_delay;
 	const char   *attr_map;
 };

From d36e5b36a2928b30e09ff59ce5ce2d5df935176e Mon Sep 17 00:00:00 2001
From: Tengda Wu <wutengda@huaweicloud.com>
Date: Mon, 21 Oct 2024 11:02:01 +0000
Subject: [PATCH 0769/1530] perf test: Use sqrtloop workload to test bperf
 event

Replace `brstack` workload with `sqrtloop` workload, because `sqrtloop`
workload contains fork(), which is suitable for testing the bperf event
inheritance feature.

Signed-off-by: Tengda Wu <wutengda@huaweicloud.com>
Cc: song@kernel.org
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20241021110201.325617-3-wutengda@huaweicloud.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/stat_bpf_counters.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
index a038c1b1a706a..95d2ad5d17c67 100755
--- a/tools/perf/tests/shell/stat_bpf_counters.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters.sh
@@ -4,7 +4,7 @@
 
 set -e
 
-workload="perf test -w brstack"
+workload="perf test -w sqrtloop"
 
 # check whether $2 is within +/- 20% of $1
 compare_number()

From f6ca73063754950bf3fbad753e3a9557e3aa85e3 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Sat, 2 Nov 2024 14:28:41 +0100
Subject: [PATCH 0770/1530] i3c: Document I3C_ADDR_SLOT_EXT_STATUS_MASK

As the mask is part of the enum, document it.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Link: https://lore.kernel.org/r/20241102132841.2446176-1-alexandre.belloni@bootlin.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 include/linux/i3c/master.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index 6e5328c6c6afd..12d532b012c5a 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -298,6 +298,7 @@ enum i3c_open_drain_speed {
  * @I3C_ADDR_SLOT_I2C_DEV: address is assigned to an I2C device
  * @I3C_ADDR_SLOT_I3C_DEV: address is assigned to an I3C device
  * @I3C_ADDR_SLOT_STATUS_MASK: address slot mask
+ * @I3C_ADDR_SLOT_EXT_STATUS_MASK: address slot mask with extended information
  * @I3C_ADDR_SLOT_EXT_DESIRED: the bitmask represents addresses that are preferred by some devices,
  *			       such as the "assigned-address" property in a device tree source.
  * On an I3C bus, addresses are assigned dynamically, and we need to know which

From d38cc57c14ff9590e03da77987217eca19ea350d Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Thu, 17 Oct 2024 21:04:47 +0300
Subject: [PATCH 0771/1530] dt-bindings: PCI: qcom,pcie-sm8550: Add SAR2130P
 compatible
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On the Qualcomm SAR2130P platform the PCIe host is compatible with the
DWC controller present on the SM8550 platorm, just using one additional
clock.

Link: https://lore.kernel.org/r/20241017-sar2130p-pci-v1-1-5b95e63d9624@linaro.org
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 Documentation/devicetree/bindings/pci/qcom,pcie-sm8550.yaml | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8550.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8550.yaml
index 24cb38673581d..2b5498a35dcc1 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8550.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8550.yaml
@@ -20,6 +20,7 @@ properties:
       - const: qcom,pcie-sm8550
       - items:
           - enum:
+              - qcom,sar2130p-pcie
               - qcom,pcie-sm8650
           - const: qcom,pcie-sm8550
 
@@ -39,7 +40,7 @@ properties:
 
   clocks:
     minItems: 7
-    maxItems: 8
+    maxItems: 9
 
   clock-names:
     minItems: 7
@@ -52,6 +53,7 @@ properties:
       - const: ddrss_sf_tbu # PCIe SF TBU clock
       - const: noc_aggr # Aggre NoC PCIe AXI clock
       - const: cnoc_sf_axi # Config NoC PCIe1 AXI clock
+      - const: qmip_pcie_ahb # QMIP PCIe AHB clock
 
   interrupts:
     minItems: 8

From ba4a2e2317b9faeca9193ed6d3193ddc3cf2aba3 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Mon, 7 Oct 2024 10:42:55 +0530
Subject: [PATCH 0772/1530] PCI: qcom: Enable MSI interrupts together with Link
 up if 'Global IRQ' is supported
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, if 'Global IRQ' is supported by the platform, only the Link up
interrupt is enabled in the PARF_INT_ALL_MASK register. This masks MSIs
on some platforms. The MSI bits in PARF_INT_ALL_MASK register are enabled
by default in the hardware, but commit 4581403f6792 ("PCI: qcom: Enumerate
endpoints based on Link up event in 'global_irq' interrupt") disabled them
and enabled only the Link up interrupt. While MSI continued to work on the
SM8450 platform that was used to test the offending commit, on other
platforms like SM8250, X1E80100, MSIs are getting masked. And they require
enabling the MSI interrupt bits in the register to unmask (enable) the
MSIs.

Even though the MSI interrupt enable bits in PARF_INT_ALL_MASK are
described as 'diagnostic' interrupts in the internal documentation,
disabling them masks MSI on these platforms. Due to this, MSIs were not
reported to be received these platforms while supporting 'Global IRQ'.

So, enable the MSI interrupts along with the Link up interrupt in the
PARF_INT_ALL_MASK register if 'Global IRQ' is supported. This ensures that
the MSIs continue to work and also the driver is able to catch the Link
up interrupt for enumerating endpoint devices.

Fixes: 4581403f6792 ("PCI: qcom: Enumerate endpoints based on Link up event in 'global_irq' interrupt")
Closes: https://lore.kernel.org/linux-pci/9a692c98-eb0a-4d86-b642-ea655981ff53@kernel.org/
Link: https://lore.kernel.org/r/20241007051255.4378-1-manivannan.sadhasivam@linaro.org
Reported-by: Konrad Dybcio <konradybcio@kernel.org>
Tested-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com> # SL7
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Qiang Yu <quic_qianyu@quicinc.com>
---
 drivers/pci/controller/dwc/pcie-qcom.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index ef44a82be058b..2b33d03ed0541 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -133,6 +133,7 @@
 
 /* PARF_INT_ALL_{STATUS/CLEAR/MASK} register fields */
 #define PARF_INT_ALL_LINK_UP			BIT(13)
+#define PARF_INT_MSI_DEV_0_7			GENMASK(30, 23)
 
 /* PARF_NO_SNOOP_OVERIDE register fields */
 #define WR_NO_SNOOP_OVERIDE_EN			BIT(1)
@@ -1716,7 +1717,8 @@ static int qcom_pcie_probe(struct platform_device *pdev)
 			goto err_host_deinit;
 		}
 
-		writel_relaxed(PARF_INT_ALL_LINK_UP, pcie->parf + PARF_INT_ALL_MASK);
+		writel_relaxed(PARF_INT_ALL_LINK_UP | PARF_INT_MSI_DEV_0_7,
+			       pcie->parf + PARF_INT_ALL_MASK);
 	}
 
 	qcom_pcie_icc_opp_update(pcie);

From 6c06f6a6b48d7f1756860120d21d5ede72735bf6 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Mon, 7 Oct 2024 13:49:36 +0200
Subject: [PATCH 0773/1530] MAINTAINERS: Add kernel hardening keywords
 __counted_by{_le|_be}

In addition to __counted_by, also match the keywords __counted_by_le and
__counted_by_be.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Link: https://lore.kernel.org/r/20241007114935.1647-2-thorsten.blum@linux.dev
Signed-off-by: Kees Cook <kees@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index a097afd76ded4..cfb32cc22673d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12349,7 +12349,7 @@ F:	mm/usercopy.c
 F:	security/Kconfig.hardening
 K:	\b(add|choose)_random_kstack_offset\b
 K:	\b__check_(object_size|heap_object)\b
-K:	\b__counted_by\b
+K:	\b__counted_by(_le|_be)?\b
 
 KERNEL JANITORS
 L:	kernel-janitors@vger.kernel.org

From a508ef4b1dcc82227edc594ffae583874dd425d7 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Fri, 1 Nov 2024 21:54:53 +0100
Subject: [PATCH 0774/1530] lib: string_helpers: silence snprintf() output
 truncation warning

The output of ".%03u" with the unsigned int in range [0, 4294966295] may
get truncated if the target buffer is not 12 bytes. This can't really
happen here as the 'remainder' variable cannot exceed 999 but the
compiler doesn't know it. To make it happy just increase the buffer to
where the warning goes away.

Fixes: 3c9f3681d0b4 ("[SCSI] lib: add generic helper to print sizes rounded to the correct SI range")
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Andy Shevchenko <andy@kernel.org>
Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Kees Cook <kees@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: https://lore.kernel.org/r/20241101205453.9353-1-brgl@bgdev.pl
Signed-off-by: Kees Cook <kees@kernel.org>
---
 lib/string_helpers.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index 4f887aa62fa0c..91fa37b5c510a 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -57,7 +57,7 @@ int string_get_size(u64 size, u64 blk_size, const enum string_size_units units,
 	static const unsigned int rounding[] = { 500, 50, 5 };
 	int i = 0, j;
 	u32 remainder = 0, sf_cap;
-	char tmp[8];
+	char tmp[12];
 	const char *unit;
 
 	tmp[0] = '\0';

From 25bc99be5fe53853053ceeaa328068c49dc1e799 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Fri, 1 Nov 2024 12:50:02 -0400
Subject: [PATCH 0775/1530] i3c: master: svc: Modify enabled_events bit 7:0 to
 act as IBI enable counter

Fix issue where disabling IBI on one device disables the entire IBI
interrupt. Modify bit 7:0 of enabled_events to serve as an IBI enable
counter, ensuring that the system IBI interrupt is disabled only when all
I3C devices have IBI disabled.

Cc: stable@kernel.org
Fixes: 7ff730ca458e ("i3c: master: svc: enable the interrupt in the enable ibi function")
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20241101165002.2479794-1-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/svc-i3c-master.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index c53f2b27662f4..c1ee3828e7eec 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -130,8 +130,8 @@
 #define SVC_I3C_PPBAUD_MAX 15
 #define SVC_I3C_QUICK_I2C_CLK 4170000
 
-#define SVC_I3C_EVENT_IBI	BIT(0)
-#define SVC_I3C_EVENT_HOTJOIN	BIT(1)
+#define SVC_I3C_EVENT_IBI	GENMASK(7, 0)
+#define SVC_I3C_EVENT_HOTJOIN	BIT(31)
 
 struct svc_i3c_cmd {
 	u8 addr;
@@ -214,7 +214,7 @@ struct svc_i3c_master {
 		spinlock_t lock;
 	} ibi;
 	struct mutex lock;
-	int enabled_events;
+	u32 enabled_events;
 	u32 mctrl_config;
 };
 
@@ -1688,7 +1688,7 @@ static int svc_i3c_master_enable_ibi(struct i3c_dev_desc *dev)
 		return ret;
 	}
 
-	master->enabled_events |= SVC_I3C_EVENT_IBI;
+	master->enabled_events++;
 	svc_i3c_master_enable_interrupts(master, SVC_I3C_MINT_SLVSTART);
 
 	return i3c_master_enec_locked(m, dev->info.dyn_addr, I3C_CCC_EVENT_SIR);
@@ -1700,7 +1700,7 @@ static int svc_i3c_master_disable_ibi(struct i3c_dev_desc *dev)
 	struct svc_i3c_master *master = to_svc_i3c_master(m);
 	int ret;
 
-	master->enabled_events &= ~SVC_I3C_EVENT_IBI;
+	master->enabled_events--;
 	if (!master->enabled_events)
 		svc_i3c_master_disable_interrupts(master);
 

From 07c2a737504457c41678c5c30abe9107cd28dce6 Mon Sep 17 00:00:00 2001
From: Tudor Ambarus <tudor.ambarus@linaro.org>
Date: Thu, 31 Oct 2024 15:00:20 +0000
Subject: [PATCH 0776/1530] scsi: ufs: exynos: Remove empty drv_init method

Remove empty method. When the method is not set, the call is not made,
saving a few cycles.

Signed-off-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20241031150033.3440894-2-peter.griffin@linaro.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-exynos.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index 9ec318ef52bff..db89ebe48bcdd 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -198,11 +198,6 @@ static inline void exynos_ufs_ungate_clks(struct exynos_ufs *ufs)
 	exynos_ufs_ctrl_clkstop(ufs, false);
 }
 
-static int exynos7_ufs_drv_init(struct device *dev, struct exynos_ufs *ufs)
-{
-	return 0;
-}
-
 static int exynosauto_ufs_drv_init(struct device *dev, struct exynos_ufs *ufs)
 {
 	struct exynos_ufs_uic_attr *attr = ufs->drv_data->uic_attr;
@@ -2036,7 +2031,6 @@ static const struct exynos_ufs_drv_data exynos_ufs_drvs = {
 				  EXYNOS_UFS_OPT_BROKEN_RX_SEL_IDX |
 				  EXYNOS_UFS_OPT_SKIP_CONNECTION_ESTAB |
 				  EXYNOS_UFS_OPT_USE_SW_HIBERN8_TIMER,
-	.drv_init		= exynos7_ufs_drv_init,
 	.pre_link		= exynos7_ufs_pre_link,
 	.post_link		= exynos7_ufs_post_link,
 	.pre_pwr_change		= exynos7_ufs_pre_pwr_change,

From afd613ca2c60d0a970d434bc73e1ddcdb925c799 Mon Sep 17 00:00:00 2001
From: Tudor Ambarus <tudor.ambarus@linaro.org>
Date: Thu, 31 Oct 2024 15:00:21 +0000
Subject: [PATCH 0777/1530] scsi: ufs: exynos: Remove superfluous function
 parameter

The pointer to device can be obtained from ufs->hba->dev, remove
superfluous function parameter.

Signed-off-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20241031150033.3440894-3-peter.griffin@linaro.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-exynos.c | 4 ++--
 drivers/ufs/host/ufs-exynos.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index db89ebe48bcdd..7e381ab1011de 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -198,7 +198,7 @@ static inline void exynos_ufs_ungate_clks(struct exynos_ufs *ufs)
 	exynos_ufs_ctrl_clkstop(ufs, false);
 }
 
-static int exynosauto_ufs_drv_init(struct device *dev, struct exynos_ufs *ufs)
+static int exynosauto_ufs_drv_init(struct exynos_ufs *ufs)
 {
 	struct exynos_ufs_uic_attr *attr = ufs->drv_data->uic_attr;
 
@@ -1424,7 +1424,7 @@ static int exynos_ufs_init(struct ufs_hba *hba)
 	exynos_ufs_fmp_init(hba, ufs);
 
 	if (ufs->drv_data->drv_init) {
-		ret = ufs->drv_data->drv_init(dev, ufs);
+		ret = ufs->drv_data->drv_init(ufs);
 		if (ret) {
 			dev_err(dev, "failed to init drv-data\n");
 			goto out;
diff --git a/drivers/ufs/host/ufs-exynos.h b/drivers/ufs/host/ufs-exynos.h
index 1646c4a9bb088..9670dc138d1e4 100644
--- a/drivers/ufs/host/ufs-exynos.h
+++ b/drivers/ufs/host/ufs-exynos.h
@@ -182,7 +182,7 @@ struct exynos_ufs_drv_data {
 	unsigned int quirks;
 	unsigned int opts;
 	/* SoC's specific operations */
-	int (*drv_init)(struct device *dev, struct exynos_ufs *ufs);
+	int (*drv_init)(struct exynos_ufs *ufs);
 	int (*pre_link)(struct exynos_ufs *ufs);
 	int (*post_link)(struct exynos_ufs *ufs);
 	int (*pre_pwr_change)(struct exynos_ufs *ufs,

From 516ceaaf539de83de3af04c46198f39180cc44a1 Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Thu, 31 Oct 2024 15:00:22 +0000
Subject: [PATCH 0778/1530] scsi: ufs: exynos: Allow UFS Gear 4

UFS Gear 4 offers faster speeds, and better power usage so lets enable
it.

Currently ufshcd_init_host_params() sets UFS_HS_G3 as a default, so even
if the device supports G4 we end up negotiating down to G3.

For SoCs like gs101 which have a UFS major controller version of 3 or
above advertise Gear 4. This then allows a Gear 4 link on Pixel 6.

For earlier controller versions keep the current default behaviour of
reporting G3.

Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20241031150033.3440894-4-peter.griffin@linaro.org
Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-exynos.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index 7e381ab1011de..33de7ff747a2f 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -766,6 +766,21 @@ static void exynos_ufs_config_sync_pattern_mask(struct exynos_ufs *ufs,
 	exynos_ufs_disable_ov_tm(hba);
 }
 
+#define UFS_HW_VER_MAJOR_MASK   GENMASK(15, 8)
+
+static u32 exynos_ufs_get_hs_gear(struct ufs_hba *hba)
+{
+	u8 major;
+
+	major = FIELD_GET(UFS_HW_VER_MAJOR_MASK, hba->ufs_version);
+
+	if (major >= 3)
+		return UFS_HS_G4;
+
+	/* Default is HS-G3 */
+	return UFS_HS_G3;
+}
+
 static int exynos_ufs_pre_pwr_mode(struct ufs_hba *hba,
 				struct ufs_pa_layer_attr *dev_max_params,
 				struct ufs_pa_layer_attr *dev_req_params)
@@ -783,6 +798,10 @@ static int exynos_ufs_pre_pwr_mode(struct ufs_hba *hba,
 
 	ufshcd_init_host_params(&host_params);
 
+	/* This driver only support symmetric gear setting e.g. hs_tx_gear == hs_rx_gear */
+	host_params.hs_tx_gear = exynos_ufs_get_hs_gear(hba);
+	host_params.hs_rx_gear = exynos_ufs_get_hs_gear(hba);
+
 	ret = ufshcd_negotiate_pwr_params(&host_params, dev_max_params, dev_req_params);
 	if (ret) {
 		pr_err("%s: failed to determine capabilities\n", __func__);

From c662cedea14efdcf373d8d886ec18019d50e0772 Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Thu, 31 Oct 2024 15:00:23 +0000
Subject: [PATCH 0779/1530] scsi: ufs: exynos: Add check inside
 exynos_ufs_config_smu()

Move the EXYNOS_UFS_OPT_UFSPR_SECURE check inside
exynos_ufs_config_smu().

This way all call sites will benefit from the check. This fixes a bug
currently in the exynos_ufs_resume() path on gs101 as it calls
exynos_ufs_config_smu() and we end up accessing registers that can only
be accessed from secure world which results in a serror.

Fixes: d11e0a318df8 ("scsi: ufs: exynos: Add support for Tensor gs101 SoC")
Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20241031150033.3440894-5-peter.griffin@linaro.org
Cc: stable@vger.kernel.org
Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-exynos.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index 33de7ff747a2f..f4454e89040f2 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -719,6 +719,9 @@ static void exynos_ufs_config_smu(struct exynos_ufs *ufs)
 {
 	u32 reg, val;
 
+	if (ufs->opts & EXYNOS_UFS_OPT_UFSPR_SECURE)
+		return;
+
 	exynos_ufs_disable_auto_ctrl_hcc_save(ufs, &val);
 
 	/* make encryption disabled by default */
@@ -1454,8 +1457,8 @@ static int exynos_ufs_init(struct ufs_hba *hba)
 	if (ret)
 		goto out;
 	exynos_ufs_specify_phy_time_attr(ufs);
-	if (!(ufs->opts & EXYNOS_UFS_OPT_UFSPR_SECURE))
-		exynos_ufs_config_smu(ufs);
+
+	exynos_ufs_config_smu(ufs);
 
 	hba->host->dma_alignment = DATA_UNIT_SIZE - 1;
 	return 0;

From 5278917250a58792b30a9f9b6e9b28dca9d30965 Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Thu, 31 Oct 2024 15:00:24 +0000
Subject: [PATCH 0780/1530] scsi: ufs: exynos: gs101: Remove
 EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL

Auto clk control works fine for gs101, so remove
EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL flag.

Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20241031150033.3440894-6-peter.griffin@linaro.org
Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-exynos.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index f4454e89040f2..2c2fed691b952 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -2138,8 +2138,7 @@ static const struct exynos_ufs_drv_data gs101_ufs_drvs = {
 				  UFSHCD_QUIRK_BROKEN_OCS_FATAL_ERROR |
 				  UFSHCI_QUIRK_SKIP_MANUAL_WB_FLUSH_CTRL |
 				  UFSHCD_QUIRK_SKIP_DEF_UNIPRO_TIMEOUT_SETTING,
-	.opts			= EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL |
-				  EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR |
+	.opts			= EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR |
 				  EXYNOS_UFS_OPT_UFSPR_SECURE |
 				  EXYNOS_UFS_OPT_TIMER_TICK_SELECT,
 	.drv_init		= exynosauto_ufs_drv_init,

From 96f3fd267fce2601d6a74689e4b4a5e4a04e10b0 Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Thu, 31 Oct 2024 15:00:25 +0000
Subject: [PATCH 0781/1530] scsi: ufs: exynos: Add
 EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR check

The values calculated in exynos_ufs_specify_phy_time_attr() are only
used in exynos_ufs_config_phy_time_attr() which is only called if the
EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR flag is not set.

Add a check for this flag to exynos_ufs_specify_phy_time_attr() and
return for platforms that don't set it.

Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20241031150033.3440894-7-peter.griffin@linaro.org
Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-exynos.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index 2c2fed691b952..0ac940690a150 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -541,6 +541,9 @@ static void exynos_ufs_specify_phy_time_attr(struct exynos_ufs *ufs)
 	struct exynos_ufs_uic_attr *attr = ufs->drv_data->uic_attr;
 	struct ufs_phy_time_cfg *t_cfg = &ufs->t_cfg;
 
+	if (ufs->opts & EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR)
+		return;
+
 	t_cfg->tx_linereset_p =
 		exynos_ufs_calc_time_cntr(ufs, attr->tx_dif_p_nsec);
 	t_cfg->tx_linereset_n =

From 5ef3cb67f3da46cb9213aee8c92758af8683a4ef Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Thu, 31 Oct 2024 15:00:26 +0000
Subject: [PATCH 0782/1530] scsi: ufs: exynos: gs101: Remove unused phy
 attribute fields

Now that exynos_ufs_specify_phy_time_attr() checks the appropriate
EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR flag. Remove the unused fields in
gs101_uic_attr.

Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20241031150033.3440894-8-peter.griffin@linaro.org
Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-exynos.c | 20 --------------------
 1 file changed, 20 deletions(-)

diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index 0ac940690a150..e477ab86e3c15 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -2064,26 +2064,6 @@ static const struct exynos_ufs_drv_data exynos_ufs_drvs = {
 
 static struct exynos_ufs_uic_attr gs101_uic_attr = {
 	.tx_trailingclks		= 0xff,
-	.tx_dif_p_nsec			= 3000000,	/* unit: ns */
-	.tx_dif_n_nsec			= 1000000,	/* unit: ns */
-	.tx_high_z_cnt_nsec		= 20000,	/* unit: ns */
-	.tx_base_unit_nsec		= 100000,	/* unit: ns */
-	.tx_gran_unit_nsec		= 4000,		/* unit: ns */
-	.tx_sleep_cnt			= 1000,		/* unit: ns */
-	.tx_min_activatetime		= 0xa,
-	.rx_filler_enable		= 0x2,
-	.rx_dif_p_nsec			= 1000000,	/* unit: ns */
-	.rx_hibern8_wait_nsec		= 4000000,	/* unit: ns */
-	.rx_base_unit_nsec		= 100000,	/* unit: ns */
-	.rx_gran_unit_nsec		= 4000,		/* unit: ns */
-	.rx_sleep_cnt			= 1280,		/* unit: ns */
-	.rx_stall_cnt			= 320,		/* unit: ns */
-	.rx_hs_g1_sync_len_cap		= SYNC_LEN_COARSE(0xf),
-	.rx_hs_g2_sync_len_cap		= SYNC_LEN_COARSE(0xf),
-	.rx_hs_g3_sync_len_cap		= SYNC_LEN_COARSE(0xf),
-	.rx_hs_g1_prep_sync_len_cap	= PREP_LEN(0xf),
-	.rx_hs_g2_prep_sync_len_cap	= PREP_LEN(0xf),
-	.rx_hs_g3_prep_sync_len_cap	= PREP_LEN(0xf),
 	.pa_dbg_opt_suite1_val		= 0x90913C1C,
 	.pa_dbg_opt_suite1_off		= PA_GS101_DBG_OPTION_SUITE1,
 	.pa_dbg_opt_suite2_val		= 0xE01C115F,

From f8fe71a3fe89836e9b694f4a338157f5e36abae8 Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Thu, 31 Oct 2024 15:00:27 +0000
Subject: [PATCH 0783/1530] scsi: ufs: exynos: remove tx_dif_p_nsec from
 exynosauto_ufs_drv_init()

Remove the assignment of tx_dif_p_nsec as both users of
exynosauto_ufs_drv_init() function (exynosauto and gs101) set the
EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR flag meaning that tx_dif_p_nsec has
no effect.

Additionally both users also set the samsung,sysreg dt property, meaning
the execution flow will always return on the regmap_update_bits() call
before the assignment.

Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20241031150033.3440894-9-peter.griffin@linaro.org
Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-exynos.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index e477ab86e3c15..378c16d905c11 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -200,8 +200,6 @@ static inline void exynos_ufs_ungate_clks(struct exynos_ufs *ufs)
 
 static int exynosauto_ufs_drv_init(struct exynos_ufs *ufs)
 {
-	struct exynos_ufs_uic_attr *attr = ufs->drv_data->uic_attr;
-
 	/* IO Coherency setting */
 	if (ufs->sysreg) {
 		return regmap_update_bits(ufs->sysreg,
@@ -209,8 +207,6 @@ static int exynosauto_ufs_drv_init(struct exynos_ufs *ufs)
 					  UFS_SHARABLE, UFS_SHARABLE);
 	}
 
-	attr->tx_dif_p_nsec = 3200000;
-
 	return 0;
 }
 

From 9cc4a4a5767756b1ebe45a76c4673432545ea70e Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Thu, 31 Oct 2024 15:00:28 +0000
Subject: [PATCH 0784/1530] scsi: ufs: exynos: Add gs101_ufs_drv_init() hook
 and enable WriteBooster

Factor out the common code into a new exynos_ufs_shareability() function
and provide a dedicated gs101_drv_init() hook.

This allows us to enable WriteBooster capability (UFSHCD_CAP_WB_EN) in a
way that doesn't effect other SoCs supported in this driver.

WriteBooster improves write speeds by enabling a pseudo SLC cache. Using
the 'fio seqwrite' test we can achieve speeds of 945MB/s with this
feature enabled (until the cache is exhausted) before dropping back to
~260MB/s (which are the speeds we see without the WriteBooster feature
enabled).

Assuming the UFSHCD_CAP_WB_EN capability is set by the host then
WriteBooster can also be enabled and disabled via sysfs so it is
possible for the system to only enable it when extra write performance
is required.

Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20241031150033.3440894-10-peter.griffin@linaro.org
Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-exynos.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index 378c16d905c11..d59e1933b64e9 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -198,7 +198,7 @@ static inline void exynos_ufs_ungate_clks(struct exynos_ufs *ufs)
 	exynos_ufs_ctrl_clkstop(ufs, false);
 }
 
-static int exynosauto_ufs_drv_init(struct exynos_ufs *ufs)
+static int exynos_ufs_shareability(struct exynos_ufs *ufs)
 {
 	/* IO Coherency setting */
 	if (ufs->sysreg) {
@@ -210,6 +210,21 @@ static int exynosauto_ufs_drv_init(struct exynos_ufs *ufs)
 	return 0;
 }
 
+static int gs101_ufs_drv_init(struct exynos_ufs *ufs)
+{
+	struct ufs_hba *hba = ufs->hba;
+
+	/* Enable WriteBooster */
+	hba->caps |= UFSHCD_CAP_WB_EN;
+
+	return exynos_ufs_shareability(ufs);
+}
+
+static int exynosauto_ufs_drv_init(struct exynos_ufs *ufs)
+{
+	return exynos_ufs_shareability(ufs);
+}
+
 static int exynosauto_ufs_post_hce_enable(struct exynos_ufs *ufs)
 {
 	struct ufs_hba *hba = ufs->hba;
@@ -2120,7 +2135,7 @@ static const struct exynos_ufs_drv_data gs101_ufs_drvs = {
 	.opts			= EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR |
 				  EXYNOS_UFS_OPT_UFSPR_SECURE |
 				  EXYNOS_UFS_OPT_TIMER_TICK_SELECT,
-	.drv_init		= exynosauto_ufs_drv_init,
+	.drv_init		= gs101_ufs_drv_init,
 	.pre_link		= gs101_ufs_pre_link,
 	.post_link		= gs101_ufs_post_link,
 	.pre_pwr_change		= gs101_ufs_pre_pwr_change,

From ef8bfb00e9f106434a43f42559a6bc42f850e2d0 Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Thu, 31 Oct 2024 15:00:29 +0000
Subject: [PATCH 0785/1530] scsi: ufs: exynos: Enable write line unique
 transactions on gs101

Currently just AXIDMA_RWDATA_BURST_LEN[3:0] field is set to 8 in
exynos_ufs_post_link() function.

To enable WLU transaction additionally we need to set Write Line Unique
enable [31], Write Line Unique Burst Length [30:27] and
AXIDMA_RWDATA_BURST_LEN[3:0].

To support WLU transaction on gs101, both burst length fields need to be
0x3. As all other SoCs expect the current value we update this in the
gs101_ufs_post_link() specific hook.

Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20241031150033.3440894-11-peter.griffin@linaro.org
Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-exynos.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index d59e1933b64e9..78307440107f0 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -48,6 +48,8 @@
 #define HCI_UNIPRO_APB_CLK_CTRL	0x68
 #define UNIPRO_APB_CLK(v, x)	(((v) & ~0xF) | ((x) & 0xF))
 #define HCI_AXIDMA_RWDATA_BURST_LEN	0x6C
+#define WLU_EN			BIT(31)
+#define WLU_BURST_LEN(x)	((x) << 27 | ((x) & 0xF))
 #define HCI_GPIO_OUT		0x70
 #define HCI_ERR_EN_PA_LAYER	0x78
 #define HCI_ERR_EN_DL_LAYER	0x7C
@@ -1922,6 +1924,12 @@ static int gs101_ufs_post_link(struct exynos_ufs *ufs)
 {
 	struct ufs_hba *hba = ufs->hba;
 
+	/*
+	 * Enable Write Line Unique. This field has to be 0x3
+	 * to support Write Line Unique transaction on gs101.
+	 */
+	hci_writel(ufs, WLU_EN | WLU_BURST_LEN(3), HCI_AXIDMA_RWDATA_BURST_LEN);
+
 	exynos_ufs_enable_dbg_mode(hba);
 	ufshcd_dme_set(hba, UIC_ARG_MIB(PA_SAVECONFIGTIME), 0x3e8);
 	exynos_ufs_disable_dbg_mode(hba);

From 36adb55631d0199b516a8b573fa886494d0e44a6 Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Thu, 31 Oct 2024 15:00:30 +0000
Subject: [PATCH 0786/1530] scsi: ufs: exynos: Set ACG to be controlled by
 UFS_ACG_DISABLE

HCI_IOP_ACG_DISABLE is an undocumented register in the TRM but the
downstream driver sets this register so we follow suit here.

The register is already 0 presumed to be set by the bootloader as the
comment downstream implies the reset state is 1. So whilst this is a nop
currently, it should protect us in case the bootloader behaviour ever
changes.

Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20241031150033.3440894-12-peter.griffin@linaro.org
Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-exynos.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index 78307440107f0..5078210b2a5ce 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -76,6 +76,10 @@
 #define CLK_CTRL_EN_MASK	(REFCLK_CTRL_EN |\
 				 UNIPRO_PCLK_CTRL_EN |\
 				 UNIPRO_MCLK_CTRL_EN)
+
+#define HCI_IOP_ACG_DISABLE	0x100
+#define HCI_IOP_ACG_DISABLE_EN	BIT(0)
+
 /* Device fatal error */
 #define DFES_ERR_EN		BIT(31)
 #define DFES_DEF_L2_ERRS	(UIC_DATA_LINK_LAYER_ERROR_RX_BUF_OF |\
@@ -215,10 +219,15 @@ static int exynos_ufs_shareability(struct exynos_ufs *ufs)
 static int gs101_ufs_drv_init(struct exynos_ufs *ufs)
 {
 	struct ufs_hba *hba = ufs->hba;
+	u32 reg;
 
 	/* Enable WriteBooster */
 	hba->caps |= UFSHCD_CAP_WB_EN;
 
+	/* set ACG to be controlled by UFS_ACG_DISABLE */
+	reg = hci_readl(ufs, HCI_IOP_ACG_DISABLE);
+	hci_writel(ufs, reg & (~HCI_IOP_ACG_DISABLE_EN), HCI_IOP_ACG_DISABLE);
+
 	return exynos_ufs_shareability(ufs);
 }
 

From ceef938bbf8b93ba3a218b4adc244cde94b582aa Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Thu, 31 Oct 2024 15:00:31 +0000
Subject: [PATCH 0787/1530] scsi: ufs: exynos: Fix hibern8 notify callbacks

v1 of the patch which introduced the ufshcd_vops_hibern8_notify()
callback used a bool instead of an enum. In v2 this was updated to an
enum based on the review feedback in [1].

ufs-exynos hibernate calls have always been broken upstream as it
follows the v1 bool implementation.

Link: https://patchwork.kernel.org/project/linux-scsi/patch/001f01d23994$719997c0$54ccc740$@samsung.com/ [1]
Fixes: 55f4b1f73631 ("scsi: ufs: ufs-exynos: Add UFS host support for Exynos SoCs")
Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20241031150033.3440894-13-peter.griffin@linaro.org
Cc: stable@vger.kernel.org
Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-exynos.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index 5078210b2a5ce..9b6c4cfd76653 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -1526,12 +1526,12 @@ static void exynos_ufs_dev_hw_reset(struct ufs_hba *hba)
 	hci_writel(ufs, 1 << 0, HCI_GPIO_OUT);
 }
 
-static void exynos_ufs_pre_hibern8(struct ufs_hba *hba, u8 enter)
+static void exynos_ufs_pre_hibern8(struct ufs_hba *hba, enum uic_cmd_dme cmd)
 {
 	struct exynos_ufs *ufs = ufshcd_get_variant(hba);
 	struct exynos_ufs_uic_attr *attr = ufs->drv_data->uic_attr;
 
-	if (!enter) {
+	if (cmd == UIC_CMD_DME_HIBER_EXIT) {
 		if (ufs->opts & EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL)
 			exynos_ufs_disable_auto_ctrl_hcc(ufs);
 		exynos_ufs_ungate_clks(ufs);
@@ -1559,11 +1559,11 @@ static void exynos_ufs_pre_hibern8(struct ufs_hba *hba, u8 enter)
 	}
 }
 
-static void exynos_ufs_post_hibern8(struct ufs_hba *hba, u8 enter)
+static void exynos_ufs_post_hibern8(struct ufs_hba *hba, enum uic_cmd_dme cmd)
 {
 	struct exynos_ufs *ufs = ufshcd_get_variant(hba);
 
-	if (!enter) {
+	if (cmd == UIC_CMD_DME_HIBER_EXIT) {
 		u32 cur_mode = 0;
 		u32 pwrmode;
 
@@ -1582,7 +1582,7 @@ static void exynos_ufs_post_hibern8(struct ufs_hba *hba, u8 enter)
 
 		if (!(ufs->opts & EXYNOS_UFS_OPT_SKIP_CONNECTION_ESTAB))
 			exynos_ufs_establish_connt(ufs);
-	} else {
+	} else if (cmd == UIC_CMD_DME_HIBER_ENTER) {
 		ufs->entry_hibern8_t = ktime_get();
 		exynos_ufs_gate_clks(ufs);
 		if (ufs->opts & EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL)
@@ -1669,15 +1669,15 @@ static int exynos_ufs_pwr_change_notify(struct ufs_hba *hba,
 }
 
 static void exynos_ufs_hibern8_notify(struct ufs_hba *hba,
-				     enum uic_cmd_dme enter,
+				     enum uic_cmd_dme cmd,
 				     enum ufs_notify_change_status notify)
 {
 	switch ((u8)notify) {
 	case PRE_CHANGE:
-		exynos_ufs_pre_hibern8(hba, enter);
+		exynos_ufs_pre_hibern8(hba, cmd);
 		break;
 	case POST_CHANGE:
-		exynos_ufs_post_hibern8(hba, enter);
+		exynos_ufs_post_hibern8(hba, cmd);
 		break;
 	}
 }

From cabc453ca6c3e7ff25b4f558b06ef1691a9535d3 Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Thu, 31 Oct 2024 15:00:32 +0000
Subject: [PATCH 0788/1530] scsi: ufs: exynos: gs101: Enable clock gating with
 hibern8

Enable clock gating and hibern8 capabilities for gs101. This leads to a
significantly cooler phone when running the upstream kernel.

The exynos_ufs_post_hibern8() hook is also updated to remove the
UIC_CMD_DME_HIBER_EXIT code path as this causes a hang on gs101.

The code path is removed rather than re-factored as no other SoC in
ufs-exynos driver sets UFSHCD_CAP_HIBERN8_WITH_CLK_GATING
capability. Additionally until the previous commit the hibern8 callbacks
were broken anyway as they expected a bool.

Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20241031150033.3440894-14-peter.griffin@linaro.org
Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-exynos.c | 24 ++++--------------------
 1 file changed, 4 insertions(+), 20 deletions(-)

diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index 9b6c4cfd76653..91827b3e582bb 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -224,6 +224,9 @@ static int gs101_ufs_drv_init(struct exynos_ufs *ufs)
 	/* Enable WriteBooster */
 	hba->caps |= UFSHCD_CAP_WB_EN;
 
+	/* Enable clock gating and hibern8 */
+	hba->caps |= UFSHCD_CAP_CLK_GATING | UFSHCD_CAP_HIBERN8_WITH_CLK_GATING;
+
 	/* set ACG to be controlled by UFS_ACG_DISABLE */
 	reg = hci_readl(ufs, HCI_IOP_ACG_DISABLE);
 	hci_writel(ufs, reg & (~HCI_IOP_ACG_DISABLE_EN), HCI_IOP_ACG_DISABLE);
@@ -1563,26 +1566,7 @@ static void exynos_ufs_post_hibern8(struct ufs_hba *hba, enum uic_cmd_dme cmd)
 {
 	struct exynos_ufs *ufs = ufshcd_get_variant(hba);
 
-	if (cmd == UIC_CMD_DME_HIBER_EXIT) {
-		u32 cur_mode = 0;
-		u32 pwrmode;
-
-		if (ufshcd_is_hs_mode(&ufs->dev_req_params))
-			pwrmode = FAST_MODE;
-		else
-			pwrmode = SLOW_MODE;
-
-		ufshcd_dme_get(hba, UIC_ARG_MIB(PA_PWRMODE), &cur_mode);
-		if (cur_mode != (pwrmode << 4 | pwrmode)) {
-			dev_warn(hba->dev, "%s: power mode change\n", __func__);
-			hba->pwr_info.pwr_rx = (cur_mode >> 4) & 0xf;
-			hba->pwr_info.pwr_tx = cur_mode & 0xf;
-			ufshcd_config_pwr_mode(hba, &hba->max_pwr_info.info);
-		}
-
-		if (!(ufs->opts & EXYNOS_UFS_OPT_SKIP_CONNECTION_ESTAB))
-			exynos_ufs_establish_connt(ufs);
-	} else if (cmd == UIC_CMD_DME_HIBER_ENTER) {
+	if (cmd == UIC_CMD_DME_HIBER_ENTER) {
 		ufs->entry_hibern8_t = ktime_get();
 		exynos_ufs_gate_clks(ufs);
 		if (ufs->opts & EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL)

From 29a64210c76788cae589f31c1cda6c46c2364111 Mon Sep 17 00:00:00 2001
From: Justin Tee <justin.tee@broadcom.com>
Date: Thu, 31 Oct 2024 15:32:09 -0700
Subject: [PATCH 0789/1530] scsi: lpfc: Modify CGN warning signal calculation
 based on EDC response

CGN warning signals are currently statically fixed to a passed in driver
parameter called lpfc_fabric_cgn_frequency.  However, CGN frequency
should be more correctly based on EDC responses from the fabric when
available.  Otherwise, still allow the driver to fall back on user
configured lpfc_fabric_cgn_frequency driver parameter.

Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Link: https://lore.kernel.org/r/20241031223219.152342-2-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_sli.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 2ec6e55771b45..80a43fd40af26 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -1932,7 +1932,7 @@ lpfc_issue_cmf_sync_wqe(struct lpfc_hba *phba, u32 ms, u64 total)
 	union lpfc_wqe128 *wqe;
 	struct lpfc_iocbq *sync_buf;
 	unsigned long iflags;
-	u32 ret_val;
+	u32 ret_val, cgn_sig_freq;
 	u32 atot, wtot, max;
 	u8 warn_sync_period = 0;
 
@@ -1987,8 +1987,10 @@ lpfc_issue_cmf_sync_wqe(struct lpfc_hba *phba, u32 ms, u64 total)
 	} else if (wtot) {
 		if (phba->cgn_reg_signal == EDC_CG_SIG_WARN_ONLY ||
 		    phba->cgn_reg_signal == EDC_CG_SIG_WARN_ALARM) {
+			cgn_sig_freq = phba->cgn_sig_freq ? phba->cgn_sig_freq :
+					lpfc_fabric_cgn_frequency;
 			/* We hit an Signal warning condition */
-			max = LPFC_SEC_TO_MSEC / lpfc_fabric_cgn_frequency *
+			max = LPFC_SEC_TO_MSEC / cgn_sig_freq *
 				lpfc_acqe_cgn_frequency;
 			bf_set(cmf_sync_wsigmax, &wqe->cmf_sync, max);
 			bf_set(cmf_sync_wsigcnt, &wqe->cmf_sync, wtot);

From 4c113ac05bb246813f0a3003307ad93b1c2d7d02 Mon Sep 17 00:00:00 2001
From: Justin Tee <justin.tee@broadcom.com>
Date: Thu, 31 Oct 2024 15:32:10 -0700
Subject: [PATCH 0790/1530] scsi: lpfc: Check devloss callbk done flag for
 potential stale NDLP ptrs

Should an rport remain in the NOTPRESENT state it is possible that
stgt_delete_work is scheduled after dev_loss_tmo_callbk.  In such cases,
dev_loss_tmo_callbk would have cleaned up the NDLP object resulting in
stale ndlp pointers in lpfc_terminate_rport_io().

Check for the DEVLOSS_CALLBK_DONE flag to know if dev_loss_tmo_callbk
has been called.  This is a more reliable way to avoid dereferencing
stale NDLP pointers.

Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Link: https://lore.kernel.org/r/20241031223219.152342-3-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_hbadisc.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 9241075f72fa4..a434faec3c92b 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -100,6 +100,12 @@ lpfc_rport_invalid(struct fc_rport *rport)
 		return -EINVAL;
 	}
 
+	if (rport->flags & FC_RPORT_DEVLOSS_CALLBK_DONE) {
+		pr_info("**** %s: devloss_callbk_done rport x%px SID x%x\n",
+			__func__, rport, rport->scsi_target_id);
+		return -EINVAL;
+	}
+
 	rdata = rport->dd_data;
 	if (!rdata) {
 		pr_err("**** %s: NULL dd_data on rport x%px SID x%x\n",

From d35f7672715d1ff3e3ad9bb4ae6ac6cb484200fe Mon Sep 17 00:00:00 2001
From: Justin Tee <justin.tee@broadcom.com>
Date: Thu, 31 Oct 2024 15:32:11 -0700
Subject: [PATCH 0791/1530] scsi: lpfc: Call lpfc_sli4_queue_unset() in restart
 and rmmod paths

During initialization, the driver allocates wq->pring in lpfc_wq_create
and lpfc_sli4_queue_unset() is the only place where kfree(wq->pring) is
called.

There is a possible memory leak in lpfc_sli_brdrestart_s4() (restart)
and lpfc_pci_remove_one_s4() (rmmod) paths because there are no calls to
lpfc_sli4_queue_unset() to kfree() the wq->pring.

Fix by inserting a call to lpfc_sli4_queue_unset() in
lpfc_sli_brdrestart_s4() and lpfc_sli4_hba_unset() routines.  Also, add
a check for the SLI_ACTIVE flag before issuing the Q_DESTROY mailbox
command.  If not set, then the mailbox command will obviously fail.  In
such cases, skip issuing the mailbox command and only execute the driver
resource clean up portions of the lpfc_*q_destroy routines.

Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Link: https://lore.kernel.org/r/20241031223219.152342-4-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_init.c |  2 ++
 drivers/scsi/lpfc/lpfc_sli.c  | 41 ++++++++++++++++++++++++++++++-----
 2 files changed, 38 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 0dd451009b079..a3658ef1141b2 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -13518,6 +13518,8 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba)
 	/* Disable FW logging to host memory */
 	lpfc_ras_stop_fwlog(phba);
 
+	lpfc_sli4_queue_unset(phba);
+
 	/* Reset SLI4 HBA FCoE function */
 	lpfc_pci_function_reset(phba);
 
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 80a43fd40af26..5ad5ff10256b6 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -5293,6 +5293,8 @@ lpfc_sli_brdrestart_s4(struct lpfc_hba *phba)
 			"0296 Restart HBA Data: x%x x%x\n",
 			phba->pport->port_state, psli->sli_flag);
 
+	lpfc_sli4_queue_unset(phba);
+
 	rc = lpfc_sli4_brdreset(phba);
 	if (rc) {
 		phba->link_state = LPFC_HBA_ERROR;
@@ -17627,6 +17629,9 @@ lpfc_eq_destroy(struct lpfc_hba *phba, struct lpfc_queue *eq)
 	if (!eq)
 		return -ENODEV;
 
+	if (!(phba->sli.sli_flag & LPFC_SLI_ACTIVE))
+		goto list_remove;
+
 	mbox = mempool_alloc(eq->phba->mbox_mem_pool, GFP_KERNEL);
 	if (!mbox)
 		return -ENOMEM;
@@ -17653,10 +17658,12 @@ lpfc_eq_destroy(struct lpfc_hba *phba, struct lpfc_queue *eq)
 				shdr_status, shdr_add_status, rc);
 		status = -ENXIO;
 	}
+	mempool_free(mbox, eq->phba->mbox_mem_pool);
 
+list_remove:
 	/* Remove eq from any list */
 	list_del_init(&eq->list);
-	mempool_free(mbox, eq->phba->mbox_mem_pool);
+
 	return status;
 }
 
@@ -17684,6 +17691,10 @@ lpfc_cq_destroy(struct lpfc_hba *phba, struct lpfc_queue *cq)
 	/* sanity check on queue memory */
 	if (!cq)
 		return -ENODEV;
+
+	if (!(phba->sli.sli_flag & LPFC_SLI_ACTIVE))
+		goto list_remove;
+
 	mbox = mempool_alloc(cq->phba->mbox_mem_pool, GFP_KERNEL);
 	if (!mbox)
 		return -ENOMEM;
@@ -17709,9 +17720,11 @@ lpfc_cq_destroy(struct lpfc_hba *phba, struct lpfc_queue *cq)
 				shdr_status, shdr_add_status, rc);
 		status = -ENXIO;
 	}
+	mempool_free(mbox, cq->phba->mbox_mem_pool);
+
+list_remove:
 	/* Remove cq from any list */
 	list_del_init(&cq->list);
-	mempool_free(mbox, cq->phba->mbox_mem_pool);
 	return status;
 }
 
@@ -17739,6 +17752,10 @@ lpfc_mq_destroy(struct lpfc_hba *phba, struct lpfc_queue *mq)
 	/* sanity check on queue memory */
 	if (!mq)
 		return -ENODEV;
+
+	if (!(phba->sli.sli_flag & LPFC_SLI_ACTIVE))
+		goto list_remove;
+
 	mbox = mempool_alloc(mq->phba->mbox_mem_pool, GFP_KERNEL);
 	if (!mbox)
 		return -ENOMEM;
@@ -17764,9 +17781,11 @@ lpfc_mq_destroy(struct lpfc_hba *phba, struct lpfc_queue *mq)
 				shdr_status, shdr_add_status, rc);
 		status = -ENXIO;
 	}
+	mempool_free(mbox, mq->phba->mbox_mem_pool);
+
+list_remove:
 	/* Remove mq from any list */
 	list_del_init(&mq->list);
-	mempool_free(mbox, mq->phba->mbox_mem_pool);
 	return status;
 }
 
@@ -17794,6 +17813,10 @@ lpfc_wq_destroy(struct lpfc_hba *phba, struct lpfc_queue *wq)
 	/* sanity check on queue memory */
 	if (!wq)
 		return -ENODEV;
+
+	if (!(phba->sli.sli_flag & LPFC_SLI_ACTIVE))
+		goto list_remove;
+
 	mbox = mempool_alloc(wq->phba->mbox_mem_pool, GFP_KERNEL);
 	if (!mbox)
 		return -ENOMEM;
@@ -17818,11 +17841,13 @@ lpfc_wq_destroy(struct lpfc_hba *phba, struct lpfc_queue *wq)
 				shdr_status, shdr_add_status, rc);
 		status = -ENXIO;
 	}
+	mempool_free(mbox, wq->phba->mbox_mem_pool);
+
+list_remove:
 	/* Remove wq from any list */
 	list_del_init(&wq->list);
 	kfree(wq->pring);
 	wq->pring = NULL;
-	mempool_free(mbox, wq->phba->mbox_mem_pool);
 	return status;
 }
 
@@ -17852,6 +17877,10 @@ lpfc_rq_destroy(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 	/* sanity check on queue memory */
 	if (!hrq || !drq)
 		return -ENODEV;
+
+	if (!(phba->sli.sli_flag & LPFC_SLI_ACTIVE))
+		goto list_remove;
+
 	mbox = mempool_alloc(hrq->phba->mbox_mem_pool, GFP_KERNEL);
 	if (!mbox)
 		return -ENOMEM;
@@ -17892,9 +17921,11 @@ lpfc_rq_destroy(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 				shdr_status, shdr_add_status, rc);
 		status = -ENXIO;
 	}
+	mempool_free(mbox, hrq->phba->mbox_mem_pool);
+
+list_remove:
 	list_del_init(&hrq->list);
 	list_del_init(&drq->list);
-	mempool_free(mbox, hrq->phba->mbox_mem_pool);
 	return status;
 }
 

From 940ddac8961209a37fec13c1f8967ce93f31d2c0 Mon Sep 17 00:00:00 2001
From: Justin Tee <justin.tee@broadcom.com>
Date: Thu, 31 Oct 2024 15:32:12 -0700
Subject: [PATCH 0792/1530] scsi: lpfc: Update lpfc_els_flush_cmd() to check
 for SLI_ACTIVE before BSG flag

During firmware errata events, the lpfc_els_flush_cmd() routine is
responsible for the clean up of outstanding ELS and CT command
submissions.  Thus, move the LPFC_SLI_ACTIVE flag check into the txcmplq
list walk and mark a piocb object for canceling if determined the HBA is
not active.  Clean up should be regardless of application or driver
layer origin.

Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Link: https://lore.kernel.org/r/20241031223219.152342-5-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_els.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index d737b897ddd82..3d965c0fd0c6d 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1236,9 +1236,9 @@ lpfc_cmpl_els_link_down(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_ELS,
 			"6445 ELS completes after LINK_DOWN: "
-			" Status %x/%x cmd x%x flg x%x\n",
+			" Status %x/%x cmd x%x flg x%x iotag x%x\n",
 			ulp_status, ulp_word4, cmd,
-			cmdiocb->cmd_flag);
+			cmdiocb->cmd_flag, cmdiocb->iotag);
 
 	if (cmdiocb->cmd_flag & LPFC_IO_FABRIC) {
 		cmdiocb->cmd_flag &= ~LPFC_IO_FABRIC;
@@ -9642,14 +9642,24 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport)
 	mbx_tmo_err = test_bit(MBX_TMO_ERR, &phba->bit_flags);
 	/* First we need to issue aborts to outstanding cmds on txcmpl */
 	list_for_each_entry_safe(piocb, tmp_iocb, &pring->txcmplq, list) {
-		if (piocb->cmd_flag & LPFC_IO_LIBDFC && !mbx_tmo_err)
-			continue;
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
+				 "2243 iotag = 0x%x cmd_flag = 0x%x "
+				 "ulp_command = 0x%x this_vport %x "
+				 "sli_flag = 0x%x\n",
+				 piocb->iotag, piocb->cmd_flag,
+				 get_job_cmnd(phba, piocb),
+				 (piocb->vport == vport),
+				 phba->sli.sli_flag);
 
 		if (piocb->vport != vport)
 			continue;
 
-		if (piocb->cmd_flag & LPFC_DRIVER_ABORTED && !mbx_tmo_err)
-			continue;
+		if ((phba->sli.sli_flag & LPFC_SLI_ACTIVE) && !mbx_tmo_err) {
+			if (piocb->cmd_flag & LPFC_IO_LIBDFC)
+				continue;
+			if (piocb->cmd_flag & LPFC_DRIVER_ABORTED)
+				continue;
+		}
 
 		/* On the ELS ring we can have ELS_REQUESTs, ELS_RSPs,
 		 * or GEN_REQUESTs waiting for a CQE response.

From 98f8d3588097e321be70f83b844fa67d4828fe5c Mon Sep 17 00:00:00 2001
From: Justin Tee <justin.tee@broadcom.com>
Date: Thu, 31 Oct 2024 15:32:13 -0700
Subject: [PATCH 0793/1530] scsi: lpfc: Check SLI_ACTIVE flag in FDMI cmpl
 before submitting follow up FDMI

The lpfc_cmpl_ct_disc_fdmi() routine has incorrect logic that treats an
FDMI completion with error LOCAL_REJECT/SLI_ABORTED as a success status.
Under the erroneous assumption of successful completion, the routine
proceeds to issue follow up FDMI commands, which may never complete if
the HBA is in an errata state as indicated by the errored completion
status.  Fix by freeing FDMI cmd resources and early return when the
LPFC_SLI_ACTIVE flag is not set and a LOCAL_REJECT/SLI_ABORTED or
SLI_DOWN status is received.

Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Link: https://lore.kernel.org/r/20241031223219.152342-6-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_ct.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index 134bc96dd1340..ce3a1f42713dd 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -2226,6 +2226,11 @@ lpfc_cmpl_ct_disc_fdmi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		ulp_status, ulp_word4, latt);
 
 	if (latt || ulp_status) {
+		lpfc_printf_vlog(vport, KERN_WARNING, LOG_DISCOVERY,
+				 "0229 FDMI cmd %04x failed, latt = %d "
+				 "ulp_status: (x%x/x%x), sli_flag x%x\n",
+				 be16_to_cpu(fdmi_cmd), latt, ulp_status,
+				 ulp_word4, phba->sli.sli_flag);
 
 		/* Look for a retryable error */
 		if (ulp_status == IOSTAT_LOCAL_REJECT) {
@@ -2234,8 +2239,16 @@ lpfc_cmpl_ct_disc_fdmi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			case IOERR_SLI_DOWN:
 				/* Driver aborted this IO.  No retry as error
 				 * is likely Offline->Online or some adapter
-				 * error.  Recovery will try again.
+				 * error.  Recovery will try again, but if port
+				 * is not active there's no point to continue
+				 * issuing follow up FDMI commands.
 				 */
+				if (!(phba->sli.sli_flag & LPFC_SLI_ACTIVE)) {
+					free_ndlp = cmdiocb->ndlp;
+					lpfc_ct_free_iocb(phba, cmdiocb);
+					lpfc_nlp_put(free_ndlp);
+					return;
+				}
 				break;
 			case IOERR_ABORT_IN_PROGRESS:
 			case IOERR_SEQUENCE_TIMEOUT:
@@ -2256,12 +2269,6 @@ lpfc_cmpl_ct_disc_fdmi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 				break;
 			}
 		}
-
-		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
-				 "0229 FDMI cmd %04x latt = %d "
-				 "ulp_status: x%x, rid x%x\n",
-				 be16_to_cpu(fdmi_cmd), latt, ulp_status,
-				 ulp_word4);
 	}
 
 	free_ndlp = cmdiocb->ndlp;

From eb038363d8e9ae0d9fa31a0600438d19b283dd41 Mon Sep 17 00:00:00 2001
From: Justin Tee <justin.tee@broadcom.com>
Date: Thu, 31 Oct 2024 15:32:14 -0700
Subject: [PATCH 0794/1530] scsi: lpfc: Add cleanup of nvmels_wq after HBA
 reset

An HBA reset request that is executed when there are outstanding NVME-LS
commands can cause delays for the reset process to complete.  Fix by
introducing a new routine called lpfc_nvmels_flush_cmd() that walks the
phba->nvmels_wq list and cancels outstanding submitted NVME-LS requests
speeding up the HBA reset process.

Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Link: https://lore.kernel.org/r/20241031223219.152342-7-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_crtn.h |  1 +
 drivers/scsi/lpfc/lpfc_init.c |  1 +
 drivers/scsi/lpfc/lpfc_nvme.c | 51 +++++++++++++++++++++++++++++++++--
 3 files changed, 51 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index d4e46a08f94da..b1e26a5abe58e 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -660,6 +660,7 @@ void lpfc_wqe_cmd_template(void);
 void lpfc_nvmet_cmd_template(void);
 void lpfc_nvme_cancel_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 			   uint32_t stat, uint32_t param);
+void lpfc_nvmels_flush_cmd(struct lpfc_hba *phba);
 extern int lpfc_enable_nvmet_cnt;
 extern unsigned long long lpfc_enable_nvmet[];
 extern int lpfc_no_hba_reset_cnt;
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index a3658ef1141b2..c16a321404c5b 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -1943,6 +1943,7 @@ lpfc_sli4_port_sta_fn_reset(struct lpfc_hba *phba, int mbx_action,
 
 	lpfc_offline_prep(phba, mbx_action);
 	lpfc_sli_flush_io_rings(phba);
+	lpfc_nvmels_flush_cmd(phba);
 	lpfc_offline(phba);
 	/* release interrupt for possible resource change */
 	lpfc_sli4_disable_intr(phba);
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index d70da2736c945..4f628e00d1c18 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -2231,6 +2231,7 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport,
 	struct lpfc_hba  *phba = vport->phba;
 	struct lpfc_sli4_hdw_queue *qp;
 	int abts_scsi, abts_nvme;
+	u16 nvmels_cnt;
 
 	/* Host transport has to clean up and confirm requiring an indefinite
 	 * wait. Print a message if a 10 second wait expires and renew the
@@ -2243,6 +2244,7 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport,
 			pending = 0;
 			abts_scsi = 0;
 			abts_nvme = 0;
+			nvmels_cnt = 0;
 			for (i = 0; i < phba->cfg_hdw_queue; i++) {
 				qp = &phba->sli4_hba.hdwq[i];
 				if (!vport->localport || !qp || !qp->io_wq)
@@ -2255,6 +2257,11 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport,
 				abts_scsi += qp->abts_scsi_io_bufs;
 				abts_nvme += qp->abts_nvme_io_bufs;
 			}
+			if (phba->sli4_hba.nvmels_wq) {
+				pring = phba->sli4_hba.nvmels_wq->pring;
+				if (pring)
+					nvmels_cnt = pring->txcmplq_cnt;
+			}
 			if (!vport->localport ||
 			    test_bit(HBA_PCI_ERR, &vport->phba->bit_flags) ||
 			    phba->link_state == LPFC_HBA_ERROR ||
@@ -2263,10 +2270,10 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport,
 
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 					 "6176 Lport x%px Localport x%px wait "
-					 "timed out. Pending %d [%d:%d]. "
+					 "timed out. Pending %d [%d:%d:%d]. "
 					 "Renewing.\n",
 					 lport, vport->localport, pending,
-					 abts_scsi, abts_nvme);
+					 abts_scsi, abts_nvme, nvmels_cnt);
 			continue;
 		}
 		break;
@@ -2841,3 +2848,43 @@ lpfc_nvme_cancel_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 	(pwqeIn->cmd_cmpl)(phba, pwqeIn, pwqeIn);
 #endif
 }
+
+/**
+ * lpfc_nvmels_flush_cmd - Clean up outstanding nvmels commands for a port
+ * @phba: Pointer to HBA context object.
+ *
+ **/
+void
+lpfc_nvmels_flush_cmd(struct lpfc_hba *phba)
+{
+#if (IS_ENABLED(CONFIG_NVME_FC))
+	LIST_HEAD(cancel_list);
+	struct lpfc_sli_ring *pring = NULL;
+	struct lpfc_iocbq *piocb, *tmp_iocb;
+	unsigned long iflags;
+
+	if (phba->sli4_hba.nvmels_wq)
+		pring = phba->sli4_hba.nvmels_wq->pring;
+
+	if (unlikely(!pring))
+		return;
+
+	spin_lock_irqsave(&phba->hbalock, iflags);
+	spin_lock(&pring->ring_lock);
+	list_splice_init(&pring->txq, &cancel_list);
+	pring->txq_cnt = 0;
+	list_for_each_entry_safe(piocb, tmp_iocb, &pring->txcmplq, list) {
+		if (piocb->cmd_flag & LPFC_IO_NVME_LS) {
+			list_move_tail(&piocb->list, &cancel_list);
+			pring->txcmplq_cnt--;
+			piocb->cmd_flag &= ~LPFC_IO_ON_TXCMPLQ;
+		}
+	}
+	spin_unlock(&pring->ring_lock);
+	spin_unlock_irqrestore(&phba->hbalock, iflags);
+
+	if (!list_empty(&cancel_list))
+		lpfc_sli_cancel_iocbs(phba, &cancel_list, IOSTAT_LOCAL_REJECT,
+				      IOERR_SLI_DOWN);
+#endif
+}

From 4281f44ea8bfedd25938a0031bebba1473ece9ad Mon Sep 17 00:00:00 2001
From: Justin Tee <justin.tee@broadcom.com>
Date: Thu, 31 Oct 2024 15:32:15 -0700
Subject: [PATCH 0795/1530] scsi: lpfc: Prevent NDLP reference count underflow
 in dev_loss_tmo callback

Current dev_loss_tmo handling checks whether there has been a previous
call to unregister with SCSI transport.  If so, the NDLP kref count is
decremented a second time in dev_loss_tmo as the final kref release.
However, this can sometimes result in a reference count underflow if
there is also a race to unregister with NVMe transport as well.  Add a
check for NVMe transport registration before decrementing the final
kref.  If NVMe transport is still registered, then the NVMe transport
unregistration is designated as the final kref decrement.

Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Link: https://lore.kernel.org/r/20241031223219.152342-8-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_hbadisc.c | 36 +++++++++++++++++++++-----------
 1 file changed, 24 insertions(+), 12 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index a434faec3c92b..3c8cb6ecc0ac0 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -161,6 +161,7 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
 	struct lpfc_hba   *phba;
 	struct lpfc_work_evt *evtp;
 	unsigned long iflags;
+	bool nvme_reg = false;
 
 	ndlp = ((struct lpfc_rport_data *)rport->dd_data)->pnode;
 	if (!ndlp)
@@ -183,38 +184,49 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
 	/* Don't schedule a worker thread event if the vport is going down. */
 	if (test_bit(FC_UNLOADING, &vport->load_flag) ||
 	    !test_bit(HBA_SETUP, &phba->hba_flag)) {
+
 		spin_lock_irqsave(&ndlp->lock, iflags);
 		ndlp->rport = NULL;
 
+		if (ndlp->fc4_xpt_flags & NVME_XPT_REGD)
+			nvme_reg = true;
+
 		/* The scsi_transport is done with the rport so lpfc cannot
-		 * call to unregister. Remove the scsi transport reference
-		 * and clean up the SCSI transport node details.
+		 * call to unregister.
 		 */
-		if (ndlp->fc4_xpt_flags & (NLP_XPT_REGD | SCSI_XPT_REGD)) {
+		if (ndlp->fc4_xpt_flags & SCSI_XPT_REGD) {
 			ndlp->fc4_xpt_flags &= ~SCSI_XPT_REGD;
 
-			/* NVME transport-registered rports need the
-			 * NLP_XPT_REGD flag to complete an unregister.
+			/* If NLP_XPT_REGD was cleared in lpfc_nlp_unreg_node,
+			 * unregister calls were made to the scsi and nvme
+			 * transports and refcnt was already decremented. Clear
+			 * the NLP_XPT_REGD flag only if the NVME Rport is
+			 * confirmed unregistered.
 			 */
-			if (!(ndlp->fc4_xpt_flags & NVME_XPT_REGD))
+			if (!nvme_reg && ndlp->fc4_xpt_flags & NLP_XPT_REGD) {
 				ndlp->fc4_xpt_flags &= ~NLP_XPT_REGD;
+				spin_unlock_irqrestore(&ndlp->lock, iflags);
+				lpfc_nlp_put(ndlp); /* may free ndlp */
+			} else {
+				spin_unlock_irqrestore(&ndlp->lock, iflags);
+			}
+		} else {
 			spin_unlock_irqrestore(&ndlp->lock, iflags);
-			lpfc_nlp_put(ndlp);
-			spin_lock_irqsave(&ndlp->lock, iflags);
 		}
 
+		spin_lock_irqsave(&ndlp->lock, iflags);
+
 		/* Only 1 thread can drop the initial node reference.  If
 		 * another thread has set NLP_DROPPED, this thread is done.
 		 */
-		if (!(ndlp->fc4_xpt_flags & NVME_XPT_REGD) &&
-		    !(ndlp->nlp_flag & NLP_DROPPED)) {
-			ndlp->nlp_flag |= NLP_DROPPED;
+		if (nvme_reg || (ndlp->nlp_flag & NLP_DROPPED)) {
 			spin_unlock_irqrestore(&ndlp->lock, iflags);
-			lpfc_nlp_put(ndlp);
 			return;
 		}
 
+		ndlp->nlp_flag |= NLP_DROPPED;
 		spin_unlock_irqrestore(&ndlp->lock, iflags);
+		lpfc_nlp_put(ndlp);
 		return;
 	}
 

From 32566a6f1ae558d0e79fed6e17a75c253367a57f Mon Sep 17 00:00:00 2001
From: Justin Tee <justin.tee@broadcom.com>
Date: Thu, 31 Oct 2024 15:32:16 -0700
Subject: [PATCH 0796/1530] scsi: lpfc: Remove NLP_RELEASE_RPI flag from
 nodelist structure

An RPI is tightly bound to an NDLP structure and is freed only upon
release of an NDLP object.  As such, there should be no logic that frees
an RPI outside of the lpfc_nlp_release() routine.  In order to reinforce
the original design usage of RPIs, remove the NLP_RELEASE_RPI flag and
related logic.

Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Link: https://lore.kernel.org/r/20241031223219.152342-9-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_crtn.h    |  2 +-
 drivers/scsi/lpfc/lpfc_disc.h    |  1 -
 drivers/scsi/lpfc/lpfc_els.c     | 32 +++-----------------
 drivers/scsi/lpfc/lpfc_hbadisc.c | 52 +++++++-------------------------
 drivers/scsi/lpfc/lpfc_init.c    | 36 +++++++---------------
 drivers/scsi/lpfc/lpfc_sli.c     | 48 +++++++++++------------------
 6 files changed, 44 insertions(+), 127 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index b1e26a5abe58e..f8a77ffdb0a89 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -571,7 +571,7 @@ int lpfc_issue_reg_vfi(struct lpfc_vport *);
 int lpfc_issue_unreg_vfi(struct lpfc_vport *);
 int lpfc_selective_reset(struct lpfc_hba *);
 int lpfc_sli4_read_config(struct lpfc_hba *);
-void lpfc_sli4_node_prep(struct lpfc_hba *);
+void lpfc_sli4_node_rpi_restore(struct lpfc_hba *phba);
 int lpfc_sli4_els_sgl_update(struct lpfc_hba *phba);
 int lpfc_sli4_nvmet_sgl_update(struct lpfc_hba *phba);
 int lpfc_io_buf_flush(struct lpfc_hba *phba, struct list_head *sglist);
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index f5ae8cc158205..5d6eabaeb094e 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -185,7 +185,6 @@ struct lpfc_node_rrq {
 /* Defines for nlp_flag (uint32) */
 #define NLP_IGNR_REG_CMPL  0x00000001 /* Rcvd rscn before we cmpl reg login */
 #define NLP_REG_LOGIN_SEND 0x00000002   /* sent reglogin to adapter */
-#define NLP_RELEASE_RPI    0x00000004   /* Release RPI to free pool */
 #define NLP_SUPPRESS_RSP   0x00000010	/* Remote NPort supports suppress rsp */
 #define NLP_PLOGI_SND      0x00000020	/* sent PLOGI request for this entry */
 #define NLP_PRLI_SND       0x00000040	/* sent PRLI request for this entry */
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 3d965c0fd0c6d..2c64f8d0a7bda 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -3063,8 +3063,6 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	 */
 	if (ndlp->nlp_flag & NLP_TARGET_REMOVE) {
 		spin_lock_irq(&ndlp->lock);
-		if (phba->sli_rev == LPFC_SLI_REV4)
-			ndlp->nlp_flag |= NLP_RELEASE_RPI;
 		ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
 		spin_unlock_irq(&ndlp->lock);
 		lpfc_disc_state_machine(vport, ndlp, cmdiocb,
@@ -5456,24 +5454,14 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	}
 
 	/* An SLI4 NPIV instance wants to drop the node at this point under
-	 * these conditions and release the RPI.
+	 * these conditions because it doesn't need the login.
 	 */
 	if (phba->sli_rev == LPFC_SLI_REV4 &&
 	    vport && vport->port_type == LPFC_NPIV_PORT &&
 	    !(ndlp->fc4_xpt_flags & SCSI_XPT_REGD)) {
-		if (ndlp->nlp_flag & NLP_RELEASE_RPI) {
-			if (ndlp->nlp_state != NLP_STE_PLOGI_ISSUE &&
-			    ndlp->nlp_state != NLP_STE_REG_LOGIN_ISSUE) {
-				lpfc_sli4_free_rpi(phba, ndlp->nlp_rpi);
-				spin_lock_irq(&ndlp->lock);
-				ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
-				ndlp->nlp_flag &= ~NLP_RELEASE_RPI;
-				spin_unlock_irq(&ndlp->lock);
-			}
-			lpfc_drop_node(vport, ndlp);
-		} else if (ndlp->nlp_state != NLP_STE_PLOGI_ISSUE &&
-			   ndlp->nlp_state != NLP_STE_REG_LOGIN_ISSUE &&
-			   ndlp->nlp_state != NLP_STE_PRLI_ISSUE) {
+		if (ndlp->nlp_state != NLP_STE_PLOGI_ISSUE &&
+		    ndlp->nlp_state != NLP_STE_REG_LOGIN_ISSUE &&
+		    ndlp->nlp_state != NLP_STE_PRLI_ISSUE) {
 			/* Drop ndlp if there is no planned or outstanding
 			 * issued PRLI.
 			 *
@@ -5852,18 +5840,6 @@ lpfc_els_rsp_reject(struct lpfc_vport *vport, uint32_t rejectError,
 		return 1;
 	}
 
-	/* The NPIV instance is rejecting this unsolicited ELS. Make sure the
-	 * node's assigned RPI gets released provided this node is not already
-	 * registered with the transport.
-	 */
-	if (phba->sli_rev == LPFC_SLI_REV4 &&
-	    vport->port_type == LPFC_NPIV_PORT &&
-	    !(ndlp->fc4_xpt_flags & SCSI_XPT_REGD)) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_RELEASE_RPI;
-		spin_unlock_irq(&ndlp->lock);
-	}
-
 	rc = lpfc_sli_issue_iocb(phba, LPFC_ELS_RING, elsiocb, 0);
 	if (rc == IOCB_ERROR) {
 		lpfc_els_free_iocb(phba, elsiocb);
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 3c8cb6ecc0ac0..af1fdecf53411 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -5212,14 +5212,6 @@ lpfc_nlp_logo_unreg(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		ndlp->nlp_defer_did = NLP_EVT_NOTHING_PENDING;
 		lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
 	} else {
-		/* NLP_RELEASE_RPI is only set for SLI4 ports. */
-		if (ndlp->nlp_flag & NLP_RELEASE_RPI) {
-			lpfc_sli4_free_rpi(vport->phba, ndlp->nlp_rpi);
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_RELEASE_RPI;
-			ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
-			spin_unlock_irq(&ndlp->lock);
-		}
 		spin_lock_irq(&ndlp->lock);
 		ndlp->nlp_flag &= ~NLP_UNREG_INP;
 		spin_unlock_irq(&ndlp->lock);
@@ -5242,8 +5234,6 @@ static void
 lpfc_set_unreg_login_mbx_cmpl(struct lpfc_hba *phba, struct lpfc_vport *vport,
 	struct lpfc_nodelist *ndlp, LPFC_MBOXQ_t *mbox)
 {
-	unsigned long iflags;
-
 	/* Driver always gets a reference on the mailbox job
 	 * in support of async jobs.
 	 */
@@ -5261,13 +5251,6 @@ lpfc_set_unreg_login_mbx_cmpl(struct lpfc_hba *phba, struct lpfc_vport *vport,
 		    (kref_read(&ndlp->kref) > 0)) {
 		mbox->mbox_cmpl = lpfc_sli4_unreg_rpi_cmpl_clr;
 	} else {
-		if (test_bit(FC_UNLOADING, &vport->load_flag)) {
-			if (phba->sli_rev == LPFC_SLI_REV4) {
-				spin_lock_irqsave(&ndlp->lock, iflags);
-				ndlp->nlp_flag |= NLP_RELEASE_RPI;
-				spin_unlock_irqrestore(&ndlp->lock, iflags);
-			}
-		}
 		mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
 	}
 }
@@ -5330,14 +5313,11 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 				return 1;
 			}
 
+			/* Accept PLOGIs after unreg_rpi_cmpl. */
 			if (mbox->mbox_cmpl == lpfc_sli4_unreg_rpi_cmpl_clr)
-				/*
-				 * accept PLOGIs after unreg_rpi_cmpl
-				 */
 				acc_plogi = 0;
-			if (((ndlp->nlp_DID & Fabric_DID_MASK) !=
-			    Fabric_DID_MASK) &&
-			    (!test_bit(FC_OFFLINE_MODE, &vport->fc_flag)))
+
+			if (!test_bit(FC_OFFLINE_MODE, &vport->fc_flag))
 				ndlp->nlp_flag |= NLP_UNREG_INP;
 
 			lpfc_printf_vlog(vport, KERN_INFO,
@@ -5561,10 +5541,6 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	list_del_init(&ndlp->dev_loss_evt.evt_listp);
 	list_del_init(&ndlp->recovery_evt.evt_listp);
 	lpfc_cleanup_vports_rrqs(vport, ndlp);
-
-	if (phba->sli_rev == LPFC_SLI_REV4)
-		ndlp->nlp_flag |= NLP_RELEASE_RPI;
-
 	return 0;
 }
 
@@ -6573,8 +6549,9 @@ lpfc_nlp_init(struct lpfc_vport *vport, uint32_t did)
 	INIT_LIST_HEAD(&ndlp->nlp_listp);
 	if (vport->phba->sli_rev == LPFC_SLI_REV4) {
 		ndlp->nlp_rpi = rpi;
-		lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_DISCOVERY,
-				 "0007 Init New ndlp x%px, rpi:x%x DID:%x "
+		lpfc_printf_vlog(vport, KERN_INFO,
+				 LOG_ELS | LOG_NODE | LOG_DISCOVERY,
+				 "0007 Init New ndlp x%px, rpi:x%x DID:x%x "
 				 "flg:x%x refcnt:%d\n",
 				 ndlp, ndlp->nlp_rpi, ndlp->nlp_DID,
 				 ndlp->nlp_flag, kref_read(&ndlp->kref));
@@ -6619,19 +6596,12 @@ lpfc_nlp_release(struct kref *kref)
 	lpfc_cancel_retry_delay_tmo(vport, ndlp);
 	lpfc_cleanup_node(vport, ndlp);
 
-	/* Not all ELS transactions have registered the RPI with the port.
-	 * In these cases the rpi usage is temporary and the node is
-	 * released when the WQE is completed.  Catch this case to free the
-	 * RPI to the pool.  Because this node is in the release path, a lock
-	 * is unnecessary.  All references are gone and the node has been
-	 * dequeued.
+	/* All nodes are initialized with an RPI that needs to be released
+	 * now. All references are gone and the node has been dequeued.
 	 */
-	if (ndlp->nlp_flag & NLP_RELEASE_RPI) {
-		if (ndlp->nlp_rpi != LPFC_RPI_ALLOC_ERROR &&
-		    !(ndlp->nlp_flag & (NLP_RPI_REGISTERED | NLP_UNREG_INP))) {
-			lpfc_sli4_free_rpi(vport->phba, ndlp->nlp_rpi);
-			ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
-		}
+	if (vport->phba->sli_rev == LPFC_SLI_REV4) {
+		lpfc_sli4_free_rpi(vport->phba, ndlp->nlp_rpi);
+		ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
 	}
 
 	/* The node is not freed back to memory, it is released to a pool so
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index c16a321404c5b..006e22506ae89 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -3380,7 +3380,7 @@ lpfc_block_mgmt_io(struct lpfc_hba *phba, int mbx_action)
 }
 
 /**
- * lpfc_sli4_node_prep - Assign RPIs for active nodes.
+ * lpfc_sli4_node_rpi_restore - Recover assigned RPIs for active nodes.
  * @phba: pointer to lpfc hba data structure.
  *
  * Allocate RPIs for all active remote nodes. This is needed whenever
@@ -3388,7 +3388,7 @@ lpfc_block_mgmt_io(struct lpfc_hba *phba, int mbx_action)
  * is to fixup the temporary rpi assignments.
  **/
 void
-lpfc_sli4_node_prep(struct lpfc_hba *phba)
+lpfc_sli4_node_rpi_restore(struct lpfc_hba *phba)
 {
 	struct lpfc_nodelist  *ndlp, *next_ndlp;
 	struct lpfc_vport **vports;
@@ -3398,10 +3398,10 @@ lpfc_sli4_node_prep(struct lpfc_hba *phba)
 		return;
 
 	vports = lpfc_create_vport_work_array(phba);
-	if (vports == NULL)
+	if (!vports)
 		return;
 
-	for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
+	for (i = 0; i <= phba->max_vports && vports[i]; i++) {
 		if (test_bit(FC_UNLOADING, &vports[i]->load_flag))
 			continue;
 
@@ -3410,7 +3410,13 @@ lpfc_sli4_node_prep(struct lpfc_hba *phba)
 					 nlp_listp) {
 			rpi = lpfc_sli4_alloc_rpi(phba);
 			if (rpi == LPFC_RPI_ALLOC_ERROR) {
-				/* TODO print log? */
+				lpfc_printf_vlog(ndlp->vport, KERN_INFO,
+						 LOG_NODE | LOG_DISCOVERY,
+						 "0099 RPI alloc error for "
+						 "ndlp x%px DID:x%06x "
+						 "flg:x%x\n",
+						 ndlp, ndlp->nlp_DID,
+						 ndlp->nlp_flag);
 				continue;
 			}
 			ndlp->nlp_rpi = rpi;
@@ -3830,26 +3836,6 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action)
 					ndlp->nlp_flag &= ~(NLP_UNREG_INP |
 							    NLP_RPI_REGISTERED);
 					spin_unlock_irq(&ndlp->lock);
-					if (phba->sli_rev == LPFC_SLI_REV4)
-						lpfc_sli_rpi_release(vports[i],
-								     ndlp);
-				} else {
-					lpfc_unreg_rpi(vports[i], ndlp);
-				}
-				/*
-				 * Whenever an SLI4 port goes offline, free the
-				 * RPI. Get a new RPI when the adapter port
-				 * comes back online.
-				 */
-				if (phba->sli_rev == LPFC_SLI_REV4) {
-					lpfc_printf_vlog(vports[i], KERN_INFO,
-						 LOG_NODE | LOG_DISCOVERY,
-						 "0011 Free RPI x%x on "
-						 "ndlp: x%px did x%x\n",
-						 ndlp->nlp_rpi, ndlp,
-						 ndlp->nlp_DID);
-					lpfc_sli4_free_rpi(phba, ndlp->nlp_rpi);
-					ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
 				}
 
 				if (ndlp->nlp_type & NLP_FABRIC) {
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 5ad5ff10256b6..c1ce05646e725 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -2844,27 +2844,6 @@ lpfc_sli_wake_mbox_wait(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 	return;
 }
 
-static void
-__lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
-{
-	unsigned long iflags;
-
-	if (ndlp->nlp_flag & NLP_RELEASE_RPI) {
-		lpfc_sli4_free_rpi(vport->phba, ndlp->nlp_rpi);
-		spin_lock_irqsave(&ndlp->lock, iflags);
-		ndlp->nlp_flag &= ~NLP_RELEASE_RPI;
-		ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
-		spin_unlock_irqrestore(&ndlp->lock, iflags);
-	}
-	ndlp->nlp_flag &= ~NLP_UNREG_INP;
-}
-
-void
-lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
-{
-	__lpfc_sli_rpi_release(vport, ndlp);
-}
-
 /**
  * lpfc_sli_def_mbox_cmpl - Default mailbox completion handler
  * @phba: Pointer to HBA context object.
@@ -2944,8 +2923,6 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 				ndlp->nlp_flag &= ~NLP_UNREG_INP;
 				ndlp->nlp_defer_did = NLP_EVT_NOTHING_PENDING;
 				lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
-			} else {
-				__lpfc_sli_rpi_release(vport, ndlp);
 			}
 
 			/* The unreg_login mailbox is complete and had a
@@ -2993,6 +2970,7 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 {
 	struct lpfc_vport  *vport = pmb->vport;
 	struct lpfc_nodelist *ndlp;
+	u32 unreg_inp;
 
 	ndlp = pmb->ctx_ndlp;
 	if (pmb->u.mb.mbxCommand == MBX_UNREG_LOGIN) {
@@ -3011,14 +2989,22 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 					 ndlp->nlp_DID, ndlp->nlp_defer_did,
 					 ndlp->nlp_flag,
 					 ndlp);
-				ndlp->nlp_flag &= ~NLP_LOGO_ACC;
+
+				/* Cleanup the nlp_flag now that the UNREG RPI
+				 * has completed.
+				 */
+				spin_lock_irq(&ndlp->lock);
+				unreg_inp = ndlp->nlp_flag & NLP_UNREG_INP;
+				ndlp->nlp_flag &=
+					~(NLP_UNREG_INP | NLP_LOGO_ACC);
+				spin_unlock_irq(&ndlp->lock);
 
 				/* Check to see if there are any deferred
 				 * events to process
 				 */
-				if ((ndlp->nlp_flag & NLP_UNREG_INP) &&
-				    (ndlp->nlp_defer_did !=
-				    NLP_EVT_NOTHING_PENDING)) {
+				if (unreg_inp &&
+				    ndlp->nlp_defer_did !=
+				    NLP_EVT_NOTHING_PENDING) {
 					lpfc_printf_vlog(
 						vport, KERN_INFO,
 						LOG_MBOX | LOG_SLI | LOG_NODE,
@@ -3027,14 +3013,12 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 						"NPort x%x Data: x%x x%px\n",
 						ndlp->nlp_rpi, ndlp->nlp_DID,
 						ndlp->nlp_defer_did, ndlp);
-					ndlp->nlp_flag &= ~NLP_UNREG_INP;
 					ndlp->nlp_defer_did =
 						NLP_EVT_NOTHING_PENDING;
 					lpfc_issue_els_plogi(
 						vport, ndlp->nlp_DID, 0);
-				} else {
-					__lpfc_sli_rpi_release(vport, ndlp);
 				}
+
 				lpfc_nlp_put(ndlp);
 			}
 		}
@@ -8752,6 +8736,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 				lpfc_sli_config_mbox_opcode_get(
 					phba, mboxq),
 				rc, dd);
+
 	/*
 	 * Allocate all resources (xri,rpi,vpi,vfi) now.  Subsequent
 	 * calls depends on these resources to complete port setup.
@@ -8764,6 +8749,8 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 		goto out_free_mbox;
 	}
 
+	lpfc_sli4_node_rpi_restore(phba);
+
 	lpfc_set_host_data(phba, mboxq);
 
 	rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
@@ -8951,7 +8938,6 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 		rc = -ENODEV;
 		goto out_free_iocblist;
 	}
-	lpfc_sli4_node_prep(phba);
 
 	if (!test_bit(HBA_FCOE_MODE, &phba->hba_flag)) {
 		if ((phba->nvmet_support == 0) || (phba->cfg_nvmet_mrq == 1)) {

From 92b99f1a73b7951f05590fd01640dcafdbc82c21 Mon Sep 17 00:00:00 2001
From: Justin Tee <justin.tee@broadcom.com>
Date: Thu, 31 Oct 2024 15:32:17 -0700
Subject: [PATCH 0797/1530] scsi: lpfc: Change lpfc_nodelist nlp_flag member
 into a bitmask

In attempt to reduce the amount of unnecessary ndlp->lock acquisitions
in the lpfc driver, change nlpa_flag into an unsigned long bitmask and
use clear_bit/test_bit bitwise atomic APIs instead of reliance on
ndlp->lock for synchronization.

Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Link: https://lore.kernel.org/r/20241031223219.152342-10-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_bsg.c       |   6 +-
 drivers/scsi/lpfc/lpfc_ct.c        |  18 +-
 drivers/scsi/lpfc/lpfc_debugfs.c   |   4 +-
 drivers/scsi/lpfc/lpfc_disc.h      |  59 ++---
 drivers/scsi/lpfc/lpfc_els.c       | 405 ++++++++++++-----------------
 drivers/scsi/lpfc/lpfc_hbadisc.c   | 225 +++++++---------
 drivers/scsi/lpfc/lpfc_init.c      |  24 +-
 drivers/scsi/lpfc/lpfc_nportdisc.c | 329 ++++++++++-------------
 drivers/scsi/lpfc/lpfc_nvme.c      |   9 +-
 drivers/scsi/lpfc/lpfc_nvmet.c     |   2 +-
 drivers/scsi/lpfc/lpfc_scsi.c      |   8 +-
 drivers/scsi/lpfc/lpfc_sli.c       |  42 ++-
 drivers/scsi/lpfc/lpfc_vport.c     |   6 +-
 13 files changed, 476 insertions(+), 661 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index 85059b83ea6b4..1c6b024160da7 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -398,7 +398,11 @@ lpfc_bsg_send_mgmt_cmd(struct bsg_job *job)
 	/* in case no data is transferred */
 	bsg_reply->reply_payload_rcv_len = 0;
 
-	if (ndlp->nlp_flag & NLP_ELS_SND_MASK)
+	if (test_bit(NLP_PLOGI_SND, &ndlp->nlp_flag) ||
+	    test_bit(NLP_PRLI_SND, &ndlp->nlp_flag) ||
+	    test_bit(NLP_ADISC_SND, &ndlp->nlp_flag) ||
+	    test_bit(NLP_LOGO_SND, &ndlp->nlp_flag) ||
+	    test_bit(NLP_RNID_SND, &ndlp->nlp_flag))
 		return -ENODEV;
 
 	/* allocate our bsg tracking structure */
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index ce3a1f42713dd..30891ad17e2a4 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -735,7 +735,7 @@ lpfc_prep_node_fc4type(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
 
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 					 "0238 Process x%06x NameServer Rsp "
-					 "Data: x%x x%x x%x x%lx x%x\n", Did,
+					 "Data: x%lx x%x x%x x%lx x%x\n", Did,
 					 ndlp->nlp_flag, ndlp->nlp_fc4_type,
 					 ndlp->nlp_state, vport->fc_flag,
 					 vport->fc_rscn_id_cnt);
@@ -744,7 +744,7 @@ lpfc_prep_node_fc4type(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
 			 * state of ndlp hit devloss, change state to
 			 * allow rediscovery.
 			 */
-			if (ndlp->nlp_flag & NLP_NPR_2B_DISC &&
+			if (test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag) &&
 			    ndlp->nlp_state == NLP_STE_UNUSED_NODE) {
 				lpfc_nlp_set_state(vport, ndlp,
 						   NLP_STE_NPR_NODE);
@@ -832,12 +832,10 @@ lpfc_ns_rsp_audit_did(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
 			if (ndlp->nlp_type != NLP_NVME_INITIATOR ||
 			    ndlp->nlp_state != NLP_STE_UNMAPPED_NODE)
 				continue;
-			spin_lock_irq(&ndlp->lock);
 			if (ndlp->nlp_DID == Did)
-				ndlp->nlp_flag &= ~NLP_NVMET_RECOV;
+				clear_bit(NLP_NVMET_RECOV, &ndlp->nlp_flag);
 			else
-				ndlp->nlp_flag |= NLP_NVMET_RECOV;
-			spin_unlock_irq(&ndlp->lock);
+				set_bit(NLP_NVMET_RECOV, &ndlp->nlp_flag);
 		}
 	}
 }
@@ -894,13 +892,11 @@ lpfc_ns_rsp(struct lpfc_vport *vport, struct lpfc_dmabuf *mp, uint8_t fc4_type,
 	 */
 	if (vport->phba->nvmet_support) {
 		list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) {
-			if (!(ndlp->nlp_flag & NLP_NVMET_RECOV))
+			if (!test_bit(NLP_NVMET_RECOV, &ndlp->nlp_flag))
 				continue;
 			lpfc_disc_state_machine(vport, ndlp, NULL,
 						NLP_EVT_DEVICE_RECOVERY);
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_NVMET_RECOV;
-			spin_unlock_irq(&ndlp->lock);
+			clear_bit(NLP_NVMET_RECOV, &ndlp->nlp_flag);
 		}
 	}
 
@@ -1440,7 +1436,7 @@ lpfc_cmpl_ct_cmd_gff_id(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	if (ndlp) {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 				 "0242 Process x%x GFF "
-				 "NameServer Rsp Data: x%x x%lx x%x\n",
+				 "NameServer Rsp Data: x%lx x%lx x%x\n",
 				 did, ndlp->nlp_flag, vport->fc_flag,
 				 vport->fc_rscn_id_cnt);
 	} else {
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index a2d2b02b34187..3fd1aa5cc78cc 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -870,8 +870,8 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 				wwn_to_u64(ndlp->nlp_nodename.u.wwn));
 		len += scnprintf(buf+len, size-len, "RPI:x%04x ",
 				 ndlp->nlp_rpi);
-		len +=  scnprintf(buf+len, size-len, "flag:x%08x ",
-			ndlp->nlp_flag);
+		len += scnprintf(buf+len, size-len, "flag:x%08lx ",
+				 ndlp->nlp_flag);
 		if (!ndlp->nlp_type)
 			len += scnprintf(buf+len, size-len, "UNKNOWN_TYPE ");
 		if (ndlp->nlp_type & NLP_FC_NODE)
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index 5d6eabaeb094e..af5d5bd75642c 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -102,7 +102,7 @@ struct lpfc_nodelist {
 
 	spinlock_t	lock;			/* Node management lock */
 
-	uint32_t         nlp_flag;		/* entry flags */
+	unsigned long    nlp_flag;		/* entry flags */
 	uint32_t         nlp_DID;		/* FC D_ID of entry */
 	uint32_t         nlp_last_elscmd;	/* Last ELS cmd sent */
 	uint16_t         nlp_type;
@@ -182,36 +182,37 @@ struct lpfc_node_rrq {
 #define lpfc_ndlp_check_qdepth(phba, ndlp) \
 	(ndlp->cmd_qdepth < phba->sli4_hba.max_cfg_param.max_xri)
 
-/* Defines for nlp_flag (uint32) */
-#define NLP_IGNR_REG_CMPL  0x00000001 /* Rcvd rscn before we cmpl reg login */
-#define NLP_REG_LOGIN_SEND 0x00000002   /* sent reglogin to adapter */
-#define NLP_SUPPRESS_RSP   0x00000010	/* Remote NPort supports suppress rsp */
-#define NLP_PLOGI_SND      0x00000020	/* sent PLOGI request for this entry */
-#define NLP_PRLI_SND       0x00000040	/* sent PRLI request for this entry */
-#define NLP_ADISC_SND      0x00000080	/* sent ADISC request for this entry */
-#define NLP_LOGO_SND       0x00000100	/* sent LOGO request for this entry */
-#define NLP_RNID_SND       0x00000400	/* sent RNID request for this entry */
-#define NLP_ELS_SND_MASK   0x000007e0	/* sent ELS request for this entry */
-#define NLP_NVMET_RECOV    0x00001000   /* NVMET auditing node for recovery. */
-#define NLP_UNREG_INP      0x00008000	/* UNREG_RPI cmd is in progress */
-#define NLP_DROPPED        0x00010000	/* Init ref count has been dropped */
-#define NLP_DELAY_TMO      0x00020000	/* delay timeout is running for node */
-#define NLP_NPR_2B_DISC    0x00040000	/* node is included in num_disc_nodes */
-#define NLP_RCV_PLOGI      0x00080000	/* Rcv'ed PLOGI from remote system */
-#define NLP_LOGO_ACC       0x00100000	/* Process LOGO after ACC completes */
-#define NLP_TGT_NO_SCSIID  0x00200000	/* good PRLI but no binding for scsid */
-#define NLP_ISSUE_LOGO     0x00400000	/* waiting to issue a LOGO */
-#define NLP_IN_DEV_LOSS    0x00800000	/* devloss in progress */
-#define NLP_ACC_REGLOGIN   0x01000000	/* Issue Reg Login after successful
+/* nlp_flag mask bits */
+enum lpfc_nlp_flag {
+	NLP_IGNR_REG_CMPL  = 0,         /* Rcvd rscn before we cmpl reg login */
+	NLP_REG_LOGIN_SEND = 1,         /* sent reglogin to adapter */
+	NLP_SUPPRESS_RSP   = 4,         /* Remote NPort supports suppress rsp */
+	NLP_PLOGI_SND      = 5,         /* sent PLOGI request for this entry */
+	NLP_PRLI_SND       = 6,         /* sent PRLI request for this entry */
+	NLP_ADISC_SND      = 7,         /* sent ADISC request for this entry */
+	NLP_LOGO_SND       = 8,         /* sent LOGO request for this entry */
+	NLP_RNID_SND       = 10,        /* sent RNID request for this entry */
+	NLP_NVMET_RECOV    = 12,        /* NVMET auditing node for recovery. */
+	NLP_UNREG_INP      = 15,        /* UNREG_RPI cmd is in progress */
+	NLP_DROPPED        = 16,        /* Init ref count has been dropped */
+	NLP_DELAY_TMO      = 17,        /* delay timeout is running for node */
+	NLP_NPR_2B_DISC    = 18,        /* node is included in num_disc_nodes */
+	NLP_RCV_PLOGI      = 19,        /* Rcv'ed PLOGI from remote system */
+	NLP_LOGO_ACC       = 20,        /* Process LOGO after ACC completes */
+	NLP_TGT_NO_SCSIID  = 21,        /* good PRLI but no binding for scsid */
+	NLP_ISSUE_LOGO     = 22,        /* waiting to issue a LOGO */
+	NLP_IN_DEV_LOSS    = 23,        /* devloss in progress */
+	NLP_ACC_REGLOGIN   = 24,        /* Issue Reg Login after successful
 					   ACC */
-#define NLP_NPR_ADISC      0x02000000	/* Issue ADISC when dq'ed from
+	NLP_NPR_ADISC      = 25,        /* Issue ADISC when dq'ed from
 					   NPR list */
-#define NLP_RM_DFLT_RPI    0x04000000	/* need to remove leftover dflt RPI */
-#define NLP_NODEV_REMOVE   0x08000000	/* Defer removal till discovery ends */
-#define NLP_TARGET_REMOVE  0x10000000   /* Target remove in process */
-#define NLP_SC_REQ         0x20000000	/* Target requires authentication */
-#define NLP_FIRSTBURST     0x40000000	/* Target supports FirstBurst */
-#define NLP_RPI_REGISTERED 0x80000000	/* nlp_rpi is valid */
+	NLP_RM_DFLT_RPI    = 26,        /* need to remove leftover dflt RPI */
+	NLP_NODEV_REMOVE   = 27,        /* Defer removal till discovery ends */
+	NLP_TARGET_REMOVE  = 28,        /* Target remove in process */
+	NLP_SC_REQ         = 29,        /* Target requires authentication */
+	NLP_FIRSTBURST     = 30,        /* Target supports FirstBurst */
+	NLP_RPI_REGISTERED = 31         /* nlp_rpi is valid */
+};
 
 /* There are 4 different double linked lists nodelist entries can reside on.
  * The Port Login (PLOGI) list and Address Discovery (ADISC) list are used
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 2c64f8d0a7bda..37f0a930d4691 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -725,11 +725,9 @@ lpfc_cmpl_els_flogi_fabric(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		list_for_each_entry_safe(np, next_np,
 					&vport->fc_nodes, nlp_listp) {
 			if ((np->nlp_state != NLP_STE_NPR_NODE) ||
-				   !(np->nlp_flag & NLP_NPR_ADISC))
+			    !test_bit(NLP_NPR_ADISC, &np->nlp_flag))
 				continue;
-			spin_lock_irq(&np->lock);
-			np->nlp_flag &= ~NLP_NPR_ADISC;
-			spin_unlock_irq(&np->lock);
+			clear_bit(NLP_NPR_ADISC, &np->nlp_flag);
 			lpfc_unreg_rpi(vport, np);
 		}
 		lpfc_cleanup_pending_mbox(vport);
@@ -864,9 +862,7 @@ lpfc_cmpl_els_flogi_nport(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		       sizeof(struct lpfc_name));
 		/* Set state will put ndlp onto node list if not already done */
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 
 		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 		if (!mbox)
@@ -1018,7 +1014,7 @@ lpfc_cmpl_els_flogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		 * registered with the SCSI transport, remove the initial
 		 * reference to trigger node release.
 		 */
-		if (!(ndlp->nlp_flag & NLP_IN_DEV_LOSS) &&
+		if (!test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag) &&
 		    !(ndlp->fc4_xpt_flags & SCSI_XPT_REGD))
 			lpfc_nlp_put(ndlp);
 
@@ -1548,7 +1544,7 @@ lpfc_initial_flogi(struct lpfc_vport *vport)
 		 * Otherwise, decrement node reference to trigger release.
 		 */
 		if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD)) &&
-		    !(ndlp->nlp_flag & NLP_IN_DEV_LOSS))
+		    !test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag))
 			lpfc_nlp_put(ndlp);
 		return 0;
 	}
@@ -1597,7 +1593,7 @@ lpfc_initial_fdisc(struct lpfc_vport *vport)
 		 * Otherwise, decrement node reference to trigger release.
 		 */
 		if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD)) &&
-		    !(ndlp->nlp_flag & NLP_IN_DEV_LOSS))
+		    !test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag))
 			lpfc_nlp_put(ndlp);
 		return 0;
 	}
@@ -1675,9 +1671,9 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 	struct lpfc_nodelist *new_ndlp;
 	struct serv_parm *sp;
 	uint8_t  name[sizeof(struct lpfc_name)];
-	uint32_t keepDID = 0, keep_nlp_flag = 0;
+	uint32_t keepDID = 0;
 	int rc;
-	uint32_t keep_new_nlp_flag = 0;
+	unsigned long keep_nlp_flag = 0, keep_new_nlp_flag = 0;
 	uint16_t keep_nlp_state;
 	u32 keep_nlp_fc4_type = 0;
 	struct lpfc_nvme_rport *keep_nrport = NULL;
@@ -1704,8 +1700,8 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 	}
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS | LOG_NODE,
-			 "3178 PLOGI confirm: ndlp x%x x%x x%x: "
-			 "new_ndlp x%x x%x x%x\n",
+			 "3178 PLOGI confirm: ndlp x%x x%lx x%x: "
+			 "new_ndlp x%x x%lx x%x\n",
 			 ndlp->nlp_DID, ndlp->nlp_flag,  ndlp->nlp_fc4_type,
 			 (new_ndlp ? new_ndlp->nlp_DID : 0),
 			 (new_ndlp ? new_ndlp->nlp_flag : 0),
@@ -1769,48 +1765,48 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 	new_ndlp->nlp_flag = ndlp->nlp_flag;
 
 	/* if new_ndlp had NLP_UNREG_INP set, keep it */
-	if (keep_new_nlp_flag & NLP_UNREG_INP)
-		new_ndlp->nlp_flag |= NLP_UNREG_INP;
+	if (test_bit(NLP_UNREG_INP, &keep_new_nlp_flag))
+		set_bit(NLP_UNREG_INP, &new_ndlp->nlp_flag);
 	else
-		new_ndlp->nlp_flag &= ~NLP_UNREG_INP;
+		clear_bit(NLP_UNREG_INP, &new_ndlp->nlp_flag);
 
 	/* if new_ndlp had NLP_RPI_REGISTERED set, keep it */
-	if (keep_new_nlp_flag & NLP_RPI_REGISTERED)
-		new_ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+	if (test_bit(NLP_RPI_REGISTERED, &keep_new_nlp_flag))
+		set_bit(NLP_RPI_REGISTERED, &new_ndlp->nlp_flag);
 	else
-		new_ndlp->nlp_flag &= ~NLP_RPI_REGISTERED;
+		clear_bit(NLP_RPI_REGISTERED, &new_ndlp->nlp_flag);
 
 	/*
 	 * Retain the DROPPED flag. This will take care of the init
 	 * refcount when affecting the state change
 	 */
-	if (keep_new_nlp_flag & NLP_DROPPED)
-		new_ndlp->nlp_flag |= NLP_DROPPED;
+	if (test_bit(NLP_DROPPED, &keep_new_nlp_flag))
+		set_bit(NLP_DROPPED, &new_ndlp->nlp_flag);
 	else
-		new_ndlp->nlp_flag &= ~NLP_DROPPED;
+		clear_bit(NLP_DROPPED, &new_ndlp->nlp_flag);
 
 	ndlp->nlp_flag = keep_new_nlp_flag;
 
 	/* if ndlp had NLP_UNREG_INP set, keep it */
-	if (keep_nlp_flag & NLP_UNREG_INP)
-		ndlp->nlp_flag |= NLP_UNREG_INP;
+	if (test_bit(NLP_UNREG_INP, &keep_nlp_flag))
+		set_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 	else
-		ndlp->nlp_flag &= ~NLP_UNREG_INP;
+		clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 
 	/* if ndlp had NLP_RPI_REGISTERED set, keep it */
-	if (keep_nlp_flag & NLP_RPI_REGISTERED)
-		ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+	if (test_bit(NLP_RPI_REGISTERED, &keep_nlp_flag))
+		set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
 	else
-		ndlp->nlp_flag &= ~NLP_RPI_REGISTERED;
+		clear_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
 
 	/*
 	 * Retain the DROPPED flag. This will take care of the init
 	 * refcount when affecting the state change
 	 */
-	if (keep_nlp_flag & NLP_DROPPED)
-		ndlp->nlp_flag |= NLP_DROPPED;
+	if (test_bit(NLP_DROPPED, &keep_nlp_flag))
+		set_bit(NLP_DROPPED, &ndlp->nlp_flag);
 	else
-		ndlp->nlp_flag &= ~NLP_DROPPED;
+		clear_bit(NLP_DROPPED, &ndlp->nlp_flag);
 
 	spin_unlock_irq(&new_ndlp->lock);
 	spin_unlock_irq(&ndlp->lock);
@@ -1888,7 +1884,7 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 			     phba->active_rrq_pool);
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS | LOG_NODE,
-			 "3173 PLOGI confirm exit: new_ndlp x%x x%x x%x\n",
+			 "3173 PLOGI confirm exit: new_ndlp x%x x%lx x%x\n",
 			 new_ndlp->nlp_DID, new_ndlp->nlp_flag,
 			 new_ndlp->nlp_fc4_type);
 
@@ -2009,7 +2005,7 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	IOCB_t *irsp;
 	struct lpfc_nodelist *ndlp, *free_ndlp;
 	struct lpfc_dmabuf *prsp;
-	int disc;
+	bool disc;
 	struct serv_parm *sp = NULL;
 	u32 ulp_status, ulp_word4, did, iotag;
 	bool release_node = false;
@@ -2044,10 +2040,7 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* Since ndlp can be freed in the disc state machine, note if this node
 	 * is being used during discovery.
 	 */
-	spin_lock_irq(&ndlp->lock);
-	disc = (ndlp->nlp_flag & NLP_NPR_2B_DISC);
-	ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-	spin_unlock_irq(&ndlp->lock);
+	disc = test_and_clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 
 	/* PLOGI completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
@@ -2060,9 +2053,7 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 	/* Check to see if link went down during discovery */
 	if (lpfc_els_chk_latt(vport)) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 		goto out;
 	}
 
@@ -2070,11 +2061,8 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		/* Check for retry */
 		if (lpfc_els_retry(phba, cmdiocb, rspiocb)) {
 			/* ELS command is being retried */
-			if (disc) {
-				spin_lock_irq(&ndlp->lock);
-				ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-				spin_unlock_irq(&ndlp->lock);
-			}
+			if (disc)
+				set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 			goto out;
 		}
 		/* Warn PLOGI status Don't print the vport to vport rjts */
@@ -2097,7 +2085,8 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		 * with the reglogin process.
 		 */
 		spin_lock_irq(&ndlp->lock);
-		if ((ndlp->nlp_flag & (NLP_ACC_REGLOGIN | NLP_RCV_PLOGI)) &&
+		if ((test_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag) ||
+		     test_bit(NLP_RCV_PLOGI, &ndlp->nlp_flag)) &&
 		    ndlp->nlp_state == NLP_STE_REG_LOGIN_ISSUE) {
 			spin_unlock_irq(&ndlp->lock);
 			goto out;
@@ -2108,8 +2097,8 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		 * start the device remove process.
 		 */
 		if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD))) {
-			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-			if (!(ndlp->nlp_flag & NLP_IN_DEV_LOSS))
+			clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
+			if (!test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag))
 				release_node = true;
 		}
 		spin_unlock_irq(&ndlp->lock);
@@ -2212,12 +2201,13 @@ lpfc_issue_els_plogi(struct lpfc_vport *vport, uint32_t did, uint8_t retry)
 	 * outstanding UNREG_RPI mbox command completes, unless we
 	 * are going offline. This logic does not apply for Fabric DIDs
 	 */
-	if ((ndlp->nlp_flag & (NLP_IGNR_REG_CMPL | NLP_UNREG_INP)) &&
+	if ((test_bit(NLP_IGNR_REG_CMPL, &ndlp->nlp_flag) ||
+	     test_bit(NLP_UNREG_INP, &ndlp->nlp_flag)) &&
 	    ((ndlp->nlp_DID & Fabric_DID_MASK) != Fabric_DID_MASK) &&
 	    !test_bit(FC_OFFLINE_MODE, &vport->fc_flag)) {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 				 "4110 Issue PLOGI x%x deferred "
-				 "on NPort x%x rpi x%x flg x%x Data:"
+				 "on NPort x%x rpi x%x flg x%lx Data:"
 				 " x%px\n",
 				 ndlp->nlp_defer_did, ndlp->nlp_DID,
 				 ndlp->nlp_rpi, ndlp->nlp_flag, ndlp);
@@ -2335,10 +2325,10 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	ulp_status = get_job_ulpstatus(phba, rspiocb);
 	ulp_word4 = get_job_word4(phba, rspiocb);
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_PRLI_SND;
+	clear_bit(NLP_PRLI_SND, &ndlp->nlp_flag);
 
 	/* Driver supports multiple FC4 types.  Counters matter. */
+	spin_lock_irq(&ndlp->lock);
 	vport->fc_prli_sent--;
 	ndlp->fc4_prli_sent--;
 	spin_unlock_irq(&ndlp->lock);
@@ -2379,7 +2369,7 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		/* Warn PRLI status */
 		lpfc_printf_vlog(vport, mode, LOG_ELS,
 				 "2754 PRLI DID:%06X Status:x%x/x%x, "
-				 "data: x%x x%x x%x\n",
+				 "data: x%x x%x x%lx\n",
 				 ndlp->nlp_DID, ulp_status,
 				 ulp_word4, ndlp->nlp_state,
 				 ndlp->fc4_prli_sent, ndlp->nlp_flag);
@@ -2396,10 +2386,10 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		if ((ndlp->nlp_state >= NLP_STE_PLOGI_ISSUE &&
 		     ndlp->nlp_state <= NLP_STE_REG_LOGIN_ISSUE) ||
 		    (ndlp->nlp_state == NLP_STE_NPR_NODE &&
-		     ndlp->nlp_flag & NLP_DELAY_TMO)) {
-			lpfc_printf_vlog(vport, KERN_WARNING, LOG_NODE,
+		     test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag))) {
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE,
 					 "2784 PRLI cmpl: Allow Node recovery "
-					 "DID x%06x nstate x%x nflag x%x\n",
+					 "DID x%06x nstate x%x nflag x%lx\n",
 					 ndlp->nlp_DID, ndlp->nlp_state,
 					 ndlp->nlp_flag);
 			goto out;
@@ -2420,8 +2410,8 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		spin_lock_irq(&ndlp->lock);
 		if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD)) &&
 		    !ndlp->fc4_prli_sent) {
-			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-			if (!(ndlp->nlp_flag & NLP_IN_DEV_LOSS))
+			clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
+			if (!test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag))
 				release_node = true;
 		}
 		spin_unlock_irq(&ndlp->lock);
@@ -2496,7 +2486,8 @@ lpfc_issue_els_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	ndlp->nlp_type &= ~(NLP_FCP_TARGET | NLP_FCP_INITIATOR);
 	ndlp->nlp_type &= ~(NLP_NVME_TARGET | NLP_NVME_INITIATOR);
 	ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
-	ndlp->nlp_flag &= ~(NLP_FIRSTBURST | NLP_NPR_2B_DISC);
+	clear_bit(NLP_FIRSTBURST, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	ndlp->nvme_fb_size = 0;
 
  send_next_prli:
@@ -2627,8 +2618,8 @@ lpfc_issue_els_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	 * the ndlp is used to track outstanding PRLIs for different
 	 * FC4 types.
 	 */
+	set_bit(NLP_PRLI_SND, &ndlp->nlp_flag);
 	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_PRLI_SND;
 	vport->fc_prli_sent++;
 	ndlp->fc4_prli_sent++;
 	spin_unlock_irq(&ndlp->lock);
@@ -2789,7 +2780,7 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	struct lpfc_vport *vport = cmdiocb->vport;
 	IOCB_t *irsp;
 	struct lpfc_nodelist *ndlp;
-	int  disc;
+	bool  disc;
 	u32 ulp_status, ulp_word4, tmo, iotag;
 	bool release_node = false;
 
@@ -2818,10 +2809,8 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* Since ndlp can be freed in the disc state machine, note if this node
 	 * is being used during discovery.
 	 */
-	spin_lock_irq(&ndlp->lock);
-	disc = (ndlp->nlp_flag & NLP_NPR_2B_DISC);
-	ndlp->nlp_flag &= ~(NLP_ADISC_SND | NLP_NPR_2B_DISC);
-	spin_unlock_irq(&ndlp->lock);
+	disc = test_and_clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
+	clear_bit(NLP_ADISC_SND, &ndlp->nlp_flag);
 	/* ADISC completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0104 ADISC completes to NPort x%x "
@@ -2832,9 +2821,7 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 	/* Check to see if link went down during discovery */
 	if (lpfc_els_chk_latt(vport)) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 		goto out;
 	}
 
@@ -2843,9 +2830,7 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		if (lpfc_els_retry(phba, cmdiocb, rspiocb)) {
 			/* ELS command is being retried */
 			if (disc) {
-				spin_lock_irq(&ndlp->lock);
-				ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-				spin_unlock_irq(&ndlp->lock);
+				set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 				lpfc_set_disctmo(vport);
 			}
 			goto out;
@@ -2864,8 +2849,8 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		 */
 		spin_lock_irq(&ndlp->lock);
 		if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD))) {
-			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-			if (!(ndlp->nlp_flag & NLP_IN_DEV_LOSS))
+			clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
+			if (!test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag))
 				release_node = true;
 		}
 		spin_unlock_irq(&ndlp->lock);
@@ -2938,9 +2923,7 @@ lpfc_issue_els_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	phba->fc_stat.elsXmitADISC++;
 	elsiocb->cmd_cmpl = lpfc_cmpl_els_adisc;
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_ADISC_SND;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_ADISC_SND, &ndlp->nlp_flag);
 	elsiocb->ndlp = lpfc_nlp_get(ndlp);
 	if (!elsiocb->ndlp) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -2961,9 +2944,7 @@ lpfc_issue_els_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	return 0;
 
 err:
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_ADISC_SND;
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_ADISC_SND, &ndlp->nlp_flag);
 	return 1;
 }
 
@@ -2985,7 +2966,6 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	struct lpfc_nodelist *ndlp = cmdiocb->ndlp;
 	struct lpfc_vport *vport = ndlp->vport;
 	IOCB_t *irsp;
-	unsigned long flags;
 	uint32_t skip_recovery = 0;
 	int wake_up_waiter = 0;
 	u32 ulp_status;
@@ -3007,8 +2987,8 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		iotag = irsp->ulpIoTag;
 	}
 
+	clear_bit(NLP_LOGO_SND, &ndlp->nlp_flag);
 	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_LOGO_SND;
 	if (ndlp->save_flags & NLP_WAIT_FOR_LOGO) {
 		wake_up_waiter = 1;
 		ndlp->save_flags &= ~NLP_WAIT_FOR_LOGO;
@@ -3023,7 +3003,7 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* LOGO completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0105 LOGO completes to NPort x%x "
-			 "IoTag x%x refcnt %d nflags x%x xflags x%x "
+			 "IoTag x%x refcnt %d nflags x%lx xflags x%x "
 			 "Data: x%x x%x x%x x%x\n",
 			 ndlp->nlp_DID, iotag,
 			 kref_read(&ndlp->kref), ndlp->nlp_flag,
@@ -3061,10 +3041,8 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* The driver sets this flag for an NPIV instance that doesn't want to
 	 * log into the remote port.
 	 */
-	if (ndlp->nlp_flag & NLP_TARGET_REMOVE) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_TARGET_REMOVE, &ndlp->nlp_flag)) {
+		clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 		lpfc_disc_state_machine(vport, ndlp, cmdiocb,
 					NLP_EVT_DEVICE_RM);
 		goto out_rsrc_free;
@@ -3087,9 +3065,7 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	if (ndlp->nlp_type & (NLP_FCP_TARGET | NLP_NVME_TARGET) &&
 	    skip_recovery == 0) {
 		lpfc_cancel_retry_delay_tmo(vport, ndlp);
-		spin_lock_irqsave(&ndlp->lock, flags);
-		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-		spin_unlock_irqrestore(&ndlp->lock, flags);
+		set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 				 "3187 LOGO completes to NPort x%x: Start "
@@ -3111,9 +3087,7 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	 * register with the transport.
 	 */
 	if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD))) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-		spin_unlock_irq(&ndlp->lock);
+		clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 		lpfc_disc_state_machine(vport, ndlp, cmdiocb,
 					NLP_EVT_DEVICE_RM);
 	}
@@ -3154,12 +3128,8 @@ lpfc_issue_els_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	uint16_t cmdsize;
 	int rc;
 
-	spin_lock_irq(&ndlp->lock);
-	if (ndlp->nlp_flag & NLP_LOGO_SND) {
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_LOGO_SND, &ndlp->nlp_flag))
 		return 0;
-	}
-	spin_unlock_irq(&ndlp->lock);
 
 	cmdsize = (2 * sizeof(uint32_t)) + sizeof(struct lpfc_name);
 	elsiocb = lpfc_prep_els_iocb(vport, 1, cmdsize, retry, ndlp,
@@ -3178,10 +3148,8 @@ lpfc_issue_els_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	phba->fc_stat.elsXmitLOGO++;
 	elsiocb->cmd_cmpl = lpfc_cmpl_els_logo;
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_LOGO_SND;
-	ndlp->nlp_flag &= ~NLP_ISSUE_LOGO;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_LOGO_SND, &ndlp->nlp_flag);
+	clear_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag);
 	elsiocb->ndlp = lpfc_nlp_get(ndlp);
 	if (!elsiocb->ndlp) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -3206,9 +3174,7 @@ lpfc_issue_els_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	return 0;
 
 err:
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_LOGO_SND;
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_LOGO_SND, &ndlp->nlp_flag);
 	return 1;
 }
 
@@ -3284,13 +3250,13 @@ lpfc_cmpl_els_cmd(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 static int
 lpfc_reg_fab_ctrl_node(struct lpfc_vport *vport, struct lpfc_nodelist *fc_ndlp)
 {
-	int rc = 0;
+	int rc;
 	struct lpfc_hba *phba = vport->phba;
 	struct lpfc_nodelist *ns_ndlp;
 	LPFC_MBOXQ_t *mbox;
 
-	if (fc_ndlp->nlp_flag & NLP_RPI_REGISTERED)
-		return rc;
+	if (test_bit(NLP_RPI_REGISTERED, &fc_ndlp->nlp_flag))
+		return 0;
 
 	ns_ndlp = lpfc_findnode_did(vport, NameServer_DID);
 	if (!ns_ndlp)
@@ -3307,7 +3273,7 @@ lpfc_reg_fab_ctrl_node(struct lpfc_vport *vport, struct lpfc_nodelist *fc_ndlp)
 	if (!mbox) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE,
 				 "0936 %s: no memory for reg_login "
-				 "Data: x%x x%x x%x x%x\n", __func__,
+				 "Data: x%x x%x x%lx x%x\n", __func__,
 				 fc_ndlp->nlp_DID, fc_ndlp->nlp_state,
 				 fc_ndlp->nlp_flag, fc_ndlp->nlp_rpi);
 		return -ENOMEM;
@@ -3319,7 +3285,7 @@ lpfc_reg_fab_ctrl_node(struct lpfc_vport *vport, struct lpfc_nodelist *fc_ndlp)
 		goto out;
 	}
 
-	fc_ndlp->nlp_flag |= NLP_REG_LOGIN_SEND;
+	set_bit(NLP_REG_LOGIN_SEND, &fc_ndlp->nlp_flag);
 	mbox->mbox_cmpl = lpfc_mbx_cmpl_fc_reg_login;
 	mbox->ctx_ndlp = lpfc_nlp_get(fc_ndlp);
 	if (!mbox->ctx_ndlp) {
@@ -3343,7 +3309,7 @@ lpfc_reg_fab_ctrl_node(struct lpfc_vport *vport, struct lpfc_nodelist *fc_ndlp)
 	lpfc_mbox_rsrc_cleanup(phba, mbox, MBOX_THD_UNLOCKED);
 	lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE,
 			 "0938 %s: failed to format reg_login "
-			 "Data: x%x x%x x%x x%x\n", __func__,
+			 "Data: x%x x%x x%lx x%x\n", __func__,
 			 fc_ndlp->nlp_DID, fc_ndlp->nlp_state,
 			 fc_ndlp->nlp_flag, fc_ndlp->nlp_rpi);
 	return rc;
@@ -4382,11 +4348,8 @@ lpfc_cancel_retry_delay_tmo(struct lpfc_vport *vport, struct lpfc_nodelist *nlp)
 {
 	struct lpfc_work_evt *evtp;
 
-	if (!(nlp->nlp_flag & NLP_DELAY_TMO))
+	if (!test_and_clear_bit(NLP_DELAY_TMO, &nlp->nlp_flag))
 		return;
-	spin_lock_irq(&nlp->lock);
-	nlp->nlp_flag &= ~NLP_DELAY_TMO;
-	spin_unlock_irq(&nlp->lock);
 	del_timer_sync(&nlp->nlp_delayfunc);
 	nlp->nlp_last_elscmd = 0;
 	if (!list_empty(&nlp->els_retry_evt.evt_listp)) {
@@ -4395,10 +4358,7 @@ lpfc_cancel_retry_delay_tmo(struct lpfc_vport *vport, struct lpfc_nodelist *nlp)
 		evtp = &nlp->els_retry_evt;
 		lpfc_nlp_put((struct lpfc_nodelist *)evtp->evt_arg1);
 	}
-	if (nlp->nlp_flag & NLP_NPR_2B_DISC) {
-		spin_lock_irq(&nlp->lock);
-		nlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-		spin_unlock_irq(&nlp->lock);
+	if (test_and_clear_bit(NLP_NPR_2B_DISC, &nlp->nlp_flag)) {
 		if (vport->num_disc_nodes) {
 			if (vport->port_state < LPFC_VPORT_READY) {
 				/* Check if there are more ADISCs to be sent */
@@ -4478,14 +4438,11 @@ lpfc_els_retry_delay_handler(struct lpfc_nodelist *ndlp)
 	spin_lock_irq(&ndlp->lock);
 	cmd = ndlp->nlp_last_elscmd;
 	ndlp->nlp_last_elscmd = 0;
+	spin_unlock_irq(&ndlp->lock);
 
-	if (!(ndlp->nlp_flag & NLP_DELAY_TMO)) {
-		spin_unlock_irq(&ndlp->lock);
+	if (!test_and_clear_bit(NLP_DELAY_TMO, &ndlp->nlp_flag))
 		return;
-	}
 
-	ndlp->nlp_flag &= ~NLP_DELAY_TMO;
-	spin_unlock_irq(&ndlp->lock);
 	/*
 	 * If a discovery event readded nlp_delayfunc after timer
 	 * firing and before processing the timer, cancel the
@@ -5008,9 +4965,7 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			/* delay is specified in milliseconds */
 			mod_timer(&ndlp->nlp_delayfunc,
 				jiffies + msecs_to_jiffies(delay));
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= NLP_DELAY_TMO;
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 
 			ndlp->nlp_prev_state = ndlp->nlp_state;
 			if ((cmd == ELS_CMD_PRLI) ||
@@ -5070,7 +5025,7 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 				 "0108 No retry ELS command x%x to remote "
 				 "NPORT x%x Retried:%d Error:x%x/%x "
-				 "IoTag x%x nflags x%x\n",
+				 "IoTag x%x nflags x%lx\n",
 				 cmd, did, cmdiocb->retry, ulp_status,
 				 ulp_word4, cmdiocb->iotag,
 				 (ndlp ? ndlp->nlp_flag : 0));
@@ -5237,7 +5192,7 @@ lpfc_cmpl_els_logo_acc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* ACC to LOGO completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0109 ACC to LOGO completes to NPort x%x refcnt %d "
-			 "last els x%x Data: x%x x%x x%x\n",
+			 "last els x%x Data: x%lx x%x x%x\n",
 			 ndlp->nlp_DID, kref_read(&ndlp->kref),
 			 ndlp->nlp_last_elscmd, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi);
@@ -5252,16 +5207,14 @@ lpfc_cmpl_els_logo_acc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		goto out;
 
 	if (ndlp->nlp_state == NLP_STE_NPR_NODE) {
-		if (ndlp->nlp_flag & NLP_RPI_REGISTERED)
+		if (test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag))
 			lpfc_unreg_rpi(vport, ndlp);
 
 		/* If came from PRLO, then PRLO_ACC is done.
 		 * Start rediscovery now.
 		 */
 		if (ndlp->nlp_last_elscmd == ELS_CMD_PRLO) {
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 			ndlp->nlp_prev_state = ndlp->nlp_state;
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_PLOGI_ISSUE);
 			lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
@@ -5298,7 +5251,7 @@ lpfc_mbx_cmpl_dflt_rpi(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 
 	if (ndlp) {
 		lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE,
-				 "0006 rpi x%x DID:%x flg:%x %d x%px "
+				 "0006 rpi x%x DID:%x flg:%lx %d x%px "
 				 "mbx_cmd x%x mbx_flag x%x x%px\n",
 				 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
 				 kref_read(&ndlp->kref), ndlp, mbx_cmd,
@@ -5309,11 +5262,9 @@ lpfc_mbx_cmpl_dflt_rpi(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		 * first on an UNREG_LOGIN and then release the final
 		 * references.
 		 */
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+		clear_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 		if (mbx_cmd == MBX_UNREG_LOGIN)
-			ndlp->nlp_flag &= ~NLP_UNREG_INP;
-		spin_unlock_irq(&ndlp->lock);
+			clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 		lpfc_nlp_put(ndlp);
 		lpfc_drop_node(ndlp->vport, ndlp);
 	}
@@ -5379,23 +5330,23 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* ELS response tag <ulpIoTag> completes */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0110 ELS response tag x%x completes "
-			 "Data: x%x x%x x%x x%x x%x x%x x%x x%x %p %p\n",
+			 "Data: x%x x%x x%x x%x x%lx x%x x%x x%x %p %p\n",
 			 iotag, ulp_status, ulp_word4, tmo,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi, kref_read(&ndlp->kref), mbox, ndlp);
 	if (mbox) {
-		if (ulp_status == 0
-		    && (ndlp->nlp_flag & NLP_ACC_REGLOGIN)) {
+		if (ulp_status == 0 &&
+		    test_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag)) {
 			if (!lpfc_unreg_rpi(vport, ndlp) &&
 			    !test_bit(FC_PT2PT, &vport->fc_flag)) {
-				if (ndlp->nlp_state ==  NLP_STE_PLOGI_ISSUE ||
+				if (ndlp->nlp_state == NLP_STE_PLOGI_ISSUE ||
 				    ndlp->nlp_state ==
 				     NLP_STE_REG_LOGIN_ISSUE) {
 					lpfc_printf_vlog(vport, KERN_INFO,
 							 LOG_DISCOVERY,
 							 "0314 PLOGI recov "
 							 "DID x%x "
-							 "Data: x%x x%x x%x\n",
+							 "Data: x%x x%x x%lx\n",
 							 ndlp->nlp_DID,
 							 ndlp->nlp_state,
 							 ndlp->nlp_rpi,
@@ -5412,18 +5363,17 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 				goto out_free_mbox;
 
 			mbox->vport = vport;
-			if (ndlp->nlp_flag & NLP_RM_DFLT_RPI) {
+			if (test_bit(NLP_RM_DFLT_RPI, &ndlp->nlp_flag)) {
 				mbox->mbox_flag |= LPFC_MBX_IMED_UNREG;
 				mbox->mbox_cmpl = lpfc_mbx_cmpl_dflt_rpi;
-			}
-			else {
+			} else {
 				mbox->mbox_cmpl = lpfc_mbx_cmpl_reg_login;
 				ndlp->nlp_prev_state = ndlp->nlp_state;
 				lpfc_nlp_set_state(vport, ndlp,
 					   NLP_STE_REG_LOGIN_ISSUE);
 			}
 
-			ndlp->nlp_flag |= NLP_REG_LOGIN_SEND;
+			set_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 			if (lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT)
 			    != MBX_NOT_FINISHED)
 				goto out;
@@ -5432,12 +5382,12 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			 * set for this failed mailbox command.
 			 */
 			lpfc_nlp_put(ndlp);
-			ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+			clear_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 
 			/* ELS rsp: Cannot issue reg_login for <NPortid> */
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				"0138 ELS rsp: Cannot issue reg_login for x%x "
-				"Data: x%x x%x x%x\n",
+				"Data: x%lx x%x x%x\n",
 				ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 				ndlp->nlp_rpi);
 		}
@@ -5446,11 +5396,9 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	}
 out:
 	if (ndlp && shost) {
-		spin_lock_irq(&ndlp->lock);
 		if (mbox)
-			ndlp->nlp_flag &= ~NLP_ACC_REGLOGIN;
-		ndlp->nlp_flag &= ~NLP_RM_DFLT_RPI;
-		spin_unlock_irq(&ndlp->lock);
+			clear_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag);
+		clear_bit(NLP_RM_DFLT_RPI, &ndlp->nlp_flag);
 	}
 
 	/* An SLI4 NPIV instance wants to drop the node at this point under
@@ -5528,9 +5476,7 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 		elsiocb = lpfc_prep_els_iocb(vport, 0, cmdsize, oldiocb->retry,
 					     ndlp, ndlp->nlp_DID, ELS_CMD_ACC);
 		if (!elsiocb) {
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_LOGO_ACC;
-			spin_unlock_irq(&ndlp->lock);
+			clear_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 			return 1;
 		}
 
@@ -5558,7 +5504,7 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 		pcmd += sizeof(uint32_t);
 
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-			"Issue ACC:       did:x%x flg:x%x",
+			"Issue ACC:       did:x%x flg:x%lx",
 			ndlp->nlp_DID, ndlp->nlp_flag, 0);
 		break;
 	case ELS_CMD_FLOGI:
@@ -5637,7 +5583,7 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 		}
 
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-			"Issue ACC FLOGI/PLOGI: did:x%x flg:x%x",
+			"Issue ACC FLOGI/PLOGI: did:x%x flg:x%lx",
 			ndlp->nlp_DID, ndlp->nlp_flag, 0);
 		break;
 	case ELS_CMD_PRLO:
@@ -5675,7 +5621,7 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 		els_pkt_ptr->un.prlo.acceptRspCode = PRLO_REQ_EXECUTED;
 
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-			"Issue ACC PRLO:  did:x%x flg:x%x",
+			"Issue ACC PRLO:  did:x%x flg:x%lx",
 			ndlp->nlp_DID, ndlp->nlp_flag, 0);
 		break;
 	case ELS_CMD_RDF:
@@ -5720,12 +5666,10 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 	default:
 		return 1;
 	}
-	if (ndlp->nlp_flag & NLP_LOGO_ACC) {
-		spin_lock_irq(&ndlp->lock);
-		if (!(ndlp->nlp_flag & NLP_RPI_REGISTERED ||
-			ndlp->nlp_flag & NLP_REG_LOGIN_SEND))
-			ndlp->nlp_flag &= ~NLP_LOGO_ACC;
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_LOGO_ACC, &ndlp->nlp_flag)) {
+		if (!test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag) &&
+		    !test_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag))
+			clear_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 		elsiocb->cmd_cmpl = lpfc_cmpl_els_logo_acc;
 	} else {
 		elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
@@ -5748,7 +5692,7 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 	/* Xmit ELS ACC response tag <ulpIoTag> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0128 Xmit ELS ACC response Status: x%x, IoTag: x%x, "
-			 "XRI: x%x, DID: x%x, nlp_flag: x%x nlp_state: x%x "
+			 "XRI: x%x, DID: x%x, nlp_flag: x%lx nlp_state: x%x "
 			 "RPI: x%x, fc_flag x%lx refcnt %d\n",
 			 rc, elsiocb->iotag, elsiocb->sli4_xritag,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
@@ -5823,13 +5767,13 @@ lpfc_els_rsp_reject(struct lpfc_vport *vport, uint32_t rejectError,
 	/* Xmit ELS RJT <err> response tag <ulpIoTag> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0129 Xmit ELS RJT x%x response tag x%x "
-			 "xri x%x, did x%x, nlp_flag x%x, nlp_state x%x, "
+			 "xri x%x, did x%x, nlp_flag x%lx, nlp_state x%x, "
 			 "rpi x%x\n",
 			 rejectError, elsiocb->iotag,
 			 get_job_ulpcontext(phba, elsiocb), ndlp->nlp_DID,
 			 ndlp->nlp_flag, ndlp->nlp_state, ndlp->nlp_rpi);
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-		"Issue LS_RJT:    did:x%x flg:x%x err:x%x",
+		"Issue LS_RJT:    did:x%x flg:x%lx err:x%x",
 		ndlp->nlp_DID, ndlp->nlp_flag, rejectError);
 
 	phba->fc_stat.elsXmitLSRJT++;
@@ -5920,7 +5864,7 @@ lpfc_issue_els_edc_rsp(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 		lpfc_format_edc_lft_desc(phba, tlv);
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-			      "Issue EDC ACC:      did:x%x flg:x%x refcnt %d",
+			      "Issue EDC ACC:      did:x%x flg:x%lx refcnt %d",
 			      ndlp->nlp_DID, ndlp->nlp_flag,
 			      kref_read(&ndlp->kref));
 	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
@@ -5942,7 +5886,7 @@ lpfc_issue_els_edc_rsp(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 	/* Xmit ELS ACC response tag <ulpIoTag> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0152 Xmit EDC ACC response Status: x%x, IoTag: x%x, "
-			 "XRI: x%x, DID: x%x, nlp_flag: x%x nlp_state: x%x "
+			 "XRI: x%x, DID: x%x, nlp_flag: x%lx nlp_state: x%x "
 			 "RPI: x%x, fc_flag x%lx\n",
 			 rc, elsiocb->iotag, elsiocb->sli4_xritag,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
@@ -6011,7 +5955,7 @@ lpfc_els_rsp_adisc_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 	/* Xmit ADISC ACC response tag <ulpIoTag> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0130 Xmit ADISC ACC response iotag x%x xri: "
-			 "x%x, did x%x, nlp_flag x%x, nlp_state x%x rpi x%x\n",
+			 "x%x, did x%x, nlp_flag x%lx, nlp_state x%x rpi x%x\n",
 			 elsiocb->iotag, ulp_context,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi);
@@ -6027,7 +5971,7 @@ lpfc_els_rsp_adisc_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 	ap->DID = be32_to_cpu(vport->fc_myDID);
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-		      "Issue ACC ADISC: did:x%x flg:x%x refcnt %d",
+		      "Issue ACC ADISC: did:x%x flg:x%lx refcnt %d",
 		      ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref));
 
 	phba->fc_stat.elsXmitACC++;
@@ -6133,7 +6077,7 @@ lpfc_els_rsp_prli_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 	/* Xmit PRLI ACC response tag <ulpIoTag> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0131 Xmit PRLI ACC response tag x%x xri x%x, "
-			 "did x%x, nlp_flag x%x, nlp_state x%x, rpi x%x\n",
+			 "did x%x, nlp_flag x%lx, nlp_state x%x, rpi x%x\n",
 			 elsiocb->iotag, ulp_context,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi);
@@ -6204,7 +6148,7 @@ lpfc_els_rsp_prli_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
 				 "6015 NVME issue PRLI ACC word1 x%08x "
-				 "word4 x%08x word5 x%08x flag x%x, "
+				 "word4 x%08x word5 x%08x flag x%lx, "
 				 "fcp_info x%x nlp_type x%x\n",
 				 npr_nvme->word1, npr_nvme->word4,
 				 npr_nvme->word5, ndlp->nlp_flag,
@@ -6219,7 +6163,7 @@ lpfc_els_rsp_prli_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 				 ndlp->nlp_DID);
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-		      "Issue ACC PRLI:  did:x%x flg:x%x",
+		      "Issue ACC PRLI:  did:x%x flg:x%lx",
 		      ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref));
 
 	phba->fc_stat.elsXmitACC++;
@@ -6333,7 +6277,7 @@ lpfc_els_rsp_rnid_acc(struct lpfc_vport *vport, uint8_t format,
 	}
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-		      "Issue ACC RNID:  did:x%x flg:x%x refcnt %d",
+		      "Issue ACC RNID:  did:x%x flg:x%lx refcnt %d",
 		      ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref));
 
 	phba->fc_stat.elsXmitACC++;
@@ -6390,7 +6334,7 @@ lpfc_els_clear_rrq(struct lpfc_vport *vport,
 			get_job_ulpcontext(phba, iocb));
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-		"Clear RRQ:  did:x%x flg:x%x exchg:x%.08x",
+		"Clear RRQ:  did:x%x flg:x%lx exchg:x%.08x",
 		ndlp->nlp_DID, ndlp->nlp_flag, rrq->rrq_exchg);
 	if (vport->fc_myDID == be32_to_cpu(bf_get(rrq_did, rrq)))
 		xri = bf_get(rrq_oxid, rrq);
@@ -6467,7 +6411,7 @@ lpfc_els_rsp_echo_acc(struct lpfc_vport *vport, uint8_t *data,
 	memcpy(pcmd, data, cmdsize - sizeof(uint32_t));
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-		      "Issue ACC ECHO:  did:x%x flg:x%x refcnt %d",
+		      "Issue ACC ECHO:  did:x%x flg:x%lx refcnt %d",
 		      ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref));
 
 	phba->fc_stat.elsXmitACC++;
@@ -6517,14 +6461,12 @@ lpfc_els_disc_adisc(struct lpfc_vport *vport)
 	list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, nlp_listp) {
 
 		if (ndlp->nlp_state != NLP_STE_NPR_NODE ||
-		    !(ndlp->nlp_flag & NLP_NPR_ADISC))
+		    !test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag))
 			continue;
 
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-		spin_unlock_irq(&ndlp->lock);
+		clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 
-		if (!(ndlp->nlp_flag & NLP_NPR_2B_DISC)) {
+		if (!test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
 			/* This node was marked for ADISC but was not picked
 			 * for discovery. This is possible if the node was
 			 * missing in gidft response.
@@ -6582,9 +6524,9 @@ lpfc_els_disc_plogi(struct lpfc_vport *vport)
 	/* go thru NPR nodes and issue any remaining ELS PLOGIs */
 	list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, nlp_listp) {
 		if (ndlp->nlp_state == NLP_STE_NPR_NODE &&
-				(ndlp->nlp_flag & NLP_NPR_2B_DISC) != 0 &&
-				(ndlp->nlp_flag & NLP_DELAY_TMO) == 0 &&
-				(ndlp->nlp_flag & NLP_NPR_ADISC) == 0) {
+		    test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag) &&
+		    !test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag) &&
+		    !test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag)) {
 			ndlp->nlp_prev_state = ndlp->nlp_state;
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_PLOGI_ISSUE);
 			lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
@@ -7080,7 +7022,7 @@ lpfc_els_rdp_cmpl(struct lpfc_hba *phba, struct lpfc_rdp_context *rdp_context,
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			"2171 Xmit RDP response tag x%x xri x%x, "
-			"did x%x, nlp_flag x%x, nlp_state x%x, rpi x%x",
+			"did x%x, nlp_flag x%lx, nlp_state x%x, rpi x%x",
 			elsiocb->iotag, ulp_context,
 			ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			ndlp->nlp_rpi);
@@ -8054,7 +7996,7 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 	 */
 	if (vport->port_state <= LPFC_NS_QRY) {
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV RSCN ignore: did:x%x/ste:x%x flg:x%x",
+			"RCV RSCN ignore: did:x%x/ste:x%x flg:x%lx",
 			ndlp->nlp_DID, vport->port_state, ndlp->nlp_flag);
 
 		lpfc_els_rsp_acc(vport, ELS_CMD_ACC, cmdiocb, ndlp, NULL);
@@ -8084,7 +8026,7 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 					 vport->fc_flag, payload_len,
 					 *lp, vport->fc_rscn_id_cnt);
 			lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-				"RCV RSCN vport:  did:x%x/ste:x%x flg:x%x",
+				"RCV RSCN vport:  did:x%x/ste:x%x flg:x%lx",
 				ndlp->nlp_DID, vport->port_state,
 				ndlp->nlp_flag);
 
@@ -8121,7 +8063,7 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 	if (test_bit(FC_RSCN_MODE, &vport->fc_flag) ||
 	    test_bit(FC_NDISC_ACTIVE, &vport->fc_flag)) {
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV RSCN defer:  did:x%x/ste:x%x flg:x%x",
+			"RCV RSCN defer:  did:x%x/ste:x%x flg:x%lx",
 			ndlp->nlp_DID, vport->port_state, ndlp->nlp_flag);
 
 		set_bit(FC_RSCN_DEFERRED, &vport->fc_flag);
@@ -8177,7 +8119,7 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 		return 0;
 	}
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-		"RCV RSCN:        did:x%x/ste:x%x flg:x%x",
+		"RCV RSCN:        did:x%x/ste:x%x flg:x%lx",
 		ndlp->nlp_DID, vport->port_state, ndlp->nlp_flag);
 
 	set_bit(FC_RSCN_MODE, &vport->fc_flag);
@@ -8683,7 +8625,7 @@ lpfc_els_rsp_rls_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	/* Xmit ELS RLS ACC response tag <ulpIoTag> */
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_ELS,
 			 "2874 Xmit ELS RLS ACC response tag x%x xri x%x, "
-			 "did x%x, nlp_flag x%x, nlp_state x%x, rpi x%x\n",
+			 "did x%x, nlp_flag x%lx, nlp_state x%x, rpi x%x\n",
 			 elsiocb->iotag, ulp_context,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi);
@@ -8845,7 +8787,7 @@ lpfc_els_rcv_rtv(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 	/* Xmit ELS RLS ACC response tag <ulpIoTag> */
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_ELS,
 			 "2875 Xmit ELS RTV ACC response tag x%x xri x%x, "
-			 "did x%x, nlp_flag x%x, nlp_state x%x, rpi x%x, "
+			 "did x%x, nlp_flag x%lx, nlp_state x%x, rpi x%x, "
 			 "Data: x%x x%x x%x\n",
 			 elsiocb->iotag, ulp_context,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
@@ -9042,7 +8984,7 @@ lpfc_els_rsp_rpl_acc(struct lpfc_vport *vport, uint16_t cmdsize,
 	/* Xmit ELS RPL ACC response tag <ulpIoTag> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0120 Xmit ELS RPL ACC response tag x%x "
-			 "xri x%x, did x%x, nlp_flag x%x, nlp_state x%x, "
+			 "xri x%x, did x%x, nlp_flag x%lx, nlp_state x%x, "
 			 "rpi x%x\n",
 			 elsiocb->iotag, ulp_context,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
@@ -10397,14 +10339,11 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	 * Do not process any unsolicited ELS commands
 	 * if the ndlp is in DEV_LOSS
 	 */
-	spin_lock_irq(&ndlp->lock);
-	if (ndlp->nlp_flag & NLP_IN_DEV_LOSS) {
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag)) {
 		if (newnode)
 			lpfc_nlp_put(ndlp);
 		goto dropit;
 	}
-	spin_unlock_irq(&ndlp->lock);
 
 	elsiocb->ndlp = lpfc_nlp_get(ndlp);
 	if (!elsiocb->ndlp)
@@ -10433,7 +10372,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	switch (cmd) {
 	case ELS_CMD_PLOGI:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV PLOGI:       did:x%x/ste:x%x flg:x%x",
+			"RCV PLOGI:       did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvPLOGI++;
@@ -10472,9 +10411,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			}
 		}
 
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_TARGET_REMOVE;
-		spin_unlock_irq(&ndlp->lock);
+		clear_bit(NLP_TARGET_REMOVE, &ndlp->nlp_flag);
 
 		lpfc_disc_state_machine(vport, ndlp, elsiocb,
 					NLP_EVT_RCV_PLOGI);
@@ -10482,7 +10419,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_FLOGI:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV FLOGI:       did:x%x/ste:x%x flg:x%x",
+			"RCV FLOGI:       did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvFLOGI++;
@@ -10509,7 +10446,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_LOGO:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV LOGO:        did:x%x/ste:x%x flg:x%x",
+			"RCV LOGO:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvLOGO++;
@@ -10526,7 +10463,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_PRLO:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV PRLO:        did:x%x/ste:x%x flg:x%x",
+			"RCV PRLO:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvPRLO++;
@@ -10555,7 +10492,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_ADISC:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV ADISC:       did:x%x/ste:x%x flg:x%x",
+			"RCV ADISC:       did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		lpfc_send_els_event(vport, ndlp, payload);
@@ -10570,7 +10507,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_PDISC:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV PDISC:       did:x%x/ste:x%x flg:x%x",
+			"RCV PDISC:       did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvPDISC++;
@@ -10584,7 +10521,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_FARPR:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV FARPR:       did:x%x/ste:x%x flg:x%x",
+			"RCV FARPR:       did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvFARPR++;
@@ -10592,7 +10529,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_FARP:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV FARP:        did:x%x/ste:x%x flg:x%x",
+			"RCV FARP:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvFARP++;
@@ -10600,7 +10537,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_FAN:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV FAN:         did:x%x/ste:x%x flg:x%x",
+			"RCV FAN:         did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvFAN++;
@@ -10609,7 +10546,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	case ELS_CMD_PRLI:
 	case ELS_CMD_NVMEPRLI:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV PRLI:        did:x%x/ste:x%x flg:x%x",
+			"RCV PRLI:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvPRLI++;
@@ -10623,7 +10560,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_LIRR:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV LIRR:        did:x%x/ste:x%x flg:x%x",
+			"RCV LIRR:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvLIRR++;
@@ -10634,7 +10571,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_RLS:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV RLS:         did:x%x/ste:x%x flg:x%x",
+			"RCV RLS:         did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvRLS++;
@@ -10645,7 +10582,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_RPL:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV RPL:         did:x%x/ste:x%x flg:x%x",
+			"RCV RPL:         did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvRPL++;
@@ -10656,7 +10593,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_RNID:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV RNID:        did:x%x/ste:x%x flg:x%x",
+			"RCV RNID:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvRNID++;
@@ -10667,7 +10604,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_RTV:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV RTV:        did:x%x/ste:x%x flg:x%x",
+			"RCV RTV:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 		phba->fc_stat.elsRcvRTV++;
 		lpfc_els_rcv_rtv(vport, elsiocb, ndlp);
@@ -10677,7 +10614,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_RRQ:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV RRQ:         did:x%x/ste:x%x flg:x%x",
+			"RCV RRQ:         did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvRRQ++;
@@ -10688,7 +10625,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_ECHO:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV ECHO:        did:x%x/ste:x%x flg:x%x",
+			"RCV ECHO:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvECHO++;
@@ -10704,7 +10641,8 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_FPIN:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-				      "RCV FPIN:       did:x%x/ste:x%x flg:x%x",
+				      "RCV FPIN:       did:x%x/ste:x%x "
+				      "flg:x%lx",
 				      did, vport->port_state, ndlp->nlp_flag);
 
 		lpfc_els_rcv_fpin(vport, (struct fc_els_fpin *)payload,
@@ -11212,9 +11150,7 @@ lpfc_retry_pport_discovery(struct lpfc_hba *phba)
 		return;
 
 	mod_timer(&ndlp->nlp_delayfunc, jiffies + msecs_to_jiffies(1000));
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_DELAY_TMO;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 	ndlp->nlp_last_elscmd = ELS_CMD_FLOGI;
 	phba->pport->port_state = LPFC_FLOGI;
 	return;
@@ -11345,11 +11281,9 @@ lpfc_cmpl_els_fdisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		list_for_each_entry_safe(np, next_np,
 			&vport->fc_nodes, nlp_listp) {
 			if ((np->nlp_state != NLP_STE_NPR_NODE) ||
-			    !(np->nlp_flag & NLP_NPR_ADISC))
+			    !test_bit(NLP_NPR_ADISC, &np->nlp_flag))
 				continue;
-			spin_lock_irq(&ndlp->lock);
-			np->nlp_flag &= ~NLP_NPR_ADISC;
-			spin_unlock_irq(&ndlp->lock);
+			clear_bit(NLP_NPR_ADISC, &np->nlp_flag);
 			lpfc_unreg_rpi(vport, np);
 		}
 		lpfc_cleanup_pending_mbox(vport);
@@ -11552,7 +11486,7 @@ lpfc_cmpl_els_npiv_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* NPIV LOGO completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "2928 NPIV LOGO completes to NPort x%x "
-			 "Data: x%x x%x x%x x%x x%x x%x x%x\n",
+			 "Data: x%x x%x x%x x%x x%x x%lx x%x\n",
 			 ndlp->nlp_DID, ulp_status, ulp_word4,
 			 tmo, vport->num_disc_nodes,
 			 kref_read(&ndlp->kref), ndlp->nlp_flag,
@@ -11568,8 +11502,9 @@ lpfc_cmpl_els_npiv_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		/* Wake up lpfc_vport_delete if waiting...*/
 		if (ndlp->logo_waitq)
 			wake_up(ndlp->logo_waitq);
+		clear_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag);
+		clear_bit(NLP_LOGO_SND, &ndlp->nlp_flag);
 		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~(NLP_ISSUE_LOGO | NLP_LOGO_SND);
 		ndlp->save_flags &= ~NLP_WAIT_FOR_LOGO;
 		spin_unlock_irq(&ndlp->lock);
 	}
@@ -11619,13 +11554,11 @@ lpfc_issue_els_npiv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	memcpy(pcmd, &vport->fc_portname, sizeof(struct lpfc_name));
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
-		"Issue LOGO npiv  did:x%x flg:x%x",
+		"Issue LOGO npiv  did:x%x flg:x%lx",
 		ndlp->nlp_DID, ndlp->nlp_flag, 0);
 
 	elsiocb->cmd_cmpl = lpfc_cmpl_els_npiv_logo;
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_LOGO_SND;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_LOGO_SND, &ndlp->nlp_flag);
 	elsiocb->ndlp = lpfc_nlp_get(ndlp);
 	if (!elsiocb->ndlp) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -11641,9 +11574,7 @@ lpfc_issue_els_npiv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	return 0;
 
 err:
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_LOGO_SND;
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_LOGO_SND, &ndlp->nlp_flag);
 	return 1;
 }
 
@@ -12124,7 +12055,7 @@ lpfc_sli_abts_recover_port(struct lpfc_vport *vport,
 	lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
 			"3094 Start rport recovery on shost id 0x%x "
 			"fc_id 0x%06x vpi 0x%x rpi 0x%x state 0x%x "
-			"flags 0x%x\n",
+			"flag 0x%lx\n",
 			shost->host_no, ndlp->nlp_DID,
 			vport->vpi, ndlp->nlp_rpi, ndlp->nlp_state,
 			ndlp->nlp_flag);
@@ -12134,8 +12065,8 @@ lpfc_sli_abts_recover_port(struct lpfc_vport *vport,
 	 */
 	spin_lock_irqsave(&ndlp->lock, flags);
 	ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
-	ndlp->nlp_flag |= NLP_ISSUE_LOGO;
 	spin_unlock_irqrestore(&ndlp->lock, flags);
+	set_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag);
 	lpfc_unreg_rpi(vport, ndlp);
 }
 
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index af1fdecf53411..4036a9838bb59 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -143,7 +143,7 @@ lpfc_terminate_rport_io(struct fc_rport *rport)
 	ndlp = rdata->pnode;
 	vport = ndlp->vport;
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_RPORT,
-			      "rport terminate: sid:x%x did:x%x flg:x%x",
+			      "rport terminate: sid:x%x did:x%x flg:x%lx",
 			      ndlp->nlp_sid, ndlp->nlp_DID, ndlp->nlp_flag);
 
 	if (ndlp->nlp_sid != NLP_NO_SID)
@@ -171,11 +171,11 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
 	phba  = vport->phba;
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_RPORT,
-		"rport devlosscb: sid:x%x did:x%x flg:x%x",
+		"rport devlosscb: sid:x%x did:x%x flg:x%lx",
 		ndlp->nlp_sid, ndlp->nlp_DID, ndlp->nlp_flag);
 
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE,
-			 "3181 dev_loss_callbk x%06x, rport x%px flg x%x "
+			 "3181 dev_loss_callbk x%06x, rport x%px flg x%lx "
 			 "load_flag x%lx refcnt %u state %d xpt x%x\n",
 			 ndlp->nlp_DID, ndlp->rport, ndlp->nlp_flag,
 			 vport->load_flag, kref_read(&ndlp->kref),
@@ -214,18 +214,13 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
 			spin_unlock_irqrestore(&ndlp->lock, iflags);
 		}
 
-		spin_lock_irqsave(&ndlp->lock, iflags);
-
 		/* Only 1 thread can drop the initial node reference.  If
 		 * another thread has set NLP_DROPPED, this thread is done.
 		 */
-		if (nvme_reg || (ndlp->nlp_flag & NLP_DROPPED)) {
-			spin_unlock_irqrestore(&ndlp->lock, iflags);
+		if (nvme_reg || test_bit(NLP_DROPPED, &ndlp->nlp_flag))
 			return;
-		}
 
-		ndlp->nlp_flag |= NLP_DROPPED;
-		spin_unlock_irqrestore(&ndlp->lock, iflags);
+		set_bit(NLP_DROPPED, &ndlp->nlp_flag);
 		lpfc_nlp_put(ndlp);
 		return;
 	}
@@ -253,14 +248,14 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
 		return;
 	}
 
-	spin_lock_irqsave(&ndlp->lock, iflags);
-	ndlp->nlp_flag |= NLP_IN_DEV_LOSS;
+	set_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag);
 
+	spin_lock_irqsave(&ndlp->lock, iflags);
 	/* If there is a PLOGI in progress, and we are in a
 	 * NLP_NPR_2B_DISC state, don't turn off the flag.
 	 */
 	if (ndlp->nlp_state != NLP_STE_PLOGI_ISSUE)
-		ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
+		clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 
 	/*
 	 * The backend does not expect any more calls associated with this
@@ -289,15 +284,13 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
 	} else {
 		lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE,
 				 "3188 worker thread is stopped %s x%06x, "
-				 " rport x%px flg x%x load_flag x%lx refcnt "
+				 " rport x%px flg x%lx load_flag x%lx refcnt "
 				 "%d\n", __func__, ndlp->nlp_DID,
 				 ndlp->rport, ndlp->nlp_flag,
 				 vport->load_flag, kref_read(&ndlp->kref));
 		if (!(ndlp->fc4_xpt_flags & NVME_XPT_REGD)) {
-			spin_lock_irqsave(&ndlp->lock, iflags);
 			/* Node is in dev loss.  No further transaction. */
-			ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS;
-			spin_unlock_irqrestore(&ndlp->lock, iflags);
+			clear_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag);
 			lpfc_disc_state_machine(vport, ndlp, NULL,
 						NLP_EVT_DEVICE_RM);
 		}
@@ -430,7 +423,7 @@ lpfc_check_nlp_post_devloss(struct lpfc_vport *vport,
 		lpfc_nlp_get(ndlp);
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY | LOG_NODE,
 				 "8438 Devloss timeout reversed on DID x%x "
-				 "refcnt %d ndlp %p flag x%x "
+				 "refcnt %d ndlp %p flag x%lx "
 				 "port_state = x%x\n",
 				 ndlp->nlp_DID, kref_read(&ndlp->kref), ndlp,
 				 ndlp->nlp_flag, vport->port_state);
@@ -473,7 +466,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 			      ndlp->nlp_DID, ndlp->nlp_type, ndlp->nlp_sid);
 
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE,
-			 "3182 %s x%06x, nflag x%x xflags x%x refcnt %d\n",
+			 "3182 %s x%06x, nflag x%lx xflags x%x refcnt %d\n",
 			 __func__, ndlp->nlp_DID, ndlp->nlp_flag,
 			 ndlp->fc4_xpt_flags, kref_read(&ndlp->kref));
 
@@ -487,9 +480,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 				 *(name+4), *(name+5), *(name+6), *(name+7),
 				 ndlp->nlp_DID);
 
-		spin_lock_irqsave(&ndlp->lock, iflags);
-		ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS;
-		spin_unlock_irqrestore(&ndlp->lock, iflags);
+		clear_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag);
 		return fcf_inuse;
 	}
 
@@ -517,7 +508,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 			}
 			break;
 		case Fabric_Cntl_DID:
-			if (ndlp->nlp_flag & NLP_REG_LOGIN_SEND)
+			if (test_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag))
 				recovering = true;
 			break;
 		case FDMI_DID:
@@ -545,15 +536,13 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 		 * the following lpfc_nlp_put is necessary after fabric node is
 		 * recovered.
 		 */
-		spin_lock_irqsave(&ndlp->lock, iflags);
-		ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS;
-		spin_unlock_irqrestore(&ndlp->lock, iflags);
+		clear_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag);
 		if (recovering) {
 			lpfc_printf_vlog(vport, KERN_INFO,
 					 LOG_DISCOVERY | LOG_NODE,
 					 "8436 Devloss timeout marked on "
 					 "DID x%x refcnt %d ndlp %p "
-					 "flag x%x port_state = x%x\n",
+					 "flag x%lx port_state = x%x\n",
 					 ndlp->nlp_DID, kref_read(&ndlp->kref),
 					 ndlp, ndlp->nlp_flag,
 					 vport->port_state);
@@ -570,7 +559,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 					 LOG_DISCOVERY | LOG_NODE,
 					 "8437 Devloss timeout ignored on "
 					 "DID x%x refcnt %d ndlp %p "
-					 "flag x%x port_state = x%x\n",
+					 "flag x%lx port_state = x%x\n",
 					 ndlp->nlp_DID, kref_read(&ndlp->kref),
 					 ndlp, ndlp->nlp_flag,
 					 vport->port_state);
@@ -590,7 +579,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				 "0203 Devloss timeout on "
 				 "WWPN %02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x "
-				 "NPort x%06x Data: x%x x%x x%x refcnt %d\n",
+				 "NPort x%06x Data: x%lx x%x x%x refcnt %d\n",
 				 *name, *(name+1), *(name+2), *(name+3),
 				 *(name+4), *(name+5), *(name+6), *(name+7),
 				 ndlp->nlp_DID, ndlp->nlp_flag,
@@ -600,15 +589,13 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_TRACE_EVENT,
 				 "0204 Devloss timeout on "
 				 "WWPN %02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x "
-				 "NPort x%06x Data: x%x x%x x%x\n",
+				 "NPort x%06x Data: x%lx x%x x%x\n",
 				 *name, *(name+1), *(name+2), *(name+3),
 				 *(name+4), *(name+5), *(name+6), *(name+7),
 				 ndlp->nlp_DID, ndlp->nlp_flag,
 				 ndlp->nlp_state, ndlp->nlp_rpi);
 	}
-	spin_lock_irqsave(&ndlp->lock, iflags);
-	ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS;
-	spin_unlock_irqrestore(&ndlp->lock, iflags);
+	clear_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag);
 
 	/* If we are devloss, but we are in the process of rediscovering the
 	 * ndlp, don't issue a NLP_EVT_DEVICE_RM event.
@@ -1373,7 +1360,7 @@ lpfc_linkup_cleanup_nodes(struct lpfc_vport *vport)
 			if (ndlp->nlp_DID != Fabric_DID)
 				lpfc_unreg_rpi(vport, ndlp);
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-		} else if (!(ndlp->nlp_flag & NLP_NPR_ADISC)) {
+		} else if (!test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag)) {
 			/* Fail outstanding IO now since device is
 			 * marked for PLOGI.
 			 */
@@ -3882,14 +3869,13 @@ lpfc_mbx_cmpl_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	pmb->ctx_ndlp = NULL;
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI | LOG_NODE | LOG_DISCOVERY,
-			 "0002 rpi:%x DID:%x flg:%x %d x%px\n",
+			 "0002 rpi:%x DID:%x flg:%lx %d x%px\n",
 			 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
 			 kref_read(&ndlp->kref),
 			 ndlp);
-	if (ndlp->nlp_flag & NLP_REG_LOGIN_SEND)
-		ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+	clear_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 
-	if (ndlp->nlp_flag & NLP_IGNR_REG_CMPL ||
+	if (test_bit(NLP_IGNR_REG_CMPL, &ndlp->nlp_flag) ||
 	    ndlp->nlp_state != NLP_STE_REG_LOGIN_ISSUE) {
 		/* We rcvd a rscn after issuing this
 		 * mbox reg login, we may have cycled
@@ -3899,16 +3885,14 @@ lpfc_mbx_cmpl_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		 * there is another reg login in
 		 * process.
 		 */
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_IGNR_REG_CMPL;
-		spin_unlock_irq(&ndlp->lock);
+		clear_bit(NLP_IGNR_REG_CMPL, &ndlp->nlp_flag);
 
 		/*
 		 * We cannot leave the RPI registered because
 		 * if we go thru discovery again for this ndlp
 		 * a subsequent REG_RPI will fail.
 		 */
-		ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+		set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
 		lpfc_unreg_rpi(vport, ndlp);
 	}
 
@@ -4221,7 +4205,7 @@ lpfc_mbx_cmpl_fabric_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 
 	if (phba->sli_rev < LPFC_SLI_REV4)
 		ndlp->nlp_rpi = mb->un.varWords[0];
-	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+	set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
 
@@ -4352,9 +4336,7 @@ lpfc_mbx_cmpl_ns_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		 * reference.
 		 */
 		if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD))) {
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-			spin_unlock_irq(&ndlp->lock);
+			clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 			lpfc_nlp_put(ndlp);
 		}
 
@@ -4375,11 +4357,11 @@ lpfc_mbx_cmpl_ns_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 
 	if (phba->sli_rev < LPFC_SLI_REV4)
 		ndlp->nlp_rpi = mb->un.varWords[0];
-	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+	set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_DISCOVERY,
-			 "0003 rpi:%x DID:%x flg:%x %d x%px\n",
+			 "0003 rpi:%x DID:%x flg:%lx %d x%px\n",
 			 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
 			 kref_read(&ndlp->kref),
 			 ndlp);
@@ -4471,8 +4453,8 @@ lpfc_mbx_cmpl_fc_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 			 __func__, ndlp->nlp_DID, ndlp->nlp_rpi,
 			 ndlp->nlp_state);
 
-	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
-	ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+	set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
+	clear_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
 
@@ -4506,7 +4488,7 @@ lpfc_register_remote_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_RPORT,
-			      "rport add:       did:x%x flg:x%x type x%x",
+			      "rport add:       did:x%x flg:x%lx type x%x",
 			      ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_type);
 
 	/* Don't add the remote port if unloading. */
@@ -4574,7 +4556,7 @@ lpfc_unregister_remote_port(struct lpfc_nodelist *ndlp)
 		return;
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_RPORT,
-		"rport delete:    did:x%x flg:x%x type x%x",
+		"rport delete:    did:x%x flg:x%lx type x%x",
 		ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_type);
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
@@ -4690,7 +4672,7 @@ lpfc_nlp_unreg_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		lpfc_printf_vlog(vport, KERN_INFO,
 				 LOG_ELS | LOG_NODE | LOG_DISCOVERY,
 				 "0999 %s Not regd: ndlp x%px rport x%px DID "
-				 "x%x FLG x%x XPT x%x\n",
+				 "x%x FLG x%lx XPT x%x\n",
 				  __func__, ndlp, ndlp->rport, ndlp->nlp_DID,
 				  ndlp->nlp_flag, ndlp->fc4_xpt_flags);
 		return;
@@ -4706,7 +4688,7 @@ lpfc_nlp_unreg_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	} else if (!ndlp->rport) {
 		lpfc_printf_vlog(vport, KERN_INFO,
 				 LOG_ELS | LOG_NODE | LOG_DISCOVERY,
-				 "1999 %s NDLP in devloss x%px DID x%x FLG x%x"
+				 "1999 %s NDLP in devloss x%px DID x%x FLG x%lx"
 				 " XPT x%x refcnt %u\n",
 				 __func__, ndlp, ndlp->nlp_DID, ndlp->nlp_flag,
 				 ndlp->fc4_xpt_flags,
@@ -4751,7 +4733,7 @@ lpfc_handle_adisc_state(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		ndlp->nlp_type |= NLP_FC_NODE;
 		fallthrough;
 	case NLP_STE_MAPPED_NODE:
-		ndlp->nlp_flag &= ~NLP_NODEV_REMOVE;
+		clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 		lpfc_nlp_reg_node(vport, ndlp);
 		break;
 
@@ -4762,7 +4744,7 @@ lpfc_handle_adisc_state(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	 * backend, attempt it now
 	 */
 	case NLP_STE_NPR_NODE:
-		ndlp->nlp_flag &= ~NLP_RCV_PLOGI;
+		clear_bit(NLP_RCV_PLOGI, &ndlp->nlp_flag);
 		fallthrough;
 	default:
 		lpfc_nlp_unreg_node(vport, ndlp);
@@ -4783,13 +4765,13 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	}
 
 	if (new_state == NLP_STE_UNMAPPED_NODE) {
-		ndlp->nlp_flag &= ~NLP_NODEV_REMOVE;
+		clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 		ndlp->nlp_type |= NLP_FC_NODE;
 	}
 	if (new_state == NLP_STE_MAPPED_NODE)
-		ndlp->nlp_flag &= ~NLP_NODEV_REMOVE;
+		clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 	if (new_state == NLP_STE_NPR_NODE)
-		ndlp->nlp_flag &= ~NLP_RCV_PLOGI;
+		clear_bit(NLP_RCV_PLOGI, &ndlp->nlp_flag);
 
 	/* Reg/Unreg for FCP and NVME Transport interface */
 	if ((old_state == NLP_STE_MAPPED_NODE ||
@@ -4797,7 +4779,7 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		/* For nodes marked for ADISC, Handle unreg in ADISC cmpl
 		 * if linkup. In linkdown do unreg_node
 		 */
-		if (!(ndlp->nlp_flag & NLP_NPR_ADISC) ||
+		if (!test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag) ||
 		    !lpfc_is_link_up(vport->phba))
 			lpfc_nlp_unreg_node(vport, ndlp);
 	}
@@ -4817,9 +4799,7 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	    (!ndlp->rport ||
 	     ndlp->rport->scsi_target_id == -1 ||
 	     ndlp->rport->scsi_target_id >= LPFC_MAX_TARGET)) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_TGT_NO_SCSIID;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_TGT_NO_SCSIID, &ndlp->nlp_flag);
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
 	}
 }
@@ -4851,7 +4831,7 @@ lpfc_nlp_set_state(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		   int state)
 {
 	int  old_state = ndlp->nlp_state;
-	int node_dropped = ndlp->nlp_flag & NLP_DROPPED;
+	bool node_dropped = test_bit(NLP_DROPPED, &ndlp->nlp_flag);
 	char name1[16], name2[16];
 	unsigned long iflags;
 
@@ -4867,7 +4847,7 @@ lpfc_nlp_set_state(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	if (node_dropped && old_state == NLP_STE_UNUSED_NODE &&
 	    state != NLP_STE_UNUSED_NODE) {
-		ndlp->nlp_flag &= ~NLP_DROPPED;
+		clear_bit(NLP_DROPPED, &ndlp->nlp_flag);
 		lpfc_nlp_get(ndlp);
 	}
 
@@ -4875,7 +4855,7 @@ lpfc_nlp_set_state(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	    state != NLP_STE_NPR_NODE)
 		lpfc_cancel_retry_delay_tmo(vport, ndlp);
 	if (old_state == NLP_STE_UNMAPPED_NODE) {
-		ndlp->nlp_flag &= ~NLP_TGT_NO_SCSIID;
+		clear_bit(NLP_TGT_NO_SCSIID, &ndlp->nlp_flag);
 		ndlp->nlp_type &= ~NLP_FC_NODE;
 	}
 
@@ -4972,14 +4952,8 @@ lpfc_drop_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	 * reference from lpfc_nlp_init.  If set, don't drop it again and
 	 * introduce an imbalance.
 	 */
-	spin_lock_irq(&ndlp->lock);
-	if (!(ndlp->nlp_flag & NLP_DROPPED)) {
-		ndlp->nlp_flag |= NLP_DROPPED;
-		spin_unlock_irq(&ndlp->lock);
+	if (!test_and_set_bit(NLP_DROPPED, &ndlp->nlp_flag))
 		lpfc_nlp_put(ndlp);
-		return;
-	}
-	spin_unlock_irq(&ndlp->lock);
 }
 
 /*
@@ -5094,9 +5068,9 @@ lpfc_check_sli_ndlp(struct lpfc_hba *phba,
 	} else if (pring->ringno == LPFC_FCP_RING) {
 		/* Skip match check if waiting to relogin to FCP target */
 		if ((ndlp->nlp_type & NLP_FCP_TARGET) &&
-		    (ndlp->nlp_flag & NLP_DELAY_TMO)) {
+		    test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag))
 			return 0;
-		}
+
 		if (ulp_context == ndlp->nlp_rpi)
 			return 1;
 	}
@@ -5166,7 +5140,7 @@ lpfc_no_rpi(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 	 * Everything that matches on txcmplq will be returned
 	 * by firmware with a no rpi error.
 	 */
-	if (ndlp->nlp_flag & NLP_RPI_REGISTERED) {
+	if (test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag)) {
 		if (phba->sli_rev != LPFC_SLI_REV4)
 			lpfc_sli3_dequeue_nport_iocbs(phba, ndlp, &completions);
 		else
@@ -5200,21 +5174,19 @@ lpfc_nlp_logo_unreg(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	lpfc_issue_els_logo(vport, ndlp, 0);
 
 	/* Check to see if there are any deferred events to process */
-	if ((ndlp->nlp_flag & NLP_UNREG_INP) &&
-	    (ndlp->nlp_defer_did != NLP_EVT_NOTHING_PENDING)) {
+	if (test_bit(NLP_UNREG_INP, &ndlp->nlp_flag) &&
+	    ndlp->nlp_defer_did != NLP_EVT_NOTHING_PENDING) {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 				 "1434 UNREG cmpl deferred logo x%x "
 				 "on NPort x%x Data: x%x x%px\n",
 				 ndlp->nlp_rpi, ndlp->nlp_DID,
 				 ndlp->nlp_defer_did, ndlp);
 
-		ndlp->nlp_flag &= ~NLP_UNREG_INP;
+		clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 		ndlp->nlp_defer_did = NLP_EVT_NOTHING_PENDING;
 		lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
 	} else {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_UNREG_INP;
-		spin_unlock_irq(&ndlp->lock);
+		clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 	}
 
 	/* The node has an outstanding reference for the unreg. Now
@@ -5241,9 +5213,8 @@ lpfc_set_unreg_login_mbx_cmpl(struct lpfc_hba *phba, struct lpfc_vport *vport,
 	if (!mbox->ctx_ndlp)
 		return;
 
-	if (ndlp->nlp_flag & NLP_ISSUE_LOGO) {
+	if (test_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag)) {
 		mbox->mbox_cmpl = lpfc_nlp_logo_unreg;
-
 	} else if (phba->sli_rev == LPFC_SLI_REV4 &&
 		   !test_bit(FC_UNLOADING, &vport->load_flag) &&
 		    (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) >=
@@ -5272,13 +5243,13 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	int rc, acc_plogi = 1;
 	uint16_t rpi;
 
-	if (ndlp->nlp_flag & NLP_RPI_REGISTERED ||
-	    ndlp->nlp_flag & NLP_REG_LOGIN_SEND) {
-		if (ndlp->nlp_flag & NLP_REG_LOGIN_SEND)
+	if (test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag) ||
+	    test_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag)) {
+		if (test_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag))
 			lpfc_printf_vlog(vport, KERN_INFO,
 					 LOG_NODE | LOG_DISCOVERY,
 					 "3366 RPI x%x needs to be "
-					 "unregistered nlp_flag x%x "
+					 "unregistered nlp_flag x%lx "
 					 "did x%x\n",
 					 ndlp->nlp_rpi, ndlp->nlp_flag,
 					 ndlp->nlp_DID);
@@ -5286,11 +5257,11 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		/* If there is already an UNREG in progress for this ndlp,
 		 * no need to queue up another one.
 		 */
-		if (ndlp->nlp_flag & NLP_UNREG_INP) {
+		if (test_bit(NLP_UNREG_INP, &ndlp->nlp_flag)) {
 			lpfc_printf_vlog(vport, KERN_INFO,
 					 LOG_NODE | LOG_DISCOVERY,
 					 "1436 unreg_rpi SKIP UNREG x%x on "
-					 "NPort x%x deferred x%x  flg x%x "
+					 "NPort x%x deferred x%x flg x%lx "
 					 "Data: x%px\n",
 					 ndlp->nlp_rpi, ndlp->nlp_DID,
 					 ndlp->nlp_defer_did,
@@ -5318,19 +5289,19 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 				acc_plogi = 0;
 
 			if (!test_bit(FC_OFFLINE_MODE, &vport->fc_flag))
-				ndlp->nlp_flag |= NLP_UNREG_INP;
+				set_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 
 			lpfc_printf_vlog(vport, KERN_INFO,
 					 LOG_NODE | LOG_DISCOVERY,
 					 "1433 unreg_rpi UNREG x%x on "
-					 "NPort x%x deferred flg x%x "
+					 "NPort x%x deferred flg x%lx "
 					 "Data:x%px\n",
 					 ndlp->nlp_rpi, ndlp->nlp_DID,
 					 ndlp->nlp_flag, ndlp);
 
 			rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
 			if (rc == MBX_NOT_FINISHED) {
-				ndlp->nlp_flag &= ~NLP_UNREG_INP;
+				clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 				mempool_free(mbox, phba->mbox_mem_pool);
 				acc_plogi = 1;
 				lpfc_nlp_put(ndlp);
@@ -5340,7 +5311,7 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 					 LOG_NODE | LOG_DISCOVERY,
 					 "1444 Failed to allocate mempool "
 					 "unreg_rpi UNREG x%x, "
-					 "DID x%x, flag x%x, "
+					 "DID x%x, flag x%lx, "
 					 "ndlp x%px\n",
 					 ndlp->nlp_rpi, ndlp->nlp_DID,
 					 ndlp->nlp_flag, ndlp);
@@ -5350,7 +5321,7 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 			 * not unloading.
 			 */
 			if (!test_bit(FC_UNLOADING, &vport->load_flag)) {
-				ndlp->nlp_flag &= ~NLP_UNREG_INP;
+				clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 				lpfc_issue_els_logo(vport, ndlp, 0);
 				ndlp->nlp_prev_state = ndlp->nlp_state;
 				lpfc_nlp_set_state(vport, ndlp,
@@ -5363,13 +5334,13 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 out:
 		if (phba->sli_rev != LPFC_SLI_REV4)
 			ndlp->nlp_rpi = 0;
-		ndlp->nlp_flag &= ~NLP_RPI_REGISTERED;
-		ndlp->nlp_flag &= ~NLP_NPR_ADISC;
+		clear_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
+		clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 		if (acc_plogi)
-			ndlp->nlp_flag &= ~NLP_LOGO_ACC;
+			clear_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 		return 1;
 	}
-	ndlp->nlp_flag &= ~NLP_LOGO_ACC;
+	clear_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 	return 0;
 }
 
@@ -5397,7 +5368,7 @@ lpfc_unreg_hba_rpis(struct lpfc_hba *phba)
 	for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
 		spin_lock_irqsave(&vports[i]->fc_nodes_list_lock, iflags);
 		list_for_each_entry(ndlp, &vports[i]->fc_nodes, nlp_listp) {
-			if (ndlp->nlp_flag & NLP_RPI_REGISTERED) {
+			if (test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag)) {
 				/* The mempool_alloc might sleep */
 				spin_unlock_irqrestore(&vports[i]->fc_nodes_list_lock,
 						       iflags);
@@ -5485,7 +5456,7 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	/* Cleanup node for NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
 			 "0900 Cleanup node for NPort x%x "
-			 "Data: x%x x%x x%x\n",
+			 "Data: x%lx x%x x%x\n",
 			 ndlp->nlp_DID, ndlp->nlp_flag,
 			 ndlp->nlp_state, ndlp->nlp_rpi);
 	lpfc_dequeue_node(vport, ndlp);
@@ -5530,9 +5501,7 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 
 	lpfc_els_abort(phba, ndlp);
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_DELAY_TMO;
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 
 	ndlp->nlp_last_elscmd = 0;
 	del_timer_sync(&ndlp->nlp_delayfunc);
@@ -5614,7 +5583,7 @@ __lpfc_findnode_did(struct lpfc_vport *vport, uint32_t did)
 				 );
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE_VERBOSE,
 					 "0929 FIND node DID "
-					 "Data: x%px x%x x%x x%x x%x x%px\n",
+					 "Data: x%px x%x x%lx x%x x%x x%px\n",
 					 ndlp, ndlp->nlp_DID,
 					 ndlp->nlp_flag, data1, ndlp->nlp_rpi,
 					 ndlp->active_rrqs_xri_bitmap);
@@ -5661,7 +5630,7 @@ lpfc_findnode_mapped(struct lpfc_vport *vport)
 					       iflags);
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE_VERBOSE,
 					 "2025 FIND node DID MAPPED "
-					 "Data: x%px x%x x%x x%x x%px\n",
+					 "Data: x%px x%x x%lx x%x x%px\n",
 					 ndlp, ndlp->nlp_DID,
 					 ndlp->nlp_flag, data1,
 					 ndlp->active_rrqs_xri_bitmap);
@@ -5695,13 +5664,11 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 				 "6453 Setup New Node 2B_DISC x%x "
-				 "Data:x%x x%x x%lx\n",
+				 "Data:x%lx x%x x%lx\n",
 				 ndlp->nlp_DID, ndlp->nlp_flag,
 				 ndlp->nlp_state, vport->fc_flag);
 
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 		return ndlp;
 	}
 
@@ -5720,7 +5687,7 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 					 "6455 Setup RSCN Node 2B_DISC x%x "
-					 "Data:x%x x%x x%lx\n",
+					 "Data:x%lx x%x x%lx\n",
 					 ndlp->nlp_DID, ndlp->nlp_flag,
 					 ndlp->nlp_state, vport->fc_flag);
 
@@ -5738,13 +5705,11 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 							NLP_EVT_DEVICE_RECOVERY);
 			}
 
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 		} else {
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 					 "6456 Skip Setup RSCN Node x%x "
-					 "Data:x%x x%x x%lx\n",
+					 "Data:x%lx x%x x%lx\n",
 					 ndlp->nlp_DID, ndlp->nlp_flag,
 					 ndlp->nlp_state, vport->fc_flag);
 			ndlp = NULL;
@@ -5752,7 +5717,7 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 	} else {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 				 "6457 Setup Active Node 2B_DISC x%x "
-				 "Data:x%x x%x x%lx\n",
+				 "Data:x%lx x%x x%lx\n",
 				 ndlp->nlp_DID, ndlp->nlp_flag,
 				 ndlp->nlp_state, vport->fc_flag);
 
@@ -5763,7 +5728,7 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 		if (ndlp->nlp_state == NLP_STE_ADISC_ISSUE ||
 		    ndlp->nlp_state == NLP_STE_PLOGI_ISSUE ||
 		    (!vport->phba->nvmet_support &&
-		     ndlp->nlp_flag & NLP_RCV_PLOGI))
+		     test_bit(NLP_RCV_PLOGI, &ndlp->nlp_flag)))
 			return NULL;
 
 		if (vport->phba->nvmet_support)
@@ -5773,10 +5738,7 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 		 * allows for rediscovery
 		 */
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	}
 	return ndlp;
 }
@@ -6147,7 +6109,7 @@ lpfc_disc_timeout_handler(struct lpfc_vport *vport)
 				/* Clean up the ndlp on Fabric connections */
 				lpfc_drop_node(vport, ndlp);
 
-			} else if (!(ndlp->nlp_flag & NLP_NPR_ADISC)) {
+			} else if (!test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag)) {
 				/* Fail outstanding IO now since device
 				 * is marked for PLOGI.
 				 */
@@ -6360,11 +6322,11 @@ lpfc_mbx_cmpl_fdmi_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 
 	if (phba->sli_rev < LPFC_SLI_REV4)
 		ndlp->nlp_rpi = mb->un.varWords[0];
-	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+	set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_DISCOVERY,
-			 "0004 rpi:%x DID:%x flg:%x %d x%px\n",
+			 "0004 rpi:%x DID:%x flg:%lx %d x%px\n",
 			 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
 			 kref_read(&ndlp->kref),
 			 ndlp);
@@ -6414,7 +6376,7 @@ __lpfc_find_node(struct lpfc_vport *vport, node_filter filter, void *param)
 		if (filter(ndlp, param)) {
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE_VERBOSE,
 					 "3185 FIND node filter %ps DID "
-					 "ndlp x%px did x%x flg x%x st x%x "
+					 "ndlp x%px did x%x flg x%lx st x%x "
 					 "xri x%x type x%x rpi x%x\n",
 					 filter, ndlp, ndlp->nlp_DID,
 					 ndlp->nlp_flag, ndlp->nlp_state,
@@ -6552,7 +6514,7 @@ lpfc_nlp_init(struct lpfc_vport *vport, uint32_t did)
 		lpfc_printf_vlog(vport, KERN_INFO,
 				 LOG_ELS | LOG_NODE | LOG_DISCOVERY,
 				 "0007 Init New ndlp x%px, rpi:x%x DID:x%x "
-				 "flg:x%x refcnt:%d\n",
+				 "flg:x%lx refcnt:%d\n",
 				 ndlp, ndlp->nlp_rpi, ndlp->nlp_DID,
 				 ndlp->nlp_flag, kref_read(&ndlp->kref));
 
@@ -6584,7 +6546,7 @@ lpfc_nlp_release(struct kref *kref)
 	struct lpfc_vport *vport = ndlp->vport;
 
 	lpfc_debugfs_disc_trc(ndlp->vport, LPFC_DISC_TRC_NODE,
-		"node release:    did:x%x flg:x%x type:x%x",
+		"node release:    did:x%x flg:x%lx type:x%x",
 		ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_type);
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
@@ -6630,7 +6592,7 @@ lpfc_nlp_get(struct lpfc_nodelist *ndlp)
 
 	if (ndlp) {
 		lpfc_debugfs_disc_trc(ndlp->vport, LPFC_DISC_TRC_NODE,
-			"node get:        did:x%x flg:x%x refcnt:x%x",
+			"node get:        did:x%x flg:x%lx refcnt:x%x",
 			ndlp->nlp_DID, ndlp->nlp_flag,
 			kref_read(&ndlp->kref));
 
@@ -6662,7 +6624,7 @@ lpfc_nlp_put(struct lpfc_nodelist *ndlp)
 {
 	if (ndlp) {
 		lpfc_debugfs_disc_trc(ndlp->vport, LPFC_DISC_TRC_NODE,
-				"node put:        did:x%x flg:x%x refcnt:x%x",
+				"node put:        did:x%x flg:x%lx refcnt:x%x",
 				ndlp->nlp_DID, ndlp->nlp_flag,
 				kref_read(&ndlp->kref));
 	} else {
@@ -6715,11 +6677,12 @@ lpfc_fcf_inuse(struct lpfc_hba *phba)
 				spin_unlock_irqrestore(&vports[i]->fc_nodes_list_lock,
 						       iflags);
 				goto out;
-			} else if (ndlp->nlp_flag & NLP_RPI_REGISTERED) {
+			} else if (test_bit(NLP_RPI_REGISTERED,
+					    &ndlp->nlp_flag)) {
 				ret = 1;
 				lpfc_printf_log(phba, KERN_INFO,
 						LOG_NODE | LOG_DISCOVERY,
-						"2624 RPI %x DID %x flag %x "
+						"2624 RPI %x DID %x flag %lx "
 						"still logged in\n",
 						ndlp->nlp_rpi, ndlp->nlp_DID,
 						ndlp->nlp_flag);
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 006e22506ae89..7f57397d91a90 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -3093,7 +3093,8 @@ lpfc_cleanup(struct lpfc_vport *vport)
 				lpfc_printf_vlog(ndlp->vport, KERN_ERR,
 						 LOG_DISCOVERY,
 						 "0282 did:x%x ndlp:x%px "
-						 "refcnt:%d xflags x%x nflag x%x\n",
+						 "refcnt:%d xflags x%x "
+						 "nflag x%lx\n",
 						 ndlp->nlp_DID, (void *)ndlp,
 						 kref_read(&ndlp->kref),
 						 ndlp->fc4_xpt_flags,
@@ -3414,7 +3415,7 @@ lpfc_sli4_node_rpi_restore(struct lpfc_hba *phba)
 						 LOG_NODE | LOG_DISCOVERY,
 						 "0099 RPI alloc error for "
 						 "ndlp x%px DID:x%06x "
-						 "flg:x%x\n",
+						 "flg:x%lx\n",
 						 ndlp, ndlp->nlp_DID,
 						 ndlp->nlp_flag);
 				continue;
@@ -3423,7 +3424,7 @@ lpfc_sli4_node_rpi_restore(struct lpfc_hba *phba)
 			lpfc_printf_vlog(ndlp->vport, KERN_INFO,
 					 LOG_NODE | LOG_DISCOVERY,
 					 "0009 Assign RPI x%x to ndlp x%px "
-					 "DID:x%06x flg:x%x\n",
+					 "DID:x%06x flg:x%lx\n",
 					 ndlp->nlp_rpi, ndlp, ndlp->nlp_DID,
 					 ndlp->nlp_flag);
 		}
@@ -3827,15 +3828,12 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action)
 						 &vports[i]->fc_nodes,
 						 nlp_listp) {
 
-				spin_lock_irq(&ndlp->lock);
-				ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-				spin_unlock_irq(&ndlp->lock);
-
+				clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 				if (offline || hba_pci_err) {
-					spin_lock_irq(&ndlp->lock);
-					ndlp->nlp_flag &= ~(NLP_UNREG_INP |
-							    NLP_RPI_REGISTERED);
-					spin_unlock_irq(&ndlp->lock);
+					clear_bit(NLP_UNREG_INP,
+						  &ndlp->nlp_flag);
+					clear_bit(NLP_RPI_REGISTERED,
+						  &ndlp->nlp_flag);
 				}
 
 				if (ndlp->nlp_type & NLP_FABRIC) {
@@ -6912,9 +6910,7 @@ lpfc_sli4_async_fip_evt(struct lpfc_hba *phba,
 			 */
 			mod_timer(&ndlp->nlp_delayfunc,
 				  jiffies + msecs_to_jiffies(1000));
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= NLP_DELAY_TMO;
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 			ndlp->nlp_last_elscmd = ELS_CMD_FDISC;
 			vport->port_state = LPFC_FDISC;
 		} else {
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 4574716c8764f..4d88cfe71caed 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -65,7 +65,7 @@ lpfc_check_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		 struct lpfc_name *nn, struct lpfc_name *pn)
 {
 	/* First, we MUST have a RPI registered */
-	if (!(ndlp->nlp_flag & NLP_RPI_REGISTERED))
+	if (!test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag))
 		return 0;
 
 	/* Compare the ADISC rsp WWNN / WWPN matches our internal node
@@ -239,7 +239,7 @@ lpfc_els_abort(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 	/* Abort outstanding I/O on NPort <nlp_DID> */
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_DISCOVERY,
 			 "2819 Abort outstanding I/O on NPort x%x "
-			 "Data: x%x x%x x%x\n",
+			 "Data: x%lx x%x x%x\n",
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi);
 	/* Clean up all fabric IOs first.*/
@@ -340,7 +340,7 @@ lpfc_defer_plogi_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *login_mbox)
 
 	/* Now process the REG_RPI cmpl */
 	lpfc_mbx_cmpl_reg_login(phba, login_mbox);
-	ndlp->nlp_flag &= ~NLP_ACC_REGLOGIN;
+	clear_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag);
 	kfree(save_iocb);
 }
 
@@ -404,7 +404,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	/* PLOGI chkparm OK */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
-			 "0114 PLOGI chkparm OK Data: x%x x%x x%x "
+			 "0114 PLOGI chkparm OK Data: x%x x%x x%lx "
 			 "x%x x%x x%lx\n",
 			 ndlp->nlp_DID, ndlp->nlp_state, ndlp->nlp_flag,
 			 ndlp->nlp_rpi, vport->port_state,
@@ -429,7 +429,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	/* if already logged in, do implicit logout */
 	switch (ndlp->nlp_state) {
 	case  NLP_STE_NPR_NODE:
-		if (!(ndlp->nlp_flag & NLP_NPR_ADISC))
+		if (!test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag))
 			break;
 		fallthrough;
 	case  NLP_STE_REG_LOGIN_ISSUE:
@@ -449,7 +449,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			ndlp->nlp_type &= ~(NLP_NVME_TARGET | NLP_NVME_INITIATOR);
 			ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
 			ndlp->nlp_nvme_info &= ~NLP_NVME_NSLER;
-			ndlp->nlp_flag &= ~NLP_FIRSTBURST;
+			clear_bit(NLP_FIRSTBURST, &ndlp->nlp_flag);
 
 			lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb,
 					 ndlp, NULL);
@@ -480,7 +480,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	ndlp->nlp_type &= ~(NLP_NVME_TARGET | NLP_NVME_INITIATOR);
 	ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
 	ndlp->nlp_nvme_info &= ~NLP_NVME_NSLER;
-	ndlp->nlp_flag &= ~NLP_FIRSTBURST;
+	clear_bit(NLP_FIRSTBURST, &ndlp->nlp_flag);
 
 	login_mbox = NULL;
 	link_mbox = NULL;
@@ -552,13 +552,13 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		lpfc_can_disctmo(vport);
 	}
 
-	ndlp->nlp_flag &= ~NLP_SUPPRESS_RSP;
+	clear_bit(NLP_SUPPRESS_RSP, &ndlp->nlp_flag);
 	if ((phba->sli.sli_flag & LPFC_SLI_SUPPRESS_RSP) &&
 	    sp->cmn.valid_vendor_ver_level) {
 		vid = be32_to_cpu(sp->un.vv.vid);
 		flag = be32_to_cpu(sp->un.vv.flags);
 		if ((vid == LPFC_VV_EMLX_ID) && (flag & LPFC_VV_SUPPRESS_RSP))
-			ndlp->nlp_flag |= NLP_SUPPRESS_RSP;
+			set_bit(NLP_SUPPRESS_RSP, &ndlp->nlp_flag);
 	}
 
 	login_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
@@ -627,10 +627,9 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			 * this ELS request. The only way to do this is
 			 * to register, then unregister the RPI.
 			 */
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= (NLP_RM_DFLT_RPI | NLP_ACC_REGLOGIN |
-					   NLP_RCV_PLOGI);
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_RM_DFLT_RPI, &ndlp->nlp_flag);
+			set_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag);
+			set_bit(NLP_RCV_PLOGI, &ndlp->nlp_flag);
 		}
 
 		stat.un.b.lsRjtRsnCode = LSRJT_INVALID_CMD;
@@ -665,9 +664,8 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	login_mbox->ctx_u.save_iocb = save_iocb; /* For PLOGI ACC */
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= (NLP_ACC_REGLOGIN | NLP_RCV_PLOGI);
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag);
+	set_bit(NLP_RCV_PLOGI, &ndlp->nlp_flag);
 
 	/* Start the ball rolling by issuing REG_LOGIN here */
 	rc = lpfc_sli_issue_mbox(phba, login_mbox, MBX_NOWAIT);
@@ -797,7 +795,7 @@ lpfc_rcv_padisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		 */
 		if (ndlp->nlp_type & (NLP_FCP_TARGET | NLP_NVME_TARGET)) {
 			if ((ndlp->nlp_state != NLP_STE_MAPPED_NODE) &&
-			    !(ndlp->nlp_flag & NLP_NPR_ADISC))
+			    !test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag))
 				lpfc_nlp_set_state(vport, ndlp,
 						   NLP_STE_MAPPED_NODE);
 		}
@@ -814,9 +812,7 @@ lpfc_rcv_padisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	/* 1 sec timeout */
 	mod_timer(&ndlp->nlp_delayfunc, jiffies + msecs_to_jiffies(1000));
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_DELAY_TMO;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 	ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 	ndlp->nlp_prev_state = ndlp->nlp_state;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
@@ -835,9 +831,7 @@ lpfc_rcv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	/* Only call LOGO ACC for first LOGO, this avoids sending unnecessary
 	 * PLOGIs during LOGO storms from a device.
 	 */
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_LOGO_ACC;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 	if (els_cmd == ELS_CMD_PRLO)
 		lpfc_els_rsp_acc(vport, ELS_CMD_PRLO, cmdiocb, ndlp, NULL);
 	else
@@ -890,9 +884,7 @@ lpfc_rcv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			 */
 			mod_timer(&ndlp->nlp_delayfunc,
 				  jiffies + msecs_to_jiffies(1000));
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= NLP_DELAY_TMO;
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 			ndlp->nlp_last_elscmd = ELS_CMD_FDISC;
 			vport->port_state = LPFC_FDISC;
 		} else {
@@ -915,14 +907,12 @@ lpfc_rcv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		     ndlp->nlp_state <= NLP_STE_PRLI_ISSUE)) {
 			mod_timer(&ndlp->nlp_delayfunc,
 				  jiffies + msecs_to_jiffies(1000 * 1));
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= NLP_DELAY_TMO;
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 			ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 			lpfc_printf_vlog(vport, KERN_INFO,
 					 LOG_NODE | LOG_ELS | LOG_DISCOVERY,
 					 "3204 Start nlpdelay on DID x%06x "
-					 "nflag x%x lastels x%x ref cnt %u",
+					 "nflag x%lx lastels x%x ref cnt %u",
 					 ndlp->nlp_DID, ndlp->nlp_flag,
 					 ndlp->nlp_last_elscmd,
 					 kref_read(&ndlp->kref));
@@ -935,9 +925,7 @@ lpfc_rcv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	ndlp->nlp_prev_state = ndlp->nlp_state;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 	/* The driver has to wait until the ACC completes before it continues
 	 * processing the LOGO.  The action will resume in
 	 * lpfc_cmpl_els_logo_acc routine. Since part of processing includes an
@@ -978,7 +966,7 @@ lpfc_rcv_prli_support_check(struct lpfc_vport *vport,
 out:
 	lpfc_printf_vlog(vport, KERN_WARNING, LOG_DISCOVERY,
 			 "6115 Rcv PRLI (%x) check failed: ndlp rpi %d "
-			 "state x%x flags x%x port_type: x%x "
+			 "state x%x flags x%lx port_type: x%x "
 			 "npr->initfcn: x%x npr->tgtfcn: x%x\n",
 			 cmd, ndlp->nlp_rpi, ndlp->nlp_state,
 			 ndlp->nlp_flag, vport->port_type,
@@ -1020,7 +1008,7 @@ lpfc_rcv_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			if (npr->prliType == PRLI_NVME_TYPE)
 				ndlp->nlp_type |= NLP_NVME_TARGET;
 			if (npr->writeXferRdyDis)
-				ndlp->nlp_flag |= NLP_FIRSTBURST;
+				set_bit(NLP_FIRSTBURST, &ndlp->nlp_flag);
 		}
 		if (npr->Retry && ndlp->nlp_type &
 					(NLP_FCP_INITIATOR | NLP_FCP_TARGET))
@@ -1057,7 +1045,7 @@ lpfc_rcv_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			roles |= FC_RPORT_ROLE_FCP_TARGET;
 
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_RPORT,
-			"rport rolechg:   role:x%x did:x%x flg:x%x",
+			"rport rolechg:   role:x%x did:x%x flg:x%lx",
 			roles, ndlp->nlp_DID, ndlp->nlp_flag);
 
 		if (vport->cfg_enable_fc4_type != LPFC_ENABLE_NVME)
@@ -1068,10 +1056,8 @@ lpfc_rcv_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 static uint32_t
 lpfc_disc_set_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 {
-	if (!(ndlp->nlp_flag & NLP_RPI_REGISTERED)) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-		spin_unlock_irq(&ndlp->lock);
+	if (!test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag)) {
+		clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 		return 0;
 	}
 
@@ -1081,16 +1067,12 @@ lpfc_disc_set_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		    (test_bit(FC_RSCN_MODE, &vport->fc_flag) ||
 		    ((ndlp->nlp_fcp_info & NLP_FCP_2_DEVICE) &&
 		     (ndlp->nlp_type & NLP_FCP_TARGET)))) {
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= NLP_NPR_ADISC;
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 			return 1;
 		}
 	}
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 	lpfc_unreg_rpi(vport, ndlp);
 	return 0;
 }
@@ -1115,10 +1097,10 @@ lpfc_release_rpi(struct lpfc_hba *phba, struct lpfc_vport *vport,
 	/* If there is already an UNREG in progress for this ndlp,
 	 * no need to queue up another one.
 	 */
-	if (ndlp->nlp_flag & NLP_UNREG_INP) {
+	if (test_bit(NLP_UNREG_INP, &ndlp->nlp_flag)) {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 				 "1435 release_rpi SKIP UNREG x%x on "
-				 "NPort x%x deferred x%x  flg x%x "
+				 "NPort x%x deferred x%x  flg x%lx "
 				 "Data: x%px\n",
 				 ndlp->nlp_rpi, ndlp->nlp_DID,
 				 ndlp->nlp_defer_did,
@@ -1143,11 +1125,11 @@ lpfc_release_rpi(struct lpfc_hba *phba, struct lpfc_vport *vport,
 
 		if (((ndlp->nlp_DID & Fabric_DID_MASK) != Fabric_DID_MASK) &&
 		    (!test_bit(FC_OFFLINE_MODE, &vport->fc_flag)))
-			ndlp->nlp_flag |= NLP_UNREG_INP;
+			set_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 				 "1437 release_rpi UNREG x%x "
-				 "on NPort x%x flg x%x\n",
+				 "on NPort x%x flg x%lx\n",
 				 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag);
 
 		rc = lpfc_sli_issue_mbox(phba, pmb, MBX_NOWAIT);
@@ -1175,7 +1157,7 @@ lpfc_disc_illegal(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	}
 	lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 			 "0271 Illegal State Transition: node x%x "
-			 "event x%x, state x%x Data: x%x x%x\n",
+			 "event x%x, state x%x Data: x%x x%lx\n",
 			 ndlp->nlp_DID, evt, ndlp->nlp_state, ndlp->nlp_rpi,
 			 ndlp->nlp_flag);
 	return ndlp->nlp_state;
@@ -1190,13 +1172,12 @@ lpfc_cmpl_plogi_illegal(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	 * working on the same NPortID, do nothing for this thread
 	 * to stop it.
 	 */
-	if (!(ndlp->nlp_flag & NLP_RCV_PLOGI)) {
+	if (!test_bit(NLP_RCV_PLOGI, &ndlp->nlp_flag))
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				 "0272 Illegal State Transition: node x%x "
-				 "event x%x, state x%x Data: x%x x%x\n",
+				 "event x%x, state x%x Data: x%x x%lx\n",
 				  ndlp->nlp_DID, evt, ndlp->nlp_state,
 				  ndlp->nlp_rpi, ndlp->nlp_flag);
-	}
 	return ndlp->nlp_state;
 }
 
@@ -1230,9 +1211,7 @@ lpfc_rcv_logo_unused_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 {
 	struct lpfc_iocbq *cmdiocb = (struct lpfc_iocbq *) arg;
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_LOGO_ACC;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 	lpfc_els_rsp_acc(vport, ELS_CMD_ACC, cmdiocb, ndlp, NULL);
 
 	return ndlp->nlp_state;
@@ -1290,11 +1269,9 @@ lpfc_rcv_plogi_plogi_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			NULL);
 	} else {
 		if (lpfc_rcv_plogi(vport, ndlp, cmdiocb) &&
-		    (ndlp->nlp_flag & NLP_NPR_2B_DISC) &&
-		    (vport->num_disc_nodes)) {
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-			spin_unlock_irq(&ndlp->lock);
+		    test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag) &&
+		    vport->num_disc_nodes) {
+			clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 			/* Check if there are more PLOGIs to be sent */
 			lpfc_more_plogi(vport);
 			if (vport->num_disc_nodes == 0) {
@@ -1356,9 +1333,7 @@ lpfc_rcv_els_plogi_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	/* Put ndlp in npr state set plogi timer for 1 sec */
 	mod_timer(&ndlp->nlp_delayfunc, jiffies + msecs_to_jiffies(1000 * 1));
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_DELAY_TMO;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 	ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 	ndlp->nlp_prev_state = NLP_STE_PLOGI_ISSUE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
@@ -1389,7 +1364,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 
 	ulp_status = get_job_ulpstatus(phba, rspiocb);
 
-	if (ndlp->nlp_flag & NLP_ACC_REGLOGIN) {
+	if (test_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag)) {
 		/* Recovery from PLOGI collision logic */
 		return ndlp->nlp_state;
 	}
@@ -1418,7 +1393,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 		goto out;
 	/* PLOGI chkparm OK */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
-			 "0121 PLOGI chkparm OK Data: x%x x%x x%x x%x\n",
+			 "0121 PLOGI chkparm OK Data: x%x x%x x%lx x%x\n",
 			 ndlp->nlp_DID, ndlp->nlp_state,
 			 ndlp->nlp_flag, ndlp->nlp_rpi);
 	if (vport->cfg_fcp_class == 2 && (sp->cls2.classValid))
@@ -1446,14 +1421,14 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 			ed_tov = (phba->fc_edtov + 999999) / 1000000;
 		}
 
-		ndlp->nlp_flag &= ~NLP_SUPPRESS_RSP;
+		clear_bit(NLP_SUPPRESS_RSP, &ndlp->nlp_flag);
 		if ((phba->sli.sli_flag & LPFC_SLI_SUPPRESS_RSP) &&
 		    sp->cmn.valid_vendor_ver_level) {
 			vid = be32_to_cpu(sp->un.vv.vid);
 			flag = be32_to_cpu(sp->un.vv.flags);
 			if ((vid == LPFC_VV_EMLX_ID) &&
 			    (flag & LPFC_VV_SUPPRESS_RSP))
-				ndlp->nlp_flag |= NLP_SUPPRESS_RSP;
+				set_bit(NLP_SUPPRESS_RSP, &ndlp->nlp_flag);
 		}
 
 		/*
@@ -1476,7 +1451,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 						 LOG_TRACE_EVENT,
 						 "0133 PLOGI: no memory "
 						 "for config_link "
-						 "Data: x%x x%x x%x x%x\n",
+						 "Data: x%x x%x x%lx x%x\n",
 						 ndlp->nlp_DID, ndlp->nlp_state,
 						 ndlp->nlp_flag, ndlp->nlp_rpi);
 				goto out;
@@ -1500,7 +1475,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 	if (!mbox) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				 "0018 PLOGI: no memory for reg_login "
-				 "Data: x%x x%x x%x x%x\n",
+				 "Data: x%x x%x x%lx x%x\n",
 				 ndlp->nlp_DID, ndlp->nlp_state,
 				 ndlp->nlp_flag, ndlp->nlp_rpi);
 		goto out;
@@ -1520,7 +1495,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 			mbox->mbox_cmpl = lpfc_mbx_cmpl_fdmi_reg_login;
 			break;
 		default:
-			ndlp->nlp_flag |= NLP_REG_LOGIN_SEND;
+			set_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 			mbox->mbox_cmpl = lpfc_mbx_cmpl_reg_login;
 		}
 
@@ -1535,8 +1510,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 					   NLP_STE_REG_LOGIN_ISSUE);
 			return ndlp->nlp_state;
 		}
-		if (ndlp->nlp_flag & NLP_REG_LOGIN_SEND)
-			ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+		clear_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 		/* decrement node reference count to the failed mbox
 		 * command
 		 */
@@ -1544,7 +1518,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 		lpfc_mbox_rsrc_cleanup(phba, mbox, MBOX_THD_UNLOCKED);
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				 "0134 PLOGI: cannot issue reg_login "
-				 "Data: x%x x%x x%x x%x\n",
+				 "Data: x%x x%x x%lx x%x\n",
 				 ndlp->nlp_DID, ndlp->nlp_state,
 				 ndlp->nlp_flag, ndlp->nlp_rpi);
 	} else {
@@ -1552,7 +1526,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				 "0135 PLOGI: cannot format reg_login "
-				 "Data: x%x x%x x%x x%x\n",
+				 "Data: x%x x%x x%lx x%x\n",
 				 ndlp->nlp_DID, ndlp->nlp_state,
 				 ndlp->nlp_flag, ndlp->nlp_rpi);
 	}
@@ -1605,18 +1579,15 @@ static uint32_t
 lpfc_device_rm_plogi_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			   void *arg, uint32_t evt)
 {
-	if (ndlp->nlp_flag & NLP_NPR_2B_DISC) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NODEV_REMOVE;
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
+		set_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 		return ndlp->nlp_state;
-	} else {
-		/* software abort outstanding PLOGI */
-		lpfc_els_abort(vport->phba, ndlp);
-
-		lpfc_drop_node(vport, ndlp);
-		return NLP_STE_FREED_NODE;
 	}
+	/* software abort outstanding PLOGI */
+	lpfc_els_abort(vport->phba, ndlp);
+
+	lpfc_drop_node(vport, ndlp);
+	return NLP_STE_FREED_NODE;
 }
 
 static uint32_t
@@ -1636,9 +1607,8 @@ lpfc_device_recov_plogi_issue(struct lpfc_vport *vport,
 
 	ndlp->nlp_prev_state = NLP_STE_PLOGI_ISSUE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 
 	return ndlp->nlp_state;
 }
@@ -1656,10 +1626,7 @@ lpfc_rcv_plogi_adisc_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	cmdiocb = (struct lpfc_iocbq *) arg;
 
 	if (lpfc_rcv_plogi(vport, ndlp, cmdiocb)) {
-		if (ndlp->nlp_flag & NLP_NPR_2B_DISC) {
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-			spin_unlock_irq(&ndlp->lock);
+		if (test_and_clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
 			if (vport->num_disc_nodes)
 				lpfc_more_adisc(vport);
 		}
@@ -1748,9 +1715,7 @@ lpfc_cmpl_adisc_adisc_issue(struct lpfc_vport *vport,
 		/* 1 sec timeout */
 		mod_timer(&ndlp->nlp_delayfunc,
 			  jiffies + msecs_to_jiffies(1000));
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_DELAY_TMO;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 		ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 
 		ndlp->nlp_prev_state = NLP_STE_ADISC_ISSUE;
@@ -1789,18 +1754,15 @@ static uint32_t
 lpfc_device_rm_adisc_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			   void *arg, uint32_t evt)
 {
-	if (ndlp->nlp_flag & NLP_NPR_2B_DISC) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NODEV_REMOVE;
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
+		set_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 		return ndlp->nlp_state;
-	} else {
-		/* software abort outstanding ADISC */
-		lpfc_els_abort(vport->phba, ndlp);
-
-		lpfc_drop_node(vport, ndlp);
-		return NLP_STE_FREED_NODE;
 	}
+	/* software abort outstanding ADISC */
+	lpfc_els_abort(vport->phba, ndlp);
+
+	lpfc_drop_node(vport, ndlp);
+	return NLP_STE_FREED_NODE;
 }
 
 static uint32_t
@@ -1820,9 +1782,8 @@ lpfc_device_recov_adisc_issue(struct lpfc_vport *vport,
 
 	ndlp->nlp_prev_state = NLP_STE_ADISC_ISSUE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	lpfc_disc_set_adisc(vport, ndlp);
 	return ndlp->nlp_state;
 }
@@ -1856,7 +1817,7 @@ lpfc_rcv_prli_reglogin_issue(struct lpfc_vport *vport,
 		 * transition to UNMAPPED provided the RPI has completed
 		 * registration.
 		 */
-		if (ndlp->nlp_flag & NLP_RPI_REGISTERED) {
+		if (test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag)) {
 			lpfc_rcv_prli(vport, ndlp, cmdiocb);
 			lpfc_els_rsp_prli_acc(vport, cmdiocb, ndlp);
 		} else {
@@ -1895,7 +1856,7 @@ lpfc_rcv_logo_reglogin_issue(struct lpfc_vport *vport,
 	if ((mb = phba->sli.mbox_active)) {
 		if ((mb->u.mb.mbxCommand == MBX_REG_LOGIN64) &&
 		   (ndlp == mb->ctx_ndlp)) {
-			ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+			clear_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 			lpfc_nlp_put(ndlp);
 			mb->ctx_ndlp = NULL;
 			mb->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
@@ -1906,7 +1867,7 @@ lpfc_rcv_logo_reglogin_issue(struct lpfc_vport *vport,
 	list_for_each_entry_safe(mb, nextmb, &phba->sli.mboxq, list) {
 		if ((mb->u.mb.mbxCommand == MBX_REG_LOGIN64) &&
 		   (ndlp == mb->ctx_ndlp)) {
-			ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+			clear_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 			lpfc_nlp_put(ndlp);
 			list_del(&mb->list);
 			phba->sli.mboxq_cnt--;
@@ -1976,9 +1937,7 @@ lpfc_cmpl_reglogin_reglogin_issue(struct lpfc_vport *vport,
 		/* Put ndlp in npr state set plogi timer for 1 sec */
 		mod_timer(&ndlp->nlp_delayfunc,
 			  jiffies + msecs_to_jiffies(1000 * 1));
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_DELAY_TMO;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 		ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 
 		lpfc_issue_els_logo(vport, ndlp, 0);
@@ -1989,7 +1948,7 @@ lpfc_cmpl_reglogin_reglogin_issue(struct lpfc_vport *vport,
 	if (phba->sli_rev < LPFC_SLI_REV4)
 		ndlp->nlp_rpi = mb->un.varWords[0];
 
-	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+	set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
 
 	/* Only if we are not a fabric nport do we issue PRLI */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
@@ -2061,15 +2020,12 @@ lpfc_device_rm_reglogin_issue(struct lpfc_vport *vport,
 			      void *arg,
 			      uint32_t evt)
 {
-	if (ndlp->nlp_flag & NLP_NPR_2B_DISC) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NODEV_REMOVE;
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
+		set_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 		return ndlp->nlp_state;
-	} else {
-		lpfc_drop_node(vport, ndlp);
-		return NLP_STE_FREED_NODE;
 	}
+	lpfc_drop_node(vport, ndlp);
+	return NLP_STE_FREED_NODE;
 }
 
 static uint32_t
@@ -2084,17 +2040,16 @@ lpfc_device_recov_reglogin_issue(struct lpfc_vport *vport,
 
 	ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-	spin_lock_irq(&ndlp->lock);
 
 	/* If we are a target we won't immediately transition into PRLI,
 	 * so if REG_LOGIN already completed we don't need to ignore it.
 	 */
-	if (!(ndlp->nlp_flag & NLP_RPI_REGISTERED) ||
+	if (!test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag) ||
 	    !vport->phba->nvmet_support)
-		ndlp->nlp_flag |= NLP_IGNR_REG_CMPL;
+		set_bit(NLP_IGNR_REG_CMPL, &ndlp->nlp_flag);
 
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	lpfc_disc_set_adisc(vport, ndlp);
 	return ndlp->nlp_state;
 }
@@ -2228,7 +2183,8 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			if (npr->targetFunc) {
 				ndlp->nlp_type |= NLP_FCP_TARGET;
 				if (npr->writeXferRdyDis)
-					ndlp->nlp_flag |= NLP_FIRSTBURST;
+					set_bit(NLP_FIRSTBURST,
+						&ndlp->nlp_flag);
 			}
 			if (npr->Retry)
 				ndlp->nlp_fcp_info |= NLP_FCP_2_DEVICE;
@@ -2272,7 +2228,7 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 				/* Both sides support FB. The target's first
 				 * burst size is a 512 byte encoded value.
 				 */
-				ndlp->nlp_flag |= NLP_FIRSTBURST;
+				set_bit(NLP_FIRSTBURST, &ndlp->nlp_flag);
 				ndlp->nvme_fb_size = bf_get_be32(prli_fb_sz,
 								 nvpr);
 
@@ -2287,7 +2243,7 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
 				 "6029 NVME PRLI Cmpl w1 x%08x "
-				 "w4 x%08x w5 x%08x flag x%x, "
+				 "w4 x%08x w5 x%08x flag x%lx, "
 				 "fcp_info x%x nlp_type x%x\n",
 				 be32_to_cpu(nvpr->word1),
 				 be32_to_cpu(nvpr->word4),
@@ -2299,9 +2255,7 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	    (vport->port_type == LPFC_NPIV_PORT) &&
 	     vport->cfg_restrict_login) {
 out:
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_TARGET_REMOVE;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_TARGET_REMOVE, &ndlp->nlp_flag);
 		lpfc_issue_els_logo(vport, ndlp, 0);
 
 		ndlp->nlp_prev_state = NLP_STE_PRLI_ISSUE;
@@ -2353,18 +2307,15 @@ static uint32_t
 lpfc_device_rm_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			  void *arg, uint32_t evt)
 {
-	if (ndlp->nlp_flag & NLP_NPR_2B_DISC) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NODEV_REMOVE;
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
+		set_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 		return ndlp->nlp_state;
-	} else {
-		/* software abort outstanding PLOGI */
-		lpfc_els_abort(vport->phba, ndlp);
-
-		lpfc_drop_node(vport, ndlp);
-		return NLP_STE_FREED_NODE;
 	}
+	/* software abort outstanding PLOGI */
+	lpfc_els_abort(vport->phba, ndlp);
+
+	lpfc_drop_node(vport, ndlp);
+	return NLP_STE_FREED_NODE;
 }
 
 
@@ -2401,9 +2352,8 @@ lpfc_device_recov_prli_issue(struct lpfc_vport *vport,
 
 	ndlp->nlp_prev_state = NLP_STE_PRLI_ISSUE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	lpfc_disc_set_adisc(vport, ndlp);
 	return ndlp->nlp_state;
 }
@@ -2442,9 +2392,7 @@ lpfc_rcv_logo_logo_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 {
 	struct lpfc_iocbq *cmdiocb = (struct lpfc_iocbq *)arg;
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_LOGO_ACC;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 	lpfc_els_rsp_acc(vport, ELS_CMD_ACC, cmdiocb, ndlp, NULL);
 	return ndlp->nlp_state;
 }
@@ -2483,9 +2431,8 @@ lpfc_cmpl_logo_logo_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 {
 	ndlp->nlp_prev_state = NLP_STE_LOGO_ISSUE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	lpfc_disc_set_adisc(vport, ndlp);
 	return ndlp->nlp_state;
 }
@@ -2591,8 +2538,9 @@ lpfc_device_recov_unmap_node(struct lpfc_vport *vport,
 {
 	ndlp->nlp_prev_state = NLP_STE_UNMAPPED_NODE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
 	ndlp->nlp_fc4_type &= ~(NLP_FC4_FCP | NLP_FC4_NVME);
 	spin_unlock_irq(&ndlp->lock);
 	lpfc_disc_set_adisc(vport, ndlp);
@@ -2653,9 +2601,7 @@ lpfc_rcv_prlo_mapped_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	lpfc_sli_abort_iocb(vport, ndlp->nlp_sid, 0, LPFC_CTX_TGT);
 
 	/* Send PRLO_ACC */
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_LOGO_ACC;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 	lpfc_els_rsp_acc(vport, ELS_CMD_PRLO, cmdiocb, ndlp, NULL);
 
 	/* Save ELS_CMD_PRLO as the last elscmd and then set to NPR.
@@ -2665,7 +2611,7 @@ lpfc_rcv_prlo_mapped_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	ndlp->nlp_prev_state = ndlp->nlp_state;
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_ELS | LOG_DISCOVERY,
-			 "3422 DID x%06x nflag x%x lastels x%x ref cnt %u\n",
+			 "3422 DID x%06x nflag x%lx lastels x%x ref cnt %u\n",
 			 ndlp->nlp_DID, ndlp->nlp_flag,
 			 ndlp->nlp_last_elscmd,
 			 kref_read(&ndlp->kref));
@@ -2685,8 +2631,9 @@ lpfc_device_recov_mapped_node(struct lpfc_vport *vport,
 
 	ndlp->nlp_prev_state = NLP_STE_MAPPED_NODE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
 	ndlp->nlp_fc4_type &= ~(NLP_FC4_FCP | NLP_FC4_NVME);
 	spin_unlock_irq(&ndlp->lock);
 	return ndlp->nlp_state;
@@ -2699,16 +2646,16 @@ lpfc_rcv_plogi_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	struct lpfc_iocbq *cmdiocb  = (struct lpfc_iocbq *) arg;
 
 	/* Ignore PLOGI if we have an outstanding LOGO */
-	if (ndlp->nlp_flag & (NLP_LOGO_SND | NLP_LOGO_ACC))
+	if (test_bit(NLP_LOGO_SND, &ndlp->nlp_flag) ||
+	    test_bit(NLP_LOGO_ACC, &ndlp->nlp_flag))
 		return ndlp->nlp_state;
 	if (lpfc_rcv_plogi(vport, ndlp, cmdiocb)) {
 		lpfc_cancel_retry_delay_tmo(vport, ndlp);
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~(NLP_NPR_ADISC | NLP_NPR_2B_DISC);
-		spin_unlock_irq(&ndlp->lock);
-	} else if (!(ndlp->nlp_flag & NLP_NPR_2B_DISC)) {
+		clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
+		clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
+	} else if (!test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
 		/* send PLOGI immediately, move to PLOGI issue state */
-		if (!(ndlp->nlp_flag & NLP_DELAY_TMO)) {
+		if (!test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag)) {
 			ndlp->nlp_prev_state = NLP_STE_NPR_NODE;
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_PLOGI_ISSUE);
 			lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
@@ -2729,14 +2676,14 @@ lpfc_rcv_prli_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	stat.un.b.lsRjtRsnCodeExp = LSEXP_NOTHING_MORE;
 	lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb, ndlp, NULL);
 
-	if (!(ndlp->nlp_flag & NLP_DELAY_TMO)) {
+	if (!test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag)) {
 		/*
 		 * ADISC nodes will be handled in regular discovery path after
 		 * receiving response from NS.
 		 *
 		 * For other nodes, Send PLOGI to trigger an implicit LOGO.
 		 */
-		if (!(ndlp->nlp_flag & NLP_NPR_ADISC)) {
+		if (!test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag)) {
 			ndlp->nlp_prev_state = NLP_STE_NPR_NODE;
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_PLOGI_ISSUE);
 			lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
@@ -2767,15 +2714,15 @@ lpfc_rcv_padisc_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	 * or discovery in progress for this node. Starting discovery
 	 * here will affect the counting of discovery threads.
 	 */
-	if (!(ndlp->nlp_flag & NLP_DELAY_TMO) &&
-	    !(ndlp->nlp_flag & NLP_NPR_2B_DISC)) {
+	if (!test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag) &&
+	    !test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
 		/*
 		 * ADISC nodes will be handled in regular discovery path after
 		 * receiving response from NS.
 		 *
 		 * For other nodes, Send PLOGI to trigger an implicit LOGO.
 		 */
-		if (!(ndlp->nlp_flag & NLP_NPR_ADISC)) {
+		if (!test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag)) {
 			ndlp->nlp_prev_state = NLP_STE_NPR_NODE;
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_PLOGI_ISSUE);
 			lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
@@ -2790,24 +2737,18 @@ lpfc_rcv_prlo_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 {
 	struct lpfc_iocbq *cmdiocb = (struct lpfc_iocbq *) arg;
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_LOGO_ACC;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 
 	lpfc_els_rsp_acc(vport, ELS_CMD_ACC, cmdiocb, ndlp, NULL);
 
-	if ((ndlp->nlp_flag & NLP_DELAY_TMO) == 0) {
+	if (!test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag)) {
 		mod_timer(&ndlp->nlp_delayfunc,
 			  jiffies + msecs_to_jiffies(1000 * 1));
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_DELAY_TMO;
-		ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
+		clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 		ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 	} else {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-		spin_unlock_irq(&ndlp->lock);
+		clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 	}
 	return ndlp->nlp_state;
 }
@@ -2844,7 +2785,7 @@ lpfc_cmpl_prli_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	ulp_status = get_job_ulpstatus(phba, rspiocb);
 
-	if (ulp_status && (ndlp->nlp_flag & NLP_NODEV_REMOVE)) {
+	if (ulp_status && test_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag)) {
 		lpfc_drop_node(vport, ndlp);
 		return NLP_STE_FREED_NODE;
 	}
@@ -2877,7 +2818,7 @@ lpfc_cmpl_adisc_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	ulp_status = get_job_ulpstatus(phba, rspiocb);
 
-	if (ulp_status && (ndlp->nlp_flag & NLP_NODEV_REMOVE)) {
+	if (ulp_status && test_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag)) {
 		lpfc_drop_node(vport, ndlp);
 		return NLP_STE_FREED_NODE;
 	}
@@ -2896,12 +2837,11 @@ lpfc_cmpl_reglogin_npr_node(struct lpfc_vport *vport,
 		/* SLI4 ports have preallocated logical rpis. */
 		if (vport->phba->sli_rev < LPFC_SLI_REV4)
 			ndlp->nlp_rpi = mb->un.varWords[0];
-		ndlp->nlp_flag |= NLP_RPI_REGISTERED;
-		if (ndlp->nlp_flag & NLP_LOGO_ACC) {
+		set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
+		if (test_bit(NLP_LOGO_ACC, &ndlp->nlp_flag))
 			lpfc_unreg_rpi(vport, ndlp);
-		}
 	} else {
-		if (ndlp->nlp_flag & NLP_NODEV_REMOVE) {
+		if (test_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag)) {
 			lpfc_drop_node(vport, ndlp);
 			return NLP_STE_FREED_NODE;
 		}
@@ -2913,10 +2853,8 @@ static uint32_t
 lpfc_device_rm_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			void *arg, uint32_t evt)
 {
-	if (ndlp->nlp_flag & NLP_NPR_2B_DISC) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NODEV_REMOVE;
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
+		set_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 		return ndlp->nlp_state;
 	}
 	lpfc_drop_node(vport, ndlp);
@@ -2932,8 +2870,9 @@ lpfc_device_recov_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		return ndlp->nlp_state;
 
 	lpfc_cancel_retry_delay_tmo(vport, ndlp);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
 	ndlp->nlp_fc4_type &= ~(NLP_FC4_FCP | NLP_FC4_NVME);
 	spin_unlock_irq(&ndlp->lock);
 	return ndlp->nlp_state;
@@ -3146,7 +3085,7 @@ lpfc_disc_state_machine(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	/* DSM in event <evt> on NPort <nlp_DID> in state <cur_state> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 			 "0211 DSM in event x%x on NPort x%x in "
-			 "state %d rpi x%x Data: x%x x%x\n",
+			 "state %d rpi x%x Data: x%lx x%x\n",
 			 evt, ndlp->nlp_DID, cur_state, ndlp->nlp_rpi,
 			 ndlp->nlp_flag, data1);
 
@@ -3163,12 +3102,12 @@ lpfc_disc_state_machine(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			((uint32_t)ndlp->nlp_type));
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 			 "0212 DSM out state %d on NPort x%x "
-			 "rpi x%x Data: x%x x%x\n",
+			 "rpi x%x Data: x%lx x%x\n",
 			 rc, ndlp->nlp_DID, ndlp->nlp_rpi, ndlp->nlp_flag,
 			 data1);
 
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_DSM,
-			"DSM out:         ste:%d did:x%x flg:x%x",
+			"DSM out:         ste:%d did:x%x flg:x%lx",
 			rc, ndlp->nlp_DID, ndlp->nlp_flag);
 		/* Decrement the ndlp reference count held for this function */
 		lpfc_nlp_put(ndlp);
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 4f628e00d1c18..6e0b27460c24b 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -1232,7 +1232,7 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport,
 
 			/* Word 5 */
 			if ((phba->cfg_nvme_enable_fb) &&
-			    (pnode->nlp_flag & NLP_FIRSTBURST)) {
+			    test_bit(NLP_FIRSTBURST, &pnode->nlp_flag)) {
 				req_len = lpfc_ncmd->nvmeCmd->payload_length;
 				if (req_len < pnode->nvme_fb_size)
 					wqe->fcp_iwrite.initial_xfer_len =
@@ -2651,14 +2651,11 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 				 * reference. Check if another thread has set
 				 * NLP_DROPPED.
 				 */
-				spin_lock_irq(&ndlp->lock);
-				if (!(ndlp->nlp_flag & NLP_DROPPED)) {
-					ndlp->nlp_flag |= NLP_DROPPED;
-					spin_unlock_irq(&ndlp->lock);
+				if (!test_and_set_bit(NLP_DROPPED,
+						      &ndlp->nlp_flag)) {
 					lpfc_nlp_put(ndlp);
 					return;
 				}
-				spin_unlock_irq(&ndlp->lock);
 			}
 		}
 	}
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 0cef5d089f34b..3b29d57d77ac5 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -2854,7 +2854,7 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 			/* In template ar=1 wqes=0 sup=0 irsp=0 irsplen=0 */
 
 			if (rsp->rsplen == LPFC_NVMET_SUCCESS_LEN) {
-				if (ndlp->nlp_flag & NLP_SUPPRESS_RSP)
+				if (test_bit(NLP_SUPPRESS_RSP, &ndlp->nlp_flag))
 					bf_set(wqe_sup,
 					       &wqe->fcp_tsend.wqe_com, 1);
 			} else {
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 0eaede8275dac..908b2f7dd70c9 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -4629,7 +4629,7 @@ static int lpfc_scsi_prep_cmnd_buf_s3(struct lpfc_vport *vport,
 			iocb_cmd->ulpCommand = CMD_FCP_IWRITE64_CR;
 			iocb_cmd->ulpPU = PARM_READ_CHECK;
 			if (vport->cfg_first_burst_size &&
-			    (pnode->nlp_flag & NLP_FIRSTBURST)) {
+			    test_bit(NLP_FIRSTBURST, &pnode->nlp_flag)) {
 				u32 xrdy_len;
 
 				fcpdl = scsi_bufflen(scsi_cmnd);
@@ -5829,7 +5829,7 @@ lpfc_send_taskmgmt(struct lpfc_vport *vport, struct fc_rport *rport,
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP,
 			 "0702 Issue %s to TGT %d LUN %llu "
-			 "rpi x%x nlp_flag x%x Data: x%x x%x\n",
+			 "rpi x%x nlp_flag x%lx Data: x%x x%x\n",
 			 lpfc_taskmgmt_name(task_mgmt_cmd), tgt_id, lun_id,
 			 pnode->nlp_rpi, pnode->nlp_flag, iocbq->sli4_xritag,
 			 iocbq->cmd_flag);
@@ -6094,8 +6094,8 @@ lpfc_target_reset_handler(struct scsi_cmnd *cmnd)
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 			"0722 Target Reset rport failure: rdata x%px\n", rdata);
 		if (pnode) {
+			clear_bit(NLP_NPR_ADISC, &pnode->nlp_flag);
 			spin_lock_irqsave(&pnode->lock, flags);
-			pnode->nlp_flag &= ~NLP_NPR_ADISC;
 			pnode->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
 			spin_unlock_irqrestore(&pnode->lock, flags);
 		}
@@ -6124,7 +6124,7 @@ lpfc_target_reset_handler(struct scsi_cmnd *cmnd)
 		    !pnode->logo_waitq) {
 			pnode->logo_waitq = &waitq;
 			pnode->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
-			pnode->nlp_flag |= NLP_ISSUE_LOGO;
+			set_bit(NLP_ISSUE_LOGO, &pnode->nlp_flag);
 			pnode->save_flags |= NLP_WAIT_FOR_LOGO;
 			spin_unlock_irqrestore(&pnode->lock, flags);
 			lpfc_unreg_rpi(vport, pnode);
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index c1ce05646e725..874644b31a3eb 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -2913,14 +2913,14 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 				vport,
 				KERN_INFO, LOG_MBOX | LOG_DISCOVERY,
 				"1438 UNREG cmpl deferred mbox x%x "
-				"on NPort x%x Data: x%x x%x x%px x%lx x%x\n",
+				"on NPort x%x Data: x%lx x%x x%px x%lx x%x\n",
 				ndlp->nlp_rpi, ndlp->nlp_DID,
 				ndlp->nlp_flag, ndlp->nlp_defer_did,
 				ndlp, vport->load_flag, kref_read(&ndlp->kref));
 
-			if ((ndlp->nlp_flag & NLP_UNREG_INP) &&
-			    (ndlp->nlp_defer_did != NLP_EVT_NOTHING_PENDING)) {
-				ndlp->nlp_flag &= ~NLP_UNREG_INP;
+			if (test_bit(NLP_UNREG_INP, &ndlp->nlp_flag) &&
+			    ndlp->nlp_defer_did != NLP_EVT_NOTHING_PENDING) {
+				clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 				ndlp->nlp_defer_did = NLP_EVT_NOTHING_PENDING;
 				lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
 			}
@@ -2970,7 +2970,7 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 {
 	struct lpfc_vport  *vport = pmb->vport;
 	struct lpfc_nodelist *ndlp;
-	u32 unreg_inp;
+	bool unreg_inp;
 
 	ndlp = pmb->ctx_ndlp;
 	if (pmb->u.mb.mbxCommand == MBX_UNREG_LOGIN) {
@@ -2983,7 +2983,7 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 					 vport, KERN_INFO,
 					 LOG_MBOX | LOG_SLI | LOG_NODE,
 					 "0010 UNREG_LOGIN vpi:x%x "
-					 "rpi:%x DID:%x defer x%x flg x%x "
+					 "rpi:%x DID:%x defer x%x flg x%lx "
 					 "x%px\n",
 					 vport->vpi, ndlp->nlp_rpi,
 					 ndlp->nlp_DID, ndlp->nlp_defer_did,
@@ -2993,11 +2993,9 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 				/* Cleanup the nlp_flag now that the UNREG RPI
 				 * has completed.
 				 */
-				spin_lock_irq(&ndlp->lock);
-				unreg_inp = ndlp->nlp_flag & NLP_UNREG_INP;
-				ndlp->nlp_flag &=
-					~(NLP_UNREG_INP | NLP_LOGO_ACC);
-				spin_unlock_irq(&ndlp->lock);
+				unreg_inp = test_and_clear_bit(NLP_UNREG_INP,
+							       &ndlp->nlp_flag);
+				clear_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 
 				/* Check to see if there are any deferred
 				 * events to process
@@ -14342,9 +14340,7 @@ lpfc_sli4_sp_handle_mbox_event(struct lpfc_hba *phba, struct lpfc_mcqe *mcqe)
 			 * an unsolicited PLOGI from the same NPortId from
 			 * starting another mailbox transaction.
 			 */
-			spin_lock_irqsave(&ndlp->lock, iflags);
-			ndlp->nlp_flag |= NLP_UNREG_INP;
-			spin_unlock_irqrestore(&ndlp->lock, iflags);
+			set_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 			lpfc_unreg_login(phba, vport->vpi,
 					 pmbox->un.varWords[0], pmb);
 			pmb->mbox_cmpl = lpfc_mbx_cmpl_dflt_rpi;
@@ -19093,9 +19089,9 @@ lpfc_sli4_seq_abort_rsp(struct lpfc_vport *vport,
 	 * to free ndlp when transmit completes
 	 */
 	if (ndlp->nlp_state == NLP_STE_UNUSED_NODE &&
-	    !(ndlp->nlp_flag & NLP_DROPPED) &&
+	    !test_bit(NLP_DROPPED, &ndlp->nlp_flag) &&
 	    !(ndlp->fc4_xpt_flags & (NVME_XPT_REGD | SCSI_XPT_REGD))) {
-		ndlp->nlp_flag |= NLP_DROPPED;
+		set_bit(NLP_DROPPED, &ndlp->nlp_flag);
 		lpfc_nlp_put(ndlp);
 	}
 }
@@ -21113,11 +21109,7 @@ lpfc_cleanup_pending_mbox(struct lpfc_vport *vport)
 				/* Unregister the RPI when mailbox complete */
 				mb->mbox_flag |= LPFC_MBX_IMED_UNREG;
 				restart_loop = 1;
-				spin_unlock_irq(&phba->hbalock);
-				spin_lock(&ndlp->lock);
-				ndlp->nlp_flag &= ~NLP_IGNR_REG_CMPL;
-				spin_unlock(&ndlp->lock);
-				spin_lock_irq(&phba->hbalock);
+				clear_bit(NLP_IGNR_REG_CMPL, &ndlp->nlp_flag);
 				break;
 			}
 		}
@@ -21132,9 +21124,7 @@ lpfc_cleanup_pending_mbox(struct lpfc_vport *vport)
 			ndlp = mb->ctx_ndlp;
 			mb->ctx_ndlp = NULL;
 			if (ndlp) {
-				spin_lock(&ndlp->lock);
-				ndlp->nlp_flag &= ~NLP_IGNR_REG_CMPL;
-				spin_unlock(&ndlp->lock);
+				clear_bit(NLP_IGNR_REG_CMPL, &ndlp->nlp_flag);
 				lpfc_nlp_put(ndlp);
 			}
 		}
@@ -21143,9 +21133,7 @@ lpfc_cleanup_pending_mbox(struct lpfc_vport *vport)
 
 	/* Release the ndlp with the cleaned-up active mailbox command */
 	if (act_mbx_ndlp) {
-		spin_lock(&act_mbx_ndlp->lock);
-		act_mbx_ndlp->nlp_flag &= ~NLP_IGNR_REG_CMPL;
-		spin_unlock(&act_mbx_ndlp->lock);
+		clear_bit(NLP_IGNR_REG_CMPL, &act_mbx_ndlp->nlp_flag);
 		lpfc_nlp_put(act_mbx_ndlp);
 	}
 }
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index 7a4d4d8e2ad55..9e0e357633779 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -496,7 +496,7 @@ lpfc_send_npiv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	    !ndlp->logo_waitq) {
 		ndlp->logo_waitq = &waitq;
 		ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
-		ndlp->nlp_flag |= NLP_ISSUE_LOGO;
+		set_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag);
 		ndlp->save_flags |= NLP_WAIT_FOR_LOGO;
 	}
 	spin_unlock_irq(&ndlp->lock);
@@ -515,8 +515,8 @@ lpfc_send_npiv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	}
 
 	/* Error - clean up node flags. */
+	clear_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag);
 	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_ISSUE_LOGO;
 	ndlp->save_flags &= ~NLP_WAIT_FOR_LOGO;
 	spin_unlock_irq(&ndlp->lock);
 
@@ -708,7 +708,7 @@ lpfc_vport_delete(struct fc_vport *fc_vport)
 
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_VPORT | LOG_ELS,
 					 "1829 DA_ID issue status %d. "
-					 "SFlag x%x NState x%x, NFlag x%x "
+					 "SFlag x%x NState x%x, NFlag x%lx "
 					 "Rpi x%x\n",
 					 rc, ndlp->save_flags, ndlp->nlp_state,
 					 ndlp->nlp_flag, ndlp->nlp_rpi);

From 3f8175c0a85900a3243530b93ec76207a9cc47cd Mon Sep 17 00:00:00 2001
From: Justin Tee <justin.tee@broadcom.com>
Date: Thu, 31 Oct 2024 15:32:18 -0700
Subject: [PATCH 0798/1530] scsi: lpfc: Update lpfc version to 14.4.0.6

Update lpfc version to 14.4.0.6

Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Link: https://lore.kernel.org/r/20241031223219.152342-11-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_version.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index e70f163fab900..61fe1220f8ad3 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "14.4.0.5"
+#define LPFC_DRIVER_VERSION "14.4.0.6"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */

From 5c169625d89e4a80c132faba3c0b9206ca3c4156 Mon Sep 17 00:00:00 2001
From: Justin Tee <justin.tee@broadcom.com>
Date: Thu, 31 Oct 2024 15:32:19 -0700
Subject: [PATCH 0799/1530] scsi: lpfc: Copyright updates for 14.4.0.6 patches

Update copyrights to 2024 for files modified in the 14.4.0.6 patch set.

Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Link: https://lore.kernel.org/r/20241031223219.152342-12-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_crtn.h | 2 +-
 drivers/scsi/lpfc/lpfc_disc.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index f8a77ffdb0a89..efeb61b15a5b5 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017-2023 Broadcom. All Rights Reserved. The term *
+ * Copyright (C) 2017-2024 Broadcom. All Rights Reserved. The term *
  * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index af5d5bd75642c..3e173b5d00e00 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017-2022 Broadcom. All Rights Reserved. The term *
+ * Copyright (C) 2017-2024 Broadcom. All Rights Reserved. The term *
  * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *

From 7d7cf89b119af433354f865fc01017b9f8aa411a Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Sat, 17 Aug 2024 11:09:03 +0530
Subject: [PATCH 0800/1530] PCI: qcom-ep: Move controller cleanups to
 qcom_pcie_perst_deassert()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, the endpoint cleanup function dw_pcie_ep_cleanup() and EPF
deinit notify function pci_epc_deinit_notify() are called during the
execution of qcom_pcie_perst_assert() i.e., when the host has asserted
PERST#. But quickly after this step, refclk will also be disabled by the
host.

All of the Qcom endpoint SoCs supported as of now depend on the refclk from
the host for keeping the controller operational. Due to this limitation,
any access to the hardware registers in the absence of refclk will result
in a whole endpoint crash. Unfortunately, most of the controller cleanups
require accessing the hardware registers (like eDMA cleanup performed in
dw_pcie_ep_cleanup(), powering down MHI EPF etc...). So these cleanup
functions are currently causing the crash in the endpoint SoC once host
asserts PERST#.

One way to address this issue is by generating the refclk in the endpoint
itself and not depending on the host. But that is not always possible as
some of the endpoint designs do require the endpoint to consume refclk from
the host (as I was told by the Qcom engineers).

Thus, fix this crash by moving the controller cleanups to the start of
the qcom_pcie_perst_deassert() function. qcom_pcie_perst_deassert() is
called whenever the host has deasserted PERST# and it is guaranteed that
the refclk would be active at this point. So at the start of this function
(after enabling resources), the controller cleanup can be performed. Once
finished, rest of the code execution for PERST# deassert can continue as
usual.

Fixes: 473b2cf9c4d1 ("PCI: endpoint: Introduce 'epc_deinit' event and notify the EPF drivers")
Fixes: 570d7715eed8 ("PCI: dwc: ep: Introduce dw_pcie_ep_cleanup() API for drivers supporting PERST#")
Link: https://lore.kernel.org/r/20240817-pci-qcom-ep-cleanup-v1-1-d6b958226559@linaro.org
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/dwc/pcie-qcom-ep.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
index e588fcc545893..b5ca5260f9049 100644
--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
+++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
@@ -396,6 +396,10 @@ static int qcom_pcie_perst_deassert(struct dw_pcie *pci)
 		return ret;
 	}
 
+	/* Perform cleanup that requires refclk */
+	pci_epc_deinit_notify(pci->ep.epc);
+	dw_pcie_ep_cleanup(&pci->ep);
+
 	/* Assert WAKE# to RC to indicate device is ready */
 	gpiod_set_value_cansleep(pcie_ep->wake, 1);
 	usleep_range(WAKE_DELAY_US, WAKE_DELAY_US + 500);
@@ -540,8 +544,6 @@ static void qcom_pcie_perst_assert(struct dw_pcie *pci)
 {
 	struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci);
 
-	pci_epc_deinit_notify(pci->ep.epc);
-	dw_pcie_ep_cleanup(&pci->ep);
 	qcom_pcie_disable_resources(pcie_ep);
 	pcie_ep->link_status = QCOM_PCIE_EP_LINK_DISABLED;
 }

From 40e2125381dc11379112485e3eefdd25c6df5375 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Sat, 17 Aug 2024 11:09:04 +0530
Subject: [PATCH 0801/1530] PCI: tegra194: Move controller cleanups to
 pex_ep_event_pex_rst_deassert()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, the endpoint cleanup function dw_pcie_ep_cleanup() and EPF
deinit notify function pci_epc_deinit_notify() are called during the
execution of pex_ep_event_pex_rst_assert() i.e., when the host has asserted
PERST#. But quickly after this step, refclk will also be disabled by the
host.

All of the tegra194 endpoint SoCs supported as of now depend on the refclk
from the host for keeping the controller operational. Due to this
limitation, any access to the hardware registers in the absence of refclk
will result in a whole endpoint crash. Unfortunately, most of the
controller cleanups require accessing the hardware registers (like eDMA
cleanup performed in dw_pcie_ep_cleanup(), etc...). So these cleanup
functions can cause the crash in the endpoint SoC once host asserts PERST#.

One way to address this issue is by generating the refclk in the endpoint
itself and not depending on the host. But that is not always possible as
some of the endpoint designs do require the endpoint to consume refclk from
the host.

Thus, fix this crash by moving the controller cleanups to the start of
the pex_ep_event_pex_rst_deassert() function. This function is called
whenever the host has deasserted PERST# and it is guaranteed that the
refclk would be active at this point. So at the start of this function
(after enabling resources) the controller cleanup can be performed. Once
finished, rest of the code execution for PERST# deassert can continue as
usual.

Fixes: 473b2cf9c4d1 ("PCI: endpoint: Introduce 'epc_deinit' event and notify the EPF drivers")
Fixes: 570d7715eed8 ("PCI: dwc: ep: Introduce dw_pcie_ep_cleanup() API for drivers supporting PERST#")
Link: https://lore.kernel.org/r/20240817-pci-qcom-ep-cleanup-v1-2-d6b958226559@linaro.org
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Cc: Jonathan Hunter <jonathanh@nvidia.com>
Cc: Thierry Reding <thierry.reding@gmail.com>
Cc: Vidya Sagar <vidyas@nvidia.com>
Cc: linux-tegra@vger.kernel.org
---
 drivers/pci/controller/dwc/pcie-tegra194.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index c1394f2ab63ff..ced3b7e7bdade 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -1704,9 +1704,6 @@ static void pex_ep_event_pex_rst_assert(struct tegra_pcie_dw *pcie)
 	if (ret)
 		dev_err(pcie->dev, "Failed to go Detect state: %d\n", ret);
 
-	pci_epc_deinit_notify(pcie->pci.ep.epc);
-	dw_pcie_ep_cleanup(&pcie->pci.ep);
-
 	reset_control_assert(pcie->core_rst);
 
 	tegra_pcie_disable_phy(pcie);
@@ -1785,6 +1782,10 @@ static void pex_ep_event_pex_rst_deassert(struct tegra_pcie_dw *pcie)
 		goto fail_phy;
 	}
 
+	/* Perform cleanup that requires refclk */
+	pci_epc_deinit_notify(pcie->pci.ep.epc);
+	dw_pcie_ep_cleanup(&pcie->pci.ep);
+
 	/* Clear any stale interrupt statuses */
 	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L0);
 	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_0_0);

From e0662dae178ddb2d890df0b6f622aa7f6f921791 Mon Sep 17 00:00:00 2001
From: devi priya <quic_devipriy@quicinc.com>
Date: Thu, 1 Aug 2024 11:18:00 +0530
Subject: [PATCH 0802/1530] dt-bindings: PCI: qcom: Document the IPQ9574 PCIe
 controller
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Document the PCIe controller on IPQ9574 platform.

Link: https://lore.kernel.org/r/20240801054803.3015572-2-quic_srichara@quicinc.com
Signed-off-by: devi priya <quic_devipriy@quicinc.com>
Signed-off-by: Sricharan Ramabadhran <quic_srichara@quicinc.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 .../devicetree/bindings/pci/qcom,pcie.yaml    | 50 +++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
index ffabbac57fc16..bd87f6b49d680 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
@@ -26,6 +26,7 @@ properties:
           - qcom,pcie-ipq8064-v2
           - qcom,pcie-ipq8074
           - qcom,pcie-ipq8074-gen3
+          - qcom,pcie-ipq9574
           - qcom,pcie-msm8996
           - qcom,pcie-qcs404
           - qcom,pcie-sdm845
@@ -164,6 +165,7 @@ allOf:
             enum:
               - qcom,pcie-ipq6018
               - qcom,pcie-ipq8074-gen3
+              - qcom,pcie-ipq9574
     then:
       properties:
         reg:
@@ -400,6 +402,53 @@ allOf:
             - const: axi_m_sticky # AXI Master Sticky reset
             - const: axi_s_sticky # AXI Slave Sticky reset
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,pcie-ipq9574
+    then:
+      properties:
+        clocks:
+          minItems: 6
+          maxItems: 6
+        clock-names:
+          items:
+            - const: axi_m # AXI Master clock
+            - const: axi_s # AXI Slave clock
+            - const: axi_bridge
+            - const: rchng
+            - const: ahb
+            - const: aux
+
+        resets:
+          minItems: 8
+          maxItems: 8
+        reset-names:
+          items:
+            - const: pipe # PIPE reset
+            - const: sticky # Core Sticky reset
+            - const: axi_s_sticky # AXI Slave Sticky reset
+            - const: axi_s # AXI Slave reset
+            - const: axi_m_sticky # AXI Master Sticky reset
+            - const: axi_m # AXI Master reset
+            - const: aux # AUX Reset
+            - const: ahb # AHB Reset
+
+        interrupts:
+          minItems: 8
+        interrupt-names:
+          items:
+            - const: msi0
+            - const: msi1
+            - const: msi2
+            - const: msi3
+            - const: msi4
+            - const: msi5
+            - const: msi6
+            - const: msi7
+
   - if:
       properties:
         compatible:
@@ -510,6 +559,7 @@ allOf:
                 - qcom,pcie-ipq8064v2
                 - qcom,pcie-ipq8074
                 - qcom,pcie-ipq8074-gen3
+                - qcom,pcie-ipq9574
                 - qcom,pcie-qcs404
     then:
       required:

From 08e835268c35e851b308f326357224248cfb445b Mon Sep 17 00:00:00 2001
From: Siddharth Vadapalli <s-vadapalli@ti.com>
Date: Fri, 24 May 2024 14:53:49 +0530
Subject: [PATCH 0803/1530] PCI: j721e: Add PCIe support for J722S SoC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

TI's J722S SoC has one instance of PCIe namely PCIe0 which is a Gen3
single lane PCIe controller. Add support for the "ti,j722s-pcie-host"
compatible specific to J722S SoC.

Link: https://lore.kernel.org/r/20240524092349.158443-1-s-vadapalli@ti.com
Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/cadence/pci-j721e.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c
index 284f2e0e4d261..c9f3103d68e18 100644
--- a/drivers/pci/controller/cadence/pci-j721e.c
+++ b/drivers/pci/controller/cadence/pci-j721e.c
@@ -386,6 +386,13 @@ static const struct j721e_pcie_data j784s4_pcie_ep_data = {
 	.max_lanes = 4,
 };
 
+static const struct j721e_pcie_data j722s_pcie_rc_data = {
+	.mode = PCI_MODE_RC,
+	.linkdown_irq_regfield = J7200_LINK_DOWN,
+	.byte_access_allowed = true,
+	.max_lanes = 1,
+};
+
 static const struct of_device_id of_j721e_pcie_match[] = {
 	{
 		.compatible = "ti,j721e-pcie-host",
@@ -419,6 +426,10 @@ static const struct of_device_id of_j721e_pcie_match[] = {
 		.compatible = "ti,j784s4-pcie-ep",
 		.data = &j784s4_pcie_ep_data,
 	},
+	{
+		.compatible = "ti,j722s-pcie-host",
+		.data = &j722s_pcie_rc_data,
+	},
 	{},
 };
 

From a63b74f2e35be3829f256922037ae5cee6bb844a Mon Sep 17 00:00:00 2001
From: devi priya <quic_devipriy@quicinc.com>
Date: Thu, 1 Aug 2024 11:18:03 +0530
Subject: [PATCH 0804/1530] PCI: qcom: Add support for IPQ9574
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the new IPQ9574 platform which is based on the Qcom IP rev. 1.27.0
and Synopsys IP rev. 5.80a.

The platform itself has four PCIe Gen3 controllers: two single-lane and
two dual-lane, all are based on Synopsys IP rev. 5.70a. As such, reuse
all the members of 'ops_2_9_0'.

Link: https://lore.kernel.org/r/20240801054803.3015572-5-quic_srichara@quicinc.com
Co-developed-by: Anusha Rao <quic_anusha@quicinc.com>
Signed-off-by: Anusha Rao <quic_anusha@quicinc.com>
Signed-off-by: devi priya <quic_devipriy@quicinc.com>
Signed-off-by: Sricharan Ramabadhran <quic_srichara@quicinc.com>
[kwilczynski: commit log]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/dwc/pcie-qcom.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 2b33d03ed0541..07286fb9adc1c 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -1830,6 +1830,7 @@ static const struct of_device_id qcom_pcie_match[] = {
 	{ .compatible = "qcom,pcie-ipq8064-v2", .data = &cfg_2_1_0 },
 	{ .compatible = "qcom,pcie-ipq8074", .data = &cfg_2_3_3 },
 	{ .compatible = "qcom,pcie-ipq8074-gen3", .data = &cfg_2_9_0 },
+	{ .compatible = "qcom,pcie-ipq9574", .data = &cfg_2_9_0 },
 	{ .compatible = "qcom,pcie-msm8996", .data = &cfg_2_3_2 },
 	{ .compatible = "qcom,pcie-qcs404", .data = &cfg_2_4_0 },
 	{ .compatible = "qcom,pcie-sa8540p", .data = &cfg_sc8280xp },

From 39a06b55df6c269315fc66c53804f8eb26502c12 Mon Sep 17 00:00:00 2001
From: Qiang Yu <quic_qianyu@quicinc.com>
Date: Thu, 31 Oct 2024 20:08:58 -0700
Subject: [PATCH 0805/1530] dt-bindings: PCI: qcom: Move OPP table to
 qcom,pcie-common.yaml
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

OPP table is a generic property that is also required by other Qcom
platforms.

Hence move this property to qcom,pcie-common.yaml so that PCIe on other
Qcom platforms is able to adjust power domain performance state and ICC
peak bandwidth according to the given PCIe generation speed and link
width.

Link: https://lore.kernel.org/r/20241101030902.579789-2-quic_qianyu@quicinc.com
Signed-off-by: Qiang Yu <quic_qianyu@quicinc.com>
[kwilczynski: commit log]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 Documentation/devicetree/bindings/pci/qcom,pcie-common.yaml | 4 ++++
 Documentation/devicetree/bindings/pci/qcom,pcie-sm8450.yaml | 4 ----
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-common.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-common.yaml
index e18900c415761..0480c58f7d998 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie-common.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie-common.yaml
@@ -81,6 +81,10 @@ properties:
   vddpe-3v3-supply:
     description: PCIe endpoint power supply
 
+  operating-points-v2: true
+  opp-table:
+    type: object
+
 required:
   - reg
   - reg-names
diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8450.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8450.yaml
index 46bd59eefadba..6e0a6d8f0ed07 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8450.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8450.yaml
@@ -70,10 +70,6 @@ properties:
       - const: msi7
       - const: global
 
-  operating-points-v2: true
-  opp-table:
-    type: object
-
   resets:
     maxItems: 1
 

From 66dc205962c5a2c03b9861cd9ccc39178b49a003 Mon Sep 17 00:00:00 2001
From: Qiang Yu <quic_qianyu@quicinc.com>
Date: Thu, 31 Oct 2024 20:08:59 -0700
Subject: [PATCH 0806/1530] dt-bindings: PCI: qcom,pcie-x1e80100: Add 'global'
 interrupt
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Qcom PCIe RC controllers are capable of generating 'global' SPI interrupt
to the host CPU. This interrupt can be used by the device driver to handle
PCIe link specific events such as Link up and Link down, which give the
driver a chance to start bus enumeration on its own when link is up and
initiate link training if link goes to a bad state. The PCIe driver can
still work without this interrupt but it will provide a nice user
experience when device gets plugged and removed.

Hence, document it in the binding along with the existing MSI interrupts.
Global interrupt is parsed as optional in driver, so adding it in bindings
will not break the ABI.

Link: https://lore.kernel.org/r/20241101030902.579789-3-quic_qianyu@quicinc.com
Signed-off-by: Qiang Yu <quic_qianyu@quicinc.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../devicetree/bindings/pci/qcom,pcie-x1e80100.yaml      | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-x1e80100.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-x1e80100.yaml
index a9db0a2315639..257068a182649 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie-x1e80100.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie-x1e80100.yaml
@@ -47,9 +47,10 @@ properties:
 
   interrupts:
     minItems: 8
-    maxItems: 8
+    maxItems: 9
 
   interrupt-names:
+    minItems: 8
     items:
       - const: msi0
       - const: msi1
@@ -59,6 +60,7 @@ properties:
       - const: msi5
       - const: msi6
       - const: msi7
+      - const: global
 
   resets:
     minItems: 1
@@ -130,9 +132,10 @@ examples:
                          <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+                         <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
             interrupt-names = "msi0", "msi1", "msi2", "msi3",
-                              "msi4", "msi5", "msi6", "msi7";
+                              "msi4", "msi5", "msi6", "msi7", "global";
             #interrupt-cells = <1>;
             interrupt-map-mask = <0 0 0 0x7>;
             interrupt-map = <0 0 0 1 &intc 0 0 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */

From 22a9120479a40a56c13c5e473a0100fad2e017c0 Mon Sep 17 00:00:00 2001
From: Siddharth Vadapalli <s-vadapalli@ti.com>
Date: Mon, 4 Nov 2024 13:14:20 +0530
Subject: [PATCH 0807/1530] PCI: j721e: Deassert PERST# after a delay of
 PCIE_T_PVPERL_MS milliseconds
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

According to Section 2.2 of the PCI Express Card Electromechanical
Specification (Revision 5.1), in order to ensure that the power and the
reference clock are stable, PERST# has to be deasserted after a delay of
100 milliseconds (TPVPERL).

Currently, it is being assumed that the power is already stable, which
is not necessarily true.

Hence, change the delay to PCIE_T_PVPERL_MS to guarantee that power and
reference clock are stable.

Fixes: f3e25911a430 ("PCI: j721e: Add TI J721E PCIe driver")
Fixes: f96b69713733 ("PCI: j721e: Use T_PERST_CLK_US macro")
Link: https://lore.kernel.org/r/20241104074420.1862932-1-s-vadapalli@ti.com
Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/cadence/pci-j721e.c | 26 ++++++++++------------
 1 file changed, 12 insertions(+), 14 deletions(-)

diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c
index c9f3103d68e18..dc10d51c13528 100644
--- a/drivers/pci/controller/cadence/pci-j721e.c
+++ b/drivers/pci/controller/cadence/pci-j721e.c
@@ -583,15 +583,14 @@ static int j721e_pcie_probe(struct platform_device *pdev)
 		pcie->refclk = clk;
 
 		/*
-		 * The "Power Sequencing and Reset Signal Timings" table of the
-		 * PCI Express Card Electromechanical Specification, Revision
-		 * 5.1, Section 2.9.2, Symbol "T_PERST-CLK", indicates PERST#
-		 * should be deasserted after minimum of 100us once REFCLK is
-		 * stable. The REFCLK to the connector in RC mode is selected
-		 * while enabling the PHY. So deassert PERST# after 100 us.
+		 * Section 2.2 of the PCI Express Card Electromechanical
+		 * Specification (Revision 5.1) mandates that the deassertion
+		 * of the PERST# signal should be delayed by 100 ms (TPVPERL).
+		 * This shall ensure that the power and the reference clock
+		 * are stable.
 		 */
 		if (gpiod) {
-			fsleep(PCIE_T_PERST_CLK_US);
+			msleep(PCIE_T_PVPERL_MS);
 			gpiod_set_value_cansleep(gpiod, 1);
 		}
 
@@ -682,15 +681,14 @@ static int j721e_pcie_resume_noirq(struct device *dev)
 			return ret;
 
 		/*
-		 * The "Power Sequencing and Reset Signal Timings" table of the
-		 * PCI Express Card Electromechanical Specification, Revision
-		 * 5.1, Section 2.9.2, Symbol "T_PERST-CLK", indicates PERST#
-		 * should be deasserted after minimum of 100us once REFCLK is
-		 * stable. The REFCLK to the connector in RC mode is selected
-		 * while enabling the PHY. So deassert PERST# after 100 us.
+		 * Section 2.2 of the PCI Express Card Electromechanical
+		 * Specification (Revision 5.1) mandates that the deassertion
+		 * of the PERST# signal should be delayed by 100 ms (TPVPERL).
+		 * This shall ensure that the power and the reference clock
+		 * are stable.
 		 */
 		if (pcie->reset_gpio) {
-			fsleep(PCIE_T_PERST_CLK_US);
+			msleep(PCIE_T_PVPERL_MS);
 			gpiod_set_value_cansleep(pcie->reset_gpio, 1);
 		}
 

From 1362af92bcf5f18cdb25c095e3ba5155b823f570 Mon Sep 17 00:00:00 2001
From: Qiang Yu <quic_qianyu@quicinc.com>
Date: Thu, 31 Oct 2024 20:09:00 -0700
Subject: [PATCH 0808/1530] PCI: qcom: Remove BDF2SID mapping config for
 SC8280X family SoC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The SC8280XP PCIe devicetree nodes do not specify an 'iommu-map' so
the config_sid() callback is effectively a no-op.

Hence introduce a new ops struct, namely ops_1_21_0 which is same as
ops_1_9_0 except that it doesn't have config_sid() callback to clean
it up.

Link: https://lore.kernel.org/r/20241101030902.579789-4-quic_qianyu@quicinc.com
Signed-off-by: Qiang Yu <quic_qianyu@quicinc.com>
[kwilczynski: commit log]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/dwc/pcie-qcom.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 07286fb9adc1c..4448ca54bdda7 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -1365,6 +1365,16 @@ static const struct qcom_pcie_ops ops_1_9_0 = {
 	.config_sid = qcom_pcie_config_sid_1_9_0,
 };
 
+/* Qcom IP rev.: 1.21.0  Synopsys IP rev.: 5.60a */
+static const struct qcom_pcie_ops ops_1_21_0 = {
+	.get_resources = qcom_pcie_get_resources_2_7_0,
+	.init = qcom_pcie_init_2_7_0,
+	.post_init = qcom_pcie_post_init_2_7_0,
+	.host_post_init = qcom_pcie_host_post_init_2_7_0,
+	.deinit = qcom_pcie_deinit_2_7_0,
+	.ltssm_enable = qcom_pcie_2_3_2_ltssm_enable,
+};
+
 /* Qcom IP rev.: 2.9.0  Synopsys IP rev.: 5.00a */
 static const struct qcom_pcie_ops ops_2_9_0 = {
 	.get_resources = qcom_pcie_get_resources_2_9_0,
@@ -1412,7 +1422,7 @@ static const struct qcom_pcie_cfg cfg_2_9_0 = {
 };
 
 static const struct qcom_pcie_cfg cfg_sc8280xp = {
-	.ops = &ops_1_9_0,
+	.ops = &ops_1_21_0,
 	.no_l0s = true,
 };
 

From fba6045161d686adc102b6ef71b2fd1e5f90a616 Mon Sep 17 00:00:00 2001
From: Qiang Yu <quic_qianyu@quicinc.com>
Date: Thu, 31 Oct 2024 20:09:01 -0700
Subject: [PATCH 0809/1530] PCI: qcom: Disable ASPM L0s for X1E80100
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, the cfg_1_9_0 which is being used for X1E80100 doesn't disable
ASPM L0s. However, hardware team recommends to disable L0s as the PHY init
sequence is not tuned support L0s. Hence reuse cfg_sc8280xp for X1E80100.

Note that the config_sid() callback is not present in cfg_sc8280xp, don't
concern about this because config_sid() callback is originally a no-op
for X1E80100.

Fixes: 6d0c39324c5f ("PCI: qcom: Add X1E80100 PCIe support")
Link: https://lore.kernel.org/r/20241101030902.579789-5-quic_qianyu@quicinc.com
Signed-off-by: Qiang Yu <quic_qianyu@quicinc.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Cc: <stable@vger.kernel.org> # 6.9
---
 drivers/pci/controller/dwc/pcie-qcom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 4448ca54bdda7..dc102d8bd58c6 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -1856,7 +1856,7 @@ static const struct of_device_id qcom_pcie_match[] = {
 	{ .compatible = "qcom,pcie-sm8450-pcie0", .data = &cfg_1_9_0 },
 	{ .compatible = "qcom,pcie-sm8450-pcie1", .data = &cfg_1_9_0 },
 	{ .compatible = "qcom,pcie-sm8550", .data = &cfg_1_9_0 },
-	{ .compatible = "qcom,pcie-x1e80100", .data = &cfg_1_9_0 },
+	{ .compatible = "qcom,pcie-x1e80100", .data = &cfg_sc8280xp },
 	{ }
 };
 

From ade7da14954a5d1003ceb316a230189c445ba357 Mon Sep 17 00:00:00 2001
From: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Date: Mon, 4 Nov 2024 12:49:34 +0100
Subject: [PATCH 0810/1530] PCI: mediatek-gen3: Add support for setting
 max-link-speed limit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for respecting the max-link-speed devicetree property,
forcing a maximum speed (Gen) for a PCI-Express port.

Since the MediaTek PCIe Gen3 controllers also expose the maximum
supported link speed in the PCIE_BASE_CFG register, if property
max-link-speed is specified in devicetree, validate it against the
controller capabilities and proceed setting the limitations only
if the wanted Gen is lower than the maximum one that is supported
by the controller itself (otherwise it makes no sense!).

Link: https://lore.kernel.org/r/20241104114935.172908-2-angelogioacchino.delregno@collabora.com
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
[kwilczynski: change dev_dbg() to dev_info() and update message wording]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Fei Shao <fshao@chromium.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/pcie-mediatek-gen3.c | 55 ++++++++++++++++++++-
 1 file changed, 53 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c
index 66ce4b5d309bb..1d208d58e94a1 100644
--- a/drivers/pci/controller/pcie-mediatek-gen3.c
+++ b/drivers/pci/controller/pcie-mediatek-gen3.c
@@ -28,7 +28,11 @@
 
 #include "../pci.h"
 
+#define PCIE_BASE_CFG_REG		0x14
+#define PCIE_BASE_CFG_SPEED		GENMASK(15, 8)
+
 #define PCIE_SETTING_REG		0x80
+#define PCIE_SETTING_GEN_SUPPORT	GENMASK(14, 12)
 #define PCIE_PCI_IDS_1			0x9c
 #define PCI_CLASS(class)		(class << 8)
 #define PCIE_RC_MODE			BIT(0)
@@ -125,6 +129,9 @@
 
 struct mtk_gen3_pcie;
 
+#define PCIE_CONF_LINK2_CTL_STS		(PCIE_CFG_OFFSET_ADDR + 0xb0)
+#define PCIE_CONF_LINK2_LCR2_LINK_SPEED	GENMASK(3, 0)
+
 /**
  * struct mtk_gen3_pcie_pdata - differentiate between host generations
  * @power_up: pcie power_up callback
@@ -160,6 +167,7 @@ struct mtk_msi_set {
  * @phy: PHY controller block
  * @clks: PCIe clocks
  * @num_clks: PCIe clocks count for this port
+ * @max_link_speed: Maximum link speed (PCIe Gen) for this port
  * @irq: PCIe controller interrupt number
  * @saved_irq_state: IRQ enable state saved at suspend time
  * @irq_lock: lock protecting IRQ register access
@@ -180,6 +188,7 @@ struct mtk_gen3_pcie {
 	struct phy *phy;
 	struct clk_bulk_data *clks;
 	int num_clks;
+	u8 max_link_speed;
 
 	int irq;
 	u32 saved_irq_state;
@@ -381,11 +390,27 @@ static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie)
 	int err;
 	u32 val;
 
-	/* Set as RC mode */
+	/* Set as RC mode and set controller PCIe Gen speed restriction, if any */
 	val = readl_relaxed(pcie->base + PCIE_SETTING_REG);
 	val |= PCIE_RC_MODE;
+	if (pcie->max_link_speed) {
+		val &= ~PCIE_SETTING_GEN_SUPPORT;
+
+		/* Can enable link speed support only from Gen2 onwards */
+		if (pcie->max_link_speed >= 2)
+			val |= FIELD_PREP(PCIE_SETTING_GEN_SUPPORT,
+					  GENMASK(pcie->max_link_speed - 2, 0));
+	}
 	writel_relaxed(val, pcie->base + PCIE_SETTING_REG);
 
+	/* Set Link Control 2 (LNKCTL2) speed restriction, if any */
+	if (pcie->max_link_speed) {
+		val = readl_relaxed(pcie->base + PCIE_CONF_LINK2_CTL_STS);
+		val &= ~PCIE_CONF_LINK2_LCR2_LINK_SPEED;
+		val |= FIELD_PREP(PCIE_CONF_LINK2_LCR2_LINK_SPEED, pcie->max_link_speed);
+		writel_relaxed(val, pcie->base + PCIE_CONF_LINK2_CTL_STS);
+	}
+
 	/* Set class code */
 	val = readl_relaxed(pcie->base + PCIE_PCI_IDS_1);
 	val &= ~GENMASK(31, 8);
@@ -1004,9 +1029,21 @@ static void mtk_pcie_power_down(struct mtk_gen3_pcie *pcie)
 	reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, pcie->phy_resets);
 }
 
+static int mtk_pcie_get_controller_max_link_speed(struct mtk_gen3_pcie *pcie)
+{
+	u32 val;
+	int ret;
+
+	val = readl_relaxed(pcie->base + PCIE_BASE_CFG_REG);
+	val = FIELD_GET(PCIE_BASE_CFG_SPEED, val);
+	ret = fls(val);
+
+	return ret > 0 ? ret : -EINVAL;
+}
+
 static int mtk_pcie_setup(struct mtk_gen3_pcie *pcie)
 {
-	int err;
+	int err, max_speed;
 
 	err = mtk_pcie_parse_port(pcie);
 	if (err)
@@ -1031,6 +1068,20 @@ static int mtk_pcie_setup(struct mtk_gen3_pcie *pcie)
 	if (err)
 		return err;
 
+	err = of_pci_get_max_link_speed(pcie->dev->of_node);
+	if (err) {
+		/* Get the maximum speed supported by the controller */
+		max_speed = mtk_pcie_get_controller_max_link_speed(pcie);
+
+		/* Set max_link_speed only if the controller supports it */
+		if (max_speed >= 0 && max_speed <= err) {
+			pcie->max_link_speed = err;
+			dev_info(pcie->dev,
+				 "maximum controller link speed Gen%d, overriding to Gen%u",
+				 max_speed, pcie->max_link_speed);
+		}
+	}
+
 	/* Try link up */
 	err = mtk_pcie_startup_port(pcie);
 	if (err)

From 13e17c9ff49119aa2826dbf1e130f34d4d7a55d9 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 28 Oct 2024 12:36:19 -0700
Subject: [PATCH 0811/1530] perf build: Make libunwind opt-in rather than
 opt-out

Having multiple unwinding libraries makes the perf code harder to
understand and we have unused/untested code paths.

Perf made BPF support an opt-out rather than opt-in feature. As libbpf
has a libelf dependency, elfutils that provides libelf will also
provide libdw. When libdw is present perf will use libdw unwinding
rather than libunwind unwinding even if libunwind support is compiled
in.

Rather than have libunwind built into perf and never used, explicitly
disable the support and make it opt-in.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: https://lore.kernel.org/r/20241028193619.247727-1-irogers@google.com
Closes: https://lore.kernel.org/linux-perf-users/CAP-5=fUXkp-d7gkzX4eF+nbjb2978dZsiHZ9abGHN=BN1qAcbg@mail.gmail.com/
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Makefile.config | 4 ++++
 tools/perf/Makefile.perf   | 2 +-
 tools/perf/tests/make      | 6 +++---
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 8da6d91b7ad51..e68f0be259a19 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -95,6 +95,10 @@ ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390 csky riscv loon
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
+ifneq ($(LIBUNWIND),1)
+  NO_LIBUNWIND := 1
+endif
+
 ifeq ($(LIBUNWIND_LIBS),)
   NO_LIBUNWIND := 1
 endif
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index b4dee7c20ed15..d74241a151313 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -52,7 +52,7 @@ include ../scripts/utilities.mak
 #
 # Define NO_LIBELF if you do not want libelf dependency (e.g. cross-builds)
 #
-# Define NO_LIBUNWIND if you do not want libunwind dependency for dwarf
+# Define LIBUNWIND if you do not want libunwind dependency for dwarf
 # backtrace post unwind.
 #
 # Define NO_BACKTRACE if you do not want stack backtrace debug feature
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index a5040772043f6..a7fcbd589752a 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -81,7 +81,7 @@ make_no_gtk2        := NO_GTK2=1
 make_no_ui          := NO_SLANG=1 NO_GTK2=1
 make_no_demangle    := NO_DEMANGLE=1
 make_no_libelf      := NO_LIBELF=1
-make_no_libunwind   := NO_LIBUNWIND=1
+make_libunwind      := LIBUNWIND=1
 make_no_libdw_dwarf_unwind := NO_LIBDW_DWARF_UNWIND=1
 make_no_backtrace   := NO_BACKTRACE=1
 make_no_libcapstone := NO_CAPSTONE=1
@@ -121,7 +121,7 @@ make_static         := LDFLAGS=-static NO_PERF_READ_VDSO32=1 NO_PERF_READ_VDSOX3
 
 # all the NO_* variable combined
 make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_GTK2=1
-make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
+make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_BACKTRACE=1
 make_minimal        += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
 make_minimal        += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1
 make_minimal        += NO_LIBCRYPTO=1 NO_SDT=1 NO_JVMTI=1 NO_LIBZSTD=1
@@ -153,7 +153,7 @@ run += make_no_gtk2
 run += make_no_ui
 run += make_no_demangle
 run += make_no_libelf
-run += make_no_libunwind
+run += make_libunwind
 run += make_no_libdw_dwarf_unwind
 run += make_no_backtrace
 run += make_no_libcapstone

From 6e59bcc9c8adec9a5bbedfa95a89946c56c510d9 Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Wed, 30 Oct 2024 16:04:24 +0000
Subject: [PATCH 0812/1530] rust: add static_branch_unlikely for
 static_key_false

Add just enough support for static key so that we can use it from
tracepoints. Tracepoints rely on `static_branch_unlikely` with a `struct
static_key_false`, so we add the same functionality to Rust.

This patch only provides a generic implementation without code patching
(matching the one used when CONFIG_JUMP_LABEL is disabled). Later
patches add support for inline asm implementations that use runtime
patching.

When CONFIG_JUMP_LABEL is unset, `static_key_count` is a static inline
function, so a Rust helper is defined for `static_key_count` in this
case. If Rust is compiled with LTO, this call should get inlined. The
helper can be eliminated once we have the necessary inline asm to make
atomic operations from Rust.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Alex Gaynor <alex.gaynor@gmail.com>
Cc: Wedson Almeida Filho <wedsonaf@gmail.com>
Cc: " =?utf-8?q?Bj=C3=B6rn_Roy_Baron?= " <bjorn3_gh@protonmail.com>
Cc: Benno Lossin <benno.lossin@proton.me>
Cc: Andreas Hindborg <a.hindborg@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Uros Bizjak <ubizjak@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Fuad Tabba <tabba@google.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Anup Patel <apatel@ventanamicro.com>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Conor Dooley <conor.dooley@microchip.com>
Cc: Samuel Holland <samuel.holland@sifive.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tianrui Zhao <zhaotianrui@loongson.cn>
Link: https://lore.kernel.org/20241030-tracepoint-v12-1-eec7f0f8ad22@google.com
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Reviewed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 rust/bindings/bindings_helper.h |  1 +
 rust/helpers/helpers.c          |  1 +
 rust/helpers/jump_label.c       | 14 ++++++++++++++
 rust/kernel/jump_label.rs       | 30 ++++++++++++++++++++++++++++++
 rust/kernel/lib.rs              |  1 +
 5 files changed, 47 insertions(+)
 create mode 100644 rust/helpers/jump_label.c
 create mode 100644 rust/kernel/jump_label.rs

diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index ae82e9c941afa..e0846e7e93e6e 100644
--- a/rust/bindings/bindings_helper.h
+++ b/rust/bindings/bindings_helper.h
@@ -14,6 +14,7 @@
 #include <linux/ethtool.h>
 #include <linux/firmware.h>
 #include <linux/jiffies.h>
+#include <linux/jump_label.h>
 #include <linux/mdio.h>
 #include <linux/phy.h>
 #include <linux/refcount.h>
diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c
index 30f40149f3a96..17e1b60d178fd 100644
--- a/rust/helpers/helpers.c
+++ b/rust/helpers/helpers.c
@@ -12,6 +12,7 @@
 #include "build_assert.c"
 #include "build_bug.c"
 #include "err.c"
+#include "jump_label.c"
 #include "kunit.c"
 #include "mutex.c"
 #include "page.c"
diff --git a/rust/helpers/jump_label.c b/rust/helpers/jump_label.c
new file mode 100644
index 0000000000000..fc1f1e0df08e7
--- /dev/null
+++ b/rust/helpers/jump_label.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (C) 2024 Google LLC.
+ */
+
+#include <linux/jump_label.h>
+
+#ifndef CONFIG_JUMP_LABEL
+int rust_helper_static_key_count(struct static_key *key)
+{
+	return static_key_count(key);
+}
+#endif
diff --git a/rust/kernel/jump_label.rs b/rust/kernel/jump_label.rs
new file mode 100644
index 0000000000000..4b7655b2a0226
--- /dev/null
+++ b/rust/kernel/jump_label.rs
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2024 Google LLC.
+
+//! Logic for static keys.
+//!
+//! C header: [`include/linux/jump_label.h`](srctree/include/linux/jump_label.h).
+
+/// Branch based on a static key.
+///
+/// Takes three arguments:
+///
+/// * `key` - the path to the static variable containing the `static_key`.
+/// * `keytyp` - the type of `key`.
+/// * `field` - the name of the field of `key` that contains the `static_key`.
+///
+/// # Safety
+///
+/// The macro must be used with a real static key defined by C.
+#[macro_export]
+macro_rules! static_branch_unlikely {
+    ($key:path, $keytyp:ty, $field:ident) => {{
+        let _key: *const $keytyp = ::core::ptr::addr_of!($key);
+        let _key: *const $crate::bindings::static_key_false = ::core::ptr::addr_of!((*_key).$field);
+        let _key: *const $crate::bindings::static_key = _key.cast();
+
+        $crate::bindings::static_key_count(_key.cast_mut()) > 0
+    }};
+}
+pub use static_branch_unlikely;
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index b5f4b3ce6b482..708ff817ccc3b 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -36,6 +36,7 @@ pub mod error;
 pub mod firmware;
 pub mod init;
 pub mod ioctl;
+pub mod jump_label;
 #[cfg(CONFIG_KUNIT)]
 pub mod kunit;
 pub mod list;

From ad37bcd965fda43f34cf5cc051f5d310880bd1e7 Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Wed, 30 Oct 2024 16:04:25 +0000
Subject: [PATCH 0813/1530] rust: add tracepoint support

Make it possible to have Rust code call into tracepoints defined by C
code. It is still required that the tracepoint is declared in a C
header, and that this header is included in the input to bindgen.

Instead of calling __DO_TRACE directly, the exported rust_do_trace_
function calls an inline helper function. This is because the `cond`
argument does not exist at the callsite of DEFINE_RUST_DO_TRACE.

__DECLARE_TRACE always emits an inline static and an extern declaration
that is only used when CREATE_RUST_TRACE_POINTS is set. These should not
end up in the final binary so it is not a problem that they sometimes
are emitted without a user.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Alex Gaynor <alex.gaynor@gmail.com>
Cc: Wedson Almeida Filho <wedsonaf@gmail.com>
Cc: " =?utf-8?q?Bj=C3=B6rn_Roy_Baron?= " <bjorn3_gh@protonmail.com>
Cc: Benno Lossin <benno.lossin@proton.me>
Cc: Andreas Hindborg <a.hindborg@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Uros Bizjak <ubizjak@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Fuad Tabba <tabba@google.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Anup Patel <apatel@ventanamicro.com>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Conor Dooley <conor.dooley@microchip.com>
Cc: Samuel Holland <samuel.holland@sifive.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tianrui Zhao <zhaotianrui@loongson.cn>
Link: https://lore.kernel.org/20241030-tracepoint-v12-2-eec7f0f8ad22@google.com
Reviewed-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/tracepoint.h      | 28 ++++++++++++++++++-
 include/trace/define_trace.h    | 12 ++++++++
 rust/bindings/bindings_helper.h |  1 +
 rust/kernel/lib.rs              |  1 +
 rust/kernel/tracepoint.rs       | 49 +++++++++++++++++++++++++++++++++
 5 files changed, 90 insertions(+), 1 deletion(-)
 create mode 100644 rust/kernel/tracepoint.rs

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 0dc67fad706c6..84c4924e499f0 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -225,6 +225,18 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 			preempt_enable_notrace();			\
 	} while (0)
 
+/*
+ * Declare an exported function that Rust code can call to trigger this
+ * tracepoint. This function does not include the static branch; that is done
+ * in Rust to avoid a function call when the tracepoint is disabled.
+ */
+#define DEFINE_RUST_DO_TRACE(name, proto, args)
+#define __DEFINE_RUST_DO_TRACE(name, proto, args)			\
+	notrace void rust_do_trace_##name(proto)			\
+	{								\
+		__rust_do_trace_##name(args);				\
+	}
+
 /*
  * Make sure the alignment of the structure in the __tracepoints section will
  * not add unwanted padding between the beginning of the section and the
@@ -240,6 +252,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 	extern int __traceiter_##name(data_proto);			\
 	DECLARE_STATIC_CALL(tp_func_##name, __traceiter_##name);	\
 	extern struct tracepoint __tracepoint_##name;			\
+	extern void rust_do_trace_##name(proto);			\
 	static inline int						\
 	register_trace_##name(void (*probe)(data_proto), void *data)	\
 	{								\
@@ -271,6 +284,12 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 
 #define __DECLARE_TRACE(name, proto, args, cond, data_proto)		\
 	__DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), cond, PARAMS(data_proto)) \
+	static inline void __rust_do_trace_##name(proto)		\
+	{								\
+		__DO_TRACE(name,					\
+			TP_ARGS(args),					\
+			TP_CONDITION(cond), 0);				\
+	}								\
 	static inline void trace_##name(proto)				\
 	{								\
 		if (static_branch_unlikely(&__tracepoint_##name.key))	\
@@ -285,6 +304,12 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 
 #define __DECLARE_TRACE_SYSCALL(name, proto, args, cond, data_proto)	\
 	__DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), cond, PARAMS(data_proto)) \
+	static inline void __rust_do_trace_##name(proto)		\
+	{								\
+		__DO_TRACE(name,					\
+			TP_ARGS(args),					\
+			TP_CONDITION(cond), 1);				\
+	}								\
 	static inline void trace_##name(proto)				\
 	{								\
 		if (static_branch_unlikely(&__tracepoint_##name.key))	\
@@ -339,7 +364,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 	void __probestub_##_name(void *__data, proto)			\
 	{								\
 	}								\
-	DEFINE_STATIC_CALL(tp_func_##_name, __traceiter_##_name);
+	DEFINE_STATIC_CALL(tp_func_##_name, __traceiter_##_name);	\
+	DEFINE_RUST_DO_TRACE(_name, TP_PROTO(proto), TP_ARGS(args))
 
 #define DEFINE_TRACE(name, proto, args)		\
 	DEFINE_TRACE_FN(name, NULL, NULL, PARAMS(proto), PARAMS(args));
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
index ff5fa17a62591..0557626b6f6a4 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -76,6 +76,13 @@
 #define DECLARE_TRACE(name, proto, args)	\
 	DEFINE_TRACE(name, PARAMS(proto), PARAMS(args))
 
+/* If requested, create helpers for calling these tracepoints from Rust. */
+#ifdef CREATE_RUST_TRACE_POINTS
+#undef DEFINE_RUST_DO_TRACE
+#define DEFINE_RUST_DO_TRACE(name, proto, args)	\
+	__DEFINE_RUST_DO_TRACE(name, PARAMS(proto), PARAMS(args))
+#endif
+
 #undef TRACE_INCLUDE
 #undef __TRACE_INCLUDE
 
@@ -134,6 +141,11 @@
 # undef UNDEF_TRACE_INCLUDE_PATH
 #endif
 
+#ifdef CREATE_RUST_TRACE_POINTS
+# undef DEFINE_RUST_DO_TRACE
+# define DEFINE_RUST_DO_TRACE(name, proto, args)
+#endif
+
 /* We may be processing more files */
 #define CREATE_TRACE_POINTS
 
diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index e0846e7e93e6e..752572e638a67 100644
--- a/rust/bindings/bindings_helper.h
+++ b/rust/bindings/bindings_helper.h
@@ -20,6 +20,7 @@
 #include <linux/refcount.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/tracepoint.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
 
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 708ff817ccc3b..55f81f49024e0 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -54,6 +54,7 @@ pub mod str;
 pub mod sync;
 pub mod task;
 pub mod time;
+pub mod tracepoint;
 pub mod types;
 pub mod uaccess;
 pub mod workqueue;
diff --git a/rust/kernel/tracepoint.rs b/rust/kernel/tracepoint.rs
new file mode 100644
index 0000000000000..c6e80aa99e8e1
--- /dev/null
+++ b/rust/kernel/tracepoint.rs
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2024 Google LLC.
+
+//! Logic for tracepoints.
+
+/// Declare the Rust entry point for a tracepoint.
+///
+/// This macro generates an unsafe function that calls into C, and its safety requirements will be
+/// whatever the relevant C code requires. To document these safety requirements, you may add
+/// doc-comments when invoking the macro.
+#[macro_export]
+macro_rules! declare_trace {
+    ($($(#[$attr:meta])* $pub:vis unsafe fn $name:ident($($argname:ident : $argtyp:ty),* $(,)?);)*) => {$(
+        $( #[$attr] )*
+        #[inline(always)]
+        $pub unsafe fn $name($($argname : $argtyp),*) {
+            #[cfg(CONFIG_TRACEPOINTS)]
+            {
+                // SAFETY: It's always okay to query the static key for a tracepoint.
+                let should_trace = unsafe {
+                    $crate::macros::paste! {
+                        $crate::jump_label::static_branch_unlikely!(
+                            $crate::bindings::[< __tracepoint_ $name >],
+                            $crate::bindings::tracepoint,
+                            key
+                        )
+                    }
+                };
+
+                if should_trace {
+                    $crate::macros::paste! {
+                        // SAFETY: The caller guarantees that it is okay to call this tracepoint.
+                        unsafe { $crate::bindings::[< rust_do_trace_ $name >]($($argname),*) };
+                    }
+                }
+            }
+
+            #[cfg(not(CONFIG_TRACEPOINTS))]
+            {
+                // If tracepoints are disabled, insert a trivial use of each argument
+                // to avoid unused argument warnings.
+                $( let _unused = $argname; )*
+            }
+        }
+    )*}
+}
+
+pub use declare_trace;

From 91d39024e1b02914cc5e2dbc137908e29b269ce4 Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Wed, 30 Oct 2024 16:04:26 +0000
Subject: [PATCH 0814/1530] rust: samples: add tracepoint to Rust sample

This updates the Rust printing sample to invoke a tracepoint. This
ensures that we have a user in-tree from the get-go even though the
patch is being merged before its real user.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Alex Gaynor <alex.gaynor@gmail.com>
Cc: Wedson Almeida Filho <wedsonaf@gmail.com>
Cc: Gary Guo <gary@garyguo.net>
Cc: " =?utf-8?q?Bj=C3=B6rn_Roy_Baron?= " <bjorn3_gh@protonmail.com>
Cc: Benno Lossin <benno.lossin@proton.me>
Cc: Andreas Hindborg <a.hindborg@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Uros Bizjak <ubizjak@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Fuad Tabba <tabba@google.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Anup Patel <apatel@ventanamicro.com>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Conor Dooley <conor.dooley@microchip.com>
Cc: Samuel Holland <samuel.holland@sifive.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tianrui Zhao <zhaotianrui@loongson.cn>
Link: https://lore.kernel.org/20241030-tracepoint-v12-3-eec7f0f8ad22@google.com
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 MAINTAINERS                        |  1 +
 include/trace/events/rust_sample.h | 31 ++++++++++++++++++++++++++++++
 rust/bindings/bindings_helper.h    |  1 +
 samples/rust/Makefile              |  3 ++-
 samples/rust/rust_print.rs         | 18 +++++++++++++++++
 samples/rust/rust_print_events.c   |  8 ++++++++
 6 files changed, 61 insertions(+), 1 deletion(-)
 create mode 100644 include/trace/events/rust_sample.h
 create mode 100644 samples/rust/rust_print_events.c

diff --git a/MAINTAINERS b/MAINTAINERS
index a097afd76ded4..a9b71411d77a1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20223,6 +20223,7 @@ C:	zulip://rust-for-linux.zulipchat.com
 P:	https://rust-for-linux.com/contributing
 T:	git https://github.com/Rust-for-Linux/linux.git rust-next
 F:	Documentation/rust/
+F:	include/trace/events/rust_sample.h
 F:	rust/
 F:	samples/rust/
 F:	scripts/*rust*
diff --git a/include/trace/events/rust_sample.h b/include/trace/events/rust_sample.h
new file mode 100644
index 0000000000000..dbc80ca2e4655
--- /dev/null
+++ b/include/trace/events/rust_sample.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Tracepoints for `samples/rust/rust_print.rs`.
+ *
+ * Copyright (C) 2024 Google, Inc.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM rust_sample
+
+#if !defined(_RUST_SAMPLE_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _RUST_SAMPLE_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(rust_sample_loaded,
+	TP_PROTO(int magic_number),
+	TP_ARGS(magic_number),
+	TP_STRUCT__entry(
+		__field(int, magic_number)
+	),
+	TP_fast_assign(
+		__entry->magic_number = magic_number;
+	),
+	TP_printk("magic=%d", __entry->magic_number)
+);
+
+#endif /* _RUST_SAMPLE_TRACE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index 752572e638a67..b072c197ce9ed 100644
--- a/rust/bindings/bindings_helper.h
+++ b/rust/bindings/bindings_helper.h
@@ -23,6 +23,7 @@
 #include <linux/tracepoint.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
+#include <trace/events/rust_sample.h>
 
 /* `bindgen` gets confused at certain things. */
 const size_t RUST_CONST_HELPER_ARCH_SLAB_MINALIGN = ARCH_SLAB_MINALIGN;
diff --git a/samples/rust/Makefile b/samples/rust/Makefile
index 03086dabbea44..f29280ec48208 100644
--- a/samples/rust/Makefile
+++ b/samples/rust/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
+ccflags-y += -I$(src)				# needed for trace events
 
 obj-$(CONFIG_SAMPLE_RUST_MINIMAL)		+= rust_minimal.o
-obj-$(CONFIG_SAMPLE_RUST_PRINT)			+= rust_print.o
+obj-$(CONFIG_SAMPLE_RUST_PRINT)			+= rust_print.o rust_print_events.o
 
 subdir-$(CONFIG_SAMPLE_RUST_HOSTPROGS)		+= hostprogs
diff --git a/samples/rust/rust_print.rs b/samples/rust/rust_print.rs
index 6eabb0d79ea3a..6d14b08cac1c2 100644
--- a/samples/rust/rust_print.rs
+++ b/samples/rust/rust_print.rs
@@ -69,6 +69,8 @@ impl kernel::Module for RustPrint {
 
         arc_print()?;
 
+        trace::trace_rust_sample_loaded(42);
+
         Ok(RustPrint)
     }
 }
@@ -78,3 +80,19 @@ impl Drop for RustPrint {
         pr_info!("Rust printing macros sample (exit)\n");
     }
 }
+
+mod trace {
+    use core::ffi::c_int;
+
+    kernel::declare_trace! {
+        /// # Safety
+        ///
+        /// Always safe to call.
+        unsafe fn rust_sample_loaded(magic: c_int);
+    }
+
+    pub(crate) fn trace_rust_sample_loaded(magic: i32) {
+        // SAFETY: Always safe to call.
+        unsafe { rust_sample_loaded(magic as c_int) }
+    }
+}
diff --git a/samples/rust/rust_print_events.c b/samples/rust/rust_print_events.c
new file mode 100644
index 0000000000000..a9169ff0edf18
--- /dev/null
+++ b/samples/rust/rust_print_events.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2024 Google LLC
+ */
+
+#define CREATE_TRACE_POINTS
+#define CREATE_RUST_TRACE_POINTS
+#include <trace/events/rust_sample.h>

From aecaf181651c91b8c89058708b065da9312a0ccd Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Wed, 30 Oct 2024 16:04:27 +0000
Subject: [PATCH 0815/1530] jump_label: adjust inline asm to be consistent

To avoid duplication of inline asm between C and Rust, we need to
import the inline asm from the relevant `jump_label.h` header into Rust.
To make that easier, this patch updates the header files to expose the
inline asm via a new ARCH_STATIC_BRANCH_ASM macro.

The header files are all updated to define a ARCH_STATIC_BRANCH_ASM that
takes the same arguments in a consistent order so that Rust can use the
same logic for every architecture.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Alex Gaynor <alex.gaynor@gmail.com>
Cc: Wedson Almeida Filho <wedsonaf@gmail.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Gary Guo <gary@garyguo.net>
Cc: " =?utf-8?q?Bj=C3=B6rn_Roy_Baron?= " <bjorn3_gh@protonmail.com>
Cc: Benno Lossin <benno.lossin@proton.me>
Cc: Andreas Hindborg <a.hindborg@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Uros Bizjak <ubizjak@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Fuad Tabba <tabba@google.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Anup Patel <apatel@ventanamicro.com>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Conor Dooley <conor.dooley@microchip.com>
Cc: Samuel Holland <samuel.holland@sifive.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tianrui Zhao <zhaotianrui@loongson.cn>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/20241030-tracepoint-v12-4-eec7f0f8ad22@google.com
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Co-developed-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com> # RISC-V
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 arch/arm/include/asm/jump_label.h       | 14 ++++---
 arch/arm64/include/asm/jump_label.h     | 20 ++++++----
 arch/loongarch/include/asm/jump_label.h | 16 +++++---
 arch/riscv/include/asm/jump_label.h     | 50 ++++++++++++++-----------
 arch/x86/include/asm/jump_label.h       | 35 +++++++----------
 5 files changed, 73 insertions(+), 62 deletions(-)

diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index e4eb54f6cd9fe..a35aba7f548cc 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -9,13 +9,17 @@
 
 #define JUMP_LABEL_NOP_SIZE 4
 
+/* This macro is also expanded on the Rust side. */
+#define ARCH_STATIC_BRANCH_ASM(key, label)		\
+	"1:\n\t"					\
+	WASM(nop) "\n\t"				\
+	".pushsection __jump_table,  \"aw\"\n\t"	\
+	".word 1b, " label ", " key "\n\t"		\
+	".popsection\n\t"				\
+
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm goto("1:\n\t"
-		 WASM(nop) "\n\t"
-		 ".pushsection __jump_table,  \"aw\"\n\t"
-		 ".word 1b, %l[l_yes], %c0\n\t"
-		 ".popsection\n\t"
+	asm goto(ARCH_STATIC_BRANCH_ASM("%c0", "%l[l_yes]")
 		 : :  "i" (&((char *)key)[branch]) :  : l_yes);
 
 	return false;
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index a0a5bbae7229e..424ed421cd979 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -19,10 +19,14 @@
 #define JUMP_TABLE_ENTRY(key, label)			\
 	".pushsection	__jump_table, \"aw\"\n\t"	\
 	".align		3\n\t"				\
-	".long		1b - ., %l["#label"] - .\n\t"	\
-	".quad		%c0 - .\n\t"			\
-	".popsection\n\t"				\
-	:  :  "i"(key) :  : label
+	".long		1b - ., " label " - .\n\t"	\
+	".quad		" key " - .\n\t"		\
+	".popsection\n\t"
+
+/* This macro is also expanded on the Rust side. */
+#define ARCH_STATIC_BRANCH_ASM(key, label)		\
+	"1:	nop\n\t"				\
+	JUMP_TABLE_ENTRY(key, label)
 
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
@@ -30,8 +34,8 @@ static __always_inline bool arch_static_branch(struct static_key * const key,
 	char *k = &((char *)key)[branch];
 
 	asm goto(
-		"1:	nop					\n\t"
-		JUMP_TABLE_ENTRY(k, l_yes)
+		ARCH_STATIC_BRANCH_ASM("%c0", "%l[l_yes]")
+		:  :  "i"(k) :  : l_yes
 		);
 
 	return false;
@@ -43,9 +47,11 @@ static __always_inline bool arch_static_branch_jump(struct static_key * const ke
 						    const bool branch)
 {
 	char *k = &((char *)key)[branch];
+
 	asm goto(
 		"1:	b		%l[l_yes]		\n\t"
-		JUMP_TABLE_ENTRY(k, l_yes)
+		JUMP_TABLE_ENTRY("%c0", "%l[l_yes]")
+		:  :  "i"(k) :  : l_yes
 		);
 	return false;
 l_yes:
diff --git a/arch/loongarch/include/asm/jump_label.h b/arch/loongarch/include/asm/jump_label.h
index 29acfe3de3faa..8a924bd69d196 100644
--- a/arch/loongarch/include/asm/jump_label.h
+++ b/arch/loongarch/include/asm/jump_label.h
@@ -13,18 +13,22 @@
 
 #define JUMP_LABEL_NOP_SIZE	4
 
-#define JUMP_TABLE_ENTRY				\
+/* This macro is also expanded on the Rust side. */
+#define JUMP_TABLE_ENTRY(key, label)			\
 	 ".pushsection	__jump_table, \"aw\"	\n\t"	\
 	 ".align	3			\n\t"	\
-	 ".long		1b - ., %l[l_yes] - .	\n\t"	\
-	 ".quad		%0 - .			\n\t"	\
+	 ".long		1b - ., " label " - .	\n\t"	\
+	 ".quad		" key " - .		\n\t"	\
 	 ".popsection				\n\t"
 
+#define ARCH_STATIC_BRANCH_ASM(key, label)		\
+	"1:	nop				\n\t"	\
+	JUMP_TABLE_ENTRY(key, label)
+
 static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
 {
 	asm goto(
-		"1:	nop			\n\t"
-		JUMP_TABLE_ENTRY
+		ARCH_STATIC_BRANCH_ASM("%0", "%l[l_yes]")
 		:  :  "i"(&((char *)key)[branch]) :  : l_yes);
 
 	return false;
@@ -37,7 +41,7 @@ static __always_inline bool arch_static_branch_jump(struct static_key * const ke
 {
 	asm goto(
 		"1:	b	%l[l_yes]	\n\t"
-		JUMP_TABLE_ENTRY
+		JUMP_TABLE_ENTRY("%0", "%l[l_yes]")
 		:  :  "i"(&((char *)key)[branch]) :  : l_yes);
 
 	return false;
diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h
index 1c768d02bd0c2..87a71cc6d146c 100644
--- a/arch/riscv/include/asm/jump_label.h
+++ b/arch/riscv/include/asm/jump_label.h
@@ -16,21 +16,28 @@
 
 #define JUMP_LABEL_NOP_SIZE 4
 
+#define JUMP_TABLE_ENTRY(key, label)			\
+	".pushsection	__jump_table, \"aw\"	\n\t"	\
+	".align		" RISCV_LGPTR "		\n\t"	\
+	".long		1b - ., " label " - .	\n\t"	\
+	"" RISCV_PTR "	" key " - .		\n\t"	\
+	".popsection				\n\t"
+
+/* This macro is also expanded on the Rust side. */
+#define ARCH_STATIC_BRANCH_ASM(key, label)		\
+	"	.align		2		\n\t"	\
+	"	.option push			\n\t"	\
+	"	.option norelax			\n\t"	\
+	"	.option norvc			\n\t"	\
+	"1:	nop				\n\t"	\
+	"	.option pop			\n\t"	\
+	JUMP_TABLE_ENTRY(key, label)
+
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
 {
 	asm goto(
-		"	.align		2			\n\t"
-		"	.option push				\n\t"
-		"	.option norelax				\n\t"
-		"	.option norvc				\n\t"
-		"1:	nop					\n\t"
-		"	.option pop				\n\t"
-		"	.pushsection	__jump_table, \"aw\"	\n\t"
-		"	.align		" RISCV_LGPTR "		\n\t"
-		"	.long		1b - ., %l[label] - .	\n\t"
-		"	" RISCV_PTR "	%0 - .			\n\t"
-		"	.popsection				\n\t"
+		ARCH_STATIC_BRANCH_ASM("%0", "%l[label]")
 		:  :  "i"(&((char *)key)[branch]) :  : label);
 
 	return false;
@@ -38,21 +45,20 @@ static __always_inline bool arch_static_branch(struct static_key * const key,
 	return true;
 }
 
+#define ARCH_STATIC_BRANCH_JUMP_ASM(key, label)		\
+	"	.align		2		\n\t"	\
+	"	.option push			\n\t"	\
+	"	.option norelax			\n\t"	\
+	"	.option norvc			\n\t"	\
+	"1:	j	" label "		\n\t" \
+	"	.option pop			\n\t"	\
+	JUMP_TABLE_ENTRY(key, label)
+
 static __always_inline bool arch_static_branch_jump(struct static_key * const key,
 						    const bool branch)
 {
 	asm goto(
-		"	.align		2			\n\t"
-		"	.option push				\n\t"
-		"	.option norelax				\n\t"
-		"	.option norvc				\n\t"
-		"1:	j		%l[label]		\n\t"
-		"	.option pop				\n\t"
-		"	.pushsection	__jump_table, \"aw\"	\n\t"
-		"	.align		" RISCV_LGPTR "		\n\t"
-		"	.long		1b - ., %l[label] - .	\n\t"
-		"	" RISCV_PTR "	%0 - .			\n\t"
-		"	.popsection				\n\t"
+		ARCH_STATIC_BRANCH_JUMP_ASM("%0", "%l[label]")
 		:  :  "i"(&((char *)key)[branch]) :  : label);
 
 	return false;
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index cbbef32517f00..3f1c1d6c0da12 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -12,35 +12,28 @@
 #include <linux/stringify.h>
 #include <linux/types.h>
 
-#define JUMP_TABLE_ENTRY				\
+#define JUMP_TABLE_ENTRY(key, label)			\
 	".pushsection __jump_table,  \"aw\" \n\t"	\
 	_ASM_ALIGN "\n\t"				\
 	".long 1b - . \n\t"				\
-	".long %l[l_yes] - . \n\t"			\
-	_ASM_PTR "%c0 + %c1 - .\n\t"			\
+	".long " label " - . \n\t"			\
+	_ASM_PTR " " key " - . \n\t"			\
 	".popsection \n\t"
 
+/* This macro is also expanded on the Rust side. */
 #ifdef CONFIG_HAVE_JUMP_LABEL_HACK
-
-static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
-{
-	asm goto("1:"
-		"jmp %l[l_yes] # objtool NOPs this \n\t"
-		JUMP_TABLE_ENTRY
-		: :  "i" (key), "i" (2 | branch) : : l_yes);
-
-	return false;
-l_yes:
-	return true;
-}
-
+#define ARCH_STATIC_BRANCH_ASM(key, label)		\
+	"1: jmp " label " # objtool NOPs this \n\t"	\
+	JUMP_TABLE_ENTRY(key " + 2", label)
 #else /* !CONFIG_HAVE_JUMP_LABEL_HACK */
+#define ARCH_STATIC_BRANCH_ASM(key, label)		\
+	"1: .byte " __stringify(BYTES_NOP5) "\n\t"	\
+	JUMP_TABLE_ENTRY(key, label)
+#endif /* CONFIG_HAVE_JUMP_LABEL_HACK */
 
 static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
 {
-	asm goto("1:"
-		".byte " __stringify(BYTES_NOP5) "\n\t"
-		JUMP_TABLE_ENTRY
+	asm goto(ARCH_STATIC_BRANCH_ASM("%c0 + %c1", "%l[l_yes]")
 		: :  "i" (key), "i" (branch) : : l_yes);
 
 	return false;
@@ -48,13 +41,11 @@ static __always_inline bool arch_static_branch(struct static_key * const key, co
 	return true;
 }
 
-#endif /* CONFIG_HAVE_JUMP_LABEL_HACK */
-
 static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
 {
 	asm goto("1:"
 		"jmp %l[l_yes]\n\t"
-		JUMP_TABLE_ENTRY
+		JUMP_TABLE_ENTRY("%c0 + %c1", "%l[l_yes]")
 		: :  "i" (key), "i" (branch) : : l_yes);
 
 	return false;

From 169484ab667788e73d1817d75c2a2c4af37dbc7f Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Wed, 30 Oct 2024 16:04:28 +0000
Subject: [PATCH 0816/1530] rust: add arch_static_branch

To allow the Rust implementation of static_key_false to use runtime code
patching instead of the generic implementation, pull in the relevant
inline assembly from the jump_label.h header by running the C
preprocessor on a .rs.S file. Build rules are added for .rs.S files.

Since the relevant inline asm has been adjusted to export the inline asm
via the ARCH_STATIC_BRANCH_ASM macro in a consistent way, the Rust side
does not need architecture specific code to pull in the asm.

It is not possible to use the existing C implementation of
arch_static_branch via a Rust helper because it passes the argument
`key` to inline assembly as an 'i' parameter. Any attempt to add a C
helper for this function will fail to compile because the value of `key`
must be known at compile-time.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Alex Gaynor <alex.gaynor@gmail.com>
Cc: Wedson Almeida Filho <wedsonaf@gmail.com>
Cc: Gary Guo <gary@garyguo.net>
Cc: " =?utf-8?q?Bj=C3=B6rn_Roy_Baron?= " <bjorn3_gh@protonmail.com>
Cc: Benno Lossin <benno.lossin@proton.me>
Cc: Andreas Hindborg <a.hindborg@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Uros Bizjak <ubizjak@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Fuad Tabba <tabba@google.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Anup Patel <apatel@ventanamicro.com>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Conor Dooley <conor.dooley@microchip.com>
Cc: Samuel Holland <samuel.holland@sifive.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tianrui Zhao <zhaotianrui@loongson.cn>
Link: https://lore.kernel.org/20241030-tracepoint-v12-5-eec7f0f8ad22@google.com
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Co-developed-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 rust/Makefile                           |  6 ++++
 rust/kernel/.gitignore                  |  3 ++
 rust/kernel/arch_static_branch_asm.rs.S |  7 ++++
 rust/kernel/jump_label.rs               | 46 ++++++++++++++++++++++++-
 rust/kernel/lib.rs                      | 35 +++++++++++++++++++
 scripts/Makefile.build                  |  9 ++++-
 6 files changed, 104 insertions(+), 2 deletions(-)
 create mode 100644 rust/kernel/.gitignore
 create mode 100644 rust/kernel/arch_static_branch_asm.rs.S

diff --git a/rust/Makefile b/rust/Makefile
index b5e0a73b78f3e..bc2a9071dd293 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -36,6 +36,8 @@ always-$(CONFIG_RUST_KERNEL_DOCTESTS) += doctests_kernel_generated_kunit.c
 obj-$(CONFIG_RUST_KERNEL_DOCTESTS) += doctests_kernel_generated.o
 obj-$(CONFIG_RUST_KERNEL_DOCTESTS) += doctests_kernel_generated_kunit.o
 
+always-$(subst y,$(CONFIG_RUST),$(CONFIG_JUMP_LABEL)) += kernel/arch_static_branch_asm.rs
+
 # Avoids running `$(RUSTC)` for the sysroot when it may not be available.
 ifdef CONFIG_RUST
 
@@ -424,4 +426,8 @@ $(obj)/kernel.o: $(src)/kernel/lib.rs $(obj)/alloc.o $(obj)/build_error.o \
     $(obj)/libmacros.so $(obj)/bindings.o $(obj)/uapi.o FORCE
 	+$(call if_changed_rule,rustc_library)
 
+ifdef CONFIG_JUMP_LABEL
+$(obj)/kernel.o: $(obj)/kernel/arch_static_branch_asm.rs
+endif
+
 endif # CONFIG_RUST
diff --git a/rust/kernel/.gitignore b/rust/kernel/.gitignore
new file mode 100644
index 0000000000000..d082731007c68
--- /dev/null
+++ b/rust/kernel/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+/arch_static_branch_asm.rs
diff --git a/rust/kernel/arch_static_branch_asm.rs.S b/rust/kernel/arch_static_branch_asm.rs.S
new file mode 100644
index 0000000000000..2afb638708db3
--- /dev/null
+++ b/rust/kernel/arch_static_branch_asm.rs.S
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/jump_label.h>
+
+// Cut here.
+
+::kernel::concat_literals!(ARCH_STATIC_BRANCH_ASM("{symb} + {off} + {branch}", "{l_yes}"))
diff --git a/rust/kernel/jump_label.rs b/rust/kernel/jump_label.rs
index 4b7655b2a0226..2f2df03a3275e 100644
--- a/rust/kernel/jump_label.rs
+++ b/rust/kernel/jump_label.rs
@@ -24,7 +24,51 @@ macro_rules! static_branch_unlikely {
         let _key: *const $crate::bindings::static_key_false = ::core::ptr::addr_of!((*_key).$field);
         let _key: *const $crate::bindings::static_key = _key.cast();
 
-        $crate::bindings::static_key_count(_key.cast_mut()) > 0
+        #[cfg(not(CONFIG_JUMP_LABEL))]
+        {
+            $crate::bindings::static_key_count(_key) > 0
+        }
+
+        #[cfg(CONFIG_JUMP_LABEL)]
+        $crate::jump_label::arch_static_branch! { $key, $keytyp, $field, false }
     }};
 }
 pub use static_branch_unlikely;
+
+/// Assert that the assembly block evaluates to a string literal.
+#[cfg(CONFIG_JUMP_LABEL)]
+const _: &str = include!(concat!(
+    env!("OBJTREE"),
+    "/rust/kernel/arch_static_branch_asm.rs"
+));
+
+#[macro_export]
+#[doc(hidden)]
+#[cfg(CONFIG_JUMP_LABEL)]
+macro_rules! arch_static_branch {
+    ($key:path, $keytyp:ty, $field:ident, $branch:expr) => {'my_label: {
+        $crate::asm!(
+            include!(concat!(env!("OBJTREE"), "/rust/kernel/arch_static_branch_asm.rs"));
+            l_yes = label {
+                break 'my_label true;
+            },
+            symb = sym $key,
+            off = const ::core::mem::offset_of!($keytyp, $field),
+            branch = const $crate::jump_label::bool_to_int($branch),
+        );
+
+        break 'my_label false;
+    }};
+}
+
+#[cfg(CONFIG_JUMP_LABEL)]
+pub use arch_static_branch;
+
+/// A helper used by inline assembly to pass a boolean to as a `const` parameter.
+///
+/// Using this function instead of a cast lets you assert that the input is a boolean, and not some
+/// other type that can also be cast to an integer.
+#[doc(hidden)]
+pub const fn bool_to_int(b: bool) -> i32 {
+    b as i32
+}
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 55f81f49024e0..97286b99270e9 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -148,3 +148,38 @@ macro_rules! container_of {
         ptr.sub(offset) as *const $type
     }}
 }
+
+/// Helper for `.rs.S` files.
+#[doc(hidden)]
+#[macro_export]
+macro_rules! concat_literals {
+    ($( $asm:literal )* ) => {
+        ::core::concat!($($asm),*)
+    };
+}
+
+/// Wrapper around `asm!` configured for use in the kernel.
+///
+/// Uses a semicolon to avoid parsing ambiguities, even though this does not match native `asm!`
+/// syntax.
+// For x86, `asm!` uses intel syntax by default, but we want to use at&t syntax in the kernel.
+#[cfg(any(target_arch = "x86", target_arch = "x86_64"))]
+#[macro_export]
+macro_rules! asm {
+    ($($asm:expr),* ; $($rest:tt)*) => {
+        ::core::arch::asm!( $($asm)*, options(att_syntax), $($rest)* )
+    };
+}
+
+/// Wrapper around `asm!` configured for use in the kernel.
+///
+/// Uses a semicolon to avoid parsing ambiguities, even though this does not match native `asm!`
+/// syntax.
+// For non-x86 arches we just pass through to `asm!`.
+#[cfg(not(any(target_arch = "x86", target_arch = "x86_64")))]
+#[macro_export]
+macro_rules! asm {
+    ($($asm:expr),* ; $($rest:tt)*) => {
+        ::core::arch::asm!( $($asm)*, $($rest)* )
+    };
+}
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 8f423a1faf507..03ee558fcd4df 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -248,12 +248,13 @@ $(obj)/%.lst: $(obj)/%.c FORCE
 # Compile Rust sources (.rs)
 # ---------------------------------------------------------------------------
 
-rust_allowed_features := new_uninit
+rust_allowed_features := asm_const,asm_goto,new_uninit
 
 # `--out-dir` is required to avoid temporaries being created by `rustc` in the
 # current working directory, which may be not accessible in the out-of-tree
 # modules case.
 rust_common_cmd = \
+	OBJTREE=$(abspath $(objtree)) \
 	RUST_MODFILE=$(modfile) $(RUSTC_OR_CLIPPY) $(rust_flags) \
 	-Zallow-features=$(rust_allowed_features) \
 	-Zcrate-attr=no_std \
@@ -303,6 +304,12 @@ quiet_cmd_rustc_ll_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
 $(obj)/%.ll: $(obj)/%.rs FORCE
 	+$(call if_changed_dep,rustc_ll_rs)
 
+quiet_cmd_rustc_rs_rs_S = RSCPP $(quiet_modtag) $@
+      cmd_rustc_rs_rs_S = $(CPP) $(c_flags) -xc -C -P $< | sed '1,/^\/\/ Cut here.$$/d' >$@
+
+$(obj)/%.rs: $(obj)/%.rs.S FORCE
+	+$(call if_changed_dep,rustc_rs_rs_S)
+
 # Compile assembler sources (.S)
 # ---------------------------------------------------------------------------
 

From e73ea1c2d4d8f7ba5daaf7aa51171f63cf79bcd8 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Sat, 12 Oct 2024 20:32:46 +0900
Subject: [PATCH 0817/1530] PCI: dwc: endpoint: Implement the
 pci_epc_ops::align_addr() operation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The function dw_pcie_prog_outbound_atu() used to program outbound ATU
entries for mapping RC PCI addresses to local CPU addresses does not
allow PCI addresses that are not aligned to the value of region_align
of struct dw_pcie. This value is determined from the iATU hardware
registers during probing of the iATU (done by dw_pcie_iatu_detect()).
This value is thus valid for all DWC PCIe controllers, and valid
regardless of the hardware configuration used when synthesizing the
DWC PCIe controller.

Implement the ->align_addr() endpoint controller operation to allow
this mapping alignment to be transparently handled by endpoint function
drivers through the function pci_epc_mem_map().

Link: https://lore.kernel.org/linux-pci/20241012113246.95634-7-dlemoal@kernel.org
Link: https://lore.kernel.org/linux-pci/20241015090712.112674-1-dlemoal@kernel.org
Link: https://lore.kernel.org/linux-pci/20241017132052.4014605-5-cassel@kernel.org
Co-developed-by: Niklas Cassel <cassel@kernel.org>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
[mani: squashed the patch that changed phy_addr_t to u64]
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
[kwilczynski: squashed patch that updated the pci_size variable]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/dwc/pcie-designware-ep.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 43ba5c6738df1..20f67fd85e837 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -268,6 +268,20 @@ static int dw_pcie_find_index(struct dw_pcie_ep *ep, phys_addr_t addr,
 	return -EINVAL;
 }
 
+static u64 dw_pcie_ep_align_addr(struct pci_epc *epc, u64 pci_addr,
+				 size_t *pci_size, size_t *offset)
+{
+	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	u64 mask = pci->region_align - 1;
+	size_t ofst = pci_addr & mask;
+
+	*pci_size = ALIGN(ofst + *pci_size, epc->mem->window.page_size);
+	*offset = ofst;
+
+	return pci_addr & ~mask;
+}
+
 static void dw_pcie_ep_unmap_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 				  phys_addr_t addr)
 {
@@ -444,6 +458,7 @@ static const struct pci_epc_ops epc_ops = {
 	.write_header		= dw_pcie_ep_write_header,
 	.set_bar		= dw_pcie_ep_set_bar,
 	.clear_bar		= dw_pcie_ep_clear_bar,
+	.align_addr		= dw_pcie_ep_align_addr,
 	.map_addr		= dw_pcie_ep_map_addr,
 	.unmap_addr		= dw_pcie_ep_unmap_addr,
 	.set_msi		= dw_pcie_ep_set_msi,

From 97110d42680e692020154f9aa89298c038196055 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 17 Oct 2024 10:06:48 +0900
Subject: [PATCH 0818/1530] PCI: endpoint: test: Synchronously cancel command
 handler work
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use cancel_delayed_work_sync() in pci_epf_test_epc_deinit() to ensure
that the command handler is really stopped before proceeding with DMA
and BAR cleanup.

The same change is also done in pci_epf_test_link_down() to ensure that
the link down handling completes with the command handler fully stopped.

Link: https://lore.kernel.org/r/20241017010648.189889-1-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
---
 drivers/pci/endpoint/functions/pci-epf-test.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index a73bc0771d358..c2e7f67e51076 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -800,7 +800,7 @@ static void pci_epf_test_epc_deinit(struct pci_epf *epf)
 {
 	struct pci_epf_test *epf_test = epf_get_drvdata(epf);
 
-	cancel_delayed_work(&epf_test->cmd_handler);
+	cancel_delayed_work_sync(&epf_test->cmd_handler);
 	pci_epf_test_clean_dma_chan(epf_test);
 	pci_epf_test_clear_bar(epf);
 }
@@ -931,7 +931,7 @@ static void pci_epf_test_unbind(struct pci_epf *epf)
 	struct pci_epf_test *epf_test = epf_get_drvdata(epf);
 	struct pci_epc *epc = epf->epc;
 
-	cancel_delayed_work(&epf_test->cmd_handler);
+	cancel_delayed_work_sync(&epf_test->cmd_handler);
 	if (epc->init_complete) {
 		pci_epf_test_clean_dma_chan(epf_test);
 		pci_epf_test_clear_bar(epf);

From cca257f0f3fbaf30e07e8073cd374a06eead7b40 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Fri, 1 Nov 2024 16:13:03 -0500
Subject: [PATCH 0819/1530] dt-bindings: input: rotary-encoder: Fix
 "rotary-encoder,rollover" type

The user and driver both indicate this property is a boolean, not int32.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Link: https://lore.kernel.org/r/20241101211304.20886-1-robh@kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 Documentation/devicetree/bindings/input/rotary-encoder.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/input/rotary-encoder.yaml b/Documentation/devicetree/bindings/input/rotary-encoder.yaml
index e315aab7f584f..f9332bb2343f2 100644
--- a/Documentation/devicetree/bindings/input/rotary-encoder.yaml
+++ b/Documentation/devicetree/bindings/input/rotary-encoder.yaml
@@ -41,7 +41,7 @@ properties:
       device, hence no steps need to be passed.
 
   rotary-encoder,rollover:
-    $ref: /schemas/types.yaml#/definitions/int32
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Automatic rollover when the rotary value becomes
       greater than the specified steps or smaller than 0. For absolute axis only.

From 4cbf2b660f46be45b71d4f67f71495d08bf04371 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 24 Oct 2024 18:10:44 +0300
Subject: [PATCH 0820/1530] pinctrl: intel: Add a human readable decoder for
 pull bias values

Add a human readable decoder for pull bias values in the comment.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 928607a21d36d..04b438f63ccbb 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -85,6 +85,18 @@
 #define PADCFG1_TERM_UP			BIT(13)
 #define PADCFG1_TERM_SHIFT		10
 #define PADCFG1_TERM_MASK		GENMASK(12, 10)
+/*
+ * Bit 0  Bit 1  Bit 2			Value, Ohms
+ *
+ *   0      0      0			-
+ *   0      0      1			20000
+ *   0      1      0			5000
+ *   0      1      1			~4000
+ *   1      0      0			1000 (if supported)
+ *   1      0      1			~952 (if supported)
+ *   1      1      0			~833 (if supported)
+ *   1      1      1			~800 (if supported)
+ */
 #define PADCFG1_TERM_20K		BIT(2)
 #define PADCFG1_TERM_5K			BIT(1)
 #define PADCFG1_TERM_4K			(BIT(2) | BIT(1))

From c6235c426d2ac78ab843a55cb1556b0f43175d9e Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 28 Oct 2024 15:43:17 +0200
Subject: [PATCH 0821/1530] pinctrl: elkhartlake: Add support for DSW community

Hardware has a DSW (Deep Sleep Well) community that might be exposed
by some BIOSes. Add support for it in the driver.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-elkhartlake.c | 38 +++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/drivers/pinctrl/intel/pinctrl-elkhartlake.c b/drivers/pinctrl/intel/pinctrl-elkhartlake.c
index 1678634ebc06c..3e45d7fb003ac 100644
--- a/drivers/pinctrl/intel/pinctrl-elkhartlake.c
+++ b/drivers/pinctrl/intel/pinctrl-elkhartlake.c
@@ -264,6 +264,43 @@ static const struct intel_pinctrl_soc_data ehl_community1_soc_data = {
 	.ncommunities = ARRAY_SIZE(ehl_community1),
 };
 
+static const struct pinctrl_pin_desc ehl_community2_pins[] = {
+	/* DSW */
+	PINCTRL_PIN(0, "BATLOWB"),
+	PINCTRL_PIN(1, "ACPRESENT"),
+	PINCTRL_PIN(2, "LAN_WAKEB"),
+	PINCTRL_PIN(3, "PWRBTNB"),
+	PINCTRL_PIN(4, "SLP_S3B"),
+	PINCTRL_PIN(5, "SLP_S4B"),
+	PINCTRL_PIN(6, "SLP_AB"),
+	PINCTRL_PIN(7, "GPD_7"),
+	PINCTRL_PIN(8, "SUSCLK"),
+	PINCTRL_PIN(9, "SLP_WLANB"),
+	PINCTRL_PIN(10, "SLP_S5B"),
+	PINCTRL_PIN(11, "LANPHYPC"),
+	PINCTRL_PIN(12, "INPUT3VSEL"),
+	PINCTRL_PIN(13, "SLP_LANB"),
+	PINCTRL_PIN(14, "SLP_SUSB"),
+	PINCTRL_PIN(15, "WAKEB"),
+	PINCTRL_PIN(16, "DRAM_RESETB"),
+};
+
+static const struct intel_padgroup ehl_community2_gpps[] = {
+	EHL_GPP(0, 0, 16),	/* DSW */
+};
+
+static const struct intel_community ehl_community2[] = {
+	EHL_COMMUNITY(0, 0, 16, ehl_community2_gpps),
+};
+
+static const struct intel_pinctrl_soc_data ehl_community2_soc_data = {
+	.uid = "2",
+	.pins = ehl_community2_pins,
+	.npins = ARRAY_SIZE(ehl_community2_pins),
+	.communities = ehl_community2,
+	.ncommunities = ARRAY_SIZE(ehl_community2),
+};
+
 static const struct pinctrl_pin_desc ehl_community3_pins[] = {
 	/* CPU */
 	PINCTRL_PIN(0, "HDACPU_SDI"),
@@ -474,6 +511,7 @@ static const struct intel_pinctrl_soc_data ehl_community5_soc_data = {
 static const struct intel_pinctrl_soc_data *ehl_soc_data_array[] = {
 	&ehl_community0_soc_data,
 	&ehl_community1_soc_data,
+	&ehl_community2_soc_data,
 	&ehl_community3_soc_data,
 	&ehl_community4_soc_data,
 	&ehl_community5_soc_data,

From 7ec151f45730435b30aa75a98d22e39849cfb7f9 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 2 Nov 2024 10:11:24 +0100
Subject: [PATCH 0822/1530] Input: synaptics - fix a typo

s/synatics/synaptics/
A 'p' is missing.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/f3365eab359feb9adc6e2dedcffc976f3b272d8b.1730538673.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/synaptics.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/mouse/synaptics.h b/drivers/input/mouse/synaptics.h
index 08533d1b1b16f..899aee598632b 100644
--- a/drivers/input/mouse/synaptics.h
+++ b/drivers/input/mouse/synaptics.h
@@ -21,7 +21,7 @@
 #define SYN_QUE_EXT_MIN_COORDS		0x0f
 #define SYN_QUE_MEXT_CAPAB_10		0x10
 
-/* synatics modes */
+/* synaptics modes */
 #define SYN_BIT_ABSOLUTE_MODE		BIT(7)
 #define SYN_BIT_HIGH_RATE		BIT(6)
 #define SYN_BIT_SLEEP_MODE		BIT(3)

From cbdc3f95cdf817e6adc5c783464658d30e9ccb61 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Fri, 25 Oct 2024 15:38:45 -0700
Subject: [PATCH 0823/1530] Input: synaptics-rmi4 - switch to using cleanup
 functions in F34

Start using __free() and guard() primitives to simplify the code
and error handling.

Reviewed-by: Lyude Paul <lyude@redhat.com>
Link: https://lore.kernel.org/r/Zxwd9c0njasZZoal@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/rmi4/rmi_f34.c | 37 ++++++++++++++----------------------
 1 file changed, 14 insertions(+), 23 deletions(-)

diff --git a/drivers/input/rmi4/rmi_f34.c b/drivers/input/rmi4/rmi_f34.c
index 3b3ac71e53dc5..7a05ac00dce2e 100644
--- a/drivers/input/rmi4/rmi_f34.c
+++ b/drivers/input/rmi4/rmi_f34.c
@@ -246,7 +246,6 @@ static int rmi_f34_update_firmware(struct f34_data *f34,
 				(const struct rmi_f34_firmware *)fw->data;
 	u32 image_size = le32_to_cpu(syn_fw->image_size);
 	u32 config_size = le32_to_cpu(syn_fw->config_size);
-	int ret;
 
 	BUILD_BUG_ON(offsetof(struct rmi_f34_firmware, data) !=
 			F34_FW_IMAGE_OFFSET);
@@ -267,8 +266,7 @@ static int rmi_f34_update_firmware(struct f34_data *f34,
 		dev_err(&f34->fn->dev,
 			"Bad firmware image: fw size %d, expected %d\n",
 			image_size, f34->v5.fw_blocks * f34->v5.block_size);
-		ret = -EILSEQ;
-		goto out;
+		return -EILSEQ;
 	}
 
 	if (config_size &&
@@ -277,25 +275,18 @@ static int rmi_f34_update_firmware(struct f34_data *f34,
 			"Bad firmware image: config size %d, expected %d\n",
 			config_size,
 			f34->v5.config_blocks * f34->v5.block_size);
-		ret = -EILSEQ;
-		goto out;
+		return -EILSEQ;
 	}
 
 	if (image_size && !config_size) {
 		dev_err(&f34->fn->dev, "Bad firmware image: no config data\n");
-		ret = -EILSEQ;
-		goto out;
+		return -EILSEQ;
 	}
 
 	dev_info(&f34->fn->dev, "Firmware image OK\n");
-	mutex_lock(&f34->v5.flash_mutex);
-
-	ret = rmi_f34_flash_firmware(f34, syn_fw);
 
-	mutex_unlock(&f34->v5.flash_mutex);
-
-out:
-	return ret;
+	guard(mutex)(&f34->v5.flash_mutex);
+	return rmi_f34_flash_firmware(f34, syn_fw);
 }
 
 static int rmi_f34_status(struct rmi_function *fn)
@@ -461,9 +452,8 @@ static ssize_t rmi_driver_update_fw_store(struct device *dev,
 {
 	struct rmi_driver_data *data = dev_get_drvdata(dev);
 	char fw_name[NAME_MAX];
-	const struct firmware *fw;
 	size_t copy_count = count;
-	int ret;
+	int error;
 
 	if (count == 0 || count >= NAME_MAX)
 		return -EINVAL;
@@ -474,17 +464,18 @@ static ssize_t rmi_driver_update_fw_store(struct device *dev,
 	memcpy(fw_name, buf, copy_count);
 	fw_name[copy_count] = '\0';
 
-	ret = request_firmware(&fw, fw_name, dev);
-	if (ret)
-		return ret;
+	const struct firmware *fw __free(firmware) = NULL;
+	error = request_firmware(&fw, fw_name, dev);
+	if (error)
+		return error;
 
 	dev_info(dev, "Flashing %s\n", fw_name);
 
-	ret = rmi_firmware_update(data, fw);
-
-	release_firmware(fw);
+	error = rmi_firmware_update(data, fw);
+	if (error)
+		return error;
 
-	return ret ?: count;
+	return count;
 }
 
 static DEVICE_ATTR(update_fw, 0200, NULL, rmi_driver_update_fw_store);

From c741c7b5e98357e9f45e012f8c4295b5aed8d5c0 Mon Sep 17 00:00:00 2001
From: Michael Petlan <mpetlan@redhat.com>
Date: Fri, 1 Nov 2024 11:28:12 +0100
Subject: [PATCH 0824/1530] perf test: Remove cpu-list BPF cgroup counter test

The cpu-list part of this testcase has proven itself to be unreliable.
Sometimes, we get "<not counted>" for system.slice when pinned to CPUs
0 and 1. In such case, the test fails.

Since we cannot simply guarantee that any system.slice load will run
on any arbitrary list of CPUs, except the whole set of all CPUs, let's
rather remove the cpu-list subtest.

Fixes: a84260e314029e6dc9904fd ("perf test stat_bpf_counters_cgrp: Enhance perf stat cgroup BPF counter test")
Signed-off-by: Michael Petlan <mpetlan@redhat.com>
Cc: vmolnaro@redhat.com
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20241101102812.576425-1-mpetlan@redhat.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/stat_bpf_counters_cgrp.sh | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
index e75d0780dc788..2ec69060c42ff 100755
--- a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
@@ -58,22 +58,9 @@ check_system_wide_counted()
 	fi
 }
 
-check_cpu_list_counted()
-{
-	check_cpu_list_counted_output=$(perf stat -C 0,1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1  2>&1)
-	if echo ${check_cpu_list_counted_output} | grep -q -F "<not "; then
-		echo "Some CPU events are not counted"
-		if [ "${verbose}" = "1" ]; then
-			echo ${check_cpu_list_counted_output}
-		fi
-		exit 1
-	fi
-}
-
 check_bpf_counter
 find_cgroups
 
 check_system_wide_counted
-check_cpu_list_counted
 
 exit 0

From d5a0a4ab4af4c27de097b78d6f1b7e7f7e31908f Mon Sep 17 00:00:00 2001
From: Yicong Yang <yangyicong@hisilicon.com>
Date: Thu, 24 Oct 2024 21:32:36 +0800
Subject: [PATCH 0825/1530] perf build: Add missing cflags when building with
 custom libtraceevent

When building with custom libtraceevent, below errors occur:

  $ make -C tools/perf NO_LIBPYTHON=1 PKG_CONFIG_PATH=<custom libtraceevent>
  In file included from util/session.h:5,
                   from builtin-buildid-list.c:17:
  util/trace-event.h:153:10: fatal error: traceevent/event-parse.h: No such file or directory
    153 | #include <traceevent/event-parse.h>
        |          ^~~~~~~~~~~~~~~~~~~~~~~~~~
  <snip similar errors of missing headers>

This is because the include path is missed in the cflags. Add it.

Fixes: 0f0e1f445690 ("perf build: Use pkg-config for feature check for libtrace{event,fs}")
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Reviewed-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: Guilherme Amadio <amadio@gentoo.org>
Cc: linuxarm@huawei.com
Link: https://lore.kernel.org/r/20241024133236.31016-1-yangyicong@huawei.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Makefile.config | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index e68f0be259a19..80bf06e828f0e 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -1183,7 +1183,7 @@ endif
 ifneq ($(NO_LIBTRACEEVENT),1)
   $(call feature_check,libtraceevent)
   ifeq ($(feature-libtraceevent), 1)
-    CFLAGS += -DHAVE_LIBTRACEEVENT
+    CFLAGS += -DHAVE_LIBTRACEEVENT $(shell $(PKG_CONFIG) --cflags libtraceevent)
     LDFLAGS += $(shell $(PKG_CONFIG) --libs-only-L libtraceevent)
     EXTLIBS += $(shell $(PKG_CONFIG) --libs-only-l libtraceevent)
     LIBTRACEEVENT_VERSION := $(shell $(PKG_CONFIG) --modversion libtraceevent).0.0

From 6e0e0a18632630bbe2f3e97c79d154ae1faf64df Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Mon, 4 Nov 2024 13:19:15 -0800
Subject: [PATCH 0826/1530] perf tools: Add all shellcheck_log to gitignore

Instead of adding specific shellcheck_log files to the gitignore, add
all of them to prevent these files from cluttering the git status.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20241104-shellcheck_gitignore-v1-1-ffc179f57dc9@rivosinc.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/.gitignore | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index f5b81d439387a..19ce1cd56f8cb 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -39,9 +39,7 @@ trace/beauty/generated/
 pmu-events/pmu-events.c
 pmu-events/jevents
 pmu-events/metric_test.log
-tests/shell/*.shellcheck_log
-tests/shell/coresight/*.shellcheck_log
-tests/shell/lib/*.shellcheck_log
+*.shellcheck_log
 feature/
 libapi/
 libbpf/

From a52143aa2127aa92b11b3936b606de81d1ef6ef3 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@kernel.org>
Date: Mon, 4 Nov 2024 11:34:58 -0300
Subject: [PATCH 0827/1530] perf test: Remove dangling CFLAGS for removed
 attr.o object

Since the C test wrapper for attr.py was removed we don't have an attr.o
object for that CFLAGS_attr.o to apply for, remove it.

Fixes: 3a447031f5fc21c4 ("perf test: Remove C test wrapper for attr.py")
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: zhaimingbing <zhaimingbing@cmss.chinamobile.com>
Link: https://lore.kernel.org/r/ZyjbksKYnV22zmz-@x1
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/Build | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 03cbdf7c50a09..01ed9335db4db 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -72,7 +72,6 @@ ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc))
 perf-test-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
 
-CFLAGS_attr.o         += -DBINDIR="BUILD_STR($(bindir_SQ))" -DPYTHON="BUILD_STR($(PYTHON_WORD))"
 CFLAGS_python-use.o   += -DPYTHONPATH="BUILD_STR($(OUTPUT)python)" -DPYTHON="BUILD_STR($(PYTHON_WORD))"
 CFLAGS_dwarf-unwind.o += -fno-optimize-sibling-calls
 

From 29bf07bc9ad2eca06a14d78f7f4dc5dc8f10aae3 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Sat, 2 Nov 2024 16:17:02 -0700
Subject: [PATCH 0828/1530] perf test: Fix ftrace test with regex patterns

During the parallel testing, I've noticed some ftrace test failures.  It
seems the regex pattern checks 100 msec of nanosleep with the error
range of 10 msec.  But sometimes it's affected by other processes and
resulted in more time in the syscall.

The following output shows that it took more than 120 msec and failed.
Let's update the regex pattern so that it can allow more drifts.

  perf ftrace profile test
  # Total (us)   Avg (us)   Max (us)      Count   Function
    121279.500 121279.500 121279.500          1   __x64_sys_clock_nanosleep
    121278.400 121278.400 121278.400          1   common_nsleep
    121277.800 121277.800 121277.800          1   hrtimer_nanosleep
    121277.100 121277.100 121277.100          1   do_nanosleep
    341760.289  56960.048 121273.400          6   schedule
       176.200     25.171     31.616          7   scheduler_tick
         0.923      0.923      0.923          1   native_smp_send_reschedule
    345522.360  69104.472 345320.600          5   __x64_sys_execve
    345486.585  69097.317 345312.700          5   do_execveat_common.isra.0
    340730.300 340730.300 340730.300          1   bprm_execve
         1.758      0.879      0.883          2   sched_mm_cid_before_execve
         1.112      1.112      1.112          1   sched_mm_cid_after_execve
  ---- end(-1) ----
   81: perf ftrace tests                                               : FAILED!

Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20241102231702.2262258-1-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/ftrace.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/ftrace.sh b/tools/perf/tests/shell/ftrace.sh
index a6ee740f0d7ec..11010711efa19 100755
--- a/tools/perf/tests/shell/ftrace.sh
+++ b/tools/perf/tests/shell/ftrace.sh
@@ -72,7 +72,7 @@ test_ftrace_profile() {
     grep sleep "${output}"
     grep schedule "${output}"
     grep execve "${output}"
-    time_re="[[:space:]]+10[[:digit:]]{4}\.[[:digit:]]{3}"
+    time_re="[[:space:]]+1[[:digit:]]{5}\.[[:digit:]]{3}"
     # 100283.000 100283.000 100283.000          1   __x64_sys_clock_nanosleep
     # Check for one *clock_nanosleep line with a Count of just 1 that takes a bit more than 0.1 seconds
     # Strip the _x64_sys part to work with other architectures

From a669c2df36db5fa7a2674ec5ae10548760702f99 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 24 Oct 2024 10:17:57 -0700
Subject: [PATCH 0829/1530] fuse: support folios in struct fuse_args_pages and
 fuse_copy_pages()

This adds support in struct fuse_args_pages and fuse_copy_pages() for
using folios instead of pages for transferring data. Both folios and
pages must be supported right now in struct fuse_args_pages and
fuse_copy_pages() until all request types have been converted to use
folios. Once all have been converted, then
struct fuse_args_pages and fuse_copy_pages() will only support folios.

Right now in fuse, all folios are one page (large folios are not yet
supported). As such, copying folio->page is sufficient for copying
the entire folio in fuse_copy_pages().

No functional changes.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dev.c    | 40 ++++++++++++++++++++++++++++++++--------
 fs/fuse/fuse_i.h | 22 +++++++++++++++++++---
 2 files changed, 51 insertions(+), 11 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index e25804097ffbc..70da1184a3f61 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1028,17 +1028,41 @@ static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes,
 	struct fuse_req *req = cs->req;
 	struct fuse_args_pages *ap = container_of(req->args, typeof(*ap), args);
 
+	if (ap->uses_folios) {
+		for (i = 0; i < ap->num_folios && (nbytes || zeroing); i++) {
+			int err;
+			unsigned int offset = ap->folio_descs[i].offset;
+			unsigned int count = min(nbytes, ap->folio_descs[i].length);
+			struct page *orig, *pagep;
 
-	for (i = 0; i < ap->num_pages && (nbytes || zeroing); i++) {
-		int err;
-		unsigned int offset = ap->descs[i].offset;
-		unsigned int count = min(nbytes, ap->descs[i].length);
+			orig = pagep = &ap->folios[i]->page;
 
-		err = fuse_copy_page(cs, &ap->pages[i], offset, count, zeroing);
-		if (err)
-			return err;
+			err = fuse_copy_page(cs, &pagep, offset, count, zeroing);
+			if (err)
+				return err;
+
+			nbytes -= count;
+
+			/*
+			 *  fuse_copy_page may have moved a page from a pipe
+			 *  instead of copying into our given page, so update
+			 *  the folios if it was replaced.
+			 */
+			if (pagep != orig)
+				ap->folios[i] = page_folio(pagep);
+		}
+	} else {
+		for (i = 0; i < ap->num_pages && (nbytes || zeroing); i++) {
+			int err;
+			unsigned int offset = ap->descs[i].offset;
+			unsigned int count = min(nbytes, ap->descs[i].length);
 
-		nbytes -= count;
+			err = fuse_copy_page(cs, &ap->pages[i], offset, count, zeroing);
+			if (err)
+				return err;
+
+			nbytes -= count;
+		}
 	}
 	return 0;
 }
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 671daa4d07adb..24a3da8400d16 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -291,6 +291,12 @@ struct fuse_page_desc {
 	unsigned int offset;
 };
 
+/** FUSE folio descriptor */
+struct fuse_folio_desc {
+	unsigned int length;
+	unsigned int offset;
+};
+
 struct fuse_args {
 	uint64_t nodeid;
 	uint32_t opcode;
@@ -319,9 +325,19 @@ struct fuse_args {
 
 struct fuse_args_pages {
 	struct fuse_args args;
-	struct page **pages;
-	struct fuse_page_desc *descs;
-	unsigned int num_pages;
+	union {
+		struct {
+			struct page **pages;
+			struct fuse_page_desc *descs;
+			unsigned int num_pages;
+		};
+		struct {
+			struct folio **folios;
+			struct fuse_folio_desc *folio_descs;
+			unsigned int num_folios;
+		};
+	};
+	bool uses_folios;
 };
 
 struct fuse_release_args {

From 29279e1d4284a29cdd4af11e9a19800b8fda2962 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 24 Oct 2024 10:17:58 -0700
Subject: [PATCH 0830/1530] fuse: add support in virtio for requests using
 folios

Until all requests have been converted to use folios instead of pages,
virtio will need to support both types. Once all requests have been
converted, then virtio will support just folios.

No functional changes.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/virtio_fs.c | 87 +++++++++++++++++++++++++++++----------------
 1 file changed, 56 insertions(+), 31 deletions(-)

diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index f685278919292..9f0d98cc20d36 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -766,6 +766,7 @@ static void virtio_fs_request_complete(struct fuse_req *req,
 	struct fuse_args_pages *ap;
 	unsigned int len, i, thislen;
 	struct page *page;
+	struct folio *folio;
 
 	/*
 	 * TODO verify that server properly follows FUSE protocol
@@ -777,15 +778,29 @@ static void virtio_fs_request_complete(struct fuse_req *req,
 	if (args->out_pages && args->page_zeroing) {
 		len = args->out_args[args->out_numargs - 1].size;
 		ap = container_of(args, typeof(*ap), args);
-		for (i = 0; i < ap->num_pages; i++) {
-			thislen = ap->descs[i].length;
-			if (len < thislen) {
-				WARN_ON(ap->descs[i].offset);
-				page = ap->pages[i];
-				zero_user_segment(page, len, thislen);
-				len = 0;
-			} else {
-				len -= thislen;
+		if (ap->uses_folios) {
+			for (i = 0; i < ap->num_folios; i++) {
+				thislen = ap->folio_descs[i].length;
+				if (len < thislen) {
+					WARN_ON(ap->folio_descs[i].offset);
+					folio = ap->folios[i];
+					folio_zero_segment(folio, len, thislen);
+					len = 0;
+				} else {
+					len -= thislen;
+				}
+			}
+		} else {
+			for (i = 0; i < ap->num_pages; i++) {
+				thislen = ap->descs[i].length;
+				if (len < thislen) {
+					WARN_ON(ap->descs[i].offset);
+					page = ap->pages[i];
+					zero_user_segment(page, len, thislen);
+					len = 0;
+				} else {
+					len -= thislen;
+				}
 			}
 		}
 	}
@@ -1272,16 +1287,22 @@ static void virtio_fs_send_interrupt(struct fuse_iqueue *fiq, struct fuse_req *r
 }
 
 /* Count number of scatter-gather elements required */
-static unsigned int sg_count_fuse_pages(struct fuse_page_desc *page_descs,
-				       unsigned int num_pages,
-				       unsigned int total_len)
+static unsigned int sg_count_fuse_pages(struct fuse_args_pages *ap,
+					unsigned int total_len)
 {
 	unsigned int i;
 	unsigned int this_len;
 
-	for (i = 0; i < num_pages && total_len; i++) {
-		this_len =  min(page_descs[i].length, total_len);
-		total_len -= this_len;
+	if (ap->uses_folios) {
+		for (i = 0; i < ap->num_folios && total_len; i++) {
+			this_len =  min(ap->folio_descs[i].length, total_len);
+			total_len -= this_len;
+		}
+	} else {
+		for (i = 0; i < ap->num_pages && total_len; i++) {
+			this_len =  min(ap->descs[i].length, total_len);
+			total_len -= this_len;
+		}
 	}
 
 	return i;
@@ -1299,8 +1320,7 @@ static unsigned int sg_count_fuse_req(struct fuse_req *req)
 
 	if (args->in_pages) {
 		size = args->in_args[args->in_numargs - 1].size;
-		total_sgs += sg_count_fuse_pages(ap->descs, ap->num_pages,
-						 size);
+		total_sgs += sg_count_fuse_pages(ap, size);
 	}
 
 	if (!test_bit(FR_ISREPLY, &req->flags))
@@ -1313,28 +1333,35 @@ static unsigned int sg_count_fuse_req(struct fuse_req *req)
 
 	if (args->out_pages) {
 		size = args->out_args[args->out_numargs - 1].size;
-		total_sgs += sg_count_fuse_pages(ap->descs, ap->num_pages,
-						 size);
+		total_sgs += sg_count_fuse_pages(ap, size);
 	}
 
 	return total_sgs;
 }
 
-/* Add pages to scatter-gather list and return number of elements used */
+/* Add pages/folios to scatter-gather list and return number of elements used */
 static unsigned int sg_init_fuse_pages(struct scatterlist *sg,
-				       struct page **pages,
-				       struct fuse_page_desc *page_descs,
-				       unsigned int num_pages,
+				       struct fuse_args_pages *ap,
 				       unsigned int total_len)
 {
 	unsigned int i;
 	unsigned int this_len;
 
-	for (i = 0; i < num_pages && total_len; i++) {
-		sg_init_table(&sg[i], 1);
-		this_len =  min(page_descs[i].length, total_len);
-		sg_set_page(&sg[i], pages[i], this_len, page_descs[i].offset);
-		total_len -= this_len;
+	if (ap->uses_folios) {
+		for (i = 0; i < ap->num_folios && total_len; i++) {
+			sg_init_table(&sg[i], 1);
+			this_len =  min(ap->folio_descs[i].length, total_len);
+			sg_set_folio(&sg[i], ap->folios[i], this_len,
+				     ap->folio_descs[i].offset);
+			total_len -= this_len;
+		}
+	} else {
+		for (i = 0; i < ap->num_pages && total_len; i++) {
+			sg_init_table(&sg[i], 1);
+			this_len =  min(ap->descs[i].length, total_len);
+			sg_set_page(&sg[i], ap->pages[i], this_len, ap->descs[i].offset);
+			total_len -= this_len;
+		}
 	}
 
 	return i;
@@ -1358,9 +1385,7 @@ static unsigned int sg_init_fuse_args(struct scatterlist *sg,
 		sg_init_one(&sg[total_sgs++], argbuf, len);
 
 	if (argpages)
-		total_sgs += sg_init_fuse_pages(&sg[total_sgs],
-						ap->pages, ap->descs,
-						ap->num_pages,
+		total_sgs += sg_init_fuse_pages(&sg[total_sgs], ap,
 						args[numargs - 1].size);
 
 	if (len_used)

From ee80369a8aa850a992e93127bd16023fe1425010 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 24 Oct 2024 10:17:59 -0700
Subject: [PATCH 0831/1530] fuse: convert cuse to use folios

Convert cuse requests to use a folio instead of a page.

No functional changes.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/cuse.c | 32 +++++++++++++++++---------------
 1 file changed, 17 insertions(+), 15 deletions(-)

diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 0b2da7b7e2ad0..eed78e3031398 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -303,8 +303,8 @@ struct cuse_init_args {
 	struct fuse_args_pages ap;
 	struct cuse_init_in in;
 	struct cuse_init_out out;
-	struct page *page;
-	struct fuse_page_desc desc;
+	struct folio *folio;
+	struct fuse_folio_desc desc;
 };
 
 /**
@@ -326,7 +326,7 @@ static void cuse_process_init_reply(struct fuse_mount *fm,
 	struct fuse_args_pages *ap = &ia->ap;
 	struct cuse_conn *cc = fc_to_cc(fc), *pos;
 	struct cuse_init_out *arg = &ia->out;
-	struct page *page = ap->pages[0];
+	struct folio *folio = ap->folios[0];
 	struct cuse_devinfo devinfo = { };
 	struct device *dev;
 	struct cdev *cdev;
@@ -343,7 +343,7 @@ static void cuse_process_init_reply(struct fuse_mount *fm,
 	/* parse init reply */
 	cc->unrestricted_ioctl = arg->flags & CUSE_UNRESTRICTED_IOCTL;
 
-	rc = cuse_parse_devinfo(page_address(page), ap->args.out_args[1].size,
+	rc = cuse_parse_devinfo(folio_address(folio), ap->args.out_args[1].size,
 				&devinfo);
 	if (rc)
 		goto err;
@@ -411,7 +411,7 @@ static void cuse_process_init_reply(struct fuse_mount *fm,
 	kobject_uevent(&dev->kobj, KOBJ_ADD);
 out:
 	kfree(ia);
-	__free_page(page);
+	folio_put(folio);
 	return;
 
 err_cdev:
@@ -429,7 +429,7 @@ static void cuse_process_init_reply(struct fuse_mount *fm,
 static int cuse_send_init(struct cuse_conn *cc)
 {
 	int rc;
-	struct page *page;
+	struct folio *folio;
 	struct fuse_mount *fm = &cc->fm;
 	struct cuse_init_args *ia;
 	struct fuse_args_pages *ap;
@@ -437,13 +437,14 @@ static int cuse_send_init(struct cuse_conn *cc)
 	BUILD_BUG_ON(CUSE_INIT_INFO_MAX > PAGE_SIZE);
 
 	rc = -ENOMEM;
-	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-	if (!page)
+
+	folio = folio_alloc(GFP_KERNEL | __GFP_ZERO, 0);
+	if (!folio)
 		goto err;
 
 	ia = kzalloc(sizeof(*ia), GFP_KERNEL);
 	if (!ia)
-		goto err_free_page;
+		goto err_free_folio;
 
 	ap = &ia->ap;
 	ia->in.major = FUSE_KERNEL_VERSION;
@@ -459,18 +460,19 @@ static int cuse_send_init(struct cuse_conn *cc)
 	ap->args.out_args[1].size = CUSE_INIT_INFO_MAX;
 	ap->args.out_argvar = true;
 	ap->args.out_pages = true;
-	ap->num_pages = 1;
-	ap->pages = &ia->page;
-	ap->descs = &ia->desc;
-	ia->page = page;
+	ap->uses_folios = true;
+	ap->num_folios = 1;
+	ap->folios = &ia->folio;
+	ap->folio_descs = &ia->desc;
+	ia->folio = folio;
 	ia->desc.length = ap->args.out_args[1].size;
 	ap->args.end = cuse_process_init_reply;
 
 	rc = fuse_simple_background(fm, &ap->args, GFP_KERNEL);
 	if (rc) {
 		kfree(ia);
-err_free_page:
-		__free_page(page);
+err_free_folio:
+		folio_put(folio);
 	}
 err:
 	return rc;

From c1e4862b135954dd59596fbd454321ca4109b67e Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 24 Oct 2024 10:18:00 -0700
Subject: [PATCH 0832/1530] fuse: convert readlink to use folios

Convert readlink requests to use a folio instead of a page.

No functional changes.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dir.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 54104dd48af7c..a08c532068d0f 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1585,14 +1585,15 @@ static int fuse_permission(struct mnt_idmap *idmap,
 	return err;
 }
 
-static int fuse_readlink_page(struct inode *inode, struct page *page)
+static int fuse_readlink_page(struct inode *inode, struct folio *folio)
 {
 	struct fuse_mount *fm = get_fuse_mount(inode);
-	struct fuse_page_desc desc = { .length = PAGE_SIZE - 1 };
+	struct fuse_folio_desc desc = { .length = PAGE_SIZE - 1 };
 	struct fuse_args_pages ap = {
-		.num_pages = 1,
-		.pages = &page,
-		.descs = &desc,
+		.uses_folios = true,
+		.num_folios = 1,
+		.folios = &folio,
+		.folio_descs = &desc,
 	};
 	char *link;
 	ssize_t res;
@@ -1614,7 +1615,7 @@ static int fuse_readlink_page(struct inode *inode, struct page *page)
 	if (WARN_ON(res >= PAGE_SIZE))
 		return -EIO;
 
-	link = page_address(page);
+	link = folio_address(folio);
 	link[res] = '\0';
 
 	return 0;
@@ -1624,7 +1625,7 @@ static const char *fuse_get_link(struct dentry *dentry, struct inode *inode,
 				 struct delayed_call *callback)
 {
 	struct fuse_conn *fc = get_fuse_conn(inode);
-	struct page *page;
+	struct folio *folio;
 	int err;
 
 	err = -EIO;
@@ -1638,20 +1639,20 @@ static const char *fuse_get_link(struct dentry *dentry, struct inode *inode,
 	if (!dentry)
 		goto out_err;
 
-	page = alloc_page(GFP_KERNEL);
+	folio = folio_alloc(GFP_KERNEL, 0);
 	err = -ENOMEM;
-	if (!page)
+	if (!folio)
 		goto out_err;
 
-	err = fuse_readlink_page(inode, page);
+	err = fuse_readlink_page(inode, folio);
 	if (err) {
-		__free_page(page);
+		folio_put(folio);
 		goto out_err;
 	}
 
-	set_delayed_call(callback, page_put_link, page);
+	set_delayed_call(callback, page_put_link, &folio->page);
 
-	return page_address(page);
+	return folio_address(folio);
 
 out_err:
 	return ERR_PTR(err);
@@ -2231,7 +2232,7 @@ void fuse_init_dir(struct inode *inode)
 
 static int fuse_symlink_read_folio(struct file *null, struct folio *folio)
 {
-	int err = fuse_readlink_page(folio->mapping->host, &folio->page);
+	int err = fuse_readlink_page(folio->mapping->host, folio);
 
 	if (!err)
 		folio_mark_uptodate(folio);

From 02b78c7a7a0c72aee6f600a167e6adee9417ac0e Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 24 Oct 2024 10:18:01 -0700
Subject: [PATCH 0833/1530] fuse: convert readdir to use folios

Convert readdir requests to use a folio instead of a page.

No functional changes.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/readdir.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c
index 0377b6dc24c80..fd0eff1b9f2de 100644
--- a/fs/fuse/readdir.c
+++ b/fs/fuse/readdir.c
@@ -331,24 +331,25 @@ static int fuse_readdir_uncached(struct file *file, struct dir_context *ctx)
 {
 	int plus;
 	ssize_t res;
-	struct page *page;
+	struct folio *folio;
 	struct inode *inode = file_inode(file);
 	struct fuse_mount *fm = get_fuse_mount(inode);
 	struct fuse_io_args ia = {};
 	struct fuse_args_pages *ap = &ia.ap;
-	struct fuse_page_desc desc = { .length = PAGE_SIZE };
+	struct fuse_folio_desc desc = { .length = PAGE_SIZE };
 	u64 attr_version = 0;
 	bool locked;
 
-	page = alloc_page(GFP_KERNEL);
-	if (!page)
+	folio = folio_alloc(GFP_KERNEL, 0);
+	if (!folio)
 		return -ENOMEM;
 
 	plus = fuse_use_readdirplus(inode, ctx);
 	ap->args.out_pages = true;
-	ap->num_pages = 1;
-	ap->pages = &page;
-	ap->descs = &desc;
+	ap->uses_folios = true;
+	ap->num_folios = 1;
+	ap->folios = &folio;
+	ap->folio_descs = &desc;
 	if (plus) {
 		attr_version = fuse_get_attr_version(fm->fc);
 		fuse_read_args_fill(&ia, file, ctx->pos, PAGE_SIZE,
@@ -367,15 +368,15 @@ static int fuse_readdir_uncached(struct file *file, struct dir_context *ctx)
 			if (ff->open_flags & FOPEN_CACHE_DIR)
 				fuse_readdir_cache_end(file, ctx->pos);
 		} else if (plus) {
-			res = parse_dirplusfile(page_address(page), res,
+			res = parse_dirplusfile(folio_address(folio), res,
 						file, ctx, attr_version);
 		} else {
-			res = parse_dirfile(page_address(page), res, file,
+			res = parse_dirfile(folio_address(folio), res, file,
 					    ctx);
 		}
 	}
 
-	__free_page(page);
+	folio_put(folio);
 	fuse_invalidate_atime(inode);
 	return res;
 }

From 51b025301824f16d51243aa505709d678f2e059e Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 24 Oct 2024 10:18:02 -0700
Subject: [PATCH 0834/1530] fuse: convert reads to use folios

Convert read requests to use folios instead of pages.

No functional changes.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c   | 67 ++++++++++++++++++++++++++++++++----------------
 fs/fuse/fuse_i.h | 12 +++++++++
 2 files changed, 57 insertions(+), 22 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index ce67af163c9ae..ece1c0319e35e 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -760,12 +760,37 @@ static struct fuse_io_args *fuse_io_alloc(struct fuse_io_priv *io,
 	return ia;
 }
 
+static struct fuse_io_args *fuse_io_folios_alloc(struct fuse_io_priv *io,
+						 unsigned int nfolios)
+{
+	struct fuse_io_args *ia;
+
+	ia = kzalloc(sizeof(*ia), GFP_KERNEL);
+	if (ia) {
+		ia->io = io;
+		ia->ap.uses_folios = true;
+		ia->ap.folios = fuse_folios_alloc(nfolios, GFP_KERNEL,
+						  &ia->ap.folio_descs);
+		if (!ia->ap.folios) {
+			kfree(ia);
+			ia = NULL;
+		}
+	}
+	return ia;
+}
+
 static void fuse_io_free(struct fuse_io_args *ia)
 {
 	kfree(ia->ap.pages);
 	kfree(ia);
 }
 
+static void fuse_io_folios_free(struct fuse_io_args *ia)
+{
+	kfree(ia->ap.folios);
+	kfree(ia);
+}
+
 static void fuse_aio_complete_req(struct fuse_mount *fm, struct fuse_args *args,
 				  int err)
 {
@@ -865,7 +890,7 @@ static void fuse_short_read(struct inode *inode, u64 attr_ver, size_t num_read,
 	 * reached the client fs yet.  So the hole is not present there.
 	 */
 	if (!fc->writeback_cache) {
-		loff_t pos = page_offset(ap->pages[0]) + num_read;
+		loff_t pos = folio_pos(ap->folios[0]) + num_read;
 		fuse_read_update_size(inode, pos, attr_ver);
 	}
 }
@@ -875,14 +900,14 @@ static int fuse_do_readfolio(struct file *file, struct folio *folio)
 	struct inode *inode = folio->mapping->host;
 	struct fuse_mount *fm = get_fuse_mount(inode);
 	loff_t pos = folio_pos(folio);
-	struct fuse_page_desc desc = { .length = PAGE_SIZE };
-	struct page *page = &folio->page;
+	struct fuse_folio_desc desc = { .length = PAGE_SIZE };
 	struct fuse_io_args ia = {
 		.ap.args.page_zeroing = true,
 		.ap.args.out_pages = true,
-		.ap.num_pages = 1,
-		.ap.pages = &page,
-		.ap.descs = &desc,
+		.ap.uses_folios = true,
+		.ap.num_folios = 1,
+		.ap.folios = &folio,
+		.ap.folio_descs = &desc,
 	};
 	ssize_t res;
 	u64 attr_ver;
@@ -941,8 +966,8 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
 	size_t num_read = args->out_args[0].size;
 	struct address_space *mapping = NULL;
 
-	for (i = 0; mapping == NULL && i < ap->num_pages; i++)
-		mapping = ap->pages[i]->mapping;
+	for (i = 0; mapping == NULL && i < ap->num_folios; i++)
+		mapping = ap->folios[i]->mapping;
 
 	if (mapping) {
 		struct inode *inode = mapping->host;
@@ -956,15 +981,12 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
 		fuse_invalidate_atime(inode);
 	}
 
-	for (i = 0; i < ap->num_pages; i++) {
-		struct folio *folio = page_folio(ap->pages[i]);
-
-		folio_end_read(folio, !err);
-	}
+	for (i = 0; i < ap->num_folios; i++)
+		folio_end_read(ap->folios[i], !err);
 	if (ia->ff)
 		fuse_file_put(ia->ff, false);
 
-	fuse_io_free(ia);
+	fuse_io_folios_free(ia);
 }
 
 static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
@@ -972,8 +994,9 @@ static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
 	struct fuse_file *ff = file->private_data;
 	struct fuse_mount *fm = ff->fm;
 	struct fuse_args_pages *ap = &ia->ap;
-	loff_t pos = page_offset(ap->pages[0]);
-	size_t count = ap->num_pages << PAGE_SHIFT;
+	loff_t pos = folio_pos(ap->folios[0]);
+	/* Currently, all folios in FUSE are one page */
+	size_t count = ap->num_folios << PAGE_SHIFT;
 	ssize_t res;
 	int err;
 
@@ -984,7 +1007,7 @@ static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
 	/* Don't overflow end offset */
 	if (pos + (count - 1) == LLONG_MAX) {
 		count--;
-		ap->descs[ap->num_pages - 1].length--;
+		ap->folio_descs[ap->num_folios - 1].length--;
 	}
 	WARN_ON((loff_t) (pos + count) < 0);
 
@@ -1045,16 +1068,16 @@ static void fuse_readahead(struct readahead_control *rac)
 			 */
 			break;
 
-		ia = fuse_io_alloc(NULL, cur_pages);
+		ia = fuse_io_folios_alloc(NULL, cur_pages);
 		if (!ia)
 			return;
 		ap = &ia->ap;
 
-		while (ap->num_pages < cur_pages) {
+		while (ap->num_folios < cur_pages) {
 			folio = readahead_folio(rac);
-			ap->pages[ap->num_pages] = &folio->page;
-			ap->descs[ap->num_pages].length = folio_size(folio);
-			ap->num_pages++;
+			ap->folios[ap->num_folios] = folio;
+			ap->folio_descs[ap->num_folios].length = folio_size(folio);
+			ap->num_folios++;
 		}
 		fuse_send_readpages(ia, rac->file);
 		nr_pages -= cur_pages;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 24a3da8400d16..b6877064c0719 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1029,6 +1029,18 @@ static inline struct page **fuse_pages_alloc(unsigned int npages, gfp_t flags,
 	return pages;
 }
 
+static inline struct folio **fuse_folios_alloc(unsigned int nfolios, gfp_t flags,
+					       struct fuse_folio_desc **desc)
+{
+	struct folio **folios;
+
+	folios = kzalloc(nfolios * (sizeof(struct folio *) +
+				    sizeof(struct fuse_folio_desc)), flags);
+	*desc = (void *) (folios + nfolios);
+
+	return folios;
+}
+
 static inline void fuse_page_descs_length_init(struct fuse_page_desc *descs,
 					       unsigned int index,
 					       unsigned int nr_pages)

From f2ef459bab7326f4800ec2098cf073fbda2185af Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 24 Oct 2024 10:18:03 -0700
Subject: [PATCH 0835/1530] fuse: convert writes (non-writeback) to use folios

Convert non-writeback write requests to use folios instead of pages.

No functional changes.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c   | 33 ++++++++++++++++++---------------
 fs/fuse/fuse_i.h |  2 +-
 2 files changed, 19 insertions(+), 16 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index ece1c0319e35e..b3d5b7b5da52e 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1197,8 +1197,8 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia,
 	bool short_write;
 	int err;
 
-	for (i = 0; i < ap->num_pages; i++)
-		fuse_wait_on_page_writeback(inode, ap->pages[i]->index);
+	for (i = 0; i < ap->num_folios; i++)
+		fuse_wait_on_folio_writeback(inode, ap->folios[i]);
 
 	fuse_write_args_fill(ia, ff, pos, count);
 	ia->write.in.flags = fuse_write_flags(iocb);
@@ -1210,10 +1210,10 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia,
 		err = -EIO;
 
 	short_write = ia->write.out.size < count;
-	offset = ap->descs[0].offset;
+	offset = ap->folio_descs[0].offset;
 	count = ia->write.out.size;
-	for (i = 0; i < ap->num_pages; i++) {
-		struct folio *folio = page_folio(ap->pages[i]);
+	for (i = 0; i < ap->num_folios; i++) {
+		struct folio *folio = ap->folios[i];
 
 		if (err) {
 			folio_clear_uptodate(folio);
@@ -1227,7 +1227,7 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia,
 			}
 			offset = 0;
 		}
-		if (ia->write.page_locked && (i == ap->num_pages - 1))
+		if (ia->write.folio_locked && (i == ap->num_folios - 1))
 			folio_unlock(folio);
 		folio_put(folio);
 	}
@@ -1243,11 +1243,12 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 	struct fuse_args_pages *ap = &ia->ap;
 	struct fuse_conn *fc = get_fuse_conn(mapping->host);
 	unsigned offset = pos & (PAGE_SIZE - 1);
+	unsigned int nr_pages = 0;
 	size_t count = 0;
 	int err;
 
 	ap->args.in_pages = true;
-	ap->descs[0].offset = offset;
+	ap->folio_descs[0].offset = offset;
 
 	do {
 		size_t tmp;
@@ -1283,9 +1284,10 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 		}
 
 		err = 0;
-		ap->pages[ap->num_pages] = &folio->page;
-		ap->descs[ap->num_pages].length = tmp;
-		ap->num_pages++;
+		ap->folios[ap->num_folios] = folio;
+		ap->folio_descs[ap->num_folios].length = tmp;
+		ap->num_folios++;
+		nr_pages++;
 
 		count += tmp;
 		pos += tmp;
@@ -1300,13 +1302,13 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 		if (folio_test_uptodate(folio)) {
 			folio_unlock(folio);
 		} else {
-			ia->write.page_locked = true;
+			ia->write.folio_locked = true;
 			break;
 		}
 		if (!fc->big_writes)
 			break;
 	} while (iov_iter_count(ii) && count < fc->max_write &&
-		 ap->num_pages < max_pages && offset == 0);
+		 nr_pages < max_pages && offset == 0);
 
 	return count > 0 ? count : err;
 }
@@ -1340,8 +1342,9 @@ static ssize_t fuse_perform_write(struct kiocb *iocb, struct iov_iter *ii)
 		unsigned int nr_pages = fuse_wr_pages(pos, iov_iter_count(ii),
 						      fc->max_pages);
 
-		ap->pages = fuse_pages_alloc(nr_pages, GFP_KERNEL, &ap->descs);
-		if (!ap->pages) {
+		ap->uses_folios = true;
+		ap->folios = fuse_folios_alloc(nr_pages, GFP_KERNEL, &ap->folio_descs);
+		if (!ap->folios) {
 			err = -ENOMEM;
 			break;
 		}
@@ -1363,7 +1366,7 @@ static ssize_t fuse_perform_write(struct kiocb *iocb, struct iov_iter *ii)
 					err = -EIO;
 			}
 		}
-		kfree(ap->pages);
+		kfree(ap->folios);
 	} while (!err && iov_iter_count(ii));
 
 	fuse_write_update_attr(inode, pos, res);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index b6877064c0719..201b08562b6b8 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1096,7 +1096,7 @@ struct fuse_io_args {
 		struct {
 			struct fuse_write_in in;
 			struct fuse_write_out out;
-			bool page_locked;
+			bool folio_locked;
 		} write;
 	};
 	struct fuse_args_pages ap;

From ac1cf6e3bbe3dd371bd61a423437c1f67bba8b2a Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 24 Oct 2024 10:18:04 -0700
Subject: [PATCH 0836/1530] fuse: convert ioctls to use folios

Convert ioctl requests to use folios instead of pages.

No functional changes.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/fuse_i.h | 10 ++++++++++
 fs/fuse/ioctl.c  | 32 ++++++++++++++++----------------
 2 files changed, 26 insertions(+), 16 deletions(-)

diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 201b08562b6b8..c1c7def8ee4be 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1051,6 +1051,16 @@ static inline void fuse_page_descs_length_init(struct fuse_page_desc *descs,
 		descs[i].length = PAGE_SIZE - descs[i].offset;
 }
 
+static inline void fuse_folio_descs_length_init(struct fuse_folio_desc *descs,
+						unsigned int index,
+						unsigned int nr_folios)
+{
+	int i;
+
+	for (i = index; i < index + nr_folios; i++)
+		descs[i].length = PAGE_SIZE - descs[i].offset;
+}
+
 static inline void fuse_sync_bucket_dec(struct fuse_sync_bucket *bucket)
 {
 	/* Need RCU protection to prevent use after free after the decrement */
diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c
index a6c8ee5516351..1c77d8a279506 100644
--- a/fs/fuse/ioctl.c
+++ b/fs/fuse/ioctl.c
@@ -251,12 +251,12 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 	BUILD_BUG_ON(sizeof(struct fuse_ioctl_iovec) * FUSE_IOCTL_MAX_IOV > PAGE_SIZE);
 
 	err = -ENOMEM;
-	ap.pages = fuse_pages_alloc(fm->fc->max_pages, GFP_KERNEL, &ap.descs);
+	ap.folios = fuse_folios_alloc(fm->fc->max_pages, GFP_KERNEL, &ap.folio_descs);
 	iov_page = (struct iovec *) __get_free_page(GFP_KERNEL);
-	if (!ap.pages || !iov_page)
+	if (!ap.folios || !iov_page)
 		goto out;
 
-	fuse_page_descs_length_init(ap.descs, 0, fm->fc->max_pages);
+	fuse_folio_descs_length_init(ap.folio_descs, 0, fm->fc->max_pages);
 
 	/*
 	 * If restricted, initialize IO parameters as encoded in @cmd.
@@ -306,14 +306,14 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 	err = -ENOMEM;
 	if (max_pages > fm->fc->max_pages)
 		goto out;
-	while (ap.num_pages < max_pages) {
-		ap.pages[ap.num_pages] = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
-		if (!ap.pages[ap.num_pages])
+	ap.uses_folios = true;
+	while (ap.num_folios < max_pages) {
+		ap.folios[ap.num_folios] = folio_alloc(GFP_KERNEL | __GFP_HIGHMEM, 0);
+		if (!ap.folios[ap.num_folios])
 			goto out;
-		ap.num_pages++;
+		ap.num_folios++;
 	}
 
-
 	/* okay, let's send it to the client */
 	ap.args.opcode = FUSE_IOCTL;
 	ap.args.nodeid = ff->nodeid;
@@ -327,8 +327,8 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 
 		err = -EFAULT;
 		iov_iter_init(&ii, ITER_SOURCE, in_iov, in_iovs, in_size);
-		for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= ap.num_pages); i++) {
-			c = copy_page_from_iter(ap.pages[i], 0, PAGE_SIZE, &ii);
+		for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= ap.num_folios); i++) {
+			c = copy_folio_from_iter(ap.folios[i], 0, PAGE_SIZE, &ii);
 			if (c != PAGE_SIZE && iov_iter_count(&ii))
 				goto out;
 		}
@@ -366,7 +366,7 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 		    in_iovs + out_iovs > FUSE_IOCTL_MAX_IOV)
 			goto out;
 
-		vaddr = kmap_local_page(ap.pages[0]);
+		vaddr = kmap_local_folio(ap.folios[0], 0);
 		err = fuse_copy_ioctl_iovec(fm->fc, iov_page, vaddr,
 					    transferred, in_iovs + out_iovs,
 					    (flags & FUSE_IOCTL_COMPAT) != 0);
@@ -394,17 +394,17 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 
 	err = -EFAULT;
 	iov_iter_init(&ii, ITER_DEST, out_iov, out_iovs, transferred);
-	for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= ap.num_pages); i++) {
-		c = copy_page_to_iter(ap.pages[i], 0, PAGE_SIZE, &ii);
+	for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= ap.num_folios); i++) {
+		c = copy_folio_to_iter(ap.folios[i], 0, PAGE_SIZE, &ii);
 		if (c != PAGE_SIZE && iov_iter_count(&ii))
 			goto out;
 	}
 	err = 0;
  out:
 	free_page((unsigned long) iov_page);
-	while (ap.num_pages)
-		__free_page(ap.pages[--ap.num_pages]);
-	kfree(ap.pages);
+	while (ap.num_folios)
+		folio_put(ap.folios[--ap.num_folios]);
+	kfree(ap.folios);
 
 	return err ? err : outarg.result;
 }

From 448895df0366041366a84861350ce471446bf560 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 24 Oct 2024 10:18:05 -0700
Subject: [PATCH 0837/1530] fuse: convert retrieves to use folios

Convert retrieve requests to use folios instead of pages.

No functional changes.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dev.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 70da1184a3f61..563a0bfa0e951 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1728,7 +1728,7 @@ static void fuse_retrieve_end(struct fuse_mount *fm, struct fuse_args *args,
 	struct fuse_retrieve_args *ra =
 		container_of(args, typeof(*ra), ap.args);
 
-	release_pages(ra->ap.pages, ra->ap.num_pages);
+	release_pages(ra->ap.folios, ra->ap.num_folios);
 	kfree(ra);
 }
 
@@ -1742,7 +1742,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 	unsigned int num;
 	unsigned int offset;
 	size_t total_len = 0;
-	unsigned int num_pages;
+	unsigned int num_pages, cur_pages = 0;
 	struct fuse_conn *fc = fm->fc;
 	struct fuse_retrieve_args *ra;
 	size_t args_size = sizeof(*ra);
@@ -1761,15 +1761,16 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 	num_pages = (num + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	num_pages = min(num_pages, fc->max_pages);
 
-	args_size += num_pages * (sizeof(ap->pages[0]) + sizeof(ap->descs[0]));
+	args_size += num_pages * (sizeof(ap->folios[0]) + sizeof(ap->folio_descs[0]));
 
 	ra = kzalloc(args_size, GFP_KERNEL);
 	if (!ra)
 		return -ENOMEM;
 
 	ap = &ra->ap;
-	ap->pages = (void *) (ra + 1);
-	ap->descs = (void *) (ap->pages + num_pages);
+	ap->folios = (void *) (ra + 1);
+	ap->folio_descs = (void *) (ap->folios + num_pages);
+	ap->uses_folios = true;
 
 	args = &ap->args;
 	args->nodeid = outarg->nodeid;
@@ -1780,7 +1781,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 
 	index = outarg->offset >> PAGE_SHIFT;
 
-	while (num && ap->num_pages < num_pages) {
+	while (num && cur_pages < num_pages) {
 		struct folio *folio;
 		unsigned int this_num;
 
@@ -1789,10 +1790,11 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 			break;
 
 		this_num = min_t(unsigned, num, PAGE_SIZE - offset);
-		ap->pages[ap->num_pages] = &folio->page;
-		ap->descs[ap->num_pages].offset = offset;
-		ap->descs[ap->num_pages].length = this_num;
-		ap->num_pages++;
+		ap->folios[ap->num_folios] = folio;
+		ap->folio_descs[ap->num_folios].offset = offset;
+		ap->folio_descs[ap->num_folios].length = this_num;
+		ap->num_folios++;
+		cur_pages++;
 
 		offset = 0;
 		num -= this_num;

From cbe9c115b7441dd790540436118eee4626ec9979 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 24 Oct 2024 10:18:06 -0700
Subject: [PATCH 0838/1530] fuse: convert writebacks to use folios

Convert writeback requests to use folios instead of pages.

No functional changes.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c | 126 +++++++++++++++++++++++++------------------------
 1 file changed, 64 insertions(+), 62 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index b3d5b7b5da52e..99af3c39e5298 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -436,7 +436,7 @@ static struct fuse_writepage_args *fuse_find_writeback(struct fuse_inode *fi,
 		wpa = rb_entry(n, struct fuse_writepage_args, writepages_entry);
 		WARN_ON(get_fuse_inode(wpa->inode) != fi);
 		curr_index = wpa->ia.write.in.offset >> PAGE_SHIFT;
-		if (idx_from >= curr_index + wpa->ia.ap.num_pages)
+		if (idx_from >= curr_index + wpa->ia.ap.num_folios)
 			n = n->rb_right;
 		else if (idx_to < curr_index)
 			n = n->rb_left;
@@ -1837,12 +1837,12 @@ static void fuse_writepage_free(struct fuse_writepage_args *wpa)
 	if (wpa->bucket)
 		fuse_sync_bucket_dec(wpa->bucket);
 
-	for (i = 0; i < ap->num_pages; i++)
-		__free_page(ap->pages[i]);
+	for (i = 0; i < ap->num_folios; i++)
+		folio_put(ap->folios[i]);
 
 	fuse_file_put(wpa->ia.ff, false);
 
-	kfree(ap->pages);
+	kfree(ap->folios);
 	kfree(wpa);
 }
 
@@ -1862,8 +1862,8 @@ static void fuse_writepage_finish(struct fuse_writepage_args *wpa)
 	struct fuse_inode *fi = get_fuse_inode(inode);
 	int i;
 
-	for (i = 0; i < ap->num_pages; i++)
-		fuse_writepage_finish_stat(inode, page_folio(ap->pages[i]));
+	for (i = 0; i < ap->num_folios; i++)
+		fuse_writepage_finish_stat(inode, ap->folios[i]);
 
 	wake_up(&fi->page_waitq);
 }
@@ -1878,7 +1878,8 @@ __acquires(fi->lock)
 	struct fuse_inode *fi = get_fuse_inode(wpa->inode);
 	struct fuse_write_in *inarg = &wpa->ia.write.in;
 	struct fuse_args *args = &wpa->ia.ap.args;
-	__u64 data_size = wpa->ia.ap.num_pages * PAGE_SIZE;
+	/* Currently, all folios in FUSE are one page */
+	__u64 data_size = wpa->ia.ap.num_folios * PAGE_SIZE;
 	int err;
 
 	fi->writectr++;
@@ -1919,7 +1920,7 @@ __acquires(fi->lock)
 		next = aux->next;
 		aux->next = NULL;
 		fuse_writepage_finish_stat(aux->inode,
-					   page_folio(aux->ia.ap.pages[0]));
+					   aux->ia.ap.folios[0]);
 		fuse_writepage_free(aux);
 	}
 
@@ -1954,11 +1955,11 @@ static struct fuse_writepage_args *fuse_insert_writeback(struct rb_root *root,
 						struct fuse_writepage_args *wpa)
 {
 	pgoff_t idx_from = wpa->ia.write.in.offset >> PAGE_SHIFT;
-	pgoff_t idx_to = idx_from + wpa->ia.ap.num_pages - 1;
+	pgoff_t idx_to = idx_from + wpa->ia.ap.num_folios - 1;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node  *parent = NULL;
 
-	WARN_ON(!wpa->ia.ap.num_pages);
+	WARN_ON(!wpa->ia.ap.num_folios);
 	while (*p) {
 		struct fuse_writepage_args *curr;
 		pgoff_t curr_index;
@@ -1969,7 +1970,7 @@ static struct fuse_writepage_args *fuse_insert_writeback(struct rb_root *root,
 		WARN_ON(curr->inode != wpa->inode);
 		curr_index = curr->ia.write.in.offset >> PAGE_SHIFT;
 
-		if (idx_from >= curr_index + curr->ia.ap.num_pages)
+		if (idx_from >= curr_index + curr->ia.ap.num_folios)
 			p = &(*p)->rb_right;
 		else if (idx_to < curr_index)
 			p = &(*p)->rb_left;
@@ -2101,9 +2102,10 @@ static struct fuse_writepage_args *fuse_writepage_args_alloc(void)
 	wpa = kzalloc(sizeof(*wpa), GFP_NOFS);
 	if (wpa) {
 		ap = &wpa->ia.ap;
-		ap->num_pages = 0;
-		ap->pages = fuse_pages_alloc(1, GFP_NOFS, &ap->descs);
-		if (!ap->pages) {
+		ap->num_folios = 0;
+		ap->uses_folios = true;
+		ap->folios = fuse_folios_alloc(1, GFP_NOFS, &ap->folio_descs);
+		if (!ap->folios) {
 			kfree(wpa);
 			wpa = NULL;
 		}
@@ -2127,16 +2129,16 @@ static void fuse_writepage_add_to_bucket(struct fuse_conn *fc,
 }
 
 static void fuse_writepage_args_page_fill(struct fuse_writepage_args *wpa, struct folio *folio,
-					  struct folio *tmp_folio, uint32_t page_index)
+					  struct folio *tmp_folio, uint32_t folio_index)
 {
 	struct inode *inode = folio->mapping->host;
 	struct fuse_args_pages *ap = &wpa->ia.ap;
 
 	folio_copy(tmp_folio, folio);
 
-	ap->pages[page_index] = &tmp_folio->page;
-	ap->descs[page_index].offset = 0;
-	ap->descs[page_index].length = PAGE_SIZE;
+	ap->folios[folio_index] = tmp_folio;
+	ap->folio_descs[folio_index].offset = 0;
+	ap->folio_descs[folio_index].length = PAGE_SIZE;
 
 	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
 	node_stat_add_folio(tmp_folio, NR_WRITEBACK_TEMP);
@@ -2193,7 +2195,7 @@ static int fuse_writepage_locked(struct folio *folio)
 		goto err_writepage_args;
 
 	ap = &wpa->ia.ap;
-	ap->num_pages = 1;
+	ap->num_folios = 1;
 
 	folio_start_writeback(folio);
 	fuse_writepage_args_page_fill(wpa, folio, tmp_folio, 0);
@@ -2221,32 +2223,32 @@ struct fuse_fill_wb_data {
 	struct fuse_writepage_args *wpa;
 	struct fuse_file *ff;
 	struct inode *inode;
-	struct page **orig_pages;
-	unsigned int max_pages;
+	struct folio **orig_folios;
+	unsigned int max_folios;
 };
 
 static bool fuse_pages_realloc(struct fuse_fill_wb_data *data)
 {
 	struct fuse_args_pages *ap = &data->wpa->ia.ap;
 	struct fuse_conn *fc = get_fuse_conn(data->inode);
-	struct page **pages;
-	struct fuse_page_desc *descs;
-	unsigned int npages = min_t(unsigned int,
-				    max_t(unsigned int, data->max_pages * 2,
-					  FUSE_DEFAULT_MAX_PAGES_PER_REQ),
+	struct folio **folios;
+	struct fuse_folio_desc *descs;
+	unsigned int nfolios = min_t(unsigned int,
+				     max_t(unsigned int, data->max_folios * 2,
+					   FUSE_DEFAULT_MAX_PAGES_PER_REQ),
 				    fc->max_pages);
-	WARN_ON(npages <= data->max_pages);
+	WARN_ON(nfolios <= data->max_folios);
 
-	pages = fuse_pages_alloc(npages, GFP_NOFS, &descs);
-	if (!pages)
+	folios = fuse_folios_alloc(nfolios, GFP_NOFS, &descs);
+	if (!folios)
 		return false;
 
-	memcpy(pages, ap->pages, sizeof(struct page *) * ap->num_pages);
-	memcpy(descs, ap->descs, sizeof(struct fuse_page_desc) * ap->num_pages);
-	kfree(ap->pages);
-	ap->pages = pages;
-	ap->descs = descs;
-	data->max_pages = npages;
+	memcpy(folios, ap->folios, sizeof(struct folio *) * ap->num_folios);
+	memcpy(descs, ap->folio_descs, sizeof(struct fuse_folio_desc) * ap->num_folios);
+	kfree(ap->folios);
+	ap->folios = folios;
+	ap->folio_descs = descs;
+	data->max_folios = nfolios;
 
 	return true;
 }
@@ -2256,7 +2258,7 @@ static void fuse_writepages_send(struct fuse_fill_wb_data *data)
 	struct fuse_writepage_args *wpa = data->wpa;
 	struct inode *inode = data->inode;
 	struct fuse_inode *fi = get_fuse_inode(inode);
-	int num_pages = wpa->ia.ap.num_pages;
+	int num_folios = wpa->ia.ap.num_folios;
 	int i;
 
 	spin_lock(&fi->lock);
@@ -2264,8 +2266,8 @@ static void fuse_writepages_send(struct fuse_fill_wb_data *data)
 	fuse_flush_writepages(inode);
 	spin_unlock(&fi->lock);
 
-	for (i = 0; i < num_pages; i++)
-		end_page_writeback(data->orig_pages[i]);
+	for (i = 0; i < num_folios; i++)
+		folio_end_writeback(data->orig_folios[i]);
 }
 
 /*
@@ -2276,15 +2278,15 @@ static void fuse_writepages_send(struct fuse_fill_wb_data *data)
  * swapping the new temp page with the old one.
  */
 static bool fuse_writepage_add(struct fuse_writepage_args *new_wpa,
-			       struct page *page)
+			       struct folio *folio)
 {
 	struct fuse_inode *fi = get_fuse_inode(new_wpa->inode);
 	struct fuse_writepage_args *tmp;
 	struct fuse_writepage_args *old_wpa;
 	struct fuse_args_pages *new_ap = &new_wpa->ia.ap;
 
-	WARN_ON(new_ap->num_pages != 0);
-	new_ap->num_pages = 1;
+	WARN_ON(new_ap->num_folios != 0);
+	new_ap->num_folios = 1;
 
 	spin_lock(&fi->lock);
 	old_wpa = fuse_insert_writeback(&fi->writepages, new_wpa);
@@ -2298,9 +2300,9 @@ static bool fuse_writepage_add(struct fuse_writepage_args *new_wpa,
 
 		WARN_ON(tmp->inode != new_wpa->inode);
 		curr_index = tmp->ia.write.in.offset >> PAGE_SHIFT;
-		if (curr_index == page->index) {
-			WARN_ON(tmp->ia.ap.num_pages != 1);
-			swap(tmp->ia.ap.pages[0], new_ap->pages[0]);
+		if (curr_index == folio->index) {
+			WARN_ON(tmp->ia.ap.num_folios != 1);
+			swap(tmp->ia.ap.folios[0], new_ap->folios[0]);
 			break;
 		}
 	}
@@ -2314,7 +2316,7 @@ static bool fuse_writepage_add(struct fuse_writepage_args *new_wpa,
 
 	if (tmp) {
 		fuse_writepage_finish_stat(new_wpa->inode,
-					   page_folio(new_ap->pages[0]));
+					   folio);
 		fuse_writepage_free(new_wpa);
 	}
 
@@ -2325,7 +2327,7 @@ static bool fuse_writepage_need_send(struct fuse_conn *fc, struct folio *folio,
 				     struct fuse_args_pages *ap,
 				     struct fuse_fill_wb_data *data)
 {
-	WARN_ON(!ap->num_pages);
+	WARN_ON(!ap->num_folios);
 
 	/*
 	 * Being under writeback is unlikely but possible.  For example direct
@@ -2337,19 +2339,19 @@ static bool fuse_writepage_need_send(struct fuse_conn *fc, struct folio *folio,
 		return true;
 
 	/* Reached max pages */
-	if (ap->num_pages == fc->max_pages)
+	if (ap->num_folios == fc->max_pages)
 		return true;
 
 	/* Reached max write bytes */
-	if ((ap->num_pages + 1) * PAGE_SIZE > fc->max_write)
+	if ((ap->num_folios + 1) * PAGE_SIZE > fc->max_write)
 		return true;
 
 	/* Discontinuity */
-	if (data->orig_pages[ap->num_pages - 1]->index + 1 != folio_index(folio))
+	if (data->orig_folios[ap->num_folios - 1]->index + 1 != folio_index(folio))
 		return true;
 
 	/* Need to grow the pages array?  If so, did the expansion fail? */
-	if (ap->num_pages == data->max_pages && !fuse_pages_realloc(data))
+	if (ap->num_folios == data->max_folios && !fuse_pages_realloc(data))
 		return true;
 
 	return false;
@@ -2393,7 +2395,7 @@ static int fuse_writepages_fill(struct folio *folio,
 	 * This is ensured by holding the page lock in page_mkwrite() while
 	 * checking fuse_page_is_writeback().  We already hold the page lock
 	 * since clear_page_dirty_for_io() and keep it held until we add the
-	 * request to the fi->writepages list and increment ap->num_pages.
+	 * request to the fi->writepages list and increment ap->num_folios.
 	 * After this fuse_page_is_writeback() will indicate that the page is
 	 * under writeback, so we can release the page lock.
 	 */
@@ -2405,13 +2407,13 @@ static int fuse_writepages_fill(struct folio *folio,
 			goto out_unlock;
 		}
 		fuse_file_get(wpa->ia.ff);
-		data->max_pages = 1;
+		data->max_folios = 1;
 		ap = &wpa->ia.ap;
 	}
 	folio_start_writeback(folio);
 
-	fuse_writepage_args_page_fill(wpa, folio, tmp_folio, ap->num_pages);
-	data->orig_pages[ap->num_pages] = &folio->page;
+	fuse_writepage_args_page_fill(wpa, folio, tmp_folio, ap->num_folios);
+	data->orig_folios[ap->num_folios] = folio;
 
 	err = 0;
 	if (data->wpa) {
@@ -2420,9 +2422,9 @@ static int fuse_writepages_fill(struct folio *folio,
 		 * fuse_page_is_writeback().
 		 */
 		spin_lock(&fi->lock);
-		ap->num_pages++;
+		ap->num_folios++;
 		spin_unlock(&fi->lock);
-	} else if (fuse_writepage_add(wpa, &folio->page)) {
+	} else if (fuse_writepage_add(wpa, folio)) {
 		data->wpa = wpa;
 	} else {
 		folio_end_writeback(folio);
@@ -2454,21 +2456,21 @@ static int fuse_writepages(struct address_space *mapping,
 	data.ff = NULL;
 
 	err = -ENOMEM;
-	data.orig_pages = kcalloc(fc->max_pages,
-				  sizeof(struct page *),
-				  GFP_NOFS);
-	if (!data.orig_pages)
+	data.orig_folios = kcalloc(fc->max_pages,
+				   sizeof(struct folio *),
+				   GFP_NOFS);
+	if (!data.orig_folios)
 		goto out;
 
 	err = write_cache_pages(mapping, wbc, fuse_writepages_fill, &data);
 	if (data.wpa) {
-		WARN_ON(!data.wpa->ia.ap.num_pages);
+		WARN_ON(!data.wpa->ia.ap.num_folios);
 		fuse_writepages_send(&data);
 	}
 	if (data.ff)
 		fuse_file_put(data.ff, false);
 
-	kfree(data.orig_pages);
+	kfree(data.orig_folios);
 out:
 	return err;
 }

From 7fce207af5ec074a9a50e90eb866b17ca4a90f06 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 24 Oct 2024 10:18:07 -0700
Subject: [PATCH 0839/1530] mm/writeback: add folio_mark_dirty_lock()

Add a new convenience helper folio_mark_dirty_lock() that grabs the
folio lock before calling folio_mark_dirty().

Refactor set_page_dirty_lock() to directly use folio_mark_dirty_lock().

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 include/linux/mm.h  |  1 +
 mm/folio-compat.c   |  6 ++++++
 mm/page-writeback.c | 22 +++++++++++-----------
 3 files changed, 18 insertions(+), 11 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ecf63d2b05825..446d7096c48fe 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2539,6 +2539,7 @@ struct kvec;
 struct page *get_dump_page(unsigned long addr);
 
 bool folio_mark_dirty(struct folio *folio);
+bool folio_mark_dirty_lock(struct folio *folio);
 bool set_page_dirty(struct page *page);
 int set_page_dirty_lock(struct page *page);
 
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 80746182e9e8e..1d1832e2a599d 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -52,6 +52,12 @@ bool set_page_dirty(struct page *page)
 }
 EXPORT_SYMBOL(set_page_dirty);
 
+int set_page_dirty_lock(struct page *page)
+{
+	return folio_mark_dirty_lock(page_folio(page));
+}
+EXPORT_SYMBOL(set_page_dirty_lock);
+
 bool clear_page_dirty_for_io(struct page *page)
 {
 	return folio_clear_dirty_for_io(page_folio(page));
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index fcd4c1439cb9c..db00a66d8b84d 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2914,25 +2914,25 @@ bool folio_mark_dirty(struct folio *folio)
 EXPORT_SYMBOL(folio_mark_dirty);
 
 /*
- * set_page_dirty() is racy if the caller has no reference against
- * page->mapping->host, and if the page is unlocked.  This is because another
- * CPU could truncate the page off the mapping and then free the mapping.
+ * folio_mark_dirty() is racy if the caller has no reference against
+ * folio->mapping->host, and if the folio is unlocked.  This is because another
+ * CPU could truncate the folio off the mapping and then free the mapping.
  *
- * Usually, the page _is_ locked, or the caller is a user-space process which
+ * Usually, the folio _is_ locked, or the caller is a user-space process which
  * holds a reference on the inode by having an open file.
  *
- * In other cases, the page should be locked before running set_page_dirty().
+ * In other cases, the folio should be locked before running folio_mark_dirty().
  */
-int set_page_dirty_lock(struct page *page)
+bool folio_mark_dirty_lock(struct folio *folio)
 {
-	int ret;
+	bool ret;
 
-	lock_page(page);
-	ret = set_page_dirty(page);
-	unlock_page(page);
+	folio_lock(folio);
+	ret = folio_mark_dirty(folio);
+	folio_unlock(folio);
 	return ret;
 }
-EXPORT_SYMBOL(set_page_dirty_lock);
+EXPORT_SYMBOL(folio_mark_dirty_lock);
 
 /*
  * This cancels just the dirty bit on the kernel page itself, it does NOT

From 3b97c3652d9128ab7f8c9b8adec6108611fdb153 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 24 Oct 2024 10:18:08 -0700
Subject: [PATCH 0840/1530] fuse: convert direct io to use folios

Convert direct io requests to use folios instead of pages.

No functional changes.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c   | 80 +++++++++++++++++++++---------------------------
 fs/fuse/fuse_i.h | 22 -------------
 2 files changed, 35 insertions(+), 67 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 99af3c39e5298..14af8c41fc832 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -665,11 +665,11 @@ static void fuse_release_user_pages(struct fuse_args_pages *ap, ssize_t nres,
 {
 	unsigned int i;
 
-	for (i = 0; i < ap->num_pages; i++) {
+	for (i = 0; i < ap->num_folios; i++) {
 		if (should_dirty)
-			set_page_dirty_lock(ap->pages[i]);
+			folio_mark_dirty_lock(ap->folios[i]);
 		if (ap->args.is_pinned)
-			unpin_user_page(ap->pages[i]);
+			unpin_folio(ap->folios[i]);
 	}
 
 	if (nres > 0 && ap->args.invalidate_vmap)
@@ -742,24 +742,6 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos)
 	kref_put(&io->refcnt, fuse_io_release);
 }
 
-static struct fuse_io_args *fuse_io_alloc(struct fuse_io_priv *io,
-					  unsigned int npages)
-{
-	struct fuse_io_args *ia;
-
-	ia = kzalloc(sizeof(*ia), GFP_KERNEL);
-	if (ia) {
-		ia->io = io;
-		ia->ap.pages = fuse_pages_alloc(npages, GFP_KERNEL,
-						&ia->ap.descs);
-		if (!ia->ap.pages) {
-			kfree(ia);
-			ia = NULL;
-		}
-	}
-	return ia;
-}
-
 static struct fuse_io_args *fuse_io_folios_alloc(struct fuse_io_priv *io,
 						 unsigned int nfolios)
 {
@@ -779,12 +761,6 @@ static struct fuse_io_args *fuse_io_folios_alloc(struct fuse_io_priv *io,
 	return ia;
 }
 
-static void fuse_io_free(struct fuse_io_args *ia)
-{
-	kfree(ia->ap.pages);
-	kfree(ia);
-}
-
 static void fuse_io_folios_free(struct fuse_io_args *ia)
 {
 	kfree(ia->ap.folios);
@@ -821,7 +797,7 @@ static void fuse_aio_complete_req(struct fuse_mount *fm, struct fuse_args *args,
 	fuse_release_user_pages(&ia->ap, err ?: nres, io->should_dirty);
 
 	fuse_aio_complete(io, err, pos);
-	fuse_io_free(ia);
+	fuse_io_folios_free(ia);
 }
 
 static ssize_t fuse_async_req_send(struct fuse_mount *fm,
@@ -1531,6 +1507,7 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
 			       bool use_pages_for_kvec_io)
 {
 	bool flush_or_invalidate = false;
+	unsigned int nr_pages = 0;
 	size_t nbytes = 0;  /* # bytes already packed in req */
 	ssize_t ret = 0;
 
@@ -1560,15 +1537,23 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
 		}
 	}
 
-	while (nbytes < *nbytesp && ap->num_pages < max_pages) {
-		unsigned npages;
+	/*
+	 * Until there is support for iov_iter_extract_folios(), we have to
+	 * manually extract pages using iov_iter_extract_pages() and then
+	 * copy that to a folios array.
+	 */
+	struct page **pages = kzalloc(max_pages * sizeof(struct page *),
+				      GFP_KERNEL);
+	if (!pages)
+		return -ENOMEM;
+
+	while (nbytes < *nbytesp && nr_pages < max_pages) {
+		unsigned nfolios, i;
 		size_t start;
-		struct page **pt_pages;
 
-		pt_pages = &ap->pages[ap->num_pages];
-		ret = iov_iter_extract_pages(ii, &pt_pages,
+		ret = iov_iter_extract_pages(ii, &pages,
 					     *nbytesp - nbytes,
-					     max_pages - ap->num_pages,
+					     max_pages - nr_pages,
 					     0, &start);
 		if (ret < 0)
 			break;
@@ -1576,15 +1561,20 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
 		nbytes += ret;
 
 		ret += start;
-		npages = DIV_ROUND_UP(ret, PAGE_SIZE);
+		/* Currently, all folios in FUSE are one page */
+		nfolios = DIV_ROUND_UP(ret, PAGE_SIZE);
 
-		ap->descs[ap->num_pages].offset = start;
-		fuse_page_descs_length_init(ap->descs, ap->num_pages, npages);
+		ap->folio_descs[ap->num_folios].offset = start;
+		fuse_folio_descs_length_init(ap->folio_descs, ap->num_folios, nfolios);
+		for (i = 0; i < nfolios; i++)
+			ap->folios[i + ap->num_folios] = page_folio(pages[i]);
 
-		ap->num_pages += npages;
-		ap->descs[ap->num_pages - 1].length -=
+		ap->num_folios += nfolios;
+		ap->folio_descs[ap->num_folios - 1].length -=
 			(PAGE_SIZE - ret) & (PAGE_SIZE - 1);
+		nr_pages += nfolios;
 	}
+	kfree(pages);
 
 	if (write && flush_or_invalidate)
 		flush_kernel_vmap_range(ap->args.vmap_base, nbytes);
@@ -1624,14 +1614,14 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 	bool fopen_direct_io = ff->open_flags & FOPEN_DIRECT_IO;
 
 	max_pages = iov_iter_npages(iter, fc->max_pages);
-	ia = fuse_io_alloc(io, max_pages);
+	ia = fuse_io_folios_alloc(io, max_pages);
 	if (!ia)
 		return -ENOMEM;
 
 	if (fopen_direct_io && fc->direct_io_allow_mmap) {
 		res = filemap_write_and_wait_range(mapping, pos, pos + count - 1);
 		if (res) {
-			fuse_io_free(ia);
+			fuse_io_folios_free(ia);
 			return res;
 		}
 	}
@@ -1646,7 +1636,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 	if (fopen_direct_io && write) {
 		res = invalidate_inode_pages2_range(mapping, idx_from, idx_to);
 		if (res) {
-			fuse_io_free(ia);
+			fuse_io_folios_free(ia);
 			return res;
 		}
 	}
@@ -1673,7 +1663,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 
 		if (!io->async || nres < 0) {
 			fuse_release_user_pages(&ia->ap, nres, io->should_dirty);
-			fuse_io_free(ia);
+			fuse_io_folios_free(ia);
 		}
 		ia = NULL;
 		if (nres < 0) {
@@ -1692,13 +1682,13 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 		}
 		if (count) {
 			max_pages = iov_iter_npages(iter, fc->max_pages);
-			ia = fuse_io_alloc(io, max_pages);
+			ia = fuse_io_folios_alloc(io, max_pages);
 			if (!ia)
 				break;
 		}
 	}
 	if (ia)
-		fuse_io_free(ia);
+		fuse_io_folios_free(ia);
 	if (res > 0)
 		*ppos = pos;
 
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index c1c7def8ee4be..d26d278da886a 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1017,18 +1017,6 @@ static inline bool fuse_is_bad(struct inode *inode)
 	return unlikely(test_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state));
 }
 
-static inline struct page **fuse_pages_alloc(unsigned int npages, gfp_t flags,
-					     struct fuse_page_desc **desc)
-{
-	struct page **pages;
-
-	pages = kzalloc(npages * (sizeof(struct page *) +
-				  sizeof(struct fuse_page_desc)), flags);
-	*desc = (void *) (pages + npages);
-
-	return pages;
-}
-
 static inline struct folio **fuse_folios_alloc(unsigned int nfolios, gfp_t flags,
 					       struct fuse_folio_desc **desc)
 {
@@ -1041,16 +1029,6 @@ static inline struct folio **fuse_folios_alloc(unsigned int nfolios, gfp_t flags
 	return folios;
 }
 
-static inline void fuse_page_descs_length_init(struct fuse_page_desc *descs,
-					       unsigned int index,
-					       unsigned int nr_pages)
-{
-	int i;
-
-	for (i = index; i < index + nr_pages; i++)
-		descs[i].length = PAGE_SIZE - descs[i].offset;
-}
-
 static inline void fuse_folio_descs_length_init(struct fuse_folio_desc *descs,
 						unsigned int index,
 						unsigned int nr_folios)

From ee51baa817eec7c5182c1e4450c4d1e8469faa96 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Mon, 9 Sep 2024 23:38:59 +0200
Subject: [PATCH 0841/1530] gfs2: Faster gfs2_upgrade_iopen_glock wakeups

Move function needs_demote() to glock.h and rename it to
glock_needs_demote().  In handle_callback(), wake up the glock when
setting the GLF_PENDING_DEMOTE flag as well.  (Setting the GLF_DEMOTE
flag already triggered a wake-up.)

With that, check for glock_needs_demote() in gfs2_upgrade_iopen_glock()
to wake up when either of those flags is set for the inode glock: the
faster we can react to contention, the better.

The GLF_PENDING_DEMOTE flag is only used for inode glocks (see
gfs2_glock_cb()) so it's okay to only check for the GLF_DEMOTE flag in
gfs2_drop_inode().  Still, using glock_needs_demote() there as well
makes the code a little easier to read.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c | 23 +++++++----------------
 fs/gfs2/glock.h |  6 ++++++
 fs/gfs2/super.c |  4 ++--
 3 files changed, 15 insertions(+), 18 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 9273ec5345eda..4567c8c60a037 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -563,11 +563,11 @@ static void state_change(struct gfs2_glock *gl, unsigned int new_state)
 	gl->gl_tchange = jiffies;
 }
 
-static void gfs2_set_demote(struct gfs2_glock *gl)
+static void gfs2_set_demote(int nr, struct gfs2_glock *gl)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 
-	set_bit(GLF_DEMOTE, &gl->gl_flags);
+	set_bit(nr, &gl->gl_flags);
 	smp_mb();
 	wake_up(&sdp->sd_async_glock_wait);
 }
@@ -1101,7 +1101,7 @@ static void glock_work_func(struct work_struct *work)
 
 		if (!delay) {
 			clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags);
-			gfs2_set_demote(gl);
+			gfs2_set_demote(GLF_DEMOTE, gl);
 		}
 	}
 	run_queue(gl, 0);
@@ -1443,10 +1443,7 @@ int gfs2_glock_async_wait(unsigned int num_gh, struct gfs2_holder *ghs)
 static void request_demote(struct gfs2_glock *gl, unsigned int state,
 			   unsigned long delay, bool remote)
 {
-	if (delay)
-		set_bit(GLF_PENDING_DEMOTE, &gl->gl_flags);
-	else
-		gfs2_set_demote(gl);
+	gfs2_set_demote(delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE, gl);
 	if (gl->gl_demote_state == LM_ST_EXCLUSIVE) {
 		gl->gl_demote_state = state;
 		gl->gl_demote_time = jiffies;
@@ -1636,12 +1633,6 @@ int gfs2_glock_poll(struct gfs2_holder *gh)
 	return test_bit(HIF_WAIT, &gh->gh_iflags) ? 0 : 1;
 }
 
-static inline bool needs_demote(struct gfs2_glock *gl)
-{
-	return (test_bit(GLF_DEMOTE, &gl->gl_flags) ||
-		test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags));
-}
-
 static void __gfs2_glock_dq(struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
@@ -1650,8 +1641,8 @@ static void __gfs2_glock_dq(struct gfs2_holder *gh)
 
 	/*
 	 * This holder should not be cached, so mark it for demote.
-	 * Note: this should be done before the check for needs_demote
-	 * below.
+	 * Note: this should be done before the glock_needs_demote
+	 * check below.
 	 */
 	if (gh->gh_flags & GL_NOCACHE)
 		request_demote(gl, LM_ST_UNLOCKED, 0, false);
@@ -1664,7 +1655,7 @@ static void __gfs2_glock_dq(struct gfs2_holder *gh)
 	 * If there hasn't been a demote request we are done.
 	 * (Let the remaining holders, if any, keep holding it.)
 	 */
-	if (!needs_demote(gl)) {
+	if (!glock_needs_demote(gl)) {
 		if (list_empty(&gl->gl_holders))
 			fast_path = 1;
 	}
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 63e101d448e96..c171f745650fd 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -285,4 +285,10 @@ static inline bool gfs2_holder_queued(struct gfs2_holder *gh)
 void gfs2_inode_remember_delete(struct gfs2_glock *gl, u64 generation);
 bool gfs2_inode_already_deleted(struct gfs2_glock *gl, u64 generation);
 
+static inline bool glock_needs_demote(struct gfs2_glock *gl)
+{
+	return (test_bit(GLF_DEMOTE, &gl->gl_flags) ||
+		test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags));
+}
+
 #endif /* __GLOCK_DOT_H__ */
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index b9cef63c78717..ea9af6d4a042c 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1030,7 +1030,7 @@ static int gfs2_drop_inode(struct inode *inode)
 	if (inode->i_nlink &&
 	    gfs2_holder_initialized(&ip->i_iopen_gh)) {
 		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
-		if (test_bit(GLF_DEMOTE, &gl->gl_flags))
+		if (glock_needs_demote(gl))
 			clear_nlink(inode);
 	}
 
@@ -1294,7 +1294,7 @@ static bool gfs2_upgrade_iopen_glock(struct inode *inode)
 
 	wait_event_interruptible_timeout(sdp->sd_async_glock_wait,
 		!test_bit(HIF_WAIT, &gh->gh_iflags) ||
-		test_bit(GLF_DEMOTE, &ip->i_gl->gl_flags),
+		glock_needs_demote(ip->i_gl),
 		5 * HZ);
 	if (!test_bit(HIF_HOLDER, &gh->gh_iflags)) {
 		gfs2_glock_dq(gh);

From 9fb794aac6ddd08a9c4982372250f06137696e90 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 12 Sep 2024 22:22:12 +0200
Subject: [PATCH 0842/1530] gfs2: Rename GIF_{DEFERRED -> DEFER}_DELETE

The GIF_DEFERRED_DELETE flag indicates an action that gfs2_evict_inode()
should take, so rename the flag to GIF_DEFER_DELETE to clarify.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c  | 4 ++--
 fs/gfs2/incore.h | 2 +-
 fs/gfs2/super.c  | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 4567c8c60a037..c095ff2efe1d4 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -980,7 +980,7 @@ static bool gfs2_try_evict(struct gfs2_glock *gl)
 		ip = NULL;
 	spin_unlock(&gl->gl_lockref.lock);
 	if (ip) {
-		set_bit(GIF_DEFERRED_DELETE, &ip->i_flags);
+		set_bit(GIF_DEFER_DELETE, &ip->i_flags);
 		d_prune_aliases(&ip->i_inode);
 		iput(&ip->i_inode);
 
@@ -988,7 +988,7 @@ static bool gfs2_try_evict(struct gfs2_glock *gl)
 		spin_lock(&gl->gl_lockref.lock);
 		ip = gl->gl_object;
 		if (ip) {
-			clear_bit(GIF_DEFERRED_DELETE, &ip->i_flags);
+			clear_bit(GIF_DEFER_DELETE, &ip->i_flags);
 			if (!igrab(&ip->i_inode))
 				ip = NULL;
 		}
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index bd1348bff90eb..4e19cce3d906d 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -376,7 +376,7 @@ enum {
 	GIF_SW_PAGED		= 3,
 	GIF_FREE_VFS_INODE      = 5,
 	GIF_GLOP_PENDING	= 6,
-	GIF_DEFERRED_DELETE	= 7,
+	GIF_DEFER_DELETE	= 7,
 };
 
 struct gfs2_inode {
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index ea9af6d4a042c..c85c07b30b20a 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1324,7 +1324,7 @@ static enum dinode_demise evict_should_delete(struct inode *inode,
 	if (unlikely(test_bit(GIF_ALLOC_FAILED, &ip->i_flags)))
 		goto should_delete;
 
-	if (test_bit(GIF_DEFERRED_DELETE, &ip->i_flags))
+	if (test_bit(GIF_DEFER_DELETE, &ip->i_flags))
 		return SHOULD_DEFER_EVICTION;
 
 	/* Deletes should never happen under memory pressure anymore.  */

From c79ba4be351a06e0ac4c51143a83023bb37888d6 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Sat, 14 Sep 2024 00:37:03 +0200
Subject: [PATCH 0843/1530] gfs2: Rename dinode_demise to evict_behavior

Rename enum dinode_demise to evict_behavior and its items
SHOULD_DELETE_DINODE to EVICT_SHOULD_DELETE,
SHOULD_NOT_DELETE_DINODE to EVICT_SHOULD_SKIP_DELETE, and
SHOULD_DEFER_EVICTION to EVICT_SHOULD_DEFER_DELETE.

In gfs2_evict_inode(), add a separate variable of type enum
evict_behavior instead of implicitly casting to int.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/super.c | 37 +++++++++++++++++++------------------
 1 file changed, 19 insertions(+), 18 deletions(-)

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index c85c07b30b20a..f43b238ccaf17 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -44,10 +44,10 @@
 #include "xattr.h"
 #include "lops.h"
 
-enum dinode_demise {
-	SHOULD_DELETE_DINODE,
-	SHOULD_NOT_DELETE_DINODE,
-	SHOULD_DEFER_EVICTION,
+enum evict_behavior {
+	EVICT_SHOULD_DELETE,
+	EVICT_SHOULD_SKIP_DELETE,
+	EVICT_SHOULD_DEFER_DELETE,
 };
 
 /**
@@ -1313,8 +1313,8 @@ static bool gfs2_upgrade_iopen_glock(struct inode *inode)
  *
  * Returns: the fate of the dinode
  */
-static enum dinode_demise evict_should_delete(struct inode *inode,
-					      struct gfs2_holder *gh)
+static enum evict_behavior evict_should_delete(struct inode *inode,
+					       struct gfs2_holder *gh)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct super_block *sb = inode->i_sb;
@@ -1325,11 +1325,11 @@ static enum dinode_demise evict_should_delete(struct inode *inode,
 		goto should_delete;
 
 	if (test_bit(GIF_DEFER_DELETE, &ip->i_flags))
-		return SHOULD_DEFER_EVICTION;
+		return EVICT_SHOULD_DEFER_DELETE;
 
 	/* Deletes should never happen under memory pressure anymore.  */
 	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC))
-		return SHOULD_DEFER_EVICTION;
+		return EVICT_SHOULD_DEFER_DELETE;
 
 	/* Must not read inode block until block type has been verified */
 	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, gh);
@@ -1337,34 +1337,34 @@ static enum dinode_demise evict_should_delete(struct inode *inode,
 		glock_clear_object(ip->i_iopen_gh.gh_gl, ip);
 		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
 		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
-		return SHOULD_DEFER_EVICTION;
+		return EVICT_SHOULD_DEFER_DELETE;
 	}
 
 	if (gfs2_inode_already_deleted(ip->i_gl, ip->i_no_formal_ino))
-		return SHOULD_NOT_DELETE_DINODE;
+		return EVICT_SHOULD_SKIP_DELETE;
 	ret = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
 	if (ret)
-		return SHOULD_NOT_DELETE_DINODE;
+		return EVICT_SHOULD_SKIP_DELETE;
 
 	ret = gfs2_instantiate(gh);
 	if (ret)
-		return SHOULD_NOT_DELETE_DINODE;
+		return EVICT_SHOULD_SKIP_DELETE;
 
 	/*
 	 * The inode may have been recreated in the meantime.
 	 */
 	if (inode->i_nlink)
-		return SHOULD_NOT_DELETE_DINODE;
+		return EVICT_SHOULD_SKIP_DELETE;
 
 should_delete:
 	if (gfs2_holder_initialized(&ip->i_iopen_gh) &&
 	    test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
 		if (!gfs2_upgrade_iopen_glock(inode)) {
 			gfs2_holder_uninit(&ip->i_iopen_gh);
-			return SHOULD_NOT_DELETE_DINODE;
+			return EVICT_SHOULD_SKIP_DELETE;
 		}
 	}
-	return SHOULD_DELETE_DINODE;
+	return EVICT_SHOULD_DELETE;
 }
 
 /**
@@ -1475,6 +1475,7 @@ static void gfs2_evict_inode(struct inode *inode)
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
+	enum evict_behavior behavior;
 	int ret;
 
 	if (inode->i_nlink || sb_rdonly(sb) || !ip->i_no_addr)
@@ -1489,10 +1490,10 @@ static void gfs2_evict_inode(struct inode *inode)
 		goto out;
 
 	gfs2_holder_mark_uninitialized(&gh);
-	ret = evict_should_delete(inode, &gh);
-	if (ret == SHOULD_DEFER_EVICTION)
+	behavior = evict_should_delete(inode, &gh);
+	if (behavior == EVICT_SHOULD_DEFER_DELETE)
 		goto out;
-	if (ret == SHOULD_DELETE_DINODE)
+	if (behavior == EVICT_SHOULD_DELETE)
 		ret = evict_unlinked_inode(inode);
 	else
 		ret = evict_linked_inode(inode);

From a94dafe87d5fdded799fc25b82b123fb93959421 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Fri, 13 Sep 2024 01:17:40 +0200
Subject: [PATCH 0844/1530] gfs2: Return enum evict_behavior from
 gfs2_upgrade_iopen_glock

In case an iopen glock cannot be upgraded, function
gfs2_upgrade_iopen_glock() needs to communicate to gfs2_evict_inode()
whether deleting the inode should be deferred or skipped altogether.
Change the function to return the appropriate enum evict_behavior value
to indicate that.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/super.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index f43b238ccaf17..46d325c2ab880 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1257,7 +1257,7 @@ static void gfs2_glock_put_eventually(struct gfs2_glock *gl)
 		gfs2_glock_put(gl);
 }
 
-static bool gfs2_upgrade_iopen_glock(struct inode *inode)
+static enum evict_behavior gfs2_upgrade_iopen_glock(struct inode *inode)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
@@ -1290,7 +1290,7 @@ static bool gfs2_upgrade_iopen_glock(struct inode *inode)
 	gfs2_holder_reinit(LM_ST_EXCLUSIVE, GL_ASYNC | GL_NOCACHE, gh);
 	error = gfs2_glock_nq(gh);
 	if (error)
-		return false;
+		return EVICT_SHOULD_SKIP_DELETE;
 
 	wait_event_interruptible_timeout(sdp->sd_async_glock_wait,
 		!test_bit(HIF_WAIT, &gh->gh_iflags) ||
@@ -1298,9 +1298,14 @@ static bool gfs2_upgrade_iopen_glock(struct inode *inode)
 		5 * HZ);
 	if (!test_bit(HIF_HOLDER, &gh->gh_iflags)) {
 		gfs2_glock_dq(gh);
-		return false;
+		if (glock_needs_demote(ip->i_gl))
+			return EVICT_SHOULD_SKIP_DELETE;
+		return EVICT_SHOULD_DEFER_DELETE;
 	}
-	return gfs2_glock_holder_ready(gh) == 0;
+	error = gfs2_glock_holder_ready(gh);
+	if (error)
+		return EVICT_SHOULD_SKIP_DELETE;
+	return EVICT_SHOULD_DELETE;
 }
 
 /**
@@ -1359,9 +1364,12 @@ static enum evict_behavior evict_should_delete(struct inode *inode,
 should_delete:
 	if (gfs2_holder_initialized(&ip->i_iopen_gh) &&
 	    test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
-		if (!gfs2_upgrade_iopen_glock(inode)) {
+		enum evict_behavior behavior =
+			gfs2_upgrade_iopen_glock(inode);
+
+		if (behavior != EVICT_SHOULD_DELETE) {
 			gfs2_holder_uninit(&ip->i_iopen_gh);
-			return EVICT_SHOULD_SKIP_DELETE;
+			return behavior;
 		}
 	}
 	return EVICT_SHOULD_DELETE;

From b4100457d02d90149129ba2230130954a03fdf0b Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 22 Aug 2024 19:33:51 +0200
Subject: [PATCH 0845/1530] gfs2: Minor delete_work_func cleanup

Move those definitions into the the scope in which they are used.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index c095ff2efe1d4..9ec305b8d4d43 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1028,8 +1028,6 @@ static void delete_work_func(struct work_struct *work)
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct gfs2_glock *gl = container_of(dwork, struct gfs2_glock, gl_delete);
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-	struct inode *inode;
-	u64 no_addr = gl->gl_name.ln_number;
 
 	if (test_and_clear_bit(GLF_TRY_TO_EVICT, &gl->gl_flags)) {
 		/*
@@ -1059,6 +1057,9 @@ static void delete_work_func(struct work_struct *work)
 	}
 
 	if (test_and_clear_bit(GLF_VERIFY_DELETE, &gl->gl_flags)) {
+		u64 no_addr = gl->gl_name.ln_number;
+		struct inode *inode;
+
 		inode = gfs2_lookup_by_inum(sdp, no_addr, gl->gl_no_formal_ino,
 					    GFS2_BLKST_UNLINKED);
 		if (IS_ERR(inode)) {

From 0baa10b60cddb587a1a252a8db76b0cea439d1be Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 12 Sep 2024 23:29:41 +0200
Subject: [PATCH 0846/1530] gfs2: Clean up delete work processing

Function delete_work_func() was previously assuming that the
GLF_TRY_TO_EVICT and GLF_VERIFY_DELETE flags won't both be set at the
same time, but there probably are races in which that can happen, so
handle that case correctly.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 9ec305b8d4d43..95f082f13a8c5 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1028,6 +1028,7 @@ static void delete_work_func(struct work_struct *work)
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct gfs2_glock *gl = container_of(dwork, struct gfs2_glock, gl_delete);
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+	bool verify_delete = test_and_clear_bit(GLF_VERIFY_DELETE, &gl->gl_flags);
 
 	if (test_and_clear_bit(GLF_TRY_TO_EVICT, &gl->gl_flags)) {
 		/*
@@ -1048,15 +1049,15 @@ static void delete_work_func(struct work_struct *work)
 		 * step entirely.
 		 */
 		if (gfs2_try_evict(gl)) {
-			if (test_bit(SDF_KILL, &sdp->sd_flags))
-				goto out;
-			if (gfs2_queue_verify_delete(gl, true))
-				return;
+			if (!test_bit(SDF_KILL, &sdp->sd_flags)) {
+				gfs2_glock_hold(gl);
+				if (!gfs2_queue_verify_delete(gl, true))
+					gfs2_glock_put(gl);
+			}
 		}
-		goto out;
 	}
 
-	if (test_and_clear_bit(GLF_VERIFY_DELETE, &gl->gl_flags)) {
+	if (verify_delete) {
 		u64 no_addr = gl->gl_name.ln_number;
 		struct inode *inode;
 
@@ -1073,7 +1074,6 @@ static void delete_work_func(struct work_struct *work)
 		}
 	}
 
-out:
 	gfs2_glock_put(gl);
 }
 

From 8c21c2c71e668a5eed9fe9981a2306f9178e6c3e Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 12 Sep 2024 22:32:46 +0200
Subject: [PATCH 0847/1530] gfs2: Call gfs2_queue_verify_delete from
 gfs2_evict_inode

Move calls to gfs2_queue_verify_delete() into gfs2_evict_inode().

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c | 13 ++-----------
 fs/gfs2/super.c |  9 ++++++++-
 2 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 95f082f13a8c5..3736e7f3b381c 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -959,10 +959,9 @@ static void gfs2_glock_poke(struct gfs2_glock *gl)
 	gfs2_holder_uninit(&gh);
 }
 
-static bool gfs2_try_evict(struct gfs2_glock *gl)
+static void gfs2_try_evict(struct gfs2_glock *gl)
 {
 	struct gfs2_inode *ip;
-	bool evicted = false;
 
 	/*
 	 * If there is contention on the iopen glock and we have an inode, try
@@ -997,9 +996,7 @@ static bool gfs2_try_evict(struct gfs2_glock *gl)
 			gfs2_glock_poke(ip->i_gl);
 			iput(&ip->i_inode);
 		}
-		evicted = !ip;
 	}
-	return evicted;
 }
 
 bool gfs2_queue_try_to_evict(struct gfs2_glock *gl)
@@ -1048,13 +1045,7 @@ static void delete_work_func(struct work_struct *work)
 		 * care about compatibility with such nodes, we can skip this
 		 * step entirely.
 		 */
-		if (gfs2_try_evict(gl)) {
-			if (!test_bit(SDF_KILL, &sdp->sd_flags)) {
-				gfs2_glock_hold(gl);
-				if (!gfs2_queue_verify_delete(gl, true))
-					gfs2_glock_put(gl);
-			}
-		}
+		gfs2_try_evict(gl);
 	}
 
 	if (verify_delete) {
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 46d325c2ab880..340bc21de2183 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1499,8 +1499,15 @@ static void gfs2_evict_inode(struct inode *inode)
 
 	gfs2_holder_mark_uninitialized(&gh);
 	behavior = evict_should_delete(inode, &gh);
-	if (behavior == EVICT_SHOULD_DEFER_DELETE)
+	if (behavior == EVICT_SHOULD_DEFER_DELETE &&
+	    !test_bit(SDF_KILL, &sdp->sd_flags)) {
+		struct gfs2_glock *io_gl = ip->i_iopen_gh.gh_gl;
+
+		gfs2_glock_hold(io_gl);
+		if (!gfs2_queue_verify_delete(io_gl, true))
+			gfs2_glock_put(io_gl);
 		goto out;
+	}
 	if (behavior == EVICT_SHOULD_DELETE)
 		ret = evict_unlinked_inode(inode);
 	else

From a6033333ccce01ecada39b3ddabc03fd967e60c0 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Mon, 23 Sep 2024 22:27:48 +0200
Subject: [PATCH 0848/1530] gfs2: Update to the evict / remote delete
 documentation

Try to be a bit more clear and remove some duplications.  We cannot
actually get rid of the verification step eventually, so remove the
comment saying so.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c | 31 ++++++++-----------------------
 fs/gfs2/super.c |  6 +++---
 2 files changed, 11 insertions(+), 26 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 3736e7f3b381c..8fff36846145c 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -965,13 +965,16 @@ static void gfs2_try_evict(struct gfs2_glock *gl)
 
 	/*
 	 * If there is contention on the iopen glock and we have an inode, try
-	 * to grab and release the inode so that it can be evicted.  This will
-	 * allow the remote node to go ahead and delete the inode without us
-	 * having to do it, which will avoid rgrp glock thrashing.
+	 * to grab and release the inode so that it can be evicted.  The
+	 * GIF_DEFER_DELETE flag indicates to gfs2_evict_inode() that the inode
+	 * should not be deleted locally.  This will allow the remote node to
+	 * go ahead and delete the inode without us having to do it, which will
+	 * avoid rgrp glock thrashing.
 	 *
 	 * The remote node is likely still holding the corresponding inode
 	 * glock, so it will run before we get to verify that the delete has
-	 * happened below.
+	 * happened below.  (Verification is triggered by the call to
+	 * gfs2_queue_verify_delete() in gfs2_evict_inode().)
 	 */
 	spin_lock(&gl->gl_lockref.lock);
 	ip = gl->gl_object;
@@ -1027,26 +1030,8 @@ static void delete_work_func(struct work_struct *work)
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	bool verify_delete = test_and_clear_bit(GLF_VERIFY_DELETE, &gl->gl_flags);
 
-	if (test_and_clear_bit(GLF_TRY_TO_EVICT, &gl->gl_flags)) {
-		/*
-		 * If we can evict the inode, give the remote node trying to
-		 * delete the inode some time before verifying that the delete
-		 * has happened.  Otherwise, if we cause contention on the inode glock
-		 * immediately, the remote node will think that we still have
-		 * the inode in use, and so it will give up waiting.
-		 *
-		 * If we can't evict the inode, signal to the remote node that
-		 * the inode is still in use.  We'll later try to delete the
-		 * inode locally in gfs2_evict_inode.
-		 *
-		 * FIXME: We only need to verify that the remote node has
-		 * deleted the inode because nodes before this remote delete
-		 * rework won't cooperate.  At a later time, when we no longer
-		 * care about compatibility with such nodes, we can skip this
-		 * step entirely.
-		 */
+	if (test_and_clear_bit(GLF_TRY_TO_EVICT, &gl->gl_flags))
 		gfs2_try_evict(gl);
-	}
 
 	if (verify_delete) {
 		u64 no_addr = gl->gl_name.ln_number;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 340bc21de2183..40158396e8db2 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1272,9 +1272,9 @@ static enum evict_behavior gfs2_upgrade_iopen_glock(struct inode *inode)
 	 * exclusive access to the iopen glock here.
 	 *
 	 * Otherwise, the other nodes holding the lock will be notified about
-	 * our locking request.  If they do not have the inode open, they are
-	 * expected to evict the cached inode and release the lock, allowing us
-	 * to proceed.
+	 * our locking request (see iopen_go_callback()).  If they do not have
+	 * the inode open, they are expected to evict the cached inode and
+	 * release the lock, allowing us to proceed.
 	 *
 	 * Otherwise, if they cannot evict the inode, they are expected to poke
 	 * the inode glock (note: not the iopen glock).  We will notice that

From f6ca45e3d2b97ddb4bfcbbe44d1dd18374cd6f85 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Fri, 13 Sep 2024 22:56:53 +0200
Subject: [PATCH 0849/1530] gfs2: Use mod_delayed_work in
 gfs2_queue_try_to_evict

In the unlikely case that we're trying to queue GLF_TRY_TO_EVICT work
for an inode that already has GLF_VERIFY_DELETE work queued, we want to
make sure that the GLF_TRY_TO_EVICT work gets scheduled immediately
instead of waiting for the delayed work timer to expire.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 8fff36846145c..5455f4dd14a31 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1008,8 +1008,7 @@ bool gfs2_queue_try_to_evict(struct gfs2_glock *gl)
 
 	if (test_and_set_bit(GLF_TRY_TO_EVICT, &gl->gl_flags))
 		return false;
-	return queue_delayed_work(sdp->sd_delete_wq,
-				  &gl->gl_delete, 0);
+	return !mod_delayed_work(sdp->sd_delete_wq, &gl->gl_delete, 0);
 }
 
 bool gfs2_queue_verify_delete(struct gfs2_glock *gl, bool later)

From 085e423b4d51dfe71e1967c9e508d1cb845063d3 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Fri, 13 Sep 2024 23:07:31 +0200
Subject: [PATCH 0850/1530] gfs2: Randomize GLF_VERIFY_DELETE work delay

Randomize the delay of GLF_VERIFY_DELETE work.  This avoids thundering
herd problems when multiple nodes schedule that kind of work in response
to an inode being unlinked remotely.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 5455f4dd14a31..46a6e97cd9301 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -36,6 +36,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/fdtable.h>
 #include <linux/file.h>
+#include <linux/random.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -1018,7 +1019,7 @@ bool gfs2_queue_verify_delete(struct gfs2_glock *gl, bool later)
 
 	if (test_and_set_bit(GLF_VERIFY_DELETE, &gl->gl_flags))
 		return false;
-	delay = later ? 5 * HZ : 0;
+	delay = later ? HZ + get_random_long() % (HZ * 9) : 0;
 	return queue_delayed_work(sdp->sd_delete_wq, &gl->gl_delete, delay);
 }
 

From 0c5bee608fbbd970e46aade6e57a0fdbbaa4621e Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Fri, 13 Sep 2024 23:10:50 +0200
Subject: [PATCH 0851/1530] gfs2: Use get_random_u32 in gfs2_orlov_skip

Use get_random_u32() instead of get_random_bytes() to remove the last
remaining call to get_random_bytes().

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/rgrp.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 5393031297153..b14e54b38ee80 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1987,10 +1987,8 @@ static bool gfs2_rgrp_used_recently(const struct gfs2_blkreserv *rs,
 static u32 gfs2_orlov_skip(const struct gfs2_inode *ip)
 {
 	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	u32 skip;
 
-	get_random_bytes(&skip, sizeof(skip));
-	return skip % sdp->sd_rgrps;
+	return get_random_u32() % sdp->sd_rgrps;
 }
 
 static bool gfs2_select_rgrp(struct gfs2_rgrpd **pos, const struct gfs2_rgrpd *begin)

From 70cddf16cbfbb6f7fb4d68bb62765850a921450d Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Mon, 16 Sep 2024 14:02:41 +0200
Subject: [PATCH 0852/1530] gfs2: Make gfs2_inode_refresh static

Function gfs2_inode_refresh() is only used in fs/gfs2/glops.c.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glops.c | 2 +-
 fs/gfs2/inode.h | 2 --
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index dbc444bfc630d..eb4714f299efb 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -470,7 +470,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
  * Returns: errno
  */
 
-int gfs2_inode_refresh(struct gfs2_inode *ip)
+static int gfs2_inode_refresh(struct gfs2_inode *ip)
 {
 	struct buffer_head *dibh;
 	int error;
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index fd15d1c6b6fb1..9e5e1622d50a6 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -93,8 +93,6 @@ struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
 				  u64 no_formal_ino,
 				  unsigned int blktype);
 
-int gfs2_inode_refresh(struct gfs2_inode *ip);
-
 struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
 			   int is_root);
 int gfs2_permission(struct mnt_idmap *idmap,

From 03ff3781bf6c149554d88e7b702a3abd5e400dc0 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Fri, 4 Oct 2024 14:10:47 +0200
Subject: [PATCH 0853/1530] gfs2: gfs2_evict_inode clarification

When function evict_should_delete() returns SHOULD_DEFER_EVICTION, gh is
never initialized, but that isn't obvious; if it did initialize gh and
then return SHOULD_DEFER_EVICTION, gfs2_evict_inode() would fail to
release it.  To clarify the code, change gfs2_evict_inode() to always
check if gh needs to be released, no matter what evict_should_delete()
returns.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/super.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 40158396e8db2..aadb83e38c17b 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1486,6 +1486,7 @@ static void gfs2_evict_inode(struct inode *inode)
 	enum evict_behavior behavior;
 	int ret;
 
+	gfs2_holder_mark_uninitialized(&gh);
 	if (inode->i_nlink || sb_rdonly(sb) || !ip->i_no_addr)
 		goto out;
 
@@ -1497,7 +1498,6 @@ static void gfs2_evict_inode(struct inode *inode)
 	if (!sdp->sd_jdesc)
 		goto out;
 
-	gfs2_holder_mark_uninitialized(&gh);
 	behavior = evict_should_delete(inode, &gh);
 	if (behavior == EVICT_SHOULD_DEFER_DELETE &&
 	    !test_bit(SDF_KILL, &sdp->sd_flags)) {
@@ -1516,11 +1516,11 @@ static void gfs2_evict_inode(struct inode *inode)
 	if (gfs2_rs_active(&ip->i_res))
 		gfs2_rs_deltree(&ip->i_res);
 
-	if (gfs2_holder_initialized(&gh))
-		gfs2_glock_dq_uninit(&gh);
 	if (ret && ret != GLR_TRYFAILED && ret != -EROFS)
 		fs_warn(sdp, "gfs2_evict_inode: %d\n", ret);
 out:
+	if (gfs2_holder_initialized(&gh))
+		gfs2_glock_dq_uninit(&gh);
 	truncate_inode_pages_final(&inode->i_data);
 	if (ip->i_qadata)
 		gfs2_assert_warn(sdp, ip->i_qadata->qa_ref == 0);

From b6900ce15191ff9e219f1974b5db107ae02bb387 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Mon, 28 Oct 2024 22:18:32 +0100
Subject: [PATCH 0854/1530] gfs2: Simplify DLM_LKF_QUECVT use

The DLM_LKF_QUECVT flag needs to be set for "upward" lock conversions to
ensure fairness, but setting it for "downward" lock conversions will
lead to a failure.  The flag is currently set based on the GLF_BLOCKING
flag and it's not immediately obvious why this is correct.  Simplify
things by figuring out if a lock conversion is "upward" by looking at
the before and after locking modes instead of relying on the
GLF_BLOCKING flag.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/lock_dlm.c | 29 +++++++++++++++++++++++++----
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index fa5134df985f7..58aeeae7ed8cd 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -224,8 +224,21 @@ static int make_mode(struct gfs2_sbd *sdp, const unsigned int lmstate)
 	return -1;
 }
 
+/* Taken from fs/dlm/lock.c. */
+
+static bool middle_conversion(int cur, int req)
+{
+	return (cur == DLM_LOCK_PR && req == DLM_LOCK_CW) ||
+	       (cur == DLM_LOCK_CW && req == DLM_LOCK_PR);
+}
+
+static bool down_conversion(int cur, int req)
+{
+	return !middle_conversion(cur, req) && req < cur;
+}
+
 static u32 make_flags(struct gfs2_glock *gl, const unsigned int gfs_flags,
-		      const int req)
+		      const int cur, const int req)
 {
 	u32 lkf = 0;
 
@@ -251,7 +264,14 @@ static u32 make_flags(struct gfs2_glock *gl, const unsigned int gfs_flags,
 
 	if (!test_bit(GLF_INITIAL, &gl->gl_flags)) {
 		lkf |= DLM_LKF_CONVERT;
-		if (test_bit(GLF_BLOCKING, &gl->gl_flags))
+
+		/*
+		 * The DLM_LKF_QUECVT flag needs to be set for "first come,
+		 * first served" semantics, but it must only be set for
+		 * "upward" lock conversions or else DLM will reject the
+		 * request as invalid.
+		 */
+		if (!down_conversion(cur, req))
 			lkf |= DLM_LKF_QUECVT;
 	}
 
@@ -271,13 +291,14 @@ static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state,
 		     unsigned int flags)
 {
 	struct lm_lockstruct *ls = &gl->gl_name.ln_sbd->sd_lockstruct;
-	int req;
+	int cur, req;
 	u32 lkf;
 	char strname[GDLM_STRNAME_BYTES] = "";
 	int error;
 
+	cur = make_mode(gl->gl_name.ln_sbd, gl->gl_state);
 	req = make_mode(gl->gl_name.ln_sbd, req_state);
-	lkf = make_flags(gl, flags, req);
+	lkf = make_flags(gl, flags, cur, req);
 	gfs2_glstats_inc(gl, GFS2_LKS_DCOUNT);
 	gfs2_sbstats_inc(gl, GFS2_LKS_DCOUNT);
 	if (test_bit(GLF_INITIAL, &gl->gl_flags)) {

From 68bfb7eb7f7de355d5b3812c25a2a36e9eead97b Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 24 Oct 2024 10:18:09 -0700
Subject: [PATCH 0855/1530] fuse: remove pages for requests and exclusively use
 folios

All fuse requests use folios instead of pages for transferring data.
Remove pages from the requests and exclusively use folios.

No functional changes.

[SzM: rename back folio_descs -> descs, etc.]

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/cuse.c      |  3 +-
 fs/fuse/dev.c       | 57 ++++++++++-----------------
 fs/fuse/dir.c       |  3 +-
 fs/fuse/file.c      | 58 +++++++++++++---------------
 fs/fuse/fuse_i.h    | 22 ++---------
 fs/fuse/ioctl.c     |  5 +--
 fs/fuse/readdir.c   |  3 +-
 fs/fuse/virtio_fs.c | 93 +++++++++++++++++----------------------------
 8 files changed, 90 insertions(+), 154 deletions(-)

diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index eed78e3031398..b39844d75a806 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -460,10 +460,9 @@ static int cuse_send_init(struct cuse_conn *cc)
 	ap->args.out_args[1].size = CUSE_INIT_INFO_MAX;
 	ap->args.out_argvar = true;
 	ap->args.out_pages = true;
-	ap->uses_folios = true;
 	ap->num_folios = 1;
 	ap->folios = &ia->folio;
-	ap->folio_descs = &ia->desc;
+	ap->descs = &ia->desc;
 	ia->folio = folio;
 	ia->desc.length = ap->args.out_args[1].size;
 	ap->args.end = cuse_process_init_reply;
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 563a0bfa0e951..29fc61a072bae 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1028,41 +1028,27 @@ static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes,
 	struct fuse_req *req = cs->req;
 	struct fuse_args_pages *ap = container_of(req->args, typeof(*ap), args);
 
-	if (ap->uses_folios) {
-		for (i = 0; i < ap->num_folios && (nbytes || zeroing); i++) {
-			int err;
-			unsigned int offset = ap->folio_descs[i].offset;
-			unsigned int count = min(nbytes, ap->folio_descs[i].length);
-			struct page *orig, *pagep;
+	for (i = 0; i < ap->num_folios && (nbytes || zeroing); i++) {
+		int err;
+		unsigned int offset = ap->descs[i].offset;
+		unsigned int count = min(nbytes, ap->descs[i].length);
+		struct page *orig, *pagep;
 
-			orig = pagep = &ap->folios[i]->page;
+		orig = pagep = &ap->folios[i]->page;
 
-			err = fuse_copy_page(cs, &pagep, offset, count, zeroing);
-			if (err)
-				return err;
-
-			nbytes -= count;
-
-			/*
-			 *  fuse_copy_page may have moved a page from a pipe
-			 *  instead of copying into our given page, so update
-			 *  the folios if it was replaced.
-			 */
-			if (pagep != orig)
-				ap->folios[i] = page_folio(pagep);
-		}
-	} else {
-		for (i = 0; i < ap->num_pages && (nbytes || zeroing); i++) {
-			int err;
-			unsigned int offset = ap->descs[i].offset;
-			unsigned int count = min(nbytes, ap->descs[i].length);
+		err = fuse_copy_page(cs, &pagep, offset, count, zeroing);
+		if (err)
+			return err;
 
-			err = fuse_copy_page(cs, &ap->pages[i], offset, count, zeroing);
-			if (err)
-				return err;
+		nbytes -= count;
 
-			nbytes -= count;
-		}
+		/*
+		 *  fuse_copy_page may have moved a page from a pipe instead of
+		 *  copying into our given page, so update the folios if it was
+		 *  replaced.
+		 */
+		if (pagep != orig)
+			ap->folios[i] = page_folio(pagep);
 	}
 	return 0;
 }
@@ -1761,7 +1747,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 	num_pages = (num + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	num_pages = min(num_pages, fc->max_pages);
 
-	args_size += num_pages * (sizeof(ap->folios[0]) + sizeof(ap->folio_descs[0]));
+	args_size += num_pages * (sizeof(ap->folios[0]) + sizeof(ap->descs[0]));
 
 	ra = kzalloc(args_size, GFP_KERNEL);
 	if (!ra)
@@ -1769,8 +1755,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 
 	ap = &ra->ap;
 	ap->folios = (void *) (ra + 1);
-	ap->folio_descs = (void *) (ap->folios + num_pages);
-	ap->uses_folios = true;
+	ap->descs = (void *) (ap->folios + num_pages);
 
 	args = &ap->args;
 	args->nodeid = outarg->nodeid;
@@ -1791,8 +1776,8 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 
 		this_num = min_t(unsigned, num, PAGE_SIZE - offset);
 		ap->folios[ap->num_folios] = folio;
-		ap->folio_descs[ap->num_folios].offset = offset;
-		ap->folio_descs[ap->num_folios].length = this_num;
+		ap->descs[ap->num_folios].offset = offset;
+		ap->descs[ap->num_folios].length = this_num;
 		ap->num_folios++;
 		cur_pages++;
 
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index a08c532068d0f..b8a4608e31afb 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1590,10 +1590,9 @@ static int fuse_readlink_page(struct inode *inode, struct folio *folio)
 	struct fuse_mount *fm = get_fuse_mount(inode);
 	struct fuse_folio_desc desc = { .length = PAGE_SIZE - 1 };
 	struct fuse_args_pages ap = {
-		.uses_folios = true,
 		.num_folios = 1,
 		.folios = &folio,
-		.folio_descs = &desc,
+		.descs = &desc,
 	};
 	char *link;
 	ssize_t res;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 14af8c41fc832..88d0946b5bc98 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -742,7 +742,7 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos)
 	kref_put(&io->refcnt, fuse_io_release);
 }
 
-static struct fuse_io_args *fuse_io_folios_alloc(struct fuse_io_priv *io,
+static struct fuse_io_args *fuse_io_alloc(struct fuse_io_priv *io,
 						 unsigned int nfolios)
 {
 	struct fuse_io_args *ia;
@@ -750,9 +750,8 @@ static struct fuse_io_args *fuse_io_folios_alloc(struct fuse_io_priv *io,
 	ia = kzalloc(sizeof(*ia), GFP_KERNEL);
 	if (ia) {
 		ia->io = io;
-		ia->ap.uses_folios = true;
 		ia->ap.folios = fuse_folios_alloc(nfolios, GFP_KERNEL,
-						  &ia->ap.folio_descs);
+						  &ia->ap.descs);
 		if (!ia->ap.folios) {
 			kfree(ia);
 			ia = NULL;
@@ -761,7 +760,7 @@ static struct fuse_io_args *fuse_io_folios_alloc(struct fuse_io_priv *io,
 	return ia;
 }
 
-static void fuse_io_folios_free(struct fuse_io_args *ia)
+static void fuse_io_free(struct fuse_io_args *ia)
 {
 	kfree(ia->ap.folios);
 	kfree(ia);
@@ -797,7 +796,7 @@ static void fuse_aio_complete_req(struct fuse_mount *fm, struct fuse_args *args,
 	fuse_release_user_pages(&ia->ap, err ?: nres, io->should_dirty);
 
 	fuse_aio_complete(io, err, pos);
-	fuse_io_folios_free(ia);
+	fuse_io_free(ia);
 }
 
 static ssize_t fuse_async_req_send(struct fuse_mount *fm,
@@ -880,10 +879,9 @@ static int fuse_do_readfolio(struct file *file, struct folio *folio)
 	struct fuse_io_args ia = {
 		.ap.args.page_zeroing = true,
 		.ap.args.out_pages = true,
-		.ap.uses_folios = true,
 		.ap.num_folios = 1,
 		.ap.folios = &folio,
-		.ap.folio_descs = &desc,
+		.ap.descs = &desc,
 	};
 	ssize_t res;
 	u64 attr_ver;
@@ -962,7 +960,7 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
 	if (ia->ff)
 		fuse_file_put(ia->ff, false);
 
-	fuse_io_folios_free(ia);
+	fuse_io_free(ia);
 }
 
 static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
@@ -983,7 +981,7 @@ static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
 	/* Don't overflow end offset */
 	if (pos + (count - 1) == LLONG_MAX) {
 		count--;
-		ap->folio_descs[ap->num_folios - 1].length--;
+		ap->descs[ap->num_folios - 1].length--;
 	}
 	WARN_ON((loff_t) (pos + count) < 0);
 
@@ -1044,7 +1042,7 @@ static void fuse_readahead(struct readahead_control *rac)
 			 */
 			break;
 
-		ia = fuse_io_folios_alloc(NULL, cur_pages);
+		ia = fuse_io_alloc(NULL, cur_pages);
 		if (!ia)
 			return;
 		ap = &ia->ap;
@@ -1052,7 +1050,7 @@ static void fuse_readahead(struct readahead_control *rac)
 		while (ap->num_folios < cur_pages) {
 			folio = readahead_folio(rac);
 			ap->folios[ap->num_folios] = folio;
-			ap->folio_descs[ap->num_folios].length = folio_size(folio);
+			ap->descs[ap->num_folios].length = folio_size(folio);
 			ap->num_folios++;
 		}
 		fuse_send_readpages(ia, rac->file);
@@ -1186,7 +1184,7 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia,
 		err = -EIO;
 
 	short_write = ia->write.out.size < count;
-	offset = ap->folio_descs[0].offset;
+	offset = ap->descs[0].offset;
 	count = ia->write.out.size;
 	for (i = 0; i < ap->num_folios; i++) {
 		struct folio *folio = ap->folios[i];
@@ -1224,7 +1222,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 	int err;
 
 	ap->args.in_pages = true;
-	ap->folio_descs[0].offset = offset;
+	ap->descs[0].offset = offset;
 
 	do {
 		size_t tmp;
@@ -1261,7 +1259,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 
 		err = 0;
 		ap->folios[ap->num_folios] = folio;
-		ap->folio_descs[ap->num_folios].length = tmp;
+		ap->descs[ap->num_folios].length = tmp;
 		ap->num_folios++;
 		nr_pages++;
 
@@ -1318,8 +1316,7 @@ static ssize_t fuse_perform_write(struct kiocb *iocb, struct iov_iter *ii)
 		unsigned int nr_pages = fuse_wr_pages(pos, iov_iter_count(ii),
 						      fc->max_pages);
 
-		ap->uses_folios = true;
-		ap->folios = fuse_folios_alloc(nr_pages, GFP_KERNEL, &ap->folio_descs);
+		ap->folios = fuse_folios_alloc(nr_pages, GFP_KERNEL, &ap->descs);
 		if (!ap->folios) {
 			err = -ENOMEM;
 			break;
@@ -1564,13 +1561,13 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
 		/* Currently, all folios in FUSE are one page */
 		nfolios = DIV_ROUND_UP(ret, PAGE_SIZE);
 
-		ap->folio_descs[ap->num_folios].offset = start;
-		fuse_folio_descs_length_init(ap->folio_descs, ap->num_folios, nfolios);
+		ap->descs[ap->num_folios].offset = start;
+		fuse_folio_descs_length_init(ap->descs, ap->num_folios, nfolios);
 		for (i = 0; i < nfolios; i++)
 			ap->folios[i + ap->num_folios] = page_folio(pages[i]);
 
 		ap->num_folios += nfolios;
-		ap->folio_descs[ap->num_folios - 1].length -=
+		ap->descs[ap->num_folios - 1].length -=
 			(PAGE_SIZE - ret) & (PAGE_SIZE - 1);
 		nr_pages += nfolios;
 	}
@@ -1614,14 +1611,14 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 	bool fopen_direct_io = ff->open_flags & FOPEN_DIRECT_IO;
 
 	max_pages = iov_iter_npages(iter, fc->max_pages);
-	ia = fuse_io_folios_alloc(io, max_pages);
+	ia = fuse_io_alloc(io, max_pages);
 	if (!ia)
 		return -ENOMEM;
 
 	if (fopen_direct_io && fc->direct_io_allow_mmap) {
 		res = filemap_write_and_wait_range(mapping, pos, pos + count - 1);
 		if (res) {
-			fuse_io_folios_free(ia);
+			fuse_io_free(ia);
 			return res;
 		}
 	}
@@ -1636,7 +1633,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 	if (fopen_direct_io && write) {
 		res = invalidate_inode_pages2_range(mapping, idx_from, idx_to);
 		if (res) {
-			fuse_io_folios_free(ia);
+			fuse_io_free(ia);
 			return res;
 		}
 	}
@@ -1663,7 +1660,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 
 		if (!io->async || nres < 0) {
 			fuse_release_user_pages(&ia->ap, nres, io->should_dirty);
-			fuse_io_folios_free(ia);
+			fuse_io_free(ia);
 		}
 		ia = NULL;
 		if (nres < 0) {
@@ -1682,13 +1679,13 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 		}
 		if (count) {
 			max_pages = iov_iter_npages(iter, fc->max_pages);
-			ia = fuse_io_folios_alloc(io, max_pages);
+			ia = fuse_io_alloc(io, max_pages);
 			if (!ia)
 				break;
 		}
 	}
 	if (ia)
-		fuse_io_folios_free(ia);
+		fuse_io_free(ia);
 	if (res > 0)
 		*ppos = pos;
 
@@ -2093,8 +2090,7 @@ static struct fuse_writepage_args *fuse_writepage_args_alloc(void)
 	if (wpa) {
 		ap = &wpa->ia.ap;
 		ap->num_folios = 0;
-		ap->uses_folios = true;
-		ap->folios = fuse_folios_alloc(1, GFP_NOFS, &ap->folio_descs);
+		ap->folios = fuse_folios_alloc(1, GFP_NOFS, &ap->descs);
 		if (!ap->folios) {
 			kfree(wpa);
 			wpa = NULL;
@@ -2127,8 +2123,8 @@ static void fuse_writepage_args_page_fill(struct fuse_writepage_args *wpa, struc
 	folio_copy(tmp_folio, folio);
 
 	ap->folios[folio_index] = tmp_folio;
-	ap->folio_descs[folio_index].offset = 0;
-	ap->folio_descs[folio_index].length = PAGE_SIZE;
+	ap->descs[folio_index].offset = 0;
+	ap->descs[folio_index].length = PAGE_SIZE;
 
 	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
 	node_stat_add_folio(tmp_folio, NR_WRITEBACK_TEMP);
@@ -2234,10 +2230,10 @@ static bool fuse_pages_realloc(struct fuse_fill_wb_data *data)
 		return false;
 
 	memcpy(folios, ap->folios, sizeof(struct folio *) * ap->num_folios);
-	memcpy(descs, ap->folio_descs, sizeof(struct fuse_folio_desc) * ap->num_folios);
+	memcpy(descs, ap->descs, sizeof(struct fuse_folio_desc) * ap->num_folios);
 	kfree(ap->folios);
 	ap->folios = folios;
-	ap->folio_descs = descs;
+	ap->descs = descs;
 	data->max_folios = nfolios;
 
 	return true;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index d26d278da886a..d35c37ccf9b54 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -285,12 +285,6 @@ struct fuse_arg {
 	void *value;
 };
 
-/** FUSE page descriptor */
-struct fuse_page_desc {
-	unsigned int length;
-	unsigned int offset;
-};
-
 /** FUSE folio descriptor */
 struct fuse_folio_desc {
 	unsigned int length;
@@ -325,19 +319,9 @@ struct fuse_args {
 
 struct fuse_args_pages {
 	struct fuse_args args;
-	union {
-		struct {
-			struct page **pages;
-			struct fuse_page_desc *descs;
-			unsigned int num_pages;
-		};
-		struct {
-			struct folio **folios;
-			struct fuse_folio_desc *folio_descs;
-			unsigned int num_folios;
-		};
-	};
-	bool uses_folios;
+	struct folio **folios;
+	struct fuse_folio_desc *descs;
+	unsigned int num_folios;
 };
 
 struct fuse_release_args {
diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c
index 1c77d8a279506..2d9abf48828f9 100644
--- a/fs/fuse/ioctl.c
+++ b/fs/fuse/ioctl.c
@@ -251,12 +251,12 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 	BUILD_BUG_ON(sizeof(struct fuse_ioctl_iovec) * FUSE_IOCTL_MAX_IOV > PAGE_SIZE);
 
 	err = -ENOMEM;
-	ap.folios = fuse_folios_alloc(fm->fc->max_pages, GFP_KERNEL, &ap.folio_descs);
+	ap.folios = fuse_folios_alloc(fm->fc->max_pages, GFP_KERNEL, &ap.descs);
 	iov_page = (struct iovec *) __get_free_page(GFP_KERNEL);
 	if (!ap.folios || !iov_page)
 		goto out;
 
-	fuse_folio_descs_length_init(ap.folio_descs, 0, fm->fc->max_pages);
+	fuse_folio_descs_length_init(ap.descs, 0, fm->fc->max_pages);
 
 	/*
 	 * If restricted, initialize IO parameters as encoded in @cmd.
@@ -306,7 +306,6 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 	err = -ENOMEM;
 	if (max_pages > fm->fc->max_pages)
 		goto out;
-	ap.uses_folios = true;
 	while (ap.num_folios < max_pages) {
 		ap.folios[ap.num_folios] = folio_alloc(GFP_KERNEL | __GFP_HIGHMEM, 0);
 		if (!ap.folios[ap.num_folios])
diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c
index fd0eff1b9f2de..a2deeada4a5ac 100644
--- a/fs/fuse/readdir.c
+++ b/fs/fuse/readdir.c
@@ -346,10 +346,9 @@ static int fuse_readdir_uncached(struct file *file, struct dir_context *ctx)
 
 	plus = fuse_use_readdirplus(inode, ctx);
 	ap->args.out_pages = true;
-	ap->uses_folios = true;
 	ap->num_folios = 1;
 	ap->folios = &folio;
-	ap->folio_descs = &desc;
+	ap->descs = &desc;
 	if (plus) {
 		attr_version = fuse_get_attr_version(fm->fc);
 		fuse_read_args_fill(&ia, file, ctx->pos, PAGE_SIZE,
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 9f0d98cc20d36..d88d3fc5306a7 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -765,7 +765,6 @@ static void virtio_fs_request_complete(struct fuse_req *req,
 	struct fuse_args *args;
 	struct fuse_args_pages *ap;
 	unsigned int len, i, thislen;
-	struct page *page;
 	struct folio *folio;
 
 	/*
@@ -778,29 +777,15 @@ static void virtio_fs_request_complete(struct fuse_req *req,
 	if (args->out_pages && args->page_zeroing) {
 		len = args->out_args[args->out_numargs - 1].size;
 		ap = container_of(args, typeof(*ap), args);
-		if (ap->uses_folios) {
-			for (i = 0; i < ap->num_folios; i++) {
-				thislen = ap->folio_descs[i].length;
-				if (len < thislen) {
-					WARN_ON(ap->folio_descs[i].offset);
-					folio = ap->folios[i];
-					folio_zero_segment(folio, len, thislen);
-					len = 0;
-				} else {
-					len -= thislen;
-				}
-			}
-		} else {
-			for (i = 0; i < ap->num_pages; i++) {
-				thislen = ap->descs[i].length;
-				if (len < thislen) {
-					WARN_ON(ap->descs[i].offset);
-					page = ap->pages[i];
-					zero_user_segment(page, len, thislen);
-					len = 0;
-				} else {
-					len -= thislen;
-				}
+		for (i = 0; i < ap->num_folios; i++) {
+			thislen = ap->descs[i].length;
+			if (len < thislen) {
+				WARN_ON(ap->descs[i].offset);
+				folio = ap->folios[i];
+				folio_zero_segment(folio, len, thislen);
+				len = 0;
+			} else {
+				len -= thislen;
 			}
 		}
 	}
@@ -1287,22 +1272,16 @@ static void virtio_fs_send_interrupt(struct fuse_iqueue *fiq, struct fuse_req *r
 }
 
 /* Count number of scatter-gather elements required */
-static unsigned int sg_count_fuse_pages(struct fuse_args_pages *ap,
-					unsigned int total_len)
+static unsigned int sg_count_fuse_folios(struct fuse_folio_desc *folio_descs,
+					 unsigned int num_folios,
+					 unsigned int total_len)
 {
 	unsigned int i;
 	unsigned int this_len;
 
-	if (ap->uses_folios) {
-		for (i = 0; i < ap->num_folios && total_len; i++) {
-			this_len =  min(ap->folio_descs[i].length, total_len);
-			total_len -= this_len;
-		}
-	} else {
-		for (i = 0; i < ap->num_pages && total_len; i++) {
-			this_len =  min(ap->descs[i].length, total_len);
-			total_len -= this_len;
-		}
+	for (i = 0; i < num_folios && total_len; i++) {
+		this_len =  min(folio_descs[i].length, total_len);
+		total_len -= this_len;
 	}
 
 	return i;
@@ -1320,7 +1299,8 @@ static unsigned int sg_count_fuse_req(struct fuse_req *req)
 
 	if (args->in_pages) {
 		size = args->in_args[args->in_numargs - 1].size;
-		total_sgs += sg_count_fuse_pages(ap, size);
+		total_sgs += sg_count_fuse_folios(ap->descs, ap->num_folios,
+						  size);
 	}
 
 	if (!test_bit(FR_ISREPLY, &req->flags))
@@ -1333,35 +1313,28 @@ static unsigned int sg_count_fuse_req(struct fuse_req *req)
 
 	if (args->out_pages) {
 		size = args->out_args[args->out_numargs - 1].size;
-		total_sgs += sg_count_fuse_pages(ap, size);
+		total_sgs += sg_count_fuse_folios(ap->descs, ap->num_folios,
+						  size);
 	}
 
 	return total_sgs;
 }
 
-/* Add pages/folios to scatter-gather list and return number of elements used */
-static unsigned int sg_init_fuse_pages(struct scatterlist *sg,
-				       struct fuse_args_pages *ap,
-				       unsigned int total_len)
+/* Add folios to scatter-gather list and return number of elements used */
+static unsigned int sg_init_fuse_folios(struct scatterlist *sg,
+					struct folio **folios,
+					struct fuse_folio_desc *folio_descs,
+					unsigned int num_folios,
+				        unsigned int total_len)
 {
 	unsigned int i;
 	unsigned int this_len;
 
-	if (ap->uses_folios) {
-		for (i = 0; i < ap->num_folios && total_len; i++) {
-			sg_init_table(&sg[i], 1);
-			this_len =  min(ap->folio_descs[i].length, total_len);
-			sg_set_folio(&sg[i], ap->folios[i], this_len,
-				     ap->folio_descs[i].offset);
-			total_len -= this_len;
-		}
-	} else {
-		for (i = 0; i < ap->num_pages && total_len; i++) {
-			sg_init_table(&sg[i], 1);
-			this_len =  min(ap->descs[i].length, total_len);
-			sg_set_page(&sg[i], ap->pages[i], this_len, ap->descs[i].offset);
-			total_len -= this_len;
-		}
+	for (i = 0; i < num_folios && total_len; i++) {
+		sg_init_table(&sg[i], 1);
+		this_len =  min(folio_descs[i].length, total_len);
+		sg_set_folio(&sg[i], folios[i], this_len, folio_descs[i].offset);
+		total_len -= this_len;
 	}
 
 	return i;
@@ -1385,8 +1358,10 @@ static unsigned int sg_init_fuse_args(struct scatterlist *sg,
 		sg_init_one(&sg[total_sgs++], argbuf, len);
 
 	if (argpages)
-		total_sgs += sg_init_fuse_pages(&sg[total_sgs], ap,
-						args[numargs - 1].size);
+		total_sgs += sg_init_fuse_folios(&sg[total_sgs],
+						 ap->folios, ap->descs,
+						 ap->num_folios,
+						 args[numargs - 1].size);
 
 	if (len_used)
 		*len_used = len;

From a7a7c1d423a6351a6541e95c797da5358e5ad1ea Mon Sep 17 00:00:00 2001
From: Xiuhong Wang <xiuhong.wang@unisoc.com>
Date: Tue, 29 Oct 2024 14:15:35 +0800
Subject: [PATCH 0856/1530] f2fs: fix fiemap failure issue when page size is
 16KB

After enable 16K page size, an infinite loop may occur in
fiemap (fm_length=UINT64_MAX) on a file, such as the 16KB
scratch.img during the remount operation in Android.

The condition for whether fiemap continues to map is to check
whether the number of bytes corresponding to the next map.m_lblk
exceeds blks_to_bytes(inode,max_inode_blocks(inode)) if there are HOLE.
The latter does not take into account the maximum size of a file with 16KB
page size, so the loop cannot be jumped out.

The following is the fail trace:
When f2fs_map_blocks reaches map.m_lblk=3936, it needs to go to the
first direct node block, so the map is 3936 + 4090 = 8026,
The next map is the second direct node block, that is,
8026 + 4090 = 12116,
The next map is the first indirect node block, that is,
12116 + 4090 * 4090 = 16740216,
The next map is the second indirect node block, that is,
16740216 + 4090 * 4090 = 33468316,
The next map is the first double indirect node block, that is,
33468316 + 4090 * 4090 * 4090 = 68451397316
Since map.m_lblk represents the address of a block, which is 32
bits, truncation will occur, that is, 68451397316 becomes
4026887876, and the number of bytes corresponding to the block
number does not exceed blks_to_bytes(inode,max_inode_blocks(inode)),
so the loop will not be jumped out.
The next time, it will be considered that it should still be a
double indirect node block, that is,
4026887876 + 4090 * 4090 * 4090 = 72444816876, which will be
truncated to 3725340140, and the loop will not be jumped out.

156.374871: f2fs_map_blocks: dev = (254,57), ino = 7449, file offset = 0, start blkaddr = 0x8e00, len = 0x200, flags = 2,seg_type = 8, may_create = 0, multidevice = 0, flag = 1, err = 0
156.374916: f2fs_map_blocks: dev = (254,57), ino = 7449, file offset = 512, start blkaddr = 0x0, len = 0x0, flags = 0 , seg_type = 8, may_create = 0, multidevice = 0, flag = 1, err = 0
156.374920: f2fs_map_blocks: dev = (254,57), ino = 7449, file offset = 513, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 8, may_create = 0, multidevice = 0, flag = 1, err = 0
......
156.385747: f2fs_map_blocks: dev = (254,57), ino = 7449, file offset = 3935, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 8, may_create = 0, multidevice = 0, flag = 1, err = 0
156.385752: f2fs_map_blocks: dev = (254,57), ino = 7449, file offset = 3936, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 8, may_create = 0, multidevice = 0, flag = 1, err = 0
156.385755: f2fs_map_blocks: dev = (254,57), ino = 7449, file offset = 8026, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 8, may_create = 0, multidevice = 0, flag = 1, err = 0
156.385758: f2fs_map_blocks: dev = (254,57), ino = 7449, file offset = 12116, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 8, may_create = 0, multidevice = 0, flag = 1, err = 0
156.385761: f2fs_map_blocks: dev = (254,57), ino = 7449, file offset = 16740216, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 8, may_create = 0, multidevice = 0, flag = 1, err = 0
156.385764: f2fs_map_blocks: dev = (254,57), ino = 7449, file offset = 33468316, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 8, may_create = 0, multidevice = 0, flag = 1, err = 0
156.385767: f2fs_map_blocks: dev = (254,57), ino = 7449, file offset = 4026887876, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 8, may_create = 0, multidevice = 0, flag = 1, err = 0
156.385770: f2fs_map_blocks: dev = (254,57), ino = 7449, file offset = 3725340140, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 8, may_create = 0, multidevice = 0, flag = 1, err = 0
156.385772: f2fs_map_blocks: dev = (254,57), ino = 7449, file offset = 4026887876, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 8, may_create = 0, multidevice = 0, flag = 1, err = 0
156.385775: f2fs_map_blocks: dev = (254,57), ino = 7449, file offset = 3725340140, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 8, may_create = 0, multidevice = 0, flag = 1, err = 0

Commit a6a010f5def5 ("f2fs: Restrict max filesize for 16K f2fs")
has set the maximum allowed file size to (U32_MAX + 1) * F2FS_BLKSIZE,
so max_file_blocks should be used here to limit it, that is,
maxbytes defined above. And the max_inode_blocks function is not
called by other functions except here, so cleanup it.

Signed-off-by: Xiuhong Wang <xiuhong.wang@unisoc.com>
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 22 +---------------------
 1 file changed, 1 insertion(+), 21 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 306b86b0595d1..402e00d54c0bc 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1901,25 +1901,6 @@ static int f2fs_xattr_fiemap(struct inode *inode,
 	return (err < 0 ? err : 0);
 }
 
-static loff_t max_inode_blocks(struct inode *inode)
-{
-	loff_t result = ADDRS_PER_INODE(inode);
-	loff_t leaf_count = ADDRS_PER_BLOCK(inode);
-
-	/* two direct node blocks */
-	result += (leaf_count * 2);
-
-	/* two indirect node blocks */
-	leaf_count *= NIDS_PER_BLOCK;
-	result += (leaf_count * 2);
-
-	/* one double indirect node block */
-	leaf_count *= NIDS_PER_BLOCK;
-	result += leaf_count;
-
-	return result;
-}
-
 int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		u64 start, u64 len)
 {
@@ -1992,8 +1973,7 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	if (!compr_cluster && !(map.m_flags & F2FS_MAP_FLAGS)) {
 		start_blk = next_pgofs;
 
-		if (blks_to_bytes(inode, start_blk) < blks_to_bytes(inode,
-						max_inode_blocks(inode)))
+		if (blks_to_bytes(inode, start_blk) < maxbytes)
 			goto prep_next;
 
 		flags |= FIEMAP_EXTENT_LAST;

From 7b0033dbc48340a1c1c3f12448ba17d6587ca092 Mon Sep 17 00:00:00 2001
From: Long Li <leo.lilong@huawei.com>
Date: Mon, 4 Nov 2024 10:05:42 +0800
Subject: [PATCH 0857/1530] f2fs: fix race in concurrent f2fs_stop_gc_thread

In my test case, concurrent calls to f2fs shutdown report the following
stack trace:

 Oops: general protection fault, probably for non-canonical address 0xc6cfff63bb5513fc: 0000 [#1] PREEMPT SMP PTI
 CPU: 0 UID: 0 PID: 678 Comm: f2fs_rep_shutdo Not tainted 6.12.0-rc5-next-20241029-g6fb2fa9805c5-dirty #85
 Call Trace:
  <TASK>
  ? show_regs+0x8b/0xa0
  ? __die_body+0x26/0xa0
  ? die_addr+0x54/0x90
  ? exc_general_protection+0x24b/0x5c0
  ? asm_exc_general_protection+0x26/0x30
  ? kthread_stop+0x46/0x390
  f2fs_stop_gc_thread+0x6c/0x110
  f2fs_do_shutdown+0x309/0x3a0
  f2fs_ioc_shutdown+0x150/0x1c0
  __f2fs_ioctl+0xffd/0x2ac0
  f2fs_ioctl+0x76/0xe0
  vfs_ioctl+0x23/0x60
  __x64_sys_ioctl+0xce/0xf0
  x64_sys_call+0x2b1b/0x4540
  do_syscall_64+0xa7/0x240
  entry_SYSCALL_64_after_hwframe+0x76/0x7e

The root cause is a race condition in f2fs_stop_gc_thread() called from
different f2fs shutdown paths:

  [CPU0]                       [CPU1]
  ----------------------       -----------------------
  f2fs_stop_gc_thread          f2fs_stop_gc_thread
                                 gc_th = sbi->gc_thread
    gc_th = sbi->gc_thread
    kfree(gc_th)
    sbi->gc_thread = NULL
                                 < gc_th != NULL >
                                 kthread_stop(gc_th->f2fs_gc_task) //UAF

The commit c7f114d864ac ("f2fs: fix to avoid use-after-free in
f2fs_stop_gc_thread()") attempted to fix this issue by using a read
semaphore to prevent races between shutdown and remount threads, but
it fails to prevent all race conditions.

Fix it by converting to write lock of s_umount in f2fs_do_shutdown().

Fixes: 7950e9ac638e ("f2fs: stop gc/discard thread after fs shutdown")
Signed-off-by: Long Li <leo.lilong@huawei.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/file.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index b619f7e556406..c0818a4f87c15 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -2365,9 +2365,12 @@ int f2fs_do_shutdown(struct f2fs_sb_info *sbi, unsigned int flag,
 	if (readonly)
 		goto out;
 
-	/* grab sb->s_umount to avoid racing w/ remount() */
+	/*
+	 * grab sb->s_umount to avoid racing w/ remount() and other shutdown
+	 * paths.
+	 */
 	if (need_lock)
-		down_read(&sbi->sb->s_umount);
+		down_write(&sbi->sb->s_umount);
 
 	f2fs_stop_gc_thread(sbi);
 	f2fs_stop_discard_thread(sbi);
@@ -2376,7 +2379,7 @@ int f2fs_do_shutdown(struct f2fs_sb_info *sbi, unsigned int flag,
 	clear_opt(sbi, DISCARD);
 
 	if (need_lock)
-		up_read(&sbi->sb->s_umount);
+		up_write(&sbi->sb->s_umount);
 
 	f2fs_update_time(sbi, REQ_TIME);
 out:

From 5dd00ebda337b9295e7027691fa70540da369ff2 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Mon, 4 Nov 2024 09:35:51 +0800
Subject: [PATCH 0858/1530] f2fs: fix to map blocks correctly for direct write

f2fs_map_blocks() supports to map continuous holes or preallocated
address, we should avoid setting F2FS_MAP_MAPPED for these cases
only, otherwise, it may fail f2fs_iomap_begin(), and make direct
write fallbacking to use buffered IO and flush, result in performance
regression.

Fixes: 9f0f6bf42714 ("f2fs: support to map continuous holes or preallocated address")
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202409122103.e45aa13b-oliver.sang@intel.com
Cc: Cyril Hrubis <chrubis@suse.cz>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 402e00d54c0bc..b33aca24b9ef2 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1676,7 +1676,8 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int flag)
 		/* reserved delalloc block should be mapped for fiemap. */
 		if (blkaddr == NEW_ADDR)
 			map->m_flags |= F2FS_MAP_DELALLOC;
-		if (flag != F2FS_GET_BLOCK_DIO || !is_hole)
+		/* DIO READ and hole case, should not map the blocks. */
+		if (!(flag == F2FS_GET_BLOCK_DIO && is_hole && !map->m_may_create))
 			map->m_flags |= F2FS_MAP_MAPPED;
 
 		map->m_pblk = blkaddr;

From 26e6f59d0bbaac76fa3413462d780bd2b5f9f653 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Mon, 4 Nov 2024 09:50:16 +0800
Subject: [PATCH 0859/1530] f2fs: fix to avoid forcing direct write to use
 buffered IO on inline_data inode

Jinsu Lee reported a performance regression issue, after commit
5c8764f8679e ("f2fs: fix to force buffered IO on inline_data
inode"), we forced direct write to use buffered IO on inline_data
inode, it will cause performace regression due to memory copy
and data flush.

It's fine to not force direct write to use buffered IO, as it
can convert inline inode before committing direct write IO.

Fixes: 5c8764f8679e ("f2fs: fix to force buffered IO on inline_data inode")
Reported-by: Jinsu Lee <jinsu1.lee@samsung.com>
Closes: https://lore.kernel.org/linux-f2fs-devel/af03dd2c-e361-4f80-b2fd-39440766cf6e@kernel.org
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/file.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index c0818a4f87c15..cb2172a698be2 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -883,7 +883,11 @@ static bool f2fs_force_buffered_io(struct inode *inode, int rw)
 		return true;
 	if (f2fs_compressed_file(inode))
 		return true;
-	if (f2fs_has_inline_data(inode))
+	/*
+	 * only force direct read to use buffered IO, for direct write,
+	 * it expects inline data conversion before committing IO.
+	 */
+	if (f2fs_has_inline_data(inode) && rw == READ)
 		return true;
 
 	/* disallow direct IO if any of devices has unaligned blksize */

From 7a56ca20c09d8b8bf20d1ff1677d68f87b570de0 Mon Sep 17 00:00:00 2001
From: Matthew Maurer <mmaurer@google.com>
Date: Wed, 30 Oct 2024 17:16:34 +0000
Subject: [PATCH 0860/1530] scripts: Remove export_report.pl

This script has been broken for 5 years with no user complaints.

It first had its .mod.c parser broken in commit a3d0cb04f7df ("modpost:
use __section in the output to *.mod.c"). Later, it had its object file
enumeration broken in commit f65a486821cf ("kbuild: change module.order
to list *.o instead of *.ko"). Both of these changes sat for years with
no reports.

Rather than reviving this script as we make further changes to `.mod.c`,
this patch gets rid of it because it is clearly unused.

Signed-off-by: Matthew Maurer <mmaurer@google.com>
Acked-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 Makefile                 |   6 +-
 scripts/export_report.pl | 186 ---------------------------------------
 2 files changed, 1 insertion(+), 191 deletions(-)
 delete mode 100755 scripts/export_report.pl

diff --git a/Makefile b/Makefile
index 8cf3cf5288924..d0a695b131882 100644
--- a/Makefile
+++ b/Makefile
@@ -1602,7 +1602,6 @@ help:
 	@echo  '                    with a stack size larger than MINSTACKSIZE (default: 100)'
 	@echo  '  versioncheck    - Sanity check on version.h usage'
 	@echo  '  includecheck    - Check for duplicate included header files'
-	@echo  '  export_report   - List the usages of all exported symbols'
 	@echo  '  headerdep       - Detect inclusion cycles in headers'
 	@echo  '  coccicheck      - Check with Coccinelle'
 	@echo  '  clang-analyzer  - Check with clang static analyzer'
@@ -2015,7 +2014,7 @@ endif
 # Scripts to check various things for consistency
 # ---------------------------------------------------------------------------
 
-PHONY += includecheck versioncheck coccicheck export_report
+PHONY += includecheck versioncheck coccicheck
 
 includecheck:
 	find $(srctree)/* $(RCS_FIND_IGNORE) \
@@ -2030,9 +2029,6 @@ versioncheck:
 coccicheck:
 	$(Q)$(BASH) $(srctree)/scripts/$@
 
-export_report:
-	$(PERL) $(srctree)/scripts/export_report.pl
-
 PHONY += checkstack kernelrelease kernelversion image_name
 
 # UML needs a little special treatment here.  It wants to use the host
diff --git a/scripts/export_report.pl b/scripts/export_report.pl
deleted file mode 100755
index feb3d5542a62d..0000000000000
--- a/scripts/export_report.pl
+++ /dev/null
@@ -1,186 +0,0 @@
-#!/usr/bin/env perl
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# (C) Copyright IBM Corporation 2006.
-#	Author : Ram Pai (linuxram@us.ibm.com)
-#
-# Usage: export_report.pl -k Module.symvers [-o report_file ] -f *.mod.c
-#
-
-use warnings;
-use Getopt::Std;
-use strict;
-
-sub numerically {
-	my $no1 = (split /\s+/, $a)[1];
-	my $no2 = (split /\s+/, $b)[1];
-	return $no1 <=> $no2;
-}
-
-sub alphabetically {
-	my ($module1, $value1) = @{$a};
-	my ($module2, $value2) = @{$b};
-	return $value1 <=> $value2 || $module2 cmp $module1;
-}
-
-sub print_depends_on {
-	my ($href) = @_;
-	print "\n";
-	for my $mod (sort keys %$href) {
-		my $list = $href->{$mod};
-		print "\t$mod:\n";
-		foreach my $sym (sort numerically @{$list}) {
-			my ($symbol, $no) = split /\s+/, $sym;
-			printf("\t\t%-25s\n", $symbol);
-		}
-		print "\n";
-	}
-	print "\n";
-	print "~"x80 , "\n";
-}
-
-sub usage {
-        print "Usage: @_ -h -k Module.symvers  [ -o outputfile ] \n",
-	      "\t-f: treat all the non-option argument as .mod.c files. ",
-	      "Recommend using this as the last option\n",
-	      "\t-h: print detailed help\n",
-	      "\t-k: the path to Module.symvers file. By default uses ",
-	      "the file from the current directory\n",
-	      "\t-o outputfile: output the report to outputfile\n";
-	exit 0;
-}
-
-sub collectcfiles {
-    my @file;
-    open my $fh, '< modules.order' or die "cannot open modules.order: $!\n";
-    while (<$fh>) {
-	s/\.ko$/.mod.c/;
-	push (@file, $_)
-    }
-    close($fh);
-    chomp @file;
-    return @file;
-}
-
-my (%SYMBOL, %MODULE, %opt, @allcfiles);
-
-if (not getopts('hk:o:f',\%opt) or defined $opt{'h'}) {
-        usage($0);
-}
-
-if (defined $opt{'f'}) {
-	@allcfiles = @ARGV;
-} else {
-	@allcfiles = collectcfiles();
-}
-
-if (not defined $opt{'k'}) {
-	$opt{'k'} = "Module.symvers";
-}
-
-open (my $module_symvers, '<', $opt{'k'})
-    or die "Sorry, cannot open $opt{'k'}: $!\n";
-
-if (defined $opt{'o'}) {
-    open (my $out, '>', $opt{'o'})
-	or die "Sorry, cannot open $opt{'o'} $!\n";
-
-    select $out;
-}
-
-#
-# collect all the symbols and their attributes from the
-# Module.symvers file
-#
-while ( <$module_symvers> ) {
-	chomp;
-	my (undef, $symbol, $module, $gpl, $namespace) = split('\t');
-	$SYMBOL { $symbol } =  [ $module , "0" , $symbol, $gpl];
-}
-close($module_symvers);
-
-#
-# collect the usage count of each symbol.
-#
-my $modversion_warnings = 0;
-
-foreach my $thismod (@allcfiles) {
-	my $module;
-
-	unless (open ($module, '<', $thismod)) {
-		warn "Sorry, cannot open $thismod: $!\n";
-		next;
-	}
-
-	my $state=0;
-	while ( <$module> ) {
-		chomp;
-		if ($state == 0) {
-			$state = 1 if ($_ =~ /static const struct modversion_info/);
-			next;
-		}
-		if ($state == 1) {
-			$state = 2 if ($_ =~ /__attribute__\(\(section\("__versions"\)\)\)/);
-			next;
-		}
-		if ($state == 2) {
-			if ( $_ !~ /0x[0-9a-f]+,/ ) {
-				next;
-			}
-			my $sym = (split /([,"])/,)[4];
-			my ($module, $value, $symbol, $gpl) = @{$SYMBOL{$sym}};
-			$SYMBOL{ $sym } =  [ $module, $value+1, $symbol, $gpl];
-			push(@{$MODULE{$thismod}} , $sym);
-		}
-	}
-	if ($state != 2) {
-		warn "WARNING:$thismod is not built with CONFIG_MODVERSIONS enabled\n";
-		$modversion_warnings++;
-	}
-	close($module);
-}
-
-print "\tThis file reports the exported symbols usage patterns by in-tree\n",
-	"\t\t\t\tmodules\n";
-printf("%s\n\n\n","x"x80);
-printf("\t\t\t\tINDEX\n\n\n");
-printf("SECTION 1: Usage counts of all exported symbols\n");
-printf("SECTION 2: List of modules and the exported symbols they use\n");
-printf("%s\n\n\n","x"x80);
-printf("SECTION 1:\tThe exported symbols and their usage count\n\n");
-printf("%-25s\t%-25s\t%-5s\t%-25s\n", "Symbol", "Module", "Usage count",
-	"export type");
-
-#
-# print the list of unused exported symbols
-#
-foreach my $list (sort alphabetically values(%SYMBOL)) {
-	my ($module, $value, $symbol, $gpl) = @{$list};
-	printf("%-25s\t%-25s\t%-10s\t", $symbol, $module, $value);
-	if (defined $gpl) {
-		printf("%-25s\n",$gpl);
-	} else {
-		printf("\n");
-	}
-}
-printf("%s\n\n\n","x"x80);
-
-printf("SECTION 2:\n\tThis section reports export-symbol-usage of in-kernel
-modules. Each module lists the modules, and the symbols from that module that
-it uses.  Each listed symbol reports the number of modules using it\n");
-
-print "\nNOTE: Got $modversion_warnings CONFIG_MODVERSIONS warnings\n\n"
-    if $modversion_warnings;
-
-print "~"x80 , "\n";
-for my $thismod (sort keys %MODULE) {
-	my $list = $MODULE{$thismod};
-	my %depends;
-	$thismod =~ s/\.mod\.c/.ko/;
-	print "\t\t\t$thismod\n";
-	foreach my $symbol (@{$list}) {
-		my ($module, $value, undef, $gpl) = @{$SYMBOL{$symbol}};
-		push (@{$depends{"$module"}}, "$symbol $value");
-	}
-	print_depends_on(\%depends);
-}

From 718c157a0b941fe2d3b4cca689148775e6ea2330 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Tue, 5 Nov 2024 15:32:16 -0600
Subject: [PATCH 0861/1530] dt-bindings: PCI: snps,dw-pcie: Drop
 "#interrupt-cells" from example
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

"#interrupt-cells" is not valid without a corresponding "interrupt-map"
or "interrupt-controller" property. As the example has neither, drop
"#interrupt-cells".

This fixes a dtc interrupt_provider warning.

Link: https://lore.kernel.org/r/20241105213217.442809-1-robh@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml | 1 -
 1 file changed, 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml b/Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml
index 548f59d76ef20..205326fb2d75c 100644
--- a/Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml
@@ -230,7 +230,6 @@ examples:
 
       interrupts = <25>, <24>;
       interrupt-names = "msi", "hp";
-      #interrupt-cells = <1>;
 
       reset-gpios = <&port0 0 1>;
 

From dda8fdb033f48e759ff190c59aa266905ecba3dd Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Thu, 24 Oct 2024 18:43:44 -0700
Subject: [PATCH 0862/1530] Input: hilkbd - use guard notation when acquiring
 spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/Zxr30BpPobpM65vO@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/hilkbd.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/input/keyboard/hilkbd.c b/drivers/input/keyboard/hilkbd.c
index c1a4d5055de63..c8d8d0ea35b0c 100644
--- a/drivers/input/keyboard/hilkbd.c
+++ b/drivers/input/keyboard/hilkbd.c
@@ -180,9 +180,8 @@ static irqreturn_t hil_interrupt(int irq, void *handle)
 /* send a command to the HIL */
 static void hil_do(unsigned char cmd, unsigned char *data, unsigned int len)
 {
-	unsigned long flags;
+	guard(spinlock_irqsave)(&hil_dev.lock);
 
-	spin_lock_irqsave(&hil_dev.lock, flags);
 	while (hil_busy())
 		/* wait */;
 	hil_command(cmd);
@@ -191,7 +190,6 @@ static void hil_do(unsigned char cmd, unsigned char *data, unsigned int len)
 			/* wait */;
 		hil_write_data(*(data++));
 	}
-	spin_unlock_irqrestore(&hil_dev.lock, flags);
 }
 
 

From 229ba714e52f7f29f41c1aa2e9f49feef3629322 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Thu, 24 Oct 2024 18:44:32 -0700
Subject: [PATCH 0863/1530] Input: locomokbd - use guard notation when
 acquiring spinlock

Using guard notation makes the code more compact and error handling
more robust by ensuring that locks are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/Zxr4AMJrzhZlHAlf@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/locomokbd.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/input/keyboard/locomokbd.c b/drivers/input/keyboard/locomokbd.c
index 4b0f8323c4922..c501a93a44178 100644
--- a/drivers/input/keyboard/locomokbd.c
+++ b/drivers/input/keyboard/locomokbd.c
@@ -112,11 +112,10 @@ static inline void locomokbd_reset_col(unsigned long membase, int col)
 static void locomokbd_scankeyboard(struct locomokbd *locomokbd)
 {
 	unsigned int row, col, rowd;
-	unsigned long flags;
 	unsigned int num_pressed;
 	unsigned long membase = locomokbd->base;
 
-	spin_lock_irqsave(&locomokbd->lock, flags);
+	guard(spinlock_irqsave)(&locomokbd->lock);
 
 	locomokbd_charge_all(membase);
 
@@ -167,8 +166,6 @@ static void locomokbd_scankeyboard(struct locomokbd *locomokbd)
 		mod_timer(&locomokbd->timer, jiffies + SCAN_INTERVAL);
 	else
 		locomokbd->count_cancel = 0;
-
-	spin_unlock_irqrestore(&locomokbd->lock, flags);
 }
 
 /*

From 6b6b40ff05ab43b603abd7ae1821892307421d49 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sun, 27 Oct 2024 22:50:18 -0700
Subject: [PATCH 0864/1530] Input: maple_keyb - use guard notation when
 acquiring mutex

Using guard notation makes the code more compact and error handling
more robust by ensuring that mutexes are released in all code paths
when control leaves critical section.

Link: https://lore.kernel.org/r/Zx8mGiWOw1Av28TX@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/maple_keyb.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/input/keyboard/maple_keyb.c b/drivers/input/keyboard/maple_keyb.c
index 91a1d29581094..1a8f1fa53fbb4 100644
--- a/drivers/input/keyboard/maple_keyb.c
+++ b/drivers/input/keyboard/maple_keyb.c
@@ -132,14 +132,11 @@ static void dc_kbd_callback(struct mapleq *mq)
 	 * We should always get the lock because the only
 	 * time it may be locked is if the driver is in the cleanup phase.
 	 */
-	if (likely(mutex_trylock(&maple_keyb_mutex))) {
-
+	scoped_guard(mutex_try, &maple_keyb_mutex) {
 		if (buf[1] == mapledev->function) {
 			memcpy(kbd->new, buf + 2, 8);
 			dc_scan_kbd(kbd);
 		}
-
-		mutex_unlock(&maple_keyb_mutex);
 	}
 }
 
@@ -211,14 +208,12 @@ static int remove_maple_kbd(struct device *dev)
 	struct maple_device *mdev = to_maple_dev(dev);
 	struct dc_kbd *kbd = maple_get_drvdata(mdev);
 
-	mutex_lock(&maple_keyb_mutex);
+	guard(mutex)(&maple_keyb_mutex);
 
 	input_unregister_device(kbd->dev);
 	kfree(kbd);
 
 	maple_set_drvdata(mdev, NULL);
-
-	mutex_unlock(&maple_keyb_mutex);
 	return 0;
 }
 

From 57a063632df8db6cb20d64ee52a06d4e2049235a Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 23 Oct 2024 11:45:24 -0700
Subject: [PATCH 0865/1530] Input: introduce notion of passive observers for
 input handlers

Sometimes it is useful to observe (and maybe modify) data coming from
an input device, but only do that if there are other users of such input
device. An example is touchpad switching functionality on Lenovo IdeaPad
Z570 where it is desirable to suppress events coming from the touchpad
if user toggles touchpad on/off button (on this laptop the firmware does
not stop the device).

Introduce notion of passive observers for input handlers to solve this
issue. An input handler marked as passive observer behaves exactly like
any other input handler or filter, but with one exception: it does not
open/start underlying input device when attaching to it.

Link: https://lore.kernel.org/r/ZxlEROX7bMo5cbZP@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/input.c | 15 ++++++++++-----
 include/linux/input.h |  5 +++++
 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/input/input.c b/drivers/input/input.c
index 3c321671793f2..3b1e88ead97e1 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -605,6 +605,9 @@ int input_open_device(struct input_handle *handle)
 
 	handle->open++;
 
+	if (handle->handler->passive_observer)
+		goto out;
+
 	if (dev->users++ || dev->inhibited) {
 		/*
 		 * Device is already opened and/or inhibited,
@@ -668,11 +671,13 @@ void input_close_device(struct input_handle *handle)
 
 	__input_release_device(handle);
 
-	if (!--dev->users && !dev->inhibited) {
-		if (dev->poller)
-			input_dev_poller_stop(dev->poller);
-		if (dev->close)
-			dev->close(dev);
+	if (!handle->handler->passive_observer) {
+		if (!--dev->users && !dev->inhibited) {
+			if (dev->poller)
+				input_dev_poller_stop(dev->poller);
+			if (dev->close)
+				dev->close(dev);
+		}
 	}
 
 	if (!--handle->open) {
diff --git a/include/linux/input.h b/include/linux/input.h
index 89a0be6ee0e23..6437c35f07968 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -286,6 +286,10 @@ struct input_handle;
  * @start: starts handler for given handle. This function is called by
  *	input core right after connect() method and also when a process
  *	that "grabbed" a device releases it
+ * @passive_observer: set to %true by drivers only interested in observing
+ *	data stream from devices if there are other users present. Such
+ *	drivers will not result in starting underlying hardware device
+ *	when input_open_device() is called for their handles
  * @legacy_minors: set to %true by drivers using legacy minor ranges
  * @minor: beginning of range of 32 legacy minors for devices this driver
  *	can provide
@@ -321,6 +325,7 @@ struct input_handler {
 	void (*disconnect)(struct input_handle *handle);
 	void (*start)(struct input_handle *handle);
 
+	bool passive_observer;
 	bool legacy_minors;
 	int minor;
 	const char *name;

From cedcf08f43dab0bf27e7a4e9bc82f27ccf89241d Mon Sep 17 00:00:00 2001
From: Zhang Zekun <zhangzekun11@huawei.com>
Date: Fri, 6 Sep 2024 13:57:42 +0800
Subject: [PATCH 0866/1530] ocfs2: remove unused declaration in header file

The definition of ocfs2_global_read_dquot() has been removed since commit
fb8dd8d78014 ("ocfs2: Fix quota locking").  Let's remove the empty
declartion

Link: https://lkml.kernel.org/r/20240906055742.105024-1-zhangzekun11@huawei.com
Signed-off-by: Zhang Zekun <zhangzekun11@huawei.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <jiangqi903@gmail.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Jun Piao <piaojun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/ocfs2/quota.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h
index ebb5c99f490ef..788a8de922a43 100644
--- a/fs/ocfs2/quota.h
+++ b/fs/ocfs2/quota.h
@@ -97,7 +97,6 @@ ssize_t ocfs2_quota_write(struct super_block *sb, int type,
 			  const char *data, size_t len, loff_t off);
 int ocfs2_global_read_info(struct super_block *sb, int type);
 int ocfs2_global_write_info(struct super_block *sb, int type);
-int ocfs2_global_read_dquot(struct dquot *dquot);
 int __ocfs2_sync_dquot(struct dquot *dquot, int freeing);
 static inline int ocfs2_sync_dquot(struct dquot *dquot)
 {

From 5c50b3b8cfefbe306f2b348eec0663b458d70221 Mon Sep 17 00:00:00 2001
From: Mohammed Anees <pvmohammedanees2003@gmail.com>
Date: Tue, 17 Sep 2024 18:51:56 +0000
Subject: [PATCH 0867/1530] ocfs2: fix typo in comment

Fix "Allcate" -> "Allocate"

Link: https://lkml.kernel.org/r/20240917185156.10580-1-pvmohammedanees2003@gmail.com
Signed-off-by: Mohammed Anees <pvmohammedanees2003@gmail.com>
Acked-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Jun Piao <piaojun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/ocfs2/alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index ea9127ba32084..395e239206322 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -4767,7 +4767,7 @@ int ocfs2_insert_extent(handle_t *handle,
 }
 
 /*
- * Allcate and add clusters into the extent b-tree.
+ * Allocate and add clusters into the extent b-tree.
  * The new clusters(clusters_to_add) will be inserted at logical_offset.
  * The extent b-tree's root is specified by et, and
  * it is not limited to the file storage. Any extent tree can use this

From 6efbd5ddb6af0408301b4c15b413e6425c7650b2 Mon Sep 17 00:00:00 2001
From: Sourabh Jain <sourabhjain@linux.ibm.com>
Date: Sat, 21 Sep 2024 16:07:45 +0530
Subject: [PATCH 0868/1530] kexec/crash: no crash update when kexec in progress

The following errors are observed when kexec is done with SMT=off on
powerpc.

[  358.458385] Removing IBM Power 842 compression device
[  374.795734] kexec_core: Starting new kernel
[  374.795748] kexec: Waking offline cpu 1.
[  374.875695] crash hp: kexec_trylock() failed, elfcorehdr may be inaccurate
[  374.935833] kexec: Waking offline cpu 2.
[  375.015664] crash hp: kexec_trylock() failed, elfcorehdr may be inaccurate
snip..
[  375.515823] kexec: Waking offline cpu 6.
[  375.635667] crash hp: kexec_trylock() failed, elfcorehdr may be inaccurate
[  375.695836] kexec: Waking offline cpu 7.

To avoid kexec kernel boot failure on PowerPC, all the present CPUs that
are offline are brought online during kexec.  For more information, refer
to commit e8e5c2155b00 ("powerpc/kexec: Fix orphaned offline CPUs across
kexec").  Bringing the CPUs online triggers the crash hotplug handler,
crash_handle_hotplug_event(), to update the kdump image.  Since the system
is on the kexec kernel boot path and the kexec lock is held, the
crash_handle_hotplug_event() function fails to acquire the same lock to
update the kdump image, resulting in the error messages mentioned above.

To fix this, return from crash_handle_hotplug_event() without printing the
error message if kexec is in progress.

The same applies to the crash_check_hotplug_support() function.  Return 0
if kexec is in progress because kernel is not in a position to update the
kdump image.

Link: https://lkml.kernel.org/r/20240921103745.560430-1-sourabhjain@linux.ibm.com
Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
Acked-by: Baoquan he <bhe@redhat.com>
Reported-by: Sachin P Bappalige <sachinpb@linux.vnet.ibm.com>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/crash_core.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index c1048893f4b68..078fe5bc5a747 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -505,7 +505,8 @@ int crash_check_hotplug_support(void)
 	crash_hotplug_lock();
 	/* Obtain lock while reading crash information */
 	if (!kexec_trylock()) {
-		pr_info("kexec_trylock() failed, kdump image may be inaccurate\n");
+		if (!kexec_in_progress)
+			pr_info("kexec_trylock() failed, kdump image may be inaccurate\n");
 		crash_hotplug_unlock();
 		return 0;
 	}
@@ -547,7 +548,8 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu,
 	crash_hotplug_lock();
 	/* Obtain lock while changing crash information */
 	if (!kexec_trylock()) {
-		pr_info("kexec_trylock() failed, kdump image may be inaccurate\n");
+		if (!kexec_in_progress)
+			pr_info("kexec_trylock() failed, kdump image may be inaccurate\n");
 		crash_hotplug_unlock();
 		return;
 	}

From 838010180241f5a9779a9ef9a621cdd2842f7354 Mon Sep 17 00:00:00 2001
From: Tio Zhang <tiozhang@didiglobal.com>
Date: Fri, 6 Sep 2024 17:47:00 +0800
Subject: [PATCH 0869/1530] kernel/watchdog: always restore
 watchdog_softlockup(,hardlockup)_user_enabled after proc show
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Otherwise when watchdog_enabled becomes 0,
watchdog_softlockup(,hardlockup)_user_enabled will changes to 0 after proc
show.

Steps to reproduce:

  step 1:
  # cat /proc/sys/kernel/*watchdog
  1
  1
  1

  | name                             | value
  |----------------------------------|--------------------------
  | watchdog_enabled                 | 1
  |----------------------------------|--------------------------
  | watchdog_hardlockup_user_enabled | 1
  |----------------------------------|--------------------------
  | watchdog_softlockup_user_enabled | 1
  |----------------------------------|--------------------------
  | watchdog_user_enabled            | 1
  |----------------------------------|--------------------------

  step 2:
  # echo 0 > /proc/sys/kernel/watchdog

  | name                             | value
  |----------------------------------|--------------------------
  | watchdog_enabled                 | 0
  |----------------------------------|--------------------------
  | watchdog_hardlockup_user_enabled | 1
  |----------------------------------|--------------------------
  | watchdog_softlockup_user_enabled | 1
  |----------------------------------|--------------------------
  | watchdog_user_enabled            | 0
  |----------------------------------|--------------------------

  step 3:
  # cat /proc/sys/kernel/*watchdog
  0
  0
  0

  | name                             | value
  |----------------------------------|--------------------------
  | watchdog_enabled                 | 0
  |----------------------------------|--------------------------
  | watchdog_hardlockup_user_enabled | 0
  |----------------------------------|--------------------------
  | watchdog_softlockup_user_enabled | 0
  |----------------------------------|--------------------------
  | watchdog_user_enabled            | 0
  |----------------------------------|--------------------------

  step 4:
  # echo 1 > /proc/sys/kernel/watchdog

  | name                             | value
  |----------------------------------|--------------------------
  | watchdog_enabled                 | 0
  |----------------------------------|--------------------------
  | watchdog_hardlockup_user_enabled | 0
  |----------------------------------|--------------------------
  | watchdog_softlockup_user_enabled | 0
  |----------------------------------|--------------------------
  | watchdog_user_enabled            | 0
  |----------------------------------|--------------------------

  step 5:
  # cat /proc/sys/kernel/*watchdog
  0
  0
  0

If we dont do "step 3", do "step 4" right after "step 2", it will be

  | name                             | value
  |----------------------------------|--------------------------
  | watchdog_enabled                 | 1
  |----------------------------------|--------------------------
  | watchdog_hardlockup_user_enabled | 1
  |----------------------------------|--------------------------
  | watchdog_softlockup_user_enabled | 1
  |----------------------------------|--------------------------
  | watchdog_user_enabled            | 1
  |----------------------------------|--------------------------

then everything works correctly.

So this patch fix "step 3"'s value into

| name                             | value
|----------------------------------|--------------------------
| watchdog_enabled                 | 0
|----------------------------------|--------------------------
| watchdog_hardlockup_user_enabled | 1
|----------------------------------|--------------------------
| watchdog_softlockup_user_enabled | 1
|----------------------------------|--------------------------
| watchdog_user_enabled            | 0
|----------------------------------|--------------------------

And still print 0 as before.

Link: https://lkml.kernel.org/r/20240906094700.GA30052@didi-ThinkCentre-M930t-N000
Signed-off-by: Tio Zhang <tiozhang@didiglobal.com>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: John Ogness <john.ogness@linutronix.de>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Krister Johansen <kjlx@templeofstupid.com>
Cc: Li Zhe <lizhe.67@bytedance.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Weißschuh <linux@weissschuh.net>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/watchdog.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 262691ba62b7a..6c91b6b72f51e 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -990,6 +990,7 @@ static int proc_watchdog_common(int which, const struct ctl_table *table, int wr
 
 	mutex_lock(&watchdog_mutex);
 
+	old = *param;
 	if (!write) {
 		/*
 		 * On read synchronize the userspace interface. This is a
@@ -997,8 +998,8 @@ static int proc_watchdog_common(int which, const struct ctl_table *table, int wr
 		 */
 		*param = (watchdog_enabled & which) != 0;
 		err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+		*param = old;
 	} else {
-		old = READ_ONCE(*param);
 		err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 		if (!err && old != READ_ONCE(*param))
 			proc_watchdog_update();

From 5c1edea773c98707fbb23d1df168bcff52f61e4b Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 25 Sep 2024 18:43:34 +0300
Subject: [PATCH 0870/1530] resource: replace open coded
 resource_intersection()

Patch series "resource: A couple of cleanups".

A couple of ad-hoc cleanups since there was a recent development of
the code in question. No functional changes intended.


This patch (of 2):

__region_intersects() uses open coded resource_intersection().  Replace it
with existing API which also make more clear what we are checking.

Link: https://lkml.kernel.org/r/20240925154355.1170859-1-andriy.shevchenko@linux.intel.com
Link: https://lkml.kernel.org/r/20240925154355.1170859-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/resource.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/kernel/resource.c b/kernel/resource.c
index 4101016e8b205..1c77ac239c7a4 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -537,17 +537,16 @@ static int __region_intersects(struct resource *parent, resource_size_t start,
 			       size_t size, unsigned long flags,
 			       unsigned long desc)
 {
-	resource_size_t ostart, oend;
 	int type = 0; int other = 0;
 	struct resource *p, *dp;
+	struct resource res, o;
 	bool is_type, covered;
-	struct resource res;
 
 	res.start = start;
 	res.end = start + size - 1;
 
 	for (p = parent->child; p ; p = p->sibling) {
-		if (!resource_overlaps(p, &res))
+		if (!resource_intersection(p, &res, &o))
 			continue;
 		is_type = (p->flags & flags) == flags &&
 			(desc == IORES_DESC_NONE || desc == p->desc);
@@ -568,8 +567,6 @@ static int __region_intersects(struct resource *parent, resource_size_t start,
 		 * |-- "System RAM" --||-- "CXL Window 0a" --|
 		 */
 		covered = false;
-		ostart = max(res.start, p->start);
-		oend = min(res.end, p->end);
 		for_each_resource(p, dp, false) {
 			if (!resource_overlaps(dp, &res))
 				continue;
@@ -578,17 +575,17 @@ static int __region_intersects(struct resource *parent, resource_size_t start,
 			if (is_type) {
 				type++;
 				/*
-				 * Range from 'ostart' to 'dp->start'
+				 * Range from 'o.start' to 'dp->start'
 				 * isn't covered by matched resource.
 				 */
-				if (dp->start > ostart)
+				if (dp->start > o.start)
 					break;
-				if (dp->end >= oend) {
+				if (dp->end >= o.end) {
 					covered = true;
 					break;
 				}
 				/* Remove covered range */
-				ostart = max(ostart, dp->end + 1);
+				o.start = max(o.start, dp->end + 1);
 			}
 		}
 		if (!covered)

From ba1eccc114ffc62c4495a5e15659190fa2c42308 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 25 Sep 2024 18:43:35 +0300
Subject: [PATCH 0871/1530] resource: introduce is_type_match() helper and use
 it

There are already a couple of places where we may replace a few lines of
code by calling a helper, which increases readability while deduplicating
the code.

Introduce is_type_match() helper and use it.

Link: https://lkml.kernel.org/r/20240925154355.1170859-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/resource.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/kernel/resource.c b/kernel/resource.c
index 1c77ac239c7a4..55bc09f50e211 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -297,6 +297,11 @@ int release_resource(struct resource *old)
 
 EXPORT_SYMBOL(release_resource);
 
+static bool is_type_match(struct resource *p, unsigned long flags, unsigned long desc)
+{
+	return (p->flags & flags) == flags && (desc == IORES_DESC_NONE || desc == p->desc);
+}
+
 /**
  * find_next_iomem_res - Finds the lowest iomem resource that covers part of
  *			 [@start..@end].
@@ -339,13 +344,9 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end,
 		if (p->end < start)
 			continue;
 
-		if ((p->flags & flags) != flags)
-			continue;
-		if ((desc != IORES_DESC_NONE) && (desc != p->desc))
-			continue;
-
 		/* Found a match, break */
-		break;
+		if (is_type_match(p, flags, desc))
+			break;
 	}
 
 	if (p) {
@@ -540,7 +541,7 @@ static int __region_intersects(struct resource *parent, resource_size_t start,
 	int type = 0; int other = 0;
 	struct resource *p, *dp;
 	struct resource res, o;
-	bool is_type, covered;
+	bool covered;
 
 	res.start = start;
 	res.end = start + size - 1;
@@ -548,9 +549,7 @@ static int __region_intersects(struct resource *parent, resource_size_t start,
 	for (p = parent->child; p ; p = p->sibling) {
 		if (!resource_intersection(p, &res, &o))
 			continue;
-		is_type = (p->flags & flags) == flags &&
-			(desc == IORES_DESC_NONE || desc == p->desc);
-		if (is_type) {
+		if (is_type_match(p, flags, desc)) {
 			type++;
 			continue;
 		}
@@ -570,9 +569,7 @@ static int __region_intersects(struct resource *parent, resource_size_t start,
 		for_each_resource(p, dp, false) {
 			if (!resource_overlaps(dp, &res))
 				continue;
-			is_type = (dp->flags & flags) == flags &&
-				(desc == IORES_DESC_NONE || desc == dp->desc);
-			if (is_type) {
+			if (is_type_match(dp, flags, desc)) {
 				type++;
 				/*
 				 * Range from 'o.start' to 'dp->start'

From 9357bf5e66660cf56da44905ff2b158056bc6087 Mon Sep 17 00:00:00 2001
From: Yu Jiaoliang <yujiaoliang@vivo.com>
Date: Thu, 26 Sep 2024 18:16:15 +0800
Subject: [PATCH 0872/1530] scripts/spelling.txt: add more spellings
 corrections

Add several common typo patterns to the scripts/spelling.txt file to
ensure checkpatch.pl can detect and prevent these typos in the future.

This update helps improve code quality by preventing recurring typos.

Link: https://lkml.kernel.org/r/20240926101617.3988613-1-yujiaoliang@vivo.com
Signed-off-by: Yu Jiaoliang <yujiaoliang@vivo.com>
Signed-off-by: Shen Lichuan <shenlichuan@vivo.com>
Signed-off-by: Yan Zhen <yanzhen@vivo.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 scripts/spelling.txt | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/scripts/spelling.txt b/scripts/spelling.txt
index 554329a074ce9..fe25bf3b605a6 100644
--- a/scripts/spelling.txt
+++ b/scripts/spelling.txt
@@ -141,6 +141,7 @@ anomoly||anomaly
 anonynous||anonymous
 anway||anyway
 aplication||application
+apeared||appeared
 appearence||appearance
 applicaion||application
 appliction||application
@@ -155,6 +156,7 @@ apropriate||appropriate
 aquainted||acquainted
 aquired||acquired
 aquisition||acquisition
+aquires||acquires
 arbitary||arbitrary
 architechture||architecture
 archtecture||architecture
@@ -185,10 +187,12 @@ assotiated||associated
 asssert||assert
 assum||assume
 assumtpion||assumption
+asume||assume
 asuming||assuming
 asycronous||asynchronous
 asychronous||asynchronous
 asynchnous||asynchronous
+asynchrnous||asynchronous
 asynchronus||asynchronous
 asynchromous||asynchronous
 asymetric||asymmetric
@@ -269,6 +273,7 @@ caculate||calculate
 caculation||calculation
 cadidate||candidate
 cahces||caches
+calcluate||calculate
 calender||calendar
 calescing||coalescing
 calibraiton||calibration
@@ -331,6 +336,7 @@ chouse||chose
 circumvernt||circumvent
 claread||cleared
 clared||cleared
+clearify||clarify
 closeing||closing
 clustred||clustered
 cnfiguration||configuration
@@ -379,12 +385,14 @@ comsumed||consumed
 comunicate||communicate
 comunication||communication
 conbination||combination
+concurent||concurrent
 conditionaly||conditionally
 conditon||condition
 condtion||condition
 condtional||conditional
 conected||connected
 conector||connector
+configed||configured
 configration||configuration
 configred||configured
 configuartion||configuration
@@ -394,6 +402,7 @@ configuratoin||configuration
 configuraton||configuration
 configuretion||configuration
 configutation||configuration
+congiuration||configuration
 conider||consider
 conjuction||conjunction
 connecetd||connected
@@ -403,6 +412,7 @@ connnection||connection
 connnections||connections
 consistancy||consistency
 consistant||consistent
+consits||consists
 containes||contains
 containts||contains
 contaisn||contains
@@ -452,6 +462,7 @@ decendants||descendants
 decompres||decompress
 decsribed||described
 decription||description
+detault||default
 dectected||detected
 defailt||default
 deferal||deferral
@@ -487,6 +498,7 @@ depreacte||deprecate
 desactivate||deactivate
 desciptor||descriptor
 desciptors||descriptors
+descritpor||descriptor
 descripto||descriptor
 descripton||description
 descrition||description
@@ -601,6 +613,7 @@ enchanced||enhanced
 encorporating||incorporating
 encrupted||encrypted
 encrypiton||encryption
+encryped||encrypted
 encryptio||encryption
 endianess||endianness
 enpoint||endpoint
@@ -630,6 +643,7 @@ etsbalishment||establishment
 evalute||evaluate
 evalutes||evaluates
 evalution||evaluation
+evaulated||evaluated
 excecutable||executable
 excceed||exceed
 exceded||exceeded
@@ -650,6 +664,7 @@ exlcude||exclude
 exlcuding||excluding
 exlcusive||exclusive
 exlusive||exclusive
+exlicitly||explicitly
 exmaple||example
 expecially||especially
 experies||expires
@@ -834,6 +849,7 @@ informations||information
 informtion||information
 infromation||information
 ingore||ignore
+inheritence||inheritance
 inital||initial
 initalized||initialized
 initalised||initialized
@@ -878,6 +894,7 @@ interoprability||interoperability
 interuupt||interrupt
 interupt||interrupt
 interupts||interrupts
+interurpt||interrupt
 interrface||interface
 interrrupt||interrupt
 interrup||interrupt
@@ -925,6 +942,7 @@ jumpimng||jumping
 juse||just
 jus||just
 kown||known
+lable||label
 langage||language
 langauage||language
 langauge||language
@@ -995,6 +1013,7 @@ metdata||metadata
 micropone||microphone
 microprocesspr||microprocessor
 migrateable||migratable
+miliseconds||milliseconds
 millenium||millennium
 milliseonds||milliseconds
 minimim||minimum
@@ -1132,6 +1151,7 @@ palne||plane
 paramameters||parameters
 paramaters||parameters
 paramater||parameter
+paramenters||parameters
 parametes||parameters
 parametised||parametrised
 paramter||parameter
@@ -1177,9 +1197,11 @@ poiter||pointer
 posible||possible
 positon||position
 possibilites||possibilities
+postion||position
 potocol||protocol
 powerfull||powerful
 pramater||parameter
+preambule||preamble
 preamle||preamble
 preample||preamble
 preapre||prepare
@@ -1269,6 +1291,7 @@ raoming||roaming
 reasearcher||researcher
 reasearchers||researchers
 reasearch||research
+recalcualte||recalculate
 receieve||receive
 recepient||recipient
 recevied||received
@@ -1291,6 +1314,7 @@ refcounf||refcount
 refence||reference
 refered||referred
 referenace||reference
+refererence||reference
 refering||referring
 refernces||references
 refernnce||reference
@@ -1315,12 +1339,14 @@ reloade||reload
 remoote||remote
 remore||remote
 removeable||removable
+repective||respective
 repectively||respectively
 replacable||replaceable
 replacments||replacements
 replys||replies
 reponse||response
 representaion||representation
+repsonse||response
 reqeust||request
 reqister||register
 requed||requeued
@@ -1444,6 +1470,7 @@ soluation||solution
 souce||source
 speach||speech
 specfic||specific
+specfication||specification
 specfield||specified
 speciefied||specified
 specifc||specific
@@ -1544,6 +1571,7 @@ syncronus||synchronous
 syste||system
 sytem||system
 sythesis||synthesis
+tagert||target
 taht||that
 tained||tainted
 tarffic||traffic
@@ -1574,6 +1602,7 @@ tiggers||triggers
 tiggered||triggered
 tipically||typically
 timeing||timing
+timming||timing
 timout||timeout
 tmis||this
 toogle||toggle
@@ -1597,8 +1626,10 @@ transision||transition
 transistioned||transitioned
 transmittd||transmitted
 transormed||transformed
+trasaction||transaction
 trasfer||transfer
 trasmission||transmission
+trasmitter||transmitter
 treshold||threshold
 triggerd||triggered
 trigerred||triggered

From f9a4d8930f272fd76edc1f76062b5ca316bda25d Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Mon, 30 Sep 2024 21:58:22 +0200
Subject: [PATCH 0873/1530] ipc/msg: replace one-element array with flexible
 array member

Replace the deprecated one-element array with a modern flexible array
member in the struct compat_msgbuf.

There are no binary differences after this conversion.

Link: https://github.com/KSPP/linux/issues/79
Link: https://lkml.kernel.org/r/20240930195824.153648-2-thorsten.blum@linux.dev
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Cc: "Sun, Jiebin" <jiebin.sun@intel.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 ipc/msg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ipc/msg.c b/ipc/msg.c
index fd08b3cb36d79..ee6af4fe52bff 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -978,7 +978,7 @@ SYSCALL_DEFINE4(msgsnd, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
 
 struct compat_msgbuf {
 	compat_long_t mtype;
-	char mtext[1];
+	char mtext[];
 };
 
 long compat_ksys_msgsnd(int msqid, compat_uptr_t msgp,

From 4cc0473d7754d387680bdf0728eb29f0ec8834bf Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Mon, 7 Oct 2024 22:49:05 +0800
Subject: [PATCH 0874/1530] get rid of __get_task_comm()

Patch series "Improve the copy of task comm", v8.

Using {memcpy,strncpy,strcpy,kstrdup} to copy the task comm relies on the
length of task comm.  Changes in the task comm could result in a
destination string that is overflow.  Therefore, we should explicitly
ensure the destination string is always NUL-terminated, regardless of the
task comm.  This approach will facilitate future extensions to the task
comm.

As suggested by Linus [0], we can identify all relevant code with the
following git grep command:

  git grep 'memcpy.*->comm\>'
  git grep 'kstrdup.*->comm\>'
  git grep 'strncpy.*->comm\>'
  git grep 'strcpy.*->comm\>'

PATCH #2~#4:   memcpy
PATCH #5~#6:   kstrdup
PATCH #7:      strcpy

Please note that strncpy() is not included in this series as it is being
tracked by another effort. [1]


This patch (of 7):

We want to eliminate the use of __get_task_comm() for the following
reasons:

- The task_lock() is unnecessary
  Quoted from Linus [0]:
  : Since user space can randomly change their names anyway, using locking
  : was always wrong for readers (for writers it probably does make sense
  : to have some lock - although practically speaking nobody cares there
  : either, but at least for a writer some kind of race could have
  : long-term mixed results

Link: https://lkml.kernel.org/r/20241007144911.27693-1-laoar.shao@gmail.com
Link: https://lkml.kernel.org/r/20241007144911.27693-2-laoar.shao@gmail.com
Link: https://lore.kernel.org/all/CAHk-=wivfrF0_zvf+oj6==Sh=-npJooP8chLPEfaFV0oNYTTBA@mail.gmail.com [0]
Link: https://lore.kernel.org/all/CAHk-=whWtUC-AjmGJveAETKOMeMFSTwKwu99v7+b6AyHMmaDFA@mail.gmail.com/
Link: https://lore.kernel.org/all/CAHk-=wjAmmHUg6vho1KjzQi2=psR30+CogFd4aXrThr2gsiS4g@mail.gmail.com/ [0]
Link: https://github.com/KSPP/linux/issues/90 [1]
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Matus Jokay <matus.jokay@stuba.sk>
Cc: Alejandro Colomar <alx@kernel.org>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Airlie <airlied@gmail.com>
Cc: Eric Paris <eparis@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Ondrej Mosnacek <omosnace@redhat.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: Simon Horman <horms@kernel.org>
Cc: Stephen Smalley <stephen.smalley.work@gmail.com>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/exec.c             | 10 ----------
 fs/proc/array.c       |  2 +-
 include/linux/sched.h | 28 ++++++++++++++++++++++------
 kernel/kthread.c      |  2 +-
 4 files changed, 24 insertions(+), 18 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index 6c53920795c2e..77364806b48db 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1189,16 +1189,6 @@ static int unshare_sighand(struct task_struct *me)
 	return 0;
 }
 
-char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk)
-{
-	task_lock(tsk);
-	/* Always NUL terminated and zero-padded */
-	strscpy_pad(buf, tsk->comm, buf_size);
-	task_unlock(tsk);
-	return buf;
-}
-EXPORT_SYMBOL_GPL(__get_task_comm);
-
 /*
  * These functions flushes out all traces of the currently running executable
  * so that a new one can be started
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 34a47fb0c57f2..55ed3510d2bbb 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -109,7 +109,7 @@ void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape)
 	else if (p->flags & PF_KTHREAD)
 		get_kthread_comm(tcomm, sizeof(tcomm), p);
 	else
-		__get_task_comm(tcomm, sizeof(tcomm), p);
+		get_task_comm(tcomm, p);
 
 	if (escape)
 		seq_escape_str(m, tcomm, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
diff --git a/include/linux/sched.h b/include/linux/sched.h
index bb343136ddd05..67718d5591ddd 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1121,9 +1121,12 @@ struct task_struct {
 	/*
 	 * executable name, excluding path.
 	 *
-	 * - normally initialized setup_new_exec()
-	 * - access it with [gs]et_task_comm()
-	 * - lock it with task_lock()
+	 * - normally initialized begin_new_exec()
+	 * - set it with set_task_comm()
+	 *   - strscpy_pad() to ensure it is always NUL-terminated and
+	 *     zero-padded
+	 *   - task_lock() to ensure the operation is atomic and the name is
+	 *     fully updated.
 	 */
 	char				comm[TASK_COMM_LEN];
 
@@ -1938,10 +1941,23 @@ static inline void set_task_comm(struct task_struct *tsk, const char *from)
 	__set_task_comm(tsk, from, false);
 }
 
-extern char *__get_task_comm(char *to, size_t len, struct task_struct *tsk);
+/*
+ * - Why not use task_lock()?
+ *   User space can randomly change their names anyway, so locking for readers
+ *   doesn't make sense. For writers, locking is probably necessary, as a race
+ *   condition could lead to long-term mixed results.
+ *   The strscpy_pad() in __set_task_comm() can ensure that the task comm is
+ *   always NUL-terminated and zero-padded. Therefore the race condition between
+ *   reader and writer is not an issue.
+ *
+ * - BUILD_BUG_ON() can help prevent the buf from being truncated.
+ *   Since the callers don't perform any return value checks, this safeguard is
+ *   necessary.
+ */
 #define get_task_comm(buf, tsk) ({			\
-	BUILD_BUG_ON(sizeof(buf) != TASK_COMM_LEN);	\
-	__get_task_comm(buf, sizeof(buf), tsk);		\
+	BUILD_BUG_ON(sizeof(buf) < TASK_COMM_LEN);	\
+	strscpy_pad(buf, (tsk)->comm);			\
+	buf;						\
 })
 
 #ifdef CONFIG_SMP
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 9bb36897b6c62..a5ac612b16092 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -101,7 +101,7 @@ void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk)
 	struct kthread *kthread = to_kthread(tsk);
 
 	if (!kthread || !kthread->full_name) {
-		__get_task_comm(buf, buf_size, tsk);
+		strscpy(buf, tsk->comm, buf_size);
 		return;
 	}
 

From 286d7a54c8a2f124337a91235199585a35822d94 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Mon, 7 Oct 2024 22:49:06 +0800
Subject: [PATCH 0875/1530] auditsc: replace memcpy() with strscpy()

Using strscpy() to read the task comm ensures that the name is always
NUL-terminated, regardless of the source string.  This approach also
facilitates future extensions to the task comm.

Link: https://lkml.kernel.org/r/20241007144911.27693-3-laoar.shao@gmail.com
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Reviewed-by: Justin Stitt <justinstitt@google.com>
Cc: Eric Paris <eparis@redhat.com>
Cc: Alejandro Colomar <alx@kernel.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Airlie <airlied@gmail.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: James Morris <jmorris@namei.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Matus Jokay <matus.jokay@stuba.sk>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Ondrej Mosnacek <omosnace@redhat.com>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Simon Horman <horms@kernel.org>
Cc: Stephen Smalley <stephen.smalley.work@gmail.com>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/auditsc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index cd57053b4a699..7adc67d5aafb0 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2730,7 +2730,7 @@ void __audit_ptrace(struct task_struct *t)
 	context->target_uid = task_uid(t);
 	context->target_sessionid = audit_get_sessionid(t);
 	security_task_getsecid_obj(t, &context->target_sid);
-	memcpy(context->target_comm, t->comm, TASK_COMM_LEN);
+	strscpy(context->target_comm, t->comm);
 }
 
 /**
@@ -2757,7 +2757,7 @@ int audit_signal_info_syscall(struct task_struct *t)
 		ctx->target_uid = t_uid;
 		ctx->target_sessionid = audit_get_sessionid(t);
 		security_task_getsecid_obj(t, &ctx->target_sid);
-		memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN);
+		strscpy(ctx->target_comm, t->comm);
 		return 0;
 	}
 
@@ -2778,7 +2778,7 @@ int audit_signal_info_syscall(struct task_struct *t)
 	axp->target_uid[axp->pid_count] = t_uid;
 	axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t);
 	security_task_getsecid_obj(t, &axp->target_sid[axp->pid_count]);
-	memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN);
+	strscpy(axp->target_comm[axp->pid_count], t->comm);
 	axp->pid_count++;
 
 	return 0;

From d4ee4ac395eec1e64f696dbea1de82e90b17127d Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Mon, 7 Oct 2024 22:49:07 +0800
Subject: [PATCH 0876/1530] security: replace memcpy() with get_task_comm()

Quoted from Linus [0]:

  selinux never wanted a lock, and never wanted any kind of *consistent*
  result, it just wanted a *stable* result.

Using get_task_comm() to read the task comm ensures that the name is
always NUL-terminated, regardless of the source string. This approach also
facilitates future extensions to the task comm.

Link: https://lkml.kernel.org/r/20241007144911.27693-4-laoar.shao@gmail.com
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Link: https://lore.kernel.org/all/CAHk-=wivfrF0_zvf+oj6==Sh=-npJooP8chLPEfaFV0oNYTTBA@mail.gmail.com/ [0]
Acked-by: Paul Moore <paul@paul-moore.com>
Cc: James Morris <jmorris@namei.org>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Stephen Smalley <stephen.smalley.work@gmail.com>
Cc: Ondrej Mosnacek <omosnace@redhat.com>
Cc: Alejandro Colomar <alx@kernel.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Airlie <airlied@gmail.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Eric Paris <eparis@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Matus Jokay <matus.jokay@stuba.sk>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: Simon Horman <horms@kernel.org>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 security/lsm_audit.c         | 4 ++--
 security/selinux/selinuxfs.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 849e832719e21..9a8352972086c 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -207,7 +207,7 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 	BUILD_BUG_ON(sizeof(a->u) > sizeof(void *)*2);
 
 	audit_log_format(ab, " pid=%d comm=", task_tgid_nr(current));
-	audit_log_untrustedstring(ab, memcpy(comm, current->comm, sizeof(comm)));
+	audit_log_untrustedstring(ab, get_task_comm(comm, current));
 
 	switch (a->type) {
 	case LSM_AUDIT_DATA_NONE:
@@ -302,7 +302,7 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 				char comm[sizeof(tsk->comm)];
 				audit_log_format(ab, " opid=%d ocomm=", pid);
 				audit_log_untrustedstring(ab,
-				    memcpy(comm, tsk->comm, sizeof(comm)));
+				    get_task_comm(comm, tsk));
 			}
 		}
 		break;
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index e172f182b65cc..c9b05be27ddbe 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -708,7 +708,7 @@ static ssize_t sel_write_checkreqprot(struct file *file, const char __user *buf,
 	if (new_value) {
 		char comm[sizeof(current->comm)];
 
-		memcpy(comm, current->comm, sizeof(comm));
+		strscpy(comm, current->comm);
 		pr_err("SELinux: %s (%d) set checkreqprot to 1. This is no longer supported.\n",
 		       comm, current->pid);
 	}

From d967757d288182522ca263a3d4472101d15a2bfb Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Mon, 7 Oct 2024 22:49:08 +0800
Subject: [PATCH 0877/1530] bpftool: ensure task comm is always NUL-terminated

Let's explicitly ensure the destination string is NUL-terminated.  This
way, it won't be affected by changes to the source string.

Link: https://lkml.kernel.org/r/20241007144911.27693-5-laoar.shao@gmail.com
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Reviewed-by: Quentin Monnet <qmo@kernel.org>
Cc: Alejandro Colomar <alx@kernel.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Airlie <airlied@gmail.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Eric Paris <eparis@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Matus Jokay <matus.jokay@stuba.sk>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Ondrej Mosnacek <omosnace@redhat.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Simon Horman <horms@kernel.org>
Cc: Stephen Smalley <stephen.smalley.work@gmail.com>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/bpf/bpftool/pids.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c
index 9b898571b49e9..23f488cf17403 100644
--- a/tools/bpf/bpftool/pids.c
+++ b/tools/bpf/bpftool/pids.c
@@ -54,6 +54,7 @@ static void add_ref(struct hashmap *map, struct pid_iter_entry *e)
 		ref = &refs->refs[refs->ref_cnt];
 		ref->pid = e->pid;
 		memcpy(ref->comm, e->comm, sizeof(ref->comm));
+		ref->comm[sizeof(ref->comm) - 1] = '\0';
 		refs->ref_cnt++;
 
 		return;
@@ -77,6 +78,7 @@ static void add_ref(struct hashmap *map, struct pid_iter_entry *e)
 	ref = &refs->refs[0];
 	ref->pid = e->pid;
 	memcpy(ref->comm, e->comm, sizeof(ref->comm));
+	ref->comm[sizeof(ref->comm) - 1] = '\0';
 	refs->ref_cnt = 1;
 	refs->has_bpf_cookie = e->has_bpf_cookie;
 	refs->bpf_cookie = e->bpf_cookie;

From 44ff630170edd89dcdca8a2552b1317fdcc65e51 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Mon, 7 Oct 2024 22:49:09 +0800
Subject: [PATCH 0878/1530] mm/util: fix possible race condition in kstrdup()

In kstrdup(), it is critical to ensure that the dest string is always
NUL-terminated.  However, potential race condition can occur between a
writer and a reader.

Consider the following scenario involving task->comm:

    reader                    writer

  len = strlen(s) + 1;
                             strlcpy(tsk->comm, buf, sizeof(tsk->comm));
  memcpy(buf, s, len);

In this case, there is a race condition between the reader and the writer.
The reader calculates the length of the string `s` based on the old value
of task->comm.  However, during the memcpy(), the string `s` might be
updated by the writer to a new value of task->comm.

If the new task->comm is larger than the old one, the `buf` might not be
NUL-terminated.  This can lead to undefined behavior and potential
security vulnerabilities.

Let's fix it by explicitly adding a NUL terminator after the memcpy.  It
is worth noting that memcpy() is not atomic, so the new string can be
shorter when memcpy() already copied past the new NUL.

Link: https://lkml.kernel.org/r/20241007144911.27693-6-laoar.shao@gmail.com
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Cc: Alejandro Colomar <alx@kernel.org>
Cc: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Airlie <airlied@gmail.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Eric Paris <eparis@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Matus Jokay <matus.jokay@stuba.sk>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Ondrej Mosnacek <omosnace@redhat.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Simon Horman <horms@kernel.org>
Cc: Stephen Smalley <stephen.smalley.work@gmail.com>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/util.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/mm/util.c b/mm/util.c
index 4f1275023eb73..858a9a2f57e7c 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -62,8 +62,15 @@ char *kstrdup(const char *s, gfp_t gfp)
 
 	len = strlen(s) + 1;
 	buf = kmalloc_track_caller(len, gfp);
-	if (buf)
+	if (buf) {
 		memcpy(buf, s, len);
+		/*
+		 * During memcpy(), the string might be updated to a new value,
+		 * which could be longer than the string when strlen() is
+		 * called. Therefore, we need to add a NUL terminator.
+		 */
+		buf[len - 1] = '\0';
+	}
 	return buf;
 }
 EXPORT_SYMBOL(kstrdup);

From 43731516facc3257b514e5c45ae80664b28d3ca3 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Mon, 7 Oct 2024 22:49:10 +0800
Subject: [PATCH 0879/1530] mm/util: deduplicate code in
 {kstrdup,kstrndup,kmemdup_nul}

These three functions follow the same pattern.  To deduplicate the code,
let's introduce a common helper __kmemdup_nul().

Link: https://lkml.kernel.org/r/20241007144911.27693-7-laoar.shao@gmail.com
Suggested-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Cc: Simon Horman <horms@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Alejandro Colomar <alx@kernel.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Airlie <airlied@gmail.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Eric Paris <eparis@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matus Jokay <matus.jokay@stuba.sk>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Ondrej Mosnacek <omosnace@redhat.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Stephen Smalley <stephen.smalley.work@gmail.com>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/util.c | 69 ++++++++++++++++++++++---------------------------------
 1 file changed, 27 insertions(+), 42 deletions(-)

diff --git a/mm/util.c b/mm/util.c
index 858a9a2f57e7c..c7d851c40843d 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -45,34 +45,41 @@ void kfree_const(const void *x)
 EXPORT_SYMBOL(kfree_const);
 
 /**
- * kstrdup - allocate space for and copy an existing string
- * @s: the string to duplicate
+ * __kmemdup_nul - Create a NUL-terminated string from @s, which might be unterminated.
+ * @s: The data to copy
+ * @len: The size of the data, not including the NUL terminator
  * @gfp: the GFP mask used in the kmalloc() call when allocating memory
  *
- * Return: newly allocated copy of @s or %NULL in case of error
+ * Return: newly allocated copy of @s with NUL-termination or %NULL in
+ * case of error
  */
-noinline
-char *kstrdup(const char *s, gfp_t gfp)
+static __always_inline char *__kmemdup_nul(const char *s, size_t len, gfp_t gfp)
 {
-	size_t len;
 	char *buf;
 
-	if (!s)
+	/* '+1' for the NUL terminator */
+	buf = kmalloc_track_caller(len + 1, gfp);
+	if (!buf)
 		return NULL;
 
-	len = strlen(s) + 1;
-	buf = kmalloc_track_caller(len, gfp);
-	if (buf) {
-		memcpy(buf, s, len);
-		/*
-		 * During memcpy(), the string might be updated to a new value,
-		 * which could be longer than the string when strlen() is
-		 * called. Therefore, we need to add a NUL terminator.
-		 */
-		buf[len - 1] = '\0';
-	}
+	memcpy(buf, s, len);
+	/* Ensure the buf is always NUL-terminated, regardless of @s. */
+	buf[len] = '\0';
 	return buf;
 }
+
+/**
+ * kstrdup - allocate space for and copy an existing string
+ * @s: the string to duplicate
+ * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ *
+ * Return: newly allocated copy of @s or %NULL in case of error
+ */
+noinline
+char *kstrdup(const char *s, gfp_t gfp)
+{
+	return s ? __kmemdup_nul(s, strlen(s), gfp) : NULL;
+}
 EXPORT_SYMBOL(kstrdup);
 
 /**
@@ -107,19 +114,7 @@ EXPORT_SYMBOL(kstrdup_const);
  */
 char *kstrndup(const char *s, size_t max, gfp_t gfp)
 {
-	size_t len;
-	char *buf;
-
-	if (!s)
-		return NULL;
-
-	len = strnlen(s, max);
-	buf = kmalloc_track_caller(len+1, gfp);
-	if (buf) {
-		memcpy(buf, s, len);
-		buf[len] = '\0';
-	}
-	return buf;
+	return s ? __kmemdup_nul(s, strnlen(s, max), gfp) : NULL;
 }
 EXPORT_SYMBOL(kstrndup);
 
@@ -193,17 +188,7 @@ EXPORT_SYMBOL(kvmemdup);
  */
 char *kmemdup_nul(const char *s, size_t len, gfp_t gfp)
 {
-	char *buf;
-
-	if (!s)
-		return NULL;
-
-	buf = kmalloc_track_caller(len + 1, gfp);
-	if (buf) {
-		memcpy(buf, s, len);
-		buf[len] = '\0';
-	}
-	return buf;
+	return s ? __kmemdup_nul(s, len, gfp) : NULL;
 }
 EXPORT_SYMBOL(kmemdup_nul);
 

From 3240aadaccc15d781d1669965ccad230a8c4a175 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Mon, 7 Oct 2024 22:49:11 +0800
Subject: [PATCH 0880/1530] drm: replace strcpy() with strscpy()

To prevent errors from occurring when the src string is longer than the
dst string in strcpy(), we should use strscpy() instead.  This approach
also facilitates future extensions to the task comm.

Link: https://lkml.kernel.org/r/20241007144911.27693-8-laoar.shao@gmail.com
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Suggested-by: Justin Stitt <justinstitt@google.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Justin Stitt <justinstitt@google.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: David Airlie <airlied@gmail.com>
Cc: Alejandro Colomar <alx@kernel.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Eric Paris <eparis@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Matus Jokay <matus.jokay@stuba.sk>
Cc: Ondrej Mosnacek <omosnace@redhat.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Simon Horman <horms@kernel.org>
Cc: Stephen Smalley <stephen.smalley.work@gmail.com>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/gpu/drm/drm_framebuffer.c     | 2 +-
 drivers/gpu/drm/i915/i915_gpu_error.c | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c
index 888aadb6a4acb..2d6993539474f 100644
--- a/drivers/gpu/drm/drm_framebuffer.c
+++ b/drivers/gpu/drm/drm_framebuffer.c
@@ -868,7 +868,7 @@ int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb,
 	INIT_LIST_HEAD(&fb->filp_head);
 
 	fb->funcs = funcs;
-	strcpy(fb->comm, current->comm);
+	strscpy(fb->comm, current->comm);
 
 	ret = __drm_mode_object_add(dev, &fb->base, DRM_MODE_OBJECT_FB,
 				    false, drm_framebuffer_free);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 6469b9bcf2ec4..9d4b25b2cd394 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1113,7 +1113,7 @@ i915_vma_coredump_create(const struct intel_gt *gt,
 	}
 
 	INIT_LIST_HEAD(&dst->page_list);
-	strcpy(dst->name, name);
+	strscpy(dst->name, name);
 	dst->next = NULL;
 
 	dst->gtt_offset = vma_res->start;
@@ -1413,7 +1413,7 @@ static bool record_context(struct i915_gem_context_coredump *e,
 	rcu_read_lock();
 	task = pid_task(ctx->pid, PIDTYPE_PID);
 	if (task) {
-		strcpy(e->comm, task->comm);
+		strscpy(e->comm, task->comm);
 		e->pid = task->pid;
 	}
 	rcu_read_unlock();
@@ -1459,7 +1459,7 @@ capture_vma_snapshot(struct intel_engine_capture_vma *next,
 		return next;
 	}
 
-	strcpy(c->name, name);
+	strscpy(c->name, name);
 	c->vma_res = i915_vma_resource_get(vma_res);
 
 	c->next = next;

From b42166427b46af0d963242283fc99d429623d303 Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 6 Oct 2024 06:22:21 +0800
Subject: [PATCH 0881/1530] lib/Kconfig.debug: move int_pow test option to
 runtime testing section

When executing 'make menuconfig' with KUNIT enabled, the int_pow test
option appears on the first page of the main menu instead of under the
runtime testing section.  Relocate the int_pow test configuration to the
appropriate runtime testing submenu, ensuring a more organized and logical
structure in the menu configuration.

Link: https://lkml.kernel.org/r/20241005222221.2154393-1-visitorckw@gmail.com
Fixes: 7fcc9b53216c ("lib/math: Add int_pow test suite")
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: David Gow <davidgow@google.com>
Cc: Luis Felipe Hernandez <luis.hernandez093@gmail.com>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/Kconfig.debug | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 7312ae7c3cc57..409dd193c09b4 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2993,6 +2993,22 @@ config TEST_OBJPOOL
 
 	  If unsure, say N.
 
+config INT_POW_TEST
+	tristate "Integer exponentiation (int_pow) test" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  This option enables the KUnit test suite for the int_pow function,
+	  which performs integer exponentiation. The test suite is designed to
+	  verify that the implementation of int_pow correctly computes the power
+	  of a given base raised to a given exponent.
+
+	  Enabling this option will include tests that check various scenarios
+	  and edge cases to ensure the accuracy and reliability of the exponentiation
+	  function.
+
+	  If unsure, say N
+
 endif # RUNTIME_TESTING_MENU
 
 config ARCH_USE_MEMTEST
@@ -3088,19 +3104,3 @@ config RUST_KERNEL_DOCTESTS
 endmenu # "Rust"
 
 endmenu # Kernel hacking
-
-config INT_POW_TEST
-	tristate "Integer exponentiation (int_pow) test" if !KUNIT_ALL_TESTS
-	depends on KUNIT
-	default KUNIT_ALL_TESTS
-	help
-	  This option enables the KUnit test suite for the int_pow function,
-	  which performs integer exponentiation. The test suite is designed to
-	  verify that the implementation of int_pow correctly computes the power
-	  of a given base raised to a given exponent.
-
-	  Enabling this option will include tests that check various scenarios
-	  and edge cases to ensure the accuracy and reliability of the exponentiation
-	  function.
-
-	  If unsure, say N

From 5a3c9366cbbf876521f570ce1fb525dc2cb0ed5c Mon Sep 17 00:00:00 2001
From: I Hsin Cheng <richard120310@gmail.com>
Date: Tue, 8 Oct 2024 14:52:53 +0800
Subject: [PATCH 0882/1530] list: test: check the size of every lists for
 list_cut_position*()

Check the total number of elements in both resultant lists are correct
within list_cut_position*().  Previously, only the first list's size was
checked.  so additional elements in the second list would not have been
caught.

Link: https://lkml.kernel.org/r/20241008065253.26673-1-richard120310@gmail.com
Signed-off-by: I Hsin Cheng <richard120310@gmail.com>
Cc: David Gow <davidgow@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/list-test.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/lib/list-test.c b/lib/list-test.c
index e207c4c98d702..9135cdc1bb39f 100644
--- a/lib/list-test.c
+++ b/lib/list-test.c
@@ -412,6 +412,8 @@ static void list_test_list_cut_position(struct kunit *test)
 		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
 		i++;
 	}
+
+	KUNIT_EXPECT_EQ(test, i, 3);
 }
 
 static void list_test_list_cut_before(struct kunit *test)
@@ -440,6 +442,8 @@ static void list_test_list_cut_before(struct kunit *test)
 		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
 		i++;
 	}
+
+	KUNIT_EXPECT_EQ(test, i, 3);
 }
 
 static void list_test_list_splice(struct kunit *test)

From 834b251b1db6b88b9364955196e5e32746e5ccc7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Wed, 9 Oct 2024 15:57:51 +0300
Subject: [PATCH 0883/1530] resource: correct reallocate_resource()
 documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

reallocate_resource() documentation claims constraint is about "the size
and alignment" but the size is provided in another parameter.  Instead of
size, constraint has the allowed memory range (min, max) so change the
wording to reflect that.

Link: https://lkml.kernel.org/r/20241009125751.8090-1-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/resource.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/resource.c b/kernel/resource.c
index 55bc09f50e211..2d4208b2f62fa 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -738,7 +738,7 @@ EXPORT_SYMBOL_GPL(find_resource_space);
  * @root: root resource descriptor
  * @old:  resource descriptor desired by caller
  * @newsize: new size of the resource descriptor
- * @constraint: the size and alignment constraints to be met.
+ * @constraint: the memory range and alignment constraints to be met.
  */
 static int reallocate_resource(struct resource *root, struct resource *old,
 			       resource_size_t newsize,

From f2fa0fd4e7db8326a77618962714924b64f5f889 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 12 Oct 2024 19:52:53 +0200
Subject: [PATCH 0884/1530] reboot: move reboot_notifier_list to
 kernel/reboot.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All the functions related to the reboot notifier list are in
kernel/reboot.c.  Move the list itself, too.  As there are no direct users
anymore, make the declaration static.

Link: https://lkml.kernel.org/r/20241012-reboot_notifier_list-v1-1-6093bb9455ce@weissschuh.net
Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/notifier.h | 2 --
 kernel/notifier.c        | 8 --------
 kernel/reboot.c          | 7 +++++++
 3 files changed, 7 insertions(+), 10 deletions(-)

diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index 45702bdcbceb4..b42e647349688 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -237,7 +237,5 @@ static inline int notifier_to_errno(int ret)
 #define KBD_KEYSYM		0x0004 /* Keyboard keysym */
 #define KBD_POST_KEYSYM		0x0005 /* Called after keyboard keysym interpretation */
 
-extern struct blocking_notifier_head reboot_notifier_list;
-
 #endif /* __KERNEL__ */
 #endif /* _LINUX_NOTIFIER_H */
diff --git a/kernel/notifier.c b/kernel/notifier.c
index b3ce28f39eb65..2f9fe7c30287f 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -5,18 +5,10 @@
 #include <linux/notifier.h>
 #include <linux/rcupdate.h>
 #include <linux/vmalloc.h>
-#include <linux/reboot.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/notifier.h>
 
-/*
- *	Notifier list for kernel code which wants to be called
- *	at shutdown. This is used to stop any idling DMA operations
- *	and the like.
- */
-BLOCKING_NOTIFIER_HEAD(reboot_notifier_list);
-
 /*
  *	Notifier chain core routines.  The exported routines below
  *	are layered on top of these, with appropriate locking added.
diff --git a/kernel/reboot.c b/kernel/reboot.c
index f05dbde2c93fe..ffdf86b717abc 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -72,6 +72,13 @@ static bool poweroff_fallback_to_halt;
  */
 void __weak (*pm_power_off)(void);
 
+/*
+ *	Notifier list for kernel code which wants to be called
+ *	at shutdown. This is used to stop any idling DMA operations
+ *	and the like.
+ */
+static BLOCKING_NOTIFIER_HEAD(reboot_notifier_list);
+
 /**
  *	emergency_restart - reboot the system
  *

From a9d38bcd7337f051912174ebfc500e1cef73982e Mon Sep 17 00:00:00 2001
From: Sui Jingfeng <sui.jingfeng@linux.dev>
Date: Sat, 12 Oct 2024 18:08:17 +0800
Subject: [PATCH 0885/1530] scatterlist: fix a typo

Replace the 'One' with 'On'.

Link: https://lkml.kernel.org/r/20241012100817.323007-1-sui.jingfeng@linux.dev
Fixes: af2880ec4402 ("scatterlist: add dedicated config for DMA flags")
Signed-off-by: Sui Jingfeng <sui.jingfeng@linux.dev>
Reviewed-by: Petr Tesarik <petr@tesarici.cz>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Michael Kelley <mhklinux@outlook.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/scatterlist.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index e61d164622db4..c5e2239b550ef 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -273,7 +273,7 @@ static inline void sg_unmark_end(struct scatterlist *sg)
 }
 
 /*
- * One 64-bit architectures there is a 4-byte padding in struct scatterlist
+ * On 64-bit architectures there is a 4-byte padding in struct scatterlist
  * (assuming also CONFIG_NEED_SG_DMA_LENGTH is set). Use this padding for DMA
  * flags bits to indicate when a specific dma address is a bus address or the
  * buffer may have been bounced via SWIOTLB.

From 5d042707089f0d0c49473d05250e4f319a71e1df Mon Sep 17 00:00:00 2001
From: Vinicius Peixoto <vpeixoto@lkcamp.dev>
Date: Sat, 12 Oct 2024 04:43:49 -0300
Subject: [PATCH 0886/1530] lib/crc16_kunit.c: add KUnit tests for crc16

Add Kunit tests for the kernel's implementation of the standard CRC-16
algorithm (<linux/crc16.h>).  The test data consists of 100
randomly-generated test cases, validated against a naive CRC-16
implementation.

This test follows roughly the same logic as lib/crc32test.c, but without
the performance measurements.

Link: https://lkml.kernel.org/r/20241012-crc16-kunit-v3-1-0ca75cb58ca9@lkcamp.dev
Signed-off-by: Vinicius Peixoto <vpeixoto@lkcamp.dev>
Co-developed-by: Enzo Bertoloti <ebertoloti@lkcamp.dev>
Signed-off-by: Enzo Bertoloti <ebertoloti@lkcamp.dev>
Co-developed-by: Fabricio Gasperin <fgasperin@lkcamp.dev>
Signed-off-by: Fabricio Gasperin <fgasperin@lkcamp.dev>
Suggested-by: David Laight <David.Laight@ACULAB.COM>
Cc: Brendan Higgins <brendan.higgins@linux.dev>
Cc: David Gow <davidgow@google.com>
Cc: Rae Moar <rmoar@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/Kconfig.debug |   9 +++
 lib/Makefile      |   1 +
 lib/crc16_kunit.c | 155 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 165 insertions(+)
 create mode 100644 lib/crc16_kunit.c

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 409dd193c09b4..eda319e9d5695 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2850,6 +2850,15 @@ config USERCOPY_KUNIT_TEST
 	  on the copy_to/from_user infrastructure, making sure basic
 	  user/kernel boundary testing is working.
 
+config CRC16_KUNIT_TEST
+	tristate "KUnit tests for CRC16"
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	select CRC16
+	help
+	  Enable this option to run unit tests for the kernel's CRC16
+	  implementation (<linux/crc16.h>).
+
 config TEST_UDELAY
 	tristate "udelay test driver"
 	help
diff --git a/lib/Makefile b/lib/Makefile
index 773adf88af416..1faed6414a85f 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -389,6 +389,7 @@ CFLAGS_fortify_kunit.o += $(DISABLE_STRUCTLEAK_PLUGIN)
 obj-$(CONFIG_FORTIFY_KUNIT_TEST) += fortify_kunit.o
 obj-$(CONFIG_SIPHASH_KUNIT_TEST) += siphash_kunit.o
 obj-$(CONFIG_USERCOPY_KUNIT_TEST) += usercopy_kunit.o
+obj-$(CONFIG_CRC16_KUNIT_TEST) += crc16_kunit.o
 
 obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o
 
diff --git a/lib/crc16_kunit.c b/lib/crc16_kunit.c
new file mode 100644
index 0000000000000..0918c98a96d26
--- /dev/null
+++ b/lib/crc16_kunit.c
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnits tests for CRC16.
+ *
+ * Copyright (C) 2024, LKCAMP
+ * Author: Vinicius Peixoto <vpeixoto@lkcamp.dev>
+ * Author: Fabricio Gasperin <fgasperin@lkcamp.dev>
+ * Author: Enzo Bertoloti <ebertoloti@lkcamp.dev>
+ */
+#include <kunit/test.h>
+#include <linux/crc16.h>
+#include <linux/prandom.h>
+
+#define CRC16_KUNIT_DATA_SIZE 4096
+#define CRC16_KUNIT_TEST_SIZE 100
+#define CRC16_KUNIT_SEED 0x12345678
+
+/**
+ * struct crc16_test - CRC16 test data
+ * @crc: initial input value to CRC16
+ * @start: Start index within the data buffer
+ * @length: Length of the data
+ */
+static struct crc16_test {
+	u16 crc;
+	u16 start;
+	u16 length;
+} tests[CRC16_KUNIT_TEST_SIZE];
+
+u8 data[CRC16_KUNIT_DATA_SIZE];
+
+
+/* Naive implementation of CRC16 for validation purposes */
+static inline u16 _crc16_naive_byte(u16 crc, u8 data)
+{
+	u8 i = 0;
+
+	crc ^= (u16) data;
+	for (i = 0; i < 8; i++) {
+		if (crc & 0x01)
+			crc = (crc >> 1) ^ 0xa001;
+		else
+			crc = crc >> 1;
+	}
+
+	return crc;
+}
+
+
+static inline u16 _crc16_naive(u16 crc, u8 *buffer, size_t len)
+{
+	while (len--)
+		crc = _crc16_naive_byte(crc, *buffer++);
+	return crc;
+}
+
+
+/* Small helper for generating pseudorandom 16-bit data */
+static inline u16 _rand16(void)
+{
+	static u32 rand = CRC16_KUNIT_SEED;
+
+	rand = next_pseudo_random32(rand);
+	return rand & 0xFFFF;
+}
+
+
+static int crc16_init_test_data(struct kunit_suite *suite)
+{
+	size_t i;
+
+	/* Fill the data buffer with random bytes */
+	for (i = 0; i < CRC16_KUNIT_DATA_SIZE; i++)
+		data[i] = _rand16() & 0xFF;
+
+	/* Generate random test data while ensuring the random
+	 * start + length values won't overflow the 4096-byte
+	 * buffer (0x7FF * 2 = 0xFFE < 0x1000)
+	 */
+	for (size_t i = 0; i < CRC16_KUNIT_TEST_SIZE; i++) {
+		tests[i].crc = _rand16();
+		tests[i].start = _rand16() & 0x7FF;
+		tests[i].length = _rand16() & 0x7FF;
+	}
+
+	return 0;
+}
+
+static void crc16_test_empty(struct kunit *test)
+{
+	u16 crc;
+
+	/* The result for empty data should be the same as the
+	 * initial crc
+	 */
+	crc = crc16(0x00, data, 0);
+	KUNIT_EXPECT_EQ(test, crc, 0);
+	crc = crc16(0xFF, data, 0);
+	KUNIT_EXPECT_EQ(test, crc, 0xFF);
+}
+
+static void crc16_test_correctness(struct kunit *test)
+{
+	size_t i;
+	u16 crc, crc_naive;
+
+	for (i = 0; i < CRC16_KUNIT_TEST_SIZE; i++) {
+		/* Compare results with the naive crc16 implementation */
+		crc = crc16(tests[i].crc, data + tests[i].start,
+			    tests[i].length);
+		crc_naive = _crc16_naive(tests[i].crc, data + tests[i].start,
+					 tests[i].length);
+		KUNIT_EXPECT_EQ(test, crc, crc_naive);
+	}
+}
+
+
+static void crc16_test_combine(struct kunit *test)
+{
+	size_t i, j;
+	u16 crc, crc_naive;
+
+	/* Make sure that combining two consecutive crc16 calculations
+	 * yields the same result as calculating the crc16 for the whole thing
+	 */
+	for (i = 0; i < CRC16_KUNIT_TEST_SIZE; i++) {
+		crc_naive = crc16(tests[i].crc, data + tests[i].start, tests[i].length);
+		for (j = 0; j < tests[i].length; j++) {
+			crc = crc16(tests[i].crc, data + tests[i].start, j);
+			crc = crc16(crc, data + tests[i].start + j, tests[i].length - j);
+			KUNIT_EXPECT_EQ(test, crc, crc_naive);
+		}
+	}
+}
+
+
+static struct kunit_case crc16_test_cases[] = {
+	KUNIT_CASE(crc16_test_empty),
+	KUNIT_CASE(crc16_test_combine),
+	KUNIT_CASE(crc16_test_correctness),
+	{},
+};
+
+static struct kunit_suite crc16_test_suite = {
+	.name = "crc16",
+	.test_cases = crc16_test_cases,
+	.suite_init = crc16_init_test_data,
+};
+kunit_test_suite(crc16_test_suite);
+
+MODULE_AUTHOR("Fabricio Gasperin <fgasperin@lkcamp.dev>");
+MODULE_AUTHOR("Vinicius Peixoto <vpeixoto@lkcamp.dev>");
+MODULE_AUTHOR("Enzo Bertoloti <ebertoloti@lkcamp.dev>");
+MODULE_DESCRIPTION("Unit tests for crc16");
+MODULE_LICENSE("GPL");

From 8801c35c3672c8492824f5d3c4d3b37f43ed63c3 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Fri, 11 Oct 2024 16:51:55 -0600
Subject: [PATCH 0887/1530] tools: fix -Wunused-result in linux.c

Fix the following -Wunused-result warnings on posix_memalign()
return values and add error handling.

./shared/linux.c:100:25: warning: ignoring return value of `posix_memalign' declared with attribute `warn_unused_result' [-Wunused-result]
  100 |          posix_memalign(&p, cachep->align, cachep->size);
      |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
../shared/linux.c: In function `kmem_cache_alloc_bulk':
../shared/linux.c:198:33: warning: ignoring return value of `posix_memalign' declared with attribute `warn_unused_result' [-Wunused-result]
  198 |          posix_memalign(&p[i], cachep->align,
      |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  199 |                                cachep->size);
      |                                ~~~~~~~~~~~~~

Link: https://lkml.kernel.org/r/20241011225155.27607-1-skhan@linuxfoundation.org
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/shared/linux.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/tools/testing/shared/linux.c b/tools/testing/shared/linux.c
index 17263696b5d88..66dbb362385f3 100644
--- a/tools/testing/shared/linux.c
+++ b/tools/testing/shared/linux.c
@@ -96,10 +96,13 @@ void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
 		p = node;
 	} else {
 		pthread_mutex_unlock(&cachep->lock);
-		if (cachep->align)
-			posix_memalign(&p, cachep->align, cachep->size);
-		else
+		if (cachep->align) {
+			if (posix_memalign(&p, cachep->align, cachep->size) < 0)
+				return NULL;
+		} else {
 			p = malloc(cachep->size);
+		}
+
 		if (cachep->ctor)
 			cachep->ctor(p);
 		else if (gfp & __GFP_ZERO)
@@ -195,8 +198,9 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
 			}
 
 			if (cachep->align) {
-				posix_memalign(&p[i], cachep->align,
-					       cachep->size);
+				if (posix_memalign(&p[i], cachep->align,
+					       cachep->size) < 0)
+					break;
 			} else {
 				p[i] = malloc(cachep->size);
 				if (!p[i])

From bf9850f6ea3577a099b0ed43f6e19ca43ef08704 Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Fri, 11 Oct 2024 22:12:14 +0800
Subject: [PATCH 0888/1530] lib/Makefile: make union-find compilation
 conditional on CONFIG_CPUSETS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, cpuset is the only user of the union-find implementation.
Compiling union-find in all configurations unnecessarily increases the
code size when building the kernel without cgroup support.  Modify the
build system to compile union-find only when CONFIG_CPUSETS is enabled.

Link: https://lore.kernel.org/lkml/1ccd6411-5002-4574-bb8e-3e64bba6a757@redhat.com/
Link: https://lkml.kernel.org/r/20241011141214.87096-1-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Suggested-by: Waiman Long <llong@redhat.com>
Acked-by: Waiman Long <longman@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Xavier <xavier_qy@163.com>
Cc: Zefan Li <lizefan.x@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 init/Kconfig | 1 +
 lib/Kconfig  | 3 +++
 lib/Makefile | 3 ++-
 3 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/init/Kconfig b/init/Kconfig
index c521e1421ad4a..5cb9b9490f30a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1157,6 +1157,7 @@ config CGROUP_HUGETLB
 config CPUSETS
 	bool "Cpuset controller"
 	depends on SMP
+	select UNION_FIND
 	help
 	  This option will let you create and manage CPUSETs which
 	  allow dynamically partitioning a system into sets of CPUs and
diff --git a/lib/Kconfig b/lib/Kconfig
index b38849af6f130..cf303bd91ddae 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -777,3 +777,6 @@ config POLYNOMIAL
 
 config FIRMWARE_TABLE
 	bool
+
+config UNION_FIND
+	bool
diff --git a/lib/Makefile b/lib/Makefile
index 1faed6414a85f..feebed74fc7a0 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -35,8 +35,9 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
 	 nmi_backtrace.o win_minmax.o memcat_p.o \
-	 buildid.o objpool.o union_find.o
+	 buildid.o objpool.o
 
+lib-$(CONFIG_UNION_FIND) += union_find.o
 lib-$(CONFIG_PRINTK) += dump_stack.o
 lib-$(CONFIG_SMP) += cpumask.o
 

From 1bb5d6609767b631526a95446198e5f436159bea Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 14 Oct 2024 03:02:10 -0700
Subject: [PATCH 0889/1530] scripts/decode_stacktrace.sh: remove trailing space

decode_stacktrace.sh adds a trailing space at the end of the decoded stack
if the module is not set (in most of the lines), which makes the some
lines of the stack having trailing space and some others not.

Do not add an extra space at the end of the line if module is not set,
adding consistency in output formatting.

Link: https://lkml.kernel.org/r/20241014100213.1873611-1-leitao@debian.org
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Elliot Berman <quic_eberman@quicinc.com>
Reviewed-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Cc: Bjorn Andersson <quic_bjorande@quicinc.com>
Cc: Luca Ceresoli <luca.ceresoli@bootlin.com>
Cc: Xiong Nandi <xndchn@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 scripts/decode_stacktrace.sh | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh
index 826836d264c6a..46fa18b80fc1b 100755
--- a/scripts/decode_stacktrace.sh
+++ b/scripts/decode_stacktrace.sh
@@ -311,7 +311,12 @@ handle_line() {
 	parse_symbol # modifies $symbol
 
 	# Add up the line number to the symbol
-	echo "${words[@]}" "$symbol $module"
+	if [[ -z ${module} ]]
+	then
+		echo "${words[@]}" "$symbol"
+	else
+		echo "${words[@]}" "$symbol $module"
+	fi
 }
 
 while read line; do

From ad8f63f935b6785c87681d35b9408f5ecd5db967 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Tue, 24 Sep 2024 11:07:13 +0200
Subject: [PATCH 0890/1530] perf/hw_breakpoint: use ERR_PTR_PCPU(),
 IS_ERR_PCPU() and PTR_ERR_PCPU() macros

Use ERR_PTR_PCPU() when returning error pointer in the percpu address
space.  Use IS_ERR_PCPU() and PTR_ERR_PCPU() when returning the error
pointer from the percpu address space.  These macros add intermediate cast
to unsigned long when switching named address spaces.

The patch will avoid future build errors due to pointer address space
mismatch with enabled strict percpu address space checks.

Link: https://lkml.kernel.org/r/20240924090813.1353586-1-ubizjak@gmail.com
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/events/hw_breakpoint.c           | 4 ++--
 samples/hw_breakpoint/data_breakpoint.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 6c2cb4e4f48da..bc4a61029b6dc 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -849,7 +849,7 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
 
 	cpu_events = alloc_percpu(typeof(*cpu_events));
 	if (!cpu_events)
-		return (void __percpu __force *)ERR_PTR(-ENOMEM);
+		return ERR_PTR_PCPU(-ENOMEM);
 
 	cpus_read_lock();
 	for_each_online_cpu(cpu) {
@@ -868,7 +868,7 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
 		return cpu_events;
 
 	unregister_wide_hw_breakpoint(cpu_events);
-	return (void __percpu __force *)ERR_PTR(err);
+	return ERR_PTR_PCPU(err);
 }
 EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint);
 
diff --git a/samples/hw_breakpoint/data_breakpoint.c b/samples/hw_breakpoint/data_breakpoint.c
index a2c831e89ce0e..fbb03b66dcbd1 100644
--- a/samples/hw_breakpoint/data_breakpoint.c
+++ b/samples/hw_breakpoint/data_breakpoint.c
@@ -52,8 +52,8 @@ static int __init hw_break_module_init(void)
 	attr.bp_type = HW_BREAKPOINT_W;
 
 	sample_hbp = register_wide_hw_breakpoint(&attr, sample_hbp_handler, NULL);
-	if (IS_ERR((void __force *)sample_hbp)) {
-		ret = PTR_ERR((void __force *)sample_hbp);
+	if (IS_ERR_PCPU(sample_hbp)) {
+		ret = PTR_ERR_PCPU(sample_hbp);
 		goto fail;
 	}
 

From f3adb88e6c0b50e18dab3d58b1d6c5abd35dfcf7 Mon Sep 17 00:00:00 2001
From: WangYuli <wangyuli@uniontech.com>
Date: Fri, 18 Oct 2024 10:47:19 +0800
Subject: [PATCH 0891/1530] scripts/spelling.txt: add typo "exprienced" and
 "rewritting"

Add typo "exprienced" and "rewritting".
They were found and fixed in follow patches:

Link: https://lore.kernel.org/all/90D42CB167CA0842+20241018021910.31359-1-wangyuli@uniontech.com/
Link: https://lore.kernel.org/all/45F06B5D4CA9F444+20241018023340.47617-1-wangyuli@uniontech.com/
Link: https://lkml.kernel.org/r/C1FE2459CF066CA5+20241018024719.58325-1-wangyuli@uniontech.com
Link: https://lore.kernel.org/all/20241017162846.GA51712@kernel.org/
Signed-off-by: WangYuli <wangyuli@uniontech.com>
Suggested-by: Simon Horman <horms@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Cc: WangYuli <wangyuli@uniontech.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 scripts/spelling.txt | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/scripts/spelling.txt b/scripts/spelling.txt
index fe25bf3b605a6..05bd9ca1fbfa1 100644
--- a/scripts/spelling.txt
+++ b/scripts/spelling.txt
@@ -674,6 +674,7 @@ explict||explicit
 explictely||explicitly
 explictly||explicitly
 expresion||expression
+exprienced||experienced
 exprimental||experimental
 extened||extended
 exteneded||extended
@@ -1388,6 +1389,7 @@ reuest||request
 reuqest||request
 reutnred||returned
 revsion||revision
+rewritting||rewriting
 rmeoved||removed
 rmeove||remove
 rmeoves||removes

From bc8f5921cd69188627c08041276238de222ab466 Mon Sep 17 00:00:00 2001
From: Ma Wupeng <mawupeng1@huawei.com>
Date: Wed, 23 Oct 2024 17:31:29 +0800
Subject: [PATCH 0892/1530] ipc: fix memleak if msg_init_ns failed in
 create_ipc_ns

Percpu memory allocation may failed during create_ipc_ns however this
fail is not handled properly since ipc sysctls and mq sysctls is not
released properly. Fix this by release these two resource when failure.

Here is the kmemleak stack when percpu failed:

unreferenced object 0xffff88819de2a600 (size 512):
  comm "shmem_2nstest", pid 120711, jiffies 4300542254
  hex dump (first 32 bytes):
    60 aa 9d 84 ff ff ff ff fc 18 48 b2 84 88 ff ff  `.........H.....
    04 00 00 00 a4 01 00 00 20 e4 56 81 ff ff ff ff  ........ .V.....
  backtrace (crc be7cba35):
    [<ffffffff81b43f83>] __kmalloc_node_track_caller_noprof+0x333/0x420
    [<ffffffff81a52e56>] kmemdup_noprof+0x26/0x50
    [<ffffffff821b2f37>] setup_mq_sysctls+0x57/0x1d0
    [<ffffffff821b29cc>] copy_ipcs+0x29c/0x3b0
    [<ffffffff815d6a10>] create_new_namespaces+0x1d0/0x920
    [<ffffffff815d7449>] copy_namespaces+0x2e9/0x3e0
    [<ffffffff815458f3>] copy_process+0x29f3/0x7ff0
    [<ffffffff8154b080>] kernel_clone+0xc0/0x650
    [<ffffffff8154b6b1>] __do_sys_clone+0xa1/0xe0
    [<ffffffff843df8ff>] do_syscall_64+0xbf/0x1c0
    [<ffffffff846000b0>] entry_SYSCALL_64_after_hwframe+0x4b/0x53

Link: https://lkml.kernel.org/r/20241023093129.3074301-1-mawupeng1@huawei.com
Fixes: 72d1e611082e ("ipc/msg: mitigate the lock contention with percpu counter")
Signed-off-by: Ma Wupeng <mawupeng1@huawei.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 ipc/namespace.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/ipc/namespace.c b/ipc/namespace.c
index 6ecc30effd3ec..4df91ceeeafe9 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -83,13 +83,15 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 
 	err = msg_init_ns(ns);
 	if (err)
-		goto fail_put;
+		goto fail_ipc;
 
 	sem_init_ns(ns);
 	shm_init_ns(ns);
 
 	return ns;
 
+fail_ipc:
+	retire_ipc_sysctls(ns);
 fail_mq:
 	retire_mq_sysctls(ns);
 

From 908ef9bb4bd36837c3619109bdcf58f6ab00bfc7 Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sat, 12 Oct 2024 12:28:26 +0800
Subject: [PATCH 0893/1530] lib/list_sort: remove unnecessary header includes

Patch series "Remove unnecessary header includes from
{tools/}lib/list_sort.c".

Remove outdated and unnecessary header includes from lib/list_sort.c and
tools/lib/list_sort.c.  Additionally, update the hunk exceptions checked
by check_headers.sh to reflect these changes.


This patch (of 3):

After commit 043b3f7b6388 ("lib/list_sort: simplify and remove
MAX_LIST_LENGTH_BITS"), list_sort.c no longer uses ARRAY_SIZE() (which
required kernel.h and bug.h for BUILD_BUG_ON_ZERO via __must_be_array) or
memset() (which required string.h).  As these headers are no longer
needed, removes them.

There are no changes to the generated code, as confirmed by 'objdump -d'.
Additionally, 'wc -l' shows that the size of lib/.list_sort.o.cmd is
reduced from 259 lines to 101 lines.

Link: https://lkml.kernel.org/r/20241012042828.471614-1-visitorckw@gmail.com
Link: https://lkml.kernel.org/r/20241012042828.471614-2-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/list_sort.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/lib/list_sort.c b/lib/list_sort.c
index 0fb59e92ca2d4..8d3f623536fed 100644
--- a/lib/list_sort.c
+++ b/lib/list_sort.c
@@ -1,9 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/kernel.h>
-#include <linux/bug.h>
 #include <linux/compiler.h>
 #include <linux/export.h>
-#include <linux/string.h>
 #include <linux/list_sort.h>
 #include <linux/list.h>
 

From ff1a39c3f86c4d998630645f6778a622a993fb8b Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sat, 12 Oct 2024 12:28:27 +0800
Subject: [PATCH 0894/1530] tools/lib/list_sort: remove unnecessary header
 includes

Since lib/list_sort.c no longer requires ARRAY_SIZE() and memset(), the
includes for kernel.h, bug.h, and string.h have been removed.  Similarly,
tools/lib/list_sort.c also does not need to include these headers, so they
have been removed as well.

Link: https://lkml.kernel.org/r/20241012042828.471614-3-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/lib/list_sort.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/tools/lib/list_sort.c b/tools/lib/list_sort.c
index 69affa251fa78..bb99e493dcd10 100644
--- a/tools/lib/list_sort.c
+++ b/tools/lib/list_sort.c
@@ -1,8 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/kernel.h>
 #include <linux/compiler.h>
 #include <linux/export.h>
-#include <linux/string.h>
 #include <linux/list_sort.h>
 #include <linux/list.h>
 

From 8f0d91f41000e769f16b62a4b44f1f6da6db905b Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sat, 12 Oct 2024 12:28:28 +0800
Subject: [PATCH 0895/1530] perf tools: update expected diff for
 lib/list_sort.c

Since there are no longer any header include differences between
lib/list_sort.c and tools/lib/list_sort.c, update the expected diff in
check-header_ignore_hunks accordingly.

Link: https://lkml.kernel.org/r/20241012042828.471614-4-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/perf/check-header_ignore_hunks/lib/list_sort.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/tools/perf/check-header_ignore_hunks/lib/list_sort.c b/tools/perf/check-header_ignore_hunks/lib/list_sort.c
index 32d98cb34f80a..b7316d29857d4 100644
--- a/tools/perf/check-header_ignore_hunks/lib/list_sort.c
+++ b/tools/perf/check-header_ignore_hunks/lib/list_sort.c
@@ -1,11 +1,4 @@
-@@ -1,5 +1,6 @@
- // SPDX-License-Identifier: GPL-2.0
- #include <linux/kernel.h>
-+#include <linux/bug.h>
- #include <linux/compiler.h>
- #include <linux/export.h>
- #include <linux/string.h>
-@@ -52,6 +53,7 @@
+@@ -50,6 +50,7 @@
  			struct list_head *a, struct list_head *b)
  {
  	struct list_head *tail = head;
@@ -13,7 +6,7 @@
  
  	for (;;) {
  		/* if equal, take 'a' -- important for sort stability */
-@@ -77,6 +79,15 @@
+@@ -75,6 +76,15 @@
  	/* Finish linking remainder of list b on to tail */
  	tail->next = b;
  	do {

From 74ef070e325465a1b364db6a5c6859785537f835 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Mon, 21 Oct 2024 10:07:36 +0200
Subject: [PATCH 0896/1530] percpu: merge VERIFY_PERCPU_PTR() into its only
 user

Merge VERIFY_PERCPU_PTR() into non-CONFIG_SMP per_cpu_ptr() to make macro
similar to CONFIG_SMP per_cpu_ptr().  This will allow a follow-up patch to
refactor common code to a macro.

No functional changes, non-CONFIG_SMP per_cpu_ptr() was the only user of
VERIFY_PERCPU_PTR().

Link: https://lkml.kernel.org/r/20241021080856.48746-1-ubizjak@gmail.com
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/percpu-defs.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 8efce7414fad6..7fa88c5f4b26c 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -254,13 +254,13 @@ do {									\
 
 #else	/* CONFIG_SMP */
 
-#define VERIFY_PERCPU_PTR(__p)						\
+#define per_cpu_ptr(ptr, cpu)						\
 ({									\
-	__verify_pcpu_ptr(__p);						\
-	(typeof(*(__p)) __kernel __force *)(__p);			\
+	(void)(cpu);							\
+	__verify_pcpu_ptr(ptr);						\
+	(typeof(*(ptr)) __kernel __force *)(ptr);			\
 })
 
-#define per_cpu_ptr(ptr, cpu)	({ (void)(cpu); VERIFY_PERCPU_PTR(ptr); })
 #define raw_cpu_ptr(ptr)	per_cpu_ptr(ptr, 0)
 #define this_cpu_ptr(ptr)	raw_cpu_ptr(ptr)
 

From 001217defda86d0d6a5a9e6cf77a6b813857e7e3 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Mon, 21 Oct 2024 10:07:37 +0200
Subject: [PATCH 0897/1530] percpu: introduce PERCPU_PTR() macro

Introduce PERCPU_PTR() macro to cast the percpu pointer from the percpu
address space to a generic (kernel) address space.  Use it in
per_cpu_ptr() and related SHIFT_PERCPU_PTR() macros.

Also remove common knowledge from SHIFT_PERCPU_PTR() comment, "weird cast"
is just a standard way to inform sparse of a cast from the percpu address
space to a generic address space.

Link: https://lkml.kernel.org/r/20241021080856.48746-2-ubizjak@gmail.com
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/percpu-defs.h | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 7fa88c5f4b26c..e1cf7982424f1 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -220,15 +220,17 @@ do {									\
 	(void)__vpp_verify;						\
 } while (0)
 
+#define PERCPU_PTR(__p)							\
+	(typeof(*(__p)) __force __kernel *)(__p);
+
 #ifdef CONFIG_SMP
 
 /*
- * Add an offset to a pointer but keep the pointer as-is.  Use RELOC_HIDE()
- * to prevent the compiler from making incorrect assumptions about the
- * pointer value.  The weird cast keeps both GCC and sparse happy.
+ * Add an offset to a pointer.  Use RELOC_HIDE() to prevent the compiler
+ * from making incorrect assumptions about the pointer value.
  */
 #define SHIFT_PERCPU_PTR(__p, __offset)					\
-	RELOC_HIDE((typeof(*(__p)) __kernel __force *)(__p), (__offset))
+	RELOC_HIDE(PERCPU_PTR(__p), (__offset))
 
 #define per_cpu_ptr(ptr, cpu)						\
 ({									\
@@ -258,7 +260,7 @@ do {									\
 ({									\
 	(void)(cpu);							\
 	__verify_pcpu_ptr(ptr);						\
-	(typeof(*(ptr)) __kernel __force *)(ptr);			\
+	PERCPU_PTR(ptr);						\
 })
 
 #define raw_cpu_ptr(ptr)	per_cpu_ptr(ptr, 0)

From dabddd687c9e1a06241d6b4d1f66b9f2b60b3ad1 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Mon, 21 Oct 2024 10:07:38 +0200
Subject: [PATCH 0898/1530] percpu: cast percpu pointer in PERCPU_PTR() via
 unsigned long

Cast pointer from percpu address space to generic (kernel) address space
in PERCPU_PTR() macro via unsigned long intermediate cast [1].  This
intermediate cast is also required to avoid build failure when GCC's
strict named address space checks for x86 targets [2] are enabled.

Found by GCC's named address space checks.

[1] https://sparse.docs.kernel.org/en/latest/annotations.html#address-space-name
[2] https://gcc.gnu.org/onlinedocs/gcc/Named-Address-Spaces.html#x86-Named-Address-Spaces

Link: https://lkml.kernel.org/r/20241021080856.48746-3-ubizjak@gmail.com
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/percpu-defs.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index e1cf7982424f1..35842d1e38796 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -221,7 +221,10 @@ do {									\
 } while (0)
 
 #define PERCPU_PTR(__p)							\
-	(typeof(*(__p)) __force __kernel *)(__p);
+({									\
+	unsigned long __pcpu_ptr = (__force unsigned long)(__p);	\
+	(typeof(*(__p)) __force __kernel *)(__pcpu_ptr);		\
+})
 
 #ifdef CONFIG_SMP
 

From 92a8b224b833e82d286d2100432adbac8cf8a2a1 Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 20 Oct 2024 12:01:51 +0800
Subject: [PATCH 0899/1530] lib/min_heap: introduce non-inline versions of min
 heap API functions

Patch series "Enhance min heap API with non-inline functions and
optimizations", v2.

Add non-inline versions of the min heap API functions in lib/min_heap.c
and updates all users outside of kernel/events/core.c to use these
non-inline versions.  To mitigate the performance impact of indirect
function calls caused by the non-inline versions of the swap and compare
functions, a builtin swap has been introduced that swaps elements based on
their size.  Additionally, it micro-optimizes the efficiency of the min
heap by pre-scaling the counter, following the same approach as in
lib/sort.c.  Documentation for the min heap API has also been added to the
core-api section.


This patch (of 10):

All current min heap API functions are marked with '__always_inline'.
However, as the number of users increases, inlining these functions
everywhere leads to a increase in kernel size.

In performance-critical paths, such as when perf events are enabled and
min heap functions are called on every context switch, it is important to
retain the inline versions for optimal performance.  To balance this, the
original inline functions are kept, and additional non-inline versions of
the functions have been added in lib/min_heap.c.

Link: https://lkml.kernel.org/r/20241020040200.939973-1-visitorckw@gmail.com
Link: https://lore.kernel.org/20240522161048.8d8bbc7b153b4ecd92c50666@linux-foundation.org
Link: https://lkml.kernel.org/r/20241020040200.939973-2-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Suggested-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Coly Li <colyli@suse.de>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Kuan-Wei Chiu <visitorckw@gmail.com>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Sakai <msakai@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/md/bcache/Kconfig |   1 +
 drivers/md/dm-vdo/Kconfig |   1 +
 fs/bcachefs/Kconfig       |   1 +
 include/linux/min_heap.h  | 129 +++++++++++++++++++++++++-------------
 kernel/events/core.c      |   6 +-
 lib/Kconfig               |   3 +
 lib/Kconfig.debug         |   1 +
 lib/Makefile              |   1 +
 lib/min_heap.c            |  70 +++++++++++++++++++++
 9 files changed, 167 insertions(+), 46 deletions(-)
 create mode 100644 lib/min_heap.c

diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig
index b2d10063d35fb..d4697e79d5a39 100644
--- a/drivers/md/bcache/Kconfig
+++ b/drivers/md/bcache/Kconfig
@@ -5,6 +5,7 @@ config BCACHE
 	select BLOCK_HOLDER_DEPRECATED if SYSFS
 	select CRC64
 	select CLOSURES
+	select MIN_HEAP
 	help
 	Allows a block device to be used as cache for other devices; uses
 	a btree for indexing and the layout is optimized for SSDs.
diff --git a/drivers/md/dm-vdo/Kconfig b/drivers/md/dm-vdo/Kconfig
index 111ecd2c2a249..2400b2bc4bc72 100644
--- a/drivers/md/dm-vdo/Kconfig
+++ b/drivers/md/dm-vdo/Kconfig
@@ -7,6 +7,7 @@ config DM_VDO
 	select DM_BUFIO
 	select LZ4_COMPRESS
 	select LZ4_DECOMPRESS
+	select MIN_HEAP
 	help
 	  This device mapper target presents a block device with
 	  deduplication, compression and thin-provisioning.
diff --git a/fs/bcachefs/Kconfig b/fs/bcachefs/Kconfig
index 5bac803ea367c..ab6c95b895b33 100644
--- a/fs/bcachefs/Kconfig
+++ b/fs/bcachefs/Kconfig
@@ -24,6 +24,7 @@ config BCACHEFS_FS
 	select XXHASH
 	select SRCU
 	select SYMBOLIC_ERRNAME
+	select MIN_HEAP
 	help
 	The bcachefs filesystem - a modern, copy on write filesystem, with
 	support for multiple devices, compression, checksumming, etc.
diff --git a/include/linux/min_heap.h b/include/linux/min_heap.h
index 43a7b9dcf15e6..0abb211739793 100644
--- a/include/linux/min_heap.h
+++ b/include/linux/min_heap.h
@@ -40,7 +40,7 @@ struct min_heap_callbacks {
 
 /* Initialize a min-heap. */
 static __always_inline
-void __min_heap_init(min_heap_char *heap, void *data, int size)
+void __min_heap_init_inline(min_heap_char *heap, void *data, int size)
 {
 	heap->nr = 0;
 	heap->size = size;
@@ -50,33 +50,33 @@ void __min_heap_init(min_heap_char *heap, void *data, int size)
 		heap->data = heap->preallocated;
 }
 
-#define min_heap_init(_heap, _data, _size)	\
-	__min_heap_init((min_heap_char *)_heap, _data, _size)
+#define min_heap_init_inline(_heap, _data, _size)	\
+	__min_heap_init_inline((min_heap_char *)_heap, _data, _size)
 
 /* Get the minimum element from the heap. */
 static __always_inline
-void *__min_heap_peek(struct min_heap_char *heap)
+void *__min_heap_peek_inline(struct min_heap_char *heap)
 {
 	return heap->nr ? heap->data : NULL;
 }
 
-#define min_heap_peek(_heap)	\
-	(__minheap_cast(_heap) __min_heap_peek((min_heap_char *)_heap))
+#define min_heap_peek_inline(_heap)	\
+	(__minheap_cast(_heap) __min_heap_peek_inline((min_heap_char *)_heap))
 
 /* Check if the heap is full. */
 static __always_inline
-bool __min_heap_full(min_heap_char *heap)
+bool __min_heap_full_inline(min_heap_char *heap)
 {
 	return heap->nr == heap->size;
 }
 
-#define min_heap_full(_heap)	\
-	__min_heap_full((min_heap_char *)_heap)
+#define min_heap_full_inline(_heap)	\
+	__min_heap_full_inline((min_heap_char *)_heap)
 
 /* Sift the element at pos down the heap. */
 static __always_inline
-void __min_heap_sift_down(min_heap_char *heap, int pos, size_t elem_size,
-		const struct min_heap_callbacks *func, void *args)
+void __min_heap_sift_down_inline(min_heap_char *heap, int pos, size_t elem_size,
+				 const struct min_heap_callbacks *func, void *args)
 {
 	void *left, *right;
 	void *data = heap->data;
@@ -108,13 +108,14 @@ void __min_heap_sift_down(min_heap_char *heap, int pos, size_t elem_size,
 	}
 }
 
-#define min_heap_sift_down(_heap, _pos, _func, _args)	\
-	__min_heap_sift_down((min_heap_char *)_heap, _pos, __minheap_obj_size(_heap), _func, _args)
+#define min_heap_sift_down_inline(_heap, _pos, _func, _args)	\
+	__min_heap_sift_down_inline((min_heap_char *)_heap, _pos, __minheap_obj_size(_heap),	\
+				    _func, _args)
 
 /* Sift up ith element from the heap, O(log2(nr)). */
 static __always_inline
-void __min_heap_sift_up(min_heap_char *heap, size_t elem_size, size_t idx,
-		const struct min_heap_callbacks *func, void *args)
+void __min_heap_sift_up_inline(min_heap_char *heap, size_t elem_size, size_t idx,
+			       const struct min_heap_callbacks *func, void *args)
 {
 	void *data = heap->data;
 	size_t parent;
@@ -128,27 +129,28 @@ void __min_heap_sift_up(min_heap_char *heap, size_t elem_size, size_t idx,
 	}
 }
 
-#define min_heap_sift_up(_heap, _idx, _func, _args)	\
-	__min_heap_sift_up((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx, _func, _args)
+#define min_heap_sift_up_inline(_heap, _idx, _func, _args)	\
+	__min_heap_sift_up_inline((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx,	\
+				  _func, _args)
 
 /* Floyd's approach to heapification that is O(nr). */
 static __always_inline
-void __min_heapify_all(min_heap_char *heap, size_t elem_size,
-		const struct min_heap_callbacks *func, void *args)
+void __min_heapify_all_inline(min_heap_char *heap, size_t elem_size,
+			      const struct min_heap_callbacks *func, void *args)
 {
 	int i;
 
 	for (i = heap->nr / 2 - 1; i >= 0; i--)
-		__min_heap_sift_down(heap, i, elem_size, func, args);
+		__min_heap_sift_down_inline(heap, i, elem_size, func, args);
 }
 
-#define min_heapify_all(_heap, _func, _args)	\
-	__min_heapify_all((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args)
+#define min_heapify_all_inline(_heap, _func, _args)	\
+	__min_heapify_all_inline((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args)
 
 /* Remove minimum element from the heap, O(log2(nr)). */
 static __always_inline
-bool __min_heap_pop(min_heap_char *heap, size_t elem_size,
-		const struct min_heap_callbacks *func, void *args)
+bool __min_heap_pop_inline(min_heap_char *heap, size_t elem_size,
+			   const struct min_heap_callbacks *func, void *args)
 {
 	void *data = heap->data;
 
@@ -158,13 +160,13 @@ bool __min_heap_pop(min_heap_char *heap, size_t elem_size,
 	/* Place last element at the root (position 0) and then sift down. */
 	heap->nr--;
 	memcpy(data, data + (heap->nr * elem_size), elem_size);
-	__min_heap_sift_down(heap, 0, elem_size, func, args);
+	__min_heap_sift_down_inline(heap, 0, elem_size, func, args);
 
 	return true;
 }
 
-#define min_heap_pop(_heap, _func, _args)	\
-	__min_heap_pop((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args)
+#define min_heap_pop_inline(_heap, _func, _args)	\
+	__min_heap_pop_inline((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args)
 
 /*
  * Remove the minimum element and then push the given element. The
@@ -172,22 +174,21 @@ bool __min_heap_pop(min_heap_char *heap, size_t elem_size,
  * efficient than a pop followed by a push that does 2.
  */
 static __always_inline
-void __min_heap_pop_push(min_heap_char *heap,
-		const void *element, size_t elem_size,
-		const struct min_heap_callbacks *func,
-		void *args)
+void __min_heap_pop_push_inline(min_heap_char *heap, const void *element, size_t elem_size,
+				const struct min_heap_callbacks *func, void *args)
 {
 	memcpy(heap->data, element, elem_size);
-	__min_heap_sift_down(heap, 0, elem_size, func, args);
+	__min_heap_sift_down_inline(heap, 0, elem_size, func, args);
 }
 
-#define min_heap_pop_push(_heap, _element, _func, _args)	\
-	__min_heap_pop_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func, _args)
+#define min_heap_pop_push_inline(_heap, _element, _func, _args)	\
+	__min_heap_pop_push_inline((min_heap_char *)_heap, _element, __minheap_obj_size(_heap),	\
+				   _func, _args)
 
 /* Push an element on to the heap, O(log2(nr)). */
 static __always_inline
-bool __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size,
-		const struct min_heap_callbacks *func, void *args)
+bool __min_heap_push_inline(min_heap_char *heap, const void *element, size_t elem_size,
+			    const struct min_heap_callbacks *func, void *args)
 {
 	void *data = heap->data;
 	int pos;
@@ -201,18 +202,19 @@ bool __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size,
 	heap->nr++;
 
 	/* Sift child at pos up. */
-	__min_heap_sift_up(heap, elem_size, pos, func, args);
+	__min_heap_sift_up_inline(heap, elem_size, pos, func, args);
 
 	return true;
 }
 
-#define min_heap_push(_heap, _element, _func, _args)	\
-	__min_heap_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func, _args)
+#define min_heap_push_inline(_heap, _element, _func, _args)	\
+	__min_heap_push_inline((min_heap_char *)_heap, _element, __minheap_obj_size(_heap),	\
+			       _func, _args)
 
 /* Remove ith element from the heap, O(log2(nr)). */
 static __always_inline
-bool __min_heap_del(min_heap_char *heap, size_t elem_size, size_t idx,
-		const struct min_heap_callbacks *func, void *args)
+bool __min_heap_del_inline(min_heap_char *heap, size_t elem_size, size_t idx,
+			   const struct min_heap_callbacks *func, void *args)
 {
 	void *data = heap->data;
 
@@ -224,12 +226,53 @@ bool __min_heap_del(min_heap_char *heap, size_t elem_size, size_t idx,
 	if (idx == heap->nr)
 		return true;
 	func->swp(data + (idx * elem_size), data + (heap->nr * elem_size), args);
-	__min_heap_sift_up(heap, elem_size, idx, func, args);
-	__min_heap_sift_down(heap, idx, elem_size, func, args);
+	__min_heap_sift_up_inline(heap, elem_size, idx, func, args);
+	__min_heap_sift_down_inline(heap, idx, elem_size, func, args);
 
 	return true;
 }
 
+#define min_heap_del_inline(_heap, _idx, _func, _args)	\
+	__min_heap_del_inline((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx,	\
+			      _func, _args)
+
+void __min_heap_init(min_heap_char *heap, void *data, int size);
+void *__min_heap_peek(struct min_heap_char *heap);
+bool __min_heap_full(min_heap_char *heap);
+void __min_heap_sift_down(min_heap_char *heap, int pos, size_t elem_size,
+			  const struct min_heap_callbacks *func, void *args);
+void __min_heap_sift_up(min_heap_char *heap, size_t elem_size, size_t idx,
+			const struct min_heap_callbacks *func, void *args);
+void __min_heapify_all(min_heap_char *heap, size_t elem_size,
+		       const struct min_heap_callbacks *func, void *args);
+bool __min_heap_pop(min_heap_char *heap, size_t elem_size,
+		    const struct min_heap_callbacks *func, void *args);
+void __min_heap_pop_push(min_heap_char *heap, const void *element, size_t elem_size,
+			 const struct min_heap_callbacks *func, void *args);
+bool __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size,
+		     const struct min_heap_callbacks *func, void *args);
+bool __min_heap_del(min_heap_char *heap, size_t elem_size, size_t idx,
+		    const struct min_heap_callbacks *func, void *args);
+
+#define min_heap_init(_heap, _data, _size)	\
+	__min_heap_init((min_heap_char *)_heap, _data, _size)
+#define min_heap_peek(_heap)	\
+	(__minheap_cast(_heap) __min_heap_peek((min_heap_char *)_heap))
+#define min_heap_full(_heap)	\
+	__min_heap_full((min_heap_char *)_heap)
+#define min_heap_sift_down(_heap, _pos, _func, _args)	\
+	__min_heap_sift_down((min_heap_char *)_heap, _pos, __minheap_obj_size(_heap), _func, _args)
+#define min_heap_sift_up(_heap, _idx, _func, _args)	\
+	__min_heap_sift_up((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx, _func, _args)
+#define min_heapify_all(_heap, _func, _args)	\
+	__min_heapify_all((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args)
+#define min_heap_pop(_heap, _func, _args)	\
+	__min_heap_pop((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args)
+#define min_heap_pop_push(_heap, _element, _func, _args)	\
+	__min_heap_pop_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap),	\
+			    _func, _args)
+#define min_heap_push(_heap, _element, _func, _args)	\
+	__min_heap_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func, _args)
 #define min_heap_del(_heap, _idx, _func, _args)	\
 	__min_heap_del((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx, _func, _args)
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index df27d08a72326..1b3c1198b2aff 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3870,7 +3870,7 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx,
 		perf_assert_pmu_disabled((*evt)->pmu_ctx->pmu);
 	}
 
-	min_heapify_all(&event_heap, &perf_min_heap, NULL);
+	min_heapify_all_inline(&event_heap, &perf_min_heap, NULL);
 
 	while (event_heap.nr) {
 		ret = func(*evt, data);
@@ -3879,9 +3879,9 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx,
 
 		*evt = perf_event_groups_next(*evt, pmu);
 		if (*evt)
-			min_heap_sift_down(&event_heap, 0, &perf_min_heap, NULL);
+			min_heap_sift_down_inline(&event_heap, 0, &perf_min_heap, NULL);
 		else
-			min_heap_pop(&event_heap, &perf_min_heap, NULL);
+			min_heap_pop_inline(&event_heap, &perf_min_heap, NULL);
 	}
 
 	return 0;
diff --git a/lib/Kconfig b/lib/Kconfig
index cf303bd91ddae..f5a2781669ead 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -780,3 +780,6 @@ config FIRMWARE_TABLE
 
 config UNION_FIND
 	bool
+
+config MIN_HEAP
+	bool
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index eda319e9d5695..2549b64b22805 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2279,6 +2279,7 @@ config TEST_LIST_SORT
 config TEST_MIN_HEAP
 	tristate "Min heap test"
 	depends on DEBUG_KERNEL || m
+	select MIN_HEAP
 	help
 	  Enable this to turn on min heap function tests. This test is
 	  executed only once during system boot (so affects only boot time),
diff --git a/lib/Makefile b/lib/Makefile
index feebed74fc7a0..1eb89962daef7 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -40,6 +40,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 lib-$(CONFIG_UNION_FIND) += union_find.o
 lib-$(CONFIG_PRINTK) += dump_stack.o
 lib-$(CONFIG_SMP) += cpumask.o
+lib-$(CONFIG_MIN_HEAP) += min_heap.o
 
 lib-y	+= kobject.o klist.o
 obj-y	+= lockref.o
diff --git a/lib/min_heap.c b/lib/min_heap.c
new file mode 100644
index 0000000000000..4485372ff3b1c
--- /dev/null
+++ b/lib/min_heap.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+#include <linux/min_heap.h>
+
+void __min_heap_init(min_heap_char *heap, void *data, int size)
+{
+	__min_heap_init_inline(heap, data, size);
+}
+EXPORT_SYMBOL(__min_heap_init);
+
+void *__min_heap_peek(struct min_heap_char *heap)
+{
+	return __min_heap_peek_inline(heap);
+}
+EXPORT_SYMBOL(__min_heap_peek);
+
+bool __min_heap_full(min_heap_char *heap)
+{
+	return __min_heap_full_inline(heap);
+}
+EXPORT_SYMBOL(__min_heap_full);
+
+void __min_heap_sift_down(min_heap_char *heap, int pos, size_t elem_size,
+			  const struct min_heap_callbacks *func, void *args)
+{
+	__min_heap_sift_down_inline(heap, pos, elem_size, func, args);
+}
+EXPORT_SYMBOL(__min_heap_sift_down);
+
+void __min_heap_sift_up(min_heap_char *heap, size_t elem_size, size_t idx,
+			const struct min_heap_callbacks *func, void *args)
+{
+	__min_heap_sift_up_inline(heap, elem_size, idx, func, args);
+}
+EXPORT_SYMBOL(__min_heap_sift_up);
+
+void __min_heapify_all(min_heap_char *heap, size_t elem_size,
+		       const struct min_heap_callbacks *func, void *args)
+{
+	__min_heapify_all_inline(heap, elem_size, func, args);
+}
+EXPORT_SYMBOL(__min_heapify_all);
+
+bool __min_heap_pop(min_heap_char *heap, size_t elem_size,
+		    const struct min_heap_callbacks *func, void *args)
+{
+	return __min_heap_pop_inline(heap, elem_size, func, args);
+}
+EXPORT_SYMBOL(__min_heap_pop);
+
+void __min_heap_pop_push(min_heap_char *heap, const void *element, size_t elem_size,
+			 const struct min_heap_callbacks *func, void *args)
+{
+	__min_heap_pop_push_inline(heap, element, elem_size, func, args);
+}
+EXPORT_SYMBOL(__min_heap_pop_push);
+
+bool __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size,
+		     const struct min_heap_callbacks *func, void *args)
+{
+	return __min_heap_push_inline(heap, element, elem_size, func, args);
+}
+EXPORT_SYMBOL(__min_heap_push);
+
+bool __min_heap_del(min_heap_char *heap, size_t elem_size, size_t idx,
+		    const struct min_heap_callbacks *func, void *args)
+{
+	return __min_heap_del_inline(heap, elem_size, idx, func, args);
+}
+EXPORT_SYMBOL(__min_heap_del);

From aa5888afc2347ebb394c2c4b694fa3026775009e Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 20 Oct 2024 12:01:52 +0800
Subject: [PATCH 0900/1530] lib min_heap: optimize min heap by prescaling
 counters for better performance

Improve the efficiency of the min heap by prescaling counters, eliminating
the need to repeatedly compute 'index * element_size' when accessing
elements.  By doing so, we avoid the overhead associated with
recalculating the byte offset for each heap operation.

However, with prescaling, the calculation for the parent element's
location is no longer as simple as '(i - 1) / 2'.  To address this, we
copy the parent function from 'lib/sort.c', which calculates the parent
offset in a branchless manner without using any division instructions.

This optimization should result in a more efficient heap implementation by
reducing the computational overhead of finding parent and child offsets.

Link: https://lkml.kernel.org/r/20241020040200.939973-3-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Coly Li <colyli@suse.de>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Sakai <msakai@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/min_heap.h | 73 +++++++++++++++++++++++++++-------------
 1 file changed, 49 insertions(+), 24 deletions(-)

diff --git a/include/linux/min_heap.h b/include/linux/min_heap.h
index 0abb211739793..41b092a142382 100644
--- a/include/linux/min_heap.h
+++ b/include/linux/min_heap.h
@@ -38,6 +38,32 @@ struct min_heap_callbacks {
 	void (*swp)(void *lhs, void *rhs, void *args);
 };
 
+/**
+ * parent - given the offset of the child, find the offset of the parent.
+ * @i: the offset of the heap element whose parent is sought.  Non-zero.
+ * @lsbit: a precomputed 1-bit mask, equal to "size & -size"
+ * @size: size of each element
+ *
+ * In terms of array indexes, the parent of element j = @i/@size is simply
+ * (j-1)/2.  But when working in byte offsets, we can't use implicit
+ * truncation of integer divides.
+ *
+ * Fortunately, we only need one bit of the quotient, not the full divide.
+ * @size has a least significant bit.  That bit will be clear if @i is
+ * an even multiple of @size, and set if it's an odd multiple.
+ *
+ * Logically, we're doing "if (i & lsbit) i -= size;", but since the
+ * branch is unpredictable, it's done with a bit of clever branch-free
+ * code instead.
+ */
+__attribute_const__ __always_inline
+static size_t parent(size_t i, unsigned int lsbit, size_t size)
+{
+	i -= size;
+	i -= size & -(i & lsbit);
+	return i / 2;
+}
+
 /* Initialize a min-heap. */
 static __always_inline
 void __min_heap_init_inline(min_heap_char *heap, void *data, int size)
@@ -78,33 +104,30 @@ static __always_inline
 void __min_heap_sift_down_inline(min_heap_char *heap, int pos, size_t elem_size,
 				 const struct min_heap_callbacks *func, void *args)
 {
-	void *left, *right;
+	const unsigned long lsbit = elem_size & -elem_size;
 	void *data = heap->data;
-	void *root = data + pos * elem_size;
-	int i = pos, j;
+	/* pre-scale counters for performance */
+	size_t a = pos * elem_size;
+	size_t b, c, d;
+	size_t n = heap->nr * elem_size;
 
 	/* Find the sift-down path all the way to the leaves. */
-	for (;;) {
-		if (i * 2 + 2 >= heap->nr)
-			break;
-		left = data + (i * 2 + 1) * elem_size;
-		right = data + (i * 2 + 2) * elem_size;
-		i = func->less(left, right, args) ? i * 2 + 1 : i * 2 + 2;
-	}
+	for (b = a; c = 2 * b + elem_size, (d = c + elem_size) < n;)
+		b = func->less(data + c, data + d, args) ? c : d;
 
 	/* Special case for the last leaf with no sibling. */
-	if (i * 2 + 2 == heap->nr)
-		i = i * 2 + 1;
+	if (d == n)
+		b = c;
 
 	/* Backtrack to the correct location. */
-	while (i != pos && func->less(root, data + i * elem_size, args))
-		i = (i - 1) / 2;
+	while (b != a && func->less(data + a, data + b, args))
+		b = parent(b, lsbit, elem_size);
 
 	/* Shift the element into its correct place. */
-	j = i;
-	while (i != pos) {
-		i = (i - 1) / 2;
-		func->swp(data + i * elem_size, data + j * elem_size, args);
+	c = b;
+	while (b != a) {
+		b = parent(b, lsbit, elem_size);
+		func->swp(data + b, data + c, args);
 	}
 }
 
@@ -117,15 +140,17 @@ static __always_inline
 void __min_heap_sift_up_inline(min_heap_char *heap, size_t elem_size, size_t idx,
 			       const struct min_heap_callbacks *func, void *args)
 {
+	const unsigned long lsbit = elem_size & -elem_size;
 	void *data = heap->data;
-	size_t parent;
+	/* pre-scale counters for performance */
+	size_t a = idx * elem_size, b;
 
-	while (idx) {
-		parent = (idx - 1) / 2;
-		if (func->less(data + parent * elem_size, data + idx * elem_size, args))
+	while (a) {
+		b = parent(a, lsbit, elem_size);
+		if (func->less(data + b, data + a, args))
 			break;
-		func->swp(data + parent * elem_size, data + idx * elem_size, args);
-		idx = parent;
+		func->swp(data + a, data + b, args);
+		a = b;
 	}
 }
 

From 03ec56d084611b5a4dc06ffa74db0928616e4d7f Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 20 Oct 2024 12:01:53 +0800
Subject: [PATCH 0901/1530] lib min_heap: avoid indirect function call by
 providing default swap

The non-inline min heap API can result in an indirect function call to the
custom swap function.  This becomes particularly costly when
CONFIG_MITIGATION_RETPOLINE is enabled, as indirect function calls are
expensive in this case.

To address this, copy the code from lib/sort.c and provide a default
builtin swap implementation that performs element swaps based on the
element size.  This change allows most users to avoid the overhead of
indirect function calls, improving efficiency.

Link: https://lkml.kernel.org/r/20241020040200.939973-4-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Coly Li <colyli@suse.de>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Sakai <msakai@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/min_heap.h | 159 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 156 insertions(+), 3 deletions(-)

diff --git a/include/linux/min_heap.h b/include/linux/min_heap.h
index 41b092a142382..e781727c89161 100644
--- a/include/linux/min_heap.h
+++ b/include/linux/min_heap.h
@@ -38,6 +38,147 @@ struct min_heap_callbacks {
 	void (*swp)(void *lhs, void *rhs, void *args);
 };
 
+/**
+ * is_aligned - is this pointer & size okay for word-wide copying?
+ * @base: pointer to data
+ * @size: size of each element
+ * @align: required alignment (typically 4 or 8)
+ *
+ * Returns true if elements can be copied using word loads and stores.
+ * The size must be a multiple of the alignment, and the base address must
+ * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS.
+ *
+ * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)"
+ * to "if ((a | b) & mask)", so we do that by hand.
+ */
+__attribute_const__ __always_inline
+static bool is_aligned(const void *base, size_t size, unsigned char align)
+{
+	unsigned char lsbits = (unsigned char)size;
+
+	(void)base;
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	lsbits |= (unsigned char)(uintptr_t)base;
+#endif
+	return (lsbits & (align - 1)) == 0;
+}
+
+/**
+ * swap_words_32 - swap two elements in 32-bit chunks
+ * @a: pointer to the first element to swap
+ * @b: pointer to the second element to swap
+ * @n: element size (must be a multiple of 4)
+ *
+ * Exchange the two objects in memory.  This exploits base+index addressing,
+ * which basically all CPUs have, to minimize loop overhead computations.
+ *
+ * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the
+ * bottom of the loop, even though the zero flag is still valid from the
+ * subtract (since the intervening mov instructions don't alter the flags).
+ * Gcc 8.1.0 doesn't have that problem.
+ */
+static __always_inline
+void swap_words_32(void *a, void *b, size_t n)
+{
+	do {
+		u32 t = *(u32 *)(a + (n -= 4));
+		*(u32 *)(a + n) = *(u32 *)(b + n);
+		*(u32 *)(b + n) = t;
+	} while (n);
+}
+
+/**
+ * swap_words_64 - swap two elements in 64-bit chunks
+ * @a: pointer to the first element to swap
+ * @b: pointer to the second element to swap
+ * @n: element size (must be a multiple of 8)
+ *
+ * Exchange the two objects in memory.  This exploits base+index
+ * addressing, which basically all CPUs have, to minimize loop overhead
+ * computations.
+ *
+ * We'd like to use 64-bit loads if possible.  If they're not, emulating
+ * one requires base+index+4 addressing which x86 has but most other
+ * processors do not.  If CONFIG_64BIT, we definitely have 64-bit loads,
+ * but it's possible to have 64-bit loads without 64-bit pointers (e.g.
+ * x32 ABI).  Are there any cases the kernel needs to worry about?
+ */
+static __always_inline
+void swap_words_64(void *a, void *b, size_t n)
+{
+	do {
+#ifdef CONFIG_64BIT
+		u64 t = *(u64 *)(a + (n -= 8));
+		*(u64 *)(a + n) = *(u64 *)(b + n);
+		*(u64 *)(b + n) = t;
+#else
+		/* Use two 32-bit transfers to avoid base+index+4 addressing */
+		u32 t = *(u32 *)(a + (n -= 4));
+		*(u32 *)(a + n) = *(u32 *)(b + n);
+		*(u32 *)(b + n) = t;
+
+		t = *(u32 *)(a + (n -= 4));
+		*(u32 *)(a + n) = *(u32 *)(b + n);
+		*(u32 *)(b + n) = t;
+#endif
+	} while (n);
+}
+
+/**
+ * swap_bytes - swap two elements a byte at a time
+ * @a: pointer to the first element to swap
+ * @b: pointer to the second element to swap
+ * @n: element size
+ *
+ * This is the fallback if alignment doesn't allow using larger chunks.
+ */
+static __always_inline
+void swap_bytes(void *a, void *b, size_t n)
+{
+	do {
+		char t = ((char *)a)[--n];
+		((char *)a)[n] = ((char *)b)[n];
+		((char *)b)[n] = t;
+	} while (n);
+}
+
+/*
+ * The values are arbitrary as long as they can't be confused with
+ * a pointer, but small integers make for the smallest compare
+ * instructions.
+ */
+#define SWAP_WORDS_64 ((void (*)(void *, void *, void *))0)
+#define SWAP_WORDS_32 ((void (*)(void *, void *, void *))1)
+#define SWAP_BYTES    ((void (*)(void *, void *, void *))2)
+
+/*
+ * Selects the appropriate swap function based on the element size.
+ */
+static __always_inline
+void *select_swap_func(const void *base, size_t size)
+{
+	if (is_aligned(base, size, 8))
+		return SWAP_WORDS_64;
+	else if (is_aligned(base, size, 4))
+		return SWAP_WORDS_32;
+	else
+		return SWAP_BYTES;
+}
+
+static __always_inline
+void do_swap(void *a, void *b, size_t size, void (*swap_func)(void *lhs, void *rhs, void *args),
+	     void *priv)
+{
+	if (swap_func == SWAP_WORDS_64)
+		swap_words_64(a, b, size);
+	else if (swap_func == SWAP_WORDS_32)
+		swap_words_32(a, b, size);
+	else if (swap_func == SWAP_BYTES)
+		swap_bytes(a, b, size);
+	else
+		swap_func(a, b, priv);
+}
+
 /**
  * parent - given the offset of the child, find the offset of the parent.
  * @i: the offset of the heap element whose parent is sought.  Non-zero.
@@ -106,11 +247,15 @@ void __min_heap_sift_down_inline(min_heap_char *heap, int pos, size_t elem_size,
 {
 	const unsigned long lsbit = elem_size & -elem_size;
 	void *data = heap->data;
+	void (*swp)(void *lhs, void *rhs, void *args) = func->swp;
 	/* pre-scale counters for performance */
 	size_t a = pos * elem_size;
 	size_t b, c, d;
 	size_t n = heap->nr * elem_size;
 
+	if (!swp)
+		swp = select_swap_func(data, elem_size);
+
 	/* Find the sift-down path all the way to the leaves. */
 	for (b = a; c = 2 * b + elem_size, (d = c + elem_size) < n;)
 		b = func->less(data + c, data + d, args) ? c : d;
@@ -127,7 +272,7 @@ void __min_heap_sift_down_inline(min_heap_char *heap, int pos, size_t elem_size,
 	c = b;
 	while (b != a) {
 		b = parent(b, lsbit, elem_size);
-		func->swp(data + b, data + c, args);
+		do_swap(data + b, data + c, elem_size, swp, args);
 	}
 }
 
@@ -142,14 +287,18 @@ void __min_heap_sift_up_inline(min_heap_char *heap, size_t elem_size, size_t idx
 {
 	const unsigned long lsbit = elem_size & -elem_size;
 	void *data = heap->data;
+	void (*swp)(void *lhs, void *rhs, void *args) = func->swp;
 	/* pre-scale counters for performance */
 	size_t a = idx * elem_size, b;
 
+	if (!swp)
+		swp = select_swap_func(data, elem_size);
+
 	while (a) {
 		b = parent(a, lsbit, elem_size);
 		if (func->less(data + b, data + a, args))
 			break;
-		func->swp(data + a, data + b, args);
+		do_swap(data + a, data + b, elem_size, swp, args);
 		a = b;
 	}
 }
@@ -242,15 +391,19 @@ bool __min_heap_del_inline(min_heap_char *heap, size_t elem_size, size_t idx,
 			   const struct min_heap_callbacks *func, void *args)
 {
 	void *data = heap->data;
+	void (*swp)(void *lhs, void *rhs, void *args) = func->swp;
 
 	if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap"))
 		return false;
 
+	if (!swp)
+		swp = select_swap_func(data, elem_size);
+
 	/* Place last element at the root (position 0) and then sift down. */
 	heap->nr--;
 	if (idx == heap->nr)
 		return true;
-	func->swp(data + (idx * elem_size), data + (heap->nr * elem_size), args);
+	do_swap(data + (idx * elem_size), data + (heap->nr * elem_size), elem_size, swp, args);
 	__min_heap_sift_up_inline(heap, elem_size, idx, func, args);
 	__min_heap_sift_down_inline(heap, idx, elem_size, func, args);
 

From d559bb2c6deea1fb4650b8a784b27e87ea12f71d Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 20 Oct 2024 12:01:54 +0800
Subject: [PATCH 0902/1530] lib/test_min_heap: update min_heap_callbacks to use
 default builtin swap

Replace the swp function pointer in the min_heap_callbacks of
test_min_heap with NULL, allowing direct usage of the default builtin swap
implementation.  This modification simplifies the code and improves
performance by removing unnecessary function indirection.

Link: https://lkml.kernel.org/r/20241020040200.939973-5-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Coly Li <colyli@suse.de>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Sakai <msakai@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/test_min_heap.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/lib/test_min_heap.c b/lib/test_min_heap.c
index 64c877e73b64d..e6fbb798558b5 100644
--- a/lib/test_min_heap.c
+++ b/lib/test_min_heap.c
@@ -23,14 +23,6 @@ static __init bool greater_than(const void *lhs, const void *rhs, void __always_
 	return *(int *)lhs > *(int *)rhs;
 }
 
-static __init void swap_ints(void *lhs, void *rhs, void __always_unused *args)
-{
-	int temp = *(int *)lhs;
-
-	*(int *)lhs = *(int *)rhs;
-	*(int *)rhs = temp;
-}
-
 static __init int pop_verify_heap(bool min_heap,
 				struct min_heap_test *heap,
 				const struct min_heap_callbacks *funcs)
@@ -72,7 +64,7 @@ static __init int test_heapify_all(bool min_heap)
 	};
 	struct min_heap_callbacks funcs = {
 		.less = min_heap ? less_than : greater_than,
-		.swp = swap_ints,
+		.swp = NULL,
 	};
 	int i, err;
 
@@ -104,7 +96,7 @@ static __init int test_heap_push(bool min_heap)
 	};
 	struct min_heap_callbacks funcs = {
 		.less = min_heap ? less_than : greater_than,
-		.swp = swap_ints,
+		.swp = NULL,
 	};
 	int i, temp, err;
 
@@ -136,7 +128,7 @@ static __init int test_heap_pop_push(bool min_heap)
 	};
 	struct min_heap_callbacks funcs = {
 		.less = min_heap ? less_than : greater_than,
-		.swp = swap_ints,
+		.swp = NULL,
 	};
 	int i, temp, err;
 
@@ -175,7 +167,7 @@ static __init int test_heap_del(bool min_heap)
 	heap.nr = ARRAY_SIZE(values);
 	struct min_heap_callbacks funcs = {
 		.less = min_heap ? less_than : greater_than,
-		.swp = swap_ints,
+		.swp = NULL,
 	};
 	int i, err;
 

From 083ad2871a8bbaf404b97eaa5e713e427e229f6b Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 20 Oct 2024 12:01:55 +0800
Subject: [PATCH 0903/1530] perf/core: update min_heap_callbacks to use default
 builtin swap

After introducing the default builtin swap implementation, update the
min_heap_callbacks to replace the swp function pointer with NULL.  This
change allows the min heap to directly utilize the builtin swap,
simplifying the code.

Link: https://lkml.kernel.org/r/20241020040200.939973-6-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Coly Li <colyli@suse.de>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Sakai <msakai@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/events/core.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1b3c1198b2aff..c2b4d7ee62967 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3778,18 +3778,11 @@ static bool perf_less_group_idx(const void *l, const void *r, void __always_unus
 	return le->group_index < re->group_index;
 }
 
-static void swap_ptr(void *l, void *r, void __always_unused *args)
-{
-	void **lp = l, **rp = r;
-
-	swap(*lp, *rp);
-}
-
 DEFINE_MIN_HEAP(struct perf_event *, perf_event_min_heap);
 
 static const struct min_heap_callbacks perf_min_heap = {
 	.less = perf_less_group_idx,
-	.swp = swap_ptr,
+	.swp = NULL,
 };
 
 static void __heap_add(struct perf_event_min_heap *heap, struct perf_event *event)

From d6844302074aac634afd00c4b70a1e1249afeff3 Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 20 Oct 2024 12:01:56 +0800
Subject: [PATCH 0904/1530] dm vdo: update min_heap_callbacks to use default
 builtin swap

Replace the swp function pointer in the min_heap_callbacks of dm-vdo with
NULL, allowing direct usage of the default builtin swap implementation.
This modification simplifies the code and improves performance by removing
unnecessary function indirection.

Link: https://lkml.kernel.org/r/20241020040200.939973-7-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Coly Li <colyli@suse.de>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Sakai <msakai@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/md/dm-vdo/repair.c     |  2 +-
 drivers/md/dm-vdo/slab-depot.c | 10 +---------
 2 files changed, 2 insertions(+), 10 deletions(-)

diff --git a/drivers/md/dm-vdo/repair.c b/drivers/md/dm-vdo/repair.c
index ffff2c999518e..8c006fb3afcf0 100644
--- a/drivers/md/dm-vdo/repair.c
+++ b/drivers/md/dm-vdo/repair.c
@@ -166,7 +166,7 @@ static void swap_mappings(void *item1, void *item2, void __always_unused *args)
 
 static const struct min_heap_callbacks repair_min_heap = {
 	.less = mapping_is_less_than,
-	.swp = swap_mappings,
+	.swp = NULL,
 };
 
 static struct numbered_block_mapping *sort_next_heap_element(struct repair_completion *repair)
diff --git a/drivers/md/dm-vdo/slab-depot.c b/drivers/md/dm-vdo/slab-depot.c
index 274f9ccd072f0..ccf7b2eac1315 100644
--- a/drivers/md/dm-vdo/slab-depot.c
+++ b/drivers/md/dm-vdo/slab-depot.c
@@ -3301,17 +3301,9 @@ static bool slab_status_is_less_than(const void *item1, const void *item2,
 	return info1->slab_number < info2->slab_number;
 }
 
-static void swap_slab_statuses(void *item1, void *item2, void __always_unused *args)
-{
-	struct slab_status *info1 = item1;
-	struct slab_status *info2 = item2;
-
-	swap(*info1, *info2);
-}
-
 static const struct min_heap_callbacks slab_status_min_heap = {
 	.less = slab_status_is_less_than,
-	.swp = swap_slab_statuses,
+	.swp = NULL,
 };
 
 /* Inform the slab actor that a action has finished on some slab; used by apply_to_slabs(). */

From 3d8a9a1c35227c3f1b0bd132c9f0a80dbda07b65 Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 20 Oct 2024 12:01:57 +0800
Subject: [PATCH 0905/1530] bcache: update min_heap_callbacks to use default
 builtin swap

Replace the swp function pointer in the min_heap_callbacks of bcache with
NULL, allowing direct usage of the default builtin swap implementation.
This modification simplifies the code and improves performance by removing
unnecessary function indirection.

Link: https://lkml.kernel.org/r/20241020040200.939973-8-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Coly Li <colyli@suse.de>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Sakai <msakai@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/md/bcache/alloc.c    | 11 ++---------
 drivers/md/bcache/bset.c     | 14 +++-----------
 drivers/md/bcache/extents.c  | 10 +---------
 drivers/md/bcache/movinggc.c | 10 +---------
 4 files changed, 7 insertions(+), 38 deletions(-)

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index da50f6661bae4..8998e61efa406 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -189,23 +189,16 @@ static inline bool new_bucket_min_cmp(const void *l, const void *r, void *args)
 	return new_bucket_prio(ca, *lhs) < new_bucket_prio(ca, *rhs);
 }
 
-static inline void new_bucket_swap(void *l, void *r, void __always_unused *args)
-{
-	struct bucket **lhs = l, **rhs = r;
-
-	swap(*lhs, *rhs);
-}
-
 static void invalidate_buckets_lru(struct cache *ca)
 {
 	struct bucket *b;
 	const struct min_heap_callbacks bucket_max_cmp_callback = {
 		.less = new_bucket_max_cmp,
-		.swp = new_bucket_swap,
+		.swp = NULL,
 	};
 	const struct min_heap_callbacks bucket_min_cmp_callback = {
 		.less = new_bucket_min_cmp,
-		.swp = new_bucket_swap,
+		.swp = NULL,
 	};
 
 	ca->heap.nr = 0;
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index bd97d86268874..68258a16e125c 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -1093,14 +1093,6 @@ static inline bool new_btree_iter_cmp(const void *l, const void *r, void __alway
 	return bkey_cmp(_l->k, _r->k) <= 0;
 }
 
-static inline void new_btree_iter_swap(void *iter1, void *iter2, void __always_unused *args)
-{
-	struct btree_iter_set *_iter1 = iter1;
-	struct btree_iter_set *_iter2 = iter2;
-
-	swap(*_iter1, *_iter2);
-}
-
 static inline bool btree_iter_end(struct btree_iter *iter)
 {
 	return !iter->heap.nr;
@@ -1111,7 +1103,7 @@ void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
 {
 	const struct min_heap_callbacks callbacks = {
 		.less = new_btree_iter_cmp,
-		.swp = new_btree_iter_swap,
+		.swp = NULL,
 	};
 
 	if (k != end)
@@ -1157,7 +1149,7 @@ static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
 	struct bkey *ret = NULL;
 	const struct min_heap_callbacks callbacks = {
 		.less = cmp,
-		.swp = new_btree_iter_swap,
+		.swp = NULL,
 	};
 
 	if (!btree_iter_end(iter)) {
@@ -1231,7 +1223,7 @@ static void btree_mergesort(struct btree_keys *b, struct bset *out,
 		: bch_ptr_invalid;
 	const struct min_heap_callbacks callbacks = {
 		.less = b->ops->sort_cmp,
-		.swp = new_btree_iter_swap,
+		.swp = NULL,
 	};
 
 	/* Heapify the iterator, using our comparison function */
diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c
index a7221e5dbe817..4b84fda1530a7 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -266,20 +266,12 @@ static bool new_bch_extent_sort_cmp(const void *l, const void *r, void __always_
 	return !(c ? c > 0 : _l->k < _r->k);
 }
 
-static inline void new_btree_iter_swap(void *iter1, void *iter2, void __always_unused *args)
-{
-	struct btree_iter_set *_iter1 = iter1;
-	struct btree_iter_set *_iter2 = iter2;
-
-	swap(*_iter1, *_iter2);
-}
-
 static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
 					  struct bkey *tmp)
 {
 	const struct min_heap_callbacks callbacks = {
 		.less = new_bch_extent_sort_cmp,
-		.swp = new_btree_iter_swap,
+		.swp = NULL,
 	};
 	while (iter->heap.nr > 1) {
 		struct btree_iter_set *top = iter->heap.data, *i = top + 1;
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 7f482729c56de..ef6abf33f9260 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -190,14 +190,6 @@ static bool new_bucket_cmp(const void *l, const void *r, void __always_unused *a
 	return GC_SECTORS_USED(*_l) >= GC_SECTORS_USED(*_r);
 }
 
-static void new_bucket_swap(void *l, void *r, void __always_unused *args)
-{
-	struct bucket **_l = l;
-	struct bucket **_r = r;
-
-	swap(*_l, *_r);
-}
-
 static unsigned int bucket_heap_top(struct cache *ca)
 {
 	struct bucket *b;
@@ -212,7 +204,7 @@ void bch_moving_gc(struct cache_set *c)
 	unsigned long sectors_to_move, reserve_sectors;
 	const struct min_heap_callbacks callbacks = {
 		.less = new_bucket_cmp,
-		.swp = new_bucket_swap,
+		.swp = NULL,
 	};
 
 	if (!c->copy_gc_enabled)

From 06ce25145bb864e5d948c4bc7e35bdb460a4e597 Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 20 Oct 2024 12:01:58 +0800
Subject: [PATCH 0906/1530] bcachefs: clean up duplicate min_heap_callbacks
 declarations

Refactor the bcachefs code to remove multiple redundant declarations of
min_heap_callbacks, ensuring that each unique declaration appears only
once.

Link: https://lore.kernel.org/20241017095520.GV16066@noisy.programming.kicks-ass.net
Link: https://lkml.kernel.org/r/20241020040200.939973-9-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Coly Li <colyli@suse.de>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Sakai <msakai@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/bcachefs/clock.c | 19 +++++--------------
 fs/bcachefs/ec.c    | 19 +++++--------------
 2 files changed, 10 insertions(+), 28 deletions(-)

diff --git a/fs/bcachefs/clock.c b/fs/bcachefs/clock.c
index 1d6b691e8da6e..1fcfcb5fd44f2 100644
--- a/fs/bcachefs/clock.c
+++ b/fs/bcachefs/clock.c
@@ -22,13 +22,13 @@ static inline void io_timer_swp(void *l, void *r, void __always_unused *args)
 	swap(*_l, *_r);
 }
 
+static const struct min_heap_callbacks callbacks = {
+	.less = io_timer_cmp,
+	.swp = io_timer_swp,
+};
+
 void bch2_io_timer_add(struct io_clock *clock, struct io_timer *timer)
 {
-	const struct min_heap_callbacks callbacks = {
-		.less = io_timer_cmp,
-		.swp = io_timer_swp,
-	};
-
 	spin_lock(&clock->timer_lock);
 
 	if (time_after_eq64((u64) atomic64_read(&clock->now), timer->expire)) {
@@ -48,11 +48,6 @@ void bch2_io_timer_add(struct io_clock *clock, struct io_timer *timer)
 
 void bch2_io_timer_del(struct io_clock *clock, struct io_timer *timer)
 {
-	const struct min_heap_callbacks callbacks = {
-		.less = io_timer_cmp,
-		.swp = io_timer_swp,
-	};
-
 	spin_lock(&clock->timer_lock);
 
 	for (size_t i = 0; i < clock->timers.nr; i++)
@@ -142,10 +137,6 @@ void bch2_kthread_io_clock_wait(struct io_clock *clock,
 static struct io_timer *get_expired_timer(struct io_clock *clock, u64 now)
 {
 	struct io_timer *ret = NULL;
-	const struct min_heap_callbacks callbacks = {
-		.less = io_timer_cmp,
-		.swp = io_timer_swp,
-	};
 
 	if (clock->timers.nr &&
 	    time_after_eq64(now, clock->timers.data[0]->expire)) {
diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c
index 749dcf368841d..6094afb0c6be7 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -1057,6 +1057,11 @@ static inline void ec_stripes_heap_swap(void *l, void *r, void *h)
 	ec_stripes_heap_set_backpointer(_h, j);
 }
 
+static const struct min_heap_callbacks callbacks = {
+	.less = ec_stripes_heap_cmp,
+	.swp = ec_stripes_heap_swap,
+};
+
 static void heap_verify_backpointer(struct bch_fs *c, size_t idx)
 {
 	ec_stripes_heap *h = &c->ec_stripes_heap;
@@ -1069,11 +1074,6 @@ static void heap_verify_backpointer(struct bch_fs *c, size_t idx)
 void bch2_stripes_heap_del(struct bch_fs *c,
 			   struct stripe *m, size_t idx)
 {
-	const struct min_heap_callbacks callbacks = {
-		.less = ec_stripes_heap_cmp,
-		.swp = ec_stripes_heap_swap,
-	};
-
 	mutex_lock(&c->ec_stripes_heap_lock);
 	heap_verify_backpointer(c, idx);
 
@@ -1084,11 +1084,6 @@ void bch2_stripes_heap_del(struct bch_fs *c,
 void bch2_stripes_heap_insert(struct bch_fs *c,
 			      struct stripe *m, size_t idx)
 {
-	const struct min_heap_callbacks callbacks = {
-		.less = ec_stripes_heap_cmp,
-		.swp = ec_stripes_heap_swap,
-	};
-
 	mutex_lock(&c->ec_stripes_heap_lock);
 	BUG_ON(min_heap_full(&c->ec_stripes_heap));
 
@@ -1107,10 +1102,6 @@ void bch2_stripes_heap_insert(struct bch_fs *c,
 void bch2_stripes_heap_update(struct bch_fs *c,
 			      struct stripe *m, size_t idx)
 {
-	const struct min_heap_callbacks callbacks = {
-		.less = ec_stripes_heap_cmp,
-		.swp = ec_stripes_heap_swap,
-	};
 	ec_stripes_heap *h = &c->ec_stripes_heap;
 	bool do_deletes;
 	size_t i;

From 75e849f3d0972e28d53fcfb540593c699a61c095 Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 20 Oct 2024 12:01:59 +0800
Subject: [PATCH 0907/1530] bcachefs: update min_heap_callbacks to use default
 builtin swap

Replace the swp function pointer in the min_heap_callbacks of bcachefs
with NULL, allowing direct usage of the default builtin swap
implementation.  This modification simplifies the code and improves
performance by removing unnecessary function indirection.

Link: https://lkml.kernel.org/r/20241020040200.939973-10-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Coly Li <colyli@suse.de>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Sakai <msakai@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/bcachefs/clock.c | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

diff --git a/fs/bcachefs/clock.c b/fs/bcachefs/clock.c
index 1fcfcb5fd44f2..1f8e035d7119f 100644
--- a/fs/bcachefs/clock.c
+++ b/fs/bcachefs/clock.c
@@ -14,17 +14,9 @@ static inline bool io_timer_cmp(const void *l, const void *r, void __always_unus
 	return (*_l)->expire < (*_r)->expire;
 }
 
-static inline void io_timer_swp(void *l, void *r, void __always_unused *args)
-{
-	struct io_timer **_l = (struct io_timer **)l;
-	struct io_timer **_r = (struct io_timer **)r;
-
-	swap(*_l, *_r);
-}
-
 static const struct min_heap_callbacks callbacks = {
 	.less = io_timer_cmp,
-	.swp = io_timer_swp,
+	.swp = NULL,
 };
 
 void bch2_io_timer_add(struct io_clock *clock, struct io_timer *timer)

From ec7c2bda802191241940e333fb199edf4b9ea67c Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 20 Oct 2024 12:02:00 +0800
Subject: [PATCH 0908/1530] Documentation/core-api: add min heap API
 introduction

Introduce an overview of the min heap API, detailing its usage and
functionality.  The documentation aims to provide developers with a clear
understanding of how to implement and utilize min heaps within the Linux
kernel, enhancing the overall accessibility of this data structure.

Link: https://lkml.kernel.org/r/20241020040200.939973-11-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Coly Li <colyli@suse.de>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Sakai <msakai@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/core-api/index.rst    |   1 +
 Documentation/core-api/min_heap.rst | 300 ++++++++++++++++++++++++++++
 2 files changed, 301 insertions(+)
 create mode 100644 Documentation/core-api/min_heap.rst

diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index 6a875743dd4b7..563b8fc0002f7 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -52,6 +52,7 @@ Library functionality that is used throughout the kernel.
    wrappers/atomic_bitops
    floating-point
    union_find
+   min_heap
 
 Low level entry and exit
 ========================
diff --git a/Documentation/core-api/min_heap.rst b/Documentation/core-api/min_heap.rst
new file mode 100644
index 0000000000000..0c636c8b7aa58
--- /dev/null
+++ b/Documentation/core-api/min_heap.rst
@@ -0,0 +1,300 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============
+Min Heap API
+============
+
+Introduction
+============
+
+The Min Heap API provides a set of functions and macros for managing min-heaps
+in the Linux kernel. A min-heap is a binary tree structure where the value of
+each node is less than or equal to the values of its children, ensuring that
+the smallest element is always at the root.
+
+This document provides a guide to the Min Heap API, detailing how to define and
+use min-heaps. Users should not directly call functions with **__min_heap_*()**
+prefixes, but should instead use the provided macro wrappers.
+
+In addition to the standard version of the functions, the API also includes a
+set of inline versions for performance-critical scenarios. These inline
+functions have the same names as their non-inline counterparts but include an
+**_inline** suffix. For example, **__min_heap_init_inline** and its
+corresponding macro wrapper **min_heap_init_inline**. The inline versions allow
+custom comparison and swap functions to be called directly, rather than through
+indirect function calls. This can significantly reduce overhead, especially
+when CONFIG_MITIGATION_RETPOLINE is enabled, as indirect function calls become
+more expensive. As with the non-inline versions, it is important to use the
+macro wrappers for inline functions instead of directly calling the functions
+themselves.
+
+Data Structures
+===============
+
+Min-Heap Definition
+-------------------
+
+The core data structure for representing a min-heap is defined using the
+**MIN_HEAP_PREALLOCATED** and **DEFINE_MIN_HEAP** macros. These macros allow
+you to define a min-heap with a preallocated buffer or dynamically allocated
+memory.
+
+Example:
+
+.. code-block:: c
+
+    #define MIN_HEAP_PREALLOCATED(_type, _name, _nr)
+    struct _name {
+        int nr;         /* Number of elements in the heap */
+        int size;       /* Maximum number of elements that can be held */
+        _type *data;    /* Pointer to the heap data */
+        _type preallocated[_nr];  /* Static preallocated array */
+    }
+
+    #define DEFINE_MIN_HEAP(_type, _name) MIN_HEAP_PREALLOCATED(_type, _name, 0)
+
+A typical heap structure will include a counter for the number of elements
+(`nr`), the maximum capacity of the heap (`size`), and a pointer to an array of
+elements (`data`). Optionally, you can specify a static array for preallocated
+heap storage using **MIN_HEAP_PREALLOCATED**.
+
+Min Heap Callbacks
+------------------
+
+The **struct min_heap_callbacks** provides customization options for ordering
+elements in the heap and swapping them. It contains two function pointers:
+
+.. code-block:: c
+
+    struct min_heap_callbacks {
+        bool (*less)(const void *lhs, const void *rhs, void *args);
+        void (*swp)(void *lhs, void *rhs, void *args);
+    };
+
+- **less** is the comparison function used to establish the order of elements.
+- **swp** is a function for swapping elements in the heap. If swp is set to
+  NULL, the default swap function will be used, which swaps the elements based on their size
+
+Macro Wrappers
+==============
+
+The following macro wrappers are provided for interacting with the heap in a
+user-friendly manner. Each macro corresponds to a function that operates on the
+heap, and they abstract away direct calls to internal functions.
+
+Each macro accepts various parameters that are detailed below.
+
+Heap Initialization
+--------------------
+
+.. code-block:: c
+
+    min_heap_init(heap, data, size);
+
+- **heap**: A pointer to the min-heap structure to be initialized.
+- **data**: A pointer to the buffer where the heap elements will be stored. If
+  `NULL`, the preallocated buffer within the heap structure will be used.
+- **size**: The maximum number of elements the heap can hold.
+
+This macro initializes the heap, setting its initial state. If `data` is
+`NULL`, the preallocated memory inside the heap structure will be used for
+storage. Otherwise, the user-provided buffer is used. The operation is **O(1)**.
+
+**Inline Version:** min_heap_init_inline(heap, data, size)
+
+Accessing the Top Element
+-------------------------
+
+.. code-block:: c
+
+    element = min_heap_peek(heap);
+
+- **heap**: A pointer to the min-heap from which to retrieve the smallest
+  element.
+
+This macro returns a pointer to the smallest element (the root) of the heap, or
+`NULL` if the heap is empty. The operation is **O(1)**.
+
+**Inline Version:** min_heap_peek_inline(heap)
+
+Heap Insertion
+--------------
+
+.. code-block:: c
+
+    success = min_heap_push(heap, element, callbacks, args);
+
+- **heap**: A pointer to the min-heap into which the element should be inserted.
+- **element**: A pointer to the element to be inserted into the heap.
+- **callbacks**: A pointer to a `struct min_heap_callbacks` providing the
+  `less` and `swp` functions.
+- **args**: Optional arguments passed to the `less` and `swp` functions.
+
+This macro inserts an element into the heap. It returns `true` if the insertion
+was successful and `false` if the heap is full. The operation is **O(log n)**.
+
+**Inline Version:** min_heap_push_inline(heap, element, callbacks, args)
+
+Heap Removal
+------------
+
+.. code-block:: c
+
+    success = min_heap_pop(heap, callbacks, args);
+
+- **heap**: A pointer to the min-heap from which to remove the smallest element.
+- **callbacks**: A pointer to a `struct min_heap_callbacks` providing the
+  `less` and `swp` functions.
+- **args**: Optional arguments passed to the `less` and `swp` functions.
+
+This macro removes the smallest element (the root) from the heap. It returns
+`true` if the element was successfully removed, or `false` if the heap is
+empty. The operation is **O(log n)**.
+
+**Inline Version:** min_heap_pop_inline(heap, callbacks, args)
+
+Heap Maintenance
+----------------
+
+You can use the following macros to maintain the heap's structure:
+
+.. code-block:: c
+
+    min_heap_sift_down(heap, pos, callbacks, args);
+
+- **heap**: A pointer to the min-heap.
+- **pos**: The index from which to start sifting down.
+- **callbacks**: A pointer to a `struct min_heap_callbacks` providing the
+  `less` and `swp` functions.
+- **args**: Optional arguments passed to the `less` and `swp` functions.
+
+This macro restores the heap property by moving the element at the specified
+index (`pos`) down the heap until it is in the correct position. The operation
+is **O(log n)**.
+
+**Inline Version:** min_heap_sift_down_inline(heap, pos, callbacks, args)
+
+.. code-block:: c
+
+    min_heap_sift_up(heap, idx, callbacks, args);
+
+- **heap**: A pointer to the min-heap.
+- **idx**: The index of the element to sift up.
+- **callbacks**: A pointer to a `struct min_heap_callbacks` providing the
+  `less` and `swp` functions.
+- **args**: Optional arguments passed to the `less` and `swp` functions.
+
+This macro restores the heap property by moving the element at the specified
+index (`idx`) up the heap. The operation is **O(log n)**.
+
+**Inline Version:** min_heap_sift_up_inline(heap, idx, callbacks, args)
+
+.. code-block:: c
+
+    min_heapify_all(heap, callbacks, args);
+
+- **heap**: A pointer to the min-heap.
+- **callbacks**: A pointer to a `struct min_heap_callbacks` providing the
+  `less` and `swp` functions.
+- **args**: Optional arguments passed to the `less` and `swp` functions.
+
+This macro ensures that the entire heap satisfies the heap property. It is
+called when the heap is built from scratch or after many modifications. The
+operation is **O(n)**.
+
+**Inline Version:** min_heapify_all_inline(heap, callbacks, args)
+
+Removing Specific Elements
+--------------------------
+
+.. code-block:: c
+
+    success = min_heap_del(heap, idx, callbacks, args);
+
+- **heap**: A pointer to the min-heap.
+- **idx**: The index of the element to delete.
+- **callbacks**: A pointer to a `struct min_heap_callbacks` providing the
+  `less` and `swp` functions.
+- **args**: Optional arguments passed to the `less` and `swp` functions.
+
+This macro removes an element at the specified index (`idx`) from the heap and
+restores the heap property. The operation is **O(log n)**.
+
+**Inline Version:** min_heap_del_inline(heap, idx, callbacks, args)
+
+Other Utilities
+===============
+
+- **min_heap_full(heap)**: Checks whether the heap is full.
+  Complexity: **O(1)**.
+
+.. code-block:: c
+
+    bool full = min_heap_full(heap);
+
+- `heap`: A pointer to the min-heap to check.
+
+This macro returns `true` if the heap is full, otherwise `false`.
+
+**Inline Version:** min_heap_full_inline(heap)
+
+- **min_heap_empty(heap)**: Checks whether the heap is empty.
+  Complexity: **O(1)**.
+
+.. code-block:: c
+
+    bool empty = min_heap_empty(heap);
+
+- `heap`: A pointer to the min-heap to check.
+
+This macro returns `true` if the heap is empty, otherwise `false`.
+
+**Inline Version:** min_heap_empty_inline(heap)
+
+Example Usage
+=============
+
+An example usage of the min-heap API would involve defining a heap structure,
+initializing it, and inserting and removing elements as needed.
+
+.. code-block:: c
+
+    #include <linux/min_heap.h>
+
+    int my_less_function(const void *lhs, const void *rhs, void *args) {
+        return (*(int *)lhs < *(int *)rhs);
+    }
+
+    struct min_heap_callbacks heap_cb = {
+        .less = my_less_function,    /* Comparison function for heap order */
+        .swp  = NULL,                /* Use default swap function */
+    };
+
+    void example_usage(void) {
+        /* Pre-populate the buffer with elements */
+        int buffer[5] = {5, 2, 8, 1, 3};
+        /* Declare a min-heap */
+        DEFINE_MIN_HEAP(int, my_heap);
+
+        /* Initialize the heap with preallocated buffer and size */
+        min_heap_init(&my_heap, buffer, 5);
+
+        /* Build the heap using min_heapify_all */
+        my_heap.nr = 5;  /* Set the number of elements in the heap */
+        min_heapify_all(&my_heap, &heap_cb, NULL);
+
+        /* Peek at the top element (should be 1 in this case) */
+        int *top = min_heap_peek(&my_heap);
+        pr_info("Top element: %d\n", *top);
+
+        /* Pop the top element (1) and get the new top (2) */
+        min_heap_pop(&my_heap, &heap_cb, NULL);
+        top = min_heap_peek(&my_heap);
+        pr_info("New top element: %d\n", *top);
+
+        /* Insert a new element (0) and recheck the top */
+        int new_element = 0;
+        min_heap_push(&my_heap, &new_element, &heap_cb, NULL);
+        top = min_heap_peek(&my_heap);
+        pr_info("Top element after insertion: %d\n", *top);
+    }

From 3ad563b1371b95f40b045b3bfa82848174e32a4c Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 27 Oct 2024 08:40:03 +0800
Subject: [PATCH 0909/1530] MAINTAINERS: add entry for min heap library code

Add a new entry in the MAINTAINERS file for the min heap library code,
with myself as the maintainer.  I am pleased to take on the responsibility
of maintaining and reviewing patches for this library, as I am
well-acquainted with its details through recent contributions.

Link: https://lkml.kernel.org/r/20241027004003.987934-1-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Cc: Kuan-Wei Chiu <visitorckw@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index bdae0faf000c7..c8c3baa4740c9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15461,6 +15461,15 @@ F:	arch/arm/boot/dts/marvell/armada-xp-crs326-24g-2s.dts
 F:	arch/arm/boot/dts/marvell/armada-xp-crs328-4c-20s-4s-bit.dts
 F:	arch/arm/boot/dts/marvell/armada-xp-crs328-4c-20s-4s.dts
 
+MIN HEAP
+M:	Kuan-Wei Chiu <visitorckw@gmail.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	Documentation/core-api/min_heap.rst
+F:	include/linux/min_heap.h
+F:	lib/min_heap.c
+F:	lib/test_min_heap.c
+
 MIPI CCS, SMIA AND SMIA++ IMAGE SENSOR DRIVER
 M:	Sakari Ailus <sakari.ailus@linux.intel.com>
 L:	linux-media@vger.kernel.org

From 25f12e46a0e05f5f75fd434e8098564e6f6793a5 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Thu, 24 Oct 2024 18:25:35 +0900
Subject: [PATCH 0910/1530] nilfs2: convert segment buffer to be folio-based

Patch series "nilfs2: Finish folio conversion".

This series converts all remaining page structure references in nilfs2 to
folio-based, except for nilfs_copy_buffer function, which was converted to
use folios in advance for cross-fs page flags cleanup.

This prioritizes folio conversion, and does not include buffer head
reference reduction, nor does it support for block sizes larger than the
system page size.

The first eight patches in this series mainly convert each of the
nilfs2-specific metadata implementations to use folios.  The last four
patches, by Matthew Wilcox, eliminate aops writepage callbacks and convert
the remaining page structure references to folio-based.  This part
reflects some corrections to the patch series posted by Matthew.


This patch (of 12):

In the segment buffer (log buffer) implementation, two parts of the block
buffer, CRC calculation and bio preparation, are still page-based, so
convert them to folio-based.

Link: https://lkml.kernel.org/r/20241024092602.13395-1-konishi.ryusuke@gmail.com
Link: https://lkml.kernel.org/r/20241024092602.13395-2-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/segbuf.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index dc431b4c34c96..e08cab03366b4 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -205,7 +205,6 @@ static void nilfs_segbuf_fill_in_data_crc(struct nilfs_segment_buffer *segbuf,
 {
 	struct buffer_head *bh;
 	struct nilfs_segment_summary *raw_sum;
-	void *kaddr;
 	u32 crc;
 
 	bh = list_entry(segbuf->sb_segsum_buffers.next, struct buffer_head,
@@ -220,9 +219,13 @@ static void nilfs_segbuf_fill_in_data_crc(struct nilfs_segment_buffer *segbuf,
 		crc = crc32_le(crc, bh->b_data, bh->b_size);
 	}
 	list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) {
-		kaddr = kmap_local_page(bh->b_page);
-		crc = crc32_le(crc, kaddr + bh_offset(bh), bh->b_size);
-		kunmap_local(kaddr);
+		size_t offset = offset_in_folio(bh->b_folio, bh->b_data);
+		unsigned char *from;
+
+		/* Do not support block sizes larger than PAGE_SIZE */
+		from = kmap_local_folio(bh->b_folio, offset);
+		crc = crc32_le(crc, from, bh->b_size);
+		kunmap_local(from);
 	}
 	raw_sum->ss_datasum = cpu_to_le32(crc);
 }
@@ -374,7 +377,7 @@ static int nilfs_segbuf_submit_bh(struct nilfs_segment_buffer *segbuf,
 				  struct nilfs_write_info *wi,
 				  struct buffer_head *bh)
 {
-	int len, err;
+	int err;
 
 	BUG_ON(wi->nr_vecs <= 0);
  repeat:
@@ -385,8 +388,8 @@ static int nilfs_segbuf_submit_bh(struct nilfs_segment_buffer *segbuf,
 			(wi->nilfs->ns_blocksize_bits - 9);
 	}
 
-	len = bio_add_page(wi->bio, bh->b_page, bh->b_size, bh_offset(bh));
-	if (len == bh->b_size) {
+	if (bio_add_folio(wi->bio, bh->b_folio, bh->b_size,
+			  offset_in_folio(bh->b_folio, bh->b_data))) {
 		wi->end++;
 		return 0;
 	}

From 4fd0a096f46887822b1138677510980fe03c002b Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Thu, 24 Oct 2024 18:25:36 +0900
Subject: [PATCH 0911/1530] nilfs2: convert common metadata file code to be
 folio-based

In the common routines for metadata files, nilfs_mdt_insert_new_block(),
which inserts a new block buffer into the cache, is still page-based, and
there are two places where bh_offset() is used.  Convert these to
page-based.

Link: https://lkml.kernel.org/r/20241024092602.13395-3-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/alloc.c  |  8 +++++---
 fs/nilfs2/cpfile.c |  4 ++--
 fs/nilfs2/mdt.c    | 21 +++++++++++++--------
 3 files changed, 20 insertions(+), 13 deletions(-)

diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index ba50388ee4bf1..d30dfed707b68 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -177,12 +177,14 @@ nilfs_palloc_entry_blkoff(const struct inode *inode, __u64 nr)
  * nilfs_palloc_desc_block_init - initialize buffer of a group descriptor block
  * @inode: inode of metadata file
  * @bh: buffer head of the buffer to be initialized
- * @kaddr: kernel address mapped for the page including the buffer
+ * @from: kernel address mapped for a chunk of the block
+ *
+ * This function does not yet support the case where block size > PAGE_SIZE.
  */
 static void nilfs_palloc_desc_block_init(struct inode *inode,
-					 struct buffer_head *bh, void *kaddr)
+					 struct buffer_head *bh, void *from)
 {
-	struct nilfs_palloc_group_desc *desc = kaddr + bh_offset(bh);
+	struct nilfs_palloc_group_desc *desc = from;
 	unsigned long n = nilfs_palloc_groups_per_desc_block(inode);
 	__le32 nfrees;
 
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index f0ce37552446c..a8046cbf27534 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -113,9 +113,9 @@ nilfs_cpfile_block_get_checkpoint(const struct inode *cpfile, __u64 cno,
 
 static void nilfs_cpfile_block_init(struct inode *cpfile,
 				    struct buffer_head *bh,
-				    void *kaddr)
+				    void *from)
 {
-	struct nilfs_checkpoint *cp = kaddr + bh_offset(bh);
+	struct nilfs_checkpoint *cp = from;
 	size_t cpsz = NILFS_MDT(cpfile)->mi_entry_size;
 	int n = nilfs_cpfile_checkpoints_per_block(cpfile);
 
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index ceb7dc0b5badd..a4c1e00aaaacd 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -33,7 +33,8 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block,
 					      struct buffer_head *, void *))
 {
 	struct nilfs_inode_info *ii = NILFS_I(inode);
-	void *kaddr;
+	struct folio *folio = bh->b_folio;
+	void *from;
 	int ret;
 
 	/* Caller exclude read accesses using page lock */
@@ -47,12 +48,14 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block,
 
 	set_buffer_mapped(bh);
 
-	kaddr = kmap_local_page(bh->b_page);
-	memset(kaddr + bh_offset(bh), 0, i_blocksize(inode));
+	/* Initialize block (block size > PAGE_SIZE not yet supported) */
+	from = kmap_local_folio(folio, offset_in_folio(folio, bh->b_data));
+	memset(from, 0, bh->b_size);
 	if (init_block)
-		init_block(inode, bh, kaddr);
-	flush_dcache_page(bh->b_page);
-	kunmap_local(kaddr);
+		init_block(inode, bh, from);
+	kunmap_local(from);
+
+	flush_dcache_folio(folio);
 
 	set_buffer_uptodate(bh);
 	mark_buffer_dirty(bh);
@@ -571,7 +574,8 @@ int nilfs_mdt_freeze_buffer(struct inode *inode, struct buffer_head *bh)
 	if (!bh_frozen)
 		bh_frozen = create_empty_buffers(folio, 1 << blkbits, 0);
 
-	bh_frozen = get_nth_bh(bh_frozen, bh_offset(bh) >> blkbits);
+	bh_frozen = get_nth_bh(bh_frozen,
+			       offset_in_folio(folio, bh->b_data) >> blkbits);
 
 	if (!buffer_uptodate(bh_frozen))
 		nilfs_copy_buffer(bh_frozen, bh);
@@ -601,7 +605,8 @@ nilfs_mdt_get_frozen_buffer(struct inode *inode, struct buffer_head *bh)
 	if (!IS_ERR(folio)) {
 		bh_frozen = folio_buffers(folio);
 		if (bh_frozen) {
-			n = bh_offset(bh) >> inode->i_blkbits;
+			n = offset_in_folio(folio, bh->b_data) >>
+				inode->i_blkbits;
 			bh_frozen = get_nth_bh(bh_frozen, n);
 		}
 		folio_unlock(folio);

From 832acfe6ea0365524a35df1e9b1d7350ed9ea5f5 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Thu, 24 Oct 2024 18:25:37 +0900
Subject: [PATCH 0912/1530] nilfs2: convert segment usage file to be
 folio-based

For the sufile, which is a metadata file that holds information about
managing segments, convert the page-based implementation to a folio-based
implementation.

kmap_local_page() is changed to use kmap_local_folio(), and where offsets
within a page are calculated using bh_offset(), are replaced with
calculations using offset_in_folio() with an additional helper function
nilfs_sufile_segment_usage_offset().

Link: https://lkml.kernel.org/r/20241024092602.13395-4-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/sufile.c | 160 +++++++++++++++++++++++----------------------
 1 file changed, 82 insertions(+), 78 deletions(-)

diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index eea5a6a12f7be..d3ecc813d6333 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -70,11 +70,20 @@ nilfs_sufile_segment_usages_in_block(const struct inode *sufile, __u64 curr,
 		     max - curr + 1);
 }
 
-static struct nilfs_segment_usage *
-nilfs_sufile_block_get_segment_usage(const struct inode *sufile, __u64 segnum,
-				     struct buffer_head *bh, void *kaddr)
+/**
+ * nilfs_sufile_segment_usage_offset - calculate the byte offset of a segment
+ *                                     usage entry in the folio containing it
+ * @sufile: segment usage file inode
+ * @segnum: number of segment usage
+ * @bh:     buffer head of block containing segment usage indexed by @segnum
+ *
+ * Return: Byte offset in the folio of the segment usage entry.
+ */
+static size_t nilfs_sufile_segment_usage_offset(const struct inode *sufile,
+						__u64 segnum,
+						struct buffer_head *bh)
 {
-	return kaddr + bh_offset(bh) +
+	return offset_in_folio(bh->b_folio, bh->b_data) +
 		nilfs_sufile_get_offset(sufile, segnum) *
 		NILFS_MDT(sufile)->mi_entry_size;
 }
@@ -112,13 +121,11 @@ static void nilfs_sufile_mod_counter(struct buffer_head *header_bh,
 				     u64 ncleanadd, u64 ndirtyadd)
 {
 	struct nilfs_sufile_header *header;
-	void *kaddr;
 
-	kaddr = kmap_local_page(header_bh->b_page);
-	header = kaddr + bh_offset(header_bh);
+	header = kmap_local_folio(header_bh->b_folio, 0);
 	le64_add_cpu(&header->sh_ncleansegs, ncleanadd);
 	le64_add_cpu(&header->sh_ndirtysegs, ndirtyadd);
-	kunmap_local(kaddr);
+	kunmap_local(header);
 
 	mark_buffer_dirty(header_bh);
 }
@@ -313,6 +320,7 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
 	struct nilfs_sufile_info *sui = NILFS_SUI(sufile);
 	size_t susz = NILFS_MDT(sufile)->mi_entry_size;
 	__u64 segnum, maxsegnum, last_alloc;
+	size_t offset;
 	void *kaddr;
 	unsigned long nsegments, nsus, cnt;
 	int ret, j;
@@ -322,10 +330,9 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
 	ret = nilfs_sufile_get_header_block(sufile, &header_bh);
 	if (ret < 0)
 		goto out_sem;
-	kaddr = kmap_local_page(header_bh->b_page);
-	header = kaddr + bh_offset(header_bh);
+	header = kmap_local_folio(header_bh->b_folio, 0);
 	last_alloc = le64_to_cpu(header->sh_last_alloc);
-	kunmap_local(kaddr);
+	kunmap_local(header);
 
 	nsegments = nilfs_sufile_get_nsegments(sufile);
 	maxsegnum = sui->allocmax;
@@ -359,9 +366,10 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
 							   &su_bh);
 		if (ret < 0)
 			goto out_header;
-		kaddr = kmap_local_page(su_bh->b_page);
-		su = nilfs_sufile_block_get_segment_usage(
-			sufile, segnum, su_bh, kaddr);
+
+		offset = nilfs_sufile_segment_usage_offset(sufile, segnum,
+							   su_bh);
+		su = kaddr = kmap_local_folio(su_bh->b_folio, offset);
 
 		nsus = nilfs_sufile_segment_usages_in_block(
 			sufile, segnum, maxsegnum);
@@ -372,12 +380,11 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
 			nilfs_segment_usage_set_dirty(su);
 			kunmap_local(kaddr);
 
-			kaddr = kmap_local_page(header_bh->b_page);
-			header = kaddr + bh_offset(header_bh);
+			header = kmap_local_folio(header_bh->b_folio, 0);
 			le64_add_cpu(&header->sh_ncleansegs, -1);
 			le64_add_cpu(&header->sh_ndirtysegs, 1);
 			header->sh_last_alloc = cpu_to_le64(segnum);
-			kunmap_local(kaddr);
+			kunmap_local(header);
 
 			sui->ncleansegs--;
 			mark_buffer_dirty(header_bh);
@@ -411,18 +418,18 @@ void nilfs_sufile_do_cancel_free(struct inode *sufile, __u64 segnum,
 				 struct buffer_head *su_bh)
 {
 	struct nilfs_segment_usage *su;
-	void *kaddr;
+	size_t offset;
 
-	kaddr = kmap_local_page(su_bh->b_page);
-	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
+	offset = nilfs_sufile_segment_usage_offset(sufile, segnum, su_bh);
+	su = kmap_local_folio(su_bh->b_folio, offset);
 	if (unlikely(!nilfs_segment_usage_clean(su))) {
 		nilfs_warn(sufile->i_sb, "%s: segment %llu must be clean",
 			   __func__, (unsigned long long)segnum);
-		kunmap_local(kaddr);
+		kunmap_local(su);
 		return;
 	}
 	nilfs_segment_usage_set_dirty(su);
-	kunmap_local(kaddr);
+	kunmap_local(su);
 
 	nilfs_sufile_mod_counter(header_bh, -1, 1);
 	NILFS_SUI(sufile)->ncleansegs--;
@@ -436,14 +443,14 @@ void nilfs_sufile_do_scrap(struct inode *sufile, __u64 segnum,
 			   struct buffer_head *su_bh)
 {
 	struct nilfs_segment_usage *su;
-	void *kaddr;
+	size_t offset;
 	int clean, dirty;
 
-	kaddr = kmap_local_page(su_bh->b_page);
-	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
+	offset = nilfs_sufile_segment_usage_offset(sufile, segnum, su_bh);
+	su = kmap_local_folio(su_bh->b_folio, offset);
 	if (su->su_flags == cpu_to_le32(BIT(NILFS_SEGMENT_USAGE_DIRTY)) &&
 	    su->su_nblocks == cpu_to_le32(0)) {
-		kunmap_local(kaddr);
+		kunmap_local(su);
 		return;
 	}
 	clean = nilfs_segment_usage_clean(su);
@@ -453,7 +460,7 @@ void nilfs_sufile_do_scrap(struct inode *sufile, __u64 segnum,
 	su->su_lastmod = cpu_to_le64(0);
 	su->su_nblocks = cpu_to_le32(0);
 	su->su_flags = cpu_to_le32(BIT(NILFS_SEGMENT_USAGE_DIRTY));
-	kunmap_local(kaddr);
+	kunmap_local(su);
 
 	nilfs_sufile_mod_counter(header_bh, clean ? (u64)-1 : 0, dirty ? 0 : 1);
 	NILFS_SUI(sufile)->ncleansegs -= clean;
@@ -467,15 +474,15 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum,
 			  struct buffer_head *su_bh)
 {
 	struct nilfs_segment_usage *su;
-	void *kaddr;
+	size_t offset;
 	int sudirty;
 
-	kaddr = kmap_local_page(su_bh->b_page);
-	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
+	offset = nilfs_sufile_segment_usage_offset(sufile, segnum, su_bh);
+	su = kmap_local_folio(su_bh->b_folio, offset);
 	if (nilfs_segment_usage_clean(su)) {
 		nilfs_warn(sufile->i_sb, "%s: segment %llu is already clean",
 			   __func__, (unsigned long long)segnum);
-		kunmap_local(kaddr);
+		kunmap_local(su);
 		return;
 	}
 	if (unlikely(nilfs_segment_usage_error(su)))
@@ -488,7 +495,7 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum,
 			   (unsigned long long)segnum);
 
 	nilfs_segment_usage_set_clean(su);
-	kunmap_local(kaddr);
+	kunmap_local(su);
 	mark_buffer_dirty(su_bh);
 
 	nilfs_sufile_mod_counter(header_bh, 1, sudirty ? (u64)-1 : 0);
@@ -507,7 +514,7 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum,
 int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum)
 {
 	struct buffer_head *bh;
-	void *kaddr;
+	size_t offset;
 	struct nilfs_segment_usage *su;
 	int ret;
 
@@ -523,12 +530,12 @@ int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum)
 		goto out_sem;
 	}
 
-	kaddr = kmap_local_page(bh->b_page);
-	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr);
+	offset = nilfs_sufile_segment_usage_offset(sufile, segnum, bh);
+	su = kmap_local_folio(bh->b_folio, offset);
 	if (unlikely(nilfs_segment_usage_error(su))) {
 		struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
 
-		kunmap_local(kaddr);
+		kunmap_local(su);
 		brelse(bh);
 		if (nilfs_segment_is_active(nilfs, segnum)) {
 			nilfs_error(sufile->i_sb,
@@ -546,7 +553,7 @@ int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum)
 		ret = -EIO;
 	} else {
 		nilfs_segment_usage_set_dirty(su);
-		kunmap_local(kaddr);
+		kunmap_local(su);
 		mark_buffer_dirty(bh);
 		nilfs_mdt_mark_dirty(sufile);
 		brelse(bh);
@@ -568,7 +575,7 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
 {
 	struct buffer_head *bh;
 	struct nilfs_segment_usage *su;
-	void *kaddr;
+	size_t offset;
 	int ret;
 
 	down_write(&NILFS_MDT(sufile)->mi_sem);
@@ -576,8 +583,8 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
 	if (ret < 0)
 		goto out_sem;
 
-	kaddr = kmap_local_page(bh->b_page);
-	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr);
+	offset = nilfs_sufile_segment_usage_offset(sufile, segnum, bh);
+	su = kmap_local_folio(bh->b_folio, offset);
 	if (modtime) {
 		/*
 		 * Check segusage error and set su_lastmod only when updating
@@ -587,7 +594,7 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
 		su->su_lastmod = cpu_to_le64(modtime);
 	}
 	su->su_nblocks = cpu_to_le32(nblocks);
-	kunmap_local(kaddr);
+	kunmap_local(su);
 
 	mark_buffer_dirty(bh);
 	nilfs_mdt_mark_dirty(sufile);
@@ -619,7 +626,6 @@ int nilfs_sufile_get_stat(struct inode *sufile, struct nilfs_sustat *sustat)
 	struct buffer_head *header_bh;
 	struct nilfs_sufile_header *header;
 	struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
-	void *kaddr;
 	int ret;
 
 	down_read(&NILFS_MDT(sufile)->mi_sem);
@@ -628,8 +634,7 @@ int nilfs_sufile_get_stat(struct inode *sufile, struct nilfs_sustat *sustat)
 	if (ret < 0)
 		goto out_sem;
 
-	kaddr = kmap_local_page(header_bh->b_page);
-	header = kaddr + bh_offset(header_bh);
+	header = kmap_local_folio(header_bh->b_folio, 0);
 	sustat->ss_nsegs = nilfs_sufile_get_nsegments(sufile);
 	sustat->ss_ncleansegs = le64_to_cpu(header->sh_ncleansegs);
 	sustat->ss_ndirtysegs = le64_to_cpu(header->sh_ndirtysegs);
@@ -638,7 +643,7 @@ int nilfs_sufile_get_stat(struct inode *sufile, struct nilfs_sustat *sustat)
 	spin_lock(&nilfs->ns_last_segment_lock);
 	sustat->ss_prot_seq = nilfs->ns_prot_seq;
 	spin_unlock(&nilfs->ns_last_segment_lock);
-	kunmap_local(kaddr);
+	kunmap_local(header);
 	brelse(header_bh);
 
  out_sem:
@@ -651,18 +656,18 @@ void nilfs_sufile_do_set_error(struct inode *sufile, __u64 segnum,
 			       struct buffer_head *su_bh)
 {
 	struct nilfs_segment_usage *su;
-	void *kaddr;
+	size_t offset;
 	int suclean;
 
-	kaddr = kmap_local_page(su_bh->b_page);
-	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
+	offset = nilfs_sufile_segment_usage_offset(sufile, segnum, su_bh);
+	su = kmap_local_folio(su_bh->b_folio, offset);
 	if (nilfs_segment_usage_error(su)) {
-		kunmap_local(kaddr);
+		kunmap_local(su);
 		return;
 	}
 	suclean = nilfs_segment_usage_clean(su);
 	nilfs_segment_usage_set_error(su);
-	kunmap_local(kaddr);
+	kunmap_local(su);
 
 	if (suclean) {
 		nilfs_sufile_mod_counter(header_bh, -1, 0);
@@ -700,7 +705,7 @@ static int nilfs_sufile_truncate_range(struct inode *sufile,
 	unsigned long segusages_per_block;
 	unsigned long nsegs, ncleaned;
 	__u64 segnum;
-	void *kaddr;
+	size_t offset;
 	ssize_t n, nc;
 	int ret;
 	int j;
@@ -731,16 +736,16 @@ static int nilfs_sufile_truncate_range(struct inode *sufile,
 			/* hole */
 			continue;
 		}
-		kaddr = kmap_local_page(su_bh->b_page);
-		su = nilfs_sufile_block_get_segment_usage(
-			sufile, segnum, su_bh, kaddr);
+		offset = nilfs_sufile_segment_usage_offset(sufile, segnum,
+							   su_bh);
+		su = kmap_local_folio(su_bh->b_folio, offset);
 		su2 = su;
 		for (j = 0; j < n; j++, su = (void *)su + susz) {
 			if ((le32_to_cpu(su->su_flags) &
 			     ~BIT(NILFS_SEGMENT_USAGE_ERROR)) ||
 			    nilfs_segment_is_active(nilfs, segnum + j)) {
 				ret = -EBUSY;
-				kunmap_local(kaddr);
+				kunmap_local(su2);
 				brelse(su_bh);
 				goto out_header;
 			}
@@ -752,7 +757,7 @@ static int nilfs_sufile_truncate_range(struct inode *sufile,
 				nc++;
 			}
 		}
-		kunmap_local(kaddr);
+		kunmap_local(su2);
 		if (nc > 0) {
 			mark_buffer_dirty(su_bh);
 			ncleaned += nc;
@@ -799,7 +804,6 @@ int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs)
 	struct buffer_head *header_bh;
 	struct nilfs_sufile_header *header;
 	struct nilfs_sufile_info *sui = NILFS_SUI(sufile);
-	void *kaddr;
 	unsigned long nsegs, nrsvsegs;
 	int ret = 0;
 
@@ -837,10 +841,9 @@ int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs)
 		sui->allocmin = 0;
 	}
 
-	kaddr = kmap_local_page(header_bh->b_page);
-	header = kaddr + bh_offset(header_bh);
+	header = kmap_local_folio(header_bh->b_folio, 0);
 	header->sh_ncleansegs = cpu_to_le64(sui->ncleansegs);
-	kunmap_local(kaddr);
+	kunmap_local(header);
 
 	mark_buffer_dirty(header_bh);
 	nilfs_mdt_mark_dirty(sufile);
@@ -874,6 +877,7 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
 	struct nilfs_suinfo *si = buf;
 	size_t susz = NILFS_MDT(sufile)->mi_entry_size;
 	struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
+	size_t offset;
 	void *kaddr;
 	unsigned long nsegs, segusages_per_block;
 	ssize_t n;
@@ -901,9 +905,9 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
 			continue;
 		}
 
-		kaddr = kmap_local_page(su_bh->b_page);
-		su = nilfs_sufile_block_get_segment_usage(
-			sufile, segnum, su_bh, kaddr);
+		offset = nilfs_sufile_segment_usage_offset(sufile, segnum,
+							   su_bh);
+		su = kaddr = kmap_local_folio(su_bh->b_folio, offset);
 		for (j = 0; j < n;
 		     j++, su = (void *)su + susz, si = (void *)si + sisz) {
 			si->sui_lastmod = le64_to_cpu(su->su_lastmod);
@@ -951,7 +955,7 @@ ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf,
 	struct buffer_head *header_bh, *bh;
 	struct nilfs_suinfo_update *sup, *supend = buf + supsz * nsup;
 	struct nilfs_segment_usage *su;
-	void *kaddr;
+	size_t offset;
 	unsigned long blkoff, prev_blkoff;
 	int cleansi, cleansu, dirtysi, dirtysu;
 	long ncleaned = 0, ndirtied = 0;
@@ -983,9 +987,9 @@ ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf,
 		goto out_header;
 
 	for (;;) {
-		kaddr = kmap_local_page(bh->b_page);
-		su = nilfs_sufile_block_get_segment_usage(
-			sufile, sup->sup_segnum, bh, kaddr);
+		offset = nilfs_sufile_segment_usage_offset(
+			sufile, sup->sup_segnum, bh);
+		su = kmap_local_folio(bh->b_folio, offset);
 
 		if (nilfs_suinfo_update_lastmod(sup))
 			su->su_lastmod = cpu_to_le64(sup->sup_sui.sui_lastmod);
@@ -1020,7 +1024,7 @@ ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf,
 			su->su_flags = cpu_to_le32(sup->sup_sui.sui_flags);
 		}
 
-		kunmap_local(kaddr);
+		kunmap_local(su);
 
 		sup = (void *)sup + supsz;
 		if (sup >= supend)
@@ -1076,6 +1080,7 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
 	struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
 	struct buffer_head *su_bh;
 	struct nilfs_segment_usage *su;
+	size_t offset;
 	void *kaddr;
 	size_t n, i, susz = NILFS_MDT(sufile)->mi_entry_size;
 	sector_t seg_start, seg_end, start_block, end_block;
@@ -1125,9 +1130,9 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
 			continue;
 		}
 
-		kaddr = kmap_local_page(su_bh->b_page);
-		su = nilfs_sufile_block_get_segment_usage(sufile, segnum,
-				su_bh, kaddr);
+		offset = nilfs_sufile_segment_usage_offset(sufile, segnum,
+							   su_bh);
+		su = kaddr = kmap_local_folio(su_bh->b_folio, offset);
 		for (i = 0; i < n; ++i, ++segnum, su = (void *)su + susz) {
 			if (!nilfs_segment_usage_clean(su))
 				continue;
@@ -1167,9 +1172,10 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
 				}
 
 				ndiscarded += nblocks;
-				kaddr = kmap_local_page(su_bh->b_page);
-				su = nilfs_sufile_block_get_segment_usage(
-					sufile, segnum, su_bh, kaddr);
+				offset = nilfs_sufile_segment_usage_offset(
+					sufile, segnum, su_bh);
+				su = kaddr = kmap_local_folio(su_bh->b_folio,
+							      offset);
 			}
 
 			/* start new extent */
@@ -1221,7 +1227,6 @@ int nilfs_sufile_read(struct super_block *sb, size_t susize,
 	struct nilfs_sufile_info *sui;
 	struct buffer_head *header_bh;
 	struct nilfs_sufile_header *header;
-	void *kaddr;
 	int err;
 
 	if (susize > sb->s_blocksize) {
@@ -1262,10 +1267,9 @@ int nilfs_sufile_read(struct super_block *sb, size_t susize,
 	}
 
 	sui = NILFS_SUI(sufile);
-	kaddr = kmap_local_page(header_bh->b_page);
-	header = kaddr + bh_offset(header_bh);
+	header = kmap_local_folio(header_bh->b_folio, 0);
 	sui->ncleansegs = le64_to_cpu(header->sh_ncleansegs);
-	kunmap_local(kaddr);
+	kunmap_local(header);
 	brelse(header_bh);
 
 	sui->allocmax = nilfs_sufile_get_nsegments(sufile) - 1;

From 21cf934eed5c82994ce570b43b3a3ed049e4275a Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Thu, 24 Oct 2024 18:25:38 +0900
Subject: [PATCH 0913/1530] nilfs2: convert persistent object allocator to be
 folio-based

Regarding the persistent oject allocator, a common mechanism for
allocating objects in metadata files such as inodes and DAT entries,
convert the page-based implementation to a folio-based implementation.

In this conversion, helper functions nilfs_palloc_group_desc_offset() and
nilfs_palloc_bitmap_offset() are added and used to calculate the byte
offset within a folio of a group descriptor structure and bitmap,
respectively, to replace kmap_local_page with kmap_local_folio.

In addition, a helper function called nilfs_palloc_entry_offset() is
provided to facilitate common calculation of the byte offset within a
folio of metadata file entries managed in the persistent object allocator
format.

Link: https://lkml.kernel.org/r/20241024092602.13395-5-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/alloc.c | 137 +++++++++++++++++++++++++++++-----------------
 fs/nilfs2/alloc.h |   2 +
 2 files changed, 89 insertions(+), 50 deletions(-)

diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index d30dfed707b68..5e0a6bd3e0159 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -339,19 +339,55 @@ static int nilfs_palloc_delete_entry_block(struct inode *inode, __u64 nr)
 }
 
 /**
- * nilfs_palloc_block_get_group_desc - get kernel address of a group descriptor
+ * nilfs_palloc_group_desc_offset - calculate the byte offset of a group
+ *                                  descriptor in the folio containing it
  * @inode: inode of metadata file using this allocator
  * @group: group number
- * @bh: buffer head of the buffer storing the group descriptor block
- * @kaddr: kernel address mapped for the page including the buffer
+ * @bh:    buffer head of the group descriptor block
+ *
+ * Return: Byte offset in the folio of the group descriptor for @group.
  */
-static struct nilfs_palloc_group_desc *
-nilfs_palloc_block_get_group_desc(const struct inode *inode,
-				  unsigned long group,
-				  const struct buffer_head *bh, void *kaddr)
+static size_t nilfs_palloc_group_desc_offset(const struct inode *inode,
+					     unsigned long group,
+					     const struct buffer_head *bh)
 {
-	return (struct nilfs_palloc_group_desc *)(kaddr + bh_offset(bh)) +
-		group % nilfs_palloc_groups_per_desc_block(inode);
+	return offset_in_folio(bh->b_folio, bh->b_data) +
+		sizeof(struct nilfs_palloc_group_desc) *
+		(group % nilfs_palloc_groups_per_desc_block(inode));
+}
+
+/**
+ * nilfs_palloc_bitmap_offset - calculate the byte offset of a bitmap block
+ *                              in the folio containing it
+ * @bh: buffer head of the bitmap block
+ *
+ * Return: Byte offset in the folio of the bitmap block for @bh.
+ */
+static size_t nilfs_palloc_bitmap_offset(const struct buffer_head *bh)
+{
+	return offset_in_folio(bh->b_folio, bh->b_data);
+}
+
+/**
+ * nilfs_palloc_entry_offset - calculate the byte offset of an entry in the
+ *                             folio containing it
+ * @inode: inode of metadata file using this allocator
+ * @nr:    serial number of the entry (e.g. inode number)
+ * @bh:    buffer head of the entry block
+ *
+ * Return: Byte offset in the folio of the entry @nr.
+ */
+size_t nilfs_palloc_entry_offset(const struct inode *inode, __u64 nr,
+				 const struct buffer_head *bh)
+{
+	unsigned long entry_index_in_group, entry_index_in_block;
+
+	nilfs_palloc_group(inode, nr, &entry_index_in_group);
+	entry_index_in_block = entry_index_in_group %
+		NILFS_MDT(inode)->mi_entries_per_block;
+
+	return offset_in_folio(bh->b_folio, bh->b_data) +
+		entry_index_in_block * NILFS_MDT(inode)->mi_entry_size;
 }
 
 /**
@@ -508,7 +544,7 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
 	struct buffer_head *desc_bh, *bitmap_bh;
 	struct nilfs_palloc_group_desc *desc;
 	unsigned char *bitmap;
-	void *desc_kaddr, *bitmap_kaddr;
+	size_t doff, boff;
 	unsigned long group, maxgroup, ngroups;
 	unsigned long group_offset, maxgroup_offset;
 	unsigned long n, entries_per_group;
@@ -531,17 +567,17 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
 		ret = nilfs_palloc_get_desc_block(inode, group, 1, &desc_bh);
 		if (ret < 0)
 			return ret;
-		desc_kaddr = kmap_local_page(desc_bh->b_page);
-		desc = nilfs_palloc_block_get_group_desc(
-			inode, group, desc_bh, desc_kaddr);
+
+		doff = nilfs_palloc_group_desc_offset(inode, group, desc_bh);
+		desc = kmap_local_folio(desc_bh->b_folio, doff);
 		n = nilfs_palloc_rest_groups_in_desc_block(inode, group,
 							   maxgroup);
-		for (j = 0; j < n; j++, desc++, group++, group_offset = 0) {
+		for (j = 0; j < n; j++, group++, group_offset = 0) {
 			lock = nilfs_mdt_bgl_lock(inode, group);
-			if (nilfs_palloc_group_desc_nfrees(desc, lock) == 0)
+			if (nilfs_palloc_group_desc_nfrees(&desc[j], lock) == 0)
 				continue;
 
-			kunmap_local(desc_kaddr);
+			kunmap_local(desc);
 			ret = nilfs_palloc_get_bitmap_block(inode, group, 1,
 							    &bitmap_bh);
 			if (unlikely(ret < 0)) {
@@ -549,12 +585,14 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
 				return ret;
 			}
 
-			desc_kaddr = kmap_local_page(desc_bh->b_page);
-			desc = nilfs_palloc_block_get_group_desc(
-				inode, group, desc_bh, desc_kaddr);
+			/*
+			 * Re-kmap the folio containing the first (and
+			 * subsequent) group descriptors.
+			 */
+			desc = kmap_local_folio(desc_bh->b_folio, doff);
 
-			bitmap_kaddr = kmap_local_page(bitmap_bh->b_page);
-			bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
+			boff = nilfs_palloc_bitmap_offset(bitmap_bh);
+			bitmap = kmap_local_folio(bitmap_bh->b_folio, boff);
 			pos = nilfs_palloc_find_available_slot(
 				bitmap, group_offset, entries_per_group, lock,
 				wrap);
@@ -564,14 +602,14 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
 			 * beginning, the wrap flag only has an effect on the
 			 * first search.
 			 */
-			kunmap_local(bitmap_kaddr);
+			kunmap_local(bitmap);
 			if (pos >= 0)
 				goto found;
 
 			brelse(bitmap_bh);
 		}
 
-		kunmap_local(desc_kaddr);
+		kunmap_local(desc);
 		brelse(desc_bh);
 	}
 
@@ -580,9 +618,9 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
 
 found:
 	/* found a free entry */
-	nilfs_palloc_group_desc_add_entries(desc, lock, -1);
+	nilfs_palloc_group_desc_add_entries(&desc[j], lock, -1);
 	req->pr_entry_nr = entries_per_group * group + pos;
-	kunmap_local(desc_kaddr);
+	kunmap_local(desc);
 
 	req->pr_desc_bh = desc_bh;
 	req->pr_bitmap_bh = bitmap_bh;
@@ -613,18 +651,18 @@ void nilfs_palloc_commit_alloc_entry(struct inode *inode,
 void nilfs_palloc_commit_free_entry(struct inode *inode,
 				    struct nilfs_palloc_req *req)
 {
-	struct nilfs_palloc_group_desc *desc;
 	unsigned long group, group_offset;
+	size_t doff, boff;
+	struct nilfs_palloc_group_desc *desc;
 	unsigned char *bitmap;
-	void *desc_kaddr, *bitmap_kaddr;
 	spinlock_t *lock;
 
 	group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset);
-	desc_kaddr = kmap_local_page(req->pr_desc_bh->b_page);
-	desc = nilfs_palloc_block_get_group_desc(inode, group,
-						 req->pr_desc_bh, desc_kaddr);
-	bitmap_kaddr = kmap_local_page(req->pr_bitmap_bh->b_page);
-	bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh);
+	doff = nilfs_palloc_group_desc_offset(inode, group, req->pr_desc_bh);
+	desc = kmap_local_folio(req->pr_desc_bh->b_folio, doff);
+
+	boff = nilfs_palloc_bitmap_offset(req->pr_bitmap_bh);
+	bitmap = kmap_local_folio(req->pr_bitmap_bh->b_folio, boff);
 	lock = nilfs_mdt_bgl_lock(inode, group);
 
 	if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap))
@@ -635,8 +673,8 @@ void nilfs_palloc_commit_free_entry(struct inode *inode,
 	else
 		nilfs_palloc_group_desc_add_entries(desc, lock, 1);
 
-	kunmap_local(bitmap_kaddr);
-	kunmap_local(desc_kaddr);
+	kunmap_local(bitmap);
+	kunmap_local(desc);
 
 	mark_buffer_dirty(req->pr_desc_bh);
 	mark_buffer_dirty(req->pr_bitmap_bh);
@@ -655,17 +693,17 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
 				    struct nilfs_palloc_req *req)
 {
 	struct nilfs_palloc_group_desc *desc;
-	void *desc_kaddr, *bitmap_kaddr;
+	size_t doff, boff;
 	unsigned char *bitmap;
 	unsigned long group, group_offset;
 	spinlock_t *lock;
 
 	group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset);
-	desc_kaddr = kmap_local_page(req->pr_desc_bh->b_page);
-	desc = nilfs_palloc_block_get_group_desc(inode, group,
-						 req->pr_desc_bh, desc_kaddr);
-	bitmap_kaddr = kmap_local_page(req->pr_bitmap_bh->b_page);
-	bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh);
+	doff = nilfs_palloc_group_desc_offset(inode, group, req->pr_desc_bh);
+	desc = kmap_local_folio(req->pr_desc_bh->b_folio, doff);
+
+	boff = nilfs_palloc_bitmap_offset(req->pr_bitmap_bh);
+	bitmap = kmap_local_folio(req->pr_bitmap_bh->b_folio, boff);
 	lock = nilfs_mdt_bgl_lock(inode, group);
 
 	if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap))
@@ -676,8 +714,8 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
 	else
 		nilfs_palloc_group_desc_add_entries(desc, lock, 1);
 
-	kunmap_local(bitmap_kaddr);
-	kunmap_local(desc_kaddr);
+	kunmap_local(bitmap);
+	kunmap_local(desc);
 
 	brelse(req->pr_bitmap_bh);
 	brelse(req->pr_desc_bh);
@@ -741,7 +779,7 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 	struct buffer_head *desc_bh, *bitmap_bh;
 	struct nilfs_palloc_group_desc *desc;
 	unsigned char *bitmap;
-	void *desc_kaddr, *bitmap_kaddr;
+	size_t doff, boff;
 	unsigned long group, group_offset;
 	__u64 group_min_nr, last_nrs[8];
 	const unsigned long epg = nilfs_palloc_entries_per_group(inode);
@@ -769,8 +807,8 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 		/* Get the first entry number of the group */
 		group_min_nr = (__u64)group * epg;
 
-		bitmap_kaddr = kmap_local_page(bitmap_bh->b_page);
-		bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
+		boff = nilfs_palloc_bitmap_offset(bitmap_bh);
+		bitmap = kmap_local_folio(bitmap_bh->b_folio, boff);
 		lock = nilfs_mdt_bgl_lock(inode, group);
 
 		j = i;
@@ -815,7 +853,7 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 			entry_start = rounddown(group_offset, epb);
 		} while (true);
 
-		kunmap_local(bitmap_kaddr);
+		kunmap_local(bitmap);
 		mark_buffer_dirty(bitmap_bh);
 		brelse(bitmap_bh);
 
@@ -829,11 +867,10 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 					   inode->i_ino);
 		}
 
-		desc_kaddr = kmap_local_page(desc_bh->b_page);
-		desc = nilfs_palloc_block_get_group_desc(
-			inode, group, desc_bh, desc_kaddr);
+		doff = nilfs_palloc_group_desc_offset(inode, group, desc_bh);
+		desc = kmap_local_folio(desc_bh->b_folio, doff);
 		nfree = nilfs_palloc_group_desc_add_entries(desc, lock, n);
-		kunmap_local(desc_kaddr);
+		kunmap_local(desc);
 		mark_buffer_dirty(desc_bh);
 		nilfs_mdt_mark_dirty(inode);
 		brelse(desc_bh);
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index e19d7eb10084b..af8f882619d41 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -33,6 +33,8 @@ int nilfs_palloc_get_entry_block(struct inode *, __u64, int,
 				 struct buffer_head **);
 void *nilfs_palloc_block_get_entry(const struct inode *, __u64,
 				   const struct buffer_head *, void *);
+size_t nilfs_palloc_entry_offset(const struct inode *inode, __u64 nr,
+				 const struct buffer_head *bh);
 
 int nilfs_palloc_count_max_entries(struct inode *, u64, u64 *);
 

From f99de3d5703a92cc18a9a95995b99b8401331bf7 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Thu, 24 Oct 2024 18:25:39 +0900
Subject: [PATCH 0914/1530] nilfs2: convert inode file to be folio-based

Convert the page-based implementation of ifile, a metadata file that
manages inodes, to folio-based.

Link: https://lkml.kernel.org/r/20241024092602.13395-6-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/ifile.c | 10 +++++-----
 fs/nilfs2/ifile.h |  4 ++--
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index 1e86b9303b7ca..e7339eb3c08a5 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -98,7 +98,7 @@ int nilfs_ifile_delete_inode(struct inode *ifile, ino_t ino)
 		.pr_entry_nr = ino, .pr_entry_bh = NULL
 	};
 	struct nilfs_inode *raw_inode;
-	void *kaddr;
+	size_t offset;
 	int ret;
 
 	ret = nilfs_palloc_prepare_free_entry(ifile, &req);
@@ -113,11 +113,11 @@ int nilfs_ifile_delete_inode(struct inode *ifile, ino_t ino)
 		return ret;
 	}
 
-	kaddr = kmap_local_page(req.pr_entry_bh->b_page);
-	raw_inode = nilfs_palloc_block_get_entry(ifile, req.pr_entry_nr,
-						 req.pr_entry_bh, kaddr);
+	offset = nilfs_palloc_entry_offset(ifile, req.pr_entry_nr,
+					   req.pr_entry_bh);
+	raw_inode = kmap_local_folio(req.pr_entry_bh->b_folio, offset);
 	raw_inode->i_flags = 0;
-	kunmap_local(kaddr);
+	kunmap_local(raw_inode);
 
 	mark_buffer_dirty(req.pr_entry_bh);
 	brelse(req.pr_entry_bh);
diff --git a/fs/nilfs2/ifile.h b/fs/nilfs2/ifile.h
index 625545cc2a989..5d116a566d9e4 100644
--- a/fs/nilfs2/ifile.h
+++ b/fs/nilfs2/ifile.h
@@ -21,9 +21,9 @@
 static inline struct nilfs_inode *
 nilfs_ifile_map_inode(struct inode *ifile, ino_t ino, struct buffer_head *ibh)
 {
-	void *kaddr = kmap_local_page(ibh->b_page);
+	size_t __offset_in_folio = nilfs_palloc_entry_offset(ifile, ino, ibh);
 
-	return nilfs_palloc_block_get_entry(ifile, ino, ibh, kaddr);
+	return kmap_local_folio(ibh->b_folio, __offset_in_folio);
 }
 
 static inline void nilfs_ifile_unmap_inode(struct nilfs_inode *raw_inode)

From aac6925e20e0e9476bc906f6bd83b6c508430d5a Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Thu, 24 Oct 2024 18:25:40 +0900
Subject: [PATCH 0915/1530] nilfs2: convert DAT file to be folio-based

Regarding the DAT, a metadata file that manages virtual block addresses,
convert the page-based implementation to a folio-based implementation.

Link: https://lkml.kernel.org/r/20241024092602.13395-7-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/dat.c | 98 ++++++++++++++++++++++++++-----------------------
 1 file changed, 52 insertions(+), 46 deletions(-)

diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index 0bef662176a4c..e220dcb08aa65 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -89,15 +89,15 @@ int nilfs_dat_prepare_alloc(struct inode *dat, struct nilfs_palloc_req *req)
 void nilfs_dat_commit_alloc(struct inode *dat, struct nilfs_palloc_req *req)
 {
 	struct nilfs_dat_entry *entry;
-	void *kaddr;
+	size_t offset;
 
-	kaddr = kmap_local_page(req->pr_entry_bh->b_page);
-	entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
-					     req->pr_entry_bh, kaddr);
+	offset = nilfs_palloc_entry_offset(dat, req->pr_entry_nr,
+					   req->pr_entry_bh);
+	entry = kmap_local_folio(req->pr_entry_bh->b_folio, offset);
 	entry->de_start = cpu_to_le64(NILFS_CNO_MIN);
 	entry->de_end = cpu_to_le64(NILFS_CNO_MAX);
 	entry->de_blocknr = cpu_to_le64(0);
-	kunmap_local(kaddr);
+	kunmap_local(entry);
 
 	nilfs_palloc_commit_alloc_entry(dat, req);
 	nilfs_dat_commit_entry(dat, req);
@@ -113,15 +113,15 @@ static void nilfs_dat_commit_free(struct inode *dat,
 				  struct nilfs_palloc_req *req)
 {
 	struct nilfs_dat_entry *entry;
-	void *kaddr;
+	size_t offset;
 
-	kaddr = kmap_local_page(req->pr_entry_bh->b_page);
-	entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
-					     req->pr_entry_bh, kaddr);
+	offset = nilfs_palloc_entry_offset(dat, req->pr_entry_nr,
+					   req->pr_entry_bh);
+	entry = kmap_local_folio(req->pr_entry_bh->b_folio, offset);
 	entry->de_start = cpu_to_le64(NILFS_CNO_MIN);
 	entry->de_end = cpu_to_le64(NILFS_CNO_MIN);
 	entry->de_blocknr = cpu_to_le64(0);
-	kunmap_local(kaddr);
+	kunmap_local(entry);
 
 	nilfs_dat_commit_entry(dat, req);
 
@@ -143,14 +143,14 @@ void nilfs_dat_commit_start(struct inode *dat, struct nilfs_palloc_req *req,
 			    sector_t blocknr)
 {
 	struct nilfs_dat_entry *entry;
-	void *kaddr;
+	size_t offset;
 
-	kaddr = kmap_local_page(req->pr_entry_bh->b_page);
-	entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
-					     req->pr_entry_bh, kaddr);
+	offset = nilfs_palloc_entry_offset(dat, req->pr_entry_nr,
+					   req->pr_entry_bh);
+	entry = kmap_local_folio(req->pr_entry_bh->b_folio, offset);
 	entry->de_start = cpu_to_le64(nilfs_mdt_cno(dat));
 	entry->de_blocknr = cpu_to_le64(blocknr);
-	kunmap_local(kaddr);
+	kunmap_local(entry);
 
 	nilfs_dat_commit_entry(dat, req);
 }
@@ -160,19 +160,19 @@ int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req)
 	struct nilfs_dat_entry *entry;
 	__u64 start;
 	sector_t blocknr;
-	void *kaddr;
+	size_t offset;
 	int ret;
 
 	ret = nilfs_dat_prepare_entry(dat, req, 0);
 	if (ret < 0)
 		return ret;
 
-	kaddr = kmap_local_page(req->pr_entry_bh->b_page);
-	entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
-					     req->pr_entry_bh, kaddr);
+	offset = nilfs_palloc_entry_offset(dat, req->pr_entry_nr,
+					   req->pr_entry_bh);
+	entry = kmap_local_folio(req->pr_entry_bh->b_folio, offset);
 	start = le64_to_cpu(entry->de_start);
 	blocknr = le64_to_cpu(entry->de_blocknr);
-	kunmap_local(kaddr);
+	kunmap_local(entry);
 
 	if (blocknr == 0) {
 		ret = nilfs_palloc_prepare_free_entry(dat, req);
@@ -200,11 +200,11 @@ void nilfs_dat_commit_end(struct inode *dat, struct nilfs_palloc_req *req,
 	struct nilfs_dat_entry *entry;
 	__u64 start, end;
 	sector_t blocknr;
-	void *kaddr;
+	size_t offset;
 
-	kaddr = kmap_local_page(req->pr_entry_bh->b_page);
-	entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
-					     req->pr_entry_bh, kaddr);
+	offset = nilfs_palloc_entry_offset(dat, req->pr_entry_nr,
+					   req->pr_entry_bh);
+	entry = kmap_local_folio(req->pr_entry_bh->b_folio, offset);
 	end = start = le64_to_cpu(entry->de_start);
 	if (!dead) {
 		end = nilfs_mdt_cno(dat);
@@ -212,7 +212,7 @@ void nilfs_dat_commit_end(struct inode *dat, struct nilfs_palloc_req *req,
 	}
 	entry->de_end = cpu_to_le64(end);
 	blocknr = le64_to_cpu(entry->de_blocknr);
-	kunmap_local(kaddr);
+	kunmap_local(entry);
 
 	if (blocknr == 0)
 		nilfs_dat_commit_free(dat, req);
@@ -225,14 +225,14 @@ void nilfs_dat_abort_end(struct inode *dat, struct nilfs_palloc_req *req)
 	struct nilfs_dat_entry *entry;
 	__u64 start;
 	sector_t blocknr;
-	void *kaddr;
+	size_t offset;
 
-	kaddr = kmap_local_page(req->pr_entry_bh->b_page);
-	entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
-					     req->pr_entry_bh, kaddr);
+	offset = nilfs_palloc_entry_offset(dat, req->pr_entry_nr,
+					   req->pr_entry_bh);
+	entry = kmap_local_folio(req->pr_entry_bh->b_folio, offset);
 	start = le64_to_cpu(entry->de_start);
 	blocknr = le64_to_cpu(entry->de_blocknr);
-	kunmap_local(kaddr);
+	kunmap_local(entry);
 
 	if (start == nilfs_mdt_cno(dat) && blocknr == 0)
 		nilfs_palloc_abort_free_entry(dat, req);
@@ -336,7 +336,7 @@ int nilfs_dat_move(struct inode *dat, __u64 vblocknr, sector_t blocknr)
 {
 	struct buffer_head *entry_bh;
 	struct nilfs_dat_entry *entry;
-	void *kaddr;
+	size_t offset;
 	int ret;
 
 	ret = nilfs_palloc_get_entry_block(dat, vblocknr, 0, &entry_bh);
@@ -359,21 +359,21 @@ int nilfs_dat_move(struct inode *dat, __u64 vblocknr, sector_t blocknr)
 		}
 	}
 
-	kaddr = kmap_local_page(entry_bh->b_page);
-	entry = nilfs_palloc_block_get_entry(dat, vblocknr, entry_bh, kaddr);
+	offset = nilfs_palloc_entry_offset(dat, vblocknr, entry_bh);
+	entry = kmap_local_folio(entry_bh->b_folio, offset);
 	if (unlikely(entry->de_blocknr == cpu_to_le64(0))) {
 		nilfs_crit(dat->i_sb,
 			   "%s: invalid vblocknr = %llu, [%llu, %llu)",
 			   __func__, (unsigned long long)vblocknr,
 			   (unsigned long long)le64_to_cpu(entry->de_start),
 			   (unsigned long long)le64_to_cpu(entry->de_end));
-		kunmap_local(kaddr);
+		kunmap_local(entry);
 		brelse(entry_bh);
 		return -EINVAL;
 	}
 	WARN_ON(blocknr == 0);
 	entry->de_blocknr = cpu_to_le64(blocknr);
-	kunmap_local(kaddr);
+	kunmap_local(entry);
 
 	mark_buffer_dirty(entry_bh);
 	nilfs_mdt_mark_dirty(dat);
@@ -407,7 +407,7 @@ int nilfs_dat_translate(struct inode *dat, __u64 vblocknr, sector_t *blocknrp)
 	struct buffer_head *entry_bh, *bh;
 	struct nilfs_dat_entry *entry;
 	sector_t blocknr;
-	void *kaddr;
+	size_t offset;
 	int ret;
 
 	ret = nilfs_palloc_get_entry_block(dat, vblocknr, 0, &entry_bh);
@@ -423,8 +423,8 @@ int nilfs_dat_translate(struct inode *dat, __u64 vblocknr, sector_t *blocknrp)
 		}
 	}
 
-	kaddr = kmap_local_page(entry_bh->b_page);
-	entry = nilfs_palloc_block_get_entry(dat, vblocknr, entry_bh, kaddr);
+	offset = nilfs_palloc_entry_offset(dat, vblocknr, entry_bh);
+	entry = kmap_local_folio(entry_bh->b_folio, offset);
 	blocknr = le64_to_cpu(entry->de_blocknr);
 	if (blocknr == 0) {
 		ret = -ENOENT;
@@ -433,7 +433,7 @@ int nilfs_dat_translate(struct inode *dat, __u64 vblocknr, sector_t *blocknrp)
 	*blocknrp = blocknr;
 
  out:
-	kunmap_local(kaddr);
+	kunmap_local(entry);
 	brelse(entry_bh);
 	return ret;
 }
@@ -442,11 +442,12 @@ ssize_t nilfs_dat_get_vinfo(struct inode *dat, void *buf, unsigned int visz,
 			    size_t nvi)
 {
 	struct buffer_head *entry_bh;
-	struct nilfs_dat_entry *entry;
+	struct nilfs_dat_entry *entry, *first_entry;
 	struct nilfs_vinfo *vinfo = buf;
 	__u64 first, last;
-	void *kaddr;
+	size_t offset;
 	unsigned long entries_per_block = NILFS_MDT(dat)->mi_entries_per_block;
+	unsigned int entry_size = NILFS_MDT(dat)->mi_entry_size;
 	int i, j, n, ret;
 
 	for (i = 0; i < nvi; i += n) {
@@ -454,23 +455,28 @@ ssize_t nilfs_dat_get_vinfo(struct inode *dat, void *buf, unsigned int visz,
 						   0, &entry_bh);
 		if (ret < 0)
 			return ret;
-		kaddr = kmap_local_page(entry_bh->b_page);
-		/* last virtual block number in this block */
+
 		first = vinfo->vi_vblocknr;
 		first = div64_ul(first, entries_per_block);
 		first *= entries_per_block;
+		/* first virtual block number in this block */
+
 		last = first + entries_per_block - 1;
+		/* last virtual block number in this block */
+
+		offset = nilfs_palloc_entry_offset(dat, first, entry_bh);
+		first_entry = kmap_local_folio(entry_bh->b_folio, offset);
 		for (j = i, n = 0;
 		     j < nvi && vinfo->vi_vblocknr >= first &&
 			     vinfo->vi_vblocknr <= last;
 		     j++, n++, vinfo = (void *)vinfo + visz) {
-			entry = nilfs_palloc_block_get_entry(
-				dat, vinfo->vi_vblocknr, entry_bh, kaddr);
+			entry = (void *)first_entry +
+				(vinfo->vi_vblocknr - first) * entry_size;
 			vinfo->vi_start = le64_to_cpu(entry->de_start);
 			vinfo->vi_end = le64_to_cpu(entry->de_end);
 			vinfo->vi_blocknr = le64_to_cpu(entry->de_blocknr);
 		}
-		kunmap_local(kaddr);
+		kunmap_local(first_entry);
 		brelse(entry_bh);
 	}
 

From cdee17960f67d1dad0738ef3ae9f1a63d3c92138 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Thu, 24 Oct 2024 18:25:41 +0900
Subject: [PATCH 0916/1530] nilfs2: remove nilfs_palloc_block_get_entry()

All calls to nilfs_palloc_block_get_entry() are now gone, so remove it.

Link: https://lkml.kernel.org/r/20241024092602.13395-8-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/alloc.c | 19 -------------------
 fs/nilfs2/alloc.h |  2 --
 2 files changed, 21 deletions(-)

diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 5e0a6bd3e0159..ba3e1f591f369 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -390,25 +390,6 @@ size_t nilfs_palloc_entry_offset(const struct inode *inode, __u64 nr,
 		entry_index_in_block * NILFS_MDT(inode)->mi_entry_size;
 }
 
-/**
- * nilfs_palloc_block_get_entry - get kernel address of an entry
- * @inode: inode of metadata file using this allocator
- * @nr: serial number of the entry (e.g. inode number)
- * @bh: buffer head of the buffer storing the entry block
- * @kaddr: kernel address mapped for the page including the buffer
- */
-void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr,
-				   const struct buffer_head *bh, void *kaddr)
-{
-	unsigned long entry_offset, group_offset;
-
-	nilfs_palloc_group(inode, nr, &group_offset);
-	entry_offset = group_offset % NILFS_MDT(inode)->mi_entries_per_block;
-
-	return kaddr + bh_offset(bh) +
-		entry_offset * NILFS_MDT(inode)->mi_entry_size;
-}
-
 /**
  * nilfs_palloc_find_available_slot - find available slot in a group
  * @bitmap: bitmap of the group
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index af8f882619d41..3f115ab7e9a76 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -31,8 +31,6 @@ nilfs_palloc_entries_per_group(const struct inode *inode)
 int nilfs_palloc_init_blockgroup(struct inode *, unsigned int);
 int nilfs_palloc_get_entry_block(struct inode *, __u64, int,
 				 struct buffer_head **);
-void *nilfs_palloc_block_get_entry(const struct inode *, __u64,
-				   const struct buffer_head *, void *);
 size_t nilfs_palloc_entry_offset(const struct inode *inode, __u64 nr,
 				 const struct buffer_head *bh);
 

From a6cb5b1e9c707c3a43ede691c7faee45e796458b Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Thu, 24 Oct 2024 18:25:42 +0900
Subject: [PATCH 0917/1530] nilfs2: convert checkpoint file to be folio-based

Regarding the cpfile, a metadata file that manages checkpoints, convert
the page-based implementation to a folio-based implementation.

This change involves some helper functions to calculate byte offsets on
folios and removing a few helper functions that are no longer needed.

Link: https://lkml.kernel.org/r/20241024092602.13395-9-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/cpfile.c | 379 ++++++++++++++++++++++++---------------------
 1 file changed, 204 insertions(+), 175 deletions(-)

diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index a8046cbf27534..c20207d7a9890 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -68,49 +68,36 @@ static inline int nilfs_cpfile_is_in_first(const struct inode *cpfile,
 static unsigned int
 nilfs_cpfile_block_add_valid_checkpoints(const struct inode *cpfile,
 					 struct buffer_head *bh,
-					 void *kaddr,
 					 unsigned int n)
 {
-	struct nilfs_checkpoint *cp = kaddr + bh_offset(bh);
+	struct nilfs_checkpoint *cp;
 	unsigned int count;
 
+	cp = kmap_local_folio(bh->b_folio,
+			      offset_in_folio(bh->b_folio, bh->b_data));
 	count = le32_to_cpu(cp->cp_checkpoints_count) + n;
 	cp->cp_checkpoints_count = cpu_to_le32(count);
+	kunmap_local(cp);
 	return count;
 }
 
 static unsigned int
 nilfs_cpfile_block_sub_valid_checkpoints(const struct inode *cpfile,
 					 struct buffer_head *bh,
-					 void *kaddr,
 					 unsigned int n)
 {
-	struct nilfs_checkpoint *cp = kaddr + bh_offset(bh);
+	struct nilfs_checkpoint *cp;
 	unsigned int count;
 
+	cp = kmap_local_folio(bh->b_folio,
+			      offset_in_folio(bh->b_folio, bh->b_data));
 	WARN_ON(le32_to_cpu(cp->cp_checkpoints_count) < n);
 	count = le32_to_cpu(cp->cp_checkpoints_count) - n;
 	cp->cp_checkpoints_count = cpu_to_le32(count);
+	kunmap_local(cp);
 	return count;
 }
 
-static inline struct nilfs_cpfile_header *
-nilfs_cpfile_block_get_header(const struct inode *cpfile,
-			      struct buffer_head *bh,
-			      void *kaddr)
-{
-	return kaddr + bh_offset(bh);
-}
-
-static struct nilfs_checkpoint *
-nilfs_cpfile_block_get_checkpoint(const struct inode *cpfile, __u64 cno,
-				  struct buffer_head *bh,
-				  void *kaddr)
-{
-	return kaddr + bh_offset(bh) + nilfs_cpfile_get_offset(cpfile, cno) *
-		NILFS_MDT(cpfile)->mi_entry_size;
-}
-
 static void nilfs_cpfile_block_init(struct inode *cpfile,
 				    struct buffer_head *bh,
 				    void *from)
@@ -125,6 +112,54 @@ static void nilfs_cpfile_block_init(struct inode *cpfile,
 	}
 }
 
+/**
+ * nilfs_cpfile_checkpoint_offset - calculate the byte offset of a checkpoint
+ *                                  entry in the folio containing it
+ * @cpfile: checkpoint file inode
+ * @cno:    checkpoint number
+ * @bh:     buffer head of block containing checkpoint indexed by @cno
+ *
+ * Return: Byte offset in the folio of the checkpoint specified by @cno.
+ */
+static size_t nilfs_cpfile_checkpoint_offset(const struct inode *cpfile,
+					     __u64 cno,
+					     struct buffer_head *bh)
+{
+	return offset_in_folio(bh->b_folio, bh->b_data) +
+		nilfs_cpfile_get_offset(cpfile, cno) *
+		NILFS_MDT(cpfile)->mi_entry_size;
+}
+
+/**
+ * nilfs_cpfile_cp_snapshot_list_offset - calculate the byte offset of a
+ *                                        checkpoint snapshot list in the folio
+ *                                        containing it
+ * @cpfile: checkpoint file inode
+ * @cno:    checkpoint number
+ * @bh:     buffer head of block containing checkpoint indexed by @cno
+ *
+ * Return: Byte offset in the folio of the checkpoint snapshot list specified
+ *         by @cno.
+ */
+static size_t nilfs_cpfile_cp_snapshot_list_offset(const struct inode *cpfile,
+						   __u64 cno,
+						   struct buffer_head *bh)
+{
+	return nilfs_cpfile_checkpoint_offset(cpfile, cno, bh) +
+		offsetof(struct nilfs_checkpoint, cp_snapshot_list);
+}
+
+/**
+ * nilfs_cpfile_ch_snapshot_list_offset - calculate the byte offset of the
+ *                                        snapshot list in the header
+ *
+ * Return: Byte offset in the folio of the checkpoint snapshot list
+ */
+static size_t nilfs_cpfile_ch_snapshot_list_offset(void)
+{
+	return offsetof(struct nilfs_cpfile_header, ch_snapshot_list);
+}
+
 static int nilfs_cpfile_get_header_block(struct inode *cpfile,
 					 struct buffer_head **bhp)
 {
@@ -214,7 +249,7 @@ int nilfs_cpfile_read_checkpoint(struct inode *cpfile, __u64 cno,
 {
 	struct buffer_head *cp_bh;
 	struct nilfs_checkpoint *cp;
-	void *kaddr;
+	size_t offset;
 	int ret;
 
 	if (cno < 1 || cno > nilfs_mdt_cno(cpfile))
@@ -228,8 +263,8 @@ int nilfs_cpfile_read_checkpoint(struct inode *cpfile, __u64 cno,
 		goto out_sem;
 	}
 
-	kaddr = kmap_local_page(cp_bh->b_page);
-	cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
+	offset = nilfs_cpfile_checkpoint_offset(cpfile, cno, cp_bh);
+	cp = kmap_local_folio(cp_bh->b_folio, offset);
 	if (nilfs_checkpoint_invalid(cp)) {
 		ret = -EINVAL;
 		goto put_cp;
@@ -254,7 +289,7 @@ int nilfs_cpfile_read_checkpoint(struct inode *cpfile, __u64 cno,
 	root->ifile = ifile;
 
 put_cp:
-	kunmap_local(kaddr);
+	kunmap_local(cp);
 	brelse(cp_bh);
 out_sem:
 	up_read(&NILFS_MDT(cpfile)->mi_sem);
@@ -282,7 +317,7 @@ int nilfs_cpfile_create_checkpoint(struct inode *cpfile, __u64 cno)
 	struct buffer_head *header_bh, *cp_bh;
 	struct nilfs_cpfile_header *header;
 	struct nilfs_checkpoint *cp;
-	void *kaddr;
+	size_t offset;
 	int ret;
 
 	if (WARN_ON_ONCE(cno < 1))
@@ -297,24 +332,22 @@ int nilfs_cpfile_create_checkpoint(struct inode *cpfile, __u64 cno)
 	if (unlikely(ret < 0))
 		goto out_header;
 
-	kaddr = kmap_local_page(cp_bh->b_page);
-	cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
+	offset = nilfs_cpfile_checkpoint_offset(cpfile, cno, cp_bh);
+	cp = kmap_local_folio(cp_bh->b_folio, offset);
 	if (nilfs_checkpoint_invalid(cp)) {
 		/* a newly-created checkpoint */
 		nilfs_checkpoint_clear_invalid(cp);
+		kunmap_local(cp);
 		if (!nilfs_cpfile_is_in_first(cpfile, cno))
 			nilfs_cpfile_block_add_valid_checkpoints(cpfile, cp_bh,
-								 kaddr, 1);
-		kunmap_local(kaddr);
+								 1);
 
-		kaddr = kmap_local_page(header_bh->b_page);
-		header = nilfs_cpfile_block_get_header(cpfile, header_bh,
-						       kaddr);
+		header = kmap_local_folio(header_bh->b_folio, 0);
 		le64_add_cpu(&header->ch_ncheckpoints, 1);
-		kunmap_local(kaddr);
+		kunmap_local(header);
 		mark_buffer_dirty(header_bh);
 	} else {
-		kunmap_local(kaddr);
+		kunmap_local(cp);
 	}
 
 	/* Force the buffer and the inode to become dirty */
@@ -353,7 +386,7 @@ int nilfs_cpfile_finalize_checkpoint(struct inode *cpfile, __u64 cno,
 {
 	struct buffer_head *cp_bh;
 	struct nilfs_checkpoint *cp;
-	void *kaddr;
+	size_t offset;
 	int ret;
 
 	if (WARN_ON_ONCE(cno < 1))
@@ -367,10 +400,10 @@ int nilfs_cpfile_finalize_checkpoint(struct inode *cpfile, __u64 cno,
 		goto out_sem;
 	}
 
-	kaddr = kmap_local_page(cp_bh->b_page);
-	cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
+	offset = nilfs_cpfile_checkpoint_offset(cpfile, cno, cp_bh);
+	cp = kmap_local_folio(cp_bh->b_folio, offset);
 	if (unlikely(nilfs_checkpoint_invalid(cp))) {
-		kunmap_local(kaddr);
+		kunmap_local(cp);
 		brelse(cp_bh);
 		goto error;
 	}
@@ -391,7 +424,7 @@ int nilfs_cpfile_finalize_checkpoint(struct inode *cpfile, __u64 cno,
 	nilfs_write_inode_common(root->ifile, &cp->cp_ifile_inode);
 	nilfs_bmap_write(NILFS_I(root->ifile)->i_bmap, &cp->cp_ifile_inode);
 
-	kunmap_local(kaddr);
+	kunmap_local(cp);
 	brelse(cp_bh);
 out_sem:
 	up_write(&NILFS_MDT(cpfile)->mi_sem);
@@ -432,6 +465,7 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
 	struct nilfs_checkpoint *cp;
 	size_t cpsz = NILFS_MDT(cpfile)->mi_entry_size;
 	__u64 cno;
+	size_t offset;
 	void *kaddr;
 	unsigned long tnicps;
 	int ret, ncps, nicps, nss, count, i;
@@ -462,9 +496,8 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
 			continue;
 		}
 
-		kaddr = kmap_local_page(cp_bh->b_page);
-		cp = nilfs_cpfile_block_get_checkpoint(
-			cpfile, cno, cp_bh, kaddr);
+		offset = nilfs_cpfile_checkpoint_offset(cpfile, cno, cp_bh);
+		cp = kaddr = kmap_local_folio(cp_bh->b_folio, offset);
 		nicps = 0;
 		for (i = 0; i < ncps; i++, cp = (void *)cp + cpsz) {
 			if (nilfs_checkpoint_snapshot(cp)) {
@@ -474,43 +507,42 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
 				nicps++;
 			}
 		}
-		if (nicps > 0) {
-			tnicps += nicps;
-			mark_buffer_dirty(cp_bh);
-			nilfs_mdt_mark_dirty(cpfile);
-			if (!nilfs_cpfile_is_in_first(cpfile, cno)) {
-				count =
-				  nilfs_cpfile_block_sub_valid_checkpoints(
-						cpfile, cp_bh, kaddr, nicps);
-				if (count == 0) {
-					/* make hole */
-					kunmap_local(kaddr);
-					brelse(cp_bh);
-					ret =
-					  nilfs_cpfile_delete_checkpoint_block(
-								   cpfile, cno);
-					if (ret == 0)
-						continue;
-					nilfs_err(cpfile->i_sb,
-						  "error %d deleting checkpoint block",
-						  ret);
-					break;
-				}
-			}
+		kunmap_local(kaddr);
+
+		if (nicps <= 0) {
+			brelse(cp_bh);
+			continue;
 		}
 
-		kunmap_local(kaddr);
+		tnicps += nicps;
+		mark_buffer_dirty(cp_bh);
+		nilfs_mdt_mark_dirty(cpfile);
+		if (nilfs_cpfile_is_in_first(cpfile, cno)) {
+			brelse(cp_bh);
+			continue;
+		}
+
+		count = nilfs_cpfile_block_sub_valid_checkpoints(cpfile, cp_bh,
+								 nicps);
 		brelse(cp_bh);
+		if (count)
+			continue;
+
+		/* Delete the block if there are no more valid checkpoints */
+		ret = nilfs_cpfile_delete_checkpoint_block(cpfile, cno);
+		if (unlikely(ret)) {
+			nilfs_err(cpfile->i_sb,
+				  "error %d deleting checkpoint block", ret);
+			break;
+		}
 	}
 
 	if (tnicps > 0) {
-		kaddr = kmap_local_page(header_bh->b_page);
-		header = nilfs_cpfile_block_get_header(cpfile, header_bh,
-						       kaddr);
+		header = kmap_local_folio(header_bh->b_folio, 0);
 		le64_add_cpu(&header->ch_ncheckpoints, -(u64)tnicps);
 		mark_buffer_dirty(header_bh);
 		nilfs_mdt_mark_dirty(cpfile);
-		kunmap_local(kaddr);
+		kunmap_local(header);
 	}
 
 	brelse(header_bh);
@@ -544,6 +576,7 @@ static ssize_t nilfs_cpfile_do_get_cpinfo(struct inode *cpfile, __u64 *cnop,
 	struct buffer_head *bh;
 	size_t cpsz = NILFS_MDT(cpfile)->mi_entry_size;
 	__u64 cur_cno = nilfs_mdt_cno(cpfile), cno = *cnop;
+	size_t offset;
 	void *kaddr;
 	int n, ret;
 	int ncps, i;
@@ -562,8 +595,8 @@ static ssize_t nilfs_cpfile_do_get_cpinfo(struct inode *cpfile, __u64 *cnop,
 		}
 		ncps = nilfs_cpfile_checkpoints_in_block(cpfile, cno, cur_cno);
 
-		kaddr = kmap_local_page(bh->b_page);
-		cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, bh, kaddr);
+		offset = nilfs_cpfile_checkpoint_offset(cpfile, cno, bh);
+		cp = kaddr = kmap_local_folio(bh->b_folio, offset);
 		for (i = 0; i < ncps && n < nci; i++, cp = (void *)cp + cpsz) {
 			if (!nilfs_checkpoint_invalid(cp)) {
 				nilfs_cpfile_checkpoint_to_cpinfo(cpfile, cp,
@@ -597,7 +630,7 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
 	struct nilfs_cpinfo *ci = buf;
 	__u64 curr = *cnop, next;
 	unsigned long curr_blkoff, next_blkoff;
-	void *kaddr;
+	size_t offset;
 	int n = 0, ret;
 
 	down_read(&NILFS_MDT(cpfile)->mi_sem);
@@ -606,10 +639,9 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
 		ret = nilfs_cpfile_get_header_block(cpfile, &bh);
 		if (ret < 0)
 			goto out;
-		kaddr = kmap_local_page(bh->b_page);
-		header = nilfs_cpfile_block_get_header(cpfile, bh, kaddr);
+		header = kmap_local_folio(bh->b_folio, 0);
 		curr = le64_to_cpu(header->ch_snapshot_list.ssl_next);
-		kunmap_local(kaddr);
+		kunmap_local(header);
 		brelse(bh);
 		if (curr == 0) {
 			ret = 0;
@@ -627,9 +659,9 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
 			ret = 0; /* No snapshots (started from a hole block) */
 		goto out;
 	}
-	kaddr = kmap_local_page(bh->b_page);
+	offset = nilfs_cpfile_checkpoint_offset(cpfile, curr, bh);
+	cp = kmap_local_folio(bh->b_folio, offset);
 	while (n < nci) {
-		cp = nilfs_cpfile_block_get_checkpoint(cpfile, curr, bh, kaddr);
 		curr = ~(__u64)0; /* Terminator */
 		if (unlikely(nilfs_checkpoint_invalid(cp) ||
 			     !nilfs_checkpoint_snapshot(cp)))
@@ -641,9 +673,9 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
 		if (next == 0)
 			break; /* reach end of the snapshot list */
 
+		kunmap_local(cp);
 		next_blkoff = nilfs_cpfile_get_blkoff(cpfile, next);
 		if (curr_blkoff != next_blkoff) {
-			kunmap_local(kaddr);
 			brelse(bh);
 			ret = nilfs_cpfile_get_checkpoint_block(cpfile, next,
 								0, &bh);
@@ -651,12 +683,13 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
 				WARN_ON(ret == -ENOENT);
 				goto out;
 			}
-			kaddr = kmap_local_page(bh->b_page);
 		}
+		offset = nilfs_cpfile_checkpoint_offset(cpfile, next, bh);
+		cp = kmap_local_folio(bh->b_folio, offset);
 		curr = next;
 		curr_blkoff = next_blkoff;
 	}
-	kunmap_local(kaddr);
+	kunmap_local(cp);
 	brelse(bh);
 	*cnop = curr;
 	ret = n;
@@ -733,26 +766,6 @@ int nilfs_cpfile_delete_checkpoint(struct inode *cpfile, __u64 cno)
 	return nilfs_cpfile_delete_checkpoints(cpfile, cno, cno + 1);
 }
 
-static struct nilfs_snapshot_list *
-nilfs_cpfile_block_get_snapshot_list(const struct inode *cpfile,
-				     __u64 cno,
-				     struct buffer_head *bh,
-				     void *kaddr)
-{
-	struct nilfs_cpfile_header *header;
-	struct nilfs_checkpoint *cp;
-	struct nilfs_snapshot_list *list;
-
-	if (cno != 0) {
-		cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, bh, kaddr);
-		list = &cp->cp_snapshot_list;
-	} else {
-		header = nilfs_cpfile_block_get_header(cpfile, bh, kaddr);
-		list = &header->ch_snapshot_list;
-	}
-	return list;
-}
-
 static int nilfs_cpfile_set_snapshot(struct inode *cpfile, __u64 cno)
 {
 	struct buffer_head *header_bh, *curr_bh, *prev_bh, *cp_bh;
@@ -761,94 +774,103 @@ static int nilfs_cpfile_set_snapshot(struct inode *cpfile, __u64 cno)
 	struct nilfs_snapshot_list *list;
 	__u64 curr, prev;
 	unsigned long curr_blkoff, prev_blkoff;
-	void *kaddr;
+	size_t offset, curr_list_offset, prev_list_offset;
 	int ret;
 
 	if (cno == 0)
 		return -ENOENT; /* checkpoint number 0 is invalid */
 	down_write(&NILFS_MDT(cpfile)->mi_sem);
 
+	ret = nilfs_cpfile_get_header_block(cpfile, &header_bh);
+	if (unlikely(ret < 0))
+		goto out_sem;
+
 	ret = nilfs_cpfile_get_checkpoint_block(cpfile, cno, 0, &cp_bh);
 	if (ret < 0)
-		goto out_sem;
-	kaddr = kmap_local_page(cp_bh->b_page);
-	cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
+		goto out_header;
+
+	offset = nilfs_cpfile_checkpoint_offset(cpfile, cno, cp_bh);
+	cp = kmap_local_folio(cp_bh->b_folio, offset);
 	if (nilfs_checkpoint_invalid(cp)) {
 		ret = -ENOENT;
-		kunmap_local(kaddr);
+		kunmap_local(cp);
 		goto out_cp;
 	}
 	if (nilfs_checkpoint_snapshot(cp)) {
 		ret = 0;
-		kunmap_local(kaddr);
+		kunmap_local(cp);
 		goto out_cp;
 	}
-	kunmap_local(kaddr);
+	kunmap_local(cp);
 
-	ret = nilfs_cpfile_get_header_block(cpfile, &header_bh);
-	if (ret < 0)
-		goto out_cp;
-	kaddr = kmap_local_page(header_bh->b_page);
-	header = nilfs_cpfile_block_get_header(cpfile, header_bh, kaddr);
+	/*
+	 * Find the last snapshot before the checkpoint being changed to
+	 * snapshot mode by going backwards through the snapshot list.
+	 * Set "prev" to its checkpoint number, or 0 if not found.
+	 */
+	header = kmap_local_folio(header_bh->b_folio, 0);
 	list = &header->ch_snapshot_list;
 	curr_bh = header_bh;
 	get_bh(curr_bh);
 	curr = 0;
 	curr_blkoff = 0;
+	curr_list_offset = nilfs_cpfile_ch_snapshot_list_offset();
 	prev = le64_to_cpu(list->ssl_prev);
 	while (prev > cno) {
 		prev_blkoff = nilfs_cpfile_get_blkoff(cpfile, prev);
 		curr = prev;
+		kunmap_local(list);
 		if (curr_blkoff != prev_blkoff) {
-			kunmap_local(kaddr);
 			brelse(curr_bh);
 			ret = nilfs_cpfile_get_checkpoint_block(cpfile, curr,
 								0, &curr_bh);
-			if (ret < 0)
-				goto out_header;
-			kaddr = kmap_local_page(curr_bh->b_page);
+			if (unlikely(ret < 0))
+				goto out_cp;
 		}
+		curr_list_offset = nilfs_cpfile_cp_snapshot_list_offset(
+			cpfile, curr, curr_bh);
+		list = kmap_local_folio(curr_bh->b_folio, curr_list_offset);
 		curr_blkoff = prev_blkoff;
-		cp = nilfs_cpfile_block_get_checkpoint(
-			cpfile, curr, curr_bh, kaddr);
-		list = &cp->cp_snapshot_list;
 		prev = le64_to_cpu(list->ssl_prev);
 	}
-	kunmap_local(kaddr);
+	kunmap_local(list);
 
 	if (prev != 0) {
 		ret = nilfs_cpfile_get_checkpoint_block(cpfile, prev, 0,
 							&prev_bh);
 		if (ret < 0)
 			goto out_curr;
+
+		prev_list_offset = nilfs_cpfile_cp_snapshot_list_offset(
+			cpfile, prev, prev_bh);
 	} else {
 		prev_bh = header_bh;
 		get_bh(prev_bh);
+		prev_list_offset = nilfs_cpfile_ch_snapshot_list_offset();
 	}
 
-	kaddr = kmap_local_page(curr_bh->b_page);
-	list = nilfs_cpfile_block_get_snapshot_list(
-		cpfile, curr, curr_bh, kaddr);
+	/* Update the list entry for the next snapshot */
+	list = kmap_local_folio(curr_bh->b_folio, curr_list_offset);
 	list->ssl_prev = cpu_to_le64(cno);
-	kunmap_local(kaddr);
+	kunmap_local(list);
 
-	kaddr = kmap_local_page(cp_bh->b_page);
-	cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
+	/* Update the checkpoint being changed to a snapshot */
+	offset = nilfs_cpfile_checkpoint_offset(cpfile, cno, cp_bh);
+	cp = kmap_local_folio(cp_bh->b_folio, offset);
 	cp->cp_snapshot_list.ssl_next = cpu_to_le64(curr);
 	cp->cp_snapshot_list.ssl_prev = cpu_to_le64(prev);
 	nilfs_checkpoint_set_snapshot(cp);
-	kunmap_local(kaddr);
+	kunmap_local(cp);
 
-	kaddr = kmap_local_page(prev_bh->b_page);
-	list = nilfs_cpfile_block_get_snapshot_list(
-		cpfile, prev, prev_bh, kaddr);
+	/* Update the list entry for the previous snapshot */
+	list = kmap_local_folio(prev_bh->b_folio, prev_list_offset);
 	list->ssl_next = cpu_to_le64(cno);
-	kunmap_local(kaddr);
+	kunmap_local(list);
 
-	kaddr = kmap_local_page(header_bh->b_page);
-	header = nilfs_cpfile_block_get_header(cpfile, header_bh, kaddr);
+	/* Update the statistics in the header */
+	header = kmap_local_folio(header_bh->b_folio, 0);
 	le64_add_cpu(&header->ch_nsnapshots, 1);
-	kunmap_local(kaddr);
+	kunmap_local(header);
 
 	mark_buffer_dirty(prev_bh);
 	mark_buffer_dirty(curr_bh);
@@ -861,12 +883,12 @@ static int nilfs_cpfile_set_snapshot(struct inode *cpfile, __u64 cno)
  out_curr:
 	brelse(curr_bh);
 
- out_header:
-	brelse(header_bh);
-
  out_cp:
 	brelse(cp_bh);
 
+ out_header:
+	brelse(header_bh);
+
  out_sem:
 	up_write(&NILFS_MDT(cpfile)->mi_sem);
 	return ret;
@@ -879,79 +901,87 @@ static int nilfs_cpfile_clear_snapshot(struct inode *cpfile, __u64 cno)
 	struct nilfs_checkpoint *cp;
 	struct nilfs_snapshot_list *list;
 	__u64 next, prev;
-	void *kaddr;
+	size_t offset, next_list_offset, prev_list_offset;
 	int ret;
 
 	if (cno == 0)
 		return -ENOENT; /* checkpoint number 0 is invalid */
 	down_write(&NILFS_MDT(cpfile)->mi_sem);
 
+	ret = nilfs_cpfile_get_header_block(cpfile, &header_bh);
+	if (unlikely(ret < 0))
+		goto out_sem;
+
 	ret = nilfs_cpfile_get_checkpoint_block(cpfile, cno, 0, &cp_bh);
 	if (ret < 0)
-		goto out_sem;
-	kaddr = kmap_local_page(cp_bh->b_page);
-	cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
+		goto out_header;
+
+	offset = nilfs_cpfile_checkpoint_offset(cpfile, cno, cp_bh);
+	cp = kmap_local_folio(cp_bh->b_folio, offset);
 	if (nilfs_checkpoint_invalid(cp)) {
 		ret = -ENOENT;
-		kunmap_local(kaddr);
+		kunmap_local(cp);
 		goto out_cp;
 	}
 	if (!nilfs_checkpoint_snapshot(cp)) {
 		ret = 0;
-		kunmap_local(kaddr);
+		kunmap_local(cp);
 		goto out_cp;
 	}
 
 	list = &cp->cp_snapshot_list;
 	next = le64_to_cpu(list->ssl_next);
 	prev = le64_to_cpu(list->ssl_prev);
-	kunmap_local(kaddr);
+	kunmap_local(cp);
 
-	ret = nilfs_cpfile_get_header_block(cpfile, &header_bh);
-	if (ret < 0)
-		goto out_cp;
 	if (next != 0) {
 		ret = nilfs_cpfile_get_checkpoint_block(cpfile, next, 0,
 							&next_bh);
 		if (ret < 0)
-			goto out_header;
+			goto out_cp;
+
+		next_list_offset = nilfs_cpfile_cp_snapshot_list_offset(
+			cpfile, next, next_bh);
 	} else {
 		next_bh = header_bh;
 		get_bh(next_bh);
+		next_list_offset = nilfs_cpfile_ch_snapshot_list_offset();
 	}
 	if (prev != 0) {
 		ret = nilfs_cpfile_get_checkpoint_block(cpfile, prev, 0,
 							&prev_bh);
 		if (ret < 0)
 			goto out_next;
+
+		prev_list_offset = nilfs_cpfile_cp_snapshot_list_offset(
+			cpfile, prev, prev_bh);
 	} else {
 		prev_bh = header_bh;
 		get_bh(prev_bh);
+		prev_list_offset = nilfs_cpfile_ch_snapshot_list_offset();
 	}
 
-	kaddr = kmap_local_page(next_bh->b_page);
-	list = nilfs_cpfile_block_get_snapshot_list(
-		cpfile, next, next_bh, kaddr);
+	/* Update the list entry for the next snapshot */
+	list = kmap_local_folio(next_bh->b_folio, next_list_offset);
 	list->ssl_prev = cpu_to_le64(prev);
-	kunmap_local(kaddr);
+	kunmap_local(list);
 
-	kaddr = kmap_local_page(prev_bh->b_page);
-	list = nilfs_cpfile_block_get_snapshot_list(
-		cpfile, prev, prev_bh, kaddr);
+	/* Update the list entry for the previous snapshot */
+	list = kmap_local_folio(prev_bh->b_folio, prev_list_offset);
 	list->ssl_next = cpu_to_le64(next);
-	kunmap_local(kaddr);
+	kunmap_local(list);
 
-	kaddr = kmap_local_page(cp_bh->b_page);
-	cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
+	/* Update the snapshot being changed back to a plain checkpoint */
+	cp = kmap_local_folio(cp_bh->b_folio, offset);
 	cp->cp_snapshot_list.ssl_next = cpu_to_le64(0);
 	cp->cp_snapshot_list.ssl_prev = cpu_to_le64(0);
 	nilfs_checkpoint_clear_snapshot(cp);
-	kunmap_local(kaddr);
+	kunmap_local(cp);
 
-	kaddr = kmap_local_page(header_bh->b_page);
-	header = nilfs_cpfile_block_get_header(cpfile, header_bh, kaddr);
+	/* Update the statistics in the header */
+	header = kmap_local_folio(header_bh->b_folio, 0);
 	le64_add_cpu(&header->ch_nsnapshots, -1);
-	kunmap_local(kaddr);
+	kunmap_local(header);
 
 	mark_buffer_dirty(next_bh);
 	mark_buffer_dirty(prev_bh);
@@ -964,12 +994,12 @@ static int nilfs_cpfile_clear_snapshot(struct inode *cpfile, __u64 cno)
  out_next:
 	brelse(next_bh);
 
- out_header:
-	brelse(header_bh);
-
  out_cp:
 	brelse(cp_bh);
 
+ out_header:
+	brelse(header_bh);
+
  out_sem:
 	up_write(&NILFS_MDT(cpfile)->mi_sem);
 	return ret;
@@ -990,7 +1020,7 @@ int nilfs_cpfile_is_snapshot(struct inode *cpfile, __u64 cno)
 {
 	struct buffer_head *bh;
 	struct nilfs_checkpoint *cp;
-	void *kaddr;
+	size_t offset;
 	int ret;
 
 	/*
@@ -1004,13 +1034,14 @@ int nilfs_cpfile_is_snapshot(struct inode *cpfile, __u64 cno)
 	ret = nilfs_cpfile_get_checkpoint_block(cpfile, cno, 0, &bh);
 	if (ret < 0)
 		goto out;
-	kaddr = kmap_local_page(bh->b_page);
-	cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, bh, kaddr);
+
+	offset = nilfs_cpfile_checkpoint_offset(cpfile, cno, bh);
+	cp = kmap_local_folio(bh->b_folio, offset);
 	if (nilfs_checkpoint_invalid(cp))
 		ret = -ENOENT;
 	else
 		ret = nilfs_checkpoint_snapshot(cp);
-	kunmap_local(kaddr);
+	kunmap_local(cp);
 	brelse(bh);
 
  out:
@@ -1079,7 +1110,6 @@ int nilfs_cpfile_get_stat(struct inode *cpfile, struct nilfs_cpstat *cpstat)
 {
 	struct buffer_head *bh;
 	struct nilfs_cpfile_header *header;
-	void *kaddr;
 	int ret;
 
 	down_read(&NILFS_MDT(cpfile)->mi_sem);
@@ -1087,12 +1117,11 @@ int nilfs_cpfile_get_stat(struct inode *cpfile, struct nilfs_cpstat *cpstat)
 	ret = nilfs_cpfile_get_header_block(cpfile, &bh);
 	if (ret < 0)
 		goto out_sem;
-	kaddr = kmap_local_page(bh->b_page);
-	header = nilfs_cpfile_block_get_header(cpfile, bh, kaddr);
+	header = kmap_local_folio(bh->b_folio, 0);
 	cpstat->cs_cno = nilfs_mdt_cno(cpfile);
 	cpstat->cs_ncps = le64_to_cpu(header->ch_ncheckpoints);
 	cpstat->cs_nsss = le64_to_cpu(header->ch_nsnapshots);
-	kunmap_local(kaddr);
+	kunmap_local(header);
 	brelse(bh);
 
  out_sem:

From 310293201ed242e466b0e9f10f53b4a4abccffec Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 24 Oct 2024 18:25:43 +0900
Subject: [PATCH 0918/1530] nilfs2: remove nilfs_writepage

Since nilfs2 has a ->writepages operation already, ->writepage is only
called by the migration code.  If we add a ->migrate_folio operation, it
won't even be used for that and so it can be deleted.

[konishi.ryusuke@gmail.com: fixed panic by using buffer_migrate_folio_norefs]
Link: https://lkml.kernel.org/r/20241002150036.1339475-2-willy@infradead.org
Link: https://lkml.kernel.org/r/20241024092602.13395-10-konishi.ryusuke@gmail.com
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/inode.c | 33 +--------------------------------
 1 file changed, 1 insertion(+), 32 deletions(-)

diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index be6acf6e2bfc5..c24f06268010b 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -170,37 +170,6 @@ static int nilfs_writepages(struct address_space *mapping,
 	return err;
 }
 
-static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
-{
-	struct folio *folio = page_folio(page);
-	struct inode *inode = folio->mapping->host;
-	int err;
-
-	if (sb_rdonly(inode->i_sb)) {
-		/*
-		 * It means that filesystem was remounted in read-only
-		 * mode because of error or metadata corruption. But we
-		 * have dirty pages that try to be flushed in background.
-		 * So, here we simply discard this dirty page.
-		 */
-		nilfs_clear_folio_dirty(folio);
-		folio_unlock(folio);
-		return -EROFS;
-	}
-
-	folio_redirty_for_writepage(wbc, folio);
-	folio_unlock(folio);
-
-	if (wbc->sync_mode == WB_SYNC_ALL) {
-		err = nilfs_construct_segment(inode->i_sb);
-		if (unlikely(err))
-			return err;
-	} else if (wbc->for_reclaim)
-		nilfs_flush_segment(inode->i_sb, inode->i_ino);
-
-	return 0;
-}
-
 static bool nilfs_dirty_folio(struct address_space *mapping,
 		struct folio *folio)
 {
@@ -295,7 +264,6 @@ nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 }
 
 const struct address_space_operations nilfs_aops = {
-	.writepage		= nilfs_writepage,
 	.read_folio		= nilfs_read_folio,
 	.writepages		= nilfs_writepages,
 	.dirty_folio		= nilfs_dirty_folio,
@@ -304,6 +272,7 @@ const struct address_space_operations nilfs_aops = {
 	.write_end		= nilfs_write_end,
 	.invalidate_folio	= block_invalidate_folio,
 	.direct_IO		= nilfs_direct_IO,
+	.migrate_folio		= buffer_migrate_folio_norefs,
 	.is_partially_uptodate  = block_is_partially_uptodate,
 };
 

From c1d73eb8d06003e7714cd3ce1d0d79832e59b1e9 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 24 Oct 2024 18:25:44 +0900
Subject: [PATCH 0919/1530] nilfs2: convert nilfs_page_count_clean_buffers() to
 take a folio

Both callers have a folio, so pass it in and use it directly.

[konishi.ryusuke@gmail.com: fixed a checkpatch warning about function declaration]
Link: https://lkml.kernel.org/r/20241002150036.1339475-3-willy@infradead.org
Link: https://lkml.kernel.org/r/20241024092602.13395-11-konishi.ryusuke@gmail.com
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/dir.c   | 2 +-
 fs/nilfs2/inode.c | 2 +-
 fs/nilfs2/page.c  | 4 ++--
 fs/nilfs2/page.h  | 4 ++--
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index a8602729586ab..14e8d82f86298 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -95,7 +95,7 @@ static void nilfs_commit_chunk(struct folio *folio,
 	unsigned int nr_dirty;
 	int err;
 
-	nr_dirty = nilfs_page_count_clean_buffers(&folio->page, from, to);
+	nr_dirty = nilfs_page_count_clean_buffers(folio, from, to);
 	copied = block_write_end(NULL, mapping, pos, len, len, folio, NULL);
 	if (pos + copied > dir->i_size)
 		i_size_write(dir, pos + copied);
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index c24f06268010b..cf9ba481ae376 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -242,7 +242,7 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping,
 	unsigned int nr_dirty;
 	int err;
 
-	nr_dirty = nilfs_page_count_clean_buffers(&folio->page, start,
+	nr_dirty = nilfs_page_count_clean_buffers(folio, start,
 						  start + copied);
 	copied = generic_write_end(file, mapping, pos, len, copied, folio,
 				   fsdata);
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 10def4b559956..e48079ebe9397 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -422,14 +422,14 @@ void nilfs_clear_folio_dirty(struct folio *folio)
 	__nilfs_clear_folio_dirty(folio);
 }
 
-unsigned int nilfs_page_count_clean_buffers(struct page *page,
+unsigned int nilfs_page_count_clean_buffers(struct folio *folio,
 					    unsigned int from, unsigned int to)
 {
 	unsigned int block_start, block_end;
 	struct buffer_head *bh, *head;
 	unsigned int nc = 0;
 
-	for (bh = head = page_buffers(page), block_start = 0;
+	for (bh = head = folio_buffers(folio), block_start = 0;
 	     bh != head || !block_start;
 	     block_start = block_end, bh = bh->b_this_page) {
 		block_end = block_start + bh->b_size;
diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h
index 64521a03a19e0..136cd1c143c9c 100644
--- a/fs/nilfs2/page.h
+++ b/fs/nilfs2/page.h
@@ -43,8 +43,8 @@ int nilfs_copy_dirty_pages(struct address_space *, struct address_space *);
 void nilfs_copy_back_pages(struct address_space *, struct address_space *);
 void nilfs_clear_folio_dirty(struct folio *folio);
 void nilfs_clear_dirty_pages(struct address_space *mapping);
-unsigned int nilfs_page_count_clean_buffers(struct page *, unsigned int,
-					    unsigned int);
+unsigned int nilfs_page_count_clean_buffers(struct folio *folio,
+		unsigned int from, unsigned int to);
 unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
 					    sector_t start_blk,
 					    sector_t *blkoff);

From b18d78dec38e0ccd06e968396388eadea1da1c4e Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 24 Oct 2024 18:25:45 +0900
Subject: [PATCH 0920/1530] nilfs2: convert nilfs_recovery_copy_block() to take
 a folio

Use memcpy_to_folio() instead of open-coding it, and use offset_in_folio()
in case anybody wants to use nilfs2 on a device with large blocks.

[konishi.ryusuke@gmail.com: added label name change]
Link: https://lkml.kernel.org/r/20241002150036.1339475-4-willy@infradead.org
Link: https://lkml.kernel.org/r/20241024092602.13395-12-konishi.ryusuke@gmail.com
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/recovery.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 21d81097a89f8..e43405bf521e8 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -481,19 +481,16 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs,
 
 static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
 				     struct nilfs_recovery_block *rb,
-				     loff_t pos, struct page *page)
+				     loff_t pos, struct folio *folio)
 {
 	struct buffer_head *bh_org;
-	size_t from = pos & ~PAGE_MASK;
-	void *kaddr;
+	size_t from = offset_in_folio(folio, pos);
 
 	bh_org = __bread(nilfs->ns_bdev, rb->blocknr, nilfs->ns_blocksize);
 	if (unlikely(!bh_org))
 		return -EIO;
 
-	kaddr = kmap_local_page(page);
-	memcpy(kaddr + from, bh_org->b_data, bh_org->b_size);
-	kunmap_local(kaddr);
+	memcpy_to_folio(folio, from, bh_org->b_data, bh_org->b_size);
 	brelse(bh_org);
 	return 0;
 }
@@ -531,13 +528,13 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
 			goto failed_inode;
 		}
 
-		err = nilfs_recovery_copy_block(nilfs, rb, pos, &folio->page);
+		err = nilfs_recovery_copy_block(nilfs, rb, pos, folio);
 		if (unlikely(err))
-			goto failed_page;
+			goto failed_folio;
 
 		err = nilfs_set_file_dirty(inode, 1);
 		if (unlikely(err))
-			goto failed_page;
+			goto failed_folio;
 
 		block_write_end(NULL, inode->i_mapping, pos, blocksize,
 				blocksize, folio, NULL);
@@ -548,7 +545,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
 		(*nr_salvaged_blocks)++;
 		goto next;
 
- failed_page:
+ failed_folio:
 		folio_unlock(folio);
 		folio_put(folio);
 

From 013a07052a1a02d6d8bebf84ad3a8cb483292da7 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 24 Oct 2024 18:25:46 +0900
Subject: [PATCH 0921/1530] nilfs2: convert metadata aops from writepage to
 writepages

By implementing ->writepages instead of ->writepage, we remove a layer of
indirect function calls from the writeback path and the last use of struct
page in nilfs2.

[konishi.ryusuke@gmail.com: fixed panic by using buffer_migrate_folio_norefs]
Link: https://lkml.kernel.org/r/20241002150036.1339475-5-willy@infradead.org
Link: https://lkml.kernel.org/r/20241024092602.13395-13-konishi.ryusuke@gmail.com
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/mdt.c | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index a4c1e00aaaacd..432181cfb0b53 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -399,10 +399,9 @@ int nilfs_mdt_fetch_dirty(struct inode *inode)
 	return test_bit(NILFS_I_DIRTY, &ii->i_state);
 }
 
-static int
-nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc)
+static int nilfs_mdt_write_folio(struct folio *folio,
+		struct writeback_control *wbc)
 {
-	struct folio *folio = page_folio(page);
 	struct inode *inode = folio->mapping->host;
 	struct super_block *sb;
 	int err = 0;
@@ -435,11 +434,23 @@ nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc)
 	return err;
 }
 
+static int nilfs_mdt_writeback(struct address_space *mapping,
+		struct writeback_control *wbc)
+{
+	struct folio *folio = NULL;
+	int error;
+
+	while ((folio = writeback_iter(mapping, wbc, folio, &error)))
+		error = nilfs_mdt_write_folio(folio, wbc);
+
+	return error;
+}
 
 static const struct address_space_operations def_mdt_aops = {
 	.dirty_folio		= block_dirty_folio,
 	.invalidate_folio	= block_invalidate_folio,
-	.writepage		= nilfs_mdt_write_page,
+	.writepages		= nilfs_mdt_writeback,
+	.migrate_folio		= buffer_migrate_folio_norefs,
 };
 
 static const struct inode_operations def_mdt_iops;

From 2f07b652384969f5d0b317e1daa5f2eb967bc73d Mon Sep 17 00:00:00 2001
From: Tamir Duberstein <tamird@gmail.com>
Date: Fri, 25 Oct 2024 19:43:19 -0400
Subject: [PATCH 0922/1530] checkpatch: always parse orig_commit in fixes tag
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Do not require the presence of `$balanced_parens` to get the commit SHA;
this allows a `Fixes: deadbeef` tag to get a correct suggestion rather
than a suggestion containing a reference to HEAD.

Given this patch:

: From: Tamir Duberstein <tamird@gmail.com>
: Subject: Test patch
: Date: Fri, 25 Oct 2024 19:30:51 -0400
:
: This is a test patch.
:
: Fixes: bd17e036b495
: Signed-off-by: Tamir Duberstein <tamird@gmail.com>
: --- /dev/null
: +++ b/new-file
: @@ -0,0 +1 @@
: +Test.


Before:

WARNING: Please use correct Fixes: style 'Fixes: <12 chars of sha1> ("<title line>")' - ie: 'Fixes: c10a7d25e68f ("Test patch")'

After:

WARNING: Please use correct Fixes: style 'Fixes: <12 chars of sha1> ("<title line>")' - ie: 'Fixes: bd17e036b495 ("checkpatch: warn for non-standard fixes tag style")'



The prior behavior incorrectly suggested the patch's own SHA and title
line rather than the referenced commit's.  This fixes that.

Ironically this:

Fixes: bd17e036b495 ("checkpatch: warn for non-standard fixes tag style")
Signed-off-by: Tamir Duberstein <tamird@gmail.com>
Cc: Andy Whitcroft <apw@canonical.com>
Cc: Dwaipayan Ray <dwaipayanray1@gmail.com>
Cc: Joe Perches <joe@perches.com>
Cc: Louis Peens <louis.peens@corigine.com>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Cc: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Cc: Philippe Schenker <philippe.schenker@toradex.com>
Cc: Simon Horman <horms@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 scripts/checkpatch.pl | 37 ++++++++++++++++---------------------
 1 file changed, 16 insertions(+), 21 deletions(-)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 4427572b24771..b03d526e4c454 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -3209,36 +3209,31 @@ sub process {
 
 # Check Fixes: styles is correct
 		if (!$in_header_lines &&
-		    $line =~ /^\s*fixes:?\s*(?:commit\s*)?[0-9a-f]{5,}\b/i) {
-			my $orig_commit = "";
-			my $id = "0123456789ab";
-			my $title = "commit title";
-			my $tag_case = 1;
-			my $tag_space = 1;
-			my $id_length = 1;
-			my $id_case = 1;
+		    $line =~ /^\s*(fixes:?)\s*(?:commit\s*)?([0-9a-f]{5,40})(?:\s*($balanced_parens))?/i) {
+			my $tag = $1;
+			my $orig_commit = $2;
+			my $title;
 			my $title_has_quotes = 0;
 			$fixes_tag = 1;
-
-			if ($line =~ /(\s*fixes:?)\s+([0-9a-f]{5,})\s+($balanced_parens)/i) {
-				my $tag = $1;
-				$orig_commit = $2;
-				$title = $3;
-
-				$tag_case = 0 if $tag eq "Fixes:";
-				$tag_space = 0 if ($line =~ /^fixes:? [0-9a-f]{5,} ($balanced_parens)/i);
-
-				$id_length = 0 if ($orig_commit =~ /^[0-9a-f]{12}$/i);
-				$id_case = 0 if ($orig_commit !~ /[A-F]/);
-
+			if (defined $3) {
 				# Always strip leading/trailing parens then double quotes if existing
-				$title = substr($title, 1, -1);
+				$title = substr($3, 1, -1);
 				if ($title =~ /^".*"$/) {
 					$title = substr($title, 1, -1);
 					$title_has_quotes = 1;
 				}
+			} else {
+				$title = "commit title"
 			}
 
+
+			my $tag_case = not ($tag eq "Fixes:");
+			my $tag_space = not ($line =~ /^fixes:? [0-9a-f]{5,40} ($balanced_parens)/i);
+
+			my $id_length = not ($orig_commit =~ /^[0-9a-f]{12}$/i);
+			my $id_case = not ($orig_commit !~ /[A-F]/);
+
+			my $id = "0123456789ab";
 			my ($cid, $ctitle) = git_commit_info($orig_commit, $id,
 							     $title);
 

From e01caa2b63c88c64ee90b83a92a584ec90feeda5 Mon Sep 17 00:00:00 2001
From: Sui Jingfeng <sui.jingfeng@linux.dev>
Date: Tue, 29 Oct 2024 02:29:20 +0800
Subject: [PATCH 0923/1530] lib/scatterlist: use sg_phys() helper

This shorten the length of code in horizential direction, therefore is
easier to read.

Link: https://lkml.kernel.org/r/20241028182920.1025819-1-sui.jingfeng@linux.dev
Signed-off-by: Sui Jingfeng <sui.jingfeng@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/scatterlist.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 473b2646f71c6..5bb6b8aff2325 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -474,14 +474,14 @@ int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append,
 		return -EOPNOTSUPP;
 
 	if (sgt_append->prv) {
-		unsigned long next_pfn = (page_to_phys(sg_page(sgt_append->prv)) +
-			sgt_append->prv->offset + sgt_append->prv->length) / PAGE_SIZE;
+		unsigned long next_pfn;
 
 		if (WARN_ON(offset))
 			return -EINVAL;
 
 		/* Merge contiguous pages into the last SG */
 		prv_len = sgt_append->prv->length;
+		next_pfn = (sg_phys(sgt_append->prv) + prv_len) / PAGE_SIZE;
 		if (page_to_pfn(pages[0]) == next_pfn) {
 			last_pg = pfn_to_page(next_pfn - 1);
 			while (n_pages && pages_are_mergeable(pages[0], last_pg)) {

From b5e60497a4b7f0b295c4c59b202cf4703b27062b Mon Sep 17 00:00:00 2001
From: Andrew Kreimer <algonell@gmail.com>
Date: Sun, 27 Oct 2024 15:35:18 +0200
Subject: [PATCH 0924/1530] ocfs2: cluster: fix a typo

Fix a typo: panicing -> panicking.

Via codespell.

Link: https://lkml.kernel.org/r/20241027133540.22090-1-algonell@gmail.com
Signed-off-by: Andrew Kreimer <algonell@gmail.com>
Acked-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Jun Piao <piaojun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/ocfs2/cluster/quorum.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c
index 15d0ed9c13e5b..8bf17231d7b73 100644
--- a/fs/ocfs2/cluster/quorum.c
+++ b/fs/ocfs2/cluster/quorum.c
@@ -60,7 +60,7 @@ static void o2quo_fence_self(void)
 	switch (o2nm_single_cluster->cl_fence_method) {
 	case O2NM_FENCE_PANIC:
 		panic("*** ocfs2 is very sorry to be fencing this system by "
-		      "panicing ***\n");
+		      "panicking ***\n");
 		break;
 	default:
 		WARN_ON(o2nm_single_cluster->cl_fence_method >=

From 77e94b0496ef39b759f23b4ece8c434a4b5c2e47 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Tue, 22 Oct 2024 01:25:43 +0100
Subject: [PATCH 0925/1530] ocfs2: remove unused errmsg function and table

dlm_errmsg() has been unused since 2010's commit 0016eedc4185
("ocfs2_dlmfs: Use the stackglue.")

Remove dlm_errmsg() and the message table it indexes.

Link: https://lkml.kernel.org/r/20241022002543.302606-1-linux@treblig.org
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Acked-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Jun Piao <piaojun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/ocfs2/dlm/dlmapi.h   |  2 --
 fs/ocfs2/dlm/dlmdebug.c | 53 -----------------------------------------
 2 files changed, 55 deletions(-)

diff --git a/fs/ocfs2/dlm/dlmapi.h b/fs/ocfs2/dlm/dlmapi.h
index bae60ca2672a8..847a52dcbe7df 100644
--- a/fs/ocfs2/dlm/dlmapi.h
+++ b/fs/ocfs2/dlm/dlmapi.h
@@ -62,8 +62,6 @@ enum dlm_status {
 	DLM_MAXSTATS,             /* 41: upper limit for return code validation */
 };
 
-/* for pretty-printing dlm_status error messages */
-const char *dlm_errmsg(enum dlm_status err);
 /* for pretty-printing dlm_status error names */
 const char *dlm_errname(enum dlm_status err);
 
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index be5e9ed7da8d9..e9ef4e2b0e752 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -164,59 +164,6 @@ static const char *dlm_errnames[] = {
 	[DLM_MAXSTATS] =		"DLM_MAXSTATS",
 };
 
-static const char *dlm_errmsgs[] = {
-	[DLM_NORMAL] = 			"request in progress",
-	[DLM_GRANTED] = 		"request granted",
-	[DLM_DENIED] = 			"request denied",
-	[DLM_DENIED_NOLOCKS] = 		"request denied, out of system resources",
-	[DLM_WORKING] = 		"async request in progress",
-	[DLM_BLOCKED] = 		"lock request blocked",
-	[DLM_BLOCKED_ORPHAN] = 		"lock request blocked by a orphan lock",
-	[DLM_DENIED_GRACE_PERIOD] = 	"topological change in progress",
-	[DLM_SYSERR] = 			"system error",
-	[DLM_NOSUPPORT] = 		"unsupported",
-	[DLM_CANCELGRANT] = 		"can't cancel convert: already granted",
-	[DLM_IVLOCKID] = 		"bad lockid",
-	[DLM_SYNC] = 			"synchronous request granted",
-	[DLM_BADTYPE] = 		"bad resource type",
-	[DLM_BADRESOURCE] = 		"bad resource handle",
-	[DLM_MAXHANDLES] = 		"no more resource handles",
-	[DLM_NOCLINFO] = 		"can't contact cluster manager",
-	[DLM_NOLOCKMGR] = 		"can't contact lock manager",
-	[DLM_NOPURGED] = 		"can't contact purge daemon",
-	[DLM_BADARGS] = 		"bad api args",
-	[DLM_VOID] = 			"no status",
-	[DLM_NOTQUEUED] = 		"NOQUEUE was specified and request failed",
-	[DLM_IVBUFLEN] = 		"invalid resource name length",
-	[DLM_CVTUNGRANT] = 		"attempted to convert ungranted lock",
-	[DLM_BADPARAM] = 		"invalid lock mode specified",
-	[DLM_VALNOTVALID] = 		"value block has been invalidated",
-	[DLM_REJECTED] = 		"request rejected, unrecognized client",
-	[DLM_ABORT] = 			"blocked lock request cancelled",
-	[DLM_CANCEL] = 			"conversion request cancelled",
-	[DLM_IVRESHANDLE] = 		"invalid resource handle",
-	[DLM_DEADLOCK] = 		"deadlock recovery refused this request",
-	[DLM_DENIED_NOASTS] = 		"failed to allocate AST",
-	[DLM_FORWARD] = 		"request must wait for primary's response",
-	[DLM_TIMEOUT] = 		"timeout value for lock has expired",
-	[DLM_IVGROUPID] = 		"invalid group specification",
-	[DLM_VERS_CONFLICT] = 		"version conflicts prevent request handling",
-	[DLM_BAD_DEVICE_PATH] = 	"Locks device does not exist or path wrong",
-	[DLM_NO_DEVICE_PERMISSION] = 	"Client has insufficient perms for device",
-	[DLM_NO_CONTROL_DEVICE] = 	"Cannot set options on opened device ",
-	[DLM_RECOVERING] = 		"lock resource being recovered",
-	[DLM_MIGRATING] = 		"lock resource being migrated",
-	[DLM_MAXSTATS] = 		"invalid error number",
-};
-
-const char *dlm_errmsg(enum dlm_status err)
-{
-	if (err >= DLM_MAXSTATS || err < 0)
-		return dlm_errmsgs[DLM_MAXSTATS];
-	return dlm_errmsgs[err];
-}
-EXPORT_SYMBOL_GPL(dlm_errmsg);
-
 const char *dlm_errname(enum dlm_status err)
 {
 	if (err >= DLM_MAXSTATS || err < 0)

From 5fb8e56542a3cf469fdf25d77f50e21cbff3ae7e Mon Sep 17 00:00:00 2001
From: Benjamin Peterson <benjamin@engflow.com>
Date: Sun, 3 Nov 2024 20:48:16 +0000
Subject: [PATCH 0926/1530] perf trace: avoid garbage when not printing a trace
 event's arguments

trace__fprintf_tp_fields may not print any tracepoint arguments. E.g., if the
argument values are all zero. Previously, this would result in a totally
uninitialized buffer being passed to fprintf, which could lead to garbage on the
console. Fix the problem by passing the number of initialized bytes fprintf.

Fixes: f11b2803bb88 ("perf trace: Allow choosing how to augment the tracepoint arguments")
Signed-off-by: Benjamin Peterson <benjamin@engflow.com>
Tested-by: Howard Chu <howardchu95@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: https://lore.kernel.org/r/20241103204816.7834-1-benjamin@engflow.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-trace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c1e9e14c86865..a661fbd870e7c 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3087,7 +3087,7 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct evsel *evsel,
 		printed += syscall_arg_fmt__scnprintf_val(arg, bf + printed, size - printed, &syscall_arg, val);
 	}
 
-	return printed + fprintf(trace->output, "%s", bf);
+	return printed + fprintf(trace->output, "%.*s", (int)printed, bf);
 }
 
 static int trace__event_handler(struct trace *trace, struct evsel *evsel,

From b609a15e7969d6a50d65067ee783b5d9365b04dd Mon Sep 17 00:00:00 2001
From: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Date: Mon, 4 Nov 2024 12:49:35 +0100
Subject: [PATCH 0927/1530] PCI: mediatek-gen3: Add support for restricting
 link width
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for restricting the port's link width by specifying
the num-lanes devicetree property in the PCIe node.

The setting is done in the GEN_SETTINGS register (in the driver
named as PCIE_SETTING_REG), where each set bit in [11:8] activates
a set of lanes (from bits 11 to 8 respectively, x16/x8/x4/x2).

Link: https://lore.kernel.org/r/20241104114935.172908-3-angelogioacchino.delregno@collabora.com
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Fei Shao <fshao@chromium.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/pcie-mediatek-gen3.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c
index 1d208d58e94a1..bbfbfe5752e6a 100644
--- a/drivers/pci/controller/pcie-mediatek-gen3.c
+++ b/drivers/pci/controller/pcie-mediatek-gen3.c
@@ -32,6 +32,7 @@
 #define PCIE_BASE_CFG_SPEED		GENMASK(15, 8)
 
 #define PCIE_SETTING_REG		0x80
+#define PCIE_SETTING_LINK_WIDTH		GENMASK(11, 8)
 #define PCIE_SETTING_GEN_SUPPORT	GENMASK(14, 12)
 #define PCIE_PCI_IDS_1			0x9c
 #define PCI_CLASS(class)		(class << 8)
@@ -168,6 +169,7 @@ struct mtk_msi_set {
  * @clks: PCIe clocks
  * @num_clks: PCIe clocks count for this port
  * @max_link_speed: Maximum link speed (PCIe Gen) for this port
+ * @num_lanes: Number of PCIe lanes for this port
  * @irq: PCIe controller interrupt number
  * @saved_irq_state: IRQ enable state saved at suspend time
  * @irq_lock: lock protecting IRQ register access
@@ -189,6 +191,7 @@ struct mtk_gen3_pcie {
 	struct clk_bulk_data *clks;
 	int num_clks;
 	u8 max_link_speed;
+	u8 num_lanes;
 
 	int irq;
 	u32 saved_irq_state;
@@ -401,6 +404,14 @@ static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie)
 			val |= FIELD_PREP(PCIE_SETTING_GEN_SUPPORT,
 					  GENMASK(pcie->max_link_speed - 2, 0));
 	}
+	if (pcie->num_lanes) {
+		val &= ~PCIE_SETTING_LINK_WIDTH;
+
+		/* Zero means one lane, each bit activates x2/x4/x8/x16 */
+		if (pcie->num_lanes > 1)
+			val |= FIELD_PREP(PCIE_SETTING_LINK_WIDTH,
+					  GENMASK(fls(pcie->num_lanes >> 2), 0));
+	};
 	writel_relaxed(val, pcie->base + PCIE_SETTING_REG);
 
 	/* Set Link Control 2 (LNKCTL2) speed restriction, if any */
@@ -838,6 +849,7 @@ static int mtk_pcie_parse_port(struct mtk_gen3_pcie *pcie)
 	struct device *dev = pcie->dev;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct resource *regs;
+	u32 num_lanes;
 
 	regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pcie-mac");
 	if (!regs)
@@ -883,6 +895,14 @@ static int mtk_pcie_parse_port(struct mtk_gen3_pcie *pcie)
 		return pcie->num_clks;
 	}
 
+       ret = of_property_read_u32(dev->of_node, "num-lanes", &num_lanes);
+       if (ret == 0) {
+	       if (num_lanes == 0 || num_lanes > 16 || (num_lanes != 1 && num_lanes % 2))
+			dev_warn(dev, "invalid num-lanes, using controller defaults\n");
+	       else
+			pcie->num_lanes = num_lanes;
+       }
+
 	return 0;
 }
 

From e1714f3b1f4d2af5df26e4a0e4a70ef64b15e3ee Mon Sep 17 00:00:00 2001
From: Jian-Hong Pan <jhp@endlessos.org>
Date: Tue, 1 Oct 2024 16:34:40 +0800
Subject: [PATCH 0928/1530] PCI/ASPM: Add notes about enabling PCI-PM L1SS to
 pci_enable_link_state(_locked)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

According to "PCIe r6.0, sec 5.5.4", add note about D0 requirement in
pci_enable_link_state() kernel-doc.

Link: https://lore.kernel.org/r/20241001083438.10070-6-jhp@endlessos.org
Signed-off-by: Jian-Hong Pan <jhp@endlessos.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/aspm.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index e943691bc9317..28567d457613b 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -1450,6 +1450,9 @@ static int __pci_enable_link_state(struct pci_dev *pdev, int state, bool locked)
  * touch the LNKCTL register. Also note that this does not enable states
  * disabled by pci_disable_link_state(). Return 0 or a negative errno.
  *
+ * Note: Ensure devices are in D0 before enabling PCI-PM L1 PM Substates, per
+ * PCIe r6.0, sec 5.5.4.
+ *
  * @pdev: PCI device
  * @state: Mask of ASPM link states to enable
  */
@@ -1466,6 +1469,9 @@ EXPORT_SYMBOL(pci_enable_link_state);
  * can't touch the LNKCTL register. Also note that this does not enable states
  * disabled by pci_disable_link_state(). Return 0 or a negative errno.
  *
+ * Note: Ensure devices are in D0 before enabling PCI-PM L1 PM Substates, per
+ * PCIe r6.0, sec 5.5.4.
+ *
  * @pdev: PCI device
  * @state: Mask of ASPM link states to enable
  *

From d7ce9c73da54a096311edbf4688b78b179dd79bc Mon Sep 17 00:00:00 2001
From: Huang Ying <ying.huang@intel.com>
Date: Tue, 29 Oct 2024 20:27:35 +0800
Subject: [PATCH 0929/1530] resource: avoid unnecessary resource tree walking
 in __region_intersects()

Currently, if __region_intersects() finds any overlapped but unmatched
resource, it walks the descendant resource tree to check for overlapped
and matched descendant resources using for_each_resource().  However, in
current kernel, for_each_resource() iterates not only the descendant tree,
but also subsequent sibling trees in certain scenarios.  While this
doesn't introduce bugs, it makes code hard to be understood and
potentially inefficient.

So, the patch revises next_resource() and for_each_resource() and makes
for_each_resource() traverse the subtree under the specified subtree root
only.  Test shows that this avoids unnecessary resource tree walking in
__region_intersects().

For the example resource tree as follows,

  X
  |
  A----D----E
  |
  B--C

if 'A' is the overlapped but unmatched resource, original kernel
iterates 'B', 'C', 'D', 'E' when it walks the descendant tree.  While
the patched kernel iterates only 'B', 'C'.

Thanks David Hildenbrand for providing a good resource tree example.

Link: https://lkml.kernel.org/r/20241029122735.79164-1-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Jonathan Cameron <jonathan.cameron@huawei.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Alison Schofield <alison.schofield@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/resource.c | 26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

diff --git a/kernel/resource.c b/kernel/resource.c
index 2d4208b2f62fa..59c6e608f1d1b 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -50,17 +50,35 @@ EXPORT_SYMBOL(iomem_resource);
 
 static DEFINE_RWLOCK(resource_lock);
 
-static struct resource *next_resource(struct resource *p, bool skip_children)
+/*
+ * Return the next node of @p in pre-order tree traversal.  If
+ * @skip_children is true, skip the descendant nodes of @p in
+ * traversal.  If @p is a descendant of @subtree_root, only traverse
+ * the subtree under @subtree_root.
+ */
+static struct resource *next_resource(struct resource *p, bool skip_children,
+				      struct resource *subtree_root)
 {
 	if (!skip_children && p->child)
 		return p->child;
-	while (!p->sibling && p->parent)
+	while (!p->sibling && p->parent) {
 		p = p->parent;
+		if (p == subtree_root)
+			return NULL;
+	}
 	return p->sibling;
 }
 
+/*
+ * Traverse the resource subtree under @_root in pre-order, excluding
+ * @_root itself.
+ *
+ * NOTE: '__p' is introduced to avoid shadowing '_p' outside of loop.
+ * And it is referenced to avoid unused variable warning.
+ */
 #define for_each_resource(_root, _p, _skip_children) \
-	for ((_p) = (_root)->child; (_p); (_p) = next_resource(_p, _skip_children))
+	for (typeof(_root) __root = (_root), __p = _p = __root->child;	\
+	     __p && _p; _p = next_resource(_p, _skip_children, __root))
 
 #ifdef CONFIG_PROC_FS
 
@@ -88,7 +106,7 @@ static void *r_next(struct seq_file *m, void *v, loff_t *pos)
 
 	(*pos)++;
 
-	return (void *)next_resource(p, false);
+	return (void *)next_resource(p, false, NULL);
 }
 
 static void r_stop(struct seq_file *m, void *v)

From 82e33f249f1126cf3c5f39a31b850d485ac33bc3 Mon Sep 17 00:00:00 2001
From: Mirsad Todorovac <mtodorovac69@gmail.com>
Date: Tue, 29 Oct 2024 06:46:52 +0100
Subject: [PATCH 0930/1530] fs/proc/kcore.c: fix coccinelle reported ERROR
 instances

Coccinelle complains about the nested reuse of the pointer `iter' with
different pointer type:

./fs/proc/kcore.c:515:26-30: ERROR: invalid reference to the index variable of the iterator on line 499
./fs/proc/kcore.c:534:23-27: ERROR: invalid reference to the index variable of the iterator on line 499
./fs/proc/kcore.c:550:40-44: ERROR: invalid reference to the index variable of the iterator on line 499
./fs/proc/kcore.c:568:27-31: ERROR: invalid reference to the index variable of the iterator on line 499
./fs/proc/kcore.c:581:28-32: ERROR: invalid reference to the index variable of the iterator on line 499
./fs/proc/kcore.c:599:27-31: ERROR: invalid reference to the index variable of the iterator on line 499
./fs/proc/kcore.c:607:38-42: ERROR: invalid reference to the index variable of the iterator on line 499
./fs/proc/kcore.c:614:26-30: ERROR: invalid reference to the index variable of the iterator on line 499

Replacing `struct kcore_list *iter' with `struct kcore_list *tmp' doesn't change the
scope and the functionality is the same and coccinelle seems happy.

NOTE: There was an issue with using `struct kcore_list *pos' as the nested iterator.
      The build did not work!

[akpm@linux-foundation.org: s/tmp/pos/]
Link: https://lkml.kernel.org/r/20241029054651.86356-2-mtodorovac69@gmail.com
Link: https://lore.kernel.org/all/CAHk-=wgRr_D8CB-D9Kg-c=EHreAsk5SqXPwr9Y7k9sA6cWXJ6w@mail.gmail.com/ [1]
Link: https://lkml.kernel.org/r/20220331223700.902556-1-jakobkoschel@gmail.com
Fixes: 04d168c6d42d ("fs/proc/kcore.c: remove check of list iterator against head past the loop body")
Signed-off-by: Jakob Koschel <jakobkoschel@gmail.com>
Signed-off-by: Mirsad Todorovac <mtodorovac69@gmail.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: "Brian Johannesmeyer" <bjohannesmeyer@gmail.com>
Cc: Cristiano Giuffrida <c.giuffrida@vu.nl>
Cc: "Bos, H.J." <h.j.bos@vu.nl>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Yan Zhen <yanzhen@vivo.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/kcore.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 51446c59388f1..7a85735d584f3 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -493,13 +493,13 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 		 * the previous entry, search for a matching entry.
 		 */
 		if (!m || start < m->addr || start >= m->addr + m->size) {
-			struct kcore_list *iter;
+			struct kcore_list *pos;
 
 			m = NULL;
-			list_for_each_entry(iter, &kclist_head, list) {
-				if (start >= iter->addr &&
-				    start < iter->addr + iter->size) {
-					m = iter;
+			list_for_each_entry(pos, &kclist_head, list) {
+				if (start >= pos->addr &&
+				    start < pos->addr + pos->size) {
+					m = pos;
 					break;
 				}
 			}

From 777620b890d783c6575f172041f390c4c075b666 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Mon, 7 Oct 2024 10:37:52 +0200
Subject: [PATCH 0931/1530] dma-buf: use atomic64_inc_return() in
 dma_buf_getfile()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use atomic64_inc_return(&ref) instead of atomic64_add_return(1, &ref) to
use optimized implementation and ease register pressure around the
primitive for targets that implement optimized variant.

Link: https://lkml.kernel.org/r/20241007083921.47525-1-ubizjak@gmail.com
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: "Christian König" <christian.koenig@amd.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/dma-buf/dma-buf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 8892bc701a662..a3649db76addc 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -558,7 +558,7 @@ static struct file *dma_buf_getfile(size_t size, int flags)
 	 * Override ->i_ino with the unique and dmabuffs specific
 	 * value.
 	 */
-	inode->i_ino = atomic64_add_return(1, &dmabuf_inode);
+	inode->i_ino = atomic64_inc_return(&dmabuf_inode);
 	flags &= O_ACCMODE | O_NONBLOCK;
 	file = alloc_file_pseudo(inode, dma_buf_mnt, "dmabuf",
 				 flags, &dma_buf_fops);

From 0a726f542d7c8cc0f9c5ed7df5a4bd4b59ac21b3 Mon Sep 17 00:00:00 2001
From: Stefan Eichenberger <stefan.eichenberger@toradex.com>
Date: Wed, 30 Oct 2024 11:32:45 +0100
Subject: [PATCH 0932/1530] PCI: imx6: Fix suspend/resume support on i.MX6QDL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The suspend/resume functionality is currently broken on the i.MX6QDL
platform, as documented in the NXP errata (ERR005723):

  https://www.nxp.com/docs/en/errata/IMX6DQCE.pdf

This patch addresses the issue by sharing most of the suspend/resume
sequences used by other i.MX devices, while avoiding modifications to
critical registers that disrupt the PCIe functionality. It targets the
same problem as the following downstream commit:

  https://github.com/nxp-imx/linux-imx/commit/4e92355e1f79d225ea842511fcfd42b343b32995

Unlike the downstream commit, this patch also resets the connected PCIe
device if possible. Without this reset, certain drivers, such as ath10k
or iwlwifi, will crash on resume. The device reset is also done by the
driver on other i.MX platforms, making this patch consistent with
existing practices.

Upon resuming, the kernel will hang and display an error. Here's an
example of the error encountered with the ath10k driver:

  ath10k_pci 0000:01:00.0: Unable to change power state from D3hot to D0, device inaccessible
  Unhandled fault: imprecise external abort (0x1406) at 0x0106f944

Without this patch, suspend/resume will fail on i.MX6QDL devices if a
PCIe device is connected.

Link: https://lore.kernel.org/r/20241030103250.83640-1-eichest@gmail.com
Signed-off-by: Stefan Eichenberger <stefan.eichenberger@toradex.com>
[kwilczynski: commit log, added tag for stable releases]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Richard Zhu <hongxing.zhu@nxp.com>
Cc: stable@vger.kernel.org
---
 drivers/pci/controller/dwc/pci-imx6.c | 57 +++++++++++++++++++++------
 1 file changed, 46 insertions(+), 11 deletions(-)

diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 808d1f1054173..c8d5c90aa4d45 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -82,6 +82,11 @@ enum imx_pcie_variants {
 #define IMX_PCIE_FLAG_HAS_SERDES		BIT(6)
 #define IMX_PCIE_FLAG_SUPPORT_64BIT		BIT(7)
 #define IMX_PCIE_FLAG_CPU_ADDR_FIXUP		BIT(8)
+/*
+ * Because of ERR005723 (PCIe does not support L2 power down) we need to
+ * workaround suspend resume on some devices which are affected by this errata.
+ */
+#define IMX_PCIE_FLAG_BROKEN_SUSPEND		BIT(9)
 
 #define imx_check_flag(pci, val)	(pci->drvdata->flags & val)
 
@@ -1237,9 +1242,19 @@ static int imx_pcie_suspend_noirq(struct device *dev)
 		return 0;
 
 	imx_pcie_msi_save_restore(imx_pcie, true);
-	imx_pcie_pm_turnoff(imx_pcie);
-	imx_pcie_stop_link(imx_pcie->pci);
-	imx_pcie_host_exit(pp);
+	if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_BROKEN_SUSPEND)) {
+		/*
+		 * The minimum for a workaround would be to set PERST# and to
+		 * set the PCIE_TEST_PD flag. However, we can also disable the
+		 * clock which saves some power.
+		 */
+		imx_pcie_assert_core_reset(imx_pcie);
+		imx_pcie->drvdata->enable_ref_clk(imx_pcie, false);
+	} else {
+		imx_pcie_pm_turnoff(imx_pcie);
+		imx_pcie_stop_link(imx_pcie->pci);
+		imx_pcie_host_exit(pp);
+	}
 
 	return 0;
 }
@@ -1253,14 +1268,32 @@ static int imx_pcie_resume_noirq(struct device *dev)
 	if (!(imx_pcie->drvdata->flags & IMX_PCIE_FLAG_SUPPORTS_SUSPEND))
 		return 0;
 
-	ret = imx_pcie_host_init(pp);
-	if (ret)
-		return ret;
-	imx_pcie_msi_save_restore(imx_pcie, false);
-	dw_pcie_setup_rc(pp);
+	if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_BROKEN_SUSPEND)) {
+		ret = imx_pcie->drvdata->enable_ref_clk(imx_pcie, true);
+		if (ret)
+			return ret;
+		ret = imx_pcie_deassert_core_reset(imx_pcie);
+		if (ret)
+			return ret;
+		/*
+		 * Using PCIE_TEST_PD seems to disable MSI and powers down the
+		 * root complex. This is why we have to setup the rc again and
+		 * why we have to restore the MSI register.
+		 */
+		ret = dw_pcie_setup_rc(&imx_pcie->pci->pp);
+		if (ret)
+			return ret;
+		imx_pcie_msi_save_restore(imx_pcie, false);
+	} else {
+		ret = imx_pcie_host_init(pp);
+		if (ret)
+			return ret;
+		imx_pcie_msi_save_restore(imx_pcie, false);
+		dw_pcie_setup_rc(pp);
 
-	if (imx_pcie->link_is_up)
-		imx_pcie_start_link(imx_pcie->pci);
+		if (imx_pcie->link_is_up)
+			imx_pcie_start_link(imx_pcie->pci);
+	}
 
 	return 0;
 }
@@ -1485,7 +1518,9 @@ static const struct imx_pcie_drvdata drvdata[] = {
 	[IMX6Q] = {
 		.variant = IMX6Q,
 		.flags = IMX_PCIE_FLAG_IMX_PHY |
-			 IMX_PCIE_FLAG_IMX_SPEED_CHANGE,
+			 IMX_PCIE_FLAG_IMX_SPEED_CHANGE |
+			 IMX_PCIE_FLAG_BROKEN_SUSPEND |
+			 IMX_PCIE_FLAG_SUPPORTS_SUSPEND,
 		.dbi_length = 0x200,
 		.gpr = "fsl,imx6q-iomuxc-gpr",
 		.clk_names = imx6q_clks,

From b727484cace4be22be9321cc0bc9487648ba447b Mon Sep 17 00:00:00 2001
From: Nirmal Patel <nirmal.patel@linux.ntel.com>
Date: Fri, 11 Oct 2024 10:56:57 -0700
Subject: [PATCH 0933/1530] PCI: vmd: Add DID 8086:B06F and 8086:B60B for Intel
 client SKUs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for this VMD device which supports the bus restriction mode.
The feature that turns off vector 0 for MSI-X remapping is also enabled.

Link: https://lore.kernel.org/r/20241011175657.249948-1-nirmal.patel@linux.intel.com
Signed-off-by: Nirmal Patel <nirmal.patel@linux.ntel.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/vmd.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 264a180403a0e..8a036d6b7d497 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -1100,6 +1100,10 @@ static const struct pci_device_id vmd_ids[] = {
 		.driver_data = VMD_FEATS_CLIENT,},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B),
 		.driver_data = VMD_FEATS_CLIENT,},
+	{PCI_VDEVICE(INTEL, 0xb60b),
+                .driver_data = VMD_FEATS_CLIENT,},
+	{PCI_VDEVICE(INTEL, 0xb06f),
+                .driver_data = VMD_FEATS_CLIENT,},
 	{0,}
 };
 MODULE_DEVICE_TABLE(pci, vmd_ids);

From d66041063192497a4a97d21dbf86b79a03a7f4fb Mon Sep 17 00:00:00 2001
From: Jian-Hong Pan <jhp@endlessos.org>
Date: Tue, 1 Oct 2024 16:34:38 +0800
Subject: [PATCH 0934/1530] PCI: vmd: Set devices to D0 before enabling PM L1
 Substates
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The remapped PCIe Root Port and the child device have PM L1 Substates
capability, but they are disabled originally.

Here is a failed example on ASUS B1400CEAE:

  Capabilities: [900 v1] L1 PM Substates
        L1SubCap: PCI-PM_L1.2+ PCI-PM_L1.1- ASPM_L1.2+ ASPM_L1.1- L1_PM_Substates+
                  PortCommonModeRestoreTime=32us PortTPowerOnTime=10us
        L1SubCtl1: PCI-PM_L1.2- PCI-PM_L1.1- ASPM_L1.2+ ASPM_L1.1-
                   T_CommonMode=0us LTR1.2_Threshold=101376ns
        L1SubCtl2: T_PwrOn=50us

Enable PCI-PM L1 PM Substates for devices below VMD while they are in D0
(see PCIe r6.0, sec 5.5.4).

Link: https://lore.kernel.org/r/20241001083438.10070-4-jhp@endlessos.org
Link: https://bugzilla.kernel.org/show_bug.cgi?id=218394
Signed-off-by: Jian-Hong Pan <jhp@endlessos.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
---
 drivers/pci/controller/vmd.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 264a180403a0e..11870d1fc8189 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -740,11 +740,9 @@ static int vmd_pm_enable_quirk(struct pci_dev *pdev, void *userdata)
 	if (!(features & VMD_FEAT_BIOS_PM_QUIRK))
 		return 0;
 
-	pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL);
-
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_LTR);
 	if (!pos)
-		return 0;
+		goto out_state_change;
 
 	/*
 	 * Skip if the max snoop LTR is non-zero, indicating BIOS has set it
@@ -752,7 +750,7 @@ static int vmd_pm_enable_quirk(struct pci_dev *pdev, void *userdata)
 	 */
 	pci_read_config_dword(pdev, pos + PCI_LTR_MAX_SNOOP_LAT, &ltr_reg);
 	if (!!(ltr_reg & (PCI_LTR_VALUE_MASK | PCI_LTR_SCALE_MASK)))
-		return 0;
+		goto out_state_change;
 
 	/*
 	 * Set the default values to the maximum required by the platform to
@@ -764,6 +762,13 @@ static int vmd_pm_enable_quirk(struct pci_dev *pdev, void *userdata)
 	pci_write_config_dword(pdev, pos + PCI_LTR_MAX_SNOOP_LAT, ltr_reg);
 	pci_info(pdev, "VMD: Default LTR value set by driver\n");
 
+out_state_change:
+	/*
+	 * Ensure devices are in D0 before enabling PCI-PM L1 PM Substates, per
+	 * PCIe r6.0, sec 5.5.4.
+	 */
+	pci_set_power_state_locked(pdev, PCI_D0);
+	pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL);
 	return 0;
 }
 

From 3b96b895127b7c0aed63d82c974b46340e8466c1 Mon Sep 17 00:00:00 2001
From: Esther Shimanovich <eshimanovich@chromium.org>
Date: Tue, 10 Sep 2024 17:57:45 +0000
Subject: [PATCH 0935/1530] PCI: Detect and trust built-in Thunderbolt chips

Some computers with CPUs that lack Thunderbolt features use discrete
Thunderbolt chips to add Thunderbolt functionality. These Thunderbolt
chips are located within the chassis; between the Root Port labeled
ExternalFacingPort and the USB-C port.

These Thunderbolt PCIe devices should be labeled as fixed and trusted, as
they are built into the computer. Otherwise, security policies that rely on
those flags may have unintended results, such as preventing USB-C ports
from enumerating.

Detect the above scenario through the process of elimination.

  1) Integrated Thunderbolt host controllers already have Thunderbolt
     implemented, so anything outside their external facing Root Port is
     removable and untrusted.

     Detect them using the following properties:

       - Most integrated host controllers have the "usb4-host-interface"
         ACPI property, as described here:

         https://learn.microsoft.com/en-us/windows-hardware/drivers/pci/dsd-for-pcie-root-ports#mapping-native-protocols-pcie-displayport-tunneled-through-usb4-to-usb4-host-routers

       - Integrated Thunderbolt PCIe Root Ports before Alder Lake do not
         have the "usb4-host-interface" ACPI property. Identify those by
         their PCI IDs instead.

  2) If a Root Port does not have integrated Thunderbolt capabilities, but
     has the "ExternalFacingPort" ACPI property, that means the
     manufacturer has opted to use a discrete Thunderbolt host controller
     that is built into the computer.

     This host controller can be identified by virtue of being located
     directly below an external-facing Root Port that lacks integrated
     Thunderbolt. Label it as trusted and fixed.

     Everything downstream from it is untrusted and removable.

The "ExternalFacingPort" ACPI property is described here:
https://learn.microsoft.com/en-us/windows-hardware/drivers/pci/dsd-for-pcie-root-ports#identifying-externally-exposed-pcie-root-ports

Link: https://lore.kernel.org/r/20240910-trust-tbt-fix-v5-1-7a7a42a5f496@chromium.org
Suggested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Esther Shimanovich <eshimanovich@chromium.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Tested-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
---
 arch/x86/pci/acpi.c | 119 ++++++++++++++++++++++++++++++++++++++++++++
 drivers/pci/probe.c |  30 ++++++++---
 include/linux/pci.h |   6 +++
 3 files changed, 148 insertions(+), 7 deletions(-)

diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 55c4b07ec1f63..0c316bae1726e 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -250,6 +250,125 @@ void __init pci_acpi_crs_quirks(void)
 		pr_info("Please notify linux-pci@vger.kernel.org so future kernels can do this automatically\n");
 }
 
+/*
+ * Check if pdev is part of a PCIe switch that is directly below the
+ * specified bridge.
+ */
+static bool pcie_switch_directly_under(struct pci_dev *bridge,
+				       struct pci_dev *pdev)
+{
+	struct pci_dev *parent = pci_upstream_bridge(pdev);
+
+	/* If the device doesn't have a parent, it's not under anything */
+	if (!parent)
+		return false;
+
+	/*
+	 * If the device has a PCIe type, check if it is below the
+	 * corresponding PCIe switch components (if applicable). Then check
+	 * if its upstream port is directly beneath the specified bridge.
+	 */
+	switch (pci_pcie_type(pdev)) {
+	case PCI_EXP_TYPE_UPSTREAM:
+		return parent == bridge;
+
+	case PCI_EXP_TYPE_DOWNSTREAM:
+		if (pci_pcie_type(parent) != PCI_EXP_TYPE_UPSTREAM)
+			return false;
+		parent = pci_upstream_bridge(parent);
+		return parent == bridge;
+
+	case PCI_EXP_TYPE_ENDPOINT:
+		if (pci_pcie_type(parent) != PCI_EXP_TYPE_DOWNSTREAM)
+			return false;
+		parent = pci_upstream_bridge(parent);
+		if (!parent || pci_pcie_type(parent) != PCI_EXP_TYPE_UPSTREAM)
+			return false;
+		parent = pci_upstream_bridge(parent);
+		return parent == bridge;
+	}
+
+	return false;
+}
+
+static bool pcie_has_usb4_host_interface(struct pci_dev *pdev)
+{
+	struct fwnode_handle *fwnode;
+
+	/*
+	 * For USB4, the tunneled PCIe Root or Downstream Ports are marked
+	 * with the "usb4-host-interface" ACPI property, so we look for
+	 * that first. This should cover most cases.
+	 */
+	fwnode = fwnode_find_reference(dev_fwnode(&pdev->dev),
+				       "usb4-host-interface", 0);
+	if (!IS_ERR(fwnode)) {
+		fwnode_handle_put(fwnode);
+		return true;
+	}
+
+	/*
+	 * Any integrated Thunderbolt 3/4 PCIe Root Ports from Intel
+	 * before Alder Lake do not have the "usb4-host-interface"
+	 * property so we use their PCI IDs instead. All these are
+	 * tunneled. This list is not expected to grow.
+	 */
+	if (pdev->vendor == PCI_VENDOR_ID_INTEL) {
+		switch (pdev->device) {
+		/* Ice Lake Thunderbolt 3 PCIe Root Ports */
+		case 0x8a1d:
+		case 0x8a1f:
+		case 0x8a21:
+		case 0x8a23:
+		/* Tiger Lake-LP Thunderbolt 4 PCIe Root Ports */
+		case 0x9a23:
+		case 0x9a25:
+		case 0x9a27:
+		case 0x9a29:
+		/* Tiger Lake-H Thunderbolt 4 PCIe Root Ports */
+		case 0x9a2b:
+		case 0x9a2d:
+		case 0x9a2f:
+		case 0x9a31:
+			return true;
+		}
+	}
+
+	return false;
+}
+
+bool arch_pci_dev_is_removable(struct pci_dev *pdev)
+{
+	struct pci_dev *parent, *root;
+
+	/* pdev without a parent or Root Port is never tunneled */
+	parent = pci_upstream_bridge(pdev);
+	if (!parent)
+		return false;
+	root = pcie_find_root_port(pdev);
+	if (!root)
+		return false;
+
+	/* Internal PCIe devices are not tunneled */
+	if (!root->external_facing)
+		return false;
+
+	/* Anything directly behind a "usb4-host-interface" is tunneled */
+	if (pcie_has_usb4_host_interface(parent))
+		return true;
+
+	/*
+	 * Check if this is a discrete Thunderbolt/USB4 controller that is
+	 * directly behind the non-USB4 PCIe Root Port marked as
+	 * "ExternalFacingPort". Those are not behind a PCIe tunnel.
+	 */
+	if (pcie_switch_directly_under(root, pdev))
+		return false;
+
+	/* PCIe devices after the discrete chip are tunneled */
+	return true;
+}
+
 #ifdef	CONFIG_PCI_MMCONFIG
 static int check_segment(u16 seg, struct device *dev, char *estr)
 {
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 4f68414c30860..924b23962c457 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1633,23 +1633,33 @@ static void set_pcie_thunderbolt(struct pci_dev *dev)
 
 static void set_pcie_untrusted(struct pci_dev *dev)
 {
-	struct pci_dev *parent;
+	struct pci_dev *parent = pci_upstream_bridge(dev);
 
+	if (!parent)
+		return;
 	/*
-	 * If the upstream bridge is untrusted we treat this device
+	 * If the upstream bridge is untrusted we treat this device as
 	 * untrusted as well.
 	 */
-	parent = pci_upstream_bridge(dev);
-	if (parent && (parent->untrusted || parent->external_facing))
+	if (parent->untrusted) {
+		dev->untrusted = true;
+		return;
+	}
+
+	if (arch_pci_dev_is_removable(dev)) {
+		pci_dbg(dev, "marking as untrusted\n");
 		dev->untrusted = true;
+	}
 }
 
 static void pci_set_removable(struct pci_dev *dev)
 {
 	struct pci_dev *parent = pci_upstream_bridge(dev);
 
+	if (!parent)
+		return;
 	/*
-	 * We (only) consider everything downstream from an external_facing
+	 * We (only) consider everything tunneled below an external_facing
 	 * device to be removable by the user. We're mainly concerned with
 	 * consumer platforms with user accessible thunderbolt ports that are
 	 * vulnerable to DMA attacks, and we expect those ports to be marked by
@@ -1659,9 +1669,15 @@ static void pci_set_removable(struct pci_dev *dev)
 	 * accessible to user / may not be removed by end user, and thus not
 	 * exposed as "removable" to userspace.
 	 */
-	if (parent &&
-	    (parent->external_facing || dev_is_removable(&parent->dev)))
+	if (dev_is_removable(&parent->dev)) {
+		dev_set_removable(&dev->dev, DEVICE_REMOVABLE);
+		return;
+	}
+
+	if (arch_pci_dev_is_removable(dev)) {
+		pci_dbg(dev, "marking as removable\n");
 		dev_set_removable(&dev->dev, DEVICE_REMOVABLE);
+	}
 }
 
 /**
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 573b4c4c2be61..4e77c4230c0a1 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2609,6 +2609,12 @@ pci_host_bridge_acpi_msi_domain(struct pci_bus *bus) { return NULL; }
 static inline bool pci_pr3_present(struct pci_dev *pdev) { return false; }
 #endif
 
+#if defined(CONFIG_X86) && defined(CONFIG_ACPI)
+bool arch_pci_dev_is_removable(struct pci_dev *pdev);
+#else
+static inline bool arch_pci_dev_is_removable(struct pci_dev *pdev) { return false; }
+#endif
+
 #ifdef CONFIG_EEH
 static inline struct eeh_dev *pci_dev_to_eeh_dev(struct pci_dev *pdev)
 {

From d49df3d39244f57957ec744fc5e560939ecb4290 Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Thu, 31 Oct 2024 15:00:33 +0000
Subject: [PATCH 0936/1530] scsi: MAINTAINERS: Update UFS Exynos entry

Add myself as a reviewer for ufs-exynos as I'm doing various work in
this driver currently for gs101 SoC and would like to help review
relevant patches.

Additionally add the linux-samsung-soc@vger.kernel.org list as that is
relevant to this driver.

Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Acked-by: Alim Akhtar <alim.akhtar@samsung.com>
Link: https://lore.kernel.org/r/20241031150033.3440894-15-peter.griffin@linaro.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 MAINTAINERS | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index c27f3190737f8..6b5e9f0ffc921 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -23816,7 +23816,9 @@ F:	drivers/ufs/host/*dwc*
 
 UNIVERSAL FLASH STORAGE HOST CONTROLLER DRIVER EXYNOS HOOKS
 M:	Alim Akhtar <alim.akhtar@samsung.com>
+R:	Peter Griffin <peter.griffin@linaro.org>
 L:	linux-scsi@vger.kernel.org
+L:	linux-samsung-soc@vger.kernel.org
 S:	Maintained
 F:	drivers/ufs/host/ufs-exynos*
 

From 7670e74ff31939acd792ff59fa83bc73d040dd8e Mon Sep 17 00:00:00 2001
From: Ed Tsai <ed.tsai@mediatek.com>
Date: Tue, 8 Oct 2024 14:59:42 +0800
Subject: [PATCH 0937/1530] scsi: ufs: ufs-mediatek: Configure individual LU
 queue flags

Previously, ufs vops config_scsi_dev was removed because there were no
users. ufs-mediatek needs it to configure the queue flags for each LU
individually. Therefore, bring it back and customize the queue flag as
required.

[mkp: fixed typo]

Signed-off-by: Ed Tsai <ed.tsai@mediatek.com>
Link: https://lore.kernel.org/r/20241008065950.23431-1-ed.tsai@mediatek.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c       |  3 +++
 drivers/ufs/host/ufs-mediatek.c | 10 ++++++++++
 include/ufs/ufshcd.h            |  1 +
 3 files changed, 14 insertions(+)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 5607aad42469a..e338867bc96ca 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -5235,6 +5235,9 @@ static int ufshcd_device_configure(struct scsi_device *sdev,
 	 */
 	sdev->silence_suspend = 1;
 
+	if (hba->vops && hba->vops->config_scsi_dev)
+		hba->vops->config_scsi_dev(sdev);
+
 	ufshcd_crypto_register(hba, q);
 
 	return 0;
diff --git a/drivers/ufs/host/ufs-mediatek.c b/drivers/ufs/host/ufs-mediatek.c
index 9a5919434c4e0..06ab1e5e8b6fb 100644
--- a/drivers/ufs/host/ufs-mediatek.c
+++ b/drivers/ufs/host/ufs-mediatek.c
@@ -1780,6 +1780,15 @@ static int ufs_mtk_config_esi(struct ufs_hba *hba)
 	return ufs_mtk_config_mcq(hba, true);
 }
 
+static void ufs_mtk_config_scsi_dev(struct scsi_device *sdev)
+{
+	struct ufs_hba *hba = shost_priv(sdev->host);
+
+	dev_dbg(hba->dev, "lu %llu scsi device configured", sdev->lun);
+	if (sdev->lun == 2)
+		blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, sdev->request_queue);
+}
+
 /*
  * struct ufs_hba_mtk_vops - UFS MTK specific variant operations
  *
@@ -1809,6 +1818,7 @@ static const struct ufs_hba_variant_ops ufs_hba_mtk_vops = {
 	.op_runtime_config   = ufs_mtk_op_runtime_config,
 	.mcq_config_resource = ufs_mtk_mcq_config_resource,
 	.config_esi          = ufs_mtk_config_esi,
+	.config_scsi_dev     = ufs_mtk_config_scsi_dev,
 };
 
 /**
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index 9ea2a7411bb58..d7aca9e61684f 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -386,6 +386,7 @@ struct ufs_hba_variant_ops {
 	int	(*get_outstanding_cqs)(struct ufs_hba *hba,
 				       unsigned long *ocqs);
 	int	(*config_esi)(struct ufs_hba *hba);
+	void	(*config_scsi_dev)(struct scsi_device *sdev);
 };
 
 /* clock gating state  */

From c8d81a438544a8c439b89bd88cfdc35117011658 Mon Sep 17 00:00:00 2001
From: Salomon Dushimirimana <salomondush@google.com>
Date: Wed, 16 Oct 2024 22:09:44 +0000
Subject: [PATCH 0938/1530] scsi: pm8001: Use module param to set pcs event log
 severity

The pm8001 driver sets pcs event log threshold very high which causes
most of the FW log messages to not be captured. Add a module parameter
to configure pcs event log severity with 3 (medium severity) as the
default.

Co-developed-by: Bhavesh Jashnani <bjashnani@google.com>
Signed-off-by: Bhavesh Jashnani <bjashnani@google.com>
Signed-off-by: Salomon Dushimirimana <salomondush@google.com>
Link: https://lore.kernel.org/r/20241016220944.370539-1-salomondush@google.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/pm8001/pm8001_init.c | 4 ++++
 drivers/scsi/pm8001/pm8001_sas.h  | 2 ++
 drivers/scsi/pm8001/pm80xx_hwi.c  | 3 ++-
 3 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index 33e1eba62ca12..4872d13f5d59f 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -68,6 +68,10 @@ static bool pm8001_read_wwn = true;
 module_param_named(read_wwn, pm8001_read_wwn, bool, 0444);
 MODULE_PARM_DESC(zoned, "Get WWN from the controller. Default: true");
 
+uint pcs_event_log_severity = 0x03;
+module_param(pcs_event_log_severity, int, 0644);
+MODULE_PARM_DESC(pcs_event_log_severity, "PCS event log severity level");
+
 static struct scsi_transport_template *pm8001_stt;
 static int pm8001_init_ccb_tag(struct pm8001_hba_info *);
 
diff --git a/drivers/scsi/pm8001/pm8001_sas.h b/drivers/scsi/pm8001/pm8001_sas.h
index ced6721380a85..42c7b3f7afbf1 100644
--- a/drivers/scsi/pm8001/pm8001_sas.h
+++ b/drivers/scsi/pm8001/pm8001_sas.h
@@ -96,6 +96,8 @@ extern struct list_head hba_list;
 extern const struct pm8001_dispatch pm8001_8001_dispatch;
 extern const struct pm8001_dispatch pm8001_80xx_dispatch;
 
+extern uint pcs_event_log_severity;
+
 struct pm8001_hba_info;
 struct pm8001_ccb_info;
 struct pm8001_device;
diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c
index a9869cd8c4c07..e65951dd2024e 100644
--- a/drivers/scsi/pm8001/pm80xx_hwi.c
+++ b/drivers/scsi/pm8001/pm80xx_hwi.c
@@ -763,7 +763,8 @@ static void init_default_table_values(struct pm8001_hba_info *pm8001_ha)
 		pm8001_ha->memoryMap.region[IOP].phys_addr_lo;
 	pm8001_ha->main_cfg_tbl.pm80xx_tbl.pcs_event_log_size		=
 							PM8001_EVENT_LOG_SIZE;
-	pm8001_ha->main_cfg_tbl.pm80xx_tbl.pcs_event_log_severity	= 0x01;
+	pm8001_ha->main_cfg_tbl.pm80xx_tbl.pcs_event_log_severity	=
+		pcs_event_log_severity;
 	pm8001_ha->main_cfg_tbl.pm80xx_tbl.fatal_err_interrupt		= 0x01;
 
 	/* Enable higher IQs and OQs, 32 to 63, bit 16 */

From 4501ea5f0a5ca1a3fe58ef7b48f1bd3829c6c7e5 Mon Sep 17 00:00:00 2001
From: Igor Pylypiv <ipylypiv@google.com>
Date: Mon, 21 Oct 2024 13:18:28 -0700
Subject: [PATCH 0939/1530] scsi: pm8001: Initialize devices in
 pm8001_alloc_dev()

Devices can be allocated and freed at runtime. For example during a soft
reset all devices are freed and reallocated upon discovery.

Currently the driver fully initializes devices once in pm8001_alloc().
Allows initialization steps to happen during runtime, avoiding any
leftover states from the device being freed.

Signed-off-by: Igor Pylypiv <ipylypiv@google.com>
Signed-off-by: Terrence Adams <tadamsjr@google.com>
Link: https://lore.kernel.org/r/20241021201828.1378858-1-tadamsjr@google.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/pm8001/pm8001_init.c |  3 ---
 drivers/scsi/pm8001/pm8001_sas.c  | 17 ++++++++++++-----
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index 4872d13f5d59f..dce40d02b73c3 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -451,9 +451,6 @@ static int pm8001_alloc(struct pm8001_hba_info *pm8001_ha,
 	}
 	for (i = 0; i < PM8001_MAX_DEVICES; i++) {
 		pm8001_ha->devices[i].dev_type = SAS_PHY_UNUSED;
-		pm8001_ha->devices[i].id = i;
-		pm8001_ha->devices[i].device_id = PM8001_MAX_DEVICES;
-		atomic_set(&pm8001_ha->devices[i].running_req, 0);
 	}
 	pm8001_ha->flags = PM8001F_INIT_TIME;
 	return 0;
diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index ee2da8e49d4cf..d80cffd25a6ed 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -572,6 +572,13 @@ void pm8001_ccb_task_free(struct pm8001_hba_info *pm8001_ha,
 	pm8001_ccb_free(pm8001_ha, ccb);
 }
 
+static void pm8001_init_dev(struct pm8001_device *pm8001_dev, int id)
+{
+	pm8001_dev->id = id;
+	pm8001_dev->device_id = PM8001_MAX_DEVICES;
+	atomic_set(&pm8001_dev->running_req, 0);
+}
+
 /**
  * pm8001_alloc_dev - find a empty pm8001_device
  * @pm8001_ha: our hba card information
@@ -580,9 +587,11 @@ static struct pm8001_device *pm8001_alloc_dev(struct pm8001_hba_info *pm8001_ha)
 {
 	u32 dev;
 	for (dev = 0; dev < PM8001_MAX_DEVICES; dev++) {
-		if (pm8001_ha->devices[dev].dev_type == SAS_PHY_UNUSED) {
-			pm8001_ha->devices[dev].id = dev;
-			return &pm8001_ha->devices[dev];
+		struct pm8001_device *pm8001_dev = &pm8001_ha->devices[dev];
+
+		if (pm8001_dev->dev_type == SAS_PHY_UNUSED) {
+			pm8001_init_dev(pm8001_dev, dev);
+			return pm8001_dev;
 		}
 	}
 	if (dev == PM8001_MAX_DEVICES) {
@@ -613,9 +622,7 @@ struct pm8001_device *pm8001_find_dev(struct pm8001_hba_info *pm8001_ha,
 
 void pm8001_free_dev(struct pm8001_device *pm8001_dev)
 {
-	u32 id = pm8001_dev->id;
 	memset(pm8001_dev, 0, sizeof(*pm8001_dev));
-	pm8001_dev->id = id;
 	pm8001_dev->dev_type = SAS_PHY_UNUSED;
 	pm8001_dev->device_id = PM8001_MAX_DEVICES;
 	pm8001_dev->sas_device = NULL;

From 53b550de463529f88c78526288260d4194cf4061 Mon Sep 17 00:00:00 2001
From: Igor Pylypiv <ipylypiv@google.com>
Date: Fri, 25 Oct 2024 18:50:09 +0000
Subject: [PATCH 0940/1530] scsi: pm8001: Increase request sg length to support
 4MiB requests

Increasing the per-request size maximum to 4MiB (8192 sectors x 512
bytes) runs into the per-device DMA scatter gather list limit
(max_segments) for users of the io vector system calls (e.g. readv and
writev).

Increase the max scatter gather list length to 1024 to enable kernel to
send 4MiB (1024 * 4KiB page size) requests.

Signed-off-by: Igor Pylypiv <ipylypiv@google.com>
Link: https://lore.kernel.org/r/20241025185009.3278297-1-ipylypiv@google.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/pm8001/pm8001_defs.h | 7 +++++--
 drivers/scsi/pm8001/pm8001_init.c | 1 +
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/pm8001/pm8001_defs.h b/drivers/scsi/pm8001/pm8001_defs.h
index 501b574239e8b..7871e29a820a0 100644
--- a/drivers/scsi/pm8001/pm8001_defs.h
+++ b/drivers/scsi/pm8001/pm8001_defs.h
@@ -92,8 +92,11 @@ enum port_type {
 #define	PM8001_MAX_MSIX_VEC	 64	/* max msi-x int for spcv/ve */
 #define	PM8001_RESERVE_SLOT	 8
 
-#define	CONFIG_SCSI_PM8001_MAX_DMA_SG	528
-#define PM8001_MAX_DMA_SG	CONFIG_SCSI_PM8001_MAX_DMA_SG
+#define PM8001_SECTOR_SIZE	512
+#define PM8001_PAGE_SIZE_4K	4096
+#define PM8001_MAX_IO_SIZE	(4 * 1024 * 1024)
+#define PM8001_MAX_DMA_SG	(PM8001_MAX_IO_SIZE / PM8001_PAGE_SIZE_4K)
+#define PM8001_MAX_SECTORS	(PM8001_MAX_IO_SIZE / PM8001_SECTOR_SIZE)
 
 enum memory_region_num {
 	AAP1 = 0x0, /* application acceleration processor */
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index dce40d02b73c3..f8c81e53e93f7 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -121,6 +121,7 @@ static const struct scsi_host_template pm8001_sht = {
 	.scan_start		= pm8001_scan_start,
 	.can_queue		= 1,
 	.sg_tablesize		= PM8001_MAX_DMA_SG,
+	.max_sectors		= PM8001_MAX_SECTORS,
 	.shost_groups		= pm8001_host_groups,
 	.sdev_groups		= pm8001_sdev_groups,
 	.track_queue_depth	= 1,

From f8da4c1cad5f836765bf147572872bfd0c3eb271 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@baylibre.com>
Date: Mon, 28 Oct 2024 09:07:55 +0100
Subject: [PATCH 0941/1530] scsi: Switch back to struct
 platform_driver::remove()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 0edb555a65d1 ("platform: Make platform_driver::remove()
return void") .remove() is (again) the right callback to implement for
platform drivers.

Convert all platform drivers below drivers/scsi to use .remove(), with
the eventual goal to drop struct platform_driver::remove_new(). As
.remove() and .remove_new() have the same prototypes, conversion is done
by just changing the structure member name in the driver initializer.

On the way do a few whitespace changes to make indention consistent.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Link: https://lore.kernel.org/r/20241028080754.429191-2-u.kleine-koenig@baylibre.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/a3000.c                   | 6 +++---
 drivers/scsi/a4000t.c                  | 6 +++---
 drivers/scsi/atari_scsi.c              | 2 +-
 drivers/scsi/bvme6000_scsi.c           | 2 +-
 drivers/scsi/hisi_sas/hisi_sas_v1_hw.c | 2 +-
 drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 2 +-
 drivers/scsi/jazz_esp.c                | 2 +-
 drivers/scsi/mac_esp.c                 | 2 +-
 drivers/scsi/mac_scsi.c                | 2 +-
 drivers/scsi/mvme16x_scsi.c            | 2 +-
 drivers/scsi/qlogicpti.c               | 2 +-
 drivers/scsi/sgiwd93.c                 | 2 +-
 drivers/scsi/sni_53c710.c              | 2 +-
 drivers/scsi/sun3_scsi.c               | 2 +-
 drivers/scsi/sun3x_esp.c               | 2 +-
 drivers/scsi/sun_esp.c                 | 2 +-
 16 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/drivers/scsi/a3000.c b/drivers/scsi/a3000.c
index ad39797890e59..bf054dd7682bf 100644
--- a/drivers/scsi/a3000.c
+++ b/drivers/scsi/a3000.c
@@ -302,9 +302,9 @@ static void __exit amiga_a3000_scsi_remove(struct platform_device *pdev)
  * triggering a section mismatch warning.
  */
 static struct platform_driver amiga_a3000_scsi_driver __refdata = {
-	.remove_new = __exit_p(amiga_a3000_scsi_remove),
-	.driver   = {
-		.name	= "amiga-a3000-scsi",
+	.remove = __exit_p(amiga_a3000_scsi_remove),
+	.driver = {
+		.name = "amiga-a3000-scsi",
 	},
 };
 
diff --git a/drivers/scsi/a4000t.c b/drivers/scsi/a4000t.c
index d9103adc87fef..75b43047a1558 100644
--- a/drivers/scsi/a4000t.c
+++ b/drivers/scsi/a4000t.c
@@ -115,9 +115,9 @@ static void __exit amiga_a4000t_scsi_remove(struct platform_device *pdev)
  * triggering a section mismatch warning.
  */
 static struct platform_driver amiga_a4000t_scsi_driver __refdata = {
-	.remove_new = __exit_p(amiga_a4000t_scsi_remove),
-	.driver   = {
-		.name	= "amiga-a4000t-scsi",
+	.remove = __exit_p(amiga_a4000t_scsi_remove),
+	.driver = {
+		.name = "amiga-a4000t-scsi",
 	},
 };
 
diff --git a/drivers/scsi/atari_scsi.c b/drivers/scsi/atari_scsi.c
index 98a1b966a0b07..85055677666c5 100644
--- a/drivers/scsi/atari_scsi.c
+++ b/drivers/scsi/atari_scsi.c
@@ -885,7 +885,7 @@ static void __exit atari_scsi_remove(struct platform_device *pdev)
  * triggering a section mismatch warning.
  */
 static struct platform_driver atari_scsi_driver __refdata = {
-	.remove_new = __exit_p(atari_scsi_remove),
+	.remove = __exit_p(atari_scsi_remove),
 	.driver = {
 		.name	= DRV_MODULE_NAME,
 	},
diff --git a/drivers/scsi/bvme6000_scsi.c b/drivers/scsi/bvme6000_scsi.c
index f893e9779e9de..baf5f4e479378 100644
--- a/drivers/scsi/bvme6000_scsi.c
+++ b/drivers/scsi/bvme6000_scsi.c
@@ -106,7 +106,7 @@ static struct platform_driver bvme6000_scsi_driver = {
 		.name		= "bvme6000-scsi",
 	},
 	.probe		= bvme6000_probe,
-	.remove_new	= bvme6000_device_remove,
+	.remove		= bvme6000_device_remove,
 };
 
 static int __init bvme6000_scsi_init(void)
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 70bba55bc5d02..c3e571be22220 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -1802,7 +1802,7 @@ MODULE_DEVICE_TABLE(acpi, sas_v1_acpi_match);
 
 static struct platform_driver hisi_sas_v1_driver = {
 	.probe = hisi_sas_v1_probe,
-	.remove_new = hisi_sas_remove,
+	.remove = hisi_sas_remove,
 	.driver = {
 		.name = DRV_NAME,
 		.of_match_table = sas_v1_of_match,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index ab6668dc5b77c..1a62b5d15eca7 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -3649,7 +3649,7 @@ MODULE_DEVICE_TABLE(acpi, sas_v2_acpi_match);
 
 static struct platform_driver hisi_sas_v2_driver = {
 	.probe = hisi_sas_v2_probe,
-	.remove_new = hisi_sas_remove,
+	.remove = hisi_sas_remove,
 	.driver = {
 		.name = DRV_NAME,
 		.of_match_table = sas_v2_of_match,
diff --git a/drivers/scsi/jazz_esp.c b/drivers/scsi/jazz_esp.c
index fb04b0b515ab1..35137f5cfb3a8 100644
--- a/drivers/scsi/jazz_esp.c
+++ b/drivers/scsi/jazz_esp.c
@@ -196,7 +196,7 @@ MODULE_ALIAS("platform:jazz_esp");
 
 static struct platform_driver esp_jazz_driver = {
 	.probe		= esp_jazz_probe,
-	.remove_new	= esp_jazz_remove,
+	.remove		= esp_jazz_remove,
 	.driver	= {
 		.name	= "jazz_esp",
 	},
diff --git a/drivers/scsi/mac_esp.c b/drivers/scsi/mac_esp.c
index 187ae0a65d404..ff0253d47a0e8 100644
--- a/drivers/scsi/mac_esp.c
+++ b/drivers/scsi/mac_esp.c
@@ -432,7 +432,7 @@ static void esp_mac_remove(struct platform_device *dev)
 
 static struct platform_driver esp_mac_driver = {
 	.probe    = esp_mac_probe,
-	.remove_new = esp_mac_remove,
+	.remove   = esp_mac_remove,
 	.driver   = {
 		.name	= DRV_MODULE_NAME,
 	},
diff --git a/drivers/scsi/mac_scsi.c b/drivers/scsi/mac_scsi.c
index f225bb20aa220..a86bd839d08e9 100644
--- a/drivers/scsi/mac_scsi.c
+++ b/drivers/scsi/mac_scsi.c
@@ -547,7 +547,7 @@ static void __exit mac_scsi_remove(struct platform_device *pdev)
  * triggering a section mismatch warning.
  */
 static struct platform_driver mac_scsi_driver __refdata = {
-	.remove_new = __exit_p(mac_scsi_remove),
+	.remove = __exit_p(mac_scsi_remove),
 	.driver = {
 		.name	= DRV_MODULE_NAME,
 	},
diff --git a/drivers/scsi/mvme16x_scsi.c b/drivers/scsi/mvme16x_scsi.c
index e08a38e2a442b..9b19d5205e508 100644
--- a/drivers/scsi/mvme16x_scsi.c
+++ b/drivers/scsi/mvme16x_scsi.c
@@ -127,7 +127,7 @@ static struct platform_driver mvme16x_scsi_driver = {
 		.name           = "mvme16x-scsi",
 	},
 	.probe          = mvme16x_probe,
-	.remove_new     = mvme16x_device_remove,
+	.remove         = mvme16x_device_remove,
 };
 
 static int __init mvme16x_scsi_init(void)
diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c
index 6177f4798f3ac..74866b9f2b145 100644
--- a/drivers/scsi/qlogicpti.c
+++ b/drivers/scsi/qlogicpti.c
@@ -1463,7 +1463,7 @@ static struct platform_driver qpti_sbus_driver = {
 		.of_match_table = qpti_match,
 	},
 	.probe		= qpti_sbus_probe,
-	.remove_new	= qpti_sbus_remove,
+	.remove		= qpti_sbus_remove,
 };
 module_platform_driver(qpti_sbus_driver);
 
diff --git a/drivers/scsi/sgiwd93.c b/drivers/scsi/sgiwd93.c
index b0bef83db7b60..6594661db5f40 100644
--- a/drivers/scsi/sgiwd93.c
+++ b/drivers/scsi/sgiwd93.c
@@ -306,7 +306,7 @@ static void sgiwd93_remove(struct platform_device *pdev)
 
 static struct platform_driver sgiwd93_driver = {
 	.probe  = sgiwd93_probe,
-	.remove_new = sgiwd93_remove,
+	.remove = sgiwd93_remove,
 	.driver = {
 		.name   = "sgiwd93",
 	}
diff --git a/drivers/scsi/sni_53c710.c b/drivers/scsi/sni_53c710.c
index 9df1c90a24c11..d1d2556c8fc4b 100644
--- a/drivers/scsi/sni_53c710.c
+++ b/drivers/scsi/sni_53c710.c
@@ -119,7 +119,7 @@ static void snirm710_driver_remove(struct platform_device *dev)
 
 static struct platform_driver snirm710_driver = {
 	.probe	= snirm710_probe,
-	.remove_new = snirm710_driver_remove,
+	.remove	= snirm710_driver_remove,
 	.driver	= {
 		.name	= "snirm_53c710",
 	},
diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c
index fffc0fa525940..bb47274d920dc 100644
--- a/drivers/scsi/sun3_scsi.c
+++ b/drivers/scsi/sun3_scsi.c
@@ -657,7 +657,7 @@ static void __exit sun3_scsi_remove(struct platform_device *pdev)
 }
 
 static struct platform_driver sun3_scsi_driver = {
-	.remove_new = __exit_p(sun3_scsi_remove),
+	.remove = __exit_p(sun3_scsi_remove),
 	.driver = {
 		.name	= DRV_MODULE_NAME,
 	},
diff --git a/drivers/scsi/sun3x_esp.c b/drivers/scsi/sun3x_esp.c
index e20f314cf3e7d..365406885b8ef 100644
--- a/drivers/scsi/sun3x_esp.c
+++ b/drivers/scsi/sun3x_esp.c
@@ -265,7 +265,7 @@ static void esp_sun3x_remove(struct platform_device *dev)
 
 static struct platform_driver esp_sun3x_driver = {
 	.probe          = esp_sun3x_probe,
-	.remove_new     = esp_sun3x_remove,
+	.remove         = esp_sun3x_remove,
 	.driver = {
 		.name   = "sun3x_esp",
 	},
diff --git a/drivers/scsi/sun_esp.c b/drivers/scsi/sun_esp.c
index 5ce6c9d19d1e6..aa430501f0c71 100644
--- a/drivers/scsi/sun_esp.c
+++ b/drivers/scsi/sun_esp.c
@@ -603,7 +603,7 @@ static struct platform_driver esp_sbus_driver = {
 		.of_match_table = esp_match,
 	},
 	.probe		= esp_sbus_probe,
-	.remove_new	= esp_sbus_remove,
+	.remove		= esp_sbus_remove,
 };
 module_platform_driver(esp_sbus_driver);
 

From 84c1e27e6c64919812824a60001988fc384840ce Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Mon, 28 Oct 2024 11:24:29 +0100
Subject: [PATCH 0942/1530] scsi: ufs: Replace deprecated PCI functions

pcim_iomap_regions() and pcim_iomap_table() have been deprecated in
commit e354bb84a4c1 ("PCI: Deprecate pcim_iomap_table(),
pcim_iomap_regions_request_all()").

Replace these functions with pcim_iomap_region().

Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Link: https://lore.kernel.org/r/20241028102428.23118-2-pstanner@redhat.com
Reviewed-by: Bean Huo <beanhuo@micron.com>
Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/tc-dwc-g210-pci.c | 8 +++-----
 drivers/ufs/host/ufshcd-pci.c      | 8 +++-----
 2 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/drivers/ufs/host/tc-dwc-g210-pci.c b/drivers/ufs/host/tc-dwc-g210-pci.c
index 876781fd6861e..0167d8bef71a1 100644
--- a/drivers/ufs/host/tc-dwc-g210-pci.c
+++ b/drivers/ufs/host/tc-dwc-g210-pci.c
@@ -80,14 +80,12 @@ tc_dwc_g210_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	pci_set_master(pdev);
 
-	err = pcim_iomap_regions(pdev, 1 << 0, UFSHCD);
-	if (err < 0) {
+	mmio_base = pcim_iomap_region(pdev, 0, UFSHCD);
+	if (IS_ERR(mmio_base)) {
 		dev_err(&pdev->dev, "request and iomap failed\n");
-		return err;
+		return PTR_ERR(mmio_base);
 	}
 
-	mmio_base = pcim_iomap_table(pdev)[0];
-
 	err = ufshcd_alloc_host(&pdev->dev, &hba);
 	if (err) {
 		dev_err(&pdev->dev, "Allocation failed\n");
diff --git a/drivers/ufs/host/ufshcd-pci.c b/drivers/ufs/host/ufshcd-pci.c
index 54e0cc0653a24..ea39c5d5b8cf1 100644
--- a/drivers/ufs/host/ufshcd-pci.c
+++ b/drivers/ufs/host/ufshcd-pci.c
@@ -588,14 +588,12 @@ ufshcd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	pci_set_master(pdev);
 
-	err = pcim_iomap_regions(pdev, 1 << 0, UFSHCD);
-	if (err < 0) {
+	mmio_base = pcim_iomap_region(pdev, 0, UFSHCD);
+	if (IS_ERR(mmio_base)) {
 		dev_err(&pdev->dev, "request and iomap failed\n");
-		return err;
+		return PTR_ERR(mmio_base);
 	}
 
-	mmio_base = pcim_iomap_table(pdev)[0];
-
 	err = ufshcd_alloc_host(&pdev->dev, &hba);
 	if (err) {
 		dev_err(&pdev->dev, "Allocation failed\n");

From da5aeca99dd0b6c7bf6679382756ea6bda195f72 Mon Sep 17 00:00:00 2001
From: Baolin Liu <liubaolin@kylinos.cn>
Date: Wed, 30 Oct 2024 10:18:00 +0800
Subject: [PATCH 0943/1530] scsi: target: Fix incorrect function name in
 pscsi_create_type_disk()

In pr_err(), bdev_open_by_path() should be renamed to
bdev_file_open_by_path()

Fixes: 034f0cf8fdf9 ("target: port block device access to file")
Signed-off-by: Baolin Liu <liubaolin@kylinos.cn>
Link: https://lore.kernel.org/r/20241030021800.234980-1-liubaolin12138@163.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_pscsi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index f98ebb18666bf..da7017113f92a 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -369,7 +369,7 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd)
 	bdev_file = bdev_file_open_by_path(dev->udev_path,
 				BLK_OPEN_WRITE | BLK_OPEN_READ, pdv, NULL);
 	if (IS_ERR(bdev_file)) {
-		pr_err("pSCSI: bdev_open_by_path() failed\n");
+		pr_err("pSCSI: bdev_file_open_by_path() failed\n");
 		scsi_device_put(sd);
 		return PTR_ERR(bdev_file);
 	}

From 2e8375df86490bf4c1aa5f5973fb031998e1542f Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sat, 2 Nov 2024 22:03:36 +0000
Subject: [PATCH 0944/1530] scsi: esas2r: Remove unused esas2r_build_cli_req()

esas2r_build_cli_req() has been unused since it was added in 2013 by
commit 26780d9e12ed ("[SCSI] esas2r: ATTO Technology ExpressSAS 6G
SAS/SATA RAID Adapter Driver")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://lore.kernel.org/r/20241102220336.80541-1-linux@treblig.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/esas2r/esas2r.h     |  4 ----
 drivers/scsi/esas2r/esas2r_vda.c | 17 -----------------
 2 files changed, 21 deletions(-)

diff --git a/drivers/scsi/esas2r/esas2r.h b/drivers/scsi/esas2r/esas2r.h
index 8a133254c4f65..1e2d7c63a8e36 100644
--- a/drivers/scsi/esas2r/esas2r.h
+++ b/drivers/scsi/esas2r/esas2r.h
@@ -1045,10 +1045,6 @@ void esas2r_build_mgt_req(struct esas2r_adapter *a,
 			  u32 length,
 			  void *data);
 void esas2r_build_ae_req(struct esas2r_adapter *a, struct esas2r_request *rq);
-void esas2r_build_cli_req(struct esas2r_adapter *a,
-			  struct esas2r_request *rq,
-			  u32 length,
-			  u32 cmd_rsp_len);
 void esas2r_build_ioctl_req(struct esas2r_adapter *a,
 			    struct esas2r_request *rq,
 			    u32 length,
diff --git a/drivers/scsi/esas2r/esas2r_vda.c b/drivers/scsi/esas2r/esas2r_vda.c
index 30028e56df637..5aa728704dfcb 100644
--- a/drivers/scsi/esas2r/esas2r_vda.c
+++ b/drivers/scsi/esas2r/esas2r_vda.c
@@ -444,23 +444,6 @@ void esas2r_build_ae_req(struct esas2r_adapter *a, struct esas2r_request *rq)
 	}
 }
 
-/* Build a VDA CLI request. */
-void esas2r_build_cli_req(struct esas2r_adapter *a,
-			  struct esas2r_request *rq,
-			  u32 length,
-			  u32 cmd_rsp_len)
-{
-	struct atto_vda_cli_req *vrq = &rq->vrq->cli;
-
-	clear_vda_request(rq);
-
-	rq->vrq->scsi.function = VDA_FUNC_CLI;
-
-	vrq->length = cpu_to_le32(length);
-	vrq->cmd_rsp_len = cpu_to_le32(cmd_rsp_len);
-	vrq->sg_list_offset = (u8)offsetof(struct atto_vda_cli_req, sge);
-}
-
 /* Build a VDA IOCTL request. */
 void esas2r_build_ioctl_req(struct esas2r_adapter *a,
 			    struct esas2r_request *rq,

From 178b8f38932d635e90f5f0e9af1986c6f4a89271 Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Wed, 23 Oct 2024 09:18:09 +0800
Subject: [PATCH 0945/1530] scsi: bfa: Fix use-after-free in
 bfad_im_module_exit()

BUG: KASAN: slab-use-after-free in __lock_acquire+0x2aca/0x3a20
Read of size 8 at addr ffff8881082d80c8 by task modprobe/25303

Call Trace:
 <TASK>
 dump_stack_lvl+0x95/0xe0
 print_report+0xcb/0x620
 kasan_report+0xbd/0xf0
 __lock_acquire+0x2aca/0x3a20
 lock_acquire+0x19b/0x520
 _raw_spin_lock+0x2b/0x40
 attribute_container_unregister+0x30/0x160
 fc_release_transport+0x19/0x90 [scsi_transport_fc]
 bfad_im_module_exit+0x23/0x60 [bfa]
 bfad_init+0xdb/0xff0 [bfa]
 do_one_initcall+0xdc/0x550
 do_init_module+0x22d/0x6b0
 load_module+0x4e96/0x5ff0
 init_module_from_file+0xcd/0x130
 idempotent_init_module+0x330/0x620
 __x64_sys_finit_module+0xb3/0x110
 do_syscall_64+0xc1/0x1d0
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
 </TASK>

Allocated by task 25303:
 kasan_save_stack+0x24/0x50
 kasan_save_track+0x14/0x30
 __kasan_kmalloc+0x7f/0x90
 fc_attach_transport+0x4f/0x4740 [scsi_transport_fc]
 bfad_im_module_init+0x17/0x80 [bfa]
 bfad_init+0x23/0xff0 [bfa]
 do_one_initcall+0xdc/0x550
 do_init_module+0x22d/0x6b0
 load_module+0x4e96/0x5ff0
 init_module_from_file+0xcd/0x130
 idempotent_init_module+0x330/0x620
 __x64_sys_finit_module+0xb3/0x110
 do_syscall_64+0xc1/0x1d0
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Freed by task 25303:
 kasan_save_stack+0x24/0x50
 kasan_save_track+0x14/0x30
 kasan_save_free_info+0x3b/0x60
 __kasan_slab_free+0x38/0x50
 kfree+0x212/0x480
 bfad_im_module_init+0x7e/0x80 [bfa]
 bfad_init+0x23/0xff0 [bfa]
 do_one_initcall+0xdc/0x550
 do_init_module+0x22d/0x6b0
 load_module+0x4e96/0x5ff0
 init_module_from_file+0xcd/0x130
 idempotent_init_module+0x330/0x620
 __x64_sys_finit_module+0xb3/0x110
 do_syscall_64+0xc1/0x1d0
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Above issue happens as follows:

bfad_init
  error = bfad_im_module_init()
    fc_release_transport(bfad_im_scsi_transport_template);
  if (error)
    goto ext;

ext:
  bfad_im_module_exit();
    fc_release_transport(bfad_im_scsi_transport_template);
    --> Trigger double release

Don't call bfad_im_module_exit() if bfad_im_module_init() failed.

Fixes: 7725ccfda597 ("[SCSI] bfa: Brocade BFA FC SCSI driver")
Signed-off-by: Ye Bin <yebin10@huawei.com>
Link: https://lore.kernel.org/r/20241023011809.63466-1-yebin@huaweicloud.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/bfa/bfad.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/scsi/bfa/bfad.c b/drivers/scsi/bfa/bfad.c
index 19675a6e0780d..6aa1d3a7e24bc 100644
--- a/drivers/scsi/bfa/bfad.c
+++ b/drivers/scsi/bfa/bfad.c
@@ -1673,9 +1673,8 @@ bfad_init(void)
 
 	error = bfad_im_module_init();
 	if (error) {
-		error = -ENOMEM;
 		printk(KERN_WARNING "bfad_im_module_init failure\n");
-		goto ext;
+		return -ENOMEM;
 	}
 
 	if (strcmp(FCPI_NAME, " fcpim") == 0)

From bd65694223f7ad11c790ab63ad1af87a771192ee Mon Sep 17 00:00:00 2001
From: Zeng Heng <zengheng4@huawei.com>
Date: Thu, 24 Oct 2024 16:44:17 +0800
Subject: [PATCH 0946/1530] scsi: fusion: Remove unused variable 'rc'

The return value of scsi_device_reprobe() is currently ignored in
_scsih_reprobe_lun(). Fixing the calling code to deal with the potential
error is non-trivial, so for now just WARN_ON().

The handling of scsi_device_reprobe()'s return value refers to
_scsih_reprobe_lun() and the following link:

https://lore.kernel.org/all/094fdbf57487af4f395238c0525b2a560c8f68f0.1469766027.git.calvinowens@fb.com/

Fixes: f99be43b3024 ("[SCSI] fusion: power pc and miscellaneous bug fixs")
Signed-off-by: Zeng Heng <zengheng4@huawei.com>
Link: https://lore.kernel.org/r/20241024084417.154655-1-zengheng4@huawei.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/message/fusion/mptsas.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index a0bcb0864ecd2..a798e26c6402d 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -4231,10 +4231,8 @@ mptsas_find_phyinfo_by_phys_disk_num(MPT_ADAPTER *ioc, u8 phys_disk_num,
 static void
 mptsas_reprobe_lun(struct scsi_device *sdev, void *data)
 {
-	int rc;
-
 	sdev->no_uld_attach = data ? 1 : 0;
-	rc = scsi_device_reprobe(sdev);
+	WARN_ON(scsi_device_reprobe(sdev));
 }
 
 static void

From c62c30429db3eb4ced35c7fcf6f04a61ce3a01bb Mon Sep 17 00:00:00 2001
From: Zhen Lei <thunder.leizhen@huawei.com>
Date: Sat, 26 Oct 2024 20:57:10 +0800
Subject: [PATCH 0947/1530] scsi: qedf: Fix a possible memory leak in
 qedf_alloc_and_init_sb()

Hook "qed_ops->common->sb_init = qed_sb_init" does not release the DMA
memory sb_virt when it fails. Add dma_free_coherent() to free it. This
is the same way as qedr_alloc_mem_sb() and qede_alloc_mem_sb().

Fixes: 61d8658b4a43 ("scsi: qedf: Add QLogic FastLinQ offload FCoE driver framework.")
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Link: https://lore.kernel.org/r/20241026125711.484-2-thunder.leizhen@huawei.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qedf/qedf_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index df756f3eef3e8..d2f47dc31dbf9 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -2738,6 +2738,7 @@ static int qedf_alloc_and_init_sb(struct qedf_ctx *qedf,
 	    sb_id, QED_SB_TYPE_STORAGE);
 
 	if (ret) {
+		dma_free_coherent(&qedf->pdev->dev, sizeof(*sb_virt), sb_virt, sb_phys);
 		QEDF_ERR(&qedf->dbg_ctx,
 			 "Status block initialization failed (0x%x) for id = %d.\n",
 			 ret, sb_id);

From 95bbdca4999bc59a72ebab01663d421d6ce5775d Mon Sep 17 00:00:00 2001
From: Zhen Lei <thunder.leizhen@huawei.com>
Date: Sat, 26 Oct 2024 20:57:11 +0800
Subject: [PATCH 0948/1530] scsi: qedi: Fix a possible memory leak in
 qedi_alloc_and_init_sb()

Hook "qedi_ops->common->sb_init = qed_sb_init" does not release the DMA
memory sb_virt when it fails. Add dma_free_coherent() to free it. This
is the same way as qedr_alloc_mem_sb() and qede_alloc_mem_sb().

Fixes: ace7f46ba5fd ("scsi: qedi: Add QLogic FastLinQ offload iSCSI driver framework.")
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Link: https://lore.kernel.org/r/20241026125711.484-3-thunder.leizhen@huawei.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qedi/qedi_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index c5aec26019d6a..628d59dda20cc 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -369,6 +369,7 @@ static int qedi_alloc_and_init_sb(struct qedi_ctx *qedi,
 	ret = qedi_ops->common->sb_init(qedi->cdev, sb_info, sb_virt, sb_phys,
 				       sb_id, QED_SB_TYPE_STORAGE);
 	if (ret) {
+		dma_free_coherent(&qedi->pdev->dev, sizeof(*sb_virt), sb_virt, sb_phys);
 		QEDI_ERR(&qedi->dbg_ctx,
 			 "Status block initialization failed for id = %d.\n",
 			  sb_id);

From 4045de893f691f75193c606aec440c365cf7a7be Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 30 Oct 2024 15:03:10 -0700
Subject: [PATCH 0949/1530] scsi: sg: Enable runtime power management

In 2010, runtime power management support was implemented in the SCSI
core.  The description of patch "[SCSI] implement runtime Power
Management" mentions that the sg driver is skipped but not why. This
patch enables runtime power management even if an instance of the sg
driver is held open.  Enabling runtime PM for the sg driver is safe
because all interactions of the sg driver with the SCSI device pass
through the block layer (blk_execute_rq_nowait()) and the block layer
already supports runtime PM.

Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Douglas Gilbert <dgilbert@interlog.com>
Fixes: bc4f24014de5 ("[SCSI] implement runtime Power Management")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241030220310.1373569-1-bvanassche@acm.org
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/sg.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index f86be197fedd0..84334ab39c810 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -307,10 +307,6 @@ sg_open(struct inode *inode, struct file *filp)
 	if (retval)
 		goto sg_put;
 
-	retval = scsi_autopm_get_device(device);
-	if (retval)
-		goto sdp_put;
-
 	/* scsi_block_when_processing_errors() may block so bypass
 	 * check if O_NONBLOCK. Permits SCSI commands to be issued
 	 * during error recovery. Tread carefully. */
@@ -318,7 +314,7 @@ sg_open(struct inode *inode, struct file *filp)
 	      scsi_block_when_processing_errors(device))) {
 		retval = -ENXIO;
 		/* we are in error recovery for this device */
-		goto error_out;
+		goto sdp_put;
 	}
 
 	mutex_lock(&sdp->open_rel_lock);
@@ -371,8 +367,6 @@ sg_open(struct inode *inode, struct file *filp)
 	}
 error_mutex_locked:
 	mutex_unlock(&sdp->open_rel_lock);
-error_out:
-	scsi_autopm_put_device(device);
 sdp_put:
 	kref_put(&sdp->d_ref, sg_device_destroy);
 	scsi_device_put(device);
@@ -392,7 +386,6 @@ sg_release(struct inode *inode, struct file *filp)
 	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_release\n"));
 
 	mutex_lock(&sdp->open_rel_lock);
-	scsi_autopm_put_device(sdp->device);
 	kref_put(&sfp->f_ref, sg_remove_sfp);
 	sdp->open_cnt--;
 

From 50133cf05263198da551e2964d654ae8ad47fe8e Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 5 Nov 2024 19:36:31 +0100
Subject: [PATCH 0950/1530] scsi: sun3: Mark driver struct with __refdata to
 prevent section mismatch
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As described in the added code comment, a reference to .exit.text is ok
for drivers registered via module_platform_driver_probe().  Make this
explicit to prevent the following section mismatch warnings

    WARNING: modpost: drivers/scsi/sun3_scsi: section mismatch in reference: sun3_scsi_driver+0x4 (section: .data) -> sun3_scsi_remove (section: .exit.text)
    WARNING: modpost: drivers/scsi/sun3_scsi_vme: section mismatch in reference: sun3_scsi_driver+0x4 (section: .data) -> sun3_scsi_remove (section: .exit.text)

that trigger on a Sun 3 allmodconfig build.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: https://lore.kernel.org/r/b2c56fa3556505befe9b4cb9a830d9e2a962e72c.1730831769.git.geert@linux-m68k.org
Acked-by: Finn Thain <fthain@linux-m68k.org>
Reviewed-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/sun3_scsi.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c
index bb47274d920dc..ca9cd691cc324 100644
--- a/drivers/scsi/sun3_scsi.c
+++ b/drivers/scsi/sun3_scsi.c
@@ -656,7 +656,13 @@ static void __exit sun3_scsi_remove(struct platform_device *pdev)
 	iounmap(ioaddr);
 }
 
-static struct platform_driver sun3_scsi_driver = {
+/*
+ * sun3_scsi_remove() lives in .exit.text. For drivers registered via
+ * module_platform_driver_probe() this is ok because they cannot get unbound at
+ * runtime. So mark the driver struct with __refdata to prevent modpost
+ * triggering a section mismatch warning.
+ */
+static struct platform_driver sun3_scsi_driver __refdata = {
 	.remove = __exit_p(sun3_scsi_remove),
 	.driver = {
 		.name	= DRV_MODULE_NAME,

From 007cd6ba9aace998acab29a3b9e9b1ce02f91f5d Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 6 Nov 2024 10:10:11 -0800
Subject: [PATCH 0951/1530] scsi: ufs: core: Restore SM8650 support

Some early UFSHCI 4.0 controllers support the UFSHCI 3.0 register set.
The UFSHCD_QUIRK_BROKEN_LSDBS_CAP quirk must be set for these controllers.
Commit b92e5937e352 ("scsi: ufs: core: Move code out of an if-statement")
changed the behavior for these controllers from working fine into
"ufshcd_add_scsi_host: failed to initialize (legacy doorbell mode not
supported)". Fix this by setting the "broken LSDBS" quirk for the
SM8650 development board.

Reported-by: Neil Armstrong <neil.armstrong@linaro.org>
Closes: https://lore.kernel.org/linux-scsi/0c0bc528-fdc2-4106-bc99-f23ae377f6f5@linaro.org/
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8650-HDK
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8650-QRD
Fixes: b92e5937e352 ("scsi: ufs: core: Move code out of an if-statement")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241106181011.4132974-1-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-qcom.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index a5a0646bb80a8..3b592492e1520 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -874,7 +874,8 @@ static void ufs_qcom_advertise_quirks(struct ufs_hba *hba)
 	if (host->hw_ver.major > 0x3)
 		hba->quirks |= UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH;
 
-	if (of_device_is_compatible(hba->dev->of_node, "qcom,sm8550-ufshc"))
+	if (of_device_is_compatible(hba->dev->of_node, "qcom,sm8550-ufshc") ||
+	    of_device_is_compatible(hba->dev->of_node, "qcom,sm8650-ufshc"))
 		hba->quirks |= UFSHCD_QUIRK_BROKEN_LSDBS_CAP;
 }
 

From 5bb2d6179d1a8039236237e1e94cfbda3be1ed9e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kai=20M=C3=A4kisara?= <Kai.Makisara@kolumbus.fi>
Date: Wed, 6 Nov 2024 11:57:21 +0200
Subject: [PATCH 0952/1530] scsi: st: Don't modify unknown block number in
 MTIOCGET
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Struct mtget field mt_blkno -1 means it is unknown. Don't add anything to
it.

Signed-off-by: Kai Mäkisara <Kai.Makisara@kolumbus.fi>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=219419#c14
Link: https://lore.kernel.org/r/20241106095723.63254-2-Kai.Makisara@kolumbus.fi
Reviewed-by: John Meneghini <jmeneghi@redhat.com>
Tested-by: John Meneghini <jmeneghi@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/st.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index d50bad3a2ce92..9f480a1b4a81a 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -3756,7 +3756,7 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
 		    ((STp->density << MT_ST_DENSITY_SHIFT) & MT_ST_DENSITY_MASK);
 		mt_status.mt_blkno = STps->drv_block;
 		mt_status.mt_fileno = STps->drv_file;
-		if (STp->block_size != 0) {
+		if (STp->block_size != 0 && mt_status.mt_blkno >= 0) {
 			if (STps->rw == ST_WRITING)
 				mt_status.mt_blkno +=
 				    (STp->buffer)->buffer_bytes / STp->block_size;

From 0b120edb37dc9dd8ca82893d386922eb6b16f860 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kai=20M=C3=A4kisara?= <Kai.Makisara@kolumbus.fi>
Date: Wed, 6 Nov 2024 11:57:22 +0200
Subject: [PATCH 0953/1530] scsi: st: Add MTIOCGET and MTLOAD to ioctls allowed
 after device reset
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Most drives rewind the tape when the device is reset. Reading and writing
are not allowed until something is done to make the tape position match the
user's expectation (e.g., rewind the tape). Add MTIOCGET and MTLOAD to
operations allowed after reset. MTIOCGET is modified to not touch the tape
if pos_unknown is non-zero. The tape location is known after MTLOAD.

Signed-off-by: Kai Mäkisara <Kai.Makisara@kolumbus.fi>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=219419#c14
Link: https://lore.kernel.org/r/20241106095723.63254-3-Kai.Makisara@kolumbus.fi
Reviewed-by: John Meneghini <jmeneghi@redhat.com>
Tested-by: John Meneghini <jmeneghi@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/st.c | 29 +++++++++++++++++++++--------
 1 file changed, 21 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 9f480a1b4a81a..4863802371a70 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -3506,6 +3506,7 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
 	int i, cmd_nr, cmd_type, bt;
 	int retval = 0;
 	unsigned int blk;
+	bool cmd_mtiocget;
 	struct scsi_tape *STp = file->private_data;
 	struct st_modedef *STm;
 	struct st_partstat *STps;
@@ -3619,6 +3620,7 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
 			 */
 			if (mtc.mt_op != MTREW &&
 			    mtc.mt_op != MTOFFL &&
+			    mtc.mt_op != MTLOAD &&
 			    mtc.mt_op != MTRETEN &&
 			    mtc.mt_op != MTERASE &&
 			    mtc.mt_op != MTSEEK &&
@@ -3732,17 +3734,28 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
 		goto out;
 	}
 
+	cmd_mtiocget = cmd_type == _IOC_TYPE(MTIOCGET) && cmd_nr == _IOC_NR(MTIOCGET);
+
 	if ((i = flush_buffer(STp, 0)) < 0) {
-		retval = i;
-		goto out;
-	}
-	if (STp->can_partitions &&
-	    (i = switch_partition(STp)) < 0) {
-		retval = i;
-		goto out;
+		if (cmd_mtiocget && STp->pos_unknown) {
+			/* flush fails -> modify status accordingly */
+			reset_state(STp);
+			STp->pos_unknown = 1;
+		} else { /* return error */
+			retval = i;
+			goto out;
+		}
+	} else { /* flush_buffer succeeds */
+		if (STp->can_partitions) {
+			i = switch_partition(STp);
+			if (i < 0) {
+				retval = i;
+				goto out;
+			}
+		}
 	}
 
-	if (cmd_type == _IOC_TYPE(MTIOCGET) && cmd_nr == _IOC_NR(MTIOCGET)) {
+	if (cmd_mtiocget) {
 		struct mtget mt_status;
 
 		if (_IOC_SIZE(cmd_in) != sizeof(struct mtget)) {

From a4550b28c8c853e7241ecf30b4f1d9c6bc631fda Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kai=20M=C3=A4kisara?= <Kai.Makisara@kolumbus.fi>
Date: Wed, 6 Nov 2024 11:57:23 +0200
Subject: [PATCH 0954/1530] scsi: st: New session only when Unit Attention for
 new tape
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently the code starts new tape session when any Unit Attention
(UA) is seen when opening the device. This leads to incorrectly
clearing pos_unknown when the UA is for reset. Set new session only
when the UA is for a new tape.

Signed-off-by: Kai Mäkisara <Kai.Makisara@kolumbus.fi>
Link: https://lore.kernel.org/r/20241106095723.63254-4-Kai.Makisara@kolumbus.fi
Reviewed-by: John Meneghini <jmeneghi@redhat.com>
Tested-by: John Meneghini <jmeneghi@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/st.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 4863802371a70..fe0618ac9769f 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -991,7 +991,10 @@ static int test_ready(struct scsi_tape *STp, int do_wait)
 			scode = cmdstatp->sense_hdr.sense_key;
 
 			if (scode == UNIT_ATTENTION) { /* New media? */
-				new_session = 1;
+				if (cmdstatp->sense_hdr.asc == 0x28) { /* New media */
+					new_session = 1;
+					DEBC_printk(STp, "New tape session.");
+				}
 				if (attentions < MAX_ATTENTIONS) {
 					attentions++;
 					continue;

From 083b0ac4f880e54ec7f6a611a899477bbfee9faf Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 16 Oct 2024 11:49:05 +0200
Subject: [PATCH 0955/1530] PCI: Deprecate pcim_iounmap_regions()

pcim_ioumap_region() has recently been made a public function and does
not have the disadvantage of having to deal with the legacy iomap table,
as pcim_iounmap_regions() does.

Deprecate pcim_iounmap_regions().

Link: https://lore.kernel.org/r/20241016094911.24818-4-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/devres.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c
index fc50d2456aed6..3b59a86a764b1 100644
--- a/drivers/pci/devres.c
+++ b/drivers/pci/devres.c
@@ -961,11 +961,14 @@ int pcim_request_all_regions(struct pci_dev *pdev, const char *name)
 EXPORT_SYMBOL(pcim_request_all_regions);
 
 /**
- * pcim_iounmap_regions - Unmap and release PCI BARs
+ * pcim_iounmap_regions - Unmap and release PCI BARs (DEPRECATED)
  * @pdev: PCI device to map IO resources for
  * @mask: Mask of BARs to unmap and release
  *
  * Unmap and release regions specified by @mask.
+ *
+ * This function is DEPRECATED. Do not use it in new code.
+ * Use pcim_iounmap_region() instead.
  */
 void pcim_iounmap_regions(struct pci_dev *pdev, int mask)
 {

From 4365792438902be22cc26ef0624b024c3fb2defa Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 16 Oct 2024 11:49:06 +0200
Subject: [PATCH 0956/1530] fpga/dfl-pci.c: Replace deprecated PCI functions

pcim_iomap_regions() and pcim_iomap_table() have been deprecated by the
PCI subsystem in commit e354bb84a4c1 ("PCI: Deprecate
pcim_iomap_table(), pcim_iomap_regions_request_all()").

Port dfl-pci.c to the successor, pcim_iomap_region().

Consistently, replace pcim_iounmap_regions() with pcim_iounmap_region().

Link: https://lore.kernel.org/r/20241016094911.24818-5-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Andy Shevchenko <andy@kernel.org>
Acked-by: Xu Yilun <yilun.xu@intel.com>
---
 drivers/fpga/dfl-pci.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/drivers/fpga/dfl-pci.c b/drivers/fpga/dfl-pci.c
index 80cac3a5f9767..602807d6afcc0 100644
--- a/drivers/fpga/dfl-pci.c
+++ b/drivers/fpga/dfl-pci.c
@@ -39,14 +39,6 @@ struct cci_drvdata {
 	struct dfl_fpga_cdev *cdev;	/* container device */
 };
 
-static void __iomem *cci_pci_ioremap_bar0(struct pci_dev *pcidev)
-{
-	if (pcim_iomap_regions(pcidev, BIT(0), DRV_NAME))
-		return NULL;
-
-	return pcim_iomap_table(pcidev)[0];
-}
-
 static int cci_pci_alloc_irq(struct pci_dev *pcidev)
 {
 	int ret, nvec = pci_msix_vec_count(pcidev);
@@ -235,9 +227,9 @@ static int find_dfls_by_default(struct pci_dev *pcidev,
 	u64 v;
 
 	/* start to find Device Feature List from Bar 0 */
-	base = cci_pci_ioremap_bar0(pcidev);
-	if (!base)
-		return -ENOMEM;
+	base = pcim_iomap_region(pcidev, 0, DRV_NAME);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
 
 	/*
 	 * PF device has FME and Ports/AFUs, and VF device only has one
@@ -296,7 +288,7 @@ static int find_dfls_by_default(struct pci_dev *pcidev,
 	}
 
 	/* release I/O mappings for next step enumeration */
-	pcim_iounmap_regions(pcidev, BIT(0));
+	pcim_iounmap_region(pcidev, 0);
 
 	return ret;
 }

From 499665679af4ed1e72202e448815dc9c2c1220a7 Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 16 Oct 2024 11:49:08 +0200
Subject: [PATCH 0957/1530] gpio: Replace deprecated PCI functions

pcim_iomap_regions() and pcim_iomap_table() have been deprecated by the
PCI subsystem in commit e354bb84a4c1 ("PCI: Deprecate
pcim_iomap_table(), pcim_iomap_regions_request_all()").

Replace those functions with calls to pcim_iomap_region().

Link: https://lore.kernel.org/r/20241016094911.24818-7-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Andy Shevchenko <andy@kernel.org>
Acked-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-merrifield.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/gpio/gpio-merrifield.c b/drivers/gpio/gpio-merrifield.c
index 421d7e3a6c66e..cd20604f26de5 100644
--- a/drivers/gpio/gpio-merrifield.c
+++ b/drivers/gpio/gpio-merrifield.c
@@ -78,24 +78,25 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	if (retval)
 		return retval;
 
-	retval = pcim_iomap_regions(pdev, BIT(1) | BIT(0), pci_name(pdev));
-	if (retval)
-		return dev_err_probe(dev, retval, "I/O memory mapping error\n");
-
-	base = pcim_iomap_table(pdev)[1];
+	base = pcim_iomap_region(pdev, 1, pci_name(pdev));
+	if (IS_ERR(base))
+		return dev_err_probe(dev, PTR_ERR(base), "I/O memory mapping error\n");
 
 	irq_base = readl(base + 0 * sizeof(u32));
 	gpio_base = readl(base + 1 * sizeof(u32));
 
 	/* Release the IO mapping, since we already get the info from BAR1 */
-	pcim_iounmap_regions(pdev, BIT(1));
+	pcim_iounmap_region(pdev, 1);
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
 	priv->dev = dev;
-	priv->reg_base = pcim_iomap_table(pdev)[0];
+	priv->reg_base = pcim_iomap_region(pdev, 0, pci_name(pdev));
+	if (IS_ERR(priv->reg_base))
+		return dev_err_probe(dev, PTR_ERR(priv->reg_base),
+				"I/O memory mapping error\n");
 
 	priv->pin_info.pin_ranges = mrfld_gpio_ranges;
 	priv->pin_info.nranges = ARRAY_SIZE(mrfld_gpio_ranges);

From 64fe9bc34f781538682af34e7adb6aee1a52c425 Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 16 Oct 2024 11:49:09 +0200
Subject: [PATCH 0958/1530] ethernet: cavium: Replace deprecated PCI functions

pcim_iomap_regions() and pcim_iomap_table() have been deprecated by
the PCI subsystem in commit e354bb84a4c1 ("PCI: Deprecate
pcim_iomap_table(), pcim_iomap_regions_request_all()").

Replace the deprecated PCI functions with their successors.

Link: https://lore.kernel.org/r/20241016094911.24818-8-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/cavium/common/cavium_ptp.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/cavium/common/cavium_ptp.c b/drivers/net/ethernet/cavium/common/cavium_ptp.c
index 9fd717b9cf69e..984f0dd7b62e1 100644
--- a/drivers/net/ethernet/cavium/common/cavium_ptp.c
+++ b/drivers/net/ethernet/cavium/common/cavium_ptp.c
@@ -239,12 +239,11 @@ static int cavium_ptp_probe(struct pci_dev *pdev,
 	if (err)
 		goto error_free;
 
-	err = pcim_iomap_regions(pdev, 1 << PCI_PTP_BAR_NO, pci_name(pdev));
+	clock->reg_base = pcim_iomap_region(pdev, PCI_PTP_BAR_NO, pci_name(pdev));
+	err = PTR_ERR_OR_ZERO(clock->reg_base);
 	if (err)
 		goto error_free;
 
-	clock->reg_base = pcim_iomap_table(pdev)[PCI_PTP_BAR_NO];
-
 	spin_lock_init(&clock->spin_lock);
 
 	cc = &clock->cycle_counter;
@@ -292,7 +291,7 @@ static int cavium_ptp_probe(struct pci_dev *pdev,
 	clock_cfg = readq(clock->reg_base + PTP_CLOCK_CFG);
 	clock_cfg &= ~PTP_CLOCK_CFG_PTP_EN;
 	writeq(clock_cfg, clock->reg_base + PTP_CLOCK_CFG);
-	pcim_iounmap_regions(pdev, 1 << PCI_PTP_BAR_NO);
+	pcim_iounmap_region(pdev, PCI_PTP_BAR_NO);
 
 error_free:
 	devm_kfree(dev, clock);

From e329b762a31eb59da1b78cb69cbe1b9ff843e081 Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Thu, 7 Nov 2024 10:59:34 +0000
Subject: [PATCH 0959/1530] dt-bindings: PCI: microchip,pcie-host: Add reg for
 Root Port 2

The PCI host controller on PolarFire SoC has multiple Root Port instances,
each with their own bridge and ctrl address spaces. The original binding
has an "apb" register region, and it is expected to be set to the base
address of the Root Complex register space. Some defines in the Linux
driver were used to compute the addresses of the bridge and ctrl address
ranges corresponding to Root Port instance 1.  Some customers want to use
Root Port instance 2 however, which requires changing the defines in the
driver, which is clearly not a portable solution.

Remove this "apb" register region from the binding and add "bridge" &
"ctrl" regions instead, that will directly communicate the address of these
regions for a specific Root Port.

Fixes: 6ee6c89aac35 ("dt-bindings: PCI: microchip: Add Microchip PolarFire host binding")
Link: https://lore.kernel.org/r/20241107-barcode-whinny-b1a4e8834b4f@spud
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
[bhelgaas: Capitalize PCIe spec terms]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Daire McNamara <daire.mcnamara@microchip.com>
---
 .../bindings/pci/microchip,pcie-host.yaml          | 11 +++++++++--
 .../bindings/pci/plda,xpressrich3-axi-common.yaml  | 14 ++++++++++----
 .../bindings/pci/starfive,jh7110-pcie.yaml         |  7 +++++++
 3 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/Documentation/devicetree/bindings/pci/microchip,pcie-host.yaml b/Documentation/devicetree/bindings/pci/microchip,pcie-host.yaml
index 612633ba59e2c..2e15475697029 100644
--- a/Documentation/devicetree/bindings/pci/microchip,pcie-host.yaml
+++ b/Documentation/devicetree/bindings/pci/microchip,pcie-host.yaml
@@ -17,6 +17,12 @@ properties:
   compatible:
     const: microchip,pcie-host-1.0 # PolarFire
 
+  reg:
+    minItems: 3
+
+  reg-names:
+    minItems: 3
+
   clocks:
     description:
       Fabric Interface Controllers, FICs, are the interface between the FPGA
@@ -62,8 +68,9 @@ examples:
             pcie0: pcie@2030000000 {
                     compatible = "microchip,pcie-host-1.0";
                     reg = <0x0 0x70000000 0x0 0x08000000>,
-                          <0x0 0x43000000 0x0 0x00010000>;
-                    reg-names = "cfg", "apb";
+                          <0x0 0x43008000 0x0 0x00002000>,
+                          <0x0 0x4300a000 0x0 0x00002000>;
+                    reg-names = "cfg", "bridge", "ctrl";
                     device_type = "pci";
                     #address-cells = <3>;
                     #size-cells = <2>;
diff --git a/Documentation/devicetree/bindings/pci/plda,xpressrich3-axi-common.yaml b/Documentation/devicetree/bindings/pci/plda,xpressrich3-axi-common.yaml
index 7a57a80052a01..039eecdbd6aad 100644
--- a/Documentation/devicetree/bindings/pci/plda,xpressrich3-axi-common.yaml
+++ b/Documentation/devicetree/bindings/pci/plda,xpressrich3-axi-common.yaml
@@ -18,12 +18,18 @@ allOf:
 
 properties:
   reg:
-    maxItems: 2
+    maxItems: 3
+    minItems: 2
 
   reg-names:
-    items:
-      - const: cfg
-      - const: apb
+    oneOf:
+      - items:
+          - const: cfg
+          - const: apb
+      - items:
+          - const: cfg
+          - const: bridge
+          - const: ctrl
 
   interrupts:
     minItems: 1
diff --git a/Documentation/devicetree/bindings/pci/starfive,jh7110-pcie.yaml b/Documentation/devicetree/bindings/pci/starfive,jh7110-pcie.yaml
index 67151aaa39480..5f432452c815b 100644
--- a/Documentation/devicetree/bindings/pci/starfive,jh7110-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/starfive,jh7110-pcie.yaml
@@ -16,6 +16,13 @@ properties:
   compatible:
     const: starfive,jh7110-pcie
 
+
+  reg:
+    maxItems: 2
+
+  reg-names:
+    maxItems: 2
+
   clocks:
     items:
       - description: NOC bus clock

From ac7f53b7e7283fee35ad12de8359f20989a47eb5 Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Thu, 7 Nov 2024 10:59:35 +0000
Subject: [PATCH 0960/1530] PCI: microchip: Add support for using either Root
 Port 1 or 2

The PCI host controller on PolarFire SoC has multiple Root Port instances,
each with their own bridge and ctrl address spaces. The original binding
has an "apb" register region, and it is expected to be set to the base
address of the Root Complex register space. Some defines in the Linux
driver were used to compute the addresses of the bridge and ctrl address
ranges corresponding to Root Port instance 1.  Some customers want to use
Root Port instance 2 however, which requires changing the defines in the
driver, which is clearly not a portable solution.

The binding has been changed from a single register region to a pair,
corresponding to the bridge and ctrl regions respectively, so modify the
driver to read these regions directly from the devicetree rather than
compute them from the base address of the abp region.

To maintain backwards compatibility with the existing binding, the driver
retains code to handle the "abp" reg and computes the base address of the
bridge and ctrl regions using the defines if it is present. reg-names has
always been a required property, so this is safe to do.

Link: https://lore.kernel.org/r/20241107-surrender-brisket-287d563a5de1@spud
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
[bhelgaas: Capitalize PCIe spec terms]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 .../pci/controller/plda/pcie-microchip-host.c | 126 ++++++++++--------
 1 file changed, 67 insertions(+), 59 deletions(-)

diff --git a/drivers/pci/controller/plda/pcie-microchip-host.c b/drivers/pci/controller/plda/pcie-microchip-host.c
index 48f60a04b740b..6630cacef3010 100644
--- a/drivers/pci/controller/plda/pcie-microchip-host.c
+++ b/drivers/pci/controller/plda/pcie-microchip-host.c
@@ -25,9 +25,6 @@
 #define MC_PCIE1_BRIDGE_ADDR			0x00008000u
 #define MC_PCIE1_CTRL_ADDR			0x0000a000u
 
-#define MC_PCIE_BRIDGE_ADDR			(MC_PCIE1_BRIDGE_ADDR)
-#define MC_PCIE_CTRL_ADDR			(MC_PCIE1_CTRL_ADDR)
-
 /* PCIe Controller Phy Regs */
 #define SEC_ERROR_EVENT_CNT			0x20
 #define DED_ERROR_EVENT_CNT			0x24
@@ -128,7 +125,6 @@
 	[EVENT_LOCAL_ ## x] = { __stringify(x), s }
 
 #define PCIE_EVENT(x) \
-	.base = MC_PCIE_CTRL_ADDR, \
 	.offset = PCIE_EVENT_INT, \
 	.mask_offset = PCIE_EVENT_INT, \
 	.mask_high = 1, \
@@ -136,7 +132,6 @@
 	.enb_mask = PCIE_EVENT_INT_ENB_MASK
 
 #define SEC_EVENT(x) \
-	.base = MC_PCIE_CTRL_ADDR, \
 	.offset = SEC_ERROR_INT, \
 	.mask_offset = SEC_ERROR_INT_MASK, \
 	.mask = SEC_ERROR_INT_ ## x ## _INT, \
@@ -144,7 +139,6 @@
 	.enb_mask = 0
 
 #define DED_EVENT(x) \
-	.base = MC_PCIE_CTRL_ADDR, \
 	.offset = DED_ERROR_INT, \
 	.mask_offset = DED_ERROR_INT_MASK, \
 	.mask_high = 1, \
@@ -152,7 +146,6 @@
 	.enb_mask = 0
 
 #define LOCAL_EVENT(x) \
-	.base = MC_PCIE_BRIDGE_ADDR, \
 	.offset = ISTATUS_LOCAL, \
 	.mask_offset = IMASK_LOCAL, \
 	.mask_high = 0, \
@@ -179,7 +172,8 @@ struct event_map {
 
 struct mc_pcie {
 	struct plda_pcie_rp plda;
-	void __iomem *axi_base_addr;
+	void __iomem *bridge_base_addr;
+	void __iomem *ctrl_base_addr;
 };
 
 struct cause {
@@ -253,7 +247,6 @@ static struct event_map local_status_to_event[] = {
 };
 
 static struct {
-	u32 base;
 	u32 offset;
 	u32 mask;
 	u32 shift;
@@ -325,8 +318,7 @@ static inline u32 reg_to_event(u32 reg, struct event_map field)
 
 static u32 pcie_events(struct mc_pcie *port)
 {
-	void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR;
-	u32 reg = readl_relaxed(ctrl_base_addr + PCIE_EVENT_INT);
+	u32 reg = readl_relaxed(port->ctrl_base_addr + PCIE_EVENT_INT);
 	u32 val = 0;
 	int i;
 
@@ -338,8 +330,7 @@ static u32 pcie_events(struct mc_pcie *port)
 
 static u32 sec_errors(struct mc_pcie *port)
 {
-	void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR;
-	u32 reg = readl_relaxed(ctrl_base_addr + SEC_ERROR_INT);
+	u32 reg = readl_relaxed(port->ctrl_base_addr + SEC_ERROR_INT);
 	u32 val = 0;
 	int i;
 
@@ -351,8 +342,7 @@ static u32 sec_errors(struct mc_pcie *port)
 
 static u32 ded_errors(struct mc_pcie *port)
 {
-	void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR;
-	u32 reg = readl_relaxed(ctrl_base_addr + DED_ERROR_INT);
+	u32 reg = readl_relaxed(port->ctrl_base_addr + DED_ERROR_INT);
 	u32 val = 0;
 	int i;
 
@@ -364,8 +354,7 @@ static u32 ded_errors(struct mc_pcie *port)
 
 static u32 local_events(struct mc_pcie *port)
 {
-	void __iomem *bridge_base_addr = port->axi_base_addr + MC_PCIE_BRIDGE_ADDR;
-	u32 reg = readl_relaxed(bridge_base_addr + ISTATUS_LOCAL);
+	u32 reg = readl_relaxed(port->bridge_base_addr + ISTATUS_LOCAL);
 	u32 val = 0;
 	int i;
 
@@ -412,8 +401,12 @@ static void mc_ack_event_irq(struct irq_data *data)
 	void __iomem *addr;
 	u32 mask;
 
-	addr = mc_port->axi_base_addr + event_descs[event].base +
-		event_descs[event].offset;
+	if (event_descs[event].offset == ISTATUS_LOCAL)
+		addr = mc_port->bridge_base_addr;
+	else
+		addr = mc_port->ctrl_base_addr;
+
+	addr += event_descs[event].offset;
 	mask = event_descs[event].mask;
 	mask |= event_descs[event].enb_mask;
 
@@ -429,8 +422,12 @@ static void mc_mask_event_irq(struct irq_data *data)
 	u32 mask;
 	u32 val;
 
-	addr = mc_port->axi_base_addr + event_descs[event].base +
-		event_descs[event].mask_offset;
+	if (event_descs[event].offset == ISTATUS_LOCAL)
+		addr = mc_port->bridge_base_addr;
+	else
+		addr = mc_port->ctrl_base_addr;
+
+	addr += event_descs[event].mask_offset;
 	mask = event_descs[event].mask;
 	if (event_descs[event].enb_mask) {
 		mask <<= PCIE_EVENT_INT_ENB_SHIFT;
@@ -460,8 +457,12 @@ static void mc_unmask_event_irq(struct irq_data *data)
 	u32 mask;
 	u32 val;
 
-	addr = mc_port->axi_base_addr + event_descs[event].base +
-		event_descs[event].mask_offset;
+	if (event_descs[event].offset == ISTATUS_LOCAL)
+		addr = mc_port->bridge_base_addr;
+	else
+		addr = mc_port->ctrl_base_addr;
+
+	addr += event_descs[event].mask_offset;
 	mask = event_descs[event].mask;
 
 	if (event_descs[event].enb_mask)
@@ -554,26 +555,20 @@ static const struct plda_event mc_event = {
 
 static inline void mc_clear_secs(struct mc_pcie *port)
 {
-	void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR;
-
-	writel_relaxed(SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT, ctrl_base_addr +
-		       SEC_ERROR_INT);
-	writel_relaxed(0, ctrl_base_addr + SEC_ERROR_EVENT_CNT);
+	writel_relaxed(SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT,
+		       port->ctrl_base_addr + SEC_ERROR_INT);
+	writel_relaxed(0, port->ctrl_base_addr + SEC_ERROR_EVENT_CNT);
 }
 
 static inline void mc_clear_deds(struct mc_pcie *port)
 {
-	void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR;
-
-	writel_relaxed(DED_ERROR_INT_ALL_RAM_DED_ERR_INT, ctrl_base_addr +
-		       DED_ERROR_INT);
-	writel_relaxed(0, ctrl_base_addr + DED_ERROR_EVENT_CNT);
+	writel_relaxed(DED_ERROR_INT_ALL_RAM_DED_ERR_INT,
+		       port->ctrl_base_addr + DED_ERROR_INT);
+	writel_relaxed(0, port->ctrl_base_addr + DED_ERROR_EVENT_CNT);
 }
 
 static void mc_disable_interrupts(struct mc_pcie *port)
 {
-	void __iomem *bridge_base_addr = port->axi_base_addr + MC_PCIE_BRIDGE_ADDR;
-	void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR;
 	u32 val;
 
 	/* Ensure ECC bypass is enabled */
@@ -581,22 +576,22 @@ static void mc_disable_interrupts(struct mc_pcie *port)
 	      ECC_CONTROL_RX_RAM_ECC_BYPASS |
 	      ECC_CONTROL_PCIE2AXI_RAM_ECC_BYPASS |
 	      ECC_CONTROL_AXI2PCIE_RAM_ECC_BYPASS;
-	writel_relaxed(val, ctrl_base_addr + ECC_CONTROL);
+	writel_relaxed(val, port->ctrl_base_addr + ECC_CONTROL);
 
 	/* Disable SEC errors and clear any outstanding */
-	writel_relaxed(SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT, ctrl_base_addr +
-		       SEC_ERROR_INT_MASK);
+	writel_relaxed(SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT,
+		       port->ctrl_base_addr + SEC_ERROR_INT_MASK);
 	mc_clear_secs(port);
 
 	/* Disable DED errors and clear any outstanding */
-	writel_relaxed(DED_ERROR_INT_ALL_RAM_DED_ERR_INT, ctrl_base_addr +
-		       DED_ERROR_INT_MASK);
+	writel_relaxed(DED_ERROR_INT_ALL_RAM_DED_ERR_INT,
+		       port->ctrl_base_addr + DED_ERROR_INT_MASK);
 	mc_clear_deds(port);
 
 	/* Disable local interrupts and clear any outstanding */
-	writel_relaxed(0, bridge_base_addr + IMASK_LOCAL);
-	writel_relaxed(GENMASK(31, 0), bridge_base_addr + ISTATUS_LOCAL);
-	writel_relaxed(GENMASK(31, 0), bridge_base_addr + ISTATUS_MSI);
+	writel_relaxed(0, port->bridge_base_addr + IMASK_LOCAL);
+	writel_relaxed(GENMASK(31, 0), port->bridge_base_addr + ISTATUS_LOCAL);
+	writel_relaxed(GENMASK(31, 0), port->bridge_base_addr + ISTATUS_MSI);
 
 	/* Disable PCIe events and clear any outstanding */
 	val = PCIE_EVENT_INT_L2_EXIT_INT |
@@ -605,11 +600,11 @@ static void mc_disable_interrupts(struct mc_pcie *port)
 	      PCIE_EVENT_INT_L2_EXIT_INT_MASK |
 	      PCIE_EVENT_INT_HOTRST_EXIT_INT_MASK |
 	      PCIE_EVENT_INT_DLUP_EXIT_INT_MASK;
-	writel_relaxed(val, ctrl_base_addr + PCIE_EVENT_INT);
+	writel_relaxed(val, port->ctrl_base_addr + PCIE_EVENT_INT);
 
 	/* Disable host interrupts and clear any outstanding */
-	writel_relaxed(0, bridge_base_addr + IMASK_HOST);
-	writel_relaxed(GENMASK(31, 0), bridge_base_addr + ISTATUS_HOST);
+	writel_relaxed(0, port->bridge_base_addr + IMASK_HOST);
+	writel_relaxed(GENMASK(31, 0), port->bridge_base_addr + ISTATUS_HOST);
 }
 
 static int mc_platform_init(struct pci_config_window *cfg)
@@ -617,12 +612,10 @@ static int mc_platform_init(struct pci_config_window *cfg)
 	struct device *dev = cfg->parent;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct pci_host_bridge *bridge = platform_get_drvdata(pdev);
-	void __iomem *bridge_base_addr =
-		port->axi_base_addr + MC_PCIE_BRIDGE_ADDR;
 	int ret;
 
 	/* Configure address translation table 0 for PCIe config space */
-	plda_pcie_setup_window(bridge_base_addr, 0, cfg->res.start,
+	plda_pcie_setup_window(port->bridge_base_addr, 0, cfg->res.start,
 			       cfg->res.start,
 			       resource_size(&cfg->res));
 
@@ -649,7 +642,7 @@ static int mc_platform_init(struct pci_config_window *cfg)
 static int mc_host_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	void __iomem *bridge_base_addr;
+	void __iomem *apb_base_addr;
 	struct plda_pcie_rp *plda;
 	int ret;
 	u32 val;
@@ -661,30 +654,45 @@ static int mc_host_probe(struct platform_device *pdev)
 	plda = &port->plda;
 	plda->dev = dev;
 
-	port->axi_base_addr = devm_platform_ioremap_resource(pdev, 1);
-	if (IS_ERR(port->axi_base_addr))
-		return PTR_ERR(port->axi_base_addr);
+	port->bridge_base_addr = devm_platform_ioremap_resource_byname(pdev,
+								    "bridge");
+	port->ctrl_base_addr = devm_platform_ioremap_resource_byname(pdev,
+								    "ctrl");
+	if (!IS_ERR(port->bridge_base_addr) && !IS_ERR(port->ctrl_base_addr))
+		goto addrs_set;
+
+	/*
+	 * The original, incorrect, binding that lumped the control and
+	 * bridge addresses together still needs to be handled by the driver.
+	 */
+	apb_base_addr = devm_platform_ioremap_resource_byname(pdev, "apb");
+	if (IS_ERR(apb_base_addr))
+		return dev_err_probe(dev, PTR_ERR(apb_base_addr),
+				     "both legacy apb register and ctrl/bridge regions missing");
+
+	port->bridge_base_addr = apb_base_addr + MC_PCIE1_BRIDGE_ADDR;
+	port->ctrl_base_addr = apb_base_addr + MC_PCIE1_CTRL_ADDR;
 
+addrs_set:
 	mc_disable_interrupts(port);
 
-	bridge_base_addr = port->axi_base_addr + MC_PCIE_BRIDGE_ADDR;
-	plda->bridge_addr = bridge_base_addr;
+	plda->bridge_addr = port->bridge_base_addr;
 	plda->num_events = NUM_EVENTS;
 
 	/* Allow enabling MSI by disabling MSI-X */
-	val = readl(bridge_base_addr + PCIE_PCI_IRQ_DW0);
+	val = readl(port->bridge_base_addr + PCIE_PCI_IRQ_DW0);
 	val &= ~MSIX_CAP_MASK;
-	writel(val, bridge_base_addr + PCIE_PCI_IRQ_DW0);
+	writel(val, port->bridge_base_addr + PCIE_PCI_IRQ_DW0);
 
 	/* Pick num vectors from bitfile programmed onto FPGA fabric */
-	val = readl(bridge_base_addr + PCIE_PCI_IRQ_DW0);
+	val = readl(port->bridge_base_addr + PCIE_PCI_IRQ_DW0);
 	val &= NUM_MSI_MSGS_MASK;
 	val >>= NUM_MSI_MSGS_SHIFT;
 
 	plda->msi.num_vectors = 1 << val;
 
 	/* Pick vector address from design */
-	plda->msi.vector_phy = readl_relaxed(bridge_base_addr + IMSI_ADDR);
+	plda->msi.vector_phy = readl_relaxed(port->bridge_base_addr + IMSI_ADDR);
 
 	ret = mc_pcie_init_clks(dev);
 	if (ret) {

From 5a938ed9481b0c06cb97aec45e722a80568256fd Mon Sep 17 00:00:00 2001
From: Kishon Vijay Abraham I <kishon@ti.com>
Date: Fri, 24 May 2024 16:27:13 +0530
Subject: [PATCH 0961/1530] PCI: keystone: Set mode as Root Complex for
 "ti,keystone-pcie" compatible
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 23284ad677a9 ("PCI: keystone: Add support for PCIe EP in AM654x
Platforms") introduced configuring "enum dw_pcie_device_mode" as part of
device data ("struct ks_pcie_of_data"). However it failed to set the
mode for "ti,keystone-pcie" compatible.

Since the mode defaults to "DW_PCIE_UNKNOWN_TYPE", the following error
message is displayed for the v3.65a controller:

  "INVALID device type 0"

Despite the driver probing successfully, the controller may not be
functional in the Root Complex mode of operation.

So, set the mode as Root Complex for "ti,keystone-pcie" compatible to
fix this.

Fixes: 23284ad677a9 ("PCI: keystone: Add support for PCIe EP in AM654x Platforms")
Link: https://lore.kernel.org/r/20240524105714.191642-2-s-vadapalli@ti.com
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
[kwilczynski: commit log, added tag for stable releases]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Cc: stable@vger.kernel.org
---
 drivers/pci/controller/dwc/pci-keystone.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 2219b1a866faf..b99bc4071fe92 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -1093,6 +1093,7 @@ static int ks_pcie_am654_set_mode(struct device *dev,
 
 static const struct ks_pcie_of_data ks_pcie_rc_of_data = {
 	.host_ops = &ks_pcie_host_ops,
+	.mode = DW_PCIE_RC_TYPE,
 	.version = DW_PCIE_VER_365A,
 };
 

From 9e9ec8d8692a6f64d81ef67d4fb6255af6be684b Mon Sep 17 00:00:00 2001
From: Kishon Vijay Abraham I <kishon@ti.com>
Date: Fri, 24 May 2024 16:27:14 +0530
Subject: [PATCH 0962/1530] PCI: keystone: Add link up check to
 ks_pcie_other_map_bus()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

K2G forwards the error triggered by a link-down state (e.g., no connected
endpoint device) on the system bus for PCI configuration transactions;
these errors are reported as an SError at system level, which is fatal and
hangs the system.

So, apply fix similar to how it was done in the DesignWare Core driver
commit 15b23906347c ("PCI: dwc: Add link up check in dw_child_pcie_ops.map_bus()").

Fixes: 10a797c6e54a ("PCI: dwc: keystone: Use pci_ops for config space accessors")
Link: https://lore.kernel.org/r/20240524105714.191642-3-s-vadapalli@ti.com
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
[kwilczynski: commit log, added tag for stable releases]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Cc: stable@vger.kernel.org
---
 drivers/pci/controller/dwc/pci-keystone.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index b99bc4071fe92..44b34559de1ac 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -455,6 +455,17 @@ static void __iomem *ks_pcie_other_map_bus(struct pci_bus *bus,
 	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
 	u32 reg;
 
+	/*
+	 * Checking whether the link is up here is a last line of defense
+	 * against platforms that forward errors on the system bus as
+	 * SError upon PCI configuration transactions issued when the link
+	 * is down. This check is racy by definition and does not stop
+	 * the system from triggering an SError if the link goes down
+	 * after this check is performed.
+	 */
+	if (!dw_pcie_link_up(pci))
+		return NULL;
+
 	reg = CFG_BUS(bus->number) | CFG_DEVICE(PCI_SLOT(devfn)) |
 		CFG_FUNC(PCI_FUNC(devfn));
 	if (!pci_is_root_bus(bus->parent))

From 9ac98662dbd3254007b2b32e792a236e93ace805 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Wed, 6 Nov 2024 14:48:26 +0000
Subject: [PATCH 0963/1530] perf: event: Remove deadcode

event_format__print() last use was removed by 2017's
commit 894f3f1732cb ("perf script: Use event_format__fprintf()")

evlist__find_tracepoint_by_id() last use was removed by 2012's
commit e60fc847cefa ("perf evlist: Remove some unused methods")

evlist__set_tp_filter_pid() last use was removed by 2017's
commit dd1a50377c92 ("perf trace: Introduce filter_loop_pids()")

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20241106144826.91728-1-linux@treblig.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/evlist.c            | 18 ------------------
 tools/perf/util/evlist.h            |  2 --
 tools/perf/util/trace-event-parse.c |  6 ------
 tools/perf/util/trace-event.h       |  3 ---
 4 files changed, 29 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 37d0fc01c1800..f0dd174e2debd 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -320,19 +320,6 @@ struct evsel *evlist__add_sched_switch(struct evlist *evlist, bool system_wide)
 }
 #endif
 
-struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id)
-{
-	struct evsel *evsel;
-
-	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->core.attr.type   == PERF_TYPE_TRACEPOINT &&
-		    (int)evsel->core.attr.config == id)
-			return evsel;
-	}
-
-	return NULL;
-}
-
 struct evsel *evlist__find_tracepoint_by_name(struct evlist *evlist, const char *name)
 {
 	struct evsel *evsel;
@@ -1157,11 +1144,6 @@ int evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids)
 	return ret;
 }
 
-int evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid)
-{
-	return evlist__set_tp_filter_pids(evlist, 1, &pid);
-}
-
 int evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids)
 {
 	char *filter = asprintf__tp_filter_pids(npids, pids);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index cd80a470a4ba5..adddb1db1ad2b 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -132,7 +132,6 @@ int __evlist__set_tracepoints_handlers(struct evlist *evlist,
 	__evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array))
 
 int evlist__set_tp_filter(struct evlist *evlist, const char *filter);
-int evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid);
 int evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids);
 
 int evlist__append_tp_filter(struct evlist *evlist, const char *filter);
@@ -140,7 +139,6 @@ int evlist__append_tp_filter(struct evlist *evlist, const char *filter);
 int evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid);
 int evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids);
 
-struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id);
 struct evsel *evlist__find_tracepoint_by_name(struct evlist *evlist, const char *name);
 
 int evlist__add_pollfd(struct evlist *evlist, int fd);
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index f0332bd3a501e..d97830cdbd7e6 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -116,12 +116,6 @@ void event_format__fprintf(struct tep_event *event,
 	trace_seq_destroy(&s);
 }
 
-void event_format__print(struct tep_event *event,
-			 int cpu, void *data, int size)
-{
-	return event_format__fprintf(event, cpu, data, size, stdout);
-}
-
 /*
  * prev_state is of size long, which is 32 bits on 32 bit architectures.
  * As it needs to have the same bits for both 32 bit and 64 bit architectures
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index bbf8b26bc8da2..0e5133f1b9103 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -42,9 +42,6 @@ struct tep_event *trace_event__tp_format_id(int id);
 void event_format__fprintf(struct tep_event *event,
 			   int cpu, void *data, int size, FILE *fp);
 
-void event_format__print(struct tep_event *event,
-			 int cpu, void *data, int size);
-
 int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size);
 int parse_event_file(struct tep_handle *pevent,
 		     char *buf, unsigned long size, char *sys);

From d8c0f8b4ee989b79d8d92f954662efed38c7b23d Mon Sep 17 00:00:00 2001
From: Haiyue Wang <haiyuewa@163.com>
Date: Wed, 6 Nov 2024 20:12:14 +0800
Subject: [PATCH 0964/1530] perf tools: Add the empty-pmu-events build to
 .gitignore

The commit 0fe881f10ceb ("perf jevents: Autogenerate empty-pmu-events.c")
build will generate two files, add them to .gitignore:

	tools/perf/pmu-events/empty-pmu-events.log
	tools/perf/pmu-events/test-empty-pmu-events.c

Signed-off-by: Haiyue Wang <haiyuewa@163.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20241106121254.2869-1-haiyuewa@163.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/.gitignore | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 19ce1cd56f8cb..5aaf73df6700d 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -39,6 +39,8 @@ trace/beauty/generated/
 pmu-events/pmu-events.c
 pmu-events/jevents
 pmu-events/metric_test.log
+pmu-events/empty-pmu-events.log
+pmu-events/test-empty-pmu-events.c
 *.shellcheck_log
 feature/
 libapi/

From 62a6d092f1e7e72365ecf65bbc3f268121130292 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 5 Nov 2024 16:48:18 -0800
Subject: [PATCH 0965/1530] perf stat: Expand metric+unit buffer size

Long metric names combined with units may exceed the metric_bf and
lead to truncation. Double metric_bf in size to avoid this.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lore.kernel.org/r/20241106004818.2174593-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/stat-shadow.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index ada787947e163..47718610d5d8c 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -517,7 +517,7 @@ static void generic_metric(struct perf_stat_config *config,
 	if (!metric_events[i]) {
 		if (expr__parse(&ratio, pctx, metric_expr) == 0) {
 			char *unit;
-			char metric_bf[64];
+			char metric_bf[128];
 
 			if (metric_threshold &&
 			    expr__parse(&threshold, pctx, metric_threshold) == 0 &&

From 2466b31201424ccb7eda00277222302a4d6576cb Mon Sep 17 00:00:00 2001
From: Luis Chamberlain <mcgrof@kernel.org>
Date: Wed, 6 Nov 2024 00:17:21 +0000
Subject: [PATCH 0966/1530] tests/module/gen_test_kallsyms.sh: use 0 value for
 variables

Use 0 for the values as we use them for the return value on init
to keep the test modules simple. This fixes a splat reported

do_init_module: 'test_kallsyms_b'->init suspiciously returned 255, it should follow 0/-E convention
do_init_module: loading module anyway...
CPU: 5 UID: 0 PID: 1873 Comm: modprobe Not tainted 6.12.0-rc3+ #4
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 2024.08-1 09/18/2024
Call Trace:
 <TASK>
 dump_stack_lvl+0x56/0x80
 do_init_module.cold+0x21/0x26
 init_module_from_file+0x88/0xf0
 idempotent_init_module+0x108/0x300
 __x64_sys_finit_module+0x5a/0xb0
 do_syscall_64+0x4b/0x110
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7f4f3a718839
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff>
RSP: 002b:00007fff97d1a9e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
RAX: ffffffffffffffda RBX: 000055b94001ab90 RCX: 00007f4f3a718839
RDX: 0000000000000000 RSI: 000055b910e68a10 RDI: 0000000000000004
RBP: 0000000000000000 R08: 00007f4f3a7f1b20 R09: 000055b94001c5b0
R10: 0000000000000040 R11: 0000000000000246 R12: 000055b910e68a10
R13: 0000000000040000 R14: 000055b94001ad60 R15: 0000000000000000
 </TASK>
do_init_module: 'test_kallsyms_b'->init suspiciously returned 255, it should follow 0/-E convention
do_init_module: loading module anyway...
CPU: 1 UID: 0 PID: 1884 Comm: modprobe Not tainted 6.12.0-rc3+ #4
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 2024.08-1 09/18/2024
Call Trace:
 <TASK>
 dump_stack_lvl+0x56/0x80
 do_init_module.cold+0x21/0x26
 init_module_from_file+0x88/0xf0
 idempotent_init_module+0x108/0x300
 __x64_sys_finit_module+0x5a/0xb0
 do_syscall_64+0x4b/0x110
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7ffaa5d18839

Reported-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 lib/tests/module/gen_test_kallsyms.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/tests/module/gen_test_kallsyms.sh b/lib/tests/module/gen_test_kallsyms.sh
index ae5966f1f904e..3f2c626350ad1 100755
--- a/lib/tests/module/gen_test_kallsyms.sh
+++ b/lib/tests/module/gen_test_kallsyms.sh
@@ -32,7 +32,7 @@ gen_num_syms()
 	PREFIX=$1
 	NUM=$2
 	for i in $(seq 1 $NUM); do
-		printf "int auto_test_%s_%010d = 0xff;\n" $PREFIX $i
+		printf "int auto_test_%s_%010d = 0;\n" $PREFIX $i
 		printf "EXPORT_SYMBOL_GPL(auto_test_%s_%010d);\n" $PREFIX $i
 	done
 	echo

From 5c822c0ce5cc83ed4cd8394f3dc46dae8d9a681d Mon Sep 17 00:00:00 2001
From: Yuan Can <yuancan@huawei.com>
Date: Thu, 7 Nov 2024 21:52:23 -0800
Subject: [PATCH 0967/1530] Input: cs40l50 - fix wrong usage of INIT_WORK()

In cs40l50_add(), the work_data is a local variable and the work_data.work
should initialize with INIT_WORK_ONSTACK() instead of INIT_WORK().
Small error in cs40l50_erase() also fixed in this commit.

Fixes: c38fe1bb5d21 ("Input: cs40l50 - Add support for the CS40L50 haptic driver")
Signed-off-by: Yuan Can <yuancan@huawei.com>
Reviewed-by: James Ogletree <jogletre@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20241106013549.78142-1-yuancan@huawei.com
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/cs40l50-vibra.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/input/misc/cs40l50-vibra.c b/drivers/input/misc/cs40l50-vibra.c
index 03bdb7c26ec09..dce3b0ec8cf36 100644
--- a/drivers/input/misc/cs40l50-vibra.c
+++ b/drivers/input/misc/cs40l50-vibra.c
@@ -334,11 +334,12 @@ static int cs40l50_add(struct input_dev *dev, struct ff_effect *effect,
 	work_data.custom_len = effect->u.periodic.custom_len;
 	work_data.vib = vib;
 	work_data.effect = effect;
-	INIT_WORK(&work_data.work, cs40l50_add_worker);
+	INIT_WORK_ONSTACK(&work_data.work, cs40l50_add_worker);
 
 	/* Push to the workqueue to serialize with playbacks */
 	queue_work(vib->vib_wq, &work_data.work);
 	flush_work(&work_data.work);
+	destroy_work_on_stack(&work_data.work);
 
 	kfree(work_data.custom_data);
 
@@ -467,11 +468,12 @@ static int cs40l50_erase(struct input_dev *dev, int effect_id)
 	work_data.vib = vib;
 	work_data.effect = &dev->ff->effects[effect_id];
 
-	INIT_WORK(&work_data.work, cs40l50_erase_worker);
+	INIT_WORK_ONSTACK(&work_data.work, cs40l50_erase_worker);
 
 	/* Push to workqueue to serialize with playbacks */
 	queue_work(vib->vib_wq, &work_data.work);
 	flush_work(&work_data.work);
+	destroy_work_on_stack(&work_data.work);
 
 	return work_data.error;
 }

From 781a07da9bb9409f14893c1be47bf83cf4858e2e Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Wed, 20 Mar 2024 08:23:07 +0100
Subject: [PATCH 0968/1530] Input: ads7846 - add dummy command register
 clearing cycle

On STM32MP135F with XPT2046 touch controller attached to SPI bus, it has
been observed that the touch controller locks up after Linux kernel has
finished booting. Adding a dummy cycle on the SPI bus seems to mitigate
the lock up.

The XPTEK XPT2046 controller seems to be an identical clone of TI TSC2046,
the datasheet seems to be a clone of the TI part as well, text seem to be
word to word identical, except all the pictures have been drawn again.

This touch controller is present e.g. on WaveShare 3.2inch RPi LCD (B)
panel, the DTO provided by WaveShare uses 50 kHz SPI clock for this
touch controller, which is unusually low and possibly might have been
used as some sort of workaround for an issue. The SPI LCD on the same
bus uses 16 MHz clock.

SPI bus DT properties spi-cs-setup-delay-ns, spi-cs-hold-delay-ns,
spi-cs-inactive-delay-ns, spi-rx-delay-us, spi-tx-delay-us set to
range of 500ns..5us seem to have no impact on the behavior of the
touch controller, the lock up always occurs. The STM32MP13xx SPI
controller users GPIO control for the nCS pins.

Since the dummy cycle happens after the controller has been put into
power down mode and both ADC and REF regulators have been disabled,
the cycle should have no impact on the configuration of the controller,
i.e. it should be a NOP.

It is unclear whether this problem is specific to this cloned XPT2046
controller, or whether this is also present on TSC2046. A test on
either TSC2046 or ADS7846 would be very welcome.

Signed-off-by: Marek Vasut <marex@denx.de>
Link: https://lore.kernel.org/r/20240320072533.170029-1-marex@denx.de
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/ads7846.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c
index f89c0dd15d8b9..f7bc0a3e56d86 100644
--- a/drivers/input/touchscreen/ads7846.c
+++ b/drivers/input/touchscreen/ads7846.c
@@ -405,9 +405,19 @@ static int ads7846_read12_ser(struct device *dev, unsigned command)
 
 	req->xfer[5].rx_buf = &req->scratch;
 	req->xfer[5].len = 2;
-	CS_CHANGE(req->xfer[5]);
 	spi_message_add_tail(&req->xfer[5], &req->msg);
 
+	/* clear the command register */
+	req->scratch = 0;
+	req->xfer[6].tx_buf = &req->scratch;
+	req->xfer[6].len = 1;
+	spi_message_add_tail(&req->xfer[6], &req->msg);
+
+	req->xfer[7].rx_buf = &req->scratch;
+	req->xfer[7].len = 2;
+	CS_CHANGE(req->xfer[7]);
+	spi_message_add_tail(&req->xfer[7], &req->msg);
+
 	mutex_lock(&ts->lock);
 	ads7846_stop(ts);
 	status = spi_sync(spi, &req->msg);

From bed0f75909b21c0cd0285da76fdfcc61a9745b0c Mon Sep 17 00:00:00 2001
From: Shivam Chaudhary <cvam0000@gmail.com>
Date: Thu, 7 Nov 2024 23:19:18 +0530
Subject: [PATCH 0969/1530] Input: i8042 - fix typo dublicate to duplicate

Fix typo in i8042-acpipnpio.h dublicate -> duplicate.

Signed-off-by: Shivam Chaudhary <cvam0000@gmail.com>
Link: https://lore.kernel.org/r/20241107174918.78335-1-cvam0000@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/i8042-acpipnpio.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index bad238f69a7af..d236469032b17 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -90,7 +90,7 @@ static inline void i8042_write_command(int val)
  * ORDERING IS IMPORTANT! The first match will be apllied and the rest ignored.
  * This allows entries to overwrite vendor wide quirks on a per device basis.
  * Where this is irrelevant, entries are sorted case sensitive by DMI_SYS_VENDOR
- * and/or DMI_BOARD_VENDOR to make it easier to avoid dublicate entries.
+ * and/or DMI_BOARD_VENDOR to make it easier to avoid duplicate entries.
  */
 static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 	{

From 86db3f0dfa962c552caec6e5559c68f1d86fe459 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Mon, 4 Nov 2024 13:44:36 -0600
Subject: [PATCH 0970/1530] pinctrl: Use of_property_present() for non-boolean
 properties

The use of of_property_read_bool() for non-boolean properties is
deprecated in favor of of_property_present() when testing for property
presence.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/20241104194437.327430-1-robh@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/freescale/pinctrl-imx.c  | 6 +++---
 drivers/pinctrl/pinctrl-xway.c           | 2 +-
 drivers/pinctrl/qcom/pinctrl-msm.c       | 2 +-
 drivers/pinctrl/qcom/pinctrl-spmi-gpio.c | 2 +-
 drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c | 2 +-
 5 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index d05c2c478e795..842a1e6cbfc41 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -633,11 +633,11 @@ static int imx_pinctrl_parse_functions(struct device_node *np,
 static bool imx_pinctrl_dt_is_flat_functions(struct device_node *np)
 {
 	for_each_child_of_node_scoped(np, function_np) {
-		if (of_property_read_bool(function_np, "fsl,pins"))
+		if (of_property_present(function_np, "fsl,pins"))
 			return true;
 
 		for_each_child_of_node_scoped(function_np, pinctrl_np) {
-			if (of_property_read_bool(pinctrl_np, "fsl,pins"))
+			if (of_property_present(pinctrl_np, "fsl,pins"))
 				return false;
 		}
 	}
@@ -746,7 +746,7 @@ int imx_pinctrl_probe(struct platform_device *pdev,
 		if (IS_ERR(ipctl->base))
 			return PTR_ERR(ipctl->base);
 
-		if (of_property_read_bool(dev_np, "fsl,input-sel")) {
+		if (of_property_present(dev_np, "fsl,input-sel")) {
 			np = of_parse_phandle(dev_np, "fsl,input-sel", 0);
 			if (!np) {
 				dev_err(&pdev->dev, "iomuxc fsl,input-sel property not found\n");
diff --git a/drivers/pinctrl/pinctrl-xway.c b/drivers/pinctrl/pinctrl-xway.c
index f4256a918165f..48f8aabf3bfa3 100644
--- a/drivers/pinctrl/pinctrl-xway.c
+++ b/drivers/pinctrl/pinctrl-xway.c
@@ -1524,7 +1524,7 @@ static int pinmux_xway_probe(struct platform_device *pdev)
 	 * files which don't set the "gpio-ranges" property or systems that
 	 * utilize ACPI the driver has to call gpiochip_add_pin_range().
 	 */
-	if (!of_property_read_bool(pdev->dev.of_node, "gpio-ranges")) {
+	if (!of_property_present(pdev->dev.of_node, "gpio-ranges")) {
 		/* finish with registering the gpio range in pinctrl */
 		xway_gpio_range.npins = xway_chip.ngpio;
 		xway_gpio_range.base = xway_chip.base;
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index aeaf0d1958f56..ec913c2e200f5 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -1457,7 +1457,7 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl)
 	 * files which don't set the "gpio-ranges" property or systems that
 	 * utilize ACPI the driver has to call gpiochip_add_pin_range().
 	 */
-	if (!of_property_read_bool(pctrl->dev->of_node, "gpio-ranges")) {
+	if (!of_property_present(pctrl->dev->of_node, "gpio-ranges")) {
 		ret = gpiochip_add_pin_range(&pctrl->chip,
 			dev_name(pctrl->dev), 0, 0, chip->ngpio);
 		if (ret) {
diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
index c33af2d667784..fd238882d921e 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
@@ -1169,7 +1169,7 @@ static int pmic_gpio_probe(struct platform_device *pdev)
 	 * files which don't set the "gpio-ranges" property or systems that
 	 * utilize ACPI the driver has to call gpiochip_add_pin_range().
 	 */
-	if (!of_property_read_bool(dev->of_node, "gpio-ranges")) {
+	if (!of_property_present(dev->of_node, "gpio-ranges")) {
 		ret = gpiochip_add_pin_range(&state->chip, dev_name(dev), 0, 0,
 					     npins);
 		if (ret) {
diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
index b750ff4db4c3e..2225dc49d477c 100644
--- a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
@@ -832,7 +832,7 @@ static int pm8xxx_gpio_probe(struct platform_device *pdev)
 	 * files which don't set the "gpio-ranges" property or systems that
 	 * utilize ACPI the driver has to call gpiochip_add_pin_range().
 	 */
-	if (!of_property_read_bool(pctrl->dev->of_node, "gpio-ranges")) {
+	if (!of_property_present(pctrl->dev->of_node, "gpio-ranges")) {
 		ret = gpiochip_add_pin_range(&pctrl->chip, dev_name(pctrl->dev),
 					     0, 0, pctrl->chip.ngpio);
 		if (ret) {

From fecb6e2af7d430d8819da070aab91a84bda82595 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Barnab=C3=A1s=20Cz=C3=A9m=C3=A1n?=
 <barnabas.czeman@mainlining.org>
Date: Thu, 31 Oct 2024 02:19:42 +0100
Subject: [PATCH 0971/1530] dt-bindings: pinctrl: qcom,pmic-gpio: add PM8937
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Document the 8 GPIOs found on PM8937. It has holes on
3,4 and 6 pins.

Signed-off-by: Barnabás Czémán <barnabas.czeman@mainlining.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/20241031-msm8917-v2-1-8a075faa89b1@mainlining.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml
index c1b799167d81b..055cea5452eb6 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml
@@ -48,6 +48,7 @@ properties:
           - qcom,pm8916-gpio
           - qcom,pm8917-gpio
           - qcom,pm8921-gpio
+          - qcom,pm8937-gpio
           - qcom,pm8941-gpio
           - qcom,pm8950-gpio
           - qcom,pm8953-gpio
@@ -184,6 +185,7 @@ allOf:
               - qcom,pm8226-gpio
               - qcom,pm8350b-gpio
               - qcom,pm8550ve-gpio
+              - qcom,pm8937-gpio
               - qcom,pm8950-gpio
               - qcom,pm8953-gpio
               - qcom,pmi632-gpio
@@ -468,6 +470,7 @@ $defs:
                  - gpio1-gpio6 for pm8550vs
                  - gpio1-gpio38 for pm8917
                  - gpio1-gpio44 for pm8921
+                 - gpio1-gpio8 for pm8937 (hole on gpio3, gpio4 and gpio6)
                  - gpio1-gpio36 for pm8941
                  - gpio1-gpio8 for pm8950 (hole on gpio3)
                  - gpio1-gpio8 for pm8953 (hole on gpio3 and gpio6)

From 89265a58ff24e3885c2c9ca722bc3aaa47018be9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Barnab=C3=A1s=20Cz=C3=A9m=C3=A1n?=
 <barnabas.czeman@mainlining.org>
Date: Thu, 31 Oct 2024 02:19:43 +0100
Subject: [PATCH 0972/1530] pinctrl: qcom-pmic-gpio: add support for PM8937
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PM8937 has 8 GPIO-s with holes on GPIO3, GPIO4 and GPIO6.

Signed-off-by: Barnabás Czémán <barnabas.czeman@mainlining.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/20241031-msm8917-v2-2-8a075faa89b1@mainlining.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-spmi-gpio.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
index fd238882d921e..ab07299ef39fa 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
@@ -1226,6 +1226,8 @@ static const struct of_device_id pmic_gpio_of_match[] = {
 	{ .compatible = "qcom,pm8550ve-gpio", .data = (void *) 8 },
 	{ .compatible = "qcom,pm8550vs-gpio", .data = (void *) 6 },
 	{ .compatible = "qcom,pm8916-gpio", .data = (void *) 4 },
+	/* pm8937 has 8 GPIOs with holes on 3, 4 and 6 */
+	{ .compatible = "qcom,pm8937-gpio", .data = (void *) 8 },
 	{ .compatible = "qcom,pm8941-gpio", .data = (void *) 36 },
 	/* pm8950 has 8 GPIOs with holes on 3 */
 	{ .compatible = "qcom,pm8950-gpio", .data = (void *) 8 },

From d33d689eda6e477b05d086955b063829c0ad081a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Barnab=C3=A1s=20Cz=C3=A9m=C3=A1n?=
 <barnabas.czeman@mainlining.org>
Date: Thu, 31 Oct 2024 02:19:44 +0100
Subject: [PATCH 0973/1530] dt-bindings: pinctrl: qcom,pmic-mpp: Document
 PM8937 compatible
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Document the Device Tree binding for PM8937 MPPs.

Signed-off-by: Barnabás Czémán <barnabas.czeman@mainlining.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/20241031-msm8917-v2-3-8a075faa89b1@mainlining.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml
index 43146709e2044..9364ae05f3e68 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml
@@ -22,6 +22,7 @@ properties:
               - qcom,pm8226-mpp
               - qcom,pm8841-mpp
               - qcom,pm8916-mpp
+              - qcom,pm8937-mpp
               - qcom,pm8941-mpp
               - qcom,pm8950-mpp
               - qcom,pmi8950-mpp
@@ -92,6 +93,7 @@ $defs:
           this subnode.  Valid pins are
                  - mpp1-mpp4 for pm8841
                  - mpp1-mpp4 for pm8916
+                 - mpp1-mpp4 for pm8937
                  - mpp1-mpp8 for pm8941
                  - mpp1-mpp4 for pm8950
                  - mpp1-mpp4 for pmi8950

From f755261190e88f5d19fe0a3b762f0bbaff6bd438 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Barnab=C3=A1s=20Cz=C3=A9m=C3=A1n?=
 <barnabas.czeman@mainlining.org>
Date: Thu, 31 Oct 2024 02:19:45 +0100
Subject: [PATCH 0974/1530] pinctrl: qcom: spmi-mpp: Add PM8937 compatible
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PM8937 provides 4 MPPs.
Add a compatible to support them.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Barnabás Czémán <barnabas.czeman@mainlining.org>
Link: https://lore.kernel.org/20241031-msm8917-v2-4-8a075faa89b1@mainlining.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-spmi-mpp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
index b5b3ac82f030b..84de584cf7ebb 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
@@ -983,6 +983,7 @@ static const struct of_device_id pmic_mpp_of_match[] = {
 	{ .compatible = "qcom,pm8226-mpp", .data = (void *) 8 },
 	{ .compatible = "qcom,pm8841-mpp", .data = (void *) 4 },
 	{ .compatible = "qcom,pm8916-mpp", .data = (void *) 4 },
+	{ .compatible = "qcom,pm8937-mpp", .data = (void *) 4 },
 	{ .compatible = "qcom,pm8941-mpp", .data = (void *) 8 },
 	{ .compatible = "qcom,pm8950-mpp", .data = (void *) 4 },
 	{ .compatible = "qcom,pmi8950-mpp", .data = (void *) 4 },

From 4905aa25d31f877c5794fbf9e2acd3598ebe01df Mon Sep 17 00:00:00 2001
From: Chen Wang <unicorn_wang@outlook.com>
Date: Tue, 29 Oct 2024 09:23:12 +0800
Subject: [PATCH 0975/1530] dt-bindings: pinctrl: correct typo of description
 for cv1800

It should be PINMUX/PINMUX2, not GPIOMUX/GPIOMUX2, see
<dt-bindings/pinctrl/pinctrl-cv1800b.h>.

Fixes: 64aa494de6fa ("dt-bindings: pinctrl: Add pinctrl for Sophgo CV1800 series SoC.")
Signed-off-by: Chen Wang <unicorn_wang@outlook.com>
Reviewed-by: Inochi Amaoto <inochiama@gmail.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/20241029012312.3448287-1-unicornxw@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../devicetree/bindings/pinctrl/sophgo,cv1800-pinctrl.yaml      | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/sophgo,cv1800-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/sophgo,cv1800-pinctrl.yaml
index 1e6a55afe26a7..feb4785a3fac5 100644
--- a/Documentation/devicetree/bindings/pinctrl/sophgo,cv1800-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/sophgo,cv1800-pinctrl.yaml
@@ -58,7 +58,7 @@ patternProperties:
           pinmux:
             description: |
               The list of GPIOs and their mux settings that properties in the
-              node apply to. This should be set using the GPIOMUX or GPIOMUX2
+              node apply to. This should be set using the PINMUX or PINMUX2
               macro.
 
           bias-pull-up:

From b8a8a0f268be85e2ad3dd97eaee05c269fb5781b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Duje=20Mihanovi=C4=87?= <duje.mihanovic@skole.hr>
Date: Mon, 4 Nov 2024 17:37:04 +0100
Subject: [PATCH 0976/1530] dt-bindings: pinctrl: pinctrl-single: add
 marvell,pxa1908-padconf compatible
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the "marvell,pxa1908-padconf" compatible to allow migrating to a
separate pinctrl driver later.

Reviewed-by: Rob Herring <robh@kernel.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Duje Mihanović <duje.mihanovic@skole.hr>
Link: https://lore.kernel.org/20241104-pxa1908-lkml-v13-2-e050609b8d6c@skole.hr
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/devicetree/bindings/pinctrl/pinctrl-single.yaml | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-single.yaml b/Documentation/devicetree/bindings/pinctrl/pinctrl-single.yaml
index e02595316c9f4..f83dbf32ad183 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-single.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-single.yaml
@@ -33,6 +33,10 @@ properties:
               - ti,omap5-padconf
               - ti,j7200-padconf
           - const: pinctrl-single
+      - items:
+          - enum:
+              - marvell,pxa1908-padconf
+          - const: pinconf-single
 
   reg:
     maxItems: 1

From ffb7474969edf3a3c0fd5571b9de5c33b6dc2d48 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Duje=20Mihanovi=C4=87?= <duje.mihanovic@skole.hr>
Date: Mon, 4 Nov 2024 17:37:05 +0100
Subject: [PATCH 0977/1530] pinctrl: single: add marvell,pxa1908-padconf
 compatible
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the "marvell,pxa1908-padconf" compatible to allow migrating to a
separate pinctrl driver later.

Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Duje Mihanović <duje.mihanovic@skole.hr>
Link: https://lore.kernel.org/20241104-pxa1908-lkml-v13-3-e050609b8d6c@skole.hr
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-single.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index 8addb08d81a1d..5be14dc979e26 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1966,6 +1966,7 @@ static const struct pcs_soc_data pinconf_single = {
 };
 
 static const struct of_device_id pcs_of_match[] = {
+	{ .compatible = "marvell,pxa1908-padconf", .data = &pinconf_single },
 	{ .compatible = "ti,am437-padconf", .data = &pinctrl_single_am437x },
 	{ .compatible = "ti,am654-padconf", .data = &pinctrl_single_am654 },
 	{ .compatible = "ti,dra7-padconf", .data = &pinctrl_single_dra7 },

From a53643fb30f84a9914a7b7205f4ff4c73fe6e7b6 Mon Sep 17 00:00:00 2001
From: Heiko Schocher <hs@denx.de>
Date: Tue, 5 Nov 2024 07:42:05 +0100
Subject: [PATCH 0978/1530] dt-bindings: pinctrl: sx150xq: allow gpio line
 naming

Adding gpio-line-names property works fine for this
device node, but dtb check drops warning:

'gpio-line-names' does not match any of the regexes: '-cfg$', 'pinctrl-[0-9]+'
from schema $id: http://devicetree.org/schemas/pinctrl/semtech,sx1501q.yaml#

Allow to add property gpio-line-names for this devices.

Signed-off-by: Heiko Schocher <hs@denx.de>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/20241105064206.43626-3-hs@denx.de
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/semtech,sx1501q.yaml     | 43 +++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/semtech,sx1501q.yaml b/Documentation/devicetree/bindings/pinctrl/semtech,sx1501q.yaml
index 4214d7311f6bd..39d7dad3313b6 100644
--- a/Documentation/devicetree/bindings/pinctrl/semtech,sx1501q.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/semtech,sx1501q.yaml
@@ -26,6 +26,10 @@ properties:
   reg:
     maxItems: 1
 
+  gpio-line-names:
+    minItems: 5
+    maxItems: 17
+
   interrupts:
     maxItems: 1
 
@@ -87,6 +91,45 @@ required:
 
 allOf:
   - $ref: pinctrl.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - semtech,sx1501q
+              - semtech,sx1504q
+              - semtech,sx1507q
+    then:
+      properties:
+        gpio-line-names:
+          minItems: 5
+          maxItems: 5
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - semtech,sx1502q
+              - semtech,sx1505q
+              - semtech,sx1508q
+    then:
+      properties:
+        gpio-line-names:
+          minItems: 9
+          maxItems: 9
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - semtech,sx1503q
+              - semtech,sx1506q
+              - semtech,sx1509q
+    then:
+      properties:
+        gpio-line-names:
+          minItems: 17
+          maxItems: 17
   - if:
       not:
         properties:

From 26ec3d7cc3f3aa591c8d5f3fde99df6caca92d02 Mon Sep 17 00:00:00 2001
From: Steve Clevenger <scclevenger@os.amperecomputing.com>
Date: Fri, 8 Nov 2024 12:11:18 -0700
Subject: [PATCH 0979/1530] perf script cs_etm: Add map_pgoff to python
 dictionary
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extract map_pgoff parameter from the dictionary, and adjust start/end
range passed to objdump based on the value.

A zero start_addr is filtered to prevent output of dso address range
check failures. This script repeatedly sees a zero value passed
in for
      start_addr = cpu_data[str(cpu) + 'addr']

These zero values are not a new problem. The start_addr/stop_addr warning
clutters the instruction trace output, hence this change.

Signed-off-by: Steve Clevenger <scclevenger@os.amperecomputing.com>
Reviewed-by: Leo Yan <leo.yan@arm.com>
Cc: suzuki.poulose@arm.com
Cc: james.clark@linaro.org
Cc: mike.leach@linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: coresight@lists.linaro.org
Cc: ilkka@os.amperecomputing.com
Link: https://lore.kernel.org/r/8d9a1142dc58ffa34a000cb7b7a26055df0a37ec.1731027120.git.scclevenger@os.amperecomputing.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/scripting-engines/trace-event-python.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index d7183134b6699..e6d4711a7d69c 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -793,7 +793,8 @@ static int set_regs_in_dict(PyObject *dict,
 static void set_sym_in_dict(PyObject *dict, struct addr_location *al,
 			    const char *dso_field, const char *dso_bid_field,
 			    const char *dso_map_start, const char *dso_map_end,
-			    const char *sym_field, const char *symoff_field)
+			    const char *sym_field, const char *symoff_field,
+			    const char *map_pgoff)
 {
 	char sbuild_id[SBUILD_ID_SIZE];
 
@@ -809,6 +810,8 @@ static void set_sym_in_dict(PyObject *dict, struct addr_location *al,
 			PyLong_FromUnsignedLong(map__start(al->map)));
 		pydict_set_item_string_decref(dict, dso_map_end,
 			PyLong_FromUnsignedLong(map__end(al->map)));
+		pydict_set_item_string_decref(dict, map_pgoff,
+			PyLong_FromUnsignedLongLong(map__pgoff(al->map)));
 	}
 	if (al->sym) {
 		pydict_set_item_string_decref(dict, sym_field,
@@ -895,7 +898,7 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 	pydict_set_item_string_decref(dict, "comm",
 			_PyUnicode_FromString(thread__comm_str(al->thread)));
 	set_sym_in_dict(dict, al, "dso", "dso_bid", "dso_map_start", "dso_map_end",
-			"symbol", "symoff");
+			"symbol", "symoff", "map_pgoff");
 
 	pydict_set_item_string_decref(dict, "callchain", callchain);
 
@@ -920,7 +923,7 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 			PyBool_FromLong(1));
 		set_sym_in_dict(dict_sample, addr_al, "addr_dso", "addr_dso_bid",
 				"addr_dso_map_start", "addr_dso_map_end",
-				"addr_symbol", "addr_symoff");
+				"addr_symbol", "addr_symoff", "addr_map_pgoff");
 	}
 
 	if (sample->flags)

From e8328bf3cd135b5f443bed77f3791ac1633ae01e Mon Sep 17 00:00:00 2001
From: Steve Clevenger <scclevenger@os.amperecomputing.com>
Date: Fri, 8 Nov 2024 12:11:17 -0700
Subject: [PATCH 0980/1530] perf script python: Adjust objdump start/end per
 map pgoff parameter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extract map_pgoff parameter from the dictionary, and adjust start/end
range passed to objdump based on the value.

A zero start_addr is filtered to prevent output of dso address range
check failures. This script repeatedly sees a zero value passed
in for
      start_addr = cpu_data[str(cpu) + 'addr']

These zero values are not a new problem. The start_addr/stop_addr warning
clutters the instruction trace output, hence this change.

Signed-off-by: Steve Clevenger <scclevenger@os.amperecomputing.com>
Reviewed-by: Leo Yan <leo.yan@arm.com>
Cc: suzuki.poulose@arm.com
Cc: james.clark@linaro.org
Cc: mike.leach@linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: coresight@lists.linaro.org
Cc: ilkka@os.amperecomputing.com
Link: https://lore.kernel.org/r/21ccdd22e664bdeccb878672d4b2c0518873c1e5.1731027120.git.scclevenger@os.amperecomputing.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/scripts/python/arm-cs-trace-disasm.py | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py
index 1128d259b4f47..ba208c90d6311 100755
--- a/tools/perf/scripts/python/arm-cs-trace-disasm.py
+++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
@@ -251,6 +251,10 @@ def process_event(param_dict):
 	dso_start = get_optional(param_dict, "dso_map_start")
 	dso_end = get_optional(param_dict, "dso_map_end")
 	symbol = get_optional(param_dict, "symbol")
+	map_pgoff = get_optional(param_dict, "map_pgoff")
+	# check for valid map offset
+	if (str(map_pgoff) == '[unknown]'):
+		map_pgoff = 0
 
 	cpu = sample["cpu"]
 	ip = sample["ip"]
@@ -318,9 +322,10 @@ def process_event(param_dict):
 	# Record for previous sample packet
 	cpu_data[str(cpu) + 'addr'] = addr
 
-	# Handle CS_ETM_TRACE_ON packet if start_addr=0 and stop_addr=4
-	if (start_addr == 0 and stop_addr == 4):
-		print("CPU%d: CS_ETM_TRACE_ON packet is inserted" % cpu)
+	# Filter out zero start_address. Optionally identify CS_ETM_TRACE_ON packet
+	if (start_addr == 0):
+		if ((stop_addr == 4) and (options.verbose == True)):
+			print("CPU%d: CS_ETM_TRACE_ON packet is inserted" % cpu)
 		return
 
 	if (start_addr < int(dso_start) or start_addr > int(dso_end)):
@@ -337,13 +342,14 @@ def process_event(param_dict):
 		# vm_start to zero.
 		if (dso == "[kernel.kallsyms]" or dso_start == 0x400000):
 			dso_vm_start = 0
+			map_pgoff = 0
 		else:
 			dso_vm_start = int(dso_start)
 
 		dso_fname = get_dso_file_path(dso, dso_bid)
 		if path.exists(dso_fname):
-			print_disam(dso_fname, dso_vm_start, start_addr, stop_addr)
+			print_disam(dso_fname, dso_vm_start, start_addr + map_pgoff, stop_addr + map_pgoff)
 		else:
-			print("Failed to find dso %s for address range [ 0x%x .. 0x%x ]" % (dso, start_addr, stop_addr))
+			print("Failed to find dso %s for address range [ 0x%x .. 0x%x ]" % (dso, start_addr + map_pgoff, stop_addr + map_pgoff))
 
 	print_srccode(comm, param_dict, sample, symbol, dso)

From 35de42cdfb64af8357b8c531cc2dad28bde5c712 Mon Sep 17 00:00:00 2001
From: Yicong Yang <yangyicong@hisilicon.com>
Date: Tue, 5 Nov 2024 18:56:49 +0800
Subject: [PATCH 0981/1530] perf build: Include libtraceevent headers directly
 indicated by pkg-config

Currently the libtraceevent's found by pkg-config, which give the
include path as:

  [root@localhost tmp]# pkg-config --cflags libtraceevent
  -I/usr/local/include/traceevent

So we should include the libtraceevent headers directly without
"traceevent/" prefix. Update all the users.

Fixes: 0f0e1f445690 ("perf build: Use pkg-config for feature check for libtrace{event,fs}")
Suggested-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/linux-perf-users/ZyF5_Hf1iL01kldE@google.com/
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Cc: leo.yan@arm.com
Cc: amadio@gentoo.org
Cc: linuxarm@huawei.com
Link: https://lore.kernel.org/r/20241105105649.45399-1-yangyicong@huawei.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/build/feature/test-libtraceevent.c               | 2 +-
 tools/perf/builtin-kmem.c                              | 2 +-
 tools/perf/builtin-kwork.c                             | 2 +-
 tools/perf/builtin-report.c                            | 2 +-
 tools/perf/builtin-script.c                            | 2 +-
 tools/perf/builtin-timechart.c                         | 2 +-
 tools/perf/builtin-trace.c                             | 2 +-
 tools/perf/tests/evsel-tp-sched.c                      | 2 +-
 tools/perf/util/data-convert-bt.c                      | 2 +-
 tools/perf/util/data-convert-json.c                    | 2 +-
 tools/perf/util/debug.c                                | 2 +-
 tools/perf/util/evsel.c                                | 2 +-
 tools/perf/util/evsel_fprintf.c                        | 2 +-
 tools/perf/util/header.c                               | 2 +-
 tools/perf/util/python.c                               | 2 +-
 tools/perf/util/scripting-engines/trace-event-perl.c   | 2 +-
 tools/perf/util/scripting-engines/trace-event-python.c | 2 +-
 tools/perf/util/sort.c                                 | 2 +-
 tools/perf/util/trace-event-parse.c                    | 2 +-
 tools/perf/util/trace-event-read.c                     | 2 +-
 tools/perf/util/trace-event-scripting.c                | 2 +-
 tools/perf/util/trace-event.c                          | 2 +-
 tools/perf/util/trace-event.h                          | 2 +-
 23 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/tools/build/feature/test-libtraceevent.c b/tools/build/feature/test-libtraceevent.c
index 416b11ffd4b4f..804ad80dbbd93 100644
--- a/tools/build/feature/test-libtraceevent.c
+++ b/tools/build/feature/test-libtraceevent.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <traceevent/trace-seq.h>
+#include <trace-seq.h>
 
 int main(void)
 {
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index a756147e2eec7..4d8d94146f8dd 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -36,7 +36,7 @@
 #include <regex.h>
 
 #include <linux/ctype.h>
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 
 static int	kmem_slab;
 static int	kmem_page;
diff --git a/tools/perf/builtin-kwork.c b/tools/perf/builtin-kwork.c
index c1daf82c9b923..8234410cba4c8 100644
--- a/tools/perf/builtin-kwork.c
+++ b/tools/perf/builtin-kwork.c
@@ -23,7 +23,7 @@
 
 #include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 
 #include <errno.h>
 #include <inttypes.h>
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 45304ee5537cb..048c91960ba91 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -70,7 +70,7 @@
 #include <linux/mman.h>
 
 #ifdef HAVE_LIBTRACEEVENT
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #endif
 
 struct report {
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 6b6d4472db6e6..9e47905f75a6b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -67,7 +67,7 @@
 
 #include <linux/ctype.h>
 #ifdef HAVE_LIBTRACEEVENT
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #endif
 
 static char const		*script_name;
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 218c8b44d7bea..9b50076449bd0 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -38,7 +38,7 @@
 #include "util/tracepoint.h"
 #include "util/util.h"
 #include <linux/err.h>
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 
 #ifdef LACKS_OPEN_MEMSTREAM_PROTOTYPE
 FILE *open_memstream(char **ptr, size_t *sizeloc);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index a661fbd870e7c..156c3e8291790 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -88,7 +88,7 @@
 #include <perf/mmap.h>
 
 #ifdef HAVE_LIBTRACEEVENT
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #endif
 
 #ifndef O_CLOEXEC
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 3da6a76eac385..226196fb96779 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/err.h>
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #include "evsel.h"
 #include "tests.h"
 #include "debug.h"
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 021e9b1d5cc52..f0599c61fab47 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -36,7 +36,7 @@
 #include "util/sample.h"
 
 #ifdef HAVE_LIBTRACEEVENT
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #endif
 
 #define pr_N(n, fmt, ...) \
diff --git a/tools/perf/util/data-convert-json.c b/tools/perf/util/data-convert-json.c
index 20bfb0884e9ea..8304cd2d4a9ce 100644
--- a/tools/perf/util/data-convert-json.c
+++ b/tools/perf/util/data-convert-json.c
@@ -28,7 +28,7 @@
 #include "util/tool.h"
 
 #ifdef HAVE_LIBTRACEEVENT
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #endif
 
 struct convert_json {
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index d633d15329fa0..995f6bb05b5f8 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -27,7 +27,7 @@
 #include <linux/ctype.h>
 
 #ifdef HAVE_LIBTRACEEVENT
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #else
 #define LIBTRACEEVENT_VERSION 0
 #endif
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f780e30aa259f..ef45a3f49056c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -70,7 +70,7 @@
 #include <linux/ctype.h>
 
 #ifdef HAVE_LIBTRACEEVENT
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #endif
 
 struct perf_missing_features perf_missing_features;
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index c2c0500d5da99..86b7f46f9e2a9 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -14,7 +14,7 @@
 #include "dso.h"
 
 #ifdef HAVE_LIBTRACEEVENT
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #endif
 
 static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...)
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a6386d12afd72..fca27b316fafc 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -58,7 +58,7 @@
 #include <internal/lib.h>
 
 #ifdef HAVE_LIBTRACEEVENT
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #endif
 
 /*
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index ee3d43a7ba457..2096cdbaa53b4 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -6,7 +6,7 @@
 #include <linux/err.h>
 #include <perf/cpumap.h>
 #ifdef HAVE_LIBTRACEEVENT
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #endif
 #include <perf/mmap.h>
 #include "evlist.h"
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index e16257d5ab2c8..85b7f188f7299 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -27,7 +27,7 @@
 #include <errno.h>
 #include <linux/bitmap.h>
 #include <linux/time64.h>
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 
 #include <stdbool.h>
 /* perl needs the following define, right after including stdbool.h */
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index e6d4711a7d69c..8bdae066e8397 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -31,7 +31,7 @@
 #include <linux/compiler.h>
 #include <linux/time64.h>
 #ifdef HAVE_LIBTRACEEVENT
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #endif
 
 #include "../build-id.h"
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 168c488f0178d..9dd60c7869a28 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -35,7 +35,7 @@
 #include <linux/string.h>
 
 #ifdef HAVE_LIBTRACEEVENT
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #endif
 
 regex_t		parent_regex;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index d97830cdbd7e6..41d53e1b43e7a 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -12,7 +12,7 @@
 
 #include <linux/ctype.h>
 #include <linux/kernel.h>
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 
 static int get_common_field(struct scripting_context *context,
 			    int *offset, int *size, const char *type)
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 1162c49b80825..ecbbb93f01853 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -11,7 +11,7 @@
 #include <sys/stat.h>
 #include <sys/wait.h>
 #include <sys/mman.h>
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #include <fcntl.h>
 #include <unistd.h>
 #include <errno.h>
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index bd0000300c774..5596fcda2c108 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -10,7 +10,7 @@
 #include <string.h>
 #include <errno.h>
 #ifdef HAVE_LIBTRACEEVENT
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #endif
 
 #include "debug.h"
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 8ad75b31e09b8..6a8c66c64b705 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -8,7 +8,7 @@
 #include <fcntl.h>
 #include <linux/kernel.h>
 #include <linux/err.h>
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #include <api/fs/tracing_path.h>
 #include <api/fs/fs.h>
 #include "trace-event.h"
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 0e5133f1b9103..79b939f947dd2 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -147,7 +147,7 @@ int common_lock_depth(struct scripting_context *context);
 int perf_sample__sprintf_flags(u32 flags, char *str, size_t sz);
 
 #if defined(LIBTRACEEVENT_VERSION) &&  LIBTRACEEVENT_VERSION >= MAKE_LIBTRACEEVENT_VERSION(1, 5, 0)
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 
 static inline bool tep_field_is_relative(unsigned long flags)
 {

From f4db95b68ae68ebaf91d35cc0487ac1cbd04261e Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 16:37:53 -0800
Subject: [PATCH 0982/1530] tools api io: Ensure line_len_out is always
 initialized

Ensure initialization to avoid compiler warnings about potential use
of uninitialized variables.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Yoshihiro Furudera <fj5100bi@fujitsu.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Junhao He <hejunhao3@huawei.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20241109003759.473460-2-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/lib/api/io.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h
index d3eb04d1bc897..1731996b2c32a 100644
--- a/tools/lib/api/io.h
+++ b/tools/lib/api/io.h
@@ -189,6 +189,7 @@ static inline ssize_t io__getdelim(struct io *io, char **line_out, size_t *line_
 err_out:
 	free(line);
 	*line_out = NULL;
+	*line_len_out = 0;
 	return -ENOMEM;
 }
 

From 4810b761f812da3ca33badd7861a04b58613a4a1 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 16:37:54 -0800
Subject: [PATCH 0983/1530] perf hwmon_pmu: Add hwmon filename parser

hwmon filenames have a specific encoding that will be used to give a
config value. The encoding is described in:
Documentation/hwmon/sysfs-interface.rst
Add a function to parse the filename into consituent enums/ints that
will then be amenable to config encoding.

Note, things are done this way to allow mapping names to config and
back without the use of hash/dynamic lookup tables.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Yoshihiro Furudera <fj5100bi@fujitsu.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Junhao He <hejunhao3@huawei.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
[namhyung: add #include <linux/string.h> for strlcpy()]
Link: https://lore.kernel.org/r/20241109003759.473460-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/Build       |   1 +
 tools/perf/util/hwmon_pmu.c | 145 ++++++++++++++++++++++++++++++++++++
 tools/perf/util/hwmon_pmu.h | 111 +++++++++++++++++++++++++++
 3 files changed, 257 insertions(+)
 create mode 100644 tools/perf/util/hwmon_pmu.c
 create mode 100644 tools/perf/util/hwmon_pmu.h

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 1eedead5f2f28..78b990c04f719 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -83,6 +83,7 @@ perf-util-y += pmu.o
 perf-util-y += pmus.o
 perf-util-y += pmu-flex.o
 perf-util-y += pmu-bison.o
+perf-util-y += hwmon_pmu.o
 perf-util-y += tool_pmu.o
 perf-util-y += svghelper.o
 perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event-info.o
diff --git a/tools/perf/util/hwmon_pmu.c b/tools/perf/util/hwmon_pmu.c
new file mode 100644
index 0000000000000..301793b13337d
--- /dev/null
+++ b/tools/perf/util/hwmon_pmu.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+#include "debug.h"
+#include "hwmon_pmu.h"
+#include <assert.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+
+/** Strings that correspond to enum hwmon_type. */
+static const char * const hwmon_type_strs[HWMON_TYPE_MAX] = {
+	NULL,
+	"cpu",
+	"curr",
+	"energy",
+	"fan",
+	"humidity",
+	"in",
+	"intrusion",
+	"power",
+	"pwm",
+	"temp",
+};
+#define LONGEST_HWMON_TYPE_STR "intrusion"
+
+/** Strings that correspond to enum hwmon_item. */
+static const char * const hwmon_item_strs[HWMON_ITEM__MAX] = {
+	NULL,
+	"accuracy",
+	"alarm",
+	"auto_channels_temp",
+	"average",
+	"average_highest",
+	"average_interval",
+	"average_interval_max",
+	"average_interval_min",
+	"average_lowest",
+	"average_max",
+	"average_min",
+	"beep",
+	"cap",
+	"cap_hyst",
+	"cap_max",
+	"cap_min",
+	"crit",
+	"crit_hyst",
+	"div",
+	"emergency",
+	"emergency_hist",
+	"enable",
+	"fault",
+	"freq",
+	"highest",
+	"input",
+	"label",
+	"lcrit",
+	"lcrit_hyst",
+	"lowest",
+	"max",
+	"max_hyst",
+	"min",
+	"min_hyst",
+	"mod",
+	"offset",
+	"pulses",
+	"rated_max",
+	"rated_min",
+	"reset_history",
+	"target",
+	"type",
+	"vid",
+};
+#define LONGEST_HWMON_ITEM_STR "average_interval_max"
+
+static int hwmon_strcmp(const void *a, const void *b)
+{
+	const char *sa = a;
+	const char * const *sb = b;
+
+	return strcmp(sa, *sb);
+}
+
+bool parse_hwmon_filename(const char *filename,
+			  enum hwmon_type *type,
+			  int *number,
+			  enum hwmon_item *item,
+			  bool *alarm)
+{
+	char fn_type[24];
+	const char **elem;
+	const char *fn_item = NULL;
+	size_t fn_item_len;
+
+	assert(strlen(LONGEST_HWMON_TYPE_STR) < sizeof(fn_type));
+	strlcpy(fn_type, filename, sizeof(fn_type));
+	for (size_t i = 0; fn_type[i] != '\0'; i++) {
+		if (fn_type[i] >= '0' && fn_type[i] <= '9') {
+			fn_type[i] = '\0';
+			*number = strtoul(&filename[i], (char **)&fn_item, 10);
+			if (*fn_item == '_')
+				fn_item++;
+			break;
+		}
+		if (fn_type[i] == '_') {
+			fn_type[i] = '\0';
+			*number = -1;
+			fn_item = &filename[i + 1];
+			break;
+		}
+	}
+	if (fn_item == NULL || fn_type[0] == '\0' || (item != NULL && fn_item[0] == '\0')) {
+		pr_debug("hwmon_pmu: not a hwmon file '%s'\n", filename);
+		return false;
+	}
+	elem = bsearch(&fn_type, hwmon_type_strs + 1, ARRAY_SIZE(hwmon_type_strs) - 1,
+		       sizeof(hwmon_type_strs[0]), hwmon_strcmp);
+	if (!elem) {
+		pr_debug("hwmon_pmu: not a hwmon type '%s' in file name '%s'\n",
+			 fn_type, filename);
+		return false;
+	}
+
+	*type = elem - &hwmon_type_strs[0];
+	if (!item)
+		return true;
+
+	*alarm = false;
+	fn_item_len = strlen(fn_item);
+	if (fn_item_len > 6 && !strcmp(&fn_item[fn_item_len - 6], "_alarm")) {
+		assert(strlen(LONGEST_HWMON_ITEM_STR) < sizeof(fn_type));
+		strlcpy(fn_type, fn_item, fn_item_len - 5);
+		fn_item = fn_type;
+		*alarm = true;
+	}
+	elem = bsearch(fn_item, hwmon_item_strs + 1, ARRAY_SIZE(hwmon_item_strs) - 1,
+		       sizeof(hwmon_item_strs[0]), hwmon_strcmp);
+	if (!elem) {
+		pr_debug("hwmon_pmu: not a hwmon item '%s' in file name '%s'\n",
+			 fn_item, filename);
+		return false;
+	}
+	*item = elem - &hwmon_item_strs[0];
+	return true;
+}
diff --git a/tools/perf/util/hwmon_pmu.h b/tools/perf/util/hwmon_pmu.h
new file mode 100644
index 0000000000000..df0ab5ff75349
--- /dev/null
+++ b/tools/perf/util/hwmon_pmu.h
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __HWMON_PMU_H
+#define __HWMON_PMU_H
+
+#include <stdbool.h>
+
+/**
+ * enum hwmon_type:
+ *
+ * As described in Documentation/hwmon/sysfs-interface.rst hwmon events are
+ * defined over multiple files of the form <type><num>_<item>. This enum
+ * captures potential <type> values.
+ *
+ * This enum is exposed for testing.
+ */
+enum hwmon_type {
+	HWMON_TYPE_NONE,
+
+	HWMON_TYPE_CPU,
+	HWMON_TYPE_CURR,
+	HWMON_TYPE_ENERGY,
+	HWMON_TYPE_FAN,
+	HWMON_TYPE_HUMIDITY,
+	HWMON_TYPE_IN,
+	HWMON_TYPE_INTRUSION,
+	HWMON_TYPE_POWER,
+	HWMON_TYPE_PWM,
+	HWMON_TYPE_TEMP,
+
+	HWMON_TYPE_MAX
+};
+
+/**
+ * enum hwmon_item:
+ *
+ * Similar to enum hwmon_type but describes the item part of a a sysfs filename.
+ *
+ * This enum is exposed for testing.
+ */
+enum hwmon_item {
+	HWMON_ITEM_NONE,
+
+	HWMON_ITEM_ACCURACY,
+	HWMON_ITEM_ALARM,
+	HWMON_ITEM_AUTO_CHANNELS_TEMP,
+	HWMON_ITEM_AVERAGE,
+	HWMON_ITEM_AVERAGE_HIGHEST,
+	HWMON_ITEM_AVERAGE_INTERVAL,
+	HWMON_ITEM_AVERAGE_INTERVAL_MAX,
+	HWMON_ITEM_AVERAGE_INTERVAL_MIN,
+	HWMON_ITEM_AVERAGE_LOWEST,
+	HWMON_ITEM_AVERAGE_MAX,
+	HWMON_ITEM_AVERAGE_MIN,
+	HWMON_ITEM_BEEP,
+	HWMON_ITEM_CAP,
+	HWMON_ITEM_CAP_HYST,
+	HWMON_ITEM_CAP_MAX,
+	HWMON_ITEM_CAP_MIN,
+	HWMON_ITEM_CRIT,
+	HWMON_ITEM_CRIT_HYST,
+	HWMON_ITEM_DIV,
+	HWMON_ITEM_EMERGENCY,
+	HWMON_ITEM_EMERGENCY_HIST,
+	HWMON_ITEM_ENABLE,
+	HWMON_ITEM_FAULT,
+	HWMON_ITEM_FREQ,
+	HWMON_ITEM_HIGHEST,
+	HWMON_ITEM_INPUT,
+	HWMON_ITEM_LABEL,
+	HWMON_ITEM_LCRIT,
+	HWMON_ITEM_LCRIT_HYST,
+	HWMON_ITEM_LOWEST,
+	HWMON_ITEM_MAX,
+	HWMON_ITEM_MAX_HYST,
+	HWMON_ITEM_MIN,
+	HWMON_ITEM_MIN_HYST,
+	HWMON_ITEM_MOD,
+	HWMON_ITEM_OFFSET,
+	HWMON_ITEM_PULSES,
+	HWMON_ITEM_RATED_MAX,
+	HWMON_ITEM_RATED_MIN,
+	HWMON_ITEM_RESET_HISTORY,
+	HWMON_ITEM_TARGET,
+	HWMON_ITEM_TYPE,
+	HWMON_ITEM_VID,
+
+	HWMON_ITEM__MAX,
+};
+
+/**
+ * parse_hwmon_filename() - Parse filename into constituent parts.
+ *
+ * @filename: To be parsed, of the form <type><number>_<item>.
+ * @type: The type defined from the parsed file name.
+ * @number: The number of the type, for example there may be more than 1 fan.
+ * @item: A hwmon <type><number> may have multiple associated items.
+ * @alarm: Is the filename for an alarm value?
+ *
+ * An example of a hwmon filename is "temp1_input". The type is temp for a
+ * temperature value. The number is 1. The item within the file is an input
+ * value - the temperature itself. This file doesn't contain an alarm value.
+ *
+ * Exposed for testing.
+ */
+bool parse_hwmon_filename(const char *filename,
+			  enum hwmon_type *type,
+			  int *number,
+			  enum hwmon_item *item,
+			  bool *alarm);
+
+#endif /* __HWMON_PMU_H */

From 8c329057def8e3409a82839b1a730935b77feeab Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 16:37:55 -0800
Subject: [PATCH 0984/1530] perf test: Add hwmon filename parser test

Filename parsing maps a hwmon filename to constituent parts enum/int
parts for the hwmon config value. Add a test case for the parsing.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Yoshihiro Furudera <fj5100bi@fujitsu.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Junhao He <hejunhao3@huawei.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
[namhyung: add #include <linux/string.h> for strlcpy()]
Link: https://lore.kernel.org/r/20241109003759.473460-4-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/Build          |   1 +
 tools/perf/tests/builtin-test.c |   1 +
 tools/perf/tests/hwmon_pmu.c    | 111 ++++++++++++++++++++++++++++++++
 tools/perf/tests/tests.h        |   1 +
 4 files changed, 114 insertions(+)
 create mode 100644 tools/perf/tests/hwmon_pmu.c

diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 01ed9335db4db..ec4e1f0347424 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -66,6 +66,7 @@ perf-test-y += sigtrap.o
 perf-test-y += event_groups.o
 perf-test-y += symbols.o
 perf-test-y += util.o
+perf-test-y += hwmon_pmu.o
 perf-test-y += tool_pmu.o
 
 ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc))
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index d2cabaa8ad922..8dcf74d3c0a39 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -71,6 +71,7 @@ static struct test_suite *generic_tests[] = {
 	&suite__PERF_RECORD,
 	&suite__pmu,
 	&suite__pmu_events,
+	&suite__hwmon_pmu,
 	&suite__tool_pmu,
 	&suite__dso_data,
 	&suite__perf_evsel__roundtrip_name_test,
diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c
new file mode 100644
index 0000000000000..111fc5c5618a1
--- /dev/null
+++ b/tools/perf/tests/hwmon_pmu.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+#include "debug.h"
+#include "hwmon_pmu.h"
+#include "tests.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+
+static int test__parse_hwmon_filename(struct test_suite *test __maybe_unused,
+				      int subtest __maybe_unused)
+{
+	const struct hwmon_parse_test {
+		const char *filename;
+		enum hwmon_type type;
+		int number;
+		enum hwmon_item item;
+		bool alarm;
+		bool parse_ok;
+	} tests[] = {
+		{
+			.filename = "cpu0_accuracy",
+			.type = HWMON_TYPE_CPU,
+			.number = 0,
+			.item = HWMON_ITEM_ACCURACY,
+			.alarm = false,
+			.parse_ok = true,
+		},
+		{
+			.filename = "temp1_input",
+			.type = HWMON_TYPE_TEMP,
+			.number = 1,
+			.item = HWMON_ITEM_INPUT,
+			.alarm = false,
+			.parse_ok = true,
+		},
+		{
+			.filename = "fan2_vid",
+			.type = HWMON_TYPE_FAN,
+			.number = 2,
+			.item = HWMON_ITEM_VID,
+			.alarm = false,
+			.parse_ok = true,
+		},
+		{
+			.filename = "power3_crit_alarm",
+			.type = HWMON_TYPE_POWER,
+			.number = 3,
+			.item = HWMON_ITEM_CRIT,
+			.alarm = true,
+			.parse_ok = true,
+		},
+		{
+			.filename = "intrusion4_average_interval_min_alarm",
+			.type = HWMON_TYPE_INTRUSION,
+			.number = 4,
+			.item = HWMON_ITEM_AVERAGE_INTERVAL_MIN,
+			.alarm = true,
+			.parse_ok = true,
+		},
+		{
+			.filename = "badtype5_baditem",
+			.type = HWMON_TYPE_NONE,
+			.number = 5,
+			.item = HWMON_ITEM_NONE,
+			.alarm = false,
+			.parse_ok = false,
+		},
+		{
+			.filename = "humidity6_baditem",
+			.type = HWMON_TYPE_NONE,
+			.number = 6,
+			.item = HWMON_ITEM_NONE,
+			.alarm = false,
+			.parse_ok = false,
+		},
+	};
+
+	for (size_t i = 0; i < ARRAY_SIZE(tests); i++) {
+		enum hwmon_type type;
+		int number;
+		enum hwmon_item item;
+		bool alarm;
+
+		TEST_ASSERT_EQUAL("parse_hwmon_filename",
+				parse_hwmon_filename(
+					tests[i].filename,
+					&type,
+					&number,
+					&item,
+					&alarm),
+				tests[i].parse_ok
+			);
+		if (tests[i].parse_ok) {
+			TEST_ASSERT_EQUAL("parse_hwmon_filename type", type, tests[i].type);
+			TEST_ASSERT_EQUAL("parse_hwmon_filename number", number, tests[i].number);
+			TEST_ASSERT_EQUAL("parse_hwmon_filename item", item, tests[i].item);
+			TEST_ASSERT_EQUAL("parse_hwmon_filename alarm", alarm, tests[i].alarm);
+		}
+	}
+	return TEST_OK;
+}
+
+static struct test_case tests__hwmon_pmu[] = {
+	TEST_CASE("Basic parsing test", parse_hwmon_filename),
+	{	.name = NULL, }
+};
+
+struct test_suite suite__hwmon_pmu = {
+	.desc = "Hwmon PMU",
+	.test_cases = tests__hwmon_pmu,
+};
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index af284dd47e5c7..cb58b43aa063c 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -92,6 +92,7 @@ DECLARE_SUITE(perf_evsel__tp_sched_test);
 DECLARE_SUITE(syscall_openat_tp_fields);
 DECLARE_SUITE(pmu);
 DECLARE_SUITE(pmu_events);
+DECLARE_SUITE(hwmon_pmu);
 DECLARE_SUITE(tool_pmu);
 DECLARE_SUITE(attr);
 DECLARE_SUITE(dso_data);

From 53cc0b351ec99278447d6c253c37fa61f4b35da0 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 16:37:56 -0800
Subject: [PATCH 0985/1530] perf hwmon_pmu: Add a tool PMU exposing events from
 hwmon in sysfs

Add a tool PMU for hwmon events but don't enable.

The hwmon sysfs ABI is defined in
Documentation/hwmon/sysfs-interface.rst. Create a PMU that reads the
hwmon input and can be used in `perf stat` and metrics much as an
uncore PMU can.

For example, when enabled by a later patch, the following shows
reading the CPU temperature and 2 fan speeds alongside the uncore
frequency:
```
$ perf stat -e temp_cpu,fan1,hwmon_thinkpad/fan2/,tool/num_cpus_online/ -M UNCORE_FREQ -I 1000
     1.001153138              52.00 'C   temp_cpu
     1.001153138              2,588 rpm  fan1
     1.001153138              2,482 rpm  hwmon_thinkpad/fan2/
     1.001153138                  8      tool/num_cpus_online/
     1.001153138      1,077,101,397      UNC_CLOCK.SOCKET                 #     1.08 UNCORE_FREQ
     1.001153138      1,012,773,595      duration_time
...
```

The PMUs are named from /sys/class/hwmon/hwmon<num>/name and have an
alias of hwmon<num>.

Hwmon data is presented in multiple <type><number>_<item> files. The
<type><number> is used to identify the event as is the <type> followed
by the contents of the <type>_label file if it exists. The
<type><number>_input file gives the data read by perf.

When enabled by a later patch, in `perf list` the other hwmon <item>
files are used to give a richer description, for example:
```
hwmon:
  temp1
       [Temperature in unit acpitz named temp1. Unit: hwmon_acpitz]
  in0
       [Voltage in unit bat0 named in0. Unit: hwmon_bat0]
  temp_core_0 OR temp2
       [Temperature in unit coretemp named Core 0. crit=100'C,max=100'C crit_alarm=0'C. Unit:
        hwmon_coretemp]
  temp_core_1 OR temp3
       [Temperature in unit coretemp named Core 1. crit=100'C,max=100'C crit_alarm=0'C. Unit:
        hwmon_coretemp]
...
  temp_package_id_0 OR temp1
       [Temperature in unit coretemp named Package id 0. crit=100'C,max=100'C crit_alarm=0'C.
        Unit: hwmon_coretemp]
  temp1
       [Temperature in unit iwlwifi_1 named temp1. Unit: hwmon_iwlwifi_1]
  temp_composite OR temp1
       [Temperature in unit nvme named Composite. alarm=0'C,crit=86.85'C,max=75.85'C,
        min=-273.15'C. Unit: hwmon_nvme]
  temp_sensor_1 OR temp2
       [Temperature in unit nvme named Sensor 1. max=65261.8'C,min=-273.15'C. Unit: hwmon_nvme]
  temp_sensor_2 OR temp3
       [Temperature in unit nvme named Sensor 2. max=65261.8'C,min=-273.15'C. Unit: hwmon_nvme]
  fan1
       [Fan in unit thinkpad named fan1. Unit: hwmon_thinkpad]
  fan2
       [Fan in unit thinkpad named fan2. Unit: hwmon_thinkpad]
...
  temp_cpu OR temp1
       [Temperature in unit thinkpad named CPU. Unit: hwmon_thinkpad]
  temp_gpu OR temp2
       [Temperature in unit thinkpad named GPU. Unit: hwmon_thinkpad]
  curr1
       [Current in unit ucsi_source_psy_usbc000_0 named curr1. max=1.5A. Unit:
        hwmon_ucsi_source_psy_usbc000_0]
  in0
       [Voltage in unit ucsi_source_psy_usbc000_0 named in0. max=5V,min=5V. Unit:
        hwmon_ucsi_source_psy_usbc000_0]
```

As there may be multiple hwmon devices a range of PMU types are
reserved for their use and to identify the PMU as belonging to the
hwmon types.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Yoshihiro Furudera <fj5100bi@fujitsu.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Junhao He <hejunhao3@huawei.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20241109003759.473460-5-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/hwmon_pmu.c | 682 ++++++++++++++++++++++++++++++++++++
 tools/perf/util/hwmon_pmu.h |  40 +++
 tools/perf/util/pmu.h       |   2 +
 3 files changed, 724 insertions(+)

diff --git a/tools/perf/util/hwmon_pmu.c b/tools/perf/util/hwmon_pmu.c
index 301793b13337d..ac2245acdc6d9 100644
--- a/tools/perf/util/hwmon_pmu.c
+++ b/tools/perf/util/hwmon_pmu.c
@@ -1,12 +1,26 @@
 // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+#include "counts.h"
 #include "debug.h"
+#include "evsel.h"
+#include "hashmap.h"
 #include "hwmon_pmu.h"
+#include "pmu.h"
+#include <internal/xyarray.h>
+#include <internal/threadmap.h>
+#include <perf/threadmap.h>
+#include <sys/types.h>
 #include <assert.h>
+#include <ctype.h>
+#include <dirent.h>
+#include <fcntl.h>
 #include <stddef.h>
 #include <stdlib.h>
 #include <string.h>
+#include <api/fs/fs.h>
+#include <api/io.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <linux/zalloc.h>
 
 /** Strings that correspond to enum hwmon_type. */
 static const char * const hwmon_type_strs[HWMON_TYPE_MAX] = {
@@ -73,6 +87,79 @@ static const char * const hwmon_item_strs[HWMON_ITEM__MAX] = {
 };
 #define LONGEST_HWMON_ITEM_STR "average_interval_max"
 
+static const char *const hwmon_units[HWMON_TYPE_MAX] = {
+	NULL,
+	"V",   /* cpu */
+	"A",   /* curr */
+	"J",   /* energy */
+	"rpm", /* fan */
+	"%",   /* humidity */
+	"V",   /* in */
+	"",    /* intrusion */
+	"W",   /* power */
+	"Hz",  /* pwm */
+	"'C",  /* temp */
+};
+
+struct hwmon_pmu {
+	struct perf_pmu pmu;
+	struct hashmap events;
+	int hwmon_dir_fd;
+};
+
+/**
+ * union hwmon_pmu_event_key: Key for hwmon_pmu->events as such each key
+ * represents an event.
+ *
+ * Related hwmon files start <type><number> that this key represents.
+ */
+union hwmon_pmu_event_key {
+	long type_and_num;
+	struct {
+		int num :16;
+		enum hwmon_type type :8;
+	};
+};
+
+/**
+ * struct hwmon_pmu_event_value: Value in hwmon_pmu->events.
+ *
+ * Hwmon files are of the form <type><number>_<item> and may have a suffix
+ * _alarm.
+ */
+struct hwmon_pmu_event_value {
+	/** @items: which item files are present. */
+	DECLARE_BITMAP(items, HWMON_ITEM__MAX);
+	/** @alarm_items: which item files are present. */
+	DECLARE_BITMAP(alarm_items, HWMON_ITEM__MAX);
+	/** @label: contents of <type><number>_label if present. */
+	char *label;
+	/** @name: name computed from label of the form <type>_<label>. */
+	char *name;
+};
+
+bool perf_pmu__is_hwmon(const struct perf_pmu *pmu)
+{
+	return pmu && pmu->type >= PERF_PMU_TYPE_HWMON_START &&
+		pmu->type <= PERF_PMU_TYPE_HWMON_END;
+}
+
+bool evsel__is_hwmon(const struct evsel *evsel)
+{
+	return perf_pmu__is_hwmon(evsel->pmu);
+}
+
+static size_t hwmon_pmu__event_hashmap_hash(long key, void *ctx __maybe_unused)
+{
+	return ((union hwmon_pmu_event_key)key).type_and_num;
+}
+
+static bool hwmon_pmu__event_hashmap_equal(long key1, long key2, void *ctx __maybe_unused)
+{
+	return ((union hwmon_pmu_event_key)key1).type_and_num ==
+	       ((union hwmon_pmu_event_key)key2).type_and_num;
+}
+
 static int hwmon_strcmp(const void *a, const void *b)
 {
 	const char *sa = a;
@@ -143,3 +230,598 @@ bool parse_hwmon_filename(const char *filename,
 	*item = elem - &hwmon_item_strs[0];
 	return true;
 }
+
+static void fix_name(char *p)
+{
+	char *s = strchr(p, '\n');
+
+	if (s)
+		*s = '\0';
+
+	while (*p != '\0') {
+		if (strchr(" :,/\n\t", *p))
+			*p = '_';
+		else
+			*p = tolower(*p);
+		p++;
+	}
+}
+
+static int hwmon_pmu__read_events(struct hwmon_pmu *pmu)
+{
+	DIR *dir;
+	struct dirent *ent;
+	int dup_fd, err = 0;
+	struct hashmap_entry *cur, *tmp;
+	size_t bkt;
+
+	if (pmu->pmu.sysfs_aliases_loaded)
+		return 0;
+
+	/* Use a dup-ed fd as closedir will close it. */
+	dup_fd = dup(pmu->hwmon_dir_fd);
+	if (dup_fd == -1)
+		return -ENOMEM;
+
+	dir = fdopendir(dup_fd);
+	if (!dir) {
+		close(dup_fd);
+		return -ENOMEM;
+	}
+
+	while ((ent = readdir(dir)) != NULL) {
+		enum hwmon_type type;
+		int number;
+		enum hwmon_item item;
+		bool alarm;
+		union hwmon_pmu_event_key key = {};
+		struct hwmon_pmu_event_value *value;
+
+		if (ent->d_type != DT_REG)
+			continue;
+
+		if (!parse_hwmon_filename(ent->d_name, &type, &number, &item, &alarm)) {
+			pr_debug("Not a hwmon file '%s'\n", ent->d_name);
+			continue;
+		}
+		key.num = number;
+		key.type = type;
+		if (!hashmap__find(&pmu->events, key.type_and_num, &value)) {
+			value = zalloc(sizeof(*value));
+			if (!value) {
+				err = -ENOMEM;
+				goto err_out;
+			}
+			err = hashmap__add(&pmu->events, key.type_and_num, value);
+			if (err) {
+				free(value);
+				err = -ENOMEM;
+				goto err_out;
+			}
+		}
+		__set_bit(item, alarm ? value->alarm_items : value->items);
+		if (item == HWMON_ITEM_LABEL) {
+			char buf[128];
+			int fd = openat(pmu->hwmon_dir_fd, ent->d_name, O_RDONLY);
+			ssize_t read_len;
+
+			if (fd < 0)
+				continue;
+
+			read_len = read(fd, buf, sizeof(buf));
+
+			while (read_len > 0 && buf[read_len - 1] == '\n')
+				read_len--;
+
+			if (read_len > 0)
+				buf[read_len] = '\0';
+
+			if (buf[0] == '\0') {
+				pr_debug("hwmon_pmu: empty label file %s %s\n",
+					 pmu->pmu.name, ent->d_name);
+				close(fd);
+				continue;
+			}
+			value->label = strdup(buf);
+			if (!value->label) {
+				pr_debug("hwmon_pmu: memory allocation failure\n");
+				close(fd);
+				continue;
+			}
+			snprintf(buf, sizeof(buf), "%s_%s", hwmon_type_strs[type], value->label);
+			fix_name(buf);
+			value->name = strdup(buf);
+			if (!value->name)
+				pr_debug("hwmon_pmu: memory allocation failure\n");
+			close(fd);
+		}
+	}
+	hashmap__for_each_entry_safe((&pmu->events), cur, tmp, bkt) {
+		union hwmon_pmu_event_key key = {
+			.type_and_num = cur->key,
+		};
+		struct hwmon_pmu_event_value *value = cur->pvalue;
+
+		if (!test_bit(HWMON_ITEM_INPUT, value->items)) {
+			pr_debug("hwmon_pmu: removing event '%s%d' that has no input file\n",
+				hwmon_type_strs[key.type], key.num);
+			hashmap__delete(&pmu->events, key.type_and_num, &key, &value);
+			zfree(&value->label);
+			zfree(&value->name);
+			free(value);
+		}
+	}
+	pmu->pmu.sysfs_aliases_loaded = true;
+
+err_out:
+	closedir(dir);
+	return err;
+}
+
+struct perf_pmu *hwmon_pmu__new(struct list_head *pmus, int hwmon_dir, const char *sysfs_name, const char *name)
+{
+	char buf[32];
+	struct hwmon_pmu *hwm;
+
+	hwm = zalloc(sizeof(*hwm));
+	if (!hwm)
+		return NULL;
+
+	hwm->hwmon_dir_fd = hwmon_dir;
+	hwm->pmu.type = PERF_PMU_TYPE_HWMON_START + strtoul(sysfs_name + 5, NULL, 10);
+	if (hwm->pmu.type > PERF_PMU_TYPE_HWMON_END) {
+		pr_err("Unable to encode hwmon type from %s in valid PMU type\n", sysfs_name);
+		goto err_out;
+	}
+	snprintf(buf, sizeof(buf), "hwmon_%s", name);
+	fix_name(buf + 6);
+	hwm->pmu.name = strdup(buf);
+	if (!hwm->pmu.name)
+		goto err_out;
+	hwm->pmu.alias_name = strdup(sysfs_name);
+	if (!hwm->pmu.alias_name)
+		goto err_out;
+	hwm->pmu.cpus = perf_cpu_map__new("0");
+	if (!hwm->pmu.cpus)
+		goto err_out;
+	INIT_LIST_HEAD(&hwm->pmu.format);
+	INIT_LIST_HEAD(&hwm->pmu.aliases);
+	INIT_LIST_HEAD(&hwm->pmu.caps);
+	hashmap__init(&hwm->events, hwmon_pmu__event_hashmap_hash,
+		      hwmon_pmu__event_hashmap_equal, /*ctx=*/NULL);
+
+	list_add_tail(&hwm->pmu.list, pmus);
+	return &hwm->pmu;
+err_out:
+	free((char *)hwm->pmu.name);
+	free(hwm->pmu.alias_name);
+	free(hwm);
+	close(hwmon_dir);
+	return NULL;
+}
+
+void hwmon_pmu__exit(struct perf_pmu *pmu)
+{
+	struct hwmon_pmu *hwm = container_of(pmu, struct hwmon_pmu, pmu);
+	struct hashmap_entry *cur, *tmp;
+	size_t bkt;
+
+	hashmap__for_each_entry_safe((&hwm->events), cur, tmp, bkt) {
+		struct hwmon_pmu_event_value *value = cur->pvalue;
+
+		zfree(&value->label);
+		zfree(&value->name);
+		free(value);
+	}
+	hashmap__clear(&hwm->events);
+	close(hwm->hwmon_dir_fd);
+}
+
+static size_t hwmon_pmu__describe_items(struct hwmon_pmu *hwm, char *out_buf, size_t out_buf_len,
+					union hwmon_pmu_event_key key,
+					const unsigned long *items, bool is_alarm)
+{
+	size_t bit;
+	char buf[64];
+	size_t len = 0;
+
+	for_each_set_bit(bit, items, HWMON_ITEM__MAX) {
+		int fd;
+
+		if (bit == HWMON_ITEM_LABEL || bit == HWMON_ITEM_INPUT)
+			continue;
+
+		snprintf(buf, sizeof(buf), "%s%d_%s%s",
+			hwmon_type_strs[key.type],
+			key.num,
+			hwmon_item_strs[bit],
+			is_alarm ? "_alarm" : "");
+		fd = openat(hwm->hwmon_dir_fd, buf, O_RDONLY);
+		if (fd > 0) {
+			ssize_t read_len = read(fd, buf, sizeof(buf));
+
+			while (read_len > 0 && buf[read_len - 1] == '\n')
+				read_len--;
+
+			if (read_len > 0) {
+				long long val;
+
+				buf[read_len] = '\0';
+				val = strtoll(buf, /*endptr=*/NULL, 10);
+				len += snprintf(out_buf + len, out_buf_len - len, "%s%s%s=%g%s",
+						len == 0 ? " " : ", ",
+						hwmon_item_strs[bit],
+						is_alarm ? "_alarm" : "",
+						(double)val / 1000.0,
+						hwmon_units[key.type]);
+			}
+			close(fd);
+		}
+	}
+	return len;
+}
+
+int hwmon_pmu__for_each_event(struct perf_pmu *pmu, void *state, pmu_event_callback cb)
+{
+	struct hwmon_pmu *hwm = container_of(pmu, struct hwmon_pmu, pmu);
+	struct hashmap_entry *cur;
+	size_t bkt;
+
+	if (hwmon_pmu__read_events(hwm))
+		return false;
+
+	hashmap__for_each_entry((&hwm->events), cur, bkt) {
+		static const char *const hwmon_scale_units[HWMON_TYPE_MAX] = {
+			NULL,
+			"0.001V", /* cpu */
+			"0.001A", /* curr */
+			"0.001J", /* energy */
+			"1rpm",   /* fan */
+			"0.001%", /* humidity */
+			"0.001V", /* in */
+			NULL,     /* intrusion */
+			"0.001W", /* power */
+			"1Hz",    /* pwm */
+			"0.001'C", /* temp */
+		};
+		static const char *const hwmon_desc[HWMON_TYPE_MAX] = {
+			NULL,
+			"CPU core reference voltage",   /* cpu */
+			"Current",                      /* curr */
+			"Cumulative energy use",        /* energy */
+			"Fan",                          /* fan */
+			"Humidity",                     /* humidity */
+			"Voltage",                      /* in */
+			"Chassis intrusion detection",  /* intrusion */
+			"Power use",                    /* power */
+			"Pulse width modulation fan control", /* pwm */
+			"Temperature",                  /* temp */
+		};
+		char alias_buf[64];
+		char desc_buf[256];
+		char encoding_buf[128];
+		union hwmon_pmu_event_key key = {
+			.type_and_num = cur->key,
+		};
+		struct hwmon_pmu_event_value *value = cur->pvalue;
+		struct pmu_event_info info = {
+			.pmu = pmu,
+			.name = value->name,
+			.alias = alias_buf,
+			.scale_unit = hwmon_scale_units[key.type],
+			.desc = desc_buf,
+			.long_desc = NULL,
+			.encoding_desc = encoding_buf,
+			.topic = "hwmon",
+			.pmu_name = pmu->name,
+			.event_type_desc = "Hwmon event",
+		};
+		int ret;
+		size_t len;
+
+		len = snprintf(alias_buf, sizeof(alias_buf), "%s%d",
+			       hwmon_type_strs[key.type], key.num);
+		if (!info.name) {
+			info.name = info.alias;
+			info.alias = NULL;
+		}
+
+		len = snprintf(desc_buf, sizeof(desc_buf), "%s in unit %s named %s.",
+			hwmon_desc[key.type],
+			pmu->name + 6,
+			value->label ?: info.name);
+
+		len += hwmon_pmu__describe_items(hwm, desc_buf + len, sizeof(desc_buf) - len,
+						key, value->items, /*is_alarm=*/false);
+
+		len += hwmon_pmu__describe_items(hwm, desc_buf + len, sizeof(desc_buf) - len,
+						key, value->alarm_items, /*is_alarm=*/true);
+
+		snprintf(encoding_buf, sizeof(encoding_buf), "%s/config=0x%lx/",
+			 pmu->name, cur->key);
+
+		ret = cb(state, &info);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+size_t hwmon_pmu__num_events(struct perf_pmu *pmu)
+{
+	struct hwmon_pmu *hwm = container_of(pmu, struct hwmon_pmu, pmu);
+
+	hwmon_pmu__read_events(hwm);
+	return hashmap__size(&hwm->events);
+}
+
+bool hwmon_pmu__have_event(struct perf_pmu *pmu, const char *name)
+{
+	struct hwmon_pmu *hwm = container_of(pmu, struct hwmon_pmu, pmu);
+	enum hwmon_type type;
+	int number;
+	union hwmon_pmu_event_key key = {};
+	struct hashmap_entry *cur;
+	size_t bkt;
+
+	if (!parse_hwmon_filename(name, &type, &number, /*item=*/NULL, /*is_alarm=*/NULL))
+		return false;
+
+	if (hwmon_pmu__read_events(hwm))
+		return false;
+
+	key.type = type;
+	key.num = number;
+	if (hashmap_find(&hwm->events, key.type_and_num, /*value=*/NULL))
+		return true;
+	if (key.num != -1)
+		return false;
+	/* Item is of form <type>_ which means we should match <type>_<label>. */
+	hashmap__for_each_entry((&hwm->events), cur, bkt) {
+		struct hwmon_pmu_event_value *value = cur->pvalue;
+
+		key.type_and_num = cur->key;
+		if (key.type == type && value->name && !strcasecmp(name, value->name))
+			return true;
+	}
+	return false;
+}
+
+static int hwmon_pmu__config_term(const struct hwmon_pmu *hwm,
+				  struct perf_event_attr *attr,
+				  struct parse_events_term *term,
+				  struct parse_events_error *err)
+{
+	if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER) {
+		enum hwmon_type type;
+		int number;
+
+		if (parse_hwmon_filename(term->config, &type, &number,
+					 /*item=*/NULL, /*is_alarm=*/NULL)) {
+			if (number == -1) {
+				/*
+				 * Item is of form <type>_ which means we should
+				 * match <type>_<label>.
+				 */
+				struct hashmap_entry *cur;
+				size_t bkt;
+
+				attr->config = 0;
+				hashmap__for_each_entry((&hwm->events), cur, bkt) {
+					union hwmon_pmu_event_key key = {
+						.type_and_num = cur->key,
+					};
+					struct hwmon_pmu_event_value *value = cur->pvalue;
+
+					if (key.type == type && value->name &&
+					    !strcasecmp(term->config, value->name)) {
+						attr->config = key.type_and_num;
+						break;
+					}
+				}
+				if (attr->config == 0)
+					return -EINVAL;
+			} else {
+				union hwmon_pmu_event_key key = {
+					.type = type,
+					.num = number,
+				};
+
+				attr->config = key.type_and_num;
+			}
+			return 0;
+		}
+	}
+	if (err) {
+		char *err_str;
+
+		parse_events_error__handle(err, term->err_val,
+					asprintf(&err_str,
+						"unexpected hwmon event term (%s) %s",
+						parse_events__term_type_str(term->type_term),
+						term->config) < 0
+					? strdup("unexpected hwmon event term")
+					: err_str,
+					NULL);
+	}
+	return -EINVAL;
+}
+
+int hwmon_pmu__config_terms(const struct perf_pmu *pmu,
+			    struct perf_event_attr *attr,
+			    struct parse_events_terms *terms,
+			    struct parse_events_error *err)
+{
+	const struct hwmon_pmu *hwm = container_of(pmu, struct hwmon_pmu, pmu);
+	struct parse_events_term *term;
+
+	assert(pmu->sysfs_aliases_loaded);
+	list_for_each_entry(term, &terms->terms, list) {
+		if (hwmon_pmu__config_term(hwm, attr, term, err))
+			return -EINVAL;
+	}
+
+	return 0;
+
+}
+
+int hwmon_pmu__check_alias(struct parse_events_terms *terms, struct perf_pmu_info *info,
+			   struct parse_events_error *err)
+{
+	struct parse_events_term *term =
+		list_first_entry(&terms->terms, struct parse_events_term, list);
+
+	if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER) {
+		enum hwmon_type type;
+		int number;
+
+		if (parse_hwmon_filename(term->config, &type, &number,
+					 /*item=*/NULL, /*is_alarm=*/NULL)) {
+			info->unit = hwmon_units[type];
+			if (type == HWMON_TYPE_FAN || type == HWMON_TYPE_PWM ||
+			    type == HWMON_TYPE_INTRUSION)
+				info->scale = 1;
+			else
+				info->scale = 0.001;
+		}
+		return 0;
+	}
+	if (err) {
+		char *err_str;
+
+		parse_events_error__handle(err, term->err_val,
+					asprintf(&err_str,
+						"unexpected hwmon event term (%s) %s",
+						parse_events__term_type_str(term->type_term),
+						term->config) < 0
+					? strdup("unexpected hwmon event term")
+					: err_str,
+					NULL);
+	}
+	return -EINVAL;
+}
+
+int perf_pmus__read_hwmon_pmus(struct list_head *pmus)
+{
+	char *line = NULL;
+	DIR *class_hwmon_dir;
+	struct dirent *class_hwmon_ent;
+	char buf[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return 0;
+
+	scnprintf(buf, sizeof(buf), "%s/class/hwmon/", sysfs);
+	class_hwmon_dir = opendir(buf);
+	if (!class_hwmon_dir)
+		return 0;
+
+	while ((class_hwmon_ent = readdir(class_hwmon_dir)) != NULL) {
+		size_t line_len;
+		int hwmon_dir, name_fd;
+		struct io io;
+
+		if (class_hwmon_ent->d_type != DT_LNK)
+			continue;
+
+		scnprintf(buf, sizeof(buf), "%s/class/hwmon/%s", sysfs, class_hwmon_ent->d_name);
+		hwmon_dir = open(buf, O_DIRECTORY);
+		if (hwmon_dir == -1) {
+			pr_debug("hwmon_pmu: not a directory: '%s/class/hwmon/%s'\n",
+				 sysfs, class_hwmon_ent->d_name);
+			continue;
+		}
+		name_fd = openat(hwmon_dir, "name", O_RDONLY);
+		if (name_fd == -1) {
+			pr_debug("hwmon_pmu: failure to open '%s/class/hwmon/%s/name'\n",
+				  sysfs, class_hwmon_ent->d_name);
+			close(hwmon_dir);
+			continue;
+		}
+		io__init(&io, name_fd, buf, sizeof(buf));
+		io__getline(&io, &line, &line_len);
+		if (line_len > 0 && line[line_len - 1] == '\n')
+			line[line_len - 1] = '\0';
+		hwmon_pmu__new(pmus, hwmon_dir, class_hwmon_ent->d_name, line);
+		close(name_fd);
+	}
+	free(line);
+	closedir(class_hwmon_dir);
+	return 0;
+}
+
+#define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y))
+
+int evsel__hwmon_pmu_open(struct evsel *evsel,
+			  struct perf_thread_map *threads,
+			  int start_cpu_map_idx, int end_cpu_map_idx)
+{
+	struct hwmon_pmu *hwm = container_of(evsel->pmu, struct hwmon_pmu, pmu);
+	union hwmon_pmu_event_key key = {
+		.type_and_num = evsel->core.attr.config,
+	};
+	int idx = 0, thread = 0, nthreads, err = 0;
+
+	nthreads = perf_thread_map__nr(threads);
+	for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) {
+		for (thread = 0; thread < nthreads; thread++) {
+			char buf[64];
+			int fd;
+
+			snprintf(buf, sizeof(buf), "%s%d_input",
+				 hwmon_type_strs[key.type], key.num);
+
+			fd = openat(hwm->hwmon_dir_fd, buf, O_RDONLY);
+			FD(evsel, idx, thread) = fd;
+			if (fd < 0) {
+				err = -errno;
+				goto out_close;
+			}
+		}
+	}
+	return 0;
+out_close:
+	if (err)
+		threads->err_thread = thread;
+
+	do {
+		while (--thread >= 0) {
+			if (FD(evsel, idx, thread) >= 0)
+				close(FD(evsel, idx, thread));
+			FD(evsel, idx, thread) = -1;
+		}
+		thread = nthreads;
+	} while (--idx >= 0);
+	return err;
+}
+
+int evsel__hwmon_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread)
+{
+	char buf[32];
+	int fd;
+	ssize_t len;
+	struct perf_counts_values *count, *old_count = NULL;
+
+	if (evsel->prev_raw_counts)
+		old_count = perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
+
+	count = perf_counts(evsel->counts, cpu_map_idx, thread);
+	fd = FD(evsel, cpu_map_idx, thread);
+	len = pread(fd, buf, sizeof(buf), 0);
+	if (len <= 0) {
+		count->lost++;
+		return -EINVAL;
+	}
+	buf[len] = '\0';
+	if (old_count) {
+		count->val = old_count->val + strtoll(buf, NULL, 10);
+		count->run = old_count->run + 1;
+		count->ena = old_count->ena + 1;
+	} else {
+		count->val = strtoll(buf, NULL, 10);
+		count->run++;
+		count->ena++;
+	}
+	return 0;
+}
diff --git a/tools/perf/util/hwmon_pmu.h b/tools/perf/util/hwmon_pmu.h
index df0ab5ff75349..882566846df46 100644
--- a/tools/perf/util/hwmon_pmu.h
+++ b/tools/perf/util/hwmon_pmu.h
@@ -2,8 +2,12 @@
 #ifndef __HWMON_PMU_H
 #define __HWMON_PMU_H
 
+#include "pmu.h"
 #include <stdbool.h>
 
+struct list_head;
+struct perf_thread_map;
+
 /**
  * enum hwmon_type:
  *
@@ -87,6 +91,9 @@ enum hwmon_item {
 	HWMON_ITEM__MAX,
 };
 
+bool perf_pmu__is_hwmon(const struct perf_pmu *pmu);
+bool evsel__is_hwmon(const struct evsel *evsel);
+
 /**
  * parse_hwmon_filename() - Parse filename into constituent parts.
  *
@@ -108,4 +115,37 @@ bool parse_hwmon_filename(const char *filename,
 			  enum hwmon_item *item,
 			  bool *alarm);
 
+/**
+ * hwmon_pmu__new() - Allocate and construct a hwmon PMU.
+ *
+ * @pmus: The list of PMUs to be added to.
+ * @hwmon_dir: An O_DIRECTORY file descriptor for a hwmon directory.
+ * @sysfs_name: Name of the hwmon sysfs directory like hwmon0.
+ * @name: The contents of the "name" file in the hwmon directory.
+ *
+ * Exposed for testing. Regular construction should happen via
+ * perf_pmus__read_hwmon_pmus.
+ */
+struct perf_pmu *hwmon_pmu__new(struct list_head *pmus, int hwmon_dir,
+				const char *sysfs_name, const char *name);
+void hwmon_pmu__exit(struct perf_pmu *pmu);
+
+int hwmon_pmu__for_each_event(struct perf_pmu *pmu, void *state, pmu_event_callback cb);
+size_t hwmon_pmu__num_events(struct perf_pmu *pmu);
+bool hwmon_pmu__have_event(struct perf_pmu *pmu, const char *name);
+int hwmon_pmu__config_terms(const struct perf_pmu *pmu,
+			    struct perf_event_attr *attr,
+			    struct parse_events_terms *terms,
+			    struct parse_events_error *err);
+int hwmon_pmu__check_alias(struct parse_events_terms *terms, struct perf_pmu_info *info,
+			   struct parse_events_error *err);
+
+int perf_pmus__read_hwmon_pmus(struct list_head *pmus);
+
+
+int evsel__hwmon_pmu_open(struct evsel *evsel,
+			 struct perf_thread_map *threads,
+			 int start_cpu_map_idx, int end_cpu_map_idx);
+int evsel__hwmon_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread);
+
 #endif /* __HWMON_PMU_H */
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index b86b3c3685a23..d511bf7cc9d06 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -37,6 +37,8 @@ struct perf_pmu_caps {
 };
 
 enum {
+	PERF_PMU_TYPE_HWMON_START = 0xFFFF0000,
+	PERF_PMU_TYPE_HWMON_END   = 0xFFFFFFFD,
 	PERF_PMU_TYPE_TOOL = 0xFFFFFFFE,
 	PERF_PMU_TYPE_FAKE = 0xFFFFFFFF,
 };

From 654986ed5d53248ee2037cfebc4052441e2d1126 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 16:37:57 -0800
Subject: [PATCH 0986/1530] perf pmu: Add calls enabling the hwmon_pmu

Add the base PMU calls necessary for hwmon_pmu(s) to be
created/deleted and events found, listed, opened and read.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Yoshihiro Furudera <fj5100bi@fujitsu.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Junhao He <hejunhao3@huawei.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20241109003759.473460-6-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/evsel.c |  9 +++++++++
 tools/perf/util/pmu.c   | 20 ++++++++++++++++++++
 tools/perf/util/pmus.c  |  2 ++
 3 files changed, 31 insertions(+)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ef45a3f49056c..f745723d486ba 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -56,6 +56,7 @@
 #include "off_cpu.h"
 #include "pmu.h"
 #include "pmus.h"
+#include "hwmon_pmu.h"
 #include "tool_pmu.h"
 #include "rlimit.h"
 #include "../perf-sys.h"
@@ -1799,6 +1800,9 @@ int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread)
 	if (evsel__is_tool(evsel))
 		return evsel__tool_pmu_read(evsel, cpu_map_idx, thread);
 
+	if (evsel__is_hwmon(evsel))
+		return evsel__hwmon_pmu_read(evsel, cpu_map_idx, thread);
+
 	if (evsel__is_retire_lat(evsel))
 		return evsel__read_retire_lat(evsel, cpu_map_idx, thread);
 
@@ -2465,6 +2469,11 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 					    start_cpu_map_idx,
 					    end_cpu_map_idx);
 	}
+	if (evsel__is_hwmon(evsel)) {
+		return evsel__hwmon_pmu_open(evsel, threads,
+					     start_cpu_map_idx,
+					     end_cpu_map_idx);
+	}
 
 	for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) {
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 0789758598c07..a02df2c80f421 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -18,6 +18,7 @@
 #include "debug.h"
 #include "evsel.h"
 #include "pmu.h"
+#include "hwmon_pmu.h"
 #include "pmus.h"
 #include "tool_pmu.h"
 #include <util/pmu-bison.h>
@@ -1529,6 +1530,9 @@ int perf_pmu__config_terms(const struct perf_pmu *pmu,
 {
 	struct parse_events_term *term;
 
+	if (perf_pmu__is_hwmon(pmu))
+		return hwmon_pmu__config_terms(pmu, attr, terms, err);
+
 	list_for_each_entry(term, &terms->terms, list) {
 		if (pmu_config_term(pmu, attr, term, terms, zero, apply_hardcoded, err))
 			return -EINVAL;
@@ -1661,6 +1665,11 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_
 	info->scale    = 0.0;
 	info->snapshot = false;
 
+	if (perf_pmu__is_hwmon(pmu)) {
+		ret = hwmon_pmu__check_alias(head_terms, info, err);
+		goto out;
+	}
+
 	/* Fake PMU doesn't rewrite terms. */
 	if (perf_pmu__is_fake(pmu))
 		goto out;
@@ -1834,6 +1843,8 @@ bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name)
 		return false;
 	if (perf_pmu__is_tool(pmu) && tool_pmu__skip_event(name))
 		return false;
+	if (perf_pmu__is_hwmon(pmu))
+		return hwmon_pmu__have_event(pmu, name);
 	if (perf_pmu__find_alias(pmu, name, /*load=*/ true) != NULL)
 		return true;
 	if (pmu->cpu_aliases_added || !pmu->events_table)
@@ -1845,6 +1856,9 @@ size_t perf_pmu__num_events(struct perf_pmu *pmu)
 {
 	size_t nr;
 
+	if (perf_pmu__is_hwmon(pmu))
+		return hwmon_pmu__num_events(pmu);
+
 	pmu_aliases_parse(pmu);
 	nr = pmu->sysfs_aliases + pmu->sys_json_aliases;
 
@@ -1908,6 +1922,9 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 	int ret = 0;
 	struct strbuf sb;
 
+	if (perf_pmu__is_hwmon(pmu))
+		return hwmon_pmu__for_each_event(pmu, state, cb);
+
 	strbuf_init(&sb, /*hint=*/ 0);
 	pmu_aliases_parse(pmu);
 	pmu_add_cpu_aliases(pmu);
@@ -2303,6 +2320,9 @@ int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename,
 
 void perf_pmu__delete(struct perf_pmu *pmu)
 {
+	if (perf_pmu__is_hwmon(pmu))
+		hwmon_pmu__exit(pmu);
+
 	perf_pmu__del_formats(&pmu->format);
 	perf_pmu__del_aliases(pmu);
 	perf_pmu__del_caps(pmu);
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index 107de86c26373..5c3e88adb9e60 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -15,6 +15,7 @@
 #include "evsel.h"
 #include "pmus.h"
 #include "pmu.h"
+#include "hwmon_pmu.h"
 #include "tool_pmu.h"
 #include "print-events.h"
 #include "strbuf.h"
@@ -234,6 +235,7 @@ static void pmu_read_sysfs(bool core_only)
 	if (!core_only) {
 		tool_pmu = perf_pmus__tool_pmu();
 		list_add_tail(&tool_pmu->list, &other_pmus);
+		perf_pmus__read_hwmon_pmus(&other_pmus);
 	}
 	list_sort(NULL, &other_pmus, pmus_cmp);
 	if (!list_empty(&core_pmus)) {

From 531ee0fd4836994fc99f22cc79ef94554f2ae54e Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 16:37:58 -0800
Subject: [PATCH 0987/1530] perf test: Add hwmon "PMU" test

Based on a mix of the sysfs PMU test (for creating the reference
files) and the tool PMU test, test that parsing given hwmon events
with there aliases creates the expected config values.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Yoshihiro Furudera <fj5100bi@fujitsu.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Junhao He <hejunhao3@huawei.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20241109003759.473460-7-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/hwmon_pmu.c | 230 +++++++++++++++++++++++++++++++++++
 tools/perf/util/pmus.c       |   7 ++
 tools/perf/util/pmus.h       |   3 +
 3 files changed, 240 insertions(+)

diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c
index 111fc5c5618a1..5c4114354c65e 100644
--- a/tools/perf/tests/hwmon_pmu.c
+++ b/tools/perf/tests/hwmon_pmu.c
@@ -1,11 +1,239 @@
 // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 #include "debug.h"
+#include "evlist.h"
 #include "hwmon_pmu.h"
+#include "parse-events.h"
 #include "tests.h"
+#include <fcntl.h>
+#include <sys/stat.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 
+static const struct test_event {
+	const char *name;
+	const char *alias;
+	long config;
+} test_events[] = {
+	{
+		"temp_test_hwmon_event1",
+		"temp1",
+		0xA0001,
+	},
+	{
+		"temp_test_hwmon_event2",
+		"temp2",
+		0xA0002,
+	},
+};
+
+/* Cleanup test PMU directory. */
+static int test_pmu_put(const char *dir, struct perf_pmu *hwm)
+{
+	char buf[PATH_MAX + 20];
+	int ret;
+
+	if (scnprintf(buf, sizeof(buf), "rm -fr %s", dir) < 0) {
+		pr_err("Failure to set up buffer for \"%s\"\n", dir);
+		return -EINVAL;
+	}
+	ret = system(buf);
+	if (ret)
+		pr_err("Failure to \"%s\"\n", buf);
+
+	perf_pmu__delete(hwm);
+	return ret;
+}
+
+/*
+ * Prepare test PMU directory data, normally exported by kernel at
+ * /sys/class/hwmon/hwmon<number>/. Give as input a buffer to hold the file
+ * path, the result is PMU loaded using that directory.
+ */
+static struct perf_pmu *test_pmu_get(char *dir, size_t sz)
+{
+	const char *test_hwmon_name_nl = "A test hwmon PMU\n";
+	const char *test_hwmon_name = "A test hwmon PMU";
+	/* Simulated hwmon items. */
+	const struct test_item {
+		const char *name;
+		const char *value;
+	} test_items[] = {
+		{ "temp1_label", "test hwmon event1\n", },
+		{ "temp1_input", "40000\n", },
+		{ "temp2_label", "test hwmon event2\n", },
+		{ "temp2_input", "50000\n", },
+	};
+	int dirfd, file;
+	struct perf_pmu *hwm = NULL;
+	ssize_t len;
+
+	/* Create equivalent of sysfs mount point. */
+	scnprintf(dir, sz, "/tmp/perf-hwmon-pmu-test-XXXXXX");
+	if (!mkdtemp(dir)) {
+		pr_err("mkdtemp failed\n");
+		dir[0] = '\0';
+		return NULL;
+	}
+	dirfd = open(dir, O_DIRECTORY);
+	if (dirfd < 0) {
+		pr_err("Failed to open test directory \"%s\"\n", dir);
+		goto err_out;
+	}
+
+	/* Create the test hwmon directory and give it a name. */
+	if (mkdirat(dirfd, "hwmon1234", 0755) < 0) {
+		pr_err("Failed to mkdir hwmon directory\n");
+		goto err_out;
+	}
+	file = openat(dirfd, "hwmon1234/name", O_WRONLY | O_CREAT, 0600);
+	if (!file) {
+		pr_err("Failed to open for writing file \"name\"\n");
+		goto err_out;
+	}
+	len = strlen(test_hwmon_name_nl);
+	if (write(file, test_hwmon_name_nl, len) < len) {
+		close(file);
+		pr_err("Failed to write to 'name' file\n");
+		goto err_out;
+	}
+	close(file);
+
+	/* Create test hwmon files. */
+	for (size_t i = 0; i < ARRAY_SIZE(test_items); i++) {
+		const struct test_item *item = &test_items[i];
+
+		file = openat(dirfd, item->name, O_WRONLY | O_CREAT, 0600);
+		if (!file) {
+			pr_err("Failed to open for writing file \"%s\"\n", item->name);
+			goto err_out;
+		}
+
+		if (write(file, item->value, strlen(item->value)) < 0) {
+			pr_err("Failed to write to file \"%s\"\n", item->name);
+			close(file);
+			goto err_out;
+		}
+		close(file);
+	}
+
+	/* Make the PMU reading the files created above. */
+	hwm = perf_pmus__add_test_hwmon_pmu(dirfd, "hwmon1234", test_hwmon_name);
+	if (!hwm)
+		pr_err("Test hwmon creation failed\n");
+
+err_out:
+	if (!hwm) {
+		test_pmu_put(dir, hwm);
+		if (dirfd >= 0)
+			close(dirfd);
+	}
+	return hwm;
+}
+
+static int do_test(size_t i, bool with_pmu, bool with_alias)
+{
+	const char *test_event = with_alias ? test_events[i].alias : test_events[i].name;
+	struct evlist *evlist = evlist__new();
+	struct evsel *evsel;
+	struct parse_events_error err;
+	int ret;
+	char str[128];
+	bool found = false;
+
+	if (!evlist) {
+		pr_err("evlist allocation failed\n");
+		return TEST_FAIL;
+	}
+
+	if (with_pmu)
+		snprintf(str, sizeof(str), "/%s/", test_event);
+	else
+		strlcpy(str, test_event, sizeof(str));
+
+	pr_debug("Testing '%s'\n", str);
+	parse_events_error__init(&err);
+	ret = parse_events(evlist, str, &err);
+	if (ret) {
+		evlist__delete(evlist);
+
+		pr_debug("FAILED %s:%d failed to parse event '%s', err %d\n",
+			 __FILE__, __LINE__, str, ret);
+		parse_events_error__print(&err, str);
+		ret = TEST_FAIL;
+		goto out;
+	}
+
+	ret = TEST_OK;
+	if (with_pmu ? (evlist->core.nr_entries != 1) : (evlist->core.nr_entries < 1)) {
+		pr_debug("FAILED %s:%d Unexpected number of events for '%s' of %d\n",
+			 __FILE__, __LINE__, str, evlist->core.nr_entries);
+		ret = TEST_FAIL;
+		goto out;
+	}
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (!perf_pmu__is_hwmon(evsel->pmu))
+			continue;
+
+		if (evsel->core.attr.config != (u64)test_events[i].config) {
+			pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n",
+				__FILE__, __LINE__, str,
+				evsel->core.attr.config,
+				test_events[i].config);
+			ret = TEST_FAIL;
+			goto out;
+		}
+		found = true;
+	}
+
+	if (!found) {
+		pr_debug("FAILED %s:%d Didn't find hwmon event '%s' in parsed evsels\n",
+			 __FILE__, __LINE__, str);
+		ret = TEST_FAIL;
+	}
+
+out:
+	evlist__delete(evlist);
+	return ret;
+}
+
+static int test__hwmon_pmu(bool with_pmu)
+{
+	char dir[PATH_MAX];
+	struct perf_pmu *pmu = test_pmu_get(dir, sizeof(dir));
+	int ret = TEST_OK;
+
+	if (!pmu)
+		return TEST_FAIL;
+
+	for (size_t i = 0; i < ARRAY_SIZE(test_events); i++) {
+		ret = do_test(i, with_pmu, /*with_alias=*/false);
+
+		if (ret != TEST_OK)
+			break;
+
+		ret = do_test(i, with_pmu, /*with_alias=*/true);
+
+		if (ret != TEST_OK)
+			break;
+	}
+	test_pmu_put(dir, pmu);
+	return ret;
+}
+
+static int test__hwmon_pmu_without_pmu(struct test_suite *test __maybe_unused,
+				      int subtest __maybe_unused)
+{
+	return test__hwmon_pmu(/*with_pmu=*/false);
+}
+
+static int test__hwmon_pmu_with_pmu(struct test_suite *test __maybe_unused,
+				   int subtest __maybe_unused)
+{
+	return test__hwmon_pmu(/*with_pmu=*/false);
+}
+
 static int test__parse_hwmon_filename(struct test_suite *test __maybe_unused,
 				      int subtest __maybe_unused)
 {
@@ -102,6 +330,8 @@ static int test__parse_hwmon_filename(struct test_suite *test __maybe_unused,
 
 static struct test_case tests__hwmon_pmu[] = {
 	TEST_CASE("Basic parsing test", parse_hwmon_filename),
+	TEST_CASE("Parsing without PMU name", hwmon_pmu_without_pmu),
+	TEST_CASE("Parsing with PMU name", hwmon_pmu_with_pmu),
 	{	.name = NULL, }
 };
 
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index 5c3e88adb9e60..451c6e00ad704 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -733,6 +733,13 @@ struct perf_pmu *perf_pmus__add_test_pmu(int test_sysfs_dirfd, const char *name)
 	return perf_pmu__lookup(&other_pmus, test_sysfs_dirfd, name, /*eager_load=*/true);
 }
 
+struct perf_pmu *perf_pmus__add_test_hwmon_pmu(int hwmon_dir,
+					       const char *sysfs_name,
+					       const char *name)
+{
+	return hwmon_pmu__new(&other_pmus, hwmon_dir, sysfs_name, name);
+}
+
 struct perf_pmu *perf_pmus__fake_pmu(void)
 {
 	static struct perf_pmu fake = {
diff --git a/tools/perf/util/pmus.h b/tools/perf/util/pmus.h
index e1742b56eec77..a0cb0eb2ff971 100644
--- a/tools/perf/util/pmus.h
+++ b/tools/perf/util/pmus.h
@@ -30,6 +30,9 @@ bool perf_pmus__supports_extended_type(void);
 char *perf_pmus__default_pmu_name(void);
 
 struct perf_pmu *perf_pmus__add_test_pmu(int test_sysfs_dirfd, const char *name);
+struct perf_pmu *perf_pmus__add_test_hwmon_pmu(int hwmon_dir,
+					       const char *sysfs_name,
+					       const char *name);
 struct perf_pmu *perf_pmus__fake_pmu(void);
 
 #endif /* __PMUS_H */

From 6d5d90a6abb98ecd964cd213db7e75a6fa5ff518 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 16:37:59 -0800
Subject: [PATCH 0988/1530] perf docs: Document tool and hwmon events

Add a few paragraphs on tool and hwmon events.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Yoshihiro Furudera <fj5100bi@fujitsu.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ze Gao <zegao2021@gmail.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Junhao He <hejunhao3@huawei.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20241109003759.473460-8-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Documentation/perf-list.txt | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 14621f39b375b..d0c65fad419a0 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -243,6 +243,21 @@ For accessing trace point events perf needs to have read access to
 /sys/kernel/tracing, even when perf_event_paranoid is in a relaxed
 setting.
 
+TOOL/HWMON EVENTS
+-----------------
+
+Some events don't have an associated PMU instead reading values
+available to software without perf_event_open. As these events don't
+support sampling they can only really be read by tools like perf stat.
+
+Tool events provide times and certain system parameters. Examples
+include duration_time, user_time, system_time and num_cpus_online.
+
+Hwmon events provide easy access to hwmon sysfs data typically in
+/sys/class/hwmon. This information includes temperatures, fan speeds
+and energy usage.
+
+
 TRACING
 -------
 

From 2bf7692eadc5e569d334c66d4a816301822c536e Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:45:46 -0800
Subject: [PATCH 0989/1530] perf bpf-prologue: Remove unused file

Commit 4a73fca22692 ("perf bpf-prologue: Remove unused file") missed
cleaning up the header file. The code was unnecessary as Commit
3d6dfae88917 ("perf parse-events: Remove BPF event support") removed
building bpf-prologue.c.

Fixes: 4a73fca22692 ("perf bpf-prologue: Remove unused file")
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-2-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/bpf-prologue.h | 37 ----------------------------------
 1 file changed, 37 deletions(-)
 delete mode 100644 tools/perf/util/bpf-prologue.h

diff --git a/tools/perf/util/bpf-prologue.h b/tools/perf/util/bpf-prologue.h
deleted file mode 100644
index 66dcf751ef654..0000000000000
--- a/tools/perf/util/bpf-prologue.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2015, He Kuang <hekuang@huawei.com>
- * Copyright (C) 2015, Huawei Inc.
- */
-#ifndef __BPF_PROLOGUE_H
-#define __BPF_PROLOGUE_H
-
-struct probe_trace_arg;
-struct bpf_insn;
-
-#define BPF_PROLOGUE_MAX_ARGS 3
-#define BPF_PROLOGUE_START_ARG_REG BPF_REG_3
-#define BPF_PROLOGUE_FETCH_RESULT_REG BPF_REG_2
-
-#ifdef HAVE_BPF_PROLOGUE
-int bpf__gen_prologue(struct probe_trace_arg *args, int nargs,
-		      struct bpf_insn *new_prog, size_t *new_cnt,
-		      size_t cnt_space);
-#else
-#include <linux/compiler.h>
-#include <errno.h>
-
-static inline int
-bpf__gen_prologue(struct probe_trace_arg *args __maybe_unused,
-		  int nargs __maybe_unused,
-		  struct bpf_insn *new_prog __maybe_unused,
-		  size_t *new_cnt,
-		  size_t cnt_space __maybe_unused)
-{
-	if (!new_cnt)
-		return -EINVAL;
-	*new_cnt = 0;
-	return -ENOTSUP;
-}
-#endif
-#endif /* __BPF_PROLOGUE_H */

From 6ac75289b2884652abacab368f3850b9c0246e4a Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:45:47 -0800
Subject: [PATCH 0990/1530] perf dwarf-regs: Remove
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET

PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET was used for BPF prologue
support which was removed in Commit 3d6dfae88917 ("perf parse-events:
Remove BPF event support"). The code is no longer used so remove.

Remove the offset from various dwarf-regs.c tables and the dependence
on ptrace.h. Rename structs starting pt_ as the ptrace derived offset is
now removed.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Makefile.config                  |   4 -
 tools/perf/arch/arm64/Makefile              |   1 -
 tools/perf/arch/arm64/util/dwarf-regs.c     |  20 +---
 tools/perf/arch/loongarch/Makefile          |   1 -
 tools/perf/arch/loongarch/util/dwarf-regs.c |  10 --
 tools/perf/arch/powerpc/Makefile            |   1 -
 tools/perf/arch/powerpc/util/dwarf-regs.c   |  26 ++---
 tools/perf/arch/riscv/Makefile              |   1 -
 tools/perf/arch/riscv/util/dwarf-regs.c     |  14 +--
 tools/perf/arch/s390/Makefile               |   1 -
 tools/perf/arch/s390/util/dwarf-regs.c      |  27 -----
 tools/perf/arch/x86/Makefile                |   1 -
 tools/perf/arch/x86/util/dwarf-regs.c       | 109 +++-----------------
 tools/perf/util/include/dwarf-regs.h        |   8 --
 14 files changed, 27 insertions(+), 197 deletions(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 80bf06e828f0e..52a216df9e2af 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -211,10 +211,6 @@ FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arc
 # include ARCH specific config
 -include $(src-perf)/arch/$(SRCARCH)/Makefile
 
-ifdef PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
-  CFLAGS += -DHAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
-endif
-
 include $(srctree)/tools/scripts/utilities.mak
 
 ifeq ($(call get-executable,$(FLEX)),)
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 8a5ffbfe809fe..ca2e359612870 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -3,7 +3,6 @@ ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_JITDUMP := 1
-PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 HAVE_KVM_STAT_SUPPORT := 1
 
 #
diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c
index 917b97d7c5d36..343a62fa4199d 100644
--- a/tools/perf/arch/arm64/util/dwarf-regs.c
+++ b/tools/perf/arch/arm64/util/dwarf-regs.c
@@ -9,10 +9,9 @@
 #include <stddef.h>
 #include <string.h>
 #include <dwarf-regs.h>
-#include <linux/ptrace.h> /* for struct user_pt_regs */
 #include <linux/stringify.h>
 
-struct pt_regs_dwarfnum {
+struct regs_dwarfnum {
 	const char *name;
 	unsigned int dwarfnum;
 };
@@ -21,14 +20,12 @@ struct pt_regs_dwarfnum {
 #define GPR_DWARFNUM_NAME(num) \
 	{.name = __stringify(%x##num), .dwarfnum = num}
 #define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
-#define DWARFNUM2OFFSET(index) \
-	(index * sizeof((struct user_pt_regs *)0)->regs[0])
 
 /*
  * Reference:
  * http://infocenter.arm.com/help/topic/com.arm.doc.ihi0057b/IHI0057B_aadwarf64.pdf
  */
-static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
+static const struct regs_dwarfnum regdwarfnum_table[] = {
 	GPR_DWARFNUM_NAME(0),
 	GPR_DWARFNUM_NAME(1),
 	GPR_DWARFNUM_NAME(2),
@@ -74,19 +71,10 @@ static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
  */
 const char *get_arch_regstr(unsigned int n)
 {
-	const struct pt_regs_dwarfnum *roff;
+	const struct regs_dwarfnum *roff;
+
 	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
 		if (roff->dwarfnum == n)
 			return roff->name;
 	return NULL;
 }
-
-int regs_query_register_offset(const char *name)
-{
-	const struct pt_regs_dwarfnum *roff;
-
-	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
-		if (!strcmp(roff->name, name))
-			return DWARFNUM2OFFSET(roff->dwarfnum);
-	return -EINVAL;
-}
diff --git a/tools/perf/arch/loongarch/Makefile b/tools/perf/arch/loongarch/Makefile
index 1cc5eb01f32b2..79b432744296e 100644
--- a/tools/perf/arch/loongarch/Makefile
+++ b/tools/perf/arch/loongarch/Makefile
@@ -2,7 +2,6 @@
 ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
-PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 PERF_HAVE_JITDUMP := 1
 HAVE_KVM_STAT_SUPPORT := 1
 
diff --git a/tools/perf/arch/loongarch/util/dwarf-regs.c b/tools/perf/arch/loongarch/util/dwarf-regs.c
index 0f6ebc3874631..bee08fdcf2fd8 100644
--- a/tools/perf/arch/loongarch/util/dwarf-regs.c
+++ b/tools/perf/arch/loongarch/util/dwarf-regs.c
@@ -32,13 +32,3 @@ const char *get_arch_regstr(unsigned int n)
 	n %= 32;
 	return loongarch_gpr_table[n].name;
 }
-
-int regs_query_register_offset(const char *name)
-{
-	const struct pt_regs_dwarfnum *roff;
-
-	for (roff = loongarch_gpr_table; roff->name != NULL; roff++)
-		if (!strcmp(roff->name, name))
-			return roff->dwarfnum;
-	return -EINVAL;
-}
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 7672d555f6cdb..ae05727835d85 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -4,7 +4,6 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 
 HAVE_KVM_STAT_SUPPORT := 1
-PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 PERF_HAVE_JITDUMP := 1
 
 #
diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c
index 104c7ae5c433d..23846c59a5222 100644
--- a/tools/perf/arch/powerpc/util/dwarf-regs.c
+++ b/tools/perf/arch/powerpc/util/dwarf-regs.c
@@ -9,29 +9,25 @@
 #include <errno.h>
 #include <string.h>
 #include <dwarf-regs.h>
-#include <linux/ptrace.h>
 #include <linux/kernel.h>
 #include <linux/stringify.h>
 
-struct pt_regs_dwarfnum {
+struct regs_dwarfnum {
 	const char *name;
 	unsigned int dwarfnum;
-	unsigned int ptregs_offset;
 };
 
 #define REG_DWARFNUM_NAME(r, num)					\
-		{.name = __stringify(%)__stringify(r), .dwarfnum = num,			\
-		.ptregs_offset = offsetof(struct pt_regs, r)}
+	{.name = __stringify(%)__stringify(r), .dwarfnum = num}
 #define GPR_DWARFNUM_NAME(num)						\
-		{.name = __stringify(%gpr##num), .dwarfnum = num,		\
-		.ptregs_offset = offsetof(struct pt_regs, gpr[num])}
-#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0, .ptregs_offset = 0}
+	{.name = __stringify(%gpr##num), .dwarfnum = num}
+#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
 
 /*
  * Reference:
  * http://refspecs.linuxfoundation.org/ELF/ppc64/PPC-elf64abi-1.9.html
  */
-static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
+static const struct regs_dwarfnum regdwarfnum_table[] = {
 	GPR_DWARFNUM_NAME(0),
 	GPR_DWARFNUM_NAME(1),
 	GPR_DWARFNUM_NAME(2),
@@ -83,22 +79,14 @@ static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
  */
 const char *get_arch_regstr(unsigned int n)
 {
-	const struct pt_regs_dwarfnum *roff;
+	const struct regs_dwarfnum *roff;
+
 	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
 		if (roff->dwarfnum == n)
 			return roff->name;
 	return NULL;
 }
 
-int regs_query_register_offset(const char *name)
-{
-	const struct pt_regs_dwarfnum *roff;
-	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
-		if (!strcmp(roff->name, name))
-			return roff->ptregs_offset;
-	return -EINVAL;
-}
-
 #define PPC_OP(op)	(((op) >> 26) & 0x3F)
 #define PPC_RA(a)	(((a) >> 16) & 0x1f)
 #define PPC_RT(t)	(((t) >> 21) & 0x1f)
diff --git a/tools/perf/arch/riscv/Makefile b/tools/perf/arch/riscv/Makefile
index 00573af87a681..d83e0f32f3a83 100644
--- a/tools/perf/arch/riscv/Makefile
+++ b/tools/perf/arch/riscv/Makefile
@@ -1,7 +1,6 @@
 ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
-PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 PERF_HAVE_JITDUMP := 1
 HAVE_KVM_STAT_SUPPORT := 1
 
diff --git a/tools/perf/arch/riscv/util/dwarf-regs.c b/tools/perf/arch/riscv/util/dwarf-regs.c
index cd0504c02e2e0..a9c4402ae57ec 100644
--- a/tools/perf/arch/riscv/util/dwarf-regs.c
+++ b/tools/perf/arch/riscv/util/dwarf-regs.c
@@ -9,7 +9,7 @@
 #include <string.h> /* for strcmp */
 #include <dwarf-regs.h>
 
-struct pt_regs_dwarfnum {
+struct regs_dwarfnum {
 	const char *name;
 	unsigned int dwarfnum;
 };
@@ -17,7 +17,7 @@ struct pt_regs_dwarfnum {
 #define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
 #define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
 
-struct pt_regs_dwarfnum riscv_dwarf_regs_table[] = {
+struct regs_dwarfnum riscv_dwarf_regs_table[] = {
 	REG_DWARFNUM_NAME("%zero", 0),
 	REG_DWARFNUM_NAME("%ra", 1),
 	REG_DWARFNUM_NAME("%sp", 2),
@@ -60,13 +60,3 @@ const char *get_arch_regstr(unsigned int n)
 {
 	return (n < RISCV_MAX_REGS) ? riscv_dwarf_regs_table[n].name : NULL;
 }
-
-int regs_query_register_offset(const char *name)
-{
-	const struct pt_regs_dwarfnum *roff;
-
-	for (roff = riscv_dwarf_regs_table; roff->name; roff++)
-		if (!strcmp(roff->name, name))
-			return roff->dwarfnum;
-	return -EINVAL;
-}
diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile
index 3f66e2ede3f7e..58e79f5b67a44 100644
--- a/tools/perf/arch/s390/Makefile
+++ b/tools/perf/arch/s390/Makefile
@@ -3,7 +3,6 @@ ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
 HAVE_KVM_STAT_SUPPORT := 1
-PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 PERF_HAVE_JITDUMP := 1
 
 #
diff --git a/tools/perf/arch/s390/util/dwarf-regs.c b/tools/perf/arch/s390/util/dwarf-regs.c
index dfddb3099bfa5..5bcf3192623a5 100644
--- a/tools/perf/arch/s390/util/dwarf-regs.c
+++ b/tools/perf/arch/s390/util/dwarf-regs.c
@@ -7,37 +7,10 @@
  *
  */
 
-#include <errno.h>
-#include <stddef.h>
-#include <stdlib.h>
 #include <linux/kernel.h>
-#include <asm/ptrace.h>
-#include <string.h>
-#include <dwarf-regs.h>
 #include "dwarf-regs-table.h"
 
 const char *get_arch_regstr(unsigned int n)
 {
 	return (n >= ARRAY_SIZE(s390_dwarf_regs)) ? NULL : s390_dwarf_regs[n];
 }
-
-/*
- * Convert the register name into an offset to struct pt_regs (kernel).
- * This is required by the BPF prologue generator.  The BPF
- * program is called in the BPF overflow handler in the perf
- * core.
- */
-int regs_query_register_offset(const char *name)
-{
-	unsigned long gpr;
-
-	if (!name || strncmp(name, "%r", 2))
-		return -EINVAL;
-
-	errno = 0;
-	gpr = strtoul(name + 2, NULL, 10);
-	if (errno || gpr >= 16)
-		return -EINVAL;
-
-	return offsetof(user_pt_regs, gprs) + 8 * gpr;
-}
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 9aa58acb55641..51cf267f4d850 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -3,7 +3,6 @@ ifndef NO_LIBDW
 PERF_HAVE_DWARF_REGS := 1
 endif
 HAVE_KVM_STAT_SUPPORT := 1
-PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 PERF_HAVE_JITDUMP := 1
 
 ###
diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c
index 399c4a0a29d8c..530905118cd4f 100644
--- a/tools/perf/arch/x86/util/dwarf-regs.c
+++ b/tools/perf/arch/x86/util/dwarf-regs.c
@@ -6,112 +6,31 @@
  * Written by Masami Hiramatsu <mhiramat@redhat.com>
  */
 
-#include <stddef.h>
 #include <errno.h> /* for EINVAL */
 #include <string.h> /* for strcmp */
-#include <linux/ptrace.h> /* for struct pt_regs */
-#include <linux/kernel.h> /* for offsetof */
+#include <linux/kernel.h> /* for ARRAY_SIZE */
 #include <dwarf-regs.h>
 
-/*
- * See arch/x86/kernel/ptrace.c.
- * Different from it:
- *
- *  - Since struct pt_regs is defined differently for user and kernel,
- *    but we want to use 'ax, bx' instead of 'rax, rbx' (which is struct
- *    field name of user's pt_regs), we make REG_OFFSET_NAME to accept
- *    both string name and reg field name.
- *
- *  - Since accessing x86_32's pt_regs from x86_64 building is difficult
- *    and vise versa, we simply fill offset with -1, so
- *    get_arch_regstr() still works but regs_query_register_offset()
- *    returns error.
- *    The only inconvenience caused by it now is that we are not allowed
- *    to generate BPF prologue for a x86_64 kernel if perf is built for
- *    x86_32. This is really a rare usecase.
- *
- *  - Order is different from kernel's ptrace.c for get_arch_regstr(). Use
- *    the order defined by dwarf.
- */
+#define DEFINE_DWARF_REGSTR_TABLE 1
+#include "dwarf-regs-table.h"
 
-struct pt_regs_offset {
-	const char *name;
-	int offset;
-};
-
-#define REG_OFFSET_END {.name = NULL, .offset = 0}
-
-#ifdef __x86_64__
-# define REG_OFFSET_NAME_64(n, r) {.name = n, .offset = offsetof(struct pt_regs, r)}
-# define REG_OFFSET_NAME_32(n, r) {.name = n, .offset = -1}
+/* Return architecture dependent register string (for kprobe-tracer) */
+const char *get_arch_regstr(unsigned int n)
+{
+#if defined(__i386__)
+	size_t len = ARRAY_SIZE(x86_32_regstr_tbl);
 #else
-# define REG_OFFSET_NAME_64(n, r) {.name = n, .offset = -1}
-# define REG_OFFSET_NAME_32(n, r) {.name = n, .offset = offsetof(struct pt_regs, r)}
+	size_t len = ARRAY_SIZE(x86_64_regstr_tbl);
 #endif
 
-/* TODO: switching by dwarf address size */
-#ifndef __x86_64__
-static const struct pt_regs_offset x86_32_regoffset_table[] = {
-	REG_OFFSET_NAME_32("%ax",	eax),
-	REG_OFFSET_NAME_32("%cx",	ecx),
-	REG_OFFSET_NAME_32("%dx",	edx),
-	REG_OFFSET_NAME_32("%bx",	ebx),
-	REG_OFFSET_NAME_32("$stack",	esp),	/* Stack address instead of %sp */
-	REG_OFFSET_NAME_32("%bp",	ebp),
-	REG_OFFSET_NAME_32("%si",	esi),
-	REG_OFFSET_NAME_32("%di",	edi),
-	REG_OFFSET_END,
-};
+	if (n >= len)
+		return NULL;
 
-#define regoffset_table x86_32_regoffset_table
+#if defined(__i386__)
+	return x86_32_regstr_tbl[n];
 #else
-static const struct pt_regs_offset x86_64_regoffset_table[] = {
-	REG_OFFSET_NAME_64("%ax",	rax),
-	REG_OFFSET_NAME_64("%dx",	rdx),
-	REG_OFFSET_NAME_64("%cx",	rcx),
-	REG_OFFSET_NAME_64("%bx",	rbx),
-	REG_OFFSET_NAME_64("%si",	rsi),
-	REG_OFFSET_NAME_64("%di",	rdi),
-	REG_OFFSET_NAME_64("%bp",	rbp),
-	REG_OFFSET_NAME_64("%sp",	rsp),
-	REG_OFFSET_NAME_64("%r8",	r8),
-	REG_OFFSET_NAME_64("%r9",	r9),
-	REG_OFFSET_NAME_64("%r10",	r10),
-	REG_OFFSET_NAME_64("%r11",	r11),
-	REG_OFFSET_NAME_64("%r12",	r12),
-	REG_OFFSET_NAME_64("%r13",	r13),
-	REG_OFFSET_NAME_64("%r14",	r14),
-	REG_OFFSET_NAME_64("%r15",	r15),
-	REG_OFFSET_END,
-};
-
-#define regoffset_table x86_64_regoffset_table
+	return x86_64_regstr_tbl[n];
 #endif
-
-/* Minus 1 for the ending REG_OFFSET_END */
-#define ARCH_MAX_REGS ((sizeof(regoffset_table) / sizeof(regoffset_table[0])) - 1)
-
-/* Return architecture dependent register string (for kprobe-tracer) */
-const char *get_arch_regstr(unsigned int n)
-{
-	return (n < ARCH_MAX_REGS) ? regoffset_table[n].name : NULL;
-}
-
-/* Reuse code from arch/x86/kernel/ptrace.c */
-/**
- * regs_query_register_offset() - query register offset from its name
- * @name:	the name of a register
- *
- * regs_query_register_offset() returns the offset of a register in struct
- * pt_regs from its name. If the name is invalid, this returns -EINVAL;
- */
-int regs_query_register_offset(const char *name)
-{
-	const struct pt_regs_offset *roff;
-	for (roff = regoffset_table; roff->name != NULL; roff++)
-		if (!strcmp(roff->name, name))
-			return roff->offset;
-	return -EINVAL;
 }
 
 struct dwarf_regs_idx {
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 29a7d0546b823..fbdd7307e0c2d 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -42,12 +42,4 @@ static inline void get_powerpc_regs(u32 raw_insn __maybe_unused, int is_source _
 void get_powerpc_regs(u32 raw_insn, int is_source, struct annotated_op_loc *op_loc);
 #endif
 
-#ifdef HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
-/*
- * Arch should support fetching the offset of a register in pt_regs
- * by its name. See kernel's regs_query_register_offset in
- * arch/xxx/kernel/ptrace.c.
- */
-int regs_query_register_offset(const char *name);
-#endif
 #endif

From ae894b77923e7531f2c728121a40902f01adc8c6 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:45:48 -0800
Subject: [PATCH 0991/1530] perf dwarf-regs: Add EM_HOST and EF_HOST defines

Computed from the build architecture defines, EM_HOST and EF_HOST give
values that can be used in dwarf register lookup. Place in
dwarf-regs.h so the value can be shared. Move some dwarf-regs.c
constants used for EM_HOST to dwarf-regs.h. Add CSky constants that
may be missing.

In disasm.c add an include of dwarf-regs.h as the included
arch/*/annotate/instructions.c files make use of the constants and we
want the elf.h/dwarf-regs.h dependency to be explicit.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-4-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/disasm.c             |  1 +
 tools/perf/util/dwarf-regs.c         |  8 ---
 tools/perf/util/include/dwarf-regs.h | 82 ++++++++++++++++++++++++++++
 3 files changed, 83 insertions(+), 8 deletions(-)

diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index bd98fec903f73..a525b80b934fd 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -18,6 +18,7 @@
 #include "disasm.h"
 #include "disasm_bpf.h"
 #include "dso.h"
+#include "dwarf-regs.h"
 #include "env.h"
 #include "evsel.h"
 #include "map.h"
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 5b7f86c0063f2..7c01bc4d7e5b3 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -13,14 +13,6 @@
 #include <errno.h>
 #include <linux/kernel.h>
 
-#ifndef EM_AARCH64
-#define EM_AARCH64	183  /* ARM 64 bit */
-#endif
-
-#ifndef EM_LOONGARCH
-#define EM_LOONGARCH	258 /* LoongArch */
-#endif
-
 /* Define const char * {arch}_register_tbl[] */
 #define DEFINE_DWARF_REGSTR_TABLE
 #include "../arch/x86/include/dwarf-regs-table.h"
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index fbdd7307e0c2d..ce9f10b3282d7 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -2,6 +2,88 @@
 #ifndef _PERF_DWARF_REGS_H_
 #define _PERF_DWARF_REGS_H_
 #include "annotate.h"
+#include <elf.h>
+
+#ifndef EM_AARCH64
+#define EM_AARCH64	183  /* ARM 64 bit */
+#endif
+
+#ifndef EM_CSKY
+#define EM_CSKY		252  /* C-SKY */
+#endif
+#ifndef EF_CSKY_ABIV1
+#define EF_CSKY_ABIV1	0X10000000
+#endif
+#ifndef EF_CSKY_ABIV2
+#define EF_CSKY_ABIV2	0X20000000
+#endif
+
+#ifndef EM_LOONGARCH
+#define EM_LOONGARCH	258 /* LoongArch */
+#endif
+
+/* EM_HOST gives the ELF machine for host, EF_HOST gives additional flags. */
+#if defined(__x86_64__)
+  #define EM_HOST EM_X86_64
+#elif defined(__i386__)
+  #define EM_HOST EM_386
+#elif defined(__aarch64__)
+  #define EM_HOST EM_AARCH64
+#elif defined(__arm__)
+  #define EM_HOST EM_ARM
+#elif defined(__alpha__)
+  #define EM_HOST EM_ALPHA
+#elif defined(__arc__)
+  #define EM_HOST EM_ARC
+#elif defined(__AVR__)
+  #define EM_HOST EM_AVR
+#elif defined(__AVR32__)
+  #define EM_HOST EM_AVR32
+#elif defined(__bfin__)
+  #define EM_HOST EM_BLACKFIN
+#elif defined(__csky__)
+  #define EM_HOST EM_CSKY
+  #if defined(__CSKYABIV2__)
+    #define EF_HOST EF_CSKY_ABIV2
+  #else
+    #define EF_HOST EF_CSKY_ABIV1
+  #endif
+#elif defined(__cris__)
+  #define EM_HOST EM_CRIS
+#elif defined(__hppa__) // HP PA-RISC
+  #define EM_HOST EM_PARISC
+#elif defined(__loongarch__)
+  #define EM_HOST EM_LOONGARCH
+#elif defined(__mips__)
+  #define EM_HOST EM_MIPS
+#elif defined(__m32r__)
+  #define EM_HOST EM_M32R
+#elif defined(__microblaze__)
+  #define EM_HOST EM_MICROBLAZE
+#elif defined(__MSP430__)
+  #define EM_HOST EM_MSP430
+#elif defined(__powerpc64__)
+  #define EM_HOST EM_PPC64
+#elif defined(__powerpc__)
+  #define EM_HOST EM_PPC
+#elif defined(__riscv)
+  #define EM_HOST EM_RISCV
+#elif defined(__s390x__)
+  #define EM_HOST EM_S390
+#elif defined(__sh__)
+  #define EM_HOST EM_SH
+#elif defined(__sparc64__) || defined(__sparc__)
+  #define EM_HOST EM_SPARC
+#elif defined(__xtensa__)
+  #define EM_HOST EM_XTENSA
+#else
+  /* Unknown host ELF machine type. */
+  #define EM_HOST EM_NONE
+#endif
+
+#if !defined(EF_HOST)
+  #define EF_HOST 0
+#endif
 
 #define DWARF_REG_PC  0xd3af9c /* random number */
 #define DWARF_REG_FB  0xd3affb /* random number */

From cd6c9dca9d4bf1d5a9d3606cf5cace513f6dc5ce Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:45:49 -0800
Subject: [PATCH 0992/1530] perf disasm: Add e_machine/e_flags to struct arch

Currently functions like get_dwarf_regnum only work with the host
architecture. Carry the elf machine and flags in struct arch so that
in disassembly these can be used to allow cross platform disassembly.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-5-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/arc/annotate/instructions.c       | 2 ++
 tools/perf/arch/arm/annotate/instructions.c       | 2 ++
 tools/perf/arch/arm64/annotate/instructions.c     | 2 ++
 tools/perf/arch/csky/annotate/instructions.c      | 7 ++++++-
 tools/perf/arch/loongarch/annotate/instructions.c | 2 ++
 tools/perf/arch/mips/annotate/instructions.c      | 2 ++
 tools/perf/arch/powerpc/annotate/instructions.c   | 2 ++
 tools/perf/arch/riscv64/annotate/instructions.c   | 2 ++
 tools/perf/arch/s390/annotate/instructions.c      | 2 ++
 tools/perf/arch/sparc/annotate/instructions.c     | 2 ++
 tools/perf/arch/x86/annotate/instructions.c       | 3 ++-
 tools/perf/util/disasm.h                          | 4 ++++
 12 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/tools/perf/arch/arc/annotate/instructions.c b/tools/perf/arch/arc/annotate/instructions.c
index 2f00e995c7e38..e5619770a1af7 100644
--- a/tools/perf/arch/arc/annotate/instructions.c
+++ b/tools/perf/arch/arc/annotate/instructions.c
@@ -5,5 +5,7 @@ static int arc__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
 	arch->initialized = true;
 	arch->objdump.comment_char = ';';
+	arch->e_machine = EM_ARC;
+	arch->e_flags = 0;
 	return 0;
 }
diff --git a/tools/perf/arch/arm/annotate/instructions.c b/tools/perf/arch/arm/annotate/instructions.c
index 2ff6cedeb9c53..cf91a43362b0e 100644
--- a/tools/perf/arch/arm/annotate/instructions.c
+++ b/tools/perf/arch/arm/annotate/instructions.c
@@ -53,6 +53,8 @@ static int arm__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 	arch->associate_instruction_ops   = arm__associate_instruction_ops;
 	arch->objdump.comment_char	  = ';';
 	arch->objdump.skip_functions_char = '+';
+	arch->e_machine = EM_ARM;
+	arch->e_flags = 0;
 	return 0;
 
 out_free_call:
diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
index f86d9f4798bd0..d465d093e7eb5 100644
--- a/tools/perf/arch/arm64/annotate/instructions.c
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -113,6 +113,8 @@ static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 	arch->associate_instruction_ops   = arm64__associate_instruction_ops;
 	arch->objdump.comment_char	  = '/';
 	arch->objdump.skip_functions_char = '+';
+	arch->e_machine = EM_AARCH64;
+	arch->e_flags = 0;
 	return 0;
 
 out_free_call:
diff --git a/tools/perf/arch/csky/annotate/instructions.c b/tools/perf/arch/csky/annotate/instructions.c
index 5337bfb7d5fcf..14270311d215e 100644
--- a/tools/perf/arch/csky/annotate/instructions.c
+++ b/tools/perf/arch/csky/annotate/instructions.c
@@ -43,6 +43,11 @@ static int csky__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 	arch->initialized = true;
 	arch->objdump.comment_char = '/';
 	arch->associate_instruction_ops = csky__associate_ins_ops;
-
+	arch->e_machine = EM_CSKY;
+#if defined(__CSKYABIV2__)
+	arch->e_flags = EF_CSKY_ABIV2;
+#else
+	arch->e_flags = EF_CSKY_ABIV1;
+#endif
 	return 0;
 }
diff --git a/tools/perf/arch/loongarch/annotate/instructions.c b/tools/perf/arch/loongarch/annotate/instructions.c
index ab43b1ab51e3b..70262d5f14442 100644
--- a/tools/perf/arch/loongarch/annotate/instructions.c
+++ b/tools/perf/arch/loongarch/annotate/instructions.c
@@ -131,6 +131,8 @@ int loongarch__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 		arch->associate_instruction_ops = loongarch__associate_ins_ops;
 		arch->initialized = true;
 		arch->objdump.comment_char = '#';
+		arch->e_machine = EM_LOONGARCH;
+		arch->e_flags = 0;
 	}
 
 	return 0;
diff --git a/tools/perf/arch/mips/annotate/instructions.c b/tools/perf/arch/mips/annotate/instructions.c
index 340993f2a897a..b50b46c613d66 100644
--- a/tools/perf/arch/mips/annotate/instructions.c
+++ b/tools/perf/arch/mips/annotate/instructions.c
@@ -40,6 +40,8 @@ int mips__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 		arch->associate_instruction_ops = mips__associate_ins_ops;
 		arch->initialized = true;
 		arch->objdump.comment_char = '#';
+		arch->e_machine = EM_MIPS;
+		arch->e_flags = 0;
 	}
 
 	return 0;
diff --git a/tools/perf/arch/powerpc/annotate/instructions.c b/tools/perf/arch/powerpc/annotate/instructions.c
index 54478cf5cccc9..ca567cfdcbdb4 100644
--- a/tools/perf/arch/powerpc/annotate/instructions.c
+++ b/tools/perf/arch/powerpc/annotate/instructions.c
@@ -309,6 +309,8 @@ static int powerpc__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 		arch->associate_instruction_ops = powerpc__associate_instruction_ops;
 		arch->objdump.comment_char      = '#';
 		annotate_opts.show_asm_raw = true;
+		arch->e_machine = EM_PPC;
+		arch->e_flags = 0;
 	}
 
 	return 0;
diff --git a/tools/perf/arch/riscv64/annotate/instructions.c b/tools/perf/arch/riscv64/annotate/instructions.c
index 869a0eb289531..55cf911633f8b 100644
--- a/tools/perf/arch/riscv64/annotate/instructions.c
+++ b/tools/perf/arch/riscv64/annotate/instructions.c
@@ -28,6 +28,8 @@ int riscv64__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 		arch->associate_instruction_ops = riscv64__associate_ins_ops;
 		arch->initialized = true;
 		arch->objdump.comment_char = '#';
+		arch->e_machine = EM_RISCV;
+		arch->e_flags = 0;
 	}
 
 	return 0;
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index eeac25cca699a..c61193f1e0964 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -166,6 +166,8 @@ static int s390__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 			if (s390__cpuid_parse(arch, cpuid))
 				err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING;
 		}
+		arch->e_machine = EM_S390;
+		arch->e_flags = 0;
 	}
 
 	return err;
diff --git a/tools/perf/arch/sparc/annotate/instructions.c b/tools/perf/arch/sparc/annotate/instructions.c
index 2614c010c2352..68c31580ccfc4 100644
--- a/tools/perf/arch/sparc/annotate/instructions.c
+++ b/tools/perf/arch/sparc/annotate/instructions.c
@@ -163,6 +163,8 @@ static int sparc__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 		arch->initialized = true;
 		arch->associate_instruction_ops = sparc__associate_instruction_ops;
 		arch->objdump.comment_char = '#';
+		arch->e_machine = EM_SPARC;
+		arch->e_flags = 0;
 	}
 
 	return 0;
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index c869abe3c31da..ae94b1f0b9cce 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -202,7 +202,8 @@ static int x86__annotate_init(struct arch *arch, char *cpuid)
 		if (x86__cpuid_parse(arch, cpuid))
 			err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING;
 	}
-
+	arch->e_machine = EM_X86_64;
+	arch->e_flags = 0;
 	arch->initialized = true;
 	return err;
 }
diff --git a/tools/perf/util/disasm.h b/tools/perf/util/disasm.h
index 486c269b29ba5..c135db2416b5c 100644
--- a/tools/perf/util/disasm.h
+++ b/tools/perf/util/disasm.h
@@ -44,6 +44,10 @@ struct arch {
 				struct data_loc_info *dloc, Dwarf_Die *cu_die,
 				struct disasm_line *dl);
 #endif
+	/** @e_machine: ELF machine associated with arch. */
+	unsigned int e_machine;
+	/** @e_flags: Optional ELF flags associated with arch. */
+	unsigned int e_flags;
 };
 
 struct ins {

From 9fc4489a16f41d9306af6c94ca97be6364d51ea9 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:45:50 -0800
Subject: [PATCH 0993/1530] perf dwarf-regs: Pass accurate disassembly machine
 to get_dwarf_regnum

Rather than pass 0/EM_NONE, use the value computed in the disasm
struct arch. Switch the EM_NONE case to EM_HOST, rewriting EM_NONE if
it were passed to get_dwarf_regnum. Pass a flags value as
architectures like csky need the flags to determine the ABI variant.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-6-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/annotate.c           | 6 +++---
 tools/perf/util/dwarf-regs.c         | 8 ++++++--
 tools/perf/util/include/dwarf-regs.h | 5 +++--
 3 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 37ce43c4eb8f6..b1d98da79be8b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2292,7 +2292,7 @@ static int extract_reg_offset(struct arch *arch, const char *str,
 	if (regname == NULL)
 		return -1;
 
-	op_loc->reg1 = get_dwarf_regnum(regname, 0);
+	op_loc->reg1 = get_dwarf_regnum(regname, arch->e_machine, arch->e_flags);
 	free(regname);
 
 	/* Get the second register */
@@ -2305,7 +2305,7 @@ static int extract_reg_offset(struct arch *arch, const char *str,
 		if (regname == NULL)
 			return -1;
 
-		op_loc->reg2 = get_dwarf_regnum(regname, 0);
+		op_loc->reg2 = get_dwarf_regnum(regname, arch->e_machine, arch->e_flags);
 		free(regname);
 	}
 	return 0;
@@ -2405,7 +2405,7 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
 				return -1;
 
 			if (*s == arch->objdump.register_char)
-				op_loc->reg1 = get_dwarf_regnum(s, 0);
+				op_loc->reg1 = get_dwarf_regnum(s, arch->e_machine, arch->e_flags);
 			else if (*s == arch->objdump.imm_char) {
 				op_loc->offset = strtol(s + 1, &p, 0);
 				if (p && p != s + 1)
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 7c01bc4d7e5b3..1321387f6948f 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -70,7 +70,7 @@ __weak int get_arch_regnum(const char *name __maybe_unused)
 }
 
 /* Return DWARF register number from architecture register name */
-int get_dwarf_regnum(const char *name, unsigned int machine)
+int get_dwarf_regnum(const char *name, unsigned int machine, unsigned int flags __maybe_unused)
 {
 	char *regname = strdup(name);
 	int reg = -1;
@@ -84,8 +84,12 @@ int get_dwarf_regnum(const char *name, unsigned int machine)
 	if (p)
 		*p = '\0';
 
+	if (machine == EM_NONE) {
+		/* Generic arch - use host arch */
+		machine = EM_HOST;
+	}
 	switch (machine) {
-	case EM_NONE:	/* Generic arch - use host arch */
+	case EM_HOST:
 		reg = get_arch_regnum(regname);
 		break;
 	default:
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index ce9f10b3282d7..3c3a908b9f366 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -103,12 +103,13 @@ int get_arch_regnum(const char *name);
  * name: architecture register name
  * machine: ELF machine signature (EM_*)
  */
-int get_dwarf_regnum(const char *name, unsigned int machine);
+int get_dwarf_regnum(const char *name, unsigned int machine, unsigned int flags);
 
 #else /* HAVE_LIBDW_SUPPORT */
 
 static inline int get_dwarf_regnum(const char *name __maybe_unused,
-				   unsigned int machine __maybe_unused)
+				   unsigned int machine __maybe_unused,
+				   unsigned int flags __maybe_unused)
 {
 	return -1;
 }

From a784847c2da1f2d17da737bb7be541e2f7b79f8f Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:45:51 -0800
Subject: [PATCH 0994/1530] perf dwarf-regs: Pass ELF flags to get_dwarf_regstr

Pass a flags value as architectures like csky need the flags to
determine the ABI variant.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-7-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/dwarf-regs.c         |  3 ++-
 tools/perf/util/include/dwarf-regs.h | 11 ++++++-----
 tools/perf/util/probe-finder.c       | 13 +++++++------
 tools/perf/util/probe-finder.h       |  3 ++-
 4 files changed, 17 insertions(+), 13 deletions(-)

diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 1321387f6948f..86b3ef638fbb3 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -29,7 +29,8 @@
 #define __get_dwarf_regstr(tbl, n) (((n) < ARRAY_SIZE(tbl)) ? (tbl)[(n)] : NULL)
 
 /* Return architecture dependent register string (for kprobe-tracer) */
-const char *get_dwarf_regstr(unsigned int n, unsigned int machine)
+const char *get_dwarf_regstr(unsigned int n, unsigned int machine,
+			     unsigned int flags __maybe_unused)
 {
 	switch (machine) {
 	case EM_NONE:	/* Generic arch - use host arch */
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 3c3a908b9f366..0ef428d07bccd 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -90,12 +90,13 @@
 
 #ifdef HAVE_LIBDW_SUPPORT
 const char *get_arch_regstr(unsigned int n);
-/*
- * get_dwarf_regstr - Returns ftrace register string from DWARF regnum
- * n: DWARF register number
- * machine: ELF machine signature (EM_*)
+/**
+ * get_dwarf_regstr() - Returns ftrace register string from DWARF regnum.
+ * @n: DWARF register number.
+ * @machine: ELF machine signature (EM_*).
+ * @flags: ELF flags for things like ABI differences.
  */
-const char *get_dwarf_regstr(unsigned int n, unsigned int machine);
+const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int flags);
 
 int get_arch_regnum(const char *name);
 /*
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index c2ca94e29aca3..7f2ee0cb43ca4 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -56,7 +56,7 @@ static struct probe_trace_arg_ref *alloc_trace_arg_ref(long offs)
  */
 static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 				     Dwarf_Op *fb_ops, Dwarf_Die *sp_die,
-				     unsigned int machine,
+				     const struct probe_finder *pf,
 				     struct probe_trace_arg *tvar)
 {
 	Dwarf_Attribute attr;
@@ -166,7 +166,7 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 	if (!tvar)
 		return ret2;
 
-	regs = get_dwarf_regstr(regn, machine);
+	regs = get_dwarf_regstr(regn, pf->e_machine, pf->e_flags);
 	if (!regs) {
 		/* This should be a bug in DWARF or this tool */
 		pr_warning("Mapping for the register number %u "
@@ -451,7 +451,7 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 		 dwarf_diename(vr_die));
 
 	ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
-					&pf->sp_die, pf->machine, pf->tvar);
+					&pf->sp_die, pf, pf->tvar);
 	if (ret == -ENOENT && pf->skip_empty_arg)
 		/* This can be found in other place. skip it */
 		return 0;
@@ -1134,7 +1134,8 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 	if (gelf_getehdr(elf, &ehdr) == NULL)
 		return -EINVAL;
 
-	pf->machine = ehdr.e_machine;
+	pf->e_machine = ehdr.e_machine;
+	pf->e_flags = ehdr.e_flags;
 
 	do {
 		GElf_Shdr shdr;
@@ -1171,7 +1172,7 @@ static int copy_variables_cb(Dwarf_Die *die_mem, void *data)
 	    (tag == DW_TAG_variable && vf->vars)) {
 		if (convert_variable_location(die_mem, vf->pf->addr,
 					      vf->pf->fb_ops, &pf->sp_die,
-					      pf->machine, NULL) == 0) {
+					      pf, /*tvar=*/NULL) == 0) {
 			vf->args[vf->nargs].var = (char *)dwarf_diename(die_mem);
 			if (vf->args[vf->nargs].var == NULL) {
 				vf->ret = -ENOMEM;
@@ -1402,7 +1403,7 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 	    tag == DW_TAG_variable) {
 		ret = convert_variable_location(die_mem, af->pf.addr,
 						af->pf.fb_ops, &af->pf.sp_die,
-						af->pf.machine, NULL);
+						&af->pf, /*tvar=*/NULL);
 		if (ret == 0 || ret == -ERANGE) {
 			int ret2;
 			bool externs = !af->child;
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index dfcf8cdd9e8db..be7b46ea24608 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -68,7 +68,8 @@ struct probe_finder {
 	/* Call Frame Information from .debug_frame. Not owned. */
 	Dwarf_CFI		*cfi_dbg;
 	Dwarf_Op		*fb_ops;	/* Frame base attribute */
-	unsigned int		machine;	/* Target machine arch */
+	unsigned int		e_machine;	/* ELF target machine arch */
+	unsigned int		e_flags;	/* ELF target machine flags */
 	struct perf_probe_arg	*pvar;		/* Current target variable */
 	struct probe_trace_arg	*tvar;		/* Current result variable */
 	bool			skip_empty_arg;	/* Skip non-exist args */

From bf4e799a0a339cab73925790ce164ee3c63f9dc1 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:45:52 -0800
Subject: [PATCH 0995/1530] perf dwarf-regs: Move x86 dwarf-regs out of arch

Move arch/x86/util/dwarf-regs.c to util/dwarf-regs-x86.c and compile
in unconditionally. To avoid get_arch_regnum being duplicated, rename
to get_x86_regnum and add to get_dwarf_regnum switch.

For get_arch_regstr, this was unused on x86 unless the machine type
was EM_NONE. Map that case to EM_HOST and remove get_arch_regstr from
dwarf-regs-x86.c.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-8-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/x86/util/Build                |  3 ---
 tools/perf/util/Build                         |  1 +
 .../dwarf-regs.c => util/dwarf-regs-x86.c}    | 24 +------------------
 tools/perf/util/dwarf-regs.c                  | 17 +++++++++++++
 tools/perf/util/include/dwarf-regs.h          |  8 +++++++
 5 files changed, 27 insertions(+), 26 deletions(-)
 rename tools/perf/{arch/x86/util/dwarf-regs.c => util/dwarf-regs-x86.c} (77%)

diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index bc56a8e70f347..848327378694d 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -11,9 +11,6 @@ perf-util-y += mem-events.o
 perf-util-y += evsel.o
 perf-util-y += iostat.o
 
-perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
-perf-util-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
-
 perf-util-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 78b990c04f719..ec0994b6b0114 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -204,6 +204,7 @@ endif
 perf-util-$(CONFIG_LIBDW) += probe-finder.o
 perf-util-$(CONFIG_LIBDW) += dwarf-aux.o
 perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
+perf-util-$(CONFIG_LIBDW) += dwarf-regs-x86.o
 perf-util-$(CONFIG_LIBDW) += debuginfo.o
 perf-util-$(CONFIG_LIBDW) += annotate-data.o
 
diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/util/dwarf-regs-x86.c
similarity index 77%
rename from tools/perf/arch/x86/util/dwarf-regs.c
rename to tools/perf/util/dwarf-regs-x86.c
index 530905118cd4f..7a55c65e8da6e 100644
--- a/tools/perf/arch/x86/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs-x86.c
@@ -11,28 +11,6 @@
 #include <linux/kernel.h> /* for ARRAY_SIZE */
 #include <dwarf-regs.h>
 
-#define DEFINE_DWARF_REGSTR_TABLE 1
-#include "dwarf-regs-table.h"
-
-/* Return architecture dependent register string (for kprobe-tracer) */
-const char *get_arch_regstr(unsigned int n)
-{
-#if defined(__i386__)
-	size_t len = ARRAY_SIZE(x86_32_regstr_tbl);
-#else
-	size_t len = ARRAY_SIZE(x86_64_regstr_tbl);
-#endif
-
-	if (n >= len)
-		return NULL;
-
-#if defined(__i386__)
-	return x86_32_regstr_tbl[n];
-#else
-	return x86_64_regstr_tbl[n];
-#endif
-}
-
 struct dwarf_regs_idx {
 	const char *name;
 	int idx;
@@ -58,7 +36,7 @@ static const struct dwarf_regs_idx x86_regidx_table[] = {
 	{ "rip", DWARF_REG_PC },
 };
 
-int get_arch_regnum(const char *name)
+int get_x86_regnum(const char *name)
 {
 	unsigned int i;
 
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 86b3ef638fbb3..eac99a2467372 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -32,9 +32,17 @@
 const char *get_dwarf_regstr(unsigned int n, unsigned int machine,
 			     unsigned int flags __maybe_unused)
 {
+#if EM_HOST == EM_X86_64 || EM_HOST == EM_386
+	if (machine == EM_NONE) {
+		/* Generic arch - use host arch */
+		machine = EM_HOST;
+	}
+#endif
 	switch (machine) {
+#if EM_HOST != EM_X86_64 && EM_HOST != EM_386
 	case EM_NONE:	/* Generic arch - use host arch */
 		return get_arch_regstr(n);
+#endif
 	case EM_386:
 		return __get_dwarf_regstr(x86_32_regstr_tbl, n);
 	case EM_X86_64:
@@ -65,10 +73,12 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine,
 	return NULL;
 }
 
+#if EM_HOST != EM_X86_64 && EM_HOST != EM_386
 __weak int get_arch_regnum(const char *name __maybe_unused)
 {
 	return -ENOTSUP;
 }
+#endif
 
 /* Return DWARF register number from architecture register name */
 int get_dwarf_regnum(const char *name, unsigned int machine, unsigned int flags __maybe_unused)
@@ -90,9 +100,16 @@ int get_dwarf_regnum(const char *name, unsigned int machine, unsigned int flags
 		machine = EM_HOST;
 	}
 	switch (machine) {
+#if EM_HOST != EM_X86_64 && EM_HOST != EM_386
 	case EM_HOST:
 		reg = get_arch_regnum(regname);
 		break;
+#endif
+	case EM_X86_64:
+		fallthrough;
+	case EM_386:
+		reg = get_x86_regnum(regname);
+		break;
 	default:
 		pr_err("ELF MACHINE %x is not supported.\n", machine);
 	}
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 0ef428d07bccd..6aa66c3759422 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -89,7 +89,10 @@
 #define DWARF_REG_FB  0xd3affb /* random number */
 
 #ifdef HAVE_LIBDW_SUPPORT
+#if !defined(__x86_64__) && !defined(__i386__)
 const char *get_arch_regstr(unsigned int n);
+#endif
+
 /**
  * get_dwarf_regstr() - Returns ftrace register string from DWARF regnum.
  * @n: DWARF register number.
@@ -98,7 +101,12 @@ const char *get_arch_regstr(unsigned int n);
  */
 const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int flags);
 
+int get_x86_regnum(const char *name);
+
+#if !defined(__x86_64__) && !defined(__i386__)
 int get_arch_regnum(const char *name);
+#endif
+
 /*
  * get_dwarf_regnum - Returns DWARF regnum from register name
  * name: architecture register name

From 6f8e8add5a0a551aa748c9345b80e6cad85ec829 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:45:53 -0800
Subject: [PATCH 0996/1530] perf arm64: Remove dwarf-regs.c

The file just provides the function get_arch_regstr, however, if in
the only caller get_dwarf_regstr EM_HOST is used for the EM_NONE case
the function can never be called. So remove as dead code. Tidy up the
EM_NONE cases for arm64 in dwarf-regs.c.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-9-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/arm64/util/Build        |  1 -
 tools/perf/arch/arm64/util/dwarf-regs.c | 80 -------------------------
 tools/perf/util/dwarf-regs.c            |  4 +-
 tools/perf/util/include/dwarf-regs.h    |  2 +-
 4 files changed, 3 insertions(+), 84 deletions(-)
 delete mode 100644 tools/perf/arch/arm64/util/dwarf-regs.c

diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index 4387a6d6a6c3b..a74521b79eaaa 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -4,7 +4,6 @@ perf-util-y += perf_regs.o
 perf-util-y += tsc.o
 perf-util-y += pmu.o
 perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o
-perf-util-$(CONFIG_LIBDW)     += dwarf-regs.o
 perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c
deleted file mode 100644
index 343a62fa4199d..0000000000000
--- a/tools/perf/arch/arm64/util/dwarf-regs.c
+++ /dev/null
@@ -1,80 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Mapping of DWARF debug register numbers into register names.
- *
- * Copyright (C) 2010 Will Deacon, ARM Ltd.
- */
-
-#include <errno.h>
-#include <stddef.h>
-#include <string.h>
-#include <dwarf-regs.h>
-#include <linux/stringify.h>
-
-struct regs_dwarfnum {
-	const char *name;
-	unsigned int dwarfnum;
-};
-
-#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
-#define GPR_DWARFNUM_NAME(num) \
-	{.name = __stringify(%x##num), .dwarfnum = num}
-#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
-
-/*
- * Reference:
- * http://infocenter.arm.com/help/topic/com.arm.doc.ihi0057b/IHI0057B_aadwarf64.pdf
- */
-static const struct regs_dwarfnum regdwarfnum_table[] = {
-	GPR_DWARFNUM_NAME(0),
-	GPR_DWARFNUM_NAME(1),
-	GPR_DWARFNUM_NAME(2),
-	GPR_DWARFNUM_NAME(3),
-	GPR_DWARFNUM_NAME(4),
-	GPR_DWARFNUM_NAME(5),
-	GPR_DWARFNUM_NAME(6),
-	GPR_DWARFNUM_NAME(7),
-	GPR_DWARFNUM_NAME(8),
-	GPR_DWARFNUM_NAME(9),
-	GPR_DWARFNUM_NAME(10),
-	GPR_DWARFNUM_NAME(11),
-	GPR_DWARFNUM_NAME(12),
-	GPR_DWARFNUM_NAME(13),
-	GPR_DWARFNUM_NAME(14),
-	GPR_DWARFNUM_NAME(15),
-	GPR_DWARFNUM_NAME(16),
-	GPR_DWARFNUM_NAME(17),
-	GPR_DWARFNUM_NAME(18),
-	GPR_DWARFNUM_NAME(19),
-	GPR_DWARFNUM_NAME(20),
-	GPR_DWARFNUM_NAME(21),
-	GPR_DWARFNUM_NAME(22),
-	GPR_DWARFNUM_NAME(23),
-	GPR_DWARFNUM_NAME(24),
-	GPR_DWARFNUM_NAME(25),
-	GPR_DWARFNUM_NAME(26),
-	GPR_DWARFNUM_NAME(27),
-	GPR_DWARFNUM_NAME(28),
-	GPR_DWARFNUM_NAME(29),
-	REG_DWARFNUM_NAME("%lr", 30),
-	REG_DWARFNUM_NAME("%sp", 31),
-	REG_DWARFNUM_END,
-};
-
-/**
- * get_arch_regstr() - lookup register name from it's DWARF register number
- * @n:	the DWARF register number
- *
- * get_arch_regstr() returns the name of the register in struct
- * regdwarfnum_table from it's DWARF register number. If the register is not
- * found in the table, this returns NULL;
- */
-const char *get_arch_regstr(unsigned int n)
-{
-	const struct regs_dwarfnum *roff;
-
-	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
-		if (roff->dwarfnum == n)
-			return roff->name;
-	return NULL;
-}
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index eac99a2467372..18e916c8e9937 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -32,14 +32,14 @@
 const char *get_dwarf_regstr(unsigned int n, unsigned int machine,
 			     unsigned int flags __maybe_unused)
 {
-#if EM_HOST == EM_X86_64 || EM_HOST == EM_386
+#if EM_HOST == EM_X86_64 || EM_HOST == EM_386 || EM_HOST == EM_AARCH64
 	if (machine == EM_NONE) {
 		/* Generic arch - use host arch */
 		machine = EM_HOST;
 	}
 #endif
 	switch (machine) {
-#if EM_HOST != EM_X86_64 && EM_HOST != EM_386
+#if EM_HOST != EM_X86_64 && EM_HOST != EM_386 && EM_HOST != EM_AARCH64
 	case EM_NONE:	/* Generic arch - use host arch */
 		return get_arch_regstr(n);
 #endif
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 6aa66c3759422..f976528fdfd62 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -89,7 +89,7 @@
 #define DWARF_REG_FB  0xd3affb /* random number */
 
 #ifdef HAVE_LIBDW_SUPPORT
-#if !defined(__x86_64__) && !defined(__i386__)
+#if !defined(__x86_64__) && !defined(__i386__) && !defined(__aarch64__)
 const char *get_arch_regstr(unsigned int n);
 #endif
 

From 0c0a20ecdf67b0af07ec6d6167335ef5c6e3b9ec Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:45:54 -0800
Subject: [PATCH 0997/1530] perf arm: Remove dwarf-regs.c

The file just provides the function get_arch_regstr, however, if in
the only caller get_dwarf_regstr EM_HOST is used for the EM_NONE case
the function can never be called. So remove as dead code. Tidy up the
EM_NONE cases for arm in dwarf-regs.c.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-10-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/arm/util/Build        |  2 -
 tools/perf/arch/arm/util/dwarf-regs.c | 61 ---------------------------
 tools/perf/util/dwarf-regs.c          |  4 +-
 tools/perf/util/include/dwarf-regs.h  |  2 +-
 4 files changed, 3 insertions(+), 66 deletions(-)
 delete mode 100644 tools/perf/arch/arm/util/dwarf-regs.c

diff --git a/tools/perf/arch/arm/util/Build b/tools/perf/arch/arm/util/Build
index e06fea1ea8ff7..f7a8b37d1c688 100644
--- a/tools/perf/arch/arm/util/Build
+++ b/tools/perf/arch/arm/util/Build
@@ -1,7 +1,5 @@
 perf-util-y += perf_regs.o
 
-perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
-
 perf-util-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
diff --git a/tools/perf/arch/arm/util/dwarf-regs.c b/tools/perf/arch/arm/util/dwarf-regs.c
deleted file mode 100644
index fc5f71c918020..0000000000000
--- a/tools/perf/arch/arm/util/dwarf-regs.c
+++ /dev/null
@@ -1,61 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Mapping of DWARF debug register numbers into register names.
- *
- * Copyright (C) 2010 Will Deacon, ARM Ltd.
- */
-
-#include <stddef.h>
-#include <linux/stringify.h>
-#include <dwarf-regs.h>
-
-struct pt_regs_dwarfnum {
-	const char *name;
-	unsigned int dwarfnum;
-};
-
-#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
-#define GPR_DWARFNUM_NAME(num) \
-	{.name = __stringify(%r##num), .dwarfnum = num}
-#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
-
-/*
- * Reference:
- * http://infocenter.arm.com/help/topic/com.arm.doc.ihi0040a/IHI0040A_aadwarf.pdf
- */
-static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
-	GPR_DWARFNUM_NAME(0),
-	GPR_DWARFNUM_NAME(1),
-	GPR_DWARFNUM_NAME(2),
-	GPR_DWARFNUM_NAME(3),
-	GPR_DWARFNUM_NAME(4),
-	GPR_DWARFNUM_NAME(5),
-	GPR_DWARFNUM_NAME(6),
-	GPR_DWARFNUM_NAME(7),
-	GPR_DWARFNUM_NAME(8),
-	GPR_DWARFNUM_NAME(9),
-	GPR_DWARFNUM_NAME(10),
-	REG_DWARFNUM_NAME("%fp", 11),
-	REG_DWARFNUM_NAME("%ip", 12),
-	REG_DWARFNUM_NAME("%sp", 13),
-	REG_DWARFNUM_NAME("%lr", 14),
-	REG_DWARFNUM_NAME("%pc", 15),
-	REG_DWARFNUM_END,
-};
-
-/**
- * get_arch_regstr() - lookup register name from it's DWARF register number
- * @n:	the DWARF register number
- *
- * get_arch_regstr() returns the name of the register in struct
- * regdwarfnum_table from it's DWARF register number. If the register is not
- * found in the table, this returns NULL;
- */
-const char *get_arch_regstr(unsigned int n)
-{
-	const struct pt_regs_dwarfnum *roff;
-	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
-		if (roff->dwarfnum == n)
-			return roff->name;
-	return NULL;
-}
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 18e916c8e9937..fd21f9e90e40b 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -32,14 +32,14 @@
 const char *get_dwarf_regstr(unsigned int n, unsigned int machine,
 			     unsigned int flags __maybe_unused)
 {
-#if EM_HOST == EM_X86_64 || EM_HOST == EM_386 || EM_HOST == EM_AARCH64
+#if EM_HOST == EM_X86_64 || EM_HOST == EM_386 || EM_HOST == EM_AARCH64 || EM_HOST == EM_ARM
 	if (machine == EM_NONE) {
 		/* Generic arch - use host arch */
 		machine = EM_HOST;
 	}
 #endif
 	switch (machine) {
-#if EM_HOST != EM_X86_64 && EM_HOST != EM_386 && EM_HOST != EM_AARCH64
+#if EM_HOST != EM_X86_64 && EM_HOST != EM_386 && EM_HOST != EM_AARCH64 && EM_HOST != EM_ARM
 	case EM_NONE:	/* Generic arch - use host arch */
 		return get_arch_regstr(n);
 #endif
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index f976528fdfd62..3652f9d98fe40 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -89,7 +89,7 @@
 #define DWARF_REG_FB  0xd3affb /* random number */
 
 #ifdef HAVE_LIBDW_SUPPORT
-#if !defined(__x86_64__) && !defined(__i386__) && !defined(__aarch64__)
+#if !defined(__x86_64__) && !defined(__i386__) && !defined(__aarch64__) && !defined(__arm__)
 const char *get_arch_regstr(unsigned int n);
 #endif
 

From d4a0c4f22121f4ec635c726727a0d1a9f5f9a7af Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:45:55 -0800
Subject: [PATCH 0998/1530] perf dwarf-regs: Move csky dwarf-regs out of arch

Move arch/csky/util/dwarf-regs.c to util/dwarf-regs-csky.c and compile
in unconditionally. To avoid get_arch_regstr being duplicated, rename
to get_csky_regstr and add to get_dwarf_regstr switch.

Update #ifdefs to allow ABI V1 and V2 tables at the same
time. Determine the table from the ELF flags.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-11-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/csky/util/Build               |  1 -
 tools/perf/util/Build                         |  1 +
 .../dwarf-regs.c => util/dwarf-regs-csky.c}   | 19 ++++++++++---------
 tools/perf/util/dwarf-regs.c                  | 11 +++++++----
 tools/perf/util/include/dwarf-regs.h          |  2 ++
 5 files changed, 20 insertions(+), 14 deletions(-)
 rename tools/perf/{arch/csky/util/dwarf-regs.c => util/dwarf-regs-csky.c} (74%)

diff --git a/tools/perf/arch/csky/util/Build b/tools/perf/arch/csky/util/Build
index 1325310cab6a4..5e6ea82c42021 100644
--- a/tools/perf/arch/csky/util/Build
+++ b/tools/perf/arch/csky/util/Build
@@ -1,4 +1,3 @@
 perf-util-y += perf_regs.o
 
-perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index ec0994b6b0114..f33b59d5a9f0a 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -204,6 +204,7 @@ endif
 perf-util-$(CONFIG_LIBDW) += probe-finder.o
 perf-util-$(CONFIG_LIBDW) += dwarf-aux.o
 perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
+perf-util-$(CONFIG_LIBDW) += dwarf-regs-csky.o
 perf-util-$(CONFIG_LIBDW) += dwarf-regs-x86.o
 perf-util-$(CONFIG_LIBDW) += debuginfo.o
 perf-util-$(CONFIG_LIBDW) += annotate-data.o
diff --git a/tools/perf/arch/csky/util/dwarf-regs.c b/tools/perf/util/dwarf-regs-csky.c
similarity index 74%
rename from tools/perf/arch/csky/util/dwarf-regs.c
rename to tools/perf/util/dwarf-regs-csky.c
index ca86ecaeacbb5..d38ef1f07f3e3 100644
--- a/tools/perf/arch/csky/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs-csky.c
@@ -5,9 +5,8 @@
 #include <stddef.h>
 #include <dwarf-regs.h>
 
-#if defined(__CSKYABIV2__)
-#define CSKY_MAX_REGS 73
-const char *csky_dwarf_regs_table[CSKY_MAX_REGS] = {
+#define CSKY_ABIV2_MAX_REGS 73
+const char *csky_dwarf_regs_table_abiv2[CSKY_ABIV2_MAX_REGS] = {
 	/* r0 ~ r8 */
 	"%a0", "%a1", "%a2", "%a3", "%regs0", "%regs1", "%regs2", "%regs3",
 	/* r9 ~ r15 */
@@ -26,9 +25,9 @@ const char *csky_dwarf_regs_table[CSKY_MAX_REGS] = {
 	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 	"%epc",
 };
-#else
-#define CSKY_MAX_REGS 57
-const char *csky_dwarf_regs_table[CSKY_MAX_REGS] = {
+
+#define CSKY_ABIV1_MAX_REGS 57
+const char *csky_dwarf_regs_table_abiv1[CSKY_ABIV1_MAX_REGS] = {
 	/* r0 ~ r8 */
 	"%sp", "%regs9", "%a0", "%a1", "%a2", "%a3", "%regs0", "%regs1",
 	/* r9 ~ r15 */
@@ -41,9 +40,11 @@ const char *csky_dwarf_regs_table[CSKY_MAX_REGS] = {
 	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 	"%epc",
 };
-#endif
 
-const char *get_arch_regstr(unsigned int n)
+const char *get_csky_regstr(unsigned int n, unsigned int flags)
 {
-	return (n < CSKY_MAX_REGS) ? csky_dwarf_regs_table[n] : NULL;
+	if (flags & EF_CSKY_ABIV2)
+		return (n < CSKY_ABIV2_MAX_REGS) ? csky_dwarf_regs_table_abiv2[n] : NULL;
+
+	return (n < CSKY_ABIV1_MAX_REGS) ? csky_dwarf_regs_table_abiv1[n] : NULL;
 }
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index fd21f9e90e40b..9a76f83af62c7 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -29,17 +29,18 @@
 #define __get_dwarf_regstr(tbl, n) (((n) < ARRAY_SIZE(tbl)) ? (tbl)[(n)] : NULL)
 
 /* Return architecture dependent register string (for kprobe-tracer) */
-const char *get_dwarf_regstr(unsigned int n, unsigned int machine,
-			     unsigned int flags __maybe_unused)
+const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int flags)
 {
-#if EM_HOST == EM_X86_64 || EM_HOST == EM_386 || EM_HOST == EM_AARCH64 || EM_HOST == EM_ARM
+#if EM_HOST == EM_X86_64 || EM_HOST == EM_386 || EM_HOST == EM_AARCH64 || EM_HOST == EM_ARM \
+    || EM_HOST == EM_CSKY
 	if (machine == EM_NONE) {
 		/* Generic arch - use host arch */
 		machine = EM_HOST;
 	}
 #endif
 	switch (machine) {
-#if EM_HOST != EM_X86_64 && EM_HOST != EM_386 && EM_HOST != EM_AARCH64 && EM_HOST != EM_ARM
+#if EM_HOST != EM_X86_64 && EM_HOST != EM_386 && EM_HOST != EM_AARCH64 && EM_HOST != EM_ARM \
+    && EM_HOST != EM_CSKY
 	case EM_NONE:	/* Generic arch - use host arch */
 		return get_arch_regstr(n);
 #endif
@@ -51,6 +52,8 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine,
 		return __get_dwarf_regstr(arm_regstr_tbl, n);
 	case EM_AARCH64:
 		return __get_dwarf_regstr(aarch64_regstr_tbl, n);
+	case EM_CSKY:
+		return get_csky_regstr(n, flags);
 	case EM_SH:
 		return __get_dwarf_regstr(sh_regstr_tbl, n);
 	case EM_S390:
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 3652f9d98fe40..0641c2942b016 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -93,6 +93,8 @@
 const char *get_arch_regstr(unsigned int n);
 #endif
 
+const char *get_csky_regstr(unsigned int n, unsigned int flags);
+
 /**
  * get_dwarf_regstr() - Returns ftrace register string from DWARF regnum.
  * @n: DWARF register number.

From 1d37bd8366d8cc99d8dbb1d39b285db8b429ec69 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:45:56 -0800
Subject: [PATCH 0999/1530] perf loongarch: Remove dwarf-regs.c

The file just provides the function get_arch_regstr, however, if in
the only caller get_dwarf_regstr EM_HOST is used for the EM_NONE case
the function can never be called. So remove as dead code. Tidy up the
EM_NONE cases for loongarch in dwarf-regs.c.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-12-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/loongarch/util/Build        |  1 -
 tools/perf/arch/loongarch/util/dwarf-regs.c | 34 ---------------------
 tools/perf/util/dwarf-regs.c                |  4 +--
 tools/perf/util/include/dwarf-regs.h        |  3 +-
 4 files changed, 4 insertions(+), 38 deletions(-)
 delete mode 100644 tools/perf/arch/loongarch/util/dwarf-regs.c

diff --git a/tools/perf/arch/loongarch/util/Build b/tools/perf/arch/loongarch/util/Build
index 06ff95394921c..0aa31986ecb5b 100644
--- a/tools/perf/arch/loongarch/util/Build
+++ b/tools/perf/arch/loongarch/util/Build
@@ -1,7 +1,6 @@
 perf-util-y += header.o
 perf-util-y += perf_regs.o
 
-perf-util-$(CONFIG_LIBDW)     += dwarf-regs.o
 perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o
diff --git a/tools/perf/arch/loongarch/util/dwarf-regs.c b/tools/perf/arch/loongarch/util/dwarf-regs.c
deleted file mode 100644
index bee08fdcf2fd8..0000000000000
--- a/tools/perf/arch/loongarch/util/dwarf-regs.c
+++ /dev/null
@@ -1,34 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * dwarf-regs.c : Mapping of DWARF debug register numbers into register names.
- *
- * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
- */
-
-#include <stdio.h>
-#include <errno.h> /* for EINVAL */
-#include <string.h> /* for strcmp */
-#include <dwarf-regs.h>
-
-struct pt_regs_dwarfnum {
-	const char *name;
-	unsigned int dwarfnum;
-};
-
-static struct pt_regs_dwarfnum loongarch_gpr_table[] = {
-	{"%r0", 0}, {"%r1", 1}, {"%r2", 2}, {"%r3", 3},
-	{"%r4", 4}, {"%r5", 5}, {"%r6", 6}, {"%r7", 7},
-	{"%r8", 8}, {"%r9", 9}, {"%r10", 10}, {"%r11", 11},
-	{"%r12", 12}, {"%r13", 13}, {"%r14", 14}, {"%r15", 15},
-	{"%r16", 16}, {"%r17", 17}, {"%r18", 18}, {"%r19", 19},
-	{"%r20", 20}, {"%r21", 21}, {"%r22", 22}, {"%r23", 23},
-	{"%r24", 24}, {"%r25", 25}, {"%r26", 26}, {"%r27", 27},
-	{"%r28", 28}, {"%r29", 29}, {"%r30", 30}, {"%r31", 31},
-	{NULL, 0}
-};
-
-const char *get_arch_regstr(unsigned int n)
-{
-	n %= 32;
-	return loongarch_gpr_table[n].name;
-}
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 9a76f83af62c7..efc41d0fbee98 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -32,7 +32,7 @@
 const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int flags)
 {
 #if EM_HOST == EM_X86_64 || EM_HOST == EM_386 || EM_HOST == EM_AARCH64 || EM_HOST == EM_ARM \
-    || EM_HOST == EM_CSKY
+    || EM_HOST == EM_CSKY || EM_HOST == EM_LOONGARCH
 	if (machine == EM_NONE) {
 		/* Generic arch - use host arch */
 		machine = EM_HOST;
@@ -40,7 +40,7 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int
 #endif
 	switch (machine) {
 #if EM_HOST != EM_X86_64 && EM_HOST != EM_386 && EM_HOST != EM_AARCH64 && EM_HOST != EM_ARM \
-    && EM_HOST != EM_CSKY
+    && EM_HOST != EM_CSKY && EM_HOST != EM_LOONGARCH
 	case EM_NONE:	/* Generic arch - use host arch */
 		return get_arch_regstr(n);
 #endif
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 0641c2942b016..4e591379f3670 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -89,7 +89,8 @@
 #define DWARF_REG_FB  0xd3affb /* random number */
 
 #ifdef HAVE_LIBDW_SUPPORT
-#if !defined(__x86_64__) && !defined(__i386__) && !defined(__aarch64__) && !defined(__arm__)
+#if !defined(__x86_64__) && !defined(__i386__) && !defined(__aarch64__) && !defined(__arm__) \
+    && !defined(__loongarch__)
 const char *get_arch_regstr(unsigned int n);
 #endif
 

From 8a768a2f65921c497e796e0d91170595a3c60abc Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:45:57 -0800
Subject: [PATCH 1000/1530] perf mips: Remove dwarf-regs.c

The file just provides the function get_arch_regstr, however, if in
the only caller get_dwarf_regstr EM_HOST is used for the EM_NONE case
the function can never be called. So remove as dead code. Tidy up the
EM_NONE cases for mips in dwarf-regs.c.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-13-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/mips/util/Build        |  1 -
 tools/perf/arch/mips/util/dwarf-regs.c | 38 --------------------------
 tools/perf/util/dwarf-regs.c           |  4 +--
 tools/perf/util/include/dwarf-regs.h   |  2 +-
 4 files changed, 3 insertions(+), 42 deletions(-)
 delete mode 100644 tools/perf/arch/mips/util/dwarf-regs.c

diff --git a/tools/perf/arch/mips/util/Build b/tools/perf/arch/mips/util/Build
index b328109fc16c6..691fa2051958a 100644
--- a/tools/perf/arch/mips/util/Build
+++ b/tools/perf/arch/mips/util/Build
@@ -1,3 +1,2 @@
 perf-util-y += perf_regs.o
-perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
 perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
diff --git a/tools/perf/arch/mips/util/dwarf-regs.c b/tools/perf/arch/mips/util/dwarf-regs.c
deleted file mode 100644
index 25c13a91c2a75..0000000000000
--- a/tools/perf/arch/mips/util/dwarf-regs.c
+++ /dev/null
@@ -1,38 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * dwarf-regs.c : Mapping of DWARF debug register numbers into register names.
- *
- * Copyright (C) 2013 Cavium, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#include <stdio.h>
-#include <dwarf-regs.h>
-
-static const char *mips_gpr_names[32] = {
-	"$0", "$1", "$2", "$3", "$4", "$5", "$6", "$7", "$8", "$9",
-	"$10", "$11", "$12", "$13", "$14", "$15", "$16", "$17", "$18", "$19",
-	"$20", "$21", "$22", "$23", "$24", "$25", "$26", "$27", "$28", "$29",
-	"$30", "$31"
-};
-
-const char *get_arch_regstr(unsigned int n)
-{
-	if (n < 32)
-		return mips_gpr_names[n];
-	if (n == 64)
-		return "hi";
-	if (n == 65)
-		return "lo";
-	return NULL;
-}
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index efc41d0fbee98..d536964df43cd 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -32,7 +32,7 @@
 const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int flags)
 {
 #if EM_HOST == EM_X86_64 || EM_HOST == EM_386 || EM_HOST == EM_AARCH64 || EM_HOST == EM_ARM \
-    || EM_HOST == EM_CSKY || EM_HOST == EM_LOONGARCH
+    || EM_HOST == EM_CSKY || EM_HOST == EM_LOONGARCH || EM_HOST == EM_MIPS
 	if (machine == EM_NONE) {
 		/* Generic arch - use host arch */
 		machine = EM_HOST;
@@ -40,7 +40,7 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int
 #endif
 	switch (machine) {
 #if EM_HOST != EM_X86_64 && EM_HOST != EM_386 && EM_HOST != EM_AARCH64 && EM_HOST != EM_ARM \
-    && EM_HOST != EM_CSKY && EM_HOST != EM_LOONGARCH
+    && EM_HOST != EM_CSKY && EM_HOST != EM_LOONGARCH && EM_HOST != EM_MIPS
 	case EM_NONE:	/* Generic arch - use host arch */
 		return get_arch_regstr(n);
 #endif
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 4e591379f3670..55f21d8082a21 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -90,7 +90,7 @@
 
 #ifdef HAVE_LIBDW_SUPPORT
 #if !defined(__x86_64__) && !defined(__i386__) && !defined(__aarch64__) && !defined(__arm__) \
-    && !defined(__loongarch__)
+    && !defined(__loongarch__) && !defined(__mips__)
 const char *get_arch_regstr(unsigned int n);
 #endif
 

From 285b523c2da2e71f529e477a64b09f2e719f9d6f Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:45:58 -0800
Subject: [PATCH 1001/1530] perf dwarf-regs: Move powerpc dwarf-regs out of
 arch

Move arch/powerpc/util/dwarf-regs.c to util/dwarf-regs-powerpc.c and
compile in unconditionally. get_arch_regstr is redundant when EM_NONE
is treated as EM_HOST so remove and update dwarf-regs.c conditions.
Make get_powerpc_regs unconditionally available whwn libdw is.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-14-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/powerpc/util/Build        |   1 -
 tools/perf/arch/powerpc/util/dwarf-regs.c | 141 ----------------------
 tools/perf/util/Build                     |   1 +
 tools/perf/util/dwarf-regs-powerpc.c      |  61 ++++++++++
 tools/perf/util/dwarf-regs.c              |   6 +-
 tools/perf/util/include/dwarf-regs.h      |   9 +-
 6 files changed, 70 insertions(+), 149 deletions(-)
 delete mode 100644 tools/perf/arch/powerpc/util/dwarf-regs.c
 create mode 100644 tools/perf/util/dwarf-regs-powerpc.c

diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 3d979480a1888..ed82715080f96 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -7,7 +7,6 @@ perf-util-y += sym-handling.o
 perf-util-y += evsel.o
 perf-util-y += event.o
 
-perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
 perf-util-$(CONFIG_LIBDW) += skip-callchain-idx.o
 
 perf-util-$(CONFIG_LIBUNWIND) += unwind-libunwind.o
diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c
deleted file mode 100644
index 23846c59a5222..0000000000000
--- a/tools/perf/arch/powerpc/util/dwarf-regs.c
+++ /dev/null
@@ -1,141 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Mapping of DWARF debug register numbers into register names.
- *
- * Copyright (C) 2010 Ian Munsie, IBM Corporation.
- */
-
-#include <stddef.h>
-#include <errno.h>
-#include <string.h>
-#include <dwarf-regs.h>
-#include <linux/kernel.h>
-#include <linux/stringify.h>
-
-struct regs_dwarfnum {
-	const char *name;
-	unsigned int dwarfnum;
-};
-
-#define REG_DWARFNUM_NAME(r, num)					\
-	{.name = __stringify(%)__stringify(r), .dwarfnum = num}
-#define GPR_DWARFNUM_NAME(num)						\
-	{.name = __stringify(%gpr##num), .dwarfnum = num}
-#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
-
-/*
- * Reference:
- * http://refspecs.linuxfoundation.org/ELF/ppc64/PPC-elf64abi-1.9.html
- */
-static const struct regs_dwarfnum regdwarfnum_table[] = {
-	GPR_DWARFNUM_NAME(0),
-	GPR_DWARFNUM_NAME(1),
-	GPR_DWARFNUM_NAME(2),
-	GPR_DWARFNUM_NAME(3),
-	GPR_DWARFNUM_NAME(4),
-	GPR_DWARFNUM_NAME(5),
-	GPR_DWARFNUM_NAME(6),
-	GPR_DWARFNUM_NAME(7),
-	GPR_DWARFNUM_NAME(8),
-	GPR_DWARFNUM_NAME(9),
-	GPR_DWARFNUM_NAME(10),
-	GPR_DWARFNUM_NAME(11),
-	GPR_DWARFNUM_NAME(12),
-	GPR_DWARFNUM_NAME(13),
-	GPR_DWARFNUM_NAME(14),
-	GPR_DWARFNUM_NAME(15),
-	GPR_DWARFNUM_NAME(16),
-	GPR_DWARFNUM_NAME(17),
-	GPR_DWARFNUM_NAME(18),
-	GPR_DWARFNUM_NAME(19),
-	GPR_DWARFNUM_NAME(20),
-	GPR_DWARFNUM_NAME(21),
-	GPR_DWARFNUM_NAME(22),
-	GPR_DWARFNUM_NAME(23),
-	GPR_DWARFNUM_NAME(24),
-	GPR_DWARFNUM_NAME(25),
-	GPR_DWARFNUM_NAME(26),
-	GPR_DWARFNUM_NAME(27),
-	GPR_DWARFNUM_NAME(28),
-	GPR_DWARFNUM_NAME(29),
-	GPR_DWARFNUM_NAME(30),
-	GPR_DWARFNUM_NAME(31),
-	REG_DWARFNUM_NAME(msr,   66),
-	REG_DWARFNUM_NAME(ctr,   109),
-	REG_DWARFNUM_NAME(link,  108),
-	REG_DWARFNUM_NAME(xer,   101),
-	REG_DWARFNUM_NAME(dar,   119),
-	REG_DWARFNUM_NAME(dsisr, 118),
-	REG_DWARFNUM_END,
-};
-
-/**
- * get_arch_regstr() - lookup register name from it's DWARF register number
- * @n:	the DWARF register number
- *
- * get_arch_regstr() returns the name of the register in struct
- * regdwarfnum_table from it's DWARF register number. If the register is not
- * found in the table, this returns NULL;
- */
-const char *get_arch_regstr(unsigned int n)
-{
-	const struct regs_dwarfnum *roff;
-
-	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
-		if (roff->dwarfnum == n)
-			return roff->name;
-	return NULL;
-}
-
-#define PPC_OP(op)	(((op) >> 26) & 0x3F)
-#define PPC_RA(a)	(((a) >> 16) & 0x1f)
-#define PPC_RT(t)	(((t) >> 21) & 0x1f)
-#define PPC_RB(b)	(((b) >> 11) & 0x1f)
-#define PPC_D(D)	((D) & 0xfffe)
-#define PPC_DS(DS)	((DS) & 0xfffc)
-#define OP_LD	58
-#define OP_STD	62
-
-static int get_source_reg(u32 raw_insn)
-{
-	return PPC_RA(raw_insn);
-}
-
-static int get_target_reg(u32 raw_insn)
-{
-	return PPC_RT(raw_insn);
-}
-
-static int get_offset_opcode(u32 raw_insn)
-{
-	int opcode = PPC_OP(raw_insn);
-
-	/* DS- form */
-	if ((opcode == OP_LD) || (opcode == OP_STD))
-		return PPC_DS(raw_insn);
-	else
-		return PPC_D(raw_insn);
-}
-
-/*
- * Fills the required fields for op_loc depending on if it
- * is a source or target.
- * D form: ins RT,D(RA) -> src_reg1 = RA, offset = D, dst_reg1 = RT
- * DS form: ins RT,DS(RA) -> src_reg1 = RA, offset = DS, dst_reg1 = RT
- * X form: ins RT,RA,RB -> src_reg1 = RA, src_reg2 = RB, dst_reg1 = RT
- */
-void get_powerpc_regs(u32 raw_insn, int is_source,
-		struct annotated_op_loc *op_loc)
-{
-	if (is_source)
-		op_loc->reg1 = get_source_reg(raw_insn);
-	else
-		op_loc->reg1 = get_target_reg(raw_insn);
-
-	if (op_loc->multi_regs)
-		op_loc->reg2 = PPC_RB(raw_insn);
-
-	/* TODO: Implement offset handling for X Form */
-	if ((op_loc->mem_ref) && (PPC_OP(raw_insn) != 31))
-		op_loc->offset = get_offset_opcode(raw_insn);
-}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index f33b59d5a9f0a..c06d2ee9024c6 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -205,6 +205,7 @@ perf-util-$(CONFIG_LIBDW) += probe-finder.o
 perf-util-$(CONFIG_LIBDW) += dwarf-aux.o
 perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
 perf-util-$(CONFIG_LIBDW) += dwarf-regs-csky.o
+perf-util-$(CONFIG_LIBDW) += dwarf-regs-powerpc.o
 perf-util-$(CONFIG_LIBDW) += dwarf-regs-x86.o
 perf-util-$(CONFIG_LIBDW) += debuginfo.o
 perf-util-$(CONFIG_LIBDW) += annotate-data.o
diff --git a/tools/perf/util/dwarf-regs-powerpc.c b/tools/perf/util/dwarf-regs-powerpc.c
new file mode 100644
index 0000000000000..caf77a234c785
--- /dev/null
+++ b/tools/perf/util/dwarf-regs-powerpc.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2010 Ian Munsie, IBM Corporation.
+ */
+
+#include <dwarf-regs.h>
+
+#define PPC_OP(op)	(((op) >> 26) & 0x3F)
+#define PPC_RA(a)	(((a) >> 16) & 0x1f)
+#define PPC_RT(t)	(((t) >> 21) & 0x1f)
+#define PPC_RB(b)	(((b) >> 11) & 0x1f)
+#define PPC_D(D)	((D) & 0xfffe)
+#define PPC_DS(DS)	((DS) & 0xfffc)
+#define OP_LD	58
+#define OP_STD	62
+
+static int get_source_reg(u32 raw_insn)
+{
+	return PPC_RA(raw_insn);
+}
+
+static int get_target_reg(u32 raw_insn)
+{
+	return PPC_RT(raw_insn);
+}
+
+static int get_offset_opcode(u32 raw_insn)
+{
+	int opcode = PPC_OP(raw_insn);
+
+	/* DS- form */
+	if ((opcode == OP_LD) || (opcode == OP_STD))
+		return PPC_DS(raw_insn);
+	else
+		return PPC_D(raw_insn);
+}
+
+/*
+ * Fills the required fields for op_loc depending on if it
+ * is a source or target.
+ * D form: ins RT,D(RA) -> src_reg1 = RA, offset = D, dst_reg1 = RT
+ * DS form: ins RT,DS(RA) -> src_reg1 = RA, offset = DS, dst_reg1 = RT
+ * X form: ins RT,RA,RB -> src_reg1 = RA, src_reg2 = RB, dst_reg1 = RT
+ */
+void get_powerpc_regs(u32 raw_insn, int is_source,
+		struct annotated_op_loc *op_loc)
+{
+	if (is_source)
+		op_loc->reg1 = get_source_reg(raw_insn);
+	else
+		op_loc->reg1 = get_target_reg(raw_insn);
+
+	if (op_loc->multi_regs)
+		op_loc->reg2 = PPC_RB(raw_insn);
+
+	/* TODO: Implement offset handling for X Form */
+	if ((op_loc->mem_ref) && (PPC_OP(raw_insn) != 31))
+		op_loc->offset = get_offset_opcode(raw_insn);
+}
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index d536964df43cd..3d98c2bf60350 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -32,7 +32,8 @@
 const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int flags)
 {
 #if EM_HOST == EM_X86_64 || EM_HOST == EM_386 || EM_HOST == EM_AARCH64 || EM_HOST == EM_ARM \
-    || EM_HOST == EM_CSKY || EM_HOST == EM_LOONGARCH || EM_HOST == EM_MIPS
+    || EM_HOST == EM_CSKY || EM_HOST == EM_LOONGARCH || EM_HOST == EM_MIPS || EM_HOST == EM_PPC \
+    || EM_HOST == EM_PPC64
 	if (machine == EM_NONE) {
 		/* Generic arch - use host arch */
 		machine = EM_HOST;
@@ -40,7 +41,8 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int
 #endif
 	switch (machine) {
 #if EM_HOST != EM_X86_64 && EM_HOST != EM_386 && EM_HOST != EM_AARCH64 && EM_HOST != EM_ARM \
-    && EM_HOST != EM_CSKY && EM_HOST != EM_LOONGARCH && EM_HOST != EM_MIPS
+    && EM_HOST != EM_CSKY && EM_HOST != EM_LOONGARCH && EM_HOST != EM_MIPS && EM_HOST != EM_PPC \
+    && EM_HOST != EM_PPC64
 	case EM_NONE:	/* Generic arch - use host arch */
 		return get_arch_regstr(n);
 #endif
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 55f21d8082a21..e47c4697da362 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -90,7 +90,8 @@
 
 #ifdef HAVE_LIBDW_SUPPORT
 #if !defined(__x86_64__) && !defined(__i386__) && !defined(__aarch64__) && !defined(__arm__) \
-    && !defined(__loongarch__) && !defined(__mips__)
+    && !defined(__loongarch__) && !defined(__mips__) && !defined(__powerpc__) \
+    && !defined(__powerpc64__)
 const char *get_arch_regstr(unsigned int n);
 #endif
 
@@ -117,6 +118,8 @@ int get_arch_regnum(const char *name);
  */
 int get_dwarf_regnum(const char *name, unsigned int machine, unsigned int flags);
 
+void get_powerpc_regs(u32 raw_insn, int is_source, struct annotated_op_loc *op_loc);
+
 #else /* HAVE_LIBDW_SUPPORT */
 
 static inline int get_dwarf_regnum(const char *name __maybe_unused,
@@ -125,16 +128,12 @@ static inline int get_dwarf_regnum(const char *name __maybe_unused,
 {
 	return -1;
 }
-#endif
 
-#if !defined(__powerpc__) || !defined(HAVE_LIBDW_SUPPORT)
 static inline void get_powerpc_regs(u32 raw_insn __maybe_unused, int is_source __maybe_unused,
 		struct annotated_op_loc *op_loc __maybe_unused)
 {
 	return;
 }
-#else
-void get_powerpc_regs(u32 raw_insn, int is_source, struct annotated_op_loc *op_loc);
 #endif
 
 #endif

From a90c4519186dfc083cbc47b62dfde421129c4fd4 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:45:59 -0800
Subject: [PATCH 1002/1530] perf riscv: Remove dwarf-regs.c and add
 dwarf-regs-table.h

The file just provides the function get_arch_regstr, however, if in
the only caller get_dwarf_regstr EM_HOST is used for the EM_NONE case,
and the register table is provided in a header file, the function can
never be called. So remove as dead code. Tidy up the EM_NONE cases for
riscv in dwarf-regs.c.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-15-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../dwarf-regs-table.h}                       | 32 ++++---------------
 tools/perf/arch/riscv/util/Build              |  1 -
 tools/perf/util/dwarf-regs.c                  |  7 ++--
 tools/perf/util/include/dwarf-regs.h          |  2 +-
 4 files changed, 12 insertions(+), 30 deletions(-)
 rename tools/perf/arch/riscv/{util/dwarf-regs.c => include/dwarf-regs-table.h} (56%)

diff --git a/tools/perf/arch/riscv/util/dwarf-regs.c b/tools/perf/arch/riscv/include/dwarf-regs-table.h
similarity index 56%
rename from tools/perf/arch/riscv/util/dwarf-regs.c
rename to tools/perf/arch/riscv/include/dwarf-regs-table.h
index a9c4402ae57ec..a45b63a6d5a8e 100644
--- a/tools/perf/arch/riscv/util/dwarf-regs.c
+++ b/tools/perf/arch/riscv/include/dwarf-regs-table.h
@@ -1,23 +1,10 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
- * Mapping of DWARF debug register numbers into register names.
- */
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
 
-#include <stddef.h>
-#include <errno.h> /* for EINVAL */
-#include <string.h> /* for strcmp */
-#include <dwarf-regs.h>
+#define REG_DWARFNUM_NAME(reg, idx)	[idx] = "%" #reg
 
-struct regs_dwarfnum {
-	const char *name;
-	unsigned int dwarfnum;
-};
-
-#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
-#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
-
-struct regs_dwarfnum riscv_dwarf_regs_table[] = {
+static const char * const riscv_regstr_tbl[] = {
 	REG_DWARFNUM_NAME("%zero", 0),
 	REG_DWARFNUM_NAME("%ra", 1),
 	REG_DWARFNUM_NAME("%sp", 2),
@@ -50,13 +37,6 @@ struct regs_dwarfnum riscv_dwarf_regs_table[] = {
 	REG_DWARFNUM_NAME("%t4", 29),
 	REG_DWARFNUM_NAME("%t5", 30),
 	REG_DWARFNUM_NAME("%t6", 31),
-	REG_DWARFNUM_END,
 };
 
-#define RISCV_MAX_REGS ((sizeof(riscv_dwarf_regs_table) / \
-		 sizeof(riscv_dwarf_regs_table[0])) - 1)
-
-const char *get_arch_regstr(unsigned int n)
-{
-	return (n < RISCV_MAX_REGS) ? riscv_dwarf_regs_table[n].name : NULL;
-}
+#endif
diff --git a/tools/perf/arch/riscv/util/Build b/tools/perf/arch/riscv/util/Build
index 8f93091b83457..58a672246024d 100644
--- a/tools/perf/arch/riscv/util/Build
+++ b/tools/perf/arch/riscv/util/Build
@@ -2,5 +2,4 @@ perf-util-y += perf_regs.o
 perf-util-y += header.o
 
 perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o
-perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 3d98c2bf60350..2c6b197556dd1 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -20,6 +20,7 @@
 #include "../arch/arm64/include/dwarf-regs-table.h"
 #include "../arch/sh/include/dwarf-regs-table.h"
 #include "../arch/powerpc/include/dwarf-regs-table.h"
+#include "../arch/riscv/include/dwarf-regs-table.h"
 #include "../arch/s390/include/dwarf-regs-table.h"
 #include "../arch/sparc/include/dwarf-regs-table.h"
 #include "../arch/xtensa/include/dwarf-regs-table.h"
@@ -33,7 +34,7 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int
 {
 #if EM_HOST == EM_X86_64 || EM_HOST == EM_386 || EM_HOST == EM_AARCH64 || EM_HOST == EM_ARM \
     || EM_HOST == EM_CSKY || EM_HOST == EM_LOONGARCH || EM_HOST == EM_MIPS || EM_HOST == EM_PPC \
-    || EM_HOST == EM_PPC64
+    || EM_HOST == EM_PPC64 || EM_HOST == EM_RISCV
 	if (machine == EM_NONE) {
 		/* Generic arch - use host arch */
 		machine = EM_HOST;
@@ -42,7 +43,7 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int
 	switch (machine) {
 #if EM_HOST != EM_X86_64 && EM_HOST != EM_386 && EM_HOST != EM_AARCH64 && EM_HOST != EM_ARM \
     && EM_HOST != EM_CSKY && EM_HOST != EM_LOONGARCH && EM_HOST != EM_MIPS && EM_HOST != EM_PPC \
-    && EM_HOST != EM_PPC64
+    && EM_HOST != EM_PPC64 && EM_HOST != EM_RISCV
 	case EM_NONE:	/* Generic arch - use host arch */
 		return get_arch_regstr(n);
 #endif
@@ -63,6 +64,8 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int
 	case EM_PPC:
 	case EM_PPC64:
 		return __get_dwarf_regstr(powerpc_regstr_tbl, n);
+	case EM_RISCV:
+		return __get_dwarf_regstr(riscv_regstr_tbl, n);
 	case EM_SPARC:
 	case EM_SPARCV9:
 		return __get_dwarf_regstr(sparc_regstr_tbl, n);
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index e47c4697da362..28075de8bcf46 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -91,7 +91,7 @@
 #ifdef HAVE_LIBDW_SUPPORT
 #if !defined(__x86_64__) && !defined(__i386__) && !defined(__aarch64__) && !defined(__arm__) \
     && !defined(__loongarch__) && !defined(__mips__) && !defined(__powerpc__) \
-    && !defined(__powerpc64__)
+    && !defined(__powerpc64__) && !defined(__riscv__)
 const char *get_arch_regstr(unsigned int n);
 #endif
 

From b232b704a78151262de55d3205f4cf71b6230089 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:46:00 -0800
Subject: [PATCH 1003/1530] perf s390: Remove dwarf-regs.c

The file just provides the function get_arch_regstr, however, if in
the only caller get_dwarf_regstr EM_HOST is used for the EM_NONE case
the function can never be called. So remove as dead code. Tidy up the
EM_NONE cases for s390 in dwarf-regs.c.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-16-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/s390/util/Build        |  1 -
 tools/perf/arch/s390/util/dwarf-regs.c | 16 ----------------
 tools/perf/util/dwarf-regs.c           |  4 ++--
 tools/perf/util/include/dwarf-regs.h   |  2 +-
 4 files changed, 3 insertions(+), 20 deletions(-)
 delete mode 100644 tools/perf/arch/s390/util/dwarf-regs.c

diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build
index 787410f99bb32..736c0ad091943 100644
--- a/tools/perf/arch/s390/util/Build
+++ b/tools/perf/arch/s390/util/Build
@@ -2,7 +2,6 @@ perf-util-y += header.o
 perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o
 perf-util-y += perf_regs.o
 
-perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
 perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
 perf-util-y += machine.o
diff --git a/tools/perf/arch/s390/util/dwarf-regs.c b/tools/perf/arch/s390/util/dwarf-regs.c
deleted file mode 100644
index 5bcf3192623a5..0000000000000
--- a/tools/perf/arch/s390/util/dwarf-regs.c
+++ /dev/null
@@ -1,16 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Mapping of DWARF debug register numbers into register names.
- *
- * Copyright IBM Corp. 2010, 2017
- * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
- *
- */
-
-#include <linux/kernel.h>
-#include "dwarf-regs-table.h"
-
-const char *get_arch_regstr(unsigned int n)
-{
-	return (n >= ARRAY_SIZE(s390_dwarf_regs)) ? NULL : s390_dwarf_regs[n];
-}
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 2c6b197556dd1..1649fc07f4f52 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -34,7 +34,7 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int
 {
 #if EM_HOST == EM_X86_64 || EM_HOST == EM_386 || EM_HOST == EM_AARCH64 || EM_HOST == EM_ARM \
     || EM_HOST == EM_CSKY || EM_HOST == EM_LOONGARCH || EM_HOST == EM_MIPS || EM_HOST == EM_PPC \
-    || EM_HOST == EM_PPC64 || EM_HOST == EM_RISCV
+    || EM_HOST == EM_PPC64 || EM_HOST == EM_RISCV || EM_HOST == EM_S390
 	if (machine == EM_NONE) {
 		/* Generic arch - use host arch */
 		machine = EM_HOST;
@@ -43,7 +43,7 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int
 	switch (machine) {
 #if EM_HOST != EM_X86_64 && EM_HOST != EM_386 && EM_HOST != EM_AARCH64 && EM_HOST != EM_ARM \
     && EM_HOST != EM_CSKY && EM_HOST != EM_LOONGARCH && EM_HOST != EM_MIPS && EM_HOST != EM_PPC \
-    && EM_HOST != EM_PPC64 && EM_HOST != EM_RISCV
+    && EM_HOST != EM_PPC64 && EM_HOST != EM_RISCV && EM_HOST != EM_S390
 	case EM_NONE:	/* Generic arch - use host arch */
 		return get_arch_regstr(n);
 #endif
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 28075de8bcf46..086b537690d78 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -91,7 +91,7 @@
 #ifdef HAVE_LIBDW_SUPPORT
 #if !defined(__x86_64__) && !defined(__i386__) && !defined(__aarch64__) && !defined(__arm__) \
     && !defined(__loongarch__) && !defined(__mips__) && !defined(__powerpc__) \
-    && !defined(__powerpc64__) && !defined(__riscv__)
+    && !defined(__powerpc64__) && !defined(__riscv__) && !defined(__s390x__)
 const char *get_arch_regstr(unsigned int n);
 #endif
 

From 04150f29e212fb0d9a908bf37f81722c39ca6f3b Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:46:01 -0800
Subject: [PATCH 1004/1530] perf sh: Remove dwarf-regs.c

The file just provides the function get_arch_regstr, however, if in
the only caller get_dwarf_regstr EM_HOST is used for the EM_NONE case
the function can never be called. So remove as dead code. As this is
the only file in the arch/sh/util clean up Build files. Tidy up the
EM_NONE cases for sh in dwarf-regs.c.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-17-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/sh/Build             |  1 -
 tools/perf/arch/sh/util/Build        |  1 -
 tools/perf/arch/sh/util/dwarf-regs.c | 41 ----------------------------
 tools/perf/util/dwarf-regs.c         |  4 +--
 tools/perf/util/include/dwarf-regs.h |  2 +-
 5 files changed, 3 insertions(+), 46 deletions(-)
 delete mode 100644 tools/perf/arch/sh/Build
 delete mode 100644 tools/perf/arch/sh/util/Build
 delete mode 100644 tools/perf/arch/sh/util/dwarf-regs.c

diff --git a/tools/perf/arch/sh/Build b/tools/perf/arch/sh/Build
deleted file mode 100644
index e63eabc2c8f41..0000000000000
--- a/tools/perf/arch/sh/Build
+++ /dev/null
@@ -1 +0,0 @@
-perf-util-y += util/
diff --git a/tools/perf/arch/sh/util/Build b/tools/perf/arch/sh/util/Build
deleted file mode 100644
index 2337a0b710a24..0000000000000
--- a/tools/perf/arch/sh/util/Build
+++ /dev/null
@@ -1 +0,0 @@
-perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
diff --git a/tools/perf/arch/sh/util/dwarf-regs.c b/tools/perf/arch/sh/util/dwarf-regs.c
deleted file mode 100644
index 4b17fc86c73bd..0000000000000
--- a/tools/perf/arch/sh/util/dwarf-regs.c
+++ /dev/null
@@ -1,41 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Mapping of DWARF debug register numbers into register names.
- *
- * Copyright (C) 2010 Matt Fleming <matt@console-pimps.org>
- */
-
-#include <stddef.h>
-#include <dwarf-regs.h>
-
-/*
- * Generic dwarf analysis helpers
- */
-
-#define SH_MAX_REGS 18
-const char *sh_regs_table[SH_MAX_REGS] = {
-	"r0",
-	"r1",
-	"r2",
-	"r3",
-	"r4",
-	"r5",
-	"r6",
-	"r7",
-	"r8",
-	"r9",
-	"r10",
-	"r11",
-	"r12",
-	"r13",
-	"r14",
-	"r15",
-	"pc",
-	"pr",
-};
-
-/* Return architecture dependent register string (for kprobe-tracer) */
-const char *get_arch_regstr(unsigned int n)
-{
-	return (n < SH_MAX_REGS) ? sh_regs_table[n] : NULL;
-}
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 1649fc07f4f52..944ff4ef0290e 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -34,7 +34,7 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int
 {
 #if EM_HOST == EM_X86_64 || EM_HOST == EM_386 || EM_HOST == EM_AARCH64 || EM_HOST == EM_ARM \
     || EM_HOST == EM_CSKY || EM_HOST == EM_LOONGARCH || EM_HOST == EM_MIPS || EM_HOST == EM_PPC \
-    || EM_HOST == EM_PPC64 || EM_HOST == EM_RISCV || EM_HOST == EM_S390
+    || EM_HOST == EM_PPC64 || EM_HOST == EM_RISCV || EM_HOST == EM_S390 || EM_HOST == EM_SH
 	if (machine == EM_NONE) {
 		/* Generic arch - use host arch */
 		machine = EM_HOST;
@@ -43,7 +43,7 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int
 	switch (machine) {
 #if EM_HOST != EM_X86_64 && EM_HOST != EM_386 && EM_HOST != EM_AARCH64 && EM_HOST != EM_ARM \
     && EM_HOST != EM_CSKY && EM_HOST != EM_LOONGARCH && EM_HOST != EM_MIPS && EM_HOST != EM_PPC \
-    && EM_HOST != EM_PPC64 && EM_HOST != EM_RISCV && EM_HOST != EM_S390
+    && EM_HOST != EM_PPC64 && EM_HOST != EM_RISCV && EM_HOST != EM_S390 && EM_HOST != EM_SH
 	case EM_NONE:	/* Generic arch - use host arch */
 		return get_arch_regstr(n);
 #endif
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 086b537690d78..7026a3d2aaa7e 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -91,7 +91,7 @@
 #ifdef HAVE_LIBDW_SUPPORT
 #if !defined(__x86_64__) && !defined(__i386__) && !defined(__aarch64__) && !defined(__arm__) \
     && !defined(__loongarch__) && !defined(__mips__) && !defined(__powerpc__) \
-    && !defined(__powerpc64__) && !defined(__riscv__) && !defined(__s390x__)
+    && !defined(__powerpc64__) && !defined(__riscv__) && !defined(__s390x__) && !defined(__sh__)
 const char *get_arch_regstr(unsigned int n);
 #endif
 

From 85567a2a8d4217203085ba2243868457664b9e24 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:46:02 -0800
Subject: [PATCH 1005/1530] perf sparc: Remove dwarf-regs.c

The file just provides the function get_arch_regstr, however, if in
the only caller get_dwarf_regstr EM_HOST is used for the EM_NONE case
the function can never be called. So remove as dead code. As this is
the only file in the arch/sparc/util clean up Build files. Tidy up the
EM_NONE cases for sparc in dwarf-regs.c.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-18-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/sparc/Build             |  1 -
 tools/perf/arch/sparc/util/Build        |  1 -
 tools/perf/arch/sparc/util/dwarf-regs.c | 39 -------------------------
 tools/perf/util/dwarf-regs.c            |  6 ++--
 tools/perf/util/include/dwarf-regs.h    |  3 +-
 5 files changed, 6 insertions(+), 44 deletions(-)
 delete mode 100644 tools/perf/arch/sparc/Build
 delete mode 100644 tools/perf/arch/sparc/util/Build
 delete mode 100644 tools/perf/arch/sparc/util/dwarf-regs.c

diff --git a/tools/perf/arch/sparc/Build b/tools/perf/arch/sparc/Build
deleted file mode 100644
index e63eabc2c8f41..0000000000000
--- a/tools/perf/arch/sparc/Build
+++ /dev/null
@@ -1 +0,0 @@
-perf-util-y += util/
diff --git a/tools/perf/arch/sparc/util/Build b/tools/perf/arch/sparc/util/Build
deleted file mode 100644
index 2337a0b710a24..0000000000000
--- a/tools/perf/arch/sparc/util/Build
+++ /dev/null
@@ -1 +0,0 @@
-perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
diff --git a/tools/perf/arch/sparc/util/dwarf-regs.c b/tools/perf/arch/sparc/util/dwarf-regs.c
deleted file mode 100644
index 1282cb2dc7bdc..0000000000000
--- a/tools/perf/arch/sparc/util/dwarf-regs.c
+++ /dev/null
@@ -1,39 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Mapping of DWARF debug register numbers into register names.
- *
- * Copyright (C) 2010 David S. Miller <davem@davemloft.net>
- */
-
-#include <stddef.h>
-#include <dwarf-regs.h>
-
-#define SPARC_MAX_REGS	96
-
-const char *sparc_regs_table[SPARC_MAX_REGS] = {
-	"%g0", "%g1", "%g2", "%g3", "%g4", "%g5", "%g6", "%g7",
-	"%o0", "%o1", "%o2", "%o3", "%o4", "%o5", "%sp", "%o7",
-	"%l0", "%l1", "%l2", "%l3", "%l4", "%l5", "%l6", "%l7",
-	"%i0", "%i1", "%i2", "%i3", "%i4", "%i5", "%fp", "%i7",
-	"%f0", "%f1", "%f2", "%f3", "%f4", "%f5", "%f6", "%f7",
-	"%f8", "%f9", "%f10", "%f11", "%f12", "%f13", "%f14", "%f15",
-	"%f16", "%f17", "%f18", "%f19", "%f20", "%f21", "%f22", "%f23",
-	"%f24", "%f25", "%f26", "%f27", "%f28", "%f29", "%f30", "%f31",
-	"%f32", "%f33", "%f34", "%f35", "%f36", "%f37", "%f38", "%f39",
-	"%f40", "%f41", "%f42", "%f43", "%f44", "%f45", "%f46", "%f47",
-	"%f48", "%f49", "%f50", "%f51", "%f52", "%f53", "%f54", "%f55",
-	"%f56", "%f57", "%f58", "%f59", "%f60", "%f61", "%f62", "%f63",
-};
-
-/**
- * get_arch_regstr() - lookup register name from it's DWARF register number
- * @n:	the DWARF register number
- *
- * get_arch_regstr() returns the name of the register in struct
- * regdwarfnum_table from it's DWARF register number. If the register is not
- * found in the table, this returns NULL;
- */
-const char *get_arch_regstr(unsigned int n)
-{
-	return (n < SPARC_MAX_REGS) ? sparc_regs_table[n] : NULL;
-}
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 944ff4ef0290e..a0bcc2529cb04 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -34,7 +34,8 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int
 {
 #if EM_HOST == EM_X86_64 || EM_HOST == EM_386 || EM_HOST == EM_AARCH64 || EM_HOST == EM_ARM \
     || EM_HOST == EM_CSKY || EM_HOST == EM_LOONGARCH || EM_HOST == EM_MIPS || EM_HOST == EM_PPC \
-    || EM_HOST == EM_PPC64 || EM_HOST == EM_RISCV || EM_HOST == EM_S390 || EM_HOST == EM_SH
+    || EM_HOST == EM_PPC64 || EM_HOST == EM_RISCV || EM_HOST == EM_S390 || EM_HOST == EM_SH \
+    || EM_HOST == EM_SPARC || EM_HOST == EM_SPARCV9
 	if (machine == EM_NONE) {
 		/* Generic arch - use host arch */
 		machine = EM_HOST;
@@ -43,7 +44,8 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int
 	switch (machine) {
 #if EM_HOST != EM_X86_64 && EM_HOST != EM_386 && EM_HOST != EM_AARCH64 && EM_HOST != EM_ARM \
     && EM_HOST != EM_CSKY && EM_HOST != EM_LOONGARCH && EM_HOST != EM_MIPS && EM_HOST != EM_PPC \
-    && EM_HOST != EM_PPC64 && EM_HOST != EM_RISCV && EM_HOST != EM_S390 && EM_HOST != EM_SH
+    && EM_HOST != EM_PPC64 && EM_HOST != EM_RISCV && EM_HOST != EM_S390 && EM_HOST != EM_SH \
+    && EM_HOST != EM_SPARC && EM_HOST != EM_SPARCV9
 	case EM_NONE:	/* Generic arch - use host arch */
 		return get_arch_regstr(n);
 #endif
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 7026a3d2aaa7e..cb632d1f46f3a 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -91,7 +91,8 @@
 #ifdef HAVE_LIBDW_SUPPORT
 #if !defined(__x86_64__) && !defined(__i386__) && !defined(__aarch64__) && !defined(__arm__) \
     && !defined(__loongarch__) && !defined(__mips__) && !defined(__powerpc__) \
-    && !defined(__powerpc64__) && !defined(__riscv__) && !defined(__s390x__) && !defined(__sh__)
+    && !defined(__powerpc64__) && !defined(__riscv__) && !defined(__s390x__) && !defined(__sh__) \
+    && !defined(__sparc64__) && !defined(__sparc__)
 const char *get_arch_regstr(unsigned int n);
 #endif
 

From a4747c09507dbe3f8b0296dc7566cd1153eb6a0e Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:46:03 -0800
Subject: [PATCH 1006/1530] perf xtensa: Remove dwarf-regs.c

The file just provides the function get_arch_regstr, however, if in
the only caller get_dwarf_regstr EM_HOST is used for the EM_NONE case
the function can never be called. So remove as dead code. As this is
the only file in the arch/xtensa/util clean up Build files. Tidy up the
EM_NONE cases for xtensa in dwarf-regs.c.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-19-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/xtensa/Build             |  1 -
 tools/perf/arch/xtensa/util/Build        |  1 -
 tools/perf/arch/xtensa/util/dwarf-regs.c | 21 ---------------------
 tools/perf/util/dwarf-regs.c             |  4 ++--
 tools/perf/util/include/dwarf-regs.h     |  2 +-
 5 files changed, 3 insertions(+), 26 deletions(-)
 delete mode 100644 tools/perf/arch/xtensa/Build
 delete mode 100644 tools/perf/arch/xtensa/util/Build
 delete mode 100644 tools/perf/arch/xtensa/util/dwarf-regs.c

diff --git a/tools/perf/arch/xtensa/Build b/tools/perf/arch/xtensa/Build
deleted file mode 100644
index e63eabc2c8f41..0000000000000
--- a/tools/perf/arch/xtensa/Build
+++ /dev/null
@@ -1 +0,0 @@
-perf-util-y += util/
diff --git a/tools/perf/arch/xtensa/util/Build b/tools/perf/arch/xtensa/util/Build
deleted file mode 100644
index 2d1a48696ad92..0000000000000
--- a/tools/perf/arch/xtensa/util/Build
+++ /dev/null
@@ -1 +0,0 @@
-perf-$(CONFIG_LIBDW) += dwarf-regs.o
diff --git a/tools/perf/arch/xtensa/util/dwarf-regs.c b/tools/perf/arch/xtensa/util/dwarf-regs.c
deleted file mode 100644
index 12f5457300f5c..0000000000000
--- a/tools/perf/arch/xtensa/util/dwarf-regs.c
+++ /dev/null
@@ -1,21 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Mapping of DWARF debug register numbers into register names.
- *
- * Copyright (c) 2015 Cadence Design Systems Inc.
- */
-
-#include <stddef.h>
-#include <dwarf-regs.h>
-
-#define XTENSA_MAX_REGS 16
-
-const char *xtensa_regs_table[XTENSA_MAX_REGS] = {
-	"a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7",
-	"a8", "a9", "a10", "a11", "a12", "a13", "a14", "a15",
-};
-
-const char *get_arch_regstr(unsigned int n)
-{
-	return n < XTENSA_MAX_REGS ? xtensa_regs_table[n] : NULL;
-}
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index a0bcc2529cb04..05fff75a8f592 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -35,7 +35,7 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int
 #if EM_HOST == EM_X86_64 || EM_HOST == EM_386 || EM_HOST == EM_AARCH64 || EM_HOST == EM_ARM \
     || EM_HOST == EM_CSKY || EM_HOST == EM_LOONGARCH || EM_HOST == EM_MIPS || EM_HOST == EM_PPC \
     || EM_HOST == EM_PPC64 || EM_HOST == EM_RISCV || EM_HOST == EM_S390 || EM_HOST == EM_SH \
-    || EM_HOST == EM_SPARC || EM_HOST == EM_SPARCV9
+    || EM_HOST == EM_SPARC || EM_HOST == EM_SPARCV9 || EM_HOST == EM_XTENSA
 	if (machine == EM_NONE) {
 		/* Generic arch - use host arch */
 		machine = EM_HOST;
@@ -45,7 +45,7 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int
 #if EM_HOST != EM_X86_64 && EM_HOST != EM_386 && EM_HOST != EM_AARCH64 && EM_HOST != EM_ARM \
     && EM_HOST != EM_CSKY && EM_HOST != EM_LOONGARCH && EM_HOST != EM_MIPS && EM_HOST != EM_PPC \
     && EM_HOST != EM_PPC64 && EM_HOST != EM_RISCV && EM_HOST != EM_S390 && EM_HOST != EM_SH \
-    && EM_HOST != EM_SPARC && EM_HOST != EM_SPARCV9
+    && EM_HOST != EM_SPARC && EM_HOST != EM_SPARCV9 && EM_HOST != EM_XTENSA
 	case EM_NONE:	/* Generic arch - use host arch */
 		return get_arch_regstr(n);
 #endif
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index cb632d1f46f3a..e0f1d65895f53 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -92,7 +92,7 @@
 #if !defined(__x86_64__) && !defined(__i386__) && !defined(__aarch64__) && !defined(__arm__) \
     && !defined(__loongarch__) && !defined(__mips__) && !defined(__powerpc__) \
     && !defined(__powerpc64__) && !defined(__riscv__) && !defined(__s390x__) && !defined(__sh__) \
-    && !defined(__sparc64__) && !defined(__sparc__)
+    && !defined(__sparc64__) && !defined(__sparc__) && !defined(__xtensa__)
 const char *get_arch_regstr(unsigned int n);
 #endif
 

From 3ef6b89a129a668814d6fffcd0d7a3f0170e4451 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:46:04 -0800
Subject: [PATCH 1007/1530] perf dwarf-regs: Remove get_arch_regstr code

get_arch_regstr no longer exists so remove declaration. Associated ifs
and switches are made unconditional.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-20-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/dwarf-regs.c         | 12 ------------
 tools/perf/util/include/dwarf-regs.h |  7 -------
 2 files changed, 19 deletions(-)

diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 05fff75a8f592..28a1cfdf26d40 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -32,23 +32,11 @@
 /* Return architecture dependent register string (for kprobe-tracer) */
 const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int flags)
 {
-#if EM_HOST == EM_X86_64 || EM_HOST == EM_386 || EM_HOST == EM_AARCH64 || EM_HOST == EM_ARM \
-    || EM_HOST == EM_CSKY || EM_HOST == EM_LOONGARCH || EM_HOST == EM_MIPS || EM_HOST == EM_PPC \
-    || EM_HOST == EM_PPC64 || EM_HOST == EM_RISCV || EM_HOST == EM_S390 || EM_HOST == EM_SH \
-    || EM_HOST == EM_SPARC || EM_HOST == EM_SPARCV9 || EM_HOST == EM_XTENSA
 	if (machine == EM_NONE) {
 		/* Generic arch - use host arch */
 		machine = EM_HOST;
 	}
-#endif
 	switch (machine) {
-#if EM_HOST != EM_X86_64 && EM_HOST != EM_386 && EM_HOST != EM_AARCH64 && EM_HOST != EM_ARM \
-    && EM_HOST != EM_CSKY && EM_HOST != EM_LOONGARCH && EM_HOST != EM_MIPS && EM_HOST != EM_PPC \
-    && EM_HOST != EM_PPC64 && EM_HOST != EM_RISCV && EM_HOST != EM_S390 && EM_HOST != EM_SH \
-    && EM_HOST != EM_SPARC && EM_HOST != EM_SPARCV9 && EM_HOST != EM_XTENSA
-	case EM_NONE:	/* Generic arch - use host arch */
-		return get_arch_regstr(n);
-#endif
 	case EM_386:
 		return __get_dwarf_regstr(x86_32_regstr_tbl, n);
 	case EM_X86_64:
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index e0f1d65895f53..6f1b9f6b24663 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -89,13 +89,6 @@
 #define DWARF_REG_FB  0xd3affb /* random number */
 
 #ifdef HAVE_LIBDW_SUPPORT
-#if !defined(__x86_64__) && !defined(__i386__) && !defined(__aarch64__) && !defined(__arm__) \
-    && !defined(__loongarch__) && !defined(__mips__) && !defined(__powerpc__) \
-    && !defined(__powerpc64__) && !defined(__riscv__) && !defined(__s390x__) && !defined(__sh__) \
-    && !defined(__sparc64__) && !defined(__sparc__) && !defined(__xtensa__)
-const char *get_arch_regstr(unsigned int n);
-#endif
-
 const char *get_csky_regstr(unsigned int n, unsigned int flags);
 
 /**

From ddbfb6f20c1b7a8b111e2194fff767cea032d491 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 8 Nov 2024 15:46:05 -0800
Subject: [PATCH 1008/1530] perf build: Remove PERF_HAVE_DWARF_REGS

PERF_HAVE_DWARF_REGS was true when an architecture had a dwarf-regs.c
file. There are no more architecture dwarf-regs.c files, selection is
done using constants from the ELF file rather than conditional
compilation. When removing PERF_HAVE_DWARF_REGS was the only variable
in the Makefile, remove the Makefile.

Add missing SPDX for RISC-V Makefile.

Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Shenlin Liang <liangshenlin@eswincomputing.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Chen Pei <cp0613@linux.alibaba.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Aditya Gupta <adityag@linux.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: linux-csky@vger.kernel.org
Link: https://lore.kernel.org/r/20241108234606.429459-21-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Makefile.config         | 13 ++++---------
 tools/perf/arch/arm/Makefile       |  3 ---
 tools/perf/arch/arm64/Makefile     |  3 ---
 tools/perf/arch/csky/Makefile      |  4 ----
 tools/perf/arch/loongarch/Makefile |  3 ---
 tools/perf/arch/mips/Makefile      |  4 ----
 tools/perf/arch/powerpc/Makefile   |  4 ----
 tools/perf/arch/riscv/Makefile     |  4 +---
 tools/perf/arch/s390/Makefile      |  3 ---
 tools/perf/arch/sh/Makefile        |  4 ----
 tools/perf/arch/sparc/Makefile     |  4 ----
 tools/perf/arch/x86/Makefile       |  3 ---
 tools/perf/arch/xtensa/Makefile    |  4 ----
 13 files changed, 5 insertions(+), 51 deletions(-)
 delete mode 100644 tools/perf/arch/csky/Makefile
 delete mode 100644 tools/perf/arch/sh/Makefile
 delete mode 100644 tools/perf/arch/xtensa/Makefile

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 52a216df9e2af..2916d59c88cd0 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -559,15 +559,10 @@ ifndef NO_LIBELF
   endif
 
   ifndef NO_LIBDW
-    ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
-      $(warning DWARF register mappings have not been defined for architecture $(SRCARCH), DWARF support disabled)
-      NO_LIBDW := 1
-    else
-      CFLAGS += -DHAVE_LIBDW_SUPPORT $(LIBDW_CFLAGS)
-      LDFLAGS += $(LIBDW_LDFLAGS)
-      EXTLIBS += ${DWARFLIBS}
-      $(call detected,CONFIG_LIBDW)
-    endif # PERF_HAVE_DWARF_REGS
+    CFLAGS += -DHAVE_LIBDW_SUPPORT $(LIBDW_CFLAGS)
+    LDFLAGS += $(LIBDW_LDFLAGS)
+    EXTLIBS += ${DWARFLIBS}
+    $(call detected,CONFIG_LIBDW)
   endif # NO_LIBDW
 
   ifndef NO_LIBBPF
diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile
index 9b164d3795485..8b59ce8efb892 100644
--- a/tools/perf/arch/arm/Makefile
+++ b/tools/perf/arch/arm/Makefile
@@ -1,5 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ifndef NO_LIBDW
-PERF_HAVE_DWARF_REGS := 1
-endif
 PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index ca2e359612870..91570d5d428e4 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -1,7 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-ifndef NO_LIBDW
-PERF_HAVE_DWARF_REGS := 1
-endif
 PERF_HAVE_JITDUMP := 1
 HAVE_KVM_STAT_SUPPORT := 1
 
diff --git a/tools/perf/arch/csky/Makefile b/tools/perf/arch/csky/Makefile
deleted file mode 100644
index 119b06a64bed4..0000000000000
--- a/tools/perf/arch/csky/Makefile
+++ /dev/null
@@ -1,4 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-ifndef NO_LIBDW
-PERF_HAVE_DWARF_REGS := 1
-endif
diff --git a/tools/perf/arch/loongarch/Makefile b/tools/perf/arch/loongarch/Makefile
index 79b432744296e..52544d59245ba 100644
--- a/tools/perf/arch/loongarch/Makefile
+++ b/tools/perf/arch/loongarch/Makefile
@@ -1,7 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-ifndef NO_LIBDW
-PERF_HAVE_DWARF_REGS := 1
-endif
 PERF_HAVE_JITDUMP := 1
 HAVE_KVM_STAT_SUPPORT := 1
 
diff --git a/tools/perf/arch/mips/Makefile b/tools/perf/arch/mips/Makefile
index 733f7b76f52de..827168f1077a6 100644
--- a/tools/perf/arch/mips/Makefile
+++ b/tools/perf/arch/mips/Makefile
@@ -1,8 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-ifndef NO_LIBDW
-PERF_HAVE_DWARF_REGS := 1
-endif
-
 # Syscall table generation for perf
 out    := $(OUTPUT)arch/mips/include/generated/asm
 header := $(out)/syscalls_n64.c
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index ae05727835d85..dc8f4fb8e324a 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -1,8 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-ifndef NO_LIBDW
-PERF_HAVE_DWARF_REGS := 1
-endif
-
 HAVE_KVM_STAT_SUPPORT := 1
 PERF_HAVE_JITDUMP := 1
 
diff --git a/tools/perf/arch/riscv/Makefile b/tools/perf/arch/riscv/Makefile
index d83e0f32f3a83..18ad078000e2b 100644
--- a/tools/perf/arch/riscv/Makefile
+++ b/tools/perf/arch/riscv/Makefile
@@ -1,6 +1,4 @@
-ifndef NO_LIBDW
-PERF_HAVE_DWARF_REGS := 1
-endif
+# SPDX-License-Identifier: GPL-2.0
 PERF_HAVE_JITDUMP := 1
 HAVE_KVM_STAT_SUPPORT := 1
 
diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile
index 58e79f5b67a44..c431c21b11ef8 100644
--- a/tools/perf/arch/s390/Makefile
+++ b/tools/perf/arch/s390/Makefile
@@ -1,7 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ifndef NO_LIBDW
-PERF_HAVE_DWARF_REGS := 1
-endif
 HAVE_KVM_STAT_SUPPORT := 1
 PERF_HAVE_JITDUMP := 1
 
diff --git a/tools/perf/arch/sh/Makefile b/tools/perf/arch/sh/Makefile
deleted file mode 100644
index 119b06a64bed4..0000000000000
--- a/tools/perf/arch/sh/Makefile
+++ /dev/null
@@ -1,4 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-ifndef NO_LIBDW
-PERF_HAVE_DWARF_REGS := 1
-endif
diff --git a/tools/perf/arch/sparc/Makefile b/tools/perf/arch/sparc/Makefile
index 7741184894c81..8b59ce8efb892 100644
--- a/tools/perf/arch/sparc/Makefile
+++ b/tools/perf/arch/sparc/Makefile
@@ -1,6 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ifndef NO_LIBDW
-PERF_HAVE_DWARF_REGS := 1
-endif
-
 PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 51cf267f4d850..a6b6e0a9308a8 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -1,7 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-ifndef NO_LIBDW
-PERF_HAVE_DWARF_REGS := 1
-endif
 HAVE_KVM_STAT_SUPPORT := 1
 PERF_HAVE_JITDUMP := 1
 
diff --git a/tools/perf/arch/xtensa/Makefile b/tools/perf/arch/xtensa/Makefile
deleted file mode 100644
index 119b06a64bed4..0000000000000
--- a/tools/perf/arch/xtensa/Makefile
+++ /dev/null
@@ -1,4 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-ifndef NO_LIBDW
-PERF_HAVE_DWARF_REGS := 1
-endif

From 3287673c1d26f94845ef958090c583c46054b70d Mon Sep 17 00:00:00 2001
From: Ed Robbins <edd.robbins@googlemail.com>
Date: Fri, 18 Oct 2024 07:07:30 +0100
Subject: [PATCH 1009/1530] power: supply: pmu_battery: Set power supply type
 to BATTERY

If the power supply type is not set it defaults to "Unknown" and upower
does not recognise it. In turn battery monitor applications do not see a
battery. Setting to POWER_SUPPLY_TYPE_BATTERY fixes this.

Signed-off-by: Ed Robbins <edd.robbins@gmail.com>
Link: https://lore.kernel.org/r/IOFJLS.120OJ5KJG9R72@googlemail.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/pmu_battery.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/power/supply/pmu_battery.c b/drivers/power/supply/pmu_battery.c
index eaab7500d99b5..ed83c5e05ca32 100644
--- a/drivers/power/supply/pmu_battery.c
+++ b/drivers/power/supply/pmu_battery.c
@@ -170,6 +170,7 @@ static int __init pmu_bat_init(void)
 		pbat->bat_desc.properties = pmu_bat_props;
 		pbat->bat_desc.num_properties = ARRAY_SIZE(pmu_bat_props);
 		pbat->bat_desc.get_property = pmu_bat_get_property;
+		pbat->bat_desc.type = POWER_SUPPLY_TYPE_BATTERY;
 		pbat->pbi = &pmu_batteries[i];
 		psy_cfg.drv_data = pbat;
 

From 8eea62ff94f4dbad8ee884b0b33202e0a0fb350b Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Wed, 23 Oct 2024 13:23:18 +0000
Subject: [PATCH 1010/1530] rust: sync: add global lock support

Add support for creating global variables that are wrapped in a mutex or
spinlock.

The implementation here is intended to replace the global mutex
workaround found in the Rust Binder RFC [1]. In both cases, the global
lock must be initialized before first use. The macro is unsafe to use
for the same reason.

The separate initialization step is required because it is tricky to
access the value of __ARCH_SPIN_LOCK_UNLOCKED from Rust. Doing so will
require changes to the C side. That change will happen as a follow-up to
this patch.

Link: https://lore.kernel.org/rust-for-linux/20231101-rust-binder-v1-2-08ba9197f637@google.com/#Z31drivers:android:context.rs [1]
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Link: https://lore.kernel.org/r/20241023-static-mutex-v6-1-d7efdadcc84f@google.com
[ Simplified a few intra-doc links. Formatted a few comments. Reworded
  title. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/sync.rs             |   1 +
 rust/kernel/sync/lock.rs        |   3 +
 rust/kernel/sync/lock/global.rs | 301 ++++++++++++++++++++++++++++++++
 3 files changed, 305 insertions(+)
 create mode 100644 rust/kernel/sync/lock/global.rs

diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs
index 0ab20975a3b5d..2bdd1cffcdab3 100644
--- a/rust/kernel/sync.rs
+++ b/rust/kernel/sync.rs
@@ -14,6 +14,7 @@ mod locked_by;
 
 pub use arc::{Arc, ArcBorrow, UniqueArc};
 pub use condvar::{new_condvar, CondVar, CondVarTimeoutResult};
+pub use lock::global::{global_lock, GlobalGuard, GlobalLock, GlobalLockBackend, GlobalLockedBy};
 pub use lock::mutex::{new_mutex, Mutex};
 pub use lock::spinlock::{new_spinlock, SpinLock};
 pub use locked_by::LockedBy;
diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs
index 90cc5416529bd..a5d89cebf106e 100644
--- a/rust/kernel/sync/lock.rs
+++ b/rust/kernel/sync/lock.rs
@@ -13,6 +13,9 @@ use macros::pin_data;
 pub mod mutex;
 pub mod spinlock;
 
+pub(super) mod global;
+pub use global::{GlobalGuard, GlobalLock, GlobalLockBackend, GlobalLockedBy};
+
 /// The "backend" of a lock.
 ///
 /// It is the actual implementation of the lock, without the need to repeat patterns used in all
diff --git a/rust/kernel/sync/lock/global.rs b/rust/kernel/sync/lock/global.rs
new file mode 100644
index 0000000000000..480ee724e3cc4
--- /dev/null
+++ b/rust/kernel/sync/lock/global.rs
@@ -0,0 +1,301 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2024 Google LLC.
+
+//! Support for defining statics containing locks.
+
+use crate::{
+    str::CStr,
+    sync::lock::{Backend, Guard, Lock},
+    sync::{LockClassKey, LockedBy},
+    types::Opaque,
+};
+use core::{
+    cell::UnsafeCell,
+    marker::{PhantomData, PhantomPinned},
+};
+
+/// Trait implemented for marker types for global locks.
+///
+/// See [`global_lock!`] for examples.
+pub trait GlobalLockBackend {
+    /// The name for this global lock.
+    const NAME: &'static CStr;
+    /// Item type stored in this global lock.
+    type Item: 'static;
+    /// The backend used for this global lock.
+    type Backend: Backend + 'static;
+    /// The class for this global lock.
+    fn get_lock_class() -> &'static LockClassKey;
+}
+
+/// Type used for global locks.
+///
+/// See [`global_lock!`] for examples.
+pub struct GlobalLock<B: GlobalLockBackend> {
+    inner: Lock<B::Item, B::Backend>,
+}
+
+impl<B: GlobalLockBackend> GlobalLock<B> {
+    /// Creates a global lock.
+    ///
+    /// # Safety
+    ///
+    /// * Before any other method on this lock is called, [`Self::init`] must be called.
+    /// * The type `B` must not be used with any other lock.
+    pub const unsafe fn new(data: B::Item) -> Self {
+        Self {
+            inner: Lock {
+                state: Opaque::uninit(),
+                data: UnsafeCell::new(data),
+                _pin: PhantomPinned,
+            },
+        }
+    }
+
+    /// Initializes a global lock.
+    ///
+    /// # Safety
+    ///
+    /// Must not be called more than once on a given lock.
+    pub unsafe fn init(&'static self) {
+        // SAFETY: The pointer to `state` is valid for the duration of this call, and both `name`
+        // and `key` are valid indefinitely. The `state` is pinned since we have a `'static`
+        // reference to `self`.
+        //
+        // We have exclusive access to the `state` since the caller of `new` promised to call
+        // `init` before using any other methods. As `init` can only be called once, all other
+        // uses of this lock must happen after this call.
+        unsafe {
+            B::Backend::init(
+                self.inner.state.get(),
+                B::NAME.as_char_ptr(),
+                B::get_lock_class().as_ptr(),
+            )
+        }
+    }
+
+    /// Lock this global lock.
+    pub fn lock(&'static self) -> GlobalGuard<B> {
+        GlobalGuard {
+            inner: self.inner.lock(),
+        }
+    }
+
+    /// Try to lock this global lock.
+    pub fn try_lock(&'static self) -> Option<GlobalGuard<B>> {
+        Some(GlobalGuard {
+            inner: self.inner.try_lock()?,
+        })
+    }
+}
+
+/// A guard for a [`GlobalLock`].
+///
+/// See [`global_lock!`] for examples.
+pub struct GlobalGuard<B: GlobalLockBackend> {
+    inner: Guard<'static, B::Item, B::Backend>,
+}
+
+impl<B: GlobalLockBackend> core::ops::Deref for GlobalGuard<B> {
+    type Target = B::Item;
+
+    fn deref(&self) -> &Self::Target {
+        &self.inner
+    }
+}
+
+impl<B: GlobalLockBackend> core::ops::DerefMut for GlobalGuard<B> {
+    fn deref_mut(&mut self) -> &mut Self::Target {
+        &mut self.inner
+    }
+}
+
+/// A version of [`LockedBy`] for a [`GlobalLock`].
+///
+/// See [`global_lock!`] for examples.
+pub struct GlobalLockedBy<T: ?Sized, B: GlobalLockBackend> {
+    _backend: PhantomData<B>,
+    value: UnsafeCell<T>,
+}
+
+// SAFETY: The same thread-safety rules as `LockedBy` apply to `GlobalLockedBy`.
+unsafe impl<T, B> Send for GlobalLockedBy<T, B>
+where
+    T: ?Sized,
+    B: GlobalLockBackend,
+    LockedBy<T, B::Item>: Send,
+{
+}
+
+// SAFETY: The same thread-safety rules as `LockedBy` apply to `GlobalLockedBy`.
+unsafe impl<T, B> Sync for GlobalLockedBy<T, B>
+where
+    T: ?Sized,
+    B: GlobalLockBackend,
+    LockedBy<T, B::Item>: Sync,
+{
+}
+
+impl<T, B: GlobalLockBackend> GlobalLockedBy<T, B> {
+    /// Create a new [`GlobalLockedBy`].
+    ///
+    /// The provided value will be protected by the global lock indicated by `B`.
+    pub fn new(val: T) -> Self {
+        Self {
+            value: UnsafeCell::new(val),
+            _backend: PhantomData,
+        }
+    }
+}
+
+impl<T: ?Sized, B: GlobalLockBackend> GlobalLockedBy<T, B> {
+    /// Access the value immutably.
+    ///
+    /// The caller must prove shared access to the lock.
+    pub fn as_ref<'a>(&'a self, _guard: &'a GlobalGuard<B>) -> &'a T {
+        // SAFETY: The lock is globally unique, so there can only be one guard.
+        unsafe { &*self.value.get() }
+    }
+
+    /// Access the value mutably.
+    ///
+    /// The caller must prove shared exclusive to the lock.
+    pub fn as_mut<'a>(&'a self, _guard: &'a mut GlobalGuard<B>) -> &'a mut T {
+        // SAFETY: The lock is globally unique, so there can only be one guard.
+        unsafe { &mut *self.value.get() }
+    }
+
+    /// Access the value mutably directly.
+    ///
+    /// The caller has exclusive access to this `GlobalLockedBy`, so they do not need to hold the
+    /// lock.
+    pub fn get_mut(&mut self) -> &mut T {
+        self.value.get_mut()
+    }
+}
+
+/// Defines a global lock.
+///
+/// The global mutex must be initialized before first use. Usually this is done by calling
+/// [`GlobalLock::init`] in the module initializer.
+///
+/// # Examples
+///
+/// A global counter:
+///
+/// ```
+/// # mod ex {
+/// # use kernel::prelude::*;
+/// kernel::sync::global_lock! {
+///     // SAFETY: Initialized in module initializer before first use.
+///     unsafe(uninit) static MY_COUNTER: Mutex<u32> = 0;
+/// }
+///
+/// fn increment_counter() -> u32 {
+///     let mut guard = MY_COUNTER.lock();
+///     *guard += 1;
+///     *guard
+/// }
+///
+/// impl kernel::Module for MyModule {
+///     fn init(_module: &'static ThisModule) -> Result<Self> {
+///         // SAFETY: Called exactly once.
+///         unsafe { MY_COUNTER.init() };
+///
+///         Ok(MyModule {})
+///     }
+/// }
+/// # struct MyModule {}
+/// # }
+/// ```
+///
+/// A global mutex used to protect all instances of a given struct:
+///
+/// ```
+/// # mod ex {
+/// # use kernel::prelude::*;
+/// use kernel::sync::{GlobalGuard, GlobalLockedBy};
+///
+/// kernel::sync::global_lock! {
+///     // SAFETY: Initialized in module initializer before first use.
+///     unsafe(uninit) static MY_MUTEX: Mutex<()> = ();
+/// }
+///
+/// /// All instances of this struct are protected by `MY_MUTEX`.
+/// struct MyStruct {
+///     my_counter: GlobalLockedBy<u32, MY_MUTEX>,
+/// }
+///
+/// impl MyStruct {
+///     /// Increment the counter in this instance.
+///     ///
+///     /// The caller must hold the `MY_MUTEX` mutex.
+///     fn increment(&self, guard: &mut GlobalGuard<MY_MUTEX>) -> u32 {
+///         let my_counter = self.my_counter.as_mut(guard);
+///         *my_counter += 1;
+///         *my_counter
+///     }
+/// }
+///
+/// impl kernel::Module for MyModule {
+///     fn init(_module: &'static ThisModule) -> Result<Self> {
+///         // SAFETY: Called exactly once.
+///         unsafe { MY_MUTEX.init() };
+///
+///         Ok(MyModule {})
+///     }
+/// }
+/// # struct MyModule {}
+/// # }
+/// ```
+#[macro_export]
+macro_rules! global_lock {
+    {
+        $(#[$meta:meta])* $pub:vis
+        unsafe(uninit) static $name:ident: $kind:ident<$valuety:ty> = $value:expr;
+    } => {
+        #[doc = ::core::concat!(
+            "Backend type used by [`",
+            ::core::stringify!($name),
+            "`](static@",
+            ::core::stringify!($name),
+            ")."
+        )]
+        #[allow(non_camel_case_types, unreachable_pub)]
+        $pub enum $name {}
+
+        impl $crate::sync::lock::GlobalLockBackend for $name {
+            const NAME: &'static $crate::str::CStr = $crate::c_str!(::core::stringify!($name));
+            type Item = $valuety;
+            type Backend = $crate::global_lock_inner!(backend $kind);
+
+            fn get_lock_class() -> &'static $crate::sync::LockClassKey {
+                $crate::static_lock_class!()
+            }
+        }
+
+        $(#[$meta])*
+        $pub static $name: $crate::sync::lock::GlobalLock<$name> = {
+            // Defined here to be outside the unsafe scope.
+            let init: $valuety = $value;
+
+            // SAFETY:
+            // * The user of this macro promises to initialize the macro before use.
+            // * We are only generating one static with this backend type.
+            unsafe { $crate::sync::lock::GlobalLock::new(init) }
+        };
+    };
+}
+pub use global_lock;
+
+#[doc(hidden)]
+#[macro_export]
+macro_rules! global_lock_inner {
+    (backend Mutex) => {
+        $crate::sync::lock::mutex::MutexBackend
+    };
+    (backend SpinLock) => {
+        $crate::sync::lock::spinlock::SpinLockBackend
+    };
+}

From 75c1fd41a671a0843b89d1526411a837a7163fa2 Mon Sep 17 00:00:00 2001
From: Gary Guo <gary@garyguo.net>
Date: Fri, 13 Sep 2024 22:29:21 +0100
Subject: [PATCH 1011/1530] rust: fix size_t in bindgen prototypes of C
 builtins

Without `-fno-builtin`, for functions like memcpy/memmove (and many
others), bindgen seems to be using the clang-provided prototype. This
prototype is ABI-wise compatible, but the issue is that it does not have
the same information as the source code w.r.t. typedefs.

For example, bindgen generates the following:

    extern "C" {
        pub fn strlen(s: *const core::ffi::c_char) -> core::ffi::c_ulong;
    }

note that the return type is `c_ulong` (i.e. unsigned long), despite the
size_t-is-usize behavior (this is default, and we have not opted out
from it using --no-size_t-is-usize).

Similarly, memchr's size argument should be of type `__kernel_size_t`,
but bindgen generates `c_ulong` directly.

We want to ensure any `size_t` is translated to Rust `usize` so that we
can avoid having them be different type on 32-bit and 64-bit
architectures, and hence would require a lot of excessive type casts
when calling FFI functions.

I found that this bindgen behavior (which probably is caused by
libclang) can be disabled by `-fno-builtin`. Using the flag for compiled
code can result in less optimisation because compiler cannot assume
about their properties anymore, but this should not affect bindgen.

[ Trevor asked: "I wonder how reliable this behavior is. Maybe bindgen
  could do a better job controlling this, is there an open issue?".

  Gary replied: ..."apparently this is indeed the suggested approach in
  https://github.com/rust-lang/rust-bindgen/issues/1770". - Miguel ]

Signed-off-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240913213041.395655-2-gary@garyguo.net
[ Formatted comment. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/Makefile | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/rust/Makefile b/rust/Makefile
index 6daaa4dc21dbc..fcec0e1d9762d 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -264,7 +264,11 @@ else
 bindgen_c_flags_lto = $(bindgen_c_flags)
 endif
 
-bindgen_c_flags_final = $(bindgen_c_flags_lto) -D__BINDGEN__
+# `-fno-builtin` is passed to avoid `bindgen` from using `clang` builtin
+# prototypes for functions like `memcpy` -- if this flag is not passed,
+# `bindgen`-generated prototypes use `c_ulong` or `c_uint` depending on
+# architecture instead of generating `usize`.
+bindgen_c_flags_final = $(bindgen_c_flags_lto) -fno-builtin -D__BINDGEN__
 
 quiet_cmd_bindgen = BINDGEN $@
       cmd_bindgen = \

From f212140962c93cd5da43283a18e31681540fc23d Mon Sep 17 00:00:00 2001
From: Jean-Michel Hautbois <jeanmichel.hautbois@yoseli.org>
Date: Wed, 16 Oct 2024 09:24:35 +0200
Subject: [PATCH 1012/1530] m68k: mcfgpio: Fix incorrect register offset for
 CONFIG_M5441x

Fix a typo in the CONFIG_M5441x preprocessor condition, where the GPIO
register offset was incorrectly set to 8 instead of 0. This prevented
proper GPIO configuration for m5441x targets.

Fixes: bea8bcb12da0 ("m68knommu: Add support for the Coldfire m5441x.")
Signed-off-by: Jean-Michel Hautbois <jeanmichel.hautbois@yoseli.org>
Signed-off-by: Greg Ungerer <gerg@kernel.org>
---
 arch/m68k/include/asm/mcfgpio.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/m68k/include/asm/mcfgpio.h b/arch/m68k/include/asm/mcfgpio.h
index 019f244395464..9c91ecdafc453 100644
--- a/arch/m68k/include/asm/mcfgpio.h
+++ b/arch/m68k/include/asm/mcfgpio.h
@@ -136,7 +136,7 @@ static inline void gpio_free(unsigned gpio)
  * read-modify-write as well as those controlled by the EPORT and GPIO modules.
  */
 #define MCFGPIO_SCR_START		40
-#elif defined(CONFIGM5441x)
+#elif defined(CONFIG_M5441x)
 /* The m5441x EPORT doesn't have its own GPIO port, uses PORT C */
 #define MCFGPIO_SCR_START		0
 #else

From 63a24cf8cc330e5a68ebd2e20ae200096974c475 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@mandelbit.com>
Date: Tue, 29 Oct 2024 22:43:15 +0100
Subject: [PATCH 1013/1530] m68k: coldfire/device.c: only build FEC when HW
 macros are defined

When CONFIG_FEC is set (due to COMPILE_TEST) along with
CONFIG_M54xx, coldfire/device.c has compile errors due to
missing MCFEC_* and MCF_IRQ_FEC_* symbols.

Make the whole FEC blocks dependent on having the HW macros
defined, rather than on CONFIG_FEC itself.

This fix is very similar to commit e6e1e7b19fa1 ("m68k: coldfire/device.c: only build for MCF_EDMA when h/w macros are defined")

Fixes: b7ce7f0d0efc ("m68knommu: merge common ColdFire FEC platform setup code")
To: Greg Ungerer <gerg@linux-m68k.org>
To: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: linux-m68k@lists.linux-m68k.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Antonio Quartulli <antonio@mandelbit.com>
Signed-off-by: Greg Ungerer <gerg@kernel.org>
---
 arch/m68k/coldfire/device.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/m68k/coldfire/device.c b/arch/m68k/coldfire/device.c
index 7dab46728aeda..b6958ec2a220c 100644
--- a/arch/m68k/coldfire/device.c
+++ b/arch/m68k/coldfire/device.c
@@ -93,7 +93,7 @@ static struct platform_device mcf_uart = {
 	.dev.platform_data	= mcf_uart_platform_data,
 };
 
-#if IS_ENABLED(CONFIG_FEC)
+#ifdef MCFFEC_BASE0
 
 #ifdef CONFIG_M5441x
 #define FEC_NAME	"enet-fec"
@@ -145,6 +145,7 @@ static struct platform_device mcf_fec0 = {
 		.platform_data		= FEC_PDATA,
 	}
 };
+#endif /* MCFFEC_BASE0 */
 
 #ifdef MCFFEC_BASE1
 static struct resource mcf_fec1_resources[] = {
@@ -182,7 +183,6 @@ static struct platform_device mcf_fec1 = {
 	}
 };
 #endif /* MCFFEC_BASE1 */
-#endif /* CONFIG_FEC */
 
 #if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 /*
@@ -624,12 +624,12 @@ static struct platform_device mcf_flexcan0 = {
 
 static struct platform_device *mcf_devices[] __initdata = {
 	&mcf_uart,
-#if IS_ENABLED(CONFIG_FEC)
+#ifdef MCFFEC_BASE0
 	&mcf_fec0,
+#endif
 #ifdef MCFFEC_BASE1
 	&mcf_fec1,
 #endif
-#endif
 #if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 	&mcf_qspi,
 #endif

From 2fd6f55c048d0c863ffbc8590b1bd2edb5ff13e5 Mon Sep 17 00:00:00 2001
From: Gary Guo <gary@garyguo.net>
Date: Fri, 13 Sep 2024 22:29:22 +0100
Subject: [PATCH 1014/1530] rust: map `__kernel_size_t` and friends also to
 usize/isize

Currently bindgen has special logic to recognise `size_t` and `ssize_t`
and map them to Rust `usize` and `isize`. Similarly, `ptrdiff_t` is
mapped to `isize`.

However this falls short for `__kernel_size_t`, `__kernel_ssize_t` and
`__kernel_ptrdiff_t`. To ensure that they are mapped to usize/isize
rather than 32/64 integers depending on platform, blocklist them in
bindgen parameters and manually provide their definition.

Signed-off-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Link: https://lore.kernel.org/r/20240913213041.395655-3-gary@garyguo.net
[ Formatted comment. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/bindgen_parameters | 5 +++++
 rust/bindings/lib.rs    | 5 +++++
 rust/uapi/lib.rs        | 5 +++++
 3 files changed, 15 insertions(+)

diff --git a/rust/bindgen_parameters b/rust/bindgen_parameters
index b7c7483123b7a..0f96af8b9a7fe 100644
--- a/rust/bindgen_parameters
+++ b/rust/bindgen_parameters
@@ -1,5 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 
+# We want to map these types to `isize`/`usize` manually, instead of
+# define them as `int`/`long` depending on platform bitwidth.
+--blocklist-type __kernel_s?size_t
+--blocklist-type __kernel_ptrdiff_t
+
 --opaque-type xregs_state
 --opaque-type desc_struct
 --opaque-type arch_lbr_state
diff --git a/rust/bindings/lib.rs b/rust/bindings/lib.rs
index d6da3011281a9..014af0d1fc70c 100644
--- a/rust/bindings/lib.rs
+++ b/rust/bindings/lib.rs
@@ -27,6 +27,11 @@
 #[allow(dead_code)]
 #[allow(clippy::undocumented_unsafe_blocks)]
 mod bindings_raw {
+    // Manual definition for blocklisted types.
+    type __kernel_size_t = usize;
+    type __kernel_ssize_t = isize;
+    type __kernel_ptrdiff_t = isize;
+
     // Use glob import here to expose all helpers.
     // Symbols defined within the module will take precedence to the glob import.
     pub use super::bindings_helper::*;
diff --git a/rust/uapi/lib.rs b/rust/uapi/lib.rs
index fea2de330d193..13495910271fa 100644
--- a/rust/uapi/lib.rs
+++ b/rust/uapi/lib.rs
@@ -25,4 +25,9 @@
     unsafe_op_in_unsafe_fn
 )]
 
+// Manual definition of blocklisted types.
+type __kernel_size_t = usize;
+type __kernel_ssize_t = isize;
+type __kernel_ptrdiff_t = isize;
+
 include!(concat!(env!("OBJTREE"), "/rust/uapi/uapi_generated.rs"));

From d072acda4862f095ec9056979b654cc06a22cc68 Mon Sep 17 00:00:00 2001
From: Gary Guo <gary@garyguo.net>
Date: Fri, 13 Sep 2024 22:29:23 +0100
Subject: [PATCH 1015/1530] rust: use custom FFI integer types

Currently FFI integer types are defined in libcore. This commit creates
the `ffi` crate and asks bindgen to use that crate for FFI integer types
instead of `core::ffi`.

This commit is preparatory and no type changes are made in this commit
yet.

Signed-off-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20240913213041.395655-4-gary@garyguo.net
[ Added `rustdoc`, `rusttest` and KUnit tests support. Rebased on top of
  `rust-next` (e.g. migrated more `core::ffi` cases). Reworded crate
  docs slightly and formatted. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/Makefile                       | 39 +++++++++++++++++++----------
 rust/ffi.rs                         | 13 ++++++++++
 rust/kernel/alloc/allocator.rs      |  2 +-
 rust/kernel/alloc/allocator_test.rs |  4 +--
 rust/kernel/alloc/kbox.rs           | 12 ++++-----
 rust/kernel/block/mq/operations.rs  | 18 ++++++-------
 rust/kernel/block/mq/raw_writer.rs  |  2 +-
 rust/kernel/block/mq/tag_set.rs     |  2 +-
 rust/kernel/error.rs                | 20 +++++++--------
 rust/kernel/init.rs                 |  2 +-
 rust/kernel/lib.rs                  |  2 ++
 rust/kernel/net/phy.rs              | 16 ++++++------
 rust/kernel/str.rs                  |  4 +--
 rust/kernel/sync/arc.rs             |  6 ++---
 rust/kernel/sync/condvar.rs         |  2 +-
 rust/kernel/sync/lock.rs            |  2 +-
 rust/kernel/sync/lock/mutex.rs      |  2 +-
 rust/kernel/sync/lock/spinlock.rs   |  2 +-
 rust/kernel/task.rs                 |  8 ++----
 rust/kernel/time.rs                 |  4 +--
 rust/kernel/types.rs                | 14 +++++------
 rust/kernel/uaccess.rs              |  6 ++---
 rust/macros/module.rs               |  8 +++---
 23 files changed, 107 insertions(+), 83 deletions(-)
 create mode 100644 rust/ffi.rs

diff --git a/rust/Makefile b/rust/Makefile
index fcec0e1d9762d..f349e7b067ea6 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -3,7 +3,7 @@
 # Where to place rustdoc generated documentation
 rustdoc_output := $(objtree)/Documentation/output/rust/rustdoc
 
-obj-$(CONFIG_RUST) += core.o compiler_builtins.o
+obj-$(CONFIG_RUST) += core.o compiler_builtins.o ffi.o
 always-$(CONFIG_RUST) += exports_core_generated.h
 
 # Missing prototypes are expected in the helpers since these are exported
@@ -103,10 +103,13 @@ rustdoc-core: $(RUST_LIB_SRC)/core/src/lib.rs FORCE
 rustdoc-compiler_builtins: $(src)/compiler_builtins.rs rustdoc-core FORCE
 	+$(call if_changed,rustdoc)
 
-rustdoc-kernel: private rustc_target_flags = \
+rustdoc-ffi: $(src)/ffi.rs rustdoc-core FORCE
+	+$(call if_changed,rustdoc)
+
+rustdoc-kernel: private rustc_target_flags = --extern ffi \
     --extern build_error --extern macros=$(objtree)/$(obj)/libmacros.so \
     --extern bindings --extern uapi
-rustdoc-kernel: $(src)/kernel/lib.rs rustdoc-core rustdoc-macros \
+rustdoc-kernel: $(src)/kernel/lib.rs rustdoc-core rustdoc-ffi rustdoc-macros \
     rustdoc-compiler_builtins $(obj)/libmacros.so \
     $(obj)/bindings.o FORCE
 	+$(call if_changed,rustdoc)
@@ -124,12 +127,15 @@ quiet_cmd_rustc_test_library = RUSTC TL $<
 rusttestlib-build_error: $(src)/build_error.rs FORCE
 	+$(call if_changed,rustc_test_library)
 
+rusttestlib-ffi: $(src)/ffi.rs FORCE
+	+$(call if_changed,rustc_test_library)
+
 rusttestlib-macros: private rustc_target_flags = --extern proc_macro
 rusttestlib-macros: private rustc_test_library_proc = yes
 rusttestlib-macros: $(src)/macros/lib.rs FORCE
 	+$(call if_changed,rustc_test_library)
 
-rusttestlib-kernel: private rustc_target_flags = \
+rusttestlib-kernel: private rustc_target_flags = --extern ffi \
     --extern build_error --extern macros \
     --extern bindings --extern uapi
 rusttestlib-kernel: $(src)/kernel/lib.rs \
@@ -137,10 +143,12 @@ rusttestlib-kernel: $(src)/kernel/lib.rs \
     $(obj)/libmacros.so $(obj)/bindings.o FORCE
 	+$(call if_changed,rustc_test_library)
 
-rusttestlib-bindings: $(src)/bindings/lib.rs FORCE
+rusttestlib-bindings: private rustc_target_flags = --extern ffi
+rusttestlib-bindings: $(src)/bindings/lib.rs rusttestlib-ffi FORCE
 	+$(call if_changed,rustc_test_library)
 
-rusttestlib-uapi: $(src)/uapi/lib.rs FORCE
+rusttestlib-uapi: private rustc_target_flags = --extern ffi
+rusttestlib-uapi: $(src)/uapi/lib.rs rusttestlib-ffi FORCE
 	+$(call if_changed,rustc_test_library)
 
 quiet_cmd_rustdoc_test = RUSTDOC T $<
@@ -160,7 +168,7 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $<
 	mkdir -p $(objtree)/$(obj)/test/doctests/kernel; \
 	OBJTREE=$(abspath $(objtree)) \
 	$(RUSTDOC) --test $(rust_flags) \
-		-L$(objtree)/$(obj) --extern kernel \
+		-L$(objtree)/$(obj) --extern ffi --extern kernel \
 		--extern build_error --extern macros \
 		--extern bindings --extern uapi \
 		--no-run --crate-name kernel -Zunstable-options \
@@ -198,9 +206,9 @@ rusttest-macros: $(src)/macros/lib.rs \
 	+$(call if_changed,rustc_test)
 	+$(call if_changed,rustdoc_test)
 
-rusttest-kernel: private rustc_target_flags = \
+rusttest-kernel: private rustc_target_flags = --extern ffi \
     --extern build_error --extern macros --extern bindings --extern uapi
-rusttest-kernel: $(src)/kernel/lib.rs rusttestlib-kernel \
+rusttest-kernel: $(src)/kernel/lib.rs rusttestlib-ffi rusttestlib-kernel \
     rusttestlib-build_error rusttestlib-macros rusttestlib-bindings \
     rusttestlib-uapi FORCE
 	+$(call if_changed,rustc_test)
@@ -273,7 +281,7 @@ bindgen_c_flags_final = $(bindgen_c_flags_lto) -fno-builtin -D__BINDGEN__
 quiet_cmd_bindgen = BINDGEN $@
       cmd_bindgen = \
 	$(BINDGEN) $< $(bindgen_target_flags) \
-		--use-core --with-derive-default --ctypes-prefix core::ffi --no-layout-tests \
+		--use-core --with-derive-default --ctypes-prefix ffi --no-layout-tests \
 		--no-debug '.*' --enable-function-attribute-detection \
 		-o $@ -- $(bindgen_c_flags_final) -DMODULE \
 		$(bindgen_target_cflags) $(bindgen_target_extra)
@@ -401,18 +409,23 @@ $(obj)/compiler_builtins.o: $(src)/compiler_builtins.rs $(obj)/core.o FORCE
 $(obj)/build_error.o: $(src)/build_error.rs $(obj)/compiler_builtins.o FORCE
 	+$(call if_changed_rule,rustc_library)
 
+$(obj)/ffi.o: $(src)/ffi.rs $(obj)/compiler_builtins.o FORCE
+	+$(call if_changed_rule,rustc_library)
+
+$(obj)/bindings.o: private rustc_target_flags = --extern ffi
 $(obj)/bindings.o: $(src)/bindings/lib.rs \
-    $(obj)/compiler_builtins.o \
+    $(obj)/ffi.o \
     $(obj)/bindings/bindings_generated.rs \
     $(obj)/bindings/bindings_helpers_generated.rs FORCE
 	+$(call if_changed_rule,rustc_library)
 
+$(obj)/uapi.o: private rustc_target_flags = --extern ffi
 $(obj)/uapi.o: $(src)/uapi/lib.rs \
-    $(obj)/compiler_builtins.o \
+    $(obj)/ffi.o \
     $(obj)/uapi/uapi_generated.rs FORCE
 	+$(call if_changed_rule,rustc_library)
 
-$(obj)/kernel.o: private rustc_target_flags = \
+$(obj)/kernel.o: private rustc_target_flags = --extern ffi \
     --extern build_error --extern macros --extern bindings --extern uapi
 $(obj)/kernel.o: $(src)/kernel/lib.rs $(obj)/build_error.o \
     $(obj)/libmacros.so $(obj)/bindings.o $(obj)/uapi.o FORCE
diff --git a/rust/ffi.rs b/rust/ffi.rs
new file mode 100644
index 0000000000000..be153c4d551b2
--- /dev/null
+++ b/rust/ffi.rs
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Foreign function interface (FFI) types.
+//!
+//! This crate provides mapping from C primitive types to Rust ones.
+//!
+//! The Rust [`core`] crate provides [`core::ffi`], which maps integer types to the platform default
+//! C ABI. The kernel does not use [`core::ffi`], so it can customise the mapping that deviates from
+//! the platform default.
+
+#![no_std]
+
+pub use core::ffi::*;
diff --git a/rust/kernel/alloc/allocator.rs b/rust/kernel/alloc/allocator.rs
index a041bbfdabecb..439985e29fbc0 100644
--- a/rust/kernel/alloc/allocator.rs
+++ b/rust/kernel/alloc/allocator.rs
@@ -58,7 +58,7 @@ fn aligned_size(new_layout: Layout) -> usize {
 ///
 /// One of the following: `krealloc`, `vrealloc`, `kvrealloc`.
 struct ReallocFunc(
-    unsafe extern "C" fn(*const core::ffi::c_void, usize, u32) -> *mut core::ffi::c_void,
+    unsafe extern "C" fn(*const crate::ffi::c_void, usize, u32) -> *mut crate::ffi::c_void,
 );
 
 impl ReallocFunc {
diff --git a/rust/kernel/alloc/allocator_test.rs b/rust/kernel/alloc/allocator_test.rs
index 54ca85964d4af..e3240d16040bd 100644
--- a/rust/kernel/alloc/allocator_test.rs
+++ b/rust/kernel/alloc/allocator_test.rs
@@ -24,10 +24,10 @@ pub type KVmalloc = Kmalloc;
 
 extern "C" {
     #[link_name = "aligned_alloc"]
-    fn libc_aligned_alloc(align: usize, size: usize) -> *mut core::ffi::c_void;
+    fn libc_aligned_alloc(align: usize, size: usize) -> *mut crate::ffi::c_void;
 
     #[link_name = "free"]
-    fn libc_free(ptr: *mut core::ffi::c_void);
+    fn libc_free(ptr: *mut crate::ffi::c_void);
 }
 
 // SAFETY:
diff --git a/rust/kernel/alloc/kbox.rs b/rust/kernel/alloc/kbox.rs
index d69c32496b86a..9ce414361c2c6 100644
--- a/rust/kernel/alloc/kbox.rs
+++ b/rust/kernel/alloc/kbox.rs
@@ -355,17 +355,17 @@ where
 {
     type Borrowed<'a> = &'a T;
 
-    fn into_foreign(self) -> *const core::ffi::c_void {
+    fn into_foreign(self) -> *const crate::ffi::c_void {
         Box::into_raw(self) as _
     }
 
-    unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self {
+    unsafe fn from_foreign(ptr: *const crate::ffi::c_void) -> Self {
         // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous
         // call to `Self::into_foreign`.
         unsafe { Box::from_raw(ptr as _) }
     }
 
-    unsafe fn borrow<'a>(ptr: *const core::ffi::c_void) -> &'a T {
+    unsafe fn borrow<'a>(ptr: *const crate::ffi::c_void) -> &'a T {
         // SAFETY: The safety requirements of this method ensure that the object remains alive and
         // immutable for the duration of 'a.
         unsafe { &*ptr.cast() }
@@ -378,18 +378,18 @@ where
 {
     type Borrowed<'a> = Pin<&'a T>;
 
-    fn into_foreign(self) -> *const core::ffi::c_void {
+    fn into_foreign(self) -> *const crate::ffi::c_void {
         // SAFETY: We are still treating the box as pinned.
         Box::into_raw(unsafe { Pin::into_inner_unchecked(self) }) as _
     }
 
-    unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self {
+    unsafe fn from_foreign(ptr: *const crate::ffi::c_void) -> Self {
         // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous
         // call to `Self::into_foreign`.
         unsafe { Pin::new_unchecked(Box::from_raw(ptr as _)) }
     }
 
-    unsafe fn borrow<'a>(ptr: *const core::ffi::c_void) -> Pin<&'a T> {
+    unsafe fn borrow<'a>(ptr: *const crate::ffi::c_void) -> Pin<&'a T> {
         // SAFETY: The safety requirements for this function ensure that the object is still alive,
         // so it is safe to dereference the raw pointer.
         // The safety requirements of `from_foreign` also ensure that the object remains alive for
diff --git a/rust/kernel/block/mq/operations.rs b/rust/kernel/block/mq/operations.rs
index 9ba7fdfeb4b22..c8646d0d98669 100644
--- a/rust/kernel/block/mq/operations.rs
+++ b/rust/kernel/block/mq/operations.rs
@@ -131,7 +131,7 @@ impl<T: Operations> OperationsVTable<T> {
     unsafe extern "C" fn poll_callback(
         _hctx: *mut bindings::blk_mq_hw_ctx,
         _iob: *mut bindings::io_comp_batch,
-    ) -> core::ffi::c_int {
+    ) -> crate::ffi::c_int {
         T::poll().into()
     }
 
@@ -145,9 +145,9 @@ impl<T: Operations> OperationsVTable<T> {
     /// for the same context.
     unsafe extern "C" fn init_hctx_callback(
         _hctx: *mut bindings::blk_mq_hw_ctx,
-        _tagset_data: *mut core::ffi::c_void,
-        _hctx_idx: core::ffi::c_uint,
-    ) -> core::ffi::c_int {
+        _tagset_data: *mut crate::ffi::c_void,
+        _hctx_idx: crate::ffi::c_uint,
+    ) -> crate::ffi::c_int {
         from_result(|| Ok(0))
     }
 
@@ -159,7 +159,7 @@ impl<T: Operations> OperationsVTable<T> {
     /// This function may only be called by blk-mq C infrastructure.
     unsafe extern "C" fn exit_hctx_callback(
         _hctx: *mut bindings::blk_mq_hw_ctx,
-        _hctx_idx: core::ffi::c_uint,
+        _hctx_idx: crate::ffi::c_uint,
     ) {
     }
 
@@ -176,9 +176,9 @@ impl<T: Operations> OperationsVTable<T> {
     unsafe extern "C" fn init_request_callback(
         _set: *mut bindings::blk_mq_tag_set,
         rq: *mut bindings::request,
-        _hctx_idx: core::ffi::c_uint,
-        _numa_node: core::ffi::c_uint,
-    ) -> core::ffi::c_int {
+        _hctx_idx: crate::ffi::c_uint,
+        _numa_node: crate::ffi::c_uint,
+    ) -> crate::ffi::c_int {
         from_result(|| {
             // SAFETY: By the safety requirements of this function, `rq` points
             // to a valid allocation.
@@ -203,7 +203,7 @@ impl<T: Operations> OperationsVTable<T> {
     unsafe extern "C" fn exit_request_callback(
         _set: *mut bindings::blk_mq_tag_set,
         rq: *mut bindings::request,
-        _hctx_idx: core::ffi::c_uint,
+        _hctx_idx: crate::ffi::c_uint,
     ) {
         // SAFETY: The tagset invariants guarantee that all requests are allocated with extra memory
         // for the request data.
diff --git a/rust/kernel/block/mq/raw_writer.rs b/rust/kernel/block/mq/raw_writer.rs
index 9222465d670bf..7e2159e4f6a6f 100644
--- a/rust/kernel/block/mq/raw_writer.rs
+++ b/rust/kernel/block/mq/raw_writer.rs
@@ -25,7 +25,7 @@ impl<'a> RawWriter<'a> {
     }
 
     pub(crate) fn from_array<const N: usize>(
-        a: &'a mut [core::ffi::c_char; N],
+        a: &'a mut [crate::ffi::c_char; N],
     ) -> Result<RawWriter<'a>> {
         Self::new(
             // SAFETY: the buffer of `a` is valid for read and write as `u8` for
diff --git a/rust/kernel/block/mq/tag_set.rs b/rust/kernel/block/mq/tag_set.rs
index f9a1ca655a35b..d7f175a05d992 100644
--- a/rust/kernel/block/mq/tag_set.rs
+++ b/rust/kernel/block/mq/tag_set.rs
@@ -53,7 +53,7 @@ impl<T: Operations> TagSet<T> {
                     queue_depth: num_tags,
                     cmd_size,
                     flags: bindings::BLK_MQ_F_SHOULD_MERGE,
-                    driver_data: core::ptr::null_mut::<core::ffi::c_void>(),
+                    driver_data: core::ptr::null_mut::<crate::ffi::c_void>(),
                     nr_maps: num_maps,
                     ..tag_set
                 }
diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs
index 7cd3bbab52f20..52c5024324474 100644
--- a/rust/kernel/error.rs
+++ b/rust/kernel/error.rs
@@ -100,7 +100,7 @@ impl Error {
     ///
     /// It is a bug to pass an out-of-range `errno`. `EINVAL` would
     /// be returned in such a case.
-    pub fn from_errno(errno: core::ffi::c_int) -> Error {
+    pub fn from_errno(errno: crate::ffi::c_int) -> Error {
         if errno < -(bindings::MAX_ERRNO as i32) || errno >= 0 {
             // TODO: Make it a `WARN_ONCE` once available.
             crate::pr_warn!(
@@ -119,7 +119,7 @@ impl Error {
     /// Creates an [`Error`] from a kernel error code.
     ///
     /// Returns [`None`] if `errno` is out-of-range.
-    const fn try_from_errno(errno: core::ffi::c_int) -> Option<Error> {
+    const fn try_from_errno(errno: crate::ffi::c_int) -> Option<Error> {
         if errno < -(bindings::MAX_ERRNO as i32) || errno >= 0 {
             return None;
         }
@@ -133,7 +133,7 @@ impl Error {
     /// # Safety
     ///
     /// `errno` must be within error code range (i.e. `>= -MAX_ERRNO && < 0`).
-    const unsafe fn from_errno_unchecked(errno: core::ffi::c_int) -> Error {
+    const unsafe fn from_errno_unchecked(errno: crate::ffi::c_int) -> Error {
         // INVARIANT: The contract ensures the type invariant
         // will hold.
         // SAFETY: The caller guarantees `errno` is non-zero.
@@ -141,7 +141,7 @@ impl Error {
     }
 
     /// Returns the kernel error code.
-    pub fn to_errno(self) -> core::ffi::c_int {
+    pub fn to_errno(self) -> crate::ffi::c_int {
         self.0.get()
     }
 
@@ -259,7 +259,7 @@ pub type Result<T = (), E = Error> = core::result::Result<T, E>;
 
 /// Converts an integer as returned by a C kernel function to an error if it's negative, and
 /// `Ok(())` otherwise.
-pub fn to_result(err: core::ffi::c_int) -> Result {
+pub fn to_result(err: crate::ffi::c_int) -> Result {
     if err < 0 {
         Err(Error::from_errno(err))
     } else {
@@ -282,15 +282,15 @@ pub fn to_result(err: core::ffi::c_int) -> Result {
 /// fn devm_platform_ioremap_resource(
 ///     pdev: &mut PlatformDevice,
 ///     index: u32,
-/// ) -> Result<*mut core::ffi::c_void> {
+/// ) -> Result<*mut kernel::ffi::c_void> {
 ///     // SAFETY: `pdev` points to a valid platform device. There are no safety requirements
 ///     // on `index`.
 ///     from_err_ptr(unsafe { bindings::devm_platform_ioremap_resource(pdev.to_ptr(), index) })
 /// }
 /// ```
 pub fn from_err_ptr<T>(ptr: *mut T) -> Result<*mut T> {
-    // CAST: Casting a pointer to `*const core::ffi::c_void` is always valid.
-    let const_ptr: *const core::ffi::c_void = ptr.cast();
+    // CAST: Casting a pointer to `*const crate::ffi::c_void` is always valid.
+    let const_ptr: *const crate::ffi::c_void = ptr.cast();
     // SAFETY: The FFI function does not deref the pointer.
     if unsafe { bindings::IS_ERR(const_ptr) } {
         // SAFETY: The FFI function does not deref the pointer.
@@ -306,7 +306,7 @@ pub fn from_err_ptr<T>(ptr: *mut T) -> Result<*mut T> {
         //
         // SAFETY: `IS_ERR()` ensures `err` is a
         // negative value greater-or-equal to `-bindings::MAX_ERRNO`.
-        return Err(unsafe { Error::from_errno_unchecked(err as core::ffi::c_int) });
+        return Err(unsafe { Error::from_errno_unchecked(err as crate::ffi::c_int) });
     }
     Ok(ptr)
 }
@@ -326,7 +326,7 @@ pub fn from_err_ptr<T>(ptr: *mut T) -> Result<*mut T> {
 /// # use kernel::bindings;
 /// unsafe extern "C" fn probe_callback(
 ///     pdev: *mut bindings::platform_device,
-/// ) -> core::ffi::c_int {
+/// ) -> kernel::ffi::c_int {
 ///     from_result(|| {
 ///         let ptr = devm_alloc(pdev)?;
 ///         bindings::platform_set_drvdata(pdev, ptr);
diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs
index c9919ba0b6836..347049df556b1 100644
--- a/rust/kernel/init.rs
+++ b/rust/kernel/init.rs
@@ -133,7 +133,7 @@
 //! # }
 //! # // `Error::from_errno` is `pub(crate)` in the `kernel` crate, thus provide a workaround.
 //! # trait FromErrno {
-//! #     fn from_errno(errno: core::ffi::c_int) -> Error {
+//! #     fn from_errno(errno: kernel::ffi::c_int) -> Error {
 //! #         // Dummy error that can be constructed outside the `kernel` crate.
 //! #         Error::from(core::fmt::Error)
 //! #     }
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index b62451f64f6ed..bf8d7f841f942 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -27,6 +27,8 @@ compile_error!("Missing kernel configuration for conditional compilation");
 // Allow proc-macros to refer to `::kernel` inside the `kernel` crate (this crate).
 extern crate self as kernel;
 
+pub use ffi;
+
 pub mod alloc;
 #[cfg(CONFIG_BLOCK)]
 pub mod block;
diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs
index 910ce867480a8..beb62ec712c37 100644
--- a/rust/kernel/net/phy.rs
+++ b/rust/kernel/net/phy.rs
@@ -314,7 +314,7 @@ impl<T: Driver> Adapter<T> {
     /// `phydev` must be passed by the corresponding callback in `phy_driver`.
     unsafe extern "C" fn soft_reset_callback(
         phydev: *mut bindings::phy_device,
-    ) -> core::ffi::c_int {
+    ) -> crate::ffi::c_int {
         from_result(|| {
             // SAFETY: This callback is called only in contexts
             // where we hold `phy_device->lock`, so the accessors on
@@ -328,7 +328,7 @@ impl<T: Driver> Adapter<T> {
     /// # Safety
     ///
     /// `phydev` must be passed by the corresponding callback in `phy_driver`.
-    unsafe extern "C" fn probe_callback(phydev: *mut bindings::phy_device) -> core::ffi::c_int {
+    unsafe extern "C" fn probe_callback(phydev: *mut bindings::phy_device) -> crate::ffi::c_int {
         from_result(|| {
             // SAFETY: This callback is called only in contexts
             // where we can exclusively access `phy_device` because
@@ -345,7 +345,7 @@ impl<T: Driver> Adapter<T> {
     /// `phydev` must be passed by the corresponding callback in `phy_driver`.
     unsafe extern "C" fn get_features_callback(
         phydev: *mut bindings::phy_device,
-    ) -> core::ffi::c_int {
+    ) -> crate::ffi::c_int {
         from_result(|| {
             // SAFETY: This callback is called only in contexts
             // where we hold `phy_device->lock`, so the accessors on
@@ -359,7 +359,7 @@ impl<T: Driver> Adapter<T> {
     /// # Safety
     ///
     /// `phydev` must be passed by the corresponding callback in `phy_driver`.
-    unsafe extern "C" fn suspend_callback(phydev: *mut bindings::phy_device) -> core::ffi::c_int {
+    unsafe extern "C" fn suspend_callback(phydev: *mut bindings::phy_device) -> crate::ffi::c_int {
         from_result(|| {
             // SAFETY: The C core code ensures that the accessors on
             // `Device` are okay to call even though `phy_device->lock`
@@ -373,7 +373,7 @@ impl<T: Driver> Adapter<T> {
     /// # Safety
     ///
     /// `phydev` must be passed by the corresponding callback in `phy_driver`.
-    unsafe extern "C" fn resume_callback(phydev: *mut bindings::phy_device) -> core::ffi::c_int {
+    unsafe extern "C" fn resume_callback(phydev: *mut bindings::phy_device) -> crate::ffi::c_int {
         from_result(|| {
             // SAFETY: The C core code ensures that the accessors on
             // `Device` are okay to call even though `phy_device->lock`
@@ -389,7 +389,7 @@ impl<T: Driver> Adapter<T> {
     /// `phydev` must be passed by the corresponding callback in `phy_driver`.
     unsafe extern "C" fn config_aneg_callback(
         phydev: *mut bindings::phy_device,
-    ) -> core::ffi::c_int {
+    ) -> crate::ffi::c_int {
         from_result(|| {
             // SAFETY: This callback is called only in contexts
             // where we hold `phy_device->lock`, so the accessors on
@@ -405,7 +405,7 @@ impl<T: Driver> Adapter<T> {
     /// `phydev` must be passed by the corresponding callback in `phy_driver`.
     unsafe extern "C" fn read_status_callback(
         phydev: *mut bindings::phy_device,
-    ) -> core::ffi::c_int {
+    ) -> crate::ffi::c_int {
         from_result(|| {
             // SAFETY: This callback is called only in contexts
             // where we hold `phy_device->lock`, so the accessors on
@@ -421,7 +421,7 @@ impl<T: Driver> Adapter<T> {
     /// `phydev` must be passed by the corresponding callback in `phy_driver`.
     unsafe extern "C" fn match_phy_device_callback(
         phydev: *mut bindings::phy_device,
-    ) -> core::ffi::c_int {
+    ) -> crate::ffi::c_int {
         // SAFETY: This callback is called only in contexts
         // where we hold `phy_device->lock`, so the accessors on
         // `Device` are okay to call.
diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
index aff6baa521d4a..d04c12a1426d1 100644
--- a/rust/kernel/str.rs
+++ b/rust/kernel/str.rs
@@ -184,7 +184,7 @@ impl CStr {
     /// last at least `'a`. When `CStr` is alive, the memory pointed by `ptr`
     /// must not be mutated.
     #[inline]
-    pub unsafe fn from_char_ptr<'a>(ptr: *const core::ffi::c_char) -> &'a Self {
+    pub unsafe fn from_char_ptr<'a>(ptr: *const crate::ffi::c_char) -> &'a Self {
         // SAFETY: The safety precondition guarantees `ptr` is a valid pointer
         // to a `NUL`-terminated C string.
         let len = unsafe { bindings::strlen(ptr) } + 1;
@@ -247,7 +247,7 @@ impl CStr {
 
     /// Returns a C pointer to the string.
     #[inline]
-    pub const fn as_char_ptr(&self) -> *const core::ffi::c_char {
+    pub const fn as_char_ptr(&self) -> *const crate::ffi::c_char {
         self.0.as_ptr() as _
     }
 
diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs
index db9da352d588f..fa4509406ee90 100644
--- a/rust/kernel/sync/arc.rs
+++ b/rust/kernel/sync/arc.rs
@@ -332,11 +332,11 @@ impl<T: ?Sized> Arc<T> {
 impl<T: 'static> ForeignOwnable for Arc<T> {
     type Borrowed<'a> = ArcBorrow<'a, T>;
 
-    fn into_foreign(self) -> *const core::ffi::c_void {
+    fn into_foreign(self) -> *const crate::ffi::c_void {
         ManuallyDrop::new(self).ptr.as_ptr() as _
     }
 
-    unsafe fn borrow<'a>(ptr: *const core::ffi::c_void) -> ArcBorrow<'a, T> {
+    unsafe fn borrow<'a>(ptr: *const crate::ffi::c_void) -> ArcBorrow<'a, T> {
         // By the safety requirement of this function, we know that `ptr` came from
         // a previous call to `Arc::into_foreign`.
         let inner = NonNull::new(ptr as *mut ArcInner<T>).unwrap();
@@ -346,7 +346,7 @@ impl<T: 'static> ForeignOwnable for Arc<T> {
         unsafe { ArcBorrow::new(inner) }
     }
 
-    unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self {
+    unsafe fn from_foreign(ptr: *const crate::ffi::c_void) -> Self {
         // SAFETY: By the safety requirement of this function, we know that `ptr` came from
         // a previous call to `Arc::into_foreign`, which guarantees that `ptr` is valid and
         // holds a reference count increment that is transferrable to us.
diff --git a/rust/kernel/sync/condvar.rs b/rust/kernel/sync/condvar.rs
index a1a29c0bdb3aa..7df565038d7d0 100644
--- a/rust/kernel/sync/condvar.rs
+++ b/rust/kernel/sync/condvar.rs
@@ -7,6 +7,7 @@
 
 use super::{lock::Backend, lock::Guard, LockClassKey};
 use crate::{
+    ffi::{c_int, c_long},
     init::PinInit,
     pin_init,
     str::CStr,
@@ -14,7 +15,6 @@ use crate::{
     time::Jiffies,
     types::Opaque,
 };
-use core::ffi::{c_int, c_long};
 use core::marker::PhantomPinned;
 use core::ptr;
 use macros::pin_data;
diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs
index a5d89cebf106e..6d3c8874eb26a 100644
--- a/rust/kernel/sync/lock.rs
+++ b/rust/kernel/sync/lock.rs
@@ -49,7 +49,7 @@ pub unsafe trait Backend {
     /// remain valid for read indefinitely.
     unsafe fn init(
         ptr: *mut Self::State,
-        name: *const core::ffi::c_char,
+        name: *const crate::ffi::c_char,
         key: *mut bindings::lock_class_key,
     );
 
diff --git a/rust/kernel/sync/lock/mutex.rs b/rust/kernel/sync/lock/mutex.rs
index 9ce43ccb45158..0e946ebefce12 100644
--- a/rust/kernel/sync/lock/mutex.rs
+++ b/rust/kernel/sync/lock/mutex.rs
@@ -96,7 +96,7 @@ unsafe impl super::Backend for MutexBackend {
 
     unsafe fn init(
         ptr: *mut Self::State,
-        name: *const core::ffi::c_char,
+        name: *const crate::ffi::c_char,
         key: *mut bindings::lock_class_key,
     ) {
         // SAFETY: The safety requirements ensure that `ptr` is valid for writes, and `name` and
diff --git a/rust/kernel/sync/lock/spinlock.rs b/rust/kernel/sync/lock/spinlock.rs
index 040dc16975a68..9f4d128bed983 100644
--- a/rust/kernel/sync/lock/spinlock.rs
+++ b/rust/kernel/sync/lock/spinlock.rs
@@ -95,7 +95,7 @@ unsafe impl super::Backend for SpinLockBackend {
 
     unsafe fn init(
         ptr: *mut Self::State,
-        name: *const core::ffi::c_char,
+        name: *const crate::ffi::c_char,
         key: *mut bindings::lock_class_key,
     ) {
         // SAFETY: The safety requirements ensure that `ptr` is valid for writes, and `name` and
diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs
index 55dff7e088bf5..5bce090a38697 100644
--- a/rust/kernel/task.rs
+++ b/rust/kernel/task.rs
@@ -4,13 +4,9 @@
 //!
 //! C header: [`include/linux/sched.h`](srctree/include/linux/sched.h).
 
+use crate::ffi::{c_int, c_long, c_uint};
 use crate::types::Opaque;
-use core::{
-    ffi::{c_int, c_long, c_uint},
-    marker::PhantomData,
-    ops::Deref,
-    ptr,
-};
+use core::{marker::PhantomData, ops::Deref, ptr};
 
 /// A sentinel value used for infinite timeouts.
 pub const MAX_SCHEDULE_TIMEOUT: c_long = c_long::MAX;
diff --git a/rust/kernel/time.rs b/rust/kernel/time.rs
index e3bb5e89f88da..379c0f5772e57 100644
--- a/rust/kernel/time.rs
+++ b/rust/kernel/time.rs
@@ -12,10 +12,10 @@
 pub const NSEC_PER_MSEC: i64 = bindings::NSEC_PER_MSEC as i64;
 
 /// The time unit of Linux kernel. One jiffy equals (1/HZ) second.
-pub type Jiffies = core::ffi::c_ulong;
+pub type Jiffies = crate::ffi::c_ulong;
 
 /// The millisecond time unit.
-pub type Msecs = core::ffi::c_uint;
+pub type Msecs = crate::ffi::c_uint;
 
 /// Converts milliseconds to jiffies.
 #[inline]
diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index fae80814fa1c5..a7eaa29f08a40 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -29,7 +29,7 @@ pub trait ForeignOwnable: Sized {
     /// For example, it might be invalid, dangling or pointing to uninitialized memory. Using it in
     /// any way except for [`ForeignOwnable::from_foreign`], [`ForeignOwnable::borrow`],
     /// [`ForeignOwnable::try_from_foreign`] can result in undefined behavior.
-    fn into_foreign(self) -> *const core::ffi::c_void;
+    fn into_foreign(self) -> *const crate::ffi::c_void;
 
     /// Borrows a foreign-owned object.
     ///
@@ -37,7 +37,7 @@ pub trait ForeignOwnable: Sized {
     ///
     /// `ptr` must have been returned by a previous call to [`ForeignOwnable::into_foreign`] for
     /// which a previous matching [`ForeignOwnable::from_foreign`] hasn't been called yet.
-    unsafe fn borrow<'a>(ptr: *const core::ffi::c_void) -> Self::Borrowed<'a>;
+    unsafe fn borrow<'a>(ptr: *const crate::ffi::c_void) -> Self::Borrowed<'a>;
 
     /// Converts a foreign-owned object back to a Rust-owned one.
     ///
@@ -47,7 +47,7 @@ pub trait ForeignOwnable: Sized {
     /// which a previous matching [`ForeignOwnable::from_foreign`] hasn't been called yet.
     /// Additionally, all instances (if any) of values returned by [`ForeignOwnable::borrow`] for
     /// this object must have been dropped.
-    unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self;
+    unsafe fn from_foreign(ptr: *const crate::ffi::c_void) -> Self;
 
     /// Tries to convert a foreign-owned object back to a Rust-owned one.
     ///
@@ -58,7 +58,7 @@ pub trait ForeignOwnable: Sized {
     ///
     /// `ptr` must either be null or satisfy the safety requirements for
     /// [`ForeignOwnable::from_foreign`].
-    unsafe fn try_from_foreign(ptr: *const core::ffi::c_void) -> Option<Self> {
+    unsafe fn try_from_foreign(ptr: *const crate::ffi::c_void) -> Option<Self> {
         if ptr.is_null() {
             None
         } else {
@@ -72,13 +72,13 @@ pub trait ForeignOwnable: Sized {
 impl ForeignOwnable for () {
     type Borrowed<'a> = ();
 
-    fn into_foreign(self) -> *const core::ffi::c_void {
+    fn into_foreign(self) -> *const crate::ffi::c_void {
         core::ptr::NonNull::dangling().as_ptr()
     }
 
-    unsafe fn borrow<'a>(_: *const core::ffi::c_void) -> Self::Borrowed<'a> {}
+    unsafe fn borrow<'a>(_: *const crate::ffi::c_void) -> Self::Borrowed<'a> {}
 
-    unsafe fn from_foreign(_: *const core::ffi::c_void) -> Self {}
+    unsafe fn from_foreign(_: *const crate::ffi::c_void) -> Self {}
 }
 
 /// Runs a cleanup function/closure when dropped.
diff --git a/rust/kernel/uaccess.rs b/rust/kernel/uaccess.rs
index 2c953ba53c771..05b0b8d13b10d 100644
--- a/rust/kernel/uaccess.rs
+++ b/rust/kernel/uaccess.rs
@@ -8,10 +8,10 @@ use crate::{
     alloc::Flags,
     bindings,
     error::Result,
+    ffi::{c_ulong, c_void},
     prelude::*,
     transmute::{AsBytes, FromBytes},
 };
-use core::ffi::{c_ulong, c_void};
 use core::mem::{size_of, MaybeUninit};
 
 /// The type used for userspace addresses.
@@ -45,7 +45,7 @@ pub type UserPtr = usize;
 /// every byte in the region.
 ///
 /// ```no_run
-/// use core::ffi::c_void;
+/// use kernel::ffi::c_void;
 /// use kernel::error::Result;
 /// use kernel::uaccess::{UserPtr, UserSlice};
 ///
@@ -67,7 +67,7 @@ pub type UserPtr = usize;
 /// Example illustrating a TOCTOU (time-of-check to time-of-use) bug.
 ///
 /// ```no_run
-/// use core::ffi::c_void;
+/// use kernel::ffi::c_void;
 /// use kernel::error::{code::EINVAL, Result};
 /// use kernel::uaccess::{UserPtr, UserSlice};
 ///
diff --git a/rust/macros/module.rs b/rust/macros/module.rs
index aef3b132f32b3..e7a087b7e8849 100644
--- a/rust/macros/module.rs
+++ b/rust/macros/module.rs
@@ -253,7 +253,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
                     #[doc(hidden)]
                     #[no_mangle]
                     #[link_section = \".init.text\"]
-                    pub unsafe extern \"C\" fn init_module() -> core::ffi::c_int {{
+                    pub unsafe extern \"C\" fn init_module() -> kernel::ffi::c_int {{
                         // SAFETY: This function is inaccessible to the outside due to the double
                         // module wrapping it. It is called exactly once by the C side via its
                         // unique name.
@@ -292,7 +292,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
                     #[doc(hidden)]
                     #[link_section = \"{initcall_section}\"]
                     #[used]
-                    pub static __{name}_initcall: extern \"C\" fn() -> core::ffi::c_int = __{name}_init;
+                    pub static __{name}_initcall: extern \"C\" fn() -> kernel::ffi::c_int = __{name}_init;
 
                     #[cfg(not(MODULE))]
                     #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)]
@@ -307,7 +307,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
                     #[cfg(not(MODULE))]
                     #[doc(hidden)]
                     #[no_mangle]
-                    pub extern \"C\" fn __{name}_init() -> core::ffi::c_int {{
+                    pub extern \"C\" fn __{name}_init() -> kernel::ffi::c_int {{
                         // SAFETY: This function is inaccessible to the outside due to the double
                         // module wrapping it. It is called exactly once by the C side via its
                         // placement above in the initcall section.
@@ -330,7 +330,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
                     /// # Safety
                     ///
                     /// This function must only be called once.
-                    unsafe fn __init() -> core::ffi::c_int {{
+                    unsafe fn __init() -> kernel::ffi::c_int {{
                         match <{type_} as kernel::Module>::init(&super::super::THIS_MODULE) {{
                             Ok(m) => {{
                                 // SAFETY: No data race, since `__MOD` can only be accessed by this

From 010e12aa4925b36700ebacb763a7e6cfd771d9a2 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sun, 3 Nov 2024 15:51:41 +0100
Subject: [PATCH 1016/1530] riscv: Move cpufeature.h macros into their own
 header

asm/cmpxchg.h will soon need riscv_has_extension_unlikely() macros and
then needs to include asm/cpufeature.h which introduces a lot of header
circular dependencies.

So move the riscv_has_extension_XXX() macros into their own header which
prevents such circular dependencies by including a restricted number of
headers.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-2-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/cpufeature-macros.h | 66 ++++++++++++++++++++++
 arch/riscv/include/asm/cpufeature.h        | 61 ++------------------
 2 files changed, 70 insertions(+), 57 deletions(-)
 create mode 100644 arch/riscv/include/asm/cpufeature-macros.h

diff --git a/arch/riscv/include/asm/cpufeature-macros.h b/arch/riscv/include/asm/cpufeature-macros.h
new file mode 100644
index 0000000000000..a8103edbf51f8
--- /dev/null
+++ b/arch/riscv/include/asm/cpufeature-macros.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2022-2024 Rivos, Inc
+ */
+
+#ifndef _ASM_CPUFEATURE_MACROS_H
+#define _ASM_CPUFEATURE_MACROS_H
+
+#include <asm/hwcap.h>
+#include <asm/alternative-macros.h>
+
+#define STANDARD_EXT		0
+
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit);
+#define riscv_isa_extension_available(isa_bitmap, ext)	\
+	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
+
+static __always_inline bool __riscv_has_extension_likely(const unsigned long vendor,
+							 const unsigned long ext)
+{
+	asm goto(ALTERNATIVE("j	%l[l_no]", "nop", %[vendor], %[ext], 1)
+	:
+	: [vendor] "i" (vendor), [ext] "i" (ext)
+	:
+	: l_no);
+
+	return true;
+l_no:
+	return false;
+}
+
+static __always_inline bool __riscv_has_extension_unlikely(const unsigned long vendor,
+							   const unsigned long ext)
+{
+	asm goto(ALTERNATIVE("nop", "j	%l[l_yes]", %[vendor], %[ext], 1)
+	:
+	: [vendor] "i" (vendor), [ext] "i" (ext)
+	:
+	: l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+static __always_inline bool riscv_has_extension_unlikely(const unsigned long ext)
+{
+	compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
+		return __riscv_has_extension_unlikely(STANDARD_EXT, ext);
+
+	return __riscv_isa_extension_available(NULL, ext);
+}
+
+static __always_inline bool riscv_has_extension_likely(const unsigned long ext)
+{
+	compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
+		return __riscv_has_extension_likely(STANDARD_EXT, ext);
+
+	return __riscv_isa_extension_available(NULL, ext);
+}
+
+#endif /* _ASM_CPUFEATURE_MACROS_H */
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 45f9c1171a486..87ed88fc950da 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -8,9 +8,11 @@
 
 #include <linux/bitmap.h>
 #include <linux/jump_label.h>
+#include <linux/kconfig.h>
+#include <linux/percpu-defs.h>
+#include <linux/threads.h>
 #include <asm/hwcap.h>
-#include <asm/alternative-macros.h>
-#include <asm/errno.h>
+#include <asm/cpufeature-macros.h>
 
 /*
  * These are probed via a device_initcall(), via either the SBI or directly
@@ -103,61 +105,6 @@ extern const size_t riscv_isa_ext_count;
 extern bool riscv_isa_fallback;
 
 unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
-
-#define STANDARD_EXT		0
-
-bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit);
-#define riscv_isa_extension_available(isa_bitmap, ext)	\
-	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
-
-static __always_inline bool __riscv_has_extension_likely(const unsigned long vendor,
-							 const unsigned long ext)
-{
-	asm goto(ALTERNATIVE("j	%l[l_no]", "nop", %[vendor], %[ext], 1)
-	:
-	: [vendor] "i" (vendor), [ext] "i" (ext)
-	:
-	: l_no);
-
-	return true;
-l_no:
-	return false;
-}
-
-static __always_inline bool __riscv_has_extension_unlikely(const unsigned long vendor,
-							   const unsigned long ext)
-{
-	asm goto(ALTERNATIVE("nop", "j	%l[l_yes]", %[vendor], %[ext], 1)
-	:
-	: [vendor] "i" (vendor), [ext] "i" (ext)
-	:
-	: l_yes);
-
-	return false;
-l_yes:
-	return true;
-}
-
-static __always_inline bool riscv_has_extension_unlikely(const unsigned long ext)
-{
-	compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
-
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
-		return __riscv_has_extension_unlikely(STANDARD_EXT, ext);
-
-	return __riscv_isa_extension_available(NULL, ext);
-}
-
-static __always_inline bool riscv_has_extension_likely(const unsigned long ext)
-{
-	compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
-
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
-		return __riscv_has_extension_likely(STANDARD_EXT, ext);
-
-	return __riscv_isa_extension_available(NULL, ext);
-}
-
 static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext)
 {
 	compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");

From af042c457db07db4bc1baa5c22d089cab69cfc5b Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sun, 3 Nov 2024 15:51:42 +0100
Subject: [PATCH 1017/1530] riscv: Do not fail to build on byte/halfword
 operations with Zawrs

riscv does not have lr instructions on byte and halfword but the
qspinlock implementation actually uses such atomics provided by the
Zabha extension, so those sizes are legitimate.

Then instead of failing to build, just fallback to the !Zawrs path.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-3-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/cmpxchg.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index ebbce134917cc..ac1d7df898ef4 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -245,6 +245,11 @@ static __always_inline void __cmpwait(volatile void *ptr,
 		 : : : : no_zawrs);
 
 	switch (size) {
+	case 1:
+		fallthrough;
+	case 2:
+		/* RISC-V doesn't have lr instructions on byte and half-word. */
+		goto no_zawrs;
 	case 4:
 		asm volatile(
 		"	lr.w	%0, %1\n"

From 38acdee32d23f789e866488c99867fd497d43c86 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sun, 3 Nov 2024 15:51:43 +0100
Subject: [PATCH 1018/1530] riscv: Implement cmpxchg32/64() using Zacas

This adds runtime support for Zacas in cmpxchg operations.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-4-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig               | 16 +++++++++++
 arch/riscv/Makefile              |  3 ++
 arch/riscv/include/asm/cmpxchg.h | 48 +++++++++++++++++++++-----------
 3 files changed, 50 insertions(+), 17 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 62545946ecf43..3542efe3088b9 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -632,6 +632,22 @@ config RISCV_ISA_ZAWRS
 	  use of these instructions in the kernel when the Zawrs extension is
 	  detected at boot.
 
+config TOOLCHAIN_HAS_ZACAS
+	bool
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zacas)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zacas)
+	depends on AS_HAS_OPTION_ARCH
+
+config RISCV_ISA_ZACAS
+	bool "Zacas extension support for atomic CAS"
+	depends on TOOLCHAIN_HAS_ZACAS
+	depends on RISCV_ALTERNATIVE
+	default y
+	help
+	  Enable the use of the Zacas ISA-extension to implement kernel atomic
+	  cmpxchg operations when it is detected at boot.
+
 	  If you don't know what to do here, say Y.
 
 config TOOLCHAIN_HAS_ZBB
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index d469db9f46f42..3700a15744130 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -82,6 +82,9 @@ else
 riscv-march-$(CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI) := $(riscv-march-y)_zicsr_zifencei
 endif
 
+# Check if the toolchain supports Zacas
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZACAS) := $(riscv-march-y)_zacas
+
 # Remove F,D,V from isa string for all. Keep extensions between "fd" and "v" by
 # matching non-v and non-multi-letter extensions out with the filter ([^v_]*)
 KBUILD_CFLAGS += -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)fd([^v_]*)v?/\1\2/')
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index ac1d7df898ef4..39c1daf39f6af 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -12,6 +12,7 @@
 #include <asm/fence.h>
 #include <asm/hwcap.h>
 #include <asm/insn-def.h>
+#include <asm/cpufeature-macros.h>
 
 #define __arch_xchg_masked(sc_sfx, prepend, append, r, p, n)		\
 ({									\
@@ -137,24 +138,37 @@
 	r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
 })
 
-#define __arch_cmpxchg(lr_sfx, sc_sfx, prepend, append, r, p, co, o, n)	\
+#define __arch_cmpxchg(lr_sfx, sc_cas_sfx, prepend, append, r, p, co, o, n)	\
 ({									\
-	register unsigned int __rc;					\
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) &&			\
+	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) {	\
+		r = o;							\
 									\
-	__asm__ __volatile__ (						\
-		prepend							\
-		"0:	lr" lr_sfx " %0, %2\n"				\
-		"	bne  %0, %z3, 1f\n"				\
-		"	sc" sc_sfx " %1, %z4, %2\n"			\
-		"	bnez %1, 0b\n"					\
-		append							\
-		"1:\n"							\
-		: "=&r" (r), "=&r" (__rc), "+A" (*(p))			\
-		: "rJ" (co o), "rJ" (n)					\
-		: "memory");						\
+		__asm__ __volatile__ (					\
+			prepend						\
+			"	amocas" sc_cas_sfx " %0, %z2, %1\n"	\
+			append						\
+			: "+&r" (r), "+A" (*(p))			\
+			: "rJ" (n)					\
+			: "memory");					\
+	} else {							\
+		register unsigned int __rc;				\
+									\
+		__asm__ __volatile__ (					\
+			prepend						\
+			"0:	lr" lr_sfx " %0, %2\n"			\
+			"	bne  %0, %z3, 1f\n"			\
+			"	sc" sc_cas_sfx " %1, %z4, %2\n"		\
+			"	bnez %1, 0b\n"				\
+			append						\
+			"1:\n"						\
+			: "=&r" (r), "=&r" (__rc), "+A" (*(p))		\
+			: "rJ" (co o), "rJ" (n)				\
+			: "memory");					\
+	}								\
 })
 
-#define _arch_cmpxchg(ptr, old, new, sc_sfx, prepend, append)		\
+#define _arch_cmpxchg(ptr, old, new, sc_cas_sfx, prepend, append)	\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
 	__typeof__(*(__ptr)) __old = (old);				\
@@ -164,15 +178,15 @@
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
 	case 2:								\
-		__arch_cmpxchg_masked(sc_sfx, prepend, append,		\
+		__arch_cmpxchg_masked(sc_cas_sfx, prepend, append,	\
 					__ret, __ptr, __old, __new);	\
 		break;							\
 	case 4:								\
-		__arch_cmpxchg(".w", ".w" sc_sfx, prepend, append,	\
+		__arch_cmpxchg(".w", ".w" sc_cas_sfx, prepend, append,	\
 				__ret, __ptr, (long), __old, __new);	\
 		break;							\
 	case 8:								\
-		__arch_cmpxchg(".d", ".d" sc_sfx, prepend, append,	\
+		__arch_cmpxchg(".d", ".d" sc_cas_sfx, prepend, append,	\
 				__ret, __ptr, /**/, __old, __new);	\
 		break;							\
 	default:							\

From 51624ddcf59dd78c810fd7da768d688e193b42d6 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sun, 3 Nov 2024 15:51:44 +0100
Subject: [PATCH 1019/1530] dt-bindings: riscv: Add Zabha ISA extension
 description

Add description for the Zabha ISA extension which was ratified in April
2024.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Guo Ren <guoren@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-5-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/devicetree/bindings/riscv/extensions.yaml | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index 2cf2026cff574..db062107823bf 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -178,6 +178,12 @@ properties:
             as ratified at commit 4a69197e5617 ("Update to ratified state") of
             riscv-svvptc.
 
+        - const: zabha
+          description: |
+            The Zabha extension for Byte and Halfword Atomic Memory Operations
+            as ratified at commit 49f49c842ff9 ("Update to Rafified state") of
+            riscv-zabha.
+
         - const: zacas
           description: |
             The Zacas extension for Atomic Compare-and-Swap (CAS) instructions

From 1658ef4314b37ff4858a6c207646ff9d280ca4f7 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sun, 3 Nov 2024 15:51:45 +0100
Subject: [PATCH 1020/1530] riscv: Implement cmpxchg8/16() using Zabha

This adds runtime support for Zabha in cmpxchg8/16() operations.

Note that in the absence of Zacas support in the toolchain, CAS
instructions from Zabha won't be used.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-6-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig               | 18 ++++++++
 arch/riscv/Makefile              |  3 ++
 arch/riscv/include/asm/cmpxchg.h | 78 ++++++++++++++++++++------------
 arch/riscv/include/asm/hwcap.h   |  1 +
 arch/riscv/kernel/cpufeature.c   |  1 +
 5 files changed, 72 insertions(+), 29 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 3542efe3088b9..668be90a42e45 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -632,6 +632,24 @@ config RISCV_ISA_ZAWRS
 	  use of these instructions in the kernel when the Zawrs extension is
 	  detected at boot.
 
+config TOOLCHAIN_HAS_ZABHA
+	bool
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zabha)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zabha)
+	depends on AS_HAS_OPTION_ARCH
+
+config RISCV_ISA_ZABHA
+	bool "Zabha extension support for atomic byte/halfword operations"
+	depends on TOOLCHAIN_HAS_ZABHA
+	depends on RISCV_ALTERNATIVE
+	default y
+	help
+	  Enable the use of the Zabha ISA-extension to implement kernel
+	  byte/halfword atomic memory operations when it is detected at boot.
+
+	  If you don't know what to do here, say Y.
+
 config TOOLCHAIN_HAS_ZACAS
 	bool
 	default y
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 3700a15744130..9fe1ee740dda8 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -85,6 +85,9 @@ endif
 # Check if the toolchain supports Zacas
 riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZACAS) := $(riscv-march-y)_zacas
 
+# Check if the toolchain supports Zabha
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZABHA) := $(riscv-march-y)_zabha
+
 # Remove F,D,V from isa string for all. Keep extensions between "fd" and "v" by
 # matching non-v and non-multi-letter extensions out with the filter ([^v_]*)
 KBUILD_CFLAGS += -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)fd([^v_]*)v?/\1\2/')
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 39c1daf39f6af..1f4cd12e4664e 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -108,34 +108,49 @@
  * indicated by comparing RETURN with OLD.
  */
 
-#define __arch_cmpxchg_masked(sc_sfx, prepend, append, r, p, o, n)	\
-({									\
-	u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
-	ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
-	ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
-			<< __s;						\
-	ulong __newx = (ulong)(n) << __s;				\
-	ulong __oldx = (ulong)(o) << __s;				\
-	ulong __retx;							\
-	ulong __rc;							\
-									\
-	__asm__ __volatile__ (						\
-		prepend							\
-		"0:	lr.w %0, %2\n"					\
-		"	and  %1, %0, %z5\n"				\
-		"	bne  %1, %z3, 1f\n"				\
-		"	and  %1, %0, %z6\n"				\
-		"	or   %1, %1, %z4\n"				\
-		"	sc.w" sc_sfx " %1, %1, %2\n"			\
-		"	bnez %1, 0b\n"					\
-		append							\
-		"1:\n"							\
-		: "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
-		: "rJ" ((long)__oldx), "rJ" (__newx),			\
-		  "rJ" (__mask), "rJ" (~__mask)				\
-		: "memory");						\
-									\
-	r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+#define __arch_cmpxchg_masked(sc_sfx, cas_sfx, prepend, append, r, p, o, n)	\
+({										\
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&				\
+	    IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) &&				\
+	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA) &&		\
+	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) {		\
+		r = o;								\
+										\
+		__asm__ __volatile__ (						\
+			prepend							\
+			"	amocas" cas_sfx " %0, %z2, %1\n"		\
+			append							\
+			: "+&r" (r), "+A" (*(p))				\
+			: "rJ" (n)						\
+			: "memory");						\
+	} else {								\
+		u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
+		ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
+		ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
+			       << __s;						\
+		ulong __newx = (ulong)(n) << __s;				\
+		ulong __oldx = (ulong)(o) << __s;				\
+		ulong __retx;							\
+		ulong __rc;							\
+										\
+		__asm__ __volatile__ (						\
+			prepend							\
+			"0:	lr.w %0, %2\n"					\
+			"	and  %1, %0, %z5\n"				\
+			"	bne  %1, %z3, 1f\n"				\
+			"	and  %1, %0, %z6\n"				\
+			"	or   %1, %1, %z4\n"				\
+			"	sc.w" sc_sfx " %1, %1, %2\n"			\
+			"	bnez %1, 0b\n"					\
+			append							\
+			"1:\n"							\
+			: "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
+			: "rJ" ((long)__oldx), "rJ" (__newx),			\
+			  "rJ" (__mask), "rJ" (~__mask)				\
+			: "memory");						\
+										\
+		r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+	}									\
 })
 
 #define __arch_cmpxchg(lr_sfx, sc_cas_sfx, prepend, append, r, p, co, o, n)	\
@@ -177,8 +192,13 @@
 									\
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
+		__arch_cmpxchg_masked(sc_cas_sfx, ".b" sc_cas_sfx,	\
+					prepend, append,		\
+					__ret, __ptr, __old, __new);    \
+		break;							\
 	case 2:								\
-		__arch_cmpxchg_masked(sc_cas_sfx, prepend, append,	\
+		__arch_cmpxchg_masked(sc_cas_sfx, ".h" sc_cas_sfx,	\
+					prepend, append,		\
 					__ret, __ptr, __old, __new);	\
 		break;							\
 	case 4:								\
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 46d9de54179ed..74bcb0e2bd1f7 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -93,6 +93,7 @@
 #define RISCV_ISA_EXT_ZCMOP		84
 #define RISCV_ISA_EXT_ZAWRS		85
 #define RISCV_ISA_EXT_SVVPTC		86
+#define RISCV_ISA_EXT_ZABHA		87
 
 #define RISCV_ISA_EXT_XLINUXENVCFG	127
 
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 3a8eeaa9310c3..5e743d8d34f5a 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -322,6 +322,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
 	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
 	__RISCV_ISA_EXT_DATA(zimop, RISCV_ISA_EXT_ZIMOP),
+	__RISCV_ISA_EXT_DATA(zabha, RISCV_ISA_EXT_ZABHA),
 	__RISCV_ISA_EXT_DATA(zacas, RISCV_ISA_EXT_ZACAS),
 	__RISCV_ISA_EXT_DATA(zawrs, RISCV_ISA_EXT_ZAWRS),
 	__RISCV_ISA_EXT_DATA(zfa, RISCV_ISA_EXT_ZFA),

From 6116e22ef33a8239f3d53bb25377e9ed733c4176 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sun, 3 Nov 2024 15:51:46 +0100
Subject: [PATCH 1021/1530] riscv: Improve zacas fully-ordered cmpxchg()

The current fully-ordered cmpxchgXX() implementation results in:

  amocas.X.rl     a5,a4,(s1)
  fence           rw,rw

This provides enough sync but we can actually use the following better
mapping instead:

  amocas.X.aqrl   a5,a4,(s1)

Suggested-by: Andrea Parri <andrea@rivosinc.com>
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-7-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/cmpxchg.h | 92 ++++++++++++++++++++++----------
 1 file changed, 64 insertions(+), 28 deletions(-)

diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 1f4cd12e4664e..052418aba11a1 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -107,8 +107,10 @@
  * store NEW in MEM.  Return the initial value in MEM.  Success is
  * indicated by comparing RETURN with OLD.
  */
-
-#define __arch_cmpxchg_masked(sc_sfx, cas_sfx, prepend, append, r, p, o, n)	\
+#define __arch_cmpxchg_masked(sc_sfx, cas_sfx,					\
+			      sc_prepend, sc_append,				\
+			      cas_prepend, cas_append,				\
+			      r, p, o, n)					\
 ({										\
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&				\
 	    IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) &&				\
@@ -117,9 +119,9 @@
 		r = o;								\
 										\
 		__asm__ __volatile__ (						\
-			prepend							\
+			cas_prepend							\
 			"	amocas" cas_sfx " %0, %z2, %1\n"		\
-			append							\
+			cas_append							\
 			: "+&r" (r), "+A" (*(p))				\
 			: "rJ" (n)						\
 			: "memory");						\
@@ -134,7 +136,7 @@
 		ulong __rc;							\
 										\
 		__asm__ __volatile__ (						\
-			prepend							\
+			sc_prepend							\
 			"0:	lr.w %0, %2\n"					\
 			"	and  %1, %0, %z5\n"				\
 			"	bne  %1, %z3, 1f\n"				\
@@ -142,7 +144,7 @@
 			"	or   %1, %1, %z4\n"				\
 			"	sc.w" sc_sfx " %1, %1, %2\n"			\
 			"	bnez %1, 0b\n"					\
-			append							\
+			sc_append							\
 			"1:\n"							\
 			: "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
 			: "rJ" ((long)__oldx), "rJ" (__newx),			\
@@ -153,16 +155,19 @@
 	}									\
 })
 
-#define __arch_cmpxchg(lr_sfx, sc_cas_sfx, prepend, append, r, p, co, o, n)	\
+#define __arch_cmpxchg(lr_sfx, sc_sfx, cas_sfx,				\
+		       sc_prepend, sc_append,				\
+		       cas_prepend, cas_append,				\
+		       r, p, co, o, n)					\
 ({									\
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) &&			\
 	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) {	\
 		r = o;							\
 									\
 		__asm__ __volatile__ (					\
-			prepend						\
-			"	amocas" sc_cas_sfx " %0, %z2, %1\n"	\
-			append						\
+			cas_prepend					\
+			"	amocas" cas_sfx " %0, %z2, %1\n"	\
+			cas_append					\
 			: "+&r" (r), "+A" (*(p))			\
 			: "rJ" (n)					\
 			: "memory");					\
@@ -170,12 +175,12 @@
 		register unsigned int __rc;				\
 									\
 		__asm__ __volatile__ (					\
-			prepend						\
+			sc_prepend					\
 			"0:	lr" lr_sfx " %0, %2\n"			\
 			"	bne  %0, %z3, 1f\n"			\
-			"	sc" sc_cas_sfx " %1, %z4, %2\n"		\
+			"	sc" sc_sfx " %1, %z4, %2\n"		\
 			"	bnez %1, 0b\n"				\
-			append						\
+			sc_append					\
 			"1:\n"						\
 			: "=&r" (r), "=&r" (__rc), "+A" (*(p))		\
 			: "rJ" (co o), "rJ" (n)				\
@@ -183,7 +188,9 @@
 	}								\
 })
 
-#define _arch_cmpxchg(ptr, old, new, sc_cas_sfx, prepend, append)	\
+#define _arch_cmpxchg(ptr, old, new, sc_sfx, cas_sfx,			\
+		      sc_prepend, sc_append,				\
+		      cas_prepend, cas_append)				\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
 	__typeof__(*(__ptr)) __old = (old);				\
@@ -192,22 +199,28 @@
 									\
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
-		__arch_cmpxchg_masked(sc_cas_sfx, ".b" sc_cas_sfx,	\
-					prepend, append,		\
-					__ret, __ptr, __old, __new);    \
+		__arch_cmpxchg_masked(sc_sfx, ".b" cas_sfx,		\
+				      sc_prepend, sc_append,		\
+				      cas_prepend, cas_append,		\
+				      __ret, __ptr, __old, __new);	\
 		break;							\
 	case 2:								\
-		__arch_cmpxchg_masked(sc_cas_sfx, ".h" sc_cas_sfx,	\
-					prepend, append,		\
-					__ret, __ptr, __old, __new);	\
+		__arch_cmpxchg_masked(sc_sfx, ".h" cas_sfx,		\
+				      sc_prepend, sc_append,		\
+				      cas_prepend, cas_append,		\
+				      __ret, __ptr, __old, __new);	\
 		break;							\
 	case 4:								\
-		__arch_cmpxchg(".w", ".w" sc_cas_sfx, prepend, append,	\
-				__ret, __ptr, (long), __old, __new);	\
+		__arch_cmpxchg(".w", ".w" sc_sfx, ".w" cas_sfx,		\
+			       sc_prepend, sc_append,			\
+			       cas_prepend, cas_append,			\
+			       __ret, __ptr, (long), __old, __new);	\
 		break;							\
 	case 8:								\
-		__arch_cmpxchg(".d", ".d" sc_cas_sfx, prepend, append,	\
-				__ret, __ptr, /**/, __old, __new);	\
+		__arch_cmpxchg(".d", ".d" sc_sfx, ".d" cas_sfx,		\
+			       sc_prepend, sc_append,			\
+			       cas_prepend, cas_append,			\
+			       __ret, __ptr, /**/, __old, __new);	\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
@@ -215,17 +228,40 @@
 	(__typeof__(*(__ptr)))__ret;					\
 })
 
+/*
+ * These macros are here to improve the readability of the arch_cmpxchg_XXX()
+ * macros.
+ */
+#define SC_SFX(x)	x
+#define CAS_SFX(x)	x
+#define SC_PREPEND(x)	x
+#define SC_APPEND(x)	x
+#define CAS_PREPEND(x)	x
+#define CAS_APPEND(x)	x
+
 #define arch_cmpxchg_relaxed(ptr, o, n)					\
-	_arch_cmpxchg((ptr), (o), (n), "", "", "")
+	_arch_cmpxchg((ptr), (o), (n),					\
+		      SC_SFX(""), CAS_SFX(""),				\
+		      SC_PREPEND(""), SC_APPEND(""),			\
+		      CAS_PREPEND(""), CAS_APPEND(""))
 
 #define arch_cmpxchg_acquire(ptr, o, n)					\
-	_arch_cmpxchg((ptr), (o), (n), "", "", RISCV_ACQUIRE_BARRIER)
+	_arch_cmpxchg((ptr), (o), (n),					\
+		      SC_SFX(""), CAS_SFX(""),				\
+		      SC_PREPEND(""), SC_APPEND(RISCV_ACQUIRE_BARRIER),	\
+		      CAS_PREPEND(""), CAS_APPEND(RISCV_ACQUIRE_BARRIER))
 
 #define arch_cmpxchg_release(ptr, o, n)					\
-	_arch_cmpxchg((ptr), (o), (n), "", RISCV_RELEASE_BARRIER, "")
+	_arch_cmpxchg((ptr), (o), (n),					\
+		      SC_SFX(""), CAS_SFX(""),				\
+		      SC_PREPEND(RISCV_RELEASE_BARRIER), SC_APPEND(""),	\
+		      CAS_PREPEND(RISCV_RELEASE_BARRIER), CAS_APPEND(""))
 
 #define arch_cmpxchg(ptr, o, n)						\
-	_arch_cmpxchg((ptr), (o), (n), ".rl", "", "	fence rw, rw\n")
+	_arch_cmpxchg((ptr), (o), (n),					\
+		      SC_SFX(".rl"), CAS_SFX(".aqrl"),			\
+		      SC_PREPEND(""), SC_APPEND(RISCV_FULL_BARRIER),	\
+		      CAS_PREPEND(""), CAS_APPEND(""))
 
 #define arch_cmpxchg_local(ptr, o, n)					\
 	arch_cmpxchg_relaxed((ptr), (o), (n))

From f7bd2be7663c7de1dde27dadd352b2c3f4e19106 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sun, 3 Nov 2024 15:51:47 +0100
Subject: [PATCH 1022/1530] riscv: Implement arch_cmpxchg128() using Zacas

Now that Zacas is supported in the kernel, let's use the double word
atomic version of amocas to improve the SLUB allocator.

Note that we have to select fixed registers, otherwise gcc fails to pick
even registers and then produces a reserved encoding which fails to
assemble.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-8-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig               |  1 +
 arch/riscv/include/asm/cmpxchg.h | 38 ++++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 668be90a42e45..093ee65373312 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -115,6 +115,7 @@ config RISCV
 	select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO
 	select HARDIRQS_SW_RESEND
 	select HAS_IOPORT if MMU
+	select HAVE_ALIGNED_STRUCT_PAGE
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 052418aba11a1..f95929f538b2d 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -296,6 +296,44 @@
 	arch_cmpxchg_release((ptr), (o), (n));				\
 })
 
+#if defined(CONFIG_64BIT) && defined(CONFIG_RISCV_ISA_ZACAS)
+
+#define system_has_cmpxchg128()        riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)
+
+union __u128_halves {
+	u128 full;
+	struct {
+		u64 low, high;
+	};
+};
+
+#define __arch_cmpxchg128(p, o, n, cas_sfx)					\
+({										\
+	__typeof__(*(p)) __o = (o);                                             \
+	union __u128_halves __hn = { .full = (n) };				\
+	union __u128_halves __ho = { .full = (__o) };				\
+	register unsigned long t1 asm ("t1") = __hn.low;			\
+	register unsigned long t2 asm ("t2") = __hn.high;			\
+	register unsigned long t3 asm ("t3") = __ho.low;			\
+	register unsigned long t4 asm ("t4") = __ho.high;			\
+										\
+	__asm__ __volatile__ (							\
+		 "       amocas.q" cas_sfx " %0, %z3, %2"			\
+		 : "+&r" (t3), "+&r" (t4), "+A" (*(p))				\
+		 : "rJ" (t1), "rJ" (t2)						\
+		 : "memory");							\
+										\
+		 ((u128)t4 << 64) | t3;						\
+})
+
+#define arch_cmpxchg128(ptr, o, n)						\
+	__arch_cmpxchg128((ptr), (o), (n), ".aqrl")
+
+#define arch_cmpxchg128_local(ptr, o, n)					\
+	__arch_cmpxchg128((ptr), (o), (n), "")
+
+#endif /* CONFIG_64BIT && CONFIG_RISCV_ISA_ZACAS */
+
 #ifdef CONFIG_RISCV_ISA_ZAWRS
 /*
  * Despite wrs.nto being "WRS-with-no-timeout", in the absence of changes to

From 97ddab7fbea8fceb044108b64ba2ee2c96ff8dab Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sun, 3 Nov 2024 15:51:48 +0100
Subject: [PATCH 1023/1530] riscv: Implement xchg8/16() using Zabha

This adds runtime support for Zabha in xchg8/16() operations.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-9-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/cmpxchg.h | 65 ++++++++++++++++++++------------
 1 file changed, 41 insertions(+), 24 deletions(-)

diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index f95929f538b2d..4cadc56220fea 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -14,29 +14,41 @@
 #include <asm/insn-def.h>
 #include <asm/cpufeature-macros.h>
 
-#define __arch_xchg_masked(sc_sfx, prepend, append, r, p, n)		\
-({									\
-	u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
-	ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
-	ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
-			<< __s;						\
-	ulong __newx = (ulong)(n) << __s;				\
-	ulong __retx;							\
-	ulong __rc;							\
-									\
-	__asm__ __volatile__ (						\
-	       prepend							\
-	       "0:	lr.w %0, %2\n"					\
-	       "	and  %1, %0, %z4\n"				\
-	       "	or   %1, %1, %z3\n"				\
-	       "	sc.w" sc_sfx " %1, %1, %2\n"			\
-	       "	bnez %1, 0b\n"					\
-	       append							\
-	       : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
-	       : "rJ" (__newx), "rJ" (~__mask)				\
-	       : "memory");						\
-									\
-	r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+#define __arch_xchg_masked(sc_sfx, swap_sfx, prepend, sc_append,		\
+			   swap_append, r, p, n)				\
+({										\
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&				\
+	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA)) {		\
+		__asm__ __volatile__ (						\
+			prepend							\
+			"	amoswap" swap_sfx " %0, %z2, %1\n"		\
+			swap_append						\
+			: "=&r" (r), "+A" (*(p))				\
+			: "rJ" (n)						\
+			: "memory");						\
+	} else {								\
+		u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
+		ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
+		ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
+				<< __s;						\
+		ulong __newx = (ulong)(n) << __s;				\
+		ulong __retx;							\
+		ulong __rc;							\
+										\
+		__asm__ __volatile__ (						\
+		       prepend							\
+		       "0:	lr.w %0, %2\n"					\
+		       "	and  %1, %0, %z4\n"				\
+		       "	or   %1, %1, %z3\n"				\
+		       "	sc.w" sc_sfx " %1, %1, %2\n"			\
+		       "	bnez %1, 0b\n"					\
+		       sc_append						\
+		       : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
+		       : "rJ" (__newx), "rJ" (~__mask)				\
+		       : "memory");						\
+										\
+		r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+	}									\
 })
 
 #define __arch_xchg(sfx, prepend, append, r, p, n)			\
@@ -59,8 +71,13 @@
 									\
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
+		__arch_xchg_masked(sc_sfx, ".b" swap_sfx,		\
+				   prepend, sc_append, swap_append,	\
+				   __ret, __ptr, __new);		\
+		break;							\
 	case 2:								\
-		__arch_xchg_masked(sc_sfx, prepend, sc_append,		\
+		__arch_xchg_masked(sc_sfx, ".h" swap_sfx,		\
+				   prepend, sc_append, swap_append,	\
 				   __ret, __ptr, __new);		\
 		break;							\
 	case 4:								\

From cbe82e140bb76e1aa9f808cc841654a25b70d4e5 Mon Sep 17 00:00:00 2001
From: Guo Ren <guoren@linux.alibaba.com>
Date: Sun, 3 Nov 2024 15:51:49 +0100
Subject: [PATCH 1024/1530] asm-generic: ticket-lock: Reuse arch_spinlock_t of
 qspinlock

The arch_spinlock_t of qspinlock has contained the atomic_t val, which
satisfies the ticket-lock requirement. Thus, unify the arch_spinlock_t
into qspinlock_types.h. This is the preparation for the next combo
spinlock.

Reviewed-by: Leonardo Bras <leobras@redhat.com>
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/linux-riscv/CAK8P3a2rnz9mQqhN6-e0CGUUv9rntRELFdxt_weiD7FxH7fkfQ@mail.gmail.com/
Signed-off-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-10-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 include/asm-generic/spinlock.h       | 14 +++++++-------
 include/asm-generic/spinlock_types.h | 12 ++----------
 2 files changed, 9 insertions(+), 17 deletions(-)

diff --git a/include/asm-generic/spinlock.h b/include/asm-generic/spinlock.h
index 90803a826ba03..4773334ee6388 100644
--- a/include/asm-generic/spinlock.h
+++ b/include/asm-generic/spinlock.h
@@ -32,7 +32,7 @@
 
 static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
 {
-	u32 val = atomic_fetch_add(1<<16, lock);
+	u32 val = atomic_fetch_add(1<<16, &lock->val);
 	u16 ticket = val >> 16;
 
 	if (ticket == (u16)val)
@@ -46,31 +46,31 @@ static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
 	 * have no outstanding writes due to the atomic_fetch_add() the extra
 	 * orderings are free.
 	 */
-	atomic_cond_read_acquire(lock, ticket == (u16)VAL);
+	atomic_cond_read_acquire(&lock->val, ticket == (u16)VAL);
 	smp_mb();
 }
 
 static __always_inline bool arch_spin_trylock(arch_spinlock_t *lock)
 {
-	u32 old = atomic_read(lock);
+	u32 old = atomic_read(&lock->val);
 
 	if ((old >> 16) != (old & 0xffff))
 		return false;
 
-	return atomic_try_cmpxchg(lock, &old, old + (1<<16)); /* SC, for RCsc */
+	return atomic_try_cmpxchg(&lock->val, &old, old + (1<<16)); /* SC, for RCsc */
 }
 
 static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	u16 *ptr = (u16 *)lock + IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
-	u32 val = atomic_read(lock);
+	u32 val = atomic_read(&lock->val);
 
 	smp_store_release(ptr, (u16)val + 1);
 }
 
 static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 {
-	u32 val = lock.counter;
+	u32 val = lock.val.counter;
 
 	return ((val >> 16) == (val & 0xffff));
 }
@@ -84,7 +84,7 @@ static __always_inline int arch_spin_is_locked(arch_spinlock_t *lock)
 
 static __always_inline int arch_spin_is_contended(arch_spinlock_t *lock)
 {
-	u32 val = atomic_read(lock);
+	u32 val = atomic_read(&lock->val);
 
 	return (s16)((val >> 16) - (val & 0xffff)) > 1;
 }
diff --git a/include/asm-generic/spinlock_types.h b/include/asm-generic/spinlock_types.h
index 8962bb730945d..f534aa5de3947 100644
--- a/include/asm-generic/spinlock_types.h
+++ b/include/asm-generic/spinlock_types.h
@@ -3,15 +3,7 @@
 #ifndef __ASM_GENERIC_SPINLOCK_TYPES_H
 #define __ASM_GENERIC_SPINLOCK_TYPES_H
 
-#include <linux/types.h>
-typedef atomic_t arch_spinlock_t;
-
-/*
- * qrwlock_types depends on arch_spinlock_t, so we must typedef that before the
- * include.
- */
-#include <asm/qrwlock_types.h>
-
-#define __ARCH_SPIN_LOCK_UNLOCKED	ATOMIC_INIT(0)
+#include <asm-generic/qspinlock_types.h>
+#include <asm-generic/qrwlock_types.h>
 
 #endif /* __ASM_GENERIC_SPINLOCK_TYPES_H */

From 22c33321e260c8b4c1877b2cc0c4e26a0c74c23f Mon Sep 17 00:00:00 2001
From: Guo Ren <guoren@linux.alibaba.com>
Date: Sun, 3 Nov 2024 15:51:50 +0100
Subject: [PATCH 1025/1530] asm-generic: ticket-lock: Add separate
 ticket-lock.h

Add a separate ticket-lock.h to include multiple spinlock versions and
select one at compile time or runtime.

Reviewed-by: Leonardo Bras <leobras@redhat.com>
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/linux-riscv/CAK8P3a2rnz9mQqhN6-e0CGUUv9rntRELFdxt_weiD7FxH7fkfQ@mail.gmail.com/
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-11-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 include/asm-generic/spinlock.h        |  87 +---------------------
 include/asm-generic/ticket_spinlock.h | 103 ++++++++++++++++++++++++++
 2 files changed, 104 insertions(+), 86 deletions(-)
 create mode 100644 include/asm-generic/ticket_spinlock.h

diff --git a/include/asm-generic/spinlock.h b/include/asm-generic/spinlock.h
index 4773334ee6388..970590baf61b6 100644
--- a/include/asm-generic/spinlock.h
+++ b/include/asm-generic/spinlock.h
@@ -1,94 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
-/*
- * 'Generic' ticket-lock implementation.
- *
- * It relies on atomic_fetch_add() having well defined forward progress
- * guarantees under contention. If your architecture cannot provide this, stick
- * to a test-and-set lock.
- *
- * It also relies on atomic_fetch_add() being safe vs smp_store_release() on a
- * sub-word of the value. This is generally true for anything LL/SC although
- * you'd be hard pressed to find anything useful in architecture specifications
- * about this. If your architecture cannot do this you might be better off with
- * a test-and-set.
- *
- * It further assumes atomic_*_release() + atomic_*_acquire() is RCpc and hence
- * uses atomic_fetch_add() which is RCsc to create an RCsc hot path, along with
- * a full fence after the spin to upgrade the otherwise-RCpc
- * atomic_cond_read_acquire().
- *
- * The implementation uses smp_cond_load_acquire() to spin, so if the
- * architecture has WFE like instructions to sleep instead of poll for word
- * modifications be sure to implement that (see ARM64 for example).
- *
- */
-
 #ifndef __ASM_GENERIC_SPINLOCK_H
 #define __ASM_GENERIC_SPINLOCK_H
 
-#include <linux/atomic.h>
-#include <asm-generic/spinlock_types.h>
-
-static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
-{
-	u32 val = atomic_fetch_add(1<<16, &lock->val);
-	u16 ticket = val >> 16;
-
-	if (ticket == (u16)val)
-		return;
-
-	/*
-	 * atomic_cond_read_acquire() is RCpc, but rather than defining a
-	 * custom cond_read_rcsc() here we just emit a full fence.  We only
-	 * need the prior reads before subsequent writes ordering from
-	 * smb_mb(), but as atomic_cond_read_acquire() just emits reads and we
-	 * have no outstanding writes due to the atomic_fetch_add() the extra
-	 * orderings are free.
-	 */
-	atomic_cond_read_acquire(&lock->val, ticket == (u16)VAL);
-	smp_mb();
-}
-
-static __always_inline bool arch_spin_trylock(arch_spinlock_t *lock)
-{
-	u32 old = atomic_read(&lock->val);
-
-	if ((old >> 16) != (old & 0xffff))
-		return false;
-
-	return atomic_try_cmpxchg(&lock->val, &old, old + (1<<16)); /* SC, for RCsc */
-}
-
-static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
-{
-	u16 *ptr = (u16 *)lock + IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
-	u32 val = atomic_read(&lock->val);
-
-	smp_store_release(ptr, (u16)val + 1);
-}
-
-static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
-{
-	u32 val = lock.val.counter;
-
-	return ((val >> 16) == (val & 0xffff));
-}
-
-static __always_inline int arch_spin_is_locked(arch_spinlock_t *lock)
-{
-	arch_spinlock_t val = READ_ONCE(*lock);
-
-	return !arch_spin_value_unlocked(val);
-}
-
-static __always_inline int arch_spin_is_contended(arch_spinlock_t *lock)
-{
-	u32 val = atomic_read(&lock->val);
-
-	return (s16)((val >> 16) - (val & 0xffff)) > 1;
-}
-
+#include <asm-generic/ticket_spinlock.h>
 #include <asm/qrwlock.h>
 
 #endif /* __ASM_GENERIC_SPINLOCK_H */
diff --git a/include/asm-generic/ticket_spinlock.h b/include/asm-generic/ticket_spinlock.h
new file mode 100644
index 0000000000000..cfcff22b37b39
--- /dev/null
+++ b/include/asm-generic/ticket_spinlock.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * 'Generic' ticket-lock implementation.
+ *
+ * It relies on atomic_fetch_add() having well defined forward progress
+ * guarantees under contention. If your architecture cannot provide this, stick
+ * to a test-and-set lock.
+ *
+ * It also relies on atomic_fetch_add() being safe vs smp_store_release() on a
+ * sub-word of the value. This is generally true for anything LL/SC although
+ * you'd be hard pressed to find anything useful in architecture specifications
+ * about this. If your architecture cannot do this you might be better off with
+ * a test-and-set.
+ *
+ * It further assumes atomic_*_release() + atomic_*_acquire() is RCpc and hence
+ * uses atomic_fetch_add() which is RCsc to create an RCsc hot path, along with
+ * a full fence after the spin to upgrade the otherwise-RCpc
+ * atomic_cond_read_acquire().
+ *
+ * The implementation uses smp_cond_load_acquire() to spin, so if the
+ * architecture has WFE like instructions to sleep instead of poll for word
+ * modifications be sure to implement that (see ARM64 for example).
+ *
+ */
+
+#ifndef __ASM_GENERIC_TICKET_SPINLOCK_H
+#define __ASM_GENERIC_TICKET_SPINLOCK_H
+
+#include <linux/atomic.h>
+#include <asm-generic/spinlock_types.h>
+
+static __always_inline void ticket_spin_lock(arch_spinlock_t *lock)
+{
+	u32 val = atomic_fetch_add(1<<16, &lock->val);
+	u16 ticket = val >> 16;
+
+	if (ticket == (u16)val)
+		return;
+
+	/*
+	 * atomic_cond_read_acquire() is RCpc, but rather than defining a
+	 * custom cond_read_rcsc() here we just emit a full fence.  We only
+	 * need the prior reads before subsequent writes ordering from
+	 * smb_mb(), but as atomic_cond_read_acquire() just emits reads and we
+	 * have no outstanding writes due to the atomic_fetch_add() the extra
+	 * orderings are free.
+	 */
+	atomic_cond_read_acquire(&lock->val, ticket == (u16)VAL);
+	smp_mb();
+}
+
+static __always_inline bool ticket_spin_trylock(arch_spinlock_t *lock)
+{
+	u32 old = atomic_read(&lock->val);
+
+	if ((old >> 16) != (old & 0xffff))
+		return false;
+
+	return atomic_try_cmpxchg(&lock->val, &old, old + (1<<16)); /* SC, for RCsc */
+}
+
+static __always_inline void ticket_spin_unlock(arch_spinlock_t *lock)
+{
+	u16 *ptr = (u16 *)lock + IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
+	u32 val = atomic_read(&lock->val);
+
+	smp_store_release(ptr, (u16)val + 1);
+}
+
+static __always_inline int ticket_spin_value_unlocked(arch_spinlock_t lock)
+{
+	u32 val = lock.val.counter;
+
+	return ((val >> 16) == (val & 0xffff));
+}
+
+static __always_inline int ticket_spin_is_locked(arch_spinlock_t *lock)
+{
+	arch_spinlock_t val = READ_ONCE(*lock);
+
+	return !ticket_spin_value_unlocked(val);
+}
+
+static __always_inline int ticket_spin_is_contended(arch_spinlock_t *lock)
+{
+	u32 val = atomic_read(&lock->val);
+
+	return (s16)((val >> 16) - (val & 0xffff)) > 1;
+}
+
+/*
+ * Remapping spinlock architecture specific functions to the corresponding
+ * ticket spinlock functions.
+ */
+#define arch_spin_is_locked(l)		ticket_spin_is_locked(l)
+#define arch_spin_is_contended(l)	ticket_spin_is_contended(l)
+#define arch_spin_value_unlocked(l)	ticket_spin_value_unlocked(l)
+#define arch_spin_lock(l)		ticket_spin_lock(l)
+#define arch_spin_trylock(l)		ticket_spin_trylock(l)
+#define arch_spin_unlock(l)		ticket_spin_unlock(l)
+
+#endif /* __ASM_GENERIC_TICKET_SPINLOCK_H */

From 2d36fe89d872f1e655670280ce13a8dbe9d366a7 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sun, 3 Nov 2024 15:51:51 +0100
Subject: [PATCH 1026/1530] riscv: Add ISA extension parsing for Ziccrse

Add support to parse the Ziccrse string in the riscv,isa string.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-12-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/hwcap.h | 1 +
 arch/riscv/kernel/cpufeature.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 74bcb0e2bd1f7..0aa3c3f5e682b 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -94,6 +94,7 @@
 #define RISCV_ISA_EXT_ZAWRS		85
 #define RISCV_ISA_EXT_SVVPTC		86
 #define RISCV_ISA_EXT_ZABHA		87
+#define RISCV_ISA_EXT_ZICCRSE		88
 
 #define RISCV_ISA_EXT_XLINUXENVCFG	127
 
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 5e743d8d34f5a..5f453a039ec96 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -314,6 +314,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 					  riscv_ext_zicbom_validate),
 	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts,
 					  riscv_ext_zicboz_validate),
+	__RISCV_ISA_EXT_DATA(ziccrse, RISCV_ISA_EXT_ZICCRSE),
 	__RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR),
 	__RISCV_ISA_EXT_DATA(zicond, RISCV_ISA_EXT_ZICOND),
 	__RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR),

From 447b2afbcde16be43c9459507f48f5c602c121c0 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sun, 3 Nov 2024 15:51:52 +0100
Subject: [PATCH 1027/1530] dt-bindings: riscv: Add Ziccrse ISA extension
 description

Add description for the Ziccrse ISA extension which was ratified in
the riscv profiles specification v1.0.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Guo Ren <guoren@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-13-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/devicetree/bindings/riscv/extensions.yaml | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index db062107823bf..35a9ad1d7e633 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -296,6 +296,12 @@ properties:
             in commit 64074bc ("Update version numbers for Zfh/Zfinx") of
             riscv-isa-manual.
 
+        - const: ziccrse
+          description:
+            The standard Ziccrse extension which provides forward progress
+            guarantee on LR/SC sequences, as ratified in commit b1d806605f87
+            ("Updated to ratified state.") of the riscv profiles specification.
+
         - const: zk
           description:
             The standard Zk Standard Scalar cryptography extension as ratified

From ab83647fadae2f1f723119dc066b39a461d6d288 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sun, 3 Nov 2024 15:51:53 +0100
Subject: [PATCH 1028/1530] riscv: Add qspinlock support

In order to produce a generic kernel, a user can select
CONFIG_COMBO_SPINLOCKS which will fallback at runtime to the ticket
spinlock implementation if Zabha or Ziccrse are not present.

Note that we can't use alternatives here because the discovery of
extensions is done too late and we need to start with the qspinlock
implementation because the ticket spinlock implementation would pollute
the spinlock value, so let's use static keys.

This is largely based on Guo's work and Leonardo reviews at [1].

Link: https://lore.kernel.org/linux-riscv/20231225125847.2778638-1-guoren@kernel.org/ [1]
Signed-off-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-14-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 .../locking/queued-spinlocks/arch-support.txt |  2 +-
 arch/riscv/Kconfig                            | 34 ++++++++++++++
 arch/riscv/include/asm/Kbuild                 |  4 +-
 arch/riscv/include/asm/spinlock.h             | 47 +++++++++++++++++++
 arch/riscv/kernel/setup.c                     | 37 +++++++++++++++
 include/asm-generic/qspinlock.h               |  2 +
 include/asm-generic/ticket_spinlock.h         |  2 +
 7 files changed, 126 insertions(+), 2 deletions(-)
 create mode 100644 arch/riscv/include/asm/spinlock.h

diff --git a/Documentation/features/locking/queued-spinlocks/arch-support.txt b/Documentation/features/locking/queued-spinlocks/arch-support.txt
index 22f2990392ff8..cf26042480e21 100644
--- a/Documentation/features/locking/queued-spinlocks/arch-support.txt
+++ b/Documentation/features/locking/queued-spinlocks/arch-support.txt
@@ -20,7 +20,7 @@
     |    openrisc: |  ok  |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
-    |       riscv: | TODO |
+    |       riscv: |  ok  |
     |        s390: | TODO |
     |          sh: | TODO |
     |       sparc: |  ok  |
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 093ee65373312..f5698ecc5cccd 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -82,6 +82,7 @@ config RISCV
 	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select ARCH_WEAK_RELEASE_ACQUIRE if ARCH_USE_QUEUED_SPINLOCKS
 	select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU
 	select BUILDTIME_TABLE_SORT if MMU
 	select CLINT_TIMER if RISCV_M_MODE
@@ -507,6 +508,39 @@ config NODES_SHIFT
 	  Specify the maximum number of NUMA Nodes available on the target
 	  system.  Increases memory reserved to accommodate various tables.
 
+choice
+	prompt "RISC-V spinlock type"
+	default RISCV_COMBO_SPINLOCKS
+
+config RISCV_TICKET_SPINLOCKS
+	bool "Using ticket spinlock"
+
+config RISCV_QUEUED_SPINLOCKS
+	bool "Using queued spinlock"
+	depends on SMP && MMU && NONPORTABLE
+	select ARCH_USE_QUEUED_SPINLOCKS
+	help
+	  The queued spinlock implementation requires the forward progress
+	  guarantee of cmpxchg()/xchg() atomic operations: CAS with Zabha or
+	  LR/SC with Ziccrse provide such guarantee.
+
+	  Select this if and only if Zabha or Ziccrse is available on your
+	  platform, RISCV_QUEUED_SPINLOCKS must not be selected for platforms
+	  without one of those extensions.
+
+	  If unsure, select RISCV_COMBO_SPINLOCKS, which will use qspinlocks
+	  when supported and otherwise ticket spinlocks.
+
+config RISCV_COMBO_SPINLOCKS
+	bool "Using combo spinlock"
+	depends on SMP && MMU
+	select ARCH_USE_QUEUED_SPINLOCKS
+	help
+	  Embed both queued spinlock and ticket lock so that the spinlock
+	  implementation can be chosen at runtime.
+
+endchoice
+
 config RISCV_ALTERNATIVE
 	bool
 	depends on !XIP_KERNEL
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index 1461af12da6e2..de13d5a234f88 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -6,10 +6,12 @@ generic-y += early_ioremap.h
 generic-y += flat.h
 generic-y += kvm_para.h
 generic-y += mmzone.h
+generic-y += mcs_spinlock.h
 generic-y += parport.h
-generic-y += spinlock.h
 generic-y += spinlock_types.h
+generic-y += ticket_spinlock.h
 generic-y += qrwlock.h
 generic-y += qrwlock_types.h
+generic-y += qspinlock.h
 generic-y += user.h
 generic-y += vmlinux.lds.h
diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h
new file mode 100644
index 0000000000000..e5121b89aceac
--- /dev/null
+++ b/arch/riscv/include/asm/spinlock.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_RISCV_SPINLOCK_H
+#define __ASM_RISCV_SPINLOCK_H
+
+#ifdef CONFIG_RISCV_COMBO_SPINLOCKS
+#define _Q_PENDING_LOOPS	(1 << 9)
+
+#define __no_arch_spinlock_redefine
+#include <asm/ticket_spinlock.h>
+#include <asm/qspinlock.h>
+#include <asm/jump_label.h>
+
+/*
+ * TODO: Use an alternative instead of a static key when we are able to parse
+ * the extensions string earlier in the boot process.
+ */
+DECLARE_STATIC_KEY_TRUE(qspinlock_key);
+
+#define SPINLOCK_BASE_DECLARE(op, type, type_lock)			\
+static __always_inline type arch_spin_##op(type_lock lock)		\
+{									\
+	if (static_branch_unlikely(&qspinlock_key))			\
+		return queued_spin_##op(lock);				\
+	return ticket_spin_##op(lock);					\
+}
+
+SPINLOCK_BASE_DECLARE(lock, void, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(unlock, void, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(is_locked, int, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(is_contended, int, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(trylock, bool, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(value_unlocked, int, arch_spinlock_t)
+
+#elif defined(CONFIG_RISCV_QUEUED_SPINLOCKS)
+
+#include <asm/qspinlock.h>
+
+#else
+
+#include <asm/ticket_spinlock.h>
+
+#endif
+
+#include <asm/qrwlock.h>
+
+#endif /* __ASM_RISCV_SPINLOCK_H */
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index a2cde65b69e95..438e4f6ad2ade 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -244,6 +244,42 @@ static void __init parse_dtb(void)
 #endif
 }
 
+#if defined(CONFIG_RISCV_COMBO_SPINLOCKS)
+DEFINE_STATIC_KEY_TRUE(qspinlock_key);
+EXPORT_SYMBOL(qspinlock_key);
+#endif
+
+static void __init riscv_spinlock_init(void)
+{
+	char *using_ext = NULL;
+
+	if (IS_ENABLED(CONFIG_RISCV_TICKET_SPINLOCKS)) {
+		pr_info("Ticket spinlock: enabled\n");
+		return;
+	}
+
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&
+	    IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) &&
+	    riscv_isa_extension_available(NULL, ZABHA) &&
+	    riscv_isa_extension_available(NULL, ZACAS)) {
+		using_ext = "using Zabha";
+	} else if (riscv_isa_extension_available(NULL, ZICCRSE)) {
+		using_ext = "using Ziccrse";
+	}
+#if defined(CONFIG_RISCV_COMBO_SPINLOCKS)
+	else {
+		static_branch_disable(&qspinlock_key);
+		pr_info("Ticket spinlock: enabled\n");
+		return;
+	}
+#endif
+
+	if (!using_ext)
+		pr_err("Queued spinlock without Zabha or Ziccrse");
+	else
+		pr_info("Queued spinlock %s: enabled\n", using_ext);
+}
+
 extern void __init init_rt_signal_env(void);
 
 void __init setup_arch(char **cmdline_p)
@@ -297,6 +333,7 @@ void __init setup_arch(char **cmdline_p)
 	riscv_set_dma_cache_alignment();
 
 	riscv_user_isa_enable();
+	riscv_spinlock_init();
 }
 
 bool arch_cpu_is_hotpluggable(int cpu)
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 0655aa5b57b29..bf47cca2c375d 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -136,6 +136,7 @@ static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 }
 #endif
 
+#ifndef __no_arch_spinlock_redefine
 /*
  * Remapping spinlock architecture specific functions to the corresponding
  * queued spinlock functions.
@@ -146,5 +147,6 @@ static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 #define arch_spin_lock(l)		queued_spin_lock(l)
 #define arch_spin_trylock(l)		queued_spin_trylock(l)
 #define arch_spin_unlock(l)		queued_spin_unlock(l)
+#endif
 
 #endif /* __ASM_GENERIC_QSPINLOCK_H */
diff --git a/include/asm-generic/ticket_spinlock.h b/include/asm-generic/ticket_spinlock.h
index cfcff22b37b39..325779970d8a0 100644
--- a/include/asm-generic/ticket_spinlock.h
+++ b/include/asm-generic/ticket_spinlock.h
@@ -89,6 +89,7 @@ static __always_inline int ticket_spin_is_contended(arch_spinlock_t *lock)
 	return (s16)((val >> 16) - (val & 0xffff)) > 1;
 }
 
+#ifndef __no_arch_spinlock_redefine
 /*
  * Remapping spinlock architecture specific functions to the corresponding
  * ticket spinlock functions.
@@ -99,5 +100,6 @@ static __always_inline int ticket_spin_is_contended(arch_spinlock_t *lock)
 #define arch_spin_lock(l)		ticket_spin_lock(l)
 #define arch_spin_trylock(l)		ticket_spin_trylock(l)
 #define arch_spin_unlock(l)		ticket_spin_unlock(l)
+#endif
 
 #endif /* __ASM_GENERIC_TICKET_SPINLOCK_H */

From 4c1d8f0547363893bc3b7755aa90755bfd89e2ed Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Nov 2024 12:17:32 -0300
Subject: [PATCH 1029/1530] perf disasm: Introduce
 symbol__disassemble_objdump()

With the first disassemble method in perf, the parsing of objdump
output, just like we have for llvm and capstone.

This paves the way to allow the user to specify what disassemblers are
preferred and to also to at some point allow building without the
objdump method.

Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Link: https://lore.kernel.org/r/20241111151734.1018476-2-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/disasm.c | 168 ++++++++++++++++++++-------------------
 1 file changed, 88 insertions(+), 80 deletions(-)

diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index a525b80b934fd..36cf61602c17f 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -2045,17 +2045,14 @@ static char *expand_tabs(char *line, char **storage, size_t *storage_len)
 	return new_line;
 }
 
-int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
+static int symbol__disassemble_objdump(const char *filename, struct symbol *sym,
+				       struct annotate_args *args)
 {
 	struct annotation_options *opts = &annotate_opts;
 	struct map *map = args->ms.map;
 	struct dso *dso = map__dso(map);
 	char *command;
 	FILE *file;
-	char symfs_filename[PATH_MAX];
-	struct kcore_extract kce;
-	bool delete_extract = false;
-	bool decomp = false;
 	int lineno = 0;
 	char *fileloc = NULL;
 	int nline;
@@ -2070,77 +2067,7 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		NULL,
 	};
 	struct child_process objdump_process;
-	int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename));
-
-	if (err)
-		return err;
-
-	pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
-		 symfs_filename, sym->name, map__unmap_ip(map, sym->start),
-		 map__unmap_ip(map, sym->end));
-
-	pr_debug("annotating [%p] %30s : [%p] %30s\n",
-		 dso, dso__long_name(dso), sym, sym->name);
-
-	if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_PROG_INFO) {
-		return symbol__disassemble_bpf(sym, args);
-	} else if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_IMAGE) {
-		return symbol__disassemble_bpf_image(sym, args);
-	} else if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) {
-		return -1;
-	} else if (dso__is_kcore(dso)) {
-		kce.kcore_filename = symfs_filename;
-		kce.addr = map__rip_2objdump(map, sym->start);
-		kce.offs = sym->start;
-		kce.len = sym->end - sym->start;
-		if (!kcore_extract__create(&kce)) {
-			delete_extract = true;
-			strlcpy(symfs_filename, kce.extract_filename,
-				sizeof(symfs_filename));
-		}
-	} else if (dso__needs_decompress(dso)) {
-		char tmp[KMOD_DECOMP_LEN];
-
-		if (dso__decompress_kmodule_path(dso, symfs_filename,
-						 tmp, sizeof(tmp)) < 0)
-			return -1;
-
-		decomp = true;
-		strcpy(symfs_filename, tmp);
-	}
-
-	/*
-	 * For powerpc data type profiling, use the dso__data_read_offset
-	 * to read raw instruction directly and interpret the binary code
-	 * to understand instructions and register fields. For sort keys as
-	 * type and typeoff, disassemble to mnemonic notation is
-	 * not required in case of powerpc.
-	 */
-	if (arch__is(args->arch, "powerpc")) {
-		extern const char *sort_order;
-
-		if (sort_order && !strstr(sort_order, "sym")) {
-			err = symbol__disassemble_raw(symfs_filename, sym, args);
-			if (err == 0)
-				goto out_remove_tmp;
-#ifdef HAVE_LIBCAPSTONE_SUPPORT
-			err = symbol__disassemble_capstone_powerpc(symfs_filename, sym, args);
-			if (err == 0)
-				goto out_remove_tmp;
-#endif
-		}
-	}
-
-#ifdef HAVE_LIBLLVM_SUPPORT
-	err = symbol__disassemble_llvm(symfs_filename, sym, args);
-	if (err == 0)
-		goto out_remove_tmp;
-#endif
-#ifdef HAVE_LIBCAPSTONE_SUPPORT
-	err = symbol__disassemble_capstone(symfs_filename, sym, args);
-	if (err == 0)
-		goto out_remove_tmp;
-#endif
+	int err;
 
 	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
@@ -2163,13 +2090,13 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 
 	if (err < 0) {
 		pr_err("Failure allocating memory for the command to run\n");
-		goto out_remove_tmp;
+		return err;
 	}
 
 	pr_debug("Executing: %s\n", command);
 
 	objdump_argv[2] = command;
-	objdump_argv[4] = symfs_filename;
+	objdump_argv[4] = filename;
 
 	/* Create a pipe to read from for stdout */
 	memset(&objdump_process, 0, sizeof(objdump_process));
@@ -2207,8 +2134,8 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 			break;
 
 		/* Skip lines containing "filename:" */
-		match = strstr(line, symfs_filename);
-		if (match && match[strlen(symfs_filename)] == ':')
+		match = strstr(line, filename);
+		if (match && match[strlen(filename)] == ':')
 			continue;
 
 		expanded_line = strim(line);
@@ -2253,6 +2180,87 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 
 out_free_command:
 	free(command);
+	return err;
+}
+
+int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
+{
+	struct map *map = args->ms.map;
+	struct dso *dso = map__dso(map);
+	char symfs_filename[PATH_MAX];
+	bool delete_extract = false;
+	struct kcore_extract kce;
+	bool decomp = false;
+	int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename));
+
+	if (err)
+		return err;
+
+	pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
+		 symfs_filename, sym->name, map__unmap_ip(map, sym->start),
+		 map__unmap_ip(map, sym->end));
+
+	pr_debug("annotating [%p] %30s : [%p] %30s\n", dso, dso__long_name(dso), sym, sym->name);
+
+	if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_PROG_INFO) {
+		return symbol__disassemble_bpf(sym, args);
+	} else if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_IMAGE) {
+		return symbol__disassemble_bpf_image(sym, args);
+	} else if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) {
+		return -1;
+	} else if (dso__is_kcore(dso)) {
+		kce.addr = map__rip_2objdump(map, sym->start);
+		kce.kcore_filename = symfs_filename;
+		kce.len = sym->end - sym->start;
+		kce.offs = sym->start;
+
+		if (!kcore_extract__create(&kce)) {
+			delete_extract = true;
+			strlcpy(symfs_filename, kce.extract_filename, sizeof(symfs_filename));
+		}
+	} else if (dso__needs_decompress(dso)) {
+		char tmp[KMOD_DECOMP_LEN];
+
+		if (dso__decompress_kmodule_path(dso, symfs_filename, tmp, sizeof(tmp)) < 0)
+			return -1;
+
+		decomp = true;
+		strcpy(symfs_filename, tmp);
+	}
+
+	/*
+	 * For powerpc data type profiling, use the dso__data_read_offset to
+	 * read raw instruction directly and interpret the binary code to
+	 * understand instructions and register fields. For sort keys as type
+	 * and typeoff, disassemble to mnemonic notation is not required in
+	 * case of powerpc.
+	 */
+	if (arch__is(args->arch, "powerpc")) {
+		extern const char *sort_order;
+
+		if (sort_order && !strstr(sort_order, "sym")) {
+			err = symbol__disassemble_raw(symfs_filename, sym, args);
+			if (err == 0)
+				goto out_remove_tmp;
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+			err = symbol__disassemble_capstone_powerpc(symfs_filename, sym, args);
+			if (err == 0)
+				goto out_remove_tmp;
+#endif
+		}
+	}
+
+#ifdef HAVE_LIBLLVM_SUPPORT
+	err = symbol__disassemble_llvm(symfs_filename, sym, args);
+	if (err == 0)
+		goto out_remove_tmp;
+#endif
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+	err = symbol__disassemble_capstone(symfs_filename, sym, args);
+	if (err == 0)
+		goto out_remove_tmp;
+#endif
+	err = symbol__disassemble_objdump(symfs_filename, sym, args);
 
 out_remove_tmp:
 	if (decomp)

From 7f33b92e5b18e904a481e6e208486da43e4dc841 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 17 Sep 2024 12:15:23 -0400
Subject: [PATCH 1030/1530] NFSD: Prevent a potential integer overflow

If the tag length is >= U32_MAX - 3 then the "length + 4" addition
can result in an integer overflow. Address this by splitting the
decoding into several steps so that decode_cb_compound4res() does
not have to perform arithmetic on the unsafe length value.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Cc: stable@vger.kernel.org
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4callback.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index b5b3ab9d719a7..478b548f4147f 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -287,17 +287,17 @@ static int decode_cb_compound4res(struct xdr_stream *xdr,
 	u32 length;
 	__be32 *p;
 
-	p = xdr_inline_decode(xdr, 4 + 4);
+	p = xdr_inline_decode(xdr, XDR_UNIT);
 	if (unlikely(p == NULL))
 		goto out_overflow;
-	hdr->status = be32_to_cpup(p++);
+	hdr->status = be32_to_cpup(p);
 	/* Ignore the tag */
-	length = be32_to_cpup(p++);
-	p = xdr_inline_decode(xdr, length + 4);
-	if (unlikely(p == NULL))
+	if (xdr_stream_decode_u32(xdr, &length) < 0)
+		goto out_overflow;
+	if (xdr_inline_decode(xdr, length) == NULL)
+		goto out_overflow;
+	if (xdr_stream_decode_u32(xdr, &hdr->nops) < 0)
 		goto out_overflow;
-	p += XDR_QUADLEN(length);
-	hdr->nops = be32_to_cpup(p);
 	return 0;
 out_overflow:
 	return -EIO;

From 3c63d8946e578663b868cb9912dac616ea68bfd0 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 17 Sep 2024 12:15:29 -0400
Subject: [PATCH 1031/1530] svcrdma: Address an integer overflow

Dan Carpenter reports:
> Commit 78147ca8b4a9 ("svcrdma: Add a "parsed chunk list" data
> structure") from Jun 22, 2020 (linux-next), leads to the following
> Smatch static checker warning:
>
>	net/sunrpc/xprtrdma/svc_rdma_recvfrom.c:498 xdr_check_write_chunk()
>	warn: potential user controlled sizeof overflow 'segcount * 4 * 4'
>
> net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
>     488 static bool xdr_check_write_chunk(struct svc_rdma_recv_ctxt *rctxt)
>     489 {
>     490         u32 segcount;
>     491         __be32 *p;
>     492
>     493         if (xdr_stream_decode_u32(&rctxt->rc_stream, &segcount))
>                                                               ^^^^^^^^
>
>     494                 return false;
>     495
>     496         /* A bogus segcount causes this buffer overflow check to fail. */
>     497         p = xdr_inline_decode(&rctxt->rc_stream,
> --> 498                               segcount * rpcrdma_segment_maxsz * sizeof(*p));
>
>
> segcount is an untrusted u32.  On 32bit systems anything >= SIZE_MAX / 16 will
> have an integer overflow and some those values will be accepted by
> xdr_inline_decode().

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Fixes: 78147ca8b4a9 ("svcrdma: Add a "parsed chunk list" data structure")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index ae3fb9bc8a216..292022f0976e1 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -493,7 +493,13 @@ static bool xdr_check_write_chunk(struct svc_rdma_recv_ctxt *rctxt)
 	if (xdr_stream_decode_u32(&rctxt->rc_stream, &segcount))
 		return false;
 
-	/* A bogus segcount causes this buffer overflow check to fail. */
+	/* Before trusting the segcount value enough to use it in
+	 * a computation, perform a simple range check. This is an
+	 * arbitrary but sensible limit (ie, not architectural).
+	 */
+	if (unlikely(segcount > RPCSVC_MAXPAGES))
+		return false;
+
 	p = xdr_inline_decode(&rctxt->rc_stream,
 			      segcount * rpcrdma_segment_maxsz * sizeof(*p));
 	return p != NULL;

From b7165ab074b8cd592dcd9304802ee1d999494c6d Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Mon, 23 Sep 2024 10:05:46 +0200
Subject: [PATCH 1032/1530] NFSD: Remove unnecessary posix_acl_entry pointer
 initialization

The posix_acl_entry pointer pe is already initialized by the
FOREACH_ACL_ENTRY() macro. Remove the unnecessary initialization.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4acl.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 96e786b5e5444..936ea1ad95867 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -198,8 +198,6 @@ summarize_posix_acl(struct posix_acl *acl, struct posix_acl_summary *pas)
 	memset(pas, 0, sizeof(*pas));
 	pas->mask = 07;
 
-	pe = acl->a_entries + acl->a_count;
-
 	FOREACH_ACL_ENTRY(pa, acl, pe) {
 		switch (pa->e_tag) {
 			case ACL_USER_OBJ:

From 612196ef5c50bdafe34314e36b085d4843fb2e9d Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 29 Sep 2024 12:29:43 -0400
Subject: [PATCH 1033/1530] NFSD: Remove unused function parameter

Clean up: Commit 65294c1f2c5e ("nfsd: add a new struct file caching
facility to nfsd") moved the fh_verify() call site out of
nfsd_open(). That was the only user of nfsd_open's @rqstp parameter,
so that parameter can be removed.

Reviewed-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/filecache.c |  3 +--
 fs/nfsd/vfs.c       | 11 ++++-------
 fs/nfsd/vfs.h       |  4 ++--
 3 files changed, 7 insertions(+), 11 deletions(-)

diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 2e6783f637124..1408166222c5f 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -1123,8 +1123,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net,
 			status = nfs_ok;
 			trace_nfsd_file_opened(nf, status);
 		} else {
-			ret = nfsd_open_verified(rqstp, fhp, may_flags,
-						 &nf->nf_file);
+			ret = nfsd_open_verified(fhp, may_flags, &nf->nf_file);
 			if (ret == -EOPENSTALE && stale_retry) {
 				stale_retry = false;
 				nfsd_file_unhash(nf);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index d6d4f2a0e8982..e0692401da33e 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -861,8 +861,7 @@ int nfsd_open_break_lease(struct inode *inode, int access)
  * N.B. After this call fhp needs an fh_put
  */
 static int
-__nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
-			int may_flags, struct file **filp)
+__nfsd_open(struct svc_fh *fhp, umode_t type, int may_flags, struct file **filp)
 {
 	struct path	path;
 	struct inode	*inode;
@@ -932,7 +931,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 retry:
 	err = fh_verify(rqstp, fhp, type, may_flags);
 	if (!err) {
-		host_err = __nfsd_open(rqstp, fhp, type, may_flags, filp);
+		host_err = __nfsd_open(fhp, type, may_flags, filp);
 		if (host_err == -EOPENSTALE && !retried) {
 			retried = true;
 			fh_put(fhp);
@@ -945,7 +944,6 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 
 /**
  * nfsd_open_verified - Open a regular file for the filecache
- * @rqstp: RPC request
  * @fhp: NFS filehandle of the file to open
  * @may_flags: internal permission flags
  * @filp: OUT: open "struct file *"
@@ -953,10 +951,9 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
  * Returns zero on success, or a negative errno value.
  */
 int
-nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags,
-		   struct file **filp)
+nfsd_open_verified(struct svc_fh *fhp, int may_flags, struct file **filp)
 {
-	return __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp);
+	return __nfsd_open(fhp, S_IFREG, may_flags, filp);
 }
 
 /*
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 3ff1465225569..854fb95dfdca4 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -114,8 +114,8 @@ __be32		nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 int 		nfsd_open_break_lease(struct inode *, int);
 __be32		nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t,
 				int, struct file **);
-int		nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp,
-				   int may_flags, struct file **filp);
+int		nfsd_open_verified(struct svc_fh *fhp, int may_flags,
+				struct file **filp);
 __be32		nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 				struct file *file, loff_t offset,
 				unsigned long *count,

From d86fca3affca04b6c2cedd7060206c3e7091ecc8 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 29 Sep 2024 20:50:11 -0400
Subject: [PATCH 1034/1530] xdrgen: Exit status should be zero on success

To use xdrgen in Makefiles, it needs to exit with a zero status if
the compilation worked. Otherwise the make command fails with an
error.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdrgen | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/net/sunrpc/xdrgen/xdrgen b/tools/net/sunrpc/xdrgen/xdrgen
index 95f303b2861b1..43762be39252d 100755
--- a/tools/net/sunrpc/xdrgen/xdrgen
+++ b/tools/net/sunrpc/xdrgen/xdrgen
@@ -128,5 +128,7 @@ There is NO WARRANTY, to the extent permitted by law.""",
 try:
     if __name__ == "__main__":
         sys.exit(main())
-except (SystemExit, KeyboardInterrupt, BrokenPipeError):
+except SystemExit:
+    sys.exit(0)
+except (KeyboardInterrupt, BrokenPipeError):
     sys.exit(1)

From 5383ccd0cc23530b69a0822fba54605615b71946 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 29 Sep 2024 20:50:12 -0400
Subject: [PATCH 1035/1530] xdrgen: Clean up type_specifier

Clean up: Make both arms of the type_specifier AST transformer
match. No behavior change is expected.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdr_ast.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index dbd3fcf9c9576..5d96c544a07b9 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -303,9 +303,9 @@ def type_specifier(self, children):
                 c_classifier=c_classifier,
             )
 
-        token = children[0].data
+        name = children[0].data.value
         return _XdrBuiltInType(
-            type_name=token.value,
+            type_name=name,
             c_classifier=c_classifier,
         )
 

From 041962d5c6a965f1a6c338be49acfe7ab51d2056 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 29 Sep 2024 20:50:13 -0400
Subject: [PATCH 1036/1530] xdrgen: Rename "variable-length strings"

I misread RFC 4506. The built-in data type is called simply
"string", as there is no fixed-length variety.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/generators/pointer.py          |  8 ++++----
 tools/net/sunrpc/xdrgen/generators/struct.py           |  8 ++++----
 tools/net/sunrpc/xdrgen/generators/typedef.py          | 10 +++++-----
 tools/net/sunrpc/xdrgen/grammars/xdr.lark              |  2 +-
 .../decoder/{variable_length_string.j2 => string.j2}   |  0
 .../{variable_length_string.j2 => string.j2}           |  0
 .../encoder/{variable_length_string.j2 => string.j2}   |  0
 .../decoder/{variable_length_string.j2 => string.j2}   |  0
 .../{variable_length_string.j2 => string.j2}           |  0
 .../encoder/{variable_length_string.j2 => string.j2}   |  0
 .../{variable_length_string.j2 => string.j2}           |  0
 .../decoder/{variable_length_string.j2 => string.j2}   |  0
 .../{variable_length_string.j2 => string.j2}           |  0
 .../encoder/{variable_length_string.j2 => string.j2}   |  0
 .../decoder/{variable_length_string.j2 => string.j2}   |  0
 tools/net/sunrpc/xdrgen/xdr_ast.py                     | 10 +++++-----
 16 files changed, 19 insertions(+), 19 deletions(-)
 rename tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/{variable_length_string.j2 => string.j2} (100%)
 rename tools/net/sunrpc/xdrgen/templates/C/pointer/definition/{variable_length_string.j2 => string.j2} (100%)
 rename tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/{variable_length_string.j2 => string.j2} (100%)
 rename tools/net/sunrpc/xdrgen/templates/C/struct/decoder/{variable_length_string.j2 => string.j2} (100%)
 rename tools/net/sunrpc/xdrgen/templates/C/struct/definition/{variable_length_string.j2 => string.j2} (100%)
 rename tools/net/sunrpc/xdrgen/templates/C/struct/encoder/{variable_length_string.j2 => string.j2} (100%)
 rename tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/{variable_length_string.j2 => string.j2} (100%)
 rename tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/{variable_length_string.j2 => string.j2} (100%)
 rename tools/net/sunrpc/xdrgen/templates/C/typedef/definition/{variable_length_string.j2 => string.j2} (100%)
 rename tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/{variable_length_string.j2 => string.j2} (100%)
 rename tools/net/sunrpc/xdrgen/templates/C/union/decoder/{variable_length_string.j2 => string.j2} (100%)

diff --git a/tools/net/sunrpc/xdrgen/generators/pointer.py b/tools/net/sunrpc/xdrgen/generators/pointer.py
index b0b27f1819c8c..0aa3d35203f52 100644
--- a/tools/net/sunrpc/xdrgen/generators/pointer.py
+++ b/tools/net/sunrpc/xdrgen/generators/pointer.py
@@ -8,7 +8,7 @@
 from generators import SourceGenerator, kernel_c_type
 from generators import create_jinja2_environment, get_jinja2_template
 
-from xdr_ast import _XdrBasic, _XdrVariableLengthString
+from xdr_ast import _XdrBasic, _XdrString
 from xdr_ast import _XdrFixedLengthOpaque, _XdrVariableLengthOpaque
 from xdr_ast import _XdrFixedLengthArray, _XdrVariableLengthArray
 from xdr_ast import _XdrOptionalData, _XdrPointer, _XdrDeclaration
@@ -46,7 +46,7 @@ def emit_pointer_member_definition(
     elif isinstance(field, _XdrVariableLengthOpaque):
         template = get_jinja2_template(environment, "definition", field.template)
         print(template.render(name=field.name))
-    elif isinstance(field, _XdrVariableLengthString):
+    elif isinstance(field, _XdrString):
         template = get_jinja2_template(environment, "definition", field.template)
         print(template.render(name=field.name))
     elif isinstance(field, _XdrFixedLengthArray):
@@ -119,7 +119,7 @@ def emit_pointer_member_decoder(
                 maxsize=field.maxsize,
             )
         )
-    elif isinstance(field, _XdrVariableLengthString):
+    elif isinstance(field, _XdrString):
         template = get_jinja2_template(environment, "decoder", field.template)
         print(
             template.render(
@@ -198,7 +198,7 @@ def emit_pointer_member_encoder(
                 maxsize=field.maxsize,
             )
         )
-    elif isinstance(field, _XdrVariableLengthString):
+    elif isinstance(field, _XdrString):
         template = get_jinja2_template(environment, "encoder", field.template)
         print(
             template.render(
diff --git a/tools/net/sunrpc/xdrgen/generators/struct.py b/tools/net/sunrpc/xdrgen/generators/struct.py
index b694cd4708290..6dd7f4d7cd535 100644
--- a/tools/net/sunrpc/xdrgen/generators/struct.py
+++ b/tools/net/sunrpc/xdrgen/generators/struct.py
@@ -8,7 +8,7 @@
 from generators import SourceGenerator, kernel_c_type
 from generators import create_jinja2_environment, get_jinja2_template
 
-from xdr_ast import _XdrBasic, _XdrVariableLengthString
+from xdr_ast import _XdrBasic, _XdrString
 from xdr_ast import _XdrFixedLengthOpaque, _XdrVariableLengthOpaque
 from xdr_ast import _XdrFixedLengthArray, _XdrVariableLengthArray
 from xdr_ast import _XdrOptionalData, _XdrStruct, _XdrDeclaration
@@ -46,7 +46,7 @@ def emit_struct_member_definition(
     elif isinstance(field, _XdrVariableLengthOpaque):
         template = get_jinja2_template(environment, "definition", field.template)
         print(template.render(name=field.name))
-    elif isinstance(field, _XdrVariableLengthString):
+    elif isinstance(field, _XdrString):
         template = get_jinja2_template(environment, "definition", field.template)
         print(template.render(name=field.name))
     elif isinstance(field, _XdrFixedLengthArray):
@@ -119,7 +119,7 @@ def emit_struct_member_decoder(
                 maxsize=field.maxsize,
             )
         )
-    elif isinstance(field, _XdrVariableLengthString):
+    elif isinstance(field, _XdrString):
         template = get_jinja2_template(environment, "decoder", field.template)
         print(
             template.render(
@@ -198,7 +198,7 @@ def emit_struct_member_encoder(
                 maxsize=field.maxsize,
             )
         )
-    elif isinstance(field, _XdrVariableLengthString):
+    elif isinstance(field, _XdrString):
         template = get_jinja2_template(environment, "encoder", field.template)
         print(
             template.render(
diff --git a/tools/net/sunrpc/xdrgen/generators/typedef.py b/tools/net/sunrpc/xdrgen/generators/typedef.py
index 85a1b23033339..6ea98445f5c82 100644
--- a/tools/net/sunrpc/xdrgen/generators/typedef.py
+++ b/tools/net/sunrpc/xdrgen/generators/typedef.py
@@ -8,7 +8,7 @@
 from generators import SourceGenerator, kernel_c_type
 from generators import create_jinja2_environment, get_jinja2_template
 
-from xdr_ast import _XdrBasic, _XdrTypedef, _XdrVariableLengthString
+from xdr_ast import _XdrBasic, _XdrTypedef, _XdrString
 from xdr_ast import _XdrFixedLengthOpaque, _XdrVariableLengthOpaque
 from xdr_ast import _XdrFixedLengthArray, _XdrVariableLengthArray
 from xdr_ast import _XdrOptionalData, _XdrVoid, _XdrDeclaration
@@ -28,7 +28,7 @@ def emit_typedef_declaration(environment: Environment, node: _XdrDeclaration) ->
                 classifier=node.spec.c_classifier,
             )
         )
-    elif isinstance(node, _XdrVariableLengthString):
+    elif isinstance(node, _XdrString):
         template = get_jinja2_template(environment, "declaration", node.template)
         print(template.render(name=node.name))
     elif isinstance(node, _XdrFixedLengthOpaque):
@@ -74,7 +74,7 @@ def emit_type_definition(environment: Environment, node: _XdrDeclaration) -> Non
                 classifier=node.spec.c_classifier,
             )
         )
-    elif isinstance(node, _XdrVariableLengthString):
+    elif isinstance(node, _XdrString):
         template = get_jinja2_template(environment, "definition", node.template)
         print(template.render(name=node.name))
     elif isinstance(node, _XdrFixedLengthOpaque):
@@ -119,7 +119,7 @@ def emit_typedef_decoder(environment: Environment, node: _XdrDeclaration) -> Non
                 type=node.spec.type_name,
             )
         )
-    elif isinstance(node, _XdrVariableLengthString):
+    elif isinstance(node, _XdrString):
         template = get_jinja2_template(environment, "decoder", node.template)
         print(
             template.render(
@@ -180,7 +180,7 @@ def emit_typedef_encoder(environment: Environment, node: _XdrDeclaration) -> Non
                 type=node.spec.type_name,
             )
         )
-    elif isinstance(node, _XdrVariableLengthString):
+    elif isinstance(node, _XdrString):
         template = get_jinja2_template(environment, "encoder", node.template)
         print(
             template.render(
diff --git a/tools/net/sunrpc/xdrgen/grammars/xdr.lark b/tools/net/sunrpc/xdrgen/grammars/xdr.lark
index f3c4552e548d6..0e1aeb02d6672 100644
--- a/tools/net/sunrpc/xdrgen/grammars/xdr.lark
+++ b/tools/net/sunrpc/xdrgen/grammars/xdr.lark
@@ -3,7 +3,7 @@
 
 declaration             : "opaque" identifier "[" value "]"            -> fixed_length_opaque
                         | "opaque" identifier "<" [ value ] ">"        -> variable_length_opaque
-                        | "string" identifier "<" [ value ] ">"        -> variable_length_string
+                        | "string" identifier "<" [ value ] ">"        -> string
                         | type_specifier identifier "[" value "]"      -> fixed_length_array
                         | type_specifier identifier "<" [ value ] ">"  -> variable_length_array
                         | type_specifier "*" identifier                -> optional_data
diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/string.j2
similarity index 100%
rename from tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_string.j2
rename to tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/string.j2
diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/string.j2
similarity index 100%
rename from tools/net/sunrpc/xdrgen/templates/C/pointer/definition/variable_length_string.j2
rename to tools/net/sunrpc/xdrgen/templates/C/pointer/definition/string.j2
diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/string.j2
similarity index 100%
rename from tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_string.j2
rename to tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/string.j2
diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/string.j2
similarity index 100%
rename from tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_string.j2
rename to tools/net/sunrpc/xdrgen/templates/C/struct/decoder/string.j2
diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/definition/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/string.j2
similarity index 100%
rename from tools/net/sunrpc/xdrgen/templates/C/struct/definition/variable_length_string.j2
rename to tools/net/sunrpc/xdrgen/templates/C/struct/definition/string.j2
diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/string.j2
similarity index 100%
rename from tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_string.j2
rename to tools/net/sunrpc/xdrgen/templates/C/struct/encoder/string.j2
diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/string.j2
similarity index 100%
rename from tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/variable_length_string.j2
rename to tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/string.j2
diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/string.j2
similarity index 100%
rename from tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/variable_length_string.j2
rename to tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/string.j2
diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/string.j2
similarity index 100%
rename from tools/net/sunrpc/xdrgen/templates/C/typedef/definition/variable_length_string.j2
rename to tools/net/sunrpc/xdrgen/templates/C/typedef/definition/string.j2
diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/string.j2
similarity index 100%
rename from tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/variable_length_string.j2
rename to tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/string.j2
diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/string.j2
similarity index 100%
rename from tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_string.j2
rename to tools/net/sunrpc/xdrgen/templates/C/union/decoder/string.j2
diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index 5d96c544a07b9..17d1689b58583 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -88,12 +88,12 @@ class _XdrVariableLengthOpaque(_XdrDeclaration):
 
 
 @dataclass
-class _XdrVariableLengthString(_XdrDeclaration):
+class _XdrString(_XdrDeclaration):
     """A (NUL-terminated) variable-length string declaration"""
 
     name: str
     maxsize: str
-    template: str = "variable_length_string"
+    template: str = "string"
 
 
 @dataclass
@@ -350,15 +350,15 @@ def variable_length_opaque(self, children):
 
         return _XdrVariableLengthOpaque(name, maxsize)
 
-    def variable_length_string(self, children):
-        """Instantiate one _XdrVariableLengthString declaration object"""
+    def string(self, children):
+        """Instantiate one _XdrString declaration object"""
         name = children[0].symbol
         if children[1] is not None:
             maxsize = children[1].value
         else:
             maxsize = "0"
 
-        return _XdrVariableLengthString(name, maxsize)
+        return _XdrString(name, maxsize)
 
     def fixed_length_array(self, children):
         """Instantiate one _XdrFixedLengthArray declaration object"""

From c060f8168bdf22aa986970955af99702d142dfbe Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 29 Sep 2024 20:50:14 -0400
Subject: [PATCH 1037/1530] xdrgen: Rename enum's declaration Jinja2 template

"close.j2" is a confusing name.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/generators/enum.py                      | 2 +-
 .../xdrgen/templates/C/enum/declaration/{close.j2 => enum.j2}   | 0
 2 files changed, 1 insertion(+), 1 deletion(-)
 rename tools/net/sunrpc/xdrgen/templates/C/enum/declaration/{close.j2 => enum.j2} (100%)

diff --git a/tools/net/sunrpc/xdrgen/generators/enum.py b/tools/net/sunrpc/xdrgen/generators/enum.py
index 855e43f4ae38e..e37b5c2978211 100644
--- a/tools/net/sunrpc/xdrgen/generators/enum.py
+++ b/tools/net/sunrpc/xdrgen/generators/enum.py
@@ -18,7 +18,7 @@ def __init__(self, language: str, peer: str):
     def emit_declaration(self, node: _XdrEnum) -> None:
         """Emit one declaration pair for an XDR enum type"""
         if node.name in public_apis:
-            template = self.environment.get_template("declaration/close.j2")
+            template = self.environment.get_template("declaration/enum.j2")
             print(template.render(name=node.name))
 
     def emit_definition(self, node: _XdrEnum) -> None:
diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/declaration/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/declaration/enum.j2
similarity index 100%
rename from tools/net/sunrpc/xdrgen/templates/C/enum/declaration/close.j2
rename to tools/net/sunrpc/xdrgen/templates/C/enum/declaration/enum.j2

From 6e853dcd2d3d6f796597c1042340a2de0ce2469f Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 29 Sep 2024 20:50:15 -0400
Subject: [PATCH 1038/1530] xdrgen: Rename "enum yada" types as just "yada"

This simplifies the generated C code and makes way for supporting
big-endian XDR enums.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/templates/C/enum/declaration/enum.j2 | 4 ++--
 tools/net/sunrpc/xdrgen/templates/C/enum/decoder/enum.j2     | 2 +-
 tools/net/sunrpc/xdrgen/templates/C/enum/definition/close.j2 | 1 +
 tools/net/sunrpc/xdrgen/templates/C/enum/encoder/enum.j2     | 2 +-
 tools/net/sunrpc/xdrgen/xdr_ast.py                           | 4 ----
 5 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/declaration/enum.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/declaration/enum.j2
index ab1e576c95318..d1405c7c5354a 100644
--- a/tools/net/sunrpc/xdrgen/templates/C/enum/declaration/enum.j2
+++ b/tools/net/sunrpc/xdrgen/templates/C/enum/declaration/enum.j2
@@ -1,4 +1,4 @@
 {# SPDX-License-Identifier: GPL-2.0 #}
 
-bool xdrgen_decode_{{ name }}(struct xdr_stream *xdr, enum {{ name }} *ptr);
-bool xdrgen_encode_{{ name }}(struct xdr_stream *xdr, enum {{ name }} value);
+bool xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ name }} *ptr);
+bool xdrgen_encode_{{ name }}(struct xdr_stream *xdr, {{ name }} value);
diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/decoder/enum.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/decoder/enum.j2
index 341d829afeda9..6482984f1cb71 100644
--- a/tools/net/sunrpc/xdrgen/templates/C/enum/decoder/enum.j2
+++ b/tools/net/sunrpc/xdrgen/templates/C/enum/decoder/enum.j2
@@ -8,7 +8,7 @@ bool
 {% else %}
 static bool __maybe_unused
 {% endif %}
-xdrgen_decode_{{ name }}(struct xdr_stream *xdr, enum {{ name }} *ptr)
+xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ name }} *ptr)
 {
 	u32 val;
 
diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/definition/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/definition/close.j2
index 9e62344a976aa..a07586cbee179 100644
--- a/tools/net/sunrpc/xdrgen/templates/C/enum/definition/close.j2
+++ b/tools/net/sunrpc/xdrgen/templates/C/enum/definition/close.j2
@@ -1,2 +1,3 @@
 {# SPDX-License-Identifier: GPL-2.0 #}
 };
+typedef enum {{ name }} {{ name }};
diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/encoder/enum.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/encoder/enum.j2
index bd0a770e50f24..67245b9a914d2 100644
--- a/tools/net/sunrpc/xdrgen/templates/C/enum/encoder/enum.j2
+++ b/tools/net/sunrpc/xdrgen/templates/C/enum/encoder/enum.j2
@@ -8,7 +8,7 @@ bool
 {% else %}
 static bool __maybe_unused
 {% endif %}
-xdrgen_encode_{{ name }}(struct xdr_stream *xdr, enum {{ name }} value)
+xdrgen_encode_{{ name }}(struct xdr_stream *xdr, {{ name }} value)
 {
 	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
 }
diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index 17d1689b58583..576e1ecfe1d78 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -15,7 +15,6 @@
 excluded_apis = []
 header_name = "none"
 public_apis = []
-enums = set()
 structs = set()
 pass_by_reference = set()
 
@@ -294,8 +293,6 @@ def type_specifier(self, children):
         c_classifier = ""
         if isinstance(children[0], _XdrIdentifier):
             name = children[0].symbol
-            if name in enums:
-                c_classifier = "enum "
             if name in structs:
                 c_classifier = "struct "
             return _XdrDefinedType(
@@ -320,7 +317,6 @@ def constant_def(self, children):
     def enum(self, children):
         """Instantiate one _XdrEnum object"""
         enum_name = children[0].symbol
-        enums.add(enum_name)
 
         i = 0
         enumerators = []

From b376d519bd142c65ba9bba35db12b6be95b46893 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 29 Sep 2024 20:50:16 -0400
Subject: [PATCH 1039/1530] xdrgen: Implement big-endian enums

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/xdr.h                    | 21 ++++++++++++
 tools/net/sunrpc/xdrgen/README                | 17 ++++++++++
 tools/net/sunrpc/xdrgen/generators/enum.py    | 17 +++++++---
 tools/net/sunrpc/xdrgen/generators/union.py   | 34 ++++++++++++++-----
 tools/net/sunrpc/xdrgen/grammars/xdr.lark     |  4 ++-
 .../templates/C/enum/decoder/enum_be.j2       | 14 ++++++++
 .../templates/C/enum/definition/close_be.j2   |  3 ++
 .../templates/C/enum/encoder/enum_be.j2       | 14 ++++++++
 .../templates/C/union/decoder/case_spec_be.j2 |  2 ++
 .../templates/C/union/encoder/case_spec_be.j2 |  2 ++
 tools/net/sunrpc/xdrgen/xdr_ast.py            |  3 ++
 11 files changed, 117 insertions(+), 14 deletions(-)
 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/enum/decoder/enum_be.j2
 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/enum/definition/close_be.j2
 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/enum/encoder/enum_be.j2
 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/decoder/case_spec_be.j2
 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/encoder/case_spec_be.j2

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 5f775e104f9ab..a2ab813a9800b 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -680,6 +680,27 @@ xdr_stream_decode_u32(struct xdr_stream *xdr, __u32 *ptr)
 	return 0;
 }
 
+/**
+ * xdr_stream_decode_be32 - Decode a big-endian 32-bit integer
+ * @xdr: pointer to xdr_stream
+ * @ptr: location to store integer
+ *
+ * Return values:
+ *   %0 on success
+ *   %-EBADMSG on XDR buffer overflow
+ */
+static inline ssize_t
+xdr_stream_decode_be32(struct xdr_stream *xdr, __be32 *ptr)
+{
+	const size_t count = sizeof(*ptr);
+	__be32 *p = xdr_inline_decode(xdr, count);
+
+	if (unlikely(!p))
+		return -EBADMSG;
+	*ptr = *p;
+	return 0;
+}
+
 /**
  * xdr_stream_decode_u64 - Decode a 64-bit integer
  * @xdr: pointer to xdr_stream
diff --git a/tools/net/sunrpc/xdrgen/README b/tools/net/sunrpc/xdrgen/README
index 92f7738ad50c3..27218a78ab402 100644
--- a/tools/net/sunrpc/xdrgen/README
+++ b/tools/net/sunrpc/xdrgen/README
@@ -150,6 +150,23 @@ Pragma directives specify exceptions to the normal generation of
 encoding and decoding functions. Currently one directive is
 implemented: "public".
 
+Pragma big_endian
+------ ----------
+
+  pragma big_endian <enum> ;
+
+For variables that might contain only a small number values, it
+is more efficient to avoid the byte-swap when encoding or decoding
+on little-endian machines. Such is often the case with error status
+codes. For example:
+
+  pragma big_endian nfsstat3;
+
+In this case, when generating an XDR struct or union containing a
+field of type "nfsstat3", xdrgen will make the type of that field
+"__be32" instead of "enum nfsstat3". XDR unions then switch on the
+non-byte-swapped value of that field.
+
 Pragma exclude
 ------ -------
 
diff --git a/tools/net/sunrpc/xdrgen/generators/enum.py b/tools/net/sunrpc/xdrgen/generators/enum.py
index e37b5c2978211..e63f45b8eb740 100644
--- a/tools/net/sunrpc/xdrgen/generators/enum.py
+++ b/tools/net/sunrpc/xdrgen/generators/enum.py
@@ -4,7 +4,7 @@
 """Generate code to handle XDR enum types"""
 
 from generators import SourceGenerator, create_jinja2_environment
-from xdr_ast import _XdrEnum, public_apis
+from xdr_ast import _XdrEnum, public_apis, big_endian
 
 
 class XdrEnumGenerator(SourceGenerator):
@@ -30,15 +30,24 @@ def emit_definition(self, node: _XdrEnum) -> None:
         for enumerator in node.enumerators:
             print(template.render(name=enumerator.name, value=enumerator.value))
 
-        template = self.environment.get_template("definition/close.j2")
+        if node.name in big_endian:
+            template = self.environment.get_template("definition/close_be.j2")
+        else:
+            template = self.environment.get_template("definition/close.j2")
         print(template.render(name=node.name))
 
     def emit_decoder(self, node: _XdrEnum) -> None:
         """Emit one decoder function for an XDR enum type"""
-        template = self.environment.get_template("decoder/enum.j2")
+        if node.name in big_endian:
+            template = self.environment.get_template("decoder/enum_be.j2")
+        else:
+            template = self.environment.get_template("decoder/enum.j2")
         print(template.render(name=node.name))
 
     def emit_encoder(self, node: _XdrEnum) -> None:
         """Emit one encoder function for an XDR enum type"""
-        template = self.environment.get_template("encoder/enum.j2")
+        if node.name in big_endian:
+            template = self.environment.get_template("encoder/enum_be.j2")
+        else:
+            template = self.environment.get_template("encoder/enum.j2")
         print(template.render(name=node.name))
diff --git a/tools/net/sunrpc/xdrgen/generators/union.py b/tools/net/sunrpc/xdrgen/generators/union.py
index 7974967bbb9fd..4522a5b7a943e 100644
--- a/tools/net/sunrpc/xdrgen/generators/union.py
+++ b/tools/net/sunrpc/xdrgen/generators/union.py
@@ -8,7 +8,7 @@
 from generators import SourceGenerator
 from generators import create_jinja2_environment, get_jinja2_template
 
-from xdr_ast import _XdrBasic, _XdrUnion, _XdrVoid
+from xdr_ast import _XdrBasic, _XdrUnion, _XdrVoid, big_endian
 from xdr_ast import _XdrDeclaration, _XdrCaseSpec, public_apis
 
 
@@ -77,13 +77,18 @@ def emit_union_switch_spec_decoder(
     print(template.render(name=node.name, type=node.spec.type_name))
 
 
-def emit_union_case_spec_decoder(environment: Environment, node: _XdrCaseSpec) -> None:
+def emit_union_case_spec_decoder(
+    environment: Environment, node: _XdrCaseSpec, big_endian_discriminant: bool
+) -> None:
     """Emit decoder functions for an XDR union's case arm"""
 
     if isinstance(node.arm, _XdrVoid):
         return
 
-    template = get_jinja2_template(environment, "decoder", "case_spec")
+    if big_endian_discriminant:
+        template = get_jinja2_template(environment, "decoder", "case_spec_be")
+    else:
+        template = get_jinja2_template(environment, "decoder", "case_spec")
     for case in node.values:
         print(template.render(case=case))
 
@@ -136,7 +141,11 @@ def emit_union_decoder(environment: Environment, node: _XdrUnion) -> None:
     emit_union_switch_spec_decoder(environment, node.discriminant)
 
     for case in node.cases:
-        emit_union_case_spec_decoder(environment, case)
+        emit_union_case_spec_decoder(
+            environment,
+            case,
+            node.discriminant.spec.type_name in big_endian,
+        )
 
     emit_union_default_spec_decoder(environment, node)
 
@@ -153,17 +162,21 @@ def emit_union_switch_spec_encoder(
     print(template.render(name=node.name, type=node.spec.type_name))
 
 
-def emit_union_case_spec_encoder(environment: Environment, node: _XdrCaseSpec) -> None:
+def emit_union_case_spec_encoder(
+    environment: Environment, node: _XdrCaseSpec, big_endian_discriminant: bool
+) -> None:
     """Emit encoder functions for an XDR union's case arm"""
 
     if isinstance(node.arm, _XdrVoid):
         return
 
-    template = get_jinja2_template(environment, "encoder", "case_spec")
+    if big_endian_discriminant:
+        template = get_jinja2_template(environment, "encoder", "case_spec_be")
+    else:
+        template = get_jinja2_template(environment, "encoder", "case_spec")
     for case in node.values:
         print(template.render(case=case))
 
-    assert isinstance(node.arm, _XdrBasic)
     template = get_jinja2_template(environment, "encoder", node.arm.template)
     print(
         template.render(
@@ -192,7 +205,6 @@ def emit_union_default_spec_encoder(environment: Environment, node: _XdrUnion) -
         print(template.render())
         return
 
-    assert isinstance(default_case.arm, _XdrBasic)
     template = get_jinja2_template(environment, "encoder", default_case.arm.template)
     print(
         template.render(
@@ -210,7 +222,11 @@ def emit_union_encoder(environment, node: _XdrUnion) -> None:
     emit_union_switch_spec_encoder(environment, node.discriminant)
 
     for case in node.cases:
-        emit_union_case_spec_encoder(environment, case)
+        emit_union_case_spec_encoder(
+            environment,
+            case,
+            node.discriminant.spec.type_name in big_endian,
+        )
 
     emit_union_default_spec_encoder(environment, node)
 
diff --git a/tools/net/sunrpc/xdrgen/grammars/xdr.lark b/tools/net/sunrpc/xdrgen/grammars/xdr.lark
index 0e1aeb02d6672..7c2c1b8c86d12 100644
--- a/tools/net/sunrpc/xdrgen/grammars/xdr.lark
+++ b/tools/net/sunrpc/xdrgen/grammars/xdr.lark
@@ -87,12 +87,14 @@ procedure_def           : type_specifier identifier "(" type_specifier ")" "=" c
 
 pragma_def              : "pragma" directive identifier [ identifier ] ";"
 
-directive               : exclude_directive
+directive               : big_endian_directive
+                        | exclude_directive
                         | header_directive
                         | pages_directive
                         | public_directive
                         | skip_directive
 
+big_endian_directive    : "big_endian"
 exclude_directive       : "exclude"
 header_directive        : "header"
 pages_directive         : "pages"
diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/decoder/enum_be.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/decoder/enum_be.j2
new file mode 100644
index 0000000000000..44c391c10b42e
--- /dev/null
+++ b/tools/net/sunrpc/xdrgen/templates/C/enum/decoder/enum_be.j2
@@ -0,0 +1,14 @@
+{# SPDX-License-Identifier: GPL-2.0 #}
+
+{% if annotate %}
+/* enum {{ name }} (big-endian) */
+{% endif %}
+{% if name in public_apis %}
+bool
+{% else %}
+static bool __maybe_unused
+{% endif %}
+xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ name }} *ptr)
+{
+	return xdr_stream_decode_be32(xdr, ptr) == 0;
+}
diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/definition/close_be.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/definition/close_be.j2
new file mode 100644
index 0000000000000..2c18948bddf75
--- /dev/null
+++ b/tools/net/sunrpc/xdrgen/templates/C/enum/definition/close_be.j2
@@ -0,0 +1,3 @@
+{# SPDX-License-Identifier: GPL-2.0 #}
+};
+typedef __be32 {{ name }};
diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/encoder/enum_be.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/encoder/enum_be.j2
new file mode 100644
index 0000000000000..fbbcc45948d6a
--- /dev/null
+++ b/tools/net/sunrpc/xdrgen/templates/C/enum/encoder/enum_be.j2
@@ -0,0 +1,14 @@
+{# SPDX-License-Identifier: GPL-2.0 #}
+
+{% if annotate %}
+/* enum {{ name }} (big-endian) */
+{% endif %}
+{% if name in public_apis %}
+bool
+{% else %}
+static bool __maybe_unused
+{% endif %}
+xdrgen_encode_{{ name }}(struct xdr_stream *xdr, {{ name }} value)
+{
+	return xdr_stream_encode_be32(xdr, value) == XDR_UNIT;
+}
diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/case_spec_be.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/case_spec_be.j2
new file mode 100644
index 0000000000000..917f3a1c45888
--- /dev/null
+++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/case_spec_be.j2
@@ -0,0 +1,2 @@
+{# SPDX-License-Identifier: GPL-2.0 #}
+	case __constant_cpu_to_be32({{ case }}):
diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/encoder/case_spec_be.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/case_spec_be.j2
new file mode 100644
index 0000000000000..917f3a1c45888
--- /dev/null
+++ b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/case_spec_be.j2
@@ -0,0 +1,2 @@
+{# SPDX-License-Identifier: GPL-2.0 #}
+	case __constant_cpu_to_be32({{ case }}):
diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index 576e1ecfe1d78..d5f0535ec84c3 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -12,6 +12,7 @@
 
 this_module = sys.modules[__name__]
 
+big_endian = []
 excluded_apis = []
 header_name = "none"
 public_apis = []
@@ -480,6 +481,8 @@ def pragma_def(self, children):
         """Instantiate one _Pragma object"""
         directive = children[0].children[0].data
         match directive:
+            case "big_endian_directive":
+                big_endian.append(children[1].symbol)
             case "exclude_directive":
                 excluded_apis.append(children[1].symbol)
             case "header_directive":

From 1acd13cbc7c9c69a09e5d8325cf6c3e3f0a75049 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:31 -0400
Subject: [PATCH 1040/1530] xdrgen: Refactor transformer arms

Clean up: Add a __post_init__ function to the data classes that
need to update the "structs" and "pass_by_reference" sets.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdr_ast.py | 57 +++++++++++++++++-------------
 1 file changed, 33 insertions(+), 24 deletions(-)

diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index d5f0535ec84c3..68f09945f2c40 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -51,13 +51,17 @@ class _XdrTypeSpecifier(_XdrAst):
     """Corresponds to 'type_specifier' in the XDR language grammar"""
 
     type_name: str
-    c_classifier: str
+    c_classifier: str = ""
 
 
 @dataclass
 class _XdrDefinedType(_XdrTypeSpecifier):
     """Corresponds to a type defined by the input specification"""
 
+    def __post_init__(self):
+        if self.type_name in structs:
+            self.c_classifier = "struct "
+
 
 @dataclass
 class _XdrBuiltInType(_XdrTypeSpecifier):
@@ -124,6 +128,10 @@ class _XdrOptionalData(_XdrDeclaration):
     spec: _XdrTypeSpecifier
     template: str = "optional_data"
 
+    def __post_init__(self):
+        structs.add(self.name)
+        pass_by_reference.add(self.name)
+
 
 @dataclass
 class _XdrBasic(_XdrDeclaration):
@@ -174,6 +182,10 @@ class _XdrStruct(_XdrAst):
     name: str
     fields: List[_XdrDeclaration]
 
+    def __post_init__(self):
+        structs.add(self.name)
+        pass_by_reference.add(self.name)
+
 
 @dataclass
 class _XdrPointer(_XdrAst):
@@ -182,6 +194,10 @@ class _XdrPointer(_XdrAst):
     name: str
     fields: List[_XdrDeclaration]
 
+    def __post_init__(self):
+        structs.add(self.name)
+        pass_by_reference.add(self.name)
+
 
 @dataclass
 class _XdrTypedef(_XdrAst):
@@ -189,6 +205,15 @@ class _XdrTypedef(_XdrAst):
 
     declaration: _XdrDeclaration
 
+    def __post_init__(self):
+        if not isinstance(self.declaration, _XdrBasic):
+            return
+
+        new_type = self.declaration
+        if isinstance(new_type.spec, _XdrDefinedType):
+            if new_type.spec.type_name in pass_by_reference:
+                pass_by_reference.add(new_type.name)
+
 
 @dataclass
 class _XdrCaseSpec(_XdrAst):
@@ -216,6 +241,10 @@ class _XdrUnion(_XdrAst):
     cases: List[_XdrCaseSpec]
     default: _XdrDeclaration
 
+    def __post_init__(self):
+        structs.add(self.name)
+        pass_by_reference.add(self.name)
+
 
 @dataclass
 class _RpcProcedure(_XdrAst):
@@ -290,22 +319,13 @@ def constant(self, children):
         return _XdrConstantValue(value)
 
     def type_specifier(self, children):
-        """Instantiate one type_specifier object"""
-        c_classifier = ""
+        """Instantiate one _XdrTypeSpecifier object"""
         if isinstance(children[0], _XdrIdentifier):
             name = children[0].symbol
-            if name in structs:
-                c_classifier = "struct "
-            return _XdrDefinedType(
-                type_name=name,
-                c_classifier=c_classifier,
-            )
+            return _XdrDefinedType(type_name=name)
 
         name = children[0].data.value
-        return _XdrBuiltInType(
-            type_name=name,
-            c_classifier=c_classifier,
-        )
+        return _XdrBuiltInType(type_name=name)
 
     def constant_def(self, children):
         """Instantiate one _XdrConstant object"""
@@ -380,8 +400,6 @@ def optional_data(self, children):
         """Instantiate one _XdrOptionalData declaration object"""
         spec = children[0]
         name = children[1].symbol
-        structs.add(name)
-        pass_by_reference.add(name)
 
         return _XdrOptionalData(name, spec)
 
@@ -400,8 +418,6 @@ def void(self, children):
     def struct(self, children):
         """Instantiate one _XdrStruct object"""
         name = children[0].symbol
-        structs.add(name)
-        pass_by_reference.add(name)
         fields = children[1].children
 
         last_field = fields[-1]
@@ -416,11 +432,6 @@ def struct(self, children):
     def typedef(self, children):
         """Instantiate one _XdrTypedef object"""
         new_type = children[0]
-        if isinstance(new_type, _XdrBasic) and isinstance(
-            new_type.spec, _XdrDefinedType
-        ):
-            if new_type.spec.type_name in pass_by_reference:
-                pass_by_reference.add(new_type.name)
 
         return _XdrTypedef(new_type)
 
@@ -442,8 +453,6 @@ def default_spec(self, children):
     def union(self, children):
         """Instantiate one _XdrUnion object"""
         name = children[0].symbol
-        structs.add(name)
-        pass_by_reference.add(name)
 
         body = children[1]
         discriminant = body.children[0].children[0]

From 189f55d93d3eb76d733c28f0c70fd2d162a9ffc5 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:32 -0400
Subject: [PATCH 1041/1530] xdrgen: Track constant values

In order to compute the numeric on-the-wire width of XDR types,
xdrgen needs to keep track of the numeric value of constants that
are defined in the input specification so it can perform
calculations with those values.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdr_ast.py | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index 68f09945f2c40..b7df45f47707b 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -19,6 +19,8 @@
 structs = set()
 pass_by_reference = set()
 
+constants = {}
+
 
 @dataclass
 class _XdrAst(ast_utils.Ast):
@@ -156,6 +158,10 @@ class _XdrConstant(_XdrAst):
     name: str
     value: str
 
+    def __post_init__(self):
+        if self.value not in constants:
+            constants[self.name] = int(self.value, 0)
+
 
 @dataclass
 class _XdrEnumerator(_XdrAst):
@@ -164,6 +170,10 @@ class _XdrEnumerator(_XdrAst):
     name: str
     value: str
 
+    def __post_init__(self):
+        if self.value not in constants:
+            constants[self.name] = int(self.value, 0)
+
 
 @dataclass
 class _XdrEnum(_XdrAst):

From 631c2925bae41c11dcf3915a2ab5f3be9af54277 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:33 -0400
Subject: [PATCH 1042/1530] xdrgen: Keep track of on-the-wire data type widths

The generic parts of the RPC layer need to know the widths (in
XDR_UNIT increments) of the XDR data types defined for each
protocol.

As a first step, add dictionaries to keep track of the symbolic and
actual maximum XDR width of XDR types.

This makes it straightforward to look up the width of a type by its
name. The built-in dictionaries are pre-loaded with the widths of
the built-in XDR types as defined in RFC 4506.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/xdrgen/_defs.h |  9 ++++++
 tools/net/sunrpc/xdrgen/xdr_ast.py  | 43 +++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+)

diff --git a/include/linux/sunrpc/xdrgen/_defs.h b/include/linux/sunrpc/xdrgen/_defs.h
index be9e623717588..20c7270aa64d2 100644
--- a/include/linux/sunrpc/xdrgen/_defs.h
+++ b/include/linux/sunrpc/xdrgen/_defs.h
@@ -23,4 +23,13 @@ typedef struct {
 	u8 *data;
 } opaque;
 
+#define XDR_void		(0)
+#define XDR_bool		(1)
+#define XDR_int			(1)
+#define XDR_unsigned_int	(1)
+#define XDR_long		(1)
+#define XDR_unsigned_long	(1)
+#define XDR_hyper		(2)
+#define XDR_unsigned_hyper	(2)
+
 #endif /* _SUNRPC_XDRGEN__DEFS_H_ */
diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index b7df45f47707b..f1d93a1d0ed8a 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -21,6 +21,31 @@
 
 constants = {}
 
+symbolic_widths = {
+    "void": ["XDR_void"],
+    "bool": ["XDR_bool"],
+    "int": ["XDR_int"],
+    "unsigned_int": ["XDR_unsigned_int"],
+    "long": ["XDR_long"],
+    "unsigned_long": ["XDR_unsigned_long"],
+    "hyper": ["XDR_hyper"],
+    "unsigned_hyper": ["XDR_unsigned_hyper"],
+}
+
+# Numeric XDR widths are tracked in a dictionary that is keyed
+# by type_name because sometimes a caller has nothing more than
+# the type_name to use to figure out the numeric width.
+max_widths = {
+    "void": 0,
+    "bool": 1,
+    "int": 1,
+    "unsigned_int": 1,
+    "long": 1,
+    "unsigned_long": 1,
+    "hyper": 2,
+    "unsigned_hyper": 2,
+}
+
 
 @dataclass
 class _XdrAst(ast_utils.Ast):
@@ -60,15 +85,24 @@ class _XdrTypeSpecifier(_XdrAst):
 class _XdrDefinedType(_XdrTypeSpecifier):
     """Corresponds to a type defined by the input specification"""
 
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        return [get_header_name().upper() + "_" + self.type_name + "_sz"]
+
     def __post_init__(self):
         if self.type_name in structs:
             self.c_classifier = "struct "
+        symbolic_widths[self.type_name] = self.symbolic_width()
 
 
 @dataclass
 class _XdrBuiltInType(_XdrTypeSpecifier):
     """Corresponds to a built-in XDR type"""
 
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        return symbolic_widths[self.type_name]
+
 
 @dataclass
 class _XdrDeclaration(_XdrAst):
@@ -148,8 +182,17 @@ class _XdrBasic(_XdrDeclaration):
 class _XdrVoid(_XdrDeclaration):
     """A void declaration"""
 
+    name: str = "void"
     template: str = "void"
 
+    def max_width(self) -> int:
+        """Return width of type in XDR_UNITS"""
+        return 0
+
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        return []
+
 
 @dataclass
 class _XdrConstant(_XdrAst):

From 3f890755c8f5958ef537a6d8f14de5ec4bfdc3fe Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:34 -0400
Subject: [PATCH 1043/1530] xdrgen: XDR widths for enum types

RFC 4506 says that an XDR enum is represented as a signed integer
on the wire; thus its width is 1 XDR_UNIT.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdr_ast.py | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index f1d93a1d0ed8a..fbee954c7f706 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -227,6 +227,18 @@ class _XdrEnum(_XdrAst):
     maximum: int
     enumerators: List[_XdrEnumerator]
 
+    def max_width(self) -> int:
+        """Return width of type in XDR_UNITS"""
+        return 1
+
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        return ["XDR_int"]
+
+    def __post_init__(self):
+        max_widths[self.name] = self.max_width()
+        symbolic_widths[self.name] = self.symbolic_width()
+
 
 @dataclass
 class _XdrStruct(_XdrAst):

From 16c98ce04a6929019f66dab40367fb14d0afc678 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:35 -0400
Subject: [PATCH 1044/1530] xdrgen: XDR width for fixed-length opaque

The XDR width for a fixed-length opaque is the byte size of the
opaque rounded up to the next XDR_UNIT, divided by XDR_UNIT.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdr_ast.py | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index fbee954c7f706..9fe7fa688caaf 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -21,6 +21,16 @@
 
 constants = {}
 
+
+def xdr_quadlen(val: str) -> int:
+    """Return integer XDR width of an XDR type"""
+    if val in constants:
+        octets = constants[val]
+    else:
+        octets = int(val)
+    return int((octets + 3) / 4)
+
+
 symbolic_widths = {
     "void": ["XDR_void"],
     "bool": ["XDR_bool"],
@@ -117,6 +127,18 @@ class _XdrFixedLengthOpaque(_XdrDeclaration):
     size: str
     template: str = "fixed_length_opaque"
 
+    def max_width(self) -> int:
+        """Return width of type in XDR_UNITS"""
+        return xdr_quadlen(self.size)
+
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        return ["XDR_QUADLEN(" + self.size + ")"]
+
+    def __post_init__(self):
+        max_widths[self.name] = self.max_width()
+        symbolic_widths[self.name] = self.symbolic_width()
+
 
 @dataclass
 class _XdrVariableLengthOpaque(_XdrDeclaration):

From b0b85ef754740102cd659aea10aa516fe27f6b36 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:36 -0400
Subject: [PATCH 1045/1530] xdrgen: XDR width for variable-length opaque

The byte size of a variable-length opaque is conveyed in an unsigned
integer. If there is a specified maximum size, that is included in
the type's widths list.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdr_ast.py | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index 9fe7fa688caaf..94cdcfb36e775 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -148,6 +148,21 @@ class _XdrVariableLengthOpaque(_XdrDeclaration):
     maxsize: str
     template: str = "variable_length_opaque"
 
+    def max_width(self) -> int:
+        """Return width of type in XDR_UNITS"""
+        return 1 + xdr_quadlen(self.maxsize)
+
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        widths = ["XDR_unsigned_int"]
+        if self.maxsize != "0":
+            widths.append("XDR_QUADLEN(" + self.maxsize + ")")
+        return widths
+
+    def __post_init__(self):
+        max_widths[self.name] = self.max_width()
+        symbolic_widths[self.name] = self.symbolic_width()
+
 
 @dataclass
 class _XdrString(_XdrDeclaration):

From da298d01136e2f80a1a3a47f81d8bb3ade2d306c Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:37 -0400
Subject: [PATCH 1046/1530] xdrgen: XDR width for a string

A string works like a variable-length opaque. See Section 4.11 of
RFC 4506.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdr_ast.py | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index 94cdcfb36e775..d5f48c094729f 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -172,6 +172,21 @@ class _XdrString(_XdrDeclaration):
     maxsize: str
     template: str = "string"
 
+    def max_width(self) -> int:
+        """Return width of type in XDR_UNITS"""
+        return 1 + xdr_quadlen(self.maxsize)
+
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        widths = ["XDR_unsigned_int"]
+        if self.maxsize != "0":
+            widths.append("XDR_QUADLEN(" + self.maxsize + ")")
+        return widths
+
+    def __post_init__(self):
+        max_widths[self.name] = self.max_width()
+        symbolic_widths[self.name] = self.symbolic_width()
+
 
 @dataclass
 class _XdrFixedLengthArray(_XdrDeclaration):

From 59b01b9636646bbf2eee59e19cc7da5b584f24c7 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:38 -0400
Subject: [PATCH 1047/1530] xdrgen: XDR width for fixed-length array

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdr_ast.py | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index d5f48c094729f..e9bc81e83b489 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -197,6 +197,19 @@ class _XdrFixedLengthArray(_XdrDeclaration):
     size: str
     template: str = "fixed_length_array"
 
+    def max_width(self) -> int:
+        """Return width of type in XDR_UNITS"""
+        return xdr_quadlen(self.size) * max_widths[self.spec.type_name]
+
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        item_width = " + ".join(symbolic_widths[self.spec.type_name])
+        return ["(" + self.size + " * (" + item_width + "))"]
+
+    def __post_init__(self):
+        max_widths[self.name] = self.max_width()
+        symbolic_widths[self.name] = self.symbolic_width()
+
 
 @dataclass
 class _XdrVariableLengthArray(_XdrDeclaration):

From 2db8940e6ceda6aeb566429e8d58c34ab093d3c7 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:39 -0400
Subject: [PATCH 1048/1530] xdrgen: XDR width for variable-length array

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdr_ast.py | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index e9bc81e83b489..cb89d5d9987c8 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -220,6 +220,22 @@ class _XdrVariableLengthArray(_XdrDeclaration):
     maxsize: str
     template: str = "variable_length_array"
 
+    def max_width(self) -> int:
+        """Return width of type in XDR_UNITS"""
+        return 1 + (xdr_quadlen(self.maxsize) * max_widths[self.spec.type_name])
+
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        widths = ["XDR_unsigned_int"]
+        if self.maxsize != "0":
+            item_width = " + ".join(symbolic_widths[self.spec.type_name])
+            widths.append("(" + self.maxsize + " * (" + item_width + "))")
+        return widths
+
+    def __post_init__(self):
+        max_widths[self.name] = self.max_width()
+        symbolic_widths[self.name] = self.symbolic_width()
+
 
 @dataclass
 class _XdrOptionalData(_XdrDeclaration):

From dc6fa83b6aff5c50277045f53a448afce9616b07 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:40 -0400
Subject: [PATCH 1049/1530] xdrgen: XDR width for optional_data type

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdr_ast.py | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index cb89d5d9987c8..f2ef78654e367 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -245,9 +245,19 @@ class _XdrOptionalData(_XdrDeclaration):
     spec: _XdrTypeSpecifier
     template: str = "optional_data"
 
+    def max_width(self) -> int:
+        """Return width of type in XDR_UNITS"""
+        return 1
+
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        return ["XDR_bool"]
+
     def __post_init__(self):
         structs.add(self.name)
         pass_by_reference.add(self.name)
+        max_widths[self.name] = self.max_width()
+        symbolic_widths[self.name] = self.symbolic_width()
 
 
 @dataclass

From 2852c92ba1305fd2d85fd69f73bb4b43a3c58146 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:41 -0400
Subject: [PATCH 1050/1530] xdrgen: XDR width for typedef

The XDR width of a typedef is the same as the width of the base type.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdr_ast.py | 34 ++++++++++++++++++++++++------
 1 file changed, 27 insertions(+), 7 deletions(-)

diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index f2ef78654e367..8996f26cbd557 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -268,6 +268,18 @@ class _XdrBasic(_XdrDeclaration):
     spec: _XdrTypeSpecifier
     template: str = "basic"
 
+    def max_width(self) -> int:
+        """Return width of type in XDR_UNITS"""
+        return max_widths[self.spec.type_name]
+
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        return symbolic_widths[self.spec.type_name]
+
+    def __post_init__(self):
+        max_widths[self.name] = self.max_width()
+        symbolic_widths[self.name] = self.symbolic_width()
+
 
 @dataclass
 class _XdrVoid(_XdrDeclaration):
@@ -361,14 +373,22 @@ class _XdrTypedef(_XdrAst):
 
     declaration: _XdrDeclaration
 
-    def __post_init__(self):
-        if not isinstance(self.declaration, _XdrBasic):
-            return
+    def max_width(self) -> int:
+        """Return width of type in XDR_UNITS"""
+        return self.declaration.max_width()
 
-        new_type = self.declaration
-        if isinstance(new_type.spec, _XdrDefinedType):
-            if new_type.spec.type_name in pass_by_reference:
-                pass_by_reference.add(new_type.name)
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        return self.declaration.symbolic_width()
+
+    def __post_init__(self):
+        if isinstance(self.declaration, _XdrBasic):
+            new_type = self.declaration
+            if isinstance(new_type.spec, _XdrDefinedType):
+                if new_type.spec.type_name in pass_by_reference:
+                    pass_by_reference.add(new_type.name)
+                max_widths[new_type.name] = self.max_width()
+                symbolic_widths[new_type.name] = self.symbolic_width()
 
 
 @dataclass

From f4bc1e996a34a47f6c8334edcd8ddcd7dc0634b1 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:42 -0400
Subject: [PATCH 1051/1530] xdrgen: XDR width for struct types

The XDR width of a struct type is the sum of the widths of each of
the struct's fields.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdr_ast.py | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index 8996f26cbd557..f34b147c8dfdf 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -350,9 +350,25 @@ class _XdrStruct(_XdrAst):
     name: str
     fields: List[_XdrDeclaration]
 
+    def max_width(self) -> int:
+        """Return width of type in XDR_UNITS"""
+        width = 0
+        for field in self.fields:
+            width += field.max_width()
+        return width
+
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        widths = []
+        for field in self.fields:
+            widths += field.symbolic_width()
+        return widths
+
     def __post_init__(self):
         structs.add(self.name)
         pass_by_reference.add(self.name)
+        max_widths[self.name] = self.max_width()
+        symbolic_widths[self.name] = self.symbolic_width()
 
 
 @dataclass

From 447dc1efebac1484d5903ba34655289e7725df6d Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:43 -0400
Subject: [PATCH 1052/1530] xdrgen: XDR width for pointer types

The XDR width of a pointer type is the sum of the widths of each of
the struct's fields, except for the last field. The width of the
implicit boolean "value follows" field is added as well.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdr_ast.py | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index f34b147c8dfdf..8d53c889eee8d 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -378,9 +378,26 @@ class _XdrPointer(_XdrAst):
     name: str
     fields: List[_XdrDeclaration]
 
+    def max_width(self) -> int:
+        """Return width of type in XDR_UNITS"""
+        width = 1
+        for field in self.fields[0:-1]:
+            width += field.max_width()
+        return width
+
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        widths = []
+        widths += ["XDR_bool"]
+        for field in self.fields[0:-1]:
+            widths += field.symbolic_width()
+        return widths
+
     def __post_init__(self):
         structs.add(self.name)
         pass_by_reference.add(self.name)
+        max_widths[self.name] = self.max_width()
+        symbolic_widths[self.name] = self.symbolic_width()
 
 
 @dataclass

From ce5a75d9939fab904d27b403011eddd2b173b495 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:44 -0400
Subject: [PATCH 1053/1530] xdrgen: XDR width for union types

Not yet complete.

The tool doesn't do any math yet. Thus, even though the maximum XDR
width of a union is the width of the union enumerator plus the width
of its largest arm, we're using the sum of all the elements of the
union for the moment.

This means that buffer size requirements are overestimated, and that
the generated maxsize macro cannot yet be used for determining data
element alignment in the XDR buffer.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/xdr_ast.py | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py
index 8d53c889eee8d..5233e73c7046a 100644
--- a/tools/net/sunrpc/xdrgen/xdr_ast.py
+++ b/tools/net/sunrpc/xdrgen/xdr_ast.py
@@ -450,9 +450,35 @@ class _XdrUnion(_XdrAst):
     cases: List[_XdrCaseSpec]
     default: _XdrDeclaration
 
+    def max_width(self) -> int:
+        """Return width of type in XDR_UNITS"""
+        max_width = 0
+        for case in self.cases:
+            if case.arm.max_width() > max_width:
+                max_width = case.arm.max_width()
+        if self.default:
+            if self.default.arm.max_width() > max_width:
+                max_width = self.default.arm.max_width()
+        return 1 + max_width
+
+    def symbolic_width(self) -> List:
+        """Return list containing XDR width of type's components"""
+        max_width = 0
+        for case in self.cases:
+            if case.arm.max_width() > max_width:
+                max_width = case.arm.max_width()
+                width = case.arm.symbolic_width()
+        if self.default:
+            if self.default.arm.max_width() > max_width:
+                max_width = self.default.arm.max_width()
+                width = self.default.arm.symbolic_width()
+        return symbolic_widths[self.discriminant.name] + width
+
     def __post_init__(self):
         structs.add(self.name)
         pass_by_reference.add(self.name)
+        max_widths[self.name] = self.max_width()
+        symbolic_widths[self.name] = self.symbolic_width()
 
 
 @dataclass

From e9e1e7e75acd737cf41c6ee64d62da6ea0c10036 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:45 -0400
Subject: [PATCH 1054/1530] xdrgen: Add generator code for XDR width macros

Introduce logic in the code generators to emit maxsize (XDR
width) definitions. In C, these are pre-processor macros.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 .../net/sunrpc/xdrgen/generators/__init__.py  |  4 ++++
 tools/net/sunrpc/xdrgen/generators/enum.py    | 13 +++++++++++-
 tools/net/sunrpc/xdrgen/generators/pointer.py | 18 ++++++++++++++++-
 tools/net/sunrpc/xdrgen/generators/struct.py  | 18 ++++++++++++++++-
 tools/net/sunrpc/xdrgen/generators/typedef.py | 18 ++++++++++++++++-
 tools/net/sunrpc/xdrgen/generators/union.py   | 20 +++++++++++++++++--
 .../xdrgen/templates/C/enum/maxsize/enum.j2   |  2 ++
 .../templates/C/pointer/maxsize/pointer.j2    |  3 +++
 .../templates/C/struct/maxsize/struct.j2      |  3 +++
 .../templates/C/typedef/maxsize/basic.j2      |  3 +++
 .../C/typedef/maxsize/fixed_length_opaque.j2  |  2 ++
 .../templates/C/typedef/maxsize/string.j2     |  2 ++
 .../typedef/maxsize/variable_length_array.j2  |  2 ++
 .../typedef/maxsize/variable_length_opaque.j2 |  2 ++
 .../xdrgen/templates/C/union/maxsize/union.j2 |  3 +++
 15 files changed, 107 insertions(+), 6 deletions(-)
 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/enum/maxsize/enum.j2
 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/maxsize/pointer.j2
 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/maxsize/struct.j2
 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/basic.j2
 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/fixed_length_opaque.j2
 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/string.j2
 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/variable_length_array.j2
 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/variable_length_opaque.j2
 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/maxsize/union.j2

diff --git a/tools/net/sunrpc/xdrgen/generators/__init__.py b/tools/net/sunrpc/xdrgen/generators/__init__.py
index fd24574612742..b98574a36a4ac 100644
--- a/tools/net/sunrpc/xdrgen/generators/__init__.py
+++ b/tools/net/sunrpc/xdrgen/generators/__init__.py
@@ -111,3 +111,7 @@ def emit_definition(self, node: _XdrAst) -> None:
     def emit_encoder(self, node: _XdrAst) -> None:
         """Emit one encoder function for this XDR type"""
         raise NotImplementedError("Encoder generation not supported")
+
+    def emit_maxsize(self, node: _XdrAst) -> None:
+        """Emit one maxsize macro for this XDR type"""
+        raise NotImplementedError("Maxsize macro generation not supported")
diff --git a/tools/net/sunrpc/xdrgen/generators/enum.py b/tools/net/sunrpc/xdrgen/generators/enum.py
index e63f45b8eb740..e62f715d3996f 100644
--- a/tools/net/sunrpc/xdrgen/generators/enum.py
+++ b/tools/net/sunrpc/xdrgen/generators/enum.py
@@ -4,7 +4,7 @@
 """Generate code to handle XDR enum types"""
 
 from generators import SourceGenerator, create_jinja2_environment
-from xdr_ast import _XdrEnum, public_apis, big_endian
+from xdr_ast import _XdrEnum, public_apis, big_endian, get_header_name
 
 
 class XdrEnumGenerator(SourceGenerator):
@@ -51,3 +51,14 @@ def emit_encoder(self, node: _XdrEnum) -> None:
         else:
             template = self.environment.get_template("encoder/enum.j2")
         print(template.render(name=node.name))
+
+    def emit_maxsize(self, node: _XdrEnum) -> None:
+        """Emit one maxsize macro for an XDR enum type"""
+        macro_name = get_header_name().upper() + "_" + node.name + "_sz"
+        template = self.environment.get_template("maxsize/enum.j2")
+        print(
+            template.render(
+                macro=macro_name,
+                width=" + ".join(node.symbolic_width()),
+            )
+        )
diff --git a/tools/net/sunrpc/xdrgen/generators/pointer.py b/tools/net/sunrpc/xdrgen/generators/pointer.py
index 0aa3d35203f52..6dbda60ad2db4 100644
--- a/tools/net/sunrpc/xdrgen/generators/pointer.py
+++ b/tools/net/sunrpc/xdrgen/generators/pointer.py
@@ -12,7 +12,7 @@
 from xdr_ast import _XdrFixedLengthOpaque, _XdrVariableLengthOpaque
 from xdr_ast import _XdrFixedLengthArray, _XdrVariableLengthArray
 from xdr_ast import _XdrOptionalData, _XdrPointer, _XdrDeclaration
-from xdr_ast import public_apis
+from xdr_ast import public_apis, get_header_name
 
 
 def emit_pointer_declaration(environment: Environment, node: _XdrPointer) -> None:
@@ -247,6 +247,18 @@ def emit_pointer_encoder(environment: Environment, node: _XdrPointer) -> None:
     print(template.render())
 
 
+def emit_pointer_maxsize(environment: Environment, node: _XdrPointer) -> None:
+    """Emit one maxsize macro for an XDR pointer type"""
+    macro_name = get_header_name().upper() + "_" + node.name + "_sz"
+    template = get_jinja2_template(environment, "maxsize", "pointer")
+    print(
+        template.render(
+            macro=macro_name,
+            width=" + ".join(node.symbolic_width()),
+        )
+    )
+
+
 class XdrPointerGenerator(SourceGenerator):
     """Generate source code for XDR pointer"""
 
@@ -270,3 +282,7 @@ def emit_decoder(self, node: _XdrPointer) -> None:
     def emit_encoder(self, node: _XdrPointer) -> None:
         """Emit one encoder function for an XDR pointer type"""
         emit_pointer_encoder(self.environment, node)
+
+    def emit_maxsize(self, node: _XdrPointer) -> None:
+        """Emit one maxsize macro for an XDR pointer type"""
+        emit_pointer_maxsize(self.environment, node)
diff --git a/tools/net/sunrpc/xdrgen/generators/struct.py b/tools/net/sunrpc/xdrgen/generators/struct.py
index 6dd7f4d7cd535..64911de46f623 100644
--- a/tools/net/sunrpc/xdrgen/generators/struct.py
+++ b/tools/net/sunrpc/xdrgen/generators/struct.py
@@ -12,7 +12,7 @@
 from xdr_ast import _XdrFixedLengthOpaque, _XdrVariableLengthOpaque
 from xdr_ast import _XdrFixedLengthArray, _XdrVariableLengthArray
 from xdr_ast import _XdrOptionalData, _XdrStruct, _XdrDeclaration
-from xdr_ast import public_apis
+from xdr_ast import public_apis, get_header_name
 
 
 def emit_struct_declaration(environment: Environment, node: _XdrStruct) -> None:
@@ -247,6 +247,18 @@ def emit_struct_encoder(environment: Environment, node: _XdrStruct) -> None:
     print(template.render())
 
 
+def emit_struct_maxsize(environment: Environment, node: _XdrStruct) -> None:
+    """Emit one maxsize macro for an XDR struct type"""
+    macro_name = get_header_name().upper() + "_" + node.name + "_sz"
+    template = get_jinja2_template(environment, "maxsize", "struct")
+    print(
+        template.render(
+            macro=macro_name,
+            width=" + ".join(node.symbolic_width()),
+        )
+    )
+
+
 class XdrStructGenerator(SourceGenerator):
     """Generate source code for XDR structs"""
 
@@ -270,3 +282,7 @@ def emit_decoder(self, node: _XdrStruct) -> None:
     def emit_encoder(self, node: _XdrStruct) -> None:
         """Emit one encoder function for an XDR struct type"""
         emit_struct_encoder(self.environment, node)
+
+    def emit_maxsize(self, node: _XdrStruct) -> None:
+        """Emit one maxsize macro for an XDR struct type"""
+        emit_struct_maxsize(self.environment, node)
diff --git a/tools/net/sunrpc/xdrgen/generators/typedef.py b/tools/net/sunrpc/xdrgen/generators/typedef.py
index 6ea98445f5c82..fab72e9d69158 100644
--- a/tools/net/sunrpc/xdrgen/generators/typedef.py
+++ b/tools/net/sunrpc/xdrgen/generators/typedef.py
@@ -12,7 +12,7 @@
 from xdr_ast import _XdrFixedLengthOpaque, _XdrVariableLengthOpaque
 from xdr_ast import _XdrFixedLengthArray, _XdrVariableLengthArray
 from xdr_ast import _XdrOptionalData, _XdrVoid, _XdrDeclaration
-from xdr_ast import public_apis
+from xdr_ast import public_apis, get_header_name
 
 
 def emit_typedef_declaration(environment: Environment, node: _XdrDeclaration) -> None:
@@ -230,6 +230,18 @@ def emit_typedef_encoder(environment: Environment, node: _XdrDeclaration) -> Non
         raise NotImplementedError("typedef: type not recognized")
 
 
+def emit_typedef_maxsize(environment: Environment, node: _XdrDeclaration) -> None:
+    """Emit a maxsize macro for an XDR typedef"""
+    macro_name = get_header_name().upper() + "_" + node.name + "_sz"
+    template = get_jinja2_template(environment, "maxsize", node.template)
+    print(
+        template.render(
+            macro=macro_name,
+            width=" + ".join(node.symbolic_width()),
+        )
+    )
+
+
 class XdrTypedefGenerator(SourceGenerator):
     """Generate source code for XDR typedefs"""
 
@@ -253,3 +265,7 @@ def emit_decoder(self, node: _XdrTypedef) -> None:
     def emit_encoder(self, node: _XdrTypedef) -> None:
         """Emit one encoder function for an XDR typedef"""
         emit_typedef_encoder(self.environment, node.declaration)
+
+    def emit_maxsize(self, node: _XdrTypedef) -> None:
+        """Emit one maxsize macro for an XDR typedef"""
+        emit_typedef_maxsize(self.environment, node.declaration)
diff --git a/tools/net/sunrpc/xdrgen/generators/union.py b/tools/net/sunrpc/xdrgen/generators/union.py
index 4522a5b7a943e..2cca00e279cd9 100644
--- a/tools/net/sunrpc/xdrgen/generators/union.py
+++ b/tools/net/sunrpc/xdrgen/generators/union.py
@@ -8,8 +8,8 @@
 from generators import SourceGenerator
 from generators import create_jinja2_environment, get_jinja2_template
 
-from xdr_ast import _XdrBasic, _XdrUnion, _XdrVoid, big_endian
-from xdr_ast import _XdrDeclaration, _XdrCaseSpec, public_apis
+from xdr_ast import _XdrBasic, _XdrUnion, _XdrVoid, get_header_name
+from xdr_ast import _XdrDeclaration, _XdrCaseSpec, public_apis, big_endian
 
 
 def emit_union_declaration(environment: Environment, node: _XdrUnion) -> None:
@@ -234,6 +234,18 @@ def emit_union_encoder(environment, node: _XdrUnion) -> None:
     print(template.render())
 
 
+def emit_union_maxsize(environment: Environment, node: _XdrUnion) -> None:
+    """Emit one maxsize macro for an XDR union type"""
+    macro_name = get_header_name().upper() + "_" + node.name + "_sz"
+    template = get_jinja2_template(environment, "maxsize", "union")
+    print(
+        template.render(
+            macro=macro_name,
+            width=" + ".join(node.symbolic_width()),
+        )
+    )
+
+
 class XdrUnionGenerator(SourceGenerator):
     """Generate source code for XDR unions"""
 
@@ -257,3 +269,7 @@ def emit_decoder(self, node: _XdrUnion) -> None:
     def emit_encoder(self, node: _XdrUnion) -> None:
         """Emit one encoder function for an XDR union"""
         emit_union_encoder(self.environment, node)
+
+    def emit_maxsize(self, node: _XdrUnion) -> None:
+        """Emit one maxsize macro for an XDR union"""
+        emit_union_maxsize(self.environment, node)
diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/maxsize/enum.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/maxsize/enum.j2
new file mode 100644
index 0000000000000..45c1d4c21b220
--- /dev/null
+++ b/tools/net/sunrpc/xdrgen/templates/C/enum/maxsize/enum.j2
@@ -0,0 +1,2 @@
+{# SPDX-License-Identifier: GPL-2.0 #}
+#define {{ '{:<31}'.format(macro) }} ({{ width }})
diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/maxsize/pointer.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/maxsize/pointer.j2
new file mode 100644
index 0000000000000..9f3bfb47d2f47
--- /dev/null
+++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/maxsize/pointer.j2
@@ -0,0 +1,3 @@
+{# SPDX-License-Identifier: GPL-2.0 #}
+#define {{ '{:<31}'.format(macro) }} \
+	({{ width }})
diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/maxsize/struct.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/maxsize/struct.j2
new file mode 100644
index 0000000000000..9f3bfb47d2f47
--- /dev/null
+++ b/tools/net/sunrpc/xdrgen/templates/C/struct/maxsize/struct.j2
@@ -0,0 +1,3 @@
+{# SPDX-License-Identifier: GPL-2.0 #}
+#define {{ '{:<31}'.format(macro) }} \
+	({{ width }})
diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/basic.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/basic.j2
new file mode 100644
index 0000000000000..9f3bfb47d2f47
--- /dev/null
+++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/basic.j2
@@ -0,0 +1,3 @@
+{# SPDX-License-Identifier: GPL-2.0 #}
+#define {{ '{:<31}'.format(macro) }} \
+	({{ width }})
diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/fixed_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/fixed_length_opaque.j2
new file mode 100644
index 0000000000000..45c1d4c21b220
--- /dev/null
+++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/fixed_length_opaque.j2
@@ -0,0 +1,2 @@
+{# SPDX-License-Identifier: GPL-2.0 #}
+#define {{ '{:<31}'.format(macro) }} ({{ width }})
diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/string.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/string.j2
new file mode 100644
index 0000000000000..45c1d4c21b220
--- /dev/null
+++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/string.j2
@@ -0,0 +1,2 @@
+{# SPDX-License-Identifier: GPL-2.0 #}
+#define {{ '{:<31}'.format(macro) }} ({{ width }})
diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/variable_length_array.j2
new file mode 100644
index 0000000000000..45c1d4c21b220
--- /dev/null
+++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/variable_length_array.j2
@@ -0,0 +1,2 @@
+{# SPDX-License-Identifier: GPL-2.0 #}
+#define {{ '{:<31}'.format(macro) }} ({{ width }})
diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/variable_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/variable_length_opaque.j2
new file mode 100644
index 0000000000000..45c1d4c21b220
--- /dev/null
+++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/maxsize/variable_length_opaque.j2
@@ -0,0 +1,2 @@
+{# SPDX-License-Identifier: GPL-2.0 #}
+#define {{ '{:<31}'.format(macro) }} ({{ width }})
diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/maxsize/union.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/maxsize/union.j2
new file mode 100644
index 0000000000000..9f3bfb47d2f47
--- /dev/null
+++ b/tools/net/sunrpc/xdrgen/templates/C/union/maxsize/union.j2
@@ -0,0 +1,3 @@
+{# SPDX-License-Identifier: GPL-2.0 #}
+#define {{ '{:<31}'.format(macro) }} \
+	({{ width }})

From ac159338d53b8846b020be8260884e8234572a70 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 3 Oct 2024 14:54:46 -0400
Subject: [PATCH 1055/1530] xdrgen: emit maxsize macros

Add "definitions" subcommand logic to emit maxsize macros in
generated code.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 .../net/sunrpc/xdrgen/subcmds/definitions.py  | 24 ++++++++++++++++---
 tools/net/sunrpc/xdrgen/subcmds/source.py     |  3 +--
 2 files changed, 22 insertions(+), 5 deletions(-)

diff --git a/tools/net/sunrpc/xdrgen/subcmds/definitions.py b/tools/net/sunrpc/xdrgen/subcmds/definitions.py
index 5cd13d53221f6..c956e27f37c09 100644
--- a/tools/net/sunrpc/xdrgen/subcmds/definitions.py
+++ b/tools/net/sunrpc/xdrgen/subcmds/definitions.py
@@ -28,9 +28,7 @@
 logger.setLevel(logging.INFO)
 
 
-def emit_header_definitions(
-    root: Specification, language: str, peer: str
-) -> None:
+def emit_header_definitions(root: Specification, language: str, peer: str) -> None:
     """Emit header definitions"""
     for definition in root.definitions:
         if isinstance(definition.value, _XdrConstant):
@@ -52,6 +50,25 @@ def emit_header_definitions(
         gen.emit_definition(definition.value)
 
 
+def emit_header_maxsize(root: Specification, language: str, peer: str) -> None:
+    """Emit header maxsize macros"""
+    print("")
+    for definition in root.definitions:
+        if isinstance(definition.value, _XdrEnum):
+            gen = XdrEnumGenerator(language, peer)
+        elif isinstance(definition.value, _XdrPointer):
+            gen = XdrPointerGenerator(language, peer)
+        elif isinstance(definition.value, _XdrTypedef):
+            gen = XdrTypedefGenerator(language, peer)
+        elif isinstance(definition.value, _XdrStruct):
+            gen = XdrStructGenerator(language, peer)
+        elif isinstance(definition.value, _XdrUnion):
+            gen = XdrUnionGenerator(language, peer)
+        else:
+            continue
+        gen.emit_maxsize(definition.value)
+
+
 def handle_parse_error(e: UnexpectedInput) -> bool:
     """Simple parse error reporting, no recovery attempted"""
     print(e)
@@ -71,6 +88,7 @@ def subcmd(args: Namespace) -> int:
         gen.emit_definition(args.filename, ast)
 
         emit_header_definitions(ast, args.language, args.peer)
+        emit_header_maxsize(ast, args.language, args.peer)
 
         gen = XdrHeaderBottomGenerator(args.language, args.peer)
         gen.emit_definition(args.filename, ast)
diff --git a/tools/net/sunrpc/xdrgen/subcmds/source.py b/tools/net/sunrpc/xdrgen/subcmds/source.py
index 00c04ad15b895..2024954748f09 100644
--- a/tools/net/sunrpc/xdrgen/subcmds/source.py
+++ b/tools/net/sunrpc/xdrgen/subcmds/source.py
@@ -83,8 +83,7 @@ def generate_client_source(filename: str, root: Specification, language: str) ->
     gen = XdrSourceTopGenerator(language, "client")
     gen.emit_source(filename, root)
 
-    # cel: todo: client needs XDR size macros
-
+    print("")
     for definition in root.definitions:
         emit_source_encoder(definition.value, language, "client")
     for definition in root.definitions:

From f67eef8da0e8c54709fefdecd16ad8d70f0c9d20 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 11 Nov 2024 11:01:13 -0500
Subject: [PATCH 1056/1530] nfsd: drop inode parameter from
 nfsd4_change_attribute()

The inode that nfs4_open_delegation() passes to this function is
wrong, which throws off the result. The inode will end up getting a
directory-style change attr instead of a regular-file-style one.

Fix up nfs4_delegation_stat() to fetch STATX_MODE, and then drop the
inode parameter from nfsd4_change_attribute(), since it's no longer
needed.

Fixes: c5967721e106 ("NFSD: handle GETATTR conflict with write delegation")
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4state.c |  5 ++---
 fs/nfsd/nfs4xdr.c   |  2 +-
 fs/nfsd/nfsfh.c     | 20 ++++++++++++--------
 fs/nfsd/nfsfh.h     |  3 +--
 4 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 551d2958ec290..d3cfc64715399 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5957,7 +5957,7 @@ nfs4_delegation_stat(struct nfs4_delegation *dp, struct svc_fh *currentfh,
 	path.dentry = file_dentry(nf->nf_file);
 
 	rc = vfs_getattr(&path, stat,
-			 (STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE),
+			 (STATX_MODE | STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE),
 			 AT_STATX_SYNC_AS_STAT);
 
 	nfsd_file_put(nf);
@@ -6041,8 +6041,7 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 		}
 		open->op_delegate_type = NFS4_OPEN_DELEGATE_WRITE;
 		dp->dl_cb_fattr.ncf_cur_fsize = stat.size;
-		dp->dl_cb_fattr.ncf_initial_cinfo =
-			nfsd4_change_attribute(&stat, d_inode(currentfh->fh_dentry));
+		dp->dl_cb_fattr.ncf_initial_cinfo = nfsd4_change_attribute(&stat);
 		trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid);
 	} else {
 		open->op_delegate_type = NFS4_OPEN_DELEGATE_READ;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index f118921250c31..8d25aef51ad15 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3040,7 +3040,7 @@ static __be32 nfsd4_encode_fattr4_change(struct xdr_stream *xdr,
 		return nfs_ok;
 	}
 
-	c = nfsd4_change_attribute(&args->stat, d_inode(args->dentry));
+	c = nfsd4_change_attribute(&args->stat);
 	return nfsd4_encode_changeid4(xdr, c);
 }
 
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 40ad58a6a0361..96e19c50a5d7e 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -667,20 +667,18 @@ fh_update(struct svc_fh *fhp)
 __be32 __must_check fh_fill_pre_attrs(struct svc_fh *fhp)
 {
 	bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
-	struct inode *inode;
 	struct kstat stat;
 	__be32 err;
 
 	if (fhp->fh_no_wcc || fhp->fh_pre_saved)
 		return nfs_ok;
 
-	inode = d_inode(fhp->fh_dentry);
 	err = fh_getattr(fhp, &stat);
 	if (err)
 		return err;
 
 	if (v4)
-		fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode);
+		fhp->fh_pre_change = nfsd4_change_attribute(&stat);
 
 	fhp->fh_pre_mtime = stat.mtime;
 	fhp->fh_pre_ctime = stat.ctime;
@@ -697,7 +695,6 @@ __be32 __must_check fh_fill_pre_attrs(struct svc_fh *fhp)
 __be32 fh_fill_post_attrs(struct svc_fh *fhp)
 {
 	bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
-	struct inode *inode = d_inode(fhp->fh_dentry);
 	__be32 err;
 
 	if (fhp->fh_no_wcc)
@@ -713,7 +710,7 @@ __be32 fh_fill_post_attrs(struct svc_fh *fhp)
 	fhp->fh_post_saved = true;
 	if (v4)
 		fhp->fh_post_change =
-			nfsd4_change_attribute(&fhp->fh_post_attr, inode);
+			nfsd4_change_attribute(&fhp->fh_post_attr);
 	return nfs_ok;
 }
 
@@ -804,7 +801,14 @@ enum fsid_source fsid_source(const struct svc_fh *fhp)
 	return FSIDSOURCE_DEV;
 }
 
-/*
+/**
+ * nfsd4_change_attribute - Generate an NFSv4 change_attribute value
+ * @stat: inode attributes
+ *
+ * Caller must fill in @stat before calling, typically by invoking
+ * vfs_getattr() with STATX_MODE, STATX_CTIME, and STATX_CHANGE_COOKIE.
+ * Returns an unsigned 64-bit changeid4 value (RFC 8881 Section 3.2).
+ *
  * We could use i_version alone as the change attribute.  However, i_version
  * can go backwards on a regular file after an unclean shutdown.  On its own
  * that doesn't necessarily cause a problem, but if i_version goes backwards
@@ -821,13 +825,13 @@ enum fsid_source fsid_source(const struct svc_fh *fhp)
  * assume that the new change attr is always logged to stable storage in some
  * fashion before the results can be seen.
  */
-u64 nfsd4_change_attribute(const struct kstat *stat, const struct inode *inode)
+u64 nfsd4_change_attribute(const struct kstat *stat)
 {
 	u64 chattr;
 
 	if (stat->result_mask & STATX_CHANGE_COOKIE) {
 		chattr = stat->change_cookie;
-		if (S_ISREG(inode->i_mode) &&
+		if (S_ISREG(stat->mode) &&
 		    !(stat->attributes & STATX_ATTR_CHANGE_MONOTONIC)) {
 			chattr += (u64)stat->ctime.tv_sec << 30;
 			chattr += stat->ctime.tv_nsec;
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 5b7394801dc42..876152a91f122 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -297,8 +297,7 @@ static inline void fh_clear_pre_post_attrs(struct svc_fh *fhp)
 	fhp->fh_pre_saved = false;
 }
 
-u64 nfsd4_change_attribute(const struct kstat *stat,
-			   const struct inode *inode);
+u64 nfsd4_change_attribute(const struct kstat *stat);
 __be32 __must_check fh_fill_pre_attrs(struct svc_fh *fhp);
 __be32 fh_fill_post_attrs(struct svc_fh *fhp);
 __be32 __must_check fh_fill_both_attrs(struct svc_fh *fhp);

From c757ca1a56edff8d288d4a6cfdbb305dd03e8048 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Fri, 4 Oct 2024 09:16:44 -0400
Subject: [PATCH 1057/1530] nfsd: drop the ncf_cb_bmap field

This is always the same value, and in a later patch we're going to need
to set bits in WORD2. We can simplify this code and save a little space
in the delegation too. Just hardcode the bitmap in the callback encode
function.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4callback.c | 5 ++++-
 fs/nfsd/nfs4state.c    | 1 -
 fs/nfsd/state.h        | 1 -
 3 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 478b548f4147f..f5ba9be917700 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -364,10 +364,13 @@ encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr,
 	struct nfs4_delegation *dp =
 		container_of(fattr, struct nfs4_delegation, dl_cb_fattr);
 	struct knfsd_fh *fh = &dp->dl_stid.sc_file->fi_fhandle;
+	u32 bmap[1];
+
+	bmap[0] = FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE;
 
 	encode_nfs_cb_opnum4(xdr, OP_CB_GETATTR);
 	encode_nfs_fh4(xdr, fh);
-	encode_bitmap4(xdr, fattr->ncf_cb_bmap, ARRAY_SIZE(fattr->ncf_cb_bmap));
+	encode_bitmap4(xdr, bmap, ARRAY_SIZE(bmap));
 	hdr->nops++;
 }
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index d3cfc64715399..f25d183987139 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1184,7 +1184,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
 	nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client,
 			&nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR);
 	dp->dl_cb_fattr.ncf_file_modified = false;
-	dp->dl_cb_fattr.ncf_cb_bmap[0] = FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE;
 	get_nfs4_file(fp);
 	dp->dl_stid.sc_file = fp;
 	return dp;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 35b3564c065fa..9721c6d6ec429 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -140,7 +140,6 @@ struct nfs4_cpntf_state {
 struct nfs4_cb_fattr {
 	struct nfsd4_callback ncf_getattr;
 	u32 ncf_cb_status;
-	u32 ncf_cb_bmap[1];
 
 	/* from CB_GETATTR reply */
 	u64 ncf_cb_change;

From 3a405432e7cd84f5e137928ce383aa85a54fb3a6 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Fri, 4 Oct 2024 09:16:45 -0400
Subject: [PATCH 1058/1530] nfsd: drop the nfsd4_fattr_args "size" field

We already have a slot for this in the kstat structure. Just overwrite
that instead of keeping a copy.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4xdr.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 8d25aef51ad15..7f1cb1cdb67e2 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2928,7 +2928,6 @@ struct nfsd4_fattr_args {
 	struct kstat		stat;
 	struct kstatfs		statfs;
 	struct nfs4_acl		*acl;
-	u64			size;
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 	void			*context;
 	int			contextlen;
@@ -3047,7 +3046,7 @@ static __be32 nfsd4_encode_fattr4_change(struct xdr_stream *xdr,
 static __be32 nfsd4_encode_fattr4_size(struct xdr_stream *xdr,
 				       const struct nfsd4_fattr_args *args)
 {
-	return nfsd4_encode_uint64_t(xdr, args->size);
+	return nfsd4_encode_uint64_t(xdr, args->stat.size);
 }
 
 static __be32 nfsd4_encode_fattr4_fsid(struct xdr_stream *xdr,
@@ -3555,7 +3554,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 		if (status)
 			goto out;
 	}
-	args.size = 0;
 	if (attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) {
 		status = nfsd4_deleg_getattr_conflict(rqstp, dentry,
 					&file_modified, &size);
@@ -3569,9 +3567,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	if (err)
 		goto out_nfserr;
 	if (file_modified)
-		args.size = size;
-	else
-		args.size = args.stat.size;
+		args.stat.size = size;
 
 	if (!(args.stat.result_mask & STATX_BTIME))
 		/* underlying FS does not offer btime so we can't share it */

From f6259e2e4f64a1780b285037dbd4f947121ae8fd Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Fri, 4 Oct 2024 09:16:46 -0400
Subject: [PATCH 1059/1530] nfsd: have nfsd4_deleg_getattr_conflict pass back
 write deleg pointer

Currently we pass back the size and whether it has been modified, but
those just mirror values tracked inside the delegation. In a later
patch, we'll need to get at the timestamps in the delegation too, so
just pass back a reference to the write delegation, and use that to
properly override values in the iattr.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4state.c | 17 ++++++++---------
 fs/nfsd/nfs4xdr.c   | 16 ++++++++++------
 fs/nfsd/state.h     |  2 +-
 3 files changed, 19 insertions(+), 16 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index f25d183987139..e0862173cd9ea 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -8863,8 +8863,7 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
  * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict
  * @rqstp: RPC transaction context
  * @dentry: dentry of inode to be checked for a conflict
- * @modified: return true if file was modified
- * @size: new size of file if modified is true
+ * @pdp: returned WRITE delegation, if one was found
  *
  * This function is called when there is a conflict between a write
  * delegation and a change/size GETATTR from another client. The server
@@ -8874,11 +8873,12 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
  * 18.7.4.
  *
  * Returns 0 if there is no conflict; otherwise an nfs_stat
- * code is returned.
+ * code is returned. If @pdp is set to a non-NULL value, then the
+ * caller must put the reference.
  */
 __be32
 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry,
-				bool *modified, u64 *size)
+			     struct nfs4_delegation **pdp)
 {
 	__be32 status;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
@@ -8889,10 +8889,9 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry,
 	struct nfs4_cb_fattr *ncf;
 	struct inode *inode = d_inode(dentry);
 
-	*modified = false;
 	ctx = locks_inode_context(inode);
 	if (!ctx)
-		return 0;
+		return nfs_ok;
 
 #define NON_NFSD_LEASE ((void *)1)
 
@@ -8958,10 +8957,10 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry,
 			goto out_status;
 		}
 		ncf->ncf_cur_fsize = ncf->ncf_cb_fsize;
-		*size = ncf->ncf_cur_fsize;
-		*modified = true;
+		*pdp = dp;
+		return nfs_ok;
 	}
-	status = 0;
+	status = nfs_ok;
 out_status:
 	nfs4_put_stid(&dp->dl_stid);
 	return status;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 7f1cb1cdb67e2..abbfd2b58c82b 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3511,6 +3511,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 		    int ignore_crossmnt)
 {
 	DECLARE_BITMAP(attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops));
+	struct nfs4_delegation *dp = NULL;
 	struct nfsd4_fattr_args args;
 	struct svc_fh *tempfh = NULL;
 	int starting_len = xdr->buf->len;
@@ -3525,8 +3526,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 		.dentry	= dentry,
 	};
 	unsigned long bit;
-	bool file_modified = false;
-	u64 size = 0;
 
 	WARN_ON_ONCE(bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1);
 	WARN_ON_ONCE(!nfsd_attrs_supported(minorversion, bmval));
@@ -3555,8 +3554,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 			goto out;
 	}
 	if (attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) {
-		status = nfsd4_deleg_getattr_conflict(rqstp, dentry,
-					&file_modified, &size);
+		status = nfsd4_deleg_getattr_conflict(rqstp, dentry, &dp);
 		if (status)
 			goto out;
 	}
@@ -3564,10 +3562,16 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	err = vfs_getattr(&path, &args.stat,
 			  STATX_BASIC_STATS | STATX_BTIME | STATX_CHANGE_COOKIE,
 			  AT_STATX_SYNC_AS_STAT);
+	if (dp) {
+		struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr;
+
+		if (ncf->ncf_file_modified)
+			args.stat.size = ncf->ncf_cur_fsize;
+
+		nfs4_put_stid(&dp->dl_stid);
+	}
 	if (err)
 		goto out_nfserr;
-	if (file_modified)
-		args.stat.size = size;
 
 	if (!(args.stat.result_mask & STATX_BTIME))
 		/* underlying FS does not offer btime so we can't share it */
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 9721c6d6ec429..da22eaff37552 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -783,5 +783,5 @@ static inline bool try_to_expire_client(struct nfs4_client *clp)
 }
 
 extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp,
-		struct dentry *dentry, bool *file_modified, u64 *size);
+		struct dentry *dentry, struct nfs4_delegation **pdp);
 #endif   /* NFSD4_STATE_H */

From 93093ea1f05928b123dae38b710631362bef1601 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 22 Oct 2024 15:48:47 -0700
Subject: [PATCH 1060/1530] PCI: Make pci_stop_dev() concurrent safe

Use the atomic ADDED flag to ensure concurrent callers can't attempt to
stop the device multiple times. Callers should currently all be holding the
pci_rescan_remove_lock, so there shouldn't be an existing race. But that
global lock can cause lock dependency issues, so this is preparing to
reduce reliance on that lock by using the existing existing atomic bit ops.

Link: https://lore.kernel.org/r/20241022224851.340648-2-kbusch@meta.com
Signed-off-by: Keith Busch <kbusch@kernel.org>
[bhelgaas: squash https://lore.kernel.org/r/20241111180659.3321671-1-kbusch@meta.com]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/bus.c    |  2 +-
 drivers/pci/pci.h    | 11 +++++++++--
 drivers/pci/remove.c | 19 +++++++++----------
 3 files changed, 19 insertions(+), 13 deletions(-)

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 55c8536860518..e41dfece0d969 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -348,7 +348,7 @@ void pci_bus_add_device(struct pci_dev *dev)
 	if (retval < 0 && retval != -EPROBE_DEFER)
 		pci_warn(dev, "device attach failed (%d)\n", retval);
 
-	pci_dev_assign_added(dev, true);
+	pci_dev_assign_added(dev);
 
 	if (dev_of_node(&dev->dev) && pci_is_bridge(dev)) {
 		retval = of_platform_populate(dev_of_node(&dev->dev), NULL, NULL,
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 14d00ce45bfa9..0d9169e0e7d2a 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -470,9 +470,16 @@ static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused)
 #define PCI_DPC_RECOVERED 1
 #define PCI_DPC_RECOVERING 2
 
-static inline void pci_dev_assign_added(struct pci_dev *dev, bool added)
+static inline void pci_dev_assign_added(struct pci_dev *dev)
 {
-	assign_bit(PCI_DEV_ADDED, &dev->priv_flags, added);
+	smp_mb__before_atomic();
+	set_bit(PCI_DEV_ADDED, &dev->priv_flags);
+	smp_mb__after_atomic();
+}
+
+static inline bool pci_dev_test_and_clear_added(struct pci_dev *dev)
+{
+	return test_and_clear_bit(PCI_DEV_ADDED, &dev->priv_flags);
 }
 
 static inline bool pci_dev_is_added(const struct pci_dev *dev)
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index e4ce1145aa3ee..78863f241a886 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -33,16 +33,15 @@ static void pci_stop_dev(struct pci_dev *dev)
 {
 	pci_pme_active(dev, false);
 
-	if (pci_dev_is_added(dev)) {
-		device_for_each_child(dev->dev.parent, dev_of_node(&dev->dev),
-				      pci_pwrctl_unregister);
-		device_release_driver(&dev->dev);
-		pci_proc_detach_device(dev);
-		pci_remove_sysfs_dev_files(dev);
-		of_pci_remove_node(dev);
-
-		pci_dev_assign_added(dev, false);
-	}
+	if (!pci_dev_test_and_clear_added(dev))
+		return;
+
+	device_for_each_child(dev->dev.parent, dev_of_node(&dev->dev),
+			      pci_pwrctl_unregister);
+	device_release_driver(&dev->dev);
+	pci_proc_detach_device(dev);
+	pci_remove_sysfs_dev_files(dev);
+	of_pci_remove_node(dev);
 }
 
 static void pci_destroy_dev(struct pci_dev *dev)

From e3f30d563a388220a7c4e3b9a7b52ac0b0324b26 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 22 Oct 2024 15:48:48 -0700
Subject: [PATCH 1061/1530] PCI: Make pci_destroy_dev() concurrent safe

Use an atomic flag instead of the racy check against the device's kobj
parent. We shouldn't be poking into device implementation details at this
level anyway.

Link: https://lore.kernel.org/r/20241022224851.340648-3-kbusch@meta.com
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/pci.h    | 6 ++++++
 drivers/pci/remove.c | 2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 0d9169e0e7d2a..187c5c83412d9 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -469,6 +469,7 @@ static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused)
 #define PCI_DEV_ADDED 0
 #define PCI_DPC_RECOVERED 1
 #define PCI_DPC_RECOVERING 2
+#define PCI_DEV_REMOVED 3
 
 static inline void pci_dev_assign_added(struct pci_dev *dev)
 {
@@ -487,6 +488,11 @@ static inline bool pci_dev_is_added(const struct pci_dev *dev)
 	return test_bit(PCI_DEV_ADDED, &dev->priv_flags);
 }
 
+static inline bool pci_dev_test_and_set_removed(struct pci_dev *dev)
+{
+	return test_and_set_bit(PCI_DEV_REMOVED, &dev->priv_flags);
+}
+
 #ifdef CONFIG_PCIEAER
 #include <linux/aer.h>
 
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index 78863f241a886..1f35945459fd7 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -46,7 +46,7 @@ static void pci_stop_dev(struct pci_dev *dev)
 
 static void pci_destroy_dev(struct pci_dev *dev)
 {
-	if (!dev->dev.kobj.parent)
+	if (pci_dev_test_and_set_removed(dev))
 		return;
 
 	pci_npem_remove(dev);

From 4d6dcd6c2fa3a80898651d323c150e5ebc03881d Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 22 Oct 2024 15:48:49 -0700
Subject: [PATCH 1062/1530] PCI: Move __pci_walk_bus() mutex to where we need
 it
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Simplify __pci_walk_bus() by moving the pci_bus_sem mutex into
pci_walk_bus(), the only place it is needed, and removing the parameter
that told __pci_walk_bus() whether to acquire the mutex.

Link: https://lore.kernel.org/r/20241022224851.340648-4-kbusch@meta.com
Signed-off-by: Keith Busch <kbusch@kernel.org>
[bhelgaas: commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/pci/bus.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index e41dfece0d969..7c07a141e8772 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -390,7 +390,7 @@ void pci_bus_add_devices(const struct pci_bus *bus)
 EXPORT_SYMBOL(pci_bus_add_devices);
 
 static void __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
-			   void *userdata, bool locked)
+			   void *userdata)
 {
 	struct pci_dev *dev;
 	struct pci_bus *bus;
@@ -398,8 +398,6 @@ static void __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void
 	int retval;
 
 	bus = top;
-	if (!locked)
-		down_read(&pci_bus_sem);
 	next = top->devices.next;
 	for (;;) {
 		if (next == &bus->devices) {
@@ -422,8 +420,6 @@ static void __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void
 		if (retval)
 			break;
 	}
-	if (!locked)
-		up_read(&pci_bus_sem);
 }
 
 /**
@@ -441,7 +437,9 @@ static void __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void
  */
 void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata)
 {
-	__pci_walk_bus(top, cb, userdata, false);
+	down_read(&pci_bus_sem);
+	__pci_walk_bus(top, cb, userdata);
+	up_read(&pci_bus_sem);
 }
 EXPORT_SYMBOL_GPL(pci_walk_bus);
 
@@ -449,7 +447,7 @@ void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *
 {
 	lockdep_assert_held(&pci_bus_sem);
 
-	__pci_walk_bus(top, cb, userdata, true);
+	__pci_walk_bus(top, cb, userdata);
 }
 EXPORT_SYMBOL_GPL(pci_walk_bus_locked);
 

From ee061da777f704976c6d3fdc1707788d11a052c5 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 22 Oct 2024 15:48:50 -0700
Subject: [PATCH 1063/1530] PCI: Convert __pci_walk_bus() to be recursive
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The original implementation of __pci_walk_bus() chose a non-recursive walk,
presumably as a precaution on stack use. We do recursive bus walking in
other places though. For example:

  pci_bus_resettable()
  pci_stop_bus_device()
  pci_remove_bus_device()
  pci_bus_allocate_dev_resources()

So recursive pci bus walking is well tested and safe, and is easier to
follow.

Convert __pci_walk_bus() to be recursive to make it easier to introduce
finer grain locking in the future.

Link: https://lore.kernel.org/r/20241022224851.340648-5-kbusch@meta.com
Signed-off-by: Keith Busch <kbusch@kernel.org>
[bhelgaas: commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/pci/bus.c | 36 +++++++++++-------------------------
 1 file changed, 11 insertions(+), 25 deletions(-)

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 7c07a141e8772..8491e9c7f0586 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -389,37 +389,23 @@ void pci_bus_add_devices(const struct pci_bus *bus)
 }
 EXPORT_SYMBOL(pci_bus_add_devices);
 
-static void __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
-			   void *userdata)
+static int __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
+			  void *userdata)
 {
 	struct pci_dev *dev;
-	struct pci_bus *bus;
-	struct list_head *next;
-	int retval;
+	int ret = 0;
 
-	bus = top;
-	next = top->devices.next;
-	for (;;) {
-		if (next == &bus->devices) {
-			/* end of this bus, go up or finish */
-			if (bus == top)
+	list_for_each_entry(dev, &top->devices, bus_list) {
+		ret = cb(dev, userdata);
+		if (ret)
+			break;
+		if (dev->subordinate) {
+			ret = __pci_walk_bus(dev->subordinate, cb, userdata);
+			if (ret)
 				break;
-			next = bus->self->bus_list.next;
-			bus = bus->self->bus;
-			continue;
 		}
-		dev = list_entry(next, struct pci_dev, bus_list);
-		if (dev->subordinate) {
-			/* this is a pci-pci bridge, do its devices next */
-			next = dev->subordinate->devices.next;
-			bus = dev->subordinate;
-		} else
-			next = dev->bus_list.next;
-
-		retval = cb(dev, userdata);
-		if (retval)
-			break;
 	}
+	return ret;
 }
 
 /**

From d2bd39c0456b75be9dfc7d774b8d021355c26ae3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 18 Oct 2024 17:47:49 +0300
Subject: [PATCH 1064/1530] PCI: Store all PCIe Supported Link Speeds
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PCIe bandwidth controller added by a subsequent commit will require
selecting PCIe Link Speeds that are lower than the Maximum Link Speed.

The struct pci_bus only stores max_bus_speed. Even if PCIe r6.1 sec 8.2.1
currently disallows gaps in supported Link Speeds, the Implementation Note
in PCIe r6.1 sec 7.5.3.18, recommends determining supported Link Speeds
using the Supported Link Speeds Vector in the Link Capabilities 2 Register
(when available) to "avoid software being confused if a future
specification defines Links that do not require support for all slower
speeds."

Reuse code in pcie_get_speed_cap() to add pcie_get_supported_speeds() to
query the Supported Link Speeds Vector of a PCIe device. The value is taken
directly from the Supported Link Speeds Vector or synthesized from the Max
Link Speed in the Link Capabilities Register when the Link Capabilities 2
Register is not available.

The Supported Link Speeds Vector in the Link Capabilities Register 2
corresponds to the bus below on Root Ports and Downstream Ports, whereas it
corresponds to the bus above on Upstream Ports and Endpoints (PCIe r6.1 sec
7.5.3.18):

  Supported Link Speeds Vector - This field indicates the supported Link
  speed(s) of the associated Port.

Add supported_speeds into the struct pci_dev that caches the
Supported Link Speeds Vector.

supported_speeds contains a set of Link Speeds only in the case where PCIe
Link Speed can be determined. Root Complex Integrated Endpoints do not have
a well-defined Link Speed because they do not implement either of the Link
Capabilities Registers, which is allowed by PCIe r6.1 sec 7.5.3 (the same
limitation applies to determining cur_bus_speed and max_bus_speed that are
PCI_SPEED_UNKNOWN in such case). This is of no concern from PCIe bandwidth
controller point of view because such devices are not attached into a PCIe
Root Port that could be controlled.

The supported_speeds field keeps the extra reserved zero at the least
significant bit to match the Link Capabilities 2 Register layout.

An attempt was made to store supported_speeds field into the struct pci_bus
as an intersection of both ends of the Link, however, the subordinate
struct pci_bus is not available early enough. The Target Speed quirk (in
pcie_failed_link_retrain()) can run either during initial scan or later,
requiring it to use the API provided by the PCIe bandwidth controller to
set the Target Link Speed in order to co-exist with the bandwidth
controller. When the Target Speed quirk is calling the bandwidth controller
during initial scan, the struct pci_bus is not yet initialized. As such,
storing supported_speeds into the struct pci_bus is not viable.

Suggested-by: Lukas Wunner <lukas@wunner.de>
Link: https://lore.kernel.org/r/20241018144755.7875-4-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
[bhelgaas: move pcie_get_supported_speeds() decl to drivers/pci/pci.h]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/pci.c             | 58 +++++++++++++++++++++++++----------
 drivers/pci/pci.h             |  1 +
 drivers/pci/probe.c           |  3 ++
 include/linux/pci.h           | 10 +++++-
 include/uapi/linux/pci_regs.h |  1 +
 5 files changed, 56 insertions(+), 17 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 7d85c04fbba2a..3d67e8b50ba2b 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -6189,38 +6189,64 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev,
 EXPORT_SYMBOL(pcie_bandwidth_available);
 
 /**
- * pcie_get_speed_cap - query for the PCI device's link speed capability
+ * pcie_get_supported_speeds - query Supported Link Speed Vector
  * @dev: PCI device to query
  *
- * Query the PCI device speed capability.  Return the maximum link speed
- * supported by the device.
+ * Query @dev supported link speeds.
+ *
+ * Implementation Note in PCIe r6.0 sec 7.5.3.18 recommends determining
+ * supported link speeds using the Supported Link Speeds Vector in the Link
+ * Capabilities 2 Register (when available).
+ *
+ * Link Capabilities 2 was added in PCIe r3.0, sec 7.8.18.
+ *
+ * Without Link Capabilities 2, i.e., prior to PCIe r3.0, Supported Link
+ * Speeds field in Link Capabilities is used and only 2.5 GT/s and 5.0 GT/s
+ * speeds were defined.
+ *
+ * For @dev without Supported Link Speed Vector, the field is synthesized
+ * from the Max Link Speed field in the Link Capabilities Register.
+ *
+ * Return: Supported Link Speeds Vector (+ reserved 0 at LSB).
  */
-enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev)
+u8 pcie_get_supported_speeds(struct pci_dev *dev)
 {
 	u32 lnkcap2, lnkcap;
+	u8 speeds;
 
 	/*
-	 * Link Capabilities 2 was added in PCIe r3.0, sec 7.8.18.  The
-	 * implementation note there recommends using the Supported Link
-	 * Speeds Vector in Link Capabilities 2 when supported.
-	 *
-	 * Without Link Capabilities 2, i.e., prior to PCIe r3.0, software
-	 * should use the Supported Link Speeds field in Link Capabilities,
-	 * where only 2.5 GT/s and 5.0 GT/s speeds were defined.
+	 * Speeds retain the reserved 0 at LSB before PCIe Supported Link
+	 * Speeds Vector to allow using SLS Vector bit defines directly.
 	 */
 	pcie_capability_read_dword(dev, PCI_EXP_LNKCAP2, &lnkcap2);
+	speeds = lnkcap2 & PCI_EXP_LNKCAP2_SLS;
 
 	/* PCIe r3.0-compliant */
-	if (lnkcap2)
-		return PCIE_LNKCAP2_SLS2SPEED(lnkcap2);
+	if (speeds)
+		return speeds;
 
 	pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap);
+
+	/* Synthesize from the Max Link Speed field */
 	if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_5_0GB)
-		return PCIE_SPEED_5_0GT;
+		speeds = PCI_EXP_LNKCAP2_SLS_5_0GB | PCI_EXP_LNKCAP2_SLS_2_5GB;
 	else if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_2_5GB)
-		return PCIE_SPEED_2_5GT;
+		speeds = PCI_EXP_LNKCAP2_SLS_2_5GB;
 
-	return PCI_SPEED_UNKNOWN;
+	return speeds;
+}
+
+/**
+ * pcie_get_speed_cap - query for the PCI device's link speed capability
+ * @dev: PCI device to query
+ *
+ * Query the PCI device speed capability.
+ *
+ * Return: the maximum link speed supported by the device.
+ */
+enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev)
+{
+	return PCIE_LNKCAP2_SLS2SPEED(dev->supported_speeds);
 }
 EXPORT_SYMBOL(pcie_get_speed_cap);
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 14d00ce45bfa9..d0a46ecf72895 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -373,6 +373,7 @@ static inline int pcie_dev_speed_mbps(enum pci_bus_speed speed)
 	return -EINVAL;
 }
 
+u8 pcie_get_supported_speeds(struct pci_dev *dev);
 const char *pci_speed_string(enum pci_bus_speed speed);
 enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev);
 enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev);
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 4f68414c30860..af153a8e82255 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1947,6 +1947,9 @@ int pci_setup_device(struct pci_dev *dev)
 
 	set_pcie_untrusted(dev);
 
+	if (pci_is_pcie(dev))
+		dev->supported_speeds = pcie_get_supported_speeds(dev);
+
 	/* "Unknown power state" */
 	dev->current_state = PCI_UNKNOWN;
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index be5ed534c39cf..99c6fa30d25be 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -318,7 +318,14 @@ struct pci_sriov;
 struct pci_p2pdma;
 struct rcec_ea;
 
-/* The pci_dev structure describes PCI devices */
+/* struct pci_dev - describes a PCI device
+ *
+ * @supported_speeds:	PCIe Supported Link Speeds Vector (+ reserved 0 at
+ *			LSB). 0 when the supported speeds cannot be
+ *			determined (e.g., for Root Complex Integrated
+ *			Endpoints without the relevant Capability
+ *			Registers).
+ */
 struct pci_dev {
 	struct list_head bus_list;	/* Node in per-bus list */
 	struct pci_bus	*bus;		/* Bus this device is on */
@@ -522,6 +529,7 @@ struct pci_dev {
 	struct npem	*npem;		/* Native PCIe Enclosure Management */
 #endif
 	u16		acs_cap;	/* ACS Capability offset */
+	u8		supported_speeds; /* Supported Link Speeds Vector */
 	phys_addr_t	rom;		/* Physical address if not from BAR */
 	size_t		romlen;		/* Length if not from BAR */
 	/*
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 12323b3334a9c..f3c9de0a497cf 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -678,6 +678,7 @@
 #define PCI_EXP_DEVSTA2		0x2a	/* Device Status 2 */
 #define PCI_CAP_EXP_RC_ENDPOINT_SIZEOF_V2 0x2c	/* end of v2 EPs w/o link */
 #define PCI_EXP_LNKCAP2		0x2c	/* Link Capabilities 2 */
+#define  PCI_EXP_LNKCAP2_SLS		0x000000fe /* Supported Link Speeds Vector */
 #define  PCI_EXP_LNKCAP2_SLS_2_5GB	0x00000002 /* Supported Speed 2.5GT/s */
 #define  PCI_EXP_LNKCAP2_SLS_5_0GB	0x00000004 /* Supported Speed 5GT/s */
 #define  PCI_EXP_LNKCAP2_SLS_8_0GB	0x00000008 /* Supported Speed 8GT/s */

From e93d9fcfd7dc643eb5fce43053774d27bea2b263 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 18 Oct 2024 17:47:50 +0300
Subject: [PATCH 1065/1530] PCI: Refactor pcie_update_link_speed()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

pcie_update_link_speed() is passed the Link Status register but not all
callers have that value at hand nor need the value.

Refactor pcie_update_link_speed() to include reading the Link Status
register and create __pcie_update_link_speed() which can be used by the
hotplug code that has the register value at hand beforehand (and needs the
value for other purposes).

Link: https://lore.kernel.org/r/20241018144755.7875-5-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/hotplug/pciehp_hpc.c |  2 +-
 drivers/pci/pci.h                |  7 ++++++-
 drivers/pci/probe.c              | 12 +++++++-----
 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 736ad8baa2a55..bb5a8d9f03ad9 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -319,7 +319,7 @@ int pciehp_check_link_status(struct controller *ctrl)
 		return -1;
 	}
 
-	pcie_update_link_speed(ctrl->pcie->port->subordinate, lnk_status);
+	__pcie_update_link_speed(ctrl->pcie->port->subordinate, lnk_status);
 
 	if (!found) {
 		ctrl_info(ctrl, "Slot(%s): No device found\n",
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index d0a46ecf72895..8137ad2fead88 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -379,7 +379,12 @@ enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev);
 enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev);
 void __pcie_print_link_status(struct pci_dev *dev, bool verbose);
 void pcie_report_downtraining(struct pci_dev *dev);
-void pcie_update_link_speed(struct pci_bus *bus, u16 link_status);
+
+static inline void __pcie_update_link_speed(struct pci_bus *bus, u16 linksta)
+{
+	bus->cur_bus_speed = pcie_link_speed[linksta & PCI_EXP_LNKSTA_CLS];
+}
+void pcie_update_link_speed(struct pci_bus *bus);
 
 /* Single Root I/O Virtualization */
 struct pci_sriov {
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index af153a8e82255..c138daf789610 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -742,9 +742,13 @@ const char *pci_speed_string(enum pci_bus_speed speed)
 }
 EXPORT_SYMBOL_GPL(pci_speed_string);
 
-void pcie_update_link_speed(struct pci_bus *bus, u16 linksta)
+void pcie_update_link_speed(struct pci_bus *bus)
 {
-	bus->cur_bus_speed = pcie_link_speed[linksta & PCI_EXP_LNKSTA_CLS];
+	struct pci_dev *bridge = bus->self;
+	u16 linksta;
+
+	pcie_capability_read_word(bridge, PCI_EXP_LNKSTA, &linksta);
+	__pcie_update_link_speed(bus, linksta);
 }
 EXPORT_SYMBOL_GPL(pcie_update_link_speed);
 
@@ -827,13 +831,11 @@ static void pci_set_bus_speed(struct pci_bus *bus)
 
 	if (pci_is_pcie(bridge)) {
 		u32 linkcap;
-		u16 linksta;
 
 		pcie_capability_read_dword(bridge, PCI_EXP_LNKCAP, &linkcap);
 		bus->max_bus_speed = pcie_link_speed[linkcap & PCI_EXP_LNKCAP_SLS];
 
-		pcie_capability_read_word(bridge, PCI_EXP_LNKSTA, &linksta);
-		pcie_update_link_speed(bus, linksta);
+		pcie_update_link_speed(bus);
 	}
 }
 

From 3491f509666865412ad344cd4dde9f3c5a52326e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 18 Oct 2024 17:47:51 +0300
Subject: [PATCH 1066/1530] PCI: Abstract LBMS seen check into pcie_lbms_seen()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Target Speed quirk in pcie_failed_link_retrain() uses the presence of
LBMS bit as one of the triggering conditions, effectively monopolizing the
use of that bit. An upcoming change will introduce a PCIe bandwidth
controller which sets up an interrupt to track LBMS. As LBMS will be
cleared by the interrupt handler, the Target Speed quirk will no longer be
able to observe LBMS directly.

As a preparatory step for the change, extract the LBMS seen check from
pcie_failed_link_retrain() into a new function pcie_lmbs_seen().

Link: https://lore.kernel.org/r/20241018144755.7875-6-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/quirks.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index dccb60c1d9cc3..a560ea403b8ef 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -33,6 +33,11 @@
 #include <linux/switchtec.h>
 #include "pci.h"
 
+static bool pcie_lbms_seen(struct pci_dev *dev, u16 lnksta)
+{
+	return lnksta & PCI_EXP_LNKSTA_LBMS;
+}
+
 /*
  * Retrain the link of a downstream PCIe port by hand if necessary.
  *
@@ -96,8 +101,7 @@ int pcie_failed_link_retrain(struct pci_dev *dev)
 
 	pcie_capability_read_word(dev, PCI_EXP_LNKCTL2, &lnkctl2);
 	pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta);
-	if ((lnksta & (PCI_EXP_LNKSTA_LBMS | PCI_EXP_LNKSTA_DLLLA)) ==
-	    PCI_EXP_LNKSTA_LBMS) {
+	if (!(lnksta & PCI_EXP_LNKSTA_DLLLA) && pcie_lbms_seen(dev, lnksta)) {
 		u16 oldlnkctl2 = lnkctl2;
 
 		pci_info(dev, "broken device, retraining non-functional downstream link at 2.5GT/s\n");

From 38a18dfe9035d5a02a53271824de1854129c61dc Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 22 Oct 2024 15:48:51 -0700
Subject: [PATCH 1067/1530] PCI: Unexport pci_walk_bus_locked()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There's only one user of pci_walk_bus_locked(), and it's internal to the
PCI core.  Unexport it and make it private to drivers/pci/.

Link: https://lore.kernel.org/r/20241022224851.340648-6-kbusch@meta.com
Signed-off-by: Keith Busch <kbusch@kernel.org>
[bhelgaas: move decl to drivers/pci/pci.h]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/pci/bus.c   | 1 -
 drivers/pci/pci.h   | 3 +++
 include/linux/pci.h | 2 --
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 8491e9c7f0586..30620f3bb0e2d 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -435,7 +435,6 @@ void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *
 
 	__pci_walk_bus(top, cb, userdata);
 }
-EXPORT_SYMBOL_GPL(pci_walk_bus_locked);
 
 struct pci_bus *pci_bus_get(struct pci_bus *bus)
 {
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 187c5c83412d9..28cccfeb80763 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -323,6 +323,9 @@ void __pci_bus_assign_resources(const struct pci_bus *bus,
 				struct list_head *realloc_head,
 				struct list_head *fail_head);
 bool pci_bus_clip_resource(struct pci_dev *dev, int idx);
+void pci_walk_bus_locked(struct pci_bus *top,
+			 int (*cb)(struct pci_dev *, void *),
+			 void *userdata);
 
 const char *pci_resource_name(struct pci_dev *dev, unsigned int i);
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 573b4c4c2be61..0562903772735 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1623,8 +1623,6 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max,
 
 void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 		  void *userdata);
-void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
-			 void *userdata);
 int pci_cfg_space_size(struct pci_dev *dev);
 unsigned char pci_bus_max_busnr(struct pci_bus *bus);
 void pci_setup_bridge(struct pci_bus *bus);

From c0f3a0124d3f1dfed700d2871f9d37f418999af2 Mon Sep 17 00:00:00 2001
From: anish kumar <yesanishhere@gmail.com>
Date: Tue, 22 Oct 2024 23:11:26 -0700
Subject: [PATCH 1068/1530] power: supply: generic-adc-battery: change my gmail

change my contact in this driver.

Signed-off-by: anish kumar <yesanishhere@gmail.com>
Link: https://lore.kernel.org/r/20241023061126.7896-1-yesanishhere@gmail.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/generic-adc-battery.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c
index 7bdc6b2636090..d5d215f5ad8b1 100644
--- a/drivers/power/supply/generic-adc-battery.c
+++ b/drivers/power/supply/generic-adc-battery.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Generic battery driver using IIO
- * Copyright (C) 2012, Anish Kumar <anish198519851985@gmail.com>
+ * Copyright (C) 2012, Anish Kumar <yesanishhere@gmail.com>
  * Copyright (c) 2023, Sebastian Reichel <sre@kernel.org>
  */
 #include <linux/interrupt.h>
@@ -295,6 +295,6 @@ static struct platform_driver gab_driver = {
 };
 module_platform_driver(gab_driver);
 
-MODULE_AUTHOR("anish kumar <anish198519851985@gmail.com>");
+MODULE_AUTHOR("anish kumar <yesanishhere@gmail.com>");
 MODULE_DESCRIPTION("generic battery driver using IIO");
 MODULE_LICENSE("GPL");

From 9fdd97d63fe2be2ab890240cce0a5790e0ef9877 Mon Sep 17 00:00:00 2001
From: Chris Morgan <macromorgan@hotmail.com>
Date: Wed, 23 Oct 2024 13:47:59 -0500
Subject: [PATCH 1069/1530] power: supply: axp20x_usb_power: Use scaled
 iio_read_channel

Change iio_read_channel_processed to iio_read_channel_processed_scale
where appropriate.

Signed-off-by: Chris Morgan <macromorgan@hotmail.com>
Link: https://lore.kernel.org/r/20241023184800.109376-2-macroalpha82@gmail.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/axp20x_usb_power.c | 33 +++++++++++--------------
 1 file changed, 15 insertions(+), 18 deletions(-)

diff --git a/drivers/power/supply/axp20x_usb_power.c b/drivers/power/supply/axp20x_usb_power.c
index 2766352ab737d..9722912268fe8 100644
--- a/drivers/power/supply/axp20x_usb_power.c
+++ b/drivers/power/supply/axp20x_usb_power.c
@@ -220,16 +220,15 @@ static int axp20x_usb_power_get_property(struct power_supply *psy,
 		return 0;
 	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
 		if (IS_ENABLED(CONFIG_AXP20X_ADC)) {
-			ret = iio_read_channel_processed(power->vbus_v,
-							 &val->intval);
-			if (ret)
-				return ret;
-
 			/*
 			 * IIO framework gives mV but Power Supply framework
 			 * gives uV.
 			 */
-			val->intval *= 1000;
+			ret = iio_read_channel_processed_scale(power->vbus_v,
+							       &val->intval, 1000);
+			if (ret)
+				return ret;
+
 			return 0;
 		}
 
@@ -253,16 +252,15 @@ static int axp20x_usb_power_get_property(struct power_supply *psy,
 		return 0;
 	case POWER_SUPPLY_PROP_CURRENT_NOW:
 		if (IS_ENABLED(CONFIG_AXP20X_ADC)) {
-			ret = iio_read_channel_processed(power->vbus_i,
-							 &val->intval);
-			if (ret)
-				return ret;
-
 			/*
 			 * IIO framework gives mA but Power Supply framework
 			 * gives uA.
 			 */
-			val->intval *= 1000;
+			ret = iio_read_channel_processed_scale(power->vbus_i,
+							       &val->intval, 1000);
+			if (ret)
+				return ret;
+
 			return 0;
 		}
 
@@ -374,16 +372,15 @@ static int axp717_usb_power_get_property(struct power_supply *psy,
 		break;
 	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
 		if (IS_ENABLED(CONFIG_AXP20X_ADC)) {
-			ret = iio_read_channel_processed(power->vbus_v,
-							 &val->intval);
-			if (ret)
-				return ret;
-
 			/*
 			 * IIO framework gives mV but Power Supply framework
 			 * gives uV.
 			 */
-			val->intval *= 1000;
+			ret = iio_read_channel_processed_scale(power->vbus_v,
+							       &val->intval, 1000);
+			if (ret)
+				return ret;
+
 			return 0;
 		}
 

From 1d3db2d99fbaa5020543bd1dc4f365faeffae4ed Mon Sep 17 00:00:00 2001
From: Chris Morgan <macromorgan@hotmail.com>
Date: Wed, 23 Oct 2024 13:48:00 -0500
Subject: [PATCH 1070/1530] power: supply: axp20x_battery: Use scaled
 iio_read_channel

Change iio_read_channel_processed to iio_read_channel_processed_scale
where appropriate.

Signed-off-by: Chris Morgan <macromorgan@hotmail.com>
Link: https://lore.kernel.org/r/20241023184800.109376-3-macroalpha82@gmail.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/axp20x_battery.c | 33 ++++++++++++++-------------
 1 file changed, 17 insertions(+), 16 deletions(-)

diff --git a/drivers/power/supply/axp20x_battery.c b/drivers/power/supply/axp20x_battery.c
index f71cc90fea127..fa27195f074e7 100644
--- a/drivers/power/supply/axp20x_battery.c
+++ b/drivers/power/supply/axp20x_battery.c
@@ -354,17 +354,18 @@ static int axp20x_battery_get_prop(struct power_supply *psy,
 		if (ret)
 			return ret;
 
+		/* IIO framework gives mA but Power Supply framework gives uA */
 		if (reg & AXP20X_PWR_STATUS_BAT_CHARGING) {
-			ret = iio_read_channel_processed(axp20x_batt->batt_chrg_i, &val->intval);
+			ret = iio_read_channel_processed_scale(axp20x_batt->batt_chrg_i,
+							       &val->intval, 1000);
 		} else {
-			ret = iio_read_channel_processed(axp20x_batt->batt_dischrg_i, &val1);
+			ret = iio_read_channel_processed_scale(axp20x_batt->batt_dischrg_i,
+							       &val1, 1000);
 			val->intval = -val1;
 		}
 		if (ret)
 			return ret;
 
-		/* IIO framework gives mA but Power Supply framework gives uA */
-		val->intval *= 1000;
 		break;
 
 	case POWER_SUPPLY_PROP_CAPACITY:
@@ -406,13 +407,12 @@ static int axp20x_battery_get_prop(struct power_supply *psy,
 		break;
 
 	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
-		ret = iio_read_channel_processed(axp20x_batt->batt_v,
-						 &val->intval);
+		/* IIO framework gives mV but Power Supply framework gives uV */
+		ret = iio_read_channel_processed_scale(axp20x_batt->batt_v,
+						 &val->intval, 1000);
 		if (ret)
 			return ret;
 
-		/* IIO framework gives mV but Power Supply framework gives uV */
-		val->intval *= 1000;
 		break;
 
 	default:
@@ -519,13 +519,15 @@ static int axp717_battery_get_prop(struct power_supply *psy,
 		 * The offset of this value is currently unknown and is
 		 * not documented in the datasheet. Based on
 		 * observation it's assumed to be somewhere around
-		 * 450ma. I will leave the value raw for now.
+		 * 450ma. I will leave the value raw for now. Note that
+		 * IIO framework gives mA but Power Supply framework
+		 * gives uA.
 		 */
-		ret = iio_read_channel_processed(axp20x_batt->batt_chrg_i, &val->intval);
+		ret = iio_read_channel_processed_scale(axp20x_batt->batt_chrg_i,
+						       &val->intval, 1000);
 		if (ret)
 			return ret;
-		/* IIO framework gives mA but Power Supply framework gives uA */
-		val->intval *= 1000;
+
 		return 0;
 
 	case POWER_SUPPLY_PROP_CAPACITY:
@@ -564,13 +566,12 @@ static int axp717_battery_get_prop(struct power_supply *psy,
 		return 0;
 
 	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
-		ret = iio_read_channel_processed(axp20x_batt->batt_v,
-						 &val->intval);
+		/* IIO framework gives mV but Power Supply framework gives uV */
+		ret = iio_read_channel_processed_scale(axp20x_batt->batt_v,
+						       &val->intval, 1000);
 		if (ret)
 			return ret;
 
-		/* IIO framework gives mV but Power Supply framework gives uV */
-		val->intval *= 1000;
 		return 0;
 
 	case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT:

From 7263d7df054e8b7759727d8fde62eca648189cc5 Mon Sep 17 00:00:00 2001
From: Ba Jing <bajing@cmss.chinamobile.com>
Date: Fri, 25 Oct 2024 17:06:59 +0800
Subject: [PATCH 1071/1530] reset: keystone-reset: remove unused macros

After reviewing the code, it was found that these macros are never
referenced in the code. Just remove them.

Signed-off-by: Ba Jing <bajing@cmss.chinamobile.com>
Link: https://lore.kernel.org/r/20241025090659.33458-1-bajing@cmss.chinamobile.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/keystone-reset.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/power/reset/keystone-reset.c b/drivers/power/reset/keystone-reset.c
index dbc4ff61cd748..cfaa54ced0d0a 100644
--- a/drivers/power/reset/keystone-reset.c
+++ b/drivers/power/reset/keystone-reset.c
@@ -16,7 +16,6 @@
 #include <linux/mfd/syscon.h>
 #include <linux/of.h>
 
-#define RSTYPE_RG			0x0
 #define RSCTRL_RG			0x4
 #define RSCFG_RG			0x8
 #define RSISO_RG			0xc
@@ -28,7 +27,6 @@
 #define RSMUX_OMODE_MASK		0xe
 #define RSMUX_OMODE_RESET_ON		0xa
 #define RSMUX_OMODE_RESET_OFF		0x0
-#define RSMUX_LOCK_MASK			0x1
 #define RSMUX_LOCK_SET			0x1
 
 #define RSCFG_RSTYPE_SOFT		0x300f

From 2da0cb9f03bd9b726fa1b4accb210ef2ab439925 Mon Sep 17 00:00:00 2001
From: Stanislav Jakubek <stano.jakubek@gmail.com>
Date: Mon, 4 Nov 2024 14:03:58 +0100
Subject: [PATCH 1072/1530] dt-bindings: power: supply: sc27xx-fg: document
 deprecated bat-detect-gpio

While the bindings have always used the correct 'battery-detect-gpios'
property, the DTS and the Linux driver have been using the incorrect
'bat-detect-gpio' property. Document this property and mark it
as deprecated.

Signed-off-by: Stanislav Jakubek <stano.jakubek@gmail.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Chunyan Zhang <zhang.lyra@gmail.com>
Link: https://lore.kernel.org/r/f334c973dd4e6390a0cd51dbde358277a07604d7.1730720720.git.stano.jakubek@gmail.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 .../devicetree/bindings/power/supply/sc27xx-fg.yaml          | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/power/supply/sc27xx-fg.yaml b/Documentation/devicetree/bindings/power/supply/sc27xx-fg.yaml
index 9108a2841caf6..b10f155afe688 100644
--- a/Documentation/devicetree/bindings/power/supply/sc27xx-fg.yaml
+++ b/Documentation/devicetree/bindings/power/supply/sc27xx-fg.yaml
@@ -27,6 +27,11 @@ properties:
   battery-detect-gpios:
     maxItems: 1
 
+  bat-detect-gpio:
+    maxItems: 1
+    deprecated: true
+    description: use battery-detect-gpios instead
+
   interrupts:
     maxItems: 1
 

From f29cc6d9a3917f98f1fb109f0c8841dd095f3fb0 Mon Sep 17 00:00:00 2001
From: Stanislav Jakubek <stano.jakubek@gmail.com>
Date: Mon, 4 Nov 2024 14:04:27 +0100
Subject: [PATCH 1073/1530] power: supply: sc27xx: Fix battery detect GPIO
 probe

The DT bindings specify the property as 'battery-detect-gpios', add
handling for it. Keep fallback to the deprecated 'bat-detect-gpio' property
to keep compatibility with older DTS.

Signed-off-by: Stanislav Jakubek <stano.jakubek@gmail.com>
Link: https://lore.kernel.org/r/ca28b2f2037929c0011fc5c779c332c1d1ad5308.1730720720.git.stano.jakubek@gmail.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/sc27xx_fuel_gauge.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/power/supply/sc27xx_fuel_gauge.c b/drivers/power/supply/sc27xx_fuel_gauge.c
index 426d423b935b5..f36edc2ba7087 100644
--- a/drivers/power/supply/sc27xx_fuel_gauge.c
+++ b/drivers/power/supply/sc27xx_fuel_gauge.c
@@ -1183,10 +1183,14 @@ static int sc27xx_fgu_probe(struct platform_device *pdev)
 		return PTR_ERR(data->charge_chan);
 	}
 
-	data->gpiod = devm_gpiod_get(dev, "bat-detect", GPIOD_IN);
+	data->gpiod = devm_gpiod_get(dev, "battery-detect", GPIOD_IN);
 	if (IS_ERR(data->gpiod)) {
-		dev_err(dev, "failed to get battery detection GPIO\n");
-		return PTR_ERR(data->gpiod);
+		data->gpiod = devm_gpiod_get(dev, "bat-detect", GPIOD_IN);
+		if (IS_ERR(data->gpiod)) {
+			dev_err(dev, "failed to get battery detection GPIO\n");
+			return PTR_ERR(data->gpiod);
+		}
+		dev_warn(dev, "bat-detect is deprecated, please use battery-detect\n");
 	}
 
 	ret = gpiod_get_value_cansleep(data->gpiod);

From 05d9044177c3e910921522e0209640d3b825a6ae Mon Sep 17 00:00:00 2001
From: Elliot Berman <quic_eberman@quicinc.com>
Date: Thu, 7 Nov 2024 15:38:25 -0800
Subject: [PATCH 1074/1530] dt-bindings: power: reset: Convert mode-.*
 properties to array

PSCI reboot mode will map a mode name to multiple magic values instead
of just one. Convert the mode-.* property to an array. Users of the
reboot-mode schema will need to specify the maxItems of the mode-.*
properties. Existing users will all be 1.

Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Elliot Berman <quic_eberman@quicinc.com>
Link: https://lore.kernel.org/r/20241107-arm-psci-system_reset2-vendor-reboots-v8-1-e8715fa65cb5@quicinc.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 .../devicetree/bindings/power/reset/nvmem-reboot-mode.yaml | 4 ++++
 .../devicetree/bindings/power/reset/qcom,pon.yaml          | 7 +++++++
 .../devicetree/bindings/power/reset/reboot-mode.yaml       | 4 ++--
 .../bindings/power/reset/syscon-reboot-mode.yaml           | 4 ++++
 4 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml b/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml
index 627f8a6078c29..7f5f94673e9c2 100644
--- a/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml
+++ b/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml
@@ -31,6 +31,10 @@ properties:
 allOf:
   - $ref: reboot-mode.yaml#
 
+patternProperties:
+  "^mode-.*$":
+    maxItems: 1
+
 required:
   - compatible
   - nvmem-cells
diff --git a/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml b/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml
index fc8105a7b9b26..3da3d02a66908 100644
--- a/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml
+++ b/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml
@@ -54,6 +54,10 @@ required:
   - compatible
   - reg
 
+patternProperties:
+  "^mode-.*$":
+    maxItems: 1
+
 unevaluatedProperties: false
 
 allOf:
@@ -75,6 +79,9 @@ allOf:
         reg-names:
           items:
             - const: pon
+    else:
+      patternProperties:
+        "^mode-.*$": false
 
     # Special case for pm8941, which doesn't store reset mode
   - if:
diff --git a/Documentation/devicetree/bindings/power/reset/reboot-mode.yaml b/Documentation/devicetree/bindings/power/reset/reboot-mode.yaml
index ad0a0b95cec12..3ddac06cec727 100644
--- a/Documentation/devicetree/bindings/power/reset/reboot-mode.yaml
+++ b/Documentation/devicetree/bindings/power/reset/reboot-mode.yaml
@@ -28,13 +28,13 @@ description: |
 
 properties:
   mode-normal:
-    $ref: /schemas/types.yaml#/definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32-array
     description:
       Default value to set on a reboot if no command was provided.
 
 patternProperties:
   "^mode-.*$":
-    $ref: /schemas/types.yaml#/definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32-array
 
 additionalProperties: true
 
diff --git a/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml b/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml
index b6acff199cdec..79ffc78b23eaf 100644
--- a/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml
+++ b/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml
@@ -32,6 +32,10 @@ properties:
 allOf:
   - $ref: reboot-mode.yaml#
 
+patternProperties:
+  "^mode-.*$":
+    maxItems: 1
+
 unevaluatedProperties: false
 
 required:

From b6d445f6724deda3fd87fa33358009d947a64c5d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 11 Nov 2024 11:44:12 +0100
Subject: [PATCH 1075/1530] power: reset: ep93xx: add AUXILIARY_BUS dependency

This fails to link when compile-testing and the auxiliary bus is not built-in:

x86_64-linux-ld: drivers/power/reset/ep93xx-restart.o: in function `ep93xx_reboot_driver_init':
ep93xx-restart.c:(.init.text+0x11): undefined reference to `__auxiliary_driver_register'
x86_64-linux-ld: drivers/power/reset/ep93xx-restart.o: in function `ep93xx_reboot_driver_exit':
ep93xx-restart.c:(.exit.text+0x8): undefined reference to `auxiliary_driver_unregister'

Add the appropriate dependency.

Fixes: 9fa7cdb4368f ("power: reset: Add a driver for the ep93xx reset")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20241111104418.3891756-1-arnd@kernel.org
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig
index 389d5a193e5dc..f5fc33a8bf443 100644
--- a/drivers/power/reset/Kconfig
+++ b/drivers/power/reset/Kconfig
@@ -79,6 +79,7 @@ config POWER_RESET_EP93XX
 	bool "Cirrus EP93XX reset driver" if COMPILE_TEST
 	depends on MFD_SYSCON
 	default ARCH_EP93XX
+	select AUXILIARY_BUS
 	help
 	  This driver provides restart support for Cirrus EP93XX SoC.
 

From 03ecb24db20e78c478b9b7c0ec767bfdc053ecd4 Mon Sep 17 00:00:00 2001
From: Lance Yang <ioworker0@gmail.com>
Date: Sun, 27 Oct 2024 20:07:46 +0800
Subject: [PATCH 1076/1530] hung_task: add detect count for hung tasks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Patch series "add detect count for hung tasks", v2.

This patchset adds a counter, hung_task_detect_count, to track the number
of times hung tasks are detected.

IHMO, hung tasks are a critical metric.  Currently, we detect them by
periodically parsing dmesg.  However, this method isn't as user-friendly
as using a counter.

Sometimes, a short-lived issue with NIC or hard drive can quickly decrease
the hung_task_warnings to zero.  Without warnings, we must directly access
the node to ensure that there are no more hung tasks and that the system
has recovered.  After all, load average alone cannot provide a clear
picture.

Once this counter is in place, in a high-density deployment pattern, we
plan to set hung_task_timeout_secs to a lower number to improve stability,
even though this might result in false positives.  And then we can set a
time-based threshold: if hung tasks last beyond this duration, we will
automatically migrate containers to other nodes.  Based on past
experience, this approach could help avoid many production disruptions.

Moreover, just like other important events such as OOM that already have
counters, having a dedicated counter for hung tasks makes sense ;)


This patch (of 2):

This commit adds a counter, hung_task_detect_count, to track the number of
times hung tasks are detected.

IHMO, hung tasks are a critical metric. Currently, we detect them by
periodically parsing dmesg. However, this method isn't as user-friendly as
using a counter.

Sometimes, a short-lived issue with NIC or hard drive can quickly decrease
the hung_task_warnings to zero. Without warnings, we must directly access
the node to ensure that there are no more hung tasks and that the system
has recovered. After all, load average alone cannot provide a clear
picture.

Once this counter is in place, in a high-density deployment pattern, we
plan to set hung_task_timeout_secs to a lower number to improve stability,
even though this might result in false positives. And then we can set a
time-based threshold: if hung tasks last beyond this duration, we will
automatically migrate containers to other nodes. Based on past experience,
this approach could help avoid many production disruptions.

Moreover, just like other important events such as OOM that already have
counters, having a dedicated counter for hung tasks makes sense.

[ioworker0@gmail.com: proc_doulongvec_minmax instead of proc_dointvec]
  Link: https://lkml.kernel.org/r/20241101114833.8377-1-ioworker0@gmail.com
Link: https://lkml.kernel.org/r/20241027120747.42833-1-ioworker0@gmail.com
Link: https://lkml.kernel.org/r/20241027120747.42833-2-ioworker0@gmail.com
Signed-off-by: Mingzhe Yang <mingzhe.yang@ly.com>
Signed-off-by: Lance Yang <ioworker0@gmail.com>
Cc: Bang Li <libang.li@antgroup.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Huang Cun <cunhuang@tencent.com>
Cc: Joel Granados <j.granados@samsung.com>
Cc: Joel Granados <joel.granados@kernel.org>
Cc: John Siddle <jsiddle@redhat.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Thomas Weißschuh <linux@weissschuh.net>
Cc: Yongliang Gao <leonylgao@tencent.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/hung_task.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 959d99583d1c8..c18717189f322 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -30,6 +30,11 @@
  */
 static int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
 
+/*
+ * Total number of tasks detected as hung since boot:
+ */
+static unsigned long __read_mostly sysctl_hung_task_detect_count;
+
 /*
  * Limit number of tasks checked in a batch.
  *
@@ -115,6 +120,12 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 	if (time_is_after_jiffies(t->last_switch_time + timeout * HZ))
 		return;
 
+	/*
+	 * This counter tracks the total number of tasks detected as hung
+	 * since boot.
+	 */
+	sysctl_hung_task_detect_count++;
+
 	trace_sched_process_hang(t);
 
 	if (sysctl_hung_task_panic) {
@@ -314,6 +325,13 @@ static struct ctl_table hung_task_sysctls[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_NEG_ONE,
 	},
+	{
+		.procname	= "hung_task_detect_count",
+		.data		= &sysctl_hung_task_detect_count,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0444,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
 };
 
 static void __init hung_task_sysctl_init(void)

From 62bf7065cc6056a51a240c810b95d887e5bb7c8c Mon Sep 17 00:00:00 2001
From: Lance Yang <ioworker0@gmail.com>
Date: Sun, 27 Oct 2024 20:07:47 +0800
Subject: [PATCH 1077/1530] hung_task: add docs for hung_task_detect_count
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This commit introduces documentation for hung_task_detect_count in
kernel.rst.

Link: https://lkml.kernel.org/r/20241027120747.42833-3-ioworker0@gmail.com
Signed-off-by: Mingzhe Yang <mingzhe.yang@ly.com>
Signed-off-by: Lance Yang <ioworker0@gmail.com>
Cc: Bang Li <libang.li@antgroup.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Huang Cun <cunhuang@tencent.com>
Cc: Joel Granados <j.granados@samsung.com>
Cc: Joel Granados <joel.granados@kernel.org>
Cc: John Siddle <jsiddle@redhat.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Thomas Weißschuh <linux@weissschuh.net>
Cc: Yongliang Gao <leonylgao@tencent.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/sysctl/kernel.rst | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index f8bc1630eba05..b2b36d0c3094d 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -401,6 +401,15 @@ The upper bound on the number of tasks that are checked.
 This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
 
 
+hung_task_detect_count
+======================
+
+Indicates the total number of tasks that have been detected as hung since
+the system boot.
+
+This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
+
+
 hung_task_timeout_secs
 ======================
 

From adc77b19f62d7e80f98400b2fca9d700d2afdd6f Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Tue, 29 Oct 2024 12:17:36 +0300
Subject: [PATCH 1078/1530] ocfs2: fix uninitialized value in
 ocfs2_file_read_iter()

Syzbot has reported the following KMSAN splat:

BUG: KMSAN: uninit-value in ocfs2_file_read_iter+0x9a4/0xf80
 ocfs2_file_read_iter+0x9a4/0xf80
 __io_read+0x8d4/0x20f0
 io_read+0x3e/0xf0
 io_issue_sqe+0x42b/0x22c0
 io_wq_submit_work+0xaf9/0xdc0
 io_worker_handle_work+0xd13/0x2110
 io_wq_worker+0x447/0x1410
 ret_from_fork+0x6f/0x90
 ret_from_fork_asm+0x1a/0x30

Uninit was created at:
 __alloc_pages_noprof+0x9a7/0xe00
 alloc_pages_mpol_noprof+0x299/0x990
 alloc_pages_noprof+0x1bf/0x1e0
 allocate_slab+0x33a/0x1250
 ___slab_alloc+0x12ef/0x35e0
 kmem_cache_alloc_bulk_noprof+0x486/0x1330
 __io_alloc_req_refill+0x84/0x560
 io_submit_sqes+0x172f/0x2f30
 __se_sys_io_uring_enter+0x406/0x41c0
 __x64_sys_io_uring_enter+0x11f/0x1a0
 x64_sys_call+0x2b54/0x3ba0
 do_syscall_64+0xcd/0x1e0
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Since an instance of 'struct kiocb' may be passed from the block layer
with 'private' field uninitialized, introduce 'ocfs2_iocb_init_rw_locked()'
and use it from where 'ocfs2_dio_end_io()' might take care, i.e. in
'ocfs2_file_read_iter()' and 'ocfs2_file_write_iter()'.

Link: https://lkml.kernel.org/r/20241029091736.1501946-1-dmantipov@yandex.ru
Fixes: 7cdfc3a1c397 ("ocfs2: Remember rw lock level during direct io")
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Reported-by: syzbot+a73e253cca4f0230a5a5@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=a73e253cca4f0230a5a5
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <jiangqi903@gmail.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Jun Piao <piaojun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/ocfs2/aops.h | 2 ++
 fs/ocfs2/file.c | 4 ++++
 2 files changed, 6 insertions(+)

diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 45db1781ea735..1d1b4b7edba02 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -70,6 +70,8 @@ enum ocfs2_iocb_lock_bits {
 	OCFS2_IOCB_NUM_LOCKS
 };
 
+#define ocfs2_iocb_init_rw_locked(iocb) \
+	(iocb->private = NULL)
 #define ocfs2_iocb_clear_rw_locked(iocb) \
 	clear_bit(OCFS2_IOCB_RW_LOCK, (unsigned long *)&iocb->private)
 #define ocfs2_iocb_rw_locked_level(iocb) \
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 06af21982c16a..cb09330a08611 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2398,6 +2398,8 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	} else
 		inode_lock(inode);
 
+	ocfs2_iocb_init_rw_locked(iocb);
+
 	/*
 	 * Concurrent O_DIRECT writes are allowed with
 	 * mount_option "coherency=buffered".
@@ -2544,6 +2546,8 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	if (!direct_io && nowait)
 		return -EOPNOTSUPP;
 
+	ocfs2_iocb_init_rw_locked(iocb);
+
 	/*
 	 * buffered reads protect themselves in ->read_folio().  O_DIRECT reads
 	 * need locks to protect pending reads from racing with truncate.

From a7306f3c283bfe03611229bb6280987aae2af8f9 Mon Sep 17 00:00:00 2001
From: Nataniel Farzan <natanielfarzan@gmail.com>
Date: Mon, 4 Nov 2024 19:22:32 -0800
Subject: [PATCH 1079/1530] Improve consistency of '#error' directive messages

Remove the use of contractions and use proper punctuation in #error
directive messages that discourage the direct inclusion of header files.

Link: https://lkml.kernel.org/r/20241105032231.28833-1-natanielfarzan@gmail.com
Signed-off-by: Nataniel Farzan <natanielfarzan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/alpha/include/asm/spinlock_types.h          | 2 +-
 arch/arm/include/asm/spinlock_types.h            | 2 +-
 arch/arm64/include/asm/spinlock_types.h          | 2 +-
 arch/hexagon/include/asm/spinlock_types.h        | 2 +-
 arch/powerpc/include/asm/simple_spinlock_types.h | 2 +-
 arch/powerpc/include/asm/spinlock_types.h        | 2 +-
 arch/s390/include/asm/spinlock_types.h           | 2 +-
 arch/sh/include/asm/spinlock_types.h             | 2 +-
 arch/xtensa/include/asm/spinlock_types.h         | 2 +-
 include/acpi/platform/aclinux.h                  | 2 +-
 include/linux/compiler-clang.h                   | 2 +-
 include/linux/compiler-gcc.h                     | 2 +-
 include/linux/pm_wakeup.h                        | 2 +-
 include/linux/rwlock.h                           | 2 +-
 include/linux/rwlock_api_smp.h                   | 2 +-
 include/linux/spinlock_api_smp.h                 | 2 +-
 include/linux/spinlock_types_up.h                | 2 +-
 include/linux/spinlock_up.h                      | 2 +-
 tools/include/linux/compiler-gcc.h               | 2 +-
 19 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/arch/alpha/include/asm/spinlock_types.h b/arch/alpha/include/asm/spinlock_types.h
index 2526fd3be5fd7..05a444d77c531 100644
--- a/arch/alpha/include/asm/spinlock_types.h
+++ b/arch/alpha/include/asm/spinlock_types.h
@@ -3,7 +3,7 @@
 #define _ALPHA_SPINLOCK_TYPES_H
 
 #ifndef __LINUX_SPINLOCK_TYPES_RAW_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 typedef struct {
diff --git a/arch/arm/include/asm/spinlock_types.h b/arch/arm/include/asm/spinlock_types.h
index 0c14b36ef1013..5404a2a96bf3c 100644
--- a/arch/arm/include/asm/spinlock_types.h
+++ b/arch/arm/include/asm/spinlock_types.h
@@ -3,7 +3,7 @@
 #define __ASM_SPINLOCK_TYPES_H
 
 #ifndef __LINUX_SPINLOCK_TYPES_RAW_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 #define TICKET_SHIFT	16
diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h
index 11ab1c0776977..7cde3d8bd0add 100644
--- a/arch/arm64/include/asm/spinlock_types.h
+++ b/arch/arm64/include/asm/spinlock_types.h
@@ -6,7 +6,7 @@
 #define __ASM_SPINLOCK_TYPES_H
 
 #if !defined(__LINUX_SPINLOCK_TYPES_RAW_H) && !defined(__ASM_SPINLOCK_H)
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 #include <asm-generic/qspinlock_types.h>
diff --git a/arch/hexagon/include/asm/spinlock_types.h b/arch/hexagon/include/asm/spinlock_types.h
index d5f66495b670f..63add2d863e81 100644
--- a/arch/hexagon/include/asm/spinlock_types.h
+++ b/arch/hexagon/include/asm/spinlock_types.h
@@ -9,7 +9,7 @@
 #define _ASM_SPINLOCK_TYPES_H
 
 #ifndef __LINUX_SPINLOCK_TYPES_RAW_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 typedef struct {
diff --git a/arch/powerpc/include/asm/simple_spinlock_types.h b/arch/powerpc/include/asm/simple_spinlock_types.h
index 08243338069d2..391fc19f72723 100644
--- a/arch/powerpc/include/asm/simple_spinlock_types.h
+++ b/arch/powerpc/include/asm/simple_spinlock_types.h
@@ -3,7 +3,7 @@
 #define _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H
 
 #ifndef __LINUX_SPINLOCK_TYPES_RAW_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 typedef struct {
diff --git a/arch/powerpc/include/asm/spinlock_types.h b/arch/powerpc/include/asm/spinlock_types.h
index 40b01446cf755..569765fa16bc4 100644
--- a/arch/powerpc/include/asm/spinlock_types.h
+++ b/arch/powerpc/include/asm/spinlock_types.h
@@ -3,7 +3,7 @@
 #define _ASM_POWERPC_SPINLOCK_TYPES_H
 
 #ifndef __LINUX_SPINLOCK_TYPES_RAW_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 #ifdef CONFIG_PPC_QUEUED_SPINLOCKS
diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h
index b69695e399574..3653ff57d6d9a 100644
--- a/arch/s390/include/asm/spinlock_types.h
+++ b/arch/s390/include/asm/spinlock_types.h
@@ -3,7 +3,7 @@
 #define __ASM_SPINLOCK_TYPES_H
 
 #ifndef __LINUX_SPINLOCK_TYPES_RAW_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 typedef struct {
diff --git a/arch/sh/include/asm/spinlock_types.h b/arch/sh/include/asm/spinlock_types.h
index 907bda4b1619a..7cb50e68448f4 100644
--- a/arch/sh/include/asm/spinlock_types.h
+++ b/arch/sh/include/asm/spinlock_types.h
@@ -3,7 +3,7 @@
 #define __ASM_SH_SPINLOCK_TYPES_H
 
 #ifndef __LINUX_SPINLOCK_TYPES_RAW_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 typedef struct {
diff --git a/arch/xtensa/include/asm/spinlock_types.h b/arch/xtensa/include/asm/spinlock_types.h
index 797aed7df3dd8..6baaeac6248b8 100644
--- a/arch/xtensa/include/asm/spinlock_types.h
+++ b/arch/xtensa/include/asm/spinlock_types.h
@@ -3,7 +3,7 @@
 #define __ASM_SPINLOCK_TYPES_H
 
 #if !defined(__LINUX_SPINLOCK_TYPES_RAW_H) && !defined(__ASM_SPINLOCK_H)
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 #include <asm-generic/qspinlock_types.h>
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index 565341c826e38..f3249b7df5cbc 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -15,7 +15,7 @@
 /* ACPICA external files should not include ACPICA headers directly. */
 
 #if !defined(BUILDING_ACPICA) && !defined(_LINUX_ACPI_H)
-#error "Please don't include <acpi/acpi.h> directly, include <linux/acpi.h> instead."
+#error "Please do not include <acpi/acpi.h> directly, include <linux/acpi.h> instead."
 #endif
 
 #endif
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 4c1a39dcb624e..2e7c2c282f3af 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __LINUX_COMPILER_TYPES_H
-#error "Please don't include <linux/compiler-clang.h> directly, include <linux/compiler.h> instead."
+#error "Please do not include <linux/compiler-clang.h> directly, include <linux/compiler.h> instead."
 #endif
 
 /* Compiler specific definitions for Clang compiler */
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index cd6f9aae311fc..d0ed9583743fc 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __LINUX_COMPILER_TYPES_H
-#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
+#error "Please do not include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
 #endif
 
 /*
diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h
index 76cd1f9f13653..222f7530806c5 100644
--- a/include/linux/pm_wakeup.h
+++ b/include/linux/pm_wakeup.h
@@ -10,7 +10,7 @@
 #define _LINUX_PM_WAKEUP_H
 
 #ifndef _DEVICE_H_
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 #include <linux/types.h>
diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h
index c0ef596f340b5..5b87c6f4a243b 100644
--- a/include/linux/rwlock.h
+++ b/include/linux/rwlock.h
@@ -2,7 +2,7 @@
 #define __LINUX_RWLOCK_H
 
 #ifndef __LINUX_INSIDE_SPINLOCK_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 /*
diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h
index dceb0a59b6927..31d3d1116323e 100644
--- a/include/linux/rwlock_api_smp.h
+++ b/include/linux/rwlock_api_smp.h
@@ -2,7 +2,7 @@
 #define __LINUX_RWLOCK_API_SMP_H
 
 #ifndef __LINUX_SPINLOCK_API_SMP_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 /*
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index 89eb6f4c659c7..9ecb0ab504e32 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -2,7 +2,7 @@
 #define __LINUX_SPINLOCK_API_SMP_H
 
 #ifndef __LINUX_INSIDE_SPINLOCK_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 /*
diff --git a/include/linux/spinlock_types_up.h b/include/linux/spinlock_types_up.h
index 7f86a2016ac5c..fc4e2d017c201 100644
--- a/include/linux/spinlock_types_up.h
+++ b/include/linux/spinlock_types_up.h
@@ -2,7 +2,7 @@
 #define __LINUX_SPINLOCK_TYPES_UP_H
 
 #ifndef __LINUX_SPINLOCK_TYPES_RAW_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 /*
diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h
index c87204247592f..1e84e71ca495e 100644
--- a/include/linux/spinlock_up.h
+++ b/include/linux/spinlock_up.h
@@ -2,7 +2,7 @@
 #define __LINUX_SPINLOCK_UP_H
 
 #ifndef __LINUX_INSIDE_SPINLOCK_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 #include <asm/processor.h>	/* for cpu_relax() */
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index 62e7c901ac28c..e20f98e14e814 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_COMPILER_H_
-#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
+#error "Please do not include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
 #endif
 
 /*

From bc73b4186736341ab5cd2c199da82db6e1134e13 Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <aardelean@baylibre.com>
Date: Tue, 5 Nov 2024 16:54:05 +0200
Subject: [PATCH 1080/1530] util_macros.h: fix/rework find_closest() macros

A bug was found in the find_closest() (find_closest_descending() is also
affected after some testing), where for certain values with small
progressions, the rounding (done by averaging 2 values) causes an
incorrect index to be returned.  The rounding issues occur for
progressions of 1, 2 and 3.  It goes away when the progression/interval
between two values is 4 or larger.

It's particularly bad for progressions of 1.  For example if there's an
array of 'a = { 1, 2, 3 }', using 'find_closest(2, a ...)' would return 0
(the index of '1'), rather than returning 1 (the index of '2').  This
means that for exact values (with a progression of 1), find_closest() will
misbehave and return the index of the value smaller than the one we're
searching for.

For progressions of 2 and 3, the exact values are obtained correctly; but
values aren't approximated correctly (as one would expect).  Starting with
progressions of 4, all seems to be good (one gets what one would expect).

While one could argue that 'find_closest()' should not be used for arrays
with progressions of 1 (i.e. '{1, 2, 3, ...}', the macro should still
behave correctly.

The bug was found while testing the 'drivers/iio/adc/ad7606.c',
specifically the oversampling feature.
For reference, the oversampling values are listed as:
   static const unsigned int ad7606_oversampling_avail[7] = {
          1, 2, 4, 8, 16, 32, 64,
   };

When doing:
  1. $ echo 1 > /sys/bus/iio/devices/iio\:device0/oversampling_ratio
     $ cat /sys/bus/iio/devices/iio\:device0/oversampling_ratio
     1  # this is fine
  2. $ echo 2 > /sys/bus/iio/devices/iio\:device0/oversampling_ratio
     $ cat /sys/bus/iio/devices/iio\:device0/oversampling_ratio
     1  # this is wrong; 2 should be returned here
  3. $ echo 3 > /sys/bus/iio/devices/iio\:device0/oversampling_ratio
     $ cat /sys/bus/iio/devices/iio\:device0/oversampling_ratio
     2  # this is fine
  4. $ echo 4 > /sys/bus/iio/devices/iio\:device0/oversampling_ratio
     $ cat /sys/bus/iio/devices/iio\:device0/oversampling_ratio
     4  # this is fine
And from here-on, the values are as correct (one gets what one would
expect.)

While writing a kunit test for this bug, a peculiar issue was found for the
array in the 'drivers/hwmon/ina2xx.c' & 'drivers/iio/adc/ina2xx-adc.c'
drivers. While running the kunit test (for 'ina226_avg_tab' from these
drivers):
  * idx = find_closest([-1 to 2], ina226_avg_tab, ARRAY_SIZE(ina226_avg_tab));
    This returns idx == 0, so value.
  * idx = find_closest(3, ina226_avg_tab, ARRAY_SIZE(ina226_avg_tab));
    This returns idx == 0, value 1; and now one could argue whether 3 is
    closer to 4 or to 1. This quirk only appears for value '3' in this
    array, but it seems to be a another rounding issue.
  * And from 4 onwards the 'find_closest'() works fine (one gets what one
    would expect).

This change reworks the find_closest() macros to also check the difference
between the left and right elements when 'x'. If the distance to the right
is smaller (than the distance to the left), the index is incremented by 1.
This also makes redundant the need for using the DIV_ROUND_CLOSEST() macro.

In order to accommodate for any mix of negative + positive values, the
internal variables '__fc_x', '__fc_mid_x', '__fc_left' & '__fc_right' are
forced to 'long' type. This also addresses any potential bugs/issues with
'x' being of an unsigned type. In those situations any comparison between
signed & unsigned would be promoted to a comparison between 2 unsigned
numbers; this is especially annoying when '__fc_left' & '__fc_right'
underflow.

The find_closest_descending() macro was also reworked and duplicated from
the find_closest(), and it is being iterated in reverse. The main reason
for this is to get the same indices as 'find_closest()' (but in reverse).
The comparison for '__fc_right < __fc_left' favors going the array in
ascending order.
For example for array '{ 1024, 512, 256, 128, 64, 16, 4, 1 }' and x = 3, we
get:
    __fc_mid_x = 2
    __fc_left = -1
    __fc_right = -2
    Then '__fc_right < __fc_left' evaluates to true and '__fc_i++' becomes 7
    which is not quite incorrect, but 3 is closer to 4 than to 1.

This change has been validated with the kunit from the next patch.

Link: https://lkml.kernel.org/r/20241105145406.554365-1-aardelean@baylibre.com
Fixes: 95d119528b0b ("util_macros.h: add find_closest() macro")
Signed-off-by: Alexandru Ardelean <aardelean@baylibre.com>
Cc: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/util_macros.h | 56 ++++++++++++++++++++++++++-----------
 1 file changed, 40 insertions(+), 16 deletions(-)

diff --git a/include/linux/util_macros.h b/include/linux/util_macros.h
index 6bb460c3e818b..825487fb66faf 100644
--- a/include/linux/util_macros.h
+++ b/include/linux/util_macros.h
@@ -4,19 +4,6 @@
 
 #include <linux/math.h>
 
-#define __find_closest(x, a, as, op)					\
-({									\
-	typeof(as) __fc_i, __fc_as = (as) - 1;				\
-	typeof(x) __fc_x = (x);						\
-	typeof(*a) const *__fc_a = (a);					\
-	for (__fc_i = 0; __fc_i < __fc_as; __fc_i++) {			\
-		if (__fc_x op DIV_ROUND_CLOSEST(__fc_a[__fc_i] +	\
-						__fc_a[__fc_i + 1], 2))	\
-			break;						\
-	}								\
-	(__fc_i);							\
-})
-
 /**
  * find_closest - locate the closest element in a sorted array
  * @x: The reference value.
@@ -25,8 +12,27 @@
  * @as: Size of 'a'.
  *
  * Returns the index of the element closest to 'x'.
+ * Note: If using an array of negative numbers (or mixed positive numbers),
+ *       then be sure that 'x' is of a signed-type to get good results.
  */
-#define find_closest(x, a, as) __find_closest(x, a, as, <=)
+#define find_closest(x, a, as)						\
+({									\
+	typeof(as) __fc_i, __fc_as = (as) - 1;				\
+	long __fc_mid_x, __fc_x = (x);					\
+	long __fc_left, __fc_right;					\
+	typeof(*a) const *__fc_a = (a);					\
+	for (__fc_i = 0; __fc_i < __fc_as; __fc_i++) {			\
+		__fc_mid_x = (__fc_a[__fc_i] + __fc_a[__fc_i + 1]) / 2;	\
+		if (__fc_x <= __fc_mid_x) {				\
+			__fc_left = __fc_x - __fc_a[__fc_i];		\
+			__fc_right = __fc_a[__fc_i + 1] - __fc_x;	\
+			if (__fc_right < __fc_left)			\
+				__fc_i++;				\
+			break;						\
+		}							\
+	}								\
+	(__fc_i);							\
+})
 
 /**
  * find_closest_descending - locate the closest element in a sorted array
@@ -36,9 +42,27 @@
  * @as: Size of 'a'.
  *
  * Similar to find_closest() but 'a' is expected to be sorted in descending
- * order.
+ * order. The iteration is done in reverse order, so that the comparison
+ * of '__fc_right' & '__fc_left' also works for unsigned numbers.
  */
-#define find_closest_descending(x, a, as) __find_closest(x, a, as, >=)
+#define find_closest_descending(x, a, as)				\
+({									\
+	typeof(as) __fc_i, __fc_as = (as) - 1;				\
+	long __fc_mid_x, __fc_x = (x);					\
+	long __fc_left, __fc_right;					\
+	typeof(*a) const *__fc_a = (a);					\
+	for (__fc_i = __fc_as; __fc_i >= 1; __fc_i--) {			\
+		__fc_mid_x = (__fc_a[__fc_i] + __fc_a[__fc_i - 1]) / 2;	\
+		if (__fc_x <= __fc_mid_x) {				\
+			__fc_left = __fc_x - __fc_a[__fc_i];		\
+			__fc_right = __fc_a[__fc_i - 1] - __fc_x;	\
+			if (__fc_right < __fc_left)			\
+				__fc_i--;				\
+			break;						\
+		}							\
+	}								\
+	(__fc_i);							\
+})
 
 /**
  * is_insidevar - check if the @ptr points inside the @var memory range.

From 111314157f7891da7a51a8f95df42eeb22f4268a Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <aardelean@baylibre.com>
Date: Tue, 5 Nov 2024 16:54:06 +0200
Subject: [PATCH 1081/1530] lib: util_macros_kunit: add kunit test for
 util_macros.h

A bug was found in the find_closest() (find_closest_descending() is also
affected after some testing), where for certain values with small
progressions of 1, 2 & 3, the rounding (done by averaging 2 values) causes
an incorrect index to be returned.

The bug is described in more detail in the commit which fixes the bug.
This commit adds a kunit test to validate that the fix works correctly.

This kunit test adds some of the arrays (from the driver-sphere) that seem
to produce issues with the 'find_closest()' macro.  Specifically the one
from ad7606 driver (with which the bug was found) and from the ina2xx
drivers, which shows the quirk with 'find_closest()' with elements in a
array that have an interval of 3.

For the find_closest_descending() tests, the same arrays are used as for
the find_closest(), but in reverse; the idea is that
'find_closest_descending()' should return the sames indices as
'find_closest()' but in reverse.

For testing both macros, there are 4 special arrays created, one for
testing find_closest{_descending}() for arrays of progressions 1, 2, 3 and
4.  The idea is to show that (for progressions of 1, 2 & 3) the fix works
as expected.  When removing the fix, the issues should start to show up.

Then an extra array of negative and positive values is added.  There are
currently no such arrays within drivers, but one could expect that these
macros behave correctly even for such arrays.

To run this kunit:
  ./tools/testing/kunit/kunit.py run "*util_macros*"

Link: https://lkml.kernel.org/r/20241105145406.554365-2-aardelean@baylibre.com
Signed-off-by: Alexandru Ardelean <aardelean@baylibre.com>
Cc: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/Kconfig.debug       |  17 +++
 lib/Makefile            |   1 +
 lib/util_macros_kunit.c | 240 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 258 insertions(+)
 create mode 100644 lib/util_macros_kunit.c

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 2549b64b22805..d7dd38f14333c 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2630,6 +2630,23 @@ config CHECKSUM_KUNIT
 
 	  If unsure, say N.
 
+config UTIL_MACROS_KUNIT
+	tristate "KUnit test util_macros.h functions at runtime" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  Enable this option to test the util_macros.h function at boot.
+
+	  KUnit tests run during boot and output the results to the debug log
+	  in TAP format (http://testanything.org/). Only useful for kernel devs
+	  running the KUnit test harness, and not intended for inclusion into a
+	  production build.
+
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
 config HASH_KUNIT_TEST
 	tristate "KUnit Test for integer hash functions" if !KUNIT_ALL_TESTS
 	depends on KUNIT
diff --git a/lib/Makefile b/lib/Makefile
index 1eb89962daef7..cc26f81722a5c 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -372,6 +372,7 @@ obj-$(CONFIG_PLDMFW) += pldmfw/
 CFLAGS_bitfield_kunit.o := $(DISABLE_STRUCTLEAK_PLUGIN)
 obj-$(CONFIG_BITFIELD_KUNIT) += bitfield_kunit.o
 obj-$(CONFIG_CHECKSUM_KUNIT) += checksum_kunit.o
+obj-$(CONFIG_UTIL_MACROS_KUNIT) += util_macros_kunit.o
 obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o
 obj-$(CONFIG_HASHTABLE_KUNIT_TEST) += hashtable_test.o
 obj-$(CONFIG_LINEAR_RANGES_TEST) += test_linear_ranges.o
diff --git a/lib/util_macros_kunit.c b/lib/util_macros_kunit.c
new file mode 100644
index 0000000000000..94cc9f0de50ab
--- /dev/null
+++ b/lib/util_macros_kunit.c
@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Test cases for bitfield helpers.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <kunit/test.h>
+#include <linux/util_macros.h>
+
+#define FIND_CLOSEST_RANGE_CHECK(from, to, array, exp_idx)		\
+{									\
+	int i;								\
+	for (i = from; i <= to; i++) {					\
+		int found = find_closest(i, array, ARRAY_SIZE(array));	\
+		KUNIT_ASSERT_EQ(ctx, exp_idx, found);			\
+	}								\
+}
+
+static void test_find_closest(struct kunit *ctx)
+{
+	/* This will test a few arrays that are found in drivers */
+	static const int ina226_avg_tab[] = { 1, 4, 16, 64, 128, 256, 512, 1024 };
+	static const unsigned int ad7616_oversampling_avail[] = {
+		1, 2, 4, 8, 16, 32, 64, 128,
+	};
+	static u32 wd_timeout_table[] = { 2, 4, 6, 8, 16, 32, 48, 64 };
+	static int array_prog1a[] = { 1, 2, 3, 4, 5 };
+	static u32 array_prog1b[] = { 2, 3, 4, 5, 6 };
+	static int array_prog1mix[] = { -2, -1, 0, 1, 2 };
+	static int array_prog2a[] = { 1, 3, 5, 7 };
+	static u32 array_prog2b[] = { 2, 4, 6, 8 };
+	static int array_prog3a[] = { 1, 4, 7, 10 };
+	static u32 array_prog3b[] = { 2, 5, 8, 11 };
+	static int array_prog4a[] = { 1, 5, 9, 13 };
+	static u32 array_prog4b[] = { 2, 6, 10, 14 };
+
+	FIND_CLOSEST_RANGE_CHECK(-3, 2, ina226_avg_tab, 0);
+	FIND_CLOSEST_RANGE_CHECK(3, 10, ina226_avg_tab, 1);
+	FIND_CLOSEST_RANGE_CHECK(11, 40, ina226_avg_tab, 2);
+	FIND_CLOSEST_RANGE_CHECK(41, 96, ina226_avg_tab, 3);
+	FIND_CLOSEST_RANGE_CHECK(97, 192, ina226_avg_tab, 4);
+	FIND_CLOSEST_RANGE_CHECK(193, 384, ina226_avg_tab, 5);
+	FIND_CLOSEST_RANGE_CHECK(385, 768, ina226_avg_tab, 6);
+	FIND_CLOSEST_RANGE_CHECK(769, 2048, ina226_avg_tab, 7);
+
+	/* The array that found the bug that caused this kunit to exist */
+	FIND_CLOSEST_RANGE_CHECK(-3, 1, ad7616_oversampling_avail, 0);
+	FIND_CLOSEST_RANGE_CHECK(2, 3, ad7616_oversampling_avail, 1);
+	FIND_CLOSEST_RANGE_CHECK(4, 6, ad7616_oversampling_avail, 2);
+	FIND_CLOSEST_RANGE_CHECK(7, 12, ad7616_oversampling_avail, 3);
+	FIND_CLOSEST_RANGE_CHECK(13, 24, ad7616_oversampling_avail, 4);
+	FIND_CLOSEST_RANGE_CHECK(25, 48, ad7616_oversampling_avail, 5);
+	FIND_CLOSEST_RANGE_CHECK(49, 96, ad7616_oversampling_avail, 6);
+	FIND_CLOSEST_RANGE_CHECK(97, 256, ad7616_oversampling_avail, 7);
+
+	FIND_CLOSEST_RANGE_CHECK(-3, 3, wd_timeout_table, 0);
+	FIND_CLOSEST_RANGE_CHECK(4, 5, wd_timeout_table, 1);
+	FIND_CLOSEST_RANGE_CHECK(6, 7, wd_timeout_table, 2);
+	FIND_CLOSEST_RANGE_CHECK(8, 12, wd_timeout_table, 3);
+	FIND_CLOSEST_RANGE_CHECK(13, 24, wd_timeout_table, 4);
+	FIND_CLOSEST_RANGE_CHECK(25, 40, wd_timeout_table, 5);
+	FIND_CLOSEST_RANGE_CHECK(41, 56, wd_timeout_table, 6);
+	FIND_CLOSEST_RANGE_CHECK(57, 128, wd_timeout_table, 7);
+
+	/* One could argue that find_closest() should not be used for monotonic
+	 * arrays (like 1,2,3,4,5), but even so, it should work as long as the
+	 * array is sorted ascending. */
+	FIND_CLOSEST_RANGE_CHECK(-3, 1, array_prog1a, 0);
+	FIND_CLOSEST_RANGE_CHECK(2, 2, array_prog1a, 1);
+	FIND_CLOSEST_RANGE_CHECK(3, 3, array_prog1a, 2);
+	FIND_CLOSEST_RANGE_CHECK(4, 4, array_prog1a, 3);
+	FIND_CLOSEST_RANGE_CHECK(5, 8, array_prog1a, 4);
+
+	FIND_CLOSEST_RANGE_CHECK(-3, 2, array_prog1b, 0);
+	FIND_CLOSEST_RANGE_CHECK(3, 3, array_prog1b, 1);
+	FIND_CLOSEST_RANGE_CHECK(4, 4, array_prog1b, 2);
+	FIND_CLOSEST_RANGE_CHECK(5, 5, array_prog1b, 3);
+	FIND_CLOSEST_RANGE_CHECK(6, 8, array_prog1b, 4);
+
+	FIND_CLOSEST_RANGE_CHECK(-4, -2, array_prog1mix, 0);
+	FIND_CLOSEST_RANGE_CHECK(-1, -1, array_prog1mix, 1);
+	FIND_CLOSEST_RANGE_CHECK(0, 0, array_prog1mix, 2);
+	FIND_CLOSEST_RANGE_CHECK(1, 1, array_prog1mix, 3);
+	FIND_CLOSEST_RANGE_CHECK(2, 5, array_prog1mix, 4);
+
+	FIND_CLOSEST_RANGE_CHECK(-3, 2, array_prog2a, 0);
+	FIND_CLOSEST_RANGE_CHECK(3, 4, array_prog2a, 1);
+	FIND_CLOSEST_RANGE_CHECK(5, 6, array_prog2a, 2);
+	FIND_CLOSEST_RANGE_CHECK(7, 10, array_prog2a, 3);
+
+	FIND_CLOSEST_RANGE_CHECK(-3, 3, array_prog2b, 0);
+	FIND_CLOSEST_RANGE_CHECK(4, 5, array_prog2b, 1);
+	FIND_CLOSEST_RANGE_CHECK(6, 7, array_prog2b, 2);
+	FIND_CLOSEST_RANGE_CHECK(8, 10, array_prog2b, 3);
+
+	FIND_CLOSEST_RANGE_CHECK(-3, 2, array_prog3a, 0);
+	FIND_CLOSEST_RANGE_CHECK(3, 5, array_prog3a, 1);
+	FIND_CLOSEST_RANGE_CHECK(6, 8, array_prog3a, 2);
+	FIND_CLOSEST_RANGE_CHECK(9, 20, array_prog3a, 3);
+
+	FIND_CLOSEST_RANGE_CHECK(-3, 3, array_prog3b, 0);
+	FIND_CLOSEST_RANGE_CHECK(4, 6, array_prog3b, 1);
+	FIND_CLOSEST_RANGE_CHECK(7, 9, array_prog3b, 2);
+	FIND_CLOSEST_RANGE_CHECK(10, 20, array_prog3b, 3);
+
+	FIND_CLOSEST_RANGE_CHECK(-3, 3, array_prog4a, 0);
+	FIND_CLOSEST_RANGE_CHECK(4, 7, array_prog4a, 1);
+	FIND_CLOSEST_RANGE_CHECK(8, 11, array_prog4a, 2);
+	FIND_CLOSEST_RANGE_CHECK(12, 20, array_prog4a, 3);
+
+	FIND_CLOSEST_RANGE_CHECK(-3, 4, array_prog4b, 0);
+	FIND_CLOSEST_RANGE_CHECK(5, 8, array_prog4b, 1);
+	FIND_CLOSEST_RANGE_CHECK(9, 12, array_prog4b, 2);
+	FIND_CLOSEST_RANGE_CHECK(13, 20, array_prog4b, 3);
+}
+
+#define FIND_CLOSEST_DESC_RANGE_CHECK(from, to, array, exp_idx)	\
+{									\
+	int i;								\
+	for (i = from; i <= to; i++) {					\
+		int found = find_closest_descending(i, array,		\
+						ARRAY_SIZE(array));	\
+		KUNIT_ASSERT_EQ(ctx, exp_idx, found);			\
+	}								\
+}
+
+static void test_find_closest_descending(struct kunit *ctx)
+{
+	/* Same arrays as 'test_find_closest' but reversed */
+	static const int ina226_avg_tab[] = { 1024, 512, 256, 128, 64, 16, 4, 1 };
+	static const unsigned int ad7616_oversampling_avail[] = {
+		128, 64, 32, 16, 8, 4, 2, 1
+	};
+	static u32 wd_timeout_table[] = { 64, 48, 32, 16, 8, 6, 4, 2 };
+	static int array_prog1a[] = { 5, 4, 3, 2, 1 };
+	static u32 array_prog1b[] = { 6, 5, 4, 3, 2 };
+	static int array_prog1mix[] = { 2, 1, 0, -1, -2 };
+	static int array_prog2a[] = { 7, 5, 3, 1 };
+	static u32 array_prog2b[] = { 8, 6, 4, 2 };
+	static int array_prog3a[] = { 10, 7, 4, 1 };
+	static u32 array_prog3b[] = { 11, 8, 5, 2 };
+	static int array_prog4a[] = { 13, 9, 5, 1 };
+	static u32 array_prog4b[] = { 14, 10, 6, 2 };
+
+	FIND_CLOSEST_DESC_RANGE_CHECK(-3, 2, ina226_avg_tab, 7);
+	FIND_CLOSEST_DESC_RANGE_CHECK(3, 10, ina226_avg_tab, 6);
+	FIND_CLOSEST_DESC_RANGE_CHECK(11, 40, ina226_avg_tab, 5);
+	FIND_CLOSEST_DESC_RANGE_CHECK(41, 96, ina226_avg_tab, 4);
+	FIND_CLOSEST_DESC_RANGE_CHECK(97, 192, ina226_avg_tab, 3);
+	FIND_CLOSEST_DESC_RANGE_CHECK(193, 384, ina226_avg_tab, 2);
+	FIND_CLOSEST_DESC_RANGE_CHECK(385, 768, ina226_avg_tab, 1);
+	FIND_CLOSEST_DESC_RANGE_CHECK(769, 2048, ina226_avg_tab, 0);
+
+	FIND_CLOSEST_DESC_RANGE_CHECK(-3, 1, ad7616_oversampling_avail, 7);
+	FIND_CLOSEST_DESC_RANGE_CHECK(2, 3, ad7616_oversampling_avail, 6);
+	FIND_CLOSEST_DESC_RANGE_CHECK(4, 6, ad7616_oversampling_avail, 5);
+	FIND_CLOSEST_DESC_RANGE_CHECK(7, 12, ad7616_oversampling_avail, 4);
+	FIND_CLOSEST_DESC_RANGE_CHECK(13, 24, ad7616_oversampling_avail, 3);
+	FIND_CLOSEST_DESC_RANGE_CHECK(25, 48, ad7616_oversampling_avail, 2);
+	FIND_CLOSEST_DESC_RANGE_CHECK(49, 96, ad7616_oversampling_avail, 1);
+	FIND_CLOSEST_DESC_RANGE_CHECK(97, 256, ad7616_oversampling_avail, 0);
+
+	FIND_CLOSEST_DESC_RANGE_CHECK(-3, 3, wd_timeout_table, 7);
+	FIND_CLOSEST_DESC_RANGE_CHECK(4, 5, wd_timeout_table, 6);
+	FIND_CLOSEST_DESC_RANGE_CHECK(6, 7, wd_timeout_table, 5);
+	FIND_CLOSEST_DESC_RANGE_CHECK(8, 12, wd_timeout_table, 4);
+	FIND_CLOSEST_DESC_RANGE_CHECK(13, 24, wd_timeout_table, 3);
+	FIND_CLOSEST_DESC_RANGE_CHECK(25, 40, wd_timeout_table, 2);
+	FIND_CLOSEST_DESC_RANGE_CHECK(41, 56, wd_timeout_table, 1);
+	FIND_CLOSEST_DESC_RANGE_CHECK(57, 128, wd_timeout_table, 0);
+
+	/* One could argue that find_closest_descending() should not be used
+	 * for monotonic arrays (like 5,4,3,2,1), but even so, it should still
+	 * it should work as long as the array is sorted descending. */
+	FIND_CLOSEST_DESC_RANGE_CHECK(-3, 1, array_prog1a, 4);
+	FIND_CLOSEST_DESC_RANGE_CHECK(2, 2, array_prog1a, 3);
+	FIND_CLOSEST_DESC_RANGE_CHECK(3, 3, array_prog1a, 2);
+	FIND_CLOSEST_DESC_RANGE_CHECK(4, 4, array_prog1a, 1);
+	FIND_CLOSEST_DESC_RANGE_CHECK(5, 8, array_prog1a, 0);
+
+	FIND_CLOSEST_DESC_RANGE_CHECK(-3, 2, array_prog1b, 4);
+	FIND_CLOSEST_DESC_RANGE_CHECK(3, 3, array_prog1b, 3);
+	FIND_CLOSEST_DESC_RANGE_CHECK(4, 4, array_prog1b, 2);
+	FIND_CLOSEST_DESC_RANGE_CHECK(5, 5, array_prog1b, 1);
+	FIND_CLOSEST_DESC_RANGE_CHECK(6, 8, array_prog1b, 0);
+
+	FIND_CLOSEST_DESC_RANGE_CHECK(-4, -2, array_prog1mix, 4);
+	FIND_CLOSEST_DESC_RANGE_CHECK(-1, -1, array_prog1mix, 3);
+	FIND_CLOSEST_DESC_RANGE_CHECK(0, 0, array_prog1mix, 2);
+	FIND_CLOSEST_DESC_RANGE_CHECK(1, 1, array_prog1mix, 1);
+	FIND_CLOSEST_DESC_RANGE_CHECK(2, 5, array_prog1mix, 0);
+
+	FIND_CLOSEST_DESC_RANGE_CHECK(-3, 2, array_prog2a, 3);
+	FIND_CLOSEST_DESC_RANGE_CHECK(3, 4, array_prog2a, 2);
+	FIND_CLOSEST_DESC_RANGE_CHECK(5, 6, array_prog2a, 1);
+	FIND_CLOSEST_DESC_RANGE_CHECK(7, 10, array_prog2a, 0);
+
+	FIND_CLOSEST_DESC_RANGE_CHECK(-3, 3, array_prog2b, 3);
+	FIND_CLOSEST_DESC_RANGE_CHECK(4, 5, array_prog2b, 2);
+	FIND_CLOSEST_DESC_RANGE_CHECK(6, 7, array_prog2b, 1);
+	FIND_CLOSEST_DESC_RANGE_CHECK(8, 10, array_prog2b, 0);
+
+	FIND_CLOSEST_DESC_RANGE_CHECK(-3, 2, array_prog3a, 3);
+	FIND_CLOSEST_DESC_RANGE_CHECK(3, 5, array_prog3a, 2);
+	FIND_CLOSEST_DESC_RANGE_CHECK(6, 8, array_prog3a, 1);
+	FIND_CLOSEST_DESC_RANGE_CHECK(9, 20, array_prog3a, 0);
+
+	FIND_CLOSEST_DESC_RANGE_CHECK(-3, 3, array_prog3b, 3);
+	FIND_CLOSEST_DESC_RANGE_CHECK(4, 6, array_prog3b, 2);
+	FIND_CLOSEST_DESC_RANGE_CHECK(7, 9, array_prog3b, 1);
+	FIND_CLOSEST_DESC_RANGE_CHECK(10, 20, array_prog3b, 0);
+
+	FIND_CLOSEST_DESC_RANGE_CHECK(-3, 3, array_prog4a, 3);
+	FIND_CLOSEST_DESC_RANGE_CHECK(4, 7, array_prog4a, 2);
+	FIND_CLOSEST_DESC_RANGE_CHECK(8, 11, array_prog4a, 1);
+	FIND_CLOSEST_DESC_RANGE_CHECK(12, 20, array_prog4a, 0);
+
+	FIND_CLOSEST_DESC_RANGE_CHECK(-3, 4, array_prog4b, 3);
+	FIND_CLOSEST_DESC_RANGE_CHECK(5, 8, array_prog4b, 2);
+	FIND_CLOSEST_DESC_RANGE_CHECK(9, 12, array_prog4b, 1);
+	FIND_CLOSEST_DESC_RANGE_CHECK(13, 20, array_prog4b, 0);
+}
+
+static struct kunit_case __refdata util_macros_test_cases[] = {
+	KUNIT_CASE(test_find_closest),
+	KUNIT_CASE(test_find_closest_descending),
+	{}
+};
+
+static struct kunit_suite util_macros_test_suite = {
+	.name = "util_macros.h",
+	.test_cases = util_macros_test_cases,
+};
+
+kunit_test_suites(&util_macros_test_suite);
+
+MODULE_AUTHOR("Alexandru Ardelean <aardelean@baylibre.com>");
+MODULE_DESCRIPTION("Test cases for util_macros.h helpers");
+MODULE_LICENSE("GPL");

From 45dac1959bbdc498a2abb89919221455225789dc Mon Sep 17 00:00:00 2001
From: zhangguopeng <zhangguopeng@kylinos.cn>
Date: Tue, 5 Nov 2024 17:49:41 +0800
Subject: [PATCH 1082/1530] kernel/reboot: replace sprintf() with sysfs_emit()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As Documentation/filesystems/sysfs.rst suggested, show() should only use
sysfs_emit() or sysfs_emit_at() when formatting the value to be returned
to user space.

No functional change intended.

Link: https://lkml.kernel.org/r/20241105094941.33739-1-zhangguopeng@kylinos.cn
Signed-off-by: zhangguopeng <zhangguopeng@kylinos.cn>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Fabio Estevam <festevam@denx.de>
Cc: Joel Granados <joel.granados@kernel.org>
Cc: Thomas Weißschuh <linux@weissschuh.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/reboot.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/reboot.c b/kernel/reboot.c
index ffdf86b717abc..a701000bab347 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -1137,7 +1137,7 @@ static ssize_t mode_show(struct kobject *kobj, struct kobj_attribute *attr, char
 		val = REBOOT_UNDEFINED_STR;
 	}
 
-	return sprintf(buf, "%s\n", val);
+	return sysfs_emit(buf, "%s\n", val);
 }
 static ssize_t mode_store(struct kobject *kobj, struct kobj_attribute *attr,
 			  const char *buf, size_t count)
@@ -1167,7 +1167,7 @@ static struct kobj_attribute reboot_mode_attr = __ATTR_RW(mode);
 #ifdef CONFIG_X86
 static ssize_t force_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%d\n", reboot_force);
+	return sysfs_emit(buf, "%d\n", reboot_force);
 }
 static ssize_t force_store(struct kobject *kobj, struct kobj_attribute *attr,
 			  const char *buf, size_t count)
@@ -1214,7 +1214,7 @@ static ssize_t type_show(struct kobject *kobj, struct kobj_attribute *attr, char
 		val = REBOOT_UNDEFINED_STR;
 	}
 
-	return sprintf(buf, "%s\n", val);
+	return sysfs_emit(buf, "%s\n", val);
 }
 static ssize_t type_store(struct kobject *kobj, struct kobj_attribute *attr,
 			  const char *buf, size_t count)
@@ -1247,7 +1247,7 @@ static struct kobj_attribute reboot_type_attr = __ATTR_RW(type);
 #ifdef CONFIG_SMP
 static ssize_t cpu_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%d\n", reboot_cpu);
+	return sysfs_emit(buf, "%d\n", reboot_cpu);
 }
 static ssize_t cpu_store(struct kobject *kobj, struct kobj_attribute *attr,
 			  const char *buf, size_t count)

From 22193c586b43ee88d66954395885742a6e4a49a9 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Mon, 11 Nov 2024 23:08:05 +0100
Subject: [PATCH 1083/1530] samples: rust: fix `rust_print` build making it a
 combined module
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The `rust_print` module, when built as a module, fails to build with:

    ERROR: modpost: missing MODULE_LICENSE() in samples/rust/rust_print_events.o
    ERROR: modpost: "__tracepoint_rust_sample_loaded" [samples/rust/rust_print.ko] undefined!
    ERROR: modpost: "rust_do_trace_rust_sample_loaded" [samples/rust/rust_print.ko] undefined!

Fix it by building it as a combined one.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Alex Gaynor <alex.gaynor@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Gary Guo <gary@garyguo.net>
Cc: Björn Roy Baron <bjorn3_gh@protonmail.com>
Cc: Benno Lossin <benno.lossin@proton.me>
Cc: Andreas Hindborg <a.hindborg@kernel.org>
Cc: Alice Ryhl <aliceryhl@google.com>
Cc: Trevor Gross <tmgross@umich.edu>
Cc: "Linux Next Mailing List" <linux-next@vger.kernel.org>
Link: https://lore.kernel.org/20241111220805.708889-1-ojeda@kernel.org
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/all/20241108152149.28459a72@canb.auug.org.au/
Fixes: 91d39024e1b0 ("rust: samples: add tracepoint to Rust sample")
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 samples/rust/Makefile                              | 4 +++-
 samples/rust/{rust_print.rs => rust_print_main.rs} | 0
 2 files changed, 3 insertions(+), 1 deletion(-)
 rename samples/rust/{rust_print.rs => rust_print_main.rs} (100%)

diff --git a/samples/rust/Makefile b/samples/rust/Makefile
index f29280ec48208..c1a5c16553955 100644
--- a/samples/rust/Makefile
+++ b/samples/rust/Makefile
@@ -2,6 +2,8 @@
 ccflags-y += -I$(src)				# needed for trace events
 
 obj-$(CONFIG_SAMPLE_RUST_MINIMAL)		+= rust_minimal.o
-obj-$(CONFIG_SAMPLE_RUST_PRINT)			+= rust_print.o rust_print_events.o
+obj-$(CONFIG_SAMPLE_RUST_PRINT)			+= rust_print.o
+
+rust_print-y := rust_print_main.o rust_print_events.o
 
 subdir-$(CONFIG_SAMPLE_RUST_HOSTPROGS)		+= hostprogs
diff --git a/samples/rust/rust_print.rs b/samples/rust/rust_print_main.rs
similarity index 100%
rename from samples/rust/rust_print.rs
rename to samples/rust/rust_print_main.rs

From b2603f8ac8217bc59f5c7f248ac248423b9b99cb Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Mon, 11 Nov 2024 21:16:07 +0100
Subject: [PATCH 1084/1530] rust: warn on bindgen < 0.69.5 and libclang >= 19.1

When testing a `clang` upgrade with Rust Binder, Alice encountered [1] a
build failure caused by `bindgen` not translating some symbols related to
tracepoints. This was caused by commit 2e770edd8ce1 ("[libclang] Compute
the right spelling location") changing the behavior of a function exposed
by `libclang`. `bindgen` fixed the regression in commit 600f63895f73
("Use clang_getFileLocation instead of clang_getSpellingLocation").

However, the regression fix is only available in `bindgen` versions
0.69.5 or later (it was backported for 0.69.x). This means that when
older bindgen versions are used with new versions of `libclang`, `bindgen`
may do the wrong thing, which could lead to a build failure.

Alice encountered the bug with some header files related to tracepoints,
but it could also cause build failures in other circumstances. Thus,
always emit a warning when using an old `bindgen` with a new `libclang`
so that other people do not have to spend time chasing down the same
bug.

However, testing just the version is inconvenient, since distributions
do patch their packages without changing the version, so I reduced the
issue into the following piece of code that can trigger the issue:

    #define F(x) int x##x
    F(foo);

In particular, an unpatched `bindgen` will ignore the macro expansion
and thus not provide a declaration for the exported `int`.

Thus add a build test to `rust_is_available.sh` using the code above
(that is only triggered if the versions appear to be affected), following
what we did for the 0.66.x issue.

Moreover, I checked the status in the major distributions we have
instructions for:

  - Fedora 41 was affected but is now OK, since it now ships `bindgen`
    0.69.5.

    Thanks Ben for the quick reply on the updates that were ongoing.

    Fedora 40 and earlier are OK (older `libclang`, and they also now
    carry `bindgen` 0.69.5).

  - Debian Sid was affected but is now OK, since they now ship a patched
    `bindgen` binary (0.66.1-7+b3). The issue was reported to Debian by
    email and then as a bug report [2].

    Thanks NoisyCoil and Matthias for the quick replies. NoisyCoil handled
    the needed updates. Debian may upgrade to `bindgen` 0.70.x, too.

    Debian Testing is OK (older `libclang` so far).

  - Ubuntu non-LTS (oracular) is affected. The issue was reported to Ubuntu
    by email and then as a bug report [3].

    Ubuntu LTS is not affected (older `libclang` so far).

  - Arch Linux, Gentoo Linux and openSUSE should be OK (newer `bindgen` is
    provided). Nix as well (older `libclang` so far).

This issue was also added to our "live list" that tracks issues around
distributions [4].

Cc: Ben Beasley <code@musicinmybrain.net>
Cc: NoisyCoil <noisycoil@tutanota.com>
Cc: Matthias Geiger <werdahias@riseup.net>
Link: https://lore.kernel.org/rust-for-linux/20241030-bindgen-libclang-warn-v1-1-3a7ba9fedcfe@google.com/ [1]
Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=1086510 [2]
Link: https://bugs.launchpad.net/ubuntu/+source/rust-bindgen-cli/+bug/2086639 [3]
Link: https://github.com/Rust-for-Linux/linux/issues/1127 [4]
Co-developed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20241111201607.653149-1-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 scripts/rust_is_available.sh                  | 15 ++++++++
 ...ust_is_available_bindgen_libclang_concat.h |  3 ++
 scripts/rust_is_available_test.py             | 34 ++++++++++++++++++-
 3 files changed, 51 insertions(+), 1 deletion(-)
 create mode 100644 scripts/rust_is_available_bindgen_libclang_concat.h

diff --git a/scripts/rust_is_available.sh b/scripts/rust_is_available.sh
index 5262c56dd674e..93c0ef7fb3fb2 100755
--- a/scripts/rust_is_available.sh
+++ b/scripts/rust_is_available.sh
@@ -225,6 +225,21 @@ if [ "$bindgen_libclang_cversion" -lt "$bindgen_libclang_min_cversion" ]; then
 	exit 1
 fi
 
+if [ "$bindgen_libclang_cversion" -ge 1900100 ] &&
+	[ "$rust_bindings_generator_cversion" -lt 6905 ]; then
+	# Distributions may have patched the issue (e.g. Debian did).
+	if ! "$BINDGEN" $(dirname $0)/rust_is_available_bindgen_libclang_concat.h | grep -q foofoo; then
+		echo >&2 "***"
+		echo >&2 "*** Rust bindings generator '$BINDGEN' < 0.69.5 together with libclang >= 19.1"
+		echo >&2 "*** may not work due to a bug (https://github.com/rust-lang/rust-bindgen/pull/2824),"
+		echo >&2 "*** unless patched (like Debian's)."
+		echo >&2 "***   Your bindgen version:  $rust_bindings_generator_version"
+		echo >&2 "***   Your libclang version: $bindgen_libclang_version"
+		echo >&2 "***"
+		warning=1
+	fi
+fi
+
 # If the C compiler is Clang, then we can also check whether its version
 # matches the `libclang` version used by the Rust bindings generator.
 #
diff --git a/scripts/rust_is_available_bindgen_libclang_concat.h b/scripts/rust_is_available_bindgen_libclang_concat.h
new file mode 100644
index 0000000000000..efc6e98d0f1d0
--- /dev/null
+++ b/scripts/rust_is_available_bindgen_libclang_concat.h
@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#define F(x) int x##x
+F(foo);
diff --git a/scripts/rust_is_available_test.py b/scripts/rust_is_available_test.py
index 413741037fb30..4fcc319dea84e 100755
--- a/scripts/rust_is_available_test.py
+++ b/scripts/rust_is_available_test.py
@@ -54,7 +54,7 @@ def generate_rustc(cls, stdout):
 """)
 
     @classmethod
-    def generate_bindgen(cls, version_stdout, libclang_stderr, version_0_66_patched=False):
+    def generate_bindgen(cls, version_stdout, libclang_stderr, version_0_66_patched=False, libclang_concat_patched=False):
         if libclang_stderr is None:
             libclang_case = f"raise SystemExit({cls.bindgen_default_bindgen_libclang_failure_exit_code})"
         else:
@@ -65,12 +65,19 @@ def generate_bindgen(cls, version_stdout, libclang_stderr, version_0_66_patched=
         else:
             version_0_66_case = "raise SystemExit(1)"
 
+        if libclang_concat_patched:
+            libclang_concat_case = "print('pub static mut foofoo: ::std::os::raw::c_int;')"
+        else:
+            libclang_concat_case = "pass"
+
         return cls.generate_executable(f"""#!/usr/bin/env python3
 import sys
 if "rust_is_available_bindgen_libclang.h" in " ".join(sys.argv):
     {libclang_case}
 elif "rust_is_available_bindgen_0_66.h" in " ".join(sys.argv):
     {version_0_66_case}
+elif "rust_is_available_bindgen_libclang_concat.h" in " ".join(sys.argv):
+    {libclang_concat_case}
 else:
     print({repr(version_stdout)})
 """)
@@ -268,6 +275,31 @@ def test_bindgen_libclang_old_version(self):
         result = self.run_script(self.Expected.FAILURE, { "BINDGEN": bindgen })
         self.assertIn(f"libclang (used by the Rust bindings generator '{bindgen}') is too old.", result.stderr)
 
+    def test_bindgen_bad_libclang_concat(self):
+        for (bindgen_version, libclang_version, expected_not_patched) in (
+            ("0.69.4", "18.0.0", self.Expected.SUCCESS),
+            ("0.69.4", "19.1.0", self.Expected.SUCCESS_WITH_WARNINGS),
+            ("0.69.4", "19.2.0", self.Expected.SUCCESS_WITH_WARNINGS),
+
+            ("0.69.5", "18.0.0", self.Expected.SUCCESS),
+            ("0.69.5", "19.1.0", self.Expected.SUCCESS),
+            ("0.69.5", "19.2.0", self.Expected.SUCCESS),
+
+            ("0.70.0", "18.0.0", self.Expected.SUCCESS),
+            ("0.70.0", "19.1.0", self.Expected.SUCCESS),
+            ("0.70.0", "19.2.0", self.Expected.SUCCESS),
+        ):
+            with self.subTest(bindgen_version=bindgen_version, libclang_version=libclang_version):
+                cc = self.generate_clang(f"clang version {libclang_version}")
+                libclang_stderr = f"scripts/rust_is_available_bindgen_libclang.h:2:9: warning: clang version {libclang_version} [-W#pragma-messages], err: false"
+                bindgen = self.generate_bindgen(f"bindgen {bindgen_version}", libclang_stderr)
+                result = self.run_script(expected_not_patched, { "BINDGEN": bindgen, "CC": cc })
+                if expected_not_patched == self.Expected.SUCCESS_WITH_WARNINGS:
+                    self.assertIn(f"Rust bindings generator '{bindgen}' < 0.69.5 together with libclang >= 19.1", result.stderr)
+
+                bindgen = self.generate_bindgen(f"bindgen {bindgen_version}", libclang_stderr, libclang_concat_patched=True)
+                result = self.run_script(self.Expected.SUCCESS, { "BINDGEN": bindgen, "CC": cc })
+
     def test_clang_matches_bindgen_libclang_different_bindgen(self):
         bindgen = self.generate_bindgen_libclang("scripts/rust_is_available_bindgen_libclang.h:2:9: warning: clang version 999.0.0 [-W#pragma-messages], err: false")
         result = self.run_script(self.Expected.SUCCESS_WITH_WARNINGS, { "BINDGEN": bindgen })

From ece8a2c77b881a379d24fee4656195d809161867 Mon Sep 17 00:00:00 2001
From: Longfang Liu <liulongfang@huawei.com>
Date: Tue, 12 Nov 2024 15:33:19 +0800
Subject: [PATCH 1085/1530] hisi_acc_vfio_pci: extract public functions for
 container_of

In the current driver, vdev is obtained from struct
hisi_acc_vf_core_device through the container_of function.
This method is used in many places in the driver. In order to
reduce this repetitive operation, It was extracted into
a public function.

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Link: https://lore.kernel.org/r/20241112073322.54550-2-liulongfang@huawei.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 21 ++++++++++---------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index 0d632ba5d2a3c..299766a33e014 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -630,6 +630,12 @@ static void hisi_acc_vf_disable_fds(struct hisi_acc_vf_core_device *hisi_acc_vde
 	}
 }
 
+static struct hisi_acc_vf_core_device *hisi_acc_get_vf_dev(struct vfio_device *vdev)
+{
+	return container_of(vdev, struct hisi_acc_vf_core_device,
+			    core_device.vdev);
+}
+
 static void hisi_acc_vf_reset(struct hisi_acc_vf_core_device *hisi_acc_vdev)
 {
 	hisi_acc_vdev->vf_qm_state = QM_NOT_READY;
@@ -1031,8 +1037,7 @@ static struct file *
 hisi_acc_vfio_pci_set_device_state(struct vfio_device *vdev,
 				   enum vfio_device_mig_state new_state)
 {
-	struct hisi_acc_vf_core_device *hisi_acc_vdev = container_of(vdev,
-			struct hisi_acc_vf_core_device, core_device.vdev);
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
 	enum vfio_device_mig_state next_state;
 	struct file *res = NULL;
 	int ret;
@@ -1073,8 +1078,7 @@ static int
 hisi_acc_vfio_pci_get_device_state(struct vfio_device *vdev,
 				   enum vfio_device_mig_state *curr_state)
 {
-	struct hisi_acc_vf_core_device *hisi_acc_vdev = container_of(vdev,
-			struct hisi_acc_vf_core_device, core_device.vdev);
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
 
 	mutex_lock(&hisi_acc_vdev->state_mutex);
 	*curr_state = hisi_acc_vdev->mig_state;
@@ -1278,8 +1282,7 @@ static long hisi_acc_vfio_pci_ioctl(struct vfio_device *core_vdev, unsigned int
 
 static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
 {
-	struct hisi_acc_vf_core_device *hisi_acc_vdev = container_of(core_vdev,
-			struct hisi_acc_vf_core_device, core_device.vdev);
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(core_vdev);
 	struct vfio_pci_core_device *vdev = &hisi_acc_vdev->core_device;
 	int ret;
 
@@ -1302,8 +1305,7 @@ static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
 
 static void hisi_acc_vfio_pci_close_device(struct vfio_device *core_vdev)
 {
-	struct hisi_acc_vf_core_device *hisi_acc_vdev = container_of(core_vdev,
-			struct hisi_acc_vf_core_device, core_device.vdev);
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(core_vdev);
 	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
 
 	iounmap(vf_qm->io_base);
@@ -1318,8 +1320,7 @@ static const struct vfio_migration_ops hisi_acc_vfio_pci_migrn_state_ops = {
 
 static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
 {
-	struct hisi_acc_vf_core_device *hisi_acc_vdev = container_of(core_vdev,
-			struct hisi_acc_vf_core_device, core_device.vdev);
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(core_vdev);
 	struct pci_dev *pdev = to_pci_dev(core_vdev->dev);
 	struct hisi_qm *pf_qm = hisi_acc_get_pf_qm(pdev);
 

From 19629206894f1265d9148be475d8665c58596ab3 Mon Sep 17 00:00:00 2001
From: Longfang Liu <liulongfang@huawei.com>
Date: Tue, 12 Nov 2024 15:33:20 +0800
Subject: [PATCH 1086/1530] hisi_acc_vfio_pci: create subfunction for data
 reading

This patch generates the code for the operation of reading data from
the device into a sub-function.
Then, it can be called during the device status data saving phase of
the live migration process and the device status data reading function
in debugfs.
Thereby reducing the redundant code of the driver.

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Link: https://lore.kernel.org/r/20241112073322.54550-3-liulongfang@huawei.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 54 +++++++++++--------
 1 file changed, 33 insertions(+), 21 deletions(-)

diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index 299766a33e014..c4a74e38c78ae 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -486,31 +486,11 @@ static int vf_qm_load_data(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 	return 0;
 }
 
-static int vf_qm_state_save(struct hisi_acc_vf_core_device *hisi_acc_vdev,
-			    struct hisi_acc_vf_migration_file *migf)
+static int vf_qm_read_data(struct hisi_qm *vf_qm, struct acc_vf_data *vf_data)
 {
-	struct acc_vf_data *vf_data = &migf->vf_data;
-	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
 	struct device *dev = &vf_qm->pdev->dev;
 	int ret;
 
-	if (unlikely(qm_wait_dev_not_ready(vf_qm))) {
-		/* Update state and return with match data */
-		vf_data->vf_qm_state = QM_NOT_READY;
-		hisi_acc_vdev->vf_qm_state = vf_data->vf_qm_state;
-		migf->total_length = QM_MATCH_SIZE;
-		return 0;
-	}
-
-	vf_data->vf_qm_state = QM_READY;
-	hisi_acc_vdev->vf_qm_state = vf_data->vf_qm_state;
-
-	ret = vf_qm_cache_wb(vf_qm);
-	if (ret) {
-		dev_err(dev, "failed to writeback QM Cache!\n");
-		return ret;
-	}
-
 	ret = qm_get_regs(vf_qm, vf_data);
 	if (ret)
 		return -EINVAL;
@@ -536,6 +516,38 @@ static int vf_qm_state_save(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 		return -EINVAL;
 	}
 
+	return 0;
+}
+
+static int vf_qm_state_save(struct hisi_acc_vf_core_device *hisi_acc_vdev,
+			    struct hisi_acc_vf_migration_file *migf)
+{
+	struct acc_vf_data *vf_data = &migf->vf_data;
+	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
+	struct device *dev = &vf_qm->pdev->dev;
+	int ret;
+
+	if (unlikely(qm_wait_dev_not_ready(vf_qm))) {
+		/* Update state and return with match data */
+		vf_data->vf_qm_state = QM_NOT_READY;
+		hisi_acc_vdev->vf_qm_state = vf_data->vf_qm_state;
+		migf->total_length = QM_MATCH_SIZE;
+		return 0;
+	}
+
+	vf_data->vf_qm_state = QM_READY;
+	hisi_acc_vdev->vf_qm_state = vf_data->vf_qm_state;
+
+	ret = vf_qm_cache_wb(vf_qm);
+	if (ret) {
+		dev_err(dev, "failed to writeback QM Cache!\n");
+		return ret;
+	}
+
+	ret = vf_qm_read_data(vf_qm, vf_data);
+	if (ret)
+		return -EINVAL;
+
 	migf->total_length = sizeof(struct acc_vf_data);
 	return 0;
 }

From 0eb512779d642b21ced83778287a0f7a3ca8f2a1 Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Fri, 8 Nov 2024 15:47:36 -0800
Subject: [PATCH 1087/1530] riscv: Fix default misaligned access trap

Commit d1703dc7bc8e ("RISC-V: Detect unaligned vector accesses
supported") removed the default handlers for handle_misaligned_load()
and handle_misaligned_store(). When the kernel is compiled without
RISCV_SCALAR_MISALIGNED, these handlers are never defined, causing
compilation errors.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Fixes: d1703dc7bc8e ("RISC-V: Detect unaligned vector accesses supported")
Reviewed-by: Jesse Taube <mr.bossman075@gmail.com>
Link: https://lore.kernel.org/r/20241108-fix_handle_misaligned_load-v2-1-91d547ce64db@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/entry-common.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h
index 7b32d2b08bb66..b28ccc6cdeea4 100644
--- a/arch/riscv/include/asm/entry-common.h
+++ b/arch/riscv/include/asm/entry-common.h
@@ -25,7 +25,19 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 void handle_page_fault(struct pt_regs *regs);
 void handle_break(struct pt_regs *regs);
 
+#ifdef CONFIG_RISCV_MISALIGNED
 int handle_misaligned_load(struct pt_regs *regs);
 int handle_misaligned_store(struct pt_regs *regs);
+#else
+static inline int handle_misaligned_load(struct pt_regs *regs)
+{
+	return -1;
+}
+
+static inline int handle_misaligned_store(struct pt_regs *regs)
+{
+	return -1;
+}
+#endif
 
 #endif /* _ASM_RISCV_ENTRY_COMMON_H */

From 35025963326e44d8bced3eecd42d2f040f4f0024 Mon Sep 17 00:00:00 2001
From: Si-Wei Liu <si-wei.liu@oracle.com>
Date: Mon, 21 Oct 2024 16:40:40 +0300
Subject: [PATCH 1088/1530] vdpa/mlx5: Fix suboptimal range on iotlb iteration

The starting iova address to iterate iotlb map entry within a range
was set to an irrelevant value when passing to the itree_next()
iterator, although luckily it doesn't affect the outcome of finding
out the granule of the smallest iotlb map size. Fix the code to make
it consistent with the following for-loop.

Fixes: 94abbccdf291 ("vdpa/mlx5: Add shared memory registration code")
Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Message-Id: <20241021134040.975221-3-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vdpa/mlx5/core/mr.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index 7d0c83b5b0715..8455f08f5d406 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -368,7 +368,6 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr
 	unsigned long lgcd = 0;
 	int log_entity_size;
 	unsigned long size;
-	u64 start = 0;
 	int err;
 	struct page *pg;
 	unsigned int nsg;
@@ -379,10 +378,9 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr
 	struct device *dma = mvdev->vdev.dma_dev;
 
 	for (map = vhost_iotlb_itree_first(iotlb, mr->start, mr->end - 1);
-	     map; map = vhost_iotlb_itree_next(map, start, mr->end - 1)) {
+	     map; map = vhost_iotlb_itree_next(map, mr->start, mr->end - 1)) {
 		size = maplen(map, mr);
 		lgcd = gcd(lgcd, size);
-		start += size;
 	}
 	log_entity_size = ilog2(lgcd);
 

From 76f0d870e75e0b00843668ace7603a47890cb9ff Mon Sep 17 00:00:00 2001
From: Philip Chen <philipchen@chromium.org>
Date: Thu, 15 Aug 2024 00:46:17 +0000
Subject: [PATCH 1089/1530] virtio_pmem: Add freeze/restore callbacks

Add basic freeze/restore PM callbacks to support hibernation (S4):
- On freeze, delete vq and quiesce the device to prepare for
  snapshotting.
- On restore, re-init vq and mark DRIVER_OK.

Signed-off-by: Philip Chen <philipchen@chromium.org>
Message-Id: <20240815004617.2325269-1-philipchen@chromium.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/nvdimm/virtio_pmem.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c
index c9b97aeabf854..2396d19ce5496 100644
--- a/drivers/nvdimm/virtio_pmem.c
+++ b/drivers/nvdimm/virtio_pmem.c
@@ -143,6 +143,28 @@ static void virtio_pmem_remove(struct virtio_device *vdev)
 	virtio_reset_device(vdev);
 }
 
+static int virtio_pmem_freeze(struct virtio_device *vdev)
+{
+	vdev->config->del_vqs(vdev);
+	virtio_reset_device(vdev);
+
+	return 0;
+}
+
+static int virtio_pmem_restore(struct virtio_device *vdev)
+{
+	int ret;
+
+	ret = init_vq(vdev->priv);
+	if (ret) {
+		dev_err(&vdev->dev, "failed to initialize virtio pmem's vq\n");
+		return ret;
+	}
+	virtio_device_ready(vdev);
+
+	return 0;
+}
+
 static unsigned int features[] = {
 	VIRTIO_PMEM_F_SHMEM_REGION,
 };
@@ -155,6 +177,8 @@ static struct virtio_driver virtio_pmem_driver = {
 	.validate		= virtio_pmem_validate,
 	.probe			= virtio_pmem_probe,
 	.remove			= virtio_pmem_remove,
+	.freeze			= virtio_pmem_freeze,
+	.restore		= virtio_pmem_restore,
 };
 
 module_virtio_driver(virtio_pmem_driver);

From a49c26f761d2b9f6506d397f6e8373ebb27c65ba Mon Sep 17 00:00:00 2001
From: Wenyu Huang <huangwenyu1998@gmail.com>
Date: Sun, 13 Oct 2024 11:32:33 +0800
Subject: [PATCH 1090/1530] virtio: Make vring_new_virtqueue support packed
 vring

It is used for testing in tools/virtio/vringh_test.c.
If vring_new_virtqueue supports packed vring, we can add support for
packed vring to vringh and test it.

Signed-off-by: Wenyu Huang <huangwenyu1998@gmail.com>
Message-Id: <20241013033233.65026-1-huangwenyu1998@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_ring.c | 227 +++++++++++++++++++----------------
 1 file changed, 121 insertions(+), 106 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 98374ed7c5772..48b297f88abac 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -223,15 +223,6 @@ struct vring_virtqueue {
 #endif
 };
 
-static struct virtqueue *__vring_new_virtqueue(unsigned int index,
-					       struct vring_virtqueue_split *vring_split,
-					       struct virtio_device *vdev,
-					       bool weak_barriers,
-					       bool context,
-					       bool (*notify)(struct virtqueue *),
-					       void (*callback)(struct virtqueue *),
-					       const char *name,
-					       struct device *dma_dev);
 static struct vring_desc_extra *vring_alloc_desc_extra(unsigned int num);
 static void vring_free(struct virtqueue *_vq);
 
@@ -1138,6 +1129,66 @@ static int vring_alloc_queue_split(struct vring_virtqueue_split *vring_split,
 	return 0;
 }
 
+static struct virtqueue *__vring_new_virtqueue_split(unsigned int index,
+					       struct vring_virtqueue_split *vring_split,
+					       struct virtio_device *vdev,
+					       bool weak_barriers,
+					       bool context,
+					       bool (*notify)(struct virtqueue *),
+					       void (*callback)(struct virtqueue *),
+					       const char *name,
+					       struct device *dma_dev)
+{
+	struct vring_virtqueue *vq;
+	int err;
+
+	vq = kmalloc(sizeof(*vq), GFP_KERNEL);
+	if (!vq)
+		return NULL;
+
+	vq->packed_ring = false;
+	vq->vq.callback = callback;
+	vq->vq.vdev = vdev;
+	vq->vq.name = name;
+	vq->vq.index = index;
+	vq->vq.reset = false;
+	vq->we_own_ring = false;
+	vq->notify = notify;
+	vq->weak_barriers = weak_barriers;
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
+	vq->broken = true;
+#else
+	vq->broken = false;
+#endif
+	vq->dma_dev = dma_dev;
+	vq->use_dma_api = vring_use_dma_api(vdev);
+	vq->premapped = false;
+	vq->do_unmap = vq->use_dma_api;
+
+	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) &&
+		!context;
+	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
+
+	if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM))
+		vq->weak_barriers = false;
+
+	err = vring_alloc_state_extra_split(vring_split);
+	if (err) {
+		kfree(vq);
+		return NULL;
+	}
+
+	virtqueue_vring_init_split(vring_split, vq);
+
+	virtqueue_init(vq, vring_split->vring.num);
+	virtqueue_vring_attach_split(vq, vring_split);
+
+	spin_lock(&vdev->vqs_list_lock);
+	list_add_tail(&vq->vq.list, &vdev->vqs);
+	spin_unlock(&vdev->vqs_list_lock);
+	return &vq->vq;
+}
+
 static struct virtqueue *vring_create_virtqueue_split(
 	unsigned int index,
 	unsigned int num,
@@ -1160,7 +1211,7 @@ static struct virtqueue *vring_create_virtqueue_split(
 	if (err)
 		return NULL;
 
-	vq = __vring_new_virtqueue(index, &vring_split, vdev, weak_barriers,
+	vq = __vring_new_virtqueue_split(index, &vring_split, vdev, weak_barriers,
 				   context, notify, callback, name, dma_dev);
 	if (!vq) {
 		vring_free_split(&vring_split, vdev, dma_dev);
@@ -2050,36 +2101,29 @@ static void virtqueue_reinit_packed(struct vring_virtqueue *vq)
 	virtqueue_vring_init_packed(&vq->packed, !!vq->vq.callback);
 }
 
-static struct virtqueue *vring_create_virtqueue_packed(
-	unsigned int index,
-	unsigned int num,
-	unsigned int vring_align,
-	struct virtio_device *vdev,
-	bool weak_barriers,
-	bool may_reduce_num,
-	bool context,
-	bool (*notify)(struct virtqueue *),
-	void (*callback)(struct virtqueue *),
-	const char *name,
-	struct device *dma_dev)
+static struct virtqueue *__vring_new_virtqueue_packed(unsigned int index,
+					       struct vring_virtqueue_packed *vring_packed,
+					       struct virtio_device *vdev,
+					       bool weak_barriers,
+					       bool context,
+					       bool (*notify)(struct virtqueue *),
+					       void (*callback)(struct virtqueue *),
+					       const char *name,
+					       struct device *dma_dev)
 {
-	struct vring_virtqueue_packed vring_packed = {};
 	struct vring_virtqueue *vq;
 	int err;
 
-	if (vring_alloc_queue_packed(&vring_packed, vdev, num, dma_dev))
-		goto err_ring;
-
 	vq = kmalloc(sizeof(*vq), GFP_KERNEL);
 	if (!vq)
-		goto err_vq;
+		return NULL;
 
 	vq->vq.callback = callback;
 	vq->vq.vdev = vdev;
 	vq->vq.name = name;
 	vq->vq.index = index;
 	vq->vq.reset = false;
-	vq->we_own_ring = true;
+	vq->we_own_ring = false;
 	vq->notify = notify;
 	vq->weak_barriers = weak_barriers;
 #ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
@@ -2100,26 +2144,52 @@ static struct virtqueue *vring_create_virtqueue_packed(
 	if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM))
 		vq->weak_barriers = false;
 
-	err = vring_alloc_state_extra_packed(&vring_packed);
-	if (err)
-		goto err_state_extra;
+	err = vring_alloc_state_extra_packed(vring_packed);
+	if (err) {
+		kfree(vq);
+		return NULL;
+	}
 
-	virtqueue_vring_init_packed(&vring_packed, !!callback);
+	virtqueue_vring_init_packed(vring_packed, !!callback);
 
-	virtqueue_init(vq, num);
-	virtqueue_vring_attach_packed(vq, &vring_packed);
+	virtqueue_init(vq, vring_packed->vring.num);
+	virtqueue_vring_attach_packed(vq, vring_packed);
 
 	spin_lock(&vdev->vqs_list_lock);
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 	spin_unlock(&vdev->vqs_list_lock);
 	return &vq->vq;
+}
 
-err_state_extra:
-	kfree(vq);
-err_vq:
-	vring_free_packed(&vring_packed, vdev, dma_dev);
-err_ring:
-	return NULL;
+static struct virtqueue *vring_create_virtqueue_packed(
+	unsigned int index,
+	unsigned int num,
+	unsigned int vring_align,
+	struct virtio_device *vdev,
+	bool weak_barriers,
+	bool may_reduce_num,
+	bool context,
+	bool (*notify)(struct virtqueue *),
+	void (*callback)(struct virtqueue *),
+	const char *name,
+	struct device *dma_dev)
+{
+	struct vring_virtqueue_packed vring_packed = {};
+	struct virtqueue *vq;
+
+	if (vring_alloc_queue_packed(&vring_packed, vdev, num, dma_dev))
+		return NULL;
+
+	vq = __vring_new_virtqueue_packed(index, &vring_packed, vdev, weak_barriers,
+					context, notify, callback, name, dma_dev);
+	if (!vq) {
+		vring_free_packed(&vring_packed, vdev, dma_dev);
+		return NULL;
+	}
+
+	to_vvq(vq)->we_own_ring = true;
+
+	return vq;
 }
 
 static int virtqueue_resize_packed(struct virtqueue *_vq, u32 num)
@@ -2598,69 +2668,7 @@ irqreturn_t vring_interrupt(int irq, void *_vq)
 }
 EXPORT_SYMBOL_GPL(vring_interrupt);
 
-/* Only available for split ring */
-static struct virtqueue *__vring_new_virtqueue(unsigned int index,
-					       struct vring_virtqueue_split *vring_split,
-					       struct virtio_device *vdev,
-					       bool weak_barriers,
-					       bool context,
-					       bool (*notify)(struct virtqueue *),
-					       void (*callback)(struct virtqueue *),
-					       const char *name,
-					       struct device *dma_dev)
-{
-	struct vring_virtqueue *vq;
-	int err;
-
-	if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
-		return NULL;
-
-	vq = kmalloc(sizeof(*vq), GFP_KERNEL);
-	if (!vq)
-		return NULL;
-
-	vq->packed_ring = false;
-	vq->vq.callback = callback;
-	vq->vq.vdev = vdev;
-	vq->vq.name = name;
-	vq->vq.index = index;
-	vq->vq.reset = false;
-	vq->we_own_ring = false;
-	vq->notify = notify;
-	vq->weak_barriers = weak_barriers;
-#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
-	vq->broken = true;
-#else
-	vq->broken = false;
-#endif
-	vq->dma_dev = dma_dev;
-	vq->use_dma_api = vring_use_dma_api(vdev);
-	vq->premapped = false;
-	vq->do_unmap = vq->use_dma_api;
 
-	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) &&
-		!context;
-	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
-
-	if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM))
-		vq->weak_barriers = false;
-
-	err = vring_alloc_state_extra_split(vring_split);
-	if (err) {
-		kfree(vq);
-		return NULL;
-	}
-
-	virtqueue_vring_init_split(vring_split, vq);
-
-	virtqueue_init(vq, vring_split->vring.num);
-	virtqueue_vring_attach_split(vq, vring_split);
-
-	spin_lock(&vdev->vqs_list_lock);
-	list_add_tail(&vq->vq.list, &vdev->vqs);
-	spin_unlock(&vdev->vqs_list_lock);
-	return &vq->vq;
-}
 
 struct virtqueue *vring_create_virtqueue(
 	unsigned int index,
@@ -2840,7 +2848,6 @@ int virtqueue_reset(struct virtqueue *_vq,
 }
 EXPORT_SYMBOL_GPL(virtqueue_reset);
 
-/* Only available for split ring */
 struct virtqueue *vring_new_virtqueue(unsigned int index,
 				      unsigned int num,
 				      unsigned int vring_align,
@@ -2854,11 +2861,19 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 {
 	struct vring_virtqueue_split vring_split = {};
 
-	if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
-		return NULL;
+	if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED)) {
+		struct vring_virtqueue_packed vring_packed = {};
+
+		vring_packed.vring.num = num;
+		vring_packed.vring.desc = pages;
+		return __vring_new_virtqueue_packed(index, &vring_packed,
+						    vdev, weak_barriers,
+						    context, notify, callback,
+						    name, vdev->dev.parent);
+	}
 
 	vring_init(&vring_split.vring, num, pages, vring_align);
-	return __vring_new_virtqueue(index, &vring_split, vdev, weak_barriers,
+	return __vring_new_virtqueue_split(index, &vring_split, vdev, weak_barriers,
 				     context, notify, callback, name,
 				     vdev->dev.parent);
 }

From 22d984f1b90f960f9aa92e31b0d310c5f90be8a6 Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <mgurtovoy@nvidia.com>
Date: Sun, 6 Oct 2024 21:43:24 +0300
Subject: [PATCH 1091/1530] virtio_fs: add informative log for new tag
 discovery

Enhance the device probing process by adding a log message when a new
virtio-fs tag is successfully discovered. This improvement provides
better visibility into the initialization of virtio-fs devices.

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Message-Id: <20241006184324.8497-1-mgurtovoy@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 fs/fuse/virtio_fs.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 6404a189e9890..04d7d61cb2b2c 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -521,6 +521,7 @@ static int virtio_fs_read_tag(struct virtio_device *vdev, struct virtio_fs *fs)
 		return -EINVAL;
 	}
 
+	dev_info(&vdev->dev, "discovered new tag: %s\n", fs->tag);
 	return 0;
 }
 

From df28040c7f24559ffb23d5323eaa2f023a107dbe Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <mgurtovoy@nvidia.com>
Date: Sun, 6 Oct 2024 21:43:41 +0300
Subject: [PATCH 1092/1530] virtio_fs: store actual queue index in mq_map

This will eliminate the need for index recalculation during the fast
path.

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Message-Id: <20241006184341.9081-1-mgurtovoy@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 fs/fuse/virtio_fs.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 04d7d61cb2b2c..28c1864baeed9 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -242,7 +242,7 @@ static ssize_t cpu_list_show(struct kobject *kobj,
 
 	qid = fsvq->vq->index;
 	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
-		if (qid < VQ_REQUEST || (fs->mq_map[cpu] == qid - VQ_REQUEST)) {
+		if (qid < VQ_REQUEST || (fs->mq_map[cpu] == qid)) {
 			if (first)
 				ret = snprintf(buf + pos, size - pos, "%u", cpu);
 			else
@@ -871,23 +871,23 @@ static void virtio_fs_map_queues(struct virtio_device *vdev, struct virtio_fs *f
 			goto fallback;
 
 		for_each_cpu(cpu, mask)
-			fs->mq_map[cpu] = q;
+			fs->mq_map[cpu] = q + VQ_REQUEST;
 	}
 
 	return;
 fallback:
 	/* Attempt to map evenly in groups over the CPUs */
 	masks = group_cpus_evenly(fs->num_request_queues);
-	/* If even this fails we default to all CPUs use queue zero */
+	/* If even this fails we default to all CPUs use first request queue */
 	if (!masks) {
 		for_each_possible_cpu(cpu)
-			fs->mq_map[cpu] = 0;
+			fs->mq_map[cpu] = VQ_REQUEST;
 		return;
 	}
 
 	for (q = 0; q < fs->num_request_queues; q++) {
 		for_each_cpu(cpu, &masks[q])
-			fs->mq_map[cpu] = q;
+			fs->mq_map[cpu] = q + VQ_REQUEST;
 	}
 	kfree(masks);
 }
@@ -1482,7 +1482,7 @@ static void virtio_fs_send_req(struct fuse_iqueue *fiq, struct fuse_req *req)
 	clear_bit(FR_PENDING, &req->flags);
 
 	fs = fiq->priv;
-	queue_id = VQ_REQUEST + fs->mq_map[raw_smp_processor_id()];
+	queue_id = fs->mq_map[raw_smp_processor_id()];
 
 	pr_debug("%s: opcode %u unique %#llx nodeid %#llx in.len %u out.len %u queue_id %u\n",
 		 __func__, req->in.h.opcode, req->in.h.unique,

From 6a39bb15b3d1c355ab198d41f9590379d734f0bb Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Thu, 7 Nov 2024 13:21:14 +0000
Subject: [PATCH 1093/1530] virtio_vdpa: remove redundant check on desc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The boolean variable has_affinity is true when desc is non-null and
ops->set_vq_affinity is non-null. Hence the call to create_affinity_masks
does not need to check for desc being non-null is redundant when
has_affinity is true, so it can be removed as well as the now unused
default_affd.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Message-Id: <20241107132114.22188-1-colin.i.king@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
---
 drivers/virtio/virtio_vdpa.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c
index 7364bd53e38dd..1f60c9d5cb181 100644
--- a/drivers/virtio/virtio_vdpa.c
+++ b/drivers/virtio/virtio_vdpa.c
@@ -364,14 +364,13 @@ static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 	struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
 	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
 	const struct vdpa_config_ops *ops = vdpa->config;
-	struct irq_affinity default_affd = { 0 };
 	struct cpumask *masks;
 	struct vdpa_callback cb;
 	bool has_affinity = desc && ops->set_vq_affinity;
 	int i, err, queue_idx = 0;
 
 	if (has_affinity) {
-		masks = create_affinity_masks(nvqs, desc ? desc : &default_affd);
+		masks = create_affinity_masks(nvqs, desc);
 		if (!masks)
 			return -ENOMEM;
 	}

From b7e9fc3361c3f0836833dc2edba3dfef054a338a Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andy.shevchenko@gmail.com>
Date: Sun, 10 Nov 2024 22:59:41 +0200
Subject: [PATCH 1094/1530] pinctrl: cy8c95x0: Use 2-argument strscpy()

Use 2-argument strscpy(), which is not only shorter but also provides
an additional check that destination buffer is an array.

Signed-off-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/20241110210040.18918-2-andy.shevchenko@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-cy8c95x0.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index 5096ccdd459ea..5f533dff44173 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -1424,7 +1424,7 @@ static int cy8c95x0_detect(struct i2c_client *client,
 	}
 
 	dev_info(&client->dev, "Found a %s chip at 0x%02x.\n", name, client->addr);
-	strscpy(info->type, name, I2C_NAME_SIZE);
+	strscpy(info->type, name);
 
 	return 0;
 }
@@ -1457,15 +1457,15 @@ static int cy8c95x0_probe(struct i2c_client *client)
 
 	switch (chip->tpin) {
 	case 20:
-		strscpy(chip->name, cy8c95x0_id[0].name, I2C_NAME_SIZE);
+		strscpy(chip->name, cy8c95x0_id[0].name);
 		regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 3 * MUXED_STRIDE;
 		break;
 	case 40:
-		strscpy(chip->name, cy8c95x0_id[1].name, I2C_NAME_SIZE);
+		strscpy(chip->name, cy8c95x0_id[1].name);
 		regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 6 * MUXED_STRIDE;
 		break;
 	case 60:
-		strscpy(chip->name, cy8c95x0_id[2].name, I2C_NAME_SIZE);
+		strscpy(chip->name, cy8c95x0_id[2].name);
 		regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 8 * MUXED_STRIDE;
 		break;
 	default:

From c13411c6fae68f8e4b35d111d955eaa1d49a8f5f Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andy.shevchenko@gmail.com>
Date: Sun, 10 Nov 2024 22:59:42 +0200
Subject: [PATCH 1095/1530] pinctrl: cy8c95x0: switch to using
 devm_regulator_get_enable()

The driver does not actively manage regulator state past probe() time,
so we can use devm_regulator_get_enable() to simplify the code.

Signed-off-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/20241110210040.18918-3-andy.shevchenko@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-cy8c95x0.c | 58 ++++++------------------------
 1 file changed, 11 insertions(+), 47 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index 5f533dff44173..cb6d9458c1e83 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -141,7 +141,6 @@ static const struct dmi_system_id cy8c95x0_dmi_acpi_irq_info[] = {
  * @nport:          Number of Gports in this chip
  * @gpio_chip:      gpiolib chip
  * @driver_data:    private driver data
- * @regulator:      Pointer to the regulator for the IC
  * @dev:            struct device
  * @pctldev:        pin controller device
  * @pinctrl_desc:   pin controller description
@@ -163,7 +162,6 @@ struct cy8c95x0_pinctrl {
 	int nport;
 	struct gpio_chip gpio_chip;
 	unsigned long driver_data;
-	struct regulator *regulator;
 	struct device *dev;
 	struct pinctrl_dev *pctldev;
 	struct pinctrl_desc pinctrl_desc;
@@ -1434,7 +1432,6 @@ static int cy8c95x0_probe(struct i2c_client *client)
 	struct cy8c95x0_pinctrl *chip;
 	struct regmap_config regmap_conf;
 	struct regmap_range_cfg regmap_range_conf;
-	struct regulator *reg;
 	int ret;
 
 	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
@@ -1448,8 +1445,6 @@ static int cy8c95x0_probe(struct i2c_client *client)
 	if (!chip->driver_data)
 		return -ENODEV;
 
-	i2c_set_clientdata(client, chip);
-
 	chip->tpin = chip->driver_data & CY8C95X0_GPIO_MASK;
 	chip->nport = DIV_ROUND_UP(CY8C95X0_PIN_TO_OFFSET(chip->tpin), BANK_SZ);
 
@@ -1472,26 +1467,15 @@ static int cy8c95x0_probe(struct i2c_client *client)
 		return -ENODEV;
 	}
 
-	reg = devm_regulator_get(&client->dev, "vdd");
-	if (IS_ERR(reg)) {
-		if (PTR_ERR(reg) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
-	} else {
-		ret = regulator_enable(reg);
-		if (ret) {
-			dev_err(&client->dev, "failed to enable regulator vdd: %d\n", ret);
-			return ret;
-		}
-		chip->regulator = reg;
-	}
+	ret = devm_regulator_get_enable(&client->dev, "vdd");
+	if (ret)
+		return dev_err_probe(&client->dev, ret, "failed to enable regulator vdd\n");
 
 	/* bring the chip out of reset if reset pin is provided */
 	chip->gpio_reset = devm_gpiod_get_optional(&client->dev, "reset", GPIOD_OUT_HIGH);
-	if (IS_ERR(chip->gpio_reset)) {
-		ret = dev_err_probe(chip->dev, PTR_ERR(chip->gpio_reset),
-				    "Failed to get GPIO 'reset'\n");
-		goto err_exit;
-	} else if (chip->gpio_reset) {
+	if (IS_ERR(chip->gpio_reset))
+		return dev_err_probe(chip->dev, PTR_ERR(chip->gpio_reset), "Failed to get GPIO 'reset'\n");
+	if (chip->gpio_reset) {
 		usleep_range(1000, 2000);
 		gpiod_set_value_cansleep(chip->gpio_reset, 0);
 		usleep_range(250000, 300000);
@@ -1506,10 +1490,8 @@ static int cy8c95x0_probe(struct i2c_client *client)
 	regmap_conf.num_reg_defaults_raw = regmap_range_conf.range_max;
 
 	chip->regmap = devm_regmap_init_i2c(client, &regmap_conf);
-	if (IS_ERR(chip->regmap)) {
-		ret = PTR_ERR(chip->regmap);
-		goto err_exit;
-	}
+	if (IS_ERR(chip->regmap))
+		return PTR_ERR(chip->regmap);
 
 	bitmap_zero(chip->push_pull, MAX_LINE);
 	bitmap_zero(chip->shiftmask, MAX_LINE);
@@ -1525,31 +1507,14 @@ static int cy8c95x0_probe(struct i2c_client *client)
 	if (client->irq) {
 		ret = cy8c95x0_irq_setup(chip, client->irq);
 		if (ret)
-			goto err_exit;
+			return ret;
 	}
 
 	ret = cy8c95x0_setup_pinctrl(chip);
 	if (ret)
-		goto err_exit;
-
-	ret = cy8c95x0_setup_gpiochip(chip);
-	if (ret)
-		goto err_exit;
-
-	return 0;
-
-err_exit:
-	if (!IS_ERR_OR_NULL(chip->regulator))
-		regulator_disable(chip->regulator);
-	return ret;
-}
-
-static void cy8c95x0_remove(struct i2c_client *client)
-{
-	struct cy8c95x0_pinctrl *chip = i2c_get_clientdata(client);
+		return ret;
 
-	if (!IS_ERR_OR_NULL(chip->regulator))
-		regulator_disable(chip->regulator);
+	return cy8c95x0_setup_gpiochip(chip);
 }
 
 static const struct acpi_device_id cy8c95x0_acpi_ids[] = {
@@ -1565,7 +1530,6 @@ static struct i2c_driver cy8c95x0_driver = {
 		.acpi_match_table = cy8c95x0_acpi_ids,
 	},
 	.probe		= cy8c95x0_probe,
-	.remove		= cy8c95x0_remove,
 	.id_table	= cy8c95x0_id,
 	.detect		= cy8c95x0_detect,
 };

From f8bd5383d8b67e08153123718d0fb6e92a70f838 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andy.shevchenko@gmail.com>
Date: Sun, 10 Nov 2024 22:59:43 +0200
Subject: [PATCH 1096/1530] pinctrl: cy8c95x0: use flexible sleeping in reset
 function

The device reset assert and deassert length was created by usleep_range()
but that does not ensure optimal handling of all the different values from
device tree properties. By switching to the new flexible sleeping helper
function, fsleep(), the correct delay function is called depending on
delay length, e.g. udelay(), usleep_range() or msleep().

While at it, move out GPIO consumer name setting of the reset conditional,
the all necessary checks are already done there, so logically that call is
not related to the reset sequence.

Signed-off-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/20241110210040.18918-4-andy.shevchenko@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-cy8c95x0.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index cb6d9458c1e83..54b080f632263 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -1475,12 +1475,11 @@ static int cy8c95x0_probe(struct i2c_client *client)
 	chip->gpio_reset = devm_gpiod_get_optional(&client->dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(chip->gpio_reset))
 		return dev_err_probe(chip->dev, PTR_ERR(chip->gpio_reset), "Failed to get GPIO 'reset'\n");
+	gpiod_set_consumer_name(chip->gpio_reset, "CY8C95X0 RESET");
 	if (chip->gpio_reset) {
-		usleep_range(1000, 2000);
+		fsleep(1000);
 		gpiod_set_value_cansleep(chip->gpio_reset, 0);
-		usleep_range(250000, 300000);
-
-		gpiod_set_consumer_name(chip->gpio_reset, "CY8C95X0 RESET");
+		fsleep(250000);
 	}
 
 	/* Regmap for direct and paged registers */

From e1b47291bdcf0416337a535a52786fb55810f00d Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andy.shevchenko@gmail.com>
Date: Sun, 10 Nov 2024 22:59:44 +0200
Subject: [PATCH 1097/1530] pinctrl: cy8c95x0: Use temporary variable for
 struct device

Use a temporary variable for the struct device pointers to avoid
dereferencing. This makes code a bit neater.

Signed-off-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/20241110210040.18918-5-andy.shevchenko@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-cy8c95x0.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index 54b080f632263..8b118fd09e9e2 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -1429,16 +1429,17 @@ static int cy8c95x0_detect(struct i2c_client *client,
 
 static int cy8c95x0_probe(struct i2c_client *client)
 {
+	struct device *dev = &client->dev;
 	struct cy8c95x0_pinctrl *chip;
 	struct regmap_config regmap_conf;
 	struct regmap_range_cfg regmap_range_conf;
 	int ret;
 
-	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
 	if (!chip)
 		return -ENOMEM;
 
-	chip->dev = &client->dev;
+	chip->dev = dev;
 
 	/* Set the device type */
 	chip->driver_data = (uintptr_t)i2c_get_match_data(client);
@@ -1467,14 +1468,14 @@ static int cy8c95x0_probe(struct i2c_client *client)
 		return -ENODEV;
 	}
 
-	ret = devm_regulator_get_enable(&client->dev, "vdd");
+	ret = devm_regulator_get_enable(dev, "vdd");
 	if (ret)
-		return dev_err_probe(&client->dev, ret, "failed to enable regulator vdd\n");
+		return dev_err_probe(dev, ret, "failed to enable regulator vdd\n");
 
 	/* bring the chip out of reset if reset pin is provided */
-	chip->gpio_reset = devm_gpiod_get_optional(&client->dev, "reset", GPIOD_OUT_HIGH);
+	chip->gpio_reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(chip->gpio_reset))
-		return dev_err_probe(chip->dev, PTR_ERR(chip->gpio_reset), "Failed to get GPIO 'reset'\n");
+		return dev_err_probe(dev, PTR_ERR(chip->gpio_reset), "Failed to get GPIO 'reset'\n");
 	gpiod_set_consumer_name(chip->gpio_reset, "CY8C95X0 RESET");
 	if (chip->gpio_reset) {
 		fsleep(1000);

From ab899a0ec3cb0748f67ca66a14615dadfa6304e7 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andy.shevchenko@gmail.com>
Date: Sun, 10 Nov 2024 22:59:45 +0200
Subject: [PATCH 1098/1530] pinctrl: cy8c95x0: embed iterator to the for-loop

When we iterate through nports the iterator variable is effectively
being not used outside of the loop. Make it clear by moving its definition
into the for-loop. This makes code cleaner as well.

Signed-off-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/20241110210040.18918-6-andy.shevchenko@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-cy8c95x0.c | 36 +++++++++++++-----------------
 1 file changed, 15 insertions(+), 21 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index 8b118fd09e9e2..8c611abd47455 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -159,7 +159,7 @@ struct cy8c95x0_pinctrl {
 	DECLARE_BITMAP(irq_trig_high, MAX_LINE);
 	DECLARE_BITMAP(push_pull, MAX_LINE);
 	DECLARE_BITMAP(shiftmask, MAX_LINE);
-	int nport;
+	unsigned int nport;
 	struct gpio_chip gpio_chip;
 	unsigned long driver_data;
 	struct device *dev;
@@ -610,9 +610,8 @@ static int cy8c95x0_write_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	DECLARE_BITMAP(tmask, MAX_LINE);
 	DECLARE_BITMAP(tval, MAX_LINE);
 	int write_val;
-	int ret = 0;
-	int i;
 	u8 bits;
+	int ret;
 
 	/* Add the 4 bit gap of Gport2 */
 	bitmap_andnot(tmask, mask, chip->shiftmask, MAX_LINE);
@@ -623,7 +622,7 @@ static int cy8c95x0_write_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_shift_left(tval, tval, 4, MAX_LINE);
 	bitmap_replace(tval, tval, val, chip->shiftmask, BANK_SZ * 3);
 
-	for (i = 0; i < chip->nport; i++) {
+	for (unsigned int i = 0; i < chip->nport; i++) {
 		/* Skip over unused banks */
 		bits = bitmap_get_value8(tmask, i * BANK_SZ);
 		if (!bits)
@@ -632,15 +631,13 @@ static int cy8c95x0_write_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 		write_val = bitmap_get_value8(tval, i * BANK_SZ);
 
 		ret = cy8c95x0_regmap_update_bits(chip, reg, i, bits, write_val);
-		if (ret < 0)
-			goto out;
+		if (ret < 0) {
+			dev_err(chip->dev, "failed writing register %d, port %u: err %d\n", reg, i, ret);
+			return ret;
+		}
 	}
-out:
-
-	if (ret < 0)
-		dev_err(chip->dev, "failed writing register %d, port %d: err %d\n", reg, i, ret);
 
-	return ret;
+	return 0;
 }
 
 static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
@@ -650,9 +647,8 @@ static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	DECLARE_BITMAP(tval, MAX_LINE);
 	DECLARE_BITMAP(tmp, MAX_LINE);
 	int read_val;
-	int ret = 0;
-	int i;
 	u8 bits;
+	int ret;
 
 	/* Add the 4 bit gap of Gport2 */
 	bitmap_andnot(tmask, mask, chip->shiftmask, MAX_LINE);
@@ -663,15 +659,17 @@ static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_shift_left(tval, tval, 4, MAX_LINE);
 	bitmap_replace(tval, tval, val, chip->shiftmask, BANK_SZ * 3);
 
-	for (i = 0; i < chip->nport; i++) {
+	for (unsigned int i = 0; i < chip->nport; i++) {
 		/* Skip over unused banks */
 		bits = bitmap_get_value8(tmask, i * BANK_SZ);
 		if (!bits)
 			continue;
 
 		ret = cy8c95x0_regmap_read(chip, reg, i, &read_val);
-		if (ret < 0)
-			goto out;
+		if (ret < 0) {
+			dev_err(chip->dev, "failed reading register %d, port %u: err %d\n", reg, i, ret);
+			return ret;
+		}
 
 		read_val &= bits;
 		read_val |= bitmap_get_value8(tval, i * BANK_SZ) & ~bits;
@@ -682,11 +680,7 @@ static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_shift_right(tmp, tval, 4, MAX_LINE);
 	bitmap_replace(val, tmp, tval, chip->shiftmask, MAX_LINE);
 
-out:
-	if (ret < 0)
-		dev_err(chip->dev, "failed reading register %d, port %d: err %d\n", reg, i, ret);
-
-	return ret;
+	return 0;
 }
 
 static int cy8c95x0_gpio_direction_input(struct gpio_chip *gc, unsigned int off)

From 581d24052a4e5ee59c8b1b08b640365ffb2d6386 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andy.shevchenko@gmail.com>
Date: Sun, 10 Nov 2024 22:59:46 +0200
Subject: [PATCH 1099/1530] pinctrl: cy8c95x0: remove unneeded goto labels

In some cases the code uses goto labels to just return an error code.
Replace those with direct return:s and drop unneeded goto labels.

Signed-off-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/20241110210040.18918-7-andy.shevchenko@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-cy8c95x0.c | 26 ++++++++------------------
 1 file changed, 8 insertions(+), 18 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index 8c611abd47455..0d6c2027d4c18 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -746,14 +746,12 @@ static int cy8c95x0_gpio_get_direction(struct gpio_chip *gc, unsigned int off)
 
 	ret = cy8c95x0_regmap_read(chip, CY8C95X0_DIRECTION, port, &reg_val);
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	if (reg_val & bit)
 		return GPIO_LINE_DIRECTION_IN;
 
 	return GPIO_LINE_DIRECTION_OUT;
-out:
-	return ret;
 }
 
 static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
@@ -815,8 +813,7 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
 	case PIN_CONFIG_SLEEP_HARDWARE_STATE:
 	case PIN_CONFIG_SLEW_RATE:
 	default:
-		ret = -ENOTSUPP;
-		goto out;
+		return -ENOTSUPP;
 	}
 	/*
 	 * Writing 1 to one of the drive mode registers will automatically
@@ -824,7 +821,7 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
 	 */
 	ret = cy8c95x0_regmap_read(chip, reg, port, &reg_val);
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	if (reg_val & bit)
 		arg = 1;
@@ -832,8 +829,7 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
 		arg = !arg;
 
 	*config = pinconf_to_config_packed(param, (u16)arg);
-out:
-	return ret;
+	return 0;
 }
 
 static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip,
@@ -845,7 +841,6 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip,
 	unsigned long param = pinconf_to_config_param(config);
 	unsigned long arg = pinconf_to_config_argument(config);
 	unsigned int reg;
-	int ret;
 
 	switch (param) {
 	case PIN_CONFIG_BIAS_PULL_UP:
@@ -876,22 +871,17 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip,
 		reg = CY8C95X0_PWMSEL;
 		break;
 	case PIN_CONFIG_OUTPUT_ENABLE:
-		ret = cy8c95x0_pinmux_direction(chip, off, !arg);
-		goto out;
+		return cy8c95x0_pinmux_direction(chip, off, !arg);
 	case PIN_CONFIG_INPUT_ENABLE:
-		ret = cy8c95x0_pinmux_direction(chip, off, arg);
-		goto out;
+		return cy8c95x0_pinmux_direction(chip, off, arg);
 	default:
-		ret = -ENOTSUPP;
-		goto out;
+		return -ENOTSUPP;
 	}
 	/*
 	 * Writing 1 to one of the drive mode registers will automatically
 	 * clear conflicting set bits in the other drive mode registers.
 	 */
-	ret = cy8c95x0_regmap_write_bits(chip, reg, port, bit, bit);
-out:
-	return ret;
+	return cy8c95x0_regmap_write_bits(chip, reg, port, bit, bit);
 }
 
 static int cy8c95x0_gpio_get_multiple(struct gpio_chip *gc,

From b02e9f9172cedc0d0e0417fb91b79f24794cbf02 Mon Sep 17 00:00:00 2001
From: Melody Olvera <quic_molvera@quicinc.com>
Date: Mon, 11 Nov 2024 16:28:42 -0800
Subject: [PATCH 1100/1530] dt-bindings: pinctrl: qcom: Add sm8750 pinctrl

Add documentation for the Qualcomm sm8750 tlmm.

Signed-off-by: Melody Olvera <quic_molvera@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/20241112002843.2804490-2-quic_molvera@quicinc.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/qcom,sm8750-tlmm.yaml    | 138 ++++++++++++++++++
 1 file changed, 138 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/qcom,sm8750-tlmm.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8750-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8750-tlmm.yaml
new file mode 100644
index 0000000000000..7aecc97745a8c
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8750-tlmm.yaml
@@ -0,0 +1,138 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,sm8750-tlmm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Technologies, Inc. SM8750 TLMM block
+
+maintainers:
+  - Melody Olvera <quic_molvera@quicinc.com>
+
+description:
+  Top Level Mode Multiplexer pin controller in Qualcomm SM8750 SoC.
+
+allOf:
+  - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml#
+
+properties:
+  compatible:
+    const: qcom,sm8750-tlmm
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  gpio-reserved-ranges:
+    minItems: 1
+    maxItems: 108
+
+  gpio-line-names:
+    maxItems: 215
+
+patternProperties:
+  "-state$":
+    oneOf:
+      - $ref: "#/$defs/qcom-sm8750-tlmm-state"
+      - patternProperties:
+          "-pins$":
+            $ref: "#/$defs/qcom-sm8750-tlmm-state"
+        additionalProperties: false
+
+$defs:
+  qcom-sm8750-tlmm-state:
+    type: object
+    description:
+      Pinctrl node's client devices use subnodes for desired pin configuration.
+      Client device subnodes use below standard properties.
+    $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
+
+    properties:
+      pins:
+        description:
+          List of gpio pins affected by the properties specified in this
+          subnode.
+        items:
+          oneOf:
+            - pattern: "^gpio([0-9]|[1-9][0-9]|1[0-9][0-9]|20[0-9]|21[0-4])$"
+            - enum: [ ufs_reset, sdc2_clk, sdc2_cmd, sdc2_data ]
+        minItems: 1
+        maxItems: 36
+
+      function:
+        description:
+          Specify the alternative function to be configured for the specified
+          pins.
+        enum: [ gpio, aoss_cti, atest_char, atest_usb, audio_ext_mclk0,
+                audio_ext_mclk1, audio_ref_clk, cam_aon_mclk2, cam_aon_mclk4,
+                cam_mclk, cci_async_in, cci_i2c_scl, cci_i2c_sda, cci_timer,
+                cmu_rng, coex_uart1_rx, coex_uart1_tx, coex_uart2_rx,
+                coex_uart2_tx, dbg_out_clk, ddr_bist_complete, ddr_bist_fail,
+                ddr_bist_start, ddr_bist_stop, ddr_pxi0, ddr_pxi1, ddr_pxi2,
+                ddr_pxi3, dp_hot, egpio, gcc_gp1, gcc_gp2, gcc_gp3, gnss_adc0,
+                gnss_adc1, i2chub0_se0, i2chub0_se1, i2chub0_se2, i2chub0_se3,
+                i2chub0_se4, i2chub0_se5, i2chub0_se6, i2chub0_se7, i2chub0_se8,
+                i2chub0_se9, i2s0_data0, i2s0_data1, i2s0_sck, i2s0_ws,
+                i2s1_data0, i2s1_data1, i2s1_sck, i2s1_ws, ibi_i3c, jitter_bist,
+                mdp_esync0_out, mdp_esync1_out, mdp_vsync, mdp_vsync0_out,
+                mdp_vsync1_out, mdp_vsync2_out, mdp_vsync3_out, mdp_vsync5_out,
+                mdp_vsync_e, nav_gpio0, nav_gpio1, nav_gpio2, nav_gpio3,
+                pcie0_clk_req_n, phase_flag, pll_bist_sync, pll_clk_aux,
+                prng_rosc0, prng_rosc1, prng_rosc2, prng_rosc3, qdss_cti,
+                qlink_big_enable, qlink_big_request, qlink_little_enable,
+                qlink_little_request, qlink_wmss, qspi0, qspi1, qspi2, qspi3,
+                qspi_clk, qspi_cs, qup1_se0, qup1_se1, qup1_se2, qup1_se3,
+                qup1_se4, qup1_se5, qup1_se6, qup1_se7, qup2_se0, qup2_se1,
+                qup2_se2, qup2_se3, qup2_se4, qup2_se5, qup2_se6, qup2_se7,
+                sd_write_protect, sdc40, sdc41, sdc42, sdc43, sdc4_clk,
+                sdc4_cmd, tb_trig_sdc2, tb_trig_sdc4, tmess_prng0, tmess_prng1,
+                tmess_prng2, tmess_prng3, tsense_pwm1, tsense_pwm2, tsense_pwm3,
+                tsense_pwm4, uim0_clk, uim0_data, uim0_present, uim0_reset,
+                uim1_clk, uim1_data, uim1_present, uim1_reset, usb1_hs, usb_phy,
+                vfr_0, vfr_1, vsense_trigger_mirnat, wcn_sw, wcn_sw_ctrl ]
+
+    required:
+      - pins
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    tlmm: pinctrl@f100000 {
+        compatible = "qcom,sm8750-tlmm";
+        reg = <0x0f100000 0x300000>;
+        gpio-controller;
+        #gpio-cells = <2>;
+        gpio-ranges = <&tlmm 0 0 216>;
+        interrupt-controller;
+        #interrupt-cells = <2>;
+        interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
+
+        gpio-wo-state {
+            pins = "gpio1";
+            function = "gpio";
+        };
+
+        uart-w-state {
+            rx-pins {
+                pins = "gpio60";
+                function = "qup1_se7";
+                bias-pull-up;
+            };
+
+            tx-pins {
+                pins = "gpio61";
+                function = "qup1_se7";
+                bias-disable;
+            };
+        };
+    };
+...

From afe9803e3b82f0d05b6848a854604dcaaeb5ded0 Mon Sep 17 00:00:00 2001
From: Melody Olvera <quic_molvera@quicinc.com>
Date: Mon, 11 Nov 2024 16:28:43 -0800
Subject: [PATCH 1101/1530] pinctrl: qcom: Add sm8750 pinctrl driver

Add TLMM pinctrl driver to support pin configuration with pinctrl
framework for sm8750 SoC.

Signed-off-by: Melody Olvera <quic_molvera@quicinc.com>
Reviewed-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/20241112002843.2804490-3-quic_molvera@quicinc.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/Kconfig.msm      |    8 +
 drivers/pinctrl/qcom/Makefile         |    1 +
 drivers/pinctrl/qcom/pinctrl-sm8750.c | 1729 +++++++++++++++++++++++++
 3 files changed, 1738 insertions(+)
 create mode 100644 drivers/pinctrl/qcom/pinctrl-sm8750.c

diff --git a/drivers/pinctrl/qcom/Kconfig.msm b/drivers/pinctrl/qcom/Kconfig.msm
index 38d44052d3c91..206226318e452 100644
--- a/drivers/pinctrl/qcom/Kconfig.msm
+++ b/drivers/pinctrl/qcom/Kconfig.msm
@@ -413,6 +413,14 @@ config PINCTRL_SM8650
 	  Qualcomm Technologies Inc TLMM block found on the Qualcomm
 	  Technologies Inc SM8650 platform.
 
+config PINCTRL_SM8750
+	tristate "Qualcomm Technologies Inc SM8750 pin controller driver"
+	depends on ARM64 || COMPILE_TEST
+	help
+	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
+	  Qualcomm Technologies Inc TLMM block found on the Qualcomm
+	  Technologies Inc SM8750 platform.
+
 config PINCTRL_X1E80100
 	tristate "Qualcomm Technologies Inc X1E80100 pin controller driver"
 	depends on ARM64 || COMPILE_TEST
diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile
index 51bf41c343803..9a23d41d801c4 100644
--- a/drivers/pinctrl/qcom/Makefile
+++ b/drivers/pinctrl/qcom/Makefile
@@ -66,6 +66,7 @@ obj-$(CONFIG_PINCTRL_SM8550) += pinctrl-sm8550.o
 obj-$(CONFIG_PINCTRL_SM8550_LPASS_LPI) += pinctrl-sm8550-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_SM8650) += pinctrl-sm8650.o
 obj-$(CONFIG_PINCTRL_SM8650_LPASS_LPI) += pinctrl-sm8650-lpass-lpi.o
+obj-$(CONFIG_PINCTRL_SM8750) += pinctrl-sm8750.o
 obj-$(CONFIG_PINCTRL_SC8280XP_LPASS_LPI) += pinctrl-sc8280xp-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_LPASS_LPI) += pinctrl-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_X1E80100)	+= pinctrl-x1e80100.o
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8750.c b/drivers/pinctrl/qcom/pinctrl-sm8750.c
new file mode 100644
index 0000000000000..1af11cd95fb0e
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-sm8750.c
@@ -0,0 +1,1729 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-msm.h"
+
+#define REG_SIZE 0x1000
+
+#define PINGROUP(id, f1, f2, f3, f4, f5, f6, f7, f8, f9, f10, f11)	\
+	{					        \
+		.grp = PINCTRL_PINGROUP("gpio" #id,	\
+			gpio##id##_pins,		\
+			ARRAY_SIZE(gpio##id##_pins)),	\
+		.funcs = (int[]){			\
+			msm_mux_gpio, /* gpio mode */	\
+			msm_mux_##f1,			\
+			msm_mux_##f2,			\
+			msm_mux_##f3,			\
+			msm_mux_##f4,			\
+			msm_mux_##f5,			\
+			msm_mux_##f6,			\
+			msm_mux_##f7,			\
+			msm_mux_##f8,			\
+			msm_mux_##f9,			\
+			msm_mux_##f10,			\
+			msm_mux_##f11 /* egpio mode */	\
+		},					        \
+		.nfuncs = 12,				\
+		.ctl_reg = REG_SIZE * id,                             \
+		.io_reg = 0x4 + REG_SIZE * id,                        \
+		.intr_cfg_reg = 0x8 + REG_SIZE * id,                  \
+		.intr_status_reg = 0xc + REG_SIZE * id,               \
+		.intr_target_reg = 0x8 + REG_SIZE * id,               \
+		.mux_bit = 2,                                         \
+		.pull_bit = 0,                                        \
+		.drv_bit = 6,                                         \
+		.egpio_enable = 12,                                   \
+		.egpio_present = 11,                                  \
+		.oe_bit = 9,                                          \
+		.in_bit = 0,                                          \
+		.out_bit = 1,                                         \
+		.intr_enable_bit = 0,                                 \
+		.intr_status_bit = 0,                                 \
+		.intr_target_bit = 5,                                 \
+		.intr_target_kpss_val = 3,                            \
+		.intr_raw_status_bit = 4,                             \
+		.intr_polarity_bit = 1,                               \
+		.intr_detection_bit = 2,                              \
+		.intr_detection_width = 2,                            \
+	}
+
+#define SDC_QDSD_PINGROUP(pg_name, ctl, pull, drv)                   \
+	{                                                            \
+		.grp = PINCTRL_PINGROUP(#pg_name,                    \
+					pg_name##_pins,              \
+					ARRAY_SIZE(pg_name##_pins)), \
+		.ctl_reg = ctl,                                      \
+		.io_reg = 0,                                         \
+		.intr_cfg_reg = 0,                                   \
+		.intr_status_reg = 0,                                \
+		.intr_target_reg = 0,                                \
+		.mux_bit = -1,                                       \
+		.pull_bit = pull,                                    \
+		.drv_bit = drv,                                      \
+		.oe_bit = -1,                                        \
+		.in_bit = -1,                                        \
+		.out_bit = -1,                                       \
+		.intr_enable_bit = -1,                               \
+		.intr_status_bit = -1,                               \
+		.intr_target_bit = -1,                               \
+		.intr_raw_status_bit = -1,                           \
+		.intr_polarity_bit = -1,                             \
+		.intr_detection_bit = -1,                            \
+		.intr_detection_width = -1,                          \
+	}
+
+#define UFS_RESET(pg_name, ctl, io)			\
+	{					        \
+		.grp = PINCTRL_PINGROUP(#pg_name,	\
+			pg_name##_pins,			\
+			ARRAY_SIZE(pg_name##_pins)),	\
+		.ctl_reg = ctl,				\
+		.io_reg = io,				\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = 3,				\
+		.drv_bit = 0,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = 0,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+static const struct pinctrl_pin_desc sm8750_pins[] = {
+	PINCTRL_PIN(0, "GPIO_0"),
+	PINCTRL_PIN(1, "GPIO_1"),
+	PINCTRL_PIN(2, "GPIO_2"),
+	PINCTRL_PIN(3, "GPIO_3"),
+	PINCTRL_PIN(4, "GPIO_4"),
+	PINCTRL_PIN(5, "GPIO_5"),
+	PINCTRL_PIN(6, "GPIO_6"),
+	PINCTRL_PIN(7, "GPIO_7"),
+	PINCTRL_PIN(8, "GPIO_8"),
+	PINCTRL_PIN(9, "GPIO_9"),
+	PINCTRL_PIN(10, "GPIO_10"),
+	PINCTRL_PIN(11, "GPIO_11"),
+	PINCTRL_PIN(12, "GPIO_12"),
+	PINCTRL_PIN(13, "GPIO_13"),
+	PINCTRL_PIN(14, "GPIO_14"),
+	PINCTRL_PIN(15, "GPIO_15"),
+	PINCTRL_PIN(16, "GPIO_16"),
+	PINCTRL_PIN(17, "GPIO_17"),
+	PINCTRL_PIN(18, "GPIO_18"),
+	PINCTRL_PIN(19, "GPIO_19"),
+	PINCTRL_PIN(20, "GPIO_20"),
+	PINCTRL_PIN(21, "GPIO_21"),
+	PINCTRL_PIN(22, "GPIO_22"),
+	PINCTRL_PIN(23, "GPIO_23"),
+	PINCTRL_PIN(24, "GPIO_24"),
+	PINCTRL_PIN(25, "GPIO_25"),
+	PINCTRL_PIN(26, "GPIO_26"),
+	PINCTRL_PIN(27, "GPIO_27"),
+	PINCTRL_PIN(28, "GPIO_28"),
+	PINCTRL_PIN(29, "GPIO_29"),
+	PINCTRL_PIN(30, "GPIO_30"),
+	PINCTRL_PIN(31, "GPIO_31"),
+	PINCTRL_PIN(32, "GPIO_32"),
+	PINCTRL_PIN(33, "GPIO_33"),
+	PINCTRL_PIN(34, "GPIO_34"),
+	PINCTRL_PIN(35, "GPIO_35"),
+	PINCTRL_PIN(36, "GPIO_36"),
+	PINCTRL_PIN(37, "GPIO_37"),
+	PINCTRL_PIN(38, "GPIO_38"),
+	PINCTRL_PIN(39, "GPIO_39"),
+	PINCTRL_PIN(40, "GPIO_40"),
+	PINCTRL_PIN(41, "GPIO_41"),
+	PINCTRL_PIN(42, "GPIO_42"),
+	PINCTRL_PIN(43, "GPIO_43"),
+	PINCTRL_PIN(44, "GPIO_44"),
+	PINCTRL_PIN(45, "GPIO_45"),
+	PINCTRL_PIN(46, "GPIO_46"),
+	PINCTRL_PIN(47, "GPIO_47"),
+	PINCTRL_PIN(48, "GPIO_48"),
+	PINCTRL_PIN(49, "GPIO_49"),
+	PINCTRL_PIN(50, "GPIO_50"),
+	PINCTRL_PIN(51, "GPIO_51"),
+	PINCTRL_PIN(52, "GPIO_52"),
+	PINCTRL_PIN(53, "GPIO_53"),
+	PINCTRL_PIN(54, "GPIO_54"),
+	PINCTRL_PIN(55, "GPIO_55"),
+	PINCTRL_PIN(56, "GPIO_56"),
+	PINCTRL_PIN(57, "GPIO_57"),
+	PINCTRL_PIN(58, "GPIO_58"),
+	PINCTRL_PIN(59, "GPIO_59"),
+	PINCTRL_PIN(60, "GPIO_60"),
+	PINCTRL_PIN(61, "GPIO_61"),
+	PINCTRL_PIN(62, "GPIO_62"),
+	PINCTRL_PIN(63, "GPIO_63"),
+	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
+	PINCTRL_PIN(69, "GPIO_69"),
+	PINCTRL_PIN(70, "GPIO_70"),
+	PINCTRL_PIN(71, "GPIO_71"),
+	PINCTRL_PIN(72, "GPIO_72"),
+	PINCTRL_PIN(73, "GPIO_73"),
+	PINCTRL_PIN(74, "GPIO_74"),
+	PINCTRL_PIN(75, "GPIO_75"),
+	PINCTRL_PIN(76, "GPIO_76"),
+	PINCTRL_PIN(77, "GPIO_77"),
+	PINCTRL_PIN(78, "GPIO_78"),
+	PINCTRL_PIN(79, "GPIO_79"),
+	PINCTRL_PIN(80, "GPIO_80"),
+	PINCTRL_PIN(81, "GPIO_81"),
+	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
+	PINCTRL_PIN(86, "GPIO_86"),
+	PINCTRL_PIN(87, "GPIO_87"),
+	PINCTRL_PIN(88, "GPIO_88"),
+	PINCTRL_PIN(89, "GPIO_89"),
+	PINCTRL_PIN(90, "GPIO_90"),
+	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93"),
+	PINCTRL_PIN(94, "GPIO_94"),
+	PINCTRL_PIN(95, "GPIO_95"),
+	PINCTRL_PIN(96, "GPIO_96"),
+	PINCTRL_PIN(97, "GPIO_97"),
+	PINCTRL_PIN(98, "GPIO_98"),
+	PINCTRL_PIN(99, "GPIO_99"),
+	PINCTRL_PIN(100, "GPIO_100"),
+	PINCTRL_PIN(101, "GPIO_101"),
+	PINCTRL_PIN(102, "GPIO_102"),
+	PINCTRL_PIN(103, "GPIO_103"),
+	PINCTRL_PIN(104, "GPIO_104"),
+	PINCTRL_PIN(105, "GPIO_105"),
+	PINCTRL_PIN(106, "GPIO_106"),
+	PINCTRL_PIN(107, "GPIO_107"),
+	PINCTRL_PIN(108, "GPIO_108"),
+	PINCTRL_PIN(109, "GPIO_109"),
+	PINCTRL_PIN(110, "GPIO_110"),
+	PINCTRL_PIN(111, "GPIO_111"),
+	PINCTRL_PIN(112, "GPIO_112"),
+	PINCTRL_PIN(113, "GPIO_113"),
+	PINCTRL_PIN(114, "GPIO_114"),
+	PINCTRL_PIN(115, "GPIO_115"),
+	PINCTRL_PIN(116, "GPIO_116"),
+	PINCTRL_PIN(117, "GPIO_117"),
+	PINCTRL_PIN(118, "GPIO_118"),
+	PINCTRL_PIN(119, "GPIO_119"),
+	PINCTRL_PIN(120, "GPIO_120"),
+	PINCTRL_PIN(121, "GPIO_121"),
+	PINCTRL_PIN(122, "GPIO_122"),
+	PINCTRL_PIN(123, "GPIO_123"),
+	PINCTRL_PIN(124, "GPIO_124"),
+	PINCTRL_PIN(125, "GPIO_125"),
+	PINCTRL_PIN(126, "GPIO_126"),
+	PINCTRL_PIN(127, "GPIO_127"),
+	PINCTRL_PIN(128, "GPIO_128"),
+	PINCTRL_PIN(129, "GPIO_129"),
+	PINCTRL_PIN(130, "GPIO_130"),
+	PINCTRL_PIN(131, "GPIO_131"),
+	PINCTRL_PIN(132, "GPIO_132"),
+	PINCTRL_PIN(133, "GPIO_133"),
+	PINCTRL_PIN(134, "GPIO_134"),
+	PINCTRL_PIN(135, "GPIO_135"),
+	PINCTRL_PIN(136, "GPIO_136"),
+	PINCTRL_PIN(137, "GPIO_137"),
+	PINCTRL_PIN(138, "GPIO_138"),
+	PINCTRL_PIN(139, "GPIO_139"),
+	PINCTRL_PIN(140, "GPIO_140"),
+	PINCTRL_PIN(141, "GPIO_141"),
+	PINCTRL_PIN(142, "GPIO_142"),
+	PINCTRL_PIN(143, "GPIO_143"),
+	PINCTRL_PIN(144, "GPIO_144"),
+	PINCTRL_PIN(145, "GPIO_145"),
+	PINCTRL_PIN(146, "GPIO_146"),
+	PINCTRL_PIN(147, "GPIO_147"),
+	PINCTRL_PIN(148, "GPIO_148"),
+	PINCTRL_PIN(149, "GPIO_149"),
+	PINCTRL_PIN(150, "GPIO_150"),
+	PINCTRL_PIN(151, "GPIO_151"),
+	PINCTRL_PIN(152, "GPIO_152"),
+	PINCTRL_PIN(153, "GPIO_153"),
+	PINCTRL_PIN(154, "GPIO_154"),
+	PINCTRL_PIN(155, "GPIO_155"),
+	PINCTRL_PIN(156, "GPIO_156"),
+	PINCTRL_PIN(157, "GPIO_157"),
+	PINCTRL_PIN(158, "GPIO_158"),
+	PINCTRL_PIN(159, "GPIO_159"),
+	PINCTRL_PIN(160, "GPIO_160"),
+	PINCTRL_PIN(161, "GPIO_161"),
+	PINCTRL_PIN(162, "GPIO_162"),
+	PINCTRL_PIN(163, "GPIO_163"),
+	PINCTRL_PIN(164, "GPIO_164"),
+	PINCTRL_PIN(165, "GPIO_165"),
+	PINCTRL_PIN(166, "GPIO_166"),
+	PINCTRL_PIN(167, "GPIO_167"),
+	PINCTRL_PIN(168, "GPIO_168"),
+	PINCTRL_PIN(169, "GPIO_169"),
+	PINCTRL_PIN(170, "GPIO_170"),
+	PINCTRL_PIN(171, "GPIO_171"),
+	PINCTRL_PIN(172, "GPIO_172"),
+	PINCTRL_PIN(173, "GPIO_173"),
+	PINCTRL_PIN(174, "GPIO_174"),
+	PINCTRL_PIN(175, "GPIO_175"),
+	PINCTRL_PIN(176, "GPIO_176"),
+	PINCTRL_PIN(177, "GPIO_177"),
+	PINCTRL_PIN(178, "GPIO_178"),
+	PINCTRL_PIN(179, "GPIO_179"),
+	PINCTRL_PIN(180, "GPIO_180"),
+	PINCTRL_PIN(181, "GPIO_181"),
+	PINCTRL_PIN(182, "GPIO_182"),
+	PINCTRL_PIN(183, "GPIO_183"),
+	PINCTRL_PIN(184, "GPIO_184"),
+	PINCTRL_PIN(185, "GPIO_185"),
+	PINCTRL_PIN(186, "GPIO_186"),
+	PINCTRL_PIN(187, "GPIO_187"),
+	PINCTRL_PIN(188, "GPIO_188"),
+	PINCTRL_PIN(189, "GPIO_189"),
+	PINCTRL_PIN(190, "GPIO_190"),
+	PINCTRL_PIN(191, "GPIO_191"),
+	PINCTRL_PIN(192, "GPIO_192"),
+	PINCTRL_PIN(193, "GPIO_193"),
+	PINCTRL_PIN(194, "GPIO_194"),
+	PINCTRL_PIN(195, "GPIO_195"),
+	PINCTRL_PIN(196, "GPIO_196"),
+	PINCTRL_PIN(197, "GPIO_197"),
+	PINCTRL_PIN(198, "GPIO_198"),
+	PINCTRL_PIN(199, "GPIO_199"),
+	PINCTRL_PIN(200, "GPIO_200"),
+	PINCTRL_PIN(201, "GPIO_201"),
+	PINCTRL_PIN(202, "GPIO_202"),
+	PINCTRL_PIN(203, "GPIO_203"),
+	PINCTRL_PIN(204, "GPIO_204"),
+	PINCTRL_PIN(205, "GPIO_205"),
+	PINCTRL_PIN(206, "GPIO_206"),
+	PINCTRL_PIN(207, "GPIO_207"),
+	PINCTRL_PIN(208, "GPIO_208"),
+	PINCTRL_PIN(209, "GPIO_209"),
+	PINCTRL_PIN(210, "GPIO_210"),
+	PINCTRL_PIN(211, "GPIO_211"),
+	PINCTRL_PIN(212, "GPIO_212"),
+	PINCTRL_PIN(213, "GPIO_213"),
+	PINCTRL_PIN(214, "GPIO_214"),
+	PINCTRL_PIN(215, "UFS_RESET"),
+	PINCTRL_PIN(216, "SDC2_CLK"),
+	PINCTRL_PIN(217, "SDC2_CMD"),
+	PINCTRL_PIN(218, "SDC2_DATA"),
+};
+
+#define DECLARE_MSM_GPIO_PINS(pin) \
+	static const unsigned int gpio##pin##_pins[] = { pin }
+DECLARE_MSM_GPIO_PINS(0);
+DECLARE_MSM_GPIO_PINS(1);
+DECLARE_MSM_GPIO_PINS(2);
+DECLARE_MSM_GPIO_PINS(3);
+DECLARE_MSM_GPIO_PINS(4);
+DECLARE_MSM_GPIO_PINS(5);
+DECLARE_MSM_GPIO_PINS(6);
+DECLARE_MSM_GPIO_PINS(7);
+DECLARE_MSM_GPIO_PINS(8);
+DECLARE_MSM_GPIO_PINS(9);
+DECLARE_MSM_GPIO_PINS(10);
+DECLARE_MSM_GPIO_PINS(11);
+DECLARE_MSM_GPIO_PINS(12);
+DECLARE_MSM_GPIO_PINS(13);
+DECLARE_MSM_GPIO_PINS(14);
+DECLARE_MSM_GPIO_PINS(15);
+DECLARE_MSM_GPIO_PINS(16);
+DECLARE_MSM_GPIO_PINS(17);
+DECLARE_MSM_GPIO_PINS(18);
+DECLARE_MSM_GPIO_PINS(19);
+DECLARE_MSM_GPIO_PINS(20);
+DECLARE_MSM_GPIO_PINS(21);
+DECLARE_MSM_GPIO_PINS(22);
+DECLARE_MSM_GPIO_PINS(23);
+DECLARE_MSM_GPIO_PINS(24);
+DECLARE_MSM_GPIO_PINS(25);
+DECLARE_MSM_GPIO_PINS(26);
+DECLARE_MSM_GPIO_PINS(27);
+DECLARE_MSM_GPIO_PINS(28);
+DECLARE_MSM_GPIO_PINS(29);
+DECLARE_MSM_GPIO_PINS(30);
+DECLARE_MSM_GPIO_PINS(31);
+DECLARE_MSM_GPIO_PINS(32);
+DECLARE_MSM_GPIO_PINS(33);
+DECLARE_MSM_GPIO_PINS(34);
+DECLARE_MSM_GPIO_PINS(35);
+DECLARE_MSM_GPIO_PINS(36);
+DECLARE_MSM_GPIO_PINS(37);
+DECLARE_MSM_GPIO_PINS(38);
+DECLARE_MSM_GPIO_PINS(39);
+DECLARE_MSM_GPIO_PINS(40);
+DECLARE_MSM_GPIO_PINS(41);
+DECLARE_MSM_GPIO_PINS(42);
+DECLARE_MSM_GPIO_PINS(43);
+DECLARE_MSM_GPIO_PINS(44);
+DECLARE_MSM_GPIO_PINS(45);
+DECLARE_MSM_GPIO_PINS(46);
+DECLARE_MSM_GPIO_PINS(47);
+DECLARE_MSM_GPIO_PINS(48);
+DECLARE_MSM_GPIO_PINS(49);
+DECLARE_MSM_GPIO_PINS(50);
+DECLARE_MSM_GPIO_PINS(51);
+DECLARE_MSM_GPIO_PINS(52);
+DECLARE_MSM_GPIO_PINS(53);
+DECLARE_MSM_GPIO_PINS(54);
+DECLARE_MSM_GPIO_PINS(55);
+DECLARE_MSM_GPIO_PINS(56);
+DECLARE_MSM_GPIO_PINS(57);
+DECLARE_MSM_GPIO_PINS(58);
+DECLARE_MSM_GPIO_PINS(59);
+DECLARE_MSM_GPIO_PINS(60);
+DECLARE_MSM_GPIO_PINS(61);
+DECLARE_MSM_GPIO_PINS(62);
+DECLARE_MSM_GPIO_PINS(63);
+DECLARE_MSM_GPIO_PINS(64);
+DECLARE_MSM_GPIO_PINS(65);
+DECLARE_MSM_GPIO_PINS(66);
+DECLARE_MSM_GPIO_PINS(67);
+DECLARE_MSM_GPIO_PINS(68);
+DECLARE_MSM_GPIO_PINS(69);
+DECLARE_MSM_GPIO_PINS(70);
+DECLARE_MSM_GPIO_PINS(71);
+DECLARE_MSM_GPIO_PINS(72);
+DECLARE_MSM_GPIO_PINS(73);
+DECLARE_MSM_GPIO_PINS(74);
+DECLARE_MSM_GPIO_PINS(75);
+DECLARE_MSM_GPIO_PINS(76);
+DECLARE_MSM_GPIO_PINS(77);
+DECLARE_MSM_GPIO_PINS(78);
+DECLARE_MSM_GPIO_PINS(79);
+DECLARE_MSM_GPIO_PINS(80);
+DECLARE_MSM_GPIO_PINS(81);
+DECLARE_MSM_GPIO_PINS(82);
+DECLARE_MSM_GPIO_PINS(83);
+DECLARE_MSM_GPIO_PINS(84);
+DECLARE_MSM_GPIO_PINS(85);
+DECLARE_MSM_GPIO_PINS(86);
+DECLARE_MSM_GPIO_PINS(87);
+DECLARE_MSM_GPIO_PINS(88);
+DECLARE_MSM_GPIO_PINS(89);
+DECLARE_MSM_GPIO_PINS(90);
+DECLARE_MSM_GPIO_PINS(91);
+DECLARE_MSM_GPIO_PINS(92);
+DECLARE_MSM_GPIO_PINS(93);
+DECLARE_MSM_GPIO_PINS(94);
+DECLARE_MSM_GPIO_PINS(95);
+DECLARE_MSM_GPIO_PINS(96);
+DECLARE_MSM_GPIO_PINS(97);
+DECLARE_MSM_GPIO_PINS(98);
+DECLARE_MSM_GPIO_PINS(99);
+DECLARE_MSM_GPIO_PINS(100);
+DECLARE_MSM_GPIO_PINS(101);
+DECLARE_MSM_GPIO_PINS(102);
+DECLARE_MSM_GPIO_PINS(103);
+DECLARE_MSM_GPIO_PINS(104);
+DECLARE_MSM_GPIO_PINS(105);
+DECLARE_MSM_GPIO_PINS(106);
+DECLARE_MSM_GPIO_PINS(107);
+DECLARE_MSM_GPIO_PINS(108);
+DECLARE_MSM_GPIO_PINS(109);
+DECLARE_MSM_GPIO_PINS(110);
+DECLARE_MSM_GPIO_PINS(111);
+DECLARE_MSM_GPIO_PINS(112);
+DECLARE_MSM_GPIO_PINS(113);
+DECLARE_MSM_GPIO_PINS(114);
+DECLARE_MSM_GPIO_PINS(115);
+DECLARE_MSM_GPIO_PINS(116);
+DECLARE_MSM_GPIO_PINS(117);
+DECLARE_MSM_GPIO_PINS(118);
+DECLARE_MSM_GPIO_PINS(119);
+DECLARE_MSM_GPIO_PINS(120);
+DECLARE_MSM_GPIO_PINS(121);
+DECLARE_MSM_GPIO_PINS(122);
+DECLARE_MSM_GPIO_PINS(123);
+DECLARE_MSM_GPIO_PINS(124);
+DECLARE_MSM_GPIO_PINS(125);
+DECLARE_MSM_GPIO_PINS(126);
+DECLARE_MSM_GPIO_PINS(127);
+DECLARE_MSM_GPIO_PINS(128);
+DECLARE_MSM_GPIO_PINS(129);
+DECLARE_MSM_GPIO_PINS(130);
+DECLARE_MSM_GPIO_PINS(131);
+DECLARE_MSM_GPIO_PINS(132);
+DECLARE_MSM_GPIO_PINS(133);
+DECLARE_MSM_GPIO_PINS(134);
+DECLARE_MSM_GPIO_PINS(135);
+DECLARE_MSM_GPIO_PINS(136);
+DECLARE_MSM_GPIO_PINS(137);
+DECLARE_MSM_GPIO_PINS(138);
+DECLARE_MSM_GPIO_PINS(139);
+DECLARE_MSM_GPIO_PINS(140);
+DECLARE_MSM_GPIO_PINS(141);
+DECLARE_MSM_GPIO_PINS(142);
+DECLARE_MSM_GPIO_PINS(143);
+DECLARE_MSM_GPIO_PINS(144);
+DECLARE_MSM_GPIO_PINS(145);
+DECLARE_MSM_GPIO_PINS(146);
+DECLARE_MSM_GPIO_PINS(147);
+DECLARE_MSM_GPIO_PINS(148);
+DECLARE_MSM_GPIO_PINS(149);
+DECLARE_MSM_GPIO_PINS(150);
+DECLARE_MSM_GPIO_PINS(151);
+DECLARE_MSM_GPIO_PINS(152);
+DECLARE_MSM_GPIO_PINS(153);
+DECLARE_MSM_GPIO_PINS(154);
+DECLARE_MSM_GPIO_PINS(155);
+DECLARE_MSM_GPIO_PINS(156);
+DECLARE_MSM_GPIO_PINS(157);
+DECLARE_MSM_GPIO_PINS(158);
+DECLARE_MSM_GPIO_PINS(159);
+DECLARE_MSM_GPIO_PINS(160);
+DECLARE_MSM_GPIO_PINS(161);
+DECLARE_MSM_GPIO_PINS(162);
+DECLARE_MSM_GPIO_PINS(163);
+DECLARE_MSM_GPIO_PINS(164);
+DECLARE_MSM_GPIO_PINS(165);
+DECLARE_MSM_GPIO_PINS(166);
+DECLARE_MSM_GPIO_PINS(167);
+DECLARE_MSM_GPIO_PINS(168);
+DECLARE_MSM_GPIO_PINS(169);
+DECLARE_MSM_GPIO_PINS(170);
+DECLARE_MSM_GPIO_PINS(171);
+DECLARE_MSM_GPIO_PINS(172);
+DECLARE_MSM_GPIO_PINS(173);
+DECLARE_MSM_GPIO_PINS(174);
+DECLARE_MSM_GPIO_PINS(175);
+DECLARE_MSM_GPIO_PINS(176);
+DECLARE_MSM_GPIO_PINS(177);
+DECLARE_MSM_GPIO_PINS(178);
+DECLARE_MSM_GPIO_PINS(179);
+DECLARE_MSM_GPIO_PINS(180);
+DECLARE_MSM_GPIO_PINS(181);
+DECLARE_MSM_GPIO_PINS(182);
+DECLARE_MSM_GPIO_PINS(183);
+DECLARE_MSM_GPIO_PINS(184);
+DECLARE_MSM_GPIO_PINS(185);
+DECLARE_MSM_GPIO_PINS(186);
+DECLARE_MSM_GPIO_PINS(187);
+DECLARE_MSM_GPIO_PINS(188);
+DECLARE_MSM_GPIO_PINS(189);
+DECLARE_MSM_GPIO_PINS(190);
+DECLARE_MSM_GPIO_PINS(191);
+DECLARE_MSM_GPIO_PINS(192);
+DECLARE_MSM_GPIO_PINS(193);
+DECLARE_MSM_GPIO_PINS(194);
+DECLARE_MSM_GPIO_PINS(195);
+DECLARE_MSM_GPIO_PINS(196);
+DECLARE_MSM_GPIO_PINS(197);
+DECLARE_MSM_GPIO_PINS(198);
+DECLARE_MSM_GPIO_PINS(199);
+DECLARE_MSM_GPIO_PINS(200);
+DECLARE_MSM_GPIO_PINS(201);
+DECLARE_MSM_GPIO_PINS(202);
+DECLARE_MSM_GPIO_PINS(203);
+DECLARE_MSM_GPIO_PINS(204);
+DECLARE_MSM_GPIO_PINS(205);
+DECLARE_MSM_GPIO_PINS(206);
+DECLARE_MSM_GPIO_PINS(207);
+DECLARE_MSM_GPIO_PINS(208);
+DECLARE_MSM_GPIO_PINS(209);
+DECLARE_MSM_GPIO_PINS(210);
+DECLARE_MSM_GPIO_PINS(211);
+DECLARE_MSM_GPIO_PINS(212);
+DECLARE_MSM_GPIO_PINS(213);
+DECLARE_MSM_GPIO_PINS(214);
+
+static const unsigned int ufs_reset_pins[] = { 215 };
+static const unsigned int sdc2_clk_pins[] = { 216 };
+static const unsigned int sdc2_cmd_pins[] = { 217 };
+static const unsigned int sdc2_data_pins[] = { 218 };
+
+enum sm8750_functions {
+	msm_mux_gpio,
+	msm_mux_aoss_cti,
+	msm_mux_atest_char,
+	msm_mux_atest_usb,
+	msm_mux_audio_ext_mclk0,
+	msm_mux_audio_ext_mclk1,
+	msm_mux_audio_ref_clk,
+	msm_mux_cam_aon_mclk2,
+	msm_mux_cam_aon_mclk4,
+	msm_mux_cam_mclk,
+	msm_mux_cci_async_in,
+	msm_mux_cci_i2c_scl,
+	msm_mux_cci_i2c_sda,
+	msm_mux_cci_timer,
+	msm_mux_cmu_rng,
+	msm_mux_coex_uart1_rx,
+	msm_mux_coex_uart1_tx,
+	msm_mux_coex_uart2_rx,
+	msm_mux_coex_uart2_tx,
+	msm_mux_dbg_out_clk,
+	msm_mux_ddr_bist_complete,
+	msm_mux_ddr_bist_fail,
+	msm_mux_ddr_bist_start,
+	msm_mux_ddr_bist_stop,
+	msm_mux_ddr_pxi0,
+	msm_mux_ddr_pxi1,
+	msm_mux_ddr_pxi2,
+	msm_mux_ddr_pxi3,
+	msm_mux_dp_hot,
+	msm_mux_egpio,
+	msm_mux_gcc_gp1,
+	msm_mux_gcc_gp2,
+	msm_mux_gcc_gp3,
+	msm_mux_gnss_adc0,
+	msm_mux_gnss_adc1,
+	msm_mux_i2chub0_se0,
+	msm_mux_i2chub0_se1,
+	msm_mux_i2chub0_se2,
+	msm_mux_i2chub0_se3,
+	msm_mux_i2chub0_se4,
+	msm_mux_i2chub0_se5,
+	msm_mux_i2chub0_se6,
+	msm_mux_i2chub0_se7,
+	msm_mux_i2chub0_se8,
+	msm_mux_i2chub0_se9,
+	msm_mux_i2s0_data0,
+	msm_mux_i2s0_data1,
+	msm_mux_i2s0_sck,
+	msm_mux_i2s0_ws,
+	msm_mux_i2s1_data0,
+	msm_mux_i2s1_data1,
+	msm_mux_i2s1_sck,
+	msm_mux_i2s1_ws,
+	msm_mux_ibi_i3c,
+	msm_mux_jitter_bist,
+	msm_mux_mdp_esync0_out,
+	msm_mux_mdp_esync1_out,
+	msm_mux_mdp_vsync,
+	msm_mux_mdp_vsync0_out,
+	msm_mux_mdp_vsync1_out,
+	msm_mux_mdp_vsync2_out,
+	msm_mux_mdp_vsync3_out,
+	msm_mux_mdp_vsync5_out,
+	msm_mux_mdp_vsync_e,
+	msm_mux_nav_gpio0,
+	msm_mux_nav_gpio1,
+	msm_mux_nav_gpio2,
+	msm_mux_nav_gpio3,
+	msm_mux_pcie0_clk_req_n,
+	msm_mux_phase_flag,
+	msm_mux_pll_bist_sync,
+	msm_mux_pll_clk_aux,
+	msm_mux_prng_rosc0,
+	msm_mux_prng_rosc1,
+	msm_mux_prng_rosc2,
+	msm_mux_prng_rosc3,
+	msm_mux_qdss_cti,
+	msm_mux_qlink_big_enable,
+	msm_mux_qlink_big_request,
+	msm_mux_qlink_little_enable,
+	msm_mux_qlink_little_request,
+	msm_mux_qlink_wmss,
+	msm_mux_qspi0,
+	msm_mux_qspi1,
+	msm_mux_qspi2,
+	msm_mux_qspi3,
+	msm_mux_qspi_clk,
+	msm_mux_qspi_cs,
+	msm_mux_qup1_se0,
+	msm_mux_qup1_se1,
+	msm_mux_qup1_se2,
+	msm_mux_qup1_se3,
+	msm_mux_qup1_se4,
+	msm_mux_qup1_se5,
+	msm_mux_qup1_se6,
+	msm_mux_qup1_se7,
+	msm_mux_qup2_se0,
+	msm_mux_qup2_se1,
+	msm_mux_qup2_se2,
+	msm_mux_qup2_se3,
+	msm_mux_qup2_se4,
+	msm_mux_qup2_se5,
+	msm_mux_qup2_se6,
+	msm_mux_qup2_se7,
+	msm_mux_sd_write_protect,
+	msm_mux_sdc40,
+	msm_mux_sdc41,
+	msm_mux_sdc42,
+	msm_mux_sdc43,
+	msm_mux_sdc4_clk,
+	msm_mux_sdc4_cmd,
+	msm_mux_tb_trig_sdc2,
+	msm_mux_tb_trig_sdc4,
+	msm_mux_tmess_prng0,
+	msm_mux_tmess_prng1,
+	msm_mux_tmess_prng2,
+	msm_mux_tmess_prng3,
+	msm_mux_tsense_pwm1,
+	msm_mux_tsense_pwm2,
+	msm_mux_tsense_pwm3,
+	msm_mux_tsense_pwm4,
+	msm_mux_uim0_clk,
+	msm_mux_uim0_data,
+	msm_mux_uim0_present,
+	msm_mux_uim0_reset,
+	msm_mux_uim1_clk,
+	msm_mux_uim1_data,
+	msm_mux_uim1_present,
+	msm_mux_uim1_reset,
+	msm_mux_usb1_hs,
+	msm_mux_usb_phy,
+	msm_mux_vfr_0,
+	msm_mux_vfr_1,
+	msm_mux_vsense_trigger_mirnat,
+	msm_mux_wcn_sw,
+	msm_mux_wcn_sw_ctrl,
+	msm_mux__,
+};
+
+static const char *const gpio_groups[] = {
+	"gpio0",   "gpio1",   "gpio2",	 "gpio3",   "gpio4",   "gpio5",
+	"gpio6",   "gpio7",   "gpio8",	 "gpio9",   "gpio10",  "gpio11",
+	"gpio12",  "gpio13",  "gpio14",	 "gpio15",  "gpio16",  "gpio17",
+	"gpio18",  "gpio19",  "gpio20",	 "gpio21",  "gpio22",  "gpio23",
+	"gpio24",  "gpio25",  "gpio26",	 "gpio27",  "gpio28",  "gpio29",
+	"gpio30",  "gpio31",  "gpio32",	 "gpio33",  "gpio34",  "gpio35",
+	"gpio36",  "gpio37",  "gpio38",	 "gpio39",  "gpio40",  "gpio41",
+	"gpio42",  "gpio43",  "gpio44",	 "gpio45",  "gpio46",  "gpio47",
+	"gpio48", "gpio49", "gpio50", "gpio51", "gpio52", "gpio53",
+	"gpio54", "gpio55", "gpio56", "gpio57", "gpio58", "gpio59",
+	"gpio60", "gpio61", "gpio62", "gpio63", "gpio64", "gpio65",
+	"gpio66",  "gpio67",  "gpio68",	 "gpio69",  "gpio70",  "gpio71",
+	"gpio72",  "gpio73",  "gpio74",	 "gpio75",  "gpio76",  "gpio77",
+	"gpio78",  "gpio79",  "gpio80",	 "gpio81",  "gpio82",  "gpio83",
+	"gpio84",  "gpio85",  "gpio86",	 "gpio87",  "gpio88",  "gpio89",
+	"gpio90",  "gpio91",  "gpio92",	 "gpio93",  "gpio94",  "gpio95",
+	"gpio96",  "gpio97",  "gpio98",	 "gpio99",  "gpio100", "gpio101",
+	"gpio102", "gpio103", "gpio104", "gpio105", "gpio106", "gpio107",
+	"gpio108", "gpio109", "gpio110", "gpio111", "gpio112", "gpio113",
+	"gpio114", "gpio115", "gpio116", "gpio117", "gpio118", "gpio119",
+	"gpio120", "gpio121", "gpio122", "gpio123", "gpio124", "gpio125",
+	"gpio126", "gpio127", "gpio128", "gpio129", "gpio130", "gpio131",
+	"gpio132", "gpio133", "gpio134", "gpio135", "gpio136", "gpio137",
+	"gpio138", "gpio139", "gpio140", "gpio141", "gpio142", "gpio143",
+	"gpio144", "gpio145", "gpio146", "gpio147", "gpio148", "gpio149",
+	"gpio150", "gpio151", "gpio152", "gpio153", "gpio154", "gpio155",
+	"gpio156", "gpio157", "gpio158", "gpio159", "gpio160", "gpio161",
+	"gpio162", "gpio163", "gpio164", "gpio165", "gpio166", "gpio167",
+	"gpio168", "gpio169", "gpio170", "gpio171", "gpio172", "gpio173",
+	"gpio174", "gpio175", "gpio176", "gpio177", "gpio178", "gpio179",
+	"gpio180", "gpio181", "gpio182", "gpio183", "gpio184", "gpio185",
+	"gpio186", "gpio187", "gpio188", "gpio189", "gpio190", "gpio191",
+	"gpio192", "gpio193", "gpio194", "gpio195", "gpio196", "gpio197",
+	"gpio198", "gpio199", "gpio200", "gpio201", "gpio202", "gpio203",
+	"gpio204", "gpio205", "gpio206", "gpio207", "gpio208", "gpio209",
+	"gpio210", "gpio211", "gpio212", "gpio213", "gpio214",
+};
+
+static const char *const egpio_groups[] = {
+	"gpio0",   "gpio1",   "gpio2",	 "gpio3",   "gpio4",   "gpio5",
+	"gpio6",   "gpio7",   "gpio32",	 "gpio33",  "gpio34",  "gpio35",
+	"gpio36",  "gpio37",  "gpio105", "gpio106", "gpio107", "gpio108",
+	"gpio165", "gpio166", "gpio167", "gpio168", "gpio169", "gpio170",
+	"gpio171", "gpio172", "gpio173", "gpio174", "gpio175", "gpio176",
+	"gpio177", "gpio178", "gpio179", "gpio180", "gpio181", "gpio182",
+	"gpio183", "gpio184", "gpio185", "gpio186", "gpio187", "gpio188",
+	"gpio189", "gpio190", "gpio191", "gpio192", "gpio193", "gpio194",
+	"gpio195", "gpio196", "gpio197", "gpio198", "gpio199", "gpio200",
+	"gpio201", "gpio202", "gpio203", "gpio204", "gpio205", "gpio206",
+	"gpio207", "gpio208", "gpio209", "gpio210", "gpio211", "gpio212",
+	"gpio213", "gpio214",
+};
+
+static const char *const aoss_cti_groups[] = {
+	"gpio50", "gpio51", "gpio60", "gpio61",
+};
+
+static const char *const atest_char_groups[] = {
+	"gpio130", "gpio131", "gpio132", "gpio133", "gpio137",
+};
+
+static const char *const atest_usb_groups[] = {
+	"gpio70", "gpio71", "gpio72", "gpio73", "gpio76",
+};
+
+static const char *const audio_ext_mclk0_groups[] = {
+	"gpio125",
+};
+
+static const char *const audio_ext_mclk1_groups[] = {
+	"gpio124",
+};
+
+static const char *const audio_ref_clk_groups[] = {
+	"gpio124",
+};
+
+static const char *const cam_aon_mclk2_groups[] = {
+	"gpio91",
+};
+
+static const char *const cam_aon_mclk4_groups[] = {
+	"gpio93",
+};
+
+static const char *const cam_mclk_groups[] = {
+	"gpio89", "gpio90", "gpio92", "gpio94", "gpio95", "gpio96",
+};
+
+static const char *const cci_async_in_groups[] = {
+	"gpio10", "gpio11", "gpio15",
+};
+
+static const char *const cci_i2c_scl_groups[] = {
+	"gpio114", "gpio116", "gpio118", "gpio120", "gpio153", "gpio164",
+};
+
+static const char *const cci_i2c_sda_groups[] = {
+	"gpio111", "gpio112", "gpio113", "gpio115", "gpio117", "gpio119",
+};
+
+static const char *const cci_timer_groups[] = {
+	"gpio109", "gpio110", "gpio111", "gpio163", "gpio164",
+};
+
+static const char *const cmu_rng_groups[] = {
+	"gpio40", "gpio41", "gpio41", "gpio43", "gpio148", "gpio149",
+	"gpio150", "gpio151",
+};
+
+static const char *const coex_uart1_rx_groups[] = {
+	"gpio148",
+};
+
+static const char *const coex_uart1_tx_groups[] = {
+	"gpio149",
+};
+
+static const char *const coex_uart2_rx_groups[] = {
+	"gpio150",
+};
+
+static const char *const coex_uart2_tx_groups[] = {
+	"gpio151",
+};
+
+static const char *const dbg_out_clk_groups[] = {
+	"gpio78",
+};
+
+static const char *const ddr_bist_complete_groups[] = {
+	"gpio44",
+};
+
+static const char *const ddr_bist_fail_groups[] = {
+	"gpio40",
+};
+
+static const char *const ddr_bist_start_groups[] = {
+	"gpio41",
+};
+
+static const char *const ddr_bist_stop_groups[] = {
+	"gpio45",
+};
+
+static const char *const ddr_pxi0_groups[] = {
+	"gpio54", "gpio55",
+};
+
+static const char *const ddr_pxi1_groups[] = {
+	"gpio44", "gpio45",
+};
+
+static const char *const ddr_pxi2_groups[] = {
+	"gpio43", "gpio52",
+};
+
+static const char *const ddr_pxi3_groups[] = {
+	"gpio46", "gpio53",
+};
+
+static const char *const dp_hot_groups[] = {
+	"gpio47",
+};
+
+static const char *const gcc_gp1_groups[] = {
+	"gpio86", "gpio134",
+};
+
+static const char *const gcc_gp2_groups[] = {
+	"gpio87", "gpio135",
+};
+
+static const char *const gcc_gp3_groups[] = {
+	"gpio88", "gpio136",
+};
+
+static const char *const gnss_adc0_groups[] = {
+	"gpio78", "gpio79",
+};
+
+static const char *const gnss_adc1_groups[] = {
+	"gpio77", "gpio99",
+};
+
+static const char *const i2chub0_se0_groups[] = {
+	"gpio64", "gpio65",
+};
+
+static const char *const i2chub0_se1_groups[] = {
+	"gpio66", "gpio67",
+};
+
+static const char *const i2chub0_se2_groups[] = {
+	"gpio68", "gpio69",
+};
+
+static const char *const i2chub0_se3_groups[] = {
+	"gpio70", "gpio71",
+};
+
+static const char *const i2chub0_se4_groups[] = {
+	"gpio72", "gpio73",
+};
+
+static const char *const i2chub0_se5_groups[] = {
+	"gpio74", "gpio75",
+};
+
+static const char *const i2chub0_se6_groups[] = {
+	"gpio76", "gpio77",
+};
+
+static const char *const i2chub0_se7_groups[] = {
+	"gpio82", "gpio83",
+};
+
+static const char *const i2chub0_se8_groups[] = {
+	"gpio206", "gpio207",
+};
+
+static const char *const i2chub0_se9_groups[] = {
+	"gpio80", "gpio81",
+};
+
+static const char *const i2s0_data0_groups[] = {
+	"gpio127",
+};
+
+static const char *const i2s0_data1_groups[] = {
+	"gpio128",
+};
+
+static const char *const i2s0_sck_groups[] = {
+	"gpio126",
+};
+
+static const char *const i2s0_ws_groups[] = {
+	"gpio129",
+};
+
+static const char *const i2s1_data0_groups[] = {
+	"gpio122",
+};
+
+static const char *const i2s1_data1_groups[] = {
+	"gpio124",
+};
+
+static const char *const i2s1_sck_groups[] = {
+	"gpio121",
+};
+
+static const char *const i2s1_ws_groups[] = {
+	"gpio123",
+};
+
+static const char *const ibi_i3c_groups[] = {
+	"gpio0",  "gpio1",  "gpio4",  "gpio5",	"gpio8",  "gpio9",
+	"gpio12", "gpio13", "gpio28", "gpio29", "gpio32", "gpio33",
+	"gpio36", "gpio37", "gpio48", "gpio49",
+};
+
+static const char *const jitter_bist_groups[] = {
+	"gpio73",
+};
+
+static const char *const mdp_esync0_out_groups[] = {
+	"gpio88",
+};
+
+static const char *const mdp_esync1_out_groups[] = {
+	"gpio100",
+};
+
+static const char *const mdp_vsync_groups[] = {
+	"gpio86", "gpio87", "gpio97", "gpio98",
+};
+
+static const char *const mdp_vsync0_out_groups[] = {
+	"gpio86",
+};
+
+static const char *const mdp_vsync1_out_groups[] = {
+	"gpio86",
+};
+
+static const char *const mdp_vsync2_out_groups[] = {
+	"gpio87",
+};
+
+static const char *const mdp_vsync3_out_groups[] = {
+	"gpio87",
+};
+
+static const char *const mdp_vsync5_out_groups[] = {
+	"gpio87",
+};
+
+static const char *const mdp_vsync_e_groups[] = {
+	"gpio88",
+};
+
+static const char *const nav_gpio0_groups[] = {
+	"gpio154",
+};
+
+static const char *const nav_gpio1_groups[] = {
+	"gpio155",
+};
+
+static const char *const nav_gpio2_groups[] = {
+	"gpio152",
+};
+
+static const char *const nav_gpio3_groups[] = {
+	"gpio154",
+};
+
+static const char *const pcie0_clk_req_n_groups[] = {
+	"gpio103",
+};
+
+static const char *const phase_flag_groups[] = {
+	"gpio10", "gpio11", "gpio14", "gpio15", "gpio16", "gpio17", "gpio18",
+	"gpio19", "gpio20", "gpio21", "gpio22", "gpio23", "gpio24", "gpio25",
+	"gpio26", "gpio27", "gpio28", "gpio29", "gpio31", "gpio64", "gpio65",
+	"gpio66", "gpio67", "gpio68", "gpio69", "gpio82", "gpio83", "gpio85",
+	"gpio101", "gpio102", "gpio103", "gpio104",
+};
+
+static const char *const pll_bist_sync_groups[] = {
+	"gpio104",
+};
+
+static const char *const pll_clk_aux_groups[] = {
+	"gpio95",
+};
+
+static const char *const prng_rosc0_groups[] = {
+	"gpio85",
+};
+
+static const char *const prng_rosc1_groups[] = {
+	"gpio64",
+};
+
+static const char *const prng_rosc2_groups[] = {
+	"gpio65",
+};
+
+static const char *const prng_rosc3_groups[] = {
+	"gpio66",
+};
+
+static const char *const qdss_cti_groups[] = {
+	"gpio27", "gpio31", "gpio72",  "gpio73", "gpio82", "gpio83", "gpio159",
+	"gpio162",
+};
+
+static const char *const qlink_big_enable_groups[] = {
+	"gpio160",
+};
+
+static const char *const qlink_big_request_groups[] = {
+	"gpio159",
+};
+
+static const char *const qlink_little_enable_groups[] = {
+	"gpio157",
+};
+
+static const char *const qlink_little_request_groups[] = {
+	"gpio156",
+};
+
+static const char *const qlink_wmss_groups[] = {
+	"gpio158",
+};
+
+static const char *const qspi0_groups[] = {
+	"gpio52",
+};
+
+static const char *const qspi1_groups[] = {
+	"gpio53",
+};
+
+static const char *const qspi2_groups[] = {
+	"gpio55",
+};
+
+static const char *const qspi3_groups[] = {
+	"gpio56",
+};
+
+static const char *const qspi_clk_groups[] = {
+	"gpio54",
+};
+
+static const char *const qspi_cs_groups[] = {
+	"gpio57", "gpio58",
+};
+
+static const char *const qup1_se0_groups[] = {
+	"gpio32", "gpio33", "gpio34", "gpio35",
+};
+
+static const char *const qup1_se1_groups[] = {
+	"gpio36", "gpio37", "gpio38", "gpio39",
+};
+
+static const char *const qup1_se2_groups[] = {
+	"gpio40", "gpio41", "gpio42", "gpio43", "gpio134", "gpio135", "gpio136",
+};
+
+static const char *const qup1_se3_groups[] = {
+	"gpio44", "gpio45", "gpio46", "gpio47",
+};
+
+static const char *const qup1_se4_groups[] = {
+	"gpio48", "gpio49", "gpio50", "gpio51",
+};
+
+static const char *const qup1_se5_groups[] = {
+	"gpio52", "gpio53", "gpio54", "gpio55",
+};
+
+static const char *const qup1_se6_groups[] = {
+	"gpio56", "gpio57", "gpio58", "gpio59",
+};
+
+static const char *const qup1_se7_groups[] = {
+	"gpio60", "gpio61", "gpio62", "gpio63",
+};
+
+static const char *const qup2_se0_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3",
+};
+
+static const char *const qup2_se1_groups[] = {
+	"gpio4", "gpio5", "gpio6", "gpio7",
+};
+
+static const char *const qup2_se2_groups[] = {
+	"gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio15",
+};
+
+static const char *const qup2_se3_groups[] = {
+	"gpio12", "gpio13", "gpio14", "gpio15",
+};
+
+static const char *const qup2_se4_groups[] = {
+	"gpio16", "gpio17", "gpio18", "gpio19",
+};
+
+static const char *const qup2_se5_groups[] = {
+	"gpio20", "gpio21", "gpio22", "gpio23",
+};
+
+static const char *const qup2_se6_groups[] = {
+	"gpio24", "gpio25", "gpio26", "gpio27",
+};
+
+static const char *const qup2_se7_groups[] = {
+	"gpio28", "gpio29", "gpio30", "gpio31",
+};
+
+static const char *const sd_write_protect_groups[] = {
+	"gpio85",
+};
+
+static const char *const sdc40_groups[] = {
+	"gpio36", "gpio49",
+};
+
+static const char *const sdc41_groups[] = {
+	"gpio37", "gpio51",
+};
+
+static const char *const sdc42_groups[] = {
+	"gpio38", "gpio60",
+};
+
+static const char *const sdc43_groups[] = {
+	"gpio39", "gpio61",
+};
+
+static const char *const sdc4_clk_groups[] = {
+	"gpio50", "gpio150",
+};
+
+static const char *const sdc4_cmd_groups[] = {
+	"gpio48", "gpio151",
+};
+
+static const char *const tb_trig_sdc2_groups[] = {
+	"gpio89",
+};
+
+static const char *const tb_trig_sdc4_groups[] = {
+	"gpio147",
+};
+
+static const char *const tmess_prng0_groups[] = {
+	"gpio85",
+};
+
+static const char *const tmess_prng1_groups[] = {
+	"gpio64",
+};
+
+static const char *const tmess_prng2_groups[] = {
+	"gpio65",
+};
+
+static const char *const tmess_prng3_groups[] = {
+	"gpio66",
+};
+
+static const char *const tsense_pwm1_groups[] = {
+	"gpio57",
+};
+
+static const char *const tsense_pwm2_groups[] = {
+	"gpio57",
+};
+
+static const char *const tsense_pwm3_groups[] = {
+	"gpio57",
+};
+
+static const char *const tsense_pwm4_groups[] = {
+	"gpio57",
+};
+
+static const char *const uim0_clk_groups[] = {
+	"gpio131",
+};
+
+static const char *const uim0_data_groups[] = {
+	"gpio130",
+};
+
+static const char *const uim0_present_groups[] = {
+	"gpio133",
+};
+
+static const char *const uim0_reset_groups[] = {
+	"gpio132",
+};
+
+static const char *const uim1_clk_groups[] = {
+	"gpio37", "gpio55", "gpio71", "gpio135",
+};
+
+static const char *const uim1_data_groups[] = {
+	"gpio134", "gpio36", "gpio54", "gpio70",
+};
+
+static const char *const uim1_present_groups[] = {
+	"gpio137",
+};
+
+static const char *const uim1_reset_groups[] = {
+	"gpio39", "gpio56", "gpio72", "gpio136",
+};
+
+static const char *const usb1_hs_groups[] = {
+	"gpio79",
+};
+
+static const char *const usb_phy_groups[] = {
+	"gpio59", "gpio61",
+};
+
+static const char *const vfr_0_groups[] = {
+	"gpio150",
+};
+
+static const char *const vfr_1_groups[] = {
+	"gpio155",
+};
+
+static const char *const vsense_trigger_mirnat_groups[] = {
+	"gpio59",
+};
+
+static const char *const wcn_sw_groups[] = {
+	"gpio19",
+};
+
+static const char *const wcn_sw_ctrl_groups[] = {
+	"gpio18",
+};
+
+static const struct pinfunction sm8750_functions[] = {
+	MSM_PIN_FUNCTION(gpio),
+	MSM_PIN_FUNCTION(aoss_cti),
+	MSM_PIN_FUNCTION(atest_char),
+	MSM_PIN_FUNCTION(atest_usb),
+	MSM_PIN_FUNCTION(audio_ext_mclk0),
+	MSM_PIN_FUNCTION(audio_ext_mclk1),
+	MSM_PIN_FUNCTION(audio_ref_clk),
+	MSM_PIN_FUNCTION(cam_aon_mclk2),
+	MSM_PIN_FUNCTION(cam_aon_mclk4),
+	MSM_PIN_FUNCTION(cam_mclk),
+	MSM_PIN_FUNCTION(cci_async_in),
+	MSM_PIN_FUNCTION(cci_i2c_scl),
+	MSM_PIN_FUNCTION(cci_i2c_sda),
+	MSM_PIN_FUNCTION(cci_timer),
+	MSM_PIN_FUNCTION(cmu_rng),
+	MSM_PIN_FUNCTION(coex_uart1_rx),
+	MSM_PIN_FUNCTION(coex_uart1_tx),
+	MSM_PIN_FUNCTION(coex_uart2_rx),
+	MSM_PIN_FUNCTION(coex_uart2_tx),
+	MSM_PIN_FUNCTION(dbg_out_clk),
+	MSM_PIN_FUNCTION(ddr_bist_complete),
+	MSM_PIN_FUNCTION(ddr_bist_fail),
+	MSM_PIN_FUNCTION(ddr_bist_start),
+	MSM_PIN_FUNCTION(ddr_bist_stop),
+	MSM_PIN_FUNCTION(ddr_pxi0),
+	MSM_PIN_FUNCTION(ddr_pxi1),
+	MSM_PIN_FUNCTION(ddr_pxi2),
+	MSM_PIN_FUNCTION(ddr_pxi3),
+	MSM_PIN_FUNCTION(dp_hot),
+	MSM_PIN_FUNCTION(egpio),
+	MSM_PIN_FUNCTION(gcc_gp1),
+	MSM_PIN_FUNCTION(gcc_gp2),
+	MSM_PIN_FUNCTION(gcc_gp3),
+	MSM_PIN_FUNCTION(gnss_adc0),
+	MSM_PIN_FUNCTION(gnss_adc1),
+	MSM_PIN_FUNCTION(i2chub0_se0),
+	MSM_PIN_FUNCTION(i2chub0_se1),
+	MSM_PIN_FUNCTION(i2chub0_se2),
+	MSM_PIN_FUNCTION(i2chub0_se3),
+	MSM_PIN_FUNCTION(i2chub0_se4),
+	MSM_PIN_FUNCTION(i2chub0_se5),
+	MSM_PIN_FUNCTION(i2chub0_se6),
+	MSM_PIN_FUNCTION(i2chub0_se7),
+	MSM_PIN_FUNCTION(i2chub0_se8),
+	MSM_PIN_FUNCTION(i2chub0_se9),
+	MSM_PIN_FUNCTION(i2s0_data0),
+	MSM_PIN_FUNCTION(i2s0_data1),
+	MSM_PIN_FUNCTION(i2s0_sck),
+	MSM_PIN_FUNCTION(i2s0_ws),
+	MSM_PIN_FUNCTION(i2s1_data0),
+	MSM_PIN_FUNCTION(i2s1_data1),
+	MSM_PIN_FUNCTION(i2s1_sck),
+	MSM_PIN_FUNCTION(i2s1_ws),
+	MSM_PIN_FUNCTION(ibi_i3c),
+	MSM_PIN_FUNCTION(jitter_bist),
+	MSM_PIN_FUNCTION(mdp_esync0_out),
+	MSM_PIN_FUNCTION(mdp_esync1_out),
+	MSM_PIN_FUNCTION(mdp_vsync),
+	MSM_PIN_FUNCTION(mdp_vsync0_out),
+	MSM_PIN_FUNCTION(mdp_vsync1_out),
+	MSM_PIN_FUNCTION(mdp_vsync2_out),
+	MSM_PIN_FUNCTION(mdp_vsync3_out),
+	MSM_PIN_FUNCTION(mdp_vsync5_out),
+	MSM_PIN_FUNCTION(mdp_vsync_e),
+	MSM_PIN_FUNCTION(nav_gpio0),
+	MSM_PIN_FUNCTION(nav_gpio1),
+	MSM_PIN_FUNCTION(nav_gpio2),
+	MSM_PIN_FUNCTION(nav_gpio3),
+	MSM_PIN_FUNCTION(pcie0_clk_req_n),
+	MSM_PIN_FUNCTION(phase_flag),
+	MSM_PIN_FUNCTION(pll_bist_sync),
+	MSM_PIN_FUNCTION(pll_clk_aux),
+	MSM_PIN_FUNCTION(prng_rosc0),
+	MSM_PIN_FUNCTION(prng_rosc1),
+	MSM_PIN_FUNCTION(prng_rosc2),
+	MSM_PIN_FUNCTION(prng_rosc3),
+	MSM_PIN_FUNCTION(qdss_cti),
+	MSM_PIN_FUNCTION(qlink_big_enable),
+	MSM_PIN_FUNCTION(qlink_big_request),
+	MSM_PIN_FUNCTION(qlink_little_enable),
+	MSM_PIN_FUNCTION(qlink_little_request),
+	MSM_PIN_FUNCTION(qlink_wmss),
+	MSM_PIN_FUNCTION(qspi0),
+	MSM_PIN_FUNCTION(qspi1),
+	MSM_PIN_FUNCTION(qspi2),
+	MSM_PIN_FUNCTION(qspi3),
+	MSM_PIN_FUNCTION(qspi_clk),
+	MSM_PIN_FUNCTION(qspi_cs),
+	MSM_PIN_FUNCTION(qup1_se0),
+	MSM_PIN_FUNCTION(qup1_se1),
+	MSM_PIN_FUNCTION(qup1_se2),
+	MSM_PIN_FUNCTION(qup1_se3),
+	MSM_PIN_FUNCTION(qup1_se4),
+	MSM_PIN_FUNCTION(qup1_se5),
+	MSM_PIN_FUNCTION(qup1_se6),
+	MSM_PIN_FUNCTION(qup1_se7),
+	MSM_PIN_FUNCTION(qup2_se0),
+	MSM_PIN_FUNCTION(qup2_se1),
+	MSM_PIN_FUNCTION(qup2_se2),
+	MSM_PIN_FUNCTION(qup2_se3),
+	MSM_PIN_FUNCTION(qup2_se4),
+	MSM_PIN_FUNCTION(qup2_se5),
+	MSM_PIN_FUNCTION(qup2_se6),
+	MSM_PIN_FUNCTION(qup2_se7),
+	MSM_PIN_FUNCTION(sd_write_protect),
+	MSM_PIN_FUNCTION(sdc40),
+	MSM_PIN_FUNCTION(sdc41),
+	MSM_PIN_FUNCTION(sdc42),
+	MSM_PIN_FUNCTION(sdc43),
+	MSM_PIN_FUNCTION(sdc4_clk),
+	MSM_PIN_FUNCTION(sdc4_cmd),
+	MSM_PIN_FUNCTION(tb_trig_sdc2),
+	MSM_PIN_FUNCTION(tb_trig_sdc4),
+	MSM_PIN_FUNCTION(tmess_prng0),
+	MSM_PIN_FUNCTION(tmess_prng1),
+	MSM_PIN_FUNCTION(tmess_prng2),
+	MSM_PIN_FUNCTION(tmess_prng3),
+	MSM_PIN_FUNCTION(tsense_pwm1),
+	MSM_PIN_FUNCTION(tsense_pwm2),
+	MSM_PIN_FUNCTION(tsense_pwm3),
+	MSM_PIN_FUNCTION(tsense_pwm4),
+	MSM_PIN_FUNCTION(uim0_clk),
+	MSM_PIN_FUNCTION(uim0_data),
+	MSM_PIN_FUNCTION(uim0_present),
+	MSM_PIN_FUNCTION(uim0_reset),
+	MSM_PIN_FUNCTION(uim1_clk),
+	MSM_PIN_FUNCTION(uim1_data),
+	MSM_PIN_FUNCTION(uim1_present),
+	MSM_PIN_FUNCTION(uim1_reset),
+	MSM_PIN_FUNCTION(usb1_hs),
+	MSM_PIN_FUNCTION(usb_phy),
+	MSM_PIN_FUNCTION(vfr_0),
+	MSM_PIN_FUNCTION(vfr_1),
+	MSM_PIN_FUNCTION(vsense_trigger_mirnat),
+	MSM_PIN_FUNCTION(wcn_sw),
+	MSM_PIN_FUNCTION(wcn_sw_ctrl),
+};
+
+/*
+ * Every pin is maintained as a single group, and missing or non-existing pin
+ * would be maintained as dummy group to synchronize pin group index with
+ * pin descriptor registered with pinctrl core.
+ * Clients would not be able to request these dummy pin groups.
+ */
+static const struct msm_pingroup sm8750_groups[] = {
+	[0] = PINGROUP(0, qup2_se0, ibi_i3c, _, _, _, _, _, _, _, _, egpio),
+	[1] = PINGROUP(1, qup2_se0, ibi_i3c, _, _, _, _, _, _, _, _, egpio),
+	[2] = PINGROUP(2, qup2_se0, _, _, _, _, _, _, _, _, _, egpio),
+	[3] = PINGROUP(3, qup2_se0, _, _, _, _, _, _, _, _, _, egpio),
+	[4] = PINGROUP(4, qup2_se1, ibi_i3c, _, _, _, _, _, _, _, _, egpio),
+	[5] = PINGROUP(5, qup2_se1, ibi_i3c, _, _, _, _, _, _, _, _, egpio),
+	[6] = PINGROUP(6, qup2_se1, _, _, _, _, _, _, _, _, _, egpio),
+	[7] = PINGROUP(7, qup2_se1, _, _, _, _, _, _, _, _, _, egpio),
+	[8] = PINGROUP(8, qup2_se2, ibi_i3c, _, _, _, _, _, _, _, _, _),
+	[9] = PINGROUP(9, qup2_se2, ibi_i3c, _, _, _, _, _, _, _, _, _),
+	[10] = PINGROUP(10, qup2_se2, cci_async_in, phase_flag, _, _, _, _, _, _, _, _),
+	[11] = PINGROUP(11, qup2_se2, cci_async_in, phase_flag, _, _, _, _, _, _, _, _),
+	[12] = PINGROUP(12, qup2_se3, ibi_i3c, qup2_se2, _, _, _, _, _, _, _, _),
+	[13] = PINGROUP(13, qup2_se3, ibi_i3c, qup2_se2, _, _, _, _, _, _, _, _),
+	[14] = PINGROUP(14, qup2_se3, phase_flag, _, _, _, _, _, _, _, _, _),
+	[15] = PINGROUP(15, qup2_se3, cci_async_in, qup2_se2, phase_flag, _, _, _, _, _, _, _),
+	[16] = PINGROUP(16, qup2_se4, phase_flag, _, _, _, _, _, _, _, _, _),
+	[17] = PINGROUP(17, qup2_se4, phase_flag, _, _, _, _, _, _, _, _, _),
+	[18] = PINGROUP(18, wcn_sw_ctrl, qup2_se4, phase_flag, _, _, _, _, _, _, _, _),
+	[19] = PINGROUP(19, wcn_sw, qup2_se4, phase_flag, _, _, _, _, _, _, _, _),
+	[20] = PINGROUP(20, qup2_se5, phase_flag, _, _, _, _, _, _, _, _, _),
+	[21] = PINGROUP(21, qup2_se5, phase_flag, _, _, _, _, _, _, _, _, _),
+	[22] = PINGROUP(22, qup2_se5, phase_flag, _, _, _, _, _, _, _, _, _),
+	[23] = PINGROUP(23, qup2_se5, qup2_se5, phase_flag, _, _, _, _, _, _, _, _),
+	[24] = PINGROUP(24, qup2_se6, phase_flag, _, _, _, _, _, _, _, _, _),
+	[25] = PINGROUP(25, qup2_se6, phase_flag, _, _, _, _, _, _, _, _, _),
+	[26] = PINGROUP(26, qup2_se6, phase_flag, _, _, _, _, _, _, _, _, _),
+	[27] = PINGROUP(27, qup2_se6, qdss_cti, phase_flag, _, _, _, _, _, _, _, _),
+	[28] = PINGROUP(28, qup2_se7, ibi_i3c, phase_flag, _, _, _, _, _, _, _, _),
+	[29] = PINGROUP(29, qup2_se7, ibi_i3c, phase_flag, _, _, _, _, _, _, _, _),
+	[30] = PINGROUP(30, qup2_se7, _, _, _, _, _, _, _, _, _, _),
+	[31] = PINGROUP(31, qup2_se7, qdss_cti, phase_flag, _, _, _, _, _, _, _, _),
+	[32] = PINGROUP(32, qup1_se0, ibi_i3c, _, _, _, _, _, _, _, _, egpio),
+	[33] = PINGROUP(33, qup1_se0, ibi_i3c, _, _, _, _, _, _, _, _, egpio),
+	[34] = PINGROUP(34, qup1_se0, _, _, _, _, _, _, _, _, _, egpio),
+	[35] = PINGROUP(35, qup1_se0, _, _, _, _, _, _, _, _, _, egpio),
+	[36] = PINGROUP(36, qup1_se1, uim1_data, ibi_i3c, sdc40, _, _, _, _, _, _, egpio),
+	[37] = PINGROUP(37, qup1_se1, uim1_clk, ibi_i3c, sdc41, _, _, _, _, _, _, egpio),
+	[38] = PINGROUP(38, qup1_se1, sdc42, _, _, _, _, _, _, _, _, _),
+	[39] = PINGROUP(39, qup1_se1, uim1_reset, sdc43, _, _, _, _, _, _, _, _),
+	[40] = PINGROUP(40, qup1_se2, cmu_rng, ddr_bist_fail, _, _, _, _, _, _, _, _),
+	[41] = PINGROUP(41, qup1_se2, cmu_rng, ddr_bist_start, _, _, _, _, _, _, _, _),
+	[42] = PINGROUP(42, qup1_se2, cmu_rng, _, _, _, _, _, _, _, _, _),
+	[43] = PINGROUP(43, qup1_se2, cmu_rng, _, ddr_pxi2, _, _, _, _, _, _, _),
+	[44] = PINGROUP(44, qup1_se3, ddr_bist_complete, ddr_pxi1, _, _, _, _, _, _, _, _),
+	[45] = PINGROUP(45, qup1_se3, ddr_bist_stop, ddr_pxi1, _, _, _, _, _, _, _, _),
+	[46] = PINGROUP(46, qup1_se3, ddr_pxi3, _, _, _, _, _, _, _, _, _),
+	[47] = PINGROUP(47, qup1_se3, dp_hot, _, _, _, _, _, _, _, _, _),
+	[48] = PINGROUP(48, qup1_se4, ibi_i3c, sdc4_cmd, _, _, _, _, _, _, _, _),
+	[49] = PINGROUP(49, qup1_se4, ibi_i3c, sdc40, _, _, _, _, _, _, _, _),
+	[50] = PINGROUP(50, qup1_se4, aoss_cti, sdc4_clk, _, _, _, _, _, _, _, _),
+	[51] = PINGROUP(51, qup1_se4, aoss_cti, sdc41, _, _, _, _, _, _, _, _),
+	[52] = PINGROUP(52, qup1_se5, qspi0, ddr_pxi2, _, _, _, _, _, _, _, _),
+	[53] = PINGROUP(53, qup1_se5, qspi1, _, ddr_pxi3, _, _, _, _, _, _, _),
+	[54] = PINGROUP(54, qup1_se5, qspi_clk, uim1_data, ddr_pxi0, _, _, _, _, _, _, _),
+	[55] = PINGROUP(55, qup1_se5, qspi2, uim1_clk, ddr_pxi0, _, _, _, _, _, _, _),
+	[56] = PINGROUP(56, qup1_se6, qspi3, uim1_reset, _, _, _, _, _, _, _, _),
+	[57] = PINGROUP(57, qup1_se6, qspi_cs, tsense_pwm1, tsense_pwm2, tsense_pwm3, tsense_pwm4,
+			_, _, _, _, _),
+	[58] = PINGROUP(58, qup1_se6, qspi_cs, _, _, _, _, _, _, _, _, _),
+	[59] = PINGROUP(59, qup1_se6, usb_phy, vsense_trigger_mirnat, _, _, _, _, _, _, _, _),
+	[60] = PINGROUP(60, qup1_se7, aoss_cti, sdc42, _, _, _, _, _, _, _, _),
+	[61] = PINGROUP(61, qup1_se7, usb_phy, aoss_cti, sdc43, _, _, _, _, _, _, _),
+	[62] = PINGROUP(62, qup1_se7, _, _, _, _, _, _, _, _, _, _),
+	[63] = PINGROUP(63, qup1_se7, _, _, _, _, _, _, _, _, _, _),
+	[64] = PINGROUP(64, i2chub0_se0, prng_rosc1, tmess_prng1, phase_flag, _, _, _, _, _, _, _),
+	[65] = PINGROUP(65, i2chub0_se0, prng_rosc2, tmess_prng2, phase_flag, _, _, _, _, _, _, _),
+	[66] = PINGROUP(66, i2chub0_se1, prng_rosc3, tmess_prng3, phase_flag, _, _, _, _, _, _, _),
+	[67] = PINGROUP(67, i2chub0_se1, phase_flag, _, _, _, _, _, _, _, _, _),
+	[68] = PINGROUP(68, i2chub0_se2, phase_flag, _, _, _, _, _, _, _, _, _),
+	[69] = PINGROUP(69, i2chub0_se2, phase_flag, _, _, _, _, _, _, _, _, _),
+	[70] = PINGROUP(70, i2chub0_se3, uim1_data, _, atest_usb, _, _, _, _, _, _, _),
+	[71] = PINGROUP(71, i2chub0_se3, uim1_clk, _, atest_usb, _, _, _, _, _, _, _),
+	[72] = PINGROUP(72, i2chub0_se4, uim1_reset, qdss_cti, _, atest_usb, _, _, _, _, _, _),
+	[73] = PINGROUP(73, i2chub0_se4, qdss_cti, jitter_bist, atest_usb, _, _, _, _, _, _, _),
+	[74] = PINGROUP(74, i2chub0_se5, _, _, _, _, _, _, _, _, _, _),
+	[75] = PINGROUP(75, i2chub0_se5, _, _, _, _, _, _, _, _, _, _),
+	[76] = PINGROUP(76, i2chub0_se6, atest_usb, _, _, _, _, _, _, _, _, _),
+	[77] = PINGROUP(77, i2chub0_se6, gnss_adc1, _, _, _, _, _, _, _, _, _),
+	[78] = PINGROUP(78, dbg_out_clk, gnss_adc0, _, _, _, _, _, _, _, _, _),
+	[79] = PINGROUP(79, usb1_hs, gnss_adc0, _, _, _, _, _, _, _, _, _),
+	[80] = PINGROUP(80, i2chub0_se9, _, _, _, _, _, _, _, _, _, _),
+	[81] = PINGROUP(81, i2chub0_se9, _, _, _, _, _, _, _, _, _, _),
+	[82] = PINGROUP(82, i2chub0_se7, qdss_cti, phase_flag, _, _, _, _, _, _, _, _),
+	[83] = PINGROUP(83, i2chub0_se7, qdss_cti, phase_flag, _, _, _, _, _, _, _, _),
+	[84] = PINGROUP(84, _, _, _, _, _, _, _, _, _, _, _),
+	[85] = PINGROUP(85, sd_write_protect, prng_rosc0, tmess_prng0, phase_flag, _, _, _, _, _,
+			_, _),
+	[86] = PINGROUP(86, mdp_vsync, mdp_vsync0_out, mdp_vsync1_out, gcc_gp1, _, _, _, _, _, _,
+			_),
+	[87] = PINGROUP(87, mdp_vsync, mdp_vsync2_out, mdp_vsync3_out, mdp_vsync5_out, gcc_gp2, _,
+			_, _, _, _, _),
+	[88] = PINGROUP(88, mdp_vsync_e, mdp_esync0_out, gcc_gp3, _, _, _, _, _, _, _, _),
+	[89] = PINGROUP(89, cam_mclk, tb_trig_sdc2, _, _, _, _, _, _, _, _, _),
+	[90] = PINGROUP(90, cam_mclk, _, _, _, _, _, _, _, _, _, _),
+	[91] = PINGROUP(91, cam_aon_mclk2, _, _, _, _, _, _, _, _, _, _),
+	[92] = PINGROUP(92, cam_mclk, _, _, _, _, _, _, _, _, _, _),
+	[93] = PINGROUP(93, cam_aon_mclk4, _, _, _, _, _, _, _, _, _, _),
+	[94] = PINGROUP(94, cam_mclk, _, _, _, _, _, _, _, _, _, _),
+	[95] = PINGROUP(95, cam_mclk, pll_clk_aux, _, _, _, _, _, _, _, _, _),
+	[96] = PINGROUP(96, cam_mclk, _, _, _, _, _, _, _, _, _, _),
+	[97] = PINGROUP(97, mdp_vsync, _, _, _, _, _, _, _, _, _, _),
+	[98] = PINGROUP(98, mdp_vsync, _, _, _, _, _, _, _, _, _, _),
+	[99] = PINGROUP(99, gnss_adc1, _, _, _, _, _, _, _, _, _, _),
+	[100] = PINGROUP(100, mdp_esync1_out, _, _, _, _, _, _, _, _, _, _),
+	[101] = PINGROUP(101, phase_flag, _, _, _, _, _, _, _, _, _, _),
+	[102] = PINGROUP(102, phase_flag, _, _, _, _, _, _, _, _, _, _),
+	[103] = PINGROUP(103, pcie0_clk_req_n, phase_flag, _, _, _, _, _, _, _, _, _),
+	[104] = PINGROUP(104, pll_bist_sync, phase_flag, _, _, _, _, _, _, _, _, _),
+	[105] = PINGROUP(105, _, _, _, _, _, _, _, _, _, _, egpio),
+	[106] = PINGROUP(106, _, _, _, _, _, _, _, _, _, _, egpio),
+	[107] = PINGROUP(107, _, _, _, _, _, _, _, _, _, _, egpio),
+	[108] = PINGROUP(108, _, _, _, _, _, _, _, _, _, _, egpio),
+	[109] = PINGROUP(109, cci_timer, _, _, _, _, _, _, _, _, _, _),
+	[110] = PINGROUP(110, cci_timer, _, _, _, _, _, _, _, _, _, _),
+	[111] = PINGROUP(111, cci_timer, cci_i2c_sda, _, _, _, _, _, _, _, _, _),
+	[112] = PINGROUP(112, cci_i2c_sda, _, _, _, _, _, _, _, _, _, _),
+	[113] = PINGROUP(113, cci_i2c_sda, _, _, _, _, _, _, _, _, _, _),
+	[114] = PINGROUP(114, cci_i2c_scl, _, _, _, _, _, _, _, _, _, _),
+	[115] = PINGROUP(115, cci_i2c_sda, _, _, _, _, _, _, _, _, _, _),
+	[116] = PINGROUP(116, cci_i2c_scl, _, _, _, _, _, _, _, _, _, _),
+	[117] = PINGROUP(117, cci_i2c_sda, _, _, _, _, _, _, _, _, _, _),
+	[118] = PINGROUP(118, cci_i2c_scl, _, _, _, _, _, _, _, _, _, _),
+	[119] = PINGROUP(119, cci_i2c_sda, _, _, _, _, _, _, _, _, _, _),
+	[120] = PINGROUP(120, cci_i2c_scl, _, _, _, _, _, _, _, _, _, _),
+	[121] = PINGROUP(121, i2s1_sck, _, _, _, _, _, _, _, _, _, _),
+	[122] = PINGROUP(122, i2s1_data0, _, _, _, _, _, _, _, _, _, _),
+	[123] = PINGROUP(123, i2s1_ws, _, _, _, _, _, _, _, _, _, _),
+	[124] = PINGROUP(124, i2s1_data1, audio_ext_mclk1, audio_ref_clk, _, _, _, _, _, _, _, _),
+	[125] = PINGROUP(125, audio_ext_mclk0, _, _, _, _, _, _, _, _, _, _),
+	[126] = PINGROUP(126, i2s0_sck, _, _, _, _, _, _, _, _, _, _),
+	[127] = PINGROUP(127, i2s0_data0, _, _, _, _, _, _, _, _, _, _),
+	[128] = PINGROUP(128, i2s0_data1, _, _, _, _, _, _, _, _, _, _),
+	[129] = PINGROUP(129, i2s0_ws, _, _, _, _, _, _, _, _, _, _),
+	[130] = PINGROUP(130, uim0_data, atest_char, _, _, _, _, _, _, _, _, _),
+	[131] = PINGROUP(131, uim0_clk, atest_char, _, _, _, _, _, _, _, _, _),
+	[132] = PINGROUP(132, uim0_reset, atest_char, _, _, _, _, _, _, _, _, _),
+	[133] = PINGROUP(133, uim0_present, atest_char, _, _, _, _, _, _, _, _, _),
+	[134] = PINGROUP(134, uim1_data, qup1_se2, gcc_gp1, _, _, _, _, _, _, _, _),
+	[135] = PINGROUP(135, uim1_clk, qup1_se2, gcc_gp2, _, _, _, _, _, _, _, _),
+	[136] = PINGROUP(136, uim1_reset, qup1_se2, gcc_gp3, _, _, _, _, _, _, _, _),
+	[137] = PINGROUP(137, uim1_present, atest_char, _, _, _, _, _, _, _, _, _),
+	[138] = PINGROUP(138, _, _, _, _, _, _, _, _, _, _, _),
+	[139] = PINGROUP(139, _, _, _, _, _, _, _, _, _, _, _),
+	[140] = PINGROUP(140, _, _, _, _, _, _, _, _, _, _, _),
+	[141] = PINGROUP(141, _, _, _, _, _, _, _, _, _, _, _),
+	[142] = PINGROUP(142, _, _, _, _, _, _, _, _, _, _, _),
+	[143] = PINGROUP(143, _, _, _, _, _, _, _, _, _, _, _),
+	[144] = PINGROUP(144, _, _, _, _, _, _, _, _, _, _, _),
+	[145] = PINGROUP(145, _, _, _, _, _, _, _, _, _, _, _),
+	[146] = PINGROUP(146, _, _, _, _, _, _, _, _, _, _, _),
+	[147] = PINGROUP(147, _, tb_trig_sdc4, _, _, _, _, _, _, _, _, _),
+	[148] = PINGROUP(148, coex_uart1_rx, cmu_rng, _, _, _, _, _, _, _, _, _),
+	[149] = PINGROUP(149, coex_uart1_tx, cmu_rng, _, _, _, _, _, _, _, _, _),
+	[150] = PINGROUP(150, _, vfr_0, coex_uart2_rx, cmu_rng, sdc4_clk, _, _, _, _, _, _),
+	[151] = PINGROUP(151, _, coex_uart2_tx, cmu_rng, sdc4_cmd, _, _, _, _, _, _, _),
+	[152] = PINGROUP(152, nav_gpio2, _, _, _, _, _, _, _, _, _, _),
+	[153] = PINGROUP(153, cci_i2c_scl, _, _, _, _, _, _, _, _, _, _),
+	[154] = PINGROUP(154, nav_gpio0, nav_gpio3, _, _, _, _, _, _, _, _, _),
+	[155] = PINGROUP(155, nav_gpio1, vfr_1, _, _, _, _, _, _, _, _, _),
+	[156] = PINGROUP(156, qlink_little_request, _, _, _, _, _, _, _, _, _, _),
+	[157] = PINGROUP(157, qlink_little_enable, _, _, _, _, _, _, _, _, _, _),
+	[158] = PINGROUP(158, qlink_wmss, _, _, _, _, _, _, _, _, _, _),
+	[159] = PINGROUP(159, qlink_big_request, qdss_cti, _, _, _, _, _, _, _, _, _),
+	[160] = PINGROUP(160, qlink_big_enable, _, _, _, _, _, _, _, _, _, _),
+	[161] = PINGROUP(161, _, _, _, _, _, _, _, _, _, _, _),
+	[162] = PINGROUP(162, qdss_cti, _, _, _, _, _, _, _, _, _, _),
+	[163] = PINGROUP(163, cci_timer, _, _, _, _, _, _, _, _, _, _),
+	[164] = PINGROUP(164, cci_timer, cci_i2c_scl, _, _, _, _, _, _, _, _, _),
+	[165] = PINGROUP(165, _, _, _, _, _, _, _, _, _, _, egpio),
+	[166] = PINGROUP(166, _, _, _, _, _, _, _, _, _, _, egpio),
+	[167] = PINGROUP(167, _, _, _, _, _, _, _, _, _, _, egpio),
+	[168] = PINGROUP(168, _, _, _, _, _, _, _, _, _, _, egpio),
+	[169] = PINGROUP(169, _, _, _, _, _, _, _, _, _, _, egpio),
+	[170] = PINGROUP(170, _, _, _, _, _, _, _, _, _, _, egpio),
+	[171] = PINGROUP(171, _, _, _, _, _, _, _, _, _, _, egpio),
+	[172] = PINGROUP(172, _, _, _, _, _, _, _, _, _, _, egpio),
+	[173] = PINGROUP(173, _, _, _, _, _, _, _, _, _, _, egpio),
+	[174] = PINGROUP(174, _, _, _, _, _, _, _, _, _, _, egpio),
+	[175] = PINGROUP(175, _, _, _, _, _, _, _, _, _, _, egpio),
+	[176] = PINGROUP(176, _, _, _, _, _, _, _, _, _, _, egpio),
+	[177] = PINGROUP(177, _, _, _, _, _, _, _, _, _, _, egpio),
+	[178] = PINGROUP(178, _, _, _, _, _, _, _, _, _, _, egpio),
+	[179] = PINGROUP(179, _, _, _, _, _, _, _, _, _, _, egpio),
+	[180] = PINGROUP(180, _, _, _, _, _, _, _, _, _, _, egpio),
+	[181] = PINGROUP(181, _, _, _, _, _, _, _, _, _, _, egpio),
+	[182] = PINGROUP(182, _, _, _, _, _, _, _, _, _, _, egpio),
+	[183] = PINGROUP(183, _, _, _, _, _, _, _, _, _, _, egpio),
+	[184] = PINGROUP(184, _, _, _, _, _, _, _, _, _, _, egpio),
+	[185] = PINGROUP(185, _, _, _, _, _, _, _, _, _, _, egpio),
+	[186] = PINGROUP(186, _, _, _, _, _, _, _, _, _, _, egpio),
+	[187] = PINGROUP(187, _, _, _, _, _, _, _, _, _, _, egpio),
+	[188] = PINGROUP(188, _, _, _, _, _, _, _, _, _, _, egpio),
+	[189] = PINGROUP(189, _, _, _, _, _, _, _, _, _, _, egpio),
+	[190] = PINGROUP(190, _, _, _, _, _, _, _, _, _, _, egpio),
+	[191] = PINGROUP(191, _, _, _, _, _, _, _, _, _, _, egpio),
+	[192] = PINGROUP(192, _, _, _, _, _, _, _, _, _, _, egpio),
+	[193] = PINGROUP(193, _, _, _, _, _, _, _, _, _, _, egpio),
+	[194] = PINGROUP(194, _, _, _, _, _, _, _, _, _, _, egpio),
+	[195] = PINGROUP(195, _, _, _, _, _, _, _, _, _, _, egpio),
+	[196] = PINGROUP(196, _, _, _, _, _, _, _, _, _, _, egpio),
+	[197] = PINGROUP(197, _, _, _, _, _, _, _, _, _, _, egpio),
+	[198] = PINGROUP(198, _, _, _, _, _, _, _, _, _, _, egpio),
+	[199] = PINGROUP(199, _, _, _, _, _, _, _, _, _, _, egpio),
+	[200] = PINGROUP(200, _, _, _, _, _, _, _, _, _, _, egpio),
+	[201] = PINGROUP(201, _, _, _, _, _, _, _, _, _, _, egpio),
+	[202] = PINGROUP(202, _, _, _, _, _, _, _, _, _, _, egpio),
+	[203] = PINGROUP(203, _, _, _, _, _, _, _, _, _, _, egpio),
+	[204] = PINGROUP(204, _, _, _, _, _, _, _, _, _, _, egpio),
+	[205] = PINGROUP(205, _, _, _, _, _, _, _, _, _, _, egpio),
+	[206] = PINGROUP(206, i2chub0_se8, _, _, _, _, _, _, _, _, _, egpio),
+	[207] = PINGROUP(207, i2chub0_se8, _, _, _, _, _, _, _, _, _, egpio),
+	[208] = PINGROUP(208, _, _, _, _, _, _, _, _, _, _, egpio),
+	[209] = PINGROUP(209, _, _, _, _, _, _, _, _, _, _, egpio),
+	[210] = PINGROUP(210, _, _, _, _, _, _, _, _, _, _, egpio),
+	[211] = PINGROUP(211, _, _, _, _, _, _, _, _, _, _, egpio),
+	[212] = PINGROUP(212, _, _, _, _, _, _, _, _, _, _, egpio),
+	[213] = PINGROUP(213, _, _, _, _, _, _, _, _, _, _, egpio),
+	[214] = PINGROUP(214, _, _, _, _, _, _, _, _, _, _, egpio),
+	[215] = UFS_RESET(ufs_reset, 0xe2004, 0xe3000),
+	[216] = SDC_QDSD_PINGROUP(sdc2_clk, 0xdb000, 14, 6),
+	[217] = SDC_QDSD_PINGROUP(sdc2_cmd, 0xdb000, 11, 3),
+	[218] = SDC_QDSD_PINGROUP(sdc2_data, 0xdb000, 9, 0),
+};
+
+static const struct msm_gpio_wakeirq_map sm8750_pdc_map[] = {
+	{ 0, 72 },    { 3, 80 },    { 4, 73 },	  { 7, 74 },	{ 8, 75 },
+	{ 11, 76 },   { 12, 87 },   { 15, 98 },	  { 18, 110 },	{ 19, 79 },
+	{ 23, 82 },   { 24, 83 },   { 27, 84 },	  { 28, 85 },	{ 31, 86 },
+	{ 32, 92 },   { 35, 68 },   { 36, 93 },	  { 39, 94 },	{ 43, 95 },
+	{ 46, 96 },   { 47, 121 },  { 48, 97 },	  { 51, 118 },	{ 54, 102 },
+	{ 55, 71 },   { 56, 103 },  { 57, 104 },  { 59, 105 },	{ 61, 81 },
+	{ 63, 91 },   { 64, 77 },   { 65, 90 },	  { 66, 106 },	{ 67, 99 },
+	{ 68, 112 },  { 69, 113 },  { 75, 114 },  { 78, 115 },	{ 79, 116 },
+	{ 80, 122 },  { 81, 123 },  { 84, 101 },  { 85, 124 },	{ 86, 125 },
+	{ 87, 126 },  { 88, 127 },  { 95, 128 },  { 96, 129 },	{ 97, 100 },
+	{ 98, 117 },  { 99, 78 },   { 102, 130 }, { 103, 131 }, { 104, 132 },
+	{ 108, 133 }, { 133, 134 }, { 137, 67 },  { 148, 135 }, { 150, 136 },
+	{ 152, 137 }, { 154, 138 }, { 155, 89 },  { 156, 139 }, { 159, 140 },
+	{ 162, 109 }, { 163, 108 }, { 166, 141 }, { 169, 142 }, { 171, 143 },
+	{ 172, 144 }, { 174, 145 }, { 176, 146 }, { 177, 120 }, { 181, 147 },
+	{ 182, 148 }, { 185, 149 }, { 188, 111 }, { 190, 88 },	{ 191, 150 },
+	{ 192, 151 }, { 193, 152 }, { 196, 153 }, { 197, 154 }, { 198, 70 },
+	{ 199, 119 }, { 200, 69 },  { 201, 155 }, { 202, 156 }, { 203, 157 },
+	{ 204, 158 }, { 205, 107 }, { 209, 159 },
+};
+
+static const struct msm_pinctrl_soc_data sm8750_tlmm = {
+	.pins = sm8750_pins,
+	.npins = ARRAY_SIZE(sm8750_pins),
+	.functions = sm8750_functions,
+	.nfunctions = ARRAY_SIZE(sm8750_functions),
+	.groups = sm8750_groups,
+	.ngroups = ARRAY_SIZE(sm8750_groups),
+	.ngpios = 216,
+	.wakeirq_map = sm8750_pdc_map,
+	.nwakeirq_map = ARRAY_SIZE(sm8750_pdc_map),
+	.egpio_func = 11,
+};
+
+static int sm8750_tlmm_probe(struct platform_device *pdev)
+{
+	return msm_pinctrl_probe(pdev, &sm8750_tlmm);
+}
+
+static const struct of_device_id sm8750_tlmm_of_match[] = {
+	{ .compatible = "qcom,sm8750-tlmm", },
+	{},
+};
+
+static struct platform_driver sm8750_tlmm_driver = {
+	.driver = {
+		.name = "sm8750-tlmm",
+		.of_match_table = sm8750_tlmm_of_match,
+	},
+	.probe = sm8750_tlmm_probe,
+	.remove = msm_pinctrl_remove,
+};
+
+static int __init sm8750_tlmm_init(void)
+{
+	return platform_driver_register(&sm8750_tlmm_driver);
+}
+arch_initcall(sm8750_tlmm_init);
+
+static void __exit sm8750_tlmm_exit(void)
+{
+	platform_driver_unregister(&sm8750_tlmm_driver);
+}
+module_exit(sm8750_tlmm_exit);
+
+MODULE_DESCRIPTION("QTI SM8750 TLMM driver");
+MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(of, sm8750_tlmm_of_match);

From e3e309b2bea8d2c37ed6f52c837848b601d3245e Mon Sep 17 00:00:00 2001
From: Bartosz Wawrzyniak <bwawrzyn@cisco.com>
Date: Fri, 18 Oct 2024 11:30:43 +0000
Subject: [PATCH 1102/1530] PCI: cadence: Lower severity of message when
 phy-names property is absent in DTS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The "phy-names" property is optional, so the message indicating its
absence during the probe should be of "info" severity rather than
"error" severity.

Link: https://lore.kernel.org/r/20241018113045.2050295-1-bwawrzyn@cisco.com
Signed-off-by: Bartosz Wawrzyniak <bwawrzyn@cisco.com>
[kwilczynski: update log messages wording, commit log]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/cadence/pcie-cadence.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/cadence/pcie-cadence.c b/drivers/pci/controller/cadence/pcie-cadence.c
index 4251fac5e3106..204e045aed8c3 100644
--- a/drivers/pci/controller/cadence/pcie-cadence.c
+++ b/drivers/pci/controller/cadence/pcie-cadence.c
@@ -197,7 +197,7 @@ int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie)
 
 	phy_count = of_property_count_strings(np, "phy-names");
 	if (phy_count < 1) {
-		dev_err(dev, "no phy-names.  PHY will not be initialized\n");
+		dev_info(dev, "no \"phy-names\" property found; PHY will not be initialized\n");
 		pcie->phy_count = 0;
 		return 0;
 	}
@@ -260,7 +260,7 @@ static int cdns_pcie_resume_noirq(struct device *dev)
 
 	ret = cdns_pcie_enable_phy(pcie);
 	if (ret) {
-		dev_err(dev, "failed to enable phy\n");
+		dev_err(dev, "failed to enable PHY\n");
 		return ret;
 	}
 

From d19ea320d3029a12993c671f4815bf6c02ae0727 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Mon, 11 Nov 2024 09:09:35 +0800
Subject: [PATCH 1103/1530] PCI: mediatek-gen3: Remove unneeded semicolon
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove a surplus semicolon and fix the following warning:

  ./drivers/pci/controller/pcie-mediatek-gen3.c:414:2-3: Unneeded semicolon

Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=11789
Link: https://lore.kernel.org/r/20241111010935.20208-1-yang.lee@linux.alibaba.com
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
[kwilczynski: commit log]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Matthias Brugger <matthias.bgg@gmail.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
 drivers/pci/controller/pcie-mediatek-gen3.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c
index bbfbfe5752e6a..64ef8ff71b035 100644
--- a/drivers/pci/controller/pcie-mediatek-gen3.c
+++ b/drivers/pci/controller/pcie-mediatek-gen3.c
@@ -411,7 +411,7 @@ static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie)
 		if (pcie->num_lanes > 1)
 			val |= FIELD_PREP(PCIE_SETTING_LINK_WIDTH,
 					  GENMASK(fls(pcie->num_lanes >> 2), 0));
-	};
+	}
 	writel_relaxed(val, pcie->base + PCIE_SETTING_REG);
 
 	/* Set Link Control 2 (LNKCTL2) speed restriction, if any */

From f7f50742a6bb5f70b0e41cf9ed6255c7fded69b5 Mon Sep 17 00:00:00 2001
From: Shen Lichuan <shenlichuan@vivo.com>
Date: Thu, 26 Sep 2024 15:57:00 +0800
Subject: [PATCH 1104/1530] nvdimm: Correct some typos in comments

Fixed some confusing typos that were currently identified with codespell,
the details are as follows:

-in the code comments:
drivers/nvdimm/nd_virtio.c:100: repsonse ==> response
drivers/nvdimm/pfn_devs.c:542: namepace ==> namespace
drivers/nvdimm/pmem.c:319: reenable ==> re-enable

Signed-off-by: Shen Lichuan <shenlichuan@vivo.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
Link: https://patch.msgid.link/20240926075700.10122-1-shenlichuan@vivo.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
 drivers/nvdimm/nd_virtio.c | 2 +-
 drivers/nvdimm/pfn_devs.c  | 2 +-
 drivers/nvdimm/pmem.c      | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/nvdimm/nd_virtio.c b/drivers/nvdimm/nd_virtio.c
index f55d60922b87d..c3f07be4aa22a 100644
--- a/drivers/nvdimm/nd_virtio.c
+++ b/drivers/nvdimm/nd_virtio.c
@@ -97,7 +97,7 @@ static int virtio_pmem_flush(struct nd_region *nd_region)
 		dev_info(&vdev->dev, "failed to send command to virtio pmem device\n");
 		err = -EIO;
 	} else {
-		/* A host repsonse results in "host_ack" getting called */
+		/* A host response results in "host_ack" getting called */
 		wait_event(req_data->host_acked, req_data->done);
 		err = le32_to_cpu(req_data->resp.ret);
 	}
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 586348125b61a..cfdfe0eaa5121 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -539,7 +539,7 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 
 	if (!nd_pfn->uuid) {
 		/*
-		 * When probing a namepace via nd_pfn_probe() the uuid
+		 * When probing a namespace via nd_pfn_probe() the uuid
 		 * is NULL (see: nd_pfn_devinit()) we init settings from
 		 * pfn_sb
 		 */
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 210fb77f51ba0..d81faa9d89c93 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -316,7 +316,7 @@ static long pmem_dax_direct_access(struct dax_device *dax_dev,
  * range, filesystem turns the normal pwrite to a dax_recovery_write.
  *
  * The recovery write consists of clearing media poison, clearing page
- * HWPoison bit, reenable page-wide read-write permission, flush the
+ * HWPoison bit, re-enable page-wide read-write permission, flush the
  * caches and finally write.  A competing pread thread will be held
  * off during the recovery process since data read back might not be
  * valid, and this is achieved by clearing the badblock records after

From b61352101470f8b68c98af674e187cfaa7c43504 Mon Sep 17 00:00:00 2001
From: Yi Yang <yiyang13@huawei.com>
Date: Fri, 8 Nov 2024 08:55:26 +0000
Subject: [PATCH 1105/1530] nvdimm: rectify the illogical code within
 nd_dax_probe()

When nd_dax is NULL, nd_pfn is consequently NULL as well. Nevertheless,
it is inadvisable to perform pointer arithmetic or address-taking on a
NULL pointer.
Introduce the nd_dax_devinit() function to enhance the code's logic and
improve its readability.

Signed-off-by: Yi Yang <yiyang13@huawei.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://patch.msgid.link/20241108085526.527957-1-yiyang13@huawei.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
 drivers/nvdimm/dax_devs.c | 4 ++--
 drivers/nvdimm/nd.h       | 7 +++++++
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/nvdimm/dax_devs.c b/drivers/nvdimm/dax_devs.c
index 6b4922de30477..37b743acbb7ba 100644
--- a/drivers/nvdimm/dax_devs.c
+++ b/drivers/nvdimm/dax_devs.c
@@ -106,12 +106,12 @@ int nd_dax_probe(struct device *dev, struct nd_namespace_common *ndns)
 
 	nvdimm_bus_lock(&ndns->dev);
 	nd_dax = nd_dax_alloc(nd_region);
-	nd_pfn = &nd_dax->nd_pfn;
-	dax_dev = nd_pfn_devinit(nd_pfn, ndns);
+	dax_dev = nd_dax_devinit(nd_dax, ndns);
 	nvdimm_bus_unlock(&ndns->dev);
 	if (!dax_dev)
 		return -ENOMEM;
 	pfn_sb = devm_kmalloc(dev, sizeof(*pfn_sb), GFP_KERNEL);
+	nd_pfn = &nd_dax->nd_pfn;
 	nd_pfn->pfn_sb = pfn_sb;
 	rc = nd_pfn_validate(nd_pfn, DAX_SIG);
 	dev_dbg(dev, "dax: %s\n", rc == 0 ? dev_name(dax_dev) : "<none>");
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 2dbb1dca17b53..5ca06e9a2d292 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -600,6 +600,13 @@ struct nd_dax *to_nd_dax(struct device *dev);
 int nd_dax_probe(struct device *dev, struct nd_namespace_common *ndns);
 bool is_nd_dax(const struct device *dev);
 struct device *nd_dax_create(struct nd_region *nd_region);
+static inline struct device *nd_dax_devinit(struct nd_dax *nd_dax,
+					    struct nd_namespace_common *ndns)
+{
+	if (!nd_dax)
+		return NULL;
+	return nd_pfn_devinit(&nd_dax->nd_pfn, ndns);
+}
 #else
 static inline int nd_dax_probe(struct device *dev,
 		struct nd_namespace_common *ndns)

From b8e6d7ce50673c39514921ac61f7af00bbb58b87 Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Thu, 17 Oct 2024 03:11:25 -0700
Subject: [PATCH 1106/1530] dax: delete a stale directory pmem

After commit: 83762cb5c7c4 ("dax: Kill DEV_DAX_PMEM_COMPAT") the pmem/
directory is not needed anymore and Makefile changes were made
accordingly in this commit, but there is a Makefile and pmem.c in pmem/
which are now stale and pmem.c is empty, remove them.

Fixes: 83762cb5c7c4 ("dax: Kill DEV_DAX_PMEM_COMPAT")
Suggested-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Link: https://patch.msgid.link/20241017101144.1654085-1-harshit.m.mogalapalli@oracle.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
 drivers/dax/pmem/Makefile |  7 -------
 drivers/dax/pmem/pmem.c   | 10 ----------
 2 files changed, 17 deletions(-)
 delete mode 100644 drivers/dax/pmem/Makefile
 delete mode 100644 drivers/dax/pmem/pmem.c

diff --git a/drivers/dax/pmem/Makefile b/drivers/dax/pmem/Makefile
deleted file mode 100644
index 191c31f0d4f00..0000000000000
--- a/drivers/dax/pmem/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
-obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem_core.o
-
-dax_pmem-y := pmem.o
-dax_pmem_core-y := core.o
-dax_pmem_compat-y := compat.o
diff --git a/drivers/dax/pmem/pmem.c b/drivers/dax/pmem/pmem.c
deleted file mode 100644
index dfe91a2990fec..0000000000000
--- a/drivers/dax/pmem/pmem.c
+++ /dev/null
@@ -1,10 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2016 - 2018 Intel Corporation. All rights reserved. */
-#include <linux/percpu-refcount.h>
-#include <linux/memremap.h>
-#include <linux/module.h>
-#include <linux/pfn_t.h>
-#include <linux/nd.h>
-#include "../bus.h"
-
-

From f3dd9ae7f03aefa5bb12a4606f3d6cca87863622 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 1 Sep 2024 17:17:09 +0200
Subject: [PATCH 1107/1530] dax: Remove an unused field in struct
 dax_operations

.dax_supported() was apparently removed by commit 7b0800d00dae ("dax:
remove dax_capable") on 2021-11.

Remove the now unused function pointer from the struct dax_operations.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/56b92b722ca0a6fd1387c871a6ec01bcb9bd525e.1725203804.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
 include/linux/dax.h | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/include/linux/dax.h b/include/linux/dax.h
index 9d3e3327af4c0..df41a0017b319 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -27,12 +27,6 @@ struct dax_operations {
 	 */
 	long (*direct_access)(struct dax_device *, pgoff_t, long,
 			enum dax_access_mode, void **, pfn_t *);
-	/*
-	 * Validate whether this device is usable as an fsdax backing
-	 * device.
-	 */
-	bool (*dax_supported)(struct dax_device *, struct block_device *, int,
-			sector_t, sector_t);
 	/* zero_page_range: required operation. Zero page range   */
 	int (*zero_page_range)(struct dax_device *, pgoff_t, size_t);
 	/*

From 1f7393adf67de6897b1ee614903e1900d7cf069b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Nov 2024 12:17:33 -0300
Subject: [PATCH 1108/1530] perf disasm: Define stubs for the LLVM and capstone
 disassemblers

This reduces the number of ifdefs in the main symbol__disassemble()
method and paves the way for allowing the user to configure the
disassemblers of preference.

Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Aditya Bodkhe <Aditya.Bodkhe1@ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Link: https://lore.kernel.org/r/20241111151734.1018476-3-acme@kernel.org
[ Applied fixes from Masami Hiramatsu and Aditya Bodkhe for when capstone devel files are not available ]
Link: https://lore.kernel.org/r/B78FB6DF-24E9-4A3C-91C9-535765EC0E2A@ibm.com
Link: https://lore.kernel.org/r/173145729034.2747044.453926054000880254.stgit@mhiramat.roam.corp.google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/disasm.c | 43 ++++++++++++++++++++++++++++++++--------
 1 file changed, 35 insertions(+), 8 deletions(-)

diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index 36cf61602c17f..6259dfe9aacc1 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -1424,6 +1424,15 @@ read_symbol(const char *filename, struct map *map, struct symbol *sym,
 }
 #endif
 
+#if !defined(HAVE_LIBCAPSTONE_SUPPORT) || !defined(HAVE_LIBLLVM_SUPPORT)
+static void symbol__disassembler_missing(const char *disassembler, const char *filename,
+					 struct symbol *sym)
+{
+	pr_debug("The %s disassembler isn't linked in for %s in %s\n",
+		 disassembler, sym->name, filename);
+}
+#endif
+
 #ifdef HAVE_LIBCAPSTONE_SUPPORT
 static void print_capstone_detail(cs_insn *insn, char *buf, size_t len,
 				  struct annotate_args *args, u64 addr)
@@ -1715,7 +1724,21 @@ static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
 	count = -1;
 	goto out;
 }
-#endif
+#else // HAVE_LIBCAPSTONE_SUPPORT
+static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
+					struct annotate_args *args __maybe_unused)
+{
+	symbol__disassembler_missing("capstone", filename, sym);
+	return -1;
+}
+
+static int symbol__disassemble_capstone_powerpc(char *filename, struct symbol *sym,
+						struct annotate_args *args __maybe_unused)
+{
+	symbol__disassembler_missing("capstone powerpc", filename, sym);
+	return -1;
+}
+#endif // HAVE_LIBCAPSTONE_SUPPORT
 
 static int symbol__disassemble_raw(char *filename, struct symbol *sym,
 					struct annotate_args *args)
@@ -1983,7 +2006,14 @@ static int symbol__disassemble_llvm(char *filename, struct symbol *sym,
 	free(line_storage);
 	return ret;
 }
-#endif
+#else // HAVE_LIBLLVM_SUPPORT
+static int symbol__disassemble_llvm(char *filename, struct symbol *sym,
+				    struct annotate_args *args __maybe_unused)
+{
+	symbol__disassembler_missing("LLVM", filename, sym);
+	return -1;
+}
+#endif // HAVE_LIBLLVM_SUPPORT
 
 /*
  * Possibly create a new version of line with tabs expanded. Returns the
@@ -2242,24 +2272,21 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 			err = symbol__disassemble_raw(symfs_filename, sym, args);
 			if (err == 0)
 				goto out_remove_tmp;
-#ifdef HAVE_LIBCAPSTONE_SUPPORT
+
 			err = symbol__disassemble_capstone_powerpc(symfs_filename, sym, args);
 			if (err == 0)
 				goto out_remove_tmp;
-#endif
 		}
 	}
 
-#ifdef HAVE_LIBLLVM_SUPPORT
 	err = symbol__disassemble_llvm(symfs_filename, sym, args);
 	if (err == 0)
 		goto out_remove_tmp;
-#endif
-#ifdef HAVE_LIBCAPSTONE_SUPPORT
+
 	err = symbol__disassemble_capstone(symfs_filename, sym, args);
 	if (err == 0)
 		goto out_remove_tmp;
-#endif
+
 	err = symbol__disassemble_objdump(symfs_filename, sym, args);
 
 out_remove_tmp:

From a6e8a58de6294578195447596fb975a9027b4d2c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Nov 2024 12:17:34 -0300
Subject: [PATCH 1109/1530] perf disasm: Allow configuring what disassemblers
 to use

The perf tools annotation code used for a long time parsing the output
of binutils's objdump (or its reimplementations, like llvm's) to then
parse and augment it with samples, allow navigation, etc.

More recently disassemblers from the capstone and llvm (libraries, not
parsing the output of tools using those libraries to mimic binutils's
objdump output) were introduced.

So when all those methods are available, there is a static preference
for a series of attempts of disassembling a binary, with the 'llvm,
capstone, objdump' sequence being hard coded.

This patch allows users to change that sequence, specifying via a 'perf
config' 'annotate.disassemblers' entry which and in what order
disassemblers should be attempted.

As alluded to in the comments in the source code of this series, this
flexibility is useful for users and developers alike, elliminating the
requirement to rebuild the tool with some specific set of libraries to
see how the output of disassembling would be for one of these methods.

  root@x1:~# rm -f ~/.perfconfig
  root@x1:~# perf annotate -v --stdio2 update_load_avg
  <SNIP>
  symbol__disassemble:
    filename=/usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux,
    sym=update_load_avg, start=0xffffffffb6148fe0, en>
  annotating [0x6ff7170]
    /usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux :
    [0x7407ca0] update_load_avg
  Disassembled with llvm
  annotate.disassemblers=llvm,capstone,objdump
  Samples: 66  of event 'cpu_atom/cycles/P', 10000 Hz,
	Event count (approx.): 5185444, [percent: local period]
  update_load_avg()
    /usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux
  Percent       0xffffffff81148fe0 <update_load_avg>:
     1.61         pushq   %r15
                  pushq   %r14
     1.00         pushq   %r13
                  movl    %edx,%r13d
     1.90         pushq   %r12
                  pushq   %rbp
                  movq    %rsi,%rbp
                  pushq   %rbx
                  movq    %rdi,%rbx
                  subq    $0x18,%rsp
    15.14         movl    0x1a4(%rdi),%eax

  root@x1:~# perf config annotate.disassemblers=capstone
  root@x1:~# cat ~/.perfconfig
  # this file is auto-generated.
  [annotate]
	  disassemblers = capstone
  root@x1:~#
  root@x1:~# perf annotate -v --stdio2 update_load_avg
  <SNIP>
  Disassembled with capstone
  annotate.disassemblers=capstone
  Samples: 66  of event 'cpu_atom/cycles/P', 10000 Hz,
  Event count (approx.): 5185444, [percent: local period]
  update_load_avg()
  /usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux
  Percent       0xffffffff81148fe0 <update_load_avg>:
     1.61         pushq   %r15
                  pushq   %r14
     1.00         pushq   %r13
                  movl    %edx,%r13d
     1.90         pushq   %r12
                  pushq   %rbp
                  movq    %rsi,%rbp
                  pushq   %rbx
                  movq    %rdi,%rbx
                  subq    $0x18,%rsp
    15.14         movl    0x1a4(%rdi),%eax
  root@x1:~# perf config annotate.disassemblers=objdump,capstone
  root@x1:~# perf config annotate.disassemblers
  annotate.disassemblers=objdump,capstone
  root@x1:~# cat ~/.perfconfig
  # this file is auto-generated.
  [annotate]
	  disassemblers = objdump,capstone
  root@x1:~# perf annotate -v --stdio2 update_load_avg
  Executing: objdump  --start-address=0xffffffff81148fe0 \
		      --stop-address=0xffffffff811497aa  \
		      -d --no-show-raw-insn -S -C "$1"
  Disassembled with objdump
  annotate.disassemblers=objdump,capstone
  Samples: 66  of event 'cpu_atom/cycles/P', 10000 Hz,
  Event count (approx.): 5185444, [percent: local period]
  update_load_avg()
  /usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux
  Percent

                Disassembly of section .text:

                ffffffff81148fe0 <update_load_avg>:
                #define DO_ATTACH       0x4

                ffffffff81148fe0 <update_load_avg>:
                #define DO_ATTACH       0x4
                #define DO_DETACH       0x8

                /* Update task and its cfs_rq load average */
                static inline void update_load_avg(struct cfs_rq *cfs_rq,
						   struct sched_entity *se,
						   int flags)
                {
     1.61         push   %r15
                  push   %r14
     1.00         push   %r13
                  mov    %edx,%r13d
     1.90         push   %r12
                  push   %rbp
                  mov    %rsi,%rbp
                  push   %rbx
                  mov    %rdi,%rbx
                  sub    $0x18,%rsp
                }

                /* rq->task_clock normalized against any time
		   this cfs_rq has spent throttled */
                static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
                {
                if (unlikely(cfs_rq->throttle_count))
    15.14         mov    0x1a4(%rdi),%eax
  root@x1:~#

After adding a way to select the disassembler from the command line a
'perf test' comparing the output of the various diassemblers should be
introduced, to test these codebases.

Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Link: https://lore.kernel.org/r/20241111151734.1018476-4-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-config.txt | 13 ++++
 tools/perf/util/annotate.c               |  6 ++
 tools/perf/util/annotate.h               |  6 ++
 tools/perf/util/disasm.c                 | 77 ++++++++++++++++++++++--
 4 files changed, 96 insertions(+), 6 deletions(-)

diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 379f9d7a8ab11..1f668d4724e37 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -247,6 +247,19 @@ annotate.*::
 	These are in control of addresses, jump function, source code
 	in lines of assembly code from a specific program.
 
+	annotate.disassemblers::
+		Choose the disassembler to use: "objdump", "llvm",  "capstone",
+		if not specified it will first try, if available, the "llvm" one,
+		then, if it fails, "capstone", and finally the original "objdump"
+		based one.
+
+		Choosing a different one is useful when handling some feature that
+		is known to be best support at some point by one of the options,
+		to compare the output when in doubt about some bug, etc.
+
+		This can be a list, in order of preference, the first one that works
+		finishes the process.
+
 	annotate.addr2line::
 		addr2line binary to use for file names and line numbers.
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index b1d98da79be8b..32e15c9f53f3c 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2116,6 +2116,12 @@ static int annotation__config(const char *var, const char *value, void *data)
 			opt->offset_level = ANNOTATION__MAX_OFFSET_LEVEL;
 		else if (opt->offset_level < ANNOTATION__MIN_OFFSET_LEVEL)
 			opt->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
+	} else if (!strcmp(var, "annotate.disassemblers")) {
+		opt->disassemblers_str = strdup(value);
+		if (!opt->disassemblers_str) {
+			pr_err("Not enough memory for annotate.disassemblers\n");
+			return -1;
+		}
 	} else if (!strcmp(var, "annotate.hide_src_code")) {
 		opt->hide_src_code = perf_config_bool("hide_src_code", value);
 	} else if (!strcmp(var, "annotate.jump_arrows")) {
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 8b9e05a1932f2..194a05cbc506e 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -34,6 +34,9 @@ struct annotated_data_type;
 #define ANNOTATION__BR_CNTR_WIDTH 30
 #define ANNOTATION_DUMMY_LEN	256
 
+// llvm, capstone, objdump
+#define MAX_DISASSEMBLERS 3
+
 struct annotation_options {
 	bool hide_src_code,
 	     use_offset,
@@ -49,11 +52,14 @@ struct annotation_options {
 	     annotate_src,
 	     full_addr;
 	u8   offset_level;
+	u8   nr_disassemblers;
 	int  min_pcnt;
 	int  max_lines;
 	int  context;
 	char *objdump_path;
 	char *disassembler_style;
+	const char *disassemblers_str;
+	const char *disassemblers[MAX_DISASSEMBLERS];
 	const char *prefix;
 	const char *prefix_strip;
 	unsigned int percent_type;
diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index 6259dfe9aacc1..41a2b08670dc5 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -2213,13 +2213,65 @@ static int symbol__disassemble_objdump(const char *filename, struct symbol *sym,
 	return err;
 }
 
+static int annotation_options__init_disassemblers(struct annotation_options *options)
+{
+	char *disassembler;
+
+	if (options->disassemblers_str == NULL) {
+		const char *default_disassemblers_str =
+#ifdef HAVE_LIBLLVM_SUPPORT
+				"llvm,"
+#endif
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+				"capstone,"
+#endif
+				"objdump";
+
+		options->disassemblers_str = strdup(default_disassemblers_str);
+		if (!options->disassemblers_str)
+			goto out_enomem;
+	}
+
+	disassembler = strdup(options->disassemblers_str);
+	if (disassembler == NULL)
+		goto out_enomem;
+
+	while (1) {
+		char *comma = strchr(disassembler, ',');
+
+		if (comma != NULL)
+			*comma = '\0';
+
+		options->disassemblers[options->nr_disassemblers++] = strim(disassembler);
+
+		if (comma == NULL)
+			break;
+
+		disassembler = comma + 1;
+
+		if (options->nr_disassemblers >= MAX_DISASSEMBLERS) {
+			pr_debug("annotate.disassemblers can have at most %d entries, ignoring \"%s\"\n",
+				 MAX_DISASSEMBLERS, disassembler);
+			break;
+		}
+	}
+
+	return 0;
+
+out_enomem:
+	pr_err("Not enough memory for annotate.disassemblers\n");
+	return -1;
+}
+
 int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
+	struct annotation_options *options = args->options;
 	struct map *map = args->ms.map;
 	struct dso *dso = map__dso(map);
 	char symfs_filename[PATH_MAX];
 	bool delete_extract = false;
 	struct kcore_extract kce;
+	const char *disassembler;
 	bool decomp = false;
 	int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename));
 
@@ -2279,16 +2331,29 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		}
 	}
 
-	err = symbol__disassemble_llvm(symfs_filename, sym, args);
-	if (err == 0)
+	err = annotation_options__init_disassemblers(options);
+	if (err)
 		goto out_remove_tmp;
 
-	err = symbol__disassemble_capstone(symfs_filename, sym, args);
-	if (err == 0)
-		goto out_remove_tmp;
+	err = -1;
 
-	err = symbol__disassemble_objdump(symfs_filename, sym, args);
+	for (int i = 0; i < options->nr_disassemblers && err != 0; ++i) {
+		disassembler = options->disassemblers[i];
 
+		if (!strcmp(disassembler, "llvm"))
+			err = symbol__disassemble_llvm(symfs_filename, sym, args);
+		else if (!strcmp(disassembler, "capstone"))
+			err = symbol__disassemble_capstone(symfs_filename, sym, args);
+		else if (!strcmp(disassembler, "objdump"))
+			err = symbol__disassemble_objdump(symfs_filename, sym, args);
+		else
+			pr_debug("Unknown disassembler %s, skipping...\n", disassembler);
+	}
+
+	if (err == 0) {
+		pr_debug("Disassembled with %s\nannotate.disassemblers=%s\n",
+			 disassembler, options->disassemblers_str);
+	}
 out_remove_tmp:
 	if (decomp)
 		unlink(symfs_filename);

From 463c2031655c08007401b0eefed817ed2da2ebfb Mon Sep 17 00:00:00 2001
From: Andrew Kreimer <algonell@gmail.com>
Date: Fri, 8 Nov 2024 15:47:15 +0200
Subject: [PATCH 1110/1530] perf tools: Fix typos Muliplier -> Multiplier

There are some typos in fprintf messages.
Fix them via codespell.

Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Andrew Kreimer <algonell@gmail.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241108134728.25515-1-algonell@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-bts.c | 2 +-
 tools/perf/util/intel-pt.c  | 2 +-
 tools/perf/util/tsc.c       | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 3ea82d5e8d2ee..a7c589fecb980 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -808,7 +808,7 @@ static int intel_bts_synth_events(struct intel_bts *bts,
 static const char * const intel_bts_info_fmts[] = {
 	[INTEL_BTS_PMU_TYPE]		= "  PMU Type           %"PRId64"\n",
 	[INTEL_BTS_TIME_SHIFT]		= "  Time Shift         %"PRIu64"\n",
-	[INTEL_BTS_TIME_MULT]		= "  Time Muliplier     %"PRIu64"\n",
+	[INTEL_BTS_TIME_MULT]		= "  Time Multiplier    %"PRIu64"\n",
 	[INTEL_BTS_TIME_ZERO]		= "  Time Zero          %"PRIu64"\n",
 	[INTEL_BTS_CAP_USER_TIME_ZERO]	= "  Cap Time Zero      %"PRId64"\n",
 	[INTEL_BTS_SNAPSHOT_MODE]	= "  Snapshot mode      %"PRId64"\n",
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 3fe67bf652b64..30be6dfe09eba 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -4110,7 +4110,7 @@ static int intel_pt_parse_vm_tm_corr_args(struct intel_pt *pt)
 static const char * const intel_pt_info_fmts[] = {
 	[INTEL_PT_PMU_TYPE]		= "  PMU Type            %"PRId64"\n",
 	[INTEL_PT_TIME_SHIFT]		= "  Time Shift          %"PRIu64"\n",
-	[INTEL_PT_TIME_MULT]		= "  Time Muliplier      %"PRIu64"\n",
+	[INTEL_PT_TIME_MULT]		= "  Time Multiplier     %"PRIu64"\n",
 	[INTEL_PT_TIME_ZERO]		= "  Time Zero           %"PRIu64"\n",
 	[INTEL_PT_CAP_USER_TIME_ZERO]	= "  Cap Time Zero       %"PRId64"\n",
 	[INTEL_PT_TSC_BIT]		= "  TSC bit             %#"PRIx64"\n",
diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c
index 2e33a20e1e1bc..511a517ce613d 100644
--- a/tools/perf/util/tsc.c
+++ b/tools/perf/util/tsc.c
@@ -119,7 +119,7 @@ size_t perf_event__fprintf_time_conv(union perf_event *event, FILE *fp)
 	size_t ret;
 
 	ret  = fprintf(fp, "\n... Time Shift      %" PRI_lu64 "\n", tc->time_shift);
-	ret += fprintf(fp, "... Time Muliplier  %" PRI_lu64 "\n", tc->time_mult);
+	ret += fprintf(fp, "... Time Multiplier %" PRI_lu64 "\n", tc->time_mult);
 	ret += fprintf(fp, "... Time Zero       %" PRI_lu64 "\n", tc->time_zero);
 
 	/*

From d99b3125726aade4f5ec4aae04805134ab4b0abd Mon Sep 17 00:00:00 2001
From: Jean-Philippe Romain <jean-philippe.romain@foss.st.com>
Date: Fri, 8 Nov 2024 18:58:01 -0800
Subject: [PATCH 1111/1530] perf list: Fix topic and pmu_name argument order

Fix function definitions to match header file declaration. Fix two
callers to pass the arguments in the right order.

On Intel Tigerlake, before:
```
$ perf list -j|grep "\"Topic\""|sort|uniq
        "Topic": "cache",
        "Topic": "cpu",
        "Topic": "floating point",
        "Topic": "frontend",
        "Topic": "memory",
        "Topic": "other",
        "Topic": "pfm icl",
        "Topic": "pfm ix86arch",
        "Topic": "pfm perf_raw",
        "Topic": "pipeline",
        "Topic": "tool",
        "Topic": "uncore interconnect",
        "Topic": "uncore memory",
        "Topic": "uncore other",
        "Topic": "virtual memory",
$ perf list -j|grep "\"Unit\""|sort|uniq
        "Unit": "cache",
        "Unit": "cpu",
        "Unit": "cstate_core",
        "Unit": "cstate_pkg",
        "Unit": "i915",
        "Unit": "icl",
        "Unit": "intel_bts",
        "Unit": "intel_pt",
        "Unit": "ix86arch",
        "Unit": "msr",
        "Unit": "perf_raw",
        "Unit": "power",
        "Unit": "tool",
        "Unit": "uncore_arb",
        "Unit": "uncore_clock",
        "Unit": "uncore_imc_free_running_0",
        "Unit": "uncore_imc_free_running_1",
```

After:
```
$ perf list -j|grep "\"Topic\""|sort|uniq
        "Topic": "cache",
        "Topic": "floating point",
        "Topic": "frontend",
        "Topic": "memory",
        "Topic": "other",
        "Topic": "pfm icl",
        "Topic": "pfm ix86arch",
        "Topic": "pfm perf_raw",
        "Topic": "pipeline",
        "Topic": "tool",
        "Topic": "uncore interconnect",
        "Topic": "uncore memory",
        "Topic": "uncore other",
        "Topic": "virtual memory",
$ perf list -j|grep "\"Unit\""|sort|uniq
        "Unit": "cpu",
        "Unit": "cstate_core",
        "Unit": "cstate_pkg",
        "Unit": "i915",
        "Unit": "icl",
        "Unit": "intel_bts",
        "Unit": "intel_pt",
        "Unit": "ix86arch",
        "Unit": "msr",
        "Unit": "perf_raw",
        "Unit": "power",
        "Unit": "tool",
        "Unit": "uncore_arb",
        "Unit": "uncore_clock",
        "Unit": "uncore_imc_free_running_0",
        "Unit": "uncore_imc_free_running_1",
```

Fixes: e5c6109f4813246a ("perf list: Reorganize to use callbacks to allow honouring command line options")
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Jean-Philippe Romain <jean-philippe.romain@foss.st.com>
Tested-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Junhao He <hejunhao3@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241109025801.560378-1-irogers@google.com
[ I fixed the two callers and added it to Jean-Phillippe's original change. ]
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-list.c | 4 ++--
 tools/perf/util/pfm.c     | 4 ++--
 tools/perf/util/pmus.c    | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index b8378ba18c282..9e7fdfcdd7ffb 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -113,7 +113,7 @@ static void wordwrap(FILE *fp, const char *s, int start, int max, int corr)
 	}
 }
 
-static void default_print_event(void *ps, const char *pmu_name, const char *topic,
+static void default_print_event(void *ps, const char *topic, const char *pmu_name,
 				const char *event_name, const char *event_alias,
 				const char *scale_unit __maybe_unused,
 				bool deprecated, const char *event_type_desc,
@@ -354,7 +354,7 @@ static void fix_escape_fprintf(FILE *fp, struct strbuf *buf, const char *fmt, ..
 	fputs(buf->buf, fp);
 }
 
-static void json_print_event(void *ps, const char *pmu_name, const char *topic,
+static void json_print_event(void *ps, const char *topic, const char *pmu_name,
 			     const char *event_name, const char *event_alias,
 			     const char *scale_unit,
 			     bool deprecated, const char *event_type_desc,
diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c
index 5ccfe4b64cdfe..0dacc133ed396 100644
--- a/tools/perf/util/pfm.c
+++ b/tools/perf/util/pfm.c
@@ -233,7 +233,7 @@ print_libpfm_event(const struct print_callbacks *print_cb, void *print_state,
 	}
 
 	if (is_libpfm_event_supported(name, cpus, threads)) {
-		print_cb->print_event(print_state, pinfo->name, topic,
+		print_cb->print_event(print_state, topic, pinfo->name,
 				      name, info->equiv,
 				      /*scale_unit=*/NULL,
 				      /*deprecated=*/NULL, "PFM event",
@@ -267,8 +267,8 @@ print_libpfm_event(const struct print_callbacks *print_cb, void *print_state,
 				continue;
 
 			print_cb->print_event(print_state,
-					pinfo->name,
 					topic,
+					pinfo->name,
 					name, /*alias=*/NULL,
 					/*scale_unit=*/NULL,
 					/*deprecated=*/NULL, "PFM event",
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index 451c6e00ad704..b493da0d22ef7 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -503,8 +503,8 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p
 			goto free;
 
 		print_cb->print_event(print_state,
-				aliases[j].pmu_name,
 				aliases[j].topic,
+				aliases[j].pmu_name,
 				aliases[j].name,
 				aliases[j].alias,
 				aliases[j].scale_unit,

From b81bb703372837a6d6b4cc964b6db58d1dfdba8b Mon Sep 17 00:00:00 2001
From: Luo Yifan <luoyifan@cmss.chinamobile.com>
Date: Mon, 11 Nov 2024 17:52:09 +0800
Subject: [PATCH 1112/1530] perf timechart: Remove redundant variable
 assignment

This patch makes a minor change that removes a redundant variable
assignment. The assignment before the for loop is duplicated by the
initialization within the loop header.

Signed-off-by: Luo Yifan <luoyifan@cmss.chinamobile.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241111095209.276332-1-luoyifan@cmss.chinamobile.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-timechart.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 9b50076449bd0..068d297aaf44b 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1158,7 +1158,6 @@ static void draw_io_bars(struct timechart *tchart)
 			}
 
 			svg_box(Y, c->start_time, c->end_time, "process3");
-			sample = c->io_samples;
 			for (sample = c->io_samples; sample; sample = sample->next) {
 				double h = (double)sample->bytes / c->max_bytes;
 

From 31bedc1fb1d93250ae1900ee92ccd56689956d22 Mon Sep 17 00:00:00 2001
From: Luo Yifan <luoyifan@cmss.chinamobile.com>
Date: Mon, 11 Nov 2024 17:17:01 +0800
Subject: [PATCH 1113/1530] libsubcmd: Move va_end() before exit

This patch makes a minor adjustment by moving the va_end call before
exit. Since the exit() function terminates the program, any code
after exit(128) (i.e., va_end(params)) is unreachable and thus not
executed. Placing va_end before exit ensures that the va_list is
properly cleaned up.

Signed-off-by: Luo Yifan <luoyifan@cmss.chinamobile.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/20241111091701.275496-1-luoyifan@cmss.chinamobile.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/subcmd/subcmd-util.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h
index dfac76e35ac73..c742b08815dcb 100644
--- a/tools/lib/subcmd/subcmd-util.h
+++ b/tools/lib/subcmd/subcmd-util.h
@@ -20,8 +20,8 @@ static __noreturn inline void die(const char *err, ...)
 
 	va_start(params, err);
 	report(" Fatal: ", err, params);
-	exit(128);
 	va_end(params);
+	exit(128);
 }
 
 #define zfree(ptr) ({ free(*ptr); *ptr = NULL; })

From 6168efbebace0db443185d4c6701ca8170a8788d Mon Sep 17 00:00:00 2001
From: Mayank Rana <quic_mrana@quicinc.com>
Date: Mon, 11 Nov 2024 14:11:52 +0530
Subject: [PATCH 1114/1530] PCI: starfive: Enable controller runtime PM before
 probing host bridge

A PCI controller device, e.g., StarFive, is parent to PCI host bridge
device. We must enable runtime PM of the controller before enabling runtime
PM of the host bridge, which will happen in pci_host_probe(), to avoid this
warning:

  pcie-starfive 940000000.pcie: Enabling runtime PM for inactive device with active children

Fix this issue by enabling StarFive controller device's runtime PM before
calling pci_host_probe() in plda_pcie_host_init().

Link: https://lore.kernel.org/r/20241111-runtime_pm-v7-1-9c164eefcd87@quicinc.com
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Mayank Rana <quic_mrana@quicinc.com>
[bhelgaas: commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/plda/pcie-starfive.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/controller/plda/pcie-starfive.c b/drivers/pci/controller/plda/pcie-starfive.c
index c9933ecf68338..0564fdce47c2a 100644
--- a/drivers/pci/controller/plda/pcie-starfive.c
+++ b/drivers/pci/controller/plda/pcie-starfive.c
@@ -404,6 +404,9 @@ static int starfive_pcie_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_get_sync(&pdev->dev);
+
 	plda->host_ops = &sf_host_ops;
 	plda->num_events = PLDA_MAX_EVENT_NUM;
 	/* mask doorbell event */
@@ -413,11 +416,12 @@ static int starfive_pcie_probe(struct platform_device *pdev)
 	plda->events_bitmap <<= PLDA_NUM_DMA_EVENTS;
 	ret = plda_pcie_host_init(&pcie->plda, &starfive_pcie_ops,
 				  &stf_pcie_event);
-	if (ret)
+	if (ret) {
+		pm_runtime_put_sync(&pdev->dev);
+		pm_runtime_disable(&pdev->dev);
 		return ret;
+	}
 
-	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
 	platform_set_drvdata(pdev, pcie);
 
 	return 0;

From dc421bb3c0db2aac926b548d259d3b550394908e Mon Sep 17 00:00:00 2001
From: Krishna chaitanya chundru <quic_krichai@quicinc.com>
Date: Mon, 11 Nov 2024 14:11:53 +0530
Subject: [PATCH 1115/1530] PCI: Enable runtime PM of the host bridge

The controller driver is the parent device of the PCIe host bridge,
PCI-PCI bridge and PCIe endpoint as shown below.

  PCIe controller (Top level parent & parent of host bridge)
                  |
                  v
  PCIe Host bridge (Parent of PCI-PCI bridge)
                  |
                  v
  PCI-PCI bridge (Parent of endpoint driver)
                  |
                  v
          PCIe endpoint driver

Now, when the controller device goes to runtime suspend, PM framework will
check the runtime PM state of the child device (host bridge) and will find
it to be disabled. So it will allow the parent (controller device) to go to
runtime suspend. Only if the child device's state was 'active' it will
prevent the parent to get suspended.

It is a property of the runtime PM framework that it can only follow
continuous dependency chains.  That is, if there is a device with runtime
PM disabled in a dependency chain, runtime PM cannot be enabled for devices
below it and above it in that chain both at the same time.

Since runtime PM is disabled for host bridge, the state of the child
devices under the host bridge is not taken into account by PM framework for
the top level parent, PCIe controller. So the PM framework allows the
controller driver to enter runtime PM irrespective of the state of the
devices under the host bridge. And this causes the topology breakage and
also possible PM issues like controller driver going to runtime suspend
while the endpoint driver is doing transfers.

Because of the above, in order to enable runtime PM for a PCIe controller
device, one needs to ensure that runtime PM is enabled for all devices in
every dependency chain between it and any PCIe endpoint (as runtime PM is
enabled for PCIe endpoints).

This means that runtime PM needs to be enabled for the host bridge device,
which is present in all of these dependency chains.

After this change, the host bridge device will be runtime-suspended by the
runtime PM framework automatically after suspending its last child and it
will be runtime-resumed automatically before resuming its first child which
will allow the runtime PM framework to track dependencies between the host
bridge device and all of its descendants.

The PM framework expects parent runtime PM to be enabled before enabling
runtime PM of the child. Ensure pm_runtime_enable() is called for the
controller drivers before calling pci_host_probe().

Link: https://lore.kernel.org/r/20241111-runtime_pm-v7-2-9c164eefcd87@quicinc.com
Signed-off-by: Krishna chaitanya chundru <quic_krichai@quicinc.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/probe.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 4f68414c30860..8b14d3af057ae 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -3106,6 +3106,17 @@ int pci_host_probe(struct pci_host_bridge *bridge)
 		pcie_bus_configure_settings(child);
 
 	pci_bus_add_devices(bus);
+
+	/*
+	 * Ensure pm_runtime_enable() is called for the controller drivers
+	 * before calling pci_host_probe(). The PM framework expects that
+	 * if the parent device supports runtime PM, it will be enabled
+	 * before child runtime PM is enabled.
+	 */
+	pm_runtime_set_active(&bridge->dev);
+	pm_runtime_no_callbacks(&bridge->dev);
+	devm_pm_runtime_enable(&bridge->dev);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pci_host_probe);

From b398f91779b86e5f285d9f0df5d2e753ddcdac3f Mon Sep 17 00:00:00 2001
From: Longfang Liu <liulongfang@huawei.com>
Date: Tue, 12 Nov 2024 15:33:21 +0800
Subject: [PATCH 1116/1530] hisi_acc_vfio_pci: register debugfs for hisilicon
 migration driver

On the debugfs framework of VFIO, if the CONFIG_VFIO_DEBUGFS macro is
enabled, the debug function is registered for the live migration driver
of the HiSilicon accelerator device.

After registering the HiSilicon accelerator device on the debugfs
framework of live migration of vfio, a directory file "hisi_acc"
of debugfs is created, and then three debug function files are
created in this directory:

   vfio
    |
    +---<dev_name1>
    |    +---migration
    |        +--state
    |        +--hisi_acc
    |            +--dev_data
    |            +--migf_data
    |            +--cmd_state
    |
    +---<dev_name2>
         +---migration
             +--state
             +--hisi_acc
                 +--dev_data
                 +--migf_data
                 +--cmd_state

dev_data file: read device data that needs to be migrated from the
current device in real time
migf_data file: read the migration data of the last live migration
from the current driver.
cmd_state: used to get the cmd channel state for the device.

+----------------+        +--------------+       +---------------+
| migration dev  |        |   src  dev   |       |   dst  dev    |
+-------+--------+        +------+-------+       +-------+-------+
        |                        |                       |
        |                 +------v-------+       +-------v-------+
        |                 |  saving_migf |       | resuming_migf |
  read  |                 |     file     |       |     file      |
        |                 +------+-------+       +-------+-------+
        |                        |          copy         |
        |                        +------------+----------+
        |                                     |
+-------v--------+                    +-------v--------+
|   data buffer  |                    |   debug_migf   |
+-------+--------+                    +-------+--------+
        |                                     |
   cat  |                                 cat |
+-------v--------+                    +-------v--------+
|   dev_data     |                    |   migf_data    |
+----------------+                    +----------------+

When accessing debugfs, user can obtain the most recent status data
of the device through the "dev_data" file. It can read recent
complete status data of the device. If the current device is being
migrated, it will wait for it to complete.
The data for the last completed migration function will be stored
in debug_migf. Users can read it via "migf_data".

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Link: https://lore.kernel.org/r/20241112073322.54550-4-liulongfang@huawei.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 191 ++++++++++++++++++
 .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h    |  19 ++
 2 files changed, 210 insertions(+)

diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index c4a74e38c78ae..451c639299eb3 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -627,15 +627,31 @@ static void hisi_acc_vf_disable_fd(struct hisi_acc_vf_migration_file *migf)
 	mutex_unlock(&migf->lock);
 }
 
+static void
+hisi_acc_debug_migf_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev,
+			 struct hisi_acc_vf_migration_file *src_migf)
+{
+	struct hisi_acc_vf_migration_file *dst_migf = hisi_acc_vdev->debug_migf;
+
+	if (!dst_migf)
+		return;
+
+	dst_migf->total_length = src_migf->total_length;
+	memcpy(&dst_migf->vf_data, &src_migf->vf_data,
+	       sizeof(struct acc_vf_data));
+}
+
 static void hisi_acc_vf_disable_fds(struct hisi_acc_vf_core_device *hisi_acc_vdev)
 {
 	if (hisi_acc_vdev->resuming_migf) {
+		hisi_acc_debug_migf_copy(hisi_acc_vdev, hisi_acc_vdev->resuming_migf);
 		hisi_acc_vf_disable_fd(hisi_acc_vdev->resuming_migf);
 		fput(hisi_acc_vdev->resuming_migf->filp);
 		hisi_acc_vdev->resuming_migf = NULL;
 	}
 
 	if (hisi_acc_vdev->saving_migf) {
+		hisi_acc_debug_migf_copy(hisi_acc_vdev, hisi_acc_vdev->saving_migf);
 		hisi_acc_vf_disable_fd(hisi_acc_vdev->saving_migf);
 		fput(hisi_acc_vdev->saving_migf->filp);
 		hisi_acc_vdev->saving_migf = NULL;
@@ -1292,6 +1308,129 @@ static long hisi_acc_vfio_pci_ioctl(struct vfio_device *core_vdev, unsigned int
 	return vfio_pci_core_ioctl(core_vdev, cmd, arg);
 }
 
+static int hisi_acc_vf_debug_check(struct seq_file *seq, struct vfio_device *vdev)
+{
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
+	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
+	int ret;
+
+	lockdep_assert_held(&hisi_acc_vdev->open_mutex);
+	/*
+	 * When the device is not opened, the io_base is not mapped.
+	 * The driver cannot perform device read and write operations.
+	 */
+	if (!hisi_acc_vdev->dev_opened) {
+		seq_puts(seq, "device not opened!\n");
+		return -EINVAL;
+	}
+
+	ret = qm_wait_dev_not_ready(vf_qm);
+	if (ret) {
+		seq_puts(seq, "VF device not ready!\n");
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int hisi_acc_vf_debug_cmd(struct seq_file *seq, void *data)
+{
+	struct device *vf_dev = seq->private;
+	struct vfio_pci_core_device *core_device = dev_get_drvdata(vf_dev);
+	struct vfio_device *vdev = &core_device->vdev;
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
+	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
+	u64 value;
+	int ret;
+
+	mutex_lock(&hisi_acc_vdev->open_mutex);
+	ret = hisi_acc_vf_debug_check(seq, vdev);
+	if (ret) {
+		mutex_unlock(&hisi_acc_vdev->open_mutex);
+		return ret;
+	}
+
+	value = readl(vf_qm->io_base + QM_MB_CMD_SEND_BASE);
+	if (value == QM_MB_CMD_NOT_READY) {
+		mutex_unlock(&hisi_acc_vdev->open_mutex);
+		seq_puts(seq, "mailbox cmd channel not ready!\n");
+		return -EINVAL;
+	}
+	mutex_unlock(&hisi_acc_vdev->open_mutex);
+	seq_puts(seq, "mailbox cmd channel ready!\n");
+
+	return 0;
+}
+
+static int hisi_acc_vf_dev_read(struct seq_file *seq, void *data)
+{
+	struct device *vf_dev = seq->private;
+	struct vfio_pci_core_device *core_device = dev_get_drvdata(vf_dev);
+	struct vfio_device *vdev = &core_device->vdev;
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
+	size_t vf_data_sz = offsetofend(struct acc_vf_data, padding);
+	struct acc_vf_data *vf_data;
+	int ret;
+
+	mutex_lock(&hisi_acc_vdev->open_mutex);
+	ret = hisi_acc_vf_debug_check(seq, vdev);
+	if (ret) {
+		mutex_unlock(&hisi_acc_vdev->open_mutex);
+		return ret;
+	}
+
+	mutex_lock(&hisi_acc_vdev->state_mutex);
+	vf_data = kzalloc(sizeof(*vf_data), GFP_KERNEL);
+	if (!vf_data) {
+		ret = -ENOMEM;
+		goto mutex_release;
+	}
+
+	vf_data->vf_qm_state = hisi_acc_vdev->vf_qm_state;
+	ret = vf_qm_read_data(&hisi_acc_vdev->vf_qm, vf_data);
+	if (ret)
+		goto migf_err;
+
+	seq_hex_dump(seq, "Dev Data:", DUMP_PREFIX_OFFSET, 16, 1,
+		     (const void *)vf_data, vf_data_sz, false);
+
+	seq_printf(seq,
+		   "guest driver load: %u\n"
+		   "data size: %lu\n",
+		   hisi_acc_vdev->vf_qm_state,
+		   sizeof(struct acc_vf_data));
+
+migf_err:
+	kfree(vf_data);
+mutex_release:
+	mutex_unlock(&hisi_acc_vdev->state_mutex);
+	mutex_unlock(&hisi_acc_vdev->open_mutex);
+
+	return ret;
+}
+
+static int hisi_acc_vf_migf_read(struct seq_file *seq, void *data)
+{
+	struct device *vf_dev = seq->private;
+	struct vfio_pci_core_device *core_device = dev_get_drvdata(vf_dev);
+	struct vfio_device *vdev = &core_device->vdev;
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
+	size_t vf_data_sz = offsetofend(struct acc_vf_data, padding);
+	struct hisi_acc_vf_migration_file *debug_migf = hisi_acc_vdev->debug_migf;
+
+	/* Check whether the live migration operation has been performed */
+	if (debug_migf->total_length < QM_MATCH_SIZE) {
+		seq_puts(seq, "device not migrated!\n");
+		return -EAGAIN;
+	}
+
+	seq_hex_dump(seq, "Mig Data:", DUMP_PREFIX_OFFSET, 16, 1,
+		     (const void *)&debug_migf->vf_data, vf_data_sz, false);
+	seq_printf(seq, "migrate data length: %lu\n", debug_migf->total_length);
+
+	return 0;
+}
+
 static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
 {
 	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(core_vdev);
@@ -1303,12 +1442,16 @@ static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
 		return ret;
 
 	if (core_vdev->mig_ops) {
+		mutex_lock(&hisi_acc_vdev->open_mutex);
 		ret = hisi_acc_vf_qm_init(hisi_acc_vdev);
 		if (ret) {
+			mutex_unlock(&hisi_acc_vdev->open_mutex);
 			vfio_pci_core_disable(vdev);
 			return ret;
 		}
 		hisi_acc_vdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
+		hisi_acc_vdev->dev_opened = true;
+		mutex_unlock(&hisi_acc_vdev->open_mutex);
 	}
 
 	vfio_pci_core_finish_enable(vdev);
@@ -1320,7 +1463,10 @@ static void hisi_acc_vfio_pci_close_device(struct vfio_device *core_vdev)
 	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(core_vdev);
 	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
 
+	mutex_lock(&hisi_acc_vdev->open_mutex);
+	hisi_acc_vdev->dev_opened = false;
 	iounmap(vf_qm->io_base);
+	mutex_unlock(&hisi_acc_vdev->open_mutex);
 	vfio_pci_core_close_device(core_vdev);
 }
 
@@ -1340,6 +1486,7 @@ static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
 	hisi_acc_vdev->pf_qm = pf_qm;
 	hisi_acc_vdev->vf_dev = pdev;
 	mutex_init(&hisi_acc_vdev->state_mutex);
+	mutex_init(&hisi_acc_vdev->open_mutex);
 
 	core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY;
 	core_vdev->mig_ops = &hisi_acc_vfio_pci_migrn_state_ops;
@@ -1385,6 +1532,47 @@ static const struct vfio_device_ops hisi_acc_vfio_pci_ops = {
 	.detach_ioas = vfio_iommufd_physical_detach_ioas,
 };
 
+static void hisi_acc_vfio_debug_init(struct hisi_acc_vf_core_device *hisi_acc_vdev)
+{
+	struct vfio_device *vdev = &hisi_acc_vdev->core_device.vdev;
+	struct hisi_acc_vf_migration_file *migf;
+	struct dentry *vfio_dev_migration;
+	struct dentry *vfio_hisi_acc;
+	struct device *dev = vdev->dev;
+
+	if (!debugfs_initialized() ||
+	    !IS_ENABLED(CONFIG_VFIO_DEBUGFS))
+		return;
+
+	if (vdev->ops != &hisi_acc_vfio_pci_migrn_ops)
+		return;
+
+	vfio_dev_migration = debugfs_lookup("migration", vdev->debug_root);
+	if (!vfio_dev_migration) {
+		dev_err(dev, "failed to lookup migration debugfs file!\n");
+		return;
+	}
+
+	migf = kzalloc(sizeof(*migf), GFP_KERNEL);
+	if (!migf)
+		return;
+	hisi_acc_vdev->debug_migf = migf;
+
+	vfio_hisi_acc = debugfs_create_dir("hisi_acc", vfio_dev_migration);
+	debugfs_create_devm_seqfile(dev, "dev_data", vfio_hisi_acc,
+				    hisi_acc_vf_dev_read);
+	debugfs_create_devm_seqfile(dev, "migf_data", vfio_hisi_acc,
+				    hisi_acc_vf_migf_read);
+	debugfs_create_devm_seqfile(dev, "cmd_state", vfio_hisi_acc,
+				    hisi_acc_vf_debug_cmd);
+}
+
+static void hisi_acc_vf_debugfs_exit(struct hisi_acc_vf_core_device *hisi_acc_vdev)
+{
+	kfree(hisi_acc_vdev->debug_migf);
+	hisi_acc_vdev->debug_migf = NULL;
+}
+
 static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct hisi_acc_vf_core_device *hisi_acc_vdev;
@@ -1411,6 +1599,8 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device
 	ret = vfio_pci_core_register_device(&hisi_acc_vdev->core_device);
 	if (ret)
 		goto out_put_vdev;
+
+	hisi_acc_vfio_debug_init(hisi_acc_vdev);
 	return 0;
 
 out_put_vdev:
@@ -1423,6 +1613,7 @@ static void hisi_acc_vfio_pci_remove(struct pci_dev *pdev)
 	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_drvdata(pdev);
 
 	vfio_pci_core_unregister_device(&hisi_acc_vdev->core_device);
+	hisi_acc_vf_debugfs_exit(hisi_acc_vdev);
 	vfio_put_device(&hisi_acc_vdev->core_device.vdev);
 }
 
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
index 5bab46602fad2..245d7537b2bcd 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
@@ -32,6 +32,7 @@
 #define QM_SQC_VFT_BASE_MASK_V2		GENMASK(15, 0)
 #define QM_SQC_VFT_NUM_SHIFT_V2		45
 #define QM_SQC_VFT_NUM_MASK_V2		GENMASK(9, 0)
+#define QM_MB_CMD_NOT_READY	0xffffffff
 
 /* RW regs */
 #define QM_REGS_MAX_LEN		7
@@ -99,6 +100,13 @@ struct hisi_acc_vf_migration_file {
 struct hisi_acc_vf_core_device {
 	struct vfio_pci_core_device core_device;
 	u8 match_done;
+	/*
+	 * io_base is only valid when dev_opened is true,
+	 * which is protected by open_mutex.
+	 */
+	bool dev_opened;
+	/* Ensure the accuracy of dev_opened operation */
+	struct mutex open_mutex;
 
 	/* For migration state */
 	struct mutex state_mutex;
@@ -107,9 +115,20 @@ struct hisi_acc_vf_core_device {
 	struct pci_dev *vf_dev;
 	struct hisi_qm *pf_qm;
 	struct hisi_qm vf_qm;
+	/*
+	 * vf_qm_state represents the QM_VF_STATE register value.
+	 * It is set by Guest driver for the ACC VF dev indicating
+	 * the driver has loaded and configured the dev correctly.
+	 */
 	u32 vf_qm_state;
 	int vf_id;
 	struct hisi_acc_vf_migration_file *resuming_migf;
 	struct hisi_acc_vf_migration_file *saving_migf;
+
+	/*
+	 * It holds migration data corresponding to the last migration
+	 * and is used by the debugfs interface to report it.
+	 */
+	struct hisi_acc_vf_migration_file *debug_migf;
 };
 #endif /* HISI_ACC_VFIO_PCI_H */

From a13bf78feebd432c31cff9d0d84968c8b78bcbfb Mon Sep 17 00:00:00 2001
From: Longfang Liu <liulongfang@huawei.com>
Date: Tue, 12 Nov 2024 15:33:22 +0800
Subject: [PATCH 1117/1530] Documentation: add debugfs description for hisi
 migration

Add a debugfs document description file to help users understand
how to use the hisilicon accelerator live migration driver's
debugfs.

Update the file paths that need to be maintained in MAINTAINERS

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Link: https://lore.kernel.org/r/20241112073322.54550-5-liulongfang@huawei.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 .../ABI/testing/debugfs-hisi-migration        | 25 +++++++++++++++++++
 1 file changed, 25 insertions(+)
 create mode 100644 Documentation/ABI/testing/debugfs-hisi-migration

diff --git a/Documentation/ABI/testing/debugfs-hisi-migration b/Documentation/ABI/testing/debugfs-hisi-migration
new file mode 100644
index 0000000000000..2c01b2d387ddd
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-hisi-migration
@@ -0,0 +1,25 @@
+What:		/sys/kernel/debug/vfio/<device>/migration/hisi_acc/dev_data
+Date:		Jan 2025
+KernelVersion:  6.13
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	Read the configuration data and some status data
+		required for device live migration. These data include device
+		status data, queue configuration data, some task configuration
+		data and device attribute data. The output format of the data
+		is defined by the live migration driver.
+
+What:		/sys/kernel/debug/vfio/<device>/migration/hisi_acc/migf_data
+Date:		Jan 2025
+KernelVersion:  6.13
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	Read the data from the last completed live migration.
+		This data includes the same device status data as in "dev_data".
+		The migf_data is the dev_data that is migrated.
+
+What:		/sys/kernel/debug/vfio/<device>/migration/hisi_acc/cmd_state
+Date:		Jan 2025
+KernelVersion:  6.13
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	Used to obtain the device command sending and receiving
+		channel status. Returns failure or success logs based on the
+		results.

From 7c1ae151e81268db1fe8c8a473d922fc5ba47b72 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Wed, 13 Nov 2024 13:51:54 +0200
Subject: [PATCH 1118/1530] virtio_pci: Introduce device parts access commands

Introduce device parts access commands via the admin queue.

These commands and their structure adhere to the Virtio 1.4
specification.

Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20241113115200.209269-2-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 include/uapi/linux/virtio_pci.h | 131 ++++++++++++++++++++++++++++++++
 1 file changed, 131 insertions(+)

diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index a8208492e8227..1beb317df1b9b 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -40,6 +40,7 @@
 #define _LINUX_VIRTIO_PCI_H
 
 #include <linux/types.h>
+#include <linux/kernel.h>
 
 #ifndef VIRTIO_PCI_NO_LEGACY
 
@@ -240,6 +241,17 @@ struct virtio_pci_cfg_cap {
 #define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ		0x5
 #define VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO		0x6
 
+/* Device parts access commands. */
+#define VIRTIO_ADMIN_CMD_CAP_ID_LIST_QUERY		0x7
+#define VIRTIO_ADMIN_CMD_DEVICE_CAP_GET			0x8
+#define VIRTIO_ADMIN_CMD_DRIVER_CAP_SET			0x9
+#define VIRTIO_ADMIN_CMD_RESOURCE_OBJ_CREATE		0xa
+#define VIRTIO_ADMIN_CMD_RESOURCE_OBJ_DESTROY		0xd
+#define VIRTIO_ADMIN_CMD_DEV_PARTS_METADATA_GET		0xe
+#define VIRTIO_ADMIN_CMD_DEV_PARTS_GET			0xf
+#define VIRTIO_ADMIN_CMD_DEV_PARTS_SET			0x10
+#define VIRTIO_ADMIN_CMD_DEV_MODE_SET			0x11
+
 struct virtio_admin_cmd_hdr {
 	__le16 opcode;
 	/*
@@ -286,4 +298,123 @@ struct virtio_admin_cmd_notify_info_result {
 	struct virtio_admin_cmd_notify_info_data entries[VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO];
 };
 
+#define VIRTIO_DEV_PARTS_CAP 0x0000
+
+struct virtio_dev_parts_cap {
+	__u8 get_parts_resource_objects_limit;
+	__u8 set_parts_resource_objects_limit;
+};
+
+#define MAX_CAP_ID __KERNEL_DIV_ROUND_UP(VIRTIO_DEV_PARTS_CAP + 1, 64)
+
+struct virtio_admin_cmd_query_cap_id_result {
+	__le64 supported_caps[MAX_CAP_ID];
+};
+
+struct virtio_admin_cmd_cap_get_data {
+	__le16 id;
+	__u8 reserved[6];
+};
+
+struct virtio_admin_cmd_cap_set_data {
+	__le16 id;
+	__u8 reserved[6];
+	__u8 cap_specific_data[];
+};
+
+struct virtio_admin_cmd_resource_obj_cmd_hdr {
+	__le16 type;
+	__u8 reserved[2];
+	__le32 id; /* Indicates unique resource object id per resource object type */
+};
+
+struct virtio_admin_cmd_resource_obj_create_data {
+	struct virtio_admin_cmd_resource_obj_cmd_hdr hdr;
+	__le64 flags;
+	__u8 resource_obj_specific_data[];
+};
+
+#define VIRTIO_RESOURCE_OBJ_DEV_PARTS 0
+
+#define VIRTIO_RESOURCE_OBJ_DEV_PARTS_TYPE_GET 0
+#define VIRTIO_RESOURCE_OBJ_DEV_PARTS_TYPE_SET 1
+
+struct virtio_resource_obj_dev_parts {
+	__u8 type;
+	__u8 reserved[7];
+};
+
+#define VIRTIO_ADMIN_CMD_DEV_PARTS_METADATA_TYPE_SIZE 0
+#define VIRTIO_ADMIN_CMD_DEV_PARTS_METADATA_TYPE_COUNT 1
+#define VIRTIO_ADMIN_CMD_DEV_PARTS_METADATA_TYPE_LIST 2
+
+struct virtio_admin_cmd_dev_parts_metadata_data {
+	struct virtio_admin_cmd_resource_obj_cmd_hdr hdr;
+	__u8 type;
+	__u8 reserved[7];
+};
+
+#define VIRTIO_DEV_PART_F_OPTIONAL 0
+
+struct virtio_dev_part_hdr {
+	__le16 part_type;
+	__u8 flags;
+	__u8 reserved;
+	union {
+		struct {
+			__le32 offset;
+			__le32 reserved;
+		} pci_common_cfg;
+		struct {
+			__le16 index;
+			__u8 reserved[6];
+		} vq_index;
+	} selector;
+	__le32 length;
+};
+
+struct virtio_dev_part {
+	struct virtio_dev_part_hdr hdr;
+	__u8 value[];
+};
+
+struct virtio_admin_cmd_dev_parts_metadata_result {
+	union {
+		struct {
+			__le32 size;
+			__le32 reserved;
+		} parts_size;
+		struct {
+			__le32 count;
+			__le32 reserved;
+		} hdr_list_count;
+		struct {
+			__le32 count;
+			__le32 reserved;
+			struct virtio_dev_part_hdr hdrs[];
+		} hdr_list;
+	};
+};
+
+#define VIRTIO_ADMIN_CMD_DEV_PARTS_GET_TYPE_SELECTED 0
+#define VIRTIO_ADMIN_CMD_DEV_PARTS_GET_TYPE_ALL 1
+
+struct virtio_admin_cmd_dev_parts_get_data {
+	struct virtio_admin_cmd_resource_obj_cmd_hdr hdr;
+	__u8 type;
+	__u8 reserved[7];
+	struct virtio_dev_part_hdr hdr_list[];
+};
+
+struct virtio_admin_cmd_dev_parts_set_data {
+	struct virtio_admin_cmd_resource_obj_cmd_hdr hdr;
+	struct virtio_dev_part parts[];
+};
+
+#define VIRTIO_ADMIN_CMD_DEV_MODE_F_STOPPED 0
+
+struct virtio_admin_cmd_dev_mode_set_data {
+	__u8 flags;
+};
+
 #endif

From 704806ca400e5daa86c110f14bfdda9d28203bb7 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Wed, 13 Nov 2024 13:51:55 +0200
Subject: [PATCH 1119/1530] virtio: Extend the admin command to include the
 result size

Extend the admin command by incorporating a result size field.

This allows higher layers to determine the actual result size from the
backend when this information is not included in the result_sg.

The additional information introduced here will be used in subsequent
patches of this series.

Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20241113115200.209269-3-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 4 +++-
 include/linux/virtio.h             | 1 +
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 9193c30d640ae..487d04610ecbb 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -64,8 +64,10 @@ void vp_modern_avq_done(struct virtqueue *vq)
 	spin_lock_irqsave(&admin_vq->lock, flags);
 	do {
 		virtqueue_disable_cb(vq);
-		while ((cmd = virtqueue_get_buf(vq, &len)))
+		while ((cmd = virtqueue_get_buf(vq, &len))) {
+			cmd->result_sg_size = len;
 			complete(&cmd->completion);
+		}
 	} while (!virtqueue_enable_cb(vq));
 	spin_unlock_irqrestore(&admin_vq->lock, flags);
 }
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 306137a15d075..b5f7a611715ab 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -111,6 +111,7 @@ struct virtio_admin_cmd {
 	struct scatterlist *data_sg;
 	struct scatterlist *result_sg;
 	struct completion completion;
+	u32 result_sg_size;
 	int ret;
 };
 

From bfcad518605d927eff17ffb8ce0a828d7b7ac79f Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Wed, 13 Nov 2024 13:51:56 +0200
Subject: [PATCH 1120/1530] virtio: Manage device and driver capabilities via
 the admin commands

Manage device and driver capabilities via the admin commands.

The device exposes its supported features and resource object limits via
an administrative command called VIRTIO_ADMIN_CMD_CAP_ID_LIST_QUERY,
using the 'self group type.'

Each capability is identified by a unique ID, and the driver
communicates the functionality and resource limits it plans to utilize.

The capability VIRTIO_DEV_PARTS_CAP specifically represents the device's
parts resource object limit.

Manage the device's parts resource object ID using a common IDA for both
get and set operations.

Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20241113115200.209269-4-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/virtio/virtio_pci_common.h |  13 +++-
 drivers/virtio/virtio_pci_modern.c | 105 +++++++++++++++++++++++++++++
 2 files changed, 116 insertions(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 1d9c49947f52d..04b1d17663b35 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -48,6 +48,9 @@ struct virtio_pci_admin_vq {
 	/* Protects virtqueue access. */
 	spinlock_t lock;
 	u64 supported_cmds;
+	u64 supported_caps;
+	u8 max_dev_parts_objects;
+	struct ida dev_parts_ida;
 	/* Name of the admin queue: avq.$vq_index. */
 	char name[10];
 	u16 vq_index;
@@ -167,15 +170,21 @@ struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev);
 	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ) | \
 	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO))
 
+#define VIRTIO_DEV_PARTS_ADMIN_CMD_BITMAP \
+	(BIT_ULL(VIRTIO_ADMIN_CMD_CAP_ID_LIST_QUERY) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_DRIVER_CAP_SET) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_DEVICE_CAP_GET))
+
 /* Unlike modern drivers which support hardware virtio devices, legacy drivers
  * assume software-based devices: e.g. they don't use proper memory barriers
  * on ARM, use big endian on PPC, etc. X86 drivers are mostly ok though, more
  * or less by chance. For now, only support legacy IO on X86.
  */
 #ifdef CONFIG_VIRTIO_PCI_ADMIN_LEGACY
-#define VIRTIO_ADMIN_CMD_BITMAP VIRTIO_LEGACY_ADMIN_CMD_BITMAP
+#define VIRTIO_ADMIN_CMD_BITMAP (VIRTIO_LEGACY_ADMIN_CMD_BITMAP | \
+				 VIRTIO_DEV_PARTS_ADMIN_CMD_BITMAP)
 #else
-#define VIRTIO_ADMIN_CMD_BITMAP 0
+#define VIRTIO_ADMIN_CMD_BITMAP VIRTIO_DEV_PARTS_ADMIN_CMD_BITMAP
 #endif
 
 void vp_modern_avq_done(struct virtqueue *vq);
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 487d04610ecbb..8ddac2829bc81 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -230,12 +230,117 @@ static void virtio_pci_admin_cmd_list_init(struct virtio_device *virtio_dev)
 	kfree(data);
 }
 
+static void
+virtio_pci_admin_cmd_dev_parts_objects_enable(struct virtio_device *virtio_dev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(virtio_dev);
+	struct virtio_admin_cmd_cap_get_data *get_data;
+	struct virtio_admin_cmd_cap_set_data *set_data;
+	struct virtio_dev_parts_cap *result;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist result_sg;
+	struct scatterlist data_sg;
+	u8 resource_objects_limit;
+	u16 set_data_size;
+	int ret;
+
+	get_data = kzalloc(sizeof(*get_data), GFP_KERNEL);
+	if (!get_data)
+		return;
+
+	result = kzalloc(sizeof(*result), GFP_KERNEL);
+	if (!result)
+		goto end;
+
+	get_data->id = cpu_to_le16(VIRTIO_DEV_PARTS_CAP);
+	sg_init_one(&data_sg, get_data, sizeof(*get_data));
+	sg_init_one(&result_sg, result, sizeof(*result));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DEVICE_CAP_GET);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.data_sg = &data_sg;
+	cmd.result_sg = &result_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (ret)
+		goto err_get;
+
+	set_data_size = sizeof(*set_data) + sizeof(*result);
+	set_data = kzalloc(set_data_size, GFP_KERNEL);
+	if (!set_data)
+		goto err_get;
+
+	set_data->id = cpu_to_le16(VIRTIO_DEV_PARTS_CAP);
+
+	/* Set the limit to the minimum value between the GET and SET values
+	 * supported by the device. Since the obj_id for VIRTIO_DEV_PARTS_CAP
+	 * is a globally unique value per PF, there is no possibility of
+	 * overlap between GET and SET operations.
+	 */
+	resource_objects_limit = min(result->get_parts_resource_objects_limit,
+				     result->set_parts_resource_objects_limit);
+	result->get_parts_resource_objects_limit = resource_objects_limit;
+	result->set_parts_resource_objects_limit = resource_objects_limit;
+	memcpy(set_data->cap_specific_data, result, sizeof(*result));
+	sg_init_one(&data_sg, set_data, set_data_size);
+	cmd.data_sg = &data_sg;
+	cmd.result_sg = NULL;
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DRIVER_CAP_SET);
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (ret)
+		goto err_set;
+
+	/* Allocate IDR to manage the dev caps objects */
+	ida_init(&vp_dev->admin_vq.dev_parts_ida);
+	vp_dev->admin_vq.max_dev_parts_objects = resource_objects_limit;
+
+err_set:
+	kfree(set_data);
+err_get:
+	kfree(result);
+end:
+	kfree(get_data);
+}
+
+static void virtio_pci_admin_cmd_cap_init(struct virtio_device *virtio_dev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(virtio_dev);
+	struct virtio_admin_cmd_query_cap_id_result *data;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist result_sg;
+	int ret;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return;
+
+	sg_init_one(&result_sg, data, sizeof(*data));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_CAP_ID_LIST_QUERY);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.result_sg = &result_sg;
+
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (ret)
+		goto end;
+
+	/* Max number of caps fits into a single u64 */
+	BUILD_BUG_ON(sizeof(data->supported_caps) > sizeof(u64));
+
+	vp_dev->admin_vq.supported_caps = le64_to_cpu(data->supported_caps[0]);
+
+	if (!(vp_dev->admin_vq.supported_caps & (1 << VIRTIO_DEV_PARTS_CAP)))
+		goto end;
+
+	virtio_pci_admin_cmd_dev_parts_objects_enable(virtio_dev);
+end:
+	kfree(data);
+}
+
 static void vp_modern_avq_activate(struct virtio_device *vdev)
 {
 	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
 		return;
 
 	virtio_pci_admin_cmd_list_init(vdev);
+	virtio_pci_admin_cmd_cap_init(vdev);
 }
 
 static void vp_modern_avq_cleanup(struct virtio_device *vdev)

From 52a22c0ed03ce23f20df81f79b23cb6637716fae Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Wed, 13 Nov 2024 13:51:57 +0200
Subject: [PATCH 1121/1530] virtio-pci: Introduce APIs to execute device parts
 admin commands

Introduce APIs to handle the execution of device parts admin commands.

These APIs cover functionalities such as mode setting, object creation
and destruction, and operations like parts get/set and metadata
retrieval.

These APIs will be utilized in upcoming patches within this series.

Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20241113115200.209269-5-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/virtio/virtio_pci_common.h |   8 +-
 drivers/virtio/virtio_pci_modern.c | 348 +++++++++++++++++++++++++++++
 include/linux/virtio_pci_admin.h   |  11 +
 3 files changed, 366 insertions(+), 1 deletion(-)

diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 04b1d17663b35..0d00740cca070 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -173,7 +173,13 @@ struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev);
 #define VIRTIO_DEV_PARTS_ADMIN_CMD_BITMAP \
 	(BIT_ULL(VIRTIO_ADMIN_CMD_CAP_ID_LIST_QUERY) | \
 	 BIT_ULL(VIRTIO_ADMIN_CMD_DRIVER_CAP_SET) | \
-	 BIT_ULL(VIRTIO_ADMIN_CMD_DEVICE_CAP_GET))
+	 BIT_ULL(VIRTIO_ADMIN_CMD_DEVICE_CAP_GET) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_RESOURCE_OBJ_CREATE) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_RESOURCE_OBJ_DESTROY) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_DEV_PARTS_METADATA_GET) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_DEV_PARTS_GET) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_DEV_PARTS_SET) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_DEV_MODE_SET))
 
 /* Unlike modern drivers which support hardware virtio devices, legacy drivers
  * assume software-based devices: e.g. they don't use proper memory barriers
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 8ddac2829bc81..3f5aba71cfded 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -15,6 +15,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/virtio_pci_admin.h>
 #define VIRTIO_PCI_NO_LEGACY
 #define VIRTIO_RING_NO_LEGACY
 #include "virtio_pci_common.h"
@@ -875,6 +876,353 @@ static bool vp_get_shm_region(struct virtio_device *vdev,
 	return true;
 }
 
+/*
+ * virtio_pci_admin_has_dev_parts - Checks whether the device parts
+ * functionality is supported
+ * @pdev: VF pci_dev
+ *
+ * Returns true on success.
+ */
+bool virtio_pci_admin_has_dev_parts(struct pci_dev *pdev)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_pci_device *vp_dev;
+
+	if (!virtio_dev)
+		return false;
+
+	if (!virtio_has_feature(virtio_dev, VIRTIO_F_ADMIN_VQ))
+		return false;
+
+	vp_dev = to_vp_device(virtio_dev);
+
+	if (!((vp_dev->admin_vq.supported_cmds & VIRTIO_DEV_PARTS_ADMIN_CMD_BITMAP) ==
+		VIRTIO_DEV_PARTS_ADMIN_CMD_BITMAP))
+		return false;
+
+	return vp_dev->admin_vq.max_dev_parts_objects;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_has_dev_parts);
+
+/*
+ * virtio_pci_admin_mode_set - Sets the mode of a member device
+ * @pdev: VF pci_dev
+ * @flags: device mode's flags
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_mode_set(struct pci_dev *pdev, u8 flags)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_dev_mode_set_data *data;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist data_sg;
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->flags = flags;
+	sg_init_one(&data_sg, data, sizeof(*data));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DEV_MODE_SET);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+
+	kfree(data);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_mode_set);
+
+/*
+ * virtio_pci_admin_obj_create - Creates an object for a given type and operation,
+ * following the max objects that can be created for that request.
+ * @pdev: VF pci_dev
+ * @obj_type: Object type
+ * @operation_type: Operation type
+ * @obj_id: Output unique object id
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_obj_create(struct pci_dev *pdev, u16 obj_type, u8 operation_type,
+				u32 *obj_id)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	u16 data_size = sizeof(struct virtio_admin_cmd_resource_obj_create_data);
+	struct virtio_admin_cmd_resource_obj_create_data *obj_create_data;
+	struct virtio_resource_obj_dev_parts obj_dev_parts = {};
+	struct virtio_pci_admin_vq *avq;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist data_sg;
+	void *data;
+	int id = -1;
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	if (obj_type != VIRTIO_RESOURCE_OBJ_DEV_PARTS)
+		return -EOPNOTSUPP;
+
+	if (operation_type != VIRTIO_RESOURCE_OBJ_DEV_PARTS_TYPE_GET &&
+	    operation_type != VIRTIO_RESOURCE_OBJ_DEV_PARTS_TYPE_SET)
+		return -EINVAL;
+
+	avq = &to_vp_device(virtio_dev)->admin_vq;
+	if (!avq->max_dev_parts_objects)
+		return -EOPNOTSUPP;
+
+	id = ida_alloc_range(&avq->dev_parts_ida, 0,
+			     avq->max_dev_parts_objects - 1, GFP_KERNEL);
+	if (id < 0)
+		return id;
+
+	*obj_id = id;
+	data_size += sizeof(obj_dev_parts);
+	data = kzalloc(data_size, GFP_KERNEL);
+	if (!data) {
+		ret = -ENOMEM;
+		goto end;
+	}
+
+	obj_create_data = data;
+	obj_create_data->hdr.type = cpu_to_le16(obj_type);
+	obj_create_data->hdr.id = cpu_to_le32(*obj_id);
+	obj_dev_parts.type = operation_type;
+	memcpy(obj_create_data->resource_obj_specific_data, &obj_dev_parts,
+	       sizeof(obj_dev_parts));
+	sg_init_one(&data_sg, data, data_size);
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_RESOURCE_OBJ_CREATE);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+
+	kfree(data);
+end:
+	if (ret)
+		ida_free(&avq->dev_parts_ida, id);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_obj_create);
+
+/*
+ * virtio_pci_admin_obj_destroy - Destroys an object of a given type and id
+ * @pdev: VF pci_dev
+ * @obj_type: Object type
+ * @id: Object id
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_obj_destroy(struct pci_dev *pdev, u16 obj_type, u32 id)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_resource_obj_cmd_hdr *data;
+	struct virtio_pci_device *vp_dev;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist data_sg;
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	if (obj_type != VIRTIO_RESOURCE_OBJ_DEV_PARTS)
+		return -EINVAL;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->type = cpu_to_le16(obj_type);
+	data->id = cpu_to_le32(id);
+	sg_init_one(&data_sg, data, sizeof(*data));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_RESOURCE_OBJ_DESTROY);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (!ret) {
+		vp_dev = to_vp_device(virtio_dev);
+		ida_free(&vp_dev->admin_vq.dev_parts_ida, id);
+	}
+
+	kfree(data);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_obj_destroy);
+
+/*
+ * virtio_pci_admin_dev_parts_metadata_get - Gets the metadata of the device parts
+ * identified by the below attributes.
+ * @pdev: VF pci_dev
+ * @obj_type: Object type
+ * @id: Object id
+ * @metadata_type: Metadata type
+ * @out: Upon success holds the output for 'metadata type size'
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_dev_parts_metadata_get(struct pci_dev *pdev, u16 obj_type,
+					    u32 id, u8 metadata_type, u32 *out)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_dev_parts_metadata_result *result;
+	struct virtio_admin_cmd_dev_parts_metadata_data *data;
+	struct scatterlist data_sg, result_sg;
+	struct virtio_admin_cmd cmd = {};
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	if (metadata_type != VIRTIO_ADMIN_CMD_DEV_PARTS_METADATA_TYPE_SIZE)
+		return -EOPNOTSUPP;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	result = kzalloc(sizeof(*result), GFP_KERNEL);
+	if (!result) {
+		ret = -ENOMEM;
+		goto end;
+	}
+
+	data->hdr.type = cpu_to_le16(obj_type);
+	data->hdr.id = cpu_to_le32(id);
+	data->type = metadata_type;
+	sg_init_one(&data_sg, data, sizeof(*data));
+	sg_init_one(&result_sg, result, sizeof(*result));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DEV_PARTS_METADATA_GET);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	cmd.result_sg = &result_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (!ret)
+		*out = le32_to_cpu(result->parts_size.size);
+
+	kfree(result);
+end:
+	kfree(data);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_dev_parts_metadata_get);
+
+/*
+ * virtio_pci_admin_dev_parts_get - Gets the device parts identified by the below attributes.
+ * @pdev: VF pci_dev
+ * @obj_type: Object type
+ * @id: Object id
+ * @get_type: Get type
+ * @res_sg: Upon success holds the output result data
+ * @res_size: Upon success holds the output result size
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_dev_parts_get(struct pci_dev *pdev, u16 obj_type, u32 id,
+				   u8 get_type, struct scatterlist *res_sg,
+				   u32 *res_size)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_dev_parts_get_data *data;
+	struct scatterlist data_sg;
+	struct virtio_admin_cmd cmd = {};
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	if (get_type != VIRTIO_ADMIN_CMD_DEV_PARTS_GET_TYPE_ALL)
+		return -EOPNOTSUPP;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->hdr.type = cpu_to_le16(obj_type);
+	data->hdr.id = cpu_to_le32(id);
+	data->type = get_type;
+	sg_init_one(&data_sg, data, sizeof(*data));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DEV_PARTS_GET);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	cmd.result_sg = res_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (!ret)
+		*res_size = cmd.result_sg_size;
+
+	kfree(data);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_dev_parts_get);
+
+/*
+ * virtio_pci_admin_dev_parts_set - Sets the device parts identified by the below attributes.
+ * @pdev: VF pci_dev
+ * @data_sg: The device parts data, its layout follows struct virtio_admin_cmd_dev_parts_set_data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_dev_parts_set(struct pci_dev *pdev, struct scatterlist *data_sg)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd cmd = {};
+	int vf_id;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DEV_PARTS_SET);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = data_sg;
+	return vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_dev_parts_set);
+
 static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.get		= NULL,
 	.set		= NULL,
diff --git a/include/linux/virtio_pci_admin.h b/include/linux/virtio_pci_admin.h
index f4a100a0fe2e1..dffc92c17ad21 100644
--- a/include/linux/virtio_pci_admin.h
+++ b/include/linux/virtio_pci_admin.h
@@ -20,4 +20,15 @@ int virtio_pci_admin_legacy_io_notify_info(struct pci_dev *pdev,
 					   u64 *bar_offset);
 #endif
 
+bool virtio_pci_admin_has_dev_parts(struct pci_dev *pdev);
+int virtio_pci_admin_mode_set(struct pci_dev *pdev, u8 mode);
+int virtio_pci_admin_obj_create(struct pci_dev *pdev, u16 obj_type, u8 operation_type,
+				u32 *obj_id);
+int virtio_pci_admin_obj_destroy(struct pci_dev *pdev, u16 obj_type, u32 id);
+int virtio_pci_admin_dev_parts_metadata_get(struct pci_dev *pdev, u16 obj_type,
+					    u32 id, u8 metadata_type, u32 *out);
+int virtio_pci_admin_dev_parts_get(struct pci_dev *pdev, u16 obj_type, u32 id,
+				   u8 get_type, struct scatterlist *res_sg, u32 *res_size);
+int virtio_pci_admin_dev_parts_set(struct pci_dev *pdev, struct scatterlist *data_sg);
+
 #endif /* _LINUX_VIRTIO_PCI_ADMIN_H */

From 2fa046449a82a7d0f6d9721dd83e348816038444 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Fri, 25 Oct 2024 15:27:54 -0700
Subject: [PATCH 1122/1530] PCI: Add 'reset_subordinate' to reset hierarchy
 below bridge

The "bus" and "cxl_bus" reset methods reset a device by asserting Secondary
Bus Reset on the bridge leading to the device.  These only work if the
device is the only device below the bridge.

Add a sysfs 'reset_subordinate' attribute on bridges that can assert
Secondary Bus Reset regardless of how many devices are below the bridge.

This resets all the devices below a bridge in a single command, including
the locking and config space save/restore that reset methods normally do.

This may be the only way to reset devices that don't support other reset
methods (ACPI, FLR, PM reset, etc).

Link: https://lore.kernel.org/r/20241025222755.3756162-1-kbusch@meta.com
Signed-off-by: Keith Busch <kbusch@kernel.org>
[bhelgaas: commit log, add capable(CAP_SYS_ADMIN) check]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Amey Narkhede <ameynarkhede03@gmail.com>
---
 Documentation/ABI/testing/sysfs-bus-pci | 11 +++++++++++
 drivers/pci/pci-sysfs.c                 | 26 +++++++++++++++++++++++++
 drivers/pci/pci.c                       |  2 +-
 drivers/pci/pci.h                       |  1 +
 4 files changed, 39 insertions(+), 1 deletion(-)

diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci
index 7f63c7e977735..5da6a14dc326b 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci
+++ b/Documentation/ABI/testing/sysfs-bus-pci
@@ -163,6 +163,17 @@ Description:
 		will be present in sysfs.  Writing 1 to this file
 		will perform reset.
 
+What:		/sys/bus/pci/devices/.../reset_subordinate
+Date:		October 2024
+Contact:	linux-pci@vger.kernel.org
+Description:
+		This is visible only for bridge devices. If you want to reset
+		all devices attached through the subordinate bus of a specific
+		bridge device, writing 1 to this will try to do it.  This will
+		affect all devices attached to the system through this bridge
+		similiar to writing 1 to their individual "reset" file, so use
+		with caution.
+
 What:		/sys/bus/pci/devices/.../vpd
 Date:		February 2008
 Contact:	Ben Hutchings <bwh@kernel.org>
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 5d0f4db1cab78..3e5a117f5b5d6 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -521,6 +521,31 @@ static ssize_t bus_rescan_store(struct device *dev,
 static struct device_attribute dev_attr_bus_rescan = __ATTR(rescan, 0200, NULL,
 							    bus_rescan_store);
 
+static ssize_t reset_subordinate_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_bus *bus = pdev->subordinate;
+	unsigned long val;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (kstrtoul(buf, 0, &val) < 0)
+		return -EINVAL;
+
+	if (val) {
+		int ret = __pci_reset_bus(bus);
+
+		if (ret)
+			return ret;
+	}
+
+	return count;
+}
+static DEVICE_ATTR_WO(reset_subordinate);
+
 #if defined(CONFIG_PM) && defined(CONFIG_ACPI)
 static ssize_t d3cold_allowed_store(struct device *dev,
 				    struct device_attribute *attr,
@@ -625,6 +650,7 @@ static struct attribute *pci_dev_attrs[] = {
 static struct attribute *pci_bridge_attrs[] = {
 	&dev_attr_subordinate_bus_number.attr,
 	&dev_attr_secondary_bus_number.attr,
+	&dev_attr_reset_subordinate.attr,
 	NULL,
 };
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 7d85c04fbba2a..338dfcd983f1e 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -5880,7 +5880,7 @@ EXPORT_SYMBOL_GPL(pci_probe_reset_bus);
  *
  * Same as above except return -EAGAIN if the bus cannot be locked
  */
-static int __pci_reset_bus(struct pci_bus *bus)
+int __pci_reset_bus(struct pci_bus *bus)
 {
 	int rc;
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 14d00ce45bfa9..1cdc2c9547a7e 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -104,6 +104,7 @@ bool pci_reset_supported(struct pci_dev *dev);
 void pci_init_reset_methods(struct pci_dev *dev);
 int pci_bridge_secondary_bus_reset(struct pci_dev *dev);
 int pci_bus_error_reset(struct pci_dev *dev);
+int __pci_reset_bus(struct pci_bus *bus);
 
 struct pci_cap_saved_data {
 	u16		cap_nr;

From a3151e6daaec171b7d46ac79170ec420ad874cae Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Fri, 25 Oct 2024 15:27:55 -0700
Subject: [PATCH 1123/1530] PCI: Warn if a running device is unaware of reset

If a reset is issued to a running device with a driver that didn't register
the notification callbacks, the driver may be unaware of this event and
have an inconsistent view of the device's state. Log a warning of this
event because there's nothing else indicating the event occured, which
could be confusing when debugging such situations.

Link: https://lore.kernel.org/r/20241025222755.3756162-2-kbusch@meta.com
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Amey Narkhede <ameynarkhede03@gmail.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/pci/pci.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 338dfcd983f1e..bbf12d4998269 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -5158,6 +5158,8 @@ static void pci_dev_save_and_disable(struct pci_dev *dev)
 	 */
 	if (err_handler && err_handler->reset_prepare)
 		err_handler->reset_prepare(dev);
+	else if (dev->driver)
+		pci_warn(dev, "resetting");
 
 	/*
 	 * Wake-up device prior to save.  PM registers default to D0 after
@@ -5191,6 +5193,8 @@ static void pci_dev_restore(struct pci_dev *dev)
 	 */
 	if (err_handler && err_handler->reset_done)
 		err_handler->reset_done(dev);
+	else if (dev->driver)
+		pci_warn(dev, "reset done");
 }
 
 /* dev->reset_methods[] is a 0-terminated list of indices into this array */

From 0bbc82e4ec79df437de49d45c512335d97f9c7ce Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Wed, 13 Nov 2024 13:51:58 +0200
Subject: [PATCH 1124/1530] vfio/virtio: Add support for the basic live
 migration functionality

Add support for basic live migration functionality in VFIO over
virtio-net devices, aligned with the virtio device specification 1.4.

This includes the following VFIO features:
VFIO_MIGRATION_STOP_COPY, VFIO_MIGRATION_P2P.

The implementation registers with the VFIO subsystem using vfio_pci_core
and then incorporates the virtio-specific logic for the migration
process.

The migration follows the definitions in uapi/vfio.h and leverages the
virtio VF-to-PF admin queue command channel for execution device parts
related commands.

Additional Notes:
-----------------
The kernel protocol between the source and target devices contains a
header with metadata, including record size, tag, and flags.

The record size allows the target to recognize and read a complete image
from the source before passing the device part data. This adheres to the
virtio device specification, which mandates that partial device parts
cannot be supplied.

The tag and flags serve as placeholders for future extensions of the
kernel protocol between the source and target, ensuring backward and
forward compatibility.

Both the source and target comply with the virtio device specification
by using a device part object with a unique ID as part of the migration
process. Since this resource is limited to a maximum of 255, its
lifecycle is confined to periods with an active live migration flow.

According to the virtio specification, a device has only two modes:
RUNNING and STOPPED. As a result, certain VFIO transitions (i.e.,
RUNNING_P2P->STOP, STOP->RUNNING_P2P) are treated as no-ops. When
transitioning to RUNNING_P2P, the device state is set to STOP, and it
will remain STOPPED until the transition out of RUNNING_P2P->RUNNING, at
which point it returns to RUNNING. During transition to STOP, the virtio
device only stops initiating outgoing requests(e.g. DMA, MSIx, etc.) but
still must accept incoming operations.

Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20241113115200.209269-6-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/virtio/Makefile  |    2 +-
 drivers/vfio/pci/virtio/common.h  |  104 +++
 drivers/vfio/pci/virtio/main.c    |   82 ++-
 drivers/vfio/pci/virtio/migrate.c | 1122 +++++++++++++++++++++++++++++
 4 files changed, 1285 insertions(+), 25 deletions(-)
 create mode 100644 drivers/vfio/pci/virtio/common.h
 create mode 100644 drivers/vfio/pci/virtio/migrate.c

diff --git a/drivers/vfio/pci/virtio/Makefile b/drivers/vfio/pci/virtio/Makefile
index 7171105baf330..bf0ccde6a91ab 100644
--- a/drivers/vfio/pci/virtio/Makefile
+++ b/drivers/vfio/pci/virtio/Makefile
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio-vfio-pci.o
-virtio-vfio-pci-y := main.o
+virtio-vfio-pci-y := main.o migrate.o
diff --git a/drivers/vfio/pci/virtio/common.h b/drivers/vfio/pci/virtio/common.h
new file mode 100644
index 0000000000000..3bdfb3ea11741
--- /dev/null
+++ b/drivers/vfio/pci/virtio/common.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef VIRTIO_VFIO_COMMON_H
+#define VIRTIO_VFIO_COMMON_H
+
+#include <linux/kernel.h>
+#include <linux/virtio.h>
+#include <linux/vfio_pci_core.h>
+#include <linux/virtio_pci.h>
+
+enum virtiovf_migf_state {
+	VIRTIOVF_MIGF_STATE_ERROR = 1,
+};
+
+enum virtiovf_load_state {
+	VIRTIOVF_LOAD_STATE_READ_HEADER,
+	VIRTIOVF_LOAD_STATE_PREP_HEADER_DATA,
+	VIRTIOVF_LOAD_STATE_READ_HEADER_DATA,
+	VIRTIOVF_LOAD_STATE_PREP_CHUNK,
+	VIRTIOVF_LOAD_STATE_READ_CHUNK,
+	VIRTIOVF_LOAD_STATE_LOAD_CHUNK,
+};
+
+struct virtiovf_data_buffer {
+	struct sg_append_table table;
+	loff_t start_pos;
+	u64 length;
+	u64 allocated_length;
+	struct list_head buf_elm;
+	u8 include_header_object:1;
+	struct virtiovf_migration_file *migf;
+	/* Optimize virtiovf_get_migration_page() for sequential access */
+	struct scatterlist *last_offset_sg;
+	unsigned int sg_last_entry;
+	unsigned long last_offset;
+};
+
+enum virtiovf_migf_header_flags {
+	VIRTIOVF_MIGF_HEADER_FLAGS_TAG_MANDATORY = 0,
+	VIRTIOVF_MIGF_HEADER_FLAGS_TAG_OPTIONAL = 1 << 0,
+};
+
+enum virtiovf_migf_header_tag {
+	VIRTIOVF_MIGF_HEADER_TAG_DEVICE_DATA = 0,
+};
+
+struct virtiovf_migration_header {
+	__le64 record_size;
+	/* For future use in case we may need to change the kernel protocol */
+	__le32 flags; /* Use virtiovf_migf_header_flags */
+	__le32 tag; /* Use virtiovf_migf_header_tag */
+	__u8 data[]; /* Its size is given in the record_size */
+};
+
+struct virtiovf_migration_file {
+	struct file *filp;
+	/* synchronize access to the file state */
+	struct mutex lock;
+	loff_t max_pos;
+	u64 record_size;
+	u32 record_tag;
+	u8 has_obj_id:1;
+	u32 obj_id;
+	enum virtiovf_migf_state state;
+	enum virtiovf_load_state load_state;
+	/* synchronize access to the lists */
+	spinlock_t list_lock;
+	struct list_head buf_list;
+	struct list_head avail_list;
+	struct virtiovf_data_buffer *buf;
+	struct virtiovf_data_buffer *buf_header;
+	struct virtiovf_pci_core_device *virtvdev;
+};
+
+struct virtiovf_pci_core_device {
+	struct vfio_pci_core_device core_device;
+	u8 *bar0_virtual_buf;
+	/* synchronize access to the virtual buf */
+	struct mutex bar_mutex;
+	void __iomem *notify_addr;
+	u64 notify_offset;
+	__le32 pci_base_addr_0;
+	__le16 pci_cmd;
+	u8 bar0_virtual_buf_size;
+	u8 notify_bar;
+
+	/* LM related */
+	u8 migrate_cap:1;
+	u8 deferred_reset:1;
+	/* protect migration state */
+	struct mutex state_mutex;
+	enum vfio_device_mig_state mig_state;
+	/* protect the reset_done flow */
+	spinlock_t reset_lock;
+	struct virtiovf_migration_file *resuming_migf;
+	struct virtiovf_migration_file *saving_migf;
+};
+
+void virtiovf_set_migratable(struct virtiovf_pci_core_device *virtvdev);
+void virtiovf_open_migration(struct virtiovf_pci_core_device *virtvdev);
+void virtiovf_close_migration(struct virtiovf_pci_core_device *virtvdev);
+void virtiovf_migration_reset_done(struct pci_dev *pdev);
+
+#endif /* VIRTIO_VFIO_COMMON_H */
diff --git a/drivers/vfio/pci/virtio/main.c b/drivers/vfio/pci/virtio/main.c
index b5d3a8c5bbc9a..e9ae172090261 100644
--- a/drivers/vfio/pci/virtio/main.c
+++ b/drivers/vfio/pci/virtio/main.c
@@ -16,18 +16,7 @@
 #include <linux/virtio_net.h>
 #include <linux/virtio_pci_admin.h>
 
-struct virtiovf_pci_core_device {
-	struct vfio_pci_core_device core_device;
-	u8 *bar0_virtual_buf;
-	/* synchronize access to the virtual buf */
-	struct mutex bar_mutex;
-	void __iomem *notify_addr;
-	u64 notify_offset;
-	__le32 pci_base_addr_0;
-	__le16 pci_cmd;
-	u8 bar0_virtual_buf_size;
-	u8 notify_bar;
-};
+#include "common.h"
 
 static int
 virtiovf_issue_legacy_rw_cmd(struct virtiovf_pci_core_device *virtvdev,
@@ -355,8 +344,8 @@ virtiovf_set_notify_addr(struct virtiovf_pci_core_device *virtvdev)
 
 static int virtiovf_pci_open_device(struct vfio_device *core_vdev)
 {
-	struct virtiovf_pci_core_device *virtvdev = container_of(
-		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	struct virtiovf_pci_core_device *virtvdev = container_of(core_vdev,
+			struct virtiovf_pci_core_device, core_device.vdev);
 	struct vfio_pci_core_device *vdev = &virtvdev->core_device;
 	int ret;
 
@@ -377,10 +366,20 @@ static int virtiovf_pci_open_device(struct vfio_device *core_vdev)
 		}
 	}
 
+	virtiovf_open_migration(virtvdev);
 	vfio_pci_core_finish_enable(vdev);
 	return 0;
 }
 
+static void virtiovf_pci_close_device(struct vfio_device *core_vdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(core_vdev,
+			struct virtiovf_pci_core_device, core_device.vdev);
+
+	virtiovf_close_migration(virtvdev);
+	vfio_pci_core_close_device(core_vdev);
+}
+
 static int virtiovf_get_device_config_size(unsigned short device)
 {
 	/* Network card */
@@ -406,8 +405,8 @@ static int virtiovf_read_notify_info(struct virtiovf_pci_core_device *virtvdev)
 
 static int virtiovf_pci_init_device(struct vfio_device *core_vdev)
 {
-	struct virtiovf_pci_core_device *virtvdev = container_of(
-		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	struct virtiovf_pci_core_device *virtvdev = container_of(core_vdev,
+			struct virtiovf_pci_core_device, core_device.vdev);
 	struct pci_dev *pdev;
 	int ret;
 
@@ -416,6 +415,10 @@ static int virtiovf_pci_init_device(struct vfio_device *core_vdev)
 		return ret;
 
 	pdev = virtvdev->core_device.pdev;
+	/*
+	 * The vfio_device_ops.init() callback is set to virtiovf_pci_init_device()
+	 * only when legacy I/O is supported. Now, let's initialize it.
+	 */
 	ret = virtiovf_read_notify_info(virtvdev);
 	if (ret)
 		return ret;
@@ -433,19 +436,38 @@ static int virtiovf_pci_init_device(struct vfio_device *core_vdev)
 
 static void virtiovf_pci_core_release_dev(struct vfio_device *core_vdev)
 {
-	struct virtiovf_pci_core_device *virtvdev = container_of(
-		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	struct virtiovf_pci_core_device *virtvdev = container_of(core_vdev,
+			struct virtiovf_pci_core_device, core_device.vdev);
 
 	kfree(virtvdev->bar0_virtual_buf);
 	vfio_pci_core_release_dev(core_vdev);
 }
 
-static const struct vfio_device_ops virtiovf_vfio_pci_tran_ops = {
-	.name = "virtio-vfio-pci-trans",
+static const struct vfio_device_ops virtiovf_vfio_pci_lm_ops = {
+	.name = "virtio-vfio-pci-lm",
+	.init = vfio_pci_core_init_dev,
+	.release = virtiovf_pci_core_release_dev,
+	.open_device = virtiovf_pci_open_device,
+	.close_device = virtiovf_pci_close_device,
+	.ioctl = vfio_pci_core_ioctl,
+	.device_feature = vfio_pci_core_ioctl_feature,
+	.read = vfio_pci_core_read,
+	.write = vfio_pci_core_write,
+	.mmap = vfio_pci_core_mmap,
+	.request = vfio_pci_core_request,
+	.match = vfio_pci_core_match,
+	.bind_iommufd = vfio_iommufd_physical_bind,
+	.unbind_iommufd = vfio_iommufd_physical_unbind,
+	.attach_ioas = vfio_iommufd_physical_attach_ioas,
+	.detach_ioas = vfio_iommufd_physical_detach_ioas,
+};
+
+static const struct vfio_device_ops virtiovf_vfio_pci_tran_lm_ops = {
+	.name = "virtio-vfio-pci-trans-lm",
 	.init = virtiovf_pci_init_device,
 	.release = virtiovf_pci_core_release_dev,
 	.open_device = virtiovf_pci_open_device,
-	.close_device = vfio_pci_core_close_device,
+	.close_device = virtiovf_pci_close_device,
 	.ioctl = virtiovf_vfio_pci_core_ioctl,
 	.device_feature = vfio_pci_core_ioctl_feature,
 	.read = virtiovf_pci_core_read,
@@ -490,17 +512,28 @@ static int virtiovf_pci_probe(struct pci_dev *pdev,
 {
 	const struct vfio_device_ops *ops = &virtiovf_vfio_pci_ops;
 	struct virtiovf_pci_core_device *virtvdev;
+	bool sup_legacy_io = false;
+	bool sup_lm = false;
 	int ret;
 
-	if (pdev->is_virtfn && virtio_pci_admin_has_legacy_io(pdev) &&
-	    !virtiovf_bar0_exists(pdev))
-		ops = &virtiovf_vfio_pci_tran_ops;
+	if (pdev->is_virtfn) {
+		sup_legacy_io = virtio_pci_admin_has_legacy_io(pdev) &&
+				!virtiovf_bar0_exists(pdev);
+		sup_lm = virtio_pci_admin_has_dev_parts(pdev);
+		if (sup_legacy_io)
+			ops = &virtiovf_vfio_pci_tran_lm_ops;
+		else if (sup_lm)
+			ops = &virtiovf_vfio_pci_lm_ops;
+	}
 
 	virtvdev = vfio_alloc_device(virtiovf_pci_core_device, core_device.vdev,
 				     &pdev->dev, ops);
 	if (IS_ERR(virtvdev))
 		return PTR_ERR(virtvdev);
 
+	if (sup_lm)
+		virtiovf_set_migratable(virtvdev);
+
 	dev_set_drvdata(&pdev->dev, &virtvdev->core_device);
 	ret = vfio_pci_core_register_device(&virtvdev->core_device);
 	if (ret)
@@ -532,6 +565,7 @@ static void virtiovf_pci_aer_reset_done(struct pci_dev *pdev)
 	struct virtiovf_pci_core_device *virtvdev = dev_get_drvdata(&pdev->dev);
 
 	virtvdev->pci_cmd = 0;
+	virtiovf_migration_reset_done(pdev);
 }
 
 static const struct pci_error_handlers virtiovf_err_handlers = {
diff --git a/drivers/vfio/pci/virtio/migrate.c b/drivers/vfio/pci/virtio/migrate.c
new file mode 100644
index 0000000000000..4fdf6ca17a3af
--- /dev/null
+++ b/drivers/vfio/pci/virtio/migrate.c
@@ -0,0 +1,1122 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/pm_runtime.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+#include <linux/vfio_pci_core.h>
+#include <linux/virtio_pci.h>
+#include <linux/virtio_net.h>
+#include <linux/virtio_pci_admin.h>
+#include <linux/anon_inodes.h>
+
+#include "common.h"
+
+/* Device specification max parts size */
+#define MAX_LOAD_SIZE (BIT_ULL(BITS_PER_TYPE \
+	(((struct virtio_admin_cmd_dev_parts_metadata_result *)0)->parts_size.size)) - 1)
+
+/* Initial target buffer size */
+#define VIRTIOVF_TARGET_INITIAL_BUF_SIZE SZ_1M
+
+static struct page *
+virtiovf_get_migration_page(struct virtiovf_data_buffer *buf,
+			    unsigned long offset)
+{
+	unsigned long cur_offset = 0;
+	struct scatterlist *sg;
+	unsigned int i;
+
+	/* All accesses are sequential */
+	if (offset < buf->last_offset || !buf->last_offset_sg) {
+		buf->last_offset = 0;
+		buf->last_offset_sg = buf->table.sgt.sgl;
+		buf->sg_last_entry = 0;
+	}
+
+	cur_offset = buf->last_offset;
+
+	for_each_sg(buf->last_offset_sg, sg,
+		    buf->table.sgt.orig_nents - buf->sg_last_entry, i) {
+		if (offset < sg->length + cur_offset) {
+			buf->last_offset_sg = sg;
+			buf->sg_last_entry += i;
+			buf->last_offset = cur_offset;
+			return nth_page(sg_page(sg),
+					(offset - cur_offset) / PAGE_SIZE);
+		}
+		cur_offset += sg->length;
+	}
+	return NULL;
+}
+
+static int virtiovf_add_migration_pages(struct virtiovf_data_buffer *buf,
+					unsigned int npages)
+{
+	unsigned int to_alloc = npages;
+	struct page **page_list;
+	unsigned long filled;
+	unsigned int to_fill;
+	int ret;
+	int i;
+
+	to_fill = min_t(unsigned int, npages, PAGE_SIZE / sizeof(*page_list));
+	page_list = kvcalloc(to_fill, sizeof(*page_list), GFP_KERNEL_ACCOUNT);
+	if (!page_list)
+		return -ENOMEM;
+
+	do {
+		filled = alloc_pages_bulk_array(GFP_KERNEL_ACCOUNT, to_fill,
+						page_list);
+		if (!filled) {
+			ret = -ENOMEM;
+			goto err;
+		}
+		to_alloc -= filled;
+		ret = sg_alloc_append_table_from_pages(&buf->table, page_list,
+			filled, 0, filled << PAGE_SHIFT, UINT_MAX,
+			SG_MAX_SINGLE_ALLOC, GFP_KERNEL_ACCOUNT);
+
+		if (ret)
+			goto err_append;
+		buf->allocated_length += filled * PAGE_SIZE;
+		/* clean input for another bulk allocation */
+		memset(page_list, 0, filled * sizeof(*page_list));
+		to_fill = min_t(unsigned int, to_alloc,
+				PAGE_SIZE / sizeof(*page_list));
+	} while (to_alloc > 0);
+
+	kvfree(page_list);
+	return 0;
+
+err_append:
+	for (i = filled - 1; i >= 0; i--)
+		__free_page(page_list[i]);
+err:
+	kvfree(page_list);
+	return ret;
+}
+
+static void virtiovf_free_data_buffer(struct virtiovf_data_buffer *buf)
+{
+	struct sg_page_iter sg_iter;
+
+	/* Undo alloc_pages_bulk_array() */
+	for_each_sgtable_page(&buf->table.sgt, &sg_iter, 0)
+		__free_page(sg_page_iter_page(&sg_iter));
+	sg_free_append_table(&buf->table);
+	kfree(buf);
+}
+
+static struct virtiovf_data_buffer *
+virtiovf_alloc_data_buffer(struct virtiovf_migration_file *migf, size_t length)
+{
+	struct virtiovf_data_buffer *buf;
+	int ret;
+
+	buf = kzalloc(sizeof(*buf), GFP_KERNEL_ACCOUNT);
+	if (!buf)
+		return ERR_PTR(-ENOMEM);
+
+	ret = virtiovf_add_migration_pages(buf,
+				DIV_ROUND_UP_ULL(length, PAGE_SIZE));
+	if (ret)
+		goto end;
+
+	buf->migf = migf;
+	return buf;
+end:
+	virtiovf_free_data_buffer(buf);
+	return ERR_PTR(ret);
+}
+
+static void virtiovf_put_data_buffer(struct virtiovf_data_buffer *buf)
+{
+	spin_lock_irq(&buf->migf->list_lock);
+	list_add_tail(&buf->buf_elm, &buf->migf->avail_list);
+	spin_unlock_irq(&buf->migf->list_lock);
+}
+
+static int
+virtiovf_pci_alloc_obj_id(struct virtiovf_pci_core_device *virtvdev, u8 type,
+			  u32 *obj_id)
+{
+	return virtio_pci_admin_obj_create(virtvdev->core_device.pdev,
+					   VIRTIO_RESOURCE_OBJ_DEV_PARTS, type, obj_id);
+}
+
+static void
+virtiovf_pci_free_obj_id(struct virtiovf_pci_core_device *virtvdev, u32 obj_id)
+{
+	virtio_pci_admin_obj_destroy(virtvdev->core_device.pdev,
+			VIRTIO_RESOURCE_OBJ_DEV_PARTS, obj_id);
+}
+
+static void virtiovf_clean_migf_resources(struct virtiovf_migration_file *migf)
+{
+	struct virtiovf_data_buffer *entry;
+
+	if (migf->buf) {
+		virtiovf_free_data_buffer(migf->buf);
+		migf->buf = NULL;
+	}
+
+	if (migf->buf_header) {
+		virtiovf_free_data_buffer(migf->buf_header);
+		migf->buf_header = NULL;
+	}
+
+	list_splice(&migf->avail_list, &migf->buf_list);
+
+	while ((entry = list_first_entry_or_null(&migf->buf_list,
+				struct virtiovf_data_buffer, buf_elm))) {
+		list_del(&entry->buf_elm);
+		virtiovf_free_data_buffer(entry);
+	}
+
+	if (migf->has_obj_id)
+		virtiovf_pci_free_obj_id(migf->virtvdev, migf->obj_id);
+}
+
+static void virtiovf_disable_fd(struct virtiovf_migration_file *migf)
+{
+	mutex_lock(&migf->lock);
+	migf->state = VIRTIOVF_MIGF_STATE_ERROR;
+	migf->filp->f_pos = 0;
+	mutex_unlock(&migf->lock);
+}
+
+static void virtiovf_disable_fds(struct virtiovf_pci_core_device *virtvdev)
+{
+	if (virtvdev->resuming_migf) {
+		virtiovf_disable_fd(virtvdev->resuming_migf);
+		virtiovf_clean_migf_resources(virtvdev->resuming_migf);
+		fput(virtvdev->resuming_migf->filp);
+		virtvdev->resuming_migf = NULL;
+	}
+	if (virtvdev->saving_migf) {
+		virtiovf_disable_fd(virtvdev->saving_migf);
+		virtiovf_clean_migf_resources(virtvdev->saving_migf);
+		fput(virtvdev->saving_migf->filp);
+		virtvdev->saving_migf = NULL;
+	}
+}
+
+/*
+ * This function is called in all state_mutex unlock cases to
+ * handle a 'deferred_reset' if exists.
+ */
+static void virtiovf_state_mutex_unlock(struct virtiovf_pci_core_device *virtvdev)
+{
+again:
+	spin_lock(&virtvdev->reset_lock);
+	if (virtvdev->deferred_reset) {
+		virtvdev->deferred_reset = false;
+		spin_unlock(&virtvdev->reset_lock);
+		virtvdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
+		virtiovf_disable_fds(virtvdev);
+		goto again;
+	}
+	mutex_unlock(&virtvdev->state_mutex);
+	spin_unlock(&virtvdev->reset_lock);
+}
+
+void virtiovf_migration_reset_done(struct pci_dev *pdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = dev_get_drvdata(&pdev->dev);
+
+	if (!virtvdev->migrate_cap)
+		return;
+
+	/*
+	 * As the higher VFIO layers are holding locks across reset and using
+	 * those same locks with the mm_lock we need to prevent ABBA deadlock
+	 * with the state_mutex and mm_lock.
+	 * In case the state_mutex was taken already we defer the cleanup work
+	 * to the unlock flow of the other running context.
+	 */
+	spin_lock(&virtvdev->reset_lock);
+	virtvdev->deferred_reset = true;
+	if (!mutex_trylock(&virtvdev->state_mutex)) {
+		spin_unlock(&virtvdev->reset_lock);
+		return;
+	}
+	spin_unlock(&virtvdev->reset_lock);
+	virtiovf_state_mutex_unlock(virtvdev);
+}
+
+static int virtiovf_release_file(struct inode *inode, struct file *filp)
+{
+	struct virtiovf_migration_file *migf = filp->private_data;
+
+	virtiovf_disable_fd(migf);
+	mutex_destroy(&migf->lock);
+	kfree(migf);
+	return 0;
+}
+
+static struct virtiovf_data_buffer *
+virtiovf_get_data_buff_from_pos(struct virtiovf_migration_file *migf,
+				loff_t pos, bool *end_of_data)
+{
+	struct virtiovf_data_buffer *buf;
+	bool found = false;
+
+	*end_of_data = false;
+	spin_lock_irq(&migf->list_lock);
+	if (list_empty(&migf->buf_list)) {
+		*end_of_data = true;
+		goto end;
+	}
+
+	buf = list_first_entry(&migf->buf_list, struct virtiovf_data_buffer,
+			       buf_elm);
+	if (pos >= buf->start_pos &&
+	    pos < buf->start_pos + buf->length) {
+		found = true;
+		goto end;
+	}
+
+	/*
+	 * As we use a stream based FD we may expect having the data always
+	 * on first chunk
+	 */
+	migf->state = VIRTIOVF_MIGF_STATE_ERROR;
+
+end:
+	spin_unlock_irq(&migf->list_lock);
+	return found ? buf : NULL;
+}
+
+static ssize_t virtiovf_buf_read(struct virtiovf_data_buffer *vhca_buf,
+				 char __user **buf, size_t *len, loff_t *pos)
+{
+	unsigned long offset;
+	ssize_t done = 0;
+	size_t copy_len;
+
+	copy_len = min_t(size_t,
+			 vhca_buf->start_pos + vhca_buf->length - *pos, *len);
+	while (copy_len) {
+		size_t page_offset;
+		struct page *page;
+		size_t page_len;
+		u8 *from_buff;
+		int ret;
+
+		offset = *pos - vhca_buf->start_pos;
+		page_offset = offset % PAGE_SIZE;
+		offset -= page_offset;
+		page = virtiovf_get_migration_page(vhca_buf, offset);
+		if (!page)
+			return -EINVAL;
+		page_len = min_t(size_t, copy_len, PAGE_SIZE - page_offset);
+		from_buff = kmap_local_page(page);
+		ret = copy_to_user(*buf, from_buff + page_offset, page_len);
+		kunmap_local(from_buff);
+		if (ret)
+			return -EFAULT;
+		*pos += page_len;
+		*len -= page_len;
+		*buf += page_len;
+		done += page_len;
+		copy_len -= page_len;
+	}
+
+	if (*pos >= vhca_buf->start_pos + vhca_buf->length) {
+		spin_lock_irq(&vhca_buf->migf->list_lock);
+		list_del_init(&vhca_buf->buf_elm);
+		list_add_tail(&vhca_buf->buf_elm, &vhca_buf->migf->avail_list);
+		spin_unlock_irq(&vhca_buf->migf->list_lock);
+	}
+
+	return done;
+}
+
+static ssize_t virtiovf_save_read(struct file *filp, char __user *buf, size_t len,
+				  loff_t *pos)
+{
+	struct virtiovf_migration_file *migf = filp->private_data;
+	struct virtiovf_data_buffer *vhca_buf;
+	bool end_of_data;
+	ssize_t done = 0;
+
+	if (pos)
+		return -ESPIPE;
+	pos = &filp->f_pos;
+
+	mutex_lock(&migf->lock);
+	if (migf->state == VIRTIOVF_MIGF_STATE_ERROR) {
+		done = -ENODEV;
+		goto out_unlock;
+	}
+
+	while (len) {
+		ssize_t count;
+
+		vhca_buf = virtiovf_get_data_buff_from_pos(migf, *pos, &end_of_data);
+		if (end_of_data)
+			goto out_unlock;
+
+		if (!vhca_buf) {
+			done = -EINVAL;
+			goto out_unlock;
+		}
+
+		count = virtiovf_buf_read(vhca_buf, &buf, &len, pos);
+		if (count < 0) {
+			done = count;
+			goto out_unlock;
+		}
+		done += count;
+	}
+
+out_unlock:
+	mutex_unlock(&migf->lock);
+	return done;
+}
+
+static const struct file_operations virtiovf_save_fops = {
+	.owner = THIS_MODULE,
+	.read = virtiovf_save_read,
+	.release = virtiovf_release_file,
+};
+
+static int
+virtiovf_add_buf_header(struct virtiovf_data_buffer *header_buf,
+			u32 data_size)
+{
+	struct virtiovf_migration_file *migf = header_buf->migf;
+	struct virtiovf_migration_header header = {};
+	struct page *page;
+	u8 *to_buff;
+
+	header.record_size = cpu_to_le64(data_size);
+	header.flags = cpu_to_le32(VIRTIOVF_MIGF_HEADER_FLAGS_TAG_MANDATORY);
+	header.tag = cpu_to_le32(VIRTIOVF_MIGF_HEADER_TAG_DEVICE_DATA);
+	page = virtiovf_get_migration_page(header_buf, 0);
+	if (!page)
+		return -EINVAL;
+	to_buff = kmap_local_page(page);
+	memcpy(to_buff, &header, sizeof(header));
+	kunmap_local(to_buff);
+	header_buf->length = sizeof(header);
+	header_buf->start_pos = header_buf->migf->max_pos;
+	migf->max_pos += header_buf->length;
+	spin_lock_irq(&migf->list_lock);
+	list_add_tail(&header_buf->buf_elm, &migf->buf_list);
+	spin_unlock_irq(&migf->list_lock);
+	return 0;
+}
+
+static int
+virtiovf_read_device_context_chunk(struct virtiovf_migration_file *migf,
+				   u32 ctx_size)
+{
+	struct virtiovf_data_buffer *header_buf;
+	struct virtiovf_data_buffer *buf;
+	bool unmark_end = false;
+	struct scatterlist *sg;
+	unsigned int i;
+	u32 res_size;
+	int nent;
+	int ret;
+
+	buf = virtiovf_alloc_data_buffer(migf, ctx_size);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
+	/* Find the total count of SG entries which satisfies the size */
+	nent = sg_nents_for_len(buf->table.sgt.sgl, ctx_size);
+	if (nent <= 0) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * Iterate to that SG entry and mark it as last (if it's not already)
+	 * to let underlay layers iterate only till that entry.
+	 */
+	for_each_sg(buf->table.sgt.sgl, sg, nent - 1, i)
+		;
+
+	if (!sg_is_last(sg)) {
+		unmark_end = true;
+		sg_mark_end(sg);
+	}
+
+	ret = virtio_pci_admin_dev_parts_get(migf->virtvdev->core_device.pdev,
+					     VIRTIO_RESOURCE_OBJ_DEV_PARTS,
+					     migf->obj_id,
+					     VIRTIO_ADMIN_CMD_DEV_PARTS_GET_TYPE_ALL,
+					     buf->table.sgt.sgl, &res_size);
+	/* Restore the original SG mark end */
+	if (unmark_end)
+		sg_unmark_end(sg);
+	if (ret)
+		goto out;
+
+	buf->length = res_size;
+	header_buf = virtiovf_alloc_data_buffer(migf,
+				sizeof(struct virtiovf_migration_header));
+	if (IS_ERR(header_buf)) {
+		ret = PTR_ERR(header_buf);
+		goto out;
+	}
+
+	ret = virtiovf_add_buf_header(header_buf, res_size);
+	if (ret)
+		goto out_header;
+
+	buf->start_pos = buf->migf->max_pos;
+	migf->max_pos += buf->length;
+	spin_lock(&migf->list_lock);
+	list_add_tail(&buf->buf_elm, &migf->buf_list);
+	spin_unlock_irq(&migf->list_lock);
+	return 0;
+
+out_header:
+	virtiovf_put_data_buffer(header_buf);
+out:
+	virtiovf_put_data_buffer(buf);
+	return ret;
+}
+
+static struct virtiovf_migration_file *
+virtiovf_pci_save_device_data(struct virtiovf_pci_core_device *virtvdev)
+{
+	struct virtiovf_migration_file *migf;
+	u32 ctx_size;
+	u32 obj_id;
+	int ret;
+
+	migf = kzalloc(sizeof(*migf), GFP_KERNEL_ACCOUNT);
+	if (!migf)
+		return ERR_PTR(-ENOMEM);
+
+	migf->filp = anon_inode_getfile("virtiovf_mig", &virtiovf_save_fops, migf,
+					O_RDONLY);
+	if (IS_ERR(migf->filp)) {
+		ret = PTR_ERR(migf->filp);
+		kfree(migf);
+		return ERR_PTR(ret);
+	}
+
+	stream_open(migf->filp->f_inode, migf->filp);
+	mutex_init(&migf->lock);
+	INIT_LIST_HEAD(&migf->buf_list);
+	INIT_LIST_HEAD(&migf->avail_list);
+	spin_lock_init(&migf->list_lock);
+	migf->virtvdev = virtvdev;
+
+	lockdep_assert_held(&virtvdev->state_mutex);
+	ret = virtiovf_pci_alloc_obj_id(virtvdev, VIRTIO_RESOURCE_OBJ_DEV_PARTS_TYPE_GET,
+					&obj_id);
+	if (ret)
+		goto out;
+
+	migf->obj_id = obj_id;
+	/* Mark as having a valid obj id which can be even 0 */
+	migf->has_obj_id = true;
+	ret = virtio_pci_admin_dev_parts_metadata_get(virtvdev->core_device.pdev,
+				VIRTIO_RESOURCE_OBJ_DEV_PARTS, obj_id,
+				VIRTIO_ADMIN_CMD_DEV_PARTS_METADATA_TYPE_SIZE,
+				&ctx_size);
+	if (ret)
+		goto out_clean;
+
+	if (!ctx_size) {
+		ret = -EINVAL;
+		goto out_clean;
+	}
+
+	ret = virtiovf_read_device_context_chunk(migf, ctx_size);
+	if (ret)
+		goto out_clean;
+
+	return migf;
+
+out_clean:
+	virtiovf_clean_migf_resources(migf);
+out:
+	fput(migf->filp);
+	return ERR_PTR(ret);
+}
+
+/*
+ * Set the required object header at the beginning of the buffer.
+ * The actual device parts data will be written post of the header offset.
+ */
+static int virtiovf_set_obj_cmd_header(struct virtiovf_data_buffer *vhca_buf)
+{
+	struct virtio_admin_cmd_resource_obj_cmd_hdr obj_hdr = {};
+	struct page *page;
+	u8 *to_buff;
+
+	obj_hdr.type = cpu_to_le16(VIRTIO_RESOURCE_OBJ_DEV_PARTS);
+	obj_hdr.id = cpu_to_le32(vhca_buf->migf->obj_id);
+	page = virtiovf_get_migration_page(vhca_buf, 0);
+	if (!page)
+		return -EINVAL;
+	to_buff = kmap_local_page(page);
+	memcpy(to_buff, &obj_hdr, sizeof(obj_hdr));
+	kunmap_local(to_buff);
+
+	/* Mark the buffer as including the header object data */
+	vhca_buf->include_header_object = 1;
+	return 0;
+}
+
+static int
+virtiovf_append_page_to_mig_buf(struct virtiovf_data_buffer *vhca_buf,
+				const char __user **buf, size_t *len,
+				loff_t *pos, ssize_t *done)
+{
+	unsigned long offset;
+	size_t page_offset;
+	struct page *page;
+	size_t page_len;
+	u8 *to_buff;
+	int ret;
+
+	offset = *pos - vhca_buf->start_pos;
+
+	if (vhca_buf->include_header_object)
+		/* The buffer holds the object header, update the offset accordingly */
+		offset += sizeof(struct virtio_admin_cmd_resource_obj_cmd_hdr);
+
+	page_offset = offset % PAGE_SIZE;
+
+	page = virtiovf_get_migration_page(vhca_buf, offset - page_offset);
+	if (!page)
+		return -EINVAL;
+
+	page_len = min_t(size_t, *len, PAGE_SIZE - page_offset);
+	to_buff = kmap_local_page(page);
+	ret = copy_from_user(to_buff + page_offset, *buf, page_len);
+	kunmap_local(to_buff);
+	if (ret)
+		return -EFAULT;
+
+	*pos += page_len;
+	*done += page_len;
+	*buf += page_len;
+	*len -= page_len;
+	vhca_buf->length += page_len;
+	return 0;
+}
+
+static ssize_t
+virtiovf_resume_read_chunk(struct virtiovf_migration_file *migf,
+			   struct virtiovf_data_buffer *vhca_buf,
+			   size_t chunk_size, const char __user **buf,
+			   size_t *len, loff_t *pos, ssize_t *done,
+			   bool *has_work)
+{
+	size_t copy_len, to_copy;
+	int ret;
+
+	to_copy = min_t(size_t, *len, chunk_size - vhca_buf->length);
+	copy_len = to_copy;
+	while (to_copy) {
+		ret = virtiovf_append_page_to_mig_buf(vhca_buf, buf, &to_copy,
+						      pos, done);
+		if (ret)
+			return ret;
+	}
+
+	*len -= copy_len;
+	if (vhca_buf->length == chunk_size) {
+		migf->load_state = VIRTIOVF_LOAD_STATE_LOAD_CHUNK;
+		migf->max_pos += chunk_size;
+		*has_work = true;
+	}
+
+	return 0;
+}
+
+static int
+virtiovf_resume_read_header_data(struct virtiovf_migration_file *migf,
+				 struct virtiovf_data_buffer *vhca_buf,
+				 const char __user **buf, size_t *len,
+				 loff_t *pos, ssize_t *done)
+{
+	size_t copy_len, to_copy;
+	size_t required_data;
+	int ret;
+
+	required_data = migf->record_size - vhca_buf->length;
+	to_copy = min_t(size_t, *len, required_data);
+	copy_len = to_copy;
+	while (to_copy) {
+		ret = virtiovf_append_page_to_mig_buf(vhca_buf, buf, &to_copy,
+						      pos, done);
+		if (ret)
+			return ret;
+	}
+
+	*len -= copy_len;
+	if (vhca_buf->length == migf->record_size) {
+		switch (migf->record_tag) {
+		default:
+			/* Optional tag */
+			break;
+		}
+
+		migf->load_state = VIRTIOVF_LOAD_STATE_READ_HEADER;
+		migf->max_pos += migf->record_size;
+		vhca_buf->length = 0;
+	}
+
+	return 0;
+}
+
+static int
+virtiovf_resume_read_header(struct virtiovf_migration_file *migf,
+			    struct virtiovf_data_buffer *vhca_buf,
+			    const char __user **buf,
+			    size_t *len, loff_t *pos,
+			    ssize_t *done, bool *has_work)
+{
+	struct page *page;
+	size_t copy_len;
+	u8 *to_buff;
+	int ret;
+
+	copy_len = min_t(size_t, *len,
+		sizeof(struct virtiovf_migration_header) - vhca_buf->length);
+	page = virtiovf_get_migration_page(vhca_buf, 0);
+	if (!page)
+		return -EINVAL;
+	to_buff = kmap_local_page(page);
+	ret = copy_from_user(to_buff + vhca_buf->length, *buf, copy_len);
+	if (ret) {
+		ret = -EFAULT;
+		goto end;
+	}
+
+	*buf += copy_len;
+	*pos += copy_len;
+	*done += copy_len;
+	*len -= copy_len;
+	vhca_buf->length += copy_len;
+	if (vhca_buf->length == sizeof(struct virtiovf_migration_header)) {
+		u64 record_size;
+		u32 flags;
+
+		record_size = le64_to_cpup((__le64 *)to_buff);
+		if (record_size > MAX_LOAD_SIZE) {
+			ret = -ENOMEM;
+			goto end;
+		}
+
+		migf->record_size = record_size;
+		flags = le32_to_cpup((__le32 *)(to_buff +
+			    offsetof(struct virtiovf_migration_header, flags)));
+		migf->record_tag = le32_to_cpup((__le32 *)(to_buff +
+			    offsetof(struct virtiovf_migration_header, tag)));
+		switch (migf->record_tag) {
+		case VIRTIOVF_MIGF_HEADER_TAG_DEVICE_DATA:
+			migf->load_state = VIRTIOVF_LOAD_STATE_PREP_CHUNK;
+			break;
+		default:
+			if (!(flags & VIRTIOVF_MIGF_HEADER_FLAGS_TAG_OPTIONAL)) {
+				ret = -EOPNOTSUPP;
+				goto end;
+			}
+			/* We may read and skip this optional record data */
+			migf->load_state = VIRTIOVF_LOAD_STATE_PREP_HEADER_DATA;
+		}
+
+		migf->max_pos += vhca_buf->length;
+		vhca_buf->length = 0;
+		*has_work = true;
+	}
+end:
+	kunmap_local(to_buff);
+	return ret;
+}
+
+static ssize_t virtiovf_resume_write(struct file *filp, const char __user *buf,
+				     size_t len, loff_t *pos)
+{
+	struct virtiovf_migration_file *migf = filp->private_data;
+	struct virtiovf_data_buffer *vhca_buf = migf->buf;
+	struct virtiovf_data_buffer *vhca_buf_header = migf->buf_header;
+	unsigned int orig_length;
+	bool has_work = false;
+	ssize_t done = 0;
+	int ret = 0;
+
+	if (pos)
+		return -ESPIPE;
+
+	pos = &filp->f_pos;
+	if (*pos < vhca_buf->start_pos)
+		return -EINVAL;
+
+	mutex_lock(&migf->virtvdev->state_mutex);
+	mutex_lock(&migf->lock);
+	if (migf->state == VIRTIOVF_MIGF_STATE_ERROR) {
+		done = -ENODEV;
+		goto out_unlock;
+	}
+
+	while (len || has_work) {
+		has_work = false;
+		switch (migf->load_state) {
+		case VIRTIOVF_LOAD_STATE_READ_HEADER:
+			ret = virtiovf_resume_read_header(migf, vhca_buf_header, &buf,
+							  &len, pos, &done, &has_work);
+			if (ret)
+				goto out_unlock;
+			break;
+		case VIRTIOVF_LOAD_STATE_PREP_HEADER_DATA:
+			if (vhca_buf_header->allocated_length < migf->record_size) {
+				virtiovf_free_data_buffer(vhca_buf_header);
+
+				migf->buf_header = virtiovf_alloc_data_buffer(migf,
+						migf->record_size);
+				if (IS_ERR(migf->buf_header)) {
+					ret = PTR_ERR(migf->buf_header);
+					migf->buf_header = NULL;
+					goto out_unlock;
+				}
+
+				vhca_buf_header = migf->buf_header;
+			}
+
+			vhca_buf_header->start_pos = migf->max_pos;
+			migf->load_state = VIRTIOVF_LOAD_STATE_READ_HEADER_DATA;
+			break;
+		case VIRTIOVF_LOAD_STATE_READ_HEADER_DATA:
+			ret = virtiovf_resume_read_header_data(migf, vhca_buf_header,
+							       &buf, &len, pos, &done);
+			if (ret)
+				goto out_unlock;
+			break;
+		case VIRTIOVF_LOAD_STATE_PREP_CHUNK:
+		{
+			u32 cmd_size = migf->record_size +
+				sizeof(struct virtio_admin_cmd_resource_obj_cmd_hdr);
+
+			/*
+			 * The DMA map/unmap is managed in virtio layer, we just need to extend
+			 * the SG pages to hold the extra required chunk data.
+			 */
+			if (vhca_buf->allocated_length < cmd_size) {
+				ret = virtiovf_add_migration_pages(vhca_buf,
+					DIV_ROUND_UP_ULL(cmd_size - vhca_buf->allocated_length,
+							 PAGE_SIZE));
+				if (ret)
+					goto out_unlock;
+			}
+
+			vhca_buf->start_pos = migf->max_pos;
+			migf->load_state = VIRTIOVF_LOAD_STATE_READ_CHUNK;
+			break;
+		}
+		case VIRTIOVF_LOAD_STATE_READ_CHUNK:
+			ret = virtiovf_resume_read_chunk(migf, vhca_buf, migf->record_size,
+							 &buf, &len, pos, &done, &has_work);
+			if (ret)
+				goto out_unlock;
+			break;
+		case VIRTIOVF_LOAD_STATE_LOAD_CHUNK:
+			/* Mark the last SG entry and set its length */
+			sg_mark_end(vhca_buf->last_offset_sg);
+			orig_length = vhca_buf->last_offset_sg->length;
+			/* Length should include the resource object command header */
+			vhca_buf->last_offset_sg->length = vhca_buf->length +
+					sizeof(struct virtio_admin_cmd_resource_obj_cmd_hdr) -
+					vhca_buf->last_offset;
+			ret = virtio_pci_admin_dev_parts_set(migf->virtvdev->core_device.pdev,
+							     vhca_buf->table.sgt.sgl);
+			/* Restore the original SG data */
+			vhca_buf->last_offset_sg->length = orig_length;
+			sg_unmark_end(vhca_buf->last_offset_sg);
+			if (ret)
+				goto out_unlock;
+			migf->load_state = VIRTIOVF_LOAD_STATE_READ_HEADER;
+			/* be ready for reading the next chunk */
+			vhca_buf->length = 0;
+			break;
+		default:
+			break;
+		}
+	}
+
+out_unlock:
+	if (ret)
+		migf->state = VIRTIOVF_MIGF_STATE_ERROR;
+	mutex_unlock(&migf->lock);
+	virtiovf_state_mutex_unlock(migf->virtvdev);
+	return ret ? ret : done;
+}
+
+static const struct file_operations virtiovf_resume_fops = {
+	.owner = THIS_MODULE,
+	.write = virtiovf_resume_write,
+	.release = virtiovf_release_file,
+};
+
+static struct virtiovf_migration_file *
+virtiovf_pci_resume_device_data(struct virtiovf_pci_core_device *virtvdev)
+{
+	struct virtiovf_migration_file *migf;
+	struct virtiovf_data_buffer *buf;
+	u32 obj_id;
+	int ret;
+
+	migf = kzalloc(sizeof(*migf), GFP_KERNEL_ACCOUNT);
+	if (!migf)
+		return ERR_PTR(-ENOMEM);
+
+	migf->filp = anon_inode_getfile("virtiovf_mig", &virtiovf_resume_fops, migf,
+					O_WRONLY);
+	if (IS_ERR(migf->filp)) {
+		ret = PTR_ERR(migf->filp);
+		kfree(migf);
+		return ERR_PTR(ret);
+	}
+
+	stream_open(migf->filp->f_inode, migf->filp);
+	mutex_init(&migf->lock);
+	INIT_LIST_HEAD(&migf->buf_list);
+	INIT_LIST_HEAD(&migf->avail_list);
+	spin_lock_init(&migf->list_lock);
+
+	buf = virtiovf_alloc_data_buffer(migf, VIRTIOVF_TARGET_INITIAL_BUF_SIZE);
+	if (IS_ERR(buf)) {
+		ret = PTR_ERR(buf);
+		goto out;
+	}
+
+	migf->buf = buf;
+
+	buf = virtiovf_alloc_data_buffer(migf,
+		sizeof(struct virtiovf_migration_header));
+	if (IS_ERR(buf)) {
+		ret = PTR_ERR(buf);
+		goto out_clean;
+	}
+
+	migf->buf_header = buf;
+	migf->load_state = VIRTIOVF_LOAD_STATE_READ_HEADER;
+
+	migf->virtvdev = virtvdev;
+	ret = virtiovf_pci_alloc_obj_id(virtvdev, VIRTIO_RESOURCE_OBJ_DEV_PARTS_TYPE_SET,
+					&obj_id);
+	if (ret)
+		goto out_clean;
+
+	migf->obj_id = obj_id;
+	/* Mark as having a valid obj id which can be even 0 */
+	migf->has_obj_id = true;
+	ret = virtiovf_set_obj_cmd_header(migf->buf);
+	if (ret)
+		goto out_clean;
+
+	return migf;
+
+out_clean:
+	virtiovf_clean_migf_resources(migf);
+out:
+	fput(migf->filp);
+	return ERR_PTR(ret);
+}
+
+static struct file *
+virtiovf_pci_step_device_state_locked(struct virtiovf_pci_core_device *virtvdev,
+				      u32 new)
+{
+	u32 cur = virtvdev->mig_state;
+	int ret;
+
+	if (cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_STOP) {
+		/* NOP */
+		return NULL;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_RUNNING_P2P) {
+		/* NOP */
+		return NULL;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_RUNNING_P2P) {
+		ret = virtio_pci_admin_mode_set(virtvdev->core_device.pdev,
+						BIT(VIRTIO_ADMIN_CMD_DEV_MODE_F_STOPPED));
+		if (ret)
+			return ERR_PTR(ret);
+		return NULL;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_RUNNING) {
+		ret = virtio_pci_admin_mode_set(virtvdev->core_device.pdev, 0);
+		if (ret)
+			return ERR_PTR(ret);
+		return NULL;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_STOP_COPY) {
+		struct virtiovf_migration_file *migf;
+
+		migf = virtiovf_pci_save_device_data(virtvdev);
+		if (IS_ERR(migf))
+			return ERR_CAST(migf);
+		get_file(migf->filp);
+		virtvdev->saving_migf = migf;
+		return migf->filp;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_STOP_COPY && new == VFIO_DEVICE_STATE_STOP) {
+		virtiovf_disable_fds(virtvdev);
+		return NULL;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_RESUMING) {
+		struct virtiovf_migration_file *migf;
+
+		migf = virtiovf_pci_resume_device_data(virtvdev);
+		if (IS_ERR(migf))
+			return ERR_CAST(migf);
+		get_file(migf->filp);
+		virtvdev->resuming_migf = migf;
+		return migf->filp;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_RESUMING && new == VFIO_DEVICE_STATE_STOP) {
+		virtiovf_disable_fds(virtvdev);
+		return NULL;
+	}
+
+	/*
+	 * vfio_mig_get_next_state() does not use arcs other than the above
+	 */
+	WARN_ON(true);
+	return ERR_PTR(-EINVAL);
+}
+
+static struct file *
+virtiovf_pci_set_device_state(struct vfio_device *vdev,
+			      enum vfio_device_mig_state new_state)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	enum vfio_device_mig_state next_state;
+	struct file *res = NULL;
+	int ret;
+
+	mutex_lock(&virtvdev->state_mutex);
+	while (new_state != virtvdev->mig_state) {
+		ret = vfio_mig_get_next_state(vdev, virtvdev->mig_state,
+					      new_state, &next_state);
+		if (ret) {
+			res = ERR_PTR(ret);
+			break;
+		}
+		res = virtiovf_pci_step_device_state_locked(virtvdev, next_state);
+		if (IS_ERR(res))
+			break;
+		virtvdev->mig_state = next_state;
+		if (WARN_ON(res && new_state != virtvdev->mig_state)) {
+			fput(res);
+			res = ERR_PTR(-EINVAL);
+			break;
+		}
+	}
+	virtiovf_state_mutex_unlock(virtvdev);
+	return res;
+}
+
+static int virtiovf_pci_get_device_state(struct vfio_device *vdev,
+				       enum vfio_device_mig_state *curr_state)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		vdev, struct virtiovf_pci_core_device, core_device.vdev);
+
+	mutex_lock(&virtvdev->state_mutex);
+	*curr_state = virtvdev->mig_state;
+	virtiovf_state_mutex_unlock(virtvdev);
+	return 0;
+}
+
+static int virtiovf_pci_get_data_size(struct vfio_device *vdev,
+				      unsigned long *stop_copy_length)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	bool obj_id_exists;
+	u32 res_size;
+	u32 obj_id;
+	int ret;
+
+	mutex_lock(&virtvdev->state_mutex);
+	obj_id_exists = virtvdev->saving_migf && virtvdev->saving_migf->has_obj_id;
+	if (!obj_id_exists) {
+		ret = virtiovf_pci_alloc_obj_id(virtvdev,
+						VIRTIO_RESOURCE_OBJ_DEV_PARTS_TYPE_GET,
+						&obj_id);
+		if (ret)
+			goto end;
+	} else {
+		obj_id = virtvdev->saving_migf->obj_id;
+	}
+
+	ret = virtio_pci_admin_dev_parts_metadata_get(virtvdev->core_device.pdev,
+				VIRTIO_RESOURCE_OBJ_DEV_PARTS, obj_id,
+				VIRTIO_ADMIN_CMD_DEV_PARTS_METADATA_TYPE_SIZE,
+				&res_size);
+	if (!ret)
+		*stop_copy_length = res_size;
+
+	/*
+	 * We can't leave this obj_id alive if didn't exist before, otherwise, it might
+	 * stay alive, even without an active migration flow (e.g. migration was cancelled)
+	 */
+	if (!obj_id_exists)
+		virtiovf_pci_free_obj_id(virtvdev, obj_id);
+end:
+	virtiovf_state_mutex_unlock(virtvdev);
+	return ret;
+}
+
+static const struct vfio_migration_ops virtvdev_pci_mig_ops = {
+	.migration_set_state = virtiovf_pci_set_device_state,
+	.migration_get_state = virtiovf_pci_get_device_state,
+	.migration_get_data_size = virtiovf_pci_get_data_size,
+};
+
+void virtiovf_set_migratable(struct virtiovf_pci_core_device *virtvdev)
+{
+	virtvdev->migrate_cap = 1;
+	mutex_init(&virtvdev->state_mutex);
+	spin_lock_init(&virtvdev->reset_lock);
+	virtvdev->core_device.vdev.migration_flags =
+		VFIO_MIGRATION_STOP_COPY |
+		VFIO_MIGRATION_P2P;
+	virtvdev->core_device.vdev.mig_ops = &virtvdev_pci_mig_ops;
+}
+
+void virtiovf_open_migration(struct virtiovf_pci_core_device *virtvdev)
+{
+	if (!virtvdev->migrate_cap)
+		return;
+
+	virtvdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
+}
+
+void virtiovf_close_migration(struct virtiovf_pci_core_device *virtvdev)
+{
+	if (!virtvdev->migrate_cap)
+		return;
+
+	virtiovf_disable_fds(virtvdev);
+}

From 6cea64b1db8885b82c226f9f80c2325f39d9d309 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Wed, 13 Nov 2024 13:51:59 +0200
Subject: [PATCH 1125/1530] vfio/virtio: Add PRE_COPY support for live
 migration

Add PRE_COPY support for live migration.

This functionality may reduce the downtime upon STOP_COPY as of letting
the target machine to get some 'initial data' from the source once the
machine is still in its RUNNING state and let it prepares itself
pre-ahead to get the final STOP_COPY data.

As the Virtio specification does not support reading partial or
incremental device contexts. This means that during the PRE_COPY state,
the vfio-virtio driver reads the full device state.

As the device state can be changed and the benefit is highest when the
pre copy data closely matches the final data we read it in a rate
limiter mode.

This means we avoid reading new data from the device for a specified
time interval after the last read.

With PRE_COPY enabled, we observed a downtime reduction of approximately
70-75% in various scenarios compared to when PRE_COPY was disabled,
while keeping the total migration time nearly the same.

Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20241113115200.209269-7-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/virtio/common.h  |   4 +
 drivers/vfio/pci/virtio/migrate.c | 231 ++++++++++++++++++++++++++++--
 2 files changed, 227 insertions(+), 8 deletions(-)

diff --git a/drivers/vfio/pci/virtio/common.h b/drivers/vfio/pci/virtio/common.h
index 3bdfb3ea11741..5704603f0f9d9 100644
--- a/drivers/vfio/pci/virtio/common.h
+++ b/drivers/vfio/pci/virtio/common.h
@@ -10,6 +10,8 @@
 
 enum virtiovf_migf_state {
 	VIRTIOVF_MIGF_STATE_ERROR = 1,
+	VIRTIOVF_MIGF_STATE_PRECOPY = 2,
+	VIRTIOVF_MIGF_STATE_COMPLETE = 3,
 };
 
 enum virtiovf_load_state {
@@ -57,6 +59,8 @@ struct virtiovf_migration_file {
 	/* synchronize access to the file state */
 	struct mutex lock;
 	loff_t max_pos;
+	u64 pre_copy_initial_bytes;
+	struct ratelimit_state pre_copy_rl_state;
 	u64 record_size;
 	u32 record_tag;
 	u8 has_obj_id:1;
diff --git a/drivers/vfio/pci/virtio/migrate.c b/drivers/vfio/pci/virtio/migrate.c
index 4fdf6ca17a3af..ee54f4c178577 100644
--- a/drivers/vfio/pci/virtio/migrate.c
+++ b/drivers/vfio/pci/virtio/migrate.c
@@ -26,6 +26,10 @@
 /* Initial target buffer size */
 #define VIRTIOVF_TARGET_INITIAL_BUF_SIZE SZ_1M
 
+static int
+virtiovf_read_device_context_chunk(struct virtiovf_migration_file *migf,
+				   u32 ctx_size);
+
 static struct page *
 virtiovf_get_migration_page(struct virtiovf_data_buffer *buf,
 			    unsigned long offset)
@@ -159,6 +163,41 @@ virtiovf_pci_free_obj_id(struct virtiovf_pci_core_device *virtvdev, u32 obj_id)
 			VIRTIO_RESOURCE_OBJ_DEV_PARTS, obj_id);
 }
 
+static struct virtiovf_data_buffer *
+virtiovf_get_data_buffer(struct virtiovf_migration_file *migf, size_t length)
+{
+	struct virtiovf_data_buffer *buf, *temp_buf;
+	struct list_head free_list;
+
+	INIT_LIST_HEAD(&free_list);
+
+	spin_lock_irq(&migf->list_lock);
+	list_for_each_entry_safe(buf, temp_buf, &migf->avail_list, buf_elm) {
+		list_del_init(&buf->buf_elm);
+		if (buf->allocated_length >= length) {
+			spin_unlock_irq(&migf->list_lock);
+			goto found;
+		}
+		/*
+		 * Prevent holding redundant buffers. Put in a free
+		 * list and call at the end not under the spin lock
+		 * (&migf->list_lock) to minimize its scope usage.
+		 */
+		list_add(&buf->buf_elm, &free_list);
+	}
+	spin_unlock_irq(&migf->list_lock);
+	buf = virtiovf_alloc_data_buffer(migf, length);
+
+found:
+	while ((temp_buf = list_first_entry_or_null(&free_list,
+				struct virtiovf_data_buffer, buf_elm))) {
+		list_del(&temp_buf->buf_elm);
+		virtiovf_free_data_buffer(temp_buf);
+	}
+
+	return buf;
+}
+
 static void virtiovf_clean_migf_resources(struct virtiovf_migration_file *migf)
 {
 	struct virtiovf_data_buffer *entry;
@@ -345,6 +384,7 @@ static ssize_t virtiovf_save_read(struct file *filp, char __user *buf, size_t le
 {
 	struct virtiovf_migration_file *migf = filp->private_data;
 	struct virtiovf_data_buffer *vhca_buf;
+	bool first_loop_call = true;
 	bool end_of_data;
 	ssize_t done = 0;
 
@@ -362,6 +402,19 @@ static ssize_t virtiovf_save_read(struct file *filp, char __user *buf, size_t le
 		ssize_t count;
 
 		vhca_buf = virtiovf_get_data_buff_from_pos(migf, *pos, &end_of_data);
+		if (first_loop_call) {
+			first_loop_call = false;
+			/* Temporary end of file as part of PRE_COPY */
+			if (end_of_data && migf->state == VIRTIOVF_MIGF_STATE_PRECOPY) {
+				done = -ENOMSG;
+				goto out_unlock;
+			}
+			if (end_of_data && migf->state != VIRTIOVF_MIGF_STATE_COMPLETE) {
+				done = -EINVAL;
+				goto out_unlock;
+			}
+		}
+
 		if (end_of_data)
 			goto out_unlock;
 
@@ -383,9 +436,101 @@ static ssize_t virtiovf_save_read(struct file *filp, char __user *buf, size_t le
 	return done;
 }
 
+static long virtiovf_precopy_ioctl(struct file *filp, unsigned int cmd,
+				   unsigned long arg)
+{
+	struct virtiovf_migration_file *migf = filp->private_data;
+	struct virtiovf_pci_core_device *virtvdev = migf->virtvdev;
+	struct vfio_precopy_info info = {};
+	loff_t *pos = &filp->f_pos;
+	bool end_of_data = false;
+	unsigned long minsz;
+	u32 ctx_size = 0;
+	int ret;
+
+	if (cmd != VFIO_MIG_GET_PRECOPY_INFO)
+		return -ENOTTY;
+
+	minsz = offsetofend(struct vfio_precopy_info, dirty_bytes);
+	if (copy_from_user(&info, (void __user *)arg, minsz))
+		return -EFAULT;
+
+	if (info.argsz < minsz)
+		return -EINVAL;
+
+	mutex_lock(&virtvdev->state_mutex);
+	if (virtvdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY &&
+	    virtvdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY_P2P) {
+		ret = -EINVAL;
+		goto err_state_unlock;
+	}
+
+	/*
+	 * The virtio specification does not include a PRE_COPY concept.
+	 * Since we can expect the data to remain the same for a certain period,
+	 * we use a rate limiter mechanism before making a call to the device.
+	 */
+	if (__ratelimit(&migf->pre_copy_rl_state)) {
+
+		ret = virtio_pci_admin_dev_parts_metadata_get(virtvdev->core_device.pdev,
+					VIRTIO_RESOURCE_OBJ_DEV_PARTS, migf->obj_id,
+					VIRTIO_ADMIN_CMD_DEV_PARTS_METADATA_TYPE_SIZE,
+					&ctx_size);
+		if (ret)
+			goto err_state_unlock;
+	}
+
+	mutex_lock(&migf->lock);
+	if (migf->state == VIRTIOVF_MIGF_STATE_ERROR) {
+		ret = -ENODEV;
+		goto err_migf_unlock;
+	}
+
+	if (migf->pre_copy_initial_bytes > *pos) {
+		info.initial_bytes = migf->pre_copy_initial_bytes - *pos;
+	} else {
+		info.dirty_bytes = migf->max_pos - *pos;
+		if (!info.dirty_bytes)
+			end_of_data = true;
+		info.dirty_bytes += ctx_size;
+	}
+
+	if (!end_of_data || !ctx_size) {
+		mutex_unlock(&migf->lock);
+		goto done;
+	}
+
+	mutex_unlock(&migf->lock);
+	/*
+	 * We finished transferring the current state and the device has a
+	 * dirty state, read a new state.
+	 */
+	ret = virtiovf_read_device_context_chunk(migf, ctx_size);
+	if (ret)
+		/*
+		 * The machine is running, and context size could be grow, so no reason to mark
+		 * the device state as VIRTIOVF_MIGF_STATE_ERROR.
+		 */
+		goto err_state_unlock;
+
+done:
+	virtiovf_state_mutex_unlock(virtvdev);
+	if (copy_to_user((void __user *)arg, &info, minsz))
+		return -EFAULT;
+	return 0;
+
+err_migf_unlock:
+	mutex_unlock(&migf->lock);
+err_state_unlock:
+	virtiovf_state_mutex_unlock(virtvdev);
+	return ret;
+}
+
 static const struct file_operations virtiovf_save_fops = {
 	.owner = THIS_MODULE,
 	.read = virtiovf_save_read,
+	.unlocked_ioctl = virtiovf_precopy_ioctl,
+	.compat_ioctl = compat_ptr_ioctl,
 	.release = virtiovf_release_file,
 };
 
@@ -429,7 +574,7 @@ virtiovf_read_device_context_chunk(struct virtiovf_migration_file *migf,
 	int nent;
 	int ret;
 
-	buf = virtiovf_alloc_data_buffer(migf, ctx_size);
+	buf = virtiovf_get_data_buffer(migf, ctx_size);
 	if (IS_ERR(buf))
 		return PTR_ERR(buf);
 
@@ -464,7 +609,7 @@ virtiovf_read_device_context_chunk(struct virtiovf_migration_file *migf,
 		goto out;
 
 	buf->length = res_size;
-	header_buf = virtiovf_alloc_data_buffer(migf,
+	header_buf = virtiovf_get_data_buffer(migf,
 				sizeof(struct virtiovf_migration_header));
 	if (IS_ERR(header_buf)) {
 		ret = PTR_ERR(header_buf);
@@ -489,8 +634,43 @@ virtiovf_read_device_context_chunk(struct virtiovf_migration_file *migf,
 	return ret;
 }
 
+static int
+virtiovf_pci_save_device_final_data(struct virtiovf_pci_core_device *virtvdev)
+{
+	struct virtiovf_migration_file *migf = virtvdev->saving_migf;
+	u32 ctx_size;
+	int ret;
+
+	if (migf->state == VIRTIOVF_MIGF_STATE_ERROR)
+		return -ENODEV;
+
+	ret = virtio_pci_admin_dev_parts_metadata_get(virtvdev->core_device.pdev,
+				VIRTIO_RESOURCE_OBJ_DEV_PARTS, migf->obj_id,
+				VIRTIO_ADMIN_CMD_DEV_PARTS_METADATA_TYPE_SIZE,
+				&ctx_size);
+	if (ret)
+		goto err;
+
+	if (!ctx_size) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	ret = virtiovf_read_device_context_chunk(migf, ctx_size);
+	if (ret)
+		goto err;
+
+	migf->state = VIRTIOVF_MIGF_STATE_COMPLETE;
+	return 0;
+
+err:
+	migf->state = VIRTIOVF_MIGF_STATE_ERROR;
+	return ret;
+}
+
 static struct virtiovf_migration_file *
-virtiovf_pci_save_device_data(struct virtiovf_pci_core_device *virtvdev)
+virtiovf_pci_save_device_data(struct virtiovf_pci_core_device *virtvdev,
+			      bool pre_copy)
 {
 	struct virtiovf_migration_file *migf;
 	u32 ctx_size;
@@ -541,6 +721,18 @@ virtiovf_pci_save_device_data(struct virtiovf_pci_core_device *virtvdev)
 	if (ret)
 		goto out_clean;
 
+	if (pre_copy) {
+		migf->pre_copy_initial_bytes = migf->max_pos;
+		/* Arbitrarily set the pre-copy rate limit to 1-second intervals */
+		ratelimit_state_init(&migf->pre_copy_rl_state, 1 * HZ, 1);
+		/* Prevent any rate messages upon its usage */
+		ratelimit_set_flags(&migf->pre_copy_rl_state,
+				    RATELIMIT_MSG_ON_RELEASE);
+		migf->state = VIRTIOVF_MIGF_STATE_PRECOPY;
+	} else {
+		migf->state = VIRTIOVF_MIGF_STATE_COMPLETE;
+	}
+
 	return migf;
 
 out_clean:
@@ -950,7 +1142,8 @@ virtiovf_pci_step_device_state_locked(struct virtiovf_pci_core_device *virtvdev,
 		return NULL;
 	}
 
-	if (cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_RUNNING_P2P) {
+	if ((cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_RUNNING_P2P) ||
+	    (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_PRE_COPY_P2P)) {
 		ret = virtio_pci_admin_mode_set(virtvdev->core_device.pdev,
 						BIT(VIRTIO_ADMIN_CMD_DEV_MODE_F_STOPPED));
 		if (ret)
@@ -958,7 +1151,8 @@ virtiovf_pci_step_device_state_locked(struct virtiovf_pci_core_device *virtvdev,
 		return NULL;
 	}
 
-	if (cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_RUNNING) {
+	if ((cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_RUNNING) ||
+	    (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && new == VFIO_DEVICE_STATE_PRE_COPY)) {
 		ret = virtio_pci_admin_mode_set(virtvdev->core_device.pdev, 0);
 		if (ret)
 			return ERR_PTR(ret);
@@ -968,7 +1162,7 @@ virtiovf_pci_step_device_state_locked(struct virtiovf_pci_core_device *virtvdev,
 	if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_STOP_COPY) {
 		struct virtiovf_migration_file *migf;
 
-		migf = virtiovf_pci_save_device_data(virtvdev);
+		migf = virtiovf_pci_save_device_data(virtvdev, false);
 		if (IS_ERR(migf))
 			return ERR_CAST(migf);
 		get_file(migf->filp);
@@ -976,7 +1170,9 @@ virtiovf_pci_step_device_state_locked(struct virtiovf_pci_core_device *virtvdev,
 		return migf->filp;
 	}
 
-	if (cur == VFIO_DEVICE_STATE_STOP_COPY && new == VFIO_DEVICE_STATE_STOP) {
+	if ((cur == VFIO_DEVICE_STATE_STOP_COPY && new == VFIO_DEVICE_STATE_STOP) ||
+	    (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_RUNNING) ||
+	    (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && new == VFIO_DEVICE_STATE_RUNNING_P2P)) {
 		virtiovf_disable_fds(virtvdev);
 		return NULL;
 	}
@@ -997,6 +1193,24 @@ virtiovf_pci_step_device_state_locked(struct virtiovf_pci_core_device *virtvdev,
 		return NULL;
 	}
 
+	if ((cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_PRE_COPY) ||
+	    (cur == VFIO_DEVICE_STATE_RUNNING_P2P &&
+	     new == VFIO_DEVICE_STATE_PRE_COPY_P2P)) {
+		struct virtiovf_migration_file *migf;
+
+		migf = virtiovf_pci_save_device_data(virtvdev, true);
+		if (IS_ERR(migf))
+			return ERR_CAST(migf);
+		get_file(migf->filp);
+		virtvdev->saving_migf = migf;
+		return migf->filp;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && new == VFIO_DEVICE_STATE_STOP_COPY) {
+		ret = virtiovf_pci_save_device_final_data(virtvdev);
+		return ret ? ERR_PTR(ret) : NULL;
+	}
+
 	/*
 	 * vfio_mig_get_next_state() does not use arcs other than the above
 	 */
@@ -1101,7 +1315,8 @@ void virtiovf_set_migratable(struct virtiovf_pci_core_device *virtvdev)
 	spin_lock_init(&virtvdev->reset_lock);
 	virtvdev->core_device.vdev.migration_flags =
 		VFIO_MIGRATION_STOP_COPY |
-		VFIO_MIGRATION_P2P;
+		VFIO_MIGRATION_P2P |
+		VFIO_MIGRATION_PRE_COPY;
 	virtvdev->core_device.vdev.mig_ops = &virtvdev_pci_mig_ops;
 }
 

From 40bcdb12c68dbb6f457deb0adab5008ef61c13d7 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Wed, 13 Nov 2024 13:52:00 +0200
Subject: [PATCH 1126/1530] vfio/virtio: Enable live migration once VIRTIO_PCI
 was configured

Now that the driver supports live migration, only the legacy IO
functionality depends on config VIRTIO_PCI_ADMIN_LEGACY.

As part of that we introduce a bool configuration option as a sub menu
under the driver's main live migration feature named
VIRTIO_VFIO_PCI_ADMIN_LEGACY, to control the legacy IO functionality.

This will let users configuring the kernel, know which features from the
description might be available in the resulting driver.

As of that, move the legacy IO into a separate file to be compiled only
once CONFIG_VIRTIO_VFIO_PCI_ADMIN_LEGACY was configured and let the live
migration depends only on VIRTIO_PCI.

Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20241113115200.209269-8-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/virtio/Kconfig     |  42 ++-
 drivers/vfio/pci/virtio/Makefile    |   1 +
 drivers/vfio/pci/virtio/common.h    |  19 ++
 drivers/vfio/pci/virtio/legacy_io.c | 418 ++++++++++++++++++++++++++++
 drivers/vfio/pci/virtio/main.c      | 410 ++-------------------------
 5 files changed, 489 insertions(+), 401 deletions(-)
 create mode 100644 drivers/vfio/pci/virtio/legacy_io.c

diff --git a/drivers/vfio/pci/virtio/Kconfig b/drivers/vfio/pci/virtio/Kconfig
index bd80eca4a196c..2770f7eb702cc 100644
--- a/drivers/vfio/pci/virtio/Kconfig
+++ b/drivers/vfio/pci/virtio/Kconfig
@@ -1,15 +1,31 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config VIRTIO_VFIO_PCI
-        tristate "VFIO support for VIRTIO NET PCI devices"
-        depends on VIRTIO_PCI && VIRTIO_PCI_ADMIN_LEGACY
-        select VFIO_PCI_CORE
-        help
-          This provides support for exposing VIRTIO NET VF devices which support
-          legacy IO access, using the VFIO framework that can work with a legacy
-          virtio driver in the guest.
-          Based on PCIe spec, VFs do not support I/O Space.
-          As of that this driver emulates I/O BAR in software to let a VF be
-          seen as a transitional device by its users and let it work with
-          a legacy driver.
-
-          If you don't know what to do here, say N.
+	tristate "VFIO support for VIRTIO NET PCI VF devices"
+	depends on VIRTIO_PCI
+	select VFIO_PCI_CORE
+	help
+	  This provides migration support for VIRTIO NET PCI VF devices
+	  using the VFIO framework. Migration support requires the
+	  SR-IOV PF device to support specific VIRTIO extensions,
+	  otherwise this driver provides no additional functionality
+	  beyond vfio-pci.
+
+	  Migration support in this driver relies on dirty page tracking
+	  provided by the IOMMU hardware and exposed through IOMMUFD, any
+	  other use cases are dis-recommended.
+
+	  If you don't know what to do here, say N.
+
+config VIRTIO_VFIO_PCI_ADMIN_LEGACY
+	bool "Legacy I/O support for VIRTIO NET PCI VF devices"
+	depends on VIRTIO_VFIO_PCI && VIRTIO_PCI_ADMIN_LEGACY
+	default y
+	help
+	  This extends the virtio-vfio-pci driver to support legacy I/O
+	  access, allowing use of legacy virtio drivers with VIRTIO NET
+	  PCI VF devices. Legacy I/O support requires the SR-IOV PF
+	  device to support and enable specific VIRTIO extensions,
+	  otherwise this driver provides no additional functionality
+	  beyond vfio-pci.
+
+	  If you don't know what to do here, say N.
diff --git a/drivers/vfio/pci/virtio/Makefile b/drivers/vfio/pci/virtio/Makefile
index bf0ccde6a91ab..d9b0bb40d6b34 100644
--- a/drivers/vfio/pci/virtio/Makefile
+++ b/drivers/vfio/pci/virtio/Makefile
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio-vfio-pci.o
 virtio-vfio-pci-y := main.o migrate.o
+virtio-vfio-pci-$(CONFIG_VIRTIO_VFIO_PCI_ADMIN_LEGACY) += legacy_io.o
diff --git a/drivers/vfio/pci/virtio/common.h b/drivers/vfio/pci/virtio/common.h
index 5704603f0f9d9..c7d7e27af386e 100644
--- a/drivers/vfio/pci/virtio/common.h
+++ b/drivers/vfio/pci/virtio/common.h
@@ -78,6 +78,7 @@ struct virtiovf_migration_file {
 
 struct virtiovf_pci_core_device {
 	struct vfio_pci_core_device core_device;
+#ifdef CONFIG_VIRTIO_VFIO_PCI_ADMIN_LEGACY
 	u8 *bar0_virtual_buf;
 	/* synchronize access to the virtual buf */
 	struct mutex bar_mutex;
@@ -87,6 +88,7 @@ struct virtiovf_pci_core_device {
 	__le16 pci_cmd;
 	u8 bar0_virtual_buf_size;
 	u8 notify_bar;
+#endif
 
 	/* LM related */
 	u8 migrate_cap:1;
@@ -105,4 +107,21 @@ void virtiovf_open_migration(struct virtiovf_pci_core_device *virtvdev);
 void virtiovf_close_migration(struct virtiovf_pci_core_device *virtvdev);
 void virtiovf_migration_reset_done(struct pci_dev *pdev);
 
+#ifdef CONFIG_VIRTIO_VFIO_PCI_ADMIN_LEGACY
+int virtiovf_open_legacy_io(struct virtiovf_pci_core_device *virtvdev);
+long virtiovf_vfio_pci_core_ioctl(struct vfio_device *core_vdev,
+				  unsigned int cmd, unsigned long arg);
+int virtiovf_pci_ioctl_get_region_info(struct vfio_device *core_vdev,
+				       unsigned int cmd, unsigned long arg);
+ssize_t virtiovf_pci_core_write(struct vfio_device *core_vdev,
+				const char __user *buf, size_t count,
+				loff_t *ppos);
+ssize_t virtiovf_pci_core_read(struct vfio_device *core_vdev, char __user *buf,
+			       size_t count, loff_t *ppos);
+bool virtiovf_support_legacy_io(struct pci_dev *pdev);
+int virtiovf_init_legacy_io(struct virtiovf_pci_core_device *virtvdev);
+void virtiovf_release_legacy_io(struct virtiovf_pci_core_device *virtvdev);
+void virtiovf_legacy_io_reset_done(struct pci_dev *pdev);
+#endif
+
 #endif /* VIRTIO_VFIO_COMMON_H */
diff --git a/drivers/vfio/pci/virtio/legacy_io.c b/drivers/vfio/pci/virtio/legacy_io.c
new file mode 100644
index 0000000000000..20382ee15faca
--- /dev/null
+++ b/drivers/vfio/pci/virtio/legacy_io.c
@@ -0,0 +1,418 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/pm_runtime.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+#include <linux/vfio_pci_core.h>
+#include <linux/virtio_pci.h>
+#include <linux/virtio_net.h>
+#include <linux/virtio_pci_admin.h>
+
+#include "common.h"
+
+static int
+virtiovf_issue_legacy_rw_cmd(struct virtiovf_pci_core_device *virtvdev,
+			     loff_t pos, char __user *buf,
+			     size_t count, bool read)
+{
+	bool msix_enabled =
+		(virtvdev->core_device.irq_type == VFIO_PCI_MSIX_IRQ_INDEX);
+	struct pci_dev *pdev = virtvdev->core_device.pdev;
+	u8 *bar0_buf = virtvdev->bar0_virtual_buf;
+	bool common;
+	u8 offset;
+	int ret;
+
+	common = pos < VIRTIO_PCI_CONFIG_OFF(msix_enabled);
+	/* offset within the relevant configuration area */
+	offset = common ? pos : pos - VIRTIO_PCI_CONFIG_OFF(msix_enabled);
+	mutex_lock(&virtvdev->bar_mutex);
+	if (read) {
+		if (common)
+			ret = virtio_pci_admin_legacy_common_io_read(pdev, offset,
+					count, bar0_buf + pos);
+		else
+			ret = virtio_pci_admin_legacy_device_io_read(pdev, offset,
+					count, bar0_buf + pos);
+		if (ret)
+			goto out;
+		if (copy_to_user(buf, bar0_buf + pos, count))
+			ret = -EFAULT;
+	} else {
+		if (copy_from_user(bar0_buf + pos, buf, count)) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		if (common)
+			ret = virtio_pci_admin_legacy_common_io_write(pdev, offset,
+					count, bar0_buf + pos);
+		else
+			ret = virtio_pci_admin_legacy_device_io_write(pdev, offset,
+					count, bar0_buf + pos);
+	}
+out:
+	mutex_unlock(&virtvdev->bar_mutex);
+	return ret;
+}
+
+static int
+virtiovf_pci_bar0_rw(struct virtiovf_pci_core_device *virtvdev,
+		     loff_t pos, char __user *buf,
+		     size_t count, bool read)
+{
+	struct vfio_pci_core_device *core_device = &virtvdev->core_device;
+	struct pci_dev *pdev = core_device->pdev;
+	u16 queue_notify;
+	int ret;
+
+	if (!(le16_to_cpu(virtvdev->pci_cmd) & PCI_COMMAND_IO))
+		return -EIO;
+
+	if (pos + count > virtvdev->bar0_virtual_buf_size)
+		return -EINVAL;
+
+	ret = pm_runtime_resume_and_get(&pdev->dev);
+	if (ret) {
+		pci_info_ratelimited(pdev, "runtime resume failed %d\n", ret);
+		return -EIO;
+	}
+
+	switch (pos) {
+	case VIRTIO_PCI_QUEUE_NOTIFY:
+		if (count != sizeof(queue_notify)) {
+			ret = -EINVAL;
+			goto end;
+		}
+		if (read) {
+			ret = vfio_pci_core_ioread16(core_device, true, &queue_notify,
+						     virtvdev->notify_addr);
+			if (ret)
+				goto end;
+			if (copy_to_user(buf, &queue_notify,
+					 sizeof(queue_notify))) {
+				ret = -EFAULT;
+				goto end;
+			}
+		} else {
+			if (copy_from_user(&queue_notify, buf, count)) {
+				ret = -EFAULT;
+				goto end;
+			}
+			ret = vfio_pci_core_iowrite16(core_device, true, queue_notify,
+						      virtvdev->notify_addr);
+		}
+		break;
+	default:
+		ret = virtiovf_issue_legacy_rw_cmd(virtvdev, pos, buf, count,
+						   read);
+	}
+
+end:
+	pm_runtime_put(&pdev->dev);
+	return ret ? ret : count;
+}
+
+static ssize_t virtiovf_pci_read_config(struct vfio_device *core_vdev,
+					char __user *buf, size_t count,
+					loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+	size_t register_offset;
+	loff_t copy_offset;
+	size_t copy_count;
+	__le32 val32;
+	__le16 val16;
+	u8 val8;
+	int ret;
+
+	ret = vfio_pci_core_read(core_vdev, buf, count, ppos);
+	if (ret < 0)
+		return ret;
+
+	if (vfio_pci_core_range_intersect_range(pos, count, PCI_DEVICE_ID,
+						sizeof(val16), &copy_offset,
+						&copy_count, &register_offset)) {
+		val16 = cpu_to_le16(VIRTIO_TRANS_ID_NET);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset, copy_count))
+			return -EFAULT;
+	}
+
+	if ((le16_to_cpu(virtvdev->pci_cmd) & PCI_COMMAND_IO) &&
+	    vfio_pci_core_range_intersect_range(pos, count, PCI_COMMAND,
+						sizeof(val16), &copy_offset,
+						&copy_count, &register_offset)) {
+		if (copy_from_user((void *)&val16 + register_offset, buf + copy_offset,
+				   copy_count))
+			return -EFAULT;
+		val16 |= cpu_to_le16(PCI_COMMAND_IO);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
+				 copy_count))
+			return -EFAULT;
+	}
+
+	if (vfio_pci_core_range_intersect_range(pos, count, PCI_REVISION_ID,
+						sizeof(val8), &copy_offset,
+						&copy_count, &register_offset)) {
+		/* Transional needs to have revision 0 */
+		val8 = 0;
+		if (copy_to_user(buf + copy_offset, &val8, copy_count))
+			return -EFAULT;
+	}
+
+	if (vfio_pci_core_range_intersect_range(pos, count, PCI_BASE_ADDRESS_0,
+						sizeof(val32), &copy_offset,
+						&copy_count, &register_offset)) {
+		u32 bar_mask = ~(virtvdev->bar0_virtual_buf_size - 1);
+		u32 pci_base_addr_0 = le32_to_cpu(virtvdev->pci_base_addr_0);
+
+		val32 = cpu_to_le32((pci_base_addr_0 & bar_mask) | PCI_BASE_ADDRESS_SPACE_IO);
+		if (copy_to_user(buf + copy_offset, (void *)&val32 + register_offset, copy_count))
+			return -EFAULT;
+	}
+
+	if (vfio_pci_core_range_intersect_range(pos, count, PCI_SUBSYSTEM_ID,
+						sizeof(val16), &copy_offset,
+						&copy_count, &register_offset)) {
+		/*
+		 * Transitional devices use the PCI subsystem device id as
+		 * virtio device id, same as legacy driver always did.
+		 */
+		val16 = cpu_to_le16(VIRTIO_ID_NET);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
+				 copy_count))
+			return -EFAULT;
+	}
+
+	if (vfio_pci_core_range_intersect_range(pos, count, PCI_SUBSYSTEM_VENDOR_ID,
+						sizeof(val16), &copy_offset,
+						&copy_count, &register_offset)) {
+		val16 = cpu_to_le16(PCI_VENDOR_ID_REDHAT_QUMRANET);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
+				 copy_count))
+			return -EFAULT;
+	}
+
+	return count;
+}
+
+ssize_t virtiovf_pci_core_read(struct vfio_device *core_vdev, char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+
+	if (!count)
+		return 0;
+
+	if (index == VFIO_PCI_CONFIG_REGION_INDEX)
+		return virtiovf_pci_read_config(core_vdev, buf, count, ppos);
+
+	if (index == VFIO_PCI_BAR0_REGION_INDEX)
+		return virtiovf_pci_bar0_rw(virtvdev, pos, buf, count, true);
+
+	return vfio_pci_core_read(core_vdev, buf, count, ppos);
+}
+
+static ssize_t virtiovf_pci_write_config(struct vfio_device *core_vdev,
+					 const char __user *buf, size_t count,
+					 loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+	size_t register_offset;
+	loff_t copy_offset;
+	size_t copy_count;
+
+	if (vfio_pci_core_range_intersect_range(pos, count, PCI_COMMAND,
+						sizeof(virtvdev->pci_cmd),
+						&copy_offset, &copy_count,
+						&register_offset)) {
+		if (copy_from_user((void *)&virtvdev->pci_cmd + register_offset,
+				   buf + copy_offset,
+				   copy_count))
+			return -EFAULT;
+	}
+
+	if (vfio_pci_core_range_intersect_range(pos, count, PCI_BASE_ADDRESS_0,
+						sizeof(virtvdev->pci_base_addr_0),
+						&copy_offset, &copy_count,
+						&register_offset)) {
+		if (copy_from_user((void *)&virtvdev->pci_base_addr_0 + register_offset,
+				   buf + copy_offset,
+				   copy_count))
+			return -EFAULT;
+	}
+
+	return vfio_pci_core_write(core_vdev, buf, count, ppos);
+}
+
+ssize_t virtiovf_pci_core_write(struct vfio_device *core_vdev, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+
+	if (!count)
+		return 0;
+
+	if (index == VFIO_PCI_CONFIG_REGION_INDEX)
+		return virtiovf_pci_write_config(core_vdev, buf, count, ppos);
+
+	if (index == VFIO_PCI_BAR0_REGION_INDEX)
+		return virtiovf_pci_bar0_rw(virtvdev, pos, (char __user *)buf, count, false);
+
+	return vfio_pci_core_write(core_vdev, buf, count, ppos);
+}
+
+int virtiovf_pci_ioctl_get_region_info(struct vfio_device *core_vdev,
+				       unsigned int cmd, unsigned long arg)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	unsigned long minsz = offsetofend(struct vfio_region_info, offset);
+	void __user *uarg = (void __user *)arg;
+	struct vfio_region_info info = {};
+
+	if (copy_from_user(&info, uarg, minsz))
+		return -EFAULT;
+
+	if (info.argsz < minsz)
+		return -EINVAL;
+
+	switch (info.index) {
+	case VFIO_PCI_BAR0_REGION_INDEX:
+		info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
+		info.size = virtvdev->bar0_virtual_buf_size;
+		info.flags = VFIO_REGION_INFO_FLAG_READ |
+			     VFIO_REGION_INFO_FLAG_WRITE;
+		return copy_to_user(uarg, &info, minsz) ? -EFAULT : 0;
+	default:
+		return vfio_pci_core_ioctl(core_vdev, cmd, arg);
+	}
+}
+
+long virtiovf_vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd,
+				  unsigned long arg)
+{
+	switch (cmd) {
+	case VFIO_DEVICE_GET_REGION_INFO:
+		return virtiovf_pci_ioctl_get_region_info(core_vdev, cmd, arg);
+	default:
+		return vfio_pci_core_ioctl(core_vdev, cmd, arg);
+	}
+}
+
+static int virtiovf_set_notify_addr(struct virtiovf_pci_core_device *virtvdev)
+{
+	struct vfio_pci_core_device *core_device = &virtvdev->core_device;
+	int ret;
+
+	/*
+	 * Setup the BAR where the 'notify' exists to be used by vfio as well
+	 * This will let us mmap it only once and use it when needed.
+	 */
+	ret = vfio_pci_core_setup_barmap(core_device,
+					 virtvdev->notify_bar);
+	if (ret)
+		return ret;
+
+	virtvdev->notify_addr = core_device->barmap[virtvdev->notify_bar] +
+			virtvdev->notify_offset;
+	return 0;
+}
+
+int virtiovf_open_legacy_io(struct virtiovf_pci_core_device *virtvdev)
+{
+	if (!virtvdev->bar0_virtual_buf)
+		return 0;
+
+	/*
+	 * Upon close_device() the vfio_pci_core_disable() is called
+	 * and will close all the previous mmaps, so it seems that the
+	 * valid life cycle for the 'notify' addr is per open/close.
+	 */
+	return virtiovf_set_notify_addr(virtvdev);
+}
+
+static int virtiovf_get_device_config_size(unsigned short device)
+{
+	/* Network card */
+	return offsetofend(struct virtio_net_config, status);
+}
+
+static int virtiovf_read_notify_info(struct virtiovf_pci_core_device *virtvdev)
+{
+	u64 offset;
+	int ret;
+	u8 bar;
+
+	ret = virtio_pci_admin_legacy_io_notify_info(virtvdev->core_device.pdev,
+				VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_MEM,
+				&bar, &offset);
+	if (ret)
+		return ret;
+
+	virtvdev->notify_bar = bar;
+	virtvdev->notify_offset = offset;
+	return 0;
+}
+
+static bool virtiovf_bar0_exists(struct pci_dev *pdev)
+{
+	struct resource *res = pdev->resource;
+
+	return res->flags;
+}
+
+bool virtiovf_support_legacy_io(struct pci_dev *pdev)
+{
+	return virtio_pci_admin_has_legacy_io(pdev) && !virtiovf_bar0_exists(pdev);
+}
+
+int virtiovf_init_legacy_io(struct virtiovf_pci_core_device *virtvdev)
+{
+	struct pci_dev *pdev = virtvdev->core_device.pdev;
+	int ret;
+
+	ret = virtiovf_read_notify_info(virtvdev);
+	if (ret)
+		return ret;
+
+	virtvdev->bar0_virtual_buf_size = VIRTIO_PCI_CONFIG_OFF(true) +
+				virtiovf_get_device_config_size(pdev->device);
+	BUILD_BUG_ON(!is_power_of_2(virtvdev->bar0_virtual_buf_size));
+	virtvdev->bar0_virtual_buf = kzalloc(virtvdev->bar0_virtual_buf_size,
+					     GFP_KERNEL);
+	if (!virtvdev->bar0_virtual_buf)
+		return -ENOMEM;
+	mutex_init(&virtvdev->bar_mutex);
+	return 0;
+}
+
+void virtiovf_release_legacy_io(struct virtiovf_pci_core_device *virtvdev)
+{
+	kfree(virtvdev->bar0_virtual_buf);
+}
+
+void virtiovf_legacy_io_reset_done(struct pci_dev *pdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = dev_get_drvdata(&pdev->dev);
+
+	virtvdev->pci_cmd = 0;
+}
diff --git a/drivers/vfio/pci/virtio/main.c b/drivers/vfio/pci/virtio/main.c
index e9ae172090261..d534d48c41633 100644
--- a/drivers/vfio/pci/virtio/main.c
+++ b/drivers/vfio/pci/virtio/main.c
@@ -18,330 +18,6 @@
 
 #include "common.h"
 
-static int
-virtiovf_issue_legacy_rw_cmd(struct virtiovf_pci_core_device *virtvdev,
-			     loff_t pos, char __user *buf,
-			     size_t count, bool read)
-{
-	bool msix_enabled =
-		(virtvdev->core_device.irq_type == VFIO_PCI_MSIX_IRQ_INDEX);
-	struct pci_dev *pdev = virtvdev->core_device.pdev;
-	u8 *bar0_buf = virtvdev->bar0_virtual_buf;
-	bool common;
-	u8 offset;
-	int ret;
-
-	common = pos < VIRTIO_PCI_CONFIG_OFF(msix_enabled);
-	/* offset within the relevant configuration area */
-	offset = common ? pos : pos - VIRTIO_PCI_CONFIG_OFF(msix_enabled);
-	mutex_lock(&virtvdev->bar_mutex);
-	if (read) {
-		if (common)
-			ret = virtio_pci_admin_legacy_common_io_read(pdev, offset,
-					count, bar0_buf + pos);
-		else
-			ret = virtio_pci_admin_legacy_device_io_read(pdev, offset,
-					count, bar0_buf + pos);
-		if (ret)
-			goto out;
-		if (copy_to_user(buf, bar0_buf + pos, count))
-			ret = -EFAULT;
-	} else {
-		if (copy_from_user(bar0_buf + pos, buf, count)) {
-			ret = -EFAULT;
-			goto out;
-		}
-
-		if (common)
-			ret = virtio_pci_admin_legacy_common_io_write(pdev, offset,
-					count, bar0_buf + pos);
-		else
-			ret = virtio_pci_admin_legacy_device_io_write(pdev, offset,
-					count, bar0_buf + pos);
-	}
-out:
-	mutex_unlock(&virtvdev->bar_mutex);
-	return ret;
-}
-
-static int
-virtiovf_pci_bar0_rw(struct virtiovf_pci_core_device *virtvdev,
-		     loff_t pos, char __user *buf,
-		     size_t count, bool read)
-{
-	struct vfio_pci_core_device *core_device = &virtvdev->core_device;
-	struct pci_dev *pdev = core_device->pdev;
-	u16 queue_notify;
-	int ret;
-
-	if (!(le16_to_cpu(virtvdev->pci_cmd) & PCI_COMMAND_IO))
-		return -EIO;
-
-	if (pos + count > virtvdev->bar0_virtual_buf_size)
-		return -EINVAL;
-
-	ret = pm_runtime_resume_and_get(&pdev->dev);
-	if (ret) {
-		pci_info_ratelimited(pdev, "runtime resume failed %d\n", ret);
-		return -EIO;
-	}
-
-	switch (pos) {
-	case VIRTIO_PCI_QUEUE_NOTIFY:
-		if (count != sizeof(queue_notify)) {
-			ret = -EINVAL;
-			goto end;
-		}
-		if (read) {
-			ret = vfio_pci_core_ioread16(core_device, true, &queue_notify,
-						     virtvdev->notify_addr);
-			if (ret)
-				goto end;
-			if (copy_to_user(buf, &queue_notify,
-					 sizeof(queue_notify))) {
-				ret = -EFAULT;
-				goto end;
-			}
-		} else {
-			if (copy_from_user(&queue_notify, buf, count)) {
-				ret = -EFAULT;
-				goto end;
-			}
-			ret = vfio_pci_core_iowrite16(core_device, true, queue_notify,
-						      virtvdev->notify_addr);
-		}
-		break;
-	default:
-		ret = virtiovf_issue_legacy_rw_cmd(virtvdev, pos, buf, count,
-						   read);
-	}
-
-end:
-	pm_runtime_put(&pdev->dev);
-	return ret ? ret : count;
-}
-
-static ssize_t virtiovf_pci_read_config(struct vfio_device *core_vdev,
-					char __user *buf, size_t count,
-					loff_t *ppos)
-{
-	struct virtiovf_pci_core_device *virtvdev = container_of(
-		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
-	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
-	size_t register_offset;
-	loff_t copy_offset;
-	size_t copy_count;
-	__le32 val32;
-	__le16 val16;
-	u8 val8;
-	int ret;
-
-	ret = vfio_pci_core_read(core_vdev, buf, count, ppos);
-	if (ret < 0)
-		return ret;
-
-	if (vfio_pci_core_range_intersect_range(pos, count, PCI_DEVICE_ID,
-						sizeof(val16), &copy_offset,
-						&copy_count, &register_offset)) {
-		val16 = cpu_to_le16(VIRTIO_TRANS_ID_NET);
-		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset, copy_count))
-			return -EFAULT;
-	}
-
-	if ((le16_to_cpu(virtvdev->pci_cmd) & PCI_COMMAND_IO) &&
-	    vfio_pci_core_range_intersect_range(pos, count, PCI_COMMAND,
-						sizeof(val16), &copy_offset,
-						&copy_count, &register_offset)) {
-		if (copy_from_user((void *)&val16 + register_offset, buf + copy_offset,
-				   copy_count))
-			return -EFAULT;
-		val16 |= cpu_to_le16(PCI_COMMAND_IO);
-		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
-				 copy_count))
-			return -EFAULT;
-	}
-
-	if (vfio_pci_core_range_intersect_range(pos, count, PCI_REVISION_ID,
-						sizeof(val8), &copy_offset,
-						&copy_count, &register_offset)) {
-		/* Transional needs to have revision 0 */
-		val8 = 0;
-		if (copy_to_user(buf + copy_offset, &val8, copy_count))
-			return -EFAULT;
-	}
-
-	if (vfio_pci_core_range_intersect_range(pos, count, PCI_BASE_ADDRESS_0,
-						sizeof(val32), &copy_offset,
-						&copy_count, &register_offset)) {
-		u32 bar_mask = ~(virtvdev->bar0_virtual_buf_size - 1);
-		u32 pci_base_addr_0 = le32_to_cpu(virtvdev->pci_base_addr_0);
-
-		val32 = cpu_to_le32((pci_base_addr_0 & bar_mask) | PCI_BASE_ADDRESS_SPACE_IO);
-		if (copy_to_user(buf + copy_offset, (void *)&val32 + register_offset, copy_count))
-			return -EFAULT;
-	}
-
-	if (vfio_pci_core_range_intersect_range(pos, count, PCI_SUBSYSTEM_ID,
-						sizeof(val16), &copy_offset,
-						&copy_count, &register_offset)) {
-		/*
-		 * Transitional devices use the PCI subsystem device id as
-		 * virtio device id, same as legacy driver always did.
-		 */
-		val16 = cpu_to_le16(VIRTIO_ID_NET);
-		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
-				 copy_count))
-			return -EFAULT;
-	}
-
-	if (vfio_pci_core_range_intersect_range(pos, count, PCI_SUBSYSTEM_VENDOR_ID,
-						sizeof(val16), &copy_offset,
-						&copy_count, &register_offset)) {
-		val16 = cpu_to_le16(PCI_VENDOR_ID_REDHAT_QUMRANET);
-		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
-				 copy_count))
-			return -EFAULT;
-	}
-
-	return count;
-}
-
-static ssize_t
-virtiovf_pci_core_read(struct vfio_device *core_vdev, char __user *buf,
-		       size_t count, loff_t *ppos)
-{
-	struct virtiovf_pci_core_device *virtvdev = container_of(
-		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
-	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
-	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
-
-	if (!count)
-		return 0;
-
-	if (index == VFIO_PCI_CONFIG_REGION_INDEX)
-		return virtiovf_pci_read_config(core_vdev, buf, count, ppos);
-
-	if (index == VFIO_PCI_BAR0_REGION_INDEX)
-		return virtiovf_pci_bar0_rw(virtvdev, pos, buf, count, true);
-
-	return vfio_pci_core_read(core_vdev, buf, count, ppos);
-}
-
-static ssize_t virtiovf_pci_write_config(struct vfio_device *core_vdev,
-					 const char __user *buf, size_t count,
-					 loff_t *ppos)
-{
-	struct virtiovf_pci_core_device *virtvdev = container_of(
-		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
-	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
-	size_t register_offset;
-	loff_t copy_offset;
-	size_t copy_count;
-
-	if (vfio_pci_core_range_intersect_range(pos, count, PCI_COMMAND,
-						sizeof(virtvdev->pci_cmd),
-						&copy_offset, &copy_count,
-						&register_offset)) {
-		if (copy_from_user((void *)&virtvdev->pci_cmd + register_offset,
-				   buf + copy_offset,
-				   copy_count))
-			return -EFAULT;
-	}
-
-	if (vfio_pci_core_range_intersect_range(pos, count, PCI_BASE_ADDRESS_0,
-						sizeof(virtvdev->pci_base_addr_0),
-						&copy_offset, &copy_count,
-						&register_offset)) {
-		if (copy_from_user((void *)&virtvdev->pci_base_addr_0 + register_offset,
-				   buf + copy_offset,
-				   copy_count))
-			return -EFAULT;
-	}
-
-	return vfio_pci_core_write(core_vdev, buf, count, ppos);
-}
-
-static ssize_t
-virtiovf_pci_core_write(struct vfio_device *core_vdev, const char __user *buf,
-			size_t count, loff_t *ppos)
-{
-	struct virtiovf_pci_core_device *virtvdev = container_of(
-		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
-	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
-	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
-
-	if (!count)
-		return 0;
-
-	if (index == VFIO_PCI_CONFIG_REGION_INDEX)
-		return virtiovf_pci_write_config(core_vdev, buf, count, ppos);
-
-	if (index == VFIO_PCI_BAR0_REGION_INDEX)
-		return virtiovf_pci_bar0_rw(virtvdev, pos, (char __user *)buf, count, false);
-
-	return vfio_pci_core_write(core_vdev, buf, count, ppos);
-}
-
-static int
-virtiovf_pci_ioctl_get_region_info(struct vfio_device *core_vdev,
-				   unsigned int cmd, unsigned long arg)
-{
-	struct virtiovf_pci_core_device *virtvdev = container_of(
-		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
-	unsigned long minsz = offsetofend(struct vfio_region_info, offset);
-	void __user *uarg = (void __user *)arg;
-	struct vfio_region_info info = {};
-
-	if (copy_from_user(&info, uarg, minsz))
-		return -EFAULT;
-
-	if (info.argsz < minsz)
-		return -EINVAL;
-
-	switch (info.index) {
-	case VFIO_PCI_BAR0_REGION_INDEX:
-		info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
-		info.size = virtvdev->bar0_virtual_buf_size;
-		info.flags = VFIO_REGION_INFO_FLAG_READ |
-			     VFIO_REGION_INFO_FLAG_WRITE;
-		return copy_to_user(uarg, &info, minsz) ? -EFAULT : 0;
-	default:
-		return vfio_pci_core_ioctl(core_vdev, cmd, arg);
-	}
-}
-
-static long
-virtiovf_vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd,
-			     unsigned long arg)
-{
-	switch (cmd) {
-	case VFIO_DEVICE_GET_REGION_INFO:
-		return virtiovf_pci_ioctl_get_region_info(core_vdev, cmd, arg);
-	default:
-		return vfio_pci_core_ioctl(core_vdev, cmd, arg);
-	}
-}
-
-static int
-virtiovf_set_notify_addr(struct virtiovf_pci_core_device *virtvdev)
-{
-	struct vfio_pci_core_device *core_device = &virtvdev->core_device;
-	int ret;
-
-	/*
-	 * Setup the BAR where the 'notify' exists to be used by vfio as well
-	 * This will let us mmap it only once and use it when needed.
-	 */
-	ret = vfio_pci_core_setup_barmap(core_device,
-					 virtvdev->notify_bar);
-	if (ret)
-		return ret;
-
-	virtvdev->notify_addr = core_device->barmap[virtvdev->notify_bar] +
-			virtvdev->notify_offset;
-	return 0;
-}
-
 static int virtiovf_pci_open_device(struct vfio_device *core_vdev)
 {
 	struct virtiovf_pci_core_device *virtvdev = container_of(core_vdev,
@@ -353,18 +29,13 @@ static int virtiovf_pci_open_device(struct vfio_device *core_vdev)
 	if (ret)
 		return ret;
 
-	if (virtvdev->bar0_virtual_buf) {
-		/*
-		 * Upon close_device() the vfio_pci_core_disable() is called
-		 * and will close all the previous mmaps, so it seems that the
-		 * valid life cycle for the 'notify' addr is per open/close.
-		 */
-		ret = virtiovf_set_notify_addr(virtvdev);
-		if (ret) {
-			vfio_pci_core_disable(vdev);
-			return ret;
-		}
+#ifdef CONFIG_VIRTIO_VFIO_PCI_ADMIN_LEGACY
+	ret = virtiovf_open_legacy_io(virtvdev);
+	if (ret) {
+		vfio_pci_core_disable(vdev);
+		return ret;
 	}
+#endif
 
 	virtiovf_open_migration(virtvdev);
 	vfio_pci_core_finish_enable(vdev);
@@ -380,66 +51,33 @@ static void virtiovf_pci_close_device(struct vfio_device *core_vdev)
 	vfio_pci_core_close_device(core_vdev);
 }
 
-static int virtiovf_get_device_config_size(unsigned short device)
-{
-	/* Network card */
-	return offsetofend(struct virtio_net_config, status);
-}
-
-static int virtiovf_read_notify_info(struct virtiovf_pci_core_device *virtvdev)
-{
-	u64 offset;
-	int ret;
-	u8 bar;
-
-	ret = virtio_pci_admin_legacy_io_notify_info(virtvdev->core_device.pdev,
-				VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_MEM,
-				&bar, &offset);
-	if (ret)
-		return ret;
-
-	virtvdev->notify_bar = bar;
-	virtvdev->notify_offset = offset;
-	return 0;
-}
-
+#ifdef CONFIG_VIRTIO_VFIO_PCI_ADMIN_LEGACY
 static int virtiovf_pci_init_device(struct vfio_device *core_vdev)
 {
 	struct virtiovf_pci_core_device *virtvdev = container_of(core_vdev,
 			struct virtiovf_pci_core_device, core_device.vdev);
-	struct pci_dev *pdev;
 	int ret;
 
 	ret = vfio_pci_core_init_dev(core_vdev);
 	if (ret)
 		return ret;
 
-	pdev = virtvdev->core_device.pdev;
 	/*
 	 * The vfio_device_ops.init() callback is set to virtiovf_pci_init_device()
 	 * only when legacy I/O is supported. Now, let's initialize it.
 	 */
-	ret = virtiovf_read_notify_info(virtvdev);
-	if (ret)
-		return ret;
-
-	virtvdev->bar0_virtual_buf_size = VIRTIO_PCI_CONFIG_OFF(true) +
-				virtiovf_get_device_config_size(pdev->device);
-	BUILD_BUG_ON(!is_power_of_2(virtvdev->bar0_virtual_buf_size));
-	virtvdev->bar0_virtual_buf = kzalloc(virtvdev->bar0_virtual_buf_size,
-					     GFP_KERNEL);
-	if (!virtvdev->bar0_virtual_buf)
-		return -ENOMEM;
-	mutex_init(&virtvdev->bar_mutex);
-	return 0;
+	return virtiovf_init_legacy_io(virtvdev);
 }
+#endif
 
 static void virtiovf_pci_core_release_dev(struct vfio_device *core_vdev)
 {
+#ifdef CONFIG_VIRTIO_VFIO_PCI_ADMIN_LEGACY
 	struct virtiovf_pci_core_device *virtvdev = container_of(core_vdev,
 			struct virtiovf_pci_core_device, core_device.vdev);
 
-	kfree(virtvdev->bar0_virtual_buf);
+	virtiovf_release_legacy_io(virtvdev);
+#endif
 	vfio_pci_core_release_dev(core_vdev);
 }
 
@@ -462,6 +100,7 @@ static const struct vfio_device_ops virtiovf_vfio_pci_lm_ops = {
 	.detach_ioas = vfio_iommufd_physical_detach_ioas,
 };
 
+#ifdef CONFIG_VIRTIO_VFIO_PCI_ADMIN_LEGACY
 static const struct vfio_device_ops virtiovf_vfio_pci_tran_lm_ops = {
 	.name = "virtio-vfio-pci-trans-lm",
 	.init = virtiovf_pci_init_device,
@@ -480,6 +119,7 @@ static const struct vfio_device_ops virtiovf_vfio_pci_tran_lm_ops = {
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
 	.detach_ioas = vfio_iommufd_physical_detach_ioas,
 };
+#endif
 
 static const struct vfio_device_ops virtiovf_vfio_pci_ops = {
 	.name = "virtio-vfio-pci",
@@ -500,13 +140,6 @@ static const struct vfio_device_ops virtiovf_vfio_pci_ops = {
 	.detach_ioas = vfio_iommufd_physical_detach_ioas,
 };
 
-static bool virtiovf_bar0_exists(struct pci_dev *pdev)
-{
-	struct resource *res = pdev->resource;
-
-	return res->flags;
-}
-
 static int virtiovf_pci_probe(struct pci_dev *pdev,
 			      const struct pci_device_id *id)
 {
@@ -517,12 +150,13 @@ static int virtiovf_pci_probe(struct pci_dev *pdev,
 	int ret;
 
 	if (pdev->is_virtfn) {
-		sup_legacy_io = virtio_pci_admin_has_legacy_io(pdev) &&
-				!virtiovf_bar0_exists(pdev);
-		sup_lm = virtio_pci_admin_has_dev_parts(pdev);
+#ifdef CONFIG_VIRTIO_VFIO_PCI_ADMIN_LEGACY
+		sup_legacy_io = virtiovf_support_legacy_io(pdev);
 		if (sup_legacy_io)
 			ops = &virtiovf_vfio_pci_tran_lm_ops;
-		else if (sup_lm)
+#endif
+		sup_lm = virtio_pci_admin_has_dev_parts(pdev);
+		if (sup_lm && !sup_legacy_io)
 			ops = &virtiovf_vfio_pci_lm_ops;
 	}
 
@@ -562,9 +196,9 @@ MODULE_DEVICE_TABLE(pci, virtiovf_pci_table);
 
 static void virtiovf_pci_aer_reset_done(struct pci_dev *pdev)
 {
-	struct virtiovf_pci_core_device *virtvdev = dev_get_drvdata(&pdev->dev);
-
-	virtvdev->pci_cmd = 0;
+#ifdef CONFIG_VIRTIO_VFIO_PCI_ADMIN_LEGACY
+	virtiovf_legacy_io_reset_done(pdev);
+#endif
 	virtiovf_migration_reset_done(pdev);
 }
 

From e434e54d3ffcd17eeadfcf3cf434bc1dff36daff Mon Sep 17 00:00:00 2001
From: Shijith Thotton <sthotton@marvell.com>
Date: Mon, 11 Nov 2024 19:15:11 +0530
Subject: [PATCH 1127/1530] PCI: hotplug: Add OCTEON PCI hotplug controller
 driver

Add a PCI hotplug controller driver for the OCTEON PCIe device. The OCTEON
PCIe device is a multi-function device where function 0 serves as the PCI
hotplug controller.

There is an out-of-band management console interface to firmware running on
function 0 whereby an administrator can disable functions to save power or
enable them with one of several personalities (virtio-net, virtio-crypto,
NVMe, etc) for the other functions.  Function 0 initiates hotplug events
handled by this driver when the other functions are enabled or disabled.

                 +--------------------------------+
                 |           Root Port            |
                 +--------------------------------+
                                 |
                                PCIe
                                 |
  +---------------------------------------------------------------+
  |              OCTEON PCIe Multifunction Device                 |
  +---------------------------------------------------------------+
               |                    |              |            |
               |                    |              |            |
  +---------------------+  +----------------+  +-----+  +----------------+
  |      Function 0     |  |   Function 1   |  | ... |  |   Function 7   |
  | (Hotplug controller)|  | (Hotplug slot) |  |     |  | (Hotplug slot) |
  +---------------------+  +----------------+  +-----+  +----------------+
               |
               |
  +-------------------------+
  |   Controller Firmware   |
  +-------------------------+

The hotplug controller driver enables hotplugging of non-controller
functions within the same device. During probing, the driver removes
the non-controller functions and registers them as PCI hotplug slots.
These slots are added back by the driver, only upon request from the
device firmware.

The controller uses MSI-X interrupts to notify the host of hotplug
events initiated by the OCTEON firmware. Additionally, the driver
allows users to enable or disable individual functions via sysfs slot
entries, as provided by the PCI hotplug framework.

Link: https://lore.kernel.org/r/20241111134523.2796699-1-sthotton@marvell.com
Co-developed-by: Vamsi Attunuru <vattunuru@marvell.com>
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
Signed-off-by: Shijith Thotton <sthotton@marvell.com>
[bhelgaas: use pci_info() when possible]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 MAINTAINERS                    |   6 +
 drivers/pci/hotplug/Kconfig    |  10 +
 drivers/pci/hotplug/Makefile   |   1 +
 drivers/pci/hotplug/octep_hp.c | 427 +++++++++++++++++++++++++++++++++
 4 files changed, 444 insertions(+)
 create mode 100644 drivers/pci/hotplug/octep_hp.c

diff --git a/MAINTAINERS b/MAINTAINERS
index c27f3190737f8..1e8714bbdea1e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13882,6 +13882,12 @@ R:	schalla@marvell.com
 R:	vattunuru@marvell.com
 F:	drivers/vdpa/octeon_ep/
 
+MARVELL OCTEON HOTPLUG DRIVER
+R:	Shijith Thotton <sthotton@marvell.com>
+R:	Vamsi Attunuru <vattunuru@marvell.com>
+S:	Supported
+F:	drivers/pci/hotplug/octep_hp.c
+
 MATROX FRAMEBUFFER DRIVER
 L:	linux-fbdev@vger.kernel.org
 S:	Orphan
diff --git a/drivers/pci/hotplug/Kconfig b/drivers/pci/hotplug/Kconfig
index 1472aef0fb812..123c4c7c2ab59 100644
--- a/drivers/pci/hotplug/Kconfig
+++ b/drivers/pci/hotplug/Kconfig
@@ -118,6 +118,16 @@ config HOTPLUG_PCI_CPCI_GENERIC
 
 	  When in doubt, say N.
 
+config HOTPLUG_PCI_OCTEONEP
+	bool "Marvell OCTEON PCI Hotplug driver"
+	depends on HOTPLUG_PCI
+	help
+	  Say Y here if you have an OCTEON PCIe device with a hotplug
+	  controller. This driver enables the non-controller functions of the
+	  device to be registered as hotplug slots.
+
+	  When in doubt, say N.
+
 config HOTPLUG_PCI_SHPC
 	bool "SHPC PCI Hotplug driver"
 	help
diff --git a/drivers/pci/hotplug/Makefile b/drivers/pci/hotplug/Makefile
index 240c99517d5e9..40aaf31fe3384 100644
--- a/drivers/pci/hotplug/Makefile
+++ b/drivers/pci/hotplug/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_HOTPLUG_PCI_RPA)		+= rpaphp.o
 obj-$(CONFIG_HOTPLUG_PCI_RPA_DLPAR)	+= rpadlpar_io.o
 obj-$(CONFIG_HOTPLUG_PCI_ACPI)		+= acpiphp.o
 obj-$(CONFIG_HOTPLUG_PCI_S390)		+= s390_pci_hpc.o
+obj-$(CONFIG_HOTPLUG_PCI_OCTEONEP)	+= octep_hp.o
 
 # acpiphp_ibm extends acpiphp, so should be linked afterwards.
 
diff --git a/drivers/pci/hotplug/octep_hp.c b/drivers/pci/hotplug/octep_hp.c
new file mode 100644
index 0000000000000..2bce7296c0504
--- /dev/null
+++ b/drivers/pci/hotplug/octep_hp.c
@@ -0,0 +1,427 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2024 Marvell. */
+
+#include <linux/cleanup.h>
+#include <linux/container_of.h>
+#include <linux/delay.h>
+#include <linux/dev_printk.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/workqueue.h>
+
+#define OCTEP_HP_INTR_OFFSET(x) (0x20400 + ((x) << 4))
+#define OCTEP_HP_INTR_VECTOR(x) (16 + (x))
+#define OCTEP_HP_DRV_NAME "octep_hp"
+
+/*
+ * Type of MSI-X interrupts. OCTEP_HP_INTR_VECTOR() and
+ * OCTEP_HP_INTR_OFFSET() generate the vector and offset for an interrupt
+ * type.
+ */
+enum octep_hp_intr_type {
+	OCTEP_HP_INTR_INVALID = -1,
+	OCTEP_HP_INTR_ENA = 0,
+	OCTEP_HP_INTR_DIS = 1,
+	OCTEP_HP_INTR_MAX = 2,
+};
+
+struct octep_hp_cmd {
+	struct list_head list;
+	enum octep_hp_intr_type intr_type;
+	u64 intr_val;
+};
+
+struct octep_hp_slot {
+	struct list_head list;
+	struct hotplug_slot slot;
+	u16 slot_number;
+	struct pci_dev *hp_pdev;
+	unsigned int hp_devfn;
+	struct octep_hp_controller *ctrl;
+};
+
+struct octep_hp_intr_info {
+	enum octep_hp_intr_type type;
+	int number;
+	char name[16];
+};
+
+struct octep_hp_controller {
+	void __iomem *base;
+	struct pci_dev *pdev;
+	struct octep_hp_intr_info intr[OCTEP_HP_INTR_MAX];
+	struct work_struct work;
+	struct list_head slot_list;
+	struct mutex slot_lock; /* Protects slot_list */
+	struct list_head hp_cmd_list;
+	spinlock_t hp_cmd_lock; /* Protects hp_cmd_list */
+};
+
+static void octep_hp_enable_pdev(struct octep_hp_controller *hp_ctrl,
+				 struct octep_hp_slot *hp_slot)
+{
+	guard(mutex)(&hp_ctrl->slot_lock);
+	if (hp_slot->hp_pdev) {
+		pci_dbg(hp_slot->hp_pdev, "Slot %s is already enabled\n",
+			hotplug_slot_name(&hp_slot->slot));
+		return;
+	}
+
+	/* Scan the device and add it to the bus */
+	hp_slot->hp_pdev = pci_scan_single_device(hp_ctrl->pdev->bus,
+						  hp_slot->hp_devfn);
+	pci_bus_assign_resources(hp_ctrl->pdev->bus);
+	pci_bus_add_device(hp_slot->hp_pdev);
+
+	dev_dbg(&hp_slot->hp_pdev->dev, "Enabled slot %s\n",
+		hotplug_slot_name(&hp_slot->slot));
+}
+
+static void octep_hp_disable_pdev(struct octep_hp_controller *hp_ctrl,
+				  struct octep_hp_slot *hp_slot)
+{
+	guard(mutex)(&hp_ctrl->slot_lock);
+	if (!hp_slot->hp_pdev) {
+		pci_dbg(hp_ctrl->pdev, "Slot %s is already disabled\n",
+			hotplug_slot_name(&hp_slot->slot));
+		return;
+	}
+
+	pci_dbg(hp_slot->hp_pdev, "Disabling slot %s\n",
+		hotplug_slot_name(&hp_slot->slot));
+
+	/* Remove the device from the bus */
+	pci_stop_and_remove_bus_device_locked(hp_slot->hp_pdev);
+	hp_slot->hp_pdev = NULL;
+}
+
+static int octep_hp_enable_slot(struct hotplug_slot *slot)
+{
+	struct octep_hp_slot *hp_slot =
+		container_of(slot, struct octep_hp_slot, slot);
+
+	octep_hp_enable_pdev(hp_slot->ctrl, hp_slot);
+	return 0;
+}
+
+static int octep_hp_disable_slot(struct hotplug_slot *slot)
+{
+	struct octep_hp_slot *hp_slot =
+		container_of(slot, struct octep_hp_slot, slot);
+
+	octep_hp_disable_pdev(hp_slot->ctrl, hp_slot);
+	return 0;
+}
+
+static struct hotplug_slot_ops octep_hp_slot_ops = {
+	.enable_slot = octep_hp_enable_slot,
+	.disable_slot = octep_hp_disable_slot,
+};
+
+#define SLOT_NAME_SIZE 16
+static struct octep_hp_slot *
+octep_hp_register_slot(struct octep_hp_controller *hp_ctrl,
+		       struct pci_dev *pdev, u16 slot_number)
+{
+	char slot_name[SLOT_NAME_SIZE];
+	struct octep_hp_slot *hp_slot;
+	int ret;
+
+	hp_slot = kzalloc(sizeof(*hp_slot), GFP_KERNEL);
+	if (!hp_slot)
+		return ERR_PTR(-ENOMEM);
+
+	hp_slot->ctrl = hp_ctrl;
+	hp_slot->hp_pdev = pdev;
+	hp_slot->hp_devfn = pdev->devfn;
+	hp_slot->slot_number = slot_number;
+	hp_slot->slot.ops = &octep_hp_slot_ops;
+
+	snprintf(slot_name, sizeof(slot_name), "octep_hp_%u", slot_number);
+	ret = pci_hp_register(&hp_slot->slot, hp_ctrl->pdev->bus,
+			      PCI_SLOT(pdev->devfn), slot_name);
+	if (ret) {
+		kfree(hp_slot);
+		return ERR_PTR(ret);
+	}
+
+	pci_info(pdev, "Registered slot %s for device %s\n",
+		 slot_name, pci_name(pdev));
+
+	list_add_tail(&hp_slot->list, &hp_ctrl->slot_list);
+	octep_hp_disable_pdev(hp_ctrl, hp_slot);
+
+	return hp_slot;
+}
+
+static void octep_hp_deregister_slot(void *data)
+{
+	struct octep_hp_slot *hp_slot = data;
+	struct octep_hp_controller *hp_ctrl = hp_slot->ctrl;
+
+	pci_hp_deregister(&hp_slot->slot);
+	octep_hp_enable_pdev(hp_ctrl, hp_slot);
+	list_del(&hp_slot->list);
+	kfree(hp_slot);
+}
+
+static const char *octep_hp_cmd_name(enum octep_hp_intr_type type)
+{
+	switch (type) {
+	case OCTEP_HP_INTR_ENA:
+		return "hotplug enable";
+	case OCTEP_HP_INTR_DIS:
+		return "hotplug disable";
+	default:
+		return "invalid";
+	}
+}
+
+static void octep_hp_cmd_handler(struct octep_hp_controller *hp_ctrl,
+				 struct octep_hp_cmd *hp_cmd)
+{
+	struct octep_hp_slot *hp_slot;
+
+	/*
+	 * Enable or disable the slots based on the slot mask.
+	 * intr_val is a bit mask where each bit represents a slot.
+	 */
+	list_for_each_entry(hp_slot, &hp_ctrl->slot_list, list) {
+		if (!(hp_cmd->intr_val & BIT(hp_slot->slot_number)))
+			continue;
+
+		pci_info(hp_ctrl->pdev, "Received %s command for slot %s\n",
+			 octep_hp_cmd_name(hp_cmd->intr_type),
+			 hotplug_slot_name(&hp_slot->slot));
+
+		switch (hp_cmd->intr_type) {
+		case OCTEP_HP_INTR_ENA:
+			octep_hp_enable_pdev(hp_ctrl, hp_slot);
+			break;
+		case OCTEP_HP_INTR_DIS:
+			octep_hp_disable_pdev(hp_ctrl, hp_slot);
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+static void octep_hp_work_handler(struct work_struct *work)
+{
+	struct octep_hp_controller *hp_ctrl;
+	struct octep_hp_cmd *hp_cmd;
+	unsigned long flags;
+
+	hp_ctrl = container_of(work, struct octep_hp_controller, work);
+
+	/* Process all the hotplug commands */
+	spin_lock_irqsave(&hp_ctrl->hp_cmd_lock, flags);
+	while (!list_empty(&hp_ctrl->hp_cmd_list)) {
+		hp_cmd = list_first_entry(&hp_ctrl->hp_cmd_list,
+					  struct octep_hp_cmd, list);
+		list_del(&hp_cmd->list);
+		spin_unlock_irqrestore(&hp_ctrl->hp_cmd_lock, flags);
+
+		octep_hp_cmd_handler(hp_ctrl, hp_cmd);
+		kfree(hp_cmd);
+
+		spin_lock_irqsave(&hp_ctrl->hp_cmd_lock, flags);
+	}
+	spin_unlock_irqrestore(&hp_ctrl->hp_cmd_lock, flags);
+}
+
+static enum octep_hp_intr_type octep_hp_intr_type(struct octep_hp_intr_info *intr,
+						  int irq)
+{
+	enum octep_hp_intr_type type;
+
+	for (type = OCTEP_HP_INTR_ENA; type < OCTEP_HP_INTR_MAX; type++) {
+		if (intr[type].number == irq)
+			return type;
+	}
+
+	return OCTEP_HP_INTR_INVALID;
+}
+
+static irqreturn_t octep_hp_intr_handler(int irq, void *data)
+{
+	struct octep_hp_controller *hp_ctrl = data;
+	struct pci_dev *pdev = hp_ctrl->pdev;
+	enum octep_hp_intr_type type;
+	struct octep_hp_cmd *hp_cmd;
+	u64 intr_val;
+
+	type = octep_hp_intr_type(hp_ctrl->intr, irq);
+	if (type == OCTEP_HP_INTR_INVALID) {
+		pci_err(pdev, "Invalid interrupt %d\n", irq);
+		return IRQ_HANDLED;
+	}
+
+	/* Read and clear the interrupt */
+	intr_val = readq(hp_ctrl->base + OCTEP_HP_INTR_OFFSET(type));
+	writeq(intr_val, hp_ctrl->base + OCTEP_HP_INTR_OFFSET(type));
+
+	hp_cmd = kzalloc(sizeof(*hp_cmd), GFP_ATOMIC);
+	if (!hp_cmd)
+		return IRQ_HANDLED;
+
+	hp_cmd->intr_val = intr_val;
+	hp_cmd->intr_type = type;
+
+	/* Add the command to the list and schedule the work */
+	spin_lock(&hp_ctrl->hp_cmd_lock);
+	list_add_tail(&hp_cmd->list, &hp_ctrl->hp_cmd_list);
+	spin_unlock(&hp_ctrl->hp_cmd_lock);
+	schedule_work(&hp_ctrl->work);
+
+	return IRQ_HANDLED;
+}
+
+static void octep_hp_irq_cleanup(void *data)
+{
+	struct octep_hp_controller *hp_ctrl = data;
+
+	pci_free_irq_vectors(hp_ctrl->pdev);
+	flush_work(&hp_ctrl->work);
+}
+
+static int octep_hp_request_irq(struct octep_hp_controller *hp_ctrl,
+				enum octep_hp_intr_type type)
+{
+	struct pci_dev *pdev = hp_ctrl->pdev;
+	struct octep_hp_intr_info *intr;
+	int irq;
+
+	irq = pci_irq_vector(pdev, OCTEP_HP_INTR_VECTOR(type));
+	if (irq < 0)
+		return irq;
+
+	intr = &hp_ctrl->intr[type];
+	intr->number = irq;
+	intr->type = type;
+	snprintf(intr->name, sizeof(intr->name), "octep_hp_%d", type);
+
+	return devm_request_irq(&pdev->dev, irq, octep_hp_intr_handler,
+				IRQF_SHARED, intr->name, hp_ctrl);
+}
+
+static int octep_hp_controller_setup(struct pci_dev *pdev,
+				     struct octep_hp_controller *hp_ctrl)
+{
+	struct device *dev = &pdev->dev;
+	enum octep_hp_intr_type type;
+	int ret;
+
+	ret = pcim_enable_device(pdev);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to enable PCI device\n");
+
+	hp_ctrl->base = pcim_iomap_region(pdev, 0, OCTEP_HP_DRV_NAME);
+	if (IS_ERR(hp_ctrl->base))
+		return dev_err_probe(dev, PTR_ERR(hp_ctrl->base),
+				     "Failed to map PCI device region\n");
+
+	pci_set_master(pdev);
+	pci_set_drvdata(pdev, hp_ctrl);
+
+	INIT_LIST_HEAD(&hp_ctrl->slot_list);
+	INIT_LIST_HEAD(&hp_ctrl->hp_cmd_list);
+	mutex_init(&hp_ctrl->slot_lock);
+	spin_lock_init(&hp_ctrl->hp_cmd_lock);
+	INIT_WORK(&hp_ctrl->work, octep_hp_work_handler);
+	hp_ctrl->pdev = pdev;
+
+	ret = pci_alloc_irq_vectors(pdev, 1,
+				    OCTEP_HP_INTR_VECTOR(OCTEP_HP_INTR_MAX),
+				    PCI_IRQ_MSIX);
+	if (ret < 0)
+		return dev_err_probe(dev, ret, "Failed to alloc MSI-X vectors\n");
+
+	ret = devm_add_action(&pdev->dev, octep_hp_irq_cleanup, hp_ctrl);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Failed to add IRQ cleanup action\n");
+
+	for (type = OCTEP_HP_INTR_ENA; type < OCTEP_HP_INTR_MAX; type++) {
+		ret = octep_hp_request_irq(hp_ctrl, type);
+		if (ret)
+			return dev_err_probe(dev, ret,
+					     "Failed to request IRQ for vector %d\n",
+					     OCTEP_HP_INTR_VECTOR(type));
+	}
+
+	return 0;
+}
+
+static int octep_hp_pci_probe(struct pci_dev *pdev,
+			      const struct pci_device_id *id)
+{
+	struct octep_hp_controller *hp_ctrl;
+	struct pci_dev *tmp_pdev, *next;
+	struct octep_hp_slot *hp_slot;
+	u16 slot_number = 0;
+	int ret;
+
+	hp_ctrl = devm_kzalloc(&pdev->dev, sizeof(*hp_ctrl), GFP_KERNEL);
+	if (!hp_ctrl)
+		return -ENOMEM;
+
+	ret = octep_hp_controller_setup(pdev, hp_ctrl);
+	if (ret)
+		return ret;
+
+	/*
+	 * Register all hotplug slots. Hotplug controller is the first function
+	 * of the PCI device. The hotplug slots are the remaining functions of
+	 * the PCI device. The hotplug slot functions are logically removed from
+	 * the bus during probing and are re-enabled by the driver when a
+	 * hotplug event is received.
+	 */
+	list_for_each_entry_safe(tmp_pdev, next, &pdev->bus->devices, bus_list) {
+		if (tmp_pdev == pdev)
+			continue;
+
+		hp_slot = octep_hp_register_slot(hp_ctrl, tmp_pdev, slot_number);
+		if (IS_ERR(hp_slot))
+			return dev_err_probe(&pdev->dev, PTR_ERR(hp_slot),
+					     "Failed to register hotplug slot %u\n",
+					     slot_number);
+
+		ret = devm_add_action(&pdev->dev, octep_hp_deregister_slot,
+				      hp_slot);
+		if (ret)
+			return dev_err_probe(&pdev->dev, ret,
+					     "Failed to add action for deregistering slot %u\n",
+					     slot_number);
+		slot_number++;
+	}
+
+	return 0;
+}
+
+#define PCI_DEVICE_ID_CAVIUM_OCTEP_HP_CTLR  0xa0e3
+static struct pci_device_id octep_hp_pci_map[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_CAVIUM_OCTEP_HP_CTLR) },
+	{ },
+};
+
+static struct pci_driver octep_hp = {
+	.name = OCTEP_HP_DRV_NAME,
+	.id_table = octep_hp_pci_map,
+	.probe = octep_hp_pci_probe,
+};
+
+module_pci_driver(octep_hp);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Marvell");
+MODULE_DESCRIPTION("Marvell OCTEON PCI Hotplug driver");

From 4752e8cde8344cb8673abdefe0dd74e9a2fe23ad Mon Sep 17 00:00:00 2001
From: Luo Yifan <luoyifan@cmss.chinamobile.com>
Date: Wed, 13 Nov 2024 10:31:37 +0800
Subject: [PATCH 1128/1530] tools/firewire: Fix several incorrect format
 specifiers

Make a minor change to eliminate static checker warnings. Fix several
incorrect format specifiers that misused signed and unsigned versions.

Signed-off-by: Luo Yifan <luoyifan@cmss.chinamobile.com>
Link: https://lore.kernel.org/r/20241113023137.291661-1-luoyifan@cmss.chinamobile.com
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
---
 tools/firewire/decode-fcp.c | 2 +-
 tools/firewire/nosy-dump.c  | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/firewire/decode-fcp.c b/tools/firewire/decode-fcp.c
index b67ebc88434d9..f115a3be8d1ef 100644
--- a/tools/firewire/decode-fcp.c
+++ b/tools/firewire/decode-fcp.c
@@ -160,7 +160,7 @@ decode_avc(struct link_transaction *t)
 		name = info->name;
 	}
 
-	printf("av/c %s, subunit_type=%s, subunit_id=%d, opcode=%s",
+	printf("av/c %s, subunit_type=%s, subunit_id=%u, opcode=%s",
 	    ctype_names[frame->ctype], subunit_type_names[frame->subunit_type],
 	    frame->subunit_id, name);
 
diff --git a/tools/firewire/nosy-dump.c b/tools/firewire/nosy-dump.c
index 156e0356e8147..9a906de3a9efa 100644
--- a/tools/firewire/nosy-dump.c
+++ b/tools/firewire/nosy-dump.c
@@ -771,7 +771,7 @@ print_packet(uint32_t *data, size_t length)
 				if (pp->phy_config.set_root)
 					printf(" set_root_id=%02x", pp->phy_config.root_id);
 				if (pp->phy_config.set_gap_count)
-					printf(" set_gap_count=%d", pp->phy_config.gap_count);
+					printf(" set_gap_count=%u", pp->phy_config.gap_count);
 			}
 			break;
 
@@ -781,13 +781,13 @@ print_packet(uint32_t *data, size_t length)
 
 		case PHY_PACKET_SELF_ID:
 			if (pp->self_id.extended) {
-				printf("extended self id: phy_id=%02x, seq=%d",
+				printf("extended self id: phy_id=%02x, seq=%u",
 				       pp->ext_self_id.phy_id, pp->ext_self_id.sequence);
 			} else {
 				static const char * const speed_names[] = {
 					"S100", "S200", "S400", "BETA"
 				};
-				printf("self id: phy_id=%02x, link %s, gap_count=%d, speed=%s%s%s",
+				printf("self id: phy_id=%02x, link %s, gap_count=%u speed=%s%s%s",
 				       pp->self_id.phy_id,
 				       (pp->self_id.link_active ? "active" : "not active"),
 				       pp->self_id.gap_count,

From e311b04db66aaed1819bdd479d42c4f338f105b9 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Tue, 12 Nov 2024 12:56:45 +0000
Subject: [PATCH 1129/1530] soundwire: Update the includes on the sdw.h header

There are quite a few things used in the sdw.h header that it relies on
the consumer to include. If something is used directly in the header it
should be included by the header. Update the includes to cover the
missing items, or add forward declarations for things that are only used
as pointers. Whilst making the change also alphabetise the list of
includes.

Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20241112125646.590240-1-ckeepax@opensource.cirrus.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 73f655334fe9c..1fd4b126287f2 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -4,12 +4,19 @@
 #ifndef __SOUNDWIRE_H
 #define __SOUNDWIRE_H
 
+#include <linux/bitfield.h>
 #include <linux/bug.h>
-#include <linux/lockdep_types.h>
+#include <linux/completion.h>
+#include <linux/device.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
+#include <linux/lockdep_types.h>
 #include <linux/mod_devicetable.h>
-#include <linux/bitfield.h>
+#include <linux/mutex.h>
+#include <linux/types.h>
+
+struct dentry;
+struct fwnode_handle;
 
 struct sdw_bus;
 struct sdw_slave;

From dd690b31de0ed46adc5856698880560b900386ba Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Tue, 12 Nov 2024 12:56:46 +0000
Subject: [PATCH 1130/1530] soundwire: Minor formatting fixups in sdw.h header

Fixup some minor formatting and whitespace in the sdw.h header file.

Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20241112125646.590240-2-ckeepax@opensource.cirrus.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 40 +++++++++++++++--------------------
 1 file changed, 17 insertions(+), 23 deletions(-)

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 1fd4b126287f2..784656f740f67 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -616,7 +616,6 @@ struct sdw_slave_ops {
 	int (*clk_stop)(struct sdw_slave *slave,
 			enum sdw_clk_stop_mode mode,
 			enum sdw_clk_stop_type type);
-
 };
 
 /**
@@ -690,8 +689,7 @@ struct sdw_master_device {
 	container_of(d, struct sdw_master_device, dev)
 
 struct sdw_driver {
-	int (*probe)(struct sdw_slave *sdw,
-			const struct sdw_device_id *id);
+	int (*probe)(struct sdw_slave *sdw, const struct sdw_device_id *id);
 	int (*remove)(struct sdw_slave *sdw);
 	void (*shutdown)(struct sdw_slave *sdw);
 
@@ -710,7 +708,7 @@ struct sdw_driver {
 	SDW_SLAVE_ENTRY_EXT((_mfg_id), (_part_id), 0, 0, (_drv_data))
 
 int sdw_handle_slave_status(struct sdw_bus *bus,
-			enum sdw_slave_status status[]);
+			    enum sdw_slave_status status[]);
 
 /*
  * SDW master structures and APIs
@@ -792,15 +790,14 @@ struct sdw_enable_ch {
  */
 struct sdw_master_port_ops {
 	int (*dpn_set_port_params)(struct sdw_bus *bus,
-			struct sdw_port_params *port_params,
-			unsigned int bank);
+				   struct sdw_port_params *port_params,
+				   unsigned int bank);
 	int (*dpn_set_port_transport_params)(struct sdw_bus *bus,
-			struct sdw_transport_params *transport_params,
-			enum sdw_reg_bank bank);
-	int (*dpn_port_prep)(struct sdw_bus *bus,
-			struct sdw_prepare_ch *prepare_ch);
+					     struct sdw_transport_params *transport_params,
+					     enum sdw_reg_bank bank);
+	int (*dpn_port_prep)(struct sdw_bus *bus, struct sdw_prepare_ch *prepare_ch);
 	int (*dpn_port_enable_ch)(struct sdw_bus *bus,
-			struct sdw_enable_ch *enable_ch, unsigned int bank);
+				  struct sdw_enable_ch *enable_ch, unsigned int bank);
 };
 
 struct sdw_msg;
@@ -835,14 +832,11 @@ struct sdw_defer {
  */
 struct sdw_master_ops {
 	int (*read_prop)(struct sdw_bus *bus);
-	u64 (*override_adr)
-			(struct sdw_bus *bus, u64 addr);
-	enum sdw_command_response (*xfer_msg)
-			(struct sdw_bus *bus, struct sdw_msg *msg);
-	enum sdw_command_response (*xfer_msg_defer)
-			(struct sdw_bus *bus);
+	u64 (*override_adr)(struct sdw_bus *bus, u64 addr);
+	enum sdw_command_response (*xfer_msg)(struct sdw_bus *bus, struct sdw_msg *msg);
+	enum sdw_command_response (*xfer_msg_defer)(struct sdw_bus *bus);
 	int (*set_bus_conf)(struct sdw_bus *bus,
-			struct sdw_bus_params *params);
+			    struct sdw_bus_params *params);
 	int (*pre_bank_switch)(struct sdw_bus *bus);
 	int (*post_bank_switch)(struct sdw_bus *bus);
 	u32 (*read_ping_status)(struct sdw_bus *bus);
@@ -1019,12 +1013,12 @@ void sdw_release_stream(struct sdw_stream_runtime *stream);
 int sdw_compute_params(struct sdw_bus *bus);
 
 int sdw_stream_add_master(struct sdw_bus *bus,
-		struct sdw_stream_config *stream_config,
-		const struct sdw_port_config *port_config,
-		unsigned int num_ports,
-		struct sdw_stream_runtime *stream);
+			  struct sdw_stream_config *stream_config,
+			  const struct sdw_port_config *port_config,
+			  unsigned int num_ports,
+			  struct sdw_stream_runtime *stream);
 int sdw_stream_remove_master(struct sdw_bus *bus,
-		struct sdw_stream_runtime *stream);
+			     struct sdw_stream_runtime *stream);
 int sdw_startup_stream(void *sdw_substream);
 int sdw_prepare_stream(struct sdw_stream_runtime *stream);
 int sdw_enable_stream(struct sdw_stream_runtime *stream);

From f89d17ae2ac42931be2a0153fecbf8533280c927 Mon Sep 17 00:00:00 2001
From: Zhen Lei <thunder.leizhen@huawei.com>
Date: Sat, 26 Oct 2024 11:56:34 +0800
Subject: [PATCH 1131/1530] fbdev: sh7760fb: Fix a possible memory leak in
 sh7760fb_alloc_mem()

When information such as info->screen_base is not ready, calling
sh7760fb_free_mem() does not release memory correctly. Call
dma_free_coherent() instead.

Fixes: 4a25e41831ee ("video: sh7760fb: SH7760/SH7763 LCDC framebuffer driver")
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/sh7760fb.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/video/fbdev/sh7760fb.c b/drivers/video/fbdev/sh7760fb.c
index 3d2a27fefc874..130adef2e4686 100644
--- a/drivers/video/fbdev/sh7760fb.c
+++ b/drivers/video/fbdev/sh7760fb.c
@@ -409,12 +409,11 @@ static int sh7760fb_alloc_mem(struct fb_info *info)
 		vram = PAGE_SIZE;
 
 	fbmem = dma_alloc_coherent(info->device, vram, &par->fbdma, GFP_KERNEL);
-
 	if (!fbmem)
 		return -ENOMEM;
 
 	if ((par->fbdma & SH7760FB_DMA_MASK) != SH7760FB_DMA_MASK) {
-		sh7760fb_free_mem(info);
+		dma_free_coherent(info->device, vram, fbmem, par->fbdma);
 		dev_err(info->device, "kernel gave me memory at 0x%08lx, which is"
 			"unusable for the LCDC\n", (unsigned long)par->fbdma);
 		return -ENOMEM;

From 8d7493133bfd89322349be3daaf39a256e4354ac Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sat, 26 Oct 2024 23:01:33 +0100
Subject: [PATCH 1132/1530] fbdev: omapfb: Remove some deadcode

commit f76ee892a99e ("omapfb: copy omapdss & displays for omapfb")
took a copy of the omapdrm code into omapfb, however at that point
a couple of functions were already unused at that point.

Remove dispc_mgr_get_clock_div() and dispc_enable_fifomerge() from
the omapfb copy.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/omap2/omapfb/dss/dispc.c | 27 --------------------
 drivers/video/fbdev/omap2/omapfb/dss/dss.h   |  3 ---
 2 files changed, 30 deletions(-)

diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
index 5832485ab998c..c3329c8b4c169 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
@@ -1230,17 +1230,6 @@ void dispc_ovl_set_fifo_threshold(enum omap_plane plane, u32 low, u32 high)
 		dispc_write_reg(DISPC_OVL_PRELOAD(plane), min(high, 0xfffu));
 }
 
-void dispc_enable_fifomerge(bool enable)
-{
-	if (!dss_has_feature(FEAT_FIFO_MERGE)) {
-		WARN_ON(enable);
-		return;
-	}
-
-	DSSDBG("FIFO merge %s\n", enable ? "enabled" : "disabled");
-	REG_FLD_MOD(DISPC_CONFIG, enable ? 1 : 0, 14, 14);
-}
-
 void dispc_ovl_compute_fifo_thresholds(enum omap_plane plane,
 		u32 *fifo_low, u32 *fifo_high, bool use_fifomerge,
 		bool manual_update)
@@ -3656,22 +3645,6 @@ void dispc_mgr_set_clock_div(enum omap_channel channel,
 	dispc_mgr_set_lcd_divisor(channel, cinfo->lck_div, cinfo->pck_div);
 }
 
-int dispc_mgr_get_clock_div(enum omap_channel channel,
-		struct dispc_clock_info *cinfo)
-{
-	unsigned long fck;
-
-	fck = dispc_fclk_rate();
-
-	cinfo->lck_div = REG_GET(DISPC_DIVISORo(channel), 23, 16);
-	cinfo->pck_div = REG_GET(DISPC_DIVISORo(channel), 7, 0);
-
-	cinfo->lck = fck / cinfo->lck_div;
-	cinfo->pck = cinfo->lck / cinfo->pck_div;
-
-	return 0;
-}
-
 u32 dispc_read_irqstatus(void)
 {
 	return dispc_read_reg(DISPC_IRQSTATUS);
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss.h b/drivers/video/fbdev/omap2/omapfb/dss/dss.h
index 21cfcbf74a6d9..a33a43f26829f 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dss.h
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dss.h
@@ -366,7 +366,6 @@ void dispc_disable_sidle(void);
 
 void dispc_lcd_enable_signal(bool enable);
 void dispc_pck_free_enable(bool enable);
-void dispc_enable_fifomerge(bool enable);
 void dispc_enable_gamma_table(bool enable);
 
 typedef bool (*dispc_div_calc_func)(int lckd, int pckd, unsigned long lck,
@@ -388,8 +387,6 @@ void dispc_ovl_compute_fifo_thresholds(enum omap_plane plane,
 
 void dispc_mgr_set_clock_div(enum omap_channel channel,
 		const struct dispc_clock_info *cinfo);
-int dispc_mgr_get_clock_div(enum omap_channel channel,
-		struct dispc_clock_info *cinfo);
 void dispc_set_tv_pclk(unsigned long pclk);
 
 u32 dispc_read_irqstatus(void);

From 22e87bf3f77c18f5982c19ffe2732ef0c7a25f16 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Thu, 14 Nov 2024 11:53:17 +0200
Subject: [PATCH 1133/1530] vfio/mlx5: Fix an unwind issue in
 mlx5vf_add_migration_pages()

Fix an unwind issue in mlx5vf_add_migration_pages().

If a set of pages is allocated but fails to be added to the SG table,
they need to be freed to prevent a memory leak.

Any pages successfully added to the SG table will be freed as part of
mlx5vf_free_data_buffer().

Fixes: 6fadb021266d ("vfio/mlx5: Implement vfio_pci driver for mlx5 devices")
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20241114095318.16556-2-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/mlx5/cmd.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c
index 41a4b0cf42975..7527e277c8989 100644
--- a/drivers/vfio/pci/mlx5/cmd.c
+++ b/drivers/vfio/pci/mlx5/cmd.c
@@ -423,6 +423,7 @@ static int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
 	unsigned long filled;
 	unsigned int to_fill;
 	int ret;
+	int i;
 
 	to_fill = min_t(unsigned int, npages, PAGE_SIZE / sizeof(*page_list));
 	page_list = kvzalloc(to_fill * sizeof(*page_list), GFP_KERNEL_ACCOUNT);
@@ -443,7 +444,7 @@ static int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
 			GFP_KERNEL_ACCOUNT);
 
 		if (ret)
-			goto err;
+			goto err_append;
 		buf->allocated_length += filled * PAGE_SIZE;
 		/* clean input for another bulk allocation */
 		memset(page_list, 0, filled * sizeof(*page_list));
@@ -454,6 +455,9 @@ static int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
 	kvfree(page_list);
 	return 0;
 
+err_append:
+	for (i = filled - 1; i >= 0; i--)
+		__free_page(page_list[i]);
 err:
 	kvfree(page_list);
 	return ret;

From cb04444c243c001fc27f275e84792ff1c2b96867 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Thu, 14 Nov 2024 11:53:18 +0200
Subject: [PATCH 1134/1530] vfio/mlx5: Fix unwind flows in
 mlx5vf_pci_save/resume_device_data()

Fix unwind flows in mlx5vf_pci_save_device_data() and
mlx5vf_pci_resume_device_data() to avoid freeing the migf pointer at the
'end' label, as this will be handled by fput(migf->filp) through
mlx5vf_release_file().

To ensure mlx5vf_release_file() functions correctly, move the
initialization of migf fields (such as migf->lock) to occur before any
potential unwind flow, as these fields may be accessed within
mlx5vf_release_file().

Fixes: 9945a67ea4b3 ("vfio/mlx5: Refactor PD usage")
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20241114095318.16556-3-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/mlx5/main.c | 35 +++++++++++++++++------------------
 1 file changed, 17 insertions(+), 18 deletions(-)

diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
index 242c23eef452e..8833e60d42f56 100644
--- a/drivers/vfio/pci/mlx5/main.c
+++ b/drivers/vfio/pci/mlx5/main.c
@@ -640,14 +640,11 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev, bool track)
 					O_RDONLY);
 	if (IS_ERR(migf->filp)) {
 		ret = PTR_ERR(migf->filp);
-		goto end;
+		kfree(migf);
+		return ERR_PTR(ret);
 	}
 
 	migf->mvdev = mvdev;
-	ret = mlx5vf_cmd_alloc_pd(migf);
-	if (ret)
-		goto out_free;
-
 	stream_open(migf->filp->f_inode, migf->filp);
 	mutex_init(&migf->lock);
 	init_waitqueue_head(&migf->poll_wait);
@@ -663,6 +660,11 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev, bool track)
 	INIT_LIST_HEAD(&migf->buf_list);
 	INIT_LIST_HEAD(&migf->avail_list);
 	spin_lock_init(&migf->list_lock);
+
+	ret = mlx5vf_cmd_alloc_pd(migf);
+	if (ret)
+		goto out;
+
 	ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &length, &full_size, 0);
 	if (ret)
 		goto out_pd;
@@ -692,10 +694,8 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev, bool track)
 	mlx5vf_free_data_buffer(buf);
 out_pd:
 	mlx5fv_cmd_clean_migf_resources(migf);
-out_free:
+out:
 	fput(migf->filp);
-end:
-	kfree(migf);
 	return ERR_PTR(ret);
 }
 
@@ -1016,13 +1016,19 @@ mlx5vf_pci_resume_device_data(struct mlx5vf_pci_core_device *mvdev)
 					O_WRONLY);
 	if (IS_ERR(migf->filp)) {
 		ret = PTR_ERR(migf->filp);
-		goto end;
+		kfree(migf);
+		return ERR_PTR(ret);
 	}
 
+	stream_open(migf->filp->f_inode, migf->filp);
+	mutex_init(&migf->lock);
+	INIT_LIST_HEAD(&migf->buf_list);
+	INIT_LIST_HEAD(&migf->avail_list);
+	spin_lock_init(&migf->list_lock);
 	migf->mvdev = mvdev;
 	ret = mlx5vf_cmd_alloc_pd(migf);
 	if (ret)
-		goto out_free;
+		goto out;
 
 	buf = mlx5vf_alloc_data_buffer(migf, 0, DMA_TO_DEVICE);
 	if (IS_ERR(buf)) {
@@ -1041,20 +1047,13 @@ mlx5vf_pci_resume_device_data(struct mlx5vf_pci_core_device *mvdev)
 	migf->buf_header[0] = buf;
 	migf->load_state = MLX5_VF_LOAD_STATE_READ_HEADER;
 
-	stream_open(migf->filp->f_inode, migf->filp);
-	mutex_init(&migf->lock);
-	INIT_LIST_HEAD(&migf->buf_list);
-	INIT_LIST_HEAD(&migf->avail_list);
-	spin_lock_init(&migf->list_lock);
 	return migf;
 out_buf:
 	mlx5vf_free_data_buffer(migf->buf[0]);
 out_pd:
 	mlx5vf_cmd_dealloc_pd(migf);
-out_free:
+out:
 	fput(migf->filp);
-end:
-	kfree(migf);
 	return ERR_PTR(ret);
 }
 

From fe4f9b4124967ffb75d66994520831231b779550 Mon Sep 17 00:00:00 2001
From: Howard Chu <howardchu95@gmail.com>
Date: Tue, 29 Oct 2024 22:24:31 -0700
Subject: [PATCH 1135/1530] perf trace: Fix tracing itself, creating feedback
 loops
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There exists a pids_filtered map in augmented_raw_syscalls.bpf.c that
ceases to provide functionality after the BPF skeleton migration done
in:

5e6da6be3082f77b ("perf trace: Migrate BPF augmentation to use a skeleton")

Before the migration, pid_filtered map works, courtesy of Arnaldo
Carvalho de Melo <acme@kernel.org>:

  ⬢ [acme@toolbox perf-tools]$ git log --oneline -5
  6f769c3458b6cf2d (HEAD) perf tests trace+probe_vfs_getname.sh: Accept quotes surrounding the filename
  7777ac3dfe29f55d perf test trace+probe_vfs_getname.sh: Remove stray \ before /
  33d9c5062113a4bd perf script python: Add stub for PMU symbol to the python binding
  e59fea47f83e8a9a perf symbols: Fix DSO kernel load and symbol process to correctly map DSO to its long_name, type and adjust_symbols
  878460e8d0ff84a0 perf build: Remove -Wno-unused-but-set-variable from the flex flags when building with clang < 13.0.0

  root@x1:/home/acme/git/perf-tools# perf trace -e /tmp/augmented_raw_syscalls.o -e write* --max-events=30  &
  [1] 180632
  root@x1:/home/acme/git/perf-tools#      0.000 ( 0.051 ms): NetworkManager/1127 write(fd: 3, buf: 0x7ffeb508ef70, count: 8)                           = 8
       0.115 ( 0.010 ms): NetworkManager/1127 write(fd: 3, buf: 0x7ffeb508ef70, count: 8)                           = 8
       0.916 ( 0.068 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 246)                         = 246
       1.699 ( 0.047 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 121)                         = 121
       2.167 ( 0.041 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 121)                         = 121
       2.739 ( 0.042 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 121)                         = 121
       3.138 ( 0.027 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 121)                         = 121
       3.477 ( 0.027 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 121)                         = 121
       3.738 ( 0.023 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 121)                         = 121
       3.946 ( 0.024 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 121)                         = 121
       4.195 ( 0.024 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 121)                         = 121
       4.212 ( 0.026 ms): NetworkManager/1127 write(fd: 3, buf: 0x7ffeb508ef70, count: 8)                           = 8
       4.285 ( 0.006 ms): NetworkManager/1127 write(fd: 3, buf: 0x7ffeb508ef70, count: 8)                           = 8
       4.445 ( 0.018 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 260)                         = 260
       4.508 ( 0.009 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 124)                         = 124
       4.592 ( 0.010 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 116)                         = 116
       4.666 ( 0.009 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 130)                         = 130
       4.715 ( 0.010 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 95)                          = 95
       4.765 ( 0.007 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 102)                         = 102
       4.815 ( 0.009 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 79)                          = 79
       4.890 ( 0.008 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 57)                          = 57
       4.937 ( 0.007 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 89)                          = 89
       5.009 ( 0.010 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 112)                         = 112
       5.059 ( 0.010 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 112)                         = 112
       5.116 ( 0.007 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 79)                          = 79
       5.152 ( 0.009 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 33)                          = 33
       5.215 ( 0.008 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 37)                          = 37
       5.293 ( 0.010 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 128)                         = 128
       5.339 ( 0.009 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 89)                          = 89
       5.384 ( 0.008 ms): sudo/156867 write(fd: 8, buf: 0x55cb4cd2f650, count: 100)                         = 100

  [1]+  Done                    perf trace -e /tmp/augmented_raw_syscalls.o -e write* --max-events=30
  root@x1:/home/acme/git/perf-tools#

No events for the 'perf trace' (pid 180632), i.e. no feedback loop.

If we leave it running:

  root@x1:/home/acme/git/perf-tools# perf trace -e /tmp/augmented_raw_syscalls.o -e landlock_add_rule &
  [1] 181068
  root@x1:/home/acme/git/perf-tools#

  And then look at what maps it sets up:

  root@x1:/home/acme/git/perf-tools# bpftool map | grep pids_filtered -A3
  1190: hash  name pids_filtered  flags 0x0
          key 4B  value 1B  max_entries 64  memlock 7264B
          btf_id 1613
          pids perf(181068)
  root@x1:/home/acme/git/perf-tools#

  And ask for dumping its contents:

  We see that we are _also_ setting it to filter those:

  root@x1:/home/acme/git/perf-tools# bpftool map dump id 1190
  [{
          "key": 181068,
          "value": 1
      },{
          "key": 156801,
          "value": 1
      }
  ]

Now testing the migration commit:

  perf $ git log
  commit 5e6da6be3082f77be06894a1a94d52a90b4007dc (HEAD)
  Author: Ian Rogers <irogers@google.com>
  Date:   Thu Aug 10 11:48:51 2023 -0700

      perf trace: Migrate BPF augmentation to use a skeleton

  perf $ ./perf trace -e write --max-events=10 & echo #!
  [1] 1808653
  perf $
       0.000 ( 0.010 ms): :1808671/1808671 write(fd: 1, buf: 0x6003f5b26fc0, count: 11) = 11
       0.162 (         ): perf/1808653 write(fd: 2, buf: 0x7fffc2174e50, count: 11)     ...
       0.174 (         ): perf/1808653 write(fd: 2, buf: 0x74ce21804563, count: 1)      ...
       0.184 (         ): perf/1808653 write(fd: 2, buf: 0x57b936589052, count: 5)

The feedback loop is there.

Keep it running, look into the bpf map:

  perf $ bpftool map | grep pids_filtered
  10675: hash  name pids_filtered  flags 0x0

  perf $ bpftool map dump id 10675
  []

The map is empty.

Now, this commit:

  64917f4df048a064 ("perf trace: Use heuristic when deciding if a syscall tracepoint "const char *" field is really a string")

Temporarily fixed the feedback loop for perf trace -e write, that's
because before using the heuristic, write is hooked to sys_enter_openat:

  perf $ git log
  commit 83a0943b1870944612a8aa0049f910826ebfd4f7 (HEAD)
  Author: Arnaldo Carvalho de Melo <acme@redhat.com>
  Date:   Thu Aug 17 12:11:51 2023 -0300

      perf trace: Use the augmented_raw_syscall BPF skel only for tracing syscalls

  perf $ ./perf trace -e write --max-events=10 -v 2>&1 | grep Reusing
  Reusing "openat" BPF sys_enter augmenter for "write"

And after the heuristic fix, it's unaugmented:

  perf $ git log
  commit 64917f4df048a0649ea7901c2321f020e71e6f24 (HEAD)
  Author: Arnaldo Carvalho de Melo <acme@redhat.com>
  Date:   Thu Aug 17 15:14:21 2023 -0300

      perf trace: Use heuristic when deciding if a syscall tracepoint "const char *" field is really a string

  perf $ ./perf trace -e write --max-events=10 -v 2>&1 | grep Reusing
  perf $

After using the heuristic, write is hooked to syscall_unaugmented, which
returns 1.

  SEC("tp/raw_syscalls/sys_enter")
  int syscall_unaugmented(struct syscall_enter_args *args)
  {
  	return 1;
  }

If the BPF program returns 1, the tracepoint filter will filter it
(since the tracepoint filter for perf is correctly set), but before the
heuristic, when it was hooked to a sys_enter_openat(), which is a BPF
program that calls bpf_perf_event_output() and writes to the buffer, it
didn't get filtered, thus creating feedback loop. So switching write to
unaugmented accidentally fixed the problem.

But some syscalls are not so lucky, for example newfstatat:
perf $ ./perf trace -e newfstatat --max-events=100 & echo #!
[1] 2166948

   457.718 (         ): perf/2166948 newfstatat(dfd: CWD, filename: "/proc/self/ns/mnt", statbuf: 0x7fff0132a9f0) ...
   457.749 (         ): perf/2166948 newfstatat(dfd: CWD, filename: "/proc/2166950/ns/mnt", statbuf: 0x7fff0132aa80) ...
   457.962 (         ): perf/2166948 newfstatat(dfd: CWD, filename: "/proc/self/ns/mnt", statbuf: 0x7fff0132a9f0) ...

Currently, write is augmented by the new BTF general augmenter (which
calls bpf_perf_event_output()). The problem, which luckily got fixed,
resurfaced, and that’s how it was discovered.

Fixes: 5e6da6be3082f77b ("perf trace: Migrate BPF augmentation to use a skeleton")
Signed-off-by: Howard Chu <howardchu95@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241030052431.2220130-1-howardchu95@gmail.com
[ Check if trace->skel is non-NULL, as it is only initialized if trace->trace_syscalls is set ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 156c3e8291790..14794725669d4 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -4326,6 +4326,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 					sizeof(__u32), BPF_ANY);
 		}
 	}
+
+	if (trace->skel)
+		trace->filter_pids.map = trace->skel->maps.pids_filtered;
 #endif
 	err = trace__set_filter_pids(trace);
 	if (err < 0)

From e7c70ee7c9aa7420d22b47d8951f4b5fef4554ea Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Thu, 7 Nov 2024 23:52:13 +0900
Subject: [PATCH 1136/1530] perf probe: Fix error message for failing to find
 line range

With --lines option, if perf-probe fails to find the specified line, it
warns as "Debuginfo analysis failed." but this misleads user as the
debuginfo is broken.

Fix this message to "Specified source line(LINESPEC) is not found." so
that user can understand the error correctly.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://lore.kernel.org/r/173099113381.2431889.16263147678401426107.stgit@mhiramat.roam.corp.google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/probe-event.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index a580aa2cd5120..9e94d66d63331 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1039,6 +1039,17 @@ static int _show_one_line(FILE *fp, int l, bool skip, bool show_num)
 	return rv;
 }
 
+static int sprint_line_description(char *sbuf, size_t size, struct line_range *lr)
+{
+	if (!lr->function)
+		return snprintf(sbuf, size, "file: %s, line: %d", lr->file, lr->start);
+
+	if (lr->file)
+		return snprintf(sbuf, size, "function: %s, file:%s, line: %d", lr->function, lr->file, lr->start);
+
+	return snprintf(sbuf, size, "function: %s, line:%d", lr->function, lr->start);
+}
+
 #define show_one_line_with_num(f,l)	_show_one_line(f,l,false,true)
 #define show_one_line(f,l)		_show_one_line(f,l,false,false)
 #define skip_one_line(f,l)		_show_one_line(f,l,true,false)
@@ -1071,6 +1082,8 @@ static int __show_line_range(struct line_range *lr, const char *module,
 		ret = get_alternative_line_range(dinfo, lr, module, user);
 		if (!ret)
 			ret = debuginfo__find_line_range(dinfo, lr);
+		else /* Ignore error, we just failed to find it. */
+			ret = -ENOENT;
 	}
 	if (dinfo->build_id) {
 		build_id__init(&bid, dinfo->build_id, BUILD_ID_SIZE);
@@ -1078,7 +1091,8 @@ static int __show_line_range(struct line_range *lr, const char *module,
 	}
 	debuginfo__delete(dinfo);
 	if (ret == 0 || ret == -ENOENT) {
-		pr_warning("Specified source line is not found.\n");
+		sprint_line_description(sbuf, sizeof(sbuf), lr);
+		pr_warning("Specified source line(%s) is not found.\n", sbuf);
 		return -ENOENT;
 	} else if (ret < 0) {
 		pr_warning("Debuginfo analysis failed.\n");

From 47fa0f99a9aa962bac8e6da09cb104e8da94e4df Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Thu, 7 Nov 2024 23:52:22 +0900
Subject: [PATCH 1137/1530] perf probe: Fix to ignore escaped characters in
 --lines option

Use strbprk_esc() and strdup_esc() to ignore escaped characters in
--lines option. This has been done for other options, but only --lines
option doesn't.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://lore.kernel.org/r/173099114272.2431889.4820591557298941207.stgit@mhiramat.roam.corp.google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/probe-event.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 9e94d66d63331..b9119391d3739 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1372,7 +1372,7 @@ int parse_line_range_desc(const char *arg, struct line_range *lr)
 	lr->start = 0;
 	lr->end = INT_MAX;
 
-	range = strchr(name, ':');
+	range = strpbrk_esc(name, ":");
 	if (range) {
 		*range++ = '\0';
 
@@ -1413,7 +1413,7 @@ int parse_line_range_desc(const char *arg, struct line_range *lr)
 		}
 	}
 
-	file = strchr(name, '@');
+	file = strpbrk_esc(name, "@");
 	if (file) {
 		*file = '\0';
 		lr->file = strdup(++file);
@@ -1422,7 +1422,7 @@ int parse_line_range_desc(const char *arg, struct line_range *lr)
 			goto err;
 		}
 		lr->function = name;
-	} else if (strchr(name, '/') || strchr(name, '.'))
+	} else if (strpbrk_esc(name, "/."))
 		lr->file = name;
 	else if (is_c_func_name(name))/* We reuse it for checking funcname */
 		lr->function = name;

From b9e577225c16fae9f5e4d3d642153c64b538c44e Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Thu, 7 Nov 2024 23:52:31 +0900
Subject: [PATCH 1138/1530] perf probe: Accept FUNC@* to specify function name
 explicitly

In Golang, the function name will have the '.', and 'perf probe'
misinterprets it as a file name.

To mitigate this situation, introduce `function@*` so that user can
explicitly specify that it is a function name.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://lore.kernel.org/r/173099115149.2431889.13682110856853358354.stgit@mhiramat.roam.corp.google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/probe-event.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index b9119391d3739..c287e89dabcb1 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1360,6 +1360,8 @@ static bool is_c_func_name(const char *name)
  *
  *         SRC[:SLN[+NUM|-ELN]]
  *         FNC[@SRC][:SLN[+NUM|-ELN]]
+ *
+ * FNC@SRC accepts `FNC@*` which forcibly specify FNC as function name.
  */
 int parse_line_range_desc(const char *arg, struct line_range *lr)
 {
@@ -1415,13 +1417,21 @@ int parse_line_range_desc(const char *arg, struct line_range *lr)
 
 	file = strpbrk_esc(name, "@");
 	if (file) {
-		*file = '\0';
-		lr->file = strdup(++file);
-		if (lr->file == NULL) {
-			err = -ENOMEM;
+		*file++ = '\0';
+		if (strcmp(file, "*")) {
+			lr->file = strdup_esc(file);
+			if (lr->file == NULL) {
+				err = -ENOMEM;
+				goto err;
+			}
+		}
+		if (*name != '\0')
+			lr->function = name;
+		if (!lr->function && !lr->file) {
+			semantic_error("Only '@*' is not allowed.\n");
+			err = -EINVAL;
 			goto err;
 		}
-		lr->function = name;
 	} else if (strpbrk_esc(name, "/."))
 		lr->file = name;
 	else if (is_c_func_name(name))/* We reuse it for checking funcname */
@@ -1622,6 +1632,8 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 				semantic_error("SRC@SRC is not allowed.\n");
 				return -EINVAL;
 			}
+			if (!strcmp(arg, "*"))
+				break;
 			pp->file = strdup_esc(arg);
 			if (pp->file == NULL)
 				return -ENOMEM;

From 313026f3ced102a9ef044fbde4a806554ccfe959 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Thu, 7 Nov 2024 23:52:40 +0900
Subject: [PATCH 1139/1530] perf string: Add strpbrk_esq() and strdup_esq() for
 escape and quote

strpbrk_esq() and strdup_esq() are new variants for strpbrk() and
strdup() which handles escaped characters and quoted strings.

- strpbrk_esq() searches specified set of characters but ignores the
  escaped characters and quoted strings.
  e.g. strpbrk_esq("'quote\d' \queue quiz", "qd") returns "quiz".

- strdup_esq() duplicates string but removes backslash and quotes which
  is used for quotation. It also keeps the string (including backslash)
  in the quoted part.
  e.g. strdup_esq("'quote\d' \queue quiz") returns "quote\d queue quiz".

The (single, double) quotes in the quoted part should be escaped by
backslash. In this case, strdup_esq() removes that backslash.
The same quotes must be paired. If you use double quotation, you need
to use the double quotation to close the quoted part.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://lore.kernel.org/r/173099116045.2431889.15772916605719019533.stgit@mhiramat.roam.corp.google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/string.c  | 100 ++++++++++++++++++++++++++++++++++++++
 tools/perf/util/string2.h |   2 +
 2 files changed, 102 insertions(+)

diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 116a642ad99d1..308fc7ec88ccd 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -263,6 +263,34 @@ char *strpbrk_esc(char *str, const char *stopset)
 	return ptr;
 }
 
+/* Like strpbrk_esc(), but not break if it is quoted with single/double quotes */
+char *strpbrk_esq(char *str, const char *stopset)
+{
+	char *_stopset = NULL;
+	char *ptr;
+	const char *squote = "'";
+	const char *dquote = "\"";
+
+	if (asprintf(&_stopset, "%s%c%c", stopset, *squote, *dquote) < 0)
+		return NULL;
+
+	do {
+		ptr = strpbrk_esc(str, _stopset);
+		if (!ptr)
+			break;
+		if (*ptr == *squote)
+			ptr = strpbrk_esc(ptr + 1, squote);
+		else if (*ptr == *dquote)
+			ptr = strpbrk_esc(ptr + 1, dquote);
+		else
+			break;
+		str = ptr + 1;
+	} while (ptr);
+
+	free(_stopset);
+	return ptr;
+}
+
 /* Like strdup, but do not copy a single backslash */
 char *strdup_esc(const char *str)
 {
@@ -293,6 +321,78 @@ char *strdup_esc(const char *str)
 	return ret;
 }
 
+/* Remove backslash right before quote and return next quote address. */
+static char *remove_consumed_esc(char *str, int len, int quote)
+{
+	char *ptr = str, *end = str + len;
+
+	while (*ptr != quote && ptr < end) {
+		if (*ptr == '\\' && *(ptr + 1) == quote) {
+			memmove(ptr, ptr + 1, end - (ptr + 1));
+			/* now *ptr is `quote`. */
+			end--;
+		}
+		ptr++;
+	}
+
+	return *ptr == quote ? ptr : NULL;
+}
+
+/*
+ * Like strdup_esc, but keep quoted string as it is (and single backslash
+ * before quote is removed). If there is no closed quote, return NULL.
+ */
+char *strdup_esq(const char *str)
+{
+	char *d, *ret;
+
+	/* If there is no quote, return normal strdup_esc() */
+	d = strpbrk_esc((char *)str, "\"'");
+	if (!d)
+		return strdup_esc(str);
+
+	ret = strdup(str);
+	if (!ret)
+		return NULL;
+
+	d = ret;
+	do {
+		d = strpbrk(d, "\\\"\'");
+		if (!d)
+			break;
+
+		if (*d == '"' || *d == '\'') {
+			/* This is non-escaped quote */
+			int quote = *d;
+			int len = strlen(d + 1) + 1;
+
+			/*
+			 * Remove the start quote and remove consumed escape (backslash
+			 * before quote) and remove the end quote. If there is no end
+			 * quote, it is the input error.
+			 */
+			memmove(d, d + 1, len);
+			d = remove_consumed_esc(d, len, quote);
+			if (!d)
+				goto error;
+			memmove(d, d + 1, strlen(d + 1) + 1);
+		}
+		if (*d == '\\') {
+			memmove(d, d + 1, strlen(d + 1) + 1);
+			if (*d == '\\') {
+				/* double backslash -- keep the second one. */
+				d++;
+			}
+		}
+	} while (*d != '\0');
+
+	return ret;
+
+error:
+	free(ret);
+	return NULL;
+}
+
 unsigned int hex(char c)
 {
 	if (c >= '0' && c <= '9')
diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h
index 52cb8ba057c77..4c8bff47cfd30 100644
--- a/tools/perf/util/string2.h
+++ b/tools/perf/util/string2.h
@@ -37,6 +37,8 @@ char *asprintf__tp_filter_pids(size_t npids, pid_t *pids);
 
 char *strpbrk_esc(char *str, const char *stopset);
 char *strdup_esc(const char *str);
+char *strpbrk_esq(char *str, const char *stopset);
+char *strdup_esq(const char *str);
 
 unsigned int hex(char c);
 char *strreplace_chars(char needle, const char *haystack, const char *replace);

From 080e47b2a2377f9cfad7bc7fa074e9819eafa394 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Thu, 7 Nov 2024 23:52:49 +0900
Subject: [PATCH 1140/1530] perf probe: Introduce quotation marks support

In non-C languages, it is possible to have ':' in the function names.

It is possible to escape it with backslashes, but if there are too many
backslashes, it is annoying.

This introduce quotation marks (`"` or `'`) support.

For example, without quotes, we have to pass it as below

  $ perf probe -x cro3 -L "cro3\:\:cmd\:\:servo\:\:run_show"
  <run_show@/work/cro3/src/cmd/servo.rs:0>
        0  fn run_show(args: &ArgsShow) -> Result<()> {
        1      let list = ServoList::discover()?;
        2      let s = list.find_by_serial(&args.servo)?;
        3      if args.json {
        4          println!("{s}");

With quotes, we can more naturally write the function name as below;

  $ perf probe -x cro3 -L \"cro3::cmd::servo::run_show\"
  <run_show@/work/cro3/src/cmd/servo.rs:0>
        0  fn run_show(args: &ArgsShow) -> Result<()> {
        1      let list = ServoList::discover()?;
        2      let s = list.find_by_serial(&args.servo)?;
        3      if args.json {
        4          println!("{s}");

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://lore.kernel.org/r/173099116941.2431889.11609129616090100386.stgit@mhiramat.roam.corp.google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/probe-event.c | 75 +++++++++++++++++++----------------
 1 file changed, 41 insertions(+), 34 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index c287e89dabcb1..1d51846978717 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1079,6 +1079,7 @@ static int __show_line_range(struct line_range *lr, const char *module,
 
 	ret = debuginfo__find_line_range(dinfo, lr);
 	if (!ret) {	/* Not found, retry with an alternative */
+		pr_debug2("Failed to find line range in debuginfo. Fallback to alternative\n");
 		ret = get_alternative_line_range(dinfo, lr, module, user);
 		if (!ret)
 			ret = debuginfo__find_line_range(dinfo, lr);
@@ -1362,30 +1363,37 @@ static bool is_c_func_name(const char *name)
  *         FNC[@SRC][:SLN[+NUM|-ELN]]
  *
  * FNC@SRC accepts `FNC@*` which forcibly specify FNC as function name.
+ * SRC and FUNC can be quoted by double/single quotes.
  */
 int parse_line_range_desc(const char *arg, struct line_range *lr)
 {
-	char *range, *file, *name = strdup(arg);
+	char *buf = strdup(arg);
+	char *p;
 	int err;
 
-	if (!name)
+	if (!buf)
 		return -ENOMEM;
 
 	lr->start = 0;
 	lr->end = INT_MAX;
 
-	range = strpbrk_esc(name, ":");
-	if (range) {
-		*range++ = '\0';
+	p = strpbrk_esq(buf, ":");
+	if (p) {
+		if (p == buf) {
+			semantic_error("No file/function name in '%s'.\n", p);
+			err = -EINVAL;
+			goto err;
+		}
+		*(p++) = '\0';
 
-		err = parse_line_num(&range, &lr->start, "start line");
+		err = parse_line_num(&p, &lr->start, "start line");
 		if (err)
 			goto err;
 
-		if (*range == '+' || *range == '-') {
-			const char c = *range++;
+		if (*p == '+' || *p == '-') {
+			const char c = *(p++);
 
-			err = parse_line_num(&range, &lr->end, "end line");
+			err = parse_line_num(&p, &lr->end, "end line");
 			if (err)
 				goto err;
 
@@ -1409,42 +1417,41 @@ int parse_line_range_desc(const char *arg, struct line_range *lr)
 				       " than end line.\n");
 			goto err;
 		}
-		if (*range != '\0') {
-			semantic_error("Tailing with invalid str '%s'.\n", range);
+		if (*p != '\0') {
+			semantic_error("Tailing with invalid str '%s'.\n", p);
 			goto err;
 		}
 	}
 
-	file = strpbrk_esc(name, "@");
-	if (file) {
-		*file++ = '\0';
-		if (strcmp(file, "*")) {
-			lr->file = strdup_esc(file);
+	p = strpbrk_esq(buf, "@");
+	if (p) {
+		*p++ = '\0';
+		if (strcmp(p, "*")) {
+			lr->file = strdup_esq(p);
 			if (lr->file == NULL) {
 				err = -ENOMEM;
 				goto err;
 			}
 		}
-		if (*name != '\0')
-			lr->function = name;
+		if (*buf != '\0')
+			lr->function = strdup_esq(buf);
 		if (!lr->function && !lr->file) {
 			semantic_error("Only '@*' is not allowed.\n");
 			err = -EINVAL;
 			goto err;
 		}
-	} else if (strpbrk_esc(name, "/."))
-		lr->file = name;
-	else if (is_c_func_name(name))/* We reuse it for checking funcname */
-		lr->function = name;
+	} else if (strpbrk_esq(buf, "/."))
+		lr->file = strdup_esq(buf);
+	else if (is_c_func_name(buf))/* We reuse it for checking funcname */
+		lr->function = strdup_esq(buf);
 	else {	/* Invalid name */
-		semantic_error("'%s' is not a valid function name.\n", name);
+		semantic_error("'%s' is not a valid function name.\n", buf);
 		err = -EINVAL;
 		goto err;
 	}
 
-	return 0;
 err:
-	free(name);
+	free(buf);
 	return err;
 }
 
@@ -1452,19 +1459,19 @@ static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
 {
 	char *ptr;
 
-	ptr = strpbrk_esc(*arg, ":");
+	ptr = strpbrk_esq(*arg, ":");
 	if (ptr) {
 		*ptr = '\0';
 		if (!pev->sdt && !is_c_func_name(*arg))
 			goto ng_name;
-		pev->group = strdup_esc(*arg);
+		pev->group = strdup_esq(*arg);
 		if (!pev->group)
 			return -ENOMEM;
 		*arg = ptr + 1;
 	} else
 		pev->group = NULL;
 
-	pev->event = strdup_esc(*arg);
+	pev->event = strdup_esq(*arg);
 	if (pev->event == NULL)
 		return -ENOMEM;
 
@@ -1503,7 +1510,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 			arg++;
 	}
 
-	ptr = strpbrk_esc(arg, ";=@+%");
+	ptr = strpbrk_esq(arg, ";=@+%");
 	if (pev->sdt) {
 		if (ptr) {
 			if (*ptr != '@') {
@@ -1517,7 +1524,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 				pev->target = build_id_cache__origname(tmp);
 				free(tmp);
 			} else
-				pev->target = strdup_esc(ptr + 1);
+				pev->target = strdup_esq(ptr + 1);
 			if (!pev->target)
 				return -ENOMEM;
 			*ptr = '\0';
@@ -1558,7 +1565,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 			file_spec = true;
 	}
 
-	ptr = strpbrk_esc(arg, ";:+@%");
+	ptr = strpbrk_esq(arg, ";:+@%");
 	if (ptr) {
 		nc = *ptr;
 		*ptr++ = '\0';
@@ -1567,7 +1574,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 	if (arg[0] == '\0')
 		tmp = NULL;
 	else {
-		tmp = strdup_esc(arg);
+		tmp = strdup_esq(arg);
 		if (tmp == NULL)
 			return -ENOMEM;
 	}
@@ -1605,7 +1612,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 				return -ENOMEM;
 			break;
 		}
-		ptr = strpbrk_esc(arg, ";:+@%");
+		ptr = strpbrk_esq(arg, ";:+@%");
 		if (ptr) {
 			nc = *ptr;
 			*ptr++ = '\0';
@@ -1634,7 +1641,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 			}
 			if (!strcmp(arg, "*"))
 				break;
-			pp->file = strdup_esc(arg);
+			pp->file = strdup_esq(arg);
 			if (pp->file == NULL)
 				return -ENOMEM;
 			break;

From 3fd7c36973a250e17a4ee305a31545a9426021f4 Mon Sep 17 00:00:00 2001
From: Benjamin Peterson <benjamin@engflow.com>
Date: Thu, 7 Nov 2024 23:21:26 +0000
Subject: [PATCH 1141/1530] perf trace: Do not lose last events in a race

If a perf trace event selector specifies a maximum number of events to output
(i.e., "/nr=N/" syntax), the event printing handler, trace__event_handler,
disables the event selector after the maximum number events are
printed.

Furthermore, trace__event_handler checked if the event selector was
disabled before doing any work. This avoided exceeding the maximum
number of events to print if more events were in the buffer before the
selector was disabled.

However, the event selector can be disabled for reasons other than
exceeding the maximum number of events. In particular, when the traced
subprocess exits, the main loop disables all event selectors. This meant
the last events of a traced subprocess might be lost to the printing
handler's short-circuiting logic.

This nondeterministic problem could be seen by running the following many times:

  $ perf trace -e syscalls:sys_enter_exit_group true

trace__event_handler should simply check for exceeding the maximum number of
events to print rather than the state of the event selector.

Fixes: a9c5e6c1e9bff42c ("perf trace: Introduce per-event maximum number of events property")
Signed-off-by: Benjamin Peterson <benjamin@engflow.com>
Tested-by: Howard Chu <howardchu95@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241107232128.108981-1-benjamin@engflow.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 14794725669d4..ca5c3f5d6c389 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3096,13 +3096,8 @@ static int trace__event_handler(struct trace *trace, struct evsel *evsel,
 {
 	struct thread *thread;
 	int callchain_ret = 0;
-	/*
-	 * Check if we called perf_evsel__disable(evsel) due to, for instance,
-	 * this event's max_events having been hit and this is an entry coming
-	 * from the ring buffer that we should discard, since the max events
-	 * have already been considered/printed.
-	 */
-	if (evsel->disabled)
+
+	if (evsel->nr_events_printed >= evsel->max_events)
 		return 0;
 
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);

From 1302e352b26f34991b619b5d0b621b76d20a3883 Mon Sep 17 00:00:00 2001
From: Benjamin Peterson <benjamin@engflow.com>
Date: Thu, 7 Nov 2024 23:21:27 +0000
Subject: [PATCH 1142/1530] perf trace: Avoid garbage when not printing a
 syscall's arguments

syscall__scnprintf_args may not place anything in the output buffer
(e.g., because the arguments are all zero). If that happened in
trace__fprintf_sys_enter, its fprintf would receive an unitialized
buffer leading to garbage output.

Fix the problem by passing the (possibly zero) bounds of the argument
buffer to the output fprintf.

Fixes: a98392bb1e169a04 ("perf trace: Use beautifiers on syscalls:sys_enter_ handlers")
Signed-off-by: Benjamin Peterson <benjamin@engflow.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Howard Chu <howardchu95@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241107232128.108981-2-benjamin@engflow.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index ca5c3f5d6c389..6a1a128fe6450 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2702,6 +2702,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct evsel *evsel,
 	char msg[1024];
 	void *args, *augmented_args = NULL;
 	int augmented_args_size;
+	size_t printed = 0;
 
 	if (sc == NULL)
 		return -1;
@@ -2717,8 +2718,8 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct evsel *evsel,
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
 	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls_args_size);
-	syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
-	fprintf(trace->output, "%s", msg);
+	printed += syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
+	fprintf(trace->output, "%.*s", (int)printed, msg);
 	err = 0;
 out_put:
 	thread__put(thread);

From f72bcb92e9a1402baedad45dd34abb686ae1e8cb Mon Sep 17 00:00:00 2001
From: Benjamin Peterson <benjamin@engflow.com>
Date: Thu, 7 Nov 2024 23:21:28 +0000
Subject: [PATCH 1143/1530] perf tests: Add test for trace output loss

Add a test that checks that trace output is not lost to races. This is
accomplished by tracing the exit_group syscall of "true" multiple times and
checking for correct output.

Signed-off-by: Benjamin Peterson <benjamin@engflow.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Howard Chu <howardchu95@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241107232128.108981-3-benjamin@engflow.com
[ Addressed two ShellCheck warnings ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/trace_exit_race.sh | 31 +++++++++++++++++++++++
 1 file changed, 31 insertions(+)
 create mode 100755 tools/perf/tests/shell/trace_exit_race.sh

diff --git a/tools/perf/tests/shell/trace_exit_race.sh b/tools/perf/tests/shell/trace_exit_race.sh
new file mode 100755
index 0000000000000..3cf2d71a5c3b9
--- /dev/null
+++ b/tools/perf/tests/shell/trace_exit_race.sh
@@ -0,0 +1,31 @@
+#!/bin/sh
+# perf trace exit race
+# SPDX-License-Identifier: GPL-2.0
+
+# Check that the last events of a perf trace'd subprocess are not
+# lost. Specifically, trace the exiting syscall of "true" 10 times and ensure
+# the output contains 10 correct lines.
+
+# shellcheck source=lib/probe.sh
+. "$(dirname $0)"/lib/probe.sh
+
+skip_if_no_perf_trace || exit 2
+
+trace_shutdown_race() {
+	for _ in $(seq 10); do
+		perf trace -e syscalls:sys_enter_exit_group true 2>>$file
+	done
+	[ "$(grep -c -E ' +[0-9]+\.[0-9]+ +true/[0-9]+ syscalls:sys_enter_exit_group\(\)$' $file)" = "10" ]
+}
+
+
+file=$(mktemp /tmp/temporary_file.XXXXX)
+
+# Do not use whatever ~/.perfconfig file, it may change the output
+# via trace.{show_timestamp,show_prefix,etc}
+export PERF_CONFIG=/dev/null
+
+trace_shutdown_race
+err=$?
+rm -f ${file}
+exit $err

From a5f040cfcfdd8cd10591d50fb6280dffe07c7a8e Mon Sep 17 00:00:00 2001
From: Maud Spierings <maud_spierings@hotmail.com>
Date: Sun, 10 Nov 2024 19:05:02 +0100
Subject: [PATCH 1144/1530] Input: fix the input_event struct documentation

Fix the datatype of the value field of the input_event struct which is
signed instead of unsigned.

Signed-off-by: Maud Spierings <maud_spierings@hotmail.com>
Link: https://lore.kernel.org/r/20241110-fix_input_doc-v1-1-745d5f908e61@hotmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 Documentation/input/input.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/input/input.rst b/Documentation/input/input.rst
index 2c67fa904adcf..d9a6de87d02de 100644
--- a/Documentation/input/input.rst
+++ b/Documentation/input/input.rst
@@ -264,7 +264,7 @@ events on a read. Their layout is::
 	    struct timeval time;
 	    unsigned short type;
 	    unsigned short code;
-	    unsigned int value;
+	    int value;
     };
 
 ``time`` is the timestamp, it returns the time at which the event happened.

From 470a271627e8c4e2b5357fd0f5759cf6e33cc145 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Mon, 11 Nov 2024 08:09:55 -0700
Subject: [PATCH 1145/1530] Input: ads7846 - increase xfer array size in
 'struct ser_req'

Clang warns (or errors with CONFIG_WERROR=y, trimmed for brevity):

  drivers/input/touchscreen/ads7846.c:412:2: error: array index 6 is past the end of the array (that has type 'struct spi_transfer[6]') [-Werror,-Warray-bounds]
    412 |         req->xfer[6].tx_buf = &req->scratch;
        |         ^         ~
  ...
  drivers/input/touchscreen/ads7846.c:416:2: error: array index 7 is past the end of the array (that has type 'struct spi_transfer[6]') [-Werror,-Warray-bounds]
    416 |         req->xfer[7].rx_buf = &req->scratch;
        |         ^         ~
  drivers/input/touchscreen/ads7846.c:334:2: note: array 'xfer' declared here
    334 |         struct spi_transfer     xfer[6];
        |         ^

Increase the size of xfer in 'struct ser_req' to ensure that there is
enough space for all necessary members and there are no out of bounds
accesses, clearing up the warning.

Fixes: 781a07da9bb9 ("Input: ads7846 - add dummy command register clearing cycle")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Marek Vasut <marex@denx.de>
Link: https://lore.kernel.org/r/20241111-input-ads7846-increase-xfer-array-size-v1-1-06cd92e9f20f@kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/ads7846.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c
index f7bc0a3e56d86..7b3711a3597c8 100644
--- a/drivers/input/touchscreen/ads7846.c
+++ b/drivers/input/touchscreen/ads7846.c
@@ -331,7 +331,7 @@ struct ser_req {
 	u8			ref_off;
 	u16			scratch;
 	struct spi_message	msg;
-	struct spi_transfer	xfer[6];
+	struct spi_transfer	xfer[8];
 	/*
 	 * DMA (thus cache coherency maintenance) requires the
 	 * transfer buffers to live in their own cache lines.

From 2c259a91d8d23a8266092b0dd51b8092877717a4 Mon Sep 17 00:00:00 2001
From: Etienne Buira <etienne.buira@free.fr>
Date: Fri, 8 Nov 2024 17:45:32 +0100
Subject: [PATCH 1146/1530] gdb: lx-symbols: do not error out on monolithic
 build

This avoids spurious message:
(gdb) lx-symbols
loading vmlinux
No source file named kernel/module/main.c.

Link: https://lkml.kernel.org/r/Zy5ALByQtpO-ddh4@Z926fQmE5jqhFMgp6
Signed-off-by: Etienne Buira <etienne.buira@free.fr>
Cc: Andrew Ballance <andrewjballance@gmail.com>
Cc: Kieran Bingham <kbingham@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 scripts/gdb/linux/modules.py | 3 +++
 scripts/gdb/linux/symbols.py | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/scripts/gdb/linux/modules.py b/scripts/gdb/linux/modules.py
index 298dfcc25eaea..fa15f872ddbe8 100644
--- a/scripts/gdb/linux/modules.py
+++ b/scripts/gdb/linux/modules.py
@@ -19,6 +19,9 @@
 module_type = utils.CachedType("struct module")
 
 
+def has_modules():
+    return utils.gdb_eval_or_none("modules") is not None
+
 def module_list():
     global module_type
     modules = utils.gdb_eval_or_none("modules")
diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py
index e8316beb17a71..f6c1b063775a7 100644
--- a/scripts/gdb/linux/symbols.py
+++ b/scripts/gdb/linux/symbols.py
@@ -178,6 +178,9 @@ def invoke(self, arg, from_tty):
 
         self.load_all_symbols()
 
+        if not modules.has_modules():
+            return
+
         if hasattr(gdb, 'Breakpoint'):
             if self.breakpoint is not None:
                 self.breakpoint.delete()

From 4a530a7c751d27f9dbd70b7fc45670cd11713b13 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 11 Oct 2024 11:00:21 +0200
Subject: [PATCH 1147/1530] fs: prepare for "explicit connectable" file handles

We would like to use the high 16bit of the handle_type field to encode
file handle traits, such as "connectable".

In preparation for this change, make sure that filesystems do not return
a handle_type value with upper bits set and that the open_by_handle_at(2)
syscall rejects these handle types.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20241011090023.655623-2-amir73il@gmail.com
Fixes: 570df4e9c23f ("ceph: snapshot nfs re-export")
Acked-by:
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/exportfs/expfs.c      | 17 +++++++++++++++--
 fs/fhandle.c             |  7 +++++++
 include/linux/exportfs.h | 11 +++++++++++
 3 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 4f2dd4ab44864..0c899cfba578a 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -382,14 +382,24 @@ int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
 			     int *max_len, struct inode *parent, int flags)
 {
 	const struct export_operations *nop = inode->i_sb->s_export_op;
+	enum fid_type type;
 
 	if (!exportfs_can_encode_fh(nop, flags))
 		return -EOPNOTSUPP;
 
 	if (!nop && (flags & EXPORT_FH_FID))
-		return exportfs_encode_ino64_fid(inode, fid, max_len);
+		type = exportfs_encode_ino64_fid(inode, fid, max_len);
+	else
+		type = nop->encode_fh(inode, fid->raw, max_len, parent);
+
+	if (type > 0 && FILEID_USER_FLAGS(type)) {
+		pr_warn_once("%s: unexpected fh type value 0x%x from fstype %s.\n",
+			     __func__, type, inode->i_sb->s_type->name);
+		return -EINVAL;
+	}
+
+	return type;
 
-	return nop->encode_fh(inode, fid->raw, max_len, parent);
 }
 EXPORT_SYMBOL_GPL(exportfs_encode_inode_fh);
 
@@ -436,6 +446,9 @@ exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len,
 	char nbuf[NAME_MAX+1];
 	int err;
 
+	if (fileid_type < 0 || FILEID_USER_FLAGS(fileid_type))
+		return ERR_PTR(-EINVAL);
+
 	/*
 	 * Try to get any dentry for the given file handle from the filesystem.
 	 */
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 82df28d45cd70..218511f38cbb1 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -307,6 +307,11 @@ static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
 		retval = -EINVAL;
 		goto out_path;
 	}
+	if (f_handle.handle_type < 0 ||
+	    FILEID_USER_FLAGS(f_handle.handle_type) & ~FILEID_VALID_USER_FLAGS) {
+		retval = -EINVAL;
+		goto out_path;
+	}
 	handle = kmalloc(struct_size(handle, f_handle, f_handle.handle_bytes),
 			 GFP_KERNEL);
 	if (!handle) {
@@ -322,6 +327,8 @@ static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
 		goto out_handle;
 	}
 
+	/* Filesystem code should not be exposed to user flags */
+	handle->handle_type &= ~FILEID_USER_FLAGS_MASK;
 	retval = do_handle_to_path(handle, path, &ctx);
 
 out_handle:
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 893a1d21dc1c4..5e14d4500a75c 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -160,6 +160,17 @@ struct fid {
 #define EXPORT_FH_FID		0x2 /* File handle may be non-decodeable */
 #define EXPORT_FH_DIR_ONLY	0x4 /* Only decode file handle for a directory */
 
+/*
+ * Filesystems use only lower 8 bits of file_handle type for fid_type.
+ * name_to_handle_at() uses upper 16 bits of type as user flags to be
+ * interpreted by open_by_handle_at().
+ */
+#define FILEID_USER_FLAGS_MASK	0xffff0000
+#define FILEID_USER_FLAGS(type) ((type) & FILEID_USER_FLAGS_MASK)
+
+/* Flags supported in encoded handle_type that is exported to user */
+#define FILEID_VALID_USER_FLAGS	(0)
+
 /**
  * struct export_operations - for nfsd to communicate with file systems
  * @encode_fh:      encode a file handle fragment from a dentry

From c374196b2b9f4b803fccd59ed82f0712041e21e1 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 11 Oct 2024 11:00:22 +0200
Subject: [PATCH 1148/1530] fs: name_to_handle_at() support for "explicit
 connectable" file handles

nfsd encodes "connectable" file handles for the subtree_check feature,
which can be resolved to an open file with a connected path.
So far, userspace nfs server could not make use of this functionality.

Introduce a new flag AT_HANDLE_CONNECTABLE to name_to_handle_at(2).
When used, the encoded file handle is "explicitly connectable".

The "explicitly connectable" file handle sets bits in the high 16bit of
the handle_type field, so open_by_handle_at(2) will know that it needs
to open a file with a connected path.

old kernels will now recognize the handle_type with high bits set,
so "explicitly connectable" file handles cannot be decoded by
open_by_handle_at(2) on old kernels.

The flag AT_HANDLE_CONNECTABLE is not allowed together with either
AT_HANDLE_FID or AT_EMPTY_PATH.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20241011090023.655623-3-amir73il@gmail.com
Fixes: 570df4e9c23f ("ceph: snapshot nfs re-export")
Acked-by:
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fhandle.c               | 48 ++++++++++++++++++++++++++++++++++----
 include/linux/exportfs.h   |  2 ++
 include/uapi/linux/fcntl.h |  1 +
 3 files changed, 46 insertions(+), 5 deletions(-)

diff --git a/fs/fhandle.c b/fs/fhandle.c
index 218511f38cbb1..8339a10410254 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -31,6 +31,14 @@ static long do_sys_name_to_handle(const struct path *path,
 	if (!exportfs_can_encode_fh(path->dentry->d_sb->s_export_op, fh_flags))
 		return -EOPNOTSUPP;
 
+	/*
+	 * A request to encode a connectable handle for a disconnected dentry
+	 * is unexpected since AT_EMPTY_PATH is not allowed.
+	 */
+	if (fh_flags & EXPORT_FH_CONNECTABLE &&
+	    WARN_ON(path->dentry->d_flags & DCACHE_DISCONNECTED))
+		return -EINVAL;
+
 	if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle)))
 		return -EFAULT;
 
@@ -45,7 +53,7 @@ static long do_sys_name_to_handle(const struct path *path,
 	/* convert handle size to multiple of sizeof(u32) */
 	handle_dwords = f_handle.handle_bytes >> 2;
 
-	/* we ask for a non connectable maybe decodeable file handle */
+	/* Encode a possibly decodeable/connectable file handle */
 	retval = exportfs_encode_fh(path->dentry,
 				    (struct fid *)handle->f_handle,
 				    &handle_dwords, fh_flags);
@@ -67,8 +75,23 @@ static long do_sys_name_to_handle(const struct path *path,
 		 * non variable part of the file_handle
 		 */
 		handle_bytes = 0;
-	} else
+	} else {
+		/*
+		 * When asked to encode a connectable file handle, encode this
+		 * property in the file handle itself, so that we later know
+		 * how to decode it.
+		 * For sanity, also encode in the file handle if the encoded
+		 * object is a directory and verify this during decode, because
+		 * decoding directory file handles is quite different than
+		 * decoding connectable non-directory file handles.
+		 */
+		if (fh_flags & EXPORT_FH_CONNECTABLE) {
+			handle->handle_type |= FILEID_IS_CONNECTABLE;
+			if (d_is_dir(path->dentry))
+				fh_flags |= FILEID_IS_DIR;
+		}
 		retval = 0;
+	}
 	/* copy the mount id */
 	if (unique_mntid) {
 		if (put_user(real_mount(path->mnt)->mnt_id_unique,
@@ -109,15 +132,30 @@ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
 {
 	struct path path;
 	int lookup_flags;
-	int fh_flags;
+	int fh_flags = 0;
 	int err;
 
 	if (flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH | AT_HANDLE_FID |
-		     AT_HANDLE_MNT_ID_UNIQUE))
+		     AT_HANDLE_MNT_ID_UNIQUE | AT_HANDLE_CONNECTABLE))
+		return -EINVAL;
+
+	/*
+	 * AT_HANDLE_FID means there is no intention to decode file handle
+	 * AT_HANDLE_CONNECTABLE means there is an intention to decode a
+	 * connected fd (with known path), so these flags are conflicting.
+	 * AT_EMPTY_PATH could be used along with a dfd that refers to a
+	 * disconnected non-directory, which cannot be used to encode a
+	 * connectable file handle, because its parent is unknown.
+	 */
+	if (flag & AT_HANDLE_CONNECTABLE &&
+	    flag & (AT_HANDLE_FID | AT_EMPTY_PATH))
 		return -EINVAL;
+	else if (flag & AT_HANDLE_FID)
+		fh_flags |= EXPORT_FH_FID;
+	else if (flag & AT_HANDLE_CONNECTABLE)
+		fh_flags |= EXPORT_FH_CONNECTABLE;
 
 	lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0;
-	fh_flags = (flag & AT_HANDLE_FID) ? EXPORT_FH_FID : 0;
 	if (flag & AT_EMPTY_PATH)
 		lookup_flags |= LOOKUP_EMPTY;
 	err = user_path_at(dfd, name, lookup_flags, &path);
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 5e14d4500a75c..4ee42b2cf4ab2 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -169,6 +169,8 @@ struct fid {
 #define FILEID_USER_FLAGS(type) ((type) & FILEID_USER_FLAGS_MASK)
 
 /* Flags supported in encoded handle_type that is exported to user */
+#define FILEID_IS_CONNECTABLE	0x10000
+#define FILEID_IS_DIR		0x20000
 #define FILEID_VALID_USER_FLAGS	(0)
 
 /**
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index 87e2dec79fea4..56ff2100e0216 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -153,6 +153,7 @@
 					   object identity and may not be
 					   usable with open_by_handle_at(2). */
 #define AT_HANDLE_MNT_ID_UNIQUE	0x001	/* Return the u64 unique mount ID. */
+#define AT_HANDLE_CONNECTABLE	0x002	/* Request a connectable file handle */
 
 #if defined(__KERNEL__)
 #define AT_GETATTR_NOSEC	0x80000000

From a20853ab8296d4a8754482cb5e9adde8ab426a25 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 11 Oct 2024 11:00:23 +0200
Subject: [PATCH 1149/1530] fs: open_by_handle_at() support for decoding
 "explicit connectable" file handles

Teach open_by_handle_at(2) about the type format of "explicit connectable"
file handles that were created using the AT_HANDLE_CONNECTABLE flag to
name_to_handle_at(2).

When decoding an "explicit connectable" file handles, name_to_handle_at(2)
should fail if it cannot open a "connected" fd with known path, which is
accessible (to capable user) from mount fd path.

Note that this does not check if the path is accessible to the calling
user, just that it is accessible wrt the mount namesapce, so if there
is no "connected" alias, or if parts of the path are hidden in the
mount namespace, open_by_handle_at(2) will return -ESTALE.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20241011090023.655623-4-amir73il@gmail.com
Fixes: 570df4e9c23f ("ceph: snapshot nfs re-export")
Acked-by:
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fhandle.c             | 20 +++++++++++++++++++-
 include/linux/exportfs.h |  2 +-
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/fs/fhandle.c b/fs/fhandle.c
index 8339a10410254..75cfd190cd69c 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -246,7 +246,13 @@ static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
 
 	if (!(ctx->flags & HANDLE_CHECK_SUBTREE) || d == root)
 		retval = 1;
-	WARN_ON_ONCE(d != root && d != root->d_sb->s_root);
+	/*
+	 * exportfs_decode_fh_raw() does not call acceptable() callback with
+	 * a disconnected directory dentry, so we should have reached either
+	 * mount fd directory or sb root.
+	 */
+	if (ctx->fh_flags & EXPORT_FH_DIR_ONLY)
+		WARN_ON_ONCE(d != root && d != root->d_sb->s_root);
 	dput(d);
 	return retval;
 }
@@ -350,6 +356,7 @@ static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
 		retval = -EINVAL;
 		goto out_path;
 	}
+
 	handle = kmalloc(struct_size(handle, f_handle, f_handle.handle_bytes),
 			 GFP_KERNEL);
 	if (!handle) {
@@ -365,6 +372,17 @@ static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
 		goto out_handle;
 	}
 
+	/*
+	 * If handle was encoded with AT_HANDLE_CONNECTABLE, verify that we
+	 * are decoding an fd with connected path, which is accessible from
+	 * the mount fd path.
+	 */
+	if (f_handle.handle_type & FILEID_IS_CONNECTABLE) {
+		ctx.fh_flags |= EXPORT_FH_CONNECTABLE;
+		ctx.flags |= HANDLE_CHECK_SUBTREE;
+	}
+	if (f_handle.handle_type & FILEID_IS_DIR)
+		ctx.fh_flags |= EXPORT_FH_DIR_ONLY;
 	/* Filesystem code should not be exposed to user flags */
 	handle->handle_type &= ~FILEID_USER_FLAGS_MASK;
 	retval = do_handle_to_path(handle, path, &ctx);
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 4ee42b2cf4ab2..fcab6ab1d38a5 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -171,7 +171,7 @@ struct fid {
 /* Flags supported in encoded handle_type that is exported to user */
 #define FILEID_IS_CONNECTABLE	0x10000
 #define FILEID_IS_DIR		0x20000
-#define FILEID_VALID_USER_FLAGS	(0)
+#define FILEID_VALID_USER_FLAGS	(FILEID_IS_CONNECTABLE | FILEID_IS_DIR)
 
 /**
  * struct export_operations - for nfsd to communicate with file systems

From 56bd06c2640b78cef985159e03f42bf3897013ff Mon Sep 17 00:00:00 2001
From: Eric Sandeen <sandeen@redhat.com>
Date: Mon, 28 Oct 2024 09:32:38 -0500
Subject: [PATCH 1150/1530] ecryptfs: Factor out mount option validation

Under the new mount API, mount options are parsed one at a time.
Any validation that examines multiple options must be done after parsing
is complete, so factor out a ecryptfs_validate_options() which can be
called separately.

To facilitate this, temporarily move the local variables that tracked
whether various options have been set in the parsing function, into the
ecryptfs_mount_crypt_stat structure so that they can be examined later.

These will be moved to a more ephemeral struct in the mount api conversion
patch to follow.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Link: https://lore.kernel.org/r/20241028143359.605061-2-sandeen@redhat.com
Acked-by: Tyler Hicks <code@tyhicks.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/ecryptfs/ecryptfs_kernel.h |  7 +++++
 fs/ecryptfs/main.c            | 55 ++++++++++++++++++++---------------
 2 files changed, 38 insertions(+), 24 deletions(-)

diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 1f562e75d0e43..15dcff94c0175 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -343,6 +343,13 @@ struct ecryptfs_mount_crypt_stat {
 	unsigned char global_default_fn_cipher_name[
 		ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1];
 	char global_default_fnek_sig[ECRYPTFS_SIG_SIZE_HEX + 1];
+	/* Mount option status trackers */
+	bool check_ruid;
+	bool sig_set;
+	bool cipher_name_set;
+	bool cipher_key_bytes_set;
+	bool fn_cipher_name_set;
+	bool fn_cipher_key_bytes_set;
 };
 
 /* superblock private data. */
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 577c563023144..d03f1c6ccc1c8 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -239,18 +239,12 @@ static void ecryptfs_init_mount_crypt_stat(
  *
  * Returns zero on success; non-zero on error
  */
-static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
-				  uid_t *check_ruid)
+static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options)
 {
 	char *p;
 	int rc = 0;
-	int sig_set = 0;
-	int cipher_name_set = 0;
-	int fn_cipher_name_set = 0;
 	int cipher_key_bytes;
-	int cipher_key_bytes_set = 0;
 	int fn_cipher_key_bytes;
-	int fn_cipher_key_bytes_set = 0;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat =
 		&sbi->mount_crypt_stat;
 	substring_t args[MAX_OPT_ARGS];
@@ -261,9 +255,6 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
 	char *fnek_src;
 	char *cipher_key_bytes_src;
 	char *fn_cipher_key_bytes_src;
-	u8 cipher_code;
-
-	*check_ruid = 0;
 
 	if (!options) {
 		rc = -EINVAL;
@@ -285,14 +276,14 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
 				       "global sig; rc = [%d]\n", rc);
 				goto out;
 			}
-			sig_set = 1;
+			mount_crypt_stat->sig_set = 1;
 			break;
 		case ecryptfs_opt_cipher:
 		case ecryptfs_opt_ecryptfs_cipher:
 			cipher_name_src = args[0].from;
 			strscpy(mount_crypt_stat->global_default_cipher_name,
 				cipher_name_src);
-			cipher_name_set = 1;
+			mount_crypt_stat->cipher_name_set = 1;
 			break;
 		case ecryptfs_opt_ecryptfs_key_bytes:
 			cipher_key_bytes_src = args[0].from;
@@ -301,7 +292,7 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
 						   &cipher_key_bytes_src, 0);
 			mount_crypt_stat->global_default_cipher_key_size =
 				cipher_key_bytes;
-			cipher_key_bytes_set = 1;
+			mount_crypt_stat->cipher_key_bytes_set = 1;
 			break;
 		case ecryptfs_opt_passthrough:
 			mount_crypt_stat->flags |=
@@ -340,7 +331,7 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
 			fn_cipher_name_src = args[0].from;
 			strscpy(mount_crypt_stat->global_default_fn_cipher_name,
 				fn_cipher_name_src);
-			fn_cipher_name_set = 1;
+			mount_crypt_stat->fn_cipher_name_set = 1;
 			break;
 		case ecryptfs_opt_fn_cipher_key_bytes:
 			fn_cipher_key_bytes_src = args[0].from;
@@ -349,7 +340,7 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
 						   &fn_cipher_key_bytes_src, 0);
 			mount_crypt_stat->global_default_fn_cipher_key_bytes =
 				fn_cipher_key_bytes;
-			fn_cipher_key_bytes_set = 1;
+			mount_crypt_stat->fn_cipher_key_bytes_set = 1;
 			break;
 		case ecryptfs_opt_unlink_sigs:
 			mount_crypt_stat->flags |= ECRYPTFS_UNLINK_SIGS;
@@ -359,7 +350,7 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
 				ECRYPTFS_GLOBAL_MOUNT_AUTH_TOK_ONLY;
 			break;
 		case ecryptfs_opt_check_dev_ruid:
-			*check_ruid = 1;
+			mount_crypt_stat->check_ruid = 1;
 			break;
 		case ecryptfs_opt_err:
 		default:
@@ -368,14 +359,25 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
 			       __func__, p);
 		}
 	}
-	if (!sig_set) {
+
+out:
+	return rc;
+}
+
+static int ecryptfs_validate_options(
+		struct ecryptfs_mount_crypt_stat *mount_crypt_stat)
+{
+	int rc = 0;
+	u8 cipher_code;
+
+	if (!mount_crypt_stat->sig_set) {
 		rc = -EINVAL;
 		ecryptfs_printk(KERN_ERR, "You must supply at least one valid "
 				"auth tok signature as a mount "
 				"parameter; see the eCryptfs README\n");
 		goto out;
 	}
-	if (!cipher_name_set) {
+	if (!mount_crypt_stat->cipher_name_set) {
 		int cipher_name_len = strlen(ECRYPTFS_DEFAULT_CIPHER);
 
 		BUG_ON(cipher_name_len > ECRYPTFS_MAX_CIPHER_NAME_SIZE);
@@ -383,13 +385,13 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
 		       ECRYPTFS_DEFAULT_CIPHER);
 	}
 	if ((mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)
-	    && !fn_cipher_name_set)
+	    && !mount_crypt_stat->fn_cipher_name_set)
 		strcpy(mount_crypt_stat->global_default_fn_cipher_name,
 		       mount_crypt_stat->global_default_cipher_name);
-	if (!cipher_key_bytes_set)
+	if (!mount_crypt_stat->cipher_key_bytes_set)
 		mount_crypt_stat->global_default_cipher_key_size = 0;
 	if ((mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)
-	    && !fn_cipher_key_bytes_set)
+	    && !mount_crypt_stat->fn_cipher_key_bytes_set)
 		mount_crypt_stat->global_default_fn_cipher_key_bytes =
 			mount_crypt_stat->global_default_cipher_key_size;
 
@@ -469,7 +471,6 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 	const char *err = "Getting sb failed";
 	struct inode *inode;
 	struct path path;
-	uid_t check_ruid;
 	int rc;
 
 	sbi = kmem_cache_zalloc(ecryptfs_sb_info_cache, GFP_KERNEL);
@@ -484,12 +485,17 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		goto out;
 	}
 
-	rc = ecryptfs_parse_options(sbi, raw_data, &check_ruid);
+	rc = ecryptfs_parse_options(sbi, raw_data);
 	if (rc) {
 		err = "Error parsing options";
 		goto out;
 	}
 	mount_crypt_stat = &sbi->mount_crypt_stat;
+	rc = ecryptfs_validate_options(mount_crypt_stat);
+	if (rc) {
+		err = "Error validationg options";
+		goto out;
+	}
 
 	s = sget(fs_type, NULL, set_anon_super, flags, NULL);
 	if (IS_ERR(s)) {
@@ -529,7 +535,8 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		goto out_free;
 	}
 
-	if (check_ruid && !uid_eq(d_inode(path.dentry)->i_uid, current_uid())) {
+	if (mount_crypt_stat->check_ruid &&
+	    !uid_eq(d_inode(path.dentry)->i_uid, current_uid())) {
 		rc = -EPERM;
 		printk(KERN_ERR "Mount of device (uid: %d) not owned by "
 		       "requested user (uid: %d)\n",

From 92f3da0d9276f921af49a05c2684fca45e1f1c21 Mon Sep 17 00:00:00 2001
From: Eric Sandeen <sandeen@redhat.com>
Date: Mon, 28 Oct 2024 09:32:39 -0500
Subject: [PATCH 1151/1530] ecryptfs: Convert ecryptfs to use the new mount API

Convert ecryptfs to the new mount API.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Link: https://lore.kernel.org/r/20241028143359.605061-3-sandeen@redhat.com
Acked-by: Tyler Hicks <code@tyhicks.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/ecryptfs/ecryptfs_kernel.h |   7 -
 fs/ecryptfs/main.c            | 392 +++++++++++++++++-----------------
 2 files changed, 197 insertions(+), 202 deletions(-)

diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 15dcff94c0175..1f562e75d0e43 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -343,13 +343,6 @@ struct ecryptfs_mount_crypt_stat {
 	unsigned char global_default_fn_cipher_name[
 		ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1];
 	char global_default_fnek_sig[ECRYPTFS_SIG_SIZE_HEX + 1];
-	/* Mount option status trackers */
-	bool check_ruid;
-	bool sig_set;
-	bool cipher_name_set;
-	bool cipher_key_bytes_set;
-	bool fn_cipher_name_set;
-	bool fn_cipher_key_bytes_set;
 };
 
 /* superblock private data. */
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index d03f1c6ccc1c8..c9aa80e534c24 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -15,10 +15,10 @@
 #include <linux/module.h>
 #include <linux/namei.h>
 #include <linux/skbuff.h>
-#include <linux/mount.h>
 #include <linux/pagemap.h>
 #include <linux/key.h>
-#include <linux/parser.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
 #include <linux/fs_stack.h>
 #include <linux/slab.h>
 #include <linux/magic.h>
@@ -153,32 +153,30 @@ void ecryptfs_put_lower_file(struct inode *inode)
 	}
 }
 
-enum { ecryptfs_opt_sig, ecryptfs_opt_ecryptfs_sig,
-       ecryptfs_opt_cipher, ecryptfs_opt_ecryptfs_cipher,
-       ecryptfs_opt_ecryptfs_key_bytes,
-       ecryptfs_opt_passthrough, ecryptfs_opt_xattr_metadata,
-       ecryptfs_opt_encrypted_view, ecryptfs_opt_fnek_sig,
-       ecryptfs_opt_fn_cipher, ecryptfs_opt_fn_cipher_key_bytes,
-       ecryptfs_opt_unlink_sigs, ecryptfs_opt_mount_auth_tok_only,
-       ecryptfs_opt_check_dev_ruid,
-       ecryptfs_opt_err };
-
-static const match_table_t tokens = {
-	{ecryptfs_opt_sig, "sig=%s"},
-	{ecryptfs_opt_ecryptfs_sig, "ecryptfs_sig=%s"},
-	{ecryptfs_opt_cipher, "cipher=%s"},
-	{ecryptfs_opt_ecryptfs_cipher, "ecryptfs_cipher=%s"},
-	{ecryptfs_opt_ecryptfs_key_bytes, "ecryptfs_key_bytes=%u"},
-	{ecryptfs_opt_passthrough, "ecryptfs_passthrough"},
-	{ecryptfs_opt_xattr_metadata, "ecryptfs_xattr_metadata"},
-	{ecryptfs_opt_encrypted_view, "ecryptfs_encrypted_view"},
-	{ecryptfs_opt_fnek_sig, "ecryptfs_fnek_sig=%s"},
-	{ecryptfs_opt_fn_cipher, "ecryptfs_fn_cipher=%s"},
-	{ecryptfs_opt_fn_cipher_key_bytes, "ecryptfs_fn_key_bytes=%u"},
-	{ecryptfs_opt_unlink_sigs, "ecryptfs_unlink_sigs"},
-	{ecryptfs_opt_mount_auth_tok_only, "ecryptfs_mount_auth_tok_only"},
-	{ecryptfs_opt_check_dev_ruid, "ecryptfs_check_dev_ruid"},
-	{ecryptfs_opt_err, NULL}
+enum {
+	Opt_sig, Opt_ecryptfs_sig, Opt_cipher, Opt_ecryptfs_cipher,
+	Opt_ecryptfs_key_bytes, Opt_passthrough, Opt_xattr_metadata,
+	Opt_encrypted_view, Opt_fnek_sig, Opt_fn_cipher,
+	Opt_fn_cipher_key_bytes, Opt_unlink_sigs, Opt_mount_auth_tok_only,
+	Opt_check_dev_ruid
+};
+
+static const struct fs_parameter_spec ecryptfs_fs_param_spec[] = {
+	fsparam_string	("sig",			    Opt_sig),
+	fsparam_string	("ecryptfs_sig",	    Opt_ecryptfs_sig),
+	fsparam_string	("cipher",		    Opt_cipher),
+	fsparam_string	("ecryptfs_cipher",	    Opt_ecryptfs_cipher),
+	fsparam_u32	("ecryptfs_key_bytes",	    Opt_ecryptfs_key_bytes),
+	fsparam_flag	("ecryptfs_passthrough",    Opt_passthrough),
+	fsparam_flag	("ecryptfs_xattr_metadata", Opt_xattr_metadata),
+	fsparam_flag	("ecryptfs_encrypted_view", Opt_encrypted_view),
+	fsparam_string	("ecryptfs_fnek_sig",	    Opt_fnek_sig),
+	fsparam_string	("ecryptfs_fn_cipher",	    Opt_fn_cipher),
+	fsparam_u32	("ecryptfs_fn_key_bytes",   Opt_fn_cipher_key_bytes),
+	fsparam_flag	("ecryptfs_unlink_sigs",    Opt_unlink_sigs),
+	fsparam_flag	("ecryptfs_mount_auth_tok_only", Opt_mount_auth_tok_only),
+	fsparam_flag	("ecryptfs_check_dev_ruid", Opt_check_dev_ruid),
+	{}
 };
 
 static int ecryptfs_init_global_auth_toks(
@@ -219,19 +217,20 @@ static void ecryptfs_init_mount_crypt_stat(
 	mount_crypt_stat->flags |= ECRYPTFS_MOUNT_CRYPT_STAT_INITIALIZED;
 }
 
+struct ecryptfs_fs_context {
+	/* Mount option status trackers */
+	bool check_ruid;
+	bool sig_set;
+	bool cipher_name_set;
+	bool cipher_key_bytes_set;
+	bool fn_cipher_name_set;
+	bool fn_cipher_key_bytes_set;
+};
+
 /**
- * ecryptfs_parse_options
- * @sbi: The ecryptfs super block
- * @options: The options passed to the kernel
- * @check_ruid: set to 1 if device uid should be checked against the ruid
- *
- * Parse mount options:
- * debug=N 	   - ecryptfs_verbosity level for debug output
- * sig=XXX	   - description(signature) of the key to use
- *
- * Returns the dentry object of the lower-level (lower/interposed)
- * directory; We want to mount our stackable file system on top of
- * that lower directory.
+ * ecryptfs_parse_param
+ * @fc: The ecryptfs filesystem context
+ * @param: The mount parameter to parse
  *
  * The signature of the key to use must be the description of a key
  * already in the keyring. Mounting will fail if the key can not be
@@ -239,145 +238,118 @@ static void ecryptfs_init_mount_crypt_stat(
  *
  * Returns zero on success; non-zero on error
  */
-static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options)
+static int ecryptfs_parse_param(
+	struct fs_context *fc,
+	struct fs_parameter *param)
 {
-	char *p;
-	int rc = 0;
-	int cipher_key_bytes;
-	int fn_cipher_key_bytes;
+	int rc;
+	int opt;
+	struct fs_parse_result result;
+	struct ecryptfs_fs_context *ctx = fc->fs_private;
+	struct ecryptfs_sb_info *sbi = fc->s_fs_info;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat =
 		&sbi->mount_crypt_stat;
-	substring_t args[MAX_OPT_ARGS];
-	int token;
-	char *sig_src;
-	char *cipher_name_src;
-	char *fn_cipher_name_src;
-	char *fnek_src;
-	char *cipher_key_bytes_src;
-	char *fn_cipher_key_bytes_src;
-
-	if (!options) {
-		rc = -EINVAL;
-		goto out;
-	}
-	ecryptfs_init_mount_crypt_stat(mount_crypt_stat);
-	while ((p = strsep(&options, ",")) != NULL) {
-		if (!*p)
-			continue;
-		token = match_token(p, tokens, args);
-		switch (token) {
-		case ecryptfs_opt_sig:
-		case ecryptfs_opt_ecryptfs_sig:
-			sig_src = args[0].from;
-			rc = ecryptfs_add_global_auth_tok(mount_crypt_stat,
-							  sig_src, 0);
-			if (rc) {
-				printk(KERN_ERR "Error attempting to register "
-				       "global sig; rc = [%d]\n", rc);
-				goto out;
-			}
-			mount_crypt_stat->sig_set = 1;
-			break;
-		case ecryptfs_opt_cipher:
-		case ecryptfs_opt_ecryptfs_cipher:
-			cipher_name_src = args[0].from;
-			strscpy(mount_crypt_stat->global_default_cipher_name,
-				cipher_name_src);
-			mount_crypt_stat->cipher_name_set = 1;
-			break;
-		case ecryptfs_opt_ecryptfs_key_bytes:
-			cipher_key_bytes_src = args[0].from;
-			cipher_key_bytes =
-				(int)simple_strtol(cipher_key_bytes_src,
-						   &cipher_key_bytes_src, 0);
-			mount_crypt_stat->global_default_cipher_key_size =
-				cipher_key_bytes;
-			mount_crypt_stat->cipher_key_bytes_set = 1;
-			break;
-		case ecryptfs_opt_passthrough:
-			mount_crypt_stat->flags |=
-				ECRYPTFS_PLAINTEXT_PASSTHROUGH_ENABLED;
-			break;
-		case ecryptfs_opt_xattr_metadata:
-			mount_crypt_stat->flags |=
-				ECRYPTFS_XATTR_METADATA_ENABLED;
-			break;
-		case ecryptfs_opt_encrypted_view:
-			mount_crypt_stat->flags |=
-				ECRYPTFS_XATTR_METADATA_ENABLED;
-			mount_crypt_stat->flags |=
-				ECRYPTFS_ENCRYPTED_VIEW_ENABLED;
-			break;
-		case ecryptfs_opt_fnek_sig:
-			fnek_src = args[0].from;
-			strscpy(mount_crypt_stat->global_default_fnek_sig,
-				fnek_src);
-			rc = ecryptfs_add_global_auth_tok(
-				mount_crypt_stat,
-				mount_crypt_stat->global_default_fnek_sig,
-				ECRYPTFS_AUTH_TOK_FNEK);
-			if (rc) {
-				printk(KERN_ERR "Error attempting to register "
-				       "global fnek sig [%s]; rc = [%d]\n",
-				       mount_crypt_stat->global_default_fnek_sig,
-				       rc);
-				goto out;
-			}
-			mount_crypt_stat->flags |=
-				(ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES
-				 | ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK);
-			break;
-		case ecryptfs_opt_fn_cipher:
-			fn_cipher_name_src = args[0].from;
-			strscpy(mount_crypt_stat->global_default_fn_cipher_name,
-				fn_cipher_name_src);
-			mount_crypt_stat->fn_cipher_name_set = 1;
-			break;
-		case ecryptfs_opt_fn_cipher_key_bytes:
-			fn_cipher_key_bytes_src = args[0].from;
-			fn_cipher_key_bytes =
-				(int)simple_strtol(fn_cipher_key_bytes_src,
-						   &fn_cipher_key_bytes_src, 0);
-			mount_crypt_stat->global_default_fn_cipher_key_bytes =
-				fn_cipher_key_bytes;
-			mount_crypt_stat->fn_cipher_key_bytes_set = 1;
-			break;
-		case ecryptfs_opt_unlink_sigs:
-			mount_crypt_stat->flags |= ECRYPTFS_UNLINK_SIGS;
-			break;
-		case ecryptfs_opt_mount_auth_tok_only:
-			mount_crypt_stat->flags |=
-				ECRYPTFS_GLOBAL_MOUNT_AUTH_TOK_ONLY;
-			break;
-		case ecryptfs_opt_check_dev_ruid:
-			mount_crypt_stat->check_ruid = 1;
-			break;
-		case ecryptfs_opt_err:
-		default:
-			printk(KERN_WARNING
-			       "%s: eCryptfs: unrecognized option [%s]\n",
-			       __func__, p);
+
+	opt = fs_parse(fc, ecryptfs_fs_param_spec, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_sig:
+	case Opt_ecryptfs_sig:
+		rc = ecryptfs_add_global_auth_tok(mount_crypt_stat,
+						  param->string, 0);
+		if (rc) {
+			printk(KERN_ERR "Error attempting to register "
+			       "global sig; rc = [%d]\n", rc);
+			return rc;
+		}
+		ctx->sig_set = 1;
+		break;
+	case Opt_cipher:
+	case Opt_ecryptfs_cipher:
+		strscpy(mount_crypt_stat->global_default_cipher_name,
+			param->string);
+		ctx->cipher_name_set = 1;
+		break;
+	case Opt_ecryptfs_key_bytes:
+		mount_crypt_stat->global_default_cipher_key_size =
+			result.uint_32;
+		ctx->cipher_key_bytes_set = 1;
+		break;
+	case Opt_passthrough:
+		mount_crypt_stat->flags |=
+			ECRYPTFS_PLAINTEXT_PASSTHROUGH_ENABLED;
+		break;
+	case Opt_xattr_metadata:
+		mount_crypt_stat->flags |= ECRYPTFS_XATTR_METADATA_ENABLED;
+		break;
+	case Opt_encrypted_view:
+		mount_crypt_stat->flags |= ECRYPTFS_XATTR_METADATA_ENABLED;
+		mount_crypt_stat->flags |= ECRYPTFS_ENCRYPTED_VIEW_ENABLED;
+		break;
+	case Opt_fnek_sig:
+		strscpy(mount_crypt_stat->global_default_fnek_sig,
+			param->string);
+		rc = ecryptfs_add_global_auth_tok(
+			mount_crypt_stat,
+			mount_crypt_stat->global_default_fnek_sig,
+			ECRYPTFS_AUTH_TOK_FNEK);
+		if (rc) {
+			printk(KERN_ERR "Error attempting to register "
+			       "global fnek sig [%s]; rc = [%d]\n",
+			       mount_crypt_stat->global_default_fnek_sig, rc);
+			return rc;
 		}
+		mount_crypt_stat->flags |=
+			(ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES
+			 | ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK);
+		break;
+	case Opt_fn_cipher:
+		strscpy(mount_crypt_stat->global_default_fn_cipher_name,
+			param->string);
+		ctx->fn_cipher_name_set = 1;
+		break;
+	case Opt_fn_cipher_key_bytes:
+		mount_crypt_stat->global_default_fn_cipher_key_bytes =
+			result.uint_32;
+		ctx->fn_cipher_key_bytes_set = 1;
+		break;
+	case Opt_unlink_sigs:
+		mount_crypt_stat->flags |= ECRYPTFS_UNLINK_SIGS;
+		break;
+	case Opt_mount_auth_tok_only:
+		mount_crypt_stat->flags |= ECRYPTFS_GLOBAL_MOUNT_AUTH_TOK_ONLY;
+		break;
+	case Opt_check_dev_ruid:
+		ctx->check_ruid = 1;
+		break;
+	default:
+		return -EINVAL;
 	}
 
-out:
-	return rc;
+	return 0;
 }
 
-static int ecryptfs_validate_options(
-		struct ecryptfs_mount_crypt_stat *mount_crypt_stat)
+static int ecryptfs_validate_options(struct fs_context *fc)
 {
 	int rc = 0;
 	u8 cipher_code;
+	struct ecryptfs_fs_context *ctx = fc->fs_private;
+	struct ecryptfs_sb_info *sbi = fc->s_fs_info;
+	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
 
-	if (!mount_crypt_stat->sig_set) {
+
+	mount_crypt_stat = &sbi->mount_crypt_stat;
+
+	if (!ctx->sig_set) {
 		rc = -EINVAL;
 		ecryptfs_printk(KERN_ERR, "You must supply at least one valid "
 				"auth tok signature as a mount "
 				"parameter; see the eCryptfs README\n");
 		goto out;
 	}
-	if (!mount_crypt_stat->cipher_name_set) {
+	if (!ctx->cipher_name_set) {
 		int cipher_name_len = strlen(ECRYPTFS_DEFAULT_CIPHER);
 
 		BUG_ON(cipher_name_len > ECRYPTFS_MAX_CIPHER_NAME_SIZE);
@@ -385,13 +357,13 @@ static int ecryptfs_validate_options(
 		       ECRYPTFS_DEFAULT_CIPHER);
 	}
 	if ((mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)
-	    && !mount_crypt_stat->fn_cipher_name_set)
+	    && !ctx->fn_cipher_name_set)
 		strcpy(mount_crypt_stat->global_default_fn_cipher_name,
 		       mount_crypt_stat->global_default_cipher_name);
-	if (!mount_crypt_stat->cipher_key_bytes_set)
+	if (!ctx->cipher_key_bytes_set)
 		mount_crypt_stat->global_default_cipher_key_size = 0;
 	if ((mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)
-	    && !mount_crypt_stat->fn_cipher_key_bytes_set)
+	    && !ctx->fn_cipher_key_bytes_set)
 		mount_crypt_stat->global_default_fn_cipher_key_bytes =
 			mount_crypt_stat->global_default_cipher_key_size;
 
@@ -455,17 +427,14 @@ struct kmem_cache *ecryptfs_sb_info_cache;
 static struct file_system_type ecryptfs_fs_type;
 
 /*
- * ecryptfs_mount
- * @fs_type: The filesystem type that the superblock should belong to
- * @flags: The flags associated with the mount
- * @dev_name: The path to mount over
- * @raw_data: The options passed into the kernel
+ * ecryptfs_get_tree
+ * @fc: The filesystem context
  */
-static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags,
-			const char *dev_name, void *raw_data)
+static int ecryptfs_get_tree(struct fs_context *fc)
 {
 	struct super_block *s;
-	struct ecryptfs_sb_info *sbi;
+	struct ecryptfs_fs_context *ctx = fc->fs_private;
+	struct ecryptfs_sb_info *sbi = fc->s_fs_info;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
 	struct ecryptfs_dentry_info *root_info;
 	const char *err = "Getting sb failed";
@@ -473,31 +442,20 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 	struct path path;
 	int rc;
 
-	sbi = kmem_cache_zalloc(ecryptfs_sb_info_cache, GFP_KERNEL);
-	if (!sbi) {
-		rc = -ENOMEM;
-		goto out;
-	}
-
-	if (!dev_name) {
+	if (!fc->source) {
 		rc = -EINVAL;
 		err = "Device name cannot be null";
 		goto out;
 	}
 
-	rc = ecryptfs_parse_options(sbi, raw_data);
-	if (rc) {
-		err = "Error parsing options";
-		goto out;
-	}
 	mount_crypt_stat = &sbi->mount_crypt_stat;
-	rc = ecryptfs_validate_options(mount_crypt_stat);
+	rc = ecryptfs_validate_options(fc);
 	if (rc) {
 		err = "Error validationg options";
 		goto out;
 	}
 
-	s = sget(fs_type, NULL, set_anon_super, flags, NULL);
+	s = sget_fc(fc, NULL, set_anon_super_fc);
 	if (IS_ERR(s)) {
 		rc = PTR_ERR(s);
 		goto out;
@@ -516,7 +474,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 	s->s_d_op = &ecryptfs_dops;
 
 	err = "Reading sb failed";
-	rc = kern_path(dev_name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
+	rc = kern_path(fc->source, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
 	if (rc) {
 		ecryptfs_printk(KERN_WARNING, "kern_path() failed\n");
 		goto out1;
@@ -535,7 +493,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		goto out_free;
 	}
 
-	if (mount_crypt_stat->check_ruid &&
+	if (ctx->check_ruid &&
 	    !uid_eq(d_inode(path.dentry)->i_uid, current_uid())) {
 		rc = -EPERM;
 		printk(KERN_ERR "Mount of device (uid: %d) not owned by "
@@ -551,7 +509,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 	 * Set the POSIX ACL flag based on whether they're enabled in the lower
 	 * mount.
 	 */
-	s->s_flags = flags & ~SB_POSIXACL;
+	s->s_flags = fc->sb_flags & ~SB_POSIXACL;
 	s->s_flags |= path.dentry->d_sb->s_flags & SB_POSIXACL;
 
 	/**
@@ -594,19 +552,19 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 	root_info->lower_path = path;
 
 	s->s_flags |= SB_ACTIVE;
-	return dget(s->s_root);
+	fc->root = dget(s->s_root);
+	return 0;
 
 out_free:
 	path_put(&path);
 out1:
 	deactivate_locked_super(s);
 out:
-	if (sbi) {
+	if (sbi)
 		ecryptfs_destroy_mount_crypt_stat(&sbi->mount_crypt_stat);
-		kmem_cache_free(ecryptfs_sb_info_cache, sbi);
-	}
+
 	printk(KERN_ERR "%s; rc = [%d]\n", err, rc);
-	return ERR_PTR(rc);
+	return rc;
 }
 
 /**
@@ -625,10 +583,54 @@ static void ecryptfs_kill_block_super(struct super_block *sb)
 	kmem_cache_free(ecryptfs_sb_info_cache, sb_info);
 }
 
+static void ecryptfs_free_fc(struct fs_context *fc)
+{
+	struct ecryptfs_fs_context *ctx = fc->fs_private;
+	struct ecryptfs_sb_info *sbi = fc->s_fs_info;
+
+	kfree(ctx);
+
+	if (sbi) {
+		ecryptfs_destroy_mount_crypt_stat(&sbi->mount_crypt_stat);
+		kmem_cache_free(ecryptfs_sb_info_cache, sbi);
+	}
+}
+
+static const struct fs_context_operations ecryptfs_context_ops = {
+	.free		= ecryptfs_free_fc,
+	.parse_param	= ecryptfs_parse_param,
+	.get_tree	= ecryptfs_get_tree,
+	.reconfigure	= NULL,
+};
+
+static int ecryptfs_init_fs_context(struct fs_context *fc)
+{
+	struct ecryptfs_fs_context *ctx;
+	struct ecryptfs_sb_info *sbi = NULL;
+
+	ctx = kzalloc(sizeof(struct ecryptfs_fs_context), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	sbi = kmem_cache_zalloc(ecryptfs_sb_info_cache, GFP_KERNEL);
+	if (!sbi) {
+		kfree(ctx);
+		ctx = NULL;
+		return -ENOMEM;
+	}
+
+	ecryptfs_init_mount_crypt_stat(&sbi->mount_crypt_stat);
+
+	fc->fs_private = ctx;
+	fc->s_fs_info = sbi;
+	fc->ops = &ecryptfs_context_ops;
+	return 0;
+}
+
 static struct file_system_type ecryptfs_fs_type = {
 	.owner = THIS_MODULE,
 	.name = "ecryptfs",
-	.mount = ecryptfs_mount,
+	.init_fs_context = ecryptfs_init_fs_context,
+	.parameters = ecryptfs_fs_param_spec,
 	.kill_sb = ecryptfs_kill_block_super,
 	.fs_flags = 0
 };

From 7ff3e945a35ac472c6783403eae1e7519d96f1cf Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Fri, 8 Nov 2024 11:25:09 +0000
Subject: [PATCH 1152/1530] ecryptfs: Fix spelling mistake "validationg" ->
 "validating"

There is a spelling mistake in an error message literal string. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Link: https://lore.kernel.org/r/20241108112509.109891-1-colin.i.king@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/ecryptfs/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index c9aa80e534c24..8dd1d7189c3b2 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -451,7 +451,7 @@ static int ecryptfs_get_tree(struct fs_context *fc)
 	mount_crypt_stat = &sbi->mount_crypt_stat;
 	rc = ecryptfs_validate_options(fc);
 	if (rc) {
-		err = "Error validationg options";
+		err = "Error validating options";
 		goto out;
 	}
 

From 7ca41faa5f5b9784ae2ef27e1c6902cddbc530ef Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 14 Nov 2024 18:13:17 -0300
Subject: [PATCH 1153/1530] perf test shell trace_exit_race: Show what went
 wrong in verbose mode

If it fails we need to check what was the reason, what were the lines
that didn't match the expected format, so:

  root@number:~# perf test -v "trace exit race"
  --- start ---
  test child forked, pid 2028724
  Lines not matching the expected regexp: ' +[0-9]+\.[0-9]+ +true/[0-9]+ syscalls:sys_enter_exit_group\(\)$':
       0.000 :2028750/2028750 syscalls:sys_enter_exit_group()
  ---- end(-1) ----
  110: perf trace exit race                                            : FAILED!
  root@number:~#

In this case we're not resolving the process COMM for some reason and
fallback to printing just the pid/tid, this will be fixed in a followup
patch.

Howard Chu spotted a problem with single code surrounding a regexp, that
made the test always fail, but since there were some failures when I
tested (COMM not being resolved in some of the results) the end inverse
grep would show some lines and thus didn't notice the single quote
problem.

He also provided a patch to test if less than the number of expected
matches took place but all of them with the expected output, in which
case the inverse grep wouldn't show anything, confusing the tester.

Reviewed-by: Howard Chu <howardchu95@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Peterson <benjamin@engflow.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/lkml/ZzdknoHqrJbojb6P@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/trace_exit_race.sh | 24 +++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/trace_exit_race.sh b/tools/perf/tests/shell/trace_exit_race.sh
index 3cf2d71a5c3b9..8ea24f4256bc8 100755
--- a/tools/perf/tests/shell/trace_exit_race.sh
+++ b/tools/perf/tests/shell/trace_exit_race.sh
@@ -11,11 +11,19 @@
 
 skip_if_no_perf_trace || exit 2
 
+if [ "$1" = "-v" ]; then
+	verbose="1"
+fi
+
+iter=10
+regexp=" +[0-9]+\.[0-9]+ +true/[0-9]+ syscalls:sys_enter_exit_group\(\)$"
+
 trace_shutdown_race() {
-	for _ in $(seq 10); do
+	for _ in $(seq $iter); do
 		perf trace -e syscalls:sys_enter_exit_group true 2>>$file
 	done
-	[ "$(grep -c -E ' +[0-9]+\.[0-9]+ +true/[0-9]+ syscalls:sys_enter_exit_group\(\)$' $file)" = "10" ]
+	result="$(grep -c -E "$regexp" $file)"
+	[ $result = $iter ]
 }
 
 
@@ -27,5 +35,17 @@ export PERF_CONFIG=/dev/null
 
 trace_shutdown_race
 err=$?
+
+if [ $err != 0 ] && [ "${verbose}" = "1" ]; then
+	lines_not_matching=$(mktemp /tmp/temporary_file.XXXXX)
+	if grep -v -E "$regexp" $file > $lines_not_matching ; then
+		echo "Lines not matching the expected regexp: '$regexp':"
+		cat $lines_not_matching
+	else
+		echo "Missing output, expected $iter but only got $result"
+	fi
+	rm -f $lines_not_matching
+fi
+
 rm -f ${file}
 exit $err

From 5e316d34b53039346e252d0019e2f4167af2c0ef Mon Sep 17 00:00:00 2001
From: Andrea della Porta <andrea.porta@suse.com>
Date: Fri, 8 Nov 2024 10:42:56 +0100
Subject: [PATCH 1154/1530] PCI: of_property: Assign PCI instead of CPU bus
 address to dynamic PCI nodes

When populating "ranges" property for a PCI bridge or endpoint,
of_pci_prop_ranges() incorrectly uses the CPU address of the resource.  In
such PCI nodes, the window should instead be in PCI address space. Call
pci_bus_address() on the resource in order to obtain the PCI bus address.

[Previous discussion at:
https://lore.kernel.org/all/8b4fa91380fc4754ea80f47330c613e4f6b6592c.1724159867.git.andrea.porta@suse.com/]

Link: https://lore.kernel.org/r/20241108094256.28933-1-andrea.porta@suse.com
Fixes: 407d1a51921e ("PCI: Create device tree node for bridge")
Tested-by: Herve Codina <herve.codina@bootlin.com>
Signed-off-by: Andrea della Porta <andrea.porta@suse.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org
---
 drivers/pci/of_property.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/of_property.c b/drivers/pci/of_property.c
index 5a0b98e697954..886c236e5de6e 100644
--- a/drivers/pci/of_property.c
+++ b/drivers/pci/of_property.c
@@ -126,7 +126,7 @@ static int of_pci_prop_ranges(struct pci_dev *pdev, struct of_changeset *ocs,
 		if (of_pci_get_addr_flags(&res[j], &flags))
 			continue;
 
-		val64 = res[j].start;
+		val64 = pci_bus_address(pdev, &res[j] - pdev->resource);
 		of_pci_set_address(pdev, rp[i].parent_addr, val64, 0, flags,
 				   false);
 		if (pci_is_bridge(pdev)) {

From 31457d4cea19dc807e3beab15883c912f19acef7 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Sat, 2 Nov 2024 12:45:37 -0500
Subject: [PATCH 1155/1530] PCI: Fix typos

Fix typos and whitespace errors.

Link: https://lore.kernel.org/r/20241102174537.1362183-1-helgaas@kernel.org
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/controller/pcie-rcar-host.c |  4 ++--
 drivers/pci/pcie/aer.c                  | 15 +++++++++------
 2 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/controller/pcie-rcar-host.c b/drivers/pci/controller/pcie-rcar-host.c
index 3dd653f3d7841..7c92eada04af4 100644
--- a/drivers/pci/controller/pcie-rcar-host.c
+++ b/drivers/pci/controller/pcie-rcar-host.c
@@ -796,8 +796,8 @@ static int rcar_pcie_enable_msi(struct rcar_pcie_host *host)
 	rcar_pci_write_reg(pcie, 0, PCIEMSIIER);
 
 	/*
-	 * Setup MSI data target using RC base address address, which
-	 * is guaranteed to be in the low 32bit range on any R-Car HW.
+	 * Setup MSI data target using RC base address, which is guaranteed
+	 * to be in the low 32bit range on any R-Car HW.
 	 */
 	rcar_pci_write_reg(pcie, lower_32_bits(res.start) | MSIFE, PCIEMSIALR);
 	rcar_pci_write_reg(pcie, upper_32_bits(res.start), PCIEMSIAUR);
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 13b8586924ead..80c5ba8d82962 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -180,7 +180,8 @@ static int disable_ecrc_checking(struct pci_dev *dev)
 }
 
 /**
- * pcie_set_ecrc_checking - set/unset PCIe ECRC checking for a device based on global policy
+ * pcie_set_ecrc_checking - set/unset PCIe ECRC checking for a device based
+ * on global policy
  * @dev: the PCI device
  */
 void pcie_set_ecrc_checking(struct pci_dev *dev)
@@ -1148,14 +1149,16 @@ static void aer_recover_work_func(struct work_struct *work)
 			continue;
 		}
 		pci_print_aer(pdev, entry.severity, entry.regs);
+
 		/*
-		 * Memory for aer_capability_regs(entry.regs) is being allocated from the
-		 * ghes_estatus_pool to protect it from overwriting when multiple sections
-		 * are present in the error status. Thus free the same after processing
-		 * the data.
+		 * Memory for aer_capability_regs(entry.regs) is being
+		 * allocated from the ghes_estatus_pool to protect it from
+		 * overwriting when multiple sections are present in the
+		 * error status. Thus free the same after processing the
+		 * data.
 		 */
 		ghes_estatus_pool_region_free((unsigned long)entry.regs,
-					      sizeof(struct aer_capability_regs));
+					    sizeof(struct aer_capability_regs));
 
 		if (entry.severity == AER_NONFATAL)
 			pcie_do_recovery(pdev, pci_channel_io_normal,

From aa46a3736afcb7b0793766d22479b8b99fc1b322 Mon Sep 17 00:00:00 2001
From: Mengyuan Lou <mengyuanlou@net-swift.com>
Date: Fri, 15 Nov 2024 10:46:04 +0800
Subject: [PATCH 1156/1530] PCI: Add ACS quirk for Wangxun FF5xxx NICs

Wangxun FF5xxx NICs are similar to SFxxx, RP1000 and RP2000 NICs.  They may
be multi-function devices, but they do not advertise an ACS capability.

But the hardware does isolate FF5xxx functions as though it had an ACS
capability and PCI_ACS_RR and PCI_ACS_CR were set in the ACS Control
register, i.e., all peer-to-peer traffic is directed upstream instead of
being routed internally.

Add ACS quirk for FF5xxx NICs in pci_quirk_wangxun_nic_acs() so the
functions can be in independent IOMMU groups.

Link: https://lore.kernel.org/r/E16053DB2B80E9A5+20241115024604.30493-1-mengyuanlou@net-swift.com
Signed-off-by: Mengyuan Lou <mengyuanlou@net-swift.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/quirks.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index dccb60c1d9cc3..8103bc24a54ea 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -4996,18 +4996,21 @@ static int pci_quirk_brcm_acs(struct pci_dev *dev, u16 acs_flags)
 }
 
 /*
- * Wangxun 10G/1G NICs have no ACS capability, and on multi-function
- * devices, peer-to-peer transactions are not be used between the functions.
- * So add an ACS quirk for below devices to isolate functions.
+ * Wangxun 40G/25G/10G/1G NICs have no ACS capability, but on
+ * multi-function devices, the hardware isolates the functions by
+ * directing all peer-to-peer traffic upstream as though PCI_ACS_RR and
+ * PCI_ACS_CR were set.
  * SFxxx 1G NICs(em).
  * RP1000/RP2000 10G NICs(sp).
+ * FF5xxx 40G/25G/10G NICs(aml).
  */
 static int  pci_quirk_wangxun_nic_acs(struct pci_dev *dev, u16 acs_flags)
 {
 	switch (dev->device) {
-	case 0x0100 ... 0x010F:
-	case 0x1001:
-	case 0x2001:
+	case 0x0100 ... 0x010F: /* EM */
+	case 0x1001: case 0x2001: /* SP */
+	case 0x5010: case 0x5025: case 0x5040: /* AML */
+	case 0x5110: case 0x5125: case 0x5140: /* AML */
 		return pci_acs_ctrl_enabled(acs_flags,
 			PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
 	}

From 587b67cf62a91b10a47f41c20ed8ad71db375334 Mon Sep 17 00:00:00 2001
From: Joe Hattori <joe@pf.is.s.u-tokyo.ac.jp>
Date: Fri, 8 Nov 2024 13:13:53 +0900
Subject: [PATCH 1157/1530] remoteproc: qcom: pas: Remove subdevs on the error
 path of adsp_probe()

Current implementation of adsp_probe() in qcom_q6v5_pas.c does not
remove the subdevs of adsp on the error path. Fix this bug by calling
qcom_remove_{ssr,sysmon,pdm,smd,glink}_subdev(), qcom_q6v5_deinit(), and
adsp_unassign_memory_region() appropriately.

Fixes: 4b48921a8f74 ("remoteproc: qcom: Use common SMD edge handler")
Signed-off-by: Joe Hattori <joe@pf.is.s.u-tokyo.ac.jp>
Link: https://lore.kernel.org/r/a1cabc64240022a7f1d5237aa2aa6f72d8fb7052.1731038950.git.joe@pf.is.s.u-tokyo.ac.jp
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_pas.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
index 297ef0c69054d..45112fddd9a73 100644
--- a/drivers/remoteproc/qcom_q6v5_pas.c
+++ b/drivers/remoteproc/qcom_q6v5_pas.c
@@ -759,16 +759,16 @@ static int adsp_probe(struct platform_device *pdev)
 
 	ret = adsp_init_clock(adsp);
 	if (ret)
-		goto free_rproc;
+		goto unassign_mem;
 
 	ret = adsp_init_regulator(adsp);
 	if (ret)
-		goto free_rproc;
+		goto unassign_mem;
 
 	ret = adsp_pds_attach(&pdev->dev, adsp->proxy_pds,
 			      desc->proxy_pd_names);
 	if (ret < 0)
-		goto free_rproc;
+		goto unassign_mem;
 	adsp->proxy_pd_count = ret;
 
 	ret = qcom_q6v5_init(&adsp->q6v5, pdev, rproc, desc->crash_reason_smem, desc->load_state,
@@ -784,18 +784,28 @@ static int adsp_probe(struct platform_device *pdev)
 					      desc->ssctl_id);
 	if (IS_ERR(adsp->sysmon)) {
 		ret = PTR_ERR(adsp->sysmon);
-		goto detach_proxy_pds;
+		goto deinit_remove_pdm_smd_glink;
 	}
 
 	qcom_add_ssr_subdev(rproc, &adsp->ssr_subdev, desc->ssr_name);
 	ret = rproc_add(rproc);
 	if (ret)
-		goto detach_proxy_pds;
+		goto remove_ssr_sysmon;
 
 	return 0;
 
+remove_ssr_sysmon:
+	qcom_remove_ssr_subdev(rproc, &adsp->ssr_subdev);
+	qcom_remove_sysmon_subdev(adsp->sysmon);
+deinit_remove_pdm_smd_glink:
+	qcom_remove_pdm_subdev(rproc, &adsp->pdm_subdev);
+	qcom_remove_smd_subdev(rproc, &adsp->smd_subdev);
+	qcom_remove_glink_subdev(rproc, &adsp->glink_subdev);
+	qcom_q6v5_deinit(&adsp->q6v5);
 detach_proxy_pds:
 	adsp_pds_detach(adsp, adsp->proxy_pds, adsp->proxy_pd_count);
+unassign_mem:
+	adsp_unassign_memory_region(adsp);
 free_rproc:
 	device_init_wakeup(adsp->dev, false);
 

From fe80d3205e91e36e67f4d3d6c326793298d15766 Mon Sep 17 00:00:00 2001
From: Joe Hattori <joe@pf.is.s.u-tokyo.ac.jp>
Date: Fri, 8 Nov 2024 13:13:54 +0900
Subject: [PATCH 1158/1530] remoteproc: qcom: adsp: Remove subdevs on the error
 path of adsp_probe()

Current implementation of adsp_probe() in qcom_q6v5_adsp.c and does not
remove the subdevs of adsp on the error path. Fix this bug by calling
qcom_remove_{ssr,sysmon,pdm,smd,glink}_subdev(), and qcom_q6v5_deinit()
appropriately.

Fixes: dc160e449122 ("remoteproc: qcom: Introduce Non-PAS ADSP PIL driver")
Signed-off-by: Joe Hattori <joe@pf.is.s.u-tokyo.ac.jp>
Link: https://lore.kernel.org/r/fed3df4219543d46b88bacf87990d947f3fac8d7.1731038950.git.joe@pf.is.s.u-tokyo.ac.jp
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_adsp.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/remoteproc/qcom_q6v5_adsp.c b/drivers/remoteproc/qcom_q6v5_adsp.c
index cbd9a914880ba..5aa11ca41c7d8 100644
--- a/drivers/remoteproc/qcom_q6v5_adsp.c
+++ b/drivers/remoteproc/qcom_q6v5_adsp.c
@@ -734,15 +734,22 @@ static int adsp_probe(struct platform_device *pdev)
 					      desc->ssctl_id);
 	if (IS_ERR(adsp->sysmon)) {
 		ret = PTR_ERR(adsp->sysmon);
-		goto disable_pm;
+		goto deinit_remove_glink_pdm_ssr;
 	}
 
 	ret = rproc_add(rproc);
 	if (ret)
-		goto disable_pm;
+		goto remove_sysmon;
 
 	return 0;
 
+remove_sysmon:
+	qcom_remove_sysmon_subdev(adsp->sysmon);
+deinit_remove_glink_pdm_ssr:
+	qcom_q6v5_deinit(&adsp->q6v5);
+	qcom_remove_glink_subdev(rproc, &adsp->glink_subdev);
+	qcom_remove_pdm_subdev(rproc, &adsp->pdm_subdev);
+	qcom_remove_ssr_subdev(rproc, &adsp->ssr_subdev);
 disable_pm:
 	qcom_rproc_pds_detach(adsp);
 

From 60e7c43e61c9a64253fc90f54fee0c92b3d1e3fe Mon Sep 17 00:00:00 2001
From: Joe Hattori <joe@pf.is.s.u-tokyo.ac.jp>
Date: Fri, 8 Nov 2024 13:13:55 +0900
Subject: [PATCH 1159/1530] remoteproc: qcom: wcss: Remove subdevs on the error
 path of q6v5_wcss_probe()

Current implementation of q6v5_wcss_probe() in qcom_q6v5_wcss.c and does
not remove the subdevs on the error path. Fix this bug by calling
qcom_remove_{ssr,sysmon,pdm,glink}_subdev(), and qcom_q6v5_deinit()
appropriately.

Signed-off-by: Joe Hattori <joe@pf.is.s.u-tokyo.ac.jp>
Link: https://lore.kernel.org/r/c4437393bfaeda69351157849b5e0a904586b1c2.1731038950.git.joe@pf.is.s.u-tokyo.ac.jp
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_wcss.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/remoteproc/qcom_q6v5_wcss.c b/drivers/remoteproc/qcom_q6v5_wcss.c
index 810441f43396f..f869187e8e77b 100644
--- a/drivers/remoteproc/qcom_q6v5_wcss.c
+++ b/drivers/remoteproc/qcom_q6v5_wcss.c
@@ -1056,18 +1056,33 @@ static int q6v5_wcss_probe(struct platform_device *pdev)
 	qcom_add_pdm_subdev(rproc, &wcss->pdm_subdev);
 	qcom_add_ssr_subdev(rproc, &wcss->ssr_subdev, "q6wcss");
 
-	if (desc->ssctl_id)
+	if (desc->ssctl_id) {
 		wcss->sysmon = qcom_add_sysmon_subdev(rproc,
 						      desc->sysmon_name,
 						      desc->ssctl_id);
+		if (IS_ERR(wcss->sysmon)) {
+			ret = PTR_ERR(wcss->sysmon);
+			goto deinit_remove_subdevs;
+		}
+	}
 
 	ret = rproc_add(rproc);
 	if (ret)
-		return ret;
+		goto remove_sysmon_subdev;
 
 	platform_set_drvdata(pdev, rproc);
 
 	return 0;
+
+remove_sysmon_subdev:
+	if (desc->ssctl_id)
+		qcom_remove_sysmon_subdev(wcss->sysmon);
+deinit_remove_subdevs:
+	qcom_q6v5_deinit(&wcss->q6v5);
+	qcom_remove_glink_subdev(rproc, &wcss->glink_subdev);
+	qcom_remove_pdm_subdev(rproc, &wcss->pdm_subdev);
+	qcom_remove_ssr_subdev(rproc, &wcss->ssr_subdev);
+	return ret;
 }
 
 static void q6v5_wcss_remove(struct platform_device *pdev)

From ec257dd3d36b49f34bf29551d2964f7a0cd6be66 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 1 Nov 2024 18:03:09 +0100
Subject: [PATCH 1160/1530] dt-bindings: remoteproc: qcom,sm8550-pas: Add
 SM8750 ADSP

Document compatible for Qualcomm SM8750 SoC ADSP PAS which looks fully
compatible with SM8550 variant.  The only difference from bindings point
of view is one more interrupt ("shutdown-ack").  Marking devices as
compatible, using SM8550 ADSP PAS fallback, requires changing some of
the conditionals in "if:then:" to "contains".

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Melody Olvera <quic_molvera@quicinc.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20241101170309.382782-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 .../bindings/remoteproc/qcom,sm8550-pas.yaml  | 48 +++++++++++++------
 1 file changed, 34 insertions(+), 14 deletions(-)

diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,sm8550-pas.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,sm8550-pas.yaml
index d7fad7b3c2c68..a24cbb61bda7d 100644
--- a/Documentation/devicetree/bindings/remoteproc/qcom,sm8550-pas.yaml
+++ b/Documentation/devicetree/bindings/remoteproc/qcom,sm8550-pas.yaml
@@ -15,16 +15,20 @@ description:
 
 properties:
   compatible:
-    enum:
-      - qcom,sdx75-mpss-pas
-      - qcom,sm8550-adsp-pas
-      - qcom,sm8550-cdsp-pas
-      - qcom,sm8550-mpss-pas
-      - qcom,sm8650-adsp-pas
-      - qcom,sm8650-cdsp-pas
-      - qcom,sm8650-mpss-pas
-      - qcom,x1e80100-adsp-pas
-      - qcom,x1e80100-cdsp-pas
+    oneOf:
+      - enum:
+          - qcom,sdx75-mpss-pas
+          - qcom,sm8550-adsp-pas
+          - qcom,sm8550-cdsp-pas
+          - qcom,sm8550-mpss-pas
+          - qcom,sm8650-adsp-pas
+          - qcom,sm8650-cdsp-pas
+          - qcom,sm8650-mpss-pas
+          - qcom,x1e80100-adsp-pas
+          - qcom,x1e80100-cdsp-pas
+      - items:
+          - const: qcom,sm8750-adsp-pas
+          - const: qcom,sm8550-adsp-pas
 
   reg:
     maxItems: 1
@@ -82,6 +86,20 @@ allOf:
           maxItems: 5
         memory-region:
           maxItems: 2
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,sm8750-adsp-pas
+    then:
+      properties:
+        interrupts:
+          maxItems: 6
+        interrupt-names:
+          maxItems: 6
+        memory-region:
+          maxItems: 2
   - if:
       properties:
         compatible:
@@ -129,10 +147,12 @@ allOf:
   - if:
       properties:
         compatible:
-          enum:
-            - qcom,sm8550-adsp-pas
-            - qcom,sm8650-adsp-pas
-            - qcom,x1e80100-adsp-pas
+          contains:
+            enum:
+              - qcom,sm8550-adsp-pas
+              - qcom,sm8650-adsp-pas
+              - qcom,sm8750-adsp-pas
+              - qcom,x1e80100-adsp-pas
     then:
       properties:
         power-domains:

From e45dd409a81a5f6f5e2b2337b0e10091f054fe11 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Sun, 27 Oct 2024 01:09:43 +0300
Subject: [PATCH 1161/1530] dt-bindings: remoteproc: qcom,sm8350-pas: add
 SAR2130P aDSP compatible

Document compatible for audio DSP on Qualcomm SAR2130P platform.

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20241027-sar2130p-adsp-v1-1-bd204e39d24e@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 .../devicetree/bindings/remoteproc/qcom,sm8350-pas.yaml        | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,sm8350-pas.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,sm8350-pas.yaml
index 4b9fb74fb9e96..fd3423e6051bc 100644
--- a/Documentation/devicetree/bindings/remoteproc/qcom,sm8350-pas.yaml
+++ b/Documentation/devicetree/bindings/remoteproc/qcom,sm8350-pas.yaml
@@ -16,6 +16,7 @@ description:
 properties:
   compatible:
     enum:
+      - qcom,sar2130p-adsp-pas
       - qcom,sm8350-adsp-pas
       - qcom,sm8350-cdsp-pas
       - qcom,sm8350-slpi-pas
@@ -61,6 +62,7 @@ allOf:
       properties:
         compatible:
           enum:
+            - qcom,sar2130p-adsp-pas
             - qcom,sm8350-adsp-pas
             - qcom,sm8350-cdsp-pas
             - qcom,sm8350-slpi-pas
@@ -101,6 +103,7 @@ allOf:
       properties:
         compatible:
           enum:
+            - qcom,sar2130p-adsp-pas
             - qcom,sm8350-adsp-pas
             - qcom,sm8350-slpi-pas
             - qcom,sm8450-adsp-pas

From e8983156d54f59f57e648ecd44f01c16572da842 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Sun, 27 Oct 2024 01:09:44 +0300
Subject: [PATCH 1162/1530] remoteproc: qcom: pas: add minidump_id to SM8350
 resources

Specify minidump_id for the SM8350 DSPs. It was omitted for in the
original commit e8b4e9a21af7 ("remoteproc: qcom: pas: Add SM8350 PAS
remoteprocs").

Fixes: e8b4e9a21af7 ("remoteproc: qcom: pas: Add SM8350 PAS remoteprocs")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20241027-sar2130p-adsp-v1-2-bd204e39d24e@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_pas.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
index 45112fddd9a73..822cf102ad360 100644
--- a/drivers/remoteproc/qcom_q6v5_pas.c
+++ b/drivers/remoteproc/qcom_q6v5_pas.c
@@ -917,6 +917,7 @@ static const struct adsp_data sm8250_adsp_resource = {
 	.crash_reason_smem = 423,
 	.firmware_name = "adsp.mdt",
 	.pas_id = 1,
+	.minidump_id = 5,
 	.auto_boot = true,
 	.proxy_pd_names = (char*[]){
 		"lcx",
@@ -1134,6 +1135,7 @@ static const struct adsp_data sm8350_cdsp_resource = {
 	.crash_reason_smem = 601,
 	.firmware_name = "cdsp.mdt",
 	.pas_id = 18,
+	.minidump_id = 7,
 	.auto_boot = true,
 	.proxy_pd_names = (char*[]){
 		"cx",

From 009e288c989b3fe548a45c82da407d7bd00418a9 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Sun, 27 Oct 2024 01:09:45 +0300
Subject: [PATCH 1163/1530] remoteproc: qcom: pas: enable SAR2130P audio DSP
 support

Enable support for the Audio DSP on the Qualcomm SAR2130P platform,
reusing the SM8350 resources.

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20241027-sar2130p-adsp-v1-3-bd204e39d24e@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_pas.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
index 822cf102ad360..566eddf232d38 100644
--- a/drivers/remoteproc/qcom_q6v5_pas.c
+++ b/drivers/remoteproc/qcom_q6v5_pas.c
@@ -1433,6 +1433,7 @@ static const struct of_device_id adsp_of_match[] = {
 	{ .compatible = "qcom,sa8775p-cdsp1-pas", .data = &sa8775p_cdsp1_resource},
 	{ .compatible = "qcom,sa8775p-gpdsp0-pas", .data = &sa8775p_gpdsp0_resource},
 	{ .compatible = "qcom,sa8775p-gpdsp1-pas", .data = &sa8775p_gpdsp1_resource},
+	{ .compatible = "qcom,sar2130p-adsp-pas", .data = &sm8350_adsp_resource},
 	{ .compatible = "qcom,sc7180-adsp-pas", .data = &sm8250_adsp_resource},
 	{ .compatible = "qcom,sc7180-mpss-pas", .data = &mpss_resource_init},
 	{ .compatible = "qcom,sc7280-adsp-pas", .data = &sm8350_adsp_resource},

From b64b1266d6195d9bbfa75a93b4265fba2d447c86 Mon Sep 17 00:00:00 2001
From: Bjorn Andersson <bjorn.andersson@oss.qualcomm.com>
Date: Tue, 22 Oct 2024 04:21:03 +0000
Subject: [PATCH 1164/1530] remoteproc: qcom: pas: Make remoteproc name human
 friendly

The remoteproc "name" property is supposed to present the "human
readable" name of the remoteproc, while using the device name is
readable, it's not "friendly".

Instead, use the "sysmon_name" as the identifier for the remoteproc
instance. It matches the typical names used when we speak about each
instance, while still being unique.

Signed-off-by: Bjorn Andersson <bjorn.andersson@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Chris Lew <quic_clew@quicinc.com>
Link: https://lore.kernel.org/r/20241022-rproc-friendly-name-v1-1-350c82b075cb@oss.qualcomm.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_pas.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
index 566eddf232d38..5034d214ac133 100644
--- a/drivers/remoteproc/qcom_q6v5_pas.c
+++ b/drivers/remoteproc/qcom_q6v5_pas.c
@@ -716,7 +716,7 @@ static int adsp_probe(struct platform_device *pdev)
 	if (desc->minidump_id)
 		ops = &adsp_minidump_ops;
 
-	rproc = devm_rproc_alloc(&pdev->dev, pdev->name, ops, fw_name, sizeof(*adsp));
+	rproc = devm_rproc_alloc(&pdev->dev, desc->sysmon_name, ops, fw_name, sizeof(*adsp));
 
 	if (!rproc) {
 		dev_err(&pdev->dev, "unable to allocate remoteproc\n");

From 8a47704d64c9afda80e7f399ba2cf898cfcc45b2 Mon Sep 17 00:00:00 2001
From: Balaji Pothunoori <quic_bpothuno@quicinc.com>
Date: Fri, 18 Oct 2024 16:29:11 +0530
Subject: [PATCH 1165/1530] remoteproc: qcom_q6v5_pas: disable auto boot for
 wpss

Currently, the rproc "atomic_t power" variable is incremented during:
a. WPSS rproc auto boot.
b. AHB power on for ath11k.

During AHB power off (rmmod ath11k_ahb.ko), rproc_shutdown fails
to unload the WPSS firmware because the rproc->power value is '2',
causing the atomic_dec_and_test(&rproc->power) condition to fail.

Consequently, during AHB power on (insmod ath11k_ahb.ko),
QMI_WLANFW_HOST_CAP_REQ_V01 fails due to the host and firmware QMI
states being out of sync.

Fixes: 300ed425dfa9 ("remoteproc: qcom_q6v5_pas: Add SC7280 ADSP, CDSP & WPSS")
Cc: stable@vger.kernel.org
Signed-off-by: Balaji Pothunoori <quic_bpothuno@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20241018105911.165415-1-quic_bpothuno@quicinc.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_pas.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
index 5034d214ac133..96da94b5d2c2d 100644
--- a/drivers/remoteproc/qcom_q6v5_pas.c
+++ b/drivers/remoteproc/qcom_q6v5_pas.c
@@ -1356,7 +1356,7 @@ static const struct adsp_data sc7280_wpss_resource = {
 	.crash_reason_smem = 626,
 	.firmware_name = "wpss.mdt",
 	.pas_id = 6,
-	.auto_boot = true,
+	.auto_boot = false,
 	.proxy_pd_names = (char*[]){
 		"cx",
 		"mx",

From 85865e839049c5d443eef4279d711bc292bee84c Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 11 Oct 2024 15:09:13 +0200
Subject: [PATCH 1166/1530] remoteproc: qcom_q6v5_adsp: Simplify with
 dev_err_probe()

Use dev_err_probe() to make error and defer code handling simpler.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20241011-remote-proc-dev-err-probe-v1-5-5abb4fc61eca@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_adsp.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/remoteproc/qcom_q6v5_adsp.c b/drivers/remoteproc/qcom_q6v5_adsp.c
index 5aa11ca41c7d8..94af77baa7a1c 100644
--- a/drivers/remoteproc/qcom_q6v5_adsp.c
+++ b/drivers/remoteproc/qcom_q6v5_adsp.c
@@ -534,15 +534,11 @@ static const struct rproc_ops adsp_ops = {
 static int adsp_init_clock(struct qcom_adsp *adsp, const char **clk_ids)
 {
 	int num_clks = 0;
-	int i, ret;
+	int i;
 
 	adsp->xo = devm_clk_get(adsp->dev, "xo");
-	if (IS_ERR(adsp->xo)) {
-		ret = PTR_ERR(adsp->xo);
-		if (ret != -EPROBE_DEFER)
-			dev_err(adsp->dev, "failed to get xo clock");
-		return ret;
-	}
+	if (IS_ERR(adsp->xo))
+		return dev_err_probe(adsp->dev, PTR_ERR(adsp->xo), "failed to get xo clock");
 
 	for (i = 0; clk_ids[i]; i++)
 		num_clks++;
@@ -708,10 +704,9 @@ static int adsp_probe(struct platform_device *pdev)
 		return ret;
 
 	ret = qcom_rproc_pds_attach(adsp, desc->pd_names, desc->num_pds);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to attach proxy power domains\n");
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "Failed to attach proxy power domains\n");
 
 	ret = adsp_init_reset(adsp);
 	if (ret)

From 63b07ee3377b8c4ce7f8aa678c80d78c2526bb28 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 11 Oct 2024 15:09:14 +0200
Subject: [PATCH 1167/1530] remoteproc: qcom_q6v5_mss: Simplify with
 dev_err_probe()

Use dev_err_probe() to make error and defer code handling simpler.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20241011-remote-proc-dev-err-probe-v1-6-5abb4fc61eca@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_mss.c | 24 ++++++++----------------
 1 file changed, 8 insertions(+), 16 deletions(-)

diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c
index 103368d11a96e..8f19086773966 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -261,7 +261,6 @@ enum {
 static int q6v5_regulator_init(struct device *dev, struct reg_info *regs,
 			       const struct qcom_mss_reg_res *reg_res)
 {
-	int rc;
 	int i;
 
 	if (!reg_res)
@@ -269,13 +268,10 @@ static int q6v5_regulator_init(struct device *dev, struct reg_info *regs,
 
 	for (i = 0; reg_res[i].supply; i++) {
 		regs[i].reg = devm_regulator_get(dev, reg_res[i].supply);
-		if (IS_ERR(regs[i].reg)) {
-			rc = PTR_ERR(regs[i].reg);
-			if (rc != -EPROBE_DEFER)
-				dev_err(dev, "Failed to get %s\n regulator",
-					reg_res[i].supply);
-			return rc;
-		}
+		if (IS_ERR(regs[i].reg))
+			return dev_err_probe(dev, PTR_ERR(regs[i].reg),
+					     "Failed to get %s\n regulator",
+					     reg_res[i].supply);
 
 		regs[i].uV = reg_res[i].uV;
 		regs[i].uA = reg_res[i].uA;
@@ -1813,14 +1809,10 @@ static int q6v5_init_clocks(struct device *dev, struct clk **clks,
 
 	for (i = 0; clk_names[i]; i++) {
 		clks[i] = devm_clk_get(dev, clk_names[i]);
-		if (IS_ERR(clks[i])) {
-			int rc = PTR_ERR(clks[i]);
-
-			if (rc != -EPROBE_DEFER)
-				dev_err(dev, "Failed to get %s clock\n",
-					clk_names[i]);
-			return rc;
-		}
+		if (IS_ERR(clks[i]))
+			return dev_err_probe(dev, PTR_ERR(clks[i]),
+					     "Failed to get %s clock\n",
+					     clk_names[i]);
 	}
 
 	return i;

From 576dac284e7168307169f62d3f3f1a98235a2d2d Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 11 Oct 2024 15:09:15 +0200
Subject: [PATCH 1168/1530] remoteproc: qcom_q6v5_mss: Drop redundant error
 printks in probe

Do not print errors of getting clocks and regulators in probe twice:
once in q6v5_init_clocks() or q6v5_regulator_init() and then again in the
probe function.  This also avoids dmesg flood on deferred probe.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20241011-remote-proc-dev-err-probe-v1-7-5abb4fc61eca@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_mss.c | 24 ++++++------------------
 1 file changed, 6 insertions(+), 18 deletions(-)

diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c
index 8f19086773966..aaddbaf1099e4 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -2020,42 +2020,32 @@ static int q6v5_probe(struct platform_device *pdev)
 
 	ret = q6v5_init_clocks(&pdev->dev, qproc->proxy_clks,
 			       desc->proxy_clk_names);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to get proxy clocks.\n");
+	if (ret < 0)
 		return ret;
-	}
 	qproc->proxy_clk_count = ret;
 
 	ret = q6v5_init_clocks(&pdev->dev, qproc->reset_clks,
 			       desc->reset_clk_names);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to get reset clocks.\n");
+	if (ret < 0)
 		return ret;
-	}
 	qproc->reset_clk_count = ret;
 
 	ret = q6v5_init_clocks(&pdev->dev, qproc->active_clks,
 			       desc->active_clk_names);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to get active clocks.\n");
+	if (ret < 0)
 		return ret;
-	}
 	qproc->active_clk_count = ret;
 
 	ret = q6v5_regulator_init(&pdev->dev, qproc->proxy_regs,
 				  desc->proxy_supply);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to get proxy regulators.\n");
+	if (ret < 0)
 		return ret;
-	}
 	qproc->proxy_reg_count = ret;
 
 	ret = q6v5_regulator_init(&pdev->dev,  qproc->active_regs,
 				  desc->active_supply);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to get active regulators.\n");
+	if (ret < 0)
 		return ret;
-	}
 	qproc->active_reg_count = ret;
 
 	ret = q6v5_pds_attach(&pdev->dev, qproc->proxy_pds,
@@ -2065,10 +2055,8 @@ static int q6v5_probe(struct platform_device *pdev)
 		ret = q6v5_regulator_init(&pdev->dev,
 					  qproc->fallback_proxy_regs,
 					  desc->fallback_proxy_supply);
-		if (ret < 0) {
-			dev_err(&pdev->dev, "Failed to get fallback proxy regulators.\n");
+		if (ret < 0)
 			return ret;
-		}
 		qproc->fallback_proxy_reg_count = ret;
 	} else if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to init power domains\n");

From 427442e873d7af7a06ff4382b57197f43afa8ed4 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 11 Oct 2024 15:09:16 +0200
Subject: [PATCH 1169/1530] remoteproc: qcom_q6v5_pas: Simplify with
 dev_err_probe()

Use dev_err_probe() to make error and defer code handling simpler.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20241011-remote-proc-dev-err-probe-v1-8-5abb4fc61eca@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_pas.c | 22 +++++++---------------
 1 file changed, 7 insertions(+), 15 deletions(-)

diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
index 96da94b5d2c2d..97c4bdd9222a8 100644
--- a/drivers/remoteproc/qcom_q6v5_pas.c
+++ b/drivers/remoteproc/qcom_q6v5_pas.c
@@ -453,24 +453,16 @@ static const struct rproc_ops adsp_minidump_ops = {
 
 static int adsp_init_clock(struct qcom_adsp *adsp)
 {
-	int ret;
-
 	adsp->xo = devm_clk_get(adsp->dev, "xo");
-	if (IS_ERR(adsp->xo)) {
-		ret = PTR_ERR(adsp->xo);
-		if (ret != -EPROBE_DEFER)
-			dev_err(adsp->dev, "failed to get xo clock");
-		return ret;
-	}
+	if (IS_ERR(adsp->xo))
+		return dev_err_probe(adsp->dev, PTR_ERR(adsp->xo),
+				     "failed to get xo clock");
+
 
 	adsp->aggre2_clk = devm_clk_get_optional(adsp->dev, "aggre2");
-	if (IS_ERR(adsp->aggre2_clk)) {
-		ret = PTR_ERR(adsp->aggre2_clk);
-		if (ret != -EPROBE_DEFER)
-			dev_err(adsp->dev,
-				"failed to get aggre2 clock");
-		return ret;
-	}
+	if (IS_ERR(adsp->aggre2_clk))
+		return dev_err_probe(adsp->dev, PTR_ERR(adsp->aggre2_clk),
+				     "failed to get aggre2 clock");
 
 	return 0;
 }

From f21e504de8eaf30b534e2b7db25d140842a920ed Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 11 Oct 2024 15:09:17 +0200
Subject: [PATCH 1170/1530] remoteproc: qcom_q6v5_wcss: Simplify with
 dev_err_probe()

Use dev_err_probe() to make error and defer code handling simpler.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20241011-remote-proc-dev-err-probe-v1-9-5abb4fc61eca@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_wcss.c | 92 ++++++++++-------------------
 1 file changed, 30 insertions(+), 62 deletions(-)

diff --git a/drivers/remoteproc/qcom_q6v5_wcss.c b/drivers/remoteproc/qcom_q6v5_wcss.c
index f869187e8e77b..93ddff437bf83 100644
--- a/drivers/remoteproc/qcom_q6v5_wcss.c
+++ b/drivers/remoteproc/qcom_q6v5_wcss.c
@@ -902,90 +902,58 @@ static int q6v5_alloc_memory_region(struct q6v5_wcss *wcss)
 
 static int q6v5_wcss_init_clock(struct q6v5_wcss *wcss)
 {
-	int ret;
-
 	wcss->xo = devm_clk_get(wcss->dev, "xo");
-	if (IS_ERR(wcss->xo)) {
-		ret = PTR_ERR(wcss->xo);
-		if (ret != -EPROBE_DEFER)
-			dev_err(wcss->dev, "failed to get xo clock");
-		return ret;
-	}
+	if (IS_ERR(wcss->xo))
+		return dev_err_probe(wcss->dev, PTR_ERR(wcss->xo),
+				     "failed to get xo clock");
 
 	wcss->gcc_abhs_cbcr = devm_clk_get(wcss->dev, "gcc_abhs_cbcr");
-	if (IS_ERR(wcss->gcc_abhs_cbcr)) {
-		ret = PTR_ERR(wcss->gcc_abhs_cbcr);
-		if (ret != -EPROBE_DEFER)
-			dev_err(wcss->dev, "failed to get gcc abhs clock");
-		return ret;
-	}
+	if (IS_ERR(wcss->gcc_abhs_cbcr))
+		return dev_err_probe(wcss->dev, PTR_ERR(wcss->gcc_abhs_cbcr),
+				     "failed to get gcc abhs clock");
 
 	wcss->gcc_axim_cbcr = devm_clk_get(wcss->dev, "gcc_axim_cbcr");
-	if (IS_ERR(wcss->gcc_axim_cbcr)) {
-		ret = PTR_ERR(wcss->gcc_axim_cbcr);
-		if (ret != -EPROBE_DEFER)
-			dev_err(wcss->dev, "failed to get gcc axim clock\n");
-		return ret;
-	}
+	if (IS_ERR(wcss->gcc_axim_cbcr))
+		return dev_err_probe(wcss->dev, PTR_ERR(wcss->gcc_axim_cbcr),
+				     "failed to get gcc axim clock\n");
 
 	wcss->ahbfabric_cbcr_clk = devm_clk_get(wcss->dev,
 						"lcc_ahbfabric_cbc");
-	if (IS_ERR(wcss->ahbfabric_cbcr_clk)) {
-		ret = PTR_ERR(wcss->ahbfabric_cbcr_clk);
-		if (ret != -EPROBE_DEFER)
-			dev_err(wcss->dev, "failed to get ahbfabric clock\n");
-		return ret;
-	}
+	if (IS_ERR(wcss->ahbfabric_cbcr_clk))
+		return dev_err_probe(wcss->dev, PTR_ERR(wcss->ahbfabric_cbcr_clk),
+				     "failed to get ahbfabric clock\n");
 
 	wcss->lcc_csr_cbcr = devm_clk_get(wcss->dev, "tcsr_lcc_cbc");
-	if (IS_ERR(wcss->lcc_csr_cbcr)) {
-		ret = PTR_ERR(wcss->lcc_csr_cbcr);
-		if (ret != -EPROBE_DEFER)
-			dev_err(wcss->dev, "failed to get csr cbcr clk\n");
-		return ret;
-	}
+	if (IS_ERR(wcss->lcc_csr_cbcr))
+		return dev_err_probe(wcss->dev, PTR_ERR(wcss->lcc_csr_cbcr),
+				     "failed to get csr cbcr clk\n");
 
 	wcss->ahbs_cbcr = devm_clk_get(wcss->dev,
 				       "lcc_abhs_cbc");
-	if (IS_ERR(wcss->ahbs_cbcr)) {
-		ret = PTR_ERR(wcss->ahbs_cbcr);
-		if (ret != -EPROBE_DEFER)
-			dev_err(wcss->dev, "failed to get ahbs_cbcr clk\n");
-		return ret;
-	}
+	if (IS_ERR(wcss->ahbs_cbcr))
+		return dev_err_probe(wcss->dev, PTR_ERR(wcss->ahbs_cbcr),
+				     "failed to get ahbs_cbcr clk\n");
 
 	wcss->tcm_slave_cbcr = devm_clk_get(wcss->dev,
 					    "lcc_tcm_slave_cbc");
-	if (IS_ERR(wcss->tcm_slave_cbcr)) {
-		ret = PTR_ERR(wcss->tcm_slave_cbcr);
-		if (ret != -EPROBE_DEFER)
-			dev_err(wcss->dev, "failed to get tcm cbcr clk\n");
-		return ret;
-	}
+	if (IS_ERR(wcss->tcm_slave_cbcr))
+		return dev_err_probe(wcss->dev, PTR_ERR(wcss->tcm_slave_cbcr),
+				     "failed to get tcm cbcr clk\n");
 
 	wcss->qdsp6ss_abhm_cbcr = devm_clk_get(wcss->dev, "lcc_abhm_cbc");
-	if (IS_ERR(wcss->qdsp6ss_abhm_cbcr)) {
-		ret = PTR_ERR(wcss->qdsp6ss_abhm_cbcr);
-		if (ret != -EPROBE_DEFER)
-			dev_err(wcss->dev, "failed to get abhm cbcr clk\n");
-		return ret;
-	}
+	if (IS_ERR(wcss->qdsp6ss_abhm_cbcr))
+		return dev_err_probe(wcss->dev, PTR_ERR(wcss->qdsp6ss_abhm_cbcr),
+				     "failed to get abhm cbcr clk\n");
 
 	wcss->qdsp6ss_axim_cbcr = devm_clk_get(wcss->dev, "lcc_axim_cbc");
-	if (IS_ERR(wcss->qdsp6ss_axim_cbcr)) {
-		ret = PTR_ERR(wcss->qdsp6ss_axim_cbcr);
-		if (ret != -EPROBE_DEFER)
-			dev_err(wcss->dev, "failed to get axim cbcr clk\n");
-		return ret;
-	}
+	if (IS_ERR(wcss->qdsp6ss_axim_cbcr))
+		return dev_err_probe(wcss->dev, PTR_ERR(wcss->qdsp6ss_axim_cbcr),
+				     "failed to get axim cbcr clk\n");
 
 	wcss->lcc_bcr_sleep = devm_clk_get(wcss->dev, "lcc_bcr_sleep");
-	if (IS_ERR(wcss->lcc_bcr_sleep)) {
-		ret = PTR_ERR(wcss->lcc_bcr_sleep);
-		if (ret != -EPROBE_DEFER)
-			dev_err(wcss->dev, "failed to get bcr cbcr clk\n");
-		return ret;
-	}
+	if (IS_ERR(wcss->lcc_bcr_sleep))
+		return dev_err_probe(wcss->dev, PTR_ERR(wcss->lcc_bcr_sleep),
+				     "failed to get bcr cbcr clk\n");
 
 	return 0;
 }

From 70d35819531875a14f12fe341486992676df5c6d Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 11 Oct 2024 15:09:18 +0200
Subject: [PATCH 1171/1530] remoteproc: qcom_wcnss_iris: Simplify with
 dev_err_probe()

Use dev_err_probe() to make error and defer code handling simpler.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20241011-remote-proc-dev-err-probe-v1-10-5abb4fc61eca@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_wcnss_iris.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/remoteproc/qcom_wcnss_iris.c b/drivers/remoteproc/qcom_wcnss_iris.c
index dd36fd077911a..b989718776bdb 100644
--- a/drivers/remoteproc/qcom_wcnss_iris.c
+++ b/drivers/remoteproc/qcom_wcnss_iris.c
@@ -155,9 +155,8 @@ struct qcom_iris *qcom_iris_probe(struct device *parent, bool *use_48mhz_xo)
 
 	iris->xo_clk = devm_clk_get(&iris->dev, "xo");
 	if (IS_ERR(iris->xo_clk)) {
-		ret = PTR_ERR(iris->xo_clk);
-		if (ret != -EPROBE_DEFER)
-			dev_err(&iris->dev, "failed to acquire xo clk\n");
+		ret = dev_err_probe(&iris->dev, PTR_ERR(iris->xo_clk),
+				    "failed to acquire xo clk\n");
 		goto err_device_del;
 	}
 

From 06c59d97f63c1b8af521fa5aef8a716fb988b285 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Mon, 7 Oct 2024 19:59:35 -0400
Subject: [PATCH 1172/1530] rpmsg: glink: use only lower 16-bits of param2 for
 CMD_OPEN name length

The name len field of the CMD_OPEN packet is only 16-bits and the upper
16-bits of "param2" are a different "prio" field, which can be nonzero in
certain situations, and CMD_OPEN packets can be unexpectedly dropped
because of this.

Fix this by masking out the upper 16 bits of param2.

Fixes: b4f8e52b89f6 ("rpmsg: Introduce Qualcomm RPM glink driver")
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20241007235935.6216-1-jonathan@marek.ca
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/rpmsg/qcom_glink_native.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/rpmsg/qcom_glink_native.c b/drivers/rpmsg/qcom_glink_native.c
index 0b2f290069080..b534b88db3f8e 100644
--- a/drivers/rpmsg/qcom_glink_native.c
+++ b/drivers/rpmsg/qcom_glink_native.c
@@ -1204,7 +1204,8 @@ void qcom_glink_native_rx(struct qcom_glink *glink)
 			ret = qcom_glink_rx_open_ack(glink, param1);
 			break;
 		case GLINK_CMD_OPEN:
-			ret = qcom_glink_rx_defer(glink, param2);
+			/* upper 16 bits of param2 are the "prio" field */
+			ret = qcom_glink_rx_defer(glink, param2 & 0xffff);
 			break;
 		case GLINK_CMD_TX_DATA:
 		case GLINK_CMD_TX_DATA_CONT:

From 7b22b7719fc17d5979a991c918c868ab041be5c8 Mon Sep 17 00:00:00 2001
From: Sibi Sankar <quic_sibis@quicinc.com>
Date: Mon, 19 Aug 2024 13:00:20 +0530
Subject: [PATCH 1173/1530] remoteproc: qcom_q6v5_mss: Re-order writes to the
 IMEM region

Any write access to the IMEM region when the Q6 is setting up XPU
protection on it will result in a XPU violation. Fix this by ensuring
IMEM writes related to the MBA post-mortem logs happen before the Q6
is brought out of reset.

Fixes: 318130cc9362 ("remoteproc: qcom_q6v5_mss: Add MBA log extraction support")
Signed-off-by: Sibi Sankar <quic_sibis@quicinc.com>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Tested-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/20240819073020.3291287-1-quic_sibis@quicinc.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_mss.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c
index aaddbaf1099e4..e78bd986dc3f2 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -1158,6 +1158,9 @@ static int q6v5_mba_load(struct q6v5 *qproc)
 		goto disable_active_clks;
 	}
 
+	if (qproc->has_mba_logs)
+		qcom_pil_info_store("mba", qproc->mba_phys, MBA_LOG_SIZE);
+
 	writel(qproc->mba_phys, qproc->rmb_base + RMB_MBA_IMAGE_REG);
 	if (qproc->dp_size) {
 		writel(qproc->mba_phys + SZ_1M, qproc->rmb_base + RMB_PMI_CODE_START_REG);
@@ -1168,9 +1171,6 @@ static int q6v5_mba_load(struct q6v5 *qproc)
 	if (ret)
 		goto reclaim_mba;
 
-	if (qproc->has_mba_logs)
-		qcom_pil_info_store("mba", qproc->mba_phys, MBA_LOG_SIZE);
-
 	ret = q6v5_rmb_mba_wait(qproc, 0, 5000);
 	if (ret == -ETIMEDOUT) {
 		dev_err(qproc->dev, "MBA boot timed out\n");

From 44024ebf25918efb8c771e1b496250bc9c4ef893 Mon Sep 17 00:00:00 2001
From: Yuesong Li <liyuesong@vivo.com>
Date: Fri, 23 Aug 2024 14:55:46 +0800
Subject: [PATCH 1174/1530] remoteproc: qcom: wcss: Remove double assignment in
 q6v5_wcss_probe()

cocci report a double assignment warning.'wcss->version' was assigned
twice in 'q6v5_wcss_probe()'.

Signed-off-by: Yuesong Li <liyuesong@vivo.com>
Link: https://lore.kernel.org/r/20240823065546.3371378-1-liyuesong@vivo.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_wcss.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/remoteproc/qcom_q6v5_wcss.c b/drivers/remoteproc/qcom_q6v5_wcss.c
index 93ddff437bf83..93648734a2f25 100644
--- a/drivers/remoteproc/qcom_q6v5_wcss.c
+++ b/drivers/remoteproc/qcom_q6v5_wcss.c
@@ -989,7 +989,6 @@ static int q6v5_wcss_probe(struct platform_device *pdev)
 
 	wcss = rproc->priv;
 	wcss->dev = &pdev->dev;
-	wcss->version = desc->version;
 
 	wcss->version = desc->version;
 	wcss->requires_force_stop = desc->requires_force_stop;

From 665745f274870c921020f610e2c99a3b1613519b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 18 Oct 2024 17:47:52 +0300
Subject: [PATCH 1175/1530] PCI/bwctrl: Re-add BW notification portdrv as PCIe
 BW controller
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This mostly reverts the commit b4c7d2076b4e ("PCI/LINK: Remove bandwidth
notification"). An upcoming commit extends this driver building PCIe
bandwidth controller on top of it.

PCIe bandwidth notifications were first added in the commit e8303bb7a75c
("PCI/LINK: Report degraded links via link bandwidth notification") but
later had to be removed. The significant changes compared with the old
bandwidth notification driver include:

1) Don't print the notifications into kernel log, just keep the Link
   Speed cached in struct pci_bus updated. While somewhat unfortunate,
   the log spam was the source of complaints that eventually lead to
   the removal of the bandwidth notifications driver (see the links
   below for further information).

2) Besides the Link Bandwidth Management Interrupt, also enable Link
   Autonomous Bandwidth Interrupt to cover the other source of bandwidth
   changes.

3) Handle Link Speed updates robustly. Refresh the cached Link Speed
   when enabling Bandwidth Notification Interrupts, and solve the race
   between Link Speed read and LBMS/LABS update in
   pcie_bwnotif_irq_thread().

4) Use concurrency safe LNKCTL RMW operations.

5) The driver is now called PCIe bwctrl (bandwidth controller) instead
   of just bandwidth notifications because of increased scope and
   functionality within the driver.

6) Coexist with the Target Link Speed quirk in pcie_failed_link_retrain().
   Provide LBMS counting API for it.

7) Tweaks to variable/functions names for consistency and length reasons.

Bandwidth Notifications enable the cur_bus_speed in the struct pci_bus to
keep track PCIe Link Speed changes.

[bhelgaas: This is based on previous work by Alexandru Gagniuc
<mr.nuke.me@gmail.com>; see e8303bb7a75c ("PCI/LINK: Report degraded links
via link bandwidth notification")]

Link: https://lore.kernel.org/r/20241018144755.7875-7-ilpo.jarvinen@linux.intel.com
Link: https://lore.kernel.org/all/20190429185611.121751-1-helgaas@kernel.org/
Link: https://lore.kernel.org/linux-pci/20190501142942.26972-1-keith.busch@intel.com/
Link: https://lore.kernel.org/linux-pci/20200115221008.GA191037@google.com/
Suggested-by: Lukas Wunner <lukas@wunner.de> # Building bwctrl on top of bwnotif
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
[bhelgaas: squash fix to drop IRQF_ONESHOT and convert to hardirq handler:
https://lore.kernel.org/r/20241115165717.15233-1-ilpo.jarvinen@linux.intel.com]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Stefan Wahren <wahrenst@gmx.net>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 MAINTAINERS                       |   6 +
 drivers/pci/hotplug/pciehp_ctrl.c |   5 +
 drivers/pci/pci.c                 |   2 +-
 drivers/pci/pci.h                 |  11 ++
 drivers/pci/pcie/Makefile         |   2 +-
 drivers/pci/pcie/bwctrl.c         | 186 ++++++++++++++++++++++++++++++
 drivers/pci/pcie/portdrv.c        |   9 +-
 drivers/pci/pcie/portdrv.h        |   6 +-
 drivers/pci/quirks.c              |   9 +-
 include/linux/pci.h               |   2 +
 10 files changed, 229 insertions(+), 9 deletions(-)
 create mode 100644 drivers/pci/pcie/bwctrl.c

diff --git a/MAINTAINERS b/MAINTAINERS
index c27f3190737f8..8c555b3325d65 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17933,6 +17933,12 @@ F:	include/linux/of_pci.h
 F:	include/linux/pci*
 F:	include/uapi/linux/pci*
 
+PCIE BANDWIDTH CONTROLLER
+M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
+L:	linux-pci@vger.kernel.org
+S:	Supported
+F:	drivers/pci/pcie/bwctrl.c
+
 PCIE DRIVER FOR AMAZON ANNAPURNA LABS
 M:	Jonathan Chocron <jonnyc@amazon.com>
 L:	linux-pci@vger.kernel.org
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index dcdbfcf404ddf..d603a7aa74838 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -19,6 +19,8 @@
 #include <linux/types.h>
 #include <linux/pm_runtime.h>
 #include <linux/pci.h>
+
+#include "../pci.h"
 #include "pciehp.h"
 
 /* The following routines constitute the bulk of the
@@ -127,6 +129,9 @@ static void remove_board(struct controller *ctrl, bool safe_removal)
 
 	pciehp_set_indicators(ctrl, PCI_EXP_SLTCTL_PWR_IND_OFF,
 			      INDICATOR_NOOP);
+
+	/* Don't carry LBMS indications across */
+	pcie_reset_lbms_count(ctrl->pcie->port);
 }
 
 static int pciehp_enable_slot(struct controller *ctrl);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 3d67e8b50ba2b..f85f380cdb9b3 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4740,7 +4740,7 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt)
 	 * to track link speed or width changes made by hardware itself
 	 * in attempt to correct unreliable link operation.
 	 */
-	pcie_capability_write_word(pdev, PCI_EXP_LNKSTA, PCI_EXP_LNKSTA_LBMS);
+	pcie_reset_lbms_count(pdev);
 	return rc;
 }
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 8137ad2fead88..8ec189c8f3f5a 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -698,6 +698,17 @@ static inline void pcie_set_ecrc_checking(struct pci_dev *dev) { }
 static inline void pcie_ecrc_get_policy(char *str) { }
 #endif
 
+#ifdef CONFIG_PCIEPORTBUS
+void pcie_reset_lbms_count(struct pci_dev *port);
+int pcie_lbms_count(struct pci_dev *port, unsigned long *val);
+#else
+static inline void pcie_reset_lbms_count(struct pci_dev *port) {}
+static inline int pcie_lbms_count(struct pci_dev *port, unsigned long *val)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 struct pci_dev_reset_methods {
 	u16 vendor;
 	u16 device;
diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile
index 6461aa93fe76e..53ccab62314d9 100644
--- a/drivers/pci/pcie/Makefile
+++ b/drivers/pci/pcie/Makefile
@@ -4,7 +4,7 @@
 
 pcieportdrv-y			:= portdrv.o rcec.o
 
-obj-$(CONFIG_PCIEPORTBUS)	+= pcieportdrv.o
+obj-$(CONFIG_PCIEPORTBUS)	+= pcieportdrv.o bwctrl.o
 
 obj-y				+= aspm.o
 obj-$(CONFIG_PCIEAER)		+= aer.o err.o
diff --git a/drivers/pci/pcie/bwctrl.c b/drivers/pci/pcie/bwctrl.c
new file mode 100644
index 0000000000000..b3da249002719
--- /dev/null
+++ b/drivers/pci/pcie/bwctrl.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * PCIe bandwidth controller
+ *
+ * Author: Alexandru Gagniuc <mr.nuke.me@gmail.com>
+ *
+ * Copyright (C) 2019 Dell Inc
+ * Copyright (C) 2023-2024 Intel Corporation
+ *
+ * This service port driver hooks into the Bandwidth Notification interrupt
+ * watching for changes or links becoming degraded in operation. It updates
+ * the cached Current Link Speed that is exposed to user space through sysfs.
+ */
+
+#define dev_fmt(fmt) "bwctrl: " fmt
+
+#include <linux/atomic.h>
+#include <linux/cleanup.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/rwsem.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include "../pci.h"
+#include "portdrv.h"
+
+/**
+ * struct pcie_bwctrl_data - PCIe bandwidth controller
+ * @lbms_count:		Count for LBMS (since last reset)
+ */
+struct pcie_bwctrl_data {
+	atomic_t lbms_count;
+};
+
+/* Prevents port removal during LBMS count accessors */
+static DECLARE_RWSEM(pcie_bwctrl_lbms_rwsem);
+
+static void pcie_bwnotif_enable(struct pcie_device *srv)
+{
+	struct pcie_bwctrl_data *data = srv->port->link_bwctrl;
+	struct pci_dev *port = srv->port;
+	u16 link_status;
+	int ret;
+
+	/* Count LBMS seen so far as one */
+	ret = pcie_capability_read_word(port, PCI_EXP_LNKSTA, &link_status);
+	if (ret == PCIBIOS_SUCCESSFUL && link_status & PCI_EXP_LNKSTA_LBMS)
+		atomic_inc(&data->lbms_count);
+
+	pcie_capability_set_word(port, PCI_EXP_LNKCTL,
+				 PCI_EXP_LNKCTL_LBMIE | PCI_EXP_LNKCTL_LABIE);
+	pcie_capability_write_word(port, PCI_EXP_LNKSTA,
+				   PCI_EXP_LNKSTA_LBMS | PCI_EXP_LNKSTA_LABS);
+
+	/*
+	 * Update after enabling notifications & clearing status bits ensures
+	 * link speed is up to date.
+	 */
+	pcie_update_link_speed(port->subordinate);
+}
+
+static void pcie_bwnotif_disable(struct pci_dev *port)
+{
+	pcie_capability_clear_word(port, PCI_EXP_LNKCTL,
+				   PCI_EXP_LNKCTL_LBMIE | PCI_EXP_LNKCTL_LABIE);
+}
+
+static irqreturn_t pcie_bwnotif_irq(int irq, void *context)
+{
+	struct pcie_device *srv = context;
+	struct pcie_bwctrl_data *data = srv->port->link_bwctrl;
+	struct pci_dev *port = srv->port;
+	u16 link_status, events;
+	int ret;
+
+	ret = pcie_capability_read_word(port, PCI_EXP_LNKSTA, &link_status);
+	if (ret != PCIBIOS_SUCCESSFUL)
+		return IRQ_NONE;
+
+	events = link_status & (PCI_EXP_LNKSTA_LBMS | PCI_EXP_LNKSTA_LABS);
+	if (!events)
+		return IRQ_NONE;
+
+	if (events & PCI_EXP_LNKSTA_LBMS)
+		atomic_inc(&data->lbms_count);
+
+	pcie_capability_write_word(port, PCI_EXP_LNKSTA, events);
+
+	/*
+	 * Interrupts will not be triggered from any further Link Speed
+	 * change until LBMS is cleared by the write. Therefore, re-read the
+	 * speed (inside pcie_update_link_speed()) after LBMS has been
+	 * cleared to avoid missing link speed changes.
+	 */
+	pcie_update_link_speed(port->subordinate);
+
+	return IRQ_HANDLED;
+}
+
+void pcie_reset_lbms_count(struct pci_dev *port)
+{
+	struct pcie_bwctrl_data *data;
+
+	guard(rwsem_read)(&pcie_bwctrl_lbms_rwsem);
+	data = port->link_bwctrl;
+	if (data)
+		atomic_set(&data->lbms_count, 0);
+	else
+		pcie_capability_write_word(port, PCI_EXP_LNKSTA,
+					   PCI_EXP_LNKSTA_LBMS);
+}
+
+int pcie_lbms_count(struct pci_dev *port, unsigned long *val)
+{
+	struct pcie_bwctrl_data *data;
+
+	guard(rwsem_read)(&pcie_bwctrl_lbms_rwsem);
+	data = port->link_bwctrl;
+	if (!data)
+		return -ENOTTY;
+
+	*val = atomic_read(&data->lbms_count);
+
+	return 0;
+}
+
+static int pcie_bwnotif_probe(struct pcie_device *srv)
+{
+	struct pci_dev *port = srv->port;
+	int ret;
+
+	struct pcie_bwctrl_data *data = devm_kzalloc(&srv->device,
+						     sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	ret = devm_request_irq(&srv->device, srv->irq, pcie_bwnotif_irq,
+			       IRQF_SHARED, "PCIe bwctrl", srv);
+	if (ret)
+		return ret;
+
+	scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) {
+		port->link_bwctrl = no_free_ptr(data);
+		pcie_bwnotif_enable(srv);
+	}
+
+	pci_dbg(port, "enabled with IRQ %d\n", srv->irq);
+
+	return 0;
+}
+
+static void pcie_bwnotif_remove(struct pcie_device *srv)
+{
+	pcie_bwnotif_disable(srv->port);
+	scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem)
+		srv->port->link_bwctrl = NULL;
+}
+
+static int pcie_bwnotif_suspend(struct pcie_device *srv)
+{
+	pcie_bwnotif_disable(srv->port);
+	return 0;
+}
+
+static int pcie_bwnotif_resume(struct pcie_device *srv)
+{
+	pcie_bwnotif_enable(srv);
+	return 0;
+}
+
+static struct pcie_port_service_driver pcie_bwctrl_driver = {
+	.name		= "pcie_bwctrl",
+	.port_type	= PCIE_ANY_PORT,
+	.service	= PCIE_PORT_SERVICE_BWCTRL,
+	.probe		= pcie_bwnotif_probe,
+	.suspend	= pcie_bwnotif_suspend,
+	.resume		= pcie_bwnotif_resume,
+	.remove		= pcie_bwnotif_remove,
+};
+
+int __init pcie_bwctrl_init(void)
+{
+	return pcie_port_service_register(&pcie_bwctrl_driver);
+}
diff --git a/drivers/pci/pcie/portdrv.c b/drivers/pci/pcie/portdrv.c
index 6af5e04258728..5e10306b63081 100644
--- a/drivers/pci/pcie/portdrv.c
+++ b/drivers/pci/pcie/portdrv.c
@@ -68,7 +68,7 @@ static int pcie_message_numbers(struct pci_dev *dev, int mask,
 	 */
 
 	if (mask & (PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP |
-		    PCIE_PORT_SERVICE_BWNOTIF)) {
+		    PCIE_PORT_SERVICE_BWCTRL)) {
 		pcie_capability_read_word(dev, PCI_EXP_FLAGS, &reg16);
 		*pme = FIELD_GET(PCI_EXP_FLAGS_IRQ, reg16);
 		nvec = *pme + 1;
@@ -150,11 +150,11 @@ static int pcie_port_enable_irq_vec(struct pci_dev *dev, int *irqs, int mask)
 
 	/* PME, hotplug and bandwidth notification share an MSI/MSI-X vector */
 	if (mask & (PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP |
-		    PCIE_PORT_SERVICE_BWNOTIF)) {
+		    PCIE_PORT_SERVICE_BWCTRL)) {
 		pcie_irq = pci_irq_vector(dev, pme);
 		irqs[PCIE_PORT_SERVICE_PME_SHIFT] = pcie_irq;
 		irqs[PCIE_PORT_SERVICE_HP_SHIFT] = pcie_irq;
-		irqs[PCIE_PORT_SERVICE_BWNOTIF_SHIFT] = pcie_irq;
+		irqs[PCIE_PORT_SERVICE_BWCTRL_SHIFT] = pcie_irq;
 	}
 
 	if (mask & PCIE_PORT_SERVICE_AER)
@@ -271,7 +271,7 @@ static int get_port_device_capability(struct pci_dev *dev)
 
 		pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &linkcap);
 		if (linkcap & PCI_EXP_LNKCAP_LBNC)
-			services |= PCIE_PORT_SERVICE_BWNOTIF;
+			services |= PCIE_PORT_SERVICE_BWCTRL;
 	}
 
 	return services;
@@ -828,6 +828,7 @@ static void __init pcie_init_services(void)
 	pcie_aer_init();
 	pcie_pme_init();
 	pcie_dpc_init();
+	pcie_bwctrl_init();
 	pcie_hp_init();
 }
 
diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h
index 12c89ea0313b9..bd29d1cc7b8bd 100644
--- a/drivers/pci/pcie/portdrv.h
+++ b/drivers/pci/pcie/portdrv.h
@@ -20,8 +20,8 @@
 #define PCIE_PORT_SERVICE_HP		(1 << PCIE_PORT_SERVICE_HP_SHIFT)
 #define PCIE_PORT_SERVICE_DPC_SHIFT	3	/* Downstream Port Containment */
 #define PCIE_PORT_SERVICE_DPC		(1 << PCIE_PORT_SERVICE_DPC_SHIFT)
-#define PCIE_PORT_SERVICE_BWNOTIF_SHIFT	4	/* Bandwidth notification */
-#define PCIE_PORT_SERVICE_BWNOTIF	(1 << PCIE_PORT_SERVICE_BWNOTIF_SHIFT)
+#define PCIE_PORT_SERVICE_BWCTRL_SHIFT	4	/* Bandwidth Controller (notifications) */
+#define PCIE_PORT_SERVICE_BWCTRL	(1 << PCIE_PORT_SERVICE_BWCTRL_SHIFT)
 
 #define PCIE_PORT_DEVICE_MAXSERVICES   5
 
@@ -51,6 +51,8 @@ int pcie_dpc_init(void);
 static inline int pcie_dpc_init(void) { return 0; }
 #endif
 
+int pcie_bwctrl_init(void);
+
 /* Port Type */
 #define PCIE_ANY_PORT			(~0)
 
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index a560ea403b8ef..e6d502dca9391 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -35,7 +35,14 @@
 
 static bool pcie_lbms_seen(struct pci_dev *dev, u16 lnksta)
 {
-	return lnksta & PCI_EXP_LNKSTA_LBMS;
+	unsigned long count;
+	int ret;
+
+	ret = pcie_lbms_count(dev, &count);
+	if (ret < 0)
+		return lnksta & PCI_EXP_LNKSTA_LBMS;
+
+	return count > 0;
 }
 
 /*
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 99c6fa30d25be..579b288334292 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -313,6 +313,7 @@ struct pci_vpd {
 };
 
 struct irq_affinity;
+struct pcie_bwctrl_data;
 struct pcie_link_state;
 struct pci_sriov;
 struct pci_p2pdma;
@@ -502,6 +503,7 @@ struct pci_dev {
 	unsigned int	dpc_rp_extensions:1;
 	u8		dpc_rp_log_size;
 #endif
+	struct pcie_bwctrl_data		*link_bwctrl;
 #ifdef CONFIG_PCI_ATS
 	union {
 		struct pci_sriov	*sriov;		/* PF: SR-IOV info */

From de9a6c8d5dbfedb5eb3722c822da0490f6a59a45 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 18 Oct 2024 17:47:53 +0300
Subject: [PATCH 1176/1530] PCI/bwctrl: Add pcie_set_target_speed() to set PCIe
 Link Speed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, PCIe Link Speeds are adjusted by custom code rather than in a
common function provided in PCI core. The PCIe bandwidth controller
(bwctrl) introduces an in-kernel API, pcie_set_target_speed(), to set PCIe
Link Speed.

Convert Target Speed quirk to use the new API. The Target Speed quirk runs
very early when bwctrl is not yet probed for a Port and can also run later
when bwctrl is already setup for the Port, which requires the per port
mutex (set_speed_mutex) to be only taken if the bwctrl setup is already
complete.

The new API is also intended to be used in an upcoming commit that adds a
thermal cooling device to throttle PCIe bandwidth when thermal thresholds
are reached.

The PCIe bandwidth control procedure is as follows. The highest speed
supported by the Port and the PCIe device which is not higher than the
requested speed is selected and written into the Target Link Speed in the
Link Control 2 Register. Then bandwidth controller retrains the PCIe Link.

Bandwidth Notifications enable the cur_bus_speed in the struct pci_bus to
keep track PCIe Link Speed changes. While Bandwidth Notifications should
also be generated when bandwidth controller alters the PCIe Link Speed, a
few platforms do not deliver LMBS interrupt after Link Training as
expected. Thus, after changing the Link Speed, bandwidth controller makes
additional read for the Link Status Register to ensure cur_bus_speed is
consistent with the new PCIe Link Speed.

Link: https://lore.kernel.org/r/20241018144755.7875-8-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
[bhelgaas: squash devm_mutex_init() error checking from
https://lore.kernel.org/r/20241030163139.2111689-1-andriy.shevchenko@linux.intel.com,
drop export of pcie_set_target_speed()]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/pci.h         |  20 +++++
 drivers/pci/pcie/bwctrl.c | 180 ++++++++++++++++++++++++++++++++++++--
 drivers/pci/quirks.c      |  17 +---
 include/linux/pci.h       |  10 +++
 4 files changed, 208 insertions(+), 19 deletions(-)

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 8ec189c8f3f5a..7573f81f58c4c 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -331,6 +331,17 @@ void pci_disable_bridge_window(struct pci_dev *dev);
 struct pci_bus *pci_bus_get(struct pci_bus *bus);
 void pci_bus_put(struct pci_bus *bus);
 
+#define PCIE_LNKCAP_SLS2SPEED(lnkcap)					\
+({									\
+	((lnkcap) == PCI_EXP_LNKCAP_SLS_64_0GB ? PCIE_SPEED_64_0GT :	\
+	 (lnkcap) == PCI_EXP_LNKCAP_SLS_32_0GB ? PCIE_SPEED_32_0GT :	\
+	 (lnkcap) == PCI_EXP_LNKCAP_SLS_16_0GB ? PCIE_SPEED_16_0GT :	\
+	 (lnkcap) == PCI_EXP_LNKCAP_SLS_8_0GB ? PCIE_SPEED_8_0GT :	\
+	 (lnkcap) == PCI_EXP_LNKCAP_SLS_5_0GB ? PCIE_SPEED_5_0GT :	\
+	 (lnkcap) == PCI_EXP_LNKCAP_SLS_2_5GB ? PCIE_SPEED_2_5GT :	\
+	 PCI_SPEED_UNKNOWN);						\
+})
+
 /* PCIe link information from Link Capabilities 2 */
 #define PCIE_LNKCAP2_SLS2SPEED(lnkcap2) \
 	((lnkcap2) & PCI_EXP_LNKCAP2_SLS_64_0GB ? PCIE_SPEED_64_0GT : \
@@ -341,6 +352,15 @@ void pci_bus_put(struct pci_bus *bus);
 	 (lnkcap2) & PCI_EXP_LNKCAP2_SLS_2_5GB ? PCIE_SPEED_2_5GT : \
 	 PCI_SPEED_UNKNOWN)
 
+#define PCIE_LNKCTL2_TLS2SPEED(lnkctl2) \
+	((lnkctl2) == PCI_EXP_LNKCTL2_TLS_64_0GT ? PCIE_SPEED_64_0GT : \
+	 (lnkctl2) == PCI_EXP_LNKCTL2_TLS_32_0GT ? PCIE_SPEED_32_0GT : \
+	 (lnkctl2) == PCI_EXP_LNKCTL2_TLS_16_0GT ? PCIE_SPEED_16_0GT : \
+	 (lnkctl2) == PCI_EXP_LNKCTL2_TLS_8_0GT ? PCIE_SPEED_8_0GT : \
+	 (lnkctl2) == PCI_EXP_LNKCTL2_TLS_5_0GT ? PCIE_SPEED_5_0GT : \
+	 (lnkctl2) == PCI_EXP_LNKCTL2_TLS_2_5GT ? PCIE_SPEED_2_5GT : \
+	 PCI_SPEED_UNKNOWN)
+
 /* PCIe speed to Mb/s reduced by encoding overhead */
 #define PCIE_SPEED2MBS_ENC(speed) \
 	((speed) == PCIE_SPEED_64_0GT ? 64000*1/1 : \
diff --git a/drivers/pci/pcie/bwctrl.c b/drivers/pci/pcie/bwctrl.c
index b3da249002719..3cd3e2d066c98 100644
--- a/drivers/pci/pcie/bwctrl.c
+++ b/drivers/pci/pcie/bwctrl.c
@@ -7,6 +7,11 @@
  * Copyright (C) 2019 Dell Inc
  * Copyright (C) 2023-2024 Intel Corporation
  *
+ * The PCIe bandwidth controller provides a way to alter PCIe Link Speeds
+ * and notify the operating system when the Link Width or Speed changes. The
+ * notification capability is required for all Root Ports and Downstream
+ * Ports supporting Link Width wider than x1 and/or multiple Link Speeds.
+ *
  * This service port driver hooks into the Bandwidth Notification interrupt
  * watching for changes or links becoming degraded in operation. It updates
  * the cached Current Link Speed that is exposed to user space through sysfs.
@@ -15,9 +20,12 @@
 #define dev_fmt(fmt) "bwctrl: " fmt
 
 #include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/bits.h>
 #include <linux/cleanup.h>
 #include <linux/errno.h>
 #include <linux/interrupt.h>
+#include <linux/mutex.h>
 #include <linux/pci.h>
 #include <linux/rwsem.h>
 #include <linux/slab.h>
@@ -28,14 +36,166 @@
 
 /**
  * struct pcie_bwctrl_data - PCIe bandwidth controller
+ * @set_speed_mutex:	Serializes link speed changes
  * @lbms_count:		Count for LBMS (since last reset)
  */
 struct pcie_bwctrl_data {
+	struct mutex set_speed_mutex;
 	atomic_t lbms_count;
 };
 
-/* Prevents port removal during LBMS count accessors */
+/*
+ * Prevent port removal during LBMS count accessors and Link Speed changes.
+ *
+ * These have to be differentiated because pcie_bwctrl_change_speed() calls
+ * pcie_retrain_link() which uses LBMS count reset accessor on success
+ * (using just one rwsem triggers "possible recursive locking detected"
+ * warning).
+ */
 static DECLARE_RWSEM(pcie_bwctrl_lbms_rwsem);
+static DECLARE_RWSEM(pcie_bwctrl_setspeed_rwsem);
+
+static bool pcie_valid_speed(enum pci_bus_speed speed)
+{
+	return (speed >= PCIE_SPEED_2_5GT) && (speed <= PCIE_SPEED_64_0GT);
+}
+
+static u16 pci_bus_speed2lnkctl2(enum pci_bus_speed speed)
+{
+	static const u8 speed_conv[] = {
+		[PCIE_SPEED_2_5GT] = PCI_EXP_LNKCTL2_TLS_2_5GT,
+		[PCIE_SPEED_5_0GT] = PCI_EXP_LNKCTL2_TLS_5_0GT,
+		[PCIE_SPEED_8_0GT] = PCI_EXP_LNKCTL2_TLS_8_0GT,
+		[PCIE_SPEED_16_0GT] = PCI_EXP_LNKCTL2_TLS_16_0GT,
+		[PCIE_SPEED_32_0GT] = PCI_EXP_LNKCTL2_TLS_32_0GT,
+		[PCIE_SPEED_64_0GT] = PCI_EXP_LNKCTL2_TLS_64_0GT,
+	};
+
+	if (WARN_ON_ONCE(!pcie_valid_speed(speed)))
+		return 0;
+
+	return speed_conv[speed];
+}
+
+static inline u16 pcie_supported_speeds2target_speed(u8 supported_speeds)
+{
+	return __fls(supported_speeds);
+}
+
+/**
+ * pcie_bwctrl_select_speed - Select Target Link Speed
+ * @port:	PCIe Port
+ * @speed_req:	Requested PCIe Link Speed
+ *
+ * Select Target Link Speed by take into account Supported Link Speeds of
+ * both the Root Port and the Endpoint.
+ *
+ * Return: Target Link Speed (1=2.5GT/s, 2=5GT/s, 3=8GT/s, etc.)
+ */
+static u16 pcie_bwctrl_select_speed(struct pci_dev *port, enum pci_bus_speed speed_req)
+{
+	struct pci_bus *bus = port->subordinate;
+	u8 desired_speeds, supported_speeds;
+	struct pci_dev *dev;
+
+	desired_speeds = GENMASK(pci_bus_speed2lnkctl2(speed_req),
+				 __fls(PCI_EXP_LNKCAP2_SLS_2_5GB));
+
+	supported_speeds = port->supported_speeds;
+	if (bus) {
+		down_read(&pci_bus_sem);
+		dev = list_first_entry_or_null(&bus->devices, struct pci_dev, bus_list);
+		if (dev)
+			supported_speeds &= dev->supported_speeds;
+		up_read(&pci_bus_sem);
+	}
+	if (!supported_speeds)
+		return PCI_EXP_LNKCAP2_SLS_2_5GB;
+
+	return pcie_supported_speeds2target_speed(supported_speeds & desired_speeds);
+}
+
+static int pcie_bwctrl_change_speed(struct pci_dev *port, u16 target_speed, bool use_lt)
+{
+	int ret;
+
+	ret = pcie_capability_clear_and_set_word(port, PCI_EXP_LNKCTL2,
+						 PCI_EXP_LNKCTL2_TLS, target_speed);
+	if (ret != PCIBIOS_SUCCESSFUL)
+		return pcibios_err_to_errno(ret);
+
+	ret = pcie_retrain_link(port, use_lt);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Ensure link speed updates also with platforms that have problems
+	 * with notifications.
+	 */
+	if (port->subordinate)
+		pcie_update_link_speed(port->subordinate);
+
+	return 0;
+}
+
+/**
+ * pcie_set_target_speed - Set downstream Link Speed for PCIe Port
+ * @port:	PCIe Port
+ * @speed_req:	Requested PCIe Link Speed
+ * @use_lt:	Wait for the LT or DLLLA bit to detect the end of link training
+ *
+ * Attempt to set PCIe Port Link Speed to @speed_req. @speed_req may be
+ * adjusted downwards to the best speed supported by both the Port and PCIe
+ * Device underneath it.
+ *
+ * Return:
+ * * 0		- on success
+ * * -EINVAL	- @speed_req is not a PCIe Link Speed
+ * * -ENODEV	- @port is not controllable
+ * * -ETIMEDOUT	- changing Link Speed took too long
+ * * -EAGAIN	- Link Speed was changed but @speed_req was not achieved
+ */
+int pcie_set_target_speed(struct pci_dev *port, enum pci_bus_speed speed_req,
+			  bool use_lt)
+{
+	struct pci_bus *bus = port->subordinate;
+	u16 target_speed;
+	int ret;
+
+	if (WARN_ON_ONCE(!pcie_valid_speed(speed_req)))
+		return -EINVAL;
+
+	if (bus && bus->cur_bus_speed == speed_req)
+		return 0;
+
+	target_speed = pcie_bwctrl_select_speed(port, speed_req);
+
+	scoped_guard(rwsem_read, &pcie_bwctrl_setspeed_rwsem) {
+		struct pcie_bwctrl_data *data = port->link_bwctrl;
+
+		/*
+		 * port->link_bwctrl is NULL during initial scan when called
+		 * e.g. from the Target Speed quirk.
+		 */
+		if (data)
+			mutex_lock(&data->set_speed_mutex);
+
+		ret = pcie_bwctrl_change_speed(port, target_speed, use_lt);
+
+		if (data)
+			mutex_unlock(&data->set_speed_mutex);
+	}
+
+	/*
+	 * Despite setting higher speed into the Target Link Speed, empty
+	 * bus won't train to 5GT+ speeds.
+	 */
+	if (!ret && bus && bus->cur_bus_speed != speed_req &&
+	    !list_empty(&bus->devices))
+		ret = -EAGAIN;
+
+	return ret;
+}
 
 static void pcie_bwnotif_enable(struct pcie_device *srv)
 {
@@ -136,14 +296,20 @@ static int pcie_bwnotif_probe(struct pcie_device *srv)
 	if (!data)
 		return -ENOMEM;
 
+	ret = devm_mutex_init(&srv->device, &data->set_speed_mutex);
+	if (ret)
+		return ret;
+
 	ret = devm_request_irq(&srv->device, srv->irq, pcie_bwnotif_irq,
 			       IRQF_SHARED, "PCIe bwctrl", srv);
 	if (ret)
 		return ret;
 
-	scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) {
-		port->link_bwctrl = no_free_ptr(data);
-		pcie_bwnotif_enable(srv);
+	scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) {
+		scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) {
+			port->link_bwctrl = no_free_ptr(data);
+			pcie_bwnotif_enable(srv);
+		}
 	}
 
 	pci_dbg(port, "enabled with IRQ %d\n", srv->irq);
@@ -154,8 +320,10 @@ static int pcie_bwnotif_probe(struct pcie_device *srv)
 static void pcie_bwnotif_remove(struct pcie_device *srv)
 {
 	pcie_bwnotif_disable(srv->port);
-	scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem)
-		srv->port->link_bwctrl = NULL;
+
+	scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem)
+		scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem)
+			srv->port->link_bwctrl = NULL;
 }
 
 static int pcie_bwnotif_suspend(struct pcie_device *srv)
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index e6d502dca9391..dcf1c86a5488b 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -113,16 +113,11 @@ int pcie_failed_link_retrain(struct pci_dev *dev)
 
 		pci_info(dev, "broken device, retraining non-functional downstream link at 2.5GT/s\n");
 
-		lnkctl2 &= ~PCI_EXP_LNKCTL2_TLS;
-		lnkctl2 |= PCI_EXP_LNKCTL2_TLS_2_5GT;
-		pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, lnkctl2);
-
-		ret = pcie_retrain_link(dev, false);
+		ret = pcie_set_target_speed(dev, PCIE_SPEED_2_5GT, false);
 		if (ret) {
 			pci_info(dev, "retraining failed\n");
-			pcie_capability_write_word(dev, PCI_EXP_LNKCTL2,
-						   oldlnkctl2);
-			pcie_retrain_link(dev, true);
+			pcie_set_target_speed(dev, PCIE_LNKCTL2_TLS2SPEED(oldlnkctl2),
+					      true);
 			return ret;
 		}
 
@@ -136,11 +131,7 @@ int pcie_failed_link_retrain(struct pci_dev *dev)
 
 		pci_info(dev, "removing 2.5GT/s downstream link speed restriction\n");
 		pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap);
-		lnkctl2 &= ~PCI_EXP_LNKCTL2_TLS;
-		lnkctl2 |= lnkcap & PCI_EXP_LNKCAP_SLS;
-		pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, lnkctl2);
-
-		ret = pcie_retrain_link(dev, false);
+		ret = pcie_set_target_speed(dev, PCIE_LNKCAP_SLS2SPEED(lnkcap), false);
 		if (ret) {
 			pci_info(dev, "retraining failed\n");
 			return ret;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 579b288334292..4f02d9f91399b 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1797,9 +1797,19 @@ static inline int pci_irqd_intx_xlate(struct irq_domain *d,
 #ifdef CONFIG_PCIEPORTBUS
 extern bool pcie_ports_disabled;
 extern bool pcie_ports_native;
+
+int pcie_set_target_speed(struct pci_dev *port, enum pci_bus_speed speed_req,
+			  bool use_lt);
 #else
 #define pcie_ports_disabled	true
 #define pcie_ports_native	false
+
+static inline int pcie_set_target_speed(struct pci_dev *port,
+					enum pci_bus_speed speed_req,
+					bool use_lt)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 #define PCIE_LINK_STATE_L0S		(BIT(0) | BIT(1)) /* Upstr/dwnstr L0s */

From d278b098282d1327f6e1be82aacb18457a4d244d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 18 Oct 2024 17:47:54 +0300
Subject: [PATCH 1177/1530] thermal: Add PCIe cooling driver
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a thermal cooling driver to provide path to access PCIe bandwidth
controller using the usual thermal interfaces.

A cooling device is instantiated for controllable PCIe Ports from the
bwctrl service driver.

If registering the cooling device fails, allow bwctrl's probe to succeed
regardless. As cdev in that case contains IS_ERR() pseudo "pointer", clean
that up inside the probe function so the remove side doesn't need to
suddenly make an odd looking IS_ERR() check.

The thermal side state 0 means no throttling, i.e., maximum supported PCIe
Link Speed.

Link: https://lore.kernel.org/r/20241018144755.7875-9-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
[bhelgaas: dropped data->cdev test per
https://lore.kernel.org/r/ZzRm1SJTwEMRsAr8@wunner.de]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org> # From the cooling device interface perspective
---
 MAINTAINERS                    |  2 +
 drivers/pci/pcie/bwctrl.c      | 12 +++++
 drivers/thermal/Kconfig        |  9 ++++
 drivers/thermal/Makefile       |  2 +
 drivers/thermal/pcie_cooling.c | 80 ++++++++++++++++++++++++++++++++++
 include/linux/pci-bwctrl.h     | 28 ++++++++++++
 6 files changed, 133 insertions(+)
 create mode 100644 drivers/thermal/pcie_cooling.c
 create mode 100644 include/linux/pci-bwctrl.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 8c555b3325d65..393ed7ce5ea18 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17938,6 +17938,8 @@ M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
 L:	linux-pci@vger.kernel.org
 S:	Supported
 F:	drivers/pci/pcie/bwctrl.c
+F:	drivers/thermal/pcie_cooling.c
+F:	include/linux/pci-bwctrl.h
 
 PCIE DRIVER FOR AMAZON ANNAPURNA LABS
 M:	Jonathan Chocron <jonnyc@amazon.com>
diff --git a/drivers/pci/pcie/bwctrl.c b/drivers/pci/pcie/bwctrl.c
index 3cd3e2d066c98..b59cacc740fa2 100644
--- a/drivers/pci/pcie/bwctrl.c
+++ b/drivers/pci/pcie/bwctrl.c
@@ -27,6 +27,7 @@
 #include <linux/interrupt.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
+#include <linux/pci-bwctrl.h>
 #include <linux/rwsem.h>
 #include <linux/slab.h>
 #include <linux/types.h>
@@ -38,10 +39,12 @@
  * struct pcie_bwctrl_data - PCIe bandwidth controller
  * @set_speed_mutex:	Serializes link speed changes
  * @lbms_count:		Count for LBMS (since last reset)
+ * @cdev:		Thermal cooling device associated with the port
  */
 struct pcie_bwctrl_data {
 	struct mutex set_speed_mutex;
 	atomic_t lbms_count;
+	struct thermal_cooling_device *cdev;
 };
 
 /*
@@ -314,11 +317,20 @@ static int pcie_bwnotif_probe(struct pcie_device *srv)
 
 	pci_dbg(port, "enabled with IRQ %d\n", srv->irq);
 
+	/* Don't fail on errors. Don't leave IS_ERR() "pointer" into ->cdev */
+	port->link_bwctrl->cdev = pcie_cooling_device_register(port);
+	if (IS_ERR(port->link_bwctrl->cdev))
+		port->link_bwctrl->cdev = NULL;
+
 	return 0;
 }
 
 static void pcie_bwnotif_remove(struct pcie_device *srv)
 {
+	struct pcie_bwctrl_data *data = srv->port->link_bwctrl;
+
+	pcie_cooling_device_unregister(data->cdev);
+
 	pcie_bwnotif_disable(srv->port);
 
 	scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem)
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 61e7ae524b1f8..d3f9686e26e71 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -220,6 +220,15 @@ config DEVFREQ_THERMAL
 
 	  If you want this support, you should say Y here.
 
+config PCIE_THERMAL
+	bool "PCIe cooling support"
+	depends on PCIEPORTBUS
+	help
+	  This implements PCIe cooling mechanism through bandwidth reduction
+	  for PCIe devices.
+
+	  If you want this support, you should say Y here.
+
 config THERMAL_EMULATION
 	bool "Thermal emulation mode support"
 	help
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index 41c4d56beb40d..210c16c914615 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -31,6 +31,8 @@ thermal_sys-$(CONFIG_CPU_IDLE_THERMAL)	+= cpuidle_cooling.o
 # devfreq cooling
 thermal_sys-$(CONFIG_DEVFREQ_THERMAL) += devfreq_cooling.o
 
+thermal_sys-$(CONFIG_PCIE_THERMAL) += pcie_cooling.o
+
 obj-$(CONFIG_K3_THERMAL)	+= k3_bandgap.o k3_j72xx_bandgap.o
 # platform thermal drivers
 obj-y				+= broadcom/
diff --git a/drivers/thermal/pcie_cooling.c b/drivers/thermal/pcie_cooling.c
new file mode 100644
index 0000000000000..a876d64f15827
--- /dev/null
+++ b/drivers/thermal/pcie_cooling.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * PCIe cooling device
+ *
+ * Copyright (C) 2023-2024 Intel Corporation
+ */
+
+#include <linux/build_bug.h>
+#include <linux/cleanup.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pci-bwctrl.h>
+#include <linux/slab.h>
+#include <linux/sprintf.h>
+#include <linux/thermal.h>
+
+#define COOLING_DEV_TYPE_PREFIX		"PCIe_Port_Link_Speed_"
+
+static int pcie_cooling_get_max_level(struct thermal_cooling_device *cdev, unsigned long *state)
+{
+	struct pci_dev *port = cdev->devdata;
+
+	/* cooling state 0 is same as the maximum PCIe speed */
+	*state = port->subordinate->max_bus_speed - PCIE_SPEED_2_5GT;
+
+	return 0;
+}
+
+static int pcie_cooling_get_cur_level(struct thermal_cooling_device *cdev, unsigned long *state)
+{
+	struct pci_dev *port = cdev->devdata;
+
+	/* cooling state 0 is same as the maximum PCIe speed */
+	*state = cdev->max_state - (port->subordinate->cur_bus_speed - PCIE_SPEED_2_5GT);
+
+	return 0;
+}
+
+static int pcie_cooling_set_cur_level(struct thermal_cooling_device *cdev, unsigned long state)
+{
+	struct pci_dev *port = cdev->devdata;
+	enum pci_bus_speed speed;
+
+	/* cooling state 0 is same as the maximum PCIe speed */
+	speed = (cdev->max_state - state) + PCIE_SPEED_2_5GT;
+
+	return pcie_set_target_speed(port, speed, true);
+}
+
+static struct thermal_cooling_device_ops pcie_cooling_ops = {
+	.get_max_state = pcie_cooling_get_max_level,
+	.get_cur_state = pcie_cooling_get_cur_level,
+	.set_cur_state = pcie_cooling_set_cur_level,
+};
+
+struct thermal_cooling_device *pcie_cooling_device_register(struct pci_dev *port)
+{
+	char *name __free(kfree) =
+		kasprintf(GFP_KERNEL, COOLING_DEV_TYPE_PREFIX "%s", pci_name(port));
+	if (!name)
+		return ERR_PTR(-ENOMEM);
+
+	return thermal_cooling_device_register(name, port, &pcie_cooling_ops);
+}
+
+void pcie_cooling_device_unregister(struct thermal_cooling_device *cdev)
+{
+	thermal_cooling_device_unregister(cdev);
+}
+
+/* For bus_speed <-> state arithmetic */
+static_assert(PCIE_SPEED_2_5GT + 1 == PCIE_SPEED_5_0GT);
+static_assert(PCIE_SPEED_5_0GT + 1 == PCIE_SPEED_8_0GT);
+static_assert(PCIE_SPEED_8_0GT + 1 == PCIE_SPEED_16_0GT);
+static_assert(PCIE_SPEED_16_0GT + 1 == PCIE_SPEED_32_0GT);
+static_assert(PCIE_SPEED_32_0GT + 1 == PCIE_SPEED_64_0GT);
+
+MODULE_AUTHOR("Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>");
+MODULE_DESCRIPTION("PCIe cooling driver");
diff --git a/include/linux/pci-bwctrl.h b/include/linux/pci-bwctrl.h
new file mode 100644
index 0000000000000..cee07127455b3
--- /dev/null
+++ b/include/linux/pci-bwctrl.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * PCIe bandwidth controller
+ *
+ * Copyright (C) 2023-2024 Intel Corporation
+ */
+
+#ifndef LINUX_PCI_BWCTRL_H
+#define LINUX_PCI_BWCTRL_H
+
+#include <linux/pci.h>
+
+struct thermal_cooling_device;
+
+#ifdef CONFIG_PCIE_THERMAL
+struct thermal_cooling_device *pcie_cooling_device_register(struct pci_dev *port);
+void pcie_cooling_device_unregister(struct thermal_cooling_device *cdev);
+#else
+static inline struct thermal_cooling_device *pcie_cooling_device_register(struct pci_dev *port)
+{
+	return NULL;
+}
+static inline void pcie_cooling_device_unregister(struct thermal_cooling_device *cdev)
+{
+}
+#endif
+
+#endif

From 838f12c3d551f8941295ed7085ad360c3d3ad665 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 18 Oct 2024 17:47:55 +0300
Subject: [PATCH 1178/1530] selftests/pcie_bwctrl: Create selftests
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Create selftests for PCIe BW control through the PCIe cooling device sysfs
interface.

First, the BW control selftest finds the PCIe Port to test with. By
default, the PCIe Port with the highest Link Speed is selected but
another PCIe Port can be provided with -d parameter.

The actual test steps the cur_state of the cooling device one-by-one
from max_state to what the cur_state was initially. The speed change
is confirmed by observing the current_link_speed for the corresponding
PCIe Port.

Link: https://lore.kernel.org/r/20241018144755.7875-10-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 MAINTAINERS                                   |   1 +
 tools/testing/selftests/Makefile              |   1 +
 tools/testing/selftests/pcie_bwctrl/Makefile  |   2 +
 .../pcie_bwctrl/set_pcie_cooling_state.sh     | 122 ++++++++++++++++++
 .../selftests/pcie_bwctrl/set_pcie_speed.sh   |  67 ++++++++++
 5 files changed, 193 insertions(+)
 create mode 100644 tools/testing/selftests/pcie_bwctrl/Makefile
 create mode 100755 tools/testing/selftests/pcie_bwctrl/set_pcie_cooling_state.sh
 create mode 100755 tools/testing/selftests/pcie_bwctrl/set_pcie_speed.sh

diff --git a/MAINTAINERS b/MAINTAINERS
index 393ed7ce5ea18..d7ffef4382dfd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17940,6 +17940,7 @@ S:	Supported
 F:	drivers/pci/pcie/bwctrl.c
 F:	drivers/thermal/pcie_cooling.c
 F:	include/linux/pci-bwctrl.h
+F:	tools/testing/selftests/pcie_bwctrl/
 
 PCIE DRIVER FOR AMAZON ANNAPURNA LABS
 M:	Jonathan Chocron <jonnyc@amazon.com>
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index b38199965f990..7181756f47ff2 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -72,6 +72,7 @@ TARGETS += net/packetdrill
 TARGETS += net/rds
 TARGETS += net/tcp_ao
 TARGETS += nsfs
+TARGETS += pcie_bwctrl
 TARGETS += perf_events
 TARGETS += pidfd
 TARGETS += pid_namespace
diff --git a/tools/testing/selftests/pcie_bwctrl/Makefile b/tools/testing/selftests/pcie_bwctrl/Makefile
new file mode 100644
index 0000000000000..3e84e26341d1c
--- /dev/null
+++ b/tools/testing/selftests/pcie_bwctrl/Makefile
@@ -0,0 +1,2 @@
+TEST_PROGS = set_pcie_cooling_state.sh
+include ../lib.mk
diff --git a/tools/testing/selftests/pcie_bwctrl/set_pcie_cooling_state.sh b/tools/testing/selftests/pcie_bwctrl/set_pcie_cooling_state.sh
new file mode 100755
index 0000000000000..9df606552af3a
--- /dev/null
+++ b/tools/testing/selftests/pcie_bwctrl/set_pcie_cooling_state.sh
@@ -0,0 +1,122 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+SYSFS=
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+retval=0
+skipmsg="skip all tests:"
+
+PCIEPORTTYPE="PCIe_Port_Link_Speed"
+
+prerequisite()
+{
+	local ports
+
+	if [ $UID != 0 ]; then
+		echo $skipmsg must be run as root >&2
+		exit $ksft_skip
+	fi
+
+	SYSFS=`mount -t sysfs | head -1 | awk '{ print $3 }'`
+
+	if [ ! -d "$SYSFS" ]; then
+		echo $skipmsg sysfs is not mounted >&2
+		exit $ksft_skip
+	fi
+
+	if ! ls $SYSFS/class/thermal/cooling_device* > /dev/null 2>&1; then
+		echo $skipmsg thermal cooling devices missing >&2
+		exit $ksft_skip
+	fi
+
+	ports=`grep -e "^$PCIEPORTTYPE" $SYSFS/class/thermal/cooling_device*/type | wc -l`
+	if [ $ports -eq 0 ]; then
+		echo $skipmsg pcie cooling devices missing >&2
+		exit $ksft_skip
+	fi
+}
+
+testport=
+find_pcie_port()
+{
+	local patt="$1"
+	local pcieports
+	local max
+	local cur
+	local delta
+	local bestdelta=-1
+
+	pcieports=`grep -l -F -e "$patt" /sys/class/thermal/cooling_device*/type`
+	if [ -z "$pcieports" ]; then
+		return
+	fi
+	pcieports=${pcieports//\/type/}
+	# Find the port with the highest PCIe Link Speed
+	for port in $pcieports; do
+		max=`cat $port/max_state`
+		cur=`cat $port/cur_state`
+		delta=$((max-cur))
+		if [ $delta -gt $bestdelta ]; then
+			testport="$port"
+			bestdelta=$delta
+		fi
+	done
+}
+
+sysfspcidev=
+find_sysfs_pci_dev()
+{
+	local typefile="$1/type"
+	local pcidir
+
+	pcidir="$SYSFS/bus/pci/devices/`sed -e "s|^${PCIEPORTTYPE}_||g" $typefile`"
+
+	if [ -r "$pcidir/current_link_speed" ]; then
+		sysfspcidev="$pcidir/current_link_speed"
+	fi
+}
+
+usage()
+{
+	echo "Usage $0 [ -d dev ]"
+	echo -e "\t-d: PCIe port BDF string (e.g., 0000:00:04.0)"
+}
+
+pattern="$PCIEPORTTYPE"
+parse_arguments()
+{
+	while getopts d:h opt; do
+		case $opt in
+			h)
+				usage "$0"
+				exit 0
+				;;
+			d)
+				pattern="$PCIEPORTTYPE_$OPTARG"
+				;;
+			*)
+				usage "$0"
+				exit 0
+				;;
+		esac
+	done
+}
+
+parse_arguments "$@"
+prerequisite
+find_pcie_port "$pattern"
+if [ -z "$testport" ]; then
+	echo $skipmsg "pcie cooling device not found from sysfs" >&2
+	exit $ksft_skip
+fi
+find_sysfs_pci_dev "$testport"
+if [ -z "$sysfspcidev" ]; then
+	echo $skipmsg "PCIe port device not found from sysfs" >&2
+	exit $ksft_skip
+fi
+
+./set_pcie_speed.sh "$testport" "$sysfspcidev"
+retval=$?
+
+exit $retval
diff --git a/tools/testing/selftests/pcie_bwctrl/set_pcie_speed.sh b/tools/testing/selftests/pcie_bwctrl/set_pcie_speed.sh
new file mode 100755
index 0000000000000..5845969493123
--- /dev/null
+++ b/tools/testing/selftests/pcie_bwctrl/set_pcie_speed.sh
@@ -0,0 +1,67 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+set -e
+
+TESTNAME=set_pcie_speed
+
+declare -a PCIELINKSPEED=(
+	"2.5 GT/s PCIe"
+	"5.0 GT/s PCIe"
+	"8.0 GT/s PCIe"
+	"16.0 GT/s PCIe"
+	"32.0 GT/s PCIe"
+	"64.0 GT/s PCIe"
+)
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+retval=0
+
+coolingdev="$1"
+statefile="$coolingdev/cur_state"
+maxfile="$coolingdev/max_state"
+linkspeedfile="$2"
+
+oldstate=`cat $statefile`
+maxstate=`cat $maxfile`
+
+set_state()
+{
+	local state=$1
+	local linkspeed
+	local expected_linkspeed
+
+	echo $state > $statefile
+
+	sleep 1
+
+	linkspeed="`cat $linkspeedfile`"
+	expected_linkspeed=$((maxstate-state))
+	expected_str="${PCIELINKSPEED[$expected_linkspeed]}"
+	if [ ! "${expected_str}" = "${linkspeed}" ]; then
+		echo "$TESTNAME failed: expected: ${expected_str}; got ${linkspeed}"
+		retval=1
+	fi
+}
+
+cleanup_skip ()
+{
+	set_state $oldstate
+	exit $ksft_skip
+}
+
+trap cleanup_skip EXIT
+
+echo "$TESTNAME: testing states $maxstate .. $oldstate with $coolingdev"
+for i in $(seq $maxstate -1 $oldstate); do
+	set_state "$i"
+done
+
+trap EXIT
+if [ $retval -eq 0 ]; then
+	echo "$TESTNAME [PASS]"
+else
+	echo "$TESTNAME [FAIL]"
+fi
+exit $retval

From ba58eee1c57b2ad45c36f782861c18faef170a55 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Mon, 11 Nov 2024 14:21:33 -0600
Subject: [PATCH 1179/1530] PCI: Drop duplicate pcie_get_speed_cap(),
 pcie_get_width_cap() declarations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

6cf57be0f78e ("PCI: Add pcie_get_speed_cap() to find max supported link
speed") and c70b65fb7f12 ("PCI: Add pcie_get_width_cap() to find max
supported link width") added declarations to drivers/pci/pci.h.

576c7218a154 ("PCI: Export pcie_get_speed_cap and pcie_get_width_cap")
subsequently added duplicates to include/linux/pci.h.

Remove the originals from drivers/pci/pci.h.  Both interfaces are used by
amdgpu, so they must be in include/linux/pci.h.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Krzysztof Wilczyński <kw@linux.com>
---
 drivers/pci/pci.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 7573f81f58c4c..1d5c519e19b14 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -395,8 +395,6 @@ static inline int pcie_dev_speed_mbps(enum pci_bus_speed speed)
 
 u8 pcie_get_supported_speeds(struct pci_dev *dev);
 const char *pci_speed_string(enum pci_bus_speed speed);
-enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev);
-enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev);
 void __pcie_print_link_status(struct pci_dev *dev, bool verbose);
 void pcie_report_downtraining(struct pci_dev *dev);
 

From 3fafc38b77bebeeea5faa2a588b92353775bb390 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Thu, 17 Oct 2024 15:20:55 +0200
Subject: [PATCH 1180/1530] PCI: dwc: ep: Use align addr function for
 dw_pcie_ep_raise_{msi,msix}_irq()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the dw_pcie_ep_align_addr() function to calculate the alignment in
dw_pcie_ep_raise_{msi,msix}_irq() instead of open coding the same.

Link: https://lore.kernel.org/r/20241017132052.4014605-6-cassel@kernel.org
Link: https://lore.kernel.org/r/20241104205144.409236-2-cassel@kernel.org
Tested-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
[kwilczynski: squashed patch that fixes memory map sizes]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 .../pci/controller/dwc/pcie-designware-ep.c   | 20 +++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 20f67fd85e837..507e40bd18c8f 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -503,7 +503,8 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 	u32 msg_addr_lower, msg_addr_upper, reg;
 	struct dw_pcie_ep_func *ep_func;
 	struct pci_epc *epc = ep->epc;
-	unsigned int aligned_offset;
+	size_t map_size = sizeof(u32);
+	size_t offset;
 	u16 msg_ctrl, msg_data;
 	bool has_upper;
 	u64 msg_addr;
@@ -531,14 +532,13 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 	}
 	msg_addr = ((u64)msg_addr_upper) << 32 | msg_addr_lower;
 
-	aligned_offset = msg_addr & (epc->mem->window.page_size - 1);
-	msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size);
+	msg_addr = dw_pcie_ep_align_addr(epc, msg_addr, &map_size, &offset);
 	ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr,
-				  epc->mem->window.page_size);
+				  map_size);
 	if (ret)
 		return ret;
 
-	writel(msg_data | (interrupt_num - 1), ep->msi_mem + aligned_offset);
+	writel(msg_data | (interrupt_num - 1), ep->msi_mem + offset);
 
 	dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys);
 
@@ -589,8 +589,9 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
 	struct pci_epf_msix_tbl *msix_tbl;
 	struct dw_pcie_ep_func *ep_func;
 	struct pci_epc *epc = ep->epc;
+	size_t map_size = sizeof(u32);
+	size_t offset;
 	u32 reg, msg_data, vec_ctrl;
-	unsigned int aligned_offset;
 	u32 tbl_offset;
 	u64 msg_addr;
 	int ret;
@@ -615,14 +616,13 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
 		return -EPERM;
 	}
 
-	aligned_offset = msg_addr & (epc->mem->window.page_size - 1);
-	msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size);
+	msg_addr = dw_pcie_ep_align_addr(epc, msg_addr, &map_size, &offset);
 	ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr,
-				  epc->mem->window.page_size);
+				  map_size);
 	if (ret)
 		return ret;
 
-	writel(msg_data, ep->msi_mem + aligned_offset);
+	writel(msg_data, ep->msi_mem + offset);
 
 	dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys);
 

From 9b80bdb10aee04ce7289896e6bdad13e33972636 Mon Sep 17 00:00:00 2001
From: Wang Jiang <jiangwang@kylinos.cn>
Date: Mon, 4 Nov 2024 18:05:14 +0800
Subject: [PATCH 1181/1530] PCI: endpoint: Remove surplus return statement from
 pci_epf_test_clean_dma_chan()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove a surplus return statement from the void function that has been
added in the commit commit 8353813c88ef ("PCI: endpoint: Enable DMA
tests for endpoints with DMA capabilities").

Especially, as an empty return statements at the end of a void functions
serve little purpose.

This fixes the following checkpatch.pl script warning:

  WARNING: void function return statements are not generally useful
  #296: FILE: drivers/pci/endpoint/functions/pci-epf-test.c:296:
  +     return;
  +}

Link: https://lore.kernel.org/r/tencent_F250BEE2A65745A524E2EFE70CF615CA8F06@qq.com
Signed-off-by: Wang Jiang <jiangwang@kylinos.cn>
[kwilczynski: commit log]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/endpoint/functions/pci-epf-test.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index c2e7f67e51076..ef6677f34116e 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -291,8 +291,6 @@ static void pci_epf_test_clean_dma_chan(struct pci_epf_test *epf_test)
 
 	dma_release_channel(epf_test->dma_chan_rx);
 	epf_test->dma_chan_rx = NULL;
-
-	return;
 }
 
 static void pci_epf_test_print_rate(struct pci_epf_test *epf_test,

From 5089b3d874e9933d9842e90410d3af1520494757 Mon Sep 17 00:00:00 2001
From: Zhongqiu Han <quic_zhonhan@quicinc.com>
Date: Tue, 5 Nov 2024 20:07:35 +0800
Subject: [PATCH 1182/1530] PCI: endpoint: epf-mhi: Avoid NULL dereference if
 DT lacks 'mmio'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If platform_get_resource_byname() fails and returns NULL because DT lacks
an 'mmio' property for the MHI endpoint, dereferencing res->start will
cause a NULL pointer access. Add a check to prevent it.

Fixes: 1bf5f25324f7 ("PCI: endpoint: Add PCI Endpoint function driver for MHI bus")
Link: https://lore.kernel.org/r/20241105120735.1240728-1-quic_zhonhan@quicinc.com
Signed-off-by: Zhongqiu Han <quic_zhonhan@quicinc.com>
[kwilczynski: error message update per the review feedback]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
[bhelgaas: commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/pci/endpoint/functions/pci-epf-mhi.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index 7d070b1def116..54286a40bdfbf 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -867,12 +867,18 @@ static int pci_epf_mhi_bind(struct pci_epf *epf)
 {
 	struct pci_epf_mhi *epf_mhi = epf_get_drvdata(epf);
 	struct pci_epc *epc = epf->epc;
+	struct device *dev = &epf->dev;
 	struct platform_device *pdev = to_platform_device(epc->dev.parent);
 	struct resource *res;
 	int ret;
 
 	/* Get MMIO base address from Endpoint controller */
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mmio");
+	if (!res) {
+		dev_err(dev, "Failed to get \"mmio\" resource\n");
+		return -ENODEV;
+	}
+
 	epf_mhi->mmio_phys = res->start;
 	epf_mhi->mmio_size = resource_size(res);
 

From 154fc1f6420840e8aa65e5b43a456ae8f34816dd Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Mon, 4 Nov 2024 13:07:13 -0600
Subject: [PATCH 1183/1530] PCI: dwc: Use of_property_present() for non-boolean
 properties
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The use of of_property_read_bool() for non-boolean properties is
deprecated in favor of of_property_present() when testing for property
presence.

Link: https://lore.kernel.org/r/20241104190714.275977-1-robh@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/dwc/pcie-designware-host.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 3e41865c72904..d2291c3ceb8be 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -474,8 +474,8 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 
 	if (pci_msi_enabled()) {
 		pp->has_msi_ctrl = !(pp->ops->msi_init ||
-				     of_property_read_bool(np, "msi-parent") ||
-				     of_property_read_bool(np, "msi-map"));
+				     of_property_present(np, "msi-parent") ||
+				     of_property_present(np, "msi-map"));
 
 		/*
 		 * For the has_msi_ctrl case the default assignment is handled

From 118397c9baaac0b7ec81896f8d755d09aa82c485 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Sat, 16 Nov 2024 01:59:51 +0100
Subject: [PATCH 1184/1530] PCI: dwc: ep: Fix advertised resizable BAR size
 regression
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The advertised resizable BAR size was fixed in commit 72e34b8593e0 ("PCI:
dwc: endpoint: Fix advertised resizable BAR size").

Commit 867ab111b242 ("PCI: dwc: ep: Add a generic dw_pcie_ep_linkdown()
API to handle Link Down event") was included shortly after this, and
moved the code to another function. When the code was moved, this fix
was mistakenly lost.

According to the spec, it is illegal to not have a bit set in
PCI_REBAR_CAP, and 1 MB is the smallest size allowed.

So, set bit 4 in PCI_REBAR_CAP, so that we actually advertise support
for a 1 MB BAR size.

Fixes: 867ab111b242 ("PCI: dwc: ep: Add a generic dw_pcie_ep_linkdown() API to handle Link Down event")
Link: https://lore.kernel.org/r/20241116005950.2480427-2-cassel@kernel.org
Link: https://lore.kernel.org/r/20240606-pci-deinit-v1-3-4395534520dc@linaro.org
Link: https://lore.kernel.org/r/20240307111520.3303774-1-cassel@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Cc: stable@vger.kernel.org
---
 drivers/pci/controller/dwc/pcie-designware-ep.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index b07ace7dc92ed..b11cca6298f20 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -690,7 +690,7 @@ static void dw_pcie_ep_init_non_sticky_registers(struct dw_pcie *pci)
 		 * for 1 MB BAR size only.
 		 */
 		for (i = 0; i < nbars; i++, offset += PCI_REBAR_CTRL)
-			dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, 0x0);
+			dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, BIT(4));
 	}
 
 	dw_pcie_setup(pci);

From 0b687912c94181fdf530aa33036871cd8a26eb72 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 15 Nov 2024 12:18:21 -0300
Subject: [PATCH 1185/1530] perf test shell trace_exit_race: Use --no-comm to
 avoid cases where COMM isn't resolved

The purpose of this test is to test for races in the exit of 'perf
trace' missing the last events, it was failing when the COMM wasn't
resolved either because we missed some PERF_RECORD_COMM or somehow
raced on getting it from procfs.

Add --no-comm to the 'perf trace' command line so that we get a
consistent, pid only output, which allows the test to achieve its goal.

This is the output from
'perf trace --no-comm -e syscalls:sys_enter_exit_group':

     0.000 21953 syscalls:sys_enter_exit_group()
     0.000 21955 syscalls:sys_enter_exit_group()
     0.000 21957 syscalls:sys_enter_exit_group()
     0.000 21959 syscalls:sys_enter_exit_group()
     0.000 21961 syscalls:sys_enter_exit_group()
     0.000 21963 syscalls:sys_enter_exit_group()
     0.000 21965 syscalls:sys_enter_exit_group()
     0.000 21967 syscalls:sys_enter_exit_group()
     0.000 21969 syscalls:sys_enter_exit_group()
     0.000 21971 syscalls:sys_enter_exit_group()

Now it passes:

  root@number:~# perf test "trace exit race"
  110: perf trace exit race                                            : Ok
  root@number:~#
  root@number:~# perf test -v "trace exit race"
  110: perf trace exit race                                            : Ok
  root@number:~#

If we artificially make it run just 9 times instead of the 10 it runs,
i.e. by manually doing:

	trace_shutdown_race() {
		for _ in $(seq 9); do

that 9 is $iter, 10 in the patch, we get:

  root@number:~# vim ~acme/libexec/perf-core/tests/shell/trace_exit_race.sh
  root@number:~# perf test -v "trace exit race"
  --- start ---
  test child forked, pid 24629
  Missing output, expected 10 but only got 9
  ---- end(-1) ----
  110: perf trace exit race                                            : FAILED!
  root@number:~#

I.e. 9 'perf trace' calls produced the expected output, the inverse grep
didn't show anything, so the patch provided by Howard for the previous
patch kicks in and shows a more informative message.

Tested-by: Howard Chu <howardchu95@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Peterson <benjamin@engflow.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/lkml/ZzdknoHqrJbojb6P@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/trace_exit_race.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/trace_exit_race.sh b/tools/perf/tests/shell/trace_exit_race.sh
index 8ea24f4256bc8..fbb0adc33a889 100755
--- a/tools/perf/tests/shell/trace_exit_race.sh
+++ b/tools/perf/tests/shell/trace_exit_race.sh
@@ -16,11 +16,11 @@ if [ "$1" = "-v" ]; then
 fi
 
 iter=10
-regexp=" +[0-9]+\.[0-9]+ +true/[0-9]+ syscalls:sys_enter_exit_group\(\)$"
+regexp=" +[0-9]+\.[0-9]+ [0-9]+ syscalls:sys_enter_exit_group\(\)$"
 
 trace_shutdown_race() {
 	for _ in $(seq $iter); do
-		perf trace -e syscalls:sys_enter_exit_group true 2>>$file
+		perf trace --no-comm -e syscalls:sys_enter_exit_group true 2>>$file
 	done
 	result="$(grep -c -E "$regexp" $file)"
 	[ $result = $iter ]

From 264708b8ac6cce132c61865bfe0463adeb80d7ef Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sat, 16 Nov 2024 15:58:50 +0000
Subject: [PATCH 1186/1530] perf util: Remove kernel version deadcode

fetch_kernel_version() has been unused since Ian's 2023 commit
3d6dfae889174340 ("perf parse-events: Remove BPF event support")

Remove it, and it's helpers.

I noticed there are a bunch of kernel-version macros that are also
unused nearby.

Also remove them.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241116155850.113129-1-linux@treblig.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/util.c | 85 ------------------------------------------
 tools/perf/util/util.h |  8 ----
 2 files changed, 93 deletions(-)

diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 280c86d61d8a7..0f031eb80b4c5 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -342,91 +342,6 @@ bool perf_event_paranoid_check(int max_level)
 	return perf_event_paranoid() <= max_level;
 }
 
-static int
-fetch_ubuntu_kernel_version(unsigned int *puint)
-{
-	ssize_t len;
-	size_t line_len = 0;
-	char *ptr, *line = NULL;
-	int version, patchlevel, sublevel, err;
-	FILE *vsig;
-
-	if (!puint)
-		return 0;
-
-	vsig = fopen("/proc/version_signature", "r");
-	if (!vsig) {
-		pr_debug("Open /proc/version_signature failed: %s\n",
-			 strerror(errno));
-		return -1;
-	}
-
-	len = getline(&line, &line_len, vsig);
-	fclose(vsig);
-	err = -1;
-	if (len <= 0) {
-		pr_debug("Reading from /proc/version_signature failed: %s\n",
-			 strerror(errno));
-		goto errout;
-	}
-
-	ptr = strrchr(line, ' ');
-	if (!ptr) {
-		pr_debug("Parsing /proc/version_signature failed: %s\n", line);
-		goto errout;
-	}
-
-	err = sscanf(ptr + 1, "%d.%d.%d",
-		     &version, &patchlevel, &sublevel);
-	if (err != 3) {
-		pr_debug("Unable to get kernel version from /proc/version_signature '%s'\n",
-			 line);
-		goto errout;
-	}
-
-	*puint = (version << 16) + (patchlevel << 8) + sublevel;
-	err = 0;
-errout:
-	free(line);
-	return err;
-}
-
-int
-fetch_kernel_version(unsigned int *puint, char *str,
-		     size_t str_size)
-{
-	struct utsname utsname;
-	int version, patchlevel, sublevel, err;
-	bool int_ver_ready = false;
-
-	if (access("/proc/version_signature", R_OK) == 0)
-		if (!fetch_ubuntu_kernel_version(puint))
-			int_ver_ready = true;
-
-	if (uname(&utsname))
-		return -1;
-
-	if (str && str_size) {
-		strncpy(str, utsname.release, str_size);
-		str[str_size - 1] = '\0';
-	}
-
-	if (!puint || int_ver_ready)
-		return 0;
-
-	err = sscanf(utsname.release, "%d.%d.%d",
-		     &version, &patchlevel, &sublevel);
-
-	if (err != 3) {
-		pr_debug("Unable to get kernel version from uname '%s'\n",
-			 utsname.release);
-		return -1;
-	}
-
-	*puint = (version << 16) + (patchlevel << 8) + sublevel;
-	return 0;
-}
-
 int perf_tip(char **strp, const char *dirpath)
 {
 	struct strlist *tips;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 2359362885eaf..3423778e39a56 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -46,14 +46,6 @@ int sysctl__max_stack(void);
 
 bool sysctl__nmi_watchdog_enabled(void);
 
-int fetch_kernel_version(unsigned int *puint,
-			 char *str, size_t str_sz);
-#define KVER_VERSION(x)		(((x) >> 16) & 0xff)
-#define KVER_PATCHLEVEL(x)	(((x) >> 8) & 0xff)
-#define KVER_SUBLEVEL(x)	((x) & 0xff)
-#define KVER_FMT	"%d.%d.%d"
-#define KVER_PARAM(x)	KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
-
 int perf_tip(char **strp, const char *dirpath);
 
 #ifndef HAVE_SCHED_GETCPU_SUPPORT

From 180fd0c1eac7cd8c5aa9a9f8b54088a61d9e05db Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Fri, 15 Nov 2024 16:15:59 +0000
Subject: [PATCH 1187/1530] perf tests: Make leader sampling test work without
 branch event

Arm a57 only has speculative branch events so this test fails there. The
test doesn't depend on branch instructions so change it to instructions
which is pretty much guaranteed to be everywhere. The
test_branch_counter() test above already tests for the existence of the
branches event and skips if its not present.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Link: https://lore.kernel.org/r/20241115161600.228994-1-james.clark@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/record.sh | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index 85d512f5a1263..0fc7a909ae9b5 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -231,7 +231,8 @@ test_cgroup() {
 
 test_leader_sampling() {
   echo "Basic leader sampling test"
-  if ! perf record -o "${perfdata}" -e "{branches,branches}:Su" perf test -w brstack 2> /dev/null
+  if ! perf record -o "${perfdata}" -e "{instructions,instructions}:Su" -- \
+    perf test -w brstack 2> /dev/null
   then
     echo "Leader sampling [Failed record]"
     err=1
@@ -241,16 +242,16 @@ test_leader_sampling() {
   perf script -i "${perfdata}" > $script_output
   while IFS= read -r line
   do
-    # Check if the two branches counts are equal in each record
-    branches=$(echo $line | awk '{for(i=1;i<=NF;i++) if($i=="branches:") print $(i-1)}')
-    if [ $(($index%2)) -ne 0 ] && [ ${branches}x != ${prev_branches}x ]
+    # Check if the two instruction counts are equal in each record
+    instructions=$(echo $line | awk '{for(i=1;i<=NF;i++) if($i=="instructions:") print $(i-1)}')
+    if [ $(($index%2)) -ne 0 ] && [ ${instructions}x != ${prev_instructions}x ]
     then
-      echo "Leader sampling [Failed inconsistent branches count]"
+      echo "Leader sampling [Failed inconsistent instructions count]"
       err=1
       return
     fi
     index=$(($index+1))
-    prev_branches=$branches
+    prev_instructions=$instructions
   done < $script_output
   echo "Basic leader sampling test [Success]"
 }

From db26a8c9e3c285092ed3e14a33755582c04e0269 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 15 Nov 2024 12:12:58 -0800
Subject: [PATCH 1188/1530] perf test: Add missing __exit calls in tool/hwmon
 tests

Address sanitizer flagged the missing parse_events_error__exit when
testing on ARM.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241115201258.509477-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/hwmon_pmu.c | 1 +
 tools/perf/tests/tool_pmu.c  | 1 +
 2 files changed, 2 insertions(+)

diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c
index 5c4114354c65e..9f44093f18df2 100644
--- a/tools/perf/tests/hwmon_pmu.c
+++ b/tools/perf/tests/hwmon_pmu.c
@@ -194,6 +194,7 @@ static int do_test(size_t i, bool with_pmu, bool with_alias)
 	}
 
 out:
+	parse_events_error__exit(&err);
 	evlist__delete(evlist);
 	return ret;
 }
diff --git a/tools/perf/tests/tool_pmu.c b/tools/perf/tests/tool_pmu.c
index 46896b485abf3..187942b749b7c 100644
--- a/tools/perf/tests/tool_pmu.c
+++ b/tools/perf/tests/tool_pmu.c
@@ -66,6 +66,7 @@ static int do_test(enum tool_pmu_event ev, bool with_pmu)
 	}
 
 out:
+	parse_events_error__exit(&err);
 	evlist__delete(evlist);
 	return ret;
 }

From 4a159e6049f319bef6f9e6d2ccdd322f57d24830 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Thu, 7 Nov 2024 08:20:28 -0800
Subject: [PATCH 1189/1530] perf jevents: fix breakage when do perf stat on
 system metric
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When do perf stat on sys metric, perf tool output nothing now:

  $ perf stat -a -M imx95_ddr_read.all -I 1000
  $

This command runs on an arm64 machine and the Soc has one DDR hw pmu
except one armv8_cortex_a55 pmu. Their maps show as follows:

const struct pmu_events_map pmu_events_map[] = {
{
	.arch = "arm64",
	.cpuid = "0x00000000410fd050",
	.event_table = {
		.pmus = pmu_events__arm_cortex_a55,
		.num_pmus = ARRAY_SIZE(pmu_events__arm_cortex_a55)
	},
	.metric_table = {
		.pmus = NULL,
		.num_pmus = 0
	}
},

static const struct pmu_sys_events pmu_sys_event_tables[] = {
{
	.event_table = {
		.pmus = pmu_events__freescale_imx95_sys,
		.num_pmus = ARRAY_SIZE(pmu_events__freescale_imx95_sys)
	},
	.metric_table = {
		.pmus = pmu_metrics__freescale_imx95_sys,
		.num_pmus = ARRAY_SIZE(pmu_metrics__freescale_imx95_sys)
	},
	.name = "pmu_events__freescale_imx95_sys",
},

Currently, pmu_metrics_table__find() will return NULL when only do perf
stat on sys metric. Then parse_groups() will never be called to parse
sys metric_name, finally perf tool will exit directly. This should be a
common problem.

To fix the issue, this will keep the logic before commit f20c15d13f01
("perf pmu-events: Remember the perf_events_map for a PMU") to return a
empty metric table rather than a NULL pointer.

This should be fine since the removed part just check if the table match
provided metric_name.  Without these code, the code in parse_groups()
will also check the validity of metrci_name too.

Fixes: f20c15d13f017d4b ("perf pmu-events: Remember the perf_events_map for a PMU")
Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Tested-by: Xu Yang <xu.yang_2@nxp.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Ben Zong-You Xie <ben717@andestech.com>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Clément Le Goffic <clement.legoffic@foss.st.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20241107162035.52206-2-irogers@google.com
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/empty-pmu-events.c | 12 +-----------
 tools/perf/pmu-events/jevents.py         | 12 +-----------
 2 files changed, 2 insertions(+), 22 deletions(-)

diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index 2b7516946dedd..b8719dab264d9 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -585,17 +585,7 @@ const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pm
         if (!map)
                 return NULL;
 
-        if (!pmu)
-                return &map->metric_table;
-
-        for (size_t i = 0; i < map->metric_table.num_pmus; i++) {
-                const struct pmu_table_entry *table_pmu = &map->metric_table.pmus[i];
-                const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
-
-                if (pmu__name_match(pmu, pmu_name))
-                           return &map->metric_table;
-        }
-        return NULL;
+	return &map->metric_table;
 }
 
 const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid)
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 6e71b09dbc2ae..70f4fd5395fb6 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -1101,17 +1101,7 @@ def print_system_mapping_table() -> None:
         if (!map)
                 return NULL;
 
-        if (!pmu)
-                return &map->metric_table;
-
-        for (size_t i = 0; i < map->metric_table.num_pmus; i++) {
-                const struct pmu_table_entry *table_pmu = &map->metric_table.pmus[i];
-                const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
-
-                if (pmu__name_match(pmu, pmu_name))
-                           return &map->metric_table;
-        }
-        return NULL;
+	return &map->metric_table;
 }
 
 const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid)

From c6fafe36bab32b9b24941fe381f0b66751021c25 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 7 Nov 2024 08:20:29 -0800
Subject: [PATCH 1190/1530] perf header: Move is_cpu_online to numa bench
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The helper function is only used in the NUMA benchmark as typically
online CPUs are determined through perf_cpu_map__new_online_cpus().

Reduce the scope of the function for now.

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Xu Yang <xu.yang_2@nxp.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ben Zong-You Xie <ben717@andestech.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Clément Le Goffic <clement.legoffic@foss.st.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20241107162035.52206-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/numa.c  | 53 ++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/header.c | 51 --------------------------------------
 tools/perf/util/header.h |  1 -
 3 files changed, 53 insertions(+), 52 deletions(-)

diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 1fbd7c947abc2..19be2aaf4dc0c 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -27,6 +27,7 @@
 #include <sys/resource.h>
 #include <sys/wait.h>
 #include <sys/prctl.h>
+#include <sys/stat.h>
 #include <sys/types.h>
 #include <linux/kernel.h>
 #include <linux/time64.h>
@@ -35,6 +36,7 @@
 
 #include "../util/header.h"
 #include "../util/mutex.h"
+#include <api/fs/fs.h>
 #include <numa.h>
 #include <numaif.h>
 
@@ -533,6 +535,57 @@ static int parse_cpu_list(const char *arg)
 	return 0;
 }
 
+/*
+ * Check whether a CPU is online
+ *
+ * Returns:
+ *     1 -> if CPU is online
+ *     0 -> if CPU is offline
+ *    -1 -> error case
+ */
+static int is_cpu_online(unsigned int cpu)
+{
+	char *str;
+	size_t strlen;
+	char buf[256];
+	int status = -1;
+	struct stat statbuf;
+
+	snprintf(buf, sizeof(buf),
+		"/sys/devices/system/cpu/cpu%d", cpu);
+	if (stat(buf, &statbuf) != 0)
+		return 0;
+
+	/*
+	 * Check if /sys/devices/system/cpu/cpux/online file
+	 * exists. Some cases cpu0 won't have online file since
+	 * it is not expected to be turned off generally.
+	 * In kernels without CONFIG_HOTPLUG_CPU, this
+	 * file won't exist
+	 */
+	snprintf(buf, sizeof(buf),
+		"/sys/devices/system/cpu/cpu%d/online", cpu);
+	if (stat(buf, &statbuf) != 0)
+		return 1;
+
+	/*
+	 * Read online file using sysfs__read_str.
+	 * If read or open fails, return -1.
+	 * If read succeeds, return value from file
+	 * which gets stored in "str"
+	 */
+	snprintf(buf, sizeof(buf),
+		"devices/system/cpu/cpu%d/online", cpu);
+
+	if (sysfs__read_str(buf, &str, &strlen) < 0)
+		return status;
+
+	status = atoi(str);
+
+	free(str);
+	return status;
+}
+
 static int parse_setup_cpu_list(void)
 {
 	struct thread_data *td;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index fca27b316fafc..c7552a78a7be2 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -987,57 +987,6 @@ static int write_dir_format(struct feat_fd *ff,
 	return do_write(ff, &data->dir.version, sizeof(data->dir.version));
 }
 
-/*
- * Check whether a CPU is online
- *
- * Returns:
- *     1 -> if CPU is online
- *     0 -> if CPU is offline
- *    -1 -> error case
- */
-int is_cpu_online(unsigned int cpu)
-{
-	char *str;
-	size_t strlen;
-	char buf[256];
-	int status = -1;
-	struct stat statbuf;
-
-	snprintf(buf, sizeof(buf),
-		"/sys/devices/system/cpu/cpu%d", cpu);
-	if (stat(buf, &statbuf) != 0)
-		return 0;
-
-	/*
-	 * Check if /sys/devices/system/cpu/cpux/online file
-	 * exists. Some cases cpu0 won't have online file since
-	 * it is not expected to be turned off generally.
-	 * In kernels without CONFIG_HOTPLUG_CPU, this
-	 * file won't exist
-	 */
-	snprintf(buf, sizeof(buf),
-		"/sys/devices/system/cpu/cpu%d/online", cpu);
-	if (stat(buf, &statbuf) != 0)
-		return 1;
-
-	/*
-	 * Read online file using sysfs__read_str.
-	 * If read or open fails, return -1.
-	 * If read succeeds, return value from file
-	 * which gets stored in "str"
-	 */
-	snprintf(buf, sizeof(buf),
-		"devices/system/cpu/cpu%d/online", cpu);
-
-	if (sysfs__read_str(buf, &str, &strlen) < 0)
-		return status;
-
-	status = atoi(str);
-
-	free(str);
-	return status;
-}
-
 #ifdef HAVE_LIBBPF_SUPPORT
 static int write_bpf_prog_info(struct feat_fd *ff,
 			       struct evlist *evlist __maybe_unused)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index a63a361f20f49..e91e89d225371 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -196,7 +196,6 @@ int write_padded(struct feat_fd *fd, const void *bf,
 
 #define MAX_CACHE_LVL 4
 
-int is_cpu_online(unsigned int cpu);
 int build_caches_for_cpu(u32 cpu, struct cpu_cache_level caches[], u32 *cntp);
 
 /*

From cec0d6572a4472848b87d016105634e4eef76d13 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 7 Nov 2024 08:20:30 -0800
Subject: [PATCH 1191/1530] perf header: Refactor get_cpuid to take a CPU for
 ARM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ARM BIG.little has no notion of a constant CPUID for both core
types. To reflect this reality, change the get_cpuid function to also
pass in a possibly unused logical cpu.

If the dummy value (-1) is passed in then ARM can, as currently happens,
select the first logical CPU's "CPUID".

The changes to ARM getcpuid happen in a follow up change.

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Xu Yang <xu.yang_2@nxp.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ben Zong-You Xie <ben717@andestech.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Clément Le Goffic <clement.legoffic@foss.st.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20241107162035.52206-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm64/util/header.c     | 2 +-
 tools/perf/arch/loongarch/util/header.c | 2 +-
 tools/perf/arch/powerpc/util/header.c   | 2 +-
 tools/perf/arch/riscv/util/header.c     | 2 +-
 tools/perf/arch/s390/util/header.c      | 2 +-
 tools/perf/arch/x86/util/auxtrace.c     | 3 ++-
 tools/perf/arch/x86/util/header.c       | 2 +-
 tools/perf/builtin-kvm.c                | 4 +++-
 tools/perf/util/env.c                   | 3 ++-
 tools/perf/util/header.c                | 9 +++++----
 tools/perf/util/header.h                | 2 +-
 11 files changed, 19 insertions(+), 14 deletions(-)

diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index 741df3614a09a..760c21784713b 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -50,7 +50,7 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
 	return ret;
 }
 
-int get_cpuid(char *buf, size_t sz)
+int get_cpuid(char *buf, size_t sz, struct perf_cpu cpu __maybe_unused)
 {
 	struct perf_cpu_map *cpus = perf_cpu_map__new_online_cpus();
 	int ret;
diff --git a/tools/perf/arch/loongarch/util/header.c b/tools/perf/arch/loongarch/util/header.c
index d962dff55512b..f1f0b116962d3 100644
--- a/tools/perf/arch/loongarch/util/header.c
+++ b/tools/perf/arch/loongarch/util/header.c
@@ -70,7 +70,7 @@ static char *_get_cpuid(void)
 	return cpuid;
 }
 
-int get_cpuid(char *buffer, size_t sz)
+int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 {
 	int ret = 0;
 	char *cpuid = _get_cpuid();
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 251cdbf58a4de..6d1a63a2922f8 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -24,7 +24,7 @@ static bool is_compat_mode(void)
 }
 
 int
-get_cpuid(char *buffer, size_t sz)
+get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 {
 	unsigned long pvr;
 	int nb;
diff --git a/tools/perf/arch/riscv/util/header.c b/tools/perf/arch/riscv/util/header.c
index 1b29030021eeb..ebac294c877f0 100644
--- a/tools/perf/arch/riscv/util/header.c
+++ b/tools/perf/arch/riscv/util/header.c
@@ -81,7 +81,7 @@ static char *_get_cpuid(void)
 	return cpuid;
 }
 
-int get_cpuid(char *buffer, size_t sz)
+int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 {
 	char *cpuid = _get_cpuid();
 	int ret = 0;
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
index 7933f6871c818..2add1a5612420 100644
--- a/tools/perf/arch/s390/util/header.c
+++ b/tools/perf/arch/s390/util/header.c
@@ -27,7 +27,7 @@
 #define SYSINFO		"/proc/sysinfo"
 #define SRVLVL		"/proc/service_levels"
 
-int get_cpuid(char *buffer, size_t sz)
+int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 {
 	char *cp, *line = NULL, *line2;
 	char type[8], model[33], version[8], manufacturer[32], authorization[8];
diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
index 354780ff1605d..ecbf61a7eb3a3 100644
--- a/tools/perf/arch/x86/util/auxtrace.c
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -55,11 +55,12 @@ struct auxtrace_record *auxtrace_record__init(struct evlist *evlist,
 					      int *err)
 {
 	char buffer[64];
+	struct perf_cpu cpu = perf_cpu_map__min(evlist->core.all_cpus);
 	int ret;
 
 	*err = 0;
 
-	ret = get_cpuid(buffer, sizeof(buffer));
+	ret = get_cpuid(buffer, sizeof(buffer), cpu);
 	if (ret) {
 		*err = ret;
 		return NULL;
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index a51444a77a5f2..690f86cbbb1ca 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -58,7 +58,7 @@ __get_cpuid(char *buffer, size_t sz, const char *fmt)
 }
 
 int
-get_cpuid(char *buffer, size_t sz)
+get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 {
 	return __get_cpuid(buffer, sz, "%s,%u,%u,%u$");
 }
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 099ce3ebf67ce..274568d712d12 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1226,7 +1226,9 @@ static int cpu_isa_config(struct perf_kvm_stat *kvm)
 	int err;
 
 	if (kvm->live) {
-		err = get_cpuid(buf, sizeof(buf));
+		struct perf_cpu cpu = {-1};
+
+		err = get_cpuid(buf, sizeof(buf), cpu);
 		if (err != 0) {
 			pr_err("Failed to look up CPU type: %s\n",
 			       str_error_r(err, buf, sizeof(buf)));
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index ccb4640266428..93cabdd7ff432 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -373,7 +373,8 @@ int perf_env__read_pmu_mappings(struct perf_env *env)
 int perf_env__read_cpuid(struct perf_env *env)
 {
 	char cpuid[128];
-	int err = get_cpuid(cpuid, sizeof(cpuid));
+	struct perf_cpu cpu = {-1};
+	int err = get_cpuid(cpuid, sizeof(cpuid), cpu);
 
 	if (err)
 		return err;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index c7552a78a7be2..ecf08b458b056 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -856,18 +856,19 @@ int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
  * default get_cpuid(): nothing gets recorded
  * actual implementation must be in arch/$(SRCARCH)/util/header.c
  */
-int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused)
+int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused,
+		     struct perf_cpu cpu __maybe_unused)
 {
 	return ENOSYS; /* Not implemented */
 }
 
-static int write_cpuid(struct feat_fd *ff,
-		       struct evlist *evlist __maybe_unused)
+static int write_cpuid(struct feat_fd *ff, struct evlist *evlist)
 {
+	struct perf_cpu cpu = perf_cpu_map__min(evlist->core.all_cpus);
 	char buffer[64];
 	int ret;
 
-	ret = get_cpuid(buffer, sizeof(buffer));
+	ret = get_cpuid(buffer, sizeof(buffer), cpu);
 	if (ret)
 		return -1;
 
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index e91e89d225371..b77f89de12dde 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -201,7 +201,7 @@ int build_caches_for_cpu(u32 cpu, struct cpu_cache_level caches[], u32 *cntp);
 /*
  * arch specific callback
  */
-int get_cpuid(char *buffer, size_t sz);
+int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu);
 
 char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused);
 int strcmp_cpuid_str(const char *s1, const char *s2);

From 538737da9625d5cceeec3ae90e66afa0792cab50 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 7 Nov 2024 08:20:31 -0800
Subject: [PATCH 1192/1530] perf arm64 header: Use cpu argument in get_cpuid
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the cpu to read the MIDR file requested. If the "any" value (-1) is
passed that keep the behavior of returning the first MIDR file that can
be read.

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Xu Yang <xu.yang_2@nxp.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ben Zong-You Xie <ben717@andestech.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Clément Le Goffic <clement.legoffic@foss.st.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20241107162035.52206-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm64/util/header.c | 63 ++++++++++++++---------------
 tools/perf/util/header.h            |  1 +
 2 files changed, 31 insertions(+), 33 deletions(-)

diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index 760c21784713b..f0907daad3ae7 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -14,55 +14,52 @@
 #define MIDR_REVISION_MASK      GENMASK(3, 0)
 #define MIDR_VARIANT_MASK	GENMASK(23, 20)
 
-static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
+static int _get_cpuid(char *buf, size_t sz, struct perf_cpu cpu)
 {
+	char path[PATH_MAX];
+	FILE *file;
 	const char *sysfs = sysfs__mountpoint();
-	struct perf_cpu cpu;
-	int idx, ret = EINVAL;
 
+	assert(cpu.cpu != -1);
 	if (!sysfs || sz < MIDR_SIZE)
 		return EINVAL;
 
-	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
-		char path[PATH_MAX];
-		FILE *file;
-
-		scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR,
-			  sysfs, cpu.cpu);
-
-		file = fopen(path, "r");
-		if (!file) {
-			pr_debug("fopen failed for file %s\n", path);
-			continue;
-		}
-
-		if (!fgets(buf, MIDR_SIZE, file)) {
-			fclose(file);
-			continue;
-		}
-		fclose(file);
+	scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR, sysfs, cpu.cpu);
 
-		/* got midr break loop */
-		ret = 0;
-		break;
+	file = fopen(path, "r");
+	if (!file) {
+		pr_debug("fopen failed for file %s\n", path);
+		return EINVAL;
 	}
 
-	return ret;
+	if (!fgets(buf, MIDR_SIZE, file)) {
+		pr_debug("Failed to read file %s\n", path);
+		fclose(file);
+		return EINVAL;
+	}
+	fclose(file);
+	return 0;
 }
 
-int get_cpuid(char *buf, size_t sz, struct perf_cpu cpu __maybe_unused)
+int get_cpuid(char *buf, size_t sz, struct perf_cpu cpu)
 {
-	struct perf_cpu_map *cpus = perf_cpu_map__new_online_cpus();
-	int ret;
+	struct perf_cpu_map *cpus;
+	int idx;
+
+	if (cpu.cpu != -1)
+		return _get_cpuid(buf, sz, cpu);
 
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		return EINVAL;
 
-	ret = _get_cpuid(buf, sz, cpus);
-
-	perf_cpu_map__put(cpus);
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+		int ret = _get_cpuid(buf, sz, cpu);
 
-	return ret;
+		if (ret == 0)
+			return 0;
+	}
+	return EINVAL;
 }
 
 char *get_cpuid_str(struct perf_pmu *pmu)
@@ -78,7 +75,7 @@ char *get_cpuid_str(struct perf_pmu *pmu)
 		return NULL;
 
 	/* read midr from list of cpus mapped to this pmu */
-	res = _get_cpuid(buf, MIDR_SIZE, pmu->cpus);
+	res = get_cpuid(buf, MIDR_SIZE, perf_cpu_map__min(pmu->cpus));
 	if (res) {
 		pr_err("failed to get cpuid string for PMU %s\n", pmu->name);
 		free(buf);
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index b77f89de12dde..3bb768455a60b 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include "env.h"
 #include "pmu.h"
+#include <perf/cpumap.h>
 
 enum {
 	HEADER_RESERVED		= 0,	/* always cleared */

From 7463ee17a74090081f0f013fa514904a01fcc954 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 7 Nov 2024 08:20:32 -0800
Subject: [PATCH 1193/1530] perf header: Avoid transitive PMU includes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently satisfied via header.h. Note, pmu.h includes parse-events.h.

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Xu Yang <xu.yang_2@nxp.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ben Zong-You Xie <ben717@andestech.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Clément Le Goffic <clement.legoffic@foss.st.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20241107162035.52206-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/expr.c       | 2 ++
 tools/perf/util/env.c         | 1 +
 tools/perf/util/probe-event.c | 1 +
 3 files changed, 4 insertions(+)

diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index e3aa9d4fcf3a5..d60f1ac1d720e 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -4,6 +4,8 @@
 #include "util/expr.h"
 #include "util/hashmap.h"
 #include "util/header.h"
+#include "util/pmu.h"
+#include "util/pmus.h"
 #include "util/smt.h"
 #include "tests.h"
 #include <math.h>
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 93cabdd7ff432..e2843ca2edd92 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -12,6 +12,7 @@
 #include <sys/utsname.h>
 #include <stdlib.h>
 #include <string.h>
+#include "pmu.h"
 #include "pmus.h"
 #include "strbuf.h"
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 1d51846978717..5dccb92dcde31 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -40,6 +40,7 @@
 #include "session.h"
 #include "string2.h"
 #include "strbuf.h"
+#include "parse-events.h"
 
 #include <subcmd/pager.h>
 #include <linux/ctype.h>

From 494c403ff159fdfdb41c364acbe79f2f53ad585d Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 7 Nov 2024 08:20:33 -0800
Subject: [PATCH 1194/1530] perf header: Pass a perf_cpu rather than a PMU to
 get_cpuid_str
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On ARM the cpuid is dependent on the core type of the CPU in
question. The PMU was passed for the sake of the CPU map but this
means in places a temporary PMU is created just to pass a CPU
value. Just pass the CPU and fix up the callers.

As there are no longer PMU users in header.h, shuffle forward
declarations earlier to work around build failures.

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Xu Yang <xu.yang_2@nxp.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ben Zong-You Xie <ben717@andestech.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Clément Le Goffic <clement.legoffic@foss.st.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20241107162035.52206-7-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm64/util/arm-spe.c     | 14 ++------------
 tools/perf/arch/arm64/util/header.c      | 12 ++++--------
 tools/perf/arch/loongarch/util/header.c  |  2 +-
 tools/perf/arch/powerpc/util/header.c    |  2 +-
 tools/perf/arch/riscv/util/header.c      |  2 +-
 tools/perf/arch/s390/util/header.c       |  4 ++--
 tools/perf/arch/x86/util/header.c        |  3 +--
 tools/perf/pmu-events/empty-pmu-events.c |  5 ++++-
 tools/perf/pmu-events/jevents.py         |  5 ++++-
 tools/perf/tests/expr.c                  |  7 +++----
 tools/perf/util/expr.c                   |  6 +++---
 tools/perf/util/header.c                 | 22 +++++++++++++++++++++-
 tools/perf/util/header.h                 | 19 ++++++++++---------
 tools/perf/util/pmu.c                    | 20 --------------------
 tools/perf/util/pmu.h                    |  1 -
 15 files changed, 57 insertions(+), 67 deletions(-)

diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 7ccdea3cd461a..22b19dcc6beb8 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -23,6 +23,7 @@
 #include "../../../util/debug.h"
 #include "../../../util/auxtrace.h"
 #include "../../../util/record.h"
+#include "../../../util/header.h"
 #include "../../../util/arm-spe.h"
 #include <tools/libc_compat.h> // reallocarray
 
@@ -85,22 +86,11 @@ static int arm_spe_save_cpu_header(struct auxtrace_record *itr,
 	struct arm_spe_recording *sper =
 			container_of(itr, struct arm_spe_recording, itr);
 	struct perf_pmu *pmu = NULL;
-	struct perf_pmu tmp_pmu;
-	char cpu_id_str[16];
 	char *cpuid = NULL;
 	u64 val;
 
-	snprintf(cpu_id_str, sizeof(cpu_id_str), "%d", cpu.cpu);
-	tmp_pmu.cpus = perf_cpu_map__new(cpu_id_str);
-	if (!tmp_pmu.cpus)
-		return -ENOMEM;
-
 	/* Read CPU MIDR */
-	cpuid = perf_pmu__getcpuid(&tmp_pmu);
-
-	/* The CPU map will not be used anymore, release it */
-	perf_cpu_map__put(tmp_pmu.cpus);
-
+	cpuid = get_cpuid_allow_env_override(cpu);
 	if (!cpuid)
 		return -ENOMEM;
 	val = strtol(cpuid, NULL, 16);
diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index f0907daad3ae7..f445a2dd62934 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -62,22 +62,18 @@ int get_cpuid(char *buf, size_t sz, struct perf_cpu cpu)
 	return EINVAL;
 }
 
-char *get_cpuid_str(struct perf_pmu *pmu)
+char *get_cpuid_str(struct perf_cpu cpu)
 {
-	char *buf = NULL;
+	char *buf = malloc(MIDR_SIZE);
 	int res;
 
-	if (!pmu || !pmu->cpus)
-		return NULL;
-
-	buf = malloc(MIDR_SIZE);
 	if (!buf)
 		return NULL;
 
 	/* read midr from list of cpus mapped to this pmu */
-	res = get_cpuid(buf, MIDR_SIZE, perf_cpu_map__min(pmu->cpus));
+	res = get_cpuid(buf, MIDR_SIZE, cpu);
 	if (res) {
-		pr_err("failed to get cpuid string for PMU %s\n", pmu->name);
+		pr_err("failed to get cpuid string for CPU %d\n", cpu.cpu);
 		free(buf);
 		buf = NULL;
 	}
diff --git a/tools/perf/arch/loongarch/util/header.c b/tools/perf/arch/loongarch/util/header.c
index f1f0b116962d3..0c6d823334a21 100644
--- a/tools/perf/arch/loongarch/util/header.c
+++ b/tools/perf/arch/loongarch/util/header.c
@@ -90,7 +90,7 @@ int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 	return ret;
 }
 
-char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+char *get_cpuid_str(struct perf_cpu cpu __maybe_unused)
 {
 	return _get_cpuid();
 }
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 6d1a63a2922f8..c7df534dbf8f8 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -42,7 +42,7 @@ get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 }
 
 char *
-get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+get_cpuid_str(struct perf_cpu cpu __maybe_unused)
 {
 	char *bufp;
 	unsigned long pvr;
diff --git a/tools/perf/arch/riscv/util/header.c b/tools/perf/arch/riscv/util/header.c
index ebac294c877f0..4b839203d4a54 100644
--- a/tools/perf/arch/riscv/util/header.c
+++ b/tools/perf/arch/riscv/util/header.c
@@ -98,7 +98,7 @@ int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 }
 
 char *
-get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+get_cpuid_str(struct perf_cpu cpu __maybe_unused)
 {
 	return _get_cpuid();
 }
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
index 2add1a5612420..db54677a17d24 100644
--- a/tools/perf/arch/s390/util/header.c
+++ b/tools/perf/arch/s390/util/header.c
@@ -137,11 +137,11 @@ int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 	return (nbytes >= sz) ? ENOBUFS : 0;
 }
 
-char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+char *get_cpuid_str(struct perf_cpu cpu)
 {
 	char *buf = malloc(128);
 
-	if (buf && get_cpuid(buf, 128))
+	if (buf && get_cpuid(buf, 128, cpu))
 		zfree(&buf);
 	return buf;
 }
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index 690f86cbbb1ca..412977f8aa837 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -63,8 +63,7 @@ get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 	return __get_cpuid(buffer, sz, "%s,%u,%u,%u$");
 }
 
-char *
-get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+char *get_cpuid_str(struct perf_cpu cpu __maybe_unused)
 {
 	char *buf = malloc(128);
 
diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index b8719dab264d9..51ca8d61c15d8 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -515,13 +515,16 @@ static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
         } last_map_search;
         static bool has_last_result, has_last_map_search;
         const struct pmu_events_map *map = NULL;
+        struct perf_cpu cpu = {-1};
         char *cpuid = NULL;
         size_t i;
 
         if (has_last_result && last_result.pmu == pmu)
                 return last_result.map;
 
-        cpuid = perf_pmu__getcpuid(pmu);
+        if (pmu)
+                cpu = perf_cpu_map__min(pmu->cpus);
+        cpuid = get_cpuid_allow_env_override(cpu);
 
         /*
          * On some platforms which uses cpus map, cpuid can be NULL for
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 70f4fd5395fb6..b5ff872e2beb3 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -1031,13 +1031,16 @@ def print_system_mapping_table() -> None:
         } last_map_search;
         static bool has_last_result, has_last_map_search;
         const struct pmu_events_map *map = NULL;
+        struct perf_cpu cpu = {-1};
         char *cpuid = NULL;
         size_t i;
 
         if (has_last_result && last_result.pmu == pmu)
                 return last_result.map;
 
-        cpuid = perf_pmu__getcpuid(pmu);
+        if (pmu)
+                cpu = perf_cpu_map__min(pmu->cpus);
+        cpuid = get_cpuid_allow_env_override(cpu);
 
         /*
          * On some platforms which uses cpus map, cpuid can be NULL for
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index d60f1ac1d720e..41ff1affdfcdf 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -4,10 +4,9 @@
 #include "util/expr.h"
 #include "util/hashmap.h"
 #include "util/header.h"
-#include "util/pmu.h"
-#include "util/pmus.h"
 #include "util/smt.h"
 #include "tests.h"
+#include <perf/cpumap.h>
 #include <math.h>
 #include <stdlib.h>
 #include <string.h>
@@ -78,8 +77,8 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 	struct expr_parse_ctx *ctx;
 	bool is_intel = false;
 	char strcmp_cpuid_buf[256];
-	struct perf_pmu *pmu = perf_pmus__find_core_pmu();
-	char *cpuid = perf_pmu__getcpuid(pmu);
+	struct perf_cpu cpu = {-1};
+	char *cpuid = get_cpuid_allow_env_override(cpu);
 	char *escaped_cpuid1, *escaped_cpuid2;
 
 	TEST_ASSERT_VAL("get_cpuid", cpuid);
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 5e3732bc2fa52..f289044a1f7c6 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -8,7 +8,6 @@
 #include "debug.h"
 #include "evlist.h"
 #include "expr.h"
-#include "pmu.h"
 #include "smt.h"
 #include "tool_pmu.h"
 #include <util/expr-bison.h>
@@ -16,6 +15,7 @@
 #include "util/hashmap.h"
 #include "util/header.h"
 #include "util/pmu.h"
+#include <perf/cpumap.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
@@ -456,8 +456,8 @@ double expr__strcmp_cpuid_str(const struct expr_parse_ctx *ctx __maybe_unused,
 		       bool compute_ids __maybe_unused, const char *test_id)
 {
 	double ret;
-	struct perf_pmu *pmu = perf_pmus__find_core_pmu();
-	char *cpuid = perf_pmu__getcpuid(pmu);
+	struct perf_cpu cpu = {-1};
+	char *cpuid = get_cpuid_allow_env_override(cpu);
 
 	if (!cpuid)
 		return NAN;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index ecf08b458b056..3451e542b69a8 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -819,11 +819,31 @@ static int write_group_desc(struct feat_fd *ff,
  * Each architecture should provide a more precise id string that
  * can be use to match the architecture's "mapfile".
  */
-char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+char * __weak get_cpuid_str(struct perf_cpu cpu __maybe_unused)
 {
 	return NULL;
 }
 
+char *get_cpuid_allow_env_override(struct perf_cpu cpu)
+{
+	char *cpuid;
+	static bool printed;
+
+	cpuid = getenv("PERF_CPUID");
+	if (cpuid)
+		cpuid = strdup(cpuid);
+	if (!cpuid)
+		cpuid = get_cpuid_str(cpu);
+	if (!cpuid)
+		return NULL;
+
+	if (!printed) {
+		pr_debug("Using CPUID %s\n", cpuid);
+		printed = true;
+	}
+	return cpuid;
+}
+
 /* Return zero when the cpuid from the mapfile.csv matches the
  * cpuid string generated on this platform.
  * Otherwise return non-zero.
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 3bb768455a60b..5201af6305f4b 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -10,9 +10,14 @@
 #include <linux/bitmap.h>
 #include <linux/types.h>
 #include "env.h"
-#include "pmu.h"
 #include <perf/cpumap.h>
 
+struct evlist;
+union perf_event;
+struct perf_header;
+struct perf_session;
+struct perf_tool;
+
 enum {
 	HEADER_RESERVED		= 0,	/* always cleared */
 	HEADER_FIRST_FEATURE	= 1,
@@ -92,8 +97,6 @@ struct perf_pipe_file_header {
 	u64				size;
 };
 
-struct perf_header;
-
 int perf_file_header__read(struct perf_file_header *header,
 			   struct perf_header *ph, int fd);
 
@@ -125,11 +128,6 @@ struct perf_header_feature_ops {
 	bool	   synthesize;
 };
 
-struct evlist;
-struct perf_session;
-struct perf_tool;
-union perf_event;
-
 extern const char perf_version_string[];
 
 int perf_session__read_header(struct perf_session *session);
@@ -204,6 +202,9 @@ int build_caches_for_cpu(u32 cpu, struct cpu_cache_level caches[], u32 *cntp);
  */
 int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu);
 
-char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused);
+char *get_cpuid_str(struct perf_cpu cpu);
+
+char *get_cpuid_allow_env_override(struct perf_cpu cpu);
+
 int strcmp_cpuid_str(const char *s1, const char *s2);
 #endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index a02df2c80f421..13067b9901a63 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -819,26 +819,6 @@ static int is_sysfs_pmu_core(const char *name)
 	return file_available(path);
 }
 
-char *perf_pmu__getcpuid(struct perf_pmu *pmu)
-{
-	char *cpuid;
-	static bool printed;
-
-	cpuid = getenv("PERF_CPUID");
-	if (cpuid)
-		cpuid = strdup(cpuid);
-	if (!cpuid)
-		cpuid = get_cpuid_str(pmu);
-	if (!cpuid)
-		return NULL;
-
-	if (!printed) {
-		pr_debug("Using CPUID %s\n", cpuid);
-		printed = true;
-	}
-	return cpuid;
-}
-
 __weak const struct pmu_metrics_table *pmu_metrics_table__find(void)
 {
 	return perf_pmu__find_metrics_table(NULL);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index d511bf7cc9d06..bd45d4af41602 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -262,7 +262,6 @@ void perf_pmu__arch_init(struct perf_pmu *pmu);
 void pmu_add_cpu_aliases_table(struct perf_pmu *pmu,
 			       const struct pmu_events_table *table);
 
-char *perf_pmu__getcpuid(struct perf_pmu *pmu);
 const struct pmu_metrics_table *pmu_metrics_table__find(void);
 bool pmu_uncore_identifier_match(const char *compat, const char *id);
 

From 0434410fa45c9aff6183bb99e0fbc255d75fcf95 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 7 Nov 2024 08:20:34 -0800
Subject: [PATCH 1195/1530] perf jevents: Add map_for_cpu()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PMU is no longer part of the map finding process and for metrics
doesn't make sense as they lack a PMU.

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Xu Yang <xu.yang_2@nxp.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ben Zong-You Xie <ben717@andestech.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Clément Le Goffic <clement.legoffic@foss.st.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20241107162035.52206-8-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/empty-pmu-events.c | 20 +++++++++++++-------
 tools/perf/pmu-events/jevents.py         | 20 +++++++++++++-------
 2 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index 51ca8d61c15d8..17306e316a3c7 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -503,11 +503,11 @@ int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table,
         return 0;
 }
 
-static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
+static const struct pmu_events_map *map_for_cpu(struct perf_cpu cpu)
 {
         static struct {
                 const struct pmu_events_map *map;
-                struct perf_pmu *pmu;
+                struct perf_cpu cpu;
         } last_result;
         static struct {
                 const struct pmu_events_map *map;
@@ -515,15 +515,12 @@ static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
         } last_map_search;
         static bool has_last_result, has_last_map_search;
         const struct pmu_events_map *map = NULL;
-        struct perf_cpu cpu = {-1};
         char *cpuid = NULL;
         size_t i;
 
-        if (has_last_result && last_result.pmu == pmu)
+        if (has_last_result && last_result.cpu.cpu == cpu.cpu)
                 return last_result.map;
 
-        if (pmu)
-                cpu = perf_cpu_map__min(pmu->cpus);
         cpuid = get_cpuid_allow_env_override(cpu);
 
         /*
@@ -555,12 +552,21 @@ static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
                has_last_map_search = true;
         }
 out_update_last_result:
-        last_result.pmu = pmu;
+        last_result.cpu = cpu;
         last_result.map = map;
         has_last_result = true;
         return map;
 }
 
+static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
+{
+        struct perf_cpu cpu = {-1};
+
+        if (pmu)
+                cpu = perf_cpu_map__min(pmu->cpus);
+        return map_for_cpu(cpu);
+}
+
 const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu)
 {
         const struct pmu_events_map *map = map_for_pmu(pmu);
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index b5ff872e2beb3..e44b72e56ac39 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -1019,11 +1019,11 @@ def print_system_mapping_table() -> None:
         return 0;
 }
 
-static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
+static const struct pmu_events_map *map_for_cpu(struct perf_cpu cpu)
 {
         static struct {
                 const struct pmu_events_map *map;
-                struct perf_pmu *pmu;
+                struct perf_cpu cpu;
         } last_result;
         static struct {
                 const struct pmu_events_map *map;
@@ -1031,15 +1031,12 @@ def print_system_mapping_table() -> None:
         } last_map_search;
         static bool has_last_result, has_last_map_search;
         const struct pmu_events_map *map = NULL;
-        struct perf_cpu cpu = {-1};
         char *cpuid = NULL;
         size_t i;
 
-        if (has_last_result && last_result.pmu == pmu)
+        if (has_last_result && last_result.cpu.cpu == cpu.cpu)
                 return last_result.map;
 
-        if (pmu)
-                cpu = perf_cpu_map__min(pmu->cpus);
         cpuid = get_cpuid_allow_env_override(cpu);
 
         /*
@@ -1071,12 +1068,21 @@ def print_system_mapping_table() -> None:
                has_last_map_search = true;
         }
 out_update_last_result:
-        last_result.pmu = pmu;
+        last_result.cpu = cpu;
         last_result.map = map;
         has_last_result = true;
         return map;
 }
 
+static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
+{
+        struct perf_cpu cpu = {-1};
+
+        if (pmu)
+                cpu = perf_cpu_map__min(pmu->cpus);
+        return map_for_cpu(cpu);
+}
+
 const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu)
 {
         const struct pmu_events_map *map = map_for_pmu(pmu);

From 8f997865ee9e73281a92a7ab7ebcab84e1a36d83 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 7 Nov 2024 08:20:35 -0800
Subject: [PATCH 1196/1530] perf pmu: Move pmu_metrics_table__find and remove
 ARM override
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move pmu_metrics_table__find() to the jevents.py generated pmu-events.c
and remove indirection override for ARM.

The movement removes perf_pmu__find_metrics_table that exists to enable
the ARM override.

The ARM override isn't necessary as just the CPUID, not PMU, is used in
the metric table lookup.

On non-ARM the CPU argument is just ignored for the CPUID, for ARM -1 is
passed so that the CPUID for the first logical CPU is read.

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Xu Yang <xu.yang_2@nxp.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ben Zong-You Xie <ben717@andestech.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Clément Le Goffic <clement.legoffic@foss.st.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20241107162035.52206-9-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm64/util/pmu.c         | 20 --------------------
 tools/perf/pmu-events/empty-pmu-events.c | 10 ++++------
 tools/perf/pmu-events/jevents.py         | 10 ++++------
 tools/perf/pmu-events/pmu-events.h       |  2 +-
 tools/perf/util/pmu.c                    |  5 -----
 tools/perf/util/pmu.h                    |  1 -
 6 files changed, 9 insertions(+), 39 deletions(-)

diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c
index a0964b191fcb9..895fb0d0610cf 100644
--- a/tools/perf/arch/arm64/util/pmu.c
+++ b/tools/perf/arch/arm64/util/pmu.c
@@ -1,29 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <internal/cpumap.h>
-#include "../../../util/cpumap.h"
-#include "../../../util/header.h"
 #include "../../../util/pmu.h"
 #include "../../../util/pmus.h"
 #include "../../../util/tool_pmu.h"
 #include <api/fs/fs.h>
-#include <math.h>
-
-const struct pmu_metrics_table *pmu_metrics_table__find(void)
-{
-	struct perf_pmu *pmu;
-
-	/* Metrics aren't currently supported on heterogeneous Arm systems */
-	if (perf_pmus__num_core_pmus() > 1)
-		return NULL;
-
-	/* Doesn't matter which one here because they'll all be the same */
-	pmu = perf_pmus__find_core_pmu();
-	if (pmu)
-		return perf_pmu__find_metrics_table(pmu);
-
-	return NULL;
-}
 
 u64 tool_pmu__cpu_slots_per_cycle(void)
 {
diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index 17306e316a3c7..1c7a2cfa321fc 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -587,14 +587,12 @@ const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu)
         return NULL;
 }
 
-const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pmu)
+const struct pmu_metrics_table *pmu_metrics_table__find(void)
 {
-        const struct pmu_events_map *map = map_for_pmu(pmu);
-
-        if (!map)
-                return NULL;
+        struct perf_cpu cpu = {-1};
+        const struct pmu_events_map *map = map_for_cpu(cpu);
 
-	return &map->metric_table;
+        return map ? &map->metric_table : NULL;
 }
 
 const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid)
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index e44b72e56ac39..d781a377757a1 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -1103,14 +1103,12 @@ def print_system_mapping_table() -> None:
         return NULL;
 }
 
-const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pmu)
+const struct pmu_metrics_table *pmu_metrics_table__find(void)
 {
-        const struct pmu_events_map *map = map_for_pmu(pmu);
-
-        if (!map)
-                return NULL;
+        struct perf_cpu cpu = {-1};
+        const struct pmu_events_map *map = map_for_cpu(cpu);
 
-	return &map->metric_table;
+        return map ? &map->metric_table : NULL;
 }
 
 const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid)
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index 5435ad92180cf..675562e6f7704 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -103,7 +103,7 @@ int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pm
 				     void *data);
 
 const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu);
-const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pmu);
+const struct pmu_metrics_table *pmu_metrics_table__find(void);
 const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid);
 const struct pmu_metrics_table *find_core_metrics_table(const char *arch, const char *cpuid);
 int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 13067b9901a63..08a9d0bd93017 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -819,11 +819,6 @@ static int is_sysfs_pmu_core(const char *name)
 	return file_available(path);
 }
 
-__weak const struct pmu_metrics_table *pmu_metrics_table__find(void)
-{
-	return perf_pmu__find_metrics_table(NULL);
-}
-
 /**
  * Return the length of the PMU name not including the suffix for uncore PMUs.
  *
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index bd45d4af41602..dbed6c243a5ef 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -262,7 +262,6 @@ void perf_pmu__arch_init(struct perf_pmu *pmu);
 void pmu_add_cpu_aliases_table(struct perf_pmu *pmu,
 			       const struct pmu_events_table *table);
 
-const struct pmu_metrics_table *pmu_metrics_table__find(void);
 bool pmu_uncore_identifier_match(const char *compat, const char *id);
 
 int perf_pmu__convert_scale(const char *scale, char **end, double *sval);

From 85c60a01b85ee956adf8d46c253fc50f75363e8f Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Tue, 22 Oct 2024 01:29:40 +0100
Subject: [PATCH 1197/1530] perf: Remove unused del_perf_probe_events()

del_perf_probe_events() last use was removed by commit 3d6dfae889174340
("perf parse-events: Remove BPF event support")

Remove it.

It was the last user of probe_file__del_events(), so remove it as well.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241022002940.302946-1-linux@treblig.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/probe-event.c | 35 -----------------------------------
 tools/perf/util/probe-event.h |  2 --
 tools/perf/util/probe-file.c  | 19 -------------------
 tools/perf/util/probe-file.h  |  1 -
 4 files changed, 57 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 5dccb92dcde31..6d51a4c98ad7c 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -3754,41 +3754,6 @@ void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 	}
 }
 
-int del_perf_probe_events(struct strfilter *filter)
-{
-	int ret, ret2, ufd = -1, kfd = -1;
-	char *str = strfilter__string(filter);
-
-	if (!str)
-		return -EINVAL;
-
-	/* Get current event names */
-	ret = probe_file__open_both(&kfd, &ufd, PF_FL_RW);
-	if (ret < 0)
-		goto out;
-
-	ret = probe_file__del_events(kfd, filter);
-	if (ret < 0 && ret != -ENOENT)
-		goto error;
-
-	ret2 = probe_file__del_events(ufd, filter);
-	if (ret2 < 0 && ret2 != -ENOENT) {
-		ret = ret2;
-		goto error;
-	}
-	ret = 0;
-
-error:
-	if (kfd >= 0)
-		close(kfd);
-	if (ufd >= 0)
-		close(ufd);
-out:
-	free(str);
-
-	return ret;
-}
-
 int show_available_funcs(const char *target, struct nsinfo *nsi,
 			 struct strfilter *_filter, bool user)
 {
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 4850e52f274e4..61a5f4ff4e9c6 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -167,8 +167,6 @@ void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs);
 
 struct strfilter;
 
-int del_perf_probe_events(struct strfilter *filter);
-
 int show_perf_probe_event(const char *group, const char *event,
 			  struct perf_probe_event *pev,
 			  const char *module, bool use_stdout);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 3d50de3217d50..ec8ac242fedb5 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -366,25 +366,6 @@ int probe_file__del_strlist(int fd, struct strlist *namelist)
 	return ret;
 }
 
-int probe_file__del_events(int fd, struct strfilter *filter)
-{
-	struct strlist *namelist;
-	int ret;
-
-	namelist = strlist__new(NULL, NULL);
-	if (!namelist)
-		return -ENOMEM;
-
-	ret = probe_file__get_events(fd, filter, namelist);
-	if (ret < 0)
-		goto out;
-
-	ret = probe_file__del_strlist(fd, namelist);
-out:
-	strlist__delete(namelist);
-	return ret;
-}
-
 /* Caller must ensure to remove this entry from list */
 static void probe_cache_entry__delete(struct probe_cache_entry *entry)
 {
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 0dba88c0f5f04..c2bb6a5b9dcce 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -44,7 +44,6 @@ struct strlist *probe_file__get_namelist(int fd);
 struct strlist *probe_file__get_rawlist(int fd);
 int probe_file__add_event(int fd, struct probe_trace_event *tev);
 
-int probe_file__del_events(int fd, struct strfilter *filter);
 int probe_file__get_events(int fd, struct strfilter *filter,
 				  struct strlist *plist);
 int probe_file__del_strlist(int fd, struct strlist *namelist);

From 9ef8568bd7cddf59e1ff6ee1b7d799539e331b73 Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Wed, 16 Oct 2024 23:41:50 +0800
Subject: [PATCH 1198/1530] mm/slub: Consider kfence case for get_orig_size()

When 'orig_size' of kmalloc object is enabled by debug option, it
should either contains the actual requested size or the cache's
'object_size'.

But it's not true if that object is a kfence-allocated one, and the
data at 'orig_size' offset of metadata could be zero or other values.
This is not a big issue for current 'orig_size' usage, as init_object()
and check_object() during alloc/free process will be skipped for kfence
addresses. But it could cause trouble for other usage in future.

Use the existing kfence helper kfence_ksize() which can return the
real original request size.

Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slub.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/slub.c b/mm/slub.c
index 2ccb016c7f998..e186e7a675977 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -768,6 +768,9 @@ static inline unsigned int get_orig_size(struct kmem_cache *s, void *object)
 {
 	void *p = kasan_reset_tag(object);
 
+	if (is_kfence_address(object))
+		return kfence_ksize(object);
+
 	if (!slub_debug_orig_size(s))
 		return s->object_size;
 

From 5474d33ca48e7764ccc38b2ac089863cca83280a Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Wed, 16 Oct 2024 23:41:51 +0800
Subject: [PATCH 1199/1530] mm/slub: Improve redzone check and zeroing for
 krealloc()

For current krealloc(), one problem is its caller doesn't pass the old
request size, say the object is 64 bytes kmalloc one, but caller may
only requested 48 bytes. Then when krealloc() shrinks or grows in the
same object, or allocate a new bigger object, it lacks this 'original
size' information to do accurate data preserving or zeroing (when
__GFP_ZERO is set).

Thus with slub debug redzone and object tracking enabled, parts of the
object after krealloc() might contain redzone data instead of zeroes,
which is violating the __GFP_ZERO guarantees. Good thing is in this
case, kmalloc caches do have this 'orig_size' feature. So solve the
problem by utilize 'org_size' to do accurate data zeroing and preserving.

[Thanks to syzbot and V, Narasimhan for discovering kfence and big
 kmalloc related issues in early patch version]

Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slub.c | 80 ++++++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 58 insertions(+), 22 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index e186e7a675977..4284cbe41d0d0 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4718,34 +4718,66 @@ static __always_inline __realloc_size(2) void *
 __do_krealloc(const void *p, size_t new_size, gfp_t flags)
 {
 	void *ret;
-	size_t ks;
+	size_t ks = 0;
+	int orig_size = 0;
+	struct kmem_cache *s = NULL;
 
-	/* Check for double-free before calling ksize. */
-	if (likely(!ZERO_OR_NULL_PTR(p))) {
-		if (!kasan_check_byte(p))
-			return NULL;
-		ks = ksize(p);
-	} else
-		ks = 0;
+	if (unlikely(ZERO_OR_NULL_PTR(p)))
+		goto alloc_new;
 
-	/* If the object still fits, repoison it precisely. */
-	if (ks >= new_size) {
-		/* Zero out spare memory. */
-		if (want_init_on_alloc(flags)) {
-			kasan_disable_current();
-			memset(kasan_reset_tag(p) + new_size, 0, ks - new_size);
-			kasan_enable_current();
+	/* Check for double-free. */
+	if (!kasan_check_byte(p))
+		return NULL;
+
+	if (is_kfence_address(p)) {
+		ks = orig_size = kfence_ksize(p);
+	} else {
+		struct folio *folio;
+
+		folio = virt_to_folio(p);
+		if (unlikely(!folio_test_slab(folio))) {
+			/* Big kmalloc object */
+			WARN_ON(folio_size(folio) <= KMALLOC_MAX_CACHE_SIZE);
+			WARN_ON(p != folio_address(folio));
+			ks = folio_size(folio);
+		} else {
+			s = folio_slab(folio)->slab_cache;
+			orig_size = get_orig_size(s, (void *)p);
+			ks = s->object_size;
 		}
+	}
 
-		p = kasan_krealloc((void *)p, new_size, flags);
-		return (void *)p;
+	/* If the old object doesn't fit, allocate a bigger one */
+	if (new_size > ks)
+		goto alloc_new;
+
+	/* Zero out spare memory. */
+	if (want_init_on_alloc(flags)) {
+		kasan_disable_current();
+		if (orig_size && orig_size < new_size)
+			memset(kasan_reset_tag(p) + orig_size, 0, new_size - orig_size);
+		else
+			memset(kasan_reset_tag(p) + new_size, 0, ks - new_size);
+		kasan_enable_current();
 	}
 
+	/* Setup kmalloc redzone when needed */
+	if (s && slub_debug_orig_size(s)) {
+		set_orig_size(s, (void *)p, new_size);
+		if (s->flags & SLAB_RED_ZONE && new_size < ks)
+			memset_no_sanitize_memory(kasan_reset_tag(p) + new_size,
+						SLUB_RED_ACTIVE, ks - new_size);
+	}
+
+	p = kasan_krealloc(p, new_size, flags);
+	return (void *)p;
+
+alloc_new:
 	ret = kmalloc_node_track_caller_noprof(new_size, flags, NUMA_NO_NODE, _RET_IP_);
 	if (ret && p) {
 		/* Disable KASAN checks as the object's redzone is accessed. */
 		kasan_disable_current();
-		memcpy(ret, kasan_reset_tag(p), ks);
+		memcpy(ret, kasan_reset_tag(p), orig_size ?: ks);
 		kasan_enable_current();
 	}
 
@@ -4766,16 +4798,20 @@ __do_krealloc(const void *p, size_t new_size, gfp_t flags)
  * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that
  * __GFP_ZERO is not fully honored by this API.
  *
- * This is the case, since krealloc() only knows about the bucket size of an
- * allocation (but not the exact size it was allocated with) and hence
- * implements the following semantics for shrinking and growing buffers with
- * __GFP_ZERO.
+ * When slub_debug_orig_size() is off, krealloc() only knows about the bucket
+ * size of an allocation (but not the exact size it was allocated with) and
+ * hence implements the following semantics for shrinking and growing buffers
+ * with __GFP_ZERO.
  *
  *         new             bucket
  * 0       size             size
  * |--------|----------------|
  * |  keep  |      zero      |
  *
+ * Otherwise, the original allocation size 'orig_size' could be used to
+ * precisely clear the requested size, and the new size will also be stored
+ * as the new 'orig_size'.
+ *
  * In any case, the contents of the object pointed to are preserved up to the
  * lesser of the new and old sizes.
  *

From 080c8579c37ec9c11cfb8b9eb25b74912b33dc06 Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Wed, 16 Oct 2024 23:41:52 +0800
Subject: [PATCH 1200/1530] mm/slub, kunit: Add testcase for krealloc redzone
 and zeroing

Danilo Krummrich raised issue about krealloc+GFP_ZERO [1], and Vlastimil
suggested to add some test case which can sanity test the kmalloc-redzone
and zeroing by utilizing the kmalloc's 'orig_size' debug feature.

It covers the grow and shrink case of krealloc() re-using current kmalloc
object, and the case of re-allocating a new bigger object.

[1]. https://lore.kernel.org/lkml/20240812223707.32049-1-dakr@kernel.org/

Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 lib/slub_kunit.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/lib/slub_kunit.c b/lib/slub_kunit.c
index 33564f965958c..f11691315c2fb 100644
--- a/lib/slub_kunit.c
+++ b/lib/slub_kunit.c
@@ -192,6 +192,47 @@ static void test_leak_destroy(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, 2, slab_errors);
 }
 
+static void test_krealloc_redzone_zeroing(struct kunit *test)
+{
+	u8 *p;
+	int i;
+	struct kmem_cache *s = test_kmem_cache_create("TestSlub_krealloc", 64,
+				SLAB_KMALLOC|SLAB_STORE_USER|SLAB_RED_ZONE);
+
+	p = alloc_hooks(__kmalloc_cache_noprof(s, GFP_KERNEL, 48));
+	memset(p, 0xff, 48);
+
+	kasan_disable_current();
+	OPTIMIZER_HIDE_VAR(p);
+
+	/* Test shrink */
+	p = krealloc(p, 40, GFP_KERNEL | __GFP_ZERO);
+	for (i = 40; i < 64; i++)
+		KUNIT_EXPECT_EQ(test, p[i], SLUB_RED_ACTIVE);
+
+	/* Test grow within the same 64B kmalloc object */
+	p = krealloc(p, 56, GFP_KERNEL | __GFP_ZERO);
+	for (i = 40; i < 56; i++)
+		KUNIT_EXPECT_EQ(test, p[i], 0);
+	for (i = 56; i < 64; i++)
+		KUNIT_EXPECT_EQ(test, p[i], SLUB_RED_ACTIVE);
+
+	validate_slab_cache(s);
+	KUNIT_EXPECT_EQ(test, 0, slab_errors);
+
+	memset(p, 0xff, 56);
+	/* Test grow with allocating a bigger 128B object */
+	p = krealloc(p, 112, GFP_KERNEL | __GFP_ZERO);
+	for (i = 0; i < 56; i++)
+		KUNIT_EXPECT_EQ(test, p[i], 0xff);
+	for (i = 56; i < 112; i++)
+		KUNIT_EXPECT_EQ(test, p[i], 0);
+
+	kfree(p);
+	kasan_enable_current();
+	kmem_cache_destroy(s);
+}
+
 static int test_init(struct kunit *test)
 {
 	slab_errors = 0;
@@ -214,6 +255,7 @@ static struct kunit_case test_cases[] = {
 	KUNIT_CASE(test_kmalloc_redzone_access),
 	KUNIT_CASE(test_kfree_rcu),
 	KUNIT_CASE(test_leak_destroy),
+	KUNIT_CASE(test_krealloc_redzone_zeroing),
 	{}
 };
 

From dbc16915279a548a204154368da23d402c141c81 Mon Sep 17 00:00:00 2001
From: "yuan.gao" <yuan.gao@ucloud.cn>
Date: Fri, 18 Oct 2024 14:44:35 +0800
Subject: [PATCH 1201/1530] mm/slub: Avoid list corruption when removing a slab
 from the full list

Boot with slub_debug=UFPZ.

If allocated object failed in alloc_consistency_checks, all objects of
the slab will be marked as used, and then the slab will be removed from
the partial list.

When an object belonging to the slab got freed later, the remove_full()
function is called. Because the slab is neither on the partial list nor
on the full list, it eventually lead to a list corruption (actually a
list poison being detected).

So we need to mark and isolate the slab page with metadata corruption,
do not put it back in circulation.

Because the debug caches avoid all the fastpaths, reusing the frozen bit
to mark slab page with metadata corruption seems to be fine.

[ 4277.385669] list_del corruption, ffffea00044b3e50->next is LIST_POISON1 (dead000000000100)
[ 4277.387023] ------------[ cut here ]------------
[ 4277.387880] kernel BUG at lib/list_debug.c:56!
[ 4277.388680] invalid opcode: 0000 [#1] PREEMPT SMP PTI
[ 4277.389562] CPU: 5 PID: 90 Comm: kworker/5:1 Kdump: loaded Tainted: G           OE      6.6.1-1 #1
[ 4277.392113] Workqueue: xfs-inodegc/vda1 xfs_inodegc_worker [xfs]
[ 4277.393551] RIP: 0010:__list_del_entry_valid_or_report+0x7b/0xc0
[ 4277.394518] Code: 48 91 82 e8 37 f9 9a ff 0f 0b 48 89 fe 48 c7 c7 28 49 91 82 e8 26 f9 9a ff 0f 0b 48 89 fe 48 c7 c7 58 49 91
[ 4277.397292] RSP: 0018:ffffc90000333b38 EFLAGS: 00010082
[ 4277.398202] RAX: 000000000000004e RBX: ffffea00044b3e50 RCX: 0000000000000000
[ 4277.399340] RDX: 0000000000000002 RSI: ffffffff828f8715 RDI: 00000000ffffffff
[ 4277.400545] RBP: ffffea00044b3e40 R08: 0000000000000000 R09: ffffc900003339f0
[ 4277.401710] R10: 0000000000000003 R11: ffffffff82d44088 R12: ffff888112cf9910
[ 4277.402887] R13: 0000000000000001 R14: 0000000000000001 R15: ffff8881000424c0
[ 4277.404049] FS:  0000000000000000(0000) GS:ffff88842fd40000(0000) knlGS:0000000000000000
[ 4277.405357] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 4277.406389] CR2: 00007f2ad0b24000 CR3: 0000000102a3a006 CR4: 00000000007706e0
[ 4277.407589] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 4277.408780] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 4277.410000] PKRU: 55555554
[ 4277.410645] Call Trace:
[ 4277.411234]  <TASK>
[ 4277.411777]  ? die+0x32/0x80
[ 4277.412439]  ? do_trap+0xd6/0x100
[ 4277.413150]  ? __list_del_entry_valid_or_report+0x7b/0xc0
[ 4277.414158]  ? do_error_trap+0x6a/0x90
[ 4277.414948]  ? __list_del_entry_valid_or_report+0x7b/0xc0
[ 4277.415915]  ? exc_invalid_op+0x4c/0x60
[ 4277.416710]  ? __list_del_entry_valid_or_report+0x7b/0xc0
[ 4277.417675]  ? asm_exc_invalid_op+0x16/0x20
[ 4277.418482]  ? __list_del_entry_valid_or_report+0x7b/0xc0
[ 4277.419466]  ? __list_del_entry_valid_or_report+0x7b/0xc0
[ 4277.420410]  free_to_partial_list+0x515/0x5e0
[ 4277.421242]  ? xfs_iext_remove+0x41a/0xa10 [xfs]
[ 4277.422298]  xfs_iext_remove+0x41a/0xa10 [xfs]
[ 4277.423316]  ? xfs_inodegc_worker+0xb4/0x1a0 [xfs]
[ 4277.424383]  xfs_bmap_del_extent_delay+0x4fe/0x7d0 [xfs]
[ 4277.425490]  __xfs_bunmapi+0x50d/0x840 [xfs]
[ 4277.426445]  xfs_itruncate_extents_flags+0x13a/0x490 [xfs]
[ 4277.427553]  xfs_inactive_truncate+0xa3/0x120 [xfs]
[ 4277.428567]  xfs_inactive+0x22d/0x290 [xfs]
[ 4277.429500]  xfs_inodegc_worker+0xb4/0x1a0 [xfs]
[ 4277.430479]  process_one_work+0x171/0x340
[ 4277.431227]  worker_thread+0x277/0x390
[ 4277.431962]  ? __pfx_worker_thread+0x10/0x10
[ 4277.432752]  kthread+0xf0/0x120
[ 4277.433382]  ? __pfx_kthread+0x10/0x10
[ 4277.434134]  ret_from_fork+0x2d/0x50
[ 4277.434837]  ? __pfx_kthread+0x10/0x10
[ 4277.435566]  ret_from_fork_asm+0x1b/0x30
[ 4277.436280]  </TASK>

Fixes: 643b113849d8 ("slub: enable tracking of full slabs")
Suggested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: yuan.gao <yuan.gao@ucloud.cn>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slab.h | 5 +++++
 mm/slub.c | 9 ++++++++-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/mm/slab.h b/mm/slab.h
index 2985670194857..632fedd71fea7 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -73,6 +73,11 @@ struct slab {
 						struct {
 							unsigned inuse:16;
 							unsigned objects:15;
+							/*
+							 * If slab debugging is enabled then the
+							 * frozen bit can be reused to indicate
+							 * that the slab was corrupted
+							 */
 							unsigned frozen:1;
 						};
 					};
diff --git a/mm/slub.c b/mm/slub.c
index 4284cbe41d0d0..ccbdd7eb37a87 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1409,6 +1409,11 @@ static int check_slab(struct kmem_cache *s, struct slab *slab)
 			slab->inuse, slab->objects);
 		return 0;
 	}
+	if (slab->frozen) {
+		slab_err(s, slab, "Slab disabled since SLUB metadata consistency check failed");
+		return 0;
+	}
+
 	/* Slab_pad_check fixes things up after itself */
 	slab_pad_check(s, slab);
 	return 1;
@@ -1589,6 +1594,7 @@ static noinline bool alloc_debug_processing(struct kmem_cache *s,
 		slab_fix(s, "Marking all objects used");
 		slab->inuse = slab->objects;
 		slab->freelist = NULL;
+		slab->frozen = 1; /* mark consistency-failed slab as frozen */
 	}
 	return false;
 }
@@ -2730,7 +2736,8 @@ static void *alloc_single_from_partial(struct kmem_cache *s,
 	slab->inuse++;
 
 	if (!alloc_debug_processing(s, slab, object, orig_size)) {
-		remove_partial(n, slab);
+		if (folio_test_slab(slab_folio(slab)))
+			remove_partial(n, slab);
 		return NULL;
 	}
 

From 2420baa8e0460b1c35008d6bf21b4e6bff023867 Mon Sep 17 00:00:00 2001
From: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Date: Fri, 1 Nov 2024 22:08:44 +0900
Subject: [PATCH 1202/1530] mm/slab: Allow cache creation to proceed even if
 sysfs registration fails

When kobject_init_and_add() fails during cache creation,
kobj->name can be leaked because SLUB does not call kobject_put(),
which should be invoked per the kobject API documentation.
This has a bit of historical context, though; SLUB does not call
kobject_put() to avoid double-free for struct kmem_cache because
1) simply calling it would free all resources related to the cache, and
2) struct kmem_cache descriptor is always freed by cache_cache()'s
error handling path, causing struct kmem_cache to be freed twice.

This issue can be reproduced by creating new slab caches while applying
failslab for kernfs_node_cache. This makes kobject_add_varg() succeed,
but causes kobject_add_internal() to fail in kobject_init_and_add()
during cache creation.

Historically, this issue has attracted developers' attention several times.
Each time a fix addressed either the leak or the double-free,
it caused the other issue. Let's summarize a bit of history here:

  The leak has existed since the early days of SLUB.

  Commit 54b6a731025f ("slub: fix leak of 'name' in sysfs_slab_add")
  introduced a double-free bug while fixing the leak.

  Commit 80da026a8e5d ("mm/slub: fix slab double-free in case of duplicate
  sysfs filename") re-introduced the leak while fixing the double-free
  error.

  Commit dde3c6b72a16 ("mm/slub: fix a memory leak in sysfs_slab_add()")
  fixed the memory leak, but it was later reverted by commit 757fed1d0898
  ("Revert "mm/slub: fix a memory leak in sysfs_slab_add()"") to avoid
  the double-free error.

  This is where we are now: we've chosen a memory leak over a double-free.

To resolve this memory leak, skip creating sysfs files if it fails
and continue with cache creation regardless (as suggested by Christoph).
This resolves the memory leak because both the cache and the kobject
remain alive on kobject_init_and_add() failure.

If SLUB tries to create an alias for a cache without sysfs files,
its symbolic link will not be generated.

Since a slab cache might not have associated sysfs files, call kobject_del()
only if such files exist.

Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slub.c | 26 ++++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index ccbdd7eb37a87..b41bc989f2056 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -6073,7 +6073,8 @@ __kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
 	s = find_mergeable(size, align, flags, name, ctor);
 	if (s) {
 		if (sysfs_slab_alias(s, name))
-			return NULL;
+			pr_err("SLUB: Unable to add cache alias %s to sysfs\n",
+			       name);
 
 		s->refcount++;
 
@@ -6155,15 +6156,18 @@ int do_kmem_cache_create(struct kmem_cache *s, const char *name,
 	if (!alloc_kmem_cache_cpus(s))
 		goto out;
 
+	err = 0;
+
 	/* Mutex is not taken during early boot */
-	if (slab_state <= UP) {
-		err = 0;
+	if (slab_state <= UP)
 		goto out;
-	}
 
-	err = sysfs_slab_add(s);
-	if (err)
-		goto out;
+	/*
+	 * Failing to create sysfs files is not critical to SLUB functionality.
+	 * If it fails, proceed with cache creation without these files.
+	 */
+	if (sysfs_slab_add(s))
+		pr_err("SLUB: Unable to add cache %s to sysfs\n", s->name);
 
 	if (s->flags & SLAB_STORE_USER)
 		debugfs_slab_add(s);
@@ -7233,7 +7237,8 @@ static int sysfs_slab_add(struct kmem_cache *s)
 
 void sysfs_slab_unlink(struct kmem_cache *s)
 {
-	kobject_del(&s->kobj);
+	if (s->kobj.state_in_sysfs)
+		kobject_del(&s->kobj);
 }
 
 void sysfs_slab_release(struct kmem_cache *s)
@@ -7262,6 +7267,11 @@ static int sysfs_slab_alias(struct kmem_cache *s, const char *name)
 		 * If we have a leftover link then remove it.
 		 */
 		sysfs_remove_link(&slab_kset->kobj, name);
+		/*
+		 * The original cache may have failed to generate sysfs file.
+		 * In that case, sysfs_create_link() returns -ENOENT and
+		 * symbolic link creation is skipped.
+		 */
 		return sysfs_create_link(&slab_kset->kobj, &s->kobj, name);
 	}
 

From a5f05a138a8cac035bf9da9b6ed0e532bc7942c8 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Wed, 2 Oct 2024 14:32:04 -0700
Subject: [PATCH 1203/1530] parisc/ftrace: Fix function graph tracing
 disablement

Due to an apparent copy-paste bug, the parisc implementation of
ftrace_disable_ftrace_graph_caller() doesn't actually do anything.
It enables the (already-enabled) static key rather than disabling it.

The result is that after function graph tracing has been "disabled", any
subsequent (non-graph) function tracing will inadvertently also enable
the slow fgraph return address hijacking.

Fixes: 98f2926171ae ("parisc/ftrace: use static key to enable/disable function graph tracer")
Cc: stable@vger.kernel.org # 5.16+
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/kernel/ftrace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index c91f9c2e61ed2..f8d08eab7db8b 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -87,7 +87,7 @@ int ftrace_enable_ftrace_graph_caller(void)
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
-	static_key_enable(&ftrace_graph_enable.key);
+	static_key_disable(&ftrace_graph_enable.key);
 	return 0;
 }
 #endif

From d7a516c6eeae29144649f1c3f586fa580ec9e040 Mon Sep 17 00:00:00 2001
From: Philipp Reisner <philipp.reisner@linbit.com>
Date: Fri, 15 Nov 2024 21:46:02 +0100
Subject: [PATCH 1204/1530] compiler.h: Fix undefined BUILD_BUG_ON_ZERO()

<linux/compiler.h> defines __must_be_array() and __must_be_cstr() and
both expand to BUILD_BUG_ON_ZERO(), but <linux/build_bug.h> defines
BUILD_BUG_ON_ZERO(). Including <linux/build_bug.h> in
<linux/compiler.h> would create a cyclic dependency as
<linux/build_bug.h> already includes <linux/compiler.h>.

Fix that by defining __BUILD_BUG_ON_ZERO_MSG() in <linux/compiler.h>
and using that for __must_be_array() and __must_be_cstr().

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Link: https://lore.kernel.org/r/20241115204602.249590-1-philipp.reisner@linbit.com
Signed-off-by: Kees Cook <kees@kernel.org>
---
 include/linux/compiler.h | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 4d4e23b6e3e76..469a64dd6495f 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -239,11 +239,18 @@ static inline void *offset_to_ptr(const int *off)
 
 #endif /* __ASSEMBLY__ */
 
+#ifdef __CHECKER__
+#define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0)
+#else /* __CHECKER__ */
+#define __BUILD_BUG_ON_ZERO_MSG(e, msg) ((int)sizeof(struct {_Static_assert(!(e), msg);}))
+#endif /* __CHECKER__ */
+
 /* &a[0] degrades to a pointer: a different type from an array */
-#define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
+#define __must_be_array(a)	__BUILD_BUG_ON_ZERO_MSG(__same_type((a), &(a)[0]), "must be array")
 
 /* Require C Strings (i.e. NUL-terminated) lack the "nonstring" attribute. */
-#define __must_be_cstr(p)	BUILD_BUG_ON_ZERO(__annotated(p, nonstring))
+#define __must_be_cstr(p) \
+	__BUILD_BUG_ON_ZERO_MSG(__annotated(p, nonstring), "must be cstr (NUL-terminated)")
 
 /*
  * This returns a constant expression while determining if an argument is

From 6bc0ebfb1d920f13c522545f114cdabb49e9408a Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Fri, 25 Oct 2024 14:16:22 +0200
Subject: [PATCH 1205/1530] pinctrl: qcom: spmi: fix debugfs drive strength

Commit 723e8462a4fe ("pinctrl: qcom: spmi-gpio: Fix the GPIO strength
mapping") fixed a long-standing issue in the Qualcomm SPMI PMIC gpio
driver which had the 'low' and 'high' drive strength settings switched
but failed to update the debugfs interface which still gets this wrong.

Fix the debugfs code so that the exported values match the hardware
settings.

Note that this probably means that most devicetrees that try to describe
the firmware settings got this wrong if the settings were derived from
debugfs. Before the above mentioned commit the settings would have
actually matched the firmware settings even if they were described
incorrectly, but now they are inverted.

Fixes: 723e8462a4fe ("pinctrl: qcom: spmi-gpio: Fix the GPIO strength mapping")
Fixes: eadff3024472 ("pinctrl: Qualcomm SPMI PMIC GPIO pin controller driver")
Cc: Anjelique Melendez <quic_amelende@quicinc.com>
Cc: stable@vger.kernel.org	# 3.19
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Link: https://lore.kernel.org/20241025121622.1496-1-johan+linaro@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-spmi-gpio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
index ab07299ef39fa..0c806b8128b63 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
@@ -667,7 +667,7 @@ static void pmic_gpio_config_dbg_show(struct pinctrl_dev *pctldev,
 		"push-pull", "open-drain", "open-source"
 	};
 	static const char *const strengths[] = {
-		"no", "high", "medium", "low"
+		"no", "low", "medium", "high"
 	};
 
 	pad = pctldev->desc->pins[pin].drv_data;

From 69eb56f69efb866c791cc87fd7bf62adf2ffcbb3 Mon Sep 17 00:00:00 2001
From: Zhang Tianci <zhangtianci.1997@bytedance.com>
Date: Mon, 18 Nov 2024 18:16:00 +0800
Subject: [PATCH 1206/1530] fuse: check attributes staleness on fuse_iget()

Function fuse_direntplus_link() might call fuse_iget() to initialize a new
fuse_inode and change its attributes. If fi->attr_version is always
initialized with 0, even if the attributes returned by the FUSE_READDIR
request is staled, as the new fi->attr_version is 0, fuse_change_attributes
will still set the staled attributes to inode. This wrong behaviour may
cause file size inconsistency even when there is no changes from
server-side.

To reproduce the issue, consider the following 2 programs (A and B) are
running concurrently,

        A                                               B
----------------------------------      --------------------------------
{ /fusemnt/dir/f is a file path in a fuse mount, the size of f is 0. }

readdir(/fusemnt/dir) start
//Daemon set size 0 to f direntry
                                        fallocate(f, 1024)
                                        stat(f) // B see size 1024
                                        echo 2 > /proc/sys/vm/drop_caches
readdir(/fusemnt/dir) reply to kernel
Kernel set 0 to the I_NEW inode

                                        stat(f) // B see size 0

In the above case, only program B is modifying the file size, however, B
observes file size changing between the 2 'readonly' stat() calls. To fix
this issue, we should make sure readdirplus still follows the rule of
attr_version staleness checking even if the fi->attr_version is lost due to
inode eviction.

To identify this situation, the new fc->evict_ctr is used to record whether
the eviction of inodes occurs during the readdirplus request processing.
If it does, the result of readdirplus may be inaccurate; otherwise, the
result of readdirplus can be trusted. Although this may still lead to
incorrect invalidation, considering the relatively low frequency of
evict occurrences, it should be acceptable.

Link: https://lore.kernel.org/lkml/20230711043405.66256-2-zhangjiachen.jaycee@bytedance.com/
Link: https://lore.kernel.org/lkml/20241114070905.48901-1-zhangtianci.1997@bytedance.com/

Reported-by: Jiachen Zhang <zhangjiachen.jaycee@bytedance.com>
Suggested-by: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: Zhang Tianci <zhangtianci.1997@bytedance.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dir.c     | 11 +++++-----
 fs/fuse/fuse_i.h  | 14 ++++++++++--
 fs/fuse/inode.c   | 56 +++++++++++++++++++++++++++++++++++++----------
 fs/fuse/readdir.c | 15 ++++++++-----
 4 files changed, 71 insertions(+), 25 deletions(-)

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index b8a4608e31afb..494ac372ace07 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -366,7 +366,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name
 	struct fuse_mount *fm = get_fuse_mount_super(sb);
 	FUSE_ARGS(args);
 	struct fuse_forget_link *forget;
-	u64 attr_version;
+	u64 attr_version, evict_ctr;
 	int err;
 
 	*inode = NULL;
@@ -381,6 +381,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name
 		goto out;
 
 	attr_version = fuse_get_attr_version(fm->fc);
+	evict_ctr = fuse_get_evict_ctr(fm->fc);
 
 	fuse_lookup_init(fm->fc, &args, nodeid, name, outarg);
 	err = fuse_simple_request(fm, &args);
@@ -398,7 +399,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name
 
 	*inode = fuse_iget(sb, outarg->nodeid, outarg->generation,
 			   &outarg->attr, ATTR_TIMEOUT(outarg),
-			   attr_version);
+			   attr_version, evict_ctr);
 	err = -ENOMEM;
 	if (!*inode) {
 		fuse_queue_forget(fm->fc, forget, outarg->nodeid, 1);
@@ -691,7 +692,7 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir,
 	ff->nodeid = outentry.nodeid;
 	ff->open_flags = outopenp->open_flags;
 	inode = fuse_iget(dir->i_sb, outentry.nodeid, outentry.generation,
-			  &outentry.attr, ATTR_TIMEOUT(&outentry), 0);
+			  &outentry.attr, ATTR_TIMEOUT(&outentry), 0, 0);
 	if (!inode) {
 		flags &= ~(O_CREAT | O_EXCL | O_TRUNC);
 		fuse_sync_release(NULL, ff, flags);
@@ -822,7 +823,7 @@ static int create_new_entry(struct mnt_idmap *idmap, struct fuse_mount *fm,
 		goto out_put_forget_req;
 
 	inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation,
-			  &outarg.attr, ATTR_TIMEOUT(&outarg), 0);
+			  &outarg.attr, ATTR_TIMEOUT(&outarg), 0, 0);
 	if (!inode) {
 		fuse_queue_forget(fm->fc, forget, outarg.nodeid, 1);
 		return -ENOMEM;
@@ -2028,7 +2029,7 @@ int fuse_do_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 
 	fuse_change_attributes_common(inode, &outarg.attr, NULL,
 				      ATTR_TIMEOUT(&outarg),
-				      fuse_get_cache_mask(inode));
+				      fuse_get_cache_mask(inode), 0);
 	oldsize = inode->i_size;
 	/* see the comment in fuse_change_attributes() */
 	if (!is_wb || is_truncate)
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index d35c37ccf9b54..74744c6f28600 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -890,6 +890,9 @@ struct fuse_conn {
 	/** Version counter for attribute changes */
 	atomic64_t attr_version;
 
+	/** Version counter for evict inode */
+	atomic64_t evict_ctr;
+
 	/** Called on final put */
 	void (*release)(struct fuse_conn *);
 
@@ -984,6 +987,11 @@ static inline u64 fuse_get_attr_version(struct fuse_conn *fc)
 	return atomic64_read(&fc->attr_version);
 }
 
+static inline u64 fuse_get_evict_ctr(struct fuse_conn *fc)
+{
+	return atomic64_read(&fc->evict_ctr);
+}
+
 static inline bool fuse_stale_inode(const struct inode *inode, int generation,
 				    struct fuse_attr *attr)
 {
@@ -1043,7 +1051,8 @@ extern const struct dentry_operations fuse_root_dentry_operations;
  */
 struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 			int generation, struct fuse_attr *attr,
-			u64 attr_valid, u64 attr_version);
+			u64 attr_valid, u64 attr_version,
+			u64 evict_ctr);
 
 int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name,
 		     struct fuse_entry_out *outarg, struct inode **inode);
@@ -1133,7 +1142,8 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
 
 void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 				   struct fuse_statx *sx,
-				   u64 attr_valid, u32 cache_mask);
+				   u64 attr_valid, u32 cache_mask,
+				   u64 evict_ctr);
 
 u32 fuse_get_cache_mask(struct inode *inode);
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index f1779ff3f8d19..3ce4f4e81d09e 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -175,6 +175,14 @@ static void fuse_evict_inode(struct inode *inode)
 			fuse_cleanup_submount_lookup(fc, fi->submount_lookup);
 			fi->submount_lookup = NULL;
 		}
+		/*
+		 * Evict of non-deleted inode may race with outstanding
+		 * LOOKUP/READDIRPLUS requests and result in inconsistency when
+		 * the request finishes.  Deal with that here by bumping a
+		 * counter that can be compared to the starting value.
+		 */
+		if (inode->i_nlink > 0)
+			atomic64_inc(&fc->evict_ctr);
 	}
 	if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) {
 		WARN_ON(fi->iocachectr != 0);
@@ -208,17 +216,30 @@ static ino_t fuse_squash_ino(u64 ino64)
 
 void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 				   struct fuse_statx *sx,
-				   u64 attr_valid, u32 cache_mask)
+				   u64 attr_valid, u32 cache_mask,
+				   u64 evict_ctr)
 {
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct fuse_inode *fi = get_fuse_inode(inode);
 
 	lockdep_assert_held(&fi->lock);
 
+	/*
+	 * Clear basic stats from invalid mask.
+	 *
+	 * Don't do this if this is coming from a fuse_iget() call and there
+	 * might have been a racing evict which would've invalidated the result
+	 * if the attr_version would've been preserved.
+	 *
+	 * !evict_ctr -> this is create
+	 * fi->attr_version != 0 -> this is not a new inode
+	 * evict_ctr == fuse_get_evict_ctr() -> no evicts while during request
+	 */
+	if (!evict_ctr || fi->attr_version || evict_ctr == fuse_get_evict_ctr(fc))
+		set_mask_bits(&fi->inval_mask, STATX_BASIC_STATS, 0);
+
 	fi->attr_version = atomic64_inc_return(&fc->attr_version);
 	fi->i_time = attr_valid;
-	/* Clear basic stats from invalid mask */
-	set_mask_bits(&fi->inval_mask, STATX_BASIC_STATS, 0);
 
 	inode->i_ino     = fuse_squash_ino(attr->ino);
 	inode->i_mode    = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
@@ -297,9 +318,9 @@ u32 fuse_get_cache_mask(struct inode *inode)
 	return STATX_MTIME | STATX_CTIME | STATX_SIZE;
 }
 
-void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
-			    struct fuse_statx *sx,
-			    u64 attr_valid, u64 attr_version)
+static void fuse_change_attributes_i(struct inode *inode, struct fuse_attr *attr,
+				     struct fuse_statx *sx, u64 attr_valid,
+				     u64 attr_version, u64 evict_ctr)
 {
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct fuse_inode *fi = get_fuse_inode(inode);
@@ -333,7 +354,8 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
 	}
 
 	old_mtime = inode_get_mtime(inode);
-	fuse_change_attributes_common(inode, attr, sx, attr_valid, cache_mask);
+	fuse_change_attributes_common(inode, attr, sx, attr_valid, cache_mask,
+				      evict_ctr);
 
 	oldsize = inode->i_size;
 	/*
@@ -374,6 +396,13 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
 		fuse_dax_dontcache(inode, attr->flags);
 }
 
+void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
+			    struct fuse_statx *sx, u64 attr_valid,
+			    u64 attr_version)
+{
+	fuse_change_attributes_i(inode, attr, sx, attr_valid, attr_version, 0);
+}
+
 static void fuse_init_submount_lookup(struct fuse_submount_lookup *sl,
 				      u64 nodeid)
 {
@@ -428,7 +457,8 @@ static int fuse_inode_set(struct inode *inode, void *_nodeidp)
 
 struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 			int generation, struct fuse_attr *attr,
-			u64 attr_valid, u64 attr_version)
+			u64 attr_valid, u64 attr_version,
+			u64 evict_ctr)
 {
 	struct inode *inode;
 	struct fuse_inode *fi;
@@ -489,8 +519,8 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 	fi->nlookup++;
 	spin_unlock(&fi->lock);
 done:
-	fuse_change_attributes(inode, attr, NULL, attr_valid, attr_version);
-
+	fuse_change_attributes_i(inode, attr, NULL, attr_valid, attr_version,
+				 evict_ctr);
 	return inode;
 }
 
@@ -942,6 +972,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
 	fc->initialized = 0;
 	fc->connected = 1;
 	atomic64_set(&fc->attr_version, 1);
+	atomic64_set(&fc->evict_ctr, 1);
 	get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
 	fc->pid_ns = get_pid_ns(task_active_pid_ns(current));
 	fc->user_ns = get_user_ns(user_ns);
@@ -1003,7 +1034,7 @@ static struct inode *fuse_get_root_inode(struct super_block *sb, unsigned mode)
 	attr.mode = mode;
 	attr.ino = FUSE_ROOT_ID;
 	attr.nlink = 1;
-	return fuse_iget(sb, FUSE_ROOT_ID, 0, &attr, 0, 0);
+	return fuse_iget(sb, FUSE_ROOT_ID, 0, &attr, 0, 0, 0);
 }
 
 struct fuse_inode_handle {
@@ -1612,7 +1643,8 @@ static int fuse_fill_super_submount(struct super_block *sb,
 		return -ENOMEM;
 
 	fuse_fill_attr_from_inode(&root_attr, parent_fi);
-	root = fuse_iget(sb, parent_fi->nodeid, 0, &root_attr, 0, 0);
+	root = fuse_iget(sb, parent_fi->nodeid, 0, &root_attr, 0, 0,
+			 fuse_get_evict_ctr(fm->fc));
 	/*
 	 * This inode is just a duplicate, so it is not looked up and
 	 * its nlookup should not be incremented.  fuse_iget() does
diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c
index a2deeada4a5ac..17ce9636a2b1a 100644
--- a/fs/fuse/readdir.c
+++ b/fs/fuse/readdir.c
@@ -149,7 +149,7 @@ static int parse_dirfile(char *buf, size_t nbytes, struct file *file,
 
 static int fuse_direntplus_link(struct file *file,
 				struct fuse_direntplus *direntplus,
-				u64 attr_version)
+				u64 attr_version, u64 evict_ctr)
 {
 	struct fuse_entry_out *o = &direntplus->entry_out;
 	struct fuse_dirent *dirent = &direntplus->dirent;
@@ -233,7 +233,7 @@ static int fuse_direntplus_link(struct file *file,
 	} else {
 		inode = fuse_iget(dir->i_sb, o->nodeid, o->generation,
 				  &o->attr, ATTR_TIMEOUT(o),
-				  attr_version);
+				  attr_version, evict_ctr);
 		if (!inode)
 			inode = ERR_PTR(-ENOMEM);
 
@@ -284,7 +284,8 @@ static void fuse_force_forget(struct file *file, u64 nodeid)
 }
 
 static int parse_dirplusfile(char *buf, size_t nbytes, struct file *file,
-			     struct dir_context *ctx, u64 attr_version)
+			     struct dir_context *ctx, u64 attr_version,
+			     u64 evict_ctr)
 {
 	struct fuse_direntplus *direntplus;
 	struct fuse_dirent *dirent;
@@ -319,7 +320,7 @@ static int parse_dirplusfile(char *buf, size_t nbytes, struct file *file,
 		buf += reclen;
 		nbytes -= reclen;
 
-		ret = fuse_direntplus_link(file, direntplus, attr_version);
+		ret = fuse_direntplus_link(file, direntplus, attr_version, evict_ctr);
 		if (ret)
 			fuse_force_forget(file, direntplus->entry_out.nodeid);
 	}
@@ -337,7 +338,7 @@ static int fuse_readdir_uncached(struct file *file, struct dir_context *ctx)
 	struct fuse_io_args ia = {};
 	struct fuse_args_pages *ap = &ia.ap;
 	struct fuse_folio_desc desc = { .length = PAGE_SIZE };
-	u64 attr_version = 0;
+	u64 attr_version = 0, evict_ctr = 0;
 	bool locked;
 
 	folio = folio_alloc(GFP_KERNEL, 0);
@@ -351,6 +352,7 @@ static int fuse_readdir_uncached(struct file *file, struct dir_context *ctx)
 	ap->descs = &desc;
 	if (plus) {
 		attr_version = fuse_get_attr_version(fm->fc);
+		evict_ctr = fuse_get_evict_ctr(fm->fc);
 		fuse_read_args_fill(&ia, file, ctx->pos, PAGE_SIZE,
 				    FUSE_READDIRPLUS);
 	} else {
@@ -368,7 +370,8 @@ static int fuse_readdir_uncached(struct file *file, struct dir_context *ctx)
 				fuse_readdir_cache_end(file, ctx->pos);
 		} else if (plus) {
 			res = parse_dirplusfile(folio_address(folio), res,
-						file, ctx, attr_version);
+						file, ctx, attr_version,
+						evict_ctr);
 		} else {
 			res = parse_dirfile(folio_address(folio), res, file,
 					    ctx);

From d1dfb5f52ffc4a142d88da5c0ed0514f3602c4b8 Mon Sep 17 00:00:00 2001
From: Asahi Lina <lina@asahilina.net>
Date: Wed, 13 Nov 2024 04:55:32 +0900
Subject: [PATCH 1207/1530] virtiofs: dax: remove ->writepages() callback

When using FUSE DAX with virtiofs, cache coherency is managed by the
host. Disk persistence is handled via fsync() and friends, which are
passed directly via the FUSE layer to the host. Therefore, there's no
need to do dax_writeback_mapping_range(). All that ends up doing is a
cache flush operation, which is not caught by KVM and doesn't do much,
since the host and guest are already cache-coherent.

Since dax_writeback_mapping_range() checks that the inode block size is
equal to PAGE_SIZE, this fixes a spurious WARN when virtiofs is used
with a mismatched guest PAGE_SIZE and virtiofs backing FS block size
(this happens, for example, when it's a tmpfs and the host and guest
have a different PAGE_SIZE). FUSE DAX does not require any particular FS
block size, since it always performs DAX mappings in aligned 2MiB
blocks.

See discussion in [1].

[1] https://lore.kernel.org/lkml/20241101-dax-page-size-v1-1-eedbd0c6b08f@asahilina.net/T/#u

[SzM: remove the empty callback]

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Asahi Lina <lina@asahilina.net>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dax.c | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index 12ef91d170bb3..9abbc2f2894f9 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -774,16 +774,6 @@ ssize_t fuse_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	return ret;
 }
 
-static int fuse_dax_writepages(struct address_space *mapping,
-			       struct writeback_control *wbc)
-{
-
-	struct inode *inode = mapping->host;
-	struct fuse_conn *fc = get_fuse_conn(inode);
-
-	return dax_writeback_mapping_range(mapping, fc->dax->dev, wbc);
-}
-
 static vm_fault_t __fuse_dax_fault(struct vm_fault *vmf, unsigned int order,
 		bool write)
 {
@@ -1323,7 +1313,6 @@ bool fuse_dax_inode_alloc(struct super_block *sb, struct fuse_inode *fi)
 }
 
 static const struct address_space_operations fuse_dax_file_aops  = {
-	.writepages	= fuse_dax_writepages,
 	.direct_IO	= noop_direct_IO,
 	.dirty_folio	= noop_dirty_folio,
 };

From 0a0d851ce1bc3f0dc0cdfc429c3b0a9ed6e9272e Mon Sep 17 00:00:00 2001
From: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Date: Thu, 14 Nov 2024 16:32:38 +0530
Subject: [PATCH 1208/1530] i3c: dw: Add support for AMDI0015 ACPI ID

Add AMDI0015 _HID for Designware I3C driver so that the dw-i3c-master
driver can be probed on AMD platforms.

Reviewed-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Link: https://lore.kernel.org/r/20241114110239.660551-2-Shyam-sundar.S-k@amd.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/dw-i3c-master.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c
index 8d694672c1104..1a7c300b6d45c 100644
--- a/drivers/i3c/master/dw-i3c-master.c
+++ b/drivers/i3c/master/dw-i3c-master.c
@@ -1748,12 +1748,19 @@ static const struct of_device_id dw_i3c_master_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, dw_i3c_master_of_match);
 
+static const struct acpi_device_id amd_i3c_device_match[] = {
+	{ "AMDI0015" },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, amd_i3c_device_match);
+
 static struct platform_driver dw_i3c_driver = {
 	.probe = dw_i3c_probe,
 	.remove_new = dw_i3c_remove,
 	.driver = {
 		.name = "dw-i3c-master",
 		.of_match_table = dw_i3c_master_of_match,
+		.acpi_match_table = amd_i3c_device_match,
 		.pm = &dw_i3c_pm_ops,
 	},
 };

From 473d0cb485876b29b71da34a0ea4b36e496cb1ea Mon Sep 17 00:00:00 2001
From: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Date: Thu, 14 Nov 2024 16:32:39 +0530
Subject: [PATCH 1209/1530] i3c: dw: Add quirk to address OD/PP timing issue on
 AMD platform

The AMD Legacy I3C is having a problem with its IP, specifically with the
push-pull and open-drain pull-up registers. These registers need to be
manually programmed for every CCC submission to align with the duty cycle.
Therefore, add a quirk to address this issue.

Reviewed-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Co-developed-by: Sanket Goswami <Sanket.Goswami@amd.com>
Signed-off-by: Sanket Goswami <Sanket.Goswami@amd.com>
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Link: https://lore.kernel.org/r/20241114110239.660551-3-Shyam-sundar.S-k@amd.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/dw-i3c-master.c | 29 ++++++++++++++++++++++++++++-
 drivers/i3c/master/dw-i3c-master.h |  1 +
 2 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c
index 1a7c300b6d45c..5b5c2e4bdc516 100644
--- a/drivers/i3c/master/dw-i3c-master.c
+++ b/drivers/i3c/master/dw-i3c-master.c
@@ -220,6 +220,14 @@
 
 #define XFER_TIMEOUT (msecs_to_jiffies(1000))
 #define RPM_AUTOSUSPEND_TIMEOUT 1000 /* ms */
+
+/* Timing values to configure 12.5MHz frequency */
+#define AMD_I3C_OD_TIMING          0x4C007C
+#define AMD_I3C_PP_TIMING          0x8001A
+
+/* List of quirks */
+#define AMD_I3C_OD_PP_TIMING		BIT(1)
+
 struct dw_i3c_cmd {
 	u32 cmd_lo;
 	u32 cmd_hi;
@@ -794,6 +802,12 @@ static int dw_i3c_ccc_get(struct dw_i3c_master *master, struct i3c_ccc_cmd *ccc)
 	return ret;
 }
 
+static void amd_configure_od_pp_quirk(struct dw_i3c_master *master)
+{
+	master->i3c_od_timing = AMD_I3C_OD_TIMING;
+	master->i3c_pp_timing = AMD_I3C_PP_TIMING;
+}
+
 static int dw_i3c_master_send_ccc_cmd(struct i3c_master_controller *m,
 				      struct i3c_ccc_cmd *ccc)
 {
@@ -803,6 +817,13 @@ static int dw_i3c_master_send_ccc_cmd(struct i3c_master_controller *m,
 	if (ccc->id == I3C_CCC_ENTDAA)
 		return -EINVAL;
 
+	/* AMD platform specific OD and PP timings */
+	if (master->quirks & AMD_I3C_OD_PP_TIMING) {
+		amd_configure_od_pp_quirk(master);
+		writel(master->i3c_pp_timing, master->regs + SCL_I3C_PP_TIMING);
+		writel(master->i3c_od_timing, master->regs + SCL_I3C_OD_TIMING);
+	}
+
 	ret = pm_runtime_resume_and_get(master->dev);
 	if (ret < 0) {
 		dev_err(master->dev,
@@ -1602,6 +1623,8 @@ int dw_i3c_common_probe(struct dw_i3c_master *master,
 	master->maxdevs = ret >> 16;
 	master->free_pos = GENMASK(master->maxdevs - 1, 0);
 
+	master->quirks = (unsigned long)device_get_match_data(&pdev->dev);
+
 	INIT_WORK(&master->hj_work, dw_i3c_hj_work);
 	ret = i3c_master_register(&master->base, &pdev->dev,
 				  &dw_mipi_i3c_ops, false);
@@ -1675,6 +1698,10 @@ static void dw_i3c_master_restore_addrs(struct dw_i3c_master *master)
 
 static void dw_i3c_master_restore_timing_regs(struct dw_i3c_master *master)
 {
+	/* AMD platform specific OD and PP timings */
+	if (master->quirks & AMD_I3C_OD_PP_TIMING)
+		amd_configure_od_pp_quirk(master);
+
 	writel(master->i3c_pp_timing, master->regs + SCL_I3C_PP_TIMING);
 	writel(master->bus_free_timing, master->regs + BUS_FREE_TIMING);
 	writel(master->i3c_od_timing, master->regs + SCL_I3C_OD_TIMING);
@@ -1749,7 +1776,7 @@ static const struct of_device_id dw_i3c_master_of_match[] = {
 MODULE_DEVICE_TABLE(of, dw_i3c_master_of_match);
 
 static const struct acpi_device_id amd_i3c_device_match[] = {
-	{ "AMDI0015" },
+	{ "AMDI0015", AMD_I3C_OD_PP_TIMING },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, amd_i3c_device_match);
diff --git a/drivers/i3c/master/dw-i3c-master.h b/drivers/i3c/master/dw-i3c-master.h
index 219ff815d3a73..c5cb695c16ab8 100644
--- a/drivers/i3c/master/dw-i3c-master.h
+++ b/drivers/i3c/master/dw-i3c-master.h
@@ -50,6 +50,7 @@ struct dw_i3c_master {
 	u32 bus_free_timing;
 	u32 i2c_fm_timing;
 	u32 i2c_fmp_timing;
+	u32 quirks;
 	/*
 	 * Per-device hardware data, used to manage the device address table
 	 * (DAT)

From 2b50719dd92f4ba8feccb4542e675060241a4d27 Mon Sep 17 00:00:00 2001
From: Billy Tsai <billy_tsai@aspeedtech.com>
Date: Wed, 13 Nov 2024 11:58:26 +0800
Subject: [PATCH 1210/1530] i3c: mipi-i3c-hci: Support SETDASA CCC

When the I3C subsystem wants to assign a dynamic address using the SETDASA
CCC, it needs to attach the I3C device with device info that includes only
the static address. In the HCI, if the driver want to send this SETDASA
CCC, a DAT entry is required to temporarily fill the device's static
address into the dynamic address field. Afterward, the reattach API will
be executed to update the DAT with the correct dynamic addrees value.

Signed-off-by: Billy Tsai <billy_tsai@aspeedtech.com>
Reviewed-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Link: https://lore.kernel.org/r/20241113035826.923918-1-billy_tsai@aspeedtech.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index b190401c89c99..e6e482a259b4c 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -436,7 +436,8 @@ static int i3c_hci_attach_i3c_dev(struct i3c_dev_desc *dev)
 			kfree(dev_data);
 			return ret;
 		}
-		mipi_i3c_hci_dat_v1.set_dynamic_addr(hci, ret, dev->info.dyn_addr);
+		mipi_i3c_hci_dat_v1.set_dynamic_addr(hci, ret,
+						     dev->info.dyn_addr ?: dev->info.static_addr);
 		dev_data->dat_idx = ret;
 	}
 	i3c_dev_set_master_data(dev, dev_data);

From 6cf7b65f7029914dc0cd7db86fac9ee5159008c6 Mon Sep 17 00:00:00 2001
From: Defa Li <defa.li@mediatek.com>
Date: Thu, 7 Nov 2024 21:25:39 +0800
Subject: [PATCH 1211/1530] i3c: Use i3cdev->desc->info instead of calling
 i3c_device_get_info() to avoid deadlock

A deadlock may happen since the i3c_master_register() acquires
&i3cbus->lock twice. See the log below.
Use i3cdev->desc->info instead of calling i3c_device_info() to
avoid acquiring the lock twice.

v2:
  - Modified the title and commit message

============================================
WARNING: possible recursive locking detected
6.11.0-mainline
--------------------------------------------
init/1 is trying to acquire lock:
f1ffff80a6a40dc0 (&i3cbus->lock){++++}-{3:3}, at: i3c_bus_normaluse_lock

but task is already holding lock:
f1ffff80a6a40dc0 (&i3cbus->lock){++++}-{3:3}, at: i3c_master_register

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&i3cbus->lock);
  lock(&i3cbus->lock);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

2 locks held by init/1:
 #0: fcffff809b6798f8 (&dev->mutex){....}-{3:3}, at: __driver_attach
 #1: f1ffff80a6a40dc0 (&i3cbus->lock){++++}-{3:3}, at: i3c_master_register

stack backtrace:
CPU: 6 UID: 0 PID: 1 Comm: init
Call trace:
 dump_backtrace+0xfc/0x17c
 show_stack+0x18/0x28
 dump_stack_lvl+0x40/0xc0
 dump_stack+0x18/0x24
 print_deadlock_bug+0x388/0x390
 __lock_acquire+0x18bc/0x32ec
 lock_acquire+0x134/0x2b0
 down_read+0x50/0x19c
 i3c_bus_normaluse_lock+0x14/0x24
 i3c_device_get_info+0x24/0x58
 i3c_device_uevent+0x34/0xa4
 dev_uevent+0x310/0x384
 kobject_uevent_env+0x244/0x414
 kobject_uevent+0x14/0x20
 device_add+0x278/0x460
 device_register+0x20/0x34
 i3c_master_register_new_i3c_devs+0x78/0x154
 i3c_master_register+0x6a0/0x6d4
 mtk_i3c_master_probe+0x3b8/0x4d8
 platform_probe+0xa0/0xe0
 really_probe+0x114/0x454
 __driver_probe_device+0xa0/0x15c
 driver_probe_device+0x3c/0x1ac
 __driver_attach+0xc4/0x1f0
 bus_for_each_dev+0x104/0x160
 driver_attach+0x24/0x34
 bus_add_driver+0x14c/0x294
 driver_register+0x68/0x104
 __platform_driver_register+0x20/0x30
 init_module+0x20/0xfe4
 do_one_initcall+0x184/0x464
 do_init_module+0x58/0x1ec
 load_module+0xefc/0x10c8
 __arm64_sys_finit_module+0x238/0x33c
 invoke_syscall+0x58/0x10c
 el0_svc_common+0xa8/0xdc
 do_el0_svc+0x1c/0x28
 el0_svc+0x50/0xac
 el0t_64_sync_handler+0x70/0xbc
 el0t_64_sync+0x1a8/0x1ac

Signed-off-by: Defa Li <defa.li@mediatek.com>
Link: https://lore.kernel.org/r/20241107132549.25439-1-defa.li@mediatek.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index 770908cff2434..42310c9a00c2d 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -282,7 +282,8 @@ static int i3c_device_uevent(const struct device *dev, struct kobj_uevent_env *e
 	struct i3c_device_info devinfo;
 	u16 manuf, part, ext;
 
-	i3c_device_get_info(i3cdev, &devinfo);
+	if (i3cdev->desc)
+		devinfo = i3cdev->desc->info;
 	manuf = I3C_PID_MANUF_ID(devinfo.pid);
 	part = I3C_PID_PART_ID(devinfo.pid);
 	ext = I3C_PID_EXTRA_INFO(devinfo.pid);

From eeecf953d697cb7f0d916f9908a2b9f451bb2667 Mon Sep 17 00:00:00 2001
From: Melody Olvera <quic_molvera@quicinc.com>
Date: Mon, 11 Nov 2024 16:26:45 -0800
Subject: [PATCH 1212/1530] regulator: qcom-rpmh: Update ranges for FTSMPS525

All FTSMPS525 regulators support LV and MV ranges; however,
the boot loader firmware will determine which range to use as
the device boots.

Nonetheless, the driver cannot determine which range was selected,
so hardcoding the ranges as either LV or MV will not cover all cases
as it's possible for the firmware to select a range not supported by
the driver's current hardcoded values.

To this end, combine the ranges for the FTSMPS525s into one struct
and point all regulators to the updated combined struct. This should
work on all boards regardless of which range is selected by the firmware
and more accurately caputres the capability of this regulator on a
hardware level.

Signed-off-by: Melody Olvera <quic_molvera@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://patch.msgid.link/20241112002645.2803506-1-quic_molvera@quicinc.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/qcom-rpmh-regulator.c | 83 +++++++++++--------------
 1 file changed, 36 insertions(+), 47 deletions(-)

diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c
index 6c343b4b9d15a..7870722b6ee21 100644
--- a/drivers/regulator/qcom-rpmh-regulator.c
+++ b/drivers/regulator/qcom-rpmh-regulator.c
@@ -843,26 +843,15 @@ static const struct rpmh_vreg_hw_data pmic5_ftsmps520 = {
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
 };
 
-static const struct rpmh_vreg_hw_data pmic5_ftsmps525_lv = {
+static const struct rpmh_vreg_hw_data pmic5_ftsmps525 = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_ops,
 	.voltage_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(300000, 0, 267, 4000),
+		REGULATOR_LINEAR_RANGE(1376000, 268, 438, 8000),
 	},
-	.n_linear_ranges = 1,
-	.n_voltages = 268,
-	.pmic_mode_map = pmic_mode_map_pmic5_smps,
-	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
-};
-
-static const struct rpmh_vreg_hw_data pmic5_ftsmps525_mv = {
-	.regulator_type = VRM,
-	.ops = &rpmh_regulator_vrm_ops,
-	.voltage_ranges = (struct linear_range[]) {
-		REGULATOR_LINEAR_RANGE(600000, 0, 267, 8000),
-	},
-	.n_linear_ranges = 1,
-	.n_voltages = 268,
+	.n_linear_ranges = 2,
+	.n_voltages = 439,
 	.pmic_mode_map = pmic_mode_map_pmic5_smps,
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
 };
@@ -1190,12 +1179,12 @@ static const struct rpmh_vreg_init_data pm8550_vreg_data[] = {
 };
 
 static const struct rpmh_vreg_init_data pm8550vs_vreg_data[] = {
-	RPMH_VREG("smps1",  "smp%s1",  &pmic5_ftsmps525_lv, "vdd-s1"),
-	RPMH_VREG("smps2",  "smp%s2",  &pmic5_ftsmps525_lv, "vdd-s2"),
-	RPMH_VREG("smps3",  "smp%s3",  &pmic5_ftsmps525_lv, "vdd-s3"),
-	RPMH_VREG("smps4",  "smp%s4",  &pmic5_ftsmps525_lv, "vdd-s4"),
-	RPMH_VREG("smps5",  "smp%s5",  &pmic5_ftsmps525_lv, "vdd-s5"),
-	RPMH_VREG("smps6",  "smp%s6",  &pmic5_ftsmps525_mv, "vdd-s6"),
+	RPMH_VREG("smps1",  "smp%s1",  &pmic5_ftsmps525, "vdd-s1"),
+	RPMH_VREG("smps2",  "smp%s2",  &pmic5_ftsmps525, "vdd-s2"),
+	RPMH_VREG("smps3",  "smp%s3",  &pmic5_ftsmps525, "vdd-s3"),
+	RPMH_VREG("smps4",  "smp%s4",  &pmic5_ftsmps525, "vdd-s4"),
+	RPMH_VREG("smps5",  "smp%s5",  &pmic5_ftsmps525, "vdd-s5"),
+	RPMH_VREG("smps6",  "smp%s6",  &pmic5_ftsmps525, "vdd-s6"),
 	RPMH_VREG("ldo1",   "ldo%s1",  &pmic5_nldo515,   "vdd-l1"),
 	RPMH_VREG("ldo2",   "ldo%s2",  &pmic5_nldo515,   "vdd-l2"),
 	RPMH_VREG("ldo3",   "ldo%s3",  &pmic5_nldo515,   "vdd-l3"),
@@ -1203,14 +1192,14 @@ static const struct rpmh_vreg_init_data pm8550vs_vreg_data[] = {
 };
 
 static const struct rpmh_vreg_init_data pm8550ve_vreg_data[] = {
-	RPMH_VREG("smps1", "smp%s1", &pmic5_ftsmps525_lv, "vdd-s1"),
-	RPMH_VREG("smps2", "smp%s2", &pmic5_ftsmps525_lv, "vdd-s2"),
-	RPMH_VREG("smps3", "smp%s3", &pmic5_ftsmps525_lv, "vdd-s3"),
-	RPMH_VREG("smps4", "smp%s4", &pmic5_ftsmps525_mv, "vdd-s4"),
-	RPMH_VREG("smps5", "smp%s5", &pmic5_ftsmps525_lv, "vdd-s5"),
-	RPMH_VREG("smps6", "smp%s6", &pmic5_ftsmps525_lv, "vdd-s6"),
-	RPMH_VREG("smps7", "smp%s7", &pmic5_ftsmps525_lv, "vdd-s7"),
-	RPMH_VREG("smps8", "smp%s8", &pmic5_ftsmps525_lv, "vdd-s8"),
+	RPMH_VREG("smps1", "smp%s1", &pmic5_ftsmps525, "vdd-s1"),
+	RPMH_VREG("smps2", "smp%s2", &pmic5_ftsmps525, "vdd-s2"),
+	RPMH_VREG("smps3", "smp%s3", &pmic5_ftsmps525, "vdd-s3"),
+	RPMH_VREG("smps4", "smp%s4", &pmic5_ftsmps525, "vdd-s4"),
+	RPMH_VREG("smps5", "smp%s5", &pmic5_ftsmps525, "vdd-s5"),
+	RPMH_VREG("smps6", "smp%s6", &pmic5_ftsmps525, "vdd-s6"),
+	RPMH_VREG("smps7", "smp%s7", &pmic5_ftsmps525, "vdd-s7"),
+	RPMH_VREG("smps8", "smp%s8", &pmic5_ftsmps525, "vdd-s8"),
 	RPMH_VREG("ldo1",  "ldo%s1", &pmic5_nldo515,   "vdd-l1"),
 	RPMH_VREG("ldo2",  "ldo%s2", &pmic5_nldo515,   "vdd-l2"),
 	RPMH_VREG("ldo3",  "ldo%s3", &pmic5_nldo515,   "vdd-l3"),
@@ -1218,14 +1207,14 @@ static const struct rpmh_vreg_init_data pm8550ve_vreg_data[] = {
 };
 
 static const struct rpmh_vreg_init_data pmc8380_vreg_data[] = {
-	RPMH_VREG("smps1", "smp%s1", &pmic5_ftsmps525_lv, "vdd-s1"),
-	RPMH_VREG("smps2", "smp%s2", &pmic5_ftsmps525_lv, "vdd-s2"),
-	RPMH_VREG("smps3", "smp%s3", &pmic5_ftsmps525_lv, "vdd-s3"),
-	RPMH_VREG("smps4", "smp%s4", &pmic5_ftsmps525_mv, "vdd-s4"),
-	RPMH_VREG("smps5", "smp%s5", &pmic5_ftsmps525_lv, "vdd-s5"),
-	RPMH_VREG("smps6", "smp%s6", &pmic5_ftsmps525_lv, "vdd-s6"),
-	RPMH_VREG("smps7", "smp%s7", &pmic5_ftsmps525_lv, "vdd-s7"),
-	RPMH_VREG("smps8", "smp%s8", &pmic5_ftsmps525_lv, "vdd-s8"),
+	RPMH_VREG("smps1", "smp%s1", &pmic5_ftsmps525, "vdd-s1"),
+	RPMH_VREG("smps2", "smp%s2", &pmic5_ftsmps525, "vdd-s2"),
+	RPMH_VREG("smps3", "smp%s3", &pmic5_ftsmps525, "vdd-s3"),
+	RPMH_VREG("smps4", "smp%s4", &pmic5_ftsmps525, "vdd-s4"),
+	RPMH_VREG("smps5", "smp%s5", &pmic5_ftsmps525, "vdd-s5"),
+	RPMH_VREG("smps6", "smp%s6", &pmic5_ftsmps525, "vdd-s6"),
+	RPMH_VREG("smps7", "smp%s7", &pmic5_ftsmps525, "vdd-s7"),
+	RPMH_VREG("smps8", "smp%s8", &pmic5_ftsmps525, "vdd-s8"),
 	RPMH_VREG("ldo1",  "ldo%s1", &pmic5_nldo515,   "vdd-l1"),
 	RPMH_VREG("ldo2",  "ldo%s2", &pmic5_nldo515,   "vdd-l2"),
 	RPMH_VREG("ldo3",  "ldo%s3", &pmic5_nldo515,   "vdd-l3"),
@@ -1409,16 +1398,16 @@ static const struct rpmh_vreg_init_data pmx65_vreg_data[] = {
 };
 
 static const struct rpmh_vreg_init_data pmx75_vreg_data[] = {
-	RPMH_VREG("smps1",   "smp%s1",    &pmic5_ftsmps525_lv, "vdd-s1"),
-	RPMH_VREG("smps2",   "smp%s2",    &pmic5_ftsmps525_lv, "vdd-s2"),
-	RPMH_VREG("smps3",   "smp%s3",    &pmic5_ftsmps525_lv, "vdd-s3"),
-	RPMH_VREG("smps4",   "smp%s4",    &pmic5_ftsmps525_mv, "vdd-s4"),
-	RPMH_VREG("smps5",   "smp%s5",    &pmic5_ftsmps525_lv, "vdd-s5"),
-	RPMH_VREG("smps6",   "smp%s6",    &pmic5_ftsmps525_lv, "vdd-s6"),
-	RPMH_VREG("smps7",   "smp%s7",    &pmic5_ftsmps525_lv, "vdd-s7"),
-	RPMH_VREG("smps8",   "smp%s8",    &pmic5_ftsmps525_lv, "vdd-s8"),
-	RPMH_VREG("smps9",   "smp%s9",    &pmic5_ftsmps525_lv, "vdd-s9"),
-	RPMH_VREG("smps10",  "smp%s10",   &pmic5_ftsmps525_lv, "vdd-s10"),
+	RPMH_VREG("smps1",   "smp%s1",    &pmic5_ftsmps525, "vdd-s1"),
+	RPMH_VREG("smps2",   "smp%s2",    &pmic5_ftsmps525, "vdd-s2"),
+	RPMH_VREG("smps3",   "smp%s3",    &pmic5_ftsmps525, "vdd-s3"),
+	RPMH_VREG("smps4",   "smp%s4",    &pmic5_ftsmps525, "vdd-s4"),
+	RPMH_VREG("smps5",   "smp%s5",    &pmic5_ftsmps525, "vdd-s5"),
+	RPMH_VREG("smps6",   "smp%s6",    &pmic5_ftsmps525, "vdd-s6"),
+	RPMH_VREG("smps7",   "smp%s7",    &pmic5_ftsmps525, "vdd-s7"),
+	RPMH_VREG("smps8",   "smp%s8",    &pmic5_ftsmps525, "vdd-s8"),
+	RPMH_VREG("smps9",   "smp%s9",    &pmic5_ftsmps525, "vdd-s9"),
+	RPMH_VREG("smps10",  "smp%s10",   &pmic5_ftsmps525, "vdd-s10"),
 	RPMH_VREG("ldo1",    "ldo%s1",    &pmic5_nldo515,   "vdd-l1"),
 	RPMH_VREG("ldo2",    "ldo%s2",    &pmic5_nldo515,   "vdd-l2-18"),
 	RPMH_VREG("ldo3",    "ldo%s3",    &pmic5_nldo515,   "vdd-l3"),

From 4acc902ed3743edd4ac2d3846604a99d17104359 Mon Sep 17 00:00:00 2001
From: Zijun Hu <quic_zijuhu@quicinc.com>
Date: Thu, 7 Nov 2024 08:53:08 +0800
Subject: [PATCH 1213/1530] PCI: endpoint: Fix PCI domain ID release in
 pci_epc_destroy()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

pci_epc_destroy() invokes pci_bus_release_domain_nr() to release the PCI
domain ID, but there are two issues:

  - 'epc->dev' is passed to pci_bus_release_domain_nr() which was already
    freed by device_unregister(), leading to a use-after-free issue.

  - Domain ID corresponds to the EPC device parent, so passing 'epc->dev'
    is also wrong.

Fix these issues by passing 'epc->dev.parent' to
pci_bus_release_domain_nr() and also do it before device_unregister().

Fixes: 0328947c5032 ("PCI: endpoint: Assign PCI domain number for endpoint controllers")
Signed-off-by: Zijun Hu <quic_zijuhu@quicinc.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20241107-epc_rfc-v2-1-da5b6a99a66f@quicinc.com
[mani: reworded subject and description]
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Cc: stable@vger.kernel.org
---
 drivers/pci/endpoint/pci-epc-core.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index 04a85d2f7e2a8..21af2dbacc333 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -923,11 +923,10 @@ EXPORT_SYMBOL_GPL(pci_epc_bus_master_enable_notify);
 void pci_epc_destroy(struct pci_epc *epc)
 {
 	pci_ep_cfs_remove_epc_group(epc->group);
-	device_unregister(&epc->dev);
-
 #ifdef CONFIG_PCI_DOMAINS_GENERIC
-	pci_bus_release_domain_nr(&epc->dev, epc->domain_nr);
+	pci_bus_release_domain_nr(epc->dev.parent, epc->domain_nr);
 #endif
+	device_unregister(&epc->dev);
 }
 EXPORT_SYMBOL_GPL(pci_epc_destroy);
 

From 688d2eb4c6fcfdcdaed0592f9df9196573ff5ce2 Mon Sep 17 00:00:00 2001
From: Zijun Hu <quic_zijuhu@quicinc.com>
Date: Thu, 7 Nov 2024 08:53:09 +0800
Subject: [PATCH 1214/1530] PCI: endpoint: Clear secondary (not primary) EPC in
 pci_epc_remove_epf()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In addition to a primary endpoint controller, an endpoint function may be
associated with a secondary endpoint controller, epf->sec_epc, to provide
NTB (non-transparent bridge) functionality.

Previously, pci_epc_remove_epf() incorrectly cleared epf->epc instead of
epf->sec_epc when removing from the secondary endpoint controller.

Extend the epc->list_lock coverage and clear either epf->epc or
epf->sec_epc as indicated.

Link: https://lore.kernel.org/r/20241107-epc_rfc-v2-2-da5b6a99a66f@quicinc.com
Fixes: 63840ff53223 ("PCI: endpoint: Add support to associate secondary EPC with EPF")
Signed-off-by: Zijun Hu <quic_zijuhu@quicinc.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
[mani: reworded subject and description]
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
[bhelgaas: commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Cc: stable@vger.kernel.org
---
 drivers/pci/endpoint/pci-epc-core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index 21af2dbacc333..bed7c7d1fe3c3 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -746,18 +746,18 @@ void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf,
 	if (IS_ERR_OR_NULL(epc) || !epf)
 		return;
 
+	mutex_lock(&epc->list_lock);
 	if (type == PRIMARY_INTERFACE) {
 		func_no = epf->func_no;
 		list = &epf->list;
+		epf->epc = NULL;
 	} else {
 		func_no = epf->sec_epc_func_no;
 		list = &epf->sec_epc_list;
+		epf->sec_epc = NULL;
 	}
-
-	mutex_lock(&epc->list_lock);
 	clear_bit(func_no, &epc->function_num_map);
 	list_del(list);
-	epf->epc = NULL;
 	mutex_unlock(&epc->list_lock);
 }
 EXPORT_SYMBOL_GPL(pci_epc_remove_epf);

From 28b6acd75e3cefbe746ec7402c7ff4fdb114f327 Mon Sep 17 00:00:00 2001
From: Rick Wertenbroek <rick.wertenbroek@gmail.com>
Date: Thu, 14 Nov 2024 17:10:32 +0100
Subject: [PATCH 1215/1530] PCI: endpoint: Fix pci_epc_map map_size kerneldoc
 string
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Because some endpoint controllers have requirements on the alignment of
the controller physical memory address that must be used to map a RC PCI
address region, the map PCI start address is not necessarily the desired
PCI base address to be mapped. This can result in map_pci_addr being
lower than pci_addr as documented. This results in map_size covering the
range map_pci_addr..pci_addr+pci_size.

The old text had the pci_addr twice instead of map_pci_addr..pci_addr,
so replace the erroneous kerneldoc string to reflect the actual range.

Link: https://lore.kernel.org/r/20241114161032.3046202-1-rick.wertenbroek@gmail.com
Signed-off-by: Rick Wertenbroek <rick.wertenbroek@gmail.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 include/linux/pci-epc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h
index de8cc3658220b..e818e3fdcded9 100644
--- a/include/linux/pci-epc.h
+++ b/include/linux/pci-epc.h
@@ -40,7 +40,7 @@ pci_epc_interface_string(enum pci_epc_interface_type type)
  * @map_pci_addr: RC PCI address used as the first address mapped (may be lower
  *                than @pci_addr)
  * @map_size: size of the controller memory needed for mapping the RC PCI address
- *            range @pci_addr..@pci_addr+@pci_size
+ *            range @map_pci_addr..@pci_addr+@pci_size
  * @phys_base: base physical address of the allocated EPC memory for mapping the
  *             RC PCI address range
  * @phys_addr: physical address at which @pci_addr is mapped

From 7643155dce1428fd63e47d7afe8bf3dbca20cc25 Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Mon, 18 Nov 2024 20:27:26 +0000
Subject: [PATCH 1216/1530] jump_label: rust: pass a mut ptr to
 `static_key_count`

When building the rust_print sample with CONFIG_JUMP_LABEL=n, the Rust
static key support falls back to using static_key_count. This function
accepts a mutable pointer to the `struct static_key`, but the Rust
abstractions are incorrectly passing a const pointer.

This means that builds using CONFIG_JUMP_LABEL=n and SAMPLE_RUST_PRINT=y
fail with the following error message:

	error[E0308]: mismatched types
	  --> <root>/samples/rust/rust_print_main.rs:87:5
	   |
	87 | /     kernel::declare_trace! {
	88 | |         /// # Safety
	89 | |         ///
	90 | |         /// Always safe to call.
	91 | |         unsafe fn rust_sample_loaded(magic: c_int);
	92 | |     }
	   | |     ^
	   | |     |
	   | |_____types differ in mutability
	   |       arguments to this function are incorrect
	   |
	   = note: expected raw pointer `*mut kernel::bindings::static_key`
	              found raw pointer `*const kernel::bindings::static_key`
	note: function defined here
	  --> <root>/rust/bindings/bindings_helpers_generated.rs:33:12
	   |
	33 |     pub fn static_key_count(key: *mut static_key) -> c_int;
	   |            ^^^^^^^^^^^^^^^^

To fix this, insert a pointer cast so that the pointer is mutable.

Link: https://lore.kernel.org/20241118202727.73646-1-aliceryhl@google.com
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202411181440.qEdcuyh6-lkp@intel.com/
Fixes: 169484ab6677 ("rust: add arch_static_branch")
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Acked-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 rust/kernel/jump_label.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/kernel/jump_label.rs b/rust/kernel/jump_label.rs
index 2f2df03a3275e..b5aff632ecc73 100644
--- a/rust/kernel/jump_label.rs
+++ b/rust/kernel/jump_label.rs
@@ -26,7 +26,7 @@ macro_rules! static_branch_unlikely {
 
         #[cfg(not(CONFIG_JUMP_LABEL))]
         {
-            $crate::bindings::static_key_count(_key) > 0
+            $crate::bindings::static_key_count(_key.cast_mut()) > 0
         }
 
         #[cfg(CONFIG_JUMP_LABEL)]

From 7e86490c5dee5c41a55f32d0dc34269e200e6909 Mon Sep 17 00:00:00 2001
From: zhang jiao <zhangjiao2@cmss.chinamobile.com>
Date: Wed, 13 Nov 2024 15:12:01 +0800
Subject: [PATCH 1217/1530] pinctrl: k210: Undef K210_PC_DEFAULT

When the temporary macro K210_PC_DEFAULT is not needed anymore,
use its name in the #undef statement instead of
the incorrect "DEFAULT" name.

Fixes: d4c34d09ab03 ("pinctrl: Add RISC-V Canaan Kendryte K210 FPIOA driver")
Signed-off-by: zhang jiao <zhangjiao2@cmss.chinamobile.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/20241113071201.5440-1-zhangjiao2@cmss.chinamobile.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-k210.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-k210.c b/drivers/pinctrl/pinctrl-k210.c
index caf20215aaba5..eddb01796a83e 100644
--- a/drivers/pinctrl/pinctrl-k210.c
+++ b/drivers/pinctrl/pinctrl-k210.c
@@ -181,7 +181,7 @@ static const u32 k210_pinconf_mode_id_to_mode[] = {
 	[K210_PC_DEFAULT_INT13] = K210_PC_MODE_IN | K210_PC_PU,
 };
 
-#undef DEFAULT
+#undef K210_PC_DEFAULT
 
 /*
  * Pin functions configuration information.

From ac6f0825e582f2216a582c9edf0cee7bfe347ba6 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Sun, 17 Nov 2024 03:45:38 -0800
Subject: [PATCH 1218/1530] pinctrl: airoha: Use unsigned long for bit search

Instead of risking alignment problems and causing (false positive) array
bound warnings when casting a u32 to (64-bit) unsigned long, just use a
native unsigned long for doing bit searches. Avoids warning with GCC 15's
-Warray-bounds -fdiagnostics-details:

In file included from ../include/linux/bitmap.h:11,
                 from ../include/linux/cpumask.h:12,
                 from ../arch/x86/include/asm/paravirt.h:21,
                 from ../arch/x86/include/asm/irqflags.h:80,
                 from ../include/linux/irqflags.h:18,
                 from ../include/linux/spinlock.h:59,
                 from ../include/linux/irq.h:14,
                 from ../include/linux/irqchip/chained_irq.h:10,
                 from ../include/linux/gpio/driver.h:8,
                 from ../drivers/pinctrl/mediatek/pinctrl-airoha.c:11:
In function 'find_next_bit',
    inlined from 'airoha_irq_handler' at ../drivers/pinctrl/mediatek/pinctrl-airoha.c:2394:3:
../include/linux/find.h:65:23: error: array subscript 'long unsigned int[0]' is partly outside array bounds of 'u32[1]' {aka 'unsigned int[1]'} [-Werror=array-bounds=]
   65 |                 val = *addr & GENMASK(size - 1, offset);
      |                       ^~~~~
../drivers/pinctrl/mediatek/pinctrl-airoha.c: In function 'airoha_irq_handler':
../drivers/pinctrl/mediatek/pinctrl-airoha.c:2387:21: note: object 'status' of size 4
 2387 |                 u32 status;
      |                     ^~~~~~

Signed-off-by: Kees Cook <kees@kernel.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://lore.kernel.org/20241117114534.work.292-kees@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/mediatek/pinctrl-airoha.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/pinctrl/mediatek/pinctrl-airoha.c b/drivers/pinctrl/mediatek/pinctrl-airoha.c
index 7692e6d9b8710..547a798b71c8a 100644
--- a/drivers/pinctrl/mediatek/pinctrl-airoha.c
+++ b/drivers/pinctrl/mediatek/pinctrl-airoha.c
@@ -2384,15 +2384,16 @@ static irqreturn_t airoha_irq_handler(int irq, void *data)
 
 	for (i = 0; i < ARRAY_SIZE(irq_status_regs); i++) {
 		struct gpio_irq_chip *girq = &pinctrl->gpiochip.chip.irq;
-		u32 status;
+		u32 regmap;
+		unsigned long status;
 		int irq;
 
 		if (regmap_read(pinctrl->regmap, pinctrl->gpiochip.status[i],
-				&status))
+				&regmap))
 			continue;
 
-		for_each_set_bit(irq, (unsigned long *)&status,
-				 AIROHA_PIN_BANK_SIZE) {
+		status = regmap;
+		for_each_set_bit(irq, &status, AIROHA_PIN_BANK_SIZE) {
 			u32 offset = irq + i * AIROHA_PIN_BANK_SIZE;
 
 			generic_handle_irq(irq_find_mapping(girq->domain,

From b9376c7e42ca22644085332fd450b153cd4e9bde Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Fri, 18 Oct 2024 14:45:01 -0400
Subject: [PATCH 1219/1530] nfsd: new tracepoint for after op_func in compound
 processing

Turn nfsd_compound_encode_err tracepoint into a class and add a new
nfsd_compound_op_err tracepoint.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4proc.c |  1 +
 fs/nfsd/trace.h    | 14 +++++++++++++-
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index d32f2dfd148fe..93089f7064f0b 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2780,6 +2780,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
 		if (op->opdesc->op_get_currentstateid)
 			op->opdesc->op_get_currentstateid(cstate, &op->u);
 		op->status = op->opdesc->op_func(rqstp, cstate, &op->u);
+		trace_nfsd_compound_op_err(rqstp, op->opnum, op->status);
 
 		/* Only from SEQUENCE */
 		if (cstate->status == nfserr_replay_cache) {
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index b8470d4cbe99e..344803cf8004a 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -163,7 +163,7 @@ TRACE_EVENT(nfsd_compound_decode_err,
 		__entry->opnum, __entry->status)
 );
 
-TRACE_EVENT(nfsd_compound_encode_err,
+DECLARE_EVENT_CLASS(nfsd_compound_err_class,
 	TP_PROTO(
 		const struct svc_rqst *rqstp,
 		u32 opnum,
@@ -184,6 +184,18 @@ TRACE_EVENT(nfsd_compound_encode_err,
 		__entry->opnum, __entry->status)
 );
 
+#define DEFINE_NFSD_COMPOUND_ERR_EVENT(name)				\
+DEFINE_EVENT(nfsd_compound_err_class, nfsd_compound_##name##_err,	\
+	TP_PROTO(							\
+		const struct svc_rqst *rqstp,				\
+		u32 opnum,						\
+		__be32 status						\
+	),								\
+	TP_ARGS(rqstp, opnum, status))
+
+DEFINE_NFSD_COMPOUND_ERR_EVENT(op);
+DEFINE_NFSD_COMPOUND_ERR_EVENT(encode);
+
 #define show_fs_file_type(x) \
 	__print_symbolic(x, \
 		{ S_IFLNK,		"LNK" }, \

From 2dc84a75229c37e350dd1a83aaf4a63dc2ba86f3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pali=20Roh=C3=A1r?= <pali@kernel.org>
Date: Fri, 13 Sep 2024 00:53:20 +0200
Subject: [PATCH 1220/1530] lockd: Fix comment about NLMv3 backwards
 compatibility
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

NLMv2 is completely different protocol than NLMv1 and NLMv3, and in
original Sun implementation is used for RPC loopback callbacks from statd
to lockd services. Linux does not use nor does not implement NLMv2.

Hence, NLMv3 is not backward compatible with NLMv2. But NLMv3 is backward
compatible with NLMv1. Fix comment.

Signed-off-by: Pali Rohár <pali@kernel.org>
Reviewed-by: NeilBrown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/lockd/clntxdr.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c
index a3e97278b997c..6ea3448d2d31e 100644
--- a/fs/lockd/clntxdr.c
+++ b/fs/lockd/clntxdr.c
@@ -2,8 +2,9 @@
 /*
  * linux/fs/lockd/clntxdr.c
  *
- * XDR functions to encode/decode NLM version 3 RPC arguments and results.
- * NLM version 3 is backwards compatible with NLM versions 1 and 2.
+ * XDR functions to encode/decode NLM version 1 and 3 RPC
+ * arguments and results. NLM version 2 is not specified
+ * by a standard, thus it is not implemented.
  *
  * NLM client-side only.
  *

From 600020927b004f027e737e6bf57c450d48f2405e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pali=20Roh=C3=A1r?= <pali@kernel.org>
Date: Sat, 5 Oct 2024 20:33:49 +0200
Subject: [PATCH 1221/1530] nfsd: Fill NFSv4.1 server implementation fields in
 OP_EXCHANGE_ID response
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

NFSv4.1 OP_EXCHANGE_ID response from server may contain server
implementation details (domain, name and build time) in optional
nfs_impl_id4 field. Currently nfsd does not fill this field.

Send these information in NFSv4.1 OP_EXCHANGE_ID response. Fill them with
the same values as what is Linux NFSv4.1 client doing. Domain is hardcoded
to "kernel.org", name is composed in the same way as "uname -srvm" output
and build time is hardcoded to zeros.

NFSv4.1 client and server implementation fields are useful for statistic
purposes or for identifying type of clients and servers.

Signed-off-by: Pali Rohár <pali@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4proc.c  |  1 +
 fs/nfsd/nfs4state.c | 31 +++++++++++++++++++++++++++++++
 fs/nfsd/nfs4xdr.c   | 24 +++++++++++++++++++++++-
 fs/nfsd/xdr4.h      |  2 ++
 4 files changed, 57 insertions(+), 1 deletion(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 93089f7064f0b..49b4cbfe914df 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -3453,6 +3453,7 @@ static const struct nfsd4_operation nfsd4_ops[] = {
 	/* NFSv4.1 operations */
 	[OP_EXCHANGE_ID] = {
 		.op_func = nfsd4_exchange_id,
+		.op_release = nfsd4_exchange_id_release,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP
 				| OP_MODIFIES_SOMETHING,
 		.op_name = "OP_EXCHANGE_ID",
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index e0862173cd9ea..2f229d007b586 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3524,6 +3524,12 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		__func__, rqstp, exid, exid->clname.len, exid->clname.data,
 		addr_str, exid->flags, exid->spa_how);
 
+	exid->server_impl_name = kasprintf(GFP_KERNEL, "%s %s %s %s",
+					   utsname()->sysname, utsname()->release,
+					   utsname()->version, utsname()->machine);
+	if (!exid->server_impl_name)
+		return nfserr_jukebox;
+
 	if (exid->flags & ~EXCHGID4_FLAG_MASK_A)
 		return nfserr_inval;
 
@@ -3661,6 +3667,23 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	exid->seqid = conf->cl_cs_slot.sl_seqid + 1;
 	nfsd4_set_ex_flags(conf, exid);
 
+	exid->nii_domain.len = sizeof("kernel.org") - 1;
+	exid->nii_domain.data = "kernel.org";
+
+	/*
+	 * Note that RFC 8881 places no length limit on
+	 * nii_name, but this implementation permits no
+	 * more than NFS4_OPAQUE_LIMIT bytes.
+	 */
+	exid->nii_name.len = strlen(exid->server_impl_name);
+	if (exid->nii_name.len > NFS4_OPAQUE_LIMIT)
+		exid->nii_name.len = NFS4_OPAQUE_LIMIT;
+	exid->nii_name.data = exid->server_impl_name;
+
+	/* just send zeros - the date is in nii_name */
+	exid->nii_time.tv_sec = 0;
+	exid->nii_time.tv_nsec = 0;
+
 	dprintk("nfsd4_exchange_id seqid %d flags %x\n",
 		conf->cl_cs_slot.sl_seqid, conf->cl_exchange_flags);
 	status = nfs_ok;
@@ -3677,6 +3700,14 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status;
 }
 
+void
+nfsd4_exchange_id_release(union nfsd4_op_u *u)
+{
+	struct nfsd4_exchange_id *exid = &u->exchange_id;
+
+	kfree(exid->server_impl_name);
+}
+
 static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, bool slot_inuse)
 {
 	/* The slot is in use, and no response has been sent. */
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index abbfd2b58c82b..37f8301cfb8a6 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4825,6 +4825,25 @@ nfsd4_encode_server_owner4(struct xdr_stream *xdr, struct svc_rqst *rqstp)
 	return nfsd4_encode_opaque(xdr, nn->nfsd_name, strlen(nn->nfsd_name));
 }
 
+static __be32
+nfsd4_encode_nfs_impl_id4(struct xdr_stream *xdr, struct nfsd4_exchange_id *exid)
+{
+	__be32 status;
+
+	/* nii_domain */
+	status = nfsd4_encode_opaque(xdr, exid->nii_domain.data,
+				     exid->nii_domain.len);
+	if (status != nfs_ok)
+		return status;
+	/* nii_name */
+	status = nfsd4_encode_opaque(xdr, exid->nii_name.data,
+				     exid->nii_name.len);
+	if (status != nfs_ok)
+		return status;
+	/* nii_time */
+	return nfsd4_encode_nfstime4(xdr, &exid->nii_time);
+}
+
 static __be32
 nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 			 union nfsd4_op_u *u)
@@ -4859,8 +4878,11 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 	if (nfserr != nfs_ok)
 		return nfserr;
 	/* eir_server_impl_id<1> */
-	if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT)
+	if (xdr_stream_encode_u32(xdr, 1) != XDR_UNIT)
 		return nfserr_resource;
+	nfserr = nfsd4_encode_nfs_impl_id4(xdr, exid);
+	if (nfserr != nfs_ok)
+		return nfserr;
 
 	return nfs_ok;
 }
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 2a21a7662e030..d5bb9a3c2da42 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -567,6 +567,7 @@ struct nfsd4_exchange_id {
 	struct xdr_netobj nii_domain;
 	struct xdr_netobj nii_name;
 	struct timespec64 nii_time;
+	char		*server_impl_name;
 };
 
 struct nfsd4_sequence {
@@ -930,6 +931,7 @@ extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *, union nfsd4_op_u *u);
 extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *, union nfsd4_op_u *u);
+void nfsd4_exchange_id_release(union nfsd4_op_u *u);
 extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *, union nfsd4_op_u *u);
 extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *,

From bb4f07f2409c26c01e97e6f9b432545f353e3b66 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pali=20Roh=C3=A1r?= <pali@kernel.org>
Date: Sat, 5 Oct 2024 18:40:39 +0200
Subject: [PATCH 1222/1530] nfsd: Fix NFSD_MAY_BYPASS_GSS and
 NFSD_MAY_BYPASS_GSS_ON_ROOT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently NFSD_MAY_BYPASS_GSS and NFSD_MAY_BYPASS_GSS_ON_ROOT do not bypass
only GSS, but bypass any method. This is a problem specially for NFS3
AUTH_NULL-only exports.

The purpose of NFSD_MAY_BYPASS_GSS_ON_ROOT is described in RFC 2623,
section 2.3.2, to allow mounting NFS2/3 GSS-only export without
authentication. So few procedures which do not expose security risk used
during mount time can be called also with AUTH_NONE or AUTH_SYS, to allow
client mount operation to finish successfully.

The problem with current implementation is that for AUTH_NULL-only exports,
the NFSD_MAY_BYPASS_GSS_ON_ROOT is active also for NFS3 AUTH_UNIX mount
attempts which confuse NFS3 clients, and make them think that AUTH_UNIX is
enabled and is working. Linux NFS3 client never switches from AUTH_UNIX to
AUTH_NONE on active mount, which makes the mount inaccessible.

Fix the NFSD_MAY_BYPASS_GSS and NFSD_MAY_BYPASS_GSS_ON_ROOT implementation
and really allow to bypass only exports which have enabled some real
authentication (GSS, TLS, or any other).

The result would be: For AUTH_NULL-only export if client attempts to do
mount with AUTH_UNIX flavor then it will receive access errors, which
instruct client that AUTH_UNIX flavor is not usable and will either try
other auth flavor (AUTH_NULL if enabled) or fails mount procedure.
Similarly if client attempt to do mount with AUTH_NULL flavor and only
AUTH_UNIX flavor is enabled then the client will receive access error.

This should fix problems with AUTH_NULL-only or AUTH_UNIX-only exports if
client attempts to mount it with other auth flavor (e.g. with AUTH_NULL for
AUTH_UNIX-only export, or with AUTH_UNIX for AUTH_NULL-only export).

Signed-off-by: Pali Rohár <pali@kernel.org>
Reviewed-by: NeilBrown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/export.c   | 21 ++++++++++++++++++++-
 fs/nfsd/export.h   |  3 ++-
 fs/nfsd/nfs4proc.c |  2 +-
 fs/nfsd/nfs4xdr.c  |  2 +-
 fs/nfsd/nfsfh.c    |  9 ++++++---
 fs/nfsd/vfs.c      |  2 +-
 6 files changed, 31 insertions(+), 8 deletions(-)

diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index c82d8e3e0d4f2..0f40003d864f4 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1078,12 +1078,14 @@ static struct svc_export *exp_find(struct cache_detail *cd,
  * check_nfsd_access - check if access to export is allowed.
  * @exp: svc_export that is being accessed.
  * @rqstp: svc_rqst attempting to access @exp (will be NULL for LOCALIO).
+ * @may_bypass_gss: reduce strictness of authorization check
  *
  * Return values:
  *   %nfs_ok if access is granted, or
  *   %nfserr_wrongsec if access is denied
  */
-__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp)
+__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp,
+			 bool may_bypass_gss)
 {
 	struct exp_flavor_info *f, *end = exp->ex_flavors + exp->ex_nflavors;
 	struct svc_xprt *xprt;
@@ -1140,6 +1142,23 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp)
 	if (nfsd4_spo_must_allow(rqstp))
 		return nfs_ok;
 
+	/* Some calls may be processed without authentication
+	 * on GSS exports. For example NFS2/3 calls on root
+	 * directory, see section 2.3.2 of rfc 2623.
+	 * For "may_bypass_gss" check that export has really
+	 * enabled some flavor with authentication (GSS or any
+	 * other) and also check that the used auth flavor is
+	 * without authentication (none or sys).
+	 */
+	if (may_bypass_gss && (
+	     rqstp->rq_cred.cr_flavor == RPC_AUTH_NULL ||
+	     rqstp->rq_cred.cr_flavor == RPC_AUTH_UNIX)) {
+		for (f = exp->ex_flavors; f < end; f++) {
+			if (f->pseudoflavor >= RPC_AUTH_DES)
+				return 0;
+		}
+	}
+
 denied:
 	return nfserr_wrongsec;
 }
diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
index 3794ae253a701..4d92b99c1ffdd 100644
--- a/fs/nfsd/export.h
+++ b/fs/nfsd/export.h
@@ -101,7 +101,8 @@ struct svc_expkey {
 
 struct svc_cred;
 int nfsexp_flags(struct svc_cred *cred, struct svc_export *exp);
-__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp);
+__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp,
+			 bool may_bypass_gss);
 
 /*
  * Function declarations
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 49b4cbfe914df..94cc7b2ac385f 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2797,7 +2797,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
 
 			if (current_fh->fh_export &&
 					need_wrongsec_check(rqstp))
-				op->status = check_nfsd_access(current_fh->fh_export, rqstp);
+				op->status = check_nfsd_access(current_fh->fh_export, rqstp, false);
 		}
 encode_op:
 		if (op->status == nfserr_replay_me) {
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 37f8301cfb8a6..5e6ef24d54507 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3767,7 +3767,7 @@ nfsd4_encode_entry4_fattr(struct nfsd4_readdir *cd, const char *name,
 			nfserr = nfserrno(err);
 			goto out_put;
 		}
-		nfserr = check_nfsd_access(exp, cd->rd_rqstp);
+		nfserr = check_nfsd_access(exp, cd->rd_rqstp, false);
 		if (nfserr)
 			goto out_put;
 
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 96e19c50a5d7e..cbb046f88eec6 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -320,6 +320,7 @@ __fh_verify(struct svc_rqst *rqstp,
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	struct svc_export *exp = NULL;
+	bool may_bypass_gss = false;
 	struct dentry	*dentry;
 	__be32		error;
 
@@ -367,8 +368,10 @@ __fh_verify(struct svc_rqst *rqstp,
 	 * which clients virtually always use auth_sys for,
 	 * even while using RPCSEC_GSS for NFS.
 	 */
-	if (access & NFSD_MAY_LOCK || access & NFSD_MAY_BYPASS_GSS)
+	if (access & NFSD_MAY_LOCK)
 		goto skip_pseudoflavor_check;
+	if (access & NFSD_MAY_BYPASS_GSS)
+		may_bypass_gss = true;
 	/*
 	 * Clients may expect to be able to use auth_sys during mount,
 	 * even if they use gss for everything else; see section 2.3.2
@@ -376,9 +379,9 @@ __fh_verify(struct svc_rqst *rqstp,
 	 */
 	if (access & NFSD_MAY_BYPASS_GSS_ON_ROOT
 			&& exp->ex_path.dentry == dentry)
-		goto skip_pseudoflavor_check;
+		may_bypass_gss = true;
 
-	error = check_nfsd_access(exp, rqstp);
+	error = check_nfsd_access(exp, rqstp, may_bypass_gss);
 	if (error)
 		goto out;
 
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index e0692401da33e..1f8540148c4af 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -321,7 +321,7 @@ nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
 	err = nfsd_lookup_dentry(rqstp, fhp, name, len, &exp, &dentry);
 	if (err)
 		return err;
-	err = check_nfsd_access(exp, rqstp);
+	err = check_nfsd_access(exp, rqstp, false);
 	if (err)
 		goto out;
 	/*

From a32442f6ca32cf402a76856d5e713bd742481ba2 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 7 Oct 2024 14:07:54 -0400
Subject: [PATCH 1223/1530] xdrgen: Add a utility for extracting XDR from RFCs

For convenience, copy the XDR extraction script from RFC

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 MAINTAINERS                 |  1 +
 tools/net/sunrpc/extract.sh | 11 +++++++++++
 2 files changed, 12 insertions(+)
 create mode 100755 tools/net/sunrpc/extract.sh

diff --git a/MAINTAINERS b/MAINTAINERS
index 21fdaa19229ae..f711449753b3e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12367,6 +12367,7 @@ F:	include/trace/misc/sunrpc.h
 F:	include/uapi/linux/nfsd/
 F:	include/uapi/linux/sunrpc/
 F:	net/sunrpc/
+F:	tools/net/sunrpc/
 
 KERNEL PACMAN PACKAGING (in addition to generic KERNEL BUILD)
 M:	Thomas Weißschuh <linux@weissschuh.net>
diff --git a/tools/net/sunrpc/extract.sh b/tools/net/sunrpc/extract.sh
new file mode 100755
index 0000000000000..f944066f25bcc
--- /dev/null
+++ b/tools/net/sunrpc/extract.sh
@@ -0,0 +1,11 @@
+#! /bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Extract an RPC protocol specification from an RFC document.
+# The version of this script comes from RFC 8166.
+#
+# Usage:
+#  $ extract.sh < rfcNNNN.txt > protocol.x
+#
+
+grep '^ *///' | sed 's?^ */// ??' | sed 's?^ *///$??'

From ed9887b876c957c9c9a0486cf0edf7c964e99cb9 Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@inria.fr>
Date: Sun, 13 Oct 2024 22:16:59 +0200
Subject: [PATCH 1224/1530] nfsd: replace call_rcu by kfree_rcu for simple
 kmem_cache_free callback

Since SLOB was removed and since
commit 6c6c47b063b5 ("mm, slab: call kvfree_rcu_barrier() from kmem_cache_destroy()"),
it is not necessary to use call_rcu when the callback only performs
kmem_cache_free. Use kfree_rcu() directly.

The changes were made using Coccinelle.

Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4state.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2f229d007b586..291db55c90e49 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -572,13 +572,6 @@ opaque_hashval(const void *ptr, int nbytes)
 	return x;
 }
 
-static void nfsd4_free_file_rcu(struct rcu_head *rcu)
-{
-	struct nfs4_file *fp = container_of(rcu, struct nfs4_file, fi_rcu);
-
-	kmem_cache_free(file_slab, fp);
-}
-
 void
 put_nfs4_file(struct nfs4_file *fi)
 {
@@ -586,7 +579,7 @@ put_nfs4_file(struct nfs4_file *fi)
 		nfsd4_file_hash_remove(fi);
 		WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate));
 		WARN_ON_ONCE(!list_empty(&fi->fi_delegations));
-		call_rcu(&fi->fi_rcu, nfsd4_free_file_rcu);
+		kfree_rcu(fi, fi_rcu);
 	}
 }
 

From 6640556b0c80edc66d6f50abe53f00311a873536 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 13 Oct 2024 16:02:28 -0400
Subject: [PATCH 1225/1530] NFSD: Replace use of NFSD_MAY_LOCK in nfsd4_lock()

NFSv4 LOCK operations should not avoid the set of authorization
checks that apply to all other NFSv4 operations. Also, the
"no_auth_nlm" export option should apply only to NLM LOCK requests.
It's not necessary or sensible to apply it to NFSv4 LOCK operations.

Instead, set no permission bits when calling fh_verify(). Subsequent
stateid processing handles authorization checks.

Reported-by: NeilBrown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4state.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 291db55c90e49..2efceeea0fe3e 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -7965,11 +7965,9 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (check_lock_length(lock->lk_offset, lock->lk_length))
 		 return nfserr_inval;
 
-	if ((status = fh_verify(rqstp, &cstate->current_fh,
-				S_IFREG, NFSD_MAY_LOCK))) {
-		dprintk("NFSD: nfsd4_lock: permission denied!\n");
+	status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0);
+	if (status != nfs_ok)
 		return status;
-	}
 	sb = cstate->current_fh.fh_dentry->d_sb;
 
 	if (lock->lk_is_new) {

From 4cc9b9f2bf4dfe13fe573da978e626e2248df388 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Fri, 18 Oct 2024 08:42:31 +1100
Subject: [PATCH 1226/1530] nfsd: refine and rename NFSD_MAY_LOCK

NFSD_MAY_LOCK means a few different things.
- it means that GSS is not required.
- it means that with NFSEXP_NOAUTHNLM, authentication is not required
- it means that OWNER_OVERRIDE is allowed.

None of these are specific to locking, they are specific to the NLM
protocol.
So:
 - rename to NFSD_MAY_NLM
 - set NFSD_MAY_OWNER_OVERRIDE and NFSD_MAY_BYPASS_GSS in nlm_fopen()
   so that NFSD_MAY_NLM doesn't need to imply these.
 - move the test on NFSEXP_NOAUTHNLM out of nfsd_permission() and
   into fh_verify where other special-case tests on the MAY flags
   happen.  nfsd_permission() can be called from other places than
   fh_verify(), but none of these will have NFSD_MAY_NLM.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/lockd.c | 13 +++++++++++--
 fs/nfsd/nfsfh.c | 12 ++++--------
 fs/nfsd/trace.h |  2 +-
 fs/nfsd/vfs.c   | 12 +-----------
 fs/nfsd/vfs.h   |  2 +-
 5 files changed, 18 insertions(+), 23 deletions(-)

diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c
index 46a7f9b813e52..edc9f75dc75c6 100644
--- a/fs/nfsd/lockd.c
+++ b/fs/nfsd/lockd.c
@@ -38,11 +38,20 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp,
 	memcpy(&fh.fh_handle.fh_raw, f->data, f->size);
 	fh.fh_export = NULL;
 
+	/*
+	 * Allow BYPASS_GSS as some client implementations use AUTH_SYS
+	 * for NLM even when GSS is used for NFS.
+	 * Allow OWNER_OVERRIDE as permission might have been changed
+	 * after the file was opened.
+	 * Pass MAY_NLM so that authentication can be completely bypassed
+	 * if NFSEXP_NOAUTHNLM is set.  Some older clients use AUTH_NULL
+	 * for NLM requests.
+	 */
 	access = (mode == O_WRONLY) ? NFSD_MAY_WRITE : NFSD_MAY_READ;
-	access |= NFSD_MAY_LOCK;
+	access |= NFSD_MAY_NLM | NFSD_MAY_OWNER_OVERRIDE | NFSD_MAY_BYPASS_GSS;
 	nfserr = nfsd_open(rqstp, &fh, S_IFREG, access, filp);
 	fh_put(&fh);
- 	/* We return nlm error codes as nlm doesn't know
+	/* We return nlm error codes as nlm doesn't know
 	 * about nfsd, but nfsd does know about nlm..
 	 */
 	switch (nfserr) {
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index cbb046f88eec6..871de925a3df5 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -363,13 +363,10 @@ __fh_verify(struct svc_rqst *rqstp,
 	if (error)
 		goto out;
 
-	/*
-	 * pseudoflavor restrictions are not enforced on NLM,
-	 * which clients virtually always use auth_sys for,
-	 * even while using RPCSEC_GSS for NFS.
-	 */
-	if (access & NFSD_MAY_LOCK)
-		goto skip_pseudoflavor_check;
+	if ((access & NFSD_MAY_NLM) && (exp->ex_flags & NFSEXP_NOAUTHNLM))
+		/* NLM is allowed to fully bypass authentication */
+		goto out;
+
 	if (access & NFSD_MAY_BYPASS_GSS)
 		may_bypass_gss = true;
 	/*
@@ -385,7 +382,6 @@ __fh_verify(struct svc_rqst *rqstp,
 	if (error)
 		goto out;
 
-skip_pseudoflavor_check:
 	/* Finally, check access permissions. */
 	error = nfsd_permission(cred, exp, dentry, access);
 out:
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 344803cf8004a..f318898cfc316 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -79,7 +79,7 @@ DEFINE_NFSD_XDR_ERR_EVENT(cant_encode);
 		{ NFSD_MAY_READ,		"READ" },		\
 		{ NFSD_MAY_SATTR,		"SATTR" },		\
 		{ NFSD_MAY_TRUNC,		"TRUNC" },		\
-		{ NFSD_MAY_LOCK,		"LOCK" },		\
+		{ NFSD_MAY_NLM,			"NLM" },		\
 		{ NFSD_MAY_OWNER_OVERRIDE,	"OWNER_OVERRIDE" },	\
 		{ NFSD_MAY_LOCAL_ACCESS,	"LOCAL_ACCESS" },	\
 		{ NFSD_MAY_BYPASS_GSS_ON_ROOT,	"BYPASS_GSS_ON_ROOT" },	\
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 1f8540148c4af..eee39bab49a84 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -2506,7 +2506,7 @@ nfsd_permission(struct svc_cred *cred, struct svc_export *exp,
 		(acc & NFSD_MAY_EXEC)?	" exec"  : "",
 		(acc & NFSD_MAY_SATTR)?	" sattr" : "",
 		(acc & NFSD_MAY_TRUNC)?	" trunc" : "",
-		(acc & NFSD_MAY_LOCK)?	" lock"  : "",
+		(acc & NFSD_MAY_NLM)?	" nlm"  : "",
 		(acc & NFSD_MAY_OWNER_OVERRIDE)? " owneroverride" : "",
 		inode->i_mode,
 		IS_IMMUTABLE(inode)?	" immut" : "",
@@ -2531,16 +2531,6 @@ nfsd_permission(struct svc_cred *cred, struct svc_export *exp,
 	if ((acc & NFSD_MAY_TRUNC) && IS_APPEND(inode))
 		return nfserr_perm;
 
-	if (acc & NFSD_MAY_LOCK) {
-		/* If we cannot rely on authentication in NLM requests,
-		 * just allow locks, otherwise require read permission, or
-		 * ownership
-		 */
-		if (exp->ex_flags & NFSEXP_NOAUTHNLM)
-			return 0;
-		else
-			acc = NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE;
-	}
 	/*
 	 * The file owner always gets access permission for accesses that
 	 * would normally be checked at open time. This is to make
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 854fb95dfdca4..f9b09b8428566 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -20,7 +20,7 @@
 #define NFSD_MAY_READ			0x004 /* == MAY_READ */
 #define NFSD_MAY_SATTR			0x008
 #define NFSD_MAY_TRUNC			0x010
-#define NFSD_MAY_LOCK			0x020
+#define NFSD_MAY_NLM			0x020 /* request is from lockd */
 #define NFSD_MAY_MASK			0x03f
 
 /* extra hints to permission and open routines: */

From d08bf5ea649c045175c191609ccd52644b85985f Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2024 11:03:51 -0400
Subject: [PATCH 1227/1530] NFSD: Remove dead code in nfsd4_create_session()

Clean up. AFAICT, there is no way to reach the out_free_conn label
with @old set to a non-NULL value, so the expire_client(old) call
is never reached and can be removed.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4state.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2efceeea0fe3e..133117b6c7ccd 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3954,7 +3954,6 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 	return status;
 
 out_expired_error:
-	old = NULL;
 	/*
 	 * Revert the slot seq_nr change so the server will process
 	 * the client's resend instead of returning a cached response.
@@ -3969,8 +3968,6 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 out_free_conn:
 	spin_unlock(&nn->client_lock);
 	free_conn(conn);
-	if (old)
-		expire_client(old);
 out_free_session:
 	__free_session(new);
 out_release_drc_mem:

From da4f777e623936d4d93427b69fca37baefd62669 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2024 11:03:52 -0400
Subject: [PATCH 1228/1530] NFSD: Remove a never-true comparison

fh_size is an unsigned int, thus it can never be less than 0.

Fixes: d8b26071e65e ("NFSD: simplify struct nfsfh")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfsfh.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 871de925a3df5..6a831cb242dfb 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -766,7 +766,7 @@ char * SVCFH_fmt(struct svc_fh *fhp)
 	struct knfsd_fh *fh = &fhp->fh_handle;
 	static char buf[2+1+1+64*3+1];
 
-	if (fh->fh_size < 0 || fh->fh_size> 64)
+	if (fh->fh_size > 64)
 		return "bad-fh";
 	sprintf(buf, "%d: %*ph", fh->fh_size, fh->fh_size, fh->fh_raw);
 	return buf;

From 1e02c641c3a43c88cecc08402000418e15578d38 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2024 11:03:53 -0400
Subject: [PATCH 1229/1530] NFSD: Prevent NULL dereference in
 nfsd4_process_cb_update()

@ses is initialized to NULL. If __nfsd4_find_backchannel() finds no
available backchannel session, setup_callback_client() will try to
dereference @ses and segfault.

Fixes: dcbeaa68dbbd ("nfsd4: allow backchannel recovery")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4callback.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index f5ba9be917700..1ffac2b32d81a 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1464,6 +1464,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 		ses = c->cn_session;
 	}
 	spin_unlock(&clp->cl_lock);
+	if (!c)
+		return;
 
 	err = setup_callback_client(clp, &conn, ses);
 	if (err) {

From 6b9c1080a69ee4d37e88f3743c13a45cce6afcbf Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2024 11:03:54 -0400
Subject: [PATCH 1230/1530] NFSD: Remove unused results in
 nfsd4_encode_pathname4()

Clean up. The result of "*p++" is saved, but is not used before it
is overwritten. The result of xdr_encode_opaque() is saved each
time through the loop but is never used.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4xdr.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 5e6ef24d54507..a3a0d27e51e60 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2699,7 +2699,6 @@ static __be32 nfsd4_encode_pathname4(struct xdr_stream *xdr,
 				     const struct path *path)
 {
 	struct path cur = *path;
-	__be32 *p;
 	struct dentry **components = NULL;
 	unsigned int ncomponents = 0;
 	__be32 err = nfserr_jukebox;
@@ -2730,24 +2729,19 @@ static __be32 nfsd4_encode_pathname4(struct xdr_stream *xdr,
 		components[ncomponents++] = cur.dentry;
 		cur.dentry = dget_parent(cur.dentry);
 	}
+
 	err = nfserr_resource;
-	p = xdr_reserve_space(xdr, 4);
-	if (!p)
+	if (xdr_stream_encode_u32(xdr, ncomponents) != XDR_UNIT)
 		goto out_free;
-	*p++ = cpu_to_be32(ncomponents);
-
 	while (ncomponents) {
 		struct dentry *dentry = components[ncomponents - 1];
-		unsigned int len;
 
 		spin_lock(&dentry->d_lock);
-		len = dentry->d_name.len;
-		p = xdr_reserve_space(xdr, len + 4);
-		if (!p) {
+		if (xdr_stream_encode_opaque(xdr, dentry->d_name.name,
+					     dentry->d_name.len) < 0) {
 			spin_unlock(&dentry->d_lock);
 			goto out_free;
 		}
-		p = xdr_encode_opaque(p, dentry->d_name.name, len);
 		dprintk("/%pd", dentry);
 		spin_unlock(&dentry->d_lock);
 		dput(dentry);

From 30c1d2411acd6d9d987f5f804aa173abb3b097ce Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2024 11:03:55 -0400
Subject: [PATCH 1231/1530] NFSD: Remove unused values from
 nfsd4_encode_components_esc()

Clean up. The computed value of @p is saved each time through the
loop but is never used.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4xdr.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index a3a0d27e51e60..53fac037611c0 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2652,13 +2652,10 @@ static __be32 nfsd4_encode_components_esc(struct xdr_stream *xdr, char sep,
 
 		strlen = end - str;
 		if (strlen) {
-			p = xdr_reserve_space(xdr, strlen + 4);
-			if (!p)
+			if (xdr_stream_encode_opaque(xdr, str, strlen) < 0)
 				return nfserr_resource;
-			p = xdr_encode_opaque(p, str, strlen);
 			count++;
-		}
-		else
+		} else
 			end++;
 		if (found_esc)
 			end = next;

From f64ea4af43161bb86ffc77e6aeb5bcf5c3229df0 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2024 11:03:56 -0400
Subject: [PATCH 1232/1530] NFSD: Cap the number of bytes copied by
 nfs4_reset_recoverydir()

It's only current caller already length-checks the string, but let's
be safe.

Fixes: 0964a3d3f1aa ("[PATCH] knfsd: nfsd4 reboot dirname fix")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4recover.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index b7d61eb8afe9e..4a765555bf845 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -659,7 +659,8 @@ nfs4_reset_recoverydir(char *recdir)
 		return status;
 	status = -ENOTDIR;
 	if (d_is_dir(path.dentry)) {
-		strcpy(user_recovery_dirname, recdir);
+		strscpy(user_recovery_dirname, recdir,
+			sizeof(user_recovery_dirname));
 		status = 0;
 	}
 	path_put(&path);

From 2f746e40e9baae878f8193e09d8f6d601dce42bb Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2024 09:36:27 -0400
Subject: [PATCH 1233/1530] lockd: Remove unused typedef

Clean up: Looks like the last usage of this typedef was removed by
commit 026fec7e7c47 ("sunrpc: properly type pc_decode callbacks") in
2017.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: NeilBrown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/lockd/xdr.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h
index 80cca94267615..17d53165d9f24 100644
--- a/include/linux/lockd/xdr.h
+++ b/include/linux/lockd/xdr.h
@@ -73,8 +73,6 @@ struct nlm_args {
 	u32			fsm_mode;
 };
 
-typedef struct nlm_args nlm_args;
-
 /*
  * Generic lockd result
  */

From e5948841285b1ad5bc3234a2f6d0586eceabfbdc Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2024 09:36:28 -0400
Subject: [PATCH 1234/1530] lockd: Remove unnecessary memset()

Since commit 103cc1fafee4 ("SUNRPC: Parametrize how much of argsize
should be zeroed") (and possibly long before that, even) all of the
memory underlying rqstp->rq_argp is zeroed already. There's no need
for the memset() in nlm4svc_decode_shareargs().

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: NeilBrown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/lockd/xdr4.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index 3d28b9c3ed150..60466b8bac588 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -268,7 +268,6 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_lock	*lock = &argp->lock;
 
-	memset(lock, 0, sizeof(*lock));
 	locks_init_lock(&lock->fl);
 	lock->svid = ~(u32)0;
 

From a872c7313ec55263e11026163f081069a8c896c6 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2024 09:36:29 -0400
Subject: [PATCH 1235/1530] lockd: Remove some snippets of unfinished code

Clean up.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: NeilBrown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/lockd/svc4proc.c | 12 ------------
 fs/lockd/svcproc.c  | 12 ------------
 2 files changed, 24 deletions(-)

diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 8a72c418cdcc0..1d0400d94b3df 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -142,18 +142,6 @@ __nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp)
 	if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file)))
 		return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
 
-#if 0
-	/* If supplied state doesn't match current state, we assume it's
-	 * an old request that time-warped somehow. Any error return would
-	 * do in this case because it's irrelevant anyway.
-	 *
-	 * NB: We don't retrieve the remote host's state yet.
-	 */
-	if (host->h_nsmstate && host->h_nsmstate != argp->state) {
-		resp->status = nlm_lck_denied_nolocks;
-	} else
-#endif
-
 	/* Now try to lock the file */
 	resp->status = nlmsvc_lock(rqstp, file, host, &argp->lock,
 					argp->block, &argp->cookie,
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index a03220e66ce02..d959a5dbe0ae8 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -165,18 +165,6 @@ __nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp)
 	if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file)))
 		return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
 
-#if 0
-	/* If supplied state doesn't match current state, we assume it's
-	 * an old request that time-warped somehow. Any error return would
-	 * do in this case because it's irrelevant anyway.
-	 *
-	 * NB: We don't retrieve the remote host's state yet.
-	 */
-	if (host->h_nsmstate && host->h_nsmstate != argp->state) {
-		resp->status = nlm_lck_denied_nolocks;
-	} else
-#endif
-
 	/* Now try to lock the file */
 	resp->status = cast_status(nlmsvc_lock(rqstp, file, host, &argp->lock,
 					       argp->block, &argp->cookie,

From 8994a512e2598c0bf1b6e9ece1e8292976b0dd65 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2024 09:36:30 -0400
Subject: [PATCH 1236/1530] lockd: Remove unused parameter to nlmsvc_testlock()

The nlm_cookie parameter has been unused since commit 09802fd2a8ca
("lockd: rip out deferred lock handling from testlock codepath").

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: NeilBrown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/lockd/svc4proc.c         | 3 ++-
 fs/lockd/svclock.c          | 2 +-
 fs/lockd/svcproc.c          | 3 ++-
 include/linux/lockd/lockd.h | 6 +++---
 4 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 1d0400d94b3df..2cb6030131117 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -108,7 +108,8 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
 
 	test_owner = argp->lock.fl.c.flc_owner;
 	/* Now check for conflicting locks */
-	resp->status = nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie);
+	resp->status = nlmsvc_testlock(rqstp, file, host, &argp->lock,
+				       &resp->lock);
 	if (resp->status == nlm_drop_reply)
 		rc = rpc_drop_reply;
 	else
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 1f2149db10f24..33e1fd1599343 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -609,7 +609,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 __be32
 nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 		struct nlm_host *host, struct nlm_lock *lock,
-		struct nlm_lock *conflock, struct nlm_cookie *cookie)
+		struct nlm_lock *conflock)
 {
 	int			error;
 	int			mode;
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index d959a5dbe0ae8..f53d5177f2673 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -130,7 +130,8 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
 	test_owner = argp->lock.fl.c.flc_owner;
 
 	/* Now check for conflicting locks */
-	resp->status = cast_status(nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie));
+	resp->status = cast_status(nlmsvc_testlock(rqstp, file, host,
+						   &argp->lock, &resp->lock));
 	if (resp->status == nlm_drop_reply)
 		rc = rpc_drop_reply;
 	else
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index 61c4b9c419042..c8f0f9458f2cc 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -278,9 +278,9 @@ __be32		  nlmsvc_lock(struct svc_rqst *, struct nlm_file *,
 			      struct nlm_host *, struct nlm_lock *, int,
 			      struct nlm_cookie *, int);
 __be32		  nlmsvc_unlock(struct net *net, struct nlm_file *, struct nlm_lock *);
-__be32		  nlmsvc_testlock(struct svc_rqst *, struct nlm_file *,
-			struct nlm_host *, struct nlm_lock *,
-			struct nlm_lock *, struct nlm_cookie *);
+__be32		  nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
+			struct nlm_host *host, struct nlm_lock *lock,
+			struct nlm_lock *conflock);
 __be32		  nlmsvc_cancel_blocked(struct net *net, struct nlm_file *, struct nlm_lock *);
 void		  nlmsvc_retry_blocked(struct svc_rqst *rqstp);
 void		  nlmsvc_traverse_blocks(struct nlm_host *, struct nlm_file *,

From 9189d23b835cec646ba5010db35d1557a77c5857 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2024 09:36:31 -0400
Subject: [PATCH 1237/1530] lockd: Remove unneeded initialization of
 file_lock::c.flc_flags

Since commit 75c7940d2a86 ("lockd: set missing fl_flags field when
retrieving args"), nlmsvc_retrieve_args() initializes the flc_flags
field. svcxdr_decode_lock() no longer needs to do this.

This clean up removes one dependency on the nlm_lock:fl field. No
behavior change is expected.

Analysis:

svcxdr_decode_lock() is called by:

nlm4svc_decode_testargs()
nlm4svc_decode_lockargs()
nlm4svc_decode_cancargs()
nlm4svc_decode_unlockargs()

nlm4svc_decode_testargs() is used by:
- NLMPROC4_TEST and NLMPROC4_TEST_MSG, which call nlmsvc_retrieve_args()
- NLMPROC4_GRANTED and NLMPROC4_GRANTED_MSG, which don't pass the
  lock's file_lock to the generic lock API

nlm4svc_decode_lockargs() is used by:
- NLMPROC4_LOCK and NLM4PROC4_LOCK_MSG, which call nlmsvc_retrieve_args()
- NLMPROC4_UNLOCK and NLM4PROC4_UNLOCK_MSG, which call nlmsvc_retrieve_args()
- NLMPROC4_NM_LOCK, which calls nlmsvc_retrieve_args()

nlm4svc_decode_cancargs() is used by:
- NLMPROC4_CANCEL and NLMPROC4_CANCEL_MSG, which call nlmsvc_retrieve_args()

nlm4svc_decode_unlockargs() is used by:
- NLMPROC4_UNLOCK and NLMPROC4_UNLOCK_MSG, which call nlmsvc_retrieve_args()

All callers except GRANTED/GRANTED_MSG eventually call
nlmsvc_retrieve_args() before using nlm_lock::fl.c.flc_flags. Thus
this change is safe.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: NeilBrown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/lockd/svc4proc.c | 5 +++--
 fs/lockd/xdr4.c     | 1 -
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 2cb6030131117..109e5caae8c70 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -46,14 +46,15 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 	if (filp != NULL) {
 		int mode = lock_to_openmode(&lock->fl);
 
+		lock->fl.c.flc_flags = FL_POSIX;
+
 		error = nlm_lookup_file(rqstp, &file, lock);
 		if (error)
 			goto no_locks;
 		*filp = file;
 
 		/* Set up the missing parts of the file_lock structure */
-		lock->fl.c.flc_flags = FL_POSIX;
-		lock->fl.c.flc_file  = file->f_file[mode];
+		lock->fl.c.flc_file = file->f_file[mode];
 		lock->fl.c.flc_pid = current->tgid;
 		lock->fl.fl_start = (loff_t)lock->lock_start;
 		lock->fl.fl_end = lock->lock_len ?
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index 60466b8bac588..e343c820301fd 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -89,7 +89,6 @@ svcxdr_decode_lock(struct xdr_stream *xdr, struct nlm_lock *lock)
 		return false;
 
 	locks_init_lock(fl);
-	fl->c.flc_flags = FL_POSIX;
 	fl->c.flc_type  = F_RDLCK;
 	nlm4svc_set_file_lock_range(fl, lock->lock_start, lock->lock_len);
 	return true;

From be8f982c369c965faffa198b46060f8853e0f1f0 Mon Sep 17 00:00:00 2001
From: Yang Erkun <yangerkun@huawei.com>
Date: Mon, 21 Oct 2024 22:23:41 +0800
Subject: [PATCH 1238/1530] nfsd: make sure exp active before svc_export_show

The function `e_show` was called with protection from RCU. This only
ensures that `exp` will not be freed. Therefore, the reference count for
`exp` can drop to zero, which will trigger a refcount use-after-free
warning when `exp_get` is called. To resolve this issue, use
`cache_get_rcu` to ensure that `exp` remains active.

------------[ cut here ]------------
refcount_t: addition on 0; use-after-free.
WARNING: CPU: 3 PID: 819 at lib/refcount.c:25
refcount_warn_saturate+0xb1/0x120
CPU: 3 UID: 0 PID: 819 Comm: cat Not tainted 6.12.0-rc3+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
1.16.1-2.fc37 04/01/2014
RIP: 0010:refcount_warn_saturate+0xb1/0x120
...
Call Trace:
 <TASK>
 e_show+0x20b/0x230 [nfsd]
 seq_read_iter+0x589/0x770
 seq_read+0x1e5/0x270
 vfs_read+0x125/0x530
 ksys_read+0xc1/0x160
 do_syscall_64+0x5f/0x170
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

Fixes: bf18f163e89c ("NFSD: Using exp_get for export getting")
Cc: stable@vger.kernel.org # 4.20+
Signed-off-by: Yang Erkun <yangerkun@huawei.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/export.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 0f40003d864f4..aa4712362b3b3 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1425,9 +1425,12 @@ static int e_show(struct seq_file *m, void *p)
 		return 0;
 	}
 
-	exp_get(exp);
+	if (!cache_get_rcu(&exp->h))
+		return 0;
+
 	if (cache_check(cd, &exp->h, NULL))
 		return 0;
+
 	exp_put(exp);
 	return svc_export_show(m, cd, cp);
 }

From 2862eee078a4d2d1f584e7f24fa50dddfa5f3471 Mon Sep 17 00:00:00 2001
From: Yang Erkun <yangerkun@huawei.com>
Date: Mon, 21 Oct 2024 22:23:42 +0800
Subject: [PATCH 1239/1530] SUNRPC: make sure cache entry active before
 cache_show

The function `c_show` was called with protection from RCU. This only
ensures that `cp` will not be freed. Therefore, the reference count for
`cp` can drop to zero, which will trigger a refcount use-after-free
warning when `cache_get` is called. To resolve this issue, use
`cache_get_rcu` to ensure that `cp` remains active.

------------[ cut here ]------------
refcount_t: addition on 0; use-after-free.
WARNING: CPU: 7 PID: 822 at lib/refcount.c:25
refcount_warn_saturate+0xb1/0x120
CPU: 7 UID: 0 PID: 822 Comm: cat Not tainted 6.12.0-rc3+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
1.16.1-2.fc37 04/01/2014
RIP: 0010:refcount_warn_saturate+0xb1/0x120

Call Trace:
 <TASK>
 c_show+0x2fc/0x380 [sunrpc]
 seq_read_iter+0x589/0x770
 seq_read+0x1e5/0x270
 proc_reg_read+0xe1/0x140
 vfs_read+0x125/0x530
 ksys_read+0xc1/0x160
 do_syscall_64+0x5f/0x170
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

Cc: stable@vger.kernel.org # v4.20+
Signed-off-by: Yang Erkun <yangerkun@huawei.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/cache.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 1bd3e531b0e09..059f6ef1ad189 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1427,7 +1427,9 @@ static int c_show(struct seq_file *m, void *p)
 		seq_printf(m, "# expiry=%lld refcnt=%d flags=%lx\n",
 			   convert_to_wallclock(cp->expiry_time),
 			   kref_read(&cp->ref), cp->flags);
-	cache_get(cp);
+	if (!cache_get_rcu(cp))
+		return 0;
+
 	if (cache_check(cd, cp, NULL))
 		/* cache_check does a cache_put on failure */
 		seq_puts(m, "# ");

From f8c989a0c89a75d30f899a7cabdc14d72522bb8d Mon Sep 17 00:00:00 2001
From: Yang Erkun <yangerkun@huawei.com>
Date: Mon, 21 Oct 2024 22:23:43 +0800
Subject: [PATCH 1240/1530] nfsd: release svc_expkey/svc_export with rcu_work

The last reference for `cache_head` can be reduced to zero in `c_show`
and `e_show`(using `rcu_read_lock` and `rcu_read_unlock`). Consequently,
`svc_export_put` and `expkey_put` will be invoked, leading to two
issues:

1. The `svc_export_put` will directly free ex_uuid. However,
   `e_show`/`c_show` will access `ex_uuid` after `cache_put`, which can
   trigger a use-after-free issue, shown below.

   ==================================================================
   BUG: KASAN: slab-use-after-free in svc_export_show+0x362/0x430 [nfsd]
   Read of size 1 at addr ff11000010fdc120 by task cat/870

   CPU: 1 UID: 0 PID: 870 Comm: cat Not tainted 6.12.0-rc3+ #1
   Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
   1.16.1-2.fc37 04/01/2014
   Call Trace:
    <TASK>
    dump_stack_lvl+0x53/0x70
    print_address_description.constprop.0+0x2c/0x3a0
    print_report+0xb9/0x280
    kasan_report+0xae/0xe0
    svc_export_show+0x362/0x430 [nfsd]
    c_show+0x161/0x390 [sunrpc]
    seq_read_iter+0x589/0x770
    seq_read+0x1e5/0x270
    proc_reg_read+0xe1/0x140
    vfs_read+0x125/0x530
    ksys_read+0xc1/0x160
    do_syscall_64+0x5f/0x170
    entry_SYSCALL_64_after_hwframe+0x76/0x7e

   Allocated by task 830:
    kasan_save_stack+0x20/0x40
    kasan_save_track+0x14/0x30
    __kasan_kmalloc+0x8f/0xa0
    __kmalloc_node_track_caller_noprof+0x1bc/0x400
    kmemdup_noprof+0x22/0x50
    svc_export_parse+0x8a9/0xb80 [nfsd]
    cache_do_downcall+0x71/0xa0 [sunrpc]
    cache_write_procfs+0x8e/0xd0 [sunrpc]
    proc_reg_write+0xe1/0x140
    vfs_write+0x1a5/0x6d0
    ksys_write+0xc1/0x160
    do_syscall_64+0x5f/0x170
    entry_SYSCALL_64_after_hwframe+0x76/0x7e

   Freed by task 868:
    kasan_save_stack+0x20/0x40
    kasan_save_track+0x14/0x30
    kasan_save_free_info+0x3b/0x60
    __kasan_slab_free+0x37/0x50
    kfree+0xf3/0x3e0
    svc_export_put+0x87/0xb0 [nfsd]
    cache_purge+0x17f/0x1f0 [sunrpc]
    nfsd_destroy_serv+0x226/0x2d0 [nfsd]
    nfsd_svc+0x125/0x1e0 [nfsd]
    write_threads+0x16a/0x2a0 [nfsd]
    nfsctl_transaction_write+0x74/0xa0 [nfsd]
    vfs_write+0x1a5/0x6d0
    ksys_write+0xc1/0x160
    do_syscall_64+0x5f/0x170
    entry_SYSCALL_64_after_hwframe+0x76/0x7e

2. We cannot sleep while using `rcu_read_lock`/`rcu_read_unlock`.
   However, `svc_export_put`/`expkey_put` will call path_put, which
   subsequently triggers a sleeping operation due to the following
   `dput`.

   =============================
   WARNING: suspicious RCU usage
   5.10.0-dirty #141 Not tainted
   -----------------------------
   ...
   Call Trace:
   dump_stack+0x9a/0xd0
   ___might_sleep+0x231/0x240
   dput+0x39/0x600
   path_put+0x1b/0x30
   svc_export_put+0x17/0x80
   e_show+0x1c9/0x200
   seq_read_iter+0x63f/0x7c0
   seq_read+0x226/0x2d0
   vfs_read+0x113/0x2c0
   ksys_read+0xc9/0x170
   do_syscall_64+0x33/0x40
   entry_SYSCALL_64_after_hwframe+0x67/0xd1

Fix these issues by using `rcu_work` to help release
`svc_expkey`/`svc_export`. This approach allows for an asynchronous
context to invoke `path_put` and also facilitates the freeing of
`uuid/exp/key` after an RCU grace period.

Fixes: 9ceddd9da134 ("knfsd: Allow lockless lookups of the exports")
Signed-off-by: Yang Erkun <yangerkun@huawei.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/export.c | 31 +++++++++++++++++++++++++------
 fs/nfsd/export.h |  4 ++--
 2 files changed, 27 insertions(+), 8 deletions(-)

diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index aa4712362b3b3..eacafe46e3b67 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -40,15 +40,24 @@
 #define	EXPKEY_HASHMAX		(1 << EXPKEY_HASHBITS)
 #define	EXPKEY_HASHMASK		(EXPKEY_HASHMAX -1)
 
-static void expkey_put(struct kref *ref)
+static void expkey_put_work(struct work_struct *work)
 {
-	struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref);
+	struct svc_expkey *key =
+		container_of(to_rcu_work(work), struct svc_expkey, ek_rcu_work);
 
 	if (test_bit(CACHE_VALID, &key->h.flags) &&
 	    !test_bit(CACHE_NEGATIVE, &key->h.flags))
 		path_put(&key->ek_path);
 	auth_domain_put(key->ek_client);
-	kfree_rcu(key, ek_rcu);
+	kfree(key);
+}
+
+static void expkey_put(struct kref *ref)
+{
+	struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref);
+
+	INIT_RCU_WORK(&key->ek_rcu_work, expkey_put_work);
+	queue_rcu_work(system_wq, &key->ek_rcu_work);
 }
 
 static int expkey_upcall(struct cache_detail *cd, struct cache_head *h)
@@ -355,16 +364,26 @@ static void export_stats_destroy(struct export_stats *stats)
 					    EXP_STATS_COUNTERS_NUM);
 }
 
-static void svc_export_put(struct kref *ref)
+static void svc_export_put_work(struct work_struct *work)
 {
-	struct svc_export *exp = container_of(ref, struct svc_export, h.ref);
+	struct svc_export *exp =
+		container_of(to_rcu_work(work), struct svc_export, ex_rcu_work);
+
 	path_put(&exp->ex_path);
 	auth_domain_put(exp->ex_client);
 	nfsd4_fslocs_free(&exp->ex_fslocs);
 	export_stats_destroy(exp->ex_stats);
 	kfree(exp->ex_stats);
 	kfree(exp->ex_uuid);
-	kfree_rcu(exp, ex_rcu);
+	kfree(exp);
+}
+
+static void svc_export_put(struct kref *ref)
+{
+	struct svc_export *exp = container_of(ref, struct svc_export, h.ref);
+
+	INIT_RCU_WORK(&exp->ex_rcu_work, svc_export_put_work);
+	queue_rcu_work(system_wq, &exp->ex_rcu_work);
 }
 
 static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h)
diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
index 4d92b99c1ffdd..6f2fbaae01fa2 100644
--- a/fs/nfsd/export.h
+++ b/fs/nfsd/export.h
@@ -75,7 +75,7 @@ struct svc_export {
 	u32			ex_layout_types;
 	struct nfsd4_deviceid_map *ex_devid_map;
 	struct cache_detail	*cd;
-	struct rcu_head		ex_rcu;
+	struct rcu_work		ex_rcu_work;
 	unsigned long		ex_xprtsec_modes;
 	struct export_stats	*ex_stats;
 };
@@ -92,7 +92,7 @@ struct svc_expkey {
 	u32			ek_fsid[6];
 
 	struct path		ek_path;
-	struct rcu_head		ek_rcu;
+	struct rcu_work		ek_rcu_work;
 };
 
 #define EX_ISSYNC(exp)		(!((exp)->ex_flags & NFSEXP_ASYNC))

From 07decac0ac6282672af182521ef0b4b61605c4b9 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 22 Oct 2024 13:43:54 -0400
Subject: [PATCH 1241/1530] xdrgen: Remove tracepoint call site

This tracepoint was a "note to self" and is not operational. It is
added only to client-side code, which so far we haven't needed. It
will cause immediate breakage once we start generating client code,
though, so remove it now.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2 | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2 b/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2
index d304eccb5c402..38c31b3f05894 100644
--- a/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2
+++ b/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2
@@ -13,10 +13,8 @@ static int {{ program }}_xdr_dec_{{ result }}(struct rpc_rqst *req,
 
 	if (!xdrgen_decode_{{ result }}(xdr, result))
 		return -EIO;
-	if (result->stat != nfs_ok) {
-		trace_nfs_xdr_status(xdr, (int)result->stat);
+	if (result->stat != nfs_ok)
 		return {{ program }}_stat_to_errno(result->stat);
-	}
 {% endif %}
 	return 0;
 }

From 82c2a36179d9bd00b792f4215cc4f71ca2d4c3a8 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 22 Oct 2024 13:44:01 -0400
Subject: [PATCH 1242/1530] xdrgen: Remove check for "nfs_ok" in C templates

Obviously, "nfs_ok" is defined only for NFS protocols. Other XDR
protocols won't know "nfs_ok" from Adam.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2 | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2 b/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2
index 38c31b3f05894..4ce4cc9fab796 100644
--- a/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2
+++ b/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2
@@ -13,7 +13,7 @@ static int {{ program }}_xdr_dec_{{ result }}(struct rpc_rqst *req,
 
 	if (!xdrgen_decode_{{ result }}(xdr, result))
 		return -EIO;
-	if (result->stat != nfs_ok)
+	if (result->stat)
 		return {{ program }}_stat_to_errno(result->stat);
 {% endif %}
 	return 0;

From 903a7d37d9ea03cfed21040467d3d345d1e6fc76 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 22 Oct 2024 13:44:08 -0400
Subject: [PATCH 1243/1530] xdrgen: Update the files included in client-side
 source code

In particular, client-side source code needs the definition of
"struct rpc_procinfo" and does not want header files that pull
in "struct svc_rqst". Otherwise, the source does not compile.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/templates/C/source_top/client.j2 | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/tools/net/sunrpc/xdrgen/templates/C/source_top/client.j2 b/tools/net/sunrpc/xdrgen/templates/C/source_top/client.j2
index e3a802cbc4d75..c5518c519854a 100644
--- a/tools/net/sunrpc/xdrgen/templates/C/source_top/client.j2
+++ b/tools/net/sunrpc/xdrgen/templates/C/source_top/client.j2
@@ -3,6 +3,11 @@
 // XDR specification file: {{ filename }}
 // XDR specification modification time: {{ mtime }}
 
-#include <linux/sunrpc/xprt.h>
+#include <linux/types.h>
 
-#include "{{ program }}xdr_gen.h"
+#include <linux/sunrpc/xdr.h>
+#include <linux/sunrpc/xdrgen/_defs.h>
+#include <linux/sunrpc/xdrgen/_builtins.h>
+#include <linux/sunrpc/xdrgen/nlm4.h>
+
+#include <linux/sunrpc/clnt.h>

From 573954a996c0056b25eda4638edfee8c010e27f7 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 22 Oct 2024 13:44:15 -0400
Subject: [PATCH 1244/1530] xdrgen: Remove program_stat_to_errno() call sites

Refactor: Translating an on-the-wire value to a local host errno is
architecturally a job for the proc function, not the XDR decoder.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2 | 2 --
 1 file changed, 2 deletions(-)

diff --git a/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2 b/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2
index 4ce4cc9fab796..aa9940e322db9 100644
--- a/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2
+++ b/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2
@@ -13,8 +13,6 @@ static int {{ program }}_xdr_dec_{{ result }}(struct rpc_rqst *req,
 
 	if (!xdrgen_decode_{{ result }}(xdr, result))
 		return -EIO;
-	if (result->stat)
-		return {{ program }}_stat_to_errno(result->stat);
 {% endif %}
 	return 0;
 }

From ce89e742a4c12b20f09a43fec1b21db33f2166cd Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Thu, 24 Oct 2024 09:55:20 +0800
Subject: [PATCH 1245/1530] svcrdma: fix miss destroy percpu_counter in
 svc_rdma_proc_init()

There's issue as follows:
RPC: Registered rdma transport module.
RPC: Registered rdma backchannel transport module.
RPC: Unregistered rdma transport module.
RPC: Unregistered rdma backchannel transport module.
BUG: unable to handle page fault for address: fffffbfff80c609a
PGD 123fee067 P4D 123fee067 PUD 123fea067 PMD 10c624067 PTE 0
Oops: Oops: 0000 [#1] PREEMPT SMP KASAN NOPTI
RIP: 0010:percpu_counter_destroy_many+0xf7/0x2a0
Call Trace:
 <TASK>
 __die+0x1f/0x70
 page_fault_oops+0x2cd/0x860
 spurious_kernel_fault+0x36/0x450
 do_kern_addr_fault+0xca/0x100
 exc_page_fault+0x128/0x150
 asm_exc_page_fault+0x26/0x30
 percpu_counter_destroy_many+0xf7/0x2a0
 mmdrop+0x209/0x350
 finish_task_switch.isra.0+0x481/0x840
 schedule_tail+0xe/0xd0
 ret_from_fork+0x23/0x80
 ret_from_fork_asm+0x1a/0x30
 </TASK>

If register_sysctl() return NULL, then svc_rdma_proc_cleanup() will not
destroy the percpu counters which init in svc_rdma_proc_init().
If CONFIG_HOTPLUG_CPU is enabled, residual nodes may be in the
'percpu_counters' list. The above issue may occur once the module is
removed. If the CONFIG_HOTPLUG_CPU configuration is not enabled, memory
leakage occurs.
To solve above issue just destroy all percpu counters when
register_sysctl() return NULL.

Fixes: 1e7e55731628 ("svcrdma: Restore read and write stats")
Fixes: 22df5a22462e ("svcrdma: Convert rdma_stat_sq_starve to a per-CPU counter")
Fixes: df971cd853c0 ("svcrdma: Convert rdma_stat_recv to a per-CPU counter")
Signed-off-by: Ye Bin <yebin10@huawei.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/xprtrdma/svc_rdma.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c
index 58ae6ec4f25b4..415c0310101f0 100644
--- a/net/sunrpc/xprtrdma/svc_rdma.c
+++ b/net/sunrpc/xprtrdma/svc_rdma.c
@@ -233,25 +233,34 @@ static int svc_rdma_proc_init(void)
 
 	rc = percpu_counter_init(&svcrdma_stat_read, 0, GFP_KERNEL);
 	if (rc)
-		goto out_err;
+		goto err;
 	rc = percpu_counter_init(&svcrdma_stat_recv, 0, GFP_KERNEL);
 	if (rc)
-		goto out_err;
+		goto err_read;
 	rc = percpu_counter_init(&svcrdma_stat_sq_starve, 0, GFP_KERNEL);
 	if (rc)
-		goto out_err;
+		goto err_recv;
 	rc = percpu_counter_init(&svcrdma_stat_write, 0, GFP_KERNEL);
 	if (rc)
-		goto out_err;
+		goto err_sq;
 
 	svcrdma_table_header = register_sysctl("sunrpc/svc_rdma",
 					       svcrdma_parm_table);
+	if (!svcrdma_table_header)
+		goto err_write;
+
 	return 0;
 
-out_err:
+err_write:
+	rc = -ENOMEM;
+	percpu_counter_destroy(&svcrdma_stat_write);
+err_sq:
 	percpu_counter_destroy(&svcrdma_stat_sq_starve);
+err_recv:
 	percpu_counter_destroy(&svcrdma_stat_recv);
+err_read:
 	percpu_counter_destroy(&svcrdma_stat_read);
+err:
 	return rc;
 }
 

From a2c0412c051ee279d338b2c288938e484ed9a6df Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Thu, 24 Oct 2024 09:10:42 +1100
Subject: [PATCH 1246/1530] nfsd: Don't fail OP_SETCLIENTID when there are too
 many clients.

Failing OP_SETCLIENTID or OP_EXCHANGE_ID should only happen if there is
memory allocation failure.  Putting a hard limit on the number of
clients is not really helpful as it will either happen too early and
prevent clients that the server can easily handle, or too late and
allow clients when the server is swamped.

The calculated limit is still useful for expiring courtesy clients where
there are "too many" clients, but it shouldn't prevent the creation of
active clients.

Testing of lots of clients against small-mem servers reports repeated
NFS4ERR_DELAY responses which doesn't seem helpful.  There may have been
reports of similar problems in production use.

Also remove an outdated comment - we do use a slab cache.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4state.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 133117b6c7ccd..ddca893a88044 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2231,21 +2231,16 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn)
 	return 1;
 }
 
-/* 
- * XXX Should we use a slab cache ?
- * This type of memory management is somewhat inefficient, but we use it
- * anyway since SETCLIENTID is not a common operation.
- */
 static struct nfs4_client *alloc_client(struct xdr_netobj name,
 				struct nfsd_net *nn)
 {
 	struct nfs4_client *clp;
 	int i;
 
-	if (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) {
+	if (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients &&
+	    atomic_read(&nn->nfsd_courtesy_clients) > 0)
 		mod_delayed_work(laundry_wq, &nn->laundromat_work, 0);
-		return NULL;
-	}
+
 	clp = kmem_cache_zalloc(client_slab, GFP_KERNEL);
 	if (clp == NULL)
 		return NULL;

From 6a404f475f65c3b74799f4652dc15753834b3be0 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Mon, 28 Oct 2024 09:04:43 +1100
Subject: [PATCH 1247/1530] nfsd: make use of warning provided by refcount_t

refcount_t, by design, checks for unwanted situations and provides
warnings.  It is rarely useful to have explicit warnings with refcount
usage.

In this case we have an explicit warning if a refcount_t reaches zero
when decremented.  Simply using refcount_dec() will provide a similar
warning and also mark the refcount_t as saturated to avoid any possible
use-after-free.

This patch drops the warning and uses refcount_dec() instead of
refcount_dec_and_test().

Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/filecache.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 1408166222c5f..c16671135d176 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -1050,7 +1050,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net,
 		 * the last one however, since we should hold another.
 		 */
 		if (nfsd_file_lru_remove(nf))
-			WARN_ON_ONCE(refcount_dec_and_test(&nf->nf_ref));
+			refcount_dec(&nf->nf_ref);
 		goto wait_for_construction;
 	}
 

From 53f9ba78e07cb19f0895b9cf905fb08b70a126f4 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 28 Oct 2024 10:26:26 -0400
Subject: [PATCH 1248/1530] nfsd: remove nfsd4_session->se_bchannel

This field is written and is never consulted again. Remove it.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4state.c | 2 --
 fs/nfsd/state.h     | 1 -
 2 files changed, 3 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index ddca893a88044..a19324a68fb3b 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2002,8 +2002,6 @@ static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs,
 	}
 
 	memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs));
-	memcpy(&new->se_bchannel, battrs, sizeof(struct nfsd4_channel_attrs));
-
 	return new;
 out_free:
 	while (i--)
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index da22eaff37552..2485e62347bd3 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -304,7 +304,6 @@ struct nfsd4_session {
 	struct nfs4_client	*se_client;
 	struct nfs4_sessionid	se_sessionid;
 	struct nfsd4_channel_attrs se_fchannel;
-	struct nfsd4_channel_attrs se_bchannel;
 	struct nfsd4_cb_sec	se_cb_sec;
 	struct list_head	se_conns;
 	u32			se_cb_prog;

From 10c93b5101ca61d03351da678b395b48678840c2 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Wed, 30 Oct 2024 10:48:46 -0400
Subject: [PATCH 1249/1530] nfsd: make nfsd4_session->se_flags a bool

While this holds the flags from the CREATE_SESSION request, nothing
ever consults them. The only flag used is NFS4_SESSION_DEAD. Make it a
simple bool instead.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4state.c | 6 +++---
 fs/nfsd/state.h     | 4 +---
 2 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index a19324a68fb3b..a334f0a0e50ad 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -149,14 +149,14 @@ void nfsd4_destroy_laundry_wq(void)
 
 static bool is_session_dead(struct nfsd4_session *ses)
 {
-	return ses->se_flags & NFS4_SESSION_DEAD;
+	return ses->se_dead;
 }
 
 static __be32 mark_session_dead_locked(struct nfsd4_session *ses, int ref_held_by_me)
 {
 	if (atomic_read(&ses->se_ref) > ref_held_by_me)
 		return nfserr_jukebox;
-	ses->se_flags |= NFS4_SESSION_DEAD;
+	ses->se_dead = true;
 	return nfs_ok;
 }
 
@@ -2133,7 +2133,7 @@ static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, stru
 	INIT_LIST_HEAD(&new->se_conns);
 
 	new->se_cb_seq_nr = 1;
-	new->se_flags = cses->flags;
+	new->se_dead = false;
 	new->se_cb_prog = cses->callback_prog;
 	new->se_cb_sec = cses->cb_sec;
 	atomic_set(&new->se_ref, 0);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 2485e62347bd3..2f735492cf6c7 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -296,11 +296,9 @@ struct nfsd4_conn {
  */
 struct nfsd4_session {
 	atomic_t		se_ref;
+	bool			se_dead;
 	struct list_head	se_hash;	/* hash by sessionid */
 	struct list_head	se_perclnt;
-/* See SESSION4_PERSIST, etc. for standard flags; this is internal-only: */
-#define NFS4_SESSION_DEAD	0x010
-	u32			se_flags;
 	struct nfs4_client	*se_client;
 	struct nfs4_sessionid	se_sessionid;
 	struct nfsd4_channel_attrs se_fchannel;

From a4452e661bc8ee56b2a893df6f523607c63f6de8 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 31 Oct 2024 09:40:02 -0400
Subject: [PATCH 1250/1530] NFSD: Add a tracepoint to record canceled async
 COPY operations

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4proc.c |  1 +
 fs/nfsd/trace.h    | 11 ++++++++++-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 94cc7b2ac385f..ca383ebc17907 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1287,6 +1287,7 @@ static void nfs4_put_copy(struct nfsd4_copy *copy)
 
 static void nfsd4_stop_copy(struct nfsd4_copy *copy)
 {
+	trace_nfsd_copy_async_cancel(copy);
 	if (!test_and_set_bit(NFSD4_COPY_F_STOPPED, &copy->cp_flags))
 		kthread_stop(copy->copy_task);
 	nfs4_put_copy(copy);
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index f318898cfc316..6b7bf8129e491 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -2244,7 +2244,7 @@ TRACE_EVENT(nfsd_copy_done,
 	)
 );
 
-TRACE_EVENT(nfsd_copy_async_done,
+DECLARE_EVENT_CLASS(nfsd_copy_async_done_class,
 	TP_PROTO(
 		const struct nfsd4_copy *copy
 	),
@@ -2313,6 +2313,15 @@ TRACE_EVENT(nfsd_copy_async_done,
 	)
 );
 
+#define DEFINE_COPY_ASYNC_DONE_EVENT(name)		\
+DEFINE_EVENT(nfsd_copy_async_done_class,		\
+	nfsd_copy_async_##name,				\
+	TP_PROTO(const struct nfsd4_copy *copy),	\
+	TP_ARGS(copy))
+
+DEFINE_COPY_ASYNC_DONE_EVENT(done);
+DEFINE_COPY_ASYNC_DONE_EVENT(cancel);
+
 #endif /* _NFSD_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH

From 62a8642ba00aa8ceb0a02ade942f5ec52e877c95 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 31 Oct 2024 09:40:03 -0400
Subject: [PATCH 1251/1530] NFSD: Fix nfsd4_shutdown_copy()

nfsd4_shutdown_copy() is just this:

	while ((copy = nfsd4_get_copy(clp)) != NULL)
		nfsd4_stop_copy(copy);

nfsd4_get_copy() bumps @copy's reference count, preventing
nfsd4_stop_copy() from releasing @copy.

A while loop like this usually works by removing the first element
of the list, but neither nfsd4_get_copy() nor nfsd4_stop_copy()
alters the async_copies list.

Best I can tell, then, is that nfsd4_shutdown_copy() continues to
loop until other threads manage to remove all the items from this
list. The spinning loop blocks shutdown until these items are gone.

Possibly the reason we haven't seen this issue in the field is
because client_has_state() prevents __destroy_client() from calling
nfsd4_shutdown_copy() if there are any items on this list. In a
subsequent patch I plan to remove that restriction.

Fixes: e0639dc5805a ("NFSD introduce async copy feature")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4proc.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index ca383ebc17907..5ad55b7345411 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1293,7 +1293,7 @@ static void nfsd4_stop_copy(struct nfsd4_copy *copy)
 	nfs4_put_copy(copy);
 }
 
-static struct nfsd4_copy *nfsd4_get_copy(struct nfs4_client *clp)
+static struct nfsd4_copy *nfsd4_unhash_copy(struct nfs4_client *clp)
 {
 	struct nfsd4_copy *copy = NULL;
 
@@ -1302,6 +1302,9 @@ static struct nfsd4_copy *nfsd4_get_copy(struct nfs4_client *clp)
 		copy = list_first_entry(&clp->async_copies, struct nfsd4_copy,
 					copies);
 		refcount_inc(&copy->refcount);
+		copy->cp_clp = NULL;
+		if (!list_empty(&copy->copies))
+			list_del_init(&copy->copies);
 	}
 	spin_unlock(&clp->async_lock);
 	return copy;
@@ -1311,7 +1314,7 @@ void nfsd4_shutdown_copy(struct nfs4_client *clp)
 {
 	struct nfsd4_copy *copy;
 
-	while ((copy = nfsd4_get_copy(clp)) != NULL)
+	while ((copy = nfsd4_unhash_copy(clp)) != NULL)
 		nfsd4_stop_copy(copy);
 }
 #ifdef CONFIG_NFSD_V4_2_INTER_SSC

From 409d6f52bd6b4fb43fbb4db9daeb5022e2e1d00c Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 31 Oct 2024 09:40:04 -0400
Subject: [PATCH 1252/1530] NFSD: Free async copy information in
 nfsd4_cb_offload_release()

RFC 7862 Section 4.8 states:

> A copy offload stateid will be valid until either (A) the client
> or server restarts or (B) the client returns the resource by
> issuing an OFFLOAD_CANCEL operation or the client replies to a
> CB_OFFLOAD operation.

Currently, NFSD purges the metadata for an async COPY operation as
soon as the CB_OFFLOAD callback has been sent. It does not wait even
for the client's CB_OFFLOAD response, as the paragraph above
suggests that it should.

This makes the OFFLOAD_STATUS operation ineffective during the
window between the completion of an asynchronous COPY and the
server's receipt of the corresponding CB_OFFLOAD response. This is
important if, for example, the client responds with NFS4ERR_DELAY,
or the transport is lost before the server receives the response. A
client might use OFFLOAD_STATUS to query the server about the still
pending asynchronous COPY, but NFSD will respond to OFFLOAD_STATUS
as if it had never heard of the presented copy stateid.

This patch starts to address this issue by extending the lifetime of
struct nfsd4_copy at least until the server has seen the client's
CB_OFFLOAD response, or the CB_OFFLOAD has timed out.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4proc.c | 17 ++++++++++-------
 fs/nfsd/xdr4.h     |  3 +++
 2 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 5ad55b7345411..5c10131410957 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -57,6 +57,8 @@ module_param(inter_copy_offload_enable, bool, 0644);
 MODULE_PARM_DESC(inter_copy_offload_enable,
 		 "Enable inter server to server copy offload. Default: false");
 
+static void cleanup_async_copy(struct nfsd4_copy *copy);
+
 #ifdef CONFIG_NFSD_V4_2_INTER_SSC
 static int nfsd4_ssc_umount_timeout = 900000;		/* default to 15 mins */
 module_param(nfsd4_ssc_umount_timeout, int, 0644);
@@ -1602,8 +1604,10 @@ static void nfsd4_cb_offload_release(struct nfsd4_callback *cb)
 {
 	struct nfsd4_cb_offload *cbo =
 		container_of(cb, struct nfsd4_cb_offload, co_cb);
+	struct nfsd4_copy *copy =
+		container_of(cbo, struct nfsd4_copy, cp_cb_offload);
 
-	kfree(cbo);
+	cleanup_async_copy(copy);
 }
 
 static int nfsd4_cb_offload_done(struct nfsd4_callback *cb,
@@ -1736,11 +1740,7 @@ static void cleanup_async_copy(struct nfsd4_copy *copy)
 
 static void nfsd4_send_cb_offload(struct nfsd4_copy *copy)
 {
-	struct nfsd4_cb_offload *cbo;
-
-	cbo = kzalloc(sizeof(*cbo), GFP_KERNEL);
-	if (!cbo)
-		return;
+	struct nfsd4_cb_offload *cbo = &copy->cp_cb_offload;
 
 	memcpy(&cbo->co_res, &copy->cp_res, sizeof(copy->cp_res));
 	memcpy(&cbo->co_fh, &copy->fh, sizeof(copy->fh));
@@ -1790,10 +1790,13 @@ static int nfsd4_do_async_copy(void *data)
 	}
 
 do_callback:
+	/* The kthread exits forthwith. Ensure that a subsequent
+	 * OFFLOAD_CANCEL won't try to kill it again. */
+	set_bit(NFSD4_COPY_F_STOPPED, &copy->cp_flags);
+
 	set_bit(NFSD4_COPY_F_COMPLETED, &copy->cp_flags);
 	trace_nfsd_copy_async_done(copy);
 	nfsd4_send_cb_offload(copy);
-	cleanup_async_copy(copy);
 	return 0;
 }
 
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index d5bb9a3c2da42..08e5d280f887f 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -700,6 +700,9 @@ struct nfsd4_copy {
 	struct nfsd42_write_res	cp_res;
 	struct knfsd_fh		fh;
 
+	/* offload callback */
+	struct nfsd4_cb_offload	cp_cb_offload;
+
 	struct nfs4_client      *cp_clp;
 
 	struct nfsd_file        *nf_src;

From 5c41f321470a5400641d3a271014ddd9b9868373 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 31 Oct 2024 09:40:05 -0400
Subject: [PATCH 1253/1530] NFSD: Handle an NFS4ERR_DELAY response to
 CB_OFFLOAD

RFC 7862 permits callback services to respond to CB_OFFLOAD with
NFS4ERR_DELAY. Currently NFSD drops the CB_OFFLOAD in that case.

To improve the reliability of COPY offload, NFSD should rather send
another CB_OFFLOAD completion notification.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4proc.c | 8 ++++++++
 fs/nfsd/xdr4.h     | 1 +
 2 files changed, 9 insertions(+)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 5c10131410957..54db3979605fb 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1617,6 +1617,13 @@ static int nfsd4_cb_offload_done(struct nfsd4_callback *cb,
 		container_of(cb, struct nfsd4_cb_offload, co_cb);
 
 	trace_nfsd_cb_offload_done(&cbo->co_res.cb_stateid, task);
+	switch (task->tk_status) {
+	case -NFS4ERR_DELAY:
+		if (cbo->co_retries--) {
+			rpc_delay(task, 1 * HZ);
+			return 0;
+		}
+	}
 	return 1;
 }
 
@@ -1745,6 +1752,7 @@ static void nfsd4_send_cb_offload(struct nfsd4_copy *copy)
 	memcpy(&cbo->co_res, &copy->cp_res, sizeof(copy->cp_res));
 	memcpy(&cbo->co_fh, &copy->fh, sizeof(copy->fh));
 	cbo->co_nfserr = copy->nfserr;
+	cbo->co_retries = 5;
 
 	nfsd4_init_cb(&cbo->co_cb, copy->cp_clp, &nfsd4_cb_offload_ops,
 		      NFSPROC4_CLNT_CB_OFFLOAD);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 08e5d280f887f..550f7e064f2ba 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -676,6 +676,7 @@ struct nfsd4_cb_offload {
 	struct nfsd4_callback	co_cb;
 	struct nfsd42_write_res	co_res;
 	__be32			co_nfserr;
+	unsigned int		co_retries;
 	struct knfsd_fh		co_fh;
 };
 

From b44ffa4c4f57ffe8a0967963538689fed169f1c8 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 31 Oct 2024 09:40:06 -0400
Subject: [PATCH 1254/1530] NFSD: Block DESTROY_CLIENTID only when there are
 ongoing async COPY operations

Currently __destroy_client() consults the nfs4_client's async_copies
list to determine whether there are ongoing async COPY operations.
However, NFSD now keeps copy state in that list even when the
async copy has completed, to enable OFFLOAD_STATUS to find the
COPY results for a while after the COPY has completed.

DESTROY_CLIENTID should not be blocked if the client's async_copies
list contains state for only completed copy operations.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4proc.c  | 30 ++++++++++++++++++++++++++++++
 fs/nfsd/nfs4state.c |  2 +-
 fs/nfsd/state.h     |  1 +
 3 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 54db3979605fb..67349eca55b11 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1278,6 +1278,36 @@ nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status;
 }
 
+/**
+ * nfsd4_has_active_async_copies - Check for ongoing copy operations
+ * @clp: Client to be checked
+ *
+ * NFSD maintains state for async COPY operations after they complete,
+ * and this state remains in the nfs4_client's async_copies list.
+ * Ongoing copies should block the destruction of the nfs4_client, but
+ * completed copies should not.
+ *
+ * Return values:
+ *   %true: At least one active async COPY is ongoing
+ *   %false: No active async COPY operations were found
+ */
+bool nfsd4_has_active_async_copies(struct nfs4_client *clp)
+{
+	struct nfsd4_copy *copy;
+	bool result = false;
+
+	spin_lock(&clp->async_lock);
+	list_for_each_entry(copy, &clp->async_copies, copies) {
+		if (!test_bit(NFSD4_COPY_F_COMPLETED, &copy->cp_flags) &&
+		    !test_bit(NFSD4_COPY_F_STOPPED, &copy->cp_flags)) {
+			result = true;
+			break;
+		}
+	}
+	spin_unlock(&clp->async_lock);
+	return result;
+}
+
 static void nfs4_put_copy(struct nfsd4_copy *copy)
 {
 	if (!refcount_dec_and_test(&copy->refcount))
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index a334f0a0e50ad..b8bedc6a157f4 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3472,7 +3472,7 @@ static bool client_has_state(struct nfs4_client *clp)
 #endif
 		|| !list_empty(&clp->cl_delegations)
 		|| !list_empty(&clp->cl_sessions)
-		|| !list_empty(&clp->async_copies);
+		|| nfsd4_has_active_async_copies(clp);
 }
 
 static __be32 copy_impl_id(struct nfs4_client *clp,
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 2f735492cf6c7..4dd7ed7ae0524 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -738,6 +738,7 @@ extern void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
 extern bool nfsd4_run_cb(struct nfsd4_callback *cb);
 extern void nfsd4_shutdown_callback(struct nfs4_client *);
 extern void nfsd4_shutdown_copy(struct nfs4_client *clp);
+bool nfsd4_has_active_async_copies(struct nfs4_client *clp);
 extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name,
 				struct xdr_netobj princhash, struct nfsd_net *nn);
 extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn);

From ac0514f4d198b5d1d5ba367b122cdf5a68e711d4 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 31 Oct 2024 09:40:07 -0400
Subject: [PATCH 1255/1530] NFSD: Add a laundromat reaper for async copy state

RFC 7862 Section 4.8 states:

> A copy offload stateid will be valid until either (A) the client
> or server restarts or (B) the client returns the resource by
> issuing an OFFLOAD_CANCEL operation or the client replies to a
> CB_OFFLOAD operation.

Instead of releasing async copy state when the CB_OFFLOAD callback
completes, now let it live until the next laundromat run after the
callback completes.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4proc.c  | 35 ++++++++++++++++++++++++++++++++++-
 fs/nfsd/nfs4state.c |  1 +
 fs/nfsd/state.h     |  1 +
 fs/nfsd/xdr4.h      |  1 +
 4 files changed, 37 insertions(+), 1 deletion(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 67349eca55b11..dfc118bf9aa5d 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1308,6 +1308,39 @@ bool nfsd4_has_active_async_copies(struct nfs4_client *clp)
 	return result;
 }
 
+/**
+ * nfsd4_async_copy_reaper - Purge completed copies
+ * @nn: Network namespace with possible active copy information
+ */
+void nfsd4_async_copy_reaper(struct nfsd_net *nn)
+{
+	struct nfs4_client *clp;
+	struct nfsd4_copy *copy;
+	LIST_HEAD(reaplist);
+
+	spin_lock(&nn->client_lock);
+	list_for_each_entry(clp, &nn->client_lru, cl_lru) {
+		struct list_head *pos, *next;
+
+		spin_lock(&clp->async_lock);
+		list_for_each_safe(pos, next, &clp->async_copies) {
+			copy = list_entry(pos, struct nfsd4_copy, copies);
+			if (test_bit(NFSD4_COPY_F_OFFLOAD_DONE, &copy->cp_flags)) {
+				list_del_init(&copy->copies);
+				list_add(&copy->copies, &reaplist);
+			}
+		}
+		spin_unlock(&clp->async_lock);
+	}
+	spin_unlock(&nn->client_lock);
+
+	while (!list_empty(&reaplist)) {
+		copy = list_first_entry(&reaplist, struct nfsd4_copy, copies);
+		list_del_init(&copy->copies);
+		cleanup_async_copy(copy);
+	}
+}
+
 static void nfs4_put_copy(struct nfsd4_copy *copy)
 {
 	if (!refcount_dec_and_test(&copy->refcount))
@@ -1637,7 +1670,7 @@ static void nfsd4_cb_offload_release(struct nfsd4_callback *cb)
 	struct nfsd4_copy *copy =
 		container_of(cbo, struct nfsd4_copy, cp_cb_offload);
 
-	cleanup_async_copy(copy);
+	set_bit(NFSD4_COPY_F_OFFLOAD_DONE, &copy->cp_flags);
 }
 
 static int nfsd4_cb_offload_done(struct nfsd4_callback *cb,
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index b8bedc6a157f4..10aa7732e9146 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -6574,6 +6574,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 			_free_cpntf_state_locked(nn, cps);
 	}
 	spin_unlock(&nn->s2s_cp_lock);
+	nfsd4_async_copy_reaper(nn);
 	nfs4_get_client_reaplist(nn, &reaplist, &lt);
 	nfs4_process_client_reaplist(&reaplist);
 
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 4dd7ed7ae0524..dcbebd53e5f40 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -738,6 +738,7 @@ extern void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
 extern bool nfsd4_run_cb(struct nfsd4_callback *cb);
 extern void nfsd4_shutdown_callback(struct nfs4_client *);
 extern void nfsd4_shutdown_copy(struct nfs4_client *clp);
+void nfsd4_async_copy_reaper(struct nfsd_net *nn);
 bool nfsd4_has_active_async_copies(struct nfs4_client *clp);
 extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name,
 				struct xdr_netobj princhash, struct nfsd_net *nn);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 550f7e064f2ba..5951360f6d039 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -695,6 +695,7 @@ struct nfsd4_copy {
 #define NFSD4_COPY_F_SYNCHRONOUS	(2)
 #define NFSD4_COPY_F_COMMITTED		(3)
 #define NFSD4_COPY_F_COMPLETED		(4)
+#define NFSD4_COPY_F_OFFLOAD_DONE	(5)
 
 	/* response */
 	__be32			nfserr;

From aa0ebd21df9c90a69f8bf00e3fa49d476be8e290 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 31 Oct 2024 09:40:08 -0400
Subject: [PATCH 1256/1530] NFSD: Add nfsd4_copy time-to-live

Keep async copy state alive for a few lease cycles after the copy
completes so that OFFLOAD_STATUS returns something meaningful.

This means that NFSD's client shutdown processing needs to purge
any of this state that happens to be waiting to die.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4proc.c |  7 +++++--
 fs/nfsd/state.h    | 15 +++++++++++++++
 fs/nfsd/xdr4.h     |  1 +
 3 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index dfc118bf9aa5d..f8a10f90bc7a4 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1326,8 +1326,10 @@ void nfsd4_async_copy_reaper(struct nfsd_net *nn)
 		list_for_each_safe(pos, next, &clp->async_copies) {
 			copy = list_entry(pos, struct nfsd4_copy, copies);
 			if (test_bit(NFSD4_COPY_F_OFFLOAD_DONE, &copy->cp_flags)) {
-				list_del_init(&copy->copies);
-				list_add(&copy->copies, &reaplist);
+				if (--copy->cp_ttl) {
+					list_del_init(&copy->copies);
+					list_add(&copy->copies, &reaplist);
+				}
 			}
 		}
 		spin_unlock(&clp->async_lock);
@@ -1921,6 +1923,7 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		async_copy->cp_nn = nn;
 		INIT_LIST_HEAD(&async_copy->copies);
 		refcount_set(&async_copy->refcount, 1);
+		async_copy->cp_ttl = NFSD_COPY_INITIAL_TTL;
 		/* Arbitrary cap on number of pending async copy operations */
 		if (atomic_inc_return(&nn->pending_async_copies) >
 				(int)rqstp->rq_pool->sp_nrthreads)
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index dcbebd53e5f40..8092894e8f3cd 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -137,6 +137,21 @@ struct nfs4_cpntf_state {
 	time64_t		cpntf_time;	/* last time stateid used */
 };
 
+/*
+ * RFC 7862 Section 4.8 states:
+ *
+ * | A copy offload stateid will be valid until either (A) the client
+ * | or server restarts or (B) the client returns the resource by
+ * | issuing an OFFLOAD_CANCEL operation or the client replies to a
+ * | CB_OFFLOAD operation.
+ *
+ * Because a client might not reply to a CB_OFFLOAD, or a reply
+ * might get lost due to connection loss, NFSD purges async copy
+ * state after a short period to prevent it from accumulating
+ * over time.
+ */
+#define NFSD_COPY_INITIAL_TTL 10
+
 struct nfs4_cb_fattr {
 	struct nfsd4_callback ncf_getattr;
 	u32 ncf_cb_status;
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 5951360f6d039..382cc13893965 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -715,6 +715,7 @@ struct nfsd4_copy {
 	struct list_head	copies;
 	struct task_struct	*copy_task;
 	refcount_t		refcount;
+	unsigned int		cp_ttl;
 
 	struct nfsd4_ssc_umount_item *ss_nsui;
 	struct nfs_fh		c_fh;

From 98100e88dd8865999dc6379a3356cd799795fe7b Mon Sep 17 00:00:00 2001
From: Yang Erkun <yangerkun@huawei.com>
Date: Tue, 5 Nov 2024 19:03:14 +0800
Subject: [PATCH 1257/1530] nfsd: fix nfs4_openowner leak when concurrent
 nfsd4_open occur

The action force umount(umount -f) will attempt to kill all rpc_task even
umount operation may ultimately fail if some files remain open.
Consequently, if an action attempts to open a file, it can potentially
send two rpc_task to nfs server.

                   NFS CLIENT
thread1                             thread2
open("file")
...
nfs4_do_open
 _nfs4_do_open
  _nfs4_open_and_get_state
   _nfs4_proc_open
    nfs4_run_open_task
     /* rpc_task1 */
     rpc_run_task
     rpc_wait_for_completion_task

                                    umount -f
                                    nfs_umount_begin
                                     rpc_killall_tasks
                                      rpc_signal_task
     rpc_task1 been wakeup
     and return -512
 _nfs4_do_open // while loop
    ...
    nfs4_run_open_task
     /* rpc_task2 */
     rpc_run_task
     rpc_wait_for_completion_task

While processing an open request, nfsd will first attempt to find or
allocate an nfs4_openowner. If it finds an nfs4_openowner that is not
marked as NFS4_OO_CONFIRMED, this nfs4_openowner will released. Since
two rpc_task can attempt to open the same file simultaneously from the
client to server, and because two instances of nfsd can run
concurrently, this situation can lead to lots of memory leak.
Additionally, when we echo 0 to /proc/fs/nfsd/threads, warning will be
triggered.

                    NFS SERVER
nfsd1                  nfsd2       echo 0 > /proc/fs/nfsd/threads

nfsd4_open
 nfsd4_process_open1
  find_or_alloc_open_stateowner
   // alloc oo1, stateid1
                       nfsd4_open
                        nfsd4_process_open1
                        find_or_alloc_open_stateowner
                        // find oo1, without NFS4_OO_CONFIRMED
                         release_openowner
                          unhash_openowner_locked
                          list_del_init(&oo->oo_perclient)
                          // cannot find this oo
                          // from client, LEAK!!!
                         alloc_stateowner // alloc oo2

 nfsd4_process_open2
  init_open_stateid
  // associate oo1
  // with stateid1, stateid1 LEAK!!!
  nfs4_get_vfs_file
  // alloc nfsd_file1 and nfsd_file_mark1
  // all LEAK!!!

                         nfsd4_process_open2
                         ...

                                    write_threads
                                     ...
                                     nfsd_destroy_serv
                                      nfsd_shutdown_net
                                       nfs4_state_shutdown_net
                                        nfs4_state_destroy_net
                                         destroy_client
                                          __destroy_client
                                          // won't find oo1!!!
                                     nfsd_shutdown_generic
                                      nfsd_file_cache_shutdown
                                       kmem_cache_destroy
                                       for nfsd_file_slab
                                       and nfsd_file_mark_slab
                                       // bark since nfsd_file1
                                       // and nfsd_file_mark1
                                       // still alive

=======================================================================
BUG nfsd_file (Not tainted): Objects remaining in nfsd_file on
__kmem_cache_shutdown()
-----------------------------------------------------------------------

Slab 0xffd4000004438a80 objects=34 used=1 fp=0xff11000110e2ad28
flags=0x17ffffc0000240(workingset|head|node=0|zone=2|lastcpupid=0x1fffff)
CPU: 4 UID: 0 PID: 757 Comm: sh Not tainted 6.12.0-rc6+ #19
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
1.16.1-2.fc37 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl+0x53/0x70
 slab_err+0xb0/0xf0
 __kmem_cache_shutdown+0x15c/0x310
 kmem_cache_destroy+0x66/0x160
 nfsd_file_cache_shutdown+0xac/0x210 [nfsd]
 nfsd_destroy_serv+0x251/0x2a0 [nfsd]
 nfsd_svc+0x125/0x1e0 [nfsd]
 write_threads+0x16a/0x2a0 [nfsd]
 nfsctl_transaction_write+0x74/0xa0 [nfsd]
 vfs_write+0x1ae/0x6d0
 ksys_write+0xc1/0x160
 do_syscall_64+0x5f/0x170
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

Disabling lock debugging due to kernel taint
Object 0xff11000110e2ac38 @offset=3128
Allocated in nfsd_file_do_acquire+0x20f/0xa30 [nfsd] age=1635 cpu=3
pid=800
 nfsd_file_do_acquire+0x20f/0xa30 [nfsd]
 nfsd_file_acquire_opened+0x5f/0x90 [nfsd]
 nfs4_get_vfs_file+0x4c9/0x570 [nfsd]
 nfsd4_process_open2+0x713/0x1070 [nfsd]
 nfsd4_open+0x74b/0x8b0 [nfsd]
 nfsd4_proc_compound+0x70b/0xc20 [nfsd]
 nfsd_dispatch+0x1b4/0x3a0 [nfsd]
 svc_process_common+0x5b8/0xc50 [sunrpc]
 svc_process+0x2ab/0x3b0 [sunrpc]
 svc_handle_xprt+0x681/0xa20 [sunrpc]
 nfsd+0x183/0x220 [nfsd]
 kthread+0x199/0x1e0
 ret_from_fork+0x31/0x60
 ret_from_fork_asm+0x1a/0x30

Add nfs4_openowner_unhashed to help found unhashed nfs4_openowner, and
break nfsd4_open process to fix this problem.

Cc: stable@vger.kernel.org # v5.4+
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Yang Erkun <yangerkun@huawei.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4state.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 10aa7732e9146..2cafe90a3328e 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1652,6 +1652,14 @@ static void release_open_stateid(struct nfs4_ol_stateid *stp)
 	free_ol_stateid_reaplist(&reaplist);
 }
 
+static bool nfs4_openowner_unhashed(struct nfs4_openowner *oo)
+{
+	lockdep_assert_held(&oo->oo_owner.so_client->cl_lock);
+
+	return list_empty(&oo->oo_owner.so_strhash) &&
+		list_empty(&oo->oo_perclient);
+}
+
 static void unhash_openowner_locked(struct nfs4_openowner *oo)
 {
 	struct nfs4_client *clp = oo->oo_owner.so_client;
@@ -4988,6 +4996,12 @@ init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open)
 	spin_lock(&oo->oo_owner.so_client->cl_lock);
 	spin_lock(&fp->fi_lock);
 
+	if (nfs4_openowner_unhashed(oo)) {
+		mutex_unlock(&stp->st_mutex);
+		stp = NULL;
+		goto out_unlock;
+	}
+
 	retstp = nfsd4_find_existing_open(fp, open);
 	if (retstp)
 		goto out_unlock;
@@ -6139,6 +6153,11 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 
 	if (!stp) {
 		stp = init_open_stateid(fp, open);
+		if (!stp) {
+			status = nfserr_jukebox;
+			goto out;
+		}
+
 		if (!open->op_stp)
 			new_stp = true;
 	}

From 07442ec85bded6692f2e5909f16ab8bbc86fb3be Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 12 Nov 2024 21:35:24 +0000
Subject: [PATCH 1258/1530] nfsd: get rid of include ../internal.h

added back in 2015 for the sake of vfs_clone_file_range(),
which is in linux/fs.h these days

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/vfs.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index eee39bab49a84..29cb7b812d713 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -35,7 +35,6 @@
 #include "xdr3.h"
 
 #ifdef CONFIG_NFSD_V4
-#include "../internal.h"
 #include "acl.h"
 #include "idmap.h"
 #include "xdr4.h"

From c840b8e1f039e90f97ca55525667eb961422f86c Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@kernel.org>
Date: Wed, 13 Nov 2024 22:59:38 -0500
Subject: [PATCH 1259/1530] nfs_common: must not hold RCU while calling
 nfsd_file_put_local

Move holding the RCU from nfs_to_nfsd_file_put_local to
nfs_to_nfsd_net_put.  It is the call to nfs_to->nfsd_serv_put that
requires the RCU anyway (the puts for nfsd_file and netns were
combined to avoid an extra indirect reference but that
micro-optimization isn't possible now).

This fixes xfstests generic/013 and it triggering:

"Voluntary context switch within RCU read-side critical section!"

[  143.545738] Call Trace:
[  143.546206]  <TASK>
[  143.546625]  ? show_regs+0x6d/0x80
[  143.547267]  ? __warn+0x91/0x140
[  143.547951]  ? rcu_note_context_switch+0x496/0x5d0
[  143.548856]  ? report_bug+0x193/0x1a0
[  143.549557]  ? handle_bug+0x63/0xa0
[  143.550214]  ? exc_invalid_op+0x1d/0x80
[  143.550938]  ? asm_exc_invalid_op+0x1f/0x30
[  143.551736]  ? rcu_note_context_switch+0x496/0x5d0
[  143.552634]  ? wakeup_preempt+0x62/0x70
[  143.553358]  __schedule+0xaa/0x1380
[  143.554025]  ? _raw_spin_unlock_irqrestore+0x12/0x40
[  143.554958]  ? try_to_wake_up+0x1fe/0x6b0
[  143.555715]  ? wake_up_process+0x19/0x20
[  143.556452]  schedule+0x2e/0x120
[  143.557066]  schedule_preempt_disabled+0x19/0x30
[  143.557933]  rwsem_down_read_slowpath+0x24d/0x4a0
[  143.558818]  ? xfs_efi_item_format+0x50/0xc0 [xfs]
[  143.559894]  down_read+0x4e/0xb0
[  143.560519]  xlog_cil_commit+0x1b2/0xbc0 [xfs]
[  143.561460]  ? _raw_spin_unlock+0x12/0x30
[  143.562212]  ? xfs_inode_item_precommit+0xc7/0x220 [xfs]
[  143.563309]  ? xfs_trans_run_precommits+0x69/0xd0 [xfs]
[  143.564394]  __xfs_trans_commit+0xb5/0x330 [xfs]
[  143.565367]  xfs_trans_roll+0x48/0xc0 [xfs]
[  143.566262]  xfs_defer_trans_roll+0x57/0x100 [xfs]
[  143.567278]  xfs_defer_finish_noroll+0x27a/0x490 [xfs]
[  143.568342]  xfs_defer_finish+0x1a/0x80 [xfs]
[  143.569267]  xfs_bunmapi_range+0x4d/0xb0 [xfs]
[  143.570208]  xfs_itruncate_extents_flags+0x13d/0x230 [xfs]
[  143.571353]  xfs_free_eofblocks+0x12e/0x190 [xfs]
[  143.572359]  xfs_file_release+0x12d/0x140 [xfs]
[  143.573324]  __fput+0xe8/0x2d0
[  143.573922]  __fput_sync+0x1d/0x30
[  143.574574]  nfsd_filp_close+0x33/0x60 [nfsd]
[  143.575430]  nfsd_file_free+0x96/0x150 [nfsd]
[  143.576274]  nfsd_file_put+0xf7/0x1a0 [nfsd]
[  143.577104]  nfsd_file_put_local+0x18/0x30 [nfsd]
[  143.578070]  nfs_close_local_fh+0x101/0x110 [nfs_localio]
[  143.579079]  __put_nfs_open_context+0xc9/0x180 [nfs]
[  143.580031]  nfs_file_clear_open_context+0x4a/0x60 [nfs]
[  143.581038]  nfs_file_release+0x3e/0x60 [nfs]
[  143.581879]  __fput+0xe8/0x2d0
[  143.582464]  __fput_sync+0x1d/0x30
[  143.583108]  __x64_sys_close+0x41/0x80
[  143.583823]  x64_sys_call+0x189a/0x20d0
[  143.584552]  do_syscall_64+0x64/0x170
[  143.585240]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  143.586185] RIP: 0033:0x7f3c5153efd7

Fixes: 65f2a5c36635 ("nfs_common: fix race in NFS calls to nfsd_file_put_local() and nfsd_serv_put()")
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfs_common/nfslocalio.c |  8 +++-----
 fs/nfsd/filecache.c        | 14 +++++++-------
 fs/nfsd/filecache.h        |  2 +-
 include/linux/nfslocalio.h | 18 +++++++++++++++---
 4 files changed, 26 insertions(+), 16 deletions(-)

diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c
index 09404d142d1ae..a74ec08f6c96d 100644
--- a/fs/nfs_common/nfslocalio.c
+++ b/fs/nfs_common/nfslocalio.c
@@ -155,11 +155,9 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid,
 	/* We have an implied reference to net thanks to nfsd_serv_try_get */
 	localio = nfs_to->nfsd_open_local_fh(net, uuid->dom, rpc_clnt,
 					     cred, nfs_fh, fmode);
-	if (IS_ERR(localio)) {
-		rcu_read_lock();
-		nfs_to->nfsd_serv_put(net);
-		rcu_read_unlock();
-	}
+	if (IS_ERR(localio))
+		nfs_to_nfsd_net_put(net);
+
 	return localio;
 }
 EXPORT_SYMBOL_GPL(nfs_open_local_fh);
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index c16671135d176..9a62b4da89bb7 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -391,19 +391,19 @@ nfsd_file_put(struct nfsd_file *nf)
 }
 
 /**
- * nfsd_file_put_local - put the reference to nfsd_file and local nfsd_serv
- * @nf: nfsd_file of which to put the references
+ * nfsd_file_put_local - put nfsd_file reference and arm nfsd_serv_put in caller
+ * @nf: nfsd_file of which to put the reference
  *
- * First put the reference of the nfsd_file and then put the
- * reference to the associated nn->nfsd_serv.
+ * First save the associated net to return to caller, then put
+ * the reference of the nfsd_file.
  */
-void
-nfsd_file_put_local(struct nfsd_file *nf) __must_hold(rcu)
+struct net *
+nfsd_file_put_local(struct nfsd_file *nf)
 {
 	struct net *net = nf->nf_net;
 
 	nfsd_file_put(nf);
-	nfsd_serv_put(net);
+	return net;
 }
 
 /**
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index cadf3c2689c44..d5db6b34ba302 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -55,7 +55,7 @@ void nfsd_file_cache_shutdown(void);
 int nfsd_file_cache_start_net(struct net *net);
 void nfsd_file_cache_shutdown_net(struct net *net);
 void nfsd_file_put(struct nfsd_file *nf);
-void nfsd_file_put_local(struct nfsd_file *nf);
+struct net *nfsd_file_put_local(struct nfsd_file *nf);
 struct nfsd_file *nfsd_file_get(struct nfsd_file *nf);
 struct file *nfsd_file_file(struct nfsd_file *nf);
 void nfsd_file_close_inode_sync(struct inode *inode);
diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h
index 3982fea799195..9202f4b24343d 100644
--- a/include/linux/nfslocalio.h
+++ b/include/linux/nfslocalio.h
@@ -55,7 +55,7 @@ struct nfsd_localio_operations {
 						const struct cred *,
 						const struct nfs_fh *,
 						const fmode_t);
-	void (*nfsd_file_put_local)(struct nfsd_file *);
+	struct net *(*nfsd_file_put_local)(struct nfsd_file *);
 	struct file *(*nfsd_file_file)(struct nfsd_file *);
 } ____cacheline_aligned;
 
@@ -66,7 +66,7 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *,
 		   struct rpc_clnt *, const struct cred *,
 		   const struct nfs_fh *, const fmode_t);
 
-static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio)
+static inline void nfs_to_nfsd_net_put(struct net *net)
 {
 	/*
 	 * Once reference to nfsd_serv is dropped, NFSD could be
@@ -74,10 +74,22 @@ static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio)
 	 * by always taking RCU.
 	 */
 	rcu_read_lock();
-	nfs_to->nfsd_file_put_local(localio);
+	nfs_to->nfsd_serv_put(net);
 	rcu_read_unlock();
 }
 
+static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio)
+{
+	/*
+	 * Must not hold RCU otherwise nfsd_file_put() can easily trigger:
+	 * "Voluntary context switch within RCU read-side critical section!"
+	 * by scheduling deep in underlying filesystem (e.g. XFS).
+	 */
+	struct net *net = nfs_to->nfsd_file_put_local(localio);
+
+	nfs_to_nfsd_net_put(net);
+}
+
 #else   /* CONFIG_NFS_LOCALIO */
 static inline void nfsd_localio_ops_init(void)
 {

From 583772eec7b0096516a8ee8b1cc31401894f1e3a Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 18 Nov 2024 09:54:34 -0500
Subject: [PATCH 1260/1530] nfsd: allow for up to 32 callback session slots

nfsd currently only uses a single slot in the callback channel, which is
proving to be a bottleneck in some cases. Widen the callback channel to
a max of 32 slots (subject to the client's target_maxreqs value).

Change the cb_holds_slot boolean to an integer that tracks the current
slot number (with -1 meaning "unassigned").  Move the callback slot
tracking info into the session. Add a new u32 that acts as a bitmap to
track which slots are in use, and a u32 to track the latest callback
target_slotid that the client reports. To protect the new fields, add
a new per-session spinlock (the se_lock). Fix nfsd41_cb_get_slot to always
search for the lowest slotid (using ffs()).

Finally, convert the session->se_cb_seq_nr field into an array of
ints and add the necessary handling to ensure that the seqids get
reset when the slot table grows after shrinking.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4callback.c | 118 ++++++++++++++++++++++++++++++-----------
 fs/nfsd/nfs4state.c    |  14 +++--
 fs/nfsd/state.h        |  15 +++---
 fs/nfsd/trace.h        |   2 +-
 4 files changed, 109 insertions(+), 40 deletions(-)

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 1ffac2b32d81a..3877b53e429fd 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -374,6 +374,19 @@ encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr,
 	hdr->nops++;
 }
 
+static u32 highest_slotid(struct nfsd4_session *ses)
+{
+	u32 idx;
+
+	spin_lock(&ses->se_lock);
+	idx = fls(~ses->se_cb_slot_avail);
+	if (idx > 0)
+		--idx;
+	idx = max(idx, ses->se_cb_highest_slot);
+	spin_unlock(&ses->se_lock);
+	return idx;
+}
+
 /*
  * CB_SEQUENCE4args
  *
@@ -400,15 +413,40 @@ static void encode_cb_sequence4args(struct xdr_stream *xdr,
 	encode_sessionid4(xdr, session);
 
 	p = xdr_reserve_space(xdr, 4 + 4 + 4 + 4 + 4);
-	*p++ = cpu_to_be32(session->se_cb_seq_nr);	/* csa_sequenceid */
-	*p++ = xdr_zero;			/* csa_slotid */
-	*p++ = xdr_zero;			/* csa_highest_slotid */
+	*p++ = cpu_to_be32(session->se_cb_seq_nr[cb->cb_held_slot]);	/* csa_sequenceid */
+	*p++ = cpu_to_be32(cb->cb_held_slot);		/* csa_slotid */
+	*p++ = cpu_to_be32(highest_slotid(session)); /* csa_highest_slotid */
 	*p++ = xdr_zero;			/* csa_cachethis */
 	xdr_encode_empty_array(p);		/* csa_referring_call_lists */
 
 	hdr->nops++;
 }
 
+static void update_cb_slot_table(struct nfsd4_session *ses, u32 target)
+{
+	/* No need to do anything if nothing changed */
+	if (likely(target == READ_ONCE(ses->se_cb_highest_slot)))
+		return;
+
+	spin_lock(&ses->se_lock);
+	if (target > ses->se_cb_highest_slot) {
+		int i;
+
+		target = min(target, NFSD_BC_SLOT_TABLE_SIZE - 1);
+
+		/*
+		 * Growing the slot table. Reset any new sequences to 1.
+		 *
+		 * NB: There is some debate about whether the RFC requires this,
+		 *     but the Linux client expects it.
+		 */
+		for (i = ses->se_cb_highest_slot + 1; i <= target; ++i)
+			ses->se_cb_seq_nr[i] = 1;
+	}
+	ses->se_cb_highest_slot = target;
+	spin_unlock(&ses->se_lock);
+}
+
 /*
  * CB_SEQUENCE4resok
  *
@@ -436,7 +474,7 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr,
 	struct nfsd4_session *session = cb->cb_clp->cl_cb_session;
 	int status = -ESERVERFAULT;
 	__be32 *p;
-	u32 dummy;
+	u32 seqid, slotid, target;
 
 	/*
 	 * If the server returns different values for sessionID, slotID or
@@ -452,21 +490,22 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr,
 	}
 	p += XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN);
 
-	dummy = be32_to_cpup(p++);
-	if (dummy != session->se_cb_seq_nr) {
+	seqid = be32_to_cpup(p++);
+	if (seqid != session->se_cb_seq_nr[cb->cb_held_slot]) {
 		dprintk("NFS: %s Invalid sequence number\n", __func__);
 		goto out;
 	}
 
-	dummy = be32_to_cpup(p++);
-	if (dummy != 0) {
+	slotid = be32_to_cpup(p++);
+	if (slotid != cb->cb_held_slot) {
 		dprintk("NFS: %s Invalid slotid\n", __func__);
 		goto out;
 	}
 
-	/*
-	 * FIXME: process highest slotid and target highest slotid
-	 */
+	p++; // ignore current highest slot value
+
+	target = be32_to_cpup(p++);
+	update_cb_slot_table(session, target);
 	status = 0;
 out:
 	cb->cb_seq_status = status;
@@ -1167,6 +1206,22 @@ void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
 	spin_unlock(&clp->cl_lock);
 }
 
+static int grab_slot(struct nfsd4_session *ses)
+{
+	int idx;
+
+	spin_lock(&ses->se_lock);
+	idx = ffs(ses->se_cb_slot_avail) - 1;
+	if (idx < 0 || idx > ses->se_cb_highest_slot) {
+		spin_unlock(&ses->se_lock);
+		return -1;
+	}
+	/* clear the bit for the slot */
+	ses->se_cb_slot_avail &= ~BIT(idx);
+	spin_unlock(&ses->se_lock);
+	return idx;
+}
+
 /*
  * There's currently a single callback channel slot.
  * If the slot is available, then mark it busy.  Otherwise, set the
@@ -1175,28 +1230,32 @@ void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
 static bool nfsd41_cb_get_slot(struct nfsd4_callback *cb, struct rpc_task *task)
 {
 	struct nfs4_client *clp = cb->cb_clp;
+	struct nfsd4_session *ses = clp->cl_cb_session;
 
-	if (!cb->cb_holds_slot &&
-	    test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
+	if (cb->cb_held_slot >= 0)
+		return true;
+	cb->cb_held_slot = grab_slot(ses);
+	if (cb->cb_held_slot < 0) {
 		rpc_sleep_on(&clp->cl_cb_waitq, task, NULL);
 		/* Race breaker */
-		if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
-			dprintk("%s slot is busy\n", __func__);
+		cb->cb_held_slot = grab_slot(ses);
+		if (cb->cb_held_slot < 0)
 			return false;
-		}
 		rpc_wake_up_queued_task(&clp->cl_cb_waitq, task);
 	}
-	cb->cb_holds_slot = true;
 	return true;
 }
 
 static void nfsd41_cb_release_slot(struct nfsd4_callback *cb)
 {
 	struct nfs4_client *clp = cb->cb_clp;
+	struct nfsd4_session *ses = clp->cl_cb_session;
 
-	if (cb->cb_holds_slot) {
-		cb->cb_holds_slot = false;
-		clear_bit(0, &clp->cl_cb_slot_busy);
+	if (cb->cb_held_slot >= 0) {
+		spin_lock(&ses->se_lock);
+		ses->se_cb_slot_avail |= BIT(cb->cb_held_slot);
+		spin_unlock(&ses->se_lock);
+		cb->cb_held_slot = -1;
 		rpc_wake_up_next(&clp->cl_cb_waitq);
 	}
 }
@@ -1213,8 +1272,8 @@ static void nfsd41_destroy_cb(struct nfsd4_callback *cb)
 }
 
 /*
- * TODO: cb_sequence should support referring call lists, cachethis, multiple
- * slots, and mark callback channel down on communication errors.
+ * TODO: cb_sequence should support referring call lists, cachethis,
+ * and mark callback channel down on communication errors.
  */
 static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
 {
@@ -1256,7 +1315,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
 		return true;
 	}
 
-	if (!cb->cb_holds_slot)
+	if (cb->cb_held_slot < 0)
 		goto need_restart;
 
 	/* This is the operation status code for CB_SEQUENCE */
@@ -1270,10 +1329,10 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
 		 * If CB_SEQUENCE returns an error, then the state of the slot
 		 * (sequence ID, cached reply) MUST NOT change.
 		 */
-		++session->se_cb_seq_nr;
+		++session->se_cb_seq_nr[cb->cb_held_slot];
 		break;
 	case -ESERVERFAULT:
-		++session->se_cb_seq_nr;
+		++session->se_cb_seq_nr[cb->cb_held_slot];
 		nfsd4_mark_cb_fault(cb->cb_clp);
 		ret = false;
 		break;
@@ -1299,17 +1358,16 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
 	case -NFS4ERR_BADSLOT:
 		goto retry_nowait;
 	case -NFS4ERR_SEQ_MISORDERED:
-		if (session->se_cb_seq_nr != 1) {
-			session->se_cb_seq_nr = 1;
+		if (session->se_cb_seq_nr[cb->cb_held_slot] != 1) {
+			session->se_cb_seq_nr[cb->cb_held_slot] = 1;
 			goto retry_nowait;
 		}
 		break;
 	default:
 		nfsd4_mark_cb_fault(cb->cb_clp);
 	}
-	nfsd41_cb_release_slot(cb);
-
 	trace_nfsd_cb_free_slot(task, cb);
+	nfsd41_cb_release_slot(cb);
 
 	if (RPC_SIGNALLED(task))
 		goto need_restart;
@@ -1529,7 +1587,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
 	INIT_WORK(&cb->cb_work, nfsd4_run_cb_work);
 	cb->cb_status = 0;
 	cb->cb_need_restart = false;
-	cb->cb_holds_slot = false;
+	cb->cb_held_slot = -1;
 }
 
 /**
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2cafe90a3328e..4c0aa17c5c466 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2010,6 +2010,10 @@ static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs,
 	}
 
 	memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs));
+	new->se_cb_slot_avail = ~0U;
+	new->se_cb_highest_slot = min(battrs->maxreqs - 1,
+				      NFSD_BC_SLOT_TABLE_SIZE - 1);
+	spin_lock_init(&new->se_lock);
 	return new;
 out_free:
 	while (i--)
@@ -2140,11 +2144,14 @@ static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, stru
 
 	INIT_LIST_HEAD(&new->se_conns);
 
-	new->se_cb_seq_nr = 1;
+	atomic_set(&new->se_ref, 0);
 	new->se_dead = false;
 	new->se_cb_prog = cses->callback_prog;
 	new->se_cb_sec = cses->cb_sec;
-	atomic_set(&new->se_ref, 0);
+
+	for (idx = 0; idx < NFSD_BC_SLOT_TABLE_SIZE; ++idx)
+		new->se_cb_seq_nr[idx] = 1;
+
 	idx = hash_sessionid(&new->se_sessionid);
 	list_add(&new->se_hash, &nn->sessionid_hashtbl[idx]);
 	spin_lock(&clp->cl_lock);
@@ -3153,7 +3160,6 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
 	kref_init(&clp->cl_nfsdfs.cl_ref);
 	nfsd4_init_cb(&clp->cl_cb_null, clp, NULL, NFSPROC4_CLNT_CB_NULL);
 	clp->cl_time = ktime_get_boottime_seconds();
-	clear_bit(0, &clp->cl_cb_slot_busy);
 	copy_verf(clp, verf);
 	memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage));
 	clp->cl_cb_session = NULL;
@@ -3935,6 +3941,8 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 	cr_ses->flags &= ~SESSION4_PERSIST;
 	/* Upshifting from TCP to RDMA is not supported */
 	cr_ses->flags &= ~SESSION4_RDMA;
+	/* Report the correct number of backchannel slots */
+	cr_ses->back_channel.maxreqs = new->se_cb_highest_slot + 1;
 
 	init_session(rqstp, new, conf, cr_ses);
 	nfsd4_get_session_locked(new);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 8092894e8f3cd..e16bb3717fb9b 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -71,8 +71,8 @@ struct nfsd4_callback {
 	struct work_struct cb_work;
 	int cb_seq_status;
 	int cb_status;
+	int cb_held_slot;
 	bool cb_need_restart;
-	bool cb_holds_slot;
 };
 
 struct nfsd4_callback_ops {
@@ -304,6 +304,9 @@ struct nfsd4_conn {
 	unsigned char cn_flags;
 };
 
+/* Maximum number of slots that nfsd will use in the backchannel */
+#define NFSD_BC_SLOT_TABLE_SIZE		(sizeof(u32) * 8)
+
 /*
  * Representation of a v4.1+ session. These are refcounted in a similar fashion
  * to the nfs4_client. References are only taken when the server is actively
@@ -311,6 +314,10 @@ struct nfsd4_conn {
  */
 struct nfsd4_session {
 	atomic_t		se_ref;
+	spinlock_t		se_lock;
+	u32			se_cb_slot_avail; /* bitmap of available slots */
+	u32			se_cb_highest_slot;	/* highest slot client wants */
+	u32			se_cb_prog;
 	bool			se_dead;
 	struct list_head	se_hash;	/* hash by sessionid */
 	struct list_head	se_perclnt;
@@ -319,8 +326,7 @@ struct nfsd4_session {
 	struct nfsd4_channel_attrs se_fchannel;
 	struct nfsd4_cb_sec	se_cb_sec;
 	struct list_head	se_conns;
-	u32			se_cb_prog;
-	u32			se_cb_seq_nr;
+	u32			se_cb_seq_nr[NFSD_BC_SLOT_TABLE_SIZE];
 	struct nfsd4_slot	*se_slots[];	/* forward channel slots */
 };
 
@@ -454,9 +460,6 @@ struct nfs4_client {
 	 */
 	struct dentry		*cl_nfsd_info_dentry;
 
-	/* for nfs41 callbacks */
-	/* We currently support a single back channel with a single slot */
-	unsigned long		cl_cb_slot_busy;
 	struct rpc_wait_queue	cl_cb_waitq;	/* backchannel callers may */
 						/* wait here for slots */
 	struct net		*net;
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 6b7bf8129e491..696c89f68a9e6 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -1697,7 +1697,7 @@ TRACE_EVENT(nfsd_cb_free_slot,
 		__entry->cl_id = sid->clientid.cl_id;
 		__entry->seqno = sid->sequence;
 		__entry->reserved = sid->reserved;
-		__entry->slot_seqno = session->se_cb_seq_nr;
+		__entry->slot_seqno = session->se_cb_seq_nr[cb->cb_held_slot];
 	),
 	TP_printk(SUNRPC_TRACE_TASK_SPECIFIER
 		" sessionid=%08x:%08x:%08x:%08x new slot seqno=%u",

From 34e77144308ff1efe2e865e68a033ce166f6411e Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Fri, 15 Nov 2024 17:50:37 +0100
Subject: [PATCH 1261/1530] Input: cypress-sf - constify struct i2c_device_id

'struct i2c_device_id' is not modified in this driver.

Constifying this structure moves some data to a read-only section, so
increase overall security.

On a x86_64, with allmodconfig:
Before:
======
   text	   data	    bss	    dec	    hex	filename
   6438	    618	      0	   7056	   1b90	drivers/input/keyboard/cypress-sf.o

After:
=====
   text	   data	    bss	    dec	    hex	filename
   6502	    554	      0	   7056	   1b90	drivers/input/keyboard/cypress-sf.o

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/4bc3e3b4d10223d9df850fe4ba48f1cefd197082.1731689418.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/cypress-sf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/keyboard/cypress-sf.c b/drivers/input/keyboard/cypress-sf.c
index eb1d0720784d9..335b72efc5aa1 100644
--- a/drivers/input/keyboard/cypress-sf.c
+++ b/drivers/input/keyboard/cypress-sf.c
@@ -208,7 +208,7 @@ static int cypress_sf_resume(struct device *dev)
 static DEFINE_SIMPLE_DEV_PM_OPS(cypress_sf_pm_ops,
 				cypress_sf_suspend, cypress_sf_resume);
 
-static struct i2c_device_id cypress_sf_id_table[] = {
+static const struct i2c_device_id cypress_sf_id_table[] = {
 	{ CYPRESS_SF_DEV_NAME },
 	{ }
 };

From c5b7a2400edc458b22133d5e5394bea26eab1923 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Tue, 19 Nov 2024 10:44:56 +0100
Subject: [PATCH 1262/1530] gfs2: Only defer deletes when we have an iopen
 glock

The mechanism to defer deleting unlinked inodes is tied to
delete_work_func(), which is tied to iopen glocks.  When we don't have
an iopen glock, we must carry out deletes immediately instead.

Fixes a NULL pointer dereference in gfs2_evict_inode().

Fixes: 8c21c2c71e66 ("gfs2: Call gfs2_queue_verify_delete from gfs2_evict_inode")
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/super.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index aadb83e38c17b..92a3b6ddafdc1 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1503,10 +1503,13 @@ static void gfs2_evict_inode(struct inode *inode)
 	    !test_bit(SDF_KILL, &sdp->sd_flags)) {
 		struct gfs2_glock *io_gl = ip->i_iopen_gh.gh_gl;
 
-		gfs2_glock_hold(io_gl);
-		if (!gfs2_queue_verify_delete(io_gl, true))
-			gfs2_glock_put(io_gl);
-		goto out;
+		if (io_gl) {
+			gfs2_glock_hold(io_gl);
+			if (!gfs2_queue_verify_delete(io_gl, true))
+				gfs2_glock_put(io_gl);
+			goto out;
+		}
+		behavior = EVICT_SHOULD_DELETE;
 	}
 	if (behavior == EVICT_SHOULD_DELETE)
 		ret = evict_unlinked_inode(inode);

From c752e87b9c3982b78dddcdd70dcb826df3cfd75d Mon Sep 17 00:00:00 2001
From: Jon Lin <jon.lin@rock-chips.com>
Date: Mon, 18 Nov 2024 22:56:46 +0800
Subject: [PATCH 1263/1530] spi: rockchip-sfc: Embedded DMA only support 4B
 aligned address

Controller limitations.

Signed-off-by: Jon Lin <jon.lin@rock-chips.com>
Link: https://patch.msgid.link/20241118145646.2609039-1-jon.lin@rock-chips.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-rockchip-sfc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-rockchip-sfc.c b/drivers/spi/spi-rockchip-sfc.c
index 316e3db884926..69d0f21755684 100644
--- a/drivers/spi/spi-rockchip-sfc.c
+++ b/drivers/spi/spi-rockchip-sfc.c
@@ -503,7 +503,7 @@ static int rockchip_sfc_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op
 	rockchip_sfc_adjust_op_work((struct spi_mem_op *)op);
 	rockchip_sfc_xfer_setup(sfc, mem, op, len);
 	if (len) {
-		if (likely(sfc->use_dma) && len >= SFC_DMA_TRANS_THRETHOLD) {
+		if (likely(sfc->use_dma) && len >= SFC_DMA_TRANS_THRETHOLD && !(len & 0x3)) {
 			init_completion(&sfc->cp);
 			rockchip_sfc_irq_unmask(sfc, SFC_IMR_DMA);
 			ret = rockchip_sfc_xfer_data_dma(sfc, op, len);

From ffd1cf0443a208b80e40100ed02892d2ec74c7e9 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Tue, 19 Nov 2024 12:15:26 +0100
Subject: [PATCH 1264/1530] gfs2: Prevent inode creation race

When a request to evict an inode comes in over the network, we are
trying to grab an inode reference via the iopen glock's gl_object
pointer.  There is a very small probability that by the time such a
request comes in, inode creation hasn't completed and the I_NEW flag is
still set.  To deal with that, wait for the inode and then check if
inode creation was successful.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 46a6e97cd9301..8db92a36194a7 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -982,6 +982,13 @@ static void gfs2_try_evict(struct gfs2_glock *gl)
 	if (ip && !igrab(&ip->i_inode))
 		ip = NULL;
 	spin_unlock(&gl->gl_lockref.lock);
+	if (ip) {
+		wait_on_inode(&ip->i_inode);
+		if (is_bad_inode(&ip->i_inode)) {
+			iput(&ip->i_inode);
+			ip = NULL;
+		}
+	}
 	if (ip) {
 		set_bit(GIF_DEFER_DELETE, &ip->i_flags);
 		d_prune_aliases(&ip->i_inode);

From f06e108a3dc53c0f5234d18de0bd224753db5019 Mon Sep 17 00:00:00 2001
From: Jan Hendrik Farr <kernel@jfarr.cc>
Date: Tue, 29 Oct 2024 15:00:36 +0100
Subject: [PATCH 1265/1530] Compiler Attributes: disable __counted_by for clang
 < 19.1.3

This patch disables __counted_by for clang versions < 19.1.3 because
of the two issues listed below. It does this by introducing
CONFIG_CC_HAS_COUNTED_BY.

1. clang < 19.1.2 has a bug that can lead to __bdos returning 0:
https://github.com/llvm/llvm-project/pull/110497

2. clang < 19.1.3 has a bug that can lead to __bdos being off by 4:
https://github.com/llvm/llvm-project/pull/112636

Fixes: c8248faf3ca2 ("Compiler Attributes: counted_by: Adjust name and identifier expansion")
Cc: stable@vger.kernel.org # 6.6.x: 16c31dd7fdf6: Compiler Attributes: counted_by: bump min gcc version
Cc: stable@vger.kernel.org # 6.6.x: 2993eb7a8d34: Compiler Attributes: counted_by: fixup clang URL
Cc: stable@vger.kernel.org # 6.6.x: 231dc3f0c936: lkdtm/bugs: Improve warning message for compilers without counted_by support
Cc: stable@vger.kernel.org # 6.6.x
Reported-by: Nathan Chancellor <nathan@kernel.org>
Closes: https://lore.kernel.org/all/20240913164630.GA4091534@thelio-3990X/
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202409260949.a1254989-oliver.sang@intel.com
Link: https://lore.kernel.org/all/Zw8iawAF5W2uzGuh@archlinux/T/#m204c09f63c076586a02d194b87dffc7e81b8de7b
Suggested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Jan Hendrik Farr <kernel@jfarr.cc>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Miguel Ojeda <ojeda@kernel.org>
Reviewed-by: Thorsten Blum <thorsten.blum@linux.dev>
Link: https://lore.kernel.org/r/20241029140036.577804-2-kernel@jfarr.cc
Signed-off-by: Kees Cook <kees@kernel.org>
---
 drivers/misc/lkdtm/bugs.c           |  2 +-
 include/linux/compiler_attributes.h | 13 -------------
 include/linux/compiler_types.h      | 19 +++++++++++++++++++
 init/Kconfig                        |  9 +++++++++
 lib/overflow_kunit.c                |  2 +-
 5 files changed, 30 insertions(+), 15 deletions(-)

diff --git a/drivers/misc/lkdtm/bugs.c b/drivers/misc/lkdtm/bugs.c
index 62ba015254797..376047beea3d6 100644
--- a/drivers/misc/lkdtm/bugs.c
+++ b/drivers/misc/lkdtm/bugs.c
@@ -445,7 +445,7 @@ static void lkdtm_FAM_BOUNDS(void)
 
 	pr_err("FAIL: survived access of invalid flexible array member index!\n");
 
-	if (!__has_attribute(__counted_by__))
+	if (!IS_ENABLED(CONFIG_CC_HAS_COUNTED_BY))
 		pr_warn("This is expected since this %s was built with a compiler that does not support __counted_by\n",
 			lkdtm_kernel_info);
 	else if (IS_ENABLED(CONFIG_UBSAN_BOUNDS))
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 32284cd26d52a..c16d4199bf923 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -94,19 +94,6 @@
 # define __copy(symbol)
 #endif
 
-/*
- * Optional: only supported since gcc >= 15
- * Optional: only supported since clang >= 18
- *
- *   gcc: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108896
- * clang: https://github.com/llvm/llvm-project/pull/76348
- */
-#if __has_attribute(__counted_by__)
-# define __counted_by(member)		__attribute__((__counted_by__(member)))
-#else
-# define __counted_by(member)
-#endif
-
 /*
  * Optional: not supported by gcc
  * Optional: only supported since clang >= 14.0
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 1a957ea2f4fe7..639be0f30b455 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -323,6 +323,25 @@ struct ftrace_likely_data {
 #define __no_sanitize_or_inline __always_inline
 #endif
 
+/*
+ * Optional: only supported since gcc >= 15
+ * Optional: only supported since clang >= 18
+ *
+ *   gcc: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108896
+ * clang: https://github.com/llvm/llvm-project/pull/76348
+ *
+ * __bdos on clang < 19.1.2 can erroneously return 0:
+ * https://github.com/llvm/llvm-project/pull/110497
+ *
+ * __bdos on clang < 19.1.3 can be off by 4:
+ * https://github.com/llvm/llvm-project/pull/112636
+ */
+#ifdef CONFIG_CC_HAS_COUNTED_BY
+# define __counted_by(member)		__attribute__((__counted_by__(member)))
+#else
+# define __counted_by(member)
+#endif
+
 /*
  * Apply __counted_by() when the Endianness matches to increase test coverage.
  */
diff --git a/init/Kconfig b/init/Kconfig
index 530a382ee0feb..92f106cf5572d 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -116,6 +116,15 @@ config CC_HAS_ASM_INLINE
 config CC_HAS_NO_PROFILE_FN_ATTR
 	def_bool $(success,echo '__attribute__((no_profile_instrument_function)) int x();' | $(CC) -x c - -c -o /dev/null -Werror)
 
+config CC_HAS_COUNTED_BY
+	# TODO: when gcc 15 is released remove the build test and add
+	# a gcc version check
+	def_bool $(success,echo 'struct flex { int count; int array[] __attribute__((__counted_by__(count))); };' | $(CC) $(CLANG_FLAGS) -x c - -c -o /dev/null -Werror)
+	# clang needs to be at least 19.1.3 to avoid __bdos miscalculations
+	# https://github.com/llvm/llvm-project/pull/110497
+	# https://github.com/llvm/llvm-project/pull/112636
+	depends on !(CC_IS_CLANG && CLANG_VERSION < 190103)
+
 config PAHOLE_VERSION
 	int
 	default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE))
diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c
index 2abc78367dd11..5222c6393f116 100644
--- a/lib/overflow_kunit.c
+++ b/lib/overflow_kunit.c
@@ -1187,7 +1187,7 @@ static void DEFINE_FLEX_test(struct kunit *test)
 {
 	/* Using _RAW_ on a __counted_by struct will initialize "counter" to zero */
 	DEFINE_RAW_FLEX(struct foo, two_but_zero, array, 2);
-#if __has_attribute(__counted_by__)
+#ifdef CONFIG_CC_HAS_COUNTED_BY
 	int expected_raw_size = sizeof(struct foo);
 #else
 	int expected_raw_size = sizeof(struct foo) + 2 * sizeof(s16);

From 5262bcbb41d526f944a91a6a6c88dfb6fba3889b Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Fri, 15 Nov 2024 11:04:26 +0100
Subject: [PATCH 1266/1530] dt-bindings: regulator: qcom-labibb-regulator:
 document the pmi8950 labibb regulator

Document the pmi8950 labibb regulator with the pmi8998 compatible
as fallback since they share the same hardware settings.

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20241115-topic-sdm450-upstream-lab-ibb-bindings-v1-1-1f4bff4583b0@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../bindings/regulator/qcom-labibb-regulator.yaml          | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/regulator/qcom-labibb-regulator.yaml b/Documentation/devicetree/bindings/regulator/qcom-labibb-regulator.yaml
index e987c39b223e7..83965076d6ab1 100644
--- a/Documentation/devicetree/bindings/regulator/qcom-labibb-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/qcom-labibb-regulator.yaml
@@ -16,7 +16,12 @@ description:
 
 properties:
   compatible:
-    const: qcom,pmi8998-lab-ibb
+    oneOf:
+      - const: qcom,pmi8998-lab-ibb
+      - items:
+          - enum:
+              - qcom,pmi8950-lab-ibb
+          - const: qcom,pmi8998-lab-ibb
 
   lab:
     type: object

From bf1d33dfb1055d008b927db5f067c647cc845930 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 14 Nov 2024 18:47:55 +0100
Subject: [PATCH 1267/1530] ACPI: processor_idle: Use acpi_idle_play_dead() for
 all C-states

Notice that acpi_processor_setup_cstates() can set state->enter_dead to acpi_idle_play_dead() for all C-states unconditionally and remove the
confusing C-state type check done before setting it.

No intentional functional impact.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Mario Limonciello <mario.limonciello@amd.com> # 6.12-rc7
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/2373563.ElGaqSPkdT@rjwysocki.net
---
 drivers/acpi/processor_idle.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 831fa4a121598..3fd3bfc9bd665 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -803,12 +803,12 @@ static int acpi_processor_setup_cstates(struct acpi_processor *pr)
 		state->enter = acpi_idle_enter;
 
 		state->flags = 0;
-		if (cx->type == ACPI_STATE_C1 || cx->type == ACPI_STATE_C2 ||
-		    cx->type == ACPI_STATE_C3) {
-			state->enter_dead = acpi_idle_play_dead;
-			if (cx->type != ACPI_STATE_C3)
-				drv->safe_state_index = count;
-		}
+
+		state->enter_dead = acpi_idle_play_dead;
+
+		if (cx->type == ACPI_STATE_C1 || cx->type == ACPI_STATE_C2)
+			drv->safe_state_index = count;
+
 		/*
 		 * Halt-induced C1 is not good for ->enter_s2idle, because it
 		 * re-enables interrupts on exit.  Moreover, C1 is generally not

From a39fbef7c411235a5caf48de3c49d4d406fd118b Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Mon, 18 Nov 2024 08:29:04 +0100
Subject: [PATCH 1268/1530] Input: spear-keyboard - don't include 'pm_wakeup.h'
 directly

The header clearly states that it does not want to be included directly,
only via 'device.h'. 'platform_device.h' works equally well. Remove the
direct inclusion.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Link: https://lore.kernel.org/r/20241118072917.3853-6-wsa+renesas@sang-engineering.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/spear-keyboard.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/input/keyboard/spear-keyboard.c b/drivers/input/keyboard/spear-keyboard.c
index 2d3f656e59dc5..2fae337562a23 100644
--- a/drivers/input/keyboard/spear-keyboard.c
+++ b/drivers/input/keyboard/spear-keyboard.c
@@ -20,7 +20,6 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
-#include <linux/pm_wakeup.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/platform_data/keyboard-spear.h>

From 048b3ae0339ef8fe9f11bc59265e5ed0027c948b Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Mon, 18 Nov 2024 08:29:05 +0100
Subject: [PATCH 1269/1530] Input: sun4i-lradc-keys - don't include
 'pm_wakeup.h' directly

The header clearly states that it does not want to be included directly,
only via 'device.h'. 'platform_device.h' works equally well. Remove the
direct inclusion.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Link: https://lore.kernel.org/r/20241118072917.3853-7-wsa+renesas@sang-engineering.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/sun4i-lradc-keys.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/input/keyboard/sun4i-lradc-keys.c b/drivers/input/keyboard/sun4i-lradc-keys.c
index f1e269605f05a..5730f08f82d79 100644
--- a/drivers/input/keyboard/sun4i-lradc-keys.c
+++ b/drivers/input/keyboard/sun4i-lradc-keys.c
@@ -24,7 +24,6 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_wakeirq.h>
-#include <linux/pm_wakeup.h>
 #include <linux/property.h>
 #include <linux/regulator/consumer.h>
 #include <linux/reset.h>

From 04337738629e8020c272c0dfcd56b9ae0a55ce98 Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Tue, 19 Nov 2024 16:27:40 -0600
Subject: [PATCH 1270/1530] Input: mpr121 - use
 devm_regulator_get_enable_read_voltage()

We can reduce boilerplate code by using
devm_regulator_get_enable_read_voltage().

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: David Lechner <dlechner@baylibre.com>
Link: https://lore.kernel.org/r/20241119-input-mpr121-regulator-get-enable-read-voltage-v3-1-1d8ee5c22f6c@baylibre.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/mpr121_touchkey.c | 45 ++----------------------
 1 file changed, 3 insertions(+), 42 deletions(-)

diff --git a/drivers/input/keyboard/mpr121_touchkey.c b/drivers/input/keyboard/mpr121_touchkey.c
index 21827d2497fa7..bd1a944ded46f 100644
--- a/drivers/input/keyboard/mpr121_touchkey.c
+++ b/drivers/input/keyboard/mpr121_touchkey.c
@@ -82,42 +82,6 @@ static const struct mpr121_init_register init_reg_table[] = {
 	{ AUTO_CONFIG_CTRL_ADDR, 0x0b },
 };
 
-static void mpr121_vdd_supply_disable(void *data)
-{
-	struct regulator *vdd_supply = data;
-
-	regulator_disable(vdd_supply);
-}
-
-static struct regulator *mpr121_vdd_supply_init(struct device *dev)
-{
-	struct regulator *vdd_supply;
-	int err;
-
-	vdd_supply = devm_regulator_get(dev, "vdd");
-	if (IS_ERR(vdd_supply)) {
-		dev_err(dev, "failed to get vdd regulator: %ld\n",
-			PTR_ERR(vdd_supply));
-		return vdd_supply;
-	}
-
-	err = regulator_enable(vdd_supply);
-	if (err) {
-		dev_err(dev, "failed to enable vdd regulator: %d\n", err);
-		return ERR_PTR(err);
-	}
-
-	err = devm_add_action_or_reset(dev, mpr121_vdd_supply_disable,
-				       vdd_supply);
-	if (err) {
-		dev_err(dev, "failed to add disable regulator action: %d\n",
-			err);
-		return ERR_PTR(err);
-	}
-
-	return vdd_supply;
-}
-
 static void mpr_touchkey_report(struct input_dev *dev)
 {
 	struct mpr121_touchkey *mpr121 = input_get_drvdata(dev);
@@ -233,7 +197,6 @@ static int mpr121_phys_init(struct mpr121_touchkey *mpr121,
 static int mpr_touchkey_probe(struct i2c_client *client)
 {
 	struct device *dev = &client->dev;
-	struct regulator *vdd_supply;
 	int vdd_uv;
 	struct mpr121_touchkey *mpr121;
 	struct input_dev *input_dev;
@@ -241,11 +204,9 @@ static int mpr_touchkey_probe(struct i2c_client *client)
 	int error;
 	int i;
 
-	vdd_supply = mpr121_vdd_supply_init(dev);
-	if (IS_ERR(vdd_supply))
-		return PTR_ERR(vdd_supply);
-
-	vdd_uv = regulator_get_voltage(vdd_supply);
+	vdd_uv = devm_regulator_get_enable_read_voltage(dev, "vdd");
+	if (vdd_uv < 0)
+		return dev_err_probe(dev, vdd_uv, "failed to get vdd voltage\n");
 
 	mpr121 = devm_kzalloc(dev, sizeof(*mpr121), GFP_KERNEL);
 	if (!mpr121)

From f13242a46438e690067a4bf47068fde4d5719947 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Sat, 16 Nov 2024 00:41:14 +1100
Subject: [PATCH 1271/1530] selftests/mount_setattr: Fix failures on 64K
 PAGE_SIZE kernels

Currently the mount_setattr_test fails on machines with a 64K PAGE_SIZE,
with errors such as:

  #  RUN           mount_setattr_idmapped.invalid_fd_negative ...
  mkfs.ext4: No space left on device while writing out and closing file system
  # mount_setattr_test.c:1055:invalid_fd_negative:Expected system("mkfs.ext4 -q /mnt/C/ext4.img") (256) == 0 (0)
  # invalid_fd_negative: Test terminated by assertion
  #          FAIL  mount_setattr_idmapped.invalid_fd_negative
  not ok 12 mount_setattr_idmapped.invalid_fd_negative

The code creates a 100,000 byte tmpfs:

	ASSERT_EQ(mount("testing", "/mnt", "tmpfs", MS_NOATIME | MS_NODEV,
			"size=100000,mode=700"), 0);

And then a little later creates a 2MB ext4 filesystem in that tmpfs:

	ASSERT_EQ(ftruncate(img_fd, 1024 * 2048), 0);
	ASSERT_EQ(system("mkfs.ext4 -q /mnt/C/ext4.img"), 0);

At first glance it seems like that should never work, after all 2MB is
larger than 100,000 bytes. However the filesystem image doesn't actually
occupy 2MB on "disk" (actually RAM, due to tmpfs). On 4K kernels the
ext4.img uses ~84KB of actual space (according to du), which just fits.

However on 64K PAGE_SIZE kernels the ext4.img takes at least 256KB,
which is too large to fit in the tmpfs, hence the errors.

It seems fraught to rely on the ext4.img taking less space on disk than
the allocated size, so instead create the tmpfs with a size of 2MB. With
that all 21 tests pass on 64K PAGE_SIZE kernels.

Fixes: 01eadc8dd96d ("tests: add mount_setattr() selftests")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20241115134114.1219555-1-mpe@ellerman.id.au
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 tools/testing/selftests/mount_setattr/mount_setattr_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
index 68801e1a9ec2d..70f65eb320a7a 100644
--- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c
+++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
@@ -1026,7 +1026,7 @@ FIXTURE_SETUP(mount_setattr_idmapped)
 			"size=100000,mode=700"), 0);
 
 	ASSERT_EQ(mount("testing", "/mnt", "tmpfs", MS_NOATIME | MS_NODEV,
-			"size=100000,mode=700"), 0);
+			"size=2m,mode=700"), 0);
 
 	ASSERT_EQ(mkdir("/mnt/A", 0777), 0);
 

From 2133ebea6b0d99e9a6ad5ea3c8df89a8881190e0 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Thu, 3 Oct 2024 02:15:46 +0100
Subject: [PATCH 1272/1530] dm cache: Remove unused
 btracker_nr_writebacks_queued

btracker_nr_writebacks_queued() has been unused since commit
2e63309507c8 ("dm cache policy smq: don't do any writebacks unless IDLE")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-cache-background-tracker.c | 6 ------
 drivers/md/dm-cache-background-tracker.h | 1 -
 2 files changed, 7 deletions(-)

diff --git a/drivers/md/dm-cache-background-tracker.c b/drivers/md/dm-cache-background-tracker.c
index f3051bd7d2df0..b4165f172d62f 100644
--- a/drivers/md/dm-cache-background-tracker.c
+++ b/drivers/md/dm-cache-background-tracker.c
@@ -143,12 +143,6 @@ static void update_stats(struct background_tracker *b, struct policy_work *w, in
 	}
 }
 
-unsigned int btracker_nr_writebacks_queued(struct background_tracker *b)
-{
-	return atomic_read(&b->pending_writebacks);
-}
-EXPORT_SYMBOL_GPL(btracker_nr_writebacks_queued);
-
 unsigned int btracker_nr_demotions_queued(struct background_tracker *b)
 {
 	return atomic_read(&b->pending_demotes);
diff --git a/drivers/md/dm-cache-background-tracker.h b/drivers/md/dm-cache-background-tracker.h
index 09c8fc59f7bb7..47156c14a44ab 100644
--- a/drivers/md/dm-cache-background-tracker.h
+++ b/drivers/md/dm-cache-background-tracker.h
@@ -50,7 +50,6 @@ struct background_tracker *btracker_create(unsigned int max_work);
  */
 void btracker_destroy(struct background_tracker *b);
 
-unsigned int btracker_nr_writebacks_queued(struct background_tracker *b);
 unsigned int btracker_nr_demotions_queued(struct background_tracker *b);
 
 /*

From 253bacc057bab6424c08a54dfcefc30e00e8d86b Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Thu, 3 Oct 2024 02:15:47 +0100
Subject: [PATCH 1273/1530] dm cache: Remove unused dm_cache_dump

dm_cache_dump() has been unused since the original commit
c6b4fcbad044 ("dm: add cache target")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-cache-metadata.c | 24 ------------------------
 drivers/md/dm-cache-metadata.h |  2 --
 2 files changed, 26 deletions(-)

diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 24cd87fddf752..5c757603ab365 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -1507,30 +1507,6 @@ int dm_cache_load_mappings(struct dm_cache_metadata *cmd,
 	return r;
 }
 
-static int __dump_mapping(void *context, uint64_t cblock, void *leaf)
-{
-	__le64 value;
-	dm_oblock_t oblock;
-	unsigned int flags;
-
-	memcpy(&value, leaf, sizeof(value));
-	unpack_value(value, &oblock, &flags);
-
-	return 0;
-}
-
-static int __dump_mappings(struct dm_cache_metadata *cmd)
-{
-	return dm_array_walk(&cmd->info, cmd->root, __dump_mapping, NULL);
-}
-
-void dm_cache_dump(struct dm_cache_metadata *cmd)
-{
-	READ_LOCK_VOID(cmd);
-	__dump_mappings(cmd);
-	READ_UNLOCK(cmd);
-}
-
 int dm_cache_changed_this_transaction(struct dm_cache_metadata *cmd)
 {
 	int r;
diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h
index 57afc70479472..3e5472173baa0 100644
--- a/drivers/md/dm-cache-metadata.h
+++ b/drivers/md/dm-cache-metadata.h
@@ -123,8 +123,6 @@ int dm_cache_get_free_metadata_block_count(struct dm_cache_metadata *cmd,
 int dm_cache_get_metadata_dev_size(struct dm_cache_metadata *cmd,
 				   dm_block_t *result);
 
-void dm_cache_dump(struct dm_cache_metadata *cmd);
-
 /*
  * The policy is invited to save a 32bit hint value for every cblock (eg,
  * for a hit count).  These are stored against the policy name.  If

From 0153b7965d55478504708a0813cc6fe1f08cc9cd Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Thu, 3 Oct 2024 02:15:48 +0100
Subject: [PATCH 1274/1530] dm cache: Remove unused dm_cache_size

dm_cache_size() has been unused since the original commit
c6b4fcbad044 ("dm: add cache target")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-cache-metadata.c | 9 ---------
 drivers/md/dm-cache-metadata.h | 1 -
 2 files changed, 10 deletions(-)

diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 5c757603ab365..a9a1ab284076a 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -1218,15 +1218,6 @@ int dm_cache_load_discards(struct dm_cache_metadata *cmd,
 	return r;
 }
 
-int dm_cache_size(struct dm_cache_metadata *cmd, dm_cblock_t *result)
-{
-	READ_LOCK(cmd);
-	*result = cmd->cache_blocks;
-	READ_UNLOCK(cmd);
-
-	return 0;
-}
-
 static int __remove(struct dm_cache_metadata *cmd, dm_cblock_t cblock)
 {
 	int r;
diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h
index 3e5472173baa0..5f77890207fed 100644
--- a/drivers/md/dm-cache-metadata.h
+++ b/drivers/md/dm-cache-metadata.h
@@ -71,7 +71,6 @@ void dm_cache_metadata_close(struct dm_cache_metadata *cmd);
  * origin blocks to map to.
  */
 int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size);
-int dm_cache_size(struct dm_cache_metadata *cmd, dm_cblock_t *result);
 
 int dm_cache_discard_bitset_resize(struct dm_cache_metadata *cmd,
 				   sector_t discard_block_size,

From 047b821ca37d262a4aca3133ced66455272cb03e Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Thu, 3 Oct 2024 02:15:49 +0100
Subject: [PATCH 1275/1530] dm cache: Remove unused functions in bio-prison-v1

dm_cache_size() and dm_cache_dump() are unused since commit
b29d4986d0da ("dm cache: significant rework to leverage dm-bio-prison-v2")

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-bio-prison-v1.c | 35 -----------------------------------
 drivers/md/dm-bio-prison-v1.h | 24 ------------------------
 2 files changed, 59 deletions(-)

diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c
index bca0f39e15b87..b4d1c4329df34 100644
--- a/drivers/md/dm-bio-prison-v1.c
+++ b/drivers/md/dm-bio-prison-v1.c
@@ -198,15 +198,6 @@ int dm_bio_detain(struct dm_bio_prison *prison,
 }
 EXPORT_SYMBOL_GPL(dm_bio_detain);
 
-int dm_get_cell(struct dm_bio_prison *prison,
-		struct dm_cell_key *key,
-		struct dm_bio_prison_cell *cell_prealloc,
-		struct dm_bio_prison_cell **cell_result)
-{
-	return bio_detain(prison, key, NULL, cell_prealloc, cell_result);
-}
-EXPORT_SYMBOL_GPL(dm_get_cell);
-
 /*
  * @inmates must have been initialised prior to this call
  */
@@ -288,32 +279,6 @@ void dm_cell_visit_release(struct dm_bio_prison *prison,
 }
 EXPORT_SYMBOL_GPL(dm_cell_visit_release);
 
-static int __promote_or_release(struct rb_root *root,
-				struct dm_bio_prison_cell *cell)
-{
-	if (bio_list_empty(&cell->bios)) {
-		rb_erase(&cell->node, root);
-		return 1;
-	}
-
-	cell->holder = bio_list_pop(&cell->bios);
-	return 0;
-}
-
-int dm_cell_promote_or_release(struct dm_bio_prison *prison,
-			       struct dm_bio_prison_cell *cell)
-{
-	int r;
-	unsigned l = lock_nr(&cell->key, prison->num_locks);
-
-	spin_lock_irq(&prison->regions[l].lock);
-	r = __promote_or_release(&prison->regions[l].cell, cell);
-	spin_unlock_irq(&prison->regions[l].lock);
-
-	return r;
-}
-EXPORT_SYMBOL_GPL(dm_cell_promote_or_release);
-
 /*----------------------------------------------------------------*/
 
 #define DEFERRED_SET_SIZE 64
diff --git a/drivers/md/dm-bio-prison-v1.h b/drivers/md/dm-bio-prison-v1.h
index 2a097ed0d85e9..d39706c484476 100644
--- a/drivers/md/dm-bio-prison-v1.h
+++ b/drivers/md/dm-bio-prison-v1.h
@@ -72,17 +72,6 @@ struct dm_bio_prison_cell *dm_bio_prison_alloc_cell(struct dm_bio_prison *prison
 void dm_bio_prison_free_cell(struct dm_bio_prison *prison,
 			     struct dm_bio_prison_cell *cell);
 
-/*
- * Creates, or retrieves a cell that overlaps the given key.
- *
- * Returns 1 if pre-existing cell returned, zero if new cell created using
- * @cell_prealloc.
- */
-int dm_get_cell(struct dm_bio_prison *prison,
-		struct dm_cell_key *key,
-		struct dm_bio_prison_cell *cell_prealloc,
-		struct dm_bio_prison_cell **cell_result);
-
 /*
  * Returns false if key is beyond BIO_PRISON_MAX_RANGE or spans a boundary.
  */
@@ -117,19 +106,6 @@ void dm_cell_visit_release(struct dm_bio_prison *prison,
 			   void (*visit_fn)(void *, struct dm_bio_prison_cell *),
 			   void *context, struct dm_bio_prison_cell *cell);
 
-/*
- * Rather than always releasing the prisoners in a cell, the client may
- * want to promote one of them to be the new holder.  There is a race here
- * though between releasing an empty cell, and other threads adding new
- * inmates.  So this function makes the decision with its lock held.
- *
- * This function can have two outcomes:
- * i) An inmate is promoted to be the holder of the cell (return value of 0).
- * ii) The cell has no inmate for promotion and is released (return value of 1).
- */
-int dm_cell_promote_or_release(struct dm_bio_prison *prison,
-			       struct dm_bio_prison_cell *cell);
-
 /*----------------------------------------------------------------*/
 
 /*

From feb83afa4e074a67b24811c9c00b688ca5c64b90 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Thu, 3 Oct 2024 02:15:50 +0100
Subject: [PATCH 1276/1530] dm: Remove unused dm_set_md_type

dm_set_md_type() has been unused since commit
ba30585936b0 ("dm: move setting md->type into dm_setup_md_queue")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm.c | 6 ------
 drivers/md/dm.h | 1 -
 2 files changed, 7 deletions(-)

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 19230404d8c2b..adf0dde689475 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2517,12 +2517,6 @@ void dm_unlock_md_type(struct mapped_device *md)
 	mutex_unlock(&md->type_lock);
 }
 
-void dm_set_md_type(struct mapped_device *md, enum dm_queue_mode type)
-{
-	BUG_ON(!mutex_is_locked(&md->type_lock));
-	md->type = type;
-}
-
 enum dm_queue_mode dm_get_md_type(struct mapped_device *md)
 {
 	return md->type;
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 8ad782249af88..d4062c3154db9 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -76,7 +76,6 @@ bool dm_table_request_based(struct dm_table *t);
 
 void dm_lock_md_type(struct mapped_device *md);
 void dm_unlock_md_type(struct mapped_device *md);
-void dm_set_md_type(struct mapped_device *md, enum dm_queue_mode type);
 enum dm_queue_mode dm_get_md_type(struct mapped_device *md);
 struct target_type *dm_get_immutable_target_type(struct mapped_device *md);
 

From ad9266118c2bb24437eb5764eb058855f93a60bc Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Thu, 3 Oct 2024 02:15:51 +0100
Subject: [PATCH 1277/1530] dm: Remove unused dm_table_bio_based

dm_table_bio_based() is unused since commit
29dec90a0f1d ("dm: fix bio_set allocation")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-table.c | 5 -----
 drivers/md/dm.h       | 1 -
 2 files changed, 6 deletions(-)

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index dbd39b9722b91..bd8b796ae683b 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1033,11 +1033,6 @@ struct dm_target *dm_table_get_wildcard_target(struct dm_table *t)
 	return NULL;
 }
 
-bool dm_table_bio_based(struct dm_table *t)
-{
-	return __table_type_bio_based(dm_table_get_type(t));
-}
-
 bool dm_table_request_based(struct dm_table *t)
 {
 	return __table_type_request_based(dm_table_get_type(t));
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index d4062c3154db9..a0a8ff1198158 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -71,7 +71,6 @@ enum dm_queue_mode dm_table_get_type(struct dm_table *t);
 struct target_type *dm_table_get_immutable_target_type(struct dm_table *t);
 struct dm_target *dm_table_get_immutable_target(struct dm_table *t);
 struct dm_target *dm_table_get_wildcard_target(struct dm_table *t);
-bool dm_table_bio_based(struct dm_table *t);
 bool dm_table_request_based(struct dm_table *t);
 
 void dm_lock_md_type(struct mapped_device *md);

From 3571fc2f9d6feb34bd355bd55129712cab41cc03 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Thu, 3 Oct 2024 02:15:52 +0100
Subject: [PATCH 1278/1530] dm: zoned: Remove unused functions

dmz_resume_metadata() is unused since it was added in commit
3b1a94c88b79 ("dm zoned: drive-managed zoned block device target")

dmz_zone_nr_blocks_shift is unused since it was added in commit
368205601375 ("dm zoned: move fields from struct dmz_dev to dmz_metadata")

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-zoned-metadata.c | 50 ----------------------------------
 drivers/md/dm-zoned.h          |  2 --
 2 files changed, 52 deletions(-)

diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 8156881a31de9..deff22ecccbb8 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -245,11 +245,6 @@ unsigned int dmz_zone_nr_blocks(struct dmz_metadata *zmd)
 	return zmd->zone_nr_blocks;
 }
 
-unsigned int dmz_zone_nr_blocks_shift(struct dmz_metadata *zmd)
-{
-	return zmd->zone_nr_blocks_shift;
-}
-
 unsigned int dmz_zone_nr_sectors(struct dmz_metadata *zmd)
 {
 	return zmd->zone_nr_sectors;
@@ -3005,48 +3000,3 @@ void dmz_dtr_metadata(struct dmz_metadata *zmd)
 	dmz_cleanup_metadata(zmd);
 	kfree(zmd);
 }
-
-/*
- * Check zone information on resume.
- */
-int dmz_resume_metadata(struct dmz_metadata *zmd)
-{
-	struct dm_zone *zone;
-	sector_t wp_block;
-	unsigned int i;
-	int ret;
-
-	/* Check zones */
-	for (i = 0; i < zmd->nr_zones; i++) {
-		zone = dmz_get(zmd, i);
-		if (!zone) {
-			dmz_zmd_err(zmd, "Unable to get zone %u", i);
-			return -EIO;
-		}
-		wp_block = zone->wp_block;
-
-		ret = dmz_update_zone(zmd, zone);
-		if (ret) {
-			dmz_zmd_err(zmd, "Broken zone %u", i);
-			return ret;
-		}
-
-		if (dmz_is_offline(zone)) {
-			dmz_zmd_warn(zmd, "Zone %u is offline", i);
-			continue;
-		}
-
-		/* Check write pointer */
-		if (!dmz_is_seq(zone))
-			zone->wp_block = 0;
-		else if (zone->wp_block != wp_block) {
-			dmz_zmd_err(zmd, "Zone %u: Invalid wp (%llu / %llu)",
-				    i, (u64)zone->wp_block, (u64)wp_block);
-			zone->wp_block = wp_block;
-			dmz_invalidate_blocks(zmd, zone, zone->wp_block,
-					      zmd->zone_nr_blocks - zone->wp_block);
-		}
-	}
-
-	return 0;
-}
diff --git a/drivers/md/dm-zoned.h b/drivers/md/dm-zoned.h
index 265494d3f7114..59ba0aaa95313 100644
--- a/drivers/md/dm-zoned.h
+++ b/drivers/md/dm-zoned.h
@@ -192,7 +192,6 @@ enum {
 int dmz_ctr_metadata(struct dmz_dev *dev, int num_dev,
 		     struct dmz_metadata **zmd, const char *devname);
 void dmz_dtr_metadata(struct dmz_metadata *zmd);
-int dmz_resume_metadata(struct dmz_metadata *zmd);
 
 void dmz_lock_map(struct dmz_metadata *zmd);
 void dmz_unlock_map(struct dmz_metadata *zmd);
@@ -230,7 +229,6 @@ unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd, int idx);
 unsigned int dmz_nr_seq_zones(struct dmz_metadata *zmd, int idx);
 unsigned int dmz_nr_unmap_seq_zones(struct dmz_metadata *zmd, int idx);
 unsigned int dmz_zone_nr_blocks(struct dmz_metadata *zmd);
-unsigned int dmz_zone_nr_blocks_shift(struct dmz_metadata *zmd);
 unsigned int dmz_zone_nr_sectors(struct dmz_metadata *zmd);
 unsigned int dmz_zone_nr_sectors_shift(struct dmz_metadata *zmd);
 

From 295815f679cef55e364b9d44fff9201a373cdefa Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Thu, 3 Oct 2024 02:15:53 +0100
Subject: [PATCH 1279/1530] dm vdo: Remove unused functions

get_data_vio_pool_active_discards()
get_data_vio_pool_discard_limit()
get_data_vio_pool_maximum_discards()
set_data_vio_pool_discard_limit()

are all unused since commit
a9da0fb6d8c6 ("dm vdo: remove all sysfs interfaces")

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Matthew Sakai <msakai@redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-vdo/data-vio.c | 29 -----------------------------
 drivers/md/dm-vdo/data-vio.h |  5 -----
 2 files changed, 34 deletions(-)

diff --git a/drivers/md/dm-vdo/data-vio.c b/drivers/md/dm-vdo/data-vio.c
index 0d502f6a86ad0..2b489e37538ea 100644
--- a/drivers/md/dm-vdo/data-vio.c
+++ b/drivers/md/dm-vdo/data-vio.c
@@ -1074,35 +1074,6 @@ void dump_data_vio_pool(struct data_vio_pool *pool, bool dump_vios)
 	spin_unlock(&pool->lock);
 }
 
-data_vio_count_t get_data_vio_pool_active_discards(struct data_vio_pool *pool)
-{
-	return READ_ONCE(pool->discard_limiter.busy);
-}
-
-data_vio_count_t get_data_vio_pool_discard_limit(struct data_vio_pool *pool)
-{
-	return READ_ONCE(pool->discard_limiter.limit);
-}
-
-data_vio_count_t get_data_vio_pool_maximum_discards(struct data_vio_pool *pool)
-{
-	return READ_ONCE(pool->discard_limiter.max_busy);
-}
-
-int set_data_vio_pool_discard_limit(struct data_vio_pool *pool, data_vio_count_t limit)
-{
-	if (get_data_vio_pool_request_limit(pool) < limit) {
-		// The discard limit may not be higher than the data_vio limit.
-		return -EINVAL;
-	}
-
-	spin_lock(&pool->lock);
-	pool->discard_limiter.limit = limit;
-	spin_unlock(&pool->lock);
-
-	return VDO_SUCCESS;
-}
-
 data_vio_count_t get_data_vio_pool_active_requests(struct data_vio_pool *pool)
 {
 	return READ_ONCE(pool->limiter.busy);
diff --git a/drivers/md/dm-vdo/data-vio.h b/drivers/md/dm-vdo/data-vio.h
index 25926b6cd98bb..067b983bb291d 100644
--- a/drivers/md/dm-vdo/data-vio.h
+++ b/drivers/md/dm-vdo/data-vio.h
@@ -336,11 +336,6 @@ void drain_data_vio_pool(struct data_vio_pool *pool, struct vdo_completion *comp
 void resume_data_vio_pool(struct data_vio_pool *pool, struct vdo_completion *completion);
 
 void dump_data_vio_pool(struct data_vio_pool *pool, bool dump_vios);
-data_vio_count_t get_data_vio_pool_active_discards(struct data_vio_pool *pool);
-data_vio_count_t get_data_vio_pool_discard_limit(struct data_vio_pool *pool);
-data_vio_count_t get_data_vio_pool_maximum_discards(struct data_vio_pool *pool);
-int __must_check set_data_vio_pool_discard_limit(struct data_vio_pool *pool,
-						 data_vio_count_t limit);
 data_vio_count_t get_data_vio_pool_active_requests(struct data_vio_pool *pool);
 data_vio_count_t get_data_vio_pool_request_limit(struct data_vio_pool *pool);
 data_vio_count_t get_data_vio_pool_maximum_requests(struct data_vio_pool *pool);

From b0e6210e7e616cdd045492576b92417aebcdde99 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Thu, 3 Oct 2024 02:15:54 +0100
Subject: [PATCH 1280/1530] dm vdo: Remove unused uds_compute_index_size

uds_compute_index_size() has been unused since it was added in
commit b46d79bdb82a ("dm vdo: add deduplication index storage interface")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Matthew Sakai <msakai@redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-vdo/indexer/index-layout.c | 26 ------------------------
 drivers/md/dm-vdo/indexer/indexer.h      |  4 ----
 2 files changed, 30 deletions(-)

diff --git a/drivers/md/dm-vdo/indexer/index-layout.c b/drivers/md/dm-vdo/indexer/index-layout.c
index 627adc24af3b7..af8fab83b0f3e 100644
--- a/drivers/md/dm-vdo/indexer/index-layout.c
+++ b/drivers/md/dm-vdo/indexer/index-layout.c
@@ -248,32 +248,6 @@ static int __must_check compute_sizes(const struct uds_configuration *config,
 	return UDS_SUCCESS;
 }
 
-int uds_compute_index_size(const struct uds_parameters *parameters, u64 *index_size)
-{
-	int result;
-	struct uds_configuration *index_config;
-	struct save_layout_sizes sizes;
-
-	if (index_size == NULL) {
-		vdo_log_error("Missing output size pointer");
-		return -EINVAL;
-	}
-
-	result = uds_make_configuration(parameters, &index_config);
-	if (result != UDS_SUCCESS) {
-		vdo_log_error_strerror(result, "cannot compute index size");
-		return uds_status_to_errno(result);
-	}
-
-	result = compute_sizes(index_config, &sizes);
-	uds_free_configuration(index_config);
-	if (result != UDS_SUCCESS)
-		return uds_status_to_errno(result);
-
-	*index_size = sizes.total_size;
-	return UDS_SUCCESS;
-}
-
 /* Create unique data using the current time and a pseudorandom number. */
 static void create_unique_nonce_data(u8 *buffer)
 {
diff --git a/drivers/md/dm-vdo/indexer/indexer.h b/drivers/md/dm-vdo/indexer/indexer.h
index 3744aaf625b05..183a94eb7e923 100644
--- a/drivers/md/dm-vdo/indexer/indexer.h
+++ b/drivers/md/dm-vdo/indexer/indexer.h
@@ -283,10 +283,6 @@ struct uds_request {
 	enum uds_index_region location;
 };
 
-/* Compute the number of bytes needed to store an index. */
-int __must_check uds_compute_index_size(const struct uds_parameters *parameters,
-					u64 *index_size);
-
 /* A session is required for most index operations. */
 int __must_check uds_create_index_session(struct uds_index_session **session);
 

From 51f0659f8777fe8ba9feef26e1d34f18edd1687c Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Thu, 24 Oct 2024 12:04:31 +0100
Subject: [PATCH 1281/1530] dm ioctl: rate limit a couple of ioctl based error
 messages

It is possible to spam the kernel log with a misbehaving user process that
is passing incorrect dm ioctls to /dev/mapper/control. Use a rate limit
on these error messages to reduce the noise.

These errors were hit when running the stress-ng's device test.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Acked-by: Mike Snitzer <snitzer@kernel.org>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-ioctl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index f299ff393a6a2..d42eac944eb54 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1912,7 +1912,7 @@ static int check_version(unsigned int cmd, struct dm_ioctl __user *user,
 
 	if ((kernel_params->version[0] != DM_VERSION_MAJOR) ||
 	    (kernel_params->version[1] > DM_VERSION_MINOR)) {
-		DMERR("ioctl interface mismatch: kernel(%u.%u.%u), user(%u.%u.%u), cmd(%d)",
+		DMERR_LIMIT("ioctl interface mismatch: kernel(%u.%u.%u), user(%u.%u.%u), cmd(%d)",
 		      DM_VERSION_MAJOR, DM_VERSION_MINOR,
 		      DM_VERSION_PATCHLEVEL,
 		      kernel_params->version[0],
@@ -1961,7 +1961,7 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern
 
 	if (unlikely(param_kernel->data_size < minimum_data_size) ||
 	    unlikely(param_kernel->data_size > DM_MAX_TARGETS * DM_MAX_TARGET_PARAMS)) {
-		DMERR("Invalid data size in the ioctl structure: %u",
+		DMERR_LIMIT("Invalid data size in the ioctl structure: %u",
 		      param_kernel->data_size);
 		return -EINVAL;
 	}

From 2deb70d3e66d538404d9e71bff236e6d260da66e Mon Sep 17 00:00:00 2001
From: Ssuhung Yeh <ssuhung@gmail.com>
Date: Thu, 31 Oct 2024 18:25:59 +0800
Subject: [PATCH 1282/1530] dm: Fix typo in error message

Remove the redundant "i" at the beginning of the error message. This "i"
came from commit 1c1318866928 ("dm: prefer
'"%s...", __func__'"), the "i" is accidentally left.

Signed-off-by: Ssuhung Yeh <ssuhung@gmail.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Fixes: 1c1318866928 ("dm: prefer '"%s...", __func__'")
Cc: stable@vger.kernel.org	# v6.3+
---
 drivers/md/persistent-data/dm-space-map-common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c
index 3a19124ee2793..22a551c407da4 100644
--- a/drivers/md/persistent-data/dm-space-map-common.c
+++ b/drivers/md/persistent-data/dm-space-map-common.c
@@ -51,7 +51,7 @@ static int index_check(const struct dm_block_validator *v,
 					       block_size - sizeof(__le32),
 					       INDEX_CSUM_XOR));
 	if (csum_disk != mi_le->csum) {
-		DMERR_LIMIT("i%s failed: csum %u != wanted %u", __func__,
+		DMERR_LIMIT("%s failed: csum %u != wanted %u", __func__,
 			    le32_to_cpu(csum_disk), le32_to_cpu(mi_le->csum));
 		return -EILSEQ;
 	}

From 87d76d286c00ae93282b6f1c8d6ed4d973c911f9 Mon Sep 17 00:00:00 2001
From: Susan LeGendre-McGhee <slegendr@redhat.com>
Date: Tue, 24 Sep 2024 11:46:24 -0400
Subject: [PATCH 1283/1530] dm-vdo murmurhash: remove u64 alignment requirement

Signed-off-by: Susan LeGendre-McGhee <slegendr@redhat.com>
Signed-off-by: Matthew Sakai <msakai@redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-vdo/murmurhash3.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/md/dm-vdo/murmurhash3.c b/drivers/md/dm-vdo/murmurhash3.c
index 13008b0892062..b0b0587d85f37 100644
--- a/drivers/md/dm-vdo/murmurhash3.c
+++ b/drivers/md/dm-vdo/murmurhash3.c
@@ -44,14 +44,11 @@ void murmurhash3_128(const void *key, const int len, const u32 seed, void *out)
 	u64 *hash_out = out;
 
 	/* body */
-
-	const u64 *blocks = (const u64 *)(data);
-
 	int i;
 
 	for (i = 0; i < nblocks; i++) {
-		u64 k1 = get_unaligned_le64(&blocks[i * 2]);
-		u64 k2 = get_unaligned_le64(&blocks[i * 2 + 1]);
+		u64 k1 = get_unaligned_le64(&data[i * 16]);
+		u64 k2 = get_unaligned_le64(&data[i * 16 + 8]);
 
 		k1 *= c1;
 		k1 = ROTL64(k1, 31);

From bd7e677c6bc4b577192f96ffeb6f965f2dbc8ecb Mon Sep 17 00:00:00 2001
From: Susan LeGendre-McGhee <slegendr@redhat.com>
Date: Tue, 24 Sep 2024 12:11:43 -0400
Subject: [PATCH 1284/1530] dm-vdo: reset bi_ioprio to the default value when
 the bio is reset

Signed-off-by: Susan LeGendre-McGhee <slegendr@redhat.com>
Signed-off-by: Matthew Sakai <msakai@redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-vdo/vio.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/md/dm-vdo/vio.c b/drivers/md/dm-vdo/vio.c
index b291578f726f5..e710f3c5a972d 100644
--- a/drivers/md/dm-vdo/vio.c
+++ b/drivers/md/dm-vdo/vio.c
@@ -202,6 +202,7 @@ int vio_reset_bio(struct vio *vio, char *data, bio_end_io_t callback,
 	if (data == NULL)
 		return VDO_SUCCESS;
 
+	bio->bi_ioprio = 0;
 	bio->bi_io_vec = bio->bi_inline_vecs;
 	bio->bi_max_vecs = vio->block_count + 1;
 	len = VDO_BLOCK_SIZE * vio->block_count;

From 7e976b2b9d0abf36665b8681e7396db2fd6412fc Mon Sep 17 00:00:00 2001
From: Matthew Sakai <msakai@redhat.com>
Date: Tue, 1 Oct 2024 18:42:41 -0400
Subject: [PATCH 1285/1530] dm vdo int-map: remove unused parameters

Remove __always_unused parameters from static functions.
Also fix minor formatting issues.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202407141607.M3E2XQ0Z-lkp@intel.com/
Closes: https://lore.kernel.org/oe-kbuild-all/202409101018.B75pIBKR-lkp@intel.com/
Closes: https://lore.kernel.org/oe-kbuild-all/202410011107.U2xbVLRA-lkp@intel.com/
Signed-off-by: Matthew Sakai <msakai@redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-vdo/int-map.c | 28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

diff --git a/drivers/md/dm-vdo/int-map.c b/drivers/md/dm-vdo/int-map.c
index f6fe58e437b3a..aeb690415dbd1 100644
--- a/drivers/md/dm-vdo/int-map.c
+++ b/drivers/md/dm-vdo/int-map.c
@@ -70,7 +70,7 @@
  * it's crucial to keep the hop fields near the buckets that they use them so they'll tend to share
  * cache lines.
  */
-struct __packed bucket {
+struct bucket {
 	/**
 	 * @first_hop: The biased offset of the first entry in the hop list of the neighborhood
 	 *             that hashes to this bucket.
@@ -82,7 +82,7 @@ struct __packed bucket {
 	u64 key;
 	/** @value: The value stored in this bucket (NULL if empty). */
 	void *value;
-};
+} __packed;
 
 /**
  * struct int_map - The concrete definition of the opaque int_map type.
@@ -310,7 +310,6 @@ static struct bucket *select_bucket(const struct int_map *map, u64 key)
 /**
  * search_hop_list() - Search the hop list associated with given hash bucket for a given search
  *                     key.
- * @map: The map being searched.
  * @bucket: The map bucket to search for the key.
  * @key: The mapping key.
  * @previous_ptr: Output. if not NULL, a pointer in which to store the bucket in the list preceding
@@ -321,9 +320,7 @@ static struct bucket *select_bucket(const struct int_map *map, u64 key)
  *
  * Return: An entry that matches the key, or NULL if not found.
  */
-static struct bucket *search_hop_list(struct int_map *map __always_unused,
-				      struct bucket *bucket,
-				      u64 key,
+static struct bucket *search_hop_list(struct bucket *bucket, u64 key,
 				      struct bucket **previous_ptr)
 {
 	struct bucket *previous = NULL;
@@ -357,7 +354,7 @@ static struct bucket *search_hop_list(struct int_map *map __always_unused,
  */
 void *vdo_int_map_get(struct int_map *map, u64 key)
 {
-	struct bucket *match = search_hop_list(map, select_bucket(map, key), key, NULL);
+	struct bucket *match = search_hop_list(select_bucket(map, key), key, NULL);
 
 	return ((match != NULL) ? match->value : NULL);
 }
@@ -443,7 +440,6 @@ find_empty_bucket(struct int_map *map, struct bucket *bucket, unsigned int max_p
 
 /**
  * move_empty_bucket() - Move an empty bucket closer to the start of the bucket array.
- * @map: The map containing the bucket.
  * @hole: The empty bucket to fill with an entry that precedes it in one of its enclosing
  *        neighborhoods.
  *
@@ -454,8 +450,7 @@ find_empty_bucket(struct int_map *map, struct bucket *bucket, unsigned int max_p
  * Return: The bucket that was vacated by moving its entry to the provided hole, or NULL if no
  *         entry could be moved.
  */
-static struct bucket *move_empty_bucket(struct int_map *map __always_unused,
-					struct bucket *hole)
+static struct bucket *move_empty_bucket(struct bucket *hole)
 {
 	/*
 	 * Examine every neighborhood that the empty bucket is part of, starting with the one in
@@ -516,7 +511,6 @@ static struct bucket *move_empty_bucket(struct int_map *map __always_unused,
 /**
  * update_mapping() - Find and update any existing mapping for a given key, returning the value
  *                    associated with the key in the provided pointer.
- * @map: The int_map to attempt to modify.
  * @neighborhood: The first bucket in the neighborhood that would contain the search key
  * @key: The key with which to associate the new value.
  * @new_value: The value to be associated with the key.
@@ -525,10 +519,10 @@ static struct bucket *move_empty_bucket(struct int_map *map __always_unused,
  *
  * Return: true if the map contains a mapping for the key, false if it does not.
  */
-static bool update_mapping(struct int_map *map, struct bucket *neighborhood,
-			   u64 key, void *new_value, bool update, void **old_value_ptr)
+static bool update_mapping(struct bucket *neighborhood, u64 key, void *new_value,
+			   bool update, void **old_value_ptr)
 {
-	struct bucket *bucket = search_hop_list(map, neighborhood, key, NULL);
+	struct bucket *bucket = search_hop_list(neighborhood, key, NULL);
 
 	if (bucket == NULL) {
 		/* There is no bucket containing the key in the neighborhood. */
@@ -584,7 +578,7 @@ static struct bucket *find_or_make_vacancy(struct int_map *map,
 		 * The nearest empty bucket isn't within the neighborhood that must contain the new
 		 * entry, so try to swap it with bucket that is closer.
 		 */
-		hole = move_empty_bucket(map, hole);
+		hole = move_empty_bucket(hole);
 	}
 
 	return NULL;
@@ -625,7 +619,7 @@ int vdo_int_map_put(struct int_map *map, u64 key, void *new_value, bool update,
 	 * Check whether the neighborhood already contains an entry for the key, in which case we
 	 * optionally update it, returning the old value.
 	 */
-	if (update_mapping(map, neighborhood, key, new_value, update, old_value_ptr))
+	if (update_mapping(neighborhood, key, new_value, update, old_value_ptr))
 		return VDO_SUCCESS;
 
 	/*
@@ -679,7 +673,7 @@ void *vdo_int_map_remove(struct int_map *map, u64 key)
 	/* Select the bucket to search and search it for an existing entry. */
 	struct bucket *bucket = select_bucket(map, key);
 	struct bucket *previous;
-	struct bucket *victim = search_hop_list(map, bucket, key, &previous);
+	struct bucket *victim = search_hop_list(bucket, key, &previous);
 
 	if (victim == NULL) {
 		/* There is no matching entry to remove. */

From 19ac19e02ffa318e77f6b086b8fb3917da0aa893 Mon Sep 17 00:00:00 2001
From: Matthew Sakai <msakai@redhat.com>
Date: Wed, 2 Oct 2024 11:52:33 -0400
Subject: [PATCH 1286/1530] dm vdo: fix function doc comment formatting

Signed-off-by: Matthew Sakai <msakai@redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-vdo/block-map.c        | 2 --
 drivers/md/dm-vdo/data-vio.c         | 7 ++++---
 drivers/md/dm-vdo/dedupe.c           | 9 +++++----
 drivers/md/dm-vdo/encodings.c        | 2 +-
 drivers/md/dm-vdo/io-submitter.c     | 2 +-
 drivers/md/dm-vdo/packer.c           | 3 +--
 drivers/md/dm-vdo/physical-zone.c    | 2 +-
 drivers/md/dm-vdo/recovery-journal.c | 2 +-
 drivers/md/dm-vdo/slab-depot.c       | 9 +++------
 drivers/md/dm-vdo/vdo.c              | 4 ++--
 10 files changed, 19 insertions(+), 23 deletions(-)

diff --git a/drivers/md/dm-vdo/block-map.c b/drivers/md/dm-vdo/block-map.c
index a0a7c1bd634e8..89cb7942ec5cc 100644
--- a/drivers/md/dm-vdo/block-map.c
+++ b/drivers/md/dm-vdo/block-map.c
@@ -209,8 +209,6 @@ static int initialize_info(struct vdo_page_cache *cache)
 /**
  * allocate_cache_components() - Allocate components of the cache which require their own
  *                               allocation.
- * @maximum_age: The number of journal blocks before a dirtied page is considered old and must be
- *               written out.
  *
  * The caller is responsible for all clean up on errors.
  *
diff --git a/drivers/md/dm-vdo/data-vio.c b/drivers/md/dm-vdo/data-vio.c
index 2b489e37538ea..810002747091f 100644
--- a/drivers/md/dm-vdo/data-vio.c
+++ b/drivers/md/dm-vdo/data-vio.c
@@ -327,8 +327,9 @@ static u32 __must_check pack_status(struct data_vio_compression_status status)
 
 /**
  * set_data_vio_compression_status() - Set the compression status of a data_vio.
- * @state: The expected current status of the data_vio.
- * @new_state: The status to set.
+ * @data_vio: The data_vio to change.
+ * @status: The expected current status of the data_vio.
+ * @new_status: The status to set.
  *
  * Return: true if the new status was set, false if the data_vio's compression status did not
  *         match the expected state, and so was left unchanged.
@@ -836,7 +837,7 @@ static void destroy_data_vio(struct data_vio *data_vio)
  * @vdo: The vdo to which the pool will belong.
  * @pool_size: The number of data_vios in the pool.
  * @discard_limit: The maximum number of data_vios which may be used for discards.
- * @pool: A pointer to hold the newly allocated pool.
+ * @pool_ptr: A pointer to hold the newly allocated pool.
  */
 int make_data_vio_pool(struct vdo *vdo, data_vio_count_t pool_size,
 		       data_vio_count_t discard_limit, struct data_vio_pool **pool_ptr)
diff --git a/drivers/md/dm-vdo/dedupe.c b/drivers/md/dm-vdo/dedupe.c
index 80628ae93fbac..b6f8e2dc7729f 100644
--- a/drivers/md/dm-vdo/dedupe.c
+++ b/drivers/md/dm-vdo/dedupe.c
@@ -565,7 +565,7 @@ static void wait_on_hash_lock(struct hash_lock *lock, struct data_vio *data_vio)
  * @waiter: The data_vio's waiter link.
  * @context: Not used.
  */
-static void abort_waiter(struct vdo_waiter *waiter, void *context __always_unused)
+static void abort_waiter(struct vdo_waiter *waiter, void __always_unused *context)
 {
 	write_data_vio(vdo_waiter_as_data_vio(waiter));
 }
@@ -1727,7 +1727,7 @@ static void report_bogus_lock_state(struct hash_lock *lock, struct data_vio *dat
 /**
  * vdo_continue_hash_lock() - Continue the processing state after writing, compressing, or
  *                            deduplicating.
- * @data_vio: The data_vio to continue processing in its hash lock.
+ * @completion: The data_vio completion to continue processing in its hash lock.
  *
  * Asynchronously continue processing a data_vio in its hash lock after it has finished writing,
  * compressing, or deduplicating, so it can share the result with any data_vios waiting in the hash
@@ -1825,7 +1825,7 @@ static inline int assert_hash_lock_preconditions(const struct data_vio *data_vio
 
 /**
  * vdo_acquire_hash_lock() - Acquire or share a lock on a record name.
- * @data_vio: The data_vio acquiring a lock on its record name.
+ * @completion: The data_vio completion acquiring a lock on its record name.
  *
  * Acquire or share a lock on the hash (record name) of the data in a data_vio, updating the
  * data_vio to reference the lock. This must only be called in the correct thread for the zone. In
@@ -2679,7 +2679,8 @@ static void get_index_statistics(struct hash_zones *zones,
 
 /**
  * vdo_get_dedupe_statistics() - Tally the statistics from all the hash zones and the UDS index.
- * @hash_zones: The hash zones to query
+ * @zones: The hash zones to query
+ * @stats: A structure to store the statistics
  *
  * Return: The sum of the hash lock statistics from all hash zones plus the statistics from the UDS
  *         index
diff --git a/drivers/md/dm-vdo/encodings.c b/drivers/md/dm-vdo/encodings.c
index a34ea0229d536..100e92f8f866c 100644
--- a/drivers/md/dm-vdo/encodings.c
+++ b/drivers/md/dm-vdo/encodings.c
@@ -858,7 +858,7 @@ static int __must_check make_partition(struct layout *layout, enum partition_id
 /**
  * vdo_initialize_layout() - Lay out the partitions of a vdo.
  * @size: The entire size of the vdo.
- * @origin: The start of the layout on the underlying storage in blocks.
+ * @offset: The start of the layout on the underlying storage in blocks.
  * @block_map_blocks: The size of the block map partition.
  * @journal_blocks: The size of the journal partition.
  * @summary_blocks: The size of the slab summary partition.
diff --git a/drivers/md/dm-vdo/io-submitter.c b/drivers/md/dm-vdo/io-submitter.c
index ab62abe18827b..421e5436c32c9 100644
--- a/drivers/md/dm-vdo/io-submitter.c
+++ b/drivers/md/dm-vdo/io-submitter.c
@@ -367,7 +367,7 @@ void __submit_metadata_vio(struct vio *vio, physical_block_number_t physical,
  *                     completions.
  * @max_requests_active: Number of bios for merge tracking.
  * @vdo: The vdo which will use this submitter.
- * @io_submitter: pointer to the new data structure.
+ * @io_submitter_ptr: pointer to the new data structure.
  *
  * Return: VDO_SUCCESS or an error.
  */
diff --git a/drivers/md/dm-vdo/packer.c b/drivers/md/dm-vdo/packer.c
index 16cf29b4c90a5..f70f5edabc100 100644
--- a/drivers/md/dm-vdo/packer.c
+++ b/drivers/md/dm-vdo/packer.c
@@ -250,7 +250,6 @@ static void abort_packing(struct data_vio *data_vio)
 /**
  * release_compressed_write_waiter() - Update a data_vio for which a successful compressed write
  *                                     has completed and send it on its way.
-
  * @data_vio: The data_vio to release.
  * @allocation: The allocation to which the compressed block was written.
  */
@@ -383,7 +382,7 @@ static void initialize_compressed_block(struct compressed_block *block, u16 size
  * @compression: The agent's compression_state to pack in to.
  * @data_vio: The data_vio to pack.
  * @offset: The offset into the compressed block at which to pack the fragment.
- * @compressed_block: The compressed block which will be written out when batch is fully packed.
+ * @block: The compressed block which will be written out when batch is fully packed.
  *
  * Return: The new amount of space used.
  */
diff --git a/drivers/md/dm-vdo/physical-zone.c b/drivers/md/dm-vdo/physical-zone.c
index 2fee3a7c1191b..a43b5c45fab7c 100644
--- a/drivers/md/dm-vdo/physical-zone.c
+++ b/drivers/md/dm-vdo/physical-zone.c
@@ -517,7 +517,7 @@ static int allocate_and_lock_block(struct allocation *allocation)
  * @waiter: The allocating_vio that was waiting to allocate.
  * @context: The context (unused).
  */
-static void retry_allocation(struct vdo_waiter *waiter, void *context __always_unused)
+static void retry_allocation(struct vdo_waiter *waiter, void __always_unused *context)
 {
 	struct data_vio *data_vio = vdo_waiter_as_data_vio(waiter);
 
diff --git a/drivers/md/dm-vdo/recovery-journal.c b/drivers/md/dm-vdo/recovery-journal.c
index ee6321a3e5238..de58184f538f5 100644
--- a/drivers/md/dm-vdo/recovery-journal.c
+++ b/drivers/md/dm-vdo/recovery-journal.c
@@ -1365,7 +1365,7 @@ static void add_queued_recovery_entries(struct recovery_journal_block *block)
  *
  * Implements waiter_callback_fn.
  */
-static void write_block(struct vdo_waiter *waiter, void *context __always_unused)
+static void write_block(struct vdo_waiter *waiter, void __always_unused *context)
 {
 	struct recovery_journal_block *block =
 		container_of(waiter, struct recovery_journal_block, write_waiter);
diff --git a/drivers/md/dm-vdo/slab-depot.c b/drivers/md/dm-vdo/slab-depot.c
index 274f9ccd072f0..625d7fd702abd 100644
--- a/drivers/md/dm-vdo/slab-depot.c
+++ b/drivers/md/dm-vdo/slab-depot.c
@@ -1287,7 +1287,7 @@ static struct reference_block * __must_check get_reference_block(struct vdo_slab
  * slab_block_number_from_pbn() - Determine the index within the slab of a particular physical
  *                                block number.
  * @slab: The slab.
- * @physical_block_number: The physical block number.
+ * @pbn: The physical block number.
  * @slab_block_number_ptr: A pointer to the slab block number.
  *
  * Return: VDO_SUCCESS or an error code.
@@ -1459,7 +1459,6 @@ static int increment_for_data(struct vdo_slab *slab, struct reference_block *blo
  * @block_number: The block to update.
  * @old_status: The reference status of the data block before this decrement.
  * @updater: The reference updater doing this operation in case we need to look up the pbn lock.
- * @lock: The pbn_lock associated with the block being decremented (may be NULL).
  * @counter_ptr: A pointer to the count for the data block (in, out).
  * @adjust_block_count: Whether to update the allocator's free block count.
  *
@@ -3232,8 +3231,7 @@ int vdo_enqueue_clean_slab_waiter(struct block_allocator *allocator,
 /**
  * vdo_modify_reference_count() - Modify the reference count of a block by first making a slab
  *                                journal entry and then updating the reference counter.
- *
- * @data_vio: The data_vio for which to add the entry.
+ * @completion: The data_vio completion for which to add the entry.
  * @updater: Which of the data_vio's reference updaters is being submitted.
  */
 void vdo_modify_reference_count(struct vdo_completion *completion,
@@ -4750,8 +4748,7 @@ void vdo_use_new_slabs(struct slab_depot *depot, struct vdo_completion *parent)
 /**
  * stop_scrubbing() - Tell the scrubber to stop scrubbing after it finishes the slab it is
  *                    currently working on.
- * @scrubber: The scrubber to stop.
- * @parent: The completion to notify when scrubbing has stopped.
+ * @allocator: The block allocator owning the scrubber to stop.
  */
 static void stop_scrubbing(struct block_allocator *allocator)
 {
diff --git a/drivers/md/dm-vdo/vdo.c b/drivers/md/dm-vdo/vdo.c
index fff847767755a..a7e32baab4afd 100644
--- a/drivers/md/dm-vdo/vdo.c
+++ b/drivers/md/dm-vdo/vdo.c
@@ -643,7 +643,7 @@ static void finish_vdo(struct vdo *vdo)
 
 /**
  * free_listeners() - Free the list of read-only listeners associated with a thread.
- * @thread_data: The thread holding the list to free.
+ * @thread: The thread holding the list to free.
  */
 static void free_listeners(struct vdo_thread *thread)
 {
@@ -852,7 +852,7 @@ int vdo_synchronous_flush(struct vdo *vdo)
 /**
  * vdo_get_state() - Get the current state of the vdo.
  * @vdo: The vdo.
-
+ *
  * Context: This method may be called from any thread.
  *
  * Return: The current state of the vdo.

From d5f01ace542de62af857fa0bd405cc16f2c45bd6 Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Thu, 31 Oct 2024 11:06:48 -0400
Subject: [PATCH 1287/1530] dm: add support for get_unique_id

This adds support to obtain a device's unique id through dm, similar to the
existing ioctl and persistent resevation handling.  We limit this to
single-target devices.

This enables knfsd to export pNFS SCSI luns that have been exported from
multipath devices.

Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/md/dm.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index adf0dde689475..12ecf07a38410 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -3343,6 +3343,59 @@ void dm_free_md_mempools(struct dm_md_mempools *pools)
 	kfree(pools);
 }
 
+struct dm_blkdev_id {
+	u8 *id;
+	enum blk_unique_id type;
+};
+
+static int __dm_get_unique_id(struct dm_target *ti, struct dm_dev *dev,
+				sector_t start, sector_t len, void *data)
+{
+	struct dm_blkdev_id *dm_id = data;
+	const struct block_device_operations *fops = dev->bdev->bd_disk->fops;
+
+	if (!fops->get_unique_id)
+		return 0;
+
+	return fops->get_unique_id(dev->bdev->bd_disk, dm_id->id, dm_id->type);
+}
+
+/*
+ * Allow access to get_unique_id() for the first device returning a
+ * non-zero result.  Reasonable use expects all devices to have the
+ * same unique id.
+ */
+static int dm_blk_get_unique_id(struct gendisk *disk, u8 *id,
+		enum blk_unique_id type)
+{
+	struct mapped_device *md = disk->private_data;
+	struct dm_table *table;
+	struct dm_target *ti;
+	int ret = 0, srcu_idx;
+
+	struct dm_blkdev_id dm_id = {
+		.id = id,
+		.type = type,
+	};
+
+	table = dm_get_live_table(md, &srcu_idx);
+	if (!table || !dm_table_get_size(table))
+		goto out;
+
+	/* We only support devices that have a single target */
+	if (table->num_targets != 1)
+		goto out;
+	ti = dm_table_get_target(table, 0);
+
+	if (!ti->type->iterate_devices)
+		goto out;
+
+	ret = ti->type->iterate_devices(ti, __dm_get_unique_id, &dm_id);
+out:
+	dm_put_live_table(md, srcu_idx);
+	return ret;
+}
+
 struct dm_pr {
 	u64	old_key;
 	u64	new_key;
@@ -3668,6 +3721,7 @@ static const struct block_device_operations dm_blk_dops = {
 	.ioctl = dm_blk_ioctl,
 	.getgeo = dm_blk_getgeo,
 	.report_zones = dm_blk_report_zones,
+	.get_unique_id = dm_blk_get_unique_id,
 	.pr_ops = &dm_pr_ops,
 	.owner = THIS_MODULE
 };
@@ -3677,6 +3731,7 @@ static const struct block_device_operations dm_rq_blk_dops = {
 	.release = dm_blk_close,
 	.ioctl = dm_blk_ioctl,
 	.getgeo = dm_blk_getgeo,
+	.get_unique_id = dm_blk_get_unique_id,
 	.pr_ops = &dm_pr_ops,
 	.owner = THIS_MODULE
 };

From e74fa2447bf9ed03d085b6d91f0256cc1b53f1a8 Mon Sep 17 00:00:00 2001
From: Yuan Can <yuancan@huawei.com>
Date: Wed, 6 Nov 2024 09:03:12 +0800
Subject: [PATCH 1288/1530] dm thin: Add missing destroy_work_on_stack()

This commit add missed destroy_work_on_stack() operations for pw->worker in
pool_work_wait().

Fixes: e7a3e871d895 ("dm thin: cleanup noflush_work to use a proper completion")
Cc: stable@vger.kernel.org
Signed-off-by: Yuan Can <yuancan@huawei.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-thin.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 89632ce977605..c9f47d0cccf9b 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2484,6 +2484,7 @@ static void pool_work_wait(struct pool_work *pw, struct pool *pool,
 	init_completion(&pw->complete);
 	queue_work(pool->wq, &pw->worker);
 	wait_for_completion(&pw->complete);
+	destroy_work_on_stack(&pw->worker);
 }
 
 /*----------------------------------------------------------------*/

From 61a57254a942705ca0a13d71a0b8387b299a65da Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Mon, 18 Nov 2024 16:14:27 +0100
Subject: [PATCH 1289/1530] dm-bufio: use kmalloc to allocate power-of-two
 sized buffers

Vlastimil Babka said [1] that kmalloc will return a power-of-two-aligned
buffer if it was called with a power-of-two size. So, we can use kmalloc
instead of our own slab cache in dm-bufio. Note that the code for the
slab cache was not removed because dm-bufio supports non-power-of-two
buffer sizes.

Link: https://lore.kernel.org/linux-mm/e7fca292-7c79-4f97-a90c-d68178d8ca59@suse.cz/ [1]

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-bufio.c | 25 ++++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 23e0b71b991e7..aab8240429b0b 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -318,9 +318,10 @@ static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *con
  */
 enum data_mode {
 	DATA_MODE_SLAB = 0,
-	DATA_MODE_GET_FREE_PAGES = 1,
-	DATA_MODE_VMALLOC = 2,
-	DATA_MODE_LIMIT = 3
+	DATA_MODE_KMALLOC = 1,
+	DATA_MODE_GET_FREE_PAGES = 2,
+	DATA_MODE_VMALLOC = 3,
+	DATA_MODE_LIMIT = 4
 };
 
 struct dm_buffer {
@@ -1062,6 +1063,7 @@ static unsigned long dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES;
 
 static unsigned long dm_bufio_peak_allocated;
 static unsigned long dm_bufio_allocated_kmem_cache;
+static unsigned long dm_bufio_allocated_kmalloc;
 static unsigned long dm_bufio_allocated_get_free_pages;
 static unsigned long dm_bufio_allocated_vmalloc;
 static unsigned long dm_bufio_current_allocated;
@@ -1104,6 +1106,7 @@ static void adjust_total_allocated(struct dm_buffer *b, bool unlink)
 
 	static unsigned long * const class_ptr[DATA_MODE_LIMIT] = {
 		&dm_bufio_allocated_kmem_cache,
+		&dm_bufio_allocated_kmalloc,
 		&dm_bufio_allocated_get_free_pages,
 		&dm_bufio_allocated_vmalloc,
 	};
@@ -1181,6 +1184,11 @@ static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask,
 		return kmem_cache_alloc(c->slab_cache, gfp_mask);
 	}
 
+	if (unlikely(c->block_size < PAGE_SIZE)) {
+		*data_mode = DATA_MODE_KMALLOC;
+		return kmalloc(c->block_size, gfp_mask | __GFP_RECLAIMABLE);
+	}
+
 	if (c->block_size <= KMALLOC_MAX_SIZE &&
 	    gfp_mask & __GFP_NORETRY) {
 		*data_mode = DATA_MODE_GET_FREE_PAGES;
@@ -1204,6 +1212,10 @@ static void free_buffer_data(struct dm_bufio_client *c,
 		kmem_cache_free(c->slab_cache, data);
 		break;
 
+	case DATA_MODE_KMALLOC:
+		kfree(data);
+		break;
+
 	case DATA_MODE_GET_FREE_PAGES:
 		free_pages((unsigned long)data,
 			   c->sectors_per_block_bits - (PAGE_SHIFT - SECTOR_SHIFT));
@@ -2519,8 +2531,7 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign
 		goto bad_dm_io;
 	}
 
-	if (block_size <= KMALLOC_MAX_SIZE &&
-	    (block_size < PAGE_SIZE || !is_power_of_2(block_size))) {
+	if (block_size <= KMALLOC_MAX_SIZE && !is_power_of_2(block_size)) {
 		unsigned int align = min(1U << __ffs(block_size), (unsigned int)PAGE_SIZE);
 
 		snprintf(slab_name, sizeof(slab_name), "dm_bufio_cache-%u-%u",
@@ -2902,6 +2913,7 @@ static int __init dm_bufio_init(void)
 	__u64 mem;
 
 	dm_bufio_allocated_kmem_cache = 0;
+	dm_bufio_allocated_kmalloc = 0;
 	dm_bufio_allocated_get_free_pages = 0;
 	dm_bufio_allocated_vmalloc = 0;
 	dm_bufio_current_allocated = 0;
@@ -2990,6 +3002,9 @@ MODULE_PARM_DESC(peak_allocated_bytes, "Tracks the maximum allocated memory");
 module_param_named(allocated_kmem_cache_bytes, dm_bufio_allocated_kmem_cache, ulong, 0444);
 MODULE_PARM_DESC(allocated_kmem_cache_bytes, "Memory allocated with kmem_cache_alloc");
 
+module_param_named(allocated_kmalloc_bytes, dm_bufio_allocated_kmalloc, ulong, 0444);
+MODULE_PARM_DESC(allocated_kmalloc_bytes, "Memory allocated with kmalloc_alloc");
+
 module_param_named(allocated_get_free_pages_bytes, dm_bufio_allocated_get_free_pages, ulong, 0444);
 MODULE_PARM_DESC(allocated_get_free_pages_bytes, "Memory allocated with get_free_pages");
 

From a573e404cbf269d46b3a96b18f7316aa57161fdf Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Mon, 18 Nov 2024 16:15:20 +0100
Subject: [PATCH 1290/1530] dm-verity: remove the unused "data_start" variable

Remove the unused "data_start" variable. It is always set to zero and the
user can't override it. If the user needs to use some existing offset
within a block device, it is possible to use the linear target.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-verity-target.c | 6 +++---
 drivers/md/dm-verity.h        | 1 -
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index c142ec5458b70..47d595f6a76e5 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -93,7 +93,7 @@ static void dm_bufio_alloc_callback(struct dm_buffer *buf)
  */
 static sector_t verity_map_sector(struct dm_verity *v, sector_t bi_sector)
 {
-	return v->data_start + dm_target_offset(v->ti, bi_sector);
+	return dm_target_offset(v->ti, bi_sector);
 }
 
 /*
@@ -952,7 +952,7 @@ static int verity_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
 
 	*bdev = v->data_dev->bdev;
 
-	if (v->data_start || ti->len != bdev_nr_sectors(v->data_dev->bdev))
+	if (ti->len != bdev_nr_sectors(v->data_dev->bdev))
 		return 1;
 	return 0;
 }
@@ -962,7 +962,7 @@ static int verity_iterate_devices(struct dm_target *ti,
 {
 	struct dm_verity *v = ti->private;
 
-	return fn(ti, v->data_dev, v->data_start, ti->len, data);
+	return fn(ti, v->data_dev, 0, ti->len, data);
 }
 
 static void verity_io_hints(struct dm_target *ti, struct queue_limits *limits)
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index c996140bda94d..8cbb57862ae19 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -50,7 +50,6 @@ struct dm_verity {
 	unsigned int sig_size;	/* root digest signature size */
 #endif /* CONFIG_SECURITY */
 	unsigned int salt_size;
-	sector_t data_start;	/* data offset in 512-byte sectors */
 	sector_t hash_start;	/* hash start in blocks */
 	sector_t data_blocks;	/* the number of data blocks */
 	sector_t hash_blocks;	/* the number of hash blocks */

From 9008fe8fad8255edfdbecea32d7eb0485d939d0d Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Wed, 20 Nov 2024 13:46:21 +0100
Subject: [PATCH 1291/1530] slab: Fix too strict alignment check in
 create_cache()

On m68k, where the minimum alignment of unsigned long is 2 bytes:

    Kernel panic - not syncing: __kmem_cache_create_args: Failed to create slab 'io_kiocb'. Error -22
    CPU: 0 UID: 0 PID: 1 Comm: swapper Not tainted 6.12.0-atari-03776-g7eaa1f99261a #1783
    Stack from 0102fe5c:
	    0102fe5c 00514a2b 00514a2b ffffff00 00000001 0051f5ed 00425e78 00514a2b
	    0041eb74 ffffffea 00000310 0051f5ed ffffffea ffffffea 00601f60 00000044
	    0102ff20 000e7a68 0051ab8e 004383b8 0051f5ed ffffffea 000000b8 00000007
	    01020c00 00000000 000e77f0 0041e5f0 005f67c0 0051f5ed 000000b6 0102fef4
	    00000310 0102fef4 00000000 00000016 005f676c 0060a34c 00000010 00000004
	    00000038 0000009a 01000000 000000b8 005f668e 0102e000 00001372 0102ff88
    Call Trace: [<00425e78>] dump_stack+0xc/0x10
     [<0041eb74>] panic+0xd8/0x26c
     [<000e7a68>] __kmem_cache_create_args+0x278/0x2e8
     [<000e77f0>] __kmem_cache_create_args+0x0/0x2e8
     [<0041e5f0>] memset+0x0/0x8c
     [<005f67c0>] io_uring_init+0x54/0xd2

The minimal alignment of an integral type may differ from its size,
hence is not safe to assume that an arbitrary freeptr_t (which is
basically an unsigned long) is always aligned to 4 or 8 bytes.

As nothing seems to require the additional alignment, it is safe to fix
this by relaxing the check to the actual minimum alignment of freeptr_t.

Fixes: aaa736b186239b7d ("io_uring: specify freeptr usage for SLAB_TYPESAFE_BY_RCU io_kiocb cache")
Fixes: d345bd2e9834e2da ("mm: add kmem_cache_create_rcu()")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Closes: https://lore.kernel.org/37c588d4-2c32-4aad-a19e-642961f200d7@roeck-us.net
Cc: <stable@vger.kernel.org>
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slab_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/slab_common.c b/mm/slab_common.c
index 62878edb0a81a..23a5d05e27c95 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -227,7 +227,7 @@ static struct kmem_cache *create_cache(const char *name,
 	if (args->use_freeptr_offset &&
 	    (args->freeptr_offset >= object_size ||
 	     !(flags & SLAB_TYPESAFE_BY_RCU) ||
-	     !IS_ALIGNED(args->freeptr_offset, sizeof(freeptr_t))))
+	     !IS_ALIGNED(args->freeptr_offset, __alignof__(freeptr_t))))
 		goto out;
 
 	err = -ENOMEM;

From 8af7a50167833b6b22e30c008bbf95ab3ff1a5fb Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 20 Nov 2024 18:59:16 +0100
Subject: [PATCH 1292/1530] rust: jump_label: skip formatting generated file
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After a source tree build of the kernel, and having used the `RSCPP`
rule, running `rustfmt` fails with:

    error: macros that expand to items must be delimited with braces or followed by a semicolon
     --> rust/kernel/arch_static_branch_asm.rs:1:27
      |
    1 | ...ls!("1: jmp " ... ".popsection \n\t")
      |       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
      |
    help: change the delimiters to curly braces
      |
    1 | ::kernel::concat_literals!{"1: jmp " ... ".popsection \n\t"}
      |                           ~                                ~
    help: add a semicolon
      |
    1 | ::kernel::concat_literals!("1: jmp " ... ".popsection \n\t");
      |                                                             +

This file is not meant to be formatted nor works on its own since it is
meant to be textually included.

Thus skip formatting it by prefixing its name with `generated_`.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Alex Gaynor <alex.gaynor@gmail.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Gary Guo <gary@garyguo.net>
Cc: Björn Roy Baron <bjorn3_gh@protonmail.com>
Cc: Benno Lossin <benno.lossin@proton.me>
Cc: Andreas Hindborg <a.hindborg@kernel.org>
Cc: Alice Ryhl <aliceryhl@google.com>
Cc: Trevor Gross <tmgross@umich.edu>
Link: https://lore.kernel.org/20241120175916.58860-1-ojeda@kernel.org
Fixes: 169484ab6677 ("rust: add arch_static_branch")
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 rust/Makefile                                                 | 4 ++--
 rust/kernel/.gitignore                                        | 2 +-
 ..._branch_asm.rs.S => generated_arch_static_branch_asm.rs.S} | 0
 rust/kernel/jump_label.rs                                     | 4 ++--
 4 files changed, 5 insertions(+), 5 deletions(-)
 rename rust/kernel/{arch_static_branch_asm.rs.S => generated_arch_static_branch_asm.rs.S} (100%)

diff --git a/rust/Makefile b/rust/Makefile
index bc2a9071dd293..99db963637e6c 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -36,7 +36,7 @@ always-$(CONFIG_RUST_KERNEL_DOCTESTS) += doctests_kernel_generated_kunit.c
 obj-$(CONFIG_RUST_KERNEL_DOCTESTS) += doctests_kernel_generated.o
 obj-$(CONFIG_RUST_KERNEL_DOCTESTS) += doctests_kernel_generated_kunit.o
 
-always-$(subst y,$(CONFIG_RUST),$(CONFIG_JUMP_LABEL)) += kernel/arch_static_branch_asm.rs
+always-$(subst y,$(CONFIG_RUST),$(CONFIG_JUMP_LABEL)) += kernel/generated_arch_static_branch_asm.rs
 
 # Avoids running `$(RUSTC)` for the sysroot when it may not be available.
 ifdef CONFIG_RUST
@@ -427,7 +427,7 @@ $(obj)/kernel.o: $(src)/kernel/lib.rs $(obj)/alloc.o $(obj)/build_error.o \
 	+$(call if_changed_rule,rustc_library)
 
 ifdef CONFIG_JUMP_LABEL
-$(obj)/kernel.o: $(obj)/kernel/arch_static_branch_asm.rs
+$(obj)/kernel.o: $(obj)/kernel/generated_arch_static_branch_asm.rs
 endif
 
 endif # CONFIG_RUST
diff --git a/rust/kernel/.gitignore b/rust/kernel/.gitignore
index d082731007c68..6ba39a178f309 100644
--- a/rust/kernel/.gitignore
+++ b/rust/kernel/.gitignore
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
 
-/arch_static_branch_asm.rs
+/generated_arch_static_branch_asm.rs
diff --git a/rust/kernel/arch_static_branch_asm.rs.S b/rust/kernel/generated_arch_static_branch_asm.rs.S
similarity index 100%
rename from rust/kernel/arch_static_branch_asm.rs.S
rename to rust/kernel/generated_arch_static_branch_asm.rs.S
diff --git a/rust/kernel/jump_label.rs b/rust/kernel/jump_label.rs
index b5aff632ecc73..4e974c768dbd5 100644
--- a/rust/kernel/jump_label.rs
+++ b/rust/kernel/jump_label.rs
@@ -39,7 +39,7 @@ pub use static_branch_unlikely;
 #[cfg(CONFIG_JUMP_LABEL)]
 const _: &str = include!(concat!(
     env!("OBJTREE"),
-    "/rust/kernel/arch_static_branch_asm.rs"
+    "/rust/kernel/generated_arch_static_branch_asm.rs"
 ));
 
 #[macro_export]
@@ -48,7 +48,7 @@ const _: &str = include!(concat!(
 macro_rules! arch_static_branch {
     ($key:path, $keytyp:ty, $field:ident, $branch:expr) => {'my_label: {
         $crate::asm!(
-            include!(concat!(env!("OBJTREE"), "/rust/kernel/arch_static_branch_asm.rs"));
+            include!(concat!(env!("OBJTREE"), "/rust/kernel/generated_arch_static_branch_asm.rs"));
             l_yes = label {
                 break 'my_label true;
             },

From d9db393f2b9ed674f965dd823c1692b41bad7bfb Mon Sep 17 00:00:00 2001
From: Luo Yifan <luoyifan@cmss.chinamobile.com>
Date: Tue, 12 Nov 2024 17:09:24 +0800
Subject: [PATCH 1293/1530] tools: PCI: Fix incorrect printf format specifiers

Fix several incorrect printf format specifiers that misused signed and
unsigned versions.

Link: https://lore.kernel.org/r/20241112090924.287056-1-luoyifan@cmss.chinamobile.com
Signed-off-by: Luo Yifan <luoyifan@cmss.chinamobile.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 tools/pci/pcitest.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c
index 470258009ddc2..7b530d838d408 100644
--- a/tools/pci/pcitest.c
+++ b/tools/pci/pcitest.c
@@ -95,7 +95,7 @@ static int run_test(struct pci_test *test)
 
 	if (test->msinum > 0 && test->msinum <= 32) {
 		ret = ioctl(fd, PCITEST_MSI, test->msinum);
-		fprintf(stdout, "MSI%d:\t\t", test->msinum);
+		fprintf(stdout, "MSI%u:\t\t", test->msinum);
 		if (ret < 0)
 			fprintf(stdout, "TEST FAILED\n");
 		else
@@ -104,7 +104,7 @@ static int run_test(struct pci_test *test)
 
 	if (test->msixnum > 0 && test->msixnum <= 2048) {
 		ret = ioctl(fd, PCITEST_MSIX, test->msixnum);
-		fprintf(stdout, "MSI-X%d:\t\t", test->msixnum);
+		fprintf(stdout, "MSI-X%u:\t\t", test->msixnum);
 		if (ret < 0)
 			fprintf(stdout, "TEST FAILED\n");
 		else
@@ -116,7 +116,7 @@ static int run_test(struct pci_test *test)
 		if (test->use_dma)
 			param.flags = PCITEST_FLAGS_USE_DMA;
 		ret = ioctl(fd, PCITEST_WRITE, &param);
-		fprintf(stdout, "WRITE (%7ld bytes):\t\t", test->size);
+		fprintf(stdout, "WRITE (%7lu bytes):\t\t", test->size);
 		if (ret < 0)
 			fprintf(stdout, "TEST FAILED\n");
 		else
@@ -128,7 +128,7 @@ static int run_test(struct pci_test *test)
 		if (test->use_dma)
 			param.flags = PCITEST_FLAGS_USE_DMA;
 		ret = ioctl(fd, PCITEST_READ, &param);
-		fprintf(stdout, "READ (%7ld bytes):\t\t", test->size);
+		fprintf(stdout, "READ (%7lu bytes):\t\t", test->size);
 		if (ret < 0)
 			fprintf(stdout, "TEST FAILED\n");
 		else
@@ -140,7 +140,7 @@ static int run_test(struct pci_test *test)
 		if (test->use_dma)
 			param.flags = PCITEST_FLAGS_USE_DMA;
 		ret = ioctl(fd, PCITEST_COPY, &param);
-		fprintf(stdout, "COPY (%7ld bytes):\t\t", test->size);
+		fprintf(stdout, "COPY (%7lu bytes):\t\t", test->size);
 		if (ret < 0)
 			fprintf(stdout, "TEST FAILED\n");
 		else

From 5bbed54ba66925ebca19092d0750630f943d7bf2 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 18 Nov 2024 11:27:07 +0200
Subject: [PATCH 1294/1530] gpio: zevio: Add missed label initialisation

Initialise the GPIO chip label correctly as it was done by
of_mm_gpiochip_add_data() before the below mentioned change.

Fixes: cf8f4462e5fa ("gpio: zevio: drop of_gpio.h header")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20241118092729.516736-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-zevio.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpio/gpio-zevio.c b/drivers/gpio/gpio-zevio.c
index 2de61337ad3b5..d7230fd83f5d6 100644
--- a/drivers/gpio/gpio-zevio.c
+++ b/drivers/gpio/gpio-zevio.c
@@ -11,6 +11,7 @@
 #include <linux/io.h>
 #include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
@@ -169,6 +170,7 @@ static const struct gpio_chip zevio_gpio_chip = {
 /* Initialization */
 static int zevio_gpio_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
 	struct zevio_gpio *controller;
 	int status, i;
 
@@ -180,6 +182,10 @@ static int zevio_gpio_probe(struct platform_device *pdev)
 	controller->chip = zevio_gpio_chip;
 	controller->chip.parent = &pdev->dev;
 
+	controller->chip.label = devm_kasprintf(dev, GFP_KERNEL, "%pfw", dev_fwnode(dev));
+	if (!controller->chip.label)
+		return -ENOMEM;
+
 	controller->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(controller->regs))
 		return dev_err_probe(&pdev->dev, PTR_ERR(controller->regs),

From c7899503ad9c06a0c6ee2796301139731cf1f5ab Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 18 Nov 2024 11:28:02 +0200
Subject: [PATCH 1295/1530] gpio: altera: Add missed base and label
 initialisations

During conversion driver to modern APIs the base field initial value
of the GPIO chip was moved from -1 to 0, which triggers a warning.
Add missed base initialisation as it was in the original code.

Initialise the GPIO chip label correctly as it was done by
of_mm_gpiochip_add_data() before the below mentioned change.

Fixes: 50dded8d9d62 ("gpio: altera: Drop legacy-of-mm-gpiochip.h header")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20241118095402.516989-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-altera.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c
index 039fef26546ec..73e660c5e38a1 100644
--- a/drivers/gpio/gpio-altera.c
+++ b/drivers/gpio/gpio-altera.c
@@ -261,6 +261,11 @@ static int altera_gpio_probe(struct platform_device *pdev)
 	altera_gc->gc.set		= altera_gpio_set;
 	altera_gc->gc.owner		= THIS_MODULE;
 	altera_gc->gc.parent		= &pdev->dev;
+	altera_gc->gc.base		= -1;
+
+	altera_gc->gc.label = devm_kasprintf(dev, GFP_KERNEL, "%pfw", dev_fwnode(dev));
+	if (!altera_gc->gc.label)
+		return -ENOMEM;
 
 	altera_gc->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(altera_gc->regs))

From 72cef64180de04a7b055b4773c138d78f4ebdb77 Mon Sep 17 00:00:00 2001
From: Sai Kumar Cholleti <skmr537@gmail.com>
Date: Tue, 5 Nov 2024 12:45:23 +0530
Subject: [PATCH 1296/1530] gpio: exar: set value when external pull-up or
 pull-down is present

Setting GPIO direction = high, sometimes results in GPIO value = 0.

If a GPIO is pulled high, the following construction results in the
value being 0 when the desired value is 1:

$ echo "high" > /sys/class/gpio/gpio336/direction
$ cat /sys/class/gpio/gpio336/value
0

Before the GPIO direction is changed from an input to an output,
exar_set_value() is called with value = 1, but since the GPIO is an
input when exar_set_value() is called, _regmap_update_bits() reads a 1
due to an external pull-up.  regmap_set_bits() sets force_write =
false, so the value (1) is not written.  When the direction is then
changed, the GPIO becomes an output with the value of 0 (the hardware
default).

regmap_write_bits() sets force_write = true, so the value is always
written by exar_set_value() and an external pull-up doesn't affect the
outcome of setting direction = high.

The same can happen when a GPIO is pulled low, but the scenario is a
little more complicated.

$ echo high > /sys/class/gpio/gpio351/direction
$ cat /sys/class/gpio/gpio351/value
1

$ echo in > /sys/class/gpio/gpio351/direction
$ cat /sys/class/gpio/gpio351/value
0

$ echo low > /sys/class/gpio/gpio351/direction
$ cat /sys/class/gpio/gpio351/value
1

Fixes: 36fb7218e878 ("gpio: exar: switch to using regmap")
Co-developed-by: Matthew McClain <mmcclain@noprivs.com>
Signed-off-by: Matthew McClain <mmcclain@noprivs.com>
Signed-off-by: Sai Kumar Cholleti <skmr537@gmail.com>
Cc: stable@vger.kernel.org
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20241105071523.2372032-1-skmr537@gmail.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-exar.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpio/gpio-exar.c b/drivers/gpio/gpio-exar.c
index 5170fe7599cdf..d5909a4f0433c 100644
--- a/drivers/gpio/gpio-exar.c
+++ b/drivers/gpio/gpio-exar.c
@@ -99,11 +99,13 @@ static void exar_set_value(struct gpio_chip *chip, unsigned int offset,
 	struct exar_gpio_chip *exar_gpio = gpiochip_get_data(chip);
 	unsigned int addr = exar_offset_to_lvl_addr(exar_gpio, offset);
 	unsigned int bit = exar_offset_to_bit(exar_gpio, offset);
+	unsigned int bit_value = value ? BIT(bit) : 0;
 
-	if (value)
-		regmap_set_bits(exar_gpio->regmap, addr, BIT(bit));
-	else
-		regmap_clear_bits(exar_gpio->regmap, addr, BIT(bit));
+	/*
+	 * regmap_write_bits() forces value to be written when an external
+	 * pull up/down might otherwise indicate value was already set.
+	 */
+	regmap_write_bits(exar_gpio->regmap, addr, BIT(bit), bit_value);
 }
 
 static int exar_direction_output(struct gpio_chip *chip, unsigned int offset,

From eb65540aa9fc828e9f3f8b30d6dc37f1ed35263d Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Fri, 15 Nov 2024 09:59:31 -0500
Subject: [PATCH 1297/1530] iomap: warn on zero range of a post-eof folio

iomap_zero_range() uses buffered writes for manual zeroing, no
longer updates i_size for such writes, but is still explicitly
called for post-eof ranges. The historical use case for this is
zeroing post-eof speculative preallocation on extending writes from
XFS. However, XFS also recently changed to convert all post-eof
delalloc mappings to unwritten in the iomap_begin() handler, which
means it now never expects manual zeroing of post-eof mappings. In
other words, all post-eof mappings should be reported as holes or
unwritten.

This is a subtle dependency that can be hard to detect if violated
because associated codepaths are likely to update i_size after folio
locks are dropped, but before writeback happens to occur. For
example, if XFS reverts back to some form of manual zeroing of
post-eof blocks on write extension, writeback of those zeroed folios
will now race with the presumed i_size update from the subsequent
buffered write.

Since iomap_zero_range() can't correctly zero post-eof mappings
beyond EOF without updating i_size, warn if this ever occurs. This
serves as minimal indication that if this use case is reintroduced
by a filesystem, iomap_zero_range() might need to reconsider i_size
updates for write extending use cases.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Link: https://lore.kernel.org/r/20241115145931.535207-1-bfoster@redhat.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/buffered-io.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index ce73d2a48c1eb..9ae71b9dafde2 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1397,6 +1397,8 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero,
 		if (iter->iomap.flags & IOMAP_F_STALE)
 			break;
 
+		/* warn about zeroing folios beyond eof that won't write back */
+		WARN_ON_ONCE(folio_pos(folio) > iter->inode->i_size);
 		offset = offset_in_folio(folio, pos);
 		if (bytes > folio_size(folio) - offset)
 			bytes = folio_size(folio) - offset;

From 2519369201f36a6b2571bc672c4e48f88c6b68d6 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Fri, 15 Nov 2024 15:01:53 -0500
Subject: [PATCH 1298/1530] iomap: reset per-iter state on non-error iter
 advances

iomap_iter_advance() zeroes the processed and mapping fields on
every non-error iteration except for the last expected iteration
(i.e. return 0 expected to terminate the iteration loop). This
appears to be circumstantial as nothing currently relies on these
fields after the final iteration.

Therefore to better faciliate iomap_iter reuse in subsequent
patches, update iomap_iter_advance() to always reset per-iteration
state on successful completion.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Link: https://lore.kernel.org/r/20241115200155.593665-2-bfoster@redhat.com
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/iter.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c
index 79a0614eaab77..3790918646af7 100644
--- a/fs/iomap/iter.c
+++ b/fs/iomap/iter.c
@@ -22,26 +22,25 @@
 static inline int iomap_iter_advance(struct iomap_iter *iter)
 {
 	bool stale = iter->iomap.flags & IOMAP_F_STALE;
+	int ret = 1;
 
 	/* handle the previous iteration (if any) */
 	if (iter->iomap.length) {
 		if (iter->processed < 0)
 			return iter->processed;
-		if (!iter->processed && !stale)
-			return 0;
 		if (WARN_ON_ONCE(iter->processed > iomap_length(iter)))
 			return -EIO;
 		iter->pos += iter->processed;
 		iter->len -= iter->processed;
-		if (!iter->len)
-			return 0;
+		if (!iter->len || (!iter->processed && !stale))
+			ret = 0;
 	}
 
-	/* clear the state for the next iteration */
+	/* clear the per iteration state */
 	iter->processed = 0;
 	memset(&iter->iomap, 0, sizeof(iter->iomap));
 	memset(&iter->srcmap, 0, sizeof(iter->srcmap));
-	return 1;
+	return ret;
 }
 
 static inline void iomap_iter_done(struct iomap_iter *iter)

From 889ac75787cbeb129df7faf917ce7d53a32ea696 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Fri, 15 Nov 2024 15:01:54 -0500
Subject: [PATCH 1299/1530] iomap: lift zeroed mapping handling into
 iomap_zero_range()

In preparation for special handling of subranges, lift the zeroed
mapping logic from the iterator into the caller. Since this puts the
pagecache dirty check and flushing in the same place, streamline the
comments a bit as well.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Link: https://lore.kernel.org/r/20241115200155.593665-3-bfoster@redhat.com
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/buffered-io.c | 66 +++++++++++++++---------------------------
 1 file changed, 24 insertions(+), 42 deletions(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 9ae71b9dafde2..cb5aa3cded0e5 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1350,40 +1350,12 @@ static inline int iomap_zero_iter_flush_and_stale(struct iomap_iter *i)
 	return filemap_write_and_wait_range(mapping, i->pos, end);
 }
 
-static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero,
-		bool *range_dirty)
+static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 {
-	const struct iomap *srcmap = iomap_iter_srcmap(iter);
 	loff_t pos = iter->pos;
 	loff_t length = iomap_length(iter);
 	loff_t written = 0;
 
-	/*
-	 * We must zero subranges of unwritten mappings that might be dirty in
-	 * pagecache from previous writes. We only know whether the entire range
-	 * was clean or not, however, and dirty folios may have been written
-	 * back or reclaimed at any point after mapping lookup.
-	 *
-	 * The easiest way to deal with this is to flush pagecache to trigger
-	 * any pending unwritten conversions and then grab the updated extents
-	 * from the fs. The flush may change the current mapping, so mark it
-	 * stale for the iterator to remap it for the next pass to handle
-	 * properly.
-	 *
-	 * Note that holes are treated the same as unwritten because zero range
-	 * is (ab)used for partial folio zeroing in some cases. Hole backed
-	 * post-eof ranges can be dirtied via mapped write and the flush
-	 * triggers writeback time post-eof zeroing.
-	 */
-	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) {
-		if (*range_dirty) {
-			*range_dirty = false;
-			return iomap_zero_iter_flush_and_stale(iter);
-		}
-		/* range is clean and already zeroed, nothing to do */
-		return length;
-	}
-
 	do {
 		struct folio *folio;
 		int status;
@@ -1435,24 +1407,34 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 	bool range_dirty;
 
 	/*
-	 * Zero range wants to skip pre-zeroed (i.e. unwritten) mappings, but
-	 * pagecache must be flushed to ensure stale data from previous
-	 * buffered writes is not exposed. A flush is only required for certain
-	 * types of mappings, but checking pagecache after mapping lookup is
-	 * racy with writeback and reclaim.
+	 * Zero range can skip mappings that are zero on disk so long as
+	 * pagecache is clean. If pagecache was dirty prior to zero range, the
+	 * mapping converts on writeback completion and so must be zeroed.
 	 *
-	 * Therefore, check the entire range first and pass along whether any
-	 * part of it is dirty. If so and an underlying mapping warrants it,
-	 * flush the cache at that point. This trades off the occasional false
-	 * positive (and spurious flush, if the dirty data and mapping don't
-	 * happen to overlap) for simplicity in handling a relatively uncommon
-	 * situation.
+	 * The simplest way to deal with this across a range is to flush
+	 * pagecache and process the updated mappings. To avoid an unconditional
+	 * flush, check pagecache state and only flush if dirty and the fs
+	 * returns a mapping that might convert on writeback.
 	 */
 	range_dirty = filemap_range_needs_writeback(inode->i_mapping,
 					pos, pos + len - 1);
+	while ((ret = iomap_iter(&iter, ops)) > 0) {
+		const struct iomap *srcmap = iomap_iter_srcmap(&iter);
 
-	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.processed = iomap_zero_iter(&iter, did_zero, &range_dirty);
+		if (srcmap->type == IOMAP_HOLE ||
+		    srcmap->type == IOMAP_UNWRITTEN) {
+			loff_t proc = iomap_length(&iter);
+
+			if (range_dirty) {
+				range_dirty = false;
+				proc = iomap_zero_iter_flush_and_stale(&iter);
+			}
+			iter.processed = proc;
+			continue;
+		}
+
+		iter.processed = iomap_zero_iter(&iter, did_zero);
+	}
 	return ret;
 }
 EXPORT_SYMBOL_GPL(iomap_zero_range);

From fde4c4c3ec1c1590eb09f97f9525fa7dd8df8343 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Fri, 15 Nov 2024 15:01:55 -0500
Subject: [PATCH 1300/1530] iomap: elide flush from partial eof zero range

iomap zero range flushes pagecache in certain situations to
determine which parts of the range might require zeroing if dirty
data is present in pagecache. The kernel robot recently reported a
regression associated with this flushing in the following stress-ng
workload on XFS:

stress-ng --timeout 60 --times --verify --metrics --no-rand-seed --metamix 64

This workload involves repeated small, strided, extending writes. On
XFS, this produces a pattern of post-eof speculative preallocation,
conversion of preallocation from delalloc to unwritten, dirtying
pagecache over newly unwritten blocks, and then rinse and repeat
from the new EOF. This leads to repetitive flushing of the EOF folio
via the zero range call XFS uses for writes that start beyond
current EOF.

To mitigate this problem, special case EOF block zeroing to prefer
zeroing the folio over a flush when the EOF folio is already dirty.
To do this, split out and open code handling of an unaligned start
offset. This brings most of the performance back by avoiding flushes
on zero range calls via write and truncate extension operations. The
flush doesn't occur in these situations because the entire range is
post-eof and therefore the folio that overlaps EOF is the only one
in the range.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Link: https://lore.kernel.org/r/20241115200155.593665-4-bfoster@redhat.com
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/buffered-io.c | 28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index cb5aa3cded0e5..0708be7767408 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1403,6 +1403,10 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 		.len		= len,
 		.flags		= IOMAP_ZERO,
 	};
+	struct address_space *mapping = inode->i_mapping;
+	unsigned int blocksize = i_blocksize(inode);
+	unsigned int off = pos & (blocksize - 1);
+	loff_t plen = min_t(loff_t, len, blocksize - off);
 	int ret;
 	bool range_dirty;
 
@@ -1412,12 +1416,28 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 	 * mapping converts on writeback completion and so must be zeroed.
 	 *
 	 * The simplest way to deal with this across a range is to flush
-	 * pagecache and process the updated mappings. To avoid an unconditional
-	 * flush, check pagecache state and only flush if dirty and the fs
-	 * returns a mapping that might convert on writeback.
+	 * pagecache and process the updated mappings. To avoid excessive
+	 * flushing on partial eof zeroing, special case it to zero the
+	 * unaligned start portion if already dirty in pagecache.
+	 */
+	if (off &&
+	    filemap_range_needs_writeback(mapping, pos, pos + plen - 1)) {
+		iter.len = plen;
+		while ((ret = iomap_iter(&iter, ops)) > 0)
+			iter.processed = iomap_zero_iter(&iter, did_zero);
+
+		iter.len = len - (iter.pos - pos);
+		if (ret || !iter.len)
+			return ret;
+	}
+
+	/*
+	 * To avoid an unconditional flush, check pagecache state and only flush
+	 * if dirty and the fs returns a mapping that might convert on
+	 * writeback.
 	 */
 	range_dirty = filemap_range_needs_writeback(inode->i_mapping,
-					pos, pos + len - 1);
+					iter.pos, iter.pos + iter.len - 1);
 	while ((ret = iomap_iter(&iter, ops)) > 0) {
 		const struct iomap *srcmap = iomap_iter_srcmap(&iter);
 

From a514e6f8f5caa24413731bed54b322bd34d918dd Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@toblux.com>
Date: Fri, 28 Jun 2024 08:23:30 +0200
Subject: [PATCH 1301/1530] fscache: Remove duplicate included header

Remove duplicate included header file linux/uio.h

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Thorsten Blum <thorsten.blum@toblux.com>
Link: https://lore.kernel.org/r/20240628062329.321162-2-thorsten.blum@toblux.com
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/fscache_io.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/netfs/fscache_io.c b/fs/netfs/fscache_io.c
index 38637e5c9b577..b1722a82c03d3 100644
--- a/fs/netfs/fscache_io.c
+++ b/fs/netfs/fscache_io.c
@@ -9,7 +9,6 @@
 #include <linux/uio.h>
 #include <linux/bvec.h>
 #include <linux/slab.h>
-#include <linux/uio.h>
 #include "internal.h"
 
 /**

From d18516a0218da360dd27ae204acbd8d1440f6d6b Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Wed, 20 Nov 2024 15:27:23 +0100
Subject: [PATCH 1302/1530] statmount: clean up unescaped option handling

Move common code from opt_array/opt_sec_array to helper.  This helper
does more than just unescape options, so rename to
statmount_opt_process().

Handle corner case of just a single character in options.

Rename some local variables to better describe their function.

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Link: https://lore.kernel.org/r/20241120142732.55210-1-mszeredi@redhat.com
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c | 44 +++++++++++++++++++-------------------------
 1 file changed, 19 insertions(+), 25 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index 6b0a17487d0f8..17563d8e382b1 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -5057,21 +5057,32 @@ static int statmount_mnt_opts(struct kstatmount *s, struct seq_file *seq)
 	return 0;
 }
 
-static inline int statmount_opt_unescape(struct seq_file *seq, char *buf_start)
+static inline int statmount_opt_process(struct seq_file *seq, size_t start)
 {
-	char *buf_end, *opt_start, *opt_end;
+	char *buf_end, *opt_end, *src, *dst;
 	int count = 0;
 
+	if (unlikely(seq_has_overflowed(seq)))
+		return -EAGAIN;
+
 	buf_end = seq->buf + seq->count;
+	dst = seq->buf + start;
+	src = dst + 1;	/* skip initial comma */
+
+	if (src >= buf_end) {
+		seq->count = start;
+		return 0;
+	}
+
 	*buf_end = '\0';
-	for (opt_start = buf_start + 1; opt_start < buf_end; opt_start = opt_end + 1) {
-		opt_end = strchrnul(opt_start, ',');
+	for (; src < buf_end; src = opt_end + 1) {
+		opt_end = strchrnul(src, ',');
 		*opt_end = '\0';
-		buf_start += string_unescape(opt_start, buf_start, 0, UNESCAPE_OCTAL) + 1;
+		dst += string_unescape(src, dst, 0, UNESCAPE_OCTAL) + 1;
 		if (WARN_ON_ONCE(++count == INT_MAX))
 			return -EOVERFLOW;
 	}
-	seq->count = buf_start - 1 - seq->buf;
+	seq->count = dst - 1 - seq->buf;
 	return count;
 }
 
@@ -5080,24 +5091,16 @@ static int statmount_opt_array(struct kstatmount *s, struct seq_file *seq)
 	struct vfsmount *mnt = s->mnt;
 	struct super_block *sb = mnt->mnt_sb;
 	size_t start = seq->count;
-	char *buf_start;
 	int err;
 
 	if (!sb->s_op->show_options)
 		return 0;
 
-	buf_start = seq->buf + start;
 	err = sb->s_op->show_options(seq, mnt->mnt_root);
 	if (err)
 		return err;
 
-	if (unlikely(seq_has_overflowed(seq)))
-		return -EAGAIN;
-
-	if (seq->count == start)
-		return 0;
-
-	err = statmount_opt_unescape(seq, buf_start);
+	err = statmount_opt_process(seq, start);
 	if (err < 0)
 		return err;
 
@@ -5110,22 +5113,13 @@ static int statmount_opt_sec_array(struct kstatmount *s, struct seq_file *seq)
 	struct vfsmount *mnt = s->mnt;
 	struct super_block *sb = mnt->mnt_sb;
 	size_t start = seq->count;
-	char *buf_start;
 	int err;
 
-	buf_start = seq->buf + start;
-
 	err = security_sb_show_options(seq, sb);
 	if (!err)
 		return err;
 
-	if (unlikely(seq_has_overflowed(seq)))
-		return -EAGAIN;
-
-	if (seq->count == start)
-		return 0;
-
-	err = statmount_opt_unescape(seq, buf_start);
+	err = statmount_opt_process(seq, start);
 	if (err < 0)
 		return err;
 

From 3e5360167ac3bccdc032cdafa68d4904a8fa0c75 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 20 Nov 2024 09:17:25 +0100
Subject: [PATCH 1303/1530] statmount: fix security option retrieval

Fix the inverted check for security_sb_show_options().

Link: https://lore.kernel.org/r/c8eaa647-5d67-49b6-9401-705afcb7e4d7@stanley.mountain
Link: https://lore.kernel.org/r/20241120-verehren-rhabarber-83a11b297bcc@brauner
Fixes: aefff51e1c29 ("statmount: retrieve security mount options")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Cc: stable@vger.kernel.org # mainline only
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index 17563d8e382b1..23e81c2a1e3fe 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -5116,7 +5116,7 @@ static int statmount_opt_sec_array(struct kstatmount *s, struct seq_file *seq)
 	int err;
 
 	err = security_sb_show_options(seq, sb);
-	if (!err)
+	if (err)
 		return err;
 
 	err = statmount_opt_process(seq, start);

From 9e141955ede223d82251a59644ff9448a5aba580 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@mandelbit.com>
Date: Fri, 15 Nov 2024 23:02:02 +0100
Subject: [PATCH 1304/1530] spi-imx: prevent overflow when estimating transfer
 time

The words delay is computed by multiplying two unsigned ints
and by adding up the result to a u64 variable.

The multiplication, however, is performed with 32bit math
thus losing data when the actual result is larger than UINT32_MAX.

Fix the operation by casting the first operand to u64, thus forcing
the multiplication to be performed with 64bit math.

This fixes 1 OVERFLOW_BEFORE_WIDEN issue reported by Coverity
Report: CID 1601859:  Integer handling issues  (OVERFLOW_BEFORE_WIDEN)

Cc: Mark Brown <broonie@kernel.org>
Cc: Shawn Guo <shawnguo@kernel.org>
Cc: Sascha Hauer <s.hauer@pengutronix.de>
Cc: Pengutronix Kernel Team <kernel@pengutronix.de>
Cc: Fabio Estevam <festevam@gmail.com>
Cc: imx@lists.linux.dev
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Antonio Quartulli <antonio@mandelbit.com>
Link: https://patch.msgid.link/20241115220202.31086-1-antonio@mandelbit.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-imx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 0b6b0151b3a3f..eeb7d082c2472 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -1685,7 +1685,7 @@ static unsigned int spi_imx_transfer_estimate_time_us(struct spi_transfer *trans
 		words = DIV_ROUND_UP(transfer->len * BITS_PER_BYTE, transfer->bits_per_word);
 		word_delay_us = DIV_ROUND_CLOSEST(spi_delay_to_ns(&transfer->word_delay, transfer),
 						  NSEC_PER_USEC);
-		result += words * word_delay_us;
+		result += (u64)words * word_delay_us;
 	}
 
 	return min(result, U32_MAX);

From 351f2bfe6362c663f45f5c6111f14365cfd094ab Mon Sep 17 00:00:00 2001
From: "Kory Maincent (Dent Project)" <kory.maincent@bootlin.com>
Date: Thu, 21 Nov 2024 15:42:28 +0100
Subject: [PATCH 1305/1530] regulator: core: Ignore unset max_uA constraints in
 current limit check

We should only consider max_uA constraints if they are explicitly defined.
In cases where it is not set, we should assume the regulator has no current
limit.

Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://patch.msgid.link/20241121-feature_poe_port_prio-v3-2-83299fa6967c@bootlin.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 84d48e310aa86..8cb948a91e60d 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -497,7 +497,8 @@ static int regulator_check_current_limit(struct regulator_dev *rdev,
 		return -EPERM;
 	}
 
-	if (*max_uA > rdev->constraints->max_uA)
+	if (*max_uA > rdev->constraints->max_uA &&
+	    rdev->constraints->max_uA)
 		*max_uA = rdev->constraints->max_uA;
 	if (*min_uA < rdev->constraints->min_uA)
 		*min_uA = rdev->constraints->min_uA;

From 7582fe07f4ca4c560eb47800b640997f06a8baa2 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Fri, 25 Oct 2024 13:24:51 +0530
Subject: [PATCH 1306/1530] PCI/pwrctl: Use of_platform_device_create() to
 create pwrctl devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The of_platform_populate() API creates platform devices by descending
through the children of the parent node. But it provides no control over
the child nodes, which makes it difficult to add checks for the child
nodes in the future.

Use of_platform_device_create() and for_each_child_of_node_scoped() to make
it possible to add checks for each node before creating the platform
device.

Link: https://lore.kernel.org/r/20241025-pci-pwrctl-rework-v2-1-568756156cbe@linaro.org
Tested-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Tested-by: Krishna chaitanya chundru <quic_krichai@quicinc.com>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/pci/bus.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 55c8536860518..9d278d3a19ff5 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -13,6 +13,7 @@
 #include <linux/ioport.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/proc_fs.h>
 #include <linux/slab.h>
 
@@ -329,6 +330,7 @@ void __weak pcibios_bus_add_device(struct pci_dev *pdev) { }
 void pci_bus_add_device(struct pci_dev *dev)
 {
 	struct device_node *dn = dev->dev.of_node;
+	struct platform_device *pdev;
 	int retval;
 
 	/*
@@ -351,11 +353,11 @@ void pci_bus_add_device(struct pci_dev *dev)
 	pci_dev_assign_added(dev, true);
 
 	if (dev_of_node(&dev->dev) && pci_is_bridge(dev)) {
-		retval = of_platform_populate(dev_of_node(&dev->dev), NULL, NULL,
-					      &dev->dev);
-		if (retval)
-			pci_err(dev, "failed to populate child OF nodes (%d)\n",
-				retval);
+		for_each_available_child_of_node_scoped(dn, child) {
+			pdev = of_platform_device_create(child, NULL, &dev->dev);
+			if (!pdev)
+				pci_err(dev, "failed to create OF node: %s\n", child->name);
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(pci_bus_add_device);

From 278dd091e95d428eea0a2c3c517d895b052de5ff Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Fri, 25 Oct 2024 13:24:52 +0530
Subject: [PATCH 1307/1530] PCI/pwrctl: Create pwrctl device only if at least
 one power supply is present
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, pwrctl devices are created if the corresponding PCI nodes are
defined in devicetree. But this is not correct, because not all PCI nodes
require pwrctl support. Pwrctl comes into the picture only when the device
requires kernel to manage its power state. This can be determined using the
power supply properties present in the devicetree node of the device.

Add of_pci_supply_present() to check whether the devicetree contains at
least one power supply property for a device. If one is present, create a
pwrctl device for that PCI node.

Suggested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Fixes: 8fb18619d910 ("PCI/pwrctl: Create platform devices for child OF nodes of the port node")
Link: https://lore.kernel.org/r/20241025-pci-pwrctl-rework-v2-2-568756156cbe@linaro.org
Tested-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Tested-by: Krishna chaitanya chundru <quic_krichai@quicinc.com>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
[bhelgaas: rename of_pci_is_supply_present() to of_pci_supply_present() for
readability]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Cc: stable+noautosel@kernel.org		# Depends on of_platform_device_create() rework
---
 drivers/pci/bus.c | 11 +++++++++++
 drivers/pci/of.c  | 27 +++++++++++++++++++++++++++
 drivers/pci/pci.h |  5 +++++
 3 files changed, 43 insertions(+)

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 9d278d3a19ff5..93bc421701225 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -354,6 +354,17 @@ void pci_bus_add_device(struct pci_dev *dev)
 
 	if (dev_of_node(&dev->dev) && pci_is_bridge(dev)) {
 		for_each_available_child_of_node_scoped(dn, child) {
+			/*
+			 * First check whether the pwrctl device needs to be
+			 * created or not. This is decided based on at least
+			 * one of the power supplies being defined in the
+			 * devicetree node of the device.
+			 */
+			if (!of_pci_supply_present(child)) {
+				pci_dbg(dev, "skipping OF node: %s\n", child->name);
+				continue;
+			}
+
 			pdev = of_platform_device_create(child, NULL, &dev->dev);
 			if (!pdev)
 				pci_err(dev, "failed to create OF node: %s\n", child->name);
diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index dacea3fc5128f..52f770bcc4819 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -728,6 +728,33 @@ void of_pci_make_dev_node(struct pci_dev *pdev)
 }
 #endif
 
+/**
+ * of_pci_supply_present() - Check if the power supply is present for the PCI
+ *				device
+ * @np: Device tree node
+ *
+ * Check if the power supply for the PCI device is present in the device tree
+ * node or not.
+ *
+ * Return: true if at least one power supply exists; false otherwise.
+ */
+bool of_pci_supply_present(struct device_node *np)
+{
+	struct property *prop;
+	char *supply;
+
+	if (!np)
+		return false;
+
+	for_each_property_of_node(np, prop) {
+		supply = strrchr(prop->name, '-');
+		if (supply && !strcmp(supply, "-supply"))
+			return true;
+	}
+
+	return false;
+}
+
 #endif /* CONFIG_PCI */
 
 /**
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 14d00ce45bfa9..64c6ca6de8029 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -746,6 +746,7 @@ void pci_set_bus_of_node(struct pci_bus *bus);
 void pci_release_bus_of_node(struct pci_bus *bus);
 
 int devm_of_pci_bridge_init(struct device *dev, struct pci_host_bridge *bridge);
+bool of_pci_supply_present(struct device_node *np);
 
 #else
 static inline int
@@ -793,6 +794,10 @@ static inline int devm_of_pci_bridge_init(struct device *dev, struct pci_host_br
 	return 0;
 }
 
+static inline bool of_pci_supply_present(struct device_node *np)
+{
+	return false;
+}
 #endif /* CONFIG_OF */
 
 struct of_changeset;

From b458ff7e8176523b9d5a8d33f2487f29d7096eb1 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Fri, 25 Oct 2024 13:24:53 +0530
Subject: [PATCH 1308/1530] PCI/pwrctl: Ensure that pwrctl drivers are probed
 before PCI client drivers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As per the kernel device driver model, a pwrctl device is the supplier for
the PCI device, but the device link that enforces the supplier-consumer
relationship was previously created by the pwrctl driver. Therefore, the
driver model didn't prevent probing PCI client drivers before probing the
corresponding pwrctl drivers. This may lead to a race condition if the PCI
device was already powered on by the bootloader (before the pwrctl driver).

If the bootloader did not power on the PCI device, this wouldn't create any
problem as the pwrctl driver will be the one powering on the device, so the
PCI client driver always gets probed afterward. But if the device was
already powered on, then the device will be seen by the PCI core and the
PCI client driver may get probed before its pwrctl driver. This creates a
race condition as the pwrctl driver may change the device power state while
the device is being accessed by the client driver.

One such issue was already reported on the Qcom X13s platform with the WLAN
device and fixed with a hack in the WCN pwrseq driver by a9aaf1ff88a8
("power: sequencing: request the WLAN enable GPIO as-is").

A cleaner way to fix the above mentioned race condition is to ensure that
the pwrctl drivers are always probed before the client drivers.

If the PCI device is associated with a pwrctl platform device with a power
supply, add a device link between the PCI device and the pwrctl device
before device_attach() in pci_bus_add_device().

Note that there is no need to explicitly remove the device link as that
will be taken care of by the driver core when the PCI device gets removed.

Fixes: 4565d2652a37 ("PCI/pwrctl: Add PCI power control core code")
Fixes: 8fb18619d910 ("PCI/pwrctl: Create platform devices for child OF nodes of the port node")
Link: https://lore.kernel.org/r/20241025-pci-pwrctl-rework-v2-3-568756156cbe@linaro.org
Tested-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Tested-by: Krishna chaitanya chundru <quic_krichai@quicinc.com>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
[bhelgaas: squash fix from
https://lore.kernel.org/r/20241120062459.6371-1-manivannan.sadhasivam@linaro.org
for SPARCv9 issue reported by Jonathan Currier <dullfire@yahoo.com>]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
[kwilczynski: wrap code to 80 columns]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Cc: stable+noautosel@kernel.org		# Depends on power supply check
---
 drivers/pci/bus.c         | 75 +++++++++++++++++++++++++++++----------
 drivers/pci/pwrctl/core.c | 10 ------
 2 files changed, 56 insertions(+), 29 deletions(-)

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 93bc421701225..90d775601789c 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -321,6 +321,46 @@ void __weak pcibios_resource_survey_bus(struct pci_bus *bus) { }
 
 void __weak pcibios_bus_add_device(struct pci_dev *pdev) { }
 
+/*
+ * Create pwrctl devices (if required) for the PCI devices to handle the power
+ * state.
+ */
+static void pci_pwrctl_create_devices(struct pci_dev *dev)
+{
+	struct device_node *np = dev_of_node(&dev->dev);
+	struct device *parent = &dev->dev;
+	struct platform_device *pdev;
+
+	/*
+	 * First ensure that we are starting from a PCI bridge and it has a
+	 * corresponding devicetree node.
+	 */
+	if (np && pci_is_bridge(dev)) {
+		/*
+		 * Now look for the child PCI device nodes and create pwrctl
+		 * devices for them. The pwrctl device drivers will manage the
+		 * power state of the devices.
+		 */
+		for_each_available_child_of_node_scoped(np, child) {
+			/*
+			 * First check whether the pwrctl device really needs to
+			 * be created or not. This is decided based on at least
+			 * one of the power supplies being defined in the
+			 * devicetree node of the device.
+			 */
+			if (!of_pci_supply_present(child)) {
+				pci_dbg(dev, "skipping OF node: %s\n", child->name);
+				return;
+			}
+
+			/* Now create the pwrctl device */
+			pdev = of_platform_device_create(child, NULL, parent);
+			if (!pdev)
+				pci_err(dev, "failed to create OF node: %s\n", child->name);
+		}
+	}
+}
+
 /**
  * pci_bus_add_device - start driver for a single device
  * @dev: device to add
@@ -345,31 +385,28 @@ void pci_bus_add_device(struct pci_dev *dev)
 	pci_proc_attach_device(dev);
 	pci_bridge_d3_update(dev);
 
+	pci_pwrctl_create_devices(dev);
+
+	/*
+	 * If the PCI device is associated with a pwrctl device with a
+	 * power supply, create a device link between the PCI device and
+	 * pwrctl device.  This ensures that pwrctl drivers are probed
+	 * before PCI client drivers.
+	 */
+	pdev = of_find_device_by_node(dn);
+	if (pdev && of_pci_supply_present(dn)) {
+		if (!device_link_add(&dev->dev, &pdev->dev,
+				     DL_FLAG_AUTOREMOVE_CONSUMER))
+			pci_err(dev, "failed to add device link to power control device %s\n",
+				pdev->name);
+	}
+
 	dev->match_driver = !dn || of_device_is_available(dn);
 	retval = device_attach(&dev->dev);
 	if (retval < 0 && retval != -EPROBE_DEFER)
 		pci_warn(dev, "device attach failed (%d)\n", retval);
 
 	pci_dev_assign_added(dev, true);
-
-	if (dev_of_node(&dev->dev) && pci_is_bridge(dev)) {
-		for_each_available_child_of_node_scoped(dn, child) {
-			/*
-			 * First check whether the pwrctl device needs to be
-			 * created or not. This is decided based on at least
-			 * one of the power supplies being defined in the
-			 * devicetree node of the device.
-			 */
-			if (!of_pci_supply_present(child)) {
-				pci_dbg(dev, "skipping OF node: %s\n", child->name);
-				continue;
-			}
-
-			pdev = of_platform_device_create(child, NULL, &dev->dev);
-			if (!pdev)
-				pci_err(dev, "failed to create OF node: %s\n", child->name);
-		}
-	}
 }
 EXPORT_SYMBOL_GPL(pci_bus_add_device);
 
diff --git a/drivers/pci/pwrctl/core.c b/drivers/pci/pwrctl/core.c
index 01d913b603160..bb5a237124341 100644
--- a/drivers/pci/pwrctl/core.c
+++ b/drivers/pci/pwrctl/core.c
@@ -33,16 +33,6 @@ static int pci_pwrctl_notify(struct notifier_block *nb, unsigned long action,
 		 */
 		dev->of_node_reused = true;
 		break;
-	case BUS_NOTIFY_BOUND_DRIVER:
-		pwrctl->link = device_link_add(dev, pwrctl->dev,
-					       DL_FLAG_AUTOREMOVE_CONSUMER);
-		if (!pwrctl->link)
-			dev_err(pwrctl->dev, "Failed to add device link\n");
-		break;
-	case BUS_NOTIFY_UNBOUND_DRIVER:
-		if (pwrctl->link)
-			device_link_remove(dev, pwrctl->dev);
-		break;
 	}
 
 	return NOTIFY_DONE;

From 681725afb6b91dfa581f4eba5f256ac5e953b463 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Fri, 25 Oct 2024 13:24:55 +0530
Subject: [PATCH 1309/1530] PCI/pwrctl: Remove pwrctl device without iterating
 over all children of pwrctl parent
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is no need to iterate over all children of the pwrctl device parent
to remove the pwrctl device. Since the pwrctl device associated with the
PCI device can be found using of_find_device_by_node() API, use it directly
instead.

Any pwrctl devices lying around without getting associated with the PCI
devices will be removed once their parent device gets removed.

Link: https://lore.kernel.org/r/20241025-pci-pwrctl-rework-v2-5-568756156cbe@linaro.org
Tested-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Tested-by: Krishna chaitanya chundru <quic_krichai@quicinc.com>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
[bhelgaas: commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/pci/remove.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index e4ce1145aa3ee..3dd9b3024956a 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -17,16 +17,16 @@ static void pci_free_resources(struct pci_dev *dev)
 	}
 }
 
-static int pci_pwrctl_unregister(struct device *dev, void *data)
+static void pci_pwrctl_unregister(struct device *dev)
 {
-	struct device_node *pci_node = data, *plat_node = dev_of_node(dev);
+	struct platform_device *pdev;
 
-	if (dev_is_platform(dev) && plat_node && plat_node == pci_node) {
-		of_device_unregister(to_platform_device(dev));
-		of_node_clear_flag(plat_node, OF_POPULATED);
-	}
+	pdev = of_find_device_by_node(dev_of_node(dev));
+	if (!pdev)
+		return;
 
-	return 0;
+	of_device_unregister(pdev);
+	of_node_clear_flag(dev_of_node(dev), OF_POPULATED);
 }
 
 static void pci_stop_dev(struct pci_dev *dev)
@@ -34,8 +34,7 @@ static void pci_stop_dev(struct pci_dev *dev)
 	pci_pme_active(dev, false);
 
 	if (pci_dev_is_added(dev)) {
-		device_for_each_child(dev->dev.parent, dev_of_node(&dev->dev),
-				      pci_pwrctl_unregister);
+		pci_pwrctl_unregister(&dev->dev);
 		device_release_driver(&dev->dev);
 		pci_proc_detach_device(dev);
 		pci_remove_sysfs_dev_files(dev);

From b88cbaaa6fa109c2eb455d8fe2a318de0d197ea2 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 15 Nov 2024 15:44:27 -0600
Subject: [PATCH 1310/1530] PCI/pwrctrl: Rename pwrctl files to pwrctrl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To slightly reduce confusion between "pwrctl" (the power controller and
power sequencing framework) and "bwctrl" (the bandwidth controller),
rename "pwrctl" to "pwrctrl" so they use the same "ctrl" suffix.

Rename drivers/pci/pwrctl/ to drivers/pci/pwrctrl/, including the related
MAINTAINERS, include file (include/linux/pci-pwrctl.h), Makefile, and
Kconfig changes.

This is the minimal rename of files only.  A subsequent commit will rename
functions and data structures.

Link: https://lore.kernel.org/r/20241115214428.2061153-2-helgaas@kernel.org
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Acked-by: Krzysztof Wilczyński <kw@linux.com>
---
 MAINTAINERS                                                 | 4 ++--
 drivers/pci/Kconfig                                         | 2 +-
 drivers/pci/Makefile                                        | 2 +-
 drivers/pci/pwrctl/Makefile                                 | 6 ------
 drivers/pci/{pwrctl => pwrctrl}/Kconfig                     | 0
 drivers/pci/pwrctrl/Makefile                                | 6 ++++++
 drivers/pci/{pwrctl => pwrctrl}/core.c                      | 2 +-
 .../pci-pwrctl-pwrseq.c => pwrctrl/pci-pwrctrl-pwrseq.c}    | 2 +-
 include/linux/{pci-pwrctl.h => pci-pwrctrl.h}               | 0
 9 files changed, 12 insertions(+), 12 deletions(-)
 delete mode 100644 drivers/pci/pwrctl/Makefile
 rename drivers/pci/{pwrctl => pwrctrl}/Kconfig (100%)
 create mode 100644 drivers/pci/pwrctrl/Makefile
 rename drivers/pci/{pwrctl => pwrctrl}/core.c (99%)
 rename drivers/pci/{pwrctl/pci-pwrctl-pwrseq.c => pwrctrl/pci-pwrctrl-pwrseq.c} (98%)
 rename include/linux/{pci-pwrctl.h => pci-pwrctrl.h} (100%)

diff --git a/MAINTAINERS b/MAINTAINERS
index c27f3190737f8..1a6096135424c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17910,8 +17910,8 @@ M:	Bartosz Golaszewski <brgl@bgdev.pl>
 L:	linux-pci@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git
-F:	drivers/pci/pwrctl/*
-F:	include/linux/pci-pwrctl.h
+F:	drivers/pci/pwrctrl/*
+F:	include/linux/pci-pwrctrl.h
 
 PCI SUBSYSTEM
 M:	Bjorn Helgaas <bhelgaas@google.com>
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 0d94e4a967d81..e1c025698a283 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -305,6 +305,6 @@ source "drivers/pci/hotplug/Kconfig"
 source "drivers/pci/controller/Kconfig"
 source "drivers/pci/endpoint/Kconfig"
 source "drivers/pci/switch/Kconfig"
-source "drivers/pci/pwrctl/Kconfig"
+source "drivers/pci/pwrctrl/Kconfig"
 
 endif
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 374c5c06d92f9..39a07890abd12 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_PCI)		+= access.o bus.o probe.o host-bridge.o \
 
 obj-$(CONFIG_PCI)		+= msi/
 obj-$(CONFIG_PCI)		+= pcie/
-obj-$(CONFIG_PCI)		+= pwrctl/
+obj-$(CONFIG_PCI)		+= pwrctrl/
 
 ifdef CONFIG_PCI
 obj-$(CONFIG_PROC_FS)		+= proc.o
diff --git a/drivers/pci/pwrctl/Makefile b/drivers/pci/pwrctl/Makefile
deleted file mode 100644
index d308aae4800cd..0000000000000
--- a/drivers/pci/pwrctl/Makefile
+++ /dev/null
@@ -1,6 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-
-obj-$(CONFIG_PCI_PWRCTL)		+= pci-pwrctl-core.o
-pci-pwrctl-core-y			:= core.o
-
-obj-$(CONFIG_PCI_PWRCTL_PWRSEQ)		+= pci-pwrctl-pwrseq.o
diff --git a/drivers/pci/pwrctl/Kconfig b/drivers/pci/pwrctrl/Kconfig
similarity index 100%
rename from drivers/pci/pwrctl/Kconfig
rename to drivers/pci/pwrctrl/Kconfig
diff --git a/drivers/pci/pwrctrl/Makefile b/drivers/pci/pwrctrl/Makefile
new file mode 100644
index 0000000000000..75c7ce531c7e2
--- /dev/null
+++ b/drivers/pci/pwrctrl/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_PCI_PWRCTL)		+= pci-pwrctrl-core.o
+pci-pwrctrl-core-y			:= core.o
+
+obj-$(CONFIG_PCI_PWRCTL_PWRSEQ)		+= pci-pwrctrl-pwrseq.o
diff --git a/drivers/pci/pwrctl/core.c b/drivers/pci/pwrctrl/core.c
similarity index 99%
rename from drivers/pci/pwrctl/core.c
rename to drivers/pci/pwrctrl/core.c
index bb5a237124341..88f06e9271bac 100644
--- a/drivers/pci/pwrctl/core.c
+++ b/drivers/pci/pwrctrl/core.c
@@ -7,7 +7,7 @@
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/pci.h>
-#include <linux/pci-pwrctl.h>
+#include <linux/pci-pwrctrl.h>
 #include <linux/property.h>
 #include <linux/slab.h>
 
diff --git a/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c b/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c
similarity index 98%
rename from drivers/pci/pwrctl/pci-pwrctl-pwrseq.c
rename to drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c
index a23a4312574b9..cc19ad61dd6e8 100644
--- a/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c
+++ b/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c
@@ -7,7 +7,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/pci-pwrctl.h>
+#include <linux/pci-pwrctrl.h>
 #include <linux/platform_device.h>
 #include <linux/pwrseq/consumer.h>
 #include <linux/slab.h>
diff --git a/include/linux/pci-pwrctl.h b/include/linux/pci-pwrctrl.h
similarity index 100%
rename from include/linux/pci-pwrctl.h
rename to include/linux/pci-pwrctrl.h

From 3f925cd6287401bbc9d568f56d796a69c8bd292a Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 15 Nov 2024 15:44:28 -0600
Subject: [PATCH 1311/1530] PCI/pwrctrl: Rename pwrctrl functions and
 structures
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rename pwrctrl functions and structures from "pwrctl" to "pwrctrl" to match
the similar file renames.

Link: https://lore.kernel.org/r/20241115214428.2061153-3-helgaas@kernel.org
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Acked-by: Krzysztof Wilczyński <kw@linux.com>
---
 drivers/pci/bus.c                        | 25 ++++----
 drivers/pci/pwrctrl/core.c               | 77 ++++++++++++------------
 drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c | 32 +++++-----
 drivers/pci/remove.c                     |  4 +-
 include/linux/pci-pwrctrl.h              | 22 +++----
 5 files changed, 81 insertions(+), 79 deletions(-)

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 90d775601789c..0d27809746df0 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -322,10 +322,10 @@ void __weak pcibios_resource_survey_bus(struct pci_bus *bus) { }
 void __weak pcibios_bus_add_device(struct pci_dev *pdev) { }
 
 /*
- * Create pwrctl devices (if required) for the PCI devices to handle the power
+ * Create pwrctrl devices (if required) for the PCI devices to handle the power
  * state.
  */
-static void pci_pwrctl_create_devices(struct pci_dev *dev)
+static void pci_pwrctrl_create_devices(struct pci_dev *dev)
 {
 	struct device_node *np = dev_of_node(&dev->dev);
 	struct device *parent = &dev->dev;
@@ -337,23 +337,24 @@ static void pci_pwrctl_create_devices(struct pci_dev *dev)
 	 */
 	if (np && pci_is_bridge(dev)) {
 		/*
-		 * Now look for the child PCI device nodes and create pwrctl
-		 * devices for them. The pwrctl device drivers will manage the
+		 * Now look for the child PCI device nodes and create pwrctrl
+		 * devices for them. The pwrctrl device drivers will manage the
 		 * power state of the devices.
 		 */
 		for_each_available_child_of_node_scoped(np, child) {
 			/*
-			 * First check whether the pwrctl device really needs to
-			 * be created or not. This is decided based on at least
-			 * one of the power supplies being defined in the
-			 * devicetree node of the device.
+			 * First check whether the pwrctrl device really
+			 * needs to be created or not. This is decided
+			 * based on at least one of the power supplies
+			 * being defined in the devicetree node of the
+			 * device.
 			 */
 			if (!of_pci_supply_present(child)) {
 				pci_dbg(dev, "skipping OF node: %s\n", child->name);
 				return;
 			}
 
-			/* Now create the pwrctl device */
+			/* Now create the pwrctrl device */
 			pdev = of_platform_device_create(child, NULL, parent);
 			if (!pdev)
 				pci_err(dev, "failed to create OF node: %s\n", child->name);
@@ -385,12 +386,12 @@ void pci_bus_add_device(struct pci_dev *dev)
 	pci_proc_attach_device(dev);
 	pci_bridge_d3_update(dev);
 
-	pci_pwrctl_create_devices(dev);
+	pci_pwrctrl_create_devices(dev);
 
 	/*
-	 * If the PCI device is associated with a pwrctl device with a
+	 * If the PCI device is associated with a pwrctrl device with a
 	 * power supply, create a device link between the PCI device and
-	 * pwrctl device.  This ensures that pwrctl drivers are probed
+	 * pwrctrl device.  This ensures that pwrctrl drivers are probed
 	 * before PCI client drivers.
 	 */
 	pdev = of_find_device_by_node(dn);
diff --git a/drivers/pci/pwrctrl/core.c b/drivers/pci/pwrctrl/core.c
index 88f06e9271bac..2fb174db91e58 100644
--- a/drivers/pci/pwrctrl/core.c
+++ b/drivers/pci/pwrctrl/core.c
@@ -11,13 +11,13 @@
 #include <linux/property.h>
 #include <linux/slab.h>
 
-static int pci_pwrctl_notify(struct notifier_block *nb, unsigned long action,
-			     void *data)
+static int pci_pwrctrl_notify(struct notifier_block *nb, unsigned long action,
+			      void *data)
 {
-	struct pci_pwrctl *pwrctl = container_of(nb, struct pci_pwrctl, nb);
+	struct pci_pwrctrl *pwrctrl = container_of(nb, struct pci_pwrctrl, nb);
 	struct device *dev = data;
 
-	if (dev_fwnode(dev) != dev_fwnode(pwrctl->dev))
+	if (dev_fwnode(dev) != dev_fwnode(pwrctrl->dev))
 		return NOTIFY_DONE;
 
 	switch (action) {
@@ -40,31 +40,32 @@ static int pci_pwrctl_notify(struct notifier_block *nb, unsigned long action,
 
 static void rescan_work_func(struct work_struct *work)
 {
-	struct pci_pwrctl *pwrctl = container_of(work, struct pci_pwrctl, work);
+	struct pci_pwrctrl *pwrctrl = container_of(work,
+						   struct pci_pwrctrl, work);
 
 	pci_lock_rescan_remove();
-	pci_rescan_bus(to_pci_dev(pwrctl->dev->parent)->bus);
+	pci_rescan_bus(to_pci_dev(pwrctrl->dev->parent)->bus);
 	pci_unlock_rescan_remove();
 }
 
 /**
- * pci_pwrctl_init() - Initialize the PCI power control context struct
+ * pci_pwrctrl_init() - Initialize the PCI power control context struct
  *
- * @pwrctl: PCI power control data
+ * @pwrctrl: PCI power control data
  * @dev: Parent device
  */
-void pci_pwrctl_init(struct pci_pwrctl *pwrctl, struct device *dev)
+void pci_pwrctrl_init(struct pci_pwrctrl *pwrctrl, struct device *dev)
 {
-	pwrctl->dev = dev;
-	INIT_WORK(&pwrctl->work, rescan_work_func);
+	pwrctrl->dev = dev;
+	INIT_WORK(&pwrctrl->work, rescan_work_func);
 }
-EXPORT_SYMBOL_GPL(pci_pwrctl_init);
+EXPORT_SYMBOL_GPL(pci_pwrctrl_init);
 
 /**
- * pci_pwrctl_device_set_ready() - Notify the pwrctl subsystem that the PCI
+ * pci_pwrctrl_device_set_ready() - Notify the pwrctrl subsystem that the PCI
  * device is powered-up and ready to be detected.
  *
- * @pwrctl: PCI power control data.
+ * @pwrctrl: PCI power control data.
  *
  * Returns:
  * 0 on success, negative error number on error.
@@ -74,31 +75,31 @@ EXPORT_SYMBOL_GPL(pci_pwrctl_init);
  * that the bus rescan was successfully started. The device will get bound to
  * its PCI driver asynchronously.
  */
-int pci_pwrctl_device_set_ready(struct pci_pwrctl *pwrctl)
+int pci_pwrctrl_device_set_ready(struct pci_pwrctrl *pwrctrl)
 {
 	int ret;
 
-	if (!pwrctl->dev)
+	if (!pwrctrl->dev)
 		return -ENODEV;
 
-	pwrctl->nb.notifier_call = pci_pwrctl_notify;
-	ret = bus_register_notifier(&pci_bus_type, &pwrctl->nb);
+	pwrctrl->nb.notifier_call = pci_pwrctrl_notify;
+	ret = bus_register_notifier(&pci_bus_type, &pwrctrl->nb);
 	if (ret)
 		return ret;
 
-	schedule_work(&pwrctl->work);
+	schedule_work(&pwrctrl->work);
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(pci_pwrctl_device_set_ready);
+EXPORT_SYMBOL_GPL(pci_pwrctrl_device_set_ready);
 
 /**
- * pci_pwrctl_device_unset_ready() - Notify the pwrctl subsystem that the PCI
+ * pci_pwrctrl_device_unset_ready() - Notify the pwrctrl subsystem that the PCI
  * device is about to be powered-down.
  *
- * @pwrctl: PCI power control data.
+ * @pwrctrl: PCI power control data.
  */
-void pci_pwrctl_device_unset_ready(struct pci_pwrctl *pwrctl)
+void pci_pwrctrl_device_unset_ready(struct pci_pwrctrl *pwrctrl)
 {
 	/*
 	 * We don't have to delete the link here. Typically, this function
@@ -106,41 +107,41 @@ void pci_pwrctl_device_unset_ready(struct pci_pwrctl *pwrctl)
 	 * it is being detached then the child PCI device must have already
 	 * been unbound too or the device core wouldn't let us unbind.
 	 */
-	bus_unregister_notifier(&pci_bus_type, &pwrctl->nb);
+	bus_unregister_notifier(&pci_bus_type, &pwrctrl->nb);
 }
-EXPORT_SYMBOL_GPL(pci_pwrctl_device_unset_ready);
+EXPORT_SYMBOL_GPL(pci_pwrctrl_device_unset_ready);
 
-static void devm_pci_pwrctl_device_unset_ready(void *data)
+static void devm_pci_pwrctrl_device_unset_ready(void *data)
 {
-	struct pci_pwrctl *pwrctl = data;
+	struct pci_pwrctrl *pwrctrl = data;
 
-	pci_pwrctl_device_unset_ready(pwrctl);
+	pci_pwrctrl_device_unset_ready(pwrctrl);
 }
 
 /**
- * devm_pci_pwrctl_device_set_ready - Managed variant of
- * pci_pwrctl_device_set_ready().
+ * devm_pci_pwrctrl_device_set_ready - Managed variant of
+ * pci_pwrctrl_device_set_ready().
  *
- * @dev: Device managing this pwrctl provider.
- * @pwrctl: PCI power control data.
+ * @dev: Device managing this pwrctrl provider.
+ * @pwrctrl: PCI power control data.
  *
  * Returns:
  * 0 on success, negative error number on error.
  */
-int devm_pci_pwrctl_device_set_ready(struct device *dev,
-				     struct pci_pwrctl *pwrctl)
+int devm_pci_pwrctrl_device_set_ready(struct device *dev,
+				      struct pci_pwrctrl *pwrctrl)
 {
 	int ret;
 
-	ret = pci_pwrctl_device_set_ready(pwrctl);
+	ret = pci_pwrctrl_device_set_ready(pwrctrl);
 	if (ret)
 		return ret;
 
 	return devm_add_action_or_reset(dev,
-					devm_pci_pwrctl_device_unset_ready,
-					pwrctl);
+					devm_pci_pwrctrl_device_unset_ready,
+					pwrctrl);
 }
-EXPORT_SYMBOL_GPL(devm_pci_pwrctl_device_set_ready);
+EXPORT_SYMBOL_GPL(devm_pci_pwrctrl_device_set_ready);
 
 MODULE_AUTHOR("Bartosz Golaszewski <bartosz.golaszewski@linaro.org>");
 MODULE_DESCRIPTION("PCI Device Power Control core driver");
diff --git a/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c b/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c
index cc19ad61dd6e8..e9f89866b7c25 100644
--- a/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c
+++ b/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c
@@ -13,21 +13,21 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 
-struct pci_pwrctl_pwrseq_data {
-	struct pci_pwrctl ctx;
+struct pci_pwrctrl_pwrseq_data {
+	struct pci_pwrctrl ctx;
 	struct pwrseq_desc *pwrseq;
 };
 
-static void devm_pci_pwrctl_pwrseq_power_off(void *data)
+static void devm_pci_pwrctrl_pwrseq_power_off(void *data)
 {
 	struct pwrseq_desc *pwrseq = data;
 
 	pwrseq_power_off(pwrseq);
 }
 
-static int pci_pwrctl_pwrseq_probe(struct platform_device *pdev)
+static int pci_pwrctrl_pwrseq_probe(struct platform_device *pdev)
 {
-	struct pci_pwrctl_pwrseq_data *data;
+	struct pci_pwrctrl_pwrseq_data *data;
 	struct device *dev = &pdev->dev;
 	int ret;
 
@@ -45,22 +45,22 @@ static int pci_pwrctl_pwrseq_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, ret,
 				     "Failed to power-on the device\n");
 
-	ret = devm_add_action_or_reset(dev, devm_pci_pwrctl_pwrseq_power_off,
+	ret = devm_add_action_or_reset(dev, devm_pci_pwrctrl_pwrseq_power_off,
 				       data->pwrseq);
 	if (ret)
 		return ret;
 
-	pci_pwrctl_init(&data->ctx, dev);
+	pci_pwrctrl_init(&data->ctx, dev);
 
-	ret = devm_pci_pwrctl_device_set_ready(dev, &data->ctx);
+	ret = devm_pci_pwrctrl_device_set_ready(dev, &data->ctx);
 	if (ret)
 		return dev_err_probe(dev, ret,
-				     "Failed to register the pwrctl wrapper\n");
+				     "Failed to register the pwrctrl wrapper\n");
 
 	return 0;
 }
 
-static const struct of_device_id pci_pwrctl_pwrseq_of_match[] = {
+static const struct of_device_id pci_pwrctrl_pwrseq_of_match[] = {
 	{
 		/* ATH11K in QCA6390 package. */
 		.compatible = "pci17cb,1101",
@@ -78,16 +78,16 @@ static const struct of_device_id pci_pwrctl_pwrseq_of_match[] = {
 	},
 	{ }
 };
-MODULE_DEVICE_TABLE(of, pci_pwrctl_pwrseq_of_match);
+MODULE_DEVICE_TABLE(of, pci_pwrctrl_pwrseq_of_match);
 
-static struct platform_driver pci_pwrctl_pwrseq_driver = {
+static struct platform_driver pci_pwrctrl_pwrseq_driver = {
 	.driver = {
-		.name = "pci-pwrctl-pwrseq",
-		.of_match_table = pci_pwrctl_pwrseq_of_match,
+		.name = "pci-pwrctrl-pwrseq",
+		.of_match_table = pci_pwrctrl_pwrseq_of_match,
 	},
-	.probe = pci_pwrctl_pwrseq_probe,
+	.probe = pci_pwrctrl_pwrseq_probe,
 };
-module_platform_driver(pci_pwrctl_pwrseq_driver);
+module_platform_driver(pci_pwrctrl_pwrseq_driver);
 
 MODULE_AUTHOR("Bartosz Golaszewski <bartosz.golaszewski@linaro.org>");
 MODULE_DESCRIPTION("Generic PCI Power Control module for power sequenced devices");
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index 3dd9b3024956a..27ef371a8443e 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -17,7 +17,7 @@ static void pci_free_resources(struct pci_dev *dev)
 	}
 }
 
-static void pci_pwrctl_unregister(struct device *dev)
+static void pci_pwrctrl_unregister(struct device *dev)
 {
 	struct platform_device *pdev;
 
@@ -34,7 +34,7 @@ static void pci_stop_dev(struct pci_dev *dev)
 	pci_pme_active(dev, false);
 
 	if (pci_dev_is_added(dev)) {
-		pci_pwrctl_unregister(&dev->dev);
+		pci_pwrctrl_unregister(&dev->dev);
 		device_release_driver(&dev->dev);
 		pci_proc_detach_device(dev);
 		pci_remove_sysfs_dev_files(dev);
diff --git a/include/linux/pci-pwrctrl.h b/include/linux/pci-pwrctrl.h
index 0d23dddf59ec8..7d439b0675e91 100644
--- a/include/linux/pci-pwrctrl.h
+++ b/include/linux/pci-pwrctrl.h
@@ -3,8 +3,8 @@
  * Copyright (C) 2024 Linaro Ltd.
  */
 
-#ifndef __PCI_PWRCTL_H__
-#define __PCI_PWRCTL_H__
+#ifndef __PCI_PWRCTRL_H__
+#define __PCI_PWRCTRL_H__
 
 #include <linux/notifier.h>
 #include <linux/workqueue.h>
@@ -29,14 +29,14 @@ struct device_link;
  */
 
 /**
- * struct pci_pwrctl - PCI device power control context.
+ * struct pci_pwrctrl - PCI device power control context.
  * @dev: Address of the power controlling device.
  *
  * An object of this type must be allocated by the PCI power control device and
- * passed to the pwrctl subsystem to trigger a bus rescan and setup a device
+ * passed to the pwrctrl subsystem to trigger a bus rescan and setup a device
  * link with the device once it's up.
  */
-struct pci_pwrctl {
+struct pci_pwrctrl {
 	struct device *dev;
 
 	/* Private: don't use. */
@@ -45,10 +45,10 @@ struct pci_pwrctl {
 	struct work_struct work;
 };
 
-void pci_pwrctl_init(struct pci_pwrctl *pwrctl, struct device *dev);
-int pci_pwrctl_device_set_ready(struct pci_pwrctl *pwrctl);
-void pci_pwrctl_device_unset_ready(struct pci_pwrctl *pwrctl);
-int devm_pci_pwrctl_device_set_ready(struct device *dev,
-				     struct pci_pwrctl *pwrctl);
+void pci_pwrctrl_init(struct pci_pwrctrl *pwrctrl, struct device *dev);
+int pci_pwrctrl_device_set_ready(struct pci_pwrctrl *pwrctrl);
+void pci_pwrctrl_device_unset_ready(struct pci_pwrctrl *pwrctrl);
+int devm_pci_pwrctrl_device_set_ready(struct device *dev,
+				     struct pci_pwrctrl *pwrctrl);
 
-#endif /* __PCI_PWRCTL_H__ */
+#endif /* __PCI_PWRCTRL_H__ */

From acff9409dd40beaca2bd982678d222e2740ad84b Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Tue, 12 Nov 2024 01:04:58 +0000
Subject: [PATCH 1312/1530] Revert "f2fs: remove unreachable lazytime mount
 option parsing"

This reverts commit 54f43a10fa257ad4af02a1d157fefef6ebcfa7dc.

The above commit broke the lazytime mount, given

mount("/dev/vdb", "/mnt/test", "f2fs", 0, "lazytime");

CC: stable@vger.kernel.org # 6.11+
Signed-off-by: Daniel Rosenberg <drosen@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/super.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 49519439b770f..35c4394e4fc64 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -150,6 +150,8 @@ enum {
 	Opt_mode,
 	Opt_fault_injection,
 	Opt_fault_type,
+	Opt_lazytime,
+	Opt_nolazytime,
 	Opt_quota,
 	Opt_noquota,
 	Opt_usrquota,
@@ -226,6 +228,8 @@ static match_table_t f2fs_tokens = {
 	{Opt_mode, "mode=%s"},
 	{Opt_fault_injection, "fault_injection=%u"},
 	{Opt_fault_type, "fault_type=%u"},
+	{Opt_lazytime, "lazytime"},
+	{Opt_nolazytime, "nolazytime"},
 	{Opt_quota, "quota"},
 	{Opt_noquota, "noquota"},
 	{Opt_usrquota, "usrquota"},
@@ -922,6 +926,12 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 			f2fs_info(sbi, "fault_type options not supported");
 			break;
 #endif
+		case Opt_lazytime:
+			sb->s_flags |= SB_LAZYTIME;
+			break;
+		case Opt_nolazytime:
+			sb->s_flags &= ~SB_LAZYTIME;
+			break;
 #ifdef CONFIG_QUOTA
 		case Opt_quota:
 		case Opt_usrquota:

From 789ca0eb47f7782b3230ab0957eabd7967b78cae Mon Sep 17 00:00:00 2001
From: Daniel Yang <danielyangkang@gmail.com>
Date: Sun, 17 Nov 2024 23:01:40 -0800
Subject: [PATCH 1313/1530] f2fs: replace deprecated strcpy with strscpy

strcpy is deprecated. Kernel docs recommend replacing strcpy with
strscpy. The function strcpy() return value isn't used so there
shouldn't be an issue replacing with the safer alternative strscpy.

Signed-off-by: Daniel Yang <danielyangkang@gmail.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/super.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 35c4394e4fc64..7bcd6471af9a6 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1172,7 +1172,11 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 				break;
 			}
 
-			strcpy(ext[ext_cnt], name);
+			ret = strscpy(ext[ext_cnt], name);
+			if (ret < 0) {
+				kfree(name);
+				return ret;
+			}
 			F2FS_OPTION(sbi).compress_ext_cnt++;
 			kfree(name);
 			break;
@@ -1201,7 +1205,11 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 				break;
 			}
 
-			strcpy(noext[noext_cnt], name);
+			ret = strscpy(noext[noext_cnt], name);
+			if (ret < 0) {
+				kfree(name);
+				return ret;
+			}
 			F2FS_OPTION(sbi).nocompress_ext_cnt++;
 			kfree(name);
 			break;

From 3273d8ad947dea925a65a78ca29e5351c960c801 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Fri, 8 Nov 2024 09:25:54 +0800
Subject: [PATCH 1314/1530] f2fs: fix to do cast in F2FS_{BLK_TO_BYTES,
 BTYES_TO_BLK} to avoid overflow

It missed to cast variable to unsigned long long type before
bit shift, which will cause overflow, fix it.

Fixes: f7ef9b83b583 ("f2fs: introduce macros to convert bytes and blocks in f2fs")
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/super.c         | 2 +-
 include/linux/f2fs_fs.h | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 7bcd6471af9a6..0097a5770fa3f 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -3344,7 +3344,7 @@ loff_t max_file_blocks(struct inode *inode)
 	 * fit within U32_MAX + 1 data units.
 	 */
 
-	result = min(result, F2FS_BYTES_TO_BLK(((loff_t)U32_MAX + 1) * 4096));
+	result = umin(result, F2FS_BYTES_TO_BLK(((loff_t)U32_MAX + 1) * 4096));
 
 	return result;
 }
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index b0b821edfd97d..3b2ad444c002e 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -24,10 +24,10 @@
 #define NEW_ADDR		((block_t)-1)	/* used as block_t addresses */
 #define COMPRESS_ADDR		((block_t)-2)	/* used as compressed data flag */
 
-#define F2FS_BYTES_TO_BLK(bytes)	((bytes) >> F2FS_BLKSIZE_BITS)
-#define F2FS_BLK_TO_BYTES(blk)		((blk) << F2FS_BLKSIZE_BITS)
+#define F2FS_BYTES_TO_BLK(bytes)	((unsigned long long)(bytes) >> F2FS_BLKSIZE_BITS)
+#define F2FS_BLK_TO_BYTES(blk)		((unsigned long long)(blk) << F2FS_BLKSIZE_BITS)
 #define F2FS_BLK_END_BYTES(blk)		(F2FS_BLK_TO_BYTES(blk + 1) - 1)
-#define F2FS_BLK_ALIGN(x)			(F2FS_BYTES_TO_BLK((x) + F2FS_BLKSIZE - 1))
+#define F2FS_BLK_ALIGN(x)		(F2FS_BYTES_TO_BLK((x) + F2FS_BLKSIZE - 1))
 
 /* 0, 1(node nid), 2(meta nid) are reserved node id */
 #define F2FS_RESERVED_NODE_NUM		3

From 7461f37094180200cb2f98e60ef99a0cea97beec Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Fri, 8 Nov 2024 09:25:55 +0800
Subject: [PATCH 1315/1530] f2fs: clean up w/ F2FS_{BLK_TO_BYTES,BTYES_TO_BLK}

f2fs doesn't support different blksize in one instance, so
bytes_to_blks() and blks_to_bytes() are equal to F2FS_BYTES_TO_BLK
and F2FS_BLK_TO_BYTES, let's use F2FS_BYTES_TO_BLK/F2FS_BLK_TO_BYTES
instead for cleanup.

Reviewed-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 68 +++++++++++++++++++++-----------------------------
 1 file changed, 29 insertions(+), 39 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index b33aca24b9ef2..0e8390cbdb5bf 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1819,16 +1819,6 @@ bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len)
 	return true;
 }
 
-static inline u64 bytes_to_blks(struct inode *inode, u64 bytes)
-{
-	return (bytes >> inode->i_blkbits);
-}
-
-static inline u64 blks_to_bytes(struct inode *inode, u64 blks)
-{
-	return (blks << inode->i_blkbits);
-}
-
 static int f2fs_xattr_fiemap(struct inode *inode,
 				struct fiemap_extent_info *fieinfo)
 {
@@ -1854,7 +1844,7 @@ static int f2fs_xattr_fiemap(struct inode *inode,
 			return err;
 		}
 
-		phys = blks_to_bytes(inode, ni.blk_addr);
+		phys = F2FS_BLK_TO_BYTES(ni.blk_addr);
 		offset = offsetof(struct f2fs_inode, i_addr) +
 					sizeof(__le32) * (DEF_ADDRS_PER_INODE -
 					get_inline_xattr_addrs(inode));
@@ -1886,7 +1876,7 @@ static int f2fs_xattr_fiemap(struct inode *inode,
 			return err;
 		}
 
-		phys = blks_to_bytes(inode, ni.blk_addr);
+		phys = F2FS_BLK_TO_BYTES(ni.blk_addr);
 		len = inode->i_sb->s_blocksize;
 
 		f2fs_put_page(page, 1);
@@ -1948,16 +1938,16 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			goto out;
 	}
 
-	if (bytes_to_blks(inode, len) == 0)
-		len = blks_to_bytes(inode, 1);
+	if (F2FS_BYTES_TO_BLK(len) == 0)
+		len = F2FS_BLKSIZE;
 
-	start_blk = bytes_to_blks(inode, start);
-	last_blk = bytes_to_blks(inode, start + len - 1);
+	start_blk = F2FS_BYTES_TO_BLK(start);
+	last_blk = F2FS_BYTES_TO_BLK(start + len - 1);
 
 next:
 	memset(&map, 0, sizeof(map));
 	map.m_lblk = start_blk;
-	map.m_len = bytes_to_blks(inode, len);
+	map.m_len = F2FS_BYTES_TO_BLK(len);
 	map.m_next_pgofs = &next_pgofs;
 	map.m_seg_type = NO_CHECK_TYPE;
 
@@ -1974,7 +1964,7 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	if (!compr_cluster && !(map.m_flags & F2FS_MAP_FLAGS)) {
 		start_blk = next_pgofs;
 
-		if (blks_to_bytes(inode, start_blk) < maxbytes)
+		if (F2FS_BLK_TO_BYTES(start_blk) < maxbytes)
 			goto prep_next;
 
 		flags |= FIEMAP_EXTENT_LAST;
@@ -2011,14 +2001,14 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	} else if (compr_appended) {
 		unsigned int appended_blks = cluster_size -
 						count_in_cluster + 1;
-		size += blks_to_bytes(inode, appended_blks);
+		size += F2FS_BLK_TO_BYTES(appended_blks);
 		start_blk += appended_blks;
 		compr_cluster = false;
 	} else {
-		logical = blks_to_bytes(inode, start_blk);
+		logical = F2FS_BLK_TO_BYTES(start_blk);
 		phys = __is_valid_data_blkaddr(map.m_pblk) ?
-			blks_to_bytes(inode, map.m_pblk) : 0;
-		size = blks_to_bytes(inode, map.m_len);
+			F2FS_BLK_TO_BYTES(map.m_pblk) : 0;
+		size = F2FS_BLK_TO_BYTES(map.m_len);
 		flags = 0;
 
 		if (compr_cluster) {
@@ -2026,13 +2016,13 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			count_in_cluster += map.m_len;
 			if (count_in_cluster == cluster_size) {
 				compr_cluster = false;
-				size += blks_to_bytes(inode, 1);
+				size += F2FS_BLKSIZE;
 			}
 		} else if (map.m_flags & F2FS_MAP_DELALLOC) {
 			flags = FIEMAP_EXTENT_UNWRITTEN;
 		}
 
-		start_blk += bytes_to_blks(inode, size);
+		start_blk += F2FS_BYTES_TO_BLK(size);
 	}
 
 prep_next:
@@ -2070,7 +2060,7 @@ static int f2fs_read_single_page(struct inode *inode, struct folio *folio,
 					struct readahead_control *rac)
 {
 	struct bio *bio = *bio_ret;
-	const unsigned blocksize = blks_to_bytes(inode, 1);
+	const unsigned int blocksize = F2FS_BLKSIZE;
 	sector_t block_in_file;
 	sector_t last_block;
 	sector_t last_block_in_file;
@@ -2080,8 +2070,8 @@ static int f2fs_read_single_page(struct inode *inode, struct folio *folio,
 
 	block_in_file = (sector_t)index;
 	last_block = block_in_file + nr_pages;
-	last_block_in_file = bytes_to_blks(inode,
-			f2fs_readpage_limit(inode) + blocksize - 1);
+	last_block_in_file = F2FS_BYTES_TO_BLK(f2fs_readpage_limit(inode) +
+							blocksize - 1);
 	if (last_block > last_block_in_file)
 		last_block = last_block_in_file;
 
@@ -2181,7 +2171,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 	struct bio *bio = *bio_ret;
 	unsigned int start_idx = cc->cluster_idx << cc->log_cluster_size;
 	sector_t last_block_in_file;
-	const unsigned blocksize = blks_to_bytes(inode, 1);
+	const unsigned int blocksize = F2FS_BLKSIZE;
 	struct decompress_io_ctx *dic = NULL;
 	struct extent_info ei = {};
 	bool from_dnode = true;
@@ -2190,8 +2180,8 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 
 	f2fs_bug_on(sbi, f2fs_cluster_is_empty(cc));
 
-	last_block_in_file = bytes_to_blks(inode,
-			f2fs_readpage_limit(inode) + blocksize - 1);
+	last_block_in_file = F2FS_BYTES_TO_BLK(f2fs_readpage_limit(inode) +
+							blocksize - 1);
 
 	/* get rid of pages beyond EOF */
 	for (i = 0; i < cc->cluster_size; i++) {
@@ -3957,7 +3947,7 @@ static int check_swap_activate(struct swap_info_struct *sis,
 	 * to be very smart.
 	 */
 	cur_lblock = 0;
-	last_lblock = bytes_to_blks(inode, i_size_read(inode));
+	last_lblock = F2FS_BYTES_TO_BLK(i_size_read(inode));
 
 	while (cur_lblock < last_lblock && cur_lblock < sis->max) {
 		struct f2fs_map_blocks map;
@@ -4200,8 +4190,8 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	pgoff_t next_pgofs = 0;
 	int err;
 
-	map.m_lblk = bytes_to_blks(inode, offset);
-	map.m_len = bytes_to_blks(inode, offset + length - 1) - map.m_lblk + 1;
+	map.m_lblk = F2FS_BYTES_TO_BLK(offset);
+	map.m_len = F2FS_BYTES_TO_BLK(offset + length - 1) - map.m_lblk + 1;
 	map.m_next_pgofs = &next_pgofs;
 	map.m_seg_type = f2fs_rw_hint_to_seg_type(F2FS_I_SB(inode),
 						inode->i_write_hint);
@@ -4212,7 +4202,7 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	if (err)
 		return err;
 
-	iomap->offset = blks_to_bytes(inode, map.m_lblk);
+	iomap->offset = F2FS_BLK_TO_BYTES(map.m_lblk);
 
 	/*
 	 * When inline encryption is enabled, sometimes I/O to an encrypted file
@@ -4232,21 +4222,21 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		if (WARN_ON_ONCE(map.m_pblk == NEW_ADDR))
 			return -EINVAL;
 
-		iomap->length = blks_to_bytes(inode, map.m_len);
+		iomap->length = F2FS_BLK_TO_BYTES(map.m_len);
 		iomap->type = IOMAP_MAPPED;
 		iomap->flags |= IOMAP_F_MERGED;
 		iomap->bdev = map.m_bdev;
-		iomap->addr = blks_to_bytes(inode, map.m_pblk);
+		iomap->addr = F2FS_BLK_TO_BYTES(map.m_pblk);
 	} else {
 		if (flags & IOMAP_WRITE)
 			return -ENOTBLK;
 
 		if (map.m_pblk == NULL_ADDR) {
-			iomap->length = blks_to_bytes(inode, next_pgofs) -
-								iomap->offset;
+			iomap->length = F2FS_BLK_TO_BYTES(next_pgofs) -
+							iomap->offset;
 			iomap->type = IOMAP_HOLE;
 		} else if (map.m_pblk == NEW_ADDR) {
-			iomap->length = blks_to_bytes(inode, map.m_len);
+			iomap->length = F2FS_BLK_TO_BYTES(map.m_len);
 			iomap->type = IOMAP_UNWRITTEN;
 		} else {
 			f2fs_bug_on(F2FS_I_SB(inode), 1);

From 77569f785c8624fa4189795fb52e635a973672e5 Mon Sep 17 00:00:00 2001
From: Zhiguo Niu <zhiguo.niu@unisoc.com>
Date: Fri, 8 Nov 2024 09:25:56 +0800
Subject: [PATCH 1316/1530] f2fs: fix to adjust appropriate length for fiemap

If user give a file size as "length" parameter for fiemap
operations, but if this size is non-block size aligned,
it will show 2 segments fiemap results even this whole file
is contiguous on disk, such as the following results:

 ./f2fs_io fiemap 0 19034 ylog/analyzer.py
Fiemap: offset = 0 len = 19034
        logical addr.    physical addr.   length           flags
0       0000000000000000 0000000020baa000 0000000000004000 00001000
1       0000000000004000 0000000020bae000 0000000000001000 00001001

after this patch:
./f2fs_io fiemap 0 19034 ylog/analyzer.py
Fiemap: offset = 0 len = 19034
    logical addr.    physical addr.   length           flags
0    0000000000000000 00000000315f3000 0000000000005000 00001001

Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c          | 6 +++---
 include/linux/f2fs_fs.h | 1 +
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 0e8390cbdb5bf..69f1cb0490ee3 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1938,12 +1938,12 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			goto out;
 	}
 
-	if (F2FS_BYTES_TO_BLK(len) == 0)
-		len = F2FS_BLKSIZE;
-
 	start_blk = F2FS_BYTES_TO_BLK(start);
 	last_blk = F2FS_BYTES_TO_BLK(start + len - 1);
 
+	if (len & F2FS_BLKSIZE_MASK)
+		len = round_up(len, F2FS_BLKSIZE);
+
 next:
 	memset(&map, 0, sizeof(map));
 	map.m_lblk = start_blk;
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 3b2ad444c002e..c24f8bc01045d 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -24,6 +24,7 @@
 #define NEW_ADDR		((block_t)-1)	/* used as block_t addresses */
 #define COMPRESS_ADDR		((block_t)-2)	/* used as compressed data flag */
 
+#define F2FS_BLKSIZE_MASK		(F2FS_BLKSIZE - 1)
 #define F2FS_BYTES_TO_BLK(bytes)	((unsigned long long)(bytes) >> F2FS_BLKSIZE_BITS)
 #define F2FS_BLK_TO_BYTES(blk)		((unsigned long long)(blk) << F2FS_BLKSIZE_BITS)
 #define F2FS_BLK_END_BYTES(blk)		(F2FS_BLK_TO_BYTES(blk + 1) - 1)

From 6787a82245857271133b63ae7f72f1dc9f29e985 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Fri, 8 Nov 2024 09:25:57 +0800
Subject: [PATCH 1317/1530] f2fs: fix to requery extent which cross boundary of
 inquiry

dd if=/dev/zero of=file bs=4k count=5
xfs_io file -c "fiemap -v 2 16384"
file:
   EXT: FILE-OFFSET      BLOCK-RANGE      TOTAL FLAGS
     0: [0..31]:         139272..139303      32 0x1000
     1: [32..39]:        139304..139311       8 0x1001
xfs_io file -c "fiemap -v 0 16384"
file:
   EXT: FILE-OFFSET      BLOCK-RANGE      TOTAL FLAGS
     0: [0..31]:         139272..139303      32 0x1000
xfs_io file -c "fiemap -v 0 16385"
file:
   EXT: FILE-OFFSET      BLOCK-RANGE      TOTAL FLAGS
     0: [0..39]:         139272..139311      40 0x1001

There are two problems:
- continuous extent is split to two
- FIEMAP_EXTENT_LAST is missing in last extent

The root cause is: if upper boundary of inquiry crosses extent,
f2fs_map_blocks() will truncate length of returned extent to
F2FS_BYTES_TO_BLK(len), and also, it will stop to query latter
extent or hole to make sure current extent is last or not.

In order to fix this issue, once we found an extent locates
in the end of inquiry range by f2fs_map_blocks(), we need to
expand inquiry range to requiry.

Cc: stable@vger.kernel.org
Fixes: 7f63eb77af7b ("f2fs: report unwritten area in f2fs_fiemap")
Reported-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 69f1cb0490ee3..ee5614324df04 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1896,7 +1896,7 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		u64 start, u64 len)
 {
 	struct f2fs_map_blocks map;
-	sector_t start_blk, last_blk;
+	sector_t start_blk, last_blk, blk_len, max_len;
 	pgoff_t next_pgofs;
 	u64 logical = 0, phys = 0, size = 0;
 	u32 flags = 0;
@@ -1940,14 +1940,13 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 
 	start_blk = F2FS_BYTES_TO_BLK(start);
 	last_blk = F2FS_BYTES_TO_BLK(start + len - 1);
-
-	if (len & F2FS_BLKSIZE_MASK)
-		len = round_up(len, F2FS_BLKSIZE);
+	blk_len = last_blk - start_blk + 1;
+	max_len = F2FS_BYTES_TO_BLK(maxbytes) - start_blk;
 
 next:
 	memset(&map, 0, sizeof(map));
 	map.m_lblk = start_blk;
-	map.m_len = F2FS_BYTES_TO_BLK(len);
+	map.m_len = blk_len;
 	map.m_next_pgofs = &next_pgofs;
 	map.m_seg_type = NO_CHECK_TYPE;
 
@@ -1970,6 +1969,17 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		flags |= FIEMAP_EXTENT_LAST;
 	}
 
+	/*
+	 * current extent may cross boundary of inquiry, increase len to
+	 * requery.
+	 */
+	if (!compr_cluster && (map.m_flags & F2FS_MAP_MAPPED) &&
+				map.m_lblk + map.m_len - 1 == last_blk &&
+				blk_len != max_len) {
+		blk_len = max_len;
+		goto next;
+	}
+
 	compr_appended = false;
 	/* In a case of compressed cluster, append this to the last extent */
 	if (compr_cluster && ((map.m_flags & F2FS_MAP_DELALLOC) ||

From a35749b1ed64ec7f4df0364fcc6002082d366486 Mon Sep 17 00:00:00 2001
From: Daeho Jeong <daehojeong@google.com>
Date: Mon, 18 Nov 2024 10:45:35 -0800
Subject: [PATCH 1318/1530] f2fs: adjust unusable cap before checkpoint=disable
 mode

The unusable cap value must be adjusted before checking whether
checkpoint=disable is feasible.

Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/super.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 0097a5770fa3f..e9d2267b87880 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -2496,6 +2496,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 		}
 	}
 
+	adjust_unusable_cap_perc(sbi);
 	if (enable_checkpoint == !!test_opt(sbi, DISABLE_CHECKPOINT)) {
 		if (test_opt(sbi, DISABLE_CHECKPOINT)) {
 			err = f2fs_disable_checkpoint(sbi);
@@ -2540,7 +2541,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 		(test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0);
 
 	limit_reserve_root(sbi);
-	adjust_unusable_cap_perc(sbi);
 	*flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME);
 	return 0;
 restore_checkpoint:

From 1015035609e4ccb32e967015a600e01158377dfc Mon Sep 17 00:00:00 2001
From: Sheng Yong <shengyong@oppo.com>
Date: Thu, 21 Nov 2024 16:26:56 +0800
Subject: [PATCH 1319/1530] f2fs: fix changing cursegs if recovery fails on
 zoned device

Fsync data recovery attempts to check and fix write pointer consistency
of cursegs and all other zones. If the write pointers of cursegs are
unaligned, cursegs are changed to new sections.

If recovery fails, zone write pointers are still checked and fixed,
but the latest checkpoint cannot be written back. Additionally, retry-
mount skips recovery and rolls back to reuse the old cursegs whose
zones are already finished. This can lead to unaligned write later.

This patch addresses the issue by leaving writer pointers untouched if
recovery fails. When retry-mount is performed, cursegs and other zones
are checked and fixed after skipping recovery.

Signed-off-by: Song Feng <songfeng@oppo.com>
Signed-off-by: Yongpeng Yang <yangyongpeng1@oppo.com>
Signed-off-by: Sheng Yong <shengyong@oppo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h     |  3 +--
 fs/f2fs/recovery.c |  9 ++-------
 fs/f2fs/segment.c  | 29 +++++++++++++++++++----------
 fs/f2fs/super.c    | 15 ++++++---------
 4 files changed, 28 insertions(+), 28 deletions(-)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 119706dbaefa9..b65b023a588a0 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3775,8 +3775,7 @@ void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
 int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
 			unsigned int val, int alloc);
 void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
-int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi);
-int f2fs_check_write_pointer(struct f2fs_sb_info *sbi);
+int f2fs_check_and_fix_write_pointer(struct f2fs_sb_info *sbi);
 int f2fs_build_segment_manager(struct f2fs_sb_info *sbi);
 void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi);
 int __init f2fs_create_segment_manager_caches(void);
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index e4d81b8705d1e..f35be2c48e3c0 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -899,13 +899,8 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	 * and the f2fs is not read only, check and fix zoned block devices'
 	 * write pointer consistency.
 	 */
-	if (f2fs_sb_has_blkzoned(sbi) && !f2fs_readonly(sbi->sb)) {
-		int err2 = f2fs_fix_curseg_write_pointer(sbi);
-
-		if (!err2)
-			err2 = f2fs_check_write_pointer(sbi);
-		if (err2)
-			err = err2;
+	if (!err) {
+		err = f2fs_check_and_fix_write_pointer(sbi);
 		ret = err;
 	}
 
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index edf2a74207b35..4236040e3994c 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -5246,7 +5246,7 @@ static int report_one_zone_cb(struct blk_zone *zone, unsigned int idx,
 	return 0;
 }
 
-static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
+static int do_fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
 {
 	struct curseg_info *cs = CURSEG_I(sbi, type);
 	struct f2fs_dev_info *zbd;
@@ -5351,12 +5351,12 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
 	return 0;
 }
 
-int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
+static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
 {
 	int i, ret;
 
 	for (i = 0; i < NR_PERSISTENT_LOG; i++) {
-		ret = fix_curseg_write_pointer(sbi, i);
+		ret = do_fix_curseg_write_pointer(sbi, i);
 		if (ret)
 			return ret;
 	}
@@ -5379,7 +5379,7 @@ static int check_zone_write_pointer_cb(struct blk_zone *zone, unsigned int idx,
 	return check_zone_write_pointer(args->sbi, args->fdev, zone);
 }
 
-int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
+static int check_write_pointer(struct f2fs_sb_info *sbi)
 {
 	int i, ret;
 	struct check_zone_write_pointer_args args;
@@ -5399,6 +5399,20 @@ int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
 	return 0;
 }
 
+int f2fs_check_and_fix_write_pointer(struct f2fs_sb_info *sbi)
+{
+	int ret;
+
+	if (!f2fs_sb_has_blkzoned(sbi) || f2fs_readonly(sbi->sb))
+		return 0;
+
+	f2fs_notice(sbi, "Checking entire write pointers");
+	ret = fix_curseg_write_pointer(sbi);
+	if (!ret)
+		ret = check_write_pointer(sbi);
+	return ret;
+}
+
 /*
  * Return the number of usable blocks in a segment. The number of blocks
  * returned is always equal to the number of blocks in a segment for
@@ -5435,12 +5449,7 @@ static inline unsigned int f2fs_usable_zone_blks_in_seg(
 	return BLKS_PER_SEG(sbi);
 }
 #else
-int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
-{
-	return 0;
-}
-
-int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
+int f2fs_check_and_fix_write_pointer(struct f2fs_sb_info *sbi)
 {
 	return 0;
 }
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index e9d2267b87880..41cc13b43ce1c 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -4774,16 +4774,13 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 reset_checkpoint:
 	/*
 	 * If the f2fs is not readonly and fsync data recovery succeeds,
-	 * check zoned block devices' write pointer consistency.
+	 * write pointer consistency of cursegs and other zones are already
+	 * checked and fixed during recovery. However, if recovery fails,
+	 * write pointers are left untouched, and retry-mount should check
+	 * them here.
 	 */
-	if (f2fs_sb_has_blkzoned(sbi) && !f2fs_readonly(sb)) {
-		int err2;
-
-		f2fs_notice(sbi, "Checking entire write pointers");
-		err2 = f2fs_check_write_pointer(sbi);
-		if (err2)
-			err = err2;
-	}
+	if (skip_recovery)
+		err = f2fs_check_and_fix_write_pointer(sbi);
 	if (err)
 		goto free_meta;
 

From f88c7904b5c7e35ab8037e2a59e10d80adf6fd7e Mon Sep 17 00:00:00 2001
From: Sheng Yong <shengyong@oppo.com>
Date: Thu, 21 Nov 2024 16:26:57 +0800
Subject: [PATCH 1320/1530] f2fs: clear SBI_POR_DOING before initing inmem
 curseg

SBI_POR_DOING can be cleared after recovery is completed, so that
changes made before recovery can be persistent, and subsequent
errors can be recorded into cp/sb.

Signed-off-by: Song Feng <songfeng@oppo.com>
Signed-off-by: Yongpeng Yang <yangyongpeng1@oppo.com>
Signed-off-by: Sheng Yong <shengyong@oppo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/super.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 41cc13b43ce1c..c0670cd619563 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -4784,13 +4784,13 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	if (err)
 		goto free_meta;
 
+	/* f2fs_recover_fsync_data() cleared this already */
+	clear_sbi_flag(sbi, SBI_POR_DOING);
+
 	err = f2fs_init_inmem_curseg(sbi);
 	if (err)
 		goto sync_free_meta;
 
-	/* f2fs_recover_fsync_data() cleared this already */
-	clear_sbi_flag(sbi, SBI_POR_DOING);
-
 	if (test_opt(sbi, DISABLE_CHECKPOINT)) {
 		err = f2fs_disable_checkpoint(sbi);
 		if (err)

From 81520c684ca67aea6a589461a3caebb9b11dcc90 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Wed, 20 Nov 2024 14:58:50 +0800
Subject: [PATCH 1321/1530] f2fs: print message if fscorrupted was found in
 f2fs_new_node_page()

If fs corruption occurs in f2fs_new_node_page(), let's print
more information about corrupted metadata into kernel log.

Meanwhile, it updates to record ERROR_INCONSISTENT_NAT instead
of ERROR_INVALID_BLKADDR if blkaddr in nat entry is not
NULL_ADDR which means nat bitmap and nat entry is inconsistent.

Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/node.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 7d904f2bd5b6c..0b900a7a48e59 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1338,7 +1338,12 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs)
 		err = -EFSCORRUPTED;
 		dec_valid_node_count(sbi, dn->inode, !ofs);
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
+		f2fs_warn_ratelimited(sbi,
+			"f2fs_new_node_page: inconsistent nat entry, "
+			"ino:%u, nid:%u, blkaddr:%u, ver:%u, flag:%u",
+			new_ni.ino, new_ni.nid, new_ni.blk_addr,
+			new_ni.version, new_ni.flag);
+		f2fs_handle_error(sbi, ERROR_INCONSISTENT_NAT);
 		goto fail;
 	}
 #endif

From 3fc5d5a182f6a1f8bd4dc775feb54c369dd2c343 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Thu, 21 Nov 2024 09:57:50 +0800
Subject: [PATCH 1322/1530] f2fs: fix to shrink read extent node in batches

We use rwlock to protect core structure data of extent tree during
its shrink, however, if there is a huge number of extent nodes in
extent tree, during shrink of extent tree, it may hold rwlock for
a very long time, which may trigger kernel hang issue.

This patch fixes to shrink read extent node in batches, so that,
critical region of the rwlock can be shrunk to avoid its extreme
long time hold.

Reported-by: Xiuhong Wang <xiuhong.wang@unisoc.com>
Closes: https://lore.kernel.org/linux-f2fs-devel/20241112110627.1314632-1-xiuhong.wang@unisoc.com/
Signed-off-by: Xiuhong Wang <xiuhong.wang@unisoc.com>
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/extent_cache.c | 69 +++++++++++++++++++++++++-----------------
 1 file changed, 41 insertions(+), 28 deletions(-)

diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 019c1f7b7fa53..b7a6817b44b00 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -379,21 +379,22 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode,
 }
 
 static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
-					struct extent_tree *et)
+				struct extent_tree *et, unsigned int nr_shrink)
 {
 	struct rb_node *node, *next;
 	struct extent_node *en;
-	unsigned int count = atomic_read(&et->node_cnt);
+	unsigned int count;
 
 	node = rb_first_cached(&et->root);
-	while (node) {
+
+	for (count = 0; node && count < nr_shrink; count++) {
 		next = rb_next(node);
 		en = rb_entry(node, struct extent_node, rb_node);
 		__release_extent_node(sbi, et, en);
 		node = next;
 	}
 
-	return count - atomic_read(&et->node_cnt);
+	return count;
 }
 
 static void __drop_largest_extent(struct extent_tree *et,
@@ -622,6 +623,30 @@ static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
 	return en;
 }
 
+static unsigned int __destroy_extent_node(struct inode *inode,
+					enum extent_type type)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct extent_tree *et = F2FS_I(inode)->extent_tree[type];
+	unsigned int nr_shrink = type == EX_READ ?
+				READ_EXTENT_CACHE_SHRINK_NUMBER :
+				AGE_EXTENT_CACHE_SHRINK_NUMBER;
+	unsigned int node_cnt = 0;
+
+	if (!et || !atomic_read(&et->node_cnt))
+		return 0;
+
+	while (atomic_read(&et->node_cnt)) {
+		write_lock(&et->lock);
+		node_cnt += __free_extent_tree(sbi, et, nr_shrink);
+		write_unlock(&et->lock);
+	}
+
+	f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
+
+	return node_cnt;
+}
+
 static void __update_extent_tree_range(struct inode *inode,
 			struct extent_info *tei, enum extent_type type)
 {
@@ -760,9 +785,6 @@ static void __update_extent_tree_range(struct inode *inode,
 		}
 	}
 
-	if (is_inode_flag_set(inode, FI_NO_EXTENT))
-		__free_extent_tree(sbi, et);
-
 	if (et->largest_updated) {
 		et->largest_updated = false;
 		updated = true;
@@ -780,6 +802,9 @@ static void __update_extent_tree_range(struct inode *inode,
 out_read_extent_cache:
 	write_unlock(&et->lock);
 
+	if (is_inode_flag_set(inode, FI_NO_EXTENT))
+		__destroy_extent_node(inode, EX_READ);
+
 	if (updated)
 		f2fs_mark_inode_dirty_sync(inode, true);
 }
@@ -942,10 +967,14 @@ static unsigned int __shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink
 	list_for_each_entry_safe(et, next, &eti->zombie_list, list) {
 		if (atomic_read(&et->node_cnt)) {
 			write_lock(&et->lock);
-			node_cnt += __free_extent_tree(sbi, et);
+			node_cnt += __free_extent_tree(sbi, et,
+					nr_shrink - node_cnt - tree_cnt);
 			write_unlock(&et->lock);
 		}
-		f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
+
+		if (atomic_read(&et->node_cnt))
+			goto unlock_out;
+
 		list_del_init(&et->list);
 		radix_tree_delete(&eti->extent_tree_root, et->ino);
 		kmem_cache_free(extent_tree_slab, et);
@@ -1084,23 +1113,6 @@ unsigned int f2fs_shrink_age_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink
 	return __shrink_extent_tree(sbi, nr_shrink, EX_BLOCK_AGE);
 }
 
-static unsigned int __destroy_extent_node(struct inode *inode,
-					enum extent_type type)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct extent_tree *et = F2FS_I(inode)->extent_tree[type];
-	unsigned int node_cnt = 0;
-
-	if (!et || !atomic_read(&et->node_cnt))
-		return 0;
-
-	write_lock(&et->lock);
-	node_cnt = __free_extent_tree(sbi, et);
-	write_unlock(&et->lock);
-
-	return node_cnt;
-}
-
 void f2fs_destroy_extent_node(struct inode *inode)
 {
 	__destroy_extent_node(inode, EX_READ);
@@ -1109,7 +1121,6 @@ void f2fs_destroy_extent_node(struct inode *inode)
 
 static void __drop_extent_tree(struct inode *inode, enum extent_type type)
 {
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct extent_tree *et = F2FS_I(inode)->extent_tree[type];
 	bool updated = false;
 
@@ -1117,7 +1128,6 @@ static void __drop_extent_tree(struct inode *inode, enum extent_type type)
 		return;
 
 	write_lock(&et->lock);
-	__free_extent_tree(sbi, et);
 	if (type == EX_READ) {
 		set_inode_flag(inode, FI_NO_EXTENT);
 		if (et->largest.len) {
@@ -1126,6 +1136,9 @@ static void __drop_extent_tree(struct inode *inode, enum extent_type type)
 		}
 	}
 	write_unlock(&et->lock);
+
+	__destroy_extent_node(inode, type);
+
 	if (updated)
 		f2fs_mark_inode_dirty_sync(inode, true);
 }

From 088f294609d8f8816dc316681aef2eb61982e0da Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Fri, 22 Nov 2024 00:11:18 +0100
Subject: [PATCH 1323/1530] fs/proc/kcore.c: Clear ret value in read_kcore_iter
 after successful iov_iter_zero

If iov_iter_zero succeeds after failed copy_from_kernel_nofault,
we need to reset the ret value to zero otherwise it will be returned
as final return value of read_kcore_iter.

This fixes objdump -d dump over /proc/kcore for me.

Cc: stable@vger.kernel.org
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Fixes: 3d5854d75e31 ("fs/proc/kcore.c: allow translation of physical memory addresses")
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20241121231118.3212000-1-jolsa@kernel.org
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/proc/kcore.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 51446c59388f1..c82c408e573ef 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -600,6 +600,7 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 					ret = -EFAULT;
 					goto out;
 				}
+				ret = 0;
 			/*
 			 * We know the bounce buffer is safe to copy from, so
 			 * use _copy_to_iter() directly.

From f57c084928661969a337c731cd05e1da97320829 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Fri, 22 Nov 2024 13:45:45 +0100
Subject: [PATCH 1324/1530] gpio: mpsse: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/2ce706d3242b9d3e4b9c20c0a7d9a8afcf8897ec.1729423829.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-mpsse.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-mpsse.c b/drivers/gpio/gpio-mpsse.c
index 9ef24449126a7..3ea32c5e33d1a 100644
--- a/drivers/gpio/gpio-mpsse.c
+++ b/drivers/gpio/gpio-mpsse.c
@@ -403,7 +403,7 @@ static void gpio_mpsse_ida_remove(void *data)
 {
 	struct mpsse_priv *priv = data;
 
-	ida_simple_remove(&gpio_mpsse_ida, priv->id);
+	ida_free(&gpio_mpsse_ida, priv->id);
 }
 
 static int gpio_mpsse_probe(struct usb_interface *interface,
@@ -422,7 +422,7 @@ static int gpio_mpsse_probe(struct usb_interface *interface,
 	priv->intf = interface;
 	priv->intf_id = interface->cur_altsetting->desc.bInterfaceNumber;
 
-	priv->id = ida_simple_get(&gpio_mpsse_ida, 0, 0, GFP_KERNEL);
+	priv->id = ida_alloc(&gpio_mpsse_ida, GFP_KERNEL);
 	if (priv->id < 0)
 		return priv->id;
 

From 1e726223be5bdedc59ccf9df3bed53456cb2fb05 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 19 Nov 2024 21:52:46 -0800
Subject: [PATCH 1325/1530] Documentation: filesystems: update filename
 extensions

Update references to most txt files to rst files.
Update one reference to an md file to a rst file.
Update one file path to its current location.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: linux-doc@vger.kernel.org
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: linux-fsdevel@vger.kernel.org
Cc: Ian Kent <raven@themaw.net>
Cc: autofs@vger.kernel.org
Cc: Alexander Aring <aahringo@redhat.com>
Cc: David Teigland <teigland@redhat.com>
Cc: gfs2@lists.linux.dev
Cc: Eric Biggers <ebiggers@kernel.org>
Cc: Theodore Y. Ts'o <tytso@mit.edu>
Cc: fsverity@lists.linux.dev
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: ocfs2-devel@lists.linux.dev
Reviewed-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20241120055246.158368-1-rdunlap@infradead.org
---
 Documentation/filesystems/autofs.rst                 | 2 +-
 Documentation/filesystems/dlmfs.rst                  | 2 +-
 Documentation/filesystems/fsverity.rst               | 2 +-
 Documentation/filesystems/path-lookup.rst            | 2 +-
 Documentation/filesystems/path-lookup.txt            | 2 +-
 Documentation/filesystems/ramfs-rootfs-initramfs.rst | 2 +-
 6 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/Documentation/filesystems/autofs.rst b/Documentation/filesystems/autofs.rst
index 1ac576458c69a..5eb02394fcc3a 100644
--- a/Documentation/filesystems/autofs.rst
+++ b/Documentation/filesystems/autofs.rst
@@ -442,7 +442,7 @@ which can be used to communicate directly with the autofs filesystem.
 It requires CAP_SYS_ADMIN for access.
 
 The 'ioctl's that can be used on this device are described in a separate
-document `autofs-mount-control.txt`, and are summarised briefly here.
+document `autofs-mount-control.rst`, and are summarised briefly here.
 Each ioctl is passed a pointer to an `autofs_dev_ioctl` structure::
 
         struct autofs_dev_ioctl {
diff --git a/Documentation/filesystems/dlmfs.rst b/Documentation/filesystems/dlmfs.rst
index 7e2b1fd471d79..70d4e48242c3a 100644
--- a/Documentation/filesystems/dlmfs.rst
+++ b/Documentation/filesystems/dlmfs.rst
@@ -36,7 +36,7 @@ None
 Usage
 =====
 
-If you're just interested in OCFS2, then please see ocfs2.txt. The
+If you're just interested in OCFS2, then please see ocfs2.rst. The
 rest of this document will be geared towards those who want to use
 dlmfs for easy to setup and easy to use clustered locking in
 userspace.
diff --git a/Documentation/filesystems/fsverity.rst b/Documentation/filesystems/fsverity.rst
index 0e2fac7a16da1..76e5382178689 100644
--- a/Documentation/filesystems/fsverity.rst
+++ b/Documentation/filesystems/fsverity.rst
@@ -16,7 +16,7 @@ btrfs filesystems.  Like fscrypt, not too much filesystem-specific
 code is needed to support fs-verity.
 
 fs-verity is similar to `dm-verity
-<https://www.kernel.org/doc/Documentation/device-mapper/verity.txt>`_
+<https://www.kernel.org/doc/Documentation/admin-guide/device-mapper/verity.rst>`_
 but works on files rather than block devices.  On regular files on
 filesystems supporting fs-verity, userspace can execute an ioctl that
 causes the filesystem to build a Merkle tree for the file and persist
diff --git a/Documentation/filesystems/path-lookup.rst b/Documentation/filesystems/path-lookup.rst
index 2b2df6aa54324..9ced1135608ea 100644
--- a/Documentation/filesystems/path-lookup.rst
+++ b/Documentation/filesystems/path-lookup.rst
@@ -531,7 +531,7 @@ this retry process in the next article.
 Automount points are locations in the filesystem where an attempt to
 lookup a name can trigger changes to how that lookup should be
 handled, in particular by mounting a filesystem there.  These are
-covered in greater detail in autofs.txt in the Linux documentation
+covered in greater detail in autofs.rst in the Linux documentation
 tree, but a few notes specifically related to path lookup are in order
 here.
 
diff --git a/Documentation/filesystems/path-lookup.txt b/Documentation/filesystems/path-lookup.txt
index 1aa7ce099f6f5..d2cf2852e1f8c 100644
--- a/Documentation/filesystems/path-lookup.txt
+++ b/Documentation/filesystems/path-lookup.txt
@@ -379,4 +379,4 @@ Papers and other documentation on dcache locking
 
 2. http://lse.sourceforge.net/locking/dcache/dcache.html
 
-3. path-lookup.md in this directory.
+3. path-lookup.rst in this directory.
diff --git a/Documentation/filesystems/ramfs-rootfs-initramfs.rst b/Documentation/filesystems/ramfs-rootfs-initramfs.rst
index 447f767c64627..fa4f81099cb44 100644
--- a/Documentation/filesystems/ramfs-rootfs-initramfs.rst
+++ b/Documentation/filesystems/ramfs-rootfs-initramfs.rst
@@ -315,7 +315,7 @@ the above threads) is:
 2) The cpio archive format chosen by the kernel is simpler and cleaner (and
    thus easier to create and parse) than any of the (literally dozens of)
    various tar archive formats.  The complete initramfs archive format is
-   explained in buffer-format.txt, created in usr/gen_init_cpio.c, and
+   explained in buffer-format.rst, created in usr/gen_init_cpio.c, and
    extracted in init/initramfs.c.  All three together come to less than 26k
    total of human-readable text.
 

From 72471fc769e4590cd6b662aa0a987eeae2be7d3b Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Wed, 20 Nov 2024 02:14:07 +0100
Subject: [PATCH 1326/1530] Documentation: pwrseq: Fix trivial misspellings

Use proper spelling for 'discrete'. When at it, capitalize 'Linux',
which is common practice in the documentation.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20241120-pwrseq-doc-trivial-fixes-v1-1-19a70f4dd156@gmail.com
---
 Documentation/driver-api/pwrseq.rst | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/driver-api/pwrseq.rst b/Documentation/driver-api/pwrseq.rst
index a644084ded17a..ad18b2326b689 100644
--- a/Documentation/driver-api/pwrseq.rst
+++ b/Documentation/driver-api/pwrseq.rst
@@ -11,7 +11,7 @@ Introduction
 ============
 
 This framework is designed to abstract complex power-up sequences that are
-shared between multiple logical devices in the linux kernel.
+shared between multiple logical devices in the Linux kernel.
 
 The intention is to allow consumers to obtain a power sequencing handle
 exposed by the power sequence provider and delegate the actual requesting and
@@ -25,7 +25,7 @@ The power sequencing API uses a number of terms specific to the subsystem:
 
 Unit
 
-    A unit is a discreet chunk of a power sequence. For instance one unit may
+    A unit is a discrete chunk of a power sequence. For instance one unit may
     enable a set of regulators, another may enable a specific GPIO. Units can
     define dependencies in the form of other units that must be enabled before
     it itself can be.
@@ -62,7 +62,7 @@ Provider interface
 The provider API is admittedly not nearly as straightforward as the one for
 consumers but it makes up for it in flexibility.
 
-Each provider can logically split the power-up sequence into descrete chunks
+Each provider can logically split the power-up sequence into discrete chunks
 (units) and define their dependencies. They can then expose named targets that
 consumers may use as the final point in the sequence that they wish to reach.
 
@@ -72,7 +72,7 @@ register with the pwrseq subsystem by calling pwrseq_device_register().
 Dynamic consumer matching
 -------------------------
 
-The main difference between pwrseq and other linux kernel providers is the
+The main difference between pwrseq and other Linux kernel providers is the
 mechanism for dynamic matching of consumers and providers. Every power sequence
 provider driver must implement the `match()` callback and pass it to the pwrseq
 core when registering with the subsystems.

From 9e6c5870bb44950d7a636db1af1948d71244e616 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 19 Nov 2024 12:32:01 -0800
Subject: [PATCH 1327/1530] Documentation: kernel-doc: enumerate identifier
 *type*s

Explain that a kernel-doc :identifiers: line can refer to a struct,
union, enum, or typedef as well as functions.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20241119203201.110953-1-rdunlap@infradead.org
---
 Documentation/doc-guide/kernel-doc.rst | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/doc-guide/kernel-doc.rst b/Documentation/doc-guide/kernel-doc.rst
index e6ffd59bb8f0f..af9697e60165d 100644
--- a/Documentation/doc-guide/kernel-doc.rst
+++ b/Documentation/doc-guide/kernel-doc.rst
@@ -533,6 +533,7 @@ identifiers: *[ function/type ...]*
   Include documentation for each *function* and *type* in *source*.
   If no *function* is specified, the documentation for all functions
   and types in the *source* will be included.
+  *type* can be a struct, union, enum, or typedef identifier.
 
   Examples::
 

From 21e500138b6f3040423bb1959ac9ffe68d138733 Mon Sep 17 00:00:00 2001
From: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Date: Tue, 19 Nov 2024 17:39:01 +0800
Subject: [PATCH 1328/1530] docs: core-api/gfp_mask-from-fs-io: indicate that
 vmalloc supports GFP_NOFS/GFP_NOIO

After the commit 451769ebb7e79 ("mm/vmalloc: alloc GFP_NO{FS,IO} for
vmalloc") in v5.17 it is now safe to use GFP_NOFS/GFP_NOIO flags
in [k]vmalloc, let's reflect it in documentation.

Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20241119093922.567138-1-ptikhomirov@virtuozzo.com
---
 .../core-api/gfp_mask-from-fs-io.rst          | 20 ++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/Documentation/core-api/gfp_mask-from-fs-io.rst b/Documentation/core-api/gfp_mask-from-fs-io.rst
index e7c32a8de126a..858b2fbcb36c7 100644
--- a/Documentation/core-api/gfp_mask-from-fs-io.rst
+++ b/Documentation/core-api/gfp_mask-from-fs-io.rst
@@ -55,14 +55,16 @@ scope.
 What about __vmalloc(GFP_NOFS)
 ==============================
 
-vmalloc doesn't support GFP_NOFS semantic because there are hardcoded
-GFP_KERNEL allocations deep inside the allocator which are quite non-trivial
-to fix up. That means that calling ``vmalloc`` with GFP_NOFS/GFP_NOIO is
-almost always a bug. The good news is that the NOFS/NOIO semantic can be
-achieved by the scope API.
+Since v5.17, and specifically after the commit 451769ebb7e79 ("mm/vmalloc:
+alloc GFP_NO{FS,IO} for vmalloc"), GFP_NOFS/GFP_NOIO are now supported in
+``[k]vmalloc`` by implicitly using scope API.
+
+In earlier kernels ``vmalloc`` didn't support GFP_NOFS semantic because there
+were hardcoded GFP_KERNEL allocations deep inside the allocator. That means
+that calling ``vmalloc`` with GFP_NOFS/GFP_NOIO was almost always a bug.
 
 In the ideal world, upper layers should already mark dangerous contexts
-and so no special care is required and vmalloc should be called without
-any problems. Sometimes if the context is not really clear or there are
-layering violations then the recommended way around that is to wrap ``vmalloc``
-by the scope API with a comment explaining the problem.
+and so no special care is required and ``vmalloc`` should be called without any
+problems. Sometimes if the context is not really clear or there are layering
+violations then the recommended way around that (on pre-v5.17 kernels) is to
+wrap ``vmalloc`` by the scope API with a comment explaining the problem.

From d8c949c577b5adb9fb87923b5429767aae4be590 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <ukleinek@kernel.org>
Date: Fri, 15 Nov 2024 11:38:41 +0100
Subject: [PATCH 1329/1530] docs/licensing: Clarify wording about "GPL" and
 "Proprietary"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are currently some doubts about out-of-tree kernel modules licensed
under GPLv3 and if they are supposed to be able to use symbols exported
using EXPORT_SYMBOL_GPL.

Clarify that "Proprietary" means anything non-GPL2 even though the
license might be an open source license. Also disambiguate "GPL
compatible" to "GPLv2 compatible".

Signed-off-by: Uwe Kleine-König <ukleinek@kernel.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20241115103842.585207-2-ukleinek@kernel.org
---
 Documentation/kernel-hacking/hacking.rst |  2 +-
 Documentation/process/license-rules.rst  | 18 ++++++++++--------
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/Documentation/kernel-hacking/hacking.rst b/Documentation/kernel-hacking/hacking.rst
index 1717348a4404e..0042776a9e17c 100644
--- a/Documentation/kernel-hacking/hacking.rst
+++ b/Documentation/kernel-hacking/hacking.rst
@@ -587,7 +587,7 @@ Defined in ``include/linux/export.h``
 
 Similar to :c:func:`EXPORT_SYMBOL()` except that the symbols
 exported by :c:func:`EXPORT_SYMBOL_GPL()` can only be seen by
-modules with a :c:func:`MODULE_LICENSE()` that specifies a GPL
+modules with a :c:func:`MODULE_LICENSE()` that specifies a GPLv2
 compatible license. It implies that the function is considered an
 internal implementation issue, and not really an interface. Some
 maintainers and developers may however require EXPORT_SYMBOL_GPL()
diff --git a/Documentation/process/license-rules.rst b/Documentation/process/license-rules.rst
index 2ef44ada3f119..59a7832df7d08 100644
--- a/Documentation/process/license-rules.rst
+++ b/Documentation/process/license-rules.rst
@@ -471,14 +471,16 @@ _`MODULE_LICENSE`
 				  source files.
 
     "Proprietary"		  The module is under a proprietary license.
-				  This string is solely for proprietary third
-				  party modules and cannot be used for modules
-				  which have their source code in the kernel
-				  tree. Modules tagged that way are tainting
-				  the kernel with the 'P' flag when loaded and
-				  the kernel module loader refuses to link such
-				  modules against symbols which are exported
-				  with EXPORT_SYMBOL_GPL().
+				  "Proprietary" is to be understood only as
+				  "The license is not compatible to GPLv2".
+                                  This string is solely for non-GPL2 compatible
+                                  third party modules and cannot be used for
+                                  modules which have their source code in the
+                                  kernel tree. Modules tagged that way are
+                                  tainting the kernel with the 'P' flag when
+                                  loaded and the kernel module loader refuses
+                                  to link such modules against symbols which
+                                  are exported with EXPORT_SYMBOL_GPL().
     ============================= =============================================
 
 

From a037699da0a17e99832875a936b5a6285d8de849 Mon Sep 17 00:00:00 2001
From: Sebastian Fricke <sebastian.fricke@collabora.com>
Date: Mon, 18 Nov 2024 08:03:50 +0100
Subject: [PATCH 1330/1530] docs: Add debugging section to process

This idea was formed after noticing that new developers experience
certain difficulty to navigate within the multitude of different
debugging options in the Kernel and while there often is good
documentation for the tools, the developer has to know first that they
exist and where to find them.
Add a general debugging section to the Kernel documentation, as an
easily locatable entry point to other documentation and as a general
guideline for the topic.

Signed-off-by: Sebastian Fricke <sebastian.fricke@collabora.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20241028-media_docs_improve_v3-v3-1-edf5c5b3746f@collabora.com
---
 .../driver_development_debugging_guide.rst    | 223 ++++++++++++++
 Documentation/process/debugging/index.rst     |  65 ++++
 .../debugging/userspace_debugging_guide.rst   | 280 ++++++++++++++++++
 Documentation/process/index.rst               |   8 +-
 4 files changed, 573 insertions(+), 3 deletions(-)
 create mode 100644 Documentation/process/debugging/driver_development_debugging_guide.rst
 create mode 100644 Documentation/process/debugging/index.rst
 create mode 100644 Documentation/process/debugging/userspace_debugging_guide.rst

diff --git a/Documentation/process/debugging/driver_development_debugging_guide.rst b/Documentation/process/debugging/driver_development_debugging_guide.rst
new file mode 100644
index 0000000000000..aef2040942050
--- /dev/null
+++ b/Documentation/process/debugging/driver_development_debugging_guide.rst
@@ -0,0 +1,223 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+========================================
+Debugging advice for driver development
+========================================
+
+This document serves as a general starting point and lookup for debugging
+device drivers.
+While this guide focuses on debugging that requires re-compiling the
+module/kernel, the :doc:`userspace debugging guide
+</process/debugging/userspace_debugging_guide>` will guide
+you through tools like dynamic debug, ftrace and other tools useful for
+debugging issues and behavior.
+For general debugging advice, see the :doc:`general advice document
+</process/debugging/index>`.
+
+.. contents::
+    :depth: 3
+
+The following sections show you the available tools.
+
+printk() & friends
+------------------
+
+These are derivatives of printf() with varying destinations and support for
+being dynamically turned on or off, or lack thereof.
+
+Simple printk()
+~~~~~~~~~~~~~~~
+
+The classic, can be used to great effect for quick and dirty development
+of new modules or to extract arbitrary necessary data for troubleshooting.
+
+Prerequisite: ``CONFIG_PRINTK`` (usually enabled by default)
+
+**Pros**:
+
+- No need to learn anything, simple to use
+- Easy to modify exactly to your needs (formatting of the data (See:
+  :doc:`/core-api/printk-formats`), visibility in the log)
+- Can cause delays in the execution of the code (beneficial to confirm whether
+  timing is a factor)
+
+**Cons**:
+
+- Requires rebuilding the kernel/module
+- Can cause delays in the execution of the code (which can cause issues to be
+  not reproducible)
+
+For the full documentation see :doc:`/core-api/printk-basics`
+
+Trace_printk
+~~~~~~~~~~~~
+
+Prerequisite: ``CONFIG_DYNAMIC_FTRACE`` & ``#include <linux/ftrace.h>``
+
+It is a tiny bit less comfortable to use than printk(), because you will have
+to read the messages from the trace file (See: :ref:`read_ftrace_log`
+instead of from the kernel log, but very useful when printk() adds unwanted
+delays into the code execution, causing issues to be flaky or hidden.)
+
+If the processing of this still causes timing issues then you can try
+trace_puts().
+
+For the full Documentation see trace_printk()
+
+dev_dbg
+~~~~~~~
+
+Print statement, which can be targeted by
+:ref:`process/debugging/userspace_debugging_guide:dynamic debug` that contains
+additional information about the device used within the context.
+
+**When is it appropriate to leave a debug print in the code?**
+
+Permanent debug statements have to be useful for a developer to troubleshoot
+driver misbehavior. Judging that is a bit more of an art than a science, but
+some guidelines are in the :ref:`Coding style guidelines
+<process/coding-style:13) printing kernel messages>`. In almost all cases the
+debug statements shouldn't be upstreamed, as a working driver is supposed to be
+silent.
+
+Custom printk
+~~~~~~~~~~~~~
+
+Example::
+
+  #define core_dbg(fmt, arg...) do { \
+	  if (core_debug) \
+		  printk(KERN_DEBUG pr_fmt("core: " fmt), ## arg); \
+	  } while (0)
+
+**When should you do this?**
+
+It is better to just use a pr_debug(), which can later be turned on/off with
+dynamic debug. Additionally, a lot of drivers activate these prints via a
+variable like ``core_debug`` set by a module parameter. However, Module
+parameters `are not recommended anymore
+<https://lore.kernel.org/all/2024032757-surcharge-grime-d3dd@gregkh>`_.
+
+Ftrace
+------
+
+Creating a custom Ftrace tracepoint
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+A tracepoint adds a hook into your code that will be called and logged when the
+tracepoint is enabled. This can be used, for example, to trace hitting a
+conditional branch or to dump the internal state at specific points of the code
+flow during a debugging session.
+
+Here is a basic description of :ref:`how to implement new tracepoints
+<trace/tracepoints:usage>`.
+
+For the full event tracing documentation see :doc:`/trace/events`
+
+For the full Ftrace documentation see :doc:`/trace/ftrace`
+
+DebugFS
+-------
+
+Prerequisite: ``CONFIG_DEBUG_FS` & `#include <linux/debugfs.h>``
+
+DebugFS differs from the other approaches of debugging, as it doesn't write
+messages to the kernel log nor add traces to the code. Instead it allows the
+developer to handle a set of files.
+With these files you can either store values of variables or make
+register/memory dumps or you can make these files writable and modify
+values/settings in the driver.
+
+Possible use-cases among others:
+
+- Store register values
+- Keep track of variables
+- Store errors
+- Store settings
+- Toggle a setting like debug on/off
+- Error injection
+
+This is especially useful, when the size of a data dump would be hard to digest
+as part of the general kernel log (for example when dumping raw bitstream data)
+or when you are not interested in all the values all the time, but with the
+possibility to inspect them.
+
+The general idea is:
+
+- Create a directory during probe (``struct dentry *parent =
+  debugfs_create_dir("my_driver", NULL);``)
+- Create a file (``debugfs_create_u32("my_value", 444, parent, &my_variable);``)
+
+  - In this example the file is found in
+    ``/sys/kernel/debug/my_driver/my_value`` (with read permissions for
+    user/group/all)
+  - any read of the file will return the current contents of the variable
+    ``my_variable``
+
+- Clean up the directory when removing the device
+  (``debugfs_remove_recursive(parent);``)
+
+For the full documentation see :doc:`/filesystems/debugfs`.
+
+KASAN, UBSAN, lockdep and other error checkers
+----------------------------------------------
+
+KASAN (Kernel Address Sanitizer)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Prerequisite: ``CONFIG_KASAN``
+
+KASAN is a dynamic memory error detector that helps to find use-after-free and
+out-of-bounds bugs. It uses compile-time instrumentation to check every memory
+access.
+
+For the full documentation see :doc:`/dev-tools/kasan`.
+
+UBSAN (Undefined Behavior Sanitizer)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Prerequisite: ``CONFIG_UBSAN``
+
+UBSAN relies on compiler instrumentation and runtime checks to detect undefined
+behavior. It is designed to find a variety of issues, including signed integer
+overflow, array index out of bounds, and more.
+
+For the full documentation see :doc:`/dev-tools/ubsan`
+
+lockdep (Lock Dependency Validator)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Prerequisite: ``CONFIG_DEBUG_LOCKDEP``
+
+lockdep is a runtime lock dependency validator that detects potential deadlocks
+and other locking-related issues in the kernel.
+It tracks lock acquisitions and releases, building a dependency graph that is
+analyzed for potential deadlocks.
+lockdep is especially useful for validating the correctness of lock ordering in
+the kernel.
+
+PSI (Pressure stall information tracking)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Prerequisite: ``CONFIG_PSI``
+
+PSI is a measurement tool to identify excessive overcommits on hardware
+resources, that can cause performance disruptions or even OOM kills.
+
+device coredump
+---------------
+
+Prerequisite: ``#include <linux/devcoredump.h>``
+
+Provides the infrastructure for a driver to provide arbitrary data to userland.
+It is most often used in conjunction with udev or similar userland application
+to listen for kernel uevents, which indicate that the dump is ready. Udev has
+rules to copy that file somewhere for long-term storage and analysis, as by
+default, the data for the dump is automatically cleaned up after 5 minutes.
+That data is analyzed with driver-specific tools or GDB.
+
+You can find an example implementation at:
+`drivers/media/platform/qcom/venus/core.c
+<https://elixir.bootlin.com/linux/v6.11.6/source/drivers/media/platform/qcom/venus/core.c#L30>`__
+
+**Copyright** ©2024 : Collabora
diff --git a/Documentation/process/debugging/index.rst b/Documentation/process/debugging/index.rst
new file mode 100644
index 0000000000000..10fa673f0fe3b
--- /dev/null
+++ b/Documentation/process/debugging/index.rst
@@ -0,0 +1,65 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============================================
+Debugging advice for Linux Kernel developers
+============================================
+
+.. toctree::
+   :maxdepth: 1
+
+   driver_development_debugging_guide
+   userspace_debugging_guide
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
+
+General debugging advice
+========================
+
+Depending on the issue, a different set of tools is available to track down the
+problem or even to realize whether there is one in the first place.
+
+As a first step you have to figure out what kind of issue you want to debug.
+Depending on the answer, your methodology and choice of tools may vary.
+
+Do I need to debug with limited access?
+---------------------------------------
+
+Do you have limited access to the machine or are you unable to stop the running
+execution?
+
+In this case your debugging capability depends on built-in debugging support of
+provided distribution kernel.
+The :doc:`/process/debugging/userspace_debugging_guide` provides a brief
+overview over a range of possible debugging tools in that situation. You can
+check the capability of your kernel, in most cases, by looking into config file
+within the /boot directory.
+
+Do I have root access to the system?
+------------------------------------
+
+Are you easily able to replace the module in question or to install a new
+kernel?
+
+In that case your range of available tools is a lot bigger, you can find the
+tools in the :doc:`/process/debugging/driver_development_debugging_guide`.
+
+Is timing a factor?
+-------------------
+
+It is important to understand if the problem you want to debug manifests itself
+consistently (i.e. given a set of inputs you always get the same, incorrect
+output), or inconsistently. If it manifests itself inconsistently, some timing
+factor might be at play. If inserting delays into the code does change the
+behavior, then quite likely timing is a factor.
+
+When timing does alter the outcome of the code execution using a simple
+printk() for debugging purposes may not work, a similar alternative is to use
+trace_printk() , which logs the debug messages to the trace file instead of the
+kernel log.
+
+**Copyright** ©2024 : Collabora
diff --git a/Documentation/process/debugging/userspace_debugging_guide.rst b/Documentation/process/debugging/userspace_debugging_guide.rst
new file mode 100644
index 0000000000000..db7396261e07a
--- /dev/null
+++ b/Documentation/process/debugging/userspace_debugging_guide.rst
@@ -0,0 +1,280 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==========================
+Userspace debugging advice
+==========================
+
+This document provides a brief overview of common tools to debug the Linux
+Kernel from userspace.
+For debugging advice aimed at driver developers go :doc:`here
+</process/debugging/driver_development_debugging_guide>`.
+For general debugging advice, see :doc:`general advice document
+</process/debugging/index>`.
+
+.. contents::
+    :depth: 3
+
+The following sections show you the available tools.
+
+Dynamic debug
+-------------
+
+Mechanism to filter what ends up in the kernel log by dis-/en-abling log
+messages.
+
+Prerequisite: ``CONFIG_DYNAMIC_DEBUG``
+
+Dynamic debug is only able to target:
+
+- pr_debug()
+- dev_dbg()
+- print_hex_dump_debug()
+- print_hex_dump_bytes()
+
+Therefore the usability of this tool is, as of now, quite limited as there is
+no uniform rule for adding debug prints to the codebase, resulting in a variety
+of ways these prints are implemented.
+
+Also, note that most debug statements are implemented as a variation of
+dprintk(), which have to be activated via a parameter in respective module,
+dynamic debug is unable to do that step for you.
+
+Here is one example, that enables all available pr_debug()'s within the file::
+
+  $ alias ddcmd='echo $* > /proc/dynamic_debug/control'
+  $ ddcmd '-p; file v4l2-h264.c +p'
+  $ grep =p /proc/dynamic_debug/control
+   drivers/media/v4l2-core/v4l2-h264.c:372 [v4l2_h264]print_ref_list_b =p
+   "ref_pic_list_b%u (cur_poc %u%c) %s"
+   drivers/media/v4l2-core/v4l2-h264.c:333 [v4l2_h264]print_ref_list_p =p
+   "ref_pic_list_p (cur_poc %u%c) %s\n"
+
+**When should you use this over Ftrace ?**
+
+- When the code contains one of the valid print statements (see above) or when
+  you have added multiple pr_debug() statements during development
+- When timing is not an issue, meaning if multiple pr_debug() statements in
+  the code won't cause delays
+- When you care more about receiving specific log messages than tracing the
+  pattern of how a function is called
+
+For the full documentation see :doc:`/admin-guide/dynamic-debug-howto`
+
+Ftrace
+------
+
+Prerequisite: ``CONFIG_DYNAMIC_FTRACE``
+
+This tool uses the tracefs file system for the control files and output files.
+That file system will be mounted as a ``tracing`` directory, which can be found
+in either ``/sys/kernel/`` or ``/sys/debug/kernel/``.
+
+Some of the most important operations for debugging are:
+
+- You can perform a function trace by adding a function name to the
+  ``set_ftrace_filter`` file (which accepts any function name found within the
+  ``available_filter_functions`` file) or you can specifically disable certain
+  functions by adding their names to the ``set_ftrace_notrace`` file (more info
+  at: :ref:`trace/ftrace:dynamic ftrace`).
+- In order to find out where calls originate from you can activate the
+  ``func_stack_trace`` option under ``options/func_stack_trace``.
+- Tracing the children of a function call and showing the return values are
+  possible by adding the desired function in the ``set_graph_function`` file
+  (requires config ``FUNCTION_GRAPH_RETVAL``); more info at
+  :ref:`trace/ftrace:dynamic ftrace with the function graph tracer`.
+
+For the full Ftrace documentation see :doc:`/trace/ftrace`
+
+Or you could also trace for specific events by :ref:`using event tracing
+<trace/events:2. using event tracing>`, which can be defined as described here:
+:ref:`Creating a custom Ftrace tracepoint
+<process/debugging/driver_development_debugging_guide:ftrace>`.
+
+For the full Ftrace event tracing documentation see :doc:`/trace/events`
+
+.. _read_ftrace_log:
+
+Reading the ftrace log
+~~~~~~~~~~~~~~~~~~~~~~
+
+The ``trace`` file can be read just like any other file (``cat``, ``tail``,
+``head``, ``vim``, etc.), the size of the file is limited by the
+``buffer_size_kb`` (``echo 1000 > buffer_size_kb``). The
+:ref:`trace/ftrace:trace_pipe` will behave similarly to the ``trace`` file, but
+whenever you read from the file the content is consumed.
+
+Kernelshark
+~~~~~~~~~~~
+
+A GUI interface to visualize the traces as a graph and list view from the
+output of the `trace-cmd
+<https://git.kernel.org/pub/scm/utils/trace-cmd/trace-cmd.git/>`__ application.
+
+For the full documentation see `<https://kernelshark.org/Documentation.html>`__
+
+Perf & alternatives
+-------------------
+
+The tools mentioned above provide ways to inspect kernel code, results,
+variable values, etc. Sometimes you have to find out first where to look and
+for those cases, a box of performance tracking tools can help you to frame the
+issue.
+
+Why should you do a performance analysis?
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+A performance analysis is a good first step when among other reasons:
+
+- you cannot define the issue
+- you do not know where it occurs
+- the running system should not be interrupted or it is a remote system, where
+  you cannot install a new module/kernel
+
+How to do a simple analysis with linux tools?
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+For the start of a performance analysis, you can start with the usual tools
+like:
+
+- ``top`` / ``htop`` / ``atop`` (*get an overview of the system load, see
+  spikes on specific processes*)
+- ``mpstat -P ALL`` (*look at the load distribution among CPUs*)
+- ``iostat -x`` (*observe input and output devices utilization and performance*)
+- ``vmstat`` (*overview of memory usage on the system*)
+- ``pidstat`` (*similar to* ``vmstat`` *but per process, to dial it down to the
+  target*)
+- ``strace -tp $PID`` (*once you know the process, you can figure out how it
+  communicates with the Kernel*)
+
+These should help to narrow down the areas to look at sufficiently.
+
+Diving deeper with perf
+~~~~~~~~~~~~~~~~~~~~~~~
+
+The **perf** tool provides a series of metrics and events to further dial down
+on issues.
+
+Prerequisite: build or install perf on your system
+
+Gather statistics data for finding all files starting with ``gcc`` in ``/usr``::
+
+  # perf stat -d find /usr -name 'gcc*' | wc -l
+
+   Performance counter stats for 'find /usr -name gcc*':
+
+     1277.81 msec    task-clock             #    0.997 CPUs utilized
+     9               context-switches       #    7.043 /sec
+     1               cpu-migrations         #    0.783 /sec
+     704             page-faults            #  550.943 /sec
+     766548897       cycles                 #    0.600 GHz                         (97.15%)
+     798285467       instructions           #    1.04  insn per cycle              (97.15%)
+     57582731        branches               #   45.064 M/sec                       (2.85%)
+     3842573         branch-misses          #    6.67% of all branches             (97.15%)
+     281616097       L1-dcache-loads        #  220.390 M/sec                       (97.15%)
+     4220975         L1-dcache-load-misses  #    1.50% of all L1-dcache accesses   (97.15%)
+     <not supported> LLC-loads
+     <not supported> LLC-load-misses
+
+   1.281746009 seconds time elapsed
+
+   0.508796000 seconds user
+   0.773209000 seconds sys
+
+
+  52
+
+The availability of events and metrics depends on the system you are running.
+
+For the full documentation see
+`<https://perf.wiki.kernel.org/index.php/Main_Page>`__
+
+Perfetto
+~~~~~~~~
+
+A set of tools to measure and analyze how well applications and systems perform.
+You can use it to:
+
+* identify bottlenecks
+* optimize code
+* make software run faster and more efficiently.
+
+**What is the difference between perfetto and perf?**
+
+* perf is tool as part of and specialized for the Linux Kernel and has CLI user
+  interface.
+* perfetto cross-platform performance analysis stack, has extended
+  functionality into userspace and provides a WEB user interface.
+
+For the full documentation see `<https://perfetto.dev/docs/>`__
+
+Kernel panic analysis tools
+---------------------------
+
+  To capture the crash dump please use ``Kdump`` & ``Kexec``. Below you can find
+  some advice for analysing the data.
+
+  For the full documentation see the :doc:`/admin-guide/kdump/kdump`
+
+  In order to find the corresponding line in the code you can use `faddr2line
+  <https://elixir.bootlin.com/linux/v6.11.6/source/scripts/faddr2line>`__; note
+  that you need to enable ``CONFIG_DEBUG_INFO`` for that to work.
+
+  An alternative to using ``faddr2line`` is the use of ``objdump`` (and its
+  derivatives for the different platforms like ``aarch64-linux-gnu-objdump``).
+  Take this line as an example:
+
+  ``[  +0.000240]  rkvdec_device_run+0x50/0x138 [rockchip_vdec]``.
+
+  We can find the corresponding line of code by executing::
+
+    aarch64-linux-gnu-objdump -dS drivers/staging/media/rkvdec/rockchip-vdec.ko | grep rkvdec_device_run\>: -A 40
+    0000000000000ac8 <rkvdec_device_run>:
+     ac8:	d503201f 	nop
+     acc:	d503201f 	nop
+    {
+     ad0:	d503233f 	paciasp
+     ad4:	a9bd7bfd 	stp	x29, x30, [sp, #-48]!
+     ad8:	910003fd 	mov	x29, sp
+     adc:	a90153f3 	stp	x19, x20, [sp, #16]
+     ae0:	a9025bf5 	stp	x21, x22, [sp, #32]
+        const struct rkvdec_coded_fmt_desc *desc = ctx->coded_fmt_desc;
+     ae4:	f9411814 	ldr	x20, [x0, #560]
+        struct rkvdec_dev *rkvdec = ctx->dev;
+     ae8:	f9418015 	ldr	x21, [x0, #768]
+        if (WARN_ON(!desc))
+     aec:	b4000654 	cbz	x20, bb4 <rkvdec_device_run+0xec>
+        ret = pm_runtime_resume_and_get(rkvdec->dev);
+     af0:	f943d2b6 	ldr	x22, [x21, #1952]
+        ret = __pm_runtime_resume(dev, RPM_GET_PUT);
+     af4:	aa0003f3 	mov	x19, x0
+     af8:	52800081 	mov	w1, #0x4                   	// #4
+     afc:	aa1603e0 	mov	x0, x22
+     b00:	94000000 	bl	0 <__pm_runtime_resume>
+        if (ret < 0) {
+     b04:	37f80340 	tbnz	w0, #31, b6c <rkvdec_device_run+0xa4>
+        dev_warn(rkvdec->dev, "Not good\n");
+     b08:	f943d2a0 	ldr	x0, [x21, #1952]
+     b0c:	90000001 	adrp	x1, 0 <rkvdec_try_ctrl-0x8>
+     b10:	91000021 	add	x1, x1, #0x0
+     b14:	94000000 	bl	0 <_dev_warn>
+        *bad = 1;
+     b18:	d2800001 	mov	x1, #0x0                   	// #0
+     ...
+
+  Meaning, in this line from the crash dump::
+
+    [  +0.000240]  rkvdec_device_run+0x50/0x138 [rockchip_vdec]
+
+  I can take the ``0x50`` as offset, which I have to add to the base address
+  of the corresponding function, which I find in this line::
+
+    0000000000000ac8 <rkvdec_device_run>:
+
+  The result of ``0xac8 + 0x50 = 0xb18``
+  And when I search for that address within the function I get the
+  following line::
+
+    *bad = 1;
+    b18:      d2800001        mov     x1, #0x0
+
+**Copyright** ©2024 : Collabora
diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst
index 6455eba3ef0c5..aa12f26601949 100644
--- a/Documentation/process/index.rst
+++ b/Documentation/process/index.rst
@@ -72,13 +72,15 @@ beyond).
 Dealing with bugs
 -----------------
 
-Bugs are a fact of life; it is important that we handle them properly.
-The documents below describe our policies around the handling of a couple
-of special classes of bugs: regressions and security problems.
+Bugs are a fact of life; it is important that we handle them properly. The
+documents below provide general advice about debugging and describe our
+policies around the handling of a couple of special classes of bugs:
+regressions and security problems.
 
 .. toctree::
    :maxdepth: 1
 
+   debugging/index
    handling-regressions
    security-bugs
    cve

From 83a474c11e8cb59e230a43365cb42fa00d3bddaa Mon Sep 17 00:00:00 2001
From: Sebastian Fricke <sebastian.fricke@collabora.com>
Date: Mon, 18 Nov 2024 08:03:51 +0100
Subject: [PATCH 1331/1530] docs: Add debugging guide for the media subsystem

Provide a guide for developers on how to debug code with a focus on the
media subsystem. This document aims to provide a rough overview over the
possibilities and a rational to help choosing the right tool for the
given circumstances.

Signed-off-by: Sebastian Fricke <sebastian.fricke@collabora.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20241028-media_docs_improve_v3-v3-2-edf5c5b3746f@collabora.com
---
 Documentation/admin-guide/media/index.rst     |   5 +
 Documentation/process/debugging/index.rst     |  13 ++
 .../media_specific_debugging_guide.rst        | 180 ++++++++++++++++++
 3 files changed, 198 insertions(+)
 create mode 100644 Documentation/process/debugging/media_specific_debugging_guide.rst

diff --git a/Documentation/admin-guide/media/index.rst b/Documentation/admin-guide/media/index.rst
index be7e0e4482ca5..b11737ae6c046 100644
--- a/Documentation/admin-guide/media/index.rst
+++ b/Documentation/admin-guide/media/index.rst
@@ -20,6 +20,11 @@ Documentation/driver-api/media/index.rst
   - for driver development information and Kernel APIs used by
     media devices;
 
+Documentation/process/debugging/media_specific_debugging_guide.rst
+
+  - for advice about essential tools and techniques to debug drivers on this
+    subsystem
+
 .. toctree::
 	:caption: Table of Contents
 	:maxdepth: 2
diff --git a/Documentation/process/debugging/index.rst b/Documentation/process/debugging/index.rst
index 10fa673f0fe3b..f6e4a00dfee32 100644
--- a/Documentation/process/debugging/index.rst
+++ b/Documentation/process/debugging/index.rst
@@ -4,12 +4,25 @@
 Debugging advice for Linux Kernel developers
 ============================================
 
+general guides
+--------------
+
 .. toctree::
    :maxdepth: 1
 
    driver_development_debugging_guide
    userspace_debugging_guide
 
+.. only::  subproject and html
+
+subsystem specific guides
+-------------------------
+
+.. toctree::
+   :maxdepth: 1
+
+   media_specific_debugging_guide
+
 .. only::  subproject and html
 
    Indices
diff --git a/Documentation/process/debugging/media_specific_debugging_guide.rst b/Documentation/process/debugging/media_specific_debugging_guide.rst
new file mode 100644
index 0000000000000..c5a93bafaf675
--- /dev/null
+++ b/Documentation/process/debugging/media_specific_debugging_guide.rst
@@ -0,0 +1,180 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============================================
+Debugging and tracing in the media subsystem
+============================================
+
+This document serves as a starting point and lookup for debugging device
+drivers in the media subsystem and to debug these drivers from userspace.
+
+.. contents::
+    :depth: 3
+
+General debugging advice
+------------------------
+
+For general advice see the :doc:`general advice document
+</process/debugging/index>`.
+
+The following sections show you some of the available tools.
+
+dev_debug module parameter
+--------------------------
+
+Every video device provides a ``dev_debug`` parameter, which allows to get
+further insights into the IOCTLs in the background.::
+
+  # cat /sys/class/video4linux/video3/name
+  rkvdec
+  # echo 0xff > /sys/class/video4linux/video3/dev_debug
+  # dmesg -wH
+  [...] videodev: v4l2_open: video3: open (0)
+  [  +0.000036] video3: VIDIOC_QUERYCAP: driver=rkvdec, card=rkvdec,
+  bus=platform:rkvdec, version=0x00060900, capabilities=0x84204000,
+  device_caps=0x04204000
+
+For the full documentation see :ref:`driver-api/media/v4l2-dev:video device
+debugging`
+
+dev_dbg() / v4l2_dbg()
+----------------------
+
+Two debug print statements, which are specific for devices and for the v4l2
+subsystem, avoid adding these to your final submission unless they have
+long-term value for investigations.
+
+For a general overview please see the
+:ref:`process/debugging/driver_development_debugging_guide:printk() & friends`
+guide.
+
+- Difference between both?
+
+  - v4l2_dbg() utilizes v4l2_printk() under the hood, which further uses
+    printk() directly, thus it cannot be targeted by dynamic debug
+  - dev_dbg() can be targeted by dynamic debug
+  - v4l2_dbg() has a more specific prefix format for the media subsystem, while
+    dev_dbg only highlights the driver name and the location of the log
+
+Dynamic debug
+-------------
+
+A method to trim down the debug output to your needs.
+
+For general advice see the
+:ref:`process/debugging/userspace_debugging_guide:dynamic debug` guide.
+
+Here is one example, that enables all available pr_debug()'s within the file::
+
+  $ alias ddcmd='echo $* > /proc/dynamic_debug/control'
+  $ ddcmd '-p; file v4l2-h264.c +p'
+  $ grep =p /proc/dynamic_debug/control
+   drivers/media/v4l2-core/v4l2-h264.c:372 [v4l2_h264]print_ref_list_b =p
+   "ref_pic_list_b%u (cur_poc %u%c) %s"
+   drivers/media/v4l2-core/v4l2-h264.c:333 [v4l2_h264]print_ref_list_p =p
+   "ref_pic_list_p (cur_poc %u%c) %s\n"
+
+Ftrace
+------
+
+An internal kernel tracer that can trace static predefined events, function
+calls, etc. Very useful for debugging problems without changing the kernel and
+understanding the behavior of subsystems.
+
+For general advice see the
+:ref:`process/debugging/userspace_debugging_guide:ftrace` guide.
+
+DebugFS
+-------
+
+This tool allows you to dump or modify internal values of your driver to files
+in a custom filesystem.
+
+For general advice see the
+:ref:`process/debugging/driver_development_debugging_guide:debugfs` guide.
+
+Perf & alternatives
+-------------------
+
+Tools to measure the various stats on a running system to diagnose issues.
+
+For general advice see the
+:ref:`process/debugging/userspace_debugging_guide:perf & alternatives` guide.
+
+Example for media devices:
+
+Gather statistics data for a decoding job: (This example is on a RK3399 SoC
+with the rkvdec codec driver using the `fluster test suite
+<https://github.com/fluendo/fluster>`__)::
+
+  perf stat -d python3 fluster.py run -d GStreamer-H.264-V4L2SL-Gst1.0 -ts
+  JVT-AVC_V1 -tv AUD_MW_E -j1
+  ...
+  Performance counter stats for 'python3 fluster.py run -d
+  GStreamer-H.264-V4L2SL-Gst1.0 -ts JVT-AVC_V1 -tv AUD_MW_E -j1 -v':
+
+         7794.23 msec task-clock:u                     #    0.697 CPUs utilized
+               0      context-switches:u               #    0.000 /sec
+               0      cpu-migrations:u                 #    0.000 /sec
+           11901      page-faults:u                    #    1.527 K/sec
+       882671556      cycles:u                         #    0.113 GHz                         (95.79%)
+       711708695      instructions:u                   #    0.81  insn per cycle              (95.79%)
+        10581935      branches:u                       #    1.358 M/sec                       (15.13%)
+         6871144      branch-misses:u                  #   64.93% of all branches             (95.79%)
+       281716547      L1-dcache-loads:u                #   36.144 M/sec                       (95.79%)
+         9019581      L1-dcache-load-misses:u          #    3.20% of all L1-dcache accesses   (95.79%)
+ <not supported>      LLC-loads:u
+ <not supported>      LLC-load-misses:u
+
+    11.180830431 seconds time elapsed
+
+     1.502318000 seconds user
+     6.377221000 seconds sys
+
+The availability of events and metrics depends on the system you are running.
+
+Error checking & panic analysis
+-------------------------------
+
+Various Kernel configuration options to enhance error detection of the Linux
+Kernel with the cost of lowering performance.
+
+For general advice see the
+:ref:`process/debugging/driver_development_debugging_guide:kasan, ubsan,
+lockdep and other error checkers` guide.
+
+Driver verification with v4l2-compliance
+----------------------------------------
+
+To verify, that a driver adheres to the v4l2 API, the tool v4l2-compliance is
+used, which is part of the `v4l_utils
+<https://git.linuxtv.org/v4l-utils.git>`__, a suite of userspace tools to work
+with the media subsystem.
+
+To see the detailed media topology (and check it) use::
+
+  v4l2-compliance -M /dev/mediaX --verbose
+
+You can also run a full compliance check for all devices referenced in the
+media topology with::
+
+  v4l2-compliance -m /dev/mediaX
+
+Debugging problems with receiving video
+---------------------------------------
+
+Implementing vidioc_log_status in the driver: this can log the current status
+to the kernel log. It's called by v4l2-ctl --log-status. Very useful for
+debugging problems with receiving video (TV/S-Video/HDMI/etc) since the video
+signal is external (so unpredictable). Less useful with camera sensor inputs
+since you have control over what the camera sensor does.
+
+Usually you can just assign the default::
+
+  .vidioc_log_status  = v4l2_ctrl_log_status,
+
+But you can also create your own callback, to create a custom status log.
+
+You can find an example in the cobalt driver
+(`drivers/media/pci/cobalt/cobalt-v4l2.c <https://elixir.bootlin.com/linux/v6.11.6/source/drivers/media/pci/cobalt/cobalt-v4l2.c#L567>`__).
+
+**Copyright** ©2024 : Collabora

From 64214c2b95364d26cdff045d8bbefd37380edbe1 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 14 Nov 2024 15:55:30 -0400
Subject: [PATCH 1332/1530] iommu: Add ops->domain_alloc_nested()

It turns out all the drivers that are using this immediately call into
another function, so just make that function directly into the op. This
makes paging=NULL for domain_alloc_user and we can remove the argument in
the next patch.

The function mirrors the similar op in the viommu that allocates a nested
domain on top of the viommu's nesting parent. This version supports cases
where a viommu is not being used.

Link: https://patch.msgid.link/r/1-v1-c252ebdeb57b+329-iommu_paging_flags_jgg@nvidia.com
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/intel/iommu.c          |  9 +++------
 drivers/iommu/intel/iommu.h          |  6 ++++--
 drivers/iommu/intel/nested.c         | 11 +++++++++--
 drivers/iommu/iommufd/hw_pagetable.c |  8 ++++----
 drivers/iommu/iommufd/selftest.c     |  7 ++++---
 include/linux/iommu.h                |  9 +++++----
 6 files changed, 29 insertions(+), 21 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 527f6f89d8a1f..6f11a075114f7 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3340,12 +3340,8 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 	struct iommu_domain *domain;
 	bool first_stage;
 
-	/* Must be NESTING domain */
-	if (parent) {
-		if (!nested_supported(iommu) || flags)
-			return ERR_PTR(-EOPNOTSUPP);
-		return intel_nested_domain_alloc(parent, user_data);
-	}
+	if (parent)
+		return ERR_PTR(-EOPNOTSUPP);
 
 	if (flags &
 	    (~(IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING
@@ -4475,6 +4471,7 @@ const struct iommu_ops intel_iommu_ops = {
 	.domain_alloc_user	= intel_iommu_domain_alloc_user,
 	.domain_alloc_sva	= intel_svm_domain_alloc,
 	.domain_alloc_paging	= intel_iommu_domain_alloc_paging,
+	.domain_alloc_nested	= intel_iommu_domain_alloc_nested,
 	.probe_device		= intel_iommu_probe_device,
 	.release_device		= intel_iommu_release_device,
 	.get_resv_regions	= intel_iommu_get_resv_regions,
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 2cca094c259dc..6ea7bbe26b19d 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -1265,8 +1265,10 @@ int __domain_setup_first_level(struct intel_iommu *iommu,
 int dmar_ir_support(void);
 
 void iommu_flush_write_buffer(struct intel_iommu *iommu);
-struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
-					       const struct iommu_user_data *user_data);
+struct iommu_domain *
+intel_iommu_domain_alloc_nested(struct device *dev, struct iommu_domain *parent,
+				u32 flags,
+				const struct iommu_user_data *user_data);
 struct device *device_rbtree_find(struct intel_iommu *iommu, u16 rid);
 
 enum cache_tag_type {
diff --git a/drivers/iommu/intel/nested.c b/drivers/iommu/intel/nested.c
index 42c4533a6ea21..aba92c00b4274 100644
--- a/drivers/iommu/intel/nested.c
+++ b/drivers/iommu/intel/nested.c
@@ -186,14 +186,21 @@ static const struct iommu_domain_ops intel_nested_domain_ops = {
 	.cache_invalidate_user	= intel_nested_cache_invalidate_user,
 };
 
-struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
-					       const struct iommu_user_data *user_data)
+struct iommu_domain *
+intel_iommu_domain_alloc_nested(struct device *dev, struct iommu_domain *parent,
+				u32 flags,
+				const struct iommu_user_data *user_data)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct dmar_domain *s2_domain = to_dmar_domain(parent);
+	struct intel_iommu *iommu = info->iommu;
 	struct iommu_hwpt_vtd_s1 vtd;
 	struct dmar_domain *domain;
 	int ret;
 
+	if (!nested_supported(iommu) || flags)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	/* Must be nested domain */
 	if (user_data->type != IOMMU_HWPT_DATA_VTD_S1)
 		return ERR_PTR(-EOPNOTSUPP);
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index 9236e8ca9aa86..ec3c64a8c7963 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -227,7 +227,7 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
 	int rc;
 
 	if ((flags & ~IOMMU_HWPT_FAULT_ID_VALID) ||
-	    !user_data->len || !ops->domain_alloc_user)
+	    !user_data->len || !ops->domain_alloc_nested)
 		return ERR_PTR(-EOPNOTSUPP);
 	if (parent->auto_domain || !parent->nest_parent ||
 	    parent->common.domain->owner != ops)
@@ -242,9 +242,9 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
 	refcount_inc(&parent->common.obj.users);
 	hwpt_nested->parent = parent;
 
-	hwpt->domain = ops->domain_alloc_user(idev->dev,
-					      flags & ~IOMMU_HWPT_FAULT_ID_VALID,
-					      parent->common.domain, user_data);
+	hwpt->domain = ops->domain_alloc_nested(
+		idev->dev, parent->common.domain,
+		flags & ~IOMMU_HWPT_FAULT_ID_VALID, user_data);
 	if (IS_ERR(hwpt->domain)) {
 		rc = PTR_ERR(hwpt->domain);
 		hwpt->domain = NULL;
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index 2f9de177dffc7..c58083c3660ae 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -356,8 +356,8 @@ __mock_domain_alloc_nested(const struct iommu_user_data *user_data)
 }
 
 static struct iommu_domain *
-mock_domain_alloc_nested(struct iommu_domain *parent, u32 flags,
-			 const struct iommu_user_data *user_data)
+mock_domain_alloc_nested(struct device *dev, struct iommu_domain *parent,
+			 u32 flags, const struct iommu_user_data *user_data)
 {
 	struct mock_iommu_domain_nested *mock_nested;
 	struct mock_iommu_domain *mock_parent;
@@ -391,7 +391,7 @@ mock_domain_alloc_user(struct device *dev, u32 flags,
 	struct iommu_domain *domain;
 
 	if (parent)
-		return mock_domain_alloc_nested(parent, flags, user_data);
+		return ERR_PTR(-EOPNOTSUPP);
 
 	if (user_data)
 		return ERR_PTR(-EOPNOTSUPP);
@@ -719,6 +719,7 @@ static const struct iommu_ops mock_ops = {
 	.hw_info = mock_domain_hw_info,
 	.domain_alloc_paging = mock_domain_alloc_paging,
 	.domain_alloc_user = mock_domain_alloc_user,
+	.domain_alloc_nested = mock_domain_alloc_nested,
 	.capable = mock_domain_capable,
 	.device_group = generic_device_group,
 	.probe_device = mock_probe_device,
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index d6aaaec3caf46..0472cc1245192 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -559,15 +559,13 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size,
  *                the caller iommu_domain_alloc() returns.
  * @domain_alloc_user: Allocate an iommu domain corresponding to the input
  *                     parameters as defined in include/uapi/linux/iommufd.h.
- *                     Upon success, if the @user_data is valid and the @parent
- *                     points to a kernel-managed domain, the new domain must be
- *                     IOMMU_DOMAIN_NESTED type; otherwise, the @parent must be
- *                     NULL while the @user_data can be optionally provided, the
+ *                     The @user_data can be optionally provided, the
  *                     new domain must support __IOMMU_DOMAIN_PAGING.
  *                     Upon failure, ERR_PTR must be returned.
  * @domain_alloc_paging: Allocate an iommu_domain that can be used for
  *                       UNMANAGED, DMA, and DMA_FQ domain types.
  * @domain_alloc_sva: Allocate an iommu_domain for Shared Virtual Addressing.
+ * @domain_alloc_nested: Allocate an iommu_domain for nested translation.
  * @probe_device: Add device to iommu driver handling
  * @release_device: Remove device from iommu driver handling
  * @probe_finalize: Do final setup work after the device is added to an IOMMU
@@ -622,6 +620,9 @@ struct iommu_ops {
 	struct iommu_domain *(*domain_alloc_paging)(struct device *dev);
 	struct iommu_domain *(*domain_alloc_sva)(struct device *dev,
 						 struct mm_struct *mm);
+	struct iommu_domain *(*domain_alloc_nested)(
+		struct device *dev, struct iommu_domain *parent, u32 flags,
+		const struct iommu_user_data *user_data);
 
 	struct iommu_device *(*probe_device)(struct device *dev);
 	void (*release_device)(struct device *dev);

From d53764723ecd639a0cc0c5ad24146847fc09f78d Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 14 Nov 2024 15:55:31 -0400
Subject: [PATCH 1333/1530] iommu: Rename ops->domain_alloc_user() to
 domain_alloc_paging_flags()

Now that the main domain allocating path is calling this function it
doesn't make sense to leave it named _user. Change the name to
alloc_paging_flags() to mirror the new iommu_paging_domain_alloc_flags()
function.

A driver should implement only one of ops->domain_alloc_paging() or
ops->domain_alloc_paging_flags(). The former is a simpler interface with
less boiler plate that the majority of drivers use. The latter is for
drivers with a greater feature set (PASID, multiple page table support,
advanced iommufd support, nesting, etc). Additional patches will be needed
to achieve this.

Link: https://patch.msgid.link/r/2-v1-c252ebdeb57b+329-iommu_paging_flags_jgg@nvidia.com
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/amd/iommu.c                   |  9 ++++-----
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c |  9 ++++-----
 drivers/iommu/intel/iommu.c                 | 10 +++-------
 drivers/iommu/iommu.c                       |  4 ++--
 drivers/iommu/iommufd/hw_pagetable.c        |  8 ++++----
 drivers/iommu/iommufd/selftest.c            | 10 +++-------
 include/linux/iommu.h                       | 20 ++++++++++++--------
 7 files changed, 32 insertions(+), 38 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 5ce8e6504ba7e..3f691e1fd22ce 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2407,9 +2407,8 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned int type)
 }
 
 static struct iommu_domain *
-amd_iommu_domain_alloc_user(struct device *dev, u32 flags,
-			    struct iommu_domain *parent,
-			    const struct iommu_user_data *user_data)
+amd_iommu_domain_alloc_paging_flags(struct device *dev, u32 flags,
+				    const struct iommu_user_data *user_data)
 
 {
 	unsigned int type = IOMMU_DOMAIN_UNMANAGED;
@@ -2420,7 +2419,7 @@ amd_iommu_domain_alloc_user(struct device *dev, u32 flags,
 	if (dev)
 		iommu = get_amd_iommu_from_dev(dev);
 
-	if ((flags & ~supported_flags) || parent || user_data)
+	if ((flags & ~supported_flags) || user_data)
 		return ERR_PTR(-EOPNOTSUPP);
 
 	/* Allocate domain with v2 page table if IOMMU supports PASID. */
@@ -2884,7 +2883,7 @@ const struct iommu_ops amd_iommu_ops = {
 	.release_domain = &release_domain,
 	.identity_domain = &identity_domain.domain,
 	.domain_alloc = amd_iommu_domain_alloc,
-	.domain_alloc_user = amd_iommu_domain_alloc_user,
+	.domain_alloc_paging_flags = amd_iommu_domain_alloc_paging_flags,
 	.domain_alloc_sva = amd_iommu_domain_alloc_sva,
 	.probe_device = amd_iommu_probe_device,
 	.release_device = amd_iommu_release_device,
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 04630dbfedd92..e4ebd9e12ad46 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -3132,9 +3132,8 @@ static struct iommu_domain arm_smmu_blocked_domain = {
 };
 
 static struct iommu_domain *
-arm_smmu_domain_alloc_user(struct device *dev, u32 flags,
-			   struct iommu_domain *parent,
-			   const struct iommu_user_data *user_data)
+arm_smmu_domain_alloc_paging_flags(struct device *dev, u32 flags,
+				   const struct iommu_user_data *user_data)
 {
 	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
 	const u32 PAGING_FLAGS = IOMMU_HWPT_ALLOC_DIRTY_TRACKING |
@@ -3145,7 +3144,7 @@ arm_smmu_domain_alloc_user(struct device *dev, u32 flags,
 
 	if (flags & ~PAGING_FLAGS)
 		return ERR_PTR(-EOPNOTSUPP);
-	if (parent || user_data)
+	if (user_data)
 		return ERR_PTR(-EOPNOTSUPP);
 
 	if (flags & IOMMU_HWPT_ALLOC_PASID)
@@ -3546,7 +3545,7 @@ static struct iommu_ops arm_smmu_ops = {
 	.hw_info		= arm_smmu_hw_info,
 	.domain_alloc_paging    = arm_smmu_domain_alloc_paging,
 	.domain_alloc_sva       = arm_smmu_sva_domain_alloc,
-	.domain_alloc_user	= arm_smmu_domain_alloc_user,
+	.domain_alloc_paging_flags = arm_smmu_domain_alloc_paging_flags,
 	.probe_device		= arm_smmu_probe_device,
 	.release_device		= arm_smmu_release_device,
 	.device_group		= arm_smmu_device_group,
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 6f11a075114f7..7d0acb74d5a54 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3328,9 +3328,8 @@ static struct dmar_domain *paging_domain_alloc(struct device *dev, bool first_st
 }
 
 static struct iommu_domain *
-intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
-			      struct iommu_domain *parent,
-			      const struct iommu_user_data *user_data)
+intel_iommu_domain_alloc_paging_flags(struct device *dev, u32 flags,
+				      const struct iommu_user_data *user_data)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	bool dirty_tracking = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
@@ -3340,9 +3339,6 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 	struct iommu_domain *domain;
 	bool first_stage;
 
-	if (parent)
-		return ERR_PTR(-EOPNOTSUPP);
-
 	if (flags &
 	    (~(IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING
 	       | IOMMU_HWPT_FAULT_ID_VALID)))
@@ -4468,7 +4464,7 @@ const struct iommu_ops intel_iommu_ops = {
 	.identity_domain	= &identity_domain,
 	.capable		= intel_iommu_capable,
 	.hw_info		= intel_iommu_hw_info,
-	.domain_alloc_user	= intel_iommu_domain_alloc_user,
+	.domain_alloc_paging_flags = intel_iommu_domain_alloc_paging_flags,
 	.domain_alloc_sva	= intel_svm_domain_alloc,
 	.domain_alloc_paging	= intel_iommu_domain_alloc_paging,
 	.domain_alloc_nested	= intel_iommu_domain_alloc_nested,
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 7618e9c65d3fa..9bc0c74cca3c7 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1987,8 +1987,8 @@ __iommu_paging_domain_alloc_flags(struct device *dev, unsigned int type,
 
 	if (ops->domain_alloc_paging && !flags)
 		domain = ops->domain_alloc_paging(dev);
-	else if (ops->domain_alloc_user)
-		domain = ops->domain_alloc_user(dev, flags, NULL, NULL);
+	else if (ops->domain_alloc_paging_flags)
+		domain = ops->domain_alloc_paging_flags(dev, flags, NULL);
 	else if (ops->domain_alloc && !flags)
 		domain = ops->domain_alloc(IOMMU_DOMAIN_UNMANAGED);
 	else
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index ec3c64a8c7963..ce03c38046515 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -119,7 +119,7 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 
 	lockdep_assert_held(&ioas->mutex);
 
-	if ((flags || user_data) && !ops->domain_alloc_user)
+	if ((flags || user_data) && !ops->domain_alloc_paging_flags)
 		return ERR_PTR(-EOPNOTSUPP);
 	if (flags & ~valid_flags)
 		return ERR_PTR(-EOPNOTSUPP);
@@ -139,9 +139,9 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 	hwpt_paging->ioas = ioas;
 	hwpt_paging->nest_parent = flags & IOMMU_HWPT_ALLOC_NEST_PARENT;
 
-	if (ops->domain_alloc_user) {
-		hwpt->domain = ops->domain_alloc_user(idev->dev, flags, NULL,
-						      user_data);
+	if (ops->domain_alloc_paging_flags) {
+		hwpt->domain = ops->domain_alloc_paging_flags(idev->dev, flags,
+							      user_data);
 		if (IS_ERR(hwpt->domain)) {
 			rc = PTR_ERR(hwpt->domain);
 			hwpt->domain = NULL;
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index c58083c3660ae..a0de6d6d4e689 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -379,9 +379,8 @@ mock_domain_alloc_nested(struct device *dev, struct iommu_domain *parent,
 }
 
 static struct iommu_domain *
-mock_domain_alloc_user(struct device *dev, u32 flags,
-		       struct iommu_domain *parent,
-		       const struct iommu_user_data *user_data)
+mock_domain_alloc_paging_flags(struct device *dev, u32 flags,
+			       const struct iommu_user_data *user_data)
 {
 	bool has_dirty_flag = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
 	const u32 PAGING_FLAGS = IOMMU_HWPT_ALLOC_DIRTY_TRACKING |
@@ -390,9 +389,6 @@ mock_domain_alloc_user(struct device *dev, u32 flags,
 			    MOCK_FLAGS_DEVICE_NO_DIRTY;
 	struct iommu_domain *domain;
 
-	if (parent)
-		return ERR_PTR(-EOPNOTSUPP);
-
 	if (user_data)
 		return ERR_PTR(-EOPNOTSUPP);
 	if ((flags & ~PAGING_FLAGS) || (has_dirty_flag && no_dirty_ops))
@@ -718,7 +714,7 @@ static const struct iommu_ops mock_ops = {
 	.pgsize_bitmap = MOCK_IO_PAGE_SIZE,
 	.hw_info = mock_domain_hw_info,
 	.domain_alloc_paging = mock_domain_alloc_paging,
-	.domain_alloc_user = mock_domain_alloc_user,
+	.domain_alloc_paging_flags = mock_domain_alloc_paging_flags,
 	.domain_alloc_nested = mock_domain_alloc_nested,
 	.capable = mock_domain_capable,
 	.device_group = generic_device_group,
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 0472cc1245192..1e3308e899969 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -557,13 +557,17 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size,
  * @domain_alloc: allocate and return an iommu domain if success. Otherwise
  *                NULL is returned. The domain is not fully initialized until
  *                the caller iommu_domain_alloc() returns.
- * @domain_alloc_user: Allocate an iommu domain corresponding to the input
- *                     parameters as defined in include/uapi/linux/iommufd.h.
- *                     The @user_data can be optionally provided, the
- *                     new domain must support __IOMMU_DOMAIN_PAGING.
- *                     Upon failure, ERR_PTR must be returned.
+ * @domain_alloc_paging_flags: Allocate an iommu domain corresponding to the
+ *                     input parameters as defined in
+ *                     include/uapi/linux/iommufd.h. The @user_data can be
+ *                     optionally provided, the new domain must support
+ *                     __IOMMU_DOMAIN_PAGING. Upon failure, ERR_PTR must be
+ *                     returned.
  * @domain_alloc_paging: Allocate an iommu_domain that can be used for
- *                       UNMANAGED, DMA, and DMA_FQ domain types.
+ *                       UNMANAGED, DMA, and DMA_FQ domain types. This is the
+ *                       same as invoking domain_alloc_paging_flags() with
+ *                       @flags=0, @user_data=NULL. A driver should implement
+ *                       only one of the two ops.
  * @domain_alloc_sva: Allocate an iommu_domain for Shared Virtual Addressing.
  * @domain_alloc_nested: Allocate an iommu_domain for nested translation.
  * @probe_device: Add device to iommu driver handling
@@ -614,8 +618,8 @@ struct iommu_ops {
 
 	/* Domain allocation and freeing by the iommu driver */
 	struct iommu_domain *(*domain_alloc)(unsigned iommu_domain_type);
-	struct iommu_domain *(*domain_alloc_user)(
-		struct device *dev, u32 flags, struct iommu_domain *parent,
+	struct iommu_domain *(*domain_alloc_paging_flags)(
+		struct device *dev, u32 flags,
 		const struct iommu_user_data *user_data);
 	struct iommu_domain *(*domain_alloc_paging)(struct device *dev);
 	struct iommu_domain *(*domain_alloc_sva)(struct device *dev,

From 82f250ed1a1dcde0ad2a1513f85af7f9514635e8 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sat, 16 Nov 2024 10:58:24 +0100
Subject: [PATCH 1334/1530] ACPI: x86: Add skip i2c clients quirk for Acer
 Iconia One 8 A1-840

The Acer Iconia One 8 A1-840 (not to be confused with the A1-840FHD which
is a different model) ships with Android 4.4 as factory OS and has the
usual broken DSDT issues for x86 Android tablets.

Add quirks to skip ACPI I2C client enumeration and disable ACPI battery/AC
and ACPI GPIO event handlers.

Also add the "INT33F5" HID for the TI PMIC used on this tablet to the list
of HIDs for which not to skip i2c_client instantiation, since we do want
an ACPI instantiated i2c_client for the PMIC.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://patch.msgid.link/20241116095825.11660-1-hdegoede@redhat.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/x86/utils.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index 423565c31d5ef..1bb425b78032a 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -308,6 +308,18 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = {
 					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY |
 					ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS),
 	},
+	{
+		/* Acer Iconia One 8 A1-840 (non FHD version) */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Insyde"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "BayTrail"),
+			/* Above strings are too generic also match BIOS date */
+			DMI_MATCH(DMI_BIOS_DATE, "04/01/2014"),
+		},
+		.driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS |
+					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY |
+					ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS),
+	},
 	{
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
@@ -425,6 +437,7 @@ static const struct acpi_device_id i2c_acpi_known_good_ids[] = {
 	{ "10EC5640", 0 }, /* RealTek ALC5640 audio codec */
 	{ "10EC5651", 0 }, /* RealTek ALC5651 audio codec */
 	{ "INT33F4", 0 },  /* X-Powers AXP288 PMIC */
+	{ "INT33F5", 0 },  /* TI Dollar Cove PMIC */
 	{ "INT33FD", 0 },  /* Intel Crystal Cove PMIC */
 	{ "INT34D3", 0 },  /* Intel Whiskey Cove PMIC */
 	{ "NPCE69A", 0 },  /* Asus Transformer keyboard dock */

From bd8aa15848f5f21951cd0b0d01510b3ad1f777d4 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sat, 16 Nov 2024 10:58:25 +0100
Subject: [PATCH 1335/1530] ACPI: x86: Clean up Asus entries in
 acpi_quirk_skip_dmi_ids[]

The Asus entries in the acpi_quirk_skip_dmi_ids[] table are the only
entries without a comment which model they apply to. Add these comments.

The Asus TF103C entry also is in the wrong place for what is supposed to
be an alphabetically sorted list. Move it up so that the list is properly
sorted and add a comment that the list is alphabetically sorted.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://patch.msgid.link/20241116095825.11660-2-hdegoede@redhat.com
[ rjw: Changelog and subject edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/x86/utils.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index 1bb425b78032a..cb45ef5240dab 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -296,6 +296,7 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = {
 	/*
 	 * 2. Devices which also have the skip i2c/serdev quirks and which
 	 *    need the x86-android-tablets module to properly work.
+	 *    Sorted alphabetically.
 	 */
 #if IS_ENABLED(CONFIG_X86_ANDROID_TABLETS)
 	{
@@ -321,6 +322,7 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = {
 					ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS),
 	},
 	{
+		/* Asus ME176C tablet */
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "ME176C"),
@@ -331,23 +333,24 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = {
 					ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS),
 	},
 	{
-		/* Lenovo Yoga Book X90F/L */
+		/* Asus TF103C transformer 2-in-1 */
 		.matches = {
-			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
-			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"),
-			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "YETI-11"),
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TF103C"),
 		},
 		.driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS |
-					ACPI_QUIRK_UART1_SKIP |
 					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY |
 					ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS),
 	},
 	{
+		/* Lenovo Yoga Book X90F/L */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "TF103C"),
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "YETI-11"),
 		},
 		.driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS |
+					ACPI_QUIRK_UART1_SKIP |
 					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY |
 					ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS),
 	},

From 9d8a2b033db179bef9b6b5bad492f611a0fe89b7 Mon Sep 17 00:00:00 2001
From: Miao Wang <shankerwangmiao@gmail.com>
Date: Thu, 21 Nov 2024 22:25:21 +0800
Subject: [PATCH 1336/1530] ACPI: introduce acpi_arch_init()

To avoid arch-specific code in general ACPI initialization flow,
introduce a weak symbol acpi_arch_init().

Currently, arm64 and riscv can utillize this to insert their
arch-specific flow.

In the future, other architectures can also have a chance to define
their own arch-specific ACPI initialization process if necessary.

Reviewed-by: Sunil V L <sunilvl@ventanamicro.com>
Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Acked-by: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Miao Wang <shankerwangmiao@gmail.com>
Link: https://patch.msgid.link/20241121-intro-acpi-arch-init-v4-1-b1fb517e7d8b@gmail.com
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/arm64/init.c |  2 +-
 drivers/acpi/bus.c        |  5 +++--
 drivers/acpi/riscv/init.c |  2 +-
 include/linux/acpi.h      | 12 +-----------
 4 files changed, 6 insertions(+), 15 deletions(-)

diff --git a/drivers/acpi/arm64/init.c b/drivers/acpi/arm64/init.c
index d0c8aed90fd16..7a47d8095a7dd 100644
--- a/drivers/acpi/arm64/init.c
+++ b/drivers/acpi/arm64/init.c
@@ -2,7 +2,7 @@
 #include <linux/acpi.h>
 #include "init.h"
 
-void __init acpi_arm_init(void)
+void __init acpi_arch_init(void)
 {
 	if (IS_ENABLED(CONFIG_ACPI_AGDI))
 		acpi_agdi_init();
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 16917dc3ad604..058910af82bca 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -1434,6 +1434,8 @@ static int __init acpi_bus_init(void)
 struct kobject *acpi_kobj;
 EXPORT_SYMBOL_GPL(acpi_kobj);
 
+void __weak __init acpi_arch_init(void) { }
+
 static int __init acpi_init(void)
 {
 	int result;
@@ -1461,8 +1463,7 @@ static int __init acpi_init(void)
 	acpi_viot_early_init();
 	acpi_hest_init();
 	acpi_ghes_init();
-	acpi_arm_init();
-	acpi_riscv_init();
+	acpi_arch_init();
 	acpi_scan_init();
 	acpi_ec_init();
 	acpi_debugfs_init();
diff --git a/drivers/acpi/riscv/init.c b/drivers/acpi/riscv/init.c
index 5ef97905a7275..673e4d5dd7527 100644
--- a/drivers/acpi/riscv/init.c
+++ b/drivers/acpi/riscv/init.c
@@ -7,7 +7,7 @@
 #include <linux/acpi.h>
 #include "init.h"
 
-void __init acpi_riscv_init(void)
+void __init acpi_arch_init(void)
 {
 	riscv_acpi_init_gsi_mapping();
 }
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 7dd24acd9ffee..05f39fbfa4856 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -1530,17 +1530,7 @@ static inline int find_acpi_cpu_topology_hetero_id(unsigned int cpu)
 }
 #endif
 
-#ifdef CONFIG_ARM64
-void acpi_arm_init(void);
-#else
-static inline void acpi_arm_init(void) { }
-#endif
-
-#ifdef CONFIG_RISCV
-void acpi_riscv_init(void);
-#else
-static inline void acpi_riscv_init(void) { }
-#endif
+void acpi_arch_init(void);
 
 #ifdef CONFIG_ACPI_PCC
 void acpi_init_pcc(void);

From fc26637d70d3f1ba9df8cd0f7c22b8b331c564e7 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Sun, 17 Nov 2024 21:26:38 -0800
Subject: [PATCH 1337/1530] perf test: Correct hwmon test PMU detection

Use name to avoid potential other hwmon PMUs.

Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20241118052638.754981-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/hwmon_pmu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c
index 9f44093f18df2..1e5f93aaaf5f9 100644
--- a/tools/perf/tests/hwmon_pmu.c
+++ b/tools/perf/tests/hwmon_pmu.c
@@ -173,7 +173,8 @@ static int do_test(size_t i, bool with_pmu, bool with_alias)
 	}
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (!perf_pmu__is_hwmon(evsel->pmu))
+		if (!evsel->pmu || !evsel->pmu->name ||
+		    strcmp(evsel->pmu->name, "hwmon_a_test_hwmon_pmu"))
 			continue;
 
 		if (evsel->core.attr.config != (u64)test_events[i].config) {

From bd077a53ad87cb111632e564cdfe8dfbe96786de Mon Sep 17 00:00:00 2001
From: Hao Ge <gehao@kylinos.cn>
Date: Wed, 13 Nov 2024 11:05:37 +0800
Subject: [PATCH 1338/1530] perf bpf-filter: Return -ENOMEM directly when pfi
 allocation fails

Directly return -ENOMEM when pfi allocation fails,
instead of performing other operations on pfi.

Fixes: 0fe2b18ddc40 ("perf bpf-filter: Support multiple events properly")
Signed-off-by: Hao Ge <gehao@kylinos.cn>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: hao.ge@linux.dev
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20241113030537.26732-1-hao.ge@linux.dev
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/bpf-filter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c
index e87b6789eb9ef..a4fdf6911ec1c 100644
--- a/tools/perf/util/bpf-filter.c
+++ b/tools/perf/util/bpf-filter.c
@@ -375,7 +375,7 @@ static int create_idx_hash(struct evsel *evsel, struct perf_bpf_filter_entry *en
 	pfi = zalloc(sizeof(*pfi));
 	if (pfi == NULL) {
 		pr_err("Cannot save pinned filter index\n");
-		goto err;
+		return -ENOMEM;
 	}
 
 	pfi->evsel = evsel;

From 5f2c8f4e1070e474642b9dea104f531b8be52e1e Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 19 Nov 2024 07:48:56 +0100
Subject: [PATCH 1339/1530] perf/test: fix perf ftrace test on s390

On s390 the perf test case ftrace sometimes fails as follows:

  # ./perf test ftrace
  79: perf ftrace tests    : FAILED!
  #

The failure depends on the kernel .config file. Some configurations
always work fine, some do not.  The ftrace profile test mostly fails,
because the ring buffer was not large enough, and some lines
(especially the interesting ones with nanosleep in it) where dropped.

To achieve success for all tested kernel configurations, enlarge
the buffer to store the traces completely without wrapping.
The default buffer size is too small for all kernel configurations.
Set the buffer size of for the ftrace profile test to 16 MB.

Output after:
  # ./perf test ftrace
  79: perf ftrace tests     : Ok
  #

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: agordeev@linux.ibm.com
Cc: gor@linux.ibm.com
Cc: hca@linux.ibm.com
Cc: sumanthk@linux.ibm.com
Link: https://lore.kernel.org/r/20241119064856.641446-1-tmricht@linux.ibm.com
Suggested-by: Sven Schnelle <svens@linux.ibm.com>
Suggested-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/ftrace.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/ftrace.sh b/tools/perf/tests/shell/ftrace.sh
index 11010711efa19..2df05052c324a 100755
--- a/tools/perf/tests/shell/ftrace.sh
+++ b/tools/perf/tests/shell/ftrace.sh
@@ -67,7 +67,7 @@ test_ftrace_latency() {
 
 test_ftrace_profile() {
     echo "perf ftrace profile test"
-    perf ftrace profile sleep 0.1 > "${output}"
+    perf ftrace profile -m 16M sleep 0.1 > "${output}"
     grep ^# "${output}"
     grep sleep "${output}"
     grep schedule "${output}"

From 870748fa1fac5a397c26126bc32662e9249762c7 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@kernel.org>
Date: Tue, 19 Nov 2024 16:34:31 -0300
Subject: [PATCH 1340/1530] perf tests hwmon_pmu: Remove double
 evlist__delete()

In the error path when failing to parse events the evlist is being
deleted twice, keep the one after the out label.

Fixes: 531ee0fd4836994f ("perf test: Add hwmon "PMU" test")
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: https://lore.kernel.org/r/ZzzoJNNcJJVnPCCe@x1
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/hwmon_pmu.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c
index 1e5f93aaaf5f9..d8ed00d45dd72 100644
--- a/tools/perf/tests/hwmon_pmu.c
+++ b/tools/perf/tests/hwmon_pmu.c
@@ -155,8 +155,6 @@ static int do_test(size_t i, bool with_pmu, bool with_alias)
 	parse_events_error__init(&err);
 	ret = parse_events(evlist, str, &err);
 	if (ret) {
-		evlist__delete(evlist);
-
 		pr_debug("FAILED %s:%d failed to parse event '%s', err %d\n",
 			 __FILE__, __LINE__, str, ret);
 		parse_events_error__print(&err, str);

From 62878b400f5b02416368eda361277c045c675466 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 19 Nov 2024 15:00:33 -0800
Subject: [PATCH 1341/1530] perf hwmon_pmu: Ensure hwmon key union is zeroed
 before use

Non-zero values led to mismatches in testing. This was reproducible
with -fsanitize=undefined.

Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Closes: https://lore.kernel.org/lkml/Zzdtj0PEWEX3ATwL@x1/
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241119230033.115369-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/hwmon_pmu.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/hwmon_pmu.c b/tools/perf/util/hwmon_pmu.c
index ac2245acdc6d9..4d9d6f4054342 100644
--- a/tools/perf/util/hwmon_pmu.c
+++ b/tools/perf/util/hwmon_pmu.c
@@ -274,7 +274,7 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu)
 		int number;
 		enum hwmon_item item;
 		bool alarm;
-		union hwmon_pmu_event_key key = {};
+		union hwmon_pmu_event_key key = { .type_and_num = 0 };
 		struct hwmon_pmu_event_value *value;
 
 		if (ent->d_type != DT_REG)
@@ -560,7 +560,7 @@ bool hwmon_pmu__have_event(struct perf_pmu *pmu, const char *name)
 	struct hwmon_pmu *hwm = container_of(pmu, struct hwmon_pmu, pmu);
 	enum hwmon_type type;
 	int number;
-	union hwmon_pmu_event_key key = {};
+	union hwmon_pmu_event_key key = { .type_and_num = 0 };
 	struct hashmap_entry *cur;
 	size_t bkt;
 
@@ -623,10 +623,11 @@ static int hwmon_pmu__config_term(const struct hwmon_pmu *hwm,
 					return -EINVAL;
 			} else {
 				union hwmon_pmu_event_key key = {
-					.type = type,
-					.num = number,
+					.type_and_num = 0,
 				};
 
+				key.type = type;
+				key.num = number;
 				attr->config = key.type_and_num;
 			}
 			return 0;

From 6d78089da9805787a72e52604ad4b2ed7380be3f Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 20 Nov 2024 16:09:55 -0800
Subject: [PATCH 1342/1530] perf tests: Fix hwmon parsing with PMU name test

Incorrectly the hwmon with PMU name test didn't pass "true". Fix and
address issue with hwmon_pmu__config_terms needing to load events - a
load bearing assert fired. Also fix missing list deletion when putting
the hwmon test PMU and lower some debug warnings to make the hwmon PMU
less spammy in verbose mode.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241121000955.536930-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/hwmon_pmu.c |  5 +++--
 tools/perf/util/hwmon_pmu.c  | 16 ++++++++++------
 2 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c
index d8ed00d45dd72..f8bcee9660d53 100644
--- a/tools/perf/tests/hwmon_pmu.c
+++ b/tools/perf/tests/hwmon_pmu.c
@@ -41,6 +41,7 @@ static int test_pmu_put(const char *dir, struct perf_pmu *hwm)
 	if (ret)
 		pr_err("Failure to \"%s\"\n", buf);
 
+	list_del(&hwm->list);
 	perf_pmu__delete(hwm);
 	return ret;
 }
@@ -147,7 +148,7 @@ static int do_test(size_t i, bool with_pmu, bool with_alias)
 	}
 
 	if (with_pmu)
-		snprintf(str, sizeof(str), "/%s/", test_event);
+		snprintf(str, sizeof(str), "hwmon_a_test_hwmon_pmu/%s/", test_event);
 	else
 		strlcpy(str, test_event, sizeof(str));
 
@@ -231,7 +232,7 @@ static int test__hwmon_pmu_without_pmu(struct test_suite *test __maybe_unused,
 static int test__hwmon_pmu_with_pmu(struct test_suite *test __maybe_unused,
 				   int subtest __maybe_unused)
 {
-	return test__hwmon_pmu(/*with_pmu=*/false);
+	return test__hwmon_pmu(/*with_pmu=*/true);
 }
 
 static int test__parse_hwmon_filename(struct test_suite *test __maybe_unused,
diff --git a/tools/perf/util/hwmon_pmu.c b/tools/perf/util/hwmon_pmu.c
index 4d9d6f4054342..e61429b38ba7b 100644
--- a/tools/perf/util/hwmon_pmu.c
+++ b/tools/perf/util/hwmon_pmu.c
@@ -197,13 +197,13 @@ bool parse_hwmon_filename(const char *filename,
 		}
 	}
 	if (fn_item == NULL || fn_type[0] == '\0' || (item != NULL && fn_item[0] == '\0')) {
-		pr_debug("hwmon_pmu: not a hwmon file '%s'\n", filename);
+		pr_debug3("hwmon_pmu: not a hwmon file '%s'\n", filename);
 		return false;
 	}
 	elem = bsearch(&fn_type, hwmon_type_strs + 1, ARRAY_SIZE(hwmon_type_strs) - 1,
 		       sizeof(hwmon_type_strs[0]), hwmon_strcmp);
 	if (!elem) {
-		pr_debug("hwmon_pmu: not a hwmon type '%s' in file name '%s'\n",
+		pr_debug3("hwmon_pmu: not a hwmon type '%s' in file name '%s'\n",
 			 fn_type, filename);
 		return false;
 	}
@@ -223,7 +223,7 @@ bool parse_hwmon_filename(const char *filename,
 	elem = bsearch(fn_item, hwmon_item_strs + 1, ARRAY_SIZE(hwmon_item_strs) - 1,
 		       sizeof(hwmon_item_strs[0]), hwmon_strcmp);
 	if (!elem) {
-		pr_debug("hwmon_pmu: not a hwmon item '%s' in file name '%s'\n",
+		pr_debug3("hwmon_pmu: not a hwmon item '%s' in file name '%s'\n",
 			 fn_item, filename);
 		return false;
 	}
@@ -281,7 +281,7 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu)
 			continue;
 
 		if (!parse_hwmon_filename(ent->d_name, &type, &number, &item, &alarm)) {
-			pr_debug("Not a hwmon file '%s'\n", ent->d_name);
+			pr_debug3("Not a hwmon file '%s'\n", ent->d_name);
 			continue;
 		}
 		key.num = number;
@@ -653,10 +653,14 @@ int hwmon_pmu__config_terms(const struct perf_pmu *pmu,
 			    struct parse_events_terms *terms,
 			    struct parse_events_error *err)
 {
-	const struct hwmon_pmu *hwm = container_of(pmu, struct hwmon_pmu, pmu);
+	struct hwmon_pmu *hwm = container_of(pmu, struct hwmon_pmu, pmu);
 	struct parse_events_term *term;
+	int ret;
+
+	ret = hwmon_pmu__read_events(hwm);
+	if (ret)
+		return ret;
 
-	assert(pmu->sysfs_aliases_loaded);
 	list_for_each_entry(term, &terms->terms, list) {
 		if (hwmon_pmu__config_term(hwm, attr, term, err))
 			return -EINVAL;

From 009a8241a8e5a14ea2dd0b8db42dbf283527dd44 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Fri, 22 Nov 2024 14:50:05 +0800
Subject: [PATCH 1343/1530] f2fs: add a sysfs node to limit max read extent
 count per-inode

Quoted:
"at this time, there are still 1086911 extent nodes in this zombie
extent tree that need to be cleaned up.

crash_arm64_sprd_v8.0.3++> extent_tree.node_cnt ffffff80896cc500
  node_cnt = {
    counter = 1086911
  },
"

As reported by Xiuhong, there will be a huge number of extent nodes
in extent tree, it may potentially cause:
- slab memory fragments
- extreme long time shrink on extent tree
- low mapping efficiency

Let's add a sysfs node to limit max read extent count for each inode,
by default, value of this threshold is 10240, it can be updated
according to user's requirement.

Reported-by: Xiuhong Wang <xiuhong.wang@unisoc.com>
Closes: https://lore.kernel.org/linux-f2fs-devel/20241112110627.1314632-1-xiuhong.wang@unisoc.com/
Signed-off-by: Xiuhong Wang <xiuhong.wang@unisoc.com>
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 Documentation/ABI/testing/sysfs-fs-f2fs |  6 ++++++
 fs/f2fs/extent_cache.c                  |  5 ++++-
 fs/f2fs/f2fs.h                          |  4 ++++
 fs/f2fs/sysfs.c                         | 10 ++++++++++
 4 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 513296bb6f297..3e1630c70d8ae 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -822,3 +822,9 @@ Description:	It controls the valid block ratio threshold not to trigger excessiv
 		for zoned deivces. The initial value of it is 95(%). F2FS will stop the
 		background GC thread from intiating GC for sections having valid blocks
 		exceeding the ratio.
+
+What:		/sys/fs/f2fs/<disk>/max_read_extent_count
+Date:		November 2024
+Contact:	"Chao Yu" <chao@kernel.org>
+Description:	It controls max read extent count for per-inode, the value of threshold
+		is 10240 by default.
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index b7a6817b44b00..347b3b6478347 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -717,7 +717,9 @@ static void __update_extent_tree_range(struct inode *inode,
 		}
 
 		if (end < org_end && (type != EX_READ ||
-				org_end - end >= F2FS_MIN_EXTENT_LEN)) {
+			(org_end - end >= F2FS_MIN_EXTENT_LEN &&
+			atomic_read(&et->node_cnt) <
+					sbi->max_read_extent_count))) {
 			if (parts) {
 				__set_extent_info(&ei,
 					end, org_end - end,
@@ -1212,6 +1214,7 @@ void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi)
 	sbi->hot_data_age_threshold = DEF_HOT_DATA_AGE_THRESHOLD;
 	sbi->warm_data_age_threshold = DEF_WARM_DATA_AGE_THRESHOLD;
 	sbi->last_age_weight = LAST_AGE_WEIGHT;
+	sbi->max_read_extent_count = DEF_MAX_READ_EXTENT_COUNT;
 }
 
 int __init f2fs_create_extent_cache(void)
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index b65b023a588a0..6f2cbf4c57402 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -635,6 +635,9 @@ enum {
 #define DEF_HOT_DATA_AGE_THRESHOLD	262144
 #define DEF_WARM_DATA_AGE_THRESHOLD	2621440
 
+/* default max read extent count per inode */
+#define DEF_MAX_READ_EXTENT_COUNT	10240
+
 /* extent cache type */
 enum extent_type {
 	EX_READ,
@@ -1619,6 +1622,7 @@ struct f2fs_sb_info {
 	/* for extent tree cache */
 	struct extent_tree_info extent_tree[NR_EXTENT_CACHES];
 	atomic64_t allocated_data_blocks;	/* for block age extent_cache */
+	unsigned int max_read_extent_count;	/* max read extent count per inode */
 
 	/* The threshold used for hot and warm data seperation*/
 	unsigned int hot_data_age_threshold;
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index bdbf24db667bb..6b99dc49f7761 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -787,6 +787,13 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
 		return count;
 	}
 
+	if (!strcmp(a->attr.name, "max_read_extent_count")) {
+		if (t > UINT_MAX)
+			return -EINVAL;
+		*ui = (unsigned int)t;
+		return count;
+	}
+
 	if (!strcmp(a->attr.name, "ipu_policy")) {
 		if (t >= BIT(F2FS_IPU_MAX))
 			return -EINVAL;
@@ -1052,6 +1059,8 @@ F2FS_SBI_GENERAL_RW_ATTR(revoked_atomic_block);
 F2FS_SBI_GENERAL_RW_ATTR(hot_data_age_threshold);
 F2FS_SBI_GENERAL_RW_ATTR(warm_data_age_threshold);
 F2FS_SBI_GENERAL_RW_ATTR(last_age_weight);
+/* read extent cache */
+F2FS_SBI_GENERAL_RW_ATTR(max_read_extent_count);
 #ifdef CONFIG_BLK_DEV_ZONED
 F2FS_SBI_GENERAL_RO_ATTR(unusable_blocks_per_sec);
 F2FS_SBI_GENERAL_RW_ATTR(blkzone_alloc_policy);
@@ -1242,6 +1251,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(hot_data_age_threshold),
 	ATTR_LIST(warm_data_age_threshold),
 	ATTR_LIST(last_age_weight),
+	ATTR_LIST(max_read_extent_count),
 	NULL,
 };
 ATTRIBUTE_GROUPS(f2fs);

From bc8aeb04fd80cb8cfae3058445c84410fd0beb5e Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Thu, 21 Nov 2024 22:17:16 +0800
Subject: [PATCH 1344/1530] f2fs: fix to drop all discards after creating
 snapshot on lvm device

Piergiorgio reported a bug in bugzilla as below:

------------[ cut here ]------------
WARNING: CPU: 2 PID: 969 at fs/f2fs/segment.c:1330
RIP: 0010:__submit_discard_cmd+0x27d/0x400 [f2fs]
Call Trace:
 __issue_discard_cmd+0x1ca/0x350 [f2fs]
 issue_discard_thread+0x191/0x480 [f2fs]
 kthread+0xcf/0x100
 ret_from_fork+0x31/0x50
 ret_from_fork_asm+0x1a/0x30

w/ below testcase, it can reproduce this bug quickly:
- pvcreate /dev/vdb
- vgcreate myvg1 /dev/vdb
- lvcreate -L 1024m -n mylv1 myvg1
- mount /dev/myvg1/mylv1 /mnt/f2fs
- dd if=/dev/zero of=/mnt/f2fs/file bs=1M count=20
- sync
- rm /mnt/f2fs/file
- sync
- lvcreate -L 1024m -s -n mylv1-snapshot /dev/myvg1/mylv1
- umount /mnt/f2fs

The root cause is: it will update discard_max_bytes of mounted lvm
device to zero after creating snapshot on this lvm device, then,
__submit_discard_cmd() will pass parameter @nr_sects w/ zero value
to __blkdev_issue_discard(), it returns a NULL bio pointer, result
in panic.

This patch changes as below for fixing:
1. Let's drop all remained discards in f2fs_unfreeze() if snapshot
of lvm device is created.
2. Checking discard_max_bytes before submitting discard during
__submit_discard_cmd().

Cc: stable@vger.kernel.org
Fixes: 35ec7d574884 ("f2fs: split discard command in prior to block layer")
Reported-by: Piergiorgio Sartor <piergiorgio.sartor@nexgo.de>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219484
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/segment.c | 16 +++++++++-------
 fs/f2fs/super.c   | 12 ++++++++++++
 2 files changed, 21 insertions(+), 7 deletions(-)

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 4236040e3994c..eade36c5ef138 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1290,16 +1290,18 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
 						wait_list, issued);
 			return 0;
 		}
-
-		/*
-		 * Issue discard for conventional zones only if the device
-		 * supports discard.
-		 */
-		if (!bdev_max_discard_sectors(bdev))
-			return -EOPNOTSUPP;
 	}
 #endif
 
+	/*
+	 * stop issuing discard for any of below cases:
+	 * 1. device is conventional zone, but it doesn't support discard.
+	 * 2. device is regulare device, after snapshot it doesn't support
+	 * discard.
+	 */
+	if (!bdev_max_discard_sectors(bdev))
+		return -EOPNOTSUPP;
+
 	trace_f2fs_issue_discard(bdev, dc->di.start, dc->di.len);
 
 	lstart = dc->di.lstart;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index c0670cd619563..fc7d463dee158 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1760,6 +1760,18 @@ static int f2fs_freeze(struct super_block *sb)
 
 static int f2fs_unfreeze(struct super_block *sb)
 {
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+
+	/*
+	 * It will update discard_max_bytes of mounted lvm device to zero
+	 * after creating snapshot on this lvm device, let's drop all
+	 * remained discards.
+	 * We don't need to disable real-time discard because discard_max_bytes
+	 * will recover after removal of snapshot.
+	 */
+	if (test_opt(sbi, DISCARD) && !f2fs_hw_support_discard(sbi))
+		f2fs_issue_discard_timeout(sbi);
+
 	clear_sbi_flag(F2FS_SB(sb), SBI_IS_FREEZING);
 	return 0;
 }

From 8281d627905dc72241ca3969ee18f3e029e96d00 Mon Sep 17 00:00:00 2001
From: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Date: Thu, 21 Nov 2024 14:18:19 +0200
Subject: [PATCH 1345/1530] hwmon: (tmp108) Do not fail in I3C probe when I3C
 regmap is a module

I3C device probe fails when CONFIG_REGMAP_I3C=m:

	p3t1085_i3c 0-23615290090: error -ENODEV: Failed to register i3c regmap

Fix this by using the IS_ENABLED(CONFIG_REGMAP_I3C) macro in the code.

Fixes: c40655e33106 ("hwmon: (tmp108) Add support for I3C device")
Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Message-ID: <20241121121819.393104-1-jarkko.nikula@linux.intel.com>
[groeck: Remove #ifdef entirely; it is not needed due to dead code elimination]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/tmp108.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/hwmon/tmp108.c b/drivers/hwmon/tmp108.c
index 1f36af2cd2d94..fbe6730091261 100644
--- a/drivers/hwmon/tmp108.c
+++ b/drivers/hwmon/tmp108.c
@@ -452,12 +452,7 @@ static int p3t1085_i3c_probe(struct i3c_device *i3cdev)
 	struct device *dev = i3cdev_to_dev(i3cdev);
 	struct regmap *regmap;
 
-#ifdef CONFIG_REGMAP_I3C
 	regmap = devm_regmap_init_i3c(i3cdev, &tmp108_regmap_config);
-#else
-	regmap = ERR_PTR(-ENODEV);
-#endif
-
 	if (IS_ERR(regmap))
 		return dev_err_probe(dev, PTR_ERR(regmap),
 				     "Failed to register i3c regmap\n");

From de2bf507fabba9c0c678cf5ed54beb546f5ca29a Mon Sep 17 00:00:00 2001
From: Murad Masimov <m.masimov@maxima.ru>
Date: Thu, 21 Nov 2024 20:36:03 +0300
Subject: [PATCH 1346/1530] hwmon: (tps23861) Fix reporting of negative
 temperatures

Negative temperatures are reported as large positive temperatures
due to missing sign extension from unsigned int to long. Cast unsigned
raw register values to signed before performing the calculations
to fix the problem.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: fff7b8ab2255 ("hwmon: add Texas Instruments TPS23861 driver")
Signed-off-by: Murad Masimov <m.masimov@maxima.ru>
Message-ID: <20241121173604.2021-1-m.masimov@maxima.ru>
[groeck: Updated subject and description]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/tps23861.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/tps23861.c b/drivers/hwmon/tps23861.c
index dfcfb09d9f3cd..80fb03f30c302 100644
--- a/drivers/hwmon/tps23861.c
+++ b/drivers/hwmon/tps23861.c
@@ -132,7 +132,7 @@ static int tps23861_read_temp(struct tps23861_data *data, long *val)
 	if (err < 0)
 		return err;
 
-	*val = (regval * TEMPERATURE_LSB) - 20000;
+	*val = ((long)regval * TEMPERATURE_LSB) - 20000;
 
 	return 0;
 }

From f26a29a038ee3982099e867bec2260576a19720f Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 16 Nov 2024 21:52:15 +0100
Subject: [PATCH 1347/1530] net: phy: ensure that
 genphy_c45_an_config_eee_aneg() sees new value of phydev->eee_cfg.eee_enabled

This is a follow-up to 41ffcd95015f ("net: phy: fix phylib's dual
eee_enabled") and resolves an issue with genphy_c45_an_config_eee_aneg()
(called from genphy_c45_ethtool_set_eee) not seeing the new value of
phydev->eee_cfg.eee_enabled.

Fixes: 49168d1980e2 ("net: phy: Add phy_support_eee() indicating MAC support EEE")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reported-by: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 4f3e742907cb6..a660a80f34b79 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1672,7 +1672,7 @@ EXPORT_SYMBOL(phy_ethtool_get_eee);
  * phy_ethtool_set_eee_noneg - Adjusts MAC LPI configuration without PHY
  *			       renegotiation
  * @phydev: pointer to the target PHY device structure
- * @data: pointer to the ethtool_keee structure containing the new EEE settings
+ * @old_cfg: pointer to the eee_config structure containing the old EEE settings
  *
  * This function updates the Energy Efficient Ethernet (EEE) configuration
  * for cases where only the MAC's Low Power Idle (LPI) configuration changes,
@@ -1683,11 +1683,10 @@ EXPORT_SYMBOL(phy_ethtool_get_eee);
  * configuration.
  */
 static void phy_ethtool_set_eee_noneg(struct phy_device *phydev,
-				      struct ethtool_keee *data)
+				      const struct eee_config *old_cfg)
 {
-	if (phydev->eee_cfg.tx_lpi_enabled != data->tx_lpi_enabled ||
-	    phydev->eee_cfg.tx_lpi_timer != data->tx_lpi_timer) {
-		eee_to_eeecfg(&phydev->eee_cfg, data);
+	if (phydev->eee_cfg.tx_lpi_enabled != old_cfg->tx_lpi_enabled ||
+	    phydev->eee_cfg.tx_lpi_timer != old_cfg->tx_lpi_timer) {
 		phydev->enable_tx_lpi = eeecfg_mac_can_tx_lpi(&phydev->eee_cfg);
 		if (phydev->link) {
 			phydev->link = false;
@@ -1707,18 +1706,23 @@ static void phy_ethtool_set_eee_noneg(struct phy_device *phydev,
  */
 int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data)
 {
+	struct eee_config old_cfg;
 	int ret;
 
 	if (!phydev->drv)
 		return -EIO;
 
 	mutex_lock(&phydev->lock);
+
+	old_cfg = phydev->eee_cfg;
+	eee_to_eeecfg(&phydev->eee_cfg, data);
+
 	ret = genphy_c45_ethtool_set_eee(phydev, data);
-	if (ret >= 0) {
-		if (ret == 0)
-			phy_ethtool_set_eee_noneg(phydev, data);
-		eee_to_eeecfg(&phydev->eee_cfg, data);
-	}
+	if (ret == 0)
+		phy_ethtool_set_eee_noneg(phydev, &old_cfg);
+	else if (ret < 0)
+		phydev->eee_cfg = old_cfg;
+
 	mutex_unlock(&phydev->lock);
 
 	return ret < 0 ? ret : 0;

From 50b9d43e6ceaaaa59c54c95aca5f8dfc862fe48e Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Tue, 8 Oct 2024 18:09:47 +0200
Subject: [PATCH 1348/1530] i2c: qup: use generic device property accessors

There's no reason for this driver to use OF-specific property helpers.
Drop the last one in favor of the generic variant and no longer include
of.h.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/busses/i2c-qup.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c
index 86ec391616b06..da20b4487c9a5 100644
--- a/drivers/i2c/busses/i2c-qup.c
+++ b/drivers/i2c/busses/i2c-qup.c
@@ -17,9 +17,9 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/module.h>
-#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/property.h>
 #include <linux/scatterlist.h>
 
 /* QUP Registers */
@@ -1683,7 +1683,7 @@ static int qup_i2c_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (of_device_is_compatible(pdev->dev.of_node, "qcom,i2c-qup-v1.1.1")) {
+	if (device_is_compatible(&pdev->dev, "qcom,i2c-qup-v1.1.1")) {
 		qup->adap.algo = &qup_i2c_algo;
 		qup->adap.quirks = &qup_i2c_quirks;
 		is_qup_v1 = true;

From 7c3a833a1da6ab1e29fcb4740edf770aea816c6f Mon Sep 17 00:00:00 2001
From: Yoshihiro Furudera <fj5100bi@fujitsu.com>
Date: Thu, 24 Oct 2024 07:15:53 +0000
Subject: [PATCH 1349/1530] i2c: designware: Add ACPI HID for DWAPB I2C
 controller on FUJITSU-MONAKA

Enable DWAPB I2C controller support on FUJITSU-MONAKA.
This will be used in the FUJITSU-MONAKA server scheduled
for shipment in 2027.

The DSDT information obtained when verified using an
in-house simulator is presented below.

     Device (SMB0)
     {
         Name (_HID, "FUJI200B")  // _HID: Hardware ID
         Name (_UID, Zero)  // _UID: Unique ID
         ...
         Name (_CRS, ResourceTemplate ()
         {
             Memory32Fixed (ReadWrite,
                 0x2A4B0000,         // Address Base
                 0x00010000,         // Address Length
                 )
             Interrupt (ResourceConsumer, Level, ActiveHigh, Exclusive, ,, )
             {
                 0x00000159,
             }
         })
         ...
     }

The expression SMB0 is used to indicate SMBus HC#0,
a string of up to four characters.

Created the SMB0 object according to the following
specifications:

ACPI Specification
13.2. Accessing the SMBus from ASL Code
https://uefi.org/htmlspecs/ACPI_Spec_6_4_html/13_ACPI_System_Mgmt_Bus_Interface_Spec/accessing-the-smbus-from-asl-code.html

IPMI Specification
Example 4: SSIF Interface(P574)
https://www.intel.co.jp/content/www/jp/ja/products/docs/servers/ipmi/ipmi-second-gen-interface-spec-v2-rev1-1.html

Signed-off-by: Yoshihiro Furudera <fj5100bi@fujitsu.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/busses/i2c-designware-platdrv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c
index 1643cad6489c9..3e12aab6bf2da 100644
--- a/drivers/i2c/busses/i2c-designware-platdrv.c
+++ b/drivers/i2c/busses/i2c-designware-platdrv.c
@@ -349,6 +349,7 @@ static const struct acpi_device_id dw_i2c_acpi_match[] = {
 	{ "AMDI0019", ACCESS_INTR_MASK | ARBITRATION_SEMAPHORE },
 	{ "AMDI0510", 0 },
 	{ "APMC0D0F", 0 },
+	{ "FUJI200B", 0 },
 	{ "HISI02A1", 0 },
 	{ "HISI02A2", 0 },
 	{ "HISI02A3", 0 },

From efdc7828b7cc8cb8a1c2a83ff6f7741ca055b1b1 Mon Sep 17 00:00:00 2001
From: Andre Przywara <andre.przywara@arm.com>
Date: Mon, 11 Nov 2024 01:30:24 +0000
Subject: [PATCH 1350/1530] dt-bindings: i2c: mv64xxx: Add Allwinner A523
 compatible string

The I2C controller IP used in the Allwinner A523/T527 SoCs is
compatible with the ones used in the other recent Allwinner SoCs.

Add the A523 specific compatible string to the list of existing names
falling back to the allwinner,sun8i-v536-i2c string.

Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 Documentation/devicetree/bindings/i2c/marvell,mv64xxx-i2c.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/i2c/marvell,mv64xxx-i2c.yaml b/Documentation/devicetree/bindings/i2c/marvell,mv64xxx-i2c.yaml
index 984fc1ed3ec6a..c4efcef591337 100644
--- a/Documentation/devicetree/bindings/i2c/marvell,mv64xxx-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/marvell,mv64xxx-i2c.yaml
@@ -33,6 +33,7 @@ properties:
               - allwinner,sun50i-a100-i2c
               - allwinner,sun50i-h616-i2c
               - allwinner,sun50i-r329-i2c
+              - allwinner,sun55i-a523-i2c
           - const: allwinner,sun8i-v536-i2c
           - const: allwinner,sun6i-a31-i2c
       - const: marvell,mv64xxx-i2c

From 2eec351eed02da9955ac7a79dd9481f61c355c9a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Wed, 9 Oct 2024 16:01:07 +0200
Subject: [PATCH 1351/1530] dt-bindings: i2c: nomadik: add mobileye,eyeq6h-i2c
 bindings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After EyeQ5, it is time for Mobileye EyeQ6H to reuse the Nomadik I2C
controller. Add a specific compatible because its HW integration is
slightly different from EyeQ5.

Do NOT add an example as it looks like EyeQ5 from a DT standpoint
(without the mobileye,olb property).

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 .../devicetree/bindings/i2c/st,nomadik-i2c.yaml       | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/i2c/st,nomadik-i2c.yaml b/Documentation/devicetree/bindings/i2c/st,nomadik-i2c.yaml
index 44c54b162bb10..7e84465c20094 100644
--- a/Documentation/devicetree/bindings/i2c/st,nomadik-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/st,nomadik-i2c.yaml
@@ -22,6 +22,7 @@ select:
         enum:
           - st,nomadik-i2c
           - mobileye,eyeq5-i2c
+          - mobileye,eyeq6h-i2c
   required:
     - compatible
 
@@ -29,15 +30,15 @@ properties:
   compatible:
     oneOf:
       - items:
-          - const: st,nomadik-i2c
+          - enum:
+              - st,nomadik-i2c
+              - mobileye,eyeq5-i2c
+              - mobileye,eyeq6h-i2c
           - const: arm,primecell
       - items:
           - const: stericsson,db8500-i2c
           - const: st,nomadik-i2c
           - const: arm,primecell
-      - items:
-          - const: mobileye,eyeq5-i2c
-          - const: arm,primecell
 
   reg:
     maxItems: 1
@@ -54,7 +55,7 @@ properties:
       - items:
           - const: mclk
           - const: apb_pclk
-      # Clock name in DB8500 or EyeQ5
+      # Clock name in DB8500 or EyeQ
       - items:
           - const: i2cclk
           - const: apb_pclk

From 54202106c0fe23693c5e9e81e7587ce89e6dd182 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Wed, 9 Oct 2024 16:01:08 +0200
Subject: [PATCH 1352/1530] dt-bindings: i2c: nomadik: support 400kHz <
 clock-frequency <= 3.4MHz
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Hardware is not limited to 400kHz, its documentation does mention how to
configure it for high-speed (a specific Speed-Mode enum value and
a different bus rate clock divider register to be used).

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 Documentation/devicetree/bindings/i2c/st,nomadik-i2c.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/i2c/st,nomadik-i2c.yaml b/Documentation/devicetree/bindings/i2c/st,nomadik-i2c.yaml
index 7e84465c20094..012402debfeb2 100644
--- a/Documentation/devicetree/bindings/i2c/st,nomadik-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/st,nomadik-i2c.yaml
@@ -68,7 +68,7 @@ properties:
 
   clock-frequency:
     minimum: 1
-    maximum: 400000
+    maximum: 3400000
 
   mobileye,olb:
     $ref: /schemas/types.yaml#/definitions/phandle-array

From a0d15cc47f29be6d588fa55bdbe116c26549178d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Wed, 9 Oct 2024 16:01:09 +0200
Subject: [PATCH 1353/1530] i2c: nomadik: switch from of_device_is_compatible()
 to of_match_device()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Compatible-specific behavior is implemented using a if-condition on the
return value from of_device_is_compatible(), from probe. It does not
scale well when compatible number increases. Switch to using a match
table and a call to of_match_device().

We DO NOT attach a .of_match_table field to our amba driver, as we do
not use the table to match our driver to devices.

Sort probe variable declarations in reverse christmas tree to try and
introduce some logic into the ordering.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/busses/i2c-nomadik.c | 35 ++++++++++++++++++++++++--------
 1 file changed, 27 insertions(+), 8 deletions(-)

diff --git a/drivers/i2c/busses/i2c-nomadik.c b/drivers/i2c/busses/i2c-nomadik.c
index ad0f02acdb121..c40328d1bca6c 100644
--- a/drivers/i2c/busses/i2c-nomadik.c
+++ b/drivers/i2c/busses/i2c-nomadik.c
@@ -26,6 +26,7 @@
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>
@@ -1046,8 +1047,6 @@ static int nmk_i2c_eyeq5_probe(struct nmk_i2c_dev *priv)
 	struct regmap *olb;
 	unsigned int id;
 
-	priv->has_32b_bus = true;
-
 	olb = syscon_regmap_lookup_by_phandle_args(np, "mobileye,olb", 1, &id);
 	if (IS_ERR(olb))
 		return PTR_ERR(olb);
@@ -1068,15 +1067,35 @@ static int nmk_i2c_eyeq5_probe(struct nmk_i2c_dev *priv)
 	return 0;
 }
 
+#define NMK_I2C_EYEQ_FLAG_32B_BUS	BIT(0)
+#define NMK_I2C_EYEQ_FLAG_IS_EYEQ5	BIT(1)
+
+static const struct of_device_id nmk_i2c_eyeq_match_table[] = {
+	{
+		.compatible = "mobileye,eyeq5-i2c",
+		.data = (void *)(NMK_I2C_EYEQ_FLAG_32B_BUS | NMK_I2C_EYEQ_FLAG_IS_EYEQ5),
+	},
+};
+
 static int nmk_i2c_probe(struct amba_device *adev, const struct amba_id *id)
 {
-	int ret = 0;
-	struct nmk_i2c_dev *priv;
+	struct i2c_vendor_data *vendor = id->data;
+	u32 max_fifo_threshold = (vendor->fifodepth / 2) - 1;
 	struct device_node *np = adev->dev.of_node;
+	const struct of_device_id *match;
 	struct device *dev = &adev->dev;
+	unsigned long match_flags = 0;
+	struct nmk_i2c_dev *priv;
 	struct i2c_adapter *adap;
-	struct i2c_vendor_data *vendor = id->data;
-	u32 max_fifo_threshold = (vendor->fifodepth / 2) - 1;
+	int ret = 0;
+
+	/*
+	 * We do not want to attach a .of_match_table to our amba driver.
+	 * Do not convert to device_get_match_data().
+	 */
+	match = of_match_device(nmk_i2c_eyeq_match_table, dev);
+	if (match)
+		match_flags = (unsigned long)match->data;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -1084,10 +1103,10 @@ static int nmk_i2c_probe(struct amba_device *adev, const struct amba_id *id)
 
 	priv->vendor = vendor;
 	priv->adev = adev;
-	priv->has_32b_bus = false;
+	priv->has_32b_bus = match_flags & NMK_I2C_EYEQ_FLAG_32B_BUS;
 	nmk_i2c_of_probe(np, priv);
 
-	if (of_device_is_compatible(np, "mobileye,eyeq5-i2c")) {
+	if (match_flags & NMK_I2C_EYEQ_FLAG_IS_EYEQ5) {
 		ret = nmk_i2c_eyeq5_probe(priv);
 		if (ret)
 			return dev_err_probe(dev, ret, "failed OLB lookup\n");

From 814a3225f4e9b3631369029ed5ecf35e7a2999bc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Wed, 9 Oct 2024 16:01:10 +0200
Subject: [PATCH 1354/1530] i2c: nomadik: support Mobileye EyeQ6H I2C
 controller
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add EyeQ6H support to the nmk-i2c AMBA driver. It shares the same quirk
as EyeQ5: the memory bus only supports 32-bit accesses. Avoid writeb()
and readb() by reusing the same `priv->has_32b_bus` flag.

It does NOT need to write speed-mode specific value into a register;
therefore it does not depend on the mobileye,olb DT property.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/busses/i2c-nomadik.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-nomadik.c b/drivers/i2c/busses/i2c-nomadik.c
index c40328d1bca6c..8f52ae4d6285a 100644
--- a/drivers/i2c/busses/i2c-nomadik.c
+++ b/drivers/i2c/busses/i2c-nomadik.c
@@ -6,10 +6,10 @@
  * I2C master mode controller driver, used in Nomadik 8815
  * and Ux500 platforms.
  *
- * The Mobileye EyeQ5 platform is also supported; it uses
+ * The Mobileye EyeQ5 and EyeQ6H platforms are also supported; they use
  * the same Ux500/DB8500 IP block with two quirks:
  *  - The memory bus only supports 32-bit accesses.
- *  - A register must be configured for the I2C speed mode;
+ *  - (only EyeQ5) A register must be configured for the I2C speed mode;
  *    it is located in a shared register region called OLB.
  *
  * Author: Srinidhi Kasagar <srinidhi.kasagar@stericsson.com>
@@ -1075,6 +1075,10 @@ static const struct of_device_id nmk_i2c_eyeq_match_table[] = {
 		.compatible = "mobileye,eyeq5-i2c",
 		.data = (void *)(NMK_I2C_EYEQ_FLAG_32B_BUS | NMK_I2C_EYEQ_FLAG_IS_EYEQ5),
 	},
+	{
+		.compatible = "mobileye,eyeq6h-i2c",
+		.data = (void *)NMK_I2C_EYEQ_FLAG_32B_BUS,
+	},
 };
 
 static int nmk_i2c_probe(struct amba_device *adev, const struct amba_id *id)

From 16674c8c488ec40cbf15806658a22a68bb15a810 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Wed, 9 Oct 2024 16:01:11 +0200
Subject: [PATCH 1355/1530] i2c: nomadik: fix BRCR computation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Current BRCR computation is:

    brcr = floor(i2cclk / (clkfreq * div))

With brcr: "baud rate counter", an internal clock divider,
 and i2cclk: input clock rate (24MHz, 38.4MHz or 48MHz),
 and clkfreq: desired bus rate,
 and div: speed-mode dependent divider (2 for standard, 3 otherwise).

Assume i2cclk=48MHz, clkfreq=3.4MHz, div=3,
  then brcr = floor(48MHz / (3.4MHz * 3)) = 4
   and resulting bus rate = 48MHz / (4 * 3) = 4MHz

Assume i2cclk=38.4MHz, clkfreq=1.0MHz, div=3,
  then brcr = floor(38.4MHz / (1.0MHz * 3)) = 12
   and resulting bus rate = 38.4MHz / (12 * 3) = 1066kHz

The current computation means we always pick the smallest divider that
gives a bus rate above target. We should instead pick the largest
divider that gives a bus rate below target, using:

    brcr = floor(i2cclk / (clkfreq * div)) + 1

If we redo the above examples:

Assume i2cclk=48MHz, clkfreq=3.4MHz, div=3,
  then brcr = floor(48MHz / (3.4MHz * 3)) + 1 = 5
   and resulting bus rate = 48MHz / (5 * 3) = 3.2MHz

Assume i2cclk=38.4MHz, clkfreq=1.0MHz, div=3,
  then brcr = floor(38.4MHz / (1.0MHz * 3)) + 1 = 13
   and resulting bus rate = 38.4MHz / (13 * 3) = 985kHz

In kernel C code, floor(x)   is DIV_ROUND_DOWN() and,
                  floor(x)+1 is DIV_ROUND_UP().

This is much less of an issue with slower bus rates (ie those currently
supported), because the gap from one divider to the next is much
smaller. It however keeps us from always using bus rates superior to
the target.

This fix is required for later on supporting faster bus rates:
I2C_FREQ_MODE_FAST_PLUS (1MHz) and I2C_FREQ_MODE_HIGH_SPEED (3.4MHz).

Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/busses/i2c-nomadik.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-nomadik.c b/drivers/i2c/busses/i2c-nomadik.c
index 8f52ae4d6285a..90e3390cd66de 100644
--- a/drivers/i2c/busses/i2c-nomadik.c
+++ b/drivers/i2c/busses/i2c-nomadik.c
@@ -454,9 +454,13 @@ static void setup_i2c_controller(struct nmk_i2c_dev *priv)
 	 * operation, and the other is for std, fast mode, fast mode
 	 * plus operation. Currently we do not supprt high speed mode
 	 * so set brcr1 to 0.
+	 *
+	 * BRCR is a clock divider amount. Pick highest value that
+	 * leads to rate strictly below target. Eg when asking for
+	 * 400kHz you want a bus rate <=400kHz (and not >=400kHz).
 	 */
 	brcr1 = FIELD_PREP(I2C_BRCR_BRCNT1, 0);
-	brcr2 = FIELD_PREP(I2C_BRCR_BRCNT2, i2c_clk / (priv->clk_freq * div));
+	brcr2 = FIELD_PREP(I2C_BRCR_BRCNT2, DIV_ROUND_UP(i2c_clk, priv->clk_freq * div));
 
 	/* set the baud rate counter register */
 	writel((brcr1 | brcr2), priv->virtbase + I2C_BRCR);

From 4fb1b640d68dba271e6b580582ac5c1381c6157a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Wed, 9 Oct 2024 16:01:12 +0200
Subject: [PATCH 1356/1530] i2c: nomadik: support >=1MHz speed modes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

 - BRCR value must go into the BRCR1 field when in high-speed mode.
   It goes into BRCR2 otherwise.

 - Remove fallback to standard mode if priv->sm > I2C_FREQ_MODE_FAST.

 - Set SM properly in probe; previously it only checked STANDARD versus
   FAST. Now we set STANDARD, FAST, FAST_PLUS or HIGH_SPEED.

 - Remove all comment sections saying we only support low-speeds.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/busses/i2c-nomadik.c | 40 +++++++++++++-------------------
 1 file changed, 16 insertions(+), 24 deletions(-)

diff --git a/drivers/i2c/busses/i2c-nomadik.c b/drivers/i2c/busses/i2c-nomadik.c
index 90e3390cd66de..efb33802804fd 100644
--- a/drivers/i2c/busses/i2c-nomadik.c
+++ b/drivers/i2c/busses/i2c-nomadik.c
@@ -397,7 +397,7 @@ static u32 load_i2c_mcr_reg(struct nmk_i2c_dev *priv, u16 flags)
  */
 static void setup_i2c_controller(struct nmk_i2c_dev *priv)
 {
-	u32 brcr1, brcr2;
+	u32 brcr;
 	u32 i2c_clk, div;
 	u32 ns;
 	u16 slsu;
@@ -444,7 +444,7 @@ static void setup_i2c_controller(struct nmk_i2c_dev *priv)
 	/*
 	 * The spec says, in case of std. mode the divider is
 	 * 2 whereas it is 3 for fast and fastplus mode of
-	 * operation. TODO - high speed support.
+	 * operation.
 	 */
 	div = (priv->clk_freq > I2C_MAX_STANDARD_MODE_FREQ) ? 3 : 2;
 
@@ -452,34 +452,23 @@ static void setup_i2c_controller(struct nmk_i2c_dev *priv)
 	 * generate the mask for baud rate counters. The controller
 	 * has two baud rate counters. One is used for High speed
 	 * operation, and the other is for std, fast mode, fast mode
-	 * plus operation. Currently we do not supprt high speed mode
-	 * so set brcr1 to 0.
+	 * plus operation.
 	 *
 	 * BRCR is a clock divider amount. Pick highest value that
 	 * leads to rate strictly below target. Eg when asking for
 	 * 400kHz you want a bus rate <=400kHz (and not >=400kHz).
 	 */
-	brcr1 = FIELD_PREP(I2C_BRCR_BRCNT1, 0);
-	brcr2 = FIELD_PREP(I2C_BRCR_BRCNT2, DIV_ROUND_UP(i2c_clk, priv->clk_freq * div));
+	brcr = DIV_ROUND_UP(i2c_clk, priv->clk_freq * div);
+
+	if (priv->sm == I2C_FREQ_MODE_HIGH_SPEED)
+		brcr = FIELD_PREP(I2C_BRCR_BRCNT1, brcr);
+	else
+		brcr = FIELD_PREP(I2C_BRCR_BRCNT2, brcr);
 
 	/* set the baud rate counter register */
-	writel((brcr1 | brcr2), priv->virtbase + I2C_BRCR);
+	writel(brcr, priv->virtbase + I2C_BRCR);
 
-	/*
-	 * set the speed mode. Currently we support
-	 * only standard and fast mode of operation
-	 * TODO - support for fast mode plus (up to 1Mb/s)
-	 * and high speed (up to 3.4 Mb/s)
-	 */
-	if (priv->sm > I2C_FREQ_MODE_FAST) {
-		dev_err(&priv->adev->dev,
-			"do not support this mode defaulting to std. mode\n");
-		brcr2 = FIELD_PREP(I2C_BRCR_BRCNT2,
-				   i2c_clk / (I2C_MAX_STANDARD_MODE_FREQ * 2));
-		writel((brcr1 | brcr2), priv->virtbase + I2C_BRCR);
-		writel(FIELD_PREP(I2C_CR_SM, I2C_FREQ_MODE_STANDARD),
-		       priv->virtbase + I2C_CR);
-	}
+	/* set the speed mode */
 	writel(FIELD_PREP(I2C_CR_SM, priv->sm), priv->virtbase + I2C_CR);
 
 	/* set the Tx and Rx FIFO threshold */
@@ -1020,11 +1009,14 @@ static void nmk_i2c_of_probe(struct device_node *np,
 	if (of_property_read_u32(np, "clock-frequency", &priv->clk_freq))
 		priv->clk_freq = I2C_MAX_STANDARD_MODE_FREQ;
 
-	/* This driver only supports 'standard' and 'fast' modes of operation. */
 	if (priv->clk_freq <= I2C_MAX_STANDARD_MODE_FREQ)
 		priv->sm = I2C_FREQ_MODE_STANDARD;
-	else
+	else if (priv->clk_freq <= I2C_MAX_FAST_MODE_FREQ)
 		priv->sm = I2C_FREQ_MODE_FAST;
+	else if (priv->clk_freq <= I2C_MAX_FAST_MODE_PLUS_FREQ)
+		priv->sm = I2C_FREQ_MODE_FAST_PLUS;
+	else
+		priv->sm = I2C_FREQ_MODE_HIGH_SPEED;
 	priv->tft = 1; /* Tx FIFO threshold */
 	priv->rft = 8; /* Rx FIFO threshold */
 

From bbc89a6e837f291e7ad04cea50915c71110e781a Mon Sep 17 00:00:00 2001
From: Michael Wu <michael.wu@kneron.us>
Date: Thu, 3 Oct 2024 19:15:23 +0800
Subject: [PATCH 1357/1530] dt-bindings: i2c: snps,designware-i2c: declare bus
 capacitance and clk freq optimized

Since there are no registers controlling the hardware parameters
IC_CAP_LOADING and IC_CLK_FREQ_OPTIMIZATION, their values can only be
declared in the device tree.

snps,bus-capacitance-pf indicates the bus capacitance in picofarads (pF).
It affects the high and low pulse width of SCL line in high speed mode.
The legal values for this property are 100 and 400 only, and default
value is 100. This property corresponds to IC_CAP_LOADING.

snps,clk-freq-optimized indicates whether the hardware reduce its
internal clock frequency by reducing the internal latency required to
generate the high period and low period of SCL line. This property
corresponds to IC_CLK_FREQ_OPTIMIZATION.

The driver can calculate the high period count and low period count of
SCL line for high speed mode based on these two properties.

Signed-off-by: Michael Wu <michael.wu@kneron.us>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 .../bindings/i2c/snps,designware-i2c.yaml      | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml b/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml
index 60035a787e5c0..e5d05263c45a5 100644
--- a/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml
@@ -97,6 +97,22 @@ properties:
       - const: tx
       - const: rx
 
+  snps,bus-capacitance-pf:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      This property indicates the bus capacitance in picofarads (pF).
+      This value is used to compute the tHIGH and tLOW periods for high speed
+      mode.
+    enum: [100, 400]
+    default: 100
+
+  snps,clk-freq-optimized:
+    description:
+      This property indicates whether the hardware reduce its clock frequency
+      by reducing the internal latency required to generate the high period and
+      low period of SCL line.
+    type: boolean
+
 unevaluatedProperties: false
 
 required:
@@ -121,6 +137,8 @@ examples:
       i2c-sda-hold-time-ns = <300>;
       i2c-sda-falling-time-ns = <300>;
       i2c-scl-falling-time-ns = <300>;
+      snps,bus-capacitance-pf = <400>;
+      snps,clk-freq-optimized;
     };
   - |
     i2c@2000 {

From 61ab42c7f32d6d881a62e5cf76c46f95cb7ca2bd Mon Sep 17 00:00:00 2001
From: Michael Wu <michael.wu@kneron.us>
Date: Thu, 3 Oct 2024 19:15:24 +0800
Subject: [PATCH 1358/1530] i2c: designware: determine HS tHIGH and tLOW based
 on HW parameters

In commit 35eba185fd1a ("i2c: designware: Calculate SCL timing parameter
for High Speed Mode") the SCL high period count and low period count for
high speed mode are calculated based on fixed tHIGH = 160 and tLOW = 120.
However, the set of two fixed values is only applicable to the combination
of hardware parameters IC_CAP_LOADING is 400 and IC_CLK_FREQ_OPTIMIZATION
is true. Outside of this combination, the SCL frequency may not reach
3.4 MHz because the fixed tHIGH and tLOW are not small enough.

If IC_CAP_LOADING is 400, it means the bus capacitance is 400pF;
Otherwise, 100 pF. If IC_CLK_FREQ_OPTIMIZATION is true, it means that the
hardware reduces its internal clock frequency by reducing the internal
latency required to generate the high period and low period of the SCL line.

Section 3.15.4.5 in DesignWare DW_apb_i2b Databook v2.03 says that when
IC_CLK_FREQ_OPTIMIZATION = 0,

    MIN_SCL_HIGHtime = 60 ns for 3.4 Mbps, bus loading = 100pF
		     = 120 ns for 3.4 Mbps, bus loading = 400pF
    MIN_SCL_LOWtime = 160 ns for 3.4 Mbps, bus loading = 100pF
		    = 320 ns for 3.4 Mbps, bus loading = 400pF

and section 3.15.4.6 says that when IC_CLK_FREQ_OPTIMIZATION = 1,

    MIN_SCL_HIGHtime = 60 ns for 3.4 Mbps, bus loading = 100pF
		     = 160 ns for 3.4 Mbps, bus loading = 400pF
    MIN_SCL_LOWtime = 120 ns for 3.4 Mbps, bus loading = 100pF
		    = 320 ns for 3.4 Mbps, bus loading = 400pF

In order to calculate more accurate SCL high period count and low period
count for high speed mode, two hardware parameters IC_CAP_LOADING and
IC_CLK_FREQ_OPTIMIZATION must be considered together. Since there're no
registers controlliing these these two hardware parameters, users can
declare them in the device tree so that the driver can obtain them.

Signed-off-by: Michael Wu <michael.wu@kneron.us>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/busses/i2c-designware-common.c |  5 +++++
 drivers/i2c/busses/i2c-designware-core.h   |  6 ++++++
 drivers/i2c/busses/i2c-designware-master.c | 23 ++++++++++++++++++++--
 3 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c
index 443f946acf361..857783d458fbd 100644
--- a/drivers/i2c/busses/i2c-designware-common.c
+++ b/drivers/i2c/busses/i2c-designware-common.c
@@ -382,6 +382,11 @@ int i2c_dw_fw_parse_and_configure(struct dw_i2c_dev *dev)
 
 	i2c_parse_fw_timings(device, t, false);
 
+	if (device_property_read_u32(device, "snps,bus-capacitance-pf", &dev->bus_capacitance_pF))
+		dev->bus_capacitance_pF = 100;
+
+	dev->clk_freq_optimized = device_property_read_bool(device, "snps,clk-freq-optimized");
+
 	i2c_dw_adjust_bus_speed(dev);
 
 	if (is_of_node(fwnode))
diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h
index 520f9699e3bd2..347843b4f5dd7 100644
--- a/drivers/i2c/busses/i2c-designware-core.h
+++ b/drivers/i2c/busses/i2c-designware-core.h
@@ -242,6 +242,10 @@ struct reset_control;
  * @set_sda_hold_time: callback to retrieve IP specific SDA hold timing
  * @mode: operation mode - DW_IC_MASTER or DW_IC_SLAVE
  * @rinfo: I²C GPIO recovery information
+ * @bus_capacitance_pF: bus capacitance in picofarads
+ * @clk_freq_optimized: if this value is true, it means the hardware reduces
+ *	its internal clock frequency by reducing the internal latency required
+ *	to generate the high period and low period of SCL line.
  *
  * HCNT and LCNT parameters can be used if the platform knows more accurate
  * values than the one computed based only on the input clock frequency.
@@ -299,6 +303,8 @@ struct dw_i2c_dev {
 	int			(*set_sda_hold_time)(struct dw_i2c_dev *dev);
 	int			mode;
 	struct i2c_bus_recovery_info rinfo;
+	u32			bus_capacitance_pF;
+	bool			clk_freq_optimized;
 };
 
 #define ACCESS_INTR_MASK			BIT(0)
diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c
index 528b969253a7f..eca8998d640fb 100644
--- a/drivers/i2c/busses/i2c-designware-master.c
+++ b/drivers/i2c/busses/i2c-designware-master.c
@@ -151,19 +151,38 @@ static int i2c_dw_set_timings_master(struct dw_i2c_dev *dev)
 			dev->hs_hcnt = 0;
 			dev->hs_lcnt = 0;
 		} else if (!dev->hs_hcnt || !dev->hs_lcnt) {
+			u32 t_high, t_low;
+
+			/*
+			 * The legal values stated in the databook for bus
+			 * capacitance are only 100pF and 400pF.
+			 * If dev->bus_capacitance_pF is greater than or equals
+			 * to 400, t_high and t_low are assumed to be
+			 * appropriate values for 400pF, otherwise 100pF.
+			 */
+			if (dev->bus_capacitance_pF >= 400) {
+				/* assume bus capacitance is 400pF */
+				t_high = dev->clk_freq_optimized ? 160 : 120;
+				t_low = 320;
+			} else {
+				/* assume bus capacitance is 100pF */
+				t_high = 60;
+				t_low = dev->clk_freq_optimized ? 120 : 160;
+			}
+
 			ic_clk = i2c_dw_clk_rate(dev);
 			dev->hs_hcnt =
 				i2c_dw_scl_hcnt(dev,
 						DW_IC_HS_SCL_HCNT,
 						ic_clk,
-						160,	/* tHIGH = 160 ns */
+						t_high,
 						sda_falling_time,
 						0);	/* No offset */
 			dev->hs_lcnt =
 				i2c_dw_scl_lcnt(dev,
 						DW_IC_HS_SCL_LCNT,
 						ic_clk,
-						320,	/* tLOW = 320 ns */
+						t_low,
 						scl_falling_time,
 						0);	/* No offset */
 		}

From 16470f60666618830cb9f0b8dfafd34a838c6dbd Mon Sep 17 00:00:00 2001
From: Brendan Higgins <brendanhiggins@google.com>
Date: Fri, 15 Nov 2024 04:43:03 +0000
Subject: [PATCH 1359/1530] MAINTAINERS: transfer i2c-aspeed maintainership
 from Brendan to Ryan

Remove Brendan Higgins <brendanhiggins@google.com> from i2c-aspeed entry
and replace with Ryan Chen <ryan_chen@aspeedtech.com>.

Signed-off-by: Brendan Higgins <brendanhiggins@google.com>
Acked-by: Ryan Chen <ryan_chen@aspeedtech.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index e7f0170977013..d59434619fdf0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2213,7 +2213,7 @@ F:	drivers/mmc/host/usdhi6rol0.c
 F:	drivers/pinctrl/pinctrl-artpec*
 
 ARM/ASPEED I2C DRIVER
-M:	Brendan Higgins <brendanhiggins@google.com>
+M:	Ryan Chen <ryan_chen@aspeedtech.com>
 R:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
 R:	Joel Stanley <joel@jms.id.au>
 L:	linux-i2c@vger.kernel.org

From 998b5a78a9ce1cc4378e7281e4ea310e37596170 Mon Sep 17 00:00:00 2001
From: Aleksa Savic <savicaleksa83@gmail.com>
Date: Sun, 24 Nov 2024 16:27:24 +0100
Subject: [PATCH 1360/1530] hwmon: (aquacomputer_d5next) Fix length of
 speed_input array

Commit 120584c728a6 ("hwmon: (aquacomputer_d5next) Add support for Octo
flow sensor") added support for reading Octo flow sensor, but didn't
update the priv->speed_input array length. Since Octo has 8 fans, with
the addition of the flow sensor the proper length for speed_input is 9.

Reported by Arne Schwabe on Github [1], who received a UBSAN warning.

Fixes: 120584c728a6 ("hwmon: (aquacomputer_d5next) Add support for Octo flow sensor")
Closes: https://github.com/aleksamagicka/aquacomputer_d5next-hwmon/issues/100 [1]
Reported-by: Arne Schwabe <arne@rfc2549.org>
Signed-off-by: Aleksa Savic <savicaleksa83@gmail.com>
Message-ID: <20241124152725.7205-1-savicaleksa83@gmail.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/aquacomputer_d5next.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/aquacomputer_d5next.c b/drivers/hwmon/aquacomputer_d5next.c
index 34cac27e4ddec..0dcb8a3a691d6 100644
--- a/drivers/hwmon/aquacomputer_d5next.c
+++ b/drivers/hwmon/aquacomputer_d5next.c
@@ -597,7 +597,7 @@ struct aqc_data {
 
 	/* Sensor values */
 	s32 temp_input[20];	/* Max 4 physical and 16 virtual or 8 physical and 12 virtual */
-	s32 speed_input[8];
+	s32 speed_input[9];
 	u32 speed_input_min[1];
 	u32 speed_input_target[1];
 	u32 speed_input_max[1];

From 8edd00b06f21800c547a9fc3a4cf83dc084fd104 Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Wed, 2 Oct 2024 11:47:59 +0100
Subject: [PATCH 1361/1530] dt-bindings: mailbox: mpfs: fix reg properties

When the binding for this was originally written, and later modified,
mistakes were made - and the precise nature of the later modification
should have been a giveaway, but alas I was naive at the time.

A more correct modelling of the hardware is to use two syscons and have
a single reg entry for the mailbox, containing the mailbox region. The
two syscons contain the general control/status registers for the mailbox
and the interrupt related registers respectively. The reason for two
syscons is that the same mailbox is present on the non-SoC version of
the FPGA, which has no interrupt controller, and the shared part of the
rtl was unchanged between devices.

This is now coming to a head, because the control/status registers share
a register region with the "tvs" (temperature & voltage sensors)
registers and, as it turns out, people do want to monitor temperatures
and voltages...

Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 .../bindings/mailbox/microchip,mpfs-mailbox.yaml    | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/mailbox/microchip,mpfs-mailbox.yaml b/Documentation/devicetree/bindings/mailbox/microchip,mpfs-mailbox.yaml
index 404477910f029..1332aab9a888f 100644
--- a/Documentation/devicetree/bindings/mailbox/microchip,mpfs-mailbox.yaml
+++ b/Documentation/devicetree/bindings/mailbox/microchip,mpfs-mailbox.yaml
@@ -15,6 +15,8 @@ properties:
 
   reg:
     oneOf:
+      - items:
+          - description: mailbox data registers
       - items:
           - description: mailbox control & data registers
           - description: mailbox interrupt registers
@@ -23,6 +25,7 @@ properties:
           - description: mailbox control registers
           - description: mailbox interrupt registers
           - description: mailbox data registers
+        deprecated: true
 
   interrupts:
     maxItems: 1
@@ -41,12 +44,12 @@ additionalProperties: false
 examples:
   - |
     soc {
-      #address-cells = <2>;
-      #size-cells = <2>;
-      mbox: mailbox@37020000 {
+      #address-cells = <1>;
+      #size-cells = <1>;
+
+      mailbox@37020800 {
         compatible = "microchip,mpfs-mailbox";
-        reg = <0x0 0x37020000 0x0 0x58>, <0x0 0x2000318C 0x0 0x40>,
-              <0x0 0x37020800 0x0 0x100>;
+        reg = <0x37020800 0x100>;
         interrupt-parent = <&L1>;
         interrupts = <96>;
         #mbox-cells = <1>;

From a4123ffab9ece0c2d3d5c460724d49c4051fd279 Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Wed, 2 Oct 2024 11:48:00 +0100
Subject: [PATCH 1362/1530] mailbox: mpfs: support new, syscon based,
 devicetree configuration

The two previous bindings for this hardware were incorrect, as the
control/status and interrupt register regions should have been described
as syscons and dealt with via regmap in the driver. Add support for
accessing these registers using that method now, so that the hwmon
driver can be supported without using auxdev or hacks with io_remap().

Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 drivers/mailbox/Kconfig        |  1 +
 drivers/mailbox/mailbox-mpfs.c | 81 ++++++++++++++++++++++++++++------
 2 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig
index 6fb995778636a..f856e01429aae 100644
--- a/drivers/mailbox/Kconfig
+++ b/drivers/mailbox/Kconfig
@@ -168,6 +168,7 @@ config MAILBOX_TEST
 config POLARFIRE_SOC_MAILBOX
 	tristate "PolarFire SoC (MPFS) Mailbox"
 	depends on HAS_IOMEM
+	depends on MFD_SYSCON
 	depends on ARCH_MICROCHIP_POLARFIRE || COMPILE_TEST
 	help
 	  This driver adds support for the PolarFire SoC (MPFS) mailbox controller.
diff --git a/drivers/mailbox/mailbox-mpfs.c b/drivers/mailbox/mailbox-mpfs.c
index 20ee283a04cc6..4df546e3b7eae 100644
--- a/drivers/mailbox/mailbox-mpfs.c
+++ b/drivers/mailbox/mailbox-mpfs.c
@@ -13,12 +13,15 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/regmap.h>
 #include <linux/interrupt.h>
+#include <linux/mfd/syscon.h>
 #include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
 #include <linux/mailbox_controller.h>
 #include <soc/microchip/mpfs.h>
 
+#define MESSAGE_INT_OFFSET		0x18cu
 #define SERVICES_CR_OFFSET		0x50u
 #define SERVICES_SR_OFFSET		0x54u
 #define MAILBOX_REG_OFFSET		0x800u
@@ -68,6 +71,7 @@ struct mpfs_mbox {
 	void __iomem *int_reg;
 	struct mbox_chan chans[1];
 	struct mpfs_mss_response *response;
+	struct regmap *sysreg_scb, *control_scb;
 	u16 resp_offset;
 };
 
@@ -75,7 +79,10 @@ static bool mpfs_mbox_busy(struct mpfs_mbox *mbox)
 {
 	u32 status;
 
-	status = readl_relaxed(mbox->ctrl_base + SERVICES_SR_OFFSET);
+	if (mbox->control_scb)
+		regmap_read(mbox->control_scb, SERVICES_SR_OFFSET, &status);
+	else
+		status = readl_relaxed(mbox->ctrl_base + SERVICES_SR_OFFSET);
 
 	return status & SCB_STATUS_BUSY_MASK;
 }
@@ -95,7 +102,11 @@ static bool mpfs_mbox_last_tx_done(struct mbox_chan *chan)
 	 * Failed services are intended to generated interrupts, but in reality
 	 * this does not happen, so the status must be checked here.
 	 */
-	val = readl_relaxed(mbox->ctrl_base + SERVICES_SR_OFFSET);
+	if (mbox->control_scb)
+		regmap_read(mbox->control_scb, SERVICES_SR_OFFSET, &val);
+	else
+		val = readl_relaxed(mbox->ctrl_base + SERVICES_SR_OFFSET);
+
 	response->resp_status = (val & SCB_STATUS_MASK) >> SCB_STATUS_POS;
 
 	return true;
@@ -143,7 +154,12 @@ static int mpfs_mbox_send_data(struct mbox_chan *chan, void *data)
 
 	tx_trigger = (opt_sel << SCB_CTRL_POS) & SCB_CTRL_MASK;
 	tx_trigger |= SCB_CTRL_REQ_MASK | SCB_STATUS_NOTIFY_MASK;
-	writel_relaxed(tx_trigger, mbox->ctrl_base + SERVICES_CR_OFFSET);
+
+	if (mbox->control_scb)
+		regmap_write(mbox->control_scb, SERVICES_CR_OFFSET, tx_trigger);
+	else
+		writel_relaxed(tx_trigger, mbox->ctrl_base + SERVICES_CR_OFFSET);
+
 
 	return 0;
 }
@@ -185,7 +201,10 @@ static irqreturn_t mpfs_mbox_inbox_isr(int irq, void *data)
 	struct mbox_chan *chan = data;
 	struct mpfs_mbox *mbox = (struct mpfs_mbox *)chan->con_priv;
 
-	writel_relaxed(0, mbox->int_reg);
+	if (mbox->control_scb)
+		regmap_write(mbox->sysreg_scb, MESSAGE_INT_OFFSET, 0);
+	else
+		writel_relaxed(0, mbox->int_reg);
 
 	mpfs_mbox_rx_data(chan);
 
@@ -221,28 +240,62 @@ static const struct mbox_chan_ops mpfs_mbox_ops = {
 	.last_tx_done = mpfs_mbox_last_tx_done,
 };
 
-static int mpfs_mbox_probe(struct platform_device *pdev)
+static inline int mpfs_mbox_syscon_probe(struct mpfs_mbox *mbox, struct platform_device *pdev)
 {
-	struct mpfs_mbox *mbox;
-	struct resource *regs;
-	int ret;
+	mbox->control_scb = syscon_regmap_lookup_by_compatible("microchip,mpfs-control-scb");
+	if (IS_ERR(mbox->control_scb))
+		return PTR_ERR(mbox->control_scb);
 
-	mbox = devm_kzalloc(&pdev->dev, sizeof(*mbox), GFP_KERNEL);
-	if (!mbox)
-		return -ENOMEM;
+	mbox->sysreg_scb = syscon_regmap_lookup_by_compatible("microchip,mpfs-sysreg-scb");
+	if (IS_ERR(mbox->sysreg_scb))
+		return PTR_ERR(mbox->sysreg_scb);
+
+	mbox->mbox_base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(mbox->ctrl_base))
+		return PTR_ERR(mbox->mbox_base);
+
+	return 0;
+}
+
+static inline int mpfs_mbox_old_format_probe(struct mpfs_mbox *mbox, struct platform_device *pdev)
+{
+	dev_warn(&pdev->dev, "falling back to old devicetree format");
 
-	mbox->ctrl_base = devm_platform_get_and_ioremap_resource(pdev, 0, &regs);
+	mbox->ctrl_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(mbox->ctrl_base))
 		return PTR_ERR(mbox->ctrl_base);
 
-	mbox->int_reg = devm_platform_get_and_ioremap_resource(pdev, 1, &regs);
+	mbox->int_reg = devm_platform_ioremap_resource(pdev, 1);
 	if (IS_ERR(mbox->int_reg))
 		return PTR_ERR(mbox->int_reg);
 
-	mbox->mbox_base = devm_platform_get_and_ioremap_resource(pdev, 2, &regs);
+	mbox->mbox_base = devm_platform_ioremap_resource(pdev, 2);
 	if (IS_ERR(mbox->mbox_base)) // account for the old dt-binding w/ 2 regs
 		mbox->mbox_base = mbox->ctrl_base + MAILBOX_REG_OFFSET;
 
+	return 0;
+}
+
+static int mpfs_mbox_probe(struct platform_device *pdev)
+{
+	struct mpfs_mbox *mbox;
+	int ret;
+
+	mbox = devm_kzalloc(&pdev->dev, sizeof(*mbox), GFP_KERNEL);
+	if (!mbox)
+		return -ENOMEM;
+
+	ret = mpfs_mbox_syscon_probe(mbox, pdev);
+	if (ret) {
+		/*
+		 * set this to null, so it can be used as the decision for to
+		 * regmap or not to regmap
+		 */
+		mbox->control_scb = NULL;
+		ret = mpfs_mbox_old_format_probe(mbox, pdev);
+		if (ret)
+			return ret;
+	}
 	mbox->irq = platform_get_irq(pdev, 0);
 	if (mbox->irq < 0)
 		return mbox->irq;

From 08fb6d8ff900a1d06ef2f4a6ded45cdaa7140c01 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Fri, 4 Oct 2024 12:41:23 +0300
Subject: [PATCH 1363/1530] mailbox: mtk-cmdq-mailbox: Switch to
 __pm_runtime_put_autosuspend()

pm_runtime_put_autosuspend() will soon be changed to include a call to
pm_runtime_mark_last_busy(). This patch switches the current users to
__pm_runtime_put_autosuspend() which will continue to have the
functionality of old pm_runtime_put_autosuspend().

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Matthias Brugger <matthias.bgg@gmail.com>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 drivers/mailbox/mtk-cmdq-mailbox.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index 4bff73532085b..180906761eda7 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -397,7 +397,7 @@ static int cmdq_mbox_send_data(struct mbox_chan *chan, void *data)
 
 	task = kzalloc(sizeof(*task), GFP_ATOMIC);
 	if (!task) {
-		pm_runtime_put_autosuspend(cmdq->mbox.dev);
+		__pm_runtime_put_autosuspend(cmdq->mbox.dev);
 		return -ENOMEM;
 	}
 
@@ -447,7 +447,7 @@ static int cmdq_mbox_send_data(struct mbox_chan *chan, void *data)
 	list_move_tail(&task->list_entry, &thread->task_busy_list);
 
 	pm_runtime_mark_last_busy(cmdq->mbox.dev);
-	pm_runtime_put_autosuspend(cmdq->mbox.dev);
+	__pm_runtime_put_autosuspend(cmdq->mbox.dev);
 
 	return 0;
 }
@@ -495,7 +495,7 @@ static void cmdq_mbox_shutdown(struct mbox_chan *chan)
 	spin_unlock_irqrestore(&thread->chan->lock, flags);
 
 	pm_runtime_mark_last_busy(cmdq->mbox.dev);
-	pm_runtime_put_autosuspend(cmdq->mbox.dev);
+	__pm_runtime_put_autosuspend(cmdq->mbox.dev);
 }
 
 static int cmdq_mbox_flush(struct mbox_chan *chan, unsigned long timeout)
@@ -535,7 +535,7 @@ static int cmdq_mbox_flush(struct mbox_chan *chan, unsigned long timeout)
 out:
 	spin_unlock_irqrestore(&thread->chan->lock, flags);
 	pm_runtime_mark_last_busy(cmdq->mbox.dev);
-	pm_runtime_put_autosuspend(cmdq->mbox.dev);
+	__pm_runtime_put_autosuspend(cmdq->mbox.dev);
 
 	return 0;
 
@@ -550,7 +550,7 @@ static int cmdq_mbox_flush(struct mbox_chan *chan, unsigned long timeout)
 		return -EFAULT;
 	}
 	pm_runtime_mark_last_busy(cmdq->mbox.dev);
-	pm_runtime_put_autosuspend(cmdq->mbox.dev);
+	__pm_runtime_put_autosuspend(cmdq->mbox.dev);
 	return 0;
 }
 

From bfa0e78da8ef59bac5db664bcf9b5662940d928d Mon Sep 17 00:00:00 2001
From: Sibi Sankar <quic_sibis@quicinc.com>
Date: Wed, 30 Oct 2024 18:25:12 +0530
Subject: [PATCH 1364/1530] mailbox: qcom-cpucp: Mark the irq with
 IRQF_NO_SUSPEND flag

The qcom-cpucp mailbox irq is expected to function during suspend-resume
cycle particularly when the scmi cpufreq driver can query the current
frequency using the get_level message after the cpus are brought up during
resume. Hence mark the irq with IRQF_NO_SUSPEND flag to fix the do_xfer
failures we see during resume.

Err Logs:
arm-scmi firmware:scmi: timed out in resp(caller:do_xfer+0x164/0x568)
cpufreq: cpufreq_online: ->get() failed

Reported-by: Johan Hovold <johan+linaro@kernel.org>
Closes: https://lore.kernel.org/lkml/ZtgFj1y5ggipgEOS@hovoldconsulting.com/
Fixes: 0e2a9a03106c ("mailbox: Add support for QTI CPUCP mailbox controller")
Signed-off-by: Sibi Sankar <quic_sibis@quicinc.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Tested-by: Johan Hovold <johan+linaro@kernel.org>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 drivers/mailbox/qcom-cpucp-mbox.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mailbox/qcom-cpucp-mbox.c b/drivers/mailbox/qcom-cpucp-mbox.c
index e5437c294803c..44f4ed15f8184 100644
--- a/drivers/mailbox/qcom-cpucp-mbox.c
+++ b/drivers/mailbox/qcom-cpucp-mbox.c
@@ -138,7 +138,7 @@ static int qcom_cpucp_mbox_probe(struct platform_device *pdev)
 		return irq;
 
 	ret = devm_request_irq(dev, irq, qcom_cpucp_mbox_irq_fn,
-			       IRQF_TRIGGER_HIGH, "apss_cpucp_mbox", cpucp);
+			       IRQF_TRIGGER_HIGH | IRQF_NO_SUSPEND, "apss_cpucp_mbox", cpucp);
 	if (ret < 0)
 		return dev_err_probe(dev, ret, "Failed to register irq: %d\n", irq);
 

From ad55c5c00ff9aac1ee0e7f6ca1205bfa79789d0b Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Tue, 15 Oct 2024 16:33:21 -0500
Subject: [PATCH 1365/1530] mailbox: ti-msgmgr: Remove use of of_match_ptr()
 helper

When OF support is disabled the of_device_id struct match table can be
conditionally compiled out, this helper allows the assignment to also be
turned into a NULL conditionally. When the of_device_id struct is not
conditionally defined based on OF then the table will be unused causing a
warning. The two options are to either set the table as _maybe_unused, or
to just remove this helper since the table will always be defined.
Do the latter here.

Signed-off-by: Andrew Davis <afd@ti.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 drivers/mailbox/ti-msgmgr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mailbox/ti-msgmgr.c b/drivers/mailbox/ti-msgmgr.c
index 9d2d4ff6cda40..8eb8df8d95a4c 100644
--- a/drivers/mailbox/ti-msgmgr.c
+++ b/drivers/mailbox/ti-msgmgr.c
@@ -920,7 +920,7 @@ static struct platform_driver ti_msgmgr_driver = {
 	.probe = ti_msgmgr_probe,
 	.driver = {
 		   .name = "ti-msgmgr",
-		   .of_match_table = of_match_ptr(ti_msgmgr_of_match),
+		   .of_match_table = ti_msgmgr_of_match,
 		   .pm = &ti_msgmgr_pm_ops,
 	},
 };

From ff391d4537585912032eaf7722ca235228660787 Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Tue, 15 Oct 2024 16:33:22 -0500
Subject: [PATCH 1366/1530] mailbox: ti-msgmgr: Allow building under
 COMPILE_TEST

The TI message manager driver can be compiled without ARCH_KEYSTONE
nor ARCH_K3 enabled. Allow it to be built under COMPILE_TEST.

Signed-off-by: Andrew Davis <afd@ti.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 drivers/mailbox/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig
index f856e01429aae..468c181129f32 100644
--- a/drivers/mailbox/Kconfig
+++ b/drivers/mailbox/Kconfig
@@ -127,7 +127,7 @@ config STI_MBOX
 
 config TI_MESSAGE_MANAGER
 	tristate "Texas Instruments Message Manager Driver"
-	depends on ARCH_KEYSTONE || ARCH_K3
+	depends on ARCH_KEYSTONE || ARCH_K3 || COMPILE_TEST
 	default ARCH_K3
 	help
 	  An implementation of Message Manager slave driver for Keystone

From 71987bc9225252e5f9de020042eca2fd22f71f32 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Thu, 17 Oct 2024 21:17:23 +0300
Subject: [PATCH 1367/1530] dt-bindings: mailbox: qcom-ipcc: Add SAR2130P
 compatible

Document compatible for the IPCC mailbox controller on SAR2130P platform.

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml b/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml
index 2d66770ed3612..ecb4ec1e0a828 100644
--- a/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml
+++ b/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml
@@ -28,6 +28,7 @@ properties:
           - qcom,qdu1000-ipcc
           - qcom,sa8255p-ipcc
           - qcom,sa8775p-ipcc
+          - qcom,sar2130p-ipcc
           - qcom,sc7280-ipcc
           - qcom,sc8280xp-ipcc
           - qcom,sdx75-ipcc

From cba781d79df85282041b2066df4d653b62157ad8 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 17 Oct 2024 11:14:47 +0200
Subject: [PATCH 1368/1530] dt-bindings: mailbox: qcom,apcs-kpss-global:
 correct expected clocks for fallbacks

Commit 1e9cb7e007dc ("dt-bindings: mailbox: qcom,apcs-kpss-global: use
fallbacks") and commit 34d8775a0edc ("dt-bindings: mailbox:
qcom,apcs-kpss-global: use fallbacks for few variants") added fallbacks
to few existing compatibles.  Neither devices with these existing
compatibles nor devices using fallbacks alone, have clocks, so the
"if:then:" block defining this constrain should be written as
"contains:".

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 .../bindings/mailbox/qcom,apcs-kpss-global.yaml     | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml
index 982c741e62251..9d2dfd85b2073 100644
--- a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml
+++ b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml
@@ -165,12 +165,13 @@ allOf:
   - if:
       properties:
         compatible:
-          enum:
-            - qcom,msm8953-apcs-kpss-global
-            - qcom,msm8994-apcs-kpss-global
-            - qcom,msm8996-apcs-hmss-global
-            - qcom,qcm2290-apcs-hmss-global
-            - qcom,sdm845-apss-shared
+          contains:
+            enum:
+              - qcom,msm8953-apcs-kpss-global
+              - qcom,msm8994-apcs-kpss-global
+              - qcom,msm8996-apcs-hmss-global
+              - qcom,qcm2290-apcs-hmss-global
+              - qcom,sdm845-apss-shared
     then:
       properties:
         clocks: false

From f8809b1f48531b2698a2c10ac874eb35222b4cc1 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 22 Oct 2024 08:42:38 +0200
Subject: [PATCH 1369/1530] dt-bindings: mailbox: qcom-ipcc: Add SM8750

Document compatible for Qualcomm SM8750 SoC IPCC, compatible with
existing generic fallback.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml b/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml
index ecb4ec1e0a828..f69c0ec5d19d3 100644
--- a/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml
+++ b/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml
@@ -39,6 +39,7 @@ properties:
           - qcom,sm8450-ipcc
           - qcom,sm8550-ipcc
           - qcom,sm8650-ipcc
+          - qcom,sm8750-ipcc
           - qcom,x1e80100-ipcc
       - const: qcom,ipcc
 

From 271ee263cc8771982809185007181ca10346fe73 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Tue, 29 Oct 2024 21:16:28 +0800
Subject: [PATCH 1370/1530] mailbox: mtk-cmdq: fix wrong use of sizeof in
 cmdq_get_clocks()

It should be size of the struct clk_bulk_data, not data pointer pass to
devm_kcalloc().

Fixes: aa1609f571ca ("mailbox: mtk-cmdq: Dynamically allocate clk_bulk_data structure")
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 drivers/mailbox/mtk-cmdq-mailbox.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index 180906761eda7..4324c53e372df 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -584,7 +584,7 @@ static int cmdq_get_clocks(struct device *dev, struct cmdq *cmdq)
 	struct clk_bulk_data *clks;
 
 	cmdq->clocks = devm_kcalloc(dev, cmdq->pdata->gce_num,
-				    sizeof(cmdq->clocks), GFP_KERNEL);
+				    sizeof(*cmdq->clocks), GFP_KERNEL);
 	if (!cmdq->clocks)
 		return -ENOMEM;
 

From 5d4d263e1c6b6b18acb4d67fd3b9af71b7404924 Mon Sep 17 00:00:00 2001
From: Michal Wilczynski <m.wilczynski@samsung.com>
Date: Mon, 4 Nov 2024 11:07:32 +0100
Subject: [PATCH 1371/1530] mailbox: Introduce support for T-head TH1520
 Mailbox driver

This driver was tested using the drm/imagination GPU driver. It was able
to successfully power on the GPU, by passing a command through mailbox
from E910 core to E902 that's responsible for powering up the GPU. The
GPU driver was able to read the BVNC version from control registers,
which confirms it was successfully powered on.

[   33.957467] powervr ffef400000.gpu: [drm] loaded firmware
powervr/rogue_36.52.104.182_v1.fw
[   33.966008] powervr ffef400000.gpu: [drm] FW version v1.0 (build
6621747 OS)
[   38.978542] powervr ffef400000.gpu: [drm] *ERROR* Firmware failed to
boot

Though the driver still fails to boot the firmware, the mailbox driver
works when used with the not-yet-upstreamed firmware AON driver. There
is ongoing work to get the BXM-4-64 supported with the drm/imagination
driver [1], though it's not completed yet.

This work is based on the driver from the vendor kernel [2].

Link: https://gitlab.freedesktop.org/imagination/linux-firmware/-/issues/2 [1]
Link: https://github.com/revyos/thead-kernel.git [2]

Signed-off-by: Michal Wilczynski <m.wilczynski@samsung.com>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 MAINTAINERS                      |   1 +
 drivers/mailbox/Kconfig          |  10 +
 drivers/mailbox/Makefile         |   2 +
 drivers/mailbox/mailbox-th1520.c | 597 +++++++++++++++++++++++++++++++
 4 files changed, 610 insertions(+)
 create mode 100644 drivers/mailbox/mailbox-th1520.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 21fdaa19229ae..0dfac18899230 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19871,6 +19871,7 @@ T:	git https://github.com/pdp7/linux.git
 F:	Documentation/devicetree/bindings/clock/thead,th1520-clk-ap.yaml
 F:	arch/riscv/boot/dts/thead/
 F:	drivers/clk/thead/clk-th1520-ap.c
+F:	drivers/mailbox/mailbox-th1520.c
 F:	include/dt-bindings/clock/thead,th1520-clk-ap.h
 
 RNBD BLOCK DRIVERS
diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig
index 468c181129f32..8ecba7fb999e9 100644
--- a/drivers/mailbox/Kconfig
+++ b/drivers/mailbox/Kconfig
@@ -296,4 +296,14 @@ config QCOM_IPCC
 	  acts as an interrupt controller for receiving interrupts from clients.
 	  Say Y here if you want to build this driver.
 
+config THEAD_TH1520_MBOX
+	tristate "T-head TH1520 Mailbox"
+	depends on ARCH_THEAD || COMPILE_TEST
+	help
+	  Mailbox driver implementation for the Thead TH-1520 platform. Enables
+	  two cores within the SoC to communicate and coordinate by passing
+	  messages. Could be used to communicate between E910 core, on which the
+	  kernel is running, and E902 core used for power management among other
+	  things.
+
 endif
diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile
index 3c3c27d54c13d..5f4f5b0ce2ccf 100644
--- a/drivers/mailbox/Makefile
+++ b/drivers/mailbox/Makefile
@@ -64,3 +64,5 @@ obj-$(CONFIG_SPRD_MBOX)		+= sprd-mailbox.o
 obj-$(CONFIG_QCOM_CPUCP_MBOX)	+= qcom-cpucp-mbox.o
 
 obj-$(CONFIG_QCOM_IPCC)		+= qcom-ipcc.o
+
+obj-$(CONFIG_THEAD_TH1520_MBOX)	+= mailbox-th1520.o
diff --git a/drivers/mailbox/mailbox-th1520.c b/drivers/mailbox/mailbox-th1520.c
new file mode 100644
index 0000000000000..4e84640ac3b87
--- /dev/null
+++ b/drivers/mailbox/mailbox-th1520.c
@@ -0,0 +1,597 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Alibaba Group Holding Limited.
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mailbox_controller.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+/* Status Register */
+#define TH_1520_MBOX_STA 0x0
+#define TH_1520_MBOX_CLR 0x4
+#define TH_1520_MBOX_MASK 0xc
+
+/* Transmit/receive data register:
+ * INFO0 ~ INFO6
+ */
+#define TH_1520_MBOX_INFO_NUM 8
+#define TH_1520_MBOX_DATA_INFO_NUM 7
+#define TH_1520_MBOX_INFO0 0x14
+/* Transmit ack register: INFO7 */
+#define TH_1520_MBOX_INFO7 0x30
+
+/* Generate remote icu IRQ Register */
+#define TH_1520_MBOX_GEN 0x10
+#define TH_1520_MBOX_GEN_RX_DATA BIT(6)
+#define TH_1520_MBOX_GEN_TX_ACK BIT(7)
+
+#define TH_1520_MBOX_CHAN_RES_SIZE 0x1000
+#define TH_1520_MBOX_CHANS 4
+#define TH_1520_MBOX_CHAN_NAME_SIZE 20
+
+#define TH_1520_MBOX_ACK_MAGIC 0xdeadbeaf
+
+#ifdef CONFIG_PM_SLEEP
+/* store MBOX context across system-wide suspend/resume transitions */
+struct th1520_mbox_context {
+	u32 intr_mask[TH_1520_MBOX_CHANS - 1];
+};
+#endif
+
+enum th1520_mbox_icu_cpu_id {
+	TH_1520_MBOX_ICU_KERNEL_CPU0, /* 910T */
+	TH_1520_MBOX_ICU_CPU1, /* 902 */
+	TH_1520_MBOX_ICU_CPU2, /* 906 */
+	TH_1520_MBOX_ICU_CPU3, /* 910R */
+};
+
+struct th1520_mbox_con_priv {
+	enum th1520_mbox_icu_cpu_id idx;
+	void __iomem *comm_local_base;
+	void __iomem *comm_remote_base;
+	char irq_desc[TH_1520_MBOX_CHAN_NAME_SIZE];
+	struct mbox_chan *chan;
+};
+
+struct th1520_mbox_priv {
+	struct device *dev;
+	void __iomem *local_icu[TH_1520_MBOX_CHANS];
+	void __iomem *remote_icu[TH_1520_MBOX_CHANS - 1];
+	void __iomem *cur_cpu_ch_base;
+	spinlock_t mbox_lock; /* control register lock */
+
+	struct mbox_controller mbox;
+	struct mbox_chan mbox_chans[TH_1520_MBOX_CHANS];
+	struct clk_bulk_data clocks[TH_1520_MBOX_CHANS];
+	struct th1520_mbox_con_priv con_priv[TH_1520_MBOX_CHANS];
+	int irq;
+#ifdef CONFIG_PM_SLEEP
+	struct th1520_mbox_context *ctx;
+#endif
+};
+
+static struct th1520_mbox_priv *
+to_th1520_mbox_priv(struct mbox_controller *mbox)
+{
+	return container_of(mbox, struct th1520_mbox_priv, mbox);
+}
+
+static void th1520_mbox_write(struct th1520_mbox_priv *priv, u32 val, u32 offs)
+{
+	iowrite32(val, priv->cur_cpu_ch_base + offs);
+}
+
+static u32 th1520_mbox_read(struct th1520_mbox_priv *priv, u32 offs)
+{
+	return ioread32(priv->cur_cpu_ch_base + offs);
+}
+
+static u32 th1520_mbox_rmw(struct th1520_mbox_priv *priv, u32 off, u32 set,
+			   u32 clr)
+{
+	unsigned long flags;
+	u32 val;
+
+	spin_lock_irqsave(&priv->mbox_lock, flags);
+	val = th1520_mbox_read(priv, off);
+	val &= ~clr;
+	val |= set;
+	th1520_mbox_write(priv, val, off);
+	spin_unlock_irqrestore(&priv->mbox_lock, flags);
+
+	return val;
+}
+
+static void th1520_mbox_chan_write(struct th1520_mbox_con_priv *cp, u32 val,
+				   u32 offs, bool is_remote)
+{
+	if (is_remote)
+		iowrite32(val, cp->comm_remote_base + offs);
+	else
+		iowrite32(val, cp->comm_local_base + offs);
+}
+
+static u32 th1520_mbox_chan_read(struct th1520_mbox_con_priv *cp, u32 offs,
+				 bool is_remote)
+{
+	if (is_remote)
+		return ioread32(cp->comm_remote_base + offs);
+	else
+		return ioread32(cp->comm_local_base + offs);
+}
+
+static void th1520_mbox_chan_rmw(struct th1520_mbox_con_priv *cp, u32 off,
+				 u32 set, u32 clr, bool is_remote)
+{
+	struct th1520_mbox_priv *priv = to_th1520_mbox_priv(cp->chan->mbox);
+	unsigned long flags;
+	u32 val;
+
+	spin_lock_irqsave(&priv->mbox_lock, flags);
+	val = th1520_mbox_chan_read(cp, off, is_remote);
+	val &= ~clr;
+	val |= set;
+	th1520_mbox_chan_write(cp, val, off, is_remote);
+	spin_unlock_irqrestore(&priv->mbox_lock, flags);
+}
+
+static void th1520_mbox_chan_rd_data(struct th1520_mbox_con_priv *cp,
+				     void *data, bool is_remote)
+{
+	u32 off = TH_1520_MBOX_INFO0;
+	u32 *arg = data;
+	u32 i;
+
+	/* read info0 ~ info6, totally 28 bytes
+	 * requires data memory size is 28 bytes
+	 */
+	for (i = 0; i < TH_1520_MBOX_DATA_INFO_NUM; i++) {
+		*arg = th1520_mbox_chan_read(cp, off, is_remote);
+		off += 4;
+		arg++;
+	}
+}
+
+static void th1520_mbox_chan_wr_data(struct th1520_mbox_con_priv *cp,
+				     void *data, bool is_remote)
+{
+	u32 off = TH_1520_MBOX_INFO0;
+	u32 *arg = data;
+	u32 i;
+
+	/* write info0 ~ info6, totally 28 bytes
+	 * requires data memory is 28 bytes valid data
+	 */
+	for (i = 0; i < TH_1520_MBOX_DATA_INFO_NUM; i++) {
+		th1520_mbox_chan_write(cp, *arg, off, is_remote);
+		off += 4;
+		arg++;
+	}
+}
+
+static void th1520_mbox_chan_wr_ack(struct th1520_mbox_con_priv *cp, void *data,
+				    bool is_remote)
+{
+	u32 off = TH_1520_MBOX_INFO7;
+	u32 *arg = data;
+
+	th1520_mbox_chan_write(cp, *arg, off, is_remote);
+}
+
+static int th1520_mbox_chan_id_to_mapbit(struct th1520_mbox_con_priv *cp)
+{
+	int mapbit = 0;
+	int i;
+
+	for (i = 0; i < TH_1520_MBOX_CHANS; i++) {
+		if (i == cp->idx)
+			return mapbit;
+
+		if (i != TH_1520_MBOX_ICU_KERNEL_CPU0)
+			mapbit++;
+	}
+
+	if (i == TH_1520_MBOX_CHANS)
+		dev_err(cp->chan->mbox->dev, "convert to mapbit failed\n");
+
+	return 0;
+}
+
+static irqreturn_t th1520_mbox_isr(int irq, void *p)
+{
+	struct mbox_chan *chan = p;
+	struct th1520_mbox_priv *priv = to_th1520_mbox_priv(chan->mbox);
+	struct th1520_mbox_con_priv *cp = chan->con_priv;
+	int mapbit = th1520_mbox_chan_id_to_mapbit(cp);
+	u32 sta, dat[TH_1520_MBOX_DATA_INFO_NUM];
+	u32 ack_magic = TH_1520_MBOX_ACK_MAGIC;
+	u32 info0_data, info7_data;
+
+	sta = th1520_mbox_read(priv, TH_1520_MBOX_STA);
+	if (!(sta & BIT(mapbit)))
+		return IRQ_NONE;
+
+	/* clear chan irq bit in STA register */
+	th1520_mbox_rmw(priv, TH_1520_MBOX_CLR, BIT(mapbit), 0);
+
+	/* info0 is the protocol word, should not be zero! */
+	info0_data = th1520_mbox_chan_read(cp, TH_1520_MBOX_INFO0, false);
+	if (info0_data) {
+		/* read info0~info6 data */
+		th1520_mbox_chan_rd_data(cp, dat, false);
+
+		/* clear local info0 */
+		th1520_mbox_chan_write(cp, 0x0, TH_1520_MBOX_INFO0, false);
+
+		/* notify remote cpu */
+		th1520_mbox_chan_wr_ack(cp, &ack_magic, true);
+		/* CPU1 902/906 use polling mode to monitor info7 */
+		if (cp->idx != TH_1520_MBOX_ICU_CPU1 &&
+		    cp->idx != TH_1520_MBOX_ICU_CPU2)
+			th1520_mbox_chan_rmw(cp, TH_1520_MBOX_GEN,
+					     TH_1520_MBOX_GEN_TX_ACK, 0, true);
+
+		/* transfer the data to client */
+		mbox_chan_received_data(chan, (void *)dat);
+	}
+
+	/* info7 magic value mean the real ack signal, not generate bit7 */
+	info7_data = th1520_mbox_chan_read(cp, TH_1520_MBOX_INFO7, false);
+	if (info7_data == TH_1520_MBOX_ACK_MAGIC) {
+		/* clear local info7 */
+		th1520_mbox_chan_write(cp, 0x0, TH_1520_MBOX_INFO7, false);
+
+		/* notify framework the last TX has completed */
+		mbox_chan_txdone(chan, 0);
+	}
+
+	if (!info0_data && !info7_data)
+		return IRQ_NONE;
+
+	return IRQ_HANDLED;
+}
+
+static int th1520_mbox_send_data(struct mbox_chan *chan, void *data)
+{
+	struct th1520_mbox_con_priv *cp = chan->con_priv;
+
+	th1520_mbox_chan_wr_data(cp, data, true);
+	th1520_mbox_chan_rmw(cp, TH_1520_MBOX_GEN, TH_1520_MBOX_GEN_RX_DATA, 0,
+			     true);
+	return 0;
+}
+
+static int th1520_mbox_startup(struct mbox_chan *chan)
+{
+	struct th1520_mbox_priv *priv = to_th1520_mbox_priv(chan->mbox);
+	struct th1520_mbox_con_priv *cp = chan->con_priv;
+	u32 data[8] = {};
+	int mask_bit;
+	int ret;
+
+	/* clear local and remote generate and info0~info7 */
+	th1520_mbox_chan_rmw(cp, TH_1520_MBOX_GEN, 0x0, 0xff, true);
+	th1520_mbox_chan_rmw(cp, TH_1520_MBOX_GEN, 0x0, 0xff, false);
+	th1520_mbox_chan_wr_ack(cp, &data[7], true);
+	th1520_mbox_chan_wr_ack(cp, &data[7], false);
+	th1520_mbox_chan_wr_data(cp, &data[0], true);
+	th1520_mbox_chan_wr_data(cp, &data[0], false);
+
+	/* enable the chan mask */
+	mask_bit = th1520_mbox_chan_id_to_mapbit(cp);
+	th1520_mbox_rmw(priv, TH_1520_MBOX_MASK, BIT(mask_bit), 0);
+
+	/*
+	 * Mixing devm_ managed resources with manual IRQ handling is generally
+	 * discouraged due to potential complexities with resource management,
+	 * especially when dealing with shared interrupts. However, in this case,
+	 * the approach is safe and effective because:
+	 *
+	 * 1. Each mailbox channel requests its IRQ within the .startup() callback
+	 *    and frees it within the .shutdown() callback.
+	 * 2. During device unbinding, the devm_ managed mailbox controller first
+	 *    iterates through all channels, ensuring that their IRQs are freed before
+	 *    any other devm_ resources are released.
+	 *
+	 * This ordering guarantees that no interrupts can be triggered from the device
+	 * while it is being unbound, preventing race conditions and ensuring system
+	 * stability.
+	 */
+	ret = request_irq(priv->irq, th1520_mbox_isr,
+			  IRQF_SHARED | IRQF_NO_SUSPEND, cp->irq_desc, chan);
+	if (ret) {
+		dev_err(priv->dev, "Unable to acquire IRQ %d\n", priv->irq);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void th1520_mbox_shutdown(struct mbox_chan *chan)
+{
+	struct th1520_mbox_priv *priv = to_th1520_mbox_priv(chan->mbox);
+	struct th1520_mbox_con_priv *cp = chan->con_priv;
+	int mask_bit;
+
+	free_irq(priv->irq, chan);
+
+	/* clear the chan mask */
+	mask_bit = th1520_mbox_chan_id_to_mapbit(cp);
+	th1520_mbox_rmw(priv, TH_1520_MBOX_MASK, 0, BIT(mask_bit));
+}
+
+static const struct mbox_chan_ops th1520_mbox_ops = {
+	.send_data = th1520_mbox_send_data,
+	.startup = th1520_mbox_startup,
+	.shutdown = th1520_mbox_shutdown,
+};
+
+static int th1520_mbox_init_generic(struct th1520_mbox_priv *priv)
+{
+#ifdef CONFIG_PM_SLEEP
+	priv->ctx = devm_kzalloc(priv->dev, sizeof(*priv->ctx), GFP_KERNEL);
+	if (!priv->ctx)
+		return -ENOMEM;
+#endif
+	/* Set default configuration */
+	th1520_mbox_write(priv, 0xff, TH_1520_MBOX_CLR);
+	th1520_mbox_write(priv, 0x0, TH_1520_MBOX_MASK);
+	return 0;
+}
+
+static struct mbox_chan *th1520_mbox_xlate(struct mbox_controller *mbox,
+					   const struct of_phandle_args *sp)
+{
+	u32 chan;
+
+	if (sp->args_count != 1) {
+		dev_err(mbox->dev, "Invalid argument count %d\n",
+			sp->args_count);
+		return ERR_PTR(-EINVAL);
+	}
+
+	chan = sp->args[0]; /* comm remote channel */
+
+	if (chan >= mbox->num_chans) {
+		dev_err(mbox->dev, "Not supported channel number: %d\n", chan);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (chan == TH_1520_MBOX_ICU_KERNEL_CPU0) {
+		dev_err(mbox->dev, "Cannot communicate with yourself\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	return &mbox->chans[chan];
+}
+
+static void __iomem *th1520_map_mmio(struct platform_device *pdev,
+				     char *res_name, size_t offset)
+{
+	void __iomem *mapped;
+	struct resource *res;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, res_name);
+
+	if (!res) {
+		dev_err(&pdev->dev, "Failed to get resource: %s\n", res_name);
+		return ERR_PTR(-EINVAL);
+	}
+
+	mapped = devm_ioremap(&pdev->dev, res->start + offset,
+			      resource_size(res) - offset);
+	if (IS_ERR(mapped))
+		dev_err(&pdev->dev, "Failed to map resource: %s\n", res_name);
+
+	return mapped;
+}
+
+static void th1520_disable_clk(void *data)
+{
+	struct th1520_mbox_priv *priv = data;
+
+	clk_bulk_disable_unprepare(ARRAY_SIZE(priv->clocks), priv->clocks);
+}
+
+static int th1520_mbox_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct th1520_mbox_priv *priv;
+	unsigned int remote_idx = 0;
+	unsigned int i;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->dev = dev;
+
+	priv->clocks[0].id = "clk-local";
+	priv->clocks[1].id = "clk-remote-icu0";
+	priv->clocks[2].id = "clk-remote-icu1";
+	priv->clocks[3].id = "clk-remote-icu2";
+
+	ret = devm_clk_bulk_get(dev, ARRAY_SIZE(priv->clocks),
+				priv->clocks);
+	if (ret) {
+		dev_err(dev, "Failed to get clocks\n");
+		return ret;
+	}
+
+	ret = clk_bulk_prepare_enable(ARRAY_SIZE(priv->clocks), priv->clocks);
+	if (ret) {
+		dev_err(dev, "Failed to enable clocks\n");
+		return ret;
+	}
+
+	ret = devm_add_action_or_reset(dev, th1520_disable_clk, priv);
+	if (ret) {
+		clk_bulk_disable_unprepare(ARRAY_SIZE(priv->clocks), priv->clocks);
+		return ret;
+	}
+
+	/*
+	 * The address mappings in the device tree align precisely with those
+	 * outlined in the manual. However, register offsets within these
+	 * mapped regions are irregular, particularly for remote-icu0.
+	 * Consequently, th1520_map_mmio() requires an additional parameter to
+	 * handle this quirk.
+	 */
+	priv->local_icu[TH_1520_MBOX_ICU_KERNEL_CPU0] =
+		th1520_map_mmio(pdev, "local", 0x0);
+	if (IS_ERR(priv->local_icu[TH_1520_MBOX_ICU_KERNEL_CPU0]))
+		return PTR_ERR(priv->local_icu[TH_1520_MBOX_ICU_KERNEL_CPU0]);
+
+	priv->remote_icu[0] = th1520_map_mmio(pdev, "remote-icu0", 0x4000);
+	if (IS_ERR(priv->remote_icu[0]))
+		return PTR_ERR(priv->remote_icu[0]);
+
+	priv->remote_icu[1] = th1520_map_mmio(pdev, "remote-icu1", 0x0);
+	if (IS_ERR(priv->remote_icu[1]))
+		return PTR_ERR(priv->remote_icu[1]);
+
+	priv->remote_icu[2] = th1520_map_mmio(pdev, "remote-icu2", 0x0);
+	if (IS_ERR(priv->remote_icu[2]))
+		return PTR_ERR(priv->remote_icu[2]);
+
+	priv->local_icu[TH_1520_MBOX_ICU_CPU1] =
+		priv->local_icu[TH_1520_MBOX_ICU_KERNEL_CPU0] +
+		TH_1520_MBOX_CHAN_RES_SIZE;
+	priv->local_icu[TH_1520_MBOX_ICU_CPU2] =
+		priv->local_icu[TH_1520_MBOX_ICU_CPU1] +
+		TH_1520_MBOX_CHAN_RES_SIZE;
+	priv->local_icu[TH_1520_MBOX_ICU_CPU3] =
+		priv->local_icu[TH_1520_MBOX_ICU_CPU2] +
+		TH_1520_MBOX_CHAN_RES_SIZE;
+
+	priv->cur_cpu_ch_base = priv->local_icu[TH_1520_MBOX_ICU_KERNEL_CPU0];
+
+	priv->irq = platform_get_irq(pdev, 0);
+	if (priv->irq < 0)
+		return priv->irq;
+
+	/* init the chans */
+	for (i = 0; i < TH_1520_MBOX_CHANS; i++) {
+		struct th1520_mbox_con_priv *cp = &priv->con_priv[i];
+
+		cp->idx = i;
+		cp->chan = &priv->mbox_chans[i];
+		priv->mbox_chans[i].con_priv = cp;
+		snprintf(cp->irq_desc, sizeof(cp->irq_desc),
+			 "th1520_mbox_chan[%i]", cp->idx);
+
+		cp->comm_local_base = priv->local_icu[i];
+		if (i != TH_1520_MBOX_ICU_KERNEL_CPU0) {
+			cp->comm_remote_base = priv->remote_icu[remote_idx];
+			remote_idx++;
+		}
+	}
+
+	spin_lock_init(&priv->mbox_lock);
+
+	priv->mbox.dev = dev;
+	priv->mbox.ops = &th1520_mbox_ops;
+	priv->mbox.chans = priv->mbox_chans;
+	priv->mbox.num_chans = TH_1520_MBOX_CHANS;
+	priv->mbox.of_xlate = th1520_mbox_xlate;
+	priv->mbox.txdone_irq = true;
+
+	platform_set_drvdata(pdev, priv);
+
+	ret = th1520_mbox_init_generic(priv);
+	if (ret) {
+		dev_err(dev, "Failed to init mailbox context\n");
+		return ret;
+	}
+
+	return devm_mbox_controller_register(dev, &priv->mbox);
+}
+
+static const struct of_device_id th1520_mbox_dt_ids[] = {
+	{ .compatible = "thead,th1520-mbox" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, th1520_mbox_dt_ids);
+
+#ifdef CONFIG_PM_SLEEP
+static int __maybe_unused th1520_mbox_suspend_noirq(struct device *dev)
+{
+	struct th1520_mbox_priv *priv = dev_get_drvdata(dev);
+	struct th1520_mbox_context *ctx = priv->ctx;
+	u32 i;
+	/*
+	 * ONLY interrupt mask bit should be stored and restores.
+	 * INFO data all assumed to be lost.
+	 */
+	for (i = 0; i < TH_1520_MBOX_CHANS; i++) {
+		ctx->intr_mask[i] =
+			ioread32(priv->local_icu[i] + TH_1520_MBOX_MASK);
+	}
+	return 0;
+}
+
+static int __maybe_unused th1520_mbox_resume_noirq(struct device *dev)
+{
+	struct th1520_mbox_priv *priv = dev_get_drvdata(dev);
+	struct th1520_mbox_context *ctx = priv->ctx;
+	u32 i;
+
+	for (i = 0; i < TH_1520_MBOX_CHANS; i++) {
+		iowrite32(ctx->intr_mask[i],
+			  priv->local_icu[i] + TH_1520_MBOX_MASK);
+	}
+
+	return 0;
+}
+#endif
+
+static int  __maybe_unused th1520_mbox_runtime_suspend(struct device *dev)
+{
+	struct th1520_mbox_priv *priv = dev_get_drvdata(dev);
+
+	clk_bulk_disable_unprepare(ARRAY_SIZE(priv->clocks), priv->clocks);
+
+	return 0;
+}
+
+static int __maybe_unused th1520_mbox_runtime_resume(struct device *dev)
+{
+	struct th1520_mbox_priv *priv = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_bulk_prepare_enable(ARRAY_SIZE(priv->clocks), priv->clocks);
+	if (ret)
+		dev_err(dev, "Failed to enable clocks in runtime resume\n");
+
+	return ret;
+}
+
+static const struct dev_pm_ops th1520_mbox_pm_ops = {
+#ifdef CONFIG_PM_SLEEP
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(th1520_mbox_suspend_noirq,
+				      th1520_mbox_resume_noirq)
+#endif
+	SET_RUNTIME_PM_OPS(th1520_mbox_runtime_suspend,
+			   th1520_mbox_runtime_resume, NULL)
+};
+
+static struct platform_driver th1520_mbox_driver = {
+	.probe		= th1520_mbox_probe,
+	.driver = {
+		.name	= "th1520-mbox",
+		.of_match_table = th1520_mbox_dt_ids,
+		.pm = &th1520_mbox_pm_ops,
+	},
+};
+module_platform_driver(th1520_mbox_driver);
+
+MODULE_DESCRIPTION("Thead TH-1520 mailbox IPC driver");
+MODULE_LICENSE("GPL");

From b2cf36e4a2ac7a7a35e0e7025a6897e4e4fcf4f3 Mon Sep 17 00:00:00 2001
From: Michal Wilczynski <m.wilczynski@samsung.com>
Date: Mon, 4 Nov 2024 11:07:33 +0100
Subject: [PATCH 1372/1530] dt-bindings: mailbox: Add thead,th1520-mailbox
 bindings

Add bindings for the mailbox controller. This work is based on the vendor
kernel. [1]

Link: https://github.com/revyos/thead-kernel.git [1]

Signed-off-by: Michal Wilczynski <m.wilczynski@samsung.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 .../bindings/mailbox/thead,th1520-mbox.yaml   | 89 +++++++++++++++++++
 MAINTAINERS                                   |  1 +
 2 files changed, 90 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/mailbox/thead,th1520-mbox.yaml

diff --git a/Documentation/devicetree/bindings/mailbox/thead,th1520-mbox.yaml b/Documentation/devicetree/bindings/mailbox/thead,th1520-mbox.yaml
new file mode 100644
index 0000000000000..0971fb97896ef
--- /dev/null
+++ b/Documentation/devicetree/bindings/mailbox/thead,th1520-mbox.yaml
@@ -0,0 +1,89 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/mailbox/thead,th1520-mbox.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: T-head TH1520 Mailbox Controller
+
+description:
+  The T-head mailbox controller enables communication and coordination between
+  cores within the SoC by passing messages (e.g., data, status, and control)
+  through mailbox channels. It also allows one core to signal another processor
+  using interrupts via the Interrupt Controller Unit (ICU).
+
+maintainers:
+  - Michal Wilczynski <m.wilczynski@samsung.com>
+
+properties:
+  compatible:
+    const: thead,th1520-mbox
+
+  clocks:
+    items:
+      - description: Clock for the local mailbox
+      - description: Clock for remote ICU 0
+      - description: Clock for remote ICU 1
+      - description: Clock for remote ICU 2
+
+  clock-names:
+    items:
+      - const: clk-local
+      - const: clk-remote-icu0
+      - const: clk-remote-icu1
+      - const: clk-remote-icu2
+
+  reg:
+    items:
+      - description: Mailbox local base address
+      - description: Remote ICU 0 base address
+      - description: Remote ICU 1 base address
+      - description: Remote ICU 2 base address
+
+  reg-names:
+    items:
+      - const: local
+      - const: remote-icu0
+      - const: remote-icu1
+      - const: remote-icu2
+
+  interrupts:
+    maxItems: 1
+
+  '#mbox-cells':
+    const: 1
+    description:
+      The one and only cell describes destination CPU ID.
+
+required:
+  - compatible
+  - clocks
+  - clock-names
+  - reg
+  - reg-names
+  - interrupts
+  - '#mbox-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/thead,th1520-clk-ap.h>
+    soc {
+      #address-cells = <2>;
+      #size-cells = <2>;
+      mailbox@ffffc38000 {
+        compatible = "thead,th1520-mbox";
+        reg = <0xff 0xffc38000 0x0 0x4000>,
+              <0xff 0xffc44000 0x0 0x1000>,
+              <0xff 0xffc4c000 0x0 0x1000>,
+              <0xff 0xffc54000 0x0 0x1000>;
+        reg-names = "local", "remote-icu0", "remote-icu1", "remote-icu2";
+        clocks = <&clk CLK_MBOX0>, <&clk CLK_MBOX1>, <&clk CLK_MBOX2>,
+                 <&clk CLK_MBOX3>;
+        clock-names = "clk-local", "clk-remote-icu0", "clk-remote-icu1",
+                      "clk-remote-icu2";
+        interrupts = <28>;
+        #mbox-cells = <1>;
+      };
+    };
diff --git a/MAINTAINERS b/MAINTAINERS
index 0dfac18899230..5a406a4ab9cf5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19869,6 +19869,7 @@ L:	linux-riscv@lists.infradead.org
 S:	Maintained
 T:	git https://github.com/pdp7/linux.git
 F:	Documentation/devicetree/bindings/clock/thead,th1520-clk-ap.yaml
+F:	Documentation/devicetree/bindings/mailbox/thead,th1520-mbox.yaml
 F:	arch/riscv/boot/dts/thead/
 F:	drivers/clk/thead/clk-th1520-ap.c
 F:	drivers/mailbox/mailbox-th1520.c

From 98fc87fe2937db5a4948c553f69b5a3cc94c230a Mon Sep 17 00:00:00 2001
From: Tanmay Shah <tanmay.shah@amd.com>
Date: Tue, 12 Nov 2024 09:06:12 -0800
Subject: [PATCH 1373/1530] mailbox: zynqmp: setup IPI for each valid child
 node

As per zynqmp-ipi bindings, zynqmp IPI node can have multiple child nodes.
Current IPI setup function is set only for first child node. If IPI node
has multiple child nodes in the device-tree, then IPI setup fails for
child nodes other than first child node. In such case kernel will crash.
Fix this crash by registering IPI setup function for each available child
node.

Signed-off-by: Tanmay Shah <tanmay.shah@amd.com>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 drivers/mailbox/zynqmp-ipi-mailbox.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mailbox/zynqmp-ipi-mailbox.c b/drivers/mailbox/zynqmp-ipi-mailbox.c
index 521d08b9ab47e..815e0492f0296 100644
--- a/drivers/mailbox/zynqmp-ipi-mailbox.c
+++ b/drivers/mailbox/zynqmp-ipi-mailbox.c
@@ -940,10 +940,10 @@ static int zynqmp_ipi_probe(struct platform_device *pdev)
 	pdata->num_mboxes = num_mboxes;
 
 	mbox = pdata->ipi_mboxes;
-	mbox->setup_ipi_fn = ipi_fn;
-
 	for_each_available_child_of_node(np, nc) {
 		mbox->pdata = pdata;
+		mbox->setup_ipi_fn = ipi_fn;
+
 		ret = zynqmp_ipi_mbox_probe(mbox, nc);
 		if (ret) {
 			of_node_put(nc);

From 192a16a3430ca459c4e986f3d10758c4d6b1aa29 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Thu, 14 Nov 2024 12:00:12 +0300
Subject: [PATCH 1374/1530] mailbox: arm_mhuv2: clean up loop in
 get_irq_chan_comb()

Both the inner and outer loops in this code use the "i" iterator.
The inner loop should really use a different iterator.

It doesn't affect things in practice because the data comes from the
device tree.  The "protocol" and "windows" variables are going to be
zero.  That means we're always going to hit the "return &chans[channel];"
statement and we're not going to want to iterate through the outer
loop again.

Still it's worth fixing this for future use cases.

Fixes: 5a6338cce9f4 ("mailbox: arm_mhuv2: Add driver")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 drivers/mailbox/arm_mhuv2.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/mailbox/arm_mhuv2.c b/drivers/mailbox/arm_mhuv2.c
index 0ec21dcdbde72..cff7c343ee082 100644
--- a/drivers/mailbox/arm_mhuv2.c
+++ b/drivers/mailbox/arm_mhuv2.c
@@ -500,7 +500,7 @@ static const struct mhuv2_protocol_ops mhuv2_data_transfer_ops = {
 static struct mbox_chan *get_irq_chan_comb(struct mhuv2 *mhu, u32 __iomem *reg)
 {
 	struct mbox_chan *chans = mhu->mbox.chans;
-	int channel = 0, i, offset = 0, windows, protocol, ch_wn;
+	int channel = 0, i, j, offset = 0, windows, protocol, ch_wn;
 	u32 stat;
 
 	for (i = 0; i < MHUV2_CMB_INT_ST_REG_CNT; i++) {
@@ -510,9 +510,9 @@ static struct mbox_chan *get_irq_chan_comb(struct mhuv2 *mhu, u32 __iomem *reg)
 
 		ch_wn = i * MHUV2_STAT_BITS + __builtin_ctz(stat);
 
-		for (i = 0; i < mhu->length; i += 2) {
-			protocol = mhu->protocols[i];
-			windows = mhu->protocols[i + 1];
+		for (j = 0; j < mhu->length; j += 2) {
+			protocol = mhu->protocols[j];
+			windows = mhu->protocols[j + 1];
 
 			if (ch_wn >= offset + windows) {
 				if (protocol == DOORBELL)

From e52673554cf2cd94472be0b3cade4d0eb771dfb1 Mon Sep 17 00:00:00 2001
From: zhang jiao <zhangjiao2@cmss.chinamobile.com>
Date: Fri, 15 Nov 2024 09:18:46 +0800
Subject: [PATCH 1375/1530] mailbox: imx: Modify the incorrect format specifier

Replace %i with %u in snprintf() because it is "unsigned int".

Signed-off-by: zhang jiao <zhangjiao2@cmss.chinamobile.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 drivers/mailbox/imx-mailbox.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c
index f815dab3be50c..3fe51b2de89ef 100644
--- a/drivers/mailbox/imx-mailbox.c
+++ b/drivers/mailbox/imx-mailbox.c
@@ -782,7 +782,7 @@ static int imx_mu_init_generic(struct imx_mu_priv *priv)
 		cp->chan = &priv->mbox_chans[i];
 		priv->mbox_chans[i].con_priv = cp;
 		snprintf(cp->irq_desc, sizeof(cp->irq_desc),
-			 "%s[%i-%i]", dev_name(priv->dev), cp->type, cp->idx);
+			 "%s[%i-%u]", dev_name(priv->dev), cp->type, cp->idx);
 	}
 
 	priv->mbox.num_chans = IMX_MU_CHANS;
@@ -819,7 +819,7 @@ static int imx_mu_init_specific(struct imx_mu_priv *priv)
 		cp->chan = &priv->mbox_chans[i];
 		priv->mbox_chans[i].con_priv = cp;
 		snprintf(cp->irq_desc, sizeof(cp->irq_desc),
-			 "%s[%i-%i]", dev_name(priv->dev), cp->type, cp->idx);
+			 "%s[%i-%u]", dev_name(priv->dev), cp->type, cp->idx);
 	}
 
 	priv->mbox.num_chans = num_chans;

From 81f939db2a44d82d3709faa45cab727c8cf7fc27 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@baylibre.com>
Date: Tue, 19 Nov 2024 09:16:51 +0100
Subject: [PATCH 1376/1530] mailbox: Switch back to struct
 platform_driver::remove()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 0edb555a65d1 ("platform: Make platform_driver::remove()
return void") .remove() is (again) the right callback to implement for
platform drivers.

Convert all platform drivers below drivers/mailbox to use .remove(),
with the eventual goal to drop struct platform_driver::remove_new(). As
.remove() and .remove_new() have the same prototypes, conversion is done
by just changing the structure member name in the driver initializer.

Make a few indentions consistent while touching these struct
initializers.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Acked-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 drivers/mailbox/bcm-flexrm-mailbox.c    | 2 +-
 drivers/mailbox/bcm-pdc-mailbox.c       | 2 +-
 drivers/mailbox/imx-mailbox.c           | 2 +-
 drivers/mailbox/mailbox-test.c          | 4 ++--
 drivers/mailbox/mtk-cmdq-mailbox.c      | 2 +-
 drivers/mailbox/qcom-apcs-ipc-mailbox.c | 2 +-
 drivers/mailbox/qcom-ipcc.c             | 2 +-
 drivers/mailbox/stm32-ipcc.c            | 2 +-
 drivers/mailbox/sun6i-msgbox.c          | 4 ++--
 drivers/mailbox/tegra-hsp.c             | 2 +-
 drivers/mailbox/zynqmp-ipi-mailbox.c    | 2 +-
 11 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/mailbox/bcm-flexrm-mailbox.c b/drivers/mailbox/bcm-flexrm-mailbox.c
index b1abc2a0c971a..41f79e51d9e5a 100644
--- a/drivers/mailbox/bcm-flexrm-mailbox.c
+++ b/drivers/mailbox/bcm-flexrm-mailbox.c
@@ -1675,7 +1675,7 @@ static struct platform_driver flexrm_mbox_driver = {
 		.of_match_table = flexrm_mbox_of_match,
 	},
 	.probe		= flexrm_mbox_probe,
-	.remove_new	= flexrm_mbox_remove,
+	.remove		= flexrm_mbox_remove,
 };
 module_platform_driver(flexrm_mbox_driver);
 
diff --git a/drivers/mailbox/bcm-pdc-mailbox.c b/drivers/mailbox/bcm-pdc-mailbox.c
index a873672a9082d..406bc41cba604 100644
--- a/drivers/mailbox/bcm-pdc-mailbox.c
+++ b/drivers/mailbox/bcm-pdc-mailbox.c
@@ -1618,7 +1618,7 @@ static void pdc_remove(struct platform_device *pdev)
 
 static struct platform_driver pdc_mbox_driver = {
 	.probe = pdc_probe,
-	.remove_new = pdc_remove,
+	.remove = pdc_remove,
 	.driver = {
 		   .name = "brcm-iproc-pdc-mbox",
 		   .of_match_table = pdc_mbox_of_match,
diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c
index 3fe51b2de89ef..6ef8338add0d6 100644
--- a/drivers/mailbox/imx-mailbox.c
+++ b/drivers/mailbox/imx-mailbox.c
@@ -1120,7 +1120,7 @@ static const struct dev_pm_ops imx_mu_pm_ops = {
 
 static struct platform_driver imx_mu_driver = {
 	.probe		= imx_mu_probe,
-	.remove_new	= imx_mu_remove,
+	.remove		= imx_mu_remove,
 	.driver = {
 		.name	= "imx_mu",
 		.of_match_table = imx_mu_dt_ids,
diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c
index 3386b4e72551c..c9dd8c42c0cdf 100644
--- a/drivers/mailbox/mailbox-test.c
+++ b/drivers/mailbox/mailbox-test.c
@@ -441,8 +441,8 @@ static struct platform_driver mbox_test_driver = {
 		.name = "mailbox_test",
 		.of_match_table = mbox_test_match,
 	},
-	.probe  = mbox_test_probe,
-	.remove_new = mbox_test_remove,
+	.probe = mbox_test_probe,
+	.remove = mbox_test_remove,
 };
 module_platform_driver(mbox_test_driver);
 
diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index 4324c53e372df..d186865b8dce6 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -796,7 +796,7 @@ MODULE_DEVICE_TABLE(of, cmdq_of_ids);
 
 static struct platform_driver cmdq_drv = {
 	.probe = cmdq_probe,
-	.remove_new = cmdq_remove,
+	.remove = cmdq_remove,
 	.driver = {
 		.name = "mtk_cmdq",
 		.pm = &cmdq_pm_ops,
diff --git a/drivers/mailbox/qcom-apcs-ipc-mailbox.c b/drivers/mailbox/qcom-apcs-ipc-mailbox.c
index 7d91e7c016ba7..f0d1fc0fb9ffc 100644
--- a/drivers/mailbox/qcom-apcs-ipc-mailbox.c
+++ b/drivers/mailbox/qcom-apcs-ipc-mailbox.c
@@ -167,7 +167,7 @@ MODULE_DEVICE_TABLE(of, qcom_apcs_ipc_of_match);
 
 static struct platform_driver qcom_apcs_ipc_driver = {
 	.probe = qcom_apcs_ipc_probe,
-	.remove_new = qcom_apcs_ipc_remove,
+	.remove = qcom_apcs_ipc_remove,
 	.driver = {
 		.name = "qcom_apcs_ipc",
 		.of_match_table = qcom_apcs_ipc_of_match,
diff --git a/drivers/mailbox/qcom-ipcc.c b/drivers/mailbox/qcom-ipcc.c
index d537cc9c4d4be..14c7907c66326 100644
--- a/drivers/mailbox/qcom-ipcc.c
+++ b/drivers/mailbox/qcom-ipcc.c
@@ -346,7 +346,7 @@ static const struct dev_pm_ops qcom_ipcc_dev_pm_ops = {
 
 static struct platform_driver qcom_ipcc_driver = {
 	.probe = qcom_ipcc_probe,
-	.remove_new = qcom_ipcc_remove,
+	.remove = qcom_ipcc_remove,
 	.driver = {
 		.name = "qcom-ipcc",
 		.of_match_table = qcom_ipcc_of_match,
diff --git a/drivers/mailbox/stm32-ipcc.c b/drivers/mailbox/stm32-ipcc.c
index 1442f275782bd..4f63f1a14ca65 100644
--- a/drivers/mailbox/stm32-ipcc.c
+++ b/drivers/mailbox/stm32-ipcc.c
@@ -379,7 +379,7 @@ static struct platform_driver stm32_ipcc_driver = {
 		.of_match_table = stm32_ipcc_of_match,
 	},
 	.probe		= stm32_ipcc_probe,
-	.remove_new	= stm32_ipcc_remove,
+	.remove		= stm32_ipcc_remove,
 };
 
 module_platform_driver(stm32_ipcc_driver);
diff --git a/drivers/mailbox/sun6i-msgbox.c b/drivers/mailbox/sun6i-msgbox.c
index 3dcc54dc83b2d..6ba6920f4645e 100644
--- a/drivers/mailbox/sun6i-msgbox.c
+++ b/drivers/mailbox/sun6i-msgbox.c
@@ -307,8 +307,8 @@ static struct platform_driver sun6i_msgbox_driver = {
 		.name = "sun6i-msgbox",
 		.of_match_table = sun6i_msgbox_of_match,
 	},
-	.probe  = sun6i_msgbox_probe,
-	.remove_new = sun6i_msgbox_remove,
+	.probe = sun6i_msgbox_probe,
+	.remove = sun6i_msgbox_remove,
 };
 module_platform_driver(sun6i_msgbox_driver);
 
diff --git a/drivers/mailbox/tegra-hsp.c b/drivers/mailbox/tegra-hsp.c
index 19ef56cbcfd39..8d5e2d7dc03b2 100644
--- a/drivers/mailbox/tegra-hsp.c
+++ b/drivers/mailbox/tegra-hsp.c
@@ -951,7 +951,7 @@ static struct platform_driver tegra_hsp_driver = {
 		.pm = &tegra_hsp_pm_ops,
 	},
 	.probe = tegra_hsp_probe,
-	.remove_new = tegra_hsp_remove,
+	.remove = tegra_hsp_remove,
 };
 
 static int __init tegra_hsp_init(void)
diff --git a/drivers/mailbox/zynqmp-ipi-mailbox.c b/drivers/mailbox/zynqmp-ipi-mailbox.c
index 815e0492f0296..aa5249da59b2f 100644
--- a/drivers/mailbox/zynqmp-ipi-mailbox.c
+++ b/drivers/mailbox/zynqmp-ipi-mailbox.c
@@ -1015,7 +1015,7 @@ MODULE_DEVICE_TABLE(of, zynqmp_ipi_of_match);
 
 static struct platform_driver zynqmp_ipi_driver = {
 	.probe = zynqmp_ipi_probe,
-	.remove_new = zynqmp_ipi_remove,
+	.remove = zynqmp_ipi_remove,
 	.driver = {
 		   .name = "zynqmp-ipi",
 		   .of_match_table = of_match_ptr(zynqmp_ipi_of_match),

From 7f9e19f207be0c534d517d65e01417ba968cdd34 Mon Sep 17 00:00:00 2001
From: Adam Young <admiyo@os.amperecomputing.com>
Date: Wed, 20 Nov 2024 14:02:14 -0500
Subject: [PATCH 1377/1530] mailbox: pcc: Check before sending MCTP PCC
 response ACK

Type 4 PCC channels have an option to send back a response
to the platform when they are done processing the request.
The flag to indicate whether or not to respond is inside
the message body, and thus is not available to the pcc
mailbox.

If the flag is not set, still set command completion
bit after processing message.

In order to read the flag, this patch maps the shared
buffer to virtual memory. To avoid duplication of mapping
the shared buffer is then made available to be used by
the driver that uses the mailbox.

Signed-off-by: Adam Young <admiyo@os.amperecomputing.com>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 drivers/mailbox/pcc.c | 61 +++++++++++++++++++++++++++++++++++++------
 include/acpi/pcc.h    |  7 +++++
 2 files changed, 60 insertions(+), 8 deletions(-)

diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c
index 94885e411085a..82102a4c5d688 100644
--- a/drivers/mailbox/pcc.c
+++ b/drivers/mailbox/pcc.c
@@ -269,6 +269,35 @@ static bool pcc_mbox_cmd_complete_check(struct pcc_chan_info *pchan)
 	return !!val;
 }
 
+static void check_and_ack(struct pcc_chan_info *pchan, struct mbox_chan *chan)
+{
+	struct acpi_pcct_ext_pcc_shared_memory pcc_hdr;
+
+	if (pchan->type != ACPI_PCCT_TYPE_EXT_PCC_SLAVE_SUBSPACE)
+		return;
+	/* If the memory region has not been mapped, we cannot
+	 * determine if we need to send the message, but we still
+	 * need to set the cmd_update flag before returning.
+	 */
+	if (pchan->chan.shmem == NULL) {
+		pcc_chan_reg_read_modify_write(&pchan->cmd_update);
+		return;
+	}
+	memcpy_fromio(&pcc_hdr, pchan->chan.shmem,
+		      sizeof(struct acpi_pcct_ext_pcc_shared_memory));
+	/*
+	 * The PCC slave subspace channel needs to set the command complete bit
+	 * after processing message. If the PCC_ACK_FLAG is set, it should also
+	 * ring the doorbell.
+	 *
+	 * The PCC master subspace channel clears chan_in_use to free channel.
+	 */
+	if (le32_to_cpup(&pcc_hdr.flags) & PCC_ACK_FLAG_MASK)
+		pcc_send_data(chan, NULL);
+	else
+		pcc_chan_reg_read_modify_write(&pchan->cmd_update);
+}
+
 /**
  * pcc_mbox_irq - PCC mailbox interrupt handler
  * @irq:	interrupt number
@@ -306,14 +335,7 @@ static irqreturn_t pcc_mbox_irq(int irq, void *p)
 
 	mbox_chan_received_data(chan, NULL);
 
-	/*
-	 * The PCC slave subspace channel needs to set the command complete bit
-	 * and ring doorbell after processing message.
-	 *
-	 * The PCC master subspace channel clears chan_in_use to free channel.
-	 */
-	if (pchan->type == ACPI_PCCT_TYPE_EXT_PCC_SLAVE_SUBSPACE)
-		pcc_send_data(chan, NULL);
+	check_and_ack(pchan, chan);
 	pchan->chan_in_use = false;
 
 	return IRQ_HANDLED;
@@ -365,14 +387,37 @@ EXPORT_SYMBOL_GPL(pcc_mbox_request_channel);
 void pcc_mbox_free_channel(struct pcc_mbox_chan *pchan)
 {
 	struct mbox_chan *chan = pchan->mchan;
+	struct pcc_chan_info *pchan_info;
+	struct pcc_mbox_chan *pcc_mbox_chan;
 
 	if (!chan || !chan->cl)
 		return;
+	pchan_info = chan->con_priv;
+	pcc_mbox_chan = &pchan_info->chan;
+	if (pcc_mbox_chan->shmem) {
+		iounmap(pcc_mbox_chan->shmem);
+		pcc_mbox_chan->shmem = NULL;
+	}
 
 	mbox_free_channel(chan);
 }
 EXPORT_SYMBOL_GPL(pcc_mbox_free_channel);
 
+int pcc_mbox_ioremap(struct mbox_chan *chan)
+{
+	struct pcc_chan_info *pchan_info;
+	struct pcc_mbox_chan *pcc_mbox_chan;
+
+	if (!chan || !chan->cl)
+		return -1;
+	pchan_info = chan->con_priv;
+	pcc_mbox_chan = &pchan_info->chan;
+	pcc_mbox_chan->shmem = ioremap(pcc_mbox_chan->shmem_base_addr,
+				       pcc_mbox_chan->shmem_size);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pcc_mbox_ioremap);
+
 /**
  * pcc_send_data - Called from Mailbox Controller code. Used
  *		here only to ring the channel doorbell. The PCC client
diff --git a/include/acpi/pcc.h b/include/acpi/pcc.h
index 9b373d172a776..699c1a37b8e78 100644
--- a/include/acpi/pcc.h
+++ b/include/acpi/pcc.h
@@ -12,6 +12,7 @@
 struct pcc_mbox_chan {
 	struct mbox_chan *mchan;
 	u64 shmem_base_addr;
+	void __iomem *shmem;
 	u64 shmem_size;
 	u32 latency;
 	u32 max_access_rate;
@@ -31,11 +32,13 @@ struct pcc_mbox_chan {
 #define PCC_CMD_COMPLETION_NOTIFY	BIT(0)
 
 #define MAX_PCC_SUBSPACES	256
+#define PCC_ACK_FLAG_MASK	0x1
 
 #ifdef CONFIG_PCC
 extern struct pcc_mbox_chan *
 pcc_mbox_request_channel(struct mbox_client *cl, int subspace_id);
 extern void pcc_mbox_free_channel(struct pcc_mbox_chan *chan);
+extern int pcc_mbox_ioremap(struct mbox_chan *chan);
 #else
 static inline struct pcc_mbox_chan *
 pcc_mbox_request_channel(struct mbox_client *cl, int subspace_id)
@@ -43,6 +46,10 @@ pcc_mbox_request_channel(struct mbox_client *cl, int subspace_id)
 	return ERR_PTR(-ENODEV);
 }
 static inline void pcc_mbox_free_channel(struct pcc_mbox_chan *chan) { }
+static inline int pcc_mbox_ioremap(struct mbox_chan *chan)
+{
+	return 0;
+};
 #endif
 
 #endif /* _PCC_H */

From 60fc1e6750133620e404d40b93df5afe32e3e6c6 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Sat, 16 Nov 2024 19:15:37 +0100
Subject: [PATCH 1378/1530] rust: allow `clippy::needless_lifetimes`

In beta Clippy (i.e. Rust 1.83.0), the `needless_lifetimes` lint has
been extended [1] to suggest eliding `impl` lifetimes, e.g.

    error: the following explicit lifetimes could be elided: 'a
    --> rust/kernel/list.rs:647:6
        |
    647 | impl<'a, T: ?Sized + ListItem<ID>, const ID: u64> FusedIterator for Iter<'a, T, ID> {}
        |      ^^                                                                  ^^
        |
        = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#needless_lifetimes
        = note: `-D clippy::needless-lifetimes` implied by `-D warnings`
        = help: to override `-D warnings` add `#[allow(clippy::needless_lifetimes)]`
    help: elide the lifetimes
        |
    647 - impl<'a, T: ?Sized + ListItem<ID>, const ID: u64> FusedIterator for Iter<'a, T, ID> {}
    647 + impl<T: ?Sized + ListItem<ID>, const ID: u64> FusedIterator for Iter<'_, T, ID> {}

A possibility would have been to clean them -- the RFC patch [2] did
this, while asking if we wanted these cleanups. There is an open issue
[3] in Clippy about being able to differentiate some of the new cases,
e.g. those that do not involve introducing `'_`. Thus it seems others
feel similarly.

Thus, for the time being, we decided to `allow` the lint.

Link: https://github.com/rust-lang/rust-clippy/pull/13286 [1]
Link: https://lore.kernel.org/rust-for-linux/20241012231300.397010-1-ojeda@kernel.org/ [2]
Link: https://github.com/rust-lang/rust-clippy/issues/13514 [3]
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Link: https://lore.kernel.org/r/20241116181538.369355-1-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Makefile b/Makefile
index a9e723cb05961..00a444603fb14 100644
--- a/Makefile
+++ b/Makefile
@@ -456,6 +456,7 @@ export rust_common_flags := --edition=2021 \
 			    -Wclippy::mut_mut \
 			    -Wclippy::needless_bitwise_bool \
 			    -Wclippy::needless_continue \
+			    -Aclippy::needless_lifetimes \
 			    -Wclippy::no_mangle_with_rust_abi \
 			    -Wclippy::undocumented_unsafe_blocks \
 			    -Wclippy::unnecessary_safety_comment \

From b160dc46dd9af4001c802cc9c7d68b6ba58d27c4 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Sun, 17 Nov 2024 14:31:27 +0100
Subject: [PATCH 1379/1530] docs: rust: remove spurious item in `expect` list

This list started as a "when to prefer `expect`" list, but at some point
during writing I changed it to a "prefer `expect` unless..." one. However,
the first bullet remained, which does not make sense anymore.

Thus remove it. In addition, fix nearby typo.

Fixes: 04866494e936 ("Documentation: rust: discuss `#[expect(...)]` in the guidelines")
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Link: https://lore.kernel.org/r/20241117133127.473937-1-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Documentation/rust/coding-guidelines.rst | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/Documentation/rust/coding-guidelines.rst b/Documentation/rust/coding-guidelines.rst
index f7194f7124b07..a2e326b42410f 100644
--- a/Documentation/rust/coding-guidelines.rst
+++ b/Documentation/rust/coding-guidelines.rst
@@ -296,9 +296,7 @@ may happen in several situations, e.g.:
 It also increases the visibility of the remaining ``allow``\ s and reduces the
 chance of misapplying one.
 
-Thus prefer ``except`` over ``allow`` unless:
-
-- The lint attribute is intended to be temporary, e.g. while developing.
+Thus prefer ``expect`` over ``allow`` unless:
 
 - Conditional compilation triggers the warning in some cases but not others.
 

From b7ed2b6f4e8d7f64649795e76ee9db67300de8eb Mon Sep 17 00:00:00 2001
From: Asahi Lina <lina@asahilina.net>
Date: Sat, 23 Nov 2024 19:29:38 +0900
Subject: [PATCH 1380/1530] rust: alloc: Fix `ArrayLayout` allocations

We were accidentally allocating a layout for the *square* of the object
size due to a variable shadowing mishap.

Fixes memory bloat and page allocation failures in drm/asahi.

Reported-by: Janne Grunau <j@jannau.net>
Fixes: 9e7bbfa18276 ("rust: alloc: introduce `ArrayLayout`")
Signed-off-by: Asahi Lina <lina@asahilina.net>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Reviewed-by: Neal Gompa <neal@gompa.dev>
Link: https://lore.kernel.org/r/20241123-rust-fix-arraylayout-v1-1-197e64c95bd4@asahilina.net
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc/layout.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/kernel/alloc/layout.rs b/rust/kernel/alloc/layout.rs
index 7e0c2f46157b7..4b3cd7fdc816c 100644
--- a/rust/kernel/alloc/layout.rs
+++ b/rust/kernel/alloc/layout.rs
@@ -45,7 +45,7 @@ impl<T> ArrayLayout<T> {
     /// When `len * size_of::<T>()` overflows or when `len * size_of::<T>() > isize::MAX`.
     pub const fn new(len: usize) -> Result<Self, LayoutError> {
         match len.checked_mul(core::mem::size_of::<T>()) {
-            Some(len) if len <= ISIZE_MAX => {
+            Some(size) if size <= ISIZE_MAX => {
                 // INVARIANT: We checked above that `len * size_of::<T>() <= isize::MAX`.
                 Ok(Self {
                     len,

From 03819abbeb11117dcbba40bfe322b88c0c88a6b6 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Sat, 16 Nov 2024 14:05:57 +0100
Subject: [PATCH 1381/1530] net: usb: lan78xx: Fix double free issue with
 interrupt buffer allocation

In lan78xx_probe(), the buffer `buf` was being freed twice: once
implicitly through `usb_free_urb(dev->urb_intr)` with the
`URB_FREE_BUFFER` flag and again explicitly by `kfree(buf)`. This caused
a double free issue.

To resolve this, reordered `kmalloc()` and `usb_alloc_urb()` calls to
simplify the initialization sequence and removed the redundant
`kfree(buf)`.  Now, `buf` is allocated after `usb_alloc_urb()`, ensuring
it is correctly managed by  `usb_fill_int_urb()` and freed by
`usb_free_urb()` as intended.

Fixes: a6df95cae40b ("lan78xx: Fix memory allocation bug")
Cc: John Efstathiades <john.efstathiades@pebblebay.com>
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20241116130558.1352230-1-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 29 ++++++++++++++---------------
 1 file changed, 14 insertions(+), 15 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 8adf77e3557e7..094a47b8b97eb 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -4414,29 +4414,30 @@ static int lan78xx_probe(struct usb_interface *intf,
 
 	period = ep_intr->desc.bInterval;
 	maxp = usb_maxpacket(dev->udev, dev->pipe_intr);
-	buf = kmalloc(maxp, GFP_KERNEL);
-	if (!buf) {
+
+	dev->urb_intr = usb_alloc_urb(0, GFP_KERNEL);
+	if (!dev->urb_intr) {
 		ret = -ENOMEM;
 		goto out5;
 	}
 
-	dev->urb_intr = usb_alloc_urb(0, GFP_KERNEL);
-	if (!dev->urb_intr) {
+	buf = kmalloc(maxp, GFP_KERNEL);
+	if (!buf) {
 		ret = -ENOMEM;
-		goto out6;
-	} else {
-		usb_fill_int_urb(dev->urb_intr, dev->udev,
-				 dev->pipe_intr, buf, maxp,
-				 intr_complete, dev, period);
-		dev->urb_intr->transfer_flags |= URB_FREE_BUFFER;
+		goto free_urbs;
 	}
 
+	usb_fill_int_urb(dev->urb_intr, dev->udev,
+			 dev->pipe_intr, buf, maxp,
+			 intr_complete, dev, period);
+	dev->urb_intr->transfer_flags |= URB_FREE_BUFFER;
+
 	dev->maxpacket = usb_maxpacket(dev->udev, dev->pipe_out);
 
 	/* Reject broken descriptors. */
 	if (dev->maxpacket == 0) {
 		ret = -ENODEV;
-		goto out6;
+		goto free_urbs;
 	}
 
 	/* driver requires remote-wakeup capability during autosuspend. */
@@ -4444,7 +4445,7 @@ static int lan78xx_probe(struct usb_interface *intf,
 
 	ret = lan78xx_phy_init(dev);
 	if (ret < 0)
-		goto out7;
+		goto free_urbs;
 
 	ret = register_netdev(netdev);
 	if (ret != 0) {
@@ -4466,10 +4467,8 @@ static int lan78xx_probe(struct usb_interface *intf,
 
 out8:
 	phy_disconnect(netdev->phydev);
-out7:
+free_urbs:
 	usb_free_urb(dev->urb_intr);
-out6:
-	kfree(buf);
 out5:
 	lan78xx_unbind(dev, intf);
 out4:

From ae7370e61c5d8f5bcefc2d4fca724bd4e9bbf789 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Sat, 16 Nov 2024 14:05:58 +0100
Subject: [PATCH 1382/1530] net: usb: lan78xx: Fix memory leak on device unplug
 by freeing PHY device

Add calls to `phy_device_free` after `fixed_phy_unregister` to fix a
memory leak that occurs when the device is unplugged. This ensures
proper cleanup of pseudo fixed-link PHYs.

Fixes: 89b36fb5e532 ("lan78xx: Lan7801 Support for Fixed PHY")
Cc: Raghuram Chary J <raghuramchary.jallipalli@microchip.com>
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20241116130558.1352230-2-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 094a47b8b97eb..9f191b6ce8215 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -2380,6 +2380,7 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 		if (dev->chipid == ID_REV_CHIP_ID_7801_) {
 			if (phy_is_pseudo_fixed_link(phydev)) {
 				fixed_phy_unregister(phydev);
+				phy_device_free(phydev);
 			} else {
 				phy_unregister_fixup_for_uid(PHY_KSZ9031RNX,
 							     0xfffffff0);
@@ -4246,8 +4247,10 @@ static void lan78xx_disconnect(struct usb_interface *intf)
 
 	phy_disconnect(net->phydev);
 
-	if (phy_is_pseudo_fixed_link(phydev))
+	if (phy_is_pseudo_fixed_link(phydev)) {
 		fixed_phy_unregister(phydev);
+		phy_device_free(phydev);
+	}
 
 	usb_scuttle_anchored_urbs(&dev->deferred);
 

From 078f644cb81b78afdfbc42b9cc2c11959f2ed65c Mon Sep 17 00:00:00 2001
From: David Wei <dw@davidwei.uk>
Date: Thu, 21 Nov 2024 22:48:21 -0800
Subject: [PATCH 1383/1530] selftests: fix nested double quotes in f-string

Replace nested double quotes in f-string with outer single quotes.

Fixes: 6116075e18f7 ("selftests: nic_link_layer: Add link layer selftest for NIC driver")
Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20241122064821.2821199-1-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py b/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py
index db84000fc75b1..79fde603cbbc2 100644
--- a/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py
+++ b/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py
@@ -218,5 +218,5 @@ def get_ethtool_field(self, field: str, remote: bool = False) -> Optional[str]:
         json_data = process[0]
         """Check if the field exist in the json data"""
         if field not in json_data:
-            raise KsftSkipEx(f"Field {field} does not exist in the output of interface {json_data["ifname"]}")
+            raise KsftSkipEx(f'Field {field} does not exist in the output of interface {json_data["ifname"]}')
         return json_data[field]

From 9b234a97b10cf1385d451a3824539b774abbcdaf Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 21 Nov 2024 19:41:05 +0000
Subject: [PATCH 1384/1530] rtnetlink: fix rtnl_dump_ifinfo() error path

syzbot found that rtnl_dump_ifinfo() could return with a lock held [1]

Move code around so that rtnl_link_ops_put() and put_net()
can be called at the end of this function.

[1]
WARNING: lock held when returning to user space!
6.12.0-rc7-syzkaller-01681-g38f83a57aa8e #0 Not tainted
syz-executor399/5841 is leaving the kernel with locks still held!
1 lock held by syz-executor399/5841:
  #0: ffffffff8f46c2a0 (&ops->srcu#2){.+.+}-{0:0}, at: rcu_lock_acquire include/linux/rcupdate.h:337 [inline]
  #0: ffffffff8f46c2a0 (&ops->srcu#2){.+.+}-{0:0}, at: rcu_read_lock include/linux/rcupdate.h:849 [inline]
  #0: ffffffff8f46c2a0 (&ops->srcu#2){.+.+}-{0:0}, at: rtnl_link_ops_get+0x22/0x250 net/core/rtnetlink.c:555

Fixes: 43c7ce69d28e ("rtnetlink: Protect struct rtnl_link_ops with SRCU.")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20241121194105.3632507-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/rtnetlink.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index dd142f444659d..58df76fe408a4 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2442,7 +2442,9 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 			tgt_net = rtnl_get_net_ns_capable(skb->sk, netnsid);
 			if (IS_ERR(tgt_net)) {
 				NL_SET_ERR_MSG(extack, "Invalid target network namespace id");
-				return PTR_ERR(tgt_net);
+				err = PTR_ERR(tgt_net);
+				netnsid = -1;
+				goto out;
 			}
 			break;
 		case IFLA_EXT_MASK:
@@ -2457,7 +2459,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 		default:
 			if (cb->strict_check) {
 				NL_SET_ERR_MSG(extack, "Unsupported attribute in link dump request");
-				return -EINVAL;
+				err = -EINVAL;
+				goto out;
 			}
 		}
 	}
@@ -2479,11 +2482,14 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 			break;
 	}
 
-	if (kind_ops)
-		rtnl_link_ops_put(kind_ops, ops_srcu_index);
 
 	cb->seq = tgt_net->dev_base_seq;
 	nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+
+out:
+
+	if (kind_ops)
+		rtnl_link_ops_put(kind_ops, ops_srcu_index);
 	if (netnsid >= 0)
 		put_net(tgt_net);
 

From 614f4d166eeeb9bd709b0ad29552f691c0f45776 Mon Sep 17 00:00:00 2001
From: Pavan Chebbi <pavan.chebbi@broadcom.com>
Date: Mon, 18 Nov 2024 21:57:41 -0800
Subject: [PATCH 1385/1530] tg3: Set coherent DMA mask bits to 31 for BCM57766
 chipsets

The hardware on Broadcom 1G chipsets have a known limitation
where they cannot handle DMA addresses that cross over 4GB.
When such an address is encountered, the hardware sets the
address overflow error bit in the DMA status register and
triggers a reset.

However, BCM57766 hardware is setting the overflow bit and
triggering a reset in some cases when there is no actual
underlying address overflow. The hardware team analyzed the
issue and concluded that it is happening when the status
block update has an address with higher (b16 to b31) bits
as 0xffff following a previous update that had lowest bits
as 0xffff.

To work around this bug in the BCM57766 hardware, set the
coherent dma mask from the current 64b to 31b. This will
ensure that upper bits of the status block DMA address are
always at most 0x7fff, thus avoiding the improper overflow
check described above. This work around is intended for only
status block and ring memories and has no effect on TX and
RX buffers as they do not require coherent memory.

Fixes: 72f2afb8a685 ("[TG3]: Add DMA address workaround")
Reported-by: Salam Noureddine <noureddine@arista.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Link: https://patch.msgid.link/20241119055741.147144-1-pavan.chebbi@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/tg3.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 01dfec1159428..9cc8db10a8d60 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -17839,6 +17839,9 @@ static int tg3_init_one(struct pci_dev *pdev,
 	} else
 		persist_dma_mask = dma_mask = DMA_BIT_MASK(64);
 
+	if (tg3_asic_rev(tp) == ASIC_REV_57766)
+		persist_dma_mask = DMA_BIT_MASK(31);
+
 	/* Configure DMA attributes. */
 	if (dma_mask > DMA_BIT_MASK(32)) {
 		err = dma_set_mask(&pdev->dev, dma_mask);

From e863ff806f72098bccaf8fa89c80d9ad6187c3b0 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Mon, 18 Nov 2024 15:03:51 +0100
Subject: [PATCH 1386/1530] net: usb: lan78xx: Fix refcounting and autosuspend
 on invalid WoL configuration

Validate Wake-on-LAN (WoL) options in `lan78xx_set_wol` before calling
`usb_autopm_get_interface`. This prevents USB autopm refcounting issues
and ensures the adapter can properly enter autosuspend when invalid WoL
options are provided.

Fixes: eb9ad088f966 ("lan78xx: Check for supported Wake-on-LAN modes")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Link: https://patch.msgid.link/20241118140351.2398166-1-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 9f191b6ce8215..531b1b6a37d19 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1652,13 +1652,13 @@ static int lan78xx_set_wol(struct net_device *netdev,
 	struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]);
 	int ret;
 
+	if (wol->wolopts & ~WAKE_ALL)
+		return -EINVAL;
+
 	ret = usb_autopm_get_interface(dev->intf);
 	if (ret < 0)
 		return ret;
 
-	if (wol->wolopts & ~WAKE_ALL)
-		return -EINVAL;
-
 	pdata->wol = wol->wolopts;
 
 	device_set_wakeup_enable(&dev->udev->dev, (bool)wol->wolopts);

From f164b296638d1eb1fb1c537e93ab5c8b49966546 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Tue, 19 Nov 2024 13:32:02 -0800
Subject: [PATCH 1387/1530] net: microchip: vcap: Add typegroup table
 terminators in kunit tests

VCAP API unit tests fail randomly with errors such as

   # vcap_api_iterator_init_test: EXPECTATION FAILED at drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c:387
   Expected 134 + 7 == iter.offset, but
       134 + 7 == 141 (0x8d)
       iter.offset == 17214 (0x433e)
   # vcap_api_iterator_init_test: EXPECTATION FAILED at drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c:388
   Expected 5 == iter.reg_idx, but
       iter.reg_idx == 702 (0x2be)
   # vcap_api_iterator_init_test: EXPECTATION FAILED at drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c:389
   Expected 11 == iter.reg_bitpos, but
       iter.reg_bitpos == 15 (0xf)
   # vcap_api_iterator_init_test: pass:0 fail:1 skip:0 total:1

Comments in the code state that "A typegroup table ends with an all-zero
terminator". Add the missing terminators.

Some of the typegroups did have a terminator of ".offset = 0, .width = 0,
.value = 0,". Replace those terminators with "{ }" (no trailing ',') for
consistency and to excplicitly state "this is a terminator".

Fixes: 67d637516fa9 ("net: microchip: sparx5: Adding KUNIT test for the VCAP API")
Cc: Steen Hegelund <steen.hegelund@microchip.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20241119213202.2884639-1-linux@roeck-us.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/microchip/vcap/vcap_api_kunit.c    | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c
index 7251121ab196e..16eb3de60eb6d 100644
--- a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c
+++ b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c
@@ -366,12 +366,13 @@ static void vcap_api_iterator_init_test(struct kunit *test)
 	struct vcap_typegroup typegroups[] = {
 		{ .offset = 0, .width = 2, .value = 2, },
 		{ .offset = 156, .width = 1, .value = 0, },
-		{ .offset = 0, .width = 0, .value = 0, },
+		{ }
 	};
 	struct vcap_typegroup typegroups2[] = {
 		{ .offset = 0, .width = 3, .value = 4, },
 		{ .offset = 49, .width = 2, .value = 0, },
 		{ .offset = 98, .width = 2, .value = 0, },
+		{ }
 	};
 
 	vcap_iter_init(&iter, 52, typegroups, 86);
@@ -399,6 +400,7 @@ static void vcap_api_iterator_next_test(struct kunit *test)
 		{ .offset = 147, .width = 3, .value = 0, },
 		{ .offset = 196, .width = 2, .value = 0, },
 		{ .offset = 245, .width = 1, .value = 0, },
+		{ }
 	};
 	int idx;
 
@@ -433,7 +435,7 @@ static void vcap_api_encode_typegroups_test(struct kunit *test)
 		{ .offset = 147, .width = 3, .value = 5, },
 		{ .offset = 196, .width = 2, .value = 2, },
 		{ .offset = 245, .width = 5, .value = 27, },
-		{ .offset = 0, .width = 0, .value = 0, },
+		{ }
 	};
 
 	vcap_encode_typegroups(stream, 49, typegroups, false);
@@ -463,6 +465,7 @@ static void vcap_api_encode_bit_test(struct kunit *test)
 		{ .offset = 147, .width = 3, .value = 5, },
 		{ .offset = 196, .width = 2, .value = 2, },
 		{ .offset = 245, .width = 1, .value = 0, },
+		{ }
 	};
 
 	vcap_iter_init(&iter, 49, typegroups, 44);
@@ -489,7 +492,7 @@ static void vcap_api_encode_field_test(struct kunit *test)
 		{ .offset = 147, .width = 3, .value = 5, },
 		{ .offset = 196, .width = 2, .value = 2, },
 		{ .offset = 245, .width = 5, .value = 27, },
-		{ .offset = 0, .width = 0, .value = 0, },
+		{ }
 	};
 	struct vcap_field rf = {
 		.type = VCAP_FIELD_U32,
@@ -538,7 +541,7 @@ static void vcap_api_encode_short_field_test(struct kunit *test)
 		{ .offset = 0, .width = 3, .value = 7, },
 		{ .offset = 21, .width = 2, .value = 3, },
 		{ .offset = 42, .width = 1, .value = 1, },
-		{ .offset = 0, .width = 0, .value = 0, },
+		{ }
 	};
 	struct vcap_field rf = {
 		.type = VCAP_FIELD_U32,
@@ -608,7 +611,7 @@ static void vcap_api_encode_keyfield_test(struct kunit *test)
 	struct vcap_typegroup tgt[] = {
 		{ .offset = 0, .width = 2, .value = 2, },
 		{ .offset = 156, .width = 1, .value = 1, },
-		{ .offset = 0, .width = 0, .value = 0, },
+		{ }
 	};
 
 	vcap_test_api_init(&admin);
@@ -671,7 +674,7 @@ static void vcap_api_encode_max_keyfield_test(struct kunit *test)
 	struct vcap_typegroup tgt[] = {
 		{ .offset = 0, .width = 2, .value = 2, },
 		{ .offset = 156, .width = 1, .value = 1, },
-		{ .offset = 0, .width = 0, .value = 0, },
+		{ }
 	};
 	u32 keyres[] = {
 		0x928e8a84,
@@ -732,7 +735,7 @@ static void vcap_api_encode_actionfield_test(struct kunit *test)
 		{ .offset = 0, .width = 2, .value = 2, },
 		{ .offset = 21, .width = 1, .value = 1, },
 		{ .offset = 42, .width = 1, .value = 0, },
-		{ .offset = 0, .width = 0, .value = 0, },
+		{ }
 	};
 
 	vcap_encode_actionfield(&rule, &caf, &rf, tgt);

From 3bf39fa849ab8ed52abb6715922e6102d3df9f97 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 19 Nov 2024 14:44:31 -0800
Subject: [PATCH 1388/1530] netlink: fix false positive warning in extack
 during dumps

Commit under fixes extended extack reporting to dumps.
It works under normal conditions, because extack errors are
usually reported during ->start() or the first ->dump(),
it's quite rare that the dump starts okay but fails later.
If the dump does fail later, however, the input skb will
already have the initiating message pulled, so checking
if bad attr falls within skb->data will fail.

Switch the check to using nlh, which is always valid.

syzbot found a way to hit that scenario by filling up
the receive queue. In this case we initiate a dump
but don't call ->dump() until there is read space for
an skb.

WARNING: CPU: 1 PID: 5845 at net/netlink/af_netlink.c:2210 netlink_ack_tlv_fill+0x1a8/0x560 net/netlink/af_netlink.c:2209
RIP: 0010:netlink_ack_tlv_fill+0x1a8/0x560 net/netlink/af_netlink.c:2209
Call Trace:
 <TASK>
 netlink_dump_done+0x513/0x970 net/netlink/af_netlink.c:2250
 netlink_dump+0x91f/0xe10 net/netlink/af_netlink.c:2351
 netlink_recvmsg+0x6bb/0x11d0 net/netlink/af_netlink.c:1983
 sock_recvmsg_nosec net/socket.c:1051 [inline]
 sock_recvmsg+0x22f/0x280 net/socket.c:1073
 __sys_recvfrom+0x246/0x3d0 net/socket.c:2267
 __do_sys_recvfrom net/socket.c:2285 [inline]
 __se_sys_recvfrom net/socket.c:2281 [inline]
 __x64_sys_recvfrom+0xde/0x100 net/socket.c:2281
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
 RIP: 0033:0x7ff37dd17a79

Reported-by: syzbot+d4373fa8042c06cefa84@syzkaller.appspotmail.com
Fixes: 8af4f60472fc ("netlink: support all extack types in dumps")
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20241119224432.1713040-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/netlink/af_netlink.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index dd3517b0fdfd5..f4e7b5e4bb59f 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2181,9 +2181,14 @@ netlink_ack_tlv_len(struct netlink_sock *nlk, int err,
 	return tlvlen;
 }
 
+static bool nlmsg_check_in_payload(const struct nlmsghdr *nlh, const void *addr)
+{
+	return !WARN_ON(addr < nlmsg_data(nlh) ||
+			addr - (const void *) nlh >= nlh->nlmsg_len);
+}
+
 static void
-netlink_ack_tlv_fill(struct sk_buff *in_skb, struct sk_buff *skb,
-		     const struct nlmsghdr *nlh, int err,
+netlink_ack_tlv_fill(struct sk_buff *skb, const struct nlmsghdr *nlh, int err,
 		     const struct netlink_ext_ack *extack)
 {
 	if (extack->_msg)
@@ -2195,9 +2200,7 @@ netlink_ack_tlv_fill(struct sk_buff *in_skb, struct sk_buff *skb,
 	if (!err)
 		return;
 
-	if (extack->bad_attr &&
-	    !WARN_ON((u8 *)extack->bad_attr < in_skb->data ||
-		     (u8 *)extack->bad_attr >= in_skb->data + in_skb->len))
+	if (extack->bad_attr && nlmsg_check_in_payload(nlh, extack->bad_attr))
 		WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS,
 				    (u8 *)extack->bad_attr - (const u8 *)nlh));
 	if (extack->policy)
@@ -2206,9 +2209,7 @@ netlink_ack_tlv_fill(struct sk_buff *in_skb, struct sk_buff *skb,
 	if (extack->miss_type)
 		WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_TYPE,
 				    extack->miss_type));
-	if (extack->miss_nest &&
-	    !WARN_ON((u8 *)extack->miss_nest < in_skb->data ||
-		     (u8 *)extack->miss_nest > in_skb->data + in_skb->len))
+	if (extack->miss_nest && nlmsg_check_in_payload(nlh, extack->miss_nest))
 		WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_NEST,
 				    (u8 *)extack->miss_nest - (const u8 *)nlh));
 }
@@ -2237,7 +2238,7 @@ static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb,
 	if (extack_len) {
 		nlh->nlmsg_flags |= NLM_F_ACK_TLVS;
 		if (skb_tailroom(skb) >= extack_len) {
-			netlink_ack_tlv_fill(cb->skb, skb, cb->nlh,
+			netlink_ack_tlv_fill(skb, cb->nlh,
 					     nlk->dump_done_errno, extack);
 			nlmsg_end(skb, nlh);
 		}
@@ -2496,7 +2497,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 	}
 
 	if (tlvlen)
-		netlink_ack_tlv_fill(in_skb, skb, nlh, err, extack);
+		netlink_ack_tlv_fill(skb, nlh, err, extack);
 
 	nlmsg_end(skb, rep);
 

From 9bb88c659673003453fd42e0ddf95c9628409094 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 19 Nov 2024 14:44:32 -0800
Subject: [PATCH 1389/1530] selftests: net: test extacks in netlink dumps

Test that extacks in dumps work. The test fills up the receive buffer
to test both the inline dump (as part of sendmsg()) and delayed one
(run during recvmsg()).

Use YNL helpers to parse the messages. We need to add the test to YNL
file to make sure the right include path are used.

Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20241119224432.1713040-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile        |   3 +-
 tools/testing/selftests/net/netlink-dumps.c | 129 ++++++++++++++++++++
 2 files changed, 130 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 3d487b03c4a09..cb2fc601de66b 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -78,7 +78,6 @@ TEST_PROGS += test_vxlan_vnifiltering.sh
 TEST_GEN_FILES += io_uring_zerocopy_tx
 TEST_PROGS += io_uring_zerocopy_tx.sh
 TEST_GEN_FILES += bind_bhash
-TEST_GEN_PROGS += netlink-dumps
 TEST_GEN_PROGS += sk_bind_sendto_listen
 TEST_GEN_PROGS += sk_connect_zero_addr
 TEST_GEN_PROGS += sk_so_peek_off
@@ -101,7 +100,7 @@ TEST_PROGS += ipv6_route_update_soft_lockup.sh
 TEST_PROGS += busy_poll_test.sh
 
 # YNL files, must be before "include ..lib.mk"
-YNL_GEN_FILES := busy_poller
+YNL_GEN_FILES := busy_poller netlink-dumps
 TEST_GEN_FILES += $(YNL_GEN_FILES)
 
 TEST_FILES := settings
diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c
index 84e29b7dffb64..07423f256f963 100644
--- a/tools/testing/selftests/net/netlink-dumps.c
+++ b/tools/testing/selftests/net/netlink-dumps.c
@@ -12,11 +12,140 @@
 #include <unistd.h>
 
 #include <linux/genetlink.h>
+#include <linux/neighbour.h>
+#include <linux/netdevice.h>
 #include <linux/netlink.h>
 #include <linux/mqueue.h>
+#include <linux/rtnetlink.h>
 
 #include "../kselftest_harness.h"
 
+#include <ynl.h>
+
+struct ext_ack {
+	int err;
+
+	__u32 attr_offs;
+	__u32 miss_type;
+	__u32 miss_nest;
+	const char *str;
+};
+
+/* 0: no done, 1: done found, 2: extack found, -1: error */
+static int nl_get_extack(char *buf, size_t n, struct ext_ack *ea)
+{
+	const struct nlmsghdr *nlh;
+	const struct nlattr *attr;
+	ssize_t rem;
+
+	for (rem = n; rem > 0; NLMSG_NEXT(nlh, rem)) {
+		nlh = (struct nlmsghdr *)&buf[n - rem];
+		if (!NLMSG_OK(nlh, rem))
+			return -1;
+
+		if (nlh->nlmsg_type != NLMSG_DONE)
+			continue;
+
+		ea->err = -*(int *)NLMSG_DATA(nlh);
+
+		if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS))
+			return 1;
+
+		ynl_attr_for_each(attr, nlh, sizeof(int)) {
+			switch (ynl_attr_type(attr)) {
+			case NLMSGERR_ATTR_OFFS:
+				ea->attr_offs = ynl_attr_get_u32(attr);
+				break;
+			case NLMSGERR_ATTR_MISS_TYPE:
+				ea->miss_type = ynl_attr_get_u32(attr);
+				break;
+			case NLMSGERR_ATTR_MISS_NEST:
+				ea->miss_nest = ynl_attr_get_u32(attr);
+				break;
+			case NLMSGERR_ATTR_MSG:
+				ea->str = ynl_attr_get_str(attr);
+				break;
+			}
+		}
+
+		return 2;
+	}
+
+	return 0;
+}
+
+static const struct {
+	struct nlmsghdr nlhdr;
+	struct ndmsg ndm;
+	struct nlattr ahdr;
+	__u32 val;
+} dump_neigh_bad = {
+	.nlhdr = {
+		.nlmsg_len	= sizeof(dump_neigh_bad),
+		.nlmsg_type	= RTM_GETNEIGH,
+		.nlmsg_flags	= NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP,
+		.nlmsg_seq	= 1,
+	},
+	.ndm = {
+		.ndm_family	= 123,
+	},
+	.ahdr = {
+		.nla_len	= 4 + 4,
+		.nla_type	= NDA_FLAGS_EXT,
+	},
+	.val = -1, // should fail MASK validation
+};
+
+TEST(dump_extack)
+{
+	int netlink_sock;
+	char buf[8192];
+	int one = 1;
+	int i, cnt;
+	ssize_t n;
+
+	netlink_sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	ASSERT_GE(netlink_sock, 0);
+
+	n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_CAP_ACK,
+		       &one, sizeof(one));
+	ASSERT_EQ(n, 0);
+	n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_EXT_ACK,
+		       &one, sizeof(one));
+	ASSERT_EQ(n, 0);
+	n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_GET_STRICT_CHK,
+		       &one, sizeof(one));
+	ASSERT_EQ(n, 0);
+
+	/* Dump so many times we fill up the buffer */
+	cnt = 64;
+	for (i = 0; i < cnt; i++) {
+		n = send(netlink_sock, &dump_neigh_bad,
+			 sizeof(dump_neigh_bad), 0);
+		ASSERT_EQ(n, sizeof(dump_neigh_bad));
+	}
+
+	/* Read out the ENOBUFS */
+	n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT);
+	EXPECT_EQ(n, -1);
+	EXPECT_EQ(errno, ENOBUFS);
+
+	for (i = 0; i < cnt; i++) {
+		struct ext_ack ea = {};
+
+		n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT);
+		if (n < 0) {
+			ASSERT_GE(i, 10);
+			break;
+		}
+		ASSERT_GE(n, (ssize_t)sizeof(struct nlmsghdr));
+
+		EXPECT_EQ(nl_get_extack(buf, n, &ea), 2);
+		EXPECT_EQ(ea.attr_offs,
+			  sizeof(struct nlmsghdr) + sizeof(struct ndmsg));
+	}
+}
+
 static const struct {
 	struct nlmsghdr nlhdr;
 	struct genlmsghdr genlhdr;

From 184fa506e392eb78364d9283c961217ff2c0617b Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Mon, 28 Oct 2024 11:23:36 +0800
Subject: [PATCH 1390/1530] exfat: fix out-of-bounds access of directory
 entries

In the case of the directory size is greater than or equal to
the cluster size, if start_clu becomes an EOF cluster(an invalid
cluster) due to file system corruption, then the directory entry
where ei->hint_femp.eidx hint is outside the directory, resulting
in an out-of-bounds access, which may cause further file system
corruption.

This commit adds a check for start_clu, if it is an invalid cluster,
the file or directory will be treated as empty.

Cc: stable@vger.kernel.org
Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Co-developed-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/namei.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 2c4c442293529..98f67e632ad16 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -637,14 +637,26 @@ static int exfat_find(struct inode *dir, struct qstr *qname,
 	info->size = le64_to_cpu(ep2->dentry.stream.valid_size);
 	info->valid_size = le64_to_cpu(ep2->dentry.stream.valid_size);
 	info->size = le64_to_cpu(ep2->dentry.stream.size);
+
+	info->start_clu = le32_to_cpu(ep2->dentry.stream.start_clu);
+	if (!is_valid_cluster(sbi, info->start_clu) && info->size) {
+		exfat_warn(sb, "start_clu is invalid cluster(0x%x)",
+				info->start_clu);
+		info->size = 0;
+		info->valid_size = 0;
+	}
+
+	if (info->valid_size > info->size) {
+		exfat_warn(sb, "valid_size(%lld) is greater than size(%lld)",
+				info->valid_size, info->size);
+		info->valid_size = info->size;
+	}
+
 	if (info->size == 0) {
 		info->flags = ALLOC_NO_FAT_CHAIN;
 		info->start_clu = EXFAT_EOF_CLUSTER;
-	} else {
+	} else
 		info->flags = ep2->dentry.stream.flags;
-		info->start_clu =
-			le32_to_cpu(ep2->dentry.stream.start_clu);
-	}
 
 	exfat_get_entry_time(sbi, &info->crtime,
 			     ep->dentry.file.create_tz,

From 02dffe9ab092fc4c8800aee68cb7eafd37a980c4 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Sat, 26 Oct 2024 13:06:15 +0900
Subject: [PATCH 1391/1530] exfat: fix uninit-value in __exfat_get_dentry_set

There is no check if stream size and start_clu are invalid.
If start_clu is EOF cluster and stream size is 4096, It will
cause uninit value access. because ei->hint_femp.eidx could
be 128(if cluster size is 4K) and wrong hint will allocate
next cluster. and this cluster will be same with the cluster
that is allocated by exfat_extend_valid_size(). The previous
patch will check invalid start_clu, but for clarity, initialize
hint_femp.eidx to zero.

Cc: stable@vger.kernel.org
Reported-by: syzbot+01218003be74b5e1213a@syzkaller.appspotmail.com
Tested-by: syzbot+01218003be74b5e1213a@syzkaller.appspotmail.com
Reviewed-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/namei.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 98f67e632ad16..337197ece5995 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -345,6 +345,7 @@ static int exfat_find_empty_entry(struct inode *inode,
 		if (ei->start_clu == EXFAT_EOF_CLUSTER) {
 			ei->start_clu = clu.dir;
 			p_dir->dir = clu.dir;
+			hint_femp.eidx = 0;
 		}
 
 		/* append to the FAT chain */

From 2e94e5bb94a3e641a25716a560bf474225fda83c Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Thu, 17 Oct 2024 09:25:06 +0800
Subject: [PATCH 1392/1530] exfat: fix file being changed by unaligned direct
 write

Unaligned direct writes are invalid and should return an error
without making any changes, rather than extending ->valid_size
and then returning an error. Therefore, alignment checking is
required before extending ->valid_size.

Fixes: 11a347fb6cef ("exfat: change to get file size from DataLength")
Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Co-developed-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/file.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index a25d7eb789f4c..fb38769c3e39d 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -584,6 +584,16 @@ static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	if (ret < 0)
 		goto unlock;
 
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		unsigned long align = pos | iov_iter_alignment(iter);
+
+		if (!IS_ALIGNED(align, i_blocksize(inode)) &&
+		    !IS_ALIGNED(align, bdev_logical_block_size(inode->i_sb->s_bdev))) {
+			ret = -EINVAL;
+			goto unlock;
+		}
+	}
+
 	if (pos > valid_size) {
 		ret = exfat_extend_valid_size(file, pos);
 		if (ret < 0 && ret != -ENOSPC) {

From 30ef0e0d7ff5b6dceda19d18a85d9d72a4909784 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Thu, 8 Aug 2024 15:37:13 +0800
Subject: [PATCH 1393/1530] exfat: remove unnecessary read entry in
 __exfat_rename()

To determine whether it is a directory, there is no need to read its
directory entry, just use S_ISDIR(inode->i_mode).

Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com>
Reviewed-by: Daniel Palmer <daniel.palmer@sony.com>
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/namei.c | 20 ++++----------------
 1 file changed, 4 insertions(+), 16 deletions(-)

diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 337197ece5995..4b7308fae3d32 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -1131,17 +1131,12 @@ static int __exfat_rename(struct inode *old_parent_inode,
 	int ret;
 	int dentry;
 	struct exfat_chain olddir, newdir;
-	struct exfat_chain *p_dir = NULL;
 	struct exfat_uni_name uni_name;
-	struct exfat_dentry *ep;
 	struct super_block *sb = old_parent_inode->i_sb;
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
 	const unsigned char *new_path = new_dentry->d_name.name;
 	struct inode *new_inode = new_dentry->d_inode;
 	struct exfat_inode_info *new_ei = NULL;
-	unsigned int new_entry_type = TYPE_UNUSED;
-	int new_entry = 0;
-	struct buffer_head *new_bh = NULL;
 
 	/* check the validity of pointer parameters */
 	if (new_path == NULL || strlen(new_path) == 0)
@@ -1167,17 +1162,8 @@ static int __exfat_rename(struct inode *old_parent_inode,
 			goto out;
 		}
 
-		p_dir = &(new_ei->dir);
-		new_entry = new_ei->entry;
-		ep = exfat_get_dentry(sb, p_dir, new_entry, &new_bh);
-		if (!ep)
-			goto out;
-
-		new_entry_type = exfat_get_entry_type(ep);
-		brelse(new_bh);
-
 		/* if new_inode exists, update ei */
-		if (new_entry_type == TYPE_DIR) {
+		if (S_ISDIR(new_inode->i_mode)) {
 			struct exfat_chain new_clu;
 
 			new_clu.dir = new_ei->start_clu;
@@ -1209,6 +1195,8 @@ static int __exfat_rename(struct inode *old_parent_inode,
 
 	if (!ret && new_inode) {
 		struct exfat_entry_set_cache es;
+		struct exfat_chain *p_dir = &(new_ei->dir);
+		int new_entry = new_ei->entry;
 
 		/* delete entries of new_dir */
 		ret = exfat_get_dentry_set(&es, sb, p_dir, new_entry,
@@ -1225,7 +1213,7 @@ static int __exfat_rename(struct inode *old_parent_inode,
 			goto del_out;
 
 		/* Free the clusters if new_inode is a dir(as if exfat_rmdir) */
-		if (new_entry_type == TYPE_DIR &&
+		if (S_ISDIR(new_inode->i_mode) &&
 		    new_ei->start_clu != EXFAT_EOF_CLUSTER) {
 			/* new_ei, new_clu_to_free */
 			struct exfat_chain new_clu_to_free;

From 06a2b0b3b490a6103376652c01c3ac6e8e22e654 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Fri, 15 Nov 2024 09:43:10 +0800
Subject: [PATCH 1394/1530] exfat: rename argument name for exfat_move_file and
 exfat_rename_file

In this exfat implementation, the relationship between inode and ei
is ei=EXFAT_I(inode). However, in the arguments of exfat_move_file()
and exfat_rename_file(), argument 'inode' indicates the parent
directory, but argument 'ei' indicates the target file to be renamed.
They do not have the above relationship, which is not friendly to code
readers.

So this commit renames 'inode' to 'parent_inode', making the argument
name match its role.

Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/namei.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 4b7308fae3d32..b0bf8c47dd5ea 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -995,15 +995,15 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry)
 	return err;
 }
 
-static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir,
+static int exfat_rename_file(struct inode *parent_inode, struct exfat_chain *p_dir,
 		int oldentry, struct exfat_uni_name *p_uniname,
 		struct exfat_inode_info *ei)
 {
 	int ret, num_new_entries;
 	struct exfat_dentry *epold, *epnew;
-	struct super_block *sb = inode->i_sb;
+	struct super_block *sb = parent_inode->i_sb;
 	struct exfat_entry_set_cache old_es, new_es;
-	int sync = IS_DIRSYNC(inode);
+	int sync = IS_DIRSYNC(parent_inode);
 
 	if (unlikely(exfat_forced_shutdown(sb)))
 		return -EIO;
@@ -1023,7 +1023,7 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir,
 	if (old_es.num_entries < num_new_entries) {
 		int newentry;
 
-		newentry = exfat_find_empty_entry(inode, p_dir, num_new_entries,
+		newentry = exfat_find_empty_entry(parent_inode, p_dir, num_new_entries,
 				&new_es);
 		if (newentry < 0) {
 			ret = newentry; /* -EIO or -ENOSPC */
@@ -1047,7 +1047,7 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir,
 		if (ret)
 			goto put_old_es;
 
-		exfat_remove_entries(inode, &old_es, ES_IDX_FILE);
+		exfat_remove_entries(parent_inode, &old_es, ES_IDX_FILE);
 		ei->dir = *p_dir;
 		ei->entry = newentry;
 	} else {
@@ -1056,7 +1056,7 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir,
 			ei->attr |= EXFAT_ATTR_ARCHIVE;
 		}
 
-		exfat_remove_entries(inode, &old_es, ES_IDX_FIRST_FILENAME + 1);
+		exfat_remove_entries(parent_inode, &old_es, ES_IDX_FIRST_FILENAME + 1);
 		exfat_init_ext_entry(&old_es, num_new_entries, p_uniname);
 	}
 	return exfat_put_dentry_set(&old_es, sync);
@@ -1066,13 +1066,13 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir,
 	return ret;
 }
 
-static int exfat_move_file(struct inode *inode, struct exfat_chain *p_olddir,
+static int exfat_move_file(struct inode *parent_inode, struct exfat_chain *p_olddir,
 		int oldentry, struct exfat_chain *p_newdir,
 		struct exfat_uni_name *p_uniname, struct exfat_inode_info *ei)
 {
 	int ret, newentry, num_new_entries;
 	struct exfat_dentry *epmov, *epnew;
-	struct super_block *sb = inode->i_sb;
+	struct super_block *sb = parent_inode->i_sb;
 	struct exfat_entry_set_cache mov_es, new_es;
 
 	num_new_entries = exfat_calc_num_entries(p_uniname);
@@ -1084,7 +1084,7 @@ static int exfat_move_file(struct inode *inode, struct exfat_chain *p_olddir,
 	if (ret)
 		return -EIO;
 
-	newentry = exfat_find_empty_entry(inode, p_newdir, num_new_entries,
+	newentry = exfat_find_empty_entry(parent_inode, p_newdir, num_new_entries,
 			&new_es);
 	if (newentry < 0) {
 		ret = newentry; /* -EIO or -ENOSPC */
@@ -1104,18 +1104,18 @@ static int exfat_move_file(struct inode *inode, struct exfat_chain *p_olddir,
 	*epnew = *epmov;
 
 	exfat_init_ext_entry(&new_es, num_new_entries, p_uniname);
-	exfat_remove_entries(inode, &mov_es, ES_IDX_FILE);
+	exfat_remove_entries(parent_inode, &mov_es, ES_IDX_FILE);
 
 	exfat_chain_set(&ei->dir, p_newdir->dir, p_newdir->size,
 		p_newdir->flags);
 
 	ei->entry = newentry;
 
-	ret = exfat_put_dentry_set(&new_es, IS_DIRSYNC(inode));
+	ret = exfat_put_dentry_set(&new_es, IS_DIRSYNC(parent_inode));
 	if (ret)
 		goto put_mov_es;
 
-	return exfat_put_dentry_set(&mov_es, IS_DIRSYNC(inode));
+	return exfat_put_dentry_set(&mov_es, IS_DIRSYNC(parent_inode));
 
 put_mov_es:
 	exfat_put_dentry_set(&mov_es, false);

From ac844e91364a03c35838fd488437605fbe56f8c3 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Fri, 13 Sep 2024 13:13:54 +0800
Subject: [PATCH 1395/1530] exfat: add exfat_get_dentry_set_by_ei() helper

This helper gets the directory entry set of the file for the exfat
inode which has been created.

It's used to remove all the instances of the pattern it replaces
making the code cleaner, it's also a preparation for changing ->dir
to record the cluster where the directory entry set is located and
changing ->entry to record the index of the directory entry within
the cluster.

Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com>
Reviewed-by: Daniel Palmer <daniel.palmer@sony.com>
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/exfat_fs.h |  2 ++
 fs/exfat/inode.c    |  2 +-
 fs/exfat/namei.c    | 53 +++++++++++++++------------------------------
 3 files changed, 21 insertions(+), 36 deletions(-)

diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 3cdc1de362a94..28cc18d29236b 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -508,6 +508,8 @@ struct exfat_dentry *exfat_get_dentry_cached(struct exfat_entry_set_cache *es,
 int exfat_get_dentry_set(struct exfat_entry_set_cache *es,
 		struct super_block *sb, struct exfat_chain *p_dir, int entry,
 		unsigned int num_entries);
+#define exfat_get_dentry_set_by_ei(es, sb, ei)		\
+	exfat_get_dentry_set(es, sb, &(ei)->dir, (ei)->entry, ES_ALL_ENTRIES)
 int exfat_get_empty_dentry_set(struct exfat_entry_set_cache *es,
 		struct super_block *sb, struct exfat_chain *p_dir, int entry,
 		unsigned int num_entries);
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index d724de8f57bf9..96952d4acb500 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -43,7 +43,7 @@ int __exfat_write_inode(struct inode *inode, int sync)
 	exfat_set_volume_dirty(sb);
 
 	/* get the directory entry of given file or directory */
-	if (exfat_get_dentry_set(&es, sb, &(ei->dir), ei->entry, ES_ALL_ENTRIES))
+	if (exfat_get_dentry_set_by_ei(&es, sb, ei))
 		return -EIO;
 	ep = exfat_get_dentry_cached(&es, ES_IDX_FILE);
 	ep2 = exfat_get_dentry_cached(&es, ES_IDX_STREAM);
diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index b0bf8c47dd5ea..b42cffe813bbb 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -779,26 +779,23 @@ static struct dentry *exfat_lookup(struct inode *dir, struct dentry *dentry,
 /* remove an entry, BUT don't truncate */
 static int exfat_unlink(struct inode *dir, struct dentry *dentry)
 {
-	struct exfat_chain cdir;
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode = dentry->d_inode;
 	struct exfat_inode_info *ei = EXFAT_I(inode);
 	struct exfat_entry_set_cache es;
-	int entry, err = 0;
+	int err = 0;
 
 	if (unlikely(exfat_forced_shutdown(sb)))
 		return -EIO;
 
 	mutex_lock(&EXFAT_SB(sb)->s_lock);
-	exfat_chain_dup(&cdir, &ei->dir);
-	entry = ei->entry;
 	if (ei->dir.dir == DIR_DELETED) {
 		exfat_err(sb, "abnormal access to deleted dentry");
 		err = -ENOENT;
 		goto unlock;
 	}
 
-	err = exfat_get_dentry_set(&es, sb, &cdir, entry, ES_ALL_ENTRIES);
+	err = exfat_get_dentry_set_by_ei(&es, sb, ei);
 	if (err) {
 		err = -EIO;
 		goto unlock;
@@ -928,21 +925,18 @@ static int exfat_check_dir_empty(struct super_block *sb,
 static int exfat_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode = dentry->d_inode;
-	struct exfat_chain cdir, clu_to_free;
+	struct exfat_chain clu_to_free;
 	struct super_block *sb = inode->i_sb;
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
 	struct exfat_inode_info *ei = EXFAT_I(inode);
 	struct exfat_entry_set_cache es;
-	int entry, err;
+	int err;
 
 	if (unlikely(exfat_forced_shutdown(sb)))
 		return -EIO;
 
 	mutex_lock(&EXFAT_SB(inode->i_sb)->s_lock);
 
-	exfat_chain_dup(&cdir, &ei->dir);
-	entry = ei->entry;
-
 	if (ei->dir.dir == DIR_DELETED) {
 		exfat_err(sb, "abnormal access to deleted dentry");
 		err = -ENOENT;
@@ -960,7 +954,7 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry)
 		goto unlock;
 	}
 
-	err = exfat_get_dentry_set(&es, sb, &cdir, entry, ES_ALL_ENTRIES);
+	err = exfat_get_dentry_set_by_ei(&es, sb, ei);
 	if (err) {
 		err = -EIO;
 		goto unlock;
@@ -995,8 +989,8 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry)
 	return err;
 }
 
-static int exfat_rename_file(struct inode *parent_inode, struct exfat_chain *p_dir,
-		int oldentry, struct exfat_uni_name *p_uniname,
+static int exfat_rename_file(struct inode *parent_inode,
+		struct exfat_chain *p_dir, struct exfat_uni_name *p_uniname,
 		struct exfat_inode_info *ei)
 {
 	int ret, num_new_entries;
@@ -1012,7 +1006,7 @@ static int exfat_rename_file(struct inode *parent_inode, struct exfat_chain *p_d
 	if (num_new_entries < 0)
 		return num_new_entries;
 
-	ret = exfat_get_dentry_set(&old_es, sb, p_dir, oldentry, ES_ALL_ENTRIES);
+	ret = exfat_get_dentry_set_by_ei(&old_es, sb, ei);
 	if (ret) {
 		ret = -EIO;
 		return ret;
@@ -1066,21 +1060,19 @@ static int exfat_rename_file(struct inode *parent_inode, struct exfat_chain *p_d
 	return ret;
 }
 
-static int exfat_move_file(struct inode *parent_inode, struct exfat_chain *p_olddir,
-		int oldentry, struct exfat_chain *p_newdir,
-		struct exfat_uni_name *p_uniname, struct exfat_inode_info *ei)
+static int exfat_move_file(struct inode *parent_inode,
+		struct exfat_chain *p_newdir, struct exfat_uni_name *p_uniname,
+		struct exfat_inode_info *ei)
 {
 	int ret, newentry, num_new_entries;
 	struct exfat_dentry *epmov, *epnew;
-	struct super_block *sb = parent_inode->i_sb;
 	struct exfat_entry_set_cache mov_es, new_es;
 
 	num_new_entries = exfat_calc_num_entries(p_uniname);
 	if (num_new_entries < 0)
 		return num_new_entries;
 
-	ret = exfat_get_dentry_set(&mov_es, sb, p_olddir, oldentry,
-			ES_ALL_ENTRIES);
+	ret = exfat_get_dentry_set_by_ei(&mov_es, parent_inode->i_sb, ei);
 	if (ret)
 		return -EIO;
 
@@ -1129,8 +1121,7 @@ static int __exfat_rename(struct inode *old_parent_inode,
 		struct dentry *new_dentry)
 {
 	int ret;
-	int dentry;
-	struct exfat_chain olddir, newdir;
+	struct exfat_chain newdir;
 	struct exfat_uni_name uni_name;
 	struct super_block *sb = old_parent_inode->i_sb;
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
@@ -1147,11 +1138,6 @@ static int __exfat_rename(struct inode *old_parent_inode,
 		return -ENOENT;
 	}
 
-	exfat_chain_set(&olddir, EXFAT_I(old_parent_inode)->start_clu,
-		EXFAT_B_TO_CLU_ROUND_UP(i_size_read(old_parent_inode), sbi),
-		EXFAT_I(old_parent_inode)->flags);
-	dentry = ei->entry;
-
 	/* check whether new dir is existing directory and empty */
 	if (new_inode) {
 		ret = -EIO;
@@ -1186,21 +1172,18 @@ static int __exfat_rename(struct inode *old_parent_inode,
 
 	exfat_set_volume_dirty(sb);
 
-	if (olddir.dir == newdir.dir)
-		ret = exfat_rename_file(new_parent_inode, &olddir, dentry,
+	if (new_parent_inode == old_parent_inode)
+		ret = exfat_rename_file(new_parent_inode, &newdir,
 				&uni_name, ei);
 	else
-		ret = exfat_move_file(new_parent_inode, &olddir, dentry,
-				&newdir, &uni_name, ei);
+		ret = exfat_move_file(new_parent_inode, &newdir,
+				&uni_name, ei);
 
 	if (!ret && new_inode) {
 		struct exfat_entry_set_cache es;
-		struct exfat_chain *p_dir = &(new_ei->dir);
-		int new_entry = new_ei->entry;
 
 		/* delete entries of new_dir */
-		ret = exfat_get_dentry_set(&es, sb, p_dir, new_entry,
-				ES_ALL_ENTRIES);
+		ret = exfat_get_dentry_set_by_ei(&es, sb, new_ei);
 		if (ret) {
 			ret = -EIO;
 			goto del_out;

From 0891c7313d87a1b6baf7162bc2f0d755ce70383f Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Fri, 13 Sep 2024 18:02:39 +0800
Subject: [PATCH 1396/1530] exfat: move exfat_chain_set() out of
 __exfat_resolve_path()

__exfat_resolve_path() mixes two functions. The first one is to
resolve and check if the path is valid. The second one is to output
the cluster assigned to the directory.

The second one is only needed when need to traverse the directory
entries, and calling exfat_chain_set() so early causes p_dir to be
passed as an argument multiple times, increasing the complexity of
the code.

This commit moves the call to exfat_chain_set() before traversing
directory entries.

Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com>
Reviewed-by: Daniel Palmer <daniel.palmer@sony.com>
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/namei.c | 60 +++++++++++++++++++++---------------------------
 1 file changed, 26 insertions(+), 34 deletions(-)

diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index b42cffe813bbb..cfe08f5565b69 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -311,6 +311,9 @@ static int exfat_find_empty_entry(struct inode *inode,
 		ei->hint_femp.eidx = EXFAT_HINT_NONE;
 	}
 
+	exfat_chain_set(p_dir, ei->start_clu,
+			EXFAT_B_TO_CLU(i_size_read(inode), sbi), ei->flags);
+
 	while ((dentry = exfat_search_empty_slot(sb, &hint_femp, p_dir,
 					num_entries, es)) < 0) {
 		if (dentry == -EIO)
@@ -386,14 +389,11 @@ static int exfat_find_empty_entry(struct inode *inode,
  * Zero if it was successful; otherwise nonzero.
  */
 static int __exfat_resolve_path(struct inode *inode, const unsigned char *path,
-		struct exfat_chain *p_dir, struct exfat_uni_name *p_uniname,
-		int lookup)
+		struct exfat_uni_name *p_uniname, int lookup)
 {
 	int namelen;
 	int lossy = NLS_NAME_NO_LOSSY;
 	struct super_block *sb = inode->i_sb;
-	struct exfat_sb_info *sbi = EXFAT_SB(sb);
-	struct exfat_inode_info *ei = EXFAT_I(inode);
 	int pathlen = strlen(path);
 
 	/*
@@ -432,24 +432,19 @@ static int __exfat_resolve_path(struct inode *inode, const unsigned char *path,
 	if ((lossy && !lookup) || !namelen)
 		return (lossy & NLS_NAME_OVERLEN) ? -ENAMETOOLONG : -EINVAL;
 
-	exfat_chain_set(p_dir, ei->start_clu,
-		EXFAT_B_TO_CLU(i_size_read(inode), sbi), ei->flags);
-
 	return 0;
 }
 
 static inline int exfat_resolve_path(struct inode *inode,
-		const unsigned char *path, struct exfat_chain *dir,
-		struct exfat_uni_name *uni)
+		const unsigned char *path, struct exfat_uni_name *uni)
 {
-	return __exfat_resolve_path(inode, path, dir, uni, 0);
+	return __exfat_resolve_path(inode, path, uni, 0);
 }
 
 static inline int exfat_resolve_path_for_lookup(struct inode *inode,
-		const unsigned char *path, struct exfat_chain *dir,
-		struct exfat_uni_name *uni)
+		const unsigned char *path, struct exfat_uni_name *uni)
 {
-	return __exfat_resolve_path(inode, path, dir, uni, 1);
+	return __exfat_resolve_path(inode, path, uni, 1);
 }
 
 static inline loff_t exfat_make_i_pos(struct exfat_dir_entry *info)
@@ -471,7 +466,7 @@ static int exfat_add_entry(struct inode *inode, const char *path,
 	int clu_size = 0;
 	unsigned int start_clu = EXFAT_FREE_CLUSTER;
 
-	ret = exfat_resolve_path(inode, path, p_dir, &uniname);
+	ret = exfat_resolve_path(inode, path, &uniname);
 	if (ret)
 		goto out;
 
@@ -602,10 +597,13 @@ static int exfat_find(struct inode *dir, struct qstr *qname,
 		return -ENOENT;
 
 	/* check the validity of directory name in the given pathname */
-	ret = exfat_resolve_path_for_lookup(dir, qname->name, &cdir, &uni_name);
+	ret = exfat_resolve_path_for_lookup(dir, qname->name, &uni_name);
 	if (ret)
 		return ret;
 
+	exfat_chain_set(&cdir, ei->start_clu,
+		EXFAT_B_TO_CLU(i_size_read(dir), sbi), ei->flags);
+
 	/* check the validation of hint_stat and initialize it if required */
 	if (ei->version != (inode_peek_iversion_raw(dir) & 0xffffffff)) {
 		ei->hint_stat.clu = cdir.dir;
@@ -990,8 +988,7 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry)
 }
 
 static int exfat_rename_file(struct inode *parent_inode,
-		struct exfat_chain *p_dir, struct exfat_uni_name *p_uniname,
-		struct exfat_inode_info *ei)
+		struct exfat_uni_name *p_uniname, struct exfat_inode_info *ei)
 {
 	int ret, num_new_entries;
 	struct exfat_dentry *epold, *epnew;
@@ -1016,9 +1013,10 @@ static int exfat_rename_file(struct inode *parent_inode,
 
 	if (old_es.num_entries < num_new_entries) {
 		int newentry;
+		struct exfat_chain dir;
 
-		newentry = exfat_find_empty_entry(parent_inode, p_dir, num_new_entries,
-				&new_es);
+		newentry = exfat_find_empty_entry(parent_inode, &dir,
+				num_new_entries, &new_es);
 		if (newentry < 0) {
 			ret = newentry; /* -EIO or -ENOSPC */
 			goto put_old_es;
@@ -1042,7 +1040,7 @@ static int exfat_rename_file(struct inode *parent_inode,
 			goto put_old_es;
 
 		exfat_remove_entries(parent_inode, &old_es, ES_IDX_FILE);
-		ei->dir = *p_dir;
+		ei->dir = dir;
 		ei->entry = newentry;
 	} else {
 		if (exfat_get_entry_type(epold) == TYPE_FILE) {
@@ -1061,12 +1059,12 @@ static int exfat_rename_file(struct inode *parent_inode,
 }
 
 static int exfat_move_file(struct inode *parent_inode,
-		struct exfat_chain *p_newdir, struct exfat_uni_name *p_uniname,
-		struct exfat_inode_info *ei)
+		struct exfat_uni_name *p_uniname, struct exfat_inode_info *ei)
 {
 	int ret, newentry, num_new_entries;
 	struct exfat_dentry *epmov, *epnew;
 	struct exfat_entry_set_cache mov_es, new_es;
+	struct exfat_chain newdir;
 
 	num_new_entries = exfat_calc_num_entries(p_uniname);
 	if (num_new_entries < 0)
@@ -1076,8 +1074,8 @@ static int exfat_move_file(struct inode *parent_inode,
 	if (ret)
 		return -EIO;
 
-	newentry = exfat_find_empty_entry(parent_inode, p_newdir, num_new_entries,
-			&new_es);
+	newentry = exfat_find_empty_entry(parent_inode, &newdir,
+			num_new_entries, &new_es);
 	if (newentry < 0) {
 		ret = newentry; /* -EIO or -ENOSPC */
 		goto put_mov_es;
@@ -1098,9 +1096,7 @@ static int exfat_move_file(struct inode *parent_inode,
 	exfat_init_ext_entry(&new_es, num_new_entries, p_uniname);
 	exfat_remove_entries(parent_inode, &mov_es, ES_IDX_FILE);
 
-	exfat_chain_set(&ei->dir, p_newdir->dir, p_newdir->size,
-		p_newdir->flags);
-
+	ei->dir = newdir;
 	ei->entry = newentry;
 
 	ret = exfat_put_dentry_set(&new_es, IS_DIRSYNC(parent_inode));
@@ -1121,7 +1117,6 @@ static int __exfat_rename(struct inode *old_parent_inode,
 		struct dentry *new_dentry)
 {
 	int ret;
-	struct exfat_chain newdir;
 	struct exfat_uni_name uni_name;
 	struct super_block *sb = old_parent_inode->i_sb;
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
@@ -1165,19 +1160,16 @@ static int __exfat_rename(struct inode *old_parent_inode,
 	}
 
 	/* check the validity of directory name in the given new pathname */
-	ret = exfat_resolve_path(new_parent_inode, new_path, &newdir,
-			&uni_name);
+	ret = exfat_resolve_path(new_parent_inode, new_path, &uni_name);
 	if (ret)
 		goto out;
 
 	exfat_set_volume_dirty(sb);
 
 	if (new_parent_inode == old_parent_inode)
-		ret = exfat_rename_file(new_parent_inode, &newdir,
-				&uni_name, ei);
+		ret = exfat_rename_file(new_parent_inode, &uni_name, ei);
 	else
-		ret = exfat_move_file(new_parent_inode, &newdir,
-				&uni_name, ei);
+		ret = exfat_move_file(new_parent_inode, &uni_name, ei);
 
 	if (!ret && new_inode) {
 		struct exfat_entry_set_cache es;

From 33a86666d37ed44a7280adcc6ca293f7718507b2 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Fri, 6 Sep 2024 14:55:53 +0800
Subject: [PATCH 1397/1530] exfat: remove argument 'p_dir' from
 exfat_add_entry()

The output of argument 'p_dir' of exfat_add_entry() is not used
in either exfat_mkdir() or exfat_create(), remove the argument.

Code refinement, no functional changes.

Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com>
Reviewed-by: Daniel Palmer <daniel.palmer@sony.com>
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/namei.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index cfe08f5565b69..8138ed61c1b28 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -453,8 +453,7 @@ static inline loff_t exfat_make_i_pos(struct exfat_dir_entry *info)
 }
 
 static int exfat_add_entry(struct inode *inode, const char *path,
-		struct exfat_chain *p_dir, unsigned int type,
-		struct exfat_dir_entry *info)
+		unsigned int type, struct exfat_dir_entry *info)
 {
 	int ret, dentry, num_entries;
 	struct super_block *sb = inode->i_sb;
@@ -477,7 +476,7 @@ static int exfat_add_entry(struct inode *inode, const char *path,
 	}
 
 	/* exfat_find_empty_entry must be called before alloc_cluster() */
-	dentry = exfat_find_empty_entry(inode, p_dir, num_entries, &es);
+	dentry = exfat_find_empty_entry(inode, &info->dir, num_entries, &es);
 	if (dentry < 0) {
 		ret = dentry; /* -EIO or -ENOSPC */
 		goto out;
@@ -504,7 +503,6 @@ static int exfat_add_entry(struct inode *inode, const char *path,
 	if (ret)
 		goto out;
 
-	info->dir = *p_dir;
 	info->entry = dentry;
 	info->flags = ALLOC_NO_FAT_CHAIN;
 	info->type = type;
@@ -537,7 +535,6 @@ static int exfat_create(struct mnt_idmap *idmap, struct inode *dir,
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode;
-	struct exfat_chain cdir;
 	struct exfat_dir_entry info;
 	loff_t i_pos;
 	int err;
@@ -548,8 +545,7 @@ static int exfat_create(struct mnt_idmap *idmap, struct inode *dir,
 
 	mutex_lock(&EXFAT_SB(sb)->s_lock);
 	exfat_set_volume_dirty(sb);
-	err = exfat_add_entry(dir, dentry->d_name.name, &cdir, TYPE_FILE,
-		&info);
+	err = exfat_add_entry(dir, dentry->d_name.name, TYPE_FILE, &info);
 	if (err)
 		goto unlock;
 
@@ -832,7 +828,6 @@ static int exfat_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode;
 	struct exfat_dir_entry info;
-	struct exfat_chain cdir;
 	loff_t i_pos;
 	int err;
 	loff_t size = i_size_read(dir);
@@ -842,8 +837,7 @@ static int exfat_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 
 	mutex_lock(&EXFAT_SB(sb)->s_lock);
 	exfat_set_volume_dirty(sb);
-	err = exfat_add_entry(dir, dentry->d_name.name, &cdir, TYPE_DIR,
-		&info);
+	err = exfat_add_entry(dir, dentry->d_name.name, TYPE_DIR, &info);
 	if (err)
 		goto unlock;
 

From 6b151eb5df78dc1a1ea7c862834199e08ea11c7b Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Thu, 12 Sep 2024 17:07:01 +0800
Subject: [PATCH 1398/1530] exfat: code cleanup for exfat_readdir()

For the root directory and other directories, the clusters
allocated to them can be obtained from exfat_inode_info, and
there is no need to distinguish them.

And there is no need to initialize atime/ctime/mtime/size in
exfat_readdir(), because exfat_iterate() does not use them.

Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com>
Reviewed-by: Daniel Palmer <daniel.palmer@sony.com>
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/dir.c | 24 ++----------------------
 1 file changed, 2 insertions(+), 22 deletions(-)

diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c
index 7446bf09a04a8..24149e0ebb82d 100644
--- a/fs/exfat/dir.c
+++ b/fs/exfat/dir.c
@@ -82,11 +82,8 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent
 	if (ei->type != TYPE_DIR)
 		return -EPERM;
 
-	if (ei->entry == -1)
-		exfat_chain_set(&dir, sbi->root_dir, 0, ALLOC_FAT_CHAIN);
-	else
-		exfat_chain_set(&dir, ei->start_clu,
-			EXFAT_B_TO_CLU(i_size_read(inode), sbi), ei->flags);
+	exfat_chain_set(&dir, ei->start_clu,
+		EXFAT_B_TO_CLU(i_size_read(inode), sbi), ei->flags);
 
 	dentries_per_clu = sbi->dentries_per_clu;
 	max_dentries = (unsigned int)min_t(u64, MAX_EXFAT_DENTRIES,
@@ -135,21 +132,6 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent
 
 			num_ext = ep->dentry.file.num_ext;
 			dir_entry->attr = le16_to_cpu(ep->dentry.file.attr);
-			exfat_get_entry_time(sbi, &dir_entry->crtime,
-					ep->dentry.file.create_tz,
-					ep->dentry.file.create_time,
-					ep->dentry.file.create_date,
-					ep->dentry.file.create_time_cs);
-			exfat_get_entry_time(sbi, &dir_entry->mtime,
-					ep->dentry.file.modify_tz,
-					ep->dentry.file.modify_time,
-					ep->dentry.file.modify_date,
-					ep->dentry.file.modify_time_cs);
-			exfat_get_entry_time(sbi, &dir_entry->atime,
-					ep->dentry.file.access_tz,
-					ep->dentry.file.access_time,
-					ep->dentry.file.access_date,
-					0);
 
 			*uni_name.name = 0x0;
 			err = exfat_get_uniname_from_ext_entry(sb, &clu, i,
@@ -166,8 +148,6 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent
 			ep = exfat_get_dentry(sb, &clu, i + 1, &bh);
 			if (!ep)
 				return -EIO;
-			dir_entry->size =
-				le64_to_cpu(ep->dentry.stream.valid_size);
 			dir_entry->entry = dentry;
 			brelse(bh);
 

From 8a3f5711ad74db9881b289a6e34d7f3b700df720 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Thu, 12 Sep 2024 16:57:06 +0800
Subject: [PATCH 1399/1530] exfat: reduce FAT chain traversal

Before this commit, ->dir and ->entry of exfat_inode_info record the
first cluster of the parent directory and the directory entry index
starting from this cluster.

The directory entry set will be gotten during write-back-inode/rmdir/
unlink/rename. If the clusters of the parent directory are not
continuous, the FAT chain will be traversed from the first cluster of
the parent directory to find the cluster where ->entry is located.

After this commit, ->dir records the cluster where the first directory
entry in the directory entry set is located, and ->entry records the
directory entry index in the cluster, so that there is almost no need
to access the FAT when getting the directory entry set.

Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com>
Reviewed-by: Daniel Palmer <daniel.palmer@sony.com>
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/dir.c      |  5 +++--
 fs/exfat/exfat_fs.h |  4 ++++
 fs/exfat/namei.c    | 32 +++++++++++++++++++++++++-------
 3 files changed, 32 insertions(+), 9 deletions(-)

diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c
index 24149e0ebb82d..fe0a9b8a0cd07 100644
--- a/fs/exfat/dir.c
+++ b/fs/exfat/dir.c
@@ -148,7 +148,8 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent
 			ep = exfat_get_dentry(sb, &clu, i + 1, &bh);
 			if (!ep)
 				return -EIO;
-			dir_entry->entry = dentry;
+			dir_entry->entry = i;
+			dir_entry->dir = clu;
 			brelse(bh);
 
 			ei->hint_bmap.off = EXFAT_DEN_TO_CLU(dentry, sbi);
@@ -256,7 +257,7 @@ static int exfat_iterate(struct file *file, struct dir_context *ctx)
 	if (!nb->lfn[0])
 		goto end_of_dir;
 
-	i_pos = ((loff_t)ei->start_clu << 32) |	(de.entry & 0xffffffff);
+	i_pos = ((loff_t)de.dir.dir << 32) | (de.entry & 0xffffffff);
 	tmp = exfat_iget(sb, i_pos);
 	if (tmp) {
 		inum = tmp->i_ino;
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 28cc18d29236b..78be6964a8a08 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -204,7 +204,9 @@ struct exfat_entry_set_cache {
 #define IS_DYNAMIC_ES(es)	((es)->__bh != (es)->bh)
 
 struct exfat_dir_entry {
+	/* the cluster where file dentry is located */
 	struct exfat_chain dir;
+	/* the index of file dentry in ->dir */
 	int entry;
 	unsigned int type;
 	unsigned int start_clu;
@@ -290,7 +292,9 @@ struct exfat_sb_info {
  * EXFAT file system inode in-memory data
  */
 struct exfat_inode_info {
+	/* the cluster where file dentry is located */
 	struct exfat_chain dir;
+	/* the index of file dentry in ->dir */
 	int entry;
 	unsigned int type;
 	unsigned short attr;
diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 8138ed61c1b28..97d2774760fe3 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -288,8 +288,22 @@ static int exfat_check_max_dentries(struct inode *inode)
 	return 0;
 }
 
-/* find empty directory entry.
- * if there isn't any empty slot, expand cluster chain.
+/*
+ * Find an empty directory entry set.
+ *
+ * If there isn't any empty slot, expand cluster chain.
+ *
+ * in:
+ *   inode: inode of the parent directory
+ *   num_entries: specifies how many dentries in the empty directory entry set
+ *
+ * out:
+ *   p_dir: the cluster where the empty directory entry set is located
+ *   es: The found empty directory entry set
+ *
+ * return:
+ *   the directory entry index in p_dir is returned on succeeds
+ *   -error code is returned on failure
  */
 static int exfat_find_empty_entry(struct inode *inode,
 		struct exfat_chain *p_dir, int num_entries,
@@ -381,7 +395,10 @@ static int exfat_find_empty_entry(struct inode *inode,
 		inode->i_blocks += sbi->cluster_size >> 9;
 	}
 
-	return dentry;
+	p_dir->dir = exfat_sector_to_cluster(sbi, es->bh[0]->b_blocknr);
+	p_dir->size -= dentry / sbi->dentries_per_clu;
+
+	return dentry & (sbi->dentries_per_clu - 1);
 }
 
 /*
@@ -613,15 +630,16 @@ static int exfat_find(struct inode *dir, struct qstr *qname,
 	if (dentry < 0)
 		return dentry; /* -error value */
 
-	info->dir = cdir;
-	info->entry = dentry;
-	info->num_subdirs = 0;
-
 	/* adjust cdir to the optimized value */
 	cdir.dir = hint_opt.clu;
 	if (cdir.flags & ALLOC_NO_FAT_CHAIN)
 		cdir.size -= dentry / sbi->dentries_per_clu;
 	dentry = hint_opt.eidx;
+
+	info->dir = cdir;
+	info->entry = dentry;
+	info->num_subdirs = 0;
+
 	if (exfat_get_dentry_set(&es, sb, &cdir, dentry, ES_2_ENTRIES))
 		return -EIO;
 	ep = exfat_get_dentry_cached(&es, ES_IDX_FILE);

From 7082503622986537f57bdb5ef23e69e70cfad881 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Thu, 14 Nov 2024 12:02:13 -0800
Subject: [PATCH 1400/1530] thermal: int3400: Fix reading of current_uuid for
 active policy

When the current_uuid attribute is set to the active policy UUID,
reading back the same attribute is returning "INVALID" instead of
the active policy UUID on some platforms before Ice Lake.

In platforms before Ice Lake, firmware provides a list of supported
thermal policies. In this case, user space can select any of the
supported thermal policies via a write to attribute "current_uuid".

In commit c7ff29763989 ("thermal: int340x: Update OS policy capability
handshake")', the OS policy handshake was updated to support Ice Lake
and later platforms and it treated priv->current_uuid_index=0 as
invalid. However, priv->current_uuid_index=0 is for the active policy,
only priv->current_uuid_index=-1 is invalid.

Fix this issue by updating the priv->current_uuid_index check.

Fixes: c7ff29763989 ("thermal: int340x: Update OS policy capability handshake")
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: 5.18+ <stable@vger.kernel.org> # 5.18+
Link: https://patch.msgid.link/20241114200213.422303-1-srinivas.pandruvada@linux.intel.com
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/intel/int340x_thermal/int3400_thermal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
index b2fc02c3a767a..c829be13d85d3 100644
--- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
@@ -137,7 +137,7 @@ static ssize_t current_uuid_show(struct device *dev,
 	struct int3400_thermal_priv *priv = dev_get_drvdata(dev);
 	int i, length = 0;
 
-	if (priv->current_uuid_index > 0)
+	if (priv->current_uuid_index >= 0)
 		return sprintf(buf, "%s\n",
 			       int3400_thermal_uuids[priv->current_uuid_index]);
 

From 13f3cbfbb8c9f3825a1e4e4371fe040fb35e41d5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Thu, 21 Nov 2024 17:29:32 +0100
Subject: [PATCH 1401/1530] thermal: int3400: Remove unneeded data_vault
 attribute_group
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The group only contains a single entry and the conditionals around its
lifecycle make clear that this won't change.

Remove the unnecessary group.

This saves some memory and it's easier to read.

The removal of a non-const bin_attribute[] instance is also a
preparation for the constification of struct bin_attributes.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://patch.msgid.link/20241121-sysfs-const-bin_attr-int340x_thermal-v1-1-2436facf9dae@weissschuh.net
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 .../intel/int340x_thermal/int3400_thermal.c      | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
index c829be13d85d3..8660ef2175be8 100644
--- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
@@ -75,11 +75,6 @@ struct odvp_attr {
 
 static BIN_ATTR_SIMPLE_RO(data_vault);
 
-static struct bin_attribute *data_attributes[] = {
-	&bin_attr_data_vault,
-	NULL,
-};
-
 static ssize_t imok_store(struct device *dev, struct device_attribute *attr,
 			  const char *buf, size_t count)
 {
@@ -108,10 +103,6 @@ static const struct attribute_group imok_attribute_group = {
 	.attrs = imok_attr,
 };
 
-static const struct attribute_group data_attribute_group = {
-	.bin_attrs = data_attributes,
-};
-
 static ssize_t available_uuids_show(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
@@ -624,8 +615,7 @@ static int int3400_thermal_probe(struct platform_device *pdev)
 	}
 
 	if (!ZERO_OR_NULL_PTR(priv->data_vault)) {
-		result = sysfs_create_group(&pdev->dev.kobj,
-					    &data_attribute_group);
+		result = device_create_bin_file(&pdev->dev, &bin_attr_data_vault);
 		if (result)
 			goto free_uuid;
 	}
@@ -648,7 +638,7 @@ static int int3400_thermal_probe(struct platform_device *pdev)
 free_sysfs:
 	cleanup_odvp(priv);
 	if (!ZERO_OR_NULL_PTR(priv->data_vault)) {
-		sysfs_remove_group(&pdev->dev.kobj, &data_attribute_group);
+		device_remove_bin_file(&pdev->dev, &bin_attr_data_vault);
 		kfree(priv->data_vault);
 	}
 free_uuid:
@@ -683,7 +673,7 @@ static void int3400_thermal_remove(struct platform_device *pdev)
 		acpi_thermal_rel_misc_device_remove(priv->adev->handle);
 
 	if (!ZERO_OR_NULL_PTR(priv->data_vault))
-		sysfs_remove_group(&pdev->dev.kobj, &data_attribute_group);
+		device_remove_bin_file(&pdev->dev, &bin_attr_data_vault);
 	sysfs_remove_group(&pdev->dev.kobj, &uuid_attribute_group);
 	sysfs_remove_group(&pdev->dev.kobj, &imok_attribute_group);
 	thermal_zone_device_unregister(priv->thermal);

From b6512519496e29270bca6b2df9baa3cc2d9d5356 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 22 Nov 2024 13:29:24 +0100
Subject: [PATCH 1402/1530] fs: require inode_owner_or_capable for
 F_SET_RW_HINT

F_SET_RW_HINT controls data placement in the file system and / or
device and should not be available to everyone who can read a given file.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20241122122931.90408-2-hch@lst.de
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fcntl.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/fcntl.c b/fs/fcntl.c
index ac77dd912412e..49884fa3c81d2 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -374,6 +374,9 @@ static long fcntl_set_rw_hint(struct file *file, unsigned int cmd,
 	u64 __user *argp = (u64 __user *)arg;
 	u64 hint;
 
+	if (!inode_owner_or_capable(file_mnt_idmap(file), inode))
+		return -EPERM;
+
 	if (copy_from_user(&hint, argp, sizeof(hint)))
 		return -EFAULT;
 	if (!rw_hint_valid(hint))

From fe4bf8d0b6716a423b16495d55b35d3fe515905d Mon Sep 17 00:00:00 2001
From: Avihai Horon <avihaih@nvidia.com>
Date: Sun, 24 Nov 2024 16:27:39 +0200
Subject: [PATCH 1403/1530] vfio/pci: Properly hide first-in-list PCIe extended
 capability

There are cases where a PCIe extended capability should be hidden from
the user. For example, an unknown capability (i.e., capability with ID
greater than PCI_EXT_CAP_ID_MAX) or a capability that is intentionally
chosen to be hidden from the user.

Hiding a capability is done by virtualizing and modifying the 'Next
Capability Offset' field of the previous capability so it points to the
capability after the one that should be hidden.

The special case where the first capability in the list should be hidden
is handled differently because there is no previous capability that can
be modified. In this case, the capability ID and version are zeroed
while leaving the next pointer intact. This hides the capability and
leaves an anchor for the rest of the capability list.

However, today, hiding the first capability in the list is not done
properly if the capability is unknown, as struct
vfio_pci_core_device->pci_config_map is set to the capability ID during
initialization but the capability ID is not properly checked later when
used in vfio_config_do_rw(). This leads to the following warning [1] and
to an out-of-bounds access to ecap_perms array.

Fix it by checking cap_id in vfio_config_do_rw(), and if it is greater
than PCI_EXT_CAP_ID_MAX, use an alternative struct perm_bits for direct
read only access instead of the ecap_perms array.

Note that this is safe since the above is the only case where cap_id can
exceed PCI_EXT_CAP_ID_MAX (except for the special capabilities, which
are already checked before).

[1]

WARNING: CPU: 118 PID: 5329 at drivers/vfio/pci/vfio_pci_config.c:1900 vfio_pci_config_rw+0x395/0x430 [vfio_pci_core]
CPU: 118 UID: 0 PID: 5329 Comm: simx-qemu-syste Not tainted 6.12.0+ #1
(snip)
Call Trace:
 <TASK>
 ? show_regs+0x69/0x80
 ? __warn+0x8d/0x140
 ? vfio_pci_config_rw+0x395/0x430 [vfio_pci_core]
 ? report_bug+0x18f/0x1a0
 ? handle_bug+0x63/0xa0
 ? exc_invalid_op+0x19/0x70
 ? asm_exc_invalid_op+0x1b/0x20
 ? vfio_pci_config_rw+0x395/0x430 [vfio_pci_core]
 ? vfio_pci_config_rw+0x244/0x430 [vfio_pci_core]
 vfio_pci_rw+0x101/0x1b0 [vfio_pci_core]
 vfio_pci_core_read+0x1d/0x30 [vfio_pci_core]
 vfio_device_fops_read+0x27/0x40 [vfio]
 vfs_read+0xbd/0x340
 ? vfio_device_fops_unl_ioctl+0xbb/0x740 [vfio]
 ? __rseq_handle_notify_resume+0xa4/0x4b0
 __x64_sys_pread64+0x96/0xc0
 x64_sys_call+0x1c3d/0x20d0
 do_syscall_64+0x4d/0x120
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

Fixes: 89e1f7d4c66d ("vfio: Add PCI device driver")
Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Tested-by: Yi Liu <yi.l.liu@intel.com>
Link: https://lore.kernel.org/r/20241124142739.21698-1-avihaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/vfio_pci_config.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 97422aafaa7b5..ea2745c1ac5e6 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -313,6 +313,10 @@ static int vfio_virt_config_read(struct vfio_pci_core_device *vdev, int pos,
 	return count;
 }
 
+static struct perm_bits direct_ro_perms = {
+	.readfn = vfio_direct_config_read,
+};
+
 /* Default capability regions to read-only, no-virtualization */
 static struct perm_bits cap_perms[PCI_CAP_ID_MAX + 1] = {
 	[0 ... PCI_CAP_ID_MAX] = { .readfn = vfio_direct_config_read }
@@ -1897,9 +1901,17 @@ static ssize_t vfio_config_do_rw(struct vfio_pci_core_device *vdev, char __user
 		cap_start = *ppos;
 	} else {
 		if (*ppos >= PCI_CFG_SPACE_SIZE) {
-			WARN_ON(cap_id > PCI_EXT_CAP_ID_MAX);
+			/*
+			 * We can get a cap_id that exceeds PCI_EXT_CAP_ID_MAX
+			 * if we're hiding an unknown capability at the start
+			 * of the extended capability list.  Use default, ro
+			 * access, which will virtualize the id and next values.
+			 */
+			if (cap_id > PCI_EXT_CAP_ID_MAX)
+				perm = &direct_ro_perms;
+			else
+				perm = &ecap_perms[cap_id];
 
-			perm = &ecap_perms[cap_id];
 			cap_start = vfio_find_cap_start(vdev, *ppos);
 		} else {
 			WARN_ON(cap_id > PCI_CAP_ID_MAX);

From 919464deeca24e5bf13b6c8efd0b1d25cc43866f Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Mon, 25 Nov 2024 09:21:21 -0800
Subject: [PATCH 1404/1530] Revert "HID: bpf: allow write access to quirks
 field in struct hid_device"

This reverts commit 6fd47effe92b, and the related self-test update
commit e14e0eaeb040 ("selftests/hid: add test for assigning a given
device to hid-generic").

It results in things like the scroll wheel on Logitech mice not working
after a reboot due to the kernel being confused about the state of the
high-resolution mode.

Quoting Benjamin Tissoires:
 "The idea of 6fd47effe92b was to be able to call hid_bpf_rdesc_fixup()
  once per reprobe of the device.

  However, because the bpf filter can now change the quirk value, the
  call had to be moved before the driver gets bound (which was
  previously ensuring the unicity of the call).

  The net effect is that now, in the case hid-generic gets loaded first
  and then the specific driver gets loaded once the disk is available,
  the value of ->quirks is not reset, but kept to the value that was set
  by hid-generic (HID_QUIRK_INPUT_PER_APP).

  Once hid-logitech-hidpp kicks in, that quirk is now set, which creates
  two inputs for the single mouse: one keyboard for fancy shortcuts, and
  one mouse node.

  However, hid-logitech-hidpp expects only one input node to be attached
  (it stores it into hidpp->input), and when a wheel event is received,
  because there is some processing with high-resolution wheel events,
  the wheel event is injected into hidpp->input.

  And of course, when HID_QUIRK_INPUT_PER_APP is set, hidpp->input gets
  the keyboard node, which doesn't have wheel event type, and the events
  are ignored"

Reported-and-bisected-by: Mike Galbraith <efault@gmx.de>
Link: https://lore.kernel.org/all/CAHk-=wiUkQM3uheit2cNM0Y0OOY5qqspJgC8LkmOkJ2p2LDxcw@mail.gmail.com/
Acked-by: Benjamin Tissoires <bentiss@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/hid/bpf/hid_bpf_struct_ops.c          |  1 -
 drivers/hid/hid-core.c                        | 11 +--
 tools/testing/selftests/hid/hid_bpf.c         | 80 +------------------
 tools/testing/selftests/hid/progs/hid.c       | 12 ---
 .../selftests/hid/progs/hid_bpf_helpers.h     |  6 +-
 5 files changed, 4 insertions(+), 106 deletions(-)

diff --git a/drivers/hid/bpf/hid_bpf_struct_ops.c b/drivers/hid/bpf/hid_bpf_struct_ops.c
index 0e611a9d79d75..702c22fae136a 100644
--- a/drivers/hid/bpf/hid_bpf_struct_ops.c
+++ b/drivers/hid/bpf/hid_bpf_struct_ops.c
@@ -79,7 +79,6 @@ static int hid_bpf_ops_btf_struct_access(struct bpf_verifier_log *log,
 		WRITE_RANGE(hid_device, name, true),
 		WRITE_RANGE(hid_device, uniq, true),
 		WRITE_RANGE(hid_device, phys, true),
-		WRITE_RANGE(hid_device, quirks, false),
 	};
 #undef WRITE_RANGE
 	const struct btf_type *state = NULL;
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 81d6c734c8bcb..98bef39642a9e 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -2692,12 +2692,6 @@ static int __hid_device_probe(struct hid_device *hdev, struct hid_driver *hdrv)
 	int ret;
 
 	if (!hdev->bpf_rsize) {
-		unsigned int quirks;
-
-		/* reset the quirks that has been previously set */
-		quirks = hid_lookup_quirk(hdev);
-		hdev->quirks = quirks;
-
 		/* in case a bpf program gets detached, we need to free the old one */
 		hid_free_bpf_rdesc(hdev);
 
@@ -2707,9 +2701,6 @@ static int __hid_device_probe(struct hid_device *hdev, struct hid_driver *hdrv)
 		/* call_hid_bpf_rdesc_fixup will always return a valid pointer */
 		hdev->bpf_rdesc = call_hid_bpf_rdesc_fixup(hdev, hdev->dev_rdesc,
 							   &hdev->bpf_rsize);
-		if (quirks ^ hdev->quirks)
-			hid_info(hdev, "HID-BPF toggled quirks on the device: %04x",
-				 quirks ^ hdev->quirks);
 	}
 
 	if (!hid_check_device_match(hdev, hdrv, &id))
@@ -2719,6 +2710,8 @@ static int __hid_device_probe(struct hid_device *hdev, struct hid_driver *hdrv)
 	if (!hdev->devres_group_id)
 		return -ENOMEM;
 
+	/* reset the quirks that has been previously set */
+	hdev->quirks = hid_lookup_quirk(hdev);
 	hdev->driver = hdrv;
 
 	if (hdrv->probe) {
diff --git a/tools/testing/selftests/hid/hid_bpf.c b/tools/testing/selftests/hid/hid_bpf.c
index ca58bfa3ca656..1e979fb3542ba 100644
--- a/tools/testing/selftests/hid/hid_bpf.c
+++ b/tools/testing/selftests/hid/hid_bpf.c
@@ -54,41 +54,11 @@ FIXTURE_TEARDOWN(hid_bpf) {
 	hid_bpf_teardown(_metadata, self, variant); \
 } while (0)
 
-struct specific_device {
-	const char test_name[64];
-	__u16 bus;
-	__u32 vid;
-	__u32 pid;
-};
-
 FIXTURE_SETUP(hid_bpf)
 {
-	const struct specific_device *match = NULL;
 	int err;
 
-	const struct specific_device devices[] = {
-	{
-		.test_name = "test_hid_driver_probe",
-		.bus = BUS_BLUETOOTH,
-		.vid = 0x05ac,  /* USB_VENDOR_ID_APPLE */
-		.pid = 0x022c,  /* USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI */
-	}, {
-		.test_name = "*",
-		.bus = BUS_USB,
-		.vid = 0x0001,
-		.pid = 0x0a36,
-	}};
-
-	for (int i = 0; i < ARRAY_SIZE(devices); i++) {
-		match = &devices[i];
-		if (!strncmp(_metadata->name, devices[i].test_name, sizeof(devices[i].test_name)))
-			break;
-	}
-
-	ASSERT_OK_PTR(match);
-
-	err = setup_uhid(_metadata, &self->hid, match->bus, match->vid, match->pid,
-			 rdesc, sizeof(rdesc));
+	err = setup_uhid(_metadata, &self->hid, BUS_USB, 0x0001, 0x0a36, rdesc, sizeof(rdesc));
 	ASSERT_OK(err);
 }
 
@@ -885,54 +855,6 @@ TEST_F(hid_bpf, test_hid_attach_flags)
 	ASSERT_EQ(buf[3], 3);
 }
 
-static bool is_using_driver(struct __test_metadata *_metadata, struct uhid_device *hid,
-			    const char *driver)
-{
-	char driver_line[512];
-	char uevent[1024];
-	char temp[512];
-	int fd, nread;
-	bool found = false;
-
-	sprintf(uevent, "/sys/bus/hid/devices/%04X:%04X:%04X.%04X/uevent",
-		hid->bus, hid->vid, hid->pid, hid->hid_id);
-
-	fd = open(uevent, O_RDONLY | O_NONBLOCK);
-	if (fd < 0) {
-		TH_LOG("couldn't open '%s': %d, %d", uevent, fd, errno);
-		return false;
-	}
-
-	sprintf(driver_line, "DRIVER=%s", driver);
-
-	nread = read(fd, temp, ARRAY_SIZE(temp));
-	if (nread > 0 && (strstr(temp, driver_line)) != NULL)
-		found = true;
-
-	close(fd);
-
-	return found;
-}
-
-/*
- * Attach hid_driver_probe to the given uhid device,
- * check that the device is now using hid-generic.
- */
-TEST_F(hid_bpf, test_hid_driver_probe)
-{
-	const struct test_program progs[] = {
-		{
-			.name = "hid_test_driver_probe",
-		},
-	};
-
-	ASSERT_TRUE(is_using_driver(_metadata, &self->hid, "apple"));
-
-	LOAD_PROGRAMS(progs);
-
-	ASSERT_TRUE(is_using_driver(_metadata, &self->hid, "hid-generic"));
-}
-
 /*
  * Attach hid_rdesc_fixup to the given uhid device,
  * retrieve and open the matching hidraw node,
diff --git a/tools/testing/selftests/hid/progs/hid.c b/tools/testing/selftests/hid/progs/hid.c
index 9b22e9a0e658f..5ecc845ef7921 100644
--- a/tools/testing/selftests/hid/progs/hid.c
+++ b/tools/testing/selftests/hid/progs/hid.c
@@ -598,15 +598,3 @@ SEC(".struct_ops.link")
 struct hid_bpf_ops test_infinite_loop_input_report = {
 	.hid_device_event = (void *)hid_test_infinite_loop_input_report,
 };
-
-SEC("?struct_ops.s/hid_rdesc_fixup")
-int BPF_PROG(hid_test_driver_probe, struct hid_bpf_ctx *hid_ctx)
-{
-	hid_ctx->hid->quirks |= HID_QUIRK_IGNORE_SPECIAL_DRIVER;
-	return 0;
-}
-
-SEC(".struct_ops.link")
-struct hid_bpf_ops test_driver_probe = {
-	.hid_rdesc_fixup = (void *)hid_test_driver_probe,
-};
diff --git a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
index 1a645684a1179..e5db897586bbf 100644
--- a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
+++ b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
@@ -84,14 +84,10 @@ struct hid_bpf_ops {
 	struct hid_device *hdev;
 };
 
-#define BIT(n) (1U << n)
-
 #ifndef BPF_F_BEFORE
-#define BPF_F_BEFORE BIT(3)
+#define BPF_F_BEFORE (1U << 3)
 #endif
 
-#define HID_QUIRK_IGNORE_SPECIAL_DRIVER		BIT(22)
-
 /* following are kfuncs exported by HID for HID-BPF */
 extern __u8 *hid_bpf_get_data(struct hid_bpf_ctx *ctx,
 			      unsigned int offset,

From 64f093c4d99d797b68b407a9d8767aadc3e3ea7a Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 17 Oct 2024 10:58:36 +0900
Subject: [PATCH 1405/1530] PCI: rockchip-ep: Fix address translation unit
 programming
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Rockchip PCIe endpoint controller handles PCIe transfers addresses
by masking the lower bits of the programmed PCI address and using the
same number of lower bits masked from the CPU address space used for the
mapping. For a PCI mapping of <size> bytes starting from <pci_addr>,
the number of bits masked is the number of address bits changing in the
address range [pci_addr..pci_addr + size - 1].

However, rockchip_pcie_prog_ep_ob_atu() calculates num_pass_bits only
using the size of the mapping, resulting in an incorrect number of mask
bits depending on the value of the PCI address to map.

Fix this by introducing the helper function
rockchip_pcie_ep_ob_atu_num_bits() to correctly calculate the number of
mask bits to use to program the address translation unit. The number of
mask bits is calculated depending on both the PCI address and size of
the mapping, and clamped between 8 and 20 using the macros
ROCKCHIP_PCIE_AT_MIN_NUM_BITS and ROCKCHIP_PCIE_AT_MAX_NUM_BITS. As
defined in the Rockchip RK3399 TRM V1.3 Part2, Sections 17.5.5.1.1 and
17.6.8.2.1, this clamping is necessary because:

  1) The lower 8 bits of the PCI address to be mapped by the outbound
     region are ignored. So a minimum of 8 address bits are needed and
     imply that the PCI address must be aligned to 256.

  2) The outbound memory regions are 1MB in size. So while we can specify
     up to 63-bits for the PCI address (num_bits filed uses bits 0 to 5 of
     the outbound address region 0 register), we must limit the number of
     valid address bits to 20 to match the memory window maximum size (1
     << 20 = 1MB).

Fixes: cf590b078391 ("PCI: rockchip: Add EP driver for Rockchip PCIe controller")
Link: https://lore.kernel.org/r/20241017015849.190271-2-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org
---
 drivers/pci/controller/pcie-rockchip-ep.c | 16 +++++++++++++---
 drivers/pci/controller/pcie-rockchip.h    |  4 ++++
 2 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 1362745336568..a6805b005798c 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -63,15 +63,25 @@ static void rockchip_pcie_clear_ep_ob_atu(struct rockchip_pcie *rockchip,
 			    ROCKCHIP_PCIE_AT_OB_REGION_DESC1(region));
 }
 
+static int rockchip_pcie_ep_ob_atu_num_bits(struct rockchip_pcie *rockchip,
+					    u64 pci_addr, size_t size)
+{
+	int num_pass_bits = fls64(pci_addr ^ (pci_addr + size - 1));
+
+	return clamp(num_pass_bits,
+		     ROCKCHIP_PCIE_AT_MIN_NUM_BITS,
+		     ROCKCHIP_PCIE_AT_MAX_NUM_BITS);
+}
+
 static void rockchip_pcie_prog_ep_ob_atu(struct rockchip_pcie *rockchip, u8 fn,
 					 u32 r, u64 cpu_addr, u64 pci_addr,
 					 size_t size)
 {
-	int num_pass_bits = fls64(size - 1);
+	int num_pass_bits;
 	u32 addr0, addr1, desc0;
 
-	if (num_pass_bits < 8)
-		num_pass_bits = 8;
+	num_pass_bits = rockchip_pcie_ep_ob_atu_num_bits(rockchip,
+							 pci_addr, size);
 
 	addr0 = ((num_pass_bits - 1) & PCIE_CORE_OB_REGION_ADDR0_NUM_BITS) |
 		(lower_32_bits(pci_addr) & PCIE_CORE_OB_REGION_ADDR0_LO_ADDR);
diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h
index 6111de35f84ca..15ee949f2485e 100644
--- a/drivers/pci/controller/pcie-rockchip.h
+++ b/drivers/pci/controller/pcie-rockchip.h
@@ -245,6 +245,10 @@
 	(PCIE_EP_PF_CONFIG_REGS_BASE + (((fn) << 12) & GENMASK(19, 12)))
 #define ROCKCHIP_PCIE_EP_VIRT_FUNC_BASE(fn) \
 	(PCIE_EP_PF_CONFIG_REGS_BASE + 0x10000 + (((fn) << 12) & GENMASK(19, 12)))
+
+#define ROCKCHIP_PCIE_AT_MIN_NUM_BITS  8
+#define ROCKCHIP_PCIE_AT_MAX_NUM_BITS  20
+
 #define ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar) \
 	(PCIE_CORE_AXI_CONF_BASE + 0x0828 + (fn) * 0x0040 + (bar) * 0x0008)
 #define ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar) \

From 739e25f51aedaebf20496fbc99c6ef43fc6d6ca1 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 17 Oct 2024 10:58:37 +0900
Subject: [PATCH 1406/1530] PCI: rockchip-ep: Use a macro to define EP
 controller .align feature
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce the macro ROCKCHIP_PCIE_AT_SIZE_ALIGN to initialize the .align
field of the controller epc_features structure to 256. This is defined
as a shift using the macro ROCKCHIP_PCIE_AT_MIN_NUM_BITS (to avoid
using the "magic" value 8 directly).

Link: https://lore.kernel.org/r/20241017015849.190271-3-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/pcie-rockchip-ep.c | 2 +-
 drivers/pci/controller/pcie-rockchip.h    | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index a6805b005798c..65014681d8592 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -449,7 +449,7 @@ static const struct pci_epc_features rockchip_pcie_epc_features = {
 	.linkup_notifier = false,
 	.msi_capable = true,
 	.msix_capable = false,
-	.align = 256,
+	.align = ROCKCHIP_PCIE_AT_SIZE_ALIGN,
 };
 
 static const struct pci_epc_features*
diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h
index 15ee949f2485e..02368ce9bd548 100644
--- a/drivers/pci/controller/pcie-rockchip.h
+++ b/drivers/pci/controller/pcie-rockchip.h
@@ -248,6 +248,7 @@
 
 #define ROCKCHIP_PCIE_AT_MIN_NUM_BITS  8
 #define ROCKCHIP_PCIE_AT_MAX_NUM_BITS  20
+#define ROCKCHIP_PCIE_AT_SIZE_ALIGN    (1UL << ROCKCHIP_PCIE_AT_MIN_NUM_BITS)
 
 #define ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar) \
 	(PCIE_CORE_AXI_CONF_BASE + 0x0828 + (fn) * 0x0040 + (bar) * 0x0008)

From 57ed93fe799b3564388fd61279fc274ae2716508 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Date: Thu, 17 Oct 2024 10:58:38 +0900
Subject: [PATCH 1407/1530] PCI: rockchip-ep: Improve
 rockchip_pcie_ep_unmap_addr()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is no need to loop over all regions to find the memory window used
to map an address. We can use rockchip_ob_region() to determine the
region index, together with a check that the address passed as argument
is the address used to create the mapping. Furthermore, the
ob_region_map bitmap should also be checked to ensure that we are not
attempting to unmap an address that is not mapped.

Link: https://lore.kernel.org/r/20241017015849.190271-4-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/controller/pcie-rockchip-ep.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 65014681d8592..b4db5459727fa 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -259,13 +259,9 @@ static void rockchip_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn,
 {
 	struct rockchip_pcie_ep *ep = epc_get_drvdata(epc);
 	struct rockchip_pcie *rockchip = &ep->rockchip;
-	u32 r;
-
-	for (r = 0; r < ep->max_regions; r++)
-		if (ep->ob_addr[r] == addr)
-			break;
+	u32 r = rockchip_ob_region(addr);
 
-	if (r == ep->max_regions)
+	if (addr != ep->ob_addr[r] || !test_bit(r, &ep->ob_region_map))
 		return;
 
 	rockchip_pcie_clear_ep_ob_atu(rockchip, r);

From d8dbd21cfafd653b02ec187e59e0bcfaebd9a884 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 17 Oct 2024 10:58:39 +0900
Subject: [PATCH 1408/1530] PCI: rockchip-ep: Improve
 rockchip_pcie_ep_map_addr()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a check to verify that the outbound region to be used for mapping an
address is not already in use.

Link: https://lore.kernel.org/r/20241017015849.190271-5-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/pcie-rockchip-ep.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index b4db5459727fa..24ee1df17a49d 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -246,6 +246,9 @@ static int rockchip_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn,
 	struct rockchip_pcie *pcie = &ep->rockchip;
 	u32 r = rockchip_ob_region(addr);
 
+	if (test_bit(r, &ep->ob_region_map))
+		return -EBUSY;
+
 	rockchip_pcie_prog_ep_ob_atu(pcie, fn, r, addr, pci_addr, size);
 
 	set_bit(r, &ep->ob_region_map);

From b21255326db2d736089b3df26c3cd4e4a131d75f Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 17 Oct 2024 10:58:40 +0900
Subject: [PATCH 1409/1530] PCI: rockchip-ep: Implement the
 pci_epc_ops::align_addr() operation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Rockchip PCIe endpoint controller handles PCIe transfers addresses
by masking the lower bits of the programmed PCI address and using the
same number of lower bits from the CPU address space used for the
mapping. For a PCI mapping of size bytes starting from pci_addr, the
number of bits masked is the number of address bits changing in the
address range [pci_addr..pci_addr + size - 1], up to 20 bits, that is,
up to 1MB mappings.

This means that when preparing a PCI address mapping, an endpoint
function driver must use an offset into the allocated controller
memory region that is equal to the mask of the starting PCI address
over rockchip_pcie_ep_ob_atu_num_bits() bits. This offset also
determines the maximum size of the mapping given the starting PCI
address and the fixed 1MB controller memory window size.

Implement the ->align_addr() endpoint controller operation to allow the
mapping alignment to be transparently handled by endpoint function
drivers through the function pci_epc_mem_map().

Link: https://lore.kernel.org/r/20241017015849.190271-6-dlemoal@kernel.org
Co-developed-by: Rick Wertenbroek <rick.wertenbroek@gmail.com>
Signed-off-by: Rick Wertenbroek <rick.wertenbroek@gmail.com>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
[kwilczynski: change local variable name for address offset]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/controller/pcie-rockchip-ep.c | 23 +++++++++++++++++++++++
 drivers/pci/controller/pcie-rockchip.h    |  5 +++++
 2 files changed, 28 insertions(+)

diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 24ee1df17a49d..5a4279591f790 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -238,6 +238,28 @@ static inline u32 rockchip_ob_region(phys_addr_t addr)
 	return (addr >> ilog2(SZ_1M)) & 0x1f;
 }
 
+static u64 rockchip_pcie_ep_align_addr(struct pci_epc *epc, u64 pci_addr,
+				       size_t *pci_size, size_t *addr_offset)
+{
+	struct rockchip_pcie_ep *ep = epc_get_drvdata(epc);
+	size_t size = *pci_size;
+	u64 offset, mask;
+	int num_bits;
+
+	num_bits = rockchip_pcie_ep_ob_atu_num_bits(&ep->rockchip,
+						    pci_addr, size);
+	mask = (1ULL << num_bits) - 1;
+
+	offset = pci_addr & mask;
+	if (size + offset > SZ_1M)
+		size = SZ_1M - offset;
+
+	*pci_size = ALIGN(offset + size, ROCKCHIP_PCIE_AT_SIZE_ALIGN);
+	*addr_offset = offset;
+
+	return pci_addr & ~mask;
+}
+
 static int rockchip_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn,
 				     phys_addr_t addr, u64 pci_addr,
 				     size_t size)
@@ -461,6 +483,7 @@ static const struct pci_epc_ops rockchip_pcie_epc_ops = {
 	.write_header	= rockchip_pcie_ep_write_header,
 	.set_bar	= rockchip_pcie_ep_set_bar,
 	.clear_bar	= rockchip_pcie_ep_clear_bar,
+	.align_addr	= rockchip_pcie_ep_align_addr,
 	.map_addr	= rockchip_pcie_ep_map_addr,
 	.unmap_addr	= rockchip_pcie_ep_unmap_addr,
 	.set_msi	= rockchip_pcie_ep_set_msi,
diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h
index 02368ce9bd548..30398156095f9 100644
--- a/drivers/pci/controller/pcie-rockchip.h
+++ b/drivers/pci/controller/pcie-rockchip.h
@@ -241,6 +241,11 @@
 #define   ROCKCHIP_PCIE_EP_MSIX_CAP_CP_MASK		GENMASK(15, 8)
 #define ROCKCHIP_PCIE_EP_DUMMY_IRQ_ADDR				0x1
 #define ROCKCHIP_PCIE_EP_PCI_LEGACY_IRQ_ADDR		0x3
+
+#define ROCKCHIP_PCIE_AT_MIN_NUM_BITS	8
+#define ROCKCHIP_PCIE_AT_MAX_NUM_BITS	20
+#define ROCKCHIP_PCIE_AT_SIZE_ALIGN	(1UL << ROCKCHIP_PCIE_AT_MIN_NUM_BITS)
+
 #define ROCKCHIP_PCIE_EP_FUNC_BASE(fn) \
 	(PCIE_EP_PF_CONFIG_REGS_BASE + (((fn) << 12) & GENMASK(19, 12)))
 #define ROCKCHIP_PCIE_EP_VIRT_FUNC_BASE(fn) \

From 9f737cca6c54edd0af0a29bb0a702837f1fc9645 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 17 Oct 2024 10:58:41 +0900
Subject: [PATCH 1410/1530] PCI: rockchip-ep: Fix MSI IRQ data mapping
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The call to rockchip_pcie_prog_ep_ob_atu() used to map the PCI address
of MSI data to the memory window allocated on probe for IRQs is done
in rockchip_pcie_ep_send_msi_irq() assuming a fixed alignment to a
256B boundary of the PCI address.  This is not correct as the alignment
constraint for the RK3399 PCI mapping depends on the number of bits of
address changing in the mapped region. This leads to an unstable system
which sometimes work and sometimes does not (crashing on paging faults
when memcpy_toio() or memcpy_fromio() are used).

Similar to regular data mapping, the MSI data mapping must thus be
handled according to the information provided by
rockchip_pcie_ep_align_addr(). Modify rockchip_pcie_ep_send_msi_irq()
to use rockchip_pcie_ep_align_addr() to correctly program entry 0 of
the ATU for sending MSI IRQs.

Link: https://lore.kernel.org/r/20241017015849.190271-7-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/controller/pcie-rockchip-ep.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 5a4279591f790..299a8a95aab7d 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -382,9 +382,10 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn,
 {
 	struct rockchip_pcie *rockchip = &ep->rockchip;
 	u32 flags, mme, data, data_mask;
+	size_t irq_pci_size, offset;
+	u64 irq_pci_addr;
 	u8 msi_count;
 	u64 pci_addr;
-	u32 r;
 
 	/* Check MSI enable bit */
 	flags = rockchip_pcie_read(&ep->rockchip,
@@ -420,18 +421,21 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn,
 				       PCI_MSI_ADDRESS_LO);
 
 	/* Set the outbound region if needed. */
-	if (unlikely(ep->irq_pci_addr != (pci_addr & PCIE_ADDR_MASK) ||
+	irq_pci_size = ~PCIE_ADDR_MASK + 1;
+	irq_pci_addr = rockchip_pcie_ep_align_addr(ep->epc,
+						   pci_addr & PCIE_ADDR_MASK,
+						   &irq_pci_size, &offset);
+	if (unlikely(ep->irq_pci_addr != irq_pci_addr ||
 		     ep->irq_pci_fn != fn)) {
-		r = rockchip_ob_region(ep->irq_phys_addr);
-		rockchip_pcie_prog_ep_ob_atu(rockchip, fn, r,
-					     ep->irq_phys_addr,
-					     pci_addr & PCIE_ADDR_MASK,
-					     ~PCIE_ADDR_MASK + 1);
-		ep->irq_pci_addr = (pci_addr & PCIE_ADDR_MASK);
+		rockchip_pcie_prog_ep_ob_atu(rockchip, fn,
+					rockchip_ob_region(ep->irq_phys_addr),
+					ep->irq_phys_addr,
+					irq_pci_addr, irq_pci_size);
+		ep->irq_pci_addr = irq_pci_addr;
 		ep->irq_pci_fn = fn;
 	}
 
-	writew(data, ep->irq_cpu_addr + (pci_addr & ~PCIE_ADDR_MASK));
+	writew(data, ep->irq_cpu_addr + offset + (pci_addr & ~PCIE_ADDR_MASK));
 	return 0;
 }
 

From 2968534e63e5bbe3d3f3c317ba32012393ee6637 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 17 Oct 2024 10:58:42 +0900
Subject: [PATCH 1411/1530] PCI: rockchip-ep: Rename
 rockchip_pcie_parse_ep_dt()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To be consistent with the usual "get_resources" naming of driver
functions that acquire controller resources like clocks, PHY etc,
rename the function rockchip_pcie_parse_ep_dt() to
rockchip_pcie_ep_get_resources().

No functional changes.

Link: https://lore.kernel.org/r/20241017015849.190271-8-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/controller/pcie-rockchip-ep.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 299a8a95aab7d..c7c4afe1ef699 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -497,8 +497,8 @@ static const struct pci_epc_ops rockchip_pcie_epc_ops = {
 	.get_features	= rockchip_pcie_ep_get_features,
 };
 
-static int rockchip_pcie_parse_ep_dt(struct rockchip_pcie *rockchip,
-				     struct rockchip_pcie_ep *ep)
+static int rockchip_pcie_ep_get_resources(struct rockchip_pcie *rockchip,
+					  struct rockchip_pcie_ep *ep)
 {
 	struct device *dev = rockchip->dev;
 	int err;
@@ -560,7 +560,7 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev)
 	ep->epc = epc;
 	epc_set_drvdata(epc, ep);
 
-	err = rockchip_pcie_parse_ep_dt(rockchip, ep);
+	err = rockchip_pcie_ep_get_resources(rockchip, ep);
 	if (err)
 		return err;
 

From 945648019466db06dca189a639af913f2834ee9b Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 17 Oct 2024 10:58:43 +0900
Subject: [PATCH 1412/1530] PCI: rockchip-ep: Refactor rockchip_pcie_ep_probe()
 memory allocations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce the function rockchip_pcie_ep_init_ob_mem() allocate the
outbound memory regions and memory needed for IRQ handling.

These changes tidy up rockchip_pcie_ep_probe().

No functional change.

Link: https://lore.kernel.org/r/20241017015849.190271-9-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/controller/pcie-rockchip-ep.c | 107 ++++++++++++----------
 1 file changed, 61 insertions(+), 46 deletions(-)

diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index c7c4afe1ef699..d497f880eb2c4 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -532,15 +532,66 @@ static const struct of_device_id rockchip_pcie_ep_of_match[] = {
 	{},
 };
 
+static int rockchip_pcie_ep_init_ob_mem(struct rockchip_pcie_ep *ep)
+{
+	struct rockchip_pcie *rockchip = &ep->rockchip;
+	struct device *dev = rockchip->dev;
+	struct pci_epc_mem_window *windows = NULL;
+	int err, i;
+
+	ep->ob_addr = devm_kcalloc(dev, ep->max_regions, sizeof(*ep->ob_addr),
+				   GFP_KERNEL);
+
+	if (!ep->ob_addr)
+		return -ENOMEM;
+
+	windows = devm_kcalloc(dev, ep->max_regions,
+			       sizeof(struct pci_epc_mem_window), GFP_KERNEL);
+	if (!windows)
+		return -ENOMEM;
+
+	for (i = 0; i < ep->max_regions; i++) {
+		windows[i].phys_base = rockchip->mem_res->start + (SZ_1M * i);
+		windows[i].size = SZ_1M;
+		windows[i].page_size = SZ_1M;
+	}
+	err = pci_epc_multi_mem_init(ep->epc, windows, ep->max_regions);
+	devm_kfree(dev, windows);
+
+	if (err < 0) {
+		dev_err(dev, "failed to initialize the memory space\n");
+		return err;
+	}
+
+	ep->irq_cpu_addr = pci_epc_mem_alloc_addr(ep->epc, &ep->irq_phys_addr,
+						  SZ_1M);
+	if (!ep->irq_cpu_addr) {
+		dev_err(dev, "failed to reserve memory space for MSI\n");
+		goto err_epc_mem_exit;
+	}
+
+	ep->irq_pci_addr = ROCKCHIP_PCIE_EP_DUMMY_IRQ_ADDR;
+
+	return 0;
+
+err_epc_mem_exit:
+	pci_epc_mem_exit(ep->epc);
+
+	return err;
+}
+
+static void rockchip_pcie_ep_exit_ob_mem(struct rockchip_pcie_ep *ep)
+{
+	pci_epc_mem_exit(ep->epc);
+}
+
 static int rockchip_pcie_ep_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct rockchip_pcie_ep *ep;
 	struct rockchip_pcie *rockchip;
 	struct pci_epc *epc;
-	size_t max_regions;
-	struct pci_epc_mem_window *windows = NULL;
-	int err, i;
+	int err;
 	u32 cfg_msi, cfg_msix_cp;
 
 	ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL);
@@ -564,10 +615,14 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	err = rockchip_pcie_enable_clocks(rockchip);
+	err = rockchip_pcie_ep_init_ob_mem(ep);
 	if (err)
 		return err;
 
+	err = rockchip_pcie_enable_clocks(rockchip);
+	if (err)
+		goto err_exit_ob_mem;
+
 	err = rockchip_pcie_init_port(rockchip);
 	if (err)
 		goto err_disable_clocks;
@@ -576,47 +631,9 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev)
 	rockchip_pcie_write(rockchip, PCIE_CLIENT_LINK_TRAIN_ENABLE,
 			    PCIE_CLIENT_CONFIG);
 
-	max_regions = ep->max_regions;
-	ep->ob_addr = devm_kcalloc(dev, max_regions, sizeof(*ep->ob_addr),
-				   GFP_KERNEL);
-
-	if (!ep->ob_addr) {
-		err = -ENOMEM;
-		goto err_uninit_port;
-	}
-
 	/* Only enable function 0 by default */
 	rockchip_pcie_write(rockchip, BIT(0), PCIE_CORE_PHY_FUNC_CFG);
 
-	windows = devm_kcalloc(dev, ep->max_regions,
-			       sizeof(struct pci_epc_mem_window), GFP_KERNEL);
-	if (!windows) {
-		err = -ENOMEM;
-		goto err_uninit_port;
-	}
-	for (i = 0; i < ep->max_regions; i++) {
-		windows[i].phys_base = rockchip->mem_res->start + (SZ_1M * i);
-		windows[i].size = SZ_1M;
-		windows[i].page_size = SZ_1M;
-	}
-	err = pci_epc_multi_mem_init(epc, windows, ep->max_regions);
-	devm_kfree(dev, windows);
-
-	if (err < 0) {
-		dev_err(dev, "failed to initialize the memory space\n");
-		goto err_uninit_port;
-	}
-
-	ep->irq_cpu_addr = pci_epc_mem_alloc_addr(epc, &ep->irq_phys_addr,
-						  SZ_1M);
-	if (!ep->irq_cpu_addr) {
-		dev_err(dev, "failed to reserve memory space for MSI\n");
-		err = -ENOMEM;
-		goto err_epc_mem_exit;
-	}
-
-	ep->irq_pci_addr = ROCKCHIP_PCIE_EP_DUMMY_IRQ_ADDR;
-
 	/*
 	 * MSI-X is not supported but the controller still advertises the MSI-X
 	 * capability by default, which can lead to the Root Complex side
@@ -646,10 +663,8 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev)
 	pci_epc_init_notify(epc);
 
 	return 0;
-err_epc_mem_exit:
-	pci_epc_mem_exit(epc);
-err_uninit_port:
-	rockchip_pcie_deinit_phys(rockchip);
+err_exit_ob_mem:
+	rockchip_pcie_ep_exit_ob_mem(ep);
 err_disable_clocks:
 	rockchip_pcie_disable_clocks(rockchip);
 	return err;

From 8efda8aebeed59bab984489407a94008f65f4d1e Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 17 Oct 2024 10:58:44 +0900
Subject: [PATCH 1413/1530] PCI: rockchip-ep: Refactor rockchip_pcie_ep_probe()
 MSI-X hiding
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move the code in rockchip_pcie_ep_probe() to hide the MSI-X capability
to its own function, rockchip_pcie_ep_hide_broken_msix_cap().

No functional changes.

Link: https://lore.kernel.org/r/20241017015849.190271-10-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/pcie-rockchip-ep.c | 54 +++++++++++++----------
 1 file changed, 30 insertions(+), 24 deletions(-)

diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index d497f880eb2c4..a53ff16b16615 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -585,6 +585,34 @@ static void rockchip_pcie_ep_exit_ob_mem(struct rockchip_pcie_ep *ep)
 	pci_epc_mem_exit(ep->epc);
 }
 
+static void rockchip_pcie_ep_hide_broken_msix_cap(struct rockchip_pcie *rockchip)
+{
+	u32 cfg_msi, cfg_msix_cp;
+
+	/*
+	 * MSI-X is not supported but the controller still advertises the MSI-X
+	 * capability by default, which can lead to the Root Complex side
+	 * allocating MSI-X vectors which cannot be used. Avoid this by skipping
+	 * the MSI-X capability entry in the PCIe capabilities linked-list: get
+	 * the next pointer from the MSI-X entry and set that in the MSI
+	 * capability entry (which is the previous entry). This way the MSI-X
+	 * entry is skipped (left out of the linked-list) and not advertised.
+	 */
+	cfg_msi = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_BASE +
+				     ROCKCHIP_PCIE_EP_MSI_CTRL_REG);
+
+	cfg_msi &= ~ROCKCHIP_PCIE_EP_MSI_CP1_MASK;
+
+	cfg_msix_cp = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_BASE +
+					 ROCKCHIP_PCIE_EP_MSIX_CAP_REG) &
+					 ROCKCHIP_PCIE_EP_MSIX_CAP_CP_MASK;
+
+	cfg_msi |= cfg_msix_cp;
+
+	rockchip_pcie_write(rockchip, cfg_msi,
+			    PCIE_EP_CONFIG_BASE + ROCKCHIP_PCIE_EP_MSI_CTRL_REG);
+}
+
 static int rockchip_pcie_ep_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -592,7 +620,6 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev)
 	struct rockchip_pcie *rockchip;
 	struct pci_epc *epc;
 	int err;
-	u32 cfg_msi, cfg_msix_cp;
 
 	ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL);
 	if (!ep)
@@ -627,6 +654,8 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev)
 	if (err)
 		goto err_disable_clocks;
 
+	rockchip_pcie_ep_hide_broken_msix_cap(rockchip);
+
 	/* Establish the link automatically */
 	rockchip_pcie_write(rockchip, PCIE_CLIENT_LINK_TRAIN_ENABLE,
 			    PCIE_CLIENT_CONFIG);
@@ -634,29 +663,6 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev)
 	/* Only enable function 0 by default */
 	rockchip_pcie_write(rockchip, BIT(0), PCIE_CORE_PHY_FUNC_CFG);
 
-	/*
-	 * MSI-X is not supported but the controller still advertises the MSI-X
-	 * capability by default, which can lead to the Root Complex side
-	 * allocating MSI-X vectors which cannot be used. Avoid this by skipping
-	 * the MSI-X capability entry in the PCIe capabilities linked-list: get
-	 * the next pointer from the MSI-X entry and set that in the MSI
-	 * capability entry (which is the previous entry). This way the MSI-X
-	 * entry is skipped (left out of the linked-list) and not advertised.
-	 */
-	cfg_msi = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_BASE +
-				     ROCKCHIP_PCIE_EP_MSI_CTRL_REG);
-
-	cfg_msi &= ~ROCKCHIP_PCIE_EP_MSI_CP1_MASK;
-
-	cfg_msix_cp = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_BASE +
-					 ROCKCHIP_PCIE_EP_MSIX_CAP_REG) &
-					 ROCKCHIP_PCIE_EP_MSIX_CAP_CP_MASK;
-
-	cfg_msi |= cfg_msix_cp;
-
-	rockchip_pcie_write(rockchip, cfg_msi,
-			    PCIE_EP_CONFIG_BASE + ROCKCHIP_PCIE_EP_MSI_CTRL_REG);
-
 	rockchip_pcie_write(rockchip, PCIE_CLIENT_CONF_ENABLE,
 			    PCIE_CLIENT_CONFIG);
 

From 091022f5f94513e5f11aa9e2f1cd9fdb4d00f83c Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 17 Oct 2024 10:58:45 +0900
Subject: [PATCH 1414/1530] PCI: rockchip-ep: Refactor endpoint link training
 enable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The function rockchip_pcie_init_port() enables link training for a
controller configured in EP mode. Enabling link training is again done
in rockchip_pcie_ep_probe() after that function executed
rockchip_pcie_init_port(). Enabling link training only needs to be done
once, and doing so at the probe stage before the controller is actually
started by the user serves no purpose.

Refactor this by removing the link training enablement from both
rockchip_pcie_init_port() and rockchip_pcie_ep_probe() and moving it to
the endpoint start operation defined with rockchip_pcie_ep_start().
Enabling the controller configuration using the PCIE_CLIENT_CONF_ENABLE
bit in the same PCIE_CLIENT_CONFIG register is also moved to
rockchip_pcie_ep_start() and both the controller configuration and link
training enable bits are set with a single call to
rockchip_pcie_write().

Link: https://lore.kernel.org/r/20241017015849.190271-11-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/controller/pcie-rockchip-ep.c | 13 ++++++-------
 drivers/pci/controller/pcie-rockchip.c    |  5 +++--
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index a53ff16b16615..6c4169b7930e6 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -467,6 +467,12 @@ static int rockchip_pcie_ep_start(struct pci_epc *epc)
 
 	rockchip_pcie_write(rockchip, cfg, PCIE_CORE_PHY_FUNC_CFG);
 
+	/* Enable configuration and start link training */
+	rockchip_pcie_write(rockchip,
+			    PCIE_CLIENT_LINK_TRAIN_ENABLE |
+			    PCIE_CLIENT_CONF_ENABLE,
+			    PCIE_CLIENT_CONFIG);
+
 	return 0;
 }
 
@@ -656,16 +662,9 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev)
 
 	rockchip_pcie_ep_hide_broken_msix_cap(rockchip);
 
-	/* Establish the link automatically */
-	rockchip_pcie_write(rockchip, PCIE_CLIENT_LINK_TRAIN_ENABLE,
-			    PCIE_CLIENT_CONFIG);
-
 	/* Only enable function 0 by default */
 	rockchip_pcie_write(rockchip, BIT(0), PCIE_CORE_PHY_FUNC_CFG);
 
-	rockchip_pcie_write(rockchip, PCIE_CLIENT_CONF_ENABLE,
-			    PCIE_CLIENT_CONFIG);
-
 	pci_epc_init_notify(epc);
 
 	return 0;
diff --git a/drivers/pci/controller/pcie-rockchip.c b/drivers/pci/controller/pcie-rockchip.c
index c07d7129f1c7c..154e78819e6e8 100644
--- a/drivers/pci/controller/pcie-rockchip.c
+++ b/drivers/pci/controller/pcie-rockchip.c
@@ -244,11 +244,12 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip)
 		rockchip_pcie_write(rockchip, PCIE_CLIENT_GEN_SEL_1,
 				    PCIE_CLIENT_CONFIG);
 
-	regs = PCIE_CLIENT_LINK_TRAIN_ENABLE | PCIE_CLIENT_ARI_ENABLE |
+	regs = PCIE_CLIENT_ARI_ENABLE |
 	       PCIE_CLIENT_CONF_LANE_NUM(rockchip->lanes);
 
 	if (rockchip->is_rc)
-		regs |= PCIE_CLIENT_CONF_ENABLE | PCIE_CLIENT_MODE_RC;
+		regs |= PCIE_CLIENT_LINK_TRAIN_ENABLE |
+			PCIE_CLIENT_CONF_ENABLE | PCIE_CLIENT_MODE_RC;
 	else
 		regs |= PCIE_CLIENT_CONF_DISABLE | PCIE_CLIENT_MODE_EP;
 

From 00080d0887df8c197c5b89e38215c14980eae544 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 17 Oct 2024 10:58:46 +0900
Subject: [PATCH 1415/1530] PCI: rockship-ep: Implement the
 pci_epc_ops::stop_link() operation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Define the EPC operation ->stop() for the Rockchip endpoint driver with
the function rockchip_pcie_ep_stop(). This function disables link
training and the controller configuration, as the reverse to what
the start operation defined with rockchip_pcie_ep_start() does.

Link: https://lore.kernel.org/r/20241017015849.190271-12-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/pcie-rockchip-ep.c | 13 +++++++++++++
 drivers/pci/controller/pcie-rockchip.h    |  1 +
 2 files changed, 14 insertions(+)

diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 6c4169b7930e6..13755e4ed59de 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -476,6 +476,18 @@ static int rockchip_pcie_ep_start(struct pci_epc *epc)
 	return 0;
 }
 
+static void rockchip_pcie_ep_stop(struct pci_epc *epc)
+{
+	struct rockchip_pcie_ep *ep = epc_get_drvdata(epc);
+	struct rockchip_pcie *rockchip = &ep->rockchip;
+
+	/* Stop link training and disable configuration */
+	rockchip_pcie_write(rockchip,
+			    PCIE_CLIENT_CONF_DISABLE |
+			    PCIE_CLIENT_LINK_TRAIN_DISABLE,
+			    PCIE_CLIENT_CONFIG);
+}
+
 static const struct pci_epc_features rockchip_pcie_epc_features = {
 	.linkup_notifier = false,
 	.msi_capable = true,
@@ -500,6 +512,7 @@ static const struct pci_epc_ops rockchip_pcie_epc_ops = {
 	.get_msi	= rockchip_pcie_ep_get_msi,
 	.raise_irq	= rockchip_pcie_ep_raise_irq,
 	.start		= rockchip_pcie_ep_start,
+	.stop		= rockchip_pcie_ep_stop,
 	.get_features	= rockchip_pcie_ep_get_features,
 };
 
diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h
index 30398156095f9..0263f158ee8de 100644
--- a/drivers/pci/controller/pcie-rockchip.h
+++ b/drivers/pci/controller/pcie-rockchip.h
@@ -32,6 +32,7 @@
 #define   PCIE_CLIENT_CONF_ENABLE	  HIWORD_UPDATE_BIT(0x0001)
 #define   PCIE_CLIENT_CONF_DISABLE       HIWORD_UPDATE(0x0001, 0)
 #define   PCIE_CLIENT_LINK_TRAIN_ENABLE	  HIWORD_UPDATE_BIT(0x0002)
+#define   PCIE_CLIENT_LINK_TRAIN_DISABLE  HIWORD_UPDATE(0x0002, 0)
 #define   PCIE_CLIENT_ARI_ENABLE	  HIWORD_UPDATE_BIT(0x0008)
 #define   PCIE_CLIENT_CONF_LANE_NUM(x)	  HIWORD_UPDATE(0x0030, ENCODE_LANES(x))
 #define   PCIE_CLIENT_MODE_RC		  HIWORD_UPDATE_BIT(0x0040)

From bd6e61df4b2e69985daa312ce28b6af629b30870 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 17 Oct 2024 10:58:47 +0900
Subject: [PATCH 1416/1530] PCI: rockchip-ep: Improve link training
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Rockchip RK3399 TRM V1.3 Part2, Section 17.5.8.1.2, step 7,
describes the endpoint mode link training process clearly and states
that:

  Insure link training completion and success by observing link_st field
  in PCIe Client BASIC_STATUS1 register change to 2'b11. If both side
  support PCIe Gen2 speed, re-train can be Initiated by asserting the
  Retrain Link field in Link Control and Status Register. The software
  should insure the BASIC_STATUS0[negotiated_speed] changes to "1", that
  indicates re-train to Gen2 successfully.

This procedure is very similar to what is done for the root-port mode
in rockchip_pcie_host_init_port().

Implement this link training procedure for the endpoint mode as well.
Given that the RK3399 SoC does not have an interrupt signaling link
status changes, training is implemented as a delayed work which is
rescheduled until the link training completes or the endpoint controller
is stopped. The link training work is first scheduled in
rockchip_pcie_ep_start() when the endpoint function is started. Link
training completion is signaled to the function using pci_epc_linkup().
Accordingly, the linkup_notifier field of the Rockchip pci_epc_features
structure is changed to true.

Link: https://lore.kernel.org/r/20241017015849.190271-13-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
[kwilczynski: update log messages to make them consistent]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/controller/pcie-rockchip-ep.c | 82 ++++++++++++++++++++++-
 drivers/pci/controller/pcie-rockchip.h    | 11 +++
 2 files changed, 92 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 13755e4ed59de..b4d405e4c9544 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -10,12 +10,14 @@
 
 #include <linux/configfs.h>
 #include <linux/delay.h>
+#include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
 #include <linux/pci-epc.h>
 #include <linux/platform_device.h>
 #include <linux/pci-epf.h>
 #include <linux/sizes.h>
+#include <linux/workqueue.h>
 
 #include "pcie-rockchip.h"
 
@@ -48,6 +50,7 @@ struct rockchip_pcie_ep {
 	u64			irq_pci_addr;
 	u8			irq_pci_fn;
 	u8			irq_pending;
+	struct delayed_work	link_training;
 };
 
 static void rockchip_pcie_clear_ep_ob_atu(struct rockchip_pcie *rockchip,
@@ -473,6 +476,8 @@ static int rockchip_pcie_ep_start(struct pci_epc *epc)
 			    PCIE_CLIENT_CONF_ENABLE,
 			    PCIE_CLIENT_CONFIG);
 
+	schedule_delayed_work(&ep->link_training, 0);
+
 	return 0;
 }
 
@@ -481,6 +486,8 @@ static void rockchip_pcie_ep_stop(struct pci_epc *epc)
 	struct rockchip_pcie_ep *ep = epc_get_drvdata(epc);
 	struct rockchip_pcie *rockchip = &ep->rockchip;
 
+	cancel_delayed_work_sync(&ep->link_training);
+
 	/* Stop link training and disable configuration */
 	rockchip_pcie_write(rockchip,
 			    PCIE_CLIENT_CONF_DISABLE |
@@ -488,8 +495,80 @@ static void rockchip_pcie_ep_stop(struct pci_epc *epc)
 			    PCIE_CLIENT_CONFIG);
 }
 
+static void rockchip_pcie_ep_retrain_link(struct rockchip_pcie *rockchip)
+{
+	u32 status;
+
+	status = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_LCS);
+	status |= PCI_EXP_LNKCTL_RL;
+	rockchip_pcie_write(rockchip, status, PCIE_EP_CONFIG_LCS);
+}
+
+static bool rockchip_pcie_ep_link_up(struct rockchip_pcie *rockchip)
+{
+	u32 val = rockchip_pcie_read(rockchip, PCIE_CLIENT_BASIC_STATUS1);
+
+	return PCIE_LINK_UP(val);
+}
+
+static void rockchip_pcie_ep_link_training(struct work_struct *work)
+{
+	struct rockchip_pcie_ep *ep =
+		container_of(work, struct rockchip_pcie_ep, link_training.work);
+	struct rockchip_pcie *rockchip = &ep->rockchip;
+	struct device *dev = rockchip->dev;
+	u32 val;
+	int ret;
+
+	/* Enable Gen1 training and wait for its completion */
+	ret = readl_poll_timeout(rockchip->apb_base + PCIE_CORE_CTRL,
+				 val, PCIE_LINK_TRAINING_DONE(val), 50,
+				 LINK_TRAIN_TIMEOUT);
+	if (ret)
+		goto again;
+
+	/* Make sure that the link is up */
+	ret = readl_poll_timeout(rockchip->apb_base + PCIE_CLIENT_BASIC_STATUS1,
+				 val, PCIE_LINK_UP(val), 50,
+				 LINK_TRAIN_TIMEOUT);
+	if (ret)
+		goto again;
+
+	/*
+	 * Check the current speed: if gen2 speed was requested and we are not
+	 * at gen2 speed yet, retrain again for gen2.
+	 */
+	val = rockchip_pcie_read(rockchip, PCIE_CORE_CTRL);
+	if (!PCIE_LINK_IS_GEN2(val) && rockchip->link_gen == 2) {
+		/* Enable retrain for gen2 */
+		rockchip_pcie_ep_retrain_link(rockchip);
+		readl_poll_timeout(rockchip->apb_base + PCIE_CORE_CTRL,
+				   val, PCIE_LINK_IS_GEN2(val), 50,
+				   LINK_TRAIN_TIMEOUT);
+	}
+
+	/* Check again that the link is up */
+	if (!rockchip_pcie_ep_link_up(rockchip))
+		goto again;
+
+	val = rockchip_pcie_read(rockchip, PCIE_CLIENT_BASIC_STATUS0);
+	dev_info(dev,
+		 "link up (negotiated speed: %sGT/s, width: x%lu)\n",
+		 (val & PCIE_CLIENT_NEG_LINK_SPEED) ? "5" : "2.5",
+		 ((val & PCIE_CLIENT_NEG_LINK_WIDTH_MASK) >>
+		  PCIE_CLIENT_NEG_LINK_WIDTH_SHIFT) << 1);
+
+	/* Notify the function */
+	pci_epc_linkup(ep->epc);
+
+	return;
+
+again:
+	schedule_delayed_work(&ep->link_training, msecs_to_jiffies(5));
+}
+
 static const struct pci_epc_features rockchip_pcie_epc_features = {
-	.linkup_notifier = false,
+	.linkup_notifier = true,
 	.msi_capable = true,
 	.msix_capable = false,
 	.align = ROCKCHIP_PCIE_AT_SIZE_ALIGN,
@@ -647,6 +726,7 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev)
 	rockchip = &ep->rockchip;
 	rockchip->is_rc = false;
 	rockchip->dev = dev;
+	INIT_DELAYED_WORK(&ep->link_training, rockchip_pcie_ep_link_training);
 
 	epc = devm_pci_epc_create(dev, &rockchip_pcie_epc_ops);
 	if (IS_ERR(epc)) {
diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h
index 0263f158ee8de..24796176f6584 100644
--- a/drivers/pci/controller/pcie-rockchip.h
+++ b/drivers/pci/controller/pcie-rockchip.h
@@ -26,6 +26,7 @@
 #define MAX_LANE_NUM			4
 #define MAX_REGION_LIMIT		32
 #define MIN_EP_APERTURE			28
+#define LINK_TRAIN_TIMEOUT		(500 * USEC_PER_MSEC)
 
 #define PCIE_CLIENT_BASE		0x0
 #define PCIE_CLIENT_CONFIG		(PCIE_CLIENT_BASE + 0x00)
@@ -50,6 +51,10 @@
 #define   PCIE_CLIENT_DEBUG_LTSSM_MASK		GENMASK(5, 0)
 #define   PCIE_CLIENT_DEBUG_LTSSM_L1		0x18
 #define   PCIE_CLIENT_DEBUG_LTSSM_L2		0x19
+#define PCIE_CLIENT_BASIC_STATUS0	(PCIE_CLIENT_BASE + 0x44)
+#define   PCIE_CLIENT_NEG_LINK_WIDTH_MASK	GENMASK(7, 6)
+#define   PCIE_CLIENT_NEG_LINK_WIDTH_SHIFT	6
+#define   PCIE_CLIENT_NEG_LINK_SPEED		BIT(5)
 #define PCIE_CLIENT_BASIC_STATUS1	(PCIE_CLIENT_BASE + 0x48)
 #define   PCIE_CLIENT_LINK_STATUS_UP		0x00300000
 #define   PCIE_CLIENT_LINK_STATUS_MASK		0x00300000
@@ -87,6 +92,8 @@
 
 #define PCIE_CORE_CTRL_MGMT_BASE	0x900000
 #define PCIE_CORE_CTRL			(PCIE_CORE_CTRL_MGMT_BASE + 0x000)
+#define   PCIE_CORE_PL_CONF_LS_MASK		0x00000001
+#define   PCIE_CORE_PL_CONF_LS_READY		0x00000001
 #define   PCIE_CORE_PL_CONF_SPEED_5G		0x00000008
 #define   PCIE_CORE_PL_CONF_SPEED_MASK		0x00000018
 #define   PCIE_CORE_PL_CONF_LANE_MASK		0x00000006
@@ -144,6 +151,7 @@
 #define PCIE_RC_CONFIG_BASE		0xa00000
 #define PCIE_EP_CONFIG_BASE		0xa00000
 #define PCIE_EP_CONFIG_DID_VID		(PCIE_EP_CONFIG_BASE + 0x00)
+#define PCIE_EP_CONFIG_LCS		(PCIE_EP_CONFIG_BASE + 0xd0)
 #define PCIE_RC_CONFIG_RID_CCR		(PCIE_RC_CONFIG_BASE + 0x08)
 #define PCIE_RC_CONFIG_DCR		(PCIE_RC_CONFIG_BASE + 0xc4)
 #define   PCIE_RC_CONFIG_DCR_CSPL_SHIFT		18
@@ -155,6 +163,7 @@
 #define PCIE_RC_CONFIG_LINK_CAP		(PCIE_RC_CONFIG_BASE + 0xcc)
 #define   PCIE_RC_CONFIG_LINK_CAP_L0S		BIT(10)
 #define PCIE_RC_CONFIG_LCS		(PCIE_RC_CONFIG_BASE + 0xd0)
+#define PCIE_EP_CONFIG_LCS		(PCIE_EP_CONFIG_BASE + 0xd0)
 #define PCIE_RC_CONFIG_L1_SUBSTATE_CTRL2 (PCIE_RC_CONFIG_BASE + 0x90c)
 #define PCIE_RC_CONFIG_THP_CAP		(PCIE_RC_CONFIG_BASE + 0x274)
 #define   PCIE_RC_CONFIG_THP_CAP_NEXT_MASK	GENMASK(31, 20)
@@ -192,6 +201,8 @@
 #define ROCKCHIP_VENDOR_ID			0x1d87
 #define PCIE_LINK_IS_L2(x) \
 	(((x) & PCIE_CLIENT_DEBUG_LTSSM_MASK) == PCIE_CLIENT_DEBUG_LTSSM_L2)
+#define PCIE_LINK_TRAINING_DONE(x) \
+	(((x) & PCIE_CORE_PL_CONF_LS_MASK) == PCIE_CORE_PL_CONF_LS_READY)
 #define PCIE_LINK_UP(x) \
 	(((x) & PCIE_CLIENT_LINK_STATUS_MASK) == PCIE_CLIENT_LINK_STATUS_UP)
 #define PCIE_LINK_IS_GEN2(x) \

From a7137cbf6bd53a9f9c40c64fc8b12b88289b3d4a Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 17 Oct 2024 10:58:48 +0900
Subject: [PATCH 1417/1530] PCI: rockchip-ep: Handle PERST# signal in EP mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, the Rockchip PCIe endpoint controller driver does not handle
the PERST# signal, which prevents detecting when link training should
actually be started or if the host resets the device. This however can
be supported using the controller reset_gpios property set as an input
GPIO for endpoint mode.

Modify the Rockchip PCI endpoint controller driver to get the reset_gpio
and its associated interrupt which is serviced using a threaded IRQ with
the function rockchip_pcie_ep_perst_irq_thread() as handler.

This handler function notifies a link down event corresponding to the RC
side asserting the PERST# signal using pci_epc_linkdown() when the gpio
is high. Once the gpio value goes down, corresponding to the RC
de-asserting the PERST# signal, link training is started. The polarity
of the gpio interrupt trigger is changed from high to low after the RC
asserted PERST#, and conversely changed from low to high after the RC
de-asserts PERST#.

Also, given that the host mode controller and the endpoint mode
controller use two different property names for the same PERST# signal
(ep_gpios property and reset_gpios property respectively), for clarity,
rename the ep_gpio field of struct rockchip_pcie to perst_gpio.

Link: https://lore.kernel.org/r/20241017015849.190271-14-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
[kwilczynski: make log messages consistent, add missing include]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/controller/pcie-rockchip-ep.c   | 133 +++++++++++++++++++-
 drivers/pci/controller/pcie-rockchip-host.c |   4 +-
 drivers/pci/controller/pcie-rockchip.c      |  16 +--
 drivers/pci/controller/pcie-rockchip.h      |   2 +-
 4 files changed, 141 insertions(+), 14 deletions(-)

diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index b4d405e4c9544..1064b7b06cef6 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -10,8 +10,10 @@
 
 #include <linux/configfs.h>
 #include <linux/delay.h>
+#include <linux/gpio/consumer.h>
 #include <linux/iopoll.h>
 #include <linux/kernel.h>
+#include <linux/irq.h>
 #include <linux/of.h>
 #include <linux/pci-epc.h>
 #include <linux/platform_device.h>
@@ -50,6 +52,9 @@ struct rockchip_pcie_ep {
 	u64			irq_pci_addr;
 	u8			irq_pci_fn;
 	u8			irq_pending;
+	int			perst_irq;
+	bool			perst_asserted;
+	bool			link_up;
 	struct delayed_work	link_training;
 };
 
@@ -470,13 +475,17 @@ static int rockchip_pcie_ep_start(struct pci_epc *epc)
 
 	rockchip_pcie_write(rockchip, cfg, PCIE_CORE_PHY_FUNC_CFG);
 
+	if (rockchip->perst_gpio)
+		enable_irq(ep->perst_irq);
+
 	/* Enable configuration and start link training */
 	rockchip_pcie_write(rockchip,
 			    PCIE_CLIENT_LINK_TRAIN_ENABLE |
 			    PCIE_CLIENT_CONF_ENABLE,
 			    PCIE_CLIENT_CONFIG);
 
-	schedule_delayed_work(&ep->link_training, 0);
+	if (!rockchip->perst_gpio)
+		schedule_delayed_work(&ep->link_training, 0);
 
 	return 0;
 }
@@ -486,6 +495,11 @@ static void rockchip_pcie_ep_stop(struct pci_epc *epc)
 	struct rockchip_pcie_ep *ep = epc_get_drvdata(epc);
 	struct rockchip_pcie *rockchip = &ep->rockchip;
 
+	if (rockchip->perst_gpio) {
+		ep->perst_asserted = true;
+		disable_irq(ep->perst_irq);
+	}
+
 	cancel_delayed_work_sync(&ep->link_training);
 
 	/* Stop link training and disable configuration */
@@ -551,6 +565,13 @@ static void rockchip_pcie_ep_link_training(struct work_struct *work)
 	if (!rockchip_pcie_ep_link_up(rockchip))
 		goto again;
 
+	/*
+	 * If PERST# was asserted while polling the link, do not notify
+	 * the function.
+	 */
+	if (ep->perst_asserted)
+		return;
+
 	val = rockchip_pcie_read(rockchip, PCIE_CLIENT_BASIC_STATUS0);
 	dev_info(dev,
 		 "link up (negotiated speed: %sGT/s, width: x%lu)\n",
@@ -560,6 +581,7 @@ static void rockchip_pcie_ep_link_training(struct work_struct *work)
 
 	/* Notify the function */
 	pci_epc_linkup(ep->epc);
+	ep->link_up = true;
 
 	return;
 
@@ -567,6 +589,103 @@ static void rockchip_pcie_ep_link_training(struct work_struct *work)
 	schedule_delayed_work(&ep->link_training, msecs_to_jiffies(5));
 }
 
+static void rockchip_pcie_ep_perst_assert(struct rockchip_pcie_ep *ep)
+{
+	struct rockchip_pcie *rockchip = &ep->rockchip;
+
+	dev_dbg(rockchip->dev, "PERST# asserted, link down\n");
+
+	if (ep->perst_asserted)
+		return;
+
+	ep->perst_asserted = true;
+
+	cancel_delayed_work_sync(&ep->link_training);
+
+	if (ep->link_up) {
+		pci_epc_linkdown(ep->epc);
+		ep->link_up = false;
+	}
+}
+
+static void rockchip_pcie_ep_perst_deassert(struct rockchip_pcie_ep *ep)
+{
+	struct rockchip_pcie *rockchip = &ep->rockchip;
+
+	dev_dbg(rockchip->dev, "PERST# de-asserted, starting link training\n");
+
+	if (!ep->perst_asserted)
+		return;
+
+	ep->perst_asserted = false;
+
+	/* Enable link re-training */
+	rockchip_pcie_ep_retrain_link(rockchip);
+
+	/* Start link training */
+	schedule_delayed_work(&ep->link_training, 0);
+}
+
+static irqreturn_t rockchip_pcie_ep_perst_irq_thread(int irq, void *data)
+{
+	struct pci_epc *epc = data;
+	struct rockchip_pcie_ep *ep = epc_get_drvdata(epc);
+	struct rockchip_pcie *rockchip = &ep->rockchip;
+	u32 perst = gpiod_get_value(rockchip->perst_gpio);
+
+	if (perst)
+		rockchip_pcie_ep_perst_assert(ep);
+	else
+		rockchip_pcie_ep_perst_deassert(ep);
+
+	irq_set_irq_type(ep->perst_irq,
+			 (perst ? IRQF_TRIGGER_HIGH : IRQF_TRIGGER_LOW));
+
+	return IRQ_HANDLED;
+}
+
+static int rockchip_pcie_ep_setup_irq(struct pci_epc *epc)
+{
+	struct rockchip_pcie_ep *ep = epc_get_drvdata(epc);
+	struct rockchip_pcie *rockchip = &ep->rockchip;
+	struct device *dev = rockchip->dev;
+	int ret;
+
+	if (!rockchip->perst_gpio)
+		return 0;
+
+	/* PCIe reset interrupt */
+	ep->perst_irq = gpiod_to_irq(rockchip->perst_gpio);
+	if (ep->perst_irq < 0) {
+		dev_err(dev,
+			"failed to get IRQ for PERST# GPIO: %d\n",
+			ep->perst_irq);
+
+		return ep->perst_irq;
+	}
+
+	/*
+	 * The perst_gpio is active low, so when it is inactive on start, it
+	 * is high and will trigger the perst_irq handler. So treat this initial
+	 * IRQ as a dummy one by faking the host asserting PERST#.
+	 */
+	ep->perst_asserted = true;
+	irq_set_status_flags(ep->perst_irq, IRQ_NOAUTOEN);
+	ret = devm_request_threaded_irq(dev, ep->perst_irq, NULL,
+					rockchip_pcie_ep_perst_irq_thread,
+					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					"pcie-ep-perst", epc);
+	if (ret) {
+		dev_err(dev,
+			"failed to request IRQ for PERST# GPIO: %d\n",
+			ret);
+
+		return ret;
+	}
+
+	return 0;
+}
+
 static const struct pci_epc_features rockchip_pcie_epc_features = {
 	.linkup_notifier = true,
 	.msi_capable = true,
@@ -730,7 +849,7 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev)
 
 	epc = devm_pci_epc_create(dev, &rockchip_pcie_epc_ops);
 	if (IS_ERR(epc)) {
-		dev_err(dev, "failed to create epc device\n");
+		dev_err(dev, "failed to create EPC device\n");
 		return PTR_ERR(epc);
 	}
 
@@ -760,11 +879,17 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev)
 
 	pci_epc_init_notify(epc);
 
+	err = rockchip_pcie_ep_setup_irq(epc);
+	if (err < 0)
+		goto err_uninit_port;
+
 	return 0;
-err_exit_ob_mem:
-	rockchip_pcie_ep_exit_ob_mem(ep);
+err_uninit_port:
+	rockchip_pcie_deinit_phys(rockchip);
 err_disable_clocks:
 	rockchip_pcie_disable_clocks(rockchip);
+err_exit_ob_mem:
+	rockchip_pcie_ep_exit_ob_mem(ep);
 	return err;
 }
 
diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c
index cbec711148253..7471d9fd18bc2 100644
--- a/drivers/pci/controller/pcie-rockchip-host.c
+++ b/drivers/pci/controller/pcie-rockchip-host.c
@@ -294,7 +294,7 @@ static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip)
 	int err, i = MAX_LANE_NUM;
 	u32 status;
 
-	gpiod_set_value_cansleep(rockchip->ep_gpio, 0);
+	gpiod_set_value_cansleep(rockchip->perst_gpio, 0);
 
 	err = rockchip_pcie_init_port(rockchip);
 	if (err)
@@ -323,7 +323,7 @@ static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip)
 			    PCIE_CLIENT_CONFIG);
 
 	msleep(PCIE_T_PVPERL_MS);
-	gpiod_set_value_cansleep(rockchip->ep_gpio, 1);
+	gpiod_set_value_cansleep(rockchip->perst_gpio, 1);
 
 	msleep(PCIE_T_RRS_READY_MS);
 
diff --git a/drivers/pci/controller/pcie-rockchip.c b/drivers/pci/controller/pcie-rockchip.c
index 154e78819e6e8..b9ade7632e113 100644
--- a/drivers/pci/controller/pcie-rockchip.c
+++ b/drivers/pci/controller/pcie-rockchip.c
@@ -119,13 +119,15 @@ int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip)
 		return PTR_ERR(rockchip->aclk_rst);
 	}
 
-	if (rockchip->is_rc) {
-		rockchip->ep_gpio = devm_gpiod_get_optional(dev, "ep",
-							    GPIOD_OUT_LOW);
-		if (IS_ERR(rockchip->ep_gpio))
-			return dev_err_probe(dev, PTR_ERR(rockchip->ep_gpio),
-					     "failed to get ep GPIO\n");
-	}
+	if (rockchip->is_rc)
+		rockchip->perst_gpio = devm_gpiod_get_optional(dev, "ep",
+							       GPIOD_OUT_LOW);
+	else
+		rockchip->perst_gpio = devm_gpiod_get_optional(dev, "reset",
+							       GPIOD_IN);
+	if (IS_ERR(rockchip->perst_gpio))
+		return dev_err_probe(dev, PTR_ERR(rockchip->perst_gpio),
+				     "failed to get PERST# GPIO\n");
 
 	rockchip->aclk_pcie = devm_clk_get(dev, "aclk");
 	if (IS_ERR(rockchip->aclk_pcie)) {
diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h
index 24796176f6584..a51b087ce8786 100644
--- a/drivers/pci/controller/pcie-rockchip.h
+++ b/drivers/pci/controller/pcie-rockchip.h
@@ -329,7 +329,7 @@ struct rockchip_pcie {
 	struct	regulator *vpcie3v3; /* 3.3V power supply */
 	struct	regulator *vpcie1v8; /* 1.8V power supply */
 	struct	regulator *vpcie0v9; /* 0.9V power supply */
-	struct	gpio_desc *ep_gpio;
+	struct	gpio_desc *perst_gpio;
 	u32	lanes;
 	u8      lanes_map;
 	int	link_gen;

From 43a43faf5376114161aa684834d24e06da596287 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 22 Nov 2024 11:18:25 -0800
Subject: [PATCH 1418/1530] futex: improve user space accesses

Josh Poimboeuf reports that he got a "will-it-scale.per_process_ops 1.9%
improvement" report for his patch that changed __get_user() to use
pointer masking instead of the explicit speculation barrier.  However,
that patch doesn't actually work in the general case, because some (very
bad) architecture-specific code actually depends on __get_user() also
working on kernel addresses.

A profile showed that the offending __get_user() was the futex code,
which really should be fixed up to not use that horrid legacy case.
Rewrite futex_get_value_locked() to use the modern user acccess helpers,
and inline it so that the compiler not only avoids the function call for
a few instructions, but can do CSE on the address masking.

It also turns out the x86 futex functions have unnecessary barriers in
other places, so let's fix those up too.

Link: https://lore.kernel.org/all/20241115230653.hfvzyf3aqqntgp63@jpoimboe/
Reported-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/include/asm/futex.h |  8 +++--
 kernel/futex/core.c          | 22 --------------
 kernel/futex/futex.h         | 59 ++++++++++++++++++++++++++++++++++--
 3 files changed, 63 insertions(+), 26 deletions(-)

diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index 99d345b686fa2..6e2458088800a 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -48,7 +48,9 @@ do {								\
 static __always_inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
 		u32 __user *uaddr)
 {
-	if (!user_access_begin(uaddr, sizeof(u32)))
+	if (can_do_masked_user_access())
+		uaddr = masked_user_access_begin(uaddr);
+	else if (!user_access_begin(uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	switch (op) {
@@ -84,7 +86,9 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 {
 	int ret = 0;
 
-	if (!user_access_begin(uaddr, sizeof(u32)))
+	if (can_do_masked_user_access())
+		uaddr = masked_user_access_begin(uaddr);
+	else if (!user_access_begin(uaddr, sizeof(u32)))
 		return -EFAULT;
 	asm volatile("\n"
 		"1:\t" LOCK_PREFIX "cmpxchgl %3, %2\n"
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 6de57246760e6..ebdd76b4ecbba 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -451,28 +451,6 @@ struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *
 	return NULL;
 }
 
-int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval)
-{
-	int ret;
-
-	pagefault_disable();
-	ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);
-	pagefault_enable();
-
-	return ret;
-}
-
-int futex_get_value_locked(u32 *dest, u32 __user *from)
-{
-	int ret;
-
-	pagefault_disable();
-	ret = __get_user(*dest, from);
-	pagefault_enable();
-
-	return ret ? -EFAULT : 0;
-}
-
 /**
  * wait_for_owner_exiting - Block until the owner has exited
  * @ret: owner's current futex lock status
diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h
index 8b195d06f4e8e..618ce1fe870e9 100644
--- a/kernel/futex/futex.h
+++ b/kernel/futex/futex.h
@@ -6,6 +6,7 @@
 #include <linux/rtmutex.h>
 #include <linux/sched/wake_q.h>
 #include <linux/compat.h>
+#include <linux/uaccess.h>
 
 #ifdef CONFIG_PREEMPT_RT
 #include <linux/rcuwait.h>
@@ -225,10 +226,64 @@ extern bool __futex_wake_mark(struct futex_q *q);
 extern void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q);
 
 extern int fault_in_user_writeable(u32 __user *uaddr);
-extern int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval);
-extern int futex_get_value_locked(u32 *dest, u32 __user *from);
 extern struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key);
 
+static inline int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval)
+{
+	int ret;
+
+	pagefault_disable();
+	ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);
+	pagefault_enable();
+
+	return ret;
+}
+
+/*
+ * This does a plain atomic user space read, and the user pointer has
+ * already been verified earlier by get_futex_key() to be both aligned
+ * and actually in user space, just like futex_atomic_cmpxchg_inatomic().
+ *
+ * We still want to avoid any speculation, and while __get_user() is
+ * the traditional model for this, it's actually slower than doing
+ * this manually these days.
+ *
+ * We could just have a per-architecture special function for it,
+ * the same way we do futex_atomic_cmpxchg_inatomic(), but rather
+ * than force everybody to do that, write it out long-hand using
+ * the low-level user-access infrastructure.
+ *
+ * This looks a bit overkill, but generally just results in a couple
+ * of instructions.
+ */
+static __always_inline int futex_read_inatomic(u32 *dest, u32 __user *from)
+{
+	u32 val;
+
+	if (can_do_masked_user_access())
+		from = masked_user_access_begin(from);
+	else if (!user_read_access_begin(from, sizeof(*from)))
+		return -EFAULT;
+	unsafe_get_user(val, from, Efault);
+	user_access_end();
+	*dest = val;
+	return 0;
+Efault:
+	user_access_end();
+	return -EFAULT;
+}
+
+static inline int futex_get_value_locked(u32 *dest, u32 __user *from)
+{
+	int ret;
+
+	pagefault_disable();
+	ret = futex_read_inatomic(dest, from);
+	pagefault_enable();
+
+	return ret;
+}
+
 extern void __futex_unqueue(struct futex_q *q);
 extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb);
 extern int futex_unqueue(struct futex_q *q);

From 573f45a9f9a47fed4c7957609689b772121b33d7 Mon Sep 17 00:00:00 2001
From: David Laight <David.Laight@ACULAB.COM>
Date: Sun, 24 Nov 2024 15:39:00 +0000
Subject: [PATCH 1419/1530] x86: fix off-by-one in access_ok()

When the size isn't a small constant, __access_ok() will call
valid_user_address() with the address after the last byte of the user
buffer.

It is valid for a buffer to end with the last valid user address so
valid_user_address() must allow accesses to the base of the guard page.

[ This introduces an off-by-one in the other direction for the plain
  non-sized accesses, but since we have that guard region that is a
  whole page, those checks "allowing" accesses to that guard region
  don't really matter. The access will fault anyway, whether to the
  guard page or if the address has been masked to all ones - Linus ]

Fixes: 86e6b1547b3d0 ("x86: fix user address masking non-canonical speculation issue")
Signed-off-by: David Laight <david.laight@aculab.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/kernel/cpu/common.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 06a516f6795b3..ca327cfa42ae2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2389,12 +2389,12 @@ void __init arch_cpu_finalize_init(void)
 	alternative_instructions();
 
 	if (IS_ENABLED(CONFIG_X86_64)) {
-		unsigned long USER_PTR_MAX = TASK_SIZE_MAX-1;
+		unsigned long USER_PTR_MAX = TASK_SIZE_MAX;
 
 		/*
 		 * Enable this when LAM is gated on LASS support
 		if (cpu_feature_enabled(X86_FEATURE_LAM))
-			USER_PTR_MAX = (1ul << 63) - PAGE_SIZE - 1;
+			USER_PTR_MAX = (1ul << 63) - PAGE_SIZE;
 		 */
 		runtime_const_init(ptr, USER_PTR_MAX);
 

From 222974c6ec9d901f7ad13bbe6e505ec1f1d822d4 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Mon, 25 Nov 2024 18:45:33 -0800
Subject: [PATCH 1420/1530] iommu: remove stale declaration left over by a
 merge conflict

The merge commit ae3325f752ef ("Merge branches 'arm/smmu', 'mediatek',
's390', 'ti/omap', 'riscv' and 'core' into next") left a stale
declaration of 'iommu_present()' even though the 'core' branch that was
merged had removed the function (and the declaration).

Remove it for real.

Reported-by: Dmitry Safonov <0x7f454c46@gmail.com>
Cc: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/iommu.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index d6aaaec3caf46..301e97d745c13 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -841,7 +841,6 @@ static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather)
 	};
 }
 
-extern bool iommu_present(const struct bus_type *bus);
 extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap);
 extern bool iommu_group_has_isolated_msi(struct iommu_group *group);
 struct iommu_domain *iommu_paging_domain_alloc_flags(struct device *dev, unsigned int flags);

From 5d066766c5f1252f98ff859265bcd1a5b52ac46c Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 18 Nov 2024 14:04:11 +0000
Subject: [PATCH 1421/1530] net/l2tp: fix warning in l2tp_exit_net found by
 syzbot

In l2tp's net exit handler, we check that an IDR is empty before
destroying it:

	WARN_ON_ONCE(!idr_is_empty(&pn->l2tp_tunnel_idr));
	idr_destroy(&pn->l2tp_tunnel_idr);

By forcing memory allocation failures in idr_alloc_32, syzbot is able
to provoke a condition where idr_is_empty returns false despite there
being no items in the IDR. This turns out to be because the radix tree
of the IDR contains only internal radix-tree nodes and it is this that
causes idr_is_empty to return false. The internal nodes are cleaned by
idr_destroy.

Use idr_for_each to check that the IDR is empty instead of
idr_is_empty to avoid the problem.

Reported-by: syzbot+332fe1e67018625f63c9@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=332fe1e67018625f63c9
Fixes: 73d33bd063c4 ("l2tp: avoid using drain_workqueue in l2tp_pre_exit_net")
Signed-off-by: James Chapman <jchapman@katalix.com>
Link: https://patch.msgid.link/20241118140411.1582555-1-jchapman@katalix.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/l2tp/l2tp_core.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 3eec23ac5ab10..369a2f2e459cd 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1870,15 +1870,31 @@ static __net_exit void l2tp_pre_exit_net(struct net *net)
 	}
 }
 
+static int l2tp_idr_item_unexpected(int id, void *p, void *data)
+{
+	const char *idr_name = data;
+
+	pr_err("l2tp: %s IDR not empty at net %d exit\n", idr_name, id);
+	WARN_ON_ONCE(1);
+	return 1;
+}
+
 static __net_exit void l2tp_exit_net(struct net *net)
 {
 	struct l2tp_net *pn = l2tp_pernet(net);
 
-	WARN_ON_ONCE(!idr_is_empty(&pn->l2tp_v2_session_idr));
+	/* Our per-net IDRs should be empty. Check that is so, to
+	 * help catch cleanup races or refcnt leaks.
+	 */
+	idr_for_each(&pn->l2tp_v2_session_idr, l2tp_idr_item_unexpected,
+		     "v2_session");
+	idr_for_each(&pn->l2tp_v3_session_idr, l2tp_idr_item_unexpected,
+		     "v3_session");
+	idr_for_each(&pn->l2tp_tunnel_idr, l2tp_idr_item_unexpected,
+		     "tunnel");
+
 	idr_destroy(&pn->l2tp_v2_session_idr);
-	WARN_ON_ONCE(!idr_is_empty(&pn->l2tp_v3_session_idr));
 	idr_destroy(&pn->l2tp_v3_session_idr);
-	WARN_ON_ONCE(!idr_is_empty(&pn->l2tp_tunnel_idr));
 	idr_destroy(&pn->l2tp_tunnel_idr);
 }
 

From ebaf81317e42aa990ad20b113cfe3a7b20d4e937 Mon Sep 17 00:00:00 2001
From: Sidraya Jayagond <sidraya@linux.ibm.com>
Date: Tue, 19 Nov 2024 16:22:19 +0100
Subject: [PATCH 1422/1530] s390/iucv: MSG_PEEK causes memory leak in
 iucv_sock_destruct()

Passing MSG_PEEK flag to skb_recv_datagram() increments skb refcount
(skb->users) and iucv_sock_recvmsg() does not decrement skb refcount
at exit.
This results in skb memory leak in skb_queue_purge() and WARN_ON in
iucv_sock_destruct() during socket close. To fix this decrease
skb refcount by one if MSG_PEEK is set in order to prevent memory
leak and WARN_ON.

WARNING: CPU: 2 PID: 6292 at net/iucv/af_iucv.c:286 iucv_sock_destruct+0x144/0x1a0 [af_iucv]
CPU: 2 PID: 6292 Comm: afiucv_test_msg Kdump: loaded Tainted: G        W          6.10.0-rc7 #1
Hardware name: IBM 3931 A01 704 (z/VM 7.3.0)
Call Trace:
        [<001587c682c4aa98>] iucv_sock_destruct+0x148/0x1a0 [af_iucv]
        [<001587c682c4a9d0>] iucv_sock_destruct+0x80/0x1a0 [af_iucv]
        [<001587c704117a32>] __sk_destruct+0x52/0x550
        [<001587c704104a54>] __sock_release+0xa4/0x230
        [<001587c704104c0c>] sock_close+0x2c/0x40
        [<001587c702c5f5a8>] __fput+0x2e8/0x970
        [<001587c7024148c4>] task_work_run+0x1c4/0x2c0
        [<001587c7023b0716>] do_exit+0x996/0x1050
        [<001587c7023b13aa>] do_group_exit+0x13a/0x360
        [<001587c7023b1626>] __s390x_sys_exit_group+0x56/0x60
        [<001587c7022bccca>] do_syscall+0x27a/0x380
        [<001587c7049a6a0c>] __do_syscall+0x9c/0x160
        [<001587c7049ce8a8>] system_call+0x70/0x98
        Last Breaking-Event-Address:
        [<001587c682c4a9d4>] iucv_sock_destruct+0x84/0x1a0 [af_iucv]

Fixes: eac3731bd04c ("[S390]: Add AF_IUCV socket support")
Reviewed-by: Alexandra Winter <wintera@linux.ibm.com>
Reviewed-by: Thorsten Winkler <twinkler@linux.ibm.com>
Signed-off-by: Sidraya Jayagond <sidraya@linux.ibm.com>
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Reviewed-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20241119152219.3712168-1-wintera@linux.ibm.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/iucv/af_iucv.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index c00323fa9eb66..7929df08d4e02 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1236,7 +1236,9 @@ static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 		return -EOPNOTSUPP;
 
 	/* receive/dequeue next skb:
-	 * the function understands MSG_PEEK and, thus, does not dequeue skb */
+	 * the function understands MSG_PEEK and, thus, does not dequeue skb
+	 * only refcount is increased.
+	 */
 	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb) {
 		if (sk->sk_shutdown & RCV_SHUTDOWN)
@@ -1252,9 +1254,8 @@ static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 
 	cskb = skb;
 	if (skb_copy_datagram_msg(cskb, offset, msg, copied)) {
-		if (!(flags & MSG_PEEK))
-			skb_queue_head(&sk->sk_receive_queue, skb);
-		return -EFAULT;
+		err = -EFAULT;
+		goto err_out;
 	}
 
 	/* SOCK_SEQPACKET: set MSG_TRUNC if recv buf size is too small */
@@ -1271,11 +1272,8 @@ static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 	err = put_cmsg(msg, SOL_IUCV, SCM_IUCV_TRGCLS,
 		       sizeof(IUCV_SKB_CB(skb)->class),
 		       (void *)&IUCV_SKB_CB(skb)->class);
-	if (err) {
-		if (!(flags & MSG_PEEK))
-			skb_queue_head(&sk->sk_receive_queue, skb);
-		return err;
-	}
+	if (err)
+		goto err_out;
 
 	/* Mark read part of skb as used */
 	if (!(flags & MSG_PEEK)) {
@@ -1331,8 +1329,18 @@ static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 	/* SOCK_SEQPACKET: return real length if MSG_TRUNC is set */
 	if (sk->sk_type == SOCK_SEQPACKET && (flags & MSG_TRUNC))
 		copied = rlen;
+	if (flags & MSG_PEEK)
+		skb_unref(skb);
 
 	return copied;
+
+err_out:
+	if (!(flags & MSG_PEEK))
+		skb_queue_head(&sk->sk_receive_queue, skb);
+	else
+		skb_unref(skb);
+
+	return err;
 }
 
 static inline __poll_t iucv_accept_poll(struct sock *parent)

From a1f8609ff1f658e410f78d800ca947d57e51996a Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 20 Nov 2024 15:56:22 +0800
Subject: [PATCH 1423/1530] rtase: Refactor the rtase_check_mac_version_valid()
 function

Different hardware requires different configurations, but this distinction
was not made previously. Additionally, the error message was not clear
enough. Therefore, this patch will address the issues mentioned above.

Fixes: a36e9f5cfe9e ("rtase: Add support for a pci table in this module")
Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/realtek/rtase/rtase.h    |  7 ++++-
 .../net/ethernet/realtek/rtase/rtase_main.c   | 28 +++++++++++--------
 2 files changed, 22 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase.h b/drivers/net/ethernet/realtek/rtase/rtase.h
index 942f1e531a851..dbc3f92eebc48 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase.h
+++ b/drivers/net/ethernet/realtek/rtase/rtase.h
@@ -9,7 +9,10 @@
 #ifndef RTASE_H
 #define RTASE_H
 
-#define RTASE_HW_VER_MASK 0x7C800000
+#define RTASE_HW_VER_MASK     0x7C800000
+#define RTASE_HW_VER_906X_7XA 0x00800000
+#define RTASE_HW_VER_906X_7XC 0x04000000
+#define RTASE_HW_VER_907XD_V1 0x04800000
 
 #define RTASE_RX_DMA_BURST_256       4
 #define RTASE_TX_DMA_BURST_UNLIMITED 7
@@ -327,6 +330,8 @@ struct rtase_private {
 	u16 int_nums;
 	u16 tx_int_mit;
 	u16 rx_int_mit;
+
+	u32 hw_ver;
 };
 
 #define RTASE_LSO_64K 64000
diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 874994d9ceb95..d4ae0dd315d3a 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -1972,20 +1972,21 @@ static void rtase_init_software_variable(struct pci_dev *pdev,
 	tp->dev->max_mtu = RTASE_MAX_JUMBO_SIZE;
 }
 
-static bool rtase_check_mac_version_valid(struct rtase_private *tp)
+static int rtase_check_mac_version_valid(struct rtase_private *tp)
 {
-	u32 hw_ver = rtase_r32(tp, RTASE_TX_CONFIG_0) & RTASE_HW_VER_MASK;
-	bool known_ver = false;
+	int ret = -ENODEV;
 
-	switch (hw_ver) {
-	case 0x00800000:
-	case 0x04000000:
-	case 0x04800000:
-		known_ver = true;
+	tp->hw_ver = rtase_r32(tp, RTASE_TX_CONFIG_0) & RTASE_HW_VER_MASK;
+
+	switch (tp->hw_ver) {
+	case RTASE_HW_VER_906X_7XA:
+	case RTASE_HW_VER_906X_7XC:
+	case RTASE_HW_VER_907XD_V1:
+		ret = 0;
 		break;
 	}
 
-	return known_ver;
+	return ret;
 }
 
 static int rtase_init_board(struct pci_dev *pdev, struct net_device **dev_out,
@@ -2105,9 +2106,12 @@ static int rtase_init_one(struct pci_dev *pdev,
 	tp->pdev = pdev;
 
 	/* identify chip attached to board */
-	if (!rtase_check_mac_version_valid(tp))
-		return dev_err_probe(&pdev->dev, -ENODEV,
-				     "unknown chip version, contact rtase maintainers (see MAINTAINERS file)\n");
+	ret = rtase_check_mac_version_valid(tp);
+	if (ret != 0) {
+		dev_err(&pdev->dev,
+			"unknown chip version: 0x%08x, contact rtase maintainers (see MAINTAINERS file)\n",
+			tp->hw_ver);
+	}
 
 	rtase_init_software_variable(pdev, tp);
 	rtase_init_hardware(tp);

From c1fc14c4df801fe2d9ec3160b52fa63569ce164c Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 20 Nov 2024 15:56:23 +0800
Subject: [PATCH 1424/1530] rtase: Correct the speed for RTL907XD-V1

Previously, the reported speed was uniformly set to SPEED_5000, but the
RTL907XD-V1 actually operates at a speed of SPEED_10000. Therefore, this
patch makes the necessary correction.

Fixes: dd7f17c40fd1 ("rtase: Implement ethtool function")
Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index d4ae0dd315d3a..c1782e32f9c6a 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -1714,10 +1714,21 @@ static int rtase_get_settings(struct net_device *dev,
 			      struct ethtool_link_ksettings *cmd)
 {
 	u32 supported = SUPPORTED_MII | SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+	const struct rtase_private *tp = netdev_priv(dev);
 
 	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
 						supported);
-	cmd->base.speed = SPEED_5000;
+
+	switch (tp->hw_ver) {
+	case RTASE_HW_VER_906X_7XA:
+	case RTASE_HW_VER_906X_7XC:
+		cmd->base.speed = SPEED_5000;
+		break;
+	case RTASE_HW_VER_907XD_V1:
+		cmd->base.speed = SPEED_10000;
+		break;
+	}
+
 	cmd->base.duplex = DUPLEX_FULL;
 	cmd->base.port = PORT_MII;
 	cmd->base.autoneg = AUTONEG_DISABLE;

From a01cfcfda5cc787552b344cbc92f9c363c81ad4f Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 20 Nov 2024 15:56:24 +0800
Subject: [PATCH 1425/1530] rtase: Corrects error handling of the
 rtase_check_mac_version_valid()

Previously, when the hardware version ID was determined to be invalid,
only an error message was printed without any further handling. Therefore,
this patch makes the necessary corrections to address this.

Fixes: a36e9f5cfe9e ("rtase: Add support for a pci table in this module")
Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index c1782e32f9c6a..de7f11232593f 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -2122,6 +2122,7 @@ static int rtase_init_one(struct pci_dev *pdev,
 		dev_err(&pdev->dev,
 			"unknown chip version: 0x%08x, contact rtase maintainers (see MAINTAINERS file)\n",
 			tp->hw_ver);
+		goto err_out_release_board;
 	}
 
 	rtase_init_software_variable(pdev, tp);
@@ -2196,6 +2197,7 @@ static int rtase_init_one(struct pci_dev *pdev,
 		netif_napi_del(&ivec->napi);
 	}
 
+err_out_release_board:
 	rtase_release_board(pdev, dev, ioaddr);
 
 	return ret;

From 59c5e1411a0a13ebb930f4ebba495cc4eb14f8f2 Mon Sep 17 00:00:00 2001
From: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Date: Wed, 20 Nov 2024 16:38:18 +0800
Subject: [PATCH 1426/1530] net: stmmac: set initial EEE policy configuration

Set the initial eee_cfg values to have 'ethtool --show-eee ' display
the initial EEE configuration.

Fixes: 49168d1980e2 ("net: phy: Add phy_support_eee() indicating MAC support EEE")
Cc: <stable@vger.kernel.org>
Signed-off-by: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20241120083818.1079456-1-yong.liang.choong@linux.intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 3cdc3910f3a08..9b262cdad60b2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1177,6 +1177,9 @@ static int stmmac_init_phy(struct net_device *dev)
 			return -ENODEV;
 		}
 
+		if (priv->dma_cap.eee)
+			phy_support_eee(phydev);
+
 		ret = phylink_connect_phy(priv->phylink, phydev);
 	} else {
 		fwnode_handle_put(phy_fwnode);

From 00b5b7aab9e422d00d5a9d03d7e0760a76b5d57f Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 20 Nov 2024 09:51:07 +0000
Subject: [PATCH 1427/1530] net/ipv6: delete temporary address if mngtmpaddr is
 removed or unmanaged
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

RFC8981 section 3.4 says that existing temporary addresses must have their
lifetimes adjusted so that no temporary addresses should ever remain "valid"
or "preferred" longer than the incoming SLAAC Prefix Information. This would
strongly imply in Linux's case that if the "mngtmpaddr" address is deleted or
un-flagged as such, its corresponding temporary addresses must be cleared out
right away.

But now the temporary address is renewed even after ‘mngtmpaddr’ is removed
or becomes unmanaged as manage_tempaddrs() set temporary addresses
prefered/valid time to 0, and later in addrconf_verify_rtnl() all checkings
failed to remove the addresses. Fix this by deleting the temporary address
directly for these situations.

Fixes: 778964f2fdf0 ("ipv6/addrconf: fix timing bug in tempaddr regen")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/addrconf.c | 41 +++++++++++++++++++++++++++++------------
 1 file changed, 29 insertions(+), 12 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 96b5b2b0d5072..c489a1e6aec9a 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2570,6 +2570,24 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev)
 	return idev;
 }
 
+static void delete_tempaddrs(struct inet6_dev *idev,
+			     struct inet6_ifaddr *ifp)
+{
+	struct inet6_ifaddr *ift, *tmp;
+
+	write_lock_bh(&idev->lock);
+	list_for_each_entry_safe(ift, tmp, &idev->tempaddr_list, tmp_list) {
+		if (ift->ifpub != ifp)
+			continue;
+
+		in6_ifa_hold(ift);
+		write_unlock_bh(&idev->lock);
+		ipv6_del_addr(ift);
+		write_lock_bh(&idev->lock);
+	}
+	write_unlock_bh(&idev->lock);
+}
+
 static void manage_tempaddrs(struct inet6_dev *idev,
 			     struct inet6_ifaddr *ifp,
 			     __u32 valid_lft, __u32 prefered_lft,
@@ -3124,11 +3142,12 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags,
 			in6_ifa_hold(ifp);
 			read_unlock_bh(&idev->lock);
 
-			if (!(ifp->flags & IFA_F_TEMPORARY) &&
-			    (ifa_flags & IFA_F_MANAGETEMPADDR))
-				manage_tempaddrs(idev, ifp, 0, 0, false,
-						 jiffies);
 			ipv6_del_addr(ifp);
+
+			if (!(ifp->flags & IFA_F_TEMPORARY) &&
+			    (ifp->flags & IFA_F_MANAGETEMPADDR))
+				delete_tempaddrs(idev, ifp);
+
 			addrconf_verify_rtnl(net);
 			if (ipv6_addr_is_multicast(pfx)) {
 				ipv6_mc_config(net->ipv6.mc_autojoin_sk,
@@ -4952,14 +4971,12 @@ static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp,
 	}
 
 	if (was_managetempaddr || ifp->flags & IFA_F_MANAGETEMPADDR) {
-		if (was_managetempaddr &&
-		    !(ifp->flags & IFA_F_MANAGETEMPADDR)) {
-			cfg->valid_lft = 0;
-			cfg->preferred_lft = 0;
-		}
-		manage_tempaddrs(ifp->idev, ifp, cfg->valid_lft,
-				 cfg->preferred_lft, !was_managetempaddr,
-				 jiffies);
+		if (was_managetempaddr && !(ifp->flags & IFA_F_MANAGETEMPADDR))
+			delete_tempaddrs(ifp->idev, ifp);
+		else
+			manage_tempaddrs(ifp->idev, ifp, cfg->valid_lft,
+					 cfg->preferred_lft, !was_managetempaddr,
+					 jiffies);
 	}
 
 	addrconf_verify_rtnl(net);

From f6e1dcd6444485356d1df9d29df702acc7bba00c Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 20 Nov 2024 09:51:08 +0000
Subject: [PATCH 1428/1530] selftests/rtnetlink.sh: add mngtempaddr test

Add a test to check the temporary address could be added/removed
correctly when mngtempaddr is set or removed/unmanaged.

Signed-off-by: Sam Edwards <cfsworks@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/rtnetlink.sh | 95 ++++++++++++++++++++++++
 1 file changed, 95 insertions(+)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 7f05b5f9b76f6..2e8243a65b507 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -29,6 +29,7 @@ ALL_TESTS="
 	kci_test_bridge_parent_id
 	kci_test_address_proto
 	kci_test_enslave_bonding
+	kci_test_mngtmpaddr
 "
 
 devdummy="test-dummy0"
@@ -44,6 +45,7 @@ check_err()
 	if [ $ret -eq 0 ]; then
 		ret=$1
 	fi
+	[ -n "$2" ] && echo "$2"
 }
 
 # same but inverted -- used when command must fail for test to pass
@@ -1239,6 +1241,99 @@ kci_test_enslave_bonding()
 	ip netns del "$testns"
 }
 
+# Called to validate the addresses on $IFNAME:
+#
+# 1. Every `temporary` address must have a matching `mngtmpaddr`
+# 2. Every `mngtmpaddr` address must have some un`deprecated` `temporary`
+#
+# If the mngtmpaddr or tempaddr checking failed, return 0 and stop slowwait
+validate_mngtmpaddr()
+{
+	local dev=$1
+	local prefix=""
+	local addr_list=$(ip -j -n $testns addr show dev ${dev})
+	local temp_addrs=$(echo ${addr_list} | \
+		jq -r '.[].addr_info[] | select(.temporary == true) | .local')
+	local mng_prefixes=$(echo ${addr_list} | \
+		jq -r '.[].addr_info[] | select(.mngtmpaddr == true) | .local' | \
+		cut -d: -f1-4 | tr '\n' ' ')
+	local undep_prefixes=$(echo ${addr_list} | \
+		jq -r '.[].addr_info[] | select(.temporary == true and .deprecated != true) | .local' | \
+		cut -d: -f1-4 | tr '\n' ' ')
+
+	# 1. All temporary addresses (temp and dep) must have a matching mngtmpaddr
+	for address in ${temp_addrs}; do
+		prefix=$(echo ${address} | cut -d: -f1-4)
+		if [[ ! " ${mng_prefixes} " =~ " $prefix " ]]; then
+			check_err 1 "FAIL: Temporary $address with no matching mngtmpaddr!";
+			return 0
+		fi
+	done
+
+	# 2. All mngtmpaddr addresses must have a temporary address (not dep)
+	for prefix in ${mng_prefixes}; do
+		if [[ ! " ${undep_prefixes} " =~ " $prefix " ]]; then
+			check_err 1 "FAIL: No undeprecated temporary in $prefix!";
+			return 0
+		fi
+	done
+
+	return 1
+}
+
+kci_test_mngtmpaddr()
+{
+	local ret=0
+
+	setup_ns testns
+	if [ $? -ne 0 ]; then
+		end_test "SKIP mngtmpaddr tests: cannot add net namespace $testns"
+		return $ksft_skip
+	fi
+
+	# 1. Create a dummy Ethernet interface
+	run_cmd ip -n $testns link add ${devdummy} type dummy
+	run_cmd ip -n $testns link set ${devdummy} up
+	run_cmd ip netns exec $testns sysctl -w net.ipv6.conf.${devdummy}.use_tempaddr=1
+	run_cmd ip netns exec $testns sysctl -w net.ipv6.conf.${devdummy}.temp_prefered_lft=10
+	run_cmd ip netns exec $testns sysctl -w net.ipv6.conf.${devdummy}.temp_valid_lft=25
+	run_cmd ip netns exec $testns sysctl -w net.ipv6.conf.${devdummy}.max_desync_factor=1
+
+	# 2. Create several mngtmpaddr addresses on that interface.
+	# with temp_*_lft configured to be pretty short (10 and 35 seconds
+	# for prefer/valid respectively)
+	for i in $(seq 1 9); do
+		run_cmd ip -n $testns addr add 2001:db8:7e57:${i}::1/64 mngtmpaddr dev ${devdummy}
+	done
+
+	# 3. Confirm that a preferred temporary address exists for each mngtmpaddr
+	# address at all times, polling once per second for 30 seconds.
+	slowwait 30 validate_mngtmpaddr ${devdummy}
+
+	# 4. Delete each mngtmpaddr address, one at a time (alternating between
+	# deleting and merely un-mngtmpaddr-ing), and confirm that the other
+	# mngtmpaddr addresses still have preferred temporaries.
+	for i in $(seq 1 9); do
+		(( $i % 4 == 0 )) && mng_flag="mngtmpaddr" || mng_flag=""
+		if (( $i % 2 == 0 )); then
+			run_cmd ip -n $testns addr del 2001:db8:7e57:${i}::1/64 $mng_flag dev ${devdummy}
+		else
+			run_cmd ip -n $testns addr change 2001:db8:7e57:${i}::1/64 dev ${devdummy}
+		fi
+		# the temp addr should be deleted
+		validate_mngtmpaddr ${devdummy}
+	done
+
+	if [ $ret -ne 0 ]; then
+		end_test "FAIL: mngtmpaddr add/remove incorrect"
+	else
+		end_test "PASS: mngtmpaddr add/remove correctly"
+	fi
+
+	ip netns del "$testns"
+	return $ret
+}
+
 kci_test_rtnl()
 {
 	local current_test

From c66f759832a83cb273ba5a55c66dcc99384efa74 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 25 Nov 2024 13:50:21 -0800
Subject: [PATCH 1429/1530] fs_parser: update mount_api doc to match function
 signature

Add the missing 'name' parameter to the mount_api documentation for
fs_validate_description().

Fixes: 96cafb9ccb15 ("fs_parser: remove fs_parameter_description name field")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20241125215021.231758-1-rdunlap@infradead.org
Cc: Eric Sandeen <sandeen@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: linux-doc@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 Documentation/filesystems/mount_api.rst | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/filesystems/mount_api.rst b/Documentation/filesystems/mount_api.rst
index 317934c9e8fca..d92c276f1575a 100644
--- a/Documentation/filesystems/mount_api.rst
+++ b/Documentation/filesystems/mount_api.rst
@@ -770,7 +770,8 @@ process the parameters it is given.
 
    * ::
 
-       bool fs_validate_description(const struct fs_parameter_description *desc);
+       bool fs_validate_description(const char *name,
+                                    const struct fs_parameter_description *desc);
 
      This performs some validation checks on a parameter description.  It
      returns true if the description is good and false if it is not.  It will

From 9cc8d0ecdd2aad42e377e971e3bb114339df609e Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Thu, 21 Nov 2024 11:31:52 -0800
Subject: [PATCH 1430/1530] net: mdio-ipq4019: add missing error check

If an optional resource is found but fails to remap, return on failure.
Avoids any potential problems when using the iomapped resource as the
assumption is that it's available.

Fixes: 23a890d493e3 ("net: mdio: Add the reset function for IPQ MDIO driver")
Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20241121193152.8966-1-rosenp@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/mdio/mdio-ipq4019.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/mdio/mdio-ipq4019.c b/drivers/net/mdio/mdio-ipq4019.c
index dd3ed2d6430b1..d9a94df482d9f 100644
--- a/drivers/net/mdio/mdio-ipq4019.c
+++ b/drivers/net/mdio/mdio-ipq4019.c
@@ -352,8 +352,11 @@ static int ipq4019_mdio_probe(struct platform_device *pdev)
 	/* The platform resource is provided on the chipset IPQ5018 */
 	/* This resource is optional */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	if (res)
+	if (res) {
 		priv->eth_ldo_rdy = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(priv->eth_ldo_rdy))
+			return PTR_ERR(priv->eth_ldo_rdy);
+	}
 
 	bus->name = "ipq4019_mdio";
 	bus->read = ipq4019_mdio_read_c22;

From e67e0eb6a98b261caf45048f9eb95fd7609289c0 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Fri, 22 Nov 2024 15:47:47 +0800
Subject: [PATCH 1431/1530] LoongArch: Explicitly specify code model in
 Makefile

LoongArch's toolchain may change the default code model from normal to
medium. This is unnecessary for kernel, and generates some relocations
which cannot be handled by the module loader. So explicitly specify the
code model to normal in Makefile (for Rust 'normal' is 'small').

Cc: stable@vger.kernel.org
Tested-by: Haiyong Sun <sunhaiyong@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index ae3f80622f4c6..567bd122a9ee4 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -59,7 +59,7 @@ endif
 
 ifdef CONFIG_64BIT
 ld-emul			= $(64bit-emul)
-cflags-y		+= -mabi=lp64s
+cflags-y		+= -mabi=lp64s -mcmodel=normal
 endif
 
 cflags-y			+= -pipe $(CC_FLAGS_NO_FPU)
@@ -104,7 +104,7 @@ ifdef CONFIG_OBJTOOL
 KBUILD_CFLAGS			+= -fno-jump-tables
 endif
 
-KBUILD_RUSTFLAGS		+= --target=loongarch64-unknown-none-softfloat
+KBUILD_RUSTFLAGS		+= --target=loongarch64-unknown-none-softfloat -Ccode-model=small
 KBUILD_RUSTFLAGS_KERNEL		+= -Zdirect-access-external-data=yes
 KBUILD_RUSTFLAGS_MODULE		+= -Zdirect-access-external-data=no
 

From 947d5d036c788156f09e83e7f16322ffe8124384 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Fri, 22 Nov 2024 15:47:47 +0800
Subject: [PATCH 1432/1530] LoongArch: Fix build failure with GCC 15
 (-std=gnu23)

Whenever I try to build the kernel with upcoming GCC 15 which defaults
to -std=gnu23 I get a build failure:

  CC      arch/loongarch/vdso/vgetcpu.o
In file included from ./include/uapi/linux/posix_types.h:5,
                 from ./include/uapi/linux/types.h:14,
                 from ./include/linux/types.h:6,
                 from ./include/linux/kasan-checks.h:5,
                 from ./include/asm-generic/rwonce.h:26,
                 from ./arch/loongarch/include/generated/asm/rwonce.h:1,
                 from ./include/linux/compiler.h:317,
                 from ./include/asm-generic/bug.h:5,
                 from ./arch/loongarch/include/asm/bug.h:60,
                 from ./include/linux/bug.h:5,
                 from ./include/linux/mmdebug.h:5,
                 from ./include/linux/mm.h:6,
                 from ./arch/loongarch/include/asm/vdso.h:10,
                 from arch/loongarch/vdso/vgetcpu.c:6:
./include/linux/stddef.h:11:9: error: expected identifier before 'false'
   11 |         false   = 0,
      |         ^~~~~
./include/linux/types.h:35:33: error: two or more data types in declaration specifiers
   35 | typedef _Bool                   bool;
      |                                 ^~~~
./include/linux/types.h:35:1: warning: useless type name in empty declaration
   35 | typedef _Bool                   bool;
      | ^~~~~~~

The kernel builds explicitly with -std=gnu11 in top Makefile, but
arch/loongarch/vdso does not use KBUILD_CFLAGS from the rest of the
kernel, just add -std=gnu11 flag to arch/loongarch/vdso/Makefile.

By the way, commit e8c07082a810 ("Kbuild: move to -std=gnu11") did a
similar change for arch/arm64/kernel/vdso32/Makefile.

Fixes: c6b99bed6b8f ("LoongArch: Add VDSO and VSYSCALL support")
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/vdso/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
index 40c1175823d61..fdde1bcd4e266 100644
--- a/arch/loongarch/vdso/Makefile
+++ b/arch/loongarch/vdso/Makefile
@@ -19,7 +19,7 @@ ccflags-vdso := \
 cflags-vdso := $(ccflags-vdso) \
 	-isystem $(shell $(CC) -print-file-name=include) \
 	$(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \
-	-O2 -g -fno-strict-aliasing -fno-common -fno-builtin \
+	-std=gnu11 -O2 -g -fno-strict-aliasing -fno-common -fno-builtin \
 	-fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
 	$(call cc-option, -fno-asynchronous-unwind-tables) \
 	$(call cc-option, -fno-stack-protector)

From 73c359d1d356cf10236ccd358bd55edab33e9424 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Fri, 22 Nov 2024 15:47:48 +0800
Subject: [PATCH 1433/1530] LoongArch: BPF: Sign-extend return values

(1) Description of Problem:

When testing BPF JIT with the latest compiler toolchains on LoongArch,
there exist some strange failed test cases, dmesg shows something like
this:

  # dmesg -t | grep FAIL | head -1
  ... ret -3 != -3 (0xfffffffd != 0xfffffffd)FAIL ...

(2) Steps to Reproduce:

  # echo 1 > /proc/sys/net/core/bpf_jit_enable
  # modprobe test_bpf

(3) Additional Info:

There are no failed test cases compiled with the lower version of GCC
such as 13.3.0, while the problems only appear with higher version of
GCC such as 14.2.0.

This is because the problems were hidden by the lower version of GCC due
to redundant sign extension instructions generated by compiler, but with
optimization of higher version of GCC, the sign extension instructions
have been removed.

(4) Root Cause Analysis:

The LoongArch architecture does not expose sub-registers, and hold all
32-bit values in a sign-extended format. While BPF, on the other hand,
exposes sub-registers, and use zero-extension (similar to arm64/x86).

This has led to some subtle bugs, where a BPF JITted program has not
sign-extended the a0 register (return value in LoongArch land), passed
the return value up the kernel, for example:

  | int from_bpf(void);
  |
  | long foo(void)
  | {
  |    return from_bpf();
  | }

Here, a0 would be 0xffffffff instead of the expected 0xffffffffffffffff.

Internally, the LoongArch JIT uses a5 as a dedicated register for BPF
return values. That is to say, the LoongArch BPF uses a5 for BPF return
values, which are zero-extended, whereas the LoongArch ABI uses a0 which
is sign-extended.

(5) Final Solution:

Keep a5 zero-extended, but explicitly sign-extend a0 (which is used
outside BPF land). Because libbpf currently defines the return value
of an ebpf program as a 32-bit unsigned integer, just use addi.w to
extend bit 31 into bits 63 through 32 of a5 to a0. This is similar to
commit 2f1b0d3d7331 ("riscv, bpf: Sign-extend return values").

Fixes: 5dc615520c4d ("LoongArch: Add BPF JIT support")
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/net/bpf_jit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index 7dbefd4ba2107..dd350cba1252f 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -179,7 +179,7 @@ static void __build_epilogue(struct jit_ctx *ctx, bool is_tail_call)
 
 	if (!is_tail_call) {
 		/* Set return value */
-		move_reg(ctx, LOONGARCH_GPR_A0, regmap[BPF_REG_0]);
+		emit_insn(ctx, addiw, LOONGARCH_GPR_A0, regmap[BPF_REG_0], 0);
 		/* Return to the caller */
 		emit_insn(ctx, jirl, LOONGARCH_GPR_RA, LOONGARCH_GPR_ZERO, 0);
 	} else {

From af4b67da652214f06fde48cca7bb438fa829741f Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Fri, 22 Nov 2024 15:47:48 +0800
Subject: [PATCH 1434/1530] LoongArch: Reduce min_delta for the arch clockevent
 device

Now the min_delta is 0x600 (1536) for LoongArch's constant clockevent
device. For a 100MHz hardware timer this means ~15us. This is a little
big, especially for PREEMPT_RT enabled kernels. So reduce it to 100 for
PREEMPT_RT kernel, and 1000 for others (we don't want too small values
to affect performance).

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/time.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index 46d7d40c87e38..a07d7eff4dc5f 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -127,7 +127,11 @@ void sync_counter(void)
 int constant_clockevent_init(void)
 {
 	unsigned int cpu = smp_processor_id();
-	unsigned long min_delta = 0x600;
+#ifdef CONFIG_PREEMPT_RT
+	unsigned long min_delta = 100;
+#else
+	unsigned long min_delta = 1000;
+#endif
 	unsigned long max_delta = (1UL << 48) - 1;
 	struct clock_event_device *cd;
 	static int irq = 0, timer_irq_installed = 0;

From 88fd2b70120d52c1010257d36776876941375490 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Fri, 22 Nov 2024 15:47:48 +0800
Subject: [PATCH 1435/1530] LoongArch: Fix sleeping in atomic context for
 PREEMPT_RT

Commit bab1c299f3945ffe79 ("LoongArch: Fix sleeping in atomic context in
setup_tlb_handler()") changes the gfp flag from GFP_KERNEL to GFP_ATOMIC
for alloc_pages_node(). However, for PREEMPT_RT kernels we can still get
a "sleeping in atomic context" error:

[    0.372259] BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48
[    0.372266] in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 0, name: swapper/1
[    0.372268] preempt_count: 1, expected: 0
[    0.372270] RCU nest depth: 1, expected: 1
[    0.372272] 3 locks held by swapper/1/0:
[    0.372274]  #0: 900000000c9f5e60 (&pcp->lock){+.+.}-{3:3}, at: get_page_from_freelist+0x524/0x1c60
[    0.372294]  #1: 90000000087013b8 (rcu_read_lock){....}-{1:3}, at: rt_spin_trylock+0x50/0x140
[    0.372305]  #2: 900000047fffd388 (&zone->lock){+.+.}-{3:3}, at: __rmqueue_pcplist+0x30c/0xea0
[    0.372314] irq event stamp: 0
[    0.372316] hardirqs last  enabled at (0): [<0000000000000000>] 0x0
[    0.372322] hardirqs last disabled at (0): [<9000000005947320>] copy_process+0x9c0/0x26e0
[    0.372329] softirqs last  enabled at (0): [<9000000005947320>] copy_process+0x9c0/0x26e0
[    0.372335] softirqs last disabled at (0): [<0000000000000000>] 0x0
[    0.372341] CPU: 1 UID: 0 PID: 0 Comm: swapper/1 Not tainted 6.12.0-rc7+ #1891
[    0.372346] Hardware name: Loongson Loongson-3A5000-7A1000-1w-CRB/Loongson-LS3A5000-7A1000-1w-CRB, BIOS vUDK2018-LoongArch-V2.0.0-prebeta9 10/21/2022
[    0.372349] Stack : 0000000000000089 9000000005a0db9c 90000000071519c8 9000000100388000
[    0.372486]         900000010038b890 0000000000000000 900000010038b898 9000000007e53788
[    0.372492]         900000000815bcc8 900000000815bcc0 900000010038b700 0000000000000001
[    0.372498]         0000000000000001 4b031894b9d6b725 00000000055ec000 9000000100338fc0
[    0.372503]         00000000000000c4 0000000000000001 000000000000002d 0000000000000003
[    0.372509]         0000000000000030 0000000000000003 00000000055ec000 0000000000000003
[    0.372515]         900000000806d000 9000000007e53788 00000000000000b0 0000000000000004
[    0.372521]         0000000000000000 0000000000000000 900000000c9f5f10 0000000000000000
[    0.372526]         90000000076f12d8 9000000007e53788 9000000005924778 0000000000000000
[    0.372532]         00000000000000b0 0000000000000004 0000000000000000 0000000000070000
[    0.372537]         ...
[    0.372540] Call Trace:
[    0.372542] [<9000000005924778>] show_stack+0x38/0x180
[    0.372548] [<90000000071519c4>] dump_stack_lvl+0x94/0xe4
[    0.372555] [<900000000599b880>] __might_resched+0x1a0/0x260
[    0.372561] [<90000000071675cc>] rt_spin_lock+0x4c/0x140
[    0.372565] [<9000000005cbb768>] __rmqueue_pcplist+0x308/0xea0
[    0.372570] [<9000000005cbed84>] get_page_from_freelist+0x564/0x1c60
[    0.372575] [<9000000005cc0d98>] __alloc_pages_noprof+0x218/0x1820
[    0.372580] [<900000000593b36c>] tlb_init+0x1ac/0x298
[    0.372585] [<9000000005924b74>] per_cpu_trap_init+0x114/0x140
[    0.372589] [<9000000005921964>] cpu_probe+0x4e4/0xa60
[    0.372592] [<9000000005934874>] start_secondary+0x34/0xc0
[    0.372599] [<900000000715615c>] smpboot_entry+0x64/0x6c

This is because in PREEMPT_RT kernels normal spinlocks are replaced by
rt spinlocks and rt_spin_lock() will cause sleeping. Fix it by disabling
NUMA optimization completely for PREEMPT_RT kernels.

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/mm/tlb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c
index 5ac9beb5f0935..3b427b319db21 100644
--- a/arch/loongarch/mm/tlb.c
+++ b/arch/loongarch/mm/tlb.c
@@ -289,7 +289,7 @@ static void setup_tlb_handler(int cpu)
 		/* Avoid lockdep warning */
 		rcutree_report_cpu_starting(cpu);
 
-#ifdef CONFIG_NUMA
+#if defined(CONFIG_NUMA) && !defined(CONFIG_PREEMPT_RT)
 		vec_sz = sizeof(exception_handlers);
 
 		if (pcpu_handlers[cpu])

From 826d2af6949f9c48fb5a249be0645e4b48b01a53 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Fri, 22 Nov 2024 15:47:53 +0800
Subject: [PATCH 1436/1530] LoongArch: Select HAVE_POSIX_CPU_TIMERS_TASK_WORK

Move POSIX CPU timer expiry and signal delivery into task context to
allow PREEMPT_RT setups to coexist with KVM.

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index d9fce0fd475a0..2443d5a80e0d2 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -155,6 +155,7 @@ config LOONGARCH
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select HAVE_PREEMPT_DYNAMIC_KEY
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE if UNWINDER_ORC

From be2ea982bb83a34003909bdfcac1d107339f5dcf Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Fri, 22 Nov 2024 15:47:53 +0800
Subject: [PATCH 1437/1530] LoongArch: Allow to enable PREEMPT_RT

It is really time.

LoongArch has all the required architecture related changes, that have
been identified over time, in order to enable PREEMPT_RT. With the recent
printk changes, the last known road block has been addressed.

Allow to enable PREEMPT_RT on LoongArch.

Below are the latency data from cyclictest on a 4-core Loongson-3A5000
machine, with a "make -j8" kernel building workload in the background.

1. PREEMPT kernel with default configuration:

./cyclictest -a -t -m -i200 -d0 -p99
policy: fifo: loadavg: 8.78 8.96 8.64 10/296 64800
T: 0 ( 4592) P:99 I:200 C:14838617 Min:   3 Act:    6 Avg:    8 Max:    844
T: 1 ( 4593) P:99 I:200 C:14838765 Min:   3 Act:    9 Avg:    8 Max:    909
T: 2 ( 4594) P:99 I:200 C:14838510 Min:   3 Act:    7 Avg:    8 Max:    832
T: 3 ( 4595) P:99 I:200 C:14838631 Min:   3 Act:    8 Avg:    8 Max:    931

2. PREEMPT_RT kernel with default configuration:

./cyclictest -a -t -m -i200 -d0 -p99
policy: fifo: loadavg: 10.38 10.47 10.35 9/336 77788
T: 0 ( 3941) P:99 I:200 C:19439626 Min:   3 Act:   12 Avg:    8 Max:    227
T: 1 ( 3942) P:99 I:200 C:19439624 Min:   2 Act:   11 Avg:    8 Max:    184
T: 2 ( 3943) P:99 I:200 C:19439623 Min:   3 Act:    4 Avg:    7 Max:    223
T: 3 ( 3944) P:99 I:200 C:19439623 Min:   2 Act:   10 Avg:    7 Max:    226

3. PREEMPT_RT kernel with tuned configuration:

./cyclictest -a -t -m -i200 -d0 -p99
policy: fifo: loadavg: 10.52 10.66 10.62 12/334 109397
T: 0 ( 4765) P:99 I:200 C:29335186 Min:   3 Act:    6 Avg:    8 Max:     62
T: 1 ( 4766) P:99 I:200 C:29335185 Min:   3 Act:   10 Avg:    8 Max:     52
T: 2 ( 4767) P:99 I:200 C:29335184 Min:   3 Act:    8 Avg:    8 Max:     64
T: 3 ( 4768) P:99 I:200 C:29335183 Min:   3 Act:   12 Avg:    8 Max:     53

Main instruments of tuned configuration include: Disable the boot rom
space in BIOS, in order to avoid kernel's speculative access to low-
speed memory (i.e. boot rom space); Disable CPUFreq scaling; Disable
RTC synchronization in the ntpd/chronyd service (also avoid other RTC
accesses when running low-latency workloads).

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 2443d5a80e0d2..d5d3679057a17 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -66,6 +66,7 @@ config LOONGARCH
 	select ARCH_SUPPORTS_LTO_CLANG
 	select ARCH_SUPPORTS_LTO_CLANG_THIN
 	select ARCH_SUPPORTS_NUMA_BALANCING
+	select ARCH_SUPPORTS_RT
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_QUEUED_RWLOCKS

From 704f06eeff65f898364981e6803e587cd941a3ed Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Fri, 22 Nov 2024 15:47:53 +0800
Subject: [PATCH 1438/1530] LoongArch: Allow to enable PREEMPT_LAZY

LoongArch has supported PREEMPT_RT now. It uses GENERIC_ENTRY, so just
add the TIF bit (TIF_NEED_RESCHED_LAZY) related definitions and select
the Kconfig symbol (ARCH_HAS_PREEMPT_LAZY) is enough to make it go.

Signed-off-by: Xi Ruoyao <xry111@xry111.site>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Kconfig                   | 1 +
 arch/loongarch/include/asm/thread_info.h | 8 +++++---
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index d5d3679057a17..dae3a9104ca65 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -23,6 +23,7 @@ config LOONGARCH
 	select ARCH_HAS_KERNEL_FPU_SUPPORT if CPU_HAS_FPU
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+	select ARCH_HAS_PREEMPT_LAZY
 	select ARCH_HAS_PTE_DEVMAP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SET_MEMORY
diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h
index 8bf0e6f515466..4f5a9441754e3 100644
--- a/arch/loongarch/include/asm/thread_info.h
+++ b/arch/loongarch/include/asm/thread_info.h
@@ -66,8 +66,9 @@ register unsigned long current_stack_pointer __asm__("$sp");
  * - pending work-to-be-done flags are in LSW
  * - other flags in MSW
  */
-#define TIF_SIGPENDING		1	/* signal pending */
-#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
+#define TIF_NEED_RESCHED	0	/* rescheduling necessary */
+#define TIF_NEED_RESCHED_LAZY	1	/* lazy rescheduling necessary */
+#define TIF_SIGPENDING		2	/* signal pending */
 #define TIF_NOTIFY_RESUME	3	/* callback before returning to user */
 #define TIF_NOTIFY_SIGNAL	4	/* signal notifications exist */
 #define TIF_RESTORE_SIGMASK	5	/* restore signal mask in do_signal() */
@@ -88,8 +89,9 @@ register unsigned long current_stack_pointer __asm__("$sp");
 #define TIF_LBT_CTX_LIVE	20	/* LBT context must be preserved */
 #define TIF_PATCH_PENDING	21	/* pending live patching update */
 
-#define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
+#define _TIF_NEED_RESCHED_LAZY	(1<<TIF_NEED_RESCHED_LAZY)
+#define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
 #define _TIF_NOTIFY_SIGNAL	(1<<TIF_NOTIFY_SIGNAL)
 #define _TIF_NOHZ		(1<<TIF_NOHZ)

From b7915af6e73b2ec896f3c811a1dba4348269d272 Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Fri, 22 Nov 2024 15:47:58 +0800
Subject: [PATCH 1439/1530] LoongArch: dts: Add I2S support to Loongson-2K1000

The module is supported, adding it.

Not all Loongson-2K1000 boards have an i2s interface, here is an example
of enabling it:

sound {
	compatible = "loongson,ls-audio-card";
	model = "Loongson-ASoC";
	mclk-fs = <512>;

	cpu {
		sound-dai = <&i2s>;
	};

	codec {
		sound-dai = <&uda1342>;
	};
};

&apbdma2 {
	status = "okay";
};

&apbdma3 {
	status = "okay";
};

&i2c3 {
	status = "okay";

	pinctrl-0 = <&i2c1_pins_default>;
	pinctrl-names = "default";

	#address-cells = <1>;
	#size-cells = <0>;

	uda1342: codec@1a {
		compatible = "nxp,uda1342";
		reg = <0x1a>;
		#sound-dai-cells = <0>;
	};
};

&i2s {
	status = "okay";

	pinctrl-0 = <&hda_pins_default>;
	pinctrl-names = "default";
};

Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/boot/dts/loongson-2k1000.dtsi | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi
index 92180140eb56e..8dff2aa524171 100644
--- a/arch/loongarch/boot/dts/loongson-2k1000.dtsi
+++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi
@@ -266,7 +266,7 @@
 			status = "disabled";
 		};
 
-		dma-controller@1fe00c20 {
+		apbdma2: dma-controller@1fe00c20 {
 			compatible = "loongson,ls2k1000-apbdma";
 			reg = <0x0 0x1fe00c20 0x0 0x8>;
 			interrupt-parent = <&liointc1>;
@@ -276,7 +276,7 @@
 			status = "disabled";
 		};
 
-		dma-controller@1fe00c30 {
+		apbdma3: dma-controller@1fe00c30 {
 			compatible = "loongson,ls2k1000-apbdma";
 			reg = <0x0 0x1fe00c30 0x0 0x8>;
 			interrupt-parent = <&liointc1>;
@@ -352,6 +352,19 @@
 			status = "disabled";
 		};
 
+		i2s: i2s@1fe2d000 {
+			compatible = "loongson,ls2k1000-i2s";
+			reg = <0 0x1fe2d000 0 0x14>,
+			      <0 0x1fe00438 0 0x8>;
+			interrupt-parent = <&liointc0>;
+			interrupts = <5 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
+			dmas = <&apbdma2 0>, <&apbdma3 0>;
+			dma-names = "tx", "rx";
+			#sound-dai-cells = <0>;
+			status = "disabled";
+		};
+
 		spi0: spi@1fff0220 {
 			compatible = "loongson,ls2k1000-spi";
 			reg = <0x0 0x1fff0220 0x0 0x10>;

From 900f6267e9e39f9f601f5eaf0ea32d620b9130d2 Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Fri, 22 Nov 2024 15:47:58 +0800
Subject: [PATCH 1440/1530] LoongArch: dts: Add I2S support to Loongson-2K2000

The module is supported, adding it.

Not all Loongson-2K1000 boards have an i2s interface, here is an example
of enabling it:

sound {
	compatible = "loongson,ls-audio-card";
	model = "Loongson-ASoC";
	mclk-fs = <512>;

	cpu {
		sound-dai = <&i2s>;
	};

	codec {
		sound-dai = <&es8323>;
	};
};

&i2c1 {
	status = "okay";
	#address-cells = <1>;
	#size-cells = <0>;

	es8323:es8323@10 {
		compatible = "everest,es8323";
		reg = <0x10>;
		#sound-dai-cells = <0>;
	};
};

&i2s {
	status = "okay";

	clock-frequency = <175000000>;
	#sound-dai-cells = <0>;
};

Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/boot/dts/loongson-2k2000.dtsi | 22 ++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi
index 0953c57078256..b4ff55a33e90b 100644
--- a/arch/loongarch/boot/dts/loongson-2k2000.dtsi
+++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi
@@ -173,6 +173,22 @@
 			status = "disabled";
 		};
 
+		i2c@1fe00120 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1fe00120 0x0 0x8>;
+			interrupt-parent = <&liointc>;
+			interrupts = <8 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		i2c@1fe00130 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1fe00130 0x0 0x8>;
+			interrupt-parent = <&liointc>;
+			interrupts = <9 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
 		uart0: serial@1fe001e0 {
 			compatible = "ns16550a";
 			reg = <0x0 0x1fe001e0 0x0 0x10>;
@@ -243,9 +259,11 @@
 				status = "disabled";
 			};
 
-			hda@7,0 {
+			i2s@7,0 {
 				reg = <0x3800 0x0 0x0 0x0 0x0>;
-				interrupts = <58 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <78 IRQ_TYPE_LEVEL_HIGH>,
+					     <79 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "tx", "rx";
 				interrupt-parent = <&pic>;
 				status = "disabled";
 			};

From 3c272a7551af1c10f6dbba0e71add7dccc7733fa Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 26 Nov 2024 18:06:54 +0800
Subject: [PATCH 1441/1530] LoongArch: Update Loongson-3 default config file

1, Enable ACPI_BGRT.
2, Enable MODULE COMPRESS.
3, Enable common DM targets.
4, Enable FS_ENCRYPTION and FS_VERITY.
5, Enable CPUFreq governors and drivers.
6, Enable PVPANIC MMIO and PCI drivers.
7, Enable some HID input drivers.
8, Enable some ASoC codec drivers.
9, Enable some Realtek WiFi drivers.
10, Remove some obsolete config options.

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/configs/loongson3_defconfig | 91 +++++++++++++++++++---
 1 file changed, 81 insertions(+), 10 deletions(-)

diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index 75b366407a60a..298177a663542 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -1,4 +1,5 @@
 # CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_KERNEL_ZSTD=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_NO_HZ=y
@@ -70,6 +71,14 @@ CONFIG_ACPI_IPMI=m
 CONFIG_ACPI_HOTPLUG_CPU=y
 CONFIG_ACPI_PCI_SLOT=y
 CONFIG_ACPI_HOTPLUG_MEMORY=y
+CONFIG_ACPI_BGRT=y
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_GOV_POWERSAVE=y
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
+CONFIG_CPU_FREQ_GOV_ONDEMAND=y
+CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
+CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y
+CONFIG_LOONGSON3_CPUFREQ=m
 CONFIG_VIRTUALIZATION=y
 CONFIG_KVM=m
 CONFIG_JUMP_LABEL=y
@@ -78,6 +87,9 @@ CONFIG_MODULE_FORCE_LOAD=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
+CONFIG_MODULE_COMPRESS=y
+CONFIG_MODULE_COMPRESS_ZSTD=y
+CONFIG_MODULE_DECOMPRESS=y
 CONFIG_BLK_DEV_ZONED=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
@@ -85,6 +97,8 @@ CONFIG_BLK_CGROUP_IOLATENCY=y
 CONFIG_BLK_CGROUP_FC_APPID=y
 CONFIG_BLK_CGROUP_IOCOST=y
 CONFIG_BLK_CGROUP_IOPRIO=y
+CONFIG_BLK_INLINE_ENCRYPTION=y
+CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_BSD_DISKLABEL=y
 CONFIG_UNIXWARE_DISKLABEL=y
@@ -413,7 +427,16 @@ CONFIG_PARPORT_PC=y
 CONFIG_PARPORT_SERIAL=y
 CONFIG_PARPORT_PC_FIFO=y
 CONFIG_ZRAM=m
+CONFIG_ZRAM_BACKEND_LZ4=y
+CONFIG_ZRAM_BACKEND_LZ4HC=y
+CONFIG_ZRAM_BACKEND_ZSTD=y
+CONFIG_ZRAM_BACKEND_DEFLATE=y
+CONFIG_ZRAM_BACKEND_842=y
+CONFIG_ZRAM_BACKEND_LZO=y
 CONFIG_ZRAM_DEF_COMP_ZSTD=y
+CONFIG_ZRAM_WRITEBACK=y
+CONFIG_ZRAM_MEMORY_TRACKING=y
+CONFIG_ZRAM_MULTI_COMP=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
@@ -433,6 +456,9 @@ CONFIG_NVME_TARGET_RDMA=m
 CONFIG_NVME_TARGET_FC=m
 CONFIG_NVME_TARGET_TCP=m
 CONFIG_EEPROM_AT24=m
+CONFIG_PVPANIC=y
+CONFIG_PVPANIC_MMIO=m
+CONFIG_PVPANIC_PCI=m
 CONFIG_BLK_DEV_SD=y
 CONFIG_BLK_DEV_SR=y
 CONFIG_CHR_DEV_SG=y
@@ -470,12 +496,10 @@ CONFIG_PATA_ATIIXP=y
 CONFIG_PATA_PCMCIA=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=m
-CONFIG_MD_LINEAR=m
 CONFIG_MD_RAID0=m
 CONFIG_MD_RAID1=m
 CONFIG_MD_RAID10=m
 CONFIG_MD_RAID456=m
-CONFIG_MD_MULTIPATH=m
 CONFIG_BCACHE=m
 CONFIG_BLK_DEV_DM=y
 CONFIG_DM_CRYPT=m
@@ -489,6 +513,16 @@ CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_MULTIPATH_QL=m
 CONFIG_DM_MULTIPATH_ST=m
+CONFIG_DM_MULTIPATH_HST=m
+CONFIG_DM_MULTIPATH_IOA=m
+CONFIG_DM_INIT=y
+CONFIG_DM_UEVENT=y
+CONFIG_DM_VERITY=m
+CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
+CONFIG_DM_VERITY_FEC=y
+CONFIG_DM_INTEGRITY=m
+CONFIG_DM_ZONED=m
+CONFIG_DM_VDO=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -500,6 +534,13 @@ CONFIG_NETDEVICES=y
 CONFIG_BONDING=m
 CONFIG_DUMMY=y
 CONFIG_WIREGUARD=m
+CONFIG_IFB=m
+CONFIG_NET_TEAM=m
+CONFIG_NET_TEAM_MODE_BROADCAST=m
+CONFIG_NET_TEAM_MODE_ROUNDROBIN=m
+CONFIG_NET_TEAM_MODE_RANDOM=m
+CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m
+CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
@@ -580,12 +621,14 @@ CONFIG_PPP_ASYNC=m
 CONFIG_PPP_SYNC_TTY=m
 CONFIG_USB_RTL8150=m
 CONFIG_USB_RTL8152=m
+CONFIG_USB_USBNET=m
 # CONFIG_USB_NET_AX8817X is not set
 # CONFIG_USB_NET_AX88179_178A is not set
 CONFIG_USB_NET_CDC_EEM=m
 CONFIG_USB_NET_HUAWEI_CDC_NCM=m
 CONFIG_USB_NET_CDC_MBIM=m
 # CONFIG_USB_NET_NET1080 is not set
+CONFIG_USB_NET_RNDIS_HOST=m
 # CONFIG_USB_BELKIN is not set
 # CONFIG_USB_ARMLINUX is not set
 # CONFIG_USB_NET_ZAURUS is not set
@@ -594,10 +637,11 @@ CONFIG_ATH9K_HTC=m
 CONFIG_IWLWIFI=m
 CONFIG_IWLDVM=m
 CONFIG_IWLMVM=m
-CONFIG_HOSTAP=m
 CONFIG_MT7601U=m
 CONFIG_RT2X00=m
 CONFIG_RT2800USB=m
+CONFIG_RTL8180=m
+CONFIG_RTL8187=m
 CONFIG_RTL8192CE=m
 CONFIG_RTL8192SE=m
 CONFIG_RTL8192DE=m
@@ -607,18 +651,26 @@ CONFIG_RTL8188EE=m
 CONFIG_RTL8192EE=m
 CONFIG_RTL8821AE=m
 CONFIG_RTL8192CU=m
+CONFIG_RTL8192DU=m
 # CONFIG_RTLWIFI_DEBUG is not set
 CONFIG_RTL8XXXU=m
 CONFIG_RTW88=m
 CONFIG_RTW88_8822BE=m
+CONFIG_RTW88_8822BU=m
 CONFIG_RTW88_8822CE=m
+CONFIG_RTW88_8822CU=m
 CONFIG_RTW88_8723DE=m
+CONFIG_RTW88_8723DU=m
 CONFIG_RTW88_8821CE=m
+CONFIG_RTW88_8821CU=m
 CONFIG_RTW89=m
+CONFIG_RTW89_8851BE=m
 CONFIG_RTW89_8852AE=m
+CONFIG_RTW89_8852BE=m
+CONFIG_RTW89_8852BTE=m
 CONFIG_RTW89_8852CE=m
+CONFIG_RTW89_8922AE=m
 CONFIG_ZD1211RW=m
-CONFIG_USB_NET_RNDIS_WLAN=m
 CONFIG_USB4_NET=m
 CONFIG_INPUT_MOUSEDEV=y
 CONFIG_INPUT_MOUSEDEV_PSAUX=y
@@ -651,6 +703,9 @@ CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_VIRTIO=m
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_PIIX4=y
+CONFIG_I2C_DESIGNWARE_CORE=y
+CONFIG_I2C_DESIGNWARE_SLAVE=y
+CONFIG_I2C_DESIGNWARE_PCI=y
 CONFIG_I2C_GPIO=y
 CONFIG_I2C_LS2X=y
 CONFIG_SPI=y
@@ -727,11 +782,22 @@ CONFIG_SND_HDA_CODEC_CONEXANT=y
 CONFIG_SND_USB_AUDIO=m
 CONFIG_SND_SOC=m
 CONFIG_SND_SOC_LOONGSON_CARD=m
+CONFIG_SND_SOC_ES7134=m
+CONFIG_SND_SOC_ES7241=m
+CONFIG_SND_SOC_ES8311=m
+CONFIG_SND_SOC_ES8316=m
+CONFIG_SND_SOC_ES8323=m
+CONFIG_SND_SOC_ES8326=m
+CONFIG_SND_SOC_ES8328_I2C=m
+CONFIG_SND_SOC_ES8328_SPI=m
+CONFIG_SND_SOC_UDA1334=m
+CONFIG_SND_SOC_UDA1342=m
 CONFIG_SND_VIRTIO=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 CONFIG_HID_A4TECH=m
 CONFIG_HID_CHERRY=m
+CONFIG_HID_ELAN=m
 CONFIG_HID_LOGITECH=m
 CONFIG_HID_LOGITECH_DJ=m
 CONFIG_LOGITECH_FF=y
@@ -740,7 +806,11 @@ CONFIG_LOGIG940_FF=y
 CONFIG_HID_MICROSOFT=m
 CONFIG_HID_MULTITOUCH=m
 CONFIG_HID_SUNPLUS=m
+CONFIG_HID_WACOM=m
 CONFIG_USB_HIDDEV=y
+CONFIG_I2C_HID_ACPI=m
+CONFIG_I2C_HID_OF=m
+CONFIG_I2C_HID_OF_ELAN=m
 CONFIG_USB=y
 CONFIG_USB_OTG=y
 CONFIG_USB_MON=y
@@ -852,6 +922,9 @@ CONFIG_F2FS_FS=m
 CONFIG_F2FS_FS_SECURITY=y
 CONFIG_F2FS_CHECK_FS=y
 CONFIG_F2FS_FS_COMPRESSION=y
+CONFIG_FS_ENCRYPTION=y
+CONFIG_FS_ENCRYPTION_INLINE_CRYPT=y
+CONFIG_FS_VERITY=y
 CONFIG_FANOTIFY=y
 CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_QUOTA=y
@@ -904,16 +977,14 @@ CONFIG_SQUASHFS_ZSTD=y
 CONFIG_MINIX_FS=m
 CONFIG_ROMFS_FS=m
 CONFIG_PSTORE=m
-CONFIG_PSTORE_LZO_COMPRESS=m
-CONFIG_PSTORE_LZ4_COMPRESS=m
-CONFIG_PSTORE_LZ4HC_COMPRESS=m
-CONFIG_PSTORE_842_COMPRESS=y
-CONFIG_PSTORE_ZSTD_COMPRESS=y
-CONFIG_PSTORE_ZSTD_COMPRESS_DEFAULT=y
+CONFIG_PSTORE_COMPRESS=y
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_EROFS_FS=m
 CONFIG_EROFS_FS_ZIP_LZMA=y
+CONFIG_EROFS_FS_ZIP_DEFLATE=y
+CONFIG_EROFS_FS_ZIP_ZSTD=y
+CONFIG_EROFS_FS_ONDEMAND=y
 CONFIG_EROFS_FS_PCPU_KTHREAD=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y

From b032ae57d4fe2b2445e3bc190db6fcaa8c102f68 Mon Sep 17 00:00:00 2001
From: Vitalii Mordan <mordan@ispras.ru>
Date: Thu, 21 Nov 2024 23:06:58 +0300
Subject: [PATCH 1442/1530] marvell: pxa168_eth: fix call balance of pep->clk
 handling routines

If the clock pep->clk was not enabled in pxa168_eth_probe,
it should not be disabled in any path.

Conversely, if it was enabled in pxa168_eth_probe, it must be disabled
in all error paths to ensure proper cleanup.

Use the devm_clk_get_enabled helper function to ensure proper call balance
for pep->clk.

Found by Linux Verification Center (linuxtesting.org) with Klever.

Fixes: a49f37eed22b ("net: add Fast Ethernet driver for PXA168.")
Signed-off-by: Vitalii Mordan <mordan@ispras.ru>
Link: https://patch.msgid.link/20241121200658.2203871-1-mordan@ispras.ru
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/marvell/pxa168_eth.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index fe38426ec42d4..2bf426cea6ddc 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1394,18 +1394,15 @@ static int pxa168_eth_probe(struct platform_device *pdev)
 
 	printk(KERN_NOTICE "PXA168 10/100 Ethernet Driver\n");
 
-	clk = devm_clk_get(&pdev->dev, NULL);
+	clk = devm_clk_get_enabled(&pdev->dev, NULL);
 	if (IS_ERR(clk)) {
-		dev_err(&pdev->dev, "Fast Ethernet failed to get clock\n");
+		dev_err(&pdev->dev, "Fast Ethernet failed to get and enable clock\n");
 		return -ENODEV;
 	}
-	clk_prepare_enable(clk);
 
 	dev = alloc_etherdev(sizeof(struct pxa168_eth_private));
-	if (!dev) {
-		err = -ENOMEM;
-		goto err_clk;
-	}
+	if (!dev)
+		return -ENOMEM;
 
 	platform_set_drvdata(pdev, dev);
 	pep = netdev_priv(dev);
@@ -1523,8 +1520,6 @@ static int pxa168_eth_probe(struct platform_device *pdev)
 	mdiobus_free(pep->smi_bus);
 err_netdev:
 	free_netdev(dev);
-err_clk:
-	clk_disable_unprepare(clk);
 	return err;
 }
 
@@ -1542,7 +1537,6 @@ static void pxa168_eth_remove(struct platform_device *pdev)
 	if (dev->phydev)
 		phy_disconnect(dev->phydev);
 
-	clk_disable_unprepare(pep->clk);
 	mdiobus_unregister(pep->smi_bus);
 	mdiobus_free(pep->smi_bus);
 	unregister_netdev(dev);

From 407618d66dba55e7db1278872e8be106808bbe91 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 22 Nov 2024 15:12:55 +0100
Subject: [PATCH 1443/1530] net: stmmac: dwmac-socfpga: Set RX watchdog
 interrupt as broken

On DWMAC3 and later, there's a RX Watchdog interrupt that's used for
interrupt coalescing. It's known to be buggy on some platforms, and
dwmac-socfpga appears to be one of them. Changing the interrupt
coalescing from ethtool doesn't appear to have any effect here.

Without disabling RIWT (Received Interrupt Watchdog Timer, I
believe...), we observe latencies while receiving traffic that amount to
around ~0.4ms. This was discovered with NTP but can be easily reproduced
with a simple ping. Without this patch :

64 bytes from 192.168.5.2: icmp_seq=1 ttl=64 time=0.657 ms

With this patch :

64 bytes from 192.168.5.2: icmp_seq=1 ttl=64 time=0.254 ms

Fixes: 801d233b7302 ("net: stmmac: Add SOCFPGA glue driver")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20241122141256.764578-1-maxime.chevallier@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index 248b30d7b864b..16020b72dec83 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -487,6 +487,8 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 	plat_dat->select_pcs = socfpga_dwmac_select_pcs;
 	plat_dat->has_gmac = true;
 
+	plat_dat->riwt_off = 1;
+
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
 		return ret;

From 7ebbbb23ea5b6d051509cb11399afac5042c9266 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Fri, 22 Nov 2024 21:50:31 +0530
Subject: [PATCH 1444/1530] octeontx2-af: RPM: Fix mismatch in lmac type

Due to a bug in the previous patch, there is a mismatch
between the lmac type reported by the driver and the actual
hardware configuration.

Fixes: 3ad3f8f93c81 ("octeontx2-af: cn10k: MAC internal loopback support")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/marvell/octeontx2/af/rpm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
index 1b34cf9c97035..9e8c5e4389f8b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
@@ -467,7 +467,7 @@ u8 rpm_get_lmac_type(void *rpmd, int lmac_id)
 	int err;
 
 	req = FIELD_SET(CMDREG_ID, CGX_CMD_GET_LINK_STS, req);
-	err = cgx_fwi_cmd_generic(req, &resp, rpm, 0);
+	err = cgx_fwi_cmd_generic(req, &resp, rpm, lmac_id);
 	if (!err)
 		return FIELD_GET(RESP_LINKSTAT_LMAC_TYPE, resp);
 	return err;

From d1e8884e050c1255a9ceb477f5ff926ee9214a23 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Fri, 22 Nov 2024 21:50:32 +0530
Subject: [PATCH 1445/1530] octeontx2-af: RPM: Fix low network performance

Low network performance is observed even on RPMs with larger
FIFO lengths.

The cn10kb silicon has three RPM blocks with the following
FIFO sizes:

         --------------------
         | RPM0  |   256KB  |
         | RPM1  |   256KB  |
         | RPM2  |   128KB  |
         --------------------

The current design stores the FIFO length in a common structure for all
RPMs (mac_ops). As a result, the FIFO length of the last RPM is applied
to all RPMs, leading to reduced network performance.

This patch resolved the problem by storing the fifo length in per MAC
structure (cgx).

Fixes: b9d0fedc6234 ("octeontx2-af: cn10kb: Add RPM_USX MAC support")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.c         | 9 +++++++--
 drivers/net/ethernet/marvell/octeontx2/af/cgx.h         | 1 +
 drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h | 5 ++++-
 drivers/net/ethernet/marvell/octeontx2/af/rpm.c         | 6 +++---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c     | 9 ++++-----
 5 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 27935c54b91bc..2f621714c54e6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -112,6 +112,11 @@ struct mac_ops *get_mac_ops(void *cgxd)
 	return ((struct cgx *)cgxd)->mac_ops;
 }
 
+u32 cgx_get_fifo_len(void *cgxd)
+{
+	return ((struct cgx *)cgxd)->fifo_len;
+}
+
 void cgx_write(struct cgx *cgx, u64 lmac, u64 offset, u64 val)
 {
 	writeq(val, cgx->reg_base + (lmac << cgx->mac_ops->lmac_offset) +
@@ -501,7 +506,7 @@ static u32 cgx_get_lmac_fifo_len(void *cgxd, int lmac_id)
 	u8 num_lmacs;
 	u32 fifo_len;
 
-	fifo_len = cgx->mac_ops->fifo_len;
+	fifo_len = cgx->fifo_len;
 	num_lmacs = cgx->mac_ops->get_nr_lmacs(cgx);
 
 	switch (num_lmacs) {
@@ -1764,7 +1769,7 @@ static void cgx_populate_features(struct cgx *cgx)
 	u64 cfg;
 
 	cfg = cgx_read(cgx, 0, CGX_CONST);
-	cgx->mac_ops->fifo_len = FIELD_GET(CGX_CONST_RXFIFO_SIZE, cfg);
+	cgx->fifo_len = FIELD_GET(CGX_CONST_RXFIFO_SIZE, cfg);
 	cgx->max_lmac_per_mac = FIELD_GET(CGX_CONST_MAX_LMACS, cfg);
 
 	if (is_dev_rpm(cgx))
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index dc9ace30554af..f9cd4b58f0c02 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -185,4 +185,5 @@ int cgx_lmac_get_pfc_frm_cfg(void *cgxd, int lmac_id, u8 *tx_pause,
 int verify_lmac_fc_cfg(void *cgxd, int lmac_id, u8 tx_pause, u8 rx_pause,
 		       int pfvf_idx);
 int cgx_lmac_reset(void *cgxd, int lmac_id, u8 pf_req_flr);
+u32 cgx_get_fifo_len(void *cgxd);
 #endif /* CGX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h
index 9ffc6790c5130..c43ff68ef1408 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h
@@ -72,7 +72,6 @@ struct mac_ops {
 	u8			irq_offset;
 	u8			int_ena_bit;
 	u8			lmac_fwi;
-	u32			fifo_len;
 	bool			non_contiguous_serdes_lane;
 	/* RPM & CGX differs in number of Receive/transmit stats */
 	u8			rx_stats_cnt;
@@ -142,6 +141,10 @@ struct cgx {
 	u8			lmac_count;
 	/* number of LMACs per MAC could be 4 or 8 */
 	u8			max_lmac_per_mac;
+	/* length of fifo varies depending on the number
+	 * of LMACS
+	 */
+	u32			fifo_len;
 #define MAX_LMAC_COUNT		8
 	struct lmac             *lmac_idmap[MAX_LMAC_COUNT];
 	struct			work_struct cgx_cmd_work;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
index 9e8c5e4389f8b..22dd50a3fcd3a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
@@ -480,7 +480,7 @@ u32 rpm_get_lmac_fifo_len(void *rpmd, int lmac_id)
 	u8 num_lmacs;
 	u32 fifo_len;
 
-	fifo_len = rpm->mac_ops->fifo_len;
+	fifo_len = rpm->fifo_len;
 	num_lmacs = rpm->mac_ops->get_nr_lmacs(rpm);
 
 	switch (num_lmacs) {
@@ -533,9 +533,9 @@ u32 rpm2_get_lmac_fifo_len(void *rpmd, int lmac_id)
 	 */
 	max_lmac = (rpm_read(rpm, 0, CGX_CONST) >> 24) & 0xFF;
 	if (max_lmac > 4)
-		fifo_len = rpm->mac_ops->fifo_len / 2;
+		fifo_len = rpm->fifo_len / 2;
 	else
-		fifo_len = rpm->mac_ops->fifo_len;
+		fifo_len = rpm->fifo_len;
 
 	if (lmac_id < 4) {
 		num_lmacs = hweight8(lmac_info & 0xF);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 266ecbc1b97a6..4dcd7bfcad4e4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -923,13 +923,12 @@ int rvu_mbox_handler_cgx_features_get(struct rvu *rvu,
 
 u32 rvu_cgx_get_fifolen(struct rvu *rvu)
 {
-	struct mac_ops *mac_ops;
-	u32 fifo_len;
+	void *cgxd = rvu_first_cgx_pdata(rvu);
 
-	mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu));
-	fifo_len = mac_ops ? mac_ops->fifo_len : 0;
+	if (!cgxd)
+		return 0;
 
-	return fifo_len;
+	return cgx_get_fifo_len(cgxd);
 }
 
 u32 rvu_cgx_get_lmac_fifolen(struct rvu *rvu, int cgx, int lmac)

From 07cd1eb166a3fa7244afa74d48bd13c9df7c559d Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Fri, 22 Nov 2024 21:50:33 +0530
Subject: [PATCH 1446/1530] octeontx2-af: RPM: fix stale RSFEC counters

The earlier patch sets the 'Stats control register' for RPM
receive/transmit statistics instead of RSFEC statistics,
causing the driver to return stale FEC counters.

Fixes: 84ad3642115d ("octeontx2-af: Add FEC stats for RPM/RPM_USX block")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/marvell/octeontx2/af/rpm.c | 13 +++++++++----
 drivers/net/ethernet/marvell/octeontx2/af/rpm.h |  4 +++-
 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
index 22dd50a3fcd3a..70629f94c27ef 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
@@ -699,6 +699,10 @@ int rpm_get_fec_stats(void *rpmd, int lmac_id, struct cgx_fec_stats_rsp *rsp)
 	if (rpm->lmac_idmap[lmac_id]->link_info.fec == OTX2_FEC_NONE)
 		return 0;
 
+	/* latched registers FCFECX_CW_HI/RSFEC_STAT_FAST_DATA_HI_CDC are common
+	 * for all counters. Acquire lock to ensure serialized reads
+	 */
+	mutex_lock(&rpm->lock);
 	if (rpm->lmac_idmap[lmac_id]->link_info.fec == OTX2_FEC_BASER) {
 		val_lo = rpm_read(rpm, lmac_id, RPMX_MTI_FCFECX_VL0_CCW_LO);
 		val_hi = rpm_read(rpm, lmac_id, RPMX_MTI_FCFECX_CW_HI);
@@ -725,20 +729,21 @@ int rpm_get_fec_stats(void *rpmd, int lmac_id, struct cgx_fec_stats_rsp *rsp)
 		}
 	} else {
 		/* enable RS-FEC capture */
-		cfg = rpm_read(rpm, 0, RPMX_MTI_STAT_STATN_CONTROL);
+		cfg = rpm_read(rpm, 0, RPMX_MTI_RSFEC_STAT_STATN_CONTROL);
 		cfg |= RPMX_RSFEC_RX_CAPTURE | BIT(lmac_id);
-		rpm_write(rpm, 0, RPMX_MTI_STAT_STATN_CONTROL, cfg);
+		rpm_write(rpm, 0, RPMX_MTI_RSFEC_STAT_STATN_CONTROL, cfg);
 
 		val_lo = rpm_read(rpm, 0,
 				  RPMX_MTI_RSFEC_STAT_COUNTER_CAPTURE_2);
-		val_hi = rpm_read(rpm, 0, RPMX_MTI_STAT_DATA_HI_CDC);
+		val_hi = rpm_read(rpm, 0, RPMX_MTI_RSFEC_STAT_FAST_DATA_HI_CDC);
 		rsp->fec_corr_blks = (val_hi << 32 | val_lo);
 
 		val_lo = rpm_read(rpm, 0,
 				  RPMX_MTI_RSFEC_STAT_COUNTER_CAPTURE_3);
-		val_hi = rpm_read(rpm, 0, RPMX_MTI_STAT_DATA_HI_CDC);
+		val_hi = rpm_read(rpm, 0, RPMX_MTI_RSFEC_STAT_FAST_DATA_HI_CDC);
 		rsp->fec_uncorr_blks = (val_hi << 32 | val_lo);
 	}
+	mutex_unlock(&rpm->lock);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
index 34b11deb0f3c1..a5773fbacaff8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
@@ -84,9 +84,11 @@
 /* FEC stats */
 #define RPMX_MTI_STAT_STATN_CONTROL			0x10018
 #define RPMX_MTI_STAT_DATA_HI_CDC			0x10038
-#define RPMX_RSFEC_RX_CAPTURE				BIT_ULL(27)
+#define RPMX_RSFEC_RX_CAPTURE				BIT_ULL(28)
 #define RPMX_CMD_CLEAR_RX				BIT_ULL(30)
 #define RPMX_CMD_CLEAR_TX				BIT_ULL(31)
+#define RPMX_MTI_RSFEC_STAT_STATN_CONTROL               0x40018
+#define RPMX_MTI_RSFEC_STAT_FAST_DATA_HI_CDC            0x40000
 #define RPMX_MTI_RSFEC_STAT_COUNTER_CAPTURE_2		0x40050
 #define RPMX_MTI_RSFEC_STAT_COUNTER_CAPTURE_3		0x40058
 #define RPMX_MTI_FCFECX_VL0_CCW_LO			0x38618

From 6fc2164108462b913a1290fa2c44054c70b060ef Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Fri, 22 Nov 2024 21:50:34 +0530
Subject: [PATCH 1447/1530] octeontx2-af: RPM: fix stale FCFEC counters

The corrected words register(FCFECX_VL0_CCW_LO)/Uncorrected words
register (FCFECX_VL0_NCCW_LO) of FCFEC counter has different LMAC
offset which needs to be accessed differently.

Fixes: 84ad3642115d ("octeontx2-af: Add FEC stats for RPM/RPM_USX block")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/marvell/octeontx2/af/rpm.c   | 24 +++++++++----------
 .../net/ethernet/marvell/octeontx2/af/rpm.h   | 10 ++++----
 2 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
index 70629f94c27ef..e97fcc51d7f24 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
@@ -704,27 +704,27 @@ int rpm_get_fec_stats(void *rpmd, int lmac_id, struct cgx_fec_stats_rsp *rsp)
 	 */
 	mutex_lock(&rpm->lock);
 	if (rpm->lmac_idmap[lmac_id]->link_info.fec == OTX2_FEC_BASER) {
-		val_lo = rpm_read(rpm, lmac_id, RPMX_MTI_FCFECX_VL0_CCW_LO);
-		val_hi = rpm_read(rpm, lmac_id, RPMX_MTI_FCFECX_CW_HI);
+		val_lo = rpm_read(rpm, 0, RPMX_MTI_FCFECX_VL0_CCW_LO(lmac_id));
+		val_hi = rpm_read(rpm, 0, RPMX_MTI_FCFECX_CW_HI(lmac_id));
 		rsp->fec_corr_blks = (val_hi << 16 | val_lo);
 
-		val_lo = rpm_read(rpm, lmac_id, RPMX_MTI_FCFECX_VL0_NCCW_LO);
-		val_hi = rpm_read(rpm, lmac_id, RPMX_MTI_FCFECX_CW_HI);
+		val_lo = rpm_read(rpm, 0, RPMX_MTI_FCFECX_VL0_NCCW_LO(lmac_id));
+		val_hi = rpm_read(rpm, 0, RPMX_MTI_FCFECX_CW_HI(lmac_id));
 		rsp->fec_uncorr_blks = (val_hi << 16 | val_lo);
 
 		/* 50G uses 2 Physical serdes lines */
 		if (rpm->lmac_idmap[lmac_id]->link_info.lmac_type_id ==
 		    LMAC_MODE_50G_R) {
-			val_lo = rpm_read(rpm, lmac_id,
-					  RPMX_MTI_FCFECX_VL1_CCW_LO);
-			val_hi = rpm_read(rpm, lmac_id,
-					  RPMX_MTI_FCFECX_CW_HI);
+			val_lo = rpm_read(rpm, 0,
+					  RPMX_MTI_FCFECX_VL1_CCW_LO(lmac_id));
+			val_hi = rpm_read(rpm, 0,
+					  RPMX_MTI_FCFECX_CW_HI(lmac_id));
 			rsp->fec_corr_blks += (val_hi << 16 | val_lo);
 
-			val_lo = rpm_read(rpm, lmac_id,
-					  RPMX_MTI_FCFECX_VL1_NCCW_LO);
-			val_hi = rpm_read(rpm, lmac_id,
-					  RPMX_MTI_FCFECX_CW_HI);
+			val_lo = rpm_read(rpm, 0,
+					  RPMX_MTI_FCFECX_VL1_NCCW_LO(lmac_id));
+			val_hi = rpm_read(rpm, 0,
+					  RPMX_MTI_FCFECX_CW_HI(lmac_id));
 			rsp->fec_uncorr_blks += (val_hi << 16 | val_lo);
 		}
 	} else {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
index a5773fbacaff8..5194fec4c3b8e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
@@ -91,11 +91,11 @@
 #define RPMX_MTI_RSFEC_STAT_FAST_DATA_HI_CDC            0x40000
 #define RPMX_MTI_RSFEC_STAT_COUNTER_CAPTURE_2		0x40050
 #define RPMX_MTI_RSFEC_STAT_COUNTER_CAPTURE_3		0x40058
-#define RPMX_MTI_FCFECX_VL0_CCW_LO			0x38618
-#define RPMX_MTI_FCFECX_VL0_NCCW_LO			0x38620
-#define RPMX_MTI_FCFECX_VL1_CCW_LO			0x38628
-#define RPMX_MTI_FCFECX_VL1_NCCW_LO			0x38630
-#define RPMX_MTI_FCFECX_CW_HI				0x38638
+#define RPMX_MTI_FCFECX_VL0_CCW_LO(a)			(0x38618 + ((a) * 0x40))
+#define RPMX_MTI_FCFECX_VL0_NCCW_LO(a)			(0x38620 + ((a) * 0x40))
+#define RPMX_MTI_FCFECX_VL1_CCW_LO(a)			(0x38628 + ((a) * 0x40))
+#define RPMX_MTI_FCFECX_VL1_NCCW_LO(a)			(0x38630 + ((a) * 0x40))
+#define RPMX_MTI_FCFECX_CW_HI(a)			(0x38638 + ((a) * 0x40))
 
 /* CN10KB CSR Declaration */
 #define  RPM2_CMRX_SW_INT				0x1b0

From 762ca6eed026346d9d41ed5ac633083c4f1e5071 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Fri, 22 Nov 2024 21:50:35 +0530
Subject: [PATCH 1448/1530] octeontx2-af: Quiesce traffic before NIX block
 reset

During initialization, the AF driver resets all blocks. The RPM (MAC)
block and NIX block operate on a credit-based model. When the NIX block
resets during active traffic flow, it doesn't release credits to the RPM
block. This causes the RPM FIFO to overflow, leading to receive traffic
struck.

To address this issue, the patch introduces the following changes:
1. Stop receiving traffic at the MAC level during AF driver
   initialization.
2. Perform an X2P reset (prevents RXFIFO of all LMACS from pushing data)
3. Reset the NIX block.
4. Clear the X2P reset and re-enable receiving traffic.

Fixes: 54d557815e15 ("octeontx2-af: Reset all RVU blocks")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/marvell/octeontx2/af/cgx.c   | 61 +++++++++++++++++++
 .../net/ethernet/marvell/octeontx2/af/cgx.h   |  4 ++
 .../marvell/octeontx2/af/lmac_common.h        |  2 +
 .../net/ethernet/marvell/octeontx2/af/rpm.c   | 42 +++++++++++++
 .../net/ethernet/marvell/octeontx2/af/rpm.h   |  4 ++
 .../net/ethernet/marvell/octeontx2/af/rvu.c   |  1 +
 .../net/ethernet/marvell/octeontx2/af/rvu.h   |  1 +
 .../ethernet/marvell/octeontx2/af/rvu_cgx.c   | 36 +++++++++--
 8 files changed, 145 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 2f621714c54e6..8216f843a7cd5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -214,6 +214,24 @@ u8 cgx_lmac_get_p2x(int cgx_id, int lmac_id)
 	return (cfg & CMR_P2X_SEL_MASK) >> CMR_P2X_SEL_SHIFT;
 }
 
+static u8 cgx_get_nix_resetbit(struct cgx *cgx)
+{
+	int first_lmac;
+	u8 p2x;
+
+	/* non 98XX silicons supports only NIX0 block */
+	if (cgx->pdev->subsystem_device != PCI_SUBSYS_DEVID_98XX)
+		return CGX_NIX0_RESET;
+
+	first_lmac = find_first_bit(&cgx->lmac_bmap, cgx->max_lmac_per_mac);
+	p2x = cgx_lmac_get_p2x(cgx->cgx_id, first_lmac);
+
+	if (p2x == CMR_P2X_SEL_NIX1)
+		return CGX_NIX1_RESET;
+	else
+		return CGX_NIX0_RESET;
+}
+
 /* Ensure the required lock for event queue(where asynchronous events are
  * posted) is acquired before calling this API. Else an asynchronous event(with
  * latest link status) can reach the destination before this function returns
@@ -1724,6 +1742,8 @@ static int cgx_lmac_init(struct cgx *cgx)
 		lmac->lmac_type = cgx->mac_ops->get_lmac_type(cgx, lmac->lmac_id);
 	}
 
+	/* Start X2P reset on given MAC block */
+	cgx->mac_ops->mac_x2p_reset(cgx, true);
 	return cgx_lmac_verify_fwi_version(cgx);
 
 err_bitmap_free:
@@ -1789,6 +1809,45 @@ static u8 cgx_get_rxid_mapoffset(struct cgx *cgx)
 		return 0x60;
 }
 
+static void cgx_x2p_reset(void *cgxd, bool enable)
+{
+	struct cgx *cgx = cgxd;
+	int lmac_id;
+	u64 cfg;
+
+	if (enable) {
+		for_each_set_bit(lmac_id, &cgx->lmac_bmap, cgx->max_lmac_per_mac)
+			cgx->mac_ops->mac_enadis_rx(cgx, lmac_id, false);
+
+		usleep_range(1000, 2000);
+
+		cfg = cgx_read(cgx, 0, CGXX_CMR_GLOBAL_CONFIG);
+		cfg |= cgx_get_nix_resetbit(cgx) | CGX_NSCI_DROP;
+		cgx_write(cgx, 0, CGXX_CMR_GLOBAL_CONFIG, cfg);
+	} else {
+		cfg = cgx_read(cgx, 0, CGXX_CMR_GLOBAL_CONFIG);
+		cfg &= ~(cgx_get_nix_resetbit(cgx) | CGX_NSCI_DROP);
+		cgx_write(cgx, 0, CGXX_CMR_GLOBAL_CONFIG, cfg);
+	}
+}
+
+static int cgx_enadis_rx(void *cgxd, int lmac_id, bool enable)
+{
+	struct cgx *cgx = cgxd;
+	u64 cfg;
+
+	if (!is_lmac_valid(cgx, lmac_id))
+		return -ENODEV;
+
+	cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_CFG);
+	if (enable)
+		cfg |= DATA_PKT_RX_EN;
+	else
+		cfg &= ~DATA_PKT_RX_EN;
+	cgx_write(cgx, lmac_id, CGXX_CMRX_CFG, cfg);
+	return 0;
+}
+
 static struct mac_ops	cgx_mac_ops    = {
 	.name		=       "cgx",
 	.csr_offset	=       0,
@@ -1820,6 +1879,8 @@ static struct mac_ops	cgx_mac_ops    = {
 	.mac_get_pfc_frm_cfg   =        cgx_lmac_get_pfc_frm_cfg,
 	.mac_reset   =			cgx_lmac_reset,
 	.mac_stats_reset       =	cgx_stats_reset,
+	.mac_x2p_reset                   =      cgx_x2p_reset,
+	.mac_enadis_rx			 =      cgx_enadis_rx,
 };
 
 static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index f9cd4b58f0c02..1cf12e5c7da87 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -32,6 +32,10 @@
 #define CGX_LMAC_TYPE_MASK		0xF
 #define CGXX_CMRX_INT			0x040
 #define FW_CGX_INT			BIT_ULL(1)
+#define CGXX_CMR_GLOBAL_CONFIG          0x08
+#define CGX_NIX0_RESET			BIT_ULL(2)
+#define CGX_NIX1_RESET			BIT_ULL(3)
+#define CGX_NSCI_DROP			BIT_ULL(9)
 #define CGXX_CMRX_INT_ENA_W1S		0x058
 #define CGXX_CMRX_RX_ID_MAP		0x060
 #define CGXX_CMRX_RX_STAT0		0x070
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h
index c43ff68ef1408..6180e68e1765a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h
@@ -132,6 +132,8 @@ struct mac_ops {
 	int			(*get_fec_stats)(void *cgxd, int lmac_id,
 						 struct cgx_fec_stats_rsp *rsp);
 	int			(*mac_stats_reset)(void *cgxd, int lmac_id);
+	void                    (*mac_x2p_reset)(void *cgxd, bool enable);
+	int			(*mac_enadis_rx)(void *cgxd, int lmac_id, bool enable);
 };
 
 struct cgx {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
index e97fcc51d7f24..2e9945446199e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
@@ -39,6 +39,8 @@ static struct mac_ops		rpm_mac_ops   = {
 	.mac_get_pfc_frm_cfg   =        rpm_lmac_get_pfc_frm_cfg,
 	.mac_reset   =			rpm_lmac_reset,
 	.mac_stats_reset		 =	  rpm_stats_reset,
+	.mac_x2p_reset                   =        rpm_x2p_reset,
+	.mac_enadis_rx			 =        rpm_enadis_rx,
 };
 
 static struct mac_ops		rpm2_mac_ops   = {
@@ -72,6 +74,8 @@ static struct mac_ops		rpm2_mac_ops   = {
 	.mac_get_pfc_frm_cfg   =        rpm_lmac_get_pfc_frm_cfg,
 	.mac_reset   =			rpm_lmac_reset,
 	.mac_stats_reset	    =	rpm_stats_reset,
+	.mac_x2p_reset              =   rpm_x2p_reset,
+	.mac_enadis_rx		    =   rpm_enadis_rx,
 };
 
 bool is_dev_rpm2(void *rpmd)
@@ -768,3 +772,41 @@ int rpm_lmac_reset(void *rpmd, int lmac_id, u8 pf_req_flr)
 
 	return 0;
 }
+
+void rpm_x2p_reset(void *rpmd, bool enable)
+{
+	rpm_t *rpm = rpmd;
+	int lmac_id;
+	u64 cfg;
+
+	if (enable) {
+		for_each_set_bit(lmac_id, &rpm->lmac_bmap, rpm->max_lmac_per_mac)
+			rpm->mac_ops->mac_enadis_rx(rpm, lmac_id, false);
+
+		usleep_range(1000, 2000);
+
+		cfg = rpm_read(rpm, 0, RPMX_CMR_GLOBAL_CFG);
+		rpm_write(rpm, 0, RPMX_CMR_GLOBAL_CFG, cfg | RPM_NIX0_RESET);
+	} else {
+		cfg = rpm_read(rpm, 0, RPMX_CMR_GLOBAL_CFG);
+		cfg &= ~RPM_NIX0_RESET;
+		rpm_write(rpm, 0, RPMX_CMR_GLOBAL_CFG, cfg);
+	}
+}
+
+int rpm_enadis_rx(void *rpmd, int lmac_id, bool enable)
+{
+	rpm_t *rpm = rpmd;
+	u64 cfg;
+
+	if (!is_lmac_valid(rpm, lmac_id))
+		return -ENODEV;
+
+	cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG);
+	if (enable)
+		cfg |= RPM_RX_EN;
+	else
+		cfg &= ~RPM_RX_EN;
+	rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg);
+	return 0;
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
index 5194fec4c3b8e..b8d3972e096ae 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
@@ -17,6 +17,8 @@
 
 /* Registers */
 #define RPMX_CMRX_CFG			0x00
+#define RPMX_CMR_GLOBAL_CFG		0x08
+#define RPM_NIX0_RESET			BIT_ULL(3)
 #define RPMX_RX_TS_PREPEND              BIT_ULL(22)
 #define RPMX_TX_PTP_1S_SUPPORT          BIT_ULL(17)
 #define RPMX_CMRX_RX_ID_MAP		0x80
@@ -139,4 +141,6 @@ bool is_dev_rpm2(void *rpmd);
 int rpm_get_fec_stats(void *cgxd, int lmac_id, struct cgx_fec_stats_rsp *rsp);
 int rpm_lmac_reset(void *rpmd, int lmac_id, u8 pf_req_flr);
 int rpm_stats_reset(void *rpmd, int lmac_id);
+void rpm_x2p_reset(void *rpmd, bool enable);
+int rpm_enadis_rx(void *rpmd, int lmac_id, bool enable);
 #endif /* RPM_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 1a97fb9032fa4..cd0d7b7774f1a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -1162,6 +1162,7 @@ static int rvu_setup_hw_resources(struct rvu *rvu)
 	}
 
 	rvu_program_channels(rvu);
+	cgx_start_linkup(rvu);
 
 	err = rvu_mcs_init(rvu);
 	if (err) {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index b897845e25fd3..a383b5ef5b2d8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -1025,6 +1025,7 @@ int rvu_cgx_prio_flow_ctrl_cfg(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_
 int rvu_cgx_cfg_pause_frm(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause);
 void rvu_mac_reset(struct rvu *rvu, u16 pcifunc);
 u32 rvu_cgx_get_lmac_fifolen(struct rvu *rvu, int cgx, int lmac);
+void cgx_start_linkup(struct rvu *rvu);
 int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, u16 pcifunc, int nixlf,
 			     int type);
 bool is_mcam_entry_enabled(struct rvu *rvu, struct npc_mcam *mcam, int blkaddr,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 4dcd7bfcad4e4..992fa0b82e8d2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -349,6 +349,7 @@ static void rvu_cgx_wq_destroy(struct rvu *rvu)
 
 int rvu_cgx_init(struct rvu *rvu)
 {
+	struct mac_ops *mac_ops;
 	int cgx, err;
 	void *cgxd;
 
@@ -375,6 +376,15 @@ int rvu_cgx_init(struct rvu *rvu)
 	if (err)
 		return err;
 
+	/* Clear X2P reset on all MAC blocks */
+	for (cgx = 0; cgx < rvu->cgx_cnt_max; cgx++) {
+		cgxd = rvu_cgx_pdata(cgx, rvu);
+		if (!cgxd)
+			continue;
+		mac_ops = get_mac_ops(cgxd);
+		mac_ops->mac_x2p_reset(cgxd, false);
+	}
+
 	/* Register for CGX events */
 	err = cgx_lmac_event_handler_init(rvu);
 	if (err)
@@ -382,10 +392,26 @@ int rvu_cgx_init(struct rvu *rvu)
 
 	mutex_init(&rvu->cgx_cfg_lock);
 
-	/* Ensure event handler registration is completed, before
-	 * we turn on the links
-	 */
-	mb();
+	return 0;
+}
+
+void cgx_start_linkup(struct rvu *rvu)
+{
+	unsigned long lmac_bmap;
+	struct mac_ops *mac_ops;
+	int cgx, lmac, err;
+	void *cgxd;
+
+	/* Enable receive on all LMACS */
+	for (cgx = 0; cgx <= rvu->cgx_cnt_max; cgx++) {
+		cgxd = rvu_cgx_pdata(cgx, rvu);
+		if (!cgxd)
+			continue;
+		mac_ops = get_mac_ops(cgxd);
+		lmac_bmap = cgx_get_lmac_bmap(cgxd);
+		for_each_set_bit(lmac, &lmac_bmap, rvu->hw->lmac_per_cgx)
+			mac_ops->mac_enadis_rx(cgxd, lmac, true);
+	}
 
 	/* Do link up for all CGX ports */
 	for (cgx = 0; cgx <= rvu->cgx_cnt_max; cgx++) {
@@ -398,8 +424,6 @@ int rvu_cgx_init(struct rvu *rvu)
 				"Link up process failed to start on cgx %d\n",
 				cgx);
 	}
-
-	return 0;
 }
 
 int rvu_cgx_exit(struct rvu *rvu)

From 2ac40e6d0ccdd93031f8b1af61b0fe5cdd704923 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cs=C3=B3k=C3=A1s=2C=20Bence?= <csokas.bence@prolan.hu>
Date: Fri, 22 Nov 2024 15:13:02 +0100
Subject: [PATCH 1449/1530] spi: atmel-quadspi: Fix register name in verbose
 logging function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

`atmel_qspi_reg_name()` is used for pretty-printing register offsets
for verbose logging of register accesses. However, due to a typo
(likely a copy-paste error), QSPI_RD's offset prints as "MR", the
name of the previous register. Fix this typo.

Fixes: c528ecfbef04 ("spi: atmel-quadspi: Add verbose debug facilities to monitor register accesses")
Signed-off-by: Csókás, Bence <csokas.bence@prolan.hu>
Reviewed-by: Alexander Dahl <ada@thorsis.com>
Link: https://patch.msgid.link/20241122141302.2599636-1-csokas.bence@prolan.hu
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/atmel-quadspi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c
index 91108ddfaef21..316bce577081f 100644
--- a/drivers/spi/atmel-quadspi.c
+++ b/drivers/spi/atmel-quadspi.c
@@ -183,7 +183,7 @@ static const char *atmel_qspi_reg_name(u32 offset, char *tmp, size_t sz)
 	case QSPI_MR:
 		return "MR";
 	case QSPI_RD:
-		return "MR";
+		return "RD";
 	case QSPI_TD:
 		return "TD";
 	case QSPI_SR:

From d24cfee7f63d6b44d45a67c5662bd1cc48e8b3ca Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Date: Fri, 22 Nov 2024 10:42:24 +0100
Subject: [PATCH 1450/1530] spi: Fix acpi deferred irq probe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When probing spi device take care of deferred probe of ACPI irq gpio
similar like for OF/DT case.

>From practical standpoint this fixes issue with vsc-tp driver on
Dell XP 9340 laptop, which try to request interrupt with spi->irq
equal to -EPROBE_DEFER and fail to probe with the following error:

vsc-tp spi-INTC10D0:00: probe with driver vsc-tp failed with error -22

Suggested-by: Hans de Goede <hdegoede@redhat.com>
Fixes: 33ada67da352 ("ACPI / spi: attach GPIO IRQ from ACPI description to SPI device")
Cc: stable@vger.kernel.org
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Tested-by: Alexis Lothoré <alexis.lothore@bootlin.com> # Dell XPS9320, ov01a10
Link: https://patch.msgid.link/20241122094224.226773-1-stanislaw.gruszka@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 460a49d9a0de0..ff1add2ecb91f 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -424,6 +424,16 @@ static int spi_probe(struct device *dev)
 			spi->irq = 0;
 	}
 
+	if (has_acpi_companion(dev) && spi->irq < 0) {
+		struct acpi_device *adev = to_acpi_device_node(dev->fwnode);
+
+		spi->irq = acpi_dev_gpio_irq_get(adev, 0);
+		if (spi->irq == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+		if (spi->irq < 0)
+			spi->irq = 0;
+	}
+
 	ret = dev_pm_domain_attach(dev, true);
 	if (ret)
 		return ret;
@@ -2866,9 +2876,6 @@ static acpi_status acpi_register_spi_device(struct spi_controller *ctlr,
 	acpi_set_modalias(adev, acpi_device_hid(adev), spi->modalias,
 			  sizeof(spi->modalias));
 
-	if (spi->irq < 0)
-		spi->irq = acpi_dev_gpio_irq_get(adev, 0);
-
 	acpi_device_set_enumerated(adev);
 
 	adev->power.flags.ignore_parent = true;

From 9cfb5e7f0ded2bfaabc270ceb5f91d13f0e805b9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 22 Nov 2024 17:13:43 +0000
Subject: [PATCH 1451/1530] net: hsr: fix hsr_init_sk() vs network/transport
 headers.

Following sequence in hsr_init_sk() is invalid :

    skb_reset_mac_header(skb);
    skb_reset_mac_len(skb);
    skb_reset_network_header(skb);
    skb_reset_transport_header(skb);

It is invalid because skb_reset_mac_len() needs the correct
network header, which should be after the mac header.

This patch moves the skb_reset_network_header()
and skb_reset_transport_header() before
the call to dev_hard_header().

As a result skb->mac_len is no longer set to a value
close to 65535.

Fixes: 48b491a5cc74 ("net: hsr: fix mac_len checks")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: George McCollister <george.mccollister@gmail.com>
Link: https://patch.msgid.link/20241122171343.897551-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/hsr/hsr_device.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 9e64496a5c1c8..31a416ee21ad9 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -268,6 +268,8 @@ static struct sk_buff *hsr_init_skb(struct hsr_port *master)
 	skb->dev = master->dev;
 	skb->priority = TC_PRIO_CONTROL;
 
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
 	if (dev_hard_header(skb, skb->dev, ETH_P_PRP,
 			    hsr->sup_multicast_addr,
 			    skb->dev->dev_addr, skb->len) <= 0)
@@ -275,8 +277,6 @@ static struct sk_buff *hsr_init_skb(struct hsr_port *master)
 
 	skb_reset_mac_header(skb);
 	skb_reset_mac_len(skb);
-	skb_reset_network_header(skb);
-	skb_reset_transport_header(skb);
 
 	return skb;
 out:

From ac1f43c03fc91eee53cc95683245350d4d87781e Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 25 Nov 2024 12:24:46 +0100
Subject: [PATCH 1452/1530] thermal: gov_power_allocator: Add missing NULL
 pointer check

Commit 0dc23567c206 ("thermal: core: Move lists of thermal instances
to trip descriptors") overlooked the case in which the Power Allocator
governor attempts to bind to a tripless thermal zone and params->trip_max
is NULL in check_power_actors().

No power actors can be found in that case, so check_power_actors() needs
to be made return 0 then to restore its previous behavior.

Fixes: 0dc23567c206 ("thermal: core: Move lists of thermal instances to trip descriptors")
Closes: https://lore.kernel.org/linux-pm/Z0NeGF4ryCe_b5rr@sashalap/
Reported-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://patch.msgid.link/2761105.mvXUDI8C0e@rjwysocki.net
---
 drivers/thermal/gov_power_allocator.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index ac6fa6b8f99f0..3b644de3292e2 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -588,10 +588,15 @@ static void allow_maximum_power(struct thermal_zone_device *tz)
 static int check_power_actors(struct thermal_zone_device *tz,
 			      struct power_allocator_params *params)
 {
-	const struct thermal_trip_desc *td = trip_to_trip_desc(params->trip_max);
+	const struct thermal_trip_desc *td;
 	struct thermal_instance *instance;
 	int ret = 0;
 
+	if (!params->trip_max)
+		return 0;
+
+	td = trip_to_trip_desc(params->trip_max);
+
 	list_for_each_entry(instance, &td->thermal_instances, trip_node) {
 		if (!cdev_is_power_actor(instance->cdev)) {
 			dev_warn(&tz->device, "power_allocator: %s is not a power actor\n",

From 69f3aa6ad92447d6e9f50c5b5aea85b56e80b198 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 10 Oct 2024 20:06:17 +0200
Subject: [PATCH 1453/1530] thermal: of: Simplify thermal_of_should_bind with
 scoped for each OF child

Use scoped for_each_child_of_node_scoped() when iterating over device
nodes to make code a bit simpler.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/20241010-b4-cleanup-h-of-node-put-thermal-v4-1-bfbe29ad81f4@linaro.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_of.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
index 07e09897165f3..e406b9150a2bc 100644
--- a/drivers/thermal/thermal_of.c
+++ b/drivers/thermal/thermal_of.c
@@ -297,7 +297,7 @@ static bool thermal_of_should_bind(struct thermal_zone_device *tz,
 				   struct thermal_cooling_device *cdev,
 				   struct cooling_spec *c)
 {
-	struct device_node *tz_np, *cm_np, *child;
+	struct device_node *tz_np, *cm_np;
 	bool result = false;
 
 	tz_np = thermal_of_zone_get_by_name(tz);
@@ -311,7 +311,7 @@ static bool thermal_of_should_bind(struct thermal_zone_device *tz,
 		goto out;
 
 	/* Look up the trip and the cdev in the cooling maps. */
-	for_each_child_of_node(cm_np, child) {
+	for_each_child_of_node_scoped(cm_np, child) {
 		struct device_node *tr_np;
 		int count, i;
 
@@ -330,7 +330,6 @@ static bool thermal_of_should_bind(struct thermal_zone_device *tz,
 				break;
 		}
 
-		of_node_put(child);
 		break;
 	}
 

From a094ccfa5277cb9b92040016f3abf22408405820 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 10 Oct 2024 20:06:18 +0200
Subject: [PATCH 1454/1530] thermal: of: Use scoped memory and OF handling to
 simplify thermal_of_trips_init()

Obtain the device node reference and allocate memory with
scoped/cleanup.h to reduce error handling and make the code a bit
simpler.

The code is not equivalent in one minor aspect: outgoing parameter
"*ntrips" will not be zeroed on errors of memory allocation.  This
difference is not important, because code was already not zeroing it in
case of earlier errors and the only caller does not rely on ntrips being
0 in case of errors.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Chen-Yu Tsai <wenst@chromium.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://patch.msgid.link/20241010-b4-cleanup-h-of-node-put-thermal-v4-2-bfbe29ad81f4@linaro.org
[ rjw: Rebase ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_of.c | 27 +++++++--------------------
 1 file changed, 7 insertions(+), 20 deletions(-)

diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
index e406b9150a2bc..9b0a3ec36a903 100644
--- a/drivers/thermal/thermal_of.c
+++ b/drivers/thermal/thermal_of.c
@@ -95,13 +95,11 @@ static int thermal_of_populate_trip(struct device_node *np,
 
 static struct thermal_trip *thermal_of_trips_init(struct device_node *np, int *ntrips)
 {
-	struct thermal_trip *tt;
-	struct device_node *trips;
 	int ret, count;
 
 	*ntrips = 0;
 	
-	trips = of_get_child_by_name(np, "trips");
+	struct device_node *trips __free(device_node) = of_get_child_by_name(np, "trips");
 	if (!trips)
 		return NULL;
 
@@ -109,31 +107,20 @@ static struct thermal_trip *thermal_of_trips_init(struct device_node *np, int *n
 	if (!count)
 		return NULL;
 
-	tt = kzalloc(sizeof(*tt) * count, GFP_KERNEL);
-	if (!tt) {
-		ret = -ENOMEM;
-		goto out_of_node_put;
-	}
-
-	*ntrips = count;
+	struct thermal_trip *tt __free(kfree) = kzalloc(sizeof(*tt) * count, GFP_KERNEL);
+	if (!tt)
+		return ERR_PTR(-ENOMEM);
 
 	count = 0;
 	for_each_child_of_node_scoped(trips, trip) {
 		ret = thermal_of_populate_trip(trip, &tt[count++]);
 		if (ret)
-			goto out_kfree;
+			return ERR_PTR(ret);
 	}
 
-	of_node_put(trips);
-
-	return tt;
-
-out_kfree:
-	kfree(tt);
-out_of_node_put:
-	of_node_put(trips);
+	*ntrips = count;
 
-	return ERR_PTR(ret);
+	return no_free_ptr(tt);
 }
 
 static struct device_node *of_thermal_zone_find(struct device_node *sensor, int id)

From 8309135a39de73af2b4bbaa8385e40ffccbfc42c Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 10 Oct 2024 20:06:19 +0200
Subject: [PATCH 1455/1530] thermal: of: Use scoped device node handling to
 simplify of_thermal_zone_find()

Obtain the device node reference with scoped/cleanup.h to reduce error
handling and make the code a bit simpler.

Reviewed-by: Chen-Yu Tsai <wenst@chromium.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/20241010-b4-cleanup-h-of-node-put-thermal-v4-3-bfbe29ad81f4@linaro.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_of.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
index 9b0a3ec36a903..fab11b98ca495 100644
--- a/drivers/thermal/thermal_of.c
+++ b/drivers/thermal/thermal_of.c
@@ -125,10 +125,9 @@ static struct thermal_trip *thermal_of_trips_init(struct device_node *np, int *n
 
 static struct device_node *of_thermal_zone_find(struct device_node *sensor, int id)
 {
-	struct device_node *np, *tz;
 	struct of_phandle_args sensor_specs;
 
-	np = of_find_node_by_name(NULL, "thermal-zones");
+	struct device_node *np __free(device_node) = of_find_node_by_name(NULL, "thermal-zones");
 	if (!np) {
 		pr_debug("No thermal zones description\n");
 		return ERR_PTR(-ENODEV);
@@ -146,8 +145,7 @@ static struct device_node *of_thermal_zone_find(struct device_node *sensor, int
 						   "#thermal-sensor-cells");
 		if (count <= 0) {
 			pr_err("%pOFn: missing thermal sensor\n", child);
-			tz = ERR_PTR(-EINVAL);
-			goto out;
+			return ERR_PTR(-EINVAL);
 		}
 
 		for (i = 0; i < count; i++) {
@@ -159,22 +157,18 @@ static struct device_node *of_thermal_zone_find(struct device_node *sensor, int
 							 i, &sensor_specs);
 			if (ret < 0) {
 				pr_err("%pOFn: Failed to read thermal-sensors cells: %d\n", child, ret);
-				tz = ERR_PTR(ret);
-				goto out;
+				return ERR_PTR(ret);
 			}
 
 			if ((sensor == sensor_specs.np) && id == (sensor_specs.args_count ?
 								  sensor_specs.args[0] : 0)) {
 				pr_debug("sensor %pOFn id=%d belongs to %pOFn\n", sensor, id, child);
-				tz = no_free_ptr(child);
-				goto out;
+				return no_free_ptr(child);
 			}
 		}
 	}
-	tz = ERR_PTR(-ENODEV);
-out:
-	of_node_put(np);
-	return tz;
+
+	return ERR_PTR(-ENODEV);
 }
 
 static int thermal_of_monitor_init(struct device_node *np, int *delay, int *pdelay)

From 4dc00afc20ddb676aedc0ab776397c99e4025e30 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 10 Oct 2024 20:06:20 +0200
Subject: [PATCH 1456/1530] thermal: qcom-spmi-adc-tm5: Simplify with scoped
 for each OF child loop

Use scoped for_each_available_child_of_node_scoped() when iterating over
device nodes to make code a bit simpler.

Reviewed-by: Chen-Yu Tsai <wenst@chromium.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/20241010-b4-cleanup-h-of-node-put-thermal-v4-4-bfbe29ad81f4@linaro.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/qcom/qcom-spmi-adc-tm5.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c
index 5e94a45eba3ee..d7f2e6ca92c2c 100644
--- a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c
+++ b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c
@@ -938,7 +938,6 @@ static const struct adc_tm5_data adc_tm5_gen2_data_pmic = {
 static int adc_tm5_get_dt_data(struct adc_tm5_chip *adc_tm, struct device_node *node)
 {
 	struct adc_tm5_channel *channels;
-	struct device_node *child;
 	u32 value;
 	int ret;
 	struct device *dev = adc_tm->dev;
@@ -982,12 +981,10 @@ static int adc_tm5_get_dt_data(struct adc_tm5_chip *adc_tm, struct device_node *
 		adc_tm->avg_samples = VADC_DEF_AVG_SAMPLES;
 	}
 
-	for_each_available_child_of_node(node, child) {
+	for_each_available_child_of_node_scoped(node, child) {
 		ret = adc_tm5_get_dt_channel_data(adc_tm, channels, child);
-		if (ret) {
-			of_node_put(child);
+		if (ret)
 			return ret;
-		}
 
 		channels++;
 	}

From 2ff772f4a93f7b5abd9d1feaa9624a6006257b71 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 10 Oct 2024 20:06:21 +0200
Subject: [PATCH 1457/1530] thermal: tegra: Simplify with scoped for each OF
 child loop

Use scoped for_each_child_of_node_scoped() when iterating over device
nodes to make code a bit simpler.

Reviewed-by: Chen-Yu Tsai <wenst@chromium.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/20241010-b4-cleanup-h-of-node-put-thermal-v4-5-bfbe29ad81f4@linaro.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/tegra/soctherm.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/thermal/tegra/soctherm.c b/drivers/thermal/tegra/soctherm.c
index 6f1501e3fcc4c..2c5ddf0db40c6 100644
--- a/drivers/thermal/tegra/soctherm.c
+++ b/drivers/thermal/tegra/soctherm.c
@@ -1651,7 +1651,7 @@ static void soctherm_init_hw_throt_cdev(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct tegra_soctherm *ts = dev_get_drvdata(dev);
-	struct device_node *np_stc, *np_stcc;
+	struct device_node *np_stc;
 	const char *name;
 	int i;
 
@@ -1668,7 +1668,7 @@ static void soctherm_init_hw_throt_cdev(struct platform_device *pdev)
 		return;
 	}
 
-	for_each_child_of_node(np_stc, np_stcc) {
+	for_each_child_of_node_scoped(np_stc, np_stcc) {
 		struct soctherm_throt_cfg *stc;
 		struct thermal_cooling_device *tcd;
 		int err;
@@ -1683,7 +1683,6 @@ static void soctherm_init_hw_throt_cdev(struct platform_device *pdev)
 
 		if (stc->init) {
 			dev_err(dev, "throttle-cfg: %s: redefined!\n", name);
-			of_node_put(np_stcc);
 			break;
 		}
 

From c79886c540b57a86df8b0465cc1b71dc32144abf Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 10 Oct 2024 20:06:22 +0200
Subject: [PATCH 1458/1530] thermal: sun8i: Use scoped device node handling to
 simplify error paths

Obtain the device node reference with scoped/cleanup.h to reduce error
handling and make the code a bit simpler.

Reviewed-by: Chen-Yu Tsai <wenst@chromium.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/20241010-b4-cleanup-h-of-node-put-thermal-v4-6-bfbe29ad81f4@linaro.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/sun8i_thermal.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/thermal/sun8i_thermal.c b/drivers/thermal/sun8i_thermal.c
index 3203d8bd13a8f..22674790629a7 100644
--- a/drivers/thermal/sun8i_thermal.c
+++ b/drivers/thermal/sun8i_thermal.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/bitmap.h>
+#include <linux/cleanup.h>
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/interrupt.h>
@@ -348,19 +349,18 @@ static void sun8i_ths_reset_control_assert(void *data)
 
 static struct regmap *sun8i_ths_get_sram_regmap(struct device_node *node)
 {
-	struct device_node *sram_node;
 	struct platform_device *sram_pdev;
 	struct regmap *regmap = NULL;
 
-	sram_node = of_parse_phandle(node, "allwinner,sram", 0);
+	struct device_node *sram_node __free(device_node) =
+		of_parse_phandle(node, "allwinner,sram", 0);
 	if (!sram_node)
 		return ERR_PTR(-ENODEV);
 
 	sram_pdev = of_find_device_by_node(sram_node);
 	if (!sram_pdev) {
 		/* platform device might not be probed yet */
-		regmap = ERR_PTR(-EPROBE_DEFER);
-		goto out_put_node;
+		return ERR_PTR(-EPROBE_DEFER);
 	}
 
 	/* If no regmap is found then the other device driver is at fault */
@@ -369,8 +369,7 @@ static struct regmap *sun8i_ths_get_sram_regmap(struct device_node *node)
 		regmap = ERR_PTR(-EINVAL);
 
 	platform_device_put(sram_pdev);
-out_put_node:
-	of_node_put(sram_node);
+
 	return regmap;
 }
 

From 5311598f7f3293683cdc761df71ae3469327332c Mon Sep 17 00:00:00 2001
From: Saravanan Vajravel <saravanan.vajravel@broadcom.com>
Date: Fri, 22 Nov 2024 14:45:41 -0800
Subject: [PATCH 1459/1530] bnxt_en: Reserve rings after PCIe AER recovery if
 NIC interface is down

After successful PCIe AER recovery, FW will reset all resource
reservations.  If it is IF_UP, the driver will call bnxt_open() and
all resources will be reserved again.  It it is IF_DOWN, we should
call bnxt_reserve_rings() so that we can reserve resources including
RoCE resources to allow RoCE to resume after AER.  Without this
patch, RoCE fails to resume in this IF_DOWN scenario.

Later, if it becomes IF_UP, bnxt_open() will see that resources have
been reserved and will not reserve again.

Fixes: fb1e6e562b37 ("bnxt_en: Fix AER recovery.")
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Saravanan Vajravel <saravanan.vajravel@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 5f7bdafcf05de..3eeaceb3ff383 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -16478,8 +16478,12 @@ static void bnxt_io_resume(struct pci_dev *pdev)
 	rtnl_lock();
 
 	err = bnxt_hwrm_func_qcaps(bp);
-	if (!err && netif_running(netdev))
-		err = bnxt_open(netdev);
+	if (!err) {
+		if (netif_running(netdev))
+			err = bnxt_open(netdev);
+		else
+			err = bnxt_reserve_rings(bp, true);
+	}
 
 	if (!err)
 		netif_device_attach(netdev);

From 5007991670941c132fb3bc0484c009cf4bcea30f Mon Sep 17 00:00:00 2001
From: Shravya KN <shravya.k-n@broadcom.com>
Date: Fri, 22 Nov 2024 14:45:42 -0800
Subject: [PATCH 1460/1530] bnxt_en: Set backplane link modes correctly for
 ethtool

Use the return value from bnxt_get_media() to determine the port and
link modes.  bnxt_get_media() returns the proper BNXT_MEDIA_KR when
the PHY is backplane.  This will correct the ethtool settings for
backplane devices.

Fixes: 5d4e1bf60664 ("bnxt_en: extend media types to supported and autoneg modes")
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Shravya KN <shravya.k-n@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 2f4987ec74643..f1f6bb328a55b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2837,19 +2837,24 @@ static int bnxt_get_link_ksettings(struct net_device *dev,
 	}
 
 	base->port = PORT_NONE;
-	if (link_info->media_type == PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP) {
+	if (media == BNXT_MEDIA_TP) {
 		base->port = PORT_TP;
 		linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT,
 				 lk_ksettings->link_modes.supported);
 		linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT,
 				 lk_ksettings->link_modes.advertising);
+	} else if (media == BNXT_MEDIA_KR) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Backplane_BIT,
+				 lk_ksettings->link_modes.supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Backplane_BIT,
+				 lk_ksettings->link_modes.advertising);
 	} else {
 		linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT,
 				 lk_ksettings->link_modes.supported);
 		linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT,
 				 lk_ksettings->link_modes.advertising);
 
-		if (link_info->media_type == PORT_PHY_QCFG_RESP_MEDIA_TYPE_DAC)
+		if (media == BNXT_MEDIA_CR)
 			base->port = PORT_DA;
 		else
 			base->port = PORT_FIBRE;

From 5ac066b7b062ee753a14557ea11bdc62364c8090 Mon Sep 17 00:00:00 2001
From: Somnath Kotur <somnath.kotur@broadcom.com>
Date: Fri, 22 Nov 2024 14:45:43 -0800
Subject: [PATCH 1461/1530] bnxt_en: Fix queue start to update vnic RSS table

HWRM_RING_FREE followed by a HWRM_RING_ALLOC is not guaranteed to
have the same FW ring ID as before.  So we must reinitialize the
RSS table with the correct ring IDs.  Otherwise, traffic may not
resume properly if the restarted ring ID is stale.  Since this
feature is only supported on P5_PLUS chips, we call
bnxt_vnic_set_rss_p5() to update the HW RSS table.

Fixes: 2d694c27d32e ("bnxt_en: implement netdev_queue_mgmt_ops")
Cc: David Wei <dw@davidwei.uk>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 3eeaceb3ff383..3bee485b50f0e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -15477,6 +15477,13 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 
 	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
 		vnic = &bp->vnic_info[i];
+
+		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
+		if (rc) {
+			netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
+				   vnic->vnic_id, rc);
+			return rc;
+		}
 		vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
 		bnxt_hwrm_vnic_update(bp, vnic,
 				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);

From 3051a77a09dfe3022aa012071346937fdf059033 Mon Sep 17 00:00:00 2001
From: Shravya KN <shravya.k-n@broadcom.com>
Date: Fri, 22 Nov 2024 14:45:44 -0800
Subject: [PATCH 1462/1530] bnxt_en: Fix receive ring space parameters when XDP
 is active

The MTU setting at the time an XDP multi-buffer is attached
determines whether the aggregation ring will be used and the
rx_skb_func handler.  This is done in bnxt_set_rx_skb_mode().

If the MTU is later changed, the aggregation ring setting may need
to be changed and it may become out-of-sync with the settings
initially done in bnxt_set_rx_skb_mode().  This may result in
random memory corruption and crashes as the HW may DMA data larger
than the allocated buffer size, such as:

BUG: kernel NULL pointer dereference, address: 00000000000003c0
PGD 0 P4D 0
Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 17 PID: 0 Comm: swapper/17 Kdump: loaded Tainted: G S         OE      6.1.0-226bf9805506 #1
Hardware name: Wiwynn Delta Lake PVT BZA.02601.0150/Delta Lake-Class1, BIOS F0E_3A12 08/26/2021
RIP: 0010:bnxt_rx_pkt+0xe97/0x1ae0 [bnxt_en]
Code: 8b 95 70 ff ff ff 4c 8b 9d 48 ff ff ff 66 41 89 87 b4 00 00 00 e9 0b f7 ff ff 0f b7 43 0a 49 8b 95 a8 04 00 00 25 ff 0f 00 00 <0f> b7 14 42 48 c1 e2 06 49 03 95 a0 04 00 00 0f b6 42 33f
RSP: 0018:ffffa19f40cc0d18 EFLAGS: 00010202
RAX: 00000000000001e0 RBX: ffff8e2c805c6100 RCX: 00000000000007ff
RDX: 0000000000000000 RSI: ffff8e2c271ab990 RDI: ffff8e2c84f12380
RBP: ffffa19f40cc0e48 R08: 000000000001000d R09: 974ea2fcddfa4cbf
R10: 0000000000000000 R11: ffffa19f40cc0ff8 R12: ffff8e2c94b58980
R13: ffff8e2c952d6600 R14: 0000000000000016 R15: ffff8e2c271ab990
FS:  0000000000000000(0000) GS:ffff8e3b3f840000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000003c0 CR3: 0000000e8580a004 CR4: 00000000007706e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
 <IRQ>
 __bnxt_poll_work+0x1c2/0x3e0 [bnxt_en]

To address the issue, we now call bnxt_set_rx_skb_mode() within
bnxt_change_mtu() to properly set the AGG rings configuration and
update rx_skb_func based on the new MTU value.
Additionally, BNXT_FLAG_NO_AGG_RINGS is cleared at the beginning of
bnxt_set_rx_skb_mode() to make sure it gets set or cleared based on
the current MTU.

Fixes: 08450ea98ae9 ("bnxt_en: Fix max_mtu setting for multi-buf XDP")
Co-developed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Shravya KN <shravya.k-n@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 3bee485b50f0e..b7541156fe46a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4661,7 +4661,7 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
 	struct net_device *dev = bp->dev;
 
 	if (page_mode) {
-		bp->flags &= ~BNXT_FLAG_AGG_RINGS;
+		bp->flags &= ~(BNXT_FLAG_AGG_RINGS | BNXT_FLAG_NO_AGG_RINGS);
 		bp->flags |= BNXT_FLAG_RX_PAGE_MODE;
 
 		if (bp->xdp_prog->aux->xdp_has_frags)
@@ -14740,6 +14740,14 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu)
 		bnxt_close_nic(bp, true, false);
 
 	WRITE_ONCE(dev->mtu, new_mtu);
+
+	/* MTU change may change the AGG ring settings if an XDP multi-buffer
+	 * program is attached.  We need to set the AGG rings settings and
+	 * rx_skb_func accordingly.
+	 */
+	if (READ_ONCE(bp->xdp_prog))
+		bnxt_set_rx_skb_mode(bp, true);
+
 	bnxt_set_ring_params(bp);
 
 	if (netif_running(dev))

From 1e9614cd956268e10a669c0593e7e54d03d0c087 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Fri, 22 Nov 2024 14:45:45 -0800
Subject: [PATCH 1463/1530] bnxt_en: Refactor bnxt_ptp_init()

Instead of passing the 2nd parameter phc_cfg to bnxt_ptp_init().
Store it in bp->ptp_cfg so that the caller doesn't need to know what
the value should be.

In the next patch, we'll need to call bnxt_ptp_init() in bnxt_resume()
and this will make it easier.

Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     | 6 +++---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c | 4 ++--
 drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h | 3 ++-
 3 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b7541156fe46a..9c4b8ea22bf94 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9296,7 +9296,6 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp)
 	struct hwrm_port_mac_ptp_qcfg_output *resp;
 	struct hwrm_port_mac_ptp_qcfg_input *req;
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
-	bool phc_cfg;
 	u8 flags;
 	int rc;
 
@@ -9343,8 +9342,9 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp)
 		rc = -ENODEV;
 		goto exit;
 	}
-	phc_cfg = (flags & PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED) != 0;
-	rc = bnxt_ptp_init(bp, phc_cfg);
+	ptp->rtc_configured =
+		(flags & PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED) != 0;
+	rc = bnxt_ptp_init(bp);
 	if (rc)
 		netdev_warn(bp->dev, "PTP initialization failed.\n");
 exit:
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 075ccd589845c..2d4e19b96ee74 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -1038,7 +1038,7 @@ static void bnxt_ptp_free(struct bnxt *bp)
 	}
 }
 
-int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg)
+int bnxt_ptp_init(struct bnxt *bp)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
 	int rc;
@@ -1061,7 +1061,7 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg)
 
 	if (BNXT_PTP_USE_RTC(bp)) {
 		bnxt_ptp_timecounter_init(bp, false);
-		rc = bnxt_ptp_init_rtc(bp, phc_cfg);
+		rc = bnxt_ptp_init_rtc(bp, ptp->rtc_configured);
 		if (rc)
 			goto out;
 	} else {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index c7851f8c971c5..a95f05e9c579b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -135,6 +135,7 @@ struct bnxt_ptp_cfg {
 					 BNXT_PTP_MSG_PDELAY_REQ |	\
 					 BNXT_PTP_MSG_PDELAY_RESP)
 	u8			tx_tstamp_en:1;
+	u8			rtc_configured:1;
 	int			rx_filter;
 	u32			tstamp_filters;
 
@@ -168,7 +169,7 @@ void bnxt_tx_ts_cmp(struct bnxt *bp, struct bnxt_napi *bnapi,
 		    struct tx_ts_cmp *tscmp);
 void bnxt_ptp_rtc_timecounter_init(struct bnxt_ptp_cfg *ptp, u64 ns);
 int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg);
-int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg);
+int bnxt_ptp_init(struct bnxt *bp);
 void bnxt_ptp_clear(struct bnxt *bp);
 static inline u64 bnxt_timecounter_cyc2time(struct bnxt_ptp_cfg *ptp, u64 ts)
 {

From 3661c05c54e8db7064aa96a0774654740974dffc Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Fri, 22 Nov 2024 14:45:46 -0800
Subject: [PATCH 1464/1530] bnxt_en: Unregister PTP during PCI shutdown and
 suspend

If we go through the PCI shutdown or suspend path, we shutdown the
NIC but PTP remains registered.  If the kernel continues to run for
a little bit, the periodic PTP .do_aux_work() function may be called
and it will read the PHC from the BAR register.  Since the device
has already been disabled, it will cause a PCIe completion timeout.
Fix it by calling bnxt_ptp_clear() in the PCI shutdown/suspend
handlers.  bnxt_ptp_clear() will unregister from PTP and
.do_aux_work() will be canceled.

In bnxt_resume(), we need to re-initialize PTP.

Fixes: a521c8a01d26 ("bnxt_en: Move bnxt_ptp_init() from bnxt_open() back to bnxt_init_one()")
Cc: Richard Cochran <richardcochran@gmail.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 9c4b8ea22bf94..57e69c0552aba 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -16245,6 +16245,7 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 	if (netif_running(dev))
 		dev_close(dev);
 
+	bnxt_ptp_clear(bp);
 	bnxt_clear_int_mode(bp);
 	pci_disable_device(pdev);
 
@@ -16272,6 +16273,7 @@ static int bnxt_suspend(struct device *device)
 		rc = bnxt_close(dev);
 	}
 	bnxt_hwrm_func_drv_unrgtr(bp);
+	bnxt_ptp_clear(bp);
 	pci_disable_device(bp->pdev);
 	bnxt_free_ctx_mem(bp, false);
 	rtnl_unlock();
@@ -16315,6 +16317,10 @@ static int bnxt_resume(struct device *device)
 	if (bp->fw_crash_mem)
 		bnxt_hwrm_crash_dump_mem_cfg(bp);
 
+	if (bnxt_ptp_init(bp)) {
+		kfree(bp->ptp_cfg);
+		bp->ptp_cfg = NULL;
+	}
 	bnxt_get_wol_settings(bp);
 	if (netif_running(dev)) {
 		rc = bnxt_open(dev);

From 0b882940665ca2849386ee459d4331aa2f8c4e7d Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 15 Nov 2024 10:45:31 -0500
Subject: [PATCH 1465/1530] Bluetooth: MGMT: Fix slab-use-after-free Read in
 set_powered_sync

This fixes the following crash:

==================================================================
BUG: KASAN: slab-use-after-free in set_powered_sync+0x3a/0xc0 net/bluetooth/mgmt.c:1353
Read of size 8 at addr ffff888029b4dd18 by task kworker/u9:0/54

CPU: 1 UID: 0 PID: 54 Comm: kworker/u9:0 Not tainted 6.11.0-rc6-syzkaller-01155-gf723224742fc #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/06/2024
Workqueue: hci0 hci_cmd_sync_work
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:93 [inline]
 dump_stack_lvl+0x241/0x360 lib/dump_stack.c:119
 print_address_description mm/kasan/report.c:377 [inline]
 print_report+0x169/0x550 mm/kasan/report.c:488
q kasan_report+0x143/0x180 mm/kasan/report.c:601
 set_powered_sync+0x3a/0xc0 net/bluetooth/mgmt.c:1353
 hci_cmd_sync_work+0x22b/0x400 net/bluetooth/hci_sync.c:328
 process_one_work kernel/workqueue.c:3231 [inline]
 process_scheduled_works+0xa2c/0x1830 kernel/workqueue.c:3312
 worker_thread+0x86d/0xd10 kernel/workqueue.c:3389
 kthread+0x2f0/0x390 kernel/kthread.c:389
 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244
 </TASK>

Allocated by task 5247:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
 poison_kmalloc_redzone mm/kasan/common.c:370 [inline]
 __kasan_kmalloc+0x98/0xb0 mm/kasan/common.c:387
 kasan_kmalloc include/linux/kasan.h:211 [inline]
 __kmalloc_cache_noprof+0x19c/0x2c0 mm/slub.c:4193
 kmalloc_noprof include/linux/slab.h:681 [inline]
 kzalloc_noprof include/linux/slab.h:807 [inline]
 mgmt_pending_new+0x65/0x250 net/bluetooth/mgmt_util.c:269
 mgmt_pending_add+0x36/0x120 net/bluetooth/mgmt_util.c:296
 set_powered+0x3cd/0x5e0 net/bluetooth/mgmt.c:1394
 hci_mgmt_cmd+0xc47/0x11d0 net/bluetooth/hci_sock.c:1712
 hci_sock_sendmsg+0x7b8/0x11c0 net/bluetooth/hci_sock.c:1832
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg+0x221/0x270 net/socket.c:745
 sock_write_iter+0x2dd/0x400 net/socket.c:1160
 new_sync_write fs/read_write.c:497 [inline]
 vfs_write+0xa72/0xc90 fs/read_write.c:590
 ksys_write+0x1a0/0x2c0 fs/read_write.c:643
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Freed by task 5246:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
 kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:579
 poison_slab_object+0xe0/0x150 mm/kasan/common.c:240
 __kasan_slab_free+0x37/0x60 mm/kasan/common.c:256
 kasan_slab_free include/linux/kasan.h:184 [inline]
 slab_free_hook mm/slub.c:2256 [inline]
 slab_free mm/slub.c:4477 [inline]
 kfree+0x149/0x360 mm/slub.c:4598
 settings_rsp+0x2bc/0x390 net/bluetooth/mgmt.c:1443
 mgmt_pending_foreach+0xd1/0x130 net/bluetooth/mgmt_util.c:259
 __mgmt_power_off+0x112/0x420 net/bluetooth/mgmt.c:9455
 hci_dev_close_sync+0x665/0x11a0 net/bluetooth/hci_sync.c:5191
 hci_dev_do_close net/bluetooth/hci_core.c:483 [inline]
 hci_dev_close+0x112/0x210 net/bluetooth/hci_core.c:508
 sock_do_ioctl+0x158/0x460 net/socket.c:1222
 sock_ioctl+0x629/0x8e0 net/socket.c:1341
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:907 [inline]
 __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:893
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83gv
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Reported-by: syzbot+03d6270b6425df1605bf@syzkaller.appspotmail.com
Tested-by: syzbot+03d6270b6425df1605bf@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=03d6270b6425df1605bf
Fixes: 275f3f648702 ("Bluetooth: Fix not checking MGMT cmd pending queue")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/mgmt.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 1f6d083682b8e..e406eb8e43277 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1318,7 +1318,8 @@ static void mgmt_set_powered_complete(struct hci_dev *hdev, void *data, int err)
 	struct mgmt_mode *cp;
 
 	/* Make sure cmd still outstanding. */
-	if (cmd != pending_find(MGMT_OP_SET_POWERED, hdev))
+	if (err == -ECANCELED ||
+	    cmd != pending_find(MGMT_OP_SET_POWERED, hdev))
 		return;
 
 	cp = cmd->param;
@@ -1351,7 +1352,13 @@ static void mgmt_set_powered_complete(struct hci_dev *hdev, void *data, int err)
 static int set_powered_sync(struct hci_dev *hdev, void *data)
 {
 	struct mgmt_pending_cmd *cmd = data;
-	struct mgmt_mode *cp = cmd->param;
+	struct mgmt_mode *cp;
+
+	/* Make sure cmd still outstanding. */
+	if (cmd != pending_find(MGMT_OP_SET_POWERED, hdev))
+		return -ECANCELED;
+
+	cp = cmd->param;
 
 	BT_DBG("%s", hdev->name);
 

From a66dfaf18fd61bb75ef8cee83db46b2aadf153d0 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 21 Nov 2024 11:09:22 -0500
Subject: [PATCH 1466/1530] Bluetooth: MGMT: Fix possible deadlocks

This fixes possible deadlocks like the following caused by
hci_cmd_sync_dequeue causing the destroy function to run:

 INFO: task kworker/u19:0:143 blocked for more than 120 seconds.
       Tainted: G        W  O        6.8.0-2024-03-19-intel-next-iLS-24ww14 #1
 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
 task:kworker/u19:0   state:D stack:0     pid:143   tgid:143   ppid:2      flags:0x00004000
 Workqueue: hci0 hci_cmd_sync_work [bluetooth]
 Call Trace:
  <TASK>
  __schedule+0x374/0xaf0
  schedule+0x3c/0xf0
  schedule_preempt_disabled+0x1c/0x30
  __mutex_lock.constprop.0+0x3ef/0x7a0
  __mutex_lock_slowpath+0x13/0x20
  mutex_lock+0x3c/0x50
  mgmt_set_connectable_complete+0xa4/0x150 [bluetooth]
  ? kfree+0x211/0x2a0
  hci_cmd_sync_dequeue+0xae/0x130 [bluetooth]
  ? __pfx_cmd_complete_rsp+0x10/0x10 [bluetooth]
  cmd_complete_rsp+0x26/0x80 [bluetooth]
  mgmt_pending_foreach+0x4d/0x70 [bluetooth]
  __mgmt_power_off+0x8d/0x180 [bluetooth]
  ? _raw_spin_unlock_irq+0x23/0x40
  hci_dev_close_sync+0x445/0x5b0 [bluetooth]
  hci_set_powered_sync+0x149/0x250 [bluetooth]
  set_powered_sync+0x24/0x60 [bluetooth]
  hci_cmd_sync_work+0x90/0x150 [bluetooth]
  process_one_work+0x13e/0x300
  worker_thread+0x2f7/0x420
  ? __pfx_worker_thread+0x10/0x10
  kthread+0x107/0x140
  ? __pfx_kthread+0x10/0x10
  ret_from_fork+0x3d/0x60
  ? __pfx_kthread+0x10/0x10
  ret_from_fork_asm+0x1b/0x30
  </TASK>

Tested-by: Kiran K <kiran.k@intel.com>
Fixes: f53e1c9c726d ("Bluetooth: MGMT: Fix possible crash on mgmt_index_removed")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/mgmt.c | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index e406eb8e43277..b31192d473d09 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1518,7 +1518,8 @@ static void mgmt_set_discoverable_complete(struct hci_dev *hdev, void *data,
 	bt_dev_dbg(hdev, "err %d", err);
 
 	/* Make sure cmd still outstanding. */
-	if (cmd != pending_find(MGMT_OP_SET_DISCOVERABLE, hdev))
+	if (err == -ECANCELED ||
+	    cmd != pending_find(MGMT_OP_SET_DISCOVERABLE, hdev))
 		return;
 
 	hci_dev_lock(hdev);
@@ -1692,7 +1693,8 @@ static void mgmt_set_connectable_complete(struct hci_dev *hdev, void *data,
 	bt_dev_dbg(hdev, "err %d", err);
 
 	/* Make sure cmd still outstanding. */
-	if (cmd != pending_find(MGMT_OP_SET_CONNECTABLE, hdev))
+	if (err == -ECANCELED ||
+	    cmd != pending_find(MGMT_OP_SET_CONNECTABLE, hdev))
 		return;
 
 	hci_dev_lock(hdev);
@@ -1924,7 +1926,7 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err)
 	bool changed;
 
 	/* Make sure cmd still outstanding. */
-	if (cmd != pending_find(MGMT_OP_SET_SSP, hdev))
+	if (err == -ECANCELED || cmd != pending_find(MGMT_OP_SET_SSP, hdev))
 		return;
 
 	if (err) {
@@ -3848,7 +3850,8 @@ static void set_name_complete(struct hci_dev *hdev, void *data, int err)
 
 	bt_dev_dbg(hdev, "err %d", err);
 
-	if (cmd != pending_find(MGMT_OP_SET_LOCAL_NAME, hdev))
+	if (err == -ECANCELED ||
+	    cmd != pending_find(MGMT_OP_SET_LOCAL_NAME, hdev))
 		return;
 
 	if (status) {
@@ -4023,7 +4026,8 @@ static void set_default_phy_complete(struct hci_dev *hdev, void *data, int err)
 	struct sk_buff *skb = cmd->skb;
 	u8 status = mgmt_status(err);
 
-	if (cmd != pending_find(MGMT_OP_SET_PHY_CONFIGURATION, hdev))
+	if (err == -ECANCELED ||
+	    cmd != pending_find(MGMT_OP_SET_PHY_CONFIGURATION, hdev))
 		return;
 
 	if (!status) {
@@ -5914,13 +5918,16 @@ static void start_discovery_complete(struct hci_dev *hdev, void *data, int err)
 {
 	struct mgmt_pending_cmd *cmd = data;
 
+	bt_dev_dbg(hdev, "err %d", err);
+
+	if (err == -ECANCELED)
+		return;
+
 	if (cmd != pending_find(MGMT_OP_START_DISCOVERY, hdev) &&
 	    cmd != pending_find(MGMT_OP_START_LIMITED_DISCOVERY, hdev) &&
 	    cmd != pending_find(MGMT_OP_START_SERVICE_DISCOVERY, hdev))
 		return;
 
-	bt_dev_dbg(hdev, "err %d", err);
-
 	mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(err),
 			  cmd->param, 1);
 	mgmt_pending_remove(cmd);
@@ -6153,7 +6160,8 @@ static void stop_discovery_complete(struct hci_dev *hdev, void *data, int err)
 {
 	struct mgmt_pending_cmd *cmd = data;
 
-	if (cmd != pending_find(MGMT_OP_STOP_DISCOVERY, hdev))
+	if (err == -ECANCELED ||
+	    cmd != pending_find(MGMT_OP_STOP_DISCOVERY, hdev))
 		return;
 
 	bt_dev_dbg(hdev, "err %d", err);
@@ -8144,7 +8152,8 @@ static void read_local_oob_ext_data_complete(struct hci_dev *hdev, void *data,
 	u8 status = mgmt_status(err);
 	u16 eir_len;
 
-	if (cmd != pending_find(MGMT_OP_READ_LOCAL_OOB_EXT_DATA, hdev))
+	if (err == -ECANCELED ||
+	    cmd != pending_find(MGMT_OP_READ_LOCAL_OOB_EXT_DATA, hdev))
 		return;
 
 	if (!status) {

From ed9588554943097bdf09588a8a105fbb058869c5 Mon Sep 17 00:00:00 2001
From: Edward Adam Davis <eadavis@qq.com>
Date: Tue, 26 Nov 2024 07:58:43 +0800
Subject: [PATCH 1467/1530] Bluetooth: SCO: remove the redundant sco_conn_put

When adding conn, it is necessary to increase and retain the conn reference
count at the same time.

Another problem was fixed along the way, conn_put is missing when hcon is NULL
in the timeout routine.

Fixes: e6720779ae61 ("Bluetooth: SCO: Use kref to track lifetime of sco_conn")
Reported-and-tested-by: syzbot+489f78df4709ac2bfdd3@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=489f78df4709ac2bfdd3
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/sco.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 1b8e468d24cf5..78f7bca244877 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -143,6 +143,7 @@ static void sco_sock_timeout(struct work_struct *work)
 	sco_conn_lock(conn);
 	if (!conn->hcon) {
 		sco_conn_unlock(conn);
+		sco_conn_put(conn);
 		return;
 	}
 	sk = sco_sock_hold(conn);
@@ -192,7 +193,6 @@ static struct sco_conn *sco_conn_add(struct hci_conn *hcon)
 			conn->hcon = hcon;
 			sco_conn_unlock(conn);
 		}
-		sco_conn_put(conn);
 		return conn;
 	}
 

From 2957fa4931a3b658d8e54eda9439d4c57967e8ad Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 26 Nov 2024 15:53:42 +0100
Subject: [PATCH 1468/1530] fs/backing_file: fix wrong argument in callback

Commit 48b50624aec4 ("backing-file: clean up the API") unintentionally
changed the argument in the ->accessed() callback from the user file to
the backing file.

Fixes: 48b50624aec4 ("backing-file: clean up the API")
Reported-by: syzbot+8d1206605b05ca9a0e6a@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-unionfs/67447b3c.050a0220.1cc393.0085.GAE@google.com/
Tested-by: syzbot+8d1206605b05ca9a0e6a@syzkaller.appspotmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20241126145342.364869-1-amir73il@gmail.com
Acked-by: Miklos Szeredi <mszeredi@redhat.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/backing-file.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/backing-file.c b/fs/backing-file.c
index 526ddb4d6f764..cbdad8b684742 100644
--- a/fs/backing-file.c
+++ b/fs/backing-file.c
@@ -327,6 +327,7 @@ int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
 		      struct backing_file_ctx *ctx)
 {
 	const struct cred *old_cred;
+	struct file *user_file = vma->vm_file;
 	int ret;
 
 	if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)))
@@ -342,7 +343,7 @@ int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
 	revert_creds_light(old_cred);
 
 	if (ctx->accessed)
-		ctx->accessed(vma->vm_file);
+		ctx->accessed(user_file);
 
 	return ret;
 }

From 8d4f1e05ff821a5d59116ab8c3a30fcae81d8597 Mon Sep 17 00:00:00 2001
From: Palmer Dabbelt <palmer@rivosinc.com>
Date: Tue, 26 Nov 2024 06:32:50 -0800
Subject: [PATCH 1469/1530] RISC-V: Remove unnecessary include from compat.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Without this I get a bunch of build errors like

    In file included from ./include/linux/sched/task_stack.h:12,
                     from ./arch/riscv/include/asm/compat.h:12,
                     from ./arch/riscv/include/asm/pgtable.h:115,
                     from ./include/linux/pgtable.h:6,
                     from ./include/linux/mm.h:30,
                     from arch/riscv/kernel/asm-offsets.c:8:
    ./include/linux/kasan.h:50:37: error: ‘MAX_PTRS_PER_PTE’ undeclared here (not in a function); did you mean ‘PTRS_PER_PTE’?
       50 | extern pte_t kasan_early_shadow_pte[MAX_PTRS_PER_PTE + PTE_HWTABLE_PTRS];
          |                                     ^~~~~~~~~~~~~~~~
          |                                     PTRS_PER_PTE
    ./include/linux/kasan.h:51:8: error: unknown type name ‘pmd_t’; did you mean ‘pgd_t’?
       51 | extern pmd_t kasan_early_shadow_pmd[MAX_PTRS_PER_PMD];
          |        ^~~~~
          |        pgd_t
    ./include/linux/kasan.h:51:37: error: ‘MAX_PTRS_PER_PMD’ undeclared here (not in a function); did you mean ‘PTRS_PER_PGD’?
       51 | extern pmd_t kasan_early_shadow_pmd[MAX_PTRS_PER_PMD];
          |                                     ^~~~~~~~~~~~~~~~
          |                                     PTRS_PER_PGD
    ./include/linux/kasan.h:52:8: error: unknown type name ‘pud_t’; did you mean ‘pgd_t’?
       52 | extern pud_t kasan_early_shadow_pud[MAX_PTRS_PER_PUD];
          |        ^~~~~
          |        pgd_t
    ./include/linux/kasan.h:52:37: error: ‘MAX_PTRS_PER_PUD’ undeclared here (not in a function); did you mean ‘PTRS_PER_PGD’?
       52 | extern pud_t kasan_early_shadow_pud[MAX_PTRS_PER_PUD];
          |                                     ^~~~~~~~~~~~~~~~
          |                                     PTRS_PER_PGD
    ./include/linux/kasan.h:53:8: error: unknown type name ‘p4d_t’; did you mean ‘pgd_t’?
       53 | extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D];
          |        ^~~~~
          |        pgd_t
    ./include/linux/kasan.h:53:37: error: ‘MAX_PTRS_PER_P4D’ undeclared here (not in a function); did you mean ‘PTRS_PER_PGD’?
       53 | extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D];
          |                                     ^~~~~~~~~~~~~~~~
          |                                     PTRS_PER_PGD

Link: https://lore.kernel.org/r/20241126143250.29708-1-palmer@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/compat.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/riscv/include/asm/compat.h b/arch/riscv/include/asm/compat.h
index aa103530a5c83..6081327e55f5b 100644
--- a/arch/riscv/include/asm/compat.h
+++ b/arch/riscv/include/asm/compat.h
@@ -9,7 +9,6 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
-#include <linux/sched/task_stack.h>
 #include <asm-generic/compat.h>
 
 static inline int is_compat_task(void)

From 1dc707e647bc919834eff9636c8d00b78c782545 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 26 Nov 2024 17:54:58 -0800
Subject: [PATCH 1470/1530] rust: fix up formatting after merge

When I merged the rust 'use' imports, I didn't realize that there's
an offical preferred idiomatic format - so while it all worked fine,
it doesn't match what 'make rustfmt' wants to make it.

Fix it up appropriately.

Suggested-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 rust/kernel/task.rs | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs
index 7a76be5831269..07bc22a7645c0 100644
--- a/rust/kernel/task.rs
+++ b/rust/kernel/task.rs
@@ -6,11 +6,15 @@
 
 use crate::{
     bindings,
+    ffi::{c_int, c_long, c_uint},
     pid_namespace::PidNamespace,
     types::{ARef, NotThreadSafe, Opaque},
 };
-use crate::ffi::{c_int, c_long, c_uint};
-use core::{cmp::{Eq, PartialEq},ops::Deref, ptr};
+use core::{
+    cmp::{Eq, PartialEq},
+    ops::Deref,
+    ptr,
+};
 
 /// A sentinel value used for infinite timeouts.
 pub const MAX_SCHEDULE_TIMEOUT: c_long = c_long::MAX;

From 3b832035387ff508fdcf0fba66701afc78f79e3d Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 27 Nov 2024 12:45:02 +0100
Subject: [PATCH 1471/1530] Revert "fs: don't block i_writecount during exec"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 2a010c41285345da60cece35575b4e0af7e7bf44.

Rui Ueyama <rui314@gmail.com> writes:

> I'm the creator and the maintainer of the mold linker
> (https://github.com/rui314/mold). Recently, we discovered that mold
> started causing process crashes in certain situations due to a change
> in the Linux kernel. Here are the details:
>
> - In general, overwriting an existing file is much faster than
> creating an empty file and writing to it on Linux, so mold attempts to
> reuse an existing executable file if it exists.
>
> - If a program is running, opening the executable file for writing
> previously failed with ETXTBSY. If that happens, mold falls back to
> creating a new file.
>
> - However, the Linux kernel recently changed the behavior so that
> writing to an executable file is now always permitted
> (https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=2a010c412853).
>
> That caused mold to write to an executable file even if there's a
> process running that file. Since changes to mmap'ed files are
> immediately visible to other processes, any processes running that
> file would almost certainly crash in a very mysterious way.
> Identifying the cause of these random crashes took us a few days.
>
> Rejecting writes to an executable file that is currently running is a
> well-known behavior, and Linux had operated that way for a very long
> time. So, I don’t believe relying on this behavior was our mistake;
> rather, I see this as a regression in the Linux kernel.

Quoting myself from commit 2a010c412853 ("fs: don't block i_writecount during exec")

> Yes, someone in userspace could potentially be relying on this. It's not
> completely out of the realm of possibility but let's find out if that's
> actually the case and not guess.

It seems we found out that someone is relying on this obscure behavior.
So revert the change.

Link: https://github.com/rui314/mold/issues/1361
Link: https://lore.kernel.org/r/4a2bc207-76be-4715-8e12-7fc45a76a125@leemhuis.info
Cc: <stable@vger.kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/binfmt_elf.c       |  2 ++
 fs/binfmt_elf_fdpic.c |  5 ++++-
 fs/binfmt_misc.c      |  7 +++++--
 fs/exec.c             | 23 +++++++++++++++--------
 kernel/fork.c         | 26 +++++++++++++++++++++++---
 5 files changed, 49 insertions(+), 14 deletions(-)

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 3039a6b7aba4b..106f0e8af1779 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1257,6 +1257,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		}
 		reloc_func_desc = interp_load_addr;
 
+		allow_write_access(interpreter);
 		fput(interpreter);
 
 		kfree(interp_elf_ex);
@@ -1353,6 +1354,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	kfree(interp_elf_ex);
 	kfree(interp_elf_phdata);
 out_free_file:
+	allow_write_access(interpreter);
 	if (interpreter)
 		fput(interpreter);
 out_free_ph:
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 31d253bd3961a..f1a7c4875c4aa 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -394,6 +394,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 			goto error;
 		}
 
+		allow_write_access(interpreter);
 		fput(interpreter);
 		interpreter = NULL;
 	}
@@ -465,8 +466,10 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 	retval = 0;
 
 error:
-	if (interpreter)
+	if (interpreter) {
+		allow_write_access(interpreter);
 		fput(interpreter);
+	}
 	kfree(interpreter_name);
 	kfree(exec_params.phdrs);
 	kfree(exec_params.loadmap);
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 31660d8cc2c61..6a3a16f910516 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -247,10 +247,13 @@ static int load_misc_binary(struct linux_binprm *bprm)
 	if (retval < 0)
 		goto ret;
 
-	if (fmt->flags & MISC_FMT_OPEN_FILE)
+	if (fmt->flags & MISC_FMT_OPEN_FILE) {
 		interp_file = file_clone_open(fmt->interp_file);
-	else
+		if (!IS_ERR(interp_file))
+			deny_write_access(interp_file);
+	} else {
 		interp_file = open_exec(fmt->interpreter);
+	}
 	retval = PTR_ERR(interp_file);
 	if (IS_ERR(interp_file))
 		goto ret;
diff --git a/fs/exec.c b/fs/exec.c
index da51ca70489ac..98cb7ba9983c7 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -883,7 +883,8 @@ EXPORT_SYMBOL(transfer_args_to_stack);
  */
 static struct file *do_open_execat(int fd, struct filename *name, int flags)
 {
-	struct file *file;
+	int err;
+	struct file *file __free(fput) = NULL;
 	struct open_flags open_exec_flags = {
 		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
 		.acc_mode = MAY_EXEC,
@@ -908,12 +909,14 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
 	 * an invariant that all non-regular files error out before we get here.
 	 */
 	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) ||
-	    path_noexec(&file->f_path)) {
-		fput(file);
+	    path_noexec(&file->f_path))
 		return ERR_PTR(-EACCES);
-	}
 
-	return file;
+	err = deny_write_access(file);
+	if (err)
+		return ERR_PTR(err);
+
+	return no_free_ptr(file);
 }
 
 /**
@@ -923,7 +926,8 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
  *
  * Returns ERR_PTR on failure or allocated struct file on success.
  *
- * As this is a wrapper for the internal do_open_execat(). Also see
+ * As this is a wrapper for the internal do_open_execat(), callers
+ * must call allow_write_access() before fput() on release. Also see
  * do_close_execat().
  */
 struct file *open_exec(const char *name)
@@ -1465,8 +1469,10 @@ static int prepare_bprm_creds(struct linux_binprm *bprm)
 /* Matches do_open_execat() */
 static void do_close_execat(struct file *file)
 {
-	if (file)
-		fput(file);
+	if (!file)
+		return;
+	allow_write_access(file);
+	fput(file);
 }
 
 static void free_bprm(struct linux_binprm *bprm)
@@ -1791,6 +1797,7 @@ static int exec_binprm(struct linux_binprm *bprm)
 		bprm->file = bprm->interpreter;
 		bprm->interpreter = NULL;
 
+		allow_write_access(exec);
 		if (unlikely(bprm->have_execfd)) {
 			if (bprm->executable) {
 				fput(exec);
diff --git a/kernel/fork.c b/kernel/fork.c
index f253e81d0c28e..1450b461d196a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -621,6 +621,12 @@ static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
 
 	exe_file = get_mm_exe_file(oldmm);
 	RCU_INIT_POINTER(mm->exe_file, exe_file);
+	/*
+	 * We depend on the oldmm having properly denied write access to the
+	 * exe_file already.
+	 */
+	if (exe_file && deny_write_access(exe_file))
+		pr_warn_once("deny_write_access() failed in %s\n", __func__);
 }
 
 #ifdef CONFIG_MMU
@@ -1413,11 +1419,20 @@ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 	 */
 	old_exe_file = rcu_dereference_raw(mm->exe_file);
 
-	if (new_exe_file)
+	if (new_exe_file) {
+		/*
+		 * We expect the caller (i.e., sys_execve) to already denied
+		 * write access, so this is unlikely to fail.
+		 */
+		if (unlikely(deny_write_access(new_exe_file)))
+			return -EACCES;
 		get_file(new_exe_file);
+	}
 	rcu_assign_pointer(mm->exe_file, new_exe_file);
-	if (old_exe_file)
+	if (old_exe_file) {
+		allow_write_access(old_exe_file);
 		fput(old_exe_file);
+	}
 	return 0;
 }
 
@@ -1456,6 +1471,9 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 			return ret;
 	}
 
+	ret = deny_write_access(new_exe_file);
+	if (ret)
+		return -EACCES;
 	get_file(new_exe_file);
 
 	/* set the new file */
@@ -1464,8 +1482,10 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 	rcu_assign_pointer(mm->exe_file, new_exe_file);
 	mmap_write_unlock(mm);
 
-	if (old_exe_file)
+	if (old_exe_file) {
+		allow_write_access(old_exe_file);
 		fput(old_exe_file);
+	}
 	return 0;
 }
 

From 1465036b10be4b8b00eb31c879e86de633ad74c1 Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Tue, 19 Nov 2024 14:31:41 +0100
Subject: [PATCH 1472/1530] llc: Improve setsockopt() handling of malformed
 user input

copy_from_sockptr() is used incorrectly: return value is the number of
bytes that could not be copied. Since it's deprecated, switch to
copy_safe_from_sockptr().

Note: Keeping the `optlen != sizeof(int)` check as copy_safe_from_sockptr()
by itself would also accept optlen > sizeof(int). Which would allow a more
lenient handling of inputs.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Suggested-by: David Wei <dw@davidwei.uk>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/llc/af_llc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 4eb52add7103b..0259cde394ba0 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -1098,7 +1098,7 @@ static int llc_ui_setsockopt(struct socket *sock, int level, int optname,
 	lock_sock(sk);
 	if (unlikely(level != SOL_LLC || optlen != sizeof(int)))
 		goto out;
-	rc = copy_from_sockptr(&opt, optval, sizeof(opt));
+	rc = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen);
 	if (rc)
 		goto out;
 	rc = -EINVAL;

From 02020056647017e70509bb58c3096448117099e1 Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Tue, 19 Nov 2024 14:31:42 +0100
Subject: [PATCH 1473/1530] rxrpc: Improve setsockopt() handling of malformed
 user input

copy_from_sockptr() does not return negative value on error; instead, it
reports the number of bytes that failed to copy. Since it's deprecated,
switch to copy_safe_from_sockptr().

Note: Keeping the `optlen != sizeof(unsigned int)` check as
copy_safe_from_sockptr() by itself would also accept
optlen > sizeof(unsigned int). Which would allow a more lenient handling
of inputs.

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/rxrpc/af_rxrpc.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index f4844683e1203..9d8bd0b37e41d 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -707,9 +707,10 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
 			ret = -EISCONN;
 			if (rx->sk.sk_state != RXRPC_UNBOUND)
 				goto error;
-			ret = copy_from_sockptr(&min_sec_level, optval,
-				       sizeof(unsigned int));
-			if (ret < 0)
+			ret = copy_safe_from_sockptr(&min_sec_level,
+						     sizeof(min_sec_level),
+						     optval, optlen);
+			if (ret)
 				goto error;
 			ret = -EINVAL;
 			if (min_sec_level > RXRPC_SECURITY_MAX)

From 49b2b973325add467270e906d4d794aa6679b38b Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Tue, 19 Nov 2024 14:31:43 +0100
Subject: [PATCH 1474/1530] net: Comment copy_from_sockptr() explaining its
 behaviour

copy_from_sockptr() has a history of misuse. Add a comment explaining that
the function follows API of copy_from_user(), i.e. returns 0 for success,
or number of bytes not copied on error.

Signed-off-by: Michal Luczaj <mhal@rbox.co>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/sockptr.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h
index 195debe2b1dbc..3e6c8e9d67aef 100644
--- a/include/linux/sockptr.h
+++ b/include/linux/sockptr.h
@@ -53,6 +53,8 @@ static inline int copy_from_sockptr_offset(void *dst, sockptr_t src,
 /* Deprecated.
  * This is unsafe, unless caller checked user provided optlen.
  * Prefer copy_safe_from_sockptr() instead.
+ *
+ * Returns 0 for success, or number of bytes not copied on error.
  */
 static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size)
 {

From e2668c34b7e1a2288ea0a97ccf3cd12e2870ca18 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sat, 23 Nov 2024 14:50:12 +0000
Subject: [PATCH 1475/1530] net: phy: fix phy_ethtool_set_eee() incorrectly
 enabling LPI

When phy_ethtool_set_eee_noneg() detects a change in the LPI
parameters, it attempts to update phylib state and trigger the link
to cycle so the MAC sees the updated parameters.

However, in doing so, it sets phydev->enable_tx_lpi depending on
whether the EEE configuration allows the MAC to generate LPI without
taking into account the result of negotiation.

This can be demonstrated with a 1000base-T FD interface by:

 # ethtool --set-eee eno0 advertise 8   # cause EEE to be not negotiated
 # ethtool --set-eee eno0 tx-lpi off
 # ethtool --set-eee eno0 tx-lpi on

This results in being true, despite EEE not having been negotiated and:
 # ethtool --show-eee eno0
	EEE status: enabled - inactive
	Tx LPI: 250 (us)
	Supported EEE link modes:  100baseT/Full
	                           1000baseT/Full
	Advertised EEE link modes:  100baseT/Full
	                                         1000baseT/Full

Fix this by keeping track of whether EEE was negotiated via a new
eee_active member in struct phy_device, and include this state in
the decision whether phydev->enable_tx_lpi should be set.

Fixes: 3e43b903da04 ("net: phy: Immediately call adjust_link if only tx_lpi_enabled changes")
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tErSe-005RhB-2R@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-c45.c |  2 +-
 drivers/net/phy/phy.c     | 30 ++++++++++++++++++------------
 include/linux/phy.h       |  2 ++
 3 files changed, 21 insertions(+), 13 deletions(-)

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 96d0b3a5a9d3d..944ae98ad1106 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -1530,7 +1530,7 @@ int genphy_c45_ethtool_get_eee(struct phy_device *phydev,
 		return ret;
 
 	data->eee_enabled = is_enabled;
-	data->eee_active = ret;
+	data->eee_active = phydev->eee_active;
 	linkmode_copy(data->supported, phydev->supported_eee);
 
 	return 0;
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index a660a80f34b79..0d20b534122b2 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -990,14 +990,14 @@ static int phy_check_link_status(struct phy_device *phydev)
 		phydev->state = PHY_RUNNING;
 		err = genphy_c45_eee_is_active(phydev,
 					       NULL, NULL, NULL);
-		if (err <= 0)
-			phydev->enable_tx_lpi = false;
-		else
-			phydev->enable_tx_lpi = phydev->eee_cfg.tx_lpi_enabled;
+		phydev->eee_active = err > 0;
+		phydev->enable_tx_lpi = phydev->eee_cfg.tx_lpi_enabled &&
+					phydev->eee_active;
 
 		phy_link_up(phydev);
 	} else if (!phydev->link && phydev->state != PHY_NOLINK) {
 		phydev->state = PHY_NOLINK;
+		phydev->eee_active = false;
 		phydev->enable_tx_lpi = false;
 		phy_link_down(phydev);
 	}
@@ -1685,15 +1685,21 @@ EXPORT_SYMBOL(phy_ethtool_get_eee);
 static void phy_ethtool_set_eee_noneg(struct phy_device *phydev,
 				      const struct eee_config *old_cfg)
 {
-	if (phydev->eee_cfg.tx_lpi_enabled != old_cfg->tx_lpi_enabled ||
+	bool enable_tx_lpi;
+
+	if (!phydev->link)
+		return;
+
+	enable_tx_lpi = phydev->eee_cfg.tx_lpi_enabled && phydev->eee_active;
+
+	if (phydev->enable_tx_lpi != enable_tx_lpi ||
 	    phydev->eee_cfg.tx_lpi_timer != old_cfg->tx_lpi_timer) {
-		phydev->enable_tx_lpi = eeecfg_mac_can_tx_lpi(&phydev->eee_cfg);
-		if (phydev->link) {
-			phydev->link = false;
-			phy_link_down(phydev);
-			phydev->link = true;
-			phy_link_up(phydev);
-		}
+		phydev->enable_tx_lpi = false;
+		phydev->link = false;
+		phy_link_down(phydev);
+		phydev->enable_tx_lpi = enable_tx_lpi;
+		phydev->link = true;
+		phy_link_up(phydev);
 	}
 }
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 77c6d6451638a..563c462056857 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -602,6 +602,7 @@ struct macsec_ops;
  * @supported_eee: supported PHY EEE linkmodes
  * @advertising_eee: Currently advertised EEE linkmodes
  * @enable_tx_lpi: When True, MAC should transmit LPI to PHY
+ * @eee_active: phylib private state, indicating that EEE has been negotiated
  * @eee_cfg: User configuration of EEE
  * @lp_advertising: Current link partner advertised linkmodes
  * @host_interfaces: PHY interface modes supported by host
@@ -723,6 +724,7 @@ struct phy_device {
 	/* Energy efficient ethernet modes which should be prohibited */
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(eee_broken_modes);
 	bool enable_tx_lpi;
+	bool eee_active;
 	struct eee_config eee_cfg;
 
 	/* Host supported PHY interface types. Should be ignored if empty. */

From c31e72d021db2714df03df6c42855a1db592716c Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Sat, 23 Nov 2024 09:42:36 -0800
Subject: [PATCH 1476/1530] tcp: Fix use-after-free of nreq in
 reqsk_timer_handler().

The cited commit replaced inet_csk_reqsk_queue_drop_and_put() with
__inet_csk_reqsk_queue_drop() and reqsk_put() in reqsk_timer_handler().

Then, oreq should be passed to reqsk_put() instead of req; otherwise
use-after-free of nreq could happen when reqsk is migrated but the
retry attempt failed (e.g. due to timeout).

Let's pass oreq to reqsk_put().

Fixes: e8c526f2bdf1 ("tcp/dccp: Don't use timer_pending() in reqsk_queue_unlink().")
Reported-by: Liu Jian <liujian56@huawei.com>
Closes: https://lore.kernel.org/netdev/1284490f-9525-42ee-b7b8-ccadf6606f6d@huawei.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Liu Jian <liujian56@huawei.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20241123174236.62438-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/inet_connection_sock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 491c2c6b683e2..6872b5aff73e5 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1191,7 +1191,7 @@ static void reqsk_timer_handler(struct timer_list *t)
 
 drop:
 	__inet_csk_reqsk_queue_drop(sk_listener, oreq, true);
-	reqsk_put(req);
+	reqsk_put(oreq);
 }
 
 static bool reqsk_queue_hash_req(struct request_sock *req,

From 122aba8c80618eca904490b1733af27fb8f07528 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sat, 23 Nov 2024 18:21:48 -0800
Subject: [PATCH 1477/1530] net_sched: sch_fq: don't follow the fast path if Tx
 is behind now

Recent kernels cause a lot of TCP retransmissions

[ ID] Interval           Transfer     Bitrate         Retr  Cwnd
[  5]   0.00-1.00   sec  2.24 GBytes  19.2 Gbits/sec  2767    442 KBytes
[  5]   1.00-2.00   sec  2.23 GBytes  19.1 Gbits/sec  2312    350 KBytes
                                                      ^^^^

Replacing the qdisc with pfifo makes retransmissions go away.

It appears that a flow may have a delayed packet with a very near
Tx time. Later, we may get busy processing Rx and the target Tx time
will pass, but we won't service Tx since the CPU is busy with Rx.
If Rx sees an ACK and we try to push more data for the delayed flow
we may fastpath the skb, not realizing that there are already "ready
to send" packets for this flow sitting in the qdisc.

Don't trust the fastpath if we are "behind" according to the projected
Tx time for next flow waiting in the Qdisc. Because we consider anything
within the offload window to be okay for fastpath we must consider
the entire offload window as "now".

Qdisc config:

qdisc fq 8001: dev eth0 parent 1234:1 limit 10000p flow_limit 100p \
  buckets 32768 orphan_mask 1023 bands 3 \
  priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 \
  weights 589824 196608 65536 quantum 3028b initial_quantum 15140b \
  low_rate_threshold 550Kbit \
  refill_delay 40ms timer_slack 10us horizon 10s horizon_drop

For iperf this change seems to do fine, the reordering is gone.
The fastpath still gets used most of the time:

  gc 0 highprio 0 fastpath 142614 throttled 418309 latency 19.1us
   xx_behind 2731

where "xx_behind" counts how many times we hit the new "return false".

CC: stable@vger.kernel.org
Fixes: 076433bd78d7 ("net_sched: sch_fq: add fast path for mostly idle qdisc")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20241124022148.3126719-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/sched/sch_fq.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index a97638bef6da5..a5e87f9ea9861 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -332,6 +332,12 @@ static bool fq_fastpath_check(const struct Qdisc *sch, struct sk_buff *skb,
 		 */
 		if (q->internal.qlen >= 8)
 			return false;
+
+		/* Ordering invariants fall apart if some delayed flows
+		 * are ready but we haven't serviced them, yet.
+		 */
+		if (q->time_next_delayed_flow <= now + q->offload_horizon)
+			return false;
 	}
 
 	sk = skb->sk;

From 663a917475530feff868a4f2bda286ea4171f420 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 24 Nov 2024 07:32:43 +0000
Subject: [PATCH 1478/1530] selftests: rds: move test.py to TEST_FILES

The test.py should not be run separately. It should be run via run.sh,
which will do some sanity checks first. Move the test.py from TEST_PROGS
to TEST_FILES.

Reported-by: Maximilian Heyne <mheyne@amazon.de>
Closes: https://lore.kernel.org/netdev/20241122150129.GB18887@dev-dsk-mheyne-1b-55676e6a.eu-west-1.amazon.com
Fixes: 3ade6ce1255e ("selftests: rds: add testing infrastructure")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Allison Henderson <allison.henderson@oracle.com>
Link: https://patch.msgid.link/20241124073243.847932-1-liuhangbin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/rds/Makefile | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/rds/Makefile b/tools/testing/selftests/net/rds/Makefile
index 1803c39dbacb1..612a7219990eb 100644
--- a/tools/testing/selftests/net/rds/Makefile
+++ b/tools/testing/selftests/net/rds/Makefile
@@ -3,10 +3,9 @@
 all:
 	@echo mk_build_dir="$(shell pwd)" > include.sh
 
-TEST_PROGS := run.sh \
-	test.py
+TEST_PROGS := run.sh
 
-TEST_FILES := include.sh
+TEST_FILES := include.sh test.py
 
 EXTRA_CLEAN := /tmp/rds_logs include.sh
 

From 11b6e701bce96f98474084f26821157cb0dccf69 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Sun, 24 Nov 2024 16:40:56 +0100
Subject: [PATCH 1479/1530] ipmr: add debug check for mr table cleanup

The multicast route tables lifecycle, for both ipv4 and ipv6, is
protected by RCU using the RTNL lock for write access. In many
places a table pointer escapes the RCU (or RTNL) protected critical
section, but such scenarios are actually safe because tables are
deleted only at namespace cleanup time or just after allocation, in
case of default rule creation failure.

Tables freed at namespace cleanup time are assured to be alive for the
whole netns lifetime; tables freed just after creation time are never
exposed to other possible users.

Ensure that the free conditions are respected in ip{,6}mr_free_table, to
document the locking schema and to prevent future possible introduction
of 'table del' operation from breaking it.

Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/ipmr.c  | 14 ++++++++++++++
 net/ipv6/ip6mr.c | 14 ++++++++++++++
 2 files changed, 28 insertions(+)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c58dd78509a27..bac0776648e09 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -120,6 +120,11 @@ static void ipmr_expire_process(struct timer_list *t);
 				lockdep_rtnl_is_held() ||		\
 				list_empty(&net->ipv4.mr_tables))
 
+static bool ipmr_can_free_table(struct net *net)
+{
+	return !check_net(net) || !net->ipv4.mr_rules_ops;
+}
+
 static struct mr_table *ipmr_mr_table_iter(struct net *net,
 					   struct mr_table *mrt)
 {
@@ -302,6 +307,11 @@ EXPORT_SYMBOL(ipmr_rule_default);
 #define ipmr_for_each_table(mrt, net) \
 	for (mrt = net->ipv4.mrt; mrt; mrt = NULL)
 
+static bool ipmr_can_free_table(struct net *net)
+{
+	return !check_net(net);
+}
+
 static struct mr_table *ipmr_mr_table_iter(struct net *net,
 					   struct mr_table *mrt)
 {
@@ -413,6 +423,10 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 
 static void ipmr_free_table(struct mr_table *mrt)
 {
+	struct net *net = read_pnet(&mrt->net);
+
+	DEBUG_NET_WARN_ON_ONCE(!ipmr_can_free_table(net));
+
 	timer_shutdown_sync(&mrt->ipmr_expire_timer);
 	mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC |
 				 MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index d66f58932a793..b80fca8949169 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -108,6 +108,11 @@ static void ipmr_expire_process(struct timer_list *t);
 				lockdep_rtnl_is_held() || \
 				list_empty(&net->ipv6.mr6_tables))
 
+static bool ip6mr_can_free_table(struct net *net)
+{
+	return !check_net(net) || !net->ipv6.mr6_rules_ops;
+}
+
 static struct mr_table *ip6mr_mr_table_iter(struct net *net,
 					    struct mr_table *mrt)
 {
@@ -291,6 +296,11 @@ EXPORT_SYMBOL(ip6mr_rule_default);
 #define ip6mr_for_each_table(mrt, net) \
 	for (mrt = net->ipv6.mrt6; mrt; mrt = NULL)
 
+static bool ip6mr_can_free_table(struct net *net)
+{
+	return !check_net(net);
+}
+
 static struct mr_table *ip6mr_mr_table_iter(struct net *net,
 					    struct mr_table *mrt)
 {
@@ -392,6 +402,10 @@ static struct mr_table *ip6mr_new_table(struct net *net, u32 id)
 
 static void ip6mr_free_table(struct mr_table *mrt)
 {
+	struct net *net = read_pnet(&mrt->net);
+
+	DEBUG_NET_WARN_ON_ONCE(!ip6mr_can_free_table(net));
+
 	timer_shutdown_sync(&mrt->ipmr_expire_timer);
 	mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC |
 				 MRT6_FLUSH_MFC | MRT6_FLUSH_MFC_STATIC);

From f1553c9894b4dbeb10a2ab15ab1aa113b3b4047c Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Sun, 24 Nov 2024 16:40:57 +0100
Subject: [PATCH 1480/1530] ip6mr: fix tables suspicious RCU usage

Several places call ip6mr_get_table() with no RCU nor RTNL lock.
Add RCU protection inside such helper and provide a lockless variant
for the few callers that already acquired the relevant lock.

Note that some users additionally reference the table outside the RCU
lock. That is actually safe as the table deletion can happen only
after all table accesses are completed.

Fixes: e2d57766e674 ("net: Provide compat support for SIOCGETMIFCNT_IN6 and SIOCGETSGCNT_IN6.")
Fixes: d7c31cbde4bc ("net: ip6mr: add RTM_GETROUTE netlink op")
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/ip6mr.c | 38 +++++++++++++++++++++++++++-----------
 1 file changed, 27 insertions(+), 11 deletions(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index b80fca8949169..4147890fe98ff 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -130,7 +130,7 @@ static struct mr_table *ip6mr_mr_table_iter(struct net *net,
 	return ret;
 }
 
-static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
+static struct mr_table *__ip6mr_get_table(struct net *net, u32 id)
 {
 	struct mr_table *mrt;
 
@@ -141,6 +141,16 @@ static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
 	return NULL;
 }
 
+static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
+{
+	struct mr_table *mrt;
+
+	rcu_read_lock();
+	mrt = __ip6mr_get_table(net, id);
+	rcu_read_unlock();
+	return mrt;
+}
+
 static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
 			    struct mr_table **mrt)
 {
@@ -182,7 +192,7 @@ static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp,
 
 	arg->table = fib_rule_get_table(rule, arg);
 
-	mrt = ip6mr_get_table(rule->fr_net, arg->table);
+	mrt = __ip6mr_get_table(rule->fr_net, arg->table);
 	if (!mrt)
 		return -EAGAIN;
 	res->mrt = mrt;
@@ -314,6 +324,8 @@ static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
 	return net->ipv6.mrt6;
 }
 
+#define __ip6mr_get_table ip6mr_get_table
+
 static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
 			    struct mr_table **mrt)
 {
@@ -392,7 +404,7 @@ static struct mr_table *ip6mr_new_table(struct net *net, u32 id)
 {
 	struct mr_table *mrt;
 
-	mrt = ip6mr_get_table(net, id);
+	mrt = __ip6mr_get_table(net, id);
 	if (mrt)
 		return mrt;
 
@@ -425,13 +437,15 @@ static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos)
 	struct net *net = seq_file_net(seq);
 	struct mr_table *mrt;
 
-	mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
-	if (!mrt)
+	rcu_read_lock();
+	mrt = __ip6mr_get_table(net, RT6_TABLE_DFLT);
+	if (!mrt) {
+		rcu_read_unlock();
 		return ERR_PTR(-ENOENT);
+	}
 
 	iter->mrt = mrt;
 
-	rcu_read_lock();
 	return mr_vif_seq_start(seq, pos);
 }
 
@@ -2292,11 +2306,13 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
 	struct mfc6_cache *cache;
 	struct rt6_info *rt = dst_rt6_info(skb_dst(skb));
 
-	mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
-	if (!mrt)
+	rcu_read_lock();
+	mrt = __ip6mr_get_table(net, RT6_TABLE_DFLT);
+	if (!mrt) {
+		rcu_read_unlock();
 		return -ENOENT;
+	}
 
-	rcu_read_lock();
 	cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr);
 	if (!cache && skb->dev) {
 		int vif = ip6mr_find_vif(mrt, skb->dev);
@@ -2576,7 +2592,7 @@ static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		grp = nla_get_in6_addr(tb[RTA_DST]);
 	tableid = nla_get_u32_default(tb[RTA_TABLE], 0);
 
-	mrt = ip6mr_get_table(net, tableid ?: RT_TABLE_DEFAULT);
+	mrt = __ip6mr_get_table(net, tableid ?: RT_TABLE_DEFAULT);
 	if (!mrt) {
 		NL_SET_ERR_MSG_MOD(extack, "MR table does not exist");
 		return -ENOENT;
@@ -2623,7 +2639,7 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 	if (filter.table_id) {
 		struct mr_table *mrt;
 
-		mrt = ip6mr_get_table(sock_net(skb->sk), filter.table_id);
+		mrt = __ip6mr_get_table(sock_net(skb->sk), filter.table_id);
 		if (!mrt) {
 			if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IP6MR)
 				return skb->len;

From fc9c273d6daaa9866f349bbe8cae25c67764c456 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Sun, 24 Nov 2024 16:40:58 +0100
Subject: [PATCH 1481/1530] ipmr: fix tables suspicious RCU usage

Similar to the previous patch, plumb the RCU lock inside
the ipmr_get_table(), provided a lockless variant and apply
the latter in the few spots were the lock is already held.

Fixes: 709b46e8d90b ("net: Add compat ioctl support for the ipv4 multicast ioctl SIOCGETSGCNT")
Fixes: f0ad0860d01e ("ipv4: ipmr: support multiple tables")
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/ipmr.c | 42 +++++++++++++++++++++++++++++-------------
 1 file changed, 29 insertions(+), 13 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index bac0776648e09..383ea8b91cc78 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -142,7 +142,7 @@ static struct mr_table *ipmr_mr_table_iter(struct net *net,
 	return ret;
 }
 
-static struct mr_table *ipmr_get_table(struct net *net, u32 id)
+static struct mr_table *__ipmr_get_table(struct net *net, u32 id)
 {
 	struct mr_table *mrt;
 
@@ -153,6 +153,16 @@ static struct mr_table *ipmr_get_table(struct net *net, u32 id)
 	return NULL;
 }
 
+static struct mr_table *ipmr_get_table(struct net *net, u32 id)
+{
+	struct mr_table *mrt;
+
+	rcu_read_lock();
+	mrt = __ipmr_get_table(net, id);
+	rcu_read_unlock();
+	return mrt;
+}
+
 static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4,
 			   struct mr_table **mrt)
 {
@@ -194,7 +204,7 @@ static int ipmr_rule_action(struct fib_rule *rule, struct flowi *flp,
 
 	arg->table = fib_rule_get_table(rule, arg);
 
-	mrt = ipmr_get_table(rule->fr_net, arg->table);
+	mrt = __ipmr_get_table(rule->fr_net, arg->table);
 	if (!mrt)
 		return -EAGAIN;
 	res->mrt = mrt;
@@ -325,6 +335,8 @@ static struct mr_table *ipmr_get_table(struct net *net, u32 id)
 	return net->ipv4.mrt;
 }
 
+#define __ipmr_get_table ipmr_get_table
+
 static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4,
 			   struct mr_table **mrt)
 {
@@ -413,7 +425,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 	if (id != RT_TABLE_DEFAULT && id >= 1000000000)
 		return ERR_PTR(-EINVAL);
 
-	mrt = ipmr_get_table(net, id);
+	mrt = __ipmr_get_table(net, id);
 	if (mrt)
 		return mrt;
 
@@ -1388,7 +1400,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
 		goto out_unlock;
 	}
 
-	mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
+	mrt = __ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
 	if (!mrt) {
 		ret = -ENOENT;
 		goto out_unlock;
@@ -2276,11 +2288,13 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
 	struct mr_table *mrt;
 	int err;
 
-	mrt = ipmr_get_table(net, RT_TABLE_DEFAULT);
-	if (!mrt)
+	rcu_read_lock();
+	mrt = __ipmr_get_table(net, RT_TABLE_DEFAULT);
+	if (!mrt) {
+		rcu_read_unlock();
 		return -ENOENT;
+	}
 
-	rcu_read_lock();
 	cache = ipmr_cache_find(mrt, saddr, daddr);
 	if (!cache && skb->dev) {
 		int vif = ipmr_find_vif(mrt, skb->dev);
@@ -2564,7 +2578,7 @@ static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	grp = nla_get_in_addr_default(tb[RTA_DST], 0);
 	tableid = nla_get_u32_default(tb[RTA_TABLE], 0);
 
-	mrt = ipmr_get_table(net, tableid ? tableid : RT_TABLE_DEFAULT);
+	mrt = __ipmr_get_table(net, tableid ? tableid : RT_TABLE_DEFAULT);
 	if (!mrt) {
 		err = -ENOENT;
 		goto errout_free;
@@ -2618,7 +2632,7 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 	if (filter.table_id) {
 		struct mr_table *mrt;
 
-		mrt = ipmr_get_table(sock_net(skb->sk), filter.table_id);
+		mrt = __ipmr_get_table(sock_net(skb->sk), filter.table_id);
 		if (!mrt) {
 			if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR)
 				return skb->len;
@@ -2726,7 +2740,7 @@ static int rtm_to_ipmr_mfcc(struct net *net, struct nlmsghdr *nlh,
 			break;
 		}
 	}
-	mrt = ipmr_get_table(net, tblid);
+	mrt = __ipmr_get_table(net, tblid);
 	if (!mrt) {
 		ret = -ENOENT;
 		goto out;
@@ -2934,13 +2948,15 @@ static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos)
 	struct net *net = seq_file_net(seq);
 	struct mr_table *mrt;
 
-	mrt = ipmr_get_table(net, RT_TABLE_DEFAULT);
-	if (!mrt)
+	rcu_read_lock();
+	mrt = __ipmr_get_table(net, RT_TABLE_DEFAULT);
+	if (!mrt) {
+		rcu_read_unlock();
 		return ERR_PTR(-ENOENT);
+	}
 
 	iter->mrt = mrt;
 
-	rcu_read_lock();
 	return mr_vif_seq_start(seq, pos);
 }
 

From 6e33123a18bf6c69c941d09e091e8bfef5fb0d41 Mon Sep 17 00:00:00 2001
From: Vyshnav Ajith <puthen1977@gmail.com>
Date: Fri, 22 Nov 2024 03:48:52 +0530
Subject: [PATCH 1482/1530] Fix spelling mistake

Changed from reequires to require. A minute typo.

Signed-off-by: Vyshnav Ajith <puthen1977@gmail.com>
Link: https://patch.msgid.link/20241121221852.10754-1-puthen1977@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/networking/cdc_mbim.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/networking/cdc_mbim.rst b/Documentation/networking/cdc_mbim.rst
index 37f968acc473a..8404a3f794f37 100644
--- a/Documentation/networking/cdc_mbim.rst
+++ b/Documentation/networking/cdc_mbim.rst
@@ -51,7 +51,7 @@ Such userspace applications includes, but are not limited to:
  - mbimcli (included with the libmbim [3] library), and
  - ModemManager [4]
 
-Establishing a MBIM IP session reequires at least these actions by the
+Establishing a MBIM IP session requires at least these actions by the
 management application:
 
  - open the control channel

From 04f5cb48995d51deed0af71aaba1b8699511313f Mon Sep 17 00:00:00 2001
From: Leo Stone <leocstone@gmail.com>
Date: Sun, 24 Nov 2024 15:00:02 -0800
Subject: [PATCH 1483/1530] Documentation: tls_offload: fix typos and grammar

Fix typos and grammar where it improves readability.

Signed-off-by: Leo Stone <leocstone@gmail.com>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Link: https://patch.msgid.link/20241124230002.56058-1-leocstone@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/networking/tls-offload.rst | 29 ++++++++++++------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst
index 5f0dea3d571e3..7354d48cdf926 100644
--- a/Documentation/networking/tls-offload.rst
+++ b/Documentation/networking/tls-offload.rst
@@ -51,7 +51,7 @@ and send them to the device for encryption and transmission.
 RX
 --
 
-On the receive side if the device handled decryption and authentication
+On the receive side, if the device handled decryption and authentication
 successfully, the driver will set the decrypted bit in the associated
 :c:type:`struct sk_buff <sk_buff>`. The packets reach the TCP stack and
 are handled normally. ``ktls`` is informed when data is queued to the socket
@@ -120,8 +120,9 @@ before installing the connection state in the kernel.
 RX
 --
 
-In RX direction local networking stack has little control over the segmentation,
-so the initial records' TCP sequence number may be anywhere inside the segment.
+In the RX direction, the local networking stack has little control over
+segmentation, so the initial records' TCP sequence number may be anywhere
+inside the segment.
 
 Normal operation
 ================
@@ -138,8 +139,8 @@ There are no guarantees on record length or record segmentation. In particular
 segments may start at any point of a record and contain any number of records.
 Assuming segments are received in order, the device should be able to perform
 crypto operations and authentication regardless of segmentation. For this
-to be possible device has to keep small amount of segment-to-segment state.
-This includes at least:
+to be possible, the device has to keep a small amount of segment-to-segment
+state. This includes at least:
 
  * partial headers (if a segment carried only a part of the TLS header)
  * partial data block
@@ -175,12 +176,12 @@ and packet transformation functions) the device validates the Layer 4
 checksum and performs a 5-tuple lookup to find any TLS connection the packet
 may belong to (technically a 4-tuple
 lookup is sufficient - IP addresses and TCP port numbers, as the protocol
-is always TCP). If connection is matched device confirms if the TCP sequence
-number is the expected one and proceeds to TLS handling (record delineation,
-decryption, authentication for each record in the packet). The device leaves
-the record framing unmodified, the stack takes care of record decapsulation.
-Device indicates successful handling of TLS offload in the per-packet context
-(descriptor) passed to the host.
+is always TCP). If the packet is matched to a connection, the device confirms
+if the TCP sequence number is the expected one and proceeds to TLS handling
+(record delineation, decryption, authentication for each record in the packet).
+The device leaves the record framing unmodified, the stack takes care of record
+decapsulation. Device indicates successful handling of TLS offload in the
+per-packet context (descriptor) passed to the host.
 
 Upon reception of a TLS offloaded packet, the driver sets
 the :c:member:`decrypted` mark in :c:type:`struct sk_buff <sk_buff>`
@@ -439,7 +440,7 @@ by the driver:
  * ``rx_tls_resync_req_end`` - number of times the TLS async resync request
     properly ended with providing the HW tracked tcp-seq.
  * ``rx_tls_resync_req_skip`` - number of times the TLS async resync request
-    procedure was started by not properly ended.
+    procedure was started but not properly ended.
  * ``rx_tls_resync_res_ok`` - number of times the TLS resync response call to
     the driver was successfully handled.
  * ``rx_tls_resync_res_skip`` - number of times the TLS resync response call to
@@ -507,8 +508,8 @@ in packets as seen on the wire.
 Transport layer transparency
 ----------------------------
 
-The device should not modify any packet headers for the purpose
-of the simplifying TLS offload.
+For the purpose of simplifying TLS offload, the device should not modify any
+packet headers.
 
 The device should not depend on any packet headers beyond what is strictly
 necessary for TLS offload.

From f6d7695b5ae22092fa2cc42529bb7462f7e0c4ad Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 28 Nov 2024 17:18:04 +0100
Subject: [PATCH 1484/1530] ipmr: fix build with clang and DEBUG_NET disabled.

Sasha reported a build issue in ipmr::

net/ipv4/ipmr.c:320:13: error: function 'ipmr_can_free_table' is not \
	needed and will not be emitted \
	[-Werror,-Wunneeded-internal-declaration]
   320 | static bool ipmr_can_free_table(struct net *net)

Apparently clang is too smart with BUILD_BUG_ON_INVALID(), let's
fallback to a plain WARN_ON_ONCE().

Reported-by: Sasha Levin <sashal@kernel.org>
Closes: https://qa-reports.linaro.org/lkft/sashal-linus-next/build/v6.11-25635-g6813e2326f1e/testrun/26111580/suite/build/test/clang-nightly-lkftconfig/details/
Fixes: 11b6e701bce9 ("ipmr: add debug check for mr table cleanup")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Link: https://patch.msgid.link/ee75faa926b2446b8302ee5fc30e129d2df73b90.1732810228.git.pabeni@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/ipmr.c  | 2 +-
 net/ipv6/ip6mr.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 383ea8b91cc78..c5b8ec5c0a8c0 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -437,7 +437,7 @@ static void ipmr_free_table(struct mr_table *mrt)
 {
 	struct net *net = read_pnet(&mrt->net);
 
-	DEBUG_NET_WARN_ON_ONCE(!ipmr_can_free_table(net));
+	WARN_ON_ONCE(!ipmr_can_free_table(net));
 
 	timer_shutdown_sync(&mrt->ipmr_expire_timer);
 	mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC |
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 4147890fe98ff..7f1902ac35862 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -416,7 +416,7 @@ static void ip6mr_free_table(struct mr_table *mrt)
 {
 	struct net *net = read_pnet(&mrt->net);
 
-	DEBUG_NET_WARN_ON_ONCE(!ip6mr_can_free_table(net));
+	WARN_ON_ONCE(!ip6mr_can_free_table(net));
 
 	timer_shutdown_sync(&mrt->ipmr_expire_timer);
 	mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC |

From 8e00072c31e28e7de1ffd9b28c773a3143aa4167 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 25 Nov 2024 17:07:18 +0800
Subject: [PATCH 1485/1530] net: enetc: read TSN capabilities from port
 register, not SI

Configuring TSN (Qbv, Qbu, PSFP) capabilities requires access to port
registers, which are available to the PSI but not the VSI.

Yet, the SI port capability register 0 (PSICAPR0), exposed to both PSIs
and VSIs, presents the same capabilities to the VF as to the PF, thus
leading the VF driver into thinking it can configure these features.

In the case of ENETC_SI_F_QBU, having it set in the VF leads to a crash:

root@ls1028ardb:~# tc qdisc add dev eno0vf0 parent root handle 100: \
mqprio num_tc 4 map 0 0 1 1 2 2 3 3 queues 1@0 1@1 1@2 1@3 hw 1
[  187.290775] Unable to handle kernel paging request at virtual address 0000000000001f00
[  187.424831] pc : enetc_mm_commit_preemptible_tcs+0x1c4/0x400
[  187.430518] lr : enetc_mm_commit_preemptible_tcs+0x30c/0x400
[  187.511140] Call trace:
[  187.513588]  enetc_mm_commit_preemptible_tcs+0x1c4/0x400
[  187.518918]  enetc_setup_tc_mqprio+0x180/0x214
[  187.523374]  enetc_vf_setup_tc+0x1c/0x30
[  187.527306]  mqprio_enable_offload+0x144/0x178
[  187.531766]  mqprio_init+0x3ec/0x668
[  187.535351]  qdisc_create+0x15c/0x488
[  187.539023]  tc_modify_qdisc+0x398/0x73c
[  187.542958]  rtnetlink_rcv_msg+0x128/0x378
[  187.547064]  netlink_rcv_skb+0x60/0x130
[  187.550910]  rtnetlink_rcv+0x18/0x24
[  187.554492]  netlink_unicast+0x300/0x36c
[  187.558425]  netlink_sendmsg+0x1a8/0x420
[  187.606759] ---[ end trace 0000000000000000 ]---

while the other TSN features in the VF are harmless, because the
net_device_ops used for the VF driver do not expose entry points for
these other features.

These capability bits are in the process of being defeatured from the SI
registers. We should read them from the port capability register, where
they are also present, and which is naturally only exposed to the PF.

The change to blame (relevant for stable backports) is the one where
this started being a problem, aka when the kernel started to crash due
to the wrong capability seen by the VF driver.

Fixes: 827145392a4a ("net: enetc: only commit preemptible TCs to hardware when MM TX is active")
Reported-by: Wei Fang <wei.fang@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc.c  |  9 ---------
 .../net/ethernet/freescale/enetc/enetc_hw.h   |  6 +++---
 .../net/ethernet/freescale/enetc/enetc_pf.c   | 19 +++++++++++++++++++
 3 files changed, 22 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 35634c516e266..bece220535a1a 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -1756,15 +1756,6 @@ void enetc_get_si_caps(struct enetc_si *si)
 		rss = enetc_rd(hw, ENETC_SIRSSCAPR);
 		si->num_rss = ENETC_SIRSSCAPR_GET_NUM_RSS(rss);
 	}
-
-	if (val & ENETC_SIPCAPR0_QBV)
-		si->hw_features |= ENETC_SI_F_QBV;
-
-	if (val & ENETC_SIPCAPR0_QBU)
-		si->hw_features |= ENETC_SI_F_QBU;
-
-	if (val & ENETC_SIPCAPR0_PSFP)
-		si->hw_features |= ENETC_SI_F_PSFP;
 }
 EXPORT_SYMBOL_GPL(enetc_get_si_caps);
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 7c3285584f8a5..55ba949230ffd 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -23,10 +23,7 @@
 #define ENETC_SICTR0	0x18
 #define ENETC_SICTR1	0x1c
 #define ENETC_SIPCAPR0	0x20
-#define ENETC_SIPCAPR0_PSFP	BIT(9)
 #define ENETC_SIPCAPR0_RSS	BIT(8)
-#define ENETC_SIPCAPR0_QBV	BIT(4)
-#define ENETC_SIPCAPR0_QBU	BIT(3)
 #define ENETC_SIPCAPR0_RFS	BIT(2)
 #define ENETC_SIPCAPR1	0x24
 #define ENETC_SITGTGR	0x30
@@ -194,6 +191,9 @@ enum enetc_bdr_type {TX, RX};
 #define ENETC_PCAPR0		0x0900
 #define ENETC_PCAPR0_RXBDR(val)	((val) >> 24)
 #define ENETC_PCAPR0_TXBDR(val)	(((val) >> 16) & 0xff)
+#define ENETC_PCAPR0_PSFP	BIT(9)
+#define ENETC_PCAPR0_QBV	BIT(4)
+#define ENETC_PCAPR0_QBU	BIT(3)
 #define ENETC_PCAPR1		0x0904
 #define ENETC_PSICFGR0(n)	(0x0940 + (n) * 0xc)  /* n = SI index */
 #define ENETC_PSICFGR0_SET_TXBDR(val)	((val) & 0xff)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index c47b4a743d93b..203862ec11142 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -409,6 +409,23 @@ static void enetc_port_assign_rfs_entries(struct enetc_si *si)
 	enetc_port_wr(hw, ENETC_PRFSMR, ENETC_PRFSMR_RFSE);
 }
 
+static void enetc_port_get_caps(struct enetc_si *si)
+{
+	struct enetc_hw *hw = &si->hw;
+	u32 val;
+
+	val = enetc_port_rd(hw, ENETC_PCAPR0);
+
+	if (val & ENETC_PCAPR0_QBV)
+		si->hw_features |= ENETC_SI_F_QBV;
+
+	if (val & ENETC_PCAPR0_QBU)
+		si->hw_features |= ENETC_SI_F_QBU;
+
+	if (val & ENETC_PCAPR0_PSFP)
+		si->hw_features |= ENETC_SI_F_PSFP;
+}
+
 static void enetc_port_si_configure(struct enetc_si *si)
 {
 	struct enetc_pf *pf = enetc_si_priv(si);
@@ -416,6 +433,8 @@ static void enetc_port_si_configure(struct enetc_si *si)
 	int num_rings, i;
 	u32 val;
 
+	enetc_port_get_caps(si);
+
 	val = enetc_port_rd(hw, ENETC_PCAPR0);
 	num_rings = min(ENETC_PCAPR0_RXBDR(val), ENETC_PCAPR0_TXBDR(val));
 

From b2420b8c81ec674552d00c55d46245e5c184b260 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 25 Nov 2024 17:07:19 +0800
Subject: [PATCH 1486/1530] net: enetc: Do not configure preemptible TCs if SIs
 do not support

Both ENETC PF and VF drivers share enetc_setup_tc_mqprio() to configure
MQPRIO. And enetc_setup_tc_mqprio() calls enetc_change_preemptible_tcs()
to configure preemptible TCs. However, only PF is able to configure
preemptible TCs. Because only PF has related registers, while VF does not
have these registers. So for VF, its hw->port pointer is NULL. Therefore,
VF will access an invalid pointer when accessing a non-existent register,
which will cause a crash issue. The simplified log is as follows.

root@ls1028ardb:~# tc qdisc add dev eno0vf0 parent root handle 100: \
mqprio num_tc 4 map 0 0 1 1 2 2 3 3 queues 1@0 1@1 1@2 1@3 hw 1
[  187.290775] Unable to handle kernel paging request at virtual address 0000000000001f00
[  187.424831] pc : enetc_mm_commit_preemptible_tcs+0x1c4/0x400
[  187.430518] lr : enetc_mm_commit_preemptible_tcs+0x30c/0x400
[  187.511140] Call trace:
[  187.513588]  enetc_mm_commit_preemptible_tcs+0x1c4/0x400
[  187.518918]  enetc_setup_tc_mqprio+0x180/0x214
[  187.523374]  enetc_vf_setup_tc+0x1c/0x30
[  187.527306]  mqprio_enable_offload+0x144/0x178
[  187.531766]  mqprio_init+0x3ec/0x668
[  187.535351]  qdisc_create+0x15c/0x488
[  187.539023]  tc_modify_qdisc+0x398/0x73c
[  187.542958]  rtnetlink_rcv_msg+0x128/0x378
[  187.547064]  netlink_rcv_skb+0x60/0x130
[  187.550910]  rtnetlink_rcv+0x18/0x24
[  187.554492]  netlink_unicast+0x300/0x36c
[  187.558425]  netlink_sendmsg+0x1a8/0x420
[  187.606759] ---[ end trace 0000000000000000 ]---

In addition, some PFs also do not support configuring preemptible TCs,
such as eno1 and eno3 on LS1028A. It won't crash like it does for VFs,
but we should prevent these PFs from accessing these unimplemented
registers.

Fixes: 827145392a4a ("net: enetc: only commit preemptible TCs to hardware when MM TX is active")
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Suggested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index bece220535a1a..535969fa0fdbe 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -29,6 +29,9 @@ EXPORT_SYMBOL_GPL(enetc_port_mac_wr);
 static void enetc_change_preemptible_tcs(struct enetc_ndev_priv *priv,
 					 u8 preemptible_tcs)
 {
+	if (!(priv->si->hw_features & ENETC_SI_F_QBU))
+		return;
+
 	priv->preemptible_tcs = preemptible_tcs;
 	enetc_mm_commit_preemptible_tcs(priv);
 }

From 0a4cc4accf00b49b4728bb7639cb90a6a5b674e2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 25 Nov 2024 09:30:39 +0000
Subject: [PATCH 1487/1530] tcp: populate XPS related fields of timewait
 sockets

syzbot reported that netdev_core_pick_tx() was reading an uninitialized
field [1].

This is indeed hapening for timewait sockets after recent commits.

We can copy the original established socket sk_tx_queue_mapping
and sk_rx_queue_mapping fields, instead of adding more checks
in fast paths.

As a bonus, packets will use the same transmit queue than
prior ones, this potentially can avoid reordering.

[1]
BUG: KMSAN: uninit-value in netdev_pick_tx+0x5c7/0x1550
 netdev_pick_tx+0x5c7/0x1550
  netdev_core_pick_tx+0x1d2/0x4a0 net/core/dev.c:4312
  __dev_queue_xmit+0x128a/0x57d0 net/core/dev.c:4394
  dev_queue_xmit include/linux/netdevice.h:3168 [inline]
  neigh_hh_output include/net/neighbour.h:523 [inline]
  neigh_output include/net/neighbour.h:537 [inline]
  ip_finish_output2+0x187c/0x1b70 net/ipv4/ip_output.c:236
 __ip_finish_output+0x287/0x810
  ip_finish_output+0x4b/0x600 net/ipv4/ip_output.c:324
  NF_HOOK_COND include/linux/netfilter.h:303 [inline]
  ip_output+0x15f/0x3f0 net/ipv4/ip_output.c:434
  dst_output include/net/dst.h:450 [inline]
  ip_local_out net/ipv4/ip_output.c:130 [inline]
  ip_send_skb net/ipv4/ip_output.c:1505 [inline]
  ip_push_pending_frames+0x444/0x570 net/ipv4/ip_output.c:1525
  ip_send_unicast_reply+0x18c1/0x1b30 net/ipv4/ip_output.c:1672
  tcp_v4_send_reset+0x238d/0x2a40 net/ipv4/tcp_ipv4.c:910
  tcp_v4_rcv+0x48f8/0x5750 net/ipv4/tcp_ipv4.c:2431
  ip_protocol_deliver_rcu+0x2a3/0x13d0 net/ipv4/ip_input.c:205
  ip_local_deliver_finish+0x336/0x500 net/ipv4/ip_input.c:233
  NF_HOOK include/linux/netfilter.h:314 [inline]
  ip_local_deliver+0x21f/0x490 net/ipv4/ip_input.c:254
  dst_input include/net/dst.h:460 [inline]
  ip_sublist_rcv_finish net/ipv4/ip_input.c:578 [inline]
  ip_list_rcv_finish net/ipv4/ip_input.c:628 [inline]
  ip_sublist_rcv+0x15f3/0x17f0 net/ipv4/ip_input.c:636
  ip_list_rcv+0x9ef/0xa40 net/ipv4/ip_input.c:670
  __netif_receive_skb_list_ptype net/core/dev.c:5715 [inline]
  __netif_receive_skb_list_core+0x15c5/0x1670 net/core/dev.c:5762
  __netif_receive_skb_list net/core/dev.c:5814 [inline]
  netif_receive_skb_list_internal+0x1085/0x1700 net/core/dev.c:5905
  gro_normal_list include/net/gro.h:515 [inline]
  napi_complete_done+0x3d4/0x810 net/core/dev.c:6256
  virtqueue_napi_complete drivers/net/virtio_net.c:758 [inline]
  virtnet_poll+0x5d80/0x6bf0 drivers/net/virtio_net.c:3013
  __napi_poll+0xe7/0x980 net/core/dev.c:6877
  napi_poll net/core/dev.c:6946 [inline]
  net_rx_action+0xa5a/0x19b0 net/core/dev.c:7068
  handle_softirqs+0x1a0/0x7c0 kernel/softirq.c:554
  __do_softirq kernel/softirq.c:588 [inline]
  invoke_softirq kernel/softirq.c:428 [inline]
  __irq_exit_rcu+0x68/0x180 kernel/softirq.c:655
  irq_exit_rcu+0x12/0x20 kernel/softirq.c:671
  common_interrupt+0x97/0xb0 arch/x86/kernel/irq.c:278
  asm_common_interrupt+0x2b/0x40 arch/x86/include/asm/idtentry.h:693
  __preempt_count_sub arch/x86/include/asm/preempt.h:84 [inline]
  kmsan_virt_addr_valid arch/x86/include/asm/kmsan.h:95 [inline]
  virt_to_page_or_null+0xfb/0x150 mm/kmsan/shadow.c:75
  kmsan_get_metadata+0x13e/0x1c0 mm/kmsan/shadow.c:141
  kmsan_get_shadow_origin_ptr+0x4d/0xb0 mm/kmsan/shadow.c:102
  get_shadow_origin_ptr mm/kmsan/instrumentation.c:38 [inline]
  __msan_metadata_ptr_for_store_4+0x27/0x40 mm/kmsan/instrumentation.c:93
  rcu_preempt_read_enter kernel/rcu/tree_plugin.h:390 [inline]
  __rcu_read_lock+0x46/0x70 kernel/rcu/tree_plugin.h:413
  rcu_read_lock include/linux/rcupdate.h:847 [inline]
  batadv_nc_purge_orig_hash net/batman-adv/network-coding.c:408 [inline]
  batadv_nc_worker+0x114/0x19e0 net/batman-adv/network-coding.c:719
  process_one_work kernel/workqueue.c:3229 [inline]
  process_scheduled_works+0xae0/0x1c40 kernel/workqueue.c:3310
  worker_thread+0xea7/0x14f0 kernel/workqueue.c:3391
  kthread+0x3e2/0x540 kernel/kthread.c:389
  ret_from_fork+0x6d/0x90 arch/x86/kernel/process.c:147
  ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244

Uninit was created at:
  __alloc_pages_noprof+0x9a7/0xe00 mm/page_alloc.c:4774
  alloc_pages_mpol_noprof+0x299/0x990 mm/mempolicy.c:2265
  alloc_pages_noprof+0x1bf/0x1e0 mm/mempolicy.c:2344
  alloc_slab_page mm/slub.c:2412 [inline]
  allocate_slab+0x320/0x12e0 mm/slub.c:2578
  new_slab mm/slub.c:2631 [inline]
  ___slab_alloc+0x12ef/0x35e0 mm/slub.c:3818
  __slab_alloc mm/slub.c:3908 [inline]
  __slab_alloc_node mm/slub.c:3961 [inline]
  slab_alloc_node mm/slub.c:4122 [inline]
  kmem_cache_alloc_noprof+0x57a/0xb20 mm/slub.c:4141
  inet_twsk_alloc+0x11f/0x9d0 net/ipv4/inet_timewait_sock.c:188
  tcp_time_wait+0x83/0xf50 net/ipv4/tcp_minisocks.c:309
 tcp_rcv_state_process+0x145a/0x49d0
  tcp_v4_do_rcv+0xbf9/0x11a0 net/ipv4/tcp_ipv4.c:1939
  tcp_v4_rcv+0x51df/0x5750 net/ipv4/tcp_ipv4.c:2351
  ip_protocol_deliver_rcu+0x2a3/0x13d0 net/ipv4/ip_input.c:205
  ip_local_deliver_finish+0x336/0x500 net/ipv4/ip_input.c:233
  NF_HOOK include/linux/netfilter.h:314 [inline]
  ip_local_deliver+0x21f/0x490 net/ipv4/ip_input.c:254
  dst_input include/net/dst.h:460 [inline]
  ip_sublist_rcv_finish net/ipv4/ip_input.c:578 [inline]
  ip_list_rcv_finish net/ipv4/ip_input.c:628 [inline]
  ip_sublist_rcv+0x15f3/0x17f0 net/ipv4/ip_input.c:636
  ip_list_rcv+0x9ef/0xa40 net/ipv4/ip_input.c:670
  __netif_receive_skb_list_ptype net/core/dev.c:5715 [inline]
  __netif_receive_skb_list_core+0x15c5/0x1670 net/core/dev.c:5762
  __netif_receive_skb_list net/core/dev.c:5814 [inline]
  netif_receive_skb_list_internal+0x1085/0x1700 net/core/dev.c:5905
  gro_normal_list include/net/gro.h:515 [inline]
  napi_complete_done+0x3d4/0x810 net/core/dev.c:6256
  virtqueue_napi_complete drivers/net/virtio_net.c:758 [inline]
  virtnet_poll+0x5d80/0x6bf0 drivers/net/virtio_net.c:3013
  __napi_poll+0xe7/0x980 net/core/dev.c:6877
  napi_poll net/core/dev.c:6946 [inline]
  net_rx_action+0xa5a/0x19b0 net/core/dev.c:7068
  handle_softirqs+0x1a0/0x7c0 kernel/softirq.c:554
  __do_softirq kernel/softirq.c:588 [inline]
  invoke_softirq kernel/softirq.c:428 [inline]
  __irq_exit_rcu+0x68/0x180 kernel/softirq.c:655
  irq_exit_rcu+0x12/0x20 kernel/softirq.c:671
  common_interrupt+0x97/0xb0 arch/x86/kernel/irq.c:278
  asm_common_interrupt+0x2b/0x40 arch/x86/include/asm/idtentry.h:693

CPU: 0 UID: 0 PID: 3962 Comm: kworker/u8:18 Not tainted 6.12.0-syzkaller-09073-g9f16d5e6f220 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024
Workqueue: bat_events batadv_nc_worker

Fixes: 79636038d37e ("ipv4: tcp: give socket pointer to control skbs")
Fixes: 507a96737d99 ("ipv6: tcp: give socket pointer to control skbs")
Reported-by: syzbot+8b0959fc16551d55896b@syzkaller.appspotmail.com
Link: https://lore.kernel.org/netdev/674442bd.050a0220.1cc393.0072.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Brian Vazquez <brianvv@google.com>
Link: https://patch.msgid.link/20241125093039.3095790-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet_timewait_sock.h | 2 ++
 net/ipv4/tcp_minisocks.c         | 4 ++++
 2 files changed, 6 insertions(+)

diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index beb533a0e8809..62c0a7e65d6bd 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -45,6 +45,8 @@ struct inet_timewait_sock {
 #define tw_node			__tw_common.skc_nulls_node
 #define tw_bind_node		__tw_common.skc_bind_node
 #define tw_refcnt		__tw_common.skc_refcnt
+#define tw_tx_queue_mapping	__tw_common.skc_tx_queue_mapping
+#define tw_rx_queue_mapping	__tw_common.skc_rx_queue_mapping
 #define tw_hash			__tw_common.skc_hash
 #define tw_prot			__tw_common.skc_prot
 #define tw_net			__tw_common.skc_net
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index bb1fe1ba867ac..7121d8573928c 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -326,6 +326,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		tcptw->tw_last_oow_ack_time = 0;
 		tcptw->tw_tx_delay	= tp->tcp_tx_delay;
 		tw->tw_txhash		= sk->sk_txhash;
+		tw->tw_tx_queue_mapping = sk->sk_tx_queue_mapping;
+#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING
+		tw->tw_rx_queue_mapping = sk->sk_rx_queue_mapping;
+#endif
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == PF_INET6) {
 			struct ipv6_pinfo *np = inet6_sk(sk);

From 98337d7c87577ded71114f6976edb70a163e27bc Mon Sep 17 00:00:00 2001
From: Ajay Kaher <ajay.kaher@broadcom.com>
Date: Mon, 25 Nov 2024 10:59:54 +0000
Subject: [PATCH 1488/1530] ptp: Add error handling for adjfine callback in
 ptp_clock_adjtime

ptp_clock_adjtime sets ptp->dialed_frequency even when adjfine
callback returns an error. This causes subsequent reads to return
an incorrect value.

Fix this by adding error check before ptp->dialed_frequency is set.

Fixes: 39a8cbd9ca05 ("ptp: remember the adjusted frequency")
Signed-off-by: Ajay Kaher <ajay.kaher@broadcom.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Link: https://patch.msgid.link/20241125105954.1509971-1-ajay.kaher@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/ptp/ptp_clock.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index c56cd0f63909a..77a36e7bddd54 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -150,7 +150,8 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx)
 		if (ppb > ops->max_adj || ppb < -ops->max_adj)
 			return -ERANGE;
 		err = ops->adjfine(ops, tx->freq);
-		ptp->dialed_frequency = tx->freq;
+		if (!err)
+			ptp->dialed_frequency = tx->freq;
 	} else if (tx->modes & ADJ_OFFSET) {
 		if (ops->adjphase) {
 			s32 max_phase_adj = ops->getmaxphase(ops);

From 1596a135e3180c92e42dd1fbcad321f4fb3e3b17 Mon Sep 17 00:00:00 2001
From: Martin Ottens <martin.ottens@fau.de>
Date: Mon, 25 Nov 2024 18:46:07 +0100
Subject: [PATCH 1489/1530] net/sched: tbf: correct backlog statistic for GSO
 packets

When the length of a GSO packet in the tbf qdisc is larger than the burst
size configured the packet will be segmented by the tbf_segment function.
Whenever this function is used to enqueue SKBs, the backlog statistic of
the tbf is not increased correctly. This can lead to underflows of the
'backlog' byte-statistic value when these packets are dequeued from tbf.

Reproduce the bug:
Ensure that the sender machine has GSO enabled. Configured the tbf on
the outgoing interface of the machine as follows (burstsize = 1 MTU):
$ tc qdisc add dev <oif> root handle 1: tbf rate 50Mbit burst 1514 latency 50ms

Send bulk TCP traffic out via this interface, e.g., by running an iPerf3
client on this machine. Check the qdisc statistics:
$ tc -s qdisc show dev <oif>

The 'backlog' byte-statistic has incorrect values while traffic is
transferred, e.g., high values due to u32 underflows. When the transfer
is stopped, the value is != 0, which should never happen.

This patch fixes this bug by updating the statistics correctly, even if
single SKBs of a GSO SKB cannot be enqueued.

Fixes: e43ac79a4bc6 ("sch_tbf: segment too big GSO packets")
Signed-off-by: Martin Ottens <martin.ottens@fau.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20241125174608.1484356-1-martin.ottens@fau.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_tbf.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index f1d09183ae632..dc26b22d53c73 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -208,7 +208,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch,
 	struct tbf_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *segs, *nskb;
 	netdev_features_t features = netif_skb_features(skb);
-	unsigned int len = 0, prev_len = qdisc_pkt_len(skb);
+	unsigned int len = 0, prev_len = qdisc_pkt_len(skb), seg_len;
 	int ret, nb;
 
 	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
@@ -219,21 +219,27 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch,
 	nb = 0;
 	skb_list_walk_safe(segs, segs, nskb) {
 		skb_mark_not_on_list(segs);
-		qdisc_skb_cb(segs)->pkt_len = segs->len;
-		len += segs->len;
+		seg_len = segs->len;
+		qdisc_skb_cb(segs)->pkt_len = seg_len;
 		ret = qdisc_enqueue(segs, q->qdisc, to_free);
 		if (ret != NET_XMIT_SUCCESS) {
 			if (net_xmit_drop_count(ret))
 				qdisc_qstats_drop(sch);
 		} else {
 			nb++;
+			len += seg_len;
 		}
 	}
 	sch->q.qlen += nb;
-	if (nb > 1)
+	sch->qstats.backlog += len;
+	if (nb > 0) {
 		qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
-	consume_skb(skb);
-	return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
+		consume_skb(skb);
+		return NET_XMIT_SUCCESS;
+	}
+
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
 }
 
 static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch,

From eedcad2f2a371786f8a32d0046794103dadcedf3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 26 Nov 2024 14:59:11 +0000
Subject: [PATCH 1490/1530] selinux: use sk_to_full_sk() in selinux_ip_output()

In blamed commit, TCP started to attach timewait sockets to
some skbs.

syzbot reported that selinux_ip_output() was not expecting them yet.

Note that using sk_to_full_sk() is still allowing the
following sk_listener() check to work as before.

BUG: KASAN: slab-out-of-bounds in selinux_sock security/selinux/include/objsec.h:207 [inline]
BUG: KASAN: slab-out-of-bounds in selinux_ip_output+0x1e0/0x1f0 security/selinux/hooks.c:5761
Read of size 8 at addr ffff88804e86e758 by task syz-executor347/5894

CPU: 0 UID: 0 PID: 5894 Comm: syz-executor347 Not tainted 6.12.0-syzkaller-05480-gfcc79e1714e8 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/30/2024
Call Trace:
 <IRQ>
  __dump_stack lib/dump_stack.c:94 [inline]
  dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:120
  print_address_description mm/kasan/report.c:377 [inline]
  print_report+0xc3/0x620 mm/kasan/report.c:488
  kasan_report+0xd9/0x110 mm/kasan/report.c:601
  selinux_sock security/selinux/include/objsec.h:207 [inline]
  selinux_ip_output+0x1e0/0x1f0 security/selinux/hooks.c:5761
  nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline]
  nf_hook_slow+0xbb/0x200 net/netfilter/core.c:626
  nf_hook+0x386/0x6d0 include/linux/netfilter.h:269
  __ip_local_out+0x339/0x640 net/ipv4/ip_output.c:119
  ip_local_out net/ipv4/ip_output.c:128 [inline]
  ip_send_skb net/ipv4/ip_output.c:1505 [inline]
  ip_push_pending_frames+0xa0/0x5b0 net/ipv4/ip_output.c:1525
  ip_send_unicast_reply+0xd0e/0x1650 net/ipv4/ip_output.c:1672
  tcp_v4_send_ack+0x976/0x13f0 net/ipv4/tcp_ipv4.c:1024
  tcp_v4_timewait_ack net/ipv4/tcp_ipv4.c:1077 [inline]
  tcp_v4_rcv+0x2f96/0x4390 net/ipv4/tcp_ipv4.c:2428
  ip_protocol_deliver_rcu+0xba/0x4c0 net/ipv4/ip_input.c:205
  ip_local_deliver_finish+0x316/0x570 net/ipv4/ip_input.c:233
  NF_HOOK include/linux/netfilter.h:314 [inline]
  NF_HOOK include/linux/netfilter.h:308 [inline]
  ip_local_deliver+0x18e/0x1f0 net/ipv4/ip_input.c:254
  dst_input include/net/dst.h:460 [inline]
  ip_rcv_finish net/ipv4/ip_input.c:447 [inline]
  NF_HOOK include/linux/netfilter.h:314 [inline]
  NF_HOOK include/linux/netfilter.h:308 [inline]
  ip_rcv+0x2c3/0x5d0 net/ipv4/ip_input.c:567
  __netif_receive_skb_one_core+0x199/0x1e0 net/core/dev.c:5672
  __netif_receive_skb+0x1d/0x160 net/core/dev.c:5785
  process_backlog+0x443/0x15f0 net/core/dev.c:6117
  __napi_poll.constprop.0+0xb7/0x550 net/core/dev.c:6877
  napi_poll net/core/dev.c:6946 [inline]
  net_rx_action+0xa94/0x1010 net/core/dev.c:7068
  handle_softirqs+0x213/0x8f0 kernel/softirq.c:554
  do_softirq kernel/softirq.c:455 [inline]
  do_softirq+0xb2/0xf0 kernel/softirq.c:442
 </IRQ>
 <TASK>
  __local_bh_enable_ip+0x100/0x120 kernel/softirq.c:382
  local_bh_enable include/linux/bottom_half.h:33 [inline]
  rcu_read_unlock_bh include/linux/rcupdate.h:919 [inline]
  __dev_queue_xmit+0x8af/0x43e0 net/core/dev.c:4461
  dev_queue_xmit include/linux/netdevice.h:3168 [inline]
  neigh_hh_output include/net/neighbour.h:523 [inline]
  neigh_output include/net/neighbour.h:537 [inline]
  ip_finish_output2+0xc6c/0x2150 net/ipv4/ip_output.c:236
  __ip_finish_output net/ipv4/ip_output.c:314 [inline]
  __ip_finish_output+0x49e/0x950 net/ipv4/ip_output.c:296
  ip_finish_output+0x35/0x380 net/ipv4/ip_output.c:324
  NF_HOOK_COND include/linux/netfilter.h:303 [inline]
  ip_output+0x13b/0x2a0 net/ipv4/ip_output.c:434
  dst_output include/net/dst.h:450 [inline]
  ip_local_out+0x33e/0x4a0 net/ipv4/ip_output.c:130
  __ip_queue_xmit+0x777/0x1970 net/ipv4/ip_output.c:536
  __tcp_transmit_skb+0x2b39/0x3df0 net/ipv4/tcp_output.c:1466
  tcp_transmit_skb net/ipv4/tcp_output.c:1484 [inline]
  tcp_write_xmit+0x12b1/0x8560 net/ipv4/tcp_output.c:2827
  __tcp_push_pending_frames+0xaf/0x390 net/ipv4/tcp_output.c:3010
  tcp_send_fin+0x154/0xc70 net/ipv4/tcp_output.c:3616
  __tcp_close+0x96b/0xff0 net/ipv4/tcp.c:3130
  tcp_close+0x28/0x120 net/ipv4/tcp.c:3221
  inet_release+0x13c/0x280 net/ipv4/af_inet.c:435
  __sock_release net/socket.c:640 [inline]
  sock_release+0x8e/0x1d0 net/socket.c:668
  smc_clcsock_release+0xb7/0xe0 net/smc/smc_close.c:34
  __smc_release+0x5c2/0x880 net/smc/af_smc.c:301
  smc_release+0x1fc/0x5f0 net/smc/af_smc.c:344
  __sock_release+0xb0/0x270 net/socket.c:640
  sock_close+0x1c/0x30 net/socket.c:1408
  __fput+0x3f8/0xb60 fs/file_table.c:450
  __fput_sync+0xa1/0xc0 fs/file_table.c:535
  __do_sys_close fs/open.c:1550 [inline]
  __se_sys_close fs/open.c:1535 [inline]
  __x64_sys_close+0x86/0x100 fs/open.c:1535
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f6814c9ae10
Code: ff f7 d8 64 89 02 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 80 3d b1 e2 07 00 00 74 17 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 48 c3 0f 1f 80 00 00 00 00 48 83 ec 18 89 7c
RSP: 002b:00007fffb2389758 EFLAGS: 00000202 ORIG_RAX: 0000000000000003
RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 00007f6814c9ae10
RDX: 0000000000000010 RSI: 0000000020000000 RDI: 0000000000000003
RBP: 00000000000f4240 R08: 0000000000000001 R09: 0000000000000001
R10: 0000000000000001 R11: 0000000000000202 R12: 00007fffb23897b0
R13: 00000000000141c3 R14: 00007fffb238977c R15: 00007fffb2389790
 </TASK>

Fixes: 79636038d37e ("ipv4: tcp: give socket pointer to control skbs")
Reported-by: syzbot+2d9f5f948c31dcb7745e@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/lkml/6745e1a2.050a0220.1286eb.001c.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20241126145911.4187198-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 security/selinux/hooks.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index f5a08f94e0940..366c87a40bd15 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -5738,7 +5738,7 @@ static unsigned int selinux_ip_output(void *priv, struct sk_buff *skb,
 	/* we do this in the LOCAL_OUT path and not the POST_ROUTING path
 	 * because we want to make sure we apply the necessary labeling
 	 * before IPsec is applied so we can leverage AH protection */
-	sk = skb->sk;
+	sk = sk_to_full_sk(skb->sk);
 	if (sk) {
 		struct sk_security_struct *sksec;
 

From 16ed454515a4fdcb8050a399bdcba6961aca089d Mon Sep 17 00:00:00 2001
From: Vyshnav Ajith <puthen1977@gmail.com>
Date: Fri, 22 Nov 2024 04:18:27 +0530
Subject: [PATCH 1491/1530] docs: net: bareudp: fix spelling and grammar
 mistakes

The BareUDP documentation had several grammar and spelling mistakes,
making it harder to read. This patch fixes those errors to improve
clarity and readability for developers.

Signed-off-by: Vyshnav Ajith <puthen1977@gmail.com>
Link: https://patch.msgid.link/20241121224827.12293-1-puthen1977@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/bareudp.rst | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/Documentation/networking/bareudp.rst b/Documentation/networking/bareudp.rst
index b9d04ee6dac14..621cb9575c8f7 100644
--- a/Documentation/networking/bareudp.rst
+++ b/Documentation/networking/bareudp.rst
@@ -6,16 +6,17 @@ Bare UDP Tunnelling Module Documentation
 
 There are various L3 encapsulation standards using UDP being discussed to
 leverage the UDP based load balancing capability of different networks.
-MPLSoUDP (__ https://tools.ietf.org/html/rfc7510) is one among them.
+MPLSoUDP (https://tools.ietf.org/html/rfc7510) is one among them.
 
 The Bareudp tunnel module provides a generic L3 encapsulation support for
 tunnelling different L3 protocols like MPLS, IP, NSH etc. inside a UDP tunnel.
 
 Special Handling
 ----------------
+
 The bareudp device supports special handling for MPLS & IP as they can have
 multiple ethertypes.
-MPLS procotcol can have ethertypes ETH_P_MPLS_UC  (unicast) & ETH_P_MPLS_MC (multicast).
+The MPLS protocol can have ethertypes ETH_P_MPLS_UC (unicast) & ETH_P_MPLS_MC (multicast).
 IP protocol can have ethertypes ETH_P_IP (v4) & ETH_P_IPV6 (v6).
 This special handling can be enabled only for ethertypes ETH_P_IP & ETH_P_MPLS_UC
 with a flag called multiproto mode.
@@ -52,7 +53,7 @@ be enabled explicitly with the "multiproto" flag.
 3) Device Usage
 
 The bareudp device could be used along with OVS or flower filter in TC.
-The OVS or TC flower layer must set the tunnel information in SKB dst field before
-sending packet buffer to the bareudp device for transmission. On reception the
-bareudp device extracts and stores the tunnel information in SKB dst field before
+The OVS or TC flower layer must set the tunnel information in the SKB dst field before
+sending the packet buffer to the bareudp device for transmission. On reception, the
+bareUDP device extracts and stores the tunnel information in the SKB dst field before
 passing the packet buffer to the network stack.

From b9653d19e556c6afd035602927a93d100a0d7644 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 26 Nov 2024 14:43:44 +0000
Subject: [PATCH 1492/1530] net: hsr: avoid potential out-of-bound access in
 fill_frame_info()

syzbot is able to feed a packet with 14 bytes, pretending
it is a vlan one.

Since fill_frame_info() is relying on skb->mac_len already,
extend the check to cover this case.

BUG: KMSAN: uninit-value in fill_frame_info net/hsr/hsr_forward.c:709 [inline]
 BUG: KMSAN: uninit-value in hsr_forward_skb+0x9ee/0x3b10 net/hsr/hsr_forward.c:724
  fill_frame_info net/hsr/hsr_forward.c:709 [inline]
  hsr_forward_skb+0x9ee/0x3b10 net/hsr/hsr_forward.c:724
  hsr_dev_xmit+0x2f0/0x350 net/hsr/hsr_device.c:235
  __netdev_start_xmit include/linux/netdevice.h:5002 [inline]
  netdev_start_xmit include/linux/netdevice.h:5011 [inline]
  xmit_one net/core/dev.c:3590 [inline]
  dev_hard_start_xmit+0x247/0xa20 net/core/dev.c:3606
  __dev_queue_xmit+0x366a/0x57d0 net/core/dev.c:4434
  dev_queue_xmit include/linux/netdevice.h:3168 [inline]
  packet_xmit+0x9c/0x6c0 net/packet/af_packet.c:276
  packet_snd net/packet/af_packet.c:3146 [inline]
  packet_sendmsg+0x91ae/0xa6f0 net/packet/af_packet.c:3178
  sock_sendmsg_nosec net/socket.c:711 [inline]
  __sock_sendmsg+0x30f/0x380 net/socket.c:726
  __sys_sendto+0x594/0x750 net/socket.c:2197
  __do_sys_sendto net/socket.c:2204 [inline]
  __se_sys_sendto net/socket.c:2200 [inline]
  __x64_sys_sendto+0x125/0x1d0 net/socket.c:2200
  x64_sys_call+0x346a/0x3c30 arch/x86/include/generated/asm/syscalls_64.h:45
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xcd/0x1e0 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Uninit was created at:
  slab_post_alloc_hook mm/slub.c:4091 [inline]
  slab_alloc_node mm/slub.c:4134 [inline]
  kmem_cache_alloc_node_noprof+0x6bf/0xb80 mm/slub.c:4186
  kmalloc_reserve+0x13d/0x4a0 net/core/skbuff.c:587
  __alloc_skb+0x363/0x7b0 net/core/skbuff.c:678
  alloc_skb include/linux/skbuff.h:1323 [inline]
  alloc_skb_with_frags+0xc8/0xd00 net/core/skbuff.c:6612
  sock_alloc_send_pskb+0xa81/0xbf0 net/core/sock.c:2881
  packet_alloc_skb net/packet/af_packet.c:2995 [inline]
  packet_snd net/packet/af_packet.c:3089 [inline]
  packet_sendmsg+0x74c6/0xa6f0 net/packet/af_packet.c:3178
  sock_sendmsg_nosec net/socket.c:711 [inline]
  __sock_sendmsg+0x30f/0x380 net/socket.c:726
  __sys_sendto+0x594/0x750 net/socket.c:2197
  __do_sys_sendto net/socket.c:2204 [inline]
  __se_sys_sendto net/socket.c:2200 [inline]
  __x64_sys_sendto+0x125/0x1d0 net/socket.c:2200
  x64_sys_call+0x346a/0x3c30 arch/x86/include/generated/asm/syscalls_64.h:45
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xcd/0x1e0 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: 48b491a5cc74 ("net: hsr: fix mac_len checks")
Reported-by: syzbot+671e2853f9851d039551@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/6745dc7f.050a0220.21d33d.0018.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: WingMan Kwok <w-kwok2@ti.com>
Cc: Murali Karicheri <m-karicheri2@ti.com>
Cc: MD Danish Anwar <danishanwar@ti.com>
Cc: Jiri Pirko <jiri@nvidia.com>
Cc: George McCollister <george.mccollister@gmail.com>
Link: https://patch.msgid.link/20241126144344.4177332-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/hsr/hsr_forward.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index aa6acebc7c1ef..87bb3a91598ee 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -700,6 +700,8 @@ static int fill_frame_info(struct hsr_frame_info *frame,
 		frame->is_vlan = true;
 
 	if (frame->is_vlan) {
+		if (skb->mac_len < offsetofend(struct hsr_vlan_ethhdr, vlanhdr))
+			return -EINVAL;
 		vlan_hdr = (struct hsr_vlan_ethhdr *)ethhdr;
 		proto = vlan_hdr->vlanhdr.h_vlan_encapsulated_proto;
 	}

From be75cda92a65a13db242117d674cd5584477a168 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 27 Nov 2024 15:58:29 -0700
Subject: [PATCH 1493/1530] bnxt_en: ethtool: Supply ntuple rss context action

Commit 2f4f9fe5bf5f ("bnxt_en: Support adding ntuple rules on RSS
contexts") added support for redirecting to an RSS context as an ntuple
rule action. However, it forgot to update the ETHTOOL_GRXCLSRULE
codepath. This caused `ethtool -n` to always report the action as
"Action: Direct to queue 0" which is wrong.

Fix by teaching bnxt driver to report the RSS context when applicable.

Fixes: 2f4f9fe5bf5f ("bnxt_en: Support adding ntuple rules on RSS contexts")
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://patch.msgid.link/2e884ae39e08dc5123be7c170a6089cefe6a78f7.1732748253.git.dxu@dxuuu.xyz
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index f1f6bb328a55b..d87681d711067 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1187,10 +1187,14 @@ static int bnxt_grxclsrule(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 		}
 	}
 
-	if (fltr->base.flags & BNXT_ACT_DROP)
+	if (fltr->base.flags & BNXT_ACT_DROP) {
 		fs->ring_cookie = RX_CLS_FLOW_DISC;
-	else
+	} else if (fltr->base.flags & BNXT_ACT_RSS_CTX) {
+		fs->flow_type |= FLOW_RSS;
+		cmd->rss_context = fltr->base.fw_vnic_id;
+	} else {
 		fs->ring_cookie = fltr->base.rxq;
+	}
 	rc = 0;
 
 fltr_err:

From 7078d43b2374daedf254662053e924c938eb86b3 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 27 Nov 2024 15:58:30 -0700
Subject: [PATCH 1494/1530] selftests: drv-net: rss_ctx: Add test for ntuple
 rule

Extend the rss_ctx test suite to test that an ntuple action that
redirects to an RSS context contains that information in `ethtool -n`.
Otherwise the output from ethtool is highly deceiving. This test helps
ensure drivers are compliant with the API.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://patch.msgid.link/759870e430b7c93ecaae6e448f30a47284c59637.1732748253.git.dxu@dxuuu.xyz
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/hw/rss_ctx.py | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index 0b49ce7ae6784..ca8a7edff3dda 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -3,7 +3,8 @@
 
 import datetime
 import random
-from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ne, ksft_ge, ksft_lt
+import re
+from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ne, ksft_ge, ksft_lt, ksft_true
 from lib.py import NetDrvEpEnv
 from lib.py import EthtoolFamily, NetdevFamily
 from lib.py import KsftSkipEx, KsftFailEx
@@ -96,6 +97,13 @@ def _send_traffic_check(cfg, port, name, params):
                 f"traffic on inactive queues ({name}): " + str(cnts))
 
 
+def _ntuple_rule_check(cfg, rule_id, ctx_id):
+    """Check that ntuple rule references RSS context ID"""
+    text = ethtool(f"-n {cfg.ifname} rule {rule_id}").stdout
+    pattern = f"RSS Context (ID: )?{ctx_id}"
+    ksft_true(re.search(pattern, text), "RSS context not referenced in ntuple rule")
+
+
 def test_rss_key_indir(cfg):
     """Test basics like updating the main RSS key and indirection table."""
 
@@ -459,6 +467,8 @@ def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None):
         ntuple = ethtool_create(cfg, "-N", flow)
         defer(ethtool, f"-N {cfg.ifname} delete {ntuple}")
 
+        _ntuple_rule_check(cfg, ntuple, ctx_id)
+
     for i in range(ctx_cnt):
         _send_traffic_check(cfg, ports[i], f"context {i}",
                             { 'target': (2+i*2, 3+i*2),

From c44daa7e3c73229f7ac74985acb8c7fb909c4e0a Mon Sep 17 00:00:00 2001
From: Dong Chenchen <dongchenchen2@huawei.com>
Date: Wed, 27 Nov 2024 12:08:50 +0800
Subject: [PATCH 1495/1530] net: Fix icmp host relookup triggering ip_rt_bug

arp link failure may trigger ip_rt_bug while xfrm enabled, call trace is:

WARNING: CPU: 0 PID: 0 at net/ipv4/route.c:1241 ip_rt_bug+0x14/0x20
Modules linked in:
CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.0-rc6-00077-g2e1b3cc9d7f7
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
RIP: 0010:ip_rt_bug+0x14/0x20
Call Trace:
 <IRQ>
 ip_send_skb+0x14/0x40
 __icmp_send+0x42d/0x6a0
 ipv4_link_failure+0xe2/0x1d0
 arp_error_report+0x3c/0x50
 neigh_invalidate+0x8d/0x100
 neigh_timer_handler+0x2e1/0x330
 call_timer_fn+0x21/0x120
 __run_timer_base.part.0+0x1c9/0x270
 run_timer_softirq+0x4c/0x80
 handle_softirqs+0xac/0x280
 irq_exit_rcu+0x62/0x80
 sysvec_apic_timer_interrupt+0x77/0x90

The script below reproduces this scenario:
ip xfrm policy add src 0.0.0.0/0 dst 0.0.0.0/0 \
	dir out priority 0 ptype main flag localok icmp
ip l a veth1 type veth
ip a a 192.168.141.111/24 dev veth0
ip l s veth0 up
ping 192.168.141.155 -c 1

icmp_route_lookup() create input routes for locally generated packets
while xfrm relookup ICMP traffic.Then it will set input route
(dst->out = ip_rt_bug) to skb for DESTUNREACH.

For ICMP err triggered by locally generated packets, dst->dev of output
route is loopback. Generally, xfrm relookup verification is not required
on loopback interfaces (net.ipv4.conf.lo.disable_xfrm = 1).

Skip icmp relookup for locally generated packets to fix it.

Fixes: 8b7817f3a959 ("[IPSEC]: Add ICMP host relookup support")
Signed-off-by: Dong Chenchen <dongchenchen2@huawei.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20241127040850.1513135-1-dongchenchen2@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/icmp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 4f088fa1c2f2c..963a89ae9c26e 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -517,6 +517,9 @@ static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4,
 	if (!IS_ERR(dst)) {
 		if (rt != rt2)
 			return rt;
+		if (inet_addr_type_dev_table(net, route_lookup_dev,
+					     fl4->daddr) == RTN_LOCAL)
+			return rt;
 	} else if (PTR_ERR(dst) == -EPERM) {
 		rt = NULL;
 	} else {

From 8165c86ff65c5bff95ab0a00e900ffa255a1497f Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 25 Nov 2024 10:29:05 +0800
Subject: [PATCH 1496/1530] net: phy: micrel: Dynamically control external
 clock of KSZ PHY

On the i.MX6ULL-14x14-EVK board, when using the 6.12 kernel, it is found
that after disabling the two network ports, the clk_enable_count of the
enet1_ref and enet2_ref clocks is not 0 (these two clocks are used as the
clock source of the RMII reference clock of the two KSZ8081 PHYs), but
there is no such problem in the 6.6 kernel.

After analysis, we found that since the commit 985329462723 ("net: phy:
micrel: use devm_clk_get_optional_enabled for the rmii-ref clock"), the
external clock of KSZ PHY has been enabled when the PHY driver probes,
and it can only be disabled when the PHY driver is removed. This causes
the clock to continue working when the system is suspended or the network
port is down.

To solve this problem, the clock is enabled when resume() of the PHY
driver is called, and the clock is disabled when suspend() is called.
Since the PHY driver's resume() and suspend() interfaces are not called
in pairs, an additional clk_enable flag is added. When suspend() is
called, the clock is disabled only if clk_enable is true. Conversely,
when resume() is called, the clock is enabled if clk_enable is false.

Fixes: 985329462723 ("net: phy: micrel: use devm_clk_get_optional_enabled for the rmii-ref clock")
Fixes: 99ac4cbcc2a5 ("net: phy: micrel: allow usage of generic ethernet-phy clock")
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/micrel.c | 103 ++++++++++++++++++++++++++++++++++++---
 1 file changed, 95 insertions(+), 8 deletions(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 3ef5088406740..44577b5d48d50 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -432,10 +432,12 @@ struct kszphy_ptp_priv {
 struct kszphy_priv {
 	struct kszphy_ptp_priv ptp_priv;
 	const struct kszphy_type *type;
+	struct clk *clk;
 	int led_mode;
 	u16 vct_ctrl1000;
 	bool rmii_ref_clk_sel;
 	bool rmii_ref_clk_sel_val;
+	bool clk_enable;
 	u64 stats[ARRAY_SIZE(kszphy_hw_stats)];
 };
 
@@ -2050,8 +2052,27 @@ static void kszphy_get_stats(struct phy_device *phydev,
 		data[i] = kszphy_get_stat(phydev, i);
 }
 
+static void kszphy_enable_clk(struct kszphy_priv *priv)
+{
+	if (!priv->clk_enable && priv->clk) {
+		clk_prepare_enable(priv->clk);
+		priv->clk_enable = true;
+	}
+}
+
+static void kszphy_disable_clk(struct kszphy_priv *priv)
+{
+	if (priv->clk_enable && priv->clk) {
+		clk_disable_unprepare(priv->clk);
+		priv->clk_enable = false;
+	}
+}
+
 static int kszphy_suspend(struct phy_device *phydev)
 {
+	struct kszphy_priv *priv = phydev->priv;
+	int ret;
+
 	/* Disable PHY Interrupts */
 	if (phy_interrupt_is_valid(phydev)) {
 		phydev->interrupts = PHY_INTERRUPT_DISABLED;
@@ -2059,7 +2080,13 @@ static int kszphy_suspend(struct phy_device *phydev)
 			phydev->drv->config_intr(phydev);
 	}
 
-	return genphy_suspend(phydev);
+	ret = genphy_suspend(phydev);
+	if (ret)
+		return ret;
+
+	kszphy_disable_clk(priv);
+
+	return 0;
 }
 
 static void kszphy_parse_led_mode(struct phy_device *phydev)
@@ -2088,8 +2115,11 @@ static void kszphy_parse_led_mode(struct phy_device *phydev)
 
 static int kszphy_resume(struct phy_device *phydev)
 {
+	struct kszphy_priv *priv = phydev->priv;
 	int ret;
 
+	kszphy_enable_clk(priv);
+
 	genphy_resume(phydev);
 
 	/* After switching from power-down to normal mode, an internal global
@@ -2112,6 +2142,24 @@ static int kszphy_resume(struct phy_device *phydev)
 	return 0;
 }
 
+static int ksz8041_resume(struct phy_device *phydev)
+{
+	struct kszphy_priv *priv = phydev->priv;
+
+	kszphy_enable_clk(priv);
+
+	return 0;
+}
+
+static int ksz8041_suspend(struct phy_device *phydev)
+{
+	struct kszphy_priv *priv = phydev->priv;
+
+	kszphy_disable_clk(priv);
+
+	return 0;
+}
+
 static int ksz9477_resume(struct phy_device *phydev)
 {
 	int ret;
@@ -2150,8 +2198,11 @@ static int ksz9477_resume(struct phy_device *phydev)
 
 static int ksz8061_resume(struct phy_device *phydev)
 {
+	struct kszphy_priv *priv = phydev->priv;
 	int ret;
 
+	kszphy_enable_clk(priv);
+
 	/* This function can be called twice when the Ethernet device is on. */
 	ret = phy_read(phydev, MII_BMCR);
 	if (ret < 0)
@@ -2194,7 +2245,7 @@ static int kszphy_probe(struct phy_device *phydev)
 
 	kszphy_parse_led_mode(phydev);
 
-	clk = devm_clk_get_optional_enabled(&phydev->mdio.dev, "rmii-ref");
+	clk = devm_clk_get_optional(&phydev->mdio.dev, "rmii-ref");
 	/* NOTE: clk may be NULL if building without CONFIG_HAVE_CLK */
 	if (!IS_ERR_OR_NULL(clk)) {
 		unsigned long rate = clk_get_rate(clk);
@@ -2216,11 +2267,14 @@ static int kszphy_probe(struct phy_device *phydev)
 		}
 	} else if (!clk) {
 		/* unnamed clock from the generic ethernet-phy binding */
-		clk = devm_clk_get_optional_enabled(&phydev->mdio.dev, NULL);
+		clk = devm_clk_get_optional(&phydev->mdio.dev, NULL);
 		if (IS_ERR(clk))
 			return PTR_ERR(clk);
 	}
 
+	if (!IS_ERR_OR_NULL(clk))
+		priv->clk = clk;
+
 	if (ksz8041_fiber_mode(phydev))
 		phydev->port = PORT_FIBRE;
 
@@ -5290,15 +5344,45 @@ static int lan8841_probe(struct phy_device *phydev)
 	return 0;
 }
 
+static int lan8804_suspend(struct phy_device *phydev)
+{
+	struct kszphy_priv *priv = phydev->priv;
+	int ret;
+
+	ret = genphy_suspend(phydev);
+	if (ret)
+		return ret;
+
+	kszphy_disable_clk(priv);
+
+	return 0;
+}
+
+static int lan8841_resume(struct phy_device *phydev)
+{
+	struct kszphy_priv *priv = phydev->priv;
+
+	kszphy_enable_clk(priv);
+
+	return genphy_resume(phydev);
+}
+
 static int lan8841_suspend(struct phy_device *phydev)
 {
 	struct kszphy_priv *priv = phydev->priv;
 	struct kszphy_ptp_priv *ptp_priv = &priv->ptp_priv;
+	int ret;
 
 	if (ptp_priv->ptp_clock)
 		ptp_cancel_worker_sync(ptp_priv->ptp_clock);
 
-	return genphy_suspend(phydev);
+	ret = genphy_suspend(phydev);
+	if (ret)
+		return ret;
+
+	kszphy_disable_clk(priv);
+
+	return 0;
 }
 
 static struct phy_driver ksphy_driver[] = {
@@ -5358,9 +5442,12 @@ static struct phy_driver ksphy_driver[] = {
 	.get_sset_count = kszphy_get_sset_count,
 	.get_strings	= kszphy_get_strings,
 	.get_stats	= kszphy_get_stats,
-	/* No suspend/resume callbacks because of errata DS80000700A,
-	 * receiver error following software power down.
+	/* Because of errata DS80000700A, receiver error following software
+	 * power down. Suspend and resume callbacks only disable and enable
+	 * external rmii reference clock.
 	 */
+	.suspend	= ksz8041_suspend,
+	.resume		= ksz8041_resume,
 }, {
 	.phy_id		= PHY_ID_KSZ8041RNLI,
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
@@ -5507,7 +5594,7 @@ static struct phy_driver ksphy_driver[] = {
 	.get_sset_count	= kszphy_get_sset_count,
 	.get_strings	= kszphy_get_strings,
 	.get_stats	= kszphy_get_stats,
-	.suspend	= genphy_suspend,
+	.suspend	= lan8804_suspend,
 	.resume		= kszphy_resume,
 	.config_intr	= lan8804_config_intr,
 	.handle_interrupt = lan8804_handle_interrupt,
@@ -5526,7 +5613,7 @@ static struct phy_driver ksphy_driver[] = {
 	.get_strings	= kszphy_get_strings,
 	.get_stats	= kszphy_get_stats,
 	.suspend	= lan8841_suspend,
-	.resume		= genphy_resume,
+	.resume		= lan8841_resume,
 	.cable_test_start	= lan8814_cable_test_start,
 	.cable_test_get_status	= ksz886x_cable_test_get_status,
 }, {

From 08a6691feda0697fb1fe1dd2fd7234bf82223cfb Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Mon, 25 Nov 2024 09:40:50 +0100
Subject: [PATCH 1497/1530] net: phy: microchip: Reset LAN88xx PHY to ensure
 clean link state on LAN7800/7850

Fix outdated MII_LPA data in the LAN88xx PHY, which is used in LAN7800
and LAN7850 USB Ethernet controllers. Due to a hardware limitation, the
PHY cannot reliably update link status after parallel detection when the
link partner does not support auto-negotiation. To mitigate this, add a
PHY reset in `lan88xx_link_change_notify()` when `phydev->state` is
`PHY_NOLINK`, ensuring the PHY starts in a clean state and reports
accurate fixed link parallel detection results.

Fixes: 792aec47d59d9 ("add microchip LAN88xx phy driver")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/microchip.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c
index d3273bc0da4a1..691969a4910f2 100644
--- a/drivers/net/phy/microchip.c
+++ b/drivers/net/phy/microchip.c
@@ -351,6 +351,22 @@ static int lan88xx_config_aneg(struct phy_device *phydev)
 static void lan88xx_link_change_notify(struct phy_device *phydev)
 {
 	int temp;
+	int ret;
+
+	/* Reset PHY to ensure MII_LPA provides up-to-date information. This
+	 * issue is reproducible only after parallel detection, as described
+	 * in IEEE 802.3-2022, Section 28.2.3.1 ("Parallel detection function"),
+	 * where the link partner does not support auto-negotiation.
+	 */
+	if (phydev->state == PHY_NOLINK) {
+		ret = phy_init_hw(phydev);
+		if (ret < 0)
+			goto link_change_notify_failed;
+
+		ret = _phy_start_aneg(phydev);
+		if (ret < 0)
+			goto link_change_notify_failed;
+	}
 
 	/* At forced 100 F/H mode, chip may fail to set mode correctly
 	 * when cable is switched between long(~50+m) and short one.
@@ -377,6 +393,11 @@ static void lan88xx_link_change_notify(struct phy_device *phydev)
 		temp |= LAN88XX_INT_MASK_MDINTPIN_EN_;
 		phy_write(phydev, LAN88XX_INT_MASK, temp);
 	}
+
+	return;
+
+link_change_notify_failed:
+	phydev_err(phydev, "Link change process failed %pe\n", ERR_PTR(ret));
 }
 
 /**

From 2ff49abfdcef7d7de021a4d6feae9f879b74887a Mon Sep 17 00:00:00 2001
From: Martin Ottens <martin.ottens@fau.de>
Date: Tue, 26 Nov 2024 00:18:25 +0100
Subject: [PATCH 1498/1530] net/sched: netem: account for backlog updates from
 child qdisc

When netem is used with a child qdisc, the child qdisc can use
'qdisc_tree_reduce_backlog' to inform its parent, netem, about created or
dropped SKBs. This function updates 'qlen' and the backlog statistics of
netem, but netem does not account for changes made by a child qdisc. If a
child qdisc creates new SKBs during enqueue and informs its parent about
this, netem's 'qlen' value is increased. When netem dequeues the newly
created SKBs from the child, the 'qlen' in netem is not updated. If 'qlen'
reaches the configured limit, the enqueue function stops working, even
though the tfifo is not full.

Reproduce the bug:
Ensure that the sender machine has GSO enabled. Configure netem as root
qdisc and tbf as its child on the outgoing interface of the machine
as follows:
$ tc qdisc add dev <oif> root handle 1: netem delay 100ms limit 100
$ tc qdisc add dev <oif> parent 1:0 tbf rate 50Mbit burst 1542 latency 50ms

Send bulk TCP traffic out via this interface, e.g., by running an iPerf3
client on the machine. Check the qdisc statistics:
$ tc -s qdisc show dev <oif>

tbf segments the GSO SKBs (tbf_segment) and updates the netem's 'qlen'.
The interface fully stops transferring packets and "locks". In this case,
the child qdisc and tfifo are empty, but 'qlen' indicates the tfifo is at
its limit and no more packets are accepted.

This patch adds a counter for the entries in the tfifo. Netem's 'qlen' is
only decreased when a packet is returned by its dequeue function, and not
during enqueuing into the child qdisc. External updates to 'qlen' are thus
accounted for and only the behavior of the backlog statistics changes.
This statistics now show the total number/length of SKBs held in the tfifo
and in the child qdisc. (Note: the 'backlog' byte-statistic of netem is
incorrect in the example above even after the patch is applied due to a
bug in tbf. See my previous patch ([PATCH] net/sched: tbf: correct backlog
statistic for GSO packets)).

Signed-off-by: Martin Ottens <martin.ottens@fau.de>
Signed-off-by: NipaLocal <nipa@local>
---
 net/sched/sch_netem.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index fe6fed291a7b8..71ec9986ed37f 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -79,6 +79,8 @@ struct netem_sched_data {
 	struct sk_buff	*t_head;
 	struct sk_buff	*t_tail;
 
+	u32 t_len;
+
 	/* optional qdisc for classful handling (NULL at netem init) */
 	struct Qdisc	*qdisc;
 
@@ -383,6 +385,7 @@ static void tfifo_reset(struct Qdisc *sch)
 	rtnl_kfree_skbs(q->t_head, q->t_tail);
 	q->t_head = NULL;
 	q->t_tail = NULL;
+	q->t_len = 0;
 }
 
 static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
@@ -412,6 +415,7 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 		rb_link_node(&nskb->rbnode, parent, p);
 		rb_insert_color(&nskb->rbnode, &q->t_root);
 	}
+	q->t_len++;
 	sch->q.qlen++;
 }
 
@@ -518,7 +522,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			1<<get_random_u32_below(8);
 	}
 
-	if (unlikely(sch->q.qlen >= sch->limit)) {
+	if (unlikely(q->t_len >= sch->limit)) {
 		/* re-link segs, so that qdisc_drop_all() frees them all */
 		skb->next = segs;
 		qdisc_drop_all(skb, sch, to_free);
@@ -702,8 +706,8 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 tfifo_dequeue:
 	skb = __qdisc_dequeue_head(&sch->q);
 	if (skb) {
-		qdisc_qstats_backlog_dec(sch, skb);
 deliver:
+		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_bstats_update(sch, skb);
 		return skb;
 	}
@@ -719,8 +723,7 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 
 		if (time_to_send <= now && q->slot.slot_next <= now) {
 			netem_erase_head(q, skb);
-			sch->q.qlen--;
-			qdisc_qstats_backlog_dec(sch, skb);
+			q->t_len--;
 			skb->next = NULL;
 			skb->prev = NULL;
 			/* skb->dev shares skb->rbnode area,
@@ -747,16 +750,21 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 					if (net_xmit_drop_count(err))
 						qdisc_qstats_drop(sch);
 					qdisc_tree_reduce_backlog(sch, 1, pkt_len);
+					sch->qstats.backlog -= pkt_len;
+					sch->q.qlen--;
 				}
 				goto tfifo_dequeue;
 			}
+			sch->q.qlen--;
 			goto deliver;
 		}
 
 		if (q->qdisc) {
 			skb = q->qdisc->ops->dequeue(q->qdisc);
-			if (skb)
+			if (skb) {
+				sch->q.qlen--;
 				goto deliver;
+			}
 		}
 
 		qdisc_watchdog_schedule_ns(&q->watchdog,
@@ -766,8 +774,10 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 
 	if (q->qdisc) {
 		skb = q->qdisc->ops->dequeue(q->qdisc);
-		if (skb)
+		if (skb) {
+			sch->q.qlen--;
 			goto deliver;
+		}
 	}
 	return NULL;
 }

From 53ebb84cc808abdf51547a010e7ab6c6250de6b4 Mon Sep 17 00:00:00 2001
From: Geetha sowjanya <gakula@marvell.com>
Date: Tue, 26 Nov 2024 17:14:31 +0530
Subject: [PATCH 1499/1530] octeontx2-af: Fix SDP MAC link credits
 configuration

Current driver allows only packet size < 512B as SDP_LINK_CREDIT
register is set to default value.
This patch fixes this issue by configure the register with
maximum HW supported value to allow packet size > 512B.

Fixes: 2f7f33a09516 ("octeontx2-pf: Add representors for sdp MAC")
Signed-off-by: Geetha sowjanya <gakula@marvell.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/marvell/octeontx2/af/common.h  | 1 +
 drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c | 3 +++
 2 files changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index 5d84386ed22da..406c59100a35a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -159,6 +159,7 @@ enum nix_scheduler {
 #define	SDP_HW_MIN_FRS			16
 #define CN10K_LMAC_LINK_MAX_FRS		16380 /* 16k - FCS */
 #define CN10K_LBK_LINK_MAX_FRS		65535 /* 64k */
+#define SDP_LINK_CREDIT			0x320202
 
 /* NIX RX action operation*/
 #define NIX_RX_ACTIONOP_DROP		(0x0ull)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 5d5a01dbbca11..a5d1e2bddd58d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -4672,6 +4672,9 @@ static void nix_link_config(struct rvu *rvu, int blkaddr,
 	rvu_get_lbk_link_max_frs(rvu, &lbk_max_frs);
 	rvu_get_lmac_link_max_frs(rvu, &lmac_max_frs);
 
+	/* Set SDP link credit */
+	rvu_write64(rvu, blkaddr, NIX_AF_SDP_LINK_CREDIT, SDP_LINK_CREDIT);
+
 	/* Set default min/max packet lengths allowed on NIX Rx links.
 	 *
 	 * With HW reset minlen value of 60byte, HW will treat ARP pkts

From c300abfd4ab77ba3d141a8212068073117a948c4 Mon Sep 17 00:00:00 2001
From: Ivan Solodovnikov <solodovnikov.ia@phystech.edu>
Date: Tue, 26 Nov 2024 17:39:02 +0300
Subject: [PATCH 1500/1530] dccp: Fix memory leak in dccp_feat_change_recv

If dccp_feat_push_confirm() fails after new value for SP feature was accepted
without reconciliation ('entry == NULL' branch), memory allocated for that value
with dccp_feat_clone_sp_val() is never freed.

Here is the kmemleak stack for this:

unreferenced object 0xffff88801d4ab488 (size 8):
  comm "syz-executor310", pid 1127, jiffies 4295085598 (age 41.666s)
  hex dump (first 8 bytes):
    01 b4 4a 1d 80 88 ff ff                          ..J.....
  backtrace:
    [<00000000db7cabfe>] kmemdup+0x23/0x50 mm/util.c:128
    [<0000000019b38405>] kmemdup include/linux/string.h:465 [inline]
    [<0000000019b38405>] dccp_feat_clone_sp_val net/dccp/feat.c:371 [inline]
    [<0000000019b38405>] dccp_feat_clone_sp_val net/dccp/feat.c:367 [inline]
    [<0000000019b38405>] dccp_feat_change_recv net/dccp/feat.c:1145 [inline]
    [<0000000019b38405>] dccp_feat_parse_options+0x1196/0x2180 net/dccp/feat.c:1416
    [<00000000b1f6d94a>] dccp_parse_options+0xa2a/0x1260 net/dccp/options.c:125
    [<0000000030d7b621>] dccp_rcv_state_process+0x197/0x13d0 net/dccp/input.c:650
    [<000000001f74c72e>] dccp_v4_do_rcv+0xf9/0x1a0 net/dccp/ipv4.c:688
    [<00000000a6c24128>] sk_backlog_rcv include/net/sock.h:1041 [inline]
    [<00000000a6c24128>] __release_sock+0x139/0x3b0 net/core/sock.c:2570
    [<00000000cf1f3a53>] release_sock+0x54/0x1b0 net/core/sock.c:3111
    [<000000008422fa23>] inet_wait_for_connect net/ipv4/af_inet.c:603 [inline]
    [<000000008422fa23>] __inet_stream_connect+0x5d0/0xf70 net/ipv4/af_inet.c:696
    [<0000000015b6f64d>] inet_stream_connect+0x53/0xa0 net/ipv4/af_inet.c:735
    [<0000000010122488>] __sys_connect_file+0x15c/0x1a0 net/socket.c:1865
    [<00000000b4b70023>] __sys_connect+0x165/0x1a0 net/socket.c:1882
    [<00000000f4cb3815>] __do_sys_connect net/socket.c:1892 [inline]
    [<00000000f4cb3815>] __se_sys_connect net/socket.c:1889 [inline]
    [<00000000f4cb3815>] __x64_sys_connect+0x6e/0xb0 net/socket.c:1889
    [<00000000e7b1e839>] do_syscall_64+0x33/0x40 arch/x86/entry/common.c:46
    [<0000000055e91434>] entry_SYSCALL_64_after_hwframe+0x67/0xd1

Clean up the allocated memory in case of dccp_feat_push_confirm() failure
and bail out with an error reset code.

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes: e77b8363b2ea ("dccp: Process incoming Change feature-negotiation options")
Signed-off-by: Ivan Solodovnikov <solodovnikov.ia@phystech.edu>
Signed-off-by: NipaLocal <nipa@local>
---
 net/dccp/feat.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index 54086bb05c42c..f7554dcdaaba9 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -1166,8 +1166,12 @@ static u8 dccp_feat_change_recv(struct list_head *fn, u8 is_mandatory, u8 opt,
 			goto not_valid_or_not_known;
 		}
 
-		return dccp_feat_push_confirm(fn, feat, local, &fval);
+		if (dccp_feat_push_confirm(fn, feat, local, &fval)) {
+			kfree(fval.sp.vec);
+			return DCCP_RESET_CODE_TOO_BUSY;
+		}
 
+		return 0;
 	} else if (entry->state == FEAT_UNSTABLE) {	/* 6.6.2 */
 		return 0;
 	}

From b765d6f3545ba782398a24b316557459ea76517d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 26 Nov 2024 19:28:27 +0000
Subject: [PATCH 1501/1530] ipv6: avoid possible NULL deref in
 modify_prefix_route()

syzbot found a NULL deref [1] in modify_prefix_route(), caused by one
fib6_info without a fib6_table pointer set.

This can happen for net->ipv6.fib6_null_entry

[1]
Oops: general protection fault, probably for non-canonical address 0xdffffc0000000006: 0000 [#1] PREEMPT SMP KASAN NOPTI
KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037]
CPU: 1 UID: 0 PID: 5837 Comm: syz-executor888 Not tainted 6.12.0-syzkaller-09567-g7eef7e306d3c #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024
 RIP: 0010:__lock_acquire+0xe4/0x3c40 kernel/locking/lockdep.c:5089
Code: 08 84 d2 0f 85 15 14 00 00 44 8b 0d ca 98 f5 0e 45 85 c9 0f 84 b4 0e 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 e2 48 c1 ea 03 <80> 3c 02 00 0f 85 96 2c 00 00 49 8b 04 24 48 3d a0 07 7f 93 0f 84
RSP: 0018:ffffc900035d7268 EFLAGS: 00010006
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 0000000000000006 RSI: 1ffff920006bae5f RDI: 0000000000000030
RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000001
R10: ffffffff90608e17 R11: 0000000000000001 R12: 0000000000000030
R13: ffff888036334880 R14: 0000000000000000 R15: 0000000000000000
FS:  0000555579e90380(0000) GS:ffff8880b8700000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ffc59cc4278 CR3: 0000000072b54000 CR4: 00000000003526f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
  lock_acquire.part.0+0x11b/0x380 kernel/locking/lockdep.c:5849
  __raw_spin_lock_bh include/linux/spinlock_api_smp.h:126 [inline]
  _raw_spin_lock_bh+0x33/0x40 kernel/locking/spinlock.c:178
  spin_lock_bh include/linux/spinlock.h:356 [inline]
  modify_prefix_route+0x30b/0x8b0 net/ipv6/addrconf.c:4831
  inet6_addr_modify net/ipv6/addrconf.c:4923 [inline]
  inet6_rtm_newaddr+0x12c7/0x1ab0 net/ipv6/addrconf.c:5055
  rtnetlink_rcv_msg+0x3c7/0xea0 net/core/rtnetlink.c:6920
  netlink_rcv_skb+0x16b/0x440 net/netlink/af_netlink.c:2541
  netlink_unicast_kernel net/netlink/af_netlink.c:1321 [inline]
  netlink_unicast+0x53c/0x7f0 net/netlink/af_netlink.c:1347
  netlink_sendmsg+0x8b8/0xd70 net/netlink/af_netlink.c:1891
  sock_sendmsg_nosec net/socket.c:711 [inline]
  __sock_sendmsg net/socket.c:726 [inline]
  ____sys_sendmsg+0xaaf/0xc90 net/socket.c:2583
  ___sys_sendmsg+0x135/0x1e0 net/socket.c:2637
  __sys_sendmsg+0x16e/0x220 net/socket.c:2669
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7fd1dcef8b79
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 c1 17 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007ffc59cc4378 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fd1dcef8b79
RDX: 0000000000040040 RSI: 0000000020000140 RDI: 0000000000000004
RBP: 00000000000113fd R08: 0000000000000006 R09: 0000000000000006
R10: 0000000000000006 R11: 0000000000000246 R12: 00007ffc59cc438c
R13: 431bde82d7b634db R14: 0000000000000001 R15: 0000000000000001
 </TASK>

Fixes: 5eb902b8e719 ("net/ipv6: Remove expired routes with a separated list of routes.")
Reported-by: syzbot+1de74b0794c40c8eb300@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/67461f7f.050a0220.1286eb.0021.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
CC: Kui-Feng Lee <thinker.li@gmail.com>
Cc: David Ahern <dsahern@kernel.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv6/addrconf.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c489a1e6aec9a..0e765466d7f79 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4821,7 +4821,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 			      ifm->ifa_prefixlen, extack);
 }
 
-static int modify_prefix_route(struct inet6_ifaddr *ifp,
+static int modify_prefix_route(struct net *net, struct inet6_ifaddr *ifp,
 			       unsigned long expires, u32 flags,
 			       bool modify_peer)
 {
@@ -4845,7 +4845,9 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
 				      ifp->prefix_len,
 				      ifp->rt_priority, ifp->idev->dev,
 				      expires, flags, GFP_KERNEL);
-	} else {
+		return 0;
+	}
+	if (f6i != net->ipv6.fib6_null_entry) {
 		table = f6i->fib6_table;
 		spin_lock_bh(&table->tb6_lock);
 
@@ -4858,9 +4860,8 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
 		}
 
 		spin_unlock_bh(&table->tb6_lock);
-
-		fib6_info_release(f6i);
 	}
+	fib6_info_release(f6i);
 
 	return 0;
 }
@@ -4939,7 +4940,7 @@ static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp,
 		int rc = -ENOENT;
 
 		if (had_prefixroute)
-			rc = modify_prefix_route(ifp, expires, flags, false);
+			rc = modify_prefix_route(net, ifp, expires, flags, false);
 
 		/* prefix route could have been deleted; if so restore it */
 		if (rc == -ENOENT) {
@@ -4949,7 +4950,7 @@ static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp,
 		}
 
 		if (had_prefixroute && !ipv6_addr_any(&ifp->peer_addr))
-			rc = modify_prefix_route(ifp, expires, flags, true);
+			rc = modify_prefix_route(net, ifp, expires, flags, true);
 
 		if (rc == -ENOENT && !ipv6_addr_any(&ifp->peer_addr)) {
 			addrconf_prefix_route(&ifp->peer_addr, ifp->prefix_len,

From 769487db835fc6a0d1b4e9914b5e781ffdd08d9d Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 27 Nov 2024 14:05:12 +0900
Subject: [PATCH 1502/1530] tipc: Fix use-after-free of kernel socket in
 cleanup_bearer().

syzkaller reported a use-after-free of UDP kernel socket
in cleanup_bearer() without repro. [0][1]

When bearer_disable() calls tipc_udp_disable(), cleanup
of the UDP kernel socket is deferred by work calling
cleanup_bearer().

tipc_net_stop() waits for such works to finish by checking
tipc_net(net)->wq_count.  However, the work decrements the
count too early before releasing the kernel socket,
unblocking cleanup_net() and resulting in use-after-free.

Let's move the decrement after releasing the socket in
cleanup_bearer().

[0]:
ref_tracker: net notrefcnt@000000009b3d1faf has 1/1 users at
     sk_alloc+0x438/0x608
     inet_create+0x4c8/0xcb0
     __sock_create+0x350/0x6b8
     sock_create_kern+0x58/0x78
     udp_sock_create4+0x68/0x398
     udp_sock_create+0x88/0xc8
     tipc_udp_enable+0x5e8/0x848
     __tipc_nl_bearer_enable+0x84c/0xed8
     tipc_nl_bearer_enable+0x38/0x60
     genl_family_rcv_msg_doit+0x170/0x248
     genl_rcv_msg+0x400/0x5b0
     netlink_rcv_skb+0x1dc/0x398
     genl_rcv+0x44/0x68
     netlink_unicast+0x678/0x8b0
     netlink_sendmsg+0x5e4/0x898
     ____sys_sendmsg+0x500/0x830

[1]:
BUG: KMSAN: use-after-free in udp_hashslot include/net/udp.h:85 [inline]
BUG: KMSAN: use-after-free in udp_lib_unhash+0x3b8/0x930 net/ipv4/udp.c:1979
 udp_hashslot include/net/udp.h:85 [inline]
 udp_lib_unhash+0x3b8/0x930 net/ipv4/udp.c:1979
 sk_common_release+0xaf/0x3f0 net/core/sock.c:3820
 inet_release+0x1e0/0x260 net/ipv4/af_inet.c:437
 inet6_release+0x6f/0xd0 net/ipv6/af_inet6.c:489
 __sock_release net/socket.c:658 [inline]
 sock_release+0xa0/0x210 net/socket.c:686
 cleanup_bearer+0x42d/0x4c0 net/tipc/udp_media.c:819
 process_one_work kernel/workqueue.c:3229 [inline]
 process_scheduled_works+0xcaf/0x1c90 kernel/workqueue.c:3310
 worker_thread+0xf6c/0x1510 kernel/workqueue.c:3391
 kthread+0x531/0x6b0 kernel/kthread.c:389
 ret_from_fork+0x60/0x80 arch/x86/kernel/process.c:147
 ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:244

Uninit was created at:
 slab_free_hook mm/slub.c:2269 [inline]
 slab_free mm/slub.c:4580 [inline]
 kmem_cache_free+0x207/0xc40 mm/slub.c:4682
 net_free net/core/net_namespace.c:454 [inline]
 cleanup_net+0x16f2/0x19d0 net/core/net_namespace.c:647
 process_one_work kernel/workqueue.c:3229 [inline]
 process_scheduled_works+0xcaf/0x1c90 kernel/workqueue.c:3310
 worker_thread+0xf6c/0x1510 kernel/workqueue.c:3391
 kthread+0x531/0x6b0 kernel/kthread.c:389
 ret_from_fork+0x60/0x80 arch/x86/kernel/process.c:147
 ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:244

CPU: 0 UID: 0 PID: 54 Comm: kworker/0:2 Not tainted 6.12.0-rc1-00131-gf66ebf37d69c #7 91723d6f74857f70725e1583cba3cf4adc716cfa
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
Workqueue: events cleanup_bearer

Fixes: 26abe14379f8 ("net: Modify sk_alloc to not reference count the netns of kernel sockets.")
Reported-by: syzkaller <syzkaller@googlegroups.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/tipc/udp_media.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 439f755399772..b7e25e7e9933b 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -814,10 +814,10 @@ static void cleanup_bearer(struct work_struct *work)
 		kfree_rcu(rcast, rcu);
 	}
 
-	atomic_dec(&tipc_net(sock_net(ub->ubsock->sk))->wq_count);
 	dst_cache_destroy(&ub->rcast.dst_cache);
 	udp_tunnel_sock_release(ub->ubsock);
 	synchronize_net();
+	atomic_dec(&tipc_net(sock_net(ub->ubsock->sk))->wq_count);
 	kfree(ub);
 }
 

From c551056badba85108262f0089941f5fb0172eb8f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Wed, 27 Nov 2024 08:27:57 +0100
Subject: [PATCH 1503/1530] ptp: kvm: Return EOPNOTSUPP instead of ENODEV from
 kvm_arch_ptp_init()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The caller ptp_kvm_init() expects EOPNOTSUPP in case KVMCLOCK is not
available and not ENODEV.
Adapt the returned error code to avoid spurious errors in the kernel log:

"fail to initialize ptp_kvm"

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/ptp/ptp_kvm_x86.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/ptp/ptp_kvm_x86.c b/drivers/ptp/ptp_kvm_x86.c
index 617c8d6706d3d..6cea4fe39bcfe 100644
--- a/drivers/ptp/ptp_kvm_x86.c
+++ b/drivers/ptp/ptp_kvm_x86.c
@@ -26,7 +26,7 @@ int kvm_arch_ptp_init(void)
 	long ret;
 
 	if (!kvm_para_available())
-		return -ENODEV;
+		return -EOPNOTSUPP;
 
 	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) {
 		p = alloc_page(GFP_KERNEL | __GFP_ZERO);
@@ -46,14 +46,14 @@ int kvm_arch_ptp_init(void)
 
 	clock_pair_gpa = slow_virt_to_phys(clock_pair);
 	if (!pvclock_get_pvti_cpu0_va()) {
-		ret = -ENODEV;
+		ret = -EOPNOTSUPP;
 		goto err;
 	}
 
 	ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, clock_pair_gpa,
 			     KVM_CLOCK_PAIRING_WALLCLOCK);
 	if (ret == -KVM_ENOSYS) {
-		ret = -ENODEV;
+		ret = -EOPNOTSUPP;
 		goto err;
 	}
 

From 89a0c2f12d7f7916ca93acdd4d94413ad1d2b871 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Krzysztof=20Ha=C5=82asa?= <khalasa@piap.pl>
Date: Wed, 27 Nov 2024 09:45:30 +0100
Subject: [PATCH 1504/1530] USBNET: Fix ASIX USB Ethernet carrier problems.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Hi,

ASIX AX88772B based USB 10/100 Ethernet adapter doesn't come
up ("carrier off"), despite the built-in 100BASE-FX PHY positive link
indication. The internal PHY is configured (using EEPROM) in fixed
100 Mbps full duplex mode.

The primary problem appears to be using carrier_netif_{on,off}() while,
at the same time, delegating carrier management to phylink. Use only the
latter and remove "manual control" in the asix driver.

Signed-off-by: Krzysztof Hałasa <khalasa@piap.pl>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/usb/asix.h         |  1 -
 drivers/net/usb/asix_common.c  | 22 ---------------
 drivers/net/usb/asix_devices.c | 49 +++++++---------------------------
 3 files changed, 9 insertions(+), 63 deletions(-)

diff --git a/drivers/net/usb/asix.h b/drivers/net/usb/asix.h
index 74162190bccc1..8531b804021aa 100644
--- a/drivers/net/usb/asix.h
+++ b/drivers/net/usb/asix.h
@@ -224,7 +224,6 @@ int asix_write_rx_ctl(struct usbnet *dev, u16 mode, int in_pm);
 
 u16 asix_read_medium_status(struct usbnet *dev, int in_pm);
 int asix_write_medium_mode(struct usbnet *dev, u16 mode, int in_pm);
-void asix_adjust_link(struct net_device *netdev);
 
 int asix_write_gpio(struct usbnet *dev, u16 value, int sleep, int in_pm);
 
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index 72ffc89b477ad..7fd763917ae2c 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -414,28 +414,6 @@ int asix_write_medium_mode(struct usbnet *dev, u16 mode, int in_pm)
 	return ret;
 }
 
-/* set MAC link settings according to information from phylib */
-void asix_adjust_link(struct net_device *netdev)
-{
-	struct phy_device *phydev = netdev->phydev;
-	struct usbnet *dev = netdev_priv(netdev);
-	u16 mode = 0;
-
-	if (phydev->link) {
-		mode = AX88772_MEDIUM_DEFAULT;
-
-		if (phydev->duplex == DUPLEX_HALF)
-			mode &= ~AX_MEDIUM_FD;
-
-		if (phydev->speed != SPEED_100)
-			mode &= ~AX_MEDIUM_PS;
-	}
-
-	asix_write_medium_mode(dev, mode, 0);
-	phy_print_status(phydev);
-	usbnet_link_change(dev, phydev->link, 0);
-}
-
 int asix_write_gpio(struct usbnet *dev, u16 value, int sleep, int in_pm)
 {
 	int ret;
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 57d6e5abc30e8..af91fc947f40c 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -40,22 +40,6 @@ struct ax88172_int_data {
 	__le16 res3;
 } __packed;
 
-static void asix_status(struct usbnet *dev, struct urb *urb)
-{
-	struct ax88172_int_data *event;
-	int link;
-
-	if (urb->actual_length < 8)
-		return;
-
-	event = urb->transfer_buffer;
-	link = event->link & 0x01;
-	if (netif_carrier_ok(dev->net) != link) {
-		usbnet_link_change(dev, link, 1);
-		netdev_dbg(dev->net, "Link Status is: %d\n", link);
-	}
-}
-
 static void asix_set_netdev_dev_addr(struct usbnet *dev, u8 *addr)
 {
 	if (is_valid_ether_addr(addr)) {
@@ -752,7 +736,6 @@ static void ax88772_mac_link_down(struct phylink_config *config,
 	struct usbnet *dev = netdev_priv(to_net_dev(config->dev));
 
 	asix_write_medium_mode(dev, 0, 0);
-	usbnet_link_change(dev, false, false);
 }
 
 static void ax88772_mac_link_up(struct phylink_config *config,
@@ -783,7 +766,6 @@ static void ax88772_mac_link_up(struct phylink_config *config,
 		m |= AX_MEDIUM_RFC;
 
 	asix_write_medium_mode(dev, m, 0);
-	usbnet_link_change(dev, true, false);
 }
 
 static const struct phylink_mac_ops ax88772_phylink_mac_ops = {
@@ -1309,40 +1291,36 @@ static int ax88178_bind(struct usbnet *dev, struct usb_interface *intf)
 static const struct driver_info ax8817x_info = {
 	.description = "ASIX AX8817x USB 2.0 Ethernet",
 	.bind = ax88172_bind,
-	.status = asix_status,
 	.link_reset = ax88172_link_reset,
 	.reset = ax88172_link_reset,
-	.flags =  FLAG_ETHER | FLAG_LINK_INTR,
+	.flags =  FLAG_ETHER,
 	.data = 0x00130103,
 };
 
 static const struct driver_info dlink_dub_e100_info = {
 	.description = "DLink DUB-E100 USB Ethernet",
 	.bind = ax88172_bind,
-	.status = asix_status,
 	.link_reset = ax88172_link_reset,
 	.reset = ax88172_link_reset,
-	.flags =  FLAG_ETHER | FLAG_LINK_INTR,
+	.flags =  FLAG_ETHER,
 	.data = 0x009f9d9f,
 };
 
 static const struct driver_info netgear_fa120_info = {
 	.description = "Netgear FA-120 USB Ethernet",
 	.bind = ax88172_bind,
-	.status = asix_status,
 	.link_reset = ax88172_link_reset,
 	.reset = ax88172_link_reset,
-	.flags =  FLAG_ETHER | FLAG_LINK_INTR,
+	.flags =  FLAG_ETHER,
 	.data = 0x00130103,
 };
 
 static const struct driver_info hawking_uf200_info = {
 	.description = "Hawking UF200 USB Ethernet",
 	.bind = ax88172_bind,
-	.status = asix_status,
 	.link_reset = ax88172_link_reset,
 	.reset = ax88172_link_reset,
-	.flags =  FLAG_ETHER | FLAG_LINK_INTR,
+	.flags =  FLAG_ETHER,
 	.data = 0x001f1d1f,
 };
 
@@ -1350,10 +1328,9 @@ static const struct driver_info ax88772_info = {
 	.description = "ASIX AX88772 USB 2.0 Ethernet",
 	.bind = ax88772_bind,
 	.unbind = ax88772_unbind,
-	.status = asix_status,
 	.reset = ax88772_reset,
 	.stop = ax88772_stop,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_MULTI_PACKET,
 	.rx_fixup = asix_rx_fixup_common,
 	.tx_fixup = asix_tx_fixup,
 };
@@ -1362,11 +1339,9 @@ static const struct driver_info ax88772b_info = {
 	.description = "ASIX AX88772B USB 2.0 Ethernet",
 	.bind = ax88772_bind,
 	.unbind = ax88772_unbind,
-	.status = asix_status,
 	.reset = ax88772_reset,
 	.stop = ax88772_stop,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
-	         FLAG_MULTI_PACKET,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_MULTI_PACKET,
 	.rx_fixup = asix_rx_fixup_common,
 	.tx_fixup = asix_tx_fixup,
 	.data = FLAG_EEPROM_MAC,
@@ -1376,11 +1351,9 @@ static const struct driver_info lxausb_t1l_info = {
 	.description = "Linux Automation GmbH USB 10Base-T1L",
 	.bind = ax88772_bind,
 	.unbind = ax88772_unbind,
-	.status = asix_status,
 	.reset = ax88772_reset,
 	.stop = ax88772_stop,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
-		 FLAG_MULTI_PACKET,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_MULTI_PACKET,
 	.rx_fixup = asix_rx_fixup_common,
 	.tx_fixup = asix_tx_fixup,
 	.data = FLAG_EEPROM_MAC,
@@ -1390,11 +1363,9 @@ static const struct driver_info ax88178_info = {
 	.description = "ASIX AX88178 USB 2.0 Ethernet",
 	.bind = ax88178_bind,
 	.unbind = ax88178_unbind,
-	.status = asix_status,
 	.link_reset = ax88178_link_reset,
 	.reset = ax88178_reset,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
-		 FLAG_MULTI_PACKET,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_MULTI_PACKET,
 	.rx_fixup = asix_rx_fixup_common,
 	.tx_fixup = asix_tx_fixup,
 };
@@ -1412,10 +1383,8 @@ static const struct driver_info hg20f9_info = {
 	.description = "HG20F9 USB 2.0 Ethernet",
 	.bind = ax88772_bind,
 	.unbind = ax88772_unbind,
-	.status = asix_status,
 	.reset = ax88772_reset,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
-	         FLAG_MULTI_PACKET,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_MULTI_PACKET,
 	.rx_fixup = asix_rx_fixup_common,
 	.tx_fixup = asix_tx_fixup,
 	.data = FLAG_EEPROM_MAC,

From 5621eea7cde20eab78149bb13d6ff9c29da28448 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Krzysztof=20Ha=C5=82asa?= <khalasa@piap.pl>
Date: Wed, 27 Nov 2024 09:56:42 +0100
Subject: [PATCH 1505/1530] PHY: Fix no autoneg corner case
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

phydev->autoneg appears to indicate if autonegotiation is enabled or
not. Unfortunately it's initially set based on the supported capability
rather than the actual hw setting. While in most cases there is no
difference (i.e., autoneg is supported and on by default), certain
adapters (e.g. fiber optics) use fixed settings, configured in hardware.

Now autoneg flag is set only when it's supported and actually used.

Signed-off-by: Krzysztof Hałasa <khalasa@piap.pl>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/phy_device.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index b26bb33cd1d48..2b15569920fe2 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -3523,7 +3523,7 @@ static int phy_probe(struct device *dev)
 	struct phy_device *phydev = to_phy_device(dev);
 	struct device_driver *drv = phydev->mdio.dev.driver;
 	struct phy_driver *phydrv = to_phy_driver(drv);
-	int err = 0;
+	int err = 0, bmcr;
 
 	phydev->drv = phydrv;
 
@@ -3565,8 +3565,12 @@ static int phy_probe(struct device *dev)
 	if (err)
 		goto out;
 
+	err = bmcr = phy_read(phydev, MII_BMCR);
+	if (err < 0)
+		goto out;
+
 	if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
-			       phydev->supported))
+			       phydev->supported) || !(bmcr & BMCR_ANENABLE))
 		phydev->autoneg = 0;
 
 	if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,

From 43fa00e64bc5da2ffb0784238875815d4ea279ab Mon Sep 17 00:00:00 2001
From: Geetha sowjanya <gakula@marvell.com>
Date: Wed, 27 Nov 2024 17:18:57 +0530
Subject: [PATCH 1506/1530] octeontx2-af: Fix installation of PF multicast
 rules

Due to target variable is being reassigned in npc_install_flow()
function, PF multicast rules are not getting installed.
This patch addresses the issue by fixing the "IF" condition
checks when rules are installed by AF.

Fixes: 6c40ca957fe5 ("octeontx2-pf: Adds TC offload support").
Signed-off-by: Geetha sowjanya <gakula@marvell.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
index da69e454662a7..8a2444a8b7d33 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@@ -1457,14 +1457,14 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
 		target = req->vf;
 
 	/* PF installing for its VF */
-	if (!from_vf && req->vf && !from_rep_dev) {
+	else if (!from_vf && req->vf && !from_rep_dev) {
 		target = (req->hdr.pcifunc & ~RVU_PFVF_FUNC_MASK) | req->vf;
 		pf_set_vfs_mac = req->default_rule &&
 				(req->features & BIT_ULL(NPC_DMAC));
 	}
 
 	/* Representor device installing for a representee */
-	if (from_rep_dev && req->vf)
+	else if (from_rep_dev && req->vf)
 		target = req->vf;
 	else
 		/* msg received from PF/VF */

From 6b67ca26ca286252ca27dedebbb541dab5692c7e Mon Sep 17 00:00:00 2001
From: Wen Gu <guwen@linux.alibaba.com>
Date: Wed, 27 Nov 2024 21:30:13 +0800
Subject: [PATCH 1507/1530] net/smc: initialize close_work early to avoid
 warning

We encountered a warning that close_work was canceled before
initialization.

  WARNING: CPU: 7 PID: 111103 at kernel/workqueue.c:3047 __flush_work+0x19e/0x1b0
  Workqueue: events smc_lgr_terminate_work [smc]
  RIP: 0010:__flush_work+0x19e/0x1b0
  Call Trace:
   ? __wake_up_common+0x7a/0x190
   ? work_busy+0x80/0x80
   __cancel_work_timer+0xe3/0x160
   smc_close_cancel_work+0x1a/0x70 [smc]
   smc_close_active_abort+0x207/0x360 [smc]
   __smc_lgr_terminate.part.38+0xc8/0x180 [smc]
   process_one_work+0x19e/0x340
   worker_thread+0x30/0x370
   ? process_one_work+0x340/0x340
   kthread+0x117/0x130
   ? __kthread_cancel_work+0x50/0x50
   ret_from_fork+0x22/0x30

This is because when smc_close_cancel_work is triggered, e.g. the RDMA
driver is rmmod and the LGR is terminated, the conn->close_work is
flushed before initialization, resulting in WARN_ON(!work->func).

__smc_lgr_terminate             | smc_connect_{rdma|ism}
-------------------------------------------------------------
                                | smc_conn_create
				| \- smc_lgr_register_conn
for conn in lgr->conns_all      |
\- smc_conn_kill                |
   \- smc_close_active_abort    |
      \- smc_close_cancel_work  |
         \- cancel_work_sync    |
            \- __flush_work     |
	         (close_work)   |
	                        | smc_close_init
	                        | \- INIT_WORK(&close_work)

So fix this by initializing close_work before establishing the
connection.

Fixes: 46c28dbd4c23 ("net/smc: no socket state changes in tasklet context")
Fixes: 413498440e30 ("net/smc: add SMC-D support in af_smc")
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-by: Alexandra Winter <wintera@linux.ibm.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/smc/af_smc.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 9d76e902fd770..ed6d4d520bc7a 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -383,6 +383,7 @@ void smc_sk_init(struct net *net, struct sock *sk, int protocol)
 	smc->limit_smc_hs = net->smc.limit_smc_hs;
 	smc->use_fallback = false; /* assume rdma capability first */
 	smc->fallback_rsn = 0;
+	smc_close_init(smc);
 }
 
 static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
@@ -1299,7 +1300,6 @@ static int smc_connect_rdma(struct smc_sock *smc,
 		goto connect_abort;
 	}
 
-	smc_close_init(smc);
 	smc_rx_init(smc);
 
 	if (ini->first_contact_local) {
@@ -1435,7 +1435,6 @@ static int smc_connect_ism(struct smc_sock *smc,
 			goto connect_abort;
 		}
 	}
-	smc_close_init(smc);
 	smc_rx_init(smc);
 	smc_tx_init(smc);
 
@@ -2479,7 +2478,6 @@ static void smc_listen_work(struct work_struct *work)
 		goto out_decl;
 
 	mutex_lock(&smc_server_lgr_pending);
-	smc_close_init(new_smc);
 	smc_rx_init(new_smc);
 	smc_tx_init(new_smc);
 

From 6a919ea4815daa08e7bf40aa02189c1be47efc2f Mon Sep 17 00:00:00 2001
From: Wen Gu <guwen@linux.alibaba.com>
Date: Wed, 27 Nov 2024 21:30:14 +0800
Subject: [PATCH 1508/1530] net/smc: fix LGR and link use-after-free issue

We encountered a LGR/link use-after-free issue, which manifested as
the LGR/link refcnt reaching 0 early and entering the clear process,
making resource access unsafe.

 refcount_t: addition on 0; use-after-free.
 WARNING: CPU: 14 PID: 107447 at lib/refcount.c:25 refcount_warn_saturate+0x9c/0x140
 Workqueue: events smc_lgr_terminate_work [smc]
 Call trace:
  refcount_warn_saturate+0x9c/0x140
  __smc_lgr_terminate.part.45+0x2a8/0x370 [smc]
  smc_lgr_terminate_work+0x28/0x30 [smc]
  process_one_work+0x1b8/0x420
  worker_thread+0x158/0x510
  kthread+0x114/0x118

or

 refcount_t: underflow; use-after-free.
 WARNING: CPU: 6 PID: 93140 at lib/refcount.c:28 refcount_warn_saturate+0xf0/0x140
 Workqueue: smc_hs_wq smc_listen_work [smc]
 Call trace:
  refcount_warn_saturate+0xf0/0x140
  smcr_link_put+0x1cc/0x1d8 [smc]
  smc_conn_free+0x110/0x1b0 [smc]
  smc_conn_abort+0x50/0x60 [smc]
  smc_listen_find_device+0x75c/0x790 [smc]
  smc_listen_work+0x368/0x8a0 [smc]
  process_one_work+0x1b8/0x420
  worker_thread+0x158/0x510
  kthread+0x114/0x118

It is caused by repeated release of LGR/link refcnt. One suspect is that
smc_conn_free() is called repeatedly because some smc_conn_free() from
server listening path are not protected by sock lock.

e.g.

Calls under socklock        | smc_listen_work
-------------------------------------------------------
lock_sock(sk)               | smc_conn_abort
smc_conn_free               | \- smc_conn_free
\- smcr_link_put            |    \- smcr_link_put (duplicated)
release_sock(sk)

So here add sock lock protection in smc_listen_work() path, making it
exclusive with other connection operations.

Fixes: 3b2dec2603d5 ("net/smc: restructure client and server code in af_smc")
Co-developed-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Co-developed-by: Kai <KaiShen@linux.alibaba.com>
Signed-off-by: Kai <KaiShen@linux.alibaba.com>
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/smc/af_smc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index ed6d4d520bc7a..9e6c69d18581c 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1900,6 +1900,7 @@ static void smc_listen_out(struct smc_sock *new_smc)
 	if (tcp_sk(new_smc->clcsock->sk)->syn_smc)
 		atomic_dec(&lsmc->queued_smc_hs);
 
+	release_sock(newsmcsk); /* lock in smc_listen_work() */
 	if (lsmc->sk.sk_state == SMC_LISTEN) {
 		lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
 		smc_accept_enqueue(&lsmc->sk, newsmcsk);
@@ -2421,6 +2422,7 @@ static void smc_listen_work(struct work_struct *work)
 	u8 accept_version;
 	int rc = 0;
 
+	lock_sock(&new_smc->sk); /* release in smc_listen_out() */
 	if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN)
 		return smc_listen_out_err(new_smc);
 

From 481ddd40645ac38c72d185b891d542f97befddc4 Mon Sep 17 00:00:00 2001
From: Louis Leseur <louis.leseur@gmail.com>
Date: Thu, 28 Nov 2024 09:33:58 +0100
Subject: [PATCH 1509/1530] net/qed: allow old cards not supporting
 "num_images" to work

Commit 43645ce03e00 ("qed: Populate nvm image attribute shadow.")
added support for populating flash image attributes, notably
"num_images". However, some cards were not able to return this
information. In such cases, the driver would return EINVAL, causing the
driver to exit.

Add check to return EOPNOTSUPP instead of EINVAL when the card is not
able to return these information. The caller function already handles
EOPNOTSUPP without error.

Fixes: 43645ce03e00 ("qed: Populate nvm image attribute shadow.")
Co-developed-by: Florian Forestier <florian@forestier.re>
Signed-off-by: Florian Forestier <florian@forestier.re>
Signed-off-by: Louis Leseur <louis.leseur@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/qlogic/qed/qed_mcp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 26a714bfad4ec..b45efc272fdbb 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -3301,7 +3301,9 @@ int qed_mcp_bist_nvm_get_num_images(struct qed_hwfn *p_hwfn,
 	if (rc)
 		return rc;
 
-	if (((rsp & FW_MSG_CODE_MASK) != FW_MSG_CODE_OK))
+	if (((rsp & FW_MSG_CODE_MASK) == FW_MSG_CODE_UNSUPPORTED))
+		rc = -EOPNOTSUPP;
+	else if (((rsp & FW_MSG_CODE_MASK) != FW_MSG_CODE_OK))
 		rc = -EINVAL;
 
 	return rc;

From edddee1e17040c41e4782b8da8d5d36f40039efa Mon Sep 17 00:00:00 2001
From: Jiri Wiesner <jwiesner@suse.de>
Date: Thu, 28 Nov 2024 09:59:50 +0100
Subject: [PATCH 1510/1530] net/ipv6: release expired exception dst cached in
 socket

Dst objects get leaked in ip6_negative_advice() when this function is
executed for an expired IPv6 route located in the exception table. There
are several conditions that must be fulfilled for the leak to occur:
* an ICMPv6 packet indicating a change of the MTU for the path is received,
  resulting in an exception dst being created
* a TCP connection that uses the exception dst for routing packets must
  start timing out so that TCP begins retransmissions
* after the exception dst expires, the FIB6 garbage collector must not run
  before TCP executes ip6_negative_advice() for the expired exception dst

When TCP executes ip6_negative_advice() for an exception dst that has
expired and if no other socket holds a reference to the exception dst, the
refcount of the exception dst is 2, which corresponds to the increment
made by dst_init() and the increment made by the TCP socket for which the
connection is timing out. The refcount made by the socket is never
released. The refcount of the dst is decremented in sk_dst_reset() but
that decrement is counteracted by a dst_hold() intentionally placed just
before the sk_dst_reset() in ip6_negative_advice(). After
ip6_negative_advice() has finished, there is no other object tied to the
dst. The socket lost its reference stored in sk_dst_cache and the dst is
no longer in the exception table. The exception dst becomes a leaked
object.

As a result of this dst leak, an unbalanced refcount is reported for the
loopback device of a net namespace being destroyed under kernels that do
not contain e5f80fcf869a ("ipv6: give an IPv6 dev to blackhole_netdev"):
unregister_netdevice: waiting for lo to become free. Usage count = 2

Fix the dst leak by removing the dst_hold() in ip6_negative_advice(). The
patch that introduced the dst_hold() in ip6_negative_advice() was
92f1655aa2b22 ("net: fix __dst_negative_advice() race"). But 92f1655aa2b22
merely refactored the code with regards to the dst refcount so the issue
was present even before 92f1655aa2b22. The bug was introduced in
54c1a859efd9f ("ipv6: Don't drop cache route entry unless timer actually
expired.") where the expired cached route is deleted and the sk_dst_cache
member of the socket is set to NULL by calling dst_negative_advice() but
the refcount belonging to the socket is left unbalanced.

The IPv4 version - ipv4_negative_advice() - is not affected by this bug.
When the TCP connection times out ipv4_negative_advice() merely resets the
sk_dst_cache of the socket while decrementing the refcount of the
exception dst.

Fixes: 92f1655aa2b22 ("net: fix __dst_negative_advice() race")
Fixes: 54c1a859efd9f ("ipv6: Don't drop cache route entry unless timer actually expired.")
Link: https://lore.kernel.org/netdev/20241113105611.GA6723@incl/T/#u
Signed-off-by: Jiri Wiesner <jwiesner@suse.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv6/route.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 63d7681c929fc..67ff16c047180 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2780,10 +2780,10 @@ static void ip6_negative_advice(struct sock *sk,
 	if (rt->rt6i_flags & RTF_CACHE) {
 		rcu_read_lock();
 		if (rt6_check_expired(rt)) {
-			/* counteract the dst_release() in sk_dst_reset() */
-			dst_hold(dst);
+			/* rt/dst can not be destroyed yet,
+			 * because of rcu_read_lock()
+			 */
 			sk_dst_reset(sk);
-
 			rt6_remove_exception_rt(rt);
 		}
 		rcu_read_unlock();

From 7cc79dcc95dc9cbf2795d3224021f52c36463521 Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Thu, 28 Nov 2024 20:14:30 +0800
Subject: [PATCH 1511/1530] net/smc: protect link down work from execute after
 lgr freed

link down work may be scheduled before lgr freed but execute
after lgr freed, which may result in crash. So it is need to
hold a reference before shedule link down work, and put the
reference after work executed or canceled.

The relevant crash call stack as follows:
 list_del corruption. prev->next should be ffffb638c9c0fe20,
    but was 0000000000000000
 ------------[ cut here ]------------
 kernel BUG at lib/list_debug.c:51!
 invalid opcode: 0000 [#1] SMP NOPTI
 CPU: 6 PID: 978112 Comm: kworker/6:119 Kdump: loaded Tainted: G #1
 Hardware name: Alibaba Cloud Alibaba Cloud ECS, BIOS 2221b89 04/01/2014
 Workqueue: events smc_link_down_work [smc]
 RIP: 0010:__list_del_entry_valid.cold+0x31/0x47
 RSP: 0018:ffffb638c9c0fdd8 EFLAGS: 00010086
 RAX: 0000000000000054 RBX: ffff942fb75e5128 RCX: 0000000000000000
 RDX: ffff943520930aa0 RSI: ffff94352091fc80 RDI: ffff94352091fc80
 RBP: 0000000000000000 R08: 0000000000000000 R09: ffffb638c9c0fc38
 R10: ffffb638c9c0fc30 R11: ffffffffa015eb28 R12: 0000000000000002
 R13: ffffb638c9c0fe20 R14: 0000000000000001 R15: ffff942f9cd051c0
 FS:  0000000000000000(0000) GS:ffff943520900000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007f4f25214000 CR3: 000000025fbae004 CR4: 00000000007706e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 PKRU: 55555554
 Call Trace:
  rwsem_down_write_slowpath+0x17e/0x470
  smc_link_down_work+0x3c/0x60 [smc]
  process_one_work+0x1ac/0x350
  worker_thread+0x49/0x2f0
  ? rescuer_thread+0x360/0x360
  kthread+0x118/0x140
  ? __kthread_bind_mask+0x60/0x60
  ret_from_fork+0x1f/0x30

Fixes: 541afa10c126 ("net/smc: add smcr_port_err() and smcr_link_down() processing")
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/smc/smc_core.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 500952c2e67ba..3b125d348b4ae 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1818,7 +1818,9 @@ void smcr_link_down_cond_sched(struct smc_link *lnk)
 {
 	if (smc_link_downing(&lnk->state)) {
 		trace_smcr_link_down(lnk, __builtin_return_address(0));
-		schedule_work(&lnk->link_down_wrk);
+		smcr_link_hold(lnk); /* smcr_link_put in link_down_wrk */
+		if (!schedule_work(&lnk->link_down_wrk))
+			smcr_link_put(lnk);
 	}
 }
 
@@ -1850,11 +1852,14 @@ static void smc_link_down_work(struct work_struct *work)
 	struct smc_link_group *lgr = link->lgr;
 
 	if (list_empty(&lgr->list))
-		return;
+		goto out;
 	wake_up_all(&lgr->llc_msg_waiter);
 	down_write(&lgr->llc_conf_mutex);
 	smcr_link_down(link);
 	up_write(&lgr->llc_conf_mutex);
+
+out:
+	smcr_link_put(link); /* smcr_link_hold by schedulers of link_down_work */
 }
 
 static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev,

From 2dbefdb45cc4ce96cd359d74956c6f21371f653e Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Thu, 28 Nov 2024 20:14:31 +0800
Subject: [PATCH 1512/1530] net/smc: set SOCK_NOSPACE when send_remaining but
 no sndbuf_space left

When application sending data more than sndbuf_space, there have chances
application will sleep in epoll_wait, and will never be wakeup again. This
is caused by a race between smc_poll and smc_cdc_tx_handler.

application                                      tasklet
smc_tx_sendmsg(len > sndbuf_space)   |
epoll_wait for EPOLL_OUT,timeout=0   |
  smc_poll                           |
    if (!smc->conn.sndbuf_space)     |
                                     |  smc_cdc_tx_handler
                                     |    atomic_add sndbuf_space
                                     |    smc_tx_sndbuf_nonfull
                                     |      if (!test_bit SOCK_NOSPACE)
                                     |        do not sk_write_space;
      set_bit SOCK_NOSPACE;          |
    return mask=0;                   |

Application will sleep in epoll_wait as smc_poll returns 0. And
smc_cdc_tx_handler will not call sk_write_space because the SOCK_NOSPACE
has not be set. If there is no inflight cdc msg, sk_write_space will not be
called any more, and application will sleep in epoll_wait forever.
So set SOCK_NOSPACE when send_remaining but no sndbuf_space left in
smc_tx_sendmsg, to ensure call sk_write_space in smc_cdc_tx_handler
even when the above race happens.

Fixes: 6889b36da78a ("net/smc: don't wait for send buffer space when data was already sent")
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Wen Gu <guwen@linux.alibaba.com>
Reviewed-by: D. Wythe <alibuda@linux.alibaba.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/smc/smc_tx.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 214ac3cbcf9ad..60cfec8eb255f 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -222,8 +222,11 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
 			conn->local_tx_ctrl.prod_flags.urg_data_pending = 1;
 
 		if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) {
-			if (send_done)
+			if (send_done) {
+				sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 				return send_done;
+			}
 			rc = smc_tx_wait(smc, msg->msg_flags);
 			if (rc)
 				goto out_err;

From 2b4aaa35492739d8647ec30561f68ace0a648108 Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Thu, 28 Nov 2024 20:14:32 +0800
Subject: [PATCH 1513/1530] net/smc: check iparea_offset and ipv6_prefixes_cnt
 when receiving proposal msg

When receiving proposal msg in server, the field iparea_offset
and the field ipv6_prefixes_cnt in proposal msg are from the
remote client and can not be fully trusted. Especially the
field iparea_offset, once exceed the max value, there has the
chance to access wrong address, and crash may happen.

This patch checks iparea_offset and ipv6_prefixes_cnt before using them.

Fixes: e7b7a64a8493 ("smc: support variable CLC proposal messages")
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Wen Gu <guwen@linux.alibaba.com>
Reviewed-by: D. Wythe <alibuda@linux.alibaba.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/smc/af_smc.c  | 6 +++++-
 net/smc/smc_clc.c | 4 ++++
 net/smc/smc_clc.h | 6 +++++-
 3 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 9e6c69d18581c..e1ff1ceef074f 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -2032,6 +2032,8 @@ static int smc_listen_prfx_check(struct smc_sock *new_smc,
 	if (pclc->hdr.typev1 == SMC_TYPE_N)
 		return 0;
 	pclc_prfx = smc_clc_proposal_get_prefix(pclc);
+	if (!pclc_prfx)
+		return -EPROTO;
 	if (smc_clc_prfx_match(newclcsock, pclc_prfx))
 		return SMC_CLC_DECL_DIFFPREFIX;
 
@@ -2221,7 +2223,9 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc,
 	int rc = 0;
 
 	/* check if ISM V1 is available */
-	if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1))
+	if (!(ini->smcd_version & SMC_V1) ||
+	    !smcd_indicated(ini->smc_type_v1) ||
+	    !pclc_smcd)
 		goto not_found;
 	ini->is_smcd = true; /* prepare ISM check */
 	ini->ism_peer_gid[0].gid = ntohll(pclc_smcd->ism.gid);
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 33fa787c28ebb..66a43b97eede0 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -354,6 +354,10 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc)
 
 	v2_ext = smc_get_clc_v2_ext(pclc);
 	pclc_prfx = smc_clc_proposal_get_prefix(pclc);
+	if (!pclc_prfx ||
+	    pclc_prfx->ipv6_prefixes_cnt > SMC_CLC_MAX_V6_PREFIX)
+		return false;
+
 	if (hdr->version == SMC_V1) {
 		if (hdr->typev1 == SMC_TYPE_N)
 			return false;
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 5fd6f5b8ef034..ac8de6a177fac 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -336,8 +336,12 @@ struct smc_clc_msg_decline_v2 {	/* clc decline message */
 static inline struct smc_clc_msg_proposal_prefix *
 smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc)
 {
+	u16 offset = ntohs(pclc->iparea_offset);
+
+	if (offset > sizeof(struct smc_clc_msg_smcd))
+		return NULL;
 	return (struct smc_clc_msg_proposal_prefix *)
-	       ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset));
+	       ((u8 *)pclc + sizeof(*pclc) + offset);
 }
 
 static inline bool smcr_indicated(int smc_type)

From e17087202da270dccc36d96b7313fc124fbddd8e Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Thu, 28 Nov 2024 20:14:33 +0800
Subject: [PATCH 1514/1530] net/smc: check v2_ext_offset/eid_cnt/ism_gid_cnt
 when receiving proposal msg

When receiving proposal msg in server, the fields v2_ext_offset/
eid_cnt/ism_gid_cnt in proposal msg are from the remote client
and can not be fully trusted. Especially the field v2_ext_offset,
once exceed the max value, there has the chance to access wrong
address, and crash may happen.

This patch checks the fields v2_ext_offset/eid_cnt/ism_gid_cnt
before using them.

Fixes: 8c3dca341aea ("net/smc: build and send V2 CLC proposal")
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Wen Gu <guwen@linux.alibaba.com>
Reviewed-by: D. Wythe <alibuda@linux.alibaba.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/smc/af_smc.c  | 3 ++-
 net/smc/smc_clc.c | 8 +++++++-
 net/smc/smc_clc.h | 8 +++++++-
 3 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index e1ff1ceef074f..cd022b4143aa2 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -2276,7 +2276,8 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc,
 		goto not_found;
 
 	smc_v2_ext = smc_get_clc_v2_ext(pclc);
-	if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL))
+	if (!smc_v2_ext ||
+	    !smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL))
 		goto not_found;
 
 	/* prepare RDMA check */
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 66a43b97eede0..f721d03efcbd7 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -352,7 +352,6 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc)
 	struct smc_clc_msg_hdr *hdr = &pclc->hdr;
 	struct smc_clc_v2_extension *v2_ext;
 
-	v2_ext = smc_get_clc_v2_ext(pclc);
 	pclc_prfx = smc_clc_proposal_get_prefix(pclc);
 	if (!pclc_prfx ||
 	    pclc_prfx->ipv6_prefixes_cnt > SMC_CLC_MAX_V6_PREFIX)
@@ -369,6 +368,13 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc)
 			sizeof(struct smc_clc_msg_trail))
 			return false;
 	} else {
+		v2_ext = smc_get_clc_v2_ext(pclc);
+		if ((hdr->typev2 != SMC_TYPE_N &&
+		     (!v2_ext || v2_ext->hdr.eid_cnt > SMC_CLC_MAX_UEID)) ||
+		    (smcd_indicated(hdr->typev2) &&
+		     v2_ext->hdr.ism_gid_cnt > SMCD_CLC_MAX_V2_GID_ENTRIES))
+			return false;
+
 		if (ntohs(hdr->length) !=
 			sizeof(*pclc) +
 			sizeof(struct smc_clc_msg_smcd) +
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index ac8de6a177fac..23afa4df862ed 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -380,8 +380,14 @@ static inline struct smc_clc_v2_extension *
 smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop)
 {
 	struct smc_clc_msg_smcd *prop_smcd = smc_get_clc_msg_smcd(prop);
+	u16 max_offset;
 
-	if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset))
+	max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) -
+		     offsetof(struct smc_clc_msg_proposal_area, pclc_smcd) -
+		     offsetofend(struct smc_clc_msg_smcd, v2_ext_offset);
+
+	if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset) ||
+	    ntohs(prop_smcd->v2_ext_offset) > max_offset)
 		return NULL;
 
 	return (struct smc_clc_v2_extension *)

From bb89b0b708cda1c7cafb523b4653620f15810900 Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Thu, 28 Nov 2024 20:14:34 +0800
Subject: [PATCH 1515/1530] net/smc: check smcd_v2_ext_offset when receiving
 proposal msg

When receiving proposal msg in server, the field smcd_v2_ext_offset in
proposal msg is from the remote client and can not be fully trusted.
Once the value of smcd_v2_ext_offset exceed the max value, there has
the chance to access wrong address, and crash may happen.

This patch checks the value of smcd_v2_ext_offset before using it.

Fixes: 5c21c4ccafe8 ("net/smc: determine accepted ISM devices")
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Wen Gu <guwen@linux.alibaba.com>
Reviewed-by: D. Wythe <alibuda@linux.alibaba.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/smc/af_smc.c  | 2 ++
 net/smc/smc_clc.h | 8 +++++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index cd022b4143aa2..c08480ee33b0f 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -2147,6 +2147,8 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
 	pclc_smcd = smc_get_clc_msg_smcd(pclc);
 	smc_v2_ext = smc_get_clc_v2_ext(pclc);
 	smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext);
+	if (!pclc_smcd || !smc_v2_ext || !smcd_v2_ext)
+		goto not_found;
 
 	mutex_lock(&smcd_dev_list.mutex);
 	if (pclc_smcd->ism.chid) {
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 23afa4df862ed..7672899254108 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -400,9 +400,15 @@ smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop)
 static inline struct smc_clc_smcd_v2_extension *
 smc_get_clc_smcd_v2_ext(struct smc_clc_v2_extension *prop_v2ext)
 {
+	u16 max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_smcd_v2_ext) -
+		offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) -
+		offsetof(struct smc_clc_v2_extension, hdr) -
+		offsetofend(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset);
+
 	if (!prop_v2ext)
 		return NULL;
-	if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset))
+	if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset) ||
+	    ntohs(prop_v2ext->hdr.smcd_v2_ext_offset) > max_offset)
 		return NULL;
 
 	return (struct smc_clc_smcd_v2_extension *)

From 891bfa90120f082aac4a5e614504468793084fa9 Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Thu, 28 Nov 2024 20:14:35 +0800
Subject: [PATCH 1516/1530] net/smc: check return value of sock_recvmsg when
 draining clc data

When receiving clc msg, the field length in smc_clc_msg_hdr indicates the
length of msg should be received from network and the value should not be
fully trusted as it is from the network. Once the value of length exceeds
the value of buflen in function smc_clc_wait_msg it may run into deadloop
when trying to drain the remaining data exceeding buflen.

This patch checks the return value of sock_recvmsg when draining data in
case of deadloop in draining.

Fixes: fb4f79264c0f ("net/smc: tolerate future SMCD versions")
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Wen Gu <guwen@linux.alibaba.com>
Reviewed-by: D. Wythe <alibuda@linux.alibaba.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/smc/smc_clc.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index f721d03efcbd7..521f5df80e10c 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -774,6 +774,11 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 						SMC_CLC_RECV_BUF_LEN : datlen;
 		iov_iter_kvec(&msg.msg_iter, ITER_DEST, &vec, 1, recvlen);
 		len = sock_recvmsg(smc->clcsock, &msg, krflags);
+		if (len < recvlen) {
+			smc->sk.sk_err = EPROTO;
+			reason_code = -EPROTO;
+			goto out;
+		}
 		datlen -= len;
 	}
 	if (clcm->type == SMC_CLC_DECLINE) {

From 6b6889f8fbd04368badeaf1d554603330498c41e Mon Sep 17 00:00:00 2001
From: Cong Wang <cong.wang@bytedance.com>
Date: Thu, 28 Nov 2024 22:31:12 -0800
Subject: [PATCH 1517/1530] rtnetlink: catch error pointer for
 rtnl_link_get_net()

Currently all callers of rtnl_link_get_net() assume that it always
returns a valid netns pointer, when rtnl_link_get_net_ifla() fails,
it uses 'src_net' as a fallback.

This is not true, because rtnl_link_get_net_ifla() can return an
error pointer too, we need to handle this error case and propagate
the error code to its callers.

Add a comment to better document its return value.

Reported-by: syzbot+21ba4d5adff0b6a7cfc6@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=21ba4d5adff0b6a7cfc6
Fixes: 0eb87b02a705 ("veth: Set VETH_INFO_PEER to veth_link_ops.peer_type.")
Fixes: 6b84e558e95d ("vxcan: Set VXCAN_INFO_PEER to vxcan_link_ops.peer_type.")
Fixes: fefd5d082172 ("netkit: Set IFLA_NETKIT_PEER_INFO to netkit_link_ops.peer_type.")
Cc: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/can/vxcan.c |  3 +++
 drivers/net/netkit.c    |  3 +++
 drivers/net/veth.c      |  3 +++
 net/core/rtnetlink.c    | 12 ++++++++++++
 4 files changed, 21 insertions(+)

diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c
index da7c72105fb6e..6d03a5314034a 100644
--- a/drivers/net/can/vxcan.c
+++ b/drivers/net/can/vxcan.c
@@ -204,6 +204,9 @@ static int vxcan_newlink(struct net *net, struct net_device *dev,
 	}
 
 	peer_net = rtnl_link_get_net(net, tbp);
+	if (IS_ERR(peer_net))
+		return PTR_ERR(peer_net);
+
 	peer = rtnl_create_link(peer_net, ifname, name_assign_type,
 				&vxcan_link_ops, tbp, extack);
 	if (IS_ERR(peer)) {
diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index bb07725d1c72b..44fe99a82ac39 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -386,6 +386,9 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev,
 		return -EOPNOTSUPP;
 
 	net = rtnl_link_get_net(src_net, tbp);
+	if (IS_ERR(net))
+		return PTR_ERR(net);
+
 	peer = rtnl_create_link(net, ifname, ifname_assign_type,
 				&netkit_link_ops, tbp, extack);
 	if (IS_ERR(peer)) {
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 0d6d0d749d440..3a42a982c638a 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1801,6 +1801,9 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 	}
 
 	net = rtnl_link_get_net(src_net, tbp);
+	if (IS_ERR(net))
+		return PTR_ERR(net);
+
 	peer = rtnl_create_link(net, ifname, name_assign_type,
 				&veth_link_ops, tbp, extack);
 	if (IS_ERR(peer)) {
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 58df76fe408a4..08d3a045edf81 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2533,6 +2533,18 @@ static struct net *rtnl_link_get_net_ifla(struct nlattr *tb[])
 	return net;
 }
 
+/**
+ * rtnl_link_get_net - Get the network namespace from the netlink attributes
+ * or just @src_net.
+ *
+ * @src_net: the source network namespace
+ * @tb: the netlink attributes
+ *
+ * Returns:
+ *   The network namespace specified in the netlink attributes,
+ *   in case of error, an error pointer is returned.
+ *   Or, @src_net if no netns attributes were passed.
+ */
 struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[])
 {
 	struct net *net = rtnl_link_get_net_ifla(tb);

From d418512b3334a7dc5d383524165713d9688c4ceb Mon Sep 17 00:00:00 2001
From: Potin Lai <potin.lai@quantatw.com>
Date: Fri, 29 Nov 2024 17:12:56 +0800
Subject: [PATCH 1518/1530] Revert "net/ncsi: change from ndo_set_mac_address
 to dev_set_mac_address"

This reverts commit 790071347a0a1a89e618eedcd51c687ea783aeb3.

We are seeing kernel panic when enabling two NCSI interfaces at same
time. It looks like mutex lock is being used in softirq caused the
issue.

Kernel panic log:
```
[  224.323380] 8021q: adding VLAN 0 to HW filter on device eth0
[  224.337533] ftgmac100 1e670000.ethernet eth0: NCSI: Handler for packet type 0x82 returned -19
[  224.358372] BUG: scheduling while atomic: systemd-network/697/0x00000100
[  224.373274] Modules linked in:
[  224.373817] 8021q: adding VLAN 0 to HW filter on device eth1
[  224.380063] CPU: 0 PID: 697 Comm: systemd-network Tainted: G        W          6.6.62-8ea1fc6-dirty-cbd80d0-gcbd80d04d13c #1
[  224.380081] Hardware name: Generic DT based system
[  224.380096]  unwind_backtrace from show_stack+0x18/0x1c
[  224.439407]  show_stack from dump_stack_lvl+0x40/0x4c
[  224.450573]  dump_stack_lvl from __schedule_bug+0x5c/0x70
[  224.462492]  __schedule_bug from __schedule+0x884/0x968
[  224.474026]  __schedule from schedule+0x58/0xa8
[  224.484026]  schedule from schedule_preempt_disabled+0x14/0x18
[  224.496906]  schedule_preempt_disabled from __mutex_lock.constprop.0+0x350/0x76c
[  224.513235]  __mutex_lock.constprop.0 from ncsi_rsp_handler_oem_gma+0x104/0x1a0
[  224.529367]  ncsi_rsp_handler_oem_gma from ncsi_rcv_rsp+0x120/0x2cc
[  224.543195]  ncsi_rcv_rsp from __netif_receive_skb_one_core+0x60/0x84
[  224.557413]  __netif_receive_skb_one_core from netif_receive_skb+0x38/0x148
[  224.572779]  netif_receive_skb from ftgmac100_poll+0x358/0x444
[  224.585656]  ftgmac100_poll from __napi_poll.constprop.0+0x34/0x1d0
[  224.599490]  __napi_poll.constprop.0 from net_rx_action+0x350/0x43c
[  224.613325]  net_rx_action from handle_softirqs+0x114/0x32c
[  224.625624]  handle_softirqs from irq_exit+0x88/0xb8
[  224.636575]  irq_exit from call_with_stack+0x18/0x20
[  224.647530]  call_with_stack from __irq_usr+0x78/0xa0
[  224.658675] Exception stack(0xe075dfb0 to 0xe075dff8)
[  224.669799] dfa0:                                     00000000 00000000 00000000 00000020
[  224.687843] dfc0: 00000069 aefde3e0 00000000 00000000 00000000 00000000 00000000 aefde4e4
[  224.705887] dfe0: 01010101 aefddf20 a6b4331c a6b43618 600f0010 ffffffff
[  224.721100] ------------[ cut here ]------------
```

Signed-off-by: Potin Lai <potin.lai.pt@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ncsi/ncsi-rsp.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index e28be33bdf2c4..0cd7b916d3f83 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -629,6 +629,7 @@ static int ncsi_rsp_handler_oem_gma(struct ncsi_request *nr, int mfr_id)
 {
 	struct ncsi_dev_priv *ndp = nr->ndp;
 	struct net_device *ndev = ndp->ndev.dev;
+	const struct net_device_ops *ops = ndev->netdev_ops;
 	struct ncsi_rsp_oem_pkt *rsp;
 	struct sockaddr saddr;
 	u32 mac_addr_off = 0;
@@ -655,9 +656,7 @@ static int ncsi_rsp_handler_oem_gma(struct ncsi_request *nr, int mfr_id)
 	/* Set the flag for GMA command which should only be called once */
 	ndp->gma_flag = 1;
 
-	rtnl_lock();
-	ret = dev_set_mac_address(ndev, &saddr, NULL);
-	rtnl_unlock();
+	ret = ops->ndo_set_mac_address(ndev, &saddr);
 	if (ret < 0)
 		netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n");
 

From 38b0f42f5b40a69826f31491c8ed588af2d7e86c Mon Sep 17 00:00:00 2001
From: Frederik Deweerdt <deweerdt.lkml@gmail.com>
Date: Fri, 29 Nov 2024 15:20:14 -0800
Subject: [PATCH 1519/1530] splice: do not checksum AF_UNIX sockets

When `skb_splice_from_iter` was introduced, it inadvertently added
checksumming for AF_UNIX sockets. This resulted in significant
slowdowns, as when using sendfile over unix sockets.

Using the test code [1] in my test setup (2G, single core x86_64 qemu),
the client receives a 1000M file in:
- without the patch: 1577ms (+/- 36.1ms)
- with the patch: 725ms (+/- 28.3ms)

This commit skips addresses the issue by skipping checksumming when
splice occurs a AF_UNIX socket.

[1] https://gist.github.com/deweerdt/a3ee2477d1d87524cf08618d3c179f06

Signed-off-by: Frederik Deweerdt <deweerdt.lkml@gmail.com>
Fixes: 2e910b95329c ("net: Add a function to splice pages into an skbuff for MSG_SPLICE_PAGES")
Signed-off-by: NipaLocal <nipa@local>
---
 net/core/skbuff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6841e61a6bd0b..49e4f9ab625fa 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -7233,7 +7233,7 @@ ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter,
 				goto out;
 			}
 
-			if (skb->ip_summed == CHECKSUM_NONE)
+			if (skb->ip_summed == CHECKSUM_NONE && skb->sk->sk_family != AF_UNIX)
 				skb_splice_csum_page(skb, page, off, part);
 
 			off = 0;

From 42613d5c716685a9d3b37603c371bdabe44e8a50 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Sat, 30 Nov 2024 13:01:01 +0300
Subject: [PATCH 1520/1530] net/mlx5: DR, prevent potential error pointer
 dereference

The dr_domain_add_vport_cap() function genereally returns NULL on error
but sometimes we want it to return ERR_PTR(-EBUSY) so the caller can
retry.  The problem here is that "ret" can be either -EBUSY or -ENOMEM
and if it's and -ENOMEM then the error pointer is propogated back and
eventually dereferenced in dr_ste_v0_build_src_gvmi_qpn_tag().

Fixes: 11a45def2e19 ("net/mlx5: DR, Add support for SF vports")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c    | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
index 3d74109f82300..a379e8358f827 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
@@ -297,6 +297,8 @@ dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport)
 	if (ret) {
 		mlx5dr_dbg(dmn, "Couldn't insert new vport into xarray (%d)\n", ret);
 		kvfree(vport_caps);
+		if (ret != -EBUSY)
+			return NULL;
 		return ERR_PTR(ret);
 	}
 

From 528f86e23f11b40c39c2b6454fa166c9555472b3 Mon Sep 17 00:00:00 2001
From: Levi Zim <rsworktech@outlook.com>
Date: Sat, 30 Nov 2024 21:38:22 +0800
Subject: [PATCH 1521/1530] skmsg: return copied bytes in
 sk_msg_memcopy_from_iter

Previously sk_msg_memcopy_from_iter returns the copied bytes from the
last copy_from_iter{,_nocache} call upon success.

This commit changes it to return the total number of copied bytes on
success.

Signed-off-by: Levi Zim <rsworktech@outlook.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/core/skmsg.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index e90fbab703b2d..a65c2e6464586 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -369,8 +369,8 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 			     struct sk_msg *msg, u32 bytes)
 {
 	int ret = -ENOSPC, i = msg->sg.curr;
+	u32 copy, buf_size, copied = 0;
 	struct scatterlist *sge;
-	u32 copy, buf_size;
 	void *to;
 
 	do {
@@ -397,6 +397,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 			goto out;
 		}
 		bytes -= copy;
+		copied += copy;
 		if (!bytes)
 			break;
 		msg->sg.copybreak = 0;
@@ -404,7 +405,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 	} while (i != msg->sg.end);
 out:
 	msg->sg.curr = i;
-	return ret;
+	return (ret < 0) ? ret : copied;
 }
 EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
 

From 23d0b1cb2411d94c5e216c12449dd84769065f82 Mon Sep 17 00:00:00 2001
From: Levi Zim <rsworktech@outlook.com>
Date: Sat, 30 Nov 2024 21:38:23 +0800
Subject: [PATCH 1522/1530] tcp_bpf: fix copied value in tcp_bpf_sendmsg

bpf kselftest sockhash::test_txmsg_cork_hangs in test_sockmap.c triggers a
kernel NULL pointer dereference:

BUG: kernel NULL pointer dereference, address: 0000000000000008
 ? __die_body+0x6e/0xb0
 ? __die+0x8b/0xa0
 ? page_fault_oops+0x358/0x3c0
 ? local_clock+0x19/0x30
 ? lock_release+0x11b/0x440
 ? kernelmode_fixup_or_oops+0x54/0x60
 ? __bad_area_nosemaphore+0x4f/0x210
 ? mmap_read_unlock+0x13/0x30
 ? bad_area_nosemaphore+0x16/0x20
 ? do_user_addr_fault+0x6fd/0x740
 ? prb_read_valid+0x1d/0x30
 ? exc_page_fault+0x55/0xd0
 ? asm_exc_page_fault+0x2b/0x30
 ? splice_to_socket+0x52e/0x630
 ? shmem_file_splice_read+0x2b1/0x310
 direct_splice_actor+0x47/0x70
 splice_direct_to_actor+0x133/0x300
 ? do_splice_direct+0x90/0x90
 do_splice_direct+0x64/0x90
 ? __ia32_sys_tee+0x30/0x30
 do_sendfile+0x214/0x300
 __se_sys_sendfile64+0x8e/0xb0
 __x64_sys_sendfile64+0x25/0x30
 x64_sys_call+0xb82/0x2840
 do_syscall_64+0x75/0x110
 entry_SYSCALL_64_after_hwframe+0x4b/0x53

This is caused by tcp_bpf_sendmsg() returning a larger value(12289) than
size (8192), which causes the while loop in splice_to_socket() to release
an uninitialized pipe buf.

The underlying cause is that this code assumes sk_msg_memcopy_from_iter()
will copy all bytes upon success but it actually might only copy part of
it.

This commit changes it to use the real copied bytes.

Signed-off-by: Levi Zim <rsworktech@outlook.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv4/tcp_bpf.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 370993c03d313..8e46c4d618cbb 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -496,7 +496,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	struct sk_msg tmp, *msg_tx = NULL;
-	int copied = 0, err = 0;
+	int copied = 0, err = 0, ret = 0;
 	struct sk_psock *psock;
 	long timeo;
 	int flags;
@@ -539,14 +539,14 @@ static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 			copy = msg_tx->sg.size - osize;
 		}
 
-		err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx,
+		ret = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx,
 					       copy);
-		if (err < 0) {
+		if (ret < 0) {
 			sk_msg_trim(sk, msg_tx, osize);
 			goto out_err;
 		}
 
-		copied += copy;
+		copied += ret;
 		if (psock->cork_bytes) {
 			if (size > psock->cork_bytes)
 				psock->cork_bytes = 0;

From 3d0eb4c65af7188f9016f28ad0ed2769c4e1b375 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@baylibre.com>
Date: Sat, 30 Nov 2024 15:53:49 +0100
Subject: [PATCH 1523/1530] ptp: Switch back to struct
 platform_driver::remove()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 0edb555a65d1 ("platform: Make platform_driver::remove()
return void") .remove() is (again) the right callback to implement for
platform drivers.

Convert all platform drivers below drivers/ptp to use .remove(), with
the eventual goal to drop struct platform_driver::remove_new(). As
.remove() and .remove_new() have the same prototypes, conversion is done
by just changing the structure member name in the driver initializer.

While touching these drivers, make the alignment of the touched
initializers consistent.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/ptp/ptp_clockmatrix.c | 2 +-
 drivers/ptp/ptp_dte.c         | 4 ++--
 drivers/ptp/ptp_fc3.c         | 2 +-
 drivers/ptp/ptp_idt82p33.c    | 2 +-
 drivers/ptp/ptp_ines.c        | 4 ++--
 drivers/ptp/ptp_qoriq.c       | 2 +-
 drivers/ptp/ptp_vmclock.c     | 2 +-
 7 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c
index b6f1941308b17..fbb3fa8fc60b2 100644
--- a/drivers/ptp/ptp_clockmatrix.c
+++ b/drivers/ptp/ptp_clockmatrix.c
@@ -2471,7 +2471,7 @@ static struct platform_driver idtcm_driver = {
 		.name = "8a3400x-phc",
 	},
 	.probe = idtcm_probe,
-	.remove_new = idtcm_remove,
+	.remove = idtcm_remove,
 };
 
 module_platform_driver(idtcm_driver);
diff --git a/drivers/ptp/ptp_dte.c b/drivers/ptp/ptp_dte.c
index 449ff90927beb..372168578a30d 100644
--- a/drivers/ptp/ptp_dte.c
+++ b/drivers/ptp/ptp_dte.c
@@ -326,8 +326,8 @@ static struct platform_driver ptp_dte_driver = {
 		.pm = PTP_DTE_PM_OPS,
 		.of_match_table = ptp_dte_of_match,
 	},
-	.probe    = ptp_dte_probe,
-	.remove_new = ptp_dte_remove,
+	.probe = ptp_dte_probe,
+	.remove = ptp_dte_remove,
 };
 module_platform_driver(ptp_dte_driver);
 
diff --git a/drivers/ptp/ptp_fc3.c b/drivers/ptp/ptp_fc3.c
index 879b82f035352..cfced36c70bcb 100644
--- a/drivers/ptp/ptp_fc3.c
+++ b/drivers/ptp/ptp_fc3.c
@@ -1003,7 +1003,7 @@ static struct platform_driver idtfc3_driver = {
 		.name = "rc38xxx-phc",
 	},
 	.probe = idtfc3_probe,
-	.remove_new = idtfc3_remove,
+	.remove = idtfc3_remove,
 };
 
 module_platform_driver(idtfc3_driver);
diff --git a/drivers/ptp/ptp_idt82p33.c b/drivers/ptp/ptp_idt82p33.c
index d5732490ed9d1..b2fd94d4f8631 100644
--- a/drivers/ptp/ptp_idt82p33.c
+++ b/drivers/ptp/ptp_idt82p33.c
@@ -1461,7 +1461,7 @@ static struct platform_driver idt82p33_driver = {
 		.name = "82p33x1x-phc",
 	},
 	.probe = idt82p33_probe,
-	.remove_new = idt82p33_remove,
+	.remove = idt82p33_remove,
 };
 
 module_platform_driver(idt82p33_driver);
diff --git a/drivers/ptp/ptp_ines.c b/drivers/ptp/ptp_ines.c
index 14a23d3a27f2c..3d723a2aa6bb0 100644
--- a/drivers/ptp/ptp_ines.c
+++ b/drivers/ptp/ptp_ines.c
@@ -781,8 +781,8 @@ static const struct of_device_id ines_ptp_ctrl_of_match[] = {
 MODULE_DEVICE_TABLE(of, ines_ptp_ctrl_of_match);
 
 static struct platform_driver ines_ptp_ctrl_driver = {
-	.probe  = ines_ptp_ctrl_probe,
-	.remove_new = ines_ptp_ctrl_remove,
+	.probe = ines_ptp_ctrl_probe,
+	.remove = ines_ptp_ctrl_remove,
 	.driver = {
 		.name = "ines_ptp_ctrl",
 		.of_match_table = ines_ptp_ctrl_of_match,
diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c
index 879cfc1537ac8..4d488c1f1941b 100644
--- a/drivers/ptp/ptp_qoriq.c
+++ b/drivers/ptp/ptp_qoriq.c
@@ -670,7 +670,7 @@ static struct platform_driver ptp_qoriq_driver = {
 		.of_match_table	= match_table,
 	},
 	.probe       = ptp_qoriq_probe,
-	.remove_new  = ptp_qoriq_remove,
+	.remove      = ptp_qoriq_remove,
 };
 
 module_platform_driver(ptp_qoriq_driver);
diff --git a/drivers/ptp/ptp_vmclock.c b/drivers/ptp/ptp_vmclock.c
index cdca8a3ad1aa1..0a2cfc8ad3c54 100644
--- a/drivers/ptp/ptp_vmclock.c
+++ b/drivers/ptp/ptp_vmclock.c
@@ -601,7 +601,7 @@ MODULE_DEVICE_TABLE(acpi, vmclock_acpi_ids);
 
 static struct platform_driver vmclock_platform_driver = {
 	.probe		= vmclock_probe,
-	.remove_new	= vmclock_remove,
+	.remove		= vmclock_remove,
 	.driver	= {
 		.name	= "vmclock",
 		.acpi_match_table = vmclock_acpi_ids,

From 23b551f3e727f9eb9a23c4d18cf61400605ea4f8 Mon Sep 17 00:00:00 2001
From: Koichiro Den <koichiro.den@canonical.com>
Date: Sun, 1 Dec 2024 03:17:44 +0900
Subject: [PATCH 1524/1530] virtio_net: drop netdev_tx_reset_queue() from
 virtnet_enable_queue_pair()

When virtnet_close is followed by virtnet_open, some TX completions can
possibly remain unconsumed, until they are finally processed during the
first NAPI poll after the netdev_tx_reset_queue(), resulting in a crash
[1]. Commit b96ed2c97c79 ("virtio_net: move netdev_tx_reset_queue() call
before RX napi enable") seems not sufficient to eliminate all BQL crash
scenarios for virtio-net.

This issue can be reproduced with the latest net-next master by running:
`while :; do ip l set DEV down; ip l set DEV up; done` under heavy network
TX load from inside the machine.

netdev_tx_reset_queue() can actually be dropped from virtnet_open path;
the device is not stopped in any case. For BQL core part, it's just like
traffic nearly ceases to exist for some period. For stall detector added
to BQL, even if virtnet_close could somehow lead to some TX completions
delayed for long, followed by virtnet_open, we can just take it as stall
as mentioned in commit 6025b9135f7a ("net: dqs: add NIC stall detector
based on BQL"). Note also that users can still reset stall_max via sysfs.

So, drop netdev_tx_reset_queue() from virtnet_enable_queue_pair(). This
eliminates the BQL crashes. With this patch, virtio-net performs only
one dql_reset() per probe.

[1]:
------------[ cut here ]------------
kernel BUG at lib/dynamic_queue_limits.c:99!
Oops: invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
CPU: 7 UID: 0 PID: 1598 Comm: ip Tainted: G    N 6.12.0net-next_main+ #2
Tainted: [N]=TEST
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), \
BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
RIP: 0010:dql_completed+0x26b/0x290
Code: b7 c2 49 89 e9 44 89 da 89 c6 4c 89 d7 e8 ed 17 47 00 58 65 ff 0d
4d 27 90 7e 0f 85 fd fe ff ff e8 ea 53 8d ff e9 f3 fe ff ff <0f> 0b 01
d2 44 89 d1 29 d1 ba 00 00 00 00 0f 48 ca e9 28 ff ff ff
RSP: 0018:ffffc900002b0d08 EFLAGS: 00010297
RAX: 0000000000000000 RBX: ffff888102398c80 RCX: 0000000080190009
RDX: 0000000000000000 RSI: 000000000000006a RDI: 0000000000000000
RBP: ffff888102398c00 R08: 0000000000000000 R09: 0000000000000000
R10: 00000000000000ca R11: 0000000000015681 R12: 0000000000000001
R13: ffffc900002b0d68 R14: ffff88811115e000 R15: ffff8881107aca40
FS:  00007f41ded69500(0000) GS:ffff888667dc0000(0000)
knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000556ccc2dc1a0 CR3: 0000000104fd8003 CR4: 0000000000772ef0
PKRU: 55555554
Call Trace:
 <IRQ>
 ? die+0x32/0x80
 ? do_trap+0xd9/0x100
 ? dql_completed+0x26b/0x290
 ? dql_completed+0x26b/0x290
 ? do_error_trap+0x6d/0xb0
 ? dql_completed+0x26b/0x290
 ? exc_invalid_op+0x4c/0x60
 ? dql_completed+0x26b/0x290
 ? asm_exc_invalid_op+0x16/0x20
 ? dql_completed+0x26b/0x290
 __free_old_xmit+0xff/0x170 [virtio_net]
 free_old_xmit+0x54/0xc0 [virtio_net]
 virtnet_poll+0xf4/0xe30 [virtio_net]
 ? __update_load_avg_cfs_rq+0x264/0x2d0
 ? update_curr+0x35/0x260
 ? reweight_entity+0x1be/0x260
 __napi_poll.constprop.0+0x28/0x1c0
 net_rx_action+0x329/0x420
 ? enqueue_hrtimer+0x35/0x90
 ? trace_hardirqs_on+0x1d/0x80
 ? kvm_sched_clock_read+0xd/0x20
 ? sched_clock+0xc/0x30
 ? kvm_sched_clock_read+0xd/0x20
 ? sched_clock+0xc/0x30
 ? sched_clock_cpu+0xd/0x1a0
 handle_softirqs+0x138/0x3e0
 do_softirq.part.0+0x89/0xc0
 </IRQ>
 <TASK>
 __local_bh_enable_ip+0xa7/0xb0
 virtnet_open+0xc8/0x310 [virtio_net]
 __dev_open+0xfa/0x1b0
 __dev_change_flags+0x1de/0x250
 dev_change_flags+0x22/0x60
 do_setlink.isra.0+0x2df/0x10b0
 ? rtnetlink_rcv_msg+0x34f/0x3f0
 ? netlink_rcv_skb+0x54/0x100
 ? netlink_unicast+0x23e/0x390
 ? netlink_sendmsg+0x21e/0x490
 ? ____sys_sendmsg+0x31b/0x350
 ? avc_has_perm_noaudit+0x67/0xf0
 ? cred_has_capability.isra.0+0x75/0x110
 ? __nla_validate_parse+0x5f/0xee0
 ? __pfx___probestub_irq_enable+0x3/0x10
 ? __create_object+0x5e/0x90
 ? security_capable+0x3b/0x70
 rtnl_newlink+0x784/0xaf0
 ? avc_has_perm_noaudit+0x67/0xf0
 ? cred_has_capability.isra.0+0x75/0x110
 ? stack_depot_save_flags+0x24/0x6d0
 ? __pfx_rtnl_newlink+0x10/0x10
 rtnetlink_rcv_msg+0x34f/0x3f0
 ? do_syscall_64+0x6c/0x180
 ? entry_SYSCALL_64_after_hwframe+0x76/0x7e
 ? __pfx_rtnetlink_rcv_msg+0x10/0x10
 netlink_rcv_skb+0x54/0x100
 netlink_unicast+0x23e/0x390
 netlink_sendmsg+0x21e/0x490
 ____sys_sendmsg+0x31b/0x350
 ? copy_msghdr_from_user+0x6d/0xa0
 ___sys_sendmsg+0x86/0xd0
 ? __pte_offset_map+0x17/0x160
 ? preempt_count_add+0x69/0xa0
 ? __call_rcu_common.constprop.0+0x147/0x610
 ? preempt_count_add+0x69/0xa0
 ? preempt_count_add+0x69/0xa0
 ? _raw_spin_trylock+0x13/0x60
 ? trace_hardirqs_on+0x1d/0x80
 __sys_sendmsg+0x66/0xc0
 do_syscall_64+0x6c/0x180
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7f41defe5b34
Code: 15 e1 12 0f 00 f7 d8 64 89 02 b8 ff ff ff ff eb bf 0f 1f 44 00 00
f3 0f 1e fa 80 3d 35 95 0f 00 00 74 13 b8 2e 00 00 00 0f 05 <48> 3d 00
f0 ff ff 77 4c c3 0f 1f 00 55 48 89 e5 48 83 ec 20 89 55
RSP: 002b:00007ffe5336ecc8 EFLAGS: 00000202 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f41defe5b34
RDX: 0000000000000000 RSI: 00007ffe5336ed30 RDI: 0000000000000003
RBP: 00007ffe5336eda0 R08: 0000000000000010 R09: 0000000000000001
R10: 00007ffe5336f6f9 R11: 0000000000000202 R12: 0000000000000003
R13: 0000000067452259 R14: 0000556ccc28b040 R15: 0000000000000000
 </TASK>
[...]
---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

Fixes: c8bd1f7f3e61 ("virtio_net: add support for Byte Queue Limits")
Cc: <stable@vger.kernel.org> # v6.11+
Signed-off-by: Koichiro Den <koichiro.den@canonical.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/virtio_net.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 64c87bb48a41c..35a36d1289db5 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3054,7 +3054,6 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
 	if (err < 0)
 		goto err_xdp_reg_mem_model;
 
-	netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, qp_index));
 	virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
 	virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);
 

From 639a7b8549e2287cc4536be25ad6c4cb26bbbf4f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sat, 30 Nov 2024 13:41:00 -0800
Subject: [PATCH 1525/1530] MAINTAINERS: list PTP drivers under networking

PTP patches go via the netdev trees, add drivers/ptp/ to the networking
entry so that get_maintainer.pl --scm lists those trees above Linus's
tree.

Thanks to the real entry using drivers/ptp/* the original entry will
still be considered more specific / higher prio.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 0456a33ef6579..f9f2f009aecfc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16194,6 +16194,7 @@ F:	Documentation/devicetree/bindings/net/
 F:	Documentation/networking/net_cachelines/net_device.rst
 F:	drivers/connector/
 F:	drivers/net/
+F:	drivers/ptp/
 F:	include/dt-bindings/net/
 F:	include/linux/cn_proc.h
 F:	include/linux/etherdevice.h

From caef96c97f29242de3a98adf3e0ee6f4625549a8 Mon Sep 17 00:00:00 2001
From: fedora Cloud User <fedora@ip-172-31-39-240.us-east-2.compute.internal>
Date: Thu, 1 Feb 2024 06:34:18 -0800
Subject: [PATCH 1526/1530] forwarding: set timeout to 3 hours

tc_actions.sh keeps hanging the forwarding tests.

sdf@: tdc & tdc-dbg started intermittenly failing around Sep 25th

Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/net/forwarding/settings | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/settings b/tools/testing/selftests/net/forwarding/settings
index e7b9417537fbc..ff3de4936a009 100644
--- a/tools/testing/selftests/net/forwarding/settings
+++ b/tools/testing/selftests/net/forwarding/settings
@@ -1 +1,2 @@
-timeout=0
+timeout=10800
+profile=1

From c2e43792f56607691fdcb22ce52eaa91e4062d8d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sat, 17 Aug 2024 10:53:12 -0700
Subject: [PATCH 1527/1530] profile patch

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/kselftest/prefix.pl | 8 ++++++++
 tools/testing/selftests/kselftest/runner.sh | 2 +-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kselftest/prefix.pl b/tools/testing/selftests/kselftest/prefix.pl
index 12a7f4ca2684d..b8e4d697e3b3a 100755
--- a/tools/testing/selftests/kselftest/prefix.pl
+++ b/tools/testing/selftests/kselftest/prefix.pl
@@ -4,12 +4,15 @@
 # to have unbuffering forced with "stdbuf -i0 -o0 -e0 $cmd".
 use strict;
 use IO::Handle;
+use Time::HiRes qw( time );
 
 binmode STDIN;
 binmode STDOUT;
 
 STDOUT->autoflush(1);
 
+my $start_time = time();
+my $prev_time = $start_time;
 my $needed = 1;
 while (1) {
 	my $char;
@@ -17,6 +20,11 @@
 	exit 0 if ($bytes == 0);
 	if ($needed) {
 		print "# ";
+		if ($ENV{kselftest_profile}) {
+			my $now = time();
+			printf("%.2f [+%.2f] ", $now - $start_time, $now - $prev_time);
+			$prev_time = $now;
+		}
 		$needed = 0;
 	}
 	print $char;
diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh
index 2c3c58e65a419..e65bffb9981f8 100644
--- a/tools/testing/selftests/kselftest/runner.sh
+++ b/tools/testing/selftests/kselftest/runner.sh
@@ -89,7 +89,7 @@ run_one()
 			fi
 			field=$(echo "$line" | cut -d= -f1)
 			value=$(echo "$line" | cut -d= -f2-)
-			eval "kselftest_$field"="$value"
+			eval "export kselftest_$field"="$value"
 		done < "$settings"
 	fi
 

From 56d3a412729d4c32b70d65650e89e7b7fb9e36f2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 29 Aug 2024 19:57:39 -0700
Subject: [PATCH 1528/1530] tc_action dbg

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 .../selftests/net/forwarding/tc_actions.sh    | 26 ++++++++++++++-----
 1 file changed, 20 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index ea89e558672db..5823d94b19e9b 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -223,19 +223,32 @@ mirred_egress_to_ingress_tcp_test()
 		ip_proto icmp \
 			action drop
 
-	ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 &
-	local rpid=$!
-	ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1
-	wait -n $rpid
-	cmp -s $mirred_e2i_tf1 $mirred_e2i_tf2
-	check_err $? "server output check failed"
+	echo P2
 
 	$MZ $h1 -c 10 -p 64 -a $h1mac -b $h1mac -A 192.0.2.1 -B 192.0.2.1 \
 		-t icmp "ping,id=42,seq=5" -q
+	echo P2.1
 	tc_check_packets "dev $h1 egress" 101 10
 	check_err $? "didn't mirred redirect ICMP"
+	echo P2.2
 	tc_check_packets "dev $h1 ingress" 102 10
 	check_err $? "didn't drop mirred ICMP"
+	echo P2.3
+
+	echo P1
+
+	ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 &
+	local rpid=$!
+	sleep 0.2
+	echo P1.1
+	ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1
+	echo P1.2
+	sleep 0.2
+	wait -n $rpid
+	cmp -s $mirred_e2i_tf1 $mirred_e2i_tf2
+	check_err $? "server output check failed"
+
+	echo P3
 
 	tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower
 	tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower
@@ -359,4 +372,5 @@ else
 	tests_run
 fi
 
+dmesg
 exit $EXIT_STATUS

From fdf18717f237a2f4fed4ea204a52e49e5c518cc6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 10 Oct 2024 06:49:21 -0700
Subject: [PATCH 1529/1530] fs/9p: use kvzalloc/kvfree to allocate struct
 p9_rdir and its buffer

The buffers can easily get large and fail allocations. One of the
networking tests running in a VM tries to run perf which occasionally
ends with:

  perf: page allocation failure: order:6, mode:0x40dc0(GFP_KERNEL|__GFP_COMP|__GFP_ZERO), nodemask=(null),cpuset=/,mems_allowed=0

Even tho free memory is available:

  free:97464 free_pcp:321 free_cma:0

Switch to kvzalloc() to make large allocations less likely to fail.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 fs/9p/vfs_dir.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index e0d34e4e9076e..0967147e03c65 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -74,6 +74,14 @@ static struct p9_rdir *v9fs_alloc_rdir_buf(struct file *filp, int buflen)
 	return fid->rdir;
 }
 
+static void v9fs_free_rdir_buf(struct file *filp)
+{
+	struct p9_fid *fid = filp->private_data;
+
+	kfree(fid->rdir);
+	fid->rdir = NULL;
+}
+
 /**
  * v9fs_dir_readdir - iterate through a directory
  * @file: opened file structure
@@ -129,8 +137,10 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx)
 			over = !dir_emit(ctx, st.name, strlen(st.name),
 					QID2INO(&st.qid), dt_type(&st));
 			p9stat_free(&st);
-			if (over)
+			if (over) {
+				v9fs_free_rdir_buf(file);
 				return 0;
+			}
 
 			rdir->head += err;
 			ctx->pos += err;
@@ -185,8 +195,10 @@ static int v9fs_dir_readdir_dotl(struct file *file, struct dir_context *ctx)
 			if (!dir_emit(ctx, curdirent.d_name,
 				      strlen(curdirent.d_name),
 				      QID2INO(&curdirent.qid),
-				      curdirent.d_type))
+				      curdirent.d_type)) {
+				v9fs_free_rdir_buf(file);
 				return 0;
+			}
 
 			ctx->pos = curdirent.d_off;
 			rdir->head += err;

From b6917721705135d4ba22479e7e14485dbb402521 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 3 Nov 2024 16:10:42 -0800
Subject: [PATCH 1530/1530] selftests: net: enable profiling

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/net/settings | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/settings b/tools/testing/selftests/net/settings
index ed8418e8217a0..a38764182822e 100644
--- a/tools/testing/selftests/net/settings
+++ b/tools/testing/selftests/net/settings
@@ -1 +1,2 @@
 timeout=3600
+profile=1