Merge branch 'linux-6.6.y' into linux-stable-update-6.6.63-nouveau

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 6
-SUBLEVEL = 62
+SUBLEVEL = 63
 EXTRAVERSION =
 NAME = Pinguïn Aangedreven
 

arch/arm/kernel/head.S

@@ -252,27 +252,31 @@ __create_page_tables:
 	 */
 	add	r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ENTRY_ORDER)
 	ldr	r6, =(_end - 1)
+
+	/* For XIP, kernel_sec_start/kernel_sec_end are currently in RO memory */
+#ifndef CONFIG_XIP_KERNEL
 	adr_l	r5, kernel_sec_start		@ _pa(kernel_sec_start)
 #if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32
 	str	r8, [r5, #4]			@ Save physical start of kernel (BE)
 #else
 	str	r8, [r5]			@ Save physical start of kernel (LE)
+#endif
 #endif
 	orr	r3, r8, r7			@ Add the MMU flags
 	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ENTRY_ORDER)
 1:	str	r3, [r0], #1 << PMD_ENTRY_ORDER
 	add	r3, r3, #1 << SECTION_SHIFT
 	cmp	r0, r6
 	bls	1b
+#ifndef CONFIG_XIP_KERNEL
 	eor	r3, r3, r7			@ Remove the MMU flags
 	adr_l	r5, kernel_sec_end		@ _pa(kernel_sec_end)
 #if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32
 	str	r3, [r5, #4]			@ Save physical end of kernel (BE)
 #else
 	str	r3, [r5]			@ Save physical end of kernel (LE)
 #endif
-
-#ifdef CONFIG_XIP_KERNEL
+#else
 	/*
 	 * Map the kernel image separately as it is not located in RAM.
 	 */

arch/arm/mm/mmu.c

@@ -1402,18 +1402,6 @@ static void __init devicemaps_init(const struct machine_desc *mdesc)
 		create_mapping(&map);
 	}
 
-	/*
-	 * Map the kernel if it is XIP.
-	 * It is always first in the modulearea.
-	 */
-#ifdef CONFIG_XIP_KERNEL
-	map.pfn = __phys_to_pfn(CONFIG_XIP_PHYS_ADDR & SECTION_MASK);
-	map.virtual = MODULES_VADDR;
-	map.length = ((unsigned long)_exiprom - map.virtual + ~SECTION_MASK) & SECTION_MASK;
-	map.type = MT_ROM;
-	create_mapping(&map);
-#endif
-
 	/*
 	 * Map the cache flushing regions.
 	 */
@@ -1603,12 +1591,27 @@ static void __init map_kernel(void)
 	 * This will only persist until we turn on proper memory management later on
 	 * and we remap the whole kernel with page granularity.
 	 */
+#ifdef CONFIG_XIP_KERNEL
+	phys_addr_t kernel_nx_start = kernel_sec_start;
+#else
 	phys_addr_t kernel_x_start = kernel_sec_start;
 	phys_addr_t kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
 	phys_addr_t kernel_nx_start = kernel_x_end;
+#endif
 	phys_addr_t kernel_nx_end = kernel_sec_end;
 	struct map_desc map;
 
+	/*
+	 * Map the kernel if it is XIP.
+	 * It is always first in the modulearea.
+	 */
+#ifdef CONFIG_XIP_KERNEL
+	map.pfn = __phys_to_pfn(CONFIG_XIP_PHYS_ADDR & SECTION_MASK);
+	map.virtual = MODULES_VADDR;
+	map.length = ((unsigned long)_exiprom - map.virtual + ~SECTION_MASK) & SECTION_MASK;
+	map.type = MT_ROM;
+	create_mapping(&map);
+#else
 	map.pfn = __phys_to_pfn(kernel_x_start);
 	map.virtual = __phys_to_virt(kernel_x_start);
 	map.length = kernel_x_end - kernel_x_start;
@@ -1618,7 +1621,7 @@ static void __init map_kernel(void)
 	/* If the nx part is small it may end up covered by the tail of the RWX section */
 	if (kernel_x_end == kernel_nx_end)
 		return;
-
+#endif
 	map.pfn = __phys_to_pfn(kernel_nx_start);
 	map.virtual = __phys_to_virt(kernel_nx_start);
 	map.length = kernel_nx_end - kernel_nx_start;
@@ -1763,6 +1766,11 @@ void __init paging_init(const struct machine_desc *mdesc)
 {
 	void *zero_page;
 
+#ifdef CONFIG_XIP_KERNEL
+	/* Store the kernel RW RAM region start/end in these variables */
+	kernel_sec_start = CONFIG_PHYS_OFFSET & SECTION_MASK;
+	kernel_sec_end = round_up(__pa(_end), SECTION_SIZE);
+#endif
 	pr_debug("physical kernel sections: 0x%08llx-0x%08llx\n",
 		 kernel_sec_start, kernel_sec_end);
 

arch/arm64/include/asm/mman.h

@@ -3,6 +3,8 @@
 #define __ASM_MMAN_H__
 
 #include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/shmem_fs.h>
 #include <linux/types.h>
 #include <uapi/asm/mman.h>
 
@@ -21,19 +23,21 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
 
-static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
+static inline unsigned long arch_calc_vm_flag_bits(struct file *file,
+						   unsigned long flags)
 {
 	/*
 	 * Only allow MTE on anonymous mappings as these are guaranteed to be
 	 * backed by tags-capable memory. The vm_flags may be overridden by a
 	 * filesystem supporting MTE (RAM-based).
 	 */
-	if (system_supports_mte() && (flags & MAP_ANONYMOUS))
+	if (system_supports_mte() &&
+	    ((flags & MAP_ANONYMOUS) || shmem_file(file)))
 		return VM_MTE_ALLOWED;
 
 	return 0;
 }
-#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
+#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags)
 
 static inline bool arch_validate_prot(unsigned long prot,
 	unsigned long addr __always_unused)

arch/loongarch/include/asm/kasan.h

@@ -51,7 +51,7 @@
 /* KAsan shadow memory start right after vmalloc. */
 #define KASAN_SHADOW_START		round_up(KFENCE_AREA_END, PGDIR_SIZE)
 #define KASAN_SHADOW_SIZE		(XKVRANGE_VC_SHADOW_END - XKPRANGE_CC_KASAN_OFFSET)
-#define KASAN_SHADOW_END		round_up(KASAN_SHADOW_START + KASAN_SHADOW_SIZE, PGDIR_SIZE)
+#define KASAN_SHADOW_END		(round_up(KASAN_SHADOW_START + KASAN_SHADOW_SIZE, PGDIR_SIZE) - 1)
 
 #define XKPRANGE_CC_SHADOW_OFFSET	(KASAN_SHADOW_START + XKPRANGE_CC_KASAN_OFFSET)
 #define XKPRANGE_UC_SHADOW_OFFSET	(KASAN_SHADOW_START + XKPRANGE_UC_KASAN_OFFSET)

arch/loongarch/kernel/smp.c

@@ -294,7 +294,7 @@ static void __init fdt_smp_setup(void)
 		__cpu_number_map[cpuid] = cpu;
 		__cpu_logical_map[cpu] = cpuid;
 
-		early_numa_add_cpu(cpu, 0);
+		early_numa_add_cpu(cpuid, 0);
 		set_cpuid_to_node(cpuid, 0);
 	}
 

arch/loongarch/mm/kasan_init.c

@@ -13,6 +13,13 @@
 
 static pgd_t kasan_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
 
+#ifdef __PAGETABLE_P4D_FOLDED
+#define __pgd_none(early, pgd) (0)
+#else
+#define __pgd_none(early, pgd) (early ? (pgd_val(pgd) == 0) : \
+(__pa(pgd_val(pgd)) == (unsigned long)__pa(kasan_early_shadow_p4d)))
+#endif
+
 #ifdef __PAGETABLE_PUD_FOLDED
 #define __p4d_none(early, p4d) (0)
 #else
@@ -142,6 +149,19 @@ static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node,
 	return pud_offset(p4dp, addr);
 }
 
+static p4d_t *__init kasan_p4d_offset(pgd_t *pgdp, unsigned long addr, int node, bool early)
+{
+	if (__pgd_none(early, pgdp_get(pgdp))) {
+		phys_addr_t p4d_phys = early ?
+			__pa_symbol(kasan_early_shadow_p4d) : kasan_alloc_zeroed_page(node);
+		if (!early)
+			memcpy(__va(p4d_phys), kasan_early_shadow_p4d, sizeof(kasan_early_shadow_p4d));
+		pgd_populate(&init_mm, pgdp, (p4d_t *)__va(p4d_phys));
+	}
+
+	return p4d_offset(pgdp, addr);
+}
+
 static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
 				      unsigned long end, int node, bool early)
 {
@@ -178,19 +198,19 @@ static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr,
 	do {
 		next = pud_addr_end(addr, end);
 		kasan_pmd_populate(pudp, addr, next, node, early);
-	} while (pudp++, addr = next, addr != end);
+	} while (pudp++, addr = next, addr != end && __pud_none(early, READ_ONCE(*pudp)));
 }
 
 static void __init kasan_p4d_populate(pgd_t *pgdp, unsigned long addr,
 					    unsigned long end, int node, bool early)
 {
 	unsigned long next;
-	p4d_t *p4dp = p4d_offset(pgdp, addr);
+	p4d_t *p4dp = kasan_p4d_offset(pgdp, addr, node, early);
 
 	do {
 		next = p4d_addr_end(addr, end);
 		kasan_pud_populate(p4dp, addr, next, node, early);
-	} while (p4dp++, addr = next, addr != end);
+	} while (p4dp++, addr = next, addr != end && __p4d_none(early, READ_ONCE(*p4dp)));
 }
 
 static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
@@ -218,7 +238,7 @@ static void __init kasan_map_populate(unsigned long start, unsigned long end,
 asmlinkage void __init kasan_early_init(void)
 {
 	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE));
-	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE));
+	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END + 1, PGDIR_SIZE));
 }
 
 static inline void kasan_set_pgd(pgd_t *pgdp, pgd_t pgdval)
@@ -233,7 +253,7 @@ static void __init clear_pgds(unsigned long start, unsigned long end)
 	 * swapper_pg_dir. pgd_clear() can't be used
 	 * here because it's nop on 2,3-level pagetable setups
 	 */
-	for (; start < end; start += PGDIR_SIZE)
+	for (; start < end; start = pgd_addr_end(start, end))
 		kasan_set_pgd((pgd_t *)pgd_offset_k(start), __pgd(0));
 }
 
@@ -242,6 +262,17 @@ void __init kasan_init(void)
 	u64 i;
 	phys_addr_t pa_start, pa_end;
 
+	/*
+	 * If PGDIR_SIZE is too large for cpu_vabits, KASAN_SHADOW_END will
+	 * overflow UINTPTR_MAX and then looks like a user space address.
+	 * For example, PGDIR_SIZE of CONFIG_4KB_4LEVEL is 2^39, which is too
+	 * large for Loongson-2K series whose cpu_vabits = 39.
+	 */
+	if (KASAN_SHADOW_END < vm_map_base) {
+		pr_warn("PGDIR_SIZE too large for cpu_vabits, KernelAddressSanitizer disabled.\n");
+		return;
+	}
+
 	/*
 	 * PGD was populated as invalid_pmd_table or invalid_pud_table
 	 * in pagetable_init() which depends on how many levels of page

arch/parisc/include/asm/mman.h

@@ -2,6 +2,7 @@
 #ifndef __ASM_MMAN_H__
 #define __ASM_MMAN_H__
 
+#include <linux/fs.h>
 #include <uapi/asm/mman.h>
 
 /* PARISC cannot allow mdwe as it needs writable stacks */
@@ -11,7 +12,7 @@ static inline bool arch_memory_deny_write_exec_supported(void)
 }
 #define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported
 
-static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
+static inline unsigned long arch_calc_vm_flag_bits(struct file *file, unsigned long flags)
 {
 	/*
 	 * The stack on parisc grows upwards, so if userspace requests memory
@@ -23,6 +24,6 @@ static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
 
 	return 0;
 }
-#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
+#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags)
 
 #endif /* __ASM_MMAN_H__ */

arch/x86/kvm/lapic.c

@@ -2603,19 +2603,26 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (apic->apicv_active) {
-		/* irr_pending is always true when apicv is activated. */
-		apic->irr_pending = true;
+	/*
+	 * When APICv is enabled, KVM must always search the IRR for a pending
+	 * IRQ, as other vCPUs and devices can set IRR bits even if the vCPU
+	 * isn't running.  If APICv is disabled, KVM _should_ search the IRR
+	 * for a pending IRQ.  But KVM currently doesn't ensure *all* hardware,
+	 * e.g. CPUs and IOMMUs, has seen the change in state, i.e. searching
+	 * the IRR at this time could race with IRQ delivery from hardware that
+	 * still sees APICv as being enabled.
+	 *
+	 * FIXME: Ensure other vCPUs and devices observe the change in APICv
+	 *        state prior to updating KVM's metadata caches, so that KVM
+	 *        can safely search the IRR and set irr_pending accordingly.
+	 */
+	apic->irr_pending = true;
+
+	if (apic->apicv_active)
 		apic->isr_count = 1;
-	} else {
-		/*
-		 * Don't clear irr_pending, searching the IRR can race with
-		 * updates from the CPU as APICv is still active from hardware's
-		 * perspective.  The flag will be cleared as appropriate when
-		 * KVM injects the interrupt.
-		 */
+	else
 		apic->isr_count = count_vectors(apic->regs + APIC_ISR);
-	}
+
 	apic->highest_isr_cache = -1;
 }
 

arch/x86/kvm/vmx/nested.c

@@ -1150,11 +1150,14 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
 		kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu);
 
 	/*
-	 * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings
-	 * for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a
-	 * full TLB flush from the guest's perspective.  This is required even
-	 * if VPID is disabled in the host as KVM may need to synchronize the
-	 * MMU in response to the guest TLB flush.
+	 * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the
+	 * same VPID as the host, and so architecturally, linear and combined
+	 * mappings for VPID=0 must be flushed at VM-Enter and VM-Exit.  KVM
+	 * emulates L2 sharing L1's VPID=0 by using vpid01 while running L2,
+	 * and so KVM must also emulate TLB flush of VPID=0, i.e. vpid01.  This
+	 * is required if VPID is disabled in KVM, as a TLB flush (there are no
+	 * VPIDs) still occurs from L1's perspective, and KVM may need to
+	 * synchronize the MMU in response to the guest TLB flush.
 	 *
 	 * Note, using TLB_FLUSH_GUEST is correct even if nested EPT is in use.
 	 * EPT is a special snowflake, as guest-physical mappings aren't
@@ -2229,6 +2232,17 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx,
 
 	vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA);
 
+	/*
+	 * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the
+	 * same VPID as the host.  Emulate this behavior by using vpid01 for L2
+	 * if VPID is disabled in vmcs12.  Note, if VPID is disabled, VM-Enter
+	 * and VM-Exit are architecturally required to flush VPID=0, but *only*
+	 * VPID=0.  I.e. using vpid02 would be ok (so long as KVM emulates the
+	 * required flushes), but doing so would cause KVM to over-flush.  E.g.
+	 * if L1 runs L2 X with VPID12=1, then runs L2 Y with VPID12 disabled,
+	 * and then runs L2 X again, then KVM can and should retain TLB entries
+	 * for VPID12=1.
+	 */
 	if (enable_vpid) {
 		if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
 			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
@@ -5827,6 +5841,12 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 		return nested_vmx_fail(vcpu,
 			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 
+	/*
+	 * Always flush the effective vpid02, i.e. never flush the current VPID
+	 * and never explicitly flush vpid01.  INVVPID targets a VPID, not a
+	 * VMCS, and so whether or not the current vmcs12 has VPID enabled is
+	 * irrelevant (and there may not be a loaded vmcs12).
+	 */
 	vpid02 = nested_get_vpid02(vcpu);
 	switch (type) {
 	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:

arch/x86/kvm/vmx/vmx.c

@@ -212,9 +212,11 @@ module_param(ple_window_shrink, uint, 0444);
 static unsigned int ple_window_max        = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
 module_param(ple_window_max, uint, 0444);
 
-/* Default is SYSTEM mode, 1 for host-guest mode */
+/* Default is SYSTEM mode, 1 for host-guest mode (which is BROKEN) */
 int __read_mostly pt_mode = PT_MODE_SYSTEM;
+#ifdef CONFIG_BROKEN
 module_param(pt_mode, int, S_IRUGO);
+#endif
 
 static u32 zx_ext_vmcs_cap;
 
@@ -3211,7 +3213,7 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu)
 
 static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu)
 {
-	if (is_guest_mode(vcpu))
+	if (is_guest_mode(vcpu) && nested_cpu_has_vpid(get_vmcs12(vcpu)))
 		return nested_get_vpid02(vcpu);
 	return to_vmx(vcpu)->vpid;
 }