diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index ef4be781fd0546..09ea62ee96d38b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -529,6 +529,7 @@ enum { /* adapter flags */ USING_SOFT_PARAMS = (1 << 6), MASTER_PF = (1 << 7), FW_OFLD_CONN = (1 << 9), + ROOT_NO_RELAXED_ORDERING = (1 << 10), }; enum { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index e403fa18f1b15e..33bb8678833adc 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -4654,11 +4654,6 @@ static void print_port_info(const struct net_device *dev) dev->name, adap->params.vpd.id, adap->name, buf); } -static void enable_pcie_relaxed_ordering(struct pci_dev *dev) -{ - pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_RELAX_EN); -} - /* * Free the following resources: * - memory used for tables @@ -4908,7 +4903,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } pci_enable_pcie_error_reporting(pdev); - enable_pcie_relaxed_ordering(pdev); pci_set_master(pdev); pci_save_state(pdev); @@ -4947,6 +4941,23 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->msg_enable = DFLT_MSG_ENABLE; memset(adapter->chan_map, 0xff, sizeof(adapter->chan_map)); + /* If possible, we use PCIe Relaxed Ordering Attribute to deliver + * Ingress Packet Data to Free List Buffers in order to allow for + * chipset performance optimizations between the Root Complex and + * Memory Controllers. (Messages to the associated Ingress Queue + * notifying new Packet Placement in the Free Lists Buffers will be + * send without the Relaxed Ordering Attribute thus guaranteeing that + * all preceding PCIe Transaction Layer Packets will be processed + * first.) But some Root Complexes have various issues with Upstream + * Transaction Layer Packets with the Relaxed Ordering Attribute set. + * The PCIe devices which under the Root Complexes will be cleared the + * Relaxed Ordering bit in the configuration space, So we check our + * PCIe configuration space to see if it's flagged with advice against + * using Relaxed Ordering. + */ + if (!pcie_relaxed_ordering_enabled(pdev)) + adapter->flags |= ROOT_NO_RELAXED_ORDERING; + spin_lock_init(&adapter->stats_lock); spin_lock_init(&adapter->tid_release_lock); spin_lock_init(&adapter->win0_lock); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index ede12209f20be4..4ef68f69b58c45 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2719,6 +2719,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, struct fw_iq_cmd c; struct sge *s = &adap->sge; struct port_info *pi = netdev_priv(dev); + int relaxed = !(adap->flags & ROOT_NO_RELAXED_ORDERING); /* Size needs to be multiple of 16, including status entry. */ iq->size = roundup(iq->size, 16); @@ -2772,8 +2773,8 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, flsz = fl->size / 8 + s->stat_len / sizeof(struct tx_desc); c.iqns_to_fl0congen |= htonl(FW_IQ_CMD_FL0PACKEN_F | - FW_IQ_CMD_FL0FETCHRO_F | - FW_IQ_CMD_FL0DATARO_F | + FW_IQ_CMD_FL0FETCHRO_V(relaxed) | + FW_IQ_CMD_FL0DATARO_V(relaxed) | FW_IQ_CMD_FL0PADEN_F); if (cong >= 0) c.iqns_to_fl0congen |= diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h index 109bc630408b65..08c6ddb84a049e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h +++ b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h @@ -408,6 +408,7 @@ enum { /* adapter flags */ USING_MSI = (1UL << 1), USING_MSIX = (1UL << 2), QUEUES_BOUND = (1UL << 3), + ROOT_NO_RELAXED_ORDERING = (1UL << 4), }; /* diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index ac7a150c54e9b4..2b85b874fd0d2c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -2888,6 +2888,24 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, */ adapter->name = pci_name(pdev); adapter->msg_enable = DFLT_MSG_ENABLE; + + /* If possible, we use PCIe Relaxed Ordering Attribute to deliver + * Ingress Packet Data to Free List Buffers in order to allow for + * chipset performance optimizations between the Root Complex and + * Memory Controllers. (Messages to the associated Ingress Queue + * notifying new Packet Placement in the Free Lists Buffers will be + * send without the Relaxed Ordering Attribute thus guaranteeing that + * all preceding PCIe Transaction Layer Packets will be processed + * first.) But some Root Complexes have various issues with Upstream + * Transaction Layer Packets with the Relaxed Ordering Attribute set. + * The PCIe devices which under the Root Complexes will be cleared the + * Relaxed Ordering bit in the configuration space, So we check our + * PCIe configuration space to see if it's flagged with advice against + * using Relaxed Ordering. + */ + if (!pcie_relaxed_ordering_enabled(pdev)) + adapter->flags |= ROOT_NO_RELAXED_ORDERING; + err = adap_init0(adapter); if (err) goto err_unmap_bar; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c index e37dde2ba97f6d..05498e7f284034 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c @@ -2205,6 +2205,7 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq, struct port_info *pi = netdev_priv(dev); struct fw_iq_cmd cmd, rpl; int ret, iqandst, flsz = 0; + int relaxed = !(adapter->flags & ROOT_NO_RELAXED_ORDERING); /* * If we're using MSI interrupts and we're not initializing the @@ -2300,6 +2301,8 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq, cpu_to_be32( FW_IQ_CMD_FL0HOSTFCMODE_V(SGE_HOSTFCMODE_NONE) | FW_IQ_CMD_FL0PACKEN_F | + FW_IQ_CMD_FL0FETCHRO_V(relaxed) | + FW_IQ_CMD_FL0DATARO_V(relaxed) | FW_IQ_CMD_FL0PADEN_F); /* In T6, for egress queue type FL there is internal overhead diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index c31310db040473..e6a917b4acd3f3 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1762,6 +1762,48 @@ static void pci_configure_extended_tags(struct pci_dev *dev) PCI_EXP_DEVCTL_EXT_TAG); } +/** + * pcie_relaxed_ordering_enabled - Probe for PCIe relaxed ordering enable + * @dev: PCI device to query + * + * Returns true if the device has enabled relaxed ordering attribute. + */ +bool pcie_relaxed_ordering_enabled(struct pci_dev *dev) +{ + u16 v; + + pcie_capability_read_word(dev, PCI_EXP_DEVCTL, &v); + + return !!(v & PCI_EXP_DEVCTL_RELAX_EN); +} +EXPORT_SYMBOL(pcie_relaxed_ordering_enabled); + +static void pci_configure_relaxed_ordering(struct pci_dev *dev) +{ + struct pci_dev *root; + + /* PCI_EXP_DEVICE_RELAX_EN is RsvdP in VFs */ + if (dev->is_virtfn) + return; + + if (!pcie_relaxed_ordering_enabled(dev)) + return; + + /* + * For now, we only deal with Relaxed Ordering issues with Root + * Ports. Peer-to-Peer DMA is another can of worms. + */ + root = pci_find_pcie_root_port(dev); + if (!root) + return; + + if (root->dev_flags & PCI_DEV_FLAGS_NO_RELAXED_ORDERING) { + pcie_capability_clear_word(dev, PCI_EXP_DEVCTL, + PCI_EXP_DEVCTL_RELAX_EN); + dev_info(&dev->dev, "Disable Relaxed Ordering because the Root Port didn't support it\n"); + } +} + static void pci_configure_device(struct pci_dev *dev) { struct hotplug_params hpp; @@ -1769,6 +1811,7 @@ static void pci_configure_device(struct pci_dev *dev) pci_configure_mps(dev); pci_configure_extended_tags(dev); + pci_configure_relaxed_ordering(dev); memset(&hpp, 0, sizeof(hpp)); ret = pci_get_hp_params(dev, &hpp); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 6967c6b4cf6b01..140760403f36a9 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4015,6 +4015,95 @@ DECLARE_PCI_FIXUP_CLASS_EARLY(0x1797, 0x6868, PCI_CLASS_NOT_DEFINED, 8, DECLARE_PCI_FIXUP_CLASS_EARLY(0x1797, 0x6869, PCI_CLASS_NOT_DEFINED, 8, quirk_tw686x_class); +/* + * Some devices have problems with Transaction Layer Packets with the Relaxed + * Ordering Attribute set. Such devices should mark themselves and other + * Device Drivers should check before sending TLPs with RO set. + */ +static void quirk_relaxedordering_disable(struct pci_dev *dev) +{ + dev->dev_flags |= PCI_DEV_FLAGS_NO_RELAXED_ORDERING; + dev_info(&dev->dev, "Disable Relaxed Ordering Attributes to avoid PCIe Completion erratum\n"); +} + +/* + * Intel Xeon processors based on Broadwell/Haswell microarchitecture Root + * Complex has a Flow Control Credit issue which can cause performance + * problems with Upstream Transaction Layer Packets with Relaxed Ordering set. + */ +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f01, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f02, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f03, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f04, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f05, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f06, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f07, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f08, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f09, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f0a, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f0b, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f0c, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f0d, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f0e, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f01, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f02, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f03, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f04, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f05, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f06, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f07, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f08, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f09, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f0a, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f0b, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f0c, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f0d, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f0e, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); + +/* + * The AMD ARM A1100 (AKA "SEATTLE") SoC has a bug in its PCIe Root Complex + * where Upstream Transaction Layer Packets with the Relaxed Ordering + * Attribute clear are allowed to bypass earlier TLPs with Relaxed Ordering + * set. This is a violation of the PCIe 3.0 Transaction Ordering Rules + * outlined in Section 2.4.1 (PCI Express(r) Base Specification Revision 3.0 + * November 10, 2010). As a result, on this platform we can't use Relaxed + * Ordering for Upstream TLPs. + */ +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_AMD, 0x1a00, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_AMD, 0x1a01, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_AMD, 0x1a02, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); + /* * Per PCIe r3.0, sec 2.2.9, "Completion headers must supply the same * values for the Attribute as were supplied in the header of the diff --git a/include/linux/pci.h b/include/linux/pci.h index 4869e66dd659a6..29606fb8946423 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -188,6 +188,8 @@ enum pci_dev_flags { * the direct_complete optimization. */ PCI_DEV_FLAGS_NEEDS_RESUME = (__force pci_dev_flags_t) (1 << 11), + /* Don't use Relaxed Ordering for TLPs directed at this device */ + PCI_DEV_FLAGS_NO_RELAXED_ORDERING = (__force pci_dev_flags_t) (1 << 12), }; enum pci_irq_reroute_variant { @@ -1125,6 +1127,7 @@ bool pci_check_pme_status(struct pci_dev *dev); void pci_pme_wakeup_bus(struct pci_bus *bus); void pci_d3cold_enable(struct pci_dev *dev); void pci_d3cold_disable(struct pci_dev *dev); +bool pcie_relaxed_ordering_enabled(struct pci_dev *dev); /* PCI Virtual Channel */ int pci_save_vc_state(struct pci_dev *dev);