diff options
40 files changed, 636 insertions, 167 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats new file mode 100644 index 000000000000..4b0318c99507 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats @@ -0,0 +1,122 @@ +========================== +PCIe Device AER statistics +========================== +These attributes show up under all the devices that are AER capable. These +statistical counters indicate the errors "as seen/reported by the device". +Note that this may mean that if an endpoint is causing problems, the AER +counters may increment at its link partner (e.g. root port) because the +errors may be "seen" / reported by the link partner and not the +problematic endpoint itself (which may report all counters as 0 as it never +saw any problems). + +Where: /sys/bus/pci/devices/<dev>/aer_dev_correctable +Date: July 2018 +Kernel Version: 4.19.0 +Contact: linux-pci@vger.kernel.org, rajatja@google.com +Description: List of correctable errors seen and reported by this + PCI device using ERR_COR. Note that since multiple errors may + be reported using a single ERR_COR message, thus + TOTAL_ERR_COR at the end of the file may not match the actual + total of all the errors in the file. Sample output: +------------------------------------------------------------------------- +localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_correctable +Receiver Error 2 +Bad TLP 0 +Bad DLLP 0 +RELAY_NUM Rollover 0 +Replay Timer Timeout 0 +Advisory Non-Fatal 0 +Corrected Internal Error 0 +Header Log Overflow 0 +TOTAL_ERR_COR 2 +------------------------------------------------------------------------- + +Where: /sys/bus/pci/devices/<dev>/aer_dev_fatal +Date: July 2018 +Kernel Version: 4.19.0 +Contact: linux-pci@vger.kernel.org, rajatja@google.com +Description: List of uncorrectable fatal errors seen and reported by this + PCI device using ERR_FATAL. Note that since multiple errors may + be reported using a single ERR_FATAL message, thus + TOTAL_ERR_FATAL at the end of the file may not match the actual + total of all the errors in the file. Sample output: +------------------------------------------------------------------------- +localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_fatal +Undefined 0 +Data Link Protocol 0 +Surprise Down Error 0 +Poisoned TLP 0 +Flow Control Protocol 0 +Completion Timeout 0 +Completer Abort 0 +Unexpected Completion 0 +Receiver Overflow 0 +Malformed TLP 0 +ECRC 0 +Unsupported Request 0 +ACS Violation 0 +Uncorrectable Internal Error 0 +MC Blocked TLP 0 +AtomicOp Egress Blocked 0 +TLP Prefix Blocked Error 0 +TOTAL_ERR_FATAL 0 +------------------------------------------------------------------------- + +Where: /sys/bus/pci/devices/<dev>/aer_dev_nonfatal +Date: July 2018 +Kernel Version: 4.19.0 +Contact: linux-pci@vger.kernel.org, rajatja@google.com +Description: List of uncorrectable nonfatal errors seen and reported by this + PCI device using ERR_NONFATAL. Note that since multiple errors + may be reported using a single ERR_FATAL message, thus + TOTAL_ERR_NONFATAL at the end of the file may not match the + actual total of all the errors in the file. Sample output: +------------------------------------------------------------------------- +localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_nonfatal +Undefined 0 +Data Link Protocol 0 +Surprise Down Error 0 +Poisoned TLP 0 +Flow Control Protocol 0 +Completion Timeout 0 +Completer Abort 0 +Unexpected Completion 0 +Receiver Overflow 0 +Malformed TLP 0 +ECRC 0 +Unsupported Request 0 +ACS Violation 0 +Uncorrectable Internal Error 0 +MC Blocked TLP 0 +AtomicOp Egress Blocked 0 +TLP Prefix Blocked Error 0 +TOTAL_ERR_NONFATAL 0 +------------------------------------------------------------------------- + +============================ +PCIe Rootport AER statistics +============================ +These attributes show up under only the rootports (or root complex event +collectors) that are AER capable. These indicate the number of error messages as +"reported to" the rootport. Please note that the rootports also transmit +(internally) the ERR_* messages for errors seen by the internal rootport PCI +device, so these counters include them and are thus cumulative of all the error +messages on the PCI hierarchy originating at that root port. + +Where: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_cor +Date: July 2018 +Kernel Version: 4.19.0 +Contact: linux-pci@vger.kernel.org, rajatja@google.com +Description: Total number of ERR_COR messages reported to rootport. + +Where: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_fatal +Date: July 2018 +Kernel Version: 4.19.0 +Contact: linux-pci@vger.kernel.org, rajatja@google.com +Description: Total number of ERR_FATAL messages reported to rootport. + +Where: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_nonfatal +Date: July 2018 +Kernel Version: 4.19.0 +Contact: linux-pci@vger.kernel.org, rajatja@google.com +Description: Total number of ERR_NONFATAL messages reported to rootport. diff --git a/Documentation/PCI/pcieaer-howto.txt b/Documentation/PCI/pcieaer-howto.txt index acd0dddd6bb8..48ce7903e3c6 100644 --- a/Documentation/PCI/pcieaer-howto.txt +++ b/Documentation/PCI/pcieaer-howto.txt @@ -73,6 +73,11 @@ In the example, 'Requester ID' means the ID of the device who sends the error message to root port. Pls. refer to pci express specs for other fields. +2.4 AER Statistics / Counters + +When PCIe AER errors are captured, the counters / statistics are also exposed +in the form of sysfs attributes which are documented at +Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats 3. Developer Guide diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 54eeb8d00bc6..843edfd000be 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1245,8 +1245,14 @@ config PCI VESA. If you have PCI, say Y, otherwise N. config PCI_DOMAINS - bool + bool "Support for multiple PCI domains" depends on PCI + help + Enable PCI domains kernel management. Say Y if your machine + has a PCI bus hierarchy that requires more than one PCI + domain (aka segment) to be correctly managed. Say N otherwise. + + If you don't know what to do here, say N. config PCI_DOMAINS_GENERIC def_bool PCI_DOMAINS diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig index c46a728df44e..25aac6ee2ab1 100644 --- a/arch/arm/mach-bcm/Kconfig +++ b/arch/arm/mach-bcm/Kconfig @@ -20,6 +20,7 @@ config ARCH_BCM_IPROC select GPIOLIB select ARM_AMBA select PINCTRL + select PCI_DOMAINS if PCI help This enables support for systems based on Broadcom IPROC architected SoCs. The IPROC complex contains one or more ARM CPUs along with common diff --git a/arch/arm/mach-socfpga/Kconfig b/arch/arm/mach-socfpga/Kconfig index d0f62eacf59d..4adb901dd5eb 100644 --- a/arch/arm/mach-socfpga/Kconfig +++ b/arch/arm/mach-socfpga/Kconfig @@ -10,6 +10,7 @@ menuconfig ARCH_SOCFPGA select HAVE_ARM_SCU select HAVE_ARM_TWD if SMP select MFD_SYSCON + select PCI_DOMAINS if PCI if ARCH_SOCFPGA config SOCFPGA_SUSPEND diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index fe9733ffffaa..471aac313b89 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -42,6 +42,8 @@ #include <asm/ppc-pci.h> #include <asm/eeh.h> +#include "../../../drivers/pci/pci.h" + /* hose_spinlock protects accesses to the the phb_bitmap. */ static DEFINE_SPINLOCK(hose_spinlock); LIST_HEAD(hose_list); @@ -1014,7 +1016,7 @@ void pcibios_setup_bus_devices(struct pci_bus *bus) /* Cardbus can call us to add new devices to a bus, so ignore * those who are already fully discovered */ - if (dev->is_added) + if (pci_dev_is_added(dev)) continue; pcibios_setup_device(dev); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 5bd0eb6681bc..70b2e1e0f23c 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -46,6 +46,7 @@ #include "powernv.h" #include "pci.h" +#include "../../../../drivers/pci/pci.h" #define PNV_IODA1_M64_NUM 16 /* Number of M64 BARs */ #define PNV_IODA1_M64_SEGS 8 /* Segments per M64 BAR */ @@ -3138,7 +3139,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) struct pci_dn *pdn; int mul, total_vfs; - if (!pdev->is_physfn || pdev->is_added) + if (!pdev->is_physfn || pci_dev_is_added(pdev)) return; pdn = pci_get_pdn(pdev); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 139f0af6c3d9..8a4868a3964b 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -71,6 +71,7 @@ #include <asm/security_features.h> #include "pseries.h" +#include "../../../../drivers/pci/pci.h" int CMO_PrPSP = -1; int CMO_SecPSP = -1; @@ -664,7 +665,7 @@ static void pseries_pci_fixup_iov_resources(struct pci_dev *pdev) const int *indexes; struct device_node *dn = pci_device_to_OF_node(pdev); - if (!pdev->is_physfn || pdev->is_added) + if (!pdev->is_physfn || pci_dev_is_added(pdev)) return; /*Firmware must support open sriov otherwise dont configure*/ indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index 46b76d5a726c..152283d7e59c 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -240,7 +240,6 @@ static int nfp_pcie_sriov_read_nfd_limit(struct nfp_pf *pf) return pci_sriov_set_totalvfs(pf->pdev, pf->limit_vfs); pf->limit_vfs = ~0; - pci_sriov_set_totalvfs(pf->pdev, 0); /* 0 is unset */ /* Allow any setting for backwards compatibility if symbol not found */ if (err == -ENOENT) return 0; @@ -668,7 +667,7 @@ static int nfp_pci_probe(struct pci_dev *pdev, err = nfp_net_pci_probe(pf); if (err) - goto err_sriov_unlimit; + goto err_fw_unload; err = nfp_hwmon_register(pf); if (err) { @@ -680,8 +679,6 @@ static int nfp_pci_probe(struct pci_dev *pdev, err_net_remove: nfp_net_pci_remove(pf); -err_sriov_unlimit: - pci_sriov_set_totalvfs(pf->pdev, 0); err_fw_unload: kfree(pf->rtbl); nfp_mip_close(pf->mip); @@ -715,7 +712,6 @@ static void nfp_pci_remove(struct pci_dev *pdev) nfp_hwmon_unregister(pf); nfp_pcie_sriov_disable(pdev); - pci_sriov_set_totalvfs(pf->pdev, 0); nfp_net_pci_remove(pf); diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile index 535201984b8b..1b2cfe51e8d7 100644 --- a/drivers/pci/Makefile +++ b/drivers/pci/Makefile @@ -28,10 +28,10 @@ obj-$(CONFIG_PCI_PF_STUB) += pci-pf-stub.o obj-$(CONFIG_PCI_ECAM) += ecam.o obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o -obj-y += controller/ -obj-y += switch/ - # Endpoint library must be initialized before its users obj-$(CONFIG_PCI_ENDPOINT) += endpoint/ +obj-y += controller/ +obj-y += switch/ + ccflags-$(CONFIG_PCI_DEBUG) := -DDEBUG diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 35b7fc87eac5..5cb40b2518f9 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -330,7 +330,7 @@ void pci_bus_add_device(struct pci_dev *dev) return; } - dev->is_added = 1; + pci_dev_assign_added(dev, true); } EXPORT_SYMBOL_GPL(pci_bus_add_device); @@ -347,14 +347,14 @@ void pci_bus_add_devices(const struct pci_bus *bus) list_for_each_entry(dev, &bus->devices, bus_list) { /* Skip already-added devices */ - if (dev->is_added) + if (pci_dev_is_added(dev)) continue; pci_bus_add_device(dev); } list_for_each_entry(dev, &bus->devices, bus_list) { /* Skip if device attach failed */ - if (!dev->is_added) + if (!pci_dev_is_added(dev)) continue; child = dev->subordinate; if (child) diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index 18fa09b3ac8f..cc9fa02d32a0 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -96,7 +96,6 @@ config PCI_HOST_GENERIC depends on OF select PCI_HOST_COMMON select IRQ_DOMAIN - select PCI_DOMAINS help Say Y here if you want to support a simple generic PCI host controller, such as the one emulated by kvmtool. @@ -138,7 +137,6 @@ config PCI_VERSATILE config PCIE_IPROC tristate - select PCI_DOMAINS help This enables the iProc PCIe core controller support for Broadcom's iProc family of SoCs. An appropriate bus interface driver needs @@ -176,7 +174,6 @@ config PCIE_IPROC_MSI config PCIE_ALTERA bool "Altera PCIe controller" depends on ARM || NIOS2 || COMPILE_TEST - select PCI_DOMAINS help Say Y here if you want to enable PCIe controller support on Altera FPGA. diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig index 16f52c626b4b..91b0194240a5 100644 --- a/drivers/pci/controller/dwc/Kconfig +++ b/drivers/pci/controller/dwc/Kconfig @@ -58,7 +58,6 @@ config PCIE_DW_PLAT_HOST depends on PCI && PCI_MSI_IRQ_DOMAIN select PCIE_DW_HOST select PCIE_DW_PLAT - default y help Enables support for the PCIe controller in the Designware IP to work in host mode. There are two instances of PCIe controller in diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 781aa03aeede..29a05759a294 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -363,7 +363,8 @@ int dw_pcie_host_init(struct pcie_port *pp) resource_list_for_each_entry_safe(win, tmp, &bridge->windows) { switch (resource_type(win->res)) { case IORESOURCE_IO: - ret = pci_remap_iospace(win->res, pp->io_base); + ret = devm_pci_remap_iospace(dev, win->res, + pp->io_base); if (ret) { dev_warn(dev, "Error %d: failed to map resource %pR\n", ret, win->res); diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index d3172d5d3d35..0fae816fba39 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -849,7 +849,7 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie) 0, 0xF8000000, 0, lower_32_bits(res->start), OB_PCIE_IO); - err = pci_remap_iospace(res, iobase); + err = devm_pci_remap_iospace(dev, res, iobase); if (err) { dev_warn(dev, "error %d: failed to map resource %pR\n", err, res); diff --git a/drivers/pci/controller/pci-ftpci100.c b/drivers/pci/controller/pci-ftpci100.c index a1ebe9ed441f..bf5ece5d9291 100644 --- a/drivers/pci/controller/pci-ftpci100.c +++ b/drivers/pci/controller/pci-ftpci100.c @@ -355,11 +355,13 @@ static int faraday_pci_setup_cascaded_irq(struct faraday_pci *p) irq = of_irq_get(intc, 0); if (irq <= 0) { dev_err(p->dev, "failed to get parent IRQ\n"); + of_node_put(intc); return irq ?: -EINVAL; } p->irqdomain = irq_domain_add_linear(intc, PCI_NUM_INTX, &faraday_pci_irqdomain_ops, p); + of_node_put(intc); if (!p->irqdomain) { dev_err(p->dev, "failed to create Gemini PCI IRQ domain\n"); return -EINVAL; @@ -501,7 +503,7 @@ static int faraday_pci_probe(struct platform_device *pdev) dev_err(dev, "illegal IO mem size\n"); return -EINVAL; } - ret = pci_remap_iospace(io, io_base); + ret = devm_pci_remap_iospace(dev, io, io_base); if (ret) { dev_warn(dev, "error %d: failed to map resource %pR\n", ret, io); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 6cc5036ac83c..f6325f1a89e8 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -1073,6 +1073,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct pci_bus *pbus; struct pci_dev *pdev; struct cpumask *dest; + unsigned long flags; struct compose_comp_ctxt comp; struct tran_int_desc *int_desc; struct { @@ -1164,14 +1165,15 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) * the channel callback directly when channel->target_cpu is * the current CPU. When the higher level interrupt code * calls us with interrupt enabled, let's add the - * local_bh_disable()/enable() to avoid race. + * local_irq_save()/restore() to avoid race: + * hv_pci_onchannelcallback() can also run in tasklet. */ - local_bh_disable(); + local_irq_save(flags); if (hbus->hdev->channel->target_cpu == smp_processor_id()) hv_pci_onchannelcallback(hbus); - local_bh_enable(); + local_irq_restore(flags); if (hpdev->state == hv_pcichild_ejecting) { dev_err_once(&hbus->hdev->device, diff --git a/drivers/pci/controller/pci-v3-semi.c b/drivers/pci/controller/pci-v3-semi.c index 68b8bfbdb867..d219404bad92 100644 --- a/drivers/pci/controller/pci-v3-semi.c +++ b/drivers/pci/controller/pci-v3-semi.c @@ -537,7 +537,7 @@ static int v3_pci_setup_resource(struct v3_pci *v3, v3->io_bus_addr = io->start - win->offset; dev_dbg(dev, "I/O window %pR, bus addr %pap\n", io, &v3->io_bus_addr); - ret = pci_remap_iospace(io, io_base); + ret = devm_pci_remap_iospace(dev, io, io_base); if (ret) { dev_warn(dev, "error %d: failed to map resource %pR\n", diff --git a/drivers/pci/controller/pci-versatile.c b/drivers/pci/controller/pci-versatile.c index 994f32061b32..f59ad2728c0b 100644 --- a/drivers/pci/controller/pci-versatile.c +++ b/drivers/pci/controller/pci-versatile.c @@ -82,7 +82,7 @@ static int versatile_pci_parse_request_of_pci_ranges(struct device *dev, switch (resource_type(res)) { case IORESOURCE_IO: - err = pci_remap_iospace(res, iobase); + err = devm_pci_remap_iospace(dev, res, iobase); if (err) { dev_warn(dev, "error %d: failed to map resource %pR\n", err, res); diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c index d854d67e873c..ffda3e8b4742 100644 --- a/drivers/pci/controller/pci-xgene.c +++ b/drivers/pci/controller/pci-xgene.c @@ -423,7 +423,7 @@ static int xgene_pcie_map_ranges(struct xgene_pcie_port *port, case IORESOURCE_IO: xgene_pcie_setup_ob_reg(port, res, OMR3BARL, io_base, res->start - window->offset); - ret = pci_remap_iospace(res, io_base); + ret = devm_pci_remap_iospace(dev, res, io_base); if (ret < 0) return ret; break; diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index 0baabe30858f..861dda69f366 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -1109,7 +1109,7 @@ static int mtk_pcie_request_resources(struct mtk_pcie *pcie) if (err < 0) return err; - pci_remap_iospace(&pcie->pio, pcie->io.start); + devm_pci_remap_iospace(dev, &pcie->pio, pcie->io.start); return 0; } diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c index 4d6c20e47bed..cf0aa7cee5b0 100644 --- a/drivers/pci/controller/pcie-mobiveil.c +++ b/drivers/pci/controller/pcie-mobiveil.c @@ -107,7 +107,7 @@ #define CFG_WINDOW_TYPE 0 #define IO_WINDOW_TYPE 1 #define MEM_WINDOW_TYPE 2 -#define IB_WIN_SIZE (256 * 1024 * 1024 * 1024) +#define IB_WIN_SIZE ((u64)256 * 1024 * 1024 * 1024) #define MAX_PIO_WINDOWS 8 /* Parameters for the waiting for link up routine */ diff --git a/drivers/pci/controller/pcie-rcar.c b/drivers/pci/controller/pcie-rcar.c index 874d75c9ee4a..c8febb009454 100644 --- a/drivers/pci/controller/pcie-rcar.c +++ b/drivers/pci/controller/pcie-rcar.c @@ -680,7 +680,11 @@ static int rcar_pcie_phy_init_gen3(struct rcar_pcie *pcie) if (err) return err; - return phy_power_on(pcie->phy); + err = phy_power_on(pcie->phy); + if (err) + phy_exit(pcie->phy); + + return err; } static int rcar_msi_alloc(struct rcar_msi *chip) @@ -1165,7 +1169,7 @@ static int rcar_pcie_probe(struct platform_device *pdev) if (rcar_pcie_hw_init(pcie)) { dev_info(dev, "PCIe link down\n"); err = -ENODEV; - goto err_clk_disable; + goto err_phy_shutdown; } data = rcar_pci_read_reg(pcie, MACSR); @@ -1177,7 +1181,7 @@ static int rcar_pcie_probe(struct platform_device *pdev) dev_err(dev, "failed to enable MSI support: %d\n", err); - goto err_clk_disable; + goto err_phy_shutdown; } } @@ -1191,6 +1195,12 @@ err_msi_teardown: if (IS_ENABLED(CONFIG_PCI_MSI)) rcar_pcie_teardown_msi(pcie); +err_phy_shutdown: + if (pcie->phy) { + phy_power_off(pcie->phy); + phy_exit(pcie->phy); + } + err_clk_disable: clk_disable_unprepare(pcie->bus_clk); diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c index 6a4bbb5b3de0..fb32840ce8e6 100644 --- a/drivers/pci/controller/pcie-xilinx-nwl.c +++ b/drivers/pci/controller/pcie-xilinx-nwl.c @@ -559,7 +559,7 @@ static int nwl_pcie_init_irq_domain(struct nwl_pcie *pcie) PCI_NUM_INTX, &legacy_domain_ops, pcie); - + of_node_put(legacy_intc_node); if (!pcie->legacy_irq_domain) { dev_err(dev, "failed to create IRQ domain\n"); return -ENOMEM; diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c index b110a3a814e3..7b1389d8e2a5 100644 --- a/drivers/pci/controller/pcie-xilinx.c +++ b/drivers/pci/controller/pcie-xilinx.c @@ -509,6 +509,7 @@ static int xilinx_pcie_init_irq_domain(struct xilinx_pcie_port *port) port->leg_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, &intx_domain_ops, port); + of_node_put(pcie_intc_node); if (!port->leg_domain) { dev_err(dev, "Failed to get a INTx IRQ domain\n"); return -ENODEV; diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index 523a8cab3bfb..825fa24427a3 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -137,6 +137,20 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar) } EXPORT_SYMBOL_GPL(pci_epf_alloc_space); +static void pci_epf_remove_cfs(struct pci_epf_driver *driver) +{ + struct config_group *group, *tmp; + + if (!IS_ENABLED(CONFIG_PCI_ENDPOINT_CONFIGFS)) + return; + + mutex_lock(&pci_epf_mutex); + list_for_each_entry_safe(group, tmp, &driver->epf_group, group_entry) + pci_ep_cfs_remove_epf_group(group); + list_del(&driver->epf_group); + mutex_unlock(&pci_epf_mutex); +} + /** * pci_epf_unregister_driver() - unregister the PCI EPF driver * @driver: the PCI EPF driver that has to be unregistered @@ -145,17 +159,38 @@ EXPORT_SYMBOL_GPL(pci_epf_alloc_space); */ void pci_epf_unregister_driver(struct pci_epf_driver *driver) { - struct config_group *group; - - mutex_lock(&pci_epf_mutex); - list_for_each_entry(group, &driver->epf_group, group_entry) - pci_ep_cfs_remove_epf_group(group); - list_del(&driver->epf_group); - mutex_unlock(&pci_epf_mutex); + pci_epf_remove_cfs(driver); driver_unregister(&driver->driver); } EXPORT_SYMBOL_GPL(pci_epf_unregister_driver); +static int pci_epf_add_cfs(struct pci_epf_driver *driver) +{ + struct config_group *group; + const struct pci_epf_device_id *id; + + if (!IS_ENABLED(CONFIG_PCI_ENDPOINT_CONFIGFS)) + return 0; + + INIT_LIST_HEAD(&driver->epf_group); + + id = driver->id_table; + while (id->name[0]) { + group = pci_ep_cfs_add_epf_group(id->name); + if (IS_ERR(group)) { + pci_epf_remove_cfs(driver); + return PTR_ERR(group); + } + + mutex_lock(&pci_epf_mutex); + list_add_tail(&group->group_entry, &driver->epf_group); + mutex_unlock(&pci_epf_mutex); + id++; + } + + return 0; +} + /** * __pci_epf_register_driver() - register a new PCI EPF driver * @driver: structure representing PCI EPF driver @@ -167,8 +202,6 @@ int __pci_epf_register_driver(struct pci_epf_driver *driver, struct module *owner) { int ret; - struct config_group *group; - const struct pci_epf_device_id *id; if (!driver->ops) return -EINVAL; @@ -183,16 +216,7 @@ int __pci_epf_register_driver(struct pci_epf_driver *driver, if (ret) return ret; - INIT_LIST_HEAD(&driver->epf_group); - - id = driver->id_table; - while (id->name[0]) { - group = pci_ep_cfs_add_epf_group(id->name); - mutex_lock(&pci_epf_mutex); - list_add_tail(&group->group_entry, &driver->epf_group); - mutex_unlock(&pci_epf_mutex); - id++; - } + pci_epf_add_cfs(driver); return 0; } diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c index 3979f89b250a..5bd6c1573295 100644 --- a/drivers/pci/hotplug/acpi_pcihp.c +++ b/drivers/pci/hotplug/acpi_pcihp.c @@ -7,7 +7,6 @@ * All rights reserved. * * Send feedback to <kristen.c.accardi@intel.com> - * */ #include <linux/module.h> @@ -87,8 +86,17 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev) return 0; /* If _OSC exists, we should not evaluate OSHP */ + + /* + * If there's no ACPI host bridge (i.e., ACPI support is compiled + * into the kernel but the hardware platform doesn't support ACPI), + * there's nothing to do here. + */ host = pci_find_host_bridge(pdev->bus); root = acpi_pci_find_root(ACPI_HANDLE(&host->dev)); + if (!root) + return 0; + if (root->osc_support_set) goto no_control; diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 3a17b290df5d..ef0b1b6ba86f 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -509,7 +509,7 @@ static void enable_slot(struct acpiphp_slot *slot) list_for_each_entry(dev, &bus->devices, bus_list) { /* Assume that newly added devices are powered on already. */ - if (!dev->is_added) + if (!pci_dev_is_added(dev)) dev->current_state = PCI_D0; } diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index d0d73dbbd5ca..0f04ae648cf1 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -575,6 +575,22 @@ void pci_iov_release(struct pci_dev *dev) } /** + * pci_iov_remove - clean up SR-IOV state after PF driver is detached + * @dev: the PCI device + */ +void pci_iov_remove(struct pci_dev *dev) +{ + struct pci_sriov *iov = dev->sriov; + + if (!dev->is_physfn) + return; + + iov->driver_max_VFs = iov->total_VFs; + if (iov->num_VFs) + pci_warn(dev, "driver left SR-IOV enabled after remove\n"); +} + +/** * pci_iov_update_resource - update a VF BAR * @dev: the PCI device * @resno: the resource number diff --git a/drivers/pci/of.c b/drivers/pci/of.c index d088c9147f10..69a60d6ebd73 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -612,7 +612,7 @@ int pci_parse_request_of_pci_ranges(struct device *dev, switch (resource_type(res)) { case IORESOURCE_IO: - err = pci_remap_iospace(res, iobase); + err = devm_pci_remap_iospace(dev, res, iobase); if (err) { dev_warn(dev, "error %d: failed to map resource %pR\n", err, res); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index c125d53033c6..6792292b5fc7 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -445,6 +445,7 @@ static int pci_device_remove(struct device *dev) } pcibios_free_irq(pci_dev); pci_dev->driver = NULL; + pci_iov_remove(pci_dev); } /* Undo the runtime PM settings in local_pci_probe() */ diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 91337faae60d..32589f5552b2 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -1745,6 +1745,9 @@ static const struct attribute_group *pci_dev_attr_groups[] = { #endif &pci_bridge_attr_group, &pcie_dev_attr_group, +#ifdef CONFIG_PCIEAER + &aer_stats_attr_group, +#endif NULL, }; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index d92d216e4f64..cada2954ecb4 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3578,6 +3578,44 @@ void pci_unmap_iospace(struct resource *res) } EXPORT_SYMBOL(pci_unmap_iospace); +static void devm_pci_unmap_iospace(struct device *dev, void *ptr) +{ + struct resource **res = ptr; + + pci_unmap_iospace(*res); +} + +/** + * devm_pci_remap_iospace - Managed pci_remap_iospace() + * @dev: Generic device to remap IO address for + * @res: Resource describing the I/O space + * @phys_addr: physical address of range to be mapped + * + * Managed pci_remap_iospace(). Map is automatically unmapped on driver + * detach. + */ +int devm_pci_remap_iospace(struct device *dev, const struct resource *res, + phys_addr_t phys_addr) +{ + const struct resource **ptr; + int error; + + ptr = devres_alloc(devm_pci_unmap_iospace, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return -ENOMEM; + + error = pci_remap_iospace(res, phys_addr); + if (error) { + devres_free(ptr); + } else { + *ptr = res; + devres_add(dev, ptr); + } + + return error; +} +EXPORT_SYMBOL(devm_pci_remap_iospace); + /** * devm_pci_remap_cfgspace - Managed pci_remap_cfgspace() * @dev: Generic device to remap IO address for diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index c358e7a07f3f..3ac0d99afe67 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -288,6 +288,7 @@ struct pci_sriov { /* pci_dev priv_flags */ #define PCI_DEV_DISCONNECTED 0 +#define PCI_DEV_ADDED 1 static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused) { @@ -300,6 +301,44 @@ static inline bool pci_dev_is_disconnected(const struct pci_dev *dev) return test_bit(PCI_DEV_DISCONNECTED, &dev->priv_flags); } +static inline void pci_dev_assign_added(struct pci_dev *dev, bool added) +{ + assign_bit(PCI_DEV_ADDED, &dev->priv_flags, added); +} + +static inline bool pci_dev_is_added(const struct pci_dev *dev) +{ + return test_bit(PCI_DEV_ADDED, &dev->priv_flags); +} + +#ifdef CONFIG_PCIEAER +#include <linux/aer.h> + +#define AER_MAX_MULTI_ERR_DEVICES 5 /* Not likely to have more */ + +struct aer_err_info { + struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES]; + int error_dev_num; + + unsigned int id:16; + + unsigned int severity:2; /* 0:NONFATAL | 1:FATAL | 2:COR */ + unsigned int __pad1:5; + unsigned int multi_error_valid:1; + + unsigned int first_error:5; + unsigned int __pad2:2; + unsigned int tlp_header_valid:1; + + unsigned int status; /* COR/UNCOR Error Status */ + unsigned int mask; /* COR/UNCOR Error Mask */ + struct aer_header_log_regs tlp; /* TLP Header */ +}; + +int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info); +void aer_print_error(struct pci_dev *dev, struct aer_err_info *info); +#endif /* CONFIG_PCIEAER */ + #ifdef CONFIG_PCI_ATS void pci_restore_ats_state(struct pci_dev *dev); #else @@ -311,6 +350,7 @@ static inline void pci_restore_ats_state(struct pci_dev *dev) #ifdef CONFIG_PCI_IOV int pci_iov_init(struct pci_dev *dev); void pci_iov_release(struct pci_dev *dev); +void pci_iov_remove(struct pci_dev *dev); void pci_iov_update_resource(struct pci_dev *dev, int resno); resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno); void pci_restore_iov_state(struct pci_dev *dev); @@ -325,6 +365,9 @@ static inline void pci_iov_release(struct pci_dev *dev) { } +static inline void pci_iov_remove(struct pci_dev *dev) +{ +} static inline void pci_restore_iov_state(struct pci_dev *dev) { } @@ -452,4 +495,19 @@ static inline int devm_of_pci_get_host_bridge_resources(struct device *dev, } #endif +#ifdef CONFIG_PCIEAER +void pci_no_aer(void); +void pci_aer_init(struct pci_dev *dev); +void pci_aer_exit(struct pci_dev *dev); +extern const struct attribute_group aer_stats_attr_group; +void pci_aer_clear_fatal_status(struct pci_dev *dev); +void pci_aer_clear_device_status(struct pci_dev *dev); +#else +static inline void pci_no_aer(void) { } +static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; } +static inline void pci_aer_exit(struct pci_dev *d) { } +static inline void pci_aer_clear_fatal_status(struct pci_dev *dev) { } +static inline void pci_aer_clear_device_status(struct pci_dev *dev) { } +#endif + #endif /* DRIVERS_PCI_H */ diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index a2e88386af28..4e823ae051a7 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -31,26 +31,9 @@ #include "portdrv.h" #define AER_ERROR_SOURCES_MAX 100 -#define AER_MAX_MULTI_ERR_DEVICES 5 /* Not likely to have more */ -struct aer_err_info { - struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES]; - int error_dev_num; - - unsigned int id:16; - - unsigned int severity:2; /* 0:NONFATAL | 1:FATAL | 2:COR */ - unsigned int __pad1:5; - unsigned int multi_error_valid:1; - - unsigned int first_error:5; - unsigned int __pad2:2; - unsigned int tlp_header_valid:1; - - unsigned int status; /* COR/UNCOR Error Status */ - unsigned int mask; /* COR/UNCOR Error Mask */ - struct aer_header_log_regs tlp; /* TLP Header */ -}; +#define AER_MAX_TYPEOF_COR_ERRS 16 /* as per PCI_ERR_COR_STATUS */ +#define AER_MAX_TYPEOF_UNCOR_ERRS 26 /* as per PCI_ERR_UNCOR_STATUS*/ struct aer_err_source { unsigned int status; @@ -76,6 +59,42 @@ struct aer_rpc { */ }; +/* AER stats for the device */ +struct aer_stats { + + /* + * Fields for all AER capable devices. They indicate the errors + * "as seen by this device". Note that this may mean that if an + * end point is causing problems, the AER counters may increment + * at its link partner (e.g. root port) because the errors will be + * "seen" by the link partner and not the the problematic end point + * itself (which may report all counters as 0 as it never saw any + * problems). + */ + /* Counters for different type of correctable errors */ + u64 dev_cor_errs[AER_MAX_TYPEOF_COR_ERRS]; + /* Counters for different type of fatal uncorrectable errors */ + u64 dev_fatal_errs[AER_MAX_TYPEOF_UNCOR_ERRS]; + /* Counters for different type of nonfatal uncorrectable errors */ + u64 dev_nonfatal_errs[AER_MAX_TYPEOF_UNCOR_ERRS]; + /* Total number of ERR_COR sent by this device */ + u64 dev_total_cor_errs; + /* Total number of ERR_FATAL sent by this device */ + u64 dev_total_fatal_errs; + /* Total number of ERR_NONFATAL sent by this device */ + u64 dev_total_nonfatal_errs; + + /* + * Fields for Root ports & root complex event collectors only, these + * indicate the total number of ERR_COR, ERR_FATAL, and ERR_NONFATAL + * messages received by the root port / event collector, INCLUDING the + * ones that are generated internally (by the rootport itself) + */ + u64 rootport_total_cor_errs; + u64 rootport_total_fatal_errs; + u64 rootport_total_nonfatal_errs; +}; + #define AER_LOG_TLP_MASKS (PCI_ERR_UNC_POISON_TLP| \ PCI_ERR_UNC_ECRC| \ PCI_ERR_UNC_UNSUP| \ @@ -303,12 +322,13 @@ int pcie_aer_get_firmware_first(struct pci_dev *dev) if (!pci_is_pcie(dev)) return 0; + if (pcie_ports_native) + return 0; + if (!dev->__aer_firmware_first_valid) aer_set_firmware_first(dev); return dev->__aer_firmware_first; } -#define PCI_EXP_AER_FLAGS (PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \ - PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE) static bool aer_firmware_first; @@ -323,6 +343,9 @@ bool aer_acpi_firmware_first(void) .firmware_first = 0, }; + if (pcie_ports_native) + return false; + if (!parsed) { apei_hest_parse(aer_hest_parse, &info); aer_firmware_first = info.firmware_first; @@ -357,16 +380,30 @@ int pci_disable_pcie_error_reporting(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting); +void pci_aer_clear_device_status(struct pci_dev *dev) +{ + u16 sta; + + pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &sta); + pcie_capability_write_word(dev, PCI_EXP_DEVSTA, sta); +} + int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) { int pos; - u32 status; + u32 status, sev; pos = dev->aer_cap; if (!pos) return -EIO; + if (pcie_aer_get_firmware_first(dev)) + return -EIO; + + /* Clear status bits for ERR_NONFATAL errors only */ pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status); + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev); + status &= ~sev; if (status) pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status); @@ -374,6 +411,26 @@ int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status); +void pci_aer_clear_fatal_status(struct pci_dev *dev) +{ + int pos; + u32 status, sev; + + pos = dev->aer_cap; + if (!pos) + return; + + if (pcie_aer_get_firmware_first(dev)) + return; + + /* Clear status bits for ERR_FATAL errors only */ + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status); + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev); + status &= sev; + if (status) + pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status); +} + int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) { int pos; @@ -387,6 +444,9 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) if (!pos) return -EIO; + if (pcie_aer_get_firmware_first(dev)) + return -EIO; + port_type = pci_pcie_type(dev); if (port_type == PCI_EXP_TYPE_ROOT_PORT) { pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &status); @@ -402,10 +462,20 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) return 0; } -int pci_aer_init(struct pci_dev *dev) +void pci_aer_init(struct pci_dev *dev) { dev->aer_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); - return pci_cleanup_aer_error_status_regs(dev); + + if (dev->aer_cap) + dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL); + + pci_cleanup_aer_error_status_regs(dev); +} + +void pci_aer_exit(struct pci_dev *dev) +{ + kfree(dev->aer_stats); + dev->aer_stats = NULL; } #define AER_AGENT_RECEIVER 0 @@ -458,52 +528,52 @@ static const char *aer_error_layer[] = { "Transaction Layer" }; -static const char *aer_correctable_error_string[] = { - "Receiver Error", /* Bit Position 0 */ +static const char *aer_correctable_error_string[AER_MAX_TYPEOF_COR_ERRS] = { + "RxErr", /* Bit Position 0 */ NULL, NULL, NULL, NULL, NULL, - "Bad TLP", /* Bit Position 6 */ - "Bad DLLP", /* Bit Position 7 */ - "RELAY_NUM Rollover", /* Bit Position 8 */ + "BadTLP", /* Bit Position 6 */ + "BadDLLP", /* Bit Position 7 */ + "Rollover", /* Bit Position 8 */ NULL, NULL, NULL, - "Replay Timer Timeout", /* Bit Position 12 */ - "Advisory Non-Fatal", /* Bit Position 13 */ - "Corrected Internal Error", /* Bit Position 14 */ - "Header Log Overflow", /* Bit Position 15 */ + "Timeout", /* Bit Position 12 */ + "NonFatalErr", /* Bit Position 13 */ + "CorrIntErr", /* Bit Position 14 */ + "HeaderOF", /* Bit Position 15 */ }; -static const char *aer_uncorrectable_error_string[] = { +static const char *aer_uncorrectable_error_string[AER_MAX_TYPEOF_UNCOR_ERRS] = { "Undefined", /* Bit Position 0 */ NULL, NULL, NULL, - "Data Link Protocol", /* Bit Position 4 */ - "Surprise Down Error", /* Bit Position 5 */ + "DLP", /* Bit Position 4 */ + "SDES", /* Bit Position 5 */ NULL, NULL, NULL, NULL, NULL, NULL, - "Poisoned TLP", /* Bit Position 12 */ - "Flow Control Protocol", /* Bit Position 13 */ - "Completion Timeout", /* Bit Position 14 */ - "Completer Abort", /* Bit Position 15 */ - "Unexpected Completion", /* Bit Position 16 */ - "Receiver Overflow", /* Bit Position 17 */ - "Malformed TLP", /* Bit Position 18 */ + "TLP", /* Bit Position 12 */ + "FCP", /* Bit Position 13 */ + "CmpltTO", /* Bit Position 14 */ + "CmpltAbrt", /* Bit Position 15 */ + "UnxCmplt", /* Bit Position 16 */ + "RxOF", /* Bit Position 17 */ + "MalfTLP", /* Bit Position 18 */ "ECRC", /* Bit Position 19 */ - "Unsupported Request", /* Bit Position 20 */ - "ACS Violation", /* Bit Position 21 */ - "Uncorrectable Internal Error", /* Bit Position 22 */ - "MC Blocked TLP", /* Bit Position 23 */ - "AtomicOp Egress Blocked", /* Bit Position 24 */ - "TLP Prefix Blocked Error", /* Bit Position 25 */ + "UnsupReq", /* Bit Position 20 */ + "ACSViol", /* Bit Position 21 */ + "UncorrIntErr", /* Bit Position 22 */ + "BlockedTLP", /* Bit Position 23 */ + "AtomicOpBlocked", /* Bit Position 24 */ + "TLPBlockedErr", /* Bit Position 25 */ }; static const char *aer_agent_string[] = { @@ -513,6 +583,144 @@ static const char *aer_agent_string[] = { "Transmitter ID" }; +#define aer_stats_dev_attr(name, stats_array, strings_array, \ + total_string, total_field) \ + static ssize_t \ + name##_show(struct device *dev, struct device_attribute *attr, \ + char *buf) \ +{ \ + unsigned int i; \ + char *str = buf; \ + struct pci_dev *pdev = to_pci_dev(dev); \ + u64 *stats = pdev->aer_stats->stats_array; \ + \ + for (i = 0; i < ARRAY_SIZE(strings_array); i++) { \ + if (strings_array[i]) \ + str += sprintf(str, "%s %llu\n", \ + strings_array[i], stats[i]); \ + else if (stats[i]) \ + str += sprintf(str, #stats_array "_bit[%d] %llu\n",\ + i, stats[i]); \ + } \ + str += sprintf(str, "TOTAL_%s %llu\n", total_string, \ + pdev->aer_stats->total_field); \ + return str-buf; \ +} \ +static DEVICE_ATTR_RO(name) + +aer_stats_dev_attr(aer_dev_correctable, dev_cor_errs, + aer_correctable_error_string, "ERR_COR", + dev_total_cor_errs); +aer_stats_dev_attr(aer_dev_fatal, dev_fatal_errs, + aer_uncorrectable_error_string, "ERR_FATAL", + dev_total_fatal_errs); +aer_stats_dev_attr(aer_dev_nonfatal, dev_nonfatal_errs, + aer_uncorrectable_error_string, "ERR_NONFATAL", + dev_total_nonfatal_errs); + +#define aer_stats_rootport_attr(name, field) \ + static ssize_t \ + name##_show(struct device *dev, struct device_attribute *attr, \ + char *buf) \ +{ \ + struct pci_dev *pdev = to_pci_dev(dev); \ + return sprintf(buf, "%llu\n", pdev->aer_stats->field); \ +} \ +static DEVICE_ATTR_RO(name) + +aer_stats_rootport_attr(aer_rootport_total_err_cor, + rootport_total_cor_errs); +aer_stats_rootport_attr(aer_rootport_total_err_fatal, + rootport_total_fatal_errs); +aer_stats_rootport_attr(aer_rootport_total_err_nonfatal, + rootport_total_nonfatal_errs); + +static struct attribute *aer_stats_attrs[] __ro_after_init = { + &dev_attr_aer_dev_correctable.attr, + &dev_attr_aer_dev_fatal.attr, + &dev_attr_aer_dev_nonfatal.attr, + &dev_attr_aer_rootport_total_err_cor.attr, + &dev_attr_aer_rootport_total_err_fatal.attr, + &dev_attr_aer_rootport_total_err_nonfatal.attr, + NULL +}; + +static umode_t aer_stats_attrs_are_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct pci_dev *pdev = to_pci_dev(dev); + + if (!pdev->aer_stats) + return 0; + + if ((a == &dev_attr_aer_rootport_total_err_cor.attr || + a == &dev_attr_aer_rootport_total_err_fatal.attr || + a == &dev_attr_aer_rootport_total_err_nonfatal.attr) && + pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT) + return 0; + + return a->mode; +} + +const struct attribute_group aer_stats_attr_group = { + .attrs = aer_stats_attrs, + .is_visible = aer_stats_attrs_are_visible, +}; + +static void pci_dev_aer_stats_incr(struct pci_dev *pdev, + struct aer_err_info *info) +{ + int status, i, max = -1; + u64 *counter = NULL; + struct aer_stats *aer_stats = pdev->aer_stats; + + if (!aer_stats) + return; + + switch (info->severity) { + case AER_CORRECTABLE: + aer_stats->dev_total_cor_errs++; + counter = &aer_stats->dev_cor_errs[0]; + max = AER_MAX_TYPEOF_COR_ERRS; + break; + case AER_NONFATAL: + aer_stats->dev_total_nonfatal_errs++; + counter = &aer_stats->dev_nonfatal_errs[0]; + max = AER_MAX_TYPEOF_UNCOR_ERRS; + break; + case AER_FATAL: + aer_stats->dev_total_fatal_errs++; + counter = &aer_stats->dev_fatal_errs[0]; + max = AER_MAX_TYPEOF_UNCOR_ERRS; + break; + } + + status = (info->status & ~info->mask); + for (i = 0; i < max; i++) + if (status & (1 << i)) + counter[i]++; +} + +static void pci_rootport_aer_stats_incr(struct pci_dev *pdev, + struct aer_err_source *e_src) +{ + struct aer_stats *aer_stats = pdev->aer_stats; + + if (!aer_stats) + return; + + if (e_src->status & PCI_ERR_ROOT_COR_RCV) + aer_stats->rootport_total_cor_errs++; + + if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) { + if (e_src->status & PCI_ERR_ROOT_FATAL_RCV) + aer_stats->rootport_total_fatal_errs++; + else + aer_stats->rootport_total_nonfatal_errs++; + } +} + static void __print_tlp_header(struct pci_dev *dev, struct aer_header_log_regs *t) { @@ -545,9 +753,10 @@ static void __aer_print_error(struct pci_dev *dev, pci_err(dev, " [%2d] Unknown Error Bit%s\n", i, info->first_error == i ? " (First)" : ""); } + pci_dev_aer_stats_incr(dev, info); } -static void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) +void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) { int layer, agent; int id = ((dev->bus->number << 8) | dev->devfn); @@ -799,6 +1008,7 @@ static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info) if (pos) pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS, info->status); + pci_aer_clear_device_status(dev); } else if (info->severity == AER_NONFATAL) pcie_do_nonfatal_recovery(dev); else if (info->severity == AER_FATAL) @@ -876,7 +1086,7 @@ EXPORT_SYMBOL_GPL(aer_recover_queue); #endif /** - * get_device_error_info - read error status from dev and store it to info + * aer_get_device_error_info - read error status from dev and store it to info * @dev: pointer to the device expected to have a error record * @info: pointer to structure to store the error record * @@ -884,7 +1094,7 @@ EXPORT_SYMBOL_GPL(aer_recover_queue); * * Note that @info is reused among all error devices. Clear fields properly. */ -static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) +int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) { int pos, temp; @@ -942,11 +1152,11 @@ static inline void aer_process_err_devices(struct aer_err_info *e_info) /* Report all before handle them, not to lost records by reset etc. */ for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) { - if (get_device_error_info(e_info->dev[i], e_info)) + if (aer_get_device_error_info(e_info->dev[i], e_info)) aer_print_error(e_info->dev[i], e_info); } for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) { - if (get_device_error_info(e_info->dev[i], e_info)) + if (aer_get_device_error_info(e_info->dev[i], e_info)) handle_error_source(e_info->dev[i], e_info); } } @@ -962,6 +1172,8 @@ static void aer_isr_one_error(struct aer_rpc *rpc, struct pci_dev *pdev = rpc->rpd; struct aer_err_info *e_info = &rpc->e_info; + pci_rootport_aer_stats_incr(pdev, e_src); + /* * There is a possibility that both correctable error and * uncorrectable error being logged. Report correctable error first. @@ -1336,20 +1548,8 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev) */ static void aer_error_resume(struct pci_dev *dev) { - int pos; - u32 status, mask; - u16 reg16; - - /* Clean up Root device status */ - pcie_capability_read_word(dev, PCI_EXP_DEVSTA, ®16); - pcie_capability_write_word(dev, PCI_EXP_DEVSTA, reg16); - - /* Clean AER Root Error Status */ - pos = dev->aer_cap; - pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status); - pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &mask); - status &= ~mask; /* Clear corresponding nonfatal bits */ - pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status); + pci_aer_clear_device_status(dev); + pci_cleanup_aer_uncorrect_error_status(dev); } static struct pcie_port_service_driver aerdriver = { diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index f7ce0cb0b0b7..674984a9277a 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -252,6 +252,7 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev, dev->error_state = state; pci_walk_bus(dev->subordinate, cb, &result_data); if (cb == report_resume) { + pci_aer_clear_device_status(dev); pci_cleanup_aer_uncorrect_error_status(dev); dev->error_state = pci_channel_io_normal; } @@ -259,15 +260,10 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev, /* * If the error is reported by an end point, we think this * error is related to the upstream link of the end point. + * The error is non fatal so the bus is ok; just invoke + * the callback for the function that logged the error. */ - if (state == pci_channel_io_normal) - /* - * the error is non fatal so the bus is ok, just invoke - * the callback for the function that logged the error. - */ - cb(dev, &result_data); - else - pci_walk_bus(dev->bus, cb, &result_data); + cb(dev, &result_data); } return result_data.result; @@ -295,6 +291,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service) parent = udev->subordinate; pci_lock_rescan_remove(); + pci_dev_get(dev); list_for_each_entry_safe_reverse(pdev, temp, &parent->devices, bus_list) { pci_dev_get(pdev); @@ -316,7 +313,8 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service) * do error recovery on all subordinates of the bridge instead * of the bridge and clear the error status of the bridge. */ - pci_cleanup_aer_uncorrect_error_status(dev); + pci_aer_clear_fatal_status(dev); + pci_aer_clear_device_status(dev); } if (result == PCI_ERS_RESULT_RECOVERED) { @@ -328,6 +326,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service) pci_info(dev, "Device recovery from fatal error failed\n"); } + pci_dev_put(dev); pci_unlock_rescan_remove(); } diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c index 973f1b80a038..b78840f54a9b 100644 --- a/drivers/pci/pcie/portdrv_pci.c +++ b/drivers/pci/pcie/portdrv_pci.c @@ -42,17 +42,6 @@ __setup("pcie_ports=", pcie_port_setup); /* global data */ -static int pcie_portdrv_restore_config(struct pci_dev *dev) -{ - int retval; - - retval = pci_enable_device(dev); - if (retval) - return retval; - pci_set_master(dev); - return 0; -} - #ifdef CONFIG_PM static int pcie_port_runtime_suspend(struct device *dev) { @@ -160,19 +149,6 @@ static pci_ers_result_t pcie_portdrv_mmio_enabled(struct pci_dev *dev) return PCI_ERS_RESULT_RECOVERED; } -static pci_ers_result_t pcie_portdrv_slot_reset(struct pci_dev *dev) -{ - /* If fatal, restore cfg space for possible link reset at upstream */ - if (dev->error_state == pci_channel_io_frozen) { - dev->state_saved = true; - pci_restore_state(dev); - pcie_portdrv_restore_config(dev); - pci_enable_pcie_error_reporting(dev); - } - - return PCI_ERS_RESULT_RECOVERED; -} - static int resume_iter(struct device *device, void *data) { struct pcie_device *pcie_device; @@ -208,7 +184,6 @@ static const struct pci_device_id port_pci_ids[] = { { static const struct pci_error_handlers pcie_portdrv_err_handler = { .error_detected = pcie_portdrv_error_detected, .mmio_enabled = pcie_portdrv_mmio_enabled, - .slot_reset = pcie_portdrv_slot_reset, .resume = pcie_portdrv_err_resume, }; diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 1ed2852dee21..155d4333a291 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2063,6 +2063,7 @@ static void pci_configure_device(struct pci_dev *dev) static void pci_release_capabilities(struct pci_dev *dev) { + pci_aer_exit(dev); pci_vpd_release(dev); pci_iov_release(dev); pci_free_cap_save_buffers(dev); @@ -2432,13 +2433,13 @@ int pci_scan_slot(struct pci_bus *bus, int devfn) dev = pci_scan_single_device(bus, devfn); if (!dev) return 0; - if (!dev->is_added) + if (!pci_dev_is_added(dev)) nr++; for (fn = next_fn(bus, dev, 0); fn > 0; fn = next_fn(bus, dev, fn)) { dev = pci_scan_single_device(bus, devfn + fn); if (dev) { - if (!dev->is_added) + if (!pci_dev_is_added(dev)) nr++; dev->multifunction = 1; } diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 01ec7fcb5634..461e7fd2756f 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -18,11 +18,12 @@ static void pci_stop_dev(struct pci_dev *dev) { pci_pme_active(dev, false); - if (dev->is_added) { + if (pci_dev_is_added(dev)) { device_release_driver(&dev->dev); pci_proc_detach_device(dev); pci_remove_sysfs_dev_files(dev); - dev->is_added = 0; + + pci_dev_assign_added(dev, false); } if (dev->bus->self) diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..d78f46f070c2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -299,6 +299,7 @@ struct pci_dev { u8 hdr_type; /* PCI header type (`multi' flag masked out) */ #ifdef CONFIG_PCIEAER u16 aer_cap; /* AER capability offset */ + struct aer_stats *aer_stats; /* AER stats for this device */ #endif u8 pcie_cap; /* PCIe capability offset */ u8 msi_cap; /* MSI capability offset */ @@ -368,7 +369,6 @@ struct pci_dev { unsigned int transparent:1; /* Subtractive decode bridge */ unsigned int multifunction:1; /* Multi-function device */ - unsigned int is_added:1; unsigned int is_busmaster:1; /* Is busmaster */ unsigned int no_msi:1; /* May not use MSI */ unsigned int no_64bit_msi:1; /* May only use 32-bit MSIs */ @@ -1240,6 +1240,8 @@ int pci_register_io_range(struct fwnode_handle *fwnode, phys_addr_t addr, unsigned long pci_address_to_pio(phys_addr_t addr); phys_addr_t pci_pio_to_address(unsigned long pio); int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr); +int devm_pci_remap_iospace(struct device *dev, const struct resource *res, + phys_addr_t phys_addr); void pci_unmap_iospace(struct resource *res); void __iomem *devm_pci_remap_cfgspace(struct device *dev, resource_size_t offset, @@ -1468,13 +1470,9 @@ static inline bool pcie_aspm_support_enabled(void) { return false; } #endif #ifdef CONFIG_PCIEAER -void pci_no_aer(void); bool pci_aer_available(void); -int pci_aer_init(struct pci_dev *dev); #else -static inline void pci_no_aer(void) { } static inline bool pci_aer_available(void) { return false; } -static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; } #endif #ifdef CONFIG_PCIE_ECRC |