summaryrefslogtreecommitdiffstats
path: root/drivers/pci
diff options
context:
space:
mode:
authorBjorn Helgaas <bhelgaas@google.com>2018-06-11 08:14:42 -0500
committerBjorn Helgaas <helgaas@kernel.org>2018-06-11 08:14:42 -0500
commitce4c7b241227ed49c0b6f0f1867653e1ee0007ef (patch)
treee6138151a93ccd0c78681fd4c8203df44f5fc1e5 /drivers/pci
parent3b3191df4e7cff160e2e693b7a78c2fc43634d64 (diff)
parent0b15f1e38f639a322213ebdc8b752300138edd0b (diff)
Merge branch 'pci/aer-squash'
- squash AER directory into drivers/pci/pcie/aer.c (Bjorn Helgaas) * pci/aer-squash: PCI/AER: Use "PCI Express" consistently in Kconfig text PCI/AER: Hoist aerdrv.c, aer_inject.c up to drivers/pci/pcie/ PCI/AER: Squash Kconfig.debug into Kconfig PCI/AER: Move private AER things to aerdrv.c PCI/AER: Move aer_irq() declaration to portdrv.h PCI/AER: Move pcie_aer_get_firmware_first() to portdrv.h PCI/AER: Remove duplicate pcie_port_bus_type declaration PCI/AER: Squash ecrc.c into aerdrv.c PCI/AER: Squash aerdrv_acpi.c into aerdrv.c PCI/AER: Squash aerdrv_errprint.c into aerdrv.c PCI/AER: Squash aerdrv_core.c into aerdrv.c PCI/AER: Reorder code to group probe/remove stuff together PCI/AER: Remove forward declarations
Diffstat (limited to 'drivers/pci')
-rw-r--r--drivers/pci/pcie/Kconfig41
-rw-r--r--drivers/pci/pcie/Makefile3
-rw-r--r--drivers/pci/pcie/aer.c1377
-rw-r--r--drivers/pci/pcie/aer/Kconfig29
-rw-r--r--drivers/pci/pcie/aer/Kconfig.debug19
-rw-r--r--drivers/pci/pcie/aer/Makefile13
-rw-r--r--drivers/pci/pcie/aer/aerdrv.c371
-rw-r--r--drivers/pci/pcie/aer/aerdrv.h95
-rw-r--r--drivers/pci/pcie/aer/aerdrv_acpi.c141
-rw-r--r--drivers/pci/pcie/aer/aerdrv_core.c496
-rw-r--r--drivers/pci/pcie/aer/aerdrv_errprint.c260
-rw-r--r--drivers/pci/pcie/aer/ecrc.c117
-rw-r--r--drivers/pci/pcie/aer_inject.c (renamed from drivers/pci/pcie/aer/aer_inject.c)3
-rw-r--r--drivers/pci/pcie/dpc.c1
-rw-r--r--drivers/pci/pcie/portdrv.h15
15 files changed, 1434 insertions, 1547 deletions
diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig
index b12e28b3d8f9..0a1e9d379bc5 100644
--- a/drivers/pci/pcie/Kconfig
+++ b/drivers/pci/pcie/Kconfig
@@ -23,7 +23,42 @@ config HOTPLUG_PCI_PCIE
When in doubt, say N.
-source "drivers/pci/pcie/aer/Kconfig"
+config PCIEAER
+ bool "PCI Express Advanced Error Reporting support"
+ depends on PCIEPORTBUS
+ select RAS
+ default y
+ help
+ This enables PCI Express Root Port Advanced Error Reporting
+ (AER) driver support. Error reporting messages sent to Root
+ Port will be handled by PCI Express AER driver.
+
+config PCIEAER_INJECT
+ tristate "PCI Express error injection support"
+ depends on PCIEAER
+ default n
+ help
+ This enables PCI Express Root Port Advanced Error Reporting
+ (AER) software error injector.
+
+ Debugging AER code is quite difficult because it is hard
+ to trigger various real hardware errors. Software-based
+ error injection can fake almost all kinds of errors with the
+ help of a user space helper tool aer-inject, which can be
+ gotten from:
+ http://www.kernel.org/pub/linux/utils/pci/aer-inject/
+
+#
+# PCI Express ECRC
+#
+config PCIE_ECRC
+ bool "PCI Express ECRC settings control"
+ depends on PCIEAER
+ help
+ Used to override firmware/bios settings for PCI Express ECRC
+ (transaction layer end-to-end CRC checking).
+
+ When in doubt, say N.
#
# PCI Express ASPM
@@ -92,7 +127,7 @@ config PCIE_PME
depends on PCIEPORTBUS && PM
config PCIE_DPC
- bool "PCIe Downstream Port Containment support"
+ bool "PCI Express Downstream Port Containment support"
depends on PCIEPORTBUS && PCIEAER
default n
help
@@ -103,7 +138,7 @@ config PCIE_DPC
it is safe to answer N.
config PCIE_PTM
- bool "PCIe Precision Time Measurement support"
+ bool "PCI Express Precision Time Measurement support"
default n
depends on PCIEPORTBUS
help
diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile
index 03f4e0b3a140..ab514083d5d4 100644
--- a/drivers/pci/pcie/Makefile
+++ b/drivers/pci/pcie/Makefile
@@ -7,7 +7,8 @@ pcieportdrv-y := portdrv_core.o portdrv_pci.o err.o
obj-$(CONFIG_PCIEPORTBUS) += pcieportdrv.o
obj-$(CONFIG_PCIEASPM) += aspm.o
-obj-$(CONFIG_PCIEAER) += aer/
+obj-$(CONFIG_PCIEAER) += aer.o
+obj-$(CONFIG_PCIEAER_INJECT) += aer_inject.o
obj-$(CONFIG_PCIE_PME) += pme.o
obj-$(CONFIG_PCIE_DPC) += dpc.o
obj-$(CONFIG_PCIE_PTM) += ptm.o
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
new file mode 100644
index 000000000000..a2e88386af28
--- /dev/null
+++ b/drivers/pci/pcie/aer.c
@@ -0,0 +1,1377 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Implement the AER root port service driver. The driver registers an IRQ
+ * handler. When a root port triggers an AER interrupt, the IRQ handler
+ * collects root port status and schedules work.
+ *
+ * Copyright (C) 2006 Intel Corp.
+ * Tom Long Nguyen (tom.l.nguyen@intel.com)
+ * Zhang Yanmin (yanmin.zhang@intel.com)
+ *
+ * (C) Copyright 2009 Hewlett-Packard Development Company, L.P.
+ * Andrew Patterson <andrew.patterson@hp.com>
+ */
+
+#include <linux/cper.h>
+#include <linux/pci.h>
+#include <linux/pci-acpi.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/kfifo.h>
+#include <linux/slab.h>
+#include <acpi/apei.h>
+#include <ras/ras_event.h>
+
+#include "../pci.h"
+#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 */
+};
+
+struct aer_err_source {
+ unsigned int status;
+ unsigned int id;
+};
+
+struct aer_rpc {
+ struct pci_dev *rpd; /* Root Port device */
+ struct work_struct dpc_handler;
+ struct aer_err_source e_sources[AER_ERROR_SOURCES_MAX];
+ struct aer_err_info e_info;
+ unsigned short prod_idx; /* Error Producer Index */
+ unsigned short cons_idx; /* Error Consumer Index */
+ int isr;
+ spinlock_t e_lock; /*
+ * Lock access to Error Status/ID Regs
+ * and error producer/consumer index
+ */
+ struct mutex rpc_mutex; /*
+ * only one thread could do
+ * recovery on the same
+ * root port hierarchy
+ */
+};
+
+#define AER_LOG_TLP_MASKS (PCI_ERR_UNC_POISON_TLP| \
+ PCI_ERR_UNC_ECRC| \
+ PCI_ERR_UNC_UNSUP| \
+ PCI_ERR_UNC_COMP_ABORT| \
+ PCI_ERR_UNC_UNX_COMP| \
+ PCI_ERR_UNC_MALF_TLP)
+
+#define SYSTEM_ERROR_INTR_ON_MESG_MASK (PCI_EXP_RTCTL_SECEE| \
+ PCI_EXP_RTCTL_SENFEE| \
+ PCI_EXP_RTCTL_SEFEE)
+#define ROOT_PORT_INTR_ON_MESG_MASK (PCI_ERR_ROOT_CMD_COR_EN| \
+ PCI_ERR_ROOT_CMD_NONFATAL_EN| \
+ PCI_ERR_ROOT_CMD_FATAL_EN)
+#define ERR_COR_ID(d) (d & 0xffff)
+#define ERR_UNCOR_ID(d) (d >> 16)
+
+static int pcie_aer_disable;
+
+void pci_no_aer(void)
+{
+ pcie_aer_disable = 1;
+}
+
+bool pci_aer_available(void)
+{
+ return !pcie_aer_disable && pci_msi_enabled();
+}
+
+#ifdef CONFIG_PCIE_ECRC
+
+#define ECRC_POLICY_DEFAULT 0 /* ECRC set by BIOS */
+#define ECRC_POLICY_OFF 1 /* ECRC off for performance */
+#define ECRC_POLICY_ON 2 /* ECRC on for data integrity */
+
+static int ecrc_policy = ECRC_POLICY_DEFAULT;
+
+static const char *ecrc_policy_str[] = {
+ [ECRC_POLICY_DEFAULT] = "bios",
+ [ECRC_POLICY_OFF] = "off",
+ [ECRC_POLICY_ON] = "on"
+};
+
+/**
+ * enable_ercr_checking - enable PCIe ECRC checking for a device
+ * @dev: the PCI device
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+static int enable_ecrc_checking(struct pci_dev *dev)
+{
+ int pos;
+ u32 reg32;
+
+ if (!pci_is_pcie(dev))
+ return -ENODEV;
+
+ pos = dev->aer_cap;
+ if (!pos)
+ return -ENODEV;
+
+ pci_read_config_dword(dev, pos + PCI_ERR_CAP, &reg32);
+ if (reg32 & PCI_ERR_CAP_ECRC_GENC)
+ reg32 |= PCI_ERR_CAP_ECRC_GENE;
+ if (reg32 & PCI_ERR_CAP_ECRC_CHKC)
+ reg32 |= PCI_ERR_CAP_ECRC_CHKE;
+ pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32);
+
+ return 0;
+}
+
+/**
+ * disable_ercr_checking - disables PCIe ECRC checking for a device
+ * @dev: the PCI device
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+static int disable_ecrc_checking(struct pci_dev *dev)
+{
+ int pos;
+ u32 reg32;
+
+ if (!pci_is_pcie(dev))
+ return -ENODEV;
+
+ pos = dev->aer_cap;
+ if (!pos)
+ return -ENODEV;
+
+ pci_read_config_dword(dev, pos + PCI_ERR_CAP, &reg32);
+ reg32 &= ~(PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE);
+ pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32);
+
+ return 0;
+}
+
+/**
+ * pcie_set_ecrc_checking - set/unset PCIe ECRC checking for a device based on global policy
+ * @dev: the PCI device
+ */
+void pcie_set_ecrc_checking(struct pci_dev *dev)
+{
+ switch (ecrc_policy) {
+ case ECRC_POLICY_DEFAULT:
+ return;
+ case ECRC_POLICY_OFF:
+ disable_ecrc_checking(dev);
+ break;
+ case ECRC_POLICY_ON:
+ enable_ecrc_checking(dev);
+ break;
+ default:
+ return;
+ }
+}
+
+/**
+ * pcie_ecrc_get_policy - parse kernel command-line ecrc option
+ */
+void pcie_ecrc_get_policy(char *str)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(ecrc_policy_str); i++)
+ if (!strncmp(str, ecrc_policy_str[i],
+ strlen(ecrc_policy_str[i])))
+ break;
+ if (i >= ARRAY_SIZE(ecrc_policy_str))
+ return;
+
+ ecrc_policy = i;
+}
+#endif /* CONFIG_PCIE_ECRC */
+
+#ifdef CONFIG_ACPI_APEI
+static inline int hest_match_pci(struct acpi_hest_aer_common *p,
+ struct pci_dev *pci)
+{
+ return ACPI_HEST_SEGMENT(p->bus) == pci_domain_nr(pci->bus) &&
+ ACPI_HEST_BUS(p->bus) == pci->bus->number &&
+ p->device == PCI_SLOT(pci->devfn) &&
+ p->function == PCI_FUNC(pci->devfn);
+}
+
+static inline bool hest_match_type(struct acpi_hest_header *hest_hdr,
+ struct pci_dev *dev)
+{
+ u16 hest_type = hest_hdr->type;
+ u8 pcie_type = pci_pcie_type(dev);
+
+ if ((hest_type == ACPI_HEST_TYPE_AER_ROOT_PORT &&
+ pcie_type == PCI_EXP_TYPE_ROOT_PORT) ||
+ (hest_type == ACPI_HEST_TYPE_AER_ENDPOINT &&
+ pcie_type == PCI_EXP_TYPE_ENDPOINT) ||
+ (hest_type == ACPI_HEST_TYPE_AER_BRIDGE &&
+ (dev->class >> 16) == PCI_BASE_CLASS_BRIDGE))
+ return true;
+ return false;
+}
+
+struct aer_hest_parse_info {
+ struct pci_dev *pci_dev;
+ int firmware_first;
+};
+
+static int hest_source_is_pcie_aer(struct acpi_hest_header *hest_hdr)
+{
+ if (hest_hdr->type == ACPI_HEST_TYPE_AER_ROOT_PORT ||
+ hest_hdr->type == ACPI_HEST_TYPE_AER_ENDPOINT ||
+ hest_hdr->type == ACPI_HEST_TYPE_AER_BRIDGE)
+ return 1;
+ return 0;
+}
+
+static int aer_hest_parse(struct acpi_hest_header *hest_hdr, void *data)
+{
+ struct aer_hest_parse_info *info = data;
+ struct acpi_hest_aer_common *p;
+ int ff;
+
+ if (!hest_source_is_pcie_aer(hest_hdr))
+ return 0;
+
+ p = (struct acpi_hest_aer_common *)(hest_hdr + 1);
+ ff = !!(p->flags & ACPI_HEST_FIRMWARE_FIRST);
+
+ /*
+ * If no specific device is supplied, determine whether
+ * FIRMWARE_FIRST is set for *any* PCIe device.
+ */
+ if (!info->pci_dev) {
+ info->firmware_first |= ff;
+ return 0;
+ }
+
+ /* Otherwise, check the specific device */
+ if (p->flags & ACPI_HEST_GLOBAL) {
+ if (hest_match_type(hest_hdr, info->pci_dev))
+ info->firmware_first = ff;
+ } else
+ if (hest_match_pci(p, info->pci_dev))
+ info->firmware_first = ff;
+
+ return 0;
+}
+
+static void aer_set_firmware_first(struct pci_dev *pci_dev)
+{
+ int rc;
+ struct aer_hest_parse_info info = {
+ .pci_dev = pci_dev,
+ .firmware_first = 0,
+ };
+
+ rc = apei_hest_parse(aer_hest_parse, &info);
+
+ if (rc)
+ pci_dev->__aer_firmware_first = 0;
+ else
+ pci_dev->__aer_firmware_first = info.firmware_first;
+ pci_dev->__aer_firmware_first_valid = 1;
+}
+
+int pcie_aer_get_firmware_first(struct pci_dev *dev)
+{
+ if (!pci_is_pcie(dev))
+ 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;
+
+/**
+ * aer_acpi_firmware_first - Check if APEI should control AER.
+ */
+bool aer_acpi_firmware_first(void)
+{
+ static bool parsed = false;
+ struct aer_hest_parse_info info = {
+ .pci_dev = NULL, /* Check all PCIe devices */
+ .firmware_first = 0,
+ };
+
+ if (!parsed) {
+ apei_hest_parse(aer_hest_parse, &info);
+ aer_firmware_first = info.firmware_first;
+ parsed = true;
+ }
+ return aer_firmware_first;
+}
+#endif
+
+#define PCI_EXP_AER_FLAGS (PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \
+ PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE)
+
+int pci_enable_pcie_error_reporting(struct pci_dev *dev)
+{
+ if (pcie_aer_get_firmware_first(dev))
+ return -EIO;
+
+ if (!dev->aer_cap)
+ return -EIO;
+
+ return pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_AER_FLAGS);
+}
+EXPORT_SYMBOL_GPL(pci_enable_pcie_error_reporting);
+
+int pci_disable_pcie_error_reporting(struct pci_dev *dev)
+{
+ if (pcie_aer_get_firmware_first(dev))
+ return -EIO;
+
+ return pcie_capability_clear_word(dev, PCI_EXP_DEVCTL,
+ PCI_EXP_AER_FLAGS);
+}
+EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting);
+
+int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
+{
+ int pos;
+ u32 status;
+
+ pos = dev->aer_cap;
+ if (!pos)
+ return -EIO;
+
+ pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+ if (status)
+ pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status);
+
+int pci_cleanup_aer_error_status_regs(struct pci_dev *dev)
+{
+ int pos;
+ u32 status;
+ int port_type;
+
+ if (!pci_is_pcie(dev))
+ return -ENODEV;
+
+ pos = dev->aer_cap;
+ if (!pos)
+ 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);
+ pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, status);
+ }
+
+ pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS, &status);
+ pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS, status);
+
+ pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+ pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
+
+ return 0;
+}
+
+int 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);
+}
+
+#define AER_AGENT_RECEIVER 0
+#define AER_AGENT_REQUESTER 1
+#define AER_AGENT_COMPLETER 2
+#define AER_AGENT_TRANSMITTER 3
+
+#define AER_AGENT_REQUESTER_MASK(t) ((t == AER_CORRECTABLE) ? \
+ 0 : (PCI_ERR_UNC_COMP_TIME|PCI_ERR_UNC_UNSUP))
+#define AER_AGENT_COMPLETER_MASK(t) ((t == AER_CORRECTABLE) ? \
+ 0 : PCI_ERR_UNC_COMP_ABORT)
+#define AER_AGENT_TRANSMITTER_MASK(t) ((t == AER_CORRECTABLE) ? \
+ (PCI_ERR_COR_REP_ROLL|PCI_ERR_COR_REP_TIMER) : 0)
+
+#define AER_GET_AGENT(t, e) \
+ ((e & AER_AGENT_COMPLETER_MASK(t)) ? AER_AGENT_COMPLETER : \
+ (e & AER_AGENT_REQUESTER_MASK(t)) ? AER_AGENT_REQUESTER : \
+ (e & AER_AGENT_TRANSMITTER_MASK(t)) ? AER_AGENT_TRANSMITTER : \
+ AER_AGENT_RECEIVER)
+
+#define AER_PHYSICAL_LAYER_ERROR 0
+#define AER_DATA_LINK_LAYER_ERROR 1
+#define AER_TRANSACTION_LAYER_ERROR 2
+
+#define AER_PHYSICAL_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ? \
+ PCI_ERR_COR_RCVR : 0)
+#define AER_DATA_LINK_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ? \
+ (PCI_ERR_COR_BAD_TLP| \
+ PCI_ERR_COR_BAD_DLLP| \
+ PCI_ERR_COR_REP_ROLL| \
+ PCI_ERR_COR_REP_TIMER) : PCI_ERR_UNC_DLP)
+
+#define AER_GET_LAYER_ERROR(t, e) \
+ ((e & AER_PHYSICAL_LAYER_ERROR_MASK(t)) ? AER_PHYSICAL_LAYER_ERROR : \
+ (e & AER_DATA_LINK_LAYER_ERROR_MASK(t)) ? AER_DATA_LINK_LAYER_ERROR : \
+ AER_TRANSACTION_LAYER_ERROR)
+
+/*
+ * AER error strings
+ */
+static const char *aer_error_severity_string[] = {
+ "Uncorrected (Non-Fatal)",
+ "Uncorrected (Fatal)",
+ "Corrected"
+};
+
+static const char *aer_error_layer[] = {
+ "Physical Layer",
+ "Data Link Layer",
+ "Transaction Layer"
+};
+
+static const char *aer_correctable_error_string[] = {
+ "Receiver Error", /* Bit Position 0 */
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ "Bad TLP", /* Bit Position 6 */
+ "Bad DLLP", /* Bit Position 7 */
+ "RELAY_NUM 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 */
+};
+
+static const char *aer_uncorrectable_error_string[] = {
+ "Undefined", /* Bit Position 0 */
+ NULL,
+ NULL,
+ NULL,
+ "Data Link Protocol", /* Bit Position 4 */
+ "Surprise Down Error", /* 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 */
+ "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 */
+};
+
+static const char *aer_agent_string[] = {
+ "Receiver ID",
+ "Requester ID",
+ "Completer ID",
+ "Transmitter ID"
+};
+
+static void __print_tlp_header(struct pci_dev *dev,
+ struct aer_header_log_regs *t)
+{
+ pci_err(dev, " TLP Header: %08x %08x %08x %08x\n",
+ t->dw0, t->dw1, t->dw2, t->dw3);
+}
+
+static void __aer_print_error(struct pci_dev *dev,
+ struct aer_err_info *info)
+{
+ int i, status;
+ const char *errmsg = NULL;
+ status = (info->status & ~info->mask);
+
+ for (i = 0; i < 32; i++) {
+ if (!(status & (1 << i)))
+ continue;
+
+ if (info->severity == AER_CORRECTABLE)
+ errmsg = i < ARRAY_SIZE(aer_correctable_error_string) ?
+ aer_correctable_error_string[i] : NULL;
+ else
+ errmsg = i < ARRAY_SIZE(aer_uncorrectable_error_string) ?
+ aer_uncorrectable_error_string[i] : NULL;
+
+ if (errmsg)
+ pci_err(dev, " [%2d] %-22s%s\n", i, errmsg,
+ info->first_error == i ? " (First)" : "");
+ else
+ pci_err(dev, " [%2d] Unknown Error Bit%s\n",
+ i, info->first_error == i ? " (First)" : "");
+ }
+}
+
+static void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
+{
+ int layer, agent;
+ int id = ((dev->bus->number << 8) | dev->devfn);
+
+ if (!info->status) {
+ pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
+ aer_error_severity_string[info->severity]);
+ goto out;
+ }
+
+ layer = AER_GET_LAYER_ERROR(info->severity, info->status);
+ agent = AER_GET_AGENT(info->severity, info->status);
+
+ pci_err(dev, "PCIe Bus Error: severity=%s, type=%s, (%s)\n",
+ aer_error_severity_string[info->severity],
+ aer_error_layer[layer], aer_agent_string[agent]);
+
+ pci_err(dev, " device [%04x:%04x] error status/mask=%08x/%08x\n",
+ dev->vendor, dev->device,
+ info->status, info->mask);
+
+ __aer_print_error(dev, info);
+
+ if (info->tlp_header_valid)
+ __print_tlp_header(dev, &info->tlp);
+
+out:
+ if (info->id && info->error_dev_num > 1 && info->id == id)
+ pci_err(dev, " Error of this Agent is reported first\n");
+
+ trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
+ info->severity, info->tlp_header_valid, &info->tlp);
+}
+
+static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
+{
+ u8 bus = info->id >> 8;
+ u8 devfn = info->id & 0xff;
+
+ pci_info(dev, "AER: %s%s error received: %04x:%02x:%02x.%d\n",
+ info->multi_error_valid ? "Multiple " : "",
+ aer_error_severity_string[info->severity],
+ pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+}
+
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+int cper_severity_to_aer(int cper_severity)
+{
+ switch (cper_severity) {
+ case CPER_SEV_RECOVERABLE:
+ return AER_NONFATAL;
+ case CPER_SEV_FATAL:
+ return AER_FATAL;
+ default:
+ return AER_CORRECTABLE;
+ }
+}
+EXPORT_SYMBOL_GPL(cper_severity_to_aer);
+
+void cper_print_aer(struct pci_dev *dev, int aer_severity,
+ struct aer_capability_regs *aer)
+{
+ int layer, agent, tlp_header_valid = 0;
+ u32 status, mask;
+ struct aer_err_info info;
+
+ if (aer_severity == AER_CORRECTABLE) {
+ status = aer->cor_status;
+ mask = aer->cor_mask;
+ } else {
+ status = aer->uncor_status;
+ mask = aer->uncor_mask;
+ tlp_header_valid = status & AER_LOG_TLP_MASKS;
+ }
+
+ layer = AER_GET_LAYER_ERROR(aer_severity, status);
+ agent = AER_GET_AGENT(aer_severity, status);
+
+ memset(&info, 0, sizeof(info));
+ info.severity = aer_severity;
+ info.status = status;
+ info.mask = mask;
+ info.first_error = PCI_ERR_CAP_FEP(aer->cap_control);
+
+ pci_err(dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", status, mask);
+ __aer_print_error(dev, &info);
+ pci_err(dev, "aer_layer=%s, aer_agent=%s\n",
+ aer_error_layer[layer], aer_agent_string[agent]);
+
+ if (aer_severity != AER_CORRECTABLE)
+ pci_err(dev, "aer_uncor_severity: 0x%08x\n",
+ aer->uncor_severity);
+
+ if (tlp_header_valid)
+ __print_tlp_header(dev, &aer->header_log);
+
+ trace_aer_event(dev_name(&dev->dev), (status & ~mask),
+ aer_severity, tlp_header_valid, &aer->header_log);
+}
+#endif
+
+/**
+ * add_error_device - list device to be handled
+ * @e_info: pointer to error info
+ * @dev: pointer to pci_dev to be added
+ */
+static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev)
+{
+ if (e_info->error_dev_num < AER_MAX_MULTI_ERR_DEVICES) {
+ e_info->dev[e_info->error_dev_num] = dev;
+ e_info->error_dev_num++;
+ return 0;
+ }
+ return -ENOSPC;
+}
+
+/**
+ * is_error_source - check whether the device is source of reported error
+ * @dev: pointer to pci_dev to be checked
+ * @e_info: pointer to reported error info
+ */
+static bool is_error_source(struct pci_dev *dev, struct aer_err_info *e_info)
+{
+ int pos;
+ u32 status, mask;
+ u16 reg16;
+
+ /*
+ * When bus id is equal to 0, it might be a bad id
+ * reported by root port.
+ */
+ if ((PCI_BUS_NUM(e_info->id) != 0) &&
+ !(dev->bus->bus_flags & PCI_BUS_FLAGS_NO_AERSID)) {
+ /* Device ID match? */
+ if (e_info->id == ((dev->bus->number << 8) | dev->devfn))
+ return true;
+
+ /* Continue id comparing if there is no multiple error */
+ if (!e_info->multi_error_valid)
+ return false;
+ }
+
+ /*
+ * When either
+ * 1) bus id is equal to 0. Some ports might lose the bus
+ * id of error source id;
+ * 2) bus flag PCI_BUS_FLAGS_NO_AERSID is set
+ * 3) There are multiple errors and prior ID comparing fails;
+ * We check AER status registers to find possible reporter.
+ */
+ if (atomic_read(&dev->enable_cnt) == 0)
+ return false;
+
+ /* Check if AER is enabled */
+ pcie_capability_read_word(dev, PCI_EXP_DEVCTL, &reg16);
+ if (!(reg16 & PCI_EXP_AER_FLAGS))
+ return false;
+
+ pos = dev->aer_cap;
+ if (!pos)
+ return false;
+
+ /* Check if error is recorded */
+ if (e_info->severity == AER_CORRECTABLE) {
+ pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS, &status);
+ pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, &mask);
+ } else {
+ pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+ pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, &mask);
+ }
+ if (status & ~mask)
+ return true;
+
+ return false;
+}
+
+static int find_device_iter(struct pci_dev *dev, void *data)
+{
+ struct aer_err_info *e_info = (struct aer_err_info *)data;
+
+ if (is_error_source(dev, e_info)) {
+ /* List this device */
+ if (add_error_device(e_info, dev)) {
+ /* We cannot handle more... Stop iteration */
+ /* TODO: Should print error message here? */
+ return 1;
+ }
+
+ /* If there is only a single error, stop iteration */
+ if (!e_info->multi_error_valid)
+ return 1;
+ }
+ return 0;
+}
+
+/**
+ * find_source_device - search through device hierarchy for source device
+ * @parent: pointer to Root Port pci_dev data structure
+ * @e_info: including detailed error information such like id
+ *
+ * Return true if found.
+ *
+ * Invoked by DPC when error is detected at the Root Port.
+ * Caller of this function must set id, severity, and multi_error_valid of
+ * struct aer_err_info pointed by @e_info properly. This function must fill
+ * e_info->error_dev_num and e_info->dev[], based on the given information.
+ */
+static bool find_source_device(struct pci_dev *parent,
+ struct aer_err_info *e_info)
+{
+ struct pci_dev *dev = parent;
+ int result;
+
+ /* Must reset in this function */
+ e_info->error_dev_num = 0;
+
+ /* Is Root Port an agent that sends error message? */
+ result = find_device_iter(dev, e_info);
+ if (result)
+ return true;
+
+ pci_walk_bus(parent->subordinate, find_device_iter, e_info);
+
+ if (!e_info->error_dev_num) {
+ pci_printk(KERN_DEBUG, parent, "can't find device of ID%04x\n",
+ e_info->id);
+ return false;
+ }
+ return true;
+}
+
+/**
+ * handle_error_source - handle logging error into an event log
+ * @dev: pointer to pci_dev data structure of error source device
+ * @info: comprehensive error information
+ *
+ * Invoked when an error being detected by Root Port.
+ */
+static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
+{
+ int pos;
+
+ if (info->severity == AER_CORRECTABLE) {
+ /*
+ * Correctable error does not need software intervention.
+ * No need to go through error recovery process.
+ */
+ pos = dev->aer_cap;
+ if (pos)
+ pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS,
+ info->status);
+ } else if (info->severity == AER_NONFATAL)
+ pcie_do_nonfatal_recovery(dev);
+ else if (info->severity == AER_FATAL)
+ pcie_do_fatal_recovery(dev, PCIE_PORT_SERVICE_AER);
+}
+
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+
+#define AER_RECOVER_RING_ORDER 4
+#define AER_RECOVER_RING_SIZE (1 << AER_RECOVER_RING_ORDER)
+
+struct aer_recover_entry {
+ u8 bus;
+ u8 devfn;
+ u16 domain;
+ int severity;
+ struct aer_capability_regs *regs;
+};
+
+static DEFINE_KFIFO(aer_recover_ring, struct aer_recover_entry,
+ AER_RECOVER_RING_SIZE);
+
+static void aer_recover_work_func(struct work_struct *work)
+{
+ struct aer_recover_entry entry;
+ struct pci_dev *pdev;
+
+ while (kfifo_get(&aer_recover_ring, &entry)) {
+ pdev = pci_get_domain_bus_and_slot(entry.domain, entry.bus,
+ entry.devfn);
+ if (!pdev) {
+ pr_err("AER recover: Can not find pci_dev for %04x:%02x:%02x:%x\n",
+ entry.domain, entry.bus,
+ PCI_SLOT(entry.devfn), PCI_FUNC(entry.devfn));
+ continue;
+ }
+ cper_print_aer(pdev, entry.severity, entry.regs);
+ if (entry.severity == AER_NONFATAL)
+ pcie_do_nonfatal_recovery(pdev);
+ else if (entry.severity == AER_FATAL)
+ pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_AER);
+ pci_dev_put(pdev);
+ }
+}
+
+/*
+ * Mutual exclusion for writers of aer_recover_ring, reader side don't
+ * need lock, because there is only one reader and lock is not needed
+ * between reader and writer.
+ */
+static DEFINE_SPINLOCK(aer_recover_ring_lock);
+static DECLARE_WORK(aer_recover_work, aer_recover_work_func);
+
+void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
+ int severity, struct aer_capability_regs *aer_regs)
+{
+ unsigned long flags;
+ struct aer_recover_entry entry = {
+ .bus = bus,
+ .devfn = devfn,
+ .domain = domain,
+ .severity = severity,
+ .regs = aer_regs,
+ };
+
+ spin_lock_irqsave(&aer_recover_ring_lock, flags);
+ if (kfifo_put(&aer_recover_ring, entry))
+ schedule_work(&aer_recover_work);
+ else
+ pr_err("AER recover: Buffer overflow when recovering AER for %04x:%02x:%02x:%x\n",
+ domain, bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+ spin_unlock_irqrestore(&aer_recover_ring_lock, flags);
+}
+EXPORT_SYMBOL_GPL(aer_recover_queue);
+#endif
+
+/**
+ * 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
+ *
+ * Return 1 on success, 0 on error.
+ *
+ * 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 pos, temp;
+
+ /* Must reset in this function */
+ info->status = 0;
+ info->tlp_header_valid = 0;
+
+ pos = dev->aer_cap;
+
+ /* The device might not support AER */
+ if (!pos)
+ return 0;
+
+ if (info->severity == AER_CORRECTABLE) {
+ pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS,
+ &info->status);
+ pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK,
+ &info->mask);
+ if (!(info->status & ~info->mask))
+ return 0;
+ } else if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
+ info->severity == AER_NONFATAL) {
+
+ /* Link is still healthy for IO reads */
+ pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS,
+ &info->status);
+ pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK,
+ &info->mask);
+ if (!(info->status & ~info->mask))
+ return 0;
+
+ /* Get First Error Pointer */
+ pci_read_config_dword(dev, pos + PCI_ERR_CAP, &temp);
+ info->first_error = PCI_ERR_CAP_FEP(temp);
+
+ if (info->status & AER_LOG_TLP_MASKS) {
+ info->tlp_header_valid = 1;
+ pci_read_config_dword(dev,
+ pos + PCI_ERR_HEADER_LOG, &info->tlp.dw0);
+ pci_read_config_dword(dev,
+ pos + PCI_ERR_HEADER_LOG + 4, &info->tlp.dw1);
+ pci_read_config_dword(dev,
+ pos + PCI_ERR_HEADER_LOG + 8, &info->tlp.dw2);
+ pci_read_config_dword(dev,
+ pos + PCI_ERR_HEADER_LOG + 12, &info->tlp.dw3);
+ }
+ }
+
+ return 1;
+}
+
+static inline void aer_process_err_devices(struct aer_err_info *e_info)
+{
+ int i;
+
+ /* Report all before handle them, not to lost records by reset etc. */
+ for (i = 0; i < e_info->error_dev_num &