Commit ce4c7b24 authored by Bjorn Helgaas's avatar Bjorn Helgaas Committed by Bjorn Helgaas

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
parents 3b3191df 0b15f1e3
......@@ -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
......
......@@ -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
// SPDX-License-Identifier: GPL-2.0
/*
* Implement the core part of PCIe AER. When a PCIe error is delivered, an
* error message will be collected and printed to console, then an error
* recovery procedure will be executed by following the PCI error recovery
* rules.
* 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/module.h>
#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/suspend.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/kfifo.h>
#include "aerdrv.h"
#include "../../pci.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)
......@@ -98,6 +408,247 @@ int pci_aer_init(struct pci_dev *dev)
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
......@@ -484,7 +1035,7 @@ static int get_e_source(struct aer_rpc *rpc, struct aer_err_source *e_src)
*
* Invoked, as DPC, when root port records new detected error
*/
void aer_isr(struct work_struct *work)
static void aer_isr(struct work_struct *work)
{
struct aer_rpc *rpc = container_of(work, struct aer_rpc, dpc_handler);
struct aer_err_source uninitialized_var(e_src);
......@@ -494,3 +1045,333 @@ void aer_isr(struct work_struct *work)
aer_isr_one_error(rpc, &e_src);
mutex_unlock(&rpc->rpc_mutex);
}
/**
* aer_irq - Root Port's ISR
* @irq: IRQ assigned to Root Port
* @context: pointer to Root Port data structure
*
* Invoked when Root Port detects AER messages.
*/
irqreturn_t aer_irq(int irq, void *context)
{
unsigned int status, id;
struct pcie_device *pdev = (struct pcie_device *)context;
struct aer_rpc *rpc = get_service_data(pdev);
int next_prod_idx;
unsigned long flags;
int pos;
pos = pdev->port->aer_cap;
/*
* Must lock access to Root Error Status Reg, Root Error ID Reg,
* and Root error producer/consumer index
*/
spin_lock_irqsave(&rpc->e_lock, flags);
/* Read error status */
pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, &status);
if (!(status & (PCI_ERR_ROOT_UNCOR_RCV|PCI_ERR_ROOT_COR_RCV))) {
spin_unlock_irqrestore(&rpc->e_lock, flags);
return IRQ_NONE;
}
/* Read error source and clear error status */
pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_ERR_SRC, &id);
pci_write_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, status);
/* Store error source for later DPC handler */
next_prod_idx = rpc->prod_idx + 1;
if (next_prod_idx == AER_ERROR_SOURCES_MAX)
next_prod_idx = 0;
if (next_prod_idx == rpc->cons_idx) {
/*
* Error Storm Condition - possibly the same error occurred.
* Drop the error.
*/
spin_unlock_irqrestore(&rpc->e_lock, flags);
return IRQ_HANDLED;
}
rpc->e_sources[rpc->prod_idx].status = status;
rpc->e_sources[rpc->prod_idx].id = id;
rpc->prod_idx = next_prod_idx;
spin_unlock_irqrestore(&rpc->e_lock, flags);
/* Invoke DPC handler */
schedule_work(&rpc->dpc_handler);
return IRQ_HANDLED;
}
EXPORT_SYMBOL_GPL(aer_irq);
static int set_device_error_reporting(struct pci_dev *dev, void *data)
{
bool enable = *((bool *)data);
int type = pci_pcie_type(dev);
if ((type == PCI_EXP_TYPE_ROOT_PORT) ||
(type == PCI_EXP_TYPE_UPSTREAM) ||
(type == PCI_EXP_TYPE_DOWNSTREAM)) {
if (enable)
pci_enable_pcie_error_reporting(dev);
else
pci_disable_pcie_error_reporting(dev);
}
if (enable)
pcie_set_ecrc_checking(dev);
return 0;
}
/**
* set_downstream_devices_error_reporting - enable/disable the error reporting bits on the root port and its downstream ports.
* @dev: pointer to root port's pci_dev data structure
* @enable: true = enable error reporting, false = disable error reporting.
*/
static void set_downstream_devices_error_reporting(struct pci_dev *dev,
bool enable)
{
set_device_error_reporting(dev, &enable);
if (!dev->subordinate)
return;
pci_walk_bus(dev->subordinate, set_device_error_reporting, &enable);
}
/**
* aer_enable_rootport - enable Root Port's interrupts when receiving messages
* @rpc: pointer to a Root Port data structure
*
* Invoked when PCIe bus loads AER service driver.
*/
static void aer_enable_rootport(struct aer_rpc *rpc)
{
struct pci_dev *pdev = rpc->rpd;
int aer_pos;
u16 reg16;
u32 reg32;
/* Clear PCIe Capability's Device Status */
pcie_capability_read_word(pdev, PCI_EXP_DEVSTA, &reg16);
pcie_capability_write_word(pdev, PCI_EXP_DEVSTA, reg16);
/* Disable system error generation in response to error messages */
pcie_capability_clear_word(pdev, PCI_EXP_RTCTL,
SYSTEM_ERROR_INTR_ON_MESG_MASK);
aer_pos = pdev->aer_cap;
/* Clear error status */
pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, &reg32);
pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, reg32);
pci_read_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, &reg32);
pci_write_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, reg32);
pci_read_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, &reg32);
pci_write_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, reg32);
/*
* Enable error reporting for the root port device and downstream port
* devices.
*/
set_downstream_devices_error_reporting(pdev, true);
/* Enable Root Port's interrupt in response to error messages */
pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_COMMAND, &reg32);
reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;
pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_COMMAND, reg32);
}
/**
* aer_disable_rootport - disable Root Port's interrupts when receiving messages
* @rpc: pointer to a Root Port data structure
*
* Invoked when PCIe bus unloads AER service driver.
*/
static void aer_disable_rootport(struct aer_rpc *rpc)
{
struct pci_dev *pdev = rpc->rpd;
u32 reg32;
int pos;
/*
* Disable error reporting for the root port device and downstream port
* devices.
*/
set_downstream_devices_error_reporting(pdev, false);
pos = pdev->aer_cap;
/* Disable Root's interrupt in response to error messages */
pci_read_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, reg32);
/* Clear Root's error status reg */
pci_read_config_dword(pdev, pos + PCI_ERR_ROOT_STATUS, &reg32);
pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_STATUS, reg32);
}
/**
* aer_alloc_rpc - allocate Root Port data structure
* @dev: pointer to the pcie_dev data structure
*
* Invoked when Root Port's AER service is loaded.
*/
static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev)
{
struct aer_rpc *rpc;
rpc = kzalloc(sizeof(struct aer_rpc), GFP_KERNEL);
if (!rpc)
return NULL;
/* Initialize Root lock access, e_lock, to Root Error Status Reg */
spin_lock_init(&rpc->e_lock);
rpc->rpd = dev->port;
INIT_WORK(&rpc->dpc_handler, aer_isr);
mutex_init(&rpc->rpc_mutex);
/* Use PCIe bus function to store rpc into PCIe device */
set_service_data(dev, rpc);
return rpc;
}
/**
* aer_remove - clean up resources
* @dev: pointer to the pcie_dev data structure
*
* Invoked when PCI Express bus unloads or AER probe fails.
*/
static void aer_remove(struct pcie_device *dev)
{
struct aer_rpc *rpc = get_service_data(dev);
if (rpc) {
/* If register interrupt service, it must be free. */
if (rpc->isr)
free_irq(dev->irq, dev);
flush_work(&rpc->dpc_handler);
aer_disable_rootport(rpc);
kfree(rpc);
set_service_data(dev, NULL);
}
}
/**
* aer_probe - initialize resources
* @dev: pointer to the pcie_dev data structure
*
* Invoked when PCI Express bus loads AER service driver.
*/
static int aer_probe(struct pcie_device *dev)
{
int status;
struct aer_rpc *rpc;
struct device *device = &dev->port->dev;
/* Alloc rpc data structure */
rpc = aer_alloc_rpc(dev);
if (!rpc) {
dev_printk(KERN_DEBUG, device, "alloc AER rpc failed\n");
aer_remove(dev);
return -ENOMEM;
}
/* Request IRQ ISR */
status = request_irq(dev->irq, aer_irq, IRQF_SHARED, "aerdrv", dev);
if (status) {
dev_printk(KERN_DEBUG, device, "request AER IRQ %d failed\n",
dev->irq);
aer_remove(dev);
return status;
}
rpc->isr = 1;
aer_enable_rootport(rpc);
dev_info(device, "AER enabled with IRQ %d\n", dev->irq);
return 0;
}
/**
* aer_root_reset - reset link on Root Port
* @dev: pointer to Root Port's pci_dev data structure
*
* Invoked by Port Bus driver when performing link reset at Root Port.
*/
static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
{
u32 reg32;
int pos;
pos = dev->aer_cap;
/* Disable Root's interrupt in response to error messages */
pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
pci_reset_bridge_secondary_bus(dev);
pci_printk(KERN_DEBUG, dev, "Root Port link has been reset\n");
/* Clear Root Error Status */
pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &reg32);
pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, reg32);
/* Enable Root Port's interrupt in response to error messages */
pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;
pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
return PCI_ERS_RESULT_RECOVERED;
}
/**
* aer_error_resume - clean up corresponding error status bits
* @dev: pointer to Root Port's pci_dev data structure
*
* Invoked by Port Bus driver during nonfatal recovery.
*/
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, &reg16);
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);
}
static struct pcie_port_service_driver aerdriver = {
.name = "aer",
.port_type = PCI_EXP_TYPE_ROOT_PORT,
.service = PCIE_PORT_SERVICE_AER,
.probe = aer_probe,
.remove = aer_remove,
.error_resume = aer_error_resume,
.reset_link = aer_root_reset,
};
/**
* aer_service_init - register AER root service driver
*
* Invoked when AER root service driver is loaded.
*/
static int __init aer_service_init(void)
{
if (!pci_aer_available() || aer_acpi_firmware_first())
return -ENXIO;
return pcie_port_service_register(&aerdriver);
}
device_initcall(aer_service_init);
# SPDX-License-Identifier: GPL-2.0
#
# PCI Express Root Port Device AER Configuration
#
config PCIEAER
bool "Root Port 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.
#
# 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.
source "drivers/pci/pcie/aer/Kconfig.debug"
# SPDX-License-Identifier: GPL-2.0
#
# PCI Express Root Port Device AER Debug Configuration
#
config PCIEAER_INJECT
tristate "PCIe AER error injector support"
depends on PCIEAER
default n
help
This enables PCI Express Root Port Advanced Error Reporting
(AER) software error injector.
Debugging PCIe 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/
# SPDX-License-Identifier: GPL-2.0
#
# Makefile for PCI-Express Root Port Advanced Error Reporting Driver
#
obj-$(CONFIG_PCIEAER) += aerdriver.o
obj-$(CONFIG_PCIE_ECRC) += ecrc.o
aerdriver-objs := aerdrv_errprint.o aerdrv_core.o aerdrv.o
aerdriver-$(CONFIG_ACPI) += aerdrv_acpi.o
obj-$(CONFIG_PCIEAER_INJECT) += aer_inject.o
// 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)
*/
#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/slab.h>
#include "aerdrv.h"
#include "../../pci.h"
static int aer_probe(struct pcie_device *dev);
static void aer_remove(struct pcie_device *dev);
static void aer_error_resume(struct pci_dev *dev);
static pci_ers_result_t aer_root_reset(struct pci_dev *dev);
static struct pcie_port_service_driver aerdriver = {
.name = "aer",
.port_type = PCI_EXP_TYPE_ROOT_PORT,
.service = PCIE_PORT_SERVICE_AER,
.probe = aer_probe,
.remove = aer_remove,
.error_resume = aer_error_resume,
.reset_link = aer_root_reset,
};
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();
}
static int set_device_error_reporting(struct pci_dev *dev, void *data)
{
bool enable = *((bool *)data);
int type = pci_pcie_type(dev);
if ((type == PCI_EXP_TYPE_ROOT_PORT) ||
(type == PCI_EXP_TYPE_UPSTREAM) ||
(type == PCI_EXP_TYPE_DOWNSTREAM)) {
if (enable)
pci_enable_pcie_error_reporting(dev);
else
pci_disable_pcie_error_reporting(dev);
}
if (enable)
pcie_set_ecrc_checking(dev);
return 0;
}
/**
* set_downstream_devices_error_reporting - enable/disable the error reporting bits on the root port and its downstream ports.
* @dev: pointer to root port's pci_dev data structure
* @enable: true = enable error reporting, false = disable error reporting.
*/
static void set_downstream_devices_error_reporting(struct pci_dev *dev,
bool enable)
{
set_device_error_reporting(dev, &enable);
if (!dev->subordinate)
return;
pci_walk_bus(dev->subordinate, set_device_error_reporting, &enable);
}
/**
* aer_enable_rootport - enable Root Port's interrupts when receiving messages
* @rpc: pointer to a Root Port data structure
*
* Invoked when PCIe bus loads AER service driver.
*/
static void aer_enable_rootport(struct aer_rpc *rpc)
{
struct pci_dev *pdev = rpc->rpd;
int aer_pos;
u16 reg16;
u32 reg32;
/* Clear PCIe Capability's Device Status */
pcie_capability_read_word(pdev, PCI_EXP_DEVSTA, &reg16);
pcie_capability_write_word(pdev, PCI_EXP_DEVSTA, reg16);
/* Disable system error generation in response to error messages */
pcie_capability_clear_word(pdev, PCI_EXP_RTCTL,
SYSTEM_ERROR_INTR_ON_MESG_MASK);
aer_pos = pdev->aer_cap;
/* Clear error status */
pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, &reg32);
pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, reg32);
pci_read_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, &reg32);
pci_write_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, reg32);
pci_read_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, &reg32);
pci_write_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, reg32);
/*
* Enable error reporting for the root port device and downstream port
* devices.
*/
set_downstream_devices_error_reporting(pdev, true);
/* Enable Root Port's interrupt in response to error messages */
pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_COMMAND, &reg32);
reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;
pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_COMMAND, reg32);
}
/**
* aer_disable_rootport - disable Root Port's interrupts when receiving messages
* @rpc: pointer to a Root Port data structure
*
* Invoked when PCIe bus unloads AER service driver.
*/
static void aer_disable_rootport(struct aer_rpc *rpc)
{
struct pci_dev *pdev = rpc->rpd;
u32 reg32;
int pos;
/*
* Disable error reporting for the root port device and downstream port
* devices.
*/
set_downstream_devices_error_reporting(pdev, false);
pos = pdev->aer_cap;
/* Disable Root's interrupt in response to error messages */
pci_read_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, reg32);
/* Clear Root's error status reg */
pci_read_config_dword(pdev, pos + PCI_ERR_ROOT_STATUS, &reg32);
pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_STATUS, reg32);
}
/**
* aer_irq - Root Port's ISR
* @irq: IRQ assigned to Root Port
* @context: pointer to Root Port data structure
*
* Invoked when Root Port detects AER messages.
*/
irqreturn_t aer_irq(int irq, void *context)
{
unsigned int status, id;
struct pcie_device *pdev = (struct pcie_device *)context;
struct aer_rpc *rpc = get_service_data(pdev);
int next_prod_idx;
unsigned long flags;
int pos;
pos = pdev->port->aer_cap;
/*
* Must lock access to Root Error Status Reg, Root Error ID Reg,
* and Root error producer/consumer index
*/
spin_lock_irqsave(&rpc->e_lock, flags);
/* Read error status */
pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, &status);
if (!(status & (PCI_ERR_ROOT_UNCOR_RCV|PCI_ERR_ROOT_COR_RCV))) {
spin_unlock_irqrestore(&rpc->e_lock, flags);
return IRQ_NONE;
}
/* Read error source and clear error status */
pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_ERR_SRC, &id);
pci_write_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, status);
/* Store error source for later DPC handler */
next_prod_idx = rpc->prod_idx + 1;
if (next_prod_idx == AER_ERROR_SOURCES_MAX)
next_prod_idx = 0;
if (next_prod_idx == rpc->cons_idx) {
/*
* Error Storm Condition - possibly the same error occurred.
* Drop the error.
*/
spin_unlock_irqrestore(&rpc->e_lock, flags);
return IRQ_HANDLED;
}
rpc->e_sources[rpc->prod_idx].status = status;
rpc->e_sources[rpc->prod_idx].id = id;
rpc->prod_idx = next_prod_idx;
spin_unlock_irqrestore(&rpc->e_lock, flags);
/* Invoke DPC handler */
schedule_work(&rpc->dpc_handler);
return IRQ_HANDLED;
}
EXPORT_SYMBOL_GPL(aer_irq);
/**
* aer_alloc_rpc - allocate Root Port data structure
* @dev: pointer to the pcie_dev data structure
*
* Invoked when Root Port's AER service is loaded.
*/
static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev)
{
struct aer_rpc *rpc;
rpc = kzalloc(sizeof(struct aer_rpc), GFP_KERNEL);
if (!rpc)
return NULL;
/* Initialize Root lock access, e_lock, to Root Error Status Reg */
spin_lock_init(&rpc->e_lock);
rpc->rpd = dev->port;
INIT_WORK(&rpc->dpc_handler, aer_isr);
mutex_init(&rpc->rpc_mutex);
/* Use PCIe bus function to store rpc into PCIe device */
set_service_data(dev, rpc);
return rpc;
}
/**
* aer_remove - clean up resources
* @dev: pointer to the pcie_dev data structure
*
* Invoked when PCI Express bus unloads or AER probe fails.
*/
static void aer_remove(struct pcie_device *dev)
{
struct aer_rpc *rpc = get_service_data(dev);
if (rpc) {
/* If register interrupt service, it must be free. */
if (rpc->isr)
free_irq(dev->irq, dev);
flush_work(&rpc->dpc_handler);
aer_disable_rootport(rpc);
kfree(rpc);
set_service_data(dev, NULL);
}
}
/**
* aer_probe - initialize resources
* @dev: pointer to the pcie_dev data structure
*
* Invoked when PCI Express bus loads AER service driver.
*/
static int aer_probe(struct pcie_device *dev)
{
int status;
struct aer_rpc *rpc;
struct device *device = &dev->port->dev;
/* Alloc rpc data structure */
rpc = aer_alloc_rpc(dev);
if (!rpc) {
dev_printk(KERN_DEBUG, device, "alloc AER rpc failed\n");
aer_remove(dev);
return -ENOMEM;
}
/* Request IRQ ISR */
status = request_irq(dev->irq, aer_irq, IRQF_SHARED, "aerdrv", dev);
if (status) {
dev_printk(KERN_DEBUG, device, "request AER IRQ %d failed\n",
dev->irq);
aer_remove(dev);
return status;
}
rpc->isr = 1;
aer_enable_rootport(rpc);
dev_info(device, "AER enabled with IRQ %d\n", dev->irq);
return 0;
}
/**
* aer_root_reset - reset link on Root Port
* @dev: pointer to Root Port's pci_dev data structure
*
* Invoked by Port Bus driver when performing link reset at Root Port.
*/
static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
{
u32 reg32;
int pos;
pos = dev->aer_cap;
/* Disable Root's interrupt in response to error messages */
pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
pci_reset_bridge_secondary_bus(dev);
pci_printk(KERN_DEBUG, dev, "Root Port link has been reset\n");
/* Clear Root Error Status */
pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &reg32);
pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, reg32);
/* Enable Root Port's interrupt in response to error messages */
pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;
pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
return PCI_ERS_RESULT_RECOVERED;
}
/**
* aer_error_resume - clean up corresponding error status bits
* @dev: pointer to Root Port's pci_dev data structure
*
* Invoked by Port Bus driver during nonfatal recovery.
*/
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, &reg16);
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);
}
/**
* aer_service_init - register AER root service driver
*
* Invoked when AER root service driver is loaded.
*/
static int __init aer_service_init(void)
{
if (!pci_aer_available() || aer_acpi_firmware_first())
return -ENXIO;
return pcie_port_service_register(&aerdriver);
}
device_initcall(aer_service_init);
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2006 Intel Corp.
* Tom Long Nguyen (tom.l.nguyen@intel.com)
* Zhang Yanmin (yanmin.zhang@intel.com)
*/
#ifndef _AERDRV_H_
#define _AERDRV_H_
#include <linux/workqueue.h>
#include <linux/aer.h>
#include <linux/interrupt.h>
#include "../portdrv.h"
#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)
#define AER_ERROR_SOURCES_MAX 100
#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 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
*/
};
extern struct bus_type pcie_port_bus_type;
void aer_isr(struct work_struct *work);
void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info);
irqreturn_t aer_irq(int irq, void *context);
#ifdef CONFIG_ACPI_APEI
int pcie_aer_get_firmware_first(struct pci_dev *pci_dev);
#else
static inline int pcie_aer_get_firmware_first(struct pci_dev *pci_dev)
{
if (pci_dev->__aer_firmware_first_valid)
return pci_dev->__aer_firmware_first;
return 0;
}
#endif
#endif /* _AERDRV_H_ */
// SPDX-License-Identifier: GPL-2.0
/*
* Access ACPI _OSC method
*
* Copyright (C) 2006 Intel Corp.
* Tom Long Nguyen (tom.l.nguyen@intel.com)
* Zhang Yanmin (yanmin.zhang@intel.com)
*/
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/pm.h>
#include <linux/suspend.h>
#include <linux/acpi.h>
#include <linux/pci-acpi.h>
#include <linux/delay.h>
#include <acpi/apei.h>
#include "aerdrv.h"
#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;
}
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
// SPDX-License-Identifier: GPL-2.0
/*
* Format error messages and print them to console.
*
* Copyright (C) 2006 Intel Corp.
* Tom Long Nguyen (tom.l.nguyen@intel.com)
* Zhang Yanmin (yanmin.zhang@intel.com)
*/
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/pm.h>
#include <linux/suspend.h>
#include <linux/cper.h>
#include "aerdrv.h"
#include <ras/ras_event.h>
#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)" : "");
}
}
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);
}
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
// SPDX-License-Identifier: GPL-2.0
/*
* Enable/disable PCIe ECRC checking
*
* (C) Copyright 2009 Hewlett-Packard Development Company, L.P.
* Andrew Patterson <andrew.patterson@hp.com>
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/pci.h>
#include <linux/pci_regs.h>
#include <linux/errno.h>
#include "../../pci.h"
#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;
}
......@@ -21,7 +21,8 @@
#include <linux/uaccess.h>
#include <linux/stddef.h>
#include <linux/device.h>
#include "aerdrv.h"
#include "portdrv.h"
/* Override the existing corrected and uncorrected error masks */
static bool aer_mask_override;
......
......@@ -13,7 +13,6 @@
#include "portdrv.h"
#include "../pci.h"
#include "aer/aerdrv.h"
struct dpc_dev {
struct pcie_device *dev;
......
......@@ -110,6 +110,21 @@ static inline bool pcie_pme_no_msi(void) { return false; }
static inline void pcie_pme_interrupt_enable(struct pci_dev *dev, bool en) {}
#endif /* !CONFIG_PCIE_PME */
#ifdef CONFIG_ACPI_APEI
int pcie_aer_get_firmware_first(struct pci_dev *pci_dev);
#else
static inline int pcie_aer_get_firmware_first(struct pci_dev *pci_dev)
{
if (pci_dev->__aer_firmware_first_valid)
return pci_dev->__aer_firmware_first;
return 0;
}
#endif
#ifdef CONFIG_PCIEAER
irqreturn_t aer_irq(int irq, void *context);
#endif
struct pcie_port_service_driver *pcie_port_find_service(struct pci_dev *dev,
u32 service);
struct device *pcie_port_find_device(struct pci_dev *dev, u32 service);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment