linux/drivers/pci/pcie/aer.c

1358 lines
35 KiB
C
Raw Normal View History

// 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 cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 09:04:11 +01:00
#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
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;
}
void pci_aer_init(struct pci_dev *dev)
{
dev->aer_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
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[] = {
"RxErr", /* Bit Position 0 */
NULL,
NULL,
NULL,
NULL,
NULL,
"BadTLP", /* Bit Position 6 */
"BadDLLP", /* Bit Position 7 */
"Rollover", /* Bit Position 8 */
NULL,
NULL,
NULL,
"Timeout", /* Bit Position 12 */
"NonFatalErr", /* Bit Position 13 */
"CorrIntErr", /* Bit Position 14 */
"HeaderOF", /* Bit Position 15 */
};
static const char *aer_uncorrectable_error_string[] = {
"Undefined", /* Bit Position 0 */
NULL,
NULL,
NULL,
"DLP", /* Bit Position 4 */
"SDES", /* Bit Position 5 */
NULL,
NULL,
NULL,
NULL,
NULL,
NULL,
"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 */
"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[] = {
"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);
}
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
/**
* 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
*
* Return 1 on success, 0 on error.
*
* Note that @info is reused among all error devices. Clear fields properly.
*/
int aer_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 && e_info->dev[i]; i++) {
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 (aer_get_device_error_info(e_info->dev[i], e_info))
handle_error_source(e_info->dev[i], e_info);
}
}
/**
* aer_isr_one_error - consume an error detected by root port
* @rpc: pointer to the root port which holds an error
* @e_src: pointer to an error source
*/
static void aer_isr_one_error(struct aer_rpc *rpc,
struct aer_err_source *e_src)
{
struct pci_dev *pdev = rpc->rpd;
struct aer_err_info *e_info = &rpc->e_info;
/*
* There is a possibility that both correctable error and
* uncorrectable error being logged. Report correctable error first.
*/
if (e_src->status & PCI_ERR_ROOT_COR_RCV) {
e_info->id = ERR_COR_ID(e_src->id);
e_info->severity = AER_CORRECTABLE;
if (e_src->status & PCI_ERR_ROOT_MULTI_COR_RCV)
e_info->multi_error_valid = 1;
else
e_info->multi_error_valid = 0;
aer_print_port_info(pdev, e_info);
if (find_source_device(pdev, e_info))
aer_process_err_devices(e_info);
}
if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
e_info->id = ERR_UNCOR_ID(e_src->id);
if (e_src->status & PCI_ERR_ROOT_FATAL_RCV)
e_info->severity = AER_FATAL;
else
e_info->severity = AER_NONFATAL;
if (e_src->status & PCI_ERR_ROOT_MULTI_UNCOR_RCV)
e_info->multi_error_valid = 1;
else
e_info->multi_error_valid = 0;
aer_print_port_info(pdev, e_info);
if (find_source_device(pdev, e_info))
aer_process_err_devices(e_info);
}
}
/**
* get_e_source - retrieve an error source
* @rpc: pointer to the root port which holds an error
* @e_src: pointer to store retrieved error source
*
* Return 1 if an error source is retrieved, otherwise 0.
*
* Invoked by DPC handler to consume an error.
*/
static int get_e_source(struct aer_rpc *rpc, struct aer_err_source *e_src)
{
unsigned long flags;
/* Lock access to Root error producer/consumer index */
spin_lock_irqsave(&rpc->e_lock, flags);
if (rpc->prod_idx == rpc->cons_idx) {
spin_unlock_irqrestore(&rpc->e_lock, flags);
return 0;
}
*e_src = rpc->e_sources[rpc->cons_idx];
rpc->cons_idx++;
if (rpc->cons_idx == AER_ERROR_SOURCES_MAX)
rpc->cons_idx = 0;
spin_unlock_irqrestore(&rpc->e_lock, flags);
return 1;
}
/**
* aer_isr - consume errors detected by root port
* @work: definition of this work item
*
* Invoked, as DPC, when root port records new detected error
*/
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);
mutex_lock(&rpc->rpc_mutex);
while (get_e_source(rpc, &e_src))
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;
2006-11-22 15:55:48 +01:00
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);
PCI/AER: Flush workqueue on device remove to avoid use-after-free A Root Port's AER structure (rpc) contains a queue of events. aer_irq() enqueues AER status information and schedules aer_isr() to dequeue and process it. When we remove a device, aer_remove() waits for the queue to be empty, then frees the rpc struct. But aer_isr() references the rpc struct after dequeueing and possibly emptying the queue, which can cause a use-after-free error as in the following scenario with two threads, aer_isr() on the left and a concurrent aer_remove() on the right: Thread A Thread B -------- -------- aer_irq(): rpc->prod_idx++ aer_remove(): wait_event(rpc->prod_idx == rpc->cons_idx) # now blocked until queue becomes empty aer_isr(): # ... rpc->cons_idx++ # unblocked because queue is now empty ... kfree(rpc) mutex_unlock(&rpc->rpc_mutex) To prevent this problem, use flush_work() to wait until the last scheduled instance of aer_isr() has completed before freeing the rpc struct in aer_remove(). I reproduced this use-after-free by flashing a device FPGA and re-enumerating the bus to find the new device. With SLUB debug, this crashes with 0x6b bytes (POISON_FREE, the use-after-free magic number) in GPR25: pcieport 0000:00:00.0: AER: Multiple Corrected error received: id=0000 Unable to handle kernel paging request for data at address 0x27ef9e3e Workqueue: events aer_isr GPR24: dd6aa000 6b6b6b6b 605f8378 605f8360 d99b12c0 604fc674 606b1704 d99b12c0 NIP [602f5328] pci_walk_bus+0xd4/0x104 [bhelgaas: changelog, stable tag] Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> CC: stable@vger.kernel.org
2016-01-25 17:08:00 +01:00
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);
PCI/AER: Handle ERR_FATAL with removal and re-enumeration of devices PCIe ERR_FATAL errors mean the Link is unreliable. Components on the Link may need to be reset to return to reliable operation (PCIe r4.0, sec 6.2.2). We previously handled these errors much differently depending on whether the platform supports Downstream Port Containment (DPC) (PCIe r4.0, sec 6.2.10) or not. The AER driver has historically logged the error details, called driver-supplied pci_error_handlers callbacks, and reset the Link. This reset downstream devices, but did not remove them from the PCI subsystem, re-enumerate them, or call their driver .remove() or .probe() methods. DPC is different because the hardware automatically disables the Link when it detects ERR_FATAL, which resets downstream devices. There's no opportunity for pci_error_handlers callbacks before resetting the Link. The DPC driver removes affected devices (which calls their driver .remove() methods), brings the Link back up, and re-enumerates (which calls driver .probe() methods). Align AER ERR_FATAL handling with DPC by resetting the Link in software, skipping the driver pci_error_handlers callbacks, removing the devices from the PCI subsystem, and re-enumerating. The idea is that drivers and devices should see the same behavior for ERR_FATAL events, regardless of whether they're handled by AER or DPC. Here are the basic ERR_FATAL recovery steps, showing the previous AER behavior, the AER behavior after this patch, and the DPC behavior: AER AER DPC previous new behavior -------- --- -------- Log error yes yes yes (minimal) drv.error_detected() yes no no Reset Link yes yes yes drv.mmio_enabled() yes no no drv.slot_reset() yes no no drv.resume() yes no no Remove PCI devices no yes yes (calls drv.remove()) Re-enumerate no yes yes (calls drv.probe()) N.B. With DPC, the Link reset happens before the driver .remove() calls, while with AER, the reset happens *after* the .remove() calls. The goal is to eventually do the reset before .remove() for AER as well. Signed-off-by: Oza Pawandeep <poza@codeaurora.org> [bhelgaas: changelog, squash doc patch into this, remove unused "result_data"] Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Keith Busch <keith.busch@intel.com>
2018-05-17 23:44:13 +02:00
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)
{
2010-09-20 18:50:00 +02:00
if (!pci_aer_available() || aer_acpi_firmware_first())
return -ENXIO;
return pcie_port_service_register(&aerdriver);
}
device_initcall(aer_service_init);