diff options
Diffstat (limited to 'drivers/pci/pcie/aer.c')
| -rw-r--r-- | drivers/pci/pcie/aer.c | 884 |
1 files changed, 613 insertions, 271 deletions
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 625f7b2cafe4..e0bcaa896803 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -2,7 +2,7 @@ /* * 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. + * collects Root Port status and schedules work. * * Copyright (C) 2006 Intel Corp. * Tom Long Nguyen (tom.l.nguyen@intel.com) @@ -17,6 +17,7 @@ #include <linux/bitops.h> #include <linux/cper.h> +#include <linux/dev_printk.h> #include <linux/pci.h> #include <linux/pci-acpi.h> #include <linux/sched.h> @@ -27,21 +28,27 @@ #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/kfifo.h> +#include <linux/ratelimit.h> #include <linux/slab.h> +#include <linux/vmcore_info.h> #include <acpi/apei.h> +#include <acpi/ghes.h> #include <ras/ras_event.h> #include "../pci.h" #include "portdrv.h" +#define aer_printk(level, pdev, fmt, arg...) \ + dev_printk(level, &(pdev)->dev, fmt, ##arg) + #define AER_ERROR_SOURCES_MAX 128 #define AER_MAX_TYPEOF_COR_ERRS 16 /* as per PCI_ERR_COR_STATUS */ -#define AER_MAX_TYPEOF_UNCOR_ERRS 27 /* as per PCI_ERR_UNCOR_STATUS*/ +#define AER_MAX_TYPEOF_UNCOR_ERRS 32 /* as per PCI_ERR_UNCOR_STATUS*/ struct aer_err_source { - unsigned int status; - unsigned int id; + u32 status; /* PCI_ERR_ROOT_STATUS */ + u32 id; /* PCI_ERR_ROOT_ERR_SRC */ }; struct aer_rpc { @@ -49,15 +56,15 @@ struct aer_rpc { DECLARE_KFIFO(aer_fifo, struct aer_err_source, AER_ERROR_SOURCES_MAX); }; -/* AER stats for the device */ -struct aer_stats { +/* AER info for the device */ +struct aer_info { /* * Fields for all AER capable devices. They indicate the errors * "as seen by this device". Note that this may mean that if an - * end point is causing problems, the AER counters may increment - * at its link partner (e.g. root port) because the errors will be - * "seen" by the link partner and not the problematic end point + * Endpoint is causing problems, the AER counters may increment + * at its link partner (e.g. Root Port) because the errors will be + * "seen" by the link partner and not the problematic Endpoint * itself (which may report all counters as 0 as it never saw any * problems). */ @@ -75,22 +82,36 @@ struct aer_stats { u64 dev_total_nonfatal_errs; /* - * Fields for Root ports & root complex event collectors only, these + * Fields for Root Ports & Root Complex Event Collectors only; these * indicate the total number of ERR_COR, ERR_FATAL, and ERR_NONFATAL - * messages received by the root port / event collector, INCLUDING the - * ones that are generated internally (by the rootport itself) + * messages received by the Root Port / Event Collector, INCLUDING the + * ones that are generated internally (by the Root Port itself) */ u64 rootport_total_cor_errs; u64 rootport_total_fatal_errs; u64 rootport_total_nonfatal_errs; + + /* Ratelimits for errors */ + struct ratelimit_state correctable_ratelimit; + struct ratelimit_state nonfatal_ratelimit; }; #define AER_LOG_TLP_MASKS (PCI_ERR_UNC_POISON_TLP| \ + PCI_ERR_UNC_POISON_BLK | \ PCI_ERR_UNC_ECRC| \ PCI_ERR_UNC_UNSUP| \ PCI_ERR_UNC_COMP_ABORT| \ PCI_ERR_UNC_UNX_COMP| \ - PCI_ERR_UNC_MALF_TLP) + PCI_ERR_UNC_ACSV | \ + PCI_ERR_UNC_MCBTLP | \ + PCI_ERR_UNC_ATOMEG | \ + PCI_ERR_UNC_DMWR_BLK | \ + PCI_ERR_UNC_XLAT_BLK | \ + PCI_ERR_UNC_TLPPRE | \ + PCI_ERR_UNC_MALF_TLP | \ + PCI_ERR_UNC_IDE_CHECK | \ + PCI_ERR_UNC_MISR_IDE | \ + PCI_ERR_UNC_PCRC_CHECK) #define SYSTEM_ERROR_INTR_ON_MESG_MASK (PCI_EXP_RTCTL_SECEE| \ PCI_EXP_RTCTL_SENFEE| \ @@ -106,12 +127,12 @@ struct aer_stats { PCI_ERR_ROOT_MULTI_COR_RCV | \ PCI_ERR_ROOT_MULTI_UNCOR_RCV) -static int pcie_aer_disable; +static bool pcie_aer_disable; static pci_ers_result_t aer_root_reset(struct pci_dev *dev); void pci_no_aer(void) { - pcie_aer_disable = 1; + pcie_aer_disable = true; } bool pci_aer_available(void) @@ -137,7 +158,7 @@ static const char * const ecrc_policy_str[] = { * enable_ecrc_checking - enable PCIe ECRC checking for a device * @dev: the PCI device * - * Returns 0 on success, or negative on failure. + * Return: 0 on success, or negative on failure. */ static int enable_ecrc_checking(struct pci_dev *dev) { @@ -158,10 +179,10 @@ static int enable_ecrc_checking(struct pci_dev *dev) } /** - * disable_ecrc_checking - disables PCIe ECRC checking for a device + * disable_ecrc_checking - disable PCIe ECRC checking for a device * @dev: the PCI device * - * Returns 0 on success, or negative on failure. + * Return: 0 on success, or negative on failure. */ static int disable_ecrc_checking(struct pci_dev *dev) { @@ -179,11 +200,15 @@ static int disable_ecrc_checking(struct pci_dev *dev) } /** - * pcie_set_ecrc_checking - set/unset PCIe ECRC checking for a device based on global policy + * 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) { + if (!pcie_aer_is_native(dev)) + return; + switch (ecrc_policy) { case ECRC_POLICY_DEFAULT: return; @@ -226,8 +251,9 @@ int pcie_aer_is_native(struct pci_dev *dev) return pcie_ports_native || host->native_aer; } +EXPORT_SYMBOL_NS_GPL(pcie_aer_is_native, "CXL"); -int pci_enable_pcie_error_reporting(struct pci_dev *dev) +static int pci_enable_pcie_error_reporting(struct pci_dev *dev) { int rc; @@ -237,19 +263,6 @@ int pci_enable_pcie_error_reporting(struct pci_dev *dev) rc = pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_AER_FLAGS); return pcibios_err_to_errno(rc); } -EXPORT_SYMBOL_GPL(pci_enable_pcie_error_reporting); - -int pci_disable_pcie_error_reporting(struct pci_dev *dev) -{ - int rc; - - if (!pcie_aer_is_native(dev)) - return -EIO; - - rc = pcie_capability_clear_word(dev, PCI_EXP_DEVCTL, PCI_EXP_AER_FLAGS); - return pcibios_err_to_errno(rc); -} -EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting); int pci_aer_clear_nonfatal_status(struct pci_dev *dev) { @@ -290,10 +303,10 @@ void pci_aer_clear_fatal_status(struct pci_dev *dev) * pci_aer_raw_clear_status - Clear AER error registers. * @dev: the PCI device * - * Clearing AER error status registers unconditionally, regardless of + * Clear AER error status registers unconditionally, regardless of * whether they're owned by firmware or the OS. * - * Returns 0 on success, or negative on failure. + * Return: 0 on success, or negative on failure. */ int pci_aer_raw_clear_status(struct pci_dev *dev) { @@ -380,13 +393,22 @@ void pci_aer_init(struct pci_dev *dev) if (!dev->aer_cap) return; - dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL); + dev->aer_info = kzalloc(sizeof(*dev->aer_info), GFP_KERNEL); + if (!dev->aer_info) { + dev->aer_cap = 0; + return; + } + + ratelimit_state_init(&dev->aer_info->correctable_ratelimit, + DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); + ratelimit_state_init(&dev->aer_info->nonfatal_ratelimit, + DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); /* * We save/restore PCI_ERR_UNCOR_MASK, PCI_ERR_UNCOR_SEVER, * PCI_ERR_COR_MASK, and PCI_ERR_CAP. Root and Root Complex Event - * Collectors also implement PCI_ERR_ROOT_COMMAND (PCIe r5.0, sec - * 7.8.4). + * Collectors also implement PCI_ERR_ROOT_COMMAND (PCIe r6.0, sec + * 7.8.4.9). */ n = pcie_cap_has_rtctl(dev) ? 5 : 4; pci_add_ext_cap_save_buffer(dev, PCI_EXT_CAP_ID_ERR, sizeof(u32) * n); @@ -401,8 +423,8 @@ void pci_aer_init(struct pci_dev *dev) void pci_aer_exit(struct pci_dev *dev) { - kfree(dev->aer_stats); - dev->aer_stats = NULL; + kfree(dev->aer_info); + dev->aer_info = NULL; } #define AER_AGENT_RECEIVER 0 @@ -443,10 +465,10 @@ void pci_aer_exit(struct pci_dev *dev) /* * AER error strings */ -static const char *aer_error_severity_string[] = { - "Uncorrected (Non-Fatal)", - "Uncorrected (Fatal)", - "Corrected" +static const char * const aer_error_severity_string[] = { + "Uncorrectable (Non-Fatal)", + "Uncorrectable (Fatal)", + "Correctable" }; static const char *aer_error_layer[] = { @@ -518,11 +540,11 @@ static const char *aer_uncorrectable_error_string[] = { "AtomicOpBlocked", /* Bit Position 24 */ "TLPBlockedErr", /* Bit Position 25 */ "PoisonTLPBlocked", /* Bit Position 26 */ - NULL, /* Bit Position 27 */ - NULL, /* Bit Position 28 */ - NULL, /* Bit Position 29 */ - NULL, /* Bit Position 30 */ - NULL, /* Bit Position 31 */ + "DMWrReqBlocked", /* Bit Position 27 */ + "IDECheck", /* Bit Position 28 */ + "MisIDETLP", /* Bit Position 29 */ + "PCRC_CHECK", /* Bit Position 30 */ + "TLPXlatBlocked", /* Bit Position 31 */ }; static const char *aer_agent_string[] = { @@ -540,10 +562,10 @@ static const char *aer_agent_string[] = { { \ unsigned int i; \ struct pci_dev *pdev = to_pci_dev(dev); \ - u64 *stats = pdev->aer_stats->stats_array; \ + u64 *stats = pdev->aer_info->stats_array; \ size_t len = 0; \ \ - for (i = 0; i < ARRAY_SIZE(pdev->aer_stats->stats_array); i++) {\ + for (i = 0; i < ARRAY_SIZE(pdev->aer_info->stats_array); i++) { \ if (strings_array[i]) \ len += sysfs_emit_at(buf, len, "%s %llu\n", \ strings_array[i], \ @@ -554,7 +576,7 @@ static const char *aer_agent_string[] = { i, stats[i]); \ } \ len += sysfs_emit_at(buf, len, "TOTAL_%s %llu\n", total_string, \ - pdev->aer_stats->total_field); \ + pdev->aer_info->total_field); \ return len; \ } \ static DEVICE_ATTR_RO(name) @@ -575,7 +597,7 @@ aer_stats_dev_attr(aer_dev_nonfatal, dev_nonfatal_errs, char *buf) \ { \ struct pci_dev *pdev = to_pci_dev(dev); \ - return sysfs_emit(buf, "%llu\n", pdev->aer_stats->field); \ + return sysfs_emit(buf, "%llu\n", pdev->aer_info->field); \ } \ static DEVICE_ATTR_RO(name) @@ -602,7 +624,7 @@ static umode_t aer_stats_attrs_are_visible(struct kobject *kobj, struct device *dev = kobj_to_dev(kobj); struct pci_dev *pdev = to_pci_dev(dev); - if (!pdev->aer_stats) + if (!pdev->aer_info) return 0; if ((a == &dev_attr_aer_rootport_total_err_cor.attr || @@ -620,31 +642,137 @@ const struct attribute_group aer_stats_attr_group = { .is_visible = aer_stats_attrs_are_visible, }; +/* + * Ratelimit interval + * <=0: disabled with ratelimit.interval = 0 + * >0: enabled with ratelimit.interval in ms + */ +#define aer_ratelimit_interval_attr(name, ratelimit) \ + static ssize_t \ + name##_show(struct device *dev, struct device_attribute *attr, \ + char *buf) \ + { \ + struct pci_dev *pdev = to_pci_dev(dev); \ + \ + return sysfs_emit(buf, "%d\n", \ + pdev->aer_info->ratelimit.interval); \ + } \ + \ + static ssize_t \ + name##_store(struct device *dev, struct device_attribute *attr, \ + const char *buf, size_t count) \ + { \ + struct pci_dev *pdev = to_pci_dev(dev); \ + int interval; \ + \ + if (!capable(CAP_SYS_ADMIN)) \ + return -EPERM; \ + \ + if (kstrtoint(buf, 0, &interval) < 0) \ + return -EINVAL; \ + \ + if (interval <= 0) \ + interval = 0; \ + else \ + interval = msecs_to_jiffies(interval); \ + \ + pdev->aer_info->ratelimit.interval = interval; \ + \ + return count; \ + } \ + static DEVICE_ATTR_RW(name); + +#define aer_ratelimit_burst_attr(name, ratelimit) \ + static ssize_t \ + name##_show(struct device *dev, struct device_attribute *attr, \ + char *buf) \ + { \ + struct pci_dev *pdev = to_pci_dev(dev); \ + \ + return sysfs_emit(buf, "%d\n", \ + pdev->aer_info->ratelimit.burst); \ + } \ + \ + static ssize_t \ + name##_store(struct device *dev, struct device_attribute *attr, \ + const char *buf, size_t count) \ + { \ + struct pci_dev *pdev = to_pci_dev(dev); \ + int burst; \ + \ + if (!capable(CAP_SYS_ADMIN)) \ + return -EPERM; \ + \ + if (kstrtoint(buf, 0, &burst) < 0) \ + return -EINVAL; \ + \ + pdev->aer_info->ratelimit.burst = burst; \ + \ + return count; \ + } \ + static DEVICE_ATTR_RW(name); + +#define aer_ratelimit_attrs(name) \ + aer_ratelimit_interval_attr(name##_ratelimit_interval_ms, \ + name##_ratelimit) \ + aer_ratelimit_burst_attr(name##_ratelimit_burst, \ + name##_ratelimit) + +aer_ratelimit_attrs(correctable) +aer_ratelimit_attrs(nonfatal) + +static struct attribute *aer_attrs[] = { + &dev_attr_correctable_ratelimit_interval_ms.attr, + &dev_attr_correctable_ratelimit_burst.attr, + &dev_attr_nonfatal_ratelimit_interval_ms.attr, + &dev_attr_nonfatal_ratelimit_burst.attr, + NULL +}; + +static umode_t aer_attrs_are_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct pci_dev *pdev = to_pci_dev(dev); + + if (!pdev->aer_info) + return 0; + + return a->mode; +} + +const struct attribute_group aer_attr_group = { + .name = "aer", + .attrs = aer_attrs, + .is_visible = aer_attrs_are_visible, +}; + static void pci_dev_aer_stats_incr(struct pci_dev *pdev, struct aer_err_info *info) { unsigned long status = info->status & ~info->mask; int i, max = -1; u64 *counter = NULL; - struct aer_stats *aer_stats = pdev->aer_stats; + struct aer_info *aer_info = pdev->aer_info; - if (!aer_stats) + if (!aer_info) return; switch (info->severity) { case AER_CORRECTABLE: - aer_stats->dev_total_cor_errs++; - counter = &aer_stats->dev_cor_errs[0]; + aer_info->dev_total_cor_errs++; + counter = &aer_info->dev_cor_errs[0]; max = AER_MAX_TYPEOF_COR_ERRS; break; case AER_NONFATAL: - aer_stats->dev_total_nonfatal_errs++; - counter = &aer_stats->dev_nonfatal_errs[0]; + aer_info->dev_total_nonfatal_errs++; + hwerr_log_error_type(HWERR_RECOV_PCI); + counter = &aer_info->dev_nonfatal_errs[0]; max = AER_MAX_TYPEOF_UNCOR_ERRS; break; case AER_FATAL: - aer_stats->dev_total_fatal_errs++; - counter = &aer_stats->dev_fatal_errs[0]; + aer_info->dev_total_fatal_errs++; + counter = &aer_info->dev_fatal_errs[0]; max = AER_MAX_TYPEOF_UNCOR_ERRS; break; } @@ -656,61 +784,105 @@ static void pci_dev_aer_stats_incr(struct pci_dev *pdev, static void pci_rootport_aer_stats_incr(struct pci_dev *pdev, struct aer_err_source *e_src) { - struct aer_stats *aer_stats = pdev->aer_stats; + struct aer_info *aer_info = pdev->aer_info; - if (!aer_stats) + if (!aer_info) return; if (e_src->status & PCI_ERR_ROOT_COR_RCV) - aer_stats->rootport_total_cor_errs++; + aer_info->rootport_total_cor_errs++; if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) { if (e_src->status & PCI_ERR_ROOT_FATAL_RCV) - aer_stats->rootport_total_fatal_errs++; + aer_info->rootport_total_fatal_errs++; else - aer_stats->rootport_total_nonfatal_errs++; + aer_info->rootport_total_nonfatal_errs++; + } +} + +static int aer_ratelimit(struct pci_dev *dev, unsigned int severity) +{ + if (!dev->aer_info) + return 1; + + switch (severity) { + case AER_NONFATAL: + return __ratelimit(&dev->aer_info->nonfatal_ratelimit); + case AER_CORRECTABLE: + return __ratelimit(&dev->aer_info->correctable_ratelimit); + default: + return 1; /* Don't ratelimit fatal errors */ } } -static void __print_tlp_header(struct pci_dev *dev, - struct aer_header_log_regs *t) +static bool tlp_header_logged(u32 status, u32 capctl) { - pci_err(dev, " TLP Header: %08x %08x %08x %08x\n", - t->dw0, t->dw1, t->dw2, t->dw3); + /* Errors for which a header is always logged (PCIe r7.0 sec 6.2.7) */ + if (status & AER_LOG_TLP_MASKS) + return true; + + /* Completion Timeout header is only logged on capable devices */ + if (status & PCI_ERR_UNC_COMP_TIME && + capctl & PCI_ERR_CAP_COMP_TIME_LOG) + return true; + + return false; } -static void __aer_print_error(struct pci_dev *dev, - struct aer_err_info *info) +static void __aer_print_error(struct pci_dev *dev, struct aer_err_info *info) { const char **strings; unsigned long status = info->status & ~info->mask; - const char *level, *errmsg; + const char *level = info->level; + const char *errmsg; int i; - if (info->severity == AER_CORRECTABLE) { + if (info->severity == AER_CORRECTABLE) strings = aer_correctable_error_string; - level = KERN_WARNING; - } else { + else strings = aer_uncorrectable_error_string; - level = KERN_ERR; - } for_each_set_bit(i, &status, 32) { errmsg = strings[i]; if (!errmsg) errmsg = "Unknown Error Bit"; - pci_printk(level, dev, " [%2d] %-22s%s\n", i, errmsg, + aer_printk(level, dev, " [%2d] %-22s%s\n", i, errmsg, info->first_error == i ? " (First)" : ""); } - pci_dev_aer_stats_incr(dev, info); } -void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) +static void aer_print_source(struct pci_dev *dev, struct aer_err_info *info, + bool found) { - int layer, agent; - int id = ((dev->bus->number << 8) | dev->devfn); - const char *level; + u16 source = info->id; + + pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d%s\n", + info->multi_error_valid ? "Multiple " : "", + aer_error_severity_string[info->severity], + pci_domain_nr(dev->bus), PCI_BUS_NUM(source), + PCI_SLOT(source), PCI_FUNC(source), + found ? "" : " (no details found"); +} + +void aer_print_error(struct aer_err_info *info, int i) +{ + struct pci_dev *dev; + int layer, agent, id; + const char *level = info->level; + + if (WARN_ON_ONCE(i >= AER_MAX_MULTI_ERR_DEVICES)) + return; + + dev = info->dev[i]; + id = pci_dev_id(dev); + + pci_dev_aer_stats_incr(dev, info); + trace_aer_event(pci_name(dev), (info->status & ~info->mask), + info->severity, info->tlp_header_valid, &info->tlp); + + if (!info->ratelimit_print[i]) + return; if (!info->status) { pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n", @@ -721,38 +893,21 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) layer = AER_GET_LAYER_ERROR(info->severity, info->status); agent = AER_GET_AGENT(info->severity, info->status); - level = (info->severity == AER_CORRECTABLE) ? KERN_WARNING : KERN_ERR; - - pci_printk(level, dev, "PCIe Bus Error: severity=%s, type=%s, (%s)\n", + aer_printk(level, 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_printk(level, dev, " device [%04x:%04x] error status/mask=%08x/%08x\n", + aer_printk(level, 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); + pcie_print_tlp_log(dev, &info->tlp, level, dev_fmt(" ")); 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, "%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 @@ -768,48 +923,57 @@ int cper_severity_to_aer(int cper_severity) } } EXPORT_SYMBOL_GPL(cper_severity_to_aer); +#endif -void cper_print_aer(struct pci_dev *dev, int aer_severity, - struct aer_capability_regs *aer) +void pci_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; + struct aer_err_info info = { + .severity = aer_severity, + .first_error = PCI_ERR_CAP_FEP(aer->cap_control), + }; if (aer_severity == AER_CORRECTABLE) { status = aer->cor_status; mask = aer->cor_mask; + info.level = KERN_WARNING; } else { status = aer->uncor_status; mask = aer->uncor_mask; - tlp_header_valid = status & AER_LOG_TLP_MASKS; + info.level = KERN_ERR; + tlp_header_valid = tlp_header_logged(status, aer->cap_control); } - 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); + pci_dev_aer_stats_incr(dev, &info); + trace_aer_event(pci_name(dev), (status & ~mask), + aer_severity, tlp_header_valid, &aer->header_log); + + if (!aer_ratelimit(dev, info.severity)) + return; + + layer = AER_GET_LAYER_ERROR(aer_severity, status); + agent = AER_GET_AGENT(aer_severity, status); + + aer_printk(info.level, 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]); + aer_printk(info.level, 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); + aer_printk(info.level, 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); + pcie_print_tlp_log(dev, &aer->header_log, info.level, + dev_fmt(" ")); } -#endif +EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL"); /** * add_error_device - list device to be handled @@ -818,12 +982,27 @@ void cper_print_aer(struct pci_dev *dev, int aer_severity, */ 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] = pci_dev_get(dev); - e_info->error_dev_num++; - return 0; + int i = e_info->error_dev_num; + + if (i >= AER_MAX_MULTI_ERR_DEVICES) + return -ENOSPC; + + e_info->dev[i] = pci_dev_get(dev); + e_info->error_dev_num++; + + /* + * Ratelimit AER log messages. "dev" is either the source + * identified by the root's Error Source ID or it has an unmasked + * error logged in its own AER Capability. Messages are emitted + * when "ratelimit_print[i]" is non-zero. If we will print detail + * for a downstream device, make sure we print the Error Source ID + * from the root as well. + */ + if (aer_ratelimit(dev, e_info->severity)) { + e_info->ratelimit_print[i] = 1; + e_info->root_ratelimit_print = 1; } - return -ENOSPC; + return 0; } /** @@ -838,24 +1017,24 @@ static bool is_error_source(struct pci_dev *dev, struct aer_err_info *e_info) u16 reg16; /* - * When bus id is equal to 0, it might be a bad id - * reported by root port. + * 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)) + if (e_info->id == pci_dev_id(dev)) return true; - /* Continue id comparing if there is no multiple error */ + /* 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; + * 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. @@ -893,7 +1072,8 @@ static int find_device_iter(struct pci_dev *dev, void *data) /* List this device */ if (add_error_device(e_info, dev)) { /* We cannot handle more... Stop iteration */ - /* TODO: Should print error message here? */ + pci_err(dev, "Exceeded max supported (%d) devices with errors logged\n", + AER_MAX_MULTI_ERR_DEVICES); return 1; } @@ -907,9 +1087,9 @@ static int find_device_iter(struct pci_dev *dev, void *data) /** * 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 + * @e_info: including detailed error information such as ID * - * Return true if found. + * 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 @@ -917,7 +1097,7 @@ static int find_device_iter(struct pci_dev *dev, void *data) * 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 aer_err_info *e_info) { struct pci_dev *dev = parent; int result; @@ -935,21 +1115,158 @@ static bool find_source_device(struct pci_dev *parent, else pci_walk_bus(parent->subordinate, find_device_iter, e_info); - if (!e_info->error_dev_num) { - pci_info(parent, "can't find device of ID%04x\n", e_info->id); + if (!e_info->error_dev_num) return false; - } return true; } +#ifdef CONFIG_PCIEAER_CXL + /** - * handle_error_source - handle logging error into an event log + * pci_aer_unmask_internal_errors - unmask internal errors + * @dev: pointer to the pci_dev data structure + * + * Unmask internal errors in the Uncorrectable and Correctable Error + * Mask registers. + * + * Note: AER must be enabled and supported by the device which must be + * checked in advance, e.g. with pcie_aer_is_native(). + */ +static void pci_aer_unmask_internal_errors(struct pci_dev *dev) +{ + int aer = dev->aer_cap; + u32 mask; + + pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_MASK, &mask); + mask &= ~PCI_ERR_UNC_INTN; + pci_write_config_dword(dev, aer + PCI_ERR_UNCOR_MASK, mask); + + pci_read_config_dword(dev, aer + PCI_ERR_COR_MASK, &mask); + mask &= ~PCI_ERR_COR_INTERNAL; + pci_write_config_dword(dev, aer + PCI_ERR_COR_MASK, mask); +} + +static bool is_cxl_mem_dev(struct pci_dev *dev) +{ + /* + * The capability, status, and control fields in Device 0, + * Function 0 DVSEC control the CXL functionality of the + * entire device (CXL 3.0, 8.1.3). + */ + if (dev->devfn != PCI_DEVFN(0, 0)) + return false; + + /* + * CXL Memory Devices must have the 502h class code set (CXL + * 3.0, 8.1.12.1). + */ + if ((dev->class >> 8) != PCI_CLASS_MEMORY_CXL) + return false; + + return true; +} + +static bool cxl_error_is_native(struct pci_dev *dev) +{ + struct pci_host_bridge *host = pci_find_host_bridge(dev->bus); + + return (pcie_ports_native || host->native_aer); +} + +static bool is_internal_error(struct aer_err_info *info) +{ + if (info->severity == AER_CORRECTABLE) + return info->status & PCI_ERR_COR_INTERNAL; + + return info->status & PCI_ERR_UNC_INTN; +} + +static int cxl_rch_handle_error_iter(struct pci_dev *dev, void *data) +{ + struct aer_err_info *info = (struct aer_err_info *)data; + const struct pci_error_handlers *err_handler; + + if (!is_cxl_mem_dev(dev) || !cxl_error_is_native(dev)) + return 0; + + /* Protect dev->driver */ + device_lock(&dev->dev); + + err_handler = dev->driver ? dev->driver->err_handler : NULL; + if (!err_handler) + goto out; + + if (info->severity == AER_CORRECTABLE) { + if (err_handler->cor_error_detected) + err_handler->cor_error_detected(dev); + } else if (err_handler->error_detected) { + if (info->severity == AER_NONFATAL) + err_handler->error_detected(dev, pci_channel_io_normal); + else if (info->severity == AER_FATAL) + err_handler->error_detected(dev, pci_channel_io_frozen); + } +out: + device_unlock(&dev->dev); + return 0; +} + +static void cxl_rch_handle_error(struct pci_dev *dev, struct aer_err_info *info) +{ + /* + * Internal errors of an RCEC indicate an AER error in an + * RCH's downstream port. Check and handle them in the CXL.mem + * device driver. + */ + if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_EC && + is_internal_error(info)) + pcie_walk_rcec(dev, cxl_rch_handle_error_iter, info); +} + +static int handles_cxl_error_iter(struct pci_dev *dev, void *data) +{ + bool *handles_cxl = data; + + if (!*handles_cxl) + *handles_cxl = is_cxl_mem_dev(dev) && cxl_error_is_native(dev); + + /* Non-zero terminates iteration */ + return *handles_cxl; +} + +static bool handles_cxl_errors(struct pci_dev *rcec) +{ + bool handles_cxl = false; + + if (pci_pcie_type(rcec) == PCI_EXP_TYPE_RC_EC && + pcie_aer_is_native(rcec)) + pcie_walk_rcec(rcec, handles_cxl_error_iter, &handles_cxl); + + return handles_cxl; +} + +static void cxl_rch_enable_rcec(struct pci_dev *rcec) +{ + if (!handles_cxl_errors(rcec)) + return; + + pci_aer_unmask_internal_errors(rcec); + pci_info(rcec, "CXL: Internal errors unmasked"); +} + +#else +static inline void cxl_rch_enable_rcec(struct pci_dev *dev) { } +static inline void cxl_rch_handle_error(struct pci_dev *dev, + struct aer_err_info *info) { } +#endif + +/** + * pci_aer_handle_error - 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) +static void pci_aer_handle_error(struct pci_dev *dev, struct aer_err_info *info) { int aer = dev->aer_cap; @@ -973,13 +1290,18 @@ static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info) pcie_do_recovery(dev, pci_channel_io_normal, aer_root_reset); else if (info->severity == AER_FATAL) pcie_do_recovery(dev, pci_channel_io_frozen, aer_root_reset); +} + +static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info) +{ + cxl_rch_handle_error(dev, info); + pci_aer_handle_error(dev, info); pci_dev_put(dev); } #ifdef CONFIG_ACPI_APEI_PCIEAER -#define AER_RECOVER_RING_ORDER 4 -#define AER_RECOVER_RING_SIZE (1 << AER_RECOVER_RING_ORDER) +#define AER_RECOVER_RING_SIZE 16 struct aer_recover_entry { u8 bus; @@ -1001,12 +1323,24 @@ static void aer_recover_work_func(struct work_struct *work) pdev = pci_get_domain_bus_and_slot(entry.domain, entry.bus, entry.devfn); if (!pdev) { - pr_err("no pci_dev for %04x:%02x:%02x.%x\n", - entry.domain, entry.bus, - PCI_SLOT(entry.devfn), PCI_FUNC(entry.devfn)); + pr_err_ratelimited("%04x:%02x:%02x.%x: no pci_dev found\n", + entry.domain, entry.bus, + PCI_SLOT(entry.devfn), + PCI_FUNC(entry.devfn)); continue; } - cper_print_aer(pdev, entry.severity, entry.regs); + pci_print_aer(pdev, entry.severity, entry.regs); + + /* + * Memory for aer_capability_regs(entry.regs) is being + * allocated from the ghes_estatus_pool to protect it from + * overwriting when multiple sections are present in the + * error status. Thus free the same after processing the + * data. + */ + ghes_estatus_pool_region_free((unsigned long)entry.regs, + sizeof(struct aer_capability_regs)); + if (entry.severity == AER_NONFATAL) pcie_do_recovery(pdev, pci_channel_io_normal, aer_root_reset); @@ -1048,18 +1382,25 @@ EXPORT_SYMBOL_GPL(aer_recover_queue); /** * 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 + * @i: index into info->dev[] * - * Return 1 on success, 0 on error. + * 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 aer_get_device_error_info(struct aer_err_info *info, int i) { - int type = pci_pcie_type(dev); - int aer = dev->aer_cap; - int temp; + struct pci_dev *dev; + int type, aer; + u32 aercc; + + if (i >= AER_MAX_MULTI_ERR_DEVICES) + return 0; + + dev = info->dev[i]; + aer = dev->aer_cap; + type = pci_pcie_type(dev); /* Must reset in this function */ info->status = 0; @@ -1090,19 +1431,16 @@ int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) return 0; /* Get First Error Pointer */ - pci_read_config_dword(dev, aer + PCI_ERR_CAP, &temp); - info->first_error = PCI_ERR_CAP_FEP(temp); + pci_read_config_dword(dev, aer + PCI_ERR_CAP, &aercc); + info->first_error = PCI_ERR_CAP_FEP(aercc); - if (info->status & AER_LOG_TLP_MASKS) { + if (tlp_header_logged(info->status, aercc)) { info->tlp_header_valid = 1; - pci_read_config_dword(dev, - aer + PCI_ERR_HEADER_LOG, &info->tlp.dw0); - pci_read_config_dword(dev, - aer + PCI_ERR_HEADER_LOG + 4, &info->tlp.dw1); - pci_read_config_dword(dev, - aer + PCI_ERR_HEADER_LOG + 8, &info->tlp.dw2); - pci_read_config_dword(dev, - aer + PCI_ERR_HEADER_LOG + 12, &info->tlp.dw3); + pcie_read_tlp_log(dev, aer + PCI_ERR_HEADER_LOG, + aer + PCI_ERR_PREFIX_LOG, + aer_tlp_log_len(dev, aercc), + aercc & PCI_ERR_CAP_TLP_LOG_FLIT, + &info->tlp); } } @@ -1113,74 +1451,98 @@ 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. */ + /* Report all before handling them, to not lose 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); + if (aer_get_device_error_info(e_info, i)) + aer_print_error(e_info, i); } 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)) + if (aer_get_device_error_info(e_info, i)) 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 + * aer_isr_one_error_type - consume a Correctable or Uncorrectable Error + * detected by Root Port or RCEC + * @root: pointer to Root Port or RCEC that signaled AER interrupt + * @info: pointer to AER error info */ -static void aer_isr_one_error(struct aer_rpc *rpc, - struct aer_err_source *e_src) +static void aer_isr_one_error_type(struct pci_dev *root, + struct aer_err_info *info) { - struct pci_dev *pdev = rpc->rpd; - struct aer_err_info e_info; + bool found; - pci_rootport_aer_stats_incr(pdev, e_src); + found = find_source_device(root, info); /* - * There is a possibility that both correctable error and - * uncorrectable error being logged. Report correctable error first. + * If we're going to log error messages, we've already set + * "info->root_ratelimit_print" and "info->ratelimit_print[i]" to + * non-zero (which enables printing) because this is either an + * ERR_FATAL or we found a device with an error logged in its AER + * Capability. + * + * If we didn't find the Error Source device, at least log the + * Requester ID from the ERR_* Message received by the Root Port or + * RCEC, ratelimited by the RP or RCEC. */ - 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 (info->root_ratelimit_print || + (!found && aer_ratelimit(root, info->severity))) + aer_print_source(root, info, found); - 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 (found) + aer_process_err_devices(info); +} - if (e_src->status & PCI_ERR_ROOT_FATAL_RCV) - e_info.severity = AER_FATAL; - else - e_info.severity = AER_NONFATAL; +/** + * aer_isr_one_error - consume error(s) signaled by an AER interrupt from + * Root Port or RCEC + * @root: pointer to Root Port or RCEC that signaled AER interrupt + * @e_src: pointer to an error source + */ +static void aer_isr_one_error(struct pci_dev *root, + struct aer_err_source *e_src) +{ + u32 status = e_src->status; - if (e_src->status & PCI_ERR_ROOT_MULTI_UNCOR_RCV) - e_info.multi_error_valid = 1; - else - e_info.multi_error_valid = 0; + pci_rootport_aer_stats_incr(root, e_src); - aer_print_port_info(pdev, &e_info); + /* + * There is a possibility that both correctable error and + * uncorrectable error being logged. Report correctable error first. + */ + if (status & PCI_ERR_ROOT_COR_RCV) { + int multi = status & PCI_ERR_ROOT_MULTI_COR_RCV; + struct aer_err_info e_info = { + .id = ERR_COR_ID(e_src->id), + .severity = AER_CORRECTABLE, + .level = KERN_WARNING, + .multi_error_valid = multi ? 1 : 0, + }; + + aer_isr_one_error_type(root, &e_info); + } - if (find_source_device(pdev, &e_info)) - aer_process_err_devices(&e_info); + if (status & PCI_ERR_ROOT_UNCOR_RCV) { + int fatal = status & PCI_ERR_ROOT_FATAL_RCV; + int multi = status & PCI_ERR_ROOT_MULTI_UNCOR_RCV; + struct aer_err_info e_info = { + .id = ERR_UNCOR_ID(e_src->id), + .severity = fatal ? AER_FATAL : AER_NONFATAL, + .level = KERN_ERR, + .multi_error_valid = multi ? 1 : 0, + }; + + aer_isr_one_error_type(root, &e_info); } } /** - * aer_isr - consume errors detected by root port + * aer_isr - consume errors detected by Root Port * @irq: IRQ assigned to Root Port * @context: pointer to Root Port data structure * - * Invoked, as DPC, when root port records new detected error + * Invoked, as DPC, when Root Port records new detected error */ static irqreturn_t aer_isr(int irq, void *context) { @@ -1192,7 +1554,7 @@ static irqreturn_t aer_isr(int irq, void *context) return IRQ_NONE; while (kfifo_get(&rpc->aer_fifo, &e_src)) - aer_isr_one_error(rpc, &e_src); + aer_isr_one_error(rpc->rpd, &e_src); return IRQ_HANDLED; } @@ -1224,40 +1586,26 @@ static irqreturn_t aer_irq(int irq, void *context) return IRQ_WAKE_THREAD; } -static int set_device_error_reporting(struct pci_dev *dev, void *data) +static void aer_enable_irq(struct pci_dev *pdev) { - bool enable = *((bool *)data); - int type = pci_pcie_type(dev); - - if ((type == PCI_EXP_TYPE_ROOT_PORT) || - (type == PCI_EXP_TYPE_RC_EC) || - (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); - } + int aer = pdev->aer_cap; + u32 reg32; - return 0; + /* Enable Root Port's interrupt in response to error messages */ + pci_read_config_dword(pdev, aer + PCI_ERR_ROOT_COMMAND, ®32); + reg32 |= ROOT_PORT_INTR_ON_MESG_MASK; + pci_write_config_dword(pdev, aer + PCI_ERR_ROOT_COMMAND, reg32); } -/** - * 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) +static void aer_disable_irq(struct pci_dev *pdev) { - set_device_error_reporting(dev, &enable); - - if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_EC) - pcie_walk_rcec(dev, set_device_error_reporting, &enable); - else if (dev->subordinate) - pci_walk_bus(dev->subordinate, set_device_error_reporting, - &enable); + int aer = pdev->aer_cap; + u32 reg32; + /* Disable Root Port's interrupt in response to error messages */ + pci_read_config_dword(pdev, aer + PCI_ERR_ROOT_COMMAND, ®32); + reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK; + pci_write_config_dword(pdev, aer + PCI_ERR_ROOT_COMMAND, reg32); } /** @@ -1289,16 +1637,7 @@ static void aer_enable_rootport(struct aer_rpc *rpc) pci_read_config_dword(pdev, aer + PCI_ERR_UNCOR_STATUS, ®32); pci_write_config_dword(pdev, aer + 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 + PCI_ERR_ROOT_COMMAND, ®32); - reg32 |= ROOT_PORT_INTR_ON_MESG_MASK; - pci_write_config_dword(pdev, aer + PCI_ERR_ROOT_COMMAND, reg32); + aer_enable_irq(pdev); } /** @@ -1313,16 +1652,7 @@ static void aer_disable_rootport(struct aer_rpc *rpc) int aer = pdev->aer_cap; u32 reg32; - /* - * Disable error reporting for the root port device and downstream port - * devices. - */ - set_downstream_devices_error_reporting(pdev, false); - - /* Disable Root's interrupt in response to error messages */ - pci_read_config_dword(pdev, aer + PCI_ERR_ROOT_COMMAND, ®32); - reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK; - pci_write_config_dword(pdev, aer + PCI_ERR_ROOT_COMMAND, reg32); + aer_disable_irq(pdev); /* Clear Root's error status reg */ pci_read_config_dword(pdev, aer + PCI_ERR_ROOT_STATUS, ®32); @@ -1380,11 +1710,28 @@ static int aer_probe(struct pcie_device *dev) return status; } + cxl_rch_enable_rcec(port); aer_enable_rootport(rpc); pci_info(port, "enabled with IRQ %d\n", dev->irq); return 0; } +static int aer_suspend(struct pcie_device *dev) +{ + struct aer_rpc *rpc = get_service_data(dev); + + aer_disable_rootport(rpc); + return 0; +} + +static int aer_resume(struct pcie_device *dev) +{ + struct aer_rpc *rpc = get_service_data(dev); + + aer_enable_rootport(rpc); + return 0; +} + /** * aer_root_reset - reset Root Port hierarchy, RCEC, or RCiEP * @dev: pointer to Root Port, RCEC, or RCiEP @@ -1417,12 +1764,8 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev) */ aer = root ? root->aer_cap : 0; - if ((host->native_aer || pcie_ports_native) && aer) { - /* Disable Root's interrupt in response to error messages */ - pci_read_config_dword(root, aer + PCI_ERR_ROOT_COMMAND, ®32); - reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK; - pci_write_config_dword(root, aer + PCI_ERR_ROOT_COMMAND, reg32); - } + if ((host->native_aer || pcie_ports_native) && aer) + aer_disable_irq(root); if (type == PCI_EXP_TYPE_RC_EC || type == PCI_EXP_TYPE_RC_END) { rc = pcie_reset_flr(dev, PCI_RESET_DO_RESET); @@ -1441,10 +1784,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev) pci_read_config_dword(root, aer + PCI_ERR_ROOT_STATUS, ®32); pci_write_config_dword(root, aer + PCI_ERR_ROOT_STATUS, reg32); - /* Enable Root Port's interrupt in response to error messages */ - pci_read_config_dword(root, aer + PCI_ERR_ROOT_COMMAND, ®32); - reg32 |= ROOT_PORT_INTR_ON_MESG_MASK; - pci_write_config_dword(root, aer + PCI_ERR_ROOT_COMMAND, reg32); + aer_enable_irq(root); } return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; @@ -1456,13 +1796,15 @@ static struct pcie_port_service_driver aerdriver = { .service = PCIE_PORT_SERVICE_AER, .probe = aer_probe, + .suspend = aer_suspend, + .resume = aer_resume, .remove = aer_remove, }; /** - * pcie_aer_init - register AER root service driver + * pcie_aer_init - register AER service driver * - * Invoked when AER root service driver is loaded. + * Invoked when AER service driver is loaded. */ int __init pcie_aer_init(void) { |