diff options
Diffstat (limited to 'drivers/pci/pcie')
| -rw-r--r-- | drivers/pci/pcie/aer.c | 515 | ||||
| -rw-r--r-- | drivers/pci/pcie/aspm.c | 17 | ||||
| -rw-r--r-- | drivers/pci/pcie/bwctrl.c | 92 | ||||
| -rw-r--r-- | drivers/pci/pcie/dpc.c | 93 | ||||
| -rw-r--r-- | drivers/pci/pcie/err.c | 1 | ||||
| -rw-r--r-- | drivers/pci/pcie/portdrv.c | 8 | ||||
| -rw-r--r-- | drivers/pci/pcie/ptm.c | 302 | ||||
| -rw-r--r-- | drivers/pci/pcie/tlp.c | 60 |
8 files changed, 790 insertions, 298 deletions
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 508474e17183..70ac66188367 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> @@ -27,6 +28,7 @@ #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/kfifo.h> +#include <linux/ratelimit.h> #include <linux/slab.h> #include <acpi/apei.h> #include <acpi/ghes.h> @@ -35,6 +37,9 @@ #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 */ @@ -50,15 +55,15 @@ 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). */ @@ -76,14 +81,18 @@ 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| \ @@ -138,7 +147,7 @@ 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) { @@ -159,10 +168,10 @@ 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) { @@ -283,10 +292,10 @@ 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) { @@ -373,13 +382,18 @@ 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); + + 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); @@ -394,8 +408,8 @@ 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 @@ -533,10 +547,10 @@ 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], \ @@ -547,7 +561,7 @@ 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) @@ -568,7 +582,7 @@ 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) @@ -595,7 +609,7 @@ 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 || @@ -613,31 +627,136 @@ 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++; + 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; } @@ -649,54 +768,88 @@ 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) +{ + 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 __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) +{ + 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) { - int layer, agent; - int id = pci_dev_id(dev); - const char *level; + 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", @@ -707,38 +860,21 @@ 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) - pcie_print_tlp_log(dev, &info->tlp, dev_fmt(" ")); + 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 message received from %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 @@ -761,40 +897,48 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity, { 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; + info.level = KERN_ERR; 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); + 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) - pcie_print_tlp_log(dev, &aer->header_log, dev_fmt(" ")); - - 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(" ")); } EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL"); @@ -805,12 +949,27 @@ EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL"); */ 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; } /** @@ -825,8 +984,8 @@ 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)) { @@ -834,15 +993,15 @@ static bool is_error_source(struct pci_dev *dev, struct aer_err_info *e_info) 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. @@ -894,9 +1053,9 @@ 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 @@ -904,7 +1063,7 @@ 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; @@ -922,15 +1081,8 @@ 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) { - u8 bus = e_info->id >> 8; - u8 devfn = e_info->id & 0xff; - - pci_info(parent, "found no error details for %04x:%02x:%02x.%d\n", - pci_domain_nr(parent->bus), bus, PCI_SLOT(devfn), - PCI_FUNC(devfn)); + if (!e_info->error_dev_num) return false; - } return true; } @@ -938,9 +1090,9 @@ static bool find_source_device(struct pci_dev *parent, /** * pci_aer_unmask_internal_errors - unmask internal errors - * @dev: pointer to the pcie_dev data structure + * @dev: pointer to the pci_dev data structure * - * Unmasks internal errors in the Uncorrectable and Correctable Error + * Unmask internal errors in the Uncorrectable and Correctable Error * Mask registers. * * Note: AER must be enabled and supported by the device which must be @@ -1003,7 +1155,7 @@ static int cxl_rch_handle_error_iter(struct pci_dev *dev, void *data) if (!is_cxl_mem_dev(dev) || !cxl_error_is_native(dev)) return 0; - /* protect dev->driver */ + /* Protect dev->driver */ device_lock(&dev->dev); err_handler = dev->driver ? dev->driver->err_handler : NULL; @@ -1137,9 +1289,10 @@ 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; } pci_print_aer(pdev, entry.severity, entry.regs); @@ -1195,19 +1348,26 @@ 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; + 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; info->tlp_header_valid = 0; @@ -1245,6 +1405,7 @@ int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) 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); } } @@ -1256,74 +1417,98 @@ 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) { @@ -1335,7 +1520,7 @@ 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; } @@ -1383,7 +1568,7 @@ static void aer_disable_irq(struct pci_dev *pdev) int aer = pdev->aer_cap; u32 reg32; - /* Disable Root's interrupt in response to error messages */ + /* 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); @@ -1583,9 +1768,9 @@ static struct pcie_port_service_driver aerdriver = { }; /** - * 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) { diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index da3e7edcf49d..29fcb0689a91 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1270,16 +1270,16 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) parent_link = link->parent; /* - * link->downstream is a pointer to the pci_dev of function 0. If - * we remove that function, the pci_dev is about to be deallocated, - * so we can't use link->downstream again. Free the link state to - * avoid this. + * Free the parent link state, no later than function 0 (i.e. + * link->downstream) being removed. * - * If we're removing a non-0 function, it's possible we could - * retain the link state, but PCIe r6.0, sec 7.5.3.7, recommends - * programming the same ASPM Control value for all functions of - * multi-function devices, so disable ASPM for all of them. + * Do not free the link state any earlier. If function 0 is a + * switch upstream port, this link state is parent_link to all + * subordinate ones. */ + if (pdev != link->downstream) + goto out; + pcie_config_aspm_link(link, 0); list_del(&link->sibling); free_link_state(link); @@ -1290,6 +1290,7 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) pcie_config_aspm_path(parent_link); } + out: mutex_unlock(&aspm_lock); up_read(&pci_bus_sem); } diff --git a/drivers/pci/pcie/bwctrl.c b/drivers/pci/pcie/bwctrl.c index 0a5e7efbce2c..36f939f23d34 100644 --- a/drivers/pci/pcie/bwctrl.c +++ b/drivers/pci/pcie/bwctrl.c @@ -38,24 +38,14 @@ /** * struct pcie_bwctrl_data - PCIe bandwidth controller * @set_speed_mutex: Serializes link speed changes - * @lbms_count: Count for LBMS (since last reset) * @cdev: Thermal cooling device associated with the port */ struct pcie_bwctrl_data { struct mutex set_speed_mutex; - atomic_t lbms_count; struct thermal_cooling_device *cdev; }; -/* - * Prevent port removal during LBMS count accessors and Link Speed changes. - * - * These have to be differentiated because pcie_bwctrl_change_speed() calls - * pcie_retrain_link() which uses LBMS count reset accessor on success - * (using just one rwsem triggers "possible recursive locking detected" - * warning). - */ -static DECLARE_RWSEM(pcie_bwctrl_lbms_rwsem); +/* Prevent port removal during Link Speed changes. */ static DECLARE_RWSEM(pcie_bwctrl_setspeed_rwsem); static bool pcie_valid_speed(enum pci_bus_speed speed) @@ -113,7 +103,7 @@ static u16 pcie_bwctrl_select_speed(struct pci_dev *port, enum pci_bus_speed spe up_read(&pci_bus_sem); } if (!supported_speeds) - return PCI_EXP_LNKCAP2_SLS_2_5GB; + supported_speeds = PCI_EXP_LNKCAP2_SLS_2_5GB; return pcie_supported_speeds2target_speed(supported_speeds & desired_speeds); } @@ -127,18 +117,7 @@ static int pcie_bwctrl_change_speed(struct pci_dev *port, u16 target_speed, bool if (ret != PCIBIOS_SUCCESSFUL) return pcibios_err_to_errno(ret); - ret = pcie_retrain_link(port, use_lt); - if (ret < 0) - return ret; - - /* - * Ensure link speed updates also with platforms that have problems - * with notifications. - */ - if (port->subordinate) - pcie_update_link_speed(port->subordinate); - - return 0; + return pcie_retrain_link(port, use_lt); } /** @@ -202,15 +181,14 @@ int pcie_set_target_speed(struct pci_dev *port, enum pci_bus_speed speed_req, static void pcie_bwnotif_enable(struct pcie_device *srv) { - struct pcie_bwctrl_data *data = srv->port->link_bwctrl; struct pci_dev *port = srv->port; u16 link_status; int ret; - /* Count LBMS seen so far as one */ + /* Note if LBMS has been seen so far */ ret = pcie_capability_read_word(port, PCI_EXP_LNKSTA, &link_status); if (ret == PCIBIOS_SUCCESSFUL && link_status & PCI_EXP_LNKSTA_LBMS) - atomic_inc(&data->lbms_count); + set_bit(PCI_LINK_LBMS_SEEN, &port->priv_flags); pcie_capability_set_word(port, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_LBMIE | PCI_EXP_LNKCTL_LABIE); @@ -233,7 +211,6 @@ static void pcie_bwnotif_disable(struct pci_dev *port) static irqreturn_t pcie_bwnotif_irq(int irq, void *context) { struct pcie_device *srv = context; - struct pcie_bwctrl_data *data = srv->port->link_bwctrl; struct pci_dev *port = srv->port; u16 link_status, events; int ret; @@ -247,7 +224,7 @@ static irqreturn_t pcie_bwnotif_irq(int irq, void *context) return IRQ_NONE; if (events & PCI_EXP_LNKSTA_LBMS) - atomic_inc(&data->lbms_count); + set_bit(PCI_LINK_LBMS_SEEN, &port->priv_flags); pcie_capability_write_word(port, PCI_EXP_LNKSTA, events); @@ -262,31 +239,10 @@ static irqreturn_t pcie_bwnotif_irq(int irq, void *context) return IRQ_HANDLED; } -void pcie_reset_lbms_count(struct pci_dev *port) +void pcie_reset_lbms(struct pci_dev *port) { - struct pcie_bwctrl_data *data; - - guard(rwsem_read)(&pcie_bwctrl_lbms_rwsem); - data = port->link_bwctrl; - if (data) - atomic_set(&data->lbms_count, 0); - else - pcie_capability_write_word(port, PCI_EXP_LNKSTA, - PCI_EXP_LNKSTA_LBMS); -} - -int pcie_lbms_count(struct pci_dev *port, unsigned long *val) -{ - struct pcie_bwctrl_data *data; - - guard(rwsem_read)(&pcie_bwctrl_lbms_rwsem); - data = port->link_bwctrl; - if (!data) - return -ENOTTY; - - *val = atomic_read(&data->lbms_count); - - return 0; + clear_bit(PCI_LINK_LBMS_SEEN, &port->priv_flags); + pcie_capability_write_word(port, PCI_EXP_LNKSTA, PCI_EXP_LNKSTA_LBMS); } static int pcie_bwnotif_probe(struct pcie_device *srv) @@ -294,6 +250,10 @@ static int pcie_bwnotif_probe(struct pcie_device *srv) struct pci_dev *port = srv->port; int ret; + /* Can happen if we run out of bus numbers during enumeration. */ + if (!port->subordinate) + return -ENODEV; + struct pcie_bwctrl_data *data = devm_kzalloc(&srv->device, sizeof(*data), GFP_KERNEL); if (!data) @@ -304,18 +264,16 @@ static int pcie_bwnotif_probe(struct pcie_device *srv) return ret; scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) { - scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) { - port->link_bwctrl = data; - - ret = request_irq(srv->irq, pcie_bwnotif_irq, - IRQF_SHARED, "PCIe bwctrl", srv); - if (ret) { - port->link_bwctrl = NULL; - return ret; - } + port->link_bwctrl = data; - pcie_bwnotif_enable(srv); + ret = request_irq(srv->irq, pcie_bwnotif_irq, + IRQF_SHARED, "PCIe bwctrl", srv); + if (ret) { + port->link_bwctrl = NULL; + return ret; } + + pcie_bwnotif_enable(srv); } pci_dbg(port, "enabled with IRQ %d\n", srv->irq); @@ -335,13 +293,11 @@ static void pcie_bwnotif_remove(struct pcie_device *srv) pcie_cooling_device_unregister(data->cdev); scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) { - scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) { - pcie_bwnotif_disable(srv->port); + pcie_bwnotif_disable(srv->port); - free_irq(srv->irq, srv); + free_irq(srv->irq, srv); - srv->port->link_bwctrl = NULL; - } + srv->port->link_bwctrl = NULL; } } diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index 242cabd5eeeb..fc18349614d7 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -219,8 +219,10 @@ static void dpc_process_rp_pio_error(struct pci_dev *pdev) goto clear_status; pcie_read_tlp_log(pdev, cap + PCI_EXP_DPC_RP_PIO_HEADER_LOG, cap + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG, - dpc_tlp_log_len(pdev), &tlp_log); - pcie_print_tlp_log(pdev, &tlp_log, dev_fmt("")); + dpc_tlp_log_len(pdev), + pdev->subordinate->flit_mode, + &tlp_log); + pcie_print_tlp_log(pdev, &tlp_log, KERN_ERR, dev_fmt("")); if (pdev->dpc_rp_log_size < PCIE_STD_NUM_TLP_HEADERLOG + 1) goto clear_status; @@ -250,46 +252,59 @@ static int dpc_get_aer_uncorrect_severity(struct pci_dev *dev, else info->severity = AER_NONFATAL; + info->level = KERN_ERR; + + info->dev[0] = dev; + info->error_dev_num = 1; + return 1; } void dpc_process_error(struct pci_dev *pdev) { u16 cap = pdev->dpc_cap, status, source, reason, ext_reason; - struct aer_err_info info; + struct aer_err_info info = {}; pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status); - pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, &source); - - pci_info(pdev, "containment event, status:%#06x source:%#06x\n", - status, source); reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN; - ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT; - pci_warn(pdev, "%s detected\n", - (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR) ? - "unmasked uncorrectable error" : - (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE) ? - "ERR_NONFATAL" : - (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE) ? - "ERR_FATAL" : - (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) ? - "RP PIO error" : - (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER) ? - "software trigger" : - "reserved error"); - - /* show RP PIO error detail information */ - if (pdev->dpc_rp_extensions && - reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT && - ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) - dpc_process_rp_pio_error(pdev); - else if (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR && - dpc_get_aer_uncorrect_severity(pdev, &info) && - aer_get_device_error_info(pdev, &info)) { - aer_print_error(pdev, &info); - pci_aer_clear_nonfatal_status(pdev); - pci_aer_clear_fatal_status(pdev); + + switch (reason) { + case PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR: + pci_warn(pdev, "containment event, status:%#06x: unmasked uncorrectable error detected\n", + status); + if (dpc_get_aer_uncorrect_severity(pdev, &info) && + aer_get_device_error_info(&info, 0)) { + aer_print_error(&info, 0); + pci_aer_clear_nonfatal_status(pdev); + pci_aer_clear_fatal_status(pdev); + } + break; + case PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE: + case PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE: + pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, + &source); + pci_warn(pdev, "containment event, status:%#06x, %s received from %04x:%02x:%02x.%d\n", + status, + (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE) ? + "ERR_FATAL" : "ERR_NONFATAL", + pci_domain_nr(pdev->bus), PCI_BUS_NUM(source), + PCI_SLOT(source), PCI_FUNC(source)); + break; + case PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT: + ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT; + pci_warn(pdev, "containment event, status:%#06x: %s detected\n", + status, + (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) ? + "RP PIO error" : + (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER) ? + "software trigger" : + "reserved error"); + /* show RP PIO error detail information */ + if (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO && + pdev->dpc_rp_extensions) + dpc_process_rp_pio_error(pdev); + break; } } @@ -398,11 +413,21 @@ void pci_dpc_init(struct pci_dev *pdev) /* Quirks may set dpc_rp_log_size if device or firmware is buggy */ if (!pdev->dpc_rp_log_size) { + u16 flags; + int ret; + + ret = pcie_capability_read_word(pdev, PCI_EXP_FLAGS, &flags); + if (ret) + return; + pdev->dpc_rp_log_size = FIELD_GET(PCI_EXP_DPC_RP_PIO_LOG_SIZE, cap); + if (FIELD_GET(PCI_EXP_FLAGS_FLIT, flags)) + pdev->dpc_rp_log_size += FIELD_GET(PCI_EXP_DPC_RP_PIO_LOG_SIZE4, + cap) << 4; + if (pdev->dpc_rp_log_size < PCIE_STD_NUM_TLP_HEADERLOG || - pdev->dpc_rp_log_size > PCIE_STD_NUM_TLP_HEADERLOG + 1 + - PCIE_STD_MAX_TLP_PREFIXLOG) { + pdev->dpc_rp_log_size > PCIE_STD_MAX_TLP_HEADERLOG + 1) { pci_err(pdev, "RP PIO log size %u is invalid\n", pdev->dpc_rp_log_size); pdev->dpc_rp_log_size = 0; diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index 31090770fffc..de6381c690f5 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -271,7 +271,6 @@ failed: pci_uevent_ers(bridge, PCI_ERS_RESULT_DISCONNECT); - /* TODO: Should kernel panic here? */ pci_info(bridge, "device recovery failed\n"); return status; diff --git a/drivers/pci/pcie/portdrv.c b/drivers/pci/pcie/portdrv.c index 02e73099bad0..e8318fd5f6ed 100644 --- a/drivers/pci/pcie/portdrv.c +++ b/drivers/pci/pcie/portdrv.c @@ -228,10 +228,12 @@ static int get_port_device_capability(struct pci_dev *dev) /* * Disable hot-plug interrupts in case they have been enabled - * by the BIOS and the hot-plug service driver is not loaded. + * by the BIOS and the hot-plug service driver won't be loaded + * to handle them. */ - pcie_capability_clear_word(dev, PCI_EXP_SLTCTL, - PCI_EXP_SLTCTL_CCIE | PCI_EXP_SLTCTL_HPIE); + if (!IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)) + pcie_capability_clear_word(dev, PCI_EXP_SLTCTL, + PCI_EXP_SLTCTL_CCIE | PCI_EXP_SLTCTL_HPIE); } #ifdef CONFIG_PCIEAER diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c index 7cfb6c0d5dcb..4bd73f038ffb 100644 --- a/drivers/pci/pcie/ptm.c +++ b/drivers/pci/pcie/ptm.c @@ -5,6 +5,7 @@ */ #include <linux/bitfield.h> +#include <linux/debugfs.h> #include <linux/module.h> #include <linux/init.h> #include <linux/pci.h> @@ -252,3 +253,304 @@ bool pcie_ptm_enabled(struct pci_dev *dev) return dev->ptm_enabled; } EXPORT_SYMBOL(pcie_ptm_enabled); + +#if IS_ENABLED(CONFIG_DEBUG_FS) +static ssize_t context_update_write(struct file *file, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct pci_ptm_debugfs *ptm_debugfs = file->private_data; + char buf[7]; + int ret; + u8 mode; + + if (!ptm_debugfs->ops->context_update_write) + return -EOPNOTSUPP; + + if (count < 1 || count >= sizeof(buf)) + return -EINVAL; + + ret = copy_from_user(buf, ubuf, count); + if (ret) + return -EFAULT; + + buf[count] = '\0'; + + if (sysfs_streq(buf, "auto")) + mode = PCIE_PTM_CONTEXT_UPDATE_AUTO; + else if (sysfs_streq(buf, "manual")) + mode = PCIE_PTM_CONTEXT_UPDATE_MANUAL; + else + return -EINVAL; + + mutex_lock(&ptm_debugfs->lock); + ret = ptm_debugfs->ops->context_update_write(ptm_debugfs->pdata, mode); + mutex_unlock(&ptm_debugfs->lock); + if (ret) + return ret; + + return count; +} + +static ssize_t context_update_read(struct file *file, char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct pci_ptm_debugfs *ptm_debugfs = file->private_data; + char buf[8]; /* Extra space for NULL termination at the end */ + ssize_t pos; + u8 mode; + + if (!ptm_debugfs->ops->context_update_read) + return -EOPNOTSUPP; + + mutex_lock(&ptm_debugfs->lock); + ptm_debugfs->ops->context_update_read(ptm_debugfs->pdata, &mode); + mutex_unlock(&ptm_debugfs->lock); + + if (mode == PCIE_PTM_CONTEXT_UPDATE_AUTO) + pos = scnprintf(buf, sizeof(buf), "auto\n"); + else + pos = scnprintf(buf, sizeof(buf), "manual\n"); + + return simple_read_from_buffer(ubuf, count, ppos, buf, pos); +} + +static const struct file_operations context_update_fops = { + .open = simple_open, + .read = context_update_read, + .write = context_update_write, +}; + +static int context_valid_get(void *data, u64 *val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + bool valid; + int ret; + + if (!ptm_debugfs->ops->context_valid_read) + return -EOPNOTSUPP; + + mutex_lock(&ptm_debugfs->lock); + ret = ptm_debugfs->ops->context_valid_read(ptm_debugfs->pdata, &valid); + mutex_unlock(&ptm_debugfs->lock); + if (ret) + return ret; + + *val = valid; + + return 0; +} + +static int context_valid_set(void *data, u64 val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + int ret; + + if (!ptm_debugfs->ops->context_valid_write) + return -EOPNOTSUPP; + + mutex_lock(&ptm_debugfs->lock); + ret = ptm_debugfs->ops->context_valid_write(ptm_debugfs->pdata, !!val); + mutex_unlock(&ptm_debugfs->lock); + + return ret; +} + +DEFINE_DEBUGFS_ATTRIBUTE(context_valid_fops, context_valid_get, + context_valid_set, "%llu\n"); + +static int local_clock_get(void *data, u64 *val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + u64 clock; + int ret; + + if (!ptm_debugfs->ops->local_clock_read) + return -EOPNOTSUPP; + + ret = ptm_debugfs->ops->local_clock_read(ptm_debugfs->pdata, &clock); + if (ret) + return ret; + + *val = clock; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(local_clock_fops, local_clock_get, NULL, "%llu\n"); + +static int master_clock_get(void *data, u64 *val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + u64 clock; + int ret; + + if (!ptm_debugfs->ops->master_clock_read) + return -EOPNOTSUPP; + + ret = ptm_debugfs->ops->master_clock_read(ptm_debugfs->pdata, &clock); + if (ret) + return ret; + + *val = clock; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(master_clock_fops, master_clock_get, NULL, "%llu\n"); + +static int t1_get(void *data, u64 *val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + u64 clock; + int ret; + + if (!ptm_debugfs->ops->t1_read) + return -EOPNOTSUPP; + + ret = ptm_debugfs->ops->t1_read(ptm_debugfs->pdata, &clock); + if (ret) + return ret; + + *val = clock; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(t1_fops, t1_get, NULL, "%llu\n"); + +static int t2_get(void *data, u64 *val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + u64 clock; + int ret; + + if (!ptm_debugfs->ops->t2_read) + return -EOPNOTSUPP; + + ret = ptm_debugfs->ops->t2_read(ptm_debugfs->pdata, &clock); + if (ret) + return ret; + + *val = clock; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(t2_fops, t2_get, NULL, "%llu\n"); + +static int t3_get(void *data, u64 *val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + u64 clock; + int ret; + + if (!ptm_debugfs->ops->t3_read) + return -EOPNOTSUPP; + + ret = ptm_debugfs->ops->t3_read(ptm_debugfs->pdata, &clock); + if (ret) + return ret; + + *val = clock; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(t3_fops, t3_get, NULL, "%llu\n"); + +static int t4_get(void *data, u64 *val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + u64 clock; + int ret; + + if (!ptm_debugfs->ops->t4_read) + return -EOPNOTSUPP; + + ret = ptm_debugfs->ops->t4_read(ptm_debugfs->pdata, &clock); + if (ret) + return ret; + + *val = clock; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(t4_fops, t4_get, NULL, "%llu\n"); + +#define pcie_ptm_create_debugfs_file(pdata, mode, attr) \ + do { \ + if (ops->attr##_visible && ops->attr##_visible(pdata)) \ + debugfs_create_file(#attr, mode, ptm_debugfs->debugfs, \ + ptm_debugfs, &attr##_fops); \ + } while (0) + +/* + * pcie_ptm_create_debugfs() - Create debugfs entries for the PTM context + * @dev: PTM capable component device + * @pdata: Private data of the PTM capable component device + * @ops: PTM callback structure + * + * Create debugfs entries for exposing the PTM context of the PTM capable + * components such as Root Complex and Endpoint controllers. + * + * Return: Pointer to 'struct pci_ptm_debugfs' if success, NULL otherwise. + */ +struct pci_ptm_debugfs *pcie_ptm_create_debugfs(struct device *dev, void *pdata, + const struct pcie_ptm_ops *ops) +{ + struct pci_ptm_debugfs *ptm_debugfs; + char *dirname; + int ret; + + /* Caller must provide check_capability() callback */ + if (!ops->check_capability) + return NULL; + + /* Check for PTM capability before creating debugfs attrbutes */ + ret = ops->check_capability(pdata); + if (!ret) { + dev_dbg(dev, "PTM capability not present\n"); + return NULL; + } + + ptm_debugfs = kzalloc(sizeof(*ptm_debugfs), GFP_KERNEL); + if (!ptm_debugfs) + return NULL; + + dirname = devm_kasprintf(dev, GFP_KERNEL, "pcie_ptm_%s", dev_name(dev)); + if (!dirname) + return NULL; + + ptm_debugfs->debugfs = debugfs_create_dir(dirname, NULL); + ptm_debugfs->pdata = pdata; + ptm_debugfs->ops = ops; + mutex_init(&ptm_debugfs->lock); + + pcie_ptm_create_debugfs_file(pdata, 0644, context_update); + pcie_ptm_create_debugfs_file(pdata, 0644, context_valid); + pcie_ptm_create_debugfs_file(pdata, 0444, local_clock); + pcie_ptm_create_debugfs_file(pdata, 0444, master_clock); + pcie_ptm_create_debugfs_file(pdata, 0444, t1); + pcie_ptm_create_debugfs_file(pdata, 0444, t2); + pcie_ptm_create_debugfs_file(pdata, 0444, t3); + pcie_ptm_create_debugfs_file(pdata, 0444, t4); + + return ptm_debugfs; +} +EXPORT_SYMBOL_GPL(pcie_ptm_create_debugfs); + +/* + * pcie_ptm_destroy_debugfs() - Destroy debugfs entries for the PTM context + * @ptm_debugfs: Pointer to the PTM debugfs struct + */ +void pcie_ptm_destroy_debugfs(struct pci_ptm_debugfs *ptm_debugfs) +{ + if (!ptm_debugfs) + return; + + mutex_destroy(&ptm_debugfs->lock); + debugfs_remove_recursive(ptm_debugfs->debugfs); +} +EXPORT_SYMBOL_GPL(pcie_ptm_destroy_debugfs); +#endif diff --git a/drivers/pci/pcie/tlp.c b/drivers/pci/pcie/tlp.c index 0860b5da837f..71f8fc9ea2ed 100644 --- a/drivers/pci/pcie/tlp.c +++ b/drivers/pci/pcie/tlp.c @@ -7,6 +7,7 @@ #include <linux/aer.h> #include <linux/array_size.h> +#include <linux/bitfield.h> #include <linux/pci.h> #include <linux/string.h> @@ -21,6 +22,9 @@ */ unsigned int aer_tlp_log_len(struct pci_dev *dev, u32 aercc) { + if (aercc & PCI_ERR_CAP_TLP_LOG_FLIT) + return FIELD_GET(PCI_ERR_CAP_TLP_LOG_SIZE, aercc); + return PCIE_STD_NUM_TLP_HEADERLOG + ((aercc & PCI_ERR_CAP_PREFIX_LOG_PRESENT) ? dev->eetlp_prefix_max : 0); @@ -49,6 +53,7 @@ unsigned int dpc_tlp_log_len(struct pci_dev *dev) * @where: PCI Config offset of TLP Header Log * @where2: PCI Config offset of TLP Prefix Log * @tlp_len: TLP Log length (Header Log + TLP Prefix Log in DWORDs) + * @flit: TLP Logged in Flit mode * @log: TLP Log structure to fill * * Fill @log from TLP Header Log registers, e.g., AER or DPC. @@ -56,28 +61,34 @@ unsigned int dpc_tlp_log_len(struct pci_dev *dev) * Return: 0 on success and filled TLP Log structure, <0 on error. */ int pcie_read_tlp_log(struct pci_dev *dev, int where, int where2, - unsigned int tlp_len, struct pcie_tlp_log *log) + unsigned int tlp_len, bool flit, struct pcie_tlp_log *log) { unsigned int i; int off, ret; - u32 *to; + + if (tlp_len > ARRAY_SIZE(log->dw)) + tlp_len = ARRAY_SIZE(log->dw); memset(log, 0, sizeof(*log)); for (i = 0; i < tlp_len; i++) { - if (i < PCIE_STD_NUM_TLP_HEADERLOG) { + if (i < PCIE_STD_NUM_TLP_HEADERLOG) off = where + i * 4; - to = &log->dw[i]; - } else { + else off = where2 + (i - PCIE_STD_NUM_TLP_HEADERLOG) * 4; - to = &log->prefix[i - PCIE_STD_NUM_TLP_HEADERLOG]; - } - ret = pci_read_config_dword(dev, off, to); + ret = pci_read_config_dword(dev, off, &log->dw[i]); if (ret) return pcibios_err_to_errno(ret); } + /* + * Hard-code non-Flit mode to 4 DWORDs, for now. The exact length + * can only be known if the TLP is parsed. + */ + log->header_len = flit ? tlp_len : 4; + log->flit = flit; + return 0; } @@ -87,29 +98,40 @@ int pcie_read_tlp_log(struct pci_dev *dev, int where, int where2, * pcie_print_tlp_log - Print TLP Header / Prefix Log contents * @dev: PCIe device * @log: TLP Log structure + * @level: Printk log level * @pfx: String prefix * * Prints TLP Header and Prefix Log information held by @log. */ void pcie_print_tlp_log(const struct pci_dev *dev, - const struct pcie_tlp_log *log, const char *pfx) + const struct pcie_tlp_log *log, const char *level, + const char *pfx) { - char buf[11 * (PCIE_STD_NUM_TLP_HEADERLOG + ARRAY_SIZE(log->prefix)) + - sizeof(EE_PREFIX_STR)]; + /* EE_PREFIX_STR fits the extended DW space needed for the Flit mode */ + char buf[11 * PCIE_STD_MAX_TLP_HEADERLOG + 1]; unsigned int i; int len; len = scnprintf(buf, sizeof(buf), "%#010x %#010x %#010x %#010x", log->dw[0], log->dw[1], log->dw[2], log->dw[3]); - if (log->prefix[0]) - len += scnprintf(buf + len, sizeof(buf) - len, EE_PREFIX_STR); - for (i = 0; i < ARRAY_SIZE(log->prefix); i++) { - if (!log->prefix[i]) - break; - len += scnprintf(buf + len, sizeof(buf) - len, - " %#010x", log->prefix[i]); + if (log->flit) { + for (i = PCIE_STD_NUM_TLP_HEADERLOG; i < log->header_len; i++) { + len += scnprintf(buf + len, sizeof(buf) - len, + " %#010x", log->dw[i]); + } + } else { + if (log->prefix[0]) + len += scnprintf(buf + len, sizeof(buf) - len, + EE_PREFIX_STR); + for (i = 0; i < ARRAY_SIZE(log->prefix); i++) { + if (!log->prefix[i]) + break; + len += scnprintf(buf + len, sizeof(buf) - len, + " %#010x", log->prefix[i]); + } } - pci_err(dev, "%sTLP Header: %s\n", pfx, buf); + dev_printk(level, &dev->dev, "%sTLP Header%s: %s\n", pfx, + log->flit ? " (Flit)" : "", buf); } |