// SPDX-License-Identifier: GPL-2.0 /* * Implement the AER root port service driver. The driver registers an IRQ * handler. When a root port triggers an AER interrupt, the IRQ handler * collects Root Port status and schedules work. * * Copyright (C) 2006 Intel Corp. * Tom Long Nguyen (tom.l.nguyen@intel.com) * Zhang Yanmin (yanmin.zhang@intel.com) * * (C) Copyright 2009 Hewlett-Packard Development Company, L.P. * Andrew Patterson <andrew.patterson@hp.com>
*/
/* * Fields for all AER capable devices. They indicate the errors * "as seen by this device". Note that this may mean that if an * 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).
*/ /* Counters for different type of correctable errors */
u64 dev_cor_errs[AER_MAX_TYPEOF_COR_ERRS]; /* Counters for different type of fatal uncorrectable errors */
u64 dev_fatal_errs[AER_MAX_TYPEOF_UNCOR_ERRS]; /* Counters for different type of nonfatal uncorrectable errors */
u64 dev_nonfatal_errs[AER_MAX_TYPEOF_UNCOR_ERRS]; /* Total number of ERR_COR sent by this device */
u64 dev_total_cor_errs; /* Total number of ERR_FATAL sent by this device */
u64 dev_total_fatal_errs; /* Total number of ERR_NONFATAL sent by this device */
u64 dev_total_nonfatal_errs;
/* * 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 Root Port itself)
*/
u64 rootport_total_cor_errs;
u64 rootport_total_fatal_errs;
u64 rootport_total_nonfatal_errs;
#define ECRC_POLICY_DEFAULT 0/* ECRC set by BIOS */ #define ECRC_POLICY_OFF 1/* ECRC off for performance */ #define ECRC_POLICY_ON 2/* ECRC on for data integrity */
/** * 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; case ECRC_POLICY_OFF:
disable_ecrc_checking(dev); break; case ECRC_POLICY_ON:
enable_ecrc_checking(dev); break; default: return;
}
}
/** * pcie_ecrc_get_policy - parse kernel command-line ecrc option * @str: ECRC policy from kernel command line to use
*/ void pcie_ecrc_get_policy(char *str)
{ int i;
i = match_string(ecrc_policy_str, ARRAY_SIZE(ecrc_policy_str), str); if (i < 0) return;
/* Clear status bits for ERR_FATAL errors only */
pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_STATUS, &status);
pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_SEVER, &sev);
status &= sev; if (status)
pci_write_config_dword(dev, aer + PCI_ERR_UNCOR_STATUS, status);
}
/** * pci_aer_raw_clear_status - Clear AER error registers. * @dev: the PCI device * * Clear AER error status registers unconditionally, regardless of * whether they're owned by firmware or the OS. * * Return: 0 on success, or negative on failure.
*/ int pci_aer_raw_clear_status(struct pci_dev *dev)
{ int aer = dev->aer_cap;
u32 status; int port_type;
staticconstchar *aer_correctable_error_string[] = { "RxErr", /* Bit Position 0 */
NULL,
NULL,
NULL,
NULL,
NULL, "BadTLP", /* Bit Position 6 */ "BadDLLP", /* Bit Position 7 */ "Rollover", /* Bit Position 8 */
NULL,
NULL,
NULL, "Timeout", /* Bit Position 12 */ "NonFatalErr", /* Bit Position 13 */ "CorrIntErr", /* Bit Position 14 */ "HeaderOF", /* Bit Position 15 */
NULL, /* Bit Position 16 */
NULL, /* Bit Position 17 */
NULL, /* Bit Position 18 */
NULL, /* Bit Position 19 */
NULL, /* Bit Position 20 */
NULL, /* Bit Position 21 */
NULL, /* Bit Position 22 */
NULL, /* Bit Position 23 */
NULL, /* Bit Position 24 */
NULL, /* Bit Position 25 */
NULL, /* Bit Position 26 */
NULL, /* Bit Position 27 */
NULL, /* Bit Position 28 */
NULL, /* Bit Position 29 */
NULL, /* Bit Position 30 */
NULL, /* Bit Position 31 */
};
staticconstchar *aer_uncorrectable_error_string[] = { "Undefined", /* Bit Position 0 */
NULL,
NULL,
NULL, "DLP", /* Bit Position 4 */ "SDES", /* Bit Position 5 */
NULL,
NULL,
NULL,
NULL,
NULL,
NULL, "TLP", /* Bit Position 12 */ "FCP", /* Bit Position 13 */ "CmpltTO", /* Bit Position 14 */ "CmpltAbrt", /* Bit Position 15 */ "UnxCmplt", /* Bit Position 16 */ "RxOF", /* Bit Position 17 */ "MalfTLP", /* Bit Position 18 */ "ECRC", /* Bit Position 19 */ "UnsupReq", /* Bit Position 20 */ "ACSViol", /* Bit Position 21 */ "UncorrIntErr", /* Bit Position 22 */ "BlockedTLP", /* Bit Position 23 */ "AtomicOpBlocked", /* Bit Position 24 */ "TLPBlockedErr", /* Bit Position 25 */ "PoisonTLPBlocked", /* Bit Position 26 */ "DMWrReqBlocked", /* Bit Position 27 */ "IDECheck", /* Bit Position 28 */ "MisIDETLP", /* Bit Position 29 */ "PCRC_CHECK", /* Bit Position 30 */ "TLPXlatBlocked", /* Bit Position 31 */
};
if (aer_severity != AER_CORRECTABLE)
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, info.level,
dev_fmt(" "));
}
EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL");
/** * add_error_device - list device to be handled * @e_info: pointer to error info * @dev: pointer to pci_dev to be added
*/ staticint add_error_device(struct aer_err_info *e_info, struct pci_dev *dev)
{ int i = e_info->error_dev_num;
if (i >= AER_MAX_MULTI_ERR_DEVICES) return -ENOSPC;
/* * 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;
} return0;
}
/** * is_error_source - check whether the device is source of reported error * @dev: pointer to pci_dev to be checked * @e_info: pointer to reported error info
*/ staticbool is_error_source(struct pci_dev *dev, struct aer_err_info *e_info)
{ int aer = dev->aer_cap;
u32 status, mask;
u16 reg16;
/* * When bus ID is equal to 0, it might be a bad ID * reported by Root Port.
*/ if ((PCI_BUS_NUM(e_info->id) != 0) &&
!(dev->bus->bus_flags & PCI_BUS_FLAGS_NO_AERSID)) { /* Device ID match? */ if (e_info->id == pci_dev_id(dev)) returntrue;
/* Continue ID comparing if there is no multiple error */ if (!e_info->multi_error_valid) returnfalse;
}
/* * When either * 1) bus ID is equal to 0. Some ports might lose the bus * ID of error source id; * 2) bus flag PCI_BUS_FLAGS_NO_AERSID is set * 3) There are multiple errors and prior ID comparing fails; * We check AER status registers to find possible reporter.
*/ if (atomic_read(&dev->enable_cnt) == 0) returnfalse;
/* Check if AER is enabled */
pcie_capability_read_word(dev, PCI_EXP_DEVCTL, ®16); if (!(reg16 & PCI_EXP_AER_FLAGS)) returnfalse;
if (!aer) returnfalse;
/* Check if error is recorded */ if (e_info->severity == AER_CORRECTABLE) {
pci_read_config_dword(dev, aer + PCI_ERR_COR_STATUS, &status);
pci_read_config_dword(dev, aer + PCI_ERR_COR_MASK, &mask);
} else {
pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_STATUS, &status);
pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_MASK, &mask);
} if (status & ~mask) returntrue;
if (is_error_source(dev, e_info)) { /* List this device */ if (add_error_device(e_info, dev)) { /* We cannot handle more... Stop iteration */
pci_err(dev, "Exceeded max supported (%d) devices with errors logged\n",
AER_MAX_MULTI_ERR_DEVICES); return1;
}
/* If there is only a single error, stop iteration */ if (!e_info->multi_error_valid) return1;
} return0;
}
/** * 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 as ID * * Return: true if found. * * Invoked by DPC when error is detected at the Root Port. * Caller of this function must set id, severity, and multi_error_valid of * struct aer_err_info pointed by @e_info properly. This function must fill * e_info->error_dev_num and e_info->dev[], based on the given information.
*/ staticbool find_source_device(struct pci_dev *parent, struct aer_err_info *e_info)
{ struct pci_dev *dev = parent; int result;
/* Must reset in this function */
e_info->error_dev_num = 0;
/* Is Root Port an agent that sends error message? */
result = find_device_iter(dev, e_info); if (result) returntrue;
if (!e_info->error_dev_num) returnfalse; returntrue;
}
#ifdef CONFIG_PCIEAER_CXL
/** * 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().
*/ staticvoid pci_aer_unmask_internal_errors(struct pci_dev *dev)
{ int aer = dev->aer_cap;
u32 mask;
staticbool 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)) returnfalse;
/* * 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) returnfalse;
if (info->severity == AER_CORRECTABLE) { if (err_handler->cor_error_detected)
err_handler->cor_error_detected(dev);
} elseif (err_handler->error_detected) { if (info->severity == AER_NONFATAL)
err_handler->error_detected(dev, pci_channel_io_normal); elseif (info->severity == AER_FATAL)
err_handler->error_detected(dev, pci_channel_io_frozen);
}
out:
device_unlock(&dev->dev); return0;
}
staticvoid 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);
}
/** * 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.
*/ staticvoid pci_aer_handle_error(struct pci_dev *dev, struct aer_err_info *info)
{ int aer = dev->aer_cap;
if (info->severity == AER_CORRECTABLE) { /* * Correctable error does not need software intervention. * No need to go through error recovery process.
*/ if (aer)
pci_write_config_dword(dev, aer + PCI_ERR_COR_STATUS,
info->status); if (pcie_aer_is_native(dev)) { struct pci_driver *pdrv = dev->driver;
while (kfifo_get(&aer_recover_ring, &entry)) {
pdev = pci_get_domain_bus_and_slot(entry.domain, entry.bus,
entry.devfn); if (!pdev) {
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);
/* * 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((unsignedlong)entry.regs, sizeof(struct aer_capability_regs));
/* * Mutual exclusion for writers of aer_recover_ring, reader side don't * need lock, because there is only one reader and lock is not needed * between reader and writer.
*/ static DEFINE_SPINLOCK(aer_recover_ring_lock); static DECLARE_WORK(aer_recover_work, aer_recover_work_func);
if (kfifo_in_spinlocked(&aer_recover_ring, &entry, 1,
&aer_recover_ring_lock))
schedule_work(&aer_recover_work); else
pr_err("buffer overflow in recovery for %04x:%02x:%02x.%x\n",
domain, bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
}
EXPORT_SYMBOL_GPL(aer_recover_queue); #endif
/** * aer_get_device_error_info - read error status from dev and store it to info * @info: pointer to structure to store the error record * @i: index into info->dev[] * * 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 aer_err_info *info, int i)
{ struct pci_dev *dev; int type, aer;
u32 aercc;
if (i >= AER_MAX_MULTI_ERR_DEVICES) return0;
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;
/* The device might not support AER */ if (!aer) return0;
if (info->severity == AER_CORRECTABLE) {
pci_read_config_dword(dev, aer + PCI_ERR_COR_STATUS,
&info->status);
pci_read_config_dword(dev, aer + PCI_ERR_COR_MASK,
&info->mask); if (!(info->status & ~info->mask)) return0;
} elseif (type == PCI_EXP_TYPE_ROOT_PORT ||
type == PCI_EXP_TYPE_RC_EC ||
type == PCI_EXP_TYPE_DOWNSTREAM ||
info->severity == AER_NONFATAL) {
/* Link is still healthy for IO reads */
pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_STATUS,
&info->status);
pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_MASK,
&info->mask); if (!(info->status & ~info->mask)) return0;
/* Get First Error Pointer */
pci_read_config_dword(dev, aer + PCI_ERR_CAP, &aercc);
info->first_error = PCI_ERR_CAP_FEP(aercc);
staticinlinevoid aer_process_err_devices(struct aer_err_info *e_info)
{ int i;
/* 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, 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, i))
handle_error_source(e_info->dev[i], e_info);
}
}
/** * 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
*/ staticvoid aer_isr_one_error_type(struct pci_dev *root, struct aer_err_info *info)
{ bool found;
found = find_source_device(root, info);
/* * 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 (info->root_ratelimit_print ||
(!found && aer_ratelimit(root, info->severity)))
aer_print_source(root, info, found);
if (found)
aer_process_err_devices(info);
}
/** * 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
*/ staticvoid aer_isr_one_error(struct pci_dev *root, struct aer_err_source *e_src)
{
u32 status = e_src->status;
pci_rootport_aer_stats_incr(root, e_src);
/* * 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 (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 * @irq: IRQ assigned to Root Port * @context: pointer to Root Port data structure * * Invoked, as DPC, when Root Port records new detected error
*/ static irqreturn_t aer_isr(int irq, void *context)
{ struct pcie_device *dev = (struct pcie_device *)context; struct aer_rpc *rpc = get_service_data(dev); struct aer_err_source e_src;
if (kfifo_is_empty(&rpc->aer_fifo)) return IRQ_NONE;
while (kfifo_get(&rpc->aer_fifo, &e_src))
aer_isr_one_error(rpc->rpd, &e_src); return IRQ_HANDLED;
}
/** * aer_irq - Root Port's ISR * @irq: IRQ assigned to Root Port * @context: pointer to Root Port data structure * * Invoked when Root Port detects AER messages.
*/ static irqreturn_t aer_irq(int irq, void *context)
{ struct pcie_device *pdev = (struct pcie_device *)context; struct aer_rpc *rpc = get_service_data(pdev); struct pci_dev *rp = rpc->rpd; int aer = rp->aer_cap; struct aer_err_source e_src = {};
/** * aer_root_reset - reset Root Port hierarchy, RCEC, or RCiEP * @dev: pointer to Root Port, RCEC, or RCiEP * * Invoked by Port Bus driver when performing reset.
*/ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
{ int type = pci_pcie_type(dev); struct pci_dev *root; int aer; struct pci_host_bridge *host = pci_find_host_bridge(dev->bus);
u32 reg32; int rc;
/* * Only Root Ports and RCECs have AER Root Command and Root Status * registers. If "dev" is an RCiEP, the relevant registers are in * the RCEC.
*/ if (type == PCI_EXP_TYPE_RC_END)
root = dev->rcec; else
root = pcie_find_root_port(dev);
/* * If the platform retained control of AER, an RCiEP may not have * an RCEC visible to us, so dev->rcec ("root") may be NULL. In * that case, firmware is responsible for these registers.
*/
aer = root ? root->aer_cap : 0;
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); if (!rc)
pci_info(dev, "has been reset\n"); else
pci_info(dev, "not reset (no FLR support: %d)\n", rc);
} else {
rc = pci_bus_error_reset(dev);
pci_info(dev, "%s Port link has been reset (%d)\n",
pci_is_root_bus(dev->bus) ? "Root" : "Downstream", rc);
}
/** * pcie_aer_init - register AER service driver * * Invoked when AER service driver is loaded.
*/ int __init pcie_aer_init(void)
{ if (!pci_aer_available()) return -ENXIO; return pcie_port_service_register(&aerdriver);
}
Messung V0.5 in Prozent
¤ Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.0.23Angebot
(Wie Sie bei der Firma Beratungs- und Dienstleistungen beauftragen können 2026-06-08)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.