pci_aer_clear_nonfatal_status() is not called when AER recovery fails. If a new AER error is subsequently reported, the AER driver calls find_source_device() to find the source of the error. It rescans the whole bus and picks the first device reporting an AER error. Because the previous error was never cleared, the error is attributed to the wrong device and AER recovery is started for the wrong device.
Add a kernel boot parameter pci=aer_clear_on_recovery_failure to clear AER error status even when recovery fails, preventing stale errors from causing incorrect device identification on subsequent AER events. Signed-off-by: Yury Murashka <[email protected]> --- Documentation/admin-guide/kernel-parameters.txt | 5 +++++ drivers/pci/pci.c | 2 ++ drivers/pci/pci.h | 2 ++ drivers/pci/pcie/err.c | 13 +++++++++++++ 4 files changed, 22 insertions(+) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 4d0f545fb..5a9e266f5 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5301,6 +5301,11 @@ Kernel parameters nomio [S390] Do not use MIO instructions. norid [S390] ignore the RID field and force use of one PCI domain per PCI function + aer_clear_on_recovery_failure + [PCIE] If the PCIEAER kernel config parameter is + enabled, this kernel boot option can be used to + enable AER errors cleanup even if error recovery + failed. notph [PCIE] If the PCIE_TPH kernel config parameter is enabled, this kernel boot option can be used to disable PCIe TLP Processing Hints support diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index d34266651..701459c62 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -6769,6 +6769,8 @@ static int __init pci_setup(char *str) disable_acs_redir_param = str + 18; } else if (!strncmp(str, "config_acs=", 11)) { config_acs_param = str + 11; + } else if (!strncmp(str, "aer_clear_on_recovery_failure", 29)) { + pci_enable_aer_clear_on_recovery_failure(); } else { pr_err("PCI: Unknown option `%s'\n", str); } diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 4a14f88e5..093a7c896 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -1292,6 +1292,7 @@ int pci_aer_clear_status(struct pci_dev *dev); int pci_aer_raw_clear_status(struct pci_dev *dev); void pci_save_aer_state(struct pci_dev *dev); void pci_restore_aer_state(struct pci_dev *dev); +void pci_enable_aer_clear_on_recovery_failure(void); #else static inline void pci_no_aer(void) { } static inline void pci_aer_init(struct pci_dev *d) { } @@ -1301,6 +1302,7 @@ static inline int pci_aer_clear_status(struct pci_dev *dev) { return -EINVAL; } static inline int pci_aer_raw_clear_status(struct pci_dev *dev) { return -EINVAL; } static inline void pci_save_aer_state(struct pci_dev *dev) { } static inline void pci_restore_aer_state(struct pci_dev *dev) { } +static inline void pci_enable_aer_clear_on_recovery_failure(void) { } #endif #ifdef CONFIG_ACPI diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index bebe4bc11..29d655a34 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -21,6 +21,13 @@ #include "portdrv.h" #include "../pci.h" +static int enable_aer_clear_on_recovery_failure; + +void pci_enable_aer_clear_on_recovery_failure(void) +{ + enable_aer_clear_on_recovery_failure = 1; +} + static pci_ers_result_t merge_result(enum pci_ers_result orig, enum pci_ers_result new) { @@ -289,6 +296,12 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev, return status; failed: + if (enable_aer_clear_on_recovery_failure && + (host->native_aer || pcie_ports_native)) { + pcie_clear_device_status(dev); + pci_aer_clear_nonfatal_status(dev); + } + pci_walk_bridge(bridge, pci_pm_runtime_put, NULL); pci_walk_bridge(bridge, report_perm_failure_detected, NULL); -- 2.51.0
