diff options
| -rw-r--r-- | Documentation/driver-api/hw-recoverable-errors.rst | 60 | ||||
| -rw-r--r-- | Documentation/driver-api/index.rst | 1 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/core.c | 4 | ||||
| -rw-r--r-- | drivers/acpi/apei/ghes.c | 36 | ||||
| -rw-r--r-- | drivers/pci/pcie/aer.c | 2 | ||||
| -rw-r--r-- | include/linux/vmcore_info.h | 8 | ||||
| -rw-r--r-- | include/uapi/linux/vmcore.h | 9 | ||||
| -rw-r--r-- | kernel/vmcore_info.c | 17 |
8 files changed, 137 insertions, 0 deletions
diff --git a/Documentation/driver-api/hw-recoverable-errors.rst b/Documentation/driver-api/hw-recoverable-errors.rst new file mode 100644 index 000000000000..fc526c3454bd --- /dev/null +++ b/Documentation/driver-api/hw-recoverable-errors.rst @@ -0,0 +1,60 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================================= +Recoverable Hardware Error Tracking in vmcoreinfo +================================================= + +Overview +-------- + +This feature provides a generic infrastructure within the Linux kernel to track +and log recoverable hardware errors. These are hardware recoverable errors +visible that might not cause immediate panics but may influence health, mainly +because new code path will be executed in the kernel. + +By recording counts and timestamps of recoverable errors into the vmcoreinfo +crash dump notes, this infrastructure aids post-mortem crash analysis tools in +correlating hardware events with kernel failures. This enables faster triage +and better understanding of root causes, especially in large-scale cloud +environments where hardware issues are common. + +Benefits +-------- + +- Facilitates correlation of hardware recoverable errors with kernel panics or + unusual code paths that lead to system crashes. +- Provides operators and cloud providers quick insights, improving reliability + and reducing troubleshooting time. +- Complements existing full hardware diagnostics without replacing them. + +Data Exposure and Consumption +----------------------------- + +- The tracked error data consists of per-error-type counts and timestamps of + last occurrence. +- This data is stored in the `hwerror_data` array, categorized by error source + types like CPU, memory, PCI, CXL, and others. +- It is exposed via vmcoreinfo crash dump notes and can be read using tools + like `crash`, `drgn`, or other kernel crash analysis utilities. +- There is no other way to read these data other than from crash dumps. +- These errors are divided by area, which includes CPU, Memory, PCI, CXL and + others. + +Typical usage example (in drgn REPL): + +.. code-block:: python + + >>> prog['hwerror_data'] + (struct hwerror_info[HWERR_RECOV_MAX]){ + { + .count = (int)844, + .timestamp = (time64_t)1752852018, + }, + ... + } + +Enabling +-------- + +- This feature is enabled when CONFIG_VMCORE_INFO is set. + diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index 3e2a270bd828..a35705b44799 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -96,6 +96,7 @@ Subsystem-specific APIs gpio/index hsi hte/index + hw-recoverable-errors i2c iio/index infiniband diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 460e90a1a0b1..08adbf4cd6ed 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -45,6 +45,7 @@ #include <linux/task_work.h> #include <linux/hardirq.h> #include <linux/kexec.h> +#include <linux/vmcore_info.h> #include <asm/fred.h> #include <asm/cpu_device_id.h> @@ -1700,6 +1701,9 @@ noinstr void do_machine_check(struct pt_regs *regs) } out: + /* Given it didn't panic, mark it as recoverable */ + hwerr_log_error_type(HWERR_RECOV_OTHERS); + instrumentation_end(); clear: diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 97ee19f2cae0..92b0e3c391b2 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -43,6 +43,7 @@ #include <linux/uuid.h> #include <linux/ras.h> #include <linux/task_work.h> +#include <linux/vmcore_info.h> #include <acpi/actbl1.h> #include <acpi/ghes.h> @@ -867,6 +868,40 @@ int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd) } EXPORT_SYMBOL_NS_GPL(cxl_cper_kfifo_get, "CXL"); +static void ghes_log_hwerr(int sev, guid_t *sec_type) +{ + if (sev != CPER_SEV_RECOVERABLE) + return; + + if (guid_equal(sec_type, &CPER_SEC_PROC_ARM) || + guid_equal(sec_type, &CPER_SEC_PROC_GENERIC) || + guid_equal(sec_type, &CPER_SEC_PROC_IA)) { + hwerr_log_error_type(HWERR_RECOV_CPU); + return; + } + + if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR) || + guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID) || + guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID) || + guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) { + hwerr_log_error_type(HWERR_RECOV_CXL); + return; + } + + if (guid_equal(sec_type, &CPER_SEC_PCIE) || + guid_equal(sec_type, &CPER_SEC_PCI_X_BUS)) { + hwerr_log_error_type(HWERR_RECOV_PCI); + return; + } + + if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) { + hwerr_log_error_type(HWERR_RECOV_MEMORY); + return; + } + + hwerr_log_error_type(HWERR_RECOV_OTHERS); +} + static void ghes_do_proc(struct ghes *ghes, const struct acpi_hest_generic_status *estatus) { @@ -888,6 +923,7 @@ static void ghes_do_proc(struct ghes *ghes, if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT) fru_text = gdata->fru_text; + ghes_log_hwerr(sev, sec_type); if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) { struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata); diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 0b5ed4722ac3..e0bcaa896803 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -30,6 +30,7 @@ #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> @@ -765,6 +766,7 @@ static void pci_dev_aer_stats_incr(struct pci_dev *pdev, break; case AER_NONFATAL: 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; diff --git a/include/linux/vmcore_info.h b/include/linux/vmcore_info.h index 37e003ae5262..e71518caacdf 100644 --- a/include/linux/vmcore_info.h +++ b/include/linux/vmcore_info.h @@ -5,6 +5,7 @@ #include <linux/linkage.h> #include <linux/elfcore.h> #include <linux/elf.h> +#include <uapi/linux/vmcore.h> #define CRASH_CORE_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4) #define CRASH_CORE_NOTE_NAME_BYTES ALIGN(sizeof(NN_PRSTATUS), 4) @@ -77,4 +78,11 @@ extern u32 *vmcoreinfo_note; Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len); void final_note(Elf_Word *buf); + +#ifdef CONFIG_VMCORE_INFO +void hwerr_log_error_type(enum hwerr_error_type src); +#else +static inline void hwerr_log_error_type(enum hwerr_error_type src) {}; +#endif + #endif /* LINUX_VMCORE_INFO_H */ diff --git a/include/uapi/linux/vmcore.h b/include/uapi/linux/vmcore.h index 3e9da91866ff..2ba89fafa518 100644 --- a/include/uapi/linux/vmcore.h +++ b/include/uapi/linux/vmcore.h @@ -15,4 +15,13 @@ struct vmcoredd_header { __u8 dump_name[VMCOREDD_MAX_NAME_BYTES]; /* Device dump's name */ }; +enum hwerr_error_type { + HWERR_RECOV_CPU, + HWERR_RECOV_MEMORY, + HWERR_RECOV_PCI, + HWERR_RECOV_CXL, + HWERR_RECOV_OTHERS, + HWERR_RECOV_MAX, +}; + #endif /* _UAPI_VMCORE_H */ diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c index e066d31d08f8..fe9bf8db1922 100644 --- a/kernel/vmcore_info.c +++ b/kernel/vmcore_info.c @@ -31,6 +31,13 @@ u32 *vmcoreinfo_note; /* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */ static unsigned char *vmcoreinfo_data_safecopy; +struct hwerr_info { + atomic_t count; + time64_t timestamp; +}; + +static struct hwerr_info hwerr_data[HWERR_RECOV_MAX]; + Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len) { @@ -118,6 +125,16 @@ phys_addr_t __weak paddr_vmcoreinfo_note(void) } EXPORT_SYMBOL(paddr_vmcoreinfo_note); +void hwerr_log_error_type(enum hwerr_error_type src) +{ + if (src < 0 || src >= HWERR_RECOV_MAX) + return; + + atomic_inc(&hwerr_data[src].count); + WRITE_ONCE(hwerr_data[src].timestamp, ktime_get_real_seconds()); +} +EXPORT_SYMBOL_GPL(hwerr_log_error_type); + static int __init crash_save_vmcoreinfo_init(void) { vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL); |