Introduce a generic infrastructure for tracking recoverable hardware
errors (HW errors that are visible to the OS but does not cause a panic)
and record them for vmcore consumption. This aids post-mortem crash
analysis tools by preserving a count and timestamp for the last
occurrence of such errors. On the other side, correctable errors, which
the OS typically remains unaware of because the underlying hardware
handles them transparently, are less relevant for crash dump
and therefore are NOT tracked in this infrastructure.
Add centralized logging for sources of recoverable hardware
errors based on the subsystem it has been notified.
hwerror_data is write-only at kernel runtime, and it is meant to be read
from vmcore using tools like crash/drgn. For example, this is how it
looks like when opening the crashdump from drgn.
>>> prog['hwerror_data']
(struct hwerror_info[1]){
{
.count = (int)844,
.timestamp = (time64_t)1752852018,
},
...
This helps fleet operators quickly triage whether a crash may be
influenced by hardware recoverable errors (which executes a uncommon
code path in the kernel), especially when recoverable errors occurred
shortly before a panic, such as the bug fixed by
commit ee62ce7a1d90 ("page_pool: Track DMA-mapped pages and unmap them
when destroying the pool")
This is not intended to replace full hardware diagnostics but provides
a fast way to correlate hardware events with kernel panics quickly.
Rare machine check exceptions—like those indicated by mce_flags.p5 or
mce_flags.winchip—are not accounted for in this method, as they fall
outside the intended usage scope for this feature’s user base.
Suggested-by: Tony Luck <tony.l...@intel.com>
Suggested-by: Shuai Xue <xuesh...@linux.alibaba.com>
Signed-off-by: Breno Leitao <lei...@debian.org>
---
Changes in v4:
- Split the error by hardware subsystem instead of kernel
subsystem/driver (Shuai)
- Do not count the corrected errors, only focusing on recoverable errors (Shuai)
- Link to v3:
https://lore.kernel.org/r/20250722-vmcore_hw_error-v3-1-ff0683fc1...@debian.org
Changes in v3:
- Add more information about this feature in the commit message
(Borislav Petkov)
- Renamed the function to hwerr_log_error_type() and use hwerr as
suffix (Borislav Petkov)
- Make the empty function static inline (kernel test robot)
- Link to v2:
https://lore.kernel.org/r/20250721-vmcore_hw_error-v2-1-ab65a6b43...@debian.org
Changes in v2:
- Split the counter by recoverable error (Tony Luck)
- Link to v1:
https://lore.kernel.org/r/20250714-vmcore_hw_error-v1-1-8cf45edb6...@debian.org
---
arch/x86/kernel/cpu/mce/core.c | 4 ++++
drivers/acpi/apei/ghes.c | 36 ++++++++++++++++++++++++++++++++++++
drivers/pci/pcie/aer.c | 2 ++
include/linux/vmcore_info.h | 17 +++++++++++++++++
kernel/vmcore_info.c | 18 ++++++++++++++++++
5 files changed, 77 insertions(+)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 4da4eab56c81d..f85759453f89a 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>
@@ -1690,6 +1691,9 @@ 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_MCE);
+
instrumentation_end();
clear:
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index a0d54993edb3b..562459e9d632e 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 70ac661883672..fe0174b972a7b 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>
@@ -751,6 +752,7 @@ 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 37e003ae52626..538a3635fb1e5 100644
--- a/include/linux/vmcore_info.h
+++ b/include/linux/vmcore_info.h
@@ -77,4 +77,21 @@ 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);
+
+enum hwerr_error_type {
+ HWERR_RECOV_MCE,
+ HWERR_RECOV_CPU,
+ HWERR_RECOV_MEMORY,
+ HWERR_RECOV_PCI,
+ HWERR_RECOV_CXL,
+ HWERR_RECOV_OTHERS,
+ HWERR_RECOV_MAX,
+};
+
+#ifdef CONFIG_VMCORE_INFO
+noinstr 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/kernel/vmcore_info.c b/kernel/vmcore_info.c
index e066d31d08f89..4b5ab45d468f5 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 {
+ int __data_racy count;
+ time64_t __data_racy 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 +125,17 @@ 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;
+
+ /* No need to atomics/locks given the precision is not important */
+ hwerr_data[src].count++;
+ 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);
---
base-commit: 89748acdf226fd1a8775ff6fa2703f8412b286c8
change-id: 20250707-vmcore_hw_error-322429e6c316
Best regards,
--
Breno Leitao <lei...@debian.org>
