[PATCH v2] vmcoreinfo: Track and log recoverable hardware errors

[PATCH v2] vmcoreinfo: Track and log recoverable hardware errors

[Breno Leitao]

Introduce a generic infrastructure for tracking recoverable hardware
errors (HW errors that did 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.

This patch adds centralized logging for three common sources of
recoverable hardware errors:

  - PCIe AER Correctable errors
  - x86 Machine Check Exceptions (MCE)
  - APEI/CPER GHES corrected or recoverable errors

hwerror_tracking 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_tracking']
	(struct hwerror_tracking_info [3]){
		{
			.count = (int)844,
			.timestamp = (time64_t)1752852018,
		},
		...

Suggested-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Breno Leitao <leitao@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-v1-1-8cf45edb6334@debian.org
---
 arch/x86/kernel/cpu/mce/core.c |  3 +++
 drivers/acpi/apei/ghes.c       |  8 ++++++--
 drivers/pci/pcie/aer.c         |  2 ++
 include/linux/vmcore_info.h    | 14 ++++++++++++++
 kernel/vmcore_info.c           | 18 ++++++++++++++++++
 5 files changed, 43 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 4da4eab56c81d..781cf574642eb 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>
@@ -1692,6 +1693,8 @@ noinstr void do_machine_check(struct pt_regs *regs)
 out:
 	instrumentation_end();
 
+	/* Given it didn't panic, mark it as recoverable */
+	hwerror_tracking_log(HWE_RECOV_MCE);
 clear:
 	mce_wrmsrq(MSR_IA32_MCG_STATUS, 0);
 }
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index a0d54993edb3b..396cdffbe6a37 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>
@@ -1136,13 +1137,16 @@ static int ghes_proc(struct ghes *ghes)
 {
 	struct acpi_hest_generic_status *estatus = ghes->estatus;
 	u64 buf_paddr;
-	int rc;
+	int rc, sev;
 
 	rc = ghes_read_estatus(ghes, estatus, &buf_paddr, FIX_APEI_GHES_IRQ);
 	if (rc)
 		goto out;
 
-	if (ghes_severity(estatus->error_severity) >= GHES_SEV_PANIC)
+	sev = ghes_severity(estatus->error_severity);
+	if (sev == GHES_SEV_RECOVERABLE || sev ==  GHES_SEV_CORRECTED)
+		hwerror_tracking_log(HWE_RECOV_GHES);
+	else if (sev >= GHES_SEV_PANIC)
 		__ghes_panic(ghes, estatus, buf_paddr, FIX_APEI_GHES_IRQ);
 
 	if (!ghes_estatus_cached(estatus)) {
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index e286c197d7167..064d220564b59 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>
@@ -746,6 +747,7 @@ static void pci_dev_aer_stats_incr(struct pci_dev *pdev,
 	switch (info->severity) {
 	case AER_CORRECTABLE:
 		aer_info->dev_total_cor_errs++;
+		hwerror_tracking_log(HWE_RECOV_AER);
 		counter = &aer_info->dev_cor_errs[0];
 		max = AER_MAX_TYPEOF_COR_ERRS;
 		break;
diff --git a/include/linux/vmcore_info.h b/include/linux/vmcore_info.h
index 37e003ae52626..5894da92a6ba4 100644
--- a/include/linux/vmcore_info.h
+++ b/include/linux/vmcore_info.h
@@ -77,4 +77,18 @@ 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 hwerror_tracking_source {
+	HWE_RECOV_AER,
+	HWE_RECOV_MCE,
+	HWE_RECOV_GHES,
+	HWE_RECOV_MAX,
+};
+
+#ifdef CONFIG_VMCORE_INFO
+void hwerror_tracking_log(enum hwerror_tracking_source src);
+#else
+void hwerror_tracking_log(enum hwerror_tracking_source src) {};
+#endif
+
 #endif /* LINUX_VMCORE_INFO_H */
diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c
index e066d31d08f89..23d7ddcd55cdd 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 hwerror_tracking_info {
+	int __data_racy count;
+	time64_t __data_racy timestamp;
+};
+
+static struct hwerror_tracking_info hwerror_tracking[HWE_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 hwerror_tracking_log(enum hwerror_tracking_source src)
+{
+	if (src < 0 || src >= HWE_RECOV_MAX)
+		return;
+
+	/* No need to atomics/locks given the precision is not important */
+	hwerror_tracking[src].count++;
+	hwerror_tracking[src].timestamp = ktime_get_real_seconds();
+}
+EXPORT_SYMBOL_GPL(hwerror_tracking_log);
+
 static int __init crash_save_vmcoreinfo_init(void)
 {
 	vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);

---
base-commit: 97987520025658f30bb787a99ffbd9bbff9ffc9d
change-id: 20250707-vmcore_hw_error-322429e6c316

Best regards,
--  
Breno Leitao <leitao@debian.org>

Re: [PATCH v2] vmcoreinfo: Track and log recoverable hardware errors

[kernel test robot]

Hi Breno,

kernel test robot noticed the following build errors:

[auto build test ERROR on 97987520025658f30bb787a99ffbd9bbff9ffc9d]

url:    https://github.com/intel-lab-lkp/linux/commits/Breno-Leitao/vmcoreinfo-Track-and-log-recoverable-hardware-errors/20250721-181439
base:   97987520025658f30bb787a99ffbd9bbff9ffc9d
patch link:    https://lore.kernel.org/r/20250721-vmcore_hw_error-v2-1-ab65a6b43c5a%40debian.org
patch subject: [PATCH v2] vmcoreinfo: Track and log recoverable hardware errors
config: x86_64-buildonly-randconfig-004-20250721 (https://download.01.org/0day-ci/archive/20250721/202507212132.OA9HtsQY-lkp@intel.com/config)
compiler: gcc-12 (Debian 12.2.0-14+deb12u1) 12.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250721/202507212132.OA9HtsQY-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202507212132.OA9HtsQY-lkp@intel.com/

All error/warnings (new ones prefixed by >>):

   In file included from include/linux/kexec.h:18,
                    from init/initramfs.c:603:
>> include/linux/vmcore_info.h:91:6: warning: no previous prototype for 'hwerror_tracking_log' [-Wmissing-prototypes]
      91 | void hwerror_tracking_log(enum hwerror_tracking_source src) {};
         |      ^~~~~~~~~~~~~~~~~~~~
--
   ld: arch/x86/kernel/traps.o: in function `hwerror_tracking_log':
>> traps.c:(.text+0x68e): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: arch/x86/kernel/traps.o: in function `__pfx_hwerror_tracking_log':
>> traps.c:(.text+0x67e): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: arch/x86/kernel/dumpstack_64.o: in function `hwerror_tracking_log':
   dumpstack_64.c:(.text+0x10): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: arch/x86/kernel/dumpstack_64.o: in function `__pfx_hwerror_tracking_log':
   dumpstack_64.c:(.text+0x0): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: arch/x86/kernel/dumpstack.o: in function `__pfx_hwerror_tracking_log':
   dumpstack.c:(.text+0xc9): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: arch/x86/kernel/dumpstack.o: in function `hwerror_tracking_log':
   dumpstack.c:(.text+0xd9): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: arch/x86/kernel/setup.o: in function `hwerror_tracking_log':
   setup.c:(.text+0x54): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: arch/x86/kernel/setup.o: in function `__pfx_hwerror_tracking_log':
   setup.c:(.text+0x44): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: arch/x86/kernel/e820.o: in function `__pfx_hwerror_tracking_log':
   e820.c:(.text+0x19f): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: arch/x86/kernel/e820.o: in function `hwerror_tracking_log':
   e820.c:(.text+0x1af): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: arch/x86/kernel/cpu/mce/core.o: in function `hwerror_tracking_log':
   core.c:(.text+0x14f0): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: arch/x86/kernel/cpu/mce/core.o: in function `__pfx_hwerror_tracking_log':
   core.c:(.text+0x14e0): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: arch/x86/kernel/acpi/madt_wakeup.o: in function `hwerror_tracking_log':
   madt_wakeup.c:(.text+0x180): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: arch/x86/kernel/acpi/madt_wakeup.o: in function `__pfx_hwerror_tracking_log':
   madt_wakeup.c:(.text+0x170): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: arch/x86/kernel/reboot.o: in function `hwerror_tracking_log':
   reboot.c:(.text+0x13d): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: arch/x86/kernel/reboot.o: in function `__pfx_hwerror_tracking_log':
   reboot.c:(.text+0x12d): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: arch/x86/kernel/smp.o: in function `hwerror_tracking_log':
   smp.c:(.text+0x28e): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: arch/x86/kernel/smp.o: in function `__pfx_hwerror_tracking_log':
   smp.c:(.text+0x27e): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: arch/x86/kernel/smpboot.o: in function `hwerror_tracking_log':
   smpboot.c:(.text+0x8fe): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: arch/x86/kernel/smpboot.o: in function `__pfx_hwerror_tracking_log':
   smpboot.c:(.text+0x8ee): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: arch/x86/kernel/setup_percpu.o: in function `hwerror_tracking_log':
   setup_percpu.c:(.text+0x10): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: arch/x86/kernel/setup_percpu.o: in function `__pfx_hwerror_tracking_log':
   setup_percpu.c:(.text+0x0): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: arch/x86/kernel/machine_kexec_64.o: in function `hwerror_tracking_log':
   machine_kexec_64.c:(.text+0x772): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: arch/x86/kernel/machine_kexec_64.o: in function `__pfx_hwerror_tracking_log':
   machine_kexec_64.c:(.text+0x762): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: arch/x86/kernel/kexec-bzimage64.o: in function `hwerror_tracking_log':
   kexec-bzimage64.c:(.text+0xb9c): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: arch/x86/kernel/kexec-bzimage64.o: in function `__pfx_hwerror_tracking_log':
   kexec-bzimage64.c:(.text+0xb8c): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: arch/x86/kernel/early_printk.o: in function `hwerror_tracking_log':
   early_printk.c:(.text+0x31e): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: arch/x86/kernel/early_printk.o: in function `__pfx_hwerror_tracking_log':
   early_printk.c:(.text+0x30e): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: kernel/panic.o: in function `hwerror_tracking_log':
   panic.c:(.text+0x466): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: kernel/panic.o: in function `__pfx_hwerror_tracking_log':
   panic.c:(.text+0x456): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: kernel/ksysfs.o: in function `hwerror_tracking_log':
   ksysfs.c:(.text+0x1f6): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: kernel/ksysfs.o: in function `__pfx_hwerror_tracking_log':
   ksysfs.c:(.text+0x1e6): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: kernel/reboot.o: in function `hwerror_tracking_log':
   reboot.c:(.text+0xd31): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: kernel/reboot.o: in function `__pfx_hwerror_tracking_log':
   reboot.c:(.text+0xd21): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: kernel/printk/printk.o: in function `hwerror_tracking_log':
   printk.c:(.text+0x2119): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: kernel/printk/printk.o: in function `__pfx_hwerror_tracking_log':
   printk.c:(.text+0x2109): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: kernel/kexec_core.o: in function `hwerror_tracking_log':
   kexec_core.c:(.text+0x346): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: kernel/kexec_core.o: in function `__pfx_hwerror_tracking_log':
   kexec_core.c:(.text+0x336): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: kernel/kexec_file.o: in function `hwerror_tracking_log':
   kexec_file.c:(.text+0x42a): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: kernel/kexec_file.o: in function `__pfx_hwerror_tracking_log':
   kexec_file.c:(.text+0x41a): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: kernel/kexec_handover.o: in function `hwerror_tracking_log':
   kexec_handover.c:(.text+0xf63): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: kernel/kexec_handover.o: in function `__pfx_hwerror_tracking_log':
   kexec_handover.c:(.text+0xf53): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: mm/mm_init.o: in function `hwerror_tracking_log':
   mm_init.c:(.text+0x26d): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: mm/mm_init.o: in function `__pfx_hwerror_tracking_log':
   mm_init.c:(.text+0x25d): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: block/blk-mq.o: in function `hwerror_tracking_log':
   blk-mq.c:(.text+0x48d3): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: block/blk-mq.o: in function `__pfx_hwerror_tracking_log':
   blk-mq.c:(.text+0x48c3): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: drivers/iommu/dma-iommu.o: in function `hwerror_tracking_log':
   dma-iommu.c:(.text+0x196e): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: drivers/iommu/dma-iommu.o: in function `__pfx_hwerror_tracking_log':
   dma-iommu.c:(.text+0x195e): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: drivers/md/dm-ioctl.o: in function `hwerror_tracking_log':
   dm-ioctl.c:(.text+0x2f65): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: drivers/md/dm-ioctl.o: in function `__pfx_hwerror_tracking_log':
   dm-ioctl.c:(.text+0x2f55): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here
   ld: drivers/firmware/efi/efi.o: in function `hwerror_tracking_log':
   efi.c:(.text+0x5f2): multiple definition of `hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x80): first defined here
   ld: drivers/firmware/efi/efi.o: in function `__pfx_hwerror_tracking_log':
   efi.c:(.text+0x5e2): multiple definition of `__pfx_hwerror_tracking_log'; init/initramfs.o:initramfs.c:(.text+0x70): first defined here

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH v2] vmcoreinfo: Track and log recoverable hardware errors

[Borislav Petkov]

On Mon, Jul 21, 2025 at 03:13:40AM -0700, Breno Leitao wrote:
> Introduce a generic infrastructure for tracking recoverable hardware
> errors (HW errors that did 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.
> 
> This patch adds centralized logging for three common sources of

"Add centralized... "

> recoverable hardware errors:
> 
>   - PCIe AER Correctable errors
>   - x86 Machine Check Exceptions (MCE)
>   - APEI/CPER GHES corrected or recoverable errors
> 
> hwerror_tracking 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_tracking']
> 	(struct hwerror_tracking_info [3]){
> 		{
> 			.count = (int)844,
> 			.timestamp = (time64_t)1752852018,
> 		},
> 		...
> 

I'm still missing the justification why rasdaemon can't be used here.
You did explain it already in past emails.

> +enum hwerror_tracking_source {
> +	HWE_RECOV_AER,
> +	HWE_RECOV_MCE,
> +	HWE_RECOV_GHES,
> +	HWE_RECOV_MAX,
> +};

Are we confident this separation will serve all cloud dudes?

> +
> +#ifdef CONFIG_VMCORE_INFO
> +void hwerror_tracking_log(enum hwerror_tracking_source src);
> +#else
> +void hwerror_tracking_log(enum hwerror_tracking_source src) {};
> +#endif
> +
>  #endif /* LINUX_VMCORE_INFO_H */
> diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c
> index e066d31d08f89..23d7ddcd55cdd 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 hwerror_tracking_info {
> +	int __data_racy count;
> +	time64_t __data_racy timestamp;
> +};
> +
> +static struct hwerror_tracking_info hwerror_tracking[HWE_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 hwerror_tracking_log(enum hwerror_tracking_source src)

A function should have a verb in its name explaining what it does:

hwerr_log_error_type()

or so.

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette

Re: [PATCH v2] vmcoreinfo: Track and log recoverable hardware errors

[Breno Leitao]

Hello Borislav,

On Mon, Jul 21, 2025 at 03:57:18PM +0200, Borislav Petkov wrote:
> On Mon, Jul 21, 2025 at 03:13:40AM -0700, Breno Leitao wrote:
> > Introduce a generic infrastructure for tracking recoverable hardware
> > errors (HW errors that did 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.
> > 
> > This patch adds centralized logging for three common sources of
> 
> "Add centralized... "

Ack!

> > recoverable hardware errors:
> > 
> >   - PCIe AER Correctable errors
> >   - x86 Machine Check Exceptions (MCE)
> >   - APEI/CPER GHES corrected or recoverable errors
> > 
> > hwerror_tracking 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_tracking']
> > 	(struct hwerror_tracking_info [3]){
> > 		{
> > 			.count = (int)844,
> > 			.timestamp = (time64_t)1752852018,
> > 		},
> > 		...
> > 
> 
> I'm still missing the justification why rasdaemon can't be used here.
> You did explain it already in past emails.

Sorry, I will update it.

> > +enum hwerror_tracking_source {
> > +	HWE_RECOV_AER,
> > +	HWE_RECOV_MCE,
> > +	HWE_RECOV_GHES,
> > +	HWE_RECOV_MAX,
> > +};
> 
> Are we confident this separation will serve all cloud dudes?

I am not, but, I've added them to CC list of this patch, so, they are
more than free to chime in.

> > +void hwerror_tracking_log(enum hwerror_tracking_source src)
> 
> A function should have a verb in its name explaining what it does:
> 
> hwerr_log_error_type()
> 
> or so.

Ack!

I will wait a bit more and send an updated version.

Thanks for the review
--breno

Re: [PATCH v2] vmcoreinfo: Track and log recoverable hardware errors

[kernel test robot]

Hi Breno,

kernel test robot noticed the following build warnings:

[auto build test WARNING on 97987520025658f30bb787a99ffbd9bbff9ffc9d]

url:    https://github.com/intel-lab-lkp/linux/commits/Breno-Leitao/vmcoreinfo-Track-and-log-recoverable-hardware-errors/20250721-181439
base:   97987520025658f30bb787a99ffbd9bbff9ffc9d
patch link:    https://lore.kernel.org/r/20250721-vmcore_hw_error-v2-1-ab65a6b43c5a%40debian.org
patch subject: [PATCH v2] vmcoreinfo: Track and log recoverable hardware errors
config: i386-buildonly-randconfig-001-20250721 (https://download.01.org/0day-ci/archive/20250722/202507220057.iVSR8aqd-lkp@intel.com/config)
compiler: clang version 20.1.8 (https://github.com/llvm/llvm-project 87f0227cb60147a26a1eeb4fb06e3b505e9c7261)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250722/202507220057.iVSR8aqd-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202507220057.iVSR8aqd-lkp@intel.com/

All warnings (new ones prefixed by >>):

   In file included from init/initramfs.c:603:
   In file included from include/linux/kexec.h:18:
>> include/linux/vmcore_info.h:91:6: warning: no previous prototype for function 'hwerror_tracking_log' [-Wmissing-prototypes]
      91 | void hwerror_tracking_log(enum hwerror_tracking_source src) {};
         |      ^
   include/linux/vmcore_info.h:91:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
      91 | void hwerror_tracking_log(enum hwerror_tracking_source src) {};
         | ^
         | static 
   1 warning generated.


vim +/hwerror_tracking_log +91 include/linux/vmcore_info.h

    87	
    88	#ifdef CONFIG_VMCORE_INFO
    89	void hwerror_tracking_log(enum hwerror_tracking_source src);
    90	#else
  > 91	void hwerror_tracking_log(enum hwerror_tracking_source src) {};
    92	#endif
    93	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki