vmcoreinfo: track and log recoverable hardware errors

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.

[[e-mail]: add hw-recoverable-errors to toctree]
Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Breno Leitao <[e-mail]>
Suggested-by: Tony Luck <[e-mail]>
Suggested-by: Shuai Xue <[e-mail]>
Reviewed-by: Shuai Xue <[e-mail]>
Reviewed-by: Hanjun Guo <[e-mail]> [APEI]
Cc: Bjorn Helgaas <[e-mail]>
Cc: Bob Moore <[e-mail]>
Cc: Borislav Betkov <[e-mail]>
Cc: "H. Peter Anvin" <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: James Morse <[e-mail]>
Cc: Konrad Rzessutek Wilk <[e-mail]>
Cc: Len Brown <[e-mail]>
Cc: Mahesh Salgaonkar <[e-mail]>
Cc: Mauro Carvalho Chehab <[e-mail]>
Cc: "Oliver O'Halloran" <[e-mail]>
Cc: Omar Sandoval <[e-mail]>
Cc: Thomas Gleinxer <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

Documentation/driver-api/hw-recoverable-errors.rst

···
+.. 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.
+

Documentation/driver-api/index.rst

···
    gpio/index
    hsi
    hte/index
+   hw-recoverable-errors
    i2c
    iio/index
    infiniband

arch/x86/kernel/cpu/mce/core.c

···
 #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>
···
 	}
 
 out:
+	/* Given it didn't panic, mark it as recoverable */
+	hwerr_log_error_type(HWERR_RECOV_OTHERS);
+
 	instrumentation_end();
 
 clear:

drivers/acpi/apei/ghes.c

···
 #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>
···
 }
 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)
 {
···
 		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);
 

drivers/pci/pcie/aer.c

···
 #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>
···
 		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;

include/linux/vmcore_info.h

···
 #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)
···
 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 */

include/uapi/linux/vmcore.h

···
 	__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 */

kernel/vmcore_info.c

···
 /* 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)
 {
···
 	return __pa(vmcoreinfo_note);
 }
 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)
 {