Files
linux/kernel/vmcore_info.c
Breno Leitao 3fa805c37d 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 ee62ce7a1d ("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.

[leitao@debian.org: add hw-recoverable-errors to toctree]
  Link: https://lkml.kernel.org/r/20251127-vmcoreinfo_fix-v1-1-26f5b1c43da9@debian.org
Link: https://lkml.kernel.org/r/20251010-vmcore_hw_error-v5-1-636ede3efe44@debian.org
Signed-off-by: Breno Leitao <leitao@debian.org>
Suggested-by: Tony Luck <tony.luck@intel.com>
Suggested-by: Shuai Xue <xueshuai@linux.alibaba.com>
Reviewed-by: Shuai Xue <xueshuai@linux.alibaba.com>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>	[APEI]
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Bob Moore <robert.moore@intel.com>
Cc: Borislav Betkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Morse <james.morse@arm.com>
Cc: Konrad Rzessutek Wilk <konrad.wilk@oracle.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Mahesh Salgaonkar <mahesh@linux.ibm.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Omar Sandoval <osandov@osandov.com>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2025-11-27 14:24:44 -08:00

251 lines
6.6 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* crash.c - kernel crash support code.
* Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com>
*/
#include <linux/buildid.h>
#include <linux/init.h>
#include <linux/utsname.h>
#include <linux/vmalloc.h>
#include <linux/sizes.h>
#include <linux/kexec.h>
#include <linux/memory.h>
#include <linux/cpuhotplug.h>
#include <linux/memblock.h>
#include <linux/kmemleak.h>
#include <asm/page.h>
#include <asm/sections.h>
#include <crypto/sha1.h>
#include "kallsyms_internal.h"
#include "kexec_internal.h"
/* vmcoreinfo stuff */
unsigned char *vmcoreinfo_data;
size_t vmcoreinfo_size;
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)
{
struct elf_note *note = (struct elf_note *)buf;
note->n_namesz = strlen(name) + 1;
note->n_descsz = data_len;
note->n_type = type;
buf += DIV_ROUND_UP(sizeof(*note), sizeof(Elf_Word));
memcpy(buf, name, note->n_namesz);
buf += DIV_ROUND_UP(note->n_namesz, sizeof(Elf_Word));
memcpy(buf, data, data_len);
buf += DIV_ROUND_UP(data_len, sizeof(Elf_Word));
return buf;
}
void final_note(Elf_Word *buf)
{
memset(buf, 0, sizeof(struct elf_note));
}
static void update_vmcoreinfo_note(void)
{
u32 *buf = vmcoreinfo_note;
if (!vmcoreinfo_size)
return;
buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data,
vmcoreinfo_size);
final_note(buf);
}
void crash_update_vmcoreinfo_safecopy(void *ptr)
{
if (ptr)
memcpy(ptr, vmcoreinfo_data, vmcoreinfo_size);
vmcoreinfo_data_safecopy = ptr;
}
void crash_save_vmcoreinfo(void)
{
if (!vmcoreinfo_note)
return;
/* Use the safe copy to generate vmcoreinfo note if have */
if (vmcoreinfo_data_safecopy)
vmcoreinfo_data = vmcoreinfo_data_safecopy;
vmcoreinfo_append_str("CRASHTIME=%lld\n", ktime_get_real_seconds());
update_vmcoreinfo_note();
}
void vmcoreinfo_append_str(const char *fmt, ...)
{
va_list args;
char buf[0x50];
size_t r;
va_start(args, fmt);
r = vscnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
r = min(r, (size_t)VMCOREINFO_BYTES - vmcoreinfo_size);
memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
vmcoreinfo_size += r;
WARN_ONCE(vmcoreinfo_size == VMCOREINFO_BYTES,
"vmcoreinfo data exceeds allocated size, truncating");
}
/*
* provide an empty default implementation here -- architecture
* code may override this
*/
void __weak arch_crash_save_vmcoreinfo(void)
{}
phys_addr_t __weak paddr_vmcoreinfo_note(void)
{
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)
{
vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);
if (!vmcoreinfo_data) {
pr_warn("Memory allocation for vmcoreinfo_data failed\n");
return -ENOMEM;
}
vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE,
GFP_KERNEL | __GFP_ZERO);
if (!vmcoreinfo_note) {
free_page((unsigned long)vmcoreinfo_data);
vmcoreinfo_data = NULL;
pr_warn("Memory allocation for vmcoreinfo_note failed\n");
return -ENOMEM;
}
VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
VMCOREINFO_BUILD_ID();
VMCOREINFO_PAGESIZE(PAGE_SIZE);
VMCOREINFO_SYMBOL(init_uts_ns);
VMCOREINFO_OFFSET(uts_namespace, name);
VMCOREINFO_SYMBOL(node_online_map);
#ifdef CONFIG_MMU
VMCOREINFO_SYMBOL_ARRAY(swapper_pg_dir);
#endif
VMCOREINFO_SYMBOL(_stext);
vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", (unsigned long) VMALLOC_START);
#ifndef CONFIG_NUMA
VMCOREINFO_SYMBOL(mem_map);
VMCOREINFO_SYMBOL(contig_page_data);
#endif
#ifdef CONFIG_SPARSEMEM_VMEMMAP
VMCOREINFO_SYMBOL_ARRAY(vmemmap);
#endif
#ifdef CONFIG_SPARSEMEM
VMCOREINFO_SYMBOL_ARRAY(mem_section);
VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
VMCOREINFO_STRUCT_SIZE(mem_section);
VMCOREINFO_OFFSET(mem_section, section_mem_map);
VMCOREINFO_NUMBER(SECTION_SIZE_BITS);
VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS);
#endif
VMCOREINFO_STRUCT_SIZE(page);
VMCOREINFO_STRUCT_SIZE(pglist_data);
VMCOREINFO_STRUCT_SIZE(zone);
VMCOREINFO_STRUCT_SIZE(free_area);
VMCOREINFO_STRUCT_SIZE(list_head);
VMCOREINFO_SIZE(nodemask_t);
VMCOREINFO_OFFSET(page, flags);
VMCOREINFO_OFFSET(page, _refcount);
VMCOREINFO_OFFSET(page, mapping);
VMCOREINFO_OFFSET(page, lru);
VMCOREINFO_OFFSET(page, _mapcount);
VMCOREINFO_OFFSET(page, private);
VMCOREINFO_OFFSET(page, compound_head);
VMCOREINFO_OFFSET(pglist_data, node_zones);
VMCOREINFO_OFFSET(pglist_data, nr_zones);
#ifdef CONFIG_FLATMEM
VMCOREINFO_OFFSET(pglist_data, node_mem_map);
#endif
VMCOREINFO_OFFSET(pglist_data, node_start_pfn);
VMCOREINFO_OFFSET(pglist_data, node_spanned_pages);
VMCOREINFO_OFFSET(pglist_data, node_id);
VMCOREINFO_OFFSET(zone, free_area);
VMCOREINFO_OFFSET(zone, vm_stat);
VMCOREINFO_OFFSET(zone, spanned_pages);
VMCOREINFO_OFFSET(free_area, free_list);
VMCOREINFO_OFFSET(list_head, next);
VMCOREINFO_OFFSET(list_head, prev);
VMCOREINFO_LENGTH(zone.free_area, NR_PAGE_ORDERS);
log_buf_vmcoreinfo_setup();
VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
VMCOREINFO_NUMBER(NR_FREE_PAGES);
VMCOREINFO_NUMBER(PG_lru);
VMCOREINFO_NUMBER(PG_private);
VMCOREINFO_NUMBER(PG_swapcache);
VMCOREINFO_NUMBER(PG_swapbacked);
#define PAGE_SLAB_MAPCOUNT_VALUE (PGTY_slab << 24)
VMCOREINFO_NUMBER(PAGE_SLAB_MAPCOUNT_VALUE);
#ifdef CONFIG_MEMORY_FAILURE
VMCOREINFO_NUMBER(PG_hwpoison);
#endif
VMCOREINFO_NUMBER(PG_head_mask);
#define PAGE_BUDDY_MAPCOUNT_VALUE (PGTY_buddy << 24)
VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
#define PAGE_HUGETLB_MAPCOUNT_VALUE (PGTY_hugetlb << 24)
VMCOREINFO_NUMBER(PAGE_HUGETLB_MAPCOUNT_VALUE);
#define PAGE_OFFLINE_MAPCOUNT_VALUE (PGTY_offline << 24)
VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE);
#ifdef CONFIG_UNACCEPTED_MEMORY
#define PAGE_UNACCEPTED_MAPCOUNT_VALUE (PGTY_unaccepted << 24)
VMCOREINFO_NUMBER(PAGE_UNACCEPTED_MAPCOUNT_VALUE);
#endif
#ifdef CONFIG_KALLSYMS
VMCOREINFO_SYMBOL(kallsyms_names);
VMCOREINFO_SYMBOL(kallsyms_num_syms);
VMCOREINFO_SYMBOL(kallsyms_token_table);
VMCOREINFO_SYMBOL(kallsyms_token_index);
VMCOREINFO_SYMBOL(kallsyms_offsets);
VMCOREINFO_SYMBOL(kallsyms_relative_base);
#endif /* CONFIG_KALLSYMS */
arch_crash_save_vmcoreinfo();
update_vmcoreinfo_note();
return 0;
}
subsys_initcall(crash_save_vmcoreinfo_init);