linux/kernel/vmcore_info.c
Zhiquan Li 247021624a crash: export PAGE_UNACCEPTED_MAPCOUNT_VALUE to vmcoreinfo
On Intel TDX guest, unaccepted memory is unusable free memory which is not
managed by buddy, until it's accepted by guest.  Before that, it cannot be
accessed by the first kernel as well as the kexec'ed kernel.  The kexec'ed
kernel will skip these pages and fill in zero data for the reader of
vmcore.

The dump tool like makedumpfile creates a page descriptor (size 24 bytes)
for each non-free page, including zero data page, but it will not create
descriptor for free pages.  If it is not able to distinguish these
unaccepted pages with zero data pages, a certain amount of space will be
wasted in proportion (~1/170).  In fact, as a special kind of free page
the unaccepted pages should be excluded, like the real free pages.

Export the page type PAGE_UNACCEPTED_MAPCOUNT_VALUE to vmcoreinfo, so that
dump tool can identify whether a page is unaccepted.

[zhiquan1.li@intel.com: fix docs: "Title underline too short" warning]
  Link: https://lore.kernel.org/all/20240809114854.3745464-5-kirill.shutemov@linux.intel.com/
  Link: https://lkml.kernel.org/r/20250405060610.860465-1-zhiquan1.li@intel.com
Link: https://lore.kernel.org/all/20240809114854.3745464-5-kirill.shutemov@linux.intel.com/
Link: https://lkml.kernel.org/r/20250403030801.758687-1-zhiquan1.li@intel.com
Signed-off-by: Zhiquan Li <zhiquan1.li@intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Baoquan He <bhe@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Zhiquan Li <zhiquan1.li@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2025-05-11 17:54:04 -07:00

233 lines
6.3 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;
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);
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);