CVE-2024-26987 mm/memory-failure: fix deadlock when hugetlb_optimize_vmemmap is enabled

2024-05-0105:27:34

Linux

www.cve.org

linux kernel

vulnerability resolved

deadlock

hugetlb_optimize_vmemmap

hard offline test

circular locking dependency

cpu deadlock

locking scenario

6.2 Medium

AI Score

Confidence

High

0.0004 Low

EPSS

Percentile

5.1%

JSON

In the Linux kernel, the following vulnerability has been resolved:

mm/memory-failure: fix deadlock when hugetlb_optimize_vmemmap is enabled

When I did hard offline test with hugetlb pages, below deadlock occurs:

======================================================
WARNING: possible circular locking dependency detected
6.8.0-11409-gf6cef5f8c37f #1 Not tainted

bash/46904 is trying to acquire lock:
ffffffffabe68910 (cpu_hotplug_lock){++++}-{0:0}, at: static_key_slow_dec+0x16/0x60

but task is already holding lock:
ffffffffabf92ea8 (pcp_batch_high_lock){+.+.}-{3:3}, at: zone_pcp_disable+0x16/0x40

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (pcp_batch_high_lock){+.+.}-{3:3}:
__mutex_lock+0x6c/0x770
page_alloc_cpu_online+0x3c/0x70
cpuhp_invoke_callback+0x397/0x5f0
__cpuhp_invoke_callback_range+0x71/0xe0
_cpu_up+0xeb/0x210
cpu_up+0x91/0xe0
cpuhp_bringup_mask+0x49/0xb0
bringup_nonboot_cpus+0xb7/0xe0
smp_init+0x25/0xa0
kernel_init_freeable+0x15f/0x3e0
kernel_init+0x15/0x1b0
ret_from_fork+0x2f/0x50
ret_from_fork_asm+0x1a/0x30

-> #0 (cpu_hotplug_lock){++++}-{0:0}:
__lock_acquire+0x1298/0x1cd0
lock_acquire+0xc0/0x2b0
cpus_read_lock+0x2a/0xc0
static_key_slow_dec+0x16/0x60
__hugetlb_vmemmap_restore_folio+0x1b9/0x200
dissolve_free_huge_page+0x211/0x260
__page_handle_poison+0x45/0xc0
memory_failure+0x65e/0xc70
hard_offline_page_store+0x55/0xa0
kernfs_fop_write_iter+0x12c/0x1d0
vfs_write+0x387/0x550
ksys_write+0x64/0xe0
do_syscall_64+0xca/0x1e0
entry_SYSCALL_64_after_hwframe+0x6d/0x75

other info that might help us debug this:

Possible unsafe locking scenario:

   CPU0                    CPU1
   ----                    ----

lock(pcp_batch_high_lock);
lock(cpu_hotplug_lock);
lock(pcp_batch_high_lock);
rlock(cpu_hotplug_lock);

*** DEADLOCK***

5 locks held by bash/46904:
#0: ffff98f6c3bb23f0 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x64/0xe0
#1: ffff98f6c328e488 (&of->mutex){+.+.}-{3:3}, at: kernfs_fop_write_iter+0xf8/0x1d0
#2: ffff98ef83b31890 (kn->active#113){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x100/0x1d0
#3: ffffffffabf9db48 (mf_mutex){+.+.}-{3:3}, at: memory_failure+0x44/0xc70
#4: ffffffffabf92ea8 (pcp_batch_high_lock){+.+.}-{3:3}, at: zone_pcp_disable+0x16/0x40

stack backtrace:
CPU: 10 PID: 46904 Comm: bash Kdump: loaded Not tainted 6.8.0-11409-gf6cef5f8c37f #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
Call Trace:
<TASK>
dump_stack_lvl+0x68/0xa0
check_noncircular+0x129/0x140
__lock_acquire+0x1298/0x1cd0
lock_acquire+0xc0/0x2b0
cpus_read_lock+0x2a/0xc0
static_key_slow_dec+0x16/0x60
__hugetlb_vmemmap_restore_folio+0x1b9/0x200
dissolve_free_huge_page+0x211/0x260
__page_handle_poison+0x45/0xc0
memory_failure+0x65e/0xc70
hard_offline_page_store+0x55/0xa0
kernfs_fop_write_iter+0x12c/0x1d0
vfs_write+0x387/0x550
ksys_write+0x64/0xe0
do_syscall_64+0xca/0x1e0
entry_SYSCALL_64_after_hwframe+0x6d/0x75
RIP: 0033:0x7fc862314887
Code: 10 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24
RSP: 002b:00007fff19311268 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 000000000000000c RCX: 00007fc862314887
RDX: 000000000000000c RSI: 000056405645fe10 RDI: 0000000000000001
RBP: 000056405645fe10 R08: 00007fc8623d1460 R09: 000000007fffffff
R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000000c
R13: 00007fc86241b780 R14: 00007fc862417600 R15: 00007fc862416a00

In short, below scene breaks the
—truncated—

CNA Affected

[
  {
    "product": "Linux",
    "vendor": "Linux",
    "defaultStatus": "unaffected",
    "repo": "https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git",
    "programFiles": [
      "mm/memory-failure.c"
    ],
    "versions": [
      {
        "version": "a6b40850c442",
        "lessThan": "5ef7ba2799a3",
        "status": "affected",
        "versionType": "git"
      },
      {
        "version": "a6b40850c442",
        "lessThan": "882e1180c83f",
        "status": "affected",
        "versionType": "git"
      },
      {
        "version": "a6b40850c442",
        "lessThan": "49955b24002d",
        "status": "affected",
        "versionType": "git"
      },
      {
        "version": "a6b40850c442",
        "lessThan": "1983184c22dd",
        "status": "affected",
        "versionType": "git"
      }
    ]
  },
  {
    "product": "Linux",
    "vendor": "Linux",
    "defaultStatus": "affected",
    "repo": "https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git",
    "programFiles": [
      "mm/memory-failure.c"
    ],
    "versions": [
      {
        "version": "5.18",
        "status": "affected"
      },
      {
        "version": "0",
        "lessThan": "5.18",
        "status": "unaffected",
        "versionType": "custom"
      },
      {
        "version": "6.1.88",
        "lessThanOrEqual": "6.1.*",
        "status": "unaffected",
        "versionType": "custom"
      },
      {
        "version": "6.6.29",
        "lessThanOrEqual": "6.6.*",
        "status": "unaffected",
        "versionType": "custom"
      },
      {
        "version": "6.8.8",
        "lessThanOrEqual": "6.8.*",
        "status": "unaffected",
        "versionType": "custom"
      },
      {
        "version": "6.9",
        "lessThanOrEqual": "*",
        "status": "unaffected",
        "versionType": "original_commit_for_fix"
      }
    ]
  }
]