syzbot


possible deadlock in ext4_writepages (2)

Status: upstream: reported on 2024/10/19 20:27
Subsystems: ext4
[Documentation on labels]
Reported-by: syzbot+eb5b4ef634a018917f3c@syzkaller.appspotmail.com
First crash: 163d, last: 11d
Discussions (1)
Title Replies (including bot) Last reply
[syzbot] [ext4?] possible deadlock in ext4_writepages (2) 0 (1) 2024/10/19 20:27
Similar bugs (2)
Kernel Title Repro Cause bisect Fix bisect Count Last Reported Patched Status
upstream possible deadlock in ext4_writepages ext4 1 957d 953d 0/28 auto-obsoleted due to no activity on 2022/12/11 07:00
linux-5.15 possible deadlock in ext4_writepages 2 694d 695d 0/3 auto-obsoleted due to no activity on 2023/08/23 09:09

Sample crash report:
EXT4-fs (loop6): mounted filesystem 00000000-0000-0000-0000-000000000000 r/w without journal. Quota mode: none.
======================================================
WARNING: possible circular locking dependency detected
6.14.0-rc6-syzkaller-00263-gd1275e99d1c4 #0 Not tainted
------------------------------------------------------
syz.6.1434/17731 is trying to acquire lock:
ffff88806b2f2b98 (&sbi->s_writepages_rwsem){++++}-{0:0}, at: ext4_writepages_down_read fs/ext4/ext4.h:1773 [inline]
ffff88806b2f2b98 (&sbi->s_writepages_rwsem){++++}-{0:0}, at: ext4_writepages+0x1bf/0x3c0 fs/ext4/inode.c:2823

but task is already holding lock:
ffff8880331a4108 (mapping.invalidate_lock){++++}-{4:4}, at: filemap_invalidate_lock include/linux/fs.h:922 [inline]
ffff8880331a4108 (mapping.invalidate_lock){++++}-{4:4}, at: ext4_insert_range fs/ext4/extents.c:5528 [inline]
ffff8880331a4108 (mapping.invalidate_lock){++++}-{4:4}, at: ext4_fallocate+0xdae/0x1ea0 fs/ext4/extents.c:4782

which lock already depends on the new lock.


the existing dependency chain (in reverse order) is:

-> #4 (mapping.invalidate_lock){++++}-{4:4}:
       lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5851
       down_read+0xb1/0xa40 kernel/locking/rwsem.c:1524
       filemap_invalidate_lock_shared include/linux/fs.h:932 [inline]
       page_cache_ra_unbounded+0x156/0x820 mm/readahead.c:228
       do_async_mmap_readahead mm/filemap.c:3278 [inline]
       filemap_fault+0x818/0x1490 mm/filemap.c:3377
       __do_fault+0x135/0x390 mm/memory.c:4989
       do_read_fault mm/memory.c:5409 [inline]
       do_fault mm/memory.c:5543 [inline]
       do_pte_missing mm/memory.c:4059 [inline]
       handle_pte_fault mm/memory.c:5888 [inline]
       __handle_mm_fault+0x40c6/0x6ef0 mm/memory.c:6031
       handle_mm_fault+0x2c1/0x7e0 mm/memory.c:6200
       faultin_page mm/gup.c:1196 [inline]
       __get_user_pages+0x1a92/0x4140 mm/gup.c:1491
       __get_user_pages_locked mm/gup.c:1757 [inline]
       get_dump_page+0x155/0x2f0 mm/gup.c:2275
       dump_user_range+0x14d/0x970 fs/coredump.c:944
       elf_core_dump+0x4054/0x4a80 fs/binfmt_elf.c:2129
       do_coredump+0x22e7/0x3290 fs/coredump.c:759
       get_signal+0x13e5/0x1720 kernel/signal.c:3021
       arch_do_signal_or_restart+0x96/0x860 arch/x86/kernel/signal.c:337
       exit_to_user_mode_loop kernel/entry/common.c:111 [inline]
       exit_to_user_mode_prepare include/linux/entry-common.h:329 [inline]
       irqentry_exit_to_user_mode+0x7e/0x250 kernel/entry/common.c:231
       exc_page_fault+0x590/0x8b0 arch/x86/mm/fault.c:1541
       asm_exc_page_fault+0x26/0x30 arch/x86/include/asm/idtentry.h:623

-> #3 (&mm->mmap_lock){++++}-{4:4}:
       lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5851
       __might_fault+0xc6/0x120 mm/memory.c:6839
       _inline_copy_to_user include/linux/uaccess.h:192 [inline]
       _copy_to_user+0x2c/0xb0 lib/usercopy.c:26
       copy_to_user include/linux/uaccess.h:225 [inline]
       fiemap_fill_next_extent+0x235/0x420 fs/ioctl.c:145
       ocfs2_fiemap+0xa03/0x1010 fs/ocfs2/extent_map.c:806
       ioctl_fiemap fs/ioctl.c:220 [inline]
       do_vfs_ioctl+0x1981/0x2770 fs/ioctl.c:840
       __do_sys_ioctl fs/ioctl.c:904 [inline]
       __se_sys_ioctl+0x80/0x170 fs/ioctl.c:892
       do_syscall_x64 arch/x86/entry/common.c:52 [inline]
       do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

-> #2 (&ocfs2_quota_ip_alloc_sem_key){++++}-{4:4}:
       lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5851
       down_write+0x99/0x220 kernel/locking/rwsem.c:1577
       ocfs2_create_local_dquot+0x1de/0x1d70 fs/ocfs2/quota_local.c:1232
       ocfs2_acquire_dquot+0x833/0xb70 fs/ocfs2/quota_global.c:883
       dqget+0x770/0xeb0 fs/quota/dquot.c:977
       dquot_set_dqblk+0x2b/0xf30 fs/quota/dquot.c:2820
       quota_setquota+0x6dc/0x850 fs/quota/quota.c:310
       __do_sys_quotactl fs/quota/quota.c:961 [inline]
       __se_sys_quotactl+0x2c4/0xa30 fs/quota/quota.c:917
       do_syscall_x64 arch/x86/entry/common.c:52 [inline]
       do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

-> #1 (&dquot->dq_lock){+.+.}-{4:4}:
       lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5851
       __mutex_lock_common kernel/locking/mutex.c:585 [inline]
       __mutex_lock+0x19c/0x1010 kernel/locking/mutex.c:730
       wait_on_dquot fs/quota/dquot.c:354 [inline]
       dqget+0x6e6/0xeb0 fs/quota/dquot.c:972
       __dquot_initialize+0x2e3/0xec0 fs/quota/dquot.c:1505
       __ext4_new_inode+0x852/0x4630 fs/ext4/ialloc.c:992
       ext4_ext_migrate+0x700/0x1440 fs/ext4/migrate.c:456
       ext4_ioctl_setflags fs/ext4/ioctl.c:702 [inline]
       ext4_fileattr_set+0xecf/0x16e0 fs/ext4/ioctl.c:1021
       vfs_fileattr_set+0x8ff/0xd50 fs/ioctl.c:696
       ioctl_setflags fs/ioctl.c:728 [inline]
       do_vfs_ioctl+0x1816/0x2770 fs/ioctl.c:869
       __do_sys_ioctl fs/ioctl.c:904 [inline]
       __se_sys_ioctl+0x80/0x170 fs/ioctl.c:892
       do_syscall_x64 arch/x86/entry/common.c:52 [inline]
       do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

-> #0 (&sbi->s_writepages_rwsem){++++}-{0:0}:
       check_prev_add kernel/locking/lockdep.c:3163 [inline]
       check_prevs_add kernel/locking/lockdep.c:3282 [inline]
       validate_chain+0x18ef/0x5920 kernel/locking/lockdep.c:3906
       __lock_acquire+0x1397/0x2100 kernel/locking/lockdep.c:5228
       lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5851
       percpu_down_read+0x44/0x1b0 include/linux/percpu-rwsem.h:51
       ext4_writepages_down_read fs/ext4/ext4.h:1773 [inline]
       ext4_writepages+0x1bf/0x3c0 fs/ext4/inode.c:2823
       do_writepages+0x35f/0x880 mm/page-writeback.c:2687
       filemap_fdatawrite_wbc mm/filemap.c:388 [inline]
       __filemap_fdatawrite_range mm/filemap.c:421 [inline]
       filemap_write_and_wait_range+0x283/0x3a0 mm/filemap.c:693
       ext4_insert_range fs/ext4/extents.c:5540 [inline]
       ext4_fallocate+0xe48/0x1ea0 fs/ext4/extents.c:4782
       vfs_fallocate+0x623/0x7a0 fs/open.c:338
       ksys_fallocate fs/open.c:362 [inline]
       __do_sys_fallocate fs/open.c:367 [inline]
       __se_sys_fallocate fs/open.c:365 [inline]
       __x64_sys_fallocate+0xbc/0x110 fs/open.c:365
       do_syscall_x64 arch/x86/entry/common.c:52 [inline]
       do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

other info that might help us debug this:

Chain exists of:
  &sbi->s_writepages_rwsem --> &mm->mmap_lock --> mapping.invalidate_lock

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(mapping.invalidate_lock);
                               lock(&mm->mmap_lock);
                               lock(mapping.invalidate_lock);
  rlock(&sbi->s_writepages_rwsem);

 *** DEADLOCK ***

3 locks held by syz.6.1434/17731:
 #0: ffff888052ed0420 (sb_writers#4){.+.+}-{0:0}, at: file_start_write include/linux/fs.h:3035 [inline]
 #0: ffff888052ed0420 (sb_writers#4){.+.+}-{0:0}, at: vfs_fallocate+0x59d/0x7a0 fs/open.c:337
 #1: ffff8880331a3f68 (&sb->s_type->i_mutex_key#7){++++}-{4:4}, at: inode_lock include/linux/fs.h:877 [inline]
 #1: ffff8880331a3f68 (&sb->s_type->i_mutex_key#7){++++}-{4:4}, at: ext4_insert_range fs/ext4/extents.c:5498 [inline]
 #1: ffff8880331a3f68 (&sb->s_type->i_mutex_key#7){++++}-{4:4}, at: ext4_fallocate+0xab9/0x1ea0 fs/ext4/extents.c:4782
 #2: ffff8880331a4108 (mapping.invalidate_lock){++++}-{4:4}, at: filemap_invalidate_lock include/linux/fs.h:922 [inline]
 #2: ffff8880331a4108 (mapping.invalidate_lock){++++}-{4:4}, at: ext4_insert_range fs/ext4/extents.c:5528 [inline]
 #2: ffff8880331a4108 (mapping.invalidate_lock){++++}-{4:4}, at: ext4_fallocate+0xdae/0x1ea0 fs/ext4/extents.c:4782

stack backtrace:
CPU: 1 UID: 0 PID: 17731 Comm: syz.6.1434 Not tainted 6.14.0-rc6-syzkaller-00263-gd1275e99d1c4 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120
 print_circular_bug+0x13a/0x1b0 kernel/locking/lockdep.c:2076
 check_noncircular+0x36a/0x4a0 kernel/locking/lockdep.c:2208
 check_prev_add kernel/locking/lockdep.c:3163 [inline]
 check_prevs_add kernel/locking/lockdep.c:3282 [inline]
 validate_chain+0x18ef/0x5920 kernel/locking/lockdep.c:3906
 __lock_acquire+0x1397/0x2100 kernel/locking/lockdep.c:5228
 lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5851
 percpu_down_read+0x44/0x1b0 include/linux/percpu-rwsem.h:51
 ext4_writepages_down_read fs/ext4/ext4.h:1773 [inline]
 ext4_writepages+0x1bf/0x3c0 fs/ext4/inode.c:2823
 do_writepages+0x35f/0x880 mm/page-writeback.c:2687
 filemap_fdatawrite_wbc mm/filemap.c:388 [inline]
 __filemap_fdatawrite_range mm/filemap.c:421 [inline]
 filemap_write_and_wait_range+0x283/0x3a0 mm/filemap.c:693
 ext4_insert_range fs/ext4/extents.c:5540 [inline]
 ext4_fallocate+0xe48/0x1ea0 fs/ext4/extents.c:4782
 vfs_fallocate+0x623/0x7a0 fs/open.c:338
 ksys_fallocate fs/open.c:362 [inline]
 __do_sys_fallocate fs/open.c:367 [inline]
 __se_sys_fallocate fs/open.c:365 [inline]
 __x64_sys_fallocate+0xbc/0x110 fs/open.c:365
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7fc8af98d169
Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fc8b07c9038 EFLAGS: 00000246 ORIG_RAX: 000000000000011d
RAX: ffffffffffffffda RBX: 00007fc8afba5fa0 RCX: 00007fc8af98d169
RDX: 0000000000000000 RSI: 0000000000000020 RDI: 0000000000000005
RBP: 00007fc8afa0e2a0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000008000 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000000000 R14: 00007fc8afba5fa0 R15: 00007ffc312866b8
 </TASK>

Crashes (4):
Time Kernel Commit Syzkaller Config Log Report Syz repro C repro VM info Assets (help?) Manager Title
2025/03/16 21:16 upstream d1275e99d1c4 e2826670 .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-fs possible deadlock in ext4_writepages
2024/12/08 23:27 upstream 62b5a46999c7 9ac0fdc6 .config console log report info [disk image] [vmlinux] [kernel image] ci-upstream-kasan-gce-root possible deadlock in ext4_writepages
2024/12/02 22:03 upstream e70140ba0d2b b499ea68 .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-fs possible deadlock in ext4_writepages
2024/10/15 20:23 upstream 2f87d0916ce0 7eb57b4a .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-fs possible deadlock in ext4_writepages
* Struck through repros no longer work on HEAD.