Re: [syzbot] [cgroups?] KASAN: slab-use-after-free Read in pressure_write

[syzbot <syzbot+33e571025d88efd1312c@syzkaller.appspotmail.com>]

Hello,

syzbot has tested the proposed patch but the reproducer is still triggering an issue:
possible deadlock in kernfs_drain_open_files

======================================================
WARNING: possible circular locking dependency detected
syzkaller #0 Not tainted
------------------------------------------------------
syz.3.20/6665 is trying to acquire lock:
ffffffff8df818f8 (drain_mutex){+.+.}-{4:4}, at: kernfs_drain_open_files+0x32/0x730 fs/kernfs/file.c:823

but task is already holding lock:
ffffffff8de0ad98 (cgroup_mutex){+.+.}-{4:4}, at: cgroup_lock include/linux/cgroup.h:394 [inline]
ffffffff8de0ad98 (cgroup_mutex){+.+.}-{4:4}, at: cgroup_kn_lock_live+0x13c/0x230 kernel/cgroup/cgroup.c:1732

which lock already depends on the new lock.


the existing dependency chain (in reverse order) is:

-> #2 (cgroup_mutex){+.+.}-{4:4}:
       __mutex_lock_common kernel/locking/rtmutex_api.c:533 [inline]
       mutex_lock_nested+0x5a/0x1d0 kernel/locking/rtmutex_api.c:552
       cgroup_lock include/linux/cgroup.h:394 [inline]
       cgroup_lock_and_drain_offline+0x8d/0x4a0 kernel/cgroup/cgroup.c:3265
       cgroup_kn_lock_live+0x120/0x230 kernel/cgroup/cgroup.c:1730
       cgroup_subtree_control_write+0x4b3/0x10a0 kernel/cgroup/cgroup.c:3580
       cgroup_file_write+0x36f/0x790 kernel/cgroup/cgroup.c:4311
       kernfs_fop_write_iter+0x3e4/0x580 fs/kernfs/file.c:357
       new_sync_write fs/read_write.c:595 [inline]
       vfs_write+0x629/0xba0 fs/read_write.c:688
       ksys_write+0x156/0x270 fs/read_write.c:740
       do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
       do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

-> #1 (&of->mutex){+.+.}-{4:4}:
       __mutex_lock_common kernel/locking/rtmutex_api.c:533 [inline]
       mutex_lock_nested+0x5a/0x1d0 kernel/locking/rtmutex_api.c:552
       kernfs_fop_write_iter+0x213/0x580 fs/kernfs/file.c:348
       new_sync_write fs/read_write.c:595 [inline]
       vfs_write+0x629/0xba0 fs/read_write.c:688
       ksys_write+0x156/0x270 fs/read_write.c:740
       do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
       do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

-> #0 (drain_mutex){+.+.}-{4:4}:
       check_prev_add kernel/locking/lockdep.c:3165 [inline]
       check_prevs_add kernel/locking/lockdep.c:3284 [inline]
       validate_chain kernel/locking/lockdep.c:3908 [inline]
       __lock_acquire+0x15a5/0x2cf0 kernel/locking/lockdep.c:5237
       lock_acquire+0xf0/0x2e0 kernel/locking/lockdep.c:5868
       __mutex_lock_common kernel/locking/rtmutex_api.c:533 [inline]
       mutex_lock_nested+0x5a/0x1d0 kernel/locking/rtmutex_api.c:552
       kernfs_drain_open_files+0x32/0x730 fs/kernfs/file.c:823
       kernfs_drain+0x470/0x600 fs/kernfs/dir.c:542
       __kernfs_remove+0x3cf/0x660 fs/kernfs/dir.c:1533
       kernfs_remove_by_name_ns+0xaf/0x130 fs/kernfs/dir.c:1742
       kernfs_remove_by_name include/linux/kernfs.h:641 [inline]
       cgroup_rm_file kernel/cgroup/cgroup.c:1758 [inline]
       cgroup_addrm_files+0x684/0xc30 kernel/cgroup/cgroup.c:4483
       cgroup_destroy_locked+0x321/0x630 kernel/cgroup/cgroup.c:6197
       cgroup_rmdir+0x3e8/0x710 kernel/cgroup/cgroup.c:6311
       kernfs_iop_rmdir+0x203/0x350 fs/kernfs/dir.c:1311
       vfs_rmdir+0x400/0x6f0 fs/namei.c:5344
       filename_rmdir+0x292/0x520 fs/namei.c:5399
       __do_sys_rmdir fs/namei.c:5422 [inline]
       __se_sys_rmdir+0x2e/0x140 fs/namei.c:5419
       do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
       do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

other info that might help us debug this:

Chain exists of:
  drain_mutex --> &of->mutex --> cgroup_mutex

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(cgroup_mutex);
                               lock(&of->mutex);
                               lock(cgroup_mutex);
  lock(drain_mutex);

 *** DEADLOCK ***

4 locks held by syz.3.20/6665:
 #0: ffff88803bdc6480 (sb_writers#9){.+.+}-{0:0}, at: mnt_want_write+0x41/0x90 fs/namespace.c:493
 #1: ffff888043d2ef78 (&type->i_mutex_dir_key#6/1){+.+.}-{4:4}, at: inode_lock_nested include/linux/fs.h:1073 [inline]
 #1: ffff888043d2ef78 (&type->i_mutex_dir_key#6/1){+.+.}-{4:4}, at: __start_dirop fs/namei.c:2929 [inline]
 #1: ffff888043d2ef78 (&type->i_mutex_dir_key#6/1){+.+.}-{4:4}, at: start_dirop fs/namei.c:2940 [inline]
 #1: ffff888043d2ef78 (&type->i_mutex_dir_key#6/1){+.+.}-{4:4}, at: filename_rmdir+0x1cd/0x520 fs/namei.c:5392
 #2: ffff888043f66478 (&type->i_mutex_dir_key#6){++++}-{4:4}, at: inode_lock include/linux/fs.h:1028 [inline]
 #2: ffff888043f66478 (&type->i_mutex_dir_key#6){++++}-{4:4}, at: vfs_rmdir+0x109/0x6f0 fs/namei.c:5329
 #3: ffffffff8de0ad98 (cgroup_mutex){+.+.}-{4:4}, at: cgroup_lock include/linux/cgroup.h:394 [inline]
 #3: ffffffff8de0ad98 (cgroup_mutex){+.+.}-{4:4}, at: cgroup_kn_lock_live+0x13c/0x230 kernel/cgroup/cgroup.c:1732

stack backtrace:
CPU: 0 UID: 0 PID: 6665 Comm: syz.3.20 Not tainted syzkaller #0 PREEMPT_{RT,(full)} 
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/18/2026
Call Trace:
 <TASK>
 dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120
 print_circular_bug+0x2e1/0x300 kernel/locking/lockdep.c:2043
 check_noncircular+0x12e/0x150 kernel/locking/lockdep.c:2175
 check_prev_add kernel/locking/lockdep.c:3165 [inline]
 check_prevs_add kernel/locking/lockdep.c:3284 [inline]
 validate_chain kernel/locking/lockdep.c:3908 [inline]
 __lock_acquire+0x15a5/0x2cf0 kernel/locking/lockdep.c:5237
 lock_acquire+0xf0/0x2e0 kernel/locking/lockdep.c:5868
 __mutex_lock_common kernel/locking/rtmutex_api.c:533 [inline]
 mutex_lock_nested+0x5a/0x1d0 kernel/locking/rtmutex_api.c:552
 kernfs_drain_open_files+0x32/0x730 fs/kernfs/file.c:823
 kernfs_drain+0x470/0x600 fs/kernfs/dir.c:542
 __kernfs_remove+0x3cf/0x660 fs/kernfs/dir.c:1533
 kernfs_remove_by_name_ns+0xaf/0x130 fs/kernfs/dir.c:1742
 kernfs_remove_by_name include/linux/kernfs.h:641 [inline]
 cgroup_rm_file kernel/cgroup/cgroup.c:1758 [inline]
 cgroup_addrm_files+0x684/0xc30 kernel/cgroup/cgroup.c:4483
 cgroup_destroy_locked+0x321/0x630 kernel/cgroup/cgroup.c:6197
 cgroup_rmdir+0x3e8/0x710 kernel/cgroup/cgroup.c:6311
 kernfs_iop_rmdir+0x203/0x350 fs/kernfs/dir.c:1311
 vfs_rmdir+0x400/0x6f0 fs/namei.c:5344
 filename_rmdir+0x292/0x520 fs/namei.c:5399
 __do_sys_rmdir fs/namei.c:5422 [inline]
 __se_sys_rmdir+0x2e/0x140 fs/namei.c:5419
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f178b75c819
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 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 e8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f178adb6028 EFLAGS: 00000246 ORIG_RAX: 0000000000000054
RAX: ffffffffffffffda RBX: 00007f178b9d5fa0 RCX: 00007f178b75c819
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000200000000100
RBP: 00007f178b7f2c91 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007f178b9d6038 R14: 00007f178b9d5fa0 R15: 00007fff5fda5b58
 </TASK>


Tested on:

commit:         7c6c4ed8 Merge tag 'vfs-7.0-rc8.fixes' of git://git.ke..
git tree:       upstream
console output: https://syzkaller.appspot.com/x/log.txt?x=141c7f4e580000
kernel config:  https://syzkaller.appspot.com/x/.config?x=45cb3c58fd963c27
dashboard link: https://syzkaller.appspot.com/bug?extid=33e571025d88efd1312c
compiler:       Debian clang version 21.1.8 (++20251221033036+2078da43e25a-1~exp1~20251221153213.50), Debian LLD 21.1.8
patch:          https://syzkaller.appspot.com/x/patch.diff?x=169a1106580000