syzbot


possible deadlock in sk_psock_stop

Status: upstream: reported on 2024/04/10 11:39
Reported-by: syzbot+e69c6393efd5d9fdfb96@syzkaller.appspotmail.com
First crash: 27d, last: 8d03h

Sample crash report:
======================================================
WARNING: possible circular locking dependency detected
5.15.157-syzkaller #0 Not tainted
------------------------------------------------------
syz-executor.1/3528 is trying to acquire lock:
ffff888019864238 (&psock->ingress_lock){+...}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:368 [inline]
ffff888019864238 (&psock->ingress_lock){+...}-{2:2}, at: sk_psock_stop+0x31/0x4c0 net/core/skmsg.c:802

but task is already holding lock:
ffff888061998068 (&htab->buckets[i].lock){+.-.}-{2:2}, at: sock_hash_delete_elem+0x177/0x400 net/core/sock_map.c:943

which lock already depends on the new lock.


the existing dependency chain (in reverse order) is:

-> #1 (&htab->buckets[i].lock){+.-.}-{2:2}:
       lock_acquire+0x1db/0x4f0 kernel/locking/lockdep.c:5623
       __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline]
       _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:178
       sock_hash_delete_elem+0x177/0x400 net/core/sock_map.c:943
       0xffffffffa002c76d
       bpf_dispatcher_nop_func include/linux/bpf.h:790 [inline]
       __bpf_prog_run include/linux/filter.h:621 [inline]
       bpf_prog_run include/linux/filter.h:635 [inline]
       __bpf_trace_run kernel/trace/bpf_trace.c:1880 [inline]
       bpf_trace_run2+0x29e/0x340 kernel/trace/bpf_trace.c:1917
       __bpf_trace_kfree+0x6e/0x90 include/trace/events/kmem.h:118
       trace_kfree include/trace/events/kmem.h:118 [inline]
       kfree+0x22f/0x270 mm/slub.c:4549
       skb_free_head net/core/skbuff.c:655 [inline]
       skb_release_data+0x73a/0x8a0 net/core/skbuff.c:677
       skb_release_all net/core/skbuff.c:742 [inline]
       __kfree_skb net/core/skbuff.c:756 [inline]
       consume_skb+0xa3/0x140 net/core/skbuff.c:914
       __sk_msg_free+0x2cd/0x350 net/core/skmsg.c:205
       sk_msg_free net/core/skmsg.c:218 [inline]
       __sk_psock_purge_ingress_msg net/core/skmsg.c:769 [inline]
       __sk_psock_zap_ingress net/core/skmsg.c:787 [inline]
       sk_psock_stop+0x44c/0x4c0 net/core/skmsg.c:805
       sock_map_close+0x17c/0x290 net/core/sock_map.c:1578
       unix_release+0x7e/0xc0 net/unix/af_unix.c:949
       __sock_release net/socket.c:649 [inline]
       sock_close+0xcd/0x230 net/socket.c:1336
       __fput+0x3bf/0x890 fs/file_table.c:280
       task_work_run+0x129/0x1a0 kernel/task_work.c:164
       tracehook_notify_resume include/linux/tracehook.h:189 [inline]
       exit_to_user_mode_loop+0x106/0x130 kernel/entry/common.c:181
       exit_to_user_mode_prepare+0xb1/0x140 kernel/entry/common.c:214
       __syscall_exit_to_user_mode_work kernel/entry/common.c:296 [inline]
       syscall_exit_to_user_mode+0x5d/0x240 kernel/entry/common.c:307
       do_syscall_64+0x47/0xb0 arch/x86/entry/common.c:86
       entry_SYSCALL_64_after_hwframe+0x66/0xd0

-> #0 (&psock->ingress_lock){+...}-{2:2}:
       check_prev_add kernel/locking/lockdep.c:3053 [inline]
       check_prevs_add kernel/locking/lockdep.c:3172 [inline]
       validate_chain+0x1649/0x5930 kernel/locking/lockdep.c:3788
       __lock_acquire+0x1295/0x1ff0 kernel/locking/lockdep.c:5012
       lock_acquire+0x1db/0x4f0 kernel/locking/lockdep.c:5623
       __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline]
       _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:178
       spin_lock_bh include/linux/spinlock.h:368 [inline]
       sk_psock_stop+0x31/0x4c0 net/core/skmsg.c:802
       sk_psock_drop+0x2aa/0x3b0 net/core/skmsg.c:844
       sock_hash_delete_elem+0x388/0x400 net/core/sock_map.c:947
       bpf_prog_2c29ac5cdc6b1842+0x3a/0xfc0
       bpf_dispatcher_nop_func include/linux/bpf.h:790 [inline]
       __bpf_prog_run include/linux/filter.h:628 [inline]
       bpf_prog_run include/linux/filter.h:635 [inline]
       __bpf_trace_run kernel/trace/bpf_trace.c:1880 [inline]
       bpf_trace_run4+0x1ea/0x390 kernel/trace/bpf_trace.c:1919
       __traceiter_ext4_free_blocks+0x87/0xd0 include/trace/events/ext4.h:901
       trace_ext4_free_blocks include/trace/events/ext4.h:901 [inline]
       ext4_free_blocks+0x2e0e/0x2ea0 fs/ext4/mballoc.c:6230
       ext4_remove_blocks fs/ext4/extents.c:2519 [inline]
       ext4_ext_rm_leaf fs/ext4/extents.c:2685 [inline]
       ext4_ext_remove_space+0x24da/0x4db0 fs/ext4/extents.c:2933
       ext4_ext_truncate+0x191/0x250 fs/ext4/extents.c:4448
       ext4_truncate+0x9fd/0x1130 fs/ext4/inode.c:4238
       ext4_evict_inode+0xba1/0x1100 fs/ext4/inode.c:289
       evict+0x2a4/0x620 fs/inode.c:587
       d_delete_notify include/linux/fsnotify.h:261 [inline]
       vfs_rmdir+0x33c/0x460 fs/namei.c:4162
       do_rmdir+0x368/0x670 fs/namei.c:4210
       __do_sys_unlinkat fs/namei.c:4390 [inline]
       __se_sys_unlinkat fs/namei.c:4384 [inline]
       __x64_sys_unlinkat+0xdc/0xf0 fs/namei.c:4384
       do_syscall_x64 arch/x86/entry/common.c:50 [inline]
       do_syscall_64+0x3b/0xb0 arch/x86/entry/common.c:80
       entry_SYSCALL_64_after_hwframe+0x66/0xd0

other info that might help us debug this:

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&htab->buckets[i].lock);
                               lock(&psock->ingress_lock);
                               lock(&htab->buckets[i].lock);
  lock(&psock->ingress_lock);

 *** DEADLOCK ***

7 locks held by syz-executor.1/3528:
 #0: ffff8880245e4460 (sb_writers#5){.+.+}-{0:0}, at: mnt_want_write+0x3b/0x80 fs/namespace.c:377
 #1: ffff8880704ba1d8 (&type->i_mutex_dir_key#4/1){+.+.}-{3:3}, at: inode_lock_nested include/linux/fs.h:824 [inline]
 #1: ffff8880704ba1d8 (&type->i_mutex_dir_key#4/1){+.+.}-{3:3}, at: do_rmdir+0x225/0x670 fs/namei.c:4197
 #2: ffff8880245e4650 (sb_internal){.+.+}-{0:0}, at: __sb_start_write include/linux/fs.h:1811 [inline]
 #2: ffff8880245e4650 (sb_internal){.+.+}-{0:0}, at: sb_start_intwrite include/linux/fs.h:1928 [inline]
 #2: ffff8880245e4650 (sb_internal){.+.+}-{0:0}, at: ext4_evict_inode+0x375/0x1100 fs/ext4/inode.c:243
 #3: ffff88814b708990 (jbd2_handle){++++}-{0:0}, at: start_this_handle+0x12b9/0x1570 fs/jbd2/transaction.c:462
 #4: ffff88805d851668 (&ei->i_data_sem){++++}-{3:3}, at: ext4_truncate+0x974/0x1130 fs/ext4/inode.c:4233
 #5: ffffffff8c91fb20 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire+0x5/0x30 include/linux/rcupdate.h:311
 #6: ffff888061998068 (&htab->buckets[i].lock){+.-.}-{2:2}, at: sock_hash_delete_elem+0x177/0x400 net/core/sock_map.c:943

stack backtrace:
CPU: 1 PID: 3528 Comm: syz-executor.1 Not tainted 5.15.157-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x1e3/0x2d0 lib/dump_stack.c:106
 check_noncircular+0x2f8/0x3b0 kernel/locking/lockdep.c:2133
 check_prev_add kernel/locking/lockdep.c:3053 [inline]
 check_prevs_add kernel/locking/lockdep.c:3172 [inline]
 validate_chain+0x1649/0x5930 kernel/locking/lockdep.c:3788
 __lock_acquire+0x1295/0x1ff0 kernel/locking/lockdep.c:5012
 lock_acquire+0x1db/0x4f0 kernel/locking/lockdep.c:5623
 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline]
 _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:178
 spin_lock_bh include/linux/spinlock.h:368 [inline]
 sk_psock_stop+0x31/0x4c0 net/core/skmsg.c:802
 sk_psock_drop+0x2aa/0x3b0 net/core/skmsg.c:844
 sock_hash_delete_elem+0x388/0x400 net/core/sock_map.c:947
 bpf_prog_2c29ac5cdc6b1842+0x3a/0xfc0
 bpf_dispatcher_nop_func include/linux/bpf.h:790 [inline]
 __bpf_prog_run include/linux/filter.h:628 [inline]
 bpf_prog_run include/linux/filter.h:635 [inline]
 __bpf_trace_run kernel/trace/bpf_trace.c:1880 [inline]
 bpf_trace_run4+0x1ea/0x390 kernel/trace/bpf_trace.c:1919
 __traceiter_ext4_free_blocks+0x87/0xd0 include/trace/events/ext4.h:901
 trace_ext4_free_blocks include/trace/events/ext4.h:901 [inline]
 ext4_free_blocks+0x2e0e/0x2ea0 fs/ext4/mballoc.c:6230
 ext4_remove_blocks fs/ext4/extents.c:2519 [inline]
 ext4_ext_rm_leaf fs/ext4/extents.c:2685 [inline]
 ext4_ext_remove_space+0x24da/0x4db0 fs/ext4/extents.c:2933
 ext4_ext_truncate+0x191/0x250 fs/ext4/extents.c:4448
 ext4_truncate+0x9fd/0x1130 fs/ext4/inode.c:4238
 ext4_evict_inode+0xba1/0x1100 fs/ext4/inode.c:289
 evict+0x2a4/0x620 fs/inode.c:587
 d_delete_notify include/linux/fsnotify.h:261 [inline]
 vfs_rmdir+0x33c/0x460 fs/namei.c:4162
 do_rmdir+0x368/0x670 fs/namei.c:4210
 __do_sys_unlinkat fs/namei.c:4390 [inline]
 __se_sys_unlinkat fs/namei.c:4384 [inline]
 __x64_sys_unlinkat+0xdc/0xf0 fs/namei.c:4384
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x3b/0xb0 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x66/0xd0
RIP: 0033:0x7fd4cb0b9687
Code: 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 b8 07 01 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007ffed17cfa68 EFLAGS: 00000207 ORIG_RAX: 0000000000000107
RAX: ffffffffffffffda RBX: 0000000000000065 RCX: 00007fd4cb0b9687
RDX: 0000000000000200 RSI: 00007ffed17d0be0 RDI: 00000000ffffff9c
RBP: 00007fd4cb1053b9 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000100 R11: 0000000000000207 R12: 00007ffed17d0be0
R13: 00007fd4cb1053b9 R14: 000000000001936c R15: 0000000000000002
 </TASK>

Crashes (2):
Time Kernel Commit Syzkaller Config Log Report Syz repro C repro VM info Assets (help?) Manager Title
2024/04/29 18:44 linux-5.15.y b925f60c6ee7 27e33c58 .config console log report info [disk image] [vmlinux] [kernel image] ci2-linux-5-15-kasan-perf possible deadlock in sk_psock_stop
2024/04/10 11:38 linux-5.15.y 9465fef4ae35 4320ec32 .config console log report info [disk image] [vmlinux] [kernel image] ci2-linux-5-15-kasan-perf possible deadlock in sk_psock_stop
* Struck through repros no longer work on HEAD.