syzbot

vcan0: j1939_tp_rxtimer: 0xffff88806f4ff000: rx timeout, send abort
======================================================
WARNING: possible circular locking dependency detected
5.18.0-rc4-syzkaller-00192-g38d741cb70b3 #0 Not tainted
------------------------------------------------------
ksoftirqd/0/15 is trying to acquire lock:
ffff888078c950d0 (&priv->j1939_socks_lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:354 [inline]
ffff888078c950d0 (&priv->j1939_socks_lock){+.-.}-{2:2}, at: j1939_sk_errqueue+0x9f/0x1a0 net/can/j1939/socket.c:1078

but task is already holding lock:
ffff888078c95088 (&priv->active_session_list_lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:354 [inline]
ffff888078c95088 (&priv->active_session_list_lock){+.-.}-{2:2}, at: j1939_session_list_lock net/can/j1939/transport.c:238 [inline]
ffff888078c95088 (&priv->active_session_list_lock){+.-.}-{2:2}, at: j1939_tp_rxtimer+0xe5/0x220 net/can/j1939/transport.c:1240

which lock already depends on the new lock.


the existing dependency chain (in reverse order) is:

-> #2 (&priv->active_session_list_lock){+.-.}-{2:2}:
       __raw_spin_lock_bh include/linux/spinlock_api_smp.h:126 [inline]
       _raw_spin_lock_bh+0x2f/0x40 kernel/locking/spinlock.c:178
       spin_lock_bh include/linux/spinlock.h:354 [inline]
       j1939_session_list_lock net/can/j1939/transport.c:238 [inline]
       j1939_session_activate+0x43/0x4b0 net/can/j1939/transport.c:1553
       j1939_sk_queue_activate_next_locked net/can/j1939/socket.c:181 [inline]
       j1939_sk_queue_activate_next+0x29b/0x460 net/can/j1939/socket.c:205
       j1939_session_deactivate_activate_next net/can/j1939/transport.c:1101 [inline]
       j1939_session_completed+0x19a/0x1f0 net/can/j1939/transport.c:1214
       j1939_xtp_rx_eoma_one net/can/j1939/transport.c:1384 [inline]
       j1939_xtp_rx_eoma+0x2a6/0x5f0 net/can/j1939/transport.c:1399
       j1939_tp_cmd_recv net/can/j1939/transport.c:2088 [inline]
       j1939_tp_recv+0x930/0xcb0 net/can/j1939/transport.c:2133
       j1939_can_recv+0x6ff/0x9a0 net/can/j1939/main.c:108
       deliver net/can/af_can.c:574 [inline]
       can_rcv_filter+0x5d4/0x8d0 net/can/af_can.c:608
       can_receive+0x31d/0x580 net/can/af_can.c:665
       can_rcv+0x120/0x1c0 net/can/af_can.c:696
       __netif_receive_skb_one_core+0x114/0x180 net/core/dev.c:5405
       __netif_receive_skb+0x24/0x1b0 net/core/dev.c:5519
       process_backlog+0x3a0/0x7c0 net/core/dev.c:5847
       __napi_poll+0xb3/0x6e0 net/core/dev.c:6413
       napi_poll net/core/dev.c:6480 [inline]
       net_rx_action+0x8ec/0xc60 net/core/dev.c:6567
       __do_softirq+0x29b/0x9c2 kernel/softirq.c:558
       run_ksoftirqd kernel/softirq.c:921 [inline]
       run_ksoftirqd+0x2d/0x60 kernel/softirq.c:913
       smpboot_thread_fn+0x645/0x9c0 kernel/smpboot.c:164
       kthread+0x2e9/0x3a0 kernel/kthread.c:376
       ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:298

-> #1 (&jsk->sk_session_queue_lock){+.-.}-{2:2}:
       __raw_spin_lock_bh include/linux/spinlock_api_smp.h:126 [inline]
       _raw_spin_lock_bh+0x2f/0x40 kernel/locking/spinlock.c:178
       spin_lock_bh include/linux/spinlock.h:354 [inline]
       j1939_sk_queue_drop_all+0x40/0x2f0 net/can/j1939/socket.c:139
       j1939_sk_netdev_event_netdown+0x7b/0x160 net/can/j1939/socket.c:1272
       j1939_netdev_notify+0x199/0x1d0 net/can/j1939/main.c:372
       notifier_call_chain+0xb5/0x200 kernel/notifier.c:84
       call_netdevice_notifiers_info+0xb5/0x130 net/core/dev.c:1938
       call_netdevice_notifiers_extack net/core/dev.c:1976 [inline]
       call_netdevice_notifiers net/core/dev.c:1990 [inline]
       __dev_notify_flags+0x1da/0x2b0 net/core/dev.c:8473
       dev_change_flags+0x112/0x170 net/core/dev.c:8509
       do_setlink+0x96d/0x3a20 net/core/rtnetlink.c:2731
       __rtnl_newlink+0xdf8/0x1760 net/core/rtnetlink.c:3416
       rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3531
       rtnetlink_rcv_msg+0x413/0xb80 net/core/rtnetlink.c:5993
       netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2503
       netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline]
       netlink_unicast+0x543/0x7f0 net/netlink/af_netlink.c:1345
       netlink_sendmsg+0x904/0xe00 net/netlink/af_netlink.c:1921
       sock_sendmsg_nosec net/socket.c:705 [inline]
       sock_sendmsg+0xcf/0x120 net/socket.c:725
       ____sys_sendmsg+0x6e2/0x800 net/socket.c:2413
       ___sys_sendmsg+0xf3/0x170 net/socket.c:2467
       __sys_sendmsg+0xe5/0x1b0 net/socket.c:2496
       do_syscall_x64 arch/x86/entry/common.c:50 [inline]
       do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
       entry_SYSCALL_64_after_hwframe+0x44/0xae

-> #0 (&priv->j1939_socks_lock){+.-.}-{2:2}:
       check_prev_add kernel/locking/lockdep.c:3065 [inline]
       check_prevs_add kernel/locking/lockdep.c:3188 [inline]
       validate_chain kernel/locking/lockdep.c:3803 [inline]
       __lock_acquire+0x2ac6/0x56c0 kernel/locking/lockdep.c:5029
       lock_acquire kernel/locking/lockdep.c:5641 [inline]
       lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5606
       __raw_spin_lock_bh include/linux/spinlock_api_smp.h:126 [inline]
       _raw_spin_lock_bh+0x2f/0x40 kernel/locking/spinlock.c:178
       spin_lock_bh include/linux/spinlock.h:354 [inline]
       j1939_sk_errqueue+0x9f/0x1a0 net/can/j1939/socket.c:1078
       __j1939_session_cancel+0x3b9/0x460 net/can/j1939/transport.c:1124
       j1939_tp_rxtimer.cold+0x1f6/0x24f net/can/j1939/transport.c:1249
       __run_hrtimer kernel/time/hrtimer.c:1685 [inline]
       __hrtimer_run_queues+0x609/0xe50 kernel/time/hrtimer.c:1749
       hrtimer_run_softirq+0x17b/0x360 kernel/time/hrtimer.c:1766
       __do_softirq+0x29b/0x9c2 kernel/softirq.c:558
       run_ksoftirqd kernel/softirq.c:921 [inline]
       run_ksoftirqd+0x2d/0x60 kernel/softirq.c:913
       smpboot_thread_fn+0x645/0x9c0 kernel/smpboot.c:164
       kthread+0x2e9/0x3a0 kernel/kthread.c:376
       ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:298

other info that might help us debug this:

Chain exists of:
  &priv->j1939_socks_lock --> &jsk->sk_session_queue_lock --> &priv->active_session_list_lock

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&priv->active_session_list_lock);
                               lock(&jsk->sk_session_queue_lock);
                               lock(&priv->active_session_list_lock);
  lock(&priv->j1939_socks_lock);

 *** DEADLOCK ***

1 lock held by ksoftirqd/0/15:
 #0: ffff888078c95088 (&priv->active_session_list_lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:354 [inline]
 #0: ffff888078c95088 (&priv->active_session_list_lock){+.-.}-{2:2}, at: j1939_session_list_lock net/can/j1939/transport.c:238 [inline]
 #0: ffff888078c95088 (&priv->active_session_list_lock){+.-.}-{2:2}, at: j1939_tp_rxtimer+0xe5/0x220 net/can/j1939/transport.c:1240

stack backtrace:
CPU: 0 PID: 15 Comm: ksoftirqd/0 Not tainted 5.18.0-rc4-syzkaller-00192-g38d741cb70b3 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106
 check_noncircular+0x25f/0x2e0 kernel/locking/lockdep.c:2145
 check_prev_add kernel/locking/lockdep.c:3065 [inline]
 check_prevs_add kernel/locking/lockdep.c:3188 [inline]
 validate_chain kernel/locking/lockdep.c:3803 [inline]
 __lock_acquire+0x2ac6/0x56c0 kernel/locking/lockdep.c:5029
 lock_acquire kernel/locking/lockdep.c:5641 [inline]
 lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5606
 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:126 [inline]
 _raw_spin_lock_bh+0x2f/0x40 kernel/locking/spinlock.c:178
 spin_lock_bh include/linux/spinlock.h:354 [inline]
 j1939_sk_errqueue+0x9f/0x1a0 net/can/j1939/socket.c:1078
 __j1939_session_cancel+0x3b9/0x460 net/can/j1939/transport.c:1124
 j1939_tp_rxtimer.cold+0x1f6/0x24f net/can/j1939/transport.c:1249
 __run_hrtimer kernel/time/hrtimer.c:1685 [inline]
 __hrtimer_run_queues+0x609/0xe50 kernel/time/hrtimer.c:1749
 hrtimer_run_softirq+0x17b/0x360 kernel/time/hrtimer.c:1766
 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558
 run_ksoftirqd kernel/softirq.c:921 [inline]
 run_ksoftirqd+0x2d/0x60 kernel/softirq.c:913
 smpboot_thread_fn+0x645/0x9c0 kernel/smpboot.c:164
 kthread+0x2e9/0x3a0 kernel/kthread.c:376
 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:298
 </TASK>
vcan0: j1939_tp_rxtimer: 0xffff88806f4ff000: abort rx timeout. Force session deactivation