possible deadlock in j1939_sk_queue_drop

possible deadlock in j1939_sk_queue_drop_all
Status: upstream: reported on 2021/09/08 09:41
Reported-by: syzbot+3bd970a1887812621b4c@syzkaller.appspotmail.com
First crash: 41d, last: 30d

Sample crash report:
bridge0: port 2(bridge_slave_1) entered disabled state
bridge0: port 1(bridge_slave_0) entered disabled state
======================================================
WARNING: possible circular locking dependency detected
5.15.0-rc1-syzkaller #0 Not tainted
------------------------------------------------------
syz-executor.1/30349 is trying to acquire lock:
ffff888038718578 (&jsk->sk_session_queue_lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:368 [inline]
ffff888038718578 (&jsk->sk_session_queue_lock){+.-.}-{2:2}, at: j1939_sk_queue_drop_all+0x40/0x2f0 net/can/j1939/socket.c:139

but task is already holding lock:
ffff888038bfd0d0 (&priv->j1939_socks_lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:368 [inline]
ffff888038bfd0d0 (&priv->j1939_socks_lock){+.-.}-{2:2}, at: j1939_sk_netdev_event_netdown+0x28/0x160 net/can/j1939/socket.c:1266

which lock already depends on the new lock.


the existing dependency chain (in reverse order) is:

-> #2 (&priv->j1939_socks_lock){+.-.}-{2:2}:
       __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline]
       _raw_spin_lock_bh+0x2f/0x40 kernel/locking/spinlock.c:178
       spin_lock_bh include/linux/spinlock.h:368 [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+0x2a8/0x36b net/can/j1939/transport.c:1250
       __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
       invoke_softirq kernel/softirq.c:432 [inline]
       __irq_exit_rcu+0x123/0x180 kernel/softirq.c:636
       irq_exit_rcu+0x5/0x20 kernel/softirq.c:648
       sysvec_apic_timer_interrupt+0x93/0xc0 arch/x86/kernel/apic/apic.c:1097
       asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:638
       pte_pfn arch/x86/include/asm/pgtable.h:187 [inline]
       vm_normal_page+0xd0/0x2a0 mm/memory.c:608
       copy_present_pte mm/memory.c:945 [inline]
       copy_pte_range mm/memory.c:1070 [inline]
       copy_pmd_range mm/memory.c:1156 [inline]
       copy_pud_range mm/memory.c:1193 [inline]
       copy_p4d_range mm/memory.c:1217 [inline]
       copy_page_range+0xdaa/0x4420 mm/memory.c:1290
       dup_mmap kernel/fork.c:610 [inline]
       dup_mm+0xa4e/0x13e0 kernel/fork.c:1453
       copy_mm kernel/fork.c:1505 [inline]
       copy_process+0x6fcf/0x7580 kernel/fork.c:2194
       kernel_clone+0xe7/0xac0 kernel/fork.c:2584
       __do_sys_clone+0xc8/0x110 kernel/fork.c:2701
       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

-> #1 (&priv->active_session_list_lock){+.-.}-{2:2}:
       __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline]
       _raw_spin_lock_bh+0x2f/0x40 kernel/locking/spinlock.c:178
       spin_lock_bh include/linux/spinlock.h:368 [inline]
       j1939_session_list_lock net/can/j1939/transport.c:238 [inline]
       j1939_session_activate+0x43/0x4b0 net/can/j1939/transport.c:1554
       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+0x2e/0x35 net/can/j1939/transport.c:1101
       j1939_xtp_rx_abort_one.cold+0x20b/0x33c net/can/j1939/transport.c:1341
       j1939_xtp_rx_abort net/can/j1939/transport.c:1352 [inline]
       j1939_tp_cmd_recv net/can/j1939/transport.c:2085 [inline]
       j1939_tp_recv+0x8f4/0xb40 net/can/j1939/transport.c:2118
       j1939_can_recv+0x6d7/0x930 net/can/j1939/main.c:101
       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:5436
       __netif_receive_skb+0x24/0x1b0 net/core/dev.c:5550
       process_backlog+0x2a5/0x6c0 net/core/dev.c:6427
       __napi_poll+0xaf/0x440 net/core/dev.c:6982
       napi_poll net/core/dev.c:7049 [inline]
       net_rx_action+0x801/0xb40 net/core/dev.c:7136
       __do_softirq+0x29b/0x9c2 kernel/softirq.c:558
       run_ksoftirqd kernel/softirq.c:920 [inline]
       run_ksoftirqd+0x2d/0x60 kernel/softirq.c:912
       smpboot_thread_fn+0x645/0x9c0 kernel/smpboot.c:164
       kthread+0x3e5/0x4d0 kernel/kthread.c:319
       ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295

-> #0 (&jsk->sk_session_queue_lock){+.-.}-{2:2}:
       check_prev_add kernel/locking/lockdep.c:3051 [inline]
       check_prevs_add kernel/locking/lockdep.c:3174 [inline]
       validate_chain kernel/locking/lockdep.c:3789 [inline]
       __lock_acquire+0x2a07/0x54a0 kernel/locking/lockdep.c:5015
       lock_acquire kernel/locking/lockdep.c:5625 [inline]
       lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5590
       __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline]
       _raw_spin_lock_bh+0x2f/0x40 kernel/locking/spinlock.c:178
       spin_lock_bh include/linux/spinlock.h:368 [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:362
       notifier_call_chain+0xb5/0x200 kernel/notifier.c:83
       call_netdevice_notifiers_info+0xb5/0x130 net/core/dev.c:1996
       call_netdevice_notifiers_extack net/core/dev.c:2008 [inline]
       call_netdevice_notifiers net/core/dev.c:2022 [inline]
       __dev_notify_flags+0x1da/0x2b0 net/core/dev.c:8797
       dev_change_flags+0x112/0x170 net/core/dev.c:8833
       do_setlink+0x96d/0x3970 net/core/rtnetlink.c:2719
       rtnl_group_changelink net/core/rtnetlink.c:3242 [inline]
       __rtnl_newlink+0xc06/0x1750 net/core/rtnetlink.c:3396
       rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3506
       rtnetlink_rcv_msg+0x413/0xb80 net/core/rtnetlink.c:5572
       netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2504
       netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline]
       netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1340
       netlink_sendmsg+0x86d/0xdb0 net/netlink/af_netlink.c:1929
       sock_sendmsg_nosec net/socket.c:704 [inline]
       sock_sendmsg+0xcf/0x120 net/socket.c:724
       ____sys_sendmsg+0x6e8/0x810 net/socket.c:2409
       ___sys_sendmsg+0xf3/0x170 net/socket.c:2463
       __sys_sendmsg+0xf3/0x1c0 net/socket.c:2492
       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

other info that might help us debug this:

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

 Possible unsafe locking scenario:

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

 *** DEADLOCK ***

2 locks held by syz-executor.1/30349:
 #0: ffffffff8d0e3968 (rtnl_mutex){+.+.}-{3:3}, at: rtnl_lock net/core/rtnetlink.c:72 [inline]
 #0: ffffffff8d0e3968 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x3be/0xb80 net/core/rtnetlink.c:5569
 #1: ffff888038bfd0d0 (&priv->j1939_socks_lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:368 [inline]
 #1: ffff888038bfd0d0 (&priv->j1939_socks_lock){+.-.}-{2:2}, at: j1939_sk_netdev_event_netdown+0x28/0x160 net/can/j1939/socket.c:1266

stack backtrace:
CPU: 1 PID: 30349 Comm: syz-executor.1 Not tainted 5.15.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __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:2131
 check_prev_add kernel/locking/lockdep.c:3051 [inline]
 check_prevs_add kernel/locking/lockdep.c:3174 [inline]
 validate_chain kernel/locking/lockdep.c:3789 [inline]
 __lock_acquire+0x2a07/0x54a0 kernel/locking/lockdep.c:5015
 lock_acquire kernel/locking/lockdep.c:5625 [inline]
 lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5590
 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline]
 _raw_spin_lock_bh+0x2f/0x40 kernel/locking/spinlock.c:178
 spin_lock_bh include/linux/spinlock.h:368 [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:362
 notifier_call_chain+0xb5/0x200 kernel/notifier.c:83
 call_netdevice_notifiers_info+0xb5/0x130 net/core/dev.c:1996
 call_netdevice_notifiers_extack net/core/dev.c:2008 [inline]
 call_netdevice_notifiers net/core/dev.c:2022 [inline]
 __dev_notify_flags+0x1da/0x2b0 net/core/dev.c:8797
 dev_change_flags+0x112/0x170 net/core/dev.c:8833
 do_setlink+0x96d/0x3970 net/core/rtnetlink.c:2719
 rtnl_group_changelink net/core/rtnetlink.c:3242 [inline]
 __rtnl_newlink+0xc06/0x1750 net/core/rtnetlink.c:3396
 rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3506
 rtnetlink_rcv_msg+0x413/0xb80 net/core/rtnetlink.c:5572
 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2504
 netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline]
 netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1340
 netlink_sendmsg+0x86d/0xdb0 net/netlink/af_netlink.c:1929
 sock_sendmsg_nosec net/socket.c:704 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:724
 ____sys_sendmsg+0x6e8/0x810 net/socket.c:2409
 ___sys_sendmsg+0xf3/0x170 net/socket.c:2463
 __sys_sendmsg+0xf3/0x1c0 net/socket.c:2492
 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
RIP: 0033:0x4665f9
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 bc ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fc6669ff188 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 000000000056bf80 RCX: 00000000004665f9
RDX: 0000000000000000 RSI: 0000000020000000 RDI: 0000000000000003
RBP: 00000000004bfcc4 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 000000000056bf80
R13: 0000000000a9fb1f R14: 00007fc6669ff300 R15: 0000000000022000
batman_adv: batadv0: Interface deactivated: batadv_slave_0
batman_adv: batadv0: Interface deactivated: batadv_slave_1
Crashes (2):
Manager	Time	Kernel	Commit	Syzkaller	Config	Log	Report	Syz repro	C repro	VM info	Title
ci-upstream-kasan-gce	2021/09/14 23:44	upstream	1619b69edce1	07e953c1	.config	log	report			info	possible deadlock in j1939_sk_queue_drop_all
ci-upstream-net-kasan-gce	2021/09/04 19:28	net-next	29ce8f970107	d236a457	.config	log	report			info	possible deadlock in j1939_sk_queue_drop_all