vxcan1: j1939_tp_rxtimer: 0xffff888076211400: rx timeout, send abort vxcan1: j1939_tp_rxtimer: 0xffff888076211400: abort rx timeout. Force session deactivation ====================================================== WARNING: possible circular locking dependency detected 5.17.0-rc1-syzkaller #0 Not tainted ------------------------------------------------------ kworker/u4:1/3680 is trying to acquire lock: ffff88804698d088 (&priv->active_session_list_lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:354 [inline] ffff88804698d088 (&priv->active_session_list_lock){+.-.}-{2:2}, at: j1939_session_list_lock net/can/j1939/transport.c:238 [inline] ffff88804698d088 (&priv->active_session_list_lock){+.-.}-{2:2}, at: j1939_session_activate+0x43/0x4b0 net/can/j1939/transport.c:1553 but task is already holding lock: ffff8880798235c0 (&jsk->sk_session_queue_lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:354 [inline] ffff8880798235c0 (&jsk->sk_session_queue_lock){+.-.}-{2:2}, at: j1939_sk_queue_activate_next+0x56/0x460 net/can/j1939/socket.c:204 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&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:1919 call_netdevice_notifiers_extack net/core/dev.c:1931 [inline] call_netdevice_notifiers net/core/dev.c:1945 [inline] __dev_notify_flags+0x1da/0x2b0 net/core/dev.c:8179 dev_change_flags+0x112/0x170 net/core/dev.c:8215 do_setlink+0x96d/0x3a10 net/core/rtnetlink.c:2729 __rtnl_newlink+0xde7/0x1750 net/core/rtnetlink.c:3412 rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3527 rtnetlink_rcv_msg+0x413/0xb80 net/core/rtnetlink.c:5592 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2494 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x539/0x7e0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x904/0xe00 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:725 ____sys_sendmsg+0x6e8/0x810 net/socket.c:2413 ___sys_sendmsg+0xf3/0x170 net/socket.c:2467 __sys_sendmsg+0xe5/0x1b0 net/socket.c:2496 do_syscall_32_irqs_on arch/x86/entry/common.c:112 [inline] __do_fast_syscall_32+0x65/0xf0 arch/x86/entry/common.c:178 do_fast_syscall_32+0x2f/0x70 arch/x86/entry/common.c:203 entry_SYSENTER_compat_after_hwframe+0x4d/0x5c -> #1 (&priv->j1939_socks_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_errqueue+0x9f/0x1a0 net/can/j1939/socket.c:1078 __j1939_session_cancel+0x3b9/0x460 net/can/j1939/transport.c:1124 j1939_tp_rxtimer.cold+0x15e/0x1aa 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 invoke_softirq kernel/softirq.c:432 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:637 irq_exit_rcu+0x5/0x20 kernel/softirq.c:649 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 bytes_is_nonzero mm/kasan/generic.c:84 [inline] memory_is_nonzero mm/kasan/generic.c:102 [inline] memory_is_poisoned_n mm/kasan/generic.c:128 [inline] memory_is_poisoned mm/kasan/generic.c:159 [inline] check_region_inline mm/kasan/generic.c:180 [inline] kasan_check_range+0xcd/0x180 mm/kasan/generic.c:189 instrument_atomic_read include/linux/instrumented.h:71 [inline] test_bit include/asm-generic/bitops/instrumented-non-atomic.h:134 [inline] cpumask_test_cpu include/linux/cpumask.h:379 [inline] cpu_online include/linux/cpumask.h:921 [inline] trace_lock_release include/trace/events/lock.h:58 [inline] lock_release+0xa1/0x720 kernel/locking/lockdep.c:5650 __raw_spin_unlock include/linux/spinlock_api_smp.h:141 [inline] _raw_spin_unlock+0x12/0x40 kernel/locking/spinlock.c:186 spin_unlock include/linux/spinlock.h:389 [inline] alloc_fd+0x2f0/0x670 fs/file.c:524 do_sys_openat2+0x134/0x4d0 fs/open.c:1212 do_sys_open fs/open.c:1230 [inline] __do_sys_openat fs/open.c:1246 [inline] __se_sys_openat fs/open.c:1241 [inline] __x64_sys_openat+0x13f/0x1f0 fs/open.c:1241 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->active_session_list_lock){+.-.}-{2:2}: check_prev_add kernel/locking/lockdep.c:3063 [inline] check_prevs_add kernel/locking/lockdep.c:3186 [inline] validate_chain kernel/locking/lockdep.c:3801 [inline] __lock_acquire+0x2a2c/0x5470 kernel/locking/lockdep.c:5027 lock_acquire kernel/locking/lockdep.c:5639 [inline] lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5604 __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+0x2e/0x35 net/can/j1939/transport.c:1101 j1939_tp_rxtimer.cold+0xbc/0x1aa net/can/j1939/transport.c:1228 __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:637 irq_exit_rcu+0x5/0x20 kernel/softirq.c:649 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 lock_acquire+0x1ef/0x510 kernel/locking/lockdep.c:5607 rcu_lock_acquire include/linux/rcupdate.h:268 [inline] rcu_read_lock include/linux/rcupdate.h:694 [inline] batadv_nc_purge_orig_hash net/batman-adv/network-coding.c:408 [inline] batadv_nc_worker+0x12d/0xfa0 net/batman-adv/network-coding.c:719 process_one_work+0x9ac/0x1650 kernel/workqueue.c:2307 worker_thread+0x657/0x1110 kernel/workqueue.c:2454 kthread+0x2e9/0x3a0 kernel/kthread.c:377 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295 other info that might help us debug this: Chain exists of: &priv->active_session_list_lock --> &priv->j1939_socks_lock --> &jsk->sk_session_queue_lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&jsk->sk_session_queue_lock); lock(&priv->j1939_socks_lock); lock(&jsk->sk_session_queue_lock); lock(&priv->active_session_list_lock); *** DEADLOCK *** 4 locks held by kworker/u4:1/3680: #0: ffff888021bf6138 ((wq_completion)bat_events){+.+.}-{0:0}, at: arch_atomic64_set arch/x86/include/asm/atomic64_64.h:34 [inline] #0: ffff888021bf6138 ((wq_completion)bat_events){+.+.}-{0:0}, at: arch_atomic_long_set include/linux/atomic/atomic-long.h:41 [inline] #0: ffff888021bf6138 ((wq_completion)bat_events){+.+.}-{0:0}, at: atomic_long_set include/linux/atomic/atomic-instrumented.h:1280 [inline] #0: ffff888021bf6138 ((wq_completion)bat_events){+.+.}-{0:0}, at: set_work_data kernel/workqueue.c:631 [inline] #0: ffff888021bf6138 ((wq_completion)bat_events){+.+.}-{0:0}, at: set_work_pool_and_clear_pending kernel/workqueue.c:658 [inline] #0: ffff888021bf6138 ((wq_completion)bat_events){+.+.}-{0:0}, at: process_one_work+0x890/0x1650 kernel/workqueue.c:2278 #1: ffffc90002a6fdb8 ((work_completion)(&(&bat_priv->nc.work)->work)){+.+.}-{0:0}, at: process_one_work+0x8c4/0x1650 kernel/workqueue.c:2282 #2: ffffffff8bb83aa0 (rcu_read_lock){....}-{1:2}, at: batadv_nc_purge_orig_hash net/batman-adv/network-coding.c:406 [inline] #2: ffffffff8bb83aa0 (rcu_read_lock){....}-{1:2}, at: batadv_nc_worker+0xf3/0xfa0 net/batman-adv/network-coding.c:719 #3: ffff8880798235c0 (&jsk->sk_session_queue_lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:354 [inline] #3: ffff8880798235c0 (&jsk->sk_session_queue_lock){+.-.}-{2:2}, at: j1939_sk_queue_activate_next+0x56/0x460 net/can/j1939/socket.c:204 stack backtrace: CPU: 0 PID: 3680 Comm: kworker/u4:1 Not tainted 5.17.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: bat_events batadv_nc_worker 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:2143 check_prev_add kernel/locking/lockdep.c:3063 [inline] check_prevs_add kernel/locking/lockdep.c:3186 [inline] validate_chain kernel/locking/lockdep.c:3801 [inline] __lock_acquire+0x2a2c/0x5470 kernel/locking/lockdep.c:5027 lock_acquire kernel/locking/lockdep.c:5639 [inline] lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5604 __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+0x2e/0x35 net/can/j1939/transport.c:1101 j1939_tp_rxtimer.cold+0xbc/0x1aa net/can/j1939/transport.c:1228 __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:637 irq_exit_rcu+0x5/0x20 kernel/softirq.c:649 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 RIP: 0010:lock_acquire+0x1ef/0x510 kernel/locking/lockdep.c:5607 Code: 31 a5 7e 83 f8 01 0f 85 b4 02 00 00 9c 58 f6 c4 02 0f 85 9f 02 00 00 48 83 7c 24 08 00 74 01 fb 48 b8 00 00 00 00 00 fc ff df <48> 01 c3 48 c7 03 00 00 00 00 48 c7 43 08 00 00 00 00 48 8b 84 24 RSP: 0018:ffffc90002a6fba8 EFLAGS: 00000206 RAX: dffffc0000000000 RBX: 1ffff9200054df77 RCX: eca22ac27fdf2f82 RDX: 1ffff110030fbc2b RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000000 R08: 0000000000000000 R09: ffffffff8ffce947 R10: fffffbfff1ff9d28 R11: 0000000000000000 R12: 0000000000000002 R13: 0000000000000000 R14: ffffffff8bb83aa0 R15: 0000000000000000 rcu_lock_acquire include/linux/rcupdate.h:268 [inline] rcu_read_lock include/linux/rcupdate.h:694 [inline] batadv_nc_purge_orig_hash net/batman-adv/network-coding.c:408 [inline] batadv_nc_worker+0x12d/0xfa0 net/batman-adv/network-coding.c:719 process_one_work+0x9ac/0x1650 kernel/workqueue.c:2307 worker_thread+0x657/0x1110 kernel/workqueue.c:2454 kthread+0x2e9/0x3a0 kernel/kthread.c:377 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295 ---------------- Code disassembly (best guess): 0: 31 a5 7e 83 f8 01 xor %esp,0x1f8837e(%rbp) 6: 0f 85 b4 02 00 00 jne 0x2c0 c: 9c pushfq d: 58 pop %rax e: f6 c4 02 test $0x2,%ah 11: 0f 85 9f 02 00 00 jne 0x2b6 17: 48 83 7c 24 08 00 cmpq $0x0,0x8(%rsp) 1d: 74 01 je 0x20 1f: fb sti 20: 48 b8 00 00 00 00 00 movabs $0xdffffc0000000000,%rax 27: fc ff df * 2a: 48 01 c3 add %rax,%rbx <-- trapping instruction 2d: 48 c7 03 00 00 00 00 movq $0x0,(%rbx) 34: 48 c7 43 08 00 00 00 movq $0x0,0x8(%rbx) 3b: 00 3c: 48 rex.W 3d: 8b .byte 0x8b 3e: 84 .byte 0x84 3f: 24 .byte 0x24