ceph: No mds server is up or the cluster is laggy ================================ WARNING: inconsistent lock state 4.19.198-syzkaller #0 Not tainted -------------------------------- inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. syz-fuzzer/8099 [HC0[0]:SC1[1]:HE1:SE0] takes: 00000000c15ef57b (slock-AF_BLUETOOTH-BTPROTO_SCO){+.?.}, at: spin_lock include/linux/spinlock.h:329 [inline] 00000000c15ef57b (slock-AF_BLUETOOTH-BTPROTO_SCO){+.?.}, at: sco_sock_timeout+0x31/0x210 net/bluetooth/sco.c:82 {SOFTIRQ-ON-W} state was registered at: mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline] _raw_spin_lock+0x2a/0x40 kernel/locking/spinlock.c:144 spin_lock include/linux/spinlock.h:329 [inline] sco_conn_del+0xe2/0x240 net/bluetooth/sco.c:175 sco_disconn_cfm+0x74/0xb0 net/bluetooth/sco.c:1133 hci_disconn_cfm include/net/bluetooth/hci_core.h:1262 [inline] hci_conn_hash_flush+0x127/0x260 net/bluetooth/hci_conn.c:1512 hci_dev_do_close+0x588/0xf20 net/bluetooth/hci_core.c:1665 hci_unregister_dev+0x18b/0x910 net/bluetooth/hci_core.c:3278 libceph: connect [d::]:6789 error -101 vhci_release+0x70/0xe0 drivers/bluetooth/hci_vhci.c:354 __fput+0x2ce/0x890 fs/file_table.c:278 task_work_run+0x148/0x1c0 kernel/task_work.c:113 exit_task_work include/linux/task_work.h:22 [inline] do_exit+0xbf3/0x2be0 kernel/exit.c:870 do_group_exit+0x125/0x310 kernel/exit.c:967 __do_sys_exit_group kernel/exit.c:978 [inline] __se_sys_exit_group kernel/exit.c:976 [inline] __x64_sys_exit_group+0x3a/0x50 kernel/exit.c:976 do_syscall_64+0xf9/0x620 arch/x86/entry/common.c:293 entry_SYSCALL_64_after_hwframe+0x49/0xbe libceph: mon0 [d::]:6789 connect error irq event stamp: 4654080 hardirqs last enabled at (4654080): [] __raw_spin_unlock_irq include/linux/spinlock_api_smp.h:168 [inline] hardirqs last enabled at (4654080): [] _raw_spin_unlock_irq+0x24/0x80 kernel/locking/spinlock.c:192 hardirqs last disabled at (4654079): [] __raw_spin_lock_irq include/linux/spinlock_api_smp.h:126 [inline] hardirqs last disabled at (4654079): [] _raw_spin_lock_irq+0x35/0x80 kernel/locking/spinlock.c:160 softirqs last enabled at (4653732): [] __do_softirq+0x678/0x980 kernel/softirq.c:318 softirqs last disabled at (4654073): [] invoke_softirq kernel/softirq.c:372 [inline] softirqs last disabled at (4654073): [] irq_exit+0x215/0x260 kernel/softirq.c:412 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(slock-AF_BLUETOOTH-BTPROTO_SCO); lock(slock-AF_BLUETOOTH-BTPROTO_SCO); *** DEADLOCK *** 1 lock held by syz-fuzzer/8099: #0: 00000000d0a4ce07 ((&sk->sk_timer)#2){+.-.}, at: lockdep_copy_map include/linux/lockdep.h:168 [inline] #0: 00000000d0a4ce07 ((&sk->sk_timer)#2){+.-.}, at: call_timer_fn+0xc9/0x700 kernel/time/timer.c:1328 ceph: No mds server is up or the cluster is laggy stack backtrace: CPU: 1 PID: 8099 Comm: syz-fuzzer Not tainted 4.19.198-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1fc/0x2ef lib/dump_stack.c:118 Bluetooth: hci1: command 0x040f tx timeout print_usage_bug.cold+0x42e/0x570 kernel/locking/lockdep.c:2545 valid_state kernel/locking/lockdep.c:2558 [inline] mark_lock_irq kernel/locking/lockdep.c:2752 [inline] mark_lock+0xc70/0x1160 kernel/locking/lockdep.c:3132 mark_irqflags kernel/locking/lockdep.c:3010 [inline] __lock_acquire+0xdc4/0x3ff0 kernel/locking/lockdep.c:3373 lock_acquire+0x170/0x3c0 kernel/locking/lockdep.c:3908 __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline] _raw_spin_lock+0x2a/0x40 kernel/locking/spinlock.c:144 spin_lock include/linux/spinlock.h:329 [inline] sco_sock_timeout+0x31/0x210 net/bluetooth/sco.c:82 call_timer_fn+0x177/0x700 kernel/time/timer.c:1338 expire_timers+0x243/0x4e0 kernel/time/timer.c:1375 __run_timers kernel/time/timer.c:1696 [inline] run_timer_softirq+0x21c/0x670 kernel/time/timer.c:1709 __do_softirq+0x265/0x980 kernel/softirq.c:292 invoke_softirq kernel/softirq.c:372 [inline] irq_exit+0x215/0x260 kernel/softirq.c:412 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0x136/0x550 arch/x86/kernel/apic/apic.c:1098 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:894 RIP: 0033:0x412881 Code: 50 48 89 3b 48 ff 06 0f b6 52 51 48 0f af d1 0f b6 4e 08 48 8d 04 02 48 8d 40 48 f6 c1 04 0f 84 2e 01 00 00 83 e1 fb 88 4e 08 <48> 89 44 24 58 48 8b 6c 24 30 48 83 c4 38 c3 48 89 34 24 48 89 54 RSP: 002b:000000c024037890 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: 000000c001800368 RBX: 000000c001800358 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 000000c01a5b74a0 RDI: 00000000000002d4 RBP: 000000c0240378c0 R08: 0000000000000080 R09: 0000000000000006 R10: 00000000000000c0 R11: 000000c001800320 R12: 0000000000000006 R13: 0000000000000033 R14: 0000000000000032 R15: 0000000000000066 mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium ceph: No mds server is up or the cluster is laggy Bluetooth: hci1: command 0x0419 tx timeout libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium Bluetooth: hci1: command 0x0407 tx timeout mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium XFS (loop1): unknown mount option [barrier]. libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error ceph: No mds server is up or the cluster is laggy XFS (loop1): unknown mount option [barrier]. mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium ceph: No mds server is up or the cluster is laggy Bluetooth: hci1: command 0x0405 tx timeout mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium ceph: No mds server is up or the cluster is laggy ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium ceph: No mds server is up or the cluster is laggy libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error ceph: No mds server is up or the cluster is laggy libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error ceph: No mds server is up or the cluster is laggy Bluetooth: hci1: command 0x0405 tx timeout libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error ceph: No mds server is up or the cluster is laggy mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium libceph: connect [d::]:6789 error -101 libceph: mon0 [d::]:6789 connect error mac80211_hwsim: wmediumd released netlink socket, switching to perfect channel medium ceph: No mds server is up or the cluster is laggy