Ceph » Linux kernel client

trivially reproducible with currenting testing branch

ubuntu@plana02:~$ [17575.980776] BUG: unable to handle kernel NULL pointer dereference at 0000000000000010
[17576.053725] IP: [<ffffffffa03b417c>] prepare_write_connect+0x14c/0x250 [libceph]
[17576.125881] PGD 21a983067 PUD 21fb0b067 PMD 0 
[17576.162234] Oops: 0000 [#1] SMP 
[17576.196273] CPU 1 
[17576.198533] Modules linked in: ceph libceph ufs qnx4 hfsplus hfs minix ntfs vfat msdos fat jfs xfs exportfs reiserf 
[17576.375071] 
[17576.404835] Pid: 640, comm: kworker/1:2 Not tainted 3.3.0-ceph-00110-g1d4a9bf #1 Dell Inc. PowerEdge R410/01V648
[17576.472797] RIP: 0010:[<ffffffffa03b417c>]  [<ffffffffa03b417c>] prepare_write_connect+0x14c/0x250 [libceph]
[17576.542074] RSP: 0018:ffff8802218a9ad0  EFLAGS: 00010246
[17576.578023] RAX: 0000000000000000 RBX: ffff8802203a2800 RCX: 0000000000000000
[17576.616808] RDX: 0000000000000001 RSI: 0000000000000001 RDI: ffff88021fb20120
[17576.655985] RBP: ffff8802218a9b00 R08: ffffffff81f58390 R09: 000000000000000f
[17576.695459] R10: 0000000000000004 R11: 0000000000000000 R12: 000000000000000f
[17576.734855] R13: 0000000000000000 R14: ffff88022722e240 R15: ffff8802218a9dc0
[17576.774297] FS:  0000000000000000(0000) GS:ffff880227220000(0000) knlGS:0000000000000000
[17576.846308] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[17576.885141] CR2: 0000000000000010 CR3: 00000002218b5000 CR4: 00000000000006e0
[17576.926049] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[17576.966732] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[17577.007199] Process kworker/1:2 (pid: 640, threadinfo ffff8802218a8000, task ffff88020e5bde80)
[17577.082688] Stack:
[17577.116681]  ffff880200000000 000000000e5bde80 ffffffff816130d2 ffff8802203a2800
[17577.188551]  ffff8802203a2c58 ffff8802203a2828 ffff8802218a9c10 ffffffffa03b5816
[17577.262528]  ffff8802203a2978 0000000000000000 ffff8802218a9b30 ffff8802203a2978
[17577.339531] Call Trace:
[17577.375575]  [<ffffffff816130d2>] ? __mutex_lock_common+0x282/0x3d0
[17577.415928]  [<ffffffffa03b5816>] try_write+0xa46/0x1030 [libceph]
[17577.455677]  [<ffffffffa03b6526>] ? con_work+0x46/0x1b30 [libceph]
[17577.494810]  [<ffffffffa03b7120>] con_work+0xc40/0x1b30 [libceph]
[17577.533359]  [<ffffffff810ab1cc>] ? __lock_acquire+0xa8c/0x15d0
[17577.571002]  [<ffffffff81615dc0>] ? _raw_spin_unlock_irq+0x30/0x40
[17577.608155]  [<ffffffff8106b256>] process_one_work+0x1a6/0x520
[17577.644210]  [<ffffffff8106b1e7>] ? process_one_work+0x137/0x520
[17577.680172]  [<ffffffffa03b64e0>] ? ceph_con_revoke_message+0x130/0x130 [libceph]
[17577.746965]  [<ffffffff8106d593>] worker_thread+0x173/0x400
[17577.783177]  [<ffffffff8106d420>] ? manage_workers+0x210/0x210
[17577.819464]  [<ffffffff8107280e>] kthread+0xbe/0xd0
[17577.854588]  [<ffffffff8161f5f4>] kernel_thread_helper+0x4/0x10
[17577.890749]  [<ffffffff81616134>] ? retint_restore_args+0x13/0x13
[17577.926334]  [<ffffffff81072750>] ? __init_kthread_worker+0x70/0x70
[17577.961824]  [<ffffffff8161f5f0>] ? gs_change+0x13/0x13
[17577.995717] Code: 29 ff ff ff 48 8b 43 28 f6 c4 20 75 c5 49 8b 45 18 48 89 83 68 01 00 00 49 8b 45 20 89 83 70 01 0c
[17578.107356] RIP  [<ffffffffa03b417c>] prepare_write_connect+0x14c/0x250 [libceph]
[17578.175891]  RSP <ffff8802218a9ad0>
[17578.209743] CR2: 0000000000000010
[17578.288962] ---[ end trace e8de61daec71ea6e ]---
[17578.322716] BUG: unable to handle kernel paging request at fffffffffffffff8
[17578.359066] IP: [<ffffffff81072170>] kthread_data+0x10/0x20
[17578.393528] PGD 1c07067 PUD 1c08067 PMD 0 
[17578.425822] Oops: 0000 [#2] SMP 
[17578.457107] CPU 1 
[17578.459375] Modules linked in: ceph libceph ufs qnx4 hfsplus hfs minix ntfs vfat msdos fat jfs xfs exportfs reiserf 
[17578.632262] 
[17578.663587] Pid: 640, comm: kworker/1:2 Tainted: G      D      3.3.0-ceph-00110-g1d4a9bf #1 Dell Inc. PowerEdge R410
[17578.737318] RIP: 0010:[<ffffffff81072170>]  [<ffffffff81072170>] kthread_data+0x10/0x20
[17578.808692] RSP: 0018:ffff8802218a96b8  EFLAGS: 00010092
[17578.845765] RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000001
[17578.885483] RDX: ffffffff81e35fc0 RSI: 0000000000000001 RDI: ffff88020e5bde80
[17578.925200] RBP: ffff8802218a96b8 R08: 0000000000989680 R09: 0000000000000001
[17578.964999] R10: 0000000000000400 R11: 0000000000000001 R12: 0000000000000001
[17579.004755] R13: ffff88020e5be220 R14: ffff880223cd0000 R15: ffff8802218a97e0
[17579.044703] FS:  0000000000000000(0000) GS:ffff880227220000(0000) knlGS:0000000000000000
[17579.118253] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[17579.156836] CR2: fffffffffffffff8 CR3: 00000002218b5000 CR4: 00000000000006e0
[17579.197399] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[17579.237192] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[17579.275979] Process kworker/1:2 (pid: 640, threadinfo ffff8802218a8000, task ffff88020e5bde80)
[17579.348411] Stack:
[17579.381924]  ffff8802218a96d8 ffffffff8106a665 ffff8802218a96d8 ffff880227233b40
[17579.453584]  ffff8802218a9768 ffffffff81614293 ffff88020e5bde80 0000000000013b40
[17579.527219]  ffff8802218a9fd8 ffff8802218a8010 0000000000013b40 0000000000013b40
[17579.604141] Call Trace:
[17579.640106]  [<ffffffff8106a665>] wq_worker_sleeping+0x15/0xa0
[17579.679774]  [<ffffffff81614293>] __schedule+0x5c3/0x810
[17579.718192]  [<ffffffff8161480f>] schedule+0x3f/0x60
[17579.755909]  [<ffffffff8105206c>] do_exit+0x60c/0x8c0
[17579.793052]  [<ffffffff8104ebe6>] ? kmsg_dump+0x116/0x160
[17579.830149]  [<ffffffff81617020>] oops_end+0xb0/0xf0
[17579.865763]  [<ffffffff8104053d>] no_context+0x11d/0x2d0
[17579.900958]  [<ffffffff8104083d>] __bad_area_nosemaphore+0x14d/0x230
[17579.937168]  [<ffffffff81619ae1>] ? do_page_fault+0x221/0x4b0
[17579.972351]  [<ffffffff81040933>] bad_area_nosemaphore+0x13/0x20
[17580.007868]  [<ffffffff81619c0e>] do_page_fault+0x34e/0x4b0
[17580.042859]  [<ffffffff8131d8fd>] ? trace_hardirqs_off_thunk+0x3a/0x3c
[17580.079185]  [<ffffffff816163b5>] page_fault+0x25/0x30
[17580.113764]  [<ffffffffa03b417c>] ? prepare_write_connect+0x14c/0x250 [libceph]
[17580.179019]  [<ffffffff816130d2>] ? __mutex_lock_common+0x282/0x3d0
[17580.215050]  [<ffffffffa03b5816>] try_write+0xa46/0x1030 [libceph]
[17580.250608]  [<ffffffffa03b6526>] ? con_work+0x46/0x1b30 [libceph]
[17580.285993]  [<ffffffffa03b7120>] con_work+0xc40/0x1b30 [libceph]
[17580.321694]  [<ffffffff810ab1cc>] ? __lock_acquire+0xa8c/0x15d0
[17580.356683]  [<ffffffff81615dc0>] ? _raw_spin_unlock_irq+0x30/0x40
[17580.391259]  [<ffffffff8106b256>] process_one_work+0x1a6/0x520
[17580.425779]  [<ffffffff8106b1e7>] ? process_one_work+0x137/0x520
[17580.459958]  [<ffffffffa03b64e0>] ? ceph_con_revoke_message+0x130/0x130 [libceph]
[17580.521872]  [<ffffffff8106d593>] worker_thread+0x173/0x400
[17580.554747]  [<ffffffff8106d420>] ? manage_workers+0x210/0x210
[17580.587176]  [<ffffffff8107280e>] kthread+0xbe/0xd0
[17580.617706]  [<ffffffff8161f5f4>] kernel_thread_helper+0x4/0x10
[17580.649757]  [<ffffffff81616134>] ? retint_restore_args+0x13/0x13
[17580.681696]  [<ffffffff81072750>] ? __init_kthread_worker+0x70/0x70
[17580.713767]  [<ffffffff8161f5f0>] ? gs_change+0x13/0x13
[17580.744798] Code: 66 66 66 90 65 48 8b 04 25 00 c8 00 00 48 8b 80 48 03 00 00 8b 40 f0 c9 c3 66 90 55 48 89 e5 66 66
[17580.848756] RIP  [<ffffffff81072170>] kthread_data+0x10/0x20
[17580.882708]  RSP <ffff8802218a96b8>
[17580.914082] CR2: fffffffffffffff8
[17580.944880] ---[ end trace e8de61daec71ea6f ]---
[17580.977233] Fixing recursive fault but reboot is needed!