Project

General

Profile

Actions

Bug #2590

open

possible irq lock inversion dependency with con->mutex and osdc->request_mutex

Added by Sage Weil almost 12 years ago. Updated over 4 years ago.

Status:
New
Priority:
Normal
Assignee:
-
Category:
libceph
Target version:
-
% Done:

0%

Source:
Q/A
Tags:
Backport:
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Crash signature (v1):
Crash signature (v2):

Description

i thought this was #147, but on closer inspection it's something else;

2012-06-13T13:58:21.449592-07:00 plana65 kernel: [ 3476.880534] =========================================================
2012-06-13T13:58:21.449608-07:00 plana65 kernel: [ 3476.908822] [ INFO: possible irq lock inversion dependency detected ]
2012-06-13T13:58:21.449613-07:00 plana65 kernel: [ 3476.938287] 3.5.0-rc1-ceph-00031-gc9b7406 #1 Not tainted
2012-06-13T13:58:21.449618-07:00 plana65 kernel: [ 3476.967012] ---------------------------------------------------------
2012-06-13T13:58:21.449622-07:00 plana65 kernel: [ 3476.997784] kswapd0/41 just changed the state of lock:
2012-06-13T13:58:21.449630-07:00 plana65 kernel: [ 3477.027662]  (&osdc->request_mutex){+.+.-.}, at: [<ffffffffa028068b>] ceph_osdc_start_request+0x8b/0x190 [libceph]
2012-06-13T13:58:21.449634-07:00 plana65 kernel: [ 3477.090018] but this lock took another, RECLAIM_FS-unsafe lock in the past:
2012-06-13T13:58:21.449641-07:00 plana65 kernel: [ 3477.123868]  (&con->mutex){+.+.+.}
2012-06-13T13:58:21.449645-07:00 plana65 kernel: [ 3477.123868] 
2012-06-13T13:58:21.449647-07:00 plana65 kernel: [ 3477.123868] and interrupts could create inverse lock ordering between them.
2012-06-13T13:58:21.449648-07:00 plana65 kernel: [ 3477.123868] 
2012-06-13T13:58:21.449653-07:00 plana65 kernel: [ 3477.238792] 
2012-06-13T13:58:21.449655-07:00 plana65 kernel: [ 3477.238792] other info that might help us debug this:
2012-06-13T13:58:21.449660-07:00 plana65 kernel: [ 3477.295691]  Possible interrupt unsafe locking scenario:
2012-06-13T13:58:21.449661-07:00 plana65 kernel: [ 3477.295691] 
2012-06-13T13:58:21.449665-07:00 plana65 kernel: [ 3477.352788]        CPU0                    CPU1
2012-06-13T13:58:21.449672-07:00 plana65 kernel: [ 3477.382400]        ----                    ----
2012-06-13T13:58:21.449676-07:00 plana65 kernel: [ 3477.411629]   lock(&con->mutex);
2012-06-13T13:58:21.449681-07:00 plana65 kernel: [ 3477.439192]                                local_irq_disable();
2012-06-13T13:58:21.449685-07:00 plana65 kernel: [ 3477.470229]                                lock(&osdc->request_mutex);
2012-06-13T13:58:21.449689-07:00 plana65 kernel: [ 3477.502045]                                lock(&con->mutex);
2012-06-13T13:58:21.449693-07:00 plana65 kernel: [ 3477.533080]   <Interrupt>
2012-06-13T13:58:21.449697-07:00 plana65 kernel: [ 3477.560193]     lock(&osdc->request_mutex);
2012-06-13T13:58:21.449704-07:00 plana65 kernel: [ 3477.589111] 
2012-06-13T13:58:21.449706-07:00 plana65 kernel: [ 3477.589111]  *** DEADLOCK ***
2012-06-13T13:58:21.449707-07:00 plana65 kernel: [ 3477.589111] 
2012-06-13T13:58:21.449712-07:00 plana65 kernel: [ 3477.667924] no locks held by kswapd0/41.
2012-06-13T13:58:21.449716-07:00 plana65 kernel: [ 3477.696274] 
2012-06-13T13:58:21.449718-07:00 plana65 kernel: [ 3477.696274] the shortest dependencies between 2nd lock and 1st lock:
2012-06-13T13:58:21.449722-07:00 plana65 kernel: [ 3477.752495]  -> (&con->mutex){+.+.+.} ops: 385786 {
2012-06-13T13:58:21.449726-07:00 plana65 kernel: [ 3477.781565]     HARDIRQ-ON-W at:
2012-06-13T13:58:21.449732-07:00 plana65 kernel: [ 3477.808189]   [<ffffffff810af31b>] __lock_acquire+0x5ab/0x15d0
2012-06-13T13:58:21.449737-07:00 plana65 kernel: [ 3477.837887]   [<ffffffff810b03e2>] lock_acquire+0xa2/0x120
2012-06-13T13:58:21.449741-07:00 plana65 kernel: [ 3477.866661]   [<ffffffff8162acdb>] __mutex_lock_common+0x4b/0x3d0
2012-06-13T13:58:21.449746-07:00 plana65 kernel: [ 3477.895674]   [<ffffffff8162b187>] mutex_lock_nested+0x37/0x50
2012-06-13T13:58:21.449750-07:00 plana65 kernel: [ 3477.923627]   [<ffffffffa0278f77>] ceph_con_send+0xa7/0x200 [libceph]
2012-06-13T13:58:21.449755-07:00 plana65 kernel: [ 3477.951761]   [<ffffffffa027c33c>] __send_prepared_auth_request+0x6c/0x90 [libceph]
2012-06-13T13:58:21.449760-07:00 plana65 kernel: [ 3478.002188]   [<ffffffffa027c533>] __open_session+0x123/0x190 [libceph]
2012-06-13T13:58:21.449767-07:00 plana65 kernel: [ 3478.031571]   [<ffffffffa027c6af>] ceph_monc_open_session+0x2f/0x50 [libceph]
2012-06-13T13:58:21.449772-07:00 plana65 kernel: [ 3478.061474]   [<ffffffffa0275259>] __ceph_open_session+0x39/0x270 [libceph]
2012-06-13T13:58:21.449777-07:00 plana65 kernel: [ 3478.091973]   [<ffffffffa04902e3>] ceph_mount+0x423/0x800 [ceph]
2012-06-13T13:58:21.449781-07:00 plana65 kernel: [ 3478.121535]   [<ffffffff81184ea3>] mount_fs+0x43/0x1b0
2012-06-13T13:58:21.449786-07:00 plana65 kernel: [ 3478.149905]   [<ffffffff811a1bb6>] vfs_kern_mount+0x76/0x120
2012-06-13T13:58:21.449790-07:00 plana65 kernel: [ 3478.178814]   [<ffffffff811a1ce2>] do_kern_mount+0x52/0x110
2012-06-13T13:58:21.449795-07:00 plana65 kernel: [ 3478.207962]   [<ffffffff811a33c7>] do_mount+0x257/0x820
2012-06-13T13:58:21.449800-07:00 plana65 kernel: [ 3478.237014]   [<ffffffff811a3a20>] sys_mount+0x90/0xe0
2012-06-13T13:58:21.449807-07:00 plana65 kernel: [ 3478.265883]   [<ffffffff816360e9>] system_call_fastpath+0x16/0x1b
2012-06-13T13:58:21.449811-07:00 plana65 kernel: [ 3478.295818]     SOFTIRQ-ON-W at:
2012-06-13T13:58:21.449816-07:00 plana65 kernel: [ 3478.322743]   [<ffffffff810af34d>] __lock_acquire+0x5dd/0x15d0
2012-06-13T13:58:21.449820-07:00 plana65 kernel: [ 3478.353341]   [<ffffffff810b03e2>] lock_acquire+0xa2/0x120
2012-06-13T13:58:21.449825-07:00 plana65 kernel: [ 3478.383554]   [<ffffffff8162acdb>] __mutex_lock_common+0x4b/0x3d0
2012-06-13T13:58:21.449829-07:00 plana65 kernel: [ 3478.414625]   [<ffffffff8162b187>] mutex_lock_nested+0x37/0x50
2012-06-13T13:58:21.449834-07:00 plana65 kernel: [ 3478.445554]   [<ffffffffa0278f77>] ceph_con_send+0xa7/0x200 [libceph]
2012-06-13T13:58:21.449841-07:00 plana65 kernel: [ 3478.477800]   [<ffffffffa027c33c>] __send_prepared_auth_request+0x6c/0x90 [libceph]
2012-06-13T13:58:21.449845-07:00 plana65 kernel: [ 3478.538161]   [<ffffffffa027c533>] __open_session+0x123/0x190 [libceph]
2012-06-13T13:58:21.449850-07:00 plana65 kernel: [ 3478.572943]   [<ffffffffa027c6af>] ceph_monc_open_session+0x2f/0x50 [libceph]
2012-06-13T13:58:21.449855-07:00 plana65 kernel: [ 3478.608380]   [<ffffffffa0275259>] __ceph_open_session+0x39/0x270 [libceph]
2012-06-13T13:58:21.449860-07:00 plana65 kernel: [ 3478.643528]   [<ffffffffa04902e3>] ceph_mount+0x423/0x800 [ceph]
2012-06-13T13:58:21.449864-07:00 plana65 kernel: [ 3478.677702]   [<ffffffff81184ea3>] mount_fs+0x43/0x1b0
2012-06-13T13:58:21.449868-07:00 plana65 kernel: [ 3478.710569]   [<ffffffff811a1bb6>] vfs_kern_mount+0x76/0x120
2012-06-13T13:58:21.449873-07:00 plana65 kernel: [ 3478.744090]   [<ffffffff811a1ce2>] do_kern_mount+0x52/0x110
2012-06-13T13:58:21.449879-07:00 plana65 kernel: [ 3478.777404]   [<ffffffff811a33c7>] do_mount+0x257/0x820
2012-06-13T13:58:21.449884-07:00 plana65 kernel: [ 3478.810031]   [<ffffffff811a3a20>] sys_mount+0x90/0xe0
2012-06-13T13:58:21.449888-07:00 plana65 kernel: [ 3478.842207]   [<ffffffff816360e9>] system_call_fastpath+0x16/0x1b
2012-06-13T13:58:21.449892-07:00 plana65 kernel: [ 3478.875331]     RECLAIM_FS-ON-W at:
2012-06-13T13:58:21.449897-07:00 plana65 kernel: [ 3478.904919]   [<ffffffff810ae68d>] mark_held_locks+0x7d/0x120
2012-06-13T13:58:21.449901-07:00 plana65 kernel: [ 3478.936951]   [<ffffffff810ae7cf>] lockdep_trace_alloc+0x9f/0xd0
2012-06-13T13:58:21.449906-07:00 plana65 kernel: [ 3478.969013]   [<ffffffff81172dca>] kmem_cache_alloc+0x3a/0x140
2012-06-13T13:58:21.449912-07:00 plana65 kernel: [ 3479.000690]   [<ffffffff81510e9d>] sock_alloc_inode+0x1d/0xd0
2012-06-13T13:58:21.449917-07:00 plana65 kernel: [ 3479.031992]   [<ffffffff8119dcd7>] alloc_inode+0x27/0xa0
2012-06-13T13:58:21.449922-07:00 plana65 kernel: [ 3479.062630]   [<ffffffff8119dd6b>] new_inode_pseudo+0x1b/0x70
2012-06-13T13:58:21.449926-07:00 plana65 kernel: [ 3479.093758]   [<ffffffff81511b9e>] sock_alloc+0x1e/0x70
2012-06-13T13:58:21.449931-07:00 plana65 kernel: [ 3479.124348]   [<ffffffff81511ff6>] __sock_create+0x96/0x280
2012-06-13T13:58:21.449935-07:00 plana65 kernel: [ 3479.155398]   [<ffffffff81512204>] sock_create_kern+0x24/0x30
2012-06-13T13:58:21.449940-07:00 plana65 kernel: [ 3479.186838]   [<ffffffffa0278900>] try_write+0xb00/0x10d0 [libceph]
2012-06-13T13:58:21.449945-07:00 plana65 kernel: [ 3479.219008]   [<ffffffffa027a3d0>] con_work+0xc60/0x1c60 [libceph]
2012-06-13T13:58:21.449951-07:00 plana65 kernel: [ 3479.250761]   [<ffffffff8106f276>] process_one_work+0x1b6/0x530
2012-06-13T13:58:21.449956-07:00 plana65 kernel: [ 3479.282098]   [<ffffffff810715b3>] worker_thread+0x173/0x400
2012-06-13T13:58:21.449960-07:00 plana65 kernel: [ 3479.313045]   [<ffffffff81076a9e>] kthread+0xbe/0xd0
2012-06-13T13:58:21.449965-07:00 plana65 kernel: [ 3479.343009]   [<ffffffff81637534>] kernel_thread_helper+0x4/0x10
2012-06-13T13:58:21.449969-07:00 plana65 kernel: [ 3479.374165]     INITIAL USE at:
2012-06-13T13:58:21.449974-07:00 plana65 kernel: [ 3479.402023]   [<ffffffff810aef76>] __lock_acquire+0x206/0x15d0
2012-06-13T13:58:21.449978-07:00 plana65 kernel: [ 3479.433238]   [<ffffffff810b03e2>] lock_acquire+0xa2/0x120
2012-06-13T13:58:21.449983-07:00 plana65 kernel: [ 3479.463279]   [<ffffffff8162acdb>] __mutex_lock_common+0x4b/0x3d0
2012-06-13T13:58:21.449989-07:00 plana65 kernel: [ 3479.493484]   [<ffffffff8162b187>] mutex_lock_nested+0x37/0x50
2012-06-13T13:58:21.449994-07:00 plana65 kernel: [ 3479.523165]   [<ffffffffa0278f77>] ceph_con_send+0xa7/0x200 [libceph]
2012-06-13T13:58:21.449999-07:00 plana65 kernel: [ 3479.553452]   [<ffffffffa027c33c>] __send_prepared_auth_request+0x6c/0x90 [libceph]
2012-06-13T13:58:21.450004-07:00 plana65 kernel: [ 3479.608360]   [<ffffffffa027c533>] __open_session+0x123/0x190 [libceph]
2012-06-13T13:58:21.450008-07:00 plana65 kernel: [ 3479.640165]   [<ffffffffa027c6af>] ceph_monc_open_session+0x2f/0x50 [libceph]
2012-06-13T13:58:21.450013-07:00 plana65 kernel: [ 3479.672912]   [<ffffffffa0275259>] __ceph_open_session+0x39/0x270 [libceph]
2012-06-13T13:58:21.450018-07:00 plana65 kernel: [ 3479.705871]   [<ffffffffa04902e3>] ceph_mount+0x423/0x800 [ceph]
2012-06-13T13:58:21.450024-07:00 plana65 kernel: [ 3479.738104]   [<ffffffff81184ea3>] mount_fs+0x43/0x1b0
2012-06-13T13:58:21.450029-07:00 plana65 kernel: [ 3479.769394]   [<ffffffff811a1bb6>] vfs_kern_mount+0x76/0x120
2012-06-13T13:58:21.450033-07:00 plana65 kernel: [ 3479.800819]   [<ffffffff811a1ce2>] do_kern_mount+0x52/0x110
2012-06-13T13:58:21.450038-07:00 plana65 kernel: [ 3479.831754]   [<ffffffff811a33c7>] do_mount+0x257/0x820
2012-06-13T13:58:21.450042-07:00 plana65 kernel: [ 3479.862151]   [<ffffffff811a3a20>] sys_mount+0x90/0xe0
2012-06-13T13:58:21.450047-07:00 plana65 kernel: [ 3479.892154]   [<ffffffff816360e9>] system_call_fastpath+0x16/0x1b
2012-06-13T13:58:21.450050-07:00 plana65 kernel: [ 3479.923375]   }
2012-06-13T13:58:21.450055-07:00 plana65 kernel: [ 3479.949754]   ... key      at: [<ffffffffa0299f18>] __key.64564+0x0/0xffffffffffff214f [libceph]
2012-06-13T13:58:21.450063-07:00 plana65 kernel: [ 3480.010658]   ... acquired at:
2012-06-13T13:58:21.450068-07:00 plana65 kernel: [ 3480.039794]    [<ffffffff810b03e2>] lock_acquire+0xa2/0x120
2012-06-13T13:58:21.450072-07:00 plana65 kernel: [ 3480.072304]    [<ffffffff8162acdb>] __mutex_lock_common+0x4b/0x3d0
2012-06-13T13:58:21.450077-07:00 plana65 kernel: [ 3480.105496]    [<ffffffff8162b187>] mutex_lock_nested+0x37/0x50
2012-06-13T13:58:21.450081-07:00 plana65 kernel: [ 3480.138432]    [<ffffffffa0278f77>] ceph_con_send+0xa7/0x200 [libceph]
2012-06-13T13:58:21.450086-07:00 plana65 kernel: [ 3480.172090]    [<ffffffffa027f8d5>] __send_request+0xc5/0x120 [libceph]
2012-06-13T13:58:21.450091-07:00 plana65 kernel: [ 3480.206028]    [<ffffffffa0280713>] ceph_osdc_start_request+0x113/0x190 [libceph]
2012-06-13T13:58:21.450098-07:00 plana65 kernel: [ 3480.268348]    [<ffffffffa0497ed9>] ceph_aio_write+0x629/0xab0 [ceph]
2012-06-13T13:58:21.450103-07:00 plana65 kernel: [ 3480.303339]    [<ffffffff811820e2>] do_sync_write+0xe2/0x120
2012-06-13T13:58:21.450108-07:00 plana65 kernel: [ 3480.337223]    [<ffffffff81182678>] vfs_write+0xc8/0x190
2012-06-13T13:58:21.450112-07:00 plana65 kernel: [ 3480.370588]    [<ffffffff81182831>] sys_write+0x51/0x90
2012-06-13T13:58:21.450117-07:00 plana65 kernel: [ 3480.403388]    [<ffffffff816360e9>] system_call_fastpath+0x16/0x1b
2012-06-13T13:58:21.450121-07:00 plana65 kernel: [ 3480.437328] 
2012-06-13T13:58:21.450125-07:00 plana65 kernel: [ 3480.465734] -> (&osdc->request_mutex){+.+.-.} ops: 568458 {
2012-06-13T13:58:21.450129-07:00 plana65 kernel: [ 3480.499110]    HARDIRQ-ON-W at:
2012-06-13T13:58:21.450137-07:00 plana65 kernel: [ 3480.528984]  [<ffffffff810af31b>] __lock_acquire+0x5ab/0x15d0
2012-06-13T13:58:21.450142-07:00 plana65 kernel: [ 3480.561725]  [<ffffffff810b03e2>] lock_acquire+0xa2/0x120
2012-06-13T13:58:21.450146-07:00 plana65 kernel: [ 3480.593813]  [<ffffffff8162acdb>] __mutex_lock_common+0x4b/0x3d0
2012-06-13T13:58:21.450151-07:00 plana65 kernel: [ 3480.626469]  [<ffffffff8162b187>] mutex_lock_nested+0x37/0x50
2012-06-13T13:58:21.450156-07:00 plana65 kernel: [ 3480.658640]  [<ffffffffa02807ce>] kick_requests+0x3e/0x2b0 [libceph]
2012-06-13T13:58:21.450161-07:00 plana65 kernel: [ 3480.691665]  [<ffffffffa0280f48>] ceph_osdc_handle_map+0x508/0x5f0 [libceph]
2012-06-13T13:58:21.450166-07:00 plana65 kernel: [ 3480.725805]  [<ffffffffa027d210>] dispatch+0x120/0x720 [libceph]
2012-06-13T13:58:21.450173-07:00 plana65 kernel: [ 3480.759022]  [<ffffffffa027ae48>] con_work+0x16d8/0x1c60 [libceph]
2012-06-13T13:58:21.450177-07:00 plana65 kernel: [ 3480.792695]  [<ffffffff8106f276>] process_one_work+0x1b6/0x530
2012-06-13T13:58:21.450182-07:00 plana65 kernel: [ 3480.826274]  [<ffffffff810715b3>] worker_thread+0x173/0x400
2012-06-13T13:58:21.450197-07:00 plana65 kernel: [ 3480.859553]  [<ffffffff81076a9e>] kthread+0xbe/0xd0
2012-06-13T13:58:21.450202-07:00 plana65 kernel: [ 3480.891544]  [<ffffffff81637534>] kernel_thread_helper+0x4/0x10
2012-06-13T13:58:21.450206-07:00 plana65 kernel: [ 3480.924382]    SOFTIRQ-ON-W at:
2012-06-13T13:58:21.450211-07:00 plana65 kernel: [ 3480.953526]  [<ffffffff810af34d>] __lock_acquire+0x5dd/0x15d0
2012-06-13T13:58:21.450216-07:00 plana65 kernel: [ 3480.986255]  [<ffffffff810b03e2>] lock_acquire+0xa2/0x120
2012-06-13T13:58:21.450224-07:00 plana65 kernel: [ 3481.018306]  [<ffffffff8162acdb>] __mutex_lock_common+0x4b/0x3d0
2012-06-13T13:58:21.450229-07:00 plana65 kernel: [ 3481.051154]  [<ffffffff8162b187>] mutex_lock_nested+0x37/0x50
2012-06-13T13:58:21.450250-07:00 plana65 kernel: [ 3481.083672]  [<ffffffffa02807ce>] kick_requests+0x3e/0x2b0 [libceph]
2012-06-13T13:58:21.450256-07:00 plana65 kernel: [ 3481.116986]  [<ffffffffa0280f48>] ceph_osdc_handle_map+0x508/0x5f0 [libceph]
2012-06-13T13:58:21.450261-07:00 plana65 kernel: [ 3481.151262]  [<ffffffffa027d210>] dispatch+0x120/0x720 [libceph]
2012-06-13T13:58:21.450266-07:00 plana65 kernel: [ 3481.184306]  [<ffffffffa027ae48>] con_work+0x16d8/0x1c60 [libceph]
2012-06-13T13:58:21.450271-07:00 plana65 kernel: [ 3481.216846]  [<ffffffff8106f276>] process_one_work+0x1b6/0x530
2012-06-13T13:58:21.450278-07:00 plana65 kernel: [ 3481.248561]  [<ffffffff810715b3>] worker_thread+0x173/0x400
2012-06-13T13:58:21.450283-07:00 plana65 kernel: [ 3481.279842]  [<ffffffff81076a9e>] kthread+0xbe/0xd0
2012-06-13T13:58:21.450290-07:00 plana65 kernel: [ 3481.310238]  [<ffffffff81637534>] kernel_thread_helper+0x4/0x10
2012-06-13T13:58:21.450295-07:00 plana65 kernel: [ 3481.342365]    IN-RECLAIM_FS-W at:
2012-06-13T13:58:21.450300-07:00 plana65 kernel: [ 3481.371770]  [<ffffffff810af1a1>] __lock_acquire+0x431/0x15d0
2012-06-13T13:58:21.450304-07:00 plana65 kernel: [ 3481.404035]  [<ffffffff810b03e2>] lock_acquire+0xa2/0x120
2012-06-13T13:58:21.450309-07:00 plana65 kernel: [ 3481.435683]  [<ffffffff8162acdb>] __mutex_lock_common+0x4b/0x3d0
2012-06-13T13:58:21.450314-07:00 plana65 kernel: [ 3481.467955]  [<ffffffff8162b187>] mutex_lock_nested+0x37/0x50
2012-06-13T13:58:21.450322-07:00 plana65 kernel: [ 3481.499647]  [<ffffffffa028068b>] ceph_osdc_start_request+0x8b/0x190 [libceph]
2012-06-13T13:58:21.450328-07:00 plana65 kernel: [ 3481.559119]  [<ffffffffa0282844>] ceph_osdc_writepages+0xe4/0x190 [libceph]
2012-06-13T13:58:21.450333-07:00 plana65 kernel: [ 3481.593888]  [<ffffffffa049a902>] writepage_nounlock+0x232/0x420 [ceph]
2012-06-13T13:58:21.450337-07:00 plana65 kernel: [ 3481.628328]  [<ffffffffa049ab2e>] ceph_writepage+0x3e/0x70 [ceph]
2012-06-13T13:58:21.450342-07:00 plana65 kernel: [ 3481.662072]  [<ffffffff81139d7f>] shrink_page_list+0x59f/0x900
2012-06-13T13:58:21.450347-07:00 plana65 kernel: [ 3481.695344]  [<ffffffff8113a566>] shrink_inactive_list+0x176/0x440
2012-06-13T13:58:21.450352-07:00 plana65 kernel: [ 3481.728964]  [<ffffffff8113af45>] shrink_lruvec+0x3d5/0x490
2012-06-13T13:58:21.450358-07:00 plana65 kernel: [ 3481.761612]  [<ffffffff8113b066>] shrink_zone+0x66/0xc0
2012-06-13T13:58:21.450363-07:00 plana65 kernel: [ 3481.793646]  [<ffffffff8113c497>] balance_pgdat+0x6c7/0x8b0
2012-06-13T13:58:21.450368-07:00 plana65 kernel: [ 3481.826064]  [<ffffffff8113c86d>] kswapd+0x1ed/0x420
2012-06-13T13:58:21.450376-07:00 plana65 kernel: [ 3481.857665]  [<ffffffff81076a9e>] kthread+0xbe/0xd0
2012-06-13T13:58:21.450381-07:00 plana65 kernel: [ 3481.888562]  [<ffffffff81637534>] kernel_thread_helper+0x4/0x10
2012-06-13T13:58:21.450385-07:00 plana65 kernel: [ 3481.920439]    INITIAL USE at:
2012-06-13T13:58:21.450389-07:00 plana65 kernel: [ 3481.949193]  [<ffffffff810aef76>] __lock_acquire+0x206/0x15d0
2012-06-13T13:58:21.450394-07:00 plana65 kernel: [ 3481.981399]  [<ffffffff810b03e2>] lock_acquire+0xa2/0x120
2012-06-13T13:58:21.450402-07:00 plana65 kernel: [ 3482.013106]  [<ffffffff8162acdb>] __mutex_lock_common+0x4b/0x3d0
2012-06-13T13:58:21.450407-07:00 plana65 kernel: [ 3482.045493]  [<ffffffff8162b187>] mutex_lock_nested+0x37/0x50
2012-06-13T13:58:21.450412-07:00 plana65 kernel: [ 3482.077357]  [<ffffffffa02807ce>] kick_requests+0x3e/0x2b0 [libceph]
2012-06-13T13:58:21.450417-07:00 plana65 kernel: [ 3482.109866]  [<ffffffffa0280f48>] ceph_osdc_handle_map+0x508/0x5f0 [libceph]
2012-06-13T13:58:21.450422-07:00 plana65 kernel: [ 3482.143470]  [<ffffffffa027d210>] dispatch+0x120/0x720 [libceph]
2012-06-13T13:58:21.450426-07:00 plana65 kernel: [ 3482.175919]  [<ffffffffa027ae48>] con_work+0x16d8/0x1c60 [libceph]
2012-06-13T13:58:21.450431-07:00 plana65 kernel: [ 3482.208615]  [<ffffffff8106f276>] process_one_work+0x1b6/0x530
2012-06-13T13:58:21.450437-07:00 plana65 kernel: [ 3482.241118]  [<ffffffff810715b3>] worker_thread+0x173/0x400
2012-06-13T13:58:21.450442-07:00 plana65 kernel: [ 3482.273284]  [<ffffffff81076a9e>] kthread+0xbe/0xd0
2012-06-13T13:58:21.450449-07:00 plana65 kernel: [ 3482.304104]  [<ffffffff81637534>] kernel_thread_helper+0x4/0x10
2012-06-13T13:58:21.450453-07:00 plana65 kernel: [ 3482.335903]  }
2012-06-13T13:58:21.450459-07:00 plana65 kernel: [ 3482.362812]  ... key      at: [<ffffffffa029aba0>] __key.38687+0x0/0xffffffffffff14c7 [libceph]
2012-06-13T13:58:21.450463-07:00 plana65 kernel: [ 3482.424535]  ... acquired at:
2012-06-13T13:58:21.450467-07:00 plana65 kernel: [ 3482.453586]    [<ffffffff810ad550>] check_usage_forwards+0x90/0x100
2012-06-13T13:58:21.450472-07:00 plana65 kernel: [ 3482.486307]    [<ffffffff810ae3b4>] mark_lock+0x1b4/0x410
2012-06-13T13:58:21.450481-07:00 plana65 kernel: [ 3482.517338]    [<ffffffff810af1a1>] __lock_acquire+0x431/0x15d0
2012-06-13T13:58:21.450486-07:00 plana65 kernel: [ 3482.548695]    [<ffffffff810b03e2>] lock_acquire+0xa2/0x120
2012-06-13T13:58:21.450491-07:00 plana65 kernel: [ 3482.579476]    [<ffffffff8162acdb>] __mutex_lock_common+0x4b/0x3d0
2012-06-13T13:58:21.450495-07:00 plana65 kernel: [ 3482.610961]    [<ffffffff8162b187>] mutex_lock_nested+0x37/0x50
2012-06-13T13:58:21.450500-07:00 plana65 kernel: [ 3482.642266]    [<ffffffffa028068b>] ceph_osdc_start_request+0x8b/0x190 [libceph]
2012-06-13T13:58:21.450505-07:00 plana65 kernel: [ 3482.701023]    [<ffffffffa0282844>] ceph_osdc_writepages+0xe4/0x190 [libceph]
2012-06-13T13:58:21.450510-07:00 plana65 kernel: [ 3482.735866]    [<ffffffffa049a902>] writepage_nounlock+0x232/0x420 [ceph]
2012-06-13T13:58:21.450517-07:00 plana65 kernel: [ 3482.770704]    [<ffffffffa049ab2e>] ceph_writepage+0x3e/0x70 [ceph]
2012-06-13T13:58:21.450522-07:00 plana65 kernel: [ 3482.805237]    [<ffffffff81139d7f>] shrink_page_list+0x59f/0x900
2012-06-13T13:58:21.450529-07:00 plana65 kernel: [ 3482.839584]    [<ffffffff8113a566>] shrink_inactive_list+0x176/0x440
2012-06-13T13:58:21.450534-07:00 plana65 kernel: [ 3482.873932]    [<ffffffff8113af45>] shrink_lruvec+0x3d5/0x490
2012-06-13T13:58:21.450539-07:00 plana65 kernel: [ 3482.907175]    [<ffffffff8113b066>] shrink_zone+0x66/0xc0
2012-06-13T13:58:21.450543-07:00 plana65 kernel: [ 3482.939840]    [<ffffffff8113c497>] balance_pgdat+0x6c7/0x8b0
2012-06-13T13:58:21.450548-07:00 plana65 kernel: [ 3482.972718]    [<ffffffff8113c86d>] kswapd+0x1ed/0x420
2012-06-13T13:58:21.450553-07:00 plana65 kernel: [ 3483.004721]    [<ffffffff81076a9e>] kthread+0xbe/0xd0
2012-06-13T13:58:21.450561-07:00 plana65 kernel: [ 3483.036233]    [<ffffffff81637534>] kernel_thread_helper+0x4/0x10
2012-06-13T13:58:21.450565-07:00 plana65 kernel: [ 3483.068782] 
2012-06-13T13:58:21.450569-07:00 plana65 kernel: [ 3483.095783] 
2012-06-13T13:58:21.450571-07:00 plana65 kernel: [ 3483.095783] stack backtrace:
2012-06-13T13:58:21.450575-07:00 plana65 kernel: [ 3483.149563] Pid: 41, comm: kswapd0 Not tainted 3.5.0-rc1-ceph-00031-gc9b7406 #1
2012-06-13T13:58:21.450579-07:00 plana65 kernel: [ 3483.208384] Call Trace:
2012-06-13T13:58:21.450584-07:00 plana65 kernel: [ 3483.236416]  [<ffffffff810ad473>] print_irq_inversion_bug+0x1d3/0x220
2012-06-13T13:58:21.450591-07:00 plana65 kernel: [ 3483.269540]  [<ffffffff810ad4c0>] ? print_irq_inversion_bug+0x220/0x220
2012-06-13T13:58:21.450596-07:00 plana65 kernel: [ 3483.302474]  [<ffffffff810ad550>] check_usage_forwards+0x90/0x100
2012-06-13T13:58:21.450603-07:00 plana65 kernel: [ 3483.334197]  [<ffffffff810ae3b4>] mark_lock+0x1b4/0x410
2012-06-13T13:58:21.450608-07:00 plana65 kernel: [ 3483.365056]  [<ffffffff810af1a1>] __lock_acquire+0x431/0x15d0
2012-06-13T13:58:21.450612-07:00 plana65 kernel: [ 3483.396131]  [<ffffffffa027b47a>] ? msgpool_alloc+0x2a/0xa0 [libceph]
2012-06-13T13:58:21.450617-07:00 plana65 kernel: [ 3483.428147]  [<ffffffff81328986>] ? vsnprintf+0x416/0x5a0
2012-06-13T13:58:21.450622-07:00 plana65 kernel: [ 3483.459048]  [<ffffffffa028068b>] ? ceph_osdc_start_request+0x8b/0x190 [libceph]
2012-06-13T13:58:21.450627-07:00 plana65 kernel: [ 3483.517918]  [<ffffffff810b03e2>] lock_acquire+0xa2/0x120
2012-06-13T13:58:21.450637-07:00 plana65 kernel: [ 3483.550068]  [<ffffffffa028068b>] ? ceph_osdc_start_request+0x8b/0x190 [libceph]
2012-06-13T13:58:21.450642-07:00 plana65 kernel: [ 3483.610380]  [<ffffffff8162acdb>] __mutex_lock_common+0x4b/0x3d0
2012-06-13T13:58:21.450647-07:00 plana65 kernel: [ 3483.643156]  [<ffffffffa028068b>] ? ceph_osdc_start_request+0x8b/0x190 [libceph]
2012-06-13T13:58:21.450652-07:00 plana65 kernel: [ 3483.703757]  [<ffffffffa028068b>] ? ceph_osdc_start_request+0x8b/0x190 [libceph]
2012-06-13T13:58:21.450657-07:00 plana65 kernel: [ 3483.767007]  [<ffffffff8162b187>] mutex_lock_nested+0x37/0x50
2012-06-13T13:58:21.450663-07:00 plana65 kernel: [ 3483.802021]  [<ffffffffa028068b>] ceph_osdc_start_request+0x8b/0x190 [libceph]
2012-06-13T13:58:21.450668-07:00 plana65 kernel: [ 3483.868658]  [<ffffffffa0282844>] ceph_osdc_writepages+0xe4/0x190 [libceph]
2012-06-13T13:58:21.450673-07:00 plana65 kernel: [ 3483.907250]  [<ffffffffa049a902>] writepage_nounlock+0x232/0x420 [ceph]
2012-06-13T13:58:21.450680-07:00 plana65 kernel: [ 3483.945893]  [<ffffffff810aea8d>] ? trace_hardirqs_on+0xd/0x10
2012-06-13T13:58:21.450686-07:00 plana65 kernel: [ 3483.983797]  [<ffffffff81133048>] ? clear_page_dirty_for_io+0xc8/0x120
2012-06-13T13:58:21.450693-07:00 plana65 kernel: [ 3484.022320]  [<ffffffffa049ab2e>] ceph_writepage+0x3e/0x70 [ceph]
2012-06-13T13:58:21.450698-07:00 plana65 kernel: [ 3484.061212]  [<ffffffff81139d7f>] shrink_page_list+0x59f/0x900
2012-06-13T13:58:21.450703-07:00 plana65 kernel: [ 3484.100326]  [<ffffffff8113a566>] shrink_inactive_list+0x176/0x440
2012-06-13T13:58:21.450708-07:00 plana65 kernel: [ 3484.139249]  [<ffffffff8113ac78>] ? shrink_lruvec+0x108/0x490
2012-06-13T13:58:21.450713-07:00 plana65 kernel: [ 3484.177027]  [<ffffffff8113af45>] shrink_lruvec+0x3d5/0x490
2012-06-13T13:58:21.450721-07:00 plana65 kernel: [ 3484.214808]  [<ffffffff810c5677>] ? css_get_next+0x87/0x120
2012-06-13T13:58:21.450726-07:00 plana65 kernel: [ 3484.252029]  [<ffffffff8113b066>] shrink_zone+0x66/0xc0
2012-06-13T13:58:21.450731-07:00 plana65 kernel: [ 3484.288746]  [<ffffffff8113c497>] balance_pgdat+0x6c7/0x8b0
2012-06-13T13:58:21.450735-07:00 plana65 kernel: [ 3484.325640]  [<ffffffff810aea8d>] ? trace_hardirqs_on+0xd/0x10
2012-06-13T13:58:21.450740-07:00 plana65 kernel: [ 3484.362716]  [<ffffffff8113c86d>] kswapd+0x1ed/0x420
2012-06-13T13:58:21.450745-07:00 plana65 kernel: [ 3484.398774]  [<ffffffff81077010>] ? wake_up_bit+0x40/0x40
2012-06-13T13:58:21.450750-07:00 plana65 kernel: [ 3484.435071]  [<ffffffff8113c680>] ? balance_pgdat+0x8b0/0x8b0
2012-06-13T13:58:21.450754-07:00 plana65 kernel: [ 3484.471581]  [<ffffffff81076a9e>] kthread+0xbe/0xd0
2012-06-13T13:58:21.450761-07:00 plana65 kernel: [ 3484.506724]  [<ffffffff81637534>] kernel_thread_helper+0x4/0x10
2012-06-13T13:58:21.450769-07:00 plana65 kernel: [ 3484.542445]  [<ffffffff8162dfb0>] ? retint_restore_args+0x13/0x13
2012-06-13T13:58:21.450774-07:00 plana65 kernel: [ 3484.577975]  [<ffffffff810769e0>] ? __init_kthread_worker+0x70/0x70
2012-06-13T13:58:21.450779-07:00 plana65 kernel: [ 3484.613409]  [<ffffffff81637530>] ? gs_change+0x13/0x13

- chef: null
- ceph: null
- kclient: null
- workunit:
    clients:
      all:
      - suites/ffsb.sh

has happened several times, pretty reproducible.


Related issues 1 (0 open1 closed)

Related to Linux kernel client - Bug #147: lockdep: possible irq lock inversion dependency w/ osdc->request_mutex and con->mutexResolvedIlya Dryomov05/25/2010

Actions
Actions

Also available in: Atom PDF