From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751353AbXCTLMg (ORCPT ); Tue, 20 Mar 2007 07:12:36 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752808AbXCTLMg (ORCPT ); Tue, 20 Mar 2007 07:12:36 -0400 Received: from poczta.o2.pl ([193.17.41.142]:46438 "EHLO poczta.o2.pl" rhost-flags-OK-FAIL-OK-FAIL) by vger.kernel.org with ESMTP id S1751486AbXCTLMe (ORCPT ); Tue, 20 Mar 2007 07:12:34 -0400 Date: Tue, 20 Mar 2007 12:17:02 +0100 From: Jarek Poplawski To: Folkert van Heusden Cc: Andrew Morton , linux-kernel@vger.kernel.org, Oleg Nesterov , Neil Brown , Christoph Hellwig , Jan Kara Subject: dquot.c: possible circular locking Re: [2.6.20] BUG: workqueue leaked lock Message-ID: <20070320111701.GB1751@ff.dom.local> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20070315191749.GS31960@vanheusden.com> User-Agent: Mutt/1.4.2.2i Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On 15-03-2007 20:17, Folkert van Heusden wrote: >>> On Tue, 13 Mar 2007 17:50:14 +0100 Folkert van Heusden wrote: ... > Haha ok :-) > > Good, since I run 2.6.20 with these debugging switches switched on, I > get occasionally errors like these. I get ALWAYS the following error > when the system first boots when the TOR executable is started: > > [ 137.324255] ======================================================= > [ 137.324359] [ INFO: possible circular locking dependency detected ] > [ 137.324412] 2.6.20 #2 > [ 137.324457] ------------------------------------------------------- > [ 137.324510] tor/4857 is trying to acquire lock: > [ 137.324559] (tty_mutex){--..}, at: [] mutex_lock+0x8/0xa > [ 137.324765] > [ 137.324766] but task is already holding lock: > [ 137.324859] (&s->s_dquot.dqptr_sem){----}, at: [] dquot_alloc_space+0x50/0x189 > [ 137.325067] > [ 137.325069] which lock already depends on the new lock. IMHO lockdep found that two locks are taken in different order: -> #1: 1) tty_mutex in con_console() 2) dqptr_sem (somewhere later) -> #0: 1) dqptr_sem 2) tty_console in dquot_alloc_space() with print_warning() Probably print_warning() and flush_warnings() should be reworked to do printing without dqptr_sem or locking order should be changed. I hope somebody from this CC can work it out better. Regards, Jarek P. > [ 137.325071] > [ 137.325206] > [ 137.325208] the existing dependency chain (in reverse order) is: > [ 137.325300] > [ 137.325301] -> #4 (&s->s_dquot.dqptr_sem){----}: > [ 137.325501] [] check_prev_add+0x154/0x206 > [ 137.325852] [] check_prevs_add+0x6a/0xd5 > [ 137.326197] [] __lock_acquire+0x61c/0xa05 > [ 137.326538] [] lock_acquire+0x62/0x81 > [ 137.326887] [] down_read+0x2b/0x3d > [ 137.327241] [] dquot_alloc_space+0x50/0x189 > [ 137.327588] [] ext3_new_blocks+0x44b/0x5a2 > [ 137.327935] [] ext3_alloc_blocks+0x40/0xdf > [ 137.328280] [] ext3_alloc_branch+0x50/0x21b > [ 137.328622] [] ext3_get_blocks_handle+0x1b8/0x367 > [ 137.328980] [] ext3_getblk+0x97/0x228 > [ 137.329330] [] ext3_bread+0x1a/0x78 > [ 137.329672] [] ext3_mkdir+0xf4/0x270 > [ 137.330022] [] vfs_mkdir+0xb3/0x161 > [ 137.330368] [] sys_mkdirat+0x8c/0xc4 > [ 137.330714] [] sys_mkdir+0x20/0x22 > [ 137.331063] [] syscall_call+0x7/0xb > [ 137.331406] [] 0xffffffff > [ 137.331771] > [ 137.331772] -> #3 (&ei->truncate_mutex){--..}: > [ 137.331979] [] check_prev_add+0x154/0x206 > [ 137.332332] [] check_prevs_add+0x6a/0xd5 > [ 137.332676] [] __lock_acquire+0x61c/0xa05 > [ 137.333025] [] lock_acquire+0x62/0x81 > [ 137.333370] [] __mutex_lock_slowpath+0x75/0x28c > [ 137.333930] [] mutex_lock+0x8/0xa > [ 137.334271] [] ext3_truncate+0x170/0x468 > [ 137.334613] [] vmtruncate+0xa6/0x116 > [ 137.334949] [] inode_setattr+0x145/0x16c > [ 137.335286] [] ext3_setattr+0x150/0x22f > [ 137.335627] [] notify_change+0x35b/0x392 > [ 137.335968] [] do_truncate+0x52/0x75 > [ 137.336305] [] may_open+0x1ec/0x231 > [ 137.336642] [] open_namei+0xda/0x59b > [ 137.336975] [] do_filp_open+0x2c/0x53 > [ 137.337310] [] do_sys_open+0x52/0xd8 > [ 137.337645] [] sys_open+0x1c/0x1e > [ 137.337980] [] syscall_call+0x7/0xb > [ 137.338315] [] 0xffffffff > [ 137.338665] > [ 137.338666] -> #2 (&inode->i_alloc_sem){--..}: > [ 137.338864] [] check_prev_add+0x154/0x206 > [ 137.339200] [] check_prevs_add+0x6a/0xd5 > [ 137.339535] [] __lock_acquire+0x61c/0xa05 > [ 137.339200] [] check_prevs_add+0x6a/0xd5 > [ 137.339535] [] __lock_acquire+0x61c/0xa05 > [ 137.339874] [] lock_acquire+0x62/0x81 > [ 137.340207] [] down_write+0x2b/0x45 > [ 137.340545] [] notify_change+0x2e2/0x392 > [ 137.340886] [] do_truncate+0x52/0x75 > [ 137.341222] [] may_open+0x1ec/0x231 > [ 137.341557] [] open_namei+0xda/0x59b > [ 137.341898] [] sys_open+0x1c/0x1e > [ 137.343109] [] syscall_call+0x7/0xb > [ 137.343444] [] 0xffffffff > [ 137.343792] > [ 137.343793] -> #1 (&sysfs_inode_imutex_key){--..}: > [ 137.343988] [] check_prev_add+0x154/0x206 > [ 137.344320] [] check_prevs_add+0x6a/0xd5 > [ 137.344655] [] __lock_acquire+0x61c/0xa05 > [ 137.344986] [] lock_acquire+0x62/0x81 > [ 137.345321] [] __mutex_lock_slowpath+0x75/0x28c > [ 137.345658] [] mutex_lock+0x8/0xa > [ 137.345991] [] sysfs_hash_and_remove+0x43/0x11c > [ 137.346328] [] sysfs_remove_file+0xd/0x12 > [ 137.346660] [] device_remove_file+0x32/0x44 > [ 137.346992] [] device_del+0x174/0x1d2 > [ 137.347325] [] device_unregister+0xb/0x15 > [ 137.347661] [] device_destroy+0x8d/0x9a > [ 137.347994] [] vcs_remove_sysfs+0x1c/0x38 > [ 137.348328] [] con_close+0x5e/0x6b > [ 137.348661] [] release_dev+0x4c4/0x6ce > [ 137.348999] [] tty_release+0x12/0x1c > [ 137.349332] [] ext3_file_write+0x2d/0xba > [ 137.358495] [] do_sync_write+0xc7/0x116 > [ 137.358838] [] vfs_write+0x182/0x187 > [ 137.359176] [] sys_write+0x3d/0x64 > [ 137.359513] [] syscall_call+0x7/0xb > [ 137.359848] [] 0xffffffff > [ 137.360200] > [ 137.360202] other info that might help us debug this: > [ 137.360204] > [ 137.360335] 3 locks held by tor/4857: > [ 137.360382] #0: (&inode->i_mutex){--..}, at: [] mutex_lock+0x8/0xa > [ 137.360625] #1: (&ei->truncate_mutex){--..}, at: [] mutex_lock+0x8/0xa > [ 137.361072] #2: (&s->s_dquot.dqptr_sem){----}, at: [] dquot_alloc_space+0x50/0x189 > [ 137.361313] > [ 137.361314] stack backtrace: > [ 137.361401] [] show_trace_log_lvl+0x1a/0x30 > [ 137.361488] [] show_trace+0x12/0x14 > [ 137.361571] [] dump_stack+0x16/0x18 > [ 137.361663] [] print_circular_bug_tail+0x6f/0x71 > [ 137.361752] [] check_prev_add+0x34/0x206 > [ 137.361838] [] check_prevs_add+0x6a/0xd5 > [ 137.362786] [] __lock_acquire+0x61c/0xa05 > [ 137.362877] [] lock_acquire+0x62/0x81 > [ 137.362960] [] __mutex_lock_slowpath+0x75/0x28c > [ 137.363047] [] mutex_lock+0x8/0xa > [ 137.363132] [] print_warning+0x8c/0x15d > [ 137.363217] [] dquot_alloc_space+0x184/0x189 > [ 137.363302] [] ext3_new_blocks+0x44b/0x5a2 > [ 137.363391] [] ext3_alloc_blocks+0x40/0xdf > [ 137.363476] [] ext3_alloc_branch+0x50/0x21b > [ 137.363561] [] ext3_get_blocks_handle+0x1b8/0x367 > [ 137.363650] [] ext3_get_block+0x78/0xe3 > [ 137.363735] [] __block_prepare_write+0x168/0x3fd > [ 137.363822] [] block_prepare_write+0x28/0x3b > [ 137.363908] [] ext3_prepare_write+0x3f/0x18d > [ 137.363996] [] generic_file_buffered_write+0x197/0x5e6 > [ 137.364084] [] __generic_file_aio_write_nolock+0x2ae/0x5ad > [ 137.364171] [] generic_file_aio_write+0x58/0xc4 > [ 137.364254] [] ext3_file_write+0x2d/0xba > [ 137.364340] [] do_sync_write+0xc7/0x116 > [ 137.364425] [] vfs_write+0x182/0x187 > [ 137.364511] [] sys_write+0x3d/0x64 > [ 137.364595] [] syscall_call+0x7/0xb > [ 137.364682] ======================= >