Messages in this thread Patch in this message | | | Date | Thu, 28 Jan 2010 13:53:34 +0100 | From | Frederic Weisbecker <> | Subject | [PATCH] reiserfs: Fix vmalloc call under reiserfs lock |
| |
On Sun, Jan 24, 2010 at 09:44:25PM +0300, Alexander Beregalov wrote: > Hi Frederic > > Here is another warning: > > [ INFO: inconsistent lock state ] > 2.6.33-rc5 #1 > --------------------------------- > inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage. > kswapd0/313 [HC0[0]:SC0[0]:HE1:SE1] takes: > (&REISERFS_SB(s)->lock){+.+.?.}, at: [<c11118c8>] > reiserfs_write_lock_once+0x28/0x50 > {RECLAIM_FS-ON-W} state was registered at: > [<c104ee32>] mark_held_locks+0x62/0x90 > [<c104eefa>] lockdep_trace_alloc+0x9a/0xc0 > [<c108f7b6>] kmem_cache_alloc+0x26/0xf0 > [<c108621c>] __get_vm_area_node+0x6c/0xf0 > [<c108690e>] __vmalloc_node+0x7e/0xa0 > [<c1086aab>] vmalloc+0x2b/0x30 > [<c110e1fb>] journal_init+0x6cb/0xa10 > [<c10f90a2>] reiserfs_fill_super+0x342/0xb80 > [<c1095665>] get_sb_bdev+0x145/0x180 > [<c10f68e1>] get_super_block+0x21/0x30 > [<c1094520>] vfs_kern_mount+0x40/0xd0 > [<c1094609>] do_kern_mount+0x39/0xd0 > [<c10aaa97>] do_mount+0x2c7/0x6d0 > [<c10aaf06>] sys_mount+0x66/0xa0 > [<c16198a7>] mount_block_root+0xc4/0x245 > [<c1619a81>] mount_root+0x59/0x5f > [<c1619b98>] prepare_namespace+0x111/0x14b > [<c1619269>] kernel_init+0xcf/0xdb > [<c100303a>] kernel_thread_helper+0x6/0x1c > irq event stamp: 63236801 > hardirqs last enabled at (63236801): [<c134e7fa>] > __mutex_unlock_slowpath+0x9a/0x120 > hardirqs last disabled at (63236800): [<c134e799>] > __mutex_unlock_slowpath+0x39/0x120 > softirqs last enabled at (63218800): [<c102f451>] __do_softirq+0xc1/0x110 > softirqs last disabled at (63218789): [<c102f4ed>] do_softirq+0x4d/0x60 > > other info that might help us debug this: > 2 locks held by kswapd0/313: > #0: (shrinker_rwsem){++++..}, at: [<c1074bb4>] shrink_slab+0x24/0x170 > #1: (&type->s_umount_key#19){++++..}, at: [<c10a2edd>] > shrink_dcache_memory+0xfd/0x1a0 > > stack backtrace: > Pid: 313, comm: kswapd0 Not tainted 2.6.33-rc5 #1 > Call Trace: > [<c134db2c>] ? printk+0x18/0x1c > [<c104e7ef>] print_usage_bug+0x15f/0x1a0 > [<c104ebcf>] mark_lock+0x39f/0x5a0 > [<c104d66b>] ? trace_hardirqs_off+0xb/0x10 > [<c1052c50>] ? check_usage_forwards+0x0/0xf0 > [<c1050c24>] __lock_acquire+0x214/0xa70 > [<c10438c5>] ? sched_clock_cpu+0x95/0x110 > [<c10514fa>] lock_acquire+0x7a/0xa0 > [<c11118c8>] ? reiserfs_write_lock_once+0x28/0x50 > [<c134f03f>] mutex_lock_nested+0x5f/0x2b0 > [<c11118c8>] ? reiserfs_write_lock_once+0x28/0x50 > [<c11118c8>] ? reiserfs_write_lock_once+0x28/0x50 > [<c11118c8>] reiserfs_write_lock_once+0x28/0x50 > [<c10f05b0>] reiserfs_delete_inode+0x50/0x140 > [<c10a653f>] ? generic_delete_inode+0x5f/0x150 > [<c10f0560>] ? reiserfs_delete_inode+0x0/0x140 > [<c10a657c>] generic_delete_inode+0x9c/0x150 > [<c10a666d>] generic_drop_inode+0x3d/0x60 > [<c10a5597>] iput+0x47/0x50 > [<c10a2a4f>] dentry_iput+0x6f/0xf0 > [<c10a2af4>] d_kill+0x24/0x50 > [<c10a2d3d>] __shrink_dcache_sb+0x21d/0x2b0 > [<c10a2f0f>] shrink_dcache_memory+0x12f/0x1a0 > [<c1074c9e>] shrink_slab+0x10e/0x170 > [<c1075177>] kswapd+0x477/0x6a0 > [<c1072d10>] ? isolate_pages_global+0x0/0x1b0 > [<c103e160>] ? autoremove_wake_function+0x0/0x40 > [<c1074d00>] ? kswapd+0x0/0x6a0 > [<c103de6c>] kthread+0x6c/0x80 > [<c103de00>] ? kthread+0x0/0x80 > [<c100303a>] kernel_thread_helper+0x6/0x1c
Ok, I think this patch fixes the issues. Unfortunately I can't reproduce this lockdep warning, even by booting with low memory and then stress testing.
I hope you can give it a try.
Thanks a lot!
--- From bbec919150037b8a2e58e32d3ba642ba3b6582a5 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker <fweisbec@gmail.com> Date: Thu, 28 Jan 2010 13:43:50 +0100 Subject: [PATCH] reiserfs: Fix vmalloc call under reiserfs lock
Vmalloc is called to allocate journal->j_cnode_free_list but we hold the reiserfs lock at this time, which raises a {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} lock inversion.
Just drop the reiserfs lock at this time, as it's not even needed but kept for paranoid reasons.
This fixes:
[ INFO: inconsistent lock state ] 2.6.33-rc5 #1 --------------------------------- inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage. kswapd0/313 [HC0[0]:SC0[0]:HE1:SE1] takes: (&REISERFS_SB(s)->lock){+.+.?.}, at: [<c11118c8>] reiserfs_write_lock_once+0x28/0x50 {RECLAIM_FS-ON-W} state was registered at: [<c104ee32>] mark_held_locks+0x62/0x90 [<c104eefa>] lockdep_trace_alloc+0x9a/0xc0 [<c108f7b6>] kmem_cache_alloc+0x26/0xf0 [<c108621c>] __get_vm_area_node+0x6c/0xf0 [<c108690e>] __vmalloc_node+0x7e/0xa0 [<c1086aab>] vmalloc+0x2b/0x30 [<c110e1fb>] journal_init+0x6cb/0xa10 [<c10f90a2>] reiserfs_fill_super+0x342/0xb80 [<c1095665>] get_sb_bdev+0x145/0x180 [<c10f68e1>] get_super_block+0x21/0x30 [<c1094520>] vfs_kern_mount+0x40/0xd0 [<c1094609>] do_kern_mount+0x39/0xd0 [<c10aaa97>] do_mount+0x2c7/0x6d0 [<c10aaf06>] sys_mount+0x66/0xa0 [<c16198a7>] mount_block_root+0xc4/0x245 [<c1619a81>] mount_root+0x59/0x5f [<c1619b98>] prepare_namespace+0x111/0x14b [<c1619269>] kernel_init+0xcf/0xdb [<c100303a>] kernel_thread_helper+0x6/0x1c irq event stamp: 63236801 hardirqs last enabled at (63236801): [<c134e7fa>] __mutex_unlock_slowpath+0x9a/0x120 hardirqs last disabled at (63236800): [<c134e799>] __mutex_unlock_slowpath+0x39/0x120 softirqs last enabled at (63218800): [<c102f451>] __do_softirq+0xc1/0x110 softirqs last disabled at (63218789): [<c102f4ed>] do_softirq+0x4d/0x60
other info that might help us debug this: 2 locks held by kswapd0/313: #0: (shrinker_rwsem){++++..}, at: [<c1074bb4>] shrink_slab+0x24/0x170 #1: (&type->s_umount_key#19){++++..}, at: [<c10a2edd>] shrink_dcache_memory+0xfd/0x1a0
stack backtrace: Pid: 313, comm: kswapd0 Not tainted 2.6.33-rc5 #1 Call Trace: [<c134db2c>] ? printk+0x18/0x1c [<c104e7ef>] print_usage_bug+0x15f/0x1a0 [<c104ebcf>] mark_lock+0x39f/0x5a0 [<c104d66b>] ? trace_hardirqs_off+0xb/0x10 [<c1052c50>] ? check_usage_forwards+0x0/0xf0 [<c1050c24>] __lock_acquire+0x214/0xa70 [<c10438c5>] ? sched_clock_cpu+0x95/0x110 [<c10514fa>] lock_acquire+0x7a/0xa0 [<c11118c8>] ? reiserfs_write_lock_once+0x28/0x50 [<c134f03f>] mutex_lock_nested+0x5f/0x2b0 [<c11118c8>] ? reiserfs_write_lock_once+0x28/0x50 [<c11118c8>] ? reiserfs_write_lock_once+0x28/0x50 [<c11118c8>] reiserfs_write_lock_once+0x28/0x50 [<c10f05b0>] reiserfs_delete_inode+0x50/0x140 [<c10a653f>] ? generic_delete_inode+0x5f/0x150 [<c10f0560>] ? reiserfs_delete_inode+0x0/0x140 [<c10a657c>] generic_delete_inode+0x9c/0x150 [<c10a666d>] generic_drop_inode+0x3d/0x60 [<c10a5597>] iput+0x47/0x50 [<c10a2a4f>] dentry_iput+0x6f/0xf0 [<c10a2af4>] d_kill+0x24/0x50 [<c10a2d3d>] __shrink_dcache_sb+0x21d/0x2b0 [<c10a2f0f>] shrink_dcache_memory+0x12f/0x1a0 [<c1074c9e>] shrink_slab+0x10e/0x170 [<c1075177>] kswapd+0x477/0x6a0 [<c1072d10>] ? isolate_pages_global+0x0/0x1b0 [<c103e160>] ? autoremove_wake_function+0x0/0x40 [<c1074d00>] ? kswapd+0x0/0x6a0 [<c103de6c>] kthread+0x6c/0x80 [<c103de00>] ? kthread+0x0/0x80 [<c100303a>] kernel_thread_helper+0x6/0x1c
Reported-by: Alexander Beregalov <a.beregalov@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Christian Kujau <lists@nerdbynature.de> Cc: Chris Mason <chris.mason@oracle.com> --- fs/reiserfs/journal.c | 2 ++ 1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 83ac4d3..ba98546 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -2913,7 +2913,9 @@ int journal_init(struct super_block *sb, const char *j_dev_name, journal->j_mount_id = 10; journal->j_state = 0; atomic_set(&(journal->j_jlock), 0); + reiserfs_write_unlock(sb); journal->j_cnode_free_list = allocate_cnodes(num_cnodes); + reiserfs_write_lock(sb); journal->j_cnode_free_orig = journal->j_cnode_free_list; journal->j_cnode_free = journal->j_cnode_free_list ? num_cnodes : 0; journal->j_cnode_used = 0; -- 1.6.2.3
| |