* [PATCH] reiserfs: Fix vmalloc call under reiserfs lock
2010-01-24 18:44 reiserfs: lockdep warning Alexander Beregalov
@ 2010-01-28 12:53 ` Frederic Weisbecker
0 siblings, 0 replies; 2+ messages in thread
From: Frederic Weisbecker @ 2010-01-28 12:53 UTC (permalink / raw)
To: Alexander Beregalov
Cc: Linux Kernel Mailing List, Christian Kujau, Chris Mason
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
^ permalink raw reply related [flat|nested] 2+ messages in thread