| From ed55b6ac077fe7f9c6490ff55172c4b563562d7c Mon Sep 17 00:00:00 2001 |
| From: Jeff Mahoney <jeffm@suse.com> |
| Date: Wed, 26 Mar 2014 14:11:26 -0400 |
| Subject: btrfs: fix lockdep warning with reclaim lock inversion |
| |
| From: Jeff Mahoney <jeffm@suse.com> |
| |
| commit ed55b6ac077fe7f9c6490ff55172c4b563562d7c upstream. |
| |
| When encountering memory pressure, testers have run into the following |
| lockdep warning. It was caused by __link_block_group calling kobject_add |
| with the groups_sem held. kobject_add calls kvasprintf with GFP_KERNEL, |
| which gets us into reclaim context. The kobject doesn't actually need |
| to be added under the lock -- it just needs to ensure that it's only |
| added for the first block group to be linked. |
| |
| ========================================================= |
| [ INFO: possible irq lock inversion dependency detected ] |
| 3.14.0-rc8-default #1 Not tainted |
| --------------------------------------------------------- |
| kswapd0/169 just changed the state of lock: |
| (&delayed_node->mutex){+.+.-.}, at: [<ffffffffa018baea>] __btrfs_release_delayed_node+0x3a/0x200 [btrfs] |
| but this lock took another, RECLAIM_FS-unsafe lock in the past: |
| (&found->groups_sem){+++++.} |
| |
| and interrupts could create inverse lock ordering between them. |
| |
| other info that might help us debug this: |
| Possible interrupt unsafe locking scenario: |
| CPU0 CPU1 |
| ---- ---- |
| lock(&found->groups_sem); |
| local_irq_disable(); |
| lock(&delayed_node->mutex); |
| lock(&found->groups_sem); |
| <Interrupt> |
| lock(&delayed_node->mutex); |
| |
| *** DEADLOCK *** |
| 2 locks held by kswapd0/169: |
| #0: (shrinker_rwsem){++++..}, at: [<ffffffff81159e8a>] shrink_slab+0x3a/0x160 |
| #1: (&type->s_umount_key#27){++++..}, at: [<ffffffff811bac6f>] grab_super_passive+0x3f/0x90 |
| |
| Signed-off-by: Jeff Mahoney <jeffm@suse.com> |
| Signed-off-by: Chris Mason <clm@fb.com> |
| Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
| |
| --- |
| fs/btrfs/extent-tree.c | 10 +++++++--- |
| 1 file changed, 7 insertions(+), 3 deletions(-) |
| |
| --- a/fs/btrfs/extent-tree.c |
| +++ b/fs/btrfs/extent-tree.c |
| @@ -8344,9 +8344,15 @@ static void __link_block_group(struct bt |
| struct btrfs_block_group_cache *cache) |
| { |
| int index = get_block_group_index(cache); |
| + bool first = false; |
| |
| down_write(&space_info->groups_sem); |
| - if (list_empty(&space_info->block_groups[index])) { |
| + if (list_empty(&space_info->block_groups[index])) |
| + first = true; |
| + list_add_tail(&cache->list, &space_info->block_groups[index]); |
| + up_write(&space_info->groups_sem); |
| + |
| + if (first) { |
| struct kobject *kobj = &space_info->block_group_kobjs[index]; |
| int ret; |
| |
| @@ -8358,8 +8364,6 @@ static void __link_block_group(struct bt |
| kobject_put(&space_info->kobj); |
| } |
| } |
| - list_add_tail(&cache->list, &space_info->block_groups[index]); |
| - up_write(&space_info->groups_sem); |
| } |
| |
| static struct btrfs_block_group_cache * |