From 73beece9ca07c003e0e4f4825b12be167334d4ad Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Fri, 17 Jul 2015 16:49:19 +0800 Subject: Btrfs: fix lockdep deadlock warning due to dev_replace Xfstests btrfs/011 complains about a deadlock warning, [ 1226.649039] ========================================================= [ 1226.649039] [ INFO: possible irq lock inversion dependency detected ] [ 1226.649039] 4.1.0+ #270 Not tainted [ 1226.649039] --------------------------------------------------------- [ 1226.652955] kswapd0/46 just changed the state of lock: [ 1226.652955] (&delayed_node->mutex){+.+.-.}, at: [] __btrfs_release_delayed_node+0x45/0x1d0 [ 1226.652955] but this lock took another, RECLAIM_FS-unsafe lock in the past: [ 1226.652955] (&fs_info->dev_replace.lock){+.+.+.} and interrupts could create inverse lock ordering between them. [ 1226.652955] other info that might help us debug this: [ 1226.652955] Chain exists of: &delayed_node->mutex --> &found->groups_sem --> &fs_info->dev_replace.lock [ 1226.652955] Possible interrupt unsafe locking scenario: [ 1226.652955] CPU0 CPU1 [ 1226.652955] ---- ---- [ 1226.652955] lock(&fs_info->dev_replace.lock); [ 1226.652955] local_irq_disable(); [ 1226.652955] lock(&delayed_node->mutex); [ 1226.652955] lock(&found->groups_sem); [ 1226.652955] [ 1226.652955] lock(&delayed_node->mutex); [ 1226.652955] *** DEADLOCK *** Commit 084b6e7c7607 ("btrfs: Fix a lockdep warning when running xfstest.") tried to fix a similar one that has the exactly same warning, but with that, we still run to this. The above lock chain comes from btrfs_commit_transaction ->btrfs_run_delayed_items ... ->__btrfs_update_delayed_inode ... ->__btrfs_cow_block ... ->find_free_extent ->cache_block_group ->load_free_space_cache ->btrfs_readpages ->submit_one_bio ... ->__btrfs_map_block ->btrfs_dev_replace_lock However, with high memory pressure, tasks which hold dev_replace.lock can be interrupted by kswapd and then kswapd is intended to release memory occupied by superblock, inodes and dentries, where we may call evict_inode, and it comes to [ 1226.652955] [] __btrfs_release_delayed_node+0x45/0x1d0 [ 1226.652955] [] btrfs_remove_delayed_node+0x24/0x30 [ 1226.652955] [] btrfs_evict_inode+0x34e/0x700 delayed_node->mutex may be acquired in __btrfs_release_delayed_node(), and it leads to a ABBA deadlock. To fix this, we can use "blocking rwlock" used in the case of extent_buffer, but things are simpler here since we only needs read's spinlock to blocking lock. With this, btrfs/011 no more produces warnings in dmesg. Signed-off-by: Liu Bo Signed-off-by: David Sterba --- fs/btrfs/reada.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'fs/btrfs/reada.c') diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index 619f92963e27..fe3d4c7b6342 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -396,7 +396,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root, } /* insert extent in reada_tree + all per-device trees, all or nothing */ - btrfs_dev_replace_lock(&fs_info->dev_replace); + btrfs_dev_replace_lock(&fs_info->dev_replace, 0); spin_lock(&fs_info->reada_lock); ret = radix_tree_insert(&fs_info->reada_tree, index, re); if (ret == -EEXIST) { @@ -404,12 +404,12 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root, BUG_ON(!re_exist); re_exist->refcnt++; spin_unlock(&fs_info->reada_lock); - btrfs_dev_replace_unlock(&fs_info->dev_replace); + btrfs_dev_replace_unlock(&fs_info->dev_replace, 0); goto error; } if (ret) { spin_unlock(&fs_info->reada_lock); - btrfs_dev_replace_unlock(&fs_info->dev_replace); + btrfs_dev_replace_unlock(&fs_info->dev_replace, 0); goto error; } prev_dev = NULL; @@ -456,12 +456,12 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root, BUG_ON(fs_info == NULL); radix_tree_delete(&fs_info->reada_tree, index); spin_unlock(&fs_info->reada_lock); - btrfs_dev_replace_unlock(&fs_info->dev_replace); + btrfs_dev_replace_unlock(&fs_info->dev_replace, 0); goto error; } } spin_unlock(&fs_info->reada_lock); - btrfs_dev_replace_unlock(&fs_info->dev_replace); + btrfs_dev_replace_unlock(&fs_info->dev_replace, 0); btrfs_put_bbio(bbio); return re; -- cgit v1.2.3