From a1e7e16ed36b9b059c5ee94e372287418e2dc7bc Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 4 Dec 2014 15:31:01 +0000 Subject: Btrfs: ensure deletion from pinned_chunks list is protected The call to remove_extent_mapping() actually deletes the extent map from the list it's included in - fs_info->pinned_chunks - and that list is protected by the chunk mutex. Therefore make that call while holding the chunk mutex and remove the redundant list delete call because it's a noop. This fixes an overlook of the patch titled "Btrfs: fix race between fs trimming and block group remove/allocation" following the same obvervation from the patch titled "Btrfs: fix unprotected deletion from pending_chunks list". Signed-off-by: Filipe Manana Signed-off-by: Chris Mason --- fs/btrfs/free-space-cache.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 030847bf7cec..edf32c5bbef1 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -3185,16 +3185,18 @@ out: spin_unlock(&block_group->lock); + lock_chunks(block_group->fs_info->chunk_root); em_tree = &block_group->fs_info->mapping_tree.map_tree; write_lock(&em_tree->lock); em = lookup_extent_mapping(em_tree, block_group->key.objectid, 1); BUG_ON(!em); /* logic error, can't happen */ + /* + * remove_extent_mapping() will delete us from the pinned_chunks + * list, which is protected by the chunk mutex. + */ remove_extent_mapping(em_tree, em); write_unlock(&em_tree->lock); - - lock_chunks(block_group->fs_info->chunk_root); - list_del_init(&em->list); unlock_chunks(block_group->fs_info->chunk_root); /* once for us and once for the tree */ -- cgit v1.2.3 From 01eacb277909de942abbdff37584ad331e3893fe Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 4 Dec 2014 18:38:30 +0000 Subject: Btrfs: always clear a block group node when removing it from the tree Always clear a block group's rbnode after removing it from the rbtree to ensure that any tasks that might be holding a reference on the block group don't end up accessing stale rbnode left and right child pointers through next_block_group(). This is a leftover from the change titled: "Btrfs: fix invalid block group rbtree access after bg is removed" Signed-off-by: Filipe Manana Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 222d6aea4a8a..974b3edf69c7 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -8872,6 +8872,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) cache_node); rb_erase(&block_group->cache_node, &info->block_group_cache_tree); + RB_CLEAR_NODE(&block_group->cache_node); spin_unlock(&info->block_group_cache_lock); down_write(&block_group->space_info->groups_sem); @@ -9130,6 +9131,7 @@ int btrfs_read_block_groups(struct btrfs_root *root) spin_lock(&info->block_group_cache_lock); rb_erase(&cache->cache_node, &info->block_group_cache_tree); + RB_CLEAR_NODE(&cache->cache_node); spin_unlock(&info->block_group_cache_lock); btrfs_put_block_group(cache); goto error; @@ -9271,6 +9273,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, spin_lock(&root->fs_info->block_group_cache_lock); rb_erase(&cache->cache_node, &root->fs_info->block_group_cache_tree); + RB_CLEAR_NODE(&cache->cache_node); spin_unlock(&root->fs_info->block_group_cache_lock); btrfs_put_block_group(cache); return ret; -- cgit v1.2.3 From 678886bdc6378c1cbd5072da2c5a3035000214e3 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Sun, 7 Dec 2014 21:31:47 +0000 Subject: Btrfs: fix fs corruption on transaction abort if device supports discard When we abort a transaction we iterate over all the ranges marked as dirty in fs_info->freed_extents[0] and fs_info->freed_extents[1], clear them from those trees, add them back (unpin) to the free space caches and, if the fs was mounted with "-o discard", perform a discard on those regions. Also, after adding the regions to the free space caches, a fitrim ioctl call can see those ranges in a block group's free space cache and perform a discard on the ranges, so the same issue can happen without "-o discard" as well. This causes corruption, affecting one or multiple btree nodes (in the worst case leaving the fs unmountable) because some of those ranges (the ones in the fs_info->pinned_extents tree) correspond to btree nodes/leafs that are referred by the last committed super block - breaking the rule that anything that was committed by a transaction is untouched until the next transaction commits successfully. I ran into this while running in a loop (for several hours) the fstest that I recently submitted: [PATCH] fstests: add btrfs test to stress chunk allocation/removal and fstrim The corruption always happened when a transaction aborted and then fsck complained like this: _check_btrfs_filesystem: filesystem on /dev/sdc is inconsistent *** fsck.btrfs output *** Check tree block failed, want=94945280, have=0 Check tree block failed, want=94945280, have=0 Check tree block failed, want=94945280, have=0 Check tree block failed, want=94945280, have=0 Check tree block failed, want=94945280, have=0 read block failed check_tree_block Couldn't open file system In this case 94945280 corresponded to the root of a tree. Using frace what I observed was the following sequence of steps happened: 1) transaction N started, fs_info->pinned_extents pointed to fs_info->freed_extents[0]; 2) node/eb 94945280 is created; 3) eb is persisted to disk; 4) transaction N commit starts, fs_info->pinned_extents now points to fs_info->freed_extents[1], and transaction N completes; 5) transaction N + 1 starts; 6) eb is COWed, and btrfs_free_tree_block() called for this eb; 7) eb range (94945280 to 94945280 + 16Kb) is added to fs_info->pinned_extents (fs_info->freed_extents[1]); 8) Something goes wrong in transaction N + 1, like hitting ENOSPC for example, and the transaction is aborted, turning the fs into readonly mode. The stack trace I got for example: [112065.253935] [] dump_stack+0x4d/0x66 [112065.254271] [] warn_slowpath_common+0x7f/0x98 [112065.254567] [] ? __btrfs_abort_transaction+0x50/0x10b [btrfs] [112065.261674] [] warn_slowpath_fmt+0x48/0x50 [112065.261922] [] ? btrfs_free_path+0x26/0x29 [btrfs] [112065.262211] [] __btrfs_abort_transaction+0x50/0x10b [btrfs] [112065.262545] [] btrfs_remove_chunk+0x537/0x58b [btrfs] [112065.262771] [] btrfs_delete_unused_bgs+0x1de/0x21b [btrfs] [112065.263105] [] cleaner_kthread+0x100/0x12f [btrfs] (...) [112065.264493] ---[ end trace dd7903a975a31a08 ]--- [112065.264673] BTRFS: error (device sdc) in btrfs_remove_chunk:2625: errno=-28 No space left [112065.264997] BTRFS info (device sdc): forced readonly 9) The clear kthread sees that the BTRFS_FS_STATE_ERROR bit is set in fs_info->fs_state and calls btrfs_cleanup_transaction(), which in turn calls btrfs_destroy_pinned_extent(); 10) Then btrfs_destroy_pinned_extent() iterates over all the ranges marked as dirty in fs_info->freed_extents[], and for each one it calls discard, if the fs was mounted with "-o discard", and adds the range to the free space cache of the respective block group; 11) btrfs_trim_block_group(), invoked from the fitrim ioctl code path, sees the free space entries and performs a discard; 12) After an umount and mount (or fsck), our eb's location on disk was full of zeroes, and it should have been untouched, because it was marked as dirty in the fs_info->pinned_extents tree, and therefore used by the trees that the last committed superblock points to. Fix this by not performing a discard and not adding the ranges to the free space caches - it's useless from this point since the fs is now in readonly mode and we won't write free space caches to disk anymore (otherwise we would leak space) nor any new superblock. By not adding the ranges to the free space caches, it prevents other code paths from allocating that space and write to it as well, therefore being safer and simpler. This isn't a new problem, as it's been present since 2011 (git commit acce952b0263825da32cf10489413dec78053347). Cc: stable@vger.kernel.org # any kernel released after 2011-01-06 Signed-off-by: Filipe Manana Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 6 ------ fs/btrfs/extent-tree.c | 10 ++++++---- 2 files changed, 6 insertions(+), 10 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 30965120772b..8c63419a7f70 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4121,12 +4121,6 @@ again: if (ret) break; - /* opt_discard */ - if (btrfs_test_opt(root, DISCARD)) - ret = btrfs_error_discard_extent(root, start, - end + 1 - start, - NULL); - clear_extent_dirty(unpin, start, end, GFP_NOFS); btrfs_error_unpin_extent_range(root, start, end); cond_resched(); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 974b3edf69c7..4f3c03d9a575 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5727,7 +5727,8 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, update_global_block_rsv(fs_info); } -static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) +static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end, + const bool return_free_space) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_group_cache *cache = NULL; @@ -5751,7 +5752,8 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) if (start < cache->last_byte_to_unpin) { len = min(len, cache->last_byte_to_unpin - start); - btrfs_add_free_space(cache, start, len); + if (return_free_space) + btrfs_add_free_space(cache, start, len); } start += len; @@ -5815,7 +5817,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, end + 1 - start, NULL); clear_extent_dirty(unpin, start, end, GFP_NOFS); - unpin_extent_range(root, start, end); + unpin_extent_range(root, start, end, true); cond_resched(); } @@ -9693,7 +9695,7 @@ out: int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) { - return unpin_extent_range(root, start, end); + return unpin_extent_range(root, start, end, false); } int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr, -- cgit v1.2.3 From 1edb647bb95439d90c0017e9ca23c4ecf00a0409 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 8 Dec 2014 14:01:12 +0000 Subject: Btrfs: remove non-sense btrfs_error_discard_extent() function It doesn't do anything special, it just calls btrfs_discard_extent(), so just remove it. Signed-off-by: Filipe Manana Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 4 ++-- fs/btrfs/extent-tree.c | 10 ++-------- fs/btrfs/free-space-cache.c | 4 ++-- 3 files changed, 6 insertions(+), 12 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index e6fbbd74b716..7e607416755a 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3481,8 +3481,8 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info); u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo); int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end); -int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr, - u64 num_bytes, u64 *actual_bytes); +int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, + u64 num_bytes, u64 *actual_bytes); int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 type); int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 4f3c03d9a575..a80b97100d90 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1889,8 +1889,8 @@ static int btrfs_issue_discard(struct block_device *bdev, return blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_NOFS, 0); } -static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, - u64 num_bytes, u64 *actual_bytes) +int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, + u64 num_bytes, u64 *actual_bytes) { int ret; u64 discarded_bytes = 0; @@ -9698,12 +9698,6 @@ int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) return unpin_extent_range(root, start, end, false); } -int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr, - u64 num_bytes, u64 *actual_bytes) -{ - return btrfs_discard_extent(root, bytenr, num_bytes, actual_bytes); -} - int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range) { struct btrfs_fs_info *fs_info = root->fs_info; diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index edf32c5bbef1..d6c03f7f136b 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2966,8 +2966,8 @@ static int do_trimming(struct btrfs_block_group_cache *block_group, spin_unlock(&block_group->lock); spin_unlock(&space_info->lock); - ret = btrfs_error_discard_extent(fs_info->extent_root, - start, bytes, &trimmed); + ret = btrfs_discard_extent(fs_info->extent_root, + start, bytes, &trimmed); if (!ret) *total_trimmed += trimmed; -- cgit v1.2.3