summaryrefslogtreecommitdiff
path: root/fs/btrfs/free-space-cache.c
diff options
context:
space:
mode:
authorFilipe Manana <fdmanana@suse.com>2014-11-28 00:14:15 +0300
committerChris Mason <clm@fb.com>2014-12-03 05:35:09 +0300
commit04216820fe83d5e27322065ba989de27dbfc104d (patch)
treefebfcea25770f1298cbb7470dbeba5d473751530 /fs/btrfs/free-space-cache.c
parentae0ab003f2840e7ed66ed762ec0d4e298ad1e725 (diff)
downloadlinux-04216820fe83d5e27322065ba989de27dbfc104d.tar.xz
Btrfs: fix race between fs trimming and block group remove/allocation
Our fs trim operation, which is completely transactionless (doesn't start or joins an existing transaction) consists of visiting all block groups and then for each one to iterate its free space entries and perform a discard operation against the space range represented by the free space entries. However before performing a discard, the corresponding free space entry is removed from the free space rbtree, and when the discard completes it is added back to the free space rbtree. If a block group remove operation happens while the discard is ongoing (or before it starts and after a free space entry is hidden), we end up not waiting for the discard to complete, remove the extent map that maps logical address to physical addresses and the corresponding chunk metadata from the the chunk and device trees. After that and before the discard completes, the current running transaction can finish and a new one start, allowing for new block groups that map to the same physical addresses to be allocated and written to. So fix this by keeping the extent map in memory until the discard completes so that the same physical addresses aren't reused before it completes. If the physical locations that are under a discard operation end up being used for a new metadata block group for example, and dirty metadata extents are written before the discard finishes (the VM might call writepages() of our btree inode's i_mapping for example, or an fsync log commit happens) we end up overwriting metadata with zeroes, which leads to errors from fsck like the following: checking extents Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 read block failed check_tree_block owner ref check failed [833912832 16384] Errors found in extent allocation tree or chunk allocation checking free space cache checking fs roots Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 read block failed check_tree_block root 5 root dir 256 error root 5 inode 260 errors 2001, no inode item, link count wrong unresolved ref dir 256 index 0 namelen 8 name foobar_3 filetype 1 errors 6, no dir index, no inode ref root 5 inode 262 errors 2001, no inode item, link count wrong unresolved ref dir 256 index 0 namelen 8 name foobar_5 filetype 1 errors 6, no dir index, no inode ref root 5 inode 263 errors 2001, no inode item, link count wrong (...) Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
Diffstat (limited to 'fs/btrfs/free-space-cache.c')
-rw-r--r--fs/btrfs/free-space-cache.c38
1 files changed, 37 insertions, 1 deletions
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 33848196550e..0ddc114e2aed 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -27,6 +27,7 @@
#include "disk-io.h"
#include "extent_io.h"
#include "inode-map.h"
+#include "volumes.h"
#define BITS_PER_BITMAP (PAGE_CACHE_SIZE * 8)
#define MAX_CACHE_BYTES_PER_GIG (32 * 1024)
@@ -3101,11 +3102,46 @@ int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
*trimmed = 0;
+ spin_lock(&block_group->lock);
+ if (block_group->removed) {
+ spin_unlock(&block_group->lock);
+ return 0;
+ }
+ atomic_inc(&block_group->trimming);
+ spin_unlock(&block_group->lock);
+
ret = trim_no_bitmap(block_group, trimmed, start, end, minlen);
if (ret)
- return ret;
+ goto out;
ret = trim_bitmaps(block_group, trimmed, start, end, minlen);
+out:
+ spin_lock(&block_group->lock);
+ if (atomic_dec_and_test(&block_group->trimming) &&
+ block_group->removed) {
+ struct extent_map_tree *em_tree;
+ struct extent_map *em;
+
+ spin_unlock(&block_group->lock);
+
+ 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(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 */
+ free_extent_map(em);
+ free_extent_map(em);
+ } else {
+ spin_unlock(&block_group->lock);
+ }
return ret;
}