diff options
Diffstat (limited to 'fs/btrfs/tree-log.c')
| -rw-r--r-- | fs/btrfs/tree-log.c | 63 |
1 files changed, 53 insertions, 10 deletions
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 6ba022ed4a52..c7190f322576 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2223,8 +2223,10 @@ again: nritems = btrfs_header_nritems(path->nodes[0]); if (path->slots[0] >= nritems) { ret = btrfs_next_leaf(root, path); - if (ret) + if (ret == 1) break; + else if (ret < 0) + goto out; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); @@ -2959,8 +2961,11 @@ out_wake_log_root: mutex_unlock(&log_root_tree->log_mutex); /* - * The barrier before waitqueue_active is implied by mutex_unlock + * The barrier before waitqueue_active is needed so all the updates + * above are seen by the woken threads. It might not be necessary, but + * proving that seems to be hard. */ + smp_mb(); if (waitqueue_active(&log_root_tree->log_commit_wait[index2])) wake_up(&log_root_tree->log_commit_wait[index2]); out: @@ -2971,8 +2976,11 @@ out: mutex_unlock(&root->log_mutex); /* - * The barrier before waitqueue_active is implied by mutex_unlock + * The barrier before waitqueue_active is needed so all the updates + * above are seen by the woken threads. It might not be necessary, but + * proving that seems to be hard. */ + smp_mb(); if (waitqueue_active(&root->log_commit_wait[index1])) wake_up(&root->log_commit_wait[index1]); return ret; @@ -3313,9 +3321,16 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, } btrfs_release_path(path); - /* find the first key from this transaction again */ + /* + * Find the first key from this transaction again. See the note for + * log_new_dir_dentries, if we're logging a directory recursively we + * won't be holding its i_mutex, which means we can modify the directory + * while we're logging it. If we remove an entry between our first + * search and this search we'll not find the key again and can just + * bail. + */ ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); - if (WARN_ON(ret != 0)) + if (ret != 0) goto done; /* @@ -3378,8 +3393,11 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, * from this directory and from this transaction */ ret = btrfs_next_leaf(root, path); - if (ret == 1) { - last_offset = (u64)-1; + if (ret) { + if (ret == 1) + last_offset = (u64)-1; + else + err = ret; goto done; } btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]); @@ -3830,6 +3848,7 @@ fill_holes: ASSERT(ret == 0); src = src_path->nodes[0]; i = 0; + need_find_last_extent = true; } btrfs_item_key_to_cpu(src, &key, i); @@ -5228,9 +5247,33 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, dir_inode = btrfs_iget(root->fs_info->sb, &inode_key, root, NULL); - /* If parent inode was deleted, skip it. */ - if (IS_ERR(dir_inode)) - continue; + /* + * If the parent inode was deleted, return an error to + * fallback to a transaction commit. This is to prevent + * getting an inode that was moved from one parent A to + * a parent B, got its former parent A deleted and then + * it got fsync'ed, from existing at both parents after + * a log replay (and the old parent still existing). + * Example: + * + * mkdir /mnt/A + * mkdir /mnt/B + * touch /mnt/B/bar + * sync + * mv /mnt/B/bar /mnt/A/bar + * mv -T /mnt/A /mnt/B + * fsync /mnt/B/bar + * <power fail> + * + * If we ignore the old parent B which got deleted, + * after a log replay we would have file bar linked + * at both parents and the old parent B would still + * exist. + */ + if (IS_ERR(dir_inode)) { + ret = PTR_ERR(dir_inode); + goto out; + } ret = btrfs_log_inode(trans, root, dir_inode, LOG_INODE_ALL, 0, LLONG_MAX, ctx); |