From de2b530bfb683fd75c31ab65ec42949f5f7a5b58 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 11 Sep 2013 09:36:30 -0400 Subject: Btrfs: actually log directory we are fsync()'ing If you just create a directory and then fsync that directory and then pull the power plug you will come back up and the directory will not be there. That is because we won't actually create directories if we've logged files inside of them since they will be created on replay, but in this check we will set our logged_trans of our current directory if it happens to be a directory, making us think it doesn't need to be logged. Fix the logic to only do this to parent directories. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 0d9613c3f5e..aaa2e2b6747 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3805,6 +3805,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, int ret = 0; struct btrfs_root *root; struct dentry *old_parent = NULL; + struct inode *orig_inode = inode; /* * for regular files, if its inode is already on disk, we don't @@ -3824,7 +3825,14 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, } while (1) { - BTRFS_I(inode)->logged_trans = trans->transid; + /* + * If we are logging a directory then we start with our inode, + * not our parents inode, so we need to skipp setting the + * logged_trans so that further down in the log code we don't + * think this inode has already been logged. + */ + if (inode != orig_inode) + BTRFS_I(inode)->logged_trans = trans->transid; smp_mb(); if (BTRFS_I(inode)->last_unlink_trans > last_committed) { -- cgit v1.2.3-70-g09d2 From dd8e721773fdab5ccc7fde44ec57e30b563243b2 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 11 Sep 2013 11:57:23 -0400 Subject: Btrfs: replay dir_index items before other items A user reported a bug where his log would not replay because he was getting -EEXIST back. This was because he had a file moved into a directory that was logged. What happens is the file had a lower inode number, and so it is processed first when replaying the log, and so we add the inode ref in for the directory it was moved to. But then we process the directories DIR_INDEX item and try to add the inode ref for that inode and it fails because we already added it when we replayed the inode. To solve this problem we need to just process any DIR_INDEX items we have in the log first so this all is taken care of, and then we can replay the rest of the items. With this patch my reproducer can remount the file system properly instead of erroring out. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index aaa2e2b6747..c91309dea8d 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -93,7 +93,8 @@ */ #define LOG_WALK_PIN_ONLY 0 #define LOG_WALK_REPLAY_INODES 1 -#define LOG_WALK_REPLAY_ALL 2 +#define LOG_WALK_REPLAY_DIR_INDEX 2 +#define LOG_WALK_REPLAY_ALL 3 static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode, @@ -2027,6 +2028,15 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, if (ret) break; } + + if (key.type == BTRFS_DIR_INDEX_KEY && + wc->stage == LOG_WALK_REPLAY_DIR_INDEX) { + ret = replay_one_dir_item(wc->trans, root, path, + eb, i, &key); + if (ret) + break; + } + if (wc->stage < LOG_WALK_REPLAY_ALL) continue; @@ -2048,8 +2058,7 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, eb, i, &key); if (ret) break; - } else if (key.type == BTRFS_DIR_ITEM_KEY || - key.type == BTRFS_DIR_INDEX_KEY) { + } else if (key.type == BTRFS_DIR_ITEM_KEY) { ret = replay_one_dir_item(wc->trans, root, path, eb, i, &key); if (ret) -- cgit v1.2.3-70-g09d2 From d555438b6e1dad139d26ab807f0af68a1fa47a86 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 11 Sep 2013 14:17:00 -0400 Subject: Btrfs: drop dir i_size when adding new names on replay So if we have dir_index items in the log that means we also have the inode item as well, which means that the inode's i_size is correct. However when we process dir_index'es we call btrfs_add_link() which will increase the directory's i_size for the new entry. To fix this we need to just set the dir items i_size to 0, and then as we find dir_index items we adjust the i_size. btrfs_add_link() will do it for new entries, and if the entry already exists we can just add the name_len to the i_size ourselves. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index c91309dea8d..79f057c0619 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -394,6 +394,7 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, if (inode_item) { struct btrfs_inode_item *item; u64 nbytes; + u32 mode; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); @@ -401,9 +402,19 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item); btrfs_set_inode_nbytes(eb, item, nbytes); + + /* + * If this is a directory we need to reset the i_size to + * 0 so that we can set it up properly when replaying + * the rest of the items in this log. + */ + mode = btrfs_inode_mode(eb, item); + if (S_ISDIR(mode)) + btrfs_set_inode_size(eb, item, 0); } } else if (inode_item) { struct btrfs_inode_item *item; + u32 mode; /* * New inode, set nbytes to 0 so that the nbytes comes out @@ -411,6 +422,15 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, */ item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item); btrfs_set_inode_nbytes(eb, item, 0); + + /* + * If this is a directory we need to reset the i_size to 0 so + * that we can set it up properly when replaying the rest of + * the items in this log. + */ + mode = btrfs_inode_mode(eb, item); + if (S_ISDIR(mode)) + btrfs_set_inode_size(eb, item, 0); } insert: btrfs_release_path(path); @@ -1497,6 +1517,7 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans, iput(inode); return -EIO; } + ret = btrfs_add_link(trans, dir, inode, name, name_len, 1, index); /* FIXME, put inode into FIXUP list */ @@ -1535,6 +1556,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, u8 log_type; int exists; int ret = 0; + bool update_size = (key->type == BTRFS_DIR_INDEX_KEY); dir = read_one_inode(root, key->objectid); if (!dir) @@ -1605,6 +1627,10 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, goto insert; out: btrfs_release_path(path); + if (!ret && update_size) { + btrfs_i_size_write(dir, dir->i_size + name_len * 2); + ret = btrfs_update_inode(trans, root, dir); + } kfree(name); iput(dir); return ret; @@ -1615,6 +1641,7 @@ insert: name, name_len, log_type, &log_key); if (ret && ret != -ENOENT) goto out; + update_size = false; ret = 0; goto out; } -- cgit v1.2.3-70-g09d2