From 41bd60676923822de1df2c50b3f9a10171f4338a Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 28 Nov 2018 14:54:28 +0000 Subject: [PATCH] Btrfs: fix fsync of files with multiple hard links in new directories The log tree has a long standing problem that when a file is fsync'ed we only check for new ancestors, created in the current transaction, by following only the hard link for which the fsync was issued. We follow the ancestors using the VFS' dget_parent() API. This means that if we create a new link for a file in a directory that is new (or in an any other new ancestor directory) and then fsync the file using an old hard link, we end up not logging the new ancestor, and on log replay that new hard link and ancestor do not exist. In some cases, involving renames, the file will not exist at all. Example: mkfs.btrfs -f /dev/sdb mount /dev/sdb /mnt mkdir /mnt/A touch /mnt/foo ln /mnt/foo /mnt/A/bar xfs_io -c fsync /mnt/foo In this example after log replay only the hard link named 'foo' exists and directory A does not exist, which is unexpected. In other major linux filesystems, such as ext4, xfs and f2fs for example, both hard links exist and so does directory A after mounting again the filesystem. Checking if any new ancestors are new and need to be logged was added in 2009 by commit 12fcfd22fe5b ("Btrfs: tree logging unlink/rename fixes"), however only for the ancestors of the hard link (dentry) for which the fsync was issued, instead of checking for all ancestors for all of the inode's hard links. So fix this by tracking the id of the last transaction where a hard link was created for an inode and then on fsync fallback to a full transaction commit when an inode has more than one hard link and at least one new hard link was created in the current transaction. This is the simplest solution since this is not a common use case (adding frequently hard links for which there's an ancestor created in the current transaction and then fsync the file). In case it ever becomes a common use case, a solution that consists of iterating the fs/subvol btree for each hard link and check if any ancestor is new, could be implemented. This solves many unexpected scenarios reported by Jayashree Mohan and Vijay Chidambaram, and for which there is a new test case for fstests under review. Fixes: 12fcfd22fe5b ("Btrfs: tree logging unlink/rename fixes") CC: stable@vger.kernel.org # 4.4+ Reported-by: Vijay Chidambaram Reported-by: Jayashree Mohan Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/btrfs_inode.h | 6 ++++++ fs/btrfs/inode.c | 17 +++++++++++++++++ fs/btrfs/tree-log.c | 16 ++++++++++++++++ 3 files changed, 39 insertions(+) diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index fc25607304f2..6f5d07415dab 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -147,6 +147,12 @@ struct btrfs_inode { */ u64 last_unlink_trans; + /* + * Track the transaction id of the last transaction used to create a + * hard link for the inode. This is used by the log tree (fsync). + */ + u64 last_link_trans; + /* * Number of bytes outstanding that are going to need csums. This is * used in ENOSPC accounting. diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d54bdef16d8d..b4129d9072ec 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3658,6 +3658,21 @@ cache_index: * inode is not a directory, logging its parent unnecessarily. */ BTRFS_I(inode)->last_unlink_trans = BTRFS_I(inode)->last_trans; + /* + * Similar reasoning for last_link_trans, needs to be set otherwise + * for a case like the following: + * + * mkdir A + * touch foo + * ln foo A/bar + * echo 2 > /proc/sys/vm/drop_caches + * fsync foo + * + * + * Would result in link bar and directory A not existing after the power + * failure. + */ + BTRFS_I(inode)->last_link_trans = BTRFS_I(inode)->last_trans; path->slots[0]++; if (inode->i_nlink != 1 || @@ -6597,6 +6612,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, if (err) goto fail; } + BTRFS_I(inode)->last_link_trans = trans->transid; d_instantiate(dentry, inode); ret = btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent, true, NULL); @@ -9123,6 +9139,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) ei->index_cnt = (u64)-1; ei->dir_index = 0; ei->last_unlink_trans = 0; + ei->last_link_trans = 0; ei->last_log_commit = 0; spin_lock_init(&ei->lock); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 013d0abcd46b..5baad9bebc62 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -5758,6 +5758,22 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, goto end_trans; } + /* + * If a new hard link was added to the inode in the current transaction + * and its link count is now greater than 1, we need to fallback to a + * transaction commit, otherwise we can end up not logging all its new + * parents for all the hard links. Here just from the dentry used to + * fsync, we can not visit the ancestor inodes for all the other hard + * links to figure out if any is new, so we fallback to a transaction + * commit (instead of adding a lot of complexity of scanning a btree, + * since this scenario is not a common use case). + */ + if (inode->vfs_inode.i_nlink > 1 && + inode->last_link_trans > last_committed) { + ret = -EMLINK; + goto end_trans; + } + while (1) { if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) break; -- 2.30.2