From d0e64a981fd841cb0f28fcd6afcac55e6f1e6994 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 21 Apr 2022 10:56:39 +0100
Subject: [PATCH] btrfs: always log symlinks in full mode
Git-commit: d0e64a981fd841cb0f28fcd6afcac55e6f1e6994
Patch-mainline: v6.2-rc7
References: bsc#1214840
On Linux, empty symlinks are invalid, and attempting to create one with
the system call symlink(2) results in an -ENOENT error and this is
explicitly documented in the man page.
If we rename a symlink that was created in the current transaction and its
parent directory was logged before, we actually end up logging the symlink
without logging its content, which is stored in an inline extent. That
means that after a power failure we can end up with an empty symlink,
having no content and an i_size of 0 bytes.
It can be easily reproduced like this:
$ mkfs.btrfs -f /dev/sdc
$ mount /dev/sdc /mnt
$ mkdir /mnt/testdir
$ sync
# Create a file inside the directory and fsync the directory.
$ touch /mnt/testdir/foo
$ xfs_io -c "fsync" /mnt/testdir
# Create a symlink inside the directory and then rename the symlink.
$ ln -s /mnt/testdir/foo /mnt/testdir/bar
$ mv /mnt/testdir/bar /mnt/testdir/baz
# Now fsync again the directory, this persist the log tree.
$ xfs_io -c "fsync" /mnt/testdir
<power failure>
$ mount /dev/sdc /mnt
$ stat -c %s /mnt/testdir/baz
0
$ readlink /mnt/testdir/baz
$
Fix this by always logging symlinks in full mode (LOG_INODE_ALL), so that
their content is also logged.
A test case for fstests will follow.
CC: stable@vger.kernel.org # 4.9+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/tree-log.c | 14 +++++++++++++-
1 file changed, 13 insertions(+), 1 deletion(-)
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 09e4f1a04e6f..11399c8eed87 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -5804,6 +5804,18 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
mutex_lock(&inode->log_mutex);
}
+ /*
+ * For symlinks, we must always log their content, which is stored in an
+ * inline extent, otherwise we could end up with an empty symlink after
+ * log replay, which is invalid on linux (symlink(2) returns -ENOENT if
+ * one attempts to create an empty symlink).
+ * We don't need to worry about flushing delalloc, because when we create
+ * the inline extent when the symlink is created (we never have delalloc
+ * for symlinks).
+ */
+ if (S_ISLNK(inode->vfs_inode.i_mode))
+ inode_only = LOG_INODE_ALL;
+
/*
* Before logging the inode item, cache the value returned by
* inode_logged(), because after that we have the need to figure out if
@@ -6182,7 +6194,7 @@ static int log_new_dir_dentries(struct btrfs_trans_handle *trans,
}
ctx->log_new_dentries = false;
- if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK)
+ if (type == BTRFS_FT_DIR)
log_mode = LOG_INODE_ALL;
ret = btrfs_log_inode(trans, BTRFS_I(di_inode),
log_mode, ctx);
--
2.35.3