summaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
authorJan Kara <jack@suse.cz>2016-07-04 10:14:01 -0400
committerTheodore Ts'o <tytso@mit.edu>2016-07-04 10:14:01 -0400
commit646caa9c8e196880b41cd3e3d33a2ebc752bdb85 (patch)
tree28d3c6dcf43b1ba8e8d1b5eff334b9c07b098db2 /fs/ext4
parentfa96454069b85a7e5d10f38b7d95edcd5dc64b9a (diff)
ext4: fix deadlock during page writeback
Commit 06bd3c36a733 (ext4: fix data exposure after a crash) uncovered a deadlock in ext4_writepages() which was previously much harder to hit. After this commit xfstest generic/130 reproduces the deadlock on small filesystems. The problem happens when ext4_do_update_inode() sets LARGE_FILE feature and marks current inode handle as synchronous. That subsequently results in ext4_journal_stop() called from ext4_writepages() to block waiting for transaction commit while still holding page locks, reference to io_end, and some prepared bio in mpd structure each of which can possibly block transaction commit from completing and thus results in deadlock. Fix the problem by releasing page locks, io_end reference, and submitting prepared bio before calling ext4_journal_stop(). [ Changed to defer the call to ext4_journal_stop() only if the handle is synchronous. --tytso ] Reported-and-tested-by: Eryu Guan <eguan@redhat.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> CC: stable@vger.kernel.org Signed-off-by: Jan Kara <jack@suse.cz>
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/inode.c29
1 files changed, 26 insertions, 3 deletions
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 44ee5d933b36..321a31cef59c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2754,13 +2754,36 @@ retry:
done = true;
}
}
- ext4_journal_stop(handle);
+ /*
+ * Caution: If the handle is synchronous,
+ * ext4_journal_stop() can wait for transaction commit
+ * to finish which may depend on writeback of pages to
+ * complete or on page lock to be released. In that
+ * case, we have to wait until after after we have
+ * submitted all the IO, released page locks we hold,
+ * and dropped io_end reference (for extent conversion
+ * to be able to complete) before stopping the handle.
+ */
+ if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
+ ext4_journal_stop(handle);
+ handle = NULL;
+ }
/* Submit prepared bio */
ext4_io_submit(&mpd.io_submit);
/* Unlock pages we didn't use */
mpage_release_unused_pages(&mpd, give_up_on_write);
- /* Drop our io_end reference we got from init */
- ext4_put_io_end(mpd.io_submit.io_end);
+ /*
+ * Drop our io_end reference we got from init. We have
+ * to be careful and use deferred io_end finishing if
+ * we are still holding the transaction as we can
+ * release the last reference to io_end which may end
+ * up doing unwritten extent conversion.
+ */
+ if (handle) {
+ ext4_put_io_end_defer(mpd.io_submit.io_end);
+ ext4_journal_stop(handle);
+ } else
+ ext4_put_io_end(mpd.io_submit.io_end);
if (ret == -ENOSPC && sbi->s_journal) {
/*