>From 3a120841a5d9a6c42bf196389467e9e663cf1cf8 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Jun 2016 10:01:45 +0200 Subject: [PATCH] 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(). Reported-by: Eryu Guan CC: stable@vger.kernel.org Signed-off-by: Jan Kara --- fs/ext4/inode.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f7140ca66e3b..ba04d57656d4 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2748,13 +2748,27 @@ retry: done = true; } } - ext4_journal_stop(handle); /* 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 as we can release + * the last reference to io_end which may end up doing unwritten + * extent conversion which we cannot do while holding + * transaction handle. + */ + ext4_put_io_end_defer(mpd.io_submit.io_end); + /* + * Caution: 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. So we can call it only + * 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). + */ + ext4_journal_stop(handle); if (ret == -ENOSPC && sbi->s_journal) { /* -- 2.6.6