[PATCH] ext4: fix bh->b_state corruption

[Nikolay Borisov <kernel@kyup.com>]

From: Jan Kara <jack@suse.com>

commit ed8ad83808f009ade97ebbf6519bc3a97fefbc0c upstream

ext4 can update bh->b_state non-atomically in _ext4_get_block() and
ext4_da_get_block_prep(). Usually this is fine since bh is just a
temporary storage for mapping information on stack but in some cases it
can be fully living bh attached to a page. In such case non-atomic
update of bh->b_state can race with an atomic update which then gets
lost. Usually when we are mapping bh and thus updating bh->b_state
non-atomically, nobody else touches the bh and so things work out fine
but there is one case to especially worry about: ext4_finish_bio() uses
BH_Uptodate_Lock on the first bh in the page to synchronize handling of
PageWriteback state. So when blocksize < pagesize, we can be atomically
modifying bh->b_state of a buffer that actually isn't under IO and thus
can race e.g. with delalloc trying to map that buffer. The result is
that we can mistakenly set / clear BH_Uptodate_Lock bit resulting in the
corruption of PageWriteback state or missed unlock of BH_Uptodate_Lock.

Fix the problem by always updating bh->b_state bits atomically.

CC: stable@vger.kernel.org
Reported-by: Nikolay Borisov <kernel@kyup.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Nikolay Borisov <kernel@kyup.com>
[NB: Backported to 4.4.2]
---
 fs/ext4/inode.c | 32 ++++++++++++++++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ea433a7f4bca..06bda0361e7c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -657,6 +657,34 @@ has_zeroout:
 	return retval;
 }
 
+/*
+ * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages
+ * we have to be careful as someone else may be manipulating b_state as well.
+ */
+static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
+{
+	unsigned long old_state;
+	unsigned long new_state;
+
+	flags &= EXT4_MAP_FLAGS;
+
+	/* Dummy buffer_head? Set non-atomically. */
+	if (!bh->b_page) {
+		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags;
+		return;
+	}
+	/*
+	 * Someone else may be modifying b_state. Be careful! This is ugly but
+	 * once we get rid of using bh as a container for mapping information
+	 * to pass to / from get_block functions, this can go away.
+	 */
+	do {
+		old_state = READ_ONCE(bh->b_state);
+		new_state = (old_state & ~EXT4_MAP_FLAGS) | flags;
+	} while (unlikely(
+		 cmpxchg(&bh->b_state, old_state, new_state) != old_state));
+}
+
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
@@ -693,7 +721,7 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 		ext4_io_end_t *io_end = ext4_inode_aio(inode);
 
 		map_bh(bh, inode->i_sb, map.m_pblk);
-		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+		ext4_update_bh_state(bh, map.m_flags);
 		if (IS_DAX(inode) && buffer_unwritten(bh)) {
 			/*
 			 * dgc: I suspect unwritten conversion on ext4+DAX is
@@ -1669,7 +1697,7 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 		return ret;
 
 	map_bh(bh, inode->i_sb, map.m_pblk);
-	bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+	ext4_update_bh_state(bh, map.m_flags);
 
 	if (buffer_unwritten(bh)) {
 		/* A delayed write to unwritten bh should be marked
-- 
2.5.0