From 51e9ac77035a3dfcb6fc0a88a0d80b6f99b5edb1 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Sat, 7 Aug 2010 21:17:00 +1000 Subject: [PATCH] md/raid10: fix deadlock with unaligned read during resync If the 'bio_split' path in raid10-read is used while resync/recovery is happening it is possible to deadlock. Fix this be elevating ->nr_waiting for the duration of both parts of the split request. This fixes a bug that has been present since 2.6.22 but has only started manifesting recently for unknown reasons. It is suitable for and -stable since then. Reported-by: Justin Bronder Tested-by: Justin Bronder Signed-off-by: NeilBrown Cc: stable@kernel.org --- drivers/md/raid10.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 42e64e4e5e25..d1d689126346 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -825,11 +825,29 @@ static int make_request(mddev_t *mddev, struct bio * bio) */ bp = bio_split(bio, chunk_sects - (bio->bi_sector & (chunk_sects - 1)) ); + + /* Each of these 'make_request' calls will call 'wait_barrier'. + * If the first succeeds but the second blocks due to the resync + * thread raising the barrier, we will deadlock because the + * IO to the underlying device will be queued in generic_make_request + * and will never complete, so will never reduce nr_pending. + * So increment nr_waiting here so no new raise_barriers will + * succeed, and so the second wait_barrier cannot block. + */ + spin_lock_irq(&conf->resync_lock); + conf->nr_waiting++; + spin_unlock_irq(&conf->resync_lock); + if (make_request(mddev, &bp->bio1)) generic_make_request(&bp->bio1); if (make_request(mddev, &bp->bio2)) generic_make_request(&bp->bio2); + spin_lock_irq(&conf->resync_lock); + conf->nr_waiting--; + wake_up(&conf->wait_barrier); + spin_unlock_irq(&conf->resync_lock); + bio_pair_release(bp); return 0; bad_map: