From 4db1aef6a2b79aba4f862285c2658348e083f2b7 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 19 Mar 2012 12:46:38 +1100 Subject: md/raid1,raid10: avoid deadlock during resync/recovery. commit d6b42dcb995e6acd7cc276774e751ffc9f0ef4bf upstream. If RAID1 or RAID10 is used under LVM or some other stacking block device, it is possible to enter a deadlock during resync or recovery. This can happen if the upper level block device creates two requests to the RAID1 or RAID10. The first request gets processed, blocks recovery and queue requests for underlying requests in current->bio_list. A resync request then starts which will wait for those requests and block new IO. But then the second request to the RAID1/10 will be attempted and it cannot progress until the resync request completes, which cannot progress until the underlying device requests complete, which are on a queue behind that second request. So allow that second request to proceed even though there is a resync request about to start. This is suitable for any -stable kernel. Reported-by: Ray Morris Tested-by: Ray Morris Signed-off-by: NeilBrown Signed-off-by: Greg Kroah-Hartman --- drivers/md/raid1.c | 17 +++++++++++++++-- drivers/md/raid10.c | 17 +++++++++++++++-- 2 files changed, 30 insertions(+), 4 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 3a9e59f..36f1ed3 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -614,9 +614,22 @@ static void wait_barrier(conf_t *conf) spin_lock_irq(&conf->resync_lock); if (conf->barrier) { conf->nr_waiting++; - wait_event_lock_irq(conf->wait_barrier, !conf->barrier, + /* Wait for the barrier to drop. + * However if there are already pending + * requests (preventing the barrier from + * rising completely), and the + * pre-process bio queue isn't empty, + * then don't wait, as we need to empty + * that queue to get the nr_pending + * count down. + */ + wait_event_lock_irq(conf->wait_barrier, + !conf->barrier || + (conf->nr_pending && + current->bio_list && + !bio_list_empty(current->bio_list)), conf->resync_lock, - ); + ); conf->nr_waiting--; } conf->nr_pending++; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 17cb6ab..0d6c42f 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -667,9 +667,22 @@ static void wait_barrier(conf_t *conf) spin_lock_irq(&conf->resync_lock); if (conf->barrier) { conf->nr_waiting++; - wait_event_lock_irq(conf->wait_barrier, !conf->barrier, + /* Wait for the barrier to drop. + * However if there are already pending + * requests (preventing the barrier from + * rising completely), and the + * pre-process bio queue isn't empty, + * then don't wait, as we need to empty + * that queue to get the nr_pending + * count down. + */ + wait_event_lock_irq(conf->wait_barrier, + !conf->barrier || + (conf->nr_pending && + current->bio_list && + !bio_list_empty(current->bio_list)), conf->resync_lock, - ); + ); conf->nr_waiting--; } conf->nr_pending++; -- cgit v1.1