On Mar 3, 2020, at 1:14 PM, Vitaly Mayatskikh [off-list ref] wrote:

When disk failure happens and the array has a spare drive, resync thread
kicks in and starts to refill the spare. However it may get blocked by
a retry thread that resubmits failed IO to a mirror and itself can get
blocked on a barrier raised by the resync thread.

Signed-off-by: Vitaly Mayatskikh <redacted>
---
drivers/md/raid10.c | 14 +++++++++++---
1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index ec136e4..f1a8e26 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c

@@ -980,6 +980,7 @@ static void wait_barrier(struct r10conf *conf)

{
	spin_lock_irq(&conf->resync_lock);
	if (conf->barrier) {
+		struct bio_list *bio_list = current->bio_list;
		conf->nr_waiting++;
		/* Wait for the barrier to drop.
		 * However if there are already pending

@@ -994,9 +995,16 @@ static void wait_barrier(struct r10conf *conf)

		wait_event_lock_irq(conf->wait_barrier,
				    !conf->barrier ||
				    (atomic_read(&conf->nr_pending) &&
-				     current->bio_list &&
-				     (!bio_list_empty(&current->bio_list[0]) ||
-				      !bio_list_empty(&current->bio_list[1]))),
+				     bio_list &&
+				     (!bio_list_empty(&bio_list[0]) ||
+				      !bio_list_empty(&bio_list[1]))) ||
+				     /* move on if recovery thread is
+				      * blocked by us
+				      */
+				     (conf->mddev->thread->tsk == current &&
+				      test_bit(MD_RECOVERY_RUNNING,
+					       &conf->mddev->recovery) &&
+				      conf->nr_queued > 0),
				    conf->resync_lock);
		conf->nr_waiting--;
		if (!conf->nr_waiting)
— 
1.8.3.1