dm rq: fix the starting and stopping of blk-mq queues

Improve dm_stop_queue() to cancel any requeue_work.  Also, have
dm_start_queue() and dm_stop_queue() clear/set the QUEUE_FLAG_STOPPED
for the blk-mq request_queue.

On suspend dm_stop_queue() handles stopping the blk-mq request_queue
BUT: even though the hw_queues are marked BLK_MQ_S_STOPPED at that point
there is still a race that is allowing block/blk-mq.c to call ->queue_rq
against a hctx that it really shouldn't.  Add a check to
dm_mq_queue_rq() that guards against this rarity (albeit _not_
race-free).

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # must patch dm.c on < 4.8 kernels

1 files changed, 19 insertions, 1 deletions

diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 7a9661868496..1ca7463e8bb2 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -78,6 +78,7 @@ void dm_start_queue(struct request_queue *q)
         if (!q->mq_ops)
                 dm_old_start_queue(q);
         else {
+                queue_flag_clear_unlocked(QUEUE_FLAG_STOPPED, q);
                 blk_mq_start_stopped_hw_queues(q, true);
                 blk_mq_kick_requeue_list(q);
         }
@@ -101,8 +102,14 @@ void dm_stop_queue(struct request_queue *q)
 {
         if (!q->mq_ops)
                 dm_old_stop_queue(q);
-        else
+        else {
+                spin_lock_irq(q->queue_lock);
+                queue_flag_set(QUEUE_FLAG_STOPPED, q);
+                spin_unlock_irq(q->queue_lock);
+
+                blk_mq_cancel_requeue_work(q);
                 blk_mq_stop_hw_queues(q);
+        }
 }
 
 static struct dm_rq_target_io *alloc_old_rq_tio(struct mapped_device *md,
@@ -864,6 +871,17 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
                 dm_put_live_table(md, srcu_idx);
         }
 
+        /*
+         * On suspend dm_stop_queue() handles stopping the blk-mq
+         * request_queue BUT: even though the hw_queues are marked
+         * BLK_MQ_S_STOPPED at that point there is still a race that
+         * is allowing block/blk-mq.c to call ->queue_rq against a
+         * hctx that it really shouldn't.  The following check guards
+         * against this rarity (albeit _not_ race-free).
+         */
+        if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
+                return BLK_MQ_RQ_QUEUE_BUSY;
+
         if (ti->type->busy && ti->type->busy(ti))
                 return BLK_MQ_RQ_QUEUE_BUSY;