diff --git a/block/blk-exec.c b/block/blk-exec.c
index f4d27b12c90b2778182cc3c0cf5a6cd09e2b0310..9924725fa50dcac5563d2654a24df0d85cfada7a 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -56,6 +56,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	bool is_pm_resume;
 
 	WARN_ON(irqs_disabled());
+	WARN_ON(rq->cmd_type == REQ_TYPE_FS);
 
 	rq->rq_disk = bd_disk;
 	rq->end_io = done;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 383ea0cb1f0a295463789d956aae820b334f4a55..c88e6089746d82267c61d572baa25fe855704f22 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -203,7 +203,6 @@ __blk_mq_alloc_request(struct blk_mq_alloc_data *data, int rw)
 	if (tag != BLK_MQ_TAG_FAIL) {
 		rq = data->hctx->tags->rqs[tag];
 
-		rq->cmd_flags = 0;
 		if (blk_mq_tag_busy(data->hctx)) {
 			rq->cmd_flags = REQ_MQ_INFLIGHT;
 			atomic_inc(&data->hctx->nr_active);
@@ -258,6 +257,7 @@ static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
 
 	if (rq->cmd_flags & REQ_MQ_INFLIGHT)
 		atomic_dec(&hctx->nr_active);
+	rq->cmd_flags = 0;
 
 	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
 	blk_mq_put_tag(hctx, tag, &ctx->last_tag);
@@ -392,6 +392,12 @@ static void blk_mq_start_request(struct request *rq, bool last)
 
 	blk_add_timer(rq);
 
+	/*
+	 * Ensure that ->deadline is visible before set the started
+	 * flag and clear the completed flag.
+	 */
+	smp_mb__before_atomic();
+
 	/*
 	 * Mark us as started and clear complete. Complete might have been
 	 * set if requeue raced with timeout, which then marked it as
@@ -473,7 +479,11 @@ static void blk_mq_requeue_work(struct work_struct *work)
 		blk_mq_insert_request(rq, false, false, false);
 	}
 
-	blk_mq_run_queues(q, false);
+	/*
+	 * Use the start variant of queue running here, so that running
+	 * the requeue work will kick stopped queues.
+	 */
+	blk_mq_start_hw_queues(q);
 }
 
 void blk_mq_add_to_requeue_list(struct request *rq, bool at_head)
@@ -957,14 +967,9 @@ void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
 
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
-	if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA) &&
-	    !(rq->cmd_flags & (REQ_FLUSH_SEQ))) {
-		blk_insert_flush(rq);
-	} else {
-		spin_lock(&ctx->lock);
-		__blk_mq_insert_request(hctx, rq, at_head);
-		spin_unlock(&ctx->lock);
-	}
+	spin_lock(&ctx->lock);
+	__blk_mq_insert_request(hctx, rq, at_head);
+	spin_unlock(&ctx->lock);
 
 	if (run_queue)
 		blk_mq_run_hw_queue(hctx, async);
@@ -1404,6 +1409,8 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 		left -= to_do * rq_size;
 		for (j = 0; j < to_do; j++) {
 			tags->rqs[i] = p;
+			tags->rqs[i]->atomic_flags = 0;
+			tags->rqs[i]->cmd_flags = 0;
 			if (set->ops->init_request) {
 				if (set->ops->init_request(set->driver_data,
 						tags->rqs[i], hctx_idx, i,
@@ -1956,7 +1963,6 @@ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 	while (--i >= 0)
 		blk_mq_free_rq_map(set, set->tags[i], i);
 
-	set->tags = NULL;
 	return -ENOMEM;
 }
 
diff --git a/block/genhd.c b/block/genhd.c
index 09da5e4a8e03bb77e33de4b9822ba26bbff8973f..e6723bd4d7a16963da3367a1d4791c6402e78a82 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -445,8 +445,6 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
  */
 void blk_free_devt(dev_t devt)
 {
-	might_sleep();
-
 	if (devt == MKDEV(0, 0))
 		return;