diff --git a/block/blk-core.c b/block/blk-core.c
index b830e14117ddd2..4bfd8674afd031 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2129,7 +2129,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	if (q->mq_ops) {
 		if (blk_queue_io_stat(q))
 			blk_account_io_start(rq, true);
-		blk_mq_sched_insert_request(rq, false, true, false);
+		blk_mq_sched_insert_request(rq, false, true, false, false);
 		return 0;
 	}
 
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 86656fdfa6378e..ed1f101652688c 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -66,7 +66,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	 * be reused after dying flag is set
 	 */
 	if (q->mq_ops) {
-		blk_mq_sched_insert_request(rq, at_head, true, false);
+		blk_mq_sched_insert_request(rq, at_head, true, false, false);
 		return;
 	}
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index d7de34ee39c208..4427896641ac74 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -456,7 +456,7 @@ void blk_insert_flush(struct request *rq)
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
 		if (q->mq_ops)
-			blk_mq_sched_insert_request(rq, false, true, false);
+			blk_mq_sched_insert_request(rq, false, true, false, false);
 		else
 			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 4139b07ab33bdc..1112752f888d0a 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -335,6 +335,64 @@ void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx)
 	}
 }
 
+/*
+ * Add flush/fua to the queue. If we fail getting a driver tag, then
+ * punt to the requeue list. Requeue will re-invoke us from a context
+ * that's safe to block from.
+ */
+static void blk_mq_sched_insert_flush(struct blk_mq_hw_ctx *hctx,
+				      struct request *rq, bool can_block)
+{
+	if (blk_mq_get_driver_tag(rq, &hctx, can_block)) {
+		blk_insert_flush(rq);
+		blk_mq_run_hw_queue(hctx, true);
+	} else
+		blk_mq_add_to_requeue_list(rq, true, true);
+}
+
+void blk_mq_sched_insert_request(struct request *rq, bool at_head,
+				 bool run_queue, bool async, bool can_block)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+
+	if (rq->tag == -1 && (rq->cmd_flags & (REQ_PREFLUSH | REQ_FUA))) {
+		blk_mq_sched_insert_flush(hctx, rq, can_block);
+		return;
+	}
+
+	if (e && e->type->ops.mq.insert_requests) {
+		LIST_HEAD(list);
+
+		list_add(&rq->queuelist, &list);
+		e->type->ops.mq.insert_requests(hctx, &list, at_head);
+	} else {
+		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);
+}
+
+void blk_mq_sched_insert_requests(struct request_queue *q,
+				  struct blk_mq_ctx *ctx,
+				  struct list_head *list, bool run_queue_async)
+{
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+	struct elevator_queue *e = hctx->queue->elevator;
+
+	if (e && e->type->ops.mq.insert_requests)
+		e->type->ops.mq.insert_requests(hctx, list, false);
+	else
+		blk_mq_insert_requests(hctx, ctx, list);
+
+	blk_mq_run_hw_queue(hctx, run_queue_async);
+}
+
 static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set,
 				   struct blk_mq_hw_ctx *hctx,
 				   unsigned int hctx_idx)
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index becbc784036436..9478aaeb48c59b 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -21,6 +21,12 @@ bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio);
 bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq);
 void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx);
 
+void blk_mq_sched_insert_request(struct request *rq, bool at_head,
+				 bool run_queue, bool async, bool can_block);
+void blk_mq_sched_insert_requests(struct request_queue *q,
+				  struct blk_mq_ctx *ctx,
+				  struct list_head *list, bool run_queue_async);
+
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
 void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
 			struct list_head *rq_list,
@@ -62,45 +68,6 @@ static inline void blk_mq_sched_put_rq_priv(struct request_queue *q,
 		e->type->ops.mq.put_rq_priv(q, rq);
 }
 
-static inline void
-blk_mq_sched_insert_request(struct request *rq, bool at_head, bool run_queue,
-			    bool async)
-{
-	struct request_queue *q = rq->q;
-	struct elevator_queue *e = q->elevator;
-	struct blk_mq_ctx *ctx = rq->mq_ctx;
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
-
-	if (e && e->type->ops.mq.insert_requests) {
-		LIST_HEAD(list);
-
-		list_add(&rq->queuelist, &list);
-		e->type->ops.mq.insert_requests(hctx, &list, at_head);
-	} else {
-		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);
-}
-
-static inline void
-blk_mq_sched_insert_requests(struct request_queue *q, struct blk_mq_ctx *ctx,
-			     struct list_head *list, bool run_queue_async)
-{
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
-	struct elevator_queue *e = hctx->queue->elevator;
-
-	if (e && e->type->ops.mq.insert_requests)
-		e->type->ops.mq.insert_requests(hctx, list, false);
-	else
-		blk_mq_insert_requests(hctx, ctx, list);
-
-	blk_mq_run_hw_queue(hctx, run_queue_async);
-}
-
 static inline bool
 blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
 			 struct bio *bio)
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index f8de2dbbb29fcb..54c84363c1b238 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -106,6 +106,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 	struct sbq_wait_state *ws;
 	DEFINE_WAIT(wait);
 	unsigned int tag_offset;
+	bool drop_ctx;
 	int tag;
 
 	if (data->flags & BLK_MQ_REQ_RESERVED) {
@@ -128,6 +129,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 		return BLK_MQ_TAG_FAIL;
 
 	ws = bt_wait_ptr(bt, data->hctx);
+	drop_ctx = data->ctx == NULL;
 	do {
 		prepare_to_wait(&ws->wait, &wait, TASK_UNINTERRUPTIBLE);
 
@@ -150,7 +152,8 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 		if (tag != -1)
 			break;
 
-		blk_mq_put_ctx(data->ctx);
+		if (data->ctx)
+			blk_mq_put_ctx(data->ctx);
 
 		io_schedule();
 
@@ -166,6 +169,9 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 		ws = bt_wait_ptr(bt, data->hctx);
 	} while (1);
 
+	if (drop_ctx && data->ctx)
+		blk_mq_put_ctx(data->ctx);
+
 	finish_wait(&ws->wait, &wait);
 
 found_tag:
diff --git a/block/blk-mq.c b/block/blk-mq.c
index da2123dd681e3e..60dac10228fe0f 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -568,13 +568,13 @@ static void blk_mq_requeue_work(struct work_struct *work)
 
 		rq->rq_flags &= ~RQF_SOFTBARRIER;
 		list_del_init(&rq->queuelist);
-		blk_mq_sched_insert_request(rq, true, false, false);
+		blk_mq_sched_insert_request(rq, true, false, false, true);
 	}
 
 	while (!list_empty(&rq_list)) {
 		rq = list_entry(rq_list.next, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		blk_mq_sched_insert_request(rq, false, false, false);
+		blk_mq_sched_insert_request(rq, false, false, false, true);
 	}
 
 	blk_mq_run_hw_queues(q, false);
@@ -847,12 +847,11 @@ static inline unsigned int queued_to_index(unsigned int queued)
 	return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
 }
 
-static bool blk_mq_get_driver_tag(struct request *rq,
-				  struct blk_mq_hw_ctx **hctx, bool wait)
+bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
+			   bool wait)
 {
 	struct blk_mq_alloc_data data = {
 		.q = rq->q,
-		.ctx = rq->mq_ctx,
 		.hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
 		.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
 	};
@@ -1395,7 +1394,7 @@ static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
 	}
 
 insert:
-	blk_mq_sched_insert_request(rq, false, true, true);
+	blk_mq_sched_insert_request(rq, false, true, true, false);
 }
 
 /*
@@ -1446,10 +1445,12 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	cookie = request_to_qc_t(data.hctx, rq);
 
 	if (unlikely(is_flush_fua)) {
+		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
 		blk_mq_get_driver_tag(rq, NULL, true);
 		blk_insert_flush(rq);
-		goto run_queue;
+		blk_mq_run_hw_queue(data.hctx, true);
+		goto done;
 	}
 
 	plug = current->plug;
@@ -1502,7 +1503,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
 		blk_mq_sched_insert_request(rq, false, true,
-						!is_sync || is_flush_fua);
+						!is_sync || is_flush_fua, true);
 		goto done;
 	}
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
@@ -1512,7 +1513,6 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		 * latter allows for merging opportunities and more efficient
 		 * dispatching.
 		 */
-run_queue:
 		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
 	}
 	blk_mq_put_ctx(data.ctx);
@@ -1568,10 +1568,12 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	cookie = request_to_qc_t(data.hctx, rq);
 
 	if (unlikely(is_flush_fua)) {
+		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
 		blk_mq_get_driver_tag(rq, NULL, true);
 		blk_insert_flush(rq);
-		goto run_queue;
+		blk_mq_run_hw_queue(data.hctx, true);
+		goto done;
 	}
 
 	/*
@@ -1612,7 +1614,7 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
 		blk_mq_sched_insert_request(rq, false, true,
-						!is_sync || is_flush_fua);
+						!is_sync || is_flush_fua, true);
 		goto done;
 	}
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
@@ -1622,7 +1624,6 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		 * latter allows for merging opportunities and more efficient
 		 * dispatching.
 		 */
-run_queue:
 		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
 	}
 
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 077a4003f1fd09..57cdbf6c0cee96 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -34,6 +34,8 @@ void blk_mq_wake_waiters(struct request_queue *q);
 bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *, struct list_head *);
 void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
 bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx);
+bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
+				bool wait);
 
 /*
  * Internal helpers for allocating/freeing the request map