diff --git a/block/blk-mq.c b/block/blk-mq.c
index 32b4797f418629dfe226c5644479a38704f776af..141f2e06803a249b9ad3ec53f4e8eff7890c5089 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -384,7 +384,7 @@ void blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
-static void blk_mq_start_request(struct request *rq)
+void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
@@ -422,16 +422,18 @@ static void blk_mq_start_request(struct request *rq)
 		rq->nr_phys_segments++;
 	}
 }
+EXPORT_SYMBOL(blk_mq_start_request);
 
 static void __blk_mq_requeue_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
 	trace_block_rq_requeue(q, rq);
-	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
 
-	if (q->dma_drain_size && blk_rq_bytes(rq))
-		rq->nr_phys_segments--;
+	if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
+		if (q->dma_drain_size && blk_rq_bytes(rq))
+			rq->nr_phys_segments--;
+	}
 }
 
 void blk_mq_requeue_request(struct request *rq)
@@ -743,8 +745,6 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 		rq = list_first_entry(&rq_list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 
-		blk_mq_start_request(rq);
-
 		ret = q->mq_ops->queue_rq(hctx, rq, list_empty(&rq_list));
 		switch (ret) {
 		case BLK_MQ_RQ_QUEUE_OK:
@@ -1186,7 +1186,6 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		int ret;
 
 		blk_mq_bio_to_request(rq, bio);
-		blk_mq_start_request(rq);
 
 		/*
 		 * For OK queue, we are done. For error, kill it. Any other
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 0e2084f37c6724a076b3c9e57b060b274c5b873c..4042440a0470df298c2de3d075c6a5b561385e24 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3783,6 +3783,8 @@ static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	if (unlikely(mtip_check_unal_depth(hctx, rq)))
 		return BLK_MQ_RQ_QUEUE_BUSY;
 
+	blk_mq_start_request(rq);
+
 	ret = mtip_submit_request(hctx, rq);
 	if (likely(!ret))
 		return BLK_MQ_RQ_QUEUE_OK;
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index c5b7315c2c13bca8e824d5b845bbb068a3fc345d..332ce20d45da1c2753d965dae379f951322cfc33 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -321,6 +321,8 @@ static int null_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	cmd->rq = rq;
 	cmd->nq = hctx->driver_data;
 
+	blk_mq_start_request(rq);
+
 	null_handle_cmd(cmd);
 	return BLK_MQ_RQ_QUEUE_OK;
 }
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 13756e01679740567d0cf6087be3aa30468a2a99..83816bf6882f7d279b3eabbf47992f5781143003 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -205,6 +205,8 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
 		}
 	}
 
+	blk_mq_start_request(req);
+
 	num = blk_rq_map_sg(hctx->queue, vbr->req, vbr->sg);
 	if (num) {
 		if (rq_data_dir(vbr->req) == WRITE)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index f1df411683916a2cf1b641c0440515e5c762a148..2dcd9078de48921d62542412789eeb279a5a36ea 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1890,6 +1890,7 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
 	scsi_init_cmd_errh(cmd);
 	cmd->scsi_done = scsi_mq_done;
 
+	blk_mq_start_request(req);
 	reason = scsi_dispatch_cmd(cmd);
 	if (reason) {
 		scsi_set_blocked(cmd, reason);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 9c4e306a9217e9f6b6ae4194d11a97bbf7c7771c..878b6f71da4804c6173b4e8fd0d9d249ae355608 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -159,6 +159,7 @@ struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
 struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
 struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int);
 
+void blk_mq_start_request(struct request *rq);
 void blk_mq_end_io(struct request *rq, int error);
 void __blk_mq_end_io(struct request *rq, int error);