diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 9381171c2fc0..c72bce2f0cf1 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1666,10 +1666,11 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 		blk_mq_start_request(req);
 	}
 
+	cmd->flags &= SCMD_PRESERVED_FLAGS;
 	if (sdev->simple_tags)
 		cmd->flags |= SCMD_TAGGED;
-	else
-		cmd->flags &= ~SCMD_TAGGED;
+	if (bd->last)
+		cmd->flags |= SCMD_LAST;
 
 	scsi_init_cmd_errh(cmd);
 	cmd->scsi_done = scsi_mq_done;
@@ -1807,10 +1808,37 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(__scsi_init_queue);
 
+static const struct blk_mq_ops scsi_mq_ops_no_commit = {
+	.get_budget	= scsi_mq_get_budget,
+	.put_budget	= scsi_mq_put_budget,
+	.queue_rq	= scsi_queue_rq,
+	.complete	= scsi_softirq_done,
+	.timeout	= scsi_timeout,
+#ifdef CONFIG_BLK_DEBUG_FS
+	.show_rq	= scsi_show_rq,
+#endif
+	.init_request	= scsi_mq_init_request,
+	.exit_request	= scsi_mq_exit_request,
+	.initialize_rq_fn = scsi_initialize_rq,
+	.busy		= scsi_mq_lld_busy,
+	.map_queues	= scsi_map_queues,
+};
+
+
+static void scsi_commit_rqs(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+	struct scsi_device *sdev = q->queuedata;
+	struct Scsi_Host *shost = sdev->host;
+
+	shost->hostt->commit_rqs(shost, hctx->queue_num);
+}
+
 static const struct blk_mq_ops scsi_mq_ops = {
 	.get_budget	= scsi_mq_get_budget,
 	.put_budget	= scsi_mq_put_budget,
 	.queue_rq	= scsi_queue_rq,
+	.commit_rqs	= scsi_commit_rqs,
 	.complete	= scsi_softirq_done,
 	.timeout	= scsi_timeout,
 #ifdef CONFIG_BLK_DEBUG_FS
@@ -1846,7 +1874,10 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
 			sizeof(struct scatterlist) * SCSI_INLINE_PROT_SG_CNT;
 
 	memset(&shost->tag_set, 0, sizeof(shost->tag_set));
-	shost->tag_set.ops = &scsi_mq_ops;
+	if (shost->hostt->commit_rqs)
+		shost->tag_set.ops = &scsi_mq_ops;
+	else
+		shost->tag_set.ops = &scsi_mq_ops_no_commit;
 	shost->tag_set.nr_hw_queues = shost->nr_hw_queues ? : 1;
 	shost->tag_set.queue_depth = shost->can_queue;
 	shost->tag_set.cmd_size = cmd_size;
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 76ed5e4acd38..91bd749a02f7 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -57,6 +57,7 @@ struct scsi_pointer {
 #define SCMD_TAGGED		(1 << 0)
 #define SCMD_UNCHECKED_ISA_DMA	(1 << 1)
 #define SCMD_INITIALIZED	(1 << 2)
+#define SCMD_LAST		(1 << 3)
 /* flags preserved across unprep / reprep */
 #define SCMD_PRESERVED_FLAGS	(SCMD_UNCHECKED_ISA_DMA | SCMD_INITIALIZED)
 
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index cc139dbd71e5..31e0d6ca1eba 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -80,8 +80,10 @@ struct scsi_host_template {
 	 * command block to the LLDD.  When the driver finished
 	 * processing the command the done callback is invoked.
 	 *
-	 * If queuecommand returns 0, then the HBA has accepted the
-	 * command.  The done() function must be called on the command
+	 * If queuecommand returns 0, then the driver has accepted the
+	 * command.  It must also push it to the HBA if the scsi_cmnd
+	 * flag SCMD_LAST is set, or if the driver does not implement
+	 * commit_rqs.  The done() function must be called on the command
 	 * when the driver has finished with it. (you may call done on the
 	 * command before queuecommand returns, but in this case you
 	 * *must* return 0 from queuecommand).
@@ -109,6 +111,16 @@ struct scsi_host_template {
 	 */
 	int (* queuecommand)(struct Scsi_Host *, struct scsi_cmnd *);
 
+	/*
+	 * The commit_rqs function is used to trigger a hardware
+	 * doorbell after some requests have been queued with
+	 * queuecommand, when an error is encountered before sending
+	 * the request with SCMD_LAST set.
+	 *
+	 * STATUS: OPTIONAL
+	 */
+	void (*commit_rqs)(struct Scsi_Host *, u16);
+
 	/*
 	 * This is an error handling strategy routine.  You don't need to
 	 * define one of these if you don't want to - there is a default