diff --git a/block/bsg.c b/block/bsg.c
index 0ce8806dd0c1a3786b6cd86ba8a90b743ca81b8d..0f63b91d0af6823a67ea3e08598518b474083a48 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -353,6 +353,8 @@ static void bsg_rq_end_io(struct request *rq, int uptodate)
 static void bsg_add_command(struct bsg_device *bd, struct request_queue *q,
 			    struct bsg_command *bc, struct request *rq)
 {
+	int at_head = (0 == (bc->hdr.flags & BSG_FLAG_Q_AT_TAIL));
+
 	/*
 	 * add bc command to busy queue and submit rq for io
 	 */
@@ -368,7 +370,7 @@ static void bsg_add_command(struct bsg_device *bd, struct request_queue *q,
 	dprintk("%s: queueing rq %p, bc %p\n", bd->name, rq, bc);
 
 	rq->end_io_data = bc;
-	blk_execute_rq_nowait(q, NULL, rq, 1, bsg_rq_end_io);
+	blk_execute_rq_nowait(q, NULL, rq, at_head, bsg_rq_end_io);
 }
 
 static struct bsg_command *bsg_next_done_cmd(struct bsg_device *bd)
@@ -924,6 +926,7 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		struct request *rq;
 		struct bio *bio, *bidi_bio = NULL;
 		struct sg_io_v4 hdr;
+		int at_head;
 		u8 sense[SCSI_SENSE_BUFFERSIZE];
 
 		if (copy_from_user(&hdr, uarg, sizeof(hdr)))
@@ -936,7 +939,9 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		bio = rq->bio;
 		if (rq->next_rq)
 			bidi_bio = rq->next_rq->bio;
-		blk_execute_rq(bd->queue, NULL, rq, 0);
+
+		at_head = (0 == (hdr.flags & BSG_FLAG_Q_AT_TAIL));
+		blk_execute_rq(bd->queue, NULL, rq, at_head);
 		ret = blk_complete_sgv4_hdr_rq(rq, &hdr, bio, bidi_bio);
 
 		if (copy_to_user(uarg, &hdr, sizeof(hdr)))
diff --git a/include/linux/bsg.h b/include/linux/bsg.h
index cf0303a6061195de840a22d97ff24a7b41d4d49e..3f0c64ace4247eae6a13fe80f0e92cc298e51d4c 100644
--- a/include/linux/bsg.h
+++ b/include/linux/bsg.h
@@ -7,6 +7,14 @@
 #define BSG_SUB_PROTOCOL_SCSI_TMF	1
 #define BSG_SUB_PROTOCOL_SCSI_TRANSPORT	2
 
+/*
+ * For flags member below
+ * sg.h sg_io_hdr also has bits defined for it's flags member. However
+ * none of these bits are implemented/used by bsg. The bits below are
+ * allocated to not conflict with sg.h ones anyway.
+ */
+#define BSG_FLAG_Q_AT_TAIL 0x10 /* default, == 0 at this bit, is Q_AT_HEAD */
+
 struct sg_io_v4 {
 	__s32 guard;		/* [i] 'Q' to differentiate from v3 */
 	__u32 protocol;		/* [i] 0 -> SCSI , .... */