diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index c4513b23f57a6..dd56d7460cb91 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -29,26 +29,25 @@
 #include <scsi/scsi_cmnd.h>
 
 /**
- * bsg_destroy_job - routine to teardown/delete a bsg job
+ * bsg_teardown_job - routine to teardown a bsg job
  * @job: bsg_job that is to be torn down
  */
-static void bsg_destroy_job(struct kref *kref)
+static void bsg_teardown_job(struct kref *kref)
 {
 	struct bsg_job *job = container_of(kref, struct bsg_job, kref);
 	struct request *rq = job->req;
 
-	blk_end_request_all(rq, BLK_STS_OK);
-
 	put_device(job->dev);	/* release reference for the request */
 
 	kfree(job->request_payload.sg_list);
 	kfree(job->reply_payload.sg_list);
-	kfree(job);
+
+	blk_end_request_all(rq, BLK_STS_OK);
 }
 
 void bsg_job_put(struct bsg_job *job)
 {
-	kref_put(&job->kref, bsg_destroy_job);
+	kref_put(&job->kref, bsg_teardown_job);
 }
 EXPORT_SYMBOL_GPL(bsg_job_put);
 
@@ -100,7 +99,7 @@ EXPORT_SYMBOL_GPL(bsg_job_done);
  */
 static void bsg_softirq_done(struct request *rq)
 {
-	struct bsg_job *job = rq->special;
+	struct bsg_job *job = blk_mq_rq_to_pdu(rq);
 
 	bsg_job_put(job);
 }
@@ -122,33 +121,20 @@ static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req)
 }
 
 /**
- * bsg_create_job - create the bsg_job structure for the bsg request
+ * bsg_prepare_job - create the bsg_job structure for the bsg request
  * @dev: device that is being sent the bsg request
  * @req: BSG request that needs a job structure
  */
-static int bsg_create_job(struct device *dev, struct request *req)
+static int bsg_prepare_job(struct device *dev, struct request *req)
 {
 	struct request *rsp = req->next_rq;
-	struct request_queue *q = req->q;
 	struct scsi_request *rq = scsi_req(req);
-	struct bsg_job *job;
+	struct bsg_job *job = blk_mq_rq_to_pdu(req);
 	int ret;
 
-	BUG_ON(req->special);
-
-	job = kzalloc(sizeof(struct bsg_job) + q->bsg_job_size, GFP_KERNEL);
-	if (!job)
-		return -ENOMEM;
-
-	req->special = job;
-	job->req = req;
-	if (q->bsg_job_size)
-		job->dd_data = (void *)&job[1];
 	job->request = rq->cmd;
 	job->request_len = rq->cmd_len;
-	job->reply = rq->sense;
-	job->reply_len = SCSI_SENSE_BUFFERSIZE;	/* Size of sense buffer
-						 * allocated */
+
 	if (req->bio) {
 		ret = bsg_map_buffer(&job->request_payload, req);
 		if (ret)
@@ -187,7 +173,6 @@ static void bsg_request_fn(struct request_queue *q)
 {
 	struct device *dev = q->queuedata;
 	struct request *req;
-	struct bsg_job *job;
 	int ret;
 
 	if (!get_device(dev))
@@ -199,7 +184,7 @@ static void bsg_request_fn(struct request_queue *q)
 			break;
 		spin_unlock_irq(q->queue_lock);
 
-		ret = bsg_create_job(dev, req);
+		ret = bsg_prepare_job(dev, req);
 		if (ret) {
 			scsi_req(req)->result = ret;
 			blk_end_request_all(req, BLK_STS_OK);
@@ -207,8 +192,7 @@ static void bsg_request_fn(struct request_queue *q)
 			continue;
 		}
 
-		job = req->special;
-		ret = q->bsg_job_fn(job);
+		ret = q->bsg_job_fn(blk_mq_rq_to_pdu(req));
 		spin_lock_irq(q->queue_lock);
 		if (ret)
 			break;
@@ -219,6 +203,35 @@ static void bsg_request_fn(struct request_queue *q)
 	spin_lock_irq(q->queue_lock);
 }
 
+static int bsg_init_rq(struct request_queue *q, struct request *req, gfp_t gfp)
+{
+	struct bsg_job *job = blk_mq_rq_to_pdu(req);
+	struct scsi_request *sreq = &job->sreq;
+
+	memset(job, 0, sizeof(*job));
+
+	scsi_req_init(sreq);
+	sreq->sense_len = SCSI_SENSE_BUFFERSIZE;
+	sreq->sense = kzalloc(sreq->sense_len, gfp);
+	if (!sreq->sense)
+		return -ENOMEM;
+
+	job->req = req;
+	job->reply = sreq->sense;
+	job->reply_len = sreq->sense_len;
+	job->dd_data = job + 1;
+
+	return 0;
+}
+
+static void bsg_exit_rq(struct request_queue *q, struct request *req)
+{
+	struct bsg_job *job = blk_mq_rq_to_pdu(req);
+	struct scsi_request *sreq = &job->sreq;
+
+	kfree(sreq->sense);
+}
+
 /**
  * bsg_setup_queue - Create and add the bsg hooks so we can receive requests
  * @dev: device to attach bsg device to
@@ -235,7 +248,9 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name,
 	q = blk_alloc_queue(GFP_KERNEL);
 	if (!q)
 		return ERR_PTR(-ENOMEM);
-	q->cmd_size = sizeof(struct scsi_request);
+	q->cmd_size = sizeof(struct bsg_job) + dd_job_size;
+	q->init_rq_fn = bsg_init_rq;
+	q->exit_rq_fn = bsg_exit_rq;
 	q->request_fn = bsg_request_fn;
 
 	ret = blk_init_allocated_queue(q);
@@ -243,7 +258,6 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name,
 		goto out_cleanup_queue;
 
 	q->queuedata = dev;
-	q->bsg_job_size = dd_job_size;
 	q->bsg_job_fn = job_fn;
 	queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q);
 	queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, q);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 25f6a0cb27d3e..2a5d52fa90f5d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -568,7 +568,6 @@ struct request_queue {
 
 #if defined(CONFIG_BLK_DEV_BSG)
 	bsg_job_fn		*bsg_job_fn;
-	int			bsg_job_size;
 	struct bsg_class_device bsg_dev;
 #endif
 
diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h
index e34dde2da0ef5..637a20cfb237d 100644
--- a/include/linux/bsg-lib.h
+++ b/include/linux/bsg-lib.h
@@ -24,6 +24,7 @@
 #define _BLK_BSG_
 
 #include <linux/blkdev.h>
+#include <scsi/scsi_request.h>
 
 struct request;
 struct device;
@@ -37,6 +38,7 @@ struct bsg_buffer {
 };
 
 struct bsg_job {
+	struct scsi_request sreq;
 	struct device *dev;
 	struct request *req;