diff --git a/block/blk-mq.c b/block/blk-mq.c
index 862f458d4760..cdc629cf075b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -171,9 +171,12 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
 }
 EXPORT_SYMBOL(blk_mq_can_queue);
 
-static void blk_mq_rq_ctx_init(struct blk_mq_ctx *ctx, struct request *rq,
-			       unsigned int rw_flags)
+static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
+			       struct request *rq, unsigned int rw_flags)
 {
+	if (blk_queue_io_stat(q))
+		rw_flags |= REQ_IO_STAT;
+
 	rq->mq_ctx = ctx;
 	rq->cmd_flags = rw_flags;
 	ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
@@ -197,7 +200,7 @@ static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
 
 		rq = __blk_mq_alloc_request(hctx, gfp & ~__GFP_WAIT, reserved);
 		if (rq) {
-			blk_mq_rq_ctx_init(ctx, rq, rw);
+			blk_mq_rq_ctx_init(q, ctx, rq, rw);
 			break;
 		} else if (!(gfp & __GFP_WAIT))
 			break;
@@ -718,6 +721,8 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 
+	trace_block_rq_insert(hctx->queue, rq);
+
 	list_add_tail(&rq->queuelist, &ctx->rq_list);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 
@@ -921,7 +926,7 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	trace_block_getrq(q, bio, rw);
 	rq = __blk_mq_alloc_request(hctx, GFP_ATOMIC, false);
 	if (likely(rq))
-		blk_mq_rq_ctx_init(ctx, rq, rw);
+		blk_mq_rq_ctx_init(q, ctx, rq, rw);
 	else {
 		blk_mq_put_ctx(ctx);
 		trace_block_sleeprq(q, bio, rw);
@@ -1377,6 +1382,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg,
 	q->queue_hw_ctx = hctxs;
 
 	q->mq_ops = reg->ops;
+	q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
 
 	blk_queue_make_request(q, blk_mq_make_request);
 	blk_queue_rq_timed_out(q, reg->ops->timeout);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 588479d58f52..6a680d4de7f1 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -199,15 +199,16 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
 
 	spin_lock_irqsave(&vblk->vq_lock, flags);
 	if (__virtblk_add_req(vblk->vq, vbr, vbr->sg, num) < 0) {
+		virtqueue_kick(vblk->vq);
 		spin_unlock_irqrestore(&vblk->vq_lock, flags);
 		blk_mq_stop_hw_queue(hctx);
-		virtqueue_kick(vblk->vq);
 		return BLK_MQ_RQ_QUEUE_BUSY;
 	}
-	spin_unlock_irqrestore(&vblk->vq_lock, flags);
 
 	if (last)
 		virtqueue_kick(vblk->vq);
+
+	spin_unlock_irqrestore(&vblk->vq_lock, flags);
 	return BLK_MQ_RQ_QUEUE_OK;
 }
 
diff --git a/fs/bio.c b/fs/bio.c
index 2bdb4e25ee77..33d79a4eb92d 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -601,7 +601,7 @@ EXPORT_SYMBOL(bio_get_nr_vecs);
 
 static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 			  *page, unsigned int len, unsigned int offset,
-			  unsigned short max_sectors)
+			  unsigned int max_sectors)
 {
 	int retried_segments = 0;
 	struct bio_vec *bvec;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index f26ec20f6354..1b135d49b279 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -505,6 +505,9 @@ struct request_queue {
 				 (1 << QUEUE_FLAG_SAME_COMP)	|	\
 				 (1 << QUEUE_FLAG_ADD_RANDOM))
 
+#define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
+				 (1 << QUEUE_FLAG_SAME_COMP))
+
 static inline void queue_lockdep_assert_held(struct request_queue *q)
 {
 	if (q->queue_lock)