block: inline fast path of driver tag allocation

If we don't use an IO scheduler or have shared tags, then we don't need
to call into this external function at all. This saves ~2% for such
a setup.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-mq.c

@@ -1324,7 +1324,7 @@ struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
 	return data.rq;
 }
 
-static bool __blk_mq_get_driver_tag(struct request *rq)
+static bool __blk_mq_alloc_driver_tag(struct request *rq)
 {
 	struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags;
 	unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags;
@@ -1348,11 +1348,9 @@ static bool __blk_mq_get_driver_tag(struct request *rq)
 	return true;
 }
 
-bool blk_mq_get_driver_tag(struct request *rq)
+bool __blk_mq_get_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq)
 {
-	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
-
-	if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq))
+	if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_alloc_driver_tag(rq))
 		return false;
 
 	if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&

block/blk-mq.h

@@ -258,7 +258,20 @@ static inline void blk_mq_put_driver_tag(struct request *rq)
 	__blk_mq_put_driver_tag(rq->mq_hctx, rq);
 }
 
-bool blk_mq_get_driver_tag(struct request *rq);
+bool __blk_mq_get_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq);
+
+static inline bool blk_mq_get_driver_tag(struct request *rq)
+{
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+	if (rq->tag != BLK_MQ_NO_TAG &&
+	    !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
+		hctx->tags->rqs[rq->tag] = rq;
+		return true;
+	}
+
+	return __blk_mq_get_driver_tag(hctx, rq);
+}
 
 static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap)
 {