blk-mq: save queue mapping result into ctx directly

Currently, the queue mapping result is saved in a two-dimensional
array. In the hot path, to get a hctx, we need do following:

  q->queue_hw_ctx[q->tag_set->map[type].mq_map[cpu]]

This isn't very efficient. We could save the queue mapping result into
ctx directly with different hctx type, like,

  ctx->hctxs[type]
Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-mq-sched.c

@@ -321,7 +321,7 @@ bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
 {
 	struct elevator_queue *e = q->elevator;
 	struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, bio->bi_opf, ctx->cpu);
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, bio->bi_opf, ctx);
 	bool ret = false;
 	enum hctx_type type;
 

block/blk-mq-tag.c

@@ -170,7 +170,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 
 		data->ctx = blk_mq_get_ctx(data->q);
 		data->hctx = blk_mq_map_queue(data->q, data->cmd_flags,
-						data->ctx->cpu);
+						data->ctx);
 		tags = blk_mq_tags_from_data(data);
 		if (data->flags & BLK_MQ_REQ_RESERVED)
 			bt = &tags->breserved_tags;

block/blk-mq.c

@@ -364,7 +364,7 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 	}
 	if (likely(!data->hctx))
 		data->hctx = blk_mq_map_queue(q, data->cmd_flags,
-						data->ctx->cpu);
+						data->ctx);
 	if (data->cmd_flags & REQ_NOWAIT)
 		data->flags |= BLK_MQ_REQ_NOWAIT;
 
@@ -2435,7 +2435,7 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 				continue;
 
 			hctx = blk_mq_map_queue_type(q, j, i);
-
+			ctx->hctxs[j] = hctx;
 			/*
 			 * If the CPU is already set in the mask, then we've
 			 * mapped this one already. This can happen if

block/blk-mq.h

@@ -23,6 +23,7 @@ struct blk_mq_ctx {
 
 	unsigned int		cpu;
 	unsigned short		index_hw[HCTX_MAX_TYPES];
+	struct blk_mq_hw_ctx 	*hctxs[HCTX_MAX_TYPES];
 
 	/* incremented at dispatch time */
 	unsigned long		rq_dispatched[2];
@@ -97,11 +98,11 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue *
  * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue
  * @q: request queue
  * @flags: request command flags
- * @cpu: CPU
+ * @cpu: cpu ctx
  */
 static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
 						     unsigned int flags,
-						     unsigned int cpu)
+						     struct blk_mq_ctx *ctx)
 {
 	enum hctx_type type = HCTX_TYPE_DEFAULT;
 
@@ -116,7 +117,7 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
 		 q->tag_set->map[HCTX_TYPE_READ].nr_queues)
 		type = HCTX_TYPE_READ;
 	
-	return blk_mq_map_queue_type(q, type, cpu);
+	return ctx->hctxs[type];
 }
 
 /*

block/blk.h

@@ -38,7 +38,7 @@ extern struct ida blk_queue_ida;
 static inline struct blk_flush_queue *
 blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx)
 {
-	return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx->cpu)->fq;
+	return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq;
 }
 
 static inline void __blk_get_queue(struct request_queue *q)