blk-mq: fix start_time_ns and alloc_time_ns for pre-allocated rq

The iocost rely on rq start_time_ns and alloc_time_ns to tell saturation
state of the block device. Most of the time request is allocated after
rq_qos_throttle() and its alloc_time_ns or start_time_ns won't be affected.

But for plug batched allocation introduced by the commit 47c122e35d7e
("block: pre-allocate requests if plug is started and is a batch"), we can
rq_qos_throttle() after the allocation of the request. This is what the
blk_mq_get_cached_request() does.

In this case, the cached request alloc_time_ns or start_time_ns is much
ahead if blocked in any qos ->throttle().

Fix it by setting alloc_time_ns and start_time_ns to now when the allocated
request is actually used.

Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20230710105516.2053478-1-chengming.zhou@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 30 insertions, 17 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5504719b970d..d50b1d62a3d9 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -328,8 +328,24 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL(blk_rq_init);
 
+/* Set start and alloc time when the allocated request is actually used */
+static inline void blk_mq_rq_time_init(struct request *rq, u64 alloc_time_ns)
+{
+	if (blk_mq_need_time_stamp(rq))
+		rq->start_time_ns = ktime_get_ns();
+	else
+		rq->start_time_ns = 0;
+
+#ifdef CONFIG_BLK_RQ_ALLOC_TIME
+	if (blk_queue_rq_alloc_time(rq->q))
+		rq->alloc_time_ns = alloc_time_ns ?: rq->start_time_ns;
+	else
+		rq->alloc_time_ns = 0;
+#endif
+}
+
 static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
-		struct blk_mq_tags *tags, unsigned int tag, u64 alloc_time_ns)
+		struct blk_mq_tags *tags, unsigned int tag)
 {
 	struct blk_mq_ctx *ctx = data->ctx;
 	struct blk_mq_hw_ctx *hctx = data->hctx;
@@ -356,14 +372,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	}
 	rq->timeout = 0;
 
-	if (blk_mq_need_time_stamp(rq))
-		rq->start_time_ns = ktime_get_ns();
-	else
-		rq->start_time_ns = 0;
 	rq->part = NULL;
-#ifdef CONFIG_BLK_RQ_ALLOC_TIME
-	rq->alloc_time_ns = alloc_time_ns;
-#endif
 	rq->io_start_time_ns = 0;
 	rq->stats_sectors = 0;
 	rq->nr_phys_segments = 0;
@@ -393,8 +402,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 }
 
 static inline struct request *
-__blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data,
-		u64 alloc_time_ns)
+__blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data)
 {
 	unsigned int tag, tag_offset;
 	struct blk_mq_tags *tags;
@@ -413,7 +421,7 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data,
 		tag = tag_offset + i;
 		prefetch(tags->static_rqs[tag]);
 		tag_mask &= ~(1UL << i);
-		rq = blk_mq_rq_ctx_init(data, tags, tag, alloc_time_ns);
+		rq = blk_mq_rq_ctx_init(data, tags, tag);
 		rq_list_add(data->cached_rq, rq);
 		nr++;
 	}
@@ -474,9 +482,11 @@ retry:
 	 * Try batched alloc if we want more than 1 tag.
 	 */
 	if (data->nr_tags > 1) {
-		rq = __blk_mq_alloc_requests_batch(data, alloc_time_ns);
-		if (rq)
+		rq = __blk_mq_alloc_requests_batch(data);
+		if (rq) {
+			blk_mq_rq_time_init(rq, alloc_time_ns);
 			return rq;
+		}
 		data->nr_tags = 1;
 	}
 
@@ -499,8 +509,9 @@ retry:
 		goto retry;
 	}
 
-	return blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag,
-					alloc_time_ns);
+	rq = blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag);
+	blk_mq_rq_time_init(rq, alloc_time_ns);
+	return rq;
 }
 
 static struct request *blk_mq_rq_cache_fill(struct request_queue *q,
@@ -555,6 +566,7 @@ static struct request *blk_mq_alloc_cached_request(struct request_queue *q,
 			return NULL;
 
 		plug->cached_rq = rq_list_next(rq);
+		blk_mq_rq_time_init(rq, 0);
 	}
 
 	rq->cmd_flags = opf;
@@ -656,8 +668,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	tag = blk_mq_get_tag(&data);
 	if (tag == BLK_MQ_NO_TAG)
 		goto out_queue_exit;
-	rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag,
-					alloc_time_ns);
+	rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag);
+	blk_mq_rq_time_init(rq, alloc_time_ns);
 	rq->__data_len = 0;
 	rq->__sector = (sector_t) -1;
 	rq->bio = rq->biotail = NULL;
@@ -2896,6 +2908,7 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
 	plug->cached_rq = rq_list_next(rq);
 	rq_qos_throttle(q, *bio);
 
+	blk_mq_rq_time_init(rq, 0);
 	rq->cmd_flags = (*bio)->bi_opf;
 	INIT_LIST_HEAD(&rq->queuelist);
 	return rq;