block: make rq sector size accessible for block stats

Currently rq->data_len will be decreased by partial completion or
zeroed by completion, so when blk_stat_add() is invoked, data_len
will be zero and there will never be samples in poll_cb because
blk_mq_poll_stats_bkt() will return -1 if data_len is zero.

We could move blk_stat_add() back to __blk_mq_complete_request(),
but that would make the effort of trying to call ktime_get_ns()
once in vain. Instead we can reuse throtl_size field, and use
it for both block stats and block throttle, and adjust the
logic in blk_mq_poll_stats_bkt() accordingly.

Fixes: 4bc6339 ("block: move blk_stat_add() to __blk_mq_end_request()")
Tested-by: Pavel Begunkov <[email protected]>
Signed-off-by: Hou Tao <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>

block/blk-mq.c

@@ -44,12 +44,12 @@ static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
 
 static int blk_mq_poll_stats_bkt(const struct request *rq)
 {
-	int ddir, bytes, bucket;
+	int ddir, sectors, bucket;
 
 	ddir = rq_data_dir(rq);
-	bytes = blk_rq_bytes(rq);
+	sectors = blk_rq_stats_sectors(rq);
 
-	bucket = ddir + 2*(ilog2(bytes) - 9);
+	bucket = ddir + 2 * ilog2(sectors);
 
 	if (bucket < 0)
 		return -1;
@@ -333,6 +333,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	else
 		rq->start_time_ns = 0;
 	rq->io_start_time_ns = 0;
+	rq->stats_sectors = 0;
 	rq->nr_phys_segments = 0;
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 	rq->nr_integrity_segments = 0;
@@ -681,9 +682,7 @@ void blk_mq_start_request(struct request *rq)
 
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
 		rq->io_start_time_ns = ktime_get_ns();
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-		rq->throtl_size = blk_rq_sectors(rq);
-#endif
+		rq->stats_sectors = blk_rq_sectors(rq);
 		rq->rq_flags |= RQF_STATS;
 		rq_qos_issue(q, rq);
 	}

block/blk-throttle.c

@@ -2248,7 +2248,8 @@ void blk_throtl_stat_add(struct request *rq, u64 time_ns)
 	struct request_queue *q = rq->q;
 	struct throtl_data *td = q->td;
 
-	throtl_track_latency(td, rq->throtl_size, req_op(rq), time_ns >> 10);
+	throtl_track_latency(td, blk_rq_stats_sectors(rq), req_op(rq),
+			     time_ns >> 10);
 }
 
 void blk_throtl_bio_endio(struct bio *bio)

include/linux/blkdev.h

@@ -206,9 +206,12 @@ struct request {
 #ifdef CONFIG_BLK_WBT
 	unsigned short wbt_flags;
 #endif
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-	unsigned short throtl_size;
-#endif
+	/*
+	 * rq sectors used for blk stats. It has the same value
+	 * with blk_rq_sectors(rq), except that it never be zeroed
+	 * by completion.
+	 */
+	unsigned short stats_sectors;
 
 	/*
 	 * Number of scatter-gather DMA addr+len pairs after
@@ -917,6 +920,7 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
  * blk_rq_err_bytes()		: bytes left till the next error boundary
  * blk_rq_sectors()		: sectors left in the entire request
  * blk_rq_cur_sectors()		: sectors left in the current segment
+ * blk_rq_stats_sectors()	: sectors of the entire request used for stats
  */
 static inline sector_t blk_rq_pos(const struct request *rq)
 {
@@ -945,6 +949,11 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 	return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
 }
 
+static inline unsigned int blk_rq_stats_sectors(const struct request *rq)
+{
+	return rq->stats_sectors;
+}
+
 #ifdef CONFIG_BLK_DEV_ZONED
 static inline unsigned int blk_rq_zone_no(struct request *rq)
 {