block: set issue time stamp based on queue state

A previous commit moved RQF_IO_STAT into blk_account_io_done(), where
it's being set rather than at allocation time. Unfortunately we do check
for that flag in blk_mq_rq_time_init(), and hence setting the
start_time_ns wasn't being done. This lead to unwieldy inflight IO counts
and times, as IO completion accounting would a 0 value rather than the
issue time for it's subtraction math.

Fix this by switching the blk_mq_rq_time_init() check to use the queue
state rather than the request state.

Fixes: b8f762400ae8 ("block: move iostat check into blk_acount_io_start()")
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202410062110.512391df-oliver.sang@intel.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/blk-mq.c b/block/blk-mq.c
index b249514c2d638482e1f02d639d391eb5b581f8b1..9a3a9a3706181c977a66e0ab51e6639376285f22 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -331,7 +331,7 @@ 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))
+       if (blk_queue_io_stat(rq->q))
                rq->start_time_ns = blk_time_get_ns();
        else
                rq->start_time_ns = 0;