blk-mq: fix mismatch between IO scheduler insert and finish
PATCH 1/1 blk-mq: fix mismatch between IO scheduler insert and finish
From: Chengming Zhou <[email protected]>
IO scheduler has requirement that one request which has been inserted must call finish_request() only once.
Now we have three special cases to consider:
1. rq has not insert, has complete: e.g. empty preflush
2. rq has insert, has not complete: e.g. merged requests will be freed
3. rq has insert, has twice complete: e.g. postflushes
Note case 1 which existed before, has been no problem since all the schedulers will check in their finish_request() if the rq has been inserted or not, like checking "rq->elv.priv[0]".
Then case 2 and case 3 are the introduced regression, we moved the scheduler finish_request() from free phase to complete phase to solve a deadlock problem. But it caused no finish_request() for request in case 2, and double finish_request() for request in case 3.
So we still need finish_request() in blk_mq_free_request() to cover case 2. And clear RQF_USE_SCHED flag to avoid double finish_request(). It should be fine since we're freeing the request now anyway.
Of course, we can also make all schedulers' finish_request() to clear "rq->elv.priv[0]" to avoid double finish. Or clear it in blk-mq, make the rq like not inserted as case 1.
FYI it's easy to reproduce warning in mq-deadline using this:
``` DEV=sdb echo mq-deadline > /sys/block/$DEV/queue/scheduler mkfs.ext4 /dev/$DEV mount /dev/$DEV /mnt cd /mnt stress-ng --symlink 4 --timeout 60 echo none > /sys/block/$DEV/queue/scheduler ```
--- block/blk-mq.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)
block/blk-mq.c +10 -1
@@ -685,8 +685,15 @@ static void blk_mq_finish_request(struct request *rq) {struct request_queue *q = rq->q; -if (rq->rq_flags &RQF_USE_SCHED ) +if (rq->rq_flags &RQF_USE_SCHED ) { q->elevator->type->ops.finish_request (rq); +/* +* For postflush request that may need to be +* completed twice, we should clear this flag +* to avoid double finish_request() on the rq. +*/ + rq->rq_flags &= ~RQF_USE_SCHED ; + } }static void __blk_mq_free_request (struct request *rq)
@@ -715,6 +722,8 @@ void blk_mq_free_request(struct request *rq) {struct request_queue *q = rq->q; +blk_mq_finish_request (rq); +if (unlikely (laptop_mode && !blk_rq_is_passthrough (rq)))laptop_io_completion (q->disk->bdi);
Signature · 1 line
2.41.0
Jens Axboe
maintainerQuoted 38 lines · On 8/18/23 9:12 PM, [email protected] wrote:
From: Chengming Zhou <[email protected]>
IO scheduler has requirement that one request which has been inserted must call
finish_request()only once.Now we have three special cases to consider:
1. rq has not insert, has complete: e.g. empty preflush
2. rq has insert, has not complete: e.g. merged requests will be freed
3. rq has insert, has twice complete: e.g. postflushesNote case 1 which existed before, has been no problem since all the schedulers will check in their
finish_request()if the rq has been inserted or not, like checking "rq->elv.priv[0]".Then case 2 and case 3 are the introduced regression, we moved the scheduler
finish_request()from free phase to complete phase to solve a deadlock problem. But it caused nofinish_request()for request in case 2, and doublefinish_request()for request in case 3.So we still need
finish_request()inblk_mq_free_request()to cover case 2. And clearRQF_USE_SCHEDflag to avoid doublefinish_request(). It should be fine since we're freeing the request now anyway.Of course, we can also make all schedulers'
finish_request()to clear "rq->elv.priv[0]" to avoid double finish. Or clear it in blk-mq, make the rq like not inserted as case 1.FYI it's easy to reproduce warning in mq-deadline using this:
``` DEV=sdb echo mq-deadline > /sys/block/$DEV/queue/scheduler mkfs.ext4 /dev/$DEV mount /dev/$DEV /mnt cd /mnt stress-ng --symlink 4 --timeout 60 echo none > /sys/block/$DEV/queue/scheduler ```
Quoted 3 lines
Reported-by kernel test robot <[email protected]>Signed-off-by Chengming Zhou <[email protected]>
I folded in this one and added a link to it as well, final result is here:
https://git.kernel.dk/cgit/linux/commit/?h=block-6.5&id=e5c0ca13659e9d18f53368d651ed7e6e433ec1cf
I'll get this sent off today.
Signature · 1 line
Jens Axboe