Re: [PATCH 1/1] blk-mq: fix blk_mq_hw_ctx active request accounting

[Ming Lei <ming.lei@redhat.com>]

On Sat, May 13, 2023 at 06:12:27PM -0400, Tian Lan wrote:
> From: Tian Lan <tian.lan@twosigma.com>
> 
> The nr_active counter continues to increase over time which causes the
> blk_mq_get_tag to hang until the thread is rescheduled to a different
> core despite there are still tags available.
> 
> kernel-stack
> 
>   INFO: task inboundIOReacto:3014879 blocked for more than 2 seconds
>   Not tainted 6.1.15-amd64 #1 Debian 6.1.15~debian11
>   "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
>   task:inboundIOReacto state:D stack:0  pid:3014879 ppid:4557 flags:0x00000000
>     Call Trace:
>     <TASK>
>     __schedule+0x351/0xa20
>     scheduler+0x5d/0xe0
>     io_schedule+0x42/0x70
>     blk_mq_get_tag+0x11a/0x2a0
>     ? dequeue_task_stop+0x70/0x70
>     __blk_mq_alloc_requests+0x191/0x2e0
> 
> kprobe output showing RQF_MQ_INFLIGHT bit is not cleared before
> __blk_mq_free_request being called.
> 
>   320    320  kworker/29:1H __blk_mq_free_request rq_flags 0x220c0 in-flight 1
>          b'__blk_mq_free_request+0x1 [kernel]'
>          b'bt_iter+0x50 [kernel]'
>          b'blk_mq_queue_tag_busy_iter+0x318 [kernel]'
>          b'blk_mq_timeout_work+0x7c [kernel]'
>          b'process_one_work+0x1c4 [kernel]'
>          b'worker_thread+0x4d [kernel]'
>          b'kthread+0xe6 [kernel]'
>          b'ret_from_fork+0x1f [kernel]'
> 
> Signed-off-by: Tian Lan <tian.lan@twosigma.com>
> ---
>  block/blk-mq.c | 8 ++++----
>  1 file changed, 4 insertions(+), 4 deletions(-)
> 
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index f6dad0886a2f..850bfb844ed2 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -683,6 +683,10 @@ static void __blk_mq_free_request(struct request *rq)
>  	blk_crypto_free_request(rq);
>  	blk_pm_mark_last_busy(rq);
>  	rq->mq_hctx = NULL;
> +
> +	if (rq->rq_flags & RQF_MQ_INFLIGHT)
> +		__blk_mq_dec_active_requests(hctx);
> +
>  	if (rq->tag != BLK_MQ_NO_TAG)
>  		blk_mq_put_tag(hctx->tags, ctx, rq->tag);
>  	if (sched_tag != BLK_MQ_NO_TAG)
> @@ -694,15 +698,11 @@ static void __blk_mq_free_request(struct request *rq)
>  void blk_mq_free_request(struct request *rq)
>  {
>  	struct request_queue *q = rq->q;
> -	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
>  
>  	if ((rq->rq_flags & RQF_ELVPRIV) &&
>  	    q->elevator->type->ops.finish_request)
>  		q->elevator->type->ops.finish_request(rq);
>  
> -	if (rq->rq_flags & RQF_MQ_INFLIGHT)
> -		__blk_mq_dec_active_requests(hctx);
> -
>  	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
>  		laptop_io_completion(q->disk->bdi);

This patch looks fine, but please add words about why this way fixes the issue
with fixes tag:

- the difference between blk_mq_free_request() and blk_mq_end_request_batch(),
wrt. when to call __blk_mq_dec_active_requests(), the former does it
before calling req_ref_put_and_test(), and the later decreases active
request after req_ref_put_and_test().

- Fixes: f794f3351f26 ("block: add support for blk_mq_end_request_batch()")

Once the above is done, feel free to add:

Reviewed-by: Ming Lei <ming.lei@redhat.com>


Thanks,
Ming