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

[Jens Axboe <axboe@kernel.dk>]

On 5/13/23 8:12 AM, 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 | 3 +++
>  1 file changed, 3 insertions(+)
> 
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index 9c8dc70020bc..5b374fab169c 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -1593,6 +1593,9 @@ void blk_mq_put_rq_ref(struct request *rq)
>  		if (rq->end_io(rq, 0) == RQ_END_IO_FREE)
>  			blk_mq_free_request(rq);
>  	} else if (req_ref_put_and_test(rq)) {
> +		if (rq->rq_flags & RQF_MQ_INFLIGHT)
> +			__blk_mq_dec_active_requests(rq->mq_hctx)
> +
>  		__blk_mq_free_request(rq);
>  	}
>  }

The fact that you didn't even compile this not withstanding, why
not just move the existing check from blk_mq_free_request() to
__blk_mq_free_request()?

-- 
Jens Axboe