linux-block.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Keith Busch <kbusch@kernel.org>
To: Yu Kuai <yukuai1@huaweicloud.com>
Cc: jack@suse.cz, axboe@kernel.dk, osandov@fb.com,
	linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
	yukuai3@huawei.com, yi.zhang@huawei.com
Subject: Re: [PATCH] sbitmap: fix possible io hung due to lost wakeup
Date: Tue, 6 Sep 2022 15:27:51 -0600	[thread overview]
Message-ID: <Yxe7V3yfBcADoYLE@kbusch-mbp.dhcp.thefacebook.com> (raw)
In-Reply-To: <20220803121504.212071-1-yukuai1@huaweicloud.com>

On Wed, Aug 03, 2022 at 08:15:04PM +0800, Yu Kuai wrote:
>  	wait_cnt = atomic_dec_return(&ws->wait_cnt);
> -	if (wait_cnt <= 0) {
> -		int ret;
> +	/*
> +	 * For concurrent callers of this, callers should call this function
> +	 * again to wakeup a new batch on a different 'ws'.
> +	 */
> +	if (wait_cnt < 0 || !waitqueue_active(&ws->wait))
> +		return true;

If wait_cnt is '0', but the waitqueue_active happens to be false due to racing
with add_wait_queue(), this returns true so the caller will retry. The next
atomic_dec will set the current waitstate wait_cnt < 0, which also forces an
early return true. When does the wake up happen, or wait_cnt and wait_index get
updated in that case?

  
> -		wake_batch = READ_ONCE(sbq->wake_batch);
> +	if (wait_cnt > 0)
> +		return false;
>  
> -		/*
> -		 * Pairs with the memory barrier in sbitmap_queue_resize() to
> -		 * ensure that we see the batch size update before the wait
> -		 * count is reset.
> -		 */
> -		smp_mb__before_atomic();
> +	wake_batch = READ_ONCE(sbq->wake_batch);
>  
> -		/*
> -		 * For concurrent callers of this, the one that failed the
> -		 * atomic_cmpxhcg() race should call this function again
> -		 * to wakeup a new batch on a different 'ws'.
> -		 */
> -		ret = atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wake_batch);
> -		if (ret == wait_cnt) {
> -			sbq_index_atomic_inc(&sbq->wake_index);
> -			wake_up_nr(&ws->wait, wake_batch);
> -			return false;
> -		}
> +	/*
> +	 * Wake up first in case that concurrent callers decrease wait_cnt
> +	 * while waitqueue is empty.
> +	 */
> +	wake_up_nr(&ws->wait, wake_batch);
>  
> -		return true;
> -	}
> +	/*
> +	 * Pairs with the memory barrier in sbitmap_queue_resize() to
> +	 * ensure that we see the batch size update before the wait
> +	 * count is reset.
> +	 *
> +	 * Also pairs with the implicit barrier between decrementing wait_cnt
> +	 * and checking for waitqueue_active() to make sure waitqueue_active()
> +	 * sees result of the wakeup if atomic_dec_return() has seen the result
> +	 * of atomic_set().
> +	 */
> +	smp_mb__before_atomic();
> +
> +	/*
> +	 * Increase wake_index before updating wait_cnt, otherwise concurrent
> +	 * callers can see valid wait_cnt in old waitqueue, which can cause
> +	 * invalid wakeup on the old waitqueue.
> +	 */
> +	sbq_index_atomic_inc(&sbq->wake_index);
> +	atomic_set(&ws->wait_cnt, wake_batch);
>  
>  	return false;
>  }
> -- 
> 2.31.1
> 

  parent reply	other threads:[~2022-09-06 21:28 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-08-03 12:15 [PATCH] sbitmap: fix possible io hung due to lost wakeup Yu Kuai
2022-08-13  5:58 ` Yu Kuai
2022-08-23 13:37 ` Jens Axboe
2022-09-06 21:27 ` Keith Busch [this message]
2022-09-07  1:12   ` Yu Kuai
2022-09-07 10:23   ` Jan Kara
2022-09-07 14:13     ` Keith Busch
2022-09-07 16:41       ` Jan Kara
2022-09-07 18:20         ` Keith Busch
2022-09-08  9:33           ` Jan Kara
2022-09-08  9:45             ` Yu Kuai

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=Yxe7V3yfBcADoYLE@kbusch-mbp.dhcp.thefacebook.com \
    --to=kbusch@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=jack@suse.cz \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=osandov@fb.com \
    --cc=yi.zhang@huawei.com \
    --cc=yukuai1@huaweicloud.com \
    --cc=yukuai3@huawei.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).