Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <b780ccfd-66b1-fdd1-b33e-aa680fbd86f1@redhat.com>
Date:   Tue, 13 Jun 2023 16:02:51 +0800
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:102.0)
 Gecko/20100101 Thunderbird/102.11.2
Subject: Re: [dm-devel] [PATCH -next v2 2/6] md: refactor action_store() for
 'idle' and 'frozen'
To:     Yu Kuai <yukuai1@huaweicloud.com>, guoqing.jiang@linux.dev,
        agk@redhat.com, snitzer@kernel.org, dm-devel@redhat.com,
        song@kernel.org
Cc:     yi.zhang@huawei.com, yangerkun@huawei.com,
        linux-kernel@vger.kernel.org, linux-raid@vger.kernel.org,
        yukuai3@huawei.com
References: <20230529132037.2124527-1-yukuai1@huaweicloud.com>
 <20230529132037.2124527-3-yukuai1@huaweicloud.com>
From:   Xiao Ni <xni@redhat.com>
In-Reply-To: <20230529132037.2124527-3-yukuai1@huaweicloud.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Precedence: bulk


在 2023/5/29 下午9:20, Yu Kuai 写道:
> From: Yu Kuai <yukuai3@huawei.com>
>
> Prepare to handle 'idle' and 'frozen' differently to fix a deadlock, there
> are no functional changes except that MD_RECOVERY_RUNNING is checked
> again after 'reconfig_mutex' is held.


Can you explain more about why it needs to check MD_RECOVERY_RUNNING 
again here?

>
> Signed-off-by: Yu Kuai <yukuai3@huawei.com>
> ---
>   drivers/md/md.c | 61 ++++++++++++++++++++++++++++++++++++-------------
>   1 file changed, 45 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/md/md.c b/drivers/md/md.c
> index 9b97731e1fe4..23e8e7eae062 100644
> --- a/drivers/md/md.c
> +++ b/drivers/md/md.c
> @@ -4755,6 +4755,46 @@ action_show(struct mddev *mddev, char *page)
>   	return sprintf(page, "%s\n", type);
>   }
>   
> +static void stop_sync_thread(struct mddev *mddev)
> +{
> +	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
> +		return;
> +
> +	if (mddev_lock(mddev))
> +		return;
> +
> +	/*
> +	 * Check again in case MD_RECOVERY_RUNNING is cleared before lock is
> +	 * held.
> +	 */
> +	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
> +		mddev_unlock(mddev);
> +		return;
> +	}
> +
> +	if (work_pending(&mddev->del_work))
> +		flush_workqueue(md_misc_wq);
> +
> +	if (mddev->sync_thread) {
> +		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
> +		md_reap_sync_thread(mddev);
> +	}
> +
> +	mddev_unlock(mddev);
> +}
> +
> +static void idle_sync_thread(struct mddev *mddev)
> +{
> +	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
> +	stop_sync_thread(mddev);
> +}
> +
> +static void frozen_sync_thread(struct mddev *mddev)
> +{
> +	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
> +	stop_sync_thread(mddev);
> +}
> +
>   static ssize_t
>   action_store(struct mddev *mddev, const char *page, size_t len)
>   {
> @@ -4762,22 +4802,11 @@ action_store(struct mddev *mddev, const char *page, size_t len)
>   		return -EINVAL;
>   
>   
> -	if (cmd_match(page, "idle") || cmd_match(page, "frozen")) {
> -		if (cmd_match(page, "frozen"))
> -			set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
> -		else
> -			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
> -		if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
> -		    mddev_lock(mddev) == 0) {
> -			if (work_pending(&mddev->del_work))
> -				flush_workqueue(md_misc_wq);
> -			if (mddev->sync_thread) {
> -				set_bit(MD_RECOVERY_INTR, &mddev->recovery);
> -				md_reap_sync_thread(mddev);
> -			}
> -			mddev_unlock(mddev);
> -		}
> -	} else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
> +	if (cmd_match(page, "idle"))
> +		idle_sync_thread(mddev);
> +	else if (cmd_match(page, "frozen"))
> +		frozen_sync_thread(mddev);
> +	else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
>   		return -EBUSY;
>   	else if (cmd_match(page, "resync"))
>   		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);