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;
From:   Jens Axboe <axboe@kernel.dk>
To:     jack@suse.cz, qiulaibin@huawei.com,
        andriy.shevchenko@linux.intel.com,
        Yu Kuai <yukuai1@huaweicloud.com>
Cc:     linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
        yukuai3@huawei.com, yi.zhang@huawei.com, yangerkun@huawei.com
In-Reply-To: <20230610023043.2559121-1-yukuai1@huaweicloud.com>
References: <20230610023043.2559121-1-yukuai1@huaweicloud.com>
Subject: Re: [PATCH -next v2] blk-mq: fix potential io hang by wrong
 'wake_batch'
Message-Id: <168658538673.969588.639148205003839147.b4-ty@kernel.dk>
Date:   Mon, 12 Jun 2023 09:56:26 -0600
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Precedence: bulk


On Sat, 10 Jun 2023 10:30:43 +0800, Yu Kuai wrote:
> In __blk_mq_tag_busy/idle(), updating 'active_queues' and calculating
> 'wake_batch' is not atomic:
> 
> t1:			t2:
> _blk_mq_tag_busy	blk_mq_tag_busy
> inc active_queues
> // assume 1->2
> 			inc active_queues
> 			// 2 -> 3
> 			blk_mq_update_wake_batch
> 			// calculate based on 3
> blk_mq_update_wake_batch
> /* calculate based on 2, while active_queues is actually 3. */
> 
> [...]

Applied, thanks!

[1/1] blk-mq: fix potential io hang by wrong 'wake_batch'
      commit: 4f1731df60f9033669f024d06ae26a6301260b55

Best regards,
-- 
Jens Axboe