linux-kernel - Re: [PATCH] blk-mq: introduce REQ_COMPLETE_WQ and add a workqueue to complete the request

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20210120095409.GB3694085@infradead.org>
Date:   Wed, 20 Jan 2021 09:54:09 +0000
From:   Christoph Hellwig <hch@...radead.org>
To:     Liu Xiang <liu.xiang@...ngsmart.com>
Cc:     linux-block@...r.kernel.org, axboe@...nel.dk,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH] blk-mq: introduce REQ_COMPLETE_WQ and add a workqueue to
 complete the request

On Wed, Jan 20, 2021 at 10:15:22AM +0800, Liu Xiang wrote:
> The commit "40d09b53bfc557af7481b9d80f060a7ac9c7d314" has solved the
> irqsoff problem by completing the request in softirq. But it may cause
> the system to suffer bad preemptoff time.
> Introduce the REQ_COMPLETE_WQ flag and blk_complete workqueue.
> This flag makes the request to be completed in the blk_complete workqueue.
> It can be used for requests that want to cut down both irqsoff and
> preemptoff time.

In addition to bloating the request_queue and introducing the completion
fast path this seems to lack an actual user.