linux-kernel - Re: [PATCH] mq-deadline: the dd->dispatch queue follows a FIFO policy

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] [day] [month] [year] [list]

Message-ID: <4acab1b8-f67e-454b-a493-ac4c00193c51@kernel.dk>
Date: Tue, 9 Dec 2025 15:11:54 -0700
From: Jens Axboe <axboe@...nel.dk>
To: Tao pilgrim <pilgrimtao@...il.com>, Bart Van Assche <bvanassche@....org>
Cc: linux-block@...r.kernel.org, linux-kernel@...r.kernel.org,
 Chengkaitao <chengkaitao@...inos.cn>
Subject: Re: [PATCH] mq-deadline: the dd->dispatch queue follows a FIFO policy

On 12/8/25 7:06 PM, Tao pilgrim wrote:
> However, now all requests in the dd->dispatch list carry
> the BLK_MQ_INSERT_AT_HEAD flag, and I can't find any justification for
> continuing to use a LIFO (last-in-first-out) policy.

What if a head insertion requires another TUR or similar before being
able to be processed?

I agree with notion that AT_HEAD should generally be issued in order,
but let's not make blanket changes like this just because you can't find
any immediate justification for why the current behavior is as it is.
It'd be different if you were fixing a bug and came across this. But
that does not seem to be the case.

-- 
Jens Axboe