linux-kernel - Re: [PATCH v3 2/5] locking/rwsem: Limit # of null owner retries for handoff writer

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]

Date:   Tue, 25 Oct 2022 15:55:09 -0400
From:   Waiman Long <longman@...hat.com>
To:     Peter Zijlstra <peterz@...radead.org>
Cc:     Ingo Molnar <mingo@...hat.com>, Will Deacon <will@...nel.org>,
        Boqun Feng <boqun.feng@...il.com>,
        linux-kernel@...r.kernel.org, john.p.donnelly@...cle.com,
        Hillf Danton <hdanton@...a.com>,
        Mukesh Ojha <quic_mojha@...cinc.com>,
        Ting11 Wang 王婷 <wangting11@...omi.com>
Subject: Re: [PATCH v3 2/5] locking/rwsem: Limit # of null owner retries for
 handoff writer

On 10/25/22 07:48, Peter Zijlstra wrote:
> On Tue, Oct 25, 2022 at 01:22:22PM +0200, Peter Zijlstra wrote:
>
>> Funny, I find the former approach much saner. Disabling preemption
>> around the whole thing fixes the fundamental problem while spin-limiting
>> is a band-aid.
>>
>> Note how rwsem_write_trylock() already does preempt_disable(), having
>> the read-side do something similar only makes sense.
> Something like the completely untested below perhaps...

That is quite a number of changes spread over many different functions. 
That is the kind of changes that may make it harder to backport to 
stable releases.

This patch is just a stop-gap measure for stable releases which I 
essentially revert in a later patch. I have no objection to disable 
preemption in within the rwsem code exception to be backported to a 
stable release. So I can add another patch on top of the series to 
essentially do that.

Cheers,
Longman