linux-kernel - Re: [RFC PATCH v2 3/5] futex: Throughput-optimized (TO) futexes

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: <57E45438.2010307@hpe.com>
Date:   Thu, 22 Sep 2016 17:59:20 -0400
From:   Waiman Long <waiman.long@....com>
To:     Thomas Gleixner <tglx@...utronix.de>
CC:     Davidlohr Bueso <dave@...olabs.net>,
        Peter Zijlstra <peterz@...radead.org>,
        Mike Galbraith <umgwanakikbuti@...il.com>,
        Ingo Molnar <mingo@...nel.org>,
        Jonathan Corbet <corbet@....net>,
        <linux-kernel@...r.kernel.org>, <linux-doc@...r.kernel.org>,
        Jason Low <jason.low2@....com>,
        Scott J Norton <scott.norton@....com>,
        Douglas Hatch <doug.hatch@....com>
Subject: Re: [RFC PATCH v2 3/5] futex: Throughput-optimized (TO) futexes

On 09/22/2016 05:41 PM, Thomas Gleixner wrote:
> On Thu, 22 Sep 2016, Davidlohr Bueso wrote:
>> On Thu, 22 Sep 2016, Waiman Long wrote:
>>
>>> BTW, my initial attempt for the new futex was to use the same workflow as
>>> the PI futexes, but use mutex which has optimistic spinning instead of
>>> rt_mutex.
>> Btw, Thomas, do you still have any interest pursuing this for rtmutexes from
>> -rt into mainline? If so I can resend the patches from a while ago.
> Certainly yes. My faint memory tells me that there was some potential issue
> due to boosting the owner only if it gets scheduled out, but I might be
> wrong.

It is tricky to add optimistic spinning to rtmutexes because of the need 
to observe process priorities. It is certainly possible to make the top 
waiter spin, but then I am not sure how much performance gain with just 
that.

Cheers,
Longman