linux-kernel - Re: [PATCH v8 03/15] futex: Add basic infrastructure for local task local hash.

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: <87ldumnjo4.ffs@tglx>
Date: Tue, 04 Feb 2025 10:28:11 +0100
From: Thomas Gleixner <tglx@...utronix.de>
To: Peter Zijlstra <peterz@...radead.org>, Sebastian Andrzej Siewior
 <bigeasy@...utronix.de>
Cc: linux-kernel@...r.kernel.org, André Almeida
 <andrealmeid@...lia.com>,
 Darren Hart <dvhart@...radead.org>, Davidlohr Bueso <dave@...olabs.net>,
 Ingo Molnar <mingo@...hat.com>, Juri Lelli <juri.lelli@...hat.com>,
 Valentin Schneider <vschneid@...hat.com>, Waiman Long <longman@...hat.com>
Subject: Re: [PATCH v8 03/15] futex: Add basic infrastructure for local task
 local hash.

On Tue, Feb 04 2025 at 09:41, Peter Zijlstra wrote:
> On Mon, Feb 03, 2025 at 04:52:51PM +0100, Sebastian Andrzej Siewior wrote:
>> On 2025-02-03 15:41:01 [+0100], Peter Zijlstra wrote:
>> > Notably, I'm also still thikning about all that pending FUTEX2_NUMA
>> > stuff.
>> 
>> With local-hash there is still room for FUTEX2_NUMA?
>
> Yes, single process can span multiple nodes, and then you still get the
> cross node contention issues.

This is strictly about process private futexes, while FUTEX2_NUMA covers
both shared and private futexes and helps to avoid the hash collision
and resulting contention problems which are caused by the current global
hash.

With the private futex seperation you obviously get the cross node
memory access problems, but not the general contention issues which
FUTEX2_NUMA tries to address.

Thanks,

        tglx