linux-kernel - Re: [PATCH v8 4/5] locking/qspinlock: Introduce starvation avoidance into CNA

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

Message-ID: <20200125111607.GV11457@worktop.programming.kicks-ass.net>
Date:   Sat, 25 Jan 2020 12:16:07 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     Waiman Long <longman@...hat.com>
Cc:     Alex Kogan <alex.kogan@...cle.com>, linux@...linux.org.uk,
        Ingo Molnar <mingo@...hat.com>,
        Will Deacon <will.deacon@....com>,
        Arnd Bergmann <arnd@...db.de>, linux-arch@...r.kernel.org,
        linux-arm-kernel <linux-arm-kernel@...ts.infradead.org>,
        linux-kernel@...r.kernel.org, Thomas Gleixner <tglx@...utronix.de>,
        Borislav Petkov <bp@...en8.de>, hpa@...or.com, x86@...nel.org,
        Hanjun Guo <guohanjun@...wei.com>,
        Jan Glauber <jglauber@...vell.com>,
        Steven Sistare <steven.sistare@...cle.com>,
        Daniel Jordan <daniel.m.jordan@...cle.com>,
        dave.dice@...cle.com
Subject: Re: [PATCH v8 4/5] locking/qspinlock: Introduce starvation avoidance
 into CNA

On Fri, Jan 24, 2020 at 11:46:53AM -0500, Waiman Long wrote:
> I also thought about that. As you said, it can be hard to guarantee that
> reliable time value can be retrieved in a timely manner across all the
> archs.

Rememer that this code is limited to 64bit archs that have NUMA, my
quick grep says that is limited to:

  alpha, arm64, ia64, mips, powerpc, s390, sparc, x86

afaict, x86 is the one with the worst clocks between the lot of them
(with exception of ia64, which has been completely buggered for a while
and nobody cares).

> Even if we can do that, we will introduce latency to important
> tasks or contexts. I like the first approach better.

In general, the kernel has no clues what is actually important.