linux-kernel - Re: [PATCH] x86/split_lock: Restore warn mode (and add a new one) to avoid userspace regression

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:   Thu, 29 Sep 2022 14:15:05 -0300
From:   "Guilherme G. Piccoli" <gpiccoli@...lia.com>
To:     Dave Hansen <dave.hansen@...el.com>, tony.luck@...el.com,
        tglx@...utronix.de, linux-kernel@...r.kernel.org, x86@...nel.org
Cc:     mingo@...hat.com, bp@...en8.de, dave.hansen@...ux.intel.com,
        hpa@...or.com, luto@...nel.org, kernel-dev@...lia.com,
        kernel@...ccoli.net, Fenghua Yu <fenghua.yu@...el.com>,
        Joshua Ashton <joshua@...ggi.es>,
        Paul Gofman <pgofman@...eweavers.com>,
        Pavel Machek <pavel@...x.de>,
        Pierre-Loup Griffais <pgriffais@...vesoftware.com>,
        Melissa Wen <mwen@...lia.com>
Subject: Re: [PATCH] x86/split_lock: Restore warn mode (and add a new one) to
 avoid userspace regression

Two responses in one:

First, I like Tony's idea - heuristic based on CPU number seems to make
sense. This number could be purely based on CPU number with a hardcoded
value, or based in a Kconfig (after N CPUs, add misery).


Now, second part below, inline:

On 29/09/2022 13:26, Dave Hansen wrote:
> [...]
> Let's be precise here, though.  It isn't that folks can't play.  It's
> that we *intentionally* put something in place that kept them from
> playing.  They can play just fine after disabling split lock detection.
>

Agreed with your wording, would just maybe "s/put something/added a
policy" heheh


>> [...]
> They don't have to live with it.  They can turn it off.  That's why the
> command-line disable is there.
> 

If they know how to do it, right? I'd rather have it as a new
non-default mechanism or at least, a Kconfig option in which gamer
distros could tune for their users, so we're not requiring them to tune
x86-specific parameters to play some game.