linux-kernel - Re: NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0

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

Message-ID: <87bjn14g04.ffs@tglx>
Date: Tue, 23 Sep 2025 12:31:23 +0200
From: Thomas Gleixner <tglx@...utronix.de>
To: Thorsten Sperber <lists+debian@...o2k.de>, Uwe Kleine-König
 <u.kleine-koenig@...libre.com>
Cc: 1111027@...s.debian.org, "Rafael J. Wysocki" <rafael@...nel.org>,
 linux-kernel@...r.kernel.org
Subject: Re: NMI: IOCK error (debug interrupt?) for reason 71 on CPU 0

On Mon, Sep 22 2025 at 19:33, Thorsten Sperber wrote:
>
> thanks for your help. It's been four days now, I'd say above average
> (last was five days) - and no crash yet. I'm going to wait at least
> until the weekend before naming a winner, but that's already looking
> pretty good.

Thanks for trying.

I suggested to try intel_idle.max_cstate=2 because these unknown NMI
backtraces all originated from a MWAIT(C3).

Can you reboot into the working 6.1.y kernel at some point and check
which idle driver is used there?

    cat /sys/devices/system/cpu/cpuidle/current_driver

and which states are advertised:

    ls /sys/devices/system/cpu/cpu0/cpuidle/state

Thanks,

        tglx