linux-kernel - Re: AMD Athlon bogus performance value causing RCU stalls?

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: <alpine.DEB.2.21.1809271703530.8118@nanos.tec.linutronix.de>
Date:   Thu, 27 Sep 2018 17:04:46 +0200 (CEST)
From:   Thomas Gleixner <tglx@...utronix.de>
To:     Rob Prowel <rprowel@...cast.net>
cc:     linux-kernel@...r.kernel.org
Subject: Re: AMD Athlon bogus performance value causing RCU stalls?

On Wed, 26 Sep 2018, Rob Prowel wrote:
> On 09/23/18 17:19, Thomas Gleixner wrote:
> > > 
> > > Other than RTFM, or please build a bunch of kernels from source on your
> > > slow
> > > machine, using differing config options to help track down the cause of
> > > this...any thoughts about a solution?
> > 
> > Yes. This was decoded recently as an issue on 32bit due to a calculation
> > which is based on 'unsigned long' but requires to be 64bit wide.
> > 
> > It's in the 4.18.8 stable kernel, which should be available from your
> > fedora repo anytime soon.
> 
> OK.  Followup on AMD performance counter problem in 4.18.7
> 
> The Dell machine I was experiencing the problem on had a lot of ACPI
> issues.  One of the invalid ACPI entries was for a system timer.
> dmesg suggests that the broken timer was used in calculating the
> Athlon performance value.  So no, 32/64 bit math was not the issue.

Uff.

> ACPI=off in the kernel boot line fixed the issue completely. Machine
> still functions well as a file/web/postgresql dev server so it's all
> good.

Thanks for letting me know. I was about to dust of that old X2 I have
somewhere.

Thanks,

	tglx