linux-kernel - Re: [PATCH] kernel/watchdog: fix spurious hard lockups

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: <9320cd00-88f4-49c5-aaa5-4bb4a80c8813@redhat.com>
Date:   Tue, 20 Jun 2017 20:12:04 -0400
From:   Prarit Bhargava <prarit@...hat.com>
To:     Andi Kleen <ak@...ux.intel.com>
Cc:     kan.liang@...el.com, linux-kernel@...r.kernel.org,
        dzickus@...hat.com, mingo@...nel.org, akpm@...ux-foundation.org,
        babu.moger@...cle.com, atomlin@...hat.com,
        torvalds@...ux-foundation.org, peterz@...radead.org,
        tglx@...utronix.de, eranian@...gle.com, acme@...hat.com,
        stable@...r.kernel.org
Subject: Re: [PATCH] kernel/watchdog: fix spurious hard lockups



On 06/20/2017 07:00 PM, Andi Kleen wrote:
> On Tue, Jun 20, 2017 at 06:34:23PM -0400, Prarit Bhargava wrote:
>>
>>
>> On 06/20/2017 05:33 PM, kan.liang@...el.com wrote:
>>> From: Kan Liang <Kan.liang@...el.com>
>>>
>>> Some users reported spurious NMI watchdog timeouts.
>>>
>>> We now have more and more systems where the Turbo range is wide enough
>>> that the NMI watchdog expires faster than the soft watchdog timer that
>>> updates the interrupt tick the NMI watchdog relies on.
>>>
>>
>> Hmm ... odd that I haven't seen this.  We're running a pretty wide
>> variety of systems here.  Do you have a reproducer?  I'd like to see
>> this occur on production HW.
> 
> It only happens on a few specific CPU SKUs with a very wide Turbo range.

Which ones?

> Reproducer is typically some stress workload that turbos very high.

So stress the single Turbo Max core?  Or any core?

P.

> 
> -Andi
>