linux-kernel - Re: HPET (?) related hangs and breakage in 2.6.35,36

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:	Tue, 9 Nov 2010 12:44:48 -0500
From:	Andrew Lutomirski <luto@....edu>
To:	Borislav Petkov <bp@...64.org>,
	Clemens Ladisch <clemens@...isch.de>,
	Andrew Lutomirski <luto@....edu>, linux-kernel@...r.kernel.org,
	Thomas Gleixner <tglx@...utronix.de>,
	Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...e.hu>, "H. Peter Anvin" <hpa@...or.com>,
	x86 <x86@...nel.org>
Subject: Re: HPET (?) related hangs and breakage in 2.6.35,36

On Tue, Nov 9, 2010 at 10:38 AM, Borislav Petkov <bp@...64.org> wrote:
> On Tue, Nov 09, 2010 at 04:20:56PM +0100, Clemens Ladisch wrote:
>> Andrew Lutomirski wrote:
>> > After several minutes of uptime, my system freezes in a strange way.
>> > All of userspace and some kernel services freeze hard (no mouse, no
>> > typing, etc.)  Caps-lock works intermittently, as does (I think)
>> > pinging.  The only debug output I've been able to get is this (typed
>> > from a blurry photo because netconsole dies along with everything
>> > else):
>> >
>> > [ 5478.244722] Clocksource tsc unstable (delta = 101399051316 ns)
>> > [ 5478.367958] Switching to clocksource hpet
>> > [ 5543.729698] BUG: soft lockup - CPU #1 stuck for 61s! [migration/1:6]
>>
>> Looks like this one:
>> http://lkml.org/lkml/2010/10/26/126
>
> I don't think so: the one at the URL above is 37-rc1 specific (issue
> came in during the merge window) while Andrew's problem can be
> reproduced with 35 and 36, reportedly.
>
> Anyway, adding more people to Cc.

I may have just reproduced after a couple of days of uptime it in
2.6.36 with hpet=disable (in any case, the system hung and netconsole
didn't work).

I'm currently testing the hpet_min_tick stuff, backported to 2.6.36,
with hpet on.  Haven't had a problem yet, but I'll see what happens
after a few hours.  So far, it said:

ACPI: HPET id: 0x8086a301 base: 0xfed00000 min tick: 128

Is there any way that a tsc delta of >100 seconds occurring awhile
after bootup on Nehalem with a single socket can real (as opposed to a
bug making the kernel think that there was a delta when there really
wasn't)?

--Andy

>
> --
> Regards/Gruss,
> Boris.
>
> Advanced Micro Devices GmbH
> Einsteinring 24, 85609 Dornach
> General Managers: Alberto Bozzo, Andrew Bowd
> Registration: Dornach, Gemeinde Aschheim, Landkreis Muenchen
> Registergericht Muenchen, HRB Nr. 43632
>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/