linux-kernel - Re: [HW PROBLEM] Intel I7 MCE. Erratum or not?

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:	Sun, 7 Dec 2008 14:13:37 -0800
From:	Arjan van de Ven <arjan@...radead.org>
To:	"Giangiacomo Mariotti" <gg.mariotti@...il.com>
Cc:	"Robert Hancock" <hancockr@...w.ca>, linux-kernel@...r.kernel.org
Subject: Re: [HW PROBLEM] Intel I7 MCE. Erratum or not?

On Sun, 7 Dec 2008 22:55:10 +0100
"Giangiacomo Mariotti" <gg.mariotti@...il.com> wrote:

> On Sun, Dec 7, 2008 at 4:25 AM, Robert Hancock <hancockr@...w.ca>
> wrote:
> >
> > If it only happened once then who knows, could be a cosmic ray or
> > something.. but if it happens again it sounds like you likely have
> > a bad CPU.
> >
> This same MCE happens every time I boot the 2.6.27.8 kernel, but it
> never happens with kernel 2.6.26.8. It appears every time at log time
> [  301.7320xx](where the x represent the scale of the approximation).
> In the previous log it appeared at [  301.732037], now it appeared at
> [  301.732042]. It happens just once at that moment and then never
> more until I reboot. No MCE gets logged with kernel 2.6.26.8 nor with
> Windows Vista 32bit, not even under very heavy load on memory and
> cpu(like 3d games or 3d mark vintage). Is this really an hardware
> problem? Why does it get logged only on kernel 2.6.27.8 at that exact
> moment? Now I'm gonna compile kernel 2.6.28-rc7 and see if there it
> happens too. Any suggestion? It would be appreciated, because,
> depending on the final result, I may be forced to change the
> hardware(It's still guaranteed, but it'd mean some months without a
> pc).

which video driver are you using?
While your HW might be defective (MCE's tend to indicate that), if it's
software dependent it might also indicate that something, usually a
video driver, gets the system in a really bad state.
Also, make sure that you have MCE enabled in both kernels (I'm sure you
do, but it's one of those things worth double checking)



-- 
Arjan van de Ven 	Intel Open Source Technology Centre
For development, discussion and tips for power savings, 
visit http://www.lesswatts.org
--
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/