From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1756104Ab1EQR50 (ORCPT <rfc822;w@1wt.eu>);
	Tue, 17 May 2011 13:57:26 -0400
Received: from mx1.redhat.com ([209.132.183.28]:27462 "EHLO mx1.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1755745Ab1EQR5Z (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Tue, 17 May 2011 13:57:25 -0400
Date: Tue, 17 May 2011 13:57:07 -0400
From: Don Zickus <dzickus@redhat.com>
To: Andi Kleen <ak@linux.intel.com>
Cc: Huang Ying <ying.huang@intel.com>, Cyrill Gorcunov <gorcunov@gmail.com>,
        huang ying <huang.ying.caritas@gmail.com>, Ingo Molnar <mingo@elte.hu>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        Andi Kleen <andi@firstfloor.org>,
        Robert Richter <robert.richter@amd.com>
Subject: Re: [RFC] x86, NMI, Treat unknown NMI as hardware error
Message-ID: <20110517175707.GP31888@redhat.com>
References: <4DCD4B85.3040702@gmail.com>
 <BANLkTin7LNo0dDLs-Rz6WqCQ9RvS=MLXcw@mail.gmail.com>
 <4DCE3493.4090404@gmail.com>
 <BANLkTin1pvdnXtw53MhwfCsEQpsu0TUUmg@mail.gmail.com>
 <4DCF7413.4070704@gmail.com>
 <4DD07959.4030608@intel.com>
 <20110516190310.GH31888@redhat.com>
 <4DD20A2F.604@intel.com>
 <20110517142427.GL31888@redhat.com>
 <20110517163847.GF24805@tassilo.jf.intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20110517163847.GF24805@tassilo.jf.intel.com>
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Tue, May 17, 2011 at 09:38:47AM -0700, Andi Kleen wrote:
> > Can we agree on this, that if an OEM implemented HEST properly such that a
> > hardware error happens it will generate a GHES record.  The subsequent NMI
> 
> Apparently there are some (rare) corner cases where it's hard/impossible
> to do. So in those cases you will see an NMI without record.

Hmm, I would be interested to know what kind, but it doesn't matter I
guess.

> 
> In the "normal" error case you will a GHES record on NMI.

Random thought, in the Firmware first mode of HEST (which is the only way
GHES records get produced??), does an SCI happen first to jump into the
firmware for processing, then an NMI?

Cheers,
Don