From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner+w=401wt.eu-S1755100AbXIAKdb@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1755100AbXIAKdb (ORCPT <rfc822;w@1wt.eu>);
	Sat, 1 Sep 2007 06:33:31 -0400
Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752991AbXIAKdU
	(ORCPT <rfc822;linux-kernel-outgoing>);
	Sat, 1 Sep 2007 06:33:20 -0400
Received: from mx1.suse.de ([195.135.220.2]:56504 "EHLO mx1.suse.de"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1752307AbXIAKdS (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Sat, 1 Sep 2007 06:33:18 -0400
From: Andi Kleen <ak@suse.de>
Organization: SUSE Linux Products GmbH, Nuernberg, GF: Markus Rex, HRB 16746 (AG Nuernberg)
To: Matthew Wilcox <matthew@wil.cx>
Subject: Re: [Bug 8942] dac960 driver stopped working with 2.6.22 kernel series
Date: Sat, 1 Sep 2007 12:18:16 +0200
User-Agent: KMail/1.9.6
Cc: Andrew Morton <akpm@linux-foundation.org>, linux-kernel@vger.kernel.org,
       Greg KH <greg@kroah.com>, alex@nibbles.it, dac@conglom-o.org,
       "bugme-daemon@kernel-bugs.osdl.org" 
	<bugme-daemon@bugzilla.kernel.org>,
       linux-scsi@vger.kernel.org
References: <bug-8942-27@http.bugzilla.kernel.org/> <20070831084259.fc2fd903.akpm@linux-foundation.org> <20070831161733.GC14130@parisc-linux.org>
In-Reply-To: <20070831161733.GC14130@parisc-linux.org>
MIME-Version: 1.0
Content-Type: text/plain;
  charset="iso-8859-1"
Content-Transfer-Encoding: 7bit
Content-Disposition: inline
Message-Id: <200709011218.17129.ak@suse.de>
Sender: linux-kernel-owner@vger.kernel.org
X-Mailing-List: linux-kernel@vger.kernel.org


> So anyway, what's actually failing is one of these:

Thanks for the analysis.

In theory we could not fail DAC if the machine has <4GB RAM to work around
such buggy drivers, but then they would fail anyways with >4GB. Also
the failure was intended to allow some drivers to use more efficient non DAC
operation.

> It seems a bit mean to write off *all* VIA bridges as data-corruptors.
> Maybe the people who haven't had problems before can help us start a
> white-list of VIA PCI bridges that don't have a problem with DAC.

The reason I blacklisted all was that there was a small triple of data corruption
reports with VIA bridges. Also it's impossible to get any errata information
out of VIA. And there are not that many >4GB VIA systems because these
chipsets are usually used in lower end systems.

-Andi