From mboxrd@z Thu Jan 1 00:00:00 1970 From: Robert Hancock Subject: Re: IO_PAGE_FAULT from SATA card during boot Date: Thu, 17 Feb 2011 18:22:41 -0600 Message-ID: <4D5DBBD1.5020108@gmail.com> References: <20110202135644.GG11670@arachsys.com> <4D49FB9F.9040304@gmail.com> <20110203085601.GB2490@arachsys.com> <20110207174838.GA21124@arachsys.com> <4D50A4B8.2070608@gmail.com> <20110208104157.GU2106@amd.com> <20110208110036.GA18763@arachsys.com> <20110208144805.GF19483@arachsys.com> <20110217094005.GS21289@arachsys.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from mail-iy0-f174.google.com ([209.85.210.174]:61338 "EHLO mail-iy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757763Ab1BRAWp (ORCPT ); Thu, 17 Feb 2011 19:22:45 -0500 Received: by iyj8 with SMTP id 8so2954949iyj.19 for ; Thu, 17 Feb 2011 16:22:45 -0800 (PST) In-Reply-To: <20110217094005.GS21289@arachsys.com> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Chris Webb Cc: "Roedel, Joerg" , "linux-ide@vger.kernel.org" On 02/17/2011 03:40 AM, Chris Webb wrote: > Chris Webb writes: > >> Robert Hancock writes: >> >>> Did you try different chipsets? The two sets of output you posted are >>> both from Marvell 88SE9123-based cards. >> >> Oh, I may have been a muppet here then. I assumed the HPT cards would be a >> different chipset. I'll find something completely different! > > A SIL-based AHCI controller card turns out to work fine in the same setup, > so it does look like a problem specific to Marvell 88SE9123-based cards. That would tend to indicate some kind of issue with that particular chip. Does anyone have any contacts at Marvell that could look into this? Also wonder if we could quirk this in the kernel somehow so that IOMMUs wouldn't freak out..