From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeff Garzik Subject: Re: [regression] 2.6.23 sata_mv EH updates broke my 7042 controller Date: Tue, 02 Oct 2007 19:23:10 -0400 Message-ID: <4702D2DE.1050504@pobox.com> References: <20071001220439.GA15332@lixom.net> <470176B8.1000109@pobox.com> <20071002023000.GA19286@lixom.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from srv5.dvmed.net ([207.36.208.214]:38966 "EHLO mail.dvmed.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751697AbXJBXXN (ORCPT ); Tue, 2 Oct 2007 19:23:13 -0400 In-Reply-To: <20071002023000.GA19286@lixom.net> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Olof Johansson Cc: linux-ide@vger.kernel.org, linux-kernel@vger.kernel.org Olof Johansson wrote: > On Mon, Oct 01, 2007 at 06:37:44PM -0400, Jeff Garzik wrote: >> Olof Johansson wrote: >>> Hardware config in my case: >>> Highpoint 2310 controller >>> PPC (big endian) >>> WD Raptor disk >>> Works fine with the other controller I've been using (SIL24), and works >>> fine if I revert the driver. >>> It also works fine if I disable the IOMMU. This would point towards >>> either a stale dma mapping, or a missing setup of one. >>> Not being much at home in the SATA drivers I could keep digging but I >>> figured I'd bring it up first in case it rings a bell for someone. >> The IOMMU data point is certainly interesting. Nothing jumps out on a >> re-review of the patch, so keep digging and let us know ;-) > > Looks like it's caused by enabling vmerge (which tends to be on for the > common PPC defconfigs). If I disable it, things look OK. > > Perhaps the Marvell controller doesn't like requests larger than 64K, > or wrapping some boundary. Do you have access to erratas/docs? > > I have verified it on a powermac now as well (had a quick scare that it > might have been some problem with the PA Semi IOMMU, but no). FWIW: I just tried the 6042 on my AMD64 platform with iommu=force, and was unable to reproduce any trouble. You could try changing MV_DMA_BOUNDARY to 0xffffU and see what happens. I'll also look through my errata, to see what is different between 6042 and 7042, if anything. Jeff