From mboxrd@z Thu Jan 1 00:00:00 1970 From: James Bottomley Subject: Re: libata/sata_sil24 cache alignment problem? Date: Tue, 12 Feb 2008 17:36:28 -0600 Message-ID: <1202859388.3137.164.camel@localhost.localdomain> References: <20080212180254.GA28237@postdiluvian.org> <20080212221257.12eeab13@core> Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit Return-path: Received: from accolon.hansenpartnership.com ([76.243.235.52]:59947 "EHLO accolon.hansenpartnership.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752053AbYBLXgf (ORCPT ); Tue, 12 Feb 2008 18:36:35 -0500 In-Reply-To: <20080212221257.12eeab13@core> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Alan Cox Cc: Mark Mason , linux-ide@vger.kernel.org, jgarzik@pobox.com On Tue, 2008-02-12 at 22:12 +0000, Alan Cox wrote: > > Has anyone else reported a problem like this? It requires > > non-coherent DMA, and a lack of a cache invalidate instruction, and > > one of the drivers that has this problem (it looks like sata_qstor > > does too, I haven't looked at others), so maybe that doesn't cover > > any other architectures. > > Nobody has, not even PA-RISC which is normally guaranteed to make life > miserable in the caching area but I agree entirely with your diagnosis > and that buffer should indeed be marked cache aligned I tell you what ... find me a parisc box that actually has IDE and we might have told you ... (actually, the pa8800's have IDE CD's on a cmd640 chip, but that oopses on boot for no reason we've tracked yet). James