Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760323AbXHWIrX (ORCPT ); Thu, 23 Aug 2007 04:47:23 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755434AbXHWIrO (ORCPT ); Thu, 23 Aug 2007 04:47:14 -0400 Received: from netops-testserver-3-out.sgi.com ([192.48.171.28]:56704 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751050AbXHWIrN (ORCPT ); Thu, 23 Aug 2007 04:47:13 -0400 Message-ID: <46CD4927.2080505@sgi.com> Date: Thu, 23 Aug 2007 10:45:27 +0200 From: Jes Sorensen User-Agent: Thunderbird 2.0.0.0 (X11/20070719) MIME-Version: 1.0 To: James Bottomley Cc: Jesse Barnes , akepner@sgi.com, Randy Dunlap , linux-kernel , rdreier@cisco.com, linux-ia64 Subject: Re: [PATCH 2/3] dma: override "dma_flags_set_dmaflush" for sn-ia64 References: <20070818002746.GU1813@sgi.com> <200708220903.23702.jbarnes@virtuousgeek.org> <1187801095.3410.49.camel@localhost.localdomain> <200708220951.05101.jbarnes@virtuousgeek.org> <1187802272.3410.58.camel@localhost.localdomain> <46CC6C4B.1030202@sgi.com> <1187806205.3410.66.camel@localhost.localdomain> In-Reply-To: <1187806205.3410.66.camel@localhost.localdomain> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1140 Lines: 26 James Bottomley wrote: > Hmm, didn't see the email ... but I'm probably not cc'd on all the > thread. However ... it isn't that you couldn't do it ... it's that you > don't want to do it because it's faster to violate the spec ... like all > those nice ATA devices that lie about having a cache and then let you > power down with uncommitted data still in it ... they work much faster > for HDIO tests ... and who ever switches their box off? James, I didn't do it, I don't know who did it, but sure we can try and track them down and line them up outside ..... Point is that this is how the chips were done and they are out there in numbers. It makes things a *lot* faster to violate the spec in such a system, yes it sucks, but thats how things are. It wouldn't be the first time someone violated the PCI spec in their implementation and I am pretty sure it won't be the last. Cheers, Jes - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/