Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756565AbYFBPza (ORCPT ); Mon, 2 Jun 2008 11:55:30 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752627AbYFBPzV (ORCPT ); Mon, 2 Jun 2008 11:55:21 -0400 Received: from az33egw02.freescale.net ([192.88.158.103]:53701 "EHLO az33egw02.freescale.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751215AbYFBPzU (ORCPT ); Mon, 2 Jun 2008 11:55:20 -0400 Date: Mon, 2 Jun 2008 10:48:12 -0500 From: Scott Wood To: Haavard Skinnemoen Cc: Geert Uytterhoeven , benh@kernel.crashing.org, Matthew Wilcox , Linus Torvalds , David Miller , linux-arch@vger.kernel.org, linuxppc-dev@ozlabs.org, alan@lxorguk.ukuu.org.uk, linux-kernel@vger.kernel.org, tpiepho@freescale.com Subject: Re: MMIO and gcc re-ordering issue Message-ID: <20080602154812.GB2734@loki.buserror.net> References: <1211924335.3286.89.camel@pasglop> <20080527214241.GA22636@parisc-linux.org> <1211926636.3286.100.camel@pasglop> <20080528103648.54eb8734@hskinnemo-gx745.norway.atmel.com> <1212110003.15633.0.camel@pasglop> <20080530080700.773a82cc@siona.local> <1212132267.15633.69.camel@pasglop> <20080530102706.56fca248@siona.local> <20080602101102.0d8979c5@hskinnemo-gx745.norway.atmel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20080602101102.0d8979c5@hskinnemo-gx745.norway.atmel.com> User-Agent: Mutt/1.5.17+20080114 (2008-01-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1006 Lines: 24 On Mon, Jun 02, 2008 at 10:11:02AM +0200, Haavard Skinnemoen wrote: > Geert Uytterhoeven wrote: > > On Fri, 30 May 2008, Haavard Skinnemoen wrote: > > > Maybe we need another interface that does not do byteswapping but > > > provides stronger ordering guarantees? > > > > The byte swapping depends on the device/bus. > > Of course. But isn't it reasonable to assume that a device integrated > on the same silicon as the CPU is connected to a somewhat sane bus > which doesn't require any byte swapping? No, unfortunately. :-( See the end of drivers/dma/fsldma.h. Likewise with Freescale's PCI host bridges; for some reason the bus itself being little endian led to the host bridge control registers also being little endian. -Scott -- 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/