From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753594AbXCZKI3 (ORCPT ); Mon, 26 Mar 2007 06:08:29 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753595AbXCZKI3 (ORCPT ); Mon, 26 Mar 2007 06:08:29 -0400 Received: from mx1.redhat.com ([66.187.233.31]:33883 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753593AbXCZKI2 (ORCPT ); Mon, 26 Mar 2007 06:08:28 -0400 From: David Howells In-Reply-To: <1174767387.10836.107.camel@localhost.localdomain> References: <1174767387.10836.107.camel@localhost.localdomain> <20070323111350.GD3980@xi.wantstofly.org> <20070303111427.GB16944@xi.wantstofly.org> <20070303113305.GB10515@flint.arm.linux.org.uk> <20070321221134.GA22497@xi.wantstofly.org> <16051.1174657433@redhat.com> To: Benjamin Herrenschmidt Cc: Lennert Buytenhek , Catalin Marinas , ARM Linux Mailing List , Dan Williams , linux-kernel@vger.kernel.org, torvalds@osdl.org, paulmck@us.ibm.com Subject: Re: I/O memory barriers vs SMP memory barriers X-Mailer: MH-E 8.0; nmh 1.1; GNU Emacs 22.0.50 Date: Mon, 26 Mar 2007 11:07:23 +0100 Message-ID: <4039.1174903643@redhat.com> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Benjamin Herrenschmidt wrote: > Hrm... I'm not sure I like the io_* name, I think it's even more > confusing, people will never know when to use what ... I'd've thought it more obvious, but given there are several types of I/O, some of which might require different barriering to others, I can see your point. However, I think mb() unadorned is also confusing. > Maybe we should dig out again my attempt at properly defining semantics > of IO accessors and related barriers and extend it to include CPU vs. > DMA barriers. That could be useful. David