From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751070AbWGHKpR (ORCPT ); Sat, 8 Jul 2006 06:45:17 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751268AbWGHKpR (ORCPT ); Sat, 8 Jul 2006 06:45:17 -0400 Received: from khc.piap.pl ([195.187.100.11]:38543 "EHLO khc.piap.pl") by vger.kernel.org with ESMTP id S1751070AbWGHKpQ (ORCPT ); Sat, 8 Jul 2006 06:45:16 -0400 To: "Albert Cahalan" Cc: linux-kernel@vger.kernel.org, "Linus Torvalds" , linux-os@analogic.com, mingo@elte.hu, akpm@osdl.org, arjan@infradead.org Subject: Re: [patch] spinlocks: remove 'volatile' References: <787b0d920607072054i237eebf5g8109a100623a1070@mail.gmail.com> From: Krzysztof Halasa Date: Sat, 08 Jul 2006 12:45:13 +0200 In-Reply-To: <787b0d920607072054i237eebf5g8109a100623a1070@mail.gmail.com> (Albert Cahalan's message of "Fri, 7 Jul 2006 23:54:10 -0400") Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org "Albert Cahalan" writes: > That's all theoretical though. Today, gcc's volatile does > not follow the C standard on modern hardware. Bummer. > It'd be low-performance anyway though. I think gcc's volatile does in fact follow the standard. The standard simply doesn't say anything about hardware accesses, SMP, PCI etc. You must know what you're doing, and for some things you need a bit of assembler. -- Krzysztof Halasa