Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1750981AbWAEXmy (ORCPT ); Thu, 5 Jan 2006 18:42:54 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751072AbWAEXmy (ORCPT ); Thu, 5 Jan 2006 18:42:54 -0500 Received: from mx2.mail.elte.hu ([157.181.151.9]:54421 "EHLO mx2.mail.elte.hu") by vger.kernel.org with ESMTP id S1750981AbWAEXmy (ORCPT ); Thu, 5 Jan 2006 18:42:54 -0500 Date: Fri, 6 Jan 2006 00:42:22 +0100 From: Ingo Molnar To: Joel Schopp Cc: Linus Torvalds , lkml , Andrew Morton , Arjan van de Ven , Nicolas Pitre , Jes Sorensen , Al Viro , Oleg Nesterov , David Howells , Alan Cox , Christoph Hellwig , Andi Kleen , Russell King , Anton Blanchard , PPC64-dev Subject: Re: [patch 00/21] mutex subsystem, -V14 Message-ID: <20060105234222.GA11474@elte.hu> References: <20060104144151.GA27646@elte.hu> <43BC5E15.207@austin.ibm.com> <20060105143502.GA16816@elte.hu> <43BD4C66.60001@austin.ibm.com> <20060105222106.GA26474@elte.hu> <43BDA672.4090704@austin.ibm.com> <43BDAD8A.60108@austin.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <43BDAD8A.60108@austin.ibm.com> User-Agent: Mutt/1.4.2.1i X-ELTE-SpamScore: -2.0 X-ELTE-SpamLevel: X-ELTE-SpamCheck: no X-ELTE-SpamVersion: ELTE 2.0 X-ELTE-SpamCheck-Details: score=-2.0 required=5.9 tests=ALL_TRUSTED,AWL autolearn=no SpamAssassin version=3.0.3 -2.8 ALL_TRUSTED Did not pass through any untrusted hosts 0.8 AWL AWL: From: address is in the auto white-list X-ELTE-VirusStatus: clean Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1053 Lines: 24 * Joel Schopp wrote: > > Shouldn't you make that "isync" dependent on SMP too? UP doesn't > > need it, since DMA will never matter, and interrupts are precise. > > I think the isync is necessary to keep heavily out of order processors > from getting ahead of themselves even on UP. Scanning back through > the powerpc spinlock code they seem to take the same view there as > well. the asm/spinlock.h ops are only built on SMP kernels. mutex.h is for both UP and SMP. On UP you should need no synchronization, because the only way another context could interfere with your critical section is by getting interrupted, and interrupts are fully synchronizing, right? On UP the only synchronization needed is when a device reads/writes memory in parallel to the CPU. Ingo - 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/