From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932727AbbJPTUy (ORCPT ); Fri, 16 Oct 2015 15:20:54 -0400 Received: from e33.co.us.ibm.com ([32.97.110.151]:43100 "EHLO e33.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753504AbbJPTUx (ORCPT ); Fri, 16 Oct 2015 15:20:53 -0400 X-IBM-Helo: d03dlp02.boulder.ibm.com X-IBM-MailFrom: paulmck@linux.vnet.ibm.com X-IBM-RcptTo: linux-kernel@vger.kernel.org Date: Fri, 16 Oct 2015 12:20:51 -0700 From: "Paul E. McKenney" To: Peter Zijlstra Cc: Catalin Marinas , Will Deacon , Linux Kernel Mailing List , Oleg Nesterov , Ingo Molnar Subject: Re: Q: schedule() and implied barriers on arm64 Message-ID: <20151016192051.GX3910@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com References: <20151016151830.GZ3816@twins.programming.kicks-ass.net> <20151016160422.GQ3910@linux.vnet.ibm.com> <20151016161608.GA3816@twins.programming.kicks-ass.net> <20151016172811.GT3910@linux.vnet.ibm.com> <20151016190741.GD3816@twins.programming.kicks-ass.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20151016190741.GD3816@twins.programming.kicks-ass.net> User-Agent: Mutt/1.5.21 (2010-09-15) X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 15101619-0009-0000-0000-00000EF713E9 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Oct 16, 2015 at 09:07:41PM +0200, Peter Zijlstra wrote: > On Fri, Oct 16, 2015 at 10:28:11AM -0700, Paul E. McKenney wrote: > > In other words, if task2() acquires the lock after task1() releases it, > > all CPUs must agree on the order of the operations in the two critical > > sections, even if these other CPUs don't acquire the lock. > > > > This same guarantee is needed if task1() and then task2() run in > > succession on the same CPU with no additional synchronization of any sort. > > > > Does this work on arm64? > > Yes, their load-acquire and store-release are RCsc. Whew!!! Thanx, Paul