From mboxrd@z Thu Jan 1 00:00:00 1970 From: Oleg Nesterov Subject: Re: Behaviour of smp_mb__{before,after}_spin* and acquire/release Date: Tue, 13 Jan 2015 19:45:10 +0100 Message-ID: <20150113184510.GA31525@redhat.com> References: <20150113163353.GE31784@arm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20150113163353.GE31784@arm.com> Sender: linux-kernel-owner@vger.kernel.org To: Will Deacon Cc: paulmck@linux.vnet.ibm.com, peterz@infradead.org, torvalds@linux-foundation.org, benh@kernel.crashing.org, linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org List-Id: linux-arch.vger.kernel.org On 01/13, Will Deacon wrote: > > 1. Does smp_mb__before_spinlock actually have to order prior loads > against later loads and stores? Documentation/memory-barriers.txt > says it does, but that doesn't match the comment The comment says that smp_mb__before_spinlock() + spin_lock() should only serialize STOREs with LOADs. This is because it was added to ensure that the setting of condition can't race with ->state check in ttwu(). But since we use wmb() it obviously serializes STOREs with STORES. I do not know if this should be documented, but we already have another user which seems to rely on this fact: set_tlb_flush_pending(). As for "prior loads", this doesn't look true... Oleg. From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mx1.redhat.com ([209.132.183.28]:51328 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753696AbbAMSqr (ORCPT ); Tue, 13 Jan 2015 13:46:47 -0500 Date: Tue, 13 Jan 2015 19:45:10 +0100 From: Oleg Nesterov Subject: Re: Behaviour of smp_mb__{before,after}_spin* and acquire/release Message-ID: <20150113184510.GA31525@redhat.com> References: <20150113163353.GE31784@arm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20150113163353.GE31784@arm.com> Sender: linux-arch-owner@vger.kernel.org List-ID: To: Will Deacon Cc: paulmck@linux.vnet.ibm.com, peterz@infradead.org, torvalds@linux-foundation.org, benh@kernel.crashing.org, linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org Message-ID: <20150113184510.-AWK1IhMRpmDTA08Gj1vNFkuJgTSP3Y2cogaqSzrQuc@z> On 01/13, Will Deacon wrote: > > 1. Does smp_mb__before_spinlock actually have to order prior loads > against later loads and stores? Documentation/memory-barriers.txt > says it does, but that doesn't match the comment The comment says that smp_mb__before_spinlock() + spin_lock() should only serialize STOREs with LOADs. This is because it was added to ensure that the setting of condition can't race with ->state check in ttwu(). But since we use wmb() it obviously serializes STOREs with STORES. I do not know if this should be documented, but we already have another user which seems to rely on this fact: set_tlb_flush_pending(). As for "prior loads", this doesn't look true... Oleg.