From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751834AbdHALrx (ORCPT ); Tue, 1 Aug 2017 07:47:53 -0400 Received: from bombadil.infradead.org ([65.50.211.133]:37011 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751115AbdHALrv (ORCPT ); Tue, 1 Aug 2017 07:47:51 -0400 Date: Tue, 1 Aug 2017 13:47:44 +0200 From: Peter Zijlstra To: Will Deacon Cc: "Paul E. McKenney" , Boqun Feng , linux-kernel@vger.kernel.org, Ingo Molnar , Thomas Gleixner , Randy Dunlap Subject: Re: [RFC][PATCH v3]: documentation,atomic: Add new documents Message-ID: <20170801114744.evjjfviqhu5kgu7v@hirez.programming.kicks-ass.net> References: <20170609193604.ncw3hhgvewzc3h5u@hirez.programming.kicks-ass.net> <20170611135632.sl72klbeklelupej@tardis> <20170612144929.3wiwtbqopsfpm3qk@hirez.programming.kicks-ass.net> <20170726115328.2sxiitivlnlq64dk@hirez.programming.kicks-ass.net> <20170726124750.vktrn5zi2gmpzfru@tardis> <20170731090535.rjgnoewqg7mhzr55@hirez.programming.kicks-ass.net> <20170731110403.ou3zqsp3uviqorkz@tardis> <20170731174345.GL3730@linux.vnet.ibm.com> <20170801090121.edo7mekhw3sann4h@hirez.programming.kicks-ass.net> <20170801101900.GB8702@arm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20170801101900.GB8702@arm.com> User-Agent: NeoMutt/20170609 (1.8.3) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Aug 01, 2017 at 11:19:00AM +0100, Will Deacon wrote: > On Tue, Aug 01, 2017 at 11:01:21AM +0200, Peter Zijlstra wrote: > > On Mon, Jul 31, 2017 at 10:43:45AM -0700, Paul E. McKenney wrote: > > > > > Why wouldn't the following have ACQUIRE semantics? > > > > > > atomic_inc(&var); > > > smp_mb__after_atomic(); > > > > > > Is the issue that there is no actual value returned or some such? > > > > Yes, so that the inc is a load-store, and thus there is a load, we loose > > the value. > > > > But I see your point I think. Irrespective of still having the value, > > the ordering is preserved and nothing should pass across that. > > > > > So if I have something like this, the assertion really can trigger? > > > > > > WRITE_ONCE(x, 1); atomic_inc(&y); > > > r0 = xchg_release(&y, 5); smp_mb__after_atomic(); > > > r1 = READ_ONCE(x); > > > > > > > > > WARN_ON(r0 == 0 && r1 == 0); > > > > > > I must confess that I am not seeing why we would want to allow this > > > outcome. > > > > No you are indeed quite right. I just wasn't creative enough. Thanks for > > the inspiration. > > Just to close this out, we agree that an smp_rmb() instead of > smp_mb__after_atomic() would *not* forbid this outcome, right? So that really hurts my brain. Per the normal rules that smp_rmb() would order the read of @x against the last ll of @y and per ll/sc ordering you then still don't get to make the WARN happen. On IRC you explained that your 8.1 LSE instructions are not in fact ordered by a smp_rmb, only by smp_wmb, which is 'surprising' since you really need to load the old value to compute the new value. Not happy... :-(