From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751505AbeBANxo (ORCPT ); Thu, 1 Feb 2018 08:53:44 -0500 Received: from merlin.infradead.org ([205.233.59.134]:54750 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750988AbeBANxm (ORCPT ); Thu, 1 Feb 2018 08:53:42 -0500 Date: Thu, 1 Feb 2018 14:53:29 +0100 From: Peter Zijlstra To: Will Deacon Cc: Stafford Horne , Paul McKenney , Jonas Bonn , Stefan Kristiansson , David Howells , Arnd Bergmann , linux-kernel@vger.kernel.org, Thomas Gleixner Subject: Re: asm-generic: Disallow no-op mb() for SMP systems Message-ID: <20180201135329.GB2269@hirez.programming.kicks-ass.net> References: <20180131130034.GR2269@hirez.programming.kicks-ass.net> <20180131131737.GA5097@arm.com> <20180131132610.GT2269@hirez.programming.kicks-ass.net> <20180201122750.GE30895@lianli.shorne-pla.net> <20180201132909.GW2249@hirez.programming.kicks-ass.net> <20180201133229.GB9182@arm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20180201133229.GB9182@arm.com> User-Agent: Mutt/1.9.2 (2017-12-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Feb 01, 2018 at 01:32:30PM +0000, Will Deacon wrote: > On Thu, Feb 01, 2018 at 02:29:09PM +0100, Peter Zijlstra wrote: > > On Thu, Feb 01, 2018 at 09:27:50PM +0900, Stafford Horne wrote: > > > I tried to clarify some of this in the spec v1.2 [0] which help formalize some of > > > the techniques we used for the SMP implementation. Its probably not perfect, > > > but I added a section "10. Multicore support" and tried to clarify some things > > > in section 7 on Atomicity. But it seems I dont cover exactly what are are > > > mentioning here. In general: > > > > > > 1 Secondary cores have memory snooping enabled meaning that any write to a > > > cached address will cause the cache line to be invalidated. > > > 2 l.swa (store atomic word) implies a store buffer flush. > > > > What about l.lwa? Can that observe 'old' values, or rather, miss values > > stuck in a remote store buffer? > > > > This will then cause the first l.swa to fail, which, per the above, > > would then sync things up? Which means you get that one extra > > merry-go-round. > > That's ok from a correctness perspective, though, as long as store buffers > are guaranteed to drain. Depends a bit if you can build control dependencies off of l.swa succeding or not I think :-) Otherwise you get into that dodgy state you suffer from where bits can leak right through. That is, I was thinking what we need for smp_mb__before_atomic. I could've gotten my brain in a twist or course, which isn't _that_ unusual. I never seem to be able to quite remember the holes you have with ll/sc on arm64 :-)