From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757484AbbIUX1W (ORCPT ); Mon, 21 Sep 2015 19:27:22 -0400 Received: from mail-ig0-f182.google.com ([209.85.213.182]:36019 "EHLO mail-ig0-f182.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755478AbbIUX1U (ORCPT ); Mon, 21 Sep 2015 19:27:20 -0400 Date: Tue, 22 Sep 2015 07:26:56 +0800 From: Boqun Feng To: Will Deacon Cc: "linux-kernel@vger.kernel.org" , "linuxppc-dev@lists.ozlabs.org" , Peter Zijlstra , Ingo Molnar , Benjamin Herrenschmidt , Paul Mackerras , Michael Ellerman , Thomas Gleixner , "Paul E. McKenney" , Waiman Long Subject: Re: [RFC v2 3/7] powerpc: atomic: Implement atomic{,64}_{add,sub}_return_* variants Message-ID: <20150921232656.GC970@fixme-laptop.cn.ibm.com> References: <1442418575-12297-1-git-send-email-boqun.feng@gmail.com> <1442418575-12297-4-git-send-email-boqun.feng@gmail.com> <20150918165902.GF12837@arm.com> <20150919153310.GB20458@fixme-laptop.cn.ibm.com> <20150920082303.GA1166@fixme-laptop.cn.ibm.com> <20150921222427.GG7356@arm.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="CblX+4bnyfN0pR09" Content-Disposition: inline In-Reply-To: <20150921222427.GG7356@arm.com> User-Agent: Mutt/1.5.24 (2015-08-30) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org --CblX+4bnyfN0pR09 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Mon, Sep 21, 2015 at 11:24:27PM +0100, Will Deacon wrote: > Hi Boqun, >=20 > On Sun, Sep 20, 2015 at 09:23:03AM +0100, Boqun Feng wrote: > > On Sat, Sep 19, 2015 at 11:33:10PM +0800, Boqun Feng wrote: > > > On Fri, Sep 18, 2015 at 05:59:02PM +0100, Will Deacon wrote: > > > > On Wed, Sep 16, 2015 at 04:49:31PM +0100, Boqun Feng wrote: > > > > > On powerpc, we don't need a general memory barrier to achieve acq= uire and > > > > > release semantics, so __atomic_op_{acquire,release} can be implem= ented > > > > > using "lwsync" and "isync". > > > >=20 > > > > I'm assuming isync+ctrl isn't transitive, so we need to get to the = bottom > > >=20 > > > Actually the transitivity is still guaranteed here, I think ;-) >=20 > The litmus test I'm thinking of is: >=20 >=20 > { > 0:r2=3Dx; > 1:r2=3Dx; 1:r5=3Dz; > 2:r2=3Dz; 2:r4=3Dx; > } > P0 | P1 | P2 ; > li r1,1 | lwz r1,0(r2) | lwz r1,0(r2) ; > stw r1,0(r2) | cmpw r1,r1 | cmpw r1,r1 ; > | beq LC00 | beq LC01 ; > | LC00: | LC01: ; > | isync | isync ; > | li r4,1 | lwz r3,0(r4) ; > | stw r4,0(r5) | ; > exists > (1:r1=3D1 /\ 2:r1=3D1 /\ 2:r3=3D0) >=20 >=20 > Which appears to be allowed. I don't think you need to worry about backwa= rds > branches for the ctrl+isync construction (none of the current example do, > afaict). >=20 Yes.. my care of backwards branches is not quite related to the topic, I concerned that mostly because my test is using atomic operation, and I just want to test the exact asm code. > Anyway, all the problematic cases seem to arise when we start mixing > ACQUIRE/RELEASE accesses with relaxed accesses (i.e. where an access from > one group reads from an access in the other group). It would be simplest > to say that this doesn't provide any transitivity guarantees, and that > an ACQUIRE must always read from a RELEASE if transitivity is required. >=20 Agreed. RELEASE alone doesn't provide transitivity and transitivity is guaranteed only if an ACQUIRE read from a RELEASE. That's exactly the direction which the link (https://lkml.org/lkml/2015/9/15/836) is heading to. So I think we are fine here to use ctrl+isync here, right? Regards, Boqun --CblX+4bnyfN0pR09 Content-Type: application/pgp-signature; name="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQEcBAABCAAGBQJWAJI8AAoJEEl56MO1B/q4zqkH/3dzlyiyx73GLcYs4Fh6gJd8 saKcJe0ELVCGM+jjXjpbFqv5ZEP9i7wf8XbjxXniT65v+E2wY3bRS9VgVvLWfNGe srgNIB14JauxakgdBotqE9wAovTsodBDXqp5CSVUNdZpBQsgvVAYAmmi2lG9IV1o BpAKcH0lm500cgMZ+iUZCk6zdl9T+hMhdbhZ6jNrsUB+h/z2u3rmEToTvv1brWPN JwzwbVpthT0YXPDDdMbD2q10A/edy9jIXBivl7BJRWNwdhNITZ4g9eEX77d8n4t5 5GshAvUVgT+QxnLSPjq60+R7dTW2XMkrUH/IV4biW7MYxCzrLGalrpsIE1LjGoM= =Ofmi -----END PGP SIGNATURE----- --CblX+4bnyfN0pR09--