From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932224AbbJUIpe (ORCPT ); Wed, 21 Oct 2015 04:45:34 -0400 Received: from mail-oi0-f45.google.com ([209.85.218.45]:33814 "EHLO mail-oi0-f45.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753231AbbJUIp2 (ORCPT ); Wed, 21 Oct 2015 04:45:28 -0400 Date: Wed, 21 Oct 2015 16:45:03 +0800 From: Boqun Feng To: "Paul E. McKenney" Cc: Peter Zijlstra , linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, Ingo Molnar , Benjamin Herrenschmidt , Paul Mackerras , Michael Ellerman , Thomas Gleixner , Will Deacon , Waiman Long , Davidlohr Bueso , stable@vger.kernel.org Subject: Re: [PATCH tip/locking/core v4 1/6] powerpc: atomic: Make *xchg and *cmpxchg a full barrier Message-ID: <20151021084503.GE17714@fixme-laptop.cn.ibm.com> References: <1444838161-17209-1-git-send-email-boqun.feng@gmail.com> <1444838161-17209-2-git-send-email-boqun.feng@gmail.com> <20151014201916.GB3910@linux.vnet.ibm.com> <20151020071532.GB17714@fixme-laptop.cn.ibm.com> <20151020092147.GX17308@twins.programming.kicks-ass.net> <20151020212835.GH5105@linux.vnet.ibm.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="wTWi5aaYRw9ix9vO" Content-Disposition: inline In-Reply-To: <20151020212835.GH5105@linux.vnet.ibm.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 --wTWi5aaYRw9ix9vO Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Tue, Oct 20, 2015 at 02:28:35PM -0700, Paul E. McKenney wrote: > On Tue, Oct 20, 2015 at 11:21:47AM +0200, Peter Zijlstra wrote: > > On Tue, Oct 20, 2015 at 03:15:32PM +0800, Boqun Feng wrote: > > > On Wed, Oct 14, 2015 at 01:19:17PM -0700, Paul E. McKenney wrote: > > > >=20 > > > > Am I missing something here? If not, it seems to me that you need > > > > the leading lwsync to instead be a sync. > > > >=20 > > > > Of course, if I am not missing something, then this applies also to= the > > > > value-returning RMW atomic operations that you pulled this pattern = =66rom. > > > > If so, it would seem that I didn't think through all the possibilit= ies > > > > back when PPC_ATOMIC_EXIT_BARRIER moved to sync... In fact, I beli= eve > > > > that I worried about the RMW atomic operation acting as a barrier, > > > > but not as the load/store itself. :-/ > > > >=20 > > >=20 > > > Paul, I know this may be difficult, but could you recall why the > > > __futex_atomic_op() and futex_atomic_cmpxchg_inatomic() also got > > > involved into the movement of PPC_ATOMIC_EXIT_BARRIER to "sync"? > > >=20 > > > I did some search, but couldn't find the discussion of that patch. > > >=20 > > > I ask this because I recall Peter once bought up a discussion: > > >=20 > > > https://lkml.org/lkml/2015/8/26/596 > > >=20 > > > Peter's conclusion seems to be that we could(though didn't want to) l= ive > > > with futex atomics not being full barriers. >=20 > I have heard of user-level applications relying on unlock-lock being a > full barrier. So paranoia would argue for the full barrier. >=20 Understood. So a full barrier on one side of these operations is enough, I think. IOW, there is no need to strengthen these operations. > > > Peter, just be clear, I'm not in favor of relaxing futex atomics. But= if > > > I make PPC_ATOMIC_ENTRY_BARRIER being "sync", it will also strengthen > > > the futex atomics, just wonder whether such strengthen is a -fix- or > > > not, considering that I want this patch to go to -stable tree. > >=20 > > So Linus' argued that since we only need to order against user accesses > > (true) and priv changes typically imply strong barriers (open) we might > > want to allow archs to rely on those instead of mandating they have > > explicit barriers in the futex primitives. > >=20 > > And I indeed forgot to follow up on that discussion. > >=20 > > So; does PPC imply full barriers on user<->kernel boundaries? If so, its > > not critical to the futex atomic implementations what extra barriers are > > added. > >=20 > > If not; then strengthening the futex ops is indeed (probably) a good > > thing :-) Peter, that's probably a good thing, but I'm not that familiar with futex right now, so I won't touch that part if unnecessary in this series. Regards, Boqun >=20 > I am not seeing a sync there, but I really have to defer to the > maintainers on this one. I could easily have missed one. >=20 > Thanx, Paul >=20 --wTWi5aaYRw9ix9vO Content-Type: application/pgp-signature; name="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQEcBAABCAAGBQJWJ1CLAAoJEEl56MO1B/q4H1sH/0035ijoSUx0KX7eQ6iadgix JiYuExgRt/4P04w6CWGQcqTp3JXk0XoIr7M3rpwhUXQsXLA16GVO3FZVt1oUmzhi HNLYwFOjizWFy7ZyjWS37eo+WIavFskUk/JkDCt5diyJ4/d9NgQRMtFt2WmIYR1w qNdMU+o1LUFJ5agr0itBHM+1hhaPSa8c8YAixLgHI8XemATtlCnW8TAQMfdH70nI cVC05yrQM8uUYMjPRtj7r6DRfQ9JEiZMEpfQbhHx+1hnUQO6P44zrGWE/gczEpcN 16Z8N3rYx89R9l5Cym8Un0IJEJww9jbebEF1VykFvo3oZPOV5v8peXfqwEGjYY4= =eECa -----END PGP SIGNATURE----- --wTWi5aaYRw9ix9vO--