From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754317AbcBBJfY (ORCPT ); Tue, 2 Feb 2016 04:35:24 -0500 Received: from mail-oi0-f42.google.com ([209.85.218.42]:33748 "EHLO mail-oi0-f42.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754158AbcBBJfU (ORCPT ); Tue, 2 Feb 2016 04:35:20 -0500 Date: Tue, 2 Feb 2016 17:34:40 +0800 From: Boqun Feng To: Linus Torvalds Cc: Paul McKenney , Will Deacon , Peter Zijlstra , "Maciej W. Rozycki" , David Daney , =?iso-8859-1?Q?M=E5ns_Rullg=E5rd?= , Ralf Baechle , Linux Kernel Mailing List Subject: Re: [RFC][PATCH] mips: Fix arch_spin_unlock() Message-ID: <20160202093440.GD1239@fixme-laptop.cn.ibm.com> References: <20160128095718.GC30928@arm.com> <20160128223131.GV4503@linux.vnet.ibm.com> <20160129095958.GA4541@arm.com> <20160129102253.GG4503@linux.vnet.ibm.com> <20160201135621.GD6828@arm.com> <20160202035458.GF6719@linux.vnet.ibm.com> <20160202051904.GC1239@fixme-laptop.cn.ibm.com> <20160202064433.GG6719@linux.vnet.ibm.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="nHwqXXcoX0o6fKCv" Content-Disposition: inline In-Reply-To: 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 --nHwqXXcoX0o6fKCv Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable Hello Linus, On Tue, Feb 02, 2016 at 12:19:04AM -0800, Linus Torvalds wrote: > On Tue, Feb 2, 2016 at 12:07 AM, Linus Torvalds > wrote: > > > > So we *absolutely* should say that *OF COURSE* these things work: > > > > - CPU A: > > > > .. initialize data structure -> smp_wmb() -> WRITE_ONCE(ptr); > > > > - CPU B: > > > > smp_load_acquire(ptr) - we can rely on things behind "ptr" being in= itialized >=20 > That's a bad example, btw. I shouldn't have made it be a "pointer", > because then we get the whole address dependency chain ordering > anyway. >=20 > So instead of "ptr", read "state flag". It might just be an "int" that > says "data has been initialized". >=20 > So >=20 > .. initialize memory .. > smp_wmb(); > WRITE_ONCE(&is_initialized, 1); >=20 > should pair with >=20 > if (smp_load_acquire(&is_initialized)) > ... we can read and write the data, knowing it has been initializ= ed .. >=20 > exactly because "smp_wmb()" (cheap write barrier) might be cheaper > than "smp_store_release()" (expensive full barrier) and thus > preferred. >=20 Just to be clear, what Will, Paul and I are discussing here is about local transitivity, which refers to something like this following example: (a, b and is_initialized are all initially zero) P0: WRITE_ONCE(a, 1); smp_store_release(&is_initialized, 1); P1: r1 =3D smp_load_acquire(&is_initialized); smp_store_release(&b, 1); P2: r2 =3D smp_load_acquire(&b); r3 =3D READ_ONCE(a); , in which case, r1 =3D=3D 1 && r2 =3D=3D 1 && r3 =3D=3D 0 can not happen b= ecause RELEASE+ACQUIRE pairs guarantee local transitivity. More on local transitvity: http://article.gmane.org/gmane.linux.kernel.virtualization/26856 And what I'm asking here is something like this following example: (a, b and is_initialized are all initially zero) P0: WRITE_ONCE(a, 1); smp_store_release(&is_initialized, 1); P1: if (r1 =3D READ_ONCE(is_initialized)) smp_store_release(&b, 1); P2: if (r2 =3D READ_ONCE(b)) { smp_rmb();=09 r3 =3D READ_ONCE(a); } , in which case, can r1 =3D=3D 1 && r2 =3D=3D 1 && r3 =3D=3D 0 happen? Please note this example is about two questions on local transitivity: 1. Could "READ_ONCE(); if" extend a locally transitive chain. 2. Could "READ_ONCE(); if; smp_rmb()" at least be a locally transitive chain termination? > So mixing ordering metaphors actually does make sense, and should be > entirely well-defined. >=20 I think Paul does agree that smp_{r,w}mb() with applicative memory operations around could pair with smp_store_release() or smp_load_acquire(). Hope I didn't misunderstand any of you or make you misunderstood with each other.. Regards, Boqun > There's likely less reason to do it the other way (ie > "smp_store_release()" on one side pairing with "LOAD_ONCE() + > smp_rmb()" on the other) since there likely isn't the same kind of > performance reason for that pairing. But even if we would never > necessarily want to do it, I think our memory ordering rules would be > *much* better for strongly stating that it has to work, than being > timid and trying to make the rules weak. >=20 > Memory ordering is confusing enough as it is. We should not make > people worry more than they already have to. Strong rules are good. >=20 > Linus --nHwqXXcoX0o6fKCv Content-Type: application/pgp-signature; name="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQEcBAABCAAGBQJWsHglAAoJEEl56MO1B/q4hJAH/0F+Q9LEQ3Xq+sPyqa6TaFyV eNhY5TixU74o8JM92pStoDS0KzP9T/ck2cODW3tRGWtPdOsrxMwJPH2k8UvLLEBC dYMrwk9vNdyEqA2hDf65qrugU5K9Vph3DhfPtk/I5zwiZfSuy+A6PnPzcSnFDHIW WMnHCJan9ZhLRZFWhTVuCgz/nsqB07wbHpMHWzZb1oaUEzMum9KAu3pkZwftbxu6 xuRbx0MvogCyQDTRKMMimayQL/6O5vqwIKysjrE66AOzp3Efq+WT4vmcX6lDCdjM 8X2m3ljupXMVRoIF9ftVsv5Wjh8JKavyHxC0zSXbA9SZss18OvA8fkmSyCwiiNc= =3gUZ -----END PGP SIGNATURE----- --nHwqXXcoX0o6fKCv--