From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751011AbcBBFTm (ORCPT ); Tue, 2 Feb 2016 00:19:42 -0500 Received: from mail-oi0-f45.google.com ([209.85.218.45]:33746 "EHLO mail-oi0-f45.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750717AbcBBFTk (ORCPT ); Tue, 2 Feb 2016 00:19:40 -0500 Date: Tue, 2 Feb 2016 13:19:04 +0800 From: Boqun Feng To: "Paul E. McKenney" Cc: Will Deacon , Peter Zijlstra , "Maciej W. Rozycki" , David Daney , =?iso-8859-1?Q?M=E5ns_Rullg=E5rd?= , Ralf Baechle , linux-kernel@vger.kernel.org, torvalds@linux-foundation.org Subject: Re: [RFC][PATCH] mips: Fix arch_spin_unlock() Message-ID: <20160202051904.GC1239@fixme-laptop.cn.ibm.com> References: <20160127114348.GF2390@arm.com> <20160127145421.GT6357@twins.programming.kicks-ass.net> <20160127152158.GJ2390@arm.com> <20160127233836.GQ4503@linux.vnet.ibm.com> <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> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="48TaNjbzBVislYPb" Content-Disposition: inline In-Reply-To: <20160202035458.GF6719@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 --48TaNjbzBVislYPb Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable Hi Paul, On Mon, Feb 01, 2016 at 07:54:58PM -0800, Paul E. McKenney wrote: > On Mon, Feb 01, 2016 at 01:56:22PM +0000, Will Deacon wrote: > > On Fri, Jan 29, 2016 at 02:22:53AM -0800, Paul E. McKenney wrote: > > > On Fri, Jan 29, 2016 at 09:59:59AM +0000, Will Deacon wrote: > > > > On Thu, Jan 28, 2016 at 02:31:31PM -0800, Paul E. McKenney wrote: > > >=20 > > > [ . . . ] > > >=20 > > > > > For Linux in general, this is a question: How strict do we want t= o be > > > > > about matching the type of write with the corresponding read? My > > > > > default approach is to initially be quite strict and loosen as ne= eded. > > > > > Here "quite strict" might mean requiring an rcu_assign_pointer() = for > > > > > the write and rcu_dereference() for the read, as opposed to (say) > > > > > ACCESS_ONCE() for the read. (I am guessing that this would be too > > > > > tight, but it makes a good example.) > > > > >=20 > > > > > Thoughts? > > > >=20 > > > > That sounds broadly sensible to me and allows rcu_assign_pointer and > > > > rcu_dereference to be used as drop-in replacements for release/acqu= ire > > > > where local transitivity isn't required. However, I don't think we = can > > > > rule out READ_ONCE/WRITE_ONCE interactions as they seem to be used > > > > already in things like the osq_lock (albeit without the address > > > > dependency). > > >=20 > > > Agreed. So in the most strict case that I can imagine anyone putting > > > up with, we have the following pairings: > >=20 > > I think we can group these up: > >=20 > > Locally transitive: > >=20 > > > o smp_store_release() -> smp_load_acquire() (locally transitive) > >=20 > > Locally transitive chain termination: > >=20 > > (i.e. these can't be used to extend a chain) >=20 > Agreed. >=20 > > > o smp_store_release() -> lockless_dereference() (???) > > > o rcu_assign_pointer() -> rcu_dereference() > > > o smp_store_release() -> READ_ONCE(); if Just want to make sure, this one is actually: o smp_store_release() -> READ_ONCE(); if ; right? Because control dependency only orders READ->WRITE. If so, do we also need to take the following pairing into consideration? o smp_store_release() -> READ_ONCE(); if ;smp_rmb(); >=20 > I am OK with the first and last, but I believe that the middle one > has real use cases. So the rcu_assign_pointer() -> rcu_dereference() > case needs to be locally transitive. >=20 Hmm... I don't think we should differ rcu_dereference() and lockless_dereference(). One reason: list_for_each_entry_rcu() are using lockless_dereference() right now, which means we used to think rcu_dereference() and lockless_dereference() are interchangeable, right? Besides, Will, what's the reason of having a locally transitive chain termination? Because on some architectures RELEASE->DEPENDENCY pairs may not be locally transitive? Regards, Boqun > > Globally transitive: > >=20 > > > o smp_mb(); WRITE_ONCE() -> READ_ONCE(); (globally transitive) > > > o synchronize_rcu(); WRITE_ONCE() -> READ_ONCE(); (globally transitiv= e) > >=20 > > RCU: > >=20 > > > o synchronize_rcu(); WRITE_ONCE() -> rcu_read_lock(); READ_ONCE() > > > (strange and wonderful properties) >=20 > Agreed. >=20 > > > Seem reasonable, or am I missing some? > >=20 > > Looks alright to me. >=20 > So I have some litmus tests to generate. ;-) >=20 > Thnax, Paul >=20 --48TaNjbzBVislYPb Content-Type: application/pgp-signature; name="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQEcBAABCAAGBQJWsDxEAAoJEEl56MO1B/q48fUIALCz18OufCUWhLh5Yn/OLkIR zWSDw59kwtGsIWUTpc8oz5lWGXr2bhb1gozSYOhq7+Qn/0sdLbmMeeVCbVWMekYR rGTOPxzBNk5mu0GaHOFyo4oGRtVflyRqsvPQG0qVui9E1L3fpjAcFICZvAe0dbMp KdZ7DLyqmCNpANhcu7RUAaUNfHLasz/EjPwpY2YTTN7PiJOeLJsYiYle0+fwbg2U vYwhYwDFe2VnilJILJtOYG5Qz2sk/tzIRPoK3RMr0D64XhJj+9MWkDStH94P4kAO Ukja2KlP7nmtcW9/EGkIp4OcXkrU3CuFaE/huRA/3aV/CYERbz76Al9GbEDnA+A= =o422 -----END PGP SIGNATURE----- --48TaNjbzBVislYPb--