From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932280AbaEIRCq (ORCPT ); Fri, 9 May 2014 13:02:46 -0400 Received: from bombadil.infradead.org ([198.137.202.9]:42013 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757096AbaEIRCo (ORCPT ); Fri, 9 May 2014 13:02:44 -0400 Date: Fri, 9 May 2014 19:02:34 +0200 From: Peter Zijlstra To: Catalin Marinas Cc: James Hogan , "mingo@kernel.org" , Thomas Gleixner , "luto@amacapital.net" , "nicolas.pitre@linaro.org" , "daniel.lezcano@linaro.org" , "umgwanakikbuti@gmail.com" , LKML , Will Deacon , ARM Kernel List Subject: Re: [RFC][PATCH 6/8] sched,idle: Avoid spurious wakeup IPIs Message-ID: <20140509170234.GZ30445@twins.programming.kicks-ass.net> References: <20140411134243.160989490@infradead.org> <20140411135218.478299389@infradead.org> <20140509141520.GV2844@laptop.programming.kicks-ass.net> <20140509144034.GF7950@arm.com> <20140509145002.GW2844@laptop.programming.kicks-ass.net> <20140509145745.GI7950@arm.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="x+IuRATsqV0DV21e" Content-Disposition: inline In-Reply-To: <20140509145745.GI7950@arm.com> User-Agent: Mutt/1.5.21 (2012-12-30) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org --x+IuRATsqV0DV21e Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Fri, May 09, 2014 at 03:57:45PM +0100, Catalin Marinas wrote: > On Fri, May 09, 2014 at 03:50:02PM +0100, Peter Zijlstra wrote: > > On Fri, May 09, 2014 at 03:40:34PM +0100, Catalin Marinas wrote: > >=20 > > > I wonder why we still need TIF_POLLING_NRFLAG for arm64. It was on arm > > > until commit 16a8016372c42c7628eb (sanitize tsk_is_polling()). On arm= 64 > > > we use wfi for idle or a firmware call but in both cases the assumpti= on > > > is that we need an interrupt for waking up. > > >=20 > > > So I think we should remove this macro for arm64. > >=20 > > Does ARM64 support idle=3Dpoll? If so, you could keep it for that, > > otherwise it does indeed appear to be pointless. >=20 > We don't support idle=3Dpoll either. >=20 > > As to 32bit ARM, are there SMP chips which do not have WFI? >=20 > No. WFI is even used for the secondary booting protocol (we need to send > an IPI to get them going). OK, so I'll queue a patch removing TIF_POLLING_NRFLAG for arm64. Thanks! --x+IuRATsqV0DV21e Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.12 (GNU/Linux) iQIcBAEBAgAGBQJTbQoqAAoJEHZH4aRLwOS6NwUQAJHLxoKK86uQfqE8pLwdT7b9 HLu9bzMWYqSMYp2fCPDl1X0m/eKDWY2LdLZN7LauRPc+n4ZFq73bHpMT5Dcyulks 7dsHws/VBKfnc90emGp7mldtEr13u7fIspiTG0cPeQh1aAvcELZ+ucH/OkjQ1UA9 Yy8lba/VLv6Ck993CrDyLDJqLJyF5jmAJii6dGf/day4zZUrA95R43M+eDLv+fV2 1n9DFdzC2HT6/z23Hc6mij1RnuYLw+AbFV3+4W19lMXGijVpJgwrq2APsauZ/1+F yxFgSGRDaJAfkz5qtrMOSL5NXvShco2H0Sj+b83wGhB+YuoIWdSWBIYbXoMkkeL1 uZ8xQyBwTO3Xa6H/g6lssurBSRXP/noZfP22kuY/1bWAWiSlG73MU9rDhCpfkcwY gO9vpTv8XpbZIVxWVd9Ho0zv6w+gGsTlRk2FC/qSa7Qu34suVkOf0C4qiScDTUmw Emf5YgWcpqTUf0cc864tgRX5yARefZlYqg3HP+fdHmvSUUsVkJ13Do4/rkiLQr40 RLcQUsXA7kE8KeeTjNqfiOPdok0wXW2ZMrh2wzYxIk7eguftQ5OoY6XkERrbmn+3 s1kwFRNrKvflL4VnDucXtcYJwnWO5YjMYT83J6kHKunm7gWKbgInSaK4R8c3d31i TgC0gtdTLUC5jf6xVzIO =nOE1 -----END PGP SIGNATURE----- --x+IuRATsqV0DV21e--