From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757761AbbBFQmq (ORCPT ); Fri, 6 Feb 2015 11:42:46 -0500 Received: from mx1.redhat.com ([209.132.183.28]:36492 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752315AbbBFQmo (ORCPT ); Fri, 6 Feb 2015 11:42:44 -0500 Message-ID: <54D4EEF5.2020901@redhat.com> Date: Fri, 06 Feb 2015 11:42:29 -0500 From: Rik van Riel User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.3.0 MIME-Version: 1.0 To: Oleg Nesterov CC: dave.hansen@linux.intel.com, sbsiddha@gmail.com, luto@amacapital.net, tglx@linutronix.de, mingo@redhat.com, hpa@zytor.com, fenghua.yu@intel.com, x86@kernel.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH 4/6] x86,fpu: use disable_task_lazy_fpu_restore helper References: <20150129210723.GA31584@redhat.com> <1422900051-10778-1-git-send-email-riel@redhat.com> <1422900051-10778-5-git-send-email-riel@redhat.com> <20150202192139.GA17624@redhat.com> In-Reply-To: <20150202192139.GA17624@redhat.com> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 On 02/02/2015 02:21 PM, Oleg Nesterov wrote: > I'll try to read this patch tomorrow. Too late for me. > > I think it is fine, but > > On 02/02, riel@redhat.com wrote: >> >> This also fixes the lazy FPU restore disabling in drop_fpu, >> which only really works when !use_eager_fpu(). ... >> >> --- a/arch/x86/include/asm/fpu-internal.h +++ >> b/arch/x86/include/asm/fpu-internal.h @@ -396,7 +396,7 @@ static >> inline void drop_fpu(struct task_struct *tsk) * Forget >> coprocessor state.. */ preempt_disable(); - >> tsk->thread.fpu_counter = 0; + >> task_disable_lazy_fpu_restore(tsk); __drop_fpu(tsk); >> clear_used_math(); > > perhaps this makes sense anyway, but I am not sure if the changelog > is right. > > Note that we clear PF_USED_MATH, last_fpu/has_fpu have no effect > after this. After a few days on the RCU code, I'm back to this :) You are right, I should drop the change above from the patch, and disable lazy fpu restore explicitly in places where we need it. I will send a v2 of these patches, without patch 6/6. Ingo, would you like me to also re-send Oleg's FPU patches that are not in -tip yet? - -- All rights reversed -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQEcBAEBAgAGBQJU1O71AAoJEM553pKExN6DUtEH/R8X02MHD7GUxO4hyiLECL9f SQDdF1l+1rqcQo7e+5nRJ5/rFvAIaNA5oBMOZJ9MlJRd6HOKS+VqLLpb8idvApeK zRiYUdeyoui3e0po2nNCx/GBfXqMYca+qH4JMMq6gzv0c9Nm9Zq9pbKDbO2znns8 10YQexvZsHUiJgt63YoZSwxFKD1iAhnTOGBhZOJu/s27Qtu+7gyuyIcuMMDFj2eu ACGqZPcjG2u7TlC+D4uivSferMrduNnWsxGq3AY32/nNhjKGmXaFJxRHDdCsYAGJ +S+SFuUWq6JoD7MuC02NQyAs/bQzqhVfn8v7gm2gromqIIQGzBABtI+Em0LGFP4= =3R+T -----END PGP SIGNATURE-----