From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753171AbbBWSmq (ORCPT ); Mon, 23 Feb 2015 13:42:46 -0500 Received: from mx1.redhat.com ([209.132.183.28]:45355 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752564AbbBWSmp (ORCPT ); Mon, 23 Feb 2015 13:42:45 -0500 Date: Mon, 23 Feb 2015 19:40:52 +0100 From: Oleg Nesterov To: Rik van Riel Cc: Borislav Petkov , Andy Lutomirski , x86@kernel.org, linux-kernel@vger.kernel.org Subject: Re: [RFC PATCH] x86, fpu: Use eagerfpu by default on all CPUs Message-ID: <20150223184052.GA21067@redhat.com> References: <20150223145929.GA10342@redhat.com> <20150223151137.GC22753@pd.tnic> <54EB4CEA.3030801@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <54EB4CEA.3030801@redhat.com> User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 02/23, Rik van Riel wrote: > > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA1 > > On 02/23/2015 10:11 AM, Borislav Petkov wrote: > > On Mon, Feb 23, 2015 at 03:59:29PM +0100, Oleg Nesterov wrote: > >> Well, but if we want this change then perhaps we should simply > >> change the default value? This way "AUTO" still can work. > > > > Yeah, sure, let's do some measurements first, to see whether this > > is even worth it. > > > > Btw, Mel pointed me at some cleanups he did a while ago in that > > area too: https://lkml.org/lkml/2014/8/6/201 > > > > If you guys could take a look, that would be awesome :) > > I don't think any of those changes would survive the > "defer FPU loading to do_notify_resume" patch series. Agreed, at least +static inline void switch_eagerfpu_prepare(struct task_struct *old, struct task_struct *new, int cpu, + fpu_switch_t *fpu) +{ + fpu->preload = tsk_used_math(new); doesn't look right if we change the rules. OTOH, perhaps it makes sense to redo these cleanups later. Oleg.