From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752572Ab0CYWQN (ORCPT ); Thu, 25 Mar 2010 18:16:13 -0400 Received: from s15228384.onlinehome-server.info ([87.106.30.177]:38562 "EHLO mail.x86-64.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751481Ab0CYWQK (ORCPT ); Thu, 25 Mar 2010 18:16:10 -0400 Date: Thu, 25 Mar 2010 23:16:38 +0100 From: Borislav Petkov To: Thomas Renninger Cc: Valdis.Kletnieks@vt.edu, akpm@linux-foundation.org, davej@redhat.com, linux@dominikbrodowski.net, mingo@elte.hu, hpa@zytor.com, tglx@linutronix.de, cpufreq@vger.kernel.org, x86@kernel.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH 3/5] cpufreq: Add APERF/MPERF support for AMD processors Message-ID: <20100325221638.GA19269@aftab> References: <1269452783-966-1-git-send-email-bp@amd64.org> <201003251043.04867.trenn@suse.de> <13218.1269546919@localhost> <201003252159.31883.trenn@suse.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <201003252159.31883.trenn@suse.de> Organization: Advanced Micro Devices =?iso-8859-1?Q?GmbH?= =?iso-8859-1?Q?=2C_Karl-Hammerschmidt-Str=2E_34=2C_85609_Dornach_bei_M=FC?= =?iso-8859-1?Q?nchen=2C_Gesch=E4ftsf=FChrer=3A_Thomas_M=2E_McCoy=2C_Giuli?= =?iso-8859-1?Q?ano_Meroni=2C_Andrew_Bowd=2C_Sitz=3A_Dornach=2C_Gemeinde_A?= =?iso-8859-1?Q?schheim=2C_Landkreis_M=FCnchen=2C_Registergericht_M=FCnche?= =?iso-8859-1?Q?n=2C?= HRB Nr. 43632 User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Thomas Renninger Date: Thu, Mar 25, 2010 at 09:59:31PM +0100 > On Thursday 25 March 2010 08:55:19 pm Valdis.Kletnieks@vt.edu wrote: > > On Thu, 25 Mar 2010 10:43:04 BST, Thomas Renninger said: > > > > + if (c->cpuid_level >= 6) { > > > > > > and remove this (arch/x86/kernel/cpu/intel.c): > > > if (c->cpuid_level > 6) { > > > > So is > or >= the correct comparator here? > > This one: >= is correct (for both). > I double checked, there is one Intel CPU type > having a cpuid_level of 6, but this would not support aperf/mperf, thus > above is still fine. Agreed. ">" won't work on machines which have base cpuidlevel == 6 (like AMD, f.e.) > The remaining question is what Borislav said: > are there other x86 CPU vendors who could use this differently. > I very much expect there are not. > > IMO you should resubmit this one or the whole series with this change Ok, will do tomorrow. > and Dave should just push this in his tree and queue it up, there was enough > time to object. The problem here is that the patches touch both cpufreq and x86 code. Hmmm... -- Regards/Gruss, Boris. -- Advanced Micro Devices, Inc. Operating Systems Research Center