From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752045Ab0CTVh5 (ORCPT ); Sat, 20 Mar 2010 17:37:57 -0400 Received: from cantor.suse.de ([195.135.220.2]:59947 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751154Ab0CTVhy (ORCPT ); Sat, 20 Mar 2010 17:37:54 -0400 From: Thomas Renninger To: Robert =?utf-8?q?Sch=C3=B6ne?= Subject: Re: [PATCH] trace power_frequency events on the correct cpu (for Intel x86 CPUs) Date: Sat, 20 Mar 2010 22:37:56 +0100 User-Agent: KMail/1.9.10 Cc: Arjan van de Ven , Dave Jones , Thomas Gleixner , Ingo Molnar , "linux-kernel" , cpufreq , x86@kernel.org References: <1268399863.3407.15.camel@localhost> <201003182143.22929.trenn@suse.de> <1268985679.3395.47.camel@localhost> In-Reply-To: <1268985679.3395.47.camel@localhost> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <201003202237.57477.trenn@suse.de> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > This wrapper would make things easier of course, since one might add the > same line for every driver ... It's simply broken and can't be fixed without chaninging the whole concept. power_frequency_events() must not only pass the cpu, but a cpumask also for acpi-cpufreq. If you look at SW_ANY SW_ALL (or similar, I can't look at code right now) parts, acpi-cpufreq can change the frequency for several cores with one MSR write. AFAIK this is for example the recommended way for Dunnington (6 cores). So the collected data can be totally wrong. Better remove this before others also start to use it. It also seem to be (hopefully) a minor feature for timechart, so this should not hurt that much (yet). Thomas