From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754026Ab0C0Vef (ORCPT ); Sat, 27 Mar 2010 17:34:35 -0400 Received: from one.firstfloor.org ([213.235.205.2]:38051 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753987Ab0C0Vee (ORCPT ); Sat, 27 Mar 2010 17:34:34 -0400 To: Peter Zijlstra Cc: Ingo Molnar , LKML , Stephane Eranian Subject: Re: [PATCH] perf, x86: Add Nehelem PMU programming errata workaround From: Andi Kleen References: <1269608924.12097.147.camel@laptop> Date: Sat, 27 Mar 2010 22:27:55 +0100 In-Reply-To: <1269608924.12097.147.camel@laptop> (Peter Zijlstra's message of "Fri, 26 Mar 2010 14:08:44 +0100") Message-ID: <87aattpi90.fsf@basil.nowhere.org> User-Agent: Gnus/5.1008 (Gnus v5.10.8) Emacs/22.3 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Peter Zijlstra writes: > Subject: perf, x86: Add Nehelem PMU programming errata workaround > From: Peter Zijlstra > Date: Fri Mar 26 13:59:41 CET 2010 > > Implement the workaround for Intel Errata AAK100 and AAP53. > > Also, remove the Core-i7 name for Nehalem events since there are also > Westmere based i7 chips. Did you actually see this happen? It looks like this will make the context switch into a perf enabled process _MUCH_ more expensive, MSR writes are very slow. -Andi -- ak@linux.intel.com -- Speaking for myself only.