From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760471Ab2BNNLS (ORCPT ); Tue, 14 Feb 2012 08:11:18 -0500 Received: from merlin.infradead.org ([205.233.59.134]:60280 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1760196Ab2BNNLR (ORCPT ); Tue, 14 Feb 2012 08:11:17 -0500 Date: Tue, 14 Feb 2012 11:10:46 -0200 From: Arnaldo Carvalho de Melo To: Joerg Roedel Cc: David Ahern , Namhyung Kim , Namhyung Kim , linux-kernel@vger.kernel.org, Ingo Molnar , Andi Kleen , Anshuman Khandual , Arun Sharma , Corey Ashford , Frederic Weisbecker , Jason Wang , Jiri Olsa , Lin Ming , Paul Mackerras , Peter Zijlstra , Roberto Agostino Vitillo , Robert Richter , Stephane Eranian , Thomas Gleixner , Vince Weaver Subject: Re: [GIT PULL 00/16] perf/core improvements and fixes Message-ID: <20120214131046.GA28614@infradead.org> References: <1329184375-27911-1-git-send-email-acme@infradead.org> <4F39CBE0.6050806@gmail.com> <4F39D00D.2060206@gmail.com> <4F39ECDB.5090609@lge.com> <4F39EFBB.2010301@gmail.com> <20120214105018.GV22598@amd.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20120214105018.GV22598@amd.com> X-Url: http://acmel.wordpress.com User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Em Tue, Feb 14, 2012 at 11:50:18AM +0100, Joerg Roedel escreveu: > On Mon, Feb 13, 2012 at 10:23:07PM -0700, David Ahern wrote: > > On 2/13/12 10:10 PM, Namhyung Kim wrote: > > >It happened because I used old kernel version that isn't aware of the > > >exclude_guest bit. So the check on attr->__reserved_1 in > > >core.c::perf_copy_attr() failed and then ended up seeing EINVAL at > > >perf_evsel__open(). > > comes back to 1aed2671738785e8f5aea663a6fda91aa7ef59b5 again. See > > https://lkml.org/lkml/2012/2/8/234 > Grr. I totally forgot that issue. Is there some way to detect the perf > kernel-features? Otherwise the only fix seems to be to drop the patch > changing the default. The crashes should be fixed by the other patch > already. Well, we need to detect it like we do with sample_id_all. In this case we would try with exclude_guest, if it fails with EINVAL, we realise it is not available, clean that bit and try again. - Arnaldo