From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756781AbaGWHQy (ORCPT ); Wed, 23 Jul 2014 03:16:54 -0400 Received: from mga11.intel.com ([192.55.52.93]:38028 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755829AbaGWHQx (ORCPT ); Wed, 23 Jul 2014 03:16:53 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.01,715,1400050800"; d="scan'208";a="565903758" Message-ID: <53CF6121.3050500@intel.com> Date: Wed, 23 Jul 2014 10:15:45 +0300 From: Adrian Hunter Organization: Intel Finland Oy, Registered Address: PL 281, 00181 Helsinki, Business Identity Code: 0357606 - 4, Domiciled in Helsinki User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.6.0 MIME-Version: 1.0 To: Peter Zijlstra CC: Arnaldo Carvalho de Melo , linux-kernel@vger.kernel.org, David Ahern , Frederic Weisbecker , Jiri Olsa , Namhyung Kim , Paul Mackerras , Stephane Eranian Subject: Re: [PATCH 01/52] perf tools: Fix jump label always changing during tracing References: <1406035081-14301-1-git-send-email-adrian.hunter@intel.com> <1406035081-14301-2-git-send-email-adrian.hunter@intel.com> <20140722140034.GE20303@kernel.org> <20140722141135.GF3935@laptop> <53CF5124.2090901@intel.com> <20140723065822.GN3935@laptop> In-Reply-To: <20140723065822.GN3935@laptop> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 07/23/2014 09:58 AM, Peter Zijlstra wrote: > On Wed, Jul 23, 2014 at 09:07:32AM +0300, Adrian Hunter wrote: >> On 07/22/2014 05:11 PM, Peter Zijlstra wrote: >>> On Tue, Jul 22, 2014 at 11:00:34AM -0300, Arnaldo Carvalho de Melo wrote: >>>> Em Tue, Jul 22, 2014 at 04:17:10PM +0300, Adrian Hunter escreveu: >>>>> Intel PT decoding walks the object code to reconstruct >>>>> the trace. A jump label change during tracing causes >>>>> decoding errors. >>> >>> You'd better fix that, jump_labels can change any time and they're all >>> over the frigging place. >>> >> >> Perhaps a general method is needed to be able to deal with kernel >> self-modifying code. > > I know people are looking at doing the same to userspace, is that also a > problem? Yes, most significantly JIT-compiled code.