From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932476Ab0KOOGl (ORCPT ); Mon, 15 Nov 2010 09:06:41 -0500 Received: from one.firstfloor.org ([213.235.205.2]:49469 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932402Ab0KOOGk (ORCPT ); Mon, 15 Nov 2010 09:06:40 -0500 Date: Mon, 15 Nov 2010 15:06:33 +0100 From: Andi Kleen To: Frederic Weisbecker Cc: Jiri Olsa , mingo@elte.hu, rostedt@goodmis.org, andi@firstfloor.org, lwoodman@redhat.com, hch@infradead.org, linux-kernel@vger.kernel.org, Thomas Gleixner Subject: Re: [PATCHv2 2/2] tracing,mm - add kernel pagefault tracepoint for x86 & x86_64 Message-ID: <20101115140632.GI7269@basil.fritz.box> References: <20101110164413.GA5360@nowhere> <1289466549-7602-3-git-send-email-jolsa@redhat.com> <20101115134325.GA5410@nowhere> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20101115134325.GA5410@nowhere> 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 > Actually I don't see any reason right now to trace only kernel faults. Do you? > If that's needed, one can still check on post-processing that the address > was in the kernel. I think the idea is to get more context on oopses. If the event only covers that the overhead in the common case (minus *_user) is much less, versus the more generalized points you use. For tracing the whole page fault me think it's better to have a generalized exception tracer with a filter on page fault. -Andi