From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756943AbYDUPVb (ORCPT ); Mon, 21 Apr 2008 11:21:31 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751486AbYDUPVX (ORCPT ); Mon, 21 Apr 2008 11:21:23 -0400 Received: from tomts5.bellnexxia.net ([209.226.175.25]:55302 "EHLO tomts5-srv.bellnexxia.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751086AbYDUPVX (ORCPT ); Mon, 21 Apr 2008 11:21:23 -0400 X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: AsAFAA1ODEhMROPA/2dsb2JhbACBUakB Date: Mon, 21 Apr 2008 11:21:20 -0400 From: Mathieu Desnoyers To: "H. Peter Anvin" Cc: Pavel Machek , mingo@elte.hu, akpm@osdl.org, Jeremy Fitzhardinge , Steven Rostedt , "Frank Ch. Eigler" , linux-kernel@vger.kernel.org Subject: Re: [RFC PATCH] x86 NMI-safe INT3 and Page Fault (v5) Message-ID: <20080421152120.GA7159@Krystal> References: <20080417165839.GA25198@Krystal> <20080417165944.GB25198@Krystal> <20080417201410.GB31616@Krystal> <20080421140054.GB4685@ucw.cz> <480CA337.3090709@zytor.com> <20080421150825.GA4070@Krystal> <480CADD3.3010209@zytor.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline In-Reply-To: <480CADD3.3010209@zytor.com> X-Editor: vi X-Info: http://krystal.dyndns.org:8080 X-Operating-System: Linux/2.6.21.3-grsec (i686) X-Uptime: 11:18:16 up 52 days, 11:29, 5 users, load average: 0.42, 0.33, 0.31 User-Agent: Mutt/1.5.16 (2007-06-11) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * H. Peter Anvin (hpa@zytor.com) wrote: > Mathieu Desnoyers wrote: >> Just to be clear : the added cost on normal interrupt return is to add a >> supplementary test of the thread flags already loaded in registers and >> a conditional branch. This is used to detect if we are nested over an >> NMI handler. I doubt anyone ever notice an impact caused by this added >> test/branch. > > Why the **** would you do this except in the handful of places where you > actually *could* be nested over an NMI handler (basically #MC, #DB and > INT3)? > > -hpa > Because I would have to do a more invasive code modification, since they currently share their return path with normal interrupts. I agree that the next step is to tune the patchset to only target traps and exceptions which may happen on top of an NMI. I'll change it in my next patchset version. Mathieu -- Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68