From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S261929AbTLPQu6 (ORCPT ); Tue, 16 Dec 2003 11:50:58 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S261936AbTLPQu6 (ORCPT ); Tue, 16 Dec 2003 11:50:58 -0500 Received: from jurand.ds.pg.gda.pl ([153.19.208.2]:19350 "EHLO jurand.ds.pg.gda.pl") by vger.kernel.org with ESMTP id S261929AbTLPQu4 (ORCPT ); Tue, 16 Dec 2003 11:50:56 -0500 Date: Tue, 16 Dec 2003 17:50:54 +0100 (CET) From: "Maciej W. Rozycki" To: "Richard B. Johnson" Cc: George Anzinger , Linux kernel Subject: Re: Catching NForce2 lockup with NMI watchdog In-Reply-To: Message-ID: References: <3FD5F9C1.5060704@nishanet.com> <3FDA40DA.20409@mvista.com> <3FDE2AC6.30902@mvista.com> Organization: Technical University of Gdansk MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 16 Dec 2003, Richard B. Johnson wrote: > Although I haven't looked at recent source-code, with APIC, the > problem is even simpler. If you booted with APIC, just set > the global "using_apic_timer" to zero and, voila`, timer-ticks > stop. Except we are writing of the 8254 timer, not the local APIC one... > ...the machine will lock-up forever because without that timer, > there will be no preemption. Once a CPU-hog gets the CPU, only > and interrupt can get it away. And the 8254 timer isn't used for preemption when local APICs are used, so disabling it won't break the whole system, only the timekeeping. -- + Maciej W. Rozycki, Technical University of Gdansk, Poland + +--------------------------------------------------------------+ + e-mail: macro@ds2.pg.gda.pl, PGP key available +