From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: nmi_watchdog fix for x86_64 to be more like i386 Date: Mon, 1 Oct 2007 21:16:59 +0200 Message-ID: <200710012116.59356.ak@suse.de> References: <46FA4A800200006C000192FE@sinclair.provo.novell.com> <200710011936.01528.ak@suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Cc: David Bahi , linux-kernel@vger.kernel.org, linux-rt-users@vger.kernel.org, Gregory Haskins To: Thomas Gleixner Return-path: Received: from mail.suse.de ([195.135.220.2]:53005 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751365AbXJATRG (ORCPT ); Mon, 1 Oct 2007 15:17:06 -0400 In-Reply-To: Content-Disposition: inline Sender: linux-rt-users-owner@vger.kernel.org List-Id: linux-rt-users.vger.kernel.org On Monday 01 October 2007 20:54:21 Thomas Gleixner wrote: > On Mon, 1 Oct 2007, Andi Kleen wrote: > > > On Wednesday 26 September 2007 20:03:12 David Bahi wrote: > > > Thanks to tglx and ghaskins for all the help in tracking down a very > > > early nmi_watchdog crash on certain x86_64 machines. > > > > The patch is totally bogus. irq 0 doesn't say anything about whether > > the current CPU still works or not. You always need some local > > interrupt. This basically disables the NMI watchdog for the non boot CPUs. > > > > It's even wrong on i386 -- i wonder how that broken patch > > made it in there. I'll remove it there. > > Right, it's wrong for the broadcast case, but simply removing it will > trigger false positives on the CPU which runs the broadcast timer. I > fix this proper. I already did this here by checking for cpu != 0. But it also needs either tracking or forbidding migrations of irq 0. I can take care of the patch. -Andi