From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH] x86, nmi: workaround sti; hlt race vs nmi; intr Date: Mon, 27 Sep 2010 11:17:59 +0200 Message-ID: <4CA06147.7080805@redhat.com> References: <1284913699-14986-1-git-send-email-avi@redhat.com> <4CA057EA.7000609@redhat.com> <768A5DC0-131A-4BC8-ADDD-044D8169545E@suse.de> <61284934-1AD3-4F7A-9488-D46FCEE9B753@suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: x86@kernel.org, linux-kernel@vger.kernel.org, kvm@vger.kernel.org To: Alexander Graf Return-path: Received: from mx1.redhat.com ([209.132.183.28]:50169 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758951Ab0I0JSH (ORCPT ); Mon, 27 Sep 2010 05:18:07 -0400 In-Reply-To: <61284934-1AD3-4F7A-9488-D46FCEE9B753@suse.de> Sender: kvm-owner@vger.kernel.org List-ID: On 09/27/2010 11:15 AM, Alexander Graf wrote: > > > > Wow, this is incredibly ugly :). Can't we just mask NMIs when the interrupt shadow is active? I plan to do that, for all the code that's out there relying on on STI interrupt shadow masking NMIs. > Yeah, that's me writing without thinking. So this means that the race can also happen on real hardware? > Yes. At least on documented hardware. Some (most? all?) hardware does mask NMIs after STI. -- error compiling committee.c: too many arguments to function