From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: KVM: PIC: enhance IPI avoidance Date: Wed, 24 Sep 2008 17:49:37 +0300 Message-ID: <48DA5381.6030301@redhat.com> References: <20080922165749.GA18733@dmt.cnet> <48DA3063.2070402@redhat.com> <20080924144038.GA5991@dmt.cnet> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: kvm-devel To: Marcelo Tosatti Return-path: Received: from mx2.redhat.com ([66.187.237.31]:52687 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752040AbYIXOtm (ORCPT ); Wed, 24 Sep 2008 10:49:42 -0400 Received: from int-mx2.corp.redhat.com (int-mx2.corp.redhat.com [172.16.27.26]) by mx2.redhat.com (8.13.8/8.13.8) with ESMTP id m8OEnfDb017226 for ; Wed, 24 Sep 2008 10:49:41 -0400 In-Reply-To: <20080924144038.GA5991@dmt.cnet> Sender: kvm-owner@vger.kernel.org List-ID: Marcelo Tosatti wrote: > >> and by register load from userspace, no? >> > > Isnt that responsability of the guest? I'm talking about a restore to previous state scenario. In this case we want to disable any IPI avoidance in case it avoids a needed IPI. > Unacked IOAPIC interrupts are not > cleared on register load, are they? > > Good question. I don't know if they should or shouldn't. But that's a different question. isr_ack is not guest visible, so nothing is lost from clearing it, but we can fail if we don't clear it. -- error compiling committee.c: too many arguments to function