From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gleb Natapov Subject: Re: [PATCH] KVM: Implement support for the RH bit Date: Thu, 1 Sep 2011 23:19:00 +0300 Message-ID: <20110901201900.GD26451@redhat.com> References: <1314893135-3839-1-git-send-email-levinsasha928@gmail.com> <20110901174528.GA26451@redhat.com> <1314903592.3992.9.camel@lappy> <20110901193152.GB26451@redhat.com> <1314907111.3992.14.camel@lappy> <20110901200303.GC26451@redhat.com> <1314907500.3992.15.camel@lappy> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: kvm@vger.kernel.org, Avi Kivity , Marcelo Tosatti To: Sasha Levin Return-path: Received: from mx1.redhat.com ([209.132.183.28]:8992 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751703Ab1IAUTZ (ORCPT ); Thu, 1 Sep 2011 16:19:25 -0400 Content-Disposition: inline In-Reply-To: <1314907500.3992.15.camel@lappy> Sender: kvm-owner@vger.kernel.org List-ID: On Thu, Sep 01, 2011 at 11:05:00PM +0300, Sasha Levin wrote: > On Thu, 2011-09-01 at 23:03 +0300, Gleb Natapov wrote: > > On Thu, Sep 01, 2011 at 10:58:31PM +0300, Sasha Levin wrote: > > > By "actual addressing model" I meant checking the ICR of of each APIC to > > > see if we should address it logically or physically. > > > > > This is definitely not what ICR of each APIC is about. > > Thats what I understood from section 10.6.2 in the spec. > Section 10.6.2 talks about ACPI messages generated by a CPU (IPIs) not about addressing mode of the CPU itself (which is, again, per message). -- Gleb.