From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gleb Natapov Subject: Re: [PATCH 0/1] x2apic implementation for kvm Date: Mon, 25 May 2009 09:13:23 +0300 Message-ID: <20090525061323.GB3948@redhat.com> References: <1242927475-6140-1-git-send-email-gleb@redhat.com> <200905251408.26870.sheng@linux.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: kvm@vger.kernel.org To: Sheng Yang Return-path: Received: from mx2.redhat.com ([66.187.237.31]:40906 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751471AbZEYGNY (ORCPT ); Mon, 25 May 2009 02:13:24 -0400 Content-Disposition: inline In-Reply-To: <200905251408.26870.sheng@linux.intel.com> Sender: kvm-owner@vger.kernel.org List-ID: On Mon, May 25, 2009 at 02:08:26PM +0800, Sheng Yang wrote: > On Friday 22 May 2009 01:37:53 Gleb Natapov wrote: > > This is implementation of x2apic for KVM that I wrote a while ago. > > Unfortunately there is no guest that can take advantage of it since > > Linux doesn't (yet?) use x2apic if interrupt remapping is not enabled > > and I don't feel like implement interrupt remapping device :) > > > > Re-based to latest kvm tree for your viewing pleasure and feedback. > > Yeah... x2apic is for interrupt remapping, and interrupt remapping is for VT-d > engine. So if we don't want to virtualize VT-d engine and interrupt remapping, > x2apic is useless for the guest... And VT-d engine(and related things) > virtualization is far from our scope now... > Can you explain why "x2apic is for interrupt remapping"? I can understand why interrupt remapping is needed to use x2apic in certain circumstances (apic ids > 256). x2apic has better virtualizable interface and that is why we want to emulate it. Can you name one technical reason why it can't be done in a context of KVM? -- Gleb.