From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: Inter VM Communication Date: Wed, 25 Mar 2009 08:44:39 +0200 Message-ID: <49C9D2D7.7030501@redhat.com> References: <3D9CB4061D1EB3408D4A0B910433453C030275936E@inbmail01.lsi.com> <49C8D5D1.3010902@redhat.com> <49C99495.5070005@codemonkey.ws> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: "Kumar, Venkat" , "kvm@vger.kernel.org" To: Anthony Liguori Return-path: Received: from mx2.redhat.com ([66.187.237.31]:43692 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754481AbZCYGoJ (ORCPT ); Wed, 25 Mar 2009 02:44:09 -0400 In-Reply-To: <49C99495.5070005@codemonkey.ws> Sender: kvm-owner@vger.kernel.org List-ID: Anthony Liguori wrote: > So one gotcha about using a BAR is that we emulate a 32-bit PCI device > so that limits where the BAR can live in memory and how large it can be. We can overcome that by emulating a 64-bit device... > I think bars also have to be powers of two in size. I think that's right; but the device can define the the range [0, X) as shared RAM and the range [X, 2^n) as undefined. So long as it makes X available in the config space. Besides, computer people have trouble imagining numbers which are not powers of two. -- I have a truly marvellous patch that fixes the bug which this signature is too narrow to contain.