From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:44256) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Vqm1D-0004RC-PY for qemu-devel@nongnu.org; Wed, 11 Dec 2013 10:48:17 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Vqm17-0007T5-Mz for qemu-devel@nongnu.org; Wed, 11 Dec 2013 10:48:11 -0500 Received: from mx1.redhat.com ([209.132.183.28]:21316) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Vqm17-0007Sw-Ec for qemu-devel@nongnu.org; Wed, 11 Dec 2013 10:48:05 -0500 Received: from int-mx10.intmail.prod.int.phx2.redhat.com (int-mx10.intmail.prod.int.phx2.redhat.com [10.5.11.23]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id rBBFm4iT028904 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK) for ; Wed, 11 Dec 2013 10:48:04 -0500 Date: Wed, 11 Dec 2013 17:51:42 +0200 From: "Michael S. Tsirkin" Message-ID: <20131211155142.GD25814@redhat.com> References: <20131128102652.GA24261@redhat.com> <52A714AC.3050703@redhat.com> <20131210150542.GA27998@amt.cnet> <20131210172144.GA29151@amt.cnet> <20131210210241.GC8476@redhat.com> <20131211134118.GB14071@amt.cnet> <20131211142000.GA23355@redhat.com> <52A87A89.4000901@redhat.com> <20131211153936.GA25814@redhat.com> <52A88794.3030709@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <52A88794.3030709@redhat.com> Subject: Re: [Qemu-devel] [PATCH rebased for-1.8] i386: pc: align gpa<->hpa on 1GB boundary (v6) List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Paolo Bonzini Cc: Marcelo Tosatti , qemu-devel@nongnu.org On Wed, Dec 11, 2013 at 04:41:08PM +0100, Paolo Bonzini wrote: > Il 11/12/2013 16:39, Michael S. Tsirkin ha scritto: > > > 2GB low memory for q35 is a bit wasteful, > > > but we have some time to fix that before release. > > > > How would you fix that? > > Just use 1GB, coupled with reducing the default MMCONFIG size to 128 > buses. > That's already ~40 PCIe devices This is not really enough, people requested more than 40 devices. We will likely need multiroot down the road because some people want more than 256 devices ... > if you count upstream/downstream > ports in addition to the actual device, and you can also use PCIe-to-PCI > bridges if you need more room. > > Paolo We don't want people to use PCI down the road. Everything should be PCIE so we can use things like native hotplug. -- MST