From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:39028) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bWgWS-0008He-II for qemu-devel@nongnu.org; Mon, 08 Aug 2016 05:07:02 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1bWgWL-0008KG-EA for qemu-devel@nongnu.org; Mon, 08 Aug 2016 05:06:59 -0400 Received: from mx1.redhat.com ([209.132.183.28]:35192) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bWgWL-0008KA-8v for qemu-devel@nongnu.org; Mon, 08 Aug 2016 05:06:53 -0400 Date: Mon, 8 Aug 2016 17:06:48 +0800 From: Peter Xu Message-ID: <20160808090648.GI3825@pxdev.xzpeter.org> References: <1469123413-20809-1-git-send-email-mst@redhat.com> <1469123413-20809-30-git-send-email-mst@redhat.com> <98a5a157-ba83-bc61-df7e-546c21e23ad3@siemens.com> <20160802083648.GJ6207@pxdev.xzpeter.org> <4fcaa50f-6c09-f607-1c49-8494ec32f0c5@siemens.com> <20160802102838.GK6207@pxdev.xzpeter.org> <20160802121202.GL6207@pxdev.xzpeter.org> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline In-Reply-To: Subject: Re: [Qemu-devel] [PULL v5 29/57] intel_iommu: add SID validation for IR List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: David Kiarie Cc: Jan Kiszka , QEMU Developers , "Michael S. Tsirkin" , Peter Maydell , Richard Henderson , Eduardo Habkost , Paolo Bonzini , Valentine Sinitsyn On Tue, Aug 02, 2016 at 03:17:20PM +0300, David Kiarie wrote: > On Tue, Aug 2, 2016 at 3:12 PM, Peter Xu wrote: > > > On Tue, Aug 02, 2016 at 02:58:55PM +0300, David Kiarie wrote: > > > > Sure. David, so do you like to do it or I cook this patch? :) > > > > > > If there are no objections I will look at this employing Jan's approach: > > > associating a write with an address space. > > > > Do you mean to translate current stl_le_phys() into something like > > address_space_stl_le(), with MemTxAttrs? (in ioapic_service()) > > > > I tried doing something like that but the write gets discarded somewhere. I > don't see the write from IOMMU side. Hi, Jan, David, Sorry to respond late, but what's the version of your guest kernel? I suspect there is bug in guest IOMMU codes with IR on EOI handling, and maybe you can try to boost IOAPIC version to 0x20 when with old kernels using "-global ioapic.version=0x20". Thanks, -- peterx