From mboxrd@z Thu Jan 1 00:00:00 1970 From: Yang Zhang Subject: Re: VFIO based vGPU(was Re: [Announcement] 2015-Q3 release of XenGT - a Mediated ...) Date: Wed, 27 Jan 2016 09:34:46 +0800 Message-ID: <56A81EB6.9070106@gmail.com> References: <569C5071.6080004@intel.com> <1453092476.32741.67.camel@redhat.com> <569CA8AD.6070200@intel.com> <1453143919.32741.169.camel@redhat.com> <569F4C86.2070501@intel.com> <56A6083E.10703@intel.com> <1453757426.32741.614.camel@redhat.com> <56A72313.9030009@intel.com> <56A77D2D.40109@gmail.com> <56A809F5.6010001@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Cc: Alex Williamson , "Tian, Kevin" , Gerd Hoffmann , Paolo Bonzini , "Lv, Zhiyuan" , "Ruan, Shuai" , "kvm@vger.kernel.org" , qemu-devel , "igvt-g@lists.01.org" , Neo Jia To: Jike Song Return-path: Received: from mail-pf0-f193.google.com ([209.85.192.193]:35875 "EHLO mail-pf0-f193.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751346AbcA0Bew (ORCPT ); Tue, 26 Jan 2016 20:34:52 -0500 Received: by mail-pf0-f193.google.com with SMTP id n128so8871731pfn.3 for ; Tue, 26 Jan 2016 17:34:52 -0800 (PST) In-Reply-To: <56A809F5.6010001@intel.com> Sender: kvm-owner@vger.kernel.org List-ID: On 2016/1/27 8:06, Jike Song wrote: > On 01/26/2016 10:05 PM, Yang Zhang wrote: >> On 2016/1/26 15:41, Jike Song wrote: >> >>> We will need to extend: >>> >>> - VFIO_DEVICE_GET_REGION_INFO >>> >>> >>> a) adding a flag: DONT_MAP. For example, the MMIO of vgpu >>> should be trapped instead of being mmap-ed. >> >> I may not in the context, but i am curious how to handle the DONT_MAP in >> vfio driver? Since there are no real MMIO maps into the region and i >> suppose the access to the region should be handled by vgpu in i915 >> driver, but currently most of the mmio accesses are handled by Qemu. >> > > Hi Yang, > > MMIO accesses are supposed to be handled in kernel, without vm-exiting > to QEMU, similar to in-kernel irqchip :) The question is current vfio doesn't support it. The long discussion between Alex and Kevin is what i am to understand how KVMGT works under vfio framework. -- best regards yang From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:40128) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1aOF0c-0005qe-8E for qemu-devel@nongnu.org; Tue, 26 Jan 2016 20:34:59 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1aOF0X-0006f9-5T for qemu-devel@nongnu.org; Tue, 26 Jan 2016 20:34:58 -0500 Received: from mail-pf0-x241.google.com ([2607:f8b0:400e:c00::241]:34624) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1aOF0W-0006f4-UN for qemu-devel@nongnu.org; Tue, 26 Jan 2016 20:34:53 -0500 Received: by mail-pf0-x241.google.com with SMTP id 65so8888849pfd.1 for ; Tue, 26 Jan 2016 17:34:52 -0800 (PST) References: <569C5071.6080004@intel.com> <1453092476.32741.67.camel@redhat.com> <569CA8AD.6070200@intel.com> <1453143919.32741.169.camel@redhat.com> <569F4C86.2070501@intel.com> <56A6083E.10703@intel.com> <1453757426.32741.614.camel@redhat.com> <56A72313.9030009@intel.com> <56A77D2D.40109@gmail.com> <56A809F5.6010001@intel.com> From: Yang Zhang Message-ID: <56A81EB6.9070106@gmail.com> Date: Wed, 27 Jan 2016 09:34:46 +0800 MIME-Version: 1.0 In-Reply-To: <56A809F5.6010001@intel.com> Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] VFIO based vGPU(was Re: [Announcement] 2015-Q3 release of XenGT - a Mediated ...) List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Jike Song Cc: "Ruan, Shuai" , "Tian, Kevin" , Neo Jia , "kvm@vger.kernel.org" , "igvt-g@lists.01.org" , qemu-devel , Alex Williamson , "Lv, Zhiyuan" , Paolo Bonzini , Gerd Hoffmann On 2016/1/27 8:06, Jike Song wrote: > On 01/26/2016 10:05 PM, Yang Zhang wrote: >> On 2016/1/26 15:41, Jike Song wrote: >> >>> We will need to extend: >>> >>> - VFIO_DEVICE_GET_REGION_INFO >>> >>> >>> a) adding a flag: DONT_MAP. For example, the MMIO of vgpu >>> should be trapped instead of being mmap-ed. >> >> I may not in the context, but i am curious how to handle the DONT_MAP in >> vfio driver? Since there are no real MMIO maps into the region and i >> suppose the access to the region should be handled by vgpu in i915 >> driver, but currently most of the mmio accesses are handled by Qemu. >> > > Hi Yang, > > MMIO accesses are supposed to be handled in kernel, without vm-exiting > to QEMU, similar to in-kernel irqchip :) The question is current vfio doesn't support it. The long discussion between Alex and Kevin is what i am to understand how KVMGT works under vfio framework. -- best regards yang