From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Ahern Subject: Re: help? need to enable VT-d for 2.6.27 Date: Tue, 30 Aug 2011 13:54:37 -0600 Message-ID: <4E5D3FFD.4010002@gmail.com> References: <4E5D0FF3.6030705@genband.com> <4E5D23F5.3070905@gmail.com> <4E5D27B5.8090004@genband.com> <4E5D2C68.2050801@gmail.com> <4E5D3C67.1020908@genband.com> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Avi Kivity , mtosatti@redhat.com, kvm@vger.kernel.org To: Chris Friesen Return-path: Received: from mail-yw0-f46.google.com ([209.85.213.46]:37866 "EHLO mail-yw0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754141Ab1H3Tyl (ORCPT ); Tue, 30 Aug 2011 15:54:41 -0400 Received: by ywf7 with SMTP id 7so5889016ywf.19 for ; Tue, 30 Aug 2011 12:54:40 -0700 (PDT) In-Reply-To: <4E5D3C67.1020908@genband.com> Sender: kvm-owner@vger.kernel.org List-ID: On 08/30/2011 01:39 PM, Chris Friesen wrote: > On 08/30/2011 12:31 PM, David Ahern wrote: >=20 >> In my case I am setting the MAC address for the VFs in the host at b= oot; >> they are getting reset on passthrough so the VM driver creates a ran= dom >> one. A backport of commit a6b5ea3 fixes one aspect. Looking at the c= ode >> for the igb driver I think commit 8fa7e0f fixes the other reset prob= lem. >> >> On the plus side I can tell you that the VF driver for the VM >> http://sourceforge.net/projects/e1000/files/igbvf%20stable/ >> >> compiles cleaning against WRL3 and appears to work fine (limited tes= ting >> with benchmarks). >> >> kernel module wise I ran some basic KVM tests with kvm-kmod-2.6.32.2= 7; I >> have not tried VF passthrough. This is on my radar as well, so I wou= ld >> be interested in what you learn. >=20 > I downloaded the latest kvm-kmod release. It looks interesting, but = it > has some issues: >=20 > 1) I use separate source and build output directories. kvm-kmod assu= mes > that there is a "source" link in my build output directory pointing b= ack > to the source directory. This doesn't exist, so the build breaks. >=20 > 2) If I create such a link, it builds a few files, and then gives the > following: >=20 > /home/cfriesen/Download/kvm-kmod-3.0b/x86/x86.c: In function > =91vcpu_enter_guest=92: > /home/cfriesen/Download/kvm-kmod-3.0b/x86/x86.c:5539:26: error: > =91prof_on=92 undeclared (first use in this function) > /home/cfriesen/Download/kvm-kmod-3.0b/x86/x86.c:5539:26: note: each > undeclared identifier is reported only once for each function it appe= ars in >=20 >=20 > This appears to be due to the fact that KVM_PROFILING is defined > unconditionally in my kernel, but "prof_on" is only defined if > CONFIG_PROFILING is enabled. Commenting out that chunk of code in x8= 6.c > lets everything build. I was a bit nervous trying kmod's from that much ahead of 2.6.27; that'= s why I picked the 2.6.32 train. Also, the notes for adding the device assignment to Fedora 11 might com= e in handy: http://fedoraproject.org/wiki/Features/KVM_PCI_Device_Assignment I have not walked through the bug references yet, but Fedora 11 is not too far ahead of WRL3. When I backported perf to WRL3 I used Fedora 10 as a reference. For VT-d, Fedora 11 would be interesting to look at -- is the support complete in F-11 and if so take a look at its kernel sou= rce. David >=20 > I haven't tried actually loading it yet, that will be next. >=20 > Thanks for the pointer. > Chris >=20 >=20