Date: Tue, 17 Aug 2010 19:18:17 +0400 From: pluknet <pluknet@gmail.com> To: Jack Vogel <jfvogel@gmail.com> Cc: Jack F Vogel <jfv@freebsd.org>, freebsd-stable <freebsd-stable@freebsd.org> Subject: Re: svn commit: r209611 - head/sys/dev/e1000 Message-ID: <AANLkTinKO1pZKRCaofeUqBdaYoMhp1OUH3Aob2qTQCvV@mail.gmail.com> In-Reply-To: <AANLkTik6fyB9lDn9Qd752onGvq14l9xlUfjUuvAIpTOz@mail.gmail.com> References: <201006301726.o5UHQl7n011935@svn.freebsd.org> <4C2BBC1F.6020405@elischer.org> <AANLkTik6fyB9lDn9Qd752onGvq14l9xlUfjUuvAIpTOz@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On 1 July 2010 02:13, Jack Vogel <jfvogel@gmail.com> wrote: > On Wed, Jun 30, 2010 at 2:50 PM, Julian Elischer <julian@elischer.org>wro= te: > >> On 6/30/10 10:26 AM, Jack F Vogel wrote: >> >>> Author: jfv >>> Date: Wed Jun 30 17:26:47 2010 >>> New Revision: 209611 >>> URL: http://svn.freebsd.org/changeset/base/209611 >>> >>> Log: >>> =A0 SR-IOV support added to igb >>> >>> =A0 What this provides is support for the 'virtual function' >>> =A0 interface that a FreeBSD VM may be assigned from a host >>> =A0 like KVM on Linux, or newer versions of Xen with such >>> =A0 support. >>> >>> =A0 When the guest is set up with the capability, a special >>> =A0 limited function 82576 PCI device is present in its virtual >>> =A0 PCI space, so with this driver installed in the guest that >>> =A0 device will be detected and function nearly like the bare >>> =A0 metal, as it were. >>> >>> =A0 The interface is only allowed a single queue in this configuration >>> =A0 however initial performance tests have looked very good. >>> >>> =A0 Enjoy!! >>> >>> >> do these extra devices turn up in a standard ifconfig output? >> in other words, can we assign them to jails using vimage? >> >> > They only show up if configured in the PF host, for instance if using Lin= ux > and KVM (I did develop and test > with Fedora 13) you must load the igb driver there specifying that you wa= nt > vf's created and how many. > Next in the management of the guest you need to assign one of these vf > devices to the guest. After you > do all that and load this igb driver then yes, it will look just like a > standard igbX device. > Hi, Jack. I set up qemu-kvm on openSUSE 11.3 with 82576 PCI device as you described. Guest fails to attach with: igb0: <Intel(R) PRO/1000 Network Connection version - 2.0.1> mem 0xf2060000-0xf2063fff,0xf2064000-0xf2067fff at device 5.0 on pci0 igb0: Unable to allocate bus resource: interrupt device_attach: igb0 attach returned 6 igb0@pci0:0:5:0: class=3D0x020000 card=3D0xa03c8086 chip=3D0x10ca808= 6 rev=3D0x01 hdr=3D0x00 vendor =3D 'Intel Corporation' class =3D network subclass =3D ethernet cap 11[40] =3D MSI-X supports 3 messages in map 0x1c Did I missed something? --=20 wbr, pluknet
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?AANLkTinKO1pZKRCaofeUqBdaYoMhp1OUH3Aob2qTQCvV>