WARNING - OLD ARCHIVES

This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
   
 
 
Xen 
 
Home Products Support Community News
 
   
 

xen-users

[Xen-users] pciback or pci-stub with VT-d and SR-IOV

To: xen-users@xxxxxxxxxxxxxxxxxxx
Subject: [Xen-users] pciback or pci-stub with VT-d and SR-IOV
From: dmw <dwhite@xxxxxxxxxxxxx>
Date: Tue, 15 Feb 2011 18:11:14 -0800 (PST)
Delivery-date: Tue, 15 Feb 2011 18:12:41 -0800
Envelope-to: www-data@xxxxxxxxxxxxxxxxxxx
List-help: <mailto:xen-users-request@lists.xensource.com?subject=help>
List-id: Xen user discussion <xen-users.lists.xensource.com>
List-post: <mailto:xen-users@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/mailman/listinfo/xen-users>, <mailto:xen-users-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-users>, <mailto:xen-users-request@lists.xensource.com?subject=unsubscribe>
Sender: xen-users-bounces@xxxxxxxxxxxxxxxxxxx
Hi all,

Should I be using pciback or pci-stub driver for SR-IOV mapping to HVMs
under xen 4.0.1 and pv_ops dom0 2.6.32.27 (from jeremy's git repo)

pciback works for physical devices in my setup.  my network interfaces
are up and can rx/tx pkts out to the network.   but pciback doesn't work
for my virtual devices.  my HVMs see the device, load the igbvf driver
but can't get out to the network.  ethtool shows no link, 'ip link show'
gives link state of UNKNOWN.

according to http://lxr.xensource.com/lxr/source/docs/misc/vtd.txt#L48
I should be using pci-stub for pv-ops dom0 (4.0.x) and kernel 2.6.30+,
but I'm getting bus errors when doing that.

pcieport 0000:00:06.0: AER: Uncorrected (Non-Fatal) error received: id=0030
pcieport 0000:00:06.0: PCIE Bus Error: severity=Uncorrected (Non-Fatal),
type=Transaction Layer, id=0030(Requester ID)
pcieport 0000:00:06.0:   device [8086:340d] error
status/mask=00100000/00000000
pcieport 0000:00:06.0:    [20] Unsupported Request    (First)
pcieport 0000:00:06.0:   TLP Header: 60000001 0a801e0f cbe2cef5 be7d5ad4

so I'm guessing that that info is old and outdated.

when I use pciback, the pci device appears in the hvm as this:

root@mav64a-hvm:~# ethtool -i eth0
driver: igbvf
version: 1.0.0-k0
firmware-version: N/A
bus-info: 0000:00:04.0

root@mav64a-hvm:~# ethtool eth0
Settings for eth0:
     Supported ports: [ ]
     Supported link modes:   1000baseT/Full
     Supports auto-negotiation: No
     Advertised link modes:  1000baseT/Full
     Advertised pause frame use: No
     Advertised auto-negotiation: No
     Speed: 1000Mb/s
     Duplex: Full
     Port: Other
     PHYAD: 0
     Transceiver: Unknown!
     Auto-negotiation: off
     Supports Wake-on: d
     Wake-on: d
     Current message level: 0x00000001 (1)
     Link detected: no

root@mav64a-hvm:~# ip link show eth0
2: eth0: <BROADCAST,MULTICAST,UP> mtu 1500 qdisc pfifo_fast state
UNKNOWN qlen 1000
     link/ether 46:4a:1f:68:c1:3c brd ff:ff:ff:ff:ff:ff

and I have no network access. the physical interface is up, with link, on my
dom0.

Any ideas?

_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users

<Prev in Thread] Current Thread [Next in Thread>
  • [Xen-users] pciback or pci-stub with VT-d and SR-IOV, dmw <=