[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-users] pciback or pci-stub with VT-d and SR-IOV
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pcieport 0000:00:06.0: TLP Header: 60000001 0a801e0f cbe2cef5 be7d5ad4 so I'm guessing that that info is old and outdated.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
|
Lists.xenproject.org is hosted with RackSpace, monitoring our |