> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Dey, Souvik
> Sent: Friday, May 29, 2015 1:22 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] Unable to bind Virtio_pci in DPDK1.7
>
> Hi All,
> I am currently facing a weird issue where I am not able to
> bind the
> virtio_pci device to igb_uio in DPDK1.7 on QEMU/KVM. I can see there are
> two fold issues.
> 1.The pci_unbind.py script where the virt_path is removed from 1.6 to 1.7
> version due to which the initial status is not able to show any interface
> name.
>
> Network devices using DPDK-compatible driver
>
>
>
> Network devices using kernel driver
> ===
> :00:03.0 'Virtio network device' if= drv=virtio-pci
> unused=virtio_pci,igb_uio
> :00:04.0 'Virtio network device' if= drv=virtio-pci
> unused=virtio_pci,igb_uio
> :00:05.0 'Virtio network device' if= drv=virtio-pci
> unused=virtio_pci,igb_uio
> :00:06.0 'Virtio network device' if= drv=virtio-pci
> unused=virtio_pci,igb_uio
>
> Other network devices
> =
>
>
>
> 2. After correcting the above issue , I am stuck where the interface is
> failing
> to bind to igb_uio. I tried to bind the interface manually to igb_uio but I
> am
> getting the following error
>
> lspci -k
> 00:05.0 Ethernet controller: Red Hat, Inc Virtio network device
> Subsystem: Red Hat, Inc Device 0001
> Kernel modules: virtio_pci
>
> echo :00:05.0 > /sys/bus/pci/drivers/igb_uio/bind
> -bash: echo: write error: No such device
>
> Due to this the bind fails and the virtio_pmd is not able to take and my app
> is
> not coming up.
> EAL: PCI device :00:03.0 on NUMA socket -1
> EAL: probe driver: 1af4:1000 rte_virtio_pmd
> EAL: :00:06.0 not managed by UIO driver, skipping
> EAL: Error - exiting with code: 1
> Cause: No Ethernet ports - bye
>
> I see lots of email threads on similar issue but none had the final
> conclusion.
> So can someone guide me on how to proceed further or get out of this error.
>
Suggest you use the dpdk_nic_bind.py in recently released dpdk package or get
it from dpdk.org repo.
I use it to bind virtio-pci device to igb_uio and after that, I bind it
reversely from igb_uio back to virtio-pci again.
It works, don't find any issue.
Thanks
Changchun