37. Poll Mode Driver that wraps vhost library

This PMD is a thin wrapper of the DPDK vhost library. The user can handle virtqueues as one of normal DPDK port.

37.1. Vhost Implementation in DPDK

Please refer to Chapter “Vhost Library” of DPDK Programmer’s Guide to know detail of vhost.

37.2. Features and Limitations of vhost PMD

Currently, the vhost PMD provides the basic functionality of packet reception, transmission and event handling.

  • It has multiple queues support.
  • It supports RTE_ETH_EVENT_INTR_LSC and RTE_ETH_EVENT_QUEUE_STATE events.
  • It supports Port Hotplug functionality.
  • Don’t need to stop RX/TX, when the user wants to stop a guest or a virtio-net driver on guest.

37.3. Vhost PMD arguments

The user can specify below arguments in –vdev option.

  1. iface:

    It is used to specify a path to connect to a QEMU virtio-net device.

  2. queues:

    It is used to specify the number of queues virtio-net device has. (Default: 1)

  3. iommu-support:

    It is used to enable iommu support in vhost library. (Default: 0 (disabled))

37.4. Vhost PMD event handling

This section describes how to handle vhost PMD events.

The user can register an event callback handler with rte_eth_dev_callback_register(). The registered callback handler will be invoked with one of below event types.

  1. RTE_ETH_EVENT_INTR_LSC:

    It means link status of the port was changed.

  2. RTE_ETH_EVENT_QUEUE_STATE:

    It means some of queue statuses were changed. Call rte_eth_vhost_get_queue_event() in the callback handler. Because changing multiple statuses may occur only one event, call the function repeatedly as long as it doesn’t return negative value.

37.5. Vhost PMD with testpmd application

This section demonstrates vhost PMD with testpmd DPDK sample application.

  1. Launch the testpmd with vhost PMD:

    ./testpmd -l 0-3 -n 4 --vdev 'net_vhost0,iface=/tmp/sock0,queues=1' -- -i

    Other basic DPDK preparations like hugepage enabling here. Please refer to the DPDK Getting Started Guide for detailed instructions.

  2. Launch the QEMU:

    qemu-system-x86_64 <snip>
            -chardev socket,id=chr0,path=/tmp/sock0 \
            -netdev vhost-user,id=net0,chardev=chr0,vhostforce,queues=1 \
            -device virtio-net-pci,netdev=net0

    This command attaches one virtio-net device to QEMU guest. After initialization processes between QEMU and DPDK vhost library are done, status of the port will be linked up.