.. BSD LICENSE
- Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
+ Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
All rights reserved.
Redistribution and use in source and binary forms, with or without
Vhost Library
=============
-The vhost cuse (cuse: user space character device driver) library implements a
-vhost cuse driver. It also creates, manages and destroys vhost devices for
-corresponding virtio devices in the guest. Vhost supported vSwitch could register
-callbacks to this library, which will be called when a vhost device is activated
-or deactivated by guest virtual machine.
+The vhost library implements a user space virtio net server allowing the user
+to manipulate the virtio ring directly. In another words, it allows the user
+to fetch/put packets from/to the VM virtio net device. To achieve this, a
+vhost library should be able to:
+
+* Access the guest memory:
+
+ For QEMU, this is done by using the ``-object memory-backend-file,share=on,...``
+ option. Which means QEMU will create a file to serve as the guest RAM.
+ The ``share=on`` option allows another process to map that file, which
+ means it can access the guest RAM.
+
+* Know all the necessary information about the vring:
+
+ Information such as where the available ring is stored. Vhost defines some
+ messages (passed through a Unix domain socket file) to tell the backend all
+ the information it needs to know how to manipulate the vring.
+
Vhost API Overview
------------------
-* Vhost driver registration
+The following is an overview of some key Vhost API functions:
+
+* ``rte_vhost_driver_register(path, flags)``
+
+ This function registers a vhost driver into the system. ``path`` specifies
+ the Unix domain socket file path.
+
+ Currently supported flags are:
+
+ - ``RTE_VHOST_USER_CLIENT``
+
+ DPDK vhost-user will act as the client when this flag is given. See below
+ for an explanation.
+
+ - ``RTE_VHOST_USER_NO_RECONNECT``
+
+ When DPDK vhost-user acts as the client it will keep trying to reconnect
+ to the server (QEMU) until it succeeds. This is useful in two cases:
+
+ * When QEMU is not started yet.
+ * When QEMU restarts (for example due to a guest OS reboot).
+
+ This reconnect option is enabled by default. However, it can be turned off
+ by setting this flag.
+
+ - ``RTE_VHOST_USER_DEQUEUE_ZERO_COPY``
+
+ Dequeue zero copy will be enabled when this flag is set. It is disabled by
+ default.
+
+ There are some truths (including limitations) you might want to know while
+ setting this flag:
+
+ * zero copy is not good for small packets (typically for packet size below
+ 512).
+
+ * zero copy is really good for VM2VM case. For iperf between two VMs, the
+ boost could be above 70% (when TSO is enableld).
+
+ * for VM2NIC case, the ``nb_tx_desc`` has to be small enough: <= 64 if virtio
+ indirect feature is not enabled and <= 128 if it is enabled.
+
+ This is because when dequeue zero copy is enabled, guest Tx used vring will
+ be updated only when corresponding mbuf is freed. Thus, the nb_tx_desc
+ has to be small enough so that the PMD driver will run out of available
+ Tx descriptors and free mbufs timely. Otherwise, guest Tx vring would be
+ starved.
+
+ * Guest memory should be backended with huge pages to achieve better
+ performance. Using 1G page size is the best.
+
+ When dequeue zero copy is enabled, the guest phys address and host phys
+ address mapping has to be established. Using non-huge pages means far
+ more page segments. To make it simple, DPDK vhost does a linear search
+ of those segments, thus the fewer the segments, the quicker we will get
+ the mapping. NOTE: we may speed it by using tree searching in future.
+
+* ``rte_vhost_driver_set_features(path, features)``
+
+ This function sets the feature bits the vhost-user driver supports. The
+ vhost-user driver could be vhost-user net, yet it could be something else,
+ say, vhost-user SCSI.
+
+* ``rte_vhost_driver_session_start()``
+
+ This function starts the vhost session loop to handle vhost messages. It
+ starts an infinite loop, therefore it should be called in a dedicated
+ thread.
+
+* ``rte_vhost_driver_callback_register(path, virtio_net_device_ops)``
+
+ This function registers a set of callbacks, to let DPDK applications take
+ the appropriate action when some events happen. The following events are
+ currently supported:
+
+ * ``new_device(int vid)``
+
+ This callback is invoked when a virtio net device becomes ready. ``vid``
+ is the virtio net device ID.
+
+ * ``destroy_device(int vid)``
+
+ This callback is invoked when a virtio net device shuts down (or when the
+ vhost connection is broken).
+
+ * ``vring_state_changed(int vid, uint16_t queue_id, int enable)``
+
+ This callback is invoked when a specific queue's state is changed, for
+ example to enabled or disabled.
+
+* ``rte_vhost_enqueue_burst(vid, queue_id, pkts, count)``
+
+ Transmits (enqueues) ``count`` packets from host to guest.
+
+* ``rte_vhost_dequeue_burst(vid, queue_id, mbuf_pool, pkts, count)``
+
+ Receives (dequeues) ``count`` packets from guest, and stored them at ``pkts``.
+
+* ``rte_vhost_driver_disable/enable_features(path, features))``
+
+ This function disables/enables some features. For example, it can be used to
+ disable mergeable buffers and TSO features, which both are enabled by
+ default.
+
+
+Vhost-user Implementations
+--------------------------
+
+Vhost-user uses Unix domain sockets for passing messages. This means the DPDK
+vhost-user implementation has two options:
+
+* DPDK vhost-user acts as the server.
- rte_vhost_driver_register registers the vhost cuse driver into the system.
- Character device file will be created in the /dev directory.
- Character device name is specified as the parameter.
+ DPDK will create a Unix domain socket server file and listen for
+ connections from the frontend.
-* Vhost session start
+ Note, this is the default mode, and the only mode before DPDK v16.07.
- rte_vhost_driver_session_start starts the vhost session loop.
- Vhost cuse session is an infinite blocking loop.
- Put the session in a dedicate DPDK thread.
-* Callback register
+* DPDK vhost-user acts as the client.
- Vhost supported vSwitch could call rte_vhost_driver_callback_register to
- register two callbacks, new_destory and destroy_device.
- When virtio device is activated or deactivated by guest virtual machine,
- the callback will be called, then vSwitch could put the device onto data
- core or remove the device from data core by setting or unsetting
- VIRTIO_DEV_RUNNING on the device flags.
+ Unlike the server mode, this mode doesn't create the socket file;
+ it just tries to connect to the server (which responses to create the
+ file instead).
-* Read/write packets from/to guest virtual machine
+ When the DPDK vhost-user application restarts, DPDK vhost-user will try to
+ connect to the server again. This is how the "reconnect" feature works.
- rte_vhost_enqueue_burst transmit host packets to guest.
- rte_vhost_dequeue_burst receives packets from guest.
+ .. Note::
+ * The "reconnect" feature requires **QEMU v2.7** (or above).
-* Feature enable/disable
+ * The vhost supported features must be exactly the same before and
+ after the restart. For example, if TSO is disabled and then enabled,
+ nothing will work and issues undefined might happen.
- Now one negotiate-able feature in vhost is merge-able.
- vSwitch could enable/disable this feature for performance consideration.
+No matter which mode is used, once a connection is established, DPDK
+vhost-user will start receiving and processing vhost messages from QEMU.
-Vhost Implementation
---------------------
+For messages with a file descriptor, the file descriptor can be used directly
+in the vhost process as it is already installed by the Unix domain socket.
-When vSwitch registers the vhost driver, it will register a cuse device driver
-into the system and creates a character device file. This cuse driver will
-receive vhost open/release/IOCTL message from QEMU simulator.
+The supported vhost messages are:
-When the open call is received, vhost driver will create a vhost device for the
-virtio device in the guest.
+* ``VHOST_SET_MEM_TABLE``
+* ``VHOST_SET_VRING_KICK``
+* ``VHOST_SET_VRING_CALL``
+* ``VHOST_SET_LOG_FD``
+* ``VHOST_SET_VRING_ERR``
-When VHOST_SET_MEM_TABLE IOCTL is received, vhost searches the memory region
-to find the starting user space virtual address that maps the memory of guest
-virtual machine. Through this virtual address and the QEMU pid, vhost could
-find the file QEMU uses to map the guest memory. Vhost maps this file into its
-address space, in this way vhost could fully access the guest physical memory,
-which means vhost could access the shared virtio ring and the guest physical
-address specified in the entry of the ring.
+For ``VHOST_SET_MEM_TABLE`` message, QEMU will send information for each
+memory region and its file descriptor in the ancillary data of the message.
+The file descriptor is used to map that region.
-The guest virtual machine tells the vhost whether the virtio device is ready
-for processing or is de-activated through VHOST_SET_BACKEND message.
-The registered callback from vSwitch will be called.
+``VHOST_SET_VRING_KICK`` is used as the signal to put the vhost device into
+the data plane, and ``VHOST_GET_VRING_BASE`` is used as the signal to remove
+the vhost device from the data plane.
-When the release call is released, vhost will destroy the device.
+When the socket connection is closed, vhost will destroy the device.
Vhost supported vSwitch reference
---------------------------------
-For how to support vhost in vSwitch, please refer to vhost example in the
-DPDK Sample Applications Guide.
+For more vhost details and how to support vhost in vSwitch, please refer to
+the vhost example in the DPDK Sample Applications Guide.
git.droids-corp.org / dpdk.git / blobdiff