1.. SPDX-License-Identifier: BSD-3-Clause 2 Copyright(c) 2010-2016 Intel Corporation. 3 4Vhost Library 5============= 6 7The vhost library implements a user space virtio net server allowing the user 8to manipulate the virtio ring directly. In another words, it allows the user 9to fetch/put packets from/to the VM virtio net device. To achieve this, a 10vhost library should be able to: 11 12* Access the guest memory: 13 14 For QEMU, this is done by using the ``-object memory-backend-file,share=on,...`` 15 option. Which means QEMU will create a file to serve as the guest RAM. 16 The ``share=on`` option allows another process to map that file, which 17 means it can access the guest RAM. 18 19* Know all the necessary information about the vring: 20 21 Information such as where the available ring is stored. Vhost defines some 22 messages (passed through a Unix domain socket file) to tell the backend all 23 the information it needs to know how to manipulate the vring. 24 25 26Vhost API Overview 27------------------ 28 29The following is an overview of some key Vhost API functions: 30 31* ``rte_vhost_driver_register(path, flags)`` 32 33 This function registers a vhost driver into the system. ``path`` specifies 34 the Unix domain socket file path. 35 36 Currently supported flags are: 37 38 - ``RTE_VHOST_USER_CLIENT`` 39 40 DPDK vhost-user will act as the client when this flag is given. See below 41 for an explanation. 42 43 - ``RTE_VHOST_USER_NO_RECONNECT`` 44 45 When DPDK vhost-user acts as the client it will keep trying to reconnect 46 to the server (QEMU) until it succeeds. This is useful in two cases: 47 48 * When QEMU is not started yet. 49 * When QEMU restarts (for example due to a guest OS reboot). 50 51 This reconnect option is enabled by default. However, it can be turned off 52 by setting this flag. 53 54 - ``RTE_VHOST_USER_IOMMU_SUPPORT`` 55 56 IOMMU support will be enabled when this flag is set. It is disabled by 57 default. 58 59 Enabling this flag makes possible to use guest vIOMMU to protect vhost 60 from accessing memory the virtio device isn't allowed to, when the feature 61 is negotiated and an IOMMU device is declared. 62 63 - ``RTE_VHOST_USER_POSTCOPY_SUPPORT`` 64 65 Postcopy live-migration support will be enabled when this flag is set. 66 It is disabled by default. 67 68 Enabling this flag should only be done when the calling application does 69 not pre-fault the guest shared memory, otherwise migration would fail. 70 71 - ``RTE_VHOST_USER_LINEARBUF_SUPPORT`` 72 73 Enabling this flag forces vhost dequeue function to only provide linear 74 pktmbuf (no multi-segmented pktmbuf). 75 76 The vhost library by default provides a single pktmbuf for given a 77 packet, but if for some reason the data doesn't fit into a single 78 pktmbuf (e.g., TSO is enabled), the library will allocate additional 79 pktmbufs from the same mempool and chain them together to create a 80 multi-segmented pktmbuf. 81 82 However, the vhost application needs to support multi-segmented format. 83 If the vhost application does not support that format and requires large 84 buffers to be dequeue, this flag should be enabled to force only linear 85 buffers (see RTE_VHOST_USER_EXTBUF_SUPPORT) or drop the packet. 86 87 It is disabled by default. 88 89 - ``RTE_VHOST_USER_EXTBUF_SUPPORT`` 90 91 Enabling this flag allows vhost dequeue function to allocate and attach 92 an external buffer to a pktmbuf if the pkmbuf doesn't provide enough 93 space to store all data. 94 95 This is useful when the vhost application wants to support large packets 96 but doesn't want to increase the default mempool object size nor to 97 support multi-segmented mbufs (non-linear). In this case, a fresh buffer 98 is allocated using rte_malloc() which gets attached to a pktmbuf using 99 rte_pktmbuf_attach_extbuf(). 100 101 See RTE_VHOST_USER_LINEARBUF_SUPPORT as well to disable multi-segmented 102 mbufs for application that doesn't support chained mbufs. 103 104 It is disabled by default. 105 106 - ``RTE_VHOST_USER_ASYNC_COPY`` 107 108 Asynchronous data path will be enabled when this flag is set. Async data 109 path allows applications to register async copy devices (typically 110 hardware DMA channels) to the vhost queues. Vhost leverages the copy 111 device registered to free CPU from memory copy operations. A set of 112 async data path APIs are defined for DPDK applications to make use of 113 the async capability. Only packets enqueued/dequeued by async APIs are 114 processed through the async data path. 115 116 Currently this feature is only implemented on split ring enqueue data 117 path. 118 119 It is disabled by default. 120 121 - ``RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS`` 122 123 Since v16.04, the vhost library forwards checksum and gso requests for 124 packets received from a virtio driver by filling Tx offload metadata in 125 the mbuf. This behavior is inconsistent with other drivers but it is left 126 untouched for existing applications that might rely on it. 127 128 This flag disables the legacy behavior and instead ask vhost to simply 129 populate Rx offload metadata in the mbuf. 130 131 It is disabled by default. 132 133* ``rte_vhost_driver_set_features(path, features)`` 134 135 This function sets the feature bits the vhost-user driver supports. The 136 vhost-user driver could be vhost-user net, yet it could be something else, 137 say, vhost-user SCSI. 138 139* ``rte_vhost_driver_callback_register(path, vhost_device_ops)`` 140 141 This function registers a set of callbacks, to let DPDK applications take 142 the appropriate action when some events happen. The following events are 143 currently supported: 144 145 * ``new_device(int vid)`` 146 147 This callback is invoked when a virtio device becomes ready. ``vid`` 148 is the vhost device ID. 149 150 * ``destroy_device(int vid)`` 151 152 This callback is invoked when a virtio device is paused or shut down. 153 154 * ``vring_state_changed(int vid, uint16_t queue_id, int enable)`` 155 156 This callback is invoked when a specific queue's state is changed, for 157 example to enabled or disabled. 158 159 * ``features_changed(int vid, uint64_t features)`` 160 161 This callback is invoked when the features is changed. For example, 162 ``VHOST_F_LOG_ALL`` will be set/cleared at the start/end of live 163 migration, respectively. 164 165 * ``new_connection(int vid)`` 166 167 This callback is invoked on new vhost-user socket connection. If DPDK 168 acts as the server the device should not be deleted before 169 ``destroy_connection`` callback is received. 170 171 * ``destroy_connection(int vid)`` 172 173 This callback is invoked when vhost-user socket connection is closed. 174 It indicates that device with id ``vid`` is no longer in use and can be 175 safely deleted. 176 177* ``rte_vhost_driver_disable/enable_features(path, features))`` 178 179 This function disables/enables some features. For example, it can be used to 180 disable mergeable buffers and TSO features, which both are enabled by 181 default. 182 183* ``rte_vhost_driver_start(path)`` 184 185 This function triggers the vhost-user negotiation. It should be invoked at 186 the end of initializing a vhost-user driver. 187 188* ``rte_vhost_enqueue_burst(vid, queue_id, pkts, count)`` 189 190 Transmits (enqueues) ``count`` packets from host to guest. 191 192* ``rte_vhost_dequeue_burst(vid, queue_id, mbuf_pool, pkts, count)`` 193 194 Receives (dequeues) ``count`` packets from guest, and stored them at ``pkts``. 195 196* ``rte_vhost_crypto_create(vid, cryptodev_id, sess_mempool, socket_id)`` 197 198 As an extension of new_device(), this function adds virtio-crypto workload 199 acceleration capability to the device. All crypto workload is processed by 200 DPDK cryptodev with the device ID of ``cryptodev_id``. 201 202* ``rte_vhost_crypto_free(vid)`` 203 204 Frees the memory and vhost-user message handlers created in 205 rte_vhost_crypto_create(). 206 207* ``rte_vhost_crypto_fetch_requests(vid, queue_id, ops, nb_ops)`` 208 209 Receives (dequeues) ``nb_ops`` virtio-crypto requests from guest, parses 210 them to DPDK Crypto Operations, and fills the ``ops`` with parsing results. 211 212* ``rte_vhost_crypto_finalize_requests(queue_id, ops, nb_ops)`` 213 214 After the ``ops`` are dequeued from Cryptodev, finalizes the jobs and 215 notifies the guest(s). 216 217* ``rte_vhost_crypto_set_zero_copy(vid, option)`` 218 219 Enable or disable zero copy feature of the vhost crypto backend. 220 221* ``rte_vhost_async_channel_register(vid, queue_id, config, ops)`` 222 223 Register an async copy device channel for a vhost queue after vring 224 is enabled. Following device ``config`` must be specified together 225 with the registration: 226 227 * ``features`` 228 229 This field is used to specify async copy device features. 230 231 ``RTE_VHOST_ASYNC_INORDER`` represents the async copy device can 232 guarantee the order of copy completion is the same as the order 233 of copy submission. 234 235 Currently, only ``RTE_VHOST_ASYNC_INORDER`` capable device is 236 supported by vhost. 237 238 * ``async_threshold`` 239 240 The copy length (in bytes) below which CPU copy will be used even if 241 applications call async vhost APIs to enqueue/dequeue data. 242 243 Typical value is 256~1024 depending on the async device capability. 244 245 Applications must provide following ``ops`` callbacks for vhost lib to 246 work with the async copy devices: 247 248 * ``transfer_data(vid, queue_id, descs, opaque_data, count)`` 249 250 vhost invokes this function to submit copy data to the async devices. 251 For non-async_inorder capable devices, ``opaque_data`` could be used 252 for identifying the completed packets. 253 254 * ``check_completed_copies(vid, queue_id, opaque_data, max_packets)`` 255 256 vhost invokes this function to get the copy data completed by async 257 devices. 258 259* ``rte_vhost_async_channel_register_thread_unsafe(vid, queue_id, config, ops)`` 260 261 Register an async copy device channel for a vhost queue without 262 performing any locking. 263 264 This function is only safe to call in vhost callback functions 265 (i.e., struct vhost_device_ops). 266 267* ``rte_vhost_async_channel_unregister(vid, queue_id)`` 268 269 Unregister the async copy device channel from a vhost queue. 270 Unregistration will fail, if the vhost queue has in-flight 271 packets that are not completed. 272 273 Unregister async copy devices in vring_state_changed() may 274 fail, as this API tries to acquire the spinlock of vhost 275 queue. The recommended way is to unregister async copy 276 devices for all vhost queues in destroy_device(), when a 277 virtio device is paused or shut down. 278 279* ``rte_vhost_async_channel_unregister_thread_unsafe(vid, queue_id)`` 280 281 Unregister the async copy device channel for a vhost queue without 282 performing any locking. 283 284 This function is only safe to call in vhost callback functions 285 (i.e., struct vhost_device_ops). 286 287* ``rte_vhost_submit_enqueue_burst(vid, queue_id, pkts, count, comp_pkts, comp_count)`` 288 289 Submit an enqueue request to transmit ``count`` packets from host to guest 290 by async data path. Successfully enqueued packets can be transfer completed 291 or being occupied by DMA engines; transfer completed packets are returned in 292 ``comp_pkts``, but others are not guaranteed to finish, when this API 293 call returns. 294 295 Applications must not free the packets submitted for enqueue until the 296 packets are completed. 297 298* ``rte_vhost_poll_enqueue_completed(vid, queue_id, pkts, count)`` 299 300 Poll enqueue completion status from async data path. Completed packets 301 are returned to applications through ``pkts``. 302 303* ``rte_vhost_async_get_inflight(vid, queue_id)`` 304 305 This function returns the amount of in-flight packets for the vhost 306 queue using async acceleration. 307 308* ``rte_vhost_clear_queue_thread_unsafe(vid, queue_id, **pkts, count)`` 309 310 Clear inflight packets which are submitted to DMA engine in vhost async data 311 path. Completed packets are returned to applications through ``pkts``. 312 313Vhost-user Implementations 314-------------------------- 315 316Vhost-user uses Unix domain sockets for passing messages. This means the DPDK 317vhost-user implementation has two options: 318 319* DPDK vhost-user acts as the server. 320 321 DPDK will create a Unix domain socket server file and listen for 322 connections from the frontend. 323 324 Note, this is the default mode, and the only mode before DPDK v16.07. 325 326 327* DPDK vhost-user acts as the client. 328 329 Unlike the server mode, this mode doesn't create the socket file; 330 it just tries to connect to the server (which responses to create the 331 file instead). 332 333 When the DPDK vhost-user application restarts, DPDK vhost-user will try to 334 connect to the server again. This is how the "reconnect" feature works. 335 336 .. Note:: 337 * The "reconnect" feature requires **QEMU v2.7** (or above). 338 339 * The vhost supported features must be exactly the same before and 340 after the restart. For example, if TSO is disabled and then enabled, 341 nothing will work and issues undefined might happen. 342 343No matter which mode is used, once a connection is established, DPDK 344vhost-user will start receiving and processing vhost messages from QEMU. 345 346For messages with a file descriptor, the file descriptor can be used directly 347in the vhost process as it is already installed by the Unix domain socket. 348 349The supported vhost messages are: 350 351* ``VHOST_SET_MEM_TABLE`` 352* ``VHOST_SET_VRING_KICK`` 353* ``VHOST_SET_VRING_CALL`` 354* ``VHOST_SET_LOG_FD`` 355* ``VHOST_SET_VRING_ERR`` 356 357For ``VHOST_SET_MEM_TABLE`` message, QEMU will send information for each 358memory region and its file descriptor in the ancillary data of the message. 359The file descriptor is used to map that region. 360 361``VHOST_SET_VRING_KICK`` is used as the signal to put the vhost device into 362the data plane, and ``VHOST_GET_VRING_BASE`` is used as the signal to remove 363the vhost device from the data plane. 364 365When the socket connection is closed, vhost will destroy the device. 366 367Guest memory requirement 368------------------------ 369 370* Memory pre-allocation 371 372 For non-async data path, guest memory pre-allocation is not a 373 must. This can help save of memory. If users really want the guest memory 374 to be pre-allocated (e.g., for performance reason), we can add option 375 ``-mem-prealloc`` when starting QEMU. Or, we can lock all memory at vhost 376 side which will force memory to be allocated when mmap at vhost side; 377 option --mlockall in ovs-dpdk is an example in hand. 378 379 For async data path, we force the VM memory to be pre-allocated at vhost 380 lib when mapping the guest memory; and also we need to lock the memory to 381 prevent pages being swapped out to disk. 382 383* Memory sharing 384 385 Make sure ``share=on`` QEMU option is given. vhost-user will not work with 386 a QEMU version without shared memory mapping. 387 388Vhost supported vSwitch reference 389--------------------------------- 390 391For more vhost details and how to support vhost in vSwitch, please refer to 392the vhost example in the DPDK Sample Applications Guide. 393 394Vhost data path acceleration (vDPA) 395----------------------------------- 396 397vDPA supports selective datapath in vhost-user lib by enabling virtio ring 398compatible devices to serve virtio driver directly for datapath acceleration. 399 400``rte_vhost_driver_attach_vdpa_device`` is used to configure the vhost device 401with accelerated backend. 402 403Also vhost device capabilities are made configurable to adopt various devices. 404Such capabilities include supported features, protocol features, queue number. 405 406Finally, a set of device ops is defined for device specific operations: 407 408* ``get_queue_num`` 409 410 Called to get supported queue number of the device. 411 412* ``get_features`` 413 414 Called to get supported features of the device. 415 416* ``get_protocol_features`` 417 418 Called to get supported protocol features of the device. 419 420* ``dev_conf`` 421 422 Called to configure the actual device when the virtio device becomes ready. 423 424* ``dev_close`` 425 426 Called to close the actual device when the virtio device is stopped. 427 428* ``set_vring_state`` 429 430 Called to change the state of the vring in the actual device when vring state 431 changes. 432 433* ``set_features`` 434 435 Called to set the negotiated features to device. 436 437* ``migration_done`` 438 439 Called to allow the device to response to RARP sending. 440 441* ``get_vfio_group_fd`` 442 443 Called to get the VFIO group fd of the device. 444 445* ``get_vfio_device_fd`` 446 447 Called to get the VFIO device fd of the device. 448 449* ``get_notify_area`` 450 451 Called to get the notify area info of the queue. 452