4 Copyright (c) 2014 Virtual Open Systems Sarl.
6 This work is licensed under the terms of the GNU GPL, version 2 or later.
7 See the COPYING file in the top-level directory.
10 This protocol is aiming to complement the ioctl interface used to control the
11 vhost implementation in the Linux kernel. It implements the control plane needed
12 to establish virtqueue sharing with a user space process on the same host. It
13 uses communication over a Unix domain socket to share file descriptors in the
14 ancillary data of the message.
16 The protocol defines 2 sides of the communication, master and slave. Master is
17 the application that shares its virtqueues, in our case QEMU. Slave is the
18 consumer of the virtqueues.
20 In the current implementation QEMU is the Master, and the Slave is intended to
21 be a software Ethernet switch running in user space, such as Snabbswitch.
23 Master and slave can be either a client (i.e. connecting) or server (listening)
24 in the socket communication.
29 Note that all numbers are in the machine native byte order. A vhost-user message
30 consists of 3 header fields and a payload:
32 ------------------------------------
33 | request | flags | size | payload |
34 ------------------------------------
36 * Request: 32-bit type of the request
37 * Flags: 32-bit bit field:
38 - Lower 2 bits are the version (currently 0x01)
39 - Bit 2 is the reply flag - needs to be sent on each reply from the slave
40 * Size - 32-bit size of the payload
43 Depending on the request type, payload can be:
45 * A single 64-bit integer
50 u64: a 64-bit unsigned integer
52 * A vring state description
60 * A vring address description
61 --------------------------------------------------------------
62 | index | flags | size | descriptor | used | available | log |
63 --------------------------------------------------------------
65 Index: a 32-bit vring index
66 Flags: a 32-bit vring flags
67 Descriptor: a 64-bit user address of the vring descriptor table
68 Used: a 64-bit user address of the vring used ring
69 Available: a 64-bit user address of the vring available ring
70 Log: a 64-bit guest address for logging
72 * Memory regions description
73 ---------------------------------------------------
74 | num regions | padding | region0 | ... | region7 |
75 ---------------------------------------------------
77 Num regions: a 32-bit number of regions
81 -----------------------------------------------------
82 | guest address | size | user address | mmap offset |
83 -----------------------------------------------------
85 Guest address: a 64-bit guest address of the region
87 User address: a 64-bit user address
88 mmap offset: 64-bit offset where region starts in the mapped memory
90 In QEMU the vhost-user message is implemented with the following struct:
92 typedef struct VhostUserMsg {
93 VhostUserRequest request;
98 struct vhost_vring_state state;
99 struct vhost_vring_addr addr;
100 VhostUserMemory memory;
102 } QEMU_PACKED VhostUserMsg;
107 The protocol for vhost-user is based on the existing implementation of vhost
108 for the Linux Kernel. Most messages that can be sent via the Unix domain socket
109 implementing vhost-user have an equivalent ioctl to the kernel implementation.
111 The communication consists of master sending message requests and slave sending
112 message replies. Most of the requests don't require replies. Here is a list of
116 * VHOST_GET_PROTOCOL_FEATURES
117 * VHOST_GET_VRING_BASE
119 There are several messages that the master sends with file descriptors passed
120 in the ancillary data:
122 * VHOST_SET_MEM_TABLE
124 * VHOST_SET_VRING_KICK
125 * VHOST_SET_VRING_CALL
126 * VHOST_SET_VRING_ERR
128 If Master is unable to send the full message or receives a wrong reply it will
129 close the connection. An optional reconnection mechanism can be implemented.
131 Any protocol extensions are gated by protocol feature bits,
132 which allows full backwards compatibility on both master
134 As older slaves don't support negotiating protocol features,
135 a feature bit was dedicated for this purpose:
136 #define VHOST_USER_F_PROTOCOL_FEATURES 30
138 Multiple queue support
139 ----------------------
141 Multiple queue is treated as a protocol extension, hence the slave has to
142 implement protocol features first. The multiple queues feature is supported
143 only when the protocol feature VHOST_USER_PROTOCOL_F_MQ (bit 0) is set:
144 #define VHOST_USER_PROTOCOL_F_MQ 0
146 The max number of queues the slave supports can be queried with message
147 VHOST_USER_GET_PROTOCOL_FEATURES. Master should stop when the number of
148 requested queues is bigger than that.
150 As all queues share one connection, the master uses a unique index for each
151 queue in the sent message to identify a specified queue. One queue pair
152 is enabled initially. More queues are enabled dynamically, by sending
153 message VHOST_USER_SET_VRING_ENABLE.
158 * VHOST_USER_GET_FEATURES
161 Equivalent ioctl: VHOST_GET_FEATURES
165 Get from the underlying vhost implementation the features bitmask.
166 Feature bit VHOST_USER_F_PROTOCOL_FEATURES signals slave support for
167 VHOST_USER_GET_PROTOCOL_FEATURES and VHOST_USER_SET_PROTOCOL_FEATURES.
169 * VHOST_USER_SET_FEATURES
172 Ioctl: VHOST_SET_FEATURES
175 Enable features in the underlying vhost implementation using a bitmask.
176 Feature bit VHOST_USER_F_PROTOCOL_FEATURES signals slave support for
177 VHOST_USER_GET_PROTOCOL_FEATURES and VHOST_USER_SET_PROTOCOL_FEATURES.
179 * VHOST_USER_GET_PROTOCOL_FEATURES
182 Equivalent ioctl: VHOST_GET_FEATURES
186 Get the protocol feature bitmask from the underlying vhost implementation.
187 Only legal if feature bit VHOST_USER_F_PROTOCOL_FEATURES is present in
188 VHOST_USER_GET_FEATURES.
189 Note: slave that reported VHOST_USER_F_PROTOCOL_FEATURES must support
190 this message even before VHOST_USER_SET_FEATURES was called.
192 * VHOST_USER_SET_PROTOCOL_FEATURES
195 Ioctl: VHOST_SET_FEATURES
198 Enable protocol features in the underlying vhost implementation.
199 Only legal if feature bit VHOST_USER_F_PROTOCOL_FEATURES is present in
200 VHOST_USER_GET_FEATURES.
201 Note: slave that reported VHOST_USER_F_PROTOCOL_FEATURES must support
202 this message even before VHOST_USER_SET_FEATURES was called.
204 * VHOST_USER_SET_OWNER
207 Equivalent ioctl: VHOST_SET_OWNER
210 Issued when a new connection is established. It sets the current Master
211 as an owner of the session. This can be used on the Slave as a
212 "session start" flag.
214 * VHOST_USER_RESET_DEVICE
217 Equivalent ioctl: VHOST_RESET_DEVICE
220 Issued when a new connection is about to be closed. The Master will no
221 longer own this connection (and will usually close it).
223 * VHOST_USER_SET_MEM_TABLE
226 Equivalent ioctl: VHOST_SET_MEM_TABLE
227 Master payload: memory regions description
229 Sets the memory map regions on the slave so it can translate the vring
230 addresses. In the ancillary data there is an array of file descriptors
231 for each memory mapped region. The size and ordering of the fds matches
232 the number and ordering of memory regions.
234 * VHOST_USER_SET_LOG_BASE
237 Equivalent ioctl: VHOST_SET_LOG_BASE
240 Sets the logging base address.
242 * VHOST_USER_SET_LOG_FD
245 Equivalent ioctl: VHOST_SET_LOG_FD
248 Sets the logging file descriptor, which is passed as ancillary data.
250 * VHOST_USER_SET_VRING_NUM
253 Equivalent ioctl: VHOST_SET_VRING_NUM
254 Master payload: vring state description
256 Sets the number of vrings for this owner.
258 * VHOST_USER_SET_VRING_ADDR
261 Equivalent ioctl: VHOST_SET_VRING_ADDR
262 Master payload: vring address description
265 Sets the addresses of the different aspects of the vring.
267 * VHOST_USER_SET_VRING_BASE
270 Equivalent ioctl: VHOST_SET_VRING_BASE
271 Master payload: vring state description
273 Sets the base offset in the available vring.
275 * VHOST_USER_GET_VRING_BASE
278 Equivalent ioctl: VHOST_USER_GET_VRING_BASE
279 Master payload: vring state description
280 Slave payload: vring state description
282 Get the available vring base offset.
284 * VHOST_USER_SET_VRING_KICK
287 Equivalent ioctl: VHOST_SET_VRING_KICK
290 Set the event file descriptor for adding buffers to the vring. It
291 is passed in the ancillary data.
292 Bits (0-7) of the payload contain the vring index. Bit 8 is the
293 invalid FD flag. This flag is set when there is no file descriptor
294 in the ancillary data. This signals that polling should be used
295 instead of waiting for a kick.
297 * VHOST_USER_SET_VRING_CALL
300 Equivalent ioctl: VHOST_SET_VRING_CALL
303 Set the event file descriptor to signal when buffers are used. It
304 is passed in the ancillary data.
305 Bits (0-7) of the payload contain the vring index. Bit 8 is the
306 invalid FD flag. This flag is set when there is no file descriptor
307 in the ancillary data. This signals that polling will be used
308 instead of waiting for the call.
310 * VHOST_USER_SET_VRING_ERR
313 Equivalent ioctl: VHOST_SET_VRING_ERR
316 Set the event file descriptor to signal when error occurs. It
317 is passed in the ancillary data.
318 Bits (0-7) of the payload contain the vring index. Bit 8 is the
319 invalid FD flag. This flag is set when there is no file descriptor
320 in the ancillary data.
322 * VHOST_USER_GET_QUEUE_NUM
325 Equivalent ioctl: N/A
329 Query how many queues the backend supports. This request should be
330 sent only when VHOST_USER_PROTOCOL_F_MQ is set in quried protocol
331 features by VHOST_USER_GET_PROTOCOL_FEATURES.
333 * VHOST_USER_SET_VRING_ENABLE
336 Equivalent ioctl: N/A
337 Master payload: vring state description
339 Signal slave to enable or disable corresponding vring.