summaryrefslogtreecommitdiffstats
path: root/qemu/roms/ipxe/src/include/xen/io/netif.h
blob: ae12eab73857dbf9bac478435c10f09da72f2822 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
/******************************************************************************
 * netif.h
 *
 * Unified network-device I/O interface for Xen guest OSes.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to
 * deal in the Software without restriction, including without limitation the
 * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
 * sell copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
 * DEALINGS IN THE SOFTWARE.
 *
 * Copyright (c) 2003-2004, Keir Fraser
 */

#ifndef __XEN_PUBLIC_IO_NETIF_H__
#define __XEN_PUBLIC_IO_NETIF_H__

FILE_LICENCE ( MIT );

#include "ring.h"
#include "../grant_table.h"

/*
 * Older implementation of Xen network frontend / backend has an
 * implicit dependency on the MAX_SKB_FRAGS as the maximum number of
 * ring slots a skb can use. Netfront / netback may not work as
 * expected when frontend and backend have different MAX_SKB_FRAGS.
 *
 * A better approach is to add mechanism for netfront / netback to
 * negotiate this value. However we cannot fix all possible
 * frontends, so we need to define a value which states the minimum
 * slots backend must support.
 *
 * The minimum value derives from older Linux kernel's MAX_SKB_FRAGS
 * (18), which is proved to work with most frontends. Any new backend
 * which doesn't negotiate with frontend should expect frontend to
 * send a valid packet using slots up to this value.
 */
#define XEN_NETIF_NR_SLOTS_MIN 18

/*
 * Notifications after enqueuing any type of message should be conditional on
 * the appropriate req_event or rsp_event field in the shared ring.
 * If the client sends notification for rx requests then it should specify
 * feature 'feature-rx-notify' via xenbus. Otherwise the backend will assume
 * that it cannot safely queue packets (as it may not be kicked to send them).
 */

/*
 * "feature-split-event-channels" is introduced to separate guest TX
 * and RX notification. Backend either doesn't support this feature or
 * advertises it via xenstore as 0 (disabled) or 1 (enabled).
 *
 * To make use of this feature, frontend should allocate two event
 * channels for TX and RX, advertise them to backend as
 * "event-channel-tx" and "event-channel-rx" respectively. If frontend
 * doesn't want to use this feature, it just writes "event-channel"
 * node as before.
 */

/*
 * Multiple transmit and receive queues:
 * If supported, the backend will write the key "multi-queue-max-queues" to
 * the directory for that vif, and set its value to the maximum supported
 * number of queues.
 * Frontends that are aware of this feature and wish to use it can write the
 * key "multi-queue-num-queues", set to the number they wish to use, which
 * must be greater than zero, and no more than the value reported by the backend
 * in "multi-queue-max-queues".
 *
 * Queues replicate the shared rings and event channels.
 * "feature-split-event-channels" may optionally be used when using
 * multiple queues, but is not mandatory.
 *
 * Each queue consists of one shared ring pair, i.e. there must be the same
 * number of tx and rx rings.
 *
 * For frontends requesting just one queue, the usual event-channel and
 * ring-ref keys are written as before, simplifying the backend processing
 * to avoid distinguishing between a frontend that doesn't understand the
 * multi-queue feature, and one that does, but requested only one queue.
 *
 * Frontends requesting two or more queues must not write the toplevel
 * event-channel (or event-channel-{tx,rx}) and {tx,rx}-ring-ref keys,
 * instead writing those keys under sub-keys having the name "queue-N" where
 * N is the integer ID of the queue for which those keys belong. Queues
 * are indexed from zero. For example, a frontend with two queues and split
 * event channels must write the following set of queue-related keys:
 *
 * /local/domain/1/device/vif/0/multi-queue-num-queues = "2"
 * /local/domain/1/device/vif/0/queue-0 = ""
 * /local/domain/1/device/vif/0/queue-0/tx-ring-ref = "<ring-ref-tx0>"
 * /local/domain/1/device/vif/0/queue-0/rx-ring-ref = "<ring-ref-rx0>"
 * /local/domain/1/device/vif/0/queue-0/event-channel-tx = "<evtchn-tx0>"
 * /local/domain/1/device/vif/0/queue-0/event-channel-rx = "<evtchn-rx0>"
 * /local/domain/1/device/vif/0/queue-1 = ""
 * /local/domain/1/device/vif/0/queue-1/tx-ring-ref = "<ring-ref-tx1>"
 * /local/domain/1/device/vif/0/queue-1/rx-ring-ref = "<ring-ref-rx1"
 * /local/domain/1/device/vif/0/queue-1/event-channel-tx = "<evtchn-tx1>"
 * /local/domain/1/device/vif/0/queue-1/event-channel-rx = "<evtchn-rx1>"
 *
 * If there is any inconsistency in the XenStore data, the backend may
 * choose not to connect any queues, instead treating the request as an
 * error. This includes scenarios where more (or fewer) queues were
 * requested than the frontend provided details for.
 *
 * Mapping of packets to queues is considered to be a function of the
 * transmitting system (backend or frontend) and is not negotiated
 * between the two. Guests are free to transmit packets on any queue
 * they choose, provided it has been set up correctly. Guests must be
 * prepared to receive packets on any queue they have requested be set up.
 */

/*
 * "feature-no-csum-offload" should be used to turn IPv4 TCP/UDP checksum
 * offload off or on. If it is missing then the feature is assumed to be on.
 * "feature-ipv6-csum-offload" should be used to turn IPv6 TCP/UDP checksum
 * offload on or off. If it is missing then the feature is assumed to be off.
 */

/*
 * "feature-gso-tcpv4" and "feature-gso-tcpv6" advertise the capability to
 * handle large TCP packets (in IPv4 or IPv6 form respectively). Neither
 * frontends nor backends are assumed to be capable unless the flags are
 * present.
 */

/*
 * This is the 'wire' format for packets:
 *  Request 1: netif_tx_request -- NETTXF_* (any flags)
 * [Request 2: netif_tx_extra]  (only if request 1 has NETTXF_extra_info)
 * [Request 3: netif_tx_extra]  (only if request 2 has XEN_NETIF_EXTRA_MORE)
 *  Request 4: netif_tx_request -- NETTXF_more_data
 *  Request 5: netif_tx_request -- NETTXF_more_data
 *  ...
 *  Request N: netif_tx_request -- 0
 */

/* Protocol checksum field is blank in the packet (hardware offload)? */
#define _NETTXF_csum_blank     (0)
#define  NETTXF_csum_blank     (1U<<_NETTXF_csum_blank)

/* Packet data has been validated against protocol checksum. */
#define _NETTXF_data_validated (1)
#define  NETTXF_data_validated (1U<<_NETTXF_data_validated)

/* Packet continues in the next request descriptor. */
#define _NETTXF_more_data      (2)
#define  NETTXF_more_data      (1U<<_NETTXF_more_data)

/* Packet to be followed by extra descriptor(s). */
#define _NETTXF_extra_info     (3)
#define  NETTXF_extra_info     (1U<<_NETTXF_extra_info)

#define XEN_NETIF_MAX_TX_SIZE 0xFFFF
struct netif_tx_request {
    grant_ref_t gref;      /* Reference to buffer page */
    uint16_t offset;       /* Offset within buffer page */
    uint16_t flags;        /* NETTXF_* */
    uint16_t id;           /* Echoed in response message. */
    uint16_t size;         /* Packet size in bytes.       */
};
typedef struct netif_tx_request netif_tx_request_t;

/* Types of netif_extra_info descriptors. */
#define XEN_NETIF_EXTRA_TYPE_NONE      (0)  /* Never used - invalid */
#define XEN_NETIF_EXTRA_TYPE_GSO       (1)  /* u.gso */
#define XEN_NETIF_EXTRA_TYPE_MCAST_ADD (2)  /* u.mcast */
#define XEN_NETIF_EXTRA_TYPE_MCAST_DEL (3)  /* u.mcast */
#define XEN_NETIF_EXTRA_TYPE_MAX       (4)

/* netif_extra_info flags. */
#define _XEN_NETIF_EXTRA_FLAG_MORE (0)
#define XEN_NETIF_EXTRA_FLAG_MORE  (1U<<_XEN_NETIF_EXTRA_FLAG_MORE)

/* GSO types */
#define XEN_NETIF_GSO_TYPE_NONE         (0)
#define XEN_NETIF_GSO_TYPE_TCPV4        (1)
#define XEN_NETIF_GSO_TYPE_TCPV6        (2)

/*
 * This structure needs to fit within both netif_tx_request and
 * netif_rx_response for compatibility.
 */
struct netif_extra_info {
    uint8_t type;  /* XEN_NETIF_EXTRA_TYPE_* */
    uint8_t flags; /* XEN_NETIF_EXTRA_FLAG_* */

    union {
        /*
         * XEN_NETIF_EXTRA_TYPE_GSO:
         */
        struct {
            /*
             * Maximum payload size of each segment. For example, for TCP this
             * is just the path MSS.
             */
            uint16_t size;

            /*
             * GSO type. This determines the protocol of the packet and any
             * extra features required to segment the packet properly.
             */
            uint8_t type; /* XEN_NETIF_GSO_TYPE_* */

            /* Future expansion. */
            uint8_t pad;

            /*
             * GSO features. This specifies any extra GSO features required
             * to process this packet, such as ECN support for TCPv4.
             */
            uint16_t features; /* XEN_NETIF_GSO_FEAT_* */
        } gso;

        /*
         * XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL}:
         * Backend advertises availability via 'feature-multicast-control'
         * xenbus node containing value '1'.
         * Frontend requests this feature by advertising
         * 'request-multicast-control' xenbus node containing value '1'.
         * If multicast control is requested then multicast flooding is
         * disabled and the frontend must explicitly register its interest
         * in multicast groups using dummy transmit requests containing
         * MCAST_{ADD,DEL} extra-info fragments.
         */
        struct {
            uint8_t addr[6]; /* Address to add/remove. */
        } mcast;

        uint16_t pad[3];
    } u;
};
typedef struct netif_extra_info netif_extra_info_t;

struct netif_tx_response {
    uint16_t id;
    int16_t  status;       /* NETIF_RSP_* */
};
typedef struct netif_tx_response netif_tx_response_t;

struct netif_rx_request {
    uint16_t    id;        /* Echoed in response message.        */
    grant_ref_t gref;      /* Reference to incoming granted frame */
};
typedef struct netif_rx_request netif_rx_request_t;

/* Packet data has been validated against protocol checksum. */
#define _NETRXF_data_validated (0)
#define  NETRXF_data_validated (1U<<_NETRXF_data_validated)

/* Protocol checksum field is blank in the packet (hardware offload)? */
#define _NETRXF_csum_blank     (1)
#define  NETRXF_csum_blank     (1U<<_NETRXF_csum_blank)

/* Packet continues in the next request descriptor. */
#define _NETRXF_more_data      (2)
#define  NETRXF_more_data      (1U<<_NETRXF_more_data)

/* Packet to be followed by extra descriptor(s). */
#define _NETRXF_extra_info     (3)
#define  NETRXF_extra_info     (1U<<_NETRXF_extra_info)

struct netif_rx_response {
    uint16_t id;
    uint16_t offset;       /* Offset in page of start of received packet  */
    uint16_t flags;        /* NETRXF_* */
    int16_t  status;       /* -ve: NETIF_RSP_* ; +ve: Rx'ed pkt size. */
};
typedef struct netif_rx_response netif_rx_response_t;

/*
 * Generate netif ring structures and types.
 */

DEFINE_RING_TYPES(netif_tx, struct netif_tx_request, struct netif_tx_response);
DEFINE_RING_TYPES(netif_rx, struct netif_rx_request, struct netif_rx_response);

#define NETIF_RSP_DROPPED         -2
#define NETIF_RSP_ERROR           -1
#define NETIF_RSP_OKAY             0
/* No response: used for auxiliary requests (e.g., netif_tx_extra). */
#define NETIF_RSP_NULL             1

#endif

/*
 * Local variables:
 * mode: C
 * c-file-style: "BSD"
 * c-basic-offset: 4
 * tab-width: 4
 * indent-tabs-mode: nil
 * End:
 */