aboutsummaryrefslogtreecommitdiff
path: root/include/block/nbd.h
blob: 113c707a5e9f05532628b86720354c5629779973 (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
/*
 *  Copyright (C) 2016-2017 Red Hat, Inc.
 *  Copyright (C) 2005  Anthony Liguori <anthony@codemonkey.ws>
 *
 *  Network Block Device
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; under version 2 of the License.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, see <http://www.gnu.org/licenses/>.
 */

#ifndef NBD_H
#define NBD_H


#include "qemu-common.h"
#include "qemu/option.h"
#include "io/channel-socket.h"
#include "crypto/tlscreds.h"

/* Handshake phase structs - this struct is passed on the wire */

struct nbd_option {
    uint64_t magic; /* NBD_OPTS_MAGIC */
    uint32_t option; /* NBD_OPT_* */
    uint32_t length;
} QEMU_PACKED;
typedef struct nbd_option nbd_option;

struct nbd_opt_reply {
    uint64_t magic; /* NBD_REP_MAGIC */
    uint32_t option; /* NBD_OPT_* */
    uint32_t type; /* NBD_REP_* */
    uint32_t length;
} QEMU_PACKED;
typedef struct nbd_opt_reply nbd_opt_reply;

/* Transmission phase structs
 *
 * Note: these are _NOT_ the same as the network representation of an NBD
 * request and reply!
 */
struct NBDRequest {
    uint64_t handle;
    uint64_t from;
    uint32_t len;
    uint16_t flags; /* NBD_CMD_FLAG_* */
    uint16_t type; /* NBD_CMD_* */
};
typedef struct NBDRequest NBDRequest;

typedef struct NBDSimpleReply {
    uint32_t magic;  /* NBD_SIMPLE_REPLY_MAGIC */
    uint32_t error;
    uint64_t handle;
} QEMU_PACKED NBDSimpleReply;

/* Header of all structured replies */
typedef struct NBDStructuredReplyChunk {
    uint32_t magic;  /* NBD_STRUCTURED_REPLY_MAGIC */
    uint16_t flags;  /* combination of NBD_REPLY_FLAG_* */
    uint16_t type;   /* NBD_REPLY_TYPE_* */
    uint64_t handle; /* request handle */
    uint32_t length; /* length of payload */
} QEMU_PACKED NBDStructuredReplyChunk;

typedef union NBDReply {
    NBDSimpleReply simple;
    NBDStructuredReplyChunk structured;
    struct {
        /* @magic and @handle fields have the same offset and size both in
         * simple reply and structured reply chunk, so let them be accessible
         * without ".simple." or ".structured." specification
         */
        uint32_t magic;
        uint32_t _skip;
        uint64_t handle;
    } QEMU_PACKED;
} NBDReply;

/* Header of chunk for NBD_REPLY_TYPE_OFFSET_DATA */
typedef struct NBDStructuredReadData {
    NBDStructuredReplyChunk h; /* h.length >= 9 */
    uint64_t offset;
    /* At least one byte of data payload follows, calculated from h.length */
} QEMU_PACKED NBDStructuredReadData;

/* Complete chunk for NBD_REPLY_TYPE_OFFSET_HOLE */
typedef struct NBDStructuredReadHole {
    NBDStructuredReplyChunk h; /* h.length == 12 */
    uint64_t offset;
    uint32_t length;
} QEMU_PACKED NBDStructuredReadHole;

/* Header of all NBD_REPLY_TYPE_ERROR* errors */
typedef struct NBDStructuredError {
    NBDStructuredReplyChunk h; /* h.length >= 6 */
    uint32_t error;
    uint16_t message_length;
} QEMU_PACKED NBDStructuredError;

/* Transmission (export) flags: sent from server to client during handshake,
   but describe what will happen during transmission */
#define NBD_FLAG_HAS_FLAGS         (1 << 0) /* Flags are there */
#define NBD_FLAG_READ_ONLY         (1 << 1) /* Device is read-only */
#define NBD_FLAG_SEND_FLUSH        (1 << 2) /* Send FLUSH */
#define NBD_FLAG_SEND_FUA          (1 << 3) /* Send FUA (Force Unit Access) */
#define NBD_FLAG_ROTATIONAL        (1 << 4) /* Use elevator algorithm -
                                               rotational media */
#define NBD_FLAG_SEND_TRIM         (1 << 5) /* Send TRIM (discard) */
#define NBD_FLAG_SEND_WRITE_ZEROES (1 << 6) /* Send WRITE_ZEROES */
#define NBD_FLAG_SEND_DF           (1 << 7) /* Send DF (Do not Fragment) */

/* New-style handshake (global) flags, sent from server to client, and
   control what will happen during handshake phase. */
#define NBD_FLAG_FIXED_NEWSTYLE   (1 << 0) /* Fixed newstyle protocol. */
#define NBD_FLAG_NO_ZEROES        (1 << 1) /* End handshake without zeroes. */

/* New-style client flags, sent from client to server to control what happens
   during handshake phase. */
#define NBD_FLAG_C_FIXED_NEWSTYLE (1 << 0) /* Fixed newstyle protocol. */
#define NBD_FLAG_C_NO_ZEROES      (1 << 1) /* End handshake without zeroes. */

/* Option requests. */
#define NBD_OPT_EXPORT_NAME      (1)
#define NBD_OPT_ABORT            (2)
#define NBD_OPT_LIST             (3)
/* #define NBD_OPT_PEEK_EXPORT   (4) not in use */
#define NBD_OPT_STARTTLS         (5)
#define NBD_OPT_INFO             (6)
#define NBD_OPT_GO               (7)
#define NBD_OPT_STRUCTURED_REPLY (8)

/* Option reply types. */
#define NBD_REP_ERR(value) ((UINT32_C(1) << 31) | (value))

#define NBD_REP_ACK             (1)             /* Data sending finished. */
#define NBD_REP_SERVER          (2)             /* Export description. */
#define NBD_REP_INFO            (3)             /* NBD_OPT_INFO/GO. */

#define NBD_REP_ERR_UNSUP           NBD_REP_ERR(1)  /* Unknown option */
#define NBD_REP_ERR_POLICY          NBD_REP_ERR(2)  /* Server denied */
#define NBD_REP_ERR_INVALID         NBD_REP_ERR(3)  /* Invalid length */
#define NBD_REP_ERR_PLATFORM        NBD_REP_ERR(4)  /* Not compiled in */
#define NBD_REP_ERR_TLS_REQD        NBD_REP_ERR(5)  /* TLS required */
#define NBD_REP_ERR_UNKNOWN         NBD_REP_ERR(6)  /* Export unknown */
#define NBD_REP_ERR_SHUTDOWN        NBD_REP_ERR(7)  /* Server shutting down */
#define NBD_REP_ERR_BLOCK_SIZE_REQD NBD_REP_ERR(8)  /* Need INFO_BLOCK_SIZE */

/* Info types, used during NBD_REP_INFO */
#define NBD_INFO_EXPORT         0
#define NBD_INFO_NAME           1
#define NBD_INFO_DESCRIPTION    2
#define NBD_INFO_BLOCK_SIZE     3

/* Request flags, sent from client to server during transmission phase */
#define NBD_CMD_FLAG_FUA        (1 << 0) /* 'force unit access' during write */
#define NBD_CMD_FLAG_NO_HOLE    (1 << 1) /* don't punch hole on zero run */
#define NBD_CMD_FLAG_DF         (1 << 2) /* don't fragment structured read */

/* Supported request types */
enum {
    NBD_CMD_READ = 0,
    NBD_CMD_WRITE = 1,
    NBD_CMD_DISC = 2,
    NBD_CMD_FLUSH = 3,
    NBD_CMD_TRIM = 4,
    /* 5 reserved for failed experiment NBD_CMD_CACHE */
    NBD_CMD_WRITE_ZEROES = 6,
};

#define NBD_DEFAULT_PORT	10809

/* Maximum size of a single READ/WRITE data buffer */
#define NBD_MAX_BUFFER_SIZE (32 * 1024 * 1024)

/* Maximum size of an export name. The NBD spec requires 256 and
 * suggests that servers support up to 4096, but we stick to only the
 * required size so that we can stack-allocate the names, and because
 * going larger would require an audit of more code to make sure we
 * aren't overflowing some other buffer. */
#define NBD_MAX_NAME_SIZE 256

/* Two types of reply structures */
#define NBD_SIMPLE_REPLY_MAGIC      0x67446698
#define NBD_STRUCTURED_REPLY_MAGIC  0x668e33ef

/* Structured reply flags */
#define NBD_REPLY_FLAG_DONE          (1 << 0) /* This reply-chunk is last */

/* Structured reply types */
#define NBD_REPLY_ERR(value)         ((1 << 15) | (value))

#define NBD_REPLY_TYPE_NONE          0
#define NBD_REPLY_TYPE_OFFSET_DATA   1
#define NBD_REPLY_TYPE_OFFSET_HOLE   2
#define NBD_REPLY_TYPE_ERROR         NBD_REPLY_ERR(1)
#define NBD_REPLY_TYPE_ERROR_OFFSET  NBD_REPLY_ERR(2)

static inline bool nbd_reply_type_is_error(int type)
{
    return type & (1 << 15);
}

/* NBD errors are based on errno numbers, so there is a 1:1 mapping,
 * but only a limited set of errno values is specified in the protocol.
 * Everything else is squashed to EINVAL.
 */
#define NBD_SUCCESS    0
#define NBD_EPERM      1
#define NBD_EIO        5
#define NBD_ENOMEM     12
#define NBD_EINVAL     22
#define NBD_ENOSPC     28
#define NBD_EOVERFLOW  75
#define NBD_ESHUTDOWN  108

/* Details collected by NBD_OPT_EXPORT_NAME and NBD_OPT_GO */
struct NBDExportInfo {
    /* Set by client before nbd_receive_negotiate() */
    bool request_sizes;

    /* In-out fields, set by client before nbd_receive_negotiate() and
     * updated by server results during nbd_receive_negotiate() */
    bool structured_reply;

    /* Set by server results during nbd_receive_negotiate() */
    uint64_t size;
    uint16_t flags;
    uint32_t min_block;
    uint32_t opt_block;
    uint32_t max_block;
};
typedef struct NBDExportInfo NBDExportInfo;

int nbd_receive_negotiate(QIOChannel *ioc, const char *name,
                          QCryptoTLSCreds *tlscreds, const char *hostname,
                          QIOChannel **outioc, NBDExportInfo *info,
                          Error **errp);
int nbd_init(int fd, QIOChannelSocket *sioc, NBDExportInfo *info,
             Error **errp);
int nbd_send_request(QIOChannel *ioc, NBDRequest *request);
int nbd_receive_reply(QIOChannel *ioc, NBDReply *reply, Error **errp);
int nbd_client(int fd);
int nbd_disconnect(int fd);
int nbd_errno_to_system_errno(int err);

typedef struct NBDExport NBDExport;
typedef struct NBDClient NBDClient;

NBDExport *nbd_export_new(BlockDriverState *bs, off_t dev_offset, off_t size,
                          uint16_t nbdflags, void (*close)(NBDExport *),
                          bool writethrough, BlockBackend *on_eject_blk,
                          Error **errp);
void nbd_export_close(NBDExport *exp);
void nbd_export_get(NBDExport *exp);
void nbd_export_put(NBDExport *exp);

BlockBackend *nbd_export_get_blockdev(NBDExport *exp);

NBDExport *nbd_export_find(const char *name);
void nbd_export_set_name(NBDExport *exp, const char *name);
void nbd_export_set_description(NBDExport *exp, const char *description);
void nbd_export_close_all(void);

void nbd_client_new(NBDExport *exp,
                    QIOChannelSocket *sioc,
                    QCryptoTLSCreds *tlscreds,
                    const char *tlsaclname,
                    void (*close_fn)(NBDClient *, bool));
void nbd_client_get(NBDClient *client);
void nbd_client_put(NBDClient *client);

void nbd_server_start(SocketAddress *addr, const char *tls_creds,
                      Error **errp);


/* nbd_read
 * Reads @size bytes from @ioc. Returns 0 on success.
 */
static inline int nbd_read(QIOChannel *ioc, void *buffer, size_t size,
                           Error **errp)
{
    return qio_channel_read_all(ioc, buffer, size, errp) < 0 ? -EIO : 0;
}

static inline bool nbd_reply_is_simple(NBDReply *reply)
{
    return reply->magic == NBD_SIMPLE_REPLY_MAGIC;
}

static inline bool nbd_reply_is_structured(NBDReply *reply)
{
    return reply->magic == NBD_STRUCTURED_REPLY_MAGIC;
}

const char *nbd_reply_type_lookup(uint16_t type);

#endif