summaryrefslogtreecommitdiffstats
path: root/block/nbd-client.c
blob: 0922b7829221b37a1a993d2cc1d27f5bc3315bd3 (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
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
/*
 * QEMU Block driver for  NBD
 *
 * Copyright (C) 2008 Bull S.A.S.
 *     Author: Laurent Vivier <Laurent.Vivier@bull.net>
 *
 * Some parts:
 *    Copyright (C) 2007 Anthony Liguori <anthony@codemonkey.ws>
 *
 * 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.
 */

#include "nbd-client.h"
#include "qemu/sockets.h"

#define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs))
#define INDEX_TO_HANDLE(bs, index)  ((index)  ^ ((uint64_t)(intptr_t)bs))

static void nbd_recv_coroutines_enter_all(NbdClientSession *s)
{
    int i;

    for (i = 0; i < MAX_NBD_REQUESTS; i++) {
        if (s->recv_coroutine[i]) {
            qemu_coroutine_enter(s->recv_coroutine[i], NULL);
        }
    }
}

static void nbd_reply_ready(void *opaque)
{
    NbdClientSession *s = opaque;
    uint64_t i;
    int ret;

    if (s->reply.handle == 0) {
        /* No reply already in flight.  Fetch a header.  It is possible
         * that another thread has done the same thing in parallel, so
         * the socket is not readable anymore.
         */
        ret = nbd_receive_reply(s->sock, &s->reply);
        if (ret == -EAGAIN) {
            return;
        }
        if (ret < 0) {
            s->reply.handle = 0;
            goto fail;
        }
    }

    /* There's no need for a mutex on the receive side, because the
     * handler acts as a synchronization point and ensures that only
     * one coroutine is called until the reply finishes.  */
    i = HANDLE_TO_INDEX(s, s->reply.handle);
    if (i >= MAX_NBD_REQUESTS) {
        goto fail;
    }

    if (s->recv_coroutine[i]) {
        qemu_coroutine_enter(s->recv_coroutine[i], NULL);
        return;
    }

fail:
    nbd_recv_coroutines_enter_all(s);
}

static void nbd_restart_write(void *opaque)
{
    NbdClientSession *s = opaque;

    qemu_coroutine_enter(s->send_coroutine, NULL);
}

static int nbd_co_send_request(NbdClientSession *s,
    struct nbd_request *request,
    QEMUIOVector *qiov, int offset)
{
    int rc, ret;

    qemu_co_mutex_lock(&s->send_mutex);
    s->send_coroutine = qemu_coroutine_self();
    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, nbd_restart_write, s);
    if (qiov) {
        if (!s->is_unix) {
            socket_set_cork(s->sock, 1);
        }
        rc = nbd_send_request(s->sock, request);
        if (rc >= 0) {
            ret = qemu_co_sendv(s->sock, qiov->iov, qiov->niov,
                                offset, request->len);
            if (ret != request->len) {
                rc = -EIO;
            }
        }
        if (!s->is_unix) {
            socket_set_cork(s->sock, 0);
        }
    } else {
        rc = nbd_send_request(s->sock, request);
    }
    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, NULL, s);
    s->send_coroutine = NULL;
    qemu_co_mutex_unlock(&s->send_mutex);
    return rc;
}

static void nbd_co_receive_reply(NbdClientSession *s,
    struct nbd_request *request, struct nbd_reply *reply,
    QEMUIOVector *qiov, int offset)
{
    int ret;

    /* Wait until we're woken up by the read handler.  TODO: perhaps
     * peek at the next reply and avoid yielding if it's ours?  */
    qemu_coroutine_yield();
    *reply = s->reply;
    if (reply->handle != request->handle) {
        reply->error = EIO;
    } else {
        if (qiov && reply->error == 0) {
            ret = qemu_co_recvv(s->sock, qiov->iov, qiov->niov,
                                offset, request->len);
            if (ret != request->len) {
                reply->error = EIO;
            }
        }

        /* Tell the read handler to read another header.  */
        s->reply.handle = 0;
    }
}

static void nbd_coroutine_start(NbdClientSession *s,
   struct nbd_request *request)
{
    int i;

    /* Poor man semaphore.  The free_sema is locked when no other request
     * can be accepted, and unlocked after receiving one reply.  */
    if (s->in_flight >= MAX_NBD_REQUESTS - 1) {
        qemu_co_mutex_lock(&s->free_sema);
        assert(s->in_flight < MAX_NBD_REQUESTS);
    }
    s->in_flight++;

    for (i = 0; i < MAX_NBD_REQUESTS; i++) {
        if (s->recv_coroutine[i] == NULL) {
            s->recv_coroutine[i] = qemu_coroutine_self();
            break;
        }
    }

    assert(i < MAX_NBD_REQUESTS);
    request->handle = INDEX_TO_HANDLE(s, i);
}

static void nbd_coroutine_end(NbdClientSession *s,
    struct nbd_request *request)
{
    int i = HANDLE_TO_INDEX(s, request->handle);
    s->recv_coroutine[i] = NULL;
    if (s->in_flight-- == MAX_NBD_REQUESTS) {
        qemu_co_mutex_unlock(&s->free_sema);
    }
}

static int nbd_co_readv_1(NbdClientSession *client, int64_t sector_num,
                          int nb_sectors, QEMUIOVector *qiov,
                          int offset)
{
    struct nbd_request request = { .type = NBD_CMD_READ };
    struct nbd_reply reply;
    ssize_t ret;

    request.from = sector_num * 512;
    request.len = nb_sectors * 512;

    nbd_coroutine_start(client, &request);
    ret = nbd_co_send_request(client, &request, NULL, 0);
    if (ret < 0) {
        reply.error = -ret;
    } else {
        nbd_co_receive_reply(client, &request, &reply, qiov, offset);
    }
    nbd_coroutine_end(client, &request);
    return -reply.error;

}

static int nbd_co_writev_1(NbdClientSession *client, int64_t sector_num,
                           int nb_sectors, QEMUIOVector *qiov,
                           int offset)
{
    struct nbd_request request = { .type = NBD_CMD_WRITE };
    struct nbd_reply reply;
    ssize_t ret;

    if (!bdrv_enable_write_cache(client->bs) &&
        (client->nbdflags & NBD_FLAG_SEND_FUA)) {
        request.type |= NBD_CMD_FLAG_FUA;
    }

    request.from = sector_num * 512;
    request.len = nb_sectors * 512;

    nbd_coroutine_start(client, &request);
    ret = nbd_co_send_request(client, &request, qiov, offset);
    if (ret < 0) {
        reply.error = -ret;
    } else {
        nbd_co_receive_reply(client, &request, &reply, NULL, 0);
    }
    nbd_coroutine_end(client, &request);
    return -reply.error;
}

/* qemu-nbd has a limit of slightly less than 1M per request.  Try to
 * remain aligned to 4K. */
#define NBD_MAX_SECTORS 2040

int nbd_client_session_co_readv(NbdClientSession *client, int64_t sector_num,
    int nb_sectors, QEMUIOVector *qiov)
{
    int offset = 0;
    int ret;
    while (nb_sectors > NBD_MAX_SECTORS) {
        ret = nbd_co_readv_1(client, sector_num,
                             NBD_MAX_SECTORS, qiov, offset);
        if (ret < 0) {
            return ret;
        }
        offset += NBD_MAX_SECTORS * 512;
        sector_num += NBD_MAX_SECTORS;
        nb_sectors -= NBD_MAX_SECTORS;
    }
    return nbd_co_readv_1(client, sector_num, nb_sectors, qiov, offset);
}

int nbd_client_session_co_writev(NbdClientSession *client, int64_t sector_num,
                                 int nb_sectors, QEMUIOVector *qiov)
{
    int offset = 0;
    int ret;
    while (nb_sectors > NBD_MAX_SECTORS) {
        ret = nbd_co_writev_1(client, sector_num,
                              NBD_MAX_SECTORS, qiov, offset);
        if (ret < 0) {
            return ret;
        }
        offset += NBD_MAX_SECTORS * 512;
        sector_num += NBD_MAX_SECTORS;
        nb_sectors -= NBD_MAX_SECTORS;
    }
    return nbd_co_writev_1(client, sector_num, nb_sectors, qiov, offset);
}

int nbd_client_session_co_flush(NbdClientSession *client)
{
    struct nbd_request request = { .type = NBD_CMD_FLUSH };
    struct nbd_reply reply;
    ssize_t ret;

    if (!(client->nbdflags & NBD_FLAG_SEND_FLUSH)) {
        return 0;
    }

    if (client->nbdflags & NBD_FLAG_SEND_FUA) {
        request.type |= NBD_CMD_FLAG_FUA;
    }

    request.from = 0;
    request.len = 0;

    nbd_coroutine_start(client, &request);
    ret = nbd_co_send_request(client, &request, NULL, 0);
    if (ret < 0) {
        reply.error = -ret;
    } else {
        nbd_co_receive_reply(client, &request, &reply, NULL, 0);
    }
    nbd_coroutine_end(client, &request);
    return -reply.error;
}

int nbd_client_session_co_discard(NbdClientSession *client, int64_t sector_num,
    int nb_sectors)
{
    struct nbd_request request = { .type = NBD_CMD_TRIM };
    struct nbd_reply reply;
    ssize_t ret;

    if (!(client->nbdflags & NBD_FLAG_SEND_TRIM)) {
        return 0;
    }
    request.from = sector_num * 512;
    request.len = nb_sectors * 512;

    nbd_coroutine_start(client, &request);
    ret = nbd_co_send_request(client, &request, NULL, 0);
    if (ret < 0) {
        reply.error = -ret;
    } else {
        nbd_co_receive_reply(client, &request, &reply, NULL, 0);
    }
    nbd_coroutine_end(client, &request);
    return -reply.error;

}

static void nbd_teardown_connection(NbdClientSession *client)
{
    struct nbd_request request = {
        .type = NBD_CMD_DISC,
        .from = 0,
        .len = 0
    };

    nbd_send_request(client->sock, &request);

    /* finish any pending coroutines */
    shutdown(client->sock, 2);
    nbd_recv_coroutines_enter_all(client);

    qemu_aio_set_fd_handler(client->sock, NULL, NULL, NULL);
    closesocket(client->sock);
    client->sock = -1;
}

void nbd_client_session_close(NbdClientSession *client)
{
    if (!client->bs) {
        return;
    }

    nbd_teardown_connection(client);
    client->bs = NULL;
}

int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
    int sock, const char *export)
{
    int ret;

    /* NBD handshake */
    logout("session init %s\n", export);
    qemu_set_block(sock);
    ret = nbd_receive_negotiate(sock, export,
                                &client->nbdflags, &client->size,
                                &client->blocksize);
    if (ret < 0) {
        logout("Failed to negotiate with the NBD server\n");
        closesocket(sock);
        return ret;
    }

    qemu_co_mutex_init(&client->send_mutex);
    qemu_co_mutex_init(&client->free_sema);
    client->bs = bs;
    client->sock = sock;

    /* Now that we're connected, set the socket to be non-blocking and
     * kick the reply mechanism.  */
    qemu_set_nonblock(sock);
    qemu_aio_set_fd_handler(sock, nbd_reply_ready, NULL, client);

    logout("Established connection with NBD server\n");
    return 0;
}
OpenPOWER on IntegriCloud