aboutsummaryrefslogtreecommitdiff
path: root/block/rbd.c
blob: 2cee70d6785050f8222dba7b4b718681d162061b (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
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
/*
 * QEMU Block driver for RADOS (Ceph)
 *
 * Copyright (C) 2010-2011 Christian Brunner <chb@muc.de>,
 *                         Josh Durgin <josh.durgin@dreamhost.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include <inttypes.h>

#include "qemu-common.h"
#include "qemu-error.h"

#include "block_int.h"

#include <rbd/librbd.h>



/*
 * When specifying the image filename use:
 *
 * rbd:poolname/devicename
 *
 * poolname must be the name of an existing rados pool
 *
 * devicename is the basename for all objects used to
 * emulate the raw device.
 *
 * Metadata information (image size, ...) is stored in an
 * object with the name "devicename.rbd".
 *
 * The raw device is split into 4MB sized objects by default.
 * The sequencenumber is encoded in a 12 byte long hex-string,
 * and is attached to the devicename, separated by a dot.
 * e.g. "devicename.1234567890ab"
 *
 */

#define OBJ_MAX_SIZE (1UL << OBJ_DEFAULT_OBJ_ORDER)

#define RBD_MAX_CONF_NAME_SIZE 128
#define RBD_MAX_CONF_VAL_SIZE 512
#define RBD_MAX_CONF_SIZE 1024
#define RBD_MAX_POOL_NAME_SIZE 128
#define RBD_MAX_SNAP_NAME_SIZE 128
#define RBD_MAX_SNAPS 100

typedef struct RBDAIOCB {
    BlockDriverAIOCB common;
    QEMUBH *bh;
    int ret;
    QEMUIOVector *qiov;
    char *bounce;
    int write;
    int64_t sector_num;
    int error;
    struct BDRVRBDState *s;
    int cancelled;
} RBDAIOCB;

typedef struct RADOSCB {
    int rcbid;
    RBDAIOCB *acb;
    struct BDRVRBDState *s;
    int done;
    int64_t size;
    char *buf;
    int ret;
} RADOSCB;

#define RBD_FD_READ 0
#define RBD_FD_WRITE 1

typedef struct BDRVRBDState {
    int fds[2];
    rados_t cluster;
    rados_ioctx_t io_ctx;
    rbd_image_t image;
    char name[RBD_MAX_IMAGE_NAME_SIZE];
    int qemu_aio_count;
    char *snap;
    int event_reader_pos;
    RADOSCB *event_rcb;
} BDRVRBDState;

static void rbd_aio_bh_cb(void *opaque);

static int qemu_rbd_next_tok(char *dst, int dst_len,
                             char *src, char delim,
                             const char *name,
                             char **p)
{
    int l;
    char *end;

    *p = NULL;

    if (delim != '\0') {
        end = strchr(src, delim);
        if (end) {
            *p = end + 1;
            *end = '\0';
        }
    }
    l = strlen(src);
    if (l >= dst_len) {
        error_report("%s too long", name);
        return -EINVAL;
    } else if (l == 0) {
        error_report("%s too short", name);
        return -EINVAL;
    }

    pstrcpy(dst, dst_len, src);

    return 0;
}

static int qemu_rbd_parsename(const char *filename,
                              char *pool, int pool_len,
                              char *snap, int snap_len,
                              char *name, int name_len)
{
    const char *start;
    char *p, *buf;
    int ret;

    if (!strstart(filename, "rbd:", &start)) {
        return -EINVAL;
    }

    buf = qemu_strdup(start);
    p = buf;

    ret = qemu_rbd_next_tok(pool, pool_len, p, '/', "pool name", &p);
    if (ret < 0 || !p) {
        ret = -EINVAL;
        goto done;
    }
    ret = qemu_rbd_next_tok(name, name_len, p, '@', "object name", &p);
    if (ret < 0) {
        goto done;
    }
    if (!p) {
        *snap = '\0';
        goto done;
    }

    ret = qemu_rbd_next_tok(snap, snap_len, p, '\0', "snap name", &p);

done:
    qemu_free(buf);
    return ret;
}

static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options)
{
    int64_t bytes = 0;
    int64_t objsize;
    int obj_order = 0;
    char pool[RBD_MAX_POOL_NAME_SIZE];
    char name[RBD_MAX_IMAGE_NAME_SIZE];
    char snap_buf[RBD_MAX_SNAP_NAME_SIZE];
    char *snap = NULL;
    rados_t cluster;
    rados_ioctx_t io_ctx;
    int ret;

    if (qemu_rbd_parsename(filename, pool, sizeof(pool),
                           snap_buf, sizeof(snap_buf),
                           name, sizeof(name)) < 0) {
        return -EINVAL;
    }
    if (snap_buf[0] != '\0') {
        snap = snap_buf;
    }

    /* Read out options */
    while (options && options->name) {
        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
            bytes = options->value.n;
        } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
            if (options->value.n) {
                objsize = options->value.n;
                if ((objsize - 1) & objsize) {    /* not a power of 2? */
                    error_report("obj size needs to be power of 2");
                    return -EINVAL;
                }
                if (objsize < 4096) {
                    error_report("obj size too small");
                    return -EINVAL;
                }
                obj_order = ffs(objsize) - 1;
            }
        }
        options++;
    }

    if (rados_create(&cluster, NULL) < 0) {
        error_report("error initializing");
        return -EIO;
    }

    if (rados_conf_read_file(cluster, NULL) < 0) {
        error_report("error reading config file");
        rados_shutdown(cluster);
        return -EIO;
    }

    if (rados_connect(cluster) < 0) {
        error_report("error connecting");
        rados_shutdown(cluster);
        return -EIO;
    }

    if (rados_ioctx_create(cluster, pool, &io_ctx) < 0) {
        error_report("error opening pool %s", pool);
        rados_shutdown(cluster);
        return -EIO;
    }

    ret = rbd_create(io_ctx, name, bytes, &obj_order);
    rados_ioctx_destroy(io_ctx);
    rados_shutdown(cluster);

    return ret;
}

/*
 * This aio completion is being called from qemu_rbd_aio_event_reader()
 * and runs in qemu context. It schedules a bh, but just in case the aio
 * was not cancelled before.
 */
static void qemu_rbd_complete_aio(RADOSCB *rcb)
{
    RBDAIOCB *acb = rcb->acb;
    int64_t r;

    if (acb->cancelled) {
        qemu_vfree(acb->bounce);
        qemu_aio_release(acb);
        goto done;
    }

    r = rcb->ret;

    if (acb->write) {
        if (r < 0) {
            acb->ret = r;
            acb->error = 1;
        } else if (!acb->error) {
            acb->ret = rcb->size;
        }
    } else {
        if (r < 0) {
            memset(rcb->buf, 0, rcb->size);
            acb->ret = r;
            acb->error = 1;
        } else if (r < rcb->size) {
            memset(rcb->buf + r, 0, rcb->size - r);
            if (!acb->error) {
                acb->ret = rcb->size;
            }
        } else if (!acb->error) {
            acb->ret = r;
        }
    }
    /* Note that acb->bh can be NULL in case where the aio was cancelled */
    acb->bh = qemu_bh_new(rbd_aio_bh_cb, acb);
    qemu_bh_schedule(acb->bh);
done:
    qemu_free(rcb);
}

/*
 * aio fd read handler. It runs in the qemu context and calls the
 * completion handling of completed rados aio operations.
 */
static void qemu_rbd_aio_event_reader(void *opaque)
{
    BDRVRBDState *s = opaque;

    ssize_t ret;

    do {
        char *p = (char *)&s->event_rcb;

        /* now read the rcb pointer that was sent from a non qemu thread */
        if ((ret = read(s->fds[RBD_FD_READ], p + s->event_reader_pos,
                        sizeof(s->event_rcb) - s->event_reader_pos)) > 0) {
            if (ret > 0) {
                s->event_reader_pos += ret;
                if (s->event_reader_pos == sizeof(s->event_rcb)) {
                    s->event_reader_pos = 0;
                    qemu_rbd_complete_aio(s->event_rcb);
                    s->qemu_aio_count--;
                }
            }
        }
    } while (ret < 0 && errno == EINTR);
}

static int qemu_rbd_aio_flush_cb(void *opaque)
{
    BDRVRBDState *s = opaque;

    return (s->qemu_aio_count > 0);
}

static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags)
{
    BDRVRBDState *s = bs->opaque;
    char pool[RBD_MAX_POOL_NAME_SIZE];
    char snap_buf[RBD_MAX_SNAP_NAME_SIZE];
    int r;

    if (qemu_rbd_parsename(filename, pool, sizeof(pool),
                           snap_buf, sizeof(snap_buf),
                           s->name, sizeof(s->name)) < 0) {
        return -EINVAL;
    }
    s->snap = NULL;
    if (snap_buf[0] != '\0') {
        s->snap = qemu_strdup(snap_buf);
    }

    r = rados_create(&s->cluster, NULL);
    if (r < 0) {
        error_report("error initializing");
        return r;
    }

    r = rados_conf_read_file(s->cluster, NULL);
    if (r < 0) {
        error_report("error reading config file");
        rados_shutdown(s->cluster);
        return r;
    }

    r = rados_connect(s->cluster);
    if (r < 0) {
        error_report("error connecting");
        rados_shutdown(s->cluster);
        return r;
    }

    r = rados_ioctx_create(s->cluster, pool, &s->io_ctx);
    if (r < 0) {
        error_report("error opening pool %s", pool);
        rados_shutdown(s->cluster);
        return r;
    }

    r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
    if (r < 0) {
        error_report("error reading header from %s", s->name);
        rados_ioctx_destroy(s->io_ctx);
        rados_shutdown(s->cluster);
        return r;
    }

    bs->read_only = (s->snap != NULL);

    s->event_reader_pos = 0;
    r = qemu_pipe(s->fds);
    if (r < 0) {
        error_report("error opening eventfd");
        goto failed;
    }
    fcntl(s->fds[0], F_SETFL, O_NONBLOCK);
    fcntl(s->fds[1], F_SETFL, O_NONBLOCK);
    qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], qemu_rbd_aio_event_reader,
                            NULL, qemu_rbd_aio_flush_cb, NULL, s);


    return 0;

failed:
    rbd_close(s->image);
    rados_ioctx_destroy(s->io_ctx);
    rados_shutdown(s->cluster);
    return r;
}

static void qemu_rbd_close(BlockDriverState *bs)
{
    BDRVRBDState *s = bs->opaque;

    close(s->fds[0]);
    close(s->fds[1]);
    qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], NULL , NULL, NULL, NULL,
        NULL);

    rbd_close(s->image);
    rados_ioctx_destroy(s->io_ctx);
    qemu_free(s->snap);
    rados_shutdown(s->cluster);
}

/*
 * Cancel aio. Since we don't reference acb in a non qemu threads,
 * it is safe to access it here.
 */
static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
{
    RBDAIOCB *acb = (RBDAIOCB *) blockacb;
    acb->cancelled = 1;
}

static AIOPool rbd_aio_pool = {
    .aiocb_size = sizeof(RBDAIOCB),
    .cancel = qemu_rbd_aio_cancel,
};

static int qemu_rbd_send_pipe(BDRVRBDState *s, RADOSCB *rcb)
{
    int ret = 0;
    while (1) {
        fd_set wfd;
        int fd = s->fds[RBD_FD_WRITE];

        /* send the op pointer to the qemu thread that is responsible
           for the aio/op completion. Must do it in a qemu thread context */
        ret = write(fd, (void *)&rcb, sizeof(rcb));
        if (ret >= 0) {
            break;
        }
        if (errno == EINTR) {
            continue;
        }
        if (errno != EAGAIN) {
            break;
        }

        FD_ZERO(&wfd);
        FD_SET(fd, &wfd);
        do {
            ret = select(fd + 1, NULL, &wfd, NULL, NULL);
        } while (ret < 0 && errno == EINTR);
    }

    return ret;
}

/*
 * This is the callback function for rbd_aio_read and _write
 *
 * Note: this function is being called from a non qemu thread so
 * we need to be careful about what we do here. Generally we only
 * write to the block notification pipe, and do the rest of the
 * io completion handling from qemu_rbd_aio_event_reader() which
 * runs in a qemu context.
 */
static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb)
{
    int ret;
    rcb->ret = rbd_aio_get_return_value(c);
    rbd_aio_release(c);
    ret = qemu_rbd_send_pipe(rcb->s, rcb);
    if (ret < 0) {
        error_report("failed writing to acb->s->fds");
        qemu_free(rcb);
    }
}

/* Callback when all queued rbd_aio requests are complete */

static void rbd_aio_bh_cb(void *opaque)
{
    RBDAIOCB *acb = opaque;

    if (!acb->write) {
        qemu_iovec_from_buffer(acb->qiov, acb->bounce, acb->qiov->size);
    }
    qemu_vfree(acb->bounce);
    acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
    qemu_bh_delete(acb->bh);
    acb->bh = NULL;

    qemu_aio_release(acb);
}

static BlockDriverAIOCB *rbd_aio_rw_vector(BlockDriverState *bs,
                                           int64_t sector_num,
                                           QEMUIOVector *qiov,
                                           int nb_sectors,
                                           BlockDriverCompletionFunc *cb,
                                           void *opaque, int write)
{
    RBDAIOCB *acb;
    RADOSCB *rcb;
    rbd_completion_t c;
    int64_t off, size;
    char *buf;

    BDRVRBDState *s = bs->opaque;

    acb = qemu_aio_get(&rbd_aio_pool, bs, cb, opaque);
    acb->write = write;
    acb->qiov = qiov;
    acb->bounce = qemu_blockalign(bs, qiov->size);
    acb->ret = 0;
    acb->error = 0;
    acb->s = s;
    acb->cancelled = 0;
    acb->bh = NULL;

    if (write) {
        qemu_iovec_to_buffer(acb->qiov, acb->bounce);
    }

    buf = acb->bounce;

    off = sector_num * BDRV_SECTOR_SIZE;
    size = nb_sectors * BDRV_SECTOR_SIZE;

    s->qemu_aio_count++; /* All the RADOSCB */

    rcb = qemu_malloc(sizeof(RADOSCB));
    rcb->done = 0;
    rcb->acb = acb;
    rcb->buf = buf;
    rcb->s = acb->s;
    rcb->size = size;

    if (write) {
        rbd_aio_create_completion(rcb, (rbd_callback_t) rbd_finish_aiocb, &c);
        rbd_aio_write(s->image, off, size, buf, c);
    } else {
        rbd_aio_create_completion(rcb, (rbd_callback_t) rbd_finish_aiocb, &c);
        rbd_aio_read(s->image, off, size, buf, c);
    }

    return &acb->common;
}

static BlockDriverAIOCB *qemu_rbd_aio_readv(BlockDriverState *bs,
                                            int64_t sector_num,
                                            QEMUIOVector *qiov,
                                            int nb_sectors,
                                            BlockDriverCompletionFunc *cb,
                                            void *opaque)
{
    return rbd_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
}

static BlockDriverAIOCB *qemu_rbd_aio_writev(BlockDriverState *bs,
                                             int64_t sector_num,
                                             QEMUIOVector *qiov,
                                             int nb_sectors,
                                             BlockDriverCompletionFunc *cb,
                                             void *opaque)
{
    return rbd_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 1);
}

static int qemu_rbd_getinfo(BlockDriverState *bs, BlockDriverInfo *bdi)
{
    BDRVRBDState *s = bs->opaque;
    rbd_image_info_t info;
    int r;

    r = rbd_stat(s->image, &info, sizeof(info));
    if (r < 0) {
        return r;
    }

    bdi->cluster_size = info.obj_size;
    return 0;
}

static int64_t qemu_rbd_getlength(BlockDriverState *bs)
{
    BDRVRBDState *s = bs->opaque;
    rbd_image_info_t info;
    int r;

    r = rbd_stat(s->image, &info, sizeof(info));
    if (r < 0) {
        return r;
    }

    return info.size;
}

static int qemu_rbd_snap_create(BlockDriverState *bs,
                                QEMUSnapshotInfo *sn_info)
{
    BDRVRBDState *s = bs->opaque;
    int r;

    if (sn_info->name[0] == '\0') {
        return -EINVAL; /* we need a name for rbd snapshots */
    }

    /*
     * rbd snapshots are using the name as the user controlled unique identifier
     * we can't use the rbd snapid for that purpose, as it can't be set
     */
    if (sn_info->id_str[0] != '\0' &&
        strcmp(sn_info->id_str, sn_info->name) != 0) {
        return -EINVAL;
    }

    if (strlen(sn_info->name) >= sizeof(sn_info->id_str)) {
        return -ERANGE;
    }

    r = rbd_snap_create(s->image, sn_info->name);
    if (r < 0) {
        error_report("failed to create snap: %s", strerror(-r));
        return r;
    }

    return 0;
}

static int qemu_rbd_snap_list(BlockDriverState *bs,
                              QEMUSnapshotInfo **psn_tab)
{
    BDRVRBDState *s = bs->opaque;
    QEMUSnapshotInfo *sn_info, *sn_tab = NULL;
    int i, snap_count;
    rbd_snap_info_t *snaps;
    int max_snaps = RBD_MAX_SNAPS;

    do {
        snaps = qemu_malloc(sizeof(*snaps) * max_snaps);
        snap_count = rbd_snap_list(s->image, snaps, &max_snaps);
        if (snap_count < 0) {
            qemu_free(snaps);
        }
    } while (snap_count == -ERANGE);

    if (snap_count <= 0) {
        return snap_count;
    }

    sn_tab = qemu_mallocz(snap_count * sizeof(QEMUSnapshotInfo));

    for (i = 0; i < snap_count; i++) {
        const char *snap_name = snaps[i].name;

        sn_info = sn_tab + i;
        pstrcpy(sn_info->id_str, sizeof(sn_info->id_str), snap_name);
        pstrcpy(sn_info->name, sizeof(sn_info->name), snap_name);

        sn_info->vm_state_size = snaps[i].size;
        sn_info->date_sec = 0;
        sn_info->date_nsec = 0;
        sn_info->vm_clock_nsec = 0;
    }
    rbd_snap_list_end(snaps);

    *psn_tab = sn_tab;
    return snap_count;
}

static QEMUOptionParameter qemu_rbd_create_options[] = {
    {
     .name = BLOCK_OPT_SIZE,
     .type = OPT_SIZE,
     .help = "Virtual disk size"
    },
    {
     .name = BLOCK_OPT_CLUSTER_SIZE,
     .type = OPT_SIZE,
     .help = "RBD object size"
    },
    {NULL}
};

static BlockDriver bdrv_rbd = {
    .format_name        = "rbd",
    .instance_size      = sizeof(BDRVRBDState),
    .bdrv_file_open     = qemu_rbd_open,
    .bdrv_close         = qemu_rbd_close,
    .bdrv_create        = qemu_rbd_create,
    .bdrv_get_info      = qemu_rbd_getinfo,
    .create_options     = qemu_rbd_create_options,
    .bdrv_getlength     = qemu_rbd_getlength,
    .protocol_name      = "rbd",

    .bdrv_aio_readv     = qemu_rbd_aio_readv,
    .bdrv_aio_writev    = qemu_rbd_aio_writev,

    .bdrv_snapshot_create = qemu_rbd_snap_create,
    .bdrv_snapshot_list = qemu_rbd_snap_list,
};

static void bdrv_rbd_init(void)
{
    bdrv_register(&bdrv_rbd);
}

block_init(bdrv_rbd_init);