aboutsummaryrefslogtreecommitdiff
path: root/block/rbd.c
blob: a57b3e3c5d5179b79726c4e497c32f8f7887a478 (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
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
/*
 * 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.
 *
 * Contributions after 2012-01-13 are licensed under the terms of the
 * GNU GPL, version 2 or (at your option) any later version.
 */

#include "qemu/osdep.h"

#include "qapi/error.h"
#include "qemu/error-report.h"
#include "block/block_int.h"
#include "crypto/secret.h"
#include "qemu/cutils.h"

#include <rbd/librbd.h>

/*
 * When specifying the image filename use:
 *
 * rbd:poolname/devicename[@snapshotname][:option1=value1[:option2=value2...]]
 *
 * poolname must be the name of an existing rados pool.
 *
 * devicename is the name of the rbd image.
 *
 * Each option given is used to configure rados, and may be any valid
 * Ceph option, "id", or "conf".
 *
 * The "id" option indicates what user we should authenticate as to
 * the Ceph cluster.  If it is excluded we will use the Ceph default
 * (normally 'admin').
 *
 * The "conf" option specifies a Ceph configuration file to read.  If
 * it is not specified, we will read from the default Ceph locations
 * (e.g., /etc/ceph/ceph.conf).  To avoid reading _any_ configuration
 * file, specify conf=/dev/null.
 *
 * Configuration values containing :, @, or = can be escaped with a
 * leading "\".
 */

/* rbd_aio_discard added in 0.1.2 */
#if LIBRBD_VERSION_CODE >= LIBRBD_VERSION(0, 1, 2)
#define LIBRBD_SUPPORTS_DISCARD
#else
#undef LIBRBD_SUPPORTS_DISCARD
#endif

#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 enum {
    RBD_AIO_READ,
    RBD_AIO_WRITE,
    RBD_AIO_DISCARD,
    RBD_AIO_FLUSH
} RBDAIOCmd;

typedef struct RBDAIOCB {
    BlockAIOCB common;
    int64_t ret;
    QEMUIOVector *qiov;
    char *bounce;
    RBDAIOCmd cmd;
    int error;
    struct BDRVRBDState *s;
} RBDAIOCB;

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

typedef struct BDRVRBDState {
    rados_t cluster;
    rados_ioctx_t io_ctx;
    rbd_image_t image;
    char name[RBD_MAX_IMAGE_NAME_SIZE];
    char *snap;
} BDRVRBDState;

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

    *p = NULL;

    if (delim != '\0') {
        for (end = src; *end; ++end) {
            if (*end == delim) {
                break;
            }
            if (*end == '\\' && end[1] != '\0') {
                end++;
            }
        }
        if (*end == delim) {
            *p = end + 1;
            *end = '\0';
        }
    }
    l = strlen(src);
    if (l >= dst_len) {
        error_setg(errp, "%s too long", name);
        return -EINVAL;
    } else if (l == 0) {
        error_setg(errp, "%s too short", name);
        return -EINVAL;
    }

    pstrcpy(dst, dst_len, src);

    return 0;
}

static void qemu_rbd_unescape(char *src)
{
    char *p;

    for (p = src; *src; ++src, ++p) {
        if (*src == '\\' && src[1] != '\0') {
            src++;
        }
        *p = *src;
    }
    *p = '\0';
}

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

    if (!strstart(filename, "rbd:", &start)) {
        error_setg(errp, "File name must start with 'rbd:'");
        return -EINVAL;
    }

    buf = g_strdup(start);
    p = buf;
    *snap = '\0';
    *conf = '\0';

    ret = qemu_rbd_next_tok(pool, pool_len, p,
                            '/', "pool name", &p, errp);
    if (ret < 0 || !p) {
        ret = -EINVAL;
        goto done;
    }
    qemu_rbd_unescape(pool);

    if (strchr(p, '@')) {
        ret = qemu_rbd_next_tok(name, name_len, p,
                                '@', "object name", &p, errp);
        if (ret < 0) {
            goto done;
        }
        ret = qemu_rbd_next_tok(snap, snap_len, p,
                                ':', "snap name", &p, errp);
        qemu_rbd_unescape(snap);
    } else {
        ret = qemu_rbd_next_tok(name, name_len, p,
                                ':', "object name", &p, errp);
    }
    qemu_rbd_unescape(name);
    if (ret < 0 || !p) {
        goto done;
    }

    ret = qemu_rbd_next_tok(conf, conf_len, p,
                            '\0', "configuration", &p, errp);

done:
    g_free(buf);
    return ret;
}

static char *qemu_rbd_parse_clientname(const char *conf, char *clientname)
{
    const char *p = conf;

    while (*p) {
        int len;
        const char *end = strchr(p, ':');

        if (end) {
            len = end - p;
        } else {
            len = strlen(p);
        }

        if (strncmp(p, "id=", 3) == 0) {
            len -= 3;
            strncpy(clientname, p + 3, len);
            clientname[len] = '\0';
            return clientname;
        }
        if (end == NULL) {
            break;
        }
        p = end + 1;
    }
    return NULL;
}


static int qemu_rbd_set_auth(rados_t cluster, const char *secretid,
                             Error **errp)
{
    if (secretid == 0) {
        return 0;
    }

    gchar *secret = qcrypto_secret_lookup_as_base64(secretid,
                                                    errp);
    if (!secret) {
        return -1;
    }

    rados_conf_set(cluster, "key", secret);
    g_free(secret);

    return 0;
}


static int qemu_rbd_set_conf(rados_t cluster, const char *conf,
                             bool only_read_conf_file,
                             Error **errp)
{
    char *p, *buf;
    char name[RBD_MAX_CONF_NAME_SIZE];
    char value[RBD_MAX_CONF_VAL_SIZE];
    int ret = 0;

    buf = g_strdup(conf);
    p = buf;

    while (p) {
        ret = qemu_rbd_next_tok(name, sizeof(name), p,
                                '=', "conf option name", &p, errp);
        if (ret < 0) {
            break;
        }
        qemu_rbd_unescape(name);

        if (!p) {
            error_setg(errp, "conf option %s has no value", name);
            ret = -EINVAL;
            break;
        }

        ret = qemu_rbd_next_tok(value, sizeof(value), p,
                                ':', "conf option value", &p, errp);
        if (ret < 0) {
            break;
        }
        qemu_rbd_unescape(value);

        if (strcmp(name, "conf") == 0) {
            /* read the conf file alone, so it doesn't override more
               specific settings for a particular device */
            if (only_read_conf_file) {
                ret = rados_conf_read_file(cluster, value);
                if (ret < 0) {
                    error_setg_errno(errp, -ret, "error reading conf file %s",
                                     value);
                    break;
                }
            }
        } else if (strcmp(name, "id") == 0) {
            /* ignore, this is parsed by qemu_rbd_parse_clientname() */
        } else if (!only_read_conf_file) {
            ret = rados_conf_set(cluster, name, value);
            if (ret < 0) {
                error_setg_errno(errp, -ret, "invalid conf option %s", name);
                ret = -EINVAL;
                break;
            }
        }
    }

    g_free(buf);
    return ret;
}

static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
{
    Error *local_err = NULL;
    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 conf[RBD_MAX_CONF_SIZE];
    char clientname_buf[RBD_MAX_CONF_SIZE];
    char *clientname;
    const char *secretid;
    rados_t cluster;
    rados_ioctx_t io_ctx;
    int ret;

    secretid = qemu_opt_get(opts, "password-secret");

    if (qemu_rbd_parsename(filename, pool, sizeof(pool),
                           snap_buf, sizeof(snap_buf),
                           name, sizeof(name),
                           conf, sizeof(conf), &local_err) < 0) {
        error_propagate(errp, local_err);
        return -EINVAL;
    }

    /* Read out options */
    bytes = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
                     BDRV_SECTOR_SIZE);
    objsize = qemu_opt_get_size_del(opts, BLOCK_OPT_CLUSTER_SIZE, 0);
    if (objsize) {
        if ((objsize - 1) & objsize) {    /* not a power of 2? */
            error_setg(errp, "obj size needs to be power of 2");
            return -EINVAL;
        }
        if (objsize < 4096) {
            error_setg(errp, "obj size too small");
            return -EINVAL;
        }
        obj_order = ctz32(objsize);
    }

    clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
    ret = rados_create(&cluster, clientname);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "error initializing");
        return ret;
    }

    if (strstr(conf, "conf=") == NULL) {
        /* try default location, but ignore failure */
        rados_conf_read_file(cluster, NULL);
    } else if (conf[0] != '\0' &&
               qemu_rbd_set_conf(cluster, conf, true, &local_err) < 0) {
        error_propagate(errp, local_err);
        ret = -EIO;
        goto shutdown;
    }

    if (conf[0] != '\0' &&
        qemu_rbd_set_conf(cluster, conf, false, &local_err) < 0) {
        error_propagate(errp, local_err);
        ret = -EIO;
        goto shutdown;
    }

    if (qemu_rbd_set_auth(cluster, secretid, errp) < 0) {
        ret = -EIO;
        goto shutdown;
    }

    ret = rados_connect(cluster);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "error connecting");
        goto shutdown;
    }

    ret = rados_ioctx_create(cluster, pool, &io_ctx);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "error opening pool %s", pool);
        goto shutdown;
    }

    ret = rbd_create(io_ctx, name, bytes, &obj_order);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "error rbd create");
    }

    rados_ioctx_destroy(io_ctx);

shutdown:
    rados_shutdown(cluster);
    return ret;
}

/*
 * This aio completion is being called from rbd_finish_bh() and runs in qemu
 * BH context.
 */
static void qemu_rbd_complete_aio(RADOSCB *rcb)
{
    RBDAIOCB *acb = rcb->acb;
    int64_t r;

    r = rcb->ret;

    if (acb->cmd != RBD_AIO_READ) {
        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;
        }
    }

    g_free(rcb);

    if (acb->cmd == RBD_AIO_READ) {
        qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
    }
    qemu_vfree(acb->bounce);
    acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));

    qemu_aio_unref(acb);
}

/* TODO Convert to fine grained options */
static QemuOptsList runtime_opts = {
    .name = "rbd",
    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
    .desc = {
        {
            .name = "filename",
            .type = QEMU_OPT_STRING,
            .help = "Specification of the rbd image",
        },
        {
            .name = "password-secret",
            .type = QEMU_OPT_STRING,
            .help = "ID of secret providing the password",
        },
        { /* end of list */ }
    },
};

static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
                         Error **errp)
{
    BDRVRBDState *s = bs->opaque;
    char pool[RBD_MAX_POOL_NAME_SIZE];
    char snap_buf[RBD_MAX_SNAP_NAME_SIZE];
    char conf[RBD_MAX_CONF_SIZE];
    char clientname_buf[RBD_MAX_CONF_SIZE];
    char *clientname;
    const char *secretid;
    QemuOpts *opts;
    Error *local_err = NULL;
    const char *filename;
    int r;

    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
    qemu_opts_absorb_qdict(opts, options, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        qemu_opts_del(opts);
        return -EINVAL;
    }

    filename = qemu_opt_get(opts, "filename");
    secretid = qemu_opt_get(opts, "password-secret");

    if (qemu_rbd_parsename(filename, pool, sizeof(pool),
                           snap_buf, sizeof(snap_buf),
                           s->name, sizeof(s->name),
                           conf, sizeof(conf), errp) < 0) {
        r = -EINVAL;
        goto failed_opts;
    }

    clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
    r = rados_create(&s->cluster, clientname);
    if (r < 0) {
        error_setg_errno(errp, -r, "error initializing");
        goto failed_opts;
    }

    s->snap = NULL;
    if (snap_buf[0] != '\0') {
        s->snap = g_strdup(snap_buf);
    }

    if (strstr(conf, "conf=") == NULL) {
        /* try default location, but ignore failure */
        rados_conf_read_file(s->cluster, NULL);
    } else if (conf[0] != '\0') {
        r = qemu_rbd_set_conf(s->cluster, conf, true, errp);
        if (r < 0) {
            goto failed_shutdown;
        }
    }

    if (conf[0] != '\0') {
        r = qemu_rbd_set_conf(s->cluster, conf, false, errp);
        if (r < 0) {
            goto failed_shutdown;
        }
    }

    if (qemu_rbd_set_auth(s->cluster, secretid, errp) < 0) {
        r = -EIO;
        goto failed_shutdown;
    }

    /*
     * Fallback to more conservative semantics if setting cache
     * options fails. Ignore errors from setting rbd_cache because the
     * only possible error is that the option does not exist, and
     * librbd defaults to no caching. If write through caching cannot
     * be set up, fall back to no caching.
     */
    if (flags & BDRV_O_NOCACHE) {
        rados_conf_set(s->cluster, "rbd_cache", "false");
    } else {
        rados_conf_set(s->cluster, "rbd_cache", "true");
    }

    r = rados_connect(s->cluster);
    if (r < 0) {
        error_setg_errno(errp, -r, "error connecting");
        goto failed_shutdown;
    }

    r = rados_ioctx_create(s->cluster, pool, &s->io_ctx);
    if (r < 0) {
        error_setg_errno(errp, -r, "error opening pool %s", pool);
        goto failed_shutdown;
    }

    r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
    if (r < 0) {
        error_setg_errno(errp, -r, "error reading header from %s", s->name);
        goto failed_open;
    }

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

    qemu_opts_del(opts);
    return 0;

failed_open:
    rados_ioctx_destroy(s->io_ctx);
failed_shutdown:
    rados_shutdown(s->cluster);
    g_free(s->snap);
failed_opts:
    qemu_opts_del(opts);
    return r;
}

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

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

static const AIOCBInfo rbd_aiocb_info = {
    .aiocb_size = sizeof(RBDAIOCB),
};

static void rbd_finish_bh(void *opaque)
{
    RADOSCB *rcb = opaque;
    qemu_rbd_complete_aio(rcb);
}

/*
 * 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
 * schedule a BH, and do the rest of the io completion handling
 * from rbd_finish_bh() which runs in a qemu context.
 */
static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb)
{
    RBDAIOCB *acb = rcb->acb;

    rcb->ret = rbd_aio_get_return_value(c);
    rbd_aio_release(c);

    aio_bh_schedule_oneshot(bdrv_get_aio_context(acb->common.bs),
                            rbd_finish_bh, rcb);
}

static int rbd_aio_discard_wrapper(rbd_image_t image,
                                   uint64_t off,
                                   uint64_t len,
                                   rbd_completion_t comp)
{
#ifdef LIBRBD_SUPPORTS_DISCARD
    return rbd_aio_discard(image, off, len, comp);
#else
    return -ENOTSUP;
#endif
}

static int rbd_aio_flush_wrapper(rbd_image_t image,
                                 rbd_completion_t comp)
{
#ifdef LIBRBD_SUPPORTS_AIO_FLUSH
    return rbd_aio_flush(image, comp);
#else
    return -ENOTSUP;
#endif
}

static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
                                 int64_t off,
                                 QEMUIOVector *qiov,
                                 int64_t size,
                                 BlockCompletionFunc *cb,
                                 void *opaque,
                                 RBDAIOCmd cmd)
{
    RBDAIOCB *acb;
    RADOSCB *rcb = NULL;
    rbd_completion_t c;
    char *buf;
    int r;

    BDRVRBDState *s = bs->opaque;

    acb = qemu_aio_get(&rbd_aiocb_info, bs, cb, opaque);
    acb->cmd = cmd;
    acb->qiov = qiov;
    assert(!qiov || qiov->size == size);
    if (cmd == RBD_AIO_DISCARD || cmd == RBD_AIO_FLUSH) {
        acb->bounce = NULL;
    } else {
        acb->bounce = qemu_try_blockalign(bs, qiov->size);
        if (acb->bounce == NULL) {
            goto failed;
        }
    }
    acb->ret = 0;
    acb->error = 0;
    acb->s = s;

    if (cmd == RBD_AIO_WRITE) {
        qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
    }

    buf = acb->bounce;

    rcb = g_new(RADOSCB, 1);
    rcb->acb = acb;
    rcb->buf = buf;
    rcb->s = acb->s;
    rcb->size = size;
    r = rbd_aio_create_completion(rcb, (rbd_callback_t) rbd_finish_aiocb, &c);
    if (r < 0) {
        goto failed;
    }

    switch (cmd) {
    case RBD_AIO_WRITE:
        r = rbd_aio_write(s->image, off, size, buf, c);
        break;
    case RBD_AIO_READ:
        r = rbd_aio_read(s->image, off, size, buf, c);
        break;
    case RBD_AIO_DISCARD:
        r = rbd_aio_discard_wrapper(s->image, off, size, c);
        break;
    case RBD_AIO_FLUSH:
        r = rbd_aio_flush_wrapper(s->image, c);
        break;
    default:
        r = -EINVAL;
    }

    if (r < 0) {
        goto failed_completion;
    }

    return &acb->common;

failed_completion:
    rbd_aio_release(c);
failed:
    g_free(rcb);
    qemu_vfree(acb->bounce);
    qemu_aio_unref(acb);
    return NULL;
}

static BlockAIOCB *qemu_rbd_aio_readv(BlockDriverState *bs,
                                      int64_t sector_num,
                                      QEMUIOVector *qiov,
                                      int nb_sectors,
                                      BlockCompletionFunc *cb,
                                      void *opaque)
{
    return rbd_start_aio(bs, sector_num << BDRV_SECTOR_BITS, qiov,
                         (int64_t) nb_sectors << BDRV_SECTOR_BITS, cb, opaque,
                         RBD_AIO_READ);
}

static BlockAIOCB *qemu_rbd_aio_writev(BlockDriverState *bs,
                                       int64_t sector_num,
                                       QEMUIOVector *qiov,
                                       int nb_sectors,
                                       BlockCompletionFunc *cb,
                                       void *opaque)
{
    return rbd_start_aio(bs, sector_num << BDRV_SECTOR_BITS, qiov,
                         (int64_t) nb_sectors << BDRV_SECTOR_BITS, cb, opaque,
                         RBD_AIO_WRITE);
}

#ifdef LIBRBD_SUPPORTS_AIO_FLUSH
static BlockAIOCB *qemu_rbd_aio_flush(BlockDriverState *bs,
                                      BlockCompletionFunc *cb,
                                      void *opaque)
{
    return rbd_start_aio(bs, 0, NULL, 0, cb, opaque, RBD_AIO_FLUSH);
}

#else

static int qemu_rbd_co_flush(BlockDriverState *bs)
{
#if LIBRBD_VERSION_CODE >= LIBRBD_VERSION(0, 1, 1)
    /* rbd_flush added in 0.1.1 */
    BDRVRBDState *s = bs->opaque;
    return rbd_flush(s->image);
#else
    return 0;
#endif
}
#endif

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_truncate(BlockDriverState *bs, int64_t offset)
{
    BDRVRBDState *s = bs->opaque;
    int r;

    r = rbd_resize(s->image, offset);
    if (r < 0) {
        return r;
    }

    return 0;
}

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_remove(BlockDriverState *bs,
                                const char *snapshot_id,
                                const char *snapshot_name,
                                Error **errp)
{
    BDRVRBDState *s = bs->opaque;
    int r;

    if (!snapshot_name) {
        error_setg(errp, "rbd need a valid snapshot name");
        return -EINVAL;
    }

    /* If snapshot_id is specified, it must be equal to name, see
       qemu_rbd_snap_list() */
    if (snapshot_id && strcmp(snapshot_id, snapshot_name)) {
        error_setg(errp,
                   "rbd do not support snapshot id, it should be NULL or "
                   "equal to snapshot name");
        return -EINVAL;
    }

    r = rbd_snap_remove(s->image, snapshot_name);
    if (r < 0) {
        error_setg_errno(errp, -r, "Failed to remove the snapshot");
    }
    return r;
}

static int qemu_rbd_snap_rollback(BlockDriverState *bs,
                                  const char *snapshot_name)
{
    BDRVRBDState *s = bs->opaque;

    return rbd_snap_rollback(s->image, snapshot_name);
}

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 = g_new(rbd_snap_info_t, max_snaps);
        snap_count = rbd_snap_list(s->image, snaps, &max_snaps);
        if (snap_count <= 0) {
            g_free(snaps);
        }
    } while (snap_count == -ERANGE);

    if (snap_count <= 0) {
        goto done;
    }

    sn_tab = g_new0(QEMUSnapshotInfo, snap_count);

    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);
    g_free(snaps);

 done:
    *psn_tab = sn_tab;
    return snap_count;
}

#ifdef LIBRBD_SUPPORTS_DISCARD
static BlockAIOCB *qemu_rbd_aio_pdiscard(BlockDriverState *bs,
                                         int64_t offset,
                                         int count,
                                         BlockCompletionFunc *cb,
                                         void *opaque)
{
    return rbd_start_aio(bs, offset, NULL, count, cb, opaque,
                         RBD_AIO_DISCARD);
}
#endif

#ifdef LIBRBD_SUPPORTS_INVALIDATE
static void qemu_rbd_invalidate_cache(BlockDriverState *bs,
                                      Error **errp)
{
    BDRVRBDState *s = bs->opaque;
    int r = rbd_invalidate_cache(s->image);
    if (r < 0) {
        error_setg_errno(errp, -r, "Failed to invalidate the cache");
    }
}
#endif

static QemuOptsList qemu_rbd_create_opts = {
    .name = "rbd-create-opts",
    .head = QTAILQ_HEAD_INITIALIZER(qemu_rbd_create_opts.head),
    .desc = {
        {
            .name = BLOCK_OPT_SIZE,
            .type = QEMU_OPT_SIZE,
            .help = "Virtual disk size"
        },
        {
            .name = BLOCK_OPT_CLUSTER_SIZE,
            .type = QEMU_OPT_SIZE,
            .help = "RBD object size"
        },
        {
            .name = "password-secret",
            .type = QEMU_OPT_STRING,
            .help = "ID of secret providing the password",
        },
        { /* end of list */ }
    }
};

static BlockDriver bdrv_rbd = {
    .format_name        = "rbd",
    .instance_size      = sizeof(BDRVRBDState),
    .bdrv_needs_filename = true,
    .bdrv_file_open     = qemu_rbd_open,
    .bdrv_close         = qemu_rbd_close,
    .bdrv_create        = qemu_rbd_create,
    .bdrv_has_zero_init = bdrv_has_zero_init_1,
    .bdrv_get_info      = qemu_rbd_getinfo,
    .create_opts        = &qemu_rbd_create_opts,
    .bdrv_getlength     = qemu_rbd_getlength,
    .bdrv_truncate      = qemu_rbd_truncate,
    .protocol_name      = "rbd",

    .bdrv_aio_readv         = qemu_rbd_aio_readv,
    .bdrv_aio_writev        = qemu_rbd_aio_writev,

#ifdef LIBRBD_SUPPORTS_AIO_FLUSH
    .bdrv_aio_flush         = qemu_rbd_aio_flush,
#else
    .bdrv_co_flush_to_disk  = qemu_rbd_co_flush,
#endif

#ifdef LIBRBD_SUPPORTS_DISCARD
    .bdrv_aio_pdiscard      = qemu_rbd_aio_pdiscard,
#endif

    .bdrv_snapshot_create   = qemu_rbd_snap_create,
    .bdrv_snapshot_delete   = qemu_rbd_snap_remove,
    .bdrv_snapshot_list     = qemu_rbd_snap_list,
    .bdrv_snapshot_goto     = qemu_rbd_snap_rollback,
#ifdef LIBRBD_SUPPORTS_INVALIDATE
    .bdrv_invalidate_cache  = qemu_rbd_invalidate_cache,
#endif
};

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

block_init(bdrv_rbd_init);