aboutsummaryrefslogtreecommitdiff
path: root/block/replication.c
blob: 9ed6e0fb04899be1aa3e025419808023a2279a29 (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
/*
 * Replication Block filter
 *
 * Copyright (c) 2016 HUAWEI TECHNOLOGIES CO., LTD.
 * Copyright (c) 2016 Intel Corporation
 * Copyright (c) 2016 FUJITSU LIMITED
 *
 * Author:
 *   Wen Congyang <wency@cn.fujitsu.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 */

#include "qemu/osdep.h"
#include "qemu/option.h"
#include "block/nbd.h"
#include "block/blockjob.h"
#include "block/block_int.h"
#include "block/block_backup.h"
#include "sysemu/block-backend.h"
#include "qapi/error.h"
#include "replication.h"

typedef enum {
    BLOCK_REPLICATION_NONE,             /* block replication is not started */
    BLOCK_REPLICATION_RUNNING,          /* block replication is running */
    BLOCK_REPLICATION_FAILOVER,         /* failover is running in background */
    BLOCK_REPLICATION_FAILOVER_FAILED,  /* failover failed */
    BLOCK_REPLICATION_DONE,             /* block replication is done */
} ReplicationStage;

typedef struct BDRVReplicationState {
    ReplicationMode mode;
    ReplicationStage stage;
    BdrvChild *active_disk;
    BdrvChild *hidden_disk;
    BdrvChild *secondary_disk;
    char *top_id;
    ReplicationState *rs;
    Error *blocker;
    int orig_hidden_flags;
    int orig_secondary_flags;
    int error;
} BDRVReplicationState;

static void replication_start(ReplicationState *rs, ReplicationMode mode,
                              Error **errp);
static void replication_do_checkpoint(ReplicationState *rs, Error **errp);
static void replication_get_error(ReplicationState *rs, Error **errp);
static void replication_stop(ReplicationState *rs, bool failover,
                             Error **errp);

#define REPLICATION_MODE        "mode"
#define REPLICATION_TOP_ID      "top-id"
static QemuOptsList replication_runtime_opts = {
    .name = "replication",
    .head = QTAILQ_HEAD_INITIALIZER(replication_runtime_opts.head),
    .desc = {
        {
            .name = REPLICATION_MODE,
            .type = QEMU_OPT_STRING,
        },
        {
            .name = REPLICATION_TOP_ID,
            .type = QEMU_OPT_STRING,
        },
        { /* end of list */ }
    },
};

static ReplicationOps replication_ops = {
    .start = replication_start,
    .checkpoint = replication_do_checkpoint,
    .get_error = replication_get_error,
    .stop = replication_stop,
};

static int replication_open(BlockDriverState *bs, QDict *options,
                            int flags, Error **errp)
{
    int ret;
    BDRVReplicationState *s = bs->opaque;
    Error *local_err = NULL;
    QemuOpts *opts = NULL;
    const char *mode;
    const char *top_id;

    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
                               false, errp);
    if (!bs->file) {
        return -EINVAL;
    }

    ret = -EINVAL;
    opts = qemu_opts_create(&replication_runtime_opts, NULL, 0, &error_abort);
    qemu_opts_absorb_qdict(opts, options, &local_err);
    if (local_err) {
        goto fail;
    }

    mode = qemu_opt_get(opts, REPLICATION_MODE);
    if (!mode) {
        error_setg(&local_err, "Missing the option mode");
        goto fail;
    }

    if (!strcmp(mode, "primary")) {
        s->mode = REPLICATION_MODE_PRIMARY;
        top_id = qemu_opt_get(opts, REPLICATION_TOP_ID);
        if (top_id) {
            error_setg(&local_err, "The primary side does not support option top-id");
            goto fail;
        }
    } else if (!strcmp(mode, "secondary")) {
        s->mode = REPLICATION_MODE_SECONDARY;
        top_id = qemu_opt_get(opts, REPLICATION_TOP_ID);
        s->top_id = g_strdup(top_id);
        if (!s->top_id) {
            error_setg(&local_err, "Missing the option top-id");
            goto fail;
        }
    } else {
        error_setg(&local_err,
                   "The option mode's value should be primary or secondary");
        goto fail;
    }

    s->rs = replication_new(bs, &replication_ops);

    ret = 0;

fail:
    qemu_opts_del(opts);
    error_propagate(errp, local_err);

    return ret;
}

static void replication_close(BlockDriverState *bs)
{
    BDRVReplicationState *s = bs->opaque;

    if (s->stage == BLOCK_REPLICATION_RUNNING) {
        replication_stop(s->rs, false, NULL);
    }
    if (s->stage == BLOCK_REPLICATION_FAILOVER) {
        block_job_cancel_sync(s->active_disk->bs->job);
    }

    if (s->mode == REPLICATION_MODE_SECONDARY) {
        g_free(s->top_id);
    }

    replication_remove(s->rs);
}

static void replication_child_perm(BlockDriverState *bs, BdrvChild *c,
                                   const BdrvChildRole *role,
                                   BlockReopenQueue *reopen_queue,
                                   uint64_t perm, uint64_t shared,
                                   uint64_t *nperm, uint64_t *nshared)
{
    *nperm = BLK_PERM_CONSISTENT_READ;
    if ((bs->open_flags & (BDRV_O_INACTIVE | BDRV_O_RDWR)) == BDRV_O_RDWR) {
        *nperm |= BLK_PERM_WRITE;
    }
    *nshared = BLK_PERM_CONSISTENT_READ \
               | BLK_PERM_WRITE \
               | BLK_PERM_WRITE_UNCHANGED;
    return;
}

static int64_t replication_getlength(BlockDriverState *bs)
{
    return bdrv_getlength(bs->file->bs);
}

static int replication_get_io_status(BDRVReplicationState *s)
{
    switch (s->stage) {
    case BLOCK_REPLICATION_NONE:
        return -EIO;
    case BLOCK_REPLICATION_RUNNING:
        return 0;
    case BLOCK_REPLICATION_FAILOVER:
        return s->mode == REPLICATION_MODE_PRIMARY ? -EIO : 0;
    case BLOCK_REPLICATION_FAILOVER_FAILED:
        return s->mode == REPLICATION_MODE_PRIMARY ? -EIO : 1;
    case BLOCK_REPLICATION_DONE:
        /*
         * active commit job completes, and active disk and secondary_disk
         * is swapped, so we can operate bs->file directly
         */
        return s->mode == REPLICATION_MODE_PRIMARY ? -EIO : 0;
    default:
        abort();
    }
}

static int replication_return_value(BDRVReplicationState *s, int ret)
{
    if (s->mode == REPLICATION_MODE_SECONDARY) {
        return ret;
    }

    if (ret < 0) {
        s->error = ret;
        ret = 0;
    }

    return ret;
}

static coroutine_fn int replication_co_readv(BlockDriverState *bs,
                                             int64_t sector_num,
                                             int remaining_sectors,
                                             QEMUIOVector *qiov)
{
    BDRVReplicationState *s = bs->opaque;
    BdrvChild *child = s->secondary_disk;
    BlockJob *job = NULL;
    CowRequest req;
    int ret;

    if (s->mode == REPLICATION_MODE_PRIMARY) {
        /* We only use it to forward primary write requests */
        return -EIO;
    }

    ret = replication_get_io_status(s);
    if (ret < 0) {
        return ret;
    }

    if (child && child->bs) {
        job = child->bs->job;
    }

    if (job) {
        uint64_t remaining_bytes = remaining_sectors * BDRV_SECTOR_SIZE;

        backup_wait_for_overlapping_requests(child->bs->job,
                                             sector_num * BDRV_SECTOR_SIZE,
                                             remaining_bytes);
        backup_cow_request_begin(&req, child->bs->job,
                                 sector_num * BDRV_SECTOR_SIZE,
                                 remaining_bytes);
        ret = bdrv_co_readv(bs->file, sector_num, remaining_sectors,
                            qiov);
        backup_cow_request_end(&req);
        goto out;
    }

    ret = bdrv_co_readv(bs->file, sector_num, remaining_sectors, qiov);
out:
    return replication_return_value(s, ret);
}

static coroutine_fn int replication_co_writev(BlockDriverState *bs,
                                              int64_t sector_num,
                                              int remaining_sectors,
                                              QEMUIOVector *qiov,
                                              int flags)
{
    BDRVReplicationState *s = bs->opaque;
    QEMUIOVector hd_qiov;
    uint64_t bytes_done = 0;
    BdrvChild *top = bs->file;
    BdrvChild *base = s->secondary_disk;
    BdrvChild *target;
    int ret;
    int64_t n;

    assert(!flags);
    ret = replication_get_io_status(s);
    if (ret < 0) {
        goto out;
    }

    if (ret == 0) {
        ret = bdrv_co_writev(top, sector_num,
                             remaining_sectors, qiov);
        return replication_return_value(s, ret);
    }

    /*
     * Failover failed, only write to active disk if the sectors
     * have already been allocated in active disk/hidden disk.
     */
    qemu_iovec_init(&hd_qiov, qiov->niov);
    while (remaining_sectors > 0) {
        int64_t count;

        ret = bdrv_is_allocated_above(top->bs, base->bs,
                                      sector_num * BDRV_SECTOR_SIZE,
                                      remaining_sectors * BDRV_SECTOR_SIZE,
                                      &count);
        if (ret < 0) {
            goto out1;
        }

        assert(QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE));
        n = count >> BDRV_SECTOR_BITS;
        qemu_iovec_reset(&hd_qiov);
        qemu_iovec_concat(&hd_qiov, qiov, bytes_done, count);

        target = ret ? top : base;
        ret = bdrv_co_writev(target, sector_num, n, &hd_qiov);
        if (ret < 0) {
            goto out1;
        }

        remaining_sectors -= n;
        sector_num += n;
        bytes_done += count;
    }

out1:
    qemu_iovec_destroy(&hd_qiov);
out:
    return ret;
}

static bool replication_recurse_is_first_non_filter(BlockDriverState *bs,
                                                    BlockDriverState *candidate)
{
    return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate);
}

static void secondary_do_checkpoint(BDRVReplicationState *s, Error **errp)
{
    Error *local_err = NULL;
    int ret;

    if (!s->secondary_disk->bs->job) {
        error_setg(errp, "Backup job was cancelled unexpectedly");
        return;
    }

    backup_do_checkpoint(s->secondary_disk->bs->job, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return;
    }

    if (!s->active_disk->bs->drv) {
        error_setg(errp, "Active disk %s is ejected",
                   s->active_disk->bs->node_name);
        return;
    }

    ret = s->active_disk->bs->drv->bdrv_make_empty(s->active_disk->bs);
    if (ret < 0) {
        error_setg(errp, "Cannot make active disk empty");
        return;
    }

    if (!s->hidden_disk->bs->drv) {
        error_setg(errp, "Hidden disk %s is ejected",
                   s->hidden_disk->bs->node_name);
        return;
    }

    ret = s->hidden_disk->bs->drv->bdrv_make_empty(s->hidden_disk->bs);
    if (ret < 0) {
        error_setg(errp, "Cannot make hidden disk empty");
        return;
    }
}

static void reopen_backing_file(BlockDriverState *bs, bool writable,
                                Error **errp)
{
    BDRVReplicationState *s = bs->opaque;
    BlockReopenQueue *reopen_queue = NULL;
    int orig_hidden_flags, orig_secondary_flags;
    int new_hidden_flags, new_secondary_flags;
    Error *local_err = NULL;

    if (writable) {
        orig_hidden_flags = s->orig_hidden_flags =
                                bdrv_get_flags(s->hidden_disk->bs);
        new_hidden_flags = (orig_hidden_flags | BDRV_O_RDWR) &
                                                    ~BDRV_O_INACTIVE;
        orig_secondary_flags = s->orig_secondary_flags =
                                bdrv_get_flags(s->secondary_disk->bs);
        new_secondary_flags = (orig_secondary_flags | BDRV_O_RDWR) &
                                                     ~BDRV_O_INACTIVE;
    } else {
        orig_hidden_flags = (s->orig_hidden_flags | BDRV_O_RDWR) &
                                                    ~BDRV_O_INACTIVE;
        new_hidden_flags = s->orig_hidden_flags;
        orig_secondary_flags = (s->orig_secondary_flags | BDRV_O_RDWR) &
                                                    ~BDRV_O_INACTIVE;
        new_secondary_flags = s->orig_secondary_flags;
    }

    bdrv_subtree_drained_begin(s->hidden_disk->bs);
    bdrv_subtree_drained_begin(s->secondary_disk->bs);

    if (orig_hidden_flags != new_hidden_flags) {
        reopen_queue = bdrv_reopen_queue(reopen_queue, s->hidden_disk->bs, NULL,
                                         new_hidden_flags);
    }

    if (!(orig_secondary_flags & BDRV_O_RDWR)) {
        reopen_queue = bdrv_reopen_queue(reopen_queue, s->secondary_disk->bs,
                                         NULL, new_secondary_flags);
    }

    if (reopen_queue) {
        bdrv_reopen_multiple(bdrv_get_aio_context(bs),
                             reopen_queue, &local_err);
        error_propagate(errp, local_err);
    }

    bdrv_subtree_drained_end(s->hidden_disk->bs);
    bdrv_subtree_drained_end(s->secondary_disk->bs);
}

static void backup_job_cleanup(BlockDriverState *bs)
{
    BDRVReplicationState *s = bs->opaque;
    BlockDriverState *top_bs;

    top_bs = bdrv_lookup_bs(s->top_id, s->top_id, NULL);
    if (!top_bs) {
        return;
    }
    bdrv_op_unblock_all(top_bs, s->blocker);
    error_free(s->blocker);
    reopen_backing_file(bs, false, NULL);
}

static void backup_job_completed(void *opaque, int ret)
{
    BlockDriverState *bs = opaque;
    BDRVReplicationState *s = bs->opaque;

    if (s->stage != BLOCK_REPLICATION_FAILOVER) {
        /* The backup job is cancelled unexpectedly */
        s->error = -EIO;
    }

    backup_job_cleanup(bs);
}

static bool check_top_bs(BlockDriverState *top_bs, BlockDriverState *bs)
{
    BdrvChild *child;

    /* The bs itself is the top_bs */
    if (top_bs == bs) {
        return true;
    }

    /* Iterate over top_bs's children */
    QLIST_FOREACH(child, &top_bs->children, next) {
        if (child->bs == bs || check_top_bs(child->bs, bs)) {
            return true;
        }
    }

    return false;
}

static void replication_start(ReplicationState *rs, ReplicationMode mode,
                              Error **errp)
{
    BlockDriverState *bs = rs->opaque;
    BDRVReplicationState *s;
    BlockDriverState *top_bs;
    int64_t active_length, hidden_length, disk_length;
    AioContext *aio_context;
    Error *local_err = NULL;
    BlockJob *job;

    aio_context = bdrv_get_aio_context(bs);
    aio_context_acquire(aio_context);
    s = bs->opaque;

    if (s->stage != BLOCK_REPLICATION_NONE) {
        error_setg(errp, "Block replication is running or done");
        aio_context_release(aio_context);
        return;
    }

    if (s->mode != mode) {
        error_setg(errp, "The parameter mode's value is invalid, needs %d,"
                   " but got %d", s->mode, mode);
        aio_context_release(aio_context);
        return;
    }

    switch (s->mode) {
    case REPLICATION_MODE_PRIMARY:
        break;
    case REPLICATION_MODE_SECONDARY:
        s->active_disk = bs->file;
        if (!s->active_disk || !s->active_disk->bs ||
                                    !s->active_disk->bs->backing) {
            error_setg(errp, "Active disk doesn't have backing file");
            aio_context_release(aio_context);
            return;
        }

        s->hidden_disk = s->active_disk->bs->backing;
        if (!s->hidden_disk->bs || !s->hidden_disk->bs->backing) {
            error_setg(errp, "Hidden disk doesn't have backing file");
            aio_context_release(aio_context);
            return;
        }

        s->secondary_disk = s->hidden_disk->bs->backing;
        if (!s->secondary_disk->bs || !bdrv_has_blk(s->secondary_disk->bs)) {
            error_setg(errp, "The secondary disk doesn't have block backend");
            aio_context_release(aio_context);
            return;
        }

        /* verify the length */
        active_length = bdrv_getlength(s->active_disk->bs);
        hidden_length = bdrv_getlength(s->hidden_disk->bs);
        disk_length = bdrv_getlength(s->secondary_disk->bs);
        if (active_length < 0 || hidden_length < 0 || disk_length < 0 ||
            active_length != hidden_length || hidden_length != disk_length) {
            error_setg(errp, "Active disk, hidden disk, secondary disk's length"
                       " are not the same");
            aio_context_release(aio_context);
            return;
        }

        /* Must be true, or the bdrv_getlength() calls would have failed */
        assert(s->active_disk->bs->drv && s->hidden_disk->bs->drv);

        if (!s->active_disk->bs->drv->bdrv_make_empty ||
            !s->hidden_disk->bs->drv->bdrv_make_empty) {
            error_setg(errp,
                       "Active disk or hidden disk doesn't support make_empty");
            aio_context_release(aio_context);
            return;
        }

        /* reopen the backing file in r/w mode */
        reopen_backing_file(bs, true, &local_err);
        if (local_err) {
            error_propagate(errp, local_err);
            aio_context_release(aio_context);
            return;
        }

        /* start backup job now */
        error_setg(&s->blocker,
                   "Block device is in use by internal backup job");

        top_bs = bdrv_lookup_bs(s->top_id, s->top_id, NULL);
        if (!top_bs || !bdrv_is_root_node(top_bs) ||
            !check_top_bs(top_bs, bs)) {
            error_setg(errp, "No top_bs or it is invalid");
            reopen_backing_file(bs, false, NULL);
            aio_context_release(aio_context);
            return;
        }
        bdrv_op_block_all(top_bs, s->blocker);
        bdrv_op_unblock(top_bs, BLOCK_OP_TYPE_DATAPLANE, s->blocker);

        job = backup_job_create(NULL, s->secondary_disk->bs, s->hidden_disk->bs,
                                0, MIRROR_SYNC_MODE_NONE, NULL, false,
                                BLOCKDEV_ON_ERROR_REPORT,
                                BLOCKDEV_ON_ERROR_REPORT, BLOCK_JOB_INTERNAL,
                                backup_job_completed, bs, NULL, &local_err);
        if (local_err) {
            error_propagate(errp, local_err);
            backup_job_cleanup(bs);
            aio_context_release(aio_context);
            return;
        }
        job_start(&job->job);
        break;
    default:
        aio_context_release(aio_context);
        abort();
    }

    s->stage = BLOCK_REPLICATION_RUNNING;

    if (s->mode == REPLICATION_MODE_SECONDARY) {
        secondary_do_checkpoint(s, errp);
    }

    s->error = 0;
    aio_context_release(aio_context);
}

static void replication_do_checkpoint(ReplicationState *rs, Error **errp)
{
    BlockDriverState *bs = rs->opaque;
    BDRVReplicationState *s;
    AioContext *aio_context;

    aio_context = bdrv_get_aio_context(bs);
    aio_context_acquire(aio_context);
    s = bs->opaque;

    if (s->mode == REPLICATION_MODE_SECONDARY) {
        secondary_do_checkpoint(s, errp);
    }
    aio_context_release(aio_context);
}

static void replication_get_error(ReplicationState *rs, Error **errp)
{
    BlockDriverState *bs = rs->opaque;
    BDRVReplicationState *s;
    AioContext *aio_context;

    aio_context = bdrv_get_aio_context(bs);
    aio_context_acquire(aio_context);
    s = bs->opaque;

    if (s->stage != BLOCK_REPLICATION_RUNNING) {
        error_setg(errp, "Block replication is not running");
        aio_context_release(aio_context);
        return;
    }

    if (s->error) {
        error_setg(errp, "I/O error occurred");
        aio_context_release(aio_context);
        return;
    }
    aio_context_release(aio_context);
}

static void replication_done(void *opaque, int ret)
{
    BlockDriverState *bs = opaque;
    BDRVReplicationState *s = bs->opaque;

    if (ret == 0) {
        s->stage = BLOCK_REPLICATION_DONE;

        /* refresh top bs's filename */
        bdrv_refresh_filename(bs);
        s->active_disk = NULL;
        s->secondary_disk = NULL;
        s->hidden_disk = NULL;
        s->error = 0;
    } else {
        s->stage = BLOCK_REPLICATION_FAILOVER_FAILED;
        s->error = -EIO;
    }
}

static void replication_stop(ReplicationState *rs, bool failover, Error **errp)
{
    BlockDriverState *bs = rs->opaque;
    BDRVReplicationState *s;
    AioContext *aio_context;

    aio_context = bdrv_get_aio_context(bs);
    aio_context_acquire(aio_context);
    s = bs->opaque;

    if (s->stage != BLOCK_REPLICATION_RUNNING) {
        error_setg(errp, "Block replication is not running");
        aio_context_release(aio_context);
        return;
    }

    switch (s->mode) {
    case REPLICATION_MODE_PRIMARY:
        s->stage = BLOCK_REPLICATION_DONE;
        s->error = 0;
        break;
    case REPLICATION_MODE_SECONDARY:
        /*
         * This BDS will be closed, and the job should be completed
         * before the BDS is closed, because we will access hidden
         * disk, secondary disk in backup_job_completed().
         */
        if (s->secondary_disk->bs->job) {
            block_job_cancel_sync(s->secondary_disk->bs->job);
        }

        if (!failover) {
            secondary_do_checkpoint(s, errp);
            s->stage = BLOCK_REPLICATION_DONE;
            aio_context_release(aio_context);
            return;
        }

        s->stage = BLOCK_REPLICATION_FAILOVER;
        commit_active_start(NULL, s->active_disk->bs, s->secondary_disk->bs,
                            BLOCK_JOB_INTERNAL, 0, BLOCKDEV_ON_ERROR_REPORT,
                            NULL, replication_done, bs, true, errp);
        break;
    default:
        aio_context_release(aio_context);
        abort();
    }
    aio_context_release(aio_context);
}

BlockDriver bdrv_replication = {
    .format_name                = "replication",
    .instance_size              = sizeof(BDRVReplicationState),

    .bdrv_open                  = replication_open,
    .bdrv_close                 = replication_close,
    .bdrv_child_perm            = replication_child_perm,

    .bdrv_getlength             = replication_getlength,
    .bdrv_co_readv              = replication_co_readv,
    .bdrv_co_writev             = replication_co_writev,

    .is_filter                  = true,
    .bdrv_recurse_is_first_non_filter = replication_recurse_is_first_non_filter,

    .has_variable_length        = true,
};

static void bdrv_replication_init(void)
{
    bdrv_register(&bdrv_replication);
}

block_init(bdrv_replication_init);