aboutsummaryrefslogtreecommitdiff
path: root/block/block-copy.c
blob: 5808cfe6570602ac86af93f6ef6ff6c18afe40d8 (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
/*
 * block_copy API
 *
 * Copyright (C) 2013 Proxmox Server Solutions
 * Copyright (c) 2019 Virtuozzo International GmbH.
 *
 * Authors:
 *  Dietmar Maurer (dietmar@proxmox.com)
 *  Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.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 "trace.h"
#include "qapi/error.h"
#include "block/block-copy.h"
#include "sysemu/block-backend.h"
#include "qemu/units.h"
#include "qemu/coroutine.h"
#include "block/aio_task.h"

#define BLOCK_COPY_MAX_COPY_RANGE (16 * MiB)
#define BLOCK_COPY_MAX_BUFFER (1 * MiB)
#define BLOCK_COPY_MAX_MEM (128 * MiB)
#define BLOCK_COPY_MAX_WORKERS 64
#define BLOCK_COPY_SLICE_TIME 100000000ULL /* ns */

static coroutine_fn int block_copy_task_entry(AioTask *task);

typedef struct BlockCopyCallState {
    /* IN parameters. Initialized in block_copy_async() and never changed. */
    BlockCopyState *s;
    int64_t offset;
    int64_t bytes;
    int max_workers;
    int64_t max_chunk;
    bool ignore_ratelimit;
    BlockCopyAsyncCallbackFunc cb;
    void *cb_opaque;

    /* Coroutine where async block-copy is running */
    Coroutine *co;

    /* To reference all call states from BlockCopyState */
    QLIST_ENTRY(BlockCopyCallState) list;

    /* State */
    int ret;
    bool finished;
    QemuCoSleep sleep;
    bool cancelled;

    /* OUT parameters */
    bool error_is_read;
} BlockCopyCallState;

typedef struct BlockCopyTask {
    AioTask task;

    BlockCopyState *s;
    BlockCopyCallState *call_state;
    int64_t offset;
    int64_t bytes;
    bool zeroes;
    bool copy_range;
    QLIST_ENTRY(BlockCopyTask) list;
    CoQueue wait_queue; /* coroutines blocked on this task */
} BlockCopyTask;

static int64_t task_end(BlockCopyTask *task)
{
    return task->offset + task->bytes;
}

typedef struct BlockCopyState {
    /*
     * BdrvChild objects are not owned or managed by block-copy. They are
     * provided by block-copy user and user is responsible for appropriate
     * permissions on these children.
     */
    BdrvChild *source;
    BdrvChild *target;
    BdrvDirtyBitmap *copy_bitmap;
    int64_t in_flight_bytes;
    int64_t cluster_size;
    bool use_copy_range;
    int64_t copy_size;
    uint64_t len;
    QLIST_HEAD(, BlockCopyTask) tasks; /* All tasks from all block-copy calls */
    QLIST_HEAD(, BlockCopyCallState) calls;

    BdrvRequestFlags write_flags;

    /*
     * skip_unallocated:
     *
     * Used by sync=top jobs, which first scan the source node for unallocated
     * areas and clear them in the copy_bitmap.  During this process, the bitmap
     * is thus not fully initialized: It may still have bits set for areas that
     * are unallocated and should actually not be copied.
     *
     * This is indicated by skip_unallocated.
     *
     * In this case, block_copy() will query the source’s allocation status,
     * skip unallocated regions, clear them in the copy_bitmap, and invoke
     * block_copy_reset_unallocated() every time it does.
     */
    bool skip_unallocated;

    ProgressMeter *progress;

    SharedResource *mem;

    uint64_t speed;
    RateLimit rate_limit;
} BlockCopyState;

static BlockCopyTask *find_conflicting_task(BlockCopyState *s,
                                            int64_t offset, int64_t bytes)
{
    BlockCopyTask *t;

    QLIST_FOREACH(t, &s->tasks, list) {
        if (offset + bytes > t->offset && offset < t->offset + t->bytes) {
            return t;
        }
    }

    return NULL;
}

/*
 * If there are no intersecting tasks return false. Otherwise, wait for the
 * first found intersecting tasks to finish and return true.
 */
static bool coroutine_fn block_copy_wait_one(BlockCopyState *s, int64_t offset,
                                             int64_t bytes)
{
    BlockCopyTask *task = find_conflicting_task(s, offset, bytes);

    if (!task) {
        return false;
    }

    qemu_co_queue_wait(&task->wait_queue, NULL);

    return true;
}

/*
 * Search for the first dirty area in offset/bytes range and create task at
 * the beginning of it.
 */
static BlockCopyTask *block_copy_task_create(BlockCopyState *s,
                                             BlockCopyCallState *call_state,
                                             int64_t offset, int64_t bytes)
{
    BlockCopyTask *task;
    int64_t max_chunk = MIN_NON_ZERO(s->copy_size, call_state->max_chunk);

    if (!bdrv_dirty_bitmap_next_dirty_area(s->copy_bitmap,
                                           offset, offset + bytes,
                                           max_chunk, &offset, &bytes))
    {
        return NULL;
    }

    assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
    bytes = QEMU_ALIGN_UP(bytes, s->cluster_size);

    /* region is dirty, so no existent tasks possible in it */
    assert(!find_conflicting_task(s, offset, bytes));

    bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, bytes);
    s->in_flight_bytes += bytes;

    task = g_new(BlockCopyTask, 1);
    *task = (BlockCopyTask) {
        .task.func = block_copy_task_entry,
        .s = s,
        .call_state = call_state,
        .offset = offset,
        .bytes = bytes,
        .copy_range = s->use_copy_range,
    };
    qemu_co_queue_init(&task->wait_queue);
    QLIST_INSERT_HEAD(&s->tasks, task, list);

    return task;
}

/*
 * block_copy_task_shrink
 *
 * Drop the tail of the task to be handled later. Set dirty bits back and
 * wake up all tasks waiting for us (may be some of them are not intersecting
 * with shrunk task)
 */
static void coroutine_fn block_copy_task_shrink(BlockCopyTask *task,
                                                int64_t new_bytes)
{
    if (new_bytes == task->bytes) {
        return;
    }

    assert(new_bytes > 0 && new_bytes < task->bytes);

    task->s->in_flight_bytes -= task->bytes - new_bytes;
    bdrv_set_dirty_bitmap(task->s->copy_bitmap,
                          task->offset + new_bytes, task->bytes - new_bytes);

    task->bytes = new_bytes;
    qemu_co_queue_restart_all(&task->wait_queue);
}

static void coroutine_fn block_copy_task_end(BlockCopyTask *task, int ret)
{
    task->s->in_flight_bytes -= task->bytes;
    if (ret < 0) {
        bdrv_set_dirty_bitmap(task->s->copy_bitmap, task->offset, task->bytes);
    }
    QLIST_REMOVE(task, list);
    qemu_co_queue_restart_all(&task->wait_queue);
}

void block_copy_state_free(BlockCopyState *s)
{
    if (!s) {
        return;
    }

    ratelimit_destroy(&s->rate_limit);
    bdrv_release_dirty_bitmap(s->copy_bitmap);
    shres_destroy(s->mem);
    g_free(s);
}

static uint32_t block_copy_max_transfer(BdrvChild *source, BdrvChild *target)
{
    return MIN_NON_ZERO(INT_MAX,
                        MIN_NON_ZERO(source->bs->bl.max_transfer,
                                     target->bs->bl.max_transfer));
}

BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
                                     int64_t cluster_size, bool use_copy_range,
                                     BdrvRequestFlags write_flags, Error **errp)
{
    BlockCopyState *s;
    BdrvDirtyBitmap *copy_bitmap;

    copy_bitmap = bdrv_create_dirty_bitmap(source->bs, cluster_size, NULL,
                                           errp);
    if (!copy_bitmap) {
        return NULL;
    }
    bdrv_disable_dirty_bitmap(copy_bitmap);

    s = g_new(BlockCopyState, 1);
    *s = (BlockCopyState) {
        .source = source,
        .target = target,
        .copy_bitmap = copy_bitmap,
        .cluster_size = cluster_size,
        .len = bdrv_dirty_bitmap_size(copy_bitmap),
        .write_flags = write_flags,
        .mem = shres_create(BLOCK_COPY_MAX_MEM),
    };

    if (block_copy_max_transfer(source, target) < cluster_size) {
        /*
         * copy_range does not respect max_transfer. We don't want to bother
         * with requests smaller than block-copy cluster size, so fallback to
         * buffered copying (read and write respect max_transfer on their
         * behalf).
         */
        s->use_copy_range = false;
        s->copy_size = cluster_size;
    } else if (write_flags & BDRV_REQ_WRITE_COMPRESSED) {
        /* Compression supports only cluster-size writes and no copy-range. */
        s->use_copy_range = false;
        s->copy_size = cluster_size;
    } else {
        /*
         * We enable copy-range, but keep small copy_size, until first
         * successful copy_range (look at block_copy_do_copy).
         */
        s->use_copy_range = use_copy_range;
        s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER);
    }

    ratelimit_init(&s->rate_limit);
    QLIST_INIT(&s->tasks);
    QLIST_INIT(&s->calls);

    return s;
}

void block_copy_set_progress_meter(BlockCopyState *s, ProgressMeter *pm)
{
    s->progress = pm;
}

/*
 * Takes ownership of @task
 *
 * If pool is NULL directly run the task, otherwise schedule it into the pool.
 *
 * Returns: task.func return code if pool is NULL
 *          otherwise -ECANCELED if pool status is bad
 *          otherwise 0 (successfully scheduled)
 */
static coroutine_fn int block_copy_task_run(AioTaskPool *pool,
                                            BlockCopyTask *task)
{
    if (!pool) {
        int ret = task->task.func(&task->task);

        g_free(task);
        return ret;
    }

    aio_task_pool_wait_slot(pool);
    if (aio_task_pool_status(pool) < 0) {
        co_put_to_shres(task->s->mem, task->bytes);
        block_copy_task_end(task, -ECANCELED);
        g_free(task);
        return -ECANCELED;
    }

    aio_task_pool_start_task(pool, &task->task);

    return 0;
}

/*
 * block_copy_do_copy
 *
 * Do copy of cluster-aligned chunk. Requested region is allowed to exceed
 * s->len only to cover last cluster when s->len is not aligned to clusters.
 *
 * No sync here: nor bitmap neighter intersecting requests handling, only copy.
 *
 * @copy_range is an in-out argument: if *copy_range is false, copy_range is not
 * done. If *copy_range is true, copy_range is attempted. If the copy_range
 * attempt fails, the function falls back to the usual read+write and
 * *copy_range is set to false. *copy_range and zeroes must not be true
 * simultaneously.
 *
 * Returns 0 on success.
 */
static int coroutine_fn block_copy_do_copy(BlockCopyState *s,
                                           int64_t offset, int64_t bytes,
                                           bool zeroes, bool *copy_range,
                                           bool *error_is_read)
{
    int ret;
    int64_t nbytes = MIN(offset + bytes, s->len) - offset;
    void *bounce_buffer = NULL;

    assert(offset >= 0 && bytes > 0 && INT64_MAX - offset >= bytes);
    assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
    assert(QEMU_IS_ALIGNED(bytes, s->cluster_size));
    assert(offset < s->len);
    assert(offset + bytes <= s->len ||
           offset + bytes == QEMU_ALIGN_UP(s->len, s->cluster_size));
    assert(nbytes < INT_MAX);
    assert(!(*copy_range && zeroes));

    if (zeroes) {
        ret = bdrv_co_pwrite_zeroes(s->target, offset, nbytes, s->write_flags &
                                    ~BDRV_REQ_WRITE_COMPRESSED);
        if (ret < 0) {
            trace_block_copy_write_zeroes_fail(s, offset, ret);
            *error_is_read = false;
        }
        return ret;
    }

    if (*copy_range) {
        ret = bdrv_co_copy_range(s->source, offset, s->target, offset, nbytes,
                                 0, s->write_flags);
        if (ret < 0) {
            trace_block_copy_copy_range_fail(s, offset, ret);
            *copy_range = false;
            /* Fallback to read+write with allocated buffer */
        } else {
            return 0;
        }
    }

    /*
     * In case of failed copy_range request above, we may proceed with buffered
     * request larger than BLOCK_COPY_MAX_BUFFER. Still, further requests will
     * be properly limited, so don't care too much. Moreover the most likely
     * case (copy_range is unsupported for the configuration, so the very first
     * copy_range request fails) is handled by setting large copy_size only
     * after first successful copy_range.
     */

    bounce_buffer = qemu_blockalign(s->source->bs, nbytes);

    ret = bdrv_co_pread(s->source, offset, nbytes, bounce_buffer, 0);
    if (ret < 0) {
        trace_block_copy_read_fail(s, offset, ret);
        *error_is_read = true;
        goto out;
    }

    ret = bdrv_co_pwrite(s->target, offset, nbytes, bounce_buffer,
                         s->write_flags);
    if (ret < 0) {
        trace_block_copy_write_fail(s, offset, ret);
        *error_is_read = false;
        goto out;
    }

out:
    qemu_vfree(bounce_buffer);

    return ret;
}

static void block_copy_handle_copy_range_result(BlockCopyState *s,
                                                bool is_success)
{
    if (!s->use_copy_range) {
        /* already disabled */
        return;
    }

    if (is_success) {
        /*
         * Successful copy-range. Now increase copy_size.  copy_range
         * does not respect max_transfer (it's a TODO), so we factor
         * that in here.
         */
        s->copy_size =
                MIN(MAX(s->cluster_size, BLOCK_COPY_MAX_COPY_RANGE),
                    QEMU_ALIGN_DOWN(block_copy_max_transfer(s->source,
                                                            s->target),
                                    s->cluster_size));
    } else {
        /* Copy-range failed, disable it. */
        s->use_copy_range = false;
        s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER);
    }
}

static coroutine_fn int block_copy_task_entry(AioTask *task)
{
    BlockCopyTask *t = container_of(task, BlockCopyTask, task);
    bool error_is_read = false;
    bool copy_range = t->copy_range;
    int ret;

    ret = block_copy_do_copy(t->s, t->offset, t->bytes, t->zeroes,
                             &copy_range, &error_is_read);
    if (t->copy_range) {
        block_copy_handle_copy_range_result(t->s, copy_range);
    }
    if (ret < 0) {
        if (!t->call_state->ret) {
            t->call_state->ret = ret;
            t->call_state->error_is_read = error_is_read;
        }
    } else {
        progress_work_done(t->s->progress, t->bytes);
    }
    co_put_to_shres(t->s->mem, t->bytes);
    block_copy_task_end(t, ret);

    return ret;
}

static int block_copy_block_status(BlockCopyState *s, int64_t offset,
                                   int64_t bytes, int64_t *pnum)
{
    int64_t num;
    BlockDriverState *base;
    int ret;

    if (s->skip_unallocated) {
        base = bdrv_backing_chain_next(s->source->bs);
    } else {
        base = NULL;
    }

    ret = bdrv_block_status_above(s->source->bs, base, offset, bytes, &num,
                                  NULL, NULL);
    if (ret < 0 || num < s->cluster_size) {
        /*
         * On error or if failed to obtain large enough chunk just fallback to
         * copy one cluster.
         */
        num = s->cluster_size;
        ret = BDRV_BLOCK_ALLOCATED | BDRV_BLOCK_DATA;
    } else if (offset + num == s->len) {
        num = QEMU_ALIGN_UP(num, s->cluster_size);
    } else {
        num = QEMU_ALIGN_DOWN(num, s->cluster_size);
    }

    *pnum = num;
    return ret;
}

/*
 * Check if the cluster starting at offset is allocated or not.
 * return via pnum the number of contiguous clusters sharing this allocation.
 */
static int block_copy_is_cluster_allocated(BlockCopyState *s, int64_t offset,
                                           int64_t *pnum)
{
    BlockDriverState *bs = s->source->bs;
    int64_t count, total_count = 0;
    int64_t bytes = s->len - offset;
    int ret;

    assert(QEMU_IS_ALIGNED(offset, s->cluster_size));

    while (true) {
        ret = bdrv_is_allocated(bs, offset, bytes, &count);
        if (ret < 0) {
            return ret;
        }

        total_count += count;

        if (ret || count == 0) {
            /*
             * ret: partial segment(s) are considered allocated.
             * otherwise: unallocated tail is treated as an entire segment.
             */
            *pnum = DIV_ROUND_UP(total_count, s->cluster_size);
            return ret;
        }

        /* Unallocated segment(s) with uncertain following segment(s) */
        if (total_count >= s->cluster_size) {
            *pnum = total_count / s->cluster_size;
            return 0;
        }

        offset += count;
        bytes -= count;
    }
}

/*
 * Reset bits in copy_bitmap starting at offset if they represent unallocated
 * data in the image. May reset subsequent contiguous bits.
 * @return 0 when the cluster at @offset was unallocated,
 *         1 otherwise, and -ret on error.
 */
int64_t block_copy_reset_unallocated(BlockCopyState *s,
                                     int64_t offset, int64_t *count)
{
    int ret;
    int64_t clusters, bytes;

    ret = block_copy_is_cluster_allocated(s, offset, &clusters);
    if (ret < 0) {
        return ret;
    }

    bytes = clusters * s->cluster_size;

    if (!ret) {
        bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, bytes);
        progress_set_remaining(s->progress,
                               bdrv_get_dirty_count(s->copy_bitmap) +
                               s->in_flight_bytes);
    }

    *count = bytes;
    return ret;
}

/*
 * block_copy_dirty_clusters
 *
 * Copy dirty clusters in @offset/@bytes range.
 * Returns 1 if dirty clusters found and successfully copied, 0 if no dirty
 * clusters found and -errno on failure.
 */
static int coroutine_fn
block_copy_dirty_clusters(BlockCopyCallState *call_state)
{
    BlockCopyState *s = call_state->s;
    int64_t offset = call_state->offset;
    int64_t bytes = call_state->bytes;

    int ret = 0;
    bool found_dirty = false;
    int64_t end = offset + bytes;
    AioTaskPool *aio = NULL;

    /*
     * block_copy() user is responsible for keeping source and target in same
     * aio context
     */
    assert(bdrv_get_aio_context(s->source->bs) ==
           bdrv_get_aio_context(s->target->bs));

    assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
    assert(QEMU_IS_ALIGNED(bytes, s->cluster_size));

    while (bytes && aio_task_pool_status(aio) == 0 && !call_state->cancelled) {
        BlockCopyTask *task;
        int64_t status_bytes;

        task = block_copy_task_create(s, call_state, offset, bytes);
        if (!task) {
            /* No more dirty bits in the bitmap */
            trace_block_copy_skip_range(s, offset, bytes);
            break;
        }
        if (task->offset > offset) {
            trace_block_copy_skip_range(s, offset, task->offset - offset);
        }

        found_dirty = true;

        ret = block_copy_block_status(s, task->offset, task->bytes,
                                      &status_bytes);
        assert(ret >= 0); /* never fail */
        if (status_bytes < task->bytes) {
            block_copy_task_shrink(task, status_bytes);
        }
        if (s->skip_unallocated && !(ret & BDRV_BLOCK_ALLOCATED)) {
            block_copy_task_end(task, 0);
            progress_set_remaining(s->progress,
                                   bdrv_get_dirty_count(s->copy_bitmap) +
                                   s->in_flight_bytes);
            trace_block_copy_skip_range(s, task->offset, task->bytes);
            offset = task_end(task);
            bytes = end - offset;
            g_free(task);
            continue;
        }
        if (ret & BDRV_BLOCK_ZERO) {
            task->zeroes = true;
            task->copy_range = false;
        }

        if (s->speed) {
            if (!call_state->ignore_ratelimit) {
                uint64_t ns = ratelimit_calculate_delay(&s->rate_limit, 0);
                if (ns > 0) {
                    block_copy_task_end(task, -EAGAIN);
                    g_free(task);
                    qemu_co_sleep_ns_wakeable(&call_state->sleep,
                                              QEMU_CLOCK_REALTIME, ns);
                    continue;
                }
            }

            ratelimit_calculate_delay(&s->rate_limit, task->bytes);
        }

        trace_block_copy_process(s, task->offset);

        co_get_from_shres(s->mem, task->bytes);

        offset = task_end(task);
        bytes = end - offset;

        if (!aio && bytes) {
            aio = aio_task_pool_new(call_state->max_workers);
        }

        ret = block_copy_task_run(aio, task);
        if (ret < 0) {
            goto out;
        }
    }

out:
    if (aio) {
        aio_task_pool_wait_all(aio);

        /*
         * We are not really interested in -ECANCELED returned from
         * block_copy_task_run. If it fails, it means some task already failed
         * for real reason, let's return first failure.
         * Still, assert that we don't rewrite failure by success.
         *
         * Note: ret may be positive here because of block-status result.
         */
        assert(ret >= 0 || aio_task_pool_status(aio) < 0);
        ret = aio_task_pool_status(aio);

        aio_task_pool_free(aio);
    }

    return ret < 0 ? ret : found_dirty;
}

void block_copy_kick(BlockCopyCallState *call_state)
{
    qemu_co_sleep_wake(&call_state->sleep);
}

/*
 * block_copy_common
 *
 * Copy requested region, accordingly to dirty bitmap.
 * Collaborate with parallel block_copy requests: if they succeed it will help
 * us. If they fail, we will retry not-copied regions. So, if we return error,
 * it means that some I/O operation failed in context of _this_ block_copy call,
 * not some parallel operation.
 */
static int coroutine_fn block_copy_common(BlockCopyCallState *call_state)
{
    int ret;

    QLIST_INSERT_HEAD(&call_state->s->calls, call_state, list);

    do {
        ret = block_copy_dirty_clusters(call_state);

        if (ret == 0 && !call_state->cancelled) {
            ret = block_copy_wait_one(call_state->s, call_state->offset,
                                      call_state->bytes);
        }

        /*
         * We retry in two cases:
         * 1. Some progress done
         *    Something was copied, which means that there were yield points
         *    and some new dirty bits may have appeared (due to failed parallel
         *    block-copy requests).
         * 2. We have waited for some intersecting block-copy request
         *    It may have failed and produced new dirty bits.
         */
    } while (ret > 0 && !call_state->cancelled);

    call_state->finished = true;

    if (call_state->cb) {
        call_state->cb(call_state->cb_opaque);
    }

    QLIST_REMOVE(call_state, list);

    return ret;
}

int coroutine_fn block_copy(BlockCopyState *s, int64_t start, int64_t bytes,
                            bool ignore_ratelimit)
{
    BlockCopyCallState call_state = {
        .s = s,
        .offset = start,
        .bytes = bytes,
        .ignore_ratelimit = ignore_ratelimit,
        .max_workers = BLOCK_COPY_MAX_WORKERS,
    };

    return block_copy_common(&call_state);
}

static void coroutine_fn block_copy_async_co_entry(void *opaque)
{
    block_copy_common(opaque);
}

BlockCopyCallState *block_copy_async(BlockCopyState *s,
                                     int64_t offset, int64_t bytes,
                                     int max_workers, int64_t max_chunk,
                                     BlockCopyAsyncCallbackFunc cb,
                                     void *cb_opaque)
{
    BlockCopyCallState *call_state = g_new(BlockCopyCallState, 1);

    *call_state = (BlockCopyCallState) {
        .s = s,
        .offset = offset,
        .bytes = bytes,
        .max_workers = max_workers,
        .max_chunk = max_chunk,
        .cb = cb,
        .cb_opaque = cb_opaque,

        .co = qemu_coroutine_create(block_copy_async_co_entry, call_state),
    };

    qemu_coroutine_enter(call_state->co);

    return call_state;
}

void block_copy_call_free(BlockCopyCallState *call_state)
{
    if (!call_state) {
        return;
    }

    assert(call_state->finished);
    g_free(call_state);
}

bool block_copy_call_finished(BlockCopyCallState *call_state)
{
    return call_state->finished;
}

bool block_copy_call_succeeded(BlockCopyCallState *call_state)
{
    return call_state->finished && !call_state->cancelled &&
        call_state->ret == 0;
}

bool block_copy_call_failed(BlockCopyCallState *call_state)
{
    return call_state->finished && !call_state->cancelled &&
        call_state->ret < 0;
}

bool block_copy_call_cancelled(BlockCopyCallState *call_state)
{
    return call_state->cancelled;
}

int block_copy_call_status(BlockCopyCallState *call_state, bool *error_is_read)
{
    assert(call_state->finished);
    if (error_is_read) {
        *error_is_read = call_state->error_is_read;
    }
    return call_state->ret;
}

void block_copy_call_cancel(BlockCopyCallState *call_state)
{
    call_state->cancelled = true;
    block_copy_kick(call_state);
}

BdrvDirtyBitmap *block_copy_dirty_bitmap(BlockCopyState *s)
{
    return s->copy_bitmap;
}

void block_copy_set_skip_unallocated(BlockCopyState *s, bool skip)
{
    s->skip_unallocated = skip;
}

void block_copy_set_speed(BlockCopyState *s, uint64_t speed)
{
    s->speed = speed;
    if (speed > 0) {
        ratelimit_set_speed(&s->rate_limit, speed, BLOCK_COPY_SLICE_TIME);
    }

    /*
     * Note: it's good to kick all call states from here, but it should be done
     * only from a coroutine, to not crash if s->calls list changed while
     * entering one call. So for now, the only user of this function kicks its
     * only one call_state by hand.
     */
}