aboutsummaryrefslogtreecommitdiff
path: root/blockjob.c
blob: d9d8ff7f5ce11fa8ac9418f8afa0367353d74d82 (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
/*
 * QEMU System Emulator block driver
 *
 * Copyright (c) 2011 IBM Corp.
 * Copyright (c) 2012 Red Hat, Inc.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block.h"
#include "block/blockjob_int.h"
#include "block/block_int.h"
#include "block/trace.h"
#include "sysemu/block-backend.h"
#include "qapi/error.h"
#include "qapi/qapi-events-block-core.h"
#include "qapi/qmp/qerror.h"
#include "qemu/coroutine.h"
#include "qemu/timer.h"

static void block_job_event_cancelled(BlockJob *job);
static void block_job_event_completed(BlockJob *job, const char *msg);
static int block_job_event_pending(BlockJob *job);

/* Transactional group of block jobs */
struct BlockJobTxn {

    /* Is this txn being cancelled? */
    bool aborting;

    /* List of jobs */
    QLIST_HEAD(, BlockJob) jobs;

    /* Reference count */
    int refcnt;
};

/*
 * The block job API is composed of two categories of functions.
 *
 * The first includes functions used by the monitor.  The monitor is
 * peculiar in that it accesses the block job list with block_job_get, and
 * therefore needs consistency across block_job_get and the actual operation
 * (e.g. block_job_set_speed).  The consistency is achieved with
 * aio_context_acquire/release.  These functions are declared in blockjob.h.
 *
 * The second includes functions used by the block job drivers and sometimes
 * by the core block layer.  These do not care about locking, because the
 * whole coroutine runs under the AioContext lock, and are declared in
 * blockjob_int.h.
 */

static bool is_block_job(Job *job)
{
    return job_type(job) == JOB_TYPE_BACKUP ||
           job_type(job) == JOB_TYPE_COMMIT ||
           job_type(job) == JOB_TYPE_MIRROR ||
           job_type(job) == JOB_TYPE_STREAM;
}

BlockJob *block_job_next(BlockJob *bjob)
{
    Job *job = bjob ? &bjob->job : NULL;

    do {
        job = job_next(job);
    } while (job && !is_block_job(job));

    return job ? container_of(job, BlockJob, job) : NULL;
}

BlockJob *block_job_get(const char *id)
{
    Job *job = job_get(id);

    if (job && is_block_job(job)) {
        return container_of(job, BlockJob, job);
    } else {
        return NULL;
    }
}

BlockJobTxn *block_job_txn_new(void)
{
    BlockJobTxn *txn = g_new0(BlockJobTxn, 1);
    QLIST_INIT(&txn->jobs);
    txn->refcnt = 1;
    return txn;
}

static void block_job_txn_ref(BlockJobTxn *txn)
{
    txn->refcnt++;
}

void block_job_txn_unref(BlockJobTxn *txn)
{
    if (txn && --txn->refcnt == 0) {
        g_free(txn);
    }
}

void block_job_txn_add_job(BlockJobTxn *txn, BlockJob *job)
{
    if (!txn) {
        return;
    }

    assert(!job->txn);
    job->txn = txn;

    QLIST_INSERT_HEAD(&txn->jobs, job, txn_list);
    block_job_txn_ref(txn);
}

static void block_job_txn_del_job(BlockJob *job)
{
    if (job->txn) {
        QLIST_REMOVE(job, txn_list);
        block_job_txn_unref(job->txn);
        job->txn = NULL;
    }
}

static void block_job_attached_aio_context(AioContext *new_context,
                                           void *opaque);
static void block_job_detach_aio_context(void *opaque);

void block_job_free(Job *job)
{
    BlockJob *bjob = container_of(job, BlockJob, job);
    BlockDriverState *bs = blk_bs(bjob->blk);

    assert(!bjob->txn);

    bs->job = NULL;
    block_job_remove_all_bdrv(bjob);
    blk_remove_aio_context_notifier(bjob->blk,
                                    block_job_attached_aio_context,
                                    block_job_detach_aio_context, bjob);
    blk_unref(bjob->blk);
    error_free(bjob->blocker);
}

static void block_job_attached_aio_context(AioContext *new_context,
                                           void *opaque)
{
    BlockJob *job = opaque;

    job->job.aio_context = new_context;
    if (job->driver->attached_aio_context) {
        job->driver->attached_aio_context(job, new_context);
    }

    job_resume(&job->job);
}

static void block_job_drain(BlockJob *job)
{
    /* If job is !job->job.busy this kicks it into the next pause point. */
    block_job_enter(job);

    blk_drain(job->blk);
    if (job->driver->drain) {
        job->driver->drain(job);
    }
}

static void block_job_detach_aio_context(void *opaque)
{
    BlockJob *job = opaque;

    /* In case the job terminates during aio_poll()... */
    job_ref(&job->job);

    job_pause(&job->job);

    while (!job->job.paused && !job_is_completed(&job->job)) {
        block_job_drain(job);
    }

    job->job.aio_context = NULL;
    job_unref(&job->job);
}

static char *child_job_get_parent_desc(BdrvChild *c)
{
    BlockJob *job = c->opaque;
    return g_strdup_printf("%s job '%s'", job_type_str(&job->job), job->job.id);
}

static void child_job_drained_begin(BdrvChild *c)
{
    BlockJob *job = c->opaque;
    job_pause(&job->job);
}

static void child_job_drained_end(BdrvChild *c)
{
    BlockJob *job = c->opaque;
    job_resume(&job->job);
}

static const BdrvChildRole child_job = {
    .get_parent_desc    = child_job_get_parent_desc,
    .drained_begin      = child_job_drained_begin,
    .drained_end        = child_job_drained_end,
    .stay_at_node       = true,
};

void block_job_remove_all_bdrv(BlockJob *job)
{
    GSList *l;
    for (l = job->nodes; l; l = l->next) {
        BdrvChild *c = l->data;
        bdrv_op_unblock_all(c->bs, job->blocker);
        bdrv_root_unref_child(c);
    }
    g_slist_free(job->nodes);
    job->nodes = NULL;
}

int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs,
                       uint64_t perm, uint64_t shared_perm, Error **errp)
{
    BdrvChild *c;

    c = bdrv_root_attach_child(bs, name, &child_job, perm, shared_perm,
                               job, errp);
    if (c == NULL) {
        return -EPERM;
    }

    job->nodes = g_slist_prepend(job->nodes, c);
    bdrv_ref(bs);
    bdrv_op_block_all(bs, job->blocker);

    return 0;
}

bool block_job_is_internal(BlockJob *job)
{
    return (job->job.id == NULL);
}

const BlockJobDriver *block_job_driver(BlockJob *job)
{
    return job->driver;
}

static void block_job_decommission(BlockJob *job)
{
    assert(job);
    job->job.busy = false;
    job->job.paused = false;
    job->job.deferred_to_main_loop = true;
    block_job_txn_del_job(job);
    job_state_transition(&job->job, JOB_STATUS_NULL);
    job_unref(&job->job);
}

static void block_job_do_dismiss(BlockJob *job)
{
    block_job_decommission(job);
}

static void block_job_conclude(BlockJob *job)
{
    job_state_transition(&job->job, JOB_STATUS_CONCLUDED);
    if (job->job.auto_dismiss || !job_started(&job->job)) {
        block_job_do_dismiss(job);
    }
}

static void block_job_update_rc(BlockJob *job)
{
    if (!job->ret && job_is_cancelled(&job->job)) {
        job->ret = -ECANCELED;
    }
    if (job->ret) {
        job_state_transition(&job->job, JOB_STATUS_ABORTING);
    }
}

static int block_job_prepare(BlockJob *job)
{
    if (job->ret == 0 && job->driver->prepare) {
        job->ret = job->driver->prepare(job);
    }
    return job->ret;
}

static void block_job_commit(BlockJob *job)
{
    assert(!job->ret);
    if (job->driver->commit) {
        job->driver->commit(job);
    }
}

static void block_job_abort(BlockJob *job)
{
    assert(job->ret);
    if (job->driver->abort) {
        job->driver->abort(job);
    }
}

static void block_job_clean(BlockJob *job)
{
    if (job->driver->clean) {
        job->driver->clean(job);
    }
}

static int block_job_finalize_single(BlockJob *job)
{
    assert(job_is_completed(&job->job));

    /* Ensure abort is called for late-transactional failures */
    block_job_update_rc(job);

    if (!job->ret) {
        block_job_commit(job);
    } else {
        block_job_abort(job);
    }
    block_job_clean(job);

    if (job->cb) {
        job->cb(job->opaque, job->ret);
    }

    /* Emit events only if we actually started */
    if (job_started(&job->job)) {
        if (job_is_cancelled(&job->job)) {
            block_job_event_cancelled(job);
        } else {
            const char *msg = NULL;
            if (job->ret < 0) {
                msg = strerror(-job->ret);
            }
            block_job_event_completed(job, msg);
        }
    }

    block_job_txn_del_job(job);
    block_job_conclude(job);
    return 0;
}

static void block_job_cancel_async(BlockJob *job, bool force)
{
    if (job->iostatus != BLOCK_DEVICE_IO_STATUS_OK) {
        block_job_iostatus_reset(job);
    }
    if (job->job.user_paused) {
        /* Do not call block_job_enter here, the caller will handle it.  */
        job->job.user_paused = false;
        job->job.pause_count--;
    }
    job->job.cancelled = true;
    /* To prevent 'force == false' overriding a previous 'force == true' */
    job->force |= force;
}

static int block_job_txn_apply(BlockJobTxn *txn, int fn(BlockJob *), bool lock)
{
    AioContext *ctx;
    BlockJob *job, *next;
    int rc = 0;

    QLIST_FOREACH_SAFE(job, &txn->jobs, txn_list, next) {
        if (lock) {
            ctx = blk_get_aio_context(job->blk);
            aio_context_acquire(ctx);
        }
        rc = fn(job);
        if (lock) {
            aio_context_release(ctx);
        }
        if (rc) {
            break;
        }
    }
    return rc;
}

static int block_job_finish_sync(BlockJob *job,
                                 void (*finish)(BlockJob *, Error **errp),
                                 Error **errp)
{
    Error *local_err = NULL;
    int ret;

    assert(blk_bs(job->blk)->job == job);

    job_ref(&job->job);

    if (finish) {
        finish(job, &local_err);
    }
    if (local_err) {
        error_propagate(errp, local_err);
        job_unref(&job->job);
        return -EBUSY;
    }
    /* block_job_drain calls block_job_enter, and it should be enough to
     * induce progress until the job completes or moves to the main thread.
    */
    while (!job->job.deferred_to_main_loop && !job_is_completed(&job->job)) {
        block_job_drain(job);
    }
    while (!job_is_completed(&job->job)) {
        aio_poll(qemu_get_aio_context(), true);
    }
    ret = (job_is_cancelled(&job->job) && job->ret == 0)
          ? -ECANCELED : job->ret;
    job_unref(&job->job);
    return ret;
}

static void block_job_completed_txn_abort(BlockJob *job)
{
    AioContext *ctx;
    BlockJobTxn *txn = job->txn;
    BlockJob *other_job;

    if (txn->aborting) {
        /*
         * We are cancelled by another job, which will handle everything.
         */
        return;
    }
    txn->aborting = true;
    block_job_txn_ref(txn);

    /* We are the first failed job. Cancel other jobs. */
    QLIST_FOREACH(other_job, &txn->jobs, txn_list) {
        ctx = blk_get_aio_context(other_job->blk);
        aio_context_acquire(ctx);
    }

    /* Other jobs are effectively cancelled by us, set the status for
     * them; this job, however, may or may not be cancelled, depending
     * on the caller, so leave it. */
    QLIST_FOREACH(other_job, &txn->jobs, txn_list) {
        if (other_job != job) {
            block_job_cancel_async(other_job, false);
        }
    }
    while (!QLIST_EMPTY(&txn->jobs)) {
        other_job = QLIST_FIRST(&txn->jobs);
        ctx = blk_get_aio_context(other_job->blk);
        if (!job_is_completed(&other_job->job)) {
            assert(job_is_cancelled(&other_job->job));
            block_job_finish_sync(other_job, NULL, NULL);
        }
        block_job_finalize_single(other_job);
        aio_context_release(ctx);
    }

    block_job_txn_unref(txn);
}

static int block_job_needs_finalize(BlockJob *job)
{
    return !job->job.auto_finalize;
}

static void block_job_do_finalize(BlockJob *job)
{
    int rc;
    assert(job && job->txn);

    /* prepare the transaction to complete */
    rc = block_job_txn_apply(job->txn, block_job_prepare, true);
    if (rc) {
        block_job_completed_txn_abort(job);
    } else {
        block_job_txn_apply(job->txn, block_job_finalize_single, true);
    }
}

static void block_job_completed_txn_success(BlockJob *job)
{
    BlockJobTxn *txn = job->txn;
    BlockJob *other_job;

    job_state_transition(&job->job, JOB_STATUS_WAITING);

    /*
     * Successful completion, see if there are other running jobs in this
     * txn.
     */
    QLIST_FOREACH(other_job, &txn->jobs, txn_list) {
        if (!job_is_completed(&other_job->job)) {
            return;
        }
        assert(other_job->ret == 0);
    }

    block_job_txn_apply(txn, block_job_event_pending, false);

    /* If no jobs need manual finalization, automatically do so */
    if (block_job_txn_apply(txn, block_job_needs_finalize, false) == 0) {
        block_job_do_finalize(job);
    }
}

/* Assumes the job_mutex is held */
static bool job_timer_pending(Job *job)
{
    return timer_pending(&job->sleep_timer);
}

void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
{
    int64_t old_speed = job->speed;

    if (job_apply_verb(&job->job, JOB_VERB_SET_SPEED, errp)) {
        return;
    }
    if (speed < 0) {
        error_setg(errp, QERR_INVALID_PARAMETER, "speed");
        return;
    }

    ratelimit_set_speed(&job->limit, speed, BLOCK_JOB_SLICE_TIME);

    job->speed = speed;
    if (speed && speed <= old_speed) {
        return;
    }

    /* kick only if a timer is pending */
    job_enter_cond(&job->job, job_timer_pending);
}

int64_t block_job_ratelimit_get_delay(BlockJob *job, uint64_t n)
{
    if (!job->speed) {
        return 0;
    }

    return ratelimit_calculate_delay(&job->limit, n);
}

void block_job_complete(BlockJob *job, Error **errp)
{
    /* Should not be reachable via external interface for internal jobs */
    assert(job->job.id);
    if (job_apply_verb(&job->job, JOB_VERB_COMPLETE, errp)) {
        return;
    }
    if (job->job.pause_count || job_is_cancelled(&job->job) ||
        !job->driver->complete)
    {
        error_setg(errp, "The active block job '%s' cannot be completed",
                   job->job.id);
        return;
    }

    job->driver->complete(job, errp);
}

void block_job_finalize(BlockJob *job, Error **errp)
{
    assert(job && job->job.id);
    if (job_apply_verb(&job->job, JOB_VERB_FINALIZE, errp)) {
        return;
    }
    block_job_do_finalize(job);
}

void block_job_dismiss(BlockJob **jobptr, Error **errp)
{
    BlockJob *job = *jobptr;
    /* similarly to _complete, this is QMP-interface only. */
    assert(job->job.id);
    if (job_apply_verb(&job->job, JOB_VERB_DISMISS, errp)) {
        return;
    }

    block_job_do_dismiss(job);
    *jobptr = NULL;
}

void block_job_cancel(BlockJob *job, bool force)
{
    if (job->job.status == JOB_STATUS_CONCLUDED) {
        block_job_do_dismiss(job);
        return;
    }
    block_job_cancel_async(job, force);
    if (!job_started(&job->job)) {
        block_job_completed(job, -ECANCELED);
    } else if (job->job.deferred_to_main_loop) {
        block_job_completed_txn_abort(job);
    } else {
        block_job_enter(job);
    }
}

void block_job_user_cancel(BlockJob *job, bool force, Error **errp)
{
    if (job_apply_verb(&job->job, JOB_VERB_CANCEL, errp)) {
        return;
    }
    block_job_cancel(job, force);
}

/* A wrapper around block_job_cancel() taking an Error ** parameter so it may be
 * used with block_job_finish_sync() without the need for (rather nasty)
 * function pointer casts there. */
static void block_job_cancel_err(BlockJob *job, Error **errp)
{
    block_job_cancel(job, false);
}

int block_job_cancel_sync(BlockJob *job)
{
    return block_job_finish_sync(job, &block_job_cancel_err, NULL);
}

void block_job_cancel_sync_all(void)
{
    BlockJob *job;
    AioContext *aio_context;

    while ((job = block_job_next(NULL))) {
        aio_context = blk_get_aio_context(job->blk);
        aio_context_acquire(aio_context);
        block_job_cancel_sync(job);
        aio_context_release(aio_context);
    }
}

int block_job_complete_sync(BlockJob *job, Error **errp)
{
    return block_job_finish_sync(job, &block_job_complete, errp);
}

void block_job_progress_update(BlockJob *job, uint64_t done)
{
    job->offset += done;
}

void block_job_progress_set_remaining(BlockJob *job, uint64_t remaining)
{
    job->len = job->offset + remaining;
}

BlockJobInfo *block_job_query(BlockJob *job, Error **errp)
{
    BlockJobInfo *info;

    if (block_job_is_internal(job)) {
        error_setg(errp, "Cannot query QEMU internal jobs");
        return NULL;
    }
    info = g_new0(BlockJobInfo, 1);
    info->type      = g_strdup(job_type_str(&job->job));
    info->device    = g_strdup(job->job.id);
    info->len       = job->len;
    info->busy      = atomic_read(&job->job.busy);
    info->paused    = job->job.pause_count > 0;
    info->offset    = job->offset;
    info->speed     = job->speed;
    info->io_status = job->iostatus;
    info->ready     = job->ready;
    info->status    = job->job.status;
    info->auto_finalize = job->job.auto_finalize;
    info->auto_dismiss  = job->job.auto_dismiss;
    info->has_error = job->ret != 0;
    info->error     = job->ret ? g_strdup(strerror(-job->ret)) : NULL;
    return info;
}

static void block_job_iostatus_set_err(BlockJob *job, int error)
{
    if (job->iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
        job->iostatus = error == ENOSPC ? BLOCK_DEVICE_IO_STATUS_NOSPACE :
                                          BLOCK_DEVICE_IO_STATUS_FAILED;
    }
}

static void block_job_event_cancelled(BlockJob *job)
{
    if (block_job_is_internal(job)) {
        return;
    }

    qapi_event_send_block_job_cancelled(job_type(&job->job),
                                        job->job.id,
                                        job->len,
                                        job->offset,
                                        job->speed,
                                        &error_abort);
}

static void block_job_event_completed(BlockJob *job, const char *msg)
{
    if (block_job_is_internal(job)) {
        return;
    }

    qapi_event_send_block_job_completed(job_type(&job->job),
                                        job->job.id,
                                        job->len,
                                        job->offset,
                                        job->speed,
                                        !!msg,
                                        msg,
                                        &error_abort);
}

static int block_job_event_pending(BlockJob *job)
{
    job_state_transition(&job->job, JOB_STATUS_PENDING);
    if (!job->job.auto_finalize && !block_job_is_internal(job)) {
        qapi_event_send_block_job_pending(job_type(&job->job),
                                          job->job.id,
                                          &error_abort);
    }
    return 0;
}

/*
 * API for block job drivers and the block layer.  These functions are
 * declared in blockjob_int.h.
 */

void *block_job_create(const char *job_id, const BlockJobDriver *driver,
                       BlockJobTxn *txn, BlockDriverState *bs, uint64_t perm,
                       uint64_t shared_perm, int64_t speed, int flags,
                       BlockCompletionFunc *cb, void *opaque, Error **errp)
{
    BlockBackend *blk;
    BlockJob *job;
    int ret;

    if (bs->job) {
        error_setg(errp, QERR_DEVICE_IN_USE, bdrv_get_device_name(bs));
        return NULL;
    }

    if (job_id == NULL && !(flags & JOB_INTERNAL)) {
        job_id = bdrv_get_device_name(bs);
    }

    blk = blk_new(perm, shared_perm);
    ret = blk_insert_bs(blk, bs, errp);
    if (ret < 0) {
        blk_unref(blk);
        return NULL;
    }

    job = job_create(job_id, &driver->job_driver, blk_get_aio_context(blk),
                     flags, errp);
    if (job == NULL) {
        blk_unref(blk);
        return NULL;
    }

    assert(is_block_job(&job->job));
    assert(job->job.driver->free == &block_job_free);
    assert(job->job.driver->user_resume == &block_job_user_resume);

    job->driver        = driver;
    job->blk           = blk;
    job->cb            = cb;
    job->opaque        = opaque;

    error_setg(&job->blocker, "block device is in use by block job: %s",
               job_type_str(&job->job));
    block_job_add_bdrv(job, "main node", bs, 0, BLK_PERM_ALL, &error_abort);
    bs->job = job;

    bdrv_op_unblock(bs, BLOCK_OP_TYPE_DATAPLANE, job->blocker);

    blk_add_aio_context_notifier(blk, block_job_attached_aio_context,
                                 block_job_detach_aio_context, job);

    /* Only set speed when necessary to avoid NotSupported error */
    if (speed != 0) {
        Error *local_err = NULL;

        block_job_set_speed(job, speed, &local_err);
        if (local_err) {
            block_job_early_fail(job);
            error_propagate(errp, local_err);
            return NULL;
        }
    }

    /* Single jobs are modeled as single-job transactions for sake of
     * consolidating the job management logic */
    if (!txn) {
        txn = block_job_txn_new();
        block_job_txn_add_job(txn, job);
        block_job_txn_unref(txn);
    } else {
        block_job_txn_add_job(txn, job);
    }

    return job;
}

void block_job_early_fail(BlockJob *job)
{
    assert(job->job.status == JOB_STATUS_CREATED);
    block_job_decommission(job);
}

void block_job_completed(BlockJob *job, int ret)
{
    assert(job && job->txn && !job_is_completed(&job->job));
    assert(blk_bs(job->blk)->job == job);
    job->ret = ret;
    block_job_update_rc(job);
    trace_block_job_completed(job, ret, job->ret);
    if (job->ret) {
        block_job_completed_txn_abort(job);
    } else {
        block_job_completed_txn_success(job);
    }
}

void block_job_enter(BlockJob *job)
{
    job_enter_cond(&job->job, NULL);
}

void block_job_yield(BlockJob *job)
{
    assert(job->job.busy);

    /* Check cancellation *before* setting busy = false, too!  */
    if (job_is_cancelled(&job->job)) {
        return;
    }

    if (!job_should_pause(&job->job)) {
        job_do_yield(&job->job, -1);
    }

    job_pause_point(&job->job);
}

void block_job_iostatus_reset(BlockJob *job)
{
    if (job->iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
        return;
    }
    assert(job->job.user_paused && job->job.pause_count > 0);
    job->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
}

void block_job_user_resume(Job *job)
{
    BlockJob *bjob = container_of(job, BlockJob, job);
    block_job_iostatus_reset(bjob);
}

void block_job_event_ready(BlockJob *job)
{
    job_state_transition(&job->job, JOB_STATUS_READY);
    job->ready = true;

    if (block_job_is_internal(job)) {
        return;
    }

    qapi_event_send_block_job_ready(job_type(&job->job),
                                    job->job.id,
                                    job->len,
                                    job->offset,
                                    job->speed, &error_abort);
}

BlockErrorAction block_job_error_action(BlockJob *job, BlockdevOnError on_err,
                                        int is_read, int error)
{
    BlockErrorAction action;

    switch (on_err) {
    case BLOCKDEV_ON_ERROR_ENOSPC:
    case BLOCKDEV_ON_ERROR_AUTO:
        action = (error == ENOSPC) ?
                 BLOCK_ERROR_ACTION_STOP : BLOCK_ERROR_ACTION_REPORT;
        break;
    case BLOCKDEV_ON_ERROR_STOP:
        action = BLOCK_ERROR_ACTION_STOP;
        break;
    case BLOCKDEV_ON_ERROR_REPORT:
        action = BLOCK_ERROR_ACTION_REPORT;
        break;
    case BLOCKDEV_ON_ERROR_IGNORE:
        action = BLOCK_ERROR_ACTION_IGNORE;
        break;
    default:
        abort();
    }
    if (!block_job_is_internal(job)) {
        qapi_event_send_block_job_error(job->job.id,
                                        is_read ? IO_OPERATION_TYPE_READ :
                                        IO_OPERATION_TYPE_WRITE,
                                        action, &error_abort);
    }
    if (action == BLOCK_ERROR_ACTION_STOP) {
        job_pause(&job->job);
        /* make the pause user visible, which will be resumed from QMP. */
        job->job.user_paused = true;
        block_job_iostatus_set_err(job, error);
    }
    return action;
}