job.c 23.7 KB
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
/*
 * Background jobs (long-running operations)
 *
 * Copyright (c) 2011 IBM Corp.
 * Copyright (c) 2012, 2018 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 "qapi/error.h"
#include "qemu/job.h"
#include "qemu/id.h"
#include "qemu/main-loop.h"
#include "block/aio-wait.h"
#include "trace-root.h"
#include "qapi/qapi-events-job.h"

static QLIST_HEAD(, Job) jobs = QLIST_HEAD_INITIALIZER(jobs);

/* Job State Transition Table */
bool JobSTT[JOB_STATUS__MAX][JOB_STATUS__MAX] = {
                                    /* U, C, R, P, Y, S, W, D, X, E, N */
    /* U: */ [JOB_STATUS_UNDEFINED] = {0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0},
    /* C: */ [JOB_STATUS_CREATED]   = {0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1},
    /* R: */ [JOB_STATUS_RUNNING]   = {0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 0},
    /* P: */ [JOB_STATUS_PAUSED]    = {0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0},
    /* Y: */ [JOB_STATUS_READY]     = {0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0},
    /* S: */ [JOB_STATUS_STANDBY]   = {0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0},
    /* W: */ [JOB_STATUS_WAITING]   = {0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0},
    /* D: */ [JOB_STATUS_PENDING]   = {0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0},
    /* X: */ [JOB_STATUS_ABORTING]  = {0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0},
    /* E: */ [JOB_STATUS_CONCLUDED] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1},
    /* N: */ [JOB_STATUS_NULL]      = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
};

bool JobVerbTable[JOB_VERB__MAX][JOB_STATUS__MAX] = {
                                    /* U, C, R, P, Y, S, W, D, X, E, N */
    [JOB_VERB_CANCEL]               = {0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0},
    [JOB_VERB_PAUSE]                = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0},
    [JOB_VERB_RESUME]               = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0},
    [JOB_VERB_SET_SPEED]            = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0},
    [JOB_VERB_COMPLETE]             = {0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0},
    [JOB_VERB_FINALIZE]             = {0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0},
    [JOB_VERB_DISMISS]              = {0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0},
};

/* Transactional group of jobs */
struct JobTxn {

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

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

    /* Reference count */
    int refcnt;
};

/* Right now, this mutex is only needed to synchronize accesses to job->busy
 * and job->sleep_timer, such as concurrent calls to job_do_yield and
 * job_enter. */
static QemuMutex job_mutex;

static void job_lock(void)
{
    qemu_mutex_lock(&job_mutex);
}

static void job_unlock(void)
{
    qemu_mutex_unlock(&job_mutex);
}

static void __attribute__((__constructor__)) job_init(void)
{
    qemu_mutex_init(&job_mutex);
}

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

static void job_txn_ref(JobTxn *txn)
{
    txn->refcnt++;
}

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

void job_txn_add_job(JobTxn *txn, Job *job)
{
    if (!txn) {
        return;
    }

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

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

static void job_txn_del_job(Job *job)
{
    if (job->txn) {
        QLIST_REMOVE(job, txn_list);
        job_txn_unref(job->txn);
        job->txn = NULL;
    }
}

static int job_txn_apply(JobTxn *txn, int fn(Job *))
{
    Job *job, *next;
    int rc = 0;

    QLIST_FOREACH_SAFE(job, &txn->jobs, txn_list, next) {
        rc = fn(job);
        if (rc) {
            break;
        }
    }
    return rc;
}

bool job_is_internal(Job *job)
{
    return (job->id == NULL);
}

static void job_state_transition(Job *job, JobStatus s1)
{
    JobStatus s0 = job->status;
    assert(s1 >= 0 && s1 < JOB_STATUS__MAX);
    trace_job_state_transition(job, job->ret,
                               JobSTT[s0][s1] ? "allowed" : "disallowed",
                               JobStatus_str(s0), JobStatus_str(s1));
    assert(JobSTT[s0][s1]);
    job->status = s1;

    if (!job_is_internal(job) && s1 != s0) {
        qapi_event_send_job_status_change(job->id, job->status);
    }
}

int job_apply_verb(Job *job, JobVerb verb, Error **errp)
{
    JobStatus s0 = job->status;
    assert(verb >= 0 && verb < JOB_VERB__MAX);
    trace_job_apply_verb(job, JobStatus_str(s0), JobVerb_str(verb),
                         JobVerbTable[verb][s0] ? "allowed" : "prohibited");
    if (JobVerbTable[verb][s0]) {
        return 0;
    }
    error_setg(errp, "Job '%s' in state '%s' cannot accept command verb '%s'",
               job->id, JobStatus_str(s0), JobVerb_str(verb));
    return -EPERM;
}

JobType job_type(const Job *job)
{
    return job->driver->job_type;
}

const char *job_type_str(const Job *job)
{
    return JobType_str(job_type(job));
}

bool job_is_cancelled(Job *job)
{
    return job->cancelled;
}

bool job_is_ready(Job *job)
{
    switch (job->status) {
    case JOB_STATUS_UNDEFINED:
    case JOB_STATUS_CREATED:
    case JOB_STATUS_RUNNING:
    case JOB_STATUS_PAUSED:
    case JOB_STATUS_WAITING:
    case JOB_STATUS_PENDING:
    case JOB_STATUS_ABORTING:
    case JOB_STATUS_CONCLUDED:
    case JOB_STATUS_NULL:
        return false;
    case JOB_STATUS_READY:
    case JOB_STATUS_STANDBY:
        return true;
    default:
        g_assert_not_reached();
    }
    return false;
}

bool job_is_completed(Job *job)
{
    switch (job->status) {
    case JOB_STATUS_UNDEFINED:
    case JOB_STATUS_CREATED:
    case JOB_STATUS_RUNNING:
    case JOB_STATUS_PAUSED:
    case JOB_STATUS_READY:
    case JOB_STATUS_STANDBY:
        return false;
    case JOB_STATUS_WAITING:
    case JOB_STATUS_PENDING:
    case JOB_STATUS_ABORTING:
    case JOB_STATUS_CONCLUDED:
    case JOB_STATUS_NULL:
        return true;
    default:
        g_assert_not_reached();
    }
    return false;
}

static bool job_started(Job *job)
{
    return job->co;
}

static bool job_should_pause(Job *job)
{
    return job->pause_count > 0;
}

Job *job_next(Job *job)
{
    if (!job) {
        return QLIST_FIRST(&jobs);
    }
    return QLIST_NEXT(job, job_list);
}

Job *job_get(const char *id)
{
    Job *job;

    QLIST_FOREACH(job, &jobs, job_list) {
        if (job->id && !strcmp(id, job->id)) {
            return job;
        }
    }

    return NULL;
}

static void job_sleep_timer_cb(void *opaque)
{
    Job *job = opaque;

    job_enter(job);
}

void *job_create(const char *job_id, const JobDriver *driver, JobTxn *txn,
                 AioContext *ctx, int flags, BlockCompletionFunc *cb,
                 void *opaque, Error **errp)
{
    Job *job;

    if (job_id) {
        if (flags & JOB_INTERNAL) {
            error_setg(errp, "Cannot specify job ID for internal job");
            return NULL;
        }
        if (!id_wellformed(job_id)) {
            error_setg(errp, "Invalid job ID '%s'", job_id);
            return NULL;
        }
        if (job_get(job_id)) {
            error_setg(errp, "Job ID '%s' already in use", job_id);
            return NULL;
        }
    } else if (!(flags & JOB_INTERNAL)) {
        error_setg(errp, "An explicit job ID is required");
        return NULL;
    }

    job = g_malloc0(driver->instance_size);
    job->driver        = driver;
    job->id            = g_strdup(job_id);
    job->refcnt        = 1;
    job->aio_context   = ctx;
    job->busy          = false;
    job->paused        = true;
    job->pause_count   = 1;
    job->auto_finalize = !(flags & JOB_MANUAL_FINALIZE);
    job->auto_dismiss  = !(flags & JOB_MANUAL_DISMISS);
    job->cb            = cb;
    job->opaque        = opaque;

    notifier_list_init(&job->on_finalize_cancelled);
    notifier_list_init(&job->on_finalize_completed);
    notifier_list_init(&job->on_pending);
    notifier_list_init(&job->on_ready);

    job_state_transition(job, JOB_STATUS_CREATED);
    aio_timer_init(qemu_get_aio_context(), &job->sleep_timer,
                   QEMU_CLOCK_REALTIME, SCALE_NS,
                   job_sleep_timer_cb, job);

    QLIST_INSERT_HEAD(&jobs, job, job_list);

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

    return job;
}

void job_ref(Job *job)
{
    ++job->refcnt;
}

void job_unref(Job *job)
{
    if (--job->refcnt == 0) {
        assert(job->status == JOB_STATUS_NULL);
        assert(!timer_pending(&job->sleep_timer));
        assert(!job->txn);

        if (job->driver->free) {
            job->driver->free(job);
        }

        QLIST_REMOVE(job, job_list);

        error_free(job->err);
        g_free(job->id);
        g_free(job);
    }
}

void job_progress_update(Job *job, uint64_t done)
{
    job->progress_current += done;
}

void job_progress_set_remaining(Job *job, uint64_t remaining)
{
    job->progress_total = job->progress_current + remaining;
}

void job_progress_increase_remaining(Job *job, uint64_t delta)
{
    job->progress_total += delta;
}

void job_event_cancelled(Job *job)
{
    notifier_list_notify(&job->on_finalize_cancelled, job);
}

void job_event_completed(Job *job)
{
    notifier_list_notify(&job->on_finalize_completed, job);
}

static void job_event_pending(Job *job)
{
    notifier_list_notify(&job->on_pending, job);
}

static void job_event_ready(Job *job)
{
    notifier_list_notify(&job->on_ready, job);
}

static void job_event_idle(Job *job)
{
    notifier_list_notify(&job->on_idle, job);
}

void job_enter_cond(Job *job, bool(*fn)(Job *job))
{
    if (!job_started(job)) {
        return;
    }
    if (job->deferred_to_main_loop) {
        return;
    }

    job_lock();
    if (job->busy) {
        job_unlock();
        return;
    }

    if (fn && !fn(job)) {
        job_unlock();
        return;
    }

    assert(!job->deferred_to_main_loop);
    timer_del(&job->sleep_timer);
    job->busy = true;
    job_unlock();
    aio_co_wake(job->co);
}

void job_enter(Job *job)
{
    job_enter_cond(job, NULL);
}

/* Yield, and schedule a timer to reenter the coroutine after @ns nanoseconds.
 * Reentering the job coroutine with job_enter() before the timer has expired
 * is allowed and cancels the timer.
 *
 * If @ns is (uint64_t) -1, no timer is scheduled and job_enter() must be
 * called explicitly. */
static void coroutine_fn job_do_yield(Job *job, uint64_t ns)
{
    job_lock();
    if (ns != -1) {
        timer_mod(&job->sleep_timer, ns);
    }
    job->busy = false;
    job_event_idle(job);
    job_unlock();
    qemu_coroutine_yield();

    /* Set by job_enter_cond() before re-entering the coroutine.  */
    assert(job->busy);
}

void coroutine_fn job_pause_point(Job *job)
{
    assert(job && job_started(job));

    if (!job_should_pause(job)) {
        return;
    }
    if (job_is_cancelled(job)) {
        return;
    }

    if (job->driver->pause) {
        job->driver->pause(job);
    }

    if (job_should_pause(job) && !job_is_cancelled(job)) {
        JobStatus status = job->status;
        job_state_transition(job, status == JOB_STATUS_READY
                                  ? JOB_STATUS_STANDBY
                                  : JOB_STATUS_PAUSED);
        job->paused = true;
        job_do_yield(job, -1);
        job->paused = false;
        job_state_transition(job, status);
    }

    if (job->driver->resume) {
        job->driver->resume(job);
    }
}

void job_yield(Job *job)
{
    assert(job->busy);

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

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

    job_pause_point(job);
}

void coroutine_fn job_sleep_ns(Job *job, int64_t ns)
{
    assert(job->busy);

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

    if (!job_should_pause(job)) {
        job_do_yield(job, qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + ns);
    }

    job_pause_point(job);
}

void job_drain(Job *job)
{
    /* If job is !busy this kicks it into the next pause point. */
    job_enter(job);

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

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

void job_pause(Job *job)
{
    job->pause_count++;
}

void job_resume(Job *job)
{
    assert(job->pause_count > 0);
    job->pause_count--;
    if (job->pause_count) {
        return;
    }

    /* kick only if no timer is pending */
    job_enter_cond(job, job_timer_not_pending);
}

void job_user_pause(Job *job, Error **errp)
{
    if (job_apply_verb(job, JOB_VERB_PAUSE, errp)) {
        return;
    }
    if (job->user_paused) {
        error_setg(errp, "Job is already paused");
        return;
    }
    job->user_paused = true;
    job_pause(job);
}

bool job_user_paused(Job *job)
{
    return job->user_paused;
}

void job_user_resume(Job *job, Error **errp)
{
    assert(job);
    if (!job->user_paused || job->pause_count <= 0) {
        error_setg(errp, "Can't resume a job that was not paused");
        return;
    }
    if (job_apply_verb(job, JOB_VERB_RESUME, errp)) {
        return;
    }
    if (job->driver->user_resume) {
        job->driver->user_resume(job);
    }
    job->user_paused = false;
    job_resume(job);
}

static void job_do_dismiss(Job *job)
{
    assert(job);
    job->busy = false;
    job->paused = false;
    job->deferred_to_main_loop = true;

    job_txn_del_job(job);

    job_state_transition(job, JOB_STATUS_NULL);
    job_unref(job);
}

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

    job_do_dismiss(job);
    *jobptr = NULL;
}

void job_early_fail(Job *job)
{
    assert(job->status == JOB_STATUS_CREATED);
    job_do_dismiss(job);
}

static void job_conclude(Job *job)
{
    job_state_transition(job, JOB_STATUS_CONCLUDED);
    if (job->auto_dismiss || !job_started(job)) {
        job_do_dismiss(job);
    }
}

static void job_update_rc(Job *job)
{
    if (!job->ret && job_is_cancelled(job)) {
        job->ret = -ECANCELED;
    }
    if (job->ret) {
        if (!job->err) {
            error_setg(&job->err, "%s", strerror(-job->ret));
        }
        job_state_transition(job, JOB_STATUS_ABORTING);
    }
}

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

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

static void job_clean(Job *job)
{
    if (job->driver->clean) {
        job->driver->clean(job);
    }
}

static int job_finalize_single(Job *job)
{
    assert(job_is_completed(job));

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

    if (!job->ret) {
        job_commit(job);
    } else {
        job_abort(job);
    }
    job_clean(job);

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

    /* Emit events only if we actually started */
    if (job_started(job)) {
        if (job_is_cancelled(job)) {
            job_event_cancelled(job);
        } else {
            job_event_completed(job);
        }
    }

    job_txn_del_job(job);
    job_conclude(job);
    return 0;
}

static void job_cancel_async(Job *job, bool force)
{
    if (job->user_paused) {
        /* Do not call job_enter here, the caller will handle it.  */
        if (job->driver->user_resume) {
            job->driver->user_resume(job);
        }
        job->user_paused = false;
        assert(job->pause_count > 0);
        job->pause_count--;
    }
    job->cancelled = true;
    /* To prevent 'force == false' overriding a previous 'force == true' */
    job->force_cancel |= force;
}

static void job_completed_txn_abort(Job *job)
{
    AioContext *outer_ctx = job->aio_context;
    AioContext *ctx;
    JobTxn *txn = job->txn;
    Job *other_job;

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

    /* We can only hold the single job's AioContext lock while calling
     * job_finalize_single() because the finalization callbacks can involve
     * calls of AIO_WAIT_WHILE(), which could deadlock otherwise. */
    aio_context_release(outer_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) {
            ctx = other_job->aio_context;
            aio_context_acquire(ctx);
            job_cancel_async(other_job, false);
            aio_context_release(ctx);
        }
    }
    while (!QLIST_EMPTY(&txn->jobs)) {
        other_job = QLIST_FIRST(&txn->jobs);
        ctx = other_job->aio_context;
        aio_context_acquire(ctx);
        if (!job_is_completed(other_job)) {
            assert(job_is_cancelled(other_job));
            job_finish_sync(other_job, NULL, NULL);
        }
        job_finalize_single(other_job);
        aio_context_release(ctx);
    }

    aio_context_acquire(outer_ctx);

    job_txn_unref(txn);
}

static int job_prepare(Job *job)
{
    if (job->ret == 0 && job->driver->prepare) {
        job->ret = job->driver->prepare(job);
        job_update_rc(job);
    }
    return job->ret;
}

static int job_needs_finalize(Job *job)
{
    return !job->auto_finalize;
}

static void job_do_finalize(Job *job)
{
    int rc;
    assert(job && job->txn);

    /* prepare the transaction to complete */
    rc = job_txn_apply(job->txn, job_prepare);
    if (rc) {
        job_completed_txn_abort(job);
    } else {
        job_txn_apply(job->txn, job_finalize_single);
    }
}

void job_finalize(Job *job, Error **errp)
{
    assert(job && job->id);
    if (job_apply_verb(job, JOB_VERB_FINALIZE, errp)) {
        return;
    }
    job_do_finalize(job);
}

static int job_transition_to_pending(Job *job)
{
    job_state_transition(job, JOB_STATUS_PENDING);
    if (!job->auto_finalize) {
        job_event_pending(job);
    }
    return 0;
}

void job_transition_to_ready(Job *job)
{
    job_state_transition(job, JOB_STATUS_READY);
    job_event_ready(job);
}

static void job_completed_txn_success(Job *job)
{
    JobTxn *txn = job->txn;
    Job *other_job;

    job_state_transition(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)) {
            return;
        }
        assert(other_job->ret == 0);
    }

    job_txn_apply(txn, job_transition_to_pending);

    /* If no jobs need manual finalization, automatically do so */
    if (job_txn_apply(txn, job_needs_finalize) == 0) {
        job_do_finalize(job);
    }
}

static void job_completed(Job *job)
{
    assert(job && job->txn && !job_is_completed(job));

    job_update_rc(job);
    trace_job_completed(job, job->ret);
    if (job->ret) {
        job_completed_txn_abort(job);
    } else {
        job_completed_txn_success(job);
    }
}

/** Useful only as a type shim for aio_bh_schedule_oneshot. */
static void job_exit(void *opaque)
{
    Job *job = (Job *)opaque;
    AioContext *ctx = job->aio_context;

    aio_context_acquire(ctx);

    /* This is a lie, we're not quiescent, but still doing the completion
     * callbacks. However, completion callbacks tend to involve operations that
     * drain block nodes, and if .drained_poll still returned true, we would
     * deadlock. */
    job->busy = false;
    job_event_idle(job);

    job_completed(job);

    aio_context_release(ctx);
}

/**
 * All jobs must allow a pause point before entering their job proper. This
 * ensures that jobs can be paused prior to being started, then resumed later.
 */
static void coroutine_fn job_co_entry(void *opaque)
{
    Job *job = opaque;

    assert(job && job->driver && job->driver->run);
    job_pause_point(job);
    job->ret = job->driver->run(job, &job->err);
    job->deferred_to_main_loop = true;
    job->busy = true;
    aio_bh_schedule_oneshot(qemu_get_aio_context(), job_exit, job);
}

void job_start(Job *job)
{
    assert(job && !job_started(job) && job->paused &&
           job->driver && job->driver->run);
    job->co = qemu_coroutine_create(job_co_entry, job);
    job->pause_count--;
    job->busy = true;
    job->paused = false;
    job_state_transition(job, JOB_STATUS_RUNNING);
    aio_co_enter(job->aio_context, job->co);
}

void job_cancel(Job *job, bool force)
{
    if (job->status == JOB_STATUS_CONCLUDED) {
        job_do_dismiss(job);
        return;
    }
    job_cancel_async(job, force);
    if (!job_started(job)) {
        job_completed(job);
    } else if (job->deferred_to_main_loop) {
        job_completed_txn_abort(job);
    } else {
        job_enter(job);
    }
}

void job_user_cancel(Job *job, bool force, Error **errp)
{
    if (job_apply_verb(job, JOB_VERB_CANCEL, errp)) {
        return;
    }
    job_cancel(job, force);
}

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

int job_cancel_sync(Job *job)
{
    return job_finish_sync(job, &job_cancel_err, NULL);
}

void job_cancel_sync_all(void)
{
    Job *job;
    AioContext *aio_context;

    while ((job = job_next(NULL))) {
        aio_context = job->aio_context;
        aio_context_acquire(aio_context);
        job_cancel_sync(job);
        aio_context_release(aio_context);
    }
}

int job_complete_sync(Job *job, Error **errp)
{
    return job_finish_sync(job, job_complete, errp);
}

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

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

int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp)
{
    Error *local_err = NULL;
    int ret;

    job_ref(job);

    if (finish) {
        finish(job, &local_err);
    }
    if (local_err) {
        error_propagate(errp, local_err);
        job_unref(job);
        return -EBUSY;
    }

    AIO_WAIT_WHILE(job->aio_context,
                   (job_drain(job), !job_is_completed(job)));

    ret = (job_is_cancelled(job) && job->ret == 0) ? -ECANCELED : job->ret;
    job_unref(job);
    return ret;
}