aboutsummaryrefslogtreecommitdiff
path: root/blockjob.c
blob: 205da9df4e03d0341312bbb77d73f447e8076b50 (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
/*
 * 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 "trace.h"
#include "block/block.h"
#include "block/blockjob.h"
#include "block/block_int.h"
#include "sysemu/block-backend.h"
#include "qapi/qmp/qerror.h"
#include "qapi/qmp/qjson.h"
#include "qemu/coroutine.h"
#include "qmp-commands.h"
#include "qemu/timer.h"
#include "qapi-event.h"

/* 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;
};

static QLIST_HEAD(, BlockJob) block_jobs = QLIST_HEAD_INITIALIZER(block_jobs);

BlockJob *block_job_next(BlockJob *job)
{
    if (!job) {
        return QLIST_FIRST(&block_jobs);
    }
    return QLIST_NEXT(job, job_list);
}

/* Normally the job runs in its BlockBackend's AioContext.  The exception is
 * block_job_defer_to_main_loop() where it runs in the QEMU main loop.  Code
 * that supports both cases uses this helper function.
 */
static AioContext *block_job_get_aio_context(BlockJob *job)
{
    return job->deferred_to_main_loop ?
           qemu_get_aio_context() :
           blk_get_aio_context(job->blk);
}

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

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

    block_job_resume(job);
}

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

    /* In case the job terminates during aio_poll()... */
    block_job_ref(job);

    block_job_pause(job);

    if (!job->paused) {
        /* If job is !job->busy this kicks it into the next pause point. */
        block_job_enter(job);
    }
    while (!job->paused && !job->completed) {
        aio_poll(block_job_get_aio_context(job), true);
    }

    block_job_unref(job);
}

void *block_job_create(const BlockJobDriver *driver, BlockDriverState *bs,
                       int64_t speed, BlockCompletionFunc *cb,
                       void *opaque, Error **errp)
{
    BlockBackend *blk;
    BlockJob *job;

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

    blk = blk_new();
    blk_insert_bs(blk, bs);

    job = g_malloc0(driver->instance_size);
    error_setg(&job->blocker, "block device is in use by block job: %s",
               BlockJobType_lookup[driver->job_type]);
    bdrv_op_block_all(bs, job->blocker);
    bdrv_op_unblock(bs, BLOCK_OP_TYPE_DATAPLANE, job->blocker);

    job->driver        = driver;
    job->id            = g_strdup(bdrv_get_device_name(bs));
    job->blk           = blk;
    job->cb            = cb;
    job->opaque        = opaque;
    job->busy          = true;
    job->refcnt        = 1;
    bs->job = job;

    QLIST_INSERT_HEAD(&block_jobs, job, job_list);

    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_unref(job);
            error_propagate(errp, local_err);
            return NULL;
        }
    }
    return job;
}

void block_job_ref(BlockJob *job)
{
    ++job->refcnt;
}

void block_job_unref(BlockJob *job)
{
    if (--job->refcnt == 0) {
        BlockDriverState *bs = blk_bs(job->blk);
        bs->job = NULL;
        bdrv_op_unblock_all(bs, job->blocker);
        blk_remove_aio_context_notifier(job->blk,
                                        block_job_attached_aio_context,
                                        block_job_detach_aio_context, job);
        blk_unref(job->blk);
        error_free(job->blocker);
        g_free(job->id);
        QLIST_REMOVE(job, job_list);
        g_free(job);
    }
}

static void block_job_completed_single(BlockJob *job)
{
    if (!job->ret) {
        if (job->driver->commit) {
            job->driver->commit(job);
        }
    } else {
        if (job->driver->abort) {
            job->driver->abort(job);
        }
    }
    job->cb(job->opaque, job->ret);
    if (job->txn) {
        block_job_txn_unref(job->txn);
    }
    block_job_unref(job);
}

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

    if (txn->aborting) {
        /*
         * We are cancelled by another job, which will handle everything.
         */
        return;
    }
    txn->aborting = true;
    /* 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);
    }
    QLIST_FOREACH(other_job, &txn->jobs, txn_list) {
        if (other_job == job || other_job->completed) {
            /* 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. */
            if (other_job != job) {
                other_job->cancelled = true;
            }
            continue;
        }
        block_job_cancel_sync(other_job);
        assert(other_job->completed);
    }
    QLIST_FOREACH_SAFE(other_job, &txn->jobs, txn_list, next) {
        ctx = blk_get_aio_context(other_job->blk);
        block_job_completed_single(other_job);
        aio_context_release(ctx);
    }
}

static void block_job_completed_txn_success(BlockJob *job)
{
    AioContext *ctx;
    BlockJobTxn *txn = job->txn;
    BlockJob *other_job, *next;
    /*
     * Successful completion, see if there are other running jobs in this
     * txn.
     */
    QLIST_FOREACH(other_job, &txn->jobs, txn_list) {
        if (!other_job->completed) {
            return;
        }
    }
    /* We are the last completed job, commit the transaction. */
    QLIST_FOREACH_SAFE(other_job, &txn->jobs, txn_list, next) {
        ctx = blk_get_aio_context(other_job->blk);
        aio_context_acquire(ctx);
        assert(other_job->ret == 0);
        block_job_completed_single(other_job);
        aio_context_release(ctx);
    }
}

void block_job_completed(BlockJob *job, int ret)
{
    assert(blk_bs(job->blk)->job == job);
    assert(!job->completed);
    job->completed = true;
    job->ret = ret;
    if (!job->txn) {
        block_job_completed_single(job);
    } else if (ret < 0 || block_job_is_cancelled(job)) {
        block_job_completed_txn_abort(job);
    } else {
        block_job_completed_txn_success(job);
    }
}

void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
{
    Error *local_err = NULL;

    if (!job->driver->set_speed) {
        error_setg(errp, QERR_UNSUPPORTED);
        return;
    }
    job->driver->set_speed(job, speed, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return;
    }

    job->speed = speed;
}

void block_job_complete(BlockJob *job, Error **errp)
{
    if (job->pause_count || job->cancelled || !job->driver->complete) {
        error_setg(errp, QERR_BLOCK_JOB_NOT_READY, job->id);
        return;
    }

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

void block_job_pause(BlockJob *job)
{
    job->pause_count++;
}

static bool block_job_should_pause(BlockJob *job)
{
    return job->pause_count > 0;
}

void coroutine_fn block_job_pause_point(BlockJob *job)
{
    if (!block_job_should_pause(job)) {
        return;
    }
    if (block_job_is_cancelled(job)) {
        return;
    }

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

    if (block_job_should_pause(job) && !block_job_is_cancelled(job)) {
        job->paused = true;
        job->busy = false;
        qemu_coroutine_yield(); /* wait for block_job_resume() */
        job->busy = true;
        job->paused = false;
    }

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

void block_job_resume(BlockJob *job)
{
    assert(job->pause_count > 0);
    job->pause_count--;
    if (job->pause_count) {
        return;
    }
    block_job_enter(job);
}

void block_job_enter(BlockJob *job)
{
    if (job->co && !job->busy) {
        qemu_coroutine_enter(job->co, NULL);
    }
}

void block_job_cancel(BlockJob *job)
{
    job->cancelled = true;
    block_job_iostatus_reset(job);
    block_job_enter(job);
}

bool block_job_is_cancelled(BlockJob *job)
{
    return job->cancelled;
}

void block_job_iostatus_reset(BlockJob *job)
{
    job->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
    if (job->driver->iostatus_reset) {
        job->driver->iostatus_reset(job);
    }
}

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);

    block_job_ref(job);
    finish(job, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        block_job_unref(job);
        return -EBUSY;
    }
    while (!job->completed) {
        aio_poll(block_job_get_aio_context(job), true);
    }
    ret = (job->cancelled && job->ret == 0) ? -ECANCELED : job->ret;
    block_job_unref(job);
    return ret;
}

/* 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);
}

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 = QLIST_FIRST(&block_jobs))) {
        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_sleep_ns(BlockJob *job, QEMUClockType type, int64_t ns)
{
    assert(job->busy);

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

    job->busy = false;
    if (!block_job_should_pause(job)) {
        co_aio_sleep_ns(blk_get_aio_context(job->blk), type, ns);
    }
    job->busy = true;

    block_job_pause_point(job);
}

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

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

    job->busy = false;
    if (!block_job_should_pause(job)) {
        qemu_coroutine_yield();
    }
    job->busy = true;

    block_job_pause_point(job);
}

BlockJobInfo *block_job_query(BlockJob *job)
{
    BlockJobInfo *info = g_new0(BlockJobInfo, 1);
    info->type      = g_strdup(BlockJobType_lookup[job->driver->job_type]);
    info->device    = g_strdup(job->id);
    info->len       = job->len;
    info->busy      = job->busy;
    info->paused    = job->pause_count > 0;
    info->offset    = job->offset;
    info->speed     = job->speed;
    info->io_status = job->iostatus;
    info->ready     = job->ready;
    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;
    }
}

void block_job_event_cancelled(BlockJob *job)
{
    qapi_event_send_block_job_cancelled(job->driver->job_type,
                                        job->id,
                                        job->len,
                                        job->offset,
                                        job->speed,
                                        &error_abort);
}

void block_job_event_completed(BlockJob *job, const char *msg)
{
    qapi_event_send_block_job_completed(job->driver->job_type,
                                        job->id,
                                        job->len,
                                        job->offset,
                                        job->speed,
                                        !!msg,
                                        msg,
                                        &error_abort);
}

void block_job_event_ready(BlockJob *job)
{
    job->ready = true;

    qapi_event_send_block_job_ready(job->driver->job_type,
                                    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:
        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();
    }
    qapi_event_send_block_job_error(job->id,
                                    is_read ? IO_OPERATION_TYPE_READ :
                                    IO_OPERATION_TYPE_WRITE,
                                    action, &error_abort);
    if (action == BLOCK_ERROR_ACTION_STOP) {
        /* make the pause user visible, which will be resumed from QMP. */
        job->user_paused = true;
        block_job_pause(job);
        block_job_iostatus_set_err(job, error);
    }
    return action;
}

typedef struct {
    BlockJob *job;
    QEMUBH *bh;
    AioContext *aio_context;
    BlockJobDeferToMainLoopFn *fn;
    void *opaque;
} BlockJobDeferToMainLoopData;

static void block_job_defer_to_main_loop_bh(void *opaque)
{
    BlockJobDeferToMainLoopData *data = opaque;
    AioContext *aio_context;

    qemu_bh_delete(data->bh);

    /* Prevent race with block_job_defer_to_main_loop() */
    aio_context_acquire(data->aio_context);

    /* Fetch BDS AioContext again, in case it has changed */
    aio_context = blk_get_aio_context(data->job->blk);
    aio_context_acquire(aio_context);

    data->job->deferred_to_main_loop = false;
    data->fn(data->job, data->opaque);

    aio_context_release(aio_context);

    aio_context_release(data->aio_context);

    g_free(data);
}

void block_job_defer_to_main_loop(BlockJob *job,
                                  BlockJobDeferToMainLoopFn *fn,
                                  void *opaque)
{
    BlockJobDeferToMainLoopData *data = g_malloc(sizeof(*data));
    data->job = job;
    data->bh = qemu_bh_new(block_job_defer_to_main_loop_bh, data);
    data->aio_context = blk_get_aio_context(job->blk);
    data->fn = fn;
    data->opaque = opaque;
    job->deferred_to_main_loop = true;

    qemu_bh_schedule(data->bh);
}

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);
}