aboutsummaryrefslogtreecommitdiff
path: root/util/aio-posix.c
blob: 731f3826c062df3df4caac5f45d26d203489ee04 (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
/*
 * QEMU aio implementation
 *
 * Copyright IBM, Corp. 2008
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 * Contributions after 2012-01-13 are licensed under the terms of the
 * GNU GPL, version 2 or (at your option) any later version.
 */

#include "qemu/osdep.h"
#include "block/block.h"
#include "block/thread-pool.h"
#include "qemu/main-loop.h"
#include "qemu/rcu.h"
#include "qemu/rcu_queue.h"
#include "qemu/sockets.h"
#include "qemu/cutils.h"
#include "trace.h"
#include "aio-posix.h"

/* Stop userspace polling on a handler if it isn't active for some time */
#define POLL_IDLE_INTERVAL_NS (7 * NANOSECONDS_PER_SECOND)

bool aio_poll_disabled(AioContext *ctx)
{
    return qatomic_read(&ctx->poll_disable_cnt);
}

void aio_add_ready_handler(AioHandlerList *ready_list,
                           AioHandler *node,
                           int revents)
{
    QLIST_SAFE_REMOVE(node, node_ready); /* remove from nested parent's list */
    node->pfd.revents = revents;
    QLIST_INSERT_HEAD(ready_list, node, node_ready);
}

static void aio_add_poll_ready_handler(AioHandlerList *ready_list,
                                       AioHandler *node)
{
    QLIST_SAFE_REMOVE(node, node_ready); /* remove from nested parent's list */
    node->poll_ready = true;
    QLIST_INSERT_HEAD(ready_list, node, node_ready);
}

static AioHandler *find_aio_handler(AioContext *ctx, int fd)
{
    AioHandler *node;

    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
        if (node->pfd.fd == fd) {
            if (!QLIST_IS_INSERTED(node, node_deleted)) {
                return node;
            }
        }
    }

    return NULL;
}

static bool aio_remove_fd_handler(AioContext *ctx, AioHandler *node)
{
    /* If the GSource is in the process of being destroyed then
     * g_source_remove_poll() causes an assertion failure.  Skip
     * removal in that case, because glib cleans up its state during
     * destruction anyway.
     */
    if (!g_source_is_destroyed(&ctx->source)) {
        g_source_remove_poll(&ctx->source, &node->pfd);
    }

    node->pfd.revents = 0;
    node->poll_ready = false;

    /* If the fd monitor has already marked it deleted, leave it alone */
    if (QLIST_IS_INSERTED(node, node_deleted)) {
        return false;
    }

    /* If a read is in progress, just mark the node as deleted */
    if (qemu_lockcnt_count(&ctx->list_lock)) {
        QLIST_INSERT_HEAD_RCU(&ctx->deleted_aio_handlers, node, node_deleted);
        return false;
    }
    /* Otherwise, delete it for real.  We can't just mark it as
     * deleted because deleted nodes are only cleaned up while
     * no one is walking the handlers list.
     */
    QLIST_SAFE_REMOVE(node, node_poll);
    QLIST_REMOVE(node, node);
    return true;
}

void aio_set_fd_handler(AioContext *ctx,
                        int fd,
                        bool is_external,
                        IOHandler *io_read,
                        IOHandler *io_write,
                        AioPollFn *io_poll,
                        IOHandler *io_poll_ready,
                        void *opaque)
{
    AioHandler *node;
    AioHandler *new_node = NULL;
    bool is_new = false;
    bool deleted = false;
    int poll_disable_change;

    if (io_poll && !io_poll_ready) {
        io_poll = NULL; /* polling only makes sense if there is a handler */
    }

    qemu_lockcnt_lock(&ctx->list_lock);

    node = find_aio_handler(ctx, fd);

    /* Are we deleting the fd handler? */
    if (!io_read && !io_write && !io_poll) {
        if (node == NULL) {
            qemu_lockcnt_unlock(&ctx->list_lock);
            return;
        }
        /* Clean events in order to unregister fd from the ctx epoll. */
        node->pfd.events = 0;

        poll_disable_change = -!node->io_poll;
    } else {
        poll_disable_change = !io_poll - (node && !node->io_poll);
        if (node == NULL) {
            is_new = true;
        }
        /* Alloc and insert if it's not already there */
        new_node = g_new0(AioHandler, 1);

        /* Update handler with latest information */
        new_node->io_read = io_read;
        new_node->io_write = io_write;
        new_node->io_poll = io_poll;
        new_node->io_poll_ready = io_poll_ready;
        new_node->opaque = opaque;
        new_node->is_external = is_external;

        if (is_new) {
            new_node->pfd.fd = fd;
        } else {
            new_node->pfd = node->pfd;
        }
        g_source_add_poll(&ctx->source, &new_node->pfd);

        new_node->pfd.events = (io_read ? G_IO_IN | G_IO_HUP | G_IO_ERR : 0);
        new_node->pfd.events |= (io_write ? G_IO_OUT | G_IO_ERR : 0);

        QLIST_INSERT_HEAD_RCU(&ctx->aio_handlers, new_node, node);
    }

    /* No need to order poll_disable_cnt writes against other updates;
     * the counter is only used to avoid wasting time and latency on
     * iterated polling when the system call will be ultimately necessary.
     * Changing handlers is a rare event, and a little wasted polling until
     * the aio_notify below is not an issue.
     */
    qatomic_set(&ctx->poll_disable_cnt,
               qatomic_read(&ctx->poll_disable_cnt) + poll_disable_change);

    ctx->fdmon_ops->update(ctx, node, new_node);
    if (node) {
        deleted = aio_remove_fd_handler(ctx, node);
    }
    qemu_lockcnt_unlock(&ctx->list_lock);
    aio_notify(ctx);

    if (deleted) {
        g_free(node);
    }
}

void aio_set_fd_poll(AioContext *ctx, int fd,
                     IOHandler *io_poll_begin,
                     IOHandler *io_poll_end)
{
    AioHandler *node = find_aio_handler(ctx, fd);

    if (!node) {
        return;
    }

    node->io_poll_begin = io_poll_begin;
    node->io_poll_end = io_poll_end;
}

void aio_set_event_notifier(AioContext *ctx,
                            EventNotifier *notifier,
                            bool is_external,
                            EventNotifierHandler *io_read,
                            AioPollFn *io_poll,
                            EventNotifierHandler *io_poll_ready)
{
    aio_set_fd_handler(ctx, event_notifier_get_fd(notifier), is_external,
                       (IOHandler *)io_read, NULL, io_poll,
                       (IOHandler *)io_poll_ready, notifier);
}

void aio_set_event_notifier_poll(AioContext *ctx,
                                 EventNotifier *notifier,
                                 EventNotifierHandler *io_poll_begin,
                                 EventNotifierHandler *io_poll_end)
{
    aio_set_fd_poll(ctx, event_notifier_get_fd(notifier),
                    (IOHandler *)io_poll_begin,
                    (IOHandler *)io_poll_end);
}

static bool poll_set_started(AioContext *ctx, AioHandlerList *ready_list,
                             bool started)
{
    AioHandler *node;
    bool progress = false;

    if (started == ctx->poll_started) {
        return false;
    }

    ctx->poll_started = started;

    qemu_lockcnt_inc(&ctx->list_lock);
    QLIST_FOREACH(node, &ctx->poll_aio_handlers, node_poll) {
        IOHandler *fn;

        if (QLIST_IS_INSERTED(node, node_deleted)) {
            continue;
        }

        if (started) {
            fn = node->io_poll_begin;
        } else {
            fn = node->io_poll_end;
        }

        if (fn) {
            fn(node->opaque);
        }

        /* Poll one last time in case ->io_poll_end() raced with the event */
        if (!started && node->io_poll(node->opaque)) {
            aio_add_poll_ready_handler(ready_list, node);
            progress = true;
        }
    }
    qemu_lockcnt_dec(&ctx->list_lock);

    return progress;
}


bool aio_prepare(AioContext *ctx)
{
    AioHandlerList ready_list = QLIST_HEAD_INITIALIZER(ready_list);

    /* Poll mode cannot be used with glib's event loop, disable it. */
    poll_set_started(ctx, &ready_list, false);
    /* TODO what to do with this list? */

    return false;
}

bool aio_pending(AioContext *ctx)
{
    AioHandler *node;
    bool result = false;

    /*
     * We have to walk very carefully in case aio_set_fd_handler is
     * called while we're walking.
     */
    qemu_lockcnt_inc(&ctx->list_lock);

    QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
        int revents;

        /* TODO should this check poll ready? */
        revents = node->pfd.revents & node->pfd.events;
        if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read &&
            aio_node_check(ctx, node->is_external)) {
            result = true;
            break;
        }
        if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write &&
            aio_node_check(ctx, node->is_external)) {
            result = true;
            break;
        }
    }
    qemu_lockcnt_dec(&ctx->list_lock);

    return result;
}

static void aio_free_deleted_handlers(AioContext *ctx)
{
    AioHandler *node;

    if (QLIST_EMPTY_RCU(&ctx->deleted_aio_handlers)) {
        return;
    }
    if (!qemu_lockcnt_dec_if_lock(&ctx->list_lock)) {
        return; /* we are nested, let the parent do the freeing */
    }

    while ((node = QLIST_FIRST_RCU(&ctx->deleted_aio_handlers))) {
        QLIST_REMOVE(node, node);
        QLIST_REMOVE(node, node_deleted);
        QLIST_SAFE_REMOVE(node, node_poll);
        g_free(node);
    }

    qemu_lockcnt_inc_and_unlock(&ctx->list_lock);
}

static bool aio_dispatch_handler(AioContext *ctx, AioHandler *node)
{
    bool progress = false;
    bool poll_ready;
    int revents;

    revents = node->pfd.revents & node->pfd.events;
    node->pfd.revents = 0;

    poll_ready = node->poll_ready;
    node->poll_ready = false;

    /*
     * Start polling AioHandlers when they become ready because activity is
     * likely to continue.  Note that starvation is theoretically possible when
     * fdmon_supports_polling(), but only until the fd fires for the first
     * time.
     */
    if (!QLIST_IS_INSERTED(node, node_deleted) &&
        !QLIST_IS_INSERTED(node, node_poll) &&
        node->io_poll) {
        trace_poll_add(ctx, node, node->pfd.fd, revents);
        if (ctx->poll_started && node->io_poll_begin) {
            node->io_poll_begin(node->opaque);
        }
        QLIST_INSERT_HEAD(&ctx->poll_aio_handlers, node, node_poll);
    }
    if (!QLIST_IS_INSERTED(node, node_deleted) &&
        poll_ready && revents == 0 &&
        aio_node_check(ctx, node->is_external) &&
        node->io_poll_ready) {
        node->io_poll_ready(node->opaque);

        /*
         * Return early since revents was zero. aio_notify() does not count as
         * progress.
         */
        return node->opaque != &ctx->notifier;
    }

    if (!QLIST_IS_INSERTED(node, node_deleted) &&
        (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) &&
        aio_node_check(ctx, node->is_external) &&
        node->io_read) {
        node->io_read(node->opaque);

        /* aio_notify() does not count as progress */
        if (node->opaque != &ctx->notifier) {
            progress = true;
        }
    }
    if (!QLIST_IS_INSERTED(node, node_deleted) &&
        (revents & (G_IO_OUT | G_IO_ERR)) &&
        aio_node_check(ctx, node->is_external) &&
        node->io_write) {
        node->io_write(node->opaque);
        progress = true;
    }

    return progress;
}

/*
 * If we have a list of ready handlers then this is more efficient than
 * scanning all handlers with aio_dispatch_handlers().
 */
static bool aio_dispatch_ready_handlers(AioContext *ctx,
                                        AioHandlerList *ready_list)
{
    bool progress = false;
    AioHandler *node;

    while ((node = QLIST_FIRST(ready_list))) {
        QLIST_REMOVE(node, node_ready);
        progress = aio_dispatch_handler(ctx, node) || progress;
    }

    return progress;
}

/* Slower than aio_dispatch_ready_handlers() but only used via glib */
static bool aio_dispatch_handlers(AioContext *ctx)
{
    AioHandler *node, *tmp;
    bool progress = false;

    QLIST_FOREACH_SAFE_RCU(node, &ctx->aio_handlers, node, tmp) {
        progress = aio_dispatch_handler(ctx, node) || progress;
    }

    return progress;
}

void aio_dispatch(AioContext *ctx)
{
    qemu_lockcnt_inc(&ctx->list_lock);
    aio_bh_poll(ctx);
    aio_dispatch_handlers(ctx);
    aio_free_deleted_handlers(ctx);
    qemu_lockcnt_dec(&ctx->list_lock);

    timerlistgroup_run_timers(&ctx->tlg);
}

static bool run_poll_handlers_once(AioContext *ctx,
                                   AioHandlerList *ready_list,
                                   int64_t now,
                                   int64_t *timeout)
{
    bool progress = false;
    AioHandler *node;
    AioHandler *tmp;

    QLIST_FOREACH_SAFE(node, &ctx->poll_aio_handlers, node_poll, tmp) {
        if (aio_node_check(ctx, node->is_external) &&
            node->io_poll(node->opaque)) {
            aio_add_poll_ready_handler(ready_list, node);

            node->poll_idle_timeout = now + POLL_IDLE_INTERVAL_NS;

            /*
             * Polling was successful, exit try_poll_mode immediately
             * to adjust the next polling time.
             */
            *timeout = 0;
            if (node->opaque != &ctx->notifier) {
                progress = true;
            }
        }

        /* Caller handles freeing deleted nodes.  Don't do it here. */
    }

    return progress;
}

static bool fdmon_supports_polling(AioContext *ctx)
{
    return ctx->fdmon_ops->need_wait != aio_poll_disabled;
}

static bool remove_idle_poll_handlers(AioContext *ctx,
                                      AioHandlerList *ready_list,
                                      int64_t now)
{
    AioHandler *node;
    AioHandler *tmp;
    bool progress = false;

    /*
     * File descriptor monitoring implementations without userspace polling
     * support suffer from starvation when a subset of handlers is polled
     * because fds will not be processed in a timely fashion.  Don't remove
     * idle poll handlers.
     */
    if (!fdmon_supports_polling(ctx)) {
        return false;
    }

    QLIST_FOREACH_SAFE(node, &ctx->poll_aio_handlers, node_poll, tmp) {
        if (node->poll_idle_timeout == 0LL) {
            node->poll_idle_timeout = now + POLL_IDLE_INTERVAL_NS;
        } else if (now >= node->poll_idle_timeout) {
            trace_poll_remove(ctx, node, node->pfd.fd);
            node->poll_idle_timeout = 0LL;
            QLIST_SAFE_REMOVE(node, node_poll);
            if (ctx->poll_started && node->io_poll_end) {
                node->io_poll_end(node->opaque);

                /*
                 * Final poll in case ->io_poll_end() races with an event.
                 * Nevermind about re-adding the handler in the rare case where
                 * this causes progress.
                 */
                if (node->io_poll(node->opaque)) {
                    aio_add_poll_ready_handler(ready_list, node);
                    progress = true;
                }
            }
        }
    }

    return progress;
}

/* run_poll_handlers:
 * @ctx: the AioContext
 * @ready_list: the list to place ready handlers on
 * @max_ns: maximum time to poll for, in nanoseconds
 *
 * Polls for a given time.
 *
 * Note that the caller must have incremented ctx->list_lock.
 *
 * Returns: true if progress was made, false otherwise
 */
static bool run_poll_handlers(AioContext *ctx, AioHandlerList *ready_list,
                              int64_t max_ns, int64_t *timeout)
{
    bool progress;
    int64_t start_time, elapsed_time;

    assert(qemu_lockcnt_count(&ctx->list_lock) > 0);

    trace_run_poll_handlers_begin(ctx, max_ns, *timeout);

    /*
     * Optimization: ->io_poll() handlers often contain RCU read critical
     * sections and we therefore see many rcu_read_lock() -> rcu_read_unlock()
     * -> rcu_read_lock() -> ... sequences with expensive memory
     * synchronization primitives.  Make the entire polling loop an RCU
     * critical section because nested rcu_read_lock()/rcu_read_unlock() calls
     * are cheap.
     */
    RCU_READ_LOCK_GUARD();

    start_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
    do {
        progress = run_poll_handlers_once(ctx, ready_list,
                                          start_time, timeout);
        elapsed_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - start_time;
        max_ns = qemu_soonest_timeout(*timeout, max_ns);
        assert(!(max_ns && progress));
    } while (elapsed_time < max_ns && !ctx->fdmon_ops->need_wait(ctx));

    if (remove_idle_poll_handlers(ctx, ready_list,
                                  start_time + elapsed_time)) {
        *timeout = 0;
        progress = true;
    }

    /* If time has passed with no successful polling, adjust *timeout to
     * keep the same ending time.
     */
    if (*timeout != -1) {
        *timeout -= MIN(*timeout, elapsed_time);
    }

    trace_run_poll_handlers_end(ctx, progress, *timeout);
    return progress;
}

/* try_poll_mode:
 * @ctx: the AioContext
 * @ready_list: list to add handlers that need to be run
 * @timeout: timeout for blocking wait, computed by the caller and updated if
 *    polling succeeds.
 *
 * Note that the caller must have incremented ctx->list_lock.
 *
 * Returns: true if progress was made, false otherwise
 */
static bool try_poll_mode(AioContext *ctx, AioHandlerList *ready_list,
                          int64_t *timeout)
{
    int64_t max_ns;

    if (QLIST_EMPTY_RCU(&ctx->poll_aio_handlers)) {
        return false;
    }

    max_ns = qemu_soonest_timeout(*timeout, ctx->poll_ns);
    if (max_ns && !ctx->fdmon_ops->need_wait(ctx)) {
        poll_set_started(ctx, ready_list, true);

        if (run_poll_handlers(ctx, ready_list, max_ns, timeout)) {
            return true;
        }
    }

    if (poll_set_started(ctx, ready_list, false)) {
        *timeout = 0;
        return true;
    }

    return false;
}

bool aio_poll(AioContext *ctx, bool blocking)
{
    AioHandlerList ready_list = QLIST_HEAD_INITIALIZER(ready_list);
    bool progress;
    bool use_notify_me;
    int64_t timeout;
    int64_t start = 0;

    /*
     * There cannot be two concurrent aio_poll calls for the same AioContext (or
     * an aio_poll concurrent with a GSource prepare/check/dispatch callback).
     * We rely on this below to avoid slow locked accesses to ctx->notify_me.
     *
     * aio_poll() may only be called in the AioContext's thread. iohandler_ctx
     * is special in that it runs in the main thread, but that thread's context
     * is qemu_aio_context.
     */
    assert(in_aio_context_home_thread(ctx == iohandler_get_aio_context() ?
                                      qemu_get_aio_context() : ctx));

    qemu_lockcnt_inc(&ctx->list_lock);

    if (ctx->poll_max_ns) {
        start = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
    }

    timeout = blocking ? aio_compute_timeout(ctx) : 0;
    progress = try_poll_mode(ctx, &ready_list, &timeout);
    assert(!(timeout && progress));

    /*
     * aio_notify can avoid the expensive event_notifier_set if
     * everything (file descriptors, bottom halves, timers) will
     * be re-evaluated before the next blocking poll().  This is
     * already true when aio_poll is called with blocking == false;
     * if blocking == true, it is only true after poll() returns,
     * so disable the optimization now.
     */
    use_notify_me = timeout != 0;
    if (use_notify_me) {
        qatomic_set(&ctx->notify_me, qatomic_read(&ctx->notify_me) + 2);
        /*
         * Write ctx->notify_me before reading ctx->notified.  Pairs with
         * smp_mb in aio_notify().
         */
        smp_mb();

        /* Don't block if aio_notify() was called */
        if (qatomic_read(&ctx->notified)) {
            timeout = 0;
        }
    }

    /* If polling is allowed, non-blocking aio_poll does not need the
     * system call---a single round of run_poll_handlers_once suffices.
     */
    if (timeout || ctx->fdmon_ops->need_wait(ctx)) {
        ctx->fdmon_ops->wait(ctx, &ready_list, timeout);
    }

    if (use_notify_me) {
        /* Finish the poll before clearing the flag.  */
        qatomic_store_release(&ctx->notify_me,
                             qatomic_read(&ctx->notify_me) - 2);
    }

    aio_notify_accept(ctx);

    /* Adjust polling time */
    if (ctx->poll_max_ns) {
        int64_t block_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - start;

        if (block_ns <= ctx->poll_ns) {
            /* This is the sweet spot, no adjustment needed */
        } else if (block_ns > ctx->poll_max_ns) {
            /* We'd have to poll for too long, poll less */
            int64_t old = ctx->poll_ns;

            if (ctx->poll_shrink) {
                ctx->poll_ns /= ctx->poll_shrink;
            } else {
                ctx->poll_ns = 0;
            }

            trace_poll_shrink(ctx, old, ctx->poll_ns);
        } else if (ctx->poll_ns < ctx->poll_max_ns &&
                   block_ns < ctx->poll_max_ns) {
            /* There is room to grow, poll longer */
            int64_t old = ctx->poll_ns;
            int64_t grow = ctx->poll_grow;

            if (grow == 0) {
                grow = 2;
            }

            if (ctx->poll_ns) {
                ctx->poll_ns *= grow;
            } else {
                ctx->poll_ns = 4000; /* start polling at 4 microseconds */
            }

            if (ctx->poll_ns > ctx->poll_max_ns) {
                ctx->poll_ns = ctx->poll_max_ns;
            }

            trace_poll_grow(ctx, old, ctx->poll_ns);
        }
    }

    progress |= aio_bh_poll(ctx);
    progress |= aio_dispatch_ready_handlers(ctx, &ready_list);

    aio_free_deleted_handlers(ctx);

    qemu_lockcnt_dec(&ctx->list_lock);

    progress |= timerlistgroup_run_timers(&ctx->tlg);

    return progress;
}

void aio_context_setup(AioContext *ctx)
{
    ctx->fdmon_ops = &fdmon_poll_ops;
    ctx->epollfd = -1;

    /* Use the fastest fd monitoring implementation if available */
    if (fdmon_io_uring_setup(ctx)) {
        return;
    }

    fdmon_epoll_setup(ctx);
}

void aio_context_destroy(AioContext *ctx)
{
    fdmon_io_uring_destroy(ctx);
    fdmon_epoll_disable(ctx);
    aio_free_deleted_handlers(ctx);
}

void aio_context_use_g_source(AioContext *ctx)
{
    /*
     * Disable io_uring when the glib main loop is used because it doesn't
     * support mixed glib/aio_poll() usage. It relies on aio_poll() being
     * called regularly so that changes to the monitored file descriptors are
     * submitted, otherwise a list of pending fd handlers builds up.
     */
    fdmon_io_uring_destroy(ctx);
    aio_free_deleted_handlers(ctx);
}

void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns,
                                 int64_t grow, int64_t shrink, Error **errp)
{
    /* No thread synchronization here, it doesn't matter if an incorrect value
     * is used once.
     */
    ctx->poll_max_ns = max_ns;
    ctx->poll_ns = 0;
    ctx->poll_grow = grow;
    ctx->poll_shrink = shrink;

    aio_notify(ctx);
}

void aio_context_set_aio_params(AioContext *ctx, int64_t max_batch,
                                Error **errp)
{
    /*
     * No thread synchronization here, it doesn't matter if an incorrect value
     * is used once.
     */
    ctx->aio_max_batch = max_batch;

    aio_notify(ctx);
}