aboutsummaryrefslogtreecommitdiff
path: root/util/async.c
blob: 3165a28f2f77df330f2b42db98c2845d449d2260 (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
/*
 * Data plane event loop
 *
 * Copyright (c) 2003-2008 Fabrice Bellard
 * Copyright (c) 2009-2017 QEMU contributors
 *
 * 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 "qapi/error.h"
#include "block/aio.h"
#include "block/thread-pool.h"
#include "qemu/main-loop.h"
#include "qemu/atomic.h"
#include "qemu/rcu_queue.h"
#include "block/raw-aio.h"
#include "qemu/coroutine_int.h"
#include "trace.h"

/***********************************************************/
/* bottom halves (can be seen as timers which expire ASAP) */

/* QEMUBH::flags values */
enum {
    /* Already enqueued and waiting for aio_bh_poll() */
    BH_PENDING   = (1 << 0),

    /* Invoke the callback */
    BH_SCHEDULED = (1 << 1),

    /* Delete without invoking callback */
    BH_DELETED   = (1 << 2),

    /* Delete after invoking callback */
    BH_ONESHOT   = (1 << 3),

    /* Schedule periodically when the event loop is idle */
    BH_IDLE      = (1 << 4),
};

struct QEMUBH {
    AioContext *ctx;
    QEMUBHFunc *cb;
    void *opaque;
    QSLIST_ENTRY(QEMUBH) next;
    unsigned flags;
};

/* Called concurrently from any thread */
static void aio_bh_enqueue(QEMUBH *bh, unsigned new_flags)
{
    AioContext *ctx = bh->ctx;
    unsigned old_flags;

    /*
     * The memory barrier implicit in atomic_fetch_or makes sure that:
     * 1. idle & any writes needed by the callback are done before the
     *    locations are read in the aio_bh_poll.
     * 2. ctx is loaded before the callback has a chance to execute and bh
     *    could be freed.
     */
    old_flags = atomic_fetch_or(&bh->flags, BH_PENDING | new_flags);
    if (!(old_flags & BH_PENDING)) {
        QSLIST_INSERT_HEAD_ATOMIC(&ctx->bh_list, bh, next);
    }

    aio_notify(ctx);
}

/* Only called from aio_bh_poll() and aio_ctx_finalize() */
static QEMUBH *aio_bh_dequeue(BHList *head, unsigned *flags)
{
    QEMUBH *bh = QSLIST_FIRST_RCU(head);

    if (!bh) {
        return NULL;
    }

    QSLIST_REMOVE_HEAD(head, next);

    /*
     * The atomic_and is paired with aio_bh_enqueue().  The implicit memory
     * barrier ensures that the callback sees all writes done by the scheduling
     * thread.  It also ensures that the scheduling thread sees the cleared
     * flag before bh->cb has run, and thus will call aio_notify again if
     * necessary.
     */
    *flags = atomic_fetch_and(&bh->flags,
                              ~(BH_PENDING | BH_SCHEDULED | BH_IDLE));
    return bh;
}

void aio_bh_schedule_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
{
    QEMUBH *bh;
    bh = g_new(QEMUBH, 1);
    *bh = (QEMUBH){
        .ctx = ctx,
        .cb = cb,
        .opaque = opaque,
    };
    aio_bh_enqueue(bh, BH_SCHEDULED | BH_ONESHOT);
}

QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
{
    QEMUBH *bh;
    bh = g_new(QEMUBH, 1);
    *bh = (QEMUBH){
        .ctx = ctx,
        .cb = cb,
        .opaque = opaque,
    };
    return bh;
}

void aio_bh_call(QEMUBH *bh)
{
    bh->cb(bh->opaque);
}

/* Multiple occurrences of aio_bh_poll cannot be called concurrently. */
int aio_bh_poll(AioContext *ctx)
{
    BHListSlice slice;
    BHListSlice *s;
    int ret = 0;

    QSLIST_MOVE_ATOMIC(&slice.bh_list, &ctx->bh_list);
    QSIMPLEQ_INSERT_TAIL(&ctx->bh_slice_list, &slice, next);

    while ((s = QSIMPLEQ_FIRST(&ctx->bh_slice_list))) {
        QEMUBH *bh;
        unsigned flags;

        bh = aio_bh_dequeue(&s->bh_list, &flags);
        if (!bh) {
            QSIMPLEQ_REMOVE_HEAD(&ctx->bh_slice_list, next);
            continue;
        }

        if ((flags & (BH_SCHEDULED | BH_DELETED)) == BH_SCHEDULED) {
            /* Idle BHs don't count as progress */
            if (!(flags & BH_IDLE)) {
                ret = 1;
            }
            aio_bh_call(bh);
        }
        if (flags & (BH_DELETED | BH_ONESHOT)) {
            g_free(bh);
        }
    }

    return ret;
}

void qemu_bh_schedule_idle(QEMUBH *bh)
{
    aio_bh_enqueue(bh, BH_SCHEDULED | BH_IDLE);
}

void qemu_bh_schedule(QEMUBH *bh)
{
    aio_bh_enqueue(bh, BH_SCHEDULED);
}

/* This func is async.
 */
void qemu_bh_cancel(QEMUBH *bh)
{
    atomic_and(&bh->flags, ~BH_SCHEDULED);
}

/* This func is async.The bottom half will do the delete action at the finial
 * end.
 */
void qemu_bh_delete(QEMUBH *bh)
{
    aio_bh_enqueue(bh, BH_DELETED);
}

static int64_t aio_compute_bh_timeout(BHList *head, int timeout)
{
    QEMUBH *bh;

    QSLIST_FOREACH_RCU(bh, head, next) {
        if ((bh->flags & (BH_SCHEDULED | BH_DELETED)) == BH_SCHEDULED) {
            if (bh->flags & BH_IDLE) {
                /* idle bottom halves will be polled at least
                 * every 10ms */
                timeout = 10000000;
            } else {
                /* non-idle bottom halves will be executed
                 * immediately */
                return 0;
            }
        }
    }

    return timeout;
}

int64_t
aio_compute_timeout(AioContext *ctx)
{
    BHListSlice *s;
    int64_t deadline;
    int timeout = -1;

    timeout = aio_compute_bh_timeout(&ctx->bh_list, timeout);
    if (timeout == 0) {
        return 0;
    }

    QSIMPLEQ_FOREACH(s, &ctx->bh_slice_list, next) {
        timeout = aio_compute_bh_timeout(&s->bh_list, timeout);
        if (timeout == 0) {
            return 0;
        }
    }

    deadline = timerlistgroup_deadline_ns(&ctx->tlg);
    if (deadline == 0) {
        return 0;
    } else {
        return qemu_soonest_timeout(timeout, deadline);
    }
}

static gboolean
aio_ctx_prepare(GSource *source, gint    *timeout)
{
    AioContext *ctx = (AioContext *) source;

    atomic_set(&ctx->notify_me, atomic_read(&ctx->notify_me) | 1);

    /*
     * Write ctx->notify_me before computing the timeout
     * (reading bottom half flags, etc.).  Pairs with
     * smp_mb in aio_notify().
     */
    smp_mb();

    /* We assume there is no timeout already supplied */
    *timeout = qemu_timeout_ns_to_ms(aio_compute_timeout(ctx));

    if (aio_prepare(ctx)) {
        *timeout = 0;
    }

    return *timeout == 0;
}

static gboolean
aio_ctx_check(GSource *source)
{
    AioContext *ctx = (AioContext *) source;
    QEMUBH *bh;
    BHListSlice *s;

    /* Finish computing the timeout before clearing the flag.  */
    atomic_store_release(&ctx->notify_me, atomic_read(&ctx->notify_me) & ~1);
    aio_notify_accept(ctx);

    QSLIST_FOREACH_RCU(bh, &ctx->bh_list, next) {
        if ((bh->flags & (BH_SCHEDULED | BH_DELETED)) == BH_SCHEDULED) {
            return true;
        }
    }

    QSIMPLEQ_FOREACH(s, &ctx->bh_slice_list, next) {
        QSLIST_FOREACH_RCU(bh, &s->bh_list, next) {
            if ((bh->flags & (BH_SCHEDULED | BH_DELETED)) == BH_SCHEDULED) {
                return true;
            }
        }
    }
    return aio_pending(ctx) || (timerlistgroup_deadline_ns(&ctx->tlg) == 0);
}

static gboolean
aio_ctx_dispatch(GSource     *source,
                 GSourceFunc  callback,
                 gpointer     user_data)
{
    AioContext *ctx = (AioContext *) source;

    assert(callback == NULL);
    aio_dispatch(ctx);
    return true;
}

static void
aio_ctx_finalize(GSource     *source)
{
    AioContext *ctx = (AioContext *) source;
    QEMUBH *bh;
    unsigned flags;

    thread_pool_free(ctx->thread_pool);

#ifdef CONFIG_LINUX_AIO
    if (ctx->linux_aio) {
        laio_detach_aio_context(ctx->linux_aio, ctx);
        laio_cleanup(ctx->linux_aio);
        ctx->linux_aio = NULL;
    }
#endif

#ifdef CONFIG_LINUX_IO_URING
    if (ctx->linux_io_uring) {
        luring_detach_aio_context(ctx->linux_io_uring, ctx);
        luring_cleanup(ctx->linux_io_uring);
        ctx->linux_io_uring = NULL;
    }
#endif

    assert(QSLIST_EMPTY(&ctx->scheduled_coroutines));
    qemu_bh_delete(ctx->co_schedule_bh);

    /* There must be no aio_bh_poll() calls going on */
    assert(QSIMPLEQ_EMPTY(&ctx->bh_slice_list));

    while ((bh = aio_bh_dequeue(&ctx->bh_list, &flags))) {
        /* qemu_bh_delete() must have been called on BHs in this AioContext */
        assert(flags & BH_DELETED);

        g_free(bh);
    }

    aio_set_event_notifier(ctx, &ctx->notifier, false, NULL, NULL);
    event_notifier_cleanup(&ctx->notifier);
    qemu_rec_mutex_destroy(&ctx->lock);
    qemu_lockcnt_destroy(&ctx->list_lock);
    timerlistgroup_deinit(&ctx->tlg);
    aio_context_destroy(ctx);
}

static GSourceFuncs aio_source_funcs = {
    aio_ctx_prepare,
    aio_ctx_check,
    aio_ctx_dispatch,
    aio_ctx_finalize
};

GSource *aio_get_g_source(AioContext *ctx)
{
    g_source_ref(&ctx->source);
    return &ctx->source;
}

ThreadPool *aio_get_thread_pool(AioContext *ctx)
{
    if (!ctx->thread_pool) {
        ctx->thread_pool = thread_pool_new(ctx);
    }
    return ctx->thread_pool;
}

#ifdef CONFIG_LINUX_AIO
LinuxAioState *aio_setup_linux_aio(AioContext *ctx, Error **errp)
{
    if (!ctx->linux_aio) {
        ctx->linux_aio = laio_init(errp);
        if (ctx->linux_aio) {
            laio_attach_aio_context(ctx->linux_aio, ctx);
        }
    }
    return ctx->linux_aio;
}

LinuxAioState *aio_get_linux_aio(AioContext *ctx)
{
    assert(ctx->linux_aio);
    return ctx->linux_aio;
}
#endif

#ifdef CONFIG_LINUX_IO_URING
LuringState *aio_setup_linux_io_uring(AioContext *ctx, Error **errp)
{
    if (ctx->linux_io_uring) {
        return ctx->linux_io_uring;
    }

    ctx->linux_io_uring = luring_init(errp);
    if (!ctx->linux_io_uring) {
        return NULL;
    }

    luring_attach_aio_context(ctx->linux_io_uring, ctx);
    return ctx->linux_io_uring;
}

LuringState *aio_get_linux_io_uring(AioContext *ctx)
{
    assert(ctx->linux_io_uring);
    return ctx->linux_io_uring;
}
#endif

void aio_notify(AioContext *ctx)
{
    /* Write e.g. bh->scheduled before reading ctx->notify_me.  Pairs
     * with smp_mb in aio_ctx_prepare or aio_poll.
     */
    smp_mb();
    if (atomic_read(&ctx->notify_me)) {
        event_notifier_set(&ctx->notifier);
        atomic_mb_set(&ctx->notified, true);
    }
}

void aio_notify_accept(AioContext *ctx)
{
    if (atomic_xchg(&ctx->notified, false)
#ifdef WIN32
        || true
#endif
    ) {
        event_notifier_test_and_clear(&ctx->notifier);
    }
}

static void aio_timerlist_notify(void *opaque, QEMUClockType type)
{
    aio_notify(opaque);
}

static void event_notifier_dummy_cb(EventNotifier *e)
{
}

/* Returns true if aio_notify() was called (e.g. a BH was scheduled) */
static bool event_notifier_poll(void *opaque)
{
    EventNotifier *e = opaque;
    AioContext *ctx = container_of(e, AioContext, notifier);

    return atomic_read(&ctx->notified);
}

static void co_schedule_bh_cb(void *opaque)
{
    AioContext *ctx = opaque;
    QSLIST_HEAD(, Coroutine) straight, reversed;

    QSLIST_MOVE_ATOMIC(&reversed, &ctx->scheduled_coroutines);
    QSLIST_INIT(&straight);

    while (!QSLIST_EMPTY(&reversed)) {
        Coroutine *co = QSLIST_FIRST(&reversed);
        QSLIST_REMOVE_HEAD(&reversed, co_scheduled_next);
        QSLIST_INSERT_HEAD(&straight, co, co_scheduled_next);
    }

    while (!QSLIST_EMPTY(&straight)) {
        Coroutine *co = QSLIST_FIRST(&straight);
        QSLIST_REMOVE_HEAD(&straight, co_scheduled_next);
        trace_aio_co_schedule_bh_cb(ctx, co);
        aio_context_acquire(ctx);

        /* Protected by write barrier in qemu_aio_coroutine_enter */
        atomic_set(&co->scheduled, NULL);
        qemu_aio_coroutine_enter(ctx, co);
        aio_context_release(ctx);
    }
}

AioContext *aio_context_new(Error **errp)
{
    int ret;
    AioContext *ctx;

    ctx = (AioContext *) g_source_new(&aio_source_funcs, sizeof(AioContext));
    QSLIST_INIT(&ctx->bh_list);
    QSIMPLEQ_INIT(&ctx->bh_slice_list);
    aio_context_setup(ctx);

    ret = event_notifier_init(&ctx->notifier, false);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "Failed to initialize event notifier");
        goto fail;
    }
    g_source_set_can_recurse(&ctx->source, true);
    qemu_lockcnt_init(&ctx->list_lock);

    ctx->co_schedule_bh = aio_bh_new(ctx, co_schedule_bh_cb, ctx);
    QSLIST_INIT(&ctx->scheduled_coroutines);

    aio_set_event_notifier(ctx, &ctx->notifier,
                           false,
                           event_notifier_dummy_cb,
                           event_notifier_poll);
#ifdef CONFIG_LINUX_AIO
    ctx->linux_aio = NULL;
#endif

#ifdef CONFIG_LINUX_IO_URING
    ctx->linux_io_uring = NULL;
#endif

    ctx->thread_pool = NULL;
    qemu_rec_mutex_init(&ctx->lock);
    timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx);

    ctx->poll_ns = 0;
    ctx->poll_max_ns = 0;
    ctx->poll_grow = 0;
    ctx->poll_shrink = 0;

    return ctx;
fail:
    g_source_destroy(&ctx->source);
    return NULL;
}

void aio_co_schedule(AioContext *ctx, Coroutine *co)
{
    trace_aio_co_schedule(ctx, co);
    const char *scheduled = atomic_cmpxchg(&co->scheduled, NULL,
                                           __func__);

    if (scheduled) {
        fprintf(stderr,
                "%s: Co-routine was already scheduled in '%s'\n",
                __func__, scheduled);
        abort();
    }

    /* The coroutine might run and release the last ctx reference before we
     * invoke qemu_bh_schedule().  Take a reference to keep ctx alive until
     * we're done.
     */
    aio_context_ref(ctx);

    QSLIST_INSERT_HEAD_ATOMIC(&ctx->scheduled_coroutines,
                              co, co_scheduled_next);
    qemu_bh_schedule(ctx->co_schedule_bh);

    aio_context_unref(ctx);
}

void aio_co_wake(struct Coroutine *co)
{
    AioContext *ctx;

    /* Read coroutine before co->ctx.  Matches smp_wmb in
     * qemu_coroutine_enter.
     */
    smp_read_barrier_depends();
    ctx = atomic_read(&co->ctx);

    aio_co_enter(ctx, co);
}

void aio_co_enter(AioContext *ctx, struct Coroutine *co)
{
    if (ctx != qemu_get_current_aio_context()) {
        aio_co_schedule(ctx, co);
        return;
    }

    if (qemu_in_coroutine()) {
        Coroutine *self = qemu_coroutine_self();
        assert(self != co);
        QSIMPLEQ_INSERT_TAIL(&self->co_queue_wakeup, co, co_queue_next);
    } else {
        aio_context_acquire(ctx);
        qemu_aio_coroutine_enter(ctx, co);
        aio_context_release(ctx);
    }
}

void aio_context_ref(AioContext *ctx)
{
    g_source_ref(&ctx->source);
}

void aio_context_unref(AioContext *ctx)
{
    g_source_unref(&ctx->source);
}

void aio_context_acquire(AioContext *ctx)
{
    qemu_rec_mutex_lock(&ctx->lock);
}

void aio_context_release(AioContext *ctx)
{
    qemu_rec_mutex_unlock(&ctx->lock);
}