summaryrefslogtreecommitdiffstats
path: root/drivers/dma-buf/dma-fence.c
blob: 227a19476d56dcdcc4fa57084ee4d707f39e3778 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Fence mechanism for dma-buf and to allow for asynchronous dma access
 *
 * Copyright (C) 2012 Canonical Ltd
 * Copyright (C) 2012 Texas Instruments
 *
 * Authors:
 * Rob Clark <robdclark@gmail.com>
 * Maarten Lankhorst <maarten.lankhorst@canonical.com>
 */

#include <linux/slab.h>
#include <linux/export.h>
#include <linux/atomic.h>
#include <linux/dma-fence.h>
#include <linux/sched/signal.h>

#define CREATE_TRACE_POINTS
#include <trace/events/dma_fence.h>

EXPORT_TRACEPOINT_SYMBOL(dma_fence_emit);
EXPORT_TRACEPOINT_SYMBOL(dma_fence_enable_signal);
EXPORT_TRACEPOINT_SYMBOL(dma_fence_signaled);

static DEFINE_SPINLOCK(dma_fence_stub_lock);
static struct dma_fence dma_fence_stub;

/*
 * fence context counter: each execution context should have its own
 * fence context, this allows checking if fences belong to the same
 * context or not. One device can have multiple separate contexts,
 * and they're used if some engine can run independently of another.
 */
static atomic64_t dma_fence_context_counter = ATOMIC64_INIT(1);

/**
 * DOC: DMA fences overview
 *
 * DMA fences, represented by &struct dma_fence, are the kernel internal
 * synchronization primitive for DMA operations like GPU rendering, video
 * encoding/decoding, or displaying buffers on a screen.
 *
 * A fence is initialized using dma_fence_init() and completed using
 * dma_fence_signal(). Fences are associated with a context, allocated through
 * dma_fence_context_alloc(), and all fences on the same context are
 * fully ordered.
 *
 * Since the purposes of fences is to facilitate cross-device and
 * cross-application synchronization, there's multiple ways to use one:
 *
 * - Individual fences can be exposed as a &sync_file, accessed as a file
 *   descriptor from userspace, created by calling sync_file_create(). This is
 *   called explicit fencing, since userspace passes around explicit
 *   synchronization points.
 *
 * - Some subsystems also have their own explicit fencing primitives, like
 *   &drm_syncobj. Compared to &sync_file, a &drm_syncobj allows the underlying
 *   fence to be updated.
 *
 * - Then there's also implicit fencing, where the synchronization points are
 *   implicitly passed around as part of shared &dma_buf instances. Such
 *   implicit fences are stored in &struct reservation_object through the
 *   &dma_buf.resv pointer.
 */

static const char *dma_fence_stub_get_name(struct dma_fence *fence)
{
        return "stub";
}

static const struct dma_fence_ops dma_fence_stub_ops = {
	.get_driver_name = dma_fence_stub_get_name,
	.get_timeline_name = dma_fence_stub_get_name,
};

/**
 * dma_fence_get_stub - return a signaled fence
 *
 * Return a stub fence which is already signaled.
 */
struct dma_fence *dma_fence_get_stub(void)
{
	spin_lock(&dma_fence_stub_lock);
	if (!dma_fence_stub.ops) {
		dma_fence_init(&dma_fence_stub,
			       &dma_fence_stub_ops,
			       &dma_fence_stub_lock,
			       0, 0);
		dma_fence_signal_locked(&dma_fence_stub);
	}
	spin_unlock(&dma_fence_stub_lock);

	return dma_fence_get(&dma_fence_stub);
}
EXPORT_SYMBOL(dma_fence_get_stub);

/**
 * dma_fence_context_alloc - allocate an array of fence contexts
 * @num: amount of contexts to allocate
 *
 * This function will return the first index of the number of fence contexts
 * allocated.  The fence context is used for setting &dma_fence.context to a
 * unique number by passing the context to dma_fence_init().
 */
u64 dma_fence_context_alloc(unsigned num)
{
	WARN_ON(!num);
	return atomic64_add_return(num, &dma_fence_context_counter) - num;
}
EXPORT_SYMBOL(dma_fence_context_alloc);

/**
 * dma_fence_signal_locked - signal completion of a fence
 * @fence: the fence to signal
 *
 * Signal completion for software callbacks on a fence, this will unblock
 * dma_fence_wait() calls and run all the callbacks added with
 * dma_fence_add_callback(). Can be called multiple times, but since a fence
 * can only go from the unsignaled to the signaled state and not back, it will
 * only be effective the first time.
 *
 * Unlike dma_fence_signal(), this function must be called with &dma_fence.lock
 * held.
 *
 * Returns 0 on success and a negative error value when @fence has been
 * signalled already.
 */
int dma_fence_signal_locked(struct dma_fence *fence)
{
	struct dma_fence_cb *cur, *tmp;
	int ret = 0;

	lockdep_assert_held(fence->lock);

	if (WARN_ON(!fence))
		return -EINVAL;

	if (test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
		ret = -EINVAL;

		/*
		 * we might have raced with the unlocked dma_fence_signal,
		 * still run through all callbacks
		 */
	} else {
		fence->timestamp = ktime_get();
		set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags);
		trace_dma_fence_signaled(fence);
	}

	list_for_each_entry_safe(cur, tmp, &fence->cb_list, node) {
		list_del_init(&cur->node);
		cur->func(fence, cur);
	}
	return ret;
}
EXPORT_SYMBOL(dma_fence_signal_locked);

/**
 * dma_fence_signal - signal completion of a fence
 * @fence: the fence to signal
 *
 * Signal completion for software callbacks on a fence, this will unblock
 * dma_fence_wait() calls and run all the callbacks added with
 * dma_fence_add_callback(). Can be called multiple times, but since a fence
 * can only go from the unsignaled to the signaled state and not back, it will
 * only be effective the first time.
 *
 * Returns 0 on success and a negative error value when @fence has been
 * signalled already.
 */
int dma_fence_signal(struct dma_fence *fence)
{
	unsigned long flags;

	if (!fence)
		return -EINVAL;

	if (test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
		return -EINVAL;

	fence->timestamp = ktime_get();
	set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags);
	trace_dma_fence_signaled(fence);

	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags)) {
		struct dma_fence_cb *cur, *tmp;

		spin_lock_irqsave(fence->lock, flags);
		list_for_each_entry_safe(cur, tmp, &fence->cb_list, node) {
			list_del_init(&cur->node);
			cur->func(fence, cur);
		}
		spin_unlock_irqrestore(fence->lock, flags);
	}
	return 0;
}
EXPORT_SYMBOL(dma_fence_signal);

/**
 * dma_fence_wait_timeout - sleep until the fence gets signaled
 * or until timeout elapses
 * @fence: the fence to wait on
 * @intr: if true, do an interruptible wait
 * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
 *
 * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the
 * remaining timeout in jiffies on success. Other error values may be
 * returned on custom implementations.
 *
 * Performs a synchronous wait on this fence. It is assumed the caller
 * directly or indirectly (buf-mgr between reservation and committing)
 * holds a reference to the fence, otherwise the fence might be
 * freed before return, resulting in undefined behavior.
 *
 * See also dma_fence_wait() and dma_fence_wait_any_timeout().
 */
signed long
dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout)
{
	signed long ret;

	if (WARN_ON(timeout < 0))
		return -EINVAL;

	trace_dma_fence_wait_start(fence);
	if (fence->ops->wait)
		ret = fence->ops->wait(fence, intr, timeout);
	else
		ret = dma_fence_default_wait(fence, intr, timeout);
	trace_dma_fence_wait_end(fence);
	return ret;
}
EXPORT_SYMBOL(dma_fence_wait_timeout);

/**
 * dma_fence_release - default relese function for fences
 * @kref: &dma_fence.recfount
 *
 * This is the default release functions for &dma_fence. Drivers shouldn't call
 * this directly, but instead call dma_fence_put().
 */
void dma_fence_release(struct kref *kref)
{
	struct dma_fence *fence =
		container_of(kref, struct dma_fence, refcount);

	trace_dma_fence_destroy(fence);

	/* Failed to signal before release, could be a refcounting issue */
	WARN_ON(!list_empty(&fence->cb_list));

	if (fence->ops->release)
		fence->ops->release(fence);
	else
		dma_fence_free(fence);
}
EXPORT_SYMBOL(dma_fence_release);

/**
 * dma_fence_free - default release function for &dma_fence.
 * @fence: fence to release
 *
 * This is the default implementation for &dma_fence_ops.release. It calls
 * kfree_rcu() on @fence.
 */
void dma_fence_free(struct dma_fence *fence)
{
	kfree_rcu(fence, rcu);
}
EXPORT_SYMBOL(dma_fence_free);

/**
 * dma_fence_enable_sw_signaling - enable signaling on fence
 * @fence: the fence to enable
 *
 * This will request for sw signaling to be enabled, to make the fence
 * complete as soon as possible. This calls &dma_fence_ops.enable_signaling
 * internally.
 */
void dma_fence_enable_sw_signaling(struct dma_fence *fence)
{
	unsigned long flags;

	if (!test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
			      &fence->flags) &&
	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) &&
	    fence->ops->enable_signaling) {
		trace_dma_fence_enable_signal(fence);

		spin_lock_irqsave(fence->lock, flags);

		if (!fence->ops->enable_signaling(fence))
			dma_fence_signal_locked(fence);

		spin_unlock_irqrestore(fence->lock, flags);
	}
}
EXPORT_SYMBOL(dma_fence_enable_sw_signaling);

/**
 * dma_fence_add_callback - add a callback to be called when the fence
 * is signaled
 * @fence: the fence to wait on
 * @cb: the callback to register
 * @func: the function to call
 *
 * @cb will be initialized by dma_fence_add_callback(), no initialization
 * by the caller is required. Any number of callbacks can be registered
 * to a fence, but a callback can only be registered to one fence at a time.
 *
 * Note that the callback can be called from an atomic context.  If
 * fence is already signaled, this function will return -ENOENT (and
 * *not* call the callback).
 *
 * Add a software callback to the fence. Same restrictions apply to
 * refcount as it does to dma_fence_wait(), however the caller doesn't need to
 * keep a refcount to fence afterward dma_fence_add_callback() has returned:
 * when software access is enabled, the creator of the fence is required to keep
 * the fence alive until after it signals with dma_fence_signal(). The callback
 * itself can be called from irq context.
 *
 * Returns 0 in case of success, -ENOENT if the fence is already signaled
 * and -EINVAL in case of error.
 */
int dma_fence_add_callback(struct dma_fence *fence, struct dma_fence_cb *cb,
			   dma_fence_func_t func)
{
	unsigned long flags;
	int ret = 0;
	bool was_set;

	if (WARN_ON(!fence || !func))
		return -EINVAL;

	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
		INIT_LIST_HEAD(&cb->node);
		return -ENOENT;
	}

	spin_lock_irqsave(fence->lock, flags);

	was_set = test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
				   &fence->flags);

	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
		ret = -ENOENT;
	else if (!was_set && fence->ops->enable_signaling) {
		trace_dma_fence_enable_signal(fence);

		if (!fence->ops->enable_signaling(fence)) {
			dma_fence_signal_locked(fence);
			ret = -ENOENT;
		}
	}

	if (!ret) {
		cb->func = func;
		list_add_tail(&cb->node, &fence->cb_list);
	} else
		INIT_LIST_HEAD(&cb->node);
	spin_unlock_irqrestore(fence->lock, flags);

	return ret;
}
EXPORT_SYMBOL(dma_fence_add_callback);

/**
 * dma_fence_get_status - returns the status upon completion
 * @fence: the dma_fence to query
 *
 * This wraps dma_fence_get_status_locked() to return the error status
 * condition on a signaled fence. See dma_fence_get_status_locked() for more
 * details.
 *
 * Returns 0 if the fence has not yet been signaled, 1 if the fence has
 * been signaled without an error condition, or a negative error code
 * if the fence has been completed in err.
 */
int dma_fence_get_status(struct dma_fence *fence)
{
	unsigned long flags;
	int status;

	spin_lock_irqsave(fence->lock, flags);
	status = dma_fence_get_status_locked(fence);
	spin_unlock_irqrestore(fence->lock, flags);

	return status;
}
EXPORT_SYMBOL(dma_fence_get_status);

/**
 * dma_fence_remove_callback - remove a callback from the signaling list
 * @fence: the fence to wait on
 * @cb: the callback to remove
 *
 * Remove a previously queued callback from the fence. This function returns
 * true if the callback is successfully removed, or false if the fence has
 * already been signaled.
 *
 * *WARNING*:
 * Cancelling a callback should only be done if you really know what you're
 * doing, since deadlocks and race conditions could occur all too easily. For
 * this reason, it should only ever be done on hardware lockup recovery,
 * with a reference held to the fence.
 *
 * Behaviour is undefined if @cb has not been added to @fence using
 * dma_fence_add_callback() beforehand.
 */
bool
dma_fence_remove_callback(struct dma_fence *fence, struct dma_fence_cb *cb)
{
	unsigned long flags;
	bool ret;

	spin_lock_irqsave(fence->lock, flags);

	ret = !list_empty(&cb->node);
	if (ret)
		list_del_init(&cb->node);

	spin_unlock_irqrestore(fence->lock, flags);

	return ret;
}
EXPORT_SYMBOL(dma_fence_remove_callback);

struct default_wait_cb {
	struct dma_fence_cb base;
	struct task_struct *task;
};

static void
dma_fence_default_wait_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
{
	struct default_wait_cb *wait =
		container_of(cb, struct default_wait_cb, base);

	wake_up_state(wait->task, TASK_NORMAL);
}

/**
 * dma_fence_default_wait - default sleep until the fence gets signaled
 * or until timeout elapses
 * @fence: the fence to wait on
 * @intr: if true, do an interruptible wait
 * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
 *
 * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the
 * remaining timeout in jiffies on success. If timeout is zero the value one is
 * returned if the fence is already signaled for consistency with other
 * functions taking a jiffies timeout.
 */
signed long
dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout)
{
	struct default_wait_cb cb;
	unsigned long flags;
	signed long ret = timeout ? timeout : 1;
	bool was_set;

	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
		return ret;

	spin_lock_irqsave(fence->lock, flags);

	if (intr && signal_pending(current)) {
		ret = -ERESTARTSYS;
		goto out;
	}

	was_set = test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
				   &fence->flags);

	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
		goto out;

	if (!was_set && fence->ops->enable_signaling) {
		trace_dma_fence_enable_signal(fence);

		if (!fence->ops->enable_signaling(fence)) {
			dma_fence_signal_locked(fence);
			goto out;
		}
	}

	if (!timeout) {
		ret = 0;
		goto out;
	}

	cb.base.func = dma_fence_default_wait_cb;
	cb.task = current;
	list_add(&cb.base.node, &fence->cb_list);

	while (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) && ret > 0) {
		if (intr)
			__set_current_state(TASK_INTERRUPTIBLE);
		else
			__set_current_state(TASK_UNINTERRUPTIBLE);
		spin_unlock_irqrestore(fence->lock, flags);

		ret = schedule_timeout(ret);

		spin_lock_irqsave(fence->lock, flags);
		if (ret > 0 && intr && signal_pending(current))
			ret = -ERESTARTSYS;
	}

	if (!list_empty(&cb.base.node))
		list_del(&cb.base.node);
	__set_current_state(TASK_RUNNING);

out:
	spin_unlock_irqrestore(fence->lock, flags);
	return ret;
}
EXPORT_SYMBOL(dma_fence_default_wait);

static bool
dma_fence_test_signaled_any(struct dma_fence **fences, uint32_t count,
			    uint32_t *idx)
{
	int i;

	for (i = 0; i < count; ++i) {
		struct dma_fence *fence = fences[i];
		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
			if (idx)
				*idx = i;
			return true;
		}
	}
	return false;
}

/**
 * dma_fence_wait_any_timeout - sleep until any fence gets signaled
 * or until timeout elapses
 * @fences: array of fences to wait on
 * @count: number of fences to wait on
 * @intr: if true, do an interruptible wait
 * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
 * @idx: used to store the first signaled fence index, meaningful only on
 *	positive return
 *
 * Returns -EINVAL on custom fence wait implementation, -ERESTARTSYS if
 * interrupted, 0 if the wait timed out, or the remaining timeout in jiffies
 * on success.
 *
 * Synchronous waits for the first fence in the array to be signaled. The
 * caller needs to hold a reference to all fences in the array, otherwise a
 * fence might be freed before return, resulting in undefined behavior.
 *
 * See also dma_fence_wait() and dma_fence_wait_timeout().
 */
signed long
dma_fence_wait_any_timeout(struct dma_fence **fences, uint32_t count,
			   bool intr, signed long timeout, uint32_t *idx)
{
	struct default_wait_cb *cb;
	signed long ret = timeout;
	unsigned i;

	if (WARN_ON(!fences || !count || timeout < 0))
		return -EINVAL;

	if (timeout == 0) {
		for (i = 0; i < count; ++i)
			if (dma_fence_is_signaled(fences[i])) {
				if (idx)
					*idx = i;
				return 1;
			}

		return 0;
	}

	cb = kcalloc(count, sizeof(struct default_wait_cb), GFP_KERNEL);
	if (cb == NULL) {
		ret = -ENOMEM;
		goto err_free_cb;
	}

	for (i = 0; i < count; ++i) {
		struct dma_fence *fence = fences[i];

		cb[i].task = current;
		if (dma_fence_add_callback(fence, &cb[i].base,
					   dma_fence_default_wait_cb)) {
			/* This fence is already signaled */
			if (idx)
				*idx = i;
			goto fence_rm_cb;
		}
	}

	while (ret > 0) {
		if (intr)
			set_current_state(TASK_INTERRUPTIBLE);
		else
			set_current_state(TASK_UNINTERRUPTIBLE);

		if (dma_fence_test_signaled_any(fences, count, idx))
			break;

		ret = schedule_timeout(ret);

		if (ret > 0 && intr && signal_pending(current))
			ret = -ERESTARTSYS;
	}

	__set_current_state(TASK_RUNNING);

fence_rm_cb:
	while (i-- > 0)
		dma_fence_remove_callback(fences[i], &cb[i].base);

err_free_cb:
	kfree(cb);

	return ret;
}
EXPORT_SYMBOL(dma_fence_wait_any_timeout);

/**
 * dma_fence_init - Initialize a custom fence.
 * @fence: the fence to initialize
 * @ops: the dma_fence_ops for operations on this fence
 * @lock: the irqsafe spinlock to use for locking this fence
 * @context: the execution context this fence is run on
 * @seqno: a linear increasing sequence number for this context
 *
 * Initializes an allocated fence, the caller doesn't have to keep its
 * refcount after committing with this fence, but it will need to hold a
 * refcount again if &dma_fence_ops.enable_signaling gets called.
 *
 * context and seqno are used for easy comparison between fences, allowing
 * to check which fence is later by simply using dma_fence_later().
 */
void
dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,
	       spinlock_t *lock, u64 context, u64 seqno)
{
	BUG_ON(!lock);
	BUG_ON(!ops || !ops->get_driver_name || !ops->get_timeline_name);

	kref_init(&fence->refcount);
	fence->ops = ops;
	INIT_LIST_HEAD(&fence->cb_list);
	fence->lock = lock;
	fence->context = context;
	fence->seqno = seqno;
	fence->flags = 0UL;
	fence->error = 0;

	trace_dma_fence_init(fence);
}
EXPORT_SYMBOL(dma_fence_init);