aboutsummaryrefslogtreecommitdiffstats
blob: 2cde7bffb11e96ab99c3ac2d3d06756c55996aae (plain) (blame)
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
/*
 * Copyright 2014 Advanced Micro Devices, 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 COPYRIGHT HOLDER(S) OR AUTHOR(S) 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.
 *
 */

#ifdef HAVE_CONFIG_H
#include "config.h"
#endif

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <errno.h>
#include <pthread.h>
#include <sched.h>
#include <sys/ioctl.h>
#ifdef HAVE_ALLOCA_H
# include <alloca.h>
#endif

#include "xf86drm.h"
#include "amdgpu_drm.h"
#include "amdgpu_internal.h"

static int amdgpu_cs_unreference_sem(amdgpu_semaphore_handle sem);
static int amdgpu_cs_reset_sem(amdgpu_semaphore_handle sem);

/**
 * Create command submission context
 *
 * \param   dev - \c [in] amdgpu device handle
 * \param   context - \c [out] amdgpu context handle
 *
 * \return  0 on success otherwise POSIX Error code
*/
int amdgpu_cs_ctx_create(amdgpu_device_handle dev,
			 amdgpu_context_handle *context)
{
	struct amdgpu_context *gpu_context;
	union drm_amdgpu_ctx args;
	int i, j, k;
	int r;

	if (!dev || !context)
		return -EINVAL;

	gpu_context = calloc(1, sizeof(struct amdgpu_context));
	if (!gpu_context)
		return -ENOMEM;

	gpu_context->dev = dev;

	r = pthread_mutex_init(&gpu_context->sequence_mutex, NULL);
	if (r)
		goto error;

	/* Create the context */
	memset(&args, 0, sizeof(args));
	args.in.op = AMDGPU_CTX_OP_ALLOC_CTX;
	r = drmCommandWriteRead(dev->fd, DRM_AMDGPU_CTX, &args, sizeof(args));
	if (r)
		goto error;

	gpu_context->id = args.out.alloc.ctx_id;
	for (i = 0; i < AMDGPU_HW_IP_NUM; i++)
		for (j = 0; j < AMDGPU_HW_IP_INSTANCE_MAX_COUNT; j++)
			for (k = 0; k < AMDGPU_CS_MAX_RINGS; k++)
				list_inithead(&gpu_context->sem_list[i][j][k]);
	*context = (amdgpu_context_handle)gpu_context;

	return 0;

error:
	pthread_mutex_destroy(&gpu_context->sequence_mutex);
	free(gpu_context);
	return r;
}

/**
 * Release command submission context
 *
 * \param   dev - \c [in] amdgpu device handle
 * \param   context - \c [in] amdgpu context handle
 *
 * \return  0 on success otherwise POSIX Error code
*/
int amdgpu_cs_ctx_free(amdgpu_context_handle context)
{
	union drm_amdgpu_ctx args;
	int i, j, k;
	int r;

	if (!context)
		return -EINVAL;

	pthread_mutex_destroy(&context->sequence_mutex);

	/* now deal with kernel side */
	memset(&args, 0, sizeof(args));
	args.in.op = AMDGPU_CTX_OP_FREE_CTX;
	args.in.ctx_id = context->id;
	r = drmCommandWriteRead(context->dev->fd, DRM_AMDGPU_CTX,
				&args, sizeof(args));
	for (i = 0; i < AMDGPU_HW_IP_NUM; i++) {
		for (j = 0; j < AMDGPU_HW_IP_INSTANCE_MAX_COUNT; j++) {
			for (k = 0; k < AMDGPU_CS_MAX_RINGS; k++) {
				amdgpu_semaphore_handle sem;
				LIST_FOR_EACH_ENTRY(sem, &context->sem_list[i][j][k], list) {
					list_del(&sem->list);
					amdgpu_cs_reset_sem(sem);
					amdgpu_cs_unreference_sem(sem);
				}
			}
		}
	}
	free(context);

	return r;
}

int amdgpu_cs_query_reset_state(amdgpu_context_handle context,
				uint32_t *state, uint32_t *hangs)
{
	union drm_amdgpu_ctx args;
	int r;

	if (!context)
		return -EINVAL;

	memset(&args, 0, sizeof(args));
	args.in.op = AMDGPU_CTX_OP_QUERY_STATE;
	args.in.ctx_id = context->id;
	r = drmCommandWriteRead(context->dev->fd, DRM_AMDGPU_CTX,
				&args, sizeof(args));
	if (!r) {
		*state = args.out.state.reset_status;
		*hangs = args.out.state.hangs;
	}
	return r;
}

/**
 * Submit command to kernel DRM
 * \param   dev - \c [in]  Device handle
 * \param   context - \c [in]  GPU Context
 * \param   ibs_request - \c [in]  Pointer to submission requests
 * \param   fence - \c [out] return fence for this submission
 *
 * \return  0 on success otherwise POSIX Error code
 * \sa amdgpu_cs_submit()
*/
static int amdgpu_cs_submit_one(amdgpu_context_handle context,
				struct amdgpu_cs_request *ibs_request)
{
	union drm_amdgpu_cs cs;
	uint64_t *chunk_array;
	struct drm_amdgpu_cs_chunk *chunks;
	struct drm_amdgpu_cs_chunk_data *chunk_data;
	struct drm_amdgpu_cs_chunk_dep *dependencies = NULL;
	struct drm_amdgpu_cs_chunk_dep *sem_dependencies = NULL;
	struct list_head *sem_list;
	amdgpu_semaphore_handle sem, tmp;
	uint32_t i, size, sem_count = 0;
	bool user_fence;
	int r = 0;

	if (ibs_request->ip_type >= AMDGPU_HW_IP_NUM)
		return -EINVAL;
	if (ibs_request->ring >= AMDGPU_CS_MAX_RINGS)
		return -EINVAL;
	if (ibs_request->number_of_ibs > AMDGPU_CS_MAX_IBS_PER_SUBMIT)
		return -EINVAL;
	if (ibs_request->number_of_ibs == 0) {
		ibs_request->seq_no = AMDGPU_NULL_SUBMIT_SEQ;
		return 0;
	}
	user_fence = (ibs_request->fence_info.handle != NULL);

	size = ibs_request->number_of_ibs + (user_fence ? 2 : 1) + 1;

	chunk_array = alloca(sizeof(uint64_t) * size);
	chunks = alloca(sizeof(struct drm_amdgpu_cs_chunk) * size);

	size = ibs_request->number_of_ibs + (user_fence ? 1 : 0);

	chunk_data = alloca(sizeof(struct drm_amdgpu_cs_chunk_data) * size);

	memset(&cs, 0, sizeof(cs));
	cs.in.chunks = (uint64_t)(uintptr_t)chunk_array;
	cs.in.ctx_id = context->id;
	if (ibs_request->resources)
		cs.in.bo_list_handle = ibs_request->resources->handle;
	cs.in.num_chunks = ibs_request->number_of_ibs;
	/* IB chunks */
	for (i = 0; i < ibs_request->number_of_ibs; i++) {
		struct amdgpu_cs_ib_info *ib;
		chunk_array[i] = (uint64_t)(uintptr_t)&chunks[i];
		chunks[i].chunk_id = AMDGPU_CHUNK_ID_IB;
		chunks[i].length_dw = sizeof(struct drm_amdgpu_cs_chunk_ib) / 4;
		chunks[i].chunk_data = (uint64_t)(uintptr_t)&chunk_data[i];

		ib = &ibs_request->ibs[i];

		chunk_data[i].ib_data._pad = 0;
		chunk_data[i].ib_data.va_start = ib->ib_mc_address;
		chunk_data[i].ib_data.ib_bytes = ib->size * 4;
		chunk_data[i].ib_data.ip_type = ibs_request->ip_type;
		chunk_data[i].ib_data.ip_instance = ibs_request->ip_instance;
		chunk_data[i].ib_data.ring = ibs_request->ring;
		chunk_data[i].ib_data.flags = ib->flags;
	}

	pthread_mutex_lock(&context->sequence_mutex);

	if (user_fence) {
		i = cs.in.num_chunks++;

		/* fence chunk */
		chunk_array[i] = (uint64_t)(uintptr_t)&chunks[i];
		chunks[i].chunk_id = AMDGPU_CHUNK_ID_FENCE;
		chunks[i].length_dw = sizeof(struct drm_amdgpu_cs_chunk_fence) / 4;
		chunks[i].chunk_data = (uint64_t)(uintptr_t)&chunk_data[i];

		/* fence bo handle */
		chunk_data[i].fence_data.handle = ibs_request->fence_info.handle->handle;
		/* offset */
		chunk_data[i].fence_data.offset = 
			ibs_request->fence_info.offset * sizeof(uint64_t);
	}

	if (ibs_request->number_of_dependencies) {
		dependencies = malloc(sizeof(struct drm_amdgpu_cs_chunk_dep) *
			ibs_request->number_of_dependencies);
		if (!dependencies) {
			r = -ENOMEM;
			goto error_unlock;
		}

		for (i = 0; i < ibs_request->number_of_dependencies; ++i) {
			struct amdgpu_cs_fence *info = &ibs_request->dependencies[i];
			struct drm_amdgpu_cs_chunk_dep *dep = &dependencies[i];
			dep->ip_type = info->ip_type;
			dep->ip_instance = info->ip_instance;
			dep->ring = info->ring;
			dep->ctx_id = info->context->id;
			dep->handle = info->fence;
		}

		i = cs.in.num_chunks++;

		/* dependencies chunk */
		chunk_array[i] = (uint64_t)(uintptr_t)&chunks[i];
		chunks[i].chunk_id = AMDGPU_CHUNK_ID_DEPENDENCIES;
		chunks[i].length_dw = sizeof(struct drm_amdgpu_cs_chunk_dep) / 4
			* ibs_request->number_of_dependencies;
		chunks[i].chunk_data = (uint64_t)(uintptr_t)dependencies;
	}

	sem_list = &context->sem_list[ibs_request->ip_type][ibs_request->ip_instance][ibs_request->ring];
	LIST_FOR_EACH_ENTRY(sem, sem_list, list)
		sem_count++;
	if (sem_count) {
		sem_dependencies = malloc(sizeof(struct drm_amdgpu_cs_chunk_dep) * sem_count);
		if (!sem_dependencies) {
			r = -ENOMEM;
			goto error_unlock;
		}
		sem_count = 0;
		LIST_FOR_EACH_ENTRY_SAFE(sem, tmp, sem_list, list) {
			struct amdgpu_cs_fence *info = &sem->signal_fence;
			struct drm_amdgpu_cs_chunk_dep *dep = &sem_dependencies[sem_count++];
			dep->ip_type = info->ip_type;
			dep->ip_instance = info->ip_instance;
			dep->ring = info->ring;
			dep->ctx_id = info->context->id;
			dep->handle = info->fence;

			list_del(&sem->list);
			amdgpu_cs_reset_sem(sem);
			amdgpu_cs_unreference_sem(sem);
		}
		i = cs.in.num_chunks++;

		/* dependencies chunk */
		chunk_array[i] = (uint64_t)(uintptr_t)&chunks[i];
		chunks[i].chunk_id = AMDGPU_CHUNK_ID_DEPENDENCIES;
		chunks[i].length_dw = sizeof(struct drm_amdgpu_cs_chunk_dep) / 4 * sem_count;
		chunks[i].chunk_data = (uint64_t)(uintptr_t)sem_dependencies;
	}

	r = drmCommandWriteRead(context->dev->fd, DRM_AMDGPU_CS,
				&cs, sizeof(cs));
	if (r)
		goto error_unlock;

	ibs_request->seq_no = cs.out.handle;
	context->last_seq[ibs_request->ip_type][ibs_request->ip_instance][ibs_request->ring] = ibs_request->seq_no;
error_unlock:
	pthread_mutex_unlock(&context->sequence_mutex);
	free(dependencies);
	free(sem_dependencies);
	return r;
}

int amdgpu_cs_submit(amdgpu_context_handle context,
		     uint64_t flags,
		     struct amdgpu_cs_request *ibs_request,
		     uint32_t number_of_requests)
{
	uint32_t i;
	int r;

	if (!context || !ibs_request)
		return -EINVAL;

	r = 0;
	for (i = 0; i < number_of_requests; i++) {
		r = amdgpu_cs_submit_one(context, ibs_request);
		if (r)
			break;
		ibs_request++;
	}

	return r;
}

/**
 * Calculate absolute timeout.
 *
 * \param   timeout - \c [in] timeout in nanoseconds.
 *
 * \return  absolute timeout in nanoseconds
*/
drm_private uint64_t amdgpu_cs_calculate_timeout(uint64_t timeout)
{
	int r;

	if (timeout != AMDGPU_TIMEOUT_INFINITE) {
		struct timespec current;
		uint64_t current_ns;
		r = clock_gettime(CLOCK_MONOTONIC, &current);
		if (r) {
			fprintf(stderr, "clock_gettime() returned error (%d)!", errno);
			return AMDGPU_TIMEOUT_INFINITE;
		}

		current_ns = ((uint64_t)current.tv_sec) * 1000000000ull;
		current_ns += current.tv_nsec;
		timeout += current_ns;
		if (timeout < current_ns)
			timeout = AMDGPU_TIMEOUT_INFINITE;
	}
	return timeout;
}

static int amdgpu_ioctl_wait_cs(amdgpu_context_handle context,
				unsigned ip,
				unsigned ip_instance,
				uint32_t ring,
				uint64_t handle,
				uint64_t timeout_ns,
				uint64_t flags,
				bool *busy)
{
	amdgpu_device_handle dev = context->dev;
	union drm_amdgpu_wait_cs args;
	int r;

	memset(&args, 0, sizeof(args));
	args.in.handle = handle;
	args.in.ip_type = ip;
	args.in.ip_instance = ip_instance;
	args.in.ring = ring;
	args.in.ctx_id = context->id;

	if (flags & AMDGPU_QUERY_FENCE_TIMEOUT_IS_ABSOLUTE)
		args.in.timeout = timeout_ns;
	else
		args.in.timeout = amdgpu_cs_calculate_timeout(timeout_ns);

	r = drmIoctl(dev->fd, DRM_IOCTL_AMDGPU_WAIT_CS, &args);
	if (r)
		return -errno;

	*busy = args.out.status;
	return 0;
}

int amdgpu_cs_query_fence_status(struct amdgpu_cs_fence *fence,
				 uint64_t timeout_ns,
				 uint64_t flags,
				 uint32_t *expired)
{
	bool busy = true;
	int r;

	if (!fence || !expired || !fence->context)
		return -EINVAL;
	if (fence->ip_type >= AMDGPU_HW_IP_NUM)
		return -EINVAL;
	if (fence->ring >= AMDGPU_CS_MAX_RINGS)
		return -EINVAL;
	if (fence->fence == AMDGPU_NULL_SUBMIT_SEQ) {
		*expired = true;
		return 0;
	}

	*expired = false;

	r = amdgpu_ioctl_wait_cs(fence->context, fence->ip_type,
				fence->ip_instance, fence->ring,
			       	fence->fence, timeout_ns, flags, &busy);

	if (!r && !busy)
		*expired = true;

	return r;
}

static int amdgpu_ioctl_wait_fences(struct amdgpu_cs_fence *fences,
				    uint32_t fence_count,
				    bool wait_all,
				    uint64_t timeout_ns,
				    uint32_t *status,
				    uint32_t *first)
{
	struct drm_amdgpu_fence *drm_fences;
	amdgpu_device_handle dev = fences[0].context->dev;
	union drm_amdgpu_wait_fences args;
	int r;
	uint32_t i;

	drm_fences = alloca(sizeof(struct drm_amdgpu_fence) * fence_count);
	for (i = 0; i < fence_count; i++) {
		drm_fences[i].ctx_id = fences[i].context->id;
		drm_fences[i].ip_type = fences[i].ip_type;
		drm_fences[i].ip_instance = fences[i].ip_instance;
		drm_fences[i].ring = fences[i].ring;
		drm_fences[i].seq_no = fences[i].fence;
	}

	memset(&args, 0, sizeof(args));
	args.in.fences = (uint64_t)(uintptr_t)drm_fences;
	args.in.fence_count = fence_count;
	args.in.wait_all = wait_all;
	args.in.timeout_ns = amdgpu_cs_calculate_timeout(timeout_ns);

	r = drmIoctl(dev->fd, DRM_IOCTL_AMDGPU_WAIT_FENCES, &args);
	if (r)
		return -errno;

	*status = args.out.status;

	if (first)
		*first = args.out.first_signaled;

	return 0;
}

int amdgpu_cs_wait_fences(struct amdgpu_cs_fence *fences,
			  uint32_t fence_count,
			  bool wait_all,
			  uint64_t timeout_ns,
			  uint32_t *status,
			  uint32_t *first)
{
	uint32_t i;

	/* Sanity check */
	if (!fences || !status || !fence_count)
		return -EINVAL;

	for (i = 0; i < fence_count; i++) {
		if (NULL == fences[i].context)
			return -EINVAL;
		if (fences[i].ip_type >= AMDGPU_HW_IP_NUM)
			return -EINVAL;
		if (fences[i].ring >= AMDGPU_CS_MAX_RINGS)
			return -EINVAL;
	}

	*status = 0;

	return amdgpu_ioctl_wait_fences(fences, fence_count, wait_all,
					timeout_ns, status, first);
}

int amdgpu_cs_create_semaphore(amdgpu_semaphore_handle *sem)
{
	struct amdgpu_semaphore *gpu_semaphore;

	if (!sem)
		return -EINVAL;

	gpu_semaphore = calloc(1, sizeof(struct amdgpu_semaphore));
	if (!gpu_semaphore)
		return -ENOMEM;

	atomic_set(&gpu_semaphore->refcount, 1);
	*sem = gpu_semaphore;

	return 0;
}

int amdgpu_cs_signal_semaphore(amdgpu_context_handle ctx,
			       uint32_t ip_type,
			       uint32_t ip_instance,
			       uint32_t ring,
			       amdgpu_semaphore_handle sem)
{
	if (!ctx || !sem)
		return -EINVAL;
	if (ip_type >= AMDGPU_HW_IP_NUM)
		return -EINVAL;
	if (ring >= AMDGPU_CS_MAX_RINGS)
		return -EINVAL;
	/* sem has been signaled */
	if (sem->signal_fence.context)
		return -EINVAL;
	pthread_mutex_lock(&ctx->sequence_mutex);
	sem->signal_fence.context = ctx;
	sem->signal_fence.ip_type = ip_type;
	sem->signal_fence.ip_instance = ip_instance;
	sem->signal_fence.ring = ring;
	sem->signal_fence.fence = ctx->last_seq[ip_type][ip_instance][ring];
	update_references(NULL, &sem->refcount);
	pthread_mutex_unlock(&ctx->sequence_mutex);
	return 0;
}

int amdgpu_cs_wait_semaphore(amdgpu_context_handle ctx,
			     uint32_t ip_type,
			     uint32_t ip_instance,
			     uint32_t ring,
			     amdgpu_semaphore_handle sem)
{
	if (!ctx || !sem)
		return -EINVAL;
	if (ip_type >= AMDGPU_HW_IP_NUM)
		return -EINVAL;
	if (ring >= AMDGPU_CS_MAX_RINGS)
		return -EINVAL;
	/* must signal first */
	if (!sem->signal_fence.context)
		return -EINVAL;

	pthread_mutex_lock(&ctx->sequence_mutex);
	list_add(&sem->list, &ctx->sem_list[ip_type][ip_instance][ring]);
	pthread_mutex_unlock(&ctx->sequence_mutex);
	return 0;
}

static int amdgpu_cs_reset_sem(amdgpu_semaphore_handle sem)
{
	if (!sem || !sem->signal_fence.context)
		return -EINVAL;

	sem->signal_fence.context = NULL;;
	sem->signal_fence.ip_type = 0;
	sem->signal_fence.ip_instance = 0;
	sem->signal_fence.ring = 0;
	sem->signal_fence.fence = 0;

	return 0;
}

static int amdgpu_cs_unreference_sem(amdgpu_semaphore_handle sem)
{
	if (!sem)
		return -EINVAL;

	if (update_references(&sem->refcount, NULL))
		free(sem);
	return 0;
}

int amdgpu_cs_destroy_semaphore(amdgpu_semaphore_handle sem)
{
	return amdgpu_cs_unreference_sem(sem);
}

int amdgpu_cs_create_syncobj(amdgpu_device_handle dev,
			     uint32_t *handle)
{
	if (NULL == dev)
		return -EINVAL;

	return drmSyncobjCreate(dev->fd, 0, handle);
}

int amdgpu_cs_destroy_syncobj(amdgpu_device_handle dev,
			      uint32_t handle)
{
	if (NULL == dev)
		return -EINVAL;

	return drmSyncobjDestroy(dev->fd, handle);
}

int amdgpu_cs_syncobj_wait(amdgpu_device_handle dev,
			   uint32_t *handles, unsigned num_handles,
			   int64_t timeout_nsec, unsigned flags,
			   uint32_t *first_signaled)
{
	if (NULL == dev)
		return -EINVAL;

	return drmSyncobjWait(dev->fd, handles, num_handles, timeout_nsec,
			      flags, first_signaled);
}

int amdgpu_cs_export_syncobj(amdgpu_device_handle dev,
			     uint32_t handle,
			     int *shared_fd)
{
	if (NULL == dev)
		return -EINVAL;

	return drmSyncobjHandleToFD(dev->fd, handle, shared_fd);
}

int amdgpu_cs_import_syncobj(amdgpu_device_handle dev,
			     int shared_fd,
			     uint32_t *handle)
{
	if (NULL == dev)
		return -EINVAL;

	return drmSyncobjFDToHandle(dev->fd, shared_fd, handle);
}

int amdgpu_cs_syncobj_export_sync_file(amdgpu_device_handle dev,
				       uint32_t syncobj,
				       int *sync_file_fd)
{
	if (NULL == dev)
		return -EINVAL;

	return drmSyncobjExportSyncFile(dev->fd, syncobj, sync_file_fd);
}

int amdgpu_cs_syncobj_import_sync_file(amdgpu_device_handle dev,
				       uint32_t syncobj,
				       int sync_file_fd)
{
	if (NULL == dev)
		return -EINVAL;

	return drmSyncobjImportSyncFile(dev->fd, syncobj, sync_file_fd);
}

int amdgpu_cs_submit_raw(amdgpu_device_handle dev,
			 amdgpu_context_handle context,
			 amdgpu_bo_list_handle bo_list_handle,
			 int num_chunks,
			 struct drm_amdgpu_cs_chunk *chunks,
			 uint64_t *seq_no)
{
	union drm_amdgpu_cs cs = {0};
	uint64_t *chunk_array;
	int i, r;
	if (num_chunks == 0)
		return -EINVAL;

	chunk_array = alloca(sizeof(uint64_t) * num_chunks);
	for (i = 0; i < num_chunks; i++)
		chunk_array[i] = (uint64_t)(uintptr_t)&chunks[i];
	cs.in.chunks = (uint64_t)(uintptr_t)chunk_array;
	cs.in.ctx_id = context->id;
	cs.in.bo_list_handle = bo_list_handle ? bo_list_handle->handle : 0;
	cs.in.num_chunks = num_chunks;
	r = drmCommandWriteRead(dev->fd, DRM_AMDGPU_CS,
				&cs, sizeof(cs));
	if (r)
		return r;

	if (seq_no)
		*seq_no = cs.out.handle;
	return 0;
}

void amdgpu_cs_chunk_fence_info_to_data(struct amdgpu_cs_fence_info *fence_info,
					struct drm_amdgpu_cs_chunk_data *data)
{
	data->fence_data.handle = fence_info->handle->handle;
	data->fence_data.offset = fence_info->offset * sizeof(uint64_t);
}

void amdgpu_cs_chunk_fence_to_dep(struct amdgpu_cs_fence *fence,
				  struct drm_amdgpu_cs_chunk_dep *dep)
{
	dep->ip_type = fence->ip_type;
	dep->ip_instance = fence->ip_instance;
	dep->ring = fence->ring;
	dep->ctx_id = fence->context->id;
	dep->handle = fence->fence;
}