aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/radeon/radeon_ring.c
blob: fc209c8b8666e86cb0168ce85760b7fb515aa6f7 (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
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
/*
 * Copyright 2008 Advanced Micro Devices, Inc.
 * Copyright 2008 Red Hat Inc.
 * Copyright 2009 Jerome Glisse.
 *
 * 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.
 *
 * Authors: Dave Airlie
 *          Alex Deucher
 *          Jerome Glisse
 *          Christian König
 */
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <drm/drmP.h>
#include <drm/radeon_drm.h>
#include "radeon_reg.h"
#include "radeon.h"
#include "atom.h"

/*
 * IB
 * IBs (Indirect Buffers) and areas of GPU accessible memory where
 * commands are stored.  You can put a pointer to the IB in the
 * command ring and the hw will fetch the commands from the IB
 * and execute them.  Generally userspace acceleration drivers
 * produce command buffers which are send to the kernel and
 * put in IBs for execution by the requested ring.
 */
int radeon_debugfs_sa_init(struct radeon_device *rdev);

/**
 * radeon_ib_get - request an IB (Indirect Buffer)
 *
 * @rdev: radeon_device pointer
 * @ring: ring index the IB is associated with
 * @ib: IB object returned
 * @size: requested IB size
 *
 * Request an IB (all asics).  IBs are allocated using the
 * suballocator.
 * Returns 0 on success, error on failure.
 */
int radeon_ib_get(struct radeon_device *rdev, int ring,
		  struct radeon_ib *ib, unsigned size)
{
	int i, r;

	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, &ib->sa_bo, size, 256, true);
	if (r) {
		dev_err(rdev->dev, "failed to get a new IB (%d)\n", r);
		return r;
	}

	r = radeon_semaphore_create(rdev, &ib->semaphore);
	if (r) {
		return r;
	}

	ib->ring = ring;
	ib->fence = NULL;
	ib->ptr = radeon_sa_bo_cpu_addr(ib->sa_bo);
	ib->gpu_addr = radeon_sa_bo_gpu_addr(ib->sa_bo);
	ib->vm_id = 0;
	ib->is_const_ib = false;
	for (i = 0; i < RADEON_NUM_RINGS; ++i)
		ib->sync_to[i] = NULL;

	return 0;
}

/**
 * radeon_ib_free - free an IB (Indirect Buffer)
 *
 * @rdev: radeon_device pointer
 * @ib: IB object to free
 *
 * Free an IB (all asics).
 */
void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib)
{
	radeon_semaphore_free(rdev, &ib->semaphore, ib->fence);
	radeon_sa_bo_free(rdev, &ib->sa_bo, ib->fence);
	radeon_fence_unref(&ib->fence);
}

/**
 * radeon_ib_schedule - schedule an IB (Indirect Buffer) on the ring
 *
 * @rdev: radeon_device pointer
 * @ib: IB object to schedule
 * @const_ib: Const IB to schedule (SI only)
 *
 * Schedule an IB on the associated ring (all asics).
 * Returns 0 on success, error on failure.
 *
 * On SI, there are two parallel engines fed from the primary ring,
 * the CE (Constant Engine) and the DE (Drawing Engine).  Since
 * resource descriptors have moved to memory, the CE allows you to
 * prime the caches while the DE is updating register state so that
 * the resource descriptors will be already in cache when the draw is
 * processed.  To accomplish this, the userspace driver submits two
 * IBs, one for the CE and one for the DE.  If there is a CE IB (called
 * a CONST_IB), it will be put on the ring prior to the DE IB.  Prior
 * to SI there was just a DE IB.
 */
int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
		       struct radeon_ib *const_ib)
{
	struct radeon_ring *ring = &rdev->ring[ib->ring];
	bool need_sync = false;
	int i, r = 0;

	if (!ib->length_dw || !ring->ready) {
		/* TODO: Nothings in the ib we should report. */
		dev_err(rdev->dev, "couldn't schedule ib\n");
		return -EINVAL;
	}

	/* 64 dwords should be enough for fence too */
	r = radeon_ring_lock(rdev, ring, 64 + RADEON_NUM_RINGS * 8);
	if (r) {
		dev_err(rdev->dev, "scheduling IB failed (%d).\n", r);
		return r;
	}
	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
		struct radeon_fence *fence = ib->sync_to[i];
		if (radeon_fence_need_sync(fence, ib->ring)) {
			need_sync = true;
			radeon_semaphore_sync_rings(rdev, ib->semaphore,
						    fence->ring, ib->ring);
			radeon_fence_note_sync(fence, ib->ring);
		}
	}
	/* immediately free semaphore when we don't need to sync */
	if (!need_sync) {
		radeon_semaphore_free(rdev, &ib->semaphore, NULL);
	}
	if (const_ib) {
		radeon_ring_ib_execute(rdev, const_ib->ring, const_ib);
		radeon_semaphore_free(rdev, &const_ib->semaphore, NULL);
	}
	radeon_ring_ib_execute(rdev, ib->ring, ib);
	r = radeon_fence_emit(rdev, &ib->fence, ib->ring);
	if (r) {
		dev_err(rdev->dev, "failed to emit fence for new IB (%d)\n", r);
		radeon_ring_unlock_undo(rdev, ring);
		return r;
	}
	if (const_ib) {
		const_ib->fence = radeon_fence_ref(ib->fence);
	}
	radeon_ring_unlock_commit(rdev, ring);
	return 0;
}

/**
 * radeon_ib_pool_init - Init the IB (Indirect Buffer) pool
 *
 * @rdev: radeon_device pointer
 *
 * Initialize the suballocator to manage a pool of memory
 * for use as IBs (all asics).
 * Returns 0 on success, error on failure.
 */
int radeon_ib_pool_init(struct radeon_device *rdev)
{
	int r;

	if (rdev->ib_pool_ready) {
		return 0;
	}
	r = radeon_sa_bo_manager_init(rdev, &rdev->ring_tmp_bo,
				      RADEON_IB_POOL_SIZE*64*1024,
				      RADEON_GEM_DOMAIN_GTT);
	if (r) {
		return r;
	}

	r = radeon_sa_bo_manager_start(rdev, &rdev->ring_tmp_bo);
	if (r) {
		return r;
	}

	rdev->ib_pool_ready = true;
	if (radeon_debugfs_sa_init(rdev)) {
		dev_err(rdev->dev, "failed to register debugfs file for SA\n");
	}
	return 0;
}

/**
 * radeon_ib_pool_fini - Free the IB (Indirect Buffer) pool
 *
 * @rdev: radeon_device pointer
 *
 * Tear down the suballocator managing the pool of memory
 * for use as IBs (all asics).
 */
void radeon_ib_pool_fini(struct radeon_device *rdev)
{
	if (rdev->ib_pool_ready) {
		radeon_sa_bo_manager_suspend(rdev, &rdev->ring_tmp_bo);
		radeon_sa_bo_manager_fini(rdev, &rdev->ring_tmp_bo);
		rdev->ib_pool_ready = false;
	}
}

/**
 * radeon_ib_ring_tests - test IBs on the rings
 *
 * @rdev: radeon_device pointer
 *
 * Test an IB (Indirect Buffer) on each ring.
 * If the test fails, disable the ring.
 * Returns 0 on success, error if the primary GFX ring
 * IB test fails.
 */
int radeon_ib_ring_tests(struct radeon_device *rdev)
{
	unsigned i;
	int r;

	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
		struct radeon_ring *ring = &rdev->ring[i];

		if (!ring->ready)
			continue;

		r = radeon_ib_test(rdev, i, ring);
		if (r) {
			ring->ready = false;

			if (i == RADEON_RING_TYPE_GFX_INDEX) {
				/* oh, oh, that's really bad */
				DRM_ERROR("radeon: failed testing IB on GFX ring (%d).\n", r);
		                rdev->accel_working = false;
				return r;

			} else {
				/* still not good, but we can live with it */
				DRM_ERROR("radeon: failed testing IB on ring %d (%d).\n", i, r);
			}
		}
	}
	return 0;
}

/*
 * Rings
 * Most engines on the GPU are fed via ring buffers.  Ring
 * buffers are areas of GPU accessible memory that the host
 * writes commands into and the GPU reads commands out of.
 * There is a rptr (read pointer) that determines where the
 * GPU is currently reading, and a wptr (write pointer)
 * which determines where the host has written.  When the
 * pointers are equal, the ring is idle.  When the host
 * writes commands to the ring buffer, it increments the
 * wptr.  The GPU then starts fetching commands and executes
 * them until the pointers are equal again.
 */
int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring);

/**
 * radeon_ring_write - write a value to the ring
 *
 * @ring: radeon_ring structure holding ring information
 * @v: dword (dw) value to write
 *
 * Write a value to the requested ring buffer (all asics).
 */
void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
{
#if DRM_DEBUG_CODE
	if (ring->count_dw <= 0) {
		DRM_ERROR("radeon: writting more dword to ring than expected !\n");
	}
#endif
	ring->ring[ring->wptr++] = v;
	ring->wptr &= ring->ptr_mask;
	ring->count_dw--;
	ring->ring_free_dw--;
}

/**
 * radeon_ring_supports_scratch_reg - check if the ring supports
 * writing to scratch registers
 *
 * @rdev: radeon_device pointer
 * @ring: radeon_ring structure holding ring information
 *
 * Check if a specific ring supports writing to scratch registers (all asics).
 * Returns true if the ring supports writing to scratch regs, false if not.
 */
bool radeon_ring_supports_scratch_reg(struct radeon_device *rdev,
				      struct radeon_ring *ring)
{
	switch (ring->idx) {
	case RADEON_RING_TYPE_GFX_INDEX:
	case CAYMAN_RING_TYPE_CP1_INDEX:
	case CAYMAN_RING_TYPE_CP2_INDEX:
		return true;
	default:
		return false;
	}
}

/**
 * radeon_ring_free_size - update the free size
 *
 * @rdev: radeon_device pointer
 * @ring: radeon_ring structure holding ring information
 *
 * Update the free dw slots in the ring buffer (all asics).
 */
void radeon_ring_free_size(struct radeon_device *rdev, struct radeon_ring *ring)
{
	u32 rptr;

	if (rdev->wb.enabled)
		rptr = le32_to_cpu(rdev->wb.wb[ring->rptr_offs/4]);
	else
		rptr = RREG32(ring->rptr_reg);
	ring->rptr = (rptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
	/* This works because ring_size is a power of 2 */
	ring->ring_free_dw = (ring->rptr + (ring->ring_size / 4));
	ring->ring_free_dw -= ring->wptr;
	ring->ring_free_dw &= ring->ptr_mask;
	if (!ring->ring_free_dw) {
		ring->ring_free_dw = ring->ring_size / 4;
	}
}

/**
 * radeon_ring_alloc - allocate space on the ring buffer
 *
 * @rdev: radeon_device pointer
 * @ring: radeon_ring structure holding ring information
 * @ndw: number of dwords to allocate in the ring buffer
 *
 * Allocate @ndw dwords in the ring buffer (all asics).
 * Returns 0 on success, error on failure.
 */
int radeon_ring_alloc(struct radeon_device *rdev, struct radeon_ring *ring, unsigned ndw)
{
	int r;

	/* Align requested size with padding so unlock_commit can
	 * pad safely */
	ndw = (ndw + ring->align_mask) & ~ring->align_mask;
	while (ndw > (ring->ring_free_dw - 1)) {
		radeon_ring_free_size(rdev, ring);
		if (ndw < ring->ring_free_dw) {
			break;
		}
		r = radeon_fence_wait_next_locked(rdev, ring->idx);
		if (r)
			return r;
	}
	ring->count_dw = ndw;
	ring->wptr_old = ring->wptr;
	return 0;
}

/**
 * radeon_ring_lock - lock the ring and allocate space on it
 *
 * @rdev: radeon_device pointer
 * @ring: radeon_ring structure holding ring information
 * @ndw: number of dwords to allocate in the ring buffer
 *
 * Lock the ring and allocate @ndw dwords in the ring buffer
 * (all asics).
 * Returns 0 on success, error on failure.
 */
int radeon_ring_lock(struct radeon_device *rdev, struct radeon_ring *ring, unsigned ndw)
{
	int r;

	mutex_lock(&rdev->ring_lock);
	r = radeon_ring_alloc(rdev, ring, ndw);
	if (r) {
		mutex_unlock(&rdev->ring_lock);
		return r;
	}
	return 0;
}

/**
 * radeon_ring_commit - tell the GPU to execute the new
 * commands on the ring buffer
 *
 * @rdev: radeon_device pointer
 * @ring: radeon_ring structure holding ring information
 *
 * Update the wptr (write pointer) to tell the GPU to
 * execute new commands on the ring buffer (all asics).
 */
void radeon_ring_commit(struct radeon_device *rdev, struct radeon_ring *ring)
{
	/* We pad to match fetch size */
	while (ring->wptr & ring->align_mask) {
		radeon_ring_write(ring, ring->nop);
	}
	DRM_MEMORYBARRIER();
	WREG32(ring->wptr_reg, (ring->wptr << ring->ptr_reg_shift) & ring->ptr_reg_mask);
	(void)RREG32(ring->wptr_reg);
}

/**
 * radeon_ring_unlock_commit - tell the GPU to execute the new
 * commands on the ring buffer and unlock it
 *
 * @rdev: radeon_device pointer
 * @ring: radeon_ring structure holding ring information
 *
 * Call radeon_ring_commit() then unlock the ring (all asics).
 */
void radeon_ring_unlock_commit(struct radeon_device *rdev, struct radeon_ring *ring)
{
	radeon_ring_commit(rdev, ring);
	mutex_unlock(&rdev->ring_lock);
}

/**
 * radeon_ring_undo - reset the wptr
 *
 * @ring: radeon_ring structure holding ring information
 *
 * Reset the driver's copy of the wtpr (all asics).
 */
void radeon_ring_undo(struct radeon_ring *ring)
{
	ring->wptr = ring->wptr_old;
}

/**
 * radeon_ring_unlock_undo - reset the wptr and unlock the ring
 *
 * @ring: radeon_ring structure holding ring information
 *
 * Call radeon_ring_undo() then unlock the ring (all asics).
 */
void radeon_ring_unlock_undo(struct radeon_device *rdev, struct radeon_ring *ring)
{
	radeon_ring_undo(ring);
	mutex_unlock(&rdev->ring_lock);
}

/**
 * radeon_ring_force_activity - add some nop packets to the ring
 *
 * @rdev: radeon_device pointer
 * @ring: radeon_ring structure holding ring information
 *
 * Add some nop packets to the ring to force activity (all asics).
 * Used for lockup detection to see if the rptr is advancing.
 */
void radeon_ring_force_activity(struct radeon_device *rdev, struct radeon_ring *ring)
{
	int r;

	radeon_ring_free_size(rdev, ring);
	if (ring->rptr == ring->wptr) {
		r = radeon_ring_alloc(rdev, ring, 1);
		if (!r) {
			radeon_ring_write(ring, ring->nop);
			radeon_ring_commit(rdev, ring);
		}
	}
}

/**
 * radeon_ring_force_activity - update lockup variables
 *
 * @ring: radeon_ring structure holding ring information
 *
 * Update the last rptr value and timestamp (all asics).
 */
void radeon_ring_lockup_update(struct radeon_ring *ring)
{
	ring->last_rptr = ring->rptr;
	ring->last_activity = jiffies;
}

/**
 * radeon_ring_test_lockup() - check if ring is lockedup by recording information
 * @rdev:       radeon device structure
 * @ring:       radeon_ring structure holding ring information
 *
 * We don't need to initialize the lockup tracking information as we will either
 * have CP rptr to a different value of jiffies wrap around which will force
 * initialization of the lockup tracking informations.
 *
 * A possible false positivie is if we get call after while and last_cp_rptr ==
 * the current CP rptr, even if it's unlikely it might happen. To avoid this
 * if the elapsed time since last call is bigger than 2 second than we return
 * false and update the tracking information. Due to this the caller must call
 * radeon_ring_test_lockup several time in less than 2sec for lockup to be reported
 * the fencing code should be cautious about that.
 *
 * Caller should write to the ring to force CP to do something so we don't get
 * false positive when CP is just gived nothing to do.
 *
 **/
bool radeon_ring_test_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
{
	unsigned long cjiffies, elapsed;
	uint32_t rptr;

	cjiffies = jiffies;
	if (!time_after(cjiffies, ring->last_activity)) {
		/* likely a wrap around */
		radeon_ring_lockup_update(ring);
		return false;
	}
	rptr = RREG32(ring->rptr_reg);
	ring->rptr = (rptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
	if (ring->rptr != ring->last_rptr) {
		/* CP is still working no lockup */
		radeon_ring_lockup_update(ring);
		return false;
	}
	elapsed = jiffies_to_msecs(cjiffies - ring->last_activity);
	if (radeon_lockup_timeout && elapsed >= radeon_lockup_timeout) {
		dev_err(rdev->dev, "GPU lockup CP stall for more than %lumsec\n", elapsed);
		return true;
	}
	/* give a chance to the GPU ... */
	return false;
}

/**
 * radeon_ring_backup - Back up the content of a ring
 *
 * @rdev: radeon_device pointer
 * @ring: the ring we want to back up
 *
 * Saves all unprocessed commits from a ring, returns the number of dwords saved.
 */
unsigned radeon_ring_backup(struct radeon_device *rdev, struct radeon_ring *ring,
			    uint32_t **data)
{
	unsigned size, ptr, i;

	/* just in case lock the ring */
	mutex_lock(&rdev->ring_lock);
	*data = NULL;

	if (ring->ring_obj == NULL) {
		mutex_unlock(&rdev->ring_lock);
		return 0;
	}

	/* it doesn't make sense to save anything if all fences are signaled */
	if (!radeon_fence_count_emitted(rdev, ring->idx)) {
		mutex_unlock(&rdev->ring_lock);
		return 0;
	}

	/* calculate the number of dw on the ring */
	if (ring->rptr_save_reg)
		ptr = RREG32(ring->rptr_save_reg);
	else if (rdev->wb.enabled)
		ptr = le32_to_cpu(*ring->next_rptr_cpu_addr);
	else {
		/* no way to read back the next rptr */
		mutex_unlock(&rdev->ring_lock);
		return 0;
	}

	size = ring->wptr + (ring->ring_size / 4);
	size -= ptr;
	size &= ring->ptr_mask;
	if (size == 0) {
		mutex_unlock(&rdev->ring_lock);
		return 0;
	}

	/* and then save the content of the ring */
	*data = kmalloc_array(size, sizeof(uint32_t), GFP_KERNEL);
	if (!*data) {
		mutex_unlock(&rdev->ring_lock);
		return 0;
	}
	for (i = 0; i < size; ++i) {
		(*data)[i] = ring->ring[ptr++];
		ptr &= ring->ptr_mask;
	}

	mutex_unlock(&rdev->ring_lock);
	return size;
}

/**
 * radeon_ring_restore - append saved commands to the ring again
 *
 * @rdev: radeon_device pointer
 * @ring: ring to append commands to
 * @size: number of dwords we want to write
 * @data: saved commands
 *
 * Allocates space on the ring and restore the previously saved commands.
 */
int radeon_ring_restore(struct radeon_device *rdev, struct radeon_ring *ring,
			unsigned size, uint32_t *data)
{
	int i, r;

	if (!size || !data)
		return 0;

	/* restore the saved ring content */
	r = radeon_ring_lock(rdev, ring, size);
	if (r)
		return r;

	for (i = 0; i < size; ++i) {
		radeon_ring_write(ring, data[i]);
	}

	radeon_ring_unlock_commit(rdev, ring);
	kfree(data);
	return 0;
}

/**
 * radeon_ring_init - init driver ring struct.
 *
 * @rdev: radeon_device pointer
 * @ring: radeon_ring structure holding ring information
 * @ring_size: size of the ring
 * @rptr_offs: offset of the rptr writeback location in the WB buffer
 * @rptr_reg: MMIO offset of the rptr register
 * @wptr_reg: MMIO offset of the wptr register
 * @ptr_reg_shift: bit offset of the rptr/wptr values
 * @ptr_reg_mask: bit mask of the rptr/wptr values
 * @nop: nop packet for this ring
 *
 * Initialize the driver information for the selected ring (all asics).
 * Returns 0 on success, error on failure.
 */
int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsigned ring_size,
		     unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg,
		     u32 ptr_reg_shift, u32 ptr_reg_mask, u32 nop)
{
	int r;

	ring->ring_size = ring_size;
	ring->rptr_offs = rptr_offs;
	ring->rptr_reg = rptr_reg;
	ring->wptr_reg = wptr_reg;
	ring->ptr_reg_shift = ptr_reg_shift;
	ring->ptr_reg_mask = ptr_reg_mask;
	ring->nop = nop;
	/* Allocate ring buffer */
	if (ring->ring_obj == NULL) {
		r = radeon_bo_create(rdev, ring->ring_size, PAGE_SIZE, true,
				     RADEON_GEM_DOMAIN_GTT,
				     NULL, &ring->ring_obj);
		if (r) {
			dev_err(rdev->dev, "(%d) ring create failed\n", r);
			return r;
		}
		r = radeon_bo_reserve(ring->ring_obj, false);
		if (unlikely(r != 0))
			return r;
		r = radeon_bo_pin(ring->ring_obj, RADEON_GEM_DOMAIN_GTT,
					&ring->gpu_addr);
		if (r) {
			radeon_bo_unreserve(ring->ring_obj);
			dev_err(rdev->dev, "(%d) ring pin failed\n", r);
			return r;
		}
		r = radeon_bo_kmap(ring->ring_obj,
				       (void **)&ring->ring);
		radeon_bo_unreserve(ring->ring_obj);
		if (r) {
			dev_err(rdev->dev, "(%d) ring map failed\n", r);
			return r;
		}
	}
	ring->ptr_mask = (ring->ring_size / 4) - 1;
	ring->ring_free_dw = ring->ring_size / 4;
	if (rdev->wb.enabled) {
		u32 index = RADEON_WB_RING0_NEXT_RPTR + (ring->idx * 4);
		ring->next_rptr_gpu_addr = rdev->wb.gpu_addr + index;
		ring->next_rptr_cpu_addr = &rdev->wb.wb[index/4];
	}
	if (radeon_debugfs_ring_init(rdev, ring)) {
		DRM_ERROR("Failed to register debugfs file for rings !\n");
	}
	radeon_ring_lockup_update(ring);
	return 0;
}

/**
 * radeon_ring_fini - tear down the driver ring struct.
 *
 * @rdev: radeon_device pointer
 * @ring: radeon_ring structure holding ring information
 *
 * Tear down the driver information for the selected ring (all asics).
 */
void radeon_ring_fini(struct radeon_device *rdev, struct radeon_ring *ring)
{
	int r;
	struct radeon_bo *ring_obj;

	mutex_lock(&rdev->ring_lock);
	ring_obj = ring->ring_obj;
	ring->ready = false;
	ring->ring = NULL;
	ring->ring_obj = NULL;
	mutex_unlock(&rdev->ring_lock);

	if (ring_obj) {
		r = radeon_bo_reserve(ring_obj, false);
		if (likely(r == 0)) {
			radeon_bo_kunmap(ring_obj);
			radeon_bo_unpin(ring_obj);
			radeon_bo_unreserve(ring_obj);
		}
		radeon_bo_unref(&ring_obj);
	}
}

/*
 * Debugfs info
 */
#if defined(CONFIG_DEBUG_FS)

static int radeon_debugfs_ring_info(struct seq_file *m, void *data)
{
	struct drm_info_node *node = (struct drm_info_node *) m->private;
	struct drm_device *dev = node->minor->dev;
	struct radeon_device *rdev = dev->dev_private;
	int ridx = *(int*)node->info_ent->data;
	struct radeon_ring *ring = &rdev->ring[ridx];
	unsigned count, i, j;

	radeon_ring_free_size(rdev, ring);
	count = (ring->ring_size / 4) - ring->ring_free_dw;
	seq_printf(m, "wptr(0x%04x): 0x%08x\n", ring->wptr_reg, RREG32(ring->wptr_reg));
	seq_printf(m, "rptr(0x%04x): 0x%08x\n", ring->rptr_reg, RREG32(ring->rptr_reg));
	if (ring->rptr_save_reg) {
		seq_printf(m, "rptr next(0x%04x): 0x%08x\n", ring->rptr_save_reg,
			   RREG32(ring->rptr_save_reg));
	}
	seq_printf(m, "driver's copy of the wptr: 0x%08x\n", ring->wptr);
	seq_printf(m, "driver's copy of the rptr: 0x%08x\n", ring->rptr);
	seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw);
	seq_printf(m, "%u dwords in ring\n", count);
	i = ring->rptr;
	for (j = 0; j <= count; j++) {
		seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
		i = (i + 1) & ring->ptr_mask;
	}
	return 0;
}

static int radeon_ring_type_gfx_index = RADEON_RING_TYPE_GFX_INDEX;
static int cayman_ring_type_cp1_index = CAYMAN_RING_TYPE_CP1_INDEX;
static int cayman_ring_type_cp2_index = CAYMAN_RING_TYPE_CP2_INDEX;

static struct drm_info_list radeon_debugfs_ring_info_list[] = {
	{"radeon_ring_gfx", radeon_debugfs_ring_info, 0, &radeon_ring_type_gfx_index},
	{"radeon_ring_cp1", radeon_debugfs_ring_info, 0, &cayman_ring_type_cp1_index},
	{"radeon_ring_cp2", radeon_debugfs_ring_info, 0, &cayman_ring_type_cp2_index},
};

static int radeon_debugfs_sa_info(struct seq_file *m, void *data)
{
	struct drm_info_node *node = (struct drm_info_node *) m->private;
	struct drm_device *dev = node->minor->dev;
	struct radeon_device *rdev = dev->dev_private;

	radeon_sa_bo_dump_debug_info(&rdev->ring_tmp_bo, m);

	return 0;

}

static struct drm_info_list radeon_debugfs_sa_list[] = {
        {"radeon_sa_info", &radeon_debugfs_sa_info, 0, NULL},
};

#endif

int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring)
{
#if defined(CONFIG_DEBUG_FS)
	unsigned i;
	for (i = 0; i < ARRAY_SIZE(radeon_debugfs_ring_info_list); ++i) {
		struct drm_info_list *info = &radeon_debugfs_ring_info_list[i];
		int ridx = *(int*)radeon_debugfs_ring_info_list[i].data;
		unsigned r;

		if (&rdev->ring[ridx] != ring)
			continue;

		r = radeon_debugfs_add_files(rdev, info, 1);
		if (r)
			return r;
	}
#endif
	return 0;
}

int radeon_debugfs_sa_init(struct radeon_device *rdev)
{
#if defined(CONFIG_DEBUG_FS)
	return radeon_debugfs_add_files(rdev, radeon_debugfs_sa_list, 1);
#else
	return 0;
#endif
}