summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
blob: ea25164e7f4b21ea4d0f9875ef32bbfb09edfa9c (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
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
/*
 * Copyright 2009 Jerome Glisse.
 * All Rights Reserved.
 *
 * 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, sub license, 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 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 NON-INFRINGEMENT. IN NO EVENT SHALL
 * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS 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.
 *
 * The above copyright notice and this permission notice (including the
 * next paragraph) shall be included in all copies or substantial portions
 * of the Software.
 *
 */
/*
 * Authors:
 *    Jerome Glisse <glisse@freedesktop.org>
 *    Thomas Hellstrom <thomas-at-tungstengraphics-dot-com>
 *    Dave Airlie
 */
#include <linux/list.h>
#include <linux/slab.h>
#include <drm/drmP.h>
#include <drm/amdgpu_drm.h>
#include <drm/drm_cache.h>
#include "amdgpu.h"
#include "amdgpu_trace.h"

static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
{
	struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
	struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);

	amdgpu_bo_kunmap(bo);

	drm_gem_object_release(&bo->gem_base);
	amdgpu_bo_unref(&bo->parent);
	if (!list_empty(&bo->shadow_list)) {
		mutex_lock(&adev->shadow_list_lock);
		list_del_init(&bo->shadow_list);
		mutex_unlock(&adev->shadow_list_lock);
	}
	kfree(bo->metadata);
	kfree(bo);
}

bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo)
{
	if (bo->destroy == &amdgpu_ttm_bo_destroy)
		return true;
	return false;
}

void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
{
	struct amdgpu_device *adev = amdgpu_ttm_adev(abo->tbo.bdev);
	struct ttm_placement *placement = &abo->placement;
	struct ttm_place *places = abo->placements;
	u64 flags = abo->flags;
	u32 c = 0;

	if (domain & AMDGPU_GEM_DOMAIN_VRAM) {
		unsigned visible_pfn = adev->mc.visible_vram_size >> PAGE_SHIFT;

		places[c].fpfn = 0;
		places[c].lpfn = 0;
		places[c].flags = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |
			TTM_PL_FLAG_VRAM;

		if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)
			places[c].lpfn = visible_pfn;
		else
			places[c].flags |= TTM_PL_FLAG_TOPDOWN;

		if (flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)
			places[c].flags |= TTM_PL_FLAG_CONTIGUOUS;
		c++;
	}

	if (domain & AMDGPU_GEM_DOMAIN_GTT) {
		places[c].fpfn = 0;
		if (flags & AMDGPU_GEM_CREATE_SHADOW)
			places[c].lpfn = adev->mc.gart_size >> PAGE_SHIFT;
		else
			places[c].lpfn = 0;
		places[c].flags = TTM_PL_FLAG_TT;
		if (flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC)
			places[c].flags |= TTM_PL_FLAG_WC |
				TTM_PL_FLAG_UNCACHED;
		else
			places[c].flags |= TTM_PL_FLAG_CACHED;
		c++;
	}

	if (domain & AMDGPU_GEM_DOMAIN_CPU) {
		places[c].fpfn = 0;
		places[c].lpfn = 0;
		places[c].flags = TTM_PL_FLAG_SYSTEM;
		if (flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC)
			places[c].flags |= TTM_PL_FLAG_WC |
				TTM_PL_FLAG_UNCACHED;
		else
			places[c].flags |= TTM_PL_FLAG_CACHED;
		c++;
	}

	if (domain & AMDGPU_GEM_DOMAIN_GDS) {
		places[c].fpfn = 0;
		places[c].lpfn = 0;
		places[c].flags = TTM_PL_FLAG_UNCACHED | AMDGPU_PL_FLAG_GDS;
		c++;
	}

	if (domain & AMDGPU_GEM_DOMAIN_GWS) {
		places[c].fpfn = 0;
		places[c].lpfn = 0;
		places[c].flags = TTM_PL_FLAG_UNCACHED | AMDGPU_PL_FLAG_GWS;
		c++;
	}

	if (domain & AMDGPU_GEM_DOMAIN_OA) {
		places[c].fpfn = 0;
		places[c].lpfn = 0;
		places[c].flags = TTM_PL_FLAG_UNCACHED | AMDGPU_PL_FLAG_OA;
		c++;
	}

	if (!c) {
		places[c].fpfn = 0;
		places[c].lpfn = 0;
		places[c].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
		c++;
	}

	placement->num_placement = c;
	placement->placement = places;

	placement->num_busy_placement = c;
	placement->busy_placement = places;
}

/**
 * amdgpu_bo_create_reserved - create reserved BO for kernel use
 *
 * @adev: amdgpu device object
 * @size: size for the new BO
 * @align: alignment for the new BO
 * @domain: where to place it
 * @bo_ptr: resulting BO
 * @gpu_addr: GPU addr of the pinned BO
 * @cpu_addr: optional CPU address mapping
 *
 * Allocates and pins a BO for kernel internal use, and returns it still
 * reserved.
 *
 * Returns 0 on success, negative error code otherwise.
 */
int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
			      unsigned long size, int align,
			      u32 domain, struct amdgpu_bo **bo_ptr,
			      u64 *gpu_addr, void **cpu_addr)
{
	bool free = false;
	int r;

	if (!*bo_ptr) {
		r = amdgpu_bo_create(adev, size, align, true, domain,
				     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
				     AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS,
				     NULL, NULL, 0, bo_ptr);
		if (r) {
			dev_err(adev->dev, "(%d) failed to allocate kernel bo\n",
				r);
			return r;
		}
		free = true;
	}

	r = amdgpu_bo_reserve(*bo_ptr, false);
	if (r) {
		dev_err(adev->dev, "(%d) failed to reserve kernel bo\n", r);
		goto error_free;
	}

	r = amdgpu_bo_pin(*bo_ptr, domain, gpu_addr);
	if (r) {
		dev_err(adev->dev, "(%d) kernel bo pin failed\n", r);
		goto error_unreserve;
	}

	if (cpu_addr) {
		r = amdgpu_bo_kmap(*bo_ptr, cpu_addr);
		if (r) {
			dev_err(adev->dev, "(%d) kernel bo map failed\n", r);
			goto error_unreserve;
		}
	}

	return 0;

error_unreserve:
	amdgpu_bo_unreserve(*bo_ptr);

error_free:
	if (free)
		amdgpu_bo_unref(bo_ptr);

	return r;
}

/**
 * amdgpu_bo_create_kernel - create BO for kernel use
 *
 * @adev: amdgpu device object
 * @size: size for the new BO
 * @align: alignment for the new BO
 * @domain: where to place it
 * @bo_ptr: resulting BO
 * @gpu_addr: GPU addr of the pinned BO
 * @cpu_addr: optional CPU address mapping
 *
 * Allocates and pins a BO for kernel internal use.
 *
 * Returns 0 on success, negative error code otherwise.
 */
int amdgpu_bo_create_kernel(struct amdgpu_device *adev,
			    unsigned long size, int align,
			    u32 domain, struct amdgpu_bo **bo_ptr,
			    u64 *gpu_addr, void **cpu_addr)
{
	int r;

	r = amdgpu_bo_create_reserved(adev, size, align, domain, bo_ptr,
				      gpu_addr, cpu_addr);

	if (r)
		return r;

	amdgpu_bo_unreserve(*bo_ptr);

	return 0;
}

/**
 * amdgpu_bo_free_kernel - free BO for kernel use
 *
 * @bo: amdgpu BO to free
 *
 * unmaps and unpin a BO for kernel internal use.
 */
void amdgpu_bo_free_kernel(struct amdgpu_bo **bo, u64 *gpu_addr,
			   void **cpu_addr)
{
	if (*bo == NULL)
		return;

	if (likely(amdgpu_bo_reserve(*bo, true) == 0)) {
		if (cpu_addr)
			amdgpu_bo_kunmap(*bo);

		amdgpu_bo_unpin(*bo);
		amdgpu_bo_unreserve(*bo);
	}
	amdgpu_bo_unref(bo);

	if (gpu_addr)
		*gpu_addr = 0;

	if (cpu_addr)
		*cpu_addr = NULL;
}

static int amdgpu_bo_do_create(struct amdgpu_device *adev,
			       unsigned long size, int byte_align,
			       bool kernel, u32 domain, u64 flags,
			       struct sg_table *sg,
			       struct reservation_object *resv,
			       uint64_t init_value,
			       struct amdgpu_bo **bo_ptr)
{
	struct amdgpu_bo *bo;
	enum ttm_bo_type type;
	unsigned long page_align;
	u64 initial_bytes_moved, bytes_moved;
	size_t acc_size;
	int r;

	page_align = roundup(byte_align, PAGE_SIZE) >> PAGE_SHIFT;
	size = ALIGN(size, PAGE_SIZE);

	if (kernel) {
		type = ttm_bo_type_kernel;
	} else if (sg) {
		type = ttm_bo_type_sg;
	} else {
		type = ttm_bo_type_device;
	}
	*bo_ptr = NULL;

	acc_size = ttm_bo_dma_acc_size(&adev->mman.bdev, size,
				       sizeof(struct amdgpu_bo));

	bo = kzalloc(sizeof(struct amdgpu_bo), GFP_KERNEL);
	if (bo == NULL)
		return -ENOMEM;
	r = drm_gem_object_init(adev->ddev, &bo->gem_base, size);
	if (unlikely(r)) {
		kfree(bo);
		return r;
	}
	INIT_LIST_HEAD(&bo->shadow_list);
	INIT_LIST_HEAD(&bo->va);
	bo->preferred_domains = domain & (AMDGPU_GEM_DOMAIN_VRAM |
					 AMDGPU_GEM_DOMAIN_GTT |
					 AMDGPU_GEM_DOMAIN_CPU |
					 AMDGPU_GEM_DOMAIN_GDS |
					 AMDGPU_GEM_DOMAIN_GWS |
					 AMDGPU_GEM_DOMAIN_OA);
	bo->allowed_domains = bo->preferred_domains;
	if (!kernel && bo->allowed_domains == AMDGPU_GEM_DOMAIN_VRAM)
		bo->allowed_domains |= AMDGPU_GEM_DOMAIN_GTT;

	bo->flags = flags;

#ifdef CONFIG_X86_32
	/* XXX: Write-combined CPU mappings of GTT seem broken on 32-bit
	 * See https://bugs.freedesktop.org/show_bug.cgi?id=84627
	 */
	bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
#elif defined(CONFIG_X86) && !defined(CONFIG_X86_PAT)
	/* Don't try to enable write-combining when it can't work, or things
	 * may be slow
	 * See https://bugs.freedesktop.org/show_bug.cgi?id=88758
	 */

#ifndef CONFIG_COMPILE_TEST
#warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \
	 thanks to write-combining
#endif

	if (bo->flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC)
		DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "
			      "better performance thanks to write-combining\n");
	bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
#else
	/* For architectures that don't support WC memory,
	 * mask out the WC flag from the BO
	 */
	if (!drm_arch_can_wc_memory())
		bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
#endif

	bo->tbo.bdev = &adev->mman.bdev;
	amdgpu_ttm_placement_from_domain(bo, domain);

	initial_bytes_moved = atomic64_read(&adev->num_bytes_moved);
	/* Kernel allocation are uninterruptible */
	r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, type,
				 &bo->placement, page_align, !kernel, NULL,
				 acc_size, sg, resv, &amdgpu_ttm_bo_destroy);
	if (unlikely(r != 0))
		return r;

	bytes_moved = atomic64_read(&adev->num_bytes_moved) -
		      initial_bytes_moved;
	if (adev->mc.visible_vram_size < adev->mc.real_vram_size &&
	    bo->tbo.mem.mem_type == TTM_PL_VRAM &&
	    bo->tbo.mem.start < adev->mc.visible_vram_size >> PAGE_SHIFT)
		amdgpu_cs_report_moved_bytes(adev, bytes_moved, bytes_moved);
	else
		amdgpu_cs_report_moved_bytes(adev, bytes_moved, 0);

	if (kernel)
		bo->tbo.priority = 1;

	if (flags & AMDGPU_GEM_CREATE_VRAM_CLEARED &&
	    bo->tbo.mem.placement & TTM_PL_FLAG_VRAM) {
		struct dma_fence *fence;

		r = amdgpu_fill_buffer(bo, init_value, bo->tbo.resv, &fence);
		if (unlikely(r))
			goto fail_unreserve;

		amdgpu_bo_fence(bo, fence, false);
		dma_fence_put(bo->tbo.moving);
		bo->tbo.moving = dma_fence_get(fence);
		dma_fence_put(fence);
	}
	if (!resv)
		amdgpu_bo_unreserve(bo);
	*bo_ptr = bo;

	trace_amdgpu_bo_create(bo);

	/* Treat CPU_ACCESS_REQUIRED only as a hint if given by UMD */
	if (type == ttm_bo_type_device)
		bo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;

	return 0;

fail_unreserve:
	if (!resv)
		ww_mutex_unlock(&bo->tbo.resv->lock);
	amdgpu_bo_unref(&bo);
	return r;
}

static int amdgpu_bo_create_shadow(struct amdgpu_device *adev,
				   unsigned long size, int byte_align,
				   struct amdgpu_bo *bo)
{
	int r;

	if (bo->shadow)
		return 0;

	r = amdgpu_bo_do_create(adev, size, byte_align, true,
				AMDGPU_GEM_DOMAIN_GTT,
				AMDGPU_GEM_CREATE_CPU_GTT_USWC |
				AMDGPU_GEM_CREATE_SHADOW,
				NULL, bo->tbo.resv, 0,
				&bo->shadow);
	if (!r) {
		bo->shadow->parent = amdgpu_bo_ref(bo);
		mutex_lock(&adev->shadow_list_lock);
		list_add_tail(&bo->shadow_list, &adev->shadow_list);
		mutex_unlock(&adev->shadow_list_lock);
	}

	return r;
}

/* init_value will only take effect when flags contains
 * AMDGPU_GEM_CREATE_VRAM_CLEARED.
 */
int amdgpu_bo_create(struct amdgpu_device *adev,
		     unsigned long size, int byte_align,
		     bool kernel, u32 domain, u64 flags,
		     struct sg_table *sg,
		     struct reservation_object *resv,
		     uint64_t init_value,
		     struct amdgpu_bo **bo_ptr)
{
	uint64_t parent_flags = flags & ~AMDGPU_GEM_CREATE_SHADOW;
	int r;

	r = amdgpu_bo_do_create(adev, size, byte_align, kernel, domain,
				parent_flags, sg, resv, init_value, bo_ptr);
	if (r)
		return r;

	if ((flags & AMDGPU_GEM_CREATE_SHADOW) && amdgpu_need_backup(adev)) {
		if (!resv)
			WARN_ON(reservation_object_lock((*bo_ptr)->tbo.resv,
							NULL));

		r = amdgpu_bo_create_shadow(adev, size, byte_align, (*bo_ptr));

		if (!resv)
			reservation_object_unlock((*bo_ptr)->tbo.resv);

		if (r)
			amdgpu_bo_unref(bo_ptr);
	}

	return r;
}

int amdgpu_bo_backup_to_shadow(struct amdgpu_device *adev,
			       struct amdgpu_ring *ring,
			       struct amdgpu_bo *bo,
			       struct reservation_object *resv,
			       struct dma_fence **fence,
			       bool direct)

{
	struct amdgpu_bo *shadow = bo->shadow;
	uint64_t bo_addr, shadow_addr;
	int r;

	if (!shadow)
		return -EINVAL;

	bo_addr = amdgpu_bo_gpu_offset(bo);
	shadow_addr = amdgpu_bo_gpu_offset(bo->shadow);

	r = reservation_object_reserve_shared(bo->tbo.resv);
	if (r)
		goto err;

	r = amdgpu_copy_buffer(ring, bo_addr, shadow_addr,
			       amdgpu_bo_size(bo), resv, fence,
			       direct, false);
	if (!r)
		amdgpu_bo_fence(bo, *fence, true);

err:
	return r;
}

int amdgpu_bo_validate(struct amdgpu_bo *bo)
{
	uint32_t domain;
	int r;

	if (bo->pin_count)
		return 0;

	domain = bo->preferred_domains;

retry:
	amdgpu_ttm_placement_from_domain(bo, domain);
	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
	if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) {
		domain = bo->allowed_domains;
		goto retry;
	}

	return r;
}

int amdgpu_bo_restore_from_shadow(struct amdgpu_device *adev,
				  struct amdgpu_ring *ring,
				  struct amdgpu_bo *bo,
				  struct reservation_object *resv,
				  struct dma_fence **fence,
				  bool direct)

{
	struct amdgpu_bo *shadow = bo->shadow;
	uint64_t bo_addr, shadow_addr;
	int r;

	if (!shadow)
		return -EINVAL;

	bo_addr = amdgpu_bo_gpu_offset(bo);
	shadow_addr = amdgpu_bo_gpu_offset(bo->shadow);

	r = reservation_object_reserve_shared(bo->tbo.resv);
	if (r)
		goto err;

	r = amdgpu_copy_buffer(ring, shadow_addr, bo_addr,
			       amdgpu_bo_size(bo), resv, fence,
			       direct, false);
	if (!r)
		amdgpu_bo_fence(bo, *fence, true);

err:
	return r;
}

int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr)
{
	void *kptr;
	long r;

	if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
		return -EPERM;

	kptr = amdgpu_bo_kptr(bo);
	if (kptr) {
		if (ptr)
			*ptr = kptr;
		return 0;
	}

	r = reservation_object_wait_timeout_rcu(bo->tbo.resv, false, false,
						MAX_SCHEDULE_TIMEOUT);
	if (r < 0)
		return r;

	r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.num_pages, &bo->kmap);
	if (r)
		return r;

	if (ptr)
		*ptr = amdgpu_bo_kptr(bo);

	return 0;
}

void *amdgpu_bo_kptr(struct amdgpu_bo *bo)
{
	bool is_iomem;

	return ttm_kmap_obj_virtual(&bo->kmap, &is_iomem);
}

void amdgpu_bo_kunmap(struct amdgpu_bo *bo)
{
	if (bo->kmap.bo)
		ttm_bo_kunmap(&bo->kmap);
}

struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo)
{
	if (bo == NULL)
		return NULL;

	ttm_bo_reference(&bo->tbo);
	return bo;
}

void amdgpu_bo_unref(struct amdgpu_bo **bo)
{
	struct ttm_buffer_object *tbo;

	if ((*bo) == NULL)
		return;

	tbo = &((*bo)->tbo);
	ttm_bo_unref(&tbo);
	if (tbo == NULL)
		*bo = NULL;
}

int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
			     u64 min_offset, u64 max_offset,
			     u64 *gpu_addr)
{
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
	int r, i;

	if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm))
		return -EPERM;

	if (WARN_ON_ONCE(min_offset > max_offset))
		return -EINVAL;

	/* A shared bo cannot be migrated to VRAM */
	if (bo->prime_shared_count && (domain == AMDGPU_GEM_DOMAIN_VRAM))
		return -EINVAL;

	if (bo->pin_count) {
		uint32_t mem_type = bo->tbo.mem.mem_type;

		if (domain != amdgpu_mem_type_to_domain(mem_type))
			return -EINVAL;

		bo->pin_count++;
		if (gpu_addr)
			*gpu_addr = amdgpu_bo_gpu_offset(bo);

		if (max_offset != 0) {
			u64 domain_start = bo->tbo.bdev->man[mem_type].gpu_offset;
			WARN_ON_ONCE(max_offset <
				     (amdgpu_bo_gpu_offset(bo) - domain_start));
		}

		return 0;
	}

	bo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
	/* force to pin into visible video ram */
	if (!(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS))
		bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
	amdgpu_ttm_placement_from_domain(bo, domain);
	for (i = 0; i < bo->placement.num_placement; i++) {
		unsigned fpfn, lpfn;

		fpfn = min_offset >> PAGE_SHIFT;
		lpfn = max_offset >> PAGE_SHIFT;

		if (fpfn > bo->placements[i].fpfn)
			bo->placements[i].fpfn = fpfn;
		if (!bo->placements[i].lpfn ||
		    (lpfn && lpfn < bo->placements[i].lpfn))
			bo->placements[i].lpfn = lpfn;
		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
	}

	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
	if (unlikely(r)) {
		dev_err(adev->dev, "%p pin failed\n", bo);
		goto error;
	}

	bo->pin_count = 1;
	if (gpu_addr != NULL) {
		r = amdgpu_ttm_bind(&bo->tbo, &bo->tbo.mem);
		if (unlikely(r)) {
			dev_err(adev->dev, "%p bind failed\n", bo);
			goto error;
		}
		*gpu_addr = amdgpu_bo_gpu_offset(bo);
	}
	if (domain == AMDGPU_GEM_DOMAIN_VRAM) {
		adev->vram_pin_size += amdgpu_bo_size(bo);
		if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
			adev->invisible_pin_size += amdgpu_bo_size(bo);
	} else if (domain == AMDGPU_GEM_DOMAIN_GTT) {
		adev->gart_pin_size += amdgpu_bo_size(bo);
	}

error:
	return r;
}

int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain, u64 *gpu_addr)
{
	return amdgpu_bo_pin_restricted(bo, domain, 0, 0, gpu_addr);
}

int amdgpu_bo_unpin(struct amdgpu_bo *bo)
{
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
	int r, i;

	if (!bo->pin_count) {
		dev_warn(adev->dev, "%p unpin not necessary\n", bo);
		return 0;
	}
	bo->pin_count--;
	if (bo->pin_count)
		return 0;
	for (i = 0; i < bo->placement.num_placement; i++) {
		bo->placements[i].lpfn = 0;
		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
	}
	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
	if (unlikely(r)) {
		dev_err(adev->dev, "%p validate failed for unpin\n", bo);
		goto error;
	}

	if (bo->tbo.mem.mem_type == TTM_PL_VRAM) {
		adev->vram_pin_size -= amdgpu_bo_size(bo);
		if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
			adev->invisible_pin_size -= amdgpu_bo_size(bo);
	} else if (bo->tbo.mem.mem_type == TTM_PL_TT) {
		adev->gart_pin_size -= amdgpu_bo_size(bo);
	}

error:
	return r;
}

int amdgpu_bo_evict_vram(struct amdgpu_device *adev)
{
	/* late 2.6.33 fix IGP hibernate - we need pm ops to do this correct */
	if (0 && (adev->flags & AMD_IS_APU)) {
		/* Useless to evict on IGP chips */
		return 0;
	}
	return ttm_bo_evict_mm(&adev->mman.bdev, TTM_PL_VRAM);
}

static const char *amdgpu_vram_names[] = {
	"UNKNOWN",
	"GDDR1",
	"DDR2",
	"GDDR3",
	"GDDR4",
	"GDDR5",
	"HBM",
	"DDR3"
};

int amdgpu_bo_init(struct amdgpu_device *adev)
{
	/* reserve PAT memory space to WC for VRAM */
	arch_io_reserve_memtype_wc(adev->mc.aper_base,
				   adev->mc.aper_size);

	/* Add an MTRR for the VRAM */
	adev->mc.vram_mtrr = arch_phys_wc_add(adev->mc.aper_base,
					      adev->mc.aper_size);
	DRM_INFO("Detected VRAM RAM=%lluM, BAR=%lluM\n",
		adev->mc.mc_vram_size >> 20,
		(unsigned long long)adev->mc.aper_size >> 20);
	DRM_INFO("RAM width %dbits %s\n",
		 adev->mc.vram_width, amdgpu_vram_names[adev->mc.vram_type]);
	return amdgpu_ttm_init(adev);
}

void amdgpu_bo_fini(struct amdgpu_device *adev)
{
	amdgpu_ttm_fini(adev);
	arch_phys_wc_del(adev->mc.vram_mtrr);
	arch_io_free_memtype_wc(adev->mc.aper_base, adev->mc.aper_size);
}

int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo,
			     struct vm_area_struct *vma)
{
	return ttm_fbdev_mmap(vma, &bo->tbo);
}

int amdgpu_bo_set_tiling_flags(struct amdgpu_bo *bo, u64 tiling_flags)
{
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);

	if (adev->family <= AMDGPU_FAMILY_CZ &&
	    AMDGPU_TILING_GET(tiling_flags, TILE_SPLIT) > 6)
		return -EINVAL;

	bo->tiling_flags = tiling_flags;
	return 0;
}

void amdgpu_bo_get_tiling_flags(struct amdgpu_bo *bo, u64 *tiling_flags)
{
	lockdep_assert_held(&bo->tbo.resv->lock.base);

	if (tiling_flags)
		*tiling_flags = bo->tiling_flags;
}

int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata,
			    uint32_t metadata_size, uint64_t flags)
{
	void *buffer;

	if (!metadata_size) {
		if (bo->metadata_size) {
			kfree(bo->metadata);
			bo->metadata = NULL;
			bo->metadata_size = 0;
		}
		return 0;
	}

	if (metadata == NULL)
		return -EINVAL;

	buffer = kmemdup(metadata, metadata_size, GFP_KERNEL);
	if (buffer == NULL)
		return -ENOMEM;

	kfree(bo->metadata);
	bo->metadata_flags = flags;
	bo->metadata = buffer;
	bo->metadata_size = metadata_size;

	return 0;
}

int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
			   size_t buffer_size, uint32_t *metadata_size,
			   uint64_t *flags)
{
	if (!buffer && !metadata_size)
		return -EINVAL;

	if (buffer) {
		if (buffer_size < bo->metadata_size)
			return -EINVAL;

		if (bo->metadata_size)
			memcpy(buffer, bo->metadata, bo->metadata_size);
	}

	if (metadata_size)
		*metadata_size = bo->metadata_size;
	if (flags)
		*flags = bo->metadata_flags;

	return 0;
}

void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
			   bool evict,
			   struct ttm_mem_reg *new_mem)
{
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
	struct amdgpu_bo *abo;
	struct ttm_mem_reg *old_mem = &bo->mem;

	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
		return;

	abo = ttm_to_amdgpu_bo(bo);
	amdgpu_vm_bo_invalidate(adev, abo, evict);

	amdgpu_bo_kunmap(abo);

	/* remember the eviction */
	if (evict)
		atomic64_inc(&adev->num_evictions);

	/* update statistics */
	if (!new_mem)
		return;

	/* move_notify is called before move happens */
	trace_amdgpu_ttm_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
}

int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
{
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
	struct amdgpu_bo *abo;
	unsigned long offset, size;
	int r;

	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
		return 0;

	abo = ttm_to_amdgpu_bo(bo);

	/* Remember that this BO was accessed by the CPU */
	abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;

	if (bo->mem.mem_type != TTM_PL_VRAM)
		return 0;

	size = bo->mem.num_pages << PAGE_SHIFT;
	offset = bo->mem.start << PAGE_SHIFT;
	if ((offset + size) <= adev->mc.visible_vram_size)
		return 0;

	/* Can't move a pinned BO to visible VRAM */
	if (abo->pin_count > 0)
		return -EINVAL;

	/* hurrah the memory is not visible ! */
	atomic64_inc(&adev->num_vram_cpu_page_faults);
	amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
					 AMDGPU_GEM_DOMAIN_GTT);

	/* Avoid costly evictions; only set GTT as a busy placement */
	abo->placement.num_busy_placement = 1;
	abo->placement.busy_placement = &abo->placements[1];

	r = ttm_bo_validate(bo, &abo->placement, false, false);
	if (unlikely(r != 0))
		return r;

	offset = bo->mem.start << PAGE_SHIFT;
	/* this should never happen */
	if (bo->mem.mem_type == TTM_PL_VRAM &&
	    (offset + size) > adev->mc.visible_vram_size)
		return -EINVAL;

	return 0;
}

/**
 * amdgpu_bo_fence - add fence to buffer object
 *
 * @bo: buffer object in question
 * @fence: fence to add
 * @shared: true if fence should be added shared
 *
 */
void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,
		     bool shared)
{
	struct reservation_object *resv = bo->tbo.resv;

	if (shared)
		reservation_object_add_shared_fence(resv, fence);
	else
		reservation_object_add_excl_fence(resv, fence);
}

/**
 * amdgpu_bo_gpu_offset - return GPU offset of bo
 * @bo:	amdgpu object for which we query the offset
 *
 * Returns current GPU offset of the object.
 *
 * Note: object should either be pinned or reserved when calling this
 * function, it might be useful to add check for this for debugging.
 */
u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo)
{
	WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_SYSTEM);
	WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_TT &&
		     !amdgpu_ttm_is_bound(bo->tbo.ttm));
	WARN_ON_ONCE(!ww_mutex_is_locked(&bo->tbo.resv->lock) &&
		     !bo->pin_count);
	WARN_ON_ONCE(bo->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET);
	WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_VRAM &&
		     !(bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS));

	return bo->tbo.offset;
}