summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
blob: 3adaa46701036d49f74378932cac32a3512e0528 (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
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
/*
 * 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
 */
#include <linux/ktime.h>
#include <linux/module.h>
#include <linux/pagemap.h>
#include <linux/pci.h>
#include <linux/dma-buf.h>

#include <drm/amdgpu_drm.h>
#include <drm/drm_drv.h>
#include <drm/drm_exec.h>
#include <drm/drm_gem_ttm_helper.h>
#include <drm/ttm/ttm_tt.h>

#include "amdgpu.h"
#include "amdgpu_display.h"
#include "amdgpu_dma_buf.h"
#include "amdgpu_hmm.h"
#include "amdgpu_xgmi.h"

static const struct drm_gem_object_funcs amdgpu_gem_object_funcs;

static vm_fault_t amdgpu_gem_fault(struct vm_fault *vmf)
{
	struct ttm_buffer_object *bo = vmf->vma->vm_private_data;
	struct drm_device *ddev = bo->base.dev;
	vm_fault_t ret;
	int idx;

	ret = ttm_bo_vm_reserve(bo, vmf);
	if (ret)
		return ret;

	if (drm_dev_enter(ddev, &idx)) {
		ret = amdgpu_bo_fault_reserve_notify(bo);
		if (ret) {
			drm_dev_exit(idx);
			goto unlock;
		}

		ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
					       TTM_BO_VM_NUM_PREFAULT);

		drm_dev_exit(idx);
	} else {
		ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot);
	}
	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
		return ret;

unlock:
	dma_resv_unlock(bo->base.resv);
	return ret;
}

static const struct vm_operations_struct amdgpu_gem_vm_ops = {
	.fault = amdgpu_gem_fault,
	.open = ttm_bo_vm_open,
	.close = ttm_bo_vm_close,
	.access = ttm_bo_vm_access
};

static void amdgpu_gem_object_free(struct drm_gem_object *gobj)
{
	struct amdgpu_bo *robj = gem_to_amdgpu_bo(gobj);

	if (robj) {
		amdgpu_hmm_unregister(robj);
		amdgpu_bo_unref(&robj);
	}
}

int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size,
			     int alignment, u32 initial_domain,
			     u64 flags, enum ttm_bo_type type,
			     struct dma_resv *resv,
			     struct drm_gem_object **obj, int8_t xcp_id_plus1)
{
	struct amdgpu_bo *bo;
	struct amdgpu_bo_user *ubo;
	struct amdgpu_bo_param bp;
	int r;

	memset(&bp, 0, sizeof(bp));
	*obj = NULL;
	flags |= AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE;

	bp.size = size;
	bp.byte_align = alignment;
	bp.type = type;
	bp.resv = resv;
	bp.preferred_domain = initial_domain;
	bp.flags = flags;
	bp.domain = initial_domain;
	bp.bo_ptr_size = sizeof(struct amdgpu_bo);
	bp.xcp_id_plus1 = xcp_id_plus1;

	r = amdgpu_bo_create_user(adev, &bp, &ubo);
	if (r)
		return r;

	bo = &ubo->bo;
	*obj = &bo->tbo.base;
	(*obj)->funcs = &amdgpu_gem_object_funcs;

	return 0;
}

void amdgpu_gem_force_release(struct amdgpu_device *adev)
{
	struct drm_device *ddev = adev_to_drm(adev);
	struct drm_file *file;

	mutex_lock(&ddev->filelist_mutex);

	list_for_each_entry(file, &ddev->filelist, lhead) {
		struct drm_gem_object *gobj;
		int handle;

		WARN_ONCE(1, "Still active user space clients!\n");
		spin_lock(&file->table_lock);
		idr_for_each_entry(&file->object_idr, gobj, handle) {
			WARN_ONCE(1, "And also active allocations!\n");
			drm_gem_object_put(gobj);
		}
		idr_destroy(&file->object_idr);
		spin_unlock(&file->table_lock);
	}

	mutex_unlock(&ddev->filelist_mutex);
}

/*
 * Call from drm_gem_handle_create which appear in both new and open ioctl
 * case.
 */
static int amdgpu_gem_object_open(struct drm_gem_object *obj,
				  struct drm_file *file_priv)
{
	struct amdgpu_bo *abo = gem_to_amdgpu_bo(obj);
	struct amdgpu_device *adev = amdgpu_ttm_adev(abo->tbo.bdev);
	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
	struct amdgpu_vm *vm = &fpriv->vm;
	struct amdgpu_bo_va *bo_va;
	struct mm_struct *mm;
	int r;

	mm = amdgpu_ttm_tt_get_usermm(abo->tbo.ttm);
	if (mm && mm != current->mm)
		return -EPERM;

	if (abo->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID &&
	    abo->tbo.base.resv != vm->root.bo->tbo.base.resv)
		return -EPERM;

	r = amdgpu_bo_reserve(abo, false);
	if (r)
		return r;

	bo_va = amdgpu_vm_bo_find(vm, abo);
	if (!bo_va)
		bo_va = amdgpu_vm_bo_add(adev, vm, abo);
	else
		++bo_va->ref_count;
	amdgpu_bo_unreserve(abo);

	/* Validate and add eviction fence to DMABuf imports with dynamic
	 * attachment in compute VMs. Re-validation will be done by
	 * amdgpu_vm_validate. Fences are on the reservation shared with the
	 * export, which is currently required to be validated and fenced
	 * already by amdgpu_amdkfd_gpuvm_restore_process_bos.
	 *
	 * Nested locking below for the case that a GEM object is opened in
	 * kfd_mem_export_dmabuf. Since the lock below is only taken for imports,
	 * but not for export, this is a different lock class that cannot lead to
	 * circular lock dependencies.
	 */
	if (!vm->is_compute_context || !vm->process_info)
		return 0;
	if (!obj->import_attach ||
	    !dma_buf_is_dynamic(obj->import_attach->dmabuf))
		return 0;
	mutex_lock_nested(&vm->process_info->lock, 1);
	if (!WARN_ON(!vm->process_info->eviction_fence)) {
		r = amdgpu_amdkfd_bo_validate_and_fence(abo, AMDGPU_GEM_DOMAIN_GTT,
							&vm->process_info->eviction_fence->base);
		if (r) {
			struct amdgpu_task_info *ti = amdgpu_vm_get_task_info_vm(vm);

			dev_warn(adev->dev, "validate_and_fence failed: %d\n", r);
			if (ti) {
				dev_warn(adev->dev, "pid %d\n", ti->pid);
				amdgpu_vm_put_task_info(ti);
			}
		}
	}
	mutex_unlock(&vm->process_info->lock);

	return r;
}

static void amdgpu_gem_object_close(struct drm_gem_object *obj,
				    struct drm_file *file_priv)
{
	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
	struct amdgpu_vm *vm = &fpriv->vm;

	struct dma_fence *fence = NULL;
	struct amdgpu_bo_va *bo_va;
	struct drm_exec exec;
	long r;

	drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 0);
	drm_exec_until_all_locked(&exec) {
		r = drm_exec_prepare_obj(&exec, &bo->tbo.base, 1);
		drm_exec_retry_on_contention(&exec);
		if (unlikely(r))
			goto out_unlock;

		r = amdgpu_vm_lock_pd(vm, &exec, 0);
		drm_exec_retry_on_contention(&exec);
		if (unlikely(r))
			goto out_unlock;
	}

	bo_va = amdgpu_vm_bo_find(vm, bo);
	if (!bo_va || --bo_va->ref_count)
		goto out_unlock;

	amdgpu_vm_bo_del(adev, bo_va);
	if (!amdgpu_vm_ready(vm))
		goto out_unlock;

	r = amdgpu_vm_clear_freed(adev, vm, &fence);
	if (unlikely(r < 0))
		dev_err(adev->dev, "failed to clear page "
			"tables on GEM object close (%ld)\n", r);
	if (r || !fence)
		goto out_unlock;

	amdgpu_bo_fence(bo, fence, true);
	dma_fence_put(fence);

out_unlock:
	if (r)
		dev_err(adev->dev, "leaking bo va (%ld)\n", r);
	drm_exec_fini(&exec);
}

static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
{
	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);

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

	/* Workaround for Thunk bug creating PROT_NONE,MAP_PRIVATE mappings
	 * for debugger access to invisible VRAM. Should have used MAP_SHARED
	 * instead. Clearing VM_MAYWRITE prevents the mapping from ever
	 * becoming writable and makes is_cow_mapping(vm_flags) false.
	 */
	if (is_cow_mapping(vma->vm_flags) &&
	    !(vma->vm_flags & VM_ACCESS_FLAGS))
		vm_flags_clear(vma, VM_MAYWRITE);

	return drm_gem_ttm_mmap(obj, vma);
}

static const struct drm_gem_object_funcs amdgpu_gem_object_funcs = {
	.free = amdgpu_gem_object_free,
	.open = amdgpu_gem_object_open,
	.close = amdgpu_gem_object_close,
	.export = amdgpu_gem_prime_export,
	.vmap = drm_gem_ttm_vmap,
	.vunmap = drm_gem_ttm_vunmap,
	.mmap = amdgpu_gem_object_mmap,
	.vm_ops = &amdgpu_gem_vm_ops,
};

/*
 * GEM ioctls.
 */
int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
			    struct drm_file *filp)
{
	struct amdgpu_device *adev = drm_to_adev(dev);
	struct amdgpu_fpriv *fpriv = filp->driver_priv;
	struct amdgpu_vm *vm = &fpriv->vm;
	union drm_amdgpu_gem_create *args = data;
	uint64_t flags = args->in.domain_flags;
	uint64_t size = args->in.bo_size;
	struct dma_resv *resv = NULL;
	struct drm_gem_object *gobj;
	uint32_t handle, initial_domain;
	int r;

	/* reject DOORBELLs until userspace code to use it is available */
	if (args->in.domains & AMDGPU_GEM_DOMAIN_DOORBELL)
		return -EINVAL;

	/* reject invalid gem flags */
	if (flags & ~(AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
		      AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
		      AMDGPU_GEM_CREATE_CPU_GTT_USWC |
		      AMDGPU_GEM_CREATE_VRAM_CLEARED |
		      AMDGPU_GEM_CREATE_VM_ALWAYS_VALID |
		      AMDGPU_GEM_CREATE_EXPLICIT_SYNC |
		      AMDGPU_GEM_CREATE_ENCRYPTED |
		      AMDGPU_GEM_CREATE_DISCARDABLE))
		return -EINVAL;

	/* reject invalid gem domains */
	if (args->in.domains & ~AMDGPU_GEM_DOMAIN_MASK)
		return -EINVAL;

	if (!amdgpu_is_tmz(adev) && (flags & AMDGPU_GEM_CREATE_ENCRYPTED)) {
		DRM_NOTE_ONCE("Cannot allocate secure buffer since TMZ is disabled\n");
		return -EINVAL;
	}

	/* create a gem object to contain this object in */
	if (args->in.domains & (AMDGPU_GEM_DOMAIN_GDS |
	    AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA)) {
		if (flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) {
			/* if gds bo is created from user space, it must be
			 * passed to bo list
			 */
			DRM_ERROR("GDS bo cannot be per-vm-bo\n");
			return -EINVAL;
		}
		flags |= AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
	}

	if (flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) {
		r = amdgpu_bo_reserve(vm->root.bo, false);
		if (r)
			return r;

		resv = vm->root.bo->tbo.base.resv;
	}

	initial_domain = (u32)(0xffffffff & args->in.domains);
retry:
	r = amdgpu_gem_object_create(adev, size, args->in.alignment,
				     initial_domain,
				     flags, ttm_bo_type_device, resv, &gobj, fpriv->xcp_id + 1);
	if (r && r != -ERESTARTSYS) {
		if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) {
			flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
			goto retry;
		}

		if (initial_domain == AMDGPU_GEM_DOMAIN_VRAM) {
			initial_domain |= AMDGPU_GEM_DOMAIN_GTT;
			goto retry;
		}
		DRM_DEBUG("Failed to allocate GEM object (%llu, %d, %llu, %d)\n",
				size, initial_domain, args->in.alignment, r);
	}

	if (flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) {
		if (!r) {
			struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj);

			abo->parent = amdgpu_bo_ref(vm->root.bo);
		}
		amdgpu_bo_unreserve(vm->root.bo);
	}
	if (r)
		return r;

	r = drm_gem_handle_create(filp, gobj, &handle);
	/* drop reference from allocate - handle holds it now */
	drm_gem_object_put(gobj);
	if (r)
		return r;

	memset(args, 0, sizeof(*args));
	args->out.handle = handle;
	return 0;
}

int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
			     struct drm_file *filp)
{
	struct ttm_operation_ctx ctx = { true, false };
	struct amdgpu_device *adev = drm_to_adev(dev);
	struct drm_amdgpu_gem_userptr *args = data;
	struct amdgpu_fpriv *fpriv = filp->driver_priv;
	struct drm_gem_object *gobj;
	struct hmm_range *range;
	struct amdgpu_bo *bo;
	uint32_t handle;
	int r;

	args->addr = untagged_addr(args->addr);

	if (offset_in_page(args->addr | args->size))
		return -EINVAL;

	/* reject unknown flag values */
	if (args->flags & ~(AMDGPU_GEM_USERPTR_READONLY |
	    AMDGPU_GEM_USERPTR_ANONONLY | AMDGPU_GEM_USERPTR_VALIDATE |
	    AMDGPU_GEM_USERPTR_REGISTER))
		return -EINVAL;

	if (!(args->flags & AMDGPU_GEM_USERPTR_READONLY) &&
	     !(args->flags & AMDGPU_GEM_USERPTR_REGISTER)) {

		/* if we want to write to it we must install a MMU notifier */
		return -EACCES;
	}

	/* create a gem object to contain this object in */
	r = amdgpu_gem_object_create(adev, args->size, 0, AMDGPU_GEM_DOMAIN_CPU,
				     0, ttm_bo_type_device, NULL, &gobj, fpriv->xcp_id + 1);
	if (r)
		return r;

	bo = gem_to_amdgpu_bo(gobj);
	bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT;
	bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT;
	r = amdgpu_ttm_tt_set_userptr(&bo->tbo, args->addr, args->flags);
	if (r)
		goto release_object;

	r = amdgpu_hmm_register(bo, args->addr);
	if (r)
		goto release_object;

	if (args->flags & AMDGPU_GEM_USERPTR_VALIDATE) {
		r = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages,
						 &range);
		if (r)
			goto release_object;

		r = amdgpu_bo_reserve(bo, true);
		if (r)
			goto user_pages_done;

		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
		amdgpu_bo_unreserve(bo);
		if (r)
			goto user_pages_done;
	}

	r = drm_gem_handle_create(filp, gobj, &handle);
	if (r)
		goto user_pages_done;

	args->handle = handle;

user_pages_done:
	if (args->flags & AMDGPU_GEM_USERPTR_VALIDATE)
		amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, range);

release_object:
	drm_gem_object_put(gobj);

	return r;
}

int amdgpu_mode_dumb_mmap(struct drm_file *filp,
			  struct drm_device *dev,
			  uint32_t handle, uint64_t *offset_p)
{
	struct drm_gem_object *gobj;
	struct amdgpu_bo *robj;

	gobj = drm_gem_object_lookup(filp, handle);
	if (!gobj)
		return -ENOENT;

	robj = gem_to_amdgpu_bo(gobj);
	if (amdgpu_ttm_tt_get_usermm(robj->tbo.ttm) ||
	    (robj->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)) {
		drm_gem_object_put(gobj);
		return -EPERM;
	}
	*offset_p = amdgpu_bo_mmap_offset(robj);
	drm_gem_object_put(gobj);
	return 0;
}

int amdgpu_gem_mmap_ioctl(struct drm_device *dev, void *data,
			  struct drm_file *filp)
{
	union drm_amdgpu_gem_mmap *args = data;
	uint32_t handle = args->in.handle;

	memset(args, 0, sizeof(*args));
	return amdgpu_mode_dumb_mmap(filp, dev, handle, &args->out.addr_ptr);
}

/**
 * amdgpu_gem_timeout - calculate jiffies timeout from absolute value
 *
 * @timeout_ns: timeout in ns
 *
 * Calculate the timeout in jiffies from an absolute timeout in ns.
 */
unsigned long amdgpu_gem_timeout(uint64_t timeout_ns)
{
	unsigned long timeout_jiffies;
	ktime_t timeout;

	/* clamp timeout if it's to large */
	if (((int64_t)timeout_ns) < 0)
		return MAX_SCHEDULE_TIMEOUT;

	timeout = ktime_sub(ns_to_ktime(timeout_ns), ktime_get());
	if (ktime_to_ns(timeout) < 0)
		return 0;

	timeout_jiffies = nsecs_to_jiffies(ktime_to_ns(timeout));
	/*  clamp timeout to avoid unsigned-> signed overflow */
	if (timeout_jiffies > MAX_SCHEDULE_TIMEOUT)
		return MAX_SCHEDULE_TIMEOUT - 1;

	return timeout_jiffies;
}

int amdgpu_gem_wait_idle_ioctl(struct drm_device *dev, void *data,
			      struct drm_file *filp)
{
	union drm_amdgpu_gem_wait_idle *args = data;
	struct drm_gem_object *gobj;
	struct amdgpu_bo *robj;
	uint32_t handle = args->in.handle;
	unsigned long timeout = amdgpu_gem_timeout(args->in.timeout);
	int r = 0;
	long ret;

	gobj = drm_gem_object_lookup(filp, handle);
	if (!gobj)
		return -ENOENT;

	robj = gem_to_amdgpu_bo(gobj);
	ret = dma_resv_wait_timeout(robj->tbo.base.resv, DMA_RESV_USAGE_READ,
				    true, timeout);

	/* ret == 0 means not signaled,
	 * ret > 0 means signaled
	 * ret < 0 means interrupted before timeout
	 */
	if (ret >= 0) {
		memset(args, 0, sizeof(*args));
		args->out.status = (ret == 0);
	} else
		r = ret;

	drm_gem_object_put(gobj);
	return r;
}

int amdgpu_gem_metadata_ioctl(struct drm_device *dev, void *data,
				struct drm_file *filp)
{
	struct drm_amdgpu_gem_metadata *args = data;
	struct drm_gem_object *gobj;
	struct amdgpu_bo *robj;
	int r = -1;

	DRM_DEBUG("%d\n", args->handle);
	gobj = drm_gem_object_lookup(filp, args->handle);
	if (gobj == NULL)
		return -ENOENT;
	robj = gem_to_amdgpu_bo(gobj);

	r = amdgpu_bo_reserve(robj, false);
	if (unlikely(r != 0))
		goto out;

	if (args->op == AMDGPU_GEM_METADATA_OP_GET_METADATA) {
		amdgpu_bo_get_tiling_flags(robj, &args->data.tiling_info);
		r = amdgpu_bo_get_metadata(robj, args->data.data,
					   sizeof(args->data.data),
					   &args->data.data_size_bytes,
					   &args->data.flags);
	} else if (args->op == AMDGPU_GEM_METADATA_OP_SET_METADATA) {
		if (args->data.data_size_bytes > sizeof(args->data.data)) {
			r = -EINVAL;
			goto unreserve;
		}
		r = amdgpu_bo_set_tiling_flags(robj, args->data.tiling_info);
		if (!r)
			r = amdgpu_bo_set_metadata(robj, args->data.data,
						   args->data.data_size_bytes,
						   args->data.flags);
	}

unreserve:
	amdgpu_bo_unreserve(robj);
out:
	drm_gem_object_put(gobj);
	return r;
}

/**
 * amdgpu_gem_va_update_vm -update the bo_va in its VM
 *
 * @adev: amdgpu_device pointer
 * @vm: vm to update
 * @bo_va: bo_va to update
 * @operation: map, unmap or clear
 *
 * Update the bo_va directly after setting its address. Errors are not
 * vital here, so they are not reported back to userspace.
 */
static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
				    struct amdgpu_vm *vm,
				    struct amdgpu_bo_va *bo_va,
				    uint32_t operation)
{
	int r;

	if (!amdgpu_vm_ready(vm))
		return;

	r = amdgpu_vm_clear_freed(adev, vm, NULL);
	if (r)
		goto error;

	if (operation == AMDGPU_VA_OP_MAP ||
	    operation == AMDGPU_VA_OP_REPLACE) {
		r = amdgpu_vm_bo_update(adev, bo_va, false);
		if (r)
			goto error;
	}

	r = amdgpu_vm_update_pdes(adev, vm, false);

error:
	if (r && r != -ERESTARTSYS)
		DRM_ERROR("Couldn't update BO_VA (%d)\n", r);
}

/**
 * amdgpu_gem_va_map_flags - map GEM UAPI flags into hardware flags
 *
 * @adev: amdgpu_device pointer
 * @flags: GEM UAPI flags
 *
 * Returns the GEM UAPI flags mapped into hardware for the ASIC.
 */
uint64_t amdgpu_gem_va_map_flags(struct amdgpu_device *adev, uint32_t flags)
{
	uint64_t pte_flag = 0;

	if (flags & AMDGPU_VM_PAGE_EXECUTABLE)
		pte_flag |= AMDGPU_PTE_EXECUTABLE;
	if (flags & AMDGPU_VM_PAGE_READABLE)
		pte_flag |= AMDGPU_PTE_READABLE;
	if (flags & AMDGPU_VM_PAGE_WRITEABLE)
		pte_flag |= AMDGPU_PTE_WRITEABLE;
	if (flags & AMDGPU_VM_PAGE_PRT)
		pte_flag |= AMDGPU_PTE_PRT;
	if (flags & AMDGPU_VM_PAGE_NOALLOC)
		pte_flag |= AMDGPU_PTE_NOALLOC;

	if (adev->gmc.gmc_funcs->map_mtype)
		pte_flag |= amdgpu_gmc_map_mtype(adev,
						 flags & AMDGPU_VM_MTYPE_MASK);

	return pte_flag;
}

int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
			  struct drm_file *filp)
{
	const uint32_t valid_flags = AMDGPU_VM_DELAY_UPDATE |
		AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE |
		AMDGPU_VM_PAGE_EXECUTABLE | AMDGPU_VM_MTYPE_MASK |
		AMDGPU_VM_PAGE_NOALLOC;
	const uint32_t prt_flags = AMDGPU_VM_DELAY_UPDATE |
		AMDGPU_VM_PAGE_PRT;

	struct drm_amdgpu_gem_va *args = data;
	struct drm_gem_object *gobj;
	struct amdgpu_device *adev = drm_to_adev(dev);
	struct amdgpu_fpriv *fpriv = filp->driver_priv;
	struct amdgpu_bo *abo;
	struct amdgpu_bo_va *bo_va;
	struct drm_exec exec;
	uint64_t va_flags;
	uint64_t vm_size;
	int r = 0;

	if (args->va_address < AMDGPU_VA_RESERVED_BOTTOM) {
		dev_dbg(dev->dev,
			"va_address 0x%llx is in reserved area 0x%llx\n",
			args->va_address, AMDGPU_VA_RESERVED_BOTTOM);
		return -EINVAL;
	}

	if (args->va_address >= AMDGPU_GMC_HOLE_START &&
	    args->va_address < AMDGPU_GMC_HOLE_END) {
		dev_dbg(dev->dev,
			"va_address 0x%llx is in VA hole 0x%llx-0x%llx\n",
			args->va_address, AMDGPU_GMC_HOLE_START,
			AMDGPU_GMC_HOLE_END);
		return -EINVAL;
	}

	args->va_address &= AMDGPU_GMC_HOLE_MASK;

	vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE;
	vm_size -= AMDGPU_VA_RESERVED_TOP;
	if (args->va_address + args->map_size > vm_size) {
		dev_dbg(dev->dev,
			"va_address 0x%llx is in top reserved area 0x%llx\n",
			args->va_address + args->map_size, vm_size);
		return -EINVAL;
	}

	if ((args->flags & ~valid_flags) && (args->flags & ~prt_flags)) {
		dev_dbg(dev->dev, "invalid flags combination 0x%08X\n",
			args->flags);
		return -EINVAL;
	}

	switch (args->operation) {
	case AMDGPU_VA_OP_MAP:
	case AMDGPU_VA_OP_UNMAP:
	case AMDGPU_VA_OP_CLEAR:
	case AMDGPU_VA_OP_REPLACE:
		break;
	default:
		dev_dbg(dev->dev, "unsupported operation %d\n",
			args->operation);
		return -EINVAL;
	}

	if ((args->operation != AMDGPU_VA_OP_CLEAR) &&
	    !(args->flags & AMDGPU_VM_PAGE_PRT)) {
		gobj = drm_gem_object_lookup(filp, args->handle);
		if (gobj == NULL)
			return -ENOENT;
		abo = gem_to_amdgpu_bo(gobj);
	} else {
		gobj = NULL;
		abo = NULL;
	}

	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT |
		      DRM_EXEC_IGNORE_DUPLICATES, 0);
	drm_exec_until_all_locked(&exec) {
		if (gobj) {
			r = drm_exec_lock_obj(&exec, gobj);
			drm_exec_retry_on_contention(&exec);
			if (unlikely(r))
				goto error;
		}

		r = amdgpu_vm_lock_pd(&fpriv->vm, &exec, 2);
		drm_exec_retry_on_contention(&exec);
		if (unlikely(r))
			goto error;
	}

	if (abo) {
		bo_va = amdgpu_vm_bo_find(&fpriv->vm, abo);
		if (!bo_va) {
			r = -ENOENT;
			goto error;
		}
	} else if (args->operation != AMDGPU_VA_OP_CLEAR) {
		bo_va = fpriv->prt_va;
	} else {
		bo_va = NULL;
	}

	switch (args->operation) {
	case AMDGPU_VA_OP_MAP:
		va_flags = amdgpu_gem_va_map_flags(adev, args->flags);
		r = amdgpu_vm_bo_map(adev, bo_va, args->va_address,
				     args->offset_in_bo, args->map_size,
				     va_flags);
		break;
	case AMDGPU_VA_OP_UNMAP:
		r = amdgpu_vm_bo_unmap(adev, bo_va, args->va_address);
		break;

	case AMDGPU_VA_OP_CLEAR:
		r = amdgpu_vm_bo_clear_mappings(adev, &fpriv->vm,
						args->va_address,
						args->map_size);
		break;
	case AMDGPU_VA_OP_REPLACE:
		va_flags = amdgpu_gem_va_map_flags(adev, args->flags);
		r = amdgpu_vm_bo_replace_map(adev, bo_va, args->va_address,
					     args->offset_in_bo, args->map_size,
					     va_flags);
		break;
	default:
		break;
	}
	if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE) && !adev->debug_vm)
		amdgpu_gem_va_update_vm(adev, &fpriv->vm, bo_va,
					args->operation);

error:
	drm_exec_fini(&exec);
	drm_gem_object_put(gobj);
	return r;
}

int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
			struct drm_file *filp)
{
	struct amdgpu_device *adev = drm_to_adev(dev);
	struct drm_amdgpu_gem_op *args = data;
	struct drm_gem_object *gobj;
	struct amdgpu_vm_bo_base *base;
	struct amdgpu_bo *robj;
	int r;

	gobj = drm_gem_object_lookup(filp, args->handle);
	if (!gobj)
		return -ENOENT;

	robj = gem_to_amdgpu_bo(gobj);

	r = amdgpu_bo_reserve(robj, false);
	if (unlikely(r))
		goto out;

	switch (args->op) {
	case AMDGPU_GEM_OP_GET_GEM_CREATE_INFO: {
		struct drm_amdgpu_gem_create_in info;
		void __user *out = u64_to_user_ptr(args->value);

		info.bo_size = robj->tbo.base.size;
		info.alignment = robj->tbo.page_alignment << PAGE_SHIFT;
		info.domains = robj->preferred_domains;
		info.domain_flags = robj->flags;
		amdgpu_bo_unreserve(robj);
		if (copy_to_user(out, &info, sizeof(info)))
			r = -EFAULT;
		break;
	}
	case AMDGPU_GEM_OP_SET_PLACEMENT:
		if (robj->tbo.base.import_attach &&
		    args->value & AMDGPU_GEM_DOMAIN_VRAM) {
			r = -EINVAL;
			amdgpu_bo_unreserve(robj);
			break;
		}
		if (amdgpu_ttm_tt_get_usermm(robj->tbo.ttm)) {
			r = -EPERM;
			amdgpu_bo_unreserve(robj);
			break;
		}
		for (base = robj->vm_bo; base; base = base->next)
			if (amdgpu_xgmi_same_hive(amdgpu_ttm_adev(robj->tbo.bdev),
				amdgpu_ttm_adev(base->vm->root.bo->tbo.bdev))) {
				r = -EINVAL;
				amdgpu_bo_unreserve(robj);
				goto out;
			}


		robj->preferred_domains = args->value & (AMDGPU_GEM_DOMAIN_VRAM |
							AMDGPU_GEM_DOMAIN_GTT |
							AMDGPU_GEM_DOMAIN_CPU);
		robj->allowed_domains = robj->preferred_domains;
		if (robj->allowed_domains == AMDGPU_GEM_DOMAIN_VRAM)
			robj->allowed_domains |= AMDGPU_GEM_DOMAIN_GTT;

		if (robj->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID)
			amdgpu_vm_bo_invalidate(adev, robj, true);

		amdgpu_bo_unreserve(robj);
		break;
	default:
		amdgpu_bo_unreserve(robj);
		r = -EINVAL;
	}

out:
	drm_gem_object_put(gobj);
	return r;
}

static int amdgpu_gem_align_pitch(struct amdgpu_device *adev,
				  int width,
				  int cpp,
				  bool tiled)
{
	int aligned = width;
	int pitch_mask = 0;

	switch (cpp) {
	case 1:
		pitch_mask = 255;
		break;
	case 2:
		pitch_mask = 127;
		break;
	case 3:
	case 4:
		pitch_mask = 63;
		break;
	}

	aligned += pitch_mask;
	aligned &= ~pitch_mask;
	return aligned * cpp;
}

int amdgpu_mode_dumb_create(struct drm_file *file_priv,
			    struct drm_device *dev,
			    struct drm_mode_create_dumb *args)
{
	struct amdgpu_device *adev = drm_to_adev(dev);
	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
	struct drm_gem_object *gobj;
	uint32_t handle;
	u64 flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
		    AMDGPU_GEM_CREATE_CPU_GTT_USWC |
		    AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
	u32 domain;
	int r;

	/*
	 * The buffer returned from this function should be cleared, but
	 * it can only be done if the ring is enabled or we'll fail to
	 * create the buffer.
	 */
	if (adev->mman.buffer_funcs_enabled)
		flags |= AMDGPU_GEM_CREATE_VRAM_CLEARED;

	args->pitch = amdgpu_gem_align_pitch(adev, args->width,
					     DIV_ROUND_UP(args->bpp, 8), 0);
	args->size = (u64)args->pitch * args->height;
	args->size = ALIGN(args->size, PAGE_SIZE);
	domain = amdgpu_bo_get_preferred_domain(adev,
				amdgpu_display_supported_domains(adev, flags));
	r = amdgpu_gem_object_create(adev, args->size, 0, domain, flags,
				     ttm_bo_type_device, NULL, &gobj, fpriv->xcp_id + 1);
	if (r)
		return -ENOMEM;

	r = drm_gem_handle_create(file_priv, gobj, &handle);
	/* drop reference from allocate - handle holds it now */
	drm_gem_object_put(gobj);
	if (r)
		return r;

	args->handle = handle;
	return 0;
}

#if defined(CONFIG_DEBUG_FS)
static int amdgpu_debugfs_gem_info_show(struct seq_file *m, void *unused)
{
	struct amdgpu_device *adev = m->private;
	struct drm_device *dev = adev_to_drm(adev);
	struct drm_file *file;
	int r;

	r = mutex_lock_interruptible(&dev->filelist_mutex);
	if (r)
		return r;

	list_for_each_entry(file, &dev->filelist, lhead) {
		struct task_struct *task;
		struct drm_gem_object *gobj;
		struct pid *pid;
		int id;

		/*
		 * Although we have a valid reference on file->pid, that does
		 * not guarantee that the task_struct who called get_pid() is
		 * still alive (e.g. get_pid(current) => fork() => exit()).
		 * Therefore, we need to protect this ->comm access using RCU.
		 */
		rcu_read_lock();
		pid = rcu_dereference(file->pid);
		task = pid_task(pid, PIDTYPE_TGID);
		seq_printf(m, "pid %8d command %s:\n", pid_nr(pid),
			   task ? task->comm : "<unknown>");
		rcu_read_unlock();

		spin_lock(&file->table_lock);
		idr_for_each_entry(&file->object_idr, gobj, id) {
			struct amdgpu_bo *bo = gem_to_amdgpu_bo(gobj);

			amdgpu_bo_print_info(id, bo, m);
		}
		spin_unlock(&file->table_lock);
	}

	mutex_unlock(&dev->filelist_mutex);
	return 0;
}

DEFINE_SHOW_ATTRIBUTE(amdgpu_debugfs_gem_info);

#endif

void amdgpu_debugfs_gem_init(struct amdgpu_device *adev)
{
#if defined(CONFIG_DEBUG_FS)
	struct drm_minor *minor = adev_to_drm(adev)->primary;
	struct dentry *root = minor->debugfs_root;

	debugfs_create_file("amdgpu_gem_info", 0444, root, adev,
			    &amdgpu_debugfs_gem_info_fops);
#endif
}