summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/radeon/radeon_ttm.c
blob: 5c65b6dfb99af7fbe922fe90b682ee88d8d6ff3e (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
/*
 * 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/debugfs.h>
#include <linux/dma-mapping.h>
#include <linux/pagemap.h>
#include <linux/pci.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/swap.h>

#include <drm/drm_device.h>
#include <drm/drm_file.h>
#include <drm/drm_prime.h>
#include <drm/radeon_drm.h>
#include <drm/ttm/ttm_bo.h>
#include <drm/ttm/ttm_placement.h>
#include <drm/ttm/ttm_range_manager.h>
#include <drm/ttm/ttm_tt.h>

#include "radeon_reg.h"
#include "radeon.h"
#include "radeon_ttm.h"

static void radeon_ttm_debugfs_init(struct radeon_device *rdev);

static int radeon_ttm_tt_bind(struct ttm_device *bdev, struct ttm_tt *ttm,
			      struct ttm_resource *bo_mem);
static void radeon_ttm_tt_unbind(struct ttm_device *bdev, struct ttm_tt *ttm);

struct radeon_device *radeon_get_rdev(struct ttm_device *bdev)
{
	struct radeon_mman *mman;
	struct radeon_device *rdev;

	mman = container_of(bdev, struct radeon_mman, bdev);
	rdev = container_of(mman, struct radeon_device, mman);
	return rdev;
}

static int radeon_ttm_init_vram(struct radeon_device *rdev)
{
	return ttm_range_man_init(&rdev->mman.bdev, TTM_PL_VRAM,
				  false, rdev->mc.real_vram_size >> PAGE_SHIFT);
}

static int radeon_ttm_init_gtt(struct radeon_device *rdev)
{
	return ttm_range_man_init(&rdev->mman.bdev, TTM_PL_TT,
				  true, rdev->mc.gtt_size >> PAGE_SHIFT);
}

static void radeon_evict_flags(struct ttm_buffer_object *bo,
				struct ttm_placement *placement)
{
	static const struct ttm_place placements = {
		.fpfn = 0,
		.lpfn = 0,
		.mem_type = TTM_PL_SYSTEM,
		.flags = 0
	};

	struct radeon_bo *rbo;

	if (!radeon_ttm_bo_is_radeon_bo(bo)) {
		placement->placement = &placements;
		placement->num_placement = 1;
		return;
	}
	rbo = container_of(bo, struct radeon_bo, tbo);
	switch (bo->resource->mem_type) {
	case TTM_PL_VRAM:
		if (rbo->rdev->ring[radeon_copy_ring_index(rbo->rdev)].ready == false)
			radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_CPU);
		else if (rbo->rdev->mc.visible_vram_size < rbo->rdev->mc.real_vram_size &&
			 bo->resource->start < (rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT)) {
			unsigned fpfn = rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
			int i;

			/* Try evicting to the CPU inaccessible part of VRAM
			 * first, but only set GTT as busy placement, so this
			 * BO will be evicted to GTT rather than causing other
			 * BOs to be evicted from VRAM
			 */
			radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM |
							 RADEON_GEM_DOMAIN_GTT);
			for (i = 0; i < rbo->placement.num_placement; i++) {
				if (rbo->placements[i].mem_type == TTM_PL_VRAM) {
					if (rbo->placements[i].fpfn < fpfn)
						rbo->placements[i].fpfn = fpfn;
					rbo->placements[0].flags |= TTM_PL_FLAG_DESIRED;
				}
			}
		} else
			radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT);
		break;
	case TTM_PL_TT:
	default:
		radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_CPU);
	}
	*placement = rbo->placement;
}

static int radeon_move_blit(struct ttm_buffer_object *bo,
			bool evict,
			struct ttm_resource *new_mem,
			struct ttm_resource *old_mem)
{
	struct radeon_device *rdev;
	uint64_t old_start, new_start;
	struct radeon_fence *fence;
	unsigned num_pages;
	int r, ridx;

	rdev = radeon_get_rdev(bo->bdev);
	ridx = radeon_copy_ring_index(rdev);
	old_start = (u64)old_mem->start << PAGE_SHIFT;
	new_start = (u64)new_mem->start << PAGE_SHIFT;

	switch (old_mem->mem_type) {
	case TTM_PL_VRAM:
		old_start += rdev->mc.vram_start;
		break;
	case TTM_PL_TT:
		old_start += rdev->mc.gtt_start;
		break;
	default:
		DRM_ERROR("Unknown placement %d\n", old_mem->mem_type);
		return -EINVAL;
	}
	switch (new_mem->mem_type) {
	case TTM_PL_VRAM:
		new_start += rdev->mc.vram_start;
		break;
	case TTM_PL_TT:
		new_start += rdev->mc.gtt_start;
		break;
	default:
		DRM_ERROR("Unknown placement %d\n", old_mem->mem_type);
		return -EINVAL;
	}
	if (!rdev->ring[ridx].ready) {
		DRM_ERROR("Trying to move memory with ring turned off.\n");
		return -EINVAL;
	}

	BUILD_BUG_ON((PAGE_SIZE % RADEON_GPU_PAGE_SIZE) != 0);

	num_pages = PFN_UP(new_mem->size) * (PAGE_SIZE / RADEON_GPU_PAGE_SIZE);
	fence = radeon_copy(rdev, old_start, new_start, num_pages, bo->base.resv);
	if (IS_ERR(fence))
		return PTR_ERR(fence);

	r = ttm_bo_move_accel_cleanup(bo, &fence->base, evict, false, new_mem);
	radeon_fence_unref(&fence);
	return r;
}

static int radeon_bo_move(struct ttm_buffer_object *bo, bool evict,
			  struct ttm_operation_ctx *ctx,
			  struct ttm_resource *new_mem,
			  struct ttm_place *hop)
{
	struct ttm_resource *old_mem = bo->resource;
	struct radeon_device *rdev;
	int r;

	if (new_mem->mem_type == TTM_PL_TT) {
		r = radeon_ttm_tt_bind(bo->bdev, bo->ttm, new_mem);
		if (r)
			return r;
	}

	r = ttm_bo_wait_ctx(bo, ctx);
	if (r)
		return r;

	rdev = radeon_get_rdev(bo->bdev);
	if (!old_mem || (old_mem->mem_type == TTM_PL_SYSTEM &&
			 bo->ttm == NULL)) {
		ttm_bo_move_null(bo, new_mem);
		goto out;
	}
	if (old_mem->mem_type == TTM_PL_SYSTEM &&
	    new_mem->mem_type == TTM_PL_TT) {
		ttm_bo_move_null(bo, new_mem);
		goto out;
	}

	if (old_mem->mem_type == TTM_PL_TT &&
	    new_mem->mem_type == TTM_PL_SYSTEM) {
		radeon_ttm_tt_unbind(bo->bdev, bo->ttm);
		ttm_resource_free(bo, &bo->resource);
		ttm_bo_assign_mem(bo, new_mem);
		goto out;
	}
	if (rdev->ring[radeon_copy_ring_index(rdev)].ready &&
	    rdev->asic->copy.copy != NULL) {
		if ((old_mem->mem_type == TTM_PL_SYSTEM &&
		     new_mem->mem_type == TTM_PL_VRAM) ||
		    (old_mem->mem_type == TTM_PL_VRAM &&
		     new_mem->mem_type == TTM_PL_SYSTEM)) {
			hop->fpfn = 0;
			hop->lpfn = 0;
			hop->mem_type = TTM_PL_TT;
			hop->flags = 0;
			return -EMULTIHOP;
		}

		r = radeon_move_blit(bo, evict, new_mem, old_mem);
	} else {
		r = -ENODEV;
	}

	if (r) {
		r = ttm_bo_move_memcpy(bo, ctx, new_mem);
		if (r)
			return r;
	}

out:
	/* update statistics */
	atomic64_add(bo->base.size, &rdev->num_bytes_moved);
	radeon_bo_move_notify(bo);
	return 0;
}

static int radeon_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *mem)
{
	struct radeon_device *rdev = radeon_get_rdev(bdev);
	size_t bus_size = (size_t)mem->size;

	switch (mem->mem_type) {
	case TTM_PL_SYSTEM:
		/* system memory */
		return 0;
	case TTM_PL_TT:
#if IS_ENABLED(CONFIG_AGP)
		if (rdev->flags & RADEON_IS_AGP) {
			/* RADEON_IS_AGP is set only if AGP is active */
			mem->bus.offset = (mem->start << PAGE_SHIFT) +
				rdev->mc.agp_base;
			mem->bus.is_iomem = !rdev->agp->cant_use_aperture;
			mem->bus.caching = ttm_write_combined;
		}
#endif
		break;
	case TTM_PL_VRAM:
		mem->bus.offset = mem->start << PAGE_SHIFT;
		/* check if it's visible */
		if ((mem->bus.offset + bus_size) > rdev->mc.visible_vram_size)
			return -EINVAL;
		mem->bus.offset += rdev->mc.aper_base;
		mem->bus.is_iomem = true;
		mem->bus.caching = ttm_write_combined;
#ifdef __alpha__
		/*
		 * Alpha: use bus.addr to hold the ioremap() return,
		 * so we can modify bus.base below.
		 */
		mem->bus.addr = ioremap_wc(mem->bus.offset, bus_size);
		if (!mem->bus.addr)
			return -ENOMEM;

		/*
		 * Alpha: Use just the bus offset plus
		 * the hose/domain memory base for bus.base.
		 * It then can be used to build PTEs for VRAM
		 * access, as done in ttm_bo_vm_fault().
		 */
		mem->bus.offset = (mem->bus.offset & 0x0ffffffffUL) +
			rdev->hose->dense_mem_base;
#endif
		break;
	default:
		return -EINVAL;
	}
	return 0;
}

/*
 * TTM backend functions.
 */
struct radeon_ttm_tt {
	struct ttm_tt		ttm;
	u64				offset;

	uint64_t			userptr;
	struct mm_struct		*usermm;
	uint32_t			userflags;
	bool bound;
};

/* prepare the sg table with the user pages */
static int radeon_ttm_tt_pin_userptr(struct ttm_device *bdev, struct ttm_tt *ttm)
{
	struct radeon_device *rdev = radeon_get_rdev(bdev);
	struct radeon_ttm_tt *gtt = (void *)ttm;
	unsigned pinned = 0;
	int r;

	int write = !(gtt->userflags & RADEON_GEM_USERPTR_READONLY);
	enum dma_data_direction direction = write ?
		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;

	if (current->mm != gtt->usermm)
		return -EPERM;

	if (gtt->userflags & RADEON_GEM_USERPTR_ANONONLY) {
		/* check that we only pin down anonymous memory
		   to prevent problems with writeback */
		unsigned long end = gtt->userptr + (u64)ttm->num_pages * PAGE_SIZE;
		struct vm_area_struct *vma;
		vma = find_vma(gtt->usermm, gtt->userptr);
		if (!vma || vma->vm_file || vma->vm_end < end)
			return -EPERM;
	}

	do {
		unsigned num_pages = ttm->num_pages - pinned;
		uint64_t userptr = gtt->userptr + pinned * PAGE_SIZE;
		struct page **pages = ttm->pages + pinned;

		r = get_user_pages(userptr, num_pages, write ? FOLL_WRITE : 0,
				   pages);
		if (r < 0)
			goto release_pages;

		pinned += r;

	} while (pinned < ttm->num_pages);

	r = sg_alloc_table_from_pages(ttm->sg, ttm->pages, ttm->num_pages, 0,
				      (u64)ttm->num_pages << PAGE_SHIFT,
				      GFP_KERNEL);
	if (r)
		goto release_sg;

	r = dma_map_sgtable(rdev->dev, ttm->sg, direction, 0);
	if (r)
		goto release_sg;

	drm_prime_sg_to_dma_addr_array(ttm->sg, gtt->ttm.dma_address,
				       ttm->num_pages);

	return 0;

release_sg:
	kfree(ttm->sg);

release_pages:
	release_pages(ttm->pages, pinned);
	return r;
}

static void radeon_ttm_tt_unpin_userptr(struct ttm_device *bdev, struct ttm_tt *ttm)
{
	struct radeon_device *rdev = radeon_get_rdev(bdev);
	struct radeon_ttm_tt *gtt = (void *)ttm;
	struct sg_page_iter sg_iter;

	int write = !(gtt->userflags & RADEON_GEM_USERPTR_READONLY);
	enum dma_data_direction direction = write ?
		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;

	/* double check that we don't free the table twice */
	if (!ttm->sg || !ttm->sg->sgl)
		return;

	/* free the sg table and pages again */
	dma_unmap_sgtable(rdev->dev, ttm->sg, direction, 0);

	for_each_sgtable_page(ttm->sg, &sg_iter, 0) {
		struct page *page = sg_page_iter_page(&sg_iter);
		if (!(gtt->userflags & RADEON_GEM_USERPTR_READONLY))
			set_page_dirty(page);

		mark_page_accessed(page);
		put_page(page);
	}

	sg_free_table(ttm->sg);
}

static bool radeon_ttm_backend_is_bound(struct ttm_tt *ttm)
{
	struct radeon_ttm_tt *gtt = (void*)ttm;

	return (gtt->bound);
}

static int radeon_ttm_backend_bind(struct ttm_device *bdev,
				   struct ttm_tt *ttm,
				   struct ttm_resource *bo_mem)
{
	struct radeon_ttm_tt *gtt = (void*)ttm;
	struct radeon_device *rdev = radeon_get_rdev(bdev);
	uint32_t flags = RADEON_GART_PAGE_VALID | RADEON_GART_PAGE_READ |
		RADEON_GART_PAGE_WRITE;
	int r;

	if (gtt->bound)
		return 0;

	if (gtt->userptr) {
		radeon_ttm_tt_pin_userptr(bdev, ttm);
		flags &= ~RADEON_GART_PAGE_WRITE;
	}

	gtt->offset = (unsigned long)(bo_mem->start << PAGE_SHIFT);
	if (!ttm->num_pages) {
		WARN(1, "nothing to bind %u pages for mreg %p back %p!\n",
		     ttm->num_pages, bo_mem, ttm);
	}
	if (ttm->caching == ttm_cached)
		flags |= RADEON_GART_PAGE_SNOOP;
	r = radeon_gart_bind(rdev, gtt->offset, ttm->num_pages,
			     ttm->pages, gtt->ttm.dma_address, flags);
	if (r) {
		DRM_ERROR("failed to bind %u pages at 0x%08X\n",
			  ttm->num_pages, (unsigned)gtt->offset);
		return r;
	}
	gtt->bound = true;
	return 0;
}

static void radeon_ttm_backend_unbind(struct ttm_device *bdev, struct ttm_tt *ttm)
{
	struct radeon_ttm_tt *gtt = (void *)ttm;
	struct radeon_device *rdev = radeon_get_rdev(bdev);

	if (gtt->userptr)
		radeon_ttm_tt_unpin_userptr(bdev, ttm);

	if (!gtt->bound)
		return;

	radeon_gart_unbind(rdev, gtt->offset, ttm->num_pages);

	gtt->bound = false;
}

static void radeon_ttm_backend_destroy(struct ttm_device *bdev, struct ttm_tt *ttm)
{
	struct radeon_ttm_tt *gtt = (void *)ttm;

	ttm_tt_fini(&gtt->ttm);
	kfree(gtt);
}

static struct ttm_tt *radeon_ttm_tt_create(struct ttm_buffer_object *bo,
					   uint32_t page_flags)
{
	struct radeon_ttm_tt *gtt;
	enum ttm_caching caching;
	struct radeon_bo *rbo;
#if IS_ENABLED(CONFIG_AGP)
	struct radeon_device *rdev = radeon_get_rdev(bo->bdev);

	if (rdev->flags & RADEON_IS_AGP) {
		return ttm_agp_tt_create(bo, rdev->agp->bridge, page_flags);
	}
#endif
	rbo = container_of(bo, struct radeon_bo, tbo);

	gtt = kzalloc(sizeof(struct radeon_ttm_tt), GFP_KERNEL);
	if (gtt == NULL) {
		return NULL;
	}

	if (rbo->flags & RADEON_GEM_GTT_UC)
		caching = ttm_uncached;
	else if (rbo->flags & RADEON_GEM_GTT_WC)
		caching = ttm_write_combined;
	else
		caching = ttm_cached;

	if (ttm_sg_tt_init(&gtt->ttm, bo, page_flags, caching)) {
		kfree(gtt);
		return NULL;
	}
	return &gtt->ttm;
}

static struct radeon_ttm_tt *radeon_ttm_tt_to_gtt(struct radeon_device *rdev,
						  struct ttm_tt *ttm)
{
#if IS_ENABLED(CONFIG_AGP)
	if (rdev->flags & RADEON_IS_AGP)
		return NULL;
#endif

	if (!ttm)
		return NULL;
	return container_of(ttm, struct radeon_ttm_tt, ttm);
}

static int radeon_ttm_tt_populate(struct ttm_device *bdev,
				  struct ttm_tt *ttm,
				  struct ttm_operation_ctx *ctx)
{
	struct radeon_device *rdev = radeon_get_rdev(bdev);
	struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(rdev, ttm);
	bool slave = !!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL);

	if (gtt && gtt->userptr) {
		ttm->sg = kzalloc(sizeof(struct sg_table), GFP_KERNEL);
		if (!ttm->sg)
			return -ENOMEM;

		ttm->page_flags |= TTM_TT_FLAG_EXTERNAL;
		return 0;
	}

	if (slave && ttm->sg) {
		drm_prime_sg_to_dma_addr_array(ttm->sg, gtt->ttm.dma_address,
					       ttm->num_pages);
		return 0;
	}

	return ttm_pool_alloc(&rdev->mman.bdev.pool, ttm, ctx);
}

static void radeon_ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm)
{
	struct radeon_device *rdev = radeon_get_rdev(bdev);
	struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(rdev, ttm);
	bool slave = !!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL);

	radeon_ttm_tt_unbind(bdev, ttm);

	if (gtt && gtt->userptr) {
		kfree(ttm->sg);
		ttm->page_flags &= ~TTM_TT_FLAG_EXTERNAL;
		return;
	}

	if (slave)
		return;

	return ttm_pool_free(&rdev->mman.bdev.pool, ttm);
}

int radeon_ttm_tt_set_userptr(struct radeon_device *rdev,
			      struct ttm_tt *ttm, uint64_t addr,
			      uint32_t flags)
{
	struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(rdev, ttm);

	if (gtt == NULL)
		return -EINVAL;

	gtt->userptr = addr;
	gtt->usermm = current->mm;
	gtt->userflags = flags;
	return 0;
}

bool radeon_ttm_tt_is_bound(struct ttm_device *bdev,
			    struct ttm_tt *ttm)
{
#if IS_ENABLED(CONFIG_AGP)
	struct radeon_device *rdev = radeon_get_rdev(bdev);
	if (rdev->flags & RADEON_IS_AGP)
		return ttm_agp_is_bound(ttm);
#endif
	return radeon_ttm_backend_is_bound(ttm);
}

static int radeon_ttm_tt_bind(struct ttm_device *bdev,
			      struct ttm_tt *ttm,
			      struct ttm_resource *bo_mem)
{
#if IS_ENABLED(CONFIG_AGP)
	struct radeon_device *rdev = radeon_get_rdev(bdev);
#endif

	if (!bo_mem)
		return -EINVAL;
#if IS_ENABLED(CONFIG_AGP)
	if (rdev->flags & RADEON_IS_AGP)
		return ttm_agp_bind(ttm, bo_mem);
#endif

	return radeon_ttm_backend_bind(bdev, ttm, bo_mem);
}

static void radeon_ttm_tt_unbind(struct ttm_device *bdev,
				 struct ttm_tt *ttm)
{
#if IS_ENABLED(CONFIG_AGP)
	struct radeon_device *rdev = radeon_get_rdev(bdev);

	if (rdev->flags & RADEON_IS_AGP) {
		ttm_agp_unbind(ttm);
		return;
	}
#endif
	radeon_ttm_backend_unbind(bdev, ttm);
}

static void radeon_ttm_tt_destroy(struct ttm_device *bdev,
				  struct ttm_tt *ttm)
{
#if IS_ENABLED(CONFIG_AGP)
	struct radeon_device *rdev = radeon_get_rdev(bdev);

	if (rdev->flags & RADEON_IS_AGP) {
		ttm_agp_destroy(ttm);
		return;
	}
#endif
	radeon_ttm_backend_destroy(bdev, ttm);
}

bool radeon_ttm_tt_has_userptr(struct radeon_device *rdev,
			       struct ttm_tt *ttm)
{
	struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(rdev, ttm);

	if (gtt == NULL)
		return false;

	return !!gtt->userptr;
}

bool radeon_ttm_tt_is_readonly(struct radeon_device *rdev,
			       struct ttm_tt *ttm)
{
	struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(rdev, ttm);

	if (gtt == NULL)
		return false;

	return !!(gtt->userflags & RADEON_GEM_USERPTR_READONLY);
}

static struct ttm_device_funcs radeon_bo_driver = {
	.ttm_tt_create = &radeon_ttm_tt_create,
	.ttm_tt_populate = &radeon_ttm_tt_populate,
	.ttm_tt_unpopulate = &radeon_ttm_tt_unpopulate,
	.ttm_tt_destroy = &radeon_ttm_tt_destroy,
	.eviction_valuable = ttm_bo_eviction_valuable,
	.evict_flags = &radeon_evict_flags,
	.move = &radeon_bo_move,
	.io_mem_reserve = &radeon_ttm_io_mem_reserve,
};

int radeon_ttm_init(struct radeon_device *rdev)
{
	int r;

	/* No others user of address space so set it to 0 */
	r = ttm_device_init(&rdev->mman.bdev, &radeon_bo_driver, rdev->dev,
			       rdev->ddev->anon_inode->i_mapping,
			       rdev->ddev->vma_offset_manager,
			       rdev->need_swiotlb,
			       dma_addressing_limited(&rdev->pdev->dev));
	if (r) {
		DRM_ERROR("failed initializing buffer object driver(%d).\n", r);
		return r;
	}
	rdev->mman.initialized = true;

	r = radeon_ttm_init_vram(rdev);
	if (r) {
		DRM_ERROR("Failed initializing VRAM heap.\n");
		return r;
	}
	/* Change the size here instead of the init above so only lpfn is affected */
	radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);

	r = radeon_bo_create(rdev, 256 * 1024, PAGE_SIZE, true,
			     RADEON_GEM_DOMAIN_VRAM, 0, NULL,
			     NULL, &rdev->stolen_vga_memory);
	if (r) {
		return r;
	}
	r = radeon_bo_reserve(rdev->stolen_vga_memory, false);
	if (r)
		return r;
	r = radeon_bo_pin(rdev->stolen_vga_memory, RADEON_GEM_DOMAIN_VRAM, NULL);
	radeon_bo_unreserve(rdev->stolen_vga_memory);
	if (r) {
		radeon_bo_unref(&rdev->stolen_vga_memory);
		return r;
	}
	DRM_INFO("radeon: %uM of VRAM memory ready\n",
		 (unsigned) (rdev->mc.real_vram_size / (1024 * 1024)));

	r = radeon_ttm_init_gtt(rdev);
	if (r) {
		DRM_ERROR("Failed initializing GTT heap.\n");
		return r;
	}
	DRM_INFO("radeon: %uM of GTT memory ready.\n",
		 (unsigned)(rdev->mc.gtt_size / (1024 * 1024)));

	radeon_ttm_debugfs_init(rdev);

	return 0;
}

void radeon_ttm_fini(struct radeon_device *rdev)
{
	int r;

	if (!rdev->mman.initialized)
		return;

	if (rdev->stolen_vga_memory) {
		r = radeon_bo_reserve(rdev->stolen_vga_memory, false);
		if (r == 0) {
			radeon_bo_unpin(rdev->stolen_vga_memory);
			radeon_bo_unreserve(rdev->stolen_vga_memory);
		}
		radeon_bo_unref(&rdev->stolen_vga_memory);
	}
	ttm_range_man_fini(&rdev->mman.bdev, TTM_PL_VRAM);
	ttm_range_man_fini(&rdev->mman.bdev, TTM_PL_TT);
	ttm_device_fini(&rdev->mman.bdev);
	radeon_gart_fini(rdev);
	rdev->mman.initialized = false;
	DRM_INFO("radeon: ttm finalized\n");
}

/* this should only be called at bootup or when userspace
 * isn't running */
void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size)
{
	struct ttm_resource_manager *man;

	if (!rdev->mman.initialized)
		return;

	man = ttm_manager_type(&rdev->mman.bdev, TTM_PL_VRAM);
	/* this just adjusts TTM size idea, which sets lpfn to the correct value */
	man->size = size >> PAGE_SHIFT;
}

#if defined(CONFIG_DEBUG_FS)

static int radeon_ttm_page_pool_show(struct seq_file *m, void *data)
{
	struct radeon_device *rdev = m->private;

	return ttm_pool_debugfs(&rdev->mman.bdev.pool, m);
}

DEFINE_SHOW_ATTRIBUTE(radeon_ttm_page_pool);

static int radeon_ttm_vram_open(struct inode *inode, struct file *filep)
{
	struct radeon_device *rdev = inode->i_private;
	i_size_write(inode, rdev->mc.mc_vram_size);
	filep->private_data = inode->i_private;
	return 0;
}

static ssize_t radeon_ttm_vram_read(struct file *f, char __user *buf,
				    size_t size, loff_t *pos)
{
	struct radeon_device *rdev = f->private_data;
	ssize_t result = 0;
	int r;

	if (size & 0x3 || *pos & 0x3)
		return -EINVAL;

	while (size) {
		unsigned long flags;
		uint32_t value;

		if (*pos >= rdev->mc.mc_vram_size)
			return result;

		spin_lock_irqsave(&rdev->mmio_idx_lock, flags);
		WREG32(RADEON_MM_INDEX, ((uint32_t)*pos) | 0x80000000);
		if (rdev->family >= CHIP_CEDAR)
			WREG32(EVERGREEN_MM_INDEX_HI, *pos >> 31);
		value = RREG32(RADEON_MM_DATA);
		spin_unlock_irqrestore(&rdev->mmio_idx_lock, flags);

		r = put_user(value, (uint32_t __user *)buf);
		if (r)
			return r;

		result += 4;
		buf += 4;
		*pos += 4;
		size -= 4;
	}

	return result;
}

static const struct file_operations radeon_ttm_vram_fops = {
	.owner = THIS_MODULE,
	.open = radeon_ttm_vram_open,
	.read = radeon_ttm_vram_read,
	.llseek = default_llseek
};

static int radeon_ttm_gtt_open(struct inode *inode, struct file *filep)
{
	struct radeon_device *rdev = inode->i_private;
	i_size_write(inode, rdev->mc.gtt_size);
	filep->private_data = inode->i_private;
	return 0;
}

static ssize_t radeon_ttm_gtt_read(struct file *f, char __user *buf,
				   size_t size, loff_t *pos)
{
	struct radeon_device *rdev = f->private_data;
	ssize_t result = 0;
	int r;

	while (size) {
		loff_t p = *pos / PAGE_SIZE;
		unsigned off = *pos & ~PAGE_MASK;
		size_t cur_size = min_t(size_t, size, PAGE_SIZE - off);
		struct page *page;
		void *ptr;

		if (p >= rdev->gart.num_cpu_pages)
			return result;

		page = rdev->gart.pages[p];
		if (page) {
			ptr = kmap_local_page(page);
			ptr += off;

			r = copy_to_user(buf, ptr, cur_size);
			kunmap_local(ptr);
		} else
			r = clear_user(buf, cur_size);

		if (r)
			return -EFAULT;

		result += cur_size;
		buf += cur_size;
		*pos += cur_size;
		size -= cur_size;
	}

	return result;
}

static const struct file_operations radeon_ttm_gtt_fops = {
	.owner = THIS_MODULE,
	.open = radeon_ttm_gtt_open,
	.read = radeon_ttm_gtt_read,
	.llseek = default_llseek
};

#endif

static void radeon_ttm_debugfs_init(struct radeon_device *rdev)
{
#if defined(CONFIG_DEBUG_FS)
	struct drm_minor *minor = rdev->ddev->primary;
	struct dentry *root = minor->debugfs_root;

	debugfs_create_file("radeon_vram", 0444, root, rdev,
			    &radeon_ttm_vram_fops);
	debugfs_create_file("radeon_gtt", 0444, root, rdev,
			    &radeon_ttm_gtt_fops);
	debugfs_create_file("ttm_page_pool", 0444, root, rdev,
			    &radeon_ttm_page_pool_fops);
	ttm_resource_manager_create_debugfs(ttm_manager_type(&rdev->mman.bdev,
							     TTM_PL_VRAM),
					    root, "radeon_vram_mm");
	ttm_resource_manager_create_debugfs(ttm_manager_type(&rdev->mman.bdev,
							     TTM_PL_TT),
					    root, "radeon_gtt_mm");
#endif
}