aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/radeon/radeon_object.c
blob: a00cf17a051044314fbeb175bd8c6a0f637950a2 (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
/*
 * 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/radeon_drm.h>
#include "radeon.h"
#include "radeon_trace.h"


int radeon_ttm_init(struct radeon_device *rdev);
void radeon_ttm_fini(struct radeon_device *rdev);
static void radeon_bo_clear_surface_reg(struct radeon_bo *bo);

/*
 * To exclude mutual BO access we rely on bo_reserve exclusion, as all
 * function are calling it.
 */

static void radeon_bo_clear_va(struct radeon_bo *bo)
{
	struct radeon_bo_va *bo_va, *tmp;

	list_for_each_entry_safe(bo_va, tmp, &bo->va, bo_list) {
		/* remove from all vm address space */
		radeon_vm_bo_rmv(bo->rdev, bo_va);
	}
}

static void radeon_update_memory_usage(struct radeon_bo *bo,
				       unsigned mem_type, int sign)
{
	struct radeon_device *rdev = bo->rdev;
	u64 size = (u64)bo->tbo.num_pages << PAGE_SHIFT;

	switch (mem_type) {
	case TTM_PL_TT:
		if (sign > 0)
			atomic64_add(size, &rdev->gtt_usage);
		else
			atomic64_sub(size, &rdev->gtt_usage);
		break;
	case TTM_PL_VRAM:
		if (sign > 0)
			atomic64_add(size, &rdev->vram_usage);
		else
			atomic64_sub(size, &rdev->vram_usage);
		break;
	}
}

static void radeon_ttm_bo_destroy(struct ttm_buffer_object *tbo)
{
	struct radeon_bo *bo;

	bo = container_of(tbo, struct radeon_bo, tbo);

	radeon_update_memory_usage(bo, bo->tbo.mem.mem_type, -1);

	mutex_lock(&bo->rdev->gem.mutex);
	list_del_init(&bo->list);
	mutex_unlock(&bo->rdev->gem.mutex);
	radeon_bo_clear_surface_reg(bo);
	radeon_bo_clear_va(bo);
	drm_gem_object_release(&bo->gem_base);
	kfree(bo);
}

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

void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
{
	u32 c = 0, i;

	rbo->placement.fpfn = 0;
	rbo->placement.lpfn = 0;
	rbo->placement.placement = rbo->placements;
	rbo->placement.busy_placement = rbo->placements;
	if (domain & RADEON_GEM_DOMAIN_VRAM)
		rbo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |
					TTM_PL_FLAG_VRAM;
	if (domain & RADEON_GEM_DOMAIN_GTT) {
		if (rbo->flags & RADEON_GEM_GTT_UC) {
			rbo->placements[c++] = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_TT;
		} else if ((rbo->flags & RADEON_GEM_GTT_WC) ||
			   (rbo->rdev->flags & RADEON_IS_AGP)) {
			rbo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |
				TTM_PL_FLAG_TT;
		} else {
			rbo->placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_TT;
		}
	}
	if (domain & RADEON_GEM_DOMAIN_CPU) {
		if (rbo->flags & RADEON_GEM_GTT_UC) {
			rbo->placements[c++] = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_SYSTEM;
		} else if ((rbo->flags & RADEON_GEM_GTT_WC) ||
		    rbo->rdev->flags & RADEON_IS_AGP) {
			rbo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |
				TTM_PL_FLAG_SYSTEM;
		} else {
			rbo->placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_SYSTEM;
		}
	}
	if (!c)
		rbo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
	rbo->placement.num_placement = c;
	rbo->placement.num_busy_placement = c;

	/*
	 * Use two-ended allocation depending on the buffer size to
	 * improve fragmentation quality.
	 * 512kb was measured as the most optimal number.
	 */
	if (rbo->tbo.mem.size > 512 * 1024) {
		for (i = 0; i < c; i++) {
			rbo->placements[i] |= TTM_PL_FLAG_TOPDOWN;
		}
	}
}

int radeon_bo_create(struct radeon_device *rdev,
		     unsigned long size, int byte_align, bool kernel, u32 domain,
		     u32 flags, struct sg_table *sg, struct radeon_bo **bo_ptr)
{
	struct radeon_bo *bo;
	enum ttm_bo_type type;
	unsigned long page_align = roundup(byte_align, PAGE_SIZE) >> PAGE_SHIFT;
	size_t acc_size;
	int r;

	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(&rdev->mman.bdev, size,
				       sizeof(struct radeon_bo));

	bo = kzalloc(sizeof(struct radeon_bo), GFP_KERNEL);
	if (bo == NULL)
		return -ENOMEM;
	r = drm_gem_object_init(rdev->ddev, &bo->gem_base, size);
	if (unlikely(r)) {
		kfree(bo);
		return r;
	}
	bo->rdev = rdev;
	bo->surface_reg = -1;
	INIT_LIST_HEAD(&bo->list);
	INIT_LIST_HEAD(&bo->va);
	bo->initial_domain = domain & (RADEON_GEM_DOMAIN_VRAM |
	                               RADEON_GEM_DOMAIN_GTT |
	                               RADEON_GEM_DOMAIN_CPU);

	bo->flags = flags;
	/* PCI GART is always snooped */
	if (!(rdev->flags & RADEON_IS_PCIE))
		bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);

	radeon_ttm_placement_from_domain(bo, domain);
	/* Kernel allocation are uninterruptible */
	down_read(&rdev->pm.mclk_lock);
	r = ttm_bo_init(&rdev->mman.bdev, &bo->tbo, size, type,
			&bo->placement, page_align, !kernel, NULL,
			acc_size, sg, &radeon_ttm_bo_destroy);
	up_read(&rdev->pm.mclk_lock);
	if (unlikely(r != 0)) {
		return r;
	}
	*bo_ptr = bo;

	trace_radeon_bo_create(bo);

	return 0;
}

int radeon_bo_kmap(struct radeon_bo *bo, void **ptr)
{
	bool is_iomem;
	int r;

	if (bo->kptr) {
		if (ptr) {
			*ptr = bo->kptr;
		}
		return 0;
	}
	r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.num_pages, &bo->kmap);
	if (r) {
		return r;
	}
	bo->kptr = ttm_kmap_obj_virtual(&bo->kmap, &is_iomem);
	if (ptr) {
		*ptr = bo->kptr;
	}
	radeon_bo_check_tiling(bo, 0, 0);
	return 0;
}

void radeon_bo_kunmap(struct radeon_bo *bo)
{
	if (bo->kptr == NULL)
		return;
	bo->kptr = NULL;
	radeon_bo_check_tiling(bo, 0, 0);
	ttm_bo_kunmap(&bo->kmap);
}

void radeon_bo_unref(struct radeon_bo **bo)
{
	struct ttm_buffer_object *tbo;
	struct radeon_device *rdev;

	if ((*bo) == NULL)
		return;
	rdev = (*bo)->rdev;
	tbo = &((*bo)->tbo);
	down_read(&rdev->pm.mclk_lock);
	ttm_bo_unref(&tbo);
	up_read(&rdev->pm.mclk_lock);
	if (tbo == NULL)
		*bo = NULL;
}

int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain, u64 max_offset,
			     u64 *gpu_addr)
{
	int r, i;

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

		if (max_offset != 0) {
			u64 domain_start;

			if (domain == RADEON_GEM_DOMAIN_VRAM)
				domain_start = bo->rdev->mc.vram_start;
			else
				domain_start = bo->rdev->mc.gtt_start;
			WARN_ON_ONCE(max_offset <
				     (radeon_bo_gpu_offset(bo) - domain_start));
		}

		return 0;
	}
	radeon_ttm_placement_from_domain(bo, domain);
	if (domain == RADEON_GEM_DOMAIN_VRAM) {
		/* force to pin into visible video ram */
		bo->placement.lpfn = bo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
	}
	if (max_offset) {
		u64 lpfn = max_offset >> PAGE_SHIFT;

		if (!bo->placement.lpfn)
			bo->placement.lpfn = bo->rdev->mc.gtt_size >> PAGE_SHIFT;

		if (lpfn < bo->placement.lpfn)
			bo->placement.lpfn = lpfn;
	}
	for (i = 0; i < bo->placement.num_placement; i++)
		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
	if (likely(r == 0)) {
		bo->pin_count = 1;
		if (gpu_addr != NULL)
			*gpu_addr = radeon_bo_gpu_offset(bo);
		if (domain == RADEON_GEM_DOMAIN_VRAM)
			bo->rdev->vram_pin_size += radeon_bo_size(bo);
		else
			bo->rdev->gart_pin_size += radeon_bo_size(bo);
	} else {
		dev_err(bo->rdev->dev, "%p pin failed\n", bo);
	}
	return r;
}

int radeon_bo_pin(struct radeon_bo *bo, u32 domain, u64 *gpu_addr)
{
	return radeon_bo_pin_restricted(bo, domain, 0, gpu_addr);
}

int radeon_bo_unpin(struct radeon_bo *bo)
{
	int r, i;

	if (!bo->pin_count) {
		dev_warn(bo->rdev->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] &= ~TTM_PL_FLAG_NO_EVICT;
	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
	if (likely(r == 0)) {
		if (bo->tbo.mem.mem_type == TTM_PL_VRAM)
			bo->rdev->vram_pin_size -= radeon_bo_size(bo);
		else
			bo->rdev->gart_pin_size -= radeon_bo_size(bo);
	} else {
		dev_err(bo->rdev->dev, "%p validate failed for unpin\n", bo);
	}
	return r;
}

int radeon_bo_evict_vram(struct radeon_device *rdev)
{
	/* late 2.6.33 fix IGP hibernate - we need pm ops to do this correct */
	if (0 && (rdev->flags & RADEON_IS_IGP)) {
		if (rdev->mc.igp_sideport_enabled == false)
			/* Useless to evict on IGP chips */
			return 0;
	}
	return ttm_bo_evict_mm(&rdev->mman.bdev, TTM_PL_VRAM);
}

void radeon_bo_force_delete(struct radeon_device *rdev)
{
	struct radeon_bo *bo, *n;

	if (list_empty(&rdev->gem.objects)) {
		return;
	}
	dev_err(rdev->dev, "Userspace still has active objects !\n");
	list_for_each_entry_safe(bo, n, &rdev->gem.objects, list) {
		mutex_lock(&rdev->ddev->struct_mutex);
		dev_err(rdev->dev, "%p %p %lu %lu force free\n",
			&bo->gem_base, bo, (unsigned long)bo->gem_base.size,
			*((unsigned long *)&bo->gem_base.refcount));
		mutex_lock(&bo->rdev->gem.mutex);
		list_del_init(&bo->list);
		mutex_unlock(&bo->rdev->gem.mutex);
		/* this should unref the ttm bo */
		drm_gem_object_unreference(&bo->gem_base);
		mutex_unlock(&rdev->ddev->struct_mutex);
	}
}

int radeon_bo_init(struct radeon_device *rdev)
{
	/* Add an MTRR for the VRAM */
	if (!rdev->fastfb_working) {
		rdev->mc.vram_mtrr = arch_phys_wc_add(rdev->mc.aper_base,
						      rdev->mc.aper_size);
	}
	DRM_INFO("Detected VRAM RAM=%lluM, BAR=%lluM\n",
		rdev->mc.mc_vram_size >> 20,
		(unsigned long long)rdev->mc.aper_size >> 20);
	DRM_INFO("RAM width %dbits %cDR\n",
			rdev->mc.vram_width, rdev->mc.vram_is_ddr ? 'D' : 'S');
	return radeon_ttm_init(rdev);
}

void radeon_bo_fini(struct radeon_device *rdev)
{
	radeon_ttm_fini(rdev);
	arch_phys_wc_del(rdev->mc.vram_mtrr);
}

/* Returns how many bytes TTM can move per IB.
 */
static u64 radeon_bo_get_threshold_for_moves(struct radeon_device *rdev)
{
	u64 real_vram_size = rdev->mc.real_vram_size;
	u64 vram_usage = atomic64_read(&rdev->vram_usage);

	/* This function is based on the current VRAM usage.
	 *
	 * - If all of VRAM is free, allow relocating the number of bytes that
	 *   is equal to 1/4 of the size of VRAM for this IB.

	 * - If more than one half of VRAM is occupied, only allow relocating
	 *   1 MB of data for this IB.
	 *
	 * - From 0 to one half of used VRAM, the threshold decreases
	 *   linearly.
	 *         __________________
	 * 1/4 of -|\               |
	 * VRAM    | \              |
	 *         |  \             |
	 *         |   \            |
	 *         |    \           |
	 *         |     \          |
	 *         |      \         |
	 *         |       \________|1 MB
	 *         |----------------|
	 *    VRAM 0 %             100 %
	 *         used            used
	 *
	 * Note: It's a threshold, not a limit. The threshold must be crossed
	 * for buffer relocations to stop, so any buffer of an arbitrary size
	 * can be moved as long as the threshold isn't crossed before
	 * the relocation takes place. We don't want to disable buffer
	 * relocations completely.
	 *
	 * The idea is that buffers should be placed in VRAM at creation time
	 * and TTM should only do a minimum number of relocations during
	 * command submission. In practice, you need to submit at least
	 * a dozen IBs to move all buffers to VRAM if they are in GTT.
	 *
	 * Also, things can get pretty crazy under memory pressure and actual
	 * VRAM usage can change a lot, so playing safe even at 50% does
	 * consistently increase performance.
	 */

	u64 half_vram = real_vram_size >> 1;
	u64 half_free_vram = vram_usage >= half_vram ? 0 : half_vram - vram_usage;
	u64 bytes_moved_threshold = half_free_vram >> 1;
	return max(bytes_moved_threshold, 1024*1024ull);
}

int radeon_bo_list_validate(struct radeon_device *rdev,
			    struct ww_acquire_ctx *ticket,
			    struct list_head *head, int ring)
{
	struct radeon_cs_reloc *lobj;
	struct radeon_bo *bo;
	int r;
	u64 bytes_moved = 0, initial_bytes_moved;
	u64 bytes_moved_threshold = radeon_bo_get_threshold_for_moves(rdev);

	r = ttm_eu_reserve_buffers(ticket, head);
	if (unlikely(r != 0)) {
		return r;
	}

	list_for_each_entry(lobj, head, tv.head) {
		bo = lobj->robj;
		if (!bo->pin_count) {
			u32 domain = lobj->prefered_domains;
			u32 current_domain =
				radeon_mem_type_to_domain(bo->tbo.mem.mem_type);

			/* Check if this buffer will be moved and don't move it
			 * if we have moved too many buffers for this IB already.
			 *
			 * Note that this allows moving at least one buffer of
			 * any size, because it doesn't take the current "bo"
			 * into account. We don't want to disallow buffer moves
			 * completely.
			 */
			if ((lobj->allowed_domains & current_domain) != 0 &&
			    (domain & current_domain) == 0 && /* will be moved */
			    bytes_moved > bytes_moved_threshold) {
				/* don't move it */
				domain = current_domain;
			}

		retry:
			radeon_ttm_placement_from_domain(bo, domain);
			if (ring == R600_RING_TYPE_UVD_INDEX)
				radeon_uvd_force_into_uvd_segment(bo);

			initial_bytes_moved = atomic64_read(&rdev->num_bytes_moved);
			r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
			bytes_moved += atomic64_read(&rdev->num_bytes_moved) -
				       initial_bytes_moved;

			if (unlikely(r)) {
				if (r != -ERESTARTSYS &&
				    domain != lobj->allowed_domains) {
					domain = lobj->allowed_domains;
					goto retry;
				}
				ttm_eu_backoff_reservation(ticket, head);
				return r;
			}
		}
		lobj->gpu_offset = radeon_bo_gpu_offset(bo);
		lobj->tiling_flags = bo->tiling_flags;
	}
	return 0;
}

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

int radeon_bo_get_surface_reg(struct radeon_bo *bo)
{
	struct radeon_device *rdev = bo->rdev;
	struct radeon_surface_reg *reg;
	struct radeon_bo *old_object;
	int steal;
	int i;

	lockdep_assert_held(&bo->tbo.resv->lock.base);

	if (!bo->tiling_flags)
		return 0;

	if (bo->surface_reg >= 0) {
		reg = &rdev->surface_regs[bo->surface_reg];
		i = bo->surface_reg;
		goto out;
	}

	steal = -1;
	for (i = 0; i < RADEON_GEM_MAX_SURFACES; i++) {

		reg = &rdev->surface_regs[i];
		if (!reg->bo)
			break;

		old_object = reg->bo;
		if (old_object->pin_count == 0)
			steal = i;
	}

	/* if we are all out */
	if (i == RADEON_GEM_MAX_SURFACES) {
		if (steal == -1)
			return -ENOMEM;
		/* find someone with a surface reg and nuke their BO */
		reg = &rdev->surface_regs[steal];
		old_object = reg->bo;
		/* blow away the mapping */
		DRM_DEBUG("stealing surface reg %d from %p\n", steal, old_object);
		ttm_bo_unmap_virtual(&old_object->tbo);
		old_object->surface_reg = -1;
		i = steal;
	}

	bo->surface_reg = i;
	reg->bo = bo;

out:
	radeon_set_surface_reg(rdev, i, bo->tiling_flags, bo->pitch,
			       bo->tbo.mem.start << PAGE_SHIFT,
			       bo->tbo.num_pages << PAGE_SHIFT);
	return 0;
}

static void radeon_bo_clear_surface_reg(struct radeon_bo *bo)
{
	struct radeon_device *rdev = bo->rdev;
	struct radeon_surface_reg *reg;

	if (bo->surface_reg == -1)
		return;

	reg = &rdev->surface_regs[bo->surface_reg];
	radeon_clear_surface_reg(rdev, bo->surface_reg);

	reg->bo = NULL;
	bo->surface_reg = -1;
}

int radeon_bo_set_tiling_flags(struct radeon_bo *bo,
				uint32_t tiling_flags, uint32_t pitch)
{
	struct radeon_device *rdev = bo->rdev;
	int r;

	if (rdev->family >= CHIP_CEDAR) {
		unsigned bankw, bankh, mtaspect, tilesplit, stilesplit;

		bankw = (tiling_flags >> RADEON_TILING_EG_BANKW_SHIFT) & RADEON_TILING_EG_BANKW_MASK;
		bankh = (tiling_flags >> RADEON_TILING_EG_BANKH_SHIFT) & RADEON_TILING_EG_BANKH_MASK;
		mtaspect = (tiling_flags >> RADEON_TILING_EG_MACRO_TILE_ASPECT_SHIFT) & RADEON_TILING_EG_MACRO_TILE_ASPECT_MASK;
		tilesplit = (tiling_flags >> RADEON_TILING_EG_TILE_SPLIT_SHIFT) & RADEON_TILING_EG_TILE_SPLIT_MASK;
		stilesplit = (tiling_flags >> RADEON_TILING_EG_STENCIL_TILE_SPLIT_SHIFT) & RADEON_TILING_EG_STENCIL_TILE_SPLIT_MASK;
		switch (bankw) {
		case 0:
		case 1:
		case 2:
		case 4:
		case 8:
			break;
		default:
			return -EINVAL;
		}
		switch (bankh) {
		case 0:
		case 1:
		case 2:
		case 4:
		case 8:
			break;
		default:
			return -EINVAL;
		}
		switch (mtaspect) {
		case 0:
		case 1:
		case 2:
		case 4:
		case 8:
			break;
		default:
			return -EINVAL;
		}
		if (tilesplit > 6) {
			return -EINVAL;
		}
		if (stilesplit > 6) {
			return -EINVAL;
		}
	}
	r = radeon_bo_reserve(bo, false);
	if (unlikely(r != 0))
		return r;
	bo->tiling_flags = tiling_flags;
	bo->pitch = pitch;
	radeon_bo_unreserve(bo);
	return 0;
}

void radeon_bo_get_tiling_flags(struct radeon_bo *bo,
				uint32_t *tiling_flags,
				uint32_t *pitch)
{
	lockdep_assert_held(&bo->tbo.resv->lock.base);

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

int radeon_bo_check_tiling(struct radeon_bo *bo, bool has_moved,
				bool force_drop)
{
	if (!force_drop)
		lockdep_assert_held(&bo->tbo.resv->lock.base);

	if (!(bo->tiling_flags & RADEON_TILING_SURFACE))
		return 0;

	if (force_drop) {
		radeon_bo_clear_surface_reg(bo);
		return 0;
	}

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

		if (bo->surface_reg >= 0)
			radeon_bo_clear_surface_reg(bo);
		return 0;
	}

	if ((bo->surface_reg >= 0) && !has_moved)
		return 0;

	return radeon_bo_get_surface_reg(bo);
}

void radeon_bo_move_notify(struct ttm_buffer_object *bo,
			   struct ttm_mem_reg *new_mem)
{
	struct radeon_bo *rbo;

	if (!radeon_ttm_bo_is_radeon_bo(bo))
		return;

	rbo = container_of(bo, struct radeon_bo, tbo);
	radeon_bo_check_tiling(rbo, 0, 1);
	radeon_vm_bo_invalidate(rbo->rdev, rbo);

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

	radeon_update_memory_usage(rbo, bo->mem.mem_type, -1);
	radeon_update_memory_usage(rbo, new_mem->mem_type, 1);
}

int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
{
	struct radeon_device *rdev;
	struct radeon_bo *rbo;
	unsigned long offset, size;
	int r;

	if (!radeon_ttm_bo_is_radeon_bo(bo))
		return 0;
	rbo = container_of(bo, struct radeon_bo, tbo);
	radeon_bo_check_tiling(rbo, 0, 0);
	rdev = rbo->rdev;
	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) <= rdev->mc.visible_vram_size)
		return 0;

	/* hurrah the memory is not visible ! */
	radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
	rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
	r = ttm_bo_validate(bo, &rbo->placement, false, false);
	if (unlikely(r == -ENOMEM)) {
		radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT);
		return ttm_bo_validate(bo, &rbo->placement, false, false);
	} else if (unlikely(r != 0)) {
		return r;
	}

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

	return 0;
}

int radeon_bo_wait(struct radeon_bo *bo, u32 *mem_type, bool no_wait)
{
	int r;

	r = ttm_bo_reserve(&bo->tbo, true, no_wait, false, NULL);
	if (unlikely(r != 0))
		return r;
	spin_lock(&bo->tbo.bdev->fence_lock);
	if (mem_type)
		*mem_type = bo->tbo.mem.mem_type;
	if (bo->tbo.sync_obj)
		r = ttm_bo_wait(&bo->tbo, true, true, no_wait);
	spin_unlock(&bo->tbo.bdev->fence_lock);
	ttm_bo_unreserve(&bo->tbo);
	return r;
}