1/*
2 * Copyright 2007 Dave Airlied
3 * All Rights Reserved.
4 *
5 * Permission is hereby granted, free of charge, to any person obtaining a
6 * copy of this software and associated documentation files (the "Software"),
7 * to deal in the Software without restriction, including without limitation
8 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
9 * and/or sell copies of the Software, and to permit persons to whom the
10 * Software is furnished to do so, subject to the following conditions:
11 *
12 * The above copyright notice and this permission notice (including the next
13 * paragraph) shall be included in all copies or substantial portions of the
14 * Software.
15 *
16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
19 * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
20 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
21 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
22 * OTHER DEALINGS IN THE SOFTWARE.
23 */
24/*
25 * Authors: Dave Airlied <airlied@linux.ie>
26 *	    Ben Skeggs   <darktama@iinet.net.au>
27 *	    Jeremy Kolb  <jkolb@brandeis.edu>
28 */
29
30#include <linux/dma-mapping.h>
31#include <linux/swiotlb.h>
32
33#include "nouveau_drv.h"
34#include "nouveau_chan.h"
35#include "nouveau_fence.h"
36
37#include "nouveau_bo.h"
38#include "nouveau_ttm.h"
39#include "nouveau_gem.h"
40#include "nouveau_mem.h"
41#include "nouveau_vmm.h"
42
43#include <nvif/class.h>
44#include <nvif/if500b.h>
45#include <nvif/if900b.h>
46
47static int nouveau_ttm_tt_bind(struct ttm_bo_device *bdev, struct ttm_tt *ttm,
48			       struct ttm_resource *reg);
49
50/*
51 * NV10-NV40 tiling helpers
52 */
53
54static void
55nv10_bo_update_tile_region(struct drm_device *dev, struct nouveau_drm_tile *reg,
56			   u32 addr, u32 size, u32 pitch, u32 flags)
57{
58	struct nouveau_drm *drm = nouveau_drm(dev);
59	int i = reg - drm->tile.reg;
60	struct nvkm_fb *fb = nvxx_fb(&drm->client.device);
61	struct nvkm_fb_tile *tile = &fb->tile.region[i];
62
63	nouveau_fence_unref(&reg->fence);
64
65	if (tile->pitch)
66		nvkm_fb_tile_fini(fb, i, tile);
67
68	if (pitch)
69		nvkm_fb_tile_init(fb, i, addr, size, pitch, flags, tile);
70
71	nvkm_fb_tile_prog(fb, i, tile);
72}
73
74static struct nouveau_drm_tile *
75nv10_bo_get_tile_region(struct drm_device *dev, int i)
76{
77	struct nouveau_drm *drm = nouveau_drm(dev);
78	struct nouveau_drm_tile *tile = &drm->tile.reg[i];
79
80	spin_lock(&drm->tile.lock);
81
82	if (!tile->used &&
83	    (!tile->fence || nouveau_fence_done(tile->fence)))
84		tile->used = true;
85	else
86		tile = NULL;
87
88	spin_unlock(&drm->tile.lock);
89	return tile;
90}
91
92static void
93nv10_bo_put_tile_region(struct drm_device *dev, struct nouveau_drm_tile *tile,
94			struct dma_fence *fence)
95{
96	struct nouveau_drm *drm = nouveau_drm(dev);
97
98	if (tile) {
99		spin_lock(&drm->tile.lock);
100		tile->fence = (struct nouveau_fence *)dma_fence_get(fence);
101		tile->used = false;
102		spin_unlock(&drm->tile.lock);
103	}
104}
105
106static struct nouveau_drm_tile *
107nv10_bo_set_tiling(struct drm_device *dev, u32 addr,
108		   u32 size, u32 pitch, u32 zeta)
109{
110	struct nouveau_drm *drm = nouveau_drm(dev);
111	struct nvkm_fb *fb = nvxx_fb(&drm->client.device);
112	struct nouveau_drm_tile *tile, *found = NULL;
113	int i;
114
115	for (i = 0; i < fb->tile.regions; i++) {
116		tile = nv10_bo_get_tile_region(dev, i);
117
118		if (pitch && !found) {
119			found = tile;
120			continue;
121
122		} else if (tile && fb->tile.region[i].pitch) {
123			/* Kill an unused tile region. */
124			nv10_bo_update_tile_region(dev, tile, 0, 0, 0, 0);
125		}
126
127		nv10_bo_put_tile_region(dev, tile, NULL);
128	}
129
130	if (found)
131		nv10_bo_update_tile_region(dev, found, addr, size, pitch, zeta);
132	return found;
133}
134
135static void
136nouveau_bo_del_ttm(struct ttm_buffer_object *bo)
137{
138	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
139	struct drm_device *dev = drm->dev;
140	struct nouveau_bo *nvbo = nouveau_bo(bo);
141
142	WARN_ON(nvbo->pin_refcnt > 0);
143	nouveau_bo_del_io_reserve_lru(bo);
144	nv10_bo_put_tile_region(dev, nvbo->tile, NULL);
145
146	/*
147	 * If nouveau_bo_new() allocated this buffer, the GEM object was never
148	 * initialized, so don't attempt to release it.
149	 */
150	if (bo->base.dev)
151		drm_gem_object_release(&bo->base);
152
153	kfree(nvbo);
154}
155
156static inline u64
157roundup_64(u64 x, u32 y)
158{
159	x += y - 1;
160	do_div(x, y);
161	return x * y;
162}
163
164static void
165nouveau_bo_fixup_align(struct nouveau_bo *nvbo, int *align, u64 *size)
166{
167	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
168	struct nvif_device *device = &drm->client.device;
169
170	if (device->info.family < NV_DEVICE_INFO_V0_TESLA) {
171		if (nvbo->mode) {
172			if (device->info.chipset >= 0x40) {
173				*align = 65536;
174				*size = roundup_64(*size, 64 * nvbo->mode);
175
176			} else if (device->info.chipset >= 0x30) {
177				*align = 32768;
178				*size = roundup_64(*size, 64 * nvbo->mode);
179
180			} else if (device->info.chipset >= 0x20) {
181				*align = 16384;
182				*size = roundup_64(*size, 64 * nvbo->mode);
183
184			} else if (device->info.chipset >= 0x10) {
185				*align = 16384;
186				*size = roundup_64(*size, 32 * nvbo->mode);
187			}
188		}
189	} else {
190		*size = roundup_64(*size, (1 << nvbo->page));
191		*align = max((1 <<  nvbo->page), *align);
192	}
193
194	*size = roundup_64(*size, PAGE_SIZE);
195}
196
197struct nouveau_bo *
198nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain,
199		 u32 tile_mode, u32 tile_flags)
200{
201	struct nouveau_drm *drm = cli->drm;
202	struct nouveau_bo *nvbo;
203	struct nvif_mmu *mmu = &cli->mmu;
204	struct nvif_vmm *vmm = cli->svm.cli ? &cli->svm.vmm : &cli->vmm.vmm;
205	int i, pi = -1;
206
207	if (!*size) {
208		NV_WARN(drm, "skipped size %016llx\n", *size);
209		return ERR_PTR(-EINVAL);
210	}
211
212	nvbo = kzalloc(sizeof(struct nouveau_bo), GFP_KERNEL);
213	if (!nvbo)
214		return ERR_PTR(-ENOMEM);
215	INIT_LIST_HEAD(&nvbo->head);
216	INIT_LIST_HEAD(&nvbo->entry);
217	INIT_LIST_HEAD(&nvbo->vma_list);
218	nvbo->bo.bdev = &drm->ttm.bdev;
219
220	/* This is confusing, and doesn't actually mean we want an uncached
221	 * mapping, but is what NOUVEAU_GEM_DOMAIN_COHERENT gets translated
222	 * into in nouveau_gem_new().
223	 */
224	if (domain & NOUVEAU_GEM_DOMAIN_COHERENT) {
225		/* Determine if we can get a cache-coherent map, forcing
226		 * uncached mapping if we can't.
227		 */
228		if (!nouveau_drm_use_coherent_gpu_mapping(drm))
229			nvbo->force_coherent = true;
230	}
231
232	if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) {
233		nvbo->kind = (tile_flags & 0x0000ff00) >> 8;
234		if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) {
235			kfree(nvbo);
236			return ERR_PTR(-EINVAL);
237		}
238
239		nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind;
240	} else
241	if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
242		nvbo->kind = (tile_flags & 0x00007f00) >> 8;
243		nvbo->comp = (tile_flags & 0x00030000) >> 16;
244		if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) {
245			kfree(nvbo);
246			return ERR_PTR(-EINVAL);
247		}
248	} else {
249		nvbo->zeta = (tile_flags & 0x00000007);
250	}
251	nvbo->mode = tile_mode;
252	nvbo->contig = !(tile_flags & NOUVEAU_GEM_TILE_NONCONTIG);
253
254	/* Determine the desirable target GPU page size for the buffer. */
255	for (i = 0; i < vmm->page_nr; i++) {
256		/* Because we cannot currently allow VMM maps to fail
257		 * during buffer migration, we need to determine page
258		 * size for the buffer up-front, and pre-allocate its
259		 * page tables.
260		 *
261		 * Skip page sizes that can't support needed domains.
262		 */
263		if (cli->device.info.family > NV_DEVICE_INFO_V0_CURIE &&
264		    (domain & NOUVEAU_GEM_DOMAIN_VRAM) && !vmm->page[i].vram)
265			continue;
266		if ((domain & NOUVEAU_GEM_DOMAIN_GART) &&
267		    (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT))
268			continue;
269
270		/* Select this page size if it's the first that supports
271		 * the potential memory domains, or when it's compatible
272		 * with the requested compression settings.
273		 */
274		if (pi < 0 || !nvbo->comp || vmm->page[i].comp)
275			pi = i;
276
277		/* Stop once the buffer is larger than the current page size. */
278		if (*size >= 1ULL << vmm->page[i].shift)
279			break;
280	}
281
282	if (WARN_ON(pi < 0)) {
283		kfree(nvbo);
284		return ERR_PTR(-EINVAL);
285	}
286
287	/* Disable compression if suitable settings couldn't be found. */
288	if (nvbo->comp && !vmm->page[pi].comp) {
289		if (mmu->object.oclass >= NVIF_CLASS_MMU_GF100)
290			nvbo->kind = mmu->kind[nvbo->kind];
291		nvbo->comp = 0;
292	}
293	nvbo->page = vmm->page[pi].shift;
294
295	nouveau_bo_fixup_align(nvbo, align, size);
296
297	return nvbo;
298}
299
300int
301nouveau_bo_init(struct nouveau_bo *nvbo, u64 size, int align, u32 domain,
302		struct sg_table *sg, struct dma_resv *robj)
303{
304	int type = sg ? ttm_bo_type_sg : ttm_bo_type_device;
305	size_t acc_size;
306	int ret;
307
308	acc_size = ttm_bo_dma_acc_size(nvbo->bo.bdev, size, sizeof(*nvbo));
309
310	nvbo->bo.mem.num_pages = size >> PAGE_SHIFT;
311	nouveau_bo_placement_set(nvbo, domain, 0);
312	INIT_LIST_HEAD(&nvbo->io_reserve_lru);
313
314	ret = ttm_bo_init(nvbo->bo.bdev, &nvbo->bo, size, type,
315			  &nvbo->placement, align >> PAGE_SHIFT, false,
316			  acc_size, sg, robj, nouveau_bo_del_ttm);
317	if (ret) {
318		/* ttm will call nouveau_bo_del_ttm if it fails.. */
319		return ret;
320	}
321
322	return 0;
323}
324
325int
326nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align,
327	       uint32_t domain, uint32_t tile_mode, uint32_t tile_flags,
328	       struct sg_table *sg, struct dma_resv *robj,
329	       struct nouveau_bo **pnvbo)
330{
331	struct nouveau_bo *nvbo;
332	int ret;
333
334	nvbo = nouveau_bo_alloc(cli, &size, &align, domain, tile_mode,
335				tile_flags);
336	if (IS_ERR(nvbo))
337		return PTR_ERR(nvbo);
338
339	ret = nouveau_bo_init(nvbo, size, align, domain, sg, robj);
340	if (ret)
341		return ret;
342
343	*pnvbo = nvbo;
344	return 0;
345}
346
347static void
348set_placement_list(struct nouveau_drm *drm, struct ttm_place *pl, unsigned *n,
349		   uint32_t domain, uint32_t flags)
350{
351	*n = 0;
352
353	if (domain & NOUVEAU_GEM_DOMAIN_VRAM) {
354		struct nvif_mmu *mmu = &drm->client.mmu;
355
356		pl[*n].mem_type = TTM_PL_VRAM;
357		pl[*n].flags = flags & ~TTM_PL_FLAG_CACHED;
358
359		/* Some BARs do not support being ioremapped WC */
360		if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA &&
361		    mmu->type[drm->ttm.type_vram].type & NVIF_MEM_UNCACHED)
362			pl[*n].flags &= ~TTM_PL_FLAG_WC;
363
364		(*n)++;
365	}
366	if (domain & NOUVEAU_GEM_DOMAIN_GART) {
367		pl[*n].mem_type = TTM_PL_TT;
368		pl[*n].flags = flags;
369
370		if (drm->agp.bridge)
371			pl[*n].flags &= ~TTM_PL_FLAG_CACHED;
372
373		(*n)++;
374	}
375	if (domain & NOUVEAU_GEM_DOMAIN_CPU) {
376		pl[*n].mem_type = TTM_PL_SYSTEM;
377		pl[(*n)++].flags = flags;
378	}
379}
380
381static void
382set_placement_range(struct nouveau_bo *nvbo, uint32_t domain)
383{
384	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
385	u32 vram_pages = drm->client.device.info.ram_size >> PAGE_SHIFT;
386	unsigned i, fpfn, lpfn;
387
388	if (drm->client.device.info.family == NV_DEVICE_INFO_V0_CELSIUS &&
389	    nvbo->mode && (domain & NOUVEAU_GEM_DOMAIN_VRAM) &&
390	    nvbo->bo.mem.num_pages < vram_pages / 4) {
391		/*
392		 * Make sure that the color and depth buffers are handled
393		 * by independent memory controller units. Up to a 9x
394		 * speed up when alpha-blending and depth-test are enabled
395		 * at the same time.
396		 */
397		if (nvbo->zeta) {
398			fpfn = vram_pages / 2;
399			lpfn = ~0;
400		} else {
401			fpfn = 0;
402			lpfn = vram_pages / 2;
403		}
404		for (i = 0; i < nvbo->placement.num_placement; ++i) {
405			nvbo->placements[i].fpfn = fpfn;
406			nvbo->placements[i].lpfn = lpfn;
407		}
408		for (i = 0; i < nvbo->placement.num_busy_placement; ++i) {
409			nvbo->busy_placements[i].fpfn = fpfn;
410			nvbo->busy_placements[i].lpfn = lpfn;
411		}
412	}
413}
414
415void
416nouveau_bo_placement_set(struct nouveau_bo *nvbo, uint32_t domain,
417			 uint32_t busy)
418{
419	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
420	struct ttm_placement *pl = &nvbo->placement;
421	uint32_t flags = (nvbo->force_coherent ? TTM_PL_FLAG_UNCACHED :
422						 TTM_PL_MASK_CACHING) |
423			 (nvbo->pin_refcnt ? TTM_PL_FLAG_NO_EVICT : 0);
424
425	pl->placement = nvbo->placements;
426	set_placement_list(drm, nvbo->placements, &pl->num_placement,
427			   domain, flags);
428
429	pl->busy_placement = nvbo->busy_placements;
430	set_placement_list(drm, nvbo->busy_placements, &pl->num_busy_placement,
431			   domain | busy, flags);
432
433	set_placement_range(nvbo, domain);
434}
435
436int
437nouveau_bo_pin(struct nouveau_bo *nvbo, uint32_t domain, bool contig)
438{
439	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
440	struct ttm_buffer_object *bo = &nvbo->bo;
441	bool force = false, evict = false;
442	int ret;
443
444	ret = ttm_bo_reserve(bo, false, false, NULL);
445	if (ret)
446		return ret;
447
448	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA &&
449	    domain == NOUVEAU_GEM_DOMAIN_VRAM && contig) {
450		if (!nvbo->contig) {
451			nvbo->contig = true;
452			force = true;
453			evict = true;
454		}
455	}
456
457	if (nvbo->pin_refcnt) {
458		bool error = evict;
459
460		switch (bo->mem.mem_type) {
461		case TTM_PL_VRAM:
462			error |= !(domain & NOUVEAU_GEM_DOMAIN_VRAM);
463			break;
464		case TTM_PL_TT:
465			error |= !(domain & NOUVEAU_GEM_DOMAIN_GART);
466		default:
467			break;
468		}
469
470		if (error) {
471			NV_ERROR(drm, "bo %p pinned elsewhere: "
472				      "0x%08x vs 0x%08x\n", bo,
473				 bo->mem.mem_type, domain);
474			ret = -EBUSY;
475		}
476		nvbo->pin_refcnt++;
477		goto out;
478	}
479
480	if (evict) {
481		nouveau_bo_placement_set(nvbo, NOUVEAU_GEM_DOMAIN_GART, 0);
482		ret = nouveau_bo_validate(nvbo, false, false);
483		if (ret)
484			goto out;
485	}
486
487	nvbo->pin_refcnt++;
488	nouveau_bo_placement_set(nvbo, domain, 0);
489
490	/* drop pin_refcnt temporarily, so we don't trip the assertion
491	 * in nouveau_bo_move() that makes sure we're not trying to
492	 * move a pinned buffer
493	 */
494	nvbo->pin_refcnt--;
495	ret = nouveau_bo_validate(nvbo, false, false);
496	if (ret)
497		goto out;
498	nvbo->pin_refcnt++;
499
500	switch (bo->mem.mem_type) {
501	case TTM_PL_VRAM:
502		drm->gem.vram_available -= bo->mem.size;
503		break;
504	case TTM_PL_TT:
505		drm->gem.gart_available -= bo->mem.size;
506		break;
507	default:
508		break;
509	}
510
511out:
512	if (force && ret)
513		nvbo->contig = false;
514	ttm_bo_unreserve(bo);
515	return ret;
516}
517
518int
519nouveau_bo_unpin(struct nouveau_bo *nvbo)
520{
521	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
522	struct ttm_buffer_object *bo = &nvbo->bo;
523	int ret, ref;
524
525	ret = ttm_bo_reserve(bo, false, false, NULL);
526	if (ret)
527		return ret;
528
529	ref = --nvbo->pin_refcnt;
530	WARN_ON_ONCE(ref < 0);
531	if (ref)
532		goto out;
533
534	switch (bo->mem.mem_type) {
535	case TTM_PL_VRAM:
536		nouveau_bo_placement_set(nvbo, NOUVEAU_GEM_DOMAIN_VRAM, 0);
537		break;
538	case TTM_PL_TT:
539		nouveau_bo_placement_set(nvbo, NOUVEAU_GEM_DOMAIN_GART, 0);
540		break;
541	default:
542		break;
543	}
544
545	ret = nouveau_bo_validate(nvbo, false, false);
546	if (ret == 0) {
547		switch (bo->mem.mem_type) {
548		case TTM_PL_VRAM:
549			drm->gem.vram_available += bo->mem.size;
550			break;
551		case TTM_PL_TT:
552			drm->gem.gart_available += bo->mem.size;
553			break;
554		default:
555			break;
556		}
557	}
558
559out:
560	ttm_bo_unreserve(bo);
561	return ret;
562}
563
564int
565nouveau_bo_map(struct nouveau_bo *nvbo)
566{
567	int ret;
568
569	ret = ttm_bo_reserve(&nvbo->bo, false, false, NULL);
570	if (ret)
571		return ret;
572
573	ret = ttm_bo_kmap(&nvbo->bo, 0, nvbo->bo.mem.num_pages, &nvbo->kmap);
574
575	ttm_bo_unreserve(&nvbo->bo);
576	return ret;
577}
578
579void
580nouveau_bo_unmap(struct nouveau_bo *nvbo)
581{
582	if (!nvbo)
583		return;
584
585	ttm_bo_kunmap(&nvbo->kmap);
586}
587
588void
589nouveau_bo_sync_for_device(struct nouveau_bo *nvbo)
590{
591	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
592	struct ttm_dma_tt *ttm_dma = (struct ttm_dma_tt *)nvbo->bo.ttm;
593	int i;
594
595	if (!ttm_dma || !ttm_dma->dma_address)
596		return;
597
598	/* Don't waste time looping if the object is coherent */
599	if (nvbo->force_coherent)
600		return;
601
602	for (i = 0; i < ttm_dma->ttm.num_pages; i++)
603		dma_sync_single_for_device(drm->dev->dev,
604					   ttm_dma->dma_address[i],
605					   PAGE_SIZE, DMA_TO_DEVICE);
606}
607
608void
609nouveau_bo_sync_for_cpu(struct nouveau_bo *nvbo)
610{
611	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
612	struct ttm_dma_tt *ttm_dma = (struct ttm_dma_tt *)nvbo->bo.ttm;
613	int i;
614
615	if (!ttm_dma || !ttm_dma->dma_address)
616		return;
617
618	/* Don't waste time looping if the object is coherent */
619	if (nvbo->force_coherent)
620		return;
621
622	for (i = 0; i < ttm_dma->ttm.num_pages; i++)
623		dma_sync_single_for_cpu(drm->dev->dev, ttm_dma->dma_address[i],
624					PAGE_SIZE, DMA_FROM_DEVICE);
625}
626
627void nouveau_bo_add_io_reserve_lru(struct ttm_buffer_object *bo)
628{
629	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
630	struct nouveau_bo *nvbo = nouveau_bo(bo);
631
632	mutex_lock(&drm->ttm.io_reserve_mutex);
633	list_move_tail(&nvbo->io_reserve_lru, &drm->ttm.io_reserve_lru);
634	mutex_unlock(&drm->ttm.io_reserve_mutex);
635}
636
637void nouveau_bo_del_io_reserve_lru(struct ttm_buffer_object *bo)
638{
639	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
640	struct nouveau_bo *nvbo = nouveau_bo(bo);
641
642	mutex_lock(&drm->ttm.io_reserve_mutex);
643	list_del_init(&nvbo->io_reserve_lru);
644	mutex_unlock(&drm->ttm.io_reserve_mutex);
645}
646
647int
648nouveau_bo_validate(struct nouveau_bo *nvbo, bool interruptible,
649		    bool no_wait_gpu)
650{
651	struct ttm_operation_ctx ctx = { interruptible, no_wait_gpu };
652	int ret;
653
654	ret = ttm_bo_validate(&nvbo->bo, &nvbo->placement, &ctx);
655	if (ret)
656		return ret;
657
658	nouveau_bo_sync_for_device(nvbo);
659
660	return 0;
661}
662
663void
664nouveau_bo_wr16(struct nouveau_bo *nvbo, unsigned index, u16 val)
665{
666	bool is_iomem;
667	u16 *mem = ttm_kmap_obj_virtual(&nvbo->kmap, &is_iomem);
668
669	mem += index;
670
671	if (is_iomem)
672		iowrite16_native(val, (void __force __iomem *)mem);
673	else
674		*mem = val;
675}
676
677u32
678nouveau_bo_rd32(struct nouveau_bo *nvbo, unsigned index)
679{
680	bool is_iomem;
681	u32 *mem = ttm_kmap_obj_virtual(&nvbo->kmap, &is_iomem);
682
683	mem += index;
684
685	if (is_iomem)
686		return ioread32_native((void __force __iomem *)mem);
687	else
688		return *mem;
689}
690
691void
692nouveau_bo_wr32(struct nouveau_bo *nvbo, unsigned index, u32 val)
693{
694	bool is_iomem;
695	u32 *mem = ttm_kmap_obj_virtual(&nvbo->kmap, &is_iomem);
696
697	mem += index;
698
699	if (is_iomem)
700		iowrite32_native(val, (void __force __iomem *)mem);
701	else
702		*mem = val;
703}
704
705static struct ttm_tt *
706nouveau_ttm_tt_create(struct ttm_buffer_object *bo, uint32_t page_flags)
707{
708#if IS_ENABLED(CONFIG_AGP)
709	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
710
711	if (drm->agp.bridge) {
712		return ttm_agp_tt_create(bo, drm->agp.bridge, page_flags);
713	}
714#endif
715
716	return nouveau_sgdma_create_ttm(bo, page_flags);
717}
718
719static int
720nouveau_ttm_tt_bind(struct ttm_bo_device *bdev, struct ttm_tt *ttm,
721		    struct ttm_resource *reg)
722{
723#if IS_ENABLED(CONFIG_AGP)
724	struct nouveau_drm *drm = nouveau_bdev(bdev);
725#endif
726	if (!reg)
727		return -EINVAL;
728#if IS_ENABLED(CONFIG_AGP)
729	if (drm->agp.bridge)
730		return ttm_agp_bind(ttm, reg);
731#endif
732	return nouveau_sgdma_bind(bdev, ttm, reg);
733}
734
735static void
736nouveau_ttm_tt_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
737{
738#if IS_ENABLED(CONFIG_AGP)
739	struct nouveau_drm *drm = nouveau_bdev(bdev);
740
741	if (drm->agp.bridge) {
742		ttm_agp_unbind(ttm);
743		return;
744	}
745#endif
746	nouveau_sgdma_unbind(bdev, ttm);
747}
748
749static void
750nouveau_bo_evict_flags(struct ttm_buffer_object *bo, struct ttm_placement *pl)
751{
752	struct nouveau_bo *nvbo = nouveau_bo(bo);
753
754	switch (bo->mem.mem_type) {
755	case TTM_PL_VRAM:
756		nouveau_bo_placement_set(nvbo, NOUVEAU_GEM_DOMAIN_GART,
757					 NOUVEAU_GEM_DOMAIN_CPU);
758		break;
759	default:
760		nouveau_bo_placement_set(nvbo, NOUVEAU_GEM_DOMAIN_CPU, 0);
761		break;
762	}
763
764	*pl = nvbo->placement;
765}
766
767static int
768nouveau_bo_move_prep(struct nouveau_drm *drm, struct ttm_buffer_object *bo,
769		     struct ttm_resource *reg)
770{
771	struct nouveau_mem *old_mem = nouveau_mem(&bo->mem);
772	struct nouveau_mem *new_mem = nouveau_mem(reg);
773	struct nvif_vmm *vmm = &drm->client.vmm.vmm;
774	int ret;
775
776	ret = nvif_vmm_get(vmm, LAZY, false, old_mem->mem.page, 0,
777			   old_mem->mem.size, &old_mem->vma[0]);
778	if (ret)
779		return ret;
780
781	ret = nvif_vmm_get(vmm, LAZY, false, new_mem->mem.page, 0,
782			   new_mem->mem.size, &old_mem->vma[1]);
783	if (ret)
784		goto done;
785
786	ret = nouveau_mem_map(old_mem, vmm, &old_mem->vma[0]);
787	if (ret)
788		goto done;
789
790	ret = nouveau_mem_map(new_mem, vmm, &old_mem->vma[1]);
791done:
792	if (ret) {
793		nvif_vmm_put(vmm, &old_mem->vma[1]);
794		nvif_vmm_put(vmm, &old_mem->vma[0]);
795	}
796	return 0;
797}
798
799static int
800nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr,
801		     bool no_wait_gpu, struct ttm_resource *new_reg)
802{
803	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
804	struct nouveau_channel *chan = drm->ttm.chan;
805	struct nouveau_cli *cli = (void *)chan->user.client;
806	struct nouveau_fence *fence;
807	int ret;
808
809	/* create temporary vmas for the transfer and attach them to the
810	 * old nvkm_mem node, these will get cleaned up after ttm has
811	 * destroyed the ttm_resource
812	 */
813	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
814		ret = nouveau_bo_move_prep(drm, bo, new_reg);
815		if (ret)
816			return ret;
817	}
818
819	mutex_lock_nested(&cli->mutex, SINGLE_DEPTH_NESTING);
820	ret = nouveau_fence_sync(nouveau_bo(bo), chan, true, intr);
821	if (ret == 0) {
822		ret = drm->ttm.move(chan, bo, &bo->mem, new_reg);
823		if (ret == 0) {
824			ret = nouveau_fence_new(chan, false, &fence);
825			if (ret == 0) {
826				/* TODO: figure out a better solution here
827				 *
828				 * wait on the fence here explicitly as going through
829				 * ttm_bo_move_accel_cleanup somehow doesn't seem to do it.
830				 *
831				 * Without this the operation can timeout and we'll fallback to a
832				 * software copy, which might take several minutes to finish.
833				 */
834				nouveau_fence_wait(fence, false, false);
835				ret = ttm_bo_move_accel_cleanup(bo,
836								&fence->base,
837								evict, false,
838								new_reg);
839				nouveau_fence_unref(&fence);
840			}
841		}
842	}
843	mutex_unlock(&cli->mutex);
844	return ret;
845}
846
847void
848nouveau_bo_move_init(struct nouveau_drm *drm)
849{
850	static const struct _method_table {
851		const char *name;
852		int engine;
853		s32 oclass;
854		int (*exec)(struct nouveau_channel *,
855			    struct ttm_buffer_object *,
856			    struct ttm_resource *, struct ttm_resource *);
857		int (*init)(struct nouveau_channel *, u32 handle);
858	} _methods[] = {
859		{  "COPY", 4, 0xc5b5, nve0_bo_move_copy, nve0_bo_move_init },
860		{  "GRCE", 0, 0xc5b5, nve0_bo_move_copy, nvc0_bo_move_init },
861		{  "COPY", 4, 0xc3b5, nve0_bo_move_copy, nve0_bo_move_init },
862		{  "GRCE", 0, 0xc3b5, nve0_bo_move_copy, nvc0_bo_move_init },
863		{  "COPY", 4, 0xc1b5, nve0_bo_move_copy, nve0_bo_move_init },
864		{  "GRCE", 0, 0xc1b5, nve0_bo_move_copy, nvc0_bo_move_init },
865		{  "COPY", 4, 0xc0b5, nve0_bo_move_copy, nve0_bo_move_init },
866		{  "GRCE", 0, 0xc0b5, nve0_bo_move_copy, nvc0_bo_move_init },
867		{  "COPY", 4, 0xb0b5, nve0_bo_move_copy, nve0_bo_move_init },
868		{  "GRCE", 0, 0xb0b5, nve0_bo_move_copy, nvc0_bo_move_init },
869		{  "COPY", 4, 0xa0b5, nve0_bo_move_copy, nve0_bo_move_init },
870		{  "GRCE", 0, 0xa0b5, nve0_bo_move_copy, nvc0_bo_move_init },
871		{ "COPY1", 5, 0x90b8, nvc0_bo_move_copy, nvc0_bo_move_init },
872		{ "COPY0", 4, 0x90b5, nvc0_bo_move_copy, nvc0_bo_move_init },
873		{  "COPY", 0, 0x85b5, nva3_bo_move_copy, nv50_bo_move_init },
874		{ "CRYPT", 0, 0x74c1, nv84_bo_move_exec, nv50_bo_move_init },
875		{  "M2MF", 0, 0x9039, nvc0_bo_move_m2mf, nvc0_bo_move_init },
876		{  "M2MF", 0, 0x5039, nv50_bo_move_m2mf, nv50_bo_move_init },
877		{  "M2MF", 0, 0x0039, nv04_bo_move_m2mf, nv04_bo_move_init },
878		{},
879	};
880	const struct _method_table *mthd = _methods;
881	const char *name = "CPU";
882	int ret;
883
884	do {
885		struct nouveau_channel *chan;
886
887		if (mthd->engine)
888			chan = drm->cechan;
889		else
890			chan = drm->channel;
891		if (chan == NULL)
892			continue;
893
894		ret = nvif_object_ctor(&chan->user, "ttmBoMove",
895				       mthd->oclass | (mthd->engine << 16),
896				       mthd->oclass, NULL, 0,
897				       &drm->ttm.copy);
898		if (ret == 0) {
899			ret = mthd->init(chan, drm->ttm.copy.handle);
900			if (ret) {
901				nvif_object_dtor(&drm->ttm.copy);
902				continue;
903			}
904
905			drm->ttm.move = mthd->exec;
906			drm->ttm.chan = chan;
907			name = mthd->name;
908			break;
909		}
910	} while ((++mthd)->exec);
911
912	NV_INFO(drm, "MM: using %s for buffer copies\n", name);
913}
914
915static int
916nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
917		      bool no_wait_gpu, struct ttm_resource *new_reg)
918{
919	struct ttm_operation_ctx ctx = { intr, no_wait_gpu };
920	struct ttm_place placement_memtype = {
921		.fpfn = 0,
922		.lpfn = 0,
923		.mem_type = TTM_PL_TT,
924		.flags = TTM_PL_MASK_CACHING
925	};
926	struct ttm_placement placement;
927	struct ttm_resource tmp_reg;
928	int ret;
929
930	placement.num_placement = placement.num_busy_placement = 1;
931	placement.placement = placement.busy_placement = &placement_memtype;
932
933	tmp_reg = *new_reg;
934	tmp_reg.mm_node = NULL;
935	ret = ttm_bo_mem_space(bo, &placement, &tmp_reg, &ctx);
936	if (ret)
937		return ret;
938
939	ret = ttm_tt_populate(bo->bdev, bo->ttm, &ctx);
940	if (ret)
941		goto out;
942
943	ret = nouveau_ttm_tt_bind(bo->bdev, bo->ttm, &tmp_reg);
944	if (ret)
945		goto out;
946
947	ret = nouveau_bo_move_m2mf(bo, true, intr, no_wait_gpu, &tmp_reg);
948	if (ret)
949		goto out;
950
951	ret = ttm_bo_move_ttm(bo, &ctx, new_reg);
952out:
953	ttm_resource_free(bo, &tmp_reg);
954	return ret;
955}
956
957static int
958nouveau_bo_move_flips(struct ttm_buffer_object *bo, bool evict, bool intr,
959		      bool no_wait_gpu, struct ttm_resource *new_reg)
960{
961	struct ttm_operation_ctx ctx = { intr, no_wait_gpu };
962	struct ttm_place placement_memtype = {
963		.fpfn = 0,
964		.lpfn = 0,
965		.mem_type = TTM_PL_TT,
966		.flags = TTM_PL_MASK_CACHING
967	};
968	struct ttm_placement placement;
969	struct ttm_resource tmp_reg;
970	int ret;
971
972	placement.num_placement = placement.num_busy_placement = 1;
973	placement.placement = placement.busy_placement = &placement_memtype;
974
975	tmp_reg = *new_reg;
976	tmp_reg.mm_node = NULL;
977	ret = ttm_bo_mem_space(bo, &placement, &tmp_reg, &ctx);
978	if (ret)
979		return ret;
980
981	ret = ttm_bo_move_ttm(bo, &ctx, &tmp_reg);
982	if (ret)
983		goto out;
984
985	ret = nouveau_bo_move_m2mf(bo, true, intr, no_wait_gpu, new_reg);
986	if (ret)
987		goto out;
988
989out:
990	ttm_resource_free(bo, &tmp_reg);
991	return ret;
992}
993
994static void
995nouveau_bo_move_ntfy(struct ttm_buffer_object *bo, bool evict,
996		     struct ttm_resource *new_reg)
997{
998	struct nouveau_mem *mem = new_reg ? nouveau_mem(new_reg) : NULL;
999	struct nouveau_bo *nvbo = nouveau_bo(bo);
1000	struct nouveau_vma *vma;
1001
1002	/* ttm can now (stupidly) pass the driver bos it didn't create... */
1003	if (bo->destroy != nouveau_bo_del_ttm)
1004		return;
1005
1006	nouveau_bo_del_io_reserve_lru(bo);
1007
1008	if (mem && new_reg->mem_type != TTM_PL_SYSTEM &&
1009	    mem->mem.page == nvbo->page) {
1010		list_for_each_entry(vma, &nvbo->vma_list, head) {
1011			nouveau_vma_map(vma, mem);
1012		}
1013	} else {
1014		list_for_each_entry(vma, &nvbo->vma_list, head) {
1015			WARN_ON(ttm_bo_wait(bo, false, false));
1016			nouveau_vma_unmap(vma);
1017		}
1018	}
1019
1020	if (new_reg) {
1021		if (new_reg->mm_node)
1022			nvbo->offset = (new_reg->start << PAGE_SHIFT);
1023		else
1024			nvbo->offset = 0;
1025	}
1026
1027}
1028
1029static int
1030nouveau_bo_vm_bind(struct ttm_buffer_object *bo, struct ttm_resource *new_reg,
1031		   struct nouveau_drm_tile **new_tile)
1032{
1033	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
1034	struct drm_device *dev = drm->dev;
1035	struct nouveau_bo *nvbo = nouveau_bo(bo);
1036	u64 offset = new_reg->start << PAGE_SHIFT;
1037
1038	*new_tile = NULL;
1039	if (new_reg->mem_type != TTM_PL_VRAM)
1040		return 0;
1041
1042	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_CELSIUS) {
1043		*new_tile = nv10_bo_set_tiling(dev, offset, new_reg->size,
1044					       nvbo->mode, nvbo->zeta);
1045	}
1046
1047	return 0;
1048}
1049
1050static void
1051nouveau_bo_vm_cleanup(struct ttm_buffer_object *bo,
1052		      struct nouveau_drm_tile *new_tile,
1053		      struct nouveau_drm_tile **old_tile)
1054{
1055	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
1056	struct drm_device *dev = drm->dev;
1057	struct dma_fence *fence = dma_resv_get_excl(bo->base.resv);
1058
1059	nv10_bo_put_tile_region(dev, *old_tile, fence);
1060	*old_tile = new_tile;
1061}
1062
1063static int
1064nouveau_bo_move(struct ttm_buffer_object *bo, bool evict,
1065		struct ttm_operation_ctx *ctx,
1066		struct ttm_resource *new_reg)
1067{
1068	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
1069	struct nouveau_bo *nvbo = nouveau_bo(bo);
1070	struct ttm_resource *old_reg = &bo->mem;
1071	struct nouveau_drm_tile *new_tile = NULL;
1072	int ret = 0;
1073
1074	ret = ttm_bo_wait(bo, ctx->interruptible, ctx->no_wait_gpu);
1075	if (ret)
1076		return ret;
1077
1078	if (nvbo->pin_refcnt)
1079		NV_WARN(drm, "Moving pinned object %p!\n", nvbo);
1080
1081	if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA) {
1082		ret = nouveau_bo_vm_bind(bo, new_reg, &new_tile);
1083		if (ret)
1084			return ret;
1085	}
1086
1087	/* Fake bo copy. */
1088	if (old_reg->mem_type == TTM_PL_SYSTEM && !bo->ttm) {
1089		ttm_bo_move_null(bo, new_reg);
1090		goto out;
1091	}
1092
1093	/* Hardware assisted copy. */
1094	if (drm->ttm.move) {
1095		if (new_reg->mem_type == TTM_PL_SYSTEM)
1096			ret = nouveau_bo_move_flipd(bo, evict,
1097						    ctx->interruptible,
1098						    ctx->no_wait_gpu, new_reg);
1099		else if (old_reg->mem_type == TTM_PL_SYSTEM)
1100			ret = nouveau_bo_move_flips(bo, evict,
1101						    ctx->interruptible,
1102						    ctx->no_wait_gpu, new_reg);
1103		else
1104			ret = nouveau_bo_move_m2mf(bo, evict,
1105						   ctx->interruptible,
1106						   ctx->no_wait_gpu, new_reg);
1107		if (!ret)
1108			goto out;
1109	}
1110
1111	/* Fallback to software copy. */
1112	ret = ttm_bo_wait(bo, ctx->interruptible, ctx->no_wait_gpu);
1113	if (ret == 0)
1114		ret = ttm_bo_move_memcpy(bo, ctx, new_reg);
1115
1116out:
1117	if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA) {
1118		if (ret)
1119			nouveau_bo_vm_cleanup(bo, NULL, &new_tile);
1120		else
1121			nouveau_bo_vm_cleanup(bo, new_tile, &nvbo->tile);
1122	}
1123
1124	return ret;
1125}
1126
1127static int
1128nouveau_bo_verify_access(struct ttm_buffer_object *bo, struct file *filp)
1129{
1130	struct nouveau_bo *nvbo = nouveau_bo(bo);
1131
1132	return drm_vma_node_verify_access(&nvbo->bo.base.vma_node,
1133					  filp->private_data);
1134}
1135
1136static void
1137nouveau_ttm_io_mem_free_locked(struct nouveau_drm *drm,
1138			       struct ttm_resource *reg)
1139{
1140	struct nouveau_mem *mem = nouveau_mem(reg);
1141
1142	if (drm->client.mem->oclass >= NVIF_CLASS_MEM_NV50) {
1143		switch (reg->mem_type) {
1144		case TTM_PL_TT:
1145			if (mem->kind)
1146				nvif_object_unmap_handle(&mem->mem.object);
1147			break;
1148		case TTM_PL_VRAM:
1149			nvif_object_unmap_handle(&mem->mem.object);
1150			break;
1151		default:
1152			break;
1153		}
1154	}
1155}
1156
1157static int
1158nouveau_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_resource *reg)
1159{
1160	struct nouveau_drm *drm = nouveau_bdev(bdev);
1161	struct nvkm_device *device = nvxx_device(&drm->client.device);
1162	struct nouveau_mem *mem = nouveau_mem(reg);
1163	int ret;
1164
1165	mutex_lock(&drm->ttm.io_reserve_mutex);
1166retry:
1167	switch (reg->mem_type) {
1168	case TTM_PL_SYSTEM:
1169		/* System memory */
1170		ret = 0;
1171		goto out;
1172	case TTM_PL_TT:
1173#if IS_ENABLED(CONFIG_AGP)
1174		if (drm->agp.bridge) {
1175			reg->bus.offset = (reg->start << PAGE_SHIFT) +
1176				drm->agp.base;
1177			reg->bus.is_iomem = !drm->agp.cma;
1178		}
1179#endif
1180		if (drm->client.mem->oclass < NVIF_CLASS_MEM_NV50 ||
1181		    !mem->kind) {
1182			/* untiled */
1183			ret = 0;
1184			break;
1185		}
1186		fallthrough;	/* tiled memory */
1187	case TTM_PL_VRAM:
1188		reg->bus.offset = (reg->start << PAGE_SHIFT) +
1189			device->func->resource_addr(device, 1);
1190		reg->bus.is_iomem = true;
1191		if (drm->client.mem->oclass >= NVIF_CLASS_MEM_NV50) {
1192			union {
1193				struct nv50_mem_map_v0 nv50;
1194				struct gf100_mem_map_v0 gf100;
1195			} args;
1196			u64 handle, length;
1197			u32 argc = 0;
1198
1199			switch (mem->mem.object.oclass) {
1200			case NVIF_CLASS_MEM_NV50:
1201				args.nv50.version = 0;
1202				args.nv50.ro = 0;
1203				args.nv50.kind = mem->kind;
1204				args.nv50.comp = mem->comp;
1205				argc = sizeof(args.nv50);
1206				break;
1207			case NVIF_CLASS_MEM_GF100:
1208				args.gf100.version = 0;
1209				args.gf100.ro = 0;
1210				args.gf100.kind = mem->kind;
1211				argc = sizeof(args.gf100);
1212				break;
1213			default:
1214				WARN_ON(1);
1215				break;
1216			}
1217
1218			ret = nvif_object_map_handle(&mem->mem.object,
1219						     &args, argc,
1220						     &handle, &length);
1221			if (ret != 1) {
1222				if (WARN_ON(ret == 0))
1223					ret = -EINVAL;
1224				goto out;
1225			}
1226
1227			reg->bus.offset = handle;
1228		}
1229		ret = 0;
1230		break;
1231	default:
1232		ret = -EINVAL;
1233	}
1234
1235out:
1236	if (ret == -ENOSPC) {
1237		struct nouveau_bo *nvbo;
1238
1239		nvbo = list_first_entry_or_null(&drm->ttm.io_reserve_lru,
1240						typeof(*nvbo),
1241						io_reserve_lru);
1242		if (nvbo) {
1243			list_del_init(&nvbo->io_reserve_lru);
1244			drm_vma_node_unmap(&nvbo->bo.base.vma_node,
1245					   bdev->dev_mapping);
1246			nouveau_ttm_io_mem_free_locked(drm, &nvbo->bo.mem);
1247			goto retry;
1248		}
1249
1250	}
1251	mutex_unlock(&drm->ttm.io_reserve_mutex);
1252	return ret;
1253}
1254
1255static void
1256nouveau_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_resource *reg)
1257{
1258	struct nouveau_drm *drm = nouveau_bdev(bdev);
1259
1260	mutex_lock(&drm->ttm.io_reserve_mutex);
1261	nouveau_ttm_io_mem_free_locked(drm, reg);
1262	mutex_unlock(&drm->ttm.io_reserve_mutex);
1263}
1264
1265static int
1266nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
1267{
1268	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
1269	struct nouveau_bo *nvbo = nouveau_bo(bo);
1270	struct nvkm_device *device = nvxx_device(&drm->client.device);
1271	u32 mappable = device->func->resource_size(device, 1) >> PAGE_SHIFT;
1272	int i, ret;
1273
1274	/* as long as the bo isn't in vram, and isn't tiled, we've got
1275	 * nothing to do here.
1276	 */
1277	if (bo->mem.mem_type != TTM_PL_VRAM) {
1278		if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA ||
1279		    !nvbo->kind)
1280			return 0;
1281
1282		if (bo->mem.mem_type == TTM_PL_SYSTEM) {
1283			nouveau_bo_placement_set(nvbo, NOUVEAU_GEM_DOMAIN_GART,
1284						 0);
1285
1286			ret = nouveau_bo_validate(nvbo, false, false);
1287			if (ret)
1288				return ret;
1289		}
1290		return 0;
1291	}
1292
1293	/* make sure bo is in mappable vram */
1294	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA ||
1295	    bo->mem.start + bo->mem.num_pages < mappable)
1296		return 0;
1297
1298	for (i = 0; i < nvbo->placement.num_placement; ++i) {
1299		nvbo->placements[i].fpfn = 0;
1300		nvbo->placements[i].lpfn = mappable;
1301	}
1302
1303	for (i = 0; i < nvbo->placement.num_busy_placement; ++i) {
1304		nvbo->busy_placements[i].fpfn = 0;
1305		nvbo->busy_placements[i].lpfn = mappable;
1306	}
1307
1308	nouveau_bo_placement_set(nvbo, NOUVEAU_GEM_DOMAIN_VRAM, 0);
1309	return nouveau_bo_validate(nvbo, false, false);
1310}
1311
1312static int
1313nouveau_ttm_tt_populate(struct ttm_bo_device *bdev,
1314			struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
1315{
1316	struct ttm_dma_tt *ttm_dma = (void *)ttm;
1317	struct nouveau_drm *drm;
1318	struct device *dev;
1319	bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG);
1320
1321	if (ttm_tt_is_populated(ttm))
1322		return 0;
1323
1324	if (slave && ttm->sg) {
1325		/* make userspace faulting work */
1326		drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
1327						 ttm_dma->dma_address, ttm->num_pages);
1328		ttm_tt_set_populated(ttm);
1329		return 0;
1330	}
1331
1332	drm = nouveau_bdev(bdev);
1333	dev = drm->dev->dev;
1334
1335#if IS_ENABLED(CONFIG_AGP)
1336	if (drm->agp.bridge) {
1337		return ttm_pool_populate(ttm, ctx);
1338	}
1339#endif
1340
1341#if IS_ENABLED(CONFIG_SWIOTLB) && IS_ENABLED(CONFIG_X86)
1342	if (swiotlb_nr_tbl()) {
1343		return ttm_dma_populate((void *)ttm, dev, ctx);
1344	}
1345#endif
1346	return ttm_populate_and_map_pages(dev, ttm_dma, ctx);
1347}
1348
1349static void
1350nouveau_ttm_tt_unpopulate(struct ttm_bo_device *bdev,
1351			  struct ttm_tt *ttm)
1352{
1353	struct ttm_dma_tt *ttm_dma = (void *)ttm;
1354	struct nouveau_drm *drm;
1355	struct device *dev;
1356	bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG);
1357
1358	if (slave)
1359		return;
1360
1361	drm = nouveau_bdev(bdev);
1362	dev = drm->dev->dev;
1363
1364#if IS_ENABLED(CONFIG_AGP)
1365	if (drm->agp.bridge) {
1366		ttm_pool_unpopulate(ttm);
1367		return;
1368	}
1369#endif
1370
1371#if IS_ENABLED(CONFIG_SWIOTLB) && IS_ENABLED(CONFIG_X86)
1372	if (swiotlb_nr_tbl()) {
1373		ttm_dma_unpopulate((void *)ttm, dev);
1374		return;
1375	}
1376#endif
1377
1378	ttm_unmap_and_unpopulate_pages(dev, ttm_dma);
1379}
1380
1381static void
1382nouveau_ttm_tt_destroy(struct ttm_bo_device *bdev,
1383		       struct ttm_tt *ttm)
1384{
1385#if IS_ENABLED(CONFIG_AGP)
1386	struct nouveau_drm *drm = nouveau_bdev(bdev);
1387	if (drm->agp.bridge) {
1388		ttm_agp_unbind(ttm);
1389		ttm_tt_destroy_common(bdev, ttm);
1390		ttm_agp_destroy(ttm);
1391		return;
1392	}
1393#endif
1394	nouveau_sgdma_destroy(bdev, ttm);
1395}
1396
1397void
1398nouveau_bo_fence(struct nouveau_bo *nvbo, struct nouveau_fence *fence, bool exclusive)
1399{
1400	struct dma_resv *resv = nvbo->bo.base.resv;
1401
1402	if (exclusive)
1403		dma_resv_add_excl_fence(resv, &fence->base);
1404	else if (fence)
1405		dma_resv_add_shared_fence(resv, &fence->base);
1406}
1407
1408struct ttm_bo_driver nouveau_bo_driver = {
1409	.ttm_tt_create = &nouveau_ttm_tt_create,
1410	.ttm_tt_populate = &nouveau_ttm_tt_populate,
1411	.ttm_tt_unpopulate = &nouveau_ttm_tt_unpopulate,
1412	.ttm_tt_bind = &nouveau_ttm_tt_bind,
1413	.ttm_tt_unbind = &nouveau_ttm_tt_unbind,
1414	.ttm_tt_destroy = &nouveau_ttm_tt_destroy,
1415	.eviction_valuable = ttm_bo_eviction_valuable,
1416	.evict_flags = nouveau_bo_evict_flags,
1417	.move_notify = nouveau_bo_move_ntfy,
1418	.move = nouveau_bo_move,
1419	.verify_access = nouveau_bo_verify_access,
1420	.fault_reserve_notify = &nouveau_ttm_fault_reserve_notify,
1421	.io_mem_reserve = &nouveau_ttm_io_mem_reserve,
1422	.io_mem_free = &nouveau_ttm_io_mem_free,
1423};
1424