aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/ttm/ttm_bo_util.c
blob: 5ca37a58a98c80be24beb227cef980f2cdbf7abf (plain) (blame)
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
/**************************************************************************
 *
 * Copyright (c) 2007-2009 VMware, Inc., Palo Alto, CA., USA
 * 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 above copyright notice and this permission notice (including the
 * next paragraph) 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 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.
 *
 **************************************************************************/
/*
 * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com>
 */

#include "ttm/ttm_bo_driver.h"
#include "ttm/ttm_placement.h"
#include <linux/io.h>
#include <linux/highmem.h>
#include <linux/wait.h>
#include <linux/vmalloc.h>
#include <linux/module.h>

void ttm_bo_free_old_node(struct ttm_buffer_object *bo)
{
	struct ttm_mem_reg *old_mem = &bo->mem;

	if (old_mem->mm_node) {
		spin_lock(&bo->glob->lru_lock);
		drm_mm_put_block(old_mem->mm_node);
		spin_unlock(&bo->glob->lru_lock);
	}
	old_mem->mm_node = NULL;
}

int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
		    bool evict, bool no_wait, struct ttm_mem_reg *new_mem)
{
	struct ttm_tt *ttm = bo->ttm;
	struct ttm_mem_reg *old_mem = &bo->mem;
	int ret;

	if (old_mem->mem_type != TTM_PL_SYSTEM) {
		ttm_tt_unbind(ttm);
		ttm_bo_free_old_node(bo);
		ttm_flag_masked(&old_mem->placement, TTM_PL_FLAG_SYSTEM,
				TTM_PL_MASK_MEM);
		old_mem->mem_type = TTM_PL_SYSTEM;
	}

	ret = ttm_tt_set_placement_caching(ttm, new_mem->placement);
	if (unlikely(ret != 0))
		return ret;

	if (new_mem->mem_type != TTM_PL_SYSTEM) {
		ret = ttm_tt_bind(ttm, new_mem);
		if (unlikely(ret != 0))
			return ret;
	}

	*old_mem = *new_mem;
	new_mem->mm_node = NULL;

	return 0;
}
EXPORT_SYMBOL(ttm_bo_move_ttm);

int ttm_mem_reg_ioremap(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem,
			void **virtual)
{
	struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type];
	unsigned long bus_offset;
	unsigned long bus_size;
	unsigned long bus_base;
	int ret;
	void *addr;

	*virtual = NULL;
	ret = ttm_bo_pci_offset(bdev, mem, &bus_base, &bus_offset, &bus_size);
	if (ret || bus_size == 0)
		return ret;

	if (!(man->flags & TTM_MEMTYPE_FLAG_NEEDS_IOREMAP))
		addr = (void *)(((u8 *) man->io_addr) + bus_offset);
	else {
		if (mem->placement & TTM_PL_FLAG_WC)
			addr = ioremap_wc(bus_base + bus_offset, bus_size);
		else
			addr = ioremap_nocache(bus_base + bus_offset, bus_size);
		if (!addr)
			return -ENOMEM;
	}
	*virtual = addr;
	return 0;
}

void ttm_mem_reg_iounmap(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem,
			 void *virtual)
{
	struct ttm_mem_type_manager *man;

	man = &bdev->man[mem->mem_type];

	if (virtual && (man->flags & TTM_MEMTYPE_FLAG_NEEDS_IOREMAP))
		iounmap(virtual);
}

static int ttm_copy_io_page(void *dst, void *src, unsigned long page)
{
	uint32_t *dstP =
	    (uint32_t *) ((unsigned long)dst + (page << PAGE_SHIFT));
	uint32_t *srcP =
	    (uint32_t *) ((unsigned long)src + (page << PAGE_SHIFT));

	int i;
	for (i = 0; i < PAGE_SIZE / sizeof(uint32_t); ++i)
		iowrite32(ioread32(srcP++), dstP++);
	return 0;
}

static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void *src,
				unsigned long page,
				pgprot_t prot)
{
	struct page *d = ttm_tt_get_page(ttm, page);
	void *dst;

	if (!d)
		return -ENOMEM;

	src = (void *)((unsigned long)src + (page << PAGE_SHIFT));

#ifdef CONFIG_X86
	dst = kmap_atomic_prot(d, KM_USER0, prot);
#else
	if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL))
		dst = vmap(&d, 1, 0, prot);
	else
		dst = kmap(d);
#endif
	if (!dst)
		return -ENOMEM;

	memcpy_fromio(dst, src, PAGE_SIZE);

#ifdef CONFIG_X86
	kunmap_atomic(dst, KM_USER0);
#else
	if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL))
		vunmap(dst);
	else
		kunmap(d);
#endif

	return 0;
}

static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst,
				unsigned long page,
				pgprot_t prot)
{
	struct page *s = ttm_tt_get_page(ttm, page);
	void *src;

	if (!s)
		return -ENOMEM;

	dst = (void *)((unsigned long)dst + (page << PAGE_SHIFT));
#ifdef CONFIG_X86
	src = kmap_atomic_prot(s, KM_USER0, prot);
#else
	if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL))
		src = vmap(&s, 1, 0, prot);
	else
		src = kmap(s);
#endif
	if (!src)
		return -ENOMEM;

	memcpy_toio(dst, src, PAGE_SIZE);

#ifdef CONFIG_X86
	kunmap_atomic(src, KM_USER0);
#else
	if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL))
		vunmap(src);
	else
		kunmap(s);
#endif

	return 0;
}

int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
		       bool evict, bool no_wait, struct ttm_mem_reg *new_mem)
{
	struct ttm_bo_device *bdev = bo->bdev;
	struct ttm_mem_type_manager *man = &bdev->man[new_mem->mem_type];
	struct ttm_tt *ttm = bo->ttm;
	struct ttm_mem_reg *old_mem = &bo->mem;
	struct ttm_mem_reg old_copy = *old_mem;
	void *old_iomap;
	void *new_iomap;
	int ret;
	unsigned long i;
	unsigned long page;
	unsigned long add = 0;
	int dir;

	ret = ttm_mem_reg_ioremap(bdev, old_mem, &old_iomap);
	if (ret)
		return ret;
	ret = ttm_mem_reg_ioremap(bdev, new_mem, &new_iomap);
	if (ret)
		goto out;

	if (old_iomap == NULL && new_iomap == NULL)
		goto out2;
	if (old_iomap == NULL && ttm == NULL)
		goto out2;

	add = 0;
	dir = 1;

	if ((old_mem->mem_type == new_mem->mem_type) &&
	    (new_mem->mm_node->start <
	     old_mem->mm_node->start + old_mem->mm_node->size)) {
		dir = -1;
		add = new_mem->num_pages - 1;
	}

	for (i = 0; i < new_mem->num_pages; ++i) {
		page = i * dir + add;
		if (old_iomap == NULL) {
			pgprot_t prot = ttm_io_prot(old_mem->placement,
						    PAGE_KERNEL);
			ret = ttm_copy_ttm_io_page(ttm, new_iomap, page,
						   prot);
		} else if (new_iomap == NULL) {
			pgprot_t prot = ttm_io_prot(new_mem->placement,
						    PAGE_KERNEL);
			ret = ttm_copy_io_ttm_page(ttm, old_iomap, page,
						   prot);
		} else
			ret = ttm_copy_io_page(new_iomap, old_iomap, page);
		if (ret)
			goto out1;
	}
	mb();
out2:
	ttm_bo_free_old_node(bo);

	*old_mem = *new_mem;
	new_mem->mm_node = NULL;

	if ((man->flags & TTM_MEMTYPE_FLAG_FIXED) && (ttm != NULL)) {
		ttm_tt_unbind(ttm);
		ttm_tt_destroy(ttm);
		bo->ttm = NULL;
	}

out1:
	ttm_mem_reg_iounmap(bdev, new_mem, new_iomap);
out:
	ttm_mem_reg_iounmap(bdev, &old_copy, old_iomap);
	return ret;
}
EXPORT_SYMBOL(ttm_bo_move_memcpy);

static void ttm_transfered_destroy(struct ttm_buffer_object *bo)
{
	kfree(bo);
}

/**
 * ttm_buffer_object_transfer
 *
 * @bo: A pointer to a struct ttm_buffer_object.
 * @new_obj: A pointer to a pointer to a newly created ttm_buffer_object,
 * holding the data of @bo with the old placement.
 *
 * This is a utility function that may be called after an accelerated move
 * has been scheduled. A new buffer object is created as a placeholder for
 * the old data while it's being copied. When that buffer object is idle,
 * it can be destroyed, releasing the space of the old placement.
 * Returns:
 * !0: Failure.
 */

static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
				      struct ttm_buffer_object **new_obj)
{
	struct ttm_buffer_object *fbo;
	struct ttm_bo_device *bdev = bo->bdev;
	struct ttm_bo_driver *driver = bdev->driver;

	fbo = kzalloc(sizeof(*fbo), GFP_KERNEL);
	if (!fbo)
		return -ENOMEM;

	*fbo = *bo;

	/**
	 * Fix up members that we shouldn't copy directly:
	 * TODO: Explicit member copy would probably be better here.
	 */

	spin_lock_init(&fbo->lock);
	init_waitqueue_head(&fbo->event_queue);
	INIT_LIST_HEAD(&fbo->ddestroy);
	INIT_LIST_HEAD(&fbo->lru);
	INIT_LIST_HEAD(&fbo->swap);
	fbo->vm_node = NULL;

	fbo->sync_obj = driver->sync_obj_ref(bo->sync_obj);
	if (fbo->mem.mm_node)
		fbo->mem.mm_node->private = (void *)fbo;
	kref_init(&fbo->list_kref);
	kref_init(&fbo->kref);
	fbo->destroy = &ttm_transfered_destroy;

	*new_obj = fbo;
	return 0;
}

pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp)
{
#if defined(__i386__) || defined(__x86_64__)
	if (caching_flags & TTM_PL_FLAG_WC)
		tmp = pgprot_writecombine(tmp);
	else if (boot_cpu_data.x86 > 3)
		tmp = pgprot_noncached(tmp);

#elif defined(__powerpc__)
	if (!(caching_flags & TTM_PL_FLAG_CACHED)) {
		pgprot_val(tmp) |= _PAGE_NO_CACHE;
		if (caching_flags & TTM_PL_FLAG_UNCACHED)
			pgprot_val(tmp) |= _PAGE_GUARDED;
	}
#endif
#if defined(__ia64__)
	if (caching_flags & TTM_PL_FLAG_WC)
		tmp = pgprot_writecombine(tmp);
	else
		tmp = pgprot_noncached(tmp);
#endif
#if defined(__sparc__)
	if (!(caching_flags & TTM_PL_FLAG_CACHED))
		tmp = pgprot_noncached(tmp);
#endif
	return tmp;
}
EXPORT_SYMBOL(ttm_io_prot);

static int ttm_bo_ioremap(struct ttm_buffer_object *bo,
			  unsigned long bus_base,
			  unsigned long bus_offset,
			  unsigned long bus_size,
			  struct ttm_bo_kmap_obj *map)
{
	struct ttm_bo_device *bdev = bo->bdev;
	struct ttm_mem_reg *mem = &bo->mem;
	struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type];

	if (!(man->flags & TTM_MEMTYPE_FLAG_NEEDS_IOREMAP)) {
		map->bo_kmap_type = ttm_bo_map_premapped;
		map->virtual = (void *)(((u8 *) man->io_addr) + bus_offset);
	} else {
		map->bo_kmap_type = ttm_bo_map_iomap;
		if (mem->placement & TTM_PL_FLAG_WC)
			map->virtual = ioremap_wc(bus_base + bus_offset,
						  bus_size);
		else
			map->virtual = ioremap_nocache(bus_base + bus_offset,
						       bus_size);
	}
	return (!map->virtual) ? -ENOMEM : 0;
}

static int ttm_bo_kmap_ttm(struct ttm_buffer_object *bo,
			   unsigned long start_page,
			   unsigned long num_pages,
			   struct ttm_bo_kmap_obj *map)
{
	struct ttm_mem_reg *mem = &bo->mem; pgprot_t prot;
	struct ttm_tt *ttm = bo->ttm;
	struct page *d;
	int i;

	BUG_ON(!ttm);
	if (num_pages == 1 && (mem->placement & TTM_PL_FLAG_CACHED)) {
		/*
		 * We're mapping a single page, and the desired
		 * page protection is consistent with the bo.
		 */

		map->bo_kmap_type = ttm_bo_map_kmap;
		map->page = ttm_tt_get_page(ttm, start_page);
		map->virtual = kmap(map->page);
	} else {
	    /*
	     * Populate the part we're mapping;
	     */
		for (i = start_page; i < start_page + num_pages; ++i) {
			d = ttm_tt_get_page(ttm, i);
			if (!d)
				return -ENOMEM;
		}

		/*
		 * We need to use vmap to get the desired page protection
		 * or to make the buffer object look contiguous.
		 */
		prot = (mem->placement & TTM_PL_FLAG_CACHED) ?
			PAGE_KERNEL :
			ttm_io_prot(mem->placement, PAGE_KERNEL);
		map->bo_kmap_type = ttm_bo_map_vmap;
		map->virtual = vmap(ttm->pages + start_page, num_pages,
				    0, prot);
	}
	return (!map->virtual) ? -ENOMEM : 0;
}

int ttm_bo_kmap(struct ttm_buffer_object *bo,
		unsigned long start_page, unsigned long num_pages,
		struct ttm_bo_kmap_obj *map)
{
	int ret;
	unsigned long bus_base;
	unsigned long bus_offset;
	unsigned long bus_size;

	BUG_ON(!list_empty(&bo->swap));
	map->virtual = NULL;
	if (num_pages > bo->num_pages)
		return -EINVAL;
	if (start_page > bo->num_pages)
		return -EINVAL;
#if 0
	if (num_pages > 1 && !DRM_SUSER(DRM_CURPROC))
		return -EPERM;
#endif
	ret = ttm_bo_pci_offset(bo->bdev, &bo->mem, &bus_base,
				&bus_offset, &bus_size);
	if (ret)
		return ret;
	if (bus_size == 0) {
		return ttm_bo_kmap_ttm(bo, start_page, num_pages, map);
	} else {
		bus_offset += start_page << PAGE_SHIFT;
		bus_size = num_pages << PAGE_SHIFT;
		return ttm_bo_ioremap(bo, bus_base, bus_offset, bus_size, map);
	}
}
EXPORT_SYMBOL(ttm_bo_kmap);

void ttm_bo_kunmap(struct ttm_bo_kmap_obj *map)
{
	if (!map->virtual)
		return;
	switch (map->bo_kmap_type) {
	case ttm_bo_map_iomap:
		iounmap(map->virtual);
		break;
	case ttm_bo_map_vmap:
		vunmap(map->virtual);
		break;
	case ttm_bo_map_kmap:
		kunmap(map->page);
		break;
	case ttm_bo_map_premapped:
		break;
	default:
		BUG();
	}
	map->virtual = NULL;
	map->page = NULL;
}
EXPORT_SYMBOL(ttm_bo_kunmap);

int ttm_bo_pfn_prot(struct ttm_buffer_object *bo,
		    unsigned long dst_offset,
		    unsigned long *pfn, pgprot_t *prot)
{
	struct ttm_mem_reg *mem = &bo->mem;
	struct ttm_bo_device *bdev = bo->bdev;
	unsigned long bus_offset;
	unsigned long bus_size;
	unsigned long bus_base;
	int ret;
	ret = ttm_bo_pci_offset(bdev, mem, &bus_base, &bus_offset,
			&bus_size);
	if (ret)
		return -EINVAL;
	if (bus_size != 0)
		*pfn = (bus_base + bus_offset + dst_offset) >> PAGE_SHIFT;
	else
		if (!bo->ttm)
			return -EINVAL;
		else
			*pfn = page_to_pfn(ttm_tt_get_page(bo->ttm,
							   dst_offset >>
							   PAGE_SHIFT));
	*prot = (mem->placement & TTM_PL_FLAG_CACHED) ?
		PAGE_KERNEL : ttm_io_prot(mem->placement, PAGE_KERNEL);

	return 0;
}

int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
			      void *sync_obj,
			      void *sync_obj_arg,
			      bool evict, bool no_wait,
			      struct ttm_mem_reg *new_mem)
{
	struct ttm_bo_device *bdev = bo->bdev;
	struct ttm_bo_driver *driver = bdev->driver;
	struct ttm_mem_type_manager *man = &bdev->man[new_mem->mem_type];
	struct ttm_mem_reg *old_mem = &bo->mem;
	int ret;
	struct ttm_buffer_object *ghost_obj;
	void *tmp_obj = NULL;

	spin_lock(&bo->lock);
	if (bo->sync_obj) {
		tmp_obj = bo->sync_obj;
		bo->sync_obj = NULL;
	}
	bo->sync_obj = driver->sync_obj_ref(sync_obj);
	bo->sync_obj_arg = sync_obj_arg;
	if (evict) {
		ret = ttm_bo_wait(bo, false, false, false);
		spin_unlock(&bo->lock);
		if (tmp_obj)
			driver->sync_obj_unref(&tmp_obj);
		if (ret)
			return ret;

		ttm_bo_free_old_node(bo);
		if ((man->flags & TTM_MEMTYPE_FLAG_FIXED) &&
		    (bo->ttm != NULL)) {
			ttm_tt_unbind(bo->ttm);
			ttm_tt_destroy(bo->ttm);
			bo->ttm = NULL;
		}
	} else {
		/**
		 * This should help pipeline ordinary buffer moves.
		 *
		 * Hang old buffer memory on a new buffer object,
		 * and leave it to be released when the GPU
		 * operation has completed.
		 */

		set_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
		spin_unlock(&bo->lock);
		if (tmp_obj)
			driver->sync_obj_unref(&tmp_obj);

		ret = ttm_buffer_object_transfer(bo, &ghost_obj);
		if (ret)
			return ret;

		/**
		 * If we're not moving to fixed memory, the TTM object
		 * needs to stay alive. Otherwhise hang it on the ghost
		 * bo to be unbound and destroyed.
		 */

		if (!(man->flags & TTM_MEMTYPE_FLAG_FIXED))
			ghost_obj->ttm = NULL;
		else
			bo->ttm = NULL;

		ttm_bo_unreserve(ghost_obj);
		ttm_bo_unref(&ghost_obj);
	}

	*old_mem = *new_mem;
	new_mem->mm_node = NULL;

	return 0;
}
EXPORT_SYMBOL(ttm_bo_move_accel_cleanup);