summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
blob: 134cc36e30c5ebfa2ce4ef054f375d5cc993a2d9 (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
/*
 * Copyright 2016 Advanced Micro Devices, Inc.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 * OTHER DEALINGS IN THE SOFTWARE.
 *
 * Authors: Christian König
 */

#include <linux/dma-mapping.h>
#include "amdgpu.h"
#include "amdgpu_vm.h"
#include "amdgpu_atomfirmware.h"
#include "atom.h"

struct amdgpu_vram_mgr {
	struct drm_mm mm;
	spinlock_t lock;
	atomic64_t usage;
	atomic64_t vis_usage;
};

/**
 * DOC: mem_info_vram_total
 *
 * The amdgpu driver provides a sysfs API for reporting current total VRAM
 * available on the device
 * The file mem_info_vram_total is used for this and returns the total
 * amount of VRAM in bytes
 */
static ssize_t amdgpu_mem_info_vram_total_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct drm_device *ddev = dev_get_drvdata(dev);
	struct amdgpu_device *adev = ddev->dev_private;

	return snprintf(buf, PAGE_SIZE, "%llu\n", adev->gmc.real_vram_size);
}

/**
 * DOC: mem_info_vis_vram_total
 *
 * The amdgpu driver provides a sysfs API for reporting current total
 * visible VRAM available on the device
 * The file mem_info_vis_vram_total is used for this and returns the total
 * amount of visible VRAM in bytes
 */
static ssize_t amdgpu_mem_info_vis_vram_total_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct drm_device *ddev = dev_get_drvdata(dev);
	struct amdgpu_device *adev = ddev->dev_private;

	return snprintf(buf, PAGE_SIZE, "%llu\n", adev->gmc.visible_vram_size);
}

/**
 * DOC: mem_info_vram_used
 *
 * The amdgpu driver provides a sysfs API for reporting current total VRAM
 * available on the device
 * The file mem_info_vram_used is used for this and returns the total
 * amount of currently used VRAM in bytes
 */
static ssize_t amdgpu_mem_info_vram_used_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct drm_device *ddev = dev_get_drvdata(dev);
	struct amdgpu_device *adev = ddev->dev_private;

	return snprintf(buf, PAGE_SIZE, "%llu\n",
		amdgpu_vram_mgr_usage(&adev->mman.bdev.man[TTM_PL_VRAM]));
}

/**
 * DOC: mem_info_vis_vram_used
 *
 * The amdgpu driver provides a sysfs API for reporting current total of
 * used visible VRAM
 * The file mem_info_vis_vram_used is used for this and returns the total
 * amount of currently used visible VRAM in bytes
 */
static ssize_t amdgpu_mem_info_vis_vram_used_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct drm_device *ddev = dev_get_drvdata(dev);
	struct amdgpu_device *adev = ddev->dev_private;

	return snprintf(buf, PAGE_SIZE, "%llu\n",
		amdgpu_vram_mgr_vis_usage(&adev->mman.bdev.man[TTM_PL_VRAM]));
}

static ssize_t amdgpu_mem_info_vram_vendor(struct device *dev,
						 struct device_attribute *attr,
						 char *buf)
{
	struct drm_device *ddev = dev_get_drvdata(dev);
	struct amdgpu_device *adev = ddev->dev_private;

	switch (adev->gmc.vram_vendor) {
	case SAMSUNG:
		return snprintf(buf, PAGE_SIZE, "samsung\n");
	case INFINEON:
		return snprintf(buf, PAGE_SIZE, "infineon\n");
	case ELPIDA:
		return snprintf(buf, PAGE_SIZE, "elpida\n");
	case ETRON:
		return snprintf(buf, PAGE_SIZE, "etron\n");
	case NANYA:
		return snprintf(buf, PAGE_SIZE, "nanya\n");
	case HYNIX:
		return snprintf(buf, PAGE_SIZE, "hynix\n");
	case MOSEL:
		return snprintf(buf, PAGE_SIZE, "mosel\n");
	case WINBOND:
		return snprintf(buf, PAGE_SIZE, "winbond\n");
	case ESMT:
		return snprintf(buf, PAGE_SIZE, "esmt\n");
	case MICRON:
		return snprintf(buf, PAGE_SIZE, "micron\n");
	default:
		return snprintf(buf, PAGE_SIZE, "unknown\n");
	}
}

static DEVICE_ATTR(mem_info_vram_total, S_IRUGO,
		   amdgpu_mem_info_vram_total_show, NULL);
static DEVICE_ATTR(mem_info_vis_vram_total, S_IRUGO,
		   amdgpu_mem_info_vis_vram_total_show,NULL);
static DEVICE_ATTR(mem_info_vram_used, S_IRUGO,
		   amdgpu_mem_info_vram_used_show, NULL);
static DEVICE_ATTR(mem_info_vis_vram_used, S_IRUGO,
		   amdgpu_mem_info_vis_vram_used_show, NULL);
static DEVICE_ATTR(mem_info_vram_vendor, S_IRUGO,
		   amdgpu_mem_info_vram_vendor, NULL);

static const struct attribute *amdgpu_vram_mgr_attributes[] = {
	&dev_attr_mem_info_vram_total.attr,
	&dev_attr_mem_info_vis_vram_total.attr,
	&dev_attr_mem_info_vram_used.attr,
	&dev_attr_mem_info_vis_vram_used.attr,
	&dev_attr_mem_info_vram_vendor.attr,
	NULL
};

/**
 * amdgpu_vram_mgr_init - init VRAM manager and DRM MM
 *
 * @man: TTM memory type manager
 * @p_size: maximum size of VRAM
 *
 * Allocate and initialize the VRAM manager.
 */
static int amdgpu_vram_mgr_init(struct ttm_mem_type_manager *man,
				unsigned long p_size)
{
	struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev);
	struct amdgpu_vram_mgr *mgr;
	int ret;

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

	drm_mm_init(&mgr->mm, 0, p_size);
	spin_lock_init(&mgr->lock);
	man->priv = mgr;

	/* Add the two VRAM-related sysfs files */
	ret = sysfs_create_files(&adev->dev->kobj, amdgpu_vram_mgr_attributes);
	if (ret)
		DRM_ERROR("Failed to register sysfs\n");

	return 0;
}

/**
 * amdgpu_vram_mgr_fini - free and destroy VRAM manager
 *
 * @man: TTM memory type manager
 *
 * Destroy and free the VRAM manager, returns -EBUSY if ranges are still
 * allocated inside it.
 */
static int amdgpu_vram_mgr_fini(struct ttm_mem_type_manager *man)
{
	struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev);
	struct amdgpu_vram_mgr *mgr = man->priv;

	spin_lock(&mgr->lock);
	drm_mm_takedown(&mgr->mm);
	spin_unlock(&mgr->lock);
	kfree(mgr);
	man->priv = NULL;
	sysfs_remove_files(&adev->dev->kobj, amdgpu_vram_mgr_attributes);
	return 0;
}

/**
 * amdgpu_vram_mgr_vis_size - Calculate visible node size
 *
 * @adev: amdgpu device structure
 * @node: MM node structure
 *
 * Calculate how many bytes of the MM node are inside visible VRAM
 */
static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev,
				    struct drm_mm_node *node)
{
	uint64_t start = node->start << PAGE_SHIFT;
	uint64_t end = (node->size + node->start) << PAGE_SHIFT;

	if (start >= adev->gmc.visible_vram_size)
		return 0;

	return (end > adev->gmc.visible_vram_size ?
		adev->gmc.visible_vram_size : end) - start;
}

/**
 * amdgpu_vram_mgr_bo_visible_size - CPU visible BO size
 *
 * @bo: &amdgpu_bo buffer object (must be in VRAM)
 *
 * Returns:
 * How much of the given &amdgpu_bo buffer object lies in CPU visible VRAM.
 */
u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo)
{
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
	struct ttm_mem_reg *mem = &bo->tbo.mem;
	struct drm_mm_node *nodes = mem->mm_node;
	unsigned pages = mem->num_pages;
	u64 usage;

	if (amdgpu_gmc_vram_full_visible(&adev->gmc))
		return amdgpu_bo_size(bo);

	if (mem->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT)
		return 0;

	for (usage = 0; nodes && pages; pages -= nodes->size, nodes++)
		usage += amdgpu_vram_mgr_vis_size(adev, nodes);

	return usage;
}

/**
 * amdgpu_vram_mgr_virt_start - update virtual start address
 *
 * @mem: ttm_mem_reg to update
 * @node: just allocated node
 *
 * Calculate a virtual BO start address to easily check if everything is CPU
 * accessible.
 */
static void amdgpu_vram_mgr_virt_start(struct ttm_mem_reg *mem,
				       struct drm_mm_node *node)
{
	unsigned long start;

	start = node->start + node->size;
	if (start > mem->num_pages)
		start -= mem->num_pages;
	else
		start = 0;
	mem->start = max(mem->start, start);
}

/**
 * amdgpu_vram_mgr_new - allocate new ranges
 *
 * @man: TTM memory type manager
 * @tbo: TTM BO we need this range for
 * @place: placement flags and restrictions
 * @mem: the resulting mem object
 *
 * Allocate VRAM for the given BO.
 */
static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,
			       struct ttm_buffer_object *tbo,
			       const struct ttm_place *place,
			       struct ttm_mem_reg *mem)
{
	struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev);
	struct amdgpu_vram_mgr *mgr = man->priv;
	struct drm_mm *mm = &mgr->mm;
	struct drm_mm_node *nodes;
	enum drm_mm_insert_mode mode;
	unsigned long lpfn, num_nodes, pages_per_node, pages_left;
	uint64_t vis_usage = 0, mem_bytes, max_bytes;
	unsigned i;
	int r;

	lpfn = place->lpfn;
	if (!lpfn)
		lpfn = man->size;

	max_bytes = adev->gmc.mc_vram_size;
	if (tbo->type != ttm_bo_type_kernel)
		max_bytes -= AMDGPU_VM_RESERVED_VRAM;

	/* bail out quickly if there's likely not enough VRAM for this BO */
	mem_bytes = (u64)mem->num_pages << PAGE_SHIFT;
	if (atomic64_add_return(mem_bytes, &mgr->usage) > max_bytes) {
		atomic64_sub(mem_bytes, &mgr->usage);
		return -ENOSPC;
	}

	if (place->flags & TTM_PL_FLAG_CONTIGUOUS) {
		pages_per_node = ~0ul;
		num_nodes = 1;
	} else {
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
		pages_per_node = HPAGE_PMD_NR;
#else
		/* default to 2MB */
		pages_per_node = (2UL << (20UL - PAGE_SHIFT));
#endif
		pages_per_node = max((uint32_t)pages_per_node, mem->page_alignment);
		num_nodes = DIV_ROUND_UP(mem->num_pages, pages_per_node);
	}

	nodes = kvmalloc_array((uint32_t)num_nodes, sizeof(*nodes),
			       GFP_KERNEL | __GFP_ZERO);
	if (!nodes) {
		atomic64_sub(mem_bytes, &mgr->usage);
		return -ENOMEM;
	}

	mode = DRM_MM_INSERT_BEST;
	if (place->flags & TTM_PL_FLAG_TOPDOWN)
		mode = DRM_MM_INSERT_HIGH;

	mem->start = 0;
	pages_left = mem->num_pages;

	spin_lock(&mgr->lock);
	for (i = 0; pages_left >= pages_per_node; ++i) {
		unsigned long pages = rounddown_pow_of_two(pages_left);

		r = drm_mm_insert_node_in_range(mm, &nodes[i], pages,
						pages_per_node, 0,
						place->fpfn, lpfn,
						mode);
		if (unlikely(r))
			break;

		vis_usage += amdgpu_vram_mgr_vis_size(adev, &nodes[i]);
		amdgpu_vram_mgr_virt_start(mem, &nodes[i]);
		pages_left -= pages;
	}

	for (; pages_left; ++i) {
		unsigned long pages = min(pages_left, pages_per_node);
		uint32_t alignment = mem->page_alignment;

		if (pages == pages_per_node)
			alignment = pages_per_node;

		r = drm_mm_insert_node_in_range(mm, &nodes[i],
						pages, alignment, 0,
						place->fpfn, lpfn,
						mode);
		if (unlikely(r))
			goto error;

		vis_usage += amdgpu_vram_mgr_vis_size(adev, &nodes[i]);
		amdgpu_vram_mgr_virt_start(mem, &nodes[i]);
		pages_left -= pages;
	}
	spin_unlock(&mgr->lock);

	atomic64_add(vis_usage, &mgr->vis_usage);

	mem->mm_node = nodes;

	return 0;

error:
	while (i--)
		drm_mm_remove_node(&nodes[i]);
	spin_unlock(&mgr->lock);
	atomic64_sub(mem->num_pages << PAGE_SHIFT, &mgr->usage);

	kvfree(nodes);
	return r;
}

/**
 * amdgpu_vram_mgr_del - free ranges
 *
 * @man: TTM memory type manager
 * @mem: TTM memory object
 *
 * Free the allocated VRAM again.
 */
static void amdgpu_vram_mgr_del(struct ttm_mem_type_manager *man,
				struct ttm_mem_reg *mem)
{
	struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev);
	struct amdgpu_vram_mgr *mgr = man->priv;
	struct drm_mm_node *nodes = mem->mm_node;
	uint64_t usage = 0, vis_usage = 0;
	unsigned pages = mem->num_pages;

	if (!mem->mm_node)
		return;

	spin_lock(&mgr->lock);
	while (pages) {
		pages -= nodes->size;
		drm_mm_remove_node(nodes);
		usage += nodes->size << PAGE_SHIFT;
		vis_usage += amdgpu_vram_mgr_vis_size(adev, nodes);
		++nodes;
	}
	spin_unlock(&mgr->lock);

	atomic64_sub(usage, &mgr->usage);
	atomic64_sub(vis_usage, &mgr->vis_usage);

	kvfree(mem->mm_node);
	mem->mm_node = NULL;
}

/**
 * amdgpu_vram_mgr_alloc_sgt - allocate and fill a sg table
 *
 * @adev: amdgpu device pointer
 * @mem: TTM memory object
 * @dev: the other device
 * @dir: dma direction
 * @sgt: resulting sg table
 *
 * Allocate and fill a sg table from a VRAM allocation.
 */
int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
			      struct ttm_mem_reg *mem,
			      struct device *dev,
			      enum dma_data_direction dir,
			      struct sg_table **sgt)
{
	struct drm_mm_node *node;
	struct scatterlist *sg;
	int num_entries = 0;
	unsigned int pages;
	int i, r;

	*sgt = kmalloc(sizeof(*sg), GFP_KERNEL);
	if (!*sgt)
		return -ENOMEM;

	for (pages = mem->num_pages, node = mem->mm_node;
	     pages; pages -= node->size, ++node)
		++num_entries;

	r = sg_alloc_table(*sgt, num_entries, GFP_KERNEL);
	if (r)
		goto error_free;

	for_each_sgtable_sg((*sgt), sg, i)
		sg->length = 0;

	node = mem->mm_node;
	for_each_sgtable_sg((*sgt), sg, i) {
		phys_addr_t phys = (node->start << PAGE_SHIFT) +
			adev->gmc.aper_base;
		size_t size = node->size << PAGE_SHIFT;
		dma_addr_t addr;

		++node;
		addr = dma_map_resource(dev, phys, size, dir,
					DMA_ATTR_SKIP_CPU_SYNC);
		r = dma_mapping_error(dev, addr);
		if (r)
			goto error_unmap;

		sg_set_page(sg, NULL, size, 0);
		sg_dma_address(sg) = addr;
		sg_dma_len(sg) = size;
	}
	return 0;

error_unmap:
	for_each_sgtable_sg((*sgt), sg, i) {
		if (!sg->length)
			continue;

		dma_unmap_resource(dev, sg->dma_address,
				   sg->length, dir,
				   DMA_ATTR_SKIP_CPU_SYNC);
	}
	sg_free_table(*sgt);

error_free:
	kfree(*sgt);
	return r;
}

/**
 * amdgpu_vram_mgr_alloc_sgt - allocate and fill a sg table
 *
 * @adev: amdgpu device pointer
 * @sgt: sg table to free
 *
 * Free a previously allocate sg table.
 */
void amdgpu_vram_mgr_free_sgt(struct amdgpu_device *adev,
			      struct device *dev,
			      enum dma_data_direction dir,
			      struct sg_table *sgt)
{
	struct scatterlist *sg;
	int i;

	for_each_sgtable_sg(sgt, sg, i)
		dma_unmap_resource(dev, sg->dma_address,
				   sg->length, dir,
				   DMA_ATTR_SKIP_CPU_SYNC);
	sg_free_table(sgt);
	kfree(sgt);
}

/**
 * amdgpu_vram_mgr_usage - how many bytes are used in this domain
 *
 * @man: TTM memory type manager
 *
 * Returns how many bytes are used in this domain.
 */
uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man)
{
	struct amdgpu_vram_mgr *mgr = man->priv;

	return atomic64_read(&mgr->usage);
}

/**
 * amdgpu_vram_mgr_vis_usage - how many bytes are used in the visible part
 *
 * @man: TTM memory type manager
 *
 * Returns how many bytes are used in the visible part of VRAM
 */
uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man)
{
	struct amdgpu_vram_mgr *mgr = man->priv;

	return atomic64_read(&mgr->vis_usage);
}

/**
 * amdgpu_vram_mgr_debug - dump VRAM table
 *
 * @man: TTM memory type manager
 * @printer: DRM printer to use
 *
 * Dump the table content using printk.
 */
static void amdgpu_vram_mgr_debug(struct ttm_mem_type_manager *man,
				  struct drm_printer *printer)
{
	struct amdgpu_vram_mgr *mgr = man->priv;

	spin_lock(&mgr->lock);
	drm_mm_print(&mgr->mm, printer);
	spin_unlock(&mgr->lock);

	drm_printf(printer, "man size:%llu pages, ram usage:%lluMB, vis usage:%lluMB\n",
		   man->size, amdgpu_vram_mgr_usage(man) >> 20,
		   amdgpu_vram_mgr_vis_usage(man) >> 20);
}

const struct ttm_mem_type_manager_func amdgpu_vram_mgr_func = {
	.init		= amdgpu_vram_mgr_init,
	.takedown	= amdgpu_vram_mgr_fini,
	.get_node	= amdgpu_vram_mgr_new,
	.put_node	= amdgpu_vram_mgr_del,
	.debug		= amdgpu_vram_mgr_debug
};