summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
blob: 74ff2812d66a1b9d08ae92db9f74bc58007b241e (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
// SPDX-License-Identifier: GPL-2.0 OR MIT
/**************************************************************************
 *
 * Copyright 2019-2023 VMware, Inc., Palo Alto, CA., USA
 *
 * 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.
 *
 **************************************************************************/
#include "vmwgfx_bo.h"
#include "vmwgfx_drv.h"

/*
 * Different methods for tracking dirty:
 * VMW_BO_DIRTY_PAGETABLE - Scan the pagetable for hardware dirty bits
 * VMW_BO_DIRTY_MKWRITE - Write-protect page table entries and record write-
 * accesses in the VM mkwrite() callback
 */
enum vmw_bo_dirty_method {
	VMW_BO_DIRTY_PAGETABLE,
	VMW_BO_DIRTY_MKWRITE,
};

/*
 * No dirtied pages at scan trigger a transition to the _MKWRITE method,
 * similarly a certain percentage of dirty pages trigger a transition to
 * the _PAGETABLE method. How many triggers should we wait for before
 * changing method?
 */
#define VMW_DIRTY_NUM_CHANGE_TRIGGERS 2

/* Percentage to trigger a transition to the _PAGETABLE method */
#define VMW_DIRTY_PERCENTAGE 10

/**
 * struct vmw_bo_dirty - Dirty information for buffer objects
 * @start: First currently dirty bit
 * @end: Last currently dirty bit + 1
 * @method: The currently used dirty method
 * @change_count: Number of consecutive method change triggers
 * @ref_count: Reference count for this structure
 * @bitmap_size: The size of the bitmap in bits. Typically equal to the
 * nuber of pages in the bo.
 * @bitmap: A bitmap where each bit represents a page. A set bit means a
 * dirty page.
 */
struct vmw_bo_dirty {
	unsigned long start;
	unsigned long end;
	enum vmw_bo_dirty_method method;
	unsigned int change_count;
	unsigned int ref_count;
	unsigned long bitmap_size;
	unsigned long bitmap[];
};

/**
 * vmw_bo_dirty_scan_pagetable - Perform a pagetable scan for dirty bits
 * @vbo: The buffer object to scan
 *
 * Scans the pagetable for dirty bits. Clear those bits and modify the
 * dirty structure with the results. This function may change the
 * dirty-tracking method.
 */
static void vmw_bo_dirty_scan_pagetable(struct vmw_bo *vbo)
{
	struct vmw_bo_dirty *dirty = vbo->dirty;
	pgoff_t offset = drm_vma_node_start(&vbo->tbo.base.vma_node);
	struct address_space *mapping = vbo->tbo.bdev->dev_mapping;
	pgoff_t num_marked;

	num_marked = clean_record_shared_mapping_range
		(mapping,
		 offset, dirty->bitmap_size,
		 offset, &dirty->bitmap[0],
		 &dirty->start, &dirty->end);
	if (num_marked == 0)
		dirty->change_count++;
	else
		dirty->change_count = 0;

	if (dirty->change_count > VMW_DIRTY_NUM_CHANGE_TRIGGERS) {
		dirty->change_count = 0;
		dirty->method = VMW_BO_DIRTY_MKWRITE;
		wp_shared_mapping_range(mapping,
					offset, dirty->bitmap_size);
		clean_record_shared_mapping_range(mapping,
						  offset, dirty->bitmap_size,
						  offset, &dirty->bitmap[0],
						  &dirty->start, &dirty->end);
	}
}

/**
 * vmw_bo_dirty_scan_mkwrite - Reset the mkwrite dirty-tracking method
 * @vbo: The buffer object to scan
 *
 * Write-protect pages written to so that consecutive write accesses will
 * trigger a call to mkwrite.
 *
 * This function may change the dirty-tracking method.
 */
static void vmw_bo_dirty_scan_mkwrite(struct vmw_bo *vbo)
{
	struct vmw_bo_dirty *dirty = vbo->dirty;
	unsigned long offset = drm_vma_node_start(&vbo->tbo.base.vma_node);
	struct address_space *mapping = vbo->tbo.bdev->dev_mapping;
	pgoff_t num_marked;

	if (dirty->end <= dirty->start)
		return;

	num_marked = wp_shared_mapping_range(vbo->tbo.bdev->dev_mapping,
					     dirty->start + offset,
					     dirty->end - dirty->start);

	if (100UL * num_marked / dirty->bitmap_size >
	    VMW_DIRTY_PERCENTAGE)
		dirty->change_count++;
	else
		dirty->change_count = 0;

	if (dirty->change_count > VMW_DIRTY_NUM_CHANGE_TRIGGERS) {
		pgoff_t start = 0;
		pgoff_t end = dirty->bitmap_size;

		dirty->method = VMW_BO_DIRTY_PAGETABLE;
		clean_record_shared_mapping_range(mapping, offset, end, offset,
						  &dirty->bitmap[0],
						  &start, &end);
		bitmap_clear(&dirty->bitmap[0], 0, dirty->bitmap_size);
		if (dirty->start < dirty->end)
			bitmap_set(&dirty->bitmap[0], dirty->start,
				   dirty->end - dirty->start);
		dirty->change_count = 0;
	}
}

/**
 * vmw_bo_dirty_scan - Scan for dirty pages and add them to the dirty
 * tracking structure
 * @vbo: The buffer object to scan
 *
 * This function may change the dirty tracking method.
 */
void vmw_bo_dirty_scan(struct vmw_bo *vbo)
{
	struct vmw_bo_dirty *dirty = vbo->dirty;

	if (dirty->method == VMW_BO_DIRTY_PAGETABLE)
		vmw_bo_dirty_scan_pagetable(vbo);
	else
		vmw_bo_dirty_scan_mkwrite(vbo);
}

/**
 * vmw_bo_dirty_pre_unmap - write-protect and pick up dirty pages before
 * an unmap_mapping_range operation.
 * @vbo: The buffer object,
 * @start: First page of the range within the buffer object.
 * @end: Last page of the range within the buffer object + 1.
 *
 * If we're using the _PAGETABLE scan method, we may leak dirty pages
 * when calling unmap_mapping_range(). This function makes sure we pick
 * up all dirty pages.
 */
static void vmw_bo_dirty_pre_unmap(struct vmw_bo *vbo,
				   pgoff_t start, pgoff_t end)
{
	struct vmw_bo_dirty *dirty = vbo->dirty;
	unsigned long offset = drm_vma_node_start(&vbo->tbo.base.vma_node);
	struct address_space *mapping = vbo->tbo.bdev->dev_mapping;

	if (dirty->method != VMW_BO_DIRTY_PAGETABLE || start >= end)
		return;

	wp_shared_mapping_range(mapping, start + offset, end - start);
	clean_record_shared_mapping_range(mapping, start + offset,
					  end - start, offset,
					  &dirty->bitmap[0], &dirty->start,
					  &dirty->end);
}

/**
 * vmw_bo_dirty_unmap - Clear all ptes pointing to a range within a bo
 * @vbo: The buffer object,
 * @start: First page of the range within the buffer object.
 * @end: Last page of the range within the buffer object + 1.
 *
 * This is similar to ttm_bo_unmap_virtual() except it takes a subrange.
 */
void vmw_bo_dirty_unmap(struct vmw_bo *vbo,
			pgoff_t start, pgoff_t end)
{
	unsigned long offset = drm_vma_node_start(&vbo->tbo.base.vma_node);
	struct address_space *mapping = vbo->tbo.bdev->dev_mapping;

	vmw_bo_dirty_pre_unmap(vbo, start, end);
	unmap_shared_mapping_range(mapping, (offset + start) << PAGE_SHIFT,
				   (loff_t) (end - start) << PAGE_SHIFT);
}

/**
 * vmw_bo_dirty_add - Add a dirty-tracking user to a buffer object
 * @vbo: The buffer object
 *
 * This function registers a dirty-tracking user to a buffer object.
 * A user can be for example a resource or a vma in a special user-space
 * mapping.
 *
 * Return: Zero on success, -ENOMEM on memory allocation failure.
 */
int vmw_bo_dirty_add(struct vmw_bo *vbo)
{
	struct vmw_bo_dirty *dirty = vbo->dirty;
	pgoff_t num_pages = PFN_UP(vbo->tbo.resource->size);
	size_t size;
	int ret;

	if (dirty) {
		dirty->ref_count++;
		return 0;
	}

	size = sizeof(*dirty) + BITS_TO_LONGS(num_pages) * sizeof(long);
	dirty = kvzalloc(size, GFP_KERNEL);
	if (!dirty) {
		ret = -ENOMEM;
		goto out_no_dirty;
	}

	dirty->bitmap_size = num_pages;
	dirty->start = dirty->bitmap_size;
	dirty->end = 0;
	dirty->ref_count = 1;
	if (num_pages < PAGE_SIZE / sizeof(pte_t)) {
		dirty->method = VMW_BO_DIRTY_PAGETABLE;
	} else {
		struct address_space *mapping = vbo->tbo.bdev->dev_mapping;
		pgoff_t offset = drm_vma_node_start(&vbo->tbo.base.vma_node);

		dirty->method = VMW_BO_DIRTY_MKWRITE;

		/* Write-protect and then pick up already dirty bits */
		wp_shared_mapping_range(mapping, offset, num_pages);
		clean_record_shared_mapping_range(mapping, offset, num_pages,
						  offset,
						  &dirty->bitmap[0],
						  &dirty->start, &dirty->end);
	}

	vbo->dirty = dirty;

	return 0;

out_no_dirty:
	return ret;
}

/**
 * vmw_bo_dirty_release - Release a dirty-tracking user from a buffer object
 * @vbo: The buffer object
 *
 * This function releases a dirty-tracking user from a buffer object.
 * If the reference count reaches zero, then the dirty-tracking object is
 * freed and the pointer to it cleared.
 *
 * Return: Zero on success, -ENOMEM on memory allocation failure.
 */
void vmw_bo_dirty_release(struct vmw_bo *vbo)
{
	struct vmw_bo_dirty *dirty = vbo->dirty;

	if (dirty && --dirty->ref_count == 0) {
		kvfree(dirty);
		vbo->dirty = NULL;
	}
}

/**
 * vmw_bo_dirty_transfer_to_res - Pick up a resource's dirty region from
 * its backing mob.
 * @res: The resource
 *
 * This function will pick up all dirty ranges affecting the resource from
 * it's backup mob, and call vmw_resource_dirty_update() once for each
 * range. The transferred ranges will be cleared from the backing mob's
 * dirty tracking.
 */
void vmw_bo_dirty_transfer_to_res(struct vmw_resource *res)
{
	struct vmw_bo *vbo = res->guest_memory_bo;
	struct vmw_bo_dirty *dirty = vbo->dirty;
	pgoff_t start, cur, end;
	unsigned long res_start = res->guest_memory_offset;
	unsigned long res_end = res->guest_memory_offset + res->guest_memory_size;

	WARN_ON_ONCE(res_start & ~PAGE_MASK);
	res_start >>= PAGE_SHIFT;
	res_end = DIV_ROUND_UP(res_end, PAGE_SIZE);

	if (res_start >= dirty->end || res_end <= dirty->start)
		return;

	cur = max(res_start, dirty->start);
	res_end = max(res_end, dirty->end);
	while (cur < res_end) {
		unsigned long num;

		start = find_next_bit(&dirty->bitmap[0], res_end, cur);
		if (start >= res_end)
			break;

		end = find_next_zero_bit(&dirty->bitmap[0], res_end, start + 1);
		cur = end + 1;
		num = end - start;
		bitmap_clear(&dirty->bitmap[0], start, num);
		vmw_resource_dirty_update(res, start, end);
	}

	if (res_start <= dirty->start && res_end > dirty->start)
		dirty->start = res_end;
	if (res_start < dirty->end && res_end >= dirty->end)
		dirty->end = res_start;
}

/**
 * vmw_bo_dirty_clear_res - Clear a resource's dirty region from
 * its backing mob.
 * @res: The resource
 *
 * This function will clear all dirty ranges affecting the resource from
 * it's backup mob's dirty tracking.
 */
void vmw_bo_dirty_clear_res(struct vmw_resource *res)
{
	unsigned long res_start = res->guest_memory_offset;
	unsigned long res_end = res->guest_memory_offset + res->guest_memory_size;
	struct vmw_bo *vbo = res->guest_memory_bo;
	struct vmw_bo_dirty *dirty = vbo->dirty;

	res_start >>= PAGE_SHIFT;
	res_end = DIV_ROUND_UP(res_end, PAGE_SIZE);

	if (res_start >= dirty->end || res_end <= dirty->start)
		return;

	res_start = max(res_start, dirty->start);
	res_end = min(res_end, dirty->end);
	bitmap_clear(&dirty->bitmap[0], res_start, res_end - res_start);

	if (res_start <= dirty->start && res_end > dirty->start)
		dirty->start = res_end;
	if (res_start < dirty->end && res_end >= dirty->end)
		dirty->end = res_start;
}

vm_fault_t vmw_bo_vm_mkwrite(struct vm_fault *vmf)
{
	struct vm_area_struct *vma = vmf->vma;
	struct ttm_buffer_object *bo = (struct ttm_buffer_object *)
	    vma->vm_private_data;
	vm_fault_t ret;
	unsigned long page_offset;
	unsigned int save_flags;
	struct vmw_bo *vbo = to_vmw_bo(&bo->base);

	/*
	 * mkwrite() doesn't handle the VM_FAULT_RETRY return value correctly.
	 * So make sure the TTM helpers are aware.
	 */
	save_flags = vmf->flags;
	vmf->flags &= ~FAULT_FLAG_ALLOW_RETRY;
	ret = ttm_bo_vm_reserve(bo, vmf);
	vmf->flags = save_flags;
	if (ret)
		return ret;

	page_offset = vmf->pgoff - drm_vma_node_start(&bo->base.vma_node);
	if (unlikely(page_offset >= PFN_UP(bo->resource->size))) {
		ret = VM_FAULT_SIGBUS;
		goto out_unlock;
	}

	if (vbo->dirty && vbo->dirty->method == VMW_BO_DIRTY_MKWRITE &&
	    !test_bit(page_offset, &vbo->dirty->bitmap[0])) {
		struct vmw_bo_dirty *dirty = vbo->dirty;

		__set_bit(page_offset, &dirty->bitmap[0]);
		dirty->start = min(dirty->start, page_offset);
		dirty->end = max(dirty->end, page_offset + 1);
	}

out_unlock:
	dma_resv_unlock(bo->base.resv);
	return ret;
}

vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf)
{
	struct vm_area_struct *vma = vmf->vma;
	struct ttm_buffer_object *bo = (struct ttm_buffer_object *)
	    vma->vm_private_data;
	struct vmw_bo *vbo = to_vmw_bo(&bo->base);
	pgoff_t num_prefault;
	pgprot_t prot;
	vm_fault_t ret;

	ret = ttm_bo_vm_reserve(bo, vmf);
	if (ret)
		return ret;

	num_prefault = (vma->vm_flags & VM_RAND_READ) ? 1 :
		TTM_BO_VM_NUM_PREFAULT;

	if (vbo->dirty) {
		pgoff_t allowed_prefault;
		unsigned long page_offset;

		page_offset = vmf->pgoff -
			drm_vma_node_start(&bo->base.vma_node);
		if (page_offset >= PFN_UP(bo->resource->size) ||
		    vmw_resources_clean(vbo, page_offset,
					page_offset + PAGE_SIZE,
					&allowed_prefault)) {
			ret = VM_FAULT_SIGBUS;
			goto out_unlock;
		}

		num_prefault = min(num_prefault, allowed_prefault);
	}

	/*
	 * If we don't track dirty using the MKWRITE method, make sure
	 * sure the page protection is write-enabled so we don't get
	 * a lot of unnecessary write faults.
	 */
	if (vbo->dirty && vbo->dirty->method == VMW_BO_DIRTY_MKWRITE)
		prot = vm_get_page_prot(vma->vm_flags & ~VM_SHARED);
	else
		prot = vm_get_page_prot(vma->vm_flags);

	ret = ttm_bo_vm_fault_reserved(vmf, prot, num_prefault);
	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
		return ret;

out_unlock:
	dma_resv_unlock(bo->base.resv);

	return ret;
}