summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/ttm/ttm_bo_vm.c
blob: f56be5bc0861ec57c06a730d27273e15790f078c (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
/* SPDX-License-Identifier: GPL-2.0 OR MIT */
/**************************************************************************
 *
 * Copyright (c) 2006-2009 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>
 */

#define pr_fmt(fmt) "[TTM] " fmt

#include <drm/ttm/ttm_bo_driver.h>
#include <drm/ttm/ttm_placement.h>
#include <drm/drm_vma_manager.h>
#include <drm/drm_drv.h>
#include <drm/drm_managed.h>
#include <linux/mm.h>
#include <linux/pfn_t.h>
#include <linux/rbtree.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/mem_encrypt.h>

static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
				struct vm_fault *vmf)
{
	vm_fault_t ret = 0;
	int err = 0;

	if (likely(!bo->moving))
		goto out_unlock;

	/*
	 * Quick non-stalling check for idle.
	 */
	if (dma_fence_is_signaled(bo->moving))
		goto out_clear;

	/*
	 * If possible, avoid waiting for GPU with mmap_lock
	 * held.  We only do this if the fault allows retry and this
	 * is the first attempt.
	 */
	if (fault_flag_allow_retry_first(vmf->flags)) {
		ret = VM_FAULT_RETRY;
		if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
			goto out_unlock;

		ttm_bo_get(bo);
		mmap_read_unlock(vmf->vma->vm_mm);
		(void) dma_fence_wait(bo->moving, true);
		dma_resv_unlock(bo->base.resv);
		ttm_bo_put(bo);
		goto out_unlock;
	}

	/*
	 * Ordinary wait.
	 */
	err = dma_fence_wait(bo->moving, true);
	if (unlikely(err != 0)) {
		ret = (err != -ERESTARTSYS) ? VM_FAULT_SIGBUS :
			VM_FAULT_NOPAGE;
		goto out_unlock;
	}

out_clear:
	dma_fence_put(bo->moving);
	bo->moving = NULL;

out_unlock:
	return ret;
}

static unsigned long ttm_bo_io_mem_pfn(struct ttm_buffer_object *bo,
				       unsigned long page_offset)
{
	struct ttm_device *bdev = bo->bdev;

	if (bdev->funcs->io_mem_pfn)
		return bdev->funcs->io_mem_pfn(bo, page_offset);

	return (bo->resource->bus.offset >> PAGE_SHIFT) + page_offset;
}

/**
 * ttm_bo_vm_reserve - Reserve a buffer object in a retryable vm callback
 * @bo: The buffer object
 * @vmf: The fault structure handed to the callback
 *
 * vm callbacks like fault() and *_mkwrite() allow for the mm_sem to be dropped
 * during long waits, and after the wait the callback will be restarted. This
 * is to allow other threads using the same virtual memory space concurrent
 * access to map(), unmap() completely unrelated buffer objects. TTM buffer
 * object reservations sometimes wait for GPU and should therefore be
 * considered long waits. This function reserves the buffer object interruptibly
 * taking this into account. Starvation is avoided by the vm system not
 * allowing too many repeated restarts.
 * This function is intended to be used in customized fault() and _mkwrite()
 * handlers.
 *
 * Return:
 *    0 on success and the bo was reserved.
 *    VM_FAULT_RETRY if blocking wait.
 *    VM_FAULT_NOPAGE if blocking wait and retrying was not allowed.
 */
vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo,
			     struct vm_fault *vmf)
{
	/*
	 * Work around locking order reversal in fault / nopfn
	 * between mmap_lock and bo_reserve: Perform a trylock operation
	 * for reserve, and if it fails, retry the fault after waiting
	 * for the buffer to become unreserved.
	 */
	if (unlikely(!dma_resv_trylock(bo->base.resv))) {
		/*
		 * If the fault allows retry and this is the first
		 * fault attempt, we try to release the mmap_lock
		 * before waiting
		 */
		if (fault_flag_allow_retry_first(vmf->flags)) {
			if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
				ttm_bo_get(bo);
				mmap_read_unlock(vmf->vma->vm_mm);
				if (!dma_resv_lock_interruptible(bo->base.resv,
								 NULL))
					dma_resv_unlock(bo->base.resv);
				ttm_bo_put(bo);
			}

			return VM_FAULT_RETRY;
		}

		if (dma_resv_lock_interruptible(bo->base.resv, NULL))
			return VM_FAULT_NOPAGE;
	}

	/*
	 * Refuse to fault imported pages. This should be handled
	 * (if at all) by redirecting mmap to the exporter.
	 */
	if (bo->ttm && (bo->ttm->page_flags & TTM_PAGE_FLAG_SG)) {
		dma_resv_unlock(bo->base.resv);
		return VM_FAULT_SIGBUS;
	}

	return 0;
}
EXPORT_SYMBOL(ttm_bo_vm_reserve);

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/**
 * ttm_bo_vm_insert_huge - Insert a pfn for PUD or PMD faults
 * @vmf: Fault data
 * @bo: The buffer object
 * @page_offset: Page offset from bo start
 * @fault_page_size: The size of the fault in pages.
 * @pgprot: The page protections.
 * Does additional checking whether it's possible to insert a PUD or PMD
 * pfn and performs the insertion.
 *
 * Return: VM_FAULT_NOPAGE on successful insertion, VM_FAULT_FALLBACK if
 * a huge fault was not possible, or on insertion error.
 */
static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf,
					struct ttm_buffer_object *bo,
					pgoff_t page_offset,
					pgoff_t fault_page_size,
					pgprot_t pgprot)
{
	pgoff_t i;
	vm_fault_t ret;
	unsigned long pfn;
	pfn_t pfnt;
	struct ttm_tt *ttm = bo->ttm;
	bool write = vmf->flags & FAULT_FLAG_WRITE;

	/* Fault should not cross bo boundary. */
	page_offset &= ~(fault_page_size - 1);
	if (page_offset + fault_page_size > bo->resource->num_pages)
		goto out_fallback;

	if (bo->resource->bus.is_iomem)
		pfn = ttm_bo_io_mem_pfn(bo, page_offset);
	else
		pfn = page_to_pfn(ttm->pages[page_offset]);

	/* pfn must be fault_page_size aligned. */
	if ((pfn & (fault_page_size - 1)) != 0)
		goto out_fallback;

	/* Check that memory is contiguous. */
	if (!bo->resource->bus.is_iomem) {
		for (i = 1; i < fault_page_size; ++i) {
			if (page_to_pfn(ttm->pages[page_offset + i]) != pfn + i)
				goto out_fallback;
		}
	} else if (bo->bdev->funcs->io_mem_pfn) {
		for (i = 1; i < fault_page_size; ++i) {
			if (ttm_bo_io_mem_pfn(bo, page_offset + i) != pfn + i)
				goto out_fallback;
		}
	}

	pfnt = __pfn_to_pfn_t(pfn, PFN_DEV);
	if (fault_page_size == (HPAGE_PMD_SIZE >> PAGE_SHIFT))
		ret = vmf_insert_pfn_pmd_prot(vmf, pfnt, pgprot, write);
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
	else if (fault_page_size == (HPAGE_PUD_SIZE >> PAGE_SHIFT))
		ret = vmf_insert_pfn_pud_prot(vmf, pfnt, pgprot, write);
#endif
	else
		WARN_ON_ONCE(ret = VM_FAULT_FALLBACK);

	if (ret != VM_FAULT_NOPAGE)
		goto out_fallback;

	return VM_FAULT_NOPAGE;
out_fallback:
	count_vm_event(THP_FAULT_FALLBACK);
	return VM_FAULT_FALLBACK;
}
#else
static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf,
					struct ttm_buffer_object *bo,
					pgoff_t page_offset,
					pgoff_t fault_page_size,
					pgprot_t pgprot)
{
	return VM_FAULT_FALLBACK;
}
#endif

/**
 * ttm_bo_vm_fault_reserved - TTM fault helper
 * @vmf: The struct vm_fault given as argument to the fault callback
 * @prot: The page protection to be used for this memory area.
 * @num_prefault: Maximum number of prefault pages. The caller may want to
 * specify this based on madvice settings and the size of the GPU object
 * backed by the memory.
 * @fault_page_size: The size of the fault in pages.
 *
 * This function inserts one or more page table entries pointing to the
 * memory backing the buffer object, and then returns a return code
 * instructing the caller to retry the page access.
 *
 * Return:
 *   VM_FAULT_NOPAGE on success or pending signal
 *   VM_FAULT_SIGBUS on unspecified error
 *   VM_FAULT_OOM on out-of-memory
 *   VM_FAULT_RETRY if retryable wait
 */
vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
				    pgprot_t prot,
				    pgoff_t num_prefault,
				    pgoff_t fault_page_size)
{
	struct vm_area_struct *vma = vmf->vma;
	struct ttm_buffer_object *bo = vma->vm_private_data;
	struct ttm_device *bdev = bo->bdev;
	unsigned long page_offset;
	unsigned long page_last;
	unsigned long pfn;
	struct ttm_tt *ttm = NULL;
	struct page *page;
	int err;
	pgoff_t i;
	vm_fault_t ret = VM_FAULT_NOPAGE;
	unsigned long address = vmf->address;

	/*
	 * Wait for buffer data in transit, due to a pipelined
	 * move.
	 */
	ret = ttm_bo_vm_fault_idle(bo, vmf);
	if (unlikely(ret != 0))
		return ret;

	err = ttm_mem_io_reserve(bdev, bo->resource);
	if (unlikely(err != 0))
		return VM_FAULT_SIGBUS;

	page_offset = ((address - vma->vm_start) >> PAGE_SHIFT) +
		vma->vm_pgoff - drm_vma_node_start(&bo->base.vma_node);
	page_last = vma_pages(vma) + vma->vm_pgoff -
		drm_vma_node_start(&bo->base.vma_node);

	if (unlikely(page_offset >= bo->resource->num_pages))
		return VM_FAULT_SIGBUS;

	prot = ttm_io_prot(bo, bo->resource, prot);
	if (!bo->resource->bus.is_iomem) {
		struct ttm_operation_ctx ctx = {
			.interruptible = false,
			.no_wait_gpu = false,
			.force_alloc = true
		};

		ttm = bo->ttm;
		if (ttm_tt_populate(bdev, bo->ttm, &ctx))
			return VM_FAULT_OOM;
	} else {
		/* Iomem should not be marked encrypted */
		prot = pgprot_decrypted(prot);
	}

	/* We don't prefault on huge faults. Yet. */
	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && fault_page_size != 1)
		return ttm_bo_vm_insert_huge(vmf, bo, page_offset,
					     fault_page_size, prot);

	/*
	 * Speculatively prefault a number of pages. Only error on
	 * first page.
	 */
	for (i = 0; i < num_prefault; ++i) {
		if (bo->resource->bus.is_iomem) {
			pfn = ttm_bo_io_mem_pfn(bo, page_offset);
		} else {
			page = ttm->pages[page_offset];
			if (unlikely(!page && i == 0)) {
				return VM_FAULT_OOM;
			} else if (unlikely(!page)) {
				break;
			}
			page->index = drm_vma_node_start(&bo->base.vma_node) +
				page_offset;
			pfn = page_to_pfn(page);
		}

		/*
		 * Note that the value of @prot at this point may differ from
		 * the value of @vma->vm_page_prot in the caching- and
		 * encryption bits. This is because the exact location of the
		 * data may not be known at mmap() time and may also change
		 * at arbitrary times while the data is mmap'ed.
		 * See vmf_insert_mixed_prot() for a discussion.
		 */
		ret = vmf_insert_pfn_prot(vma, address, pfn, prot);

		/* Never error on prefaulted PTEs */
		if (unlikely((ret & VM_FAULT_ERROR))) {
			if (i == 0)
				return VM_FAULT_NOPAGE;
			else
				break;
		}

		address += PAGE_SIZE;
		if (unlikely(++page_offset >= page_last))
			break;
	}
	return ret;
}
EXPORT_SYMBOL(ttm_bo_vm_fault_reserved);

static void ttm_bo_release_dummy_page(struct drm_device *dev, void *res)
{
	struct page *dummy_page = (struct page *)res;

	__free_page(dummy_page);
}

vm_fault_t ttm_bo_vm_dummy_page(struct vm_fault *vmf, pgprot_t prot)
{
	struct vm_area_struct *vma = vmf->vma;
	struct ttm_buffer_object *bo = vma->vm_private_data;
	struct drm_device *ddev = bo->base.dev;
	vm_fault_t ret = VM_FAULT_NOPAGE;
	unsigned long address;
	unsigned long pfn;
	struct page *page;

	/* Allocate new dummy page to map all the VA range in this VMA to it*/
	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
	if (!page)
		return VM_FAULT_OOM;

	/* Set the page to be freed using drmm release action */
	if (drmm_add_action_or_reset(ddev, ttm_bo_release_dummy_page, page))
		return VM_FAULT_OOM;

	pfn = page_to_pfn(page);

	/* Prefault the entire VMA range right away to avoid further faults */
	for (address = vma->vm_start; address < vma->vm_end;
	     address += PAGE_SIZE)
		ret = vmf_insert_pfn_prot(vma, address, pfn, prot);

	return ret;
}
EXPORT_SYMBOL(ttm_bo_vm_dummy_page);

vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
{
	struct vm_area_struct *vma = vmf->vma;
	pgprot_t prot;
	struct ttm_buffer_object *bo = vma->vm_private_data;
	struct drm_device *ddev = bo->base.dev;
	vm_fault_t ret;
	int idx;

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

	prot = vma->vm_page_prot;
	if (drm_dev_enter(ddev, &idx)) {
		ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT, 1);
		drm_dev_exit(idx);
	} else {
		ret = ttm_bo_vm_dummy_page(vmf, prot);
	}
	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
		return ret;

	dma_resv_unlock(bo->base.resv);

	return ret;
}
EXPORT_SYMBOL(ttm_bo_vm_fault);

void ttm_bo_vm_open(struct vm_area_struct *vma)
{
	struct ttm_buffer_object *bo = vma->vm_private_data;

	WARN_ON(bo->bdev->dev_mapping != vma->vm_file->f_mapping);

	ttm_bo_get(bo);
}
EXPORT_SYMBOL(ttm_bo_vm_open);

void ttm_bo_vm_close(struct vm_area_struct *vma)
{
	struct ttm_buffer_object *bo = vma->vm_private_data;

	ttm_bo_put(bo);
	vma->vm_private_data = NULL;
}
EXPORT_SYMBOL(ttm_bo_vm_close);

static int ttm_bo_vm_access_kmap(struct ttm_buffer_object *bo,
				 unsigned long offset,
				 uint8_t *buf, int len, int write)
{
	unsigned long page = offset >> PAGE_SHIFT;
	unsigned long bytes_left = len;
	int ret;

	/* Copy a page at a time, that way no extra virtual address
	 * mapping is needed
	 */
	offset -= page << PAGE_SHIFT;
	do {
		unsigned long bytes = min(bytes_left, PAGE_SIZE - offset);
		struct ttm_bo_kmap_obj map;
		void *ptr;
		bool is_iomem;

		ret = ttm_bo_kmap(bo, page, 1, &map);
		if (ret)
			return ret;

		ptr = (uint8_t *)ttm_kmap_obj_virtual(&map, &is_iomem) + offset;
		WARN_ON_ONCE(is_iomem);
		if (write)
			memcpy(ptr, buf, bytes);
		else
			memcpy(buf, ptr, bytes);
		ttm_bo_kunmap(&map);

		page++;
		buf += bytes;
		bytes_left -= bytes;
		offset = 0;
	} while (bytes_left);

	return len;
}

int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr,
		     void *buf, int len, int write)
{
	struct ttm_buffer_object *bo = vma->vm_private_data;
	unsigned long offset = (addr) - vma->vm_start +
		((vma->vm_pgoff - drm_vma_node_start(&bo->base.vma_node))
		 << PAGE_SHIFT);
	int ret;

	if (len < 1 || (offset + len) >> PAGE_SHIFT > bo->resource->num_pages)
		return -EIO;

	ret = ttm_bo_reserve(bo, true, false, NULL);
	if (ret)
		return ret;

	switch (bo->resource->mem_type) {
	case TTM_PL_SYSTEM:
		if (unlikely(bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)) {
			ret = ttm_tt_swapin(bo->ttm);
			if (unlikely(ret != 0))
				return ret;
		}
		fallthrough;
	case TTM_PL_TT:
		ret = ttm_bo_vm_access_kmap(bo, offset, buf, len, write);
		break;
	default:
		if (bo->bdev->funcs->access_memory)
			ret = bo->bdev->funcs->access_memory(
				bo, offset, buf, len, write);
		else
			ret = -EIO;
	}

	ttm_bo_unreserve(bo);

	return ret;
}
EXPORT_SYMBOL(ttm_bo_vm_access);

static const struct vm_operations_struct ttm_bo_vm_ops = {
	.fault = ttm_bo_vm_fault,
	.open = ttm_bo_vm_open,
	.close = ttm_bo_vm_close,
	.access = ttm_bo_vm_access,
};

int ttm_bo_mmap_obj(struct vm_area_struct *vma, struct ttm_buffer_object *bo)
{
	/* Enforce no COW since would have really strange behavior with it. */
	if (is_cow_mapping(vma->vm_flags))
		return -EINVAL;

	ttm_bo_get(bo);

	/*
	 * Drivers may want to override the vm_ops field. Otherwise we
	 * use TTM's default callbacks.
	 */
	if (!vma->vm_ops)
		vma->vm_ops = &ttm_bo_vm_ops;

	/*
	 * Note: We're transferring the bo reference to
	 * vma->vm_private_data here.
	 */

	vma->vm_private_data = bo;

	vma->vm_flags |= VM_PFNMAP;
	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
	return 0;
}
EXPORT_SYMBOL(ttm_bo_mmap_obj);