summaryrefslogtreecommitdiffstats
path: root/mm/pagewalk.c
blob: 9b2d23fbf4d358caf508851b037d3bd6fa0e6bb9 (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
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
// SPDX-License-Identifier: GPL-2.0
#include <linux/pagewalk.h>
#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/hugetlb.h>

/*
 * We want to know the real level where a entry is located ignoring any
 * folding of levels which may be happening. For example if p4d is folded then
 * a missing entry found at level 1 (p4d) is actually at level 0 (pgd).
 */
static int real_depth(int depth)
{
	if (depth == 3 && PTRS_PER_PMD == 1)
		depth = 2;
	if (depth == 2 && PTRS_PER_PUD == 1)
		depth = 1;
	if (depth == 1 && PTRS_PER_P4D == 1)
		depth = 0;
	return depth;
}

static int walk_pte_range_inner(pte_t *pte, unsigned long addr,
				unsigned long end, struct mm_walk *walk)
{
	const struct mm_walk_ops *ops = walk->ops;
	int err = 0;

	for (;;) {
		err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
		if (err)
		       break;
		if (addr >= end - PAGE_SIZE)
			break;
		addr += PAGE_SIZE;
		pte++;
	}
	return err;
}

static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
			  struct mm_walk *walk)
{
	pte_t *pte;
	int err = 0;
	spinlock_t *ptl;

	if (walk->no_vma) {
		/*
		 * pte_offset_map() might apply user-specific validation.
		 * Indeed, on x86_64 the pmd entries set up by init_espfix_ap()
		 * fit its pmd_bad() check (_PAGE_NX set and _PAGE_RW clear),
		 * and CONFIG_EFI_PGT_DUMP efi_mm goes so far as to walk them.
		 */
		if (walk->mm == &init_mm || addr >= TASK_SIZE)
			pte = pte_offset_kernel(pmd, addr);
		else
			pte = pte_offset_map(pmd, addr);
		if (pte) {
			err = walk_pte_range_inner(pte, addr, end, walk);
			if (walk->mm != &init_mm)
				pte_unmap(pte);
		}
	} else {
		pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
		if (pte) {
			err = walk_pte_range_inner(pte, addr, end, walk);
			pte_unmap_unlock(pte, ptl);
		}
	}
	if (!pte)
		walk->action = ACTION_AGAIN;
	return err;
}

#ifdef CONFIG_ARCH_HAS_HUGEPD
static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr,
			     unsigned long end, struct mm_walk *walk, int pdshift)
{
	int err = 0;
	const struct mm_walk_ops *ops = walk->ops;
	int shift = hugepd_shift(*phpd);
	int page_size = 1 << shift;

	if (!ops->pte_entry)
		return 0;

	if (addr & (page_size - 1))
		return 0;

	for (;;) {
		pte_t *pte;

		spin_lock(&walk->mm->page_table_lock);
		pte = hugepte_offset(*phpd, addr, pdshift);
		err = ops->pte_entry(pte, addr, addr + page_size, walk);
		spin_unlock(&walk->mm->page_table_lock);

		if (err)
			break;
		if (addr >= end - page_size)
			break;
		addr += page_size;
	}
	return err;
}
#else
static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr,
			     unsigned long end, struct mm_walk *walk, int pdshift)
{
	return 0;
}
#endif

static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
			  struct mm_walk *walk)
{
	pmd_t *pmd;
	unsigned long next;
	const struct mm_walk_ops *ops = walk->ops;
	int err = 0;
	int depth = real_depth(3);

	pmd = pmd_offset(pud, addr);
	do {
again:
		next = pmd_addr_end(addr, end);
		if (pmd_none(*pmd)) {
			if (ops->pte_hole)
				err = ops->pte_hole(addr, next, depth, walk);
			if (err)
				break;
			continue;
		}

		walk->action = ACTION_SUBTREE;

		/*
		 * This implies that each ->pmd_entry() handler
		 * needs to know about pmd_trans_huge() pmds
		 */
		if (ops->pmd_entry)
			err = ops->pmd_entry(pmd, addr, next, walk);
		if (err)
			break;

		if (walk->action == ACTION_AGAIN)
			goto again;

		/*
		 * Check this here so we only break down trans_huge
		 * pages when we _need_ to
		 */
		if ((!walk->vma && (pmd_leaf(*pmd) || !pmd_present(*pmd))) ||
		    walk->action == ACTION_CONTINUE ||
		    !(ops->pte_entry))
			continue;

		if (walk->vma)
			split_huge_pmd(walk->vma, pmd, addr);

		if (is_hugepd(__hugepd(pmd_val(*pmd))))
			err = walk_hugepd_range((hugepd_t *)pmd, addr, next, walk, PMD_SHIFT);
		else
			err = walk_pte_range(pmd, addr, next, walk);
		if (err)
			break;

		if (walk->action == ACTION_AGAIN)
			goto again;

	} while (pmd++, addr = next, addr != end);

	return err;
}

static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
			  struct mm_walk *walk)
{
	pud_t *pud;
	unsigned long next;
	const struct mm_walk_ops *ops = walk->ops;
	int err = 0;
	int depth = real_depth(2);

	pud = pud_offset(p4d, addr);
	do {
 again:
		next = pud_addr_end(addr, end);
		if (pud_none(*pud)) {
			if (ops->pte_hole)
				err = ops->pte_hole(addr, next, depth, walk);
			if (err)
				break;
			continue;
		}

		walk->action = ACTION_SUBTREE;

		if (ops->pud_entry)
			err = ops->pud_entry(pud, addr, next, walk);
		if (err)
			break;

		if (walk->action == ACTION_AGAIN)
			goto again;

		if ((!walk->vma && (pud_leaf(*pud) || !pud_present(*pud))) ||
		    walk->action == ACTION_CONTINUE ||
		    !(ops->pmd_entry || ops->pte_entry))
			continue;

		if (walk->vma)
			split_huge_pud(walk->vma, pud, addr);
		if (pud_none(*pud))
			goto again;

		if (is_hugepd(__hugepd(pud_val(*pud))))
			err = walk_hugepd_range((hugepd_t *)pud, addr, next, walk, PUD_SHIFT);
		else
			err = walk_pmd_range(pud, addr, next, walk);
		if (err)
			break;
	} while (pud++, addr = next, addr != end);

	return err;
}

static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
			  struct mm_walk *walk)
{
	p4d_t *p4d;
	unsigned long next;
	const struct mm_walk_ops *ops = walk->ops;
	int err = 0;
	int depth = real_depth(1);

	p4d = p4d_offset(pgd, addr);
	do {
		next = p4d_addr_end(addr, end);
		if (p4d_none_or_clear_bad(p4d)) {
			if (ops->pte_hole)
				err = ops->pte_hole(addr, next, depth, walk);
			if (err)
				break;
			continue;
		}
		if (ops->p4d_entry) {
			err = ops->p4d_entry(p4d, addr, next, walk);
			if (err)
				break;
		}
		if (is_hugepd(__hugepd(p4d_val(*p4d))))
			err = walk_hugepd_range((hugepd_t *)p4d, addr, next, walk, P4D_SHIFT);
		else if (ops->pud_entry || ops->pmd_entry || ops->pte_entry)
			err = walk_pud_range(p4d, addr, next, walk);
		if (err)
			break;
	} while (p4d++, addr = next, addr != end);

	return err;
}

static int walk_pgd_range(unsigned long addr, unsigned long end,
			  struct mm_walk *walk)
{
	pgd_t *pgd;
	unsigned long next;
	const struct mm_walk_ops *ops = walk->ops;
	int err = 0;

	if (walk->pgd)
		pgd = walk->pgd + pgd_index(addr);
	else
		pgd = pgd_offset(walk->mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd)) {
			if (ops->pte_hole)
				err = ops->pte_hole(addr, next, 0, walk);
			if (err)
				break;
			continue;
		}
		if (ops->pgd_entry) {
			err = ops->pgd_entry(pgd, addr, next, walk);
			if (err)
				break;
		}
		if (is_hugepd(__hugepd(pgd_val(*pgd))))
			err = walk_hugepd_range((hugepd_t *)pgd, addr, next, walk, PGDIR_SHIFT);
		else if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || ops->pte_entry)
			err = walk_p4d_range(pgd, addr, next, walk);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);

	return err;
}

#ifdef CONFIG_HUGETLB_PAGE
static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr,
				       unsigned long end)
{
	unsigned long boundary = (addr & huge_page_mask(h)) + huge_page_size(h);
	return boundary < end ? boundary : end;
}

static int walk_hugetlb_range(unsigned long addr, unsigned long end,
			      struct mm_walk *walk)
{
	struct vm_area_struct *vma = walk->vma;
	struct hstate *h = hstate_vma(vma);
	unsigned long next;
	unsigned long hmask = huge_page_mask(h);
	unsigned long sz = huge_page_size(h);
	pte_t *pte;
	const struct mm_walk_ops *ops = walk->ops;
	int err = 0;

	hugetlb_vma_lock_read(vma);
	do {
		next = hugetlb_entry_end(h, addr, end);
		pte = hugetlb_walk(vma, addr & hmask, sz);
		if (pte)
			err = ops->hugetlb_entry(pte, hmask, addr, next, walk);
		else if (ops->pte_hole)
			err = ops->pte_hole(addr, next, -1, walk);
		if (err)
			break;
	} while (addr = next, addr != end);
	hugetlb_vma_unlock_read(vma);

	return err;
}

#else /* CONFIG_HUGETLB_PAGE */
static int walk_hugetlb_range(unsigned long addr, unsigned long end,
			      struct mm_walk *walk)
{
	return 0;
}

#endif /* CONFIG_HUGETLB_PAGE */

/*
 * Decide whether we really walk over the current vma on [@start, @end)
 * or skip it via the returned value. Return 0 if we do walk over the
 * current vma, and return 1 if we skip the vma. Negative values means
 * error, where we abort the current walk.
 */
static int walk_page_test(unsigned long start, unsigned long end,
			struct mm_walk *walk)
{
	struct vm_area_struct *vma = walk->vma;
	const struct mm_walk_ops *ops = walk->ops;

	if (ops->test_walk)
		return ops->test_walk(start, end, walk);

	/*
	 * vma(VM_PFNMAP) doesn't have any valid struct pages behind VM_PFNMAP
	 * range, so we don't walk over it as we do for normal vmas. However,
	 * Some callers are interested in handling hole range and they don't
	 * want to just ignore any single address range. Such users certainly
	 * define their ->pte_hole() callbacks, so let's delegate them to handle
	 * vma(VM_PFNMAP).
	 */
	if (vma->vm_flags & VM_PFNMAP) {
		int err = 1;
		if (ops->pte_hole)
			err = ops->pte_hole(start, end, -1, walk);
		return err ? err : 1;
	}
	return 0;
}

static int __walk_page_range(unsigned long start, unsigned long end,
			struct mm_walk *walk)
{
	int err = 0;
	struct vm_area_struct *vma = walk->vma;
	const struct mm_walk_ops *ops = walk->ops;

	if (ops->pre_vma) {
		err = ops->pre_vma(start, end, walk);
		if (err)
			return err;
	}

	if (is_vm_hugetlb_page(vma)) {
		if (ops->hugetlb_entry)
			err = walk_hugetlb_range(start, end, walk);
	} else
		err = walk_pgd_range(start, end, walk);

	if (ops->post_vma)
		ops->post_vma(walk);

	return err;
}

static inline void process_mm_walk_lock(struct mm_struct *mm,
					enum page_walk_lock walk_lock)
{
	if (walk_lock == PGWALK_RDLOCK)
		mmap_assert_locked(mm);
	else
		mmap_assert_write_locked(mm);
}

static inline void process_vma_walk_lock(struct vm_area_struct *vma,
					 enum page_walk_lock walk_lock)
{
#ifdef CONFIG_PER_VMA_LOCK
	switch (walk_lock) {
	case PGWALK_WRLOCK:
		vma_start_write(vma);
		break;
	case PGWALK_WRLOCK_VERIFY:
		vma_assert_write_locked(vma);
		break;
	case PGWALK_RDLOCK:
		/* PGWALK_RDLOCK is handled by process_mm_walk_lock */
		break;
	}
#endif
}

/**
 * walk_page_range - walk page table with caller specific callbacks
 * @mm:		mm_struct representing the target process of page table walk
 * @start:	start address of the virtual address range
 * @end:	end address of the virtual address range
 * @ops:	operation to call during the walk
 * @private:	private data for callbacks' usage
 *
 * Recursively walk the page table tree of the process represented by @mm
 * within the virtual address range [@start, @end). During walking, we can do
 * some caller-specific works for each entry, by setting up pmd_entry(),
 * pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these
 * callbacks, the associated entries/pages are just ignored.
 * The return values of these callbacks are commonly defined like below:
 *
 *  - 0  : succeeded to handle the current entry, and if you don't reach the
 *         end address yet, continue to walk.
 *  - >0 : succeeded to handle the current entry, and return to the caller
 *         with caller specific value.
 *  - <0 : failed to handle the current entry, and return to the caller
 *         with error code.
 *
 * Before starting to walk page table, some callers want to check whether
 * they really want to walk over the current vma, typically by checking
 * its vm_flags. walk_page_test() and @ops->test_walk() are used for this
 * purpose.
 *
 * If operations need to be staged before and committed after a vma is walked,
 * there are two callbacks, pre_vma() and post_vma(). Note that post_vma(),
 * since it is intended to handle commit-type operations, can't return any
 * errors.
 *
 * struct mm_walk keeps current values of some common data like vma and pmd,
 * which are useful for the access from callbacks. If you want to pass some
 * caller-specific data to callbacks, @private should be helpful.
 *
 * Locking:
 *   Callers of walk_page_range() and walk_page_vma() should hold @mm->mmap_lock,
 *   because these function traverse vma list and/or access to vma's data.
 */
int walk_page_range(struct mm_struct *mm, unsigned long start,
		unsigned long end, const struct mm_walk_ops *ops,
		void *private)
{
	int err = 0;
	unsigned long next;
	struct vm_area_struct *vma;
	struct mm_walk walk = {
		.ops		= ops,
		.mm		= mm,
		.private	= private,
	};

	if (start >= end)
		return -EINVAL;

	if (!walk.mm)
		return -EINVAL;

	process_mm_walk_lock(walk.mm, ops->walk_lock);

	vma = find_vma(walk.mm, start);
	do {
		if (!vma) { /* after the last vma */
			walk.vma = NULL;
			next = end;
			if (ops->pte_hole)
				err = ops->pte_hole(start, next, -1, &walk);
		} else if (start < vma->vm_start) { /* outside vma */
			walk.vma = NULL;
			next = min(end, vma->vm_start);
			if (ops->pte_hole)
				err = ops->pte_hole(start, next, -1, &walk);
		} else { /* inside vma */
			process_vma_walk_lock(vma, ops->walk_lock);
			walk.vma = vma;
			next = min(end, vma->vm_end);
			vma = find_vma(mm, vma->vm_end);

			err = walk_page_test(start, next, &walk);
			if (err > 0) {
				/*
				 * positive return values are purely for
				 * controlling the pagewalk, so should never
				 * be passed to the callers.
				 */
				err = 0;
				continue;
			}
			if (err < 0)
				break;
			err = __walk_page_range(start, next, &walk);
		}
		if (err)
			break;
	} while (start = next, start < end);
	return err;
}

/**
 * walk_page_range_novma - walk a range of pagetables not backed by a vma
 * @mm:		mm_struct representing the target process of page table walk
 * @start:	start address of the virtual address range
 * @end:	end address of the virtual address range
 * @ops:	operation to call during the walk
 * @pgd:	pgd to walk if different from mm->pgd
 * @private:	private data for callbacks' usage
 *
 * Similar to walk_page_range() but can walk any page tables even if they are
 * not backed by VMAs. Because 'unusual' entries may be walked this function
 * will also not lock the PTEs for the pte_entry() callback. This is useful for
 * walking the kernel pages tables or page tables for firmware.
 */
int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
			  unsigned long end, const struct mm_walk_ops *ops,
			  pgd_t *pgd,
			  void *private)
{
	struct mm_walk walk = {
		.ops		= ops,
		.mm		= mm,
		.pgd		= pgd,
		.private	= private,
		.no_vma		= true
	};

	if (start >= end || !walk.mm)
		return -EINVAL;

	mmap_assert_write_locked(walk.mm);

	return walk_pgd_range(start, end, &walk);
}

int walk_page_range_vma(struct vm_area_struct *vma, unsigned long start,
			unsigned long end, const struct mm_walk_ops *ops,
			void *private)
{
	struct mm_walk walk = {
		.ops		= ops,
		.mm		= vma->vm_mm,
		.vma		= vma,
		.private	= private,
	};

	if (start >= end || !walk.mm)
		return -EINVAL;
	if (start < vma->vm_start || end > vma->vm_end)
		return -EINVAL;

	process_mm_walk_lock(walk.mm, ops->walk_lock);
	process_vma_walk_lock(vma, ops->walk_lock);
	return __walk_page_range(start, end, &walk);
}

int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
		void *private)
{
	struct mm_walk walk = {
		.ops		= ops,
		.mm		= vma->vm_mm,
		.vma		= vma,
		.private	= private,
	};

	if (!walk.mm)
		return -EINVAL;

	process_mm_walk_lock(walk.mm, ops->walk_lock);
	process_vma_walk_lock(vma, ops->walk_lock);
	return __walk_page_range(vma->vm_start, vma->vm_end, &walk);
}

/**
 * walk_page_mapping - walk all memory areas mapped into a struct address_space.
 * @mapping: Pointer to the struct address_space
 * @first_index: First page offset in the address_space
 * @nr: Number of incremental page offsets to cover
 * @ops:	operation to call during the walk
 * @private:	private data for callbacks' usage
 *
 * This function walks all memory areas mapped into a struct address_space.
 * The walk is limited to only the given page-size index range, but if
 * the index boundaries cross a huge page-table entry, that entry will be
 * included.
 *
 * Also see walk_page_range() for additional information.
 *
 * Locking:
 *   This function can't require that the struct mm_struct::mmap_lock is held,
 *   since @mapping may be mapped by multiple processes. Instead
 *   @mapping->i_mmap_rwsem must be held. This might have implications in the
 *   callbacks, and it's up tho the caller to ensure that the
 *   struct mm_struct::mmap_lock is not needed.
 *
 *   Also this means that a caller can't rely on the struct
 *   vm_area_struct::vm_flags to be constant across a call,
 *   except for immutable flags. Callers requiring this shouldn't use
 *   this function.
 *
 * Return: 0 on success, negative error code on failure, positive number on
 * caller defined premature termination.
 */
int walk_page_mapping(struct address_space *mapping, pgoff_t first_index,
		      pgoff_t nr, const struct mm_walk_ops *ops,
		      void *private)
{
	struct mm_walk walk = {
		.ops		= ops,
		.private	= private,
	};
	struct vm_area_struct *vma;
	pgoff_t vba, vea, cba, cea;
	unsigned long start_addr, end_addr;
	int err = 0;

	lockdep_assert_held(&mapping->i_mmap_rwsem);
	vma_interval_tree_foreach(vma, &mapping->i_mmap, first_index,
				  first_index + nr - 1) {
		/* Clip to the vma */
		vba = vma->vm_pgoff;
		vea = vba + vma_pages(vma);
		cba = first_index;
		cba = max(cba, vba);
		cea = first_index + nr;
		cea = min(cea, vea);

		start_addr = ((cba - vba) << PAGE_SHIFT) + vma->vm_start;
		end_addr = ((cea - vba) << PAGE_SHIFT) + vma->vm_start;
		if (start_addr >= end_addr)
			continue;

		walk.vma = vma;
		walk.mm = vma->vm_mm;

		err = walk_page_test(vma->vm_start, vma->vm_end, &walk);
		if (err > 0) {
			err = 0;
			break;
		} else if (err < 0)
			break;

		err = __walk_page_range(start_addr, end_addr, &walk);
		if (err)
			break;
	}

	return err;
}