summaryrefslogtreecommitdiff
path: root/mm/mlock.c
blob: df590fda56887ab5e1dee8ae6cb6b171e1a16346 (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
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
// SPDX-License-Identifier: GPL-2.0
/*
 *	linux/mm/mlock.c
 *
 *  (C) Copyright 1995 Linus Torvalds
 *  (C) Copyright 2002 Christoph Hellwig
 */

#include <linux/capability.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/sched/user.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/mempolicy.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
#include <linux/export.h>
#include <linux/rmap.h>
#include <linux/mmzone.h>
#include <linux/hugetlb.h>
#include <linux/memcontrol.h>
#include <linux/mm_inline.h>

#include "internal.h"

bool can_do_mlock(void)
{
	if (rlimit(RLIMIT_MEMLOCK) != 0)
		return true;
	if (capable(CAP_IPC_LOCK))
		return true;
	return false;
}
EXPORT_SYMBOL(can_do_mlock);

/*
 * Mlocked pages are marked with PageMlocked() flag for efficient testing
 * in vmscan and, possibly, the fault path; and to support semi-accurate
 * statistics.
 *
 * An mlocked page [PageMlocked(page)] is unevictable.  As such, it will
 * be placed on the LRU "unevictable" list, rather than the [in]active lists.
 * The unevictable list is an LRU sibling list to the [in]active lists.
 * PageUnevictable is set to indicate the unevictable state.
 *
 * When lazy mlocking via vmscan, it is important to ensure that the
 * vma's VM_LOCKED status is not concurrently being modified, otherwise we
 * may have mlocked a page that is being munlocked. So lazy mlock must take
 * the mmap_lock for read, and verify that the vma really is locked
 * (see mm/rmap.c).
 */

/*
 *  LRU accounting for clear_page_mlock()
 */
void clear_page_mlock(struct page *page)
{
	int nr_pages;

	if (!TestClearPageMlocked(page))
		return;

	nr_pages = thp_nr_pages(page);
	mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
	count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages);
	/*
	 * The previous TestClearPageMlocked() corresponds to the smp_mb()
	 * in __pagevec_lru_add_fn().
	 *
	 * See __pagevec_lru_add_fn for more explanation.
	 */
	if (!isolate_lru_page(page)) {
		putback_lru_page(page);
	} else {
		/*
		 * We lost the race. the page already moved to evictable list.
		 */
		if (PageUnevictable(page))
			count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages);
	}
}

/*
 * Mark page as mlocked if not already.
 * If page on LRU, isolate and putback to move to unevictable list.
 */
void mlock_vma_page(struct page *page)
{
	/* Serialize with page migration */
	BUG_ON(!PageLocked(page));

	VM_BUG_ON_PAGE(PageTail(page), page);
	VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page);

	if (!TestSetPageMlocked(page)) {
		int nr_pages = thp_nr_pages(page);

		mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages);
		count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages);
		if (!isolate_lru_page(page))
			putback_lru_page(page);
	}
}

/*
 * Finish munlock after successful page isolation
 *
 * Page must be locked. This is a wrapper for try_to_munlock()
 * and putback_lru_page() with munlock accounting.
 */
static void __munlock_isolated_page(struct page *page)
{
	/*
	 * Optimization: if the page was mapped just once, that's our mapping
	 * and we don't need to check all the other vmas.
	 */
	if (page_mapcount(page) > 1)
		try_to_munlock(page);

	/* Did try_to_unlock() succeed or punt? */
	if (!PageMlocked(page))
		count_vm_events(UNEVICTABLE_PGMUNLOCKED, thp_nr_pages(page));

	putback_lru_page(page);
}

/*
 * Accounting for page isolation fail during munlock
 *
 * Performs accounting when page isolation fails in munlock. There is nothing
 * else to do because it means some other task has already removed the page
 * from the LRU. putback_lru_page() will take care of removing the page from
 * the unevictable list, if necessary. vmscan [page_referenced()] will move
 * the page back to the unevictable list if some other vma has it mlocked.
 */
static void __munlock_isolation_failed(struct page *page)
{
	int nr_pages = thp_nr_pages(page);

	if (PageUnevictable(page))
		__count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages);
	else
		__count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages);
}

/**
 * munlock_vma_page - munlock a vma page
 * @page: page to be unlocked, either a normal page or THP page head
 *
 * returns the size of the page as a page mask (0 for normal page,
 *         HPAGE_PMD_NR - 1 for THP head page)
 *
 * called from munlock()/munmap() path with page supposedly on the LRU.
 * When we munlock a page, because the vma where we found the page is being
 * munlock()ed or munmap()ed, we want to check whether other vmas hold the
 * page locked so that we can leave it on the unevictable lru list and not
 * bother vmscan with it.  However, to walk the page's rmap list in
 * try_to_munlock() we must isolate the page from the LRU.  If some other
 * task has removed the page from the LRU, we won't be able to do that.
 * So we clear the PageMlocked as we might not get another chance.  If we
 * can't isolate the page, we leave it for putback_lru_page() and vmscan
 * [page_referenced()/try_to_unmap()] to deal with.
 */
unsigned int munlock_vma_page(struct page *page)
{
	int nr_pages;

	/* For try_to_munlock() and to serialize with page migration */
	BUG_ON(!PageLocked(page));
	VM_BUG_ON_PAGE(PageTail(page), page);

	if (!TestClearPageMlocked(page)) {
		/* Potentially, PTE-mapped THP: do not skip the rest PTEs */
		return 0;
	}

	nr_pages = thp_nr_pages(page);
	mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);

	if (!isolate_lru_page(page))
		__munlock_isolated_page(page);
	else
		__munlock_isolation_failed(page);

	return nr_pages - 1;
}

/*
 * convert get_user_pages() return value to posix mlock() error
 */
static int __mlock_posix_error_return(long retval)
{
	if (retval == -EFAULT)
		retval = -ENOMEM;
	else if (retval == -ENOMEM)
		retval = -EAGAIN;
	return retval;
}

/*
 * Prepare page for fast batched LRU putback via putback_lru_evictable_pagevec()
 *
 * The fast path is available only for evictable pages with single mapping.
 * Then we can bypass the per-cpu pvec and get better performance.
 * when mapcount > 1 we need try_to_munlock() which can fail.
 * when !page_evictable(), we need the full redo logic of putback_lru_page to
 * avoid leaving evictable page in unevictable list.
 *
 * In case of success, @page is added to @pvec and @pgrescued is incremented
 * in case that the page was previously unevictable. @page is also unlocked.
 */
static bool __putback_lru_fast_prepare(struct page *page, struct pagevec *pvec,
		int *pgrescued)
{
	VM_BUG_ON_PAGE(PageLRU(page), page);
	VM_BUG_ON_PAGE(!PageLocked(page), page);

	if (page_mapcount(page) <= 1 && page_evictable(page)) {
		pagevec_add(pvec, page);
		if (TestClearPageUnevictable(page))
			(*pgrescued)++;
		unlock_page(page);
		return true;
	}

	return false;
}

/*
 * Putback multiple evictable pages to the LRU
 *
 * Batched putback of evictable pages that bypasses the per-cpu pvec. Some of
 * the pages might have meanwhile become unevictable but that is OK.
 */
static void __putback_lru_fast(struct pagevec *pvec, int pgrescued)
{
	count_vm_events(UNEVICTABLE_PGMUNLOCKED, pagevec_count(pvec));
	/*
	 *__pagevec_lru_add() calls release_pages() so we don't call
	 * put_page() explicitly
	 */
	__pagevec_lru_add(pvec);
	count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
}

/*
 * Munlock a batch of pages from the same zone
 *
 * The work is split to two main phases. First phase clears the Mlocked flag
 * and attempts to isolate the pages, all under a single zone lru lock.
 * The second phase finishes the munlock only for pages where isolation
 * succeeded.
 *
 * Note that the pagevec may be modified during the process.
 */
static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
{
	int i;
	int nr = pagevec_count(pvec);
	int delta_munlocked = -nr;
	struct pagevec pvec_putback;
	struct lruvec *lruvec = NULL;
	int pgrescued = 0;

	pagevec_init(&pvec_putback);

	/* Phase 1: page isolation */
	for (i = 0; i < nr; i++) {
		struct page *page = pvec->pages[i];

		if (TestClearPageMlocked(page)) {
			/*
			 * We already have pin from follow_page_mask()
			 * so we can spare the get_page() here.
			 */
			if (TestClearPageLRU(page)) {
				lruvec = relock_page_lruvec_irq(page, lruvec);
				del_page_from_lru_list(page, lruvec);
				continue;
			} else
				__munlock_isolation_failed(page);
		} else {
			delta_munlocked++;
		}

		/*
		 * We won't be munlocking this page in the next phase
		 * but we still need to release the follow_page_mask()
		 * pin. We cannot do it under lru_lock however. If it's
		 * the last pin, __page_cache_release() would deadlock.
		 */
		pagevec_add(&pvec_putback, pvec->pages[i]);
		pvec->pages[i] = NULL;
	}
	if (lruvec) {
		__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
		unlock_page_lruvec_irq(lruvec);
	} else if (delta_munlocked) {
		mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
	}

	/* Now we can release pins of pages that we are not munlocking */
	pagevec_release(&pvec_putback);

	/* Phase 2: page munlock */
	for (i = 0; i < nr; i++) {
		struct page *page = pvec->pages[i];

		if (page) {
			lock_page(page);
			if (!__putback_lru_fast_prepare(page, &pvec_putback,
					&pgrescued)) {
				/*
				 * Slow path. We don't want to lose the last
				 * pin before unlock_page()
				 */
				get_page(page); /* for putback_lru_page() */
				__munlock_isolated_page(page);
				unlock_page(page);
				put_page(page); /* from follow_page_mask() */
			}
		}
	}

	/*
	 * Phase 3: page putback for pages that qualified for the fast path
	 * This will also call put_page() to return pin from follow_page_mask()
	 */
	if (pagevec_count(&pvec_putback))
		__putback_lru_fast(&pvec_putback, pgrescued);
}

/*
 * Fill up pagevec for __munlock_pagevec using pte walk
 *
 * The function expects that the struct page corresponding to @start address is
 * a non-TPH page already pinned and in the @pvec, and that it belongs to @zone.
 *
 * The rest of @pvec is filled by subsequent pages within the same pmd and same
 * zone, as long as the pte's are present and vm_normal_page() succeeds. These
 * pages also get pinned.
 *
 * Returns the address of the next page that should be scanned. This equals
 * @start + PAGE_SIZE when no page could be added by the pte walk.
 */
static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
			struct vm_area_struct *vma, struct zone *zone,
			unsigned long start, unsigned long end)
{
	pte_t *pte;
	spinlock_t *ptl;

	/*
	 * Initialize pte walk starting at the already pinned page where we
	 * are sure that there is a pte, as it was pinned under the same
	 * mmap_lock write op.
	 */
	pte = get_locked_pte(vma->vm_mm, start,	&ptl);
	/* Make sure we do not cross the page table boundary */
	end = pgd_addr_end(start, end);
	end = p4d_addr_end(start, end);
	end = pud_addr_end(start, end);
	end = pmd_addr_end(start, end);

	/* The page next to the pinned page is the first we will try to get */
	start += PAGE_SIZE;
	while (start < end) {
		struct page *page = NULL;
		pte++;
		if (pte_present(*pte))
			page = vm_normal_page(vma, start, *pte);
		/*
		 * Break if page could not be obtained or the page's node+zone does not
		 * match
		 */
		if (!page || page_zone(page) != zone)
			break;

		/*
		 * Do not use pagevec for PTE-mapped THP,
		 * munlock_vma_pages_range() will handle them.
		 */
		if (PageTransCompound(page))
			break;

		get_page(page);
		/*
		 * Increase the address that will be returned *before* the
		 * eventual break due to pvec becoming full by adding the page
		 */
		start += PAGE_SIZE;
		if (pagevec_add(pvec, page) == 0)
			break;
	}
	pte_unmap_unlock(pte, ptl);
	return start;
}

/*
 * munlock_vma_pages_range() - munlock all pages in the vma range.'
 * @vma - vma containing range to be munlock()ed.
 * @start - start address in @vma of the range
 * @end - end of range in @vma.
 *
 *  For mremap(), munmap() and exit().
 *
 * Called with @vma VM_LOCKED.
 *
 * Returns with VM_LOCKED cleared.  Callers must be prepared to
 * deal with this.
 *
 * We don't save and restore VM_LOCKED here because pages are
 * still on lru.  In unmap path, pages might be scanned by reclaim
 * and re-mlocked by try_to_{munlock|unmap} before we unmap and
 * free them.  This will result in freeing mlocked pages.
 */
void munlock_vma_pages_range(struct vm_area_struct *vma,
			     unsigned long start, unsigned long end)
{
	vma->vm_flags &= VM_LOCKED_CLEAR_MASK;

	while (start < end) {
		struct page *page;
		unsigned int page_mask = 0;
		unsigned long page_increm;
		struct pagevec pvec;
		struct zone *zone;

		pagevec_init(&pvec);
		/*
		 * Although FOLL_DUMP is intended for get_dump_page(),
		 * it just so happens that its special treatment of the
		 * ZERO_PAGE (returning an error instead of doing get_page)
		 * suits munlock very well (and if somehow an abnormal page
		 * has sneaked into the range, we won't oops here: great).
		 */
		page = follow_page(vma, start, FOLL_GET | FOLL_DUMP);

		if (page && !IS_ERR(page)) {
			if (PageTransTail(page)) {
				VM_BUG_ON_PAGE(PageMlocked(page), page);
				put_page(page); /* follow_page_mask() */
			} else if (PageTransHuge(page)) {
				lock_page(page);
				/*
				 * Any THP page found by follow_page_mask() may
				 * have gotten split before reaching
				 * munlock_vma_page(), so we need to compute
				 * the page_mask here instead.
				 */
				page_mask = munlock_vma_page(page);
				unlock_page(page);
				put_page(page); /* follow_page_mask() */
			} else {
				/*
				 * Non-huge pages are handled in batches via
				 * pagevec. The pin from follow_page_mask()
				 * prevents them from collapsing by THP.
				 */
				pagevec_add(&pvec, page);
				zone = page_zone(page);

				/*
				 * Try to fill the rest of pagevec using fast
				 * pte walk. This will also update start to
				 * the next page to process. Then munlock the
				 * pagevec.
				 */
				start = __munlock_pagevec_fill(&pvec, vma,
						zone, start, end);
				__munlock_pagevec(&pvec, zone);
				goto next;
			}
		}
		page_increm = 1 + page_mask;
		start += page_increm * PAGE_SIZE;
next:
		cond_resched();
	}
}

/*
 * mlock_fixup  - handle mlock[all]/munlock[all] requests.
 *
 * Filters out "special" vmas -- VM_LOCKED never gets set for these, and
 * munlock is a no-op.  However, for some special vmas, we go ahead and
 * populate the ptes.
 *
 * For vmas that pass the filters, merge/split as appropriate.
 */
static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
	unsigned long start, unsigned long end, vm_flags_t newflags)
{
	struct mm_struct *mm = vma->vm_mm;
	pgoff_t pgoff;
	int nr_pages;
	int ret = 0;
	int lock = !!(newflags & VM_LOCKED);
	vm_flags_t old_flags = vma->vm_flags;

	if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) ||
	    vma_is_dax(vma))
		/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
		goto out;

	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
	*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
			  vma->vm_file, pgoff, vma_policy(vma),
			  vma->vm_userfaultfd_ctx);
	if (*prev) {
		vma = *prev;
		goto success;
	}

	if (start != vma->vm_start) {
		ret = split_vma(mm, vma, start, 1);
		if (ret)
			goto out;
	}

	if (end != vma->vm_end) {
		ret = split_vma(mm, vma, end, 0);
		if (ret)
			goto out;
	}

success:
	/*
	 * Keep track of amount of locked VM.
	 */
	nr_pages = (end - start) >> PAGE_SHIFT;
	if (!lock)
		nr_pages = -nr_pages;
	else if (old_flags & VM_LOCKED)
		nr_pages = 0;
	mm->locked_vm += nr_pages;

	/*
	 * vm_flags is protected by the mmap_lock held in write mode.
	 * It's okay if try_to_unmap_one unmaps a page just after we
	 * set VM_LOCKED, populate_vma_page_range will bring it back.
	 */

	if (lock)
		vma->vm_flags = newflags;
	else
		munlock_vma_pages_range(vma, start, end);

out:
	*prev = vma;
	return ret;
}

static int apply_vma_lock_flags(unsigned long start, size_t len,
				vm_flags_t flags)
{
	unsigned long nstart, end, tmp;
	struct vm_area_struct *vma, *prev;
	int error;

	VM_BUG_ON(offset_in_page(start));
	VM_BUG_ON(len != PAGE_ALIGN(len));
	end = start + len;
	if (end < start)
		return -EINVAL;
	if (end == start)
		return 0;
	vma = find_vma(current->mm, start);
	if (!vma || vma->vm_start > start)
		return -ENOMEM;

	prev = vma->vm_prev;
	if (start > vma->vm_start)
		prev = vma;

	for (nstart = start ; ; ) {
		vm_flags_t newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;

		newflags |= flags;

		/* Here we know that  vma->vm_start <= nstart < vma->vm_end. */
		tmp = vma->vm_end;
		if (tmp > end)
			tmp = end;
		error = mlock_fixup(vma, &prev, nstart, tmp, newflags);
		if (error)
			break;
		nstart = tmp;
		if (nstart < prev->vm_end)
			nstart = prev->vm_end;
		if (nstart >= end)
			break;

		vma = prev->vm_next;
		if (!vma || vma->vm_start != nstart) {
			error = -ENOMEM;
			break;
		}
	}
	return error;
}

/*
 * Go through vma areas and sum size of mlocked
 * vma pages, as return value.
 * Note deferred memory locking case(mlock2(,,MLOCK_ONFAULT)
 * is also counted.
 * Return value: previously mlocked page counts
 */
static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm,
		unsigned long start, size_t len)
{
	struct vm_area_struct *vma;
	unsigned long count = 0;

	if (mm == NULL)
		mm = current->mm;

	vma = find_vma(mm, start);
	if (vma == NULL)
		return 0;

	for (; vma ; vma = vma->vm_next) {
		if (start >= vma->vm_end)
			continue;
		if (start + len <=  vma->vm_start)
			break;
		if (vma->vm_flags & VM_LOCKED) {
			if (start > vma->vm_start)
				count -= (start - vma->vm_start);
			if (start + len < vma->vm_end) {
				count += start + len - vma->vm_start;
				break;
			}
			count += vma->vm_end - vma->vm_start;
		}
	}

	return count >> PAGE_SHIFT;
}

static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags)
{
	unsigned long locked;
	unsigned long lock_limit;
	int error = -ENOMEM;

	start = untagged_addr(start);

	if (!can_do_mlock())
		return -EPERM;

	len = PAGE_ALIGN(len + (offset_in_page(start)));
	start &= PAGE_MASK;

	lock_limit = rlimit(RLIMIT_MEMLOCK);
	lock_limit >>= PAGE_SHIFT;
	locked = len >> PAGE_SHIFT;

	if (mmap_write_lock_killable(current->mm))
		return -EINTR;

	locked += current->mm->locked_vm;
	if ((locked > lock_limit) && (!capable(CAP_IPC_LOCK))) {
		/*
		 * It is possible that the regions requested intersect with
		 * previously mlocked areas, that part area in "mm->locked_vm"
		 * should not be counted to new mlock increment count. So check
		 * and adjust locked count if necessary.
		 */
		locked -= count_mm_mlocked_page_nr(current->mm,
				start, len);
	}

	/* check against resource limits */
	if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
		error = apply_vma_lock_flags(start, len, flags);

	mmap_write_unlock(current->mm);
	if (error)
		return error;

	error = __mm_populate(start, len, 0);
	if (error)
		return __mlock_posix_error_return(error);
	return 0;
}

SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
{
	return do_mlock(start, len, VM_LOCKED);
}

SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags)
{
	vm_flags_t vm_flags = VM_LOCKED;

	if (flags & ~MLOCK_ONFAULT)
		return -EINVAL;

	if (flags & MLOCK_ONFAULT)
		vm_flags |= VM_LOCKONFAULT;

	return do_mlock(start, len, vm_flags);
}

SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
{
	int ret;

	start = untagged_addr(start);

	len = PAGE_ALIGN(len + (offset_in_page(start)));
	start &= PAGE_MASK;

	if (mmap_write_lock_killable(current->mm))
		return -EINTR;
	ret = apply_vma_lock_flags(start, len, 0);
	mmap_write_unlock(current->mm);

	return ret;
}

/*
 * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall)
 * and translate into the appropriate modifications to mm->def_flags and/or the
 * flags for all current VMAs.
 *
 * There are a couple of subtleties with this.  If mlockall() is called multiple
 * times with different flags, the values do not necessarily stack.  If mlockall
 * is called once including the MCL_FUTURE flag and then a second time without
 * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags.
 */
static int apply_mlockall_flags(int flags)
{
	struct vm_area_struct *vma, *prev = NULL;
	vm_flags_t to_add = 0;

	current->mm->def_flags &= VM_LOCKED_CLEAR_MASK;
	if (flags & MCL_FUTURE) {
		current->mm->def_flags |= VM_LOCKED;

		if (flags & MCL_ONFAULT)
			current->mm->def_flags |= VM_LOCKONFAULT;

		if (!(flags & MCL_CURRENT))
			goto out;
	}

	if (flags & MCL_CURRENT) {
		to_add |= VM_LOCKED;
		if (flags & MCL_ONFAULT)
			to_add |= VM_LOCKONFAULT;
	}

	for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
		vm_flags_t newflags;

		newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
		newflags |= to_add;

		/* Ignore errors */
		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
		cond_resched();
	}
out:
	return 0;
}

SYSCALL_DEFINE1(mlockall, int, flags)
{
	unsigned long lock_limit;
	int ret;

	if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) ||
	    flags == MCL_ONFAULT)
		return -EINVAL;

	if (!can_do_mlock())
		return -EPERM;

	lock_limit = rlimit(RLIMIT_MEMLOCK);
	lock_limit >>= PAGE_SHIFT;

	if (mmap_write_lock_killable(current->mm))
		return -EINTR;

	ret = -ENOMEM;
	if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
	    capable(CAP_IPC_LOCK))
		ret = apply_mlockall_flags(flags);
	mmap_write_unlock(current->mm);
	if (!ret && (flags & MCL_CURRENT))
		mm_populate(0, TASK_SIZE);

	return ret;
}

SYSCALL_DEFINE0(munlockall)
{
	int ret;

	if (mmap_write_lock_killable(current->mm))
		return -EINTR;
	ret = apply_mlockall_flags(0);
	mmap_write_unlock(current->mm);
	return ret;
}

/*
 * Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB
 * shm segments) get accounted against the user_struct instead.
 */
static DEFINE_SPINLOCK(shmlock_user_lock);

int user_shm_lock(size_t size, struct user_struct *user)
{
	unsigned long lock_limit, locked;
	int allowed = 0;

	locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
	lock_limit = rlimit(RLIMIT_MEMLOCK);
	if (lock_limit == RLIM_INFINITY)
		allowed = 1;
	lock_limit >>= PAGE_SHIFT;
	spin_lock(&shmlock_user_lock);
	if (!allowed &&
	    locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK))
		goto out;
	get_uid(user);
	user->locked_shm += locked;
	allowed = 1;
out:
	spin_unlock(&shmlock_user_lock);
	return allowed;
}

void user_shm_unlock(size_t size, struct user_struct *user)
{
	spin_lock(&shmlock_user_lock);
	user->locked_shm -= (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
	spin_unlock(&shmlock_user_lock);
	free_uid(user);
}