summaryrefslogtreecommitdiffstats
path: root/mm/mprotect.c
blob: 7cd7f644da800d7d10cd1a9dc016dd02b04157b0 (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
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
// SPDX-License-Identifier: GPL-2.0
/*
 *  mm/mprotect.c
 *
 *  (C) Copyright 1994 Linus Torvalds
 *  (C) Copyright 2002 Christoph Hellwig
 *
 *  Address space accounting code	<alan@lxorguk.ukuu.org.uk>
 *  (C) Copyright 2002 Red Hat Inc, All Rights Reserved
 */

#include <linux/pagewalk.h>
#include <linux/hugetlb.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/fs.h>
#include <linux/highmem.h>
#include <linux/security.h>
#include <linux/mempolicy.h>
#include <linux/personality.h>
#include <linux/syscalls.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/mmu_notifier.h>
#include <linux/migrate.h>
#include <linux/perf_event.h>
#include <linux/pkeys.h>
#include <linux/ksm.h>
#include <linux/uaccess.h>
#include <linux/mm_inline.h>
#include <linux/pgtable.h>
#include <linux/sched/sysctl.h>
#include <linux/userfaultfd_k.h>
#include <linux/memory-tiers.h>
#include <asm/cacheflush.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
#include <asm/tlb.h>

#include "internal.h"

bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr,
			     pte_t pte)
{
	struct page *page;

	if (WARN_ON_ONCE(!(vma->vm_flags & VM_WRITE)))
		return false;

	/* Don't touch entries that are not even readable. */
	if (pte_protnone(pte))
		return false;

	/* Do we need write faults for softdirty tracking? */
	if (vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte))
		return false;

	/* Do we need write faults for uffd-wp tracking? */
	if (userfaultfd_pte_wp(vma, pte))
		return false;

	if (!(vma->vm_flags & VM_SHARED)) {
		/*
		 * Writable MAP_PRIVATE mapping: We can only special-case on
		 * exclusive anonymous pages, because we know that our
		 * write-fault handler similarly would map them writable without
		 * any additional checks while holding the PT lock.
		 */
		page = vm_normal_page(vma, addr, pte);
		return page && PageAnon(page) && PageAnonExclusive(page);
	}

	/*
	 * Writable MAP_SHARED mapping: "clean" might indicate that the FS still
	 * needs a real write-fault for writenotify
	 * (see vma_wants_writenotify()). If "dirty", the assumption is that the
	 * FS was already notified and we can simply mark the PTE writable
	 * just like the write-fault handler would do.
	 */
	return pte_dirty(pte);
}

static long change_pte_range(struct mmu_gather *tlb,
		struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr,
		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
{
	pte_t *pte, oldpte;
	spinlock_t *ptl;
	long pages = 0;
	int target_node = NUMA_NO_NODE;
	bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;

	tlb_change_page_size(tlb, PAGE_SIZE);
	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	if (!pte)
		return -EAGAIN;

	/* Get target node for single threaded private VMAs */
	if (prot_numa && !(vma->vm_flags & VM_SHARED) &&
	    atomic_read(&vma->vm_mm->mm_users) == 1)
		target_node = numa_node_id();

	flush_tlb_batched_pending(vma->vm_mm);
	arch_enter_lazy_mmu_mode();
	do {
		oldpte = ptep_get(pte);
		if (pte_present(oldpte)) {
			pte_t ptent;

			/*
			 * Avoid trapping faults against the zero or KSM
			 * pages. See similar comment in change_huge_pmd.
			 */
			if (prot_numa) {
				struct page *page;
				int nid;
				bool toptier;

				/* Avoid TLB flush if possible */
				if (pte_protnone(oldpte))
					continue;

				page = vm_normal_page(vma, addr, oldpte);
				if (!page || is_zone_device_page(page) || PageKsm(page))
					continue;

				/* Also skip shared copy-on-write pages */
				if (is_cow_mapping(vma->vm_flags) &&
				    page_count(page) != 1)
					continue;

				/*
				 * While migration can move some dirty pages,
				 * it cannot move them all from MIGRATE_ASYNC
				 * context.
				 */
				if (page_is_file_lru(page) && PageDirty(page))
					continue;

				/*
				 * Don't mess with PTEs if page is already on the node
				 * a single-threaded process is running on.
				 */
				nid = page_to_nid(page);
				if (target_node == nid)
					continue;
				toptier = node_is_toptier(nid);

				/*
				 * Skip scanning top tier node if normal numa
				 * balancing is disabled
				 */
				if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) &&
				    toptier)
					continue;
				if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING &&
				    !toptier)
					xchg_page_access_time(page,
						jiffies_to_msecs(jiffies));
			}

			oldpte = ptep_modify_prot_start(vma, addr, pte);
			ptent = pte_modify(oldpte, newprot);

			if (uffd_wp)
				ptent = pte_mkuffd_wp(ptent);
			else if (uffd_wp_resolve)
				ptent = pte_clear_uffd_wp(ptent);

			/*
			 * In some writable, shared mappings, we might want
			 * to catch actual write access -- see
			 * vma_wants_writenotify().
			 *
			 * In all writable, private mappings, we have to
			 * properly handle COW.
			 *
			 * In both cases, we can sometimes still change PTEs
			 * writable and avoid the write-fault handler, for
			 * example, if a PTE is already dirty and no other
			 * COW or special handling is required.
			 */
			if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) &&
			    !pte_write(ptent) &&
			    can_change_pte_writable(vma, addr, ptent))
				ptent = pte_mkwrite(ptent);

			ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
			if (pte_needs_flush(oldpte, ptent))
				tlb_flush_pte_range(tlb, addr, PAGE_SIZE);
			pages++;
		} else if (is_swap_pte(oldpte)) {
			swp_entry_t entry = pte_to_swp_entry(oldpte);
			pte_t newpte;

			if (is_writable_migration_entry(entry)) {
				struct page *page = pfn_swap_entry_to_page(entry);

				/*
				 * A protection check is difficult so
				 * just be safe and disable write
				 */
				if (PageAnon(page))
					entry = make_readable_exclusive_migration_entry(
							     swp_offset(entry));
				else
					entry = make_readable_migration_entry(swp_offset(entry));
				newpte = swp_entry_to_pte(entry);
				if (pte_swp_soft_dirty(oldpte))
					newpte = pte_swp_mksoft_dirty(newpte);
			} else if (is_writable_device_private_entry(entry)) {
				/*
				 * We do not preserve soft-dirtiness. See
				 * copy_nonpresent_pte() for explanation.
				 */
				entry = make_readable_device_private_entry(
							swp_offset(entry));
				newpte = swp_entry_to_pte(entry);
				if (pte_swp_uffd_wp(oldpte))
					newpte = pte_swp_mkuffd_wp(newpte);
			} else if (is_writable_device_exclusive_entry(entry)) {
				entry = make_readable_device_exclusive_entry(
							swp_offset(entry));
				newpte = swp_entry_to_pte(entry);
				if (pte_swp_soft_dirty(oldpte))
					newpte = pte_swp_mksoft_dirty(newpte);
				if (pte_swp_uffd_wp(oldpte))
					newpte = pte_swp_mkuffd_wp(newpte);
			} else if (is_pte_marker_entry(entry)) {
				/*
				 * Ignore error swap entries unconditionally,
				 * because any access should sigbus anyway.
				 */
				if (is_poisoned_swp_entry(entry))
					continue;
				/*
				 * If this is uffd-wp pte marker and we'd like
				 * to unprotect it, drop it; the next page
				 * fault will trigger without uffd trapping.
				 */
				if (uffd_wp_resolve) {
					pte_clear(vma->vm_mm, addr, pte);
					pages++;
				}
				continue;
			} else {
				newpte = oldpte;
			}

			if (uffd_wp)
				newpte = pte_swp_mkuffd_wp(newpte);
			else if (uffd_wp_resolve)
				newpte = pte_swp_clear_uffd_wp(newpte);

			if (!pte_same(oldpte, newpte)) {
				set_pte_at(vma->vm_mm, addr, pte, newpte);
				pages++;
			}
		} else {
			/* It must be an none page, or what else?.. */
			WARN_ON_ONCE(!pte_none(oldpte));

			/*
			 * Nobody plays with any none ptes besides
			 * userfaultfd when applying the protections.
			 */
			if (likely(!uffd_wp))
				continue;

			if (userfaultfd_wp_use_markers(vma)) {
				/*
				 * For file-backed mem, we need to be able to
				 * wr-protect a none pte, because even if the
				 * pte is none, the page/swap cache could
				 * exist.  Doing that by install a marker.
				 */
				set_pte_at(vma->vm_mm, addr, pte,
					   make_pte_marker(PTE_MARKER_UFFD_WP));
				pages++;
			}
		}
	} while (pte++, addr += PAGE_SIZE, addr != end);
	arch_leave_lazy_mmu_mode();
	pte_unmap_unlock(pte - 1, ptl);

	return pages;
}

/*
 * Return true if we want to split THPs into PTE mappings in change
 * protection procedure, false otherwise.
 */
static inline bool
pgtable_split_needed(struct vm_area_struct *vma, unsigned long cp_flags)
{
	/*
	 * pte markers only resides in pte level, if we need pte markers,
	 * we need to split.  We cannot wr-protect shmem thp because file
	 * thp is handled differently when split by erasing the pmd so far.
	 */
	return (cp_flags & MM_CP_UFFD_WP) && !vma_is_anonymous(vma);
}

/*
 * Return true if we want to populate pgtables in change protection
 * procedure, false otherwise
 */
static inline bool
pgtable_populate_needed(struct vm_area_struct *vma, unsigned long cp_flags)
{
	/* If not within ioctl(UFFDIO_WRITEPROTECT), then don't bother */
	if (!(cp_flags & MM_CP_UFFD_WP))
		return false;

	/* Populate if the userfaultfd mode requires pte markers */
	return userfaultfd_wp_use_markers(vma);
}

/*
 * Populate the pgtable underneath for whatever reason if requested.
 * When {pte|pmd|...}_alloc() failed we treat it the same way as pgtable
 * allocation failures during page faults by kicking OOM and returning
 * error.
 */
#define  change_pmd_prepare(vma, pmd, cp_flags)				\
	({								\
		long err = 0;						\
		if (unlikely(pgtable_populate_needed(vma, cp_flags))) {	\
			if (pte_alloc(vma->vm_mm, pmd))			\
				err = -ENOMEM;				\
		}							\
		err;							\
	})

/*
 * This is the general pud/p4d/pgd version of change_pmd_prepare(). We need to
 * have separate change_pmd_prepare() because pte_alloc() returns 0 on success,
 * while {pmd|pud|p4d}_alloc() returns the valid pointer on success.
 */
#define  change_prepare(vma, high, low, addr, cp_flags)			\
	  ({								\
		long err = 0;						\
		if (unlikely(pgtable_populate_needed(vma, cp_flags))) {	\
			low##_t *p = low##_alloc(vma->vm_mm, high, addr); \
			if (p == NULL)					\
				err = -ENOMEM;				\
		}							\
		err;							\
	})

static inline long change_pmd_range(struct mmu_gather *tlb,
		struct vm_area_struct *vma, pud_t *pud, unsigned long addr,
		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
{
	pmd_t *pmd;
	unsigned long next;
	long pages = 0;
	unsigned long nr_huge_updates = 0;
	struct mmu_notifier_range range;

	range.start = 0;

	pmd = pmd_offset(pud, addr);
	do {
		long ret;
		pmd_t _pmd;
again:
		next = pmd_addr_end(addr, end);

		ret = change_pmd_prepare(vma, pmd, cp_flags);
		if (ret) {
			pages = ret;
			break;
		}

		if (pmd_none(*pmd))
			goto next;

		/* invoke the mmu notifier if the pmd is populated */
		if (!range.start) {
			mmu_notifier_range_init(&range,
				MMU_NOTIFY_PROTECTION_VMA, 0,
				vma->vm_mm, addr, end);
			mmu_notifier_invalidate_range_start(&range);
		}

		_pmd = pmdp_get_lockless(pmd);
		if (is_swap_pmd(_pmd) || pmd_trans_huge(_pmd) || pmd_devmap(_pmd)) {
			if ((next - addr != HPAGE_PMD_SIZE) ||
			    pgtable_split_needed(vma, cp_flags)) {
				__split_huge_pmd(vma, pmd, addr, false, NULL);
				/*
				 * For file-backed, the pmd could have been
				 * cleared; make sure pmd populated if
				 * necessary, then fall-through to pte level.
				 */
				ret = change_pmd_prepare(vma, pmd, cp_flags);
				if (ret) {
					pages = ret;
					break;
				}
			} else {
				ret = change_huge_pmd(tlb, vma, pmd,
						addr, newprot, cp_flags);
				if (ret) {
					if (ret == HPAGE_PMD_NR) {
						pages += HPAGE_PMD_NR;
						nr_huge_updates++;
					}

					/* huge pmd was handled */
					goto next;
				}
			}
			/* fall through, the trans huge pmd just split */
		}

		ret = change_pte_range(tlb, vma, pmd, addr, next, newprot,
				       cp_flags);
		if (ret < 0)
			goto again;
		pages += ret;
next:
		cond_resched();
	} while (pmd++, addr = next, addr != end);

	if (range.start)
		mmu_notifier_invalidate_range_end(&range);

	if (nr_huge_updates)
		count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
	return pages;
}

static inline long change_pud_range(struct mmu_gather *tlb,
		struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr,
		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
{
	pud_t *pud;
	unsigned long next;
	long pages = 0, ret;

	pud = pud_offset(p4d, addr);
	do {
		next = pud_addr_end(addr, end);
		ret = change_prepare(vma, pud, pmd, addr, cp_flags);
		if (ret)
			return ret;
		if (pud_none_or_clear_bad(pud))
			continue;
		pages += change_pmd_range(tlb, vma, pud, addr, next, newprot,
					  cp_flags);
	} while (pud++, addr = next, addr != end);

	return pages;
}

static inline long change_p4d_range(struct mmu_gather *tlb,
		struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr,
		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
{
	p4d_t *p4d;
	unsigned long next;
	long pages = 0, ret;

	p4d = p4d_offset(pgd, addr);
	do {
		next = p4d_addr_end(addr, end);
		ret = change_prepare(vma, p4d, pud, addr, cp_flags);
		if (ret)
			return ret;
		if (p4d_none_or_clear_bad(p4d))
			continue;
		pages += change_pud_range(tlb, vma, p4d, addr, next, newprot,
					  cp_flags);
	} while (p4d++, addr = next, addr != end);

	return pages;
}

static long change_protection_range(struct mmu_gather *tlb,
		struct vm_area_struct *vma, unsigned long addr,
		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
{
	struct mm_struct *mm = vma->vm_mm;
	pgd_t *pgd;
	unsigned long next;
	long pages = 0, ret;

	BUG_ON(addr >= end);
	pgd = pgd_offset(mm, addr);
	tlb_start_vma(tlb, vma);
	do {
		next = pgd_addr_end(addr, end);
		ret = change_prepare(vma, pgd, p4d, addr, cp_flags);
		if (ret) {
			pages = ret;
			break;
		}
		if (pgd_none_or_clear_bad(pgd))
			continue;
		pages += change_p4d_range(tlb, vma, pgd, addr, next, newprot,
					  cp_flags);
	} while (pgd++, addr = next, addr != end);

	tlb_end_vma(tlb, vma);

	return pages;
}

long change_protection(struct mmu_gather *tlb,
		       struct vm_area_struct *vma, unsigned long start,
		       unsigned long end, unsigned long cp_flags)
{
	pgprot_t newprot = vma->vm_page_prot;
	long pages;

	BUG_ON((cp_flags & MM_CP_UFFD_WP_ALL) == MM_CP_UFFD_WP_ALL);

#ifdef CONFIG_NUMA_BALANCING
	/*
	 * Ordinary protection updates (mprotect, uffd-wp, softdirty tracking)
	 * are expected to reflect their requirements via VMA flags such that
	 * vma_set_page_prot() will adjust vma->vm_page_prot accordingly.
	 */
	if (cp_flags & MM_CP_PROT_NUMA)
		newprot = PAGE_NONE;
#else
	WARN_ON_ONCE(cp_flags & MM_CP_PROT_NUMA);
#endif

	if (is_vm_hugetlb_page(vma))
		pages = hugetlb_change_protection(vma, start, end, newprot,
						  cp_flags);
	else
		pages = change_protection_range(tlb, vma, start, end, newprot,
						cp_flags);

	return pages;
}

static int prot_none_pte_entry(pte_t *pte, unsigned long addr,
			       unsigned long next, struct mm_walk *walk)
{
	return pfn_modify_allowed(pte_pfn(ptep_get(pte)),
				  *(pgprot_t *)(walk->private)) ?
		0 : -EACCES;
}

static int prot_none_hugetlb_entry(pte_t *pte, unsigned long hmask,
				   unsigned long addr, unsigned long next,
				   struct mm_walk *walk)
{
	return pfn_modify_allowed(pte_pfn(ptep_get(pte)),
				  *(pgprot_t *)(walk->private)) ?
		0 : -EACCES;
}

static int prot_none_test(unsigned long addr, unsigned long next,
			  struct mm_walk *walk)
{
	return 0;
}

static const struct mm_walk_ops prot_none_walk_ops = {
	.pte_entry		= prot_none_pte_entry,
	.hugetlb_entry		= prot_none_hugetlb_entry,
	.test_walk		= prot_none_test,
};

int
mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb,
	       struct vm_area_struct *vma, struct vm_area_struct **pprev,
	       unsigned long start, unsigned long end, unsigned long newflags)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long oldflags = vma->vm_flags;
	long nrpages = (end - start) >> PAGE_SHIFT;
	unsigned int mm_cp_flags = 0;
	unsigned long charged = 0;
	pgoff_t pgoff;
	int error;

	if (newflags == oldflags) {
		*pprev = vma;
		return 0;
	}

	/*
	 * Do PROT_NONE PFN permission checks here when we can still
	 * bail out without undoing a lot of state. This is a rather
	 * uncommon case, so doesn't need to be very optimized.
	 */
	if (arch_has_pfn_modify_check() &&
	    (vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
	    (newflags & VM_ACCESS_FLAGS) == 0) {
		pgprot_t new_pgprot = vm_get_page_prot(newflags);

		error = walk_page_range(current->mm, start, end,
				&prot_none_walk_ops, &new_pgprot);
		if (error)
			return error;
	}

	/*
	 * If we make a private mapping writable we increase our commit;
	 * but (without finer accounting) cannot reduce our commit if we
	 * make it unwritable again. hugetlb mapping were accounted for
	 * even if read-only so there is no need to account for them here
	 */
	if (newflags & VM_WRITE) {
		/* Check space limits when area turns into data. */
		if (!may_expand_vm(mm, newflags, nrpages) &&
				may_expand_vm(mm, oldflags, nrpages))
			return -ENOMEM;
		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
						VM_SHARED|VM_NORESERVE))) {
			charged = nrpages;
			if (security_vm_enough_memory_mm(mm, charged))
				return -ENOMEM;
			newflags |= VM_ACCOUNT;
		}
	}

	/*
	 * First try to merge with previous and/or next vma.
	 */
	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
	*pprev = vma_merge(vmi, mm, *pprev, start, end, newflags,
			   vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
			   vma->vm_userfaultfd_ctx, anon_vma_name(vma));
	if (*pprev) {
		vma = *pprev;
		VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY);
		goto success;
	}

	*pprev = vma;

	if (start != vma->vm_start) {
		error = split_vma(vmi, vma, start, 1);
		if (error)
			goto fail;
	}

	if (end != vma->vm_end) {
		error = split_vma(vmi, vma, end, 0);
		if (error)
			goto fail;
	}

success:
	/*
	 * vm_flags and vm_page_prot are protected by the mmap_lock
	 * held in write mode.
	 */
	vma_start_write(vma);
	vm_flags_reset(vma, newflags);
	if (vma_wants_manual_pte_write_upgrade(vma))
		mm_cp_flags |= MM_CP_TRY_CHANGE_WRITABLE;
	vma_set_page_prot(vma);

	change_protection(tlb, vma, start, end, mm_cp_flags);

	/*
	 * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major
	 * fault on access.
	 */
	if ((oldflags & (VM_WRITE | VM_SHARED | VM_LOCKED)) == VM_LOCKED &&
			(newflags & VM_WRITE)) {
		populate_vma_page_range(vma, start, end, NULL);
	}

	vm_stat_account(mm, oldflags, -nrpages);
	vm_stat_account(mm, newflags, nrpages);
	perf_event_mmap(vma);
	return 0;

fail:
	vm_unacct_memory(charged);
	return error;
}

/*
 * pkey==-1 when doing a legacy mprotect()
 */
static int do_mprotect_pkey(unsigned long start, size_t len,
		unsigned long prot, int pkey)
{
	unsigned long nstart, end, tmp, reqprot;
	struct vm_area_struct *vma, *prev;
	int error;
	const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP);
	const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
				(prot & PROT_READ);
	struct mmu_gather tlb;
	struct vma_iterator vmi;

	start = untagged_addr(start);

	prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
	if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
		return -EINVAL;

	if (start & ~PAGE_MASK)
		return -EINVAL;
	if (!len)
		return 0;
	len = PAGE_ALIGN(len);
	end = start + len;
	if (end <= start)
		return -ENOMEM;
	if (!arch_validate_prot(prot, start))
		return -EINVAL;

	reqprot = prot;

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

	/*
	 * If userspace did not allocate the pkey, do not let
	 * them use it here.
	 */
	error = -EINVAL;
	if ((pkey != -1) && !mm_pkey_is_allocated(current->mm, pkey))
		goto out;

	vma_iter_init(&vmi, current->mm, start);
	vma = vma_find(&vmi, end);
	error = -ENOMEM;
	if (!vma)
		goto out;

	if (unlikely(grows & PROT_GROWSDOWN)) {
		if (vma->vm_start >= end)
			goto out;
		start = vma->vm_start;
		error = -EINVAL;
		if (!(vma->vm_flags & VM_GROWSDOWN))
			goto out;
	} else {
		if (vma->vm_start > start)
			goto out;
		if (unlikely(grows & PROT_GROWSUP)) {
			end = vma->vm_end;
			error = -EINVAL;
			if (!(vma->vm_flags & VM_GROWSUP))
				goto out;
		}
	}

	prev = vma_prev(&vmi);
	if (start > vma->vm_start)
		prev = vma;

	tlb_gather_mmu(&tlb, current->mm);
	nstart = start;
	tmp = vma->vm_start;
	for_each_vma_range(vmi, vma, end) {
		unsigned long mask_off_old_flags;
		unsigned long newflags;
		int new_vma_pkey;

		if (vma->vm_start != tmp) {
			error = -ENOMEM;
			break;
		}

		/* Does the application expect PROT_READ to imply PROT_EXEC */
		if (rier && (vma->vm_flags & VM_MAYEXEC))
			prot |= PROT_EXEC;

		/*
		 * Each mprotect() call explicitly passes r/w/x permissions.
		 * If a permission is not passed to mprotect(), it must be
		 * cleared from the VMA.
		 */
		mask_off_old_flags = VM_ACCESS_FLAGS | VM_FLAGS_CLEAR;

		new_vma_pkey = arch_override_mprotect_pkey(vma, prot, pkey);
		newflags = calc_vm_prot_bits(prot, new_vma_pkey);
		newflags |= (vma->vm_flags & ~mask_off_old_flags);

		/* newflags >> 4 shift VM_MAY% in place of VM_% */
		if ((newflags & ~(newflags >> 4)) & VM_ACCESS_FLAGS) {
			error = -EACCES;
			break;
		}

		if (map_deny_write_exec(vma, newflags)) {
			error = -EACCES;
			break;
		}

		/* Allow architectures to sanity-check the new flags */
		if (!arch_validate_flags(newflags)) {
			error = -EINVAL;
			break;
		}

		error = security_file_mprotect(vma, reqprot, prot);
		if (error)
			break;

		tmp = vma->vm_end;
		if (tmp > end)
			tmp = end;

		if (vma->vm_ops && vma->vm_ops->mprotect) {
			error = vma->vm_ops->mprotect(vma, nstart, tmp, newflags);
			if (error)
				break;
		}

		error = mprotect_fixup(&vmi, &tlb, vma, &prev, nstart, tmp, newflags);
		if (error)
			break;

		tmp = vma_iter_end(&vmi);
		nstart = tmp;
		prot = reqprot;
	}
	tlb_finish_mmu(&tlb);

	if (!error && tmp < end)
		error = -ENOMEM;

out:
	mmap_write_unlock(current->mm);
	return error;
}

SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
		unsigned long, prot)
{
	return do_mprotect_pkey(start, len, prot, -1);
}

#ifdef CONFIG_ARCH_HAS_PKEYS

SYSCALL_DEFINE4(pkey_mprotect, unsigned long, start, size_t, len,
		unsigned long, prot, int, pkey)
{
	return do_mprotect_pkey(start, len, prot, pkey);
}

SYSCALL_DEFINE2(pkey_alloc, unsigned long, flags, unsigned long, init_val)
{
	int pkey;
	int ret;

	/* No flags supported yet. */
	if (flags)
		return -EINVAL;
	/* check for unsupported init values */
	if (init_val & ~PKEY_ACCESS_MASK)
		return -EINVAL;

	mmap_write_lock(current->mm);
	pkey = mm_pkey_alloc(current->mm);

	ret = -ENOSPC;
	if (pkey == -1)
		goto out;

	ret = arch_set_user_pkey_access(current, pkey, init_val);
	if (ret) {
		mm_pkey_free(current->mm, pkey);
		goto out;
	}
	ret = pkey;
out:
	mmap_write_unlock(current->mm);
	return ret;
}

SYSCALL_DEFINE1(pkey_free, int, pkey)
{
	int ret;

	mmap_write_lock(current->mm);
	ret = mm_pkey_free(current->mm, pkey);
	mmap_write_unlock(current->mm);

	/*
	 * We could provide warnings or errors if any VMA still
	 * has the pkey set here.
	 */
	return ret;
}

#endif /* CONFIG_ARCH_HAS_PKEYS */