summaryrefslogtreecommitdiffstats
path: root/mm/mremap.c
blob: 975a14c4a24ea4e38b3be8e145cef06b6d3e365b (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
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
// SPDX-License-Identifier: GPL-2.0
/*
 *	mm/mremap.c
 *
 *	(C) Copyright 1996 Linus Torvalds
 *
 *	Address space accounting code	<alan@lxorguk.ukuu.org.uk>
 *	(C) Copyright 2002 Red Hat Inc, All Rights Reserved
 */

#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/shm.h>
#include <linux/ksm.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/capability.h>
#include <linux/fs.h>
#include <linux/swapops.h>
#include <linux/highmem.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/mmu_notifier.h>
#include <linux/uaccess.h>
#include <linux/mm-arch-hooks.h>
#include <linux/userfaultfd_k.h>

#include <asm/cacheflush.h>
#include <asm/tlbflush.h>

#include "internal.h"

static pud_t *get_old_pud(struct mm_struct *mm, unsigned long addr)
{
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;

	pgd = pgd_offset(mm, addr);
	if (pgd_none_or_clear_bad(pgd))
		return NULL;

	p4d = p4d_offset(pgd, addr);
	if (p4d_none_or_clear_bad(p4d))
		return NULL;

	pud = pud_offset(p4d, addr);
	if (pud_none_or_clear_bad(pud))
		return NULL;

	return pud;
}

static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
{
	pud_t *pud;
	pmd_t *pmd;

	pud = get_old_pud(mm, addr);
	if (!pud)
		return NULL;

	pmd = pmd_offset(pud, addr);
	if (pmd_none(*pmd))
		return NULL;

	return pmd;
}

static pud_t *alloc_new_pud(struct mm_struct *mm, struct vm_area_struct *vma,
			    unsigned long addr)
{
	pgd_t *pgd;
	p4d_t *p4d;

	pgd = pgd_offset(mm, addr);
	p4d = p4d_alloc(mm, pgd, addr);
	if (!p4d)
		return NULL;

	return pud_alloc(mm, p4d, addr);
}

static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
			    unsigned long addr)
{
	pud_t *pud;
	pmd_t *pmd;

	pud = alloc_new_pud(mm, vma, addr);
	if (!pud)
		return NULL;

	pmd = pmd_alloc(mm, pud, addr);
	if (!pmd)
		return NULL;

	VM_BUG_ON(pmd_trans_huge(*pmd));

	return pmd;
}

static void take_rmap_locks(struct vm_area_struct *vma)
{
	if (vma->vm_file)
		i_mmap_lock_write(vma->vm_file->f_mapping);
	if (vma->anon_vma)
		anon_vma_lock_write(vma->anon_vma);
}

static void drop_rmap_locks(struct vm_area_struct *vma)
{
	if (vma->anon_vma)
		anon_vma_unlock_write(vma->anon_vma);
	if (vma->vm_file)
		i_mmap_unlock_write(vma->vm_file->f_mapping);
}

static pte_t move_soft_dirty_pte(pte_t pte)
{
	/*
	 * Set soft dirty bit so we can notice
	 * in userspace the ptes were moved.
	 */
#ifdef CONFIG_MEM_SOFT_DIRTY
	if (pte_present(pte))
		pte = pte_mksoft_dirty(pte);
	else if (is_swap_pte(pte))
		pte = pte_swp_mksoft_dirty(pte);
#endif
	return pte;
}

static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
		unsigned long old_addr, unsigned long old_end,
		struct vm_area_struct *new_vma, pmd_t *new_pmd,
		unsigned long new_addr, bool need_rmap_locks)
{
	struct mm_struct *mm = vma->vm_mm;
	pte_t *old_pte, *new_pte, pte;
	spinlock_t *old_ptl, *new_ptl;
	bool force_flush = false;
	unsigned long len = old_end - old_addr;

	/*
	 * When need_rmap_locks is true, we take the i_mmap_rwsem and anon_vma
	 * locks to ensure that rmap will always observe either the old or the
	 * new ptes. This is the easiest way to avoid races with
	 * truncate_pagecache(), page migration, etc...
	 *
	 * When need_rmap_locks is false, we use other ways to avoid
	 * such races:
	 *
	 * - During exec() shift_arg_pages(), we use a specially tagged vma
	 *   which rmap call sites look for using vma_is_temporary_stack().
	 *
	 * - During mremap(), new_vma is often known to be placed after vma
	 *   in rmap traversal order. This ensures rmap will always observe
	 *   either the old pte, or the new pte, or both (the page table locks
	 *   serialize access to individual ptes, but only rmap traversal
	 *   order guarantees that we won't miss both the old and new ptes).
	 */
	if (need_rmap_locks)
		take_rmap_locks(vma);

	/*
	 * We don't have to worry about the ordering of src and dst
	 * pte locks because exclusive mmap_lock prevents deadlock.
	 */
	old_pte = pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl);
	new_pte = pte_offset_map(new_pmd, new_addr);
	new_ptl = pte_lockptr(mm, new_pmd);
	if (new_ptl != old_ptl)
		spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
	flush_tlb_batched_pending(vma->vm_mm);
	arch_enter_lazy_mmu_mode();

	for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE,
				   new_pte++, new_addr += PAGE_SIZE) {
		if (pte_none(*old_pte))
			continue;

		pte = ptep_get_and_clear(mm, old_addr, old_pte);
		/*
		 * If we are remapping a valid PTE, make sure
		 * to flush TLB before we drop the PTL for the
		 * PTE.
		 *
		 * NOTE! Both old and new PTL matter: the old one
		 * for racing with page_mkclean(), the new one to
		 * make sure the physical page stays valid until
		 * the TLB entry for the old mapping has been
		 * flushed.
		 */
		if (pte_present(pte))
			force_flush = true;
		pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr);
		pte = move_soft_dirty_pte(pte);
		set_pte_at(mm, new_addr, new_pte, pte);
	}

	arch_leave_lazy_mmu_mode();
	if (force_flush)
		flush_tlb_range(vma, old_end - len, old_end);
	if (new_ptl != old_ptl)
		spin_unlock(new_ptl);
	pte_unmap(new_pte - 1);
	pte_unmap_unlock(old_pte - 1, old_ptl);
	if (need_rmap_locks)
		drop_rmap_locks(vma);
}

#ifdef CONFIG_HAVE_MOVE_PMD
static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
		  unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd)
{
	spinlock_t *old_ptl, *new_ptl;
	struct mm_struct *mm = vma->vm_mm;
	pmd_t pmd;

	/*
	 * The destination pmd shouldn't be established, free_pgtables()
	 * should have released it.
	 *
	 * However, there's a case during execve() where we use mremap
	 * to move the initial stack, and in that case the target area
	 * may overlap the source area (always moving down).
	 *
	 * If everything is PMD-aligned, that works fine, as moving
	 * each pmd down will clear the source pmd. But if we first
	 * have a few 4kB-only pages that get moved down, and then
	 * hit the "now the rest is PMD-aligned, let's do everything
	 * one pmd at a time", we will still have the old (now empty
	 * of any 4kB pages, but still there) PMD in the page table
	 * tree.
	 *
	 * Warn on it once - because we really should try to figure
	 * out how to do this better - but then say "I won't move
	 * this pmd".
	 *
	 * One alternative might be to just unmap the target pmd at
	 * this point, and verify that it really is empty. We'll see.
	 */
	if (WARN_ON_ONCE(!pmd_none(*new_pmd)))
		return false;

	/*
	 * We don't have to worry about the ordering of src and dst
	 * ptlocks because exclusive mmap_lock prevents deadlock.
	 */
	old_ptl = pmd_lock(vma->vm_mm, old_pmd);
	new_ptl = pmd_lockptr(mm, new_pmd);
	if (new_ptl != old_ptl)
		spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);

	/* Clear the pmd */
	pmd = *old_pmd;
	pmd_clear(old_pmd);

	VM_BUG_ON(!pmd_none(*new_pmd));

	/* Set the new pmd */
	set_pmd_at(mm, new_addr, new_pmd, pmd);
	flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
	if (new_ptl != old_ptl)
		spin_unlock(new_ptl);
	spin_unlock(old_ptl);

	return true;
}
#else
static inline bool move_normal_pmd(struct vm_area_struct *vma,
		unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd,
		pmd_t *new_pmd)
{
	return false;
}
#endif

#ifdef CONFIG_HAVE_MOVE_PUD
static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr,
		  unsigned long new_addr, pud_t *old_pud, pud_t *new_pud)
{
	spinlock_t *old_ptl, *new_ptl;
	struct mm_struct *mm = vma->vm_mm;
	pud_t pud;

	/*
	 * The destination pud shouldn't be established, free_pgtables()
	 * should have released it.
	 */
	if (WARN_ON_ONCE(!pud_none(*new_pud)))
		return false;

	/*
	 * We don't have to worry about the ordering of src and dst
	 * ptlocks because exclusive mmap_lock prevents deadlock.
	 */
	old_ptl = pud_lock(vma->vm_mm, old_pud);
	new_ptl = pud_lockptr(mm, new_pud);
	if (new_ptl != old_ptl)
		spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);

	/* Clear the pud */
	pud = *old_pud;
	pud_clear(old_pud);

	VM_BUG_ON(!pud_none(*new_pud));

	/* Set the new pud */
	set_pud_at(mm, new_addr, new_pud, pud);
	flush_tlb_range(vma, old_addr, old_addr + PUD_SIZE);
	if (new_ptl != old_ptl)
		spin_unlock(new_ptl);
	spin_unlock(old_ptl);

	return true;
}
#else
static inline bool move_normal_pud(struct vm_area_struct *vma,
		unsigned long old_addr, unsigned long new_addr, pud_t *old_pud,
		pud_t *new_pud)
{
	return false;
}
#endif

enum pgt_entry {
	NORMAL_PMD,
	HPAGE_PMD,
	NORMAL_PUD,
};

/*
 * Returns an extent of the corresponding size for the pgt_entry specified if
 * valid. Else returns a smaller extent bounded by the end of the source and
 * destination pgt_entry.
 */
static unsigned long get_extent(enum pgt_entry entry, unsigned long old_addr,
			unsigned long old_end, unsigned long new_addr)
{
	unsigned long next, extent, mask, size;

	switch (entry) {
	case HPAGE_PMD:
	case NORMAL_PMD:
		mask = PMD_MASK;
		size = PMD_SIZE;
		break;
	case NORMAL_PUD:
		mask = PUD_MASK;
		size = PUD_SIZE;
		break;
	default:
		BUILD_BUG();
		break;
	}

	next = (old_addr + size) & mask;
	/* even if next overflowed, extent below will be ok */
	extent = (next > old_end) ? old_end - old_addr : next - old_addr;
	next = (new_addr + size) & mask;
	if (extent > next - new_addr)
		extent = next - new_addr;
	return extent;
}

/*
 * Attempts to speedup the move by moving entry at the level corresponding to
 * pgt_entry. Returns true if the move was successful, else false.
 */
static bool move_pgt_entry(enum pgt_entry entry, struct vm_area_struct *vma,
			unsigned long old_addr, unsigned long new_addr,
			void *old_entry, void *new_entry, bool need_rmap_locks)
{
	bool moved = false;

	/* See comment in move_ptes() */
	if (need_rmap_locks)
		take_rmap_locks(vma);

	switch (entry) {
	case NORMAL_PMD:
		moved = move_normal_pmd(vma, old_addr, new_addr, old_entry,
					new_entry);
		break;
	case NORMAL_PUD:
		moved = move_normal_pud(vma, old_addr, new_addr, old_entry,
					new_entry);
		break;
	case HPAGE_PMD:
		moved = IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
			move_huge_pmd(vma, old_addr, new_addr, old_entry,
				      new_entry);
		break;
	default:
		WARN_ON_ONCE(1);
		break;
	}

	if (need_rmap_locks)
		drop_rmap_locks(vma);

	return moved;
}

unsigned long move_page_tables(struct vm_area_struct *vma,
		unsigned long old_addr, struct vm_area_struct *new_vma,
		unsigned long new_addr, unsigned long len,
		bool need_rmap_locks)
{
	unsigned long extent, old_end;
	struct mmu_notifier_range range;
	pmd_t *old_pmd, *new_pmd;

	old_end = old_addr + len;
	flush_cache_range(vma, old_addr, old_end);

	mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
				old_addr, old_end);
	mmu_notifier_invalidate_range_start(&range);

	for (; old_addr < old_end; old_addr += extent, new_addr += extent) {
		cond_resched();
		/*
		 * If extent is PUD-sized try to speed up the move by moving at the
		 * PUD level if possible.
		 */
		extent = get_extent(NORMAL_PUD, old_addr, old_end, new_addr);
		if (IS_ENABLED(CONFIG_HAVE_MOVE_PUD) && extent == PUD_SIZE) {
			pud_t *old_pud, *new_pud;

			old_pud = get_old_pud(vma->vm_mm, old_addr);
			if (!old_pud)
				continue;
			new_pud = alloc_new_pud(vma->vm_mm, vma, new_addr);
			if (!new_pud)
				break;
			if (move_pgt_entry(NORMAL_PUD, vma, old_addr, new_addr,
					   old_pud, new_pud, need_rmap_locks))
				continue;
		}

		extent = get_extent(NORMAL_PMD, old_addr, old_end, new_addr);
		old_pmd = get_old_pmd(vma->vm_mm, old_addr);
		if (!old_pmd)
			continue;
		new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr);
		if (!new_pmd)
			break;
		if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd) ||
		    pmd_devmap(*old_pmd)) {
			if (extent == HPAGE_PMD_SIZE &&
			    move_pgt_entry(HPAGE_PMD, vma, old_addr, new_addr,
					   old_pmd, new_pmd, need_rmap_locks))
				continue;
			split_huge_pmd(vma, old_pmd, old_addr);
			if (pmd_trans_unstable(old_pmd))
				continue;
		} else if (IS_ENABLED(CONFIG_HAVE_MOVE_PMD) &&
			   extent == PMD_SIZE) {
			/*
			 * If the extent is PMD-sized, try to speed the move by
			 * moving at the PMD level if possible.
			 */
			if (move_pgt_entry(NORMAL_PMD, vma, old_addr, new_addr,
					   old_pmd, new_pmd, need_rmap_locks))
				continue;
		}

		if (pte_alloc(new_vma->vm_mm, new_pmd))
			break;
		move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma,
			  new_pmd, new_addr, need_rmap_locks);
	}

	mmu_notifier_invalidate_range_end(&range);

	return len + old_addr - old_end;	/* how much done */
}

static unsigned long move_vma(struct vm_area_struct *vma,
		unsigned long old_addr, unsigned long old_len,
		unsigned long new_len, unsigned long new_addr,
		bool *locked, unsigned long flags,
		struct vm_userfaultfd_ctx *uf, struct list_head *uf_unmap)
{
	struct mm_struct *mm = vma->vm_mm;
	struct vm_area_struct *new_vma;
	unsigned long vm_flags = vma->vm_flags;
	unsigned long new_pgoff;
	unsigned long moved_len;
	unsigned long excess = 0;
	unsigned long hiwater_vm;
	int split = 0;
	int err;
	bool need_rmap_locks;

	/*
	 * We'd prefer to avoid failure later on in do_munmap:
	 * which may split one vma into three before unmapping.
	 */
	if (mm->map_count >= sysctl_max_map_count - 3)
		return -ENOMEM;

	/*
	 * Advise KSM to break any KSM pages in the area to be moved:
	 * it would be confusing if they were to turn up at the new
	 * location, where they happen to coincide with different KSM
	 * pages recently unmapped.  But leave vma->vm_flags as it was,
	 * so KSM can come around to merge on vma and new_vma afterwards.
	 */
	err = ksm_madvise(vma, old_addr, old_addr + old_len,
						MADV_UNMERGEABLE, &vm_flags);
	if (err)
		return err;

	new_pgoff = vma->vm_pgoff + ((old_addr - vma->vm_start) >> PAGE_SHIFT);
	new_vma = copy_vma(&vma, new_addr, new_len, new_pgoff,
			   &need_rmap_locks);
	if (!new_vma)
		return -ENOMEM;

	moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len,
				     need_rmap_locks);
	if (moved_len < old_len) {
		err = -ENOMEM;
	} else if (vma->vm_ops && vma->vm_ops->mremap) {
		err = vma->vm_ops->mremap(new_vma);
	}

	if (unlikely(err)) {
		/*
		 * On error, move entries back from new area to old,
		 * which will succeed since page tables still there,
		 * and then proceed to unmap new area instead of old.
		 */
		move_page_tables(new_vma, new_addr, vma, old_addr, moved_len,
				 true);
		vma = new_vma;
		old_len = new_len;
		old_addr = new_addr;
		new_addr = err;
	} else {
		mremap_userfaultfd_prep(new_vma, uf);
		arch_remap(mm, old_addr, old_addr + old_len,
			   new_addr, new_addr + new_len);
	}

	/* Conceal VM_ACCOUNT so old reservation is not undone */
	if (vm_flags & VM_ACCOUNT) {
		vma->vm_flags &= ~VM_ACCOUNT;
		excess = vma->vm_end - vma->vm_start - old_len;
		if (old_addr > vma->vm_start &&
		    old_addr + old_len < vma->vm_end)
			split = 1;
	}

	/*
	 * If we failed to move page tables we still do total_vm increment
	 * since do_munmap() will decrement it by old_len == new_len.
	 *
	 * Since total_vm is about to be raised artificially high for a
	 * moment, we need to restore high watermark afterwards: if stats
	 * are taken meanwhile, total_vm and hiwater_vm appear too high.
	 * If this were a serious issue, we'd add a flag to do_munmap().
	 */
	hiwater_vm = mm->hiwater_vm;
	vm_stat_account(mm, vma->vm_flags, new_len >> PAGE_SHIFT);

	/* Tell pfnmap has moved from this vma */
	if (unlikely(vma->vm_flags & VM_PFNMAP))
		untrack_pfn_moved(vma);

	if (unlikely(!err && (flags & MREMAP_DONTUNMAP))) {
		if (vm_flags & VM_ACCOUNT) {
			/* Always put back VM_ACCOUNT since we won't unmap */
			vma->vm_flags |= VM_ACCOUNT;

			vm_acct_memory(new_len >> PAGE_SHIFT);
		}

		/*
		 * VMAs can actually be merged back together in copy_vma
		 * calling merge_vma. This can happen with anonymous vmas
		 * which have not yet been faulted, so if we were to consider
		 * this VMA split we'll end up adding VM_ACCOUNT on the
		 * next VMA, which is completely unrelated if this VMA
		 * was re-merged.
		 */
		if (split && new_vma == vma)
			split = 0;

		/* We always clear VM_LOCKED[ONFAULT] on the old vma */
		vma->vm_flags &= VM_LOCKED_CLEAR_MASK;

		/* Because we won't unmap we don't need to touch locked_vm */
		goto out;
	}

	if (do_munmap(mm, old_addr, old_len, uf_unmap) < 0) {
		/* OOM: unable to split vma, just get accounts right */
		if (vm_flags & VM_ACCOUNT)
			vm_acct_memory(new_len >> PAGE_SHIFT);
		excess = 0;
	}

	if (vm_flags & VM_LOCKED) {
		mm->locked_vm += new_len >> PAGE_SHIFT;
		*locked = true;
	}
out:
	mm->hiwater_vm = hiwater_vm;

	/* Restore VM_ACCOUNT if one or two pieces of vma left */
	if (excess) {
		vma->vm_flags |= VM_ACCOUNT;
		if (split)
			vma->vm_next->vm_flags |= VM_ACCOUNT;
	}

	return new_addr;
}

static struct vm_area_struct *vma_to_resize(unsigned long addr,
	unsigned long old_len, unsigned long new_len, unsigned long flags,
	unsigned long *p)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma = find_vma(mm, addr);
	unsigned long pgoff;

	if (!vma || vma->vm_start > addr)
		return ERR_PTR(-EFAULT);

	/*
	 * !old_len is a special case where an attempt is made to 'duplicate'
	 * a mapping.  This makes no sense for private mappings as it will
	 * instead create a fresh/new mapping unrelated to the original.  This
	 * is contrary to the basic idea of mremap which creates new mappings
	 * based on the original.  There are no known use cases for this
	 * behavior.  As a result, fail such attempts.
	 */
	if (!old_len && !(vma->vm_flags & (VM_SHARED | VM_MAYSHARE))) {
		pr_warn_once("%s (%d): attempted to duplicate a private mapping with mremap.  This is not supported.\n", current->comm, current->pid);
		return ERR_PTR(-EINVAL);
	}

	if (flags & MREMAP_DONTUNMAP && (!vma_is_anonymous(vma) ||
			vma->vm_flags & VM_SHARED))
		return ERR_PTR(-EINVAL);

	if (is_vm_hugetlb_page(vma))
		return ERR_PTR(-EINVAL);

	/* We can't remap across vm area boundaries */
	if (old_len > vma->vm_end - addr)
		return ERR_PTR(-EFAULT);

	if (new_len == old_len)
		return vma;

	/* Need to be careful about a growing mapping */
	pgoff = (addr - vma->vm_start) >> PAGE_SHIFT;
	pgoff += vma->vm_pgoff;
	if (pgoff + (new_len >> PAGE_SHIFT) < pgoff)
		return ERR_PTR(-EINVAL);

	if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP))
		return ERR_PTR(-EFAULT);

	if (vma->vm_flags & VM_LOCKED) {
		unsigned long locked, lock_limit;
		locked = mm->locked_vm << PAGE_SHIFT;
		lock_limit = rlimit(RLIMIT_MEMLOCK);
		locked += new_len - old_len;
		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
			return ERR_PTR(-EAGAIN);
	}

	if (!may_expand_vm(mm, vma->vm_flags,
				(new_len - old_len) >> PAGE_SHIFT))
		return ERR_PTR(-ENOMEM);

	if (vma->vm_flags & VM_ACCOUNT) {
		unsigned long charged = (new_len - old_len) >> PAGE_SHIFT;
		if (security_vm_enough_memory_mm(mm, charged))
			return ERR_PTR(-ENOMEM);
		*p = charged;
	}

	return vma;
}

static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
		unsigned long new_addr, unsigned long new_len, bool *locked,
		unsigned long flags, struct vm_userfaultfd_ctx *uf,
		struct list_head *uf_unmap_early,
		struct list_head *uf_unmap)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	unsigned long ret = -EINVAL;
	unsigned long charged = 0;
	unsigned long map_flags = 0;

	if (offset_in_page(new_addr))
		goto out;

	if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len)
		goto out;

	/* Ensure the old/new locations do not overlap */
	if (addr + old_len > new_addr && new_addr + new_len > addr)
		goto out;

	/*
	 * move_vma() need us to stay 4 maps below the threshold, otherwise
	 * it will bail out at the very beginning.
	 * That is a problem if we have already unmaped the regions here
	 * (new_addr, and old_addr), because userspace will not know the
	 * state of the vma's after it gets -ENOMEM.
	 * So, to avoid such scenario we can pre-compute if the whole
	 * operation has high chances to success map-wise.
	 * Worst-scenario case is when both vma's (new_addr and old_addr) get
	 * split in 3 before unmaping it.
	 * That means 2 more maps (1 for each) to the ones we already hold.
	 * Check whether current map count plus 2 still leads us to 4 maps below
	 * the threshold, otherwise return -ENOMEM here to be more safe.
	 */
	if ((mm->map_count + 2) >= sysctl_max_map_count - 3)
		return -ENOMEM;

	if (flags & MREMAP_FIXED) {
		ret = do_munmap(mm, new_addr, new_len, uf_unmap_early);
		if (ret)
			goto out;
	}

	if (old_len >= new_len) {
		ret = do_munmap(mm, addr+new_len, old_len - new_len, uf_unmap);
		if (ret && old_len != new_len)
			goto out;
		old_len = new_len;
	}

	vma = vma_to_resize(addr, old_len, new_len, flags, &charged);
	if (IS_ERR(vma)) {
		ret = PTR_ERR(vma);
		goto out;
	}

	/* MREMAP_DONTUNMAP expands by old_len since old_len == new_len */
	if (flags & MREMAP_DONTUNMAP &&
		!may_expand_vm(mm, vma->vm_flags, old_len >> PAGE_SHIFT)) {
		ret = -ENOMEM;
		goto out;
	}

	if (flags & MREMAP_FIXED)
		map_flags |= MAP_FIXED;

	if (vma->vm_flags & VM_MAYSHARE)
		map_flags |= MAP_SHARED;

	ret = get_unmapped_area(vma->vm_file, new_addr, new_len, vma->vm_pgoff +
				((addr - vma->vm_start) >> PAGE_SHIFT),
				map_flags);
	if (IS_ERR_VALUE(ret))
		goto out1;

	/* We got a new mapping */
	if (!(flags & MREMAP_FIXED))
		new_addr = ret;

	ret = move_vma(vma, addr, old_len, new_len, new_addr, locked, flags, uf,
		       uf_unmap);

	if (!(offset_in_page(ret)))
		goto out;

out1:
	vm_unacct_memory(charged);

out:
	return ret;
}

static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
{
	unsigned long end = vma->vm_end + delta;
	if (end < vma->vm_end) /* overflow */
		return 0;
	if (vma->vm_next && vma->vm_next->vm_start < end) /* intersection */
		return 0;
	if (get_unmapped_area(NULL, vma->vm_start, end - vma->vm_start,
			      0, MAP_FIXED) & ~PAGE_MASK)
		return 0;
	return 1;
}

/*
 * Expand (or shrink) an existing mapping, potentially moving it at the
 * same time (controlled by the MREMAP_MAYMOVE flag and available VM space)
 *
 * MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise
 * This option implies MREMAP_MAYMOVE.
 */
SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
		unsigned long, new_len, unsigned long, flags,
		unsigned long, new_addr)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	unsigned long ret = -EINVAL;
	unsigned long charged = 0;
	bool locked = false;
	bool downgraded = false;
	struct vm_userfaultfd_ctx uf = NULL_VM_UFFD_CTX;
	LIST_HEAD(uf_unmap_early);
	LIST_HEAD(uf_unmap);

	/*
	 * There is a deliberate asymmetry here: we strip the pointer tag
	 * from the old address but leave the new address alone. This is
	 * for consistency with mmap(), where we prevent the creation of
	 * aliasing mappings in userspace by leaving the tag bits of the
	 * mapping address intact. A non-zero tag will cause the subsequent
	 * range checks to reject the address as invalid.
	 *
	 * See Documentation/arm64/tagged-address-abi.rst for more information.
	 */
	addr = untagged_addr(addr);

	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP))
		return ret;

	if (flags & MREMAP_FIXED && !(flags & MREMAP_MAYMOVE))
		return ret;

	/*
	 * MREMAP_DONTUNMAP is always a move and it does not allow resizing
	 * in the process.
	 */
	if (flags & MREMAP_DONTUNMAP &&
			(!(flags & MREMAP_MAYMOVE) || old_len != new_len))
		return ret;


	if (offset_in_page(addr))
		return ret;

	old_len = PAGE_ALIGN(old_len);
	new_len = PAGE_ALIGN(new_len);

	/*
	 * We allow a zero old-len as a special case
	 * for DOS-emu "duplicate shm area" thing. But
	 * a zero new-len is nonsensical.
	 */
	if (!new_len)
		return ret;

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

	if (flags & (MREMAP_FIXED | MREMAP_DONTUNMAP)) {
		ret = mremap_to(addr, old_len, new_addr, new_len,
				&locked, flags, &uf, &uf_unmap_early,
				&uf_unmap);
		goto out;
	}

	/*
	 * Always allow a shrinking remap: that just unmaps
	 * the unnecessary pages..
	 * __do_munmap does all the needed commit accounting, and
	 * downgrades mmap_lock to read if so directed.
	 */
	if (old_len >= new_len) {
		int retval;

		retval = __do_munmap(mm, addr+new_len, old_len - new_len,
				  &uf_unmap, true);
		if (retval < 0 && old_len != new_len) {
			ret = retval;
			goto out;
		/* Returning 1 indicates mmap_lock is downgraded to read. */
		} else if (retval == 1)
			downgraded = true;
		ret = addr;
		goto out;
	}

	/*
	 * Ok, we need to grow..
	 */
	vma = vma_to_resize(addr, old_len, new_len, flags, &charged);
	if (IS_ERR(vma)) {
		ret = PTR_ERR(vma);
		goto out;
	}

	/* old_len exactly to the end of the area..
	 */
	if (old_len == vma->vm_end - addr) {
		/* can we just expand the current mapping? */
		if (vma_expandable(vma, new_len - old_len)) {
			int pages = (new_len - old_len) >> PAGE_SHIFT;

			if (vma_adjust(vma, vma->vm_start, addr + new_len,
				       vma->vm_pgoff, NULL)) {
				ret = -ENOMEM;
				goto out;
			}

			vm_stat_account(mm, vma->vm_flags, pages);
			if (vma->vm_flags & VM_LOCKED) {
				mm->locked_vm += pages;
				locked = true;
				new_addr = addr;
			}
			ret = addr;
			goto out;
		}
	}

	/*
	 * We weren't able to just expand or shrink the area,
	 * we need to create a new one and move it..
	 */
	ret = -ENOMEM;
	if (flags & MREMAP_MAYMOVE) {
		unsigned long map_flags = 0;
		if (vma->vm_flags & VM_MAYSHARE)
			map_flags |= MAP_SHARED;

		new_addr = get_unmapped_area(vma->vm_file, 0, new_len,
					vma->vm_pgoff +
					((addr - vma->vm_start) >> PAGE_SHIFT),
					map_flags);
		if (IS_ERR_VALUE(new_addr)) {
			ret = new_addr;
			goto out;
		}

		ret = move_vma(vma, addr, old_len, new_len, new_addr,
			       &locked, flags, &uf, &uf_unmap);
	}
out:
	if (offset_in_page(ret)) {
		vm_unacct_memory(charged);
		locked = false;
	}
	if (downgraded)
		mmap_read_unlock(current->mm);
	else
		mmap_write_unlock(current->mm);
	if (locked && new_len > old_len)
		mm_populate(new_addr + old_len, new_len - old_len);
	userfaultfd_unmap_complete(mm, &uf_unmap_early);
	mremap_userfaultfd_complete(&uf, addr, ret, old_len);
	userfaultfd_unmap_complete(mm, &uf_unmap);
	return ret;
}