summaryrefslogtreecommitdiffstats
path: root/mm/madvise.c
blob: 1b68520ea3f4d40f1c27e91515d2000f222d8990 (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
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
// SPDX-License-Identifier: GPL-2.0
/*
 *	linux/mm/madvise.c
 *
 * Copyright (C) 1999  Linus Torvalds
 * Copyright (C) 2002  Christoph Hellwig
 */

#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/mempolicy.h>
#include <linux/page-isolation.h>
#include <linux/page_idle.h>
#include <linux/userfaultfd_k.h>
#include <linux/hugetlb.h>
#include <linux/falloc.h>
#include <linux/fadvise.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/uio.h>
#include <linux/ksm.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/pagewalk.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/shmem_fs.h>
#include <linux/mmu_notifier.h>

#include <asm/tlb.h>

#include "internal.h"

struct madvise_walk_private {
	struct mmu_gather *tlb;
	bool pageout;
};

/*
 * Any behaviour which results in changes to the vma->vm_flags needs to
 * take mmap_lock for writing. Others, which simply traverse vmas, need
 * to only take it for reading.
 */
static int madvise_need_mmap_write(int behavior)
{
	switch (behavior) {
	case MADV_REMOVE:
	case MADV_WILLNEED:
	case MADV_DONTNEED:
	case MADV_COLD:
	case MADV_PAGEOUT:
	case MADV_FREE:
		return 0;
	default:
		/* be safe, default to 1. list exceptions explicitly */
		return 1;
	}
}

/*
 * We can potentially split a vm area into separate
 * areas, each area with its own behavior.
 */
static long madvise_behavior(struct vm_area_struct *vma,
		     struct vm_area_struct **prev,
		     unsigned long start, unsigned long end, int behavior)
{
	struct mm_struct *mm = vma->vm_mm;
	int error = 0;
	pgoff_t pgoff;
	unsigned long new_flags = vma->vm_flags;

	switch (behavior) {
	case MADV_NORMAL:
		new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ;
		break;
	case MADV_SEQUENTIAL:
		new_flags = (new_flags & ~VM_RAND_READ) | VM_SEQ_READ;
		break;
	case MADV_RANDOM:
		new_flags = (new_flags & ~VM_SEQ_READ) | VM_RAND_READ;
		break;
	case MADV_DONTFORK:
		new_flags |= VM_DONTCOPY;
		break;
	case MADV_DOFORK:
		if (vma->vm_flags & VM_IO) {
			error = -EINVAL;
			goto out;
		}
		new_flags &= ~VM_DONTCOPY;
		break;
	case MADV_WIPEONFORK:
		/* MADV_WIPEONFORK is only supported on anonymous memory. */
		if (vma->vm_file || vma->vm_flags & VM_SHARED) {
			error = -EINVAL;
			goto out;
		}
		new_flags |= VM_WIPEONFORK;
		break;
	case MADV_KEEPONFORK:
		new_flags &= ~VM_WIPEONFORK;
		break;
	case MADV_DONTDUMP:
		new_flags |= VM_DONTDUMP;
		break;
	case MADV_DODUMP:
		if (!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) {
			error = -EINVAL;
			goto out;
		}
		new_flags &= ~VM_DONTDUMP;
		break;
	case MADV_MERGEABLE:
	case MADV_UNMERGEABLE:
		error = ksm_madvise(vma, start, end, behavior, &new_flags);
		if (error)
			goto out_convert_errno;
		break;
	case MADV_HUGEPAGE:
	case MADV_NOHUGEPAGE:
		error = hugepage_madvise(vma, &new_flags, behavior);
		if (error)
			goto out_convert_errno;
		break;
	}

	if (new_flags == vma->vm_flags) {
		*prev = vma;
		goto out;
	}

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

	*prev = vma;

	if (start != vma->vm_start) {
		if (unlikely(mm->map_count >= sysctl_max_map_count)) {
			error = -ENOMEM;
			goto out;
		}
		error = __split_vma(mm, vma, start, 1);
		if (error)
			goto out_convert_errno;
	}

	if (end != vma->vm_end) {
		if (unlikely(mm->map_count >= sysctl_max_map_count)) {
			error = -ENOMEM;
			goto out;
		}
		error = __split_vma(mm, vma, end, 0);
		if (error)
			goto out_convert_errno;
	}

success:
	/*
	 * vm_flags is protected by the mmap_lock held in write mode.
	 */
	vma->vm_flags = new_flags;

out_convert_errno:
	/*
	 * madvise() returns EAGAIN if kernel resources, such as
	 * slab, are temporarily unavailable.
	 */
	if (error == -ENOMEM)
		error = -EAGAIN;
out:
	return error;
}

#ifdef CONFIG_SWAP
static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
	unsigned long end, struct mm_walk *walk)
{
	pte_t *orig_pte;
	struct vm_area_struct *vma = walk->private;
	unsigned long index;

	if (pmd_none_or_trans_huge_or_clear_bad(pmd))
		return 0;

	for (index = start; index != end; index += PAGE_SIZE) {
		pte_t pte;
		swp_entry_t entry;
		struct page *page;
		spinlock_t *ptl;

		orig_pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl);
		pte = *(orig_pte + ((index - start) / PAGE_SIZE));
		pte_unmap_unlock(orig_pte, ptl);

		if (pte_present(pte) || pte_none(pte))
			continue;
		entry = pte_to_swp_entry(pte);
		if (unlikely(non_swap_entry(entry)))
			continue;

		page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
							vma, index, false);
		if (page)
			put_page(page);
	}

	return 0;
}

static const struct mm_walk_ops swapin_walk_ops = {
	.pmd_entry		= swapin_walk_pmd_entry,
};

static void force_shm_swapin_readahead(struct vm_area_struct *vma,
		unsigned long start, unsigned long end,
		struct address_space *mapping)
{
	XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start));
	pgoff_t end_index = linear_page_index(vma, end + PAGE_SIZE - 1);
	struct page *page;

	rcu_read_lock();
	xas_for_each(&xas, page, end_index) {
		swp_entry_t swap;

		if (!xa_is_value(page))
			continue;
		xas_pause(&xas);
		rcu_read_unlock();

		swap = radix_to_swp_entry(page);
		page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE,
							NULL, 0, false);
		if (page)
			put_page(page);

		rcu_read_lock();
	}
	rcu_read_unlock();

	lru_add_drain();	/* Push any new pages onto the LRU now */
}
#endif		/* CONFIG_SWAP */

/*
 * Schedule all required I/O operations.  Do not wait for completion.
 */
static long madvise_willneed(struct vm_area_struct *vma,
			     struct vm_area_struct **prev,
			     unsigned long start, unsigned long end)
{
	struct mm_struct *mm = vma->vm_mm;
	struct file *file = vma->vm_file;
	loff_t offset;

	*prev = vma;
#ifdef CONFIG_SWAP
	if (!file) {
		walk_page_range(vma->vm_mm, start, end, &swapin_walk_ops, vma);
		lru_add_drain(); /* Push any new pages onto the LRU now */
		return 0;
	}

	if (shmem_mapping(file->f_mapping)) {
		force_shm_swapin_readahead(vma, start, end,
					file->f_mapping);
		return 0;
	}
#else
	if (!file)
		return -EBADF;
#endif

	if (IS_DAX(file_inode(file))) {
		/* no bad return value, but ignore advice */
		return 0;
	}

	/*
	 * Filesystem's fadvise may need to take various locks.  We need to
	 * explicitly grab a reference because the vma (and hence the
	 * vma's reference to the file) can go away as soon as we drop
	 * mmap_lock.
	 */
	*prev = NULL;	/* tell sys_madvise we drop mmap_lock */
	get_file(file);
	offset = (loff_t)(start - vma->vm_start)
			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
	mmap_read_unlock(mm);
	vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED);
	fput(file);
	mmap_read_lock(mm);
	return 0;
}

static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
				unsigned long addr, unsigned long end,
				struct mm_walk *walk)
{
	struct madvise_walk_private *private = walk->private;
	struct mmu_gather *tlb = private->tlb;
	bool pageout = private->pageout;
	struct mm_struct *mm = tlb->mm;
	struct vm_area_struct *vma = walk->vma;
	pte_t *orig_pte, *pte, ptent;
	spinlock_t *ptl;
	struct page *page = NULL;
	LIST_HEAD(page_list);

	if (fatal_signal_pending(current))
		return -EINTR;

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	if (pmd_trans_huge(*pmd)) {
		pmd_t orig_pmd;
		unsigned long next = pmd_addr_end(addr, end);

		tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
		ptl = pmd_trans_huge_lock(pmd, vma);
		if (!ptl)
			return 0;

		orig_pmd = *pmd;
		if (is_huge_zero_pmd(orig_pmd))
			goto huge_unlock;

		if (unlikely(!pmd_present(orig_pmd))) {
			VM_BUG_ON(thp_migration_supported() &&
					!is_pmd_migration_entry(orig_pmd));
			goto huge_unlock;
		}

		page = pmd_page(orig_pmd);

		/* Do not interfere with other mappings of this page */
		if (page_mapcount(page) != 1)
			goto huge_unlock;

		if (next - addr != HPAGE_PMD_SIZE) {
			int err;

			get_page(page);
			spin_unlock(ptl);
			lock_page(page);
			err = split_huge_page(page);
			unlock_page(page);
			put_page(page);
			if (!err)
				goto regular_page;
			return 0;
		}

		if (pmd_young(orig_pmd)) {
			pmdp_invalidate(vma, addr, pmd);
			orig_pmd = pmd_mkold(orig_pmd);

			set_pmd_at(mm, addr, pmd, orig_pmd);
			tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
		}

		ClearPageReferenced(page);
		test_and_clear_page_young(page);
		if (pageout) {
			if (!isolate_lru_page(page)) {
				if (PageUnevictable(page))
					putback_lru_page(page);
				else
					list_add(&page->lru, &page_list);
			}
		} else
			deactivate_page(page);
huge_unlock:
		spin_unlock(ptl);
		if (pageout)
			reclaim_pages(&page_list);
		return 0;
	}

regular_page:
	if (pmd_trans_unstable(pmd))
		return 0;
#endif
	tlb_change_page_size(tlb, PAGE_SIZE);
	orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	flush_tlb_batched_pending(mm);
	arch_enter_lazy_mmu_mode();
	for (; addr < end; pte++, addr += PAGE_SIZE) {
		ptent = *pte;

		if (pte_none(ptent))
			continue;

		if (!pte_present(ptent))
			continue;

		page = vm_normal_page(vma, addr, ptent);
		if (!page)
			continue;

		/*
		 * Creating a THP page is expensive so split it only if we
		 * are sure it's worth. Split it if we are only owner.
		 */
		if (PageTransCompound(page)) {
			if (page_mapcount(page) != 1)
				break;
			get_page(page);
			if (!trylock_page(page)) {
				put_page(page);
				break;
			}
			pte_unmap_unlock(orig_pte, ptl);
			if (split_huge_page(page)) {
				unlock_page(page);
				put_page(page);
				pte_offset_map_lock(mm, pmd, addr, &ptl);
				break;
			}
			unlock_page(page);
			put_page(page);
			pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
			pte--;
			addr -= PAGE_SIZE;
			continue;
		}

		/* Do not interfere with other mappings of this page */
		if (page_mapcount(page) != 1)
			continue;

		VM_BUG_ON_PAGE(PageTransCompound(page), page);

		if (pte_young(ptent)) {
			ptent = ptep_get_and_clear_full(mm, addr, pte,
							tlb->fullmm);
			ptent = pte_mkold(ptent);
			set_pte_at(mm, addr, pte, ptent);
			tlb_remove_tlb_entry(tlb, pte, addr);
		}

		/*
		 * We are deactivating a page for accelerating reclaiming.
		 * VM couldn't reclaim the page unless we clear PG_young.
		 * As a side effect, it makes confuse idle-page tracking
		 * because they will miss recent referenced history.
		 */
		ClearPageReferenced(page);
		test_and_clear_page_young(page);
		if (pageout) {
			if (!isolate_lru_page(page)) {
				if (PageUnevictable(page))
					putback_lru_page(page);
				else
					list_add(&page->lru, &page_list);
			}
		} else
			deactivate_page(page);
	}

	arch_leave_lazy_mmu_mode();
	pte_unmap_unlock(orig_pte, ptl);
	if (pageout)
		reclaim_pages(&page_list);
	cond_resched();

	return 0;
}

static const struct mm_walk_ops cold_walk_ops = {
	.pmd_entry = madvise_cold_or_pageout_pte_range,
};

static void madvise_cold_page_range(struct mmu_gather *tlb,
			     struct vm_area_struct *vma,
			     unsigned long addr, unsigned long end)
{
	struct madvise_walk_private walk_private = {
		.pageout = false,
		.tlb = tlb,
	};

	tlb_start_vma(tlb, vma);
	walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private);
	tlb_end_vma(tlb, vma);
}

static long madvise_cold(struct vm_area_struct *vma,
			struct vm_area_struct **prev,
			unsigned long start_addr, unsigned long end_addr)
{
	struct mm_struct *mm = vma->vm_mm;
	struct mmu_gather tlb;

	*prev = vma;
	if (!can_madv_lru_vma(vma))
		return -EINVAL;

	lru_add_drain();
	tlb_gather_mmu(&tlb, mm, start_addr, end_addr);
	madvise_cold_page_range(&tlb, vma, start_addr, end_addr);
	tlb_finish_mmu(&tlb);

	return 0;
}

static void madvise_pageout_page_range(struct mmu_gather *tlb,
			     struct vm_area_struct *vma,
			     unsigned long addr, unsigned long end)
{
	struct madvise_walk_private walk_private = {
		.pageout = true,
		.tlb = tlb,
	};

	tlb_start_vma(tlb, vma);
	walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private);
	tlb_end_vma(tlb, vma);
}

static inline bool can_do_pageout(struct vm_area_struct *vma)
{
	if (vma_is_anonymous(vma))
		return true;
	if (!vma->vm_file)
		return false;
	/*
	 * paging out pagecache only for non-anonymous mappings that correspond
	 * to the files the calling process could (if tried) open for writing;
	 * otherwise we'd be including shared non-exclusive mappings, which
	 * opens a side channel.
	 */
	return inode_owner_or_capable(file_inode(vma->vm_file)) ||
		inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0;
}

static long madvise_pageout(struct vm_area_struct *vma,
			struct vm_area_struct **prev,
			unsigned long start_addr, unsigned long end_addr)
{
	struct mm_struct *mm = vma->vm_mm;
	struct mmu_gather tlb;

	*prev = vma;
	if (!can_madv_lru_vma(vma))
		return -EINVAL;

	if (!can_do_pageout(vma))
		return 0;

	lru_add_drain();
	tlb_gather_mmu(&tlb, mm, start_addr, end_addr);
	madvise_pageout_page_range(&tlb, vma, start_addr, end_addr);
	tlb_finish_mmu(&tlb);

	return 0;
}

static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
				unsigned long end, struct mm_walk *walk)

{
	struct mmu_gather *tlb = walk->private;
	struct mm_struct *mm = tlb->mm;
	struct vm_area_struct *vma = walk->vma;
	spinlock_t *ptl;
	pte_t *orig_pte, *pte, ptent;
	struct page *page;
	int nr_swap = 0;
	unsigned long next;

	next = pmd_addr_end(addr, end);
	if (pmd_trans_huge(*pmd))
		if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next))
			goto next;

	if (pmd_trans_unstable(pmd))
		return 0;

	tlb_change_page_size(tlb, PAGE_SIZE);
	orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
	flush_tlb_batched_pending(mm);
	arch_enter_lazy_mmu_mode();
	for (; addr != end; pte++, addr += PAGE_SIZE) {
		ptent = *pte;

		if (pte_none(ptent))
			continue;
		/*
		 * If the pte has swp_entry, just clear page table to
		 * prevent swap-in which is more expensive rather than
		 * (page allocation + zeroing).
		 */
		if (!pte_present(ptent)) {
			swp_entry_t entry;

			entry = pte_to_swp_entry(ptent);
			if (non_swap_entry(entry))
				continue;
			nr_swap--;
			free_swap_and_cache(entry);
			pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
			continue;
		}

		page = vm_normal_page(vma, addr, ptent);
		if (!page)
			continue;

		/*
		 * If pmd isn't transhuge but the page is THP and
		 * is owned by only this process, split it and
		 * deactivate all pages.
		 */
		if (PageTransCompound(page)) {
			if (page_mapcount(page) != 1)
				goto out;
			get_page(page);
			if (!trylock_page(page)) {
				put_page(page);
				goto out;
			}
			pte_unmap_unlock(orig_pte, ptl);
			if (split_huge_page(page)) {
				unlock_page(page);
				put_page(page);
				pte_offset_map_lock(mm, pmd, addr, &ptl);
				goto out;
			}
			unlock_page(page);
			put_page(page);
			pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
			pte--;
			addr -= PAGE_SIZE;
			continue;
		}

		VM_BUG_ON_PAGE(PageTransCompound(page), page);

		if (PageSwapCache(page) || PageDirty(page)) {
			if (!trylock_page(page))
				continue;
			/*
			 * If page is shared with others, we couldn't clear
			 * PG_dirty of the page.
			 */
			if (page_mapcount(page) != 1) {
				unlock_page(page);
				continue;
			}

			if (PageSwapCache(page) && !try_to_free_swap(page)) {
				unlock_page(page);
				continue;
			}

			ClearPageDirty(page);
			unlock_page(page);
		}

		if (pte_young(ptent) || pte_dirty(ptent)) {
			/*
			 * Some of architecture(ex, PPC) don't update TLB
			 * with set_pte_at and tlb_remove_tlb_entry so for
			 * the portability, remap the pte with old|clean
			 * after pte clearing.
			 */
			ptent = ptep_get_and_clear_full(mm, addr, pte,
							tlb->fullmm);

			ptent = pte_mkold(ptent);
			ptent = pte_mkclean(ptent);
			set_pte_at(mm, addr, pte, ptent);
			tlb_remove_tlb_entry(tlb, pte, addr);
		}
		mark_page_lazyfree(page);
	}
out:
	if (nr_swap) {
		if (current->mm == mm)
			sync_mm_rss(mm);

		add_mm_counter(mm, MM_SWAPENTS, nr_swap);
	}
	arch_leave_lazy_mmu_mode();
	pte_unmap_unlock(orig_pte, ptl);
	cond_resched();
next:
	return 0;
}

static const struct mm_walk_ops madvise_free_walk_ops = {
	.pmd_entry		= madvise_free_pte_range,
};

static int madvise_free_single_vma(struct vm_area_struct *vma,
			unsigned long start_addr, unsigned long end_addr)
{
	struct mm_struct *mm = vma->vm_mm;
	struct mmu_notifier_range range;
	struct mmu_gather tlb;

	/* MADV_FREE works for only anon vma at the moment */
	if (!vma_is_anonymous(vma))
		return -EINVAL;

	range.start = max(vma->vm_start, start_addr);
	if (range.start >= vma->vm_end)
		return -EINVAL;
	range.end = min(vma->vm_end, end_addr);
	if (range.end <= vma->vm_start)
		return -EINVAL;
	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm,
				range.start, range.end);

	lru_add_drain();
	tlb_gather_mmu(&tlb, mm, range.start, range.end);
	update_hiwater_rss(mm);

	mmu_notifier_invalidate_range_start(&range);
	tlb_start_vma(&tlb, vma);
	walk_page_range(vma->vm_mm, range.start, range.end,
			&madvise_free_walk_ops, &tlb);
	tlb_end_vma(&tlb, vma);
	mmu_notifier_invalidate_range_end(&range);
	tlb_finish_mmu(&tlb);

	return 0;
}

/*
 * Application no longer needs these pages.  If the pages are dirty,
 * it's OK to just throw them away.  The app will be more careful about
 * data it wants to keep.  Be sure to free swap resources too.  The
 * zap_page_range call sets things up for shrink_active_list to actually free
 * these pages later if no one else has touched them in the meantime,
 * although we could add these pages to a global reuse list for
 * shrink_active_list to pick up before reclaiming other pages.
 *
 * NB: This interface discards data rather than pushes it out to swap,
 * as some implementations do.  This has performance implications for
 * applications like large transactional databases which want to discard
 * pages in anonymous maps after committing to backing store the data
 * that was kept in them.  There is no reason to write this data out to
 * the swap area if the application is discarding it.
 *
 * An interface that causes the system to free clean pages and flush
 * dirty pages is already available as msync(MS_INVALIDATE).
 */
static long madvise_dontneed_single_vma(struct vm_area_struct *vma,
					unsigned long start, unsigned long end)
{
	zap_page_range(vma, start, end - start);
	return 0;
}

static long madvise_dontneed_free(struct vm_area_struct *vma,
				  struct vm_area_struct **prev,
				  unsigned long start, unsigned long end,
				  int behavior)
{
	struct mm_struct *mm = vma->vm_mm;

	*prev = vma;
	if (!can_madv_lru_vma(vma))
		return -EINVAL;

	if (!userfaultfd_remove(vma, start, end)) {
		*prev = NULL; /* mmap_lock has been dropped, prev is stale */

		mmap_read_lock(mm);
		vma = find_vma(mm, start);
		if (!vma)
			return -ENOMEM;
		if (start < vma->vm_start) {
			/*
			 * This "vma" under revalidation is the one
			 * with the lowest vma->vm_start where start
			 * is also < vma->vm_end. If start <
			 * vma->vm_start it means an hole materialized
			 * in the user address space within the
			 * virtual range passed to MADV_DONTNEED
			 * or MADV_FREE.
			 */
			return -ENOMEM;
		}
		if (!can_madv_lru_vma(vma))
			return -EINVAL;
		if (end > vma->vm_end) {
			/*
			 * Don't fail if end > vma->vm_end. If the old
			 * vma was splitted while the mmap_lock was
			 * released the effect of the concurrent
			 * operation may not cause madvise() to
			 * have an undefined result. There may be an
			 * adjacent next vma that we'll walk
			 * next. userfaultfd_remove() will generate an
			 * UFFD_EVENT_REMOVE repetition on the
			 * end-vma->vm_end range, but the manager can
			 * handle a repetition fine.
			 */
			end = vma->vm_end;
		}
		VM_WARN_ON(start >= end);
	}

	if (behavior == MADV_DONTNEED)
		return madvise_dontneed_single_vma(vma, start, end);
	else if (behavior == MADV_FREE)
		return madvise_free_single_vma(vma, start, end);
	else
		return -EINVAL;
}

/*
 * Application wants to free up the pages and associated backing store.
 * This is effectively punching a hole into the middle of a file.
 */
static long madvise_remove(struct vm_area_struct *vma,
				struct vm_area_struct **prev,
				unsigned long start, unsigned long end)
{
	loff_t offset;
	int error;
	struct file *f;
	struct mm_struct *mm = vma->vm_mm;

	*prev = NULL;	/* tell sys_madvise we drop mmap_lock */

	if (vma->vm_flags & VM_LOCKED)
		return -EINVAL;

	f = vma->vm_file;

	if (!f || !f->f_mapping || !f->f_mapping->host) {
			return -EINVAL;
	}

	if ((vma->vm_flags & (VM_SHARED|VM_WRITE)) != (VM_SHARED|VM_WRITE))
		return -EACCES;

	offset = (loff_t)(start - vma->vm_start)
			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);

	/*
	 * Filesystem's fallocate may need to take i_mutex.  We need to
	 * explicitly grab a reference because the vma (and hence the
	 * vma's reference to the file) can go away as soon as we drop
	 * mmap_lock.
	 */
	get_file(f);
	if (userfaultfd_remove(vma, start, end)) {
		/* mmap_lock was not released by userfaultfd_remove() */
		mmap_read_unlock(mm);
	}
	error = vfs_fallocate(f,
				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
				offset, end - start);
	fput(f);
	mmap_read_lock(mm);
	return error;
}

#ifdef CONFIG_MEMORY_FAILURE
/*
 * Error injection support for memory error handling.
 */
static int madvise_inject_error(int behavior,
		unsigned long start, unsigned long end)
{
	unsigned long size;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;


	for (; start < end; start += size) {
		unsigned long pfn;
		struct page *page;
		int ret;

		ret = get_user_pages_fast(start, 1, 0, &page);
		if (ret != 1)
			return ret;
		pfn = page_to_pfn(page);

		/*
		 * When soft offlining hugepages, after migrating the page
		 * we dissolve it, therefore in the second loop "page" will
		 * no longer be a compound page.
		 */
		size = page_size(compound_head(page));

		if (behavior == MADV_SOFT_OFFLINE) {
			pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n",
				 pfn, start);
			ret = soft_offline_page(pfn, MF_COUNT_INCREASED);
		} else {
			pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n",
				 pfn, start);
			ret = memory_failure(pfn, MF_COUNT_INCREASED);
		}

		if (ret)
			return ret;
	}

	return 0;
}
#endif

static long
madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
		unsigned long start, unsigned long end, int behavior)
{
	switch (behavior) {
	case MADV_REMOVE:
		return madvise_remove(vma, prev, start, end);
	case MADV_WILLNEED:
		return madvise_willneed(vma, prev, start, end);
	case MADV_COLD:
		return madvise_cold(vma, prev, start, end);
	case MADV_PAGEOUT:
		return madvise_pageout(vma, prev, start, end);
	case MADV_FREE:
	case MADV_DONTNEED:
		return madvise_dontneed_free(vma, prev, start, end, behavior);
	default:
		return madvise_behavior(vma, prev, start, end, behavior);
	}
}

static bool
madvise_behavior_valid(int behavior)
{
	switch (behavior) {
	case MADV_DOFORK:
	case MADV_DONTFORK:
	case MADV_NORMAL:
	case MADV_SEQUENTIAL:
	case MADV_RANDOM:
	case MADV_REMOVE:
	case MADV_WILLNEED:
	case MADV_DONTNEED:
	case MADV_FREE:
	case MADV_COLD:
	case MADV_PAGEOUT:
#ifdef CONFIG_KSM
	case MADV_MERGEABLE:
	case MADV_UNMERGEABLE:
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	case MADV_HUGEPAGE:
	case MADV_NOHUGEPAGE:
#endif
	case MADV_DONTDUMP:
	case MADV_DODUMP:
	case MADV_WIPEONFORK:
	case MADV_KEEPONFORK:
#ifdef CONFIG_MEMORY_FAILURE
	case MADV_SOFT_OFFLINE:
	case MADV_HWPOISON:
#endif
		return true;

	default:
		return false;
	}
}

static bool
process_madvise_behavior_valid(int behavior)
{
	switch (behavior) {
	case MADV_COLD:
	case MADV_PAGEOUT:
		return true;
	default:
		return false;
	}
}

/*
 * The madvise(2) system call.
 *
 * Applications can use madvise() to advise the kernel how it should
 * handle paging I/O in this VM area.  The idea is to help the kernel
 * use appropriate read-ahead and caching techniques.  The information
 * provided is advisory only, and can be safely disregarded by the
 * kernel without affecting the correct operation of the application.
 *
 * behavior values:
 *  MADV_NORMAL - the default behavior is to read clusters.  This
 *		results in some read-ahead and read-behind.
 *  MADV_RANDOM - the system should read the minimum amount of data
 *		on any access, since it is unlikely that the appli-
 *		cation will need more than what it asks for.
 *  MADV_SEQUENTIAL - pages in the given range will probably be accessed
 *		once, so they can be aggressively read ahead, and
 *		can be freed soon after they are accessed.
 *  MADV_WILLNEED - the application is notifying the system to read
 *		some pages ahead.
 *  MADV_DONTNEED - the application is finished with the given range,
 *		so the kernel can free resources associated with it.
 *  MADV_FREE - the application marks pages in the given range as lazy free,
 *		where actual purges are postponed until memory pressure happens.
 *  MADV_REMOVE - the application wants to free up the given range of
 *		pages and associated backing store.
 *  MADV_DONTFORK - omit this area from child's address space when forking:
 *		typically, to avoid COWing pages pinned by get_user_pages().
 *  MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking.
 *  MADV_WIPEONFORK - present the child process with zero-filled memory in this
 *              range after a fork.
 *  MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK
 *  MADV_HWPOISON - trigger memory error handler as if the given memory range
 *		were corrupted by unrecoverable hardware memory failure.
 *  MADV_SOFT_OFFLINE - try to soft-offline the given range of memory.
 *  MADV_MERGEABLE - the application recommends that KSM try to merge pages in
 *		this area with pages of identical content from other such areas.
 *  MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others.
 *  MADV_HUGEPAGE - the application wants to back the given range by transparent
 *		huge pages in the future. Existing pages might be coalesced and
 *		new pages might be allocated as THP.
 *  MADV_NOHUGEPAGE - mark the given range as not worth being backed by
 *		transparent huge pages so the existing pages will not be
 *		coalesced into THP and new pages will not be allocated as THP.
 *  MADV_DONTDUMP - the application wants to prevent pages in the given range
 *		from being included in its core dump.
 *  MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.
 *  MADV_COLD - the application is not expected to use this memory soon,
 *		deactivate pages in this range so that they can be reclaimed
 *		easily if memory pressure hanppens.
 *  MADV_PAGEOUT - the application is not expected to use this memory soon,
 *		page out the pages in this range immediately.
 *
 * return values:
 *  zero    - success
 *  -EINVAL - start + len < 0, start is not page-aligned,
 *		"behavior" is not a valid value, or application
 *		is attempting to release locked or shared pages,
 *		or the specified address range includes file, Huge TLB,
 *		MAP_SHARED or VMPFNMAP range.
 *  -ENOMEM - addresses in the specified range are not currently
 *		mapped, or are outside the AS of the process.
 *  -EIO    - an I/O error occurred while paging in data.
 *  -EBADF  - map exists, but area maps something that isn't a file.
 *  -EAGAIN - a kernel resource was temporarily unavailable.
 */
int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior)
{
	unsigned long end, tmp;
	struct vm_area_struct *vma, *prev;
	int unmapped_error = 0;
	int error = -EINVAL;
	int write;
	size_t len;
	struct blk_plug plug;

	start = untagged_addr(start);

	if (!madvise_behavior_valid(behavior))
		return error;

	if (!PAGE_ALIGNED(start))
		return error;
	len = PAGE_ALIGN(len_in);

	/* Check to see whether len was rounded up from small -ve to zero */
	if (len_in && !len)
		return error;

	end = start + len;
	if (end < start)
		return error;

	error = 0;
	if (end == start)
		return error;

#ifdef CONFIG_MEMORY_FAILURE
	if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE)
		return madvise_inject_error(behavior, start, start + len_in);
#endif

	write = madvise_need_mmap_write(behavior);
	if (write) {
		if (mmap_write_lock_killable(mm))
			return -EINTR;
	} else {
		mmap_read_lock(mm);
	}

	/*
	 * If the interval [start,end) covers some unmapped address
	 * ranges, just ignore them, but return -ENOMEM at the end.
	 * - different from the way of handling in mlock etc.
	 */
	vma = find_vma_prev(mm, start, &prev);
	if (vma && start > vma->vm_start)
		prev = vma;

	blk_start_plug(&plug);
	for (;;) {
		/* Still start < end. */
		error = -ENOMEM;
		if (!vma)
			goto out;

		/* Here start < (end|vma->vm_end). */
		if (start < vma->vm_start) {
			unmapped_error = -ENOMEM;
			start = vma->vm_start;
			if (start >= end)
				goto out;
		}

		/* Here vma->vm_start <= start < (end|vma->vm_end) */
		tmp = vma->vm_end;
		if (end < tmp)
			tmp = end;

		/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
		error = madvise_vma(vma, &prev, start, tmp, behavior);
		if (error)
			goto out;
		start = tmp;
		if (prev && start < prev->vm_end)
			start = prev->vm_end;
		error = unmapped_error;
		if (start >= end)
			goto out;
		if (prev)
			vma = prev->vm_next;
		else	/* madvise_remove dropped mmap_lock */
			vma = find_vma(mm, start);
	}
out:
	blk_finish_plug(&plug);
	if (write)
		mmap_write_unlock(mm);
	else
		mmap_read_unlock(mm);

	return error;
}

SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
{
	return do_madvise(current->mm, start, len_in, behavior);
}

SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
		size_t, vlen, int, behavior, unsigned int, flags)
{
	ssize_t ret;
	struct iovec iovstack[UIO_FASTIOV], iovec;
	struct iovec *iov = iovstack;
	struct iov_iter iter;
	struct pid *pid;
	struct task_struct *task;
	struct mm_struct *mm;
	size_t total_len;
	unsigned int f_flags;

	if (flags != 0) {
		ret = -EINVAL;
		goto out;
	}

	ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
	if (ret < 0)
		goto out;

	pid = pidfd_get_pid(pidfd, &f_flags);
	if (IS_ERR(pid)) {
		ret = PTR_ERR(pid);
		goto free_iov;
	}

	task = get_pid_task(pid, PIDTYPE_PID);
	if (!task) {
		ret = -ESRCH;
		goto put_pid;
	}

	if (!process_madvise_behavior_valid(behavior)) {
		ret = -EINVAL;
		goto release_task;
	}

	mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS);
	if (IS_ERR_OR_NULL(mm)) {
		ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
		goto release_task;
	}

	total_len = iov_iter_count(&iter);

	while (iov_iter_count(&iter)) {
		iovec = iov_iter_iovec(&iter);
		ret = do_madvise(mm, (unsigned long)iovec.iov_base,
					iovec.iov_len, behavior);
		if (ret < 0)
			break;
		iov_iter_advance(&iter, iovec.iov_len);
	}

	if (ret == 0)
		ret = total_len - iov_iter_count(&iter);

	mmput(mm);
release_task:
	put_task_struct(task);
put_pid:
	put_pid(pid);
free_iov:
	kfree(iov);
out:
	return ret;
}