summaryrefslogtreecommitdiff
path: root/mm/internal.h
blob: cc2c5e07fad3ba75713b780d216e675c49713ce6 (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
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
/* SPDX-License-Identifier: GPL-2.0-or-later */
/* internal.h: mm/ internal definitions
 *
 * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 */
#ifndef __MM_INTERNAL_H
#define __MM_INTERNAL_H

#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/tracepoint-defs.h>

struct folio_batch;

/*
 * The set of flags that only affect watermark checking and reclaim
 * behaviour. This is used by the MM to obey the caller constraints
 * about IO, FS and watermark checking while ignoring placement
 * hints such as HIGHMEM usage.
 */
#define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
			__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\
			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
			__GFP_NOLOCKDEP)

/* The GFP flags allowed during early boot */
#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS))

/* Control allocation cpuset and node placement constraints */
#define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE)

/* Do not use these with a slab allocator */
#define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)

/*
 * Different from WARN_ON_ONCE(), no warning will be issued
 * when we specify __GFP_NOWARN.
 */
#define WARN_ON_ONCE_GFP(cond, gfp)	({				\
	static bool __section(".data.once") __warned;			\
	int __ret_warn_once = !!(cond);					\
									\
	if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \
		__warned = true;					\
		WARN_ON(1);						\
	}								\
	unlikely(__ret_warn_once);					\
})

void page_writeback_init(void);

/*
 * If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages,
 * its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit
 * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE).  Hugetlb currently
 * leaves nr_pages_mapped at 0, but avoid surprise if it participates later.
 */
#define ENTIRELY_MAPPED		0x800000
#define FOLIO_PAGES_MAPPED	(ENTIRELY_MAPPED - 1)

/*
 * Flags passed to __show_mem() and show_free_areas() to suppress output in
 * various contexts.
 */
#define SHOW_MEM_FILTER_NODES		(0x0001u)	/* disallowed nodes */

/*
 * How many individual pages have an elevated _mapcount.  Excludes
 * the folio's entire_mapcount.
 *
 * Don't use this function outside of debugging code.
 */
static inline int folio_nr_pages_mapped(const struct folio *folio)
{
	return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED;
}

/*
 * Retrieve the first entry of a folio based on a provided entry within the
 * folio. We cannot rely on folio->swap as there is no guarantee that it has
 * been initialized. Used for calling arch_swap_restore()
 */
static inline swp_entry_t folio_swap(swp_entry_t entry,
		const struct folio *folio)
{
	swp_entry_t swap = {
		.val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)),
	};

	return swap;
}

static inline void *folio_raw_mapping(const struct folio *folio)
{
	unsigned long mapping = (unsigned long)folio->mapping;

	return (void *)(mapping & ~PAGE_MAPPING_FLAGS);
}

#ifdef CONFIG_MMU

/* Flags for folio_pte_batch(). */
typedef int __bitwise fpb_t;

/* Compare PTEs after pte_mkclean(), ignoring the dirty bit. */
#define FPB_IGNORE_DIRTY		((__force fpb_t)BIT(0))

/* Compare PTEs after pte_clear_soft_dirty(), ignoring the soft-dirty bit. */
#define FPB_IGNORE_SOFT_DIRTY		((__force fpb_t)BIT(1))

static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
{
	if (flags & FPB_IGNORE_DIRTY)
		pte = pte_mkclean(pte);
	if (likely(flags & FPB_IGNORE_SOFT_DIRTY))
		pte = pte_clear_soft_dirty(pte);
	return pte_wrprotect(pte_mkold(pte));
}

/**
 * folio_pte_batch - detect a PTE batch for a large folio
 * @folio: The large folio to detect a PTE batch for.
 * @addr: The user virtual address the first page is mapped at.
 * @start_ptep: Page table pointer for the first entry.
 * @pte: Page table entry for the first page.
 * @max_nr: The maximum number of table entries to consider.
 * @flags: Flags to modify the PTE batch semantics.
 * @any_writable: Optional pointer to indicate whether any entry except the
 *		  first one is writable.
 * @any_young: Optional pointer to indicate whether any entry except the
 *		  first one is young.
 * @any_dirty: Optional pointer to indicate whether any entry except the
 *		  first one is dirty.
 *
 * Detect a PTE batch: consecutive (present) PTEs that map consecutive
 * pages of the same large folio.
 *
 * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN,
 * the accessed bit, writable bit, dirty bit (with FPB_IGNORE_DIRTY) and
 * soft-dirty bit (with FPB_IGNORE_SOFT_DIRTY).
 *
 * start_ptep must map any page of the folio. max_nr must be at least one and
 * must be limited by the caller so scanning cannot exceed a single page table.
 *
 * Return: the number of table entries in the batch.
 */
static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
		pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags,
		bool *any_writable, bool *any_young, bool *any_dirty)
{
	unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
	const pte_t *end_ptep = start_ptep + max_nr;
	pte_t expected_pte, *ptep;
	bool writable, young, dirty;
	int nr;

	if (any_writable)
		*any_writable = false;
	if (any_young)
		*any_young = false;
	if (any_dirty)
		*any_dirty = false;

	VM_WARN_ON_FOLIO(!pte_present(pte), folio);
	VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio);
	VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio);

	nr = pte_batch_hint(start_ptep, pte);
	expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags);
	ptep = start_ptep + nr;

	while (ptep < end_ptep) {
		pte = ptep_get(ptep);
		if (any_writable)
			writable = !!pte_write(pte);
		if (any_young)
			young = !!pte_young(pte);
		if (any_dirty)
			dirty = !!pte_dirty(pte);
		pte = __pte_batch_clear_ignored(pte, flags);

		if (!pte_same(pte, expected_pte))
			break;

		/*
		 * Stop immediately once we reached the end of the folio. In
		 * corner cases the next PFN might fall into a different
		 * folio.
		 */
		if (pte_pfn(pte) >= folio_end_pfn)
			break;

		if (any_writable)
			*any_writable |= writable;
		if (any_young)
			*any_young |= young;
		if (any_dirty)
			*any_dirty |= dirty;

		nr = pte_batch_hint(ptep, pte);
		expected_pte = pte_advance_pfn(expected_pte, nr);
		ptep += nr;
	}

	return min(ptep - start_ptep, max_nr);
}

/**
 * pte_next_swp_offset - Increment the swap entry offset field of a swap pte.
 * @pte: The initial pte state; is_swap_pte(pte) must be true and
 *	 non_swap_entry() must be false.
 *
 * Increments the swap offset, while maintaining all other fields, including
 * swap type, and any swp pte bits. The resulting pte is returned.
 */
static inline pte_t pte_next_swp_offset(pte_t pte)
{
	swp_entry_t entry = pte_to_swp_entry(pte);
	pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry),
						   (swp_offset(entry) + 1)));

	if (pte_swp_soft_dirty(pte))
		new = pte_swp_mksoft_dirty(new);
	if (pte_swp_exclusive(pte))
		new = pte_swp_mkexclusive(new);
	if (pte_swp_uffd_wp(pte))
		new = pte_swp_mkuffd_wp(new);

	return new;
}

/**
 * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries
 * @start_ptep: Page table pointer for the first entry.
 * @max_nr: The maximum number of table entries to consider.
 * @pte: Page table entry for the first entry.
 *
 * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs
 * containing swap entries all with consecutive offsets and targeting the same
 * swap type, all with matching swp pte bits.
 *
 * max_nr must be at least one and must be limited by the caller so scanning
 * cannot exceed a single page table.
 *
 * Return: the number of table entries in the batch.
 */
static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte)
{
	pte_t expected_pte = pte_next_swp_offset(pte);
	const pte_t *end_ptep = start_ptep + max_nr;
	pte_t *ptep = start_ptep + 1;

	VM_WARN_ON(max_nr < 1);
	VM_WARN_ON(!is_swap_pte(pte));
	VM_WARN_ON(non_swap_entry(pte_to_swp_entry(pte)));

	while (ptep < end_ptep) {
		pte = ptep_get(ptep);

		if (!pte_same(pte, expected_pte))
			break;

		expected_pte = pte_next_swp_offset(expected_pte);
		ptep++;
	}

	return ptep - start_ptep;
}
#endif /* CONFIG_MMU */

void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio,
						int nr_throttled);
static inline void acct_reclaim_writeback(struct folio *folio)
{
	pg_data_t *pgdat = folio_pgdat(folio);
	int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled);

	if (nr_throttled)
		__acct_reclaim_writeback(pgdat, folio, nr_throttled);
}

static inline void wake_throttle_isolated(pg_data_t *pgdat)
{
	wait_queue_head_t *wqh;

	wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED];
	if (waitqueue_active(wqh))
		wake_up(wqh);
}

vm_fault_t vmf_anon_prepare(struct vm_fault *vmf);
vm_fault_t do_swap_page(struct vm_fault *vmf);
void folio_rotate_reclaimable(struct folio *folio);
bool __folio_end_writeback(struct folio *folio);
void deactivate_file_folio(struct folio *folio);
void folio_activate(struct folio *folio);

void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
		   struct vm_area_struct *start_vma, unsigned long floor,
		   unsigned long ceiling, bool mm_wr_locked);
void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte);

struct zap_details;
void unmap_page_range(struct mmu_gather *tlb,
			     struct vm_area_struct *vma,
			     unsigned long addr, unsigned long end,
			     struct zap_details *details);

void page_cache_ra_order(struct readahead_control *, struct file_ra_state *,
		unsigned int order);
void force_page_cache_ra(struct readahead_control *, unsigned long nr);
static inline void force_page_cache_readahead(struct address_space *mapping,
		struct file *file, pgoff_t index, unsigned long nr_to_read)
{
	DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index);
	force_page_cache_ra(&ractl, nr_to_read);
}

unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start,
		pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices);
unsigned find_get_entries(struct address_space *mapping, pgoff_t *start,
		pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices);
void filemap_free_folio(struct address_space *mapping, struct folio *folio);
int truncate_inode_folio(struct address_space *mapping, struct folio *folio);
bool truncate_inode_partial_folio(struct folio *folio, loff_t start,
		loff_t end);
long mapping_evict_folio(struct address_space *mapping, struct folio *folio);
unsigned long mapping_try_invalidate(struct address_space *mapping,
		pgoff_t start, pgoff_t end, unsigned long *nr_failed);

/**
 * folio_evictable - Test whether a folio is evictable.
 * @folio: The folio to test.
 *
 * Test whether @folio is evictable -- i.e., should be placed on
 * active/inactive lists vs unevictable list.
 *
 * Reasons folio might not be evictable:
 * 1. folio's mapping marked unevictable
 * 2. One of the pages in the folio is part of an mlocked VMA
 */
static inline bool folio_evictable(struct folio *folio)
{
	bool ret;

	/* Prevent address_space of inode and swap cache from being freed */
	rcu_read_lock();
	ret = !mapping_unevictable(folio_mapping(folio)) &&
			!folio_test_mlocked(folio);
	rcu_read_unlock();
	return ret;
}

/*
 * Turn a non-refcounted page (->_refcount == 0) into refcounted with
 * a count of one.
 */
static inline void set_page_refcounted(struct page *page)
{
	VM_BUG_ON_PAGE(PageTail(page), page);
	VM_BUG_ON_PAGE(page_ref_count(page), page);
	set_page_count(page, 1);
}

/*
 * Return true if a folio needs ->release_folio() calling upon it.
 */
static inline bool folio_needs_release(struct folio *folio)
{
	struct address_space *mapping = folio_mapping(folio);

	return folio_has_private(folio) ||
		(mapping && mapping_release_always(mapping));
}

extern unsigned long highest_memmap_pfn;

/*
 * Maximum number of reclaim retries without progress before the OOM
 * killer is consider the only way forward.
 */
#define MAX_RECLAIM_RETRIES 16

/*
 * in mm/vmscan.c:
 */
bool isolate_lru_page(struct page *page);
bool folio_isolate_lru(struct folio *folio);
void putback_lru_page(struct page *page);
void folio_putback_lru(struct folio *folio);
extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason);

/*
 * in mm/rmap.c:
 */
pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);

/*
 * in mm/page_alloc.c
 */
#define K(x) ((x) << (PAGE_SHIFT-10))

extern char * const zone_names[MAX_NR_ZONES];

/* perform sanity checks on struct pages being allocated or freed */
DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled);

extern int min_free_kbytes;

void setup_per_zone_wmarks(void);
void calculate_min_free_kbytes(void);
int __meminit init_per_zone_wmark_min(void);
void page_alloc_sysctl_init(void);

/*
 * Structure for holding the mostly immutable allocation parameters passed
 * between functions involved in allocations, including the alloc_pages*
 * family of functions.
 *
 * nodemask, migratetype and highest_zoneidx are initialized only once in
 * __alloc_pages() and then never change.
 *
 * zonelist, preferred_zone and highest_zoneidx are set first in
 * __alloc_pages() for the fast path, and might be later changed
 * in __alloc_pages_slowpath(). All other functions pass the whole structure
 * by a const pointer.
 */
struct alloc_context {
	struct zonelist *zonelist;
	nodemask_t *nodemask;
	struct zoneref *preferred_zoneref;
	int migratetype;

	/*
	 * highest_zoneidx represents highest usable zone index of
	 * the allocation request. Due to the nature of the zone,
	 * memory on lower zone than the highest_zoneidx will be
	 * protected by lowmem_reserve[highest_zoneidx].
	 *
	 * highest_zoneidx is also used by reclaim/compaction to limit
	 * the target zone since higher zone than this index cannot be
	 * usable for this allocation request.
	 */
	enum zone_type highest_zoneidx;
	bool spread_dirty_pages;
};

/*
 * This function returns the order of a free page in the buddy system. In
 * general, page_zone(page)->lock must be held by the caller to prevent the
 * page from being allocated in parallel and returning garbage as the order.
 * If a caller does not hold page_zone(page)->lock, it must guarantee that the
 * page cannot be allocated or merged in parallel. Alternatively, it must
 * handle invalid values gracefully, and use buddy_order_unsafe() below.
 */
static inline unsigned int buddy_order(struct page *page)
{
	/* PageBuddy() must be checked by the caller */
	return page_private(page);
}

/*
 * Like buddy_order(), but for callers who cannot afford to hold the zone lock.
 * PageBuddy() should be checked first by the caller to minimize race window,
 * and invalid values must be handled gracefully.
 *
 * READ_ONCE is used so that if the caller assigns the result into a local
 * variable and e.g. tests it for valid range before using, the compiler cannot
 * decide to remove the variable and inline the page_private(page) multiple
 * times, potentially observing different values in the tests and the actual
 * use of the result.
 */
#define buddy_order_unsafe(page)	READ_ONCE(page_private(page))

/*
 * This function checks whether a page is free && is the buddy
 * we can coalesce a page and its buddy if
 * (a) the buddy is not in a hole (check before calling!) &&
 * (b) the buddy is in the buddy system &&
 * (c) a page and its buddy have the same order &&
 * (d) a page and its buddy are in the same zone.
 *
 * For recording whether a page is in the buddy system, we set PageBuddy.
 * Setting, clearing, and testing PageBuddy is serialized by zone->lock.
 *
 * For recording page's order, we use page_private(page).
 */
static inline bool page_is_buddy(struct page *page, struct page *buddy,
				 unsigned int order)
{
	if (!page_is_guard(buddy) && !PageBuddy(buddy))
		return false;

	if (buddy_order(buddy) != order)
		return false;

	/*
	 * zone check is done late to avoid uselessly calculating
	 * zone/node ids for pages that could never merge.
	 */
	if (page_zone_id(page) != page_zone_id(buddy))
		return false;

	VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);

	return true;
}

/*
 * Locate the struct page for both the matching buddy in our
 * pair (buddy1) and the combined O(n+1) page they form (page).
 *
 * 1) Any buddy B1 will have an order O twin B2 which satisfies
 * the following equation:
 *     B2 = B1 ^ (1 << O)
 * For example, if the starting buddy (buddy2) is #8 its order
 * 1 buddy is #10:
 *     B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10
 *
 * 2) Any buddy B will have an order O+1 parent P which
 * satisfies the following equation:
 *     P = B & ~(1 << O)
 *
 * Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER
 */
static inline unsigned long
__find_buddy_pfn(unsigned long page_pfn, unsigned int order)
{
	return page_pfn ^ (1 << order);
}

/*
 * Find the buddy of @page and validate it.
 * @page: The input page
 * @pfn: The pfn of the page, it saves a call to page_to_pfn() when the
 *       function is used in the performance-critical __free_one_page().
 * @order: The order of the page
 * @buddy_pfn: The output pointer to the buddy pfn, it also saves a call to
 *             page_to_pfn().
 *
 * The found buddy can be a non PageBuddy, out of @page's zone, or its order is
 * not the same as @page. The validation is necessary before use it.
 *
 * Return: the found buddy page or NULL if not found.
 */
static inline struct page *find_buddy_page_pfn(struct page *page,
			unsigned long pfn, unsigned int order, unsigned long *buddy_pfn)
{
	unsigned long __buddy_pfn = __find_buddy_pfn(pfn, order);
	struct page *buddy;

	buddy = page + (__buddy_pfn - pfn);
	if (buddy_pfn)
		*buddy_pfn = __buddy_pfn;

	if (page_is_buddy(page, buddy, order))
		return buddy;
	return NULL;
}

extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
				unsigned long end_pfn, struct zone *zone);

static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn,
				unsigned long end_pfn, struct zone *zone)
{
	if (zone->contiguous)
		return pfn_to_page(start_pfn);

	return __pageblock_pfn_to_page(start_pfn, end_pfn, zone);
}

void set_zone_contiguous(struct zone *zone);

static inline void clear_zone_contiguous(struct zone *zone)
{
	zone->contiguous = false;
}

extern int __isolate_free_page(struct page *page, unsigned int order);
extern void __putback_isolated_page(struct page *page, unsigned int order,
				    int mt);
extern void memblock_free_pages(struct page *page, unsigned long pfn,
					unsigned int order);
extern void __free_pages_core(struct page *page, unsigned int order);

/*
 * This will have no effect, other than possibly generating a warning, if the
 * caller passes in a non-large folio.
 */
static inline void folio_set_order(struct folio *folio, unsigned int order)
{
	if (WARN_ON_ONCE(!order || !folio_test_large(folio)))
		return;

	folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order;
#ifdef CONFIG_64BIT
	folio->_folio_nr_pages = 1U << order;
#endif
}

void folio_undo_large_rmappable(struct folio *folio);

static inline struct folio *page_rmappable_folio(struct page *page)
{
	struct folio *folio = (struct folio *)page;

	if (folio && folio_test_large(folio))
		folio_set_large_rmappable(folio);
	return folio;
}

static inline void prep_compound_head(struct page *page, unsigned int order)
{
	struct folio *folio = (struct folio *)page;

	folio_set_order(folio, order);
	atomic_set(&folio->_large_mapcount, -1);
	atomic_set(&folio->_entire_mapcount, -1);
	atomic_set(&folio->_nr_pages_mapped, 0);
	atomic_set(&folio->_pincount, 0);
	if (order > 1)
		INIT_LIST_HEAD(&folio->_deferred_list);
}

static inline void prep_compound_tail(struct page *head, int tail_idx)
{
	struct page *p = head + tail_idx;

	p->mapping = TAIL_MAPPING;
	set_compound_head(p, head);
	set_page_private(p, 0);
}

extern void prep_compound_page(struct page *page, unsigned int order);

extern void post_alloc_hook(struct page *page, unsigned int order,
					gfp_t gfp_flags);
extern bool free_pages_prepare(struct page *page, unsigned int order);

extern int user_min_free_kbytes;

void free_unref_page(struct page *page, unsigned int order);
void free_unref_folios(struct folio_batch *fbatch);

extern void zone_pcp_reset(struct zone *zone);
extern void zone_pcp_disable(struct zone *zone);
extern void zone_pcp_enable(struct zone *zone);
extern void zone_pcp_init(struct zone *zone);

extern void *memmap_alloc(phys_addr_t size, phys_addr_t align,
			  phys_addr_t min_addr,
			  int nid, bool exact_nid);

void memmap_init_range(unsigned long, int, unsigned long, unsigned long,
		unsigned long, enum meminit_context, struct vmem_altmap *, int);

#if defined CONFIG_COMPACTION || defined CONFIG_CMA

/*
 * in mm/compaction.c
 */
/*
 * compact_control is used to track pages being migrated and the free pages
 * they are being migrated to during memory compaction. The free_pfn starts
 * at the end of a zone and migrate_pfn begins at the start. Movable pages
 * are moved to the end of a zone during a compaction run and the run
 * completes when free_pfn <= migrate_pfn
 */
struct compact_control {
	struct list_head freepages[NR_PAGE_ORDERS];	/* List of free pages to migrate to */
	struct list_head migratepages;	/* List of pages being migrated */
	unsigned int nr_freepages;	/* Number of isolated free pages */
	unsigned int nr_migratepages;	/* Number of pages to migrate */
	unsigned long free_pfn;		/* isolate_freepages search base */
	/*
	 * Acts as an in/out parameter to page isolation for migration.
	 * isolate_migratepages uses it as a search base.
	 * isolate_migratepages_block will update the value to the next pfn
	 * after the last isolated one.
	 */
	unsigned long migrate_pfn;
	unsigned long fast_start_pfn;	/* a pfn to start linear scan from */
	struct zone *zone;
	unsigned long total_migrate_scanned;
	unsigned long total_free_scanned;
	unsigned short fast_search_fail;/* failures to use free list searches */
	short search_order;		/* order to start a fast search at */
	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
	int order;			/* order a direct compactor needs */
	int migratetype;		/* migratetype of direct compactor */
	const unsigned int alloc_flags;	/* alloc flags of a direct compactor */
	const int highest_zoneidx;	/* zone index of a direct compactor */
	enum migrate_mode mode;		/* Async or sync migration mode */
	bool ignore_skip_hint;		/* Scan blocks even if marked skip */
	bool no_set_skip_hint;		/* Don't mark blocks for skipping */
	bool ignore_block_suitable;	/* Scan blocks considered unsuitable */
	bool direct_compaction;		/* False from kcompactd or /proc/... */
	bool proactive_compaction;	/* kcompactd proactive compaction */
	bool whole_zone;		/* Whole zone should/has been scanned */
	bool contended;			/* Signal lock contention */
	bool finish_pageblock;		/* Scan the remainder of a pageblock. Used
					 * when there are potentially transient
					 * isolation or migration failures to
					 * ensure forward progress.
					 */
	bool alloc_contig;		/* alloc_contig_range allocation */
};

/*
 * Used in direct compaction when a page should be taken from the freelists
 * immediately when one is created during the free path.
 */
struct capture_control {
	struct compact_control *cc;
	struct page *page;
};

unsigned long
isolate_freepages_range(struct compact_control *cc,
			unsigned long start_pfn, unsigned long end_pfn);
int
isolate_migratepages_range(struct compact_control *cc,
			   unsigned long low_pfn, unsigned long end_pfn);

int __alloc_contig_migrate_range(struct compact_control *cc,
					unsigned long start, unsigned long end,
					int migratetype);

/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
void init_cma_reserved_pageblock(struct page *page);

#endif /* CONFIG_COMPACTION || CONFIG_CMA */

int find_suitable_fallback(struct free_area *area, unsigned int order,
			int migratetype, bool only_stealable, bool *can_steal);

static inline bool free_area_empty(struct free_area *area, int migratetype)
{
	return list_empty(&area->free_list[migratetype]);
}

/*
 * These three helpers classifies VMAs for virtual memory accounting.
 */

/*
 * Executable code area - executable, not writable, not stack
 */
static inline bool is_exec_mapping(vm_flags_t flags)
{
	return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC;
}

/*
 * Stack area (including shadow stacks)
 *
 * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous:
 * do_mmap() forbids all other combinations.
 */
static inline bool is_stack_mapping(vm_flags_t flags)
{
	return ((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK);
}

/*
 * Data area - private, writable, not stack
 */
static inline bool is_data_mapping(vm_flags_t flags)
{
	return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE;
}

/* mm/util.c */
struct anon_vma *folio_anon_vma(struct folio *folio);

#ifdef CONFIG_MMU
void unmap_mapping_folio(struct folio *folio);
extern long populate_vma_page_range(struct vm_area_struct *vma,
		unsigned long start, unsigned long end, int *locked);
extern long faultin_page_range(struct mm_struct *mm, unsigned long start,
		unsigned long end, bool write, int *locked);
extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags,
			       unsigned long bytes);

/*
 * NOTE: This function can't tell whether the folio is "fully mapped" in the
 * range.
 * "fully mapped" means all the pages of folio is associated with the page
 * table of range while this function just check whether the folio range is
 * within the range [start, end). Function caller needs to do page table
 * check if it cares about the page table association.
 *
 * Typical usage (like mlock or madvise) is:
 * Caller knows at least 1 page of folio is associated with page table of VMA
 * and the range [start, end) is intersect with the VMA range. Caller wants
 * to know whether the folio is fully associated with the range. It calls
 * this function to check whether the folio is in the range first. Then checks
 * the page table to know whether the folio is fully mapped to the range.
 */
static inline bool
folio_within_range(struct folio *folio, struct vm_area_struct *vma,
		unsigned long start, unsigned long end)
{
	pgoff_t pgoff, addr;
	unsigned long vma_pglen = vma_pages(vma);

	VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio);
	if (start > end)
		return false;

	if (start < vma->vm_start)
		start = vma->vm_start;

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

	pgoff = folio_pgoff(folio);

	/* if folio start address is not in vma range */
	if (!in_range(pgoff, vma->vm_pgoff, vma_pglen))
		return false;

	addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);

	return !(addr < start || end - addr < folio_size(folio));
}

static inline bool
folio_within_vma(struct folio *folio, struct vm_area_struct *vma)
{
	return folio_within_range(folio, vma, vma->vm_start, vma->vm_end);
}

/*
 * mlock_vma_folio() and munlock_vma_folio():
 * should be called with vma's mmap_lock held for read or write,
 * under page table lock for the pte/pmd being added or removed.
 *
 * mlock is usually called at the end of folio_add_*_rmap_*(), munlock at
 * the end of folio_remove_rmap_*(); but new anon folios are managed by
 * folio_add_lru_vma() calling mlock_new_folio().
 */
void mlock_folio(struct folio *folio);
static inline void mlock_vma_folio(struct folio *folio,
				struct vm_area_struct *vma)
{
	/*
	 * The VM_SPECIAL check here serves two purposes.
	 * 1) VM_IO check prevents migration from double-counting during mlock.
	 * 2) Although mmap_region() and mlock_fixup() take care that VM_LOCKED
	 *    is never left set on a VM_SPECIAL vma, there is an interval while
	 *    file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may
	 *    still be set while VM_SPECIAL bits are added: so ignore it then.
	 */
	if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED))
		mlock_folio(folio);
}

void munlock_folio(struct folio *folio);
static inline void munlock_vma_folio(struct folio *folio,
					struct vm_area_struct *vma)
{
	/*
	 * munlock if the function is called. Ideally, we should only
	 * do munlock if any page of folio is unmapped from VMA and
	 * cause folio not fully mapped to VMA.
	 *
	 * But it's not easy to confirm that's the situation. So we
	 * always munlock the folio and page reclaim will correct it
	 * if it's wrong.
	 */
	if (unlikely(vma->vm_flags & VM_LOCKED))
		munlock_folio(folio);
}

void mlock_new_folio(struct folio *folio);
bool need_mlock_drain(int cpu);
void mlock_drain_local(void);
void mlock_drain_remote(int cpu);

extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);

/**
 * vma_address - Find the virtual address a page range is mapped at
 * @vma: The vma which maps this object.
 * @pgoff: The page offset within its object.
 * @nr_pages: The number of pages to consider.
 *
 * If any page in this range is mapped by this VMA, return the first address
 * where any of these pages appear.  Otherwise, return -EFAULT.
 */
static inline unsigned long vma_address(struct vm_area_struct *vma,
		pgoff_t pgoff, unsigned long nr_pages)
{
	unsigned long address;

	if (pgoff >= vma->vm_pgoff) {
		address = vma->vm_start +
			((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
		/* Check for address beyond vma (or wrapped through 0?) */
		if (address < vma->vm_start || address >= vma->vm_end)
			address = -EFAULT;
	} else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) {
		/* Test above avoids possibility of wrap to 0 on 32-bit */
		address = vma->vm_start;
	} else {
		address = -EFAULT;
	}
	return address;
}

/*
 * Then at what user virtual address will none of the range be found in vma?
 * Assumes that vma_address() already returned a good starting address.
 */
static inline unsigned long vma_address_end(struct page_vma_mapped_walk *pvmw)
{
	struct vm_area_struct *vma = pvmw->vma;
	pgoff_t pgoff;
	unsigned long address;

	/* Common case, plus ->pgoff is invalid for KSM */
	if (pvmw->nr_pages == 1)
		return pvmw->address + PAGE_SIZE;

	pgoff = pvmw->pgoff + pvmw->nr_pages;
	address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
	/* Check for address beyond vma (or wrapped through 0?) */
	if (address < vma->vm_start || address > vma->vm_end)
		address = vma->vm_end;
	return address;
}

static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
						    struct file *fpin)
{
	int flags = vmf->flags;

	if (fpin)
		return fpin;

	/*
	 * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
	 * anything, so we only pin the file and drop the mmap_lock if only
	 * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt.
	 */
	if (fault_flag_allow_retry_first(flags) &&
	    !(flags & FAULT_FLAG_RETRY_NOWAIT)) {
		fpin = get_file(vmf->vma->vm_file);
		release_fault_lock(vmf);
	}
	return fpin;
}
#else /* !CONFIG_MMU */
static inline void unmap_mapping_folio(struct folio *folio) { }
static inline void mlock_new_folio(struct folio *folio) { }
static inline bool need_mlock_drain(int cpu) { return false; }
static inline void mlock_drain_local(void) { }
static inline void mlock_drain_remote(int cpu) { }
static inline void vunmap_range_noflush(unsigned long start, unsigned long end)
{
}
#endif /* !CONFIG_MMU */

/* Memory initialisation debug and verification */
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
DECLARE_STATIC_KEY_TRUE(deferred_pages);

bool __init deferred_grow_zone(struct zone *zone, unsigned int order);
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */

enum mminit_level {
	MMINIT_WARNING,
	MMINIT_VERIFY,
	MMINIT_TRACE
};

#ifdef CONFIG_DEBUG_MEMORY_INIT

extern int mminit_loglevel;

#define mminit_dprintk(level, prefix, fmt, arg...) \
do { \
	if (level < mminit_loglevel) { \
		if (level <= MMINIT_WARNING) \
			pr_warn("mminit::" prefix " " fmt, ##arg);	\
		else \
			printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \
	} \
} while (0)

extern void mminit_verify_pageflags_layout(void);
extern void mminit_verify_zonelist(void);
#else

static inline void mminit_dprintk(enum mminit_level level,
				const char *prefix, const char *fmt, ...)
{
}

static inline void mminit_verify_pageflags_layout(void)
{
}

static inline void mminit_verify_zonelist(void)
{
}
#endif /* CONFIG_DEBUG_MEMORY_INIT */

#define NODE_RECLAIM_NOSCAN	-2
#define NODE_RECLAIM_FULL	-1
#define NODE_RECLAIM_SOME	0
#define NODE_RECLAIM_SUCCESS	1

#ifdef CONFIG_NUMA
extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int);
extern int find_next_best_node(int node, nodemask_t *used_node_mask);
#else
static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask,
				unsigned int order)
{
	return NODE_RECLAIM_NOSCAN;
}
static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
{
	return NUMA_NO_NODE;
}
#endif

/*
 * mm/memory-failure.c
 */
void shake_folio(struct folio *folio);
extern int hwpoison_filter(struct page *p);

extern u32 hwpoison_filter_dev_major;
extern u32 hwpoison_filter_dev_minor;
extern u64 hwpoison_filter_flags_mask;
extern u64 hwpoison_filter_flags_value;
extern u64 hwpoison_filter_memcg;
extern u32 hwpoison_filter_enable;

extern unsigned long  __must_check vm_mmap_pgoff(struct file *, unsigned long,
        unsigned long, unsigned long,
        unsigned long, unsigned long);

extern void set_pageblock_order(void);
unsigned long reclaim_pages(struct list_head *folio_list);
unsigned int reclaim_clean_pages_from_list(struct zone *zone,
					    struct list_head *folio_list);
/* The ALLOC_WMARK bits are used as an index to zone->watermark */
#define ALLOC_WMARK_MIN		WMARK_MIN
#define ALLOC_WMARK_LOW		WMARK_LOW
#define ALLOC_WMARK_HIGH	WMARK_HIGH
#define ALLOC_NO_WATERMARKS	0x04 /* don't check watermarks at all */

/* Mask to get the watermark bits */
#define ALLOC_WMARK_MASK	(ALLOC_NO_WATERMARKS-1)

/*
 * Only MMU archs have async oom victim reclaim - aka oom_reaper so we
 * cannot assume a reduced access to memory reserves is sufficient for
 * !MMU
 */
#ifdef CONFIG_MMU
#define ALLOC_OOM		0x08
#else
#define ALLOC_OOM		ALLOC_NO_WATERMARKS
#endif

#define ALLOC_NON_BLOCK		 0x10 /* Caller cannot block. Allow access
				       * to 25% of the min watermark or
				       * 62.5% if __GFP_HIGH is set.
				       */
#define ALLOC_MIN_RESERVE	 0x20 /* __GFP_HIGH set. Allow access to 50%
				       * of the min watermark.
				       */
#define ALLOC_CPUSET		 0x40 /* check for correct cpuset */
#define ALLOC_CMA		 0x80 /* allow allocations from CMA areas */
#ifdef CONFIG_ZONE_DMA32
#define ALLOC_NOFRAGMENT	0x100 /* avoid mixing pageblock types */
#else
#define ALLOC_NOFRAGMENT	  0x0
#endif
#define ALLOC_HIGHATOMIC	0x200 /* Allows access to MIGRATE_HIGHATOMIC */
#define ALLOC_KSWAPD		0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */

/* Flags that allow allocations below the min watermark. */
#define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM)

enum ttu_flags;
struct tlbflush_unmap_batch;


/*
 * only for MM internal work items which do not depend on
 * any allocations or locks which might depend on allocations
 */
extern struct workqueue_struct *mm_percpu_wq;

#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
void try_to_unmap_flush(void);
void try_to_unmap_flush_dirty(void);
void flush_tlb_batched_pending(struct mm_struct *mm);
#else
static inline void try_to_unmap_flush(void)
{
}
static inline void try_to_unmap_flush_dirty(void)
{
}
static inline void flush_tlb_batched_pending(struct mm_struct *mm)
{
}
#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */

extern const struct trace_print_flags pageflag_names[];
extern const struct trace_print_flags pagetype_names[];
extern const struct trace_print_flags vmaflag_names[];
extern const struct trace_print_flags gfpflag_names[];

static inline bool is_migrate_highatomic(enum migratetype migratetype)
{
	return migratetype == MIGRATE_HIGHATOMIC;
}

void setup_zone_pageset(struct zone *zone);

struct migration_target_control {
	int nid;		/* preferred node id */
	nodemask_t *nmask;
	gfp_t gfp_mask;
	enum migrate_reason reason;
};

/*
 * mm/filemap.c
 */
size_t splice_folio_into_pipe(struct pipe_inode_info *pipe,
			      struct folio *folio, loff_t fpos, size_t size);

/*
 * mm/vmalloc.c
 */
#ifdef CONFIG_MMU
void __init vmalloc_init(void);
int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end,
                pgprot_t prot, struct page **pages, unsigned int page_shift);
#else
static inline void vmalloc_init(void)
{
}

static inline
int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end,
                pgprot_t prot, struct page **pages, unsigned int page_shift)
{
	return -EINVAL;
}
#endif

int __must_check __vmap_pages_range_noflush(unsigned long addr,
			       unsigned long end, pgprot_t prot,
			       struct page **pages, unsigned int page_shift);

void vunmap_range_noflush(unsigned long start, unsigned long end);

void __vunmap_range_noflush(unsigned long start, unsigned long end);

int numa_migrate_prep(struct folio *folio, struct vm_fault *vmf,
		      unsigned long addr, int page_nid, int *flags);

void free_zone_device_folio(struct folio *folio);
int migrate_device_coherent_page(struct page *page);

/*
 * mm/gup.c
 */
int __must_check try_grab_folio(struct folio *folio, int refs,
				unsigned int flags);

/*
 * mm/huge_memory.c
 */
void touch_pud(struct vm_area_struct *vma, unsigned long addr,
	       pud_t *pud, bool write);
void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
	       pmd_t *pmd, bool write);

/*
 * mm/mmap.c
 */
struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi,
					struct vm_area_struct *vma,
					unsigned long delta);

enum {
	/* mark page accessed */
	FOLL_TOUCH = 1 << 16,
	/* a retry, previous pass started an IO */
	FOLL_TRIED = 1 << 17,
	/* we are working on non-current tsk/mm */
	FOLL_REMOTE = 1 << 18,
	/* pages must be released via unpin_user_page */
	FOLL_PIN = 1 << 19,
	/* gup_fast: prevent fall-back to slow gup */
	FOLL_FAST_ONLY = 1 << 20,
	/* allow unlocking the mmap lock */
	FOLL_UNLOCKABLE = 1 << 21,
	/* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */
	FOLL_MADV_POPULATE = 1 << 22,
};

#define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \
			    FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \
			    FOLL_MADV_POPULATE)

/*
 * Indicates for which pages that are write-protected in the page table,
 * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the
 * GUP pin will remain consistent with the pages mapped into the page tables
 * of the MM.
 *
 * Temporary unmapping of PageAnonExclusive() pages or clearing of
 * PageAnonExclusive() has to protect against concurrent GUP:
 * * Ordinary GUP: Using the PT lock
 * * GUP-fast and fork(): mm->write_protect_seq
 * * GUP-fast and KSM or temporary unmapping (swap, migration): see
 *    folio_try_share_anon_rmap_*()
 *
 * Must be called with the (sub)page that's actually referenced via the
 * page table entry, which might not necessarily be the head page for a
 * PTE-mapped THP.
 *
 * If the vma is NULL, we're coming from the GUP-fast path and might have
 * to fallback to the slow path just to lookup the vma.
 */
static inline bool gup_must_unshare(struct vm_area_struct *vma,
				    unsigned int flags, struct page *page)
{
	/*
	 * FOLL_WRITE is implicitly handled correctly as the page table entry
	 * has to be writable -- and if it references (part of) an anonymous
	 * folio, that part is required to be marked exclusive.
	 */
	if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN)
		return false;
	/*
	 * Note: PageAnon(page) is stable until the page is actually getting
	 * freed.
	 */
	if (!PageAnon(page)) {
		/*
		 * We only care about R/O long-term pining: R/O short-term
		 * pinning does not have the semantics to observe successive
		 * changes through the process page tables.
		 */
		if (!(flags & FOLL_LONGTERM))
			return false;

		/* We really need the vma ... */
		if (!vma)
			return true;

		/*
		 * ... because we only care about writable private ("COW")
		 * mappings where we have to break COW early.
		 */
		return is_cow_mapping(vma->vm_flags);
	}

	/* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */
	if (IS_ENABLED(CONFIG_HAVE_GUP_FAST))
		smp_rmb();

	/*
	 * Note that PageKsm() pages cannot be exclusive, and consequently,
	 * cannot get pinned.
	 */
	return !PageAnonExclusive(page);
}

extern bool mirrored_kernelcore;
extern bool memblock_has_mirror(void);

static __always_inline void vma_set_range(struct vm_area_struct *vma,
					  unsigned long start, unsigned long end,
					  pgoff_t pgoff)
{
	vma->vm_start = start;
	vma->vm_end = end;
	vma->vm_pgoff = pgoff;
}

static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma)
{
	/*
	 * NOTE: we must check this before VM_SOFTDIRTY on soft-dirty
	 * enablements, because when without soft-dirty being compiled in,
	 * VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY)
	 * will be constantly true.
	 */
	if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY))
		return false;

	/*
	 * Soft-dirty is kind of special: its tracking is enabled when the
	 * vma flags not set.
	 */
	return !(vma->vm_flags & VM_SOFTDIRTY);
}

static inline void vma_iter_config(struct vma_iterator *vmi,
		unsigned long index, unsigned long last)
{
	__mas_set_range(&vmi->mas, index, last - 1);
}

static inline void vma_iter_reset(struct vma_iterator *vmi)
{
	mas_reset(&vmi->mas);
}

static inline
struct vm_area_struct *vma_iter_prev_range_limit(struct vma_iterator *vmi, unsigned long min)
{
	return mas_prev_range(&vmi->mas, min);
}

static inline
struct vm_area_struct *vma_iter_next_range_limit(struct vma_iterator *vmi, unsigned long max)
{
	return mas_next_range(&vmi->mas, max);
}

static inline int vma_iter_area_lowest(struct vma_iterator *vmi, unsigned long min,
				       unsigned long max, unsigned long size)
{
	return mas_empty_area(&vmi->mas, min, max - 1, size);
}

static inline int vma_iter_area_highest(struct vma_iterator *vmi, unsigned long min,
					unsigned long max, unsigned long size)
{
	return mas_empty_area_rev(&vmi->mas, min, max - 1, size);
}

/*
 * VMA Iterator functions shared between nommu and mmap
 */
static inline int vma_iter_prealloc(struct vma_iterator *vmi,
		struct vm_area_struct *vma)
{
	return mas_preallocate(&vmi->mas, vma, GFP_KERNEL);
}

static inline void vma_iter_clear(struct vma_iterator *vmi)
{
	mas_store_prealloc(&vmi->mas, NULL);
}

static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi)
{
	return mas_walk(&vmi->mas);
}

/* Store a VMA with preallocated memory */
static inline void vma_iter_store(struct vma_iterator *vmi,
				  struct vm_area_struct *vma)
{

#if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
	if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start &&
			vmi->mas.index > vma->vm_start)) {
		pr_warn("%lx > %lx\n store vma %lx-%lx\n into slot %lx-%lx\n",
			vmi->mas.index, vma->vm_start, vma->vm_start,
			vma->vm_end, vmi->mas.index, vmi->mas.last);
	}
	if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start &&
			vmi->mas.last <  vma->vm_start)) {
		pr_warn("%lx < %lx\nstore vma %lx-%lx\ninto slot %lx-%lx\n",
		       vmi->mas.last, vma->vm_start, vma->vm_start, vma->vm_end,
		       vmi->mas.index, vmi->mas.last);
	}
#endif

	if (vmi->mas.status != ma_start &&
	    ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start)))
		vma_iter_invalidate(vmi);

	__mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1);
	mas_store_prealloc(&vmi->mas, vma);
}

static inline int vma_iter_store_gfp(struct vma_iterator *vmi,
			struct vm_area_struct *vma, gfp_t gfp)
{
	if (vmi->mas.status != ma_start &&
	    ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start)))
		vma_iter_invalidate(vmi);

	__mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1);
	mas_store_gfp(&vmi->mas, vma, gfp);
	if (unlikely(mas_is_err(&vmi->mas)))
		return -ENOMEM;

	return 0;
}

/*
 * VMA lock generalization
 */
struct vma_prepare {
	struct vm_area_struct *vma;
	struct vm_area_struct *adj_next;
	struct file *file;
	struct address_space *mapping;
	struct anon_vma *anon_vma;
	struct vm_area_struct *insert;
	struct vm_area_struct *remove;
	struct vm_area_struct *remove2;
};

void __meminit __init_single_page(struct page *page, unsigned long pfn,
				unsigned long zone, int nid);

/* shrinker related functions */
unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg,
			  int priority);

#ifdef CONFIG_64BIT
static inline int can_do_mseal(unsigned long flags)
{
	if (flags)
		return -EINVAL;

	return 0;
}

bool can_modify_mm(struct mm_struct *mm, unsigned long start,
		unsigned long end);
bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start,
		unsigned long end, int behavior);
#else
static inline int can_do_mseal(unsigned long flags)
{
	return -EPERM;
}

static inline bool can_modify_mm(struct mm_struct *mm, unsigned long start,
		unsigned long end)
{
	return true;
}

static inline bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start,
		unsigned long end, int behavior)
{
	return true;
}
#endif

#ifdef CONFIG_SHRINKER_DEBUG
static inline __printf(2, 0) int shrinker_debugfs_name_alloc(
			struct shrinker *shrinker, const char *fmt, va_list ap)
{
	shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap);

	return shrinker->name ? 0 : -ENOMEM;
}

static inline void shrinker_debugfs_name_free(struct shrinker *shrinker)
{
	kfree_const(shrinker->name);
	shrinker->name = NULL;
}

extern int shrinker_debugfs_add(struct shrinker *shrinker);
extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker,
					      int *debugfs_id);
extern void shrinker_debugfs_remove(struct dentry *debugfs_entry,
				    int debugfs_id);
#else /* CONFIG_SHRINKER_DEBUG */
static inline int shrinker_debugfs_add(struct shrinker *shrinker)
{
	return 0;
}
static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker,
					      const char *fmt, va_list ap)
{
	return 0;
}
static inline void shrinker_debugfs_name_free(struct shrinker *shrinker)
{
}
static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker,
						     int *debugfs_id)
{
	*debugfs_id = -1;
	return NULL;
}
static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry,
					   int debugfs_id)
{
}
#endif /* CONFIG_SHRINKER_DEBUG */

/* Only track the nodes of mappings with shadow entries */
void workingset_update_node(struct xa_node *node);
extern struct list_lru shadow_nodes;

#endif	/* __MM_INTERNAL_H */