summaryrefslogtreecommitdiff
path: root/include/linux/pgtable.h
blob: e8b2ac6bd2ae3b0a768734c8411f45a7d162e12d (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
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_PGTABLE_H
#define _LINUX_PGTABLE_H

#include <linux/pfn.h>
#include <asm/pgtable.h>

#define PMD_ORDER	(PMD_SHIFT - PAGE_SHIFT)
#define PUD_ORDER	(PUD_SHIFT - PAGE_SHIFT)

#ifndef __ASSEMBLY__
#ifdef CONFIG_MMU

#include <linux/mm_types.h>
#include <linux/bug.h>
#include <linux/errno.h>
#include <asm-generic/pgtable_uffd.h>
#include <linux/page_table_check.h>

#if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \
	defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS
#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED
#endif

/*
 * On almost all architectures and configurations, 0 can be used as the
 * upper ceiling to free_pgtables(): on many architectures it has the same
 * effect as using TASK_SIZE.  However, there is one configuration which
 * must impose a more careful limit, to avoid freeing kernel pgtables.
 */
#ifndef USER_PGTABLES_CEILING
#define USER_PGTABLES_CEILING	0UL
#endif

/*
 * This defines the first usable user address. Platforms
 * can override its value with custom FIRST_USER_ADDRESS
 * defined in their respective <asm/pgtable.h>.
 */
#ifndef FIRST_USER_ADDRESS
#define FIRST_USER_ADDRESS	0UL
#endif

/*
 * This defines the generic helper for accessing PMD page
 * table page. Although platforms can still override this
 * via their respective <asm/pgtable.h>.
 */
#ifndef pmd_pgtable
#define pmd_pgtable(pmd) pmd_page(pmd)
#endif

#define pmd_folio(pmd) page_folio(pmd_page(pmd))

/*
 * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD]
 *
 * The pXx_index() functions return the index of the entry in the page
 * table page which would control the given virtual address
 *
 * As these functions may be used by the same code for different levels of
 * the page table folding, they are always available, regardless of
 * CONFIG_PGTABLE_LEVELS value. For the folded levels they simply return 0
 * because in such cases PTRS_PER_PxD equals 1.
 */

static inline unsigned long pte_index(unsigned long address)
{
	return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
}

#ifndef pmd_index
static inline unsigned long pmd_index(unsigned long address)
{
	return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1);
}
#define pmd_index pmd_index
#endif

#ifndef pud_index
static inline unsigned long pud_index(unsigned long address)
{
	return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
}
#define pud_index pud_index
#endif

#ifndef pgd_index
/* Must be a compile-time constant, so implement it as a macro */
#define pgd_index(a)  (((a) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
#endif

#ifndef pte_offset_kernel
static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address)
{
	return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address);
}
#define pte_offset_kernel pte_offset_kernel
#endif

#ifdef CONFIG_HIGHPTE
#define __pte_map(pmd, address) \
	((pte_t *)kmap_local_page(pmd_page(*(pmd))) + pte_index((address)))
#define pte_unmap(pte)	do {	\
	kunmap_local((pte));	\
	rcu_read_unlock();	\
} while (0)
#else
static inline pte_t *__pte_map(pmd_t *pmd, unsigned long address)
{
	return pte_offset_kernel(pmd, address);
}
static inline void pte_unmap(pte_t *pte)
{
	rcu_read_unlock();
}
#endif

void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable);

/* Find an entry in the second-level page table.. */
#ifndef pmd_offset
static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
{
	return pud_pgtable(*pud) + pmd_index(address);
}
#define pmd_offset pmd_offset
#endif

#ifndef pud_offset
static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
{
	return p4d_pgtable(*p4d) + pud_index(address);
}
#define pud_offset pud_offset
#endif

static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address)
{
	return (pgd + pgd_index(address));
};

/*
 * a shortcut to get a pgd_t in a given mm
 */
#ifndef pgd_offset
#define pgd_offset(mm, address)		pgd_offset_pgd((mm)->pgd, (address))
#endif

/*
 * a shortcut which implies the use of the kernel's pgd, instead
 * of a process's
 */
#define pgd_offset_k(address)		pgd_offset(&init_mm, (address))

/*
 * In many cases it is known that a virtual address is mapped at PMD or PTE
 * level, so instead of traversing all the page table levels, we can get a
 * pointer to the PMD entry in user or kernel page table or translate a virtual
 * address to the pointer in the PTE in the kernel page tables with simple
 * helpers.
 */
static inline pmd_t *pmd_off(struct mm_struct *mm, unsigned long va)
{
	return pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, va), va), va), va);
}

static inline pmd_t *pmd_off_k(unsigned long va)
{
	return pmd_offset(pud_offset(p4d_offset(pgd_offset_k(va), va), va), va);
}

static inline pte_t *virt_to_kpte(unsigned long vaddr)
{
	pmd_t *pmd = pmd_off_k(vaddr);

	return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr);
}

#ifndef pmd_young
static inline int pmd_young(pmd_t pmd)
{
	return 0;
}
#endif

#ifndef pmd_dirty
static inline int pmd_dirty(pmd_t pmd)
{
	return 0;
}
#endif

/*
 * A facility to provide lazy MMU batching.  This allows PTE updates and
 * page invalidations to be delayed until a call to leave lazy MMU mode
 * is issued.  Some architectures may benefit from doing this, and it is
 * beneficial for both shadow and direct mode hypervisors, which may batch
 * the PTE updates which happen during this window.  Note that using this
 * interface requires that read hazards be removed from the code.  A read
 * hazard could result in the direct mode hypervisor case, since the actual
 * write to the page tables may not yet have taken place, so reads though
 * a raw PTE pointer after it has been modified are not guaranteed to be
 * up to date.  This mode can only be entered and left under the protection of
 * the page table locks for all page tables which may be modified.  In the UP
 * case, this is required so that preemption is disabled, and in the SMP case,
 * it must synchronize the delayed page table writes properly on other CPUs.
 */
#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE
#define arch_enter_lazy_mmu_mode()	do {} while (0)
#define arch_leave_lazy_mmu_mode()	do {} while (0)
#define arch_flush_lazy_mmu_mode()	do {} while (0)
#endif

#ifndef pte_batch_hint
/**
 * pte_batch_hint - Number of pages that can be added to batch without scanning.
 * @ptep: Page table pointer for the entry.
 * @pte: Page table entry.
 *
 * Some architectures know that a set of contiguous ptes all map the same
 * contiguous memory with the same permissions. In this case, it can provide a
 * hint to aid pte batching without the core code needing to scan every pte.
 *
 * An architecture implementation may ignore the PTE accessed state. Further,
 * the dirty state must apply atomically to all the PTEs described by the hint.
 *
 * May be overridden by the architecture, else pte_batch_hint is always 1.
 */
static inline unsigned int pte_batch_hint(pte_t *ptep, pte_t pte)
{
	return 1;
}
#endif

#ifndef pte_advance_pfn
static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr)
{
	return __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT));
}
#endif

#define pte_next_pfn(pte) pte_advance_pfn(pte, 1)

#ifndef set_ptes
/**
 * set_ptes - Map consecutive pages to a contiguous range of addresses.
 * @mm: Address space to map the pages into.
 * @addr: Address to map the first page at.
 * @ptep: Page table pointer for the first entry.
 * @pte: Page table entry for the first page.
 * @nr: Number of pages to map.
 *
 * When nr==1, initial state of pte may be present or not present, and new state
 * may be present or not present. When nr>1, initial state of all ptes must be
 * not present, and new state must be present.
 *
 * May be overridden by the architecture, or the architecture can define
 * set_pte() and PFN_PTE_SHIFT.
 *
 * Context: The caller holds the page table lock.  The pages all belong
 * to the same folio.  The PTEs are all in the same PMD.
 */
static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
		pte_t *ptep, pte_t pte, unsigned int nr)
{
	page_table_check_ptes_set(mm, ptep, pte, nr);

	arch_enter_lazy_mmu_mode();
	for (;;) {
		set_pte(ptep, pte);
		if (--nr == 0)
			break;
		ptep++;
		pte = pte_next_pfn(pte);
	}
	arch_leave_lazy_mmu_mode();
}
#endif
#define set_pte_at(mm, addr, ptep, pte) set_ptes(mm, addr, ptep, pte, 1)

#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
extern int ptep_set_access_flags(struct vm_area_struct *vma,
				 unsigned long address, pte_t *ptep,
				 pte_t entry, int dirty);
#endif

#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern int pmdp_set_access_flags(struct vm_area_struct *vma,
				 unsigned long address, pmd_t *pmdp,
				 pmd_t entry, int dirty);
extern int pudp_set_access_flags(struct vm_area_struct *vma,
				 unsigned long address, pud_t *pudp,
				 pud_t entry, int dirty);
#else
static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
					unsigned long address, pmd_t *pmdp,
					pmd_t entry, int dirty)
{
	BUILD_BUG();
	return 0;
}
static inline int pudp_set_access_flags(struct vm_area_struct *vma,
					unsigned long address, pud_t *pudp,
					pud_t entry, int dirty)
{
	BUILD_BUG();
	return 0;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif

#ifndef ptep_get
static inline pte_t ptep_get(pte_t *ptep)
{
	return READ_ONCE(*ptep);
}
#endif

#ifndef pmdp_get
static inline pmd_t pmdp_get(pmd_t *pmdp)
{
	return READ_ONCE(*pmdp);
}
#endif

#ifndef pudp_get
static inline pud_t pudp_get(pud_t *pudp)
{
	return READ_ONCE(*pudp);
}
#endif

#ifndef p4dp_get
static inline p4d_t p4dp_get(p4d_t *p4dp)
{
	return READ_ONCE(*p4dp);
}
#endif

#ifndef pgdp_get
static inline pgd_t pgdp_get(pgd_t *pgdp)
{
	return READ_ONCE(*pgdp);
}
#endif

#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
					    unsigned long address,
					    pte_t *ptep)
{
	pte_t pte = ptep_get(ptep);
	int r = 1;
	if (!pte_young(pte))
		r = 0;
	else
		set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte));
	return r;
}
#endif

#ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
					    unsigned long address,
					    pmd_t *pmdp)
{
	pmd_t pmd = *pmdp;
	int r = 1;
	if (!pmd_young(pmd))
		r = 0;
	else
		set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd));
	return r;
}
#else
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
					    unsigned long address,
					    pmd_t *pmdp)
{
	BUILD_BUG();
	return 0;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */
#endif

#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
int ptep_clear_flush_young(struct vm_area_struct *vma,
			   unsigned long address, pte_t *ptep);
#endif

#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
				  unsigned long address, pmd_t *pmdp);
#else
/*
 * Despite relevant to THP only, this API is called from generic rmap code
 * under PageTransHuge(), hence needs a dummy implementation for !THP
 */
static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
					 unsigned long address, pmd_t *pmdp)
{
	BUILD_BUG();
	return 0;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif

#ifndef arch_has_hw_nonleaf_pmd_young
/*
 * Return whether the accessed bit in non-leaf PMD entries is supported on the
 * local CPU.
 */
static inline bool arch_has_hw_nonleaf_pmd_young(void)
{
	return IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG);
}
#endif

#ifndef arch_has_hw_pte_young
/*
 * Return whether the accessed bit is supported on the local CPU.
 *
 * This stub assumes accessing through an old PTE triggers a page fault.
 * Architectures that automatically set the access bit should overwrite it.
 */
static inline bool arch_has_hw_pte_young(void)
{
	return IS_ENABLED(CONFIG_ARCH_HAS_HW_PTE_YOUNG);
}
#endif

#ifndef arch_check_zapped_pte
static inline void arch_check_zapped_pte(struct vm_area_struct *vma,
					 pte_t pte)
{
}
#endif

#ifndef arch_check_zapped_pmd
static inline void arch_check_zapped_pmd(struct vm_area_struct *vma,
					 pmd_t pmd)
{
}
#endif

#ifndef arch_check_zapped_pud
static inline void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud)
{
}
#endif

#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
				       unsigned long address,
				       pte_t *ptep)
{
	pte_t pte = ptep_get(ptep);
	pte_clear(mm, address, ptep);
	page_table_check_pte_clear(mm, pte);
	return pte;
}
#endif

#ifndef clear_young_dirty_ptes
/**
 * clear_young_dirty_ptes - Mark PTEs that map consecutive pages of the
 *		same folio as old/clean.
 * @mm: Address space the pages are mapped into.
 * @addr: Address the first page is mapped at.
 * @ptep: Page table pointer for the first entry.
 * @nr: Number of entries to mark old/clean.
 * @flags: Flags to modify the PTE batch semantics.
 *
 * May be overridden by the architecture; otherwise, implemented by
 * get_and_clear/modify/set for each pte in the range.
 *
 * Note that PTE bits in the PTE range besides the PFN can differ. For example,
 * some PTEs might be write-protected.
 *
 * Context: The caller holds the page table lock.  The PTEs map consecutive
 * pages that belong to the same folio.  The PTEs are all in the same PMD.
 */
static inline void clear_young_dirty_ptes(struct vm_area_struct *vma,
					  unsigned long addr, pte_t *ptep,
					  unsigned int nr, cydp_t flags)
{
	pte_t pte;

	for (;;) {
		if (flags == CYDP_CLEAR_YOUNG)
			ptep_test_and_clear_young(vma, addr, ptep);
		else {
			pte = ptep_get_and_clear(vma->vm_mm, addr, ptep);
			if (flags & CYDP_CLEAR_YOUNG)
				pte = pte_mkold(pte);
			if (flags & CYDP_CLEAR_DIRTY)
				pte = pte_mkclean(pte);
			set_pte_at(vma->vm_mm, addr, ptep, pte);
		}
		if (--nr == 0)
			break;
		ptep++;
		addr += PAGE_SIZE;
	}
}
#endif

static inline void ptep_clear(struct mm_struct *mm, unsigned long addr,
			      pte_t *ptep)
{
	ptep_get_and_clear(mm, addr, ptep);
}

#ifdef CONFIG_GUP_GET_PXX_LOW_HIGH
/*
 * For walking the pagetables without holding any locks.  Some architectures
 * (eg x86-32 PAE) cannot load the entries atomically without using expensive
 * instructions.  We are guaranteed that a PTE will only either go from not
 * present to present, or present to not present -- it will not switch to a
 * completely different present page without a TLB flush inbetween; which we
 * are blocking by holding interrupts off.
 *
 * Setting ptes from not present to present goes:
 *
 *   ptep->pte_high = h;
 *   smp_wmb();
 *   ptep->pte_low = l;
 *
 * And present to not present goes:
 *
 *   ptep->pte_low = 0;
 *   smp_wmb();
 *   ptep->pte_high = 0;
 *
 * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'.
 * We load pte_high *after* loading pte_low, which ensures we don't see an older
 * value of pte_high.  *Then* we recheck pte_low, which ensures that we haven't
 * picked up a changed pte high. We might have gotten rubbish values from
 * pte_low and pte_high, but we are guaranteed that pte_low will not have the
 * present bit set *unless* it is 'l'. Because get_user_pages_fast() only
 * operates on present ptes we're safe.
 */
static inline pte_t ptep_get_lockless(pte_t *ptep)
{
	pte_t pte;

	do {
		pte.pte_low = ptep->pte_low;
		smp_rmb();
		pte.pte_high = ptep->pte_high;
		smp_rmb();
	} while (unlikely(pte.pte_low != ptep->pte_low));

	return pte;
}
#define ptep_get_lockless ptep_get_lockless

#if CONFIG_PGTABLE_LEVELS > 2
static inline pmd_t pmdp_get_lockless(pmd_t *pmdp)
{
	pmd_t pmd;

	do {
		pmd.pmd_low = pmdp->pmd_low;
		smp_rmb();
		pmd.pmd_high = pmdp->pmd_high;
		smp_rmb();
	} while (unlikely(pmd.pmd_low != pmdp->pmd_low));

	return pmd;
}
#define pmdp_get_lockless pmdp_get_lockless
#define pmdp_get_lockless_sync() tlb_remove_table_sync_one()
#endif /* CONFIG_PGTABLE_LEVELS > 2 */
#endif /* CONFIG_GUP_GET_PXX_LOW_HIGH */

/*
 * We require that the PTE can be read atomically.
 */
#ifndef ptep_get_lockless
static inline pte_t ptep_get_lockless(pte_t *ptep)
{
	return ptep_get(ptep);
}
#endif

#ifndef pmdp_get_lockless
static inline pmd_t pmdp_get_lockless(pmd_t *pmdp)
{
	return pmdp_get(pmdp);
}
static inline void pmdp_get_lockless_sync(void)
{
}
#endif

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
					    unsigned long address,
					    pmd_t *pmdp)
{
	pmd_t pmd = *pmdp;

	pmd_clear(pmdp);
	page_table_check_pmd_clear(mm, pmd);

	return pmd;
}
#endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */
#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR
static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
					    unsigned long address,
					    pud_t *pudp)
{
	pud_t pud = *pudp;

	pud_clear(pudp);
	page_table_check_pud_clear(mm, pud);

	return pud;
}
#endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
static inline pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma,
					    unsigned long address, pmd_t *pmdp,
					    int full)
{
	return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
}
#endif

#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL
static inline pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma,
					    unsigned long address, pud_t *pudp,
					    int full)
{
	return pudp_huge_get_and_clear(vma->vm_mm, address, pudp);
}
#endif
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
					    unsigned long address, pte_t *ptep,
					    int full)
{
	return ptep_get_and_clear(mm, address, ptep);
}
#endif

#ifndef get_and_clear_full_ptes
/**
 * get_and_clear_full_ptes - Clear present PTEs that map consecutive pages of
 *			     the same folio, collecting dirty/accessed bits.
 * @mm: Address space the pages are mapped into.
 * @addr: Address the first page is mapped at.
 * @ptep: Page table pointer for the first entry.
 * @nr: Number of entries to clear.
 * @full: Whether we are clearing a full mm.
 *
 * May be overridden by the architecture; otherwise, implemented as a simple
 * loop over ptep_get_and_clear_full(), merging dirty/accessed bits into the
 * returned PTE.
 *
 * Note that PTE bits in the PTE range besides the PFN can differ. For example,
 * some PTEs might be write-protected.
 *
 * Context: The caller holds the page table lock.  The PTEs map consecutive
 * pages that belong to the same folio.  The PTEs are all in the same PMD.
 */
static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm,
		unsigned long addr, pte_t *ptep, unsigned int nr, int full)
{
	pte_t pte, tmp_pte;

	pte = ptep_get_and_clear_full(mm, addr, ptep, full);
	while (--nr) {
		ptep++;
		addr += PAGE_SIZE;
		tmp_pte = ptep_get_and_clear_full(mm, addr, ptep, full);
		if (pte_dirty(tmp_pte))
			pte = pte_mkdirty(pte);
		if (pte_young(tmp_pte))
			pte = pte_mkyoung(pte);
	}
	return pte;
}
#endif

#ifndef clear_full_ptes
/**
 * clear_full_ptes - Clear present PTEs that map consecutive pages of the same
 *		     folio.
 * @mm: Address space the pages are mapped into.
 * @addr: Address the first page is mapped at.
 * @ptep: Page table pointer for the first entry.
 * @nr: Number of entries to clear.
 * @full: Whether we are clearing a full mm.
 *
 * May be overridden by the architecture; otherwise, implemented as a simple
 * loop over ptep_get_and_clear_full().
 *
 * Note that PTE bits in the PTE range besides the PFN can differ. For example,
 * some PTEs might be write-protected.
 *
 * Context: The caller holds the page table lock.  The PTEs map consecutive
 * pages that belong to the same folio.  The PTEs are all in the same PMD.
 */
static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr,
		pte_t *ptep, unsigned int nr, int full)
{
	for (;;) {
		ptep_get_and_clear_full(mm, addr, ptep, full);
		if (--nr == 0)
			break;
		ptep++;
		addr += PAGE_SIZE;
	}
}
#endif

/*
 * If two threads concurrently fault at the same page, the thread that
 * won the race updates the PTE and its local TLB/Cache. The other thread
 * gives up, simply does nothing, and continues; on architectures where
 * software can update TLB,  local TLB can be updated here to avoid next page
 * fault. This function updates TLB only, do nothing with cache or others.
 * It is the difference with function update_mmu_cache.
 */
#ifndef update_mmu_tlb_range
static inline void update_mmu_tlb_range(struct vm_area_struct *vma,
				unsigned long address, pte_t *ptep, unsigned int nr)
{
}
#endif

static inline void update_mmu_tlb(struct vm_area_struct *vma,
				unsigned long address, pte_t *ptep)
{
	update_mmu_tlb_range(vma, address, ptep, 1);
}

/*
 * Some architectures may be able to avoid expensive synchronization
 * primitives when modifications are made to PTE's which are already
 * not present, or in the process of an address space destruction.
 */
#ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL
static inline void pte_clear_not_present_full(struct mm_struct *mm,
					      unsigned long address,
					      pte_t *ptep,
					      int full)
{
	pte_clear(mm, address, ptep);
}
#endif

#ifndef clear_not_present_full_ptes
/**
 * clear_not_present_full_ptes - Clear multiple not present PTEs which are
 *				 consecutive in the pgtable.
 * @mm: Address space the ptes represent.
 * @addr: Address of the first pte.
 * @ptep: Page table pointer for the first entry.
 * @nr: Number of entries to clear.
 * @full: Whether we are clearing a full mm.
 *
 * May be overridden by the architecture; otherwise, implemented as a simple
 * loop over pte_clear_not_present_full().
 *
 * Context: The caller holds the page table lock.  The PTEs are all not present.
 * The PTEs are all in the same PMD.
 */
static inline void clear_not_present_full_ptes(struct mm_struct *mm,
		unsigned long addr, pte_t *ptep, unsigned int nr, int full)
{
	for (;;) {
		pte_clear_not_present_full(mm, addr, ptep, full);
		if (--nr == 0)
			break;
		ptep++;
		addr += PAGE_SIZE;
	}
}
#endif

#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
extern pte_t ptep_clear_flush(struct vm_area_struct *vma,
			      unsigned long address,
			      pte_t *ptep);
#endif

#ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH
extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
			      unsigned long address,
			      pmd_t *pmdp);
extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma,
			      unsigned long address,
			      pud_t *pudp);
#endif

#ifndef pte_mkwrite
static inline pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma)
{
	return pte_mkwrite_novma(pte);
}
#endif

#if defined(CONFIG_ARCH_WANT_PMD_MKWRITE) && !defined(pmd_mkwrite)
static inline pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
{
	return pmd_mkwrite_novma(pmd);
}
#endif

#ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT
struct mm_struct;
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
{
	pte_t old_pte = ptep_get(ptep);
	set_pte_at(mm, address, ptep, pte_wrprotect(old_pte));
}
#endif

#ifndef wrprotect_ptes
/**
 * wrprotect_ptes - Write-protect PTEs that map consecutive pages of the same
 *		    folio.
 * @mm: Address space the pages are mapped into.
 * @addr: Address the first page is mapped at.
 * @ptep: Page table pointer for the first entry.
 * @nr: Number of entries to write-protect.
 *
 * May be overridden by the architecture; otherwise, implemented as a simple
 * loop over ptep_set_wrprotect().
 *
 * Note that PTE bits in the PTE range besides the PFN can differ. For example,
 * some PTEs might be write-protected.
 *
 * Context: The caller holds the page table lock.  The PTEs map consecutive
 * pages that belong to the same folio.  The PTEs are all in the same PMD.
 */
static inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
		pte_t *ptep, unsigned int nr)
{
	for (;;) {
		ptep_set_wrprotect(mm, addr, ptep);
		if (--nr == 0)
			break;
		ptep++;
		addr += PAGE_SIZE;
	}
}
#endif

/*
 * On some architectures hardware does not set page access bit when accessing
 * memory page, it is responsibility of software setting this bit. It brings
 * out extra page fault penalty to track page access bit. For optimization page
 * access bit can be set during all page fault flow on these arches.
 * To be differentiate with macro pte_mkyoung, this macro is used on platforms
 * where software maintains page access bit.
 */
#ifndef pte_sw_mkyoung
static inline pte_t pte_sw_mkyoung(pte_t pte)
{
	return pte;
}
#define pte_sw_mkyoung	pte_sw_mkyoung
#endif

#ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
				      unsigned long address, pmd_t *pmdp)
{
	pmd_t old_pmd = *pmdp;
	set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd));
}
#else
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
				      unsigned long address, pmd_t *pmdp)
{
	BUILD_BUG();
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
#ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline void pudp_set_wrprotect(struct mm_struct *mm,
				      unsigned long address, pud_t *pudp)
{
	pud_t old_pud = *pudp;

	set_pud_at(mm, address, pudp, pud_wrprotect(old_pud));
}
#else
static inline void pudp_set_wrprotect(struct mm_struct *mm,
				      unsigned long address, pud_t *pudp)
{
	BUILD_BUG();
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
#endif

#ifndef pmdp_collapse_flush
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
				 unsigned long address, pmd_t *pmdp);
#else
static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
					unsigned long address,
					pmd_t *pmdp)
{
	BUILD_BUG();
	return *pmdp;
}
#define pmdp_collapse_flush pmdp_collapse_flush
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif

#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
				       pgtable_t pgtable);
#endif

#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
#endif

#ifndef arch_needs_pgtable_deposit
#define arch_needs_pgtable_deposit() (false)
#endif

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
 * This is an implementation of pmdp_establish() that is only suitable for an
 * architecture that doesn't have hardware dirty/accessed bits. In this case we
 * can't race with CPU which sets these bits and non-atomic approach is fine.
 */
static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma,
		unsigned long address, pmd_t *pmdp, pmd_t pmd)
{
	pmd_t old_pmd = *pmdp;
	set_pmd_at(vma->vm_mm, address, pmdp, pmd);
	return old_pmd;
}
#endif

#ifndef __HAVE_ARCH_PMDP_INVALIDATE
extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
			    pmd_t *pmdp);
#endif

#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD

/*
 * pmdp_invalidate_ad() invalidates the PMD while changing a transparent
 * hugepage mapping in the page tables. This function is similar to
 * pmdp_invalidate(), but should only be used if the access and dirty bits would
 * not be cleared by the software in the new PMD value. The function ensures
 * that hardware changes of the access and dirty bits updates would not be lost.
 *
 * Doing so can allow in certain architectures to avoid a TLB flush in most
 * cases. Yet, another TLB flush might be necessary later if the PMD update
 * itself requires such flush (e.g., if protection was set to be stricter). Yet,
 * even when a TLB flush is needed because of the update, the caller may be able
 * to batch these TLB flushing operations, so fewer TLB flush operations are
 * needed.
 */
extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma,
				unsigned long address, pmd_t *pmdp);
#endif

#ifndef __HAVE_ARCH_PTE_SAME
static inline int pte_same(pte_t pte_a, pte_t pte_b)
{
	return pte_val(pte_a) == pte_val(pte_b);
}
#endif

#ifndef __HAVE_ARCH_PTE_UNUSED
/*
 * Some architectures provide facilities to virtualization guests
 * so that they can flag allocated pages as unused. This allows the
 * host to transparently reclaim unused pages. This function returns
 * whether the pte's page is unused.
 */
static inline int pte_unused(pte_t pte)
{
	return 0;
}
#endif

#ifndef pte_access_permitted
#define pte_access_permitted(pte, write) \
	(pte_present(pte) && (!(write) || pte_write(pte)))
#endif

#ifndef pmd_access_permitted
#define pmd_access_permitted(pmd, write) \
	(pmd_present(pmd) && (!(write) || pmd_write(pmd)))
#endif

#ifndef pud_access_permitted
#define pud_access_permitted(pud, write) \
	(pud_present(pud) && (!(write) || pud_write(pud)))
#endif

#ifndef p4d_access_permitted
#define p4d_access_permitted(p4d, write) \
	(p4d_present(p4d) && (!(write) || p4d_write(p4d)))
#endif

#ifndef pgd_access_permitted
#define pgd_access_permitted(pgd, write) \
	(pgd_present(pgd) && (!(write) || pgd_write(pgd)))
#endif

#ifndef __HAVE_ARCH_PMD_SAME
static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
{
	return pmd_val(pmd_a) == pmd_val(pmd_b);
}
#endif

#ifndef pud_same
static inline int pud_same(pud_t pud_a, pud_t pud_b)
{
	return pud_val(pud_a) == pud_val(pud_b);
}
#define pud_same pud_same
#endif

#ifndef __HAVE_ARCH_P4D_SAME
static inline int p4d_same(p4d_t p4d_a, p4d_t p4d_b)
{
	return p4d_val(p4d_a) == p4d_val(p4d_b);
}
#endif

#ifndef __HAVE_ARCH_PGD_SAME
static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b)
{
	return pgd_val(pgd_a) == pgd_val(pgd_b);
}
#endif

/*
 * Use set_p*_safe(), and elide TLB flushing, when confident that *no*
 * TLB flush will be required as a result of the "set". For example, use
 * in scenarios where it is known ahead of time that the routine is
 * setting non-present entries, or re-setting an existing entry to the
 * same value. Otherwise, use the typical "set" helpers and flush the
 * TLB.
 */
#define set_pte_safe(ptep, pte) \
({ \
	WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \
	set_pte(ptep, pte); \
})

#define set_pmd_safe(pmdp, pmd) \
({ \
	WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \
	set_pmd(pmdp, pmd); \
})

#define set_pud_safe(pudp, pud) \
({ \
	WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \
	set_pud(pudp, pud); \
})

#define set_p4d_safe(p4dp, p4d) \
({ \
	WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \
	set_p4d(p4dp, p4d); \
})

#define set_pgd_safe(pgdp, pgd) \
({ \
	WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \
	set_pgd(pgdp, pgd); \
})

#ifndef __HAVE_ARCH_DO_SWAP_PAGE
static inline void arch_do_swap_page_nr(struct mm_struct *mm,
				     struct vm_area_struct *vma,
				     unsigned long addr,
				     pte_t pte, pte_t oldpte,
				     int nr)
{

}
#else
/*
 * Some architectures support metadata associated with a page. When a
 * page is being swapped out, this metadata must be saved so it can be
 * restored when the page is swapped back in. SPARC M7 and newer
 * processors support an ADI (Application Data Integrity) tag for the
 * page as metadata for the page. arch_do_swap_page() can restore this
 * metadata when a page is swapped back in.
 */
static inline void arch_do_swap_page_nr(struct mm_struct *mm,
					struct vm_area_struct *vma,
					unsigned long addr,
					pte_t pte, pte_t oldpte,
					int nr)
{
	for (int i = 0; i < nr; i++) {
		arch_do_swap_page(vma->vm_mm, vma, addr + i * PAGE_SIZE,
				pte_advance_pfn(pte, i),
				pte_advance_pfn(oldpte, i));
	}
}
#endif

#ifndef __HAVE_ARCH_UNMAP_ONE
/*
 * Some architectures support metadata associated with a page. When a
 * page is being swapped out, this metadata must be saved so it can be
 * restored when the page is swapped back in. SPARC M7 and newer
 * processors support an ADI (Application Data Integrity) tag for the
 * page as metadata for the page. arch_unmap_one() can save this
 * metadata on a swap-out of a page.
 */
static inline int arch_unmap_one(struct mm_struct *mm,
				  struct vm_area_struct *vma,
				  unsigned long addr,
				  pte_t orig_pte)
{
	return 0;
}
#endif

/*
 * Allow architectures to preserve additional metadata associated with
 * swapped-out pages. The corresponding __HAVE_ARCH_SWAP_* macros and function
 * prototypes must be defined in the arch-specific asm/pgtable.h file.
 */
#ifndef __HAVE_ARCH_PREPARE_TO_SWAP
static inline int arch_prepare_to_swap(struct folio *folio)
{
	return 0;
}
#endif

#ifndef __HAVE_ARCH_SWAP_INVALIDATE
static inline void arch_swap_invalidate_page(int type, pgoff_t offset)
{
}

static inline void arch_swap_invalidate_area(int type)
{
}
#endif

#ifndef __HAVE_ARCH_SWAP_RESTORE
static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
{
}
#endif

#ifndef __HAVE_ARCH_PGD_OFFSET_GATE
#define pgd_offset_gate(mm, addr)	pgd_offset(mm, addr)
#endif

#ifndef __HAVE_ARCH_MOVE_PTE
#define move_pte(pte, old_addr, new_addr)	(pte)
#endif

#ifndef pte_accessible
# define pte_accessible(mm, pte)	((void)(pte), 1)
#endif

#ifndef flush_tlb_fix_spurious_fault
#define flush_tlb_fix_spurious_fault(vma, address, ptep) flush_tlb_page(vma, address)
#endif

/*
 * When walking page tables, get the address of the next boundary,
 * or the end address of the range if that comes earlier.  Although no
 * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout.
 */

#define pgd_addr_end(addr, end)						\
({	unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK;	\
	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
})

#ifndef p4d_addr_end
#define p4d_addr_end(addr, end)						\
({	unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK;	\
	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
})
#endif

#ifndef pud_addr_end
#define pud_addr_end(addr, end)						\
({	unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK;	\
	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
})
#endif

#ifndef pmd_addr_end
#define pmd_addr_end(addr, end)						\
({	unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK;	\
	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
})
#endif

/*
 * When walking page tables, we usually want to skip any p?d_none entries;
 * and any p?d_bad entries - reporting the error before resetting to none.
 * Do the tests inline, but report and clear the bad entry in mm/memory.c.
 */
void pgd_clear_bad(pgd_t *);

#ifndef __PAGETABLE_P4D_FOLDED
void p4d_clear_bad(p4d_t *);
#else
#define p4d_clear_bad(p4d)        do { } while (0)
#endif

#ifndef __PAGETABLE_PUD_FOLDED
void pud_clear_bad(pud_t *);
#else
#define pud_clear_bad(p4d)        do { } while (0)
#endif

void pmd_clear_bad(pmd_t *);

static inline int pgd_none_or_clear_bad(pgd_t *pgd)
{
	if (pgd_none(*pgd))
		return 1;
	if (unlikely(pgd_bad(*pgd))) {
		pgd_clear_bad(pgd);
		return 1;
	}
	return 0;
}

static inline int p4d_none_or_clear_bad(p4d_t *p4d)
{
	if (p4d_none(*p4d))
		return 1;
	if (unlikely(p4d_bad(*p4d))) {
		p4d_clear_bad(p4d);
		return 1;
	}
	return 0;
}

static inline int pud_none_or_clear_bad(pud_t *pud)
{
	if (pud_none(*pud))
		return 1;
	if (unlikely(pud_bad(*pud))) {
		pud_clear_bad(pud);
		return 1;
	}
	return 0;
}

static inline int pmd_none_or_clear_bad(pmd_t *pmd)
{
	if (pmd_none(*pmd))
		return 1;
	if (unlikely(pmd_bad(*pmd))) {
		pmd_clear_bad(pmd);
		return 1;
	}
	return 0;
}

static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma,
					     unsigned long addr,
					     pte_t *ptep)
{
	/*
	 * Get the current pte state, but zero it out to make it
	 * non-present, preventing the hardware from asynchronously
	 * updating it.
	 */
	return ptep_get_and_clear(vma->vm_mm, addr, ptep);
}

static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma,
					     unsigned long addr,
					     pte_t *ptep, pte_t pte)
{
	/*
	 * The pte is non-present, so there's no hardware state to
	 * preserve.
	 */
	set_pte_at(vma->vm_mm, addr, ptep, pte);
}

#ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
/*
 * Start a pte protection read-modify-write transaction, which
 * protects against asynchronous hardware modifications to the pte.
 * The intention is not to prevent the hardware from making pte
 * updates, but to prevent any updates it may make from being lost.
 *
 * This does not protect against other software modifications of the
 * pte; the appropriate pte lock must be held over the transaction.
 *
 * Note that this interface is intended to be batchable, meaning that
 * ptep_modify_prot_commit may not actually update the pte, but merely
 * queue the update to be done at some later time.  The update must be
 * actually committed before the pte lock is released, however.
 */
static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
					   unsigned long addr,
					   pte_t *ptep)
{
	return __ptep_modify_prot_start(vma, addr, ptep);
}

/*
 * Commit an update to a pte, leaving any hardware-controlled bits in
 * the PTE unmodified.
 */
static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
					   unsigned long addr,
					   pte_t *ptep, pte_t old_pte, pte_t pte)
{
	__ptep_modify_prot_commit(vma, addr, ptep, pte);
}
#endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
#endif /* CONFIG_MMU */

/*
 * No-op macros that just return the current protection value. Defined here
 * because these macros can be used even if CONFIG_MMU is not defined.
 */

#ifndef pgprot_nx
#define pgprot_nx(prot)	(prot)
#endif

#ifndef pgprot_noncached
#define pgprot_noncached(prot)	(prot)
#endif

#ifndef pgprot_writecombine
#define pgprot_writecombine pgprot_noncached
#endif

#ifndef pgprot_writethrough
#define pgprot_writethrough pgprot_noncached
#endif

#ifndef pgprot_device
#define pgprot_device pgprot_noncached
#endif

#ifndef pgprot_mhp
#define pgprot_mhp(prot)	(prot)
#endif

#ifdef CONFIG_MMU
#ifndef pgprot_modify
#define pgprot_modify pgprot_modify
static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
{
	if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot)))
		newprot = pgprot_noncached(newprot);
	if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot)))
		newprot = pgprot_writecombine(newprot);
	if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot)))
		newprot = pgprot_device(newprot);
	return newprot;
}
#endif
#endif /* CONFIG_MMU */

#ifndef pgprot_encrypted
#define pgprot_encrypted(prot)	(prot)
#endif

#ifndef pgprot_decrypted
#define pgprot_decrypted(prot)	(prot)
#endif

/*
 * A facility to provide batching of the reload of page tables and
 * other process state with the actual context switch code for
 * paravirtualized guests.  By convention, only one of the batched
 * update (lazy) modes (CPU, MMU) should be active at any given time,
 * entry should never be nested, and entry and exits should always be
 * paired.  This is for sanity of maintaining and reasoning about the
 * kernel code.  In this case, the exit (end of the context switch) is
 * in architecture-specific code, and so doesn't need a generic
 * definition.
 */
#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH
#define arch_start_context_switch(prev)	do {} while (0)
#endif

#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
#ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION
static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
{
	return pmd;
}

static inline int pmd_swp_soft_dirty(pmd_t pmd)
{
	return 0;
}

static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
{
	return pmd;
}
#endif
#else /* !CONFIG_HAVE_ARCH_SOFT_DIRTY */
static inline int pte_soft_dirty(pte_t pte)
{
	return 0;
}

static inline int pmd_soft_dirty(pmd_t pmd)
{
	return 0;
}

static inline pte_t pte_mksoft_dirty(pte_t pte)
{
	return pte;
}

static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
{
	return pmd;
}

static inline pte_t pte_clear_soft_dirty(pte_t pte)
{
	return pte;
}

static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd)
{
	return pmd;
}

static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
{
	return pte;
}

static inline int pte_swp_soft_dirty(pte_t pte)
{
	return 0;
}

static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
{
	return pte;
}

static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
{
	return pmd;
}

static inline int pmd_swp_soft_dirty(pmd_t pmd)
{
	return 0;
}

static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
{
	return pmd;
}
#endif

#ifndef __HAVE_PFNMAP_TRACKING
/*
 * Interfaces that can be used by architecture code to keep track of
 * memory type of pfn mappings specified by the remap_pfn_range,
 * vmf_insert_pfn.
 */

/*
 * track_pfn_remap is called when a _new_ pfn mapping is being established
 * by remap_pfn_range() for physical range indicated by pfn and size.
 */
static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
				  unsigned long pfn, unsigned long addr,
				  unsigned long size)
{
	return 0;
}

/*
 * track_pfn_insert is called when a _new_ single pfn is established
 * by vmf_insert_pfn().
 */
static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
				    pfn_t pfn)
{
}

/*
 * track_pfn_copy is called when vma that is covering the pfnmap gets
 * copied through copy_page_range().
 */
static inline int track_pfn_copy(struct vm_area_struct *vma)
{
	return 0;
}

/*
 * untrack_pfn is called while unmapping a pfnmap for a region.
 * untrack can be called for a specific region indicated by pfn and size or
 * can be for the entire vma (in which case pfn, size are zero).
 */
static inline void untrack_pfn(struct vm_area_struct *vma,
			       unsigned long pfn, unsigned long size,
			       bool mm_wr_locked)
{
}

/*
 * untrack_pfn_clear is called while mremapping a pfnmap for a new region
 * or fails to copy pgtable during duplicate vm area.
 */
static inline void untrack_pfn_clear(struct vm_area_struct *vma)
{
}
#else
extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
			   unsigned long pfn, unsigned long addr,
			   unsigned long size);
extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
			     pfn_t pfn);
extern int track_pfn_copy(struct vm_area_struct *vma);
extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
			unsigned long size, bool mm_wr_locked);
extern void untrack_pfn_clear(struct vm_area_struct *vma);
#endif

#ifdef CONFIG_MMU
#ifdef __HAVE_COLOR_ZERO_PAGE
static inline int is_zero_pfn(unsigned long pfn)
{
	extern unsigned long zero_pfn;
	unsigned long offset_from_zero_pfn = pfn - zero_pfn;
	return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
}

#define my_zero_pfn(addr)	page_to_pfn(ZERO_PAGE(addr))

#else
static inline int is_zero_pfn(unsigned long pfn)
{
	extern unsigned long zero_pfn;
	return pfn == zero_pfn;
}

static inline unsigned long my_zero_pfn(unsigned long addr)
{
	extern unsigned long zero_pfn;
	return zero_pfn;
}
#endif
#else
static inline int is_zero_pfn(unsigned long pfn)
{
	return 0;
}

static inline unsigned long my_zero_pfn(unsigned long addr)
{
	return 0;
}
#endif /* CONFIG_MMU */

#ifdef CONFIG_MMU

#ifndef CONFIG_TRANSPARENT_HUGEPAGE
static inline int pmd_trans_huge(pmd_t pmd)
{
	return 0;
}
#ifndef pmd_write
static inline int pmd_write(pmd_t pmd)
{
	BUG();
	return 0;
}
#endif /* pmd_write */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

#ifndef pud_write
static inline int pud_write(pud_t pud)
{
	BUG();
	return 0;
}
#endif /* pud_write */

#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE)
static inline int pmd_devmap(pmd_t pmd)
{
	return 0;
}
static inline int pud_devmap(pud_t pud)
{
	return 0;
}
static inline int pgd_devmap(pgd_t pgd)
{
	return 0;
}
#endif

#if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \
	!defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
static inline int pud_trans_huge(pud_t pud)
{
	return 0;
}
#endif

static inline int pud_trans_unstable(pud_t *pud)
{
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
	pud_t pudval = READ_ONCE(*pud);

	if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval))
		return 1;
	if (unlikely(pud_bad(pudval))) {
		pud_clear_bad(pud);
		return 1;
	}
#endif
	return 0;
}

#ifndef CONFIG_NUMA_BALANCING
/*
 * In an inaccessible (PROT_NONE) VMA, pte_protnone() may indicate "yes". It is
 * perfectly valid to indicate "no" in that case, which is why our default
 * implementation defaults to "always no".
 *
 * In an accessible VMA, however, pte_protnone() reliably indicates PROT_NONE
 * page protection due to NUMA hinting. NUMA hinting faults only apply in
 * accessible VMAs.
 *
 * So, to reliably identify PROT_NONE PTEs that require a NUMA hinting fault,
 * looking at the VMA accessibility is sufficient.
 */
static inline int pte_protnone(pte_t pte)
{
	return 0;
}

static inline int pmd_protnone(pmd_t pmd)
{
	return 0;
}
#endif /* CONFIG_NUMA_BALANCING */

#endif /* CONFIG_MMU */

#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP

#ifndef __PAGETABLE_P4D_FOLDED
int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot);
void p4d_clear_huge(p4d_t *p4d);
#else
static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
{
	return 0;
}
static inline void p4d_clear_huge(p4d_t *p4d) { }
#endif /* !__PAGETABLE_P4D_FOLDED */

int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
int pud_clear_huge(pud_t *pud);
int pmd_clear_huge(pmd_t *pmd);
int p4d_free_pud_page(p4d_t *p4d, unsigned long addr);
int pud_free_pmd_page(pud_t *pud, unsigned long addr);
int pmd_free_pte_page(pmd_t *pmd, unsigned long addr);
#else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
{
	return 0;
}
static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
{
	return 0;
}
static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
{
	return 0;
}
static inline void p4d_clear_huge(p4d_t *p4d) { }
static inline int pud_clear_huge(pud_t *pud)
{
	return 0;
}
static inline int pmd_clear_huge(pmd_t *pmd)
{
	return 0;
}
static inline int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
{
	return 0;
}
static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr)
{
	return 0;
}
static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
{
	return 0;
}
#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */

#ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
 * ARCHes with special requirements for evicting THP backing TLB entries can
 * implement this. Otherwise also, it can help optimize normal TLB flush in
 * THP regime. Stock flush_tlb_range() typically has optimization to nuke the
 * entire TLB if flush span is greater than a threshold, which will
 * likely be true for a single huge page. Thus a single THP flush will
 * invalidate the entire TLB which is not desirable.
 * e.g. see arch/arc: flush_pmd_tlb_range
 */
#define flush_pmd_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
#define flush_pud_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
#else
#define flush_pmd_tlb_range(vma, addr, end)	BUILD_BUG()
#define flush_pud_tlb_range(vma, addr, end)	BUILD_BUG()
#endif
#endif

struct file;
int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
			unsigned long size, pgprot_t *vma_prot);

#ifndef CONFIG_X86_ESPFIX64
static inline void init_espfix_bsp(void) { }
#endif

extern void __init pgtable_cache_init(void);

#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
{
	return true;
}

static inline bool arch_has_pfn_modify_check(void)
{
	return false;
}
#endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */

/*
 * Architecture PAGE_KERNEL_* fallbacks
 *
 * Some architectures don't define certain PAGE_KERNEL_* flags. This is either
 * because they really don't support them, or the port needs to be updated to
 * reflect the required functionality. Below are a set of relatively safe
 * fallbacks, as best effort, which we can count on in lieu of the architectures
 * not defining them on their own yet.
 */

#ifndef PAGE_KERNEL_RO
# define PAGE_KERNEL_RO PAGE_KERNEL
#endif

#ifndef PAGE_KERNEL_EXEC
# define PAGE_KERNEL_EXEC PAGE_KERNEL
#endif

/*
 * Page Table Modification bits for pgtbl_mod_mask.
 *
 * These are used by the p?d_alloc_track*() set of functions an in the generic
 * vmalloc/ioremap code to track at which page-table levels entries have been
 * modified. Based on that the code can better decide when vmalloc and ioremap
 * mapping changes need to be synchronized to other page-tables in the system.
 */
#define		__PGTBL_PGD_MODIFIED	0
#define		__PGTBL_P4D_MODIFIED	1
#define		__PGTBL_PUD_MODIFIED	2
#define		__PGTBL_PMD_MODIFIED	3
#define		__PGTBL_PTE_MODIFIED	4

#define		PGTBL_PGD_MODIFIED	BIT(__PGTBL_PGD_MODIFIED)
#define		PGTBL_P4D_MODIFIED	BIT(__PGTBL_P4D_MODIFIED)
#define		PGTBL_PUD_MODIFIED	BIT(__PGTBL_PUD_MODIFIED)
#define		PGTBL_PMD_MODIFIED	BIT(__PGTBL_PMD_MODIFIED)
#define		PGTBL_PTE_MODIFIED	BIT(__PGTBL_PTE_MODIFIED)

/* Page-Table Modification Mask */
typedef unsigned int pgtbl_mod_mask;

#endif /* !__ASSEMBLY__ */

#if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT)
#ifdef CONFIG_PHYS_ADDR_T_64BIT
/*
 * ZSMALLOC needs to know the highest PFN on 32-bit architectures
 * with physical address space extension, but falls back to
 * BITS_PER_LONG otherwise.
 */
#error Missing MAX_POSSIBLE_PHYSMEM_BITS definition
#else
#define MAX_POSSIBLE_PHYSMEM_BITS 32
#endif
#endif

#ifndef has_transparent_hugepage
#define has_transparent_hugepage() IS_BUILTIN(CONFIG_TRANSPARENT_HUGEPAGE)
#endif

#ifndef has_transparent_pud_hugepage
#define has_transparent_pud_hugepage() IS_BUILTIN(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
#endif
/*
 * On some architectures it depends on the mm if the p4d/pud or pmd
 * layer of the page table hierarchy is folded or not.
 */
#ifndef mm_p4d_folded
#define mm_p4d_folded(mm)	__is_defined(__PAGETABLE_P4D_FOLDED)
#endif

#ifndef mm_pud_folded
#define mm_pud_folded(mm)	__is_defined(__PAGETABLE_PUD_FOLDED)
#endif

#ifndef mm_pmd_folded
#define mm_pmd_folded(mm)	__is_defined(__PAGETABLE_PMD_FOLDED)
#endif

#ifndef p4d_offset_lockless
#define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address)
#endif
#ifndef pud_offset_lockless
#define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address)
#endif
#ifndef pmd_offset_lockless
#define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address)
#endif

/*
 * pXd_leaf() is the API to check whether a pgtable entry is a huge page
 * mapping.  It should work globally across all archs, without any
 * dependency on CONFIG_* options.  For architectures that do not support
 * huge mappings on specific levels, below fallbacks will be used.
 *
 * A leaf pgtable entry should always imply the following:
 *
 * - It is a "present" entry.  IOW, before using this API, please check it
 *   with pXd_present() first. NOTE: it may not always mean the "present
 *   bit" is set.  For example, PROT_NONE entries are always "present".
 *
 * - It should _never_ be a swap entry of any type.  Above "present" check
 *   should have guarded this, but let's be crystal clear on this.
 *
 * - It should contain a huge PFN, which points to a huge page larger than
 *   PAGE_SIZE of the platform.  The PFN format isn't important here.
 *
 * - It should cover all kinds of huge mappings (e.g., pXd_trans_huge(),
 *   pXd_devmap(), or hugetlb mappings).
 */
#ifndef pgd_leaf
#define pgd_leaf(x)	false
#endif
#ifndef p4d_leaf
#define p4d_leaf(x)	false
#endif
#ifndef pud_leaf
#define pud_leaf(x)	false
#endif
#ifndef pmd_leaf
#define pmd_leaf(x)	false
#endif

#ifndef pgd_leaf_size
#define pgd_leaf_size(x) (1ULL << PGDIR_SHIFT)
#endif
#ifndef p4d_leaf_size
#define p4d_leaf_size(x) P4D_SIZE
#endif
#ifndef pud_leaf_size
#define pud_leaf_size(x) PUD_SIZE
#endif
#ifndef pmd_leaf_size
#define pmd_leaf_size(x) PMD_SIZE
#endif
#ifndef __pte_leaf_size
#ifndef pte_leaf_size
#define pte_leaf_size(x) PAGE_SIZE
#endif
#define __pte_leaf_size(x,y) pte_leaf_size(y)
#endif

/*
 * We always define pmd_pfn for all archs as it's used in lots of generic
 * code.  Now it happens too for pud_pfn (and can happen for larger
 * mappings too in the future; we're not there yet).  Instead of defining
 * it for all archs (like pmd_pfn), provide a fallback.
 *
 * Note that returning 0 here means any arch that didn't define this can
 * get severely wrong when it hits a real pud leaf.  It's arch's
 * responsibility to properly define it when a huge pud is possible.
 */
#ifndef pud_pfn
#define pud_pfn(x) 0
#endif

/*
 * Some architectures have MMUs that are configurable or selectable at boot
 * time. These lead to variable PTRS_PER_x. For statically allocated arrays it
 * helps to have a static maximum value.
 */

#ifndef MAX_PTRS_PER_PTE
#define MAX_PTRS_PER_PTE PTRS_PER_PTE
#endif

#ifndef MAX_PTRS_PER_PMD
#define MAX_PTRS_PER_PMD PTRS_PER_PMD
#endif

#ifndef MAX_PTRS_PER_PUD
#define MAX_PTRS_PER_PUD PTRS_PER_PUD
#endif

#ifndef MAX_PTRS_PER_P4D
#define MAX_PTRS_PER_P4D PTRS_PER_P4D
#endif

#ifndef pte_pgprot
#define pte_pgprot(x) ((pgprot_t) {0})
#endif

#ifndef pmd_pgprot
#define pmd_pgprot(x) ((pgprot_t) {0})
#endif

#ifndef pud_pgprot
#define pud_pgprot(x) ((pgprot_t) {0})
#endif

/* description of effects of mapping type and prot in current implementation.
 * this is due to the limited x86 page protection hardware.  The expected
 * behavior is in parens:
 *
 * map_type	prot
 *		PROT_NONE	PROT_READ	PROT_WRITE	PROT_EXEC
 * MAP_SHARED	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
 *		w: (no) no	w: (no) no	w: (yes) yes	w: (no) no
 *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
 *
 * MAP_PRIVATE	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
 *		w: (no) no	w: (no) no	w: (copy) copy	w: (no) no
 *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
 *
 * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and
 * MAP_PRIVATE (with Enhanced PAN supported):
 *								r: (no) no
 *								w: (no) no
 *								x: (yes) yes
 */
#define DECLARE_VM_GET_PAGE_PROT					\
pgprot_t vm_get_page_prot(unsigned long vm_flags)			\
{									\
		return protection_map[vm_flags &			\
			(VM_READ | VM_WRITE | VM_EXEC | VM_SHARED)];	\
}									\
EXPORT_SYMBOL(vm_get_page_prot);

#endif /* _LINUX_PGTABLE_H */