summaryrefslogtreecommitdiff
path: root/arch/x86/include/asm/pgtable.h
blob: 57bab91bbf504e58bf19a07c2b6186dd0628b9fd (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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_X86_PGTABLE_H
#define _ASM_X86_PGTABLE_H

#include <linux/mem_encrypt.h>
#include <asm/page.h>
#include <asm/pgtable_types.h>

/*
 * Macro to mark a page protection value as UC-
 */
#define pgprot_noncached(prot)						\
	((boot_cpu_data.x86 > 3)					\
	 ? (__pgprot(pgprot_val(prot) |					\
		     cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS)))	\
	 : (prot))

#ifndef __ASSEMBLY__
#include <linux/spinlock.h>
#include <asm/x86_init.h>
#include <asm/pkru.h>
#include <asm/fpu/api.h>
#include <asm/coco.h>
#include <asm-generic/pgtable_uffd.h>
#include <linux/page_table_check.h>

extern pgd_t early_top_pgt[PTRS_PER_PGD];
bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd);

struct seq_file;
void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm);
void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm,
				   bool user);
void ptdump_walk_pgd_level_checkwx(void);
void ptdump_walk_user_pgd_level_checkwx(void);

/*
 * Macros to add or remove encryption attribute
 */
#define pgprot_encrypted(prot)	__pgprot(cc_mkenc(pgprot_val(prot)))
#define pgprot_decrypted(prot)	__pgprot(cc_mkdec(pgprot_val(prot)))

#ifdef CONFIG_DEBUG_WX
#define debug_checkwx()		ptdump_walk_pgd_level_checkwx()
#define debug_checkwx_user()	ptdump_walk_user_pgd_level_checkwx()
#else
#define debug_checkwx()		do { } while (0)
#define debug_checkwx_user()	do { } while (0)
#endif

/*
 * ZERO_PAGE is a global shared page that is always zero: used
 * for zero-mapped memory areas etc..
 */
extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
	__visible;
#define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page))

extern spinlock_t pgd_lock;
extern struct list_head pgd_list;

extern struct mm_struct *pgd_page_get_mm(struct page *page);

extern pmdval_t early_pmd_flags;

#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
#else  /* !CONFIG_PARAVIRT_XXL */
#define set_pte(ptep, pte)		native_set_pte(ptep, pte)

#define set_pte_atomic(ptep, pte)					\
	native_set_pte_atomic(ptep, pte)

#define set_pmd(pmdp, pmd)		native_set_pmd(pmdp, pmd)

#ifndef __PAGETABLE_P4D_FOLDED
#define set_pgd(pgdp, pgd)		native_set_pgd(pgdp, pgd)
#define pgd_clear(pgd)			(pgtable_l5_enabled() ? native_pgd_clear(pgd) : 0)
#endif

#ifndef set_p4d
# define set_p4d(p4dp, p4d)		native_set_p4d(p4dp, p4d)
#endif

#ifndef __PAGETABLE_PUD_FOLDED
#define p4d_clear(p4d)			native_p4d_clear(p4d)
#endif

#ifndef set_pud
# define set_pud(pudp, pud)		native_set_pud(pudp, pud)
#endif

#ifndef __PAGETABLE_PUD_FOLDED
#define pud_clear(pud)			native_pud_clear(pud)
#endif

#define pte_clear(mm, addr, ptep)	native_pte_clear(mm, addr, ptep)
#define pmd_clear(pmd)			native_pmd_clear(pmd)

#define pgd_val(x)	native_pgd_val(x)
#define __pgd(x)	native_make_pgd(x)

#ifndef __PAGETABLE_P4D_FOLDED
#define p4d_val(x)	native_p4d_val(x)
#define __p4d(x)	native_make_p4d(x)
#endif

#ifndef __PAGETABLE_PUD_FOLDED
#define pud_val(x)	native_pud_val(x)
#define __pud(x)	native_make_pud(x)
#endif

#ifndef __PAGETABLE_PMD_FOLDED
#define pmd_val(x)	native_pmd_val(x)
#define __pmd(x)	native_make_pmd(x)
#endif

#define pte_val(x)	native_pte_val(x)
#define __pte(x)	native_make_pte(x)

#define arch_end_context_switch(prev)	do {} while(0)
#endif	/* CONFIG_PARAVIRT_XXL */

/*
 * The following only work if pte_present() is true.
 * Undefined behaviour if not..
 */
static inline bool pte_dirty(pte_t pte)
{
	return pte_flags(pte) & _PAGE_DIRTY_BITS;
}

static inline bool pte_shstk(pte_t pte)
{
	return cpu_feature_enabled(X86_FEATURE_SHSTK) &&
	       (pte_flags(pte) & (_PAGE_RW | _PAGE_DIRTY)) == _PAGE_DIRTY;
}

static inline int pte_young(pte_t pte)
{
	return pte_flags(pte) & _PAGE_ACCESSED;
}

static inline bool pmd_dirty(pmd_t pmd)
{
	return pmd_flags(pmd) & _PAGE_DIRTY_BITS;
}

static inline bool pmd_shstk(pmd_t pmd)
{
	return cpu_feature_enabled(X86_FEATURE_SHSTK) &&
	       (pmd_flags(pmd) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) ==
	       (_PAGE_DIRTY | _PAGE_PSE);
}

#define pmd_young pmd_young
static inline int pmd_young(pmd_t pmd)
{
	return pmd_flags(pmd) & _PAGE_ACCESSED;
}

static inline bool pud_dirty(pud_t pud)
{
	return pud_flags(pud) & _PAGE_DIRTY_BITS;
}

static inline int pud_young(pud_t pud)
{
	return pud_flags(pud) & _PAGE_ACCESSED;
}

static inline int pte_write(pte_t pte)
{
	/*
	 * Shadow stack pages are logically writable, but do not have
	 * _PAGE_RW.  Check for them separately from _PAGE_RW itself.
	 */
	return (pte_flags(pte) & _PAGE_RW) || pte_shstk(pte);
}

#define pmd_write pmd_write
static inline int pmd_write(pmd_t pmd)
{
	/*
	 * Shadow stack pages are logically writable, but do not have
	 * _PAGE_RW.  Check for them separately from _PAGE_RW itself.
	 */
	return (pmd_flags(pmd) & _PAGE_RW) || pmd_shstk(pmd);
}

#define pud_write pud_write
static inline int pud_write(pud_t pud)
{
	return pud_flags(pud) & _PAGE_RW;
}

static inline int pte_huge(pte_t pte)
{
	return pte_flags(pte) & _PAGE_PSE;
}

static inline int pte_global(pte_t pte)
{
	return pte_flags(pte) & _PAGE_GLOBAL;
}

static inline int pte_exec(pte_t pte)
{
	return !(pte_flags(pte) & _PAGE_NX);
}

static inline int pte_special(pte_t pte)
{
	return pte_flags(pte) & _PAGE_SPECIAL;
}

/* Entries that were set to PROT_NONE are inverted */

static inline u64 protnone_mask(u64 val);

#define PFN_PTE_SHIFT	PAGE_SHIFT

static inline unsigned long pte_pfn(pte_t pte)
{
	phys_addr_t pfn = pte_val(pte);
	pfn ^= protnone_mask(pfn);
	return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT;
}

static inline unsigned long pmd_pfn(pmd_t pmd)
{
	phys_addr_t pfn = pmd_val(pmd);
	pfn ^= protnone_mask(pfn);
	return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
}

static inline unsigned long pud_pfn(pud_t pud)
{
	phys_addr_t pfn = pud_val(pud);
	pfn ^= protnone_mask(pfn);
	return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT;
}

static inline unsigned long p4d_pfn(p4d_t p4d)
{
	return (p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT;
}

static inline unsigned long pgd_pfn(pgd_t pgd)
{
	return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT;
}

#define p4d_leaf	p4d_large
static inline int p4d_large(p4d_t p4d)
{
	/* No 512 GiB pages yet */
	return 0;
}

#define pte_page(pte)	pfn_to_page(pte_pfn(pte))

#define pmd_leaf	pmd_large
static inline int pmd_large(pmd_t pte)
{
	return pmd_flags(pte) & _PAGE_PSE;
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_large */
static inline int pmd_trans_huge(pmd_t pmd)
{
	return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
}

#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static inline int pud_trans_huge(pud_t pud)
{
	return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
}
#endif

#define has_transparent_hugepage has_transparent_hugepage
static inline int has_transparent_hugepage(void)
{
	return boot_cpu_has(X86_FEATURE_PSE);
}

#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
static inline int pmd_devmap(pmd_t pmd)
{
	return !!(pmd_val(pmd) & _PAGE_DEVMAP);
}

#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static inline int pud_devmap(pud_t pud)
{
	return !!(pud_val(pud) & _PAGE_DEVMAP);
}
#else
static inline int pud_devmap(pud_t pud)
{
	return 0;
}
#endif

static inline int pgd_devmap(pgd_t pgd)
{
	return 0;
}
#endif
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

static inline pte_t pte_set_flags(pte_t pte, pteval_t set)
{
	pteval_t v = native_pte_val(pte);

	return native_make_pte(v | set);
}

static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear)
{
	pteval_t v = native_pte_val(pte);

	return native_make_pte(v & ~clear);
}

/*
 * Write protection operations can result in Dirty=1,Write=0 PTEs. But in the
 * case of X86_FEATURE_USER_SHSTK, these PTEs denote shadow stack memory. So
 * when creating dirty, write-protected memory, a software bit is used:
 * _PAGE_BIT_SAVED_DIRTY. The following functions take a PTE and transition the
 * Dirty bit to SavedDirty, and vice-vesra.
 *
 * This shifting is only done if needed. In the case of shifting
 * Dirty->SavedDirty, the condition is if the PTE is Write=0. In the case of
 * shifting SavedDirty->Dirty, the condition is Write=1.
 */
static inline pgprotval_t mksaveddirty_shift(pgprotval_t v)
{
	pgprotval_t cond = (~v >> _PAGE_BIT_RW) & 1;

	v |= ((v >> _PAGE_BIT_DIRTY) & cond) << _PAGE_BIT_SAVED_DIRTY;
	v &= ~(cond << _PAGE_BIT_DIRTY);

	return v;
}

static inline pgprotval_t clear_saveddirty_shift(pgprotval_t v)
{
	pgprotval_t cond = (v >> _PAGE_BIT_RW) & 1;

	v |= ((v >> _PAGE_BIT_SAVED_DIRTY) & cond) << _PAGE_BIT_DIRTY;
	v &= ~(cond << _PAGE_BIT_SAVED_DIRTY);

	return v;
}

static inline pte_t pte_mksaveddirty(pte_t pte)
{
	pteval_t v = native_pte_val(pte);

	v = mksaveddirty_shift(v);
	return native_make_pte(v);
}

static inline pte_t pte_clear_saveddirty(pte_t pte)
{
	pteval_t v = native_pte_val(pte);

	v = clear_saveddirty_shift(v);
	return native_make_pte(v);
}

static inline pte_t pte_wrprotect(pte_t pte)
{
	pte = pte_clear_flags(pte, _PAGE_RW);

	/*
	 * Blindly clearing _PAGE_RW might accidentally create
	 * a shadow stack PTE (Write=0,Dirty=1). Move the hardware
	 * dirty value to the software bit, if present.
	 */
	return pte_mksaveddirty(pte);
}

#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
static inline int pte_uffd_wp(pte_t pte)
{
	bool wp = pte_flags(pte) & _PAGE_UFFD_WP;

#ifdef CONFIG_DEBUG_VM
	/*
	 * Having write bit for wr-protect-marked present ptes is fatal,
	 * because it means the uffd-wp bit will be ignored and write will
	 * just go through.
	 *
	 * Use any chance of pgtable walking to verify this (e.g., when
	 * page swapped out or being migrated for all purposes). It means
	 * something is already wrong.  Tell the admin even before the
	 * process crashes. We also nail it with wrong pgtable setup.
	 */
	WARN_ON_ONCE(wp && pte_write(pte));
#endif

	return wp;
}

static inline pte_t pte_mkuffd_wp(pte_t pte)
{
	return pte_wrprotect(pte_set_flags(pte, _PAGE_UFFD_WP));
}

static inline pte_t pte_clear_uffd_wp(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_UFFD_WP);
}
#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */

static inline pte_t pte_mkclean(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_DIRTY_BITS);
}

static inline pte_t pte_mkold(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_ACCESSED);
}

static inline pte_t pte_mkexec(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_NX);
}

static inline pte_t pte_mkdirty(pte_t pte)
{
	pte = pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);

	return pte_mksaveddirty(pte);
}

static inline pte_t pte_mkwrite_shstk(pte_t pte)
{
	pte = pte_clear_flags(pte, _PAGE_RW);

	return pte_set_flags(pte, _PAGE_DIRTY);
}

static inline pte_t pte_mkyoung(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_ACCESSED);
}

static inline pte_t pte_mkwrite_novma(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_RW);
}

struct vm_area_struct;
pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma);
#define pte_mkwrite pte_mkwrite

static inline pte_t pte_mkhuge(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_PSE);
}

static inline pte_t pte_clrhuge(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_PSE);
}

static inline pte_t pte_mkglobal(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_GLOBAL);
}

static inline pte_t pte_clrglobal(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_GLOBAL);
}

static inline pte_t pte_mkspecial(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_SPECIAL);
}

static inline pte_t pte_mkdevmap(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP);
}

static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set)
{
	pmdval_t v = native_pmd_val(pmd);

	return native_make_pmd(v | set);
}

static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
{
	pmdval_t v = native_pmd_val(pmd);

	return native_make_pmd(v & ~clear);
}

/* See comments above mksaveddirty_shift() */
static inline pmd_t pmd_mksaveddirty(pmd_t pmd)
{
	pmdval_t v = native_pmd_val(pmd);

	v = mksaveddirty_shift(v);
	return native_make_pmd(v);
}

/* See comments above mksaveddirty_shift() */
static inline pmd_t pmd_clear_saveddirty(pmd_t pmd)
{
	pmdval_t v = native_pmd_val(pmd);

	v = clear_saveddirty_shift(v);
	return native_make_pmd(v);
}

static inline pmd_t pmd_wrprotect(pmd_t pmd)
{
	pmd = pmd_clear_flags(pmd, _PAGE_RW);

	/*
	 * Blindly clearing _PAGE_RW might accidentally create
	 * a shadow stack PMD (RW=0, Dirty=1). Move the hardware
	 * dirty value to the software bit.
	 */
	return pmd_mksaveddirty(pmd);
}

#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
static inline int pmd_uffd_wp(pmd_t pmd)
{
	return pmd_flags(pmd) & _PAGE_UFFD_WP;
}

static inline pmd_t pmd_mkuffd_wp(pmd_t pmd)
{
	return pmd_wrprotect(pmd_set_flags(pmd, _PAGE_UFFD_WP));
}

static inline pmd_t pmd_clear_uffd_wp(pmd_t pmd)
{
	return pmd_clear_flags(pmd, _PAGE_UFFD_WP);
}
#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */

static inline pmd_t pmd_mkold(pmd_t pmd)
{
	return pmd_clear_flags(pmd, _PAGE_ACCESSED);
}

static inline pmd_t pmd_mkclean(pmd_t pmd)
{
	return pmd_clear_flags(pmd, _PAGE_DIRTY_BITS);
}

static inline pmd_t pmd_mkdirty(pmd_t pmd)
{
	pmd = pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);

	return pmd_mksaveddirty(pmd);
}

static inline pmd_t pmd_mkwrite_shstk(pmd_t pmd)
{
	pmd = pmd_clear_flags(pmd, _PAGE_RW);

	return pmd_set_flags(pmd, _PAGE_DIRTY);
}

static inline pmd_t pmd_mkdevmap(pmd_t pmd)
{
	return pmd_set_flags(pmd, _PAGE_DEVMAP);
}

static inline pmd_t pmd_mkhuge(pmd_t pmd)
{
	return pmd_set_flags(pmd, _PAGE_PSE);
}

static inline pmd_t pmd_mkyoung(pmd_t pmd)
{
	return pmd_set_flags(pmd, _PAGE_ACCESSED);
}

static inline pmd_t pmd_mkwrite_novma(pmd_t pmd)
{
	return pmd_set_flags(pmd, _PAGE_RW);
}

pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
#define pmd_mkwrite pmd_mkwrite

static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
{
	pudval_t v = native_pud_val(pud);

	return native_make_pud(v | set);
}

static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
{
	pudval_t v = native_pud_val(pud);

	return native_make_pud(v & ~clear);
}

/* See comments above mksaveddirty_shift() */
static inline pud_t pud_mksaveddirty(pud_t pud)
{
	pudval_t v = native_pud_val(pud);

	v = mksaveddirty_shift(v);
	return native_make_pud(v);
}

/* See comments above mksaveddirty_shift() */
static inline pud_t pud_clear_saveddirty(pud_t pud)
{
	pudval_t v = native_pud_val(pud);

	v = clear_saveddirty_shift(v);
	return native_make_pud(v);
}

static inline pud_t pud_mkold(pud_t pud)
{
	return pud_clear_flags(pud, _PAGE_ACCESSED);
}

static inline pud_t pud_mkclean(pud_t pud)
{
	return pud_clear_flags(pud, _PAGE_DIRTY_BITS);
}

static inline pud_t pud_wrprotect(pud_t pud)
{
	pud = pud_clear_flags(pud, _PAGE_RW);

	/*
	 * Blindly clearing _PAGE_RW might accidentally create
	 * a shadow stack PUD (RW=0, Dirty=1). Move the hardware
	 * dirty value to the software bit.
	 */
	return pud_mksaveddirty(pud);
}

static inline pud_t pud_mkdirty(pud_t pud)
{
	pud = pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);

	return pud_mksaveddirty(pud);
}

static inline pud_t pud_mkdevmap(pud_t pud)
{
	return pud_set_flags(pud, _PAGE_DEVMAP);
}

static inline pud_t pud_mkhuge(pud_t pud)
{
	return pud_set_flags(pud, _PAGE_PSE);
}

static inline pud_t pud_mkyoung(pud_t pud)
{
	return pud_set_flags(pud, _PAGE_ACCESSED);
}

static inline pud_t pud_mkwrite(pud_t pud)
{
	pud = pud_set_flags(pud, _PAGE_RW);

	return pud_clear_saveddirty(pud);
}

#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
static inline int pte_soft_dirty(pte_t pte)
{
	return pte_flags(pte) & _PAGE_SOFT_DIRTY;
}

static inline int pmd_soft_dirty(pmd_t pmd)
{
	return pmd_flags(pmd) & _PAGE_SOFT_DIRTY;
}

static inline int pud_soft_dirty(pud_t pud)
{
	return pud_flags(pud) & _PAGE_SOFT_DIRTY;
}

static inline pte_t pte_mksoft_dirty(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_SOFT_DIRTY);
}

static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
{
	return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);
}

static inline pud_t pud_mksoft_dirty(pud_t pud)
{
	return pud_set_flags(pud, _PAGE_SOFT_DIRTY);
}

static inline pte_t pte_clear_soft_dirty(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_SOFT_DIRTY);
}

static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd)
{
	return pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY);
}

static inline pud_t pud_clear_soft_dirty(pud_t pud)
{
	return pud_clear_flags(pud, _PAGE_SOFT_DIRTY);
}

#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */

/*
 * Mask out unsupported bits in a present pgprot.  Non-present pgprots
 * can use those bits for other purposes, so leave them be.
 */
static inline pgprotval_t massage_pgprot(pgprot_t pgprot)
{
	pgprotval_t protval = pgprot_val(pgprot);

	if (protval & _PAGE_PRESENT)
		protval &= __supported_pte_mask;

	return protval;
}

static inline pgprotval_t check_pgprot(pgprot_t pgprot)
{
	pgprotval_t massaged_val = massage_pgprot(pgprot);

	/* mmdebug.h can not be included here because of dependencies */
#ifdef CONFIG_DEBUG_VM
	WARN_ONCE(pgprot_val(pgprot) != massaged_val,
		  "attempted to set unsupported pgprot: %016llx "
		  "bits: %016llx supported: %016llx\n",
		  (u64)pgprot_val(pgprot),
		  (u64)pgprot_val(pgprot) ^ massaged_val,
		  (u64)__supported_pte_mask);
#endif

	return massaged_val;
}

static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
{
	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
	pfn ^= protnone_mask(pgprot_val(pgprot));
	pfn &= PTE_PFN_MASK;
	return __pte(pfn | check_pgprot(pgprot));
}

static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
{
	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
	pfn ^= protnone_mask(pgprot_val(pgprot));
	pfn &= PHYSICAL_PMD_PAGE_MASK;
	return __pmd(pfn | check_pgprot(pgprot));
}

static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
{
	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
	pfn ^= protnone_mask(pgprot_val(pgprot));
	pfn &= PHYSICAL_PUD_PAGE_MASK;
	return __pud(pfn | check_pgprot(pgprot));
}

static inline pmd_t pmd_mkinvalid(pmd_t pmd)
{
	return pfn_pmd(pmd_pfn(pmd),
		      __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE)));
}

static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask);

static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
	pteval_t val = pte_val(pte), oldval = val;
	pte_t pte_result;

	/*
	 * Chop off the NX bit (if present), and add the NX portion of
	 * the newprot (if present):
	 */
	val &= _PAGE_CHG_MASK;
	val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK;
	val = flip_protnone_guard(oldval, val, PTE_PFN_MASK);

	pte_result = __pte(val);

	/*
	 * To avoid creating Write=0,Dirty=1 PTEs, pte_modify() needs to avoid:
	 *  1. Marking Write=0 PTEs Dirty=1
	 *  2. Marking Dirty=1 PTEs Write=0
	 *
	 * The first case cannot happen because the _PAGE_CHG_MASK will filter
	 * out any Dirty bit passed in newprot. Handle the second case by
	 * going through the mksaveddirty exercise. Only do this if the old
	 * value was Write=1 to avoid doing this on Shadow Stack PTEs.
	 */
	if (oldval & _PAGE_RW)
		pte_result = pte_mksaveddirty(pte_result);
	else
		pte_result = pte_clear_saveddirty(pte_result);

	return pte_result;
}

static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
{
	pmdval_t val = pmd_val(pmd), oldval = val;
	pmd_t pmd_result;

	val &= (_HPAGE_CHG_MASK & ~_PAGE_DIRTY);
	val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK;
	val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK);

	pmd_result = __pmd(val);

	/*
	 * To avoid creating Write=0,Dirty=1 PMDs, pte_modify() needs to avoid:
	 *  1. Marking Write=0 PMDs Dirty=1
	 *  2. Marking Dirty=1 PMDs Write=0
	 *
	 * The first case cannot happen because the _PAGE_CHG_MASK will filter
	 * out any Dirty bit passed in newprot. Handle the second case by
	 * going through the mksaveddirty exercise. Only do this if the old
	 * value was Write=1 to avoid doing this on Shadow Stack PTEs.
	 */
	if (oldval & _PAGE_RW)
		pmd_result = pmd_mksaveddirty(pmd_result);
	else
		pmd_result = pmd_clear_saveddirty(pmd_result);

	return pmd_result;
}

/*
 * mprotect needs to preserve PAT and encryption bits when updating
 * vm_page_prot
 */
#define pgprot_modify pgprot_modify
static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
{
	pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK;
	pgprotval_t addbits = pgprot_val(newprot) & ~_PAGE_CHG_MASK;
	return __pgprot(preservebits | addbits);
}

#define pte_pgprot(x) __pgprot(pte_flags(x))
#define pmd_pgprot(x) __pgprot(pmd_flags(x))
#define pud_pgprot(x) __pgprot(pud_flags(x))
#define p4d_pgprot(x) __pgprot(p4d_flags(x))

#define canon_pgprot(p) __pgprot(massage_pgprot(p))

static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
					 enum page_cache_mode pcm,
					 enum page_cache_mode new_pcm)
{
	/*
	 * PAT type is always WB for untracked ranges, so no need to check.
	 */
	if (x86_platform.is_untracked_pat_range(paddr, paddr + size))
		return 1;

	/*
	 * Certain new memtypes are not allowed with certain
	 * requested memtype:
	 * - request is uncached, return cannot be write-back
	 * - request is write-combine, return cannot be write-back
	 * - request is write-through, return cannot be write-back
	 * - request is write-through, return cannot be write-combine
	 */
	if ((pcm == _PAGE_CACHE_MODE_UC_MINUS &&
	     new_pcm == _PAGE_CACHE_MODE_WB) ||
	    (pcm == _PAGE_CACHE_MODE_WC &&
	     new_pcm == _PAGE_CACHE_MODE_WB) ||
	    (pcm == _PAGE_CACHE_MODE_WT &&
	     new_pcm == _PAGE_CACHE_MODE_WB) ||
	    (pcm == _PAGE_CACHE_MODE_WT &&
	     new_pcm == _PAGE_CACHE_MODE_WC)) {
		return 0;
	}

	return 1;
}

pmd_t *populate_extra_pmd(unsigned long vaddr);
pte_t *populate_extra_pte(unsigned long vaddr);

#ifdef CONFIG_PAGE_TABLE_ISOLATION
pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd);

/*
 * Take a PGD location (pgdp) and a pgd value that needs to be set there.
 * Populates the user and returns the resulting PGD that must be set in
 * the kernel copy of the page tables.
 */
static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
{
	if (!static_cpu_has(X86_FEATURE_PTI))
		return pgd;
	return __pti_set_user_pgtbl(pgdp, pgd);
}
#else   /* CONFIG_PAGE_TABLE_ISOLATION */
static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
{
	return pgd;
}
#endif  /* CONFIG_PAGE_TABLE_ISOLATION */

#endif	/* __ASSEMBLY__ */


#ifdef CONFIG_X86_32
# include <asm/pgtable_32.h>
#else
# include <asm/pgtable_64.h>
#endif

#ifndef __ASSEMBLY__
#include <linux/mm_types.h>
#include <linux/mmdebug.h>
#include <linux/log2.h>
#include <asm/fixmap.h>

static inline int pte_none(pte_t pte)
{
	return !(pte.pte & ~(_PAGE_KNL_ERRATUM_MASK));
}

#define __HAVE_ARCH_PTE_SAME
static inline int pte_same(pte_t a, pte_t b)
{
	return a.pte == b.pte;
}

static inline pte_t pte_next_pfn(pte_t pte)
{
	if (__pte_needs_invert(pte_val(pte)))
		return __pte(pte_val(pte) - (1UL << PFN_PTE_SHIFT));
	return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
}
#define pte_next_pfn	pte_next_pfn

static inline int pte_present(pte_t a)
{
	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
}

#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
static inline int pte_devmap(pte_t a)
{
	return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP;
}
#endif

#define pte_accessible pte_accessible
static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
{
	if (pte_flags(a) & _PAGE_PRESENT)
		return true;

	if ((pte_flags(a) & _PAGE_PROTNONE) &&
			atomic_read(&mm->tlb_flush_pending))
		return true;

	return false;
}

static inline int pmd_present(pmd_t pmd)
{
	/*
	 * Checking for _PAGE_PSE is needed too because
	 * split_huge_page will temporarily clear the present bit (but
	 * the _PAGE_PSE flag will remain set at all times while the
	 * _PAGE_PRESENT bit is clear).
	 */
	return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE);
}

#ifdef CONFIG_NUMA_BALANCING
/*
 * These work without NUMA balancing but the kernel does not care. See the
 * comment in include/linux/pgtable.h
 */
static inline int pte_protnone(pte_t pte)
{
	return (pte_flags(pte) & (_PAGE_PROTNONE | _PAGE_PRESENT))
		== _PAGE_PROTNONE;
}

static inline int pmd_protnone(pmd_t pmd)
{
	return (pmd_flags(pmd) & (_PAGE_PROTNONE | _PAGE_PRESENT))
		== _PAGE_PROTNONE;
}
#endif /* CONFIG_NUMA_BALANCING */

static inline int pmd_none(pmd_t pmd)
{
	/* Only check low word on 32-bit platforms, since it might be
	   out of sync with upper half. */
	unsigned long val = native_pmd_val(pmd);
	return (val & ~_PAGE_KNL_ERRATUM_MASK) == 0;
}

static inline unsigned long pmd_page_vaddr(pmd_t pmd)
{
	return (unsigned long)__va(pmd_val(pmd) & pmd_pfn_mask(pmd));
}

/*
 * Currently stuck as a macro due to indirect forward reference to
 * linux/mmzone.h's __section_mem_map_addr() definition:
 */
#define pmd_page(pmd)	pfn_to_page(pmd_pfn(pmd))

/*
 * Conversion functions: convert a page and protection to a page entry,
 * and a page entry and page directory to the page they refer to.
 *
 * (Currently stuck as a macro because of indirect forward reference
 * to linux/mm.h:page_to_nid())
 */
#define mk_pte(page, pgprot)						  \
({									  \
	pgprot_t __pgprot = pgprot;					  \
									  \
	WARN_ON_ONCE((pgprot_val(__pgprot) & (_PAGE_DIRTY | _PAGE_RW)) == \
		    _PAGE_DIRTY);					  \
	pfn_pte(page_to_pfn(page), __pgprot);				  \
})

static inline int pmd_bad(pmd_t pmd)
{
	return (pmd_flags(pmd) & ~(_PAGE_USER | _PAGE_ACCESSED)) !=
	       (_KERNPG_TABLE & ~_PAGE_ACCESSED);
}

static inline unsigned long pages_to_mb(unsigned long npg)
{
	return npg >> (20 - PAGE_SHIFT);
}

#if CONFIG_PGTABLE_LEVELS > 2
static inline int pud_none(pud_t pud)
{
	return (native_pud_val(pud) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0;
}

static inline int pud_present(pud_t pud)
{
	return pud_flags(pud) & _PAGE_PRESENT;
}

static inline pmd_t *pud_pgtable(pud_t pud)
{
	return (pmd_t *)__va(pud_val(pud) & pud_pfn_mask(pud));
}

/*
 * Currently stuck as a macro due to indirect forward reference to
 * linux/mmzone.h's __section_mem_map_addr() definition:
 */
#define pud_page(pud)	pfn_to_page(pud_pfn(pud))

#define pud_leaf	pud_large
static inline int pud_large(pud_t pud)
{
	return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) ==
		(_PAGE_PSE | _PAGE_PRESENT);
}

static inline int pud_bad(pud_t pud)
{
	return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
}
#else
#define pud_leaf	pud_large
static inline int pud_large(pud_t pud)
{
	return 0;
}
#endif	/* CONFIG_PGTABLE_LEVELS > 2 */

#if CONFIG_PGTABLE_LEVELS > 3
static inline int p4d_none(p4d_t p4d)
{
	return (native_p4d_val(p4d) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0;
}

static inline int p4d_present(p4d_t p4d)
{
	return p4d_flags(p4d) & _PAGE_PRESENT;
}

static inline pud_t *p4d_pgtable(p4d_t p4d)
{
	return (pud_t *)__va(p4d_val(p4d) & p4d_pfn_mask(p4d));
}

/*
 * Currently stuck as a macro due to indirect forward reference to
 * linux/mmzone.h's __section_mem_map_addr() definition:
 */
#define p4d_page(p4d)	pfn_to_page(p4d_pfn(p4d))

static inline int p4d_bad(p4d_t p4d)
{
	unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER;

	if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
		ignore_flags |= _PAGE_NX;

	return (p4d_flags(p4d) & ~ignore_flags) != 0;
}
#endif  /* CONFIG_PGTABLE_LEVELS > 3 */

static inline unsigned long p4d_index(unsigned long address)
{
	return (address >> P4D_SHIFT) & (PTRS_PER_P4D - 1);
}

#if CONFIG_PGTABLE_LEVELS > 4
static inline int pgd_present(pgd_t pgd)
{
	if (!pgtable_l5_enabled())
		return 1;
	return pgd_flags(pgd) & _PAGE_PRESENT;
}

static inline unsigned long pgd_page_vaddr(pgd_t pgd)
{
	return (unsigned long)__va((unsigned long)pgd_val(pgd) & PTE_PFN_MASK);
}

/*
 * Currently stuck as a macro due to indirect forward reference to
 * linux/mmzone.h's __section_mem_map_addr() definition:
 */
#define pgd_page(pgd)	pfn_to_page(pgd_pfn(pgd))

/* to find an entry in a page-table-directory. */
static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
{
	if (!pgtable_l5_enabled())
		return (p4d_t *)pgd;
	return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address);
}

static inline int pgd_bad(pgd_t pgd)
{
	unsigned long ignore_flags = _PAGE_USER;

	if (!pgtable_l5_enabled())
		return 0;

	if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
		ignore_flags |= _PAGE_NX;

	return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
}

static inline int pgd_none(pgd_t pgd)
{
	if (!pgtable_l5_enabled())
		return 0;
	/*
	 * There is no need to do a workaround for the KNL stray
	 * A/D bit erratum here.  PGDs only point to page tables
	 * except on 32-bit non-PAE which is not supported on
	 * KNL.
	 */
	return !native_pgd_val(pgd);
}
#endif	/* CONFIG_PGTABLE_LEVELS > 4 */

#endif	/* __ASSEMBLY__ */

#define KERNEL_PGD_BOUNDARY	pgd_index(PAGE_OFFSET)
#define KERNEL_PGD_PTRS		(PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)

#ifndef __ASSEMBLY__

extern int direct_gbpages;
void init_mem_mapping(void);
void early_alloc_pgt_buf(void);
extern void memblock_find_dma_reserve(void);
void __init poking_init(void);
unsigned long init_memory_mapping(unsigned long start,
				  unsigned long end, pgprot_t prot);

#ifdef CONFIG_X86_64
extern pgd_t trampoline_pgd_entry;
#endif

/* local pte updates need not use xchg for locking */
static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
{
	pte_t res = *ptep;

	/* Pure native function needs no input for mm, addr */
	native_pte_clear(NULL, 0, ptep);
	return res;
}

static inline pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp)
{
	pmd_t res = *pmdp;

	native_pmd_clear(pmdp);
	return res;
}

static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp)
{
	pud_t res = *pudp;

	native_pud_clear(pudp);
	return res;
}

static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
			      pmd_t *pmdp, pmd_t pmd)
{
	page_table_check_pmd_set(mm, pmdp, pmd);
	set_pmd(pmdp, pmd);
}

static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
			      pud_t *pudp, pud_t pud)
{
	page_table_check_pud_set(mm, pudp, pud);
	native_set_pud(pudp, pud);
}

/*
 * We only update the dirty/accessed state if we set
 * the dirty bit by hand in the kernel, since the hardware
 * will do the accessed bit for us, and we don't want to
 * race with other CPU's that might be updating the dirty
 * bit at the same time.
 */
struct vm_area_struct;

#define  __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);

#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
extern int ptep_test_and_clear_young(struct vm_area_struct *vma,
				     unsigned long addr, pte_t *ptep);

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

#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
				       pte_t *ptep)
{
	pte_t pte = native_ptep_get_and_clear(ptep);
	page_table_check_pte_clear(mm, pte);
	return pte;
}

#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
					    unsigned long addr, pte_t *ptep,
					    int full)
{
	pte_t pte;
	if (full) {
		/*
		 * Full address destruction in progress; paravirt does not
		 * care about updates and native needs no locking
		 */
		pte = native_local_ptep_get_and_clear(ptep);
		page_table_check_pte_clear(mm, pte);
	} else {
		pte = ptep_get_and_clear(mm, addr, ptep);
	}
	return pte;
}

#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm,
				      unsigned long addr, pte_t *ptep)
{
	/*
	 * Avoid accidentally creating shadow stack PTEs
	 * (Write=0,Dirty=1).  Use cmpxchg() to prevent races with
	 * the hardware setting Dirty=1.
	 */
	pte_t old_pte, new_pte;

	old_pte = READ_ONCE(*ptep);
	do {
		new_pte = pte_wrprotect(old_pte);
	} while (!try_cmpxchg((long *)&ptep->pte, (long *)&old_pte, *(long *)&new_pte));
}

#define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0)

#define mk_pmd(page, pgprot)   pfn_pmd(page_to_pfn(page), (pgprot))

#define  __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
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);

#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
				     unsigned long addr, pmd_t *pmdp);
extern int pudp_test_and_clear_young(struct vm_area_struct *vma,
				     unsigned long addr, pud_t *pudp);

#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
				  unsigned long address, pmd_t *pmdp);


#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr,
				       pmd_t *pmdp)
{
	pmd_t pmd = native_pmdp_get_and_clear(pmdp);

	page_table_check_pmd_clear(mm, pmd);

	return pmd;
}

#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR
static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
					unsigned long addr, pud_t *pudp)
{
	pud_t pud = native_pudp_get_and_clear(pudp);

	page_table_check_pud_clear(mm, pud);

	return pud;
}

#define __HAVE_ARCH_PMDP_SET_WRPROTECT
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
				      unsigned long addr, pmd_t *pmdp)
{
	/*
	 * Avoid accidentally creating shadow stack PTEs
	 * (Write=0,Dirty=1).  Use cmpxchg() to prevent races with
	 * the hardware setting Dirty=1.
	 */
	pmd_t old_pmd, new_pmd;

	old_pmd = READ_ONCE(*pmdp);
	do {
		new_pmd = pmd_wrprotect(old_pmd);
	} while (!try_cmpxchg((long *)pmdp, (long *)&old_pmd, *(long *)&new_pmd));
}

#ifndef pmdp_establish
#define pmdp_establish pmdp_establish
static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
		unsigned long address, pmd_t *pmdp, pmd_t pmd)
{
	page_table_check_pmd_set(vma->vm_mm, pmdp, pmd);
	if (IS_ENABLED(CONFIG_SMP)) {
		return xchg(pmdp, pmd);
	} else {
		pmd_t old = *pmdp;
		WRITE_ONCE(*pmdp, pmd);
		return old;
	}
}
#endif

#define __HAVE_ARCH_PMDP_INVALIDATE_AD
extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma,
				unsigned long address, pmd_t *pmdp);

/*
 * Page table pages are page-aligned.  The lower half of the top
 * level is used for userspace and the top half for the kernel.
 *
 * Returns true for parts of the PGD that map userspace and
 * false for the parts that map the kernel.
 */
static inline bool pgdp_maps_userspace(void *__ptr)
{
	unsigned long ptr = (unsigned long)__ptr;

	return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START);
}

#define pgd_leaf	pgd_large
static inline int pgd_large(pgd_t pgd) { return 0; }

#ifdef CONFIG_PAGE_TABLE_ISOLATION
/*
 * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
 * (8k-aligned and 8k in size).  The kernel one is at the beginning 4k and
 * the user one is in the last 4k.  To switch between them, you
 * just need to flip the 12th bit in their addresses.
 */
#define PTI_PGTABLE_SWITCH_BIT	PAGE_SHIFT

/*
 * This generates better code than the inline assembly in
 * __set_bit().
 */
static inline void *ptr_set_bit(void *ptr, int bit)
{
	unsigned long __ptr = (unsigned long)ptr;

	__ptr |= BIT(bit);
	return (void *)__ptr;
}
static inline void *ptr_clear_bit(void *ptr, int bit)
{
	unsigned long __ptr = (unsigned long)ptr;

	__ptr &= ~BIT(bit);
	return (void *)__ptr;
}

static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
{
	return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
}

static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
{
	return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
}

static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
{
	return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
}

static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
{
	return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
}
#endif /* CONFIG_PAGE_TABLE_ISOLATION */

/*
 * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
 *
 *  dst - pointer to pgd range anywhere on a pgd page
 *  src - ""
 *  count - the number of pgds to copy.
 *
 * dst and src can be on the same page, but the range must not overlap,
 * and must not cross a page boundary.
 */
static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
{
	memcpy(dst, src, count * sizeof(pgd_t));
#ifdef CONFIG_PAGE_TABLE_ISOLATION
	if (!static_cpu_has(X86_FEATURE_PTI))
		return;
	/* Clone the user space pgd as well */
	memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src),
	       count * sizeof(pgd_t));
#endif
}

#define PTE_SHIFT ilog2(PTRS_PER_PTE)
static inline int page_level_shift(enum pg_level level)
{
	return (PAGE_SHIFT - PTE_SHIFT) + level * PTE_SHIFT;
}
static inline unsigned long page_level_size(enum pg_level level)
{
	return 1UL << page_level_shift(level);
}
static inline unsigned long page_level_mask(enum pg_level level)
{
	return ~(page_level_size(level) - 1);
}

/*
 * The x86 doesn't have any external MMU info: the kernel page
 * tables contain all the necessary information.
 */
static inline void update_mmu_cache(struct vm_area_struct *vma,
		unsigned long addr, pte_t *ptep)
{
}
static inline void update_mmu_cache_range(struct vm_fault *vmf,
		struct vm_area_struct *vma, unsigned long addr,
		pte_t *ptep, unsigned int nr)
{
}
static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
		unsigned long addr, pmd_t *pmd)
{
}
static inline void update_mmu_cache_pud(struct vm_area_struct *vma,
		unsigned long addr, pud_t *pud)
{
}
static inline pte_t pte_swp_mkexclusive(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE);
}

static inline int pte_swp_exclusive(pte_t pte)
{
	return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE;
}

static inline pte_t pte_swp_clear_exclusive(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_SWP_EXCLUSIVE);
}

#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
}

static inline int pte_swp_soft_dirty(pte_t pte)
{
	return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
}

static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
}

#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
{
	return pmd_set_flags(pmd, _PAGE_SWP_SOFT_DIRTY);
}

static inline int pmd_swp_soft_dirty(pmd_t pmd)
{
	return pmd_flags(pmd) & _PAGE_SWP_SOFT_DIRTY;
}

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

#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
static inline pte_t pte_swp_mkuffd_wp(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_SWP_UFFD_WP);
}

static inline int pte_swp_uffd_wp(pte_t pte)
{
	return pte_flags(pte) & _PAGE_SWP_UFFD_WP;
}

static inline pte_t pte_swp_clear_uffd_wp(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_SWP_UFFD_WP);
}

static inline pmd_t pmd_swp_mkuffd_wp(pmd_t pmd)
{
	return pmd_set_flags(pmd, _PAGE_SWP_UFFD_WP);
}

static inline int pmd_swp_uffd_wp(pmd_t pmd)
{
	return pmd_flags(pmd) & _PAGE_SWP_UFFD_WP;
}

static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd)
{
	return pmd_clear_flags(pmd, _PAGE_SWP_UFFD_WP);
}
#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */

static inline u16 pte_flags_pkey(unsigned long pte_flags)
{
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
	/* ifdef to avoid doing 59-bit shift on 32-bit values */
	return (pte_flags & _PAGE_PKEY_MASK) >> _PAGE_BIT_PKEY_BIT0;
#else
	return 0;
#endif
}

static inline bool __pkru_allows_pkey(u16 pkey, bool write)
{
	u32 pkru = read_pkru();

	if (!__pkru_allows_read(pkru, pkey))
		return false;
	if (write && !__pkru_allows_write(pkru, pkey))
		return false;

	return true;
}

/*
 * 'pteval' can come from a PTE, PMD or PUD.  We only check
 * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the
 * same value on all 3 types.
 */
static inline bool __pte_access_permitted(unsigned long pteval, bool write)
{
	unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER;

	/*
	 * Write=0,Dirty=1 PTEs are shadow stack, which the kernel
	 * shouldn't generally allow access to, but since they
	 * are already Write=0, the below logic covers both cases.
	 */
	if (write)
		need_pte_bits |= _PAGE_RW;

	if ((pteval & need_pte_bits) != need_pte_bits)
		return 0;

	return __pkru_allows_pkey(pte_flags_pkey(pteval), write);
}

#define pte_access_permitted pte_access_permitted
static inline bool pte_access_permitted(pte_t pte, bool write)
{
	return __pte_access_permitted(pte_val(pte), write);
}

#define pmd_access_permitted pmd_access_permitted
static inline bool pmd_access_permitted(pmd_t pmd, bool write)
{
	return __pte_access_permitted(pmd_val(pmd), write);
}

#define pud_access_permitted pud_access_permitted
static inline bool pud_access_permitted(pud_t pud, bool write)
{
	return __pte_access_permitted(pud_val(pud), write);
}

#define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1
extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot);

static inline bool arch_has_pfn_modify_check(void)
{
	return boot_cpu_has_bug(X86_BUG_L1TF);
}

#define arch_has_hw_pte_young arch_has_hw_pte_young
static inline bool arch_has_hw_pte_young(void)
{
	return true;
}

#define arch_check_zapped_pte arch_check_zapped_pte
void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte);

#define arch_check_zapped_pmd arch_check_zapped_pmd
void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd);

#ifdef CONFIG_XEN_PV
#define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young
static inline bool arch_has_hw_nonleaf_pmd_young(void)
{
	return !cpu_feature_enabled(X86_FEATURE_XENPV);
}
#endif

#ifdef CONFIG_PAGE_TABLE_CHECK
static inline bool pte_user_accessible_page(pte_t pte)
{
	return (pte_val(pte) & _PAGE_PRESENT) && (pte_val(pte) & _PAGE_USER);
}

static inline bool pmd_user_accessible_page(pmd_t pmd)
{
	return pmd_leaf(pmd) && (pmd_val(pmd) & _PAGE_PRESENT) && (pmd_val(pmd) & _PAGE_USER);
}

static inline bool pud_user_accessible_page(pud_t pud)
{
	return pud_leaf(pud) && (pud_val(pud) & _PAGE_PRESENT) && (pud_val(pud) & _PAGE_USER);
}
#endif

#ifdef CONFIG_X86_SGX
int arch_memory_failure(unsigned long pfn, int flags);
#define arch_memory_failure arch_memory_failure

bool arch_is_platform_page(u64 paddr);
#define arch_is_platform_page arch_is_platform_page
#endif

#endif	/* __ASSEMBLY__ */

#endif /* _ASM_X86_PGTABLE_H */