summaryrefslogtreecommitdiff
path: root/arch/x86/mm/init_64.c
blob: e2942335d1437dc88747052208f34965dc0ef146 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  linux/arch/x86_64/mm/init.c
 *
 *  Copyright (C) 1995  Linus Torvalds
 *  Copyright (C) 2000  Pavel Machek <pavel@ucw.cz>
 *  Copyright (C) 2002,2003 Andi Kleen <ak@suse.de>
 */

#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/initrd.h>
#include <linux/pagemap.h>
#include <linux/memblock.h>
#include <linux/proc_fs.h>
#include <linux/pci.h>
#include <linux/pfn.h>
#include <linux/poison.h>
#include <linux/dma-mapping.h>
#include <linux/memory.h>
#include <linux/memory_hotplug.h>
#include <linux/memremap.h>
#include <linux/nmi.h>
#include <linux/gfp.h>
#include <linux/kcore.h>
#include <linux/bootmem_info.h>

#include <asm/processor.h>
#include <asm/bios_ebda.h>
#include <linux/uaccess.h>
#include <asm/pgalloc.h>
#include <asm/dma.h>
#include <asm/fixmap.h>
#include <asm/e820/api.h>
#include <asm/apic.h>
#include <asm/tlb.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/smp.h>
#include <asm/sections.h>
#include <asm/kdebug.h>
#include <asm/numa.h>
#include <asm/set_memory.h>
#include <asm/init.h>
#include <asm/uv/uv.h>
#include <asm/setup.h>
#include <asm/ftrace.h>

#include "mm_internal.h"

#include "ident_map.c"

#define DEFINE_POPULATE(fname, type1, type2, init)		\
static inline void fname##_init(struct mm_struct *mm,		\
		type1##_t *arg1, type2##_t *arg2, bool init)	\
{								\
	if (init)						\
		fname##_safe(mm, arg1, arg2);			\
	else							\
		fname(mm, arg1, arg2);				\
}

DEFINE_POPULATE(p4d_populate, p4d, pud, init)
DEFINE_POPULATE(pgd_populate, pgd, p4d, init)
DEFINE_POPULATE(pud_populate, pud, pmd, init)
DEFINE_POPULATE(pmd_populate_kernel, pmd, pte, init)

#define DEFINE_ENTRY(type1, type2, init)			\
static inline void set_##type1##_init(type1##_t *arg1,		\
			type2##_t arg2, bool init)		\
{								\
	if (init)						\
		set_##type1##_safe(arg1, arg2);			\
	else							\
		set_##type1(arg1, arg2);			\
}

DEFINE_ENTRY(p4d, p4d, init)
DEFINE_ENTRY(pud, pud, init)
DEFINE_ENTRY(pmd, pmd, init)
DEFINE_ENTRY(pte, pte, init)


/*
 * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
 * physical space so we can cache the place of the first one and move
 * around without checking the pgd every time.
 */

/* Bits supported by the hardware: */
pteval_t __supported_pte_mask __read_mostly = ~0;
/* Bits allowed in normal kernel mappings: */
pteval_t __default_kernel_pte_mask __read_mostly = ~0;
EXPORT_SYMBOL_GPL(__supported_pte_mask);
/* Used in PAGE_KERNEL_* macros which are reasonably used out-of-tree: */
EXPORT_SYMBOL(__default_kernel_pte_mask);

int force_personality32;

/*
 * noexec32=on|off
 * Control non executable heap for 32bit processes.
 * To control the stack too use noexec=off
 *
 * on	PROT_READ does not imply PROT_EXEC for 32-bit processes (default)
 * off	PROT_READ implies PROT_EXEC
 */
static int __init nonx32_setup(char *str)
{
	if (!strcmp(str, "on"))
		force_personality32 &= ~READ_IMPLIES_EXEC;
	else if (!strcmp(str, "off"))
		force_personality32 |= READ_IMPLIES_EXEC;
	return 1;
}
__setup("noexec32=", nonx32_setup);

static void sync_global_pgds_l5(unsigned long start, unsigned long end)
{
	unsigned long addr;

	for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
		const pgd_t *pgd_ref = pgd_offset_k(addr);
		struct page *page;

		/* Check for overflow */
		if (addr < start)
			break;

		if (pgd_none(*pgd_ref))
			continue;

		spin_lock(&pgd_lock);
		list_for_each_entry(page, &pgd_list, lru) {
			pgd_t *pgd;
			spinlock_t *pgt_lock;

			pgd = (pgd_t *)page_address(page) + pgd_index(addr);
			/* the pgt_lock only for Xen */
			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
			spin_lock(pgt_lock);

			if (!pgd_none(*pgd_ref) && !pgd_none(*pgd))
				BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));

			if (pgd_none(*pgd))
				set_pgd(pgd, *pgd_ref);

			spin_unlock(pgt_lock);
		}
		spin_unlock(&pgd_lock);
	}
}

static void sync_global_pgds_l4(unsigned long start, unsigned long end)
{
	unsigned long addr;

	for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
		pgd_t *pgd_ref = pgd_offset_k(addr);
		const p4d_t *p4d_ref;
		struct page *page;

		/*
		 * With folded p4d, pgd_none() is always false, we need to
		 * handle synchronization on p4d level.
		 */
		MAYBE_BUILD_BUG_ON(pgd_none(*pgd_ref));
		p4d_ref = p4d_offset(pgd_ref, addr);

		if (p4d_none(*p4d_ref))
			continue;

		spin_lock(&pgd_lock);
		list_for_each_entry(page, &pgd_list, lru) {
			pgd_t *pgd;
			p4d_t *p4d;
			spinlock_t *pgt_lock;

			pgd = (pgd_t *)page_address(page) + pgd_index(addr);
			p4d = p4d_offset(pgd, addr);
			/* the pgt_lock only for Xen */
			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
			spin_lock(pgt_lock);

			if (!p4d_none(*p4d_ref) && !p4d_none(*p4d))
				BUG_ON(p4d_pgtable(*p4d)
				       != p4d_pgtable(*p4d_ref));

			if (p4d_none(*p4d))
				set_p4d(p4d, *p4d_ref);

			spin_unlock(pgt_lock);
		}
		spin_unlock(&pgd_lock);
	}
}

/*
 * When memory was added make sure all the processes MM have
 * suitable PGD entries in the local PGD level page.
 */
static void sync_global_pgds(unsigned long start, unsigned long end)
{
	if (pgtable_l5_enabled())
		sync_global_pgds_l5(start, end);
	else
		sync_global_pgds_l4(start, end);
}

/*
 * NOTE: This function is marked __ref because it calls __init function
 * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
 */
static __ref void *spp_getpage(void)
{
	void *ptr;

	if (after_bootmem)
		ptr = (void *) get_zeroed_page(GFP_ATOMIC);
	else
		ptr = memblock_alloc(PAGE_SIZE, PAGE_SIZE);

	if (!ptr || ((unsigned long)ptr & ~PAGE_MASK)) {
		panic("set_pte_phys: cannot allocate page data %s\n",
			after_bootmem ? "after bootmem" : "");
	}

	pr_debug("spp_getpage %p\n", ptr);

	return ptr;
}

static p4d_t *fill_p4d(pgd_t *pgd, unsigned long vaddr)
{
	if (pgd_none(*pgd)) {
		p4d_t *p4d = (p4d_t *)spp_getpage();
		pgd_populate(&init_mm, pgd, p4d);
		if (p4d != p4d_offset(pgd, 0))
			printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n",
			       p4d, p4d_offset(pgd, 0));
	}
	return p4d_offset(pgd, vaddr);
}

static pud_t *fill_pud(p4d_t *p4d, unsigned long vaddr)
{
	if (p4d_none(*p4d)) {
		pud_t *pud = (pud_t *)spp_getpage();
		p4d_populate(&init_mm, p4d, pud);
		if (pud != pud_offset(p4d, 0))
			printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n",
			       pud, pud_offset(p4d, 0));
	}
	return pud_offset(p4d, vaddr);
}

static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr)
{
	if (pud_none(*pud)) {
		pmd_t *pmd = (pmd_t *) spp_getpage();
		pud_populate(&init_mm, pud, pmd);
		if (pmd != pmd_offset(pud, 0))
			printk(KERN_ERR "PAGETABLE BUG #02! %p <-> %p\n",
			       pmd, pmd_offset(pud, 0));
	}
	return pmd_offset(pud, vaddr);
}

static pte_t *fill_pte(pmd_t *pmd, unsigned long vaddr)
{
	if (pmd_none(*pmd)) {
		pte_t *pte = (pte_t *) spp_getpage();
		pmd_populate_kernel(&init_mm, pmd, pte);
		if (pte != pte_offset_kernel(pmd, 0))
			printk(KERN_ERR "PAGETABLE BUG #03!\n");
	}
	return pte_offset_kernel(pmd, vaddr);
}

static void __set_pte_vaddr(pud_t *pud, unsigned long vaddr, pte_t new_pte)
{
	pmd_t *pmd = fill_pmd(pud, vaddr);
	pte_t *pte = fill_pte(pmd, vaddr);

	set_pte(pte, new_pte);

	/*
	 * It's enough to flush this one mapping.
	 * (PGE mappings get flushed as well)
	 */
	flush_tlb_one_kernel(vaddr);
}

void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte)
{
	p4d_t *p4d = p4d_page + p4d_index(vaddr);
	pud_t *pud = fill_pud(p4d, vaddr);

	__set_pte_vaddr(pud, vaddr, new_pte);
}

void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
{
	pud_t *pud = pud_page + pud_index(vaddr);

	__set_pte_vaddr(pud, vaddr, new_pte);
}

void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
{
	pgd_t *pgd;
	p4d_t *p4d_page;

	pr_debug("set_pte_vaddr %lx to %lx\n", vaddr, native_pte_val(pteval));

	pgd = pgd_offset_k(vaddr);
	if (pgd_none(*pgd)) {
		printk(KERN_ERR
			"PGD FIXMAP MISSING, it should be setup in head.S!\n");
		return;
	}

	p4d_page = p4d_offset(pgd, 0);
	set_pte_vaddr_p4d(p4d_page, vaddr, pteval);
}

pmd_t * __init populate_extra_pmd(unsigned long vaddr)
{
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;

	pgd = pgd_offset_k(vaddr);
	p4d = fill_p4d(pgd, vaddr);
	pud = fill_pud(p4d, vaddr);
	return fill_pmd(pud, vaddr);
}

pte_t * __init populate_extra_pte(unsigned long vaddr)
{
	pmd_t *pmd;

	pmd = populate_extra_pmd(vaddr);
	return fill_pte(pmd, vaddr);
}

/*
 * Create large page table mappings for a range of physical addresses.
 */
static void __init __init_extra_mapping(unsigned long phys, unsigned long size,
					enum page_cache_mode cache)
{
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pgprot_t prot;

	pgprot_val(prot) = pgprot_val(PAGE_KERNEL_LARGE) |
		protval_4k_2_large(cachemode2protval(cache));
	BUG_ON((phys & ~PMD_MASK) || (size & ~PMD_MASK));
	for (; size; phys += PMD_SIZE, size -= PMD_SIZE) {
		pgd = pgd_offset_k((unsigned long)__va(phys));
		if (pgd_none(*pgd)) {
			p4d = (p4d_t *) spp_getpage();
			set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE |
						_PAGE_USER));
		}
		p4d = p4d_offset(pgd, (unsigned long)__va(phys));
		if (p4d_none(*p4d)) {
			pud = (pud_t *) spp_getpage();
			set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE |
						_PAGE_USER));
		}
		pud = pud_offset(p4d, (unsigned long)__va(phys));
		if (pud_none(*pud)) {
			pmd = (pmd_t *) spp_getpage();
			set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE |
						_PAGE_USER));
		}
		pmd = pmd_offset(pud, phys);
		BUG_ON(!pmd_none(*pmd));
		set_pmd(pmd, __pmd(phys | pgprot_val(prot)));
	}
}

void __init init_extra_mapping_wb(unsigned long phys, unsigned long size)
{
	__init_extra_mapping(phys, size, _PAGE_CACHE_MODE_WB);
}

void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
{
	__init_extra_mapping(phys, size, _PAGE_CACHE_MODE_UC);
}

/*
 * The head.S code sets up the kernel high mapping:
 *
 *   from __START_KERNEL_map to __START_KERNEL_map + size (== _end-_text)
 *
 * phys_base holds the negative offset to the kernel, which is added
 * to the compile time generated pmds. This results in invalid pmds up
 * to the point where we hit the physaddr 0 mapping.
 *
 * We limit the mappings to the region from _text to _brk_end.  _brk_end
 * is rounded up to the 2MB boundary. This catches the invalid pmds as
 * well, as they are located before _text:
 */
void __init cleanup_highmap(void)
{
	unsigned long vaddr = __START_KERNEL_map;
	unsigned long vaddr_end = __START_KERNEL_map + KERNEL_IMAGE_SIZE;
	unsigned long end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
	pmd_t *pmd = level2_kernel_pgt;

	/*
	 * Native path, max_pfn_mapped is not set yet.
	 * Xen has valid max_pfn_mapped set in
	 *	arch/x86/xen/mmu.c:xen_setup_kernel_pagetable().
	 */
	if (max_pfn_mapped)
		vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT);

	for (; vaddr + PMD_SIZE - 1 < vaddr_end; pmd++, vaddr += PMD_SIZE) {
		if (pmd_none(*pmd))
			continue;
		if (vaddr < (unsigned long) _text || vaddr > end)
			set_pmd(pmd, __pmd(0));
	}
}

/*
 * Create PTE level page table mapping for physical addresses.
 * It returns the last physical address mapped.
 */
static unsigned long __meminit
phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end,
	      pgprot_t prot, bool init)
{
	unsigned long pages = 0, paddr_next;
	unsigned long paddr_last = paddr_end;
	pte_t *pte;
	int i;

	pte = pte_page + pte_index(paddr);
	i = pte_index(paddr);

	for (; i < PTRS_PER_PTE; i++, paddr = paddr_next, pte++) {
		paddr_next = (paddr & PAGE_MASK) + PAGE_SIZE;
		if (paddr >= paddr_end) {
			if (!after_bootmem &&
			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
					     E820_TYPE_RAM) &&
			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
					     E820_TYPE_RESERVED_KERN))
				set_pte_init(pte, __pte(0), init);
			continue;
		}

		/*
		 * We will re-use the existing mapping.
		 * Xen for example has some special requirements, like mapping
		 * pagetable pages as RO. So assume someone who pre-setup
		 * these mappings are more intelligent.
		 */
		if (!pte_none(*pte)) {
			if (!after_bootmem)
				pages++;
			continue;
		}

		if (0)
			pr_info("   pte=%p addr=%lx pte=%016lx\n", pte, paddr,
				pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL).pte);
		pages++;
		set_pte_init(pte, pfn_pte(paddr >> PAGE_SHIFT, prot), init);
		paddr_last = (paddr & PAGE_MASK) + PAGE_SIZE;
	}

	update_page_count(PG_LEVEL_4K, pages);

	return paddr_last;
}

/*
 * Create PMD level page table mapping for physical addresses. The virtual
 * and physical address have to be aligned at this level.
 * It returns the last physical address mapped.
 */
static unsigned long __meminit
phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end,
	      unsigned long page_size_mask, pgprot_t prot, bool init)
{
	unsigned long pages = 0, paddr_next;
	unsigned long paddr_last = paddr_end;

	int i = pmd_index(paddr);

	for (; i < PTRS_PER_PMD; i++, paddr = paddr_next) {
		pmd_t *pmd = pmd_page + pmd_index(paddr);
		pte_t *pte;
		pgprot_t new_prot = prot;

		paddr_next = (paddr & PMD_MASK) + PMD_SIZE;
		if (paddr >= paddr_end) {
			if (!after_bootmem &&
			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
					     E820_TYPE_RAM) &&
			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
					     E820_TYPE_RESERVED_KERN))
				set_pmd_init(pmd, __pmd(0), init);
			continue;
		}

		if (!pmd_none(*pmd)) {
			if (!pmd_large(*pmd)) {
				spin_lock(&init_mm.page_table_lock);
				pte = (pte_t *)pmd_page_vaddr(*pmd);
				paddr_last = phys_pte_init(pte, paddr,
							   paddr_end, prot,
							   init);
				spin_unlock(&init_mm.page_table_lock);
				continue;
			}
			/*
			 * If we are ok with PG_LEVEL_2M mapping, then we will
			 * use the existing mapping,
			 *
			 * Otherwise, we will split the large page mapping but
			 * use the same existing protection bits except for
			 * large page, so that we don't violate Intel's TLB
			 * Application note (317080) which says, while changing
			 * the page sizes, new and old translations should
			 * not differ with respect to page frame and
			 * attributes.
			 */
			if (page_size_mask & (1 << PG_LEVEL_2M)) {
				if (!after_bootmem)
					pages++;
				paddr_last = paddr_next;
				continue;
			}
			new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
		}

		if (page_size_mask & (1<<PG_LEVEL_2M)) {
			pages++;
			spin_lock(&init_mm.page_table_lock);
			set_pte_init((pte_t *)pmd,
				     pfn_pte((paddr & PMD_MASK) >> PAGE_SHIFT,
					     __pgprot(pgprot_val(prot) | _PAGE_PSE)),
				     init);
			spin_unlock(&init_mm.page_table_lock);
			paddr_last = paddr_next;
			continue;
		}

		pte = alloc_low_page();
		paddr_last = phys_pte_init(pte, paddr, paddr_end, new_prot, init);

		spin_lock(&init_mm.page_table_lock);
		pmd_populate_kernel_init(&init_mm, pmd, pte, init);
		spin_unlock(&init_mm.page_table_lock);
	}
	update_page_count(PG_LEVEL_2M, pages);
	return paddr_last;
}

/*
 * Create PUD level page table mapping for physical addresses. The virtual
 * and physical address do not have to be aligned at this level. KASLR can
 * randomize virtual addresses up to this level.
 * It returns the last physical address mapped.
 */
static unsigned long __meminit
phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
	      unsigned long page_size_mask, pgprot_t _prot, bool init)
{
	unsigned long pages = 0, paddr_next;
	unsigned long paddr_last = paddr_end;
	unsigned long vaddr = (unsigned long)__va(paddr);
	int i = pud_index(vaddr);

	for (; i < PTRS_PER_PUD; i++, paddr = paddr_next) {
		pud_t *pud;
		pmd_t *pmd;
		pgprot_t prot = _prot;

		vaddr = (unsigned long)__va(paddr);
		pud = pud_page + pud_index(vaddr);
		paddr_next = (paddr & PUD_MASK) + PUD_SIZE;

		if (paddr >= paddr_end) {
			if (!after_bootmem &&
			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
					     E820_TYPE_RAM) &&
			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
					     E820_TYPE_RESERVED_KERN))
				set_pud_init(pud, __pud(0), init);
			continue;
		}

		if (!pud_none(*pud)) {
			if (!pud_large(*pud)) {
				pmd = pmd_offset(pud, 0);
				paddr_last = phys_pmd_init(pmd, paddr,
							   paddr_end,
							   page_size_mask,
							   prot, init);
				continue;
			}
			/*
			 * If we are ok with PG_LEVEL_1G mapping, then we will
			 * use the existing mapping.
			 *
			 * Otherwise, we will split the gbpage mapping but use
			 * the same existing protection  bits except for large
			 * page, so that we don't violate Intel's TLB
			 * Application note (317080) which says, while changing
			 * the page sizes, new and old translations should
			 * not differ with respect to page frame and
			 * attributes.
			 */
			if (page_size_mask & (1 << PG_LEVEL_1G)) {
				if (!after_bootmem)
					pages++;
				paddr_last = paddr_next;
				continue;
			}
			prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
		}

		if (page_size_mask & (1<<PG_LEVEL_1G)) {
			pages++;
			spin_lock(&init_mm.page_table_lock);

			prot = __pgprot(pgprot_val(prot) | __PAGE_KERNEL_LARGE);

			set_pte_init((pte_t *)pud,
				     pfn_pte((paddr & PUD_MASK) >> PAGE_SHIFT,
					     prot),
				     init);
			spin_unlock(&init_mm.page_table_lock);
			paddr_last = paddr_next;
			continue;
		}

		pmd = alloc_low_page();
		paddr_last = phys_pmd_init(pmd, paddr, paddr_end,
					   page_size_mask, prot, init);

		spin_lock(&init_mm.page_table_lock);
		pud_populate_init(&init_mm, pud, pmd, init);
		spin_unlock(&init_mm.page_table_lock);
	}

	update_page_count(PG_LEVEL_1G, pages);

	return paddr_last;
}

static unsigned long __meminit
phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
	      unsigned long page_size_mask, pgprot_t prot, bool init)
{
	unsigned long vaddr, vaddr_end, vaddr_next, paddr_next, paddr_last;

	paddr_last = paddr_end;
	vaddr = (unsigned long)__va(paddr);
	vaddr_end = (unsigned long)__va(paddr_end);

	if (!pgtable_l5_enabled())
		return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end,
				     page_size_mask, prot, init);

	for (; vaddr < vaddr_end; vaddr = vaddr_next) {
		p4d_t *p4d = p4d_page + p4d_index(vaddr);
		pud_t *pud;

		vaddr_next = (vaddr & P4D_MASK) + P4D_SIZE;
		paddr = __pa(vaddr);

		if (paddr >= paddr_end) {
			paddr_next = __pa(vaddr_next);
			if (!after_bootmem &&
			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
					     E820_TYPE_RAM) &&
			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
					     E820_TYPE_RESERVED_KERN))
				set_p4d_init(p4d, __p4d(0), init);
			continue;
		}

		if (!p4d_none(*p4d)) {
			pud = pud_offset(p4d, 0);
			paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end),
					page_size_mask, prot, init);
			continue;
		}

		pud = alloc_low_page();
		paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end),
					   page_size_mask, prot, init);

		spin_lock(&init_mm.page_table_lock);
		p4d_populate_init(&init_mm, p4d, pud, init);
		spin_unlock(&init_mm.page_table_lock);
	}

	return paddr_last;
}

static unsigned long __meminit
__kernel_physical_mapping_init(unsigned long paddr_start,
			       unsigned long paddr_end,
			       unsigned long page_size_mask,
			       pgprot_t prot, bool init)
{
	bool pgd_changed = false;
	unsigned long vaddr, vaddr_start, vaddr_end, vaddr_next, paddr_last;

	paddr_last = paddr_end;
	vaddr = (unsigned long)__va(paddr_start);
	vaddr_end = (unsigned long)__va(paddr_end);
	vaddr_start = vaddr;

	for (; vaddr < vaddr_end; vaddr = vaddr_next) {
		pgd_t *pgd = pgd_offset_k(vaddr);
		p4d_t *p4d;

		vaddr_next = (vaddr & PGDIR_MASK) + PGDIR_SIZE;

		if (pgd_val(*pgd)) {
			p4d = (p4d_t *)pgd_page_vaddr(*pgd);
			paddr_last = phys_p4d_init(p4d, __pa(vaddr),
						   __pa(vaddr_end),
						   page_size_mask,
						   prot, init);
			continue;
		}

		p4d = alloc_low_page();
		paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end),
					   page_size_mask, prot, init);

		spin_lock(&init_mm.page_table_lock);
		if (pgtable_l5_enabled())
			pgd_populate_init(&init_mm, pgd, p4d, init);
		else
			p4d_populate_init(&init_mm, p4d_offset(pgd, vaddr),
					  (pud_t *) p4d, init);

		spin_unlock(&init_mm.page_table_lock);
		pgd_changed = true;
	}

	if (pgd_changed)
		sync_global_pgds(vaddr_start, vaddr_end - 1);

	return paddr_last;
}


/*
 * Create page table mapping for the physical memory for specific physical
 * addresses. Note that it can only be used to populate non-present entries.
 * The virtual and physical addresses have to be aligned on PMD level
 * down. It returns the last physical address mapped.
 */
unsigned long __meminit
kernel_physical_mapping_init(unsigned long paddr_start,
			     unsigned long paddr_end,
			     unsigned long page_size_mask, pgprot_t prot)
{
	return __kernel_physical_mapping_init(paddr_start, paddr_end,
					      page_size_mask, prot, true);
}

/*
 * This function is similar to kernel_physical_mapping_init() above with the
 * exception that it uses set_{pud,pmd}() instead of the set_{pud,pte}_safe()
 * when updating the mapping. The caller is responsible to flush the TLBs after
 * the function returns.
 */
unsigned long __meminit
kernel_physical_mapping_change(unsigned long paddr_start,
			       unsigned long paddr_end,
			       unsigned long page_size_mask)
{
	return __kernel_physical_mapping_init(paddr_start, paddr_end,
					      page_size_mask, PAGE_KERNEL,
					      false);
}

#ifndef CONFIG_NUMA
void __init initmem_init(void)
{
	memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
}
#endif

void __init paging_init(void)
{
	sparse_init();

	/*
	 * clear the default setting with node 0
	 * note: don't use nodes_clear here, that is really clearing when
	 *	 numa support is not compiled in, and later node_set_state
	 *	 will not set it back.
	 */
	node_clear_state(0, N_MEMORY);
	node_clear_state(0, N_NORMAL_MEMORY);

	zone_sizes_init();
}

#ifdef CONFIG_SPARSEMEM_VMEMMAP
#define PAGE_UNUSED 0xFD

/*
 * The unused vmemmap range, which was not yet memset(PAGE_UNUSED), ranges
 * from unused_pmd_start to next PMD_SIZE boundary.
 */
static unsigned long unused_pmd_start __meminitdata;

static void __meminit vmemmap_flush_unused_pmd(void)
{
	if (!unused_pmd_start)
		return;
	/*
	 * Clears (unused_pmd_start, PMD_END]
	 */
	memset((void *)unused_pmd_start, PAGE_UNUSED,
	       ALIGN(unused_pmd_start, PMD_SIZE) - unused_pmd_start);
	unused_pmd_start = 0;
}

#ifdef CONFIG_MEMORY_HOTPLUG
/* Returns true if the PMD is completely unused and thus it can be freed */
static bool __meminit vmemmap_pmd_is_unused(unsigned long addr, unsigned long end)
{
	unsigned long start = ALIGN_DOWN(addr, PMD_SIZE);

	/*
	 * Flush the unused range cache to ensure that memchr_inv() will work
	 * for the whole range.
	 */
	vmemmap_flush_unused_pmd();
	memset((void *)addr, PAGE_UNUSED, end - addr);

	return !memchr_inv((void *)start, PAGE_UNUSED, PMD_SIZE);
}
#endif

static void __meminit __vmemmap_use_sub_pmd(unsigned long start)
{
	/*
	 * As we expect to add in the same granularity as we remove, it's
	 * sufficient to mark only some piece used to block the memmap page from
	 * getting removed when removing some other adjacent memmap (just in
	 * case the first memmap never gets initialized e.g., because the memory
	 * block never gets onlined).
	 */
	memset((void *)start, 0, sizeof(struct page));
}

static void __meminit vmemmap_use_sub_pmd(unsigned long start, unsigned long end)
{
	/*
	 * We only optimize if the new used range directly follows the
	 * previously unused range (esp., when populating consecutive sections).
	 */
	if (unused_pmd_start == start) {
		if (likely(IS_ALIGNED(end, PMD_SIZE)))
			unused_pmd_start = 0;
		else
			unused_pmd_start = end;
		return;
	}

	/*
	 * If the range does not contiguously follows previous one, make sure
	 * to mark the unused range of the previous one so it can be removed.
	 */
	vmemmap_flush_unused_pmd();
	__vmemmap_use_sub_pmd(start);
}


static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end)
{
	const unsigned long page = ALIGN_DOWN(start, PMD_SIZE);

	vmemmap_flush_unused_pmd();

	/*
	 * Could be our memmap page is filled with PAGE_UNUSED already from a
	 * previous remove. Make sure to reset it.
	 */
	__vmemmap_use_sub_pmd(start);

	/*
	 * Mark with PAGE_UNUSED the unused parts of the new memmap range
	 */
	if (!IS_ALIGNED(start, PMD_SIZE))
		memset((void *)page, PAGE_UNUSED, start - page);

	/*
	 * We want to avoid memset(PAGE_UNUSED) when populating the vmemmap of
	 * consecutive sections. Remember for the last added PMD where the
	 * unused range begins.
	 */
	if (!IS_ALIGNED(end, PMD_SIZE))
		unused_pmd_start = end;
}
#endif

/*
 * Memory hotplug specific functions
 */
#ifdef CONFIG_MEMORY_HOTPLUG
/*
 * After memory hotplug the variables max_pfn, max_low_pfn and high_memory need
 * updating.
 */
static void update_end_of_memory_vars(u64 start, u64 size)
{
	unsigned long end_pfn = PFN_UP(start + size);

	if (end_pfn > max_pfn) {
		max_pfn = end_pfn;
		max_low_pfn = end_pfn;
		high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
	}
}

int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
	      struct mhp_params *params)
{
	int ret;

	ret = __add_pages(nid, start_pfn, nr_pages, params);
	WARN_ON_ONCE(ret);

	/* update max_pfn, max_low_pfn and high_memory */
	update_end_of_memory_vars(start_pfn << PAGE_SHIFT,
				  nr_pages << PAGE_SHIFT);

	return ret;
}

int arch_add_memory(int nid, u64 start, u64 size,
		    struct mhp_params *params)
{
	unsigned long start_pfn = start >> PAGE_SHIFT;
	unsigned long nr_pages = size >> PAGE_SHIFT;

	init_memory_mapping(start, start + size, params->pgprot);

	return add_pages(nid, start_pfn, nr_pages, params);
}

static void __meminit free_pagetable(struct page *page, int order)
{
	unsigned long magic;
	unsigned int nr_pages = 1 << order;

	/* bootmem page has reserved flag */
	if (PageReserved(page)) {
		__ClearPageReserved(page);

		magic = page->index;
		if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
			while (nr_pages--)
				put_page_bootmem(page++);
		} else
			while (nr_pages--)
				free_reserved_page(page++);
	} else
		free_pages((unsigned long)page_address(page), order);
}

static void __meminit free_hugepage_table(struct page *page,
		struct vmem_altmap *altmap)
{
	if (altmap)
		vmem_altmap_free(altmap, PMD_SIZE / PAGE_SIZE);
	else
		free_pagetable(page, get_order(PMD_SIZE));
}

static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
{
	pte_t *pte;
	int i;

	for (i = 0; i < PTRS_PER_PTE; i++) {
		pte = pte_start + i;
		if (!pte_none(*pte))
			return;
	}

	/* free a pte talbe */
	free_pagetable(pmd_page(*pmd), 0);
	spin_lock(&init_mm.page_table_lock);
	pmd_clear(pmd);
	spin_unlock(&init_mm.page_table_lock);
}

static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
{
	pmd_t *pmd;
	int i;

	for (i = 0; i < PTRS_PER_PMD; i++) {
		pmd = pmd_start + i;
		if (!pmd_none(*pmd))
			return;
	}

	/* free a pmd talbe */
	free_pagetable(pud_page(*pud), 0);
	spin_lock(&init_mm.page_table_lock);
	pud_clear(pud);
	spin_unlock(&init_mm.page_table_lock);
}

static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d)
{
	pud_t *pud;
	int i;

	for (i = 0; i < PTRS_PER_PUD; i++) {
		pud = pud_start + i;
		if (!pud_none(*pud))
			return;
	}

	/* free a pud talbe */
	free_pagetable(p4d_page(*p4d), 0);
	spin_lock(&init_mm.page_table_lock);
	p4d_clear(p4d);
	spin_unlock(&init_mm.page_table_lock);
}

static void __meminit
remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
		 bool direct)
{
	unsigned long next, pages = 0;
	pte_t *pte;
	phys_addr_t phys_addr;

	pte = pte_start + pte_index(addr);
	for (; addr < end; addr = next, pte++) {
		next = (addr + PAGE_SIZE) & PAGE_MASK;
		if (next > end)
			next = end;

		if (!pte_present(*pte))
			continue;

		/*
		 * We mapped [0,1G) memory as identity mapping when
		 * initializing, in arch/x86/kernel/head_64.S. These
		 * pagetables cannot be removed.
		 */
		phys_addr = pte_val(*pte) + (addr & PAGE_MASK);
		if (phys_addr < (phys_addr_t)0x40000000)
			return;

		if (!direct)
			free_pagetable(pte_page(*pte), 0);

		spin_lock(&init_mm.page_table_lock);
		pte_clear(&init_mm, addr, pte);
		spin_unlock(&init_mm.page_table_lock);

		/* For non-direct mapping, pages means nothing. */
		pages++;
	}

	/* Call free_pte_table() in remove_pmd_table(). */
	flush_tlb_all();
	if (direct)
		update_page_count(PG_LEVEL_4K, -pages);
}

static void __meminit
remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
		 bool direct, struct vmem_altmap *altmap)
{
	unsigned long next, pages = 0;
	pte_t *pte_base;
	pmd_t *pmd;

	pmd = pmd_start + pmd_index(addr);
	for (; addr < end; addr = next, pmd++) {
		next = pmd_addr_end(addr, end);

		if (!pmd_present(*pmd))
			continue;

		if (pmd_large(*pmd)) {
			if (IS_ALIGNED(addr, PMD_SIZE) &&
			    IS_ALIGNED(next, PMD_SIZE)) {
				if (!direct)
					free_hugepage_table(pmd_page(*pmd),
							    altmap);

				spin_lock(&init_mm.page_table_lock);
				pmd_clear(pmd);
				spin_unlock(&init_mm.page_table_lock);
				pages++;
			}
#ifdef CONFIG_SPARSEMEM_VMEMMAP
			else if (vmemmap_pmd_is_unused(addr, next)) {
					free_hugepage_table(pmd_page(*pmd),
							    altmap);
					spin_lock(&init_mm.page_table_lock);
					pmd_clear(pmd);
					spin_unlock(&init_mm.page_table_lock);
			}
#endif
			continue;
		}

		pte_base = (pte_t *)pmd_page_vaddr(*pmd);
		remove_pte_table(pte_base, addr, next, direct);
		free_pte_table(pte_base, pmd);
	}

	/* Call free_pmd_table() in remove_pud_table(). */
	if (direct)
		update_page_count(PG_LEVEL_2M, -pages);
}

static void __meminit
remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
		 struct vmem_altmap *altmap, bool direct)
{
	unsigned long next, pages = 0;
	pmd_t *pmd_base;
	pud_t *pud;

	pud = pud_start + pud_index(addr);
	for (; addr < end; addr = next, pud++) {
		next = pud_addr_end(addr, end);

		if (!pud_present(*pud))
			continue;

		if (pud_large(*pud) &&
		    IS_ALIGNED(addr, PUD_SIZE) &&
		    IS_ALIGNED(next, PUD_SIZE)) {
			spin_lock(&init_mm.page_table_lock);
			pud_clear(pud);
			spin_unlock(&init_mm.page_table_lock);
			pages++;
			continue;
		}

		pmd_base = pmd_offset(pud, 0);
		remove_pmd_table(pmd_base, addr, next, direct, altmap);
		free_pmd_table(pmd_base, pud);
	}

	if (direct)
		update_page_count(PG_LEVEL_1G, -pages);
}

static void __meminit
remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end,
		 struct vmem_altmap *altmap, bool direct)
{
	unsigned long next, pages = 0;
	pud_t *pud_base;
	p4d_t *p4d;

	p4d = p4d_start + p4d_index(addr);
	for (; addr < end; addr = next, p4d++) {
		next = p4d_addr_end(addr, end);

		if (!p4d_present(*p4d))
			continue;

		BUILD_BUG_ON(p4d_large(*p4d));

		pud_base = pud_offset(p4d, 0);
		remove_pud_table(pud_base, addr, next, altmap, direct);
		/*
		 * For 4-level page tables we do not want to free PUDs, but in the
		 * 5-level case we should free them. This code will have to change
		 * to adapt for boot-time switching between 4 and 5 level page tables.
		 */
		if (pgtable_l5_enabled())
			free_pud_table(pud_base, p4d);
	}

	if (direct)
		update_page_count(PG_LEVEL_512G, -pages);
}

/* start and end are both virtual address. */
static void __meminit
remove_pagetable(unsigned long start, unsigned long end, bool direct,
		struct vmem_altmap *altmap)
{
	unsigned long next;
	unsigned long addr;
	pgd_t *pgd;
	p4d_t *p4d;

	for (addr = start; addr < end; addr = next) {
		next = pgd_addr_end(addr, end);

		pgd = pgd_offset_k(addr);
		if (!pgd_present(*pgd))
			continue;

		p4d = p4d_offset(pgd, 0);
		remove_p4d_table(p4d, addr, next, altmap, direct);
	}

	flush_tlb_all();
}

void __ref vmemmap_free(unsigned long start, unsigned long end,
		struct vmem_altmap *altmap)
{
	VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE));
	VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE));

	remove_pagetable(start, end, false, altmap);
}

static void __meminit
kernel_physical_mapping_remove(unsigned long start, unsigned long end)
{
	start = (unsigned long)__va(start);
	end = (unsigned long)__va(end);

	remove_pagetable(start, end, true, NULL);
}

void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
{
	unsigned long start_pfn = start >> PAGE_SHIFT;
	unsigned long nr_pages = size >> PAGE_SHIFT;

	__remove_pages(start_pfn, nr_pages, altmap);
	kernel_physical_mapping_remove(start, start + size);
}
#endif /* CONFIG_MEMORY_HOTPLUG */

static struct kcore_list kcore_vsyscall;

static void __init register_page_bootmem_info(void)
{
#if defined(CONFIG_NUMA) || defined(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP)
	int i;

	for_each_online_node(i)
		register_page_bootmem_info_node(NODE_DATA(i));
#endif
}

/*
 * Pre-allocates page-table pages for the vmalloc area in the kernel page-table.
 * Only the level which needs to be synchronized between all page-tables is
 * allocated because the synchronization can be expensive.
 */
static void __init preallocate_vmalloc_pages(void)
{
	unsigned long addr;
	const char *lvl;

	for (addr = VMALLOC_START; addr <= VMALLOC_END; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
		pgd_t *pgd = pgd_offset_k(addr);
		p4d_t *p4d;
		pud_t *pud;

		lvl = "p4d";
		p4d = p4d_alloc(&init_mm, pgd, addr);
		if (!p4d)
			goto failed;

		if (pgtable_l5_enabled())
			continue;

		/*
		 * The goal here is to allocate all possibly required
		 * hardware page tables pointed to by the top hardware
		 * level.
		 *
		 * On 4-level systems, the P4D layer is folded away and
		 * the above code does no preallocation.  Below, go down
		 * to the pud _software_ level to ensure the second
		 * hardware level is allocated on 4-level systems too.
		 */
		lvl = "pud";
		pud = pud_alloc(&init_mm, p4d, addr);
		if (!pud)
			goto failed;
	}

	return;

failed:

	/*
	 * The pages have to be there now or they will be missing in
	 * process page-tables later.
	 */
	panic("Failed to pre-allocate %s pages for vmalloc area\n", lvl);
}

void __init mem_init(void)
{
	pci_iommu_alloc();

	/* clear_bss() already clear the empty_zero_page */

	/* this will put all memory onto the freelists */
	memblock_free_all();
	after_bootmem = 1;
	x86_init.hyper.init_after_bootmem();

	/*
	 * Must be done after boot memory is put on freelist, because here we
	 * might set fields in deferred struct pages that have not yet been
	 * initialized, and memblock_free_all() initializes all the reserved
	 * deferred pages for us.
	 */
	register_page_bootmem_info();

	/* Register memory areas for /proc/kcore */
	if (get_gate_vma(&init_mm))
		kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER);

	preallocate_vmalloc_pages();
}

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask)
{
	/*
	 * More CPUs always led to greater speedups on tested systems, up to
	 * all the nodes' CPUs.  Use all since the system is otherwise idle
	 * now.
	 */
	return max_t(int, cpumask_weight(node_cpumask), 1);
}
#endif

int kernel_set_to_readonly;

void mark_rodata_ro(void)
{
	unsigned long start = PFN_ALIGN(_text);
	unsigned long rodata_start = PFN_ALIGN(__start_rodata);
	unsigned long end = (unsigned long)__end_rodata_hpage_align;
	unsigned long text_end = PFN_ALIGN(_etext);
	unsigned long rodata_end = PFN_ALIGN(__end_rodata);
	unsigned long all_end;

	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
	       (end - start) >> 10);
	set_memory_ro(start, (end - start) >> PAGE_SHIFT);

	kernel_set_to_readonly = 1;

	/*
	 * The rodata/data/bss/brk section (but not the kernel text!)
	 * should also be not-executable.
	 *
	 * We align all_end to PMD_SIZE because the existing mapping
	 * is a full PMD. If we would align _brk_end to PAGE_SIZE we
	 * split the PMD and the reminder between _brk_end and the end
	 * of the PMD will remain mapped executable.
	 *
	 * Any PMD which was setup after the one which covers _brk_end
	 * has been zapped already via cleanup_highmem().
	 */
	all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
	set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT);

	set_ftrace_ops_ro();

#ifdef CONFIG_CPA_DEBUG
	printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end);
	set_memory_rw(start, (end-start) >> PAGE_SHIFT);

	printk(KERN_INFO "Testing CPA: again\n");
	set_memory_ro(start, (end-start) >> PAGE_SHIFT);
#endif

	free_kernel_image_pages("unused kernel image (text/rodata gap)",
				(void *)text_end, (void *)rodata_start);
	free_kernel_image_pages("unused kernel image (rodata/data gap)",
				(void *)rodata_end, (void *)_sdata);

	debug_checkwx();
}

int kern_addr_valid(unsigned long addr)
{
	unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	if (above != 0 && above != -1UL)
		return 0;

	pgd = pgd_offset_k(addr);
	if (pgd_none(*pgd))
		return 0;

	p4d = p4d_offset(pgd, addr);
	if (!p4d_present(*p4d))
		return 0;

	pud = pud_offset(p4d, addr);
	if (!pud_present(*pud))
		return 0;

	if (pud_large(*pud))
		return pfn_valid(pud_pfn(*pud));

	pmd = pmd_offset(pud, addr);
	if (!pmd_present(*pmd))
		return 0;

	if (pmd_large(*pmd))
		return pfn_valid(pmd_pfn(*pmd));

	pte = pte_offset_kernel(pmd, addr);
	if (pte_none(*pte))
		return 0;

	return pfn_valid(pte_pfn(*pte));
}

/*
 * Block size is the minimum amount of memory which can be hotplugged or
 * hotremoved. It must be power of two and must be equal or larger than
 * MIN_MEMORY_BLOCK_SIZE.
 */
#define MAX_BLOCK_SIZE (2UL << 30)

/* Amount of ram needed to start using large blocks */
#define MEM_SIZE_FOR_LARGE_BLOCK (64UL << 30)

/* Adjustable memory block size */
static unsigned long set_memory_block_size;
int __init set_memory_block_size_order(unsigned int order)
{
	unsigned long size = 1UL << order;

	if (size > MEM_SIZE_FOR_LARGE_BLOCK || size < MIN_MEMORY_BLOCK_SIZE)
		return -EINVAL;

	set_memory_block_size = size;
	return 0;
}

static unsigned long probe_memory_block_size(void)
{
	unsigned long boot_mem_end = max_pfn << PAGE_SHIFT;
	unsigned long bz;

	/* If memory block size has been set, then use it */
	bz = set_memory_block_size;
	if (bz)
		goto done;

	/* Use regular block if RAM is smaller than MEM_SIZE_FOR_LARGE_BLOCK */
	if (boot_mem_end < MEM_SIZE_FOR_LARGE_BLOCK) {
		bz = MIN_MEMORY_BLOCK_SIZE;
		goto done;
	}

	/*
	 * Use max block size to minimize overhead on bare metal, where
	 * alignment for memory hotplug isn't a concern.
	 */
	if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
		bz = MAX_BLOCK_SIZE;
		goto done;
	}

	/* Find the largest allowed block size that aligns to memory end */
	for (bz = MAX_BLOCK_SIZE; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) {
		if (IS_ALIGNED(boot_mem_end, bz))
			break;
	}
done:
	pr_info("x86/mm: Memory block size: %ldMB\n", bz >> 20);

	return bz;
}

static unsigned long memory_block_size_probed;
unsigned long memory_block_size_bytes(void)
{
	if (!memory_block_size_probed)
		memory_block_size_probed = probe_memory_block_size();

	return memory_block_size_probed;
}

#ifdef CONFIG_SPARSEMEM_VMEMMAP
/*
 * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
 */
static long __meminitdata addr_start, addr_end;
static void __meminitdata *p_start, *p_end;
static int __meminitdata node_start;

static int __meminit vmemmap_populate_hugepages(unsigned long start,
		unsigned long end, int node, struct vmem_altmap *altmap)
{
	unsigned long addr;
	unsigned long next;
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;

	for (addr = start; addr < end; addr = next) {
		next = pmd_addr_end(addr, end);

		pgd = vmemmap_pgd_populate(addr, node);
		if (!pgd)
			return -ENOMEM;

		p4d = vmemmap_p4d_populate(pgd, addr, node);
		if (!p4d)
			return -ENOMEM;

		pud = vmemmap_pud_populate(p4d, addr, node);
		if (!pud)
			return -ENOMEM;

		pmd = pmd_offset(pud, addr);
		if (pmd_none(*pmd)) {
			void *p;

			p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
			if (p) {
				pte_t entry;

				entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
						PAGE_KERNEL_LARGE);
				set_pmd(pmd, __pmd(pte_val(entry)));

				/* check to see if we have contiguous blocks */
				if (p_end != p || node_start != node) {
					if (p_start)
						pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n",
						       addr_start, addr_end-1, p_start, p_end-1, node_start);
					addr_start = addr;
					node_start = node;
					p_start = p;
				}

				addr_end = addr + PMD_SIZE;
				p_end = p + PMD_SIZE;

				if (!IS_ALIGNED(addr, PMD_SIZE) ||
				    !IS_ALIGNED(next, PMD_SIZE))
					vmemmap_use_new_sub_pmd(addr, next);

				continue;
			} else if (altmap)
				return -ENOMEM; /* no fallback */
		} else if (pmd_large(*pmd)) {
			vmemmap_verify((pte_t *)pmd, node, addr, next);
			vmemmap_use_sub_pmd(addr, next);
			continue;
		}
		if (vmemmap_populate_basepages(addr, next, node, NULL))
			return -ENOMEM;
	}
	return 0;
}

int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
		struct vmem_altmap *altmap)
{
	int err;

	VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE));
	VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE));

	if (end - start < PAGES_PER_SECTION * sizeof(struct page))
		err = vmemmap_populate_basepages(start, end, node, NULL);
	else if (boot_cpu_has(X86_FEATURE_PSE))
		err = vmemmap_populate_hugepages(start, end, node, altmap);
	else if (altmap) {
		pr_err_once("%s: no cpu support for altmap allocations\n",
				__func__);
		err = -ENOMEM;
	} else
		err = vmemmap_populate_basepages(start, end, node, NULL);
	if (!err)
		sync_global_pgds(start, end - 1);
	return err;
}

#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
void register_page_bootmem_memmap(unsigned long section_nr,
				  struct page *start_page, unsigned long nr_pages)
{
	unsigned long addr = (unsigned long)start_page;
	unsigned long end = (unsigned long)(start_page + nr_pages);
	unsigned long next;
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	unsigned int nr_pmd_pages;
	struct page *page;

	for (; addr < end; addr = next) {
		pte_t *pte = NULL;

		pgd = pgd_offset_k(addr);
		if (pgd_none(*pgd)) {
			next = (addr + PAGE_SIZE) & PAGE_MASK;
			continue;
		}
		get_page_bootmem(section_nr, pgd_page(*pgd), MIX_SECTION_INFO);

		p4d = p4d_offset(pgd, addr);
		if (p4d_none(*p4d)) {
			next = (addr + PAGE_SIZE) & PAGE_MASK;
			continue;
		}
		get_page_bootmem(section_nr, p4d_page(*p4d), MIX_SECTION_INFO);

		pud = pud_offset(p4d, addr);
		if (pud_none(*pud)) {
			next = (addr + PAGE_SIZE) & PAGE_MASK;
			continue;
		}
		get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO);

		if (!boot_cpu_has(X86_FEATURE_PSE)) {
			next = (addr + PAGE_SIZE) & PAGE_MASK;
			pmd = pmd_offset(pud, addr);
			if (pmd_none(*pmd))
				continue;
			get_page_bootmem(section_nr, pmd_page(*pmd),
					 MIX_SECTION_INFO);

			pte = pte_offset_kernel(pmd, addr);
			if (pte_none(*pte))
				continue;
			get_page_bootmem(section_nr, pte_page(*pte),
					 SECTION_INFO);
		} else {
			next = pmd_addr_end(addr, end);

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

			nr_pmd_pages = 1 << get_order(PMD_SIZE);
			page = pmd_page(*pmd);
			while (nr_pmd_pages--)
				get_page_bootmem(section_nr, page++,
						 SECTION_INFO);
		}
	}
}
#endif

void __meminit vmemmap_populate_print_last(void)
{
	if (p_start) {
		pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n",
			addr_start, addr_end-1, p_start, p_end-1, node_start);
		p_start = NULL;
		p_end = NULL;
		node_start = 0;
	}
}
#endif