summaryrefslogtreecommitdiffstats
path: root/arch/x86/mm/pageattr.c
blob: ae242a7c11c7473cfeb163b78d54fa62005b8e44 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
/*
 * Copyright 2002 Andi Kleen, SuSE Labs.
 * Thanks to Ben LaHaise for precious feedback.
 */
#include <linux/highmem.h>
#include <linux/bootmem.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/pfn.h>
#include <linux/percpu.h>
#include <linux/gfp.h>
#include <linux/pci.h>

#include <asm/e820.h>
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/uaccess.h>
#include <asm/pgalloc.h>
#include <asm/proto.h>
#include <asm/pat.h>

/*
 * The current flushing context - we pass it instead of 5 arguments:
 */
struct cpa_data {
	unsigned long	*vaddr;
	pgd_t		*pgd;
	pgprot_t	mask_set;
	pgprot_t	mask_clr;
	int		numpages;
	int		flags;
	unsigned long	pfn;
	unsigned	force_split : 1;
	int		curpage;
	struct page	**pages;
};

/*
 * Serialize cpa() (for !DEBUG_PAGEALLOC which uses large identity mappings)
 * using cpa_lock. So that we don't allow any other cpu, with stale large tlb
 * entries change the page attribute in parallel to some other cpu
 * splitting a large page entry along with changing the attribute.
 */
static DEFINE_SPINLOCK(cpa_lock);

#define CPA_FLUSHTLB 1
#define CPA_ARRAY 2
#define CPA_PAGES_ARRAY 4

#ifdef CONFIG_PROC_FS
static unsigned long direct_pages_count[PG_LEVEL_NUM];

void update_page_count(int level, unsigned long pages)
{
	/* Protect against CPA */
	spin_lock(&pgd_lock);
	direct_pages_count[level] += pages;
	spin_unlock(&pgd_lock);
}

static void split_page_count(int level)
{
	direct_pages_count[level]--;
	direct_pages_count[level - 1] += PTRS_PER_PTE;
}

void arch_report_meminfo(struct seq_file *m)
{
	seq_printf(m, "DirectMap4k:    %8lu kB\n",
			direct_pages_count[PG_LEVEL_4K] << 2);
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
	seq_printf(m, "DirectMap2M:    %8lu kB\n",
			direct_pages_count[PG_LEVEL_2M] << 11);
#else
	seq_printf(m, "DirectMap4M:    %8lu kB\n",
			direct_pages_count[PG_LEVEL_2M] << 12);
#endif
#ifdef CONFIG_X86_64
	if (direct_gbpages)
		seq_printf(m, "DirectMap1G:    %8lu kB\n",
			direct_pages_count[PG_LEVEL_1G] << 20);
#endif
}
#else
static inline void split_page_count(int level) { }
#endif

#ifdef CONFIG_X86_64

static inline unsigned long highmap_start_pfn(void)
{
	return __pa_symbol(_text) >> PAGE_SHIFT;
}

static inline unsigned long highmap_end_pfn(void)
{
	return __pa_symbol(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT;
}

#endif

#ifdef CONFIG_DEBUG_PAGEALLOC
# define debug_pagealloc 1
#else
# define debug_pagealloc 0
#endif

static inline int
within(unsigned long addr, unsigned long start, unsigned long end)
{
	return addr >= start && addr < end;
}

/*
 * Flushing functions
 */

/**
 * clflush_cache_range - flush a cache range with clflush
 * @vaddr:	virtual start address
 * @size:	number of bytes to flush
 *
 * clflushopt is an unordered instruction which needs fencing with mfence or
 * sfence to avoid ordering issues.
 */
void clflush_cache_range(void *vaddr, unsigned int size)
{
	void *vend = vaddr + size - 1;

	mb();

	for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size)
		clflushopt(vaddr);
	/*
	 * Flush any possible final partial cacheline:
	 */
	clflushopt(vend);

	mb();
}
EXPORT_SYMBOL_GPL(clflush_cache_range);

static void __cpa_flush_all(void *arg)
{
	unsigned long cache = (unsigned long)arg;

	/*
	 * Flush all to work around Errata in early athlons regarding
	 * large page flushing.
	 */
	__flush_tlb_all();

	if (cache && boot_cpu_data.x86 >= 4)
		wbinvd();
}

static void cpa_flush_all(unsigned long cache)
{
	BUG_ON(irqs_disabled());

	on_each_cpu(__cpa_flush_all, (void *) cache, 1);
}

static void __cpa_flush_range(void *arg)
{
	/*
	 * We could optimize that further and do individual per page
	 * tlb invalidates for a low number of pages. Caveat: we must
	 * flush the high aliases on 64bit as well.
	 */
	__flush_tlb_all();
}

static void cpa_flush_range(unsigned long start, int numpages, int cache)
{
	unsigned int i, level;
	unsigned long addr;

	BUG_ON(irqs_disabled());
	WARN_ON(PAGE_ALIGN(start) != start);

	on_each_cpu(__cpa_flush_range, NULL, 1);

	if (!cache)
		return;

	/*
	 * We only need to flush on one CPU,
	 * clflush is a MESI-coherent instruction that
	 * will cause all other CPUs to flush the same
	 * cachelines:
	 */
	for (i = 0, addr = start; i < numpages; i++, addr += PAGE_SIZE) {
		pte_t *pte = lookup_address(addr, &level);

		/*
		 * Only flush present addresses:
		 */
		if (pte && (pte_val(*pte) & _PAGE_PRESENT))
			clflush_cache_range((void *) addr, PAGE_SIZE);
	}
}

static void cpa_flush_array(unsigned long *start, int numpages, int cache,
			    int in_flags, struct page **pages)
{
	unsigned int i, level;
	unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */

	BUG_ON(irqs_disabled());

	on_each_cpu(__cpa_flush_all, (void *) do_wbinvd, 1);

	if (!cache || do_wbinvd)
		return;

	/*
	 * We only need to flush on one CPU,
	 * clflush is a MESI-coherent instruction that
	 * will cause all other CPUs to flush the same
	 * cachelines:
	 */
	for (i = 0; i < numpages; i++) {
		unsigned long addr;
		pte_t *pte;

		if (in_flags & CPA_PAGES_ARRAY)
			addr = (unsigned long)page_address(pages[i]);
		else
			addr = start[i];

		pte = lookup_address(addr, &level);

		/*
		 * Only flush present addresses:
		 */
		if (pte && (pte_val(*pte) & _PAGE_PRESENT))
			clflush_cache_range((void *)addr, PAGE_SIZE);
	}
}

/*
 * Certain areas of memory on x86 require very specific protection flags,
 * for example the BIOS area or kernel text. Callers don't always get this
 * right (again, ioremap() on BIOS memory is not uncommon) so this function
 * checks and fixes these known static required protection bits.
 */
static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
				   unsigned long pfn)
{
	pgprot_t forbidden = __pgprot(0);

	/*
	 * The BIOS area between 640k and 1Mb needs to be executable for
	 * PCI BIOS based config access (CONFIG_PCI_GOBIOS) support.
	 */
#ifdef CONFIG_PCI_BIOS
	if (pcibios_enabled && within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT))
		pgprot_val(forbidden) |= _PAGE_NX;
#endif

	/*
	 * The kernel text needs to be executable for obvious reasons
	 * Does not cover __inittext since that is gone later on. On
	 * 64bit we do not enforce !NX on the low mapping
	 */
	if (within(address, (unsigned long)_text, (unsigned long)_etext))
		pgprot_val(forbidden) |= _PAGE_NX;

	/*
	 * The .rodata section needs to be read-only. Using the pfn
	 * catches all aliases.
	 */
	if (within(pfn, __pa_symbol(__start_rodata) >> PAGE_SHIFT,
		   __pa_symbol(__end_rodata) >> PAGE_SHIFT))
		pgprot_val(forbidden) |= _PAGE_RW;

#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
	/*
	 * Once the kernel maps the text as RO (kernel_set_to_readonly is set),
	 * kernel text mappings for the large page aligned text, rodata sections
	 * will be always read-only. For the kernel identity mappings covering
	 * the holes caused by this alignment can be anything that user asks.
	 *
	 * This will preserve the large page mappings for kernel text/data
	 * at no extra cost.
	 */
	if (kernel_set_to_readonly &&
	    within(address, (unsigned long)_text,
		   (unsigned long)__end_rodata_hpage_align)) {
		unsigned int level;

		/*
		 * Don't enforce the !RW mapping for the kernel text mapping,
		 * if the current mapping is already using small page mapping.
		 * No need to work hard to preserve large page mappings in this
		 * case.
		 *
		 * This also fixes the Linux Xen paravirt guest boot failure
		 * (because of unexpected read-only mappings for kernel identity
		 * mappings). In this paravirt guest case, the kernel text
		 * mapping and the kernel identity mapping share the same
		 * page-table pages. Thus we can't really use different
		 * protections for the kernel text and identity mappings. Also,
		 * these shared mappings are made of small page mappings.
		 * Thus this don't enforce !RW mapping for small page kernel
		 * text mapping logic will help Linux Xen parvirt guest boot
		 * as well.
		 */
		if (lookup_address(address, &level) && (level != PG_LEVEL_4K))
			pgprot_val(forbidden) |= _PAGE_RW;
	}
#endif

	prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden));

	return prot;
}

/*
 * Lookup the page table entry for a virtual address in a specific pgd.
 * Return a pointer to the entry and the level of the mapping.
 */
pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
			     unsigned int *level)
{
	pud_t *pud;
	pmd_t *pmd;

	*level = PG_LEVEL_NONE;

	if (pgd_none(*pgd))
		return NULL;

	pud = pud_offset(pgd, address);
	if (pud_none(*pud))
		return NULL;

	*level = PG_LEVEL_1G;
	if (pud_large(*pud) || !pud_present(*pud))
		return (pte_t *)pud;

	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd))
		return NULL;

	*level = PG_LEVEL_2M;
	if (pmd_large(*pmd) || !pmd_present(*pmd))
		return (pte_t *)pmd;

	*level = PG_LEVEL_4K;

	return pte_offset_kernel(pmd, address);
}

/*
 * Lookup the page table entry for a virtual address. Return a pointer
 * to the entry and the level of the mapping.
 *
 * Note: We return pud and pmd either when the entry is marked large
 * or when the present bit is not set. Otherwise we would return a
 * pointer to a nonexisting mapping.
 */
pte_t *lookup_address(unsigned long address, unsigned int *level)
{
        return lookup_address_in_pgd(pgd_offset_k(address), address, level);
}
EXPORT_SYMBOL_GPL(lookup_address);

static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
				  unsigned int *level)
{
        if (cpa->pgd)
		return lookup_address_in_pgd(cpa->pgd + pgd_index(address),
					       address, level);

        return lookup_address(address, level);
}

/*
 * This is necessary because __pa() does not work on some
 * kinds of memory, like vmalloc() or the alloc_remap()
 * areas on 32-bit NUMA systems.  The percpu areas can
 * end up in this kind of memory, for instance.
 *
 * This could be optimized, but it is only intended to be
 * used at inititalization time, and keeping it
 * unoptimized should increase the testing coverage for
 * the more obscure platforms.
 */
phys_addr_t slow_virt_to_phys(void *__virt_addr)
{
	unsigned long virt_addr = (unsigned long)__virt_addr;
	phys_addr_t phys_addr;
	unsigned long offset;
	enum pg_level level;
	unsigned long psize;
	unsigned long pmask;
	pte_t *pte;

	pte = lookup_address(virt_addr, &level);
	BUG_ON(!pte);
	psize = page_level_size(level);
	pmask = page_level_mask(level);
	offset = virt_addr & ~pmask;
	phys_addr = pte_pfn(*pte) << PAGE_SHIFT;
	return (phys_addr | offset);
}
EXPORT_SYMBOL_GPL(slow_virt_to_phys);

/*
 * Set the new pmd in all the pgds we know about:
 */
static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte)
{
	/* change init_mm */
	set_pte_atomic(kpte, pte);
#ifdef CONFIG_X86_32
	if (!SHARED_KERNEL_PMD) {
		struct page *page;

		list_for_each_entry(page, &pgd_list, lru) {
			pgd_t *pgd;
			pud_t *pud;
			pmd_t *pmd;

			pgd = (pgd_t *)page_address(page) + pgd_index(address);
			pud = pud_offset(pgd, address);
			pmd = pmd_offset(pud, address);
			set_pte_atomic((pte_t *)pmd, pte);
		}
	}
#endif
}

static int
try_preserve_large_page(pte_t *kpte, unsigned long address,
			struct cpa_data *cpa)
{
	unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn;
	pte_t new_pte, old_pte, *tmp;
	pgprot_t old_prot, new_prot, req_prot;
	int i, do_split = 1;
	enum pg_level level;

	if (cpa->force_split)
		return 1;

	spin_lock(&pgd_lock);
	/*
	 * Check for races, another CPU might have split this page
	 * up already:
	 */
	tmp = _lookup_address_cpa(cpa, address, &level);
	if (tmp != kpte)
		goto out_unlock;

	switch (level) {
	case PG_LEVEL_2M:
#ifdef CONFIG_X86_64
	case PG_LEVEL_1G:
#endif
		psize = page_level_size(level);
		pmask = page_level_mask(level);
		break;
	default:
		do_split = -EINVAL;
		goto out_unlock;
	}

	/*
	 * Calculate the number of pages, which fit into this large
	 * page starting at address:
	 */
	nextpage_addr = (address + psize) & pmask;
	numpages = (nextpage_addr - address) >> PAGE_SHIFT;
	if (numpages < cpa->numpages)
		cpa->numpages = numpages;

	/*
	 * We are safe now. Check whether the new pgprot is the same:
	 */
	old_pte = *kpte;
	old_prot = req_prot = pte_pgprot(old_pte);

	pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr);
	pgprot_val(req_prot) |= pgprot_val(cpa->mask_set);

	/*
	 * Set the PSE and GLOBAL flags only if the PRESENT flag is
	 * set otherwise pmd_present/pmd_huge will return true even on
	 * a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL
	 * for the ancient hardware that doesn't support it.
	 */
	if (pgprot_val(req_prot) & _PAGE_PRESENT)
		pgprot_val(req_prot) |= _PAGE_PSE | _PAGE_GLOBAL;
	else
		pgprot_val(req_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL);

	req_prot = canon_pgprot(req_prot);

	/*
	 * old_pte points to the large page base address. So we need
	 * to add the offset of the virtual address:
	 */
	pfn = pte_pfn(old_pte) + ((address & (psize - 1)) >> PAGE_SHIFT);
	cpa->pfn = pfn;

	new_prot = static_protections(req_prot, address, pfn);

	/*
	 * We need to check the full range, whether
	 * static_protection() requires a different pgprot for one of
	 * the pages in the range we try to preserve:
	 */
	addr = address & pmask;
	pfn = pte_pfn(old_pte);
	for (i = 0; i < (psize >> PAGE_SHIFT); i++, addr += PAGE_SIZE, pfn++) {
		pgprot_t chk_prot = static_protections(req_prot, addr, pfn);

		if (pgprot_val(chk_prot) != pgprot_val(new_prot))
			goto out_unlock;
	}

	/*
	 * If there are no changes, return. maxpages has been updated
	 * above:
	 */
	if (pgprot_val(new_prot) == pgprot_val(old_prot)) {
		do_split = 0;
		goto out_unlock;
	}

	/*
	 * We need to change the attributes. Check, whether we can
	 * change the large page in one go. We request a split, when
	 * the address is not aligned and the number of pages is
	 * smaller than the number of pages in the large page. Note
	 * that we limited the number of possible pages already to
	 * the number of pages in the large page.
	 */
	if (address == (address & pmask) && cpa->numpages == (psize >> PAGE_SHIFT)) {
		/*
		 * The address is aligned and the number of pages
		 * covers the full page.
		 */
		new_pte = pfn_pte(pte_pfn(old_pte), new_prot);
		__set_pmd_pte(kpte, address, new_pte);
		cpa->flags |= CPA_FLUSHTLB;
		do_split = 0;
	}

out_unlock:
	spin_unlock(&pgd_lock);

	return do_split;
}

static int
__split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
		   struct page *base)
{
	pte_t *pbase = (pte_t *)page_address(base);
	unsigned long pfn, pfninc = 1;
	unsigned int i, level;
	pte_t *tmp;
	pgprot_t ref_prot;

	spin_lock(&pgd_lock);
	/*
	 * Check for races, another CPU might have split this page
	 * up for us already:
	 */
	tmp = _lookup_address_cpa(cpa, address, &level);
	if (tmp != kpte) {
		spin_unlock(&pgd_lock);
		return 1;
	}

	paravirt_alloc_pte(&init_mm, page_to_pfn(base));
	ref_prot = pte_pgprot(pte_clrhuge(*kpte));
	/*
	 * If we ever want to utilize the PAT bit, we need to
	 * update this function to make sure it's converted from
	 * bit 12 to bit 7 when we cross from the 2MB level to
	 * the 4K level:
	 */
	WARN_ON_ONCE(pgprot_val(ref_prot) & _PAGE_PAT_LARGE);

#ifdef CONFIG_X86_64
	if (level == PG_LEVEL_1G) {
		pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT;
		/*
		 * Set the PSE flags only if the PRESENT flag is set
		 * otherwise pmd_present/pmd_huge will return true
		 * even on a non present pmd.
		 */
		if (pgprot_val(ref_prot) & _PAGE_PRESENT)
			pgprot_val(ref_prot) |= _PAGE_PSE;
		else
			pgprot_val(ref_prot) &= ~_PAGE_PSE;
	}
#endif

	/*
	 * Set the GLOBAL flags only if the PRESENT flag is set
	 * otherwise pmd/pte_present will return true even on a non
	 * present pmd/pte. The canon_pgprot will clear _PAGE_GLOBAL
	 * for the ancient hardware that doesn't support it.
	 */
	if (pgprot_val(ref_prot) & _PAGE_PRESENT)
		pgprot_val(ref_prot) |= _PAGE_GLOBAL;
	else
		pgprot_val(ref_prot) &= ~_PAGE_GLOBAL;

	/*
	 * Get the target pfn from the original entry:
	 */
	pfn = pte_pfn(*kpte);
	for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc)
		set_pte(&pbase[i], pfn_pte(pfn, canon_pgprot(ref_prot)));

	if (pfn_range_is_mapped(PFN_DOWN(__pa(address)),
				PFN_DOWN(__pa(address)) + 1))
		split_page_count(level);

	/*
	 * Install the new, split up pagetable.
	 *
	 * We use the standard kernel pagetable protections for the new
	 * pagetable protections, the actual ptes set above control the
	 * primary protection behavior:
	 */
	__set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE)));

	/*
	 * Intel Atom errata AAH41 workaround.
	 *
	 * The real fix should be in hw or in a microcode update, but
	 * we also probabilistically try to reduce the window of having
	 * a large TLB mixed with 4K TLBs while instruction fetches are
	 * going on.
	 */
	__flush_tlb_all();
	spin_unlock(&pgd_lock);

	return 0;
}

static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
			    unsigned long address)
{
	struct page *base;

	if (!debug_pagealloc)
		spin_unlock(&cpa_lock);
	base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0);
	if (!debug_pagealloc)
		spin_lock(&cpa_lock);
	if (!base)
		return -ENOMEM;

	if (__split_large_page(cpa, kpte, address, base))
		__free_page(base);

	return 0;
}

static bool try_to_free_pte_page(pte_t *pte)
{
	int i;

	for (i = 0; i < PTRS_PER_PTE; i++)
		if (!pte_none(pte[i]))
			return false;

	free_page((unsigned long)pte);
	return true;
}

static bool try_to_free_pmd_page(pmd_t *pmd)
{
	int i;

	for (i = 0; i < PTRS_PER_PMD; i++)
		if (!pmd_none(pmd[i]))
			return false;

	free_page((unsigned long)pmd);
	return true;
}

static bool try_to_free_pud_page(pud_t *pud)
{
	int i;

	for (i = 0; i < PTRS_PER_PUD; i++)
		if (!pud_none(pud[i]))
			return false;

	free_page((unsigned long)pud);
	return true;
}

static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
{
	pte_t *pte = pte_offset_kernel(pmd, start);

	while (start < end) {
		set_pte(pte, __pte(0));

		start += PAGE_SIZE;
		pte++;
	}

	if (try_to_free_pte_page((pte_t *)pmd_page_vaddr(*pmd))) {
		pmd_clear(pmd);
		return true;
	}
	return false;
}

static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd,
			      unsigned long start, unsigned long end)
{
	if (unmap_pte_range(pmd, start, end))
		if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
			pud_clear(pud);
}

static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end)
{
	pmd_t *pmd = pmd_offset(pud, start);

	/*
	 * Not on a 2MB page boundary?
	 */
	if (start & (PMD_SIZE - 1)) {
		unsigned long next_page = (start + PMD_SIZE) & PMD_MASK;
		unsigned long pre_end = min_t(unsigned long, end, next_page);

		__unmap_pmd_range(pud, pmd, start, pre_end);

		start = pre_end;
		pmd++;
	}

	/*
	 * Try to unmap in 2M chunks.
	 */
	while (end - start >= PMD_SIZE) {
		if (pmd_large(*pmd))
			pmd_clear(pmd);
		else
			__unmap_pmd_range(pud, pmd, start, start + PMD_SIZE);

		start += PMD_SIZE;
		pmd++;
	}

	/*
	 * 4K leftovers?
	 */
	if (start < end)
		return __unmap_pmd_range(pud, pmd, start, end);

	/*
	 * Try again to free the PMD page if haven't succeeded above.
	 */
	if (!pud_none(*pud))
		if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
			pud_clear(pud);
}

static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
{
	pud_t *pud = pud_offset(pgd, start);

	/*
	 * Not on a GB page boundary?
	 */
	if (start & (PUD_SIZE - 1)) {
		unsigned long next_page = (start + PUD_SIZE) & PUD_MASK;
		unsigned long pre_end	= min_t(unsigned long, end, next_page);

		unmap_pmd_range(pud, start, pre_end);

		start = pre_end;
		pud++;
	}

	/*
	 * Try to unmap in 1G chunks?
	 */
	while (end - start >= PUD_SIZE) {

		if (pud_large(*pud))
			pud_clear(pud);
		else
			unmap_pmd_range(pud, start, start + PUD_SIZE);

		start += PUD_SIZE;
		pud++;
	}

	/*
	 * 2M leftovers?
	 */
	if (start < end)
		unmap_pmd_range(pud, start, end);

	/*
	 * No need to try to free the PUD page because we'll free it in
	 * populate_pgd's error path
	 */
}

static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end)
{
	pgd_t *pgd_entry = root + pgd_index(addr);

	unmap_pud_range(pgd_entry, addr, end);

	if (try_to_free_pud_page((pud_t *)pgd_page_vaddr(*pgd_entry)))
		pgd_clear(pgd_entry);
}

static int alloc_pte_page(pmd_t *pmd)
{
	pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
	if (!pte)
		return -1;

	set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
	return 0;
}

static int alloc_pmd_page(pud_t *pud)
{
	pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
	if (!pmd)
		return -1;

	set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
	return 0;
}

static void populate_pte(struct cpa_data *cpa,
			 unsigned long start, unsigned long end,
			 unsigned num_pages, pmd_t *pmd, pgprot_t pgprot)
{
	pte_t *pte;

	pte = pte_offset_kernel(pmd, start);

	while (num_pages-- && start < end) {

		/* deal with the NX bit */
		if (!(pgprot_val(pgprot) & _PAGE_NX))
			cpa->pfn &= ~_PAGE_NX;

		set_pte(pte, pfn_pte(cpa->pfn >> PAGE_SHIFT, pgprot));

		start	 += PAGE_SIZE;
		cpa->pfn += PAGE_SIZE;
		pte++;
	}
}

static int populate_pmd(struct cpa_data *cpa,
			unsigned long start, unsigned long end,
			unsigned num_pages, pud_t *pud, pgprot_t pgprot)
{
	unsigned int cur_pages = 0;
	pmd_t *pmd;

	/*
	 * Not on a 2M boundary?
	 */
	if (start & (PMD_SIZE - 1)) {
		unsigned long pre_end = start + (num_pages << PAGE_SHIFT);
		unsigned long next_page = (start + PMD_SIZE) & PMD_MASK;

		pre_end   = min_t(unsigned long, pre_end, next_page);
		cur_pages = (pre_end - start) >> PAGE_SHIFT;
		cur_pages = min_t(unsigned int, num_pages, cur_pages);

		/*
		 * Need a PTE page?
		 */
		pmd = pmd_offset(pud, start);
		if (pmd_none(*pmd))
			if (alloc_pte_page(pmd))
				return -1;

		populate_pte(cpa, start, pre_end, cur_pages, pmd, pgprot);

		start = pre_end;
	}

	/*
	 * We mapped them all?
	 */
	if (num_pages == cur_pages)
		return cur_pages;

	while (end - start >= PMD_SIZE) {

		/*
		 * We cannot use a 1G page so allocate a PMD page if needed.
		 */
		if (pud_none(*pud))
			if (alloc_pmd_page(pud))
				return -1;

		pmd = pmd_offset(pud, start);

		set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot)));

		start	  += PMD_SIZE;
		cpa->pfn  += PMD_SIZE;
		cur_pages += PMD_SIZE >> PAGE_SHIFT;
	}

	/*
	 * Map trailing 4K pages.
	 */
	if (start < end) {
		pmd = pmd_offset(pud, start);
		if (pmd_none(*pmd))
			if (alloc_pte_page(pmd))
				return -1;

		populate_pte(cpa, start, end, num_pages - cur_pages,
			     pmd, pgprot);
	}
	return num_pages;
}

static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
			pgprot_t pgprot)
{
	pud_t *pud;
	unsigned long end;
	int cur_pages = 0;

	end = start + (cpa->numpages << PAGE_SHIFT);

	/*
	 * Not on a Gb page boundary? => map everything up to it with
	 * smaller pages.
	 */
	if (start & (PUD_SIZE - 1)) {
		unsigned long pre_end;
		unsigned long next_page = (start + PUD_SIZE) & PUD_MASK;

		pre_end   = min_t(unsigned long, end, next_page);
		cur_pages = (pre_end - start) >> PAGE_SHIFT;
		cur_pages = min_t(int, (int)cpa->numpages, cur_pages);

		pud = pud_offset(pgd, start);

		/*
		 * Need a PMD page?
		 */
		if (pud_none(*pud))
			if (alloc_pmd_page(pud))
				return -1;

		cur_pages = populate_pmd(cpa, start, pre_end, cur_pages,
					 pud, pgprot);
		if (cur_pages < 0)
			return cur_pages;

		start = pre_end;
	}

	/* We mapped them all? */
	if (cpa->numpages == cur_pages)
		return cur_pages;

	pud = pud_offset(pgd, start);

	/*
	 * Map everything starting from the Gb boundary, possibly with 1G pages
	 */
	while (end - start >= PUD_SIZE) {
		set_pud(pud, __pud(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot)));

		start	  += PUD_SIZE;
		cpa->pfn  += PUD_SIZE;
		cur_pages += PUD_SIZE >> PAGE_SHIFT;
		pud++;
	}

	/* Map trailing leftover */
	if (start < end) {
		int tmp;

		pud = pud_offset(pgd, start);
		if (pud_none(*pud))
			if (alloc_pmd_page(pud))
				return -1;

		tmp = populate_pmd(cpa, start, end, cpa->numpages - cur_pages,
				   pud, pgprot);
		if (tmp < 0)
			return cur_pages;

		cur_pages += tmp;
	}
	return cur_pages;
}

/*
 * Restrictions for kernel page table do not necessarily apply when mapping in
 * an alternate PGD.
 */
static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
{
	pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
	pud_t *pud = NULL;	/* shut up gcc */
	pgd_t *pgd_entry;
	int ret;

	pgd_entry = cpa->pgd + pgd_index(addr);

	/*
	 * Allocate a PUD page and hand it down for mapping.
	 */
	if (pgd_none(*pgd_entry)) {
		pud = (pud_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
		if (!pud)
			return -1;

		set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE));
	}

	pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr);
	pgprot_val(pgprot) |=  pgprot_val(cpa->mask_set);

	ret = populate_pud(cpa, addr, pgd_entry, pgprot);
	if (ret < 0) {
		unmap_pgd_range(cpa->pgd, addr,
				addr + (cpa->numpages << PAGE_SHIFT));
		return ret;
	}

	cpa->numpages = ret;
	return 0;
}

static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr,
			       int primary)
{
	if (cpa->pgd)
		return populate_pgd(cpa, vaddr);

	/*
	 * Ignore all non primary paths.
	 */
	if (!primary)
		return 0;

	/*
	 * Ignore the NULL PTE for kernel identity mapping, as it is expected
	 * to have holes.
	 * Also set numpages to '1' indicating that we processed cpa req for
	 * one virtual address page and its pfn. TBD: numpages can be set based
	 * on the initial value and the level returned by lookup_address().
	 */
	if (within(vaddr, PAGE_OFFSET,
		   PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))) {
		cpa->numpages = 1;
		cpa->pfn = __pa(vaddr) >> PAGE_SHIFT;
		return 0;
	} else {
		WARN(1, KERN_WARNING "CPA: called for zero pte. "
			"vaddr = %lx cpa->vaddr = %lx\n", vaddr,
			*cpa->vaddr);

		return -EFAULT;
	}
}

static int __change_page_attr(struct cpa_data *cpa, int primary)
{
	unsigned long address;
	int do_split, err;
	unsigned int level;
	pte_t *kpte, old_pte;

	if (cpa->flags & CPA_PAGES_ARRAY) {
		struct page *page = cpa->pages[cpa->curpage];
		if (unlikely(PageHighMem(page)))
			return 0;
		address = (unsigned long)page_address(page);
	} else if (cpa->flags & CPA_ARRAY)
		address = cpa->vaddr[cpa->curpage];
	else
		address = *cpa->vaddr;
repeat:
	kpte = _lookup_address_cpa(cpa, address, &level);
	if (!kpte)
		return __cpa_process_fault(cpa, address, primary);

	old_pte = *kpte;
	if (!pte_val(old_pte))
		return __cpa_process_fault(cpa, address, primary);

	if (level == PG_LEVEL_4K) {
		pte_t new_pte;
		pgprot_t new_prot = pte_pgprot(old_pte);
		unsigned long pfn = pte_pfn(old_pte);

		pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr);
		pgprot_val(new_prot) |= pgprot_val(cpa->mask_set);

		new_prot = static_protections(new_prot, address, pfn);

		/*
		 * Set the GLOBAL flags only if the PRESENT flag is
		 * set otherwise pte_present will return true even on
		 * a non present pte. The canon_pgprot will clear
		 * _PAGE_GLOBAL for the ancient hardware that doesn't
		 * support it.
		 */
		if (pgprot_val(new_prot) & _PAGE_PRESENT)
			pgprot_val(new_prot) |= _PAGE_GLOBAL;
		else
			pgprot_val(new_prot) &= ~_PAGE_GLOBAL;

		/*
		 * We need to keep the pfn from the existing PTE,
		 * after all we're only going to change it's attributes
		 * not the memory it points to
		 */
		new_pte = pfn_pte(pfn, canon_pgprot(new_prot));
		cpa->pfn = pfn;
		/*
		 * Do we really change anything ?
		 */
		if (pte_val(old_pte) != pte_val(new_pte)) {
			set_pte_atomic(kpte, new_pte);
			cpa->flags |= CPA_FLUSHTLB;
		}
		cpa->numpages = 1;
		return 0;
	}

	/*
	 * Check, whether we can keep the large page intact
	 * and just change the pte:
	 */
	do_split = try_preserve_large_page(kpte, address, cpa);
	/*
	 * When the range fits into the existing large page,
	 * return. cp->numpages and cpa->tlbflush have been updated in
	 * try_large_page:
	 */
	if (do_split <= 0)
		return do_split;

	/*
	 * We have to split the large page:
	 */
	err = split_large_page(cpa, kpte, address);
	if (!err) {
		/*
	 	 * Do a global flush tlb after splitting the large page
	 	 * and before we do the actual change page attribute in the PTE.
	 	 *
	 	 * With out this, we violate the TLB application note, that says
	 	 * "The TLBs may contain both ordinary and large-page
		 *  translations for a 4-KByte range of linear addresses. This
		 *  may occur if software modifies the paging structures so that
		 *  the page size used for the address range changes. If the two
		 *  translations differ with respect to page frame or attributes
		 *  (e.g., permissions), processor behavior is undefined and may
		 *  be implementation-specific."
	 	 *
	 	 * We do this global tlb flush inside the cpa_lock, so that we
		 * don't allow any other cpu, with stale tlb entries change the
		 * page attribute in parallel, that also falls into the
		 * just split large page entry.
	 	 */
		flush_tlb_all();
		goto repeat;
	}

	return err;
}

static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias);

static int cpa_process_alias(struct cpa_data *cpa)
{
	struct cpa_data alias_cpa;
	unsigned long laddr = (unsigned long)__va(cpa->pfn << PAGE_SHIFT);
	unsigned long vaddr;
	int ret;

	if (!pfn_range_is_mapped(cpa->pfn, cpa->pfn + 1))
		return 0;

	/*
	 * No need to redo, when the primary call touched the direct
	 * mapping already:
	 */
	if (cpa->flags & CPA_PAGES_ARRAY) {
		struct page *page = cpa->pages[cpa->curpage];
		if (unlikely(PageHighMem(page)))
			return 0;
		vaddr = (unsigned long)page_address(page);
	} else if (cpa->flags & CPA_ARRAY)
		vaddr = cpa->vaddr[cpa->curpage];
	else
		vaddr = *cpa->vaddr;

	if (!(within(vaddr, PAGE_OFFSET,
		    PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT)))) {

		alias_cpa = *cpa;
		alias_cpa.vaddr = &laddr;
		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);

		ret = __change_page_attr_set_clr(&alias_cpa, 0);
		if (ret)
			return ret;
	}

#ifdef CONFIG_X86_64
	/*
	 * If the primary call didn't touch the high mapping already
	 * and the physical address is inside the kernel map, we need
	 * to touch the high mapped kernel as well:
	 */
	if (!within(vaddr, (unsigned long)_text, _brk_end) &&
	    within(cpa->pfn, highmap_start_pfn(), highmap_end_pfn())) {
		unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) +
					       __START_KERNEL_map - phys_base;
		alias_cpa = *cpa;
		alias_cpa.vaddr = &temp_cpa_vaddr;
		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);

		/*
		 * The high mapping range is imprecise, so ignore the
		 * return value.
		 */
		__change_page_attr_set_clr(&alias_cpa, 0);
	}
#endif

	return 0;
}

static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
{
	int ret, numpages = cpa->numpages;

	while (numpages) {
		/*
		 * Store the remaining nr of pages for the large page
		 * preservation check.
		 */
		cpa->numpages = numpages;
		/* for array changes, we can't use large page */
		if (cpa->flags & (CPA_ARRAY | CPA_PAGES_ARRAY))
			cpa->numpages = 1;

		if (!debug_pagealloc)
			spin_lock(&cpa_lock);
		ret = __change_page_attr(cpa, checkalias);
		if (!debug_pagealloc)
			spin_unlock(&cpa_lock);
		if (ret)
			return ret;

		if (checkalias) {
			ret = cpa_process_alias(cpa);
			if (ret)
				return ret;
		}

		/*
		 * Adjust the number of pages with the result of the
		 * CPA operation. Either a large page has been
		 * preserved or a single page update happened.
		 */
		BUG_ON(cpa->numpages > numpages);
		numpages -= cpa->numpages;
		if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY))
			cpa->curpage++;
		else
			*cpa->vaddr += cpa->numpages * PAGE_SIZE;

	}
	return 0;
}

static inline int cache_attr(pgprot_t attr)
{
	return pgprot_val(attr) &
		(_PAGE_PAT | _PAGE_PAT_LARGE | _PAGE_PWT | _PAGE_PCD);
}

static int change_page_attr_set_clr(unsigned long *addr, int numpages,
				    pgprot_t mask_set, pgprot_t mask_clr,
				    int force_split, int in_flag,
				    struct page **pages)
{
	struct cpa_data cpa;
	int ret, cache, checkalias;
	unsigned long baddr = 0;

	memset(&cpa, 0, sizeof(cpa));

	/*
	 * Check, if we are requested to change a not supported
	 * feature:
	 */
	mask_set = canon_pgprot(mask_set);
	mask_clr = canon_pgprot(mask_clr);
	if (!pgprot_val(mask_set) && !pgprot_val(mask_clr) && !force_split)
		return 0;

	/* Ensure we are PAGE_SIZE aligned */
	if (in_flag & CPA_ARRAY) {
		int i;
		for (i = 0; i < numpages; i++) {
			if (addr[i] & ~PAGE_MASK) {
				addr[i] &= PAGE_MASK;
				WARN_ON_ONCE(1);
			}
		}
	} else if (!(in_flag & CPA_PAGES_ARRAY)) {
		/*
		 * in_flag of CPA_PAGES_ARRAY implies it is aligned.
		 * No need to cehck in that case
		 */
		if (*addr & ~PAGE_MASK) {
			*addr &= PAGE_MASK;
			/*
			 * People should not be passing in unaligned addresses:
			 */
			WARN_ON_ONCE(1);
		}
		/*
		 * Save address for cache flush. *addr is modified in the call
		 * to __change_page_attr_set_clr() below.
		 */
		baddr = *addr;
	}

	/* Must avoid aliasing mappings in the highmem code */
	kmap_flush_unused();

	vm_unmap_aliases();

	cpa.vaddr = addr;
	cpa.pages = pages;
	cpa.numpages = numpages;
	cpa.mask_set = mask_set;
	cpa.mask_clr = mask_clr;
	cpa.flags = 0;
	cpa.curpage = 0;
	cpa.force_split = force_split;

	if (in_flag & (CPA_ARRAY | CPA_PAGES_ARRAY))
		cpa.flags |= in_flag;

	/* No alias checking for _NX bit modifications */
	checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX;

	ret = __change_page_attr_set_clr(&cpa, checkalias);

	/*
	 * Check whether we really changed something:
	 */
	if (!(cpa.flags & CPA_FLUSHTLB))
		goto out;

	/*
	 * No need to flush, when we did not set any of the caching
	 * attributes:
	 */
	cache = cache_attr(mask_set);

	/*
	 * On success we use CLFLUSH, when the CPU supports it to
	 * avoid the WBINVD. If the CPU does not support it and in the
	 * error case we fall back to cpa_flush_all (which uses
	 * WBINVD):
	 */
	if (!ret && cpu_has_clflush) {
		if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
			cpa_flush_array(addr, numpages, cache,
					cpa.flags, pages);
		} else
			cpa_flush_range(baddr, numpages, cache);
	} else
		cpa_flush_all(cache);

out:
	return ret;
}

static inline int change_page_attr_set(unsigned long *addr, int numpages,
				       pgprot_t mask, int array)
{
	return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0), 0,
		(array ? CPA_ARRAY : 0), NULL);
}

static inline int change_page_attr_clear(unsigned long *addr, int numpages,
					 pgprot_t mask, int array)
{
	return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask, 0,
		(array ? CPA_ARRAY : 0), NULL);
}

static inline int cpa_set_pages_array(struct page **pages, int numpages,
				       pgprot_t mask)
{
	return change_page_attr_set_clr(NULL, numpages, mask, __pgprot(0), 0,
		CPA_PAGES_ARRAY, pages);
}

static inline int cpa_clear_pages_array(struct page **pages, int numpages,
					 pgprot_t mask)
{
	return change_page_attr_set_clr(NULL, numpages, __pgprot(0), mask, 0,
		CPA_PAGES_ARRAY, pages);
}

int _set_memory_uc(unsigned long addr, int numpages)
{
	/*
	 * for now UC MINUS. see comments in ioremap_nocache()
	 */
	return change_page_attr_set(&addr, numpages,
				    __pgprot(_PAGE_CACHE_UC_MINUS), 0);
}

int set_memory_uc(unsigned long addr, int numpages)
{
	int ret;

	/*
	 * for now UC MINUS. see comments in ioremap_nocache()
	 */
	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
			    _PAGE_CACHE_UC_MINUS, NULL);
	if (ret)
		goto out_err;

	ret = _set_memory_uc(addr, numpages);
	if (ret)
		goto out_free;

	return 0;

out_free:
	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
out_err:
	return ret;
}
EXPORT_SYMBOL(set_memory_uc);

static int _set_memory_array(unsigned long *addr, int addrinarray,
		unsigned long new_type)
{
	int i, j;
	int ret;

	/*
	 * for now UC MINUS. see comments in ioremap_nocache()
	 */
	for (i = 0; i < addrinarray; i++) {
		ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE,
					new_type, NULL);
		if (ret)
			goto out_free;
	}

	ret = change_page_attr_set(addr, addrinarray,
				    __pgprot(_PAGE_CACHE_UC_MINUS), 1);

	if (!ret && new_type == _PAGE_CACHE_WC)
		ret = change_page_attr_set_clr(addr, addrinarray,
					       __pgprot(_PAGE_CACHE_WC),
					       __pgprot(_PAGE_CACHE_MASK),
					       0, CPA_ARRAY, NULL);
	if (ret)
		goto out_free;

	return 0;

out_free:
	for (j = 0; j < i; j++)
		free_memtype(__pa(addr[j]), __pa(addr[j]) + PAGE_SIZE);

	return ret;
}

int set_memory_array_uc(unsigned long *addr, int addrinarray)
{
	return _set_memory_array(addr, addrinarray, _PAGE_CACHE_UC_MINUS);
}
EXPORT_SYMBOL(set_memory_array_uc);

int set_memory_array_wc(unsigned long *addr, int addrinarray)
{
	return _set_memory_array(addr, addrinarray, _PAGE_CACHE_WC);
}
EXPORT_SYMBOL(set_memory_array_wc);

int _set_memory_wc(unsigned long addr, int numpages)
{
	int ret;
	unsigned long addr_copy = addr;

	ret = change_page_attr_set(&addr, numpages,
				    __pgprot(_PAGE_CACHE_UC_MINUS), 0);
	if (!ret) {
		ret = change_page_attr_set_clr(&addr_copy, numpages,
					       __pgprot(_PAGE_CACHE_WC),
					       __pgprot(_PAGE_CACHE_MASK),
					       0, 0, NULL);
	}
	return ret;
}

int set_memory_wc(unsigned long addr, int numpages)
{
	int ret;

	if (!pat_enabled)
		return set_memory_uc(addr, numpages);

	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
		_PAGE_CACHE_WC, NULL);
	if (ret)
		goto out_err;

	ret = _set_memory_wc(addr, numpages);
	if (ret)
		goto out_free;

	return 0;

out_free:
	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
out_err:
	return ret;
}
EXPORT_SYMBOL(set_memory_wc);

int _set_memory_wb(unsigned long addr, int numpages)
{
	return change_page_attr_clear(&addr, numpages,
				      __pgprot(_PAGE_CACHE_MASK), 0);
}

int set_memory_wb(unsigned long addr, int numpages)
{
	int ret;

	ret = _set_memory_wb(addr, numpages);
	if (ret)
		return ret;

	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
	return 0;
}
EXPORT_SYMBOL(set_memory_wb);

int set_memory_array_wb(unsigned long *addr, int addrinarray)
{
	int i;
	int ret;

	ret = change_page_attr_clear(addr, addrinarray,
				      __pgprot(_PAGE_CACHE_MASK), 1);
	if (ret)
		return ret;

	for (i = 0; i < addrinarray; i++)
		free_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE);

	return 0;
}
EXPORT_SYMBOL(set_memory_array_wb);

int set_memory_x(unsigned long addr, int numpages)
{
	if (!(__supported_pte_mask & _PAGE_NX))
		return 0;

	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_NX), 0);
}
EXPORT_SYMBOL(set_memory_x);

int set_memory_nx(unsigned long addr, int numpages)
{
	if (!(__supported_pte_mask & _PAGE_NX))
		return 0;

	return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_NX), 0);
}
EXPORT_SYMBOL(set_memory_nx);

int set_memory_ro(unsigned long addr, int numpages)
{
	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_RW), 0);
}
EXPORT_SYMBOL_GPL(set_memory_ro);

int set_memory_rw(unsigned long addr, int numpages)
{
	return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_RW), 0);
}
EXPORT_SYMBOL_GPL(set_memory_rw);

int set_memory_np(unsigned long addr, int numpages)
{
	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
}

int set_memory_4k(unsigned long addr, int numpages)
{
	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
					__pgprot(0), 1, 0, NULL);
}

int set_pages_uc(struct page *page, int numpages)
{
	unsigned long addr = (unsigned long)page_address(page);

	return set_memory_uc(addr, numpages);
}
EXPORT_SYMBOL(set_pages_uc);

static int _set_pages_array(struct page **pages, int addrinarray,
		unsigned long new_type)
{
	unsigned long start;
	unsigned long end;
	int i;
	int free_idx;
	int ret;

	for (i = 0; i < addrinarray; i++) {
		if (PageHighMem(pages[i]))
			continue;
		start = page_to_pfn(pages[i]) << PAGE_SHIFT;
		end = start + PAGE_SIZE;
		if (reserve_memtype(start, end, new_type, NULL))
			goto err_out;
	}

	ret = cpa_set_pages_array(pages, addrinarray,
			__pgprot(_PAGE_CACHE_UC_MINUS));
	if (!ret && new_type == _PAGE_CACHE_WC)
		ret = change_page_attr_set_clr(NULL, addrinarray,
					       __pgprot(_PAGE_CACHE_WC),
					       __pgprot(_PAGE_CACHE_MASK),
					       0, CPA_PAGES_ARRAY, pages);
	if (ret)
		goto err_out;
	return 0; /* Success */
err_out:
	free_idx = i;
	for (i = 0; i < free_idx; i++) {
		if (PageHighMem(pages[i]))
			continue;
		start = page_to_pfn(pages[i]) << PAGE_SHIFT;
		end = start + PAGE_SIZE;
		free_memtype(start, end);
	}
	return -EINVAL;
}

int set_pages_array_uc(struct page **pages, int addrinarray)
{
	return _set_pages_array(pages, addrinarray, _PAGE_CACHE_UC_MINUS);
}
EXPORT_SYMBOL(set_pages_array_uc);

int set_pages_array_wc(struct page **pages, int addrinarray)
{
	return _set_pages_array(pages, addrinarray, _PAGE_CACHE_WC);
}
EXPORT_SYMBOL(set_pages_array_wc);

int set_pages_wb(struct page *page, int numpages)
{
	unsigned long addr = (unsigned long)page_address(page);

	return set_memory_wb(addr, numpages);
}
EXPORT_SYMBOL(set_pages_wb);

int set_pages_array_wb(struct page **pages, int addrinarray)
{
	int retval;
	unsigned long start;
	unsigned long end;
	int i;

	retval = cpa_clear_pages_array(pages, addrinarray,
			__pgprot(_PAGE_CACHE_MASK));
	if (retval)
		return retval;

	for (i = 0; i < addrinarray; i++) {
		if (PageHighMem(pages[i]))
			continue;
		start = page_to_pfn(pages[i]) << PAGE_SHIFT;
		end = start + PAGE_SIZE;
		free_memtype(start, end);
	}

	return 0;
}
EXPORT_SYMBOL(set_pages_array_wb);

int set_pages_x(struct page *page, int numpages)
{
	unsigned long addr = (unsigned long)page_address(page);

	return set_memory_x(addr, numpages);
}
EXPORT_SYMBOL(set_pages_x);

int set_pages_nx(struct page *page, int numpages)
{
	unsigned long addr = (unsigned long)page_address(page);

	return set_memory_nx(addr, numpages);
}
EXPORT_SYMBOL(set_pages_nx);

int set_pages_ro(struct page *page, int numpages)
{
	unsigned long addr = (unsigned long)page_address(page);

	return set_memory_ro(addr, numpages);
}

int set_pages_rw(struct page *page, int numpages)
{
	unsigned long addr = (unsigned long)page_address(page);

	return set_memory_rw(addr, numpages);
}

#ifdef CONFIG_DEBUG_PAGEALLOC

static int __set_pages_p(struct page *page, int numpages)
{
	unsigned long tempaddr = (unsigned long) page_address(page);
	struct cpa_data cpa = { .vaddr = &tempaddr,
				.pgd = NULL,
				.numpages = numpages,
				.mask_set = __pgprot(_PAGE_PRESENT | _PAGE_RW),
				.mask_clr = __pgprot(0),
				.flags = 0};

	/*
	 * No alias checking needed for setting present flag. otherwise,
	 * we may need to break large pages for 64-bit kernel text
	 * mappings (this adds to complexity if we want to do this from
	 * atomic context especially). Let's keep it simple!
	 */
	return __change_page_attr_set_clr(&cpa, 0);
}

static int __set_pages_np(struct page *page, int numpages)
{
	unsigned long tempaddr = (unsigned long) page_address(page);
	struct cpa_data cpa = { .vaddr = &tempaddr,
				.pgd = NULL,
				.numpages = numpages,
				.mask_set = __pgprot(0),
				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW),
				.flags = 0};

	/*
	 * No alias checking needed for setting not present flag. otherwise,
	 * we may need to break large pages for 64-bit kernel text
	 * mappings (this adds to complexity if we want to do this from
	 * atomic context especially). Let's keep it simple!
	 */
	return __change_page_attr_set_clr(&cpa, 0);
}

void kernel_map_pages(struct page *page, int numpages, int enable)
{
	if (PageHighMem(page))
		return;
	if (!enable) {
		debug_check_no_locks_freed(page_address(page),
					   numpages * PAGE_SIZE);
	}

	/*
	 * The return value is ignored as the calls cannot fail.
	 * Large pages for identity mappings are not used at boot time
	 * and hence no memory allocations during large page split.
	 */
	if (enable)
		__set_pages_p(page, numpages);
	else
		__set_pages_np(page, numpages);

	/*
	 * We should perform an IPI and flush all tlbs,
	 * but that can deadlock->flush only current cpu:
	 */
	__flush_tlb_all();

	arch_flush_lazy_mmu_mode();
}

#ifdef CONFIG_HIBERNATION

bool kernel_page_present(struct page *page)
{
	unsigned int level;
	pte_t *pte;

	if (PageHighMem(page))
		return false;

	pte = lookup_address((unsigned long)page_address(page), &level);
	return (pte_val(*pte) & _PAGE_PRESENT);
}

#endif /* CONFIG_HIBERNATION */

#endif /* CONFIG_DEBUG_PAGEALLOC */

int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
			    unsigned numpages, unsigned long page_flags)
{
	int retval = -EINVAL;

	struct cpa_data cpa = {
		.vaddr = &address,
		.pfn = pfn,
		.pgd = pgd,
		.numpages = numpages,
		.mask_set = __pgprot(0),
		.mask_clr = __pgprot(0),
		.flags = 0,
	};

	if (!(__supported_pte_mask & _PAGE_NX))
		goto out;

	if (!(page_flags & _PAGE_NX))
		cpa.mask_clr = __pgprot(_PAGE_NX);

	cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags);

	retval = __change_page_attr_set_clr(&cpa, 0);
	__flush_tlb_all();

out:
	return retval;
}

void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
			       unsigned numpages)
{
	unmap_pgd_range(root, address, address + (numpages << PAGE_SHIFT));
}

/*
 * The testcases use internal knowledge of the implementation that shouldn't
 * be exposed to the rest of the kernel. Include these directly here.
 */
#ifdef CONFIG_CPA_DEBUG
#include "pageattr-test.c"
#endif