summaryrefslogtreecommitdiffstats
path: root/arch/x86/mm/pat/set_memory.c
blob: 19fdfbb171ed6ea2cd8e09d22a4404ac7fc2c6dd (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright 2002 Andi Kleen, SuSE Labs.
 * Thanks to Ben LaHaise for precious feedback.
 */
#include <linux/highmem.h>
#include <linux/memblock.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/debugfs.h>
#include <linux/pfn.h>
#include <linux/percpu.h>
#include <linux/gfp.h>
#include <linux/pci.h>
#include <linux/vmalloc.h>
#include <linux/libnvdimm.h>
#include <linux/vmstat.h>
#include <linux/kernel.h>
#include <linux/cc_platform.h>
#include <linux/set_memory.h>
#include <linux/memregion.h>

#include <asm/e820/api.h>
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <linux/uaccess.h>
#include <asm/pgalloc.h>
#include <asm/proto.h>
#include <asm/memtype.h>
#include <asm/hyperv-tlfs.h>
#include <asm/mshyperv.h>

#include "../mm_internal.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;
	unsigned long	numpages;
	unsigned long	curpage;
	unsigned long	pfn;
	unsigned int	flags;
	unsigned int	force_split		: 1,
			force_static_prot	: 1,
			force_flush_all		: 1;
	struct page	**pages;
};

enum cpa_warn {
	CPA_CONFLICT,
	CPA_PROTECT,
	CPA_DETECT,
};

static const int cpa_warn_level = CPA_PROTECT;

/*
 * 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
#define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */

static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm)
{
	return __pgprot(cachemode2protval(pcm));
}

#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)
{
	if (direct_pages_count[level] == 0)
		return;

	direct_pages_count[level]--;
	if (system_state == SYSTEM_RUNNING) {
		if (level == PG_LEVEL_2M)
			count_vm_event(DIRECT_MAP_LEVEL2_SPLIT);
		else if (level == PG_LEVEL_1G)
			count_vm_event(DIRECT_MAP_LEVEL3_SPLIT);
	}
	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
	if (direct_gbpages)
		seq_printf(m, "DirectMap1G:    %8lu kB\n",
			direct_pages_count[PG_LEVEL_1G] << 20);
}
#else
static inline void split_page_count(int level) { }
#endif

#ifdef CONFIG_X86_CPA_STATISTICS

static unsigned long cpa_1g_checked;
static unsigned long cpa_1g_sameprot;
static unsigned long cpa_1g_preserved;
static unsigned long cpa_2m_checked;
static unsigned long cpa_2m_sameprot;
static unsigned long cpa_2m_preserved;
static unsigned long cpa_4k_install;

static inline void cpa_inc_1g_checked(void)
{
	cpa_1g_checked++;
}

static inline void cpa_inc_2m_checked(void)
{
	cpa_2m_checked++;
}

static inline void cpa_inc_4k_install(void)
{
	data_race(cpa_4k_install++);
}

static inline void cpa_inc_lp_sameprot(int level)
{
	if (level == PG_LEVEL_1G)
		cpa_1g_sameprot++;
	else
		cpa_2m_sameprot++;
}

static inline void cpa_inc_lp_preserved(int level)
{
	if (level == PG_LEVEL_1G)
		cpa_1g_preserved++;
	else
		cpa_2m_preserved++;
}

static int cpastats_show(struct seq_file *m, void *p)
{
	seq_printf(m, "1G pages checked:     %16lu\n", cpa_1g_checked);
	seq_printf(m, "1G pages sameprot:    %16lu\n", cpa_1g_sameprot);
	seq_printf(m, "1G pages preserved:   %16lu\n", cpa_1g_preserved);
	seq_printf(m, "2M pages checked:     %16lu\n", cpa_2m_checked);
	seq_printf(m, "2M pages sameprot:    %16lu\n", cpa_2m_sameprot);
	seq_printf(m, "2M pages preserved:   %16lu\n", cpa_2m_preserved);
	seq_printf(m, "4K pages set-checked: %16lu\n", cpa_4k_install);
	return 0;
}

static int cpastats_open(struct inode *inode, struct file *file)
{
	return single_open(file, cpastats_show, NULL);
}

static const struct file_operations cpastats_fops = {
	.open		= cpastats_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};

static int __init cpa_stats_init(void)
{
	debugfs_create_file("cpa_stats", S_IRUSR, arch_debugfs_dir, NULL,
			    &cpastats_fops);
	return 0;
}
late_initcall(cpa_stats_init);
#else
static inline void cpa_inc_1g_checked(void) { }
static inline void cpa_inc_2m_checked(void) { }
static inline void cpa_inc_4k_install(void) { }
static inline void cpa_inc_lp_sameprot(int level) { }
static inline void cpa_inc_lp_preserved(int level) { }
#endif


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

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

#ifdef CONFIG_X86_64

/*
 * The kernel image is mapped into two places in the virtual address space
 * (addresses without KASLR, of course):
 *
 * 1. The kernel direct map (0xffff880000000000)
 * 2. The "high kernel map" (0xffffffff81000000)
 *
 * We actually execute out of #2. If we get the address of a kernel symbol, it
 * points to #2, but almost all physical-to-virtual translations point to #1.
 *
 * This is so that we can have both a directmap of all physical memory *and*
 * take full advantage of the limited (s32) immediate addressing range (2G)
 * of x86_64.
 *
 * See Documentation/arch/x86/x86_64/mm.rst for more detail.
 */

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

static inline unsigned long highmap_end_pfn(void)
{
	/* Do not reference physical address outside the kernel. */
	return __pa_symbol(roundup(_brk_end, PMD_SIZE) - 1) >> PAGE_SHIFT;
}

static bool __cpa_pfn_in_highmap(unsigned long pfn)
{
	/*
	 * Kernel text has an alias mapping at a high address, known
	 * here as "highmap".
	 */
	return within_inclusive(pfn, highmap_start_pfn(), highmap_end_pfn());
}

#else

static bool __cpa_pfn_in_highmap(unsigned long pfn)
{
	/* There is no highmap on 32-bit */
	return false;
}

#endif

/*
 * See set_mce_nospec().
 *
 * Machine check recovery code needs to change cache mode of poisoned pages to
 * UC to avoid speculative access logging another error. But passing the
 * address of the 1:1 mapping to set_memory_uc() is a fine way to encourage a
 * speculative access. So we cheat and flip the top bit of the address. This
 * works fine for the code that updates the page tables. But at the end of the
 * process we need to flush the TLB and cache and the non-canonical address
 * causes a #GP fault when used by the INVLPG and CLFLUSH instructions.
 *
 * But in the common case we already have a canonical address. This code
 * will fix the top bit if needed and is a no-op otherwise.
 */
static inline unsigned long fix_addr(unsigned long addr)
{
#ifdef CONFIG_X86_64
	return (long)(addr << 1) >> 1;
#else
	return addr;
#endif
}

static unsigned long __cpa_addr(struct cpa_data *cpa, unsigned long idx)
{
	if (cpa->flags & CPA_PAGES_ARRAY) {
		struct page *page = cpa->pages[idx];

		if (unlikely(PageHighMem(page)))
			return 0;

		return (unsigned long)page_address(page);
	}

	if (cpa->flags & CPA_ARRAY)
		return cpa->vaddr[idx];

	return *cpa->vaddr + idx * PAGE_SIZE;
}

/*
 * Flushing functions
 */

static void clflush_cache_range_opt(void *vaddr, unsigned int size)
{
	const unsigned long clflush_size = boot_cpu_data.x86_clflush_size;
	void *p = (void *)((unsigned long)vaddr & ~(clflush_size - 1));
	void *vend = vaddr + size;

	if (p >= vend)
		return;

	for (; p < vend; p += clflush_size)
		clflushopt(p);
}

/**
 * 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)
{
	mb();
	clflush_cache_range_opt(vaddr, size);
	mb();
}
EXPORT_SYMBOL_GPL(clflush_cache_range);

#ifdef CONFIG_ARCH_HAS_PMEM_API
void arch_invalidate_pmem(void *addr, size_t size)
{
	clflush_cache_range(addr, size);
}
EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
#endif

#ifdef CONFIG_ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
bool cpu_cache_has_invalidate_memregion(void)
{
	return !cpu_feature_enabled(X86_FEATURE_HYPERVISOR);
}
EXPORT_SYMBOL_NS_GPL(cpu_cache_has_invalidate_memregion, DEVMEM);

int cpu_cache_invalidate_memregion(int res_desc)
{
	if (WARN_ON_ONCE(!cpu_cache_has_invalidate_memregion()))
		return -ENXIO;
	wbinvd_on_all_cpus();
	return 0;
}
EXPORT_SYMBOL_NS_GPL(cpu_cache_invalidate_memregion, DEVMEM);
#endif

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() && !early_boot_irqs_disabled);

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

static void __cpa_flush_tlb(void *data)
{
	struct cpa_data *cpa = data;
	unsigned int i;

	for (i = 0; i < cpa->numpages; i++)
		flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i)));
}

static void cpa_flush(struct cpa_data *data, int cache)
{
	struct cpa_data *cpa = data;
	unsigned int i;

	BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);

	if (cache && !static_cpu_has(X86_FEATURE_CLFLUSH)) {
		cpa_flush_all(cache);
		return;
	}

	if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling)
		flush_tlb_all();
	else
		on_each_cpu(__cpa_flush_tlb, cpa, 1);

	if (!cache)
		return;

	mb();
	for (i = 0; i < cpa->numpages; i++) {
		unsigned long addr = __cpa_addr(cpa, i);
		unsigned int level;

		pte_t *pte = lookup_address(addr, &level);

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

static bool overlaps(unsigned long r1_start, unsigned long r1_end,
		     unsigned long r2_start, unsigned long r2_end)
{
	return (r1_start <= r2_end && r1_end >= r2_start) ||
		(r2_start <= r1_end && r2_end >= r1_start);
}

#ifdef CONFIG_PCI_BIOS
/*
 * The BIOS area between 640k and 1Mb needs to be executable for PCI BIOS
 * based config access (CONFIG_PCI_GOBIOS) support.
 */
#define BIOS_PFN	PFN_DOWN(BIOS_BEGIN)
#define BIOS_PFN_END	PFN_DOWN(BIOS_END - 1)

static pgprotval_t protect_pci_bios(unsigned long spfn, unsigned long epfn)
{
	if (pcibios_enabled && overlaps(spfn, epfn, BIOS_PFN, BIOS_PFN_END))
		return _PAGE_NX;
	return 0;
}
#else
static pgprotval_t protect_pci_bios(unsigned long spfn, unsigned long epfn)
{
	return 0;
}
#endif

/*
 * The .rodata section needs to be read-only. Using the pfn catches all
 * aliases.  This also includes __ro_after_init, so do not enforce until
 * kernel_set_to_readonly is true.
 */
static pgprotval_t protect_rodata(unsigned long spfn, unsigned long epfn)
{
	unsigned long epfn_ro, spfn_ro = PFN_DOWN(__pa_symbol(__start_rodata));

	/*
	 * Note: __end_rodata is at page aligned and not inclusive, so
	 * subtract 1 to get the last enforced PFN in the rodata area.
	 */
	epfn_ro = PFN_DOWN(__pa_symbol(__end_rodata)) - 1;

	if (kernel_set_to_readonly && overlaps(spfn, epfn, spfn_ro, epfn_ro))
		return _PAGE_RW;
	return 0;
}

/*
 * Protect kernel text against becoming non executable by forbidding
 * _PAGE_NX.  This protects only the high kernel mapping (_text -> _etext)
 * out of which the kernel actually executes.  Do not protect the low
 * mapping.
 *
 * This does not cover __inittext since that is gone after boot.
 */
static pgprotval_t protect_kernel_text(unsigned long start, unsigned long end)
{
	unsigned long t_end = (unsigned long)_etext - 1;
	unsigned long t_start = (unsigned long)_text;

	if (overlaps(start, end, t_start, t_end))
		return _PAGE_NX;
	return 0;
}

#if defined(CONFIG_X86_64)
/*
 * 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.
 */
static pgprotval_t protect_kernel_text_ro(unsigned long start,
					  unsigned long end)
{
	unsigned long t_end = (unsigned long)__end_rodata_hpage_align - 1;
	unsigned long t_start = (unsigned long)_text;
	unsigned int level;

	if (!kernel_set_to_readonly || !overlaps(start, end, t_start, t_end))
		return 0;
	/*
	 * 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 caused
	 * by 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,
	 * so the protections for kernel text and identity mappings have to
	 * be the same.
	 */
	if (lookup_address(start, &level) && (level != PG_LEVEL_4K))
		return _PAGE_RW;
	return 0;
}
#else
static pgprotval_t protect_kernel_text_ro(unsigned long start,
					  unsigned long end)
{
	return 0;
}
#endif

static inline bool conflicts(pgprot_t prot, pgprotval_t val)
{
	return (pgprot_val(prot) & ~val) != pgprot_val(prot);
}

static inline void check_conflict(int warnlvl, pgprot_t prot, pgprotval_t val,
				  unsigned long start, unsigned long end,
				  unsigned long pfn, const char *txt)
{
	static const char *lvltxt[] = {
		[CPA_CONFLICT]	= "conflict",
		[CPA_PROTECT]	= "protect",
		[CPA_DETECT]	= "detect",
	};

	if (warnlvl > cpa_warn_level || !conflicts(prot, val))
		return;

	pr_warn("CPA %8s %10s: 0x%016lx - 0x%016lx PFN %lx req %016llx prevent %016llx\n",
		lvltxt[warnlvl], txt, start, end, pfn, (unsigned long long)pgprot_val(prot),
		(unsigned long long)val);
}

/*
 * 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 start,
					  unsigned long pfn, unsigned long npg,
					  unsigned long lpsize, int warnlvl)
{
	pgprotval_t forbidden, res;
	unsigned long end;

	/*
	 * There is no point in checking RW/NX conflicts when the requested
	 * mapping is setting the page !PRESENT.
	 */
	if (!(pgprot_val(prot) & _PAGE_PRESENT))
		return prot;

	/* Operate on the virtual address */
	end = start + npg * PAGE_SIZE - 1;

	res = protect_kernel_text(start, end);
	check_conflict(warnlvl, prot, res, start, end, pfn, "Text NX");
	forbidden = res;

	/*
	 * Special case to preserve a large page. If the change spawns the
	 * full large page mapping then there is no point to split it
	 * up. Happens with ftrace and is going to be removed once ftrace
	 * switched to text_poke().
	 */
	if (lpsize != (npg * PAGE_SIZE) || (start & (lpsize - 1))) {
		res = protect_kernel_text_ro(start, end);
		check_conflict(warnlvl, prot, res, start, end, pfn, "Text RO");
		forbidden |= res;
	}

	/* Check the PFN directly */
	res = protect_pci_bios(pfn, pfn + npg - 1);
	check_conflict(warnlvl, prot, res, start, end, pfn, "PCIBIOS NX");
	forbidden |= res;

	res = protect_rodata(pfn, pfn + npg - 1);
	check_conflict(warnlvl, prot, res, start, end, pfn, "Rodata RO");
	forbidden |= res;

	return __pgprot(pgprot_val(prot) & ~forbidden);
}

/*
 * Validate strict W^X semantics.
 */
static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long start,
				  unsigned long pfn, unsigned long npg,
				  bool nx, bool rw)
{
	unsigned long end;

	/*
	 * 32-bit has some unfixable W+X issues, like EFI code
	 * and writeable data being in the same page.  Disable
	 * detection and enforcement there.
	 */
	if (IS_ENABLED(CONFIG_X86_32))
		return new;

	/* Only verify when NX is supported: */
	if (!(__supported_pte_mask & _PAGE_NX))
		return new;

	if (!((pgprot_val(old) ^ pgprot_val(new)) & (_PAGE_RW | _PAGE_NX)))
		return new;

	if ((pgprot_val(new) & (_PAGE_RW | _PAGE_NX)) != _PAGE_RW)
		return new;

	/* Non-leaf translation entries can disable writing or execution. */
	if (!rw || nx)
		return new;

	end = start + npg * PAGE_SIZE - 1;
	WARN_ONCE(1, "CPA detected W^X violation: %016llx -> %016llx range: 0x%016lx - 0x%016lx PFN %lx\n",
		  (unsigned long long)pgprot_val(old),
		  (unsigned long long)pgprot_val(new),
		  start, end, pfn);

	/*
	 * For now, allow all permission change attempts by returning the
	 * attempted permissions.  This can 'return old' to actively
	 * refuse the permission change at a later time.
	 */
	return new;
}

/*
 * Lookup the page table entry for a virtual address in a specific pgd.
 * Return a pointer to the entry, the level of the mapping, and the effective
 * NX and RW bits of all page table levels.
 */
pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
				  unsigned int *level, bool *nx, bool *rw)
{
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;

	*level = PG_LEVEL_NONE;
	*nx = false;
	*rw = true;

	if (pgd_none(*pgd))
		return NULL;

	*nx |= pgd_flags(*pgd) & _PAGE_NX;
	*rw &= pgd_flags(*pgd) & _PAGE_RW;

	p4d = p4d_offset(pgd, address);
	if (p4d_none(*p4d))
		return NULL;

	*level = PG_LEVEL_512G;
	if (p4d_leaf(*p4d) || !p4d_present(*p4d))
		return (pte_t *)p4d;

	*nx |= p4d_flags(*p4d) & _PAGE_NX;
	*rw &= p4d_flags(*p4d) & _PAGE_RW;

	pud = pud_offset(p4d, address);
	if (pud_none(*pud))
		return NULL;

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

	*nx |= pud_flags(*pud) & _PAGE_NX;
	*rw &= pud_flags(*pud) & _PAGE_RW;

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

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

	*nx |= pmd_flags(*pmd) & _PAGE_NX;
	*rw &= pmd_flags(*pmd) & _PAGE_RW;

	*level = PG_LEVEL_4K;

	return pte_offset_kernel(pmd, address);
}

/*
 * 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)
{
	bool nx, rw;

	return lookup_address_in_pgd_attr(pgd, address, level, &nx, &rw);
}

/*
 * 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, bool *nx, bool *rw)
{
	pgd_t *pgd;

	if (!cpa->pgd)
		pgd = pgd_offset_k(address);
	else
		pgd = cpa->pgd + pgd_index(address);

	return lookup_address_in_pgd_attr(pgd, address, level, nx, rw);
}

/*
 * Lookup the PMD entry for a virtual address. Return a pointer to the entry
 * or NULL if not present.
 */
pmd_t *lookup_pmd_address(unsigned long address)
{
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;

	pgd = pgd_offset_k(address);
	if (pgd_none(*pgd))
		return NULL;

	p4d = p4d_offset(pgd, address);
	if (p4d_none(*p4d) || p4d_leaf(*p4d) || !p4d_present(*p4d))
		return NULL;

	pud = pud_offset(p4d, address);
	if (pud_none(*pud) || pud_leaf(*pud) || !pud_present(*pud))
		return NULL;

	return pmd_offset(pud, address);
}

/*
 * 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.
 *
 * Note that as long as the PTEs are well-formed with correct PFNs, this
 * works without checking the PRESENT bit in the leaf PTE.  This is unlike
 * the similar vmalloc_to_page() and derivatives.  Callers may depend on
 * this behavior.
 *
 * This could be optimized, but it is only used in paths that are not perf
 * sensitive, 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;
	pte_t *pte;

	pte = lookup_address(virt_addr, &level);
	BUG_ON(!pte);

	/*
	 * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t
	 * before being left-shifted PAGE_SHIFT bits -- this trick is to
	 * make 32-PAE kernel work correctly.
	 */
	switch (level) {
	case PG_LEVEL_1G:
		phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT;
		offset = virt_addr & ~PUD_MASK;
		break;
	case PG_LEVEL_2M:
		phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT;
		offset = virt_addr & ~PMD_MASK;
		break;
	default:
		phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
		offset = virt_addr & ~PAGE_MASK;
	}

	return (phys_addr_t)(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;
			p4d_t *p4d;
			pud_t *pud;
			pmd_t *pmd;

			pgd = (pgd_t *)page_address(page) + pgd_index(address);
			p4d = p4d_offset(pgd, address);
			pud = pud_offset(p4d, address);
			pmd = pmd_offset(pud, address);
			set_pte_atomic((pte_t *)pmd, pte);
		}
	}
#endif
}

static pgprot_t pgprot_clear_protnone_bits(pgprot_t prot)
{
	/*
	 * _PAGE_GLOBAL means "global page" for present PTEs.
	 * But, it is also used to indicate _PAGE_PROTNONE
	 * for non-present PTEs.
	 *
	 * This ensures that a _PAGE_GLOBAL PTE going from
	 * present to non-present is not confused as
	 * _PAGE_PROTNONE.
	 */
	if (!(pgprot_val(prot) & _PAGE_PRESENT))
		pgprot_val(prot) &= ~_PAGE_GLOBAL;

	return prot;
}

static int __should_split_large_page(pte_t *kpte, unsigned long address,
				     struct cpa_data *cpa)
{
	unsigned long numpages, pmask, psize, lpaddr, pfn, old_pfn;
	pgprot_t old_prot, new_prot, req_prot, chk_prot;
	pte_t new_pte, *tmp;
	enum pg_level level;
	bool nx, rw;

	/*
	 * Check for races, another CPU might have split this page
	 * up already:
	 */
	tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw);
	if (tmp != kpte)
		return 1;

	switch (level) {
	case PG_LEVEL_2M:
		old_prot = pmd_pgprot(*(pmd_t *)kpte);
		old_pfn = pmd_pfn(*(pmd_t *)kpte);
		cpa_inc_2m_checked();
		break;
	case PG_LEVEL_1G:
		old_prot = pud_pgprot(*(pud_t *)kpte);
		old_pfn = pud_pfn(*(pud_t *)kpte);
		cpa_inc_1g_checked();
		break;
	default:
		return -EINVAL;
	}

	psize = page_level_size(level);
	pmask = page_level_mask(level);

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

	/*
	 * We are safe now. Check whether the new pgprot is the same:
	 * Convert protection attributes to 4k-format, as cpa->mask* are set
	 * up accordingly.
	 */

	/* Clear PSE (aka _PAGE_PAT) and move PAT bit to correct position */
	req_prot = pgprot_large_2_4k(old_prot);

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

	/*
	 * req_prot is in format of 4k pages. It must be converted to large
	 * page format: the caching mode includes the PAT bit located at
	 * different bit positions in the two formats.
	 */
	req_prot = pgprot_4k_2_large(req_prot);
	req_prot = pgprot_clear_protnone_bits(req_prot);
	if (pgprot_val(req_prot) & _PAGE_PRESENT)
		pgprot_val(req_prot) |= _PAGE_PSE;

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

	/*
	 * Calculate the large page base address and the number of 4K pages
	 * in the large page
	 */
	lpaddr = address & pmask;
	numpages = psize >> PAGE_SHIFT;

	/*
	 * Sanity check that the existing mapping is correct versus the static
	 * protections. static_protections() guards against !PRESENT, so no
	 * extra conditional required here.
	 */
	chk_prot = static_protections(old_prot, lpaddr, old_pfn, numpages,
				      psize, CPA_CONFLICT);

	if (WARN_ON_ONCE(pgprot_val(chk_prot) != pgprot_val(old_prot))) {
		/*
		 * Split the large page and tell the split code to
		 * enforce static protections.
		 */
		cpa->force_static_prot = 1;
		return 1;
	}

	/*
	 * Optimization: If the requested pgprot is the same as the current
	 * pgprot, then the large page can be preserved and no updates are
	 * required independent of alignment and length of the requested
	 * range. The above already established that the current pgprot is
	 * correct, which in consequence makes the requested pgprot correct
	 * as well if it is the same. The static protection scan below will
	 * not come to a different conclusion.
	 */
	if (pgprot_val(req_prot) == pgprot_val(old_prot)) {
		cpa_inc_lp_sameprot(level);
		return 0;
	}

	/*
	 * If the requested range does not cover the full page, split it up
	 */
	if (address != lpaddr || cpa->numpages != numpages)
		return 1;

	/*
	 * Check whether the requested pgprot is conflicting with a static
	 * protection requirement in the large page.
	 */
	new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages,
				      psize, CPA_DETECT);

	new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages,
			      nx, rw);

	/*
	 * If there is a conflict, split the large page.
	 *
	 * There used to be a 4k wise evaluation trying really hard to
	 * preserve the large pages, but experimentation has shown, that this
	 * does not help at all. There might be corner cases which would
	 * preserve one large page occasionally, but it's really not worth the
	 * extra code and cycles for the common case.
	 */
	if (pgprot_val(req_prot) != pgprot_val(new_prot))
		return 1;

	/* All checks passed. Update the large page mapping. */
	new_pte = pfn_pte(old_pfn, new_prot);
	__set_pmd_pte(kpte, address, new_pte);
	cpa->flags |= CPA_FLUSHTLB;
	cpa_inc_lp_preserved(level);
	return 0;
}

static int should_split_large_page(pte_t *kpte, unsigned long address,
				   struct cpa_data *cpa)
{
	int do_split;

	if (cpa->force_split)
		return 1;

	spin_lock(&pgd_lock);
	do_split = __should_split_large_page(kpte, address, cpa);
	spin_unlock(&pgd_lock);

	return do_split;
}

static void split_set_pte(struct cpa_data *cpa, pte_t *pte, unsigned long pfn,
			  pgprot_t ref_prot, unsigned long address,
			  unsigned long size)
{
	unsigned int npg = PFN_DOWN(size);
	pgprot_t prot;

	/*
	 * If should_split_large_page() discovered an inconsistent mapping,
	 * remove the invalid protection in the split mapping.
	 */
	if (!cpa->force_static_prot)
		goto set;

	/* Hand in lpsize = 0 to enforce the protection mechanism */
	prot = static_protections(ref_prot, address, pfn, npg, 0, CPA_PROTECT);

	if (pgprot_val(prot) == pgprot_val(ref_prot))
		goto set;

	/*
	 * If this is splitting a PMD, fix it up. PUD splits cannot be
	 * fixed trivially as that would require to rescan the newly
	 * installed PMD mappings after returning from split_large_page()
	 * so an eventual further split can allocate the necessary PTE
	 * pages. Warn for now and revisit it in case this actually
	 * happens.
	 */
	if (size == PAGE_SIZE)
		ref_prot = prot;
	else
		pr_warn_once("CPA: Cannot fixup static protections for PUD split\n");
set:
	set_pte(pte, pfn_pte(pfn, ref_prot));
}

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

	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, &nx, &rw);
	if (tmp != kpte) {
		spin_unlock(&pgd_lock);
		return 1;
	}

	paravirt_alloc_pte(&init_mm, page_to_pfn(base));

	switch (level) {
	case PG_LEVEL_2M:
		ref_prot = pmd_pgprot(*(pmd_t *)kpte);
		/*
		 * Clear PSE (aka _PAGE_PAT) and move
		 * PAT bit to correct position.
		 */
		ref_prot = pgprot_large_2_4k(ref_prot);
		ref_pfn = pmd_pfn(*(pmd_t *)kpte);
		lpaddr = address & PMD_MASK;
		lpinc = PAGE_SIZE;
		break;

	case PG_LEVEL_1G:
		ref_prot = pud_pgprot(*(pud_t *)kpte);
		ref_pfn = pud_pfn(*(pud_t *)kpte);
		pfninc = PMD_SIZE >> PAGE_SHIFT;
		lpaddr = address & PUD_MASK;
		lpinc = PMD_SIZE;
		/*
		 * Clear the PSE flags if the PRESENT flag is not 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;
		break;

	default:
		spin_unlock(&pgd_lock);
		return 1;
	}

	ref_prot = pgprot_clear_protnone_bits(ref_prot);

	/*
	 * Get the target pfn from the original entry:
	 */
	pfn = ref_pfn;
	for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc, lpaddr += lpinc)
		split_set_pte(cpa, pbase + i, pfn, ref_prot, lpaddr, lpinc);

	if (virt_addr_valid(address)) {
		unsigned long pfn = PFN_DOWN(__pa(address));

		if (pfn_range_is_mapped(pfn, pfn + 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)));

	/*
	 * Do a global flush tlb after splitting the large page
	 * and before we do the actual change page attribute in the PTE.
	 *
	 * Without 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();
	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_enabled())
		spin_unlock(&cpa_lock);
	base = alloc_pages(GFP_KERNEL, 0);
	if (!debug_pagealloc_enabled())
		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 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(pud_pgtable(*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_leaf(*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(pud_pgtable(*pud)))
			pud_clear(pud);
}

static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end)
{
	pud_t *pud = pud_offset(p4d, 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_leaf(*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 int alloc_pte_page(pmd_t *pmd)
{
	pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL);
	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);
	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);

	pgprot = pgprot_clear_protnone_bits(pgprot);

	while (num_pages-- && start < end) {
		set_pte(pte, pfn_pte(cpa->pfn, pgprot));

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

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

	/*
	 * 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;

	pmd_pgprot = pgprot_4k_2_large(pgprot);

	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_mkhuge(pfn_pmd(cpa->pfn,
					canon_pgprot(pmd_pgprot))));

		start	  += PMD_SIZE;
		cpa->pfn  += PMD_SIZE >> PAGE_SHIFT;
		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, p4d_t *p4d,
			pgprot_t pgprot)
{
	pud_t *pud;
	unsigned long end;
	long cur_pages = 0;
	pgprot_t pud_pgprot;

	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(p4d, 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(p4d, start);
	pud_pgprot = pgprot_4k_2_large(pgprot);

	/*
	 * Map everything starting from the Gb boundary, possibly with 1G pages
	 */
	while (boot_cpu_has(X86_FEATURE_GBPAGES) && end - start >= PUD_SIZE) {
		set_pud(pud, pud_mkhuge(pfn_pud(cpa->pfn,
				   canon_pgprot(pud_pgprot))));

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

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

		pud = pud_offset(p4d, 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 */
	p4d_t *p4d;
	pgd_t *pgd_entry;
	long ret;

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

	if (pgd_none(*pgd_entry)) {
		p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL);
		if (!p4d)
			return -1;

		set_pgd(pgd_entry, __pgd(__pa(p4d) | _KERNPG_TABLE));
	}

	/*
	 * Allocate a PUD page and hand it down for mapping.
	 */
	p4d = p4d_offset(pgd_entry, addr);
	if (p4d_none(*p4d)) {
		pud = (pud_t *)get_zeroed_page(GFP_KERNEL);
		if (!pud)
			return -1;

		set_p4d(p4d, __p4d(__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, p4d, pgprot);
	if (ret < 0) {
		/*
		 * Leave the PUD page in place in case some other CPU or thread
		 * already found it, but remove any useless entries we just
		 * added to it.
		 */
		unmap_pud_range(p4d, 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) {
		/*
		 * Right now, we only execute this code path when mapping
		 * the EFI virtual memory map regions, no other users
		 * provide a ->pgd value. This may change in the future.
		 */
		return populate_pgd(cpa, vaddr);
	}

	/*
	 * Ignore all non primary paths.
	 */
	if (!primary) {
		cpa->numpages = 1;
		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 if (__cpa_pfn_in_highmap(cpa->pfn)) {
		/* Faults in the highmap are OK, so do not warn: */
		return -EFAULT;
	} 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;
	bool nx, rw;

	address = __cpa_addr(cpa, cpa->curpage);
repeat:
	kpte = _lookup_address_cpa(cpa, address, &level, &nx, &rw);
	if (!kpte)
		return __cpa_process_fault(cpa, address, primary);

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

	if (level == PG_LEVEL_4K) {
		pte_t new_pte;
		pgprot_t old_prot = pte_pgprot(old_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);

		cpa_inc_4k_install();
		/* Hand in lpsize = 0 to enforce the protection mechanism */
		new_prot = static_protections(new_prot, address, pfn, 1, 0,
					      CPA_PROTECT);

		new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1,
				      nx, rw);

		new_prot = pgprot_clear_protnone_bits(new_prot);

		/*
		 * We need to keep the pfn from the existing PTE,
		 * after all we're only going to change its attributes
		 * not the memory it points to
		 */
		new_pte = pfn_pte(pfn, 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 = should_split_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)
		goto repeat;

	return err;
}

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

/*
 * Check the directmap and "high kernel map" 'aliases'.
 */
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:
	 */
	vaddr = __cpa_addr(cpa, cpa->curpage);
	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);
		alias_cpa.curpage = 0;

		/* Directmap always has NX set, do not modify. */
		if (__supported_pte_mask & _PAGE_NX) {
			alias_cpa.mask_clr.pgprot &= ~_PAGE_NX;
			alias_cpa.mask_set.pgprot &= ~_PAGE_NX;
		}

		cpa->force_flush_all = 1;

		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) &&
	    __cpa_pfn_in_highmap(cpa->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);
		alias_cpa.curpage = 0;

		/*
		 * [_text, _brk_end) also covers data, do not modify NX except
		 * in cases where the highmap is the primary target.
		 */
		if (__supported_pte_mask & _PAGE_NX) {
			alias_cpa.mask_clr.pgprot &= ~_PAGE_NX;
			alias_cpa.mask_set.pgprot &= ~_PAGE_NX;
		}

		cpa->force_flush_all = 1;
		/*
		 * 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 primary)
{
	unsigned long numpages = cpa->numpages;
	unsigned long rempages = numpages;
	int ret = 0;

	/*
	 * No changes, easy!
	 */
	if (!(pgprot_val(cpa->mask_set) | pgprot_val(cpa->mask_clr)) &&
	    !cpa->force_split)
		return ret;

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

		if (!debug_pagealloc_enabled())
			spin_lock(&cpa_lock);
		ret = __change_page_attr(cpa, primary);
		if (!debug_pagealloc_enabled())
			spin_unlock(&cpa_lock);
		if (ret)
			goto out;

		if (primary && !(cpa->flags & CPA_NO_CHECK_ALIAS)) {
			ret = cpa_process_alias(cpa);
			if (ret)
				goto out;
		}

		/*
		 * 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 > rempages || !cpa->numpages);
		rempages -= cpa->numpages;
		cpa->curpage += cpa->numpages;
	}

out:
	/* Restore the original numpages */
	cpa->numpages = numpages;
	return ret;
}

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;

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

	/*
	 * Check, if we are requested to set a not supported
	 * feature.  Clearing non-supported features is OK.
	 */
	mask_set = canon_pgprot(mask_set);

	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 check in that case
		 */
		if (*addr & ~PAGE_MASK) {
			*addr &= PAGE_MASK;
			/*
			 * People should not be passing in unaligned addresses:
			 */
			WARN_ON_ONCE(1);
		}
	}

	/* 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 = in_flag;
	cpa.curpage = 0;
	cpa.force_split = force_split;

	ret = __change_page_attr_set_clr(&cpa, 1);

	/*
	 * 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 = !!pgprot2cachemode(mask_set);

	/*
	 * On error; flush everything to be sure.
	 */
	if (ret) {
		cpa_flush_all(cache);
		goto out;
	}

	cpa_flush(&cpa, 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);
}

/*
 * __set_memory_prot is an internal helper for callers that have been passed
 * a pgprot_t value from upper layers and a reservation has already been taken.
 * If you want to set the pgprot to a specific page protocol, use the
 * set_memory_xx() functions.
 */
int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot)
{
	return change_page_attr_set_clr(&addr, numpages, prot,
					__pgprot(~pgprot_val(prot)), 0, 0,
					NULL);
}

int _set_memory_uc(unsigned long addr, int numpages)
{
	/*
	 * for now UC MINUS. see comments in ioremap()
	 * If you really need strong UC use ioremap_uc(), but note
	 * that you cannot override IO areas with set_memory_*() as
	 * these helpers cannot work with IO memory.
	 */
	return change_page_attr_set(&addr, numpages,
				    cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
				    0);
}

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

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

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

	return 0;

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

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

	ret = change_page_attr_set(&addr, numpages,
				   cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
				   0);
	if (!ret) {
		ret = change_page_attr_set_clr(&addr, numpages,
					       cachemode2pgprot(_PAGE_CACHE_MODE_WC),
					       __pgprot(_PAGE_CACHE_MASK),
					       0, 0, NULL);
	}
	return ret;
}

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

	ret = memtype_reserve(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
		_PAGE_CACHE_MODE_WC, NULL);
	if (ret)
		return ret;

	ret = _set_memory_wc(addr, numpages);
	if (ret)
		memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);

	return ret;
}
EXPORT_SYMBOL(set_memory_wc);

int _set_memory_wt(unsigned long addr, int numpages)
{
	return change_page_attr_set(&addr, numpages,
				    cachemode2pgprot(_PAGE_CACHE_MODE_WT), 0);
}

int _set_memory_wb(unsigned long addr, int numpages)
{
	/* WB cache mode is hard wired to all cache attribute bits being 0 */
	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;

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

/* Prevent speculative access to a page by marking it not-present */
#ifdef CONFIG_X86_64
int set_mce_nospec(unsigned long pfn)
{
	unsigned long decoy_addr;
	int rc;

	/* SGX pages are not in the 1:1 map */
	if (arch_is_platform_page(pfn << PAGE_SHIFT))
		return 0;
	/*
	 * We would like to just call:
	 *      set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1);
	 * but doing that would radically increase the odds of a
	 * speculative access to the poison page because we'd have
	 * the virtual address of the kernel 1:1 mapping sitting
	 * around in registers.
	 * Instead we get tricky.  We create a non-canonical address
	 * that looks just like the one we want, but has bit 63 flipped.
	 * This relies on set_memory_XX() properly sanitizing any __pa()
	 * results with __PHYSICAL_MASK or PTE_PFN_MASK.
	 */
	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));

	rc = set_memory_np(decoy_addr, 1);
	if (rc)
		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
	return rc;
}

/* Restore full speculative operation to the pfn. */
int clear_mce_nospec(unsigned long pfn)
{
	unsigned long addr = (unsigned long) pfn_to_kaddr(pfn);

	return set_memory_p(addr, 1);
}
EXPORT_SYMBOL_GPL(clear_mce_nospec);
#endif /* CONFIG_X86_64 */

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);
}

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);
}

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

int set_memory_rox(unsigned long addr, int numpages)
{
	pgprot_t clr = __pgprot(_PAGE_RW | _PAGE_DIRTY);

	if (__supported_pte_mask & _PAGE_NX)
		clr.pgprot |= _PAGE_NX;

	return change_page_attr_clear(&addr, numpages, clr, 0);
}

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

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

int set_memory_np_noalias(unsigned long addr, int numpages)
{
	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
					__pgprot(_PAGE_PRESENT), 0,
					CPA_NO_CHECK_ALIAS, NULL);
}

int set_memory_p(unsigned long addr, int numpages)
{
	return change_page_attr_set(&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_memory_nonglobal(unsigned long addr, int numpages)
{
	return change_page_attr_clear(&addr, numpages,
				      __pgprot(_PAGE_GLOBAL), 0);
}

int set_memory_global(unsigned long addr, int numpages)
{
	return change_page_attr_set(&addr, numpages,
				    __pgprot(_PAGE_GLOBAL), 0);
}

/*
 * __set_memory_enc_pgtable() is used for the hypervisors that get
 * informed about "encryption" status via page tables.
 */
static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
{
	pgprot_t empty = __pgprot(0);
	struct cpa_data cpa;
	int ret;

	/* Should not be working on unaligned addresses */
	if (WARN_ONCE(addr & ~PAGE_MASK, "misaligned address: %#lx\n", addr))
		addr &= PAGE_MASK;

	memset(&cpa, 0, sizeof(cpa));
	cpa.vaddr = &addr;
	cpa.numpages = numpages;
	cpa.mask_set = enc ? pgprot_encrypted(empty) : pgprot_decrypted(empty);
	cpa.mask_clr = enc ? pgprot_decrypted(empty) : pgprot_encrypted(empty);
	cpa.pgd = init_mm.pgd;

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

	/* Flush the caches as needed before changing the encryption attribute. */
	if (x86_platform.guest.enc_tlb_flush_required(enc))
		cpa_flush(&cpa, x86_platform.guest.enc_cache_flush_required());

	/* Notify hypervisor that we are about to set/clr encryption attribute. */
	if (!x86_platform.guest.enc_status_change_prepare(addr, numpages, enc))
		goto vmm_fail;

	ret = __change_page_attr_set_clr(&cpa, 1);

	/*
	 * After changing the encryption attribute, we need to flush TLBs again
	 * in case any speculative TLB caching occurred (but no need to flush
	 * caches again).  We could just use cpa_flush_all(), but in case TLB
	 * flushing gets optimized in the cpa_flush() path use the same logic
	 * as above.
	 */
	cpa_flush(&cpa, 0);

	if (ret)
		return ret;

	/* Notify hypervisor that we have successfully set/clr encryption attribute. */
	if (!x86_platform.guest.enc_status_change_finish(addr, numpages, enc))
		goto vmm_fail;

	return 0;

vmm_fail:
	WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s.\n",
		  (void *)addr, numpages, enc ? "private" : "shared");

	return -EIO;
}

static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
{
	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
		return __set_memory_enc_pgtable(addr, numpages, enc);

	return 0;
}

int set_memory_encrypted(unsigned long addr, int numpages)
{
	return __set_memory_enc_dec(addr, numpages, true);
}
EXPORT_SYMBOL_GPL(set_memory_encrypted);

int set_memory_decrypted(unsigned long addr, int numpages)
{
	return __set_memory_enc_dec(addr, numpages, false);
}
EXPORT_SYMBOL_GPL(set_memory_decrypted);

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 numpages,
		enum page_cache_mode new_type)
{
	unsigned long start;
	unsigned long end;
	enum page_cache_mode set_type;
	int i;
	int free_idx;
	int ret;

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

	/* If WC, set to UC- first and then WC */
	set_type = (new_type == _PAGE_CACHE_MODE_WC) ?
				_PAGE_CACHE_MODE_UC_MINUS : new_type;

	ret = cpa_set_pages_array(pages, numpages,
				  cachemode2pgprot(set_type));
	if (!ret && new_type == _PAGE_CACHE_MODE_WC)
		ret = change_page_attr_set_clr(NULL, numpages,
					       cachemode2pgprot(
						_PAGE_CACHE_MODE_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;
		memtype_free(start, end);
	}
	return -EINVAL;
}

int set_pages_array_uc(struct page **pages, int numpages)
{
	return _set_pages_array(pages, numpages, _PAGE_CACHE_MODE_UC_MINUS);
}
EXPORT_SYMBOL(set_pages_array_uc);

int set_pages_array_wc(struct page **pages, int numpages)
{
	return _set_pages_array(pages, numpages, _PAGE_CACHE_MODE_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 numpages)
{
	int retval;
	unsigned long start;
	unsigned long end;
	int i;

	/* WB cache mode is hard wired to all cache attribute bits being 0 */
	retval = cpa_clear_pages_array(pages, numpages,
			__pgprot(_PAGE_CACHE_MASK));
	if (retval)
		return retval;

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

	return 0;
}
EXPORT_SYMBOL(set_pages_array_wb);

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);
}

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 = CPA_NO_CHECK_ALIAS };

	/*
	 * 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, 1);
}

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 = CPA_NO_CHECK_ALIAS };

	/*
	 * 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, 1);
}

int set_direct_map_invalid_noflush(struct page *page)
{
	return __set_pages_np(page, 1);
}

int set_direct_map_default_noflush(struct page *page)
{
	return __set_pages_p(page, 1);
}

#ifdef CONFIG_DEBUG_PAGEALLOC
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.
	 * Preemption needs to be disabled around __flush_tlb_all() due to
	 * CR3 reload in __native_flush_tlb().
	 */
	preempt_disable();
	__flush_tlb_all();
	preempt_enable();

	arch_flush_lazy_mmu_mode();
}
#endif /* CONFIG_DEBUG_PAGEALLOC */

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);
}

int __init 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(~page_flags & (_PAGE_NX|_PAGE_RW)),
		.flags = CPA_NO_CHECK_ALIAS,
	};

	WARN_ONCE(num_online_cpus() > 1, "Don't call after initializing SMP");

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

	if (!(page_flags & _PAGE_ENC))
		cpa.mask_clr = pgprot_encrypted(cpa.mask_clr);

	cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags);

	retval = __change_page_attr_set_clr(&cpa, 1);
	__flush_tlb_all();

out:
	return retval;
}

/*
 * __flush_tlb_all() flushes mappings only on current CPU and hence this
 * function shouldn't be used in an SMP environment. Presently, it's used only
 * during boot (way before smp_init()) by EFI subsystem and hence is ok.
 */
int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address,
				     unsigned long numpages)
{
	int retval;

	/*
	 * The typical sequence for unmapping is to find a pte through
	 * lookup_address_in_pgd() (ideally, it should never return NULL because
	 * the address is already mapped) and change its protections. As pfn is
	 * the *target* of a mapping, it's not useful while unmapping.
	 */
	struct cpa_data cpa = {
		.vaddr		= &address,
		.pfn		= 0,
		.pgd		= pgd,
		.numpages	= numpages,
		.mask_set	= __pgprot(0),
		.mask_clr	= __pgprot(_PAGE_PRESENT | _PAGE_RW),
		.flags		= CPA_NO_CHECK_ALIAS,
	};

	WARN_ONCE(num_online_cpus() > 1, "Don't call after initializing SMP");

	retval = __change_page_attr_set_clr(&cpa, 1);
	__flush_tlb_all();

	return retval;
}

/*
 * 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 "cpa-test.c"
#endif