summaryrefslogtreecommitdiff
path: root/virt/kvm/arm/mmu.c
blob: 91aaf73b00df8a385a28c2a221505b6ba82062b1 (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
/*
 * Copyright (C) 2012 - Virtual Open Systems and Columbia University
 * Author: Christoffer Dall <c.dall@virtualopensystems.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License, version 2, as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 */

#include <linux/mman.h>
#include <linux/kvm_host.h>
#include <linux/io.h>
#include <linux/hugetlb.h>
#include <linux/sched/signal.h>
#include <trace/events/kvm.h>
#include <asm/pgalloc.h>
#include <asm/cacheflush.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_mmio.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/virt.h>
#include <asm/system_misc.h>

#include "trace.h"

static pgd_t *boot_hyp_pgd;
static pgd_t *hyp_pgd;
static pgd_t *merged_hyp_pgd;
static DEFINE_MUTEX(kvm_hyp_pgd_mutex);

static unsigned long hyp_idmap_start;
static unsigned long hyp_idmap_end;
static phys_addr_t hyp_idmap_vector;

static unsigned long io_map_base;

#define S2_PGD_SIZE	(PTRS_PER_S2_PGD * sizeof(pgd_t))
#define hyp_pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))

#define KVM_S2PTE_FLAG_IS_IOMAP		(1UL << 0)
#define KVM_S2_FLAG_LOGGING_ACTIVE	(1UL << 1)

static bool memslot_is_logging(struct kvm_memory_slot *memslot)
{
	return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY);
}

/**
 * kvm_flush_remote_tlbs() - flush all VM TLB entries for v7/8
 * @kvm:	pointer to kvm structure.
 *
 * Interface to HYP function to flush all VM TLB entries
 */
void kvm_flush_remote_tlbs(struct kvm *kvm)
{
	kvm_call_hyp(__kvm_tlb_flush_vmid, kvm);
}

static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
{
	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
}

/*
 * D-Cache management functions. They take the page table entries by
 * value, as they are flushing the cache using the kernel mapping (or
 * kmap on 32bit).
 */
static void kvm_flush_dcache_pte(pte_t pte)
{
	__kvm_flush_dcache_pte(pte);
}

static void kvm_flush_dcache_pmd(pmd_t pmd)
{
	__kvm_flush_dcache_pmd(pmd);
}

static void kvm_flush_dcache_pud(pud_t pud)
{
	__kvm_flush_dcache_pud(pud);
}

static bool kvm_is_device_pfn(unsigned long pfn)
{
	return !pfn_valid(pfn);
}

/**
 * stage2_dissolve_pmd() - clear and flush huge PMD entry
 * @kvm:	pointer to kvm structure.
 * @addr:	IPA
 * @pmd:	pmd pointer for IPA
 *
 * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs. Marks all
 * pages in the range dirty.
 */
static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd)
{
	if (!pmd_thp_or_huge(*pmd))
		return;

	pmd_clear(pmd);
	kvm_tlb_flush_vmid_ipa(kvm, addr);
	put_page(virt_to_page(pmd));
}

static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
				  int min, int max)
{
	void *page;

	BUG_ON(max > KVM_NR_MEM_OBJS);
	if (cache->nobjs >= min)
		return 0;
	while (cache->nobjs < max) {
		page = (void *)__get_free_page(PGALLOC_GFP);
		if (!page)
			return -ENOMEM;
		cache->objects[cache->nobjs++] = page;
	}
	return 0;
}

static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc)
{
	while (mc->nobjs)
		free_page((unsigned long)mc->objects[--mc->nobjs]);
}

static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
{
	void *p;

	BUG_ON(!mc || !mc->nobjs);
	p = mc->objects[--mc->nobjs];
	return p;
}

static void clear_stage2_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
{
	pud_t *pud_table __maybe_unused = stage2_pud_offset(pgd, 0UL);
	stage2_pgd_clear(pgd);
	kvm_tlb_flush_vmid_ipa(kvm, addr);
	stage2_pud_free(pud_table);
	put_page(virt_to_page(pgd));
}

static void clear_stage2_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
{
	pmd_t *pmd_table __maybe_unused = stage2_pmd_offset(pud, 0);
	VM_BUG_ON(stage2_pud_huge(*pud));
	stage2_pud_clear(pud);
	kvm_tlb_flush_vmid_ipa(kvm, addr);
	stage2_pmd_free(pmd_table);
	put_page(virt_to_page(pud));
}

static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
{
	pte_t *pte_table = pte_offset_kernel(pmd, 0);
	VM_BUG_ON(pmd_thp_or_huge(*pmd));
	pmd_clear(pmd);
	kvm_tlb_flush_vmid_ipa(kvm, addr);
	pte_free_kernel(NULL, pte_table);
	put_page(virt_to_page(pmd));
}

static inline void kvm_set_pte(pte_t *ptep, pte_t new_pte)
{
	WRITE_ONCE(*ptep, new_pte);
	dsb(ishst);
}

static inline void kvm_set_pmd(pmd_t *pmdp, pmd_t new_pmd)
{
	WRITE_ONCE(*pmdp, new_pmd);
	dsb(ishst);
}

static inline void kvm_pmd_populate(pmd_t *pmdp, pte_t *ptep)
{
	kvm_set_pmd(pmdp, kvm_mk_pmd(ptep));
}

static inline void kvm_pud_populate(pud_t *pudp, pmd_t *pmdp)
{
	WRITE_ONCE(*pudp, kvm_mk_pud(pmdp));
	dsb(ishst);
}

static inline void kvm_pgd_populate(pgd_t *pgdp, pud_t *pudp)
{
	WRITE_ONCE(*pgdp, kvm_mk_pgd(pudp));
	dsb(ishst);
}

/*
 * Unmapping vs dcache management:
 *
 * If a guest maps certain memory pages as uncached, all writes will
 * bypass the data cache and go directly to RAM.  However, the CPUs
 * can still speculate reads (not writes) and fill cache lines with
 * data.
 *
 * Those cache lines will be *clean* cache lines though, so a
 * clean+invalidate operation is equivalent to an invalidate
 * operation, because no cache lines are marked dirty.
 *
 * Those clean cache lines could be filled prior to an uncached write
 * by the guest, and the cache coherent IO subsystem would therefore
 * end up writing old data to disk.
 *
 * This is why right after unmapping a page/section and invalidating
 * the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure
 * the IO subsystem will never hit in the cache.
 *
 * This is all avoided on systems that have ARM64_HAS_STAGE2_FWB, as
 * we then fully enforce cacheability of RAM, no matter what the guest
 * does.
 */
static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
		       phys_addr_t addr, phys_addr_t end)
{
	phys_addr_t start_addr = addr;
	pte_t *pte, *start_pte;

	start_pte = pte = pte_offset_kernel(pmd, addr);
	do {
		if (!pte_none(*pte)) {
			pte_t old_pte = *pte;

			kvm_set_pte(pte, __pte(0));
			kvm_tlb_flush_vmid_ipa(kvm, addr);

			/* No need to invalidate the cache for device mappings */
			if (!kvm_is_device_pfn(pte_pfn(old_pte)))
				kvm_flush_dcache_pte(old_pte);

			put_page(virt_to_page(pte));
		}
	} while (pte++, addr += PAGE_SIZE, addr != end);

	if (stage2_pte_table_empty(start_pte))
		clear_stage2_pmd_entry(kvm, pmd, start_addr);
}

static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud,
		       phys_addr_t addr, phys_addr_t end)
{
	phys_addr_t next, start_addr = addr;
	pmd_t *pmd, *start_pmd;

	start_pmd = pmd = stage2_pmd_offset(pud, addr);
	do {
		next = stage2_pmd_addr_end(addr, end);
		if (!pmd_none(*pmd)) {
			if (pmd_thp_or_huge(*pmd)) {
				pmd_t old_pmd = *pmd;

				pmd_clear(pmd);
				kvm_tlb_flush_vmid_ipa(kvm, addr);

				kvm_flush_dcache_pmd(old_pmd);

				put_page(virt_to_page(pmd));
			} else {
				unmap_stage2_ptes(kvm, pmd, addr, next);
			}
		}
	} while (pmd++, addr = next, addr != end);

	if (stage2_pmd_table_empty(start_pmd))
		clear_stage2_pud_entry(kvm, pud, start_addr);
}

static void unmap_stage2_puds(struct kvm *kvm, pgd_t *pgd,
		       phys_addr_t addr, phys_addr_t end)
{
	phys_addr_t next, start_addr = addr;
	pud_t *pud, *start_pud;

	start_pud = pud = stage2_pud_offset(pgd, addr);
	do {
		next = stage2_pud_addr_end(addr, end);
		if (!stage2_pud_none(*pud)) {
			if (stage2_pud_huge(*pud)) {
				pud_t old_pud = *pud;

				stage2_pud_clear(pud);
				kvm_tlb_flush_vmid_ipa(kvm, addr);
				kvm_flush_dcache_pud(old_pud);
				put_page(virt_to_page(pud));
			} else {
				unmap_stage2_pmds(kvm, pud, addr, next);
			}
		}
	} while (pud++, addr = next, addr != end);

	if (stage2_pud_table_empty(start_pud))
		clear_stage2_pgd_entry(kvm, pgd, start_addr);
}

/**
 * unmap_stage2_range -- Clear stage2 page table entries to unmap a range
 * @kvm:   The VM pointer
 * @start: The intermediate physical base address of the range to unmap
 * @size:  The size of the area to unmap
 *
 * Clear a range of stage-2 mappings, lowering the various ref-counts.  Must
 * be called while holding mmu_lock (unless for freeing the stage2 pgd before
 * destroying the VM), otherwise another faulting VCPU may come in and mess
 * with things behind our backs.
 */
static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
{
	pgd_t *pgd;
	phys_addr_t addr = start, end = start + size;
	phys_addr_t next;

	assert_spin_locked(&kvm->mmu_lock);
	WARN_ON(size & ~PAGE_MASK);

	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
	do {
		/*
		 * Make sure the page table is still active, as another thread
		 * could have possibly freed the page table, while we released
		 * the lock.
		 */
		if (!READ_ONCE(kvm->arch.pgd))
			break;
		next = stage2_pgd_addr_end(addr, end);
		if (!stage2_pgd_none(*pgd))
			unmap_stage2_puds(kvm, pgd, addr, next);
		/*
		 * If the range is too large, release the kvm->mmu_lock
		 * to prevent starvation and lockup detector warnings.
		 */
		if (next != end)
			cond_resched_lock(&kvm->mmu_lock);
	} while (pgd++, addr = next, addr != end);
}

static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
			      phys_addr_t addr, phys_addr_t end)
{
	pte_t *pte;

	pte = pte_offset_kernel(pmd, addr);
	do {
		if (!pte_none(*pte) && !kvm_is_device_pfn(pte_pfn(*pte)))
			kvm_flush_dcache_pte(*pte);
	} while (pte++, addr += PAGE_SIZE, addr != end);
}

static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
			      phys_addr_t addr, phys_addr_t end)
{
	pmd_t *pmd;
	phys_addr_t next;

	pmd = stage2_pmd_offset(pud, addr);
	do {
		next = stage2_pmd_addr_end(addr, end);
		if (!pmd_none(*pmd)) {
			if (pmd_thp_or_huge(*pmd))
				kvm_flush_dcache_pmd(*pmd);
			else
				stage2_flush_ptes(kvm, pmd, addr, next);
		}
	} while (pmd++, addr = next, addr != end);
}

static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd,
			      phys_addr_t addr, phys_addr_t end)
{
	pud_t *pud;
	phys_addr_t next;

	pud = stage2_pud_offset(pgd, addr);
	do {
		next = stage2_pud_addr_end(addr, end);
		if (!stage2_pud_none(*pud)) {
			if (stage2_pud_huge(*pud))
				kvm_flush_dcache_pud(*pud);
			else
				stage2_flush_pmds(kvm, pud, addr, next);
		}
	} while (pud++, addr = next, addr != end);
}

static void stage2_flush_memslot(struct kvm *kvm,
				 struct kvm_memory_slot *memslot)
{
	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
	phys_addr_t next;
	pgd_t *pgd;

	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
	do {
		next = stage2_pgd_addr_end(addr, end);
		stage2_flush_puds(kvm, pgd, addr, next);
	} while (pgd++, addr = next, addr != end);
}

/**
 * stage2_flush_vm - Invalidate cache for pages mapped in stage 2
 * @kvm: The struct kvm pointer
 *
 * Go through the stage 2 page tables and invalidate any cache lines
 * backing memory already mapped to the VM.
 */
static void stage2_flush_vm(struct kvm *kvm)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;
	int idx;

	idx = srcu_read_lock(&kvm->srcu);
	spin_lock(&kvm->mmu_lock);

	slots = kvm_memslots(kvm);
	kvm_for_each_memslot(memslot, slots)
		stage2_flush_memslot(kvm, memslot);

	spin_unlock(&kvm->mmu_lock);
	srcu_read_unlock(&kvm->srcu, idx);
}

static void clear_hyp_pgd_entry(pgd_t *pgd)
{
	pud_t *pud_table __maybe_unused = pud_offset(pgd, 0UL);
	pgd_clear(pgd);
	pud_free(NULL, pud_table);
	put_page(virt_to_page(pgd));
}

static void clear_hyp_pud_entry(pud_t *pud)
{
	pmd_t *pmd_table __maybe_unused = pmd_offset(pud, 0);
	VM_BUG_ON(pud_huge(*pud));
	pud_clear(pud);
	pmd_free(NULL, pmd_table);
	put_page(virt_to_page(pud));
}

static void clear_hyp_pmd_entry(pmd_t *pmd)
{
	pte_t *pte_table = pte_offset_kernel(pmd, 0);
	VM_BUG_ON(pmd_thp_or_huge(*pmd));
	pmd_clear(pmd);
	pte_free_kernel(NULL, pte_table);
	put_page(virt_to_page(pmd));
}

static void unmap_hyp_ptes(pmd_t *pmd, phys_addr_t addr, phys_addr_t end)
{
	pte_t *pte, *start_pte;

	start_pte = pte = pte_offset_kernel(pmd, addr);
	do {
		if (!pte_none(*pte)) {
			kvm_set_pte(pte, __pte(0));
			put_page(virt_to_page(pte));
		}
	} while (pte++, addr += PAGE_SIZE, addr != end);

	if (hyp_pte_table_empty(start_pte))
		clear_hyp_pmd_entry(pmd);
}

static void unmap_hyp_pmds(pud_t *pud, phys_addr_t addr, phys_addr_t end)
{
	phys_addr_t next;
	pmd_t *pmd, *start_pmd;

	start_pmd = pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		/* Hyp doesn't use huge pmds */
		if (!pmd_none(*pmd))
			unmap_hyp_ptes(pmd, addr, next);
	} while (pmd++, addr = next, addr != end);

	if (hyp_pmd_table_empty(start_pmd))
		clear_hyp_pud_entry(pud);
}

static void unmap_hyp_puds(pgd_t *pgd, phys_addr_t addr, phys_addr_t end)
{
	phys_addr_t next;
	pud_t *pud, *start_pud;

	start_pud = pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		/* Hyp doesn't use huge puds */
		if (!pud_none(*pud))
			unmap_hyp_pmds(pud, addr, next);
	} while (pud++, addr = next, addr != end);

	if (hyp_pud_table_empty(start_pud))
		clear_hyp_pgd_entry(pgd);
}

static unsigned int kvm_pgd_index(unsigned long addr, unsigned int ptrs_per_pgd)
{
	return (addr >> PGDIR_SHIFT) & (ptrs_per_pgd - 1);
}

static void __unmap_hyp_range(pgd_t *pgdp, unsigned long ptrs_per_pgd,
			      phys_addr_t start, u64 size)
{
	pgd_t *pgd;
	phys_addr_t addr = start, end = start + size;
	phys_addr_t next;

	/*
	 * We don't unmap anything from HYP, except at the hyp tear down.
	 * Hence, we don't have to invalidate the TLBs here.
	 */
	pgd = pgdp + kvm_pgd_index(addr, ptrs_per_pgd);
	do {
		next = pgd_addr_end(addr, end);
		if (!pgd_none(*pgd))
			unmap_hyp_puds(pgd, addr, next);
	} while (pgd++, addr = next, addr != end);
}

static void unmap_hyp_range(pgd_t *pgdp, phys_addr_t start, u64 size)
{
	__unmap_hyp_range(pgdp, PTRS_PER_PGD, start, size);
}

static void unmap_hyp_idmap_range(pgd_t *pgdp, phys_addr_t start, u64 size)
{
	__unmap_hyp_range(pgdp, __kvm_idmap_ptrs_per_pgd(), start, size);
}

/**
 * free_hyp_pgds - free Hyp-mode page tables
 *
 * Assumes hyp_pgd is a page table used strictly in Hyp-mode and
 * therefore contains either mappings in the kernel memory area (above
 * PAGE_OFFSET), or device mappings in the idmap range.
 *
 * boot_hyp_pgd should only map the idmap range, and is only used in
 * the extended idmap case.
 */
void free_hyp_pgds(void)
{
	pgd_t *id_pgd;

	mutex_lock(&kvm_hyp_pgd_mutex);

	id_pgd = boot_hyp_pgd ? boot_hyp_pgd : hyp_pgd;

	if (id_pgd) {
		/* In case we never called hyp_mmu_init() */
		if (!io_map_base)
			io_map_base = hyp_idmap_start;
		unmap_hyp_idmap_range(id_pgd, io_map_base,
				      hyp_idmap_start + PAGE_SIZE - io_map_base);
	}

	if (boot_hyp_pgd) {
		free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order);
		boot_hyp_pgd = NULL;
	}

	if (hyp_pgd) {
		unmap_hyp_range(hyp_pgd, kern_hyp_va(PAGE_OFFSET),
				(uintptr_t)high_memory - PAGE_OFFSET);

		free_pages((unsigned long)hyp_pgd, hyp_pgd_order);
		hyp_pgd = NULL;
	}
	if (merged_hyp_pgd) {
		clear_page(merged_hyp_pgd);
		free_page((unsigned long)merged_hyp_pgd);
		merged_hyp_pgd = NULL;
	}

	mutex_unlock(&kvm_hyp_pgd_mutex);
}

static void create_hyp_pte_mappings(pmd_t *pmd, unsigned long start,
				    unsigned long end, unsigned long pfn,
				    pgprot_t prot)
{
	pte_t *pte;
	unsigned long addr;

	addr = start;
	do {
		pte = pte_offset_kernel(pmd, addr);
		kvm_set_pte(pte, pfn_pte(pfn, prot));
		get_page(virt_to_page(pte));
		pfn++;
	} while (addr += PAGE_SIZE, addr != end);
}

static int create_hyp_pmd_mappings(pud_t *pud, unsigned long start,
				   unsigned long end, unsigned long pfn,
				   pgprot_t prot)
{
	pmd_t *pmd;
	pte_t *pte;
	unsigned long addr, next;

	addr = start;
	do {
		pmd = pmd_offset(pud, addr);

		BUG_ON(pmd_sect(*pmd));

		if (pmd_none(*pmd)) {
			pte = pte_alloc_one_kernel(NULL, addr);
			if (!pte) {
				kvm_err("Cannot allocate Hyp pte\n");
				return -ENOMEM;
			}
			kvm_pmd_populate(pmd, pte);
			get_page(virt_to_page(pmd));
		}

		next = pmd_addr_end(addr, end);

		create_hyp_pte_mappings(pmd, addr, next, pfn, prot);
		pfn += (next - addr) >> PAGE_SHIFT;
	} while (addr = next, addr != end);

	return 0;
}

static int create_hyp_pud_mappings(pgd_t *pgd, unsigned long start,
				   unsigned long end, unsigned long pfn,
				   pgprot_t prot)
{
	pud_t *pud;
	pmd_t *pmd;
	unsigned long addr, next;
	int ret;

	addr = start;
	do {
		pud = pud_offset(pgd, addr);

		if (pud_none_or_clear_bad(pud)) {
			pmd = pmd_alloc_one(NULL, addr);
			if (!pmd) {
				kvm_err("Cannot allocate Hyp pmd\n");
				return -ENOMEM;
			}
			kvm_pud_populate(pud, pmd);
			get_page(virt_to_page(pud));
		}

		next = pud_addr_end(addr, end);
		ret = create_hyp_pmd_mappings(pud, addr, next, pfn, prot);
		if (ret)
			return ret;
		pfn += (next - addr) >> PAGE_SHIFT;
	} while (addr = next, addr != end);

	return 0;
}

static int __create_hyp_mappings(pgd_t *pgdp, unsigned long ptrs_per_pgd,
				 unsigned long start, unsigned long end,
				 unsigned long pfn, pgprot_t prot)
{
	pgd_t *pgd;
	pud_t *pud;
	unsigned long addr, next;
	int err = 0;

	mutex_lock(&kvm_hyp_pgd_mutex);
	addr = start & PAGE_MASK;
	end = PAGE_ALIGN(end);
	do {
		pgd = pgdp + kvm_pgd_index(addr, ptrs_per_pgd);

		if (pgd_none(*pgd)) {
			pud = pud_alloc_one(NULL, addr);
			if (!pud) {
				kvm_err("Cannot allocate Hyp pud\n");
				err = -ENOMEM;
				goto out;
			}
			kvm_pgd_populate(pgd, pud);
			get_page(virt_to_page(pgd));
		}

		next = pgd_addr_end(addr, end);
		err = create_hyp_pud_mappings(pgd, addr, next, pfn, prot);
		if (err)
			goto out;
		pfn += (next - addr) >> PAGE_SHIFT;
	} while (addr = next, addr != end);
out:
	mutex_unlock(&kvm_hyp_pgd_mutex);
	return err;
}

static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
{
	if (!is_vmalloc_addr(kaddr)) {
		BUG_ON(!virt_addr_valid(kaddr));
		return __pa(kaddr);
	} else {
		return page_to_phys(vmalloc_to_page(kaddr)) +
		       offset_in_page(kaddr);
	}
}

/**
 * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
 * @from:	The virtual kernel start address of the range
 * @to:		The virtual kernel end address of the range (exclusive)
 * @prot:	The protection to be applied to this range
 *
 * The same virtual address as the kernel virtual address is also used
 * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying
 * physical pages.
 */
int create_hyp_mappings(void *from, void *to, pgprot_t prot)
{
	phys_addr_t phys_addr;
	unsigned long virt_addr;
	unsigned long start = kern_hyp_va((unsigned long)from);
	unsigned long end = kern_hyp_va((unsigned long)to);

	if (is_kernel_in_hyp_mode())
		return 0;

	start = start & PAGE_MASK;
	end = PAGE_ALIGN(end);

	for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) {
		int err;

		phys_addr = kvm_kaddr_to_phys(from + virt_addr - start);
		err = __create_hyp_mappings(hyp_pgd, PTRS_PER_PGD,
					    virt_addr, virt_addr + PAGE_SIZE,
					    __phys_to_pfn(phys_addr),
					    prot);
		if (err)
			return err;
	}

	return 0;
}

static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size,
					unsigned long *haddr, pgprot_t prot)
{
	pgd_t *pgd = hyp_pgd;
	unsigned long base;
	int ret = 0;

	mutex_lock(&kvm_hyp_pgd_mutex);

	/*
	 * This assumes that we we have enough space below the idmap
	 * page to allocate our VAs. If not, the check below will
	 * kick. A potential alternative would be to detect that
	 * overflow and switch to an allocation above the idmap.
	 *
	 * The allocated size is always a multiple of PAGE_SIZE.
	 */
	size = PAGE_ALIGN(size + offset_in_page(phys_addr));
	base = io_map_base - size;

	/*
	 * Verify that BIT(VA_BITS - 1) hasn't been flipped by
	 * allocating the new area, as it would indicate we've
	 * overflowed the idmap/IO address range.
	 */
	if ((base ^ io_map_base) & BIT(VA_BITS - 1))
		ret = -ENOMEM;
	else
		io_map_base = base;

	mutex_unlock(&kvm_hyp_pgd_mutex);

	if (ret)
		goto out;

	if (__kvm_cpu_uses_extended_idmap())
		pgd = boot_hyp_pgd;

	ret = __create_hyp_mappings(pgd, __kvm_idmap_ptrs_per_pgd(),
				    base, base + size,
				    __phys_to_pfn(phys_addr), prot);
	if (ret)
		goto out;

	*haddr = base + offset_in_page(phys_addr);

out:
	return ret;
}

/**
 * create_hyp_io_mappings - Map IO into both kernel and HYP
 * @phys_addr:	The physical start address which gets mapped
 * @size:	Size of the region being mapped
 * @kaddr:	Kernel VA for this mapping
 * @haddr:	HYP VA for this mapping
 */
int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
			   void __iomem **kaddr,
			   void __iomem **haddr)
{
	unsigned long addr;
	int ret;

	*kaddr = ioremap(phys_addr, size);
	if (!*kaddr)
		return -ENOMEM;

	if (is_kernel_in_hyp_mode()) {
		*haddr = *kaddr;
		return 0;
	}

	ret = __create_hyp_private_mapping(phys_addr, size,
					   &addr, PAGE_HYP_DEVICE);
	if (ret) {
		iounmap(*kaddr);
		*kaddr = NULL;
		*haddr = NULL;
		return ret;
	}

	*haddr = (void __iomem *)addr;
	return 0;
}

/**
 * create_hyp_exec_mappings - Map an executable range into HYP
 * @phys_addr:	The physical start address which gets mapped
 * @size:	Size of the region being mapped
 * @haddr:	HYP VA for this mapping
 */
int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
			     void **haddr)
{
	unsigned long addr;
	int ret;

	BUG_ON(is_kernel_in_hyp_mode());

	ret = __create_hyp_private_mapping(phys_addr, size,
					   &addr, PAGE_HYP_EXEC);
	if (ret) {
		*haddr = NULL;
		return ret;
	}

	*haddr = (void *)addr;
	return 0;
}

/**
 * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
 * @kvm:	The KVM struct pointer for the VM.
 *
 * Allocates only the stage-2 HW PGD level table(s) (can support either full
 * 40-bit input addresses or limited to 32-bit input addresses). Clears the
 * allocated pages.
 *
 * Note we don't need locking here as this is only called when the VM is
 * created, which can only be done once.
 */
int kvm_alloc_stage2_pgd(struct kvm *kvm)
{
	pgd_t *pgd;

	if (kvm->arch.pgd != NULL) {
		kvm_err("kvm_arch already initialized?\n");
		return -EINVAL;
	}

	/* Allocate the HW PGD, making sure that each page gets its own refcount */
	pgd = alloc_pages_exact(S2_PGD_SIZE, GFP_KERNEL | __GFP_ZERO);
	if (!pgd)
		return -ENOMEM;

	kvm->arch.pgd = pgd;
	return 0;
}

static void stage2_unmap_memslot(struct kvm *kvm,
				 struct kvm_memory_slot *memslot)
{
	hva_t hva = memslot->userspace_addr;
	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
	phys_addr_t size = PAGE_SIZE * memslot->npages;
	hva_t reg_end = hva + size;

	/*
	 * A memory region could potentially cover multiple VMAs, and any holes
	 * between them, so iterate over all of them to find out if we should
	 * unmap any of them.
	 *
	 *     +--------------------------------------------+
	 * +---------------+----------------+   +----------------+
	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
	 * +---------------+----------------+   +----------------+
	 *     |               memory region                |
	 *     +--------------------------------------------+
	 */
	do {
		struct vm_area_struct *vma = find_vma(current->mm, hva);
		hva_t vm_start, vm_end;

		if (!vma || vma->vm_start >= reg_end)
			break;

		/*
		 * Take the intersection of this VMA with the memory region
		 */
		vm_start = max(hva, vma->vm_start);
		vm_end = min(reg_end, vma->vm_end);

		if (!(vma->vm_flags & VM_PFNMAP)) {
			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
			unmap_stage2_range(kvm, gpa, vm_end - vm_start);
		}
		hva = vm_end;
	} while (hva < reg_end);
}

/**
 * stage2_unmap_vm - Unmap Stage-2 RAM mappings
 * @kvm: The struct kvm pointer
 *
 * Go through the memregions and unmap any reguler RAM
 * backing memory already mapped to the VM.
 */
void stage2_unmap_vm(struct kvm *kvm)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;
	int idx;

	idx = srcu_read_lock(&kvm->srcu);
	down_read(&current->mm->mmap_sem);
	spin_lock(&kvm->mmu_lock);

	slots = kvm_memslots(kvm);
	kvm_for_each_memslot(memslot, slots)
		stage2_unmap_memslot(kvm, memslot);

	spin_unlock(&kvm->mmu_lock);
	up_read(&current->mm->mmap_sem);
	srcu_read_unlock(&kvm->srcu, idx);
}

/**
 * kvm_free_stage2_pgd - free all stage-2 tables
 * @kvm:	The KVM struct pointer for the VM.
 *
 * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all
 * underlying level-2 and level-3 tables before freeing the actual level-1 table
 * and setting the struct pointer to NULL.
 */
void kvm_free_stage2_pgd(struct kvm *kvm)
{
	void *pgd = NULL;

	spin_lock(&kvm->mmu_lock);
	if (kvm->arch.pgd) {
		unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
		pgd = READ_ONCE(kvm->arch.pgd);
		kvm->arch.pgd = NULL;
	}
	spin_unlock(&kvm->mmu_lock);

	/* Free the HW pgd, one page at a time */
	if (pgd)
		free_pages_exact(pgd, S2_PGD_SIZE);
}

static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
			     phys_addr_t addr)
{
	pgd_t *pgd;
	pud_t *pud;

	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
	if (WARN_ON(stage2_pgd_none(*pgd))) {
		if (!cache)
			return NULL;
		pud = mmu_memory_cache_alloc(cache);
		stage2_pgd_populate(pgd, pud);
		get_page(virt_to_page(pgd));
	}

	return stage2_pud_offset(pgd, addr);
}

static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
			     phys_addr_t addr)
{
	pud_t *pud;
	pmd_t *pmd;

	pud = stage2_get_pud(kvm, cache, addr);
	if (!pud)
		return NULL;

	if (stage2_pud_none(*pud)) {
		if (!cache)
			return NULL;
		pmd = mmu_memory_cache_alloc(cache);
		stage2_pud_populate(pud, pmd);
		get_page(virt_to_page(pud));
	}

	return stage2_pmd_offset(pud, addr);
}

static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
			       *cache, phys_addr_t addr, const pmd_t *new_pmd)
{
	pmd_t *pmd, old_pmd;

	pmd = stage2_get_pmd(kvm, cache, addr);
	VM_BUG_ON(!pmd);

	old_pmd = *pmd;
	if (pmd_present(old_pmd)) {
		/*
		 * Multiple vcpus faulting on the same PMD entry, can
		 * lead to them sequentially updating the PMD with the
		 * same value. Following the break-before-make
		 * (pmd_clear() followed by tlb_flush()) process can
		 * hinder forward progress due to refaults generated
		 * on missing translations.
		 *
		 * Skip updating the page table if the entry is
		 * unchanged.
		 */
		if (pmd_val(old_pmd) == pmd_val(*new_pmd))
			return 0;

		/*
		 * Mapping in huge pages should only happen through a
		 * fault.  If a page is merged into a transparent huge
		 * page, the individual subpages of that huge page
		 * should be unmapped through MMU notifiers before we
		 * get here.
		 *
		 * Merging of CompoundPages is not supported; they
		 * should become splitting first, unmapped, merged,
		 * and mapped back in on-demand.
		 */
		VM_BUG_ON(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd));

		pmd_clear(pmd);
		kvm_tlb_flush_vmid_ipa(kvm, addr);
	} else {
		get_page(virt_to_page(pmd));
	}

	kvm_set_pmd(pmd, *new_pmd);
	return 0;
}

static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
{
	pmd_t *pmdp;
	pte_t *ptep;

	pmdp = stage2_get_pmd(kvm, NULL, addr);
	if (!pmdp || pmd_none(*pmdp) || !pmd_present(*pmdp))
		return false;

	if (pmd_thp_or_huge(*pmdp))
		return kvm_s2pmd_exec(pmdp);

	ptep = pte_offset_kernel(pmdp, addr);
	if (!ptep || pte_none(*ptep) || !pte_present(*ptep))
		return false;

	return kvm_s2pte_exec(ptep);
}

static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
			  phys_addr_t addr, const pte_t *new_pte,
			  unsigned long flags)
{
	pmd_t *pmd;
	pte_t *pte, old_pte;
	bool iomap = flags & KVM_S2PTE_FLAG_IS_IOMAP;
	bool logging_active = flags & KVM_S2_FLAG_LOGGING_ACTIVE;

	VM_BUG_ON(logging_active && !cache);

	/* Create stage-2 page table mapping - Levels 0 and 1 */
	pmd = stage2_get_pmd(kvm, cache, addr);
	if (!pmd) {
		/*
		 * Ignore calls from kvm_set_spte_hva for unallocated
		 * address ranges.
		 */
		return 0;
	}

	/*
	 * While dirty page logging - dissolve huge PMD, then continue on to
	 * allocate page.
	 */
	if (logging_active)
		stage2_dissolve_pmd(kvm, addr, pmd);

	/* Create stage-2 page mappings - Level 2 */
	if (pmd_none(*pmd)) {
		if (!cache)
			return 0; /* ignore calls from kvm_set_spte_hva */
		pte = mmu_memory_cache_alloc(cache);
		kvm_pmd_populate(pmd, pte);
		get_page(virt_to_page(pmd));
	}

	pte = pte_offset_kernel(pmd, addr);

	if (iomap && pte_present(*pte))
		return -EFAULT;

	/* Create 2nd stage page table mapping - Level 3 */
	old_pte = *pte;
	if (pte_present(old_pte)) {
		/* Skip page table update if there is no change */
		if (pte_val(old_pte) == pte_val(*new_pte))
			return 0;

		kvm_set_pte(pte, __pte(0));
		kvm_tlb_flush_vmid_ipa(kvm, addr);
	} else {
		get_page(virt_to_page(pte));
	}

	kvm_set_pte(pte, *new_pte);
	return 0;
}

#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
static int stage2_ptep_test_and_clear_young(pte_t *pte)
{
	if (pte_young(*pte)) {
		*pte = pte_mkold(*pte);
		return 1;
	}
	return 0;
}
#else
static int stage2_ptep_test_and_clear_young(pte_t *pte)
{
	return __ptep_test_and_clear_young(pte);
}
#endif

static int stage2_pmdp_test_and_clear_young(pmd_t *pmd)
{
	return stage2_ptep_test_and_clear_young((pte_t *)pmd);
}

/**
 * kvm_phys_addr_ioremap - map a device range to guest IPA
 *
 * @kvm:	The KVM pointer
 * @guest_ipa:	The IPA at which to insert the mapping
 * @pa:		The physical address of the device
 * @size:	The size of the mapping
 */
int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
			  phys_addr_t pa, unsigned long size, bool writable)
{
	phys_addr_t addr, end;
	int ret = 0;
	unsigned long pfn;
	struct kvm_mmu_memory_cache cache = { 0, };

	end = (guest_ipa + size + PAGE_SIZE - 1) & PAGE_MASK;
	pfn = __phys_to_pfn(pa);

	for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) {
		pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE);

		if (writable)
			pte = kvm_s2pte_mkwrite(pte);

		ret = mmu_topup_memory_cache(&cache, KVM_MMU_CACHE_MIN_PAGES,
						KVM_NR_MEM_OBJS);
		if (ret)
			goto out;
		spin_lock(&kvm->mmu_lock);
		ret = stage2_set_pte(kvm, &cache, addr, &pte,
						KVM_S2PTE_FLAG_IS_IOMAP);
		spin_unlock(&kvm->mmu_lock);
		if (ret)
			goto out;

		pfn++;
	}

out:
	mmu_free_memory_cache(&cache);
	return ret;
}

static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap)
{
	kvm_pfn_t pfn = *pfnp;
	gfn_t gfn = *ipap >> PAGE_SHIFT;

	if (PageTransCompoundMap(pfn_to_page(pfn))) {
		unsigned long mask;
		/*
		 * The address we faulted on is backed by a transparent huge
		 * page.  However, because we map the compound huge page and
		 * not the individual tail page, we need to transfer the
		 * refcount to the head page.  We have to be careful that the
		 * THP doesn't start to split while we are adjusting the
		 * refcounts.
		 *
		 * We are sure this doesn't happen, because mmu_notifier_retry
		 * was successful and we are holding the mmu_lock, so if this
		 * THP is trying to split, it will be blocked in the mmu
		 * notifier before touching any of the pages, specifically
		 * before being able to call __split_huge_page_refcount().
		 *
		 * We can therefore safely transfer the refcount from PG_tail
		 * to PG_head and switch the pfn from a tail page to the head
		 * page accordingly.
		 */
		mask = PTRS_PER_PMD - 1;
		VM_BUG_ON((gfn & mask) != (pfn & mask));
		if (pfn & mask) {
			*ipap &= PMD_MASK;
			kvm_release_pfn_clean(pfn);
			pfn &= ~mask;
			kvm_get_pfn(pfn);
			*pfnp = pfn;
		}

		return true;
	}

	return false;
}

static bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
{
	if (kvm_vcpu_trap_is_iabt(vcpu))
		return false;

	return kvm_vcpu_dabt_iswrite(vcpu);
}

/**
 * stage2_wp_ptes - write protect PMD range
 * @pmd:	pointer to pmd entry
 * @addr:	range start address
 * @end:	range end address
 */
static void stage2_wp_ptes(pmd_t *pmd, phys_addr_t addr, phys_addr_t end)
{
	pte_t *pte;

	pte = pte_offset_kernel(pmd, addr);
	do {
		if (!pte_none(*pte)) {
			if (!kvm_s2pte_readonly(pte))
				kvm_set_s2pte_readonly(pte);
		}
	} while (pte++, addr += PAGE_SIZE, addr != end);
}

/**
 * stage2_wp_pmds - write protect PUD range
 * @pud:	pointer to pud entry
 * @addr:	range start address
 * @end:	range end address
 */
static void stage2_wp_pmds(pud_t *pud, phys_addr_t addr, phys_addr_t end)
{
	pmd_t *pmd;
	phys_addr_t next;

	pmd = stage2_pmd_offset(pud, addr);

	do {
		next = stage2_pmd_addr_end(addr, end);
		if (!pmd_none(*pmd)) {
			if (pmd_thp_or_huge(*pmd)) {
				if (!kvm_s2pmd_readonly(pmd))
					kvm_set_s2pmd_readonly(pmd);
			} else {
				stage2_wp_ptes(pmd, addr, next);
			}
		}
	} while (pmd++, addr = next, addr != end);
}

/**
  * stage2_wp_puds - write protect PGD range
  * @pgd:	pointer to pgd entry
  * @addr:	range start address
  * @end:	range end address
  *
  * Process PUD entries, for a huge PUD we cause a panic.
  */
static void  stage2_wp_puds(pgd_t *pgd, phys_addr_t addr, phys_addr_t end)
{
	pud_t *pud;
	phys_addr_t next;

	pud = stage2_pud_offset(pgd, addr);
	do {
		next = stage2_pud_addr_end(addr, end);
		if (!stage2_pud_none(*pud)) {
			/* TODO:PUD not supported, revisit later if supported */
			BUG_ON(stage2_pud_huge(*pud));
			stage2_wp_pmds(pud, addr, next);
		}
	} while (pud++, addr = next, addr != end);
}

/**
 * stage2_wp_range() - write protect stage2 memory region range
 * @kvm:	The KVM pointer
 * @addr:	Start address of range
 * @end:	End address of range
 */
static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
{
	pgd_t *pgd;
	phys_addr_t next;

	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
	do {
		/*
		 * Release kvm_mmu_lock periodically if the memory region is
		 * large. Otherwise, we may see kernel panics with
		 * CONFIG_DETECT_HUNG_TASK, CONFIG_LOCKUP_DETECTOR,
		 * CONFIG_LOCKDEP. Additionally, holding the lock too long
		 * will also starve other vCPUs. We have to also make sure
		 * that the page tables are not freed while we released
		 * the lock.
		 */
		cond_resched_lock(&kvm->mmu_lock);
		if (!READ_ONCE(kvm->arch.pgd))
			break;
		next = stage2_pgd_addr_end(addr, end);
		if (stage2_pgd_present(*pgd))
			stage2_wp_puds(pgd, addr, next);
	} while (pgd++, addr = next, addr != end);
}

/**
 * kvm_mmu_wp_memory_region() - write protect stage 2 entries for memory slot
 * @kvm:	The KVM pointer
 * @slot:	The memory slot to write protect
 *
 * Called to start logging dirty pages after memory region
 * KVM_MEM_LOG_DIRTY_PAGES operation is called. After this function returns
 * all present PMD and PTEs are write protected in the memory region.
 * Afterwards read of dirty page log can be called.
 *
 * Acquires kvm_mmu_lock. Called with kvm->slots_lock mutex acquired,
 * serializing operations for VM memory regions.
 */
void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
{
	struct kvm_memslots *slots = kvm_memslots(kvm);
	struct kvm_memory_slot *memslot = id_to_memslot(slots, slot);
	phys_addr_t start = memslot->base_gfn << PAGE_SHIFT;
	phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;

	spin_lock(&kvm->mmu_lock);
	stage2_wp_range(kvm, start, end);
	spin_unlock(&kvm->mmu_lock);
	kvm_flush_remote_tlbs(kvm);
}

/**
 * kvm_mmu_write_protect_pt_masked() - write protect dirty pages
 * @kvm:	The KVM pointer
 * @slot:	The memory slot associated with mask
 * @gfn_offset:	The gfn offset in memory slot
 * @mask:	The mask of dirty pages at offset 'gfn_offset' in this memory
 *		slot to be write protected
 *
 * Walks bits set in mask write protects the associated pte's. Caller must
 * acquire kvm_mmu_lock.
 */
static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
		struct kvm_memory_slot *slot,
		gfn_t gfn_offset, unsigned long mask)
{
	phys_addr_t base_gfn = slot->base_gfn + gfn_offset;
	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;

	stage2_wp_range(kvm, start, end);
}

/*
 * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected
 * dirty pages.
 *
 * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to
 * enable dirty logging for them.
 */
void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
		struct kvm_memory_slot *slot,
		gfn_t gfn_offset, unsigned long mask)
{
	kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}

static void clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
{
	__clean_dcache_guest_page(pfn, size);
}

static void invalidate_icache_guest_page(kvm_pfn_t pfn, unsigned long size)
{
	__invalidate_icache_guest_page(pfn, size);
}

static void kvm_send_hwpoison_signal(unsigned long address,
				     struct vm_area_struct *vma)
{
	siginfo_t info;

	clear_siginfo(&info);
	info.si_signo   = SIGBUS;
	info.si_errno   = 0;
	info.si_code    = BUS_MCEERR_AR;
	info.si_addr    = (void __user *)address;

	if (is_vm_hugetlb_page(vma))
		info.si_addr_lsb = huge_page_shift(hstate_vma(vma));
	else
		info.si_addr_lsb = PAGE_SHIFT;

	send_sig_info(SIGBUS, &info, current);
}

static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
			  struct kvm_memory_slot *memslot, unsigned long hva,
			  unsigned long fault_status)
{
	int ret;
	bool write_fault, exec_fault, writable, hugetlb = false, force_pte = false;
	unsigned long mmu_seq;
	gfn_t gfn = fault_ipa >> PAGE_SHIFT;
	struct kvm *kvm = vcpu->kvm;
	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
	struct vm_area_struct *vma;
	kvm_pfn_t pfn;
	pgprot_t mem_type = PAGE_S2;
	bool logging_active = memslot_is_logging(memslot);
	unsigned long flags = 0;

	write_fault = kvm_is_write_fault(vcpu);
	exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
	VM_BUG_ON(write_fault && exec_fault);

	if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
		kvm_err("Unexpected L2 read permission error\n");
		return -EFAULT;
	}

	/* Let's check if we will get back a huge page backed by hugetlbfs */
	down_read(&current->mm->mmap_sem);
	vma = find_vma_intersection(current->mm, hva, hva + 1);
	if (unlikely(!vma)) {
		kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
		up_read(&current->mm->mmap_sem);
		return -EFAULT;
	}

	if (vma_kernel_pagesize(vma) == PMD_SIZE && !logging_active) {
		hugetlb = true;
		gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
	} else {
		/*
		 * Pages belonging to memslots that don't have the same
		 * alignment for userspace and IPA cannot be mapped using
		 * block descriptors even if the pages belong to a THP for
		 * the process, because the stage-2 block descriptor will
		 * cover more than a single THP and we loose atomicity for
		 * unmapping, updates, and splits of the THP or other pages
		 * in the stage-2 block range.
		 */
		if ((memslot->userspace_addr & ~PMD_MASK) !=
		    ((memslot->base_gfn << PAGE_SHIFT) & ~PMD_MASK))
			force_pte = true;
	}
	up_read(&current->mm->mmap_sem);

	/* We need minimum second+third level pages */
	ret = mmu_topup_memory_cache(memcache, KVM_MMU_CACHE_MIN_PAGES,
				     KVM_NR_MEM_OBJS);
	if (ret)
		return ret;

	mmu_seq = vcpu->kvm->mmu_notifier_seq;
	/*
	 * Ensure the read of mmu_notifier_seq happens before we call
	 * gfn_to_pfn_prot (which calls get_user_pages), so that we don't risk
	 * the page we just got a reference to gets unmapped before we have a
	 * chance to grab the mmu_lock, which ensure that if the page gets
	 * unmapped afterwards, the call to kvm_unmap_hva will take it away
	 * from us again properly. This smp_rmb() interacts with the smp_wmb()
	 * in kvm_mmu_notifier_invalidate_<page|range_end>.
	 */
	smp_rmb();

	pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable);
	if (pfn == KVM_PFN_ERR_HWPOISON) {
		kvm_send_hwpoison_signal(hva, vma);
		return 0;
	}
	if (is_error_noslot_pfn(pfn))
		return -EFAULT;

	if (kvm_is_device_pfn(pfn)) {
		mem_type = PAGE_S2_DEVICE;
		flags |= KVM_S2PTE_FLAG_IS_IOMAP;
	} else if (logging_active) {
		/*
		 * Faults on pages in a memslot with logging enabled
		 * should not be mapped with huge pages (it introduces churn
		 * and performance degradation), so force a pte mapping.
		 */
		force_pte = true;
		flags |= KVM_S2_FLAG_LOGGING_ACTIVE;

		/*
		 * Only actually map the page as writable if this was a write
		 * fault.
		 */
		if (!write_fault)
			writable = false;
	}

	spin_lock(&kvm->mmu_lock);
	if (mmu_notifier_retry(kvm, mmu_seq))
		goto out_unlock;

	if (!hugetlb && !force_pte)
		hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);

	if (hugetlb) {
		pmd_t new_pmd = pfn_pmd(pfn, mem_type);
		new_pmd = pmd_mkhuge(new_pmd);
		if (writable) {
			new_pmd = kvm_s2pmd_mkwrite(new_pmd);
			kvm_set_pfn_dirty(pfn);
		}

		if (fault_status != FSC_PERM)
			clean_dcache_guest_page(pfn, PMD_SIZE);

		if (exec_fault) {
			new_pmd = kvm_s2pmd_mkexec(new_pmd);
			invalidate_icache_guest_page(pfn, PMD_SIZE);
		} else if (fault_status == FSC_PERM) {
			/* Preserve execute if XN was already cleared */
			if (stage2_is_exec(kvm, fault_ipa))
				new_pmd = kvm_s2pmd_mkexec(new_pmd);
		}

		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
	} else {
		pte_t new_pte = pfn_pte(pfn, mem_type);

		if (writable) {
			new_pte = kvm_s2pte_mkwrite(new_pte);
			kvm_set_pfn_dirty(pfn);
			mark_page_dirty(kvm, gfn);
		}

		if (fault_status != FSC_PERM)
			clean_dcache_guest_page(pfn, PAGE_SIZE);

		if (exec_fault) {
			new_pte = kvm_s2pte_mkexec(new_pte);
			invalidate_icache_guest_page(pfn, PAGE_SIZE);
		} else if (fault_status == FSC_PERM) {
			/* Preserve execute if XN was already cleared */
			if (stage2_is_exec(kvm, fault_ipa))
				new_pte = kvm_s2pte_mkexec(new_pte);
		}

		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags);
	}

out_unlock:
	spin_unlock(&kvm->mmu_lock);
	kvm_set_pfn_accessed(pfn);
	kvm_release_pfn_clean(pfn);
	return ret;
}

/*
 * Resolve the access fault by making the page young again.
 * Note that because the faulting entry is guaranteed not to be
 * cached in the TLB, we don't need to invalidate anything.
 * Only the HW Access Flag updates are supported for Stage 2 (no DBM),
 * so there is no need for atomic (pte|pmd)_mkyoung operations.
 */
static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
{
	pmd_t *pmd;
	pte_t *pte;
	kvm_pfn_t pfn;
	bool pfn_valid = false;

	trace_kvm_access_fault(fault_ipa);

	spin_lock(&vcpu->kvm->mmu_lock);

	pmd = stage2_get_pmd(vcpu->kvm, NULL, fault_ipa);
	if (!pmd || pmd_none(*pmd))	/* Nothing there */
		goto out;

	if (pmd_thp_or_huge(*pmd)) {	/* THP, HugeTLB */
		*pmd = pmd_mkyoung(*pmd);
		pfn = pmd_pfn(*pmd);
		pfn_valid = true;
		goto out;
	}

	pte = pte_offset_kernel(pmd, fault_ipa);
	if (pte_none(*pte))		/* Nothing there either */
		goto out;

	*pte = pte_mkyoung(*pte);	/* Just a page... */
	pfn = pte_pfn(*pte);
	pfn_valid = true;
out:
	spin_unlock(&vcpu->kvm->mmu_lock);
	if (pfn_valid)
		kvm_set_pfn_accessed(pfn);
}

/**
 * kvm_handle_guest_abort - handles all 2nd stage aborts
 * @vcpu:	the VCPU pointer
 * @run:	the kvm_run structure
 *
 * Any abort that gets to the host is almost guaranteed to be caused by a
 * missing second stage translation table entry, which can mean that either the
 * guest simply needs more memory and we must allocate an appropriate page or it
 * can mean that the guest tried to access I/O memory, which is emulated by user
 * space. The distinction is based on the IPA causing the fault and whether this
 * memory region has been registered as standard RAM by user space.
 */
int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
	unsigned long fault_status;
	phys_addr_t fault_ipa;
	struct kvm_memory_slot *memslot;
	unsigned long hva;
	bool is_iabt, write_fault, writable;
	gfn_t gfn;
	int ret, idx;

	fault_status = kvm_vcpu_trap_get_fault_type(vcpu);

	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);

	/* Synchronous External Abort? */
	if (kvm_vcpu_dabt_isextabt(vcpu)) {
		/*
		 * For RAS the host kernel may handle this abort.
		 * There is no need to pass the error into the guest.
		 */
		if (!handle_guest_sea(fault_ipa, kvm_vcpu_get_hsr(vcpu)))
			return 1;

		if (unlikely(!is_iabt)) {
			kvm_inject_vabt(vcpu);
			return 1;
		}
	}

	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu),
			      kvm_vcpu_get_hfar(vcpu), fault_ipa);

	/* Check the stage-2 fault is trans. fault or write fault */
	if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
	    fault_status != FSC_ACCESS) {
		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
			kvm_vcpu_trap_get_class(vcpu),
			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
			(unsigned long)kvm_vcpu_get_hsr(vcpu));
		return -EFAULT;
	}

	idx = srcu_read_lock(&vcpu->kvm->srcu);

	gfn = fault_ipa >> PAGE_SHIFT;
	memslot = gfn_to_memslot(vcpu->kvm, gfn);
	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
	write_fault = kvm_is_write_fault(vcpu);
	if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
		if (is_iabt) {
			/* Prefetch Abort on I/O address */
			kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
			ret = 1;
			goto out_unlock;
		}

		/*
		 * Check for a cache maintenance operation. Since we
		 * ended-up here, we know it is outside of any memory
		 * slot. But we can't find out if that is for a device,
		 * or if the guest is just being stupid. The only thing
		 * we know for sure is that this range cannot be cached.
		 *
		 * So let's assume that the guest is just being
		 * cautious, and skip the instruction.
		 */
		if (kvm_vcpu_dabt_is_cm(vcpu)) {
			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
			ret = 1;
			goto out_unlock;
		}

		/*
		 * The IPA is reported as [MAX:12], so we need to
		 * complement it with the bottom 12 bits from the
		 * faulting VA. This is always 12 bits, irrespective
		 * of the page size.
		 */
		fault_ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1);
		ret = io_mem_abort(vcpu, run, fault_ipa);
		goto out_unlock;
	}

	/* Userspace should not be able to register out-of-bounds IPAs */
	VM_BUG_ON(fault_ipa >= KVM_PHYS_SIZE);

	if (fault_status == FSC_ACCESS) {
		handle_access_fault(vcpu, fault_ipa);
		ret = 1;
		goto out_unlock;
	}

	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
	if (ret == 0)
		ret = 1;
out_unlock:
	srcu_read_unlock(&vcpu->kvm->srcu, idx);
	return ret;
}

static int handle_hva_to_gpa(struct kvm *kvm,
			     unsigned long start,
			     unsigned long end,
			     int (*handler)(struct kvm *kvm,
					    gpa_t gpa, u64 size,
					    void *data),
			     void *data)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;
	int ret = 0;

	slots = kvm_memslots(kvm);

	/* we only care about the pages that the guest sees */
	kvm_for_each_memslot(memslot, slots) {
		unsigned long hva_start, hva_end;
		gfn_t gpa;

		hva_start = max(start, memslot->userspace_addr);
		hva_end = min(end, memslot->userspace_addr +
					(memslot->npages << PAGE_SHIFT));
		if (hva_start >= hva_end)
			continue;

		gpa = hva_to_gfn_memslot(hva_start, memslot) << PAGE_SHIFT;
		ret |= handler(kvm, gpa, (u64)(hva_end - hva_start), data);
	}

	return ret;
}

static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
{
	unmap_stage2_range(kvm, gpa, size);
	return 0;
}

int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
{
	unsigned long end = hva + PAGE_SIZE;

	if (!kvm->arch.pgd)
		return 0;

	trace_kvm_unmap_hva(hva);
	handle_hva_to_gpa(kvm, hva, end, &kvm_unmap_hva_handler, NULL);
	return 0;
}

int kvm_unmap_hva_range(struct kvm *kvm,
			unsigned long start, unsigned long end)
{
	if (!kvm->arch.pgd)
		return 0;

	trace_kvm_unmap_hva_range(start, end);
	handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL);
	return 0;
}

static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
{
	pte_t *pte = (pte_t *)data;

	WARN_ON(size != PAGE_SIZE);
	/*
	 * We can always call stage2_set_pte with KVM_S2PTE_FLAG_LOGGING_ACTIVE
	 * flag clear because MMU notifiers will have unmapped a huge PMD before
	 * calling ->change_pte() (which in turn calls kvm_set_spte_hva()) and
	 * therefore stage2_set_pte() never needs to clear out a huge PMD
	 * through this calling path.
	 */
	stage2_set_pte(kvm, NULL, gpa, pte, 0);
	return 0;
}


void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
{
	unsigned long end = hva + PAGE_SIZE;
	pte_t stage2_pte;

	if (!kvm->arch.pgd)
		return;

	trace_kvm_set_spte_hva(hva);
	stage2_pte = pfn_pte(pte_pfn(pte), PAGE_S2);
	handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte);
}

static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
{
	pmd_t *pmd;
	pte_t *pte;

	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE);
	pmd = stage2_get_pmd(kvm, NULL, gpa);
	if (!pmd || pmd_none(*pmd))	/* Nothing there */
		return 0;

	if (pmd_thp_or_huge(*pmd))	/* THP, HugeTLB */
		return stage2_pmdp_test_and_clear_young(pmd);

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

	return stage2_ptep_test_and_clear_young(pte);
}

static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
{
	pmd_t *pmd;
	pte_t *pte;

	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE);
	pmd = stage2_get_pmd(kvm, NULL, gpa);
	if (!pmd || pmd_none(*pmd))	/* Nothing there */
		return 0;

	if (pmd_thp_or_huge(*pmd))		/* THP, HugeTLB */
		return pmd_young(*pmd);

	pte = pte_offset_kernel(pmd, gpa);
	if (!pte_none(*pte))		/* Just a page... */
		return pte_young(*pte);

	return 0;
}

int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
{
	if (!kvm->arch.pgd)
		return 0;
	trace_kvm_age_hva(start, end);
	return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL);
}

int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
{
	if (!kvm->arch.pgd)
		return 0;
	trace_kvm_test_age_hva(hva);
	return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL);
}

void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu)
{
	mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
}

phys_addr_t kvm_mmu_get_httbr(void)
{
	if (__kvm_cpu_uses_extended_idmap())
		return virt_to_phys(merged_hyp_pgd);
	else
		return virt_to_phys(hyp_pgd);
}

phys_addr_t kvm_get_idmap_vector(void)
{
	return hyp_idmap_vector;
}

static int kvm_map_idmap_text(pgd_t *pgd)
{
	int err;

	/* Create the idmap in the boot page tables */
	err = 	__create_hyp_mappings(pgd, __kvm_idmap_ptrs_per_pgd(),
				      hyp_idmap_start, hyp_idmap_end,
				      __phys_to_pfn(hyp_idmap_start),
				      PAGE_HYP_EXEC);
	if (err)
		kvm_err("Failed to idmap %lx-%lx\n",
			hyp_idmap_start, hyp_idmap_end);

	return err;
}

int kvm_mmu_init(void)
{
	int err;

	hyp_idmap_start = kvm_virt_to_phys(__hyp_idmap_text_start);
	hyp_idmap_start = ALIGN_DOWN(hyp_idmap_start, PAGE_SIZE);
	hyp_idmap_end = kvm_virt_to_phys(__hyp_idmap_text_end);
	hyp_idmap_end = ALIGN(hyp_idmap_end, PAGE_SIZE);
	hyp_idmap_vector = kvm_virt_to_phys(__kvm_hyp_init);

	/*
	 * We rely on the linker script to ensure at build time that the HYP
	 * init code does not cross a page boundary.
	 */
	BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK);

	kvm_debug("IDMAP page: %lx\n", hyp_idmap_start);
	kvm_debug("HYP VA range: %lx:%lx\n",
		  kern_hyp_va(PAGE_OFFSET),
		  kern_hyp_va((unsigned long)high_memory - 1));

	if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) &&
	    hyp_idmap_start <  kern_hyp_va((unsigned long)high_memory - 1) &&
	    hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) {
		/*
		 * The idmap page is intersecting with the VA space,
		 * it is not safe to continue further.
		 */
		kvm_err("IDMAP intersecting with HYP VA, unable to continue\n");
		err = -EINVAL;
		goto out;
	}

	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
	if (!hyp_pgd) {
		kvm_err("Hyp mode PGD not allocated\n");
		err = -ENOMEM;
		goto out;
	}

	if (__kvm_cpu_uses_extended_idmap()) {
		boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
							 hyp_pgd_order);
		if (!boot_hyp_pgd) {
			kvm_err("Hyp boot PGD not allocated\n");
			err = -ENOMEM;
			goto out;
		}

		err = kvm_map_idmap_text(boot_hyp_pgd);
		if (err)
			goto out;

		merged_hyp_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
		if (!merged_hyp_pgd) {
			kvm_err("Failed to allocate extra HYP pgd\n");
			goto out;
		}
		__kvm_extend_hypmap(boot_hyp_pgd, hyp_pgd, merged_hyp_pgd,
				    hyp_idmap_start);
	} else {
		err = kvm_map_idmap_text(hyp_pgd);
		if (err)
			goto out;
	}

	io_map_base = hyp_idmap_start;
	return 0;
out:
	free_hyp_pgds();
	return err;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				   const struct kvm_userspace_memory_region *mem,
				   const struct kvm_memory_slot *old,
				   const struct kvm_memory_slot *new,
				   enum kvm_mr_change change)
{
	/*
	 * At this point memslot has been committed and there is an
	 * allocated dirty_bitmap[], dirty pages will be be tracked while the
	 * memory slot is write protected.
	 */
	if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES)
		kvm_mmu_wp_memory_region(kvm, mem->slot);
}

int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *memslot,
				   const struct kvm_userspace_memory_region *mem,
				   enum kvm_mr_change change)
{
	hva_t hva = mem->userspace_addr;
	hva_t reg_end = hva + mem->memory_size;
	bool writable = !(mem->flags & KVM_MEM_READONLY);
	int ret = 0;

	if (change != KVM_MR_CREATE && change != KVM_MR_MOVE &&
			change != KVM_MR_FLAGS_ONLY)
		return 0;

	/*
	 * Prevent userspace from creating a memory region outside of the IPA
	 * space addressable by the KVM guest IPA space.
	 */
	if (memslot->base_gfn + memslot->npages >=
	    (KVM_PHYS_SIZE >> PAGE_SHIFT))
		return -EFAULT;

	down_read(&current->mm->mmap_sem);
	/*
	 * A memory region could potentially cover multiple VMAs, and any holes
	 * between them, so iterate over all of them to find out if we can map
	 * any of them right now.
	 *
	 *     +--------------------------------------------+
	 * +---------------+----------------+   +----------------+
	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
	 * +---------------+----------------+   +----------------+
	 *     |               memory region                |
	 *     +--------------------------------------------+
	 */
	do {
		struct vm_area_struct *vma = find_vma(current->mm, hva);
		hva_t vm_start, vm_end;

		if (!vma || vma->vm_start >= reg_end)
			break;

		/*
		 * Mapping a read-only VMA is only allowed if the
		 * memory region is configured as read-only.
		 */
		if (writable && !(vma->vm_flags & VM_WRITE)) {
			ret = -EPERM;
			break;
		}

		/*
		 * Take the intersection of this VMA with the memory region
		 */
		vm_start = max(hva, vma->vm_start);
		vm_end = min(reg_end, vma->vm_end);

		if (vma->vm_flags & VM_PFNMAP) {
			gpa_t gpa = mem->guest_phys_addr +
				    (vm_start - mem->userspace_addr);
			phys_addr_t pa;

			pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
			pa += vm_start - vma->vm_start;

			/* IO region dirty page logging not allowed */
			if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) {
				ret = -EINVAL;
				goto out;
			}

			ret = kvm_phys_addr_ioremap(kvm, gpa, pa,
						    vm_end - vm_start,
						    writable);
			if (ret)
				break;
		}
		hva = vm_end;
	} while (hva < reg_end);

	if (change == KVM_MR_FLAGS_ONLY)
		goto out;

	spin_lock(&kvm->mmu_lock);
	if (ret)
		unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size);
	else
		stage2_flush_memslot(kvm, memslot);
	spin_unlock(&kvm->mmu_lock);
out:
	up_read(&current->mm->mmap_sem);
	return ret;
}

void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
			   struct kvm_memory_slot *dont)
{
}

int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
			    unsigned long npages)
{
	return 0;
}

void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots)
{
}

void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
	kvm_free_stage2_pgd(kvm);
}

void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
				   struct kvm_memory_slot *slot)
{
	gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
	phys_addr_t size = slot->npages << PAGE_SHIFT;

	spin_lock(&kvm->mmu_lock);
	unmap_stage2_range(kvm, gpa, size);
	spin_unlock(&kvm->mmu_lock);
}

/*
 * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
 *
 * Main problems:
 * - S/W ops are local to a CPU (not broadcast)
 * - We have line migration behind our back (speculation)
 * - System caches don't support S/W at all (damn!)
 *
 * In the face of the above, the best we can do is to try and convert
 * S/W ops to VA ops. Because the guest is not allowed to infer the
 * S/W to PA mapping, it can only use S/W to nuke the whole cache,
 * which is a rather good thing for us.
 *
 * Also, it is only used when turning caches on/off ("The expected
 * usage of the cache maintenance instructions that operate by set/way
 * is associated with the cache maintenance instructions associated
 * with the powerdown and powerup of caches, if this is required by
 * the implementation.").
 *
 * We use the following policy:
 *
 * - If we trap a S/W operation, we enable VM trapping to detect
 *   caches being turned on/off, and do a full clean.
 *
 * - We flush the caches on both caches being turned on and off.
 *
 * - Once the caches are enabled, we stop trapping VM ops.
 */
void kvm_set_way_flush(struct kvm_vcpu *vcpu)
{
	unsigned long hcr = *vcpu_hcr(vcpu);

	/*
	 * If this is the first time we do a S/W operation
	 * (i.e. HCR_TVM not set) flush the whole memory, and set the
	 * VM trapping.
	 *
	 * Otherwise, rely on the VM trapping to wait for the MMU +
	 * Caches to be turned off. At that point, we'll be able to
	 * clean the caches again.
	 */
	if (!(hcr & HCR_TVM)) {
		trace_kvm_set_way_flush(*vcpu_pc(vcpu),
					vcpu_has_cache_enabled(vcpu));
		stage2_flush_vm(vcpu->kvm);
		*vcpu_hcr(vcpu) = hcr | HCR_TVM;
	}
}

void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled)
{
	bool now_enabled = vcpu_has_cache_enabled(vcpu);

	/*
	 * If switching the MMU+caches on, need to invalidate the caches.
	 * If switching it off, need to clean the caches.
	 * Clean + invalidate does the trick always.
	 */
	if (now_enabled != was_enabled)
		stage2_flush_vm(vcpu->kvm);

	/* Caches are now on, stop trapping VM ops (until a S/W op) */
	if (now_enabled)
		*vcpu_hcr(vcpu) &= ~HCR_TVM;

	trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled);
}