summaryrefslogtreecommitdiff
path: root/arch/arm64/kvm/mmu.c
blob: 0f7658aefa1a3ddb0ee5a5e6a6cc25857d80b9c6 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2012 - Virtual Open Systems and Columbia University
 * Author: Christoffer Dall <c.dall@virtualopensystems.com>
 */

#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_pgtable.h>
#include <asm/kvm_ras.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/virt.h>

#include "trace.h"

static struct kvm_pgtable *hyp_pgtable;
static DEFINE_MUTEX(kvm_hyp_pgd_mutex);

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

static unsigned long __ro_after_init io_map_base;

static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end,
					   phys_addr_t size)
{
	phys_addr_t boundary = ALIGN_DOWN(addr + size, size);

	return (boundary - 1 < end - 1) ? boundary : end;
}

static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
{
	phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL);

	return __stage2_range_addr_end(addr, end, size);
}

/*
 * 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.
 */
static int stage2_apply_range(struct kvm_s2_mmu *mmu, phys_addr_t addr,
			      phys_addr_t end,
			      int (*fn)(struct kvm_pgtable *, u64, u64),
			      bool resched)
{
	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
	int ret;
	u64 next;

	do {
		struct kvm_pgtable *pgt = mmu->pgt;
		if (!pgt)
			return -EINVAL;

		next = stage2_range_addr_end(addr, end);
		ret = fn(pgt, addr, next - addr);
		if (ret)
			break;

		if (resched && next != end)
			cond_resched_rwlock_write(&kvm->mmu_lock);
	} while (addr = next, addr != end);

	return ret;
}

#define stage2_apply_range_resched(mmu, addr, end, fn)			\
	stage2_apply_range(mmu, addr, end, fn, true)

/*
 * Get the maximum number of page-tables pages needed to split a range
 * of blocks into PAGE_SIZE PTEs. It assumes the range is already
 * mapped at level 2, or at level 1 if allowed.
 */
static int kvm_mmu_split_nr_page_tables(u64 range)
{
	int n = 0;

	if (KVM_PGTABLE_MIN_BLOCK_LEVEL < 2)
		n += DIV_ROUND_UP(range, PUD_SIZE);
	n += DIV_ROUND_UP(range, PMD_SIZE);
	return n;
}

static bool need_split_memcache_topup_or_resched(struct kvm *kvm)
{
	struct kvm_mmu_memory_cache *cache;
	u64 chunk_size, min;

	if (need_resched() || rwlock_needbreak(&kvm->mmu_lock))
		return true;

	chunk_size = kvm->arch.mmu.split_page_chunk_size;
	min = kvm_mmu_split_nr_page_tables(chunk_size);
	cache = &kvm->arch.mmu.split_page_cache;
	return kvm_mmu_memory_cache_nr_free_objects(cache) < min;
}

static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr,
				    phys_addr_t end)
{
	struct kvm_mmu_memory_cache *cache;
	struct kvm_pgtable *pgt;
	int ret, cache_capacity;
	u64 next, chunk_size;

	lockdep_assert_held_write(&kvm->mmu_lock);

	chunk_size = kvm->arch.mmu.split_page_chunk_size;
	cache_capacity = kvm_mmu_split_nr_page_tables(chunk_size);

	if (chunk_size == 0)
		return 0;

	cache = &kvm->arch.mmu.split_page_cache;

	do {
		if (need_split_memcache_topup_or_resched(kvm)) {
			write_unlock(&kvm->mmu_lock);
			cond_resched();
			/* Eager page splitting is best-effort. */
			ret = __kvm_mmu_topup_memory_cache(cache,
							   cache_capacity,
							   cache_capacity);
			write_lock(&kvm->mmu_lock);
			if (ret)
				break;
		}

		pgt = kvm->arch.mmu.pgt;
		if (!pgt)
			return -EINVAL;

		next = __stage2_range_addr_end(addr, end, chunk_size);
		ret = kvm_pgtable_stage2_split(pgt, addr, next - addr, cache);
		if (ret)
			break;
	} while (addr = next, addr != end);

	return ret;
}

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

/**
 * kvm_arch_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
 */
int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
{
	kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
	return 0;
}

int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
				      gfn_t gfn, u64 nr_pages)
{
	kvm_tlb_flush_vmid_range(&kvm->arch.mmu,
				gfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
	return 0;
}

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

static void *stage2_memcache_zalloc_page(void *arg)
{
	struct kvm_mmu_memory_cache *mc = arg;
	void *virt;

	/* Allocated with __GFP_ZERO, so no need to zero */
	virt = kvm_mmu_memory_cache_alloc(mc);
	if (virt)
		kvm_account_pgtable_pages(virt, 1);
	return virt;
}

static void *kvm_host_zalloc_pages_exact(size_t size)
{
	return alloc_pages_exact(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
}

static void *kvm_s2_zalloc_pages_exact(size_t size)
{
	void *virt = kvm_host_zalloc_pages_exact(size);

	if (virt)
		kvm_account_pgtable_pages(virt, (size >> PAGE_SHIFT));
	return virt;
}

static void kvm_s2_free_pages_exact(void *virt, size_t size)
{
	kvm_account_pgtable_pages(virt, -(size >> PAGE_SHIFT));
	free_pages_exact(virt, size);
}

static struct kvm_pgtable_mm_ops kvm_s2_mm_ops;

static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head)
{
	struct page *page = container_of(head, struct page, rcu_head);
	void *pgtable = page_to_virt(page);
	s8 level = page_private(page);

	kvm_pgtable_stage2_free_unlinked(&kvm_s2_mm_ops, pgtable, level);
}

static void stage2_free_unlinked_table(void *addr, s8 level)
{
	struct page *page = virt_to_page(addr);

	set_page_private(page, (unsigned long)level);
	call_rcu(&page->rcu_head, stage2_free_unlinked_table_rcu_cb);
}

static void kvm_host_get_page(void *addr)
{
	get_page(virt_to_page(addr));
}

static void kvm_host_put_page(void *addr)
{
	put_page(virt_to_page(addr));
}

static void kvm_s2_put_page(void *addr)
{
	struct page *p = virt_to_page(addr);
	/* Dropping last refcount, the page will be freed */
	if (page_count(p) == 1)
		kvm_account_pgtable_pages(addr, -1);
	put_page(p);
}

static int kvm_host_page_count(void *addr)
{
	return page_count(virt_to_page(addr));
}

static phys_addr_t kvm_host_pa(void *addr)
{
	return __pa(addr);
}

static void *kvm_host_va(phys_addr_t phys)
{
	return __va(phys);
}

static void clean_dcache_guest_page(void *va, size_t size)
{
	__clean_dcache_guest_page(va, size);
}

static void invalidate_icache_guest_page(void *va, size_t size)
{
	__invalidate_icache_guest_page(va, size);
}

/*
 * 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 flush 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.
 */
/**
 * __unmap_stage2_range -- Clear stage2 page table entries to unmap a range
 * @mmu:   The KVM stage-2 MMU pointer
 * @start: The intermediate physical base address of the range to unmap
 * @size:  The size of the area to unmap
 * @may_block: Whether or not we are permitted to block
 *
 * 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_s2_mmu *mmu, phys_addr_t start, u64 size,
				 bool may_block)
{
	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
	phys_addr_t end = start + size;

	lockdep_assert_held_write(&kvm->mmu_lock);
	WARN_ON(size & ~PAGE_MASK);
	WARN_ON(stage2_apply_range(mmu, start, end, kvm_pgtable_stage2_unmap,
				   may_block));
}

void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
			    u64 size, bool may_block)
{
	__unmap_stage2_range(mmu, start, size, may_block);
}

void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
{
	stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_flush);
}

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;

	kvm_stage2_flush_range(&kvm->arch.mmu, 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, bkt;

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

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

	kvm_nested_s2_flush(kvm);

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

/**
 * free_hyp_pgds - free Hyp-mode page tables
 */
void __init free_hyp_pgds(void)
{
	mutex_lock(&kvm_hyp_pgd_mutex);
	if (hyp_pgtable) {
		kvm_pgtable_hyp_destroy(hyp_pgtable);
		kfree(hyp_pgtable);
		hyp_pgtable = NULL;
	}
	mutex_unlock(&kvm_hyp_pgd_mutex);
}

static bool kvm_host_owns_hyp_mappings(void)
{
	if (is_kernel_in_hyp_mode())
		return false;

	if (static_branch_likely(&kvm_protected_mode_initialized))
		return false;

	/*
	 * This can happen at boot time when __create_hyp_mappings() is called
	 * after the hyp protection has been enabled, but the static key has
	 * not been flipped yet.
	 */
	if (!hyp_pgtable && is_protected_kvm_enabled())
		return false;

	WARN_ON(!hyp_pgtable);

	return true;
}

int __create_hyp_mappings(unsigned long start, unsigned long size,
			  unsigned long phys, enum kvm_pgtable_prot prot)
{
	int err;

	if (WARN_ON(!kvm_host_owns_hyp_mappings()))
		return -EINVAL;

	mutex_lock(&kvm_hyp_pgd_mutex);
	err = kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot);
	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);
	}
}

struct hyp_shared_pfn {
	u64 pfn;
	int count;
	struct rb_node node;
};

static DEFINE_MUTEX(hyp_shared_pfns_lock);
static struct rb_root hyp_shared_pfns = RB_ROOT;

static struct hyp_shared_pfn *find_shared_pfn(u64 pfn, struct rb_node ***node,
					      struct rb_node **parent)
{
	struct hyp_shared_pfn *this;

	*node = &hyp_shared_pfns.rb_node;
	*parent = NULL;
	while (**node) {
		this = container_of(**node, struct hyp_shared_pfn, node);
		*parent = **node;
		if (this->pfn < pfn)
			*node = &((**node)->rb_left);
		else if (this->pfn > pfn)
			*node = &((**node)->rb_right);
		else
			return this;
	}

	return NULL;
}

static int share_pfn_hyp(u64 pfn)
{
	struct rb_node **node, *parent;
	struct hyp_shared_pfn *this;
	int ret = 0;

	mutex_lock(&hyp_shared_pfns_lock);
	this = find_shared_pfn(pfn, &node, &parent);
	if (this) {
		this->count++;
		goto unlock;
	}

	this = kzalloc(sizeof(*this), GFP_KERNEL);
	if (!this) {
		ret = -ENOMEM;
		goto unlock;
	}

	this->pfn = pfn;
	this->count = 1;
	rb_link_node(&this->node, parent, node);
	rb_insert_color(&this->node, &hyp_shared_pfns);
	ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp, pfn, 1);
unlock:
	mutex_unlock(&hyp_shared_pfns_lock);

	return ret;
}

static int unshare_pfn_hyp(u64 pfn)
{
	struct rb_node **node, *parent;
	struct hyp_shared_pfn *this;
	int ret = 0;

	mutex_lock(&hyp_shared_pfns_lock);
	this = find_shared_pfn(pfn, &node, &parent);
	if (WARN_ON(!this)) {
		ret = -ENOENT;
		goto unlock;
	}

	this->count--;
	if (this->count)
		goto unlock;

	rb_erase(&this->node, &hyp_shared_pfns);
	kfree(this);
	ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_hyp, pfn, 1);
unlock:
	mutex_unlock(&hyp_shared_pfns_lock);

	return ret;
}

int kvm_share_hyp(void *from, void *to)
{
	phys_addr_t start, end, cur;
	u64 pfn;
	int ret;

	if (is_kernel_in_hyp_mode())
		return 0;

	/*
	 * The share hcall maps things in the 'fixed-offset' region of the hyp
	 * VA space, so we can only share physically contiguous data-structures
	 * for now.
	 */
	if (is_vmalloc_or_module_addr(from) || is_vmalloc_or_module_addr(to))
		return -EINVAL;

	if (kvm_host_owns_hyp_mappings())
		return create_hyp_mappings(from, to, PAGE_HYP);

	start = ALIGN_DOWN(__pa(from), PAGE_SIZE);
	end = PAGE_ALIGN(__pa(to));
	for (cur = start; cur < end; cur += PAGE_SIZE) {
		pfn = __phys_to_pfn(cur);
		ret = share_pfn_hyp(pfn);
		if (ret)
			return ret;
	}

	return 0;
}

void kvm_unshare_hyp(void *from, void *to)
{
	phys_addr_t start, end, cur;
	u64 pfn;

	if (is_kernel_in_hyp_mode() || kvm_host_owns_hyp_mappings() || !from)
		return;

	start = ALIGN_DOWN(__pa(from), PAGE_SIZE);
	end = PAGE_ALIGN(__pa(to));
	for (cur = start; cur < end; cur += PAGE_SIZE) {
		pfn = __phys_to_pfn(cur);
		WARN_ON(unshare_pfn_hyp(pfn));
	}
}

/**
 * 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, enum kvm_pgtable_prot 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;

	if (!kvm_host_owns_hyp_mappings())
		return -EPERM;

	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(virt_addr, PAGE_SIZE, phys_addr,
					    prot);
		if (err)
			return err;
	}

	return 0;
}

static int __hyp_alloc_private_va_range(unsigned long base)
{
	lockdep_assert_held(&kvm_hyp_pgd_mutex);

	if (!PAGE_ALIGNED(base))
		return -EINVAL;

	/*
	 * 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))
		return -ENOMEM;

	io_map_base = base;

	return 0;
}

/**
 * hyp_alloc_private_va_range - Allocates a private VA range.
 * @size:	The size of the VA range to reserve.
 * @haddr:	The hypervisor virtual start address of the allocation.
 *
 * The private virtual address (VA) range is allocated below io_map_base
 * and aligned based on the order of @size.
 *
 * Return: 0 on success or negative error code on failure.
 */
int hyp_alloc_private_va_range(size_t size, unsigned long *haddr)
{
	unsigned long base;
	int ret = 0;

	mutex_lock(&kvm_hyp_pgd_mutex);

	/*
	 * This assumes that we have enough space below the idmap
	 * page to allocate our VAs. If not, the check in
	 * __hyp_alloc_private_va_range() 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);
	base = io_map_base - size;
	ret = __hyp_alloc_private_va_range(base);

	mutex_unlock(&kvm_hyp_pgd_mutex);

	if (!ret)
		*haddr = base;

	return ret;
}

static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size,
					unsigned long *haddr,
					enum kvm_pgtable_prot prot)
{
	unsigned long addr;
	int ret = 0;

	if (!kvm_host_owns_hyp_mappings()) {
		addr = kvm_call_hyp_nvhe(__pkvm_create_private_mapping,
					 phys_addr, size, prot);
		if (IS_ERR_VALUE(addr))
			return addr;
		*haddr = addr;

		return 0;
	}

	size = PAGE_ALIGN(size + offset_in_page(phys_addr));
	ret = hyp_alloc_private_va_range(size, &addr);
	if (ret)
		return ret;

	ret = __create_hyp_mappings(addr, size, phys_addr, prot);
	if (ret)
		return ret;

	*haddr = addr + offset_in_page(phys_addr);
	return ret;
}

int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr)
{
	unsigned long base;
	size_t size;
	int ret;

	mutex_lock(&kvm_hyp_pgd_mutex);
	/*
	 * Efficient stack verification using the PAGE_SHIFT bit implies
	 * an alignment of our allocation on the order of the size.
	 */
	size = PAGE_SIZE * 2;
	base = ALIGN_DOWN(io_map_base - size, size);

	ret = __hyp_alloc_private_va_range(base);

	mutex_unlock(&kvm_hyp_pgd_mutex);

	if (ret) {
		kvm_err("Cannot allocate hyp stack guard page\n");
		return ret;
	}

	/*
	 * Since the stack grows downwards, map the stack to the page
	 * at the higher address and leave the lower guard page
	 * unbacked.
	 *
	 * Any valid stack address now has the PAGE_SHIFT bit as 1
	 * and addresses corresponding to the guard page have the
	 * PAGE_SHIFT bit as 0 - this is used for overflow detection.
	 */
	ret = __create_hyp_mappings(base + PAGE_SIZE, PAGE_SIZE, phys_addr,
				    PAGE_HYP);
	if (ret)
		kvm_err("Cannot map hyp stack\n");

	*haddr = base + size;

	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;

	if (is_protected_kvm_enabled())
		return -EPERM;

	*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;
}

static struct kvm_pgtable_mm_ops kvm_user_mm_ops = {
	/* We shouldn't need any other callback to walk the PT */
	.phys_to_virt		= kvm_host_va,
};

static int get_user_mapping_size(struct kvm *kvm, u64 addr)
{
	struct kvm_pgtable pgt = {
		.pgd		= (kvm_pteref_t)kvm->mm->pgd,
		.ia_bits	= vabits_actual,
		.start_level	= (KVM_PGTABLE_LAST_LEVEL -
				   ARM64_HW_PGTABLE_LEVELS(pgt.ia_bits) + 1),
		.mm_ops		= &kvm_user_mm_ops,
	};
	unsigned long flags;
	kvm_pte_t pte = 0;	/* Keep GCC quiet... */
	s8 level = S8_MAX;
	int ret;

	/*
	 * Disable IRQs so that we hazard against a concurrent
	 * teardown of the userspace page tables (which relies on
	 * IPI-ing threads).
	 */
	local_irq_save(flags);
	ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level);
	local_irq_restore(flags);

	if (ret)
		return ret;

	/*
	 * Not seeing an error, but not updating level? Something went
	 * deeply wrong...
	 */
	if (WARN_ON(level > KVM_PGTABLE_LAST_LEVEL))
		return -EFAULT;
	if (WARN_ON(level < KVM_PGTABLE_FIRST_LEVEL))
		return -EFAULT;

	/* Oops, the userspace PTs are gone... Replay the fault */
	if (!kvm_pte_valid(pte))
		return -EAGAIN;

	return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level));
}

static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
	.zalloc_page		= stage2_memcache_zalloc_page,
	.zalloc_pages_exact	= kvm_s2_zalloc_pages_exact,
	.free_pages_exact	= kvm_s2_free_pages_exact,
	.free_unlinked_table	= stage2_free_unlinked_table,
	.get_page		= kvm_host_get_page,
	.put_page		= kvm_s2_put_page,
	.page_count		= kvm_host_page_count,
	.phys_to_virt		= kvm_host_va,
	.virt_to_phys		= kvm_host_pa,
	.dcache_clean_inval_poc	= clean_dcache_guest_page,
	.icache_inval_pou	= invalidate_icache_guest_page,
};

static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type)
{
	u32 kvm_ipa_limit = get_kvm_ipa_limit();
	u64 mmfr0, mmfr1;
	u32 phys_shift;

	if (type & ~KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
		return -EINVAL;

	phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type);
	if (is_protected_kvm_enabled()) {
		phys_shift = kvm_ipa_limit;
	} else if (phys_shift) {
		if (phys_shift > kvm_ipa_limit ||
		    phys_shift < ARM64_MIN_PARANGE_BITS)
			return -EINVAL;
	} else {
		phys_shift = KVM_PHYS_SHIFT;
		if (phys_shift > kvm_ipa_limit) {
			pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n",
				     current->comm);
			return -EINVAL;
		}
	}

	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
	mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
	mmu->vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift);

	return 0;
}

/**
 * kvm_init_stage2_mmu - Initialise a S2 MMU structure
 * @kvm:	The pointer to the KVM structure
 * @mmu:	The pointer to the s2 MMU structure
 * @type:	The machine type of the virtual machine
 *
 * Allocates only the stage-2 HW PGD level table(s).
 * Note we don't need locking here as this is only called in two cases:
 *
 * - when the VM is created, which can't race against anything
 *
 * - when secondary kvm_s2_mmu structures are initialised for NV
 *   guests, and the caller must hold kvm->lock as this is called on a
 *   per-vcpu basis.
 */
int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type)
{
	int cpu, err;
	struct kvm_pgtable *pgt;

	/*
	 * If we already have our page tables in place, and that the
	 * MMU context is the canonical one, we have a bug somewhere,
	 * as this is only supposed to ever happen once per VM.
	 *
	 * Otherwise, we're building nested page tables, and that's
	 * probably because userspace called KVM_ARM_VCPU_INIT more
	 * than once on the same vcpu. Since that's actually legal,
	 * don't kick a fuss and leave gracefully.
	 */
	if (mmu->pgt != NULL) {
		if (kvm_is_nested_s2_mmu(kvm, mmu))
			return 0;

		kvm_err("kvm_arch already initialized?\n");
		return -EINVAL;
	}

	err = kvm_init_ipa_range(mmu, type);
	if (err)
		return err;

	pgt = kzalloc(sizeof(*pgt), GFP_KERNEL_ACCOUNT);
	if (!pgt)
		return -ENOMEM;

	mmu->arch = &kvm->arch;
	err = kvm_pgtable_stage2_init(pgt, mmu, &kvm_s2_mm_ops);
	if (err)
		goto out_free_pgtable;

	mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran));
	if (!mmu->last_vcpu_ran) {
		err = -ENOMEM;
		goto out_destroy_pgtable;
	}

	for_each_possible_cpu(cpu)
		*per_cpu_ptr(mmu->last_vcpu_ran, cpu) = -1;

	 /* The eager page splitting is disabled by default */
	mmu->split_page_chunk_size = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT;
	mmu->split_page_cache.gfp_zero = __GFP_ZERO;

	mmu->pgt = pgt;
	mmu->pgd_phys = __pa(pgt->pgd);

	if (kvm_is_nested_s2_mmu(kvm, mmu))
		kvm_init_nested_s2_mmu(mmu);

	return 0;

out_destroy_pgtable:
	kvm_pgtable_stage2_destroy(pgt);
out_free_pgtable:
	kfree(pgt);
	return err;
}

void kvm_uninit_stage2_mmu(struct kvm *kvm)
{
	kvm_free_stage2_pgd(&kvm->arch.mmu);
	kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache);
}

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;
		hva_t vm_start, vm_end;

		vma = find_vma_intersection(current->mm, hva, reg_end);
		if (!vma)
			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);
			kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start, true);
		}
		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 regular 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, bkt;

	idx = srcu_read_lock(&kvm->srcu);
	mmap_read_lock(current->mm);
	write_lock(&kvm->mmu_lock);

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

	kvm_nested_s2_unmap(kvm, true);

	write_unlock(&kvm->mmu_lock);
	mmap_read_unlock(current->mm);
	srcu_read_unlock(&kvm->srcu, idx);
}

void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
{
	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
	struct kvm_pgtable *pgt = NULL;

	write_lock(&kvm->mmu_lock);
	pgt = mmu->pgt;
	if (pgt) {
		mmu->pgd_phys = 0;
		mmu->pgt = NULL;
		free_percpu(mmu->last_vcpu_ran);
	}
	write_unlock(&kvm->mmu_lock);

	if (pgt) {
		kvm_pgtable_stage2_destroy(pgt);
		kfree(pgt);
	}
}

static void hyp_mc_free_fn(void *addr, void *unused)
{
	free_page((unsigned long)addr);
}

static void *hyp_mc_alloc_fn(void *unused)
{
	return (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
}

void free_hyp_memcache(struct kvm_hyp_memcache *mc)
{
	if (is_protected_kvm_enabled())
		__free_hyp_memcache(mc, hyp_mc_free_fn,
				    kvm_host_va, NULL);
}

int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages)
{
	if (!is_protected_kvm_enabled())
		return 0;

	return __topup_hyp_memcache(mc, min_pages, hyp_mc_alloc_fn,
				    kvm_host_pa, NULL);
}

/**
 * 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
 * @writable:   Whether or not to create a writable 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;
	int ret = 0;
	struct kvm_mmu_memory_cache cache = { .gfp_zero = __GFP_ZERO };
	struct kvm_s2_mmu *mmu = &kvm->arch.mmu;
	struct kvm_pgtable *pgt = mmu->pgt;
	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_DEVICE |
				     KVM_PGTABLE_PROT_R |
				     (writable ? KVM_PGTABLE_PROT_W : 0);

	if (is_protected_kvm_enabled())
		return -EPERM;

	size += offset_in_page(guest_ipa);
	guest_ipa &= PAGE_MASK;

	for (addr = guest_ipa; addr < guest_ipa + size; addr += PAGE_SIZE) {
		ret = kvm_mmu_topup_memory_cache(&cache,
						 kvm_mmu_cache_min_pages(mmu));
		if (ret)
			break;

		write_lock(&kvm->mmu_lock);
		ret = kvm_pgtable_stage2_map(pgt, addr, PAGE_SIZE, pa, prot,
					     &cache, 0);
		write_unlock(&kvm->mmu_lock);
		if (ret)
			break;

		pa += PAGE_SIZE;
	}

	kvm_mmu_free_memory_cache(&cache);
	return ret;
}

/**
 * kvm_stage2_wp_range() - write protect stage2 memory region range
 * @mmu:        The KVM stage-2 MMU pointer
 * @addr:	Start address of range
 * @end:	End address of range
 */
void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
{
	stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_wrprotect);
}

/**
 * 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 PUD, 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.
 */
static 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, end;

	if (WARN_ON_ONCE(!memslot))
		return;

	start = memslot->base_gfn << PAGE_SHIFT;
	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;

	write_lock(&kvm->mmu_lock);
	kvm_stage2_wp_range(&kvm->arch.mmu, start, end);
	kvm_nested_s2_wp(kvm);
	write_unlock(&kvm->mmu_lock);
	kvm_flush_remote_tlbs_memslot(kvm, memslot);
}

/**
 * kvm_mmu_split_memory_region() - split the stage 2 blocks into PAGE_SIZE
 *				   pages for memory slot
 * @kvm:	The KVM pointer
 * @slot:	The memory slot to split
 *
 * Acquires kvm->mmu_lock. Called with kvm->slots_lock mutex acquired,
 * serializing operations for VM memory regions.
 */
static void kvm_mmu_split_memory_region(struct kvm *kvm, int slot)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;
	phys_addr_t start, end;

	lockdep_assert_held(&kvm->slots_lock);

	slots = kvm_memslots(kvm);
	memslot = id_to_memslot(slots, slot);

	start = memslot->base_gfn << PAGE_SHIFT;
	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;

	write_lock(&kvm->mmu_lock);
	kvm_mmu_split_huge_pages(kvm, start, end);
	write_unlock(&kvm->mmu_lock);
}

/*
 * kvm_arch_mmu_enable_log_dirty_pt_masked() - enable dirty logging for selected pages.
 * @kvm:	The KVM pointer
 * @slot:	The memory slot associated with mask
 * @gfn_offset:	The gfn offset in memory slot
 * @mask:	The mask of pages at offset 'gfn_offset' in this memory
 *		slot to enable dirty logging on
 *
 * Writes protect selected pages to enable dirty logging, and then
 * splits them to PAGE_SIZE. Caller must acquire kvm->mmu_lock.
 */
void kvm_arch_mmu_enable_log_dirty_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;

	lockdep_assert_held_write(&kvm->mmu_lock);

	kvm_stage2_wp_range(&kvm->arch.mmu, start, end);

	/*
	 * Eager-splitting is done when manual-protect is set.  We
	 * also check for initially-all-set because we can avoid
	 * eager-splitting if initially-all-set is false.
	 * Initially-all-set equal false implies that huge-pages were
	 * already split when enabling dirty logging: no need to do it
	 * again.
	 */
	if (kvm_dirty_log_manual_protect_and_init_set(kvm))
		kvm_mmu_split_huge_pages(kvm, start, end);

	kvm_nested_s2_wp(kvm);
}

static void kvm_send_hwpoison_signal(unsigned long address, short lsb)
{
	send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, current);
}

static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
					       unsigned long hva,
					       unsigned long map_size)
{
	gpa_t gpa_start;
	hva_t uaddr_start, uaddr_end;
	size_t size;

	/* The memslot and the VMA are guaranteed to be aligned to PAGE_SIZE */
	if (map_size == PAGE_SIZE)
		return true;

	size = memslot->npages * PAGE_SIZE;

	gpa_start = memslot->base_gfn << PAGE_SHIFT;

	uaddr_start = memslot->userspace_addr;
	uaddr_end = uaddr_start + size;

	/*
	 * Pages belonging to memslots that don't have the same alignment
	 * within a PMD/PUD for userspace and IPA cannot be mapped with stage-2
	 * PMD/PUD entries, because we'll end up mapping the wrong pages.
	 *
	 * Consider a layout like the following:
	 *
	 *    memslot->userspace_addr:
	 *    +-----+--------------------+--------------------+---+
	 *    |abcde|fgh  Stage-1 block  |    Stage-1 block tv|xyz|
	 *    +-----+--------------------+--------------------+---+
	 *
	 *    memslot->base_gfn << PAGE_SHIFT:
	 *      +---+--------------------+--------------------+-----+
	 *      |abc|def  Stage-2 block  |    Stage-2 block   |tvxyz|
	 *      +---+--------------------+--------------------+-----+
	 *
	 * If we create those stage-2 blocks, we'll end up with this incorrect
	 * mapping:
	 *   d -> f
	 *   e -> g
	 *   f -> h
	 */
	if ((gpa_start & (map_size - 1)) != (uaddr_start & (map_size - 1)))
		return false;

	/*
	 * Next, let's make sure we're not trying to map anything not covered
	 * by the memslot. This means we have to prohibit block size mappings
	 * for the beginning and end of a non-block aligned and non-block sized
	 * memory slot (illustrated by the head and tail parts of the
	 * userspace view above containing pages 'abcde' and 'xyz',
	 * respectively).
	 *
	 * Note that it doesn't matter if we do the check using the
	 * userspace_addr or the base_gfn, as both are equally aligned (per
	 * the check above) and equally sized.
	 */
	return (hva & ~(map_size - 1)) >= uaddr_start &&
	       (hva & ~(map_size - 1)) + map_size <= uaddr_end;
}

/*
 * Check if the given hva is backed by a transparent huge page (THP) and
 * whether it can be mapped using block mapping in stage2. If so, adjust
 * the stage2 PFN and IPA accordingly. Only PMD_SIZE THPs are currently
 * supported. This will need to be updated to support other THP sizes.
 *
 * Returns the size of the mapping.
 */
static long
transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot,
			    unsigned long hva, kvm_pfn_t *pfnp,
			    phys_addr_t *ipap)
{
	kvm_pfn_t pfn = *pfnp;

	/*
	 * Make sure the adjustment is done only for THP pages. Also make
	 * sure that the HVA and IPA are sufficiently aligned and that the
	 * block map is contained within the memslot.
	 */
	if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) {
		int sz = get_user_mapping_size(kvm, hva);

		if (sz < 0)
			return sz;

		if (sz < PMD_SIZE)
			return PAGE_SIZE;

		*ipap &= PMD_MASK;
		pfn &= ~(PTRS_PER_PMD - 1);
		*pfnp = pfn;

		return PMD_SIZE;
	}

	/* Use page mapping if we cannot use block mapping. */
	return PAGE_SIZE;
}

static int get_vma_page_shift(struct vm_area_struct *vma, unsigned long hva)
{
	unsigned long pa;

	if (is_vm_hugetlb_page(vma) && !(vma->vm_flags & VM_PFNMAP))
		return huge_page_shift(hstate_vma(vma));

	if (!(vma->vm_flags & VM_PFNMAP))
		return PAGE_SHIFT;

	VM_BUG_ON(is_vm_hugetlb_page(vma));

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

#ifndef __PAGETABLE_PMD_FOLDED
	if ((hva & (PUD_SIZE - 1)) == (pa & (PUD_SIZE - 1)) &&
	    ALIGN_DOWN(hva, PUD_SIZE) >= vma->vm_start &&
	    ALIGN(hva, PUD_SIZE) <= vma->vm_end)
		return PUD_SHIFT;
#endif

	if ((hva & (PMD_SIZE - 1)) == (pa & (PMD_SIZE - 1)) &&
	    ALIGN_DOWN(hva, PMD_SIZE) >= vma->vm_start &&
	    ALIGN(hva, PMD_SIZE) <= vma->vm_end)
		return PMD_SHIFT;

	return PAGE_SHIFT;
}

/*
 * The page will be mapped in stage 2 as Normal Cacheable, so the VM will be
 * able to see the page's tags and therefore they must be initialised first. If
 * PG_mte_tagged is set, tags have already been initialised.
 *
 * The race in the test/set of the PG_mte_tagged flag is handled by:
 * - preventing VM_SHARED mappings in a memslot with MTE preventing two VMs
 *   racing to santise the same page
 * - mmap_lock protects between a VM faulting a page in and the VMM performing
 *   an mprotect() to add VM_MTE
 */
static void sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn,
			      unsigned long size)
{
	unsigned long i, nr_pages = size >> PAGE_SHIFT;
	struct page *page = pfn_to_page(pfn);

	if (!kvm_has_mte(kvm))
		return;

	for (i = 0; i < nr_pages; i++, page++) {
		if (try_page_mte_tagging(page)) {
			mte_clear_page_tags(page_address(page));
			set_page_mte_tagged(page);
		}
	}
}

static bool kvm_vma_mte_allowed(struct vm_area_struct *vma)
{
	return vma->vm_flags & VM_MTE_ALLOWED;
}

static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
			  struct kvm_s2_trans *nested,
			  struct kvm_memory_slot *memslot, unsigned long hva,
			  bool fault_is_perm)
{
	int ret = 0;
	bool write_fault, writable, force_pte = false;
	bool exec_fault, mte_allowed;
	bool device = false, vfio_allow_any_uc = false;
	unsigned long mmu_seq;
	phys_addr_t ipa = fault_ipa;
	struct kvm *kvm = vcpu->kvm;
	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
	struct vm_area_struct *vma;
	short vma_shift;
	gfn_t gfn;
	kvm_pfn_t pfn;
	bool logging_active = memslot_is_logging(memslot);
	long vma_pagesize, fault_granule;
	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
	struct kvm_pgtable *pgt;

	if (fault_is_perm)
		fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu);
	write_fault = kvm_is_write_fault(vcpu);
	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
	VM_BUG_ON(write_fault && exec_fault);

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

	/*
	 * Permission faults just need to update the existing leaf entry,
	 * and so normally don't require allocations from the memcache. The
	 * only exception to this is when dirty logging is enabled at runtime
	 * and a write fault needs to collapse a block entry into a table.
	 */
	if (!fault_is_perm || (logging_active && write_fault)) {
		ret = kvm_mmu_topup_memory_cache(memcache,
						 kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu));
		if (ret)
			return ret;
	}

	/*
	 * Let's check if we will get back a huge page backed by hugetlbfs, or
	 * get block mapping for device MMIO region.
	 */
	mmap_read_lock(current->mm);
	vma = vma_lookup(current->mm, hva);
	if (unlikely(!vma)) {
		kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
		mmap_read_unlock(current->mm);
		return -EFAULT;
	}

	/*
	 * logging_active is guaranteed to never be true for VM_PFNMAP
	 * memslots.
	 */
	if (logging_active) {
		force_pte = true;
		vma_shift = PAGE_SHIFT;
	} else {
		vma_shift = get_vma_page_shift(vma, hva);
	}

	switch (vma_shift) {
#ifndef __PAGETABLE_PMD_FOLDED
	case PUD_SHIFT:
		if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE))
			break;
		fallthrough;
#endif
	case CONT_PMD_SHIFT:
		vma_shift = PMD_SHIFT;
		fallthrough;
	case PMD_SHIFT:
		if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE))
			break;
		fallthrough;
	case CONT_PTE_SHIFT:
		vma_shift = PAGE_SHIFT;
		force_pte = true;
		fallthrough;
	case PAGE_SHIFT:
		break;
	default:
		WARN_ONCE(1, "Unknown vma_shift %d", vma_shift);
	}

	vma_pagesize = 1UL << vma_shift;

	if (nested) {
		unsigned long max_map_size;

		max_map_size = force_pte ? PAGE_SIZE : PUD_SIZE;

		ipa = kvm_s2_trans_output(nested);

		/*
		 * If we're about to create a shadow stage 2 entry, then we
		 * can only create a block mapping if the guest stage 2 page
		 * table uses at least as big a mapping.
		 */
		max_map_size = min(kvm_s2_trans_size(nested), max_map_size);

		/*
		 * Be careful that if the mapping size falls between
		 * two host sizes, take the smallest of the two.
		 */
		if (max_map_size >= PMD_SIZE && max_map_size < PUD_SIZE)
			max_map_size = PMD_SIZE;
		else if (max_map_size >= PAGE_SIZE && max_map_size < PMD_SIZE)
			max_map_size = PAGE_SIZE;

		force_pte = (max_map_size == PAGE_SIZE);
		vma_pagesize = min(vma_pagesize, (long)max_map_size);
	}

	/*
	 * Both the canonical IPA and fault IPA must be hugepage-aligned to
	 * ensure we find the right PFN and lay down the mapping in the right
	 * place.
	 */
	if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) {
		fault_ipa &= ~(vma_pagesize - 1);
		ipa &= ~(vma_pagesize - 1);
	}

	gfn = ipa >> PAGE_SHIFT;
	mte_allowed = kvm_vma_mte_allowed(vma);

	vfio_allow_any_uc = vma->vm_flags & VM_ALLOW_ANY_UNCACHED;

	/* Don't use the VMA after the unlock -- it may have vanished */
	vma = NULL;

	/*
	 * Read mmu_invalidate_seq so that KVM can detect if the results of
	 * vma_lookup() or __gfn_to_pfn_memslot() become stale prior to
	 * acquiring kvm->mmu_lock.
	 *
	 * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs
	 * with the smp_wmb() in kvm_mmu_invalidate_end().
	 */
	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
	mmap_read_unlock(current->mm);

	pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
				   write_fault, &writable, NULL);
	if (pfn == KVM_PFN_ERR_HWPOISON) {
		kvm_send_hwpoison_signal(hva, vma_shift);
		return 0;
	}
	if (is_error_noslot_pfn(pfn))
		return -EFAULT;

	if (kvm_is_device_pfn(pfn)) {
		/*
		 * If the page was identified as device early by looking at
		 * the VMA flags, vma_pagesize is already representing the
		 * largest quantity we can map.  If instead it was mapped
		 * via gfn_to_pfn_prot(), vma_pagesize is set to PAGE_SIZE
		 * and must not be upgraded.
		 *
		 * In both cases, we don't let transparent_hugepage_adjust()
		 * change things at the last minute.
		 */
		device = true;
	} else if (logging_active && !write_fault) {
		/*
		 * Only actually map the page as writable if this was a write
		 * fault.
		 */
		writable = false;
	}

	if (exec_fault && device)
		return -ENOEXEC;

	/*
	 * Potentially reduce shadow S2 permissions to match the guest's own
	 * S2. For exec faults, we'd only reach this point if the guest
	 * actually allowed it (see kvm_s2_handle_perm_fault).
	 *
	 * Also encode the level of the original translation in the SW bits
	 * of the leaf entry as a proxy for the span of that translation.
	 * This will be retrieved on TLB invalidation from the guest and
	 * used to limit the invalidation scope if a TTL hint or a range
	 * isn't provided.
	 */
	if (nested) {
		writable &= kvm_s2_trans_writable(nested);
		if (!kvm_s2_trans_readable(nested))
			prot &= ~KVM_PGTABLE_PROT_R;

		prot |= kvm_encode_nested_level(nested);
	}

	read_lock(&kvm->mmu_lock);
	pgt = vcpu->arch.hw_mmu->pgt;
	if (mmu_invalidate_retry(kvm, mmu_seq)) {
		ret = -EAGAIN;
		goto out_unlock;
	}

	/*
	 * If we are not forced to use page mapping, check if we are
	 * backed by a THP and thus use block mapping if possible.
	 */
	if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) {
		if (fault_is_perm && fault_granule > PAGE_SIZE)
			vma_pagesize = fault_granule;
		else
			vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
								   hva, &pfn,
								   &fault_ipa);

		if (vma_pagesize < 0) {
			ret = vma_pagesize;
			goto out_unlock;
		}
	}

	if (!fault_is_perm && !device && kvm_has_mte(kvm)) {
		/* Check the VMM hasn't introduced a new disallowed VMA */
		if (mte_allowed) {
			sanitise_mte_tags(kvm, pfn, vma_pagesize);
		} else {
			ret = -EFAULT;
			goto out_unlock;
		}
	}

	if (writable)
		prot |= KVM_PGTABLE_PROT_W;

	if (exec_fault)
		prot |= KVM_PGTABLE_PROT_X;

	if (device) {
		if (vfio_allow_any_uc)
			prot |= KVM_PGTABLE_PROT_NORMAL_NC;
		else
			prot |= KVM_PGTABLE_PROT_DEVICE;
	} else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC) &&
		   (!nested || kvm_s2_trans_executable(nested))) {
		prot |= KVM_PGTABLE_PROT_X;
	}

	/*
	 * Under the premise of getting a FSC_PERM fault, we just need to relax
	 * permissions only if vma_pagesize equals fault_granule. Otherwise,
	 * kvm_pgtable_stage2_map() should be called to change block size.
	 */
	if (fault_is_perm && vma_pagesize == fault_granule) {
		/*
		 * Drop the SW bits in favour of those stored in the
		 * PTE, which will be preserved.
		 */
		prot &= ~KVM_NV_GUEST_MAP_SZ;
		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
	} else {
		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
					     __pfn_to_phys(pfn), prot,
					     memcache,
					     KVM_PGTABLE_WALK_HANDLE_FAULT |
					     KVM_PGTABLE_WALK_SHARED);
	}

out_unlock:
	read_unlock(&kvm->mmu_lock);

	/* Mark the page dirty only if the fault is handled successfully */
	if (writable && !ret) {
		kvm_set_pfn_dirty(pfn);
		mark_page_dirty_in_slot(kvm, memslot, gfn);
	}

	kvm_release_pfn_clean(pfn);
	return ret != -EAGAIN ? ret : 0;
}

/* Resolve the access fault by making the page young again. */
static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
{
	kvm_pte_t pte;
	struct kvm_s2_mmu *mmu;

	trace_kvm_access_fault(fault_ipa);

	read_lock(&vcpu->kvm->mmu_lock);
	mmu = vcpu->arch.hw_mmu;
	pte = kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa);
	read_unlock(&vcpu->kvm->mmu_lock);

	if (kvm_pte_valid(pte))
		kvm_set_pfn_accessed(kvm_pte_to_pfn(pte));
}

/**
 * kvm_handle_guest_abort - handles all 2nd stage aborts
 * @vcpu:	the VCPU pointer
 *
 * 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_s2_trans nested_trans, *nested = NULL;
	unsigned long esr;
	phys_addr_t fault_ipa; /* The address we faulted on */
	phys_addr_t ipa; /* Always the IPA in the L1 guest phys space */
	struct kvm_memory_slot *memslot;
	unsigned long hva;
	bool is_iabt, write_fault, writable;
	gfn_t gfn;
	int ret, idx;

	esr = kvm_vcpu_get_esr(vcpu);

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

	if (esr_fsc_is_translation_fault(esr)) {
		/* Beyond sanitised PARange (which is the IPA limit) */
		if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
			kvm_inject_size_fault(vcpu);
			return 1;
		}

		/* Falls between the IPA range and the PARange? */
		if (fault_ipa >= BIT_ULL(vcpu->arch.hw_mmu->pgt->ia_bits)) {
			fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0);

			if (is_iabt)
				kvm_inject_pabt(vcpu, fault_ipa);
			else
				kvm_inject_dabt(vcpu, fault_ipa);
			return 1;
		}
	}

	/* Synchronous External Abort? */
	if (kvm_vcpu_abt_issea(vcpu)) {
		/*
		 * For RAS the host kernel may handle this abort.
		 * There is no need to pass the error into the guest.
		 */
		if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
			kvm_inject_vabt(vcpu);

		return 1;
	}

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

	/* Check the stage-2 fault is trans. fault or write fault */
	if (!esr_fsc_is_translation_fault(esr) &&
	    !esr_fsc_is_permission_fault(esr) &&
	    !esr_fsc_is_access_flag_fault(esr)) {
		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_esr(vcpu));
		return -EFAULT;
	}

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

	/*
	 * We may have faulted on a shadow stage 2 page table if we are
	 * running a nested guest.  In this case, we have to resolve the L2
	 * IPA to the L1 IPA first, before knowing what kind of memory should
	 * back the L1 IPA.
	 *
	 * If the shadow stage 2 page table walk faults, then we simply inject
	 * this to the guest and carry on.
	 *
	 * If there are no shadow S2 PTs because S2 is disabled, there is
	 * nothing to walk and we treat it as a 1:1 before going through the
	 * canonical translation.
	 */
	if (kvm_is_nested_s2_mmu(vcpu->kvm,vcpu->arch.hw_mmu) &&
	    vcpu->arch.hw_mmu->nested_stage2_enabled) {
		u32 esr;

		ret = kvm_walk_nested_s2(vcpu, fault_ipa, &nested_trans);
		if (ret) {
			esr = kvm_s2_trans_esr(&nested_trans);
			kvm_inject_s2_fault(vcpu, esr);
			goto out_unlock;
		}

		ret = kvm_s2_handle_perm_fault(vcpu, &nested_trans);
		if (ret) {
			esr = kvm_s2_trans_esr(&nested_trans);
			kvm_inject_s2_fault(vcpu, esr);
			goto out_unlock;
		}

		ipa = kvm_s2_trans_output(&nested_trans);
		nested = &nested_trans;
	}

	gfn = 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)) {
		/*
		 * The guest has put either its instructions or its page-tables
		 * somewhere it shouldn't have. Userspace won't be able to do
		 * anything about this (there's no syndrome for a start), so
		 * re-inject the abort back into the guest.
		 */
		if (is_iabt) {
			ret = -ENOEXEC;
			goto out;
		}

		if (kvm_vcpu_abt_iss1tw(vcpu)) {
			kvm_inject_dabt(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_is_error_hva(hva) && kvm_vcpu_dabt_is_cm(vcpu)) {
			kvm_incr_pc(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.
		 */
		ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0);
		ret = io_mem_abort(vcpu, ipa);
		goto out_unlock;
	}

	/* Userspace should not be able to register out-of-bounds IPAs */
	VM_BUG_ON(ipa >= kvm_phys_size(vcpu->arch.hw_mmu));

	if (esr_fsc_is_access_flag_fault(esr)) {
		handle_access_fault(vcpu, fault_ipa);
		ret = 1;
		goto out_unlock;
	}

	ret = user_mem_abort(vcpu, fault_ipa, nested, memslot, hva,
			     esr_fsc_is_permission_fault(esr));
	if (ret == 0)
		ret = 1;
out:
	if (ret == -ENOEXEC) {
		kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
		ret = 1;
	}
out_unlock:
	srcu_read_unlock(&vcpu->kvm->srcu, idx);
	return ret;
}

bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
{
	if (!kvm->arch.mmu.pgt)
		return false;

	__unmap_stage2_range(&kvm->arch.mmu, range->start << PAGE_SHIFT,
			     (range->end - range->start) << PAGE_SHIFT,
			     range->may_block);

	kvm_nested_s2_unmap(kvm, range->may_block);
	return false;
}

bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	u64 size = (range->end - range->start) << PAGE_SHIFT;

	if (!kvm->arch.mmu.pgt)
		return false;

	return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
						   range->start << PAGE_SHIFT,
						   size, true);
	/*
	 * TODO: Handle nested_mmu structures here using the reverse mapping in
	 * a later version of patch series.
	 */
}

bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	u64 size = (range->end - range->start) << PAGE_SHIFT;

	if (!kvm->arch.mmu.pgt)
		return false;

	return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
						   range->start << PAGE_SHIFT,
						   size, false);
}

phys_addr_t kvm_mmu_get_httbr(void)
{
	return __pa(hyp_pgtable->pgd);
}

phys_addr_t kvm_get_idmap_vector(void)
{
	return hyp_idmap_vector;
}

static int kvm_map_idmap_text(void)
{
	unsigned long size = hyp_idmap_end - hyp_idmap_start;
	int err = __create_hyp_mappings(hyp_idmap_start, size, hyp_idmap_start,
					PAGE_HYP_EXEC);
	if (err)
		kvm_err("Failed to idmap %lx-%lx\n",
			hyp_idmap_start, hyp_idmap_end);

	return err;
}

static void *kvm_hyp_zalloc_page(void *arg)
{
	return (void *)get_zeroed_page(GFP_KERNEL);
}

static struct kvm_pgtable_mm_ops kvm_hyp_mm_ops = {
	.zalloc_page		= kvm_hyp_zalloc_page,
	.get_page		= kvm_host_get_page,
	.put_page		= kvm_host_put_page,
	.phys_to_virt		= kvm_host_va,
	.virt_to_phys		= kvm_host_pa,
};

int __init kvm_mmu_init(u32 *hyp_va_bits)
{
	int err;
	u32 idmap_bits;
	u32 kernel_bits;

	hyp_idmap_start = __pa_symbol(__hyp_idmap_text_start);
	hyp_idmap_start = ALIGN_DOWN(hyp_idmap_start, PAGE_SIZE);
	hyp_idmap_end = __pa_symbol(__hyp_idmap_text_end);
	hyp_idmap_end = ALIGN(hyp_idmap_end, PAGE_SIZE);
	hyp_idmap_vector = __pa_symbol(__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);

	/*
	 * The ID map is always configured for 48 bits of translation, which
	 * may be fewer than the number of VA bits used by the regular kernel
	 * stage 1, when VA_BITS=52.
	 *
	 * At EL2, there is only one TTBR register, and we can't switch between
	 * translation tables *and* update TCR_EL2.T0SZ at the same time. Bottom
	 * line: we need to use the extended range with *both* our translation
	 * tables.
	 *
	 * So use the maximum of the idmap VA bits and the regular kernel stage
	 * 1 VA bits to assure that the hypervisor can both ID map its code page
	 * and map any kernel memory.
	 */
	idmap_bits = IDMAP_VA_BITS;
	kernel_bits = vabits_actual;
	*hyp_va_bits = max(idmap_bits, kernel_bits);

	kvm_debug("Using %u-bit virtual addresses at EL2\n", *hyp_va_bits);
	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_pgtable = kzalloc(sizeof(*hyp_pgtable), GFP_KERNEL);
	if (!hyp_pgtable) {
		kvm_err("Hyp mode page-table not allocated\n");
		err = -ENOMEM;
		goto out;
	}

	err = kvm_pgtable_hyp_init(hyp_pgtable, *hyp_va_bits, &kvm_hyp_mm_ops);
	if (err)
		goto out_free_pgtable;

	err = kvm_map_idmap_text();
	if (err)
		goto out_destroy_pgtable;

	io_map_base = hyp_idmap_start;
	return 0;

out_destroy_pgtable:
	kvm_pgtable_hyp_destroy(hyp_pgtable);
out_free_pgtable:
	kfree(hyp_pgtable);
	hyp_pgtable = NULL;
out:
	return err;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *old,
				   const struct kvm_memory_slot *new,
				   enum kvm_mr_change change)
{
	bool log_dirty_pages = new && new->flags & KVM_MEM_LOG_DIRTY_PAGES;

	/*
	 * At this point memslot has been committed and there is an
	 * allocated dirty_bitmap[], dirty pages will be tracked while the
	 * memory slot is write protected.
	 */
	if (log_dirty_pages) {

		if (change == KVM_MR_DELETE)
			return;

		/*
		 * Huge and normal pages are write-protected and split
		 * on either of these two cases:
		 *
		 * 1. with initial-all-set: gradually with CLEAR ioctls,
		 */
		if (kvm_dirty_log_manual_protect_and_init_set(kvm))
			return;
		/*
		 * or
		 * 2. without initial-all-set: all in one shot when
		 *    enabling dirty logging.
		 */
		kvm_mmu_wp_memory_region(kvm, new->id);
		kvm_mmu_split_memory_region(kvm, new->id);
	} else {
		/*
		 * Free any leftovers from the eager page splitting cache. Do
		 * this when deleting, moving, disabling dirty logging, or
		 * creating the memslot (a nop). Doing it for deletes makes
		 * sure we don't leak memory, and there's no need to keep the
		 * cache around for any of the other cases.
		 */
		kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache);
	}
}

int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   const struct kvm_memory_slot *old,
				   struct kvm_memory_slot *new,
				   enum kvm_mr_change change)
{
	hva_t hva, reg_end;
	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 ((new->base_gfn + new->npages) > (kvm_phys_size(&kvm->arch.mmu) >> PAGE_SHIFT))
		return -EFAULT;

	hva = new->userspace_addr;
	reg_end = hva + (new->npages << PAGE_SHIFT);

	mmap_read_lock(current->mm);
	/*
	 * A memory region could potentially cover multiple VMAs, and any holes
	 * between them, so iterate over all of them.
	 *
	 *     +--------------------------------------------+
	 * +---------------+----------------+   +----------------+
	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
	 * +---------------+----------------+   +----------------+
	 *     |               memory region                |
	 *     +--------------------------------------------+
	 */
	do {
		struct vm_area_struct *vma;

		vma = find_vma_intersection(current->mm, hva, reg_end);
		if (!vma)
			break;

		if (kvm_has_mte(kvm) && !kvm_vma_mte_allowed(vma)) {
			ret = -EINVAL;
			break;
		}

		if (vma->vm_flags & VM_PFNMAP) {
			/* IO region dirty page logging not allowed */
			if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) {
				ret = -EINVAL;
				break;
			}
		}
		hva = min(reg_end, vma->vm_end);
	} while (hva < reg_end);

	mmap_read_unlock(current->mm);
	return ret;
}

void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
{
}

void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
{
}

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;

	write_lock(&kvm->mmu_lock);
	kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size, true);
	kvm_nested_s2_unmap(kvm, true);
	write_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);
}