summaryrefslogtreecommitdiff
path: root/arch/arm64/kvm/hyp/pgtable.c
blob: a40dafc43bb642abde9d55f5009165d4417229da (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Stand-alone page-table allocator for hyp stage-1 and guest stage-2.
 * No bombay mix was harmed in the writing of this file.
 *
 * Copyright (C) 2020 Google LLC
 * Author: Will Deacon <will@kernel.org>
 */

#include <linux/bitfield.h>
#include <asm/kvm_pgtable.h>
#include <asm/stage2_pgtable.h>


#define KVM_PTE_TYPE			BIT(1)
#define KVM_PTE_TYPE_BLOCK		0
#define KVM_PTE_TYPE_PAGE		1
#define KVM_PTE_TYPE_TABLE		1

#define KVM_PTE_LEAF_ATTR_LO		GENMASK(11, 2)

#define KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX	GENMASK(4, 2)
#define KVM_PTE_LEAF_ATTR_LO_S1_AP	GENMASK(7, 6)
#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RO		\
	({ cpus_have_final_cap(ARM64_KVM_HVHE) ? 2 : 3; })
#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RW		\
	({ cpus_have_final_cap(ARM64_KVM_HVHE) ? 0 : 1; })
#define KVM_PTE_LEAF_ATTR_LO_S1_SH	GENMASK(9, 8)
#define KVM_PTE_LEAF_ATTR_LO_S1_SH_IS	3
#define KVM_PTE_LEAF_ATTR_LO_S1_AF	BIT(10)

#define KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR	GENMASK(5, 2)
#define KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R	BIT(6)
#define KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W	BIT(7)
#define KVM_PTE_LEAF_ATTR_LO_S2_SH	GENMASK(9, 8)
#define KVM_PTE_LEAF_ATTR_LO_S2_SH_IS	3
#define KVM_PTE_LEAF_ATTR_LO_S2_AF	BIT(10)

#define KVM_PTE_LEAF_ATTR_HI		GENMASK(63, 50)

#define KVM_PTE_LEAF_ATTR_HI_SW		GENMASK(58, 55)

#define KVM_PTE_LEAF_ATTR_HI_S1_XN	BIT(54)

#define KVM_PTE_LEAF_ATTR_HI_S2_XN	BIT(54)

#define KVM_PTE_LEAF_ATTR_HI_S1_GP	BIT(50)

#define KVM_PTE_LEAF_ATTR_S2_PERMS	(KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R | \
					 KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | \
					 KVM_PTE_LEAF_ATTR_HI_S2_XN)

#define KVM_INVALID_PTE_OWNER_MASK	GENMASK(9, 2)
#define KVM_MAX_OWNER_ID		1

/*
 * Used to indicate a pte for which a 'break-before-make' sequence is in
 * progress.
 */
#define KVM_INVALID_PTE_LOCKED		BIT(10)

struct kvm_pgtable_walk_data {
	struct kvm_pgtable_walker	*walker;

	const u64			start;
	u64				addr;
	const u64			end;
};

static bool kvm_pgtable_walk_skip_bbm_tlbi(const struct kvm_pgtable_visit_ctx *ctx)
{
	return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_BBM_TLBI);
}

static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx)
{
	return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_CMO);
}

static bool kvm_phys_is_valid(u64 phys)
{
	u64 parange_max = kvm_get_parange_max();
	u8 shift = id_aa64mmfr0_parange_to_phys_shift(parange_max);

	return phys < BIT(shift);
}

static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, u64 phys)
{
	u64 granule = kvm_granule_size(ctx->level);

	if (!kvm_level_supports_block_mapping(ctx->level))
		return false;

	if (granule > (ctx->end - ctx->addr))
		return false;

	if (kvm_phys_is_valid(phys) && !IS_ALIGNED(phys, granule))
		return false;

	return IS_ALIGNED(ctx->addr, granule);
}

static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, s8 level)
{
	u64 shift = kvm_granule_shift(level);
	u64 mask = BIT(PAGE_SHIFT - 3) - 1;

	return (data->addr >> shift) & mask;
}

static u32 kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr)
{
	u64 shift = kvm_granule_shift(pgt->start_level - 1); /* May underflow */
	u64 mask = BIT(pgt->ia_bits) - 1;

	return (addr & mask) >> shift;
}

static u32 kvm_pgd_pages(u32 ia_bits, s8 start_level)
{
	struct kvm_pgtable pgt = {
		.ia_bits	= ia_bits,
		.start_level	= start_level,
	};

	return kvm_pgd_page_idx(&pgt, -1ULL) + 1;
}

static bool kvm_pte_table(kvm_pte_t pte, s8 level)
{
	if (level == KVM_PGTABLE_LAST_LEVEL)
		return false;

	if (!kvm_pte_valid(pte))
		return false;

	return FIELD_GET(KVM_PTE_TYPE, pte) == KVM_PTE_TYPE_TABLE;
}

static kvm_pte_t *kvm_pte_follow(kvm_pte_t pte, struct kvm_pgtable_mm_ops *mm_ops)
{
	return mm_ops->phys_to_virt(kvm_pte_to_phys(pte));
}

static void kvm_clear_pte(kvm_pte_t *ptep)
{
	WRITE_ONCE(*ptep, 0);
}

static kvm_pte_t kvm_init_table_pte(kvm_pte_t *childp, struct kvm_pgtable_mm_ops *mm_ops)
{
	kvm_pte_t pte = kvm_phys_to_pte(mm_ops->virt_to_phys(childp));

	pte |= FIELD_PREP(KVM_PTE_TYPE, KVM_PTE_TYPE_TABLE);
	pte |= KVM_PTE_VALID;
	return pte;
}

static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, s8 level)
{
	kvm_pte_t pte = kvm_phys_to_pte(pa);
	u64 type = (level == KVM_PGTABLE_LAST_LEVEL) ? KVM_PTE_TYPE_PAGE :
						       KVM_PTE_TYPE_BLOCK;

	pte |= attr & (KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI);
	pte |= FIELD_PREP(KVM_PTE_TYPE, type);
	pte |= KVM_PTE_VALID;

	return pte;
}

static kvm_pte_t kvm_init_invalid_leaf_owner(u8 owner_id)
{
	return FIELD_PREP(KVM_INVALID_PTE_OWNER_MASK, owner_id);
}

static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data,
				  const struct kvm_pgtable_visit_ctx *ctx,
				  enum kvm_pgtable_walk_flags visit)
{
	struct kvm_pgtable_walker *walker = data->walker;

	/* Ensure the appropriate lock is held (e.g. RCU lock for stage-2 MMU) */
	WARN_ON_ONCE(kvm_pgtable_walk_shared(ctx) && !kvm_pgtable_walk_lock_held());
	return walker->cb(ctx, visit);
}

static bool kvm_pgtable_walk_continue(const struct kvm_pgtable_walker *walker,
				      int r)
{
	/*
	 * Visitor callbacks return EAGAIN when the conditions that led to a
	 * fault are no longer reflected in the page tables due to a race to
	 * update a PTE. In the context of a fault handler this is interpreted
	 * as a signal to retry guest execution.
	 *
	 * Ignore the return code altogether for walkers outside a fault handler
	 * (e.g. write protecting a range of memory) and chug along with the
	 * page table walk.
	 */
	if (r == -EAGAIN)
		return !(walker->flags & KVM_PGTABLE_WALK_HANDLE_FAULT);

	return !r;
}

static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level);

static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
				      struct kvm_pgtable_mm_ops *mm_ops,
				      kvm_pteref_t pteref, s8 level)
{
	enum kvm_pgtable_walk_flags flags = data->walker->flags;
	kvm_pte_t *ptep = kvm_dereference_pteref(data->walker, pteref);
	struct kvm_pgtable_visit_ctx ctx = {
		.ptep	= ptep,
		.old	= READ_ONCE(*ptep),
		.arg	= data->walker->arg,
		.mm_ops	= mm_ops,
		.start	= data->start,
		.addr	= data->addr,
		.end	= data->end,
		.level	= level,
		.flags	= flags,
	};
	int ret = 0;
	bool reload = false;
	kvm_pteref_t childp;
	bool table = kvm_pte_table(ctx.old, level);

	if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE)) {
		ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_PRE);
		reload = true;
	}

	if (!table && (ctx.flags & KVM_PGTABLE_WALK_LEAF)) {
		ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_LEAF);
		reload = true;
	}

	/*
	 * Reload the page table after invoking the walker callback for leaf
	 * entries or after pre-order traversal, to allow the walker to descend
	 * into a newly installed or replaced table.
	 */
	if (reload) {
		ctx.old = READ_ONCE(*ptep);
		table = kvm_pte_table(ctx.old, level);
	}

	if (!kvm_pgtable_walk_continue(data->walker, ret))
		goto out;

	if (!table) {
		data->addr = ALIGN_DOWN(data->addr, kvm_granule_size(level));
		data->addr += kvm_granule_size(level);
		goto out;
	}

	childp = (kvm_pteref_t)kvm_pte_follow(ctx.old, mm_ops);
	ret = __kvm_pgtable_walk(data, mm_ops, childp, level + 1);
	if (!kvm_pgtable_walk_continue(data->walker, ret))
		goto out;

	if (ctx.flags & KVM_PGTABLE_WALK_TABLE_POST)
		ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_POST);

out:
	if (kvm_pgtable_walk_continue(data->walker, ret))
		return 0;

	return ret;
}

static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level)
{
	u32 idx;
	int ret = 0;

	if (WARN_ON_ONCE(level < KVM_PGTABLE_FIRST_LEVEL ||
			 level > KVM_PGTABLE_LAST_LEVEL))
		return -EINVAL;

	for (idx = kvm_pgtable_idx(data, level); idx < PTRS_PER_PTE; ++idx) {
		kvm_pteref_t pteref = &pgtable[idx];

		if (data->addr >= data->end)
			break;

		ret = __kvm_pgtable_visit(data, mm_ops, pteref, level);
		if (ret)
			break;
	}

	return ret;
}

static int _kvm_pgtable_walk(struct kvm_pgtable *pgt, struct kvm_pgtable_walk_data *data)
{
	u32 idx;
	int ret = 0;
	u64 limit = BIT(pgt->ia_bits);

	if (data->addr > limit || data->end > limit)
		return -ERANGE;

	if (!pgt->pgd)
		return -EINVAL;

	for (idx = kvm_pgd_page_idx(pgt, data->addr); data->addr < data->end; ++idx) {
		kvm_pteref_t pteref = &pgt->pgd[idx * PTRS_PER_PTE];

		ret = __kvm_pgtable_walk(data, pgt->mm_ops, pteref, pgt->start_level);
		if (ret)
			break;
	}

	return ret;
}

int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
		     struct kvm_pgtable_walker *walker)
{
	struct kvm_pgtable_walk_data walk_data = {
		.start	= ALIGN_DOWN(addr, PAGE_SIZE),
		.addr	= ALIGN_DOWN(addr, PAGE_SIZE),
		.end	= PAGE_ALIGN(walk_data.addr + size),
		.walker	= walker,
	};
	int r;

	r = kvm_pgtable_walk_begin(walker);
	if (r)
		return r;

	r = _kvm_pgtable_walk(pgt, &walk_data);
	kvm_pgtable_walk_end(walker);

	return r;
}

struct leaf_walk_data {
	kvm_pte_t	pte;
	s8		level;
};

static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx,
		       enum kvm_pgtable_walk_flags visit)
{
	struct leaf_walk_data *data = ctx->arg;

	data->pte   = ctx->old;
	data->level = ctx->level;

	return 0;
}

int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
			 kvm_pte_t *ptep, s8 *level)
{
	struct leaf_walk_data data;
	struct kvm_pgtable_walker walker = {
		.cb	= leaf_walker,
		.flags	= KVM_PGTABLE_WALK_LEAF,
		.arg	= &data,
	};
	int ret;

	ret = kvm_pgtable_walk(pgt, ALIGN_DOWN(addr, PAGE_SIZE),
			       PAGE_SIZE, &walker);
	if (!ret) {
		if (ptep)
			*ptep  = data.pte;
		if (level)
			*level = data.level;
	}

	return ret;
}

struct hyp_map_data {
	const u64			phys;
	kvm_pte_t			attr;
};

static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep)
{
	bool device = prot & KVM_PGTABLE_PROT_DEVICE;
	u32 mtype = device ? MT_DEVICE_nGnRE : MT_NORMAL;
	kvm_pte_t attr = FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX, mtype);
	u32 sh = KVM_PTE_LEAF_ATTR_LO_S1_SH_IS;
	u32 ap = (prot & KVM_PGTABLE_PROT_W) ? KVM_PTE_LEAF_ATTR_LO_S1_AP_RW :
					       KVM_PTE_LEAF_ATTR_LO_S1_AP_RO;

	if (!(prot & KVM_PGTABLE_PROT_R))
		return -EINVAL;

	if (prot & KVM_PGTABLE_PROT_X) {
		if (prot & KVM_PGTABLE_PROT_W)
			return -EINVAL;

		if (device)
			return -EINVAL;

		if (system_supports_bti_kernel())
			attr |= KVM_PTE_LEAF_ATTR_HI_S1_GP;
	} else {
		attr |= KVM_PTE_LEAF_ATTR_HI_S1_XN;
	}

	attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_AP, ap);
	if (!kvm_lpa2_is_enabled())
		attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh);
	attr |= KVM_PTE_LEAF_ATTR_LO_S1_AF;
	attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW;
	*ptep = attr;

	return 0;
}

enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte)
{
	enum kvm_pgtable_prot prot = pte & KVM_PTE_LEAF_ATTR_HI_SW;
	u32 ap;

	if (!kvm_pte_valid(pte))
		return prot;

	if (!(pte & KVM_PTE_LEAF_ATTR_HI_S1_XN))
		prot |= KVM_PGTABLE_PROT_X;

	ap = FIELD_GET(KVM_PTE_LEAF_ATTR_LO_S1_AP, pte);
	if (ap == KVM_PTE_LEAF_ATTR_LO_S1_AP_RO)
		prot |= KVM_PGTABLE_PROT_R;
	else if (ap == KVM_PTE_LEAF_ATTR_LO_S1_AP_RW)
		prot |= KVM_PGTABLE_PROT_RW;

	return prot;
}

static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx,
				    struct hyp_map_data *data)
{
	u64 phys = data->phys + (ctx->addr - ctx->start);
	kvm_pte_t new;

	if (!kvm_block_mapping_supported(ctx, phys))
		return false;

	new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level);
	if (ctx->old == new)
		return true;
	if (!kvm_pte_valid(ctx->old))
		ctx->mm_ops->get_page(ctx->ptep);
	else if (WARN_ON((ctx->old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW))
		return false;

	smp_store_release(ctx->ptep, new);
	return true;
}

static int hyp_map_walker(const struct kvm_pgtable_visit_ctx *ctx,
			  enum kvm_pgtable_walk_flags visit)
{
	kvm_pte_t *childp, new;
	struct hyp_map_data *data = ctx->arg;
	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;

	if (hyp_map_walker_try_leaf(ctx, data))
		return 0;

	if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL))
		return -EINVAL;

	childp = (kvm_pte_t *)mm_ops->zalloc_page(NULL);
	if (!childp)
		return -ENOMEM;

	new = kvm_init_table_pte(childp, mm_ops);
	mm_ops->get_page(ctx->ptep);
	smp_store_release(ctx->ptep, new);

	return 0;
}

int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
			enum kvm_pgtable_prot prot)
{
	int ret;
	struct hyp_map_data map_data = {
		.phys	= ALIGN_DOWN(phys, PAGE_SIZE),
	};
	struct kvm_pgtable_walker walker = {
		.cb	= hyp_map_walker,
		.flags	= KVM_PGTABLE_WALK_LEAF,
		.arg	= &map_data,
	};

	ret = hyp_set_prot_attr(prot, &map_data.attr);
	if (ret)
		return ret;

	ret = kvm_pgtable_walk(pgt, addr, size, &walker);
	dsb(ishst);
	isb();
	return ret;
}

static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
			    enum kvm_pgtable_walk_flags visit)
{
	kvm_pte_t *childp = NULL;
	u64 granule = kvm_granule_size(ctx->level);
	u64 *unmapped = ctx->arg;
	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;

	if (!kvm_pte_valid(ctx->old))
		return -EINVAL;

	if (kvm_pte_table(ctx->old, ctx->level)) {
		childp = kvm_pte_follow(ctx->old, mm_ops);

		if (mm_ops->page_count(childp) != 1)
			return 0;

		kvm_clear_pte(ctx->ptep);
		dsb(ishst);
		__tlbi_level(vae2is, __TLBI_VADDR(ctx->addr, 0), TLBI_TTL_UNKNOWN);
	} else {
		if (ctx->end - ctx->addr < granule)
			return -EINVAL;

		kvm_clear_pte(ctx->ptep);
		dsb(ishst);
		__tlbi_level(vale2is, __TLBI_VADDR(ctx->addr, 0), ctx->level);
		*unmapped += granule;
	}

	dsb(ish);
	isb();
	mm_ops->put_page(ctx->ptep);

	if (childp)
		mm_ops->put_page(childp);

	return 0;
}

u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
{
	u64 unmapped = 0;
	struct kvm_pgtable_walker walker = {
		.cb	= hyp_unmap_walker,
		.arg	= &unmapped,
		.flags	= KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST,
	};

	if (!pgt->mm_ops->page_count)
		return 0;

	kvm_pgtable_walk(pgt, addr, size, &walker);
	return unmapped;
}

int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits,
			 struct kvm_pgtable_mm_ops *mm_ops)
{
	s8 start_level = KVM_PGTABLE_LAST_LEVEL + 1 -
			 ARM64_HW_PGTABLE_LEVELS(va_bits);

	if (start_level < KVM_PGTABLE_FIRST_LEVEL ||
	    start_level > KVM_PGTABLE_LAST_LEVEL)
		return -EINVAL;

	pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_page(NULL);
	if (!pgt->pgd)
		return -ENOMEM;

	pgt->ia_bits		= va_bits;
	pgt->start_level	= start_level;
	pgt->mm_ops		= mm_ops;
	pgt->mmu		= NULL;
	pgt->force_pte_cb	= NULL;

	return 0;
}

static int hyp_free_walker(const struct kvm_pgtable_visit_ctx *ctx,
			   enum kvm_pgtable_walk_flags visit)
{
	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;

	if (!kvm_pte_valid(ctx->old))
		return 0;

	mm_ops->put_page(ctx->ptep);

	if (kvm_pte_table(ctx->old, ctx->level))
		mm_ops->put_page(kvm_pte_follow(ctx->old, mm_ops));

	return 0;
}

void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt)
{
	struct kvm_pgtable_walker walker = {
		.cb	= hyp_free_walker,
		.flags	= KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST,
	};

	WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker));
	pgt->mm_ops->put_page(kvm_dereference_pteref(&walker, pgt->pgd));
	pgt->pgd = NULL;
}

struct stage2_map_data {
	const u64			phys;
	kvm_pte_t			attr;
	u8				owner_id;

	kvm_pte_t			*anchor;
	kvm_pte_t			*childp;

	struct kvm_s2_mmu		*mmu;
	void				*memcache;

	/* Force mappings to page granularity */
	bool				force_pte;
};

u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
{
	u64 vtcr = VTCR_EL2_FLAGS;
	s8 lvls;

	vtcr |= kvm_get_parange(mmfr0) << VTCR_EL2_PS_SHIFT;
	vtcr |= VTCR_EL2_T0SZ(phys_shift);
	/*
	 * Use a minimum 2 level page table to prevent splitting
	 * host PMD huge pages at stage2.
	 */
	lvls = stage2_pgtable_levels(phys_shift);
	if (lvls < 2)
		lvls = 2;

	/*
	 * When LPA2 is enabled, the HW supports an extra level of translation
	 * (for 5 in total) when using 4K pages. It also introduces VTCR_EL2.SL2
	 * to as an addition to SL0 to enable encoding this extra start level.
	 * However, since we always use concatenated pages for the first level
	 * lookup, we will never need this extra level and therefore do not need
	 * to touch SL2.
	 */
	vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls);

#ifdef CONFIG_ARM64_HW_AFDBM
	/*
	 * Enable the Hardware Access Flag management, unconditionally
	 * on all CPUs. In systems that have asymmetric support for the feature
	 * this allows KVM to leverage hardware support on the subset of cores
	 * that implement the feature.
	 *
	 * The architecture requires VTCR_EL2.HA to be RES0 (thus ignored by
	 * hardware) on implementations that do not advertise support for the
	 * feature. As such, setting HA unconditionally is safe, unless you
	 * happen to be running on a design that has unadvertised support for
	 * HAFDBS. Here be dragons.
	 */
	if (!cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38))
		vtcr |= VTCR_EL2_HA;
#endif /* CONFIG_ARM64_HW_AFDBM */

	if (kvm_lpa2_is_enabled())
		vtcr |= VTCR_EL2_DS;

	/* Set the vmid bits */
	vtcr |= (get_vmid_bits(mmfr1) == 16) ?
		VTCR_EL2_VS_16BIT :
		VTCR_EL2_VS_8BIT;

	return vtcr;
}

static bool stage2_has_fwb(struct kvm_pgtable *pgt)
{
	if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
		return false;

	return !(pgt->flags & KVM_PGTABLE_S2_NOFWB);
}

void kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
				phys_addr_t addr, size_t size)
{
	unsigned long pages, inval_pages;

	if (!system_supports_tlb_range()) {
		kvm_call_hyp(__kvm_tlb_flush_vmid, mmu);
		return;
	}

	pages = size >> PAGE_SHIFT;
	while (pages > 0) {
		inval_pages = min(pages, MAX_TLBI_RANGE_PAGES);
		kvm_call_hyp(__kvm_tlb_flush_vmid_range, mmu, addr, inval_pages);

		addr += inval_pages << PAGE_SHIFT;
		pages -= inval_pages;
	}
}

#define KVM_S2_MEMATTR(pgt, attr) PAGE_S2_MEMATTR(attr, stage2_has_fwb(pgt))

static int stage2_set_prot_attr(struct kvm_pgtable *pgt, enum kvm_pgtable_prot prot,
				kvm_pte_t *ptep)
{
	kvm_pte_t attr;
	u32 sh = KVM_PTE_LEAF_ATTR_LO_S2_SH_IS;

	switch (prot & (KVM_PGTABLE_PROT_DEVICE |
			KVM_PGTABLE_PROT_NORMAL_NC)) {
	case KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_NORMAL_NC:
		return -EINVAL;
	case KVM_PGTABLE_PROT_DEVICE:
		if (prot & KVM_PGTABLE_PROT_X)
			return -EINVAL;
		attr = KVM_S2_MEMATTR(pgt, DEVICE_nGnRE);
		break;
	case KVM_PGTABLE_PROT_NORMAL_NC:
		if (prot & KVM_PGTABLE_PROT_X)
			return -EINVAL;
		attr = KVM_S2_MEMATTR(pgt, NORMAL_NC);
		break;
	default:
		attr = KVM_S2_MEMATTR(pgt, NORMAL);
	}

	if (!(prot & KVM_PGTABLE_PROT_X))
		attr |= KVM_PTE_LEAF_ATTR_HI_S2_XN;

	if (prot & KVM_PGTABLE_PROT_R)
		attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R;

	if (prot & KVM_PGTABLE_PROT_W)
		attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W;

	if (!kvm_lpa2_is_enabled())
		attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh);

	attr |= KVM_PTE_LEAF_ATTR_LO_S2_AF;
	attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW;
	*ptep = attr;

	return 0;
}

enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte)
{
	enum kvm_pgtable_prot prot = pte & KVM_PTE_LEAF_ATTR_HI_SW;

	if (!kvm_pte_valid(pte))
		return prot;

	if (pte & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R)
		prot |= KVM_PGTABLE_PROT_R;
	if (pte & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W)
		prot |= KVM_PGTABLE_PROT_W;
	if (!(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN))
		prot |= KVM_PGTABLE_PROT_X;

	return prot;
}

static bool stage2_pte_needs_update(kvm_pte_t old, kvm_pte_t new)
{
	if (!kvm_pte_valid(old) || !kvm_pte_valid(new))
		return true;

	return ((old ^ new) & (~KVM_PTE_LEAF_ATTR_S2_PERMS));
}

static bool stage2_pte_is_counted(kvm_pte_t pte)
{
	/*
	 * The refcount tracks valid entries as well as invalid entries if they
	 * encode ownership of a page to another entity than the page-table
	 * owner, whose id is 0.
	 */
	return !!pte;
}

static bool stage2_pte_is_locked(kvm_pte_t pte)
{
	return !kvm_pte_valid(pte) && (pte & KVM_INVALID_PTE_LOCKED);
}

static bool stage2_try_set_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new)
{
	if (!kvm_pgtable_walk_shared(ctx)) {
		WRITE_ONCE(*ctx->ptep, new);
		return true;
	}

	return cmpxchg(ctx->ptep, ctx->old, new) == ctx->old;
}

/**
 * stage2_try_break_pte() - Invalidates a pte according to the
 *			    'break-before-make' requirements of the
 *			    architecture.
 *
 * @ctx: context of the visited pte.
 * @mmu: stage-2 mmu
 *
 * Returns: true if the pte was successfully broken.
 *
 * If the removed pte was valid, performs the necessary serialization and TLB
 * invalidation for the old value. For counted ptes, drops the reference count
 * on the containing table page.
 */
static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx,
				 struct kvm_s2_mmu *mmu)
{
	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;

	if (stage2_pte_is_locked(ctx->old)) {
		/*
		 * Should never occur if this walker has exclusive access to the
		 * page tables.
		 */
		WARN_ON(!kvm_pgtable_walk_shared(ctx));
		return false;
	}

	if (!stage2_try_set_pte(ctx, KVM_INVALID_PTE_LOCKED))
		return false;

	if (!kvm_pgtable_walk_skip_bbm_tlbi(ctx)) {
		/*
		 * Perform the appropriate TLB invalidation based on the
		 * evicted pte value (if any).
		 */
		if (kvm_pte_table(ctx->old, ctx->level))
			kvm_tlb_flush_vmid_range(mmu, ctx->addr,
						kvm_granule_size(ctx->level));
		else if (kvm_pte_valid(ctx->old))
			kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
				     ctx->addr, ctx->level);
	}

	if (stage2_pte_is_counted(ctx->old))
		mm_ops->put_page(ctx->ptep);

	return true;
}

static void stage2_make_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new)
{
	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;

	WARN_ON(!stage2_pte_is_locked(*ctx->ptep));

	if (stage2_pte_is_counted(new))
		mm_ops->get_page(ctx->ptep);

	smp_store_release(ctx->ptep, new);
}

static bool stage2_unmap_defer_tlb_flush(struct kvm_pgtable *pgt)
{
	/*
	 * If FEAT_TLBIRANGE is implemented, defer the individual
	 * TLB invalidations until the entire walk is finished, and
	 * then use the range-based TLBI instructions to do the
	 * invalidations. Condition deferred TLB invalidation on the
	 * system supporting FWB as the optimization is entirely
	 * pointless when the unmap walker needs to perform CMOs.
	 */
	return system_supports_tlb_range() && stage2_has_fwb(pgt);
}

static void stage2_unmap_put_pte(const struct kvm_pgtable_visit_ctx *ctx,
				struct kvm_s2_mmu *mmu,
				struct kvm_pgtable_mm_ops *mm_ops)
{
	struct kvm_pgtable *pgt = ctx->arg;

	/*
	 * Clear the existing PTE, and perform break-before-make if it was
	 * valid. Depending on the system support, defer the TLB maintenance
	 * for the same until the entire unmap walk is completed.
	 */
	if (kvm_pte_valid(ctx->old)) {
		kvm_clear_pte(ctx->ptep);

		if (kvm_pte_table(ctx->old, ctx->level)) {
			kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr,
				     TLBI_TTL_UNKNOWN);
		} else if (!stage2_unmap_defer_tlb_flush(pgt)) {
			kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr,
				     ctx->level);
		}
	}

	mm_ops->put_page(ctx->ptep);
}

static bool stage2_pte_cacheable(struct kvm_pgtable *pgt, kvm_pte_t pte)
{
	u64 memattr = pte & KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR;
	return memattr == KVM_S2_MEMATTR(pgt, NORMAL);
}

static bool stage2_pte_executable(kvm_pte_t pte)
{
	return !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN);
}

static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx,
				       const struct stage2_map_data *data)
{
	u64 phys = data->phys;

	/*
	 * Stage-2 walks to update ownership data are communicated to the map
	 * walker using an invalid PA. Avoid offsetting an already invalid PA,
	 * which could overflow and make the address valid again.
	 */
	if (!kvm_phys_is_valid(phys))
		return phys;

	/*
	 * Otherwise, work out the correct PA based on how far the walk has
	 * gotten.
	 */
	return phys + (ctx->addr - ctx->start);
}

static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx,
					struct stage2_map_data *data)
{
	u64 phys = stage2_map_walker_phys_addr(ctx, data);

	if (data->force_pte && ctx->level < KVM_PGTABLE_LAST_LEVEL)
		return false;

	return kvm_block_mapping_supported(ctx, phys);
}

static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx,
				      struct stage2_map_data *data)
{
	kvm_pte_t new;
	u64 phys = stage2_map_walker_phys_addr(ctx, data);
	u64 granule = kvm_granule_size(ctx->level);
	struct kvm_pgtable *pgt = data->mmu->pgt;
	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;

	if (!stage2_leaf_mapping_allowed(ctx, data))
		return -E2BIG;

	if (kvm_phys_is_valid(phys))
		new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level);
	else
		new = kvm_init_invalid_leaf_owner(data->owner_id);

	/*
	 * Skip updating the PTE if we are trying to recreate the exact
	 * same mapping or only change the access permissions. Instead,
	 * the vCPU will exit one more time from guest if still needed
	 * and then go through the path of relaxing permissions.
	 */
	if (!stage2_pte_needs_update(ctx->old, new))
		return -EAGAIN;

	if (!stage2_try_break_pte(ctx, data->mmu))
		return -EAGAIN;

	/* Perform CMOs before installation of the guest stage-2 PTE */
	if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->dcache_clean_inval_poc &&
	    stage2_pte_cacheable(pgt, new))
		mm_ops->dcache_clean_inval_poc(kvm_pte_follow(new, mm_ops),
					       granule);

	if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->icache_inval_pou &&
	    stage2_pte_executable(new))
		mm_ops->icache_inval_pou(kvm_pte_follow(new, mm_ops), granule);

	stage2_make_pte(ctx, new);

	return 0;
}

static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx,
				     struct stage2_map_data *data)
{
	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
	kvm_pte_t *childp = kvm_pte_follow(ctx->old, mm_ops);
	int ret;

	if (!stage2_leaf_mapping_allowed(ctx, data))
		return 0;

	ret = stage2_map_walker_try_leaf(ctx, data);
	if (ret)
		return ret;

	mm_ops->free_unlinked_table(childp, ctx->level);
	return 0;
}

static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx,
				struct stage2_map_data *data)
{
	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
	kvm_pte_t *childp, new;
	int ret;

	ret = stage2_map_walker_try_leaf(ctx, data);
	if (ret != -E2BIG)
		return ret;

	if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL))
		return -EINVAL;

	if (!data->memcache)
		return -ENOMEM;

	childp = mm_ops->zalloc_page(data->memcache);
	if (!childp)
		return -ENOMEM;

	if (!stage2_try_break_pte(ctx, data->mmu)) {
		mm_ops->put_page(childp);
		return -EAGAIN;
	}

	/*
	 * If we've run into an existing block mapping then replace it with
	 * a table. Accesses beyond 'end' that fall within the new table
	 * will be mapped lazily.
	 */
	new = kvm_init_table_pte(childp, mm_ops);
	stage2_make_pte(ctx, new);

	return 0;
}

/*
 * The TABLE_PRE callback runs for table entries on the way down, looking
 * for table entries which we could conceivably replace with a block entry
 * for this mapping. If it finds one it replaces the entry and calls
 * kvm_pgtable_mm_ops::free_unlinked_table() to tear down the detached table.
 *
 * Otherwise, the LEAF callback performs the mapping at the existing leaves
 * instead.
 */
static int stage2_map_walker(const struct kvm_pgtable_visit_ctx *ctx,
			     enum kvm_pgtable_walk_flags visit)
{
	struct stage2_map_data *data = ctx->arg;

	switch (visit) {
	case KVM_PGTABLE_WALK_TABLE_PRE:
		return stage2_map_walk_table_pre(ctx, data);
	case KVM_PGTABLE_WALK_LEAF:
		return stage2_map_walk_leaf(ctx, data);
	default:
		return -EINVAL;
	}
}

int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
			   u64 phys, enum kvm_pgtable_prot prot,
			   void *mc, enum kvm_pgtable_walk_flags flags)
{
	int ret;
	struct stage2_map_data map_data = {
		.phys		= ALIGN_DOWN(phys, PAGE_SIZE),
		.mmu		= pgt->mmu,
		.memcache	= mc,
		.force_pte	= pgt->force_pte_cb && pgt->force_pte_cb(addr, addr + size, prot),
	};
	struct kvm_pgtable_walker walker = {
		.cb		= stage2_map_walker,
		.flags		= flags |
				  KVM_PGTABLE_WALK_TABLE_PRE |
				  KVM_PGTABLE_WALK_LEAF,
		.arg		= &map_data,
	};

	if (WARN_ON((pgt->flags & KVM_PGTABLE_S2_IDMAP) && (addr != phys)))
		return -EINVAL;

	ret = stage2_set_prot_attr(pgt, prot, &map_data.attr);
	if (ret)
		return ret;

	ret = kvm_pgtable_walk(pgt, addr, size, &walker);
	dsb(ishst);
	return ret;
}

int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
				 void *mc, u8 owner_id)
{
	int ret;
	struct stage2_map_data map_data = {
		.phys		= KVM_PHYS_INVALID,
		.mmu		= pgt->mmu,
		.memcache	= mc,
		.owner_id	= owner_id,
		.force_pte	= true,
	};
	struct kvm_pgtable_walker walker = {
		.cb		= stage2_map_walker,
		.flags		= KVM_PGTABLE_WALK_TABLE_PRE |
				  KVM_PGTABLE_WALK_LEAF,
		.arg		= &map_data,
	};

	if (owner_id > KVM_MAX_OWNER_ID)
		return -EINVAL;

	ret = kvm_pgtable_walk(pgt, addr, size, &walker);
	return ret;
}

static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
			       enum kvm_pgtable_walk_flags visit)
{
	struct kvm_pgtable *pgt = ctx->arg;
	struct kvm_s2_mmu *mmu = pgt->mmu;
	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
	kvm_pte_t *childp = NULL;
	bool need_flush = false;

	if (!kvm_pte_valid(ctx->old)) {
		if (stage2_pte_is_counted(ctx->old)) {
			kvm_clear_pte(ctx->ptep);
			mm_ops->put_page(ctx->ptep);
		}
		return 0;
	}

	if (kvm_pte_table(ctx->old, ctx->level)) {
		childp = kvm_pte_follow(ctx->old, mm_ops);

		if (mm_ops->page_count(childp) != 1)
			return 0;
	} else if (stage2_pte_cacheable(pgt, ctx->old)) {
		need_flush = !stage2_has_fwb(pgt);
	}

	/*
	 * This is similar to the map() path in that we unmap the entire
	 * block entry and rely on the remaining portions being faulted
	 * back lazily.
	 */
	stage2_unmap_put_pte(ctx, mmu, mm_ops);

	if (need_flush && mm_ops->dcache_clean_inval_poc)
		mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops),
					       kvm_granule_size(ctx->level));

	if (childp)
		mm_ops->put_page(childp);

	return 0;
}

int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
{
	int ret;
	struct kvm_pgtable_walker walker = {
		.cb	= stage2_unmap_walker,
		.arg	= pgt,
		.flags	= KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST,
	};

	ret = kvm_pgtable_walk(pgt, addr, size, &walker);
	if (stage2_unmap_defer_tlb_flush(pgt))
		/* Perform the deferred TLB invalidations */
		kvm_tlb_flush_vmid_range(pgt->mmu, addr, size);

	return ret;
}

struct stage2_attr_data {
	kvm_pte_t			attr_set;
	kvm_pte_t			attr_clr;
	kvm_pte_t			pte;
	s8				level;
};

static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx,
			      enum kvm_pgtable_walk_flags visit)
{
	kvm_pte_t pte = ctx->old;
	struct stage2_attr_data *data = ctx->arg;
	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;

	if (!kvm_pte_valid(ctx->old))
		return -EAGAIN;

	data->level = ctx->level;
	data->pte = pte;
	pte &= ~data->attr_clr;
	pte |= data->attr_set;

	/*
	 * We may race with the CPU trying to set the access flag here,
	 * but worst-case the access flag update gets lost and will be
	 * set on the next access instead.
	 */
	if (data->pte != pte) {
		/*
		 * Invalidate instruction cache before updating the guest
		 * stage-2 PTE if we are going to add executable permission.
		 */
		if (mm_ops->icache_inval_pou &&
		    stage2_pte_executable(pte) && !stage2_pte_executable(ctx->old))
			mm_ops->icache_inval_pou(kvm_pte_follow(pte, mm_ops),
						  kvm_granule_size(ctx->level));

		if (!stage2_try_set_pte(ctx, pte))
			return -EAGAIN;
	}

	return 0;
}

static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr,
				    u64 size, kvm_pte_t attr_set,
				    kvm_pte_t attr_clr, kvm_pte_t *orig_pte,
				    s8 *level, enum kvm_pgtable_walk_flags flags)
{
	int ret;
	kvm_pte_t attr_mask = KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI;
	struct stage2_attr_data data = {
		.attr_set	= attr_set & attr_mask,
		.attr_clr	= attr_clr & attr_mask,
	};
	struct kvm_pgtable_walker walker = {
		.cb		= stage2_attr_walker,
		.arg		= &data,
		.flags		= flags | KVM_PGTABLE_WALK_LEAF,
	};

	ret = kvm_pgtable_walk(pgt, addr, size, &walker);
	if (ret)
		return ret;

	if (orig_pte)
		*orig_pte = data.pte;

	if (level)
		*level = data.level;
	return 0;
}

int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
{
	return stage2_update_leaf_attrs(pgt, addr, size, 0,
					KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W,
					NULL, NULL, 0);
}

kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr)
{
	kvm_pte_t pte = 0;
	int ret;

	ret = stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0,
				       &pte, NULL,
				       KVM_PGTABLE_WALK_HANDLE_FAULT |
				       KVM_PGTABLE_WALK_SHARED);
	if (!ret)
		dsb(ishst);

	return pte;
}

struct stage2_age_data {
	bool	mkold;
	bool	young;
};

static int stage2_age_walker(const struct kvm_pgtable_visit_ctx *ctx,
			     enum kvm_pgtable_walk_flags visit)
{
	kvm_pte_t new = ctx->old & ~KVM_PTE_LEAF_ATTR_LO_S2_AF;
	struct stage2_age_data *data = ctx->arg;

	if (!kvm_pte_valid(ctx->old) || new == ctx->old)
		return 0;

	data->young = true;

	/*
	 * stage2_age_walker() is always called while holding the MMU lock for
	 * write, so this will always succeed. Nonetheless, this deliberately
	 * follows the race detection pattern of the other stage-2 walkers in
	 * case the locking mechanics of the MMU notifiers is ever changed.
	 */
	if (data->mkold && !stage2_try_set_pte(ctx, new))
		return -EAGAIN;

	/*
	 * "But where's the TLBI?!", you scream.
	 * "Over in the core code", I sigh.
	 *
	 * See the '->clear_flush_young()' callback on the KVM mmu notifier.
	 */
	return 0;
}

bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
					 u64 size, bool mkold)
{
	struct stage2_age_data data = {
		.mkold		= mkold,
	};
	struct kvm_pgtable_walker walker = {
		.cb		= stage2_age_walker,
		.arg		= &data,
		.flags		= KVM_PGTABLE_WALK_LEAF,
	};

	WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker));
	return data.young;
}

int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
				   enum kvm_pgtable_prot prot)
{
	int ret;
	s8 level;
	kvm_pte_t set = 0, clr = 0;

	if (prot & KVM_PTE_LEAF_ATTR_HI_SW)
		return -EINVAL;

	if (prot & KVM_PGTABLE_PROT_R)
		set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R;

	if (prot & KVM_PGTABLE_PROT_W)
		set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W;

	if (prot & KVM_PGTABLE_PROT_X)
		clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN;

	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level,
				       KVM_PGTABLE_WALK_HANDLE_FAULT |
				       KVM_PGTABLE_WALK_SHARED);
	if (!ret || ret == -EAGAIN)
		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level);
	return ret;
}

static int stage2_flush_walker(const struct kvm_pgtable_visit_ctx *ctx,
			       enum kvm_pgtable_walk_flags visit)
{
	struct kvm_pgtable *pgt = ctx->arg;
	struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops;

	if (!kvm_pte_valid(ctx->old) || !stage2_pte_cacheable(pgt, ctx->old))
		return 0;

	if (mm_ops->dcache_clean_inval_poc)
		mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops),
					       kvm_granule_size(ctx->level));
	return 0;
}

int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
{
	struct kvm_pgtable_walker walker = {
		.cb	= stage2_flush_walker,
		.flags	= KVM_PGTABLE_WALK_LEAF,
		.arg	= pgt,
	};

	if (stage2_has_fwb(pgt))
		return 0;

	return kvm_pgtable_walk(pgt, addr, size, &walker);
}

kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
					      u64 phys, s8 level,
					      enum kvm_pgtable_prot prot,
					      void *mc, bool force_pte)
{
	struct stage2_map_data map_data = {
		.phys		= phys,
		.mmu		= pgt->mmu,
		.memcache	= mc,
		.force_pte	= force_pte,
	};
	struct kvm_pgtable_walker walker = {
		.cb		= stage2_map_walker,
		.flags		= KVM_PGTABLE_WALK_LEAF |
				  KVM_PGTABLE_WALK_SKIP_BBM_TLBI |
				  KVM_PGTABLE_WALK_SKIP_CMO,
		.arg		= &map_data,
	};
	/*
	 * The input address (.addr) is irrelevant for walking an
	 * unlinked table. Construct an ambiguous IA range to map
	 * kvm_granule_size(level) worth of memory.
	 */
	struct kvm_pgtable_walk_data data = {
		.walker	= &walker,
		.addr	= 0,
		.end	= kvm_granule_size(level),
	};
	struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops;
	kvm_pte_t *pgtable;
	int ret;

	if (!IS_ALIGNED(phys, kvm_granule_size(level)))
		return ERR_PTR(-EINVAL);

	ret = stage2_set_prot_attr(pgt, prot, &map_data.attr);
	if (ret)
		return ERR_PTR(ret);

	pgtable = mm_ops->zalloc_page(mc);
	if (!pgtable)
		return ERR_PTR(-ENOMEM);

	ret = __kvm_pgtable_walk(&data, mm_ops, (kvm_pteref_t)pgtable,
				 level + 1);
	if (ret) {
		kvm_pgtable_stage2_free_unlinked(mm_ops, pgtable, level);
		return ERR_PTR(ret);
	}

	return pgtable;
}

/*
 * Get the number of page-tables needed to replace a block with a
 * fully populated tree up to the PTE entries. Note that @level is
 * interpreted as in "level @level entry".
 */
static int stage2_block_get_nr_page_tables(s8 level)
{
	switch (level) {
	case 1:
		return PTRS_PER_PTE + 1;
	case 2:
		return 1;
	case 3:
		return 0;
	default:
		WARN_ON_ONCE(level < KVM_PGTABLE_MIN_BLOCK_LEVEL ||
			     level > KVM_PGTABLE_LAST_LEVEL);
		return -EINVAL;
	};
}

static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx,
			       enum kvm_pgtable_walk_flags visit)
{
	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
	struct kvm_mmu_memory_cache *mc = ctx->arg;
	struct kvm_s2_mmu *mmu;
	kvm_pte_t pte = ctx->old, new, *childp;
	enum kvm_pgtable_prot prot;
	s8 level = ctx->level;
	bool force_pte;
	int nr_pages;
	u64 phys;

	/* No huge-pages exist at the last level */
	if (level == KVM_PGTABLE_LAST_LEVEL)
		return 0;

	/* We only split valid block mappings */
	if (!kvm_pte_valid(pte))
		return 0;

	nr_pages = stage2_block_get_nr_page_tables(level);
	if (nr_pages < 0)
		return nr_pages;

	if (mc->nobjs >= nr_pages) {
		/* Build a tree mapped down to the PTE granularity. */
		force_pte = true;
	} else {
		/*
		 * Don't force PTEs, so create_unlinked() below does
		 * not populate the tree up to the PTE level. The
		 * consequence is that the call will require a single
		 * page of level 2 entries at level 1, or a single
		 * page of PTEs at level 2. If we are at level 1, the
		 * PTEs will be created recursively.
		 */
		force_pte = false;
		nr_pages = 1;
	}

	if (mc->nobjs < nr_pages)
		return -ENOMEM;

	mmu = container_of(mc, struct kvm_s2_mmu, split_page_cache);
	phys = kvm_pte_to_phys(pte);
	prot = kvm_pgtable_stage2_pte_prot(pte);

	childp = kvm_pgtable_stage2_create_unlinked(mmu->pgt, phys,
						    level, prot, mc, force_pte);
	if (IS_ERR(childp))
		return PTR_ERR(childp);

	if (!stage2_try_break_pte(ctx, mmu)) {
		kvm_pgtable_stage2_free_unlinked(mm_ops, childp, level);
		return -EAGAIN;
	}

	/*
	 * Note, the contents of the page table are guaranteed to be made
	 * visible before the new PTE is assigned because stage2_make_pte()
	 * writes the PTE using smp_store_release().
	 */
	new = kvm_init_table_pte(childp, mm_ops);
	stage2_make_pte(ctx, new);
	dsb(ishst);
	return 0;
}

int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size,
			     struct kvm_mmu_memory_cache *mc)
{
	struct kvm_pgtable_walker walker = {
		.cb	= stage2_split_walker,
		.flags	= KVM_PGTABLE_WALK_LEAF,
		.arg	= mc,
	};

	return kvm_pgtable_walk(pgt, addr, size, &walker);
}

int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
			      struct kvm_pgtable_mm_ops *mm_ops,
			      enum kvm_pgtable_stage2_flags flags,
			      kvm_pgtable_force_pte_cb_t force_pte_cb)
{
	size_t pgd_sz;
	u64 vtcr = mmu->vtcr;
	u32 ia_bits = VTCR_EL2_IPA(vtcr);
	u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
	s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;

	pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
	pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_pages_exact(pgd_sz);
	if (!pgt->pgd)
		return -ENOMEM;

	pgt->ia_bits		= ia_bits;
	pgt->start_level	= start_level;
	pgt->mm_ops		= mm_ops;
	pgt->mmu		= mmu;
	pgt->flags		= flags;
	pgt->force_pte_cb	= force_pte_cb;

	/* Ensure zeroed PGD pages are visible to the hardware walker */
	dsb(ishst);
	return 0;
}

size_t kvm_pgtable_stage2_pgd_size(u64 vtcr)
{
	u32 ia_bits = VTCR_EL2_IPA(vtcr);
	u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
	s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;

	return kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
}

static int stage2_free_walker(const struct kvm_pgtable_visit_ctx *ctx,
			      enum kvm_pgtable_walk_flags visit)
{
	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;

	if (!stage2_pte_is_counted(ctx->old))
		return 0;

	mm_ops->put_page(ctx->ptep);

	if (kvm_pte_table(ctx->old, ctx->level))
		mm_ops->put_page(kvm_pte_follow(ctx->old, mm_ops));

	return 0;
}

void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
{
	size_t pgd_sz;
	struct kvm_pgtable_walker walker = {
		.cb	= stage2_free_walker,
		.flags	= KVM_PGTABLE_WALK_LEAF |
			  KVM_PGTABLE_WALK_TABLE_POST,
	};

	WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker));
	pgd_sz = kvm_pgd_pages(pgt->ia_bits, pgt->start_level) * PAGE_SIZE;
	pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(&walker, pgt->pgd), pgd_sz);
	pgt->pgd = NULL;
}

void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level)
{
	kvm_pteref_t ptep = (kvm_pteref_t)pgtable;
	struct kvm_pgtable_walker walker = {
		.cb	= stage2_free_walker,
		.flags	= KVM_PGTABLE_WALK_LEAF |
			  KVM_PGTABLE_WALK_TABLE_POST,
	};
	struct kvm_pgtable_walk_data data = {
		.walker	= &walker,

		/*
		 * At this point the IPA really doesn't matter, as the page
		 * table being traversed has already been removed from the stage
		 * 2. Set an appropriate range to cover the entire page table.
		 */
		.addr	= 0,
		.end	= kvm_granule_size(level),
	};

	WARN_ON(__kvm_pgtable_walk(&data, mm_ops, ptep, level + 1));

	WARN_ON(mm_ops->page_count(pgtable) != 1);
	mm_ops->put_page(pgtable);
}