summaryrefslogtreecommitdiffstats
path: root/arch/arm/kvm/mmu.c
blob: 136662547ca6298f0fd5b6f2c73c7aea557ff472 (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
/*
 * Copyright (C) 2012 - Virtual Open Systems and Columbia University
 * Author: Christoffer Dall <c.dall@virtualopensystems.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License, version 2, as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 */

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

#include "trace.h"

extern char  __hyp_idmap_text_start[], __hyp_idmap_text_end[];

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

static void *init_bounce_page;
static unsigned long hyp_idmap_start;
static unsigned long hyp_idmap_end;
static phys_addr_t hyp_idmap_vector;

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

#define kvm_pmd_huge(_x)	(pmd_huge(_x) || pmd_trans_huge(_x))

static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
{
	/*
	 * This function also gets called when dealing with HYP page
	 * tables. As HYP doesn't have an associated struct kvm (and
	 * the HYP page tables are fairly static), we don't do
	 * anything there.
	 */
	if (kvm)
		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
}

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

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

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

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

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

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

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

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

static void clear_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
{
	pud_t *pud_table __maybe_unused = pud_offset(pgd, 0);
	pgd_clear(pgd);
	kvm_tlb_flush_vmid_ipa(kvm, addr);
	pud_free(NULL, pud_table);
	put_page(virt_to_page(pgd));
}

static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
{
	pmd_t *pmd_table = pmd_offset(pud, 0);
	VM_BUG_ON(pud_huge(*pud));
	pud_clear(pud);
	kvm_tlb_flush_vmid_ipa(kvm, addr);
	pmd_free(NULL, pmd_table);
	put_page(virt_to_page(pud));
}

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

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

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

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

			/* No need to invalidate the cache for device mappings */
			if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
				kvm_flush_dcache_pte(old_pte);

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

	if (kvm_pte_table_empty(kvm, start_pte))
		clear_pmd_entry(kvm, pmd, start_addr);
}

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

	start_pmd = pmd = pmd_offset(pud, addr);
	do {
		next = kvm_pmd_addr_end(addr, end);
		if (!pmd_none(*pmd)) {
			if (kvm_pmd_huge(*pmd)) {
				pmd_t old_pmd = *pmd;

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

				kvm_flush_dcache_pmd(old_pmd);

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

	if (kvm_pmd_table_empty(kvm, start_pmd))
		clear_pud_entry(kvm, pud, start_addr);
}

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

	start_pud = pud = pud_offset(pgd, addr);
	do {
		next = kvm_pud_addr_end(addr, end);
		if (!pud_none(*pud)) {
			if (pud_huge(*pud)) {
				pud_t old_pud = *pud;

				pud_clear(pud);
				kvm_tlb_flush_vmid_ipa(kvm, addr);

				kvm_flush_dcache_pud(old_pud);

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

	if (kvm_pud_table_empty(kvm, start_pud))
		clear_pgd_entry(kvm, pgd, start_addr);
}


static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
			phys_addr_t start, u64 size)
{
	pgd_t *pgd;
	phys_addr_t addr = start, end = start + size;
	phys_addr_t next;

	pgd = pgdp + pgd_index(addr);
	do {
		next = kvm_pgd_addr_end(addr, end);
		if (!pgd_none(*pgd))
			unmap_puds(kvm, pgd, addr, next);
	} while (pgd++, addr = next, addr != end);
}

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

	pte = pte_offset_kernel(pmd, addr);
	do {
		if (!pte_none(*pte) &&
		    (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
			kvm_flush_dcache_pte(*pte);
	} while (pte++, addr += PAGE_SIZE, addr != end);
}

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

	pmd = pmd_offset(pud, addr);
	do {
		next = kvm_pmd_addr_end(addr, end);
		if (!pmd_none(*pmd)) {
			if (kvm_pmd_huge(*pmd))
				kvm_flush_dcache_pmd(*pmd);
			else
				stage2_flush_ptes(kvm, pmd, addr, next);
		}
	} while (pmd++, addr = next, addr != end);
}

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

	pud = pud_offset(pgd, addr);
	do {
		next = kvm_pud_addr_end(addr, end);
		if (!pud_none(*pud)) {
			if (pud_huge(*pud))
				kvm_flush_dcache_pud(*pud);
			else
				stage2_flush_pmds(kvm, pud, addr, next);
		}
	} while (pud++, addr = next, addr != end);
}

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

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

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

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

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

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

/**
 * free_boot_hyp_pgd - free HYP boot page tables
 *
 * Free the HYP boot page tables. The bounce page is also freed.
 */
void free_boot_hyp_pgd(void)
{
	mutex_lock(&kvm_hyp_pgd_mutex);

	if (boot_hyp_pgd) {
		unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
		unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
		free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order);
		boot_hyp_pgd = NULL;
	}

	if (hyp_pgd)
		unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);

	free_page((unsigned long)init_bounce_page);
	init_bounce_page = NULL;

	mutex_unlock(&kvm_hyp_pgd_mutex);
}

/**
 * free_hyp_pgds - free Hyp-mode page tables
 *
 * Assumes hyp_pgd is a page table used strictly in Hyp-mode and
 * therefore contains either mappings in the kernel memory area (above
 * PAGE_OFFSET), or device mappings in the vmalloc range (from
 * VMALLOC_START to VMALLOC_END).
 *
 * boot_hyp_pgd should only map two pages for the init code.
 */
void free_hyp_pgds(void)
{
	unsigned long addr;

	free_boot_hyp_pgd();

	mutex_lock(&kvm_hyp_pgd_mutex);

	if (hyp_pgd) {
		for (addr = PAGE_OFFSET; virt_addr_valid(addr); addr += PGDIR_SIZE)
			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);

		free_pages((unsigned long)hyp_pgd, hyp_pgd_order);
		hyp_pgd = NULL;
	}

	mutex_unlock(&kvm_hyp_pgd_mutex);
}

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

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

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

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

		BUG_ON(pmd_sect(*pmd));

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

		next = pmd_addr_end(addr, end);

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

	return 0;
}

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

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

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

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

	return 0;
}

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

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

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

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

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

/**
 * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
 * @from:	The virtual kernel start address of the range
 * @to:		The virtual kernel end address of the range (exclusive)
 *
 * 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)
{
	phys_addr_t phys_addr;
	unsigned long virt_addr;
	unsigned long start = KERN_TO_HYP((unsigned long)from);
	unsigned long end = KERN_TO_HYP((unsigned long)to);

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

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

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

	return 0;
}

/**
 * create_hyp_io_mappings - duplicate a kernel IO mapping into Hyp mode
 * @from:	The kernel start VA of the range
 * @to:		The kernel end VA of the range (exclusive)
 * @phys_addr:	The physical start address which gets mapped
 *
 * The resulting HYP VA is the same as the kernel VA, modulo
 * HYP_PAGE_OFFSET.
 */
int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
{
	unsigned long start = KERN_TO_HYP((unsigned long)from);
	unsigned long end = KERN_TO_HYP((unsigned long)to);

	/* Check for a valid kernel IO mapping */
	if (!is_vmalloc_addr(from) || !is_vmalloc_addr(to - 1))
		return -EINVAL;

	return __create_hyp_mappings(hyp_pgd, start, end,
				     __phys_to_pfn(phys_addr), PAGE_HYP_DEVICE);
}

/**
 * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
 * @kvm:	The KVM struct pointer for the VM.
 *
 * Allocates the 1st level table only of size defined by S2_PGD_ORDER (can
 * support either full 40-bit input addresses or limited to 32-bit input
 * addresses). Clears the allocated pages.
 *
 * Note we don't need locking here as this is only called when the VM is
 * created, which can only be done once.
 */
int kvm_alloc_stage2_pgd(struct kvm *kvm)
{
	int ret;
	pgd_t *pgd;

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

	if (KVM_PREALLOC_LEVEL > 0) {
		/*
		 * Allocate fake pgd for the page table manipulation macros to
		 * work.  This is not used by the hardware and we have no
		 * alignment requirement for this allocation.
		 */
		pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
				       GFP_KERNEL | __GFP_ZERO);
	} else {
		/*
		 * Allocate actual first-level Stage-2 page table used by the
		 * hardware for Stage-2 page table walks.
		 */
		pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, S2_PGD_ORDER);
	}

	if (!pgd)
		return -ENOMEM;

	ret = kvm_prealloc_hwpgd(kvm, pgd);
	if (ret)
		goto out_err;

	kvm_clean_pgd(pgd);
	kvm->arch.pgd = pgd;
	return 0;
out_err:
	if (KVM_PREALLOC_LEVEL > 0)
		kfree(pgd);
	else
		free_pages((unsigned long)pgd, S2_PGD_ORDER);
	return ret;
}

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

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

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

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

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

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

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

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

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

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

/**
 * kvm_free_stage2_pgd - free all stage-2 tables
 * @kvm:	The KVM struct pointer for the VM.
 *
 * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all
 * underlying level-2 and level-3 tables before freeing the actual level-1 table
 * and setting the struct pointer to NULL.
 *
 * Note we don't need locking here as this is only called when the VM is
 * destroyed, which can only be done once.
 */
void kvm_free_stage2_pgd(struct kvm *kvm)
{
	if (kvm->arch.pgd == NULL)
		return;

	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
	kvm_free_hwpgd(kvm);
	if (KVM_PREALLOC_LEVEL > 0)
		kfree(kvm->arch.pgd);
	else
		free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER);
	kvm->arch.pgd = NULL;
}

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

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

	return pud_offset(pgd, addr);
}

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

	pud = stage2_get_pud(kvm, cache, addr);
	if (pud_none(*pud)) {
		if (!cache)
			return NULL;
		pmd = mmu_memory_cache_alloc(cache);
		pud_populate(NULL, pud, pmd);
		get_page(virt_to_page(pud));
	}

	return pmd_offset(pud, addr);
}

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

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

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

	old_pmd = *pmd;
	kvm_set_pmd(pmd, *new_pmd);
	if (pmd_present(old_pmd))
		kvm_tlb_flush_vmid_ipa(kvm, addr);
	else
		get_page(virt_to_page(pmd));
	return 0;
}

static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
			  phys_addr_t addr, const pte_t *new_pte, bool iomap)
{
	pmd_t *pmd;
	pte_t *pte, old_pte;

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

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

	pte = pte_offset_kernel(pmd, addr);

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

	/* Create 2nd stage page table mapping - Level 3 */
	old_pte = *pte;
	kvm_set_pte(pte, *new_pte);
	if (pte_present(old_pte))
		kvm_tlb_flush_vmid_ipa(kvm, addr);
	else
		get_page(virt_to_page(pte));

	return 0;
}

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

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

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

		if (writable)
			kvm_set_s2pte_writable(&pte);

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

		pfn++;
	}

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

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

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

		return true;
	}

	return false;
}

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

	return kvm_vcpu_dabt_iswrite(vcpu);
}

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

static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
				      unsigned long size, bool uncached)
{
	__coherent_cache_guest_page(vcpu, pfn, size, uncached);
}

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

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

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

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

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

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

	pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable);
	if (is_error_pfn(pfn))
		return -EFAULT;

	if (kvm_is_device_pfn(pfn))
		mem_type = PAGE_S2_DEVICE;

	spin_lock(&kvm->mmu_lock);
	if (mmu_notifier_retry(kvm, mmu_seq))
		goto out_unlock;
	if (!hugetlb && !force_pte)
		hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);

	fault_ipa_uncached = memslot->flags & KVM_MEMSLOT_INCOHERENT;

	if (hugetlb) {
		pmd_t new_pmd = pfn_pmd(pfn, mem_type);
		new_pmd = pmd_mkhuge(new_pmd);
		if (writable) {
			kvm_set_s2pmd_writable(&new_pmd);
			kvm_set_pfn_dirty(pfn);
		}
		coherent_cache_guest_page(vcpu, pfn, PMD_SIZE, fault_ipa_uncached);
		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
	} else {
		pte_t new_pte = pfn_pte(pfn, mem_type);
		if (writable) {
			kvm_set_s2pte_writable(&new_pte);
			kvm_set_pfn_dirty(pfn);
		}
		coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE, fault_ipa_uncached);
		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte,
			pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE));
	}


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

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

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

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

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

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

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

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

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

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

static void handle_hva_to_gpa(struct kvm *kvm,
			      unsigned long start,
			      unsigned long end,
			      void (*handler)(struct kvm *kvm,
					      gpa_t gpa, void *data),
			      void *data)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;

	slots = kvm_memslots(kvm);

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

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

		/*
		 * {gfn(page) | page intersects with [hva_start, hva_end)} =
		 * {gfn_start, gfn_start+1, ..., gfn_end-1}.
		 */
		gfn = hva_to_gfn_memslot(hva_start, memslot);
		gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);

		for (; gfn < gfn_end; ++gfn) {
			gpa_t gpa = gfn << PAGE_SHIFT;
			handler(kvm, gpa, data);
		}
	}
}

static void kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
{
	unmap_stage2_range(kvm, gpa, PAGE_SIZE);
}

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

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

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

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

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

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

	stage2_set_pte(kvm, NULL, gpa, pte, false);
}


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

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

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

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

phys_addr_t kvm_mmu_get_httbr(void)
{
	return virt_to_phys(hyp_pgd);
}

phys_addr_t kvm_mmu_get_boot_httbr(void)
{
	return virt_to_phys(boot_hyp_pgd);
}

phys_addr_t kvm_get_idmap_vector(void)
{
	return hyp_idmap_vector;
}

int kvm_mmu_init(void)
{
	int err;

	hyp_idmap_start = kvm_virt_to_phys(__hyp_idmap_text_start);
	hyp_idmap_end = kvm_virt_to_phys(__hyp_idmap_text_end);
	hyp_idmap_vector = kvm_virt_to_phys(__kvm_hyp_init);

	if ((hyp_idmap_start ^ hyp_idmap_end) & PAGE_MASK) {
		/*
		 * Our init code is crossing a page boundary. Allocate
		 * a bounce page, copy the code over and use that.
		 */
		size_t len = __hyp_idmap_text_end - __hyp_idmap_text_start;
		phys_addr_t phys_base;

		init_bounce_page = (void *)__get_free_page(GFP_KERNEL);
		if (!init_bounce_page) {
			kvm_err("Couldn't allocate HYP init bounce page\n");
			err = -ENOMEM;
			goto out;
		}

		memcpy(init_bounce_page, __hyp_idmap_text_start, len);
		/*
		 * Warning: the code we just copied to the bounce page
		 * must be flushed to the point of coherency.
		 * Otherwise, the data may be sitting in L2, and HYP
		 * mode won't be able to observe it as it runs with
		 * caches off at that point.
		 */
		kvm_flush_dcache_to_poc(init_bounce_page, len);

		phys_base = kvm_virt_to_phys(init_bounce_page);
		hyp_idmap_vector += phys_base - hyp_idmap_start;
		hyp_idmap_start = phys_base;
		hyp_idmap_end = phys_base + len;

		kvm_info("Using HYP init bounce page @%lx\n",
			 (unsigned long)phys_base);
	}

	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
	boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);

	if (!hyp_pgd || !boot_hyp_pgd) {
		kvm_err("Hyp mode PGD not allocated\n");
		err = -ENOMEM;
		goto out;
	}

	/* Create the idmap in the boot page tables */
	err = 	__create_hyp_mappings(boot_hyp_pgd,
				      hyp_idmap_start, hyp_idmap_end,
				      __phys_to_pfn(hyp_idmap_start),
				      PAGE_HYP);

	if (err) {
		kvm_err("Failed to idmap %lx-%lx\n",
			hyp_idmap_start, hyp_idmap_end);
		goto out;
	}

	/* Map the very same page at the trampoline VA */
	err = 	__create_hyp_mappings(boot_hyp_pgd,
				      TRAMPOLINE_VA, TRAMPOLINE_VA + PAGE_SIZE,
				      __phys_to_pfn(hyp_idmap_start),
				      PAGE_HYP);
	if (err) {
		kvm_err("Failed to map trampoline @%lx into boot HYP pgd\n",
			TRAMPOLINE_VA);
		goto out;
	}

	/* Map the same page again into the runtime page tables */
	err = 	__create_hyp_mappings(hyp_pgd,
				      TRAMPOLINE_VA, TRAMPOLINE_VA + PAGE_SIZE,
				      __phys_to_pfn(hyp_idmap_start),
				      PAGE_HYP);
	if (err) {
		kvm_err("Failed to map trampoline @%lx into runtime HYP pgd\n",
			TRAMPOLINE_VA);
		goto out;
	}

	return 0;
out:
	free_hyp_pgds();
	return err;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				   struct kvm_userspace_memory_region *mem,
				   const struct kvm_memory_slot *old,
				   enum kvm_mr_change change)
{
}

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

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

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

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

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

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

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

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

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

	spin_lock(&kvm->mmu_lock);
	if (ret)
		unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size);
	else
		stage2_flush_memslot(kvm, memslot);
	spin_unlock(&kvm->mmu_lock);
	return ret;
}

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

int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
			    unsigned long npages)
{
	/*
	 * Readonly memslots are not incoherent with the caches by definition,
	 * but in practice, they are used mostly to emulate ROMs or NOR flashes
	 * that the guest may consider devices and hence map as uncached.
	 * To prevent incoherency issues in these cases, tag all readonly
	 * regions as incoherent.
	 */
	if (slot->flags & KVM_MEM_READONLY)
		slot->flags |= KVM_MEMSLOT_INCOHERENT;
	return 0;
}

void kvm_arch_memslots_updated(struct kvm *kvm)
{
}

void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
}

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

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

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

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