summaryrefslogtreecommitdiffstats
path: root/virt/kvm/arm/vgic/vgic-its.c
blob: ffd0a801aeb593527c463a7276ab7bdfeba96a35 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
/*
 * GICv3 ITS emulation
 *
 * Copyright (C) 2015,2016 ARM Ltd.
 * Author: Andre Przywara <andre.przywara@arm.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, see <http://www.gnu.org/licenses/>.
 */

#include <linux/cpu.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/interrupt.h>
#include <linux/list.h>
#include <linux/uaccess.h>

#include <linux/irqchip/arm-gic-v3.h>

#include <asm/kvm_emulate.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_mmu.h>

#include "vgic.h"
#include "vgic-mmio.h"

static int vgic_its_save_tables_v0(struct vgic_its *its);
static int vgic_its_restore_tables_v0(struct vgic_its *its);
static int vgic_its_commit_v0(struct vgic_its *its);
static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
			     struct kvm_vcpu *filter_vcpu);

/*
 * Creates a new (reference to a) struct vgic_irq for a given LPI.
 * If this LPI is already mapped on another ITS, we increase its refcount
 * and return a pointer to the existing structure.
 * If this is a "new" LPI, we allocate and initialize a new struct vgic_irq.
 * This function returns a pointer to the _unlocked_ structure.
 */
static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
				     struct kvm_vcpu *vcpu)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq;
	int ret;

	/* In this case there is no put, since we keep the reference. */
	if (irq)
		return irq;

	irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL);
	if (!irq)
		return ERR_PTR(-ENOMEM);

	INIT_LIST_HEAD(&irq->lpi_list);
	INIT_LIST_HEAD(&irq->ap_list);
	spin_lock_init(&irq->irq_lock);

	irq->config = VGIC_CONFIG_EDGE;
	kref_init(&irq->refcount);
	irq->intid = intid;
	irq->target_vcpu = vcpu;

	spin_lock(&dist->lpi_list_lock);

	/*
	 * There could be a race with another vgic_add_lpi(), so we need to
	 * check that we don't add a second list entry with the same LPI.
	 */
	list_for_each_entry(oldirq, &dist->lpi_list_head, lpi_list) {
		if (oldirq->intid != intid)
			continue;

		/* Someone was faster with adding this LPI, lets use that. */
		kfree(irq);
		irq = oldirq;

		/*
		 * This increases the refcount, the caller is expected to
		 * call vgic_put_irq() on the returned pointer once it's
		 * finished with the IRQ.
		 */
		vgic_get_irq_kref(irq);

		goto out_unlock;
	}

	list_add_tail(&irq->lpi_list, &dist->lpi_list_head);
	dist->lpi_list_count++;

out_unlock:
	spin_unlock(&dist->lpi_list_lock);

	/*
	 * We "cache" the configuration table entries in our struct vgic_irq's.
	 * However we only have those structs for mapped IRQs, so we read in
	 * the respective config data from memory here upon mapping the LPI.
	 */
	ret = update_lpi_config(kvm, irq, NULL);
	if (ret)
		return ERR_PTR(ret);

	ret = vgic_v3_lpi_sync_pending_status(kvm, irq);
	if (ret)
		return ERR_PTR(ret);

	return irq;
}

struct its_device {
	struct list_head dev_list;

	/* the head for the list of ITTEs */
	struct list_head itt_head;
	u32 num_eventid_bits;
	gpa_t itt_addr;
	u32 device_id;
};

#define COLLECTION_NOT_MAPPED ((u32)~0)

struct its_collection {
	struct list_head coll_list;

	u32 collection_id;
	u32 target_addr;
};

#define its_is_collection_mapped(coll) ((coll) && \
				((coll)->target_addr != COLLECTION_NOT_MAPPED))

struct its_ite {
	struct list_head ite_list;

	struct vgic_irq *irq;
	struct its_collection *collection;
	u32 lpi;
	u32 event_id;
};

/**
 * struct vgic_its_abi - ITS abi ops and settings
 * @cte_esz: collection table entry size
 * @dte_esz: device table entry size
 * @ite_esz: interrupt translation table entry size
 * @save tables: save the ITS tables into guest RAM
 * @restore_tables: restore the ITS internal structs from tables
 *  stored in guest RAM
 * @commit: initialize the registers which expose the ABI settings,
 *  especially the entry sizes
 */
struct vgic_its_abi {
	int cte_esz;
	int dte_esz;
	int ite_esz;
	int (*save_tables)(struct vgic_its *its);
	int (*restore_tables)(struct vgic_its *its);
	int (*commit)(struct vgic_its *its);
};

static const struct vgic_its_abi its_table_abi_versions[] = {
	[0] = {.cte_esz = 8, .dte_esz = 8, .ite_esz = 8,
	 .save_tables = vgic_its_save_tables_v0,
	 .restore_tables = vgic_its_restore_tables_v0,
	 .commit = vgic_its_commit_v0,
	},
};

#define NR_ITS_ABIS	ARRAY_SIZE(its_table_abi_versions)

inline const struct vgic_its_abi *vgic_its_get_abi(struct vgic_its *its)
{
	return &its_table_abi_versions[its->abi_rev];
}

int vgic_its_set_abi(struct vgic_its *its, int rev)
{
	const struct vgic_its_abi *abi;

	its->abi_rev = rev;
	abi = vgic_its_get_abi(its);
	return abi->commit(its);
}

/*
 * Find and returns a device in the device table for an ITS.
 * Must be called with the its_lock mutex held.
 */
static struct its_device *find_its_device(struct vgic_its *its, u32 device_id)
{
	struct its_device *device;

	list_for_each_entry(device, &its->device_list, dev_list)
		if (device_id == device->device_id)
			return device;

	return NULL;
}

/*
 * Find and returns an interrupt translation table entry (ITTE) for a given
 * Device ID/Event ID pair on an ITS.
 * Must be called with the its_lock mutex held.
 */
static struct its_ite *find_ite(struct vgic_its *its, u32 device_id,
				  u32 event_id)
{
	struct its_device *device;
	struct its_ite *ite;

	device = find_its_device(its, device_id);
	if (device == NULL)
		return NULL;

	list_for_each_entry(ite, &device->itt_head, ite_list)
		if (ite->event_id == event_id)
			return ite;

	return NULL;
}

/* To be used as an iterator this macro misses the enclosing parentheses */
#define for_each_lpi_its(dev, ite, its) \
	list_for_each_entry(dev, &(its)->device_list, dev_list) \
		list_for_each_entry(ite, &(dev)->itt_head, ite_list)

/*
 * We only implement 48 bits of PA at the moment, although the ITS
 * supports more. Let's be restrictive here.
 */
#define BASER_ADDRESS(x)	((x) & GENMASK_ULL(47, 16))
#define CBASER_ADDRESS(x)	((x) & GENMASK_ULL(47, 12))

#define GIC_LPI_OFFSET 8192

#define VITS_TYPER_IDBITS 16
#define VITS_TYPER_DEVBITS 16

/*
 * Finds and returns a collection in the ITS collection table.
 * Must be called with the its_lock mutex held.
 */
static struct its_collection *find_collection(struct vgic_its *its, int coll_id)
{
	struct its_collection *collection;

	list_for_each_entry(collection, &its->collection_list, coll_list) {
		if (coll_id == collection->collection_id)
			return collection;
	}

	return NULL;
}

#define LPI_PROP_ENABLE_BIT(p)	((p) & LPI_PROP_ENABLED)
#define LPI_PROP_PRIORITY(p)	((p) & 0xfc)

/*
 * Reads the configuration data for a given LPI from guest memory and
 * updates the fields in struct vgic_irq.
 * If filter_vcpu is not NULL, applies only if the IRQ is targeting this
 * VCPU. Unconditionally applies if filter_vcpu is NULL.
 */
static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
			     struct kvm_vcpu *filter_vcpu)
{
	u64 propbase = GICR_PROPBASER_ADDRESS(kvm->arch.vgic.propbaser);
	u8 prop;
	int ret;

	ret = kvm_read_guest(kvm, propbase + irq->intid - GIC_LPI_OFFSET,
			     &prop, 1);

	if (ret)
		return ret;

	spin_lock(&irq->irq_lock);

	if (!filter_vcpu || filter_vcpu == irq->target_vcpu) {
		irq->priority = LPI_PROP_PRIORITY(prop);
		irq->enabled = LPI_PROP_ENABLE_BIT(prop);

		vgic_queue_irq_unlock(kvm, irq);
	} else {
		spin_unlock(&irq->irq_lock);
	}

	return 0;
}

/*
 * Create a snapshot of the current LPI list, so that we can enumerate all
 * LPIs without holding any lock.
 * Returns the array length and puts the kmalloc'ed array into intid_ptr.
 */
static int vgic_copy_lpi_list(struct kvm *kvm, u32 **intid_ptr)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct vgic_irq *irq;
	u32 *intids;
	int irq_count = dist->lpi_list_count, i = 0;

	/*
	 * We use the current value of the list length, which may change
	 * after the kmalloc. We don't care, because the guest shouldn't
	 * change anything while the command handling is still running,
	 * and in the worst case we would miss a new IRQ, which one wouldn't
	 * expect to be covered by this command anyway.
	 */
	intids = kmalloc_array(irq_count, sizeof(intids[0]), GFP_KERNEL);
	if (!intids)
		return -ENOMEM;

	spin_lock(&dist->lpi_list_lock);
	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
		/* We don't need to "get" the IRQ, as we hold the list lock. */
		intids[i] = irq->intid;
		if (++i == irq_count)
			break;
	}
	spin_unlock(&dist->lpi_list_lock);

	*intid_ptr = intids;
	return irq_count;
}

/*
 * Promotes the ITS view of affinity of an ITTE (which redistributor this LPI
 * is targeting) to the VGIC's view, which deals with target VCPUs.
 * Needs to be called whenever either the collection for a LPIs has
 * changed or the collection itself got retargeted.
 */
static void update_affinity_ite(struct kvm *kvm, struct its_ite *ite)
{
	struct kvm_vcpu *vcpu;

	if (!its_is_collection_mapped(ite->collection))
		return;

	vcpu = kvm_get_vcpu(kvm, ite->collection->target_addr);

	spin_lock(&ite->irq->irq_lock);
	ite->irq->target_vcpu = vcpu;
	spin_unlock(&ite->irq->irq_lock);
}

/*
 * Updates the target VCPU for every LPI targeting this collection.
 * Must be called with the its_lock mutex held.
 */
static void update_affinity_collection(struct kvm *kvm, struct vgic_its *its,
				       struct its_collection *coll)
{
	struct its_device *device;
	struct its_ite *ite;

	for_each_lpi_its(device, ite, its) {
		if (!ite->collection || coll != ite->collection)
			continue;

		update_affinity_ite(kvm, ite);
	}
}

static u32 max_lpis_propbaser(u64 propbaser)
{
	int nr_idbits = (propbaser & 0x1f) + 1;

	return 1U << min(nr_idbits, INTERRUPT_ID_BITS_ITS);
}

/*
 * Scan the whole LPI pending table and sync the pending bit in there
 * with our own data structures. This relies on the LPI being
 * mapped before.
 */
static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
{
	gpa_t pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
	struct vgic_irq *irq;
	int last_byte_offset = -1;
	int ret = 0;
	u32 *intids;
	int nr_irqs, i;

	nr_irqs = vgic_copy_lpi_list(vcpu->kvm, &intids);
	if (nr_irqs < 0)
		return nr_irqs;

	for (i = 0; i < nr_irqs; i++) {
		int byte_offset, bit_nr;
		u8 pendmask;

		byte_offset = intids[i] / BITS_PER_BYTE;
		bit_nr = intids[i] % BITS_PER_BYTE;

		/*
		 * For contiguously allocated LPIs chances are we just read
		 * this very same byte in the last iteration. Reuse that.
		 */
		if (byte_offset != last_byte_offset) {
			ret = kvm_read_guest(vcpu->kvm, pendbase + byte_offset,
					     &pendmask, 1);
			if (ret) {
				kfree(intids);
				return ret;
			}
			last_byte_offset = byte_offset;
		}

		irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]);
		spin_lock(&irq->irq_lock);
		irq->pending_latch = pendmask & (1U << bit_nr);
		vgic_queue_irq_unlock(vcpu->kvm, irq);
		vgic_put_irq(vcpu->kvm, irq);
	}

	kfree(intids);

	return ret;
}

static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm,
					      struct vgic_its *its,
					      gpa_t addr, unsigned int len)
{
	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
	u64 reg = GITS_TYPER_PLPIS;

	/*
	 * We use linear CPU numbers for redistributor addressing,
	 * so GITS_TYPER.PTA is 0.
	 * Also we force all PROPBASER registers to be the same, so
	 * CommonLPIAff is 0 as well.
	 * To avoid memory waste in the guest, we keep the number of IDBits and
	 * DevBits low - as least for the time being.
	 */
	reg |= GIC_ENCODE_SZ(VITS_TYPER_DEVBITS, 5) << GITS_TYPER_DEVBITS_SHIFT;
	reg |= GIC_ENCODE_SZ(VITS_TYPER_IDBITS, 5) << GITS_TYPER_IDBITS_SHIFT;
	reg |= GIC_ENCODE_SZ(abi->ite_esz, 4) << GITS_TYPER_ITT_ENTRY_SIZE_SHIFT;

	return extract_bytes(reg, addr & 7, len);
}

static unsigned long vgic_mmio_read_its_iidr(struct kvm *kvm,
					     struct vgic_its *its,
					     gpa_t addr, unsigned int len)
{
	u32 val;

	val = (its->abi_rev << GITS_IIDR_REV_SHIFT) & GITS_IIDR_REV_MASK;
	val |= (PRODUCT_ID_KVM << GITS_IIDR_PRODUCTID_SHIFT) | IMPLEMENTER_ARM;
	return val;
}

static int vgic_mmio_uaccess_write_its_iidr(struct kvm *kvm,
					    struct vgic_its *its,
					    gpa_t addr, unsigned int len,
					    unsigned long val)
{
	u32 rev = GITS_IIDR_REV(val);

	if (rev >= NR_ITS_ABIS)
		return -EINVAL;
	return vgic_its_set_abi(its, rev);
}

static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm,
					       struct vgic_its *its,
					       gpa_t addr, unsigned int len)
{
	switch (addr & 0xffff) {
	case GITS_PIDR0:
		return 0x92;	/* part number, bits[7:0] */
	case GITS_PIDR1:
		return 0xb4;	/* part number, bits[11:8] */
	case GITS_PIDR2:
		return GIC_PIDR2_ARCH_GICv3 | 0x0b;
	case GITS_PIDR4:
		return 0x40;	/* This is a 64K software visible page */
	/* The following are the ID registers for (any) GIC. */
	case GITS_CIDR0:
		return 0x0d;
	case GITS_CIDR1:
		return 0xf0;
	case GITS_CIDR2:
		return 0x05;
	case GITS_CIDR3:
		return 0xb1;
	}

	return 0;
}

/*
 * Find the target VCPU and the LPI number for a given devid/eventid pair
 * and make this IRQ pending, possibly injecting it.
 * Must be called with the its_lock mutex held.
 * Returns 0 on success, a positive error value for any ITS mapping
 * related errors and negative error values for generic errors.
 */
static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its,
				u32 devid, u32 eventid)
{
	struct kvm_vcpu *vcpu;
	struct its_ite *ite;

	if (!its->enabled)
		return -EBUSY;

	ite = find_ite(its, devid, eventid);
	if (!ite || !its_is_collection_mapped(ite->collection))
		return E_ITS_INT_UNMAPPED_INTERRUPT;

	vcpu = kvm_get_vcpu(kvm, ite->collection->target_addr);
	if (!vcpu)
		return E_ITS_INT_UNMAPPED_INTERRUPT;

	if (!vcpu->arch.vgic_cpu.lpis_enabled)
		return -EBUSY;

	spin_lock(&ite->irq->irq_lock);
	ite->irq->pending_latch = true;
	vgic_queue_irq_unlock(kvm, ite->irq);

	return 0;
}

static struct vgic_io_device *vgic_get_its_iodev(struct kvm_io_device *dev)
{
	struct vgic_io_device *iodev;

	if (dev->ops != &kvm_io_gic_ops)
		return NULL;

	iodev = container_of(dev, struct vgic_io_device, dev);

	if (iodev->iodev_type != IODEV_ITS)
		return NULL;

	return iodev;
}

/*
 * Queries the KVM IO bus framework to get the ITS pointer from the given
 * doorbell address.
 * We then call vgic_its_trigger_msi() with the decoded data.
 * According to the KVM_SIGNAL_MSI API description returns 1 on success.
 */
int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi)
{
	u64 address;
	struct kvm_io_device *kvm_io_dev;
	struct vgic_io_device *iodev;
	int ret;

	if (!vgic_has_its(kvm))
		return -ENODEV;

	if (!(msi->flags & KVM_MSI_VALID_DEVID))
		return -EINVAL;

	address = (u64)msi->address_hi << 32 | msi->address_lo;

	kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, address);
	if (!kvm_io_dev)
		return -EINVAL;

	iodev = vgic_get_its_iodev(kvm_io_dev);
	if (!iodev)
		return -EINVAL;

	mutex_lock(&iodev->its->its_lock);
	ret = vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data);
	mutex_unlock(&iodev->its->its_lock);

	if (ret < 0)
		return ret;

	/*
	 * KVM_SIGNAL_MSI demands a return value > 0 for success and 0
	 * if the guest has blocked the MSI. So we map any LPI mapping
	 * related error to that.
	 */
	if (ret)
		return 0;
	else
		return 1;
}

/* Requires the its_lock to be held. */
static void its_free_ite(struct kvm *kvm, struct its_ite *ite)
{
	list_del(&ite->ite_list);

	/* This put matches the get in vgic_add_lpi. */
	if (ite->irq)
		vgic_put_irq(kvm, ite->irq);

	kfree(ite);
}

static u64 its_cmd_mask_field(u64 *its_cmd, int word, int shift, int size)
{
	return (le64_to_cpu(its_cmd[word]) >> shift) & (BIT_ULL(size) - 1);
}

#define its_cmd_get_command(cmd)	its_cmd_mask_field(cmd, 0,  0,  8)
#define its_cmd_get_deviceid(cmd)	its_cmd_mask_field(cmd, 0, 32, 32)
#define its_cmd_get_size(cmd)		(its_cmd_mask_field(cmd, 1,  0,  5) + 1)
#define its_cmd_get_id(cmd)		its_cmd_mask_field(cmd, 1,  0, 32)
#define its_cmd_get_physical_id(cmd)	its_cmd_mask_field(cmd, 1, 32, 32)
#define its_cmd_get_collection(cmd)	its_cmd_mask_field(cmd, 2,  0, 16)
#define its_cmd_get_ittaddr(cmd)	(its_cmd_mask_field(cmd, 2,  8, 44) << 8)
#define its_cmd_get_target_addr(cmd)	its_cmd_mask_field(cmd, 2, 16, 32)
#define its_cmd_get_validbit(cmd)	its_cmd_mask_field(cmd, 2, 63,  1)

/*
 * The DISCARD command frees an Interrupt Translation Table Entry (ITTE).
 * Must be called with the its_lock mutex held.
 */
static int vgic_its_cmd_handle_discard(struct kvm *kvm, struct vgic_its *its,
				       u64 *its_cmd)
{
	u32 device_id = its_cmd_get_deviceid(its_cmd);
	u32 event_id = its_cmd_get_id(its_cmd);
	struct its_ite *ite;


	ite = find_ite(its, device_id, event_id);
	if (ite && ite->collection) {
		/*
		 * Though the spec talks about removing the pending state, we
		 * don't bother here since we clear the ITTE anyway and the
		 * pending state is a property of the ITTE struct.
		 */
		its_free_ite(kvm, ite);
		return 0;
	}

	return E_ITS_DISCARD_UNMAPPED_INTERRUPT;
}

/*
 * The MOVI command moves an ITTE to a different collection.
 * Must be called with the its_lock mutex held.
 */
static int vgic_its_cmd_handle_movi(struct kvm *kvm, struct vgic_its *its,
				    u64 *its_cmd)
{
	u32 device_id = its_cmd_get_deviceid(its_cmd);
	u32 event_id = its_cmd_get_id(its_cmd);
	u32 coll_id = its_cmd_get_collection(its_cmd);
	struct kvm_vcpu *vcpu;
	struct its_ite *ite;
	struct its_collection *collection;

	ite = find_ite(its, device_id, event_id);
	if (!ite)
		return E_ITS_MOVI_UNMAPPED_INTERRUPT;

	if (!its_is_collection_mapped(ite->collection))
		return E_ITS_MOVI_UNMAPPED_COLLECTION;

	collection = find_collection(its, coll_id);
	if (!its_is_collection_mapped(collection))
		return E_ITS_MOVI_UNMAPPED_COLLECTION;

	ite->collection = collection;
	vcpu = kvm_get_vcpu(kvm, collection->target_addr);

	spin_lock(&ite->irq->irq_lock);
	ite->irq->target_vcpu = vcpu;
	spin_unlock(&ite->irq->irq_lock);

	return 0;
}

/*
 * Check whether an ID can be stored into the corresponding guest table.
 * For a direct table this is pretty easy, but gets a bit nasty for
 * indirect tables. We check whether the resulting guest physical address
 * is actually valid (covered by a memslot and guest accessible).
 * For this we have to read the respective first level entry.
 */
static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id)
{
	int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K;
	u64 indirect_ptr, type = GITS_BASER_TYPE(baser);
	int esz = GITS_BASER_ENTRY_SIZE(baser);
	int index;
	gfn_t gfn;

	switch (type) {
	case GITS_BASER_TYPE_DEVICE:
		if (id >= BIT_ULL(VITS_TYPER_DEVBITS))
			return false;
		break;
	case GITS_BASER_TYPE_COLLECTION:
		/* as GITS_TYPER.CIL == 0, ITS supports 16-bit collection ID */
		if (id >= BIT_ULL(16))
			return false;
		break;
	default:
		return false;
	}

	if (!(baser & GITS_BASER_INDIRECT)) {
		phys_addr_t addr;

		if (id >= (l1_tbl_size / esz))
			return false;

		addr = BASER_ADDRESS(baser) + id * esz;
		gfn = addr >> PAGE_SHIFT;

		return kvm_is_visible_gfn(its->dev->kvm, gfn);
	}

	/* calculate and check the index into the 1st level */
	index = id / (SZ_64K / esz);
	if (index >= (l1_tbl_size / sizeof(u64)))
		return false;

	/* Each 1st level entry is represented by a 64-bit value. */
	if (kvm_read_guest(its->dev->kvm,
			   BASER_ADDRESS(baser) + index * sizeof(indirect_ptr),
			   &indirect_ptr, sizeof(indirect_ptr)))
		return false;

	indirect_ptr = le64_to_cpu(indirect_ptr);

	/* check the valid bit of the first level entry */
	if (!(indirect_ptr & BIT_ULL(63)))
		return false;

	/*
	 * Mask the guest physical address and calculate the frame number.
	 * Any address beyond our supported 48 bits of PA will be caught
	 * by the actual check in the final step.
	 */
	indirect_ptr &= GENMASK_ULL(51, 16);

	/* Find the address of the actual entry */
	index = id % (SZ_64K / esz);
	indirect_ptr += index * esz;
	gfn = indirect_ptr >> PAGE_SHIFT;

	return kvm_is_visible_gfn(its->dev->kvm, gfn);
}

static int vgic_its_alloc_collection(struct vgic_its *its,
				     struct its_collection **colp,
				     u32 coll_id)
{
	struct its_collection *collection;

	if (!vgic_its_check_id(its, its->baser_coll_table, coll_id))
		return E_ITS_MAPC_COLLECTION_OOR;

	collection = kzalloc(sizeof(*collection), GFP_KERNEL);

	collection->collection_id = coll_id;
	collection->target_addr = COLLECTION_NOT_MAPPED;

	list_add_tail(&collection->coll_list, &its->collection_list);
	*colp = collection;

	return 0;
}

static void vgic_its_free_collection(struct vgic_its *its, u32 coll_id)
{
	struct its_collection *collection;
	struct its_device *device;
	struct its_ite *ite;

	/*
	 * Clearing the mapping for that collection ID removes the
	 * entry from the list. If there wasn't any before, we can
	 * go home early.
	 */
	collection = find_collection(its, coll_id);
	if (!collection)
		return;

	for_each_lpi_its(device, ite, its)
		if (ite->collection &&
		    ite->collection->collection_id == coll_id)
			ite->collection = NULL;

	list_del(&collection->coll_list);
	kfree(collection);
}

/*
 * The MAPTI and MAPI commands map LPIs to ITTEs.
 * Must be called with its_lock mutex held.
 */
static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its,
				    u64 *its_cmd)
{
	u32 device_id = its_cmd_get_deviceid(its_cmd);
	u32 event_id = its_cmd_get_id(its_cmd);
	u32 coll_id = its_cmd_get_collection(its_cmd);
	struct its_ite *ite;
	struct kvm_vcpu *vcpu = NULL;
	struct its_device *device;
	struct its_collection *collection, *new_coll = NULL;
	int lpi_nr;
	struct vgic_irq *irq;

	device = find_its_device(its, device_id);
	if (!device)
		return E_ITS_MAPTI_UNMAPPED_DEVICE;

	if (event_id >= BIT_ULL(device->num_eventid_bits))
		return E_ITS_MAPTI_ID_OOR;

	if (its_cmd_get_command(its_cmd) == GITS_CMD_MAPTI)
		lpi_nr = its_cmd_get_physical_id(its_cmd);
	else
		lpi_nr = event_id;
	if (lpi_nr < GIC_LPI_OFFSET ||
	    lpi_nr >= max_lpis_propbaser(kvm->arch.vgic.propbaser))
		return E_ITS_MAPTI_PHYSICALID_OOR;

	/* If there is an existing mapping, behavior is UNPREDICTABLE. */
	if (find_ite(its, device_id, event_id))
		return 0;

	collection = find_collection(its, coll_id);
	if (!collection) {
		int ret = vgic_its_alloc_collection(its, &collection, coll_id);
		if (ret)
			return ret;
		new_coll = collection;
	}

	ite = kzalloc(sizeof(struct its_ite), GFP_KERNEL);
	if (!ite) {
		if (new_coll)
			vgic_its_free_collection(its, coll_id);
		return -ENOMEM;
	}

	ite->event_id	= event_id;
	list_add_tail(&ite->ite_list, &device->itt_head);

	ite->collection = collection;
	ite->lpi = lpi_nr;

	if (its_is_collection_mapped(collection))
		vcpu = kvm_get_vcpu(kvm, collection->target_addr);

	irq = vgic_add_lpi(kvm, lpi_nr, vcpu);
	if (IS_ERR(irq)) {
		if (new_coll)
			vgic_its_free_collection(its, coll_id);
		its_free_ite(kvm, ite);
		return PTR_ERR(irq);
	}
	ite->irq = irq;

	return 0;
}

/* Requires the its_lock to be held. */
static void vgic_its_unmap_device(struct kvm *kvm, struct its_device *device)
{
	struct its_ite *ite, *temp;

	/*
	 * The spec says that unmapping a device with still valid
	 * ITTEs associated is UNPREDICTABLE. We remove all ITTEs,
	 * since we cannot leave the memory unreferenced.
	 */
	list_for_each_entry_safe(ite, temp, &device->itt_head, ite_list)
		its_free_ite(kvm, ite);

	list_del(&device->dev_list);
	kfree(device);
}

/*
 * MAPD maps or unmaps a device ID to Interrupt Translation Tables (ITTs).
 * Must be called with the its_lock mutex held.
 */
static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its,
				    u64 *its_cmd)
{
	u32 device_id = its_cmd_get_deviceid(its_cmd);
	bool valid = its_cmd_get_validbit(its_cmd);
	u8 num_eventid_bits = its_cmd_get_size(its_cmd);
	gpa_t itt_addr = its_cmd_get_ittaddr(its_cmd);
	struct its_device *device;

	if (!vgic_its_check_id(its, its->baser_device_table, device_id))
		return E_ITS_MAPD_DEVICE_OOR;

	if (valid && num_eventid_bits > VITS_TYPER_IDBITS)
		return E_ITS_MAPD_ITTSIZE_OOR;

	device = find_its_device(its, device_id);

	/*
	 * The spec says that calling MAPD on an already mapped device
	 * invalidates all cached data for this device. We implement this
	 * by removing the mapping and re-establishing it.
	 */
	if (device)
		vgic_its_unmap_device(kvm, device);

	/*
	 * The spec does not say whether unmapping a not-mapped device
	 * is an error, so we are done in any case.
	 */
	if (!valid)
		return 0;

	device = kzalloc(sizeof(struct its_device), GFP_KERNEL);
	if (!device)
		return -ENOMEM;

	device->device_id = device_id;
	device->num_eventid_bits = num_eventid_bits;
	device->itt_addr = itt_addr;

	INIT_LIST_HEAD(&device->itt_head);

	list_add_tail(&device->dev_list, &its->device_list);

	return 0;
}

/*
 * The MAPC command maps collection IDs to redistributors.
 * Must be called with the its_lock mutex held.
 */
static int vgic_its_cmd_handle_mapc(struct kvm *kvm, struct vgic_its *its,
				    u64 *its_cmd)
{
	u16 coll_id;
	u32 target_addr;
	struct its_collection *collection;
	bool valid;

	valid = its_cmd_get_validbit(its_cmd);
	coll_id = its_cmd_get_collection(its_cmd);
	target_addr = its_cmd_get_target_addr(its_cmd);

	if (target_addr >= atomic_read(&kvm->online_vcpus))
		return E_ITS_MAPC_PROCNUM_OOR;

	if (!valid) {
		vgic_its_free_collection(its, coll_id);
	} else {
		collection = find_collection(its, coll_id);

		if (!collection) {
			int ret;

			ret = vgic_its_alloc_collection(its, &collection,
							coll_id);
			if (ret)
				return ret;
			collection->target_addr = target_addr;
		} else {
			collection->target_addr = target_addr;
			update_affinity_collection(kvm, its, collection);
		}
	}

	return 0;
}

/*
 * The CLEAR command removes the pending state for a particular LPI.
 * Must be called with the its_lock mutex held.
 */
static int vgic_its_cmd_handle_clear(struct kvm *kvm, struct vgic_its *its,
				     u64 *its_cmd)
{
	u32 device_id = its_cmd_get_deviceid(its_cmd);
	u32 event_id = its_cmd_get_id(its_cmd);
	struct its_ite *ite;


	ite = find_ite(its, device_id, event_id);
	if (!ite)
		return E_ITS_CLEAR_UNMAPPED_INTERRUPT;

	ite->irq->pending_latch = false;

	return 0;
}

/*
 * The INV command syncs the configuration bits from the memory table.
 * Must be called with the its_lock mutex held.
 */
static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its,
				   u64 *its_cmd)
{
	u32 device_id = its_cmd_get_deviceid(its_cmd);
	u32 event_id = its_cmd_get_id(its_cmd);
	struct its_ite *ite;


	ite = find_ite(its, device_id, event_id);
	if (!ite)
		return E_ITS_INV_UNMAPPED_INTERRUPT;

	return update_lpi_config(kvm, ite->irq, NULL);
}

/*
 * The INVALL command requests flushing of all IRQ data in this collection.
 * Find the VCPU mapped to that collection, then iterate over the VM's list
 * of mapped LPIs and update the configuration for each IRQ which targets
 * the specified vcpu. The configuration will be read from the in-memory
 * configuration table.
 * Must be called with the its_lock mutex held.
 */
static int vgic_its_cmd_handle_invall(struct kvm *kvm, struct vgic_its *its,
				      u64 *its_cmd)
{
	u32 coll_id = its_cmd_get_collection(its_cmd);
	struct its_collection *collection;
	struct kvm_vcpu *vcpu;
	struct vgic_irq *irq;
	u32 *intids;
	int irq_count, i;

	collection = find_collection(its, coll_id);
	if (!its_is_collection_mapped(collection))
		return E_ITS_INVALL_UNMAPPED_COLLECTION;

	vcpu = kvm_get_vcpu(kvm, collection->target_addr);

	irq_count = vgic_copy_lpi_list(kvm, &intids);
	if (irq_count < 0)
		return irq_count;

	for (i = 0; i < irq_count; i++) {
		irq = vgic_get_irq(kvm, NULL, intids[i]);
		if (!irq)
			continue;
		update_lpi_config(kvm, irq, vcpu);
		vgic_put_irq(kvm, irq);
	}

	kfree(intids);

	return 0;
}

/*
 * The MOVALL command moves the pending state of all IRQs targeting one
 * redistributor to another. We don't hold the pending state in the VCPUs,
 * but in the IRQs instead, so there is really not much to do for us here.
 * However the spec says that no IRQ must target the old redistributor
 * afterwards, so we make sure that no LPI is using the associated target_vcpu.
 * This command affects all LPIs in the system that target that redistributor.
 */
static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its,
				      u64 *its_cmd)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	u32 target1_addr = its_cmd_get_target_addr(its_cmd);
	u32 target2_addr = its_cmd_mask_field(its_cmd, 3, 16, 32);
	struct kvm_vcpu *vcpu1, *vcpu2;
	struct vgic_irq *irq;

	if (target1_addr >= atomic_read(&kvm->online_vcpus) ||
	    target2_addr >= atomic_read(&kvm->online_vcpus))
		return E_ITS_MOVALL_PROCNUM_OOR;

	if (target1_addr == target2_addr)
		return 0;

	vcpu1 = kvm_get_vcpu(kvm, target1_addr);
	vcpu2 = kvm_get_vcpu(kvm, target2_addr);

	spin_lock(&dist->lpi_list_lock);

	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
		spin_lock(&irq->irq_lock);

		if (irq->target_vcpu == vcpu1)
			irq->target_vcpu = vcpu2;

		spin_unlock(&irq->irq_lock);
	}

	spin_unlock(&dist->lpi_list_lock);

	return 0;
}

/*
 * The INT command injects the LPI associated with that DevID/EvID pair.
 * Must be called with the its_lock mutex held.
 */
static int vgic_its_cmd_handle_int(struct kvm *kvm, struct vgic_its *its,
				   u64 *its_cmd)
{
	u32 msi_data = its_cmd_get_id(its_cmd);
	u64 msi_devid = its_cmd_get_deviceid(its_cmd);

	return vgic_its_trigger_msi(kvm, its, msi_devid, msi_data);
}

/*
 * This function is called with the its_cmd lock held, but the ITS data
 * structure lock dropped.
 */
static int vgic_its_handle_command(struct kvm *kvm, struct vgic_its *its,
				   u64 *its_cmd)
{
	int ret = -ENODEV;

	mutex_lock(&its->its_lock);
	switch (its_cmd_get_command(its_cmd)) {
	case GITS_CMD_MAPD:
		ret = vgic_its_cmd_handle_mapd(kvm, its, its_cmd);
		break;
	case GITS_CMD_MAPC:
		ret = vgic_its_cmd_handle_mapc(kvm, its, its_cmd);
		break;
	case GITS_CMD_MAPI:
		ret = vgic_its_cmd_handle_mapi(kvm, its, its_cmd);
		break;
	case GITS_CMD_MAPTI:
		ret = vgic_its_cmd_handle_mapi(kvm, its, its_cmd);
		break;
	case GITS_CMD_MOVI:
		ret = vgic_its_cmd_handle_movi(kvm, its, its_cmd);
		break;
	case GITS_CMD_DISCARD:
		ret = vgic_its_cmd_handle_discard(kvm, its, its_cmd);
		break;
	case GITS_CMD_CLEAR:
		ret = vgic_its_cmd_handle_clear(kvm, its, its_cmd);
		break;
	case GITS_CMD_MOVALL:
		ret = vgic_its_cmd_handle_movall(kvm, its, its_cmd);
		break;
	case GITS_CMD_INT:
		ret = vgic_its_cmd_handle_int(kvm, its, its_cmd);
		break;
	case GITS_CMD_INV:
		ret = vgic_its_cmd_handle_inv(kvm, its, its_cmd);
		break;
	case GITS_CMD_INVALL:
		ret = vgic_its_cmd_handle_invall(kvm, its, its_cmd);
		break;
	case GITS_CMD_SYNC:
		/* we ignore this command: we are in sync all of the time */
		ret = 0;
		break;
	}
	mutex_unlock(&its->its_lock);

	return ret;
}

static u64 vgic_sanitise_its_baser(u64 reg)
{
	reg = vgic_sanitise_field(reg, GITS_BASER_SHAREABILITY_MASK,
				  GITS_BASER_SHAREABILITY_SHIFT,
				  vgic_sanitise_shareability);
	reg = vgic_sanitise_field(reg, GITS_BASER_INNER_CACHEABILITY_MASK,
				  GITS_BASER_INNER_CACHEABILITY_SHIFT,
				  vgic_sanitise_inner_cacheability);
	reg = vgic_sanitise_field(reg, GITS_BASER_OUTER_CACHEABILITY_MASK,
				  GITS_BASER_OUTER_CACHEABILITY_SHIFT,
				  vgic_sanitise_outer_cacheability);

	/* Bits 15:12 contain bits 51:48 of the PA, which we don't support. */
	reg &= ~GENMASK_ULL(15, 12);

	/* We support only one (ITS) page size: 64K */
	reg = (reg & ~GITS_BASER_PAGE_SIZE_MASK) | GITS_BASER_PAGE_SIZE_64K;

	return reg;
}

static u64 vgic_sanitise_its_cbaser(u64 reg)
{
	reg = vgic_sanitise_field(reg, GITS_CBASER_SHAREABILITY_MASK,
				  GITS_CBASER_SHAREABILITY_SHIFT,
				  vgic_sanitise_shareability);
	reg = vgic_sanitise_field(reg, GITS_CBASER_INNER_CACHEABILITY_MASK,
				  GITS_CBASER_INNER_CACHEABILITY_SHIFT,
				  vgic_sanitise_inner_cacheability);
	reg = vgic_sanitise_field(reg, GITS_CBASER_OUTER_CACHEABILITY_MASK,
				  GITS_CBASER_OUTER_CACHEABILITY_SHIFT,
				  vgic_sanitise_outer_cacheability);

	/*
	 * Sanitise the physical address to be 64k aligned.
	 * Also limit the physical addresses to 48 bits.
	 */
	reg &= ~(GENMASK_ULL(51, 48) | GENMASK_ULL(15, 12));

	return reg;
}

static unsigned long vgic_mmio_read_its_cbaser(struct kvm *kvm,
					       struct vgic_its *its,
					       gpa_t addr, unsigned int len)
{
	return extract_bytes(its->cbaser, addr & 7, len);
}

static void vgic_mmio_write_its_cbaser(struct kvm *kvm, struct vgic_its *its,
				       gpa_t addr, unsigned int len,
				       unsigned long val)
{
	/* When GITS_CTLR.Enable is 1, this register is RO. */
	if (its->enabled)
		return;

	mutex_lock(&its->cmd_lock);
	its->cbaser = update_64bit_reg(its->cbaser, addr & 7, len, val);
	its->cbaser = vgic_sanitise_its_cbaser(its->cbaser);
	its->creadr = 0;
	/*
	 * CWRITER is architecturally UNKNOWN on reset, but we need to reset
	 * it to CREADR to make sure we start with an empty command buffer.
	 */
	its->cwriter = its->creadr;
	mutex_unlock(&its->cmd_lock);
}

#define ITS_CMD_BUFFER_SIZE(baser)	((((baser) & 0xff) + 1) << 12)
#define ITS_CMD_SIZE			32
#define ITS_CMD_OFFSET(reg)		((reg) & GENMASK(19, 5))

/* Must be called with the cmd_lock held. */
static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its)
{
	gpa_t cbaser;
	u64 cmd_buf[4];

	/* Commands are only processed when the ITS is enabled. */
	if (!its->enabled)
		return;

	cbaser = CBASER_ADDRESS(its->cbaser);

	while (its->cwriter != its->creadr) {
		int ret = kvm_read_guest(kvm, cbaser + its->creadr,
					 cmd_buf, ITS_CMD_SIZE);
		/*
		 * If kvm_read_guest() fails, this could be due to the guest
		 * programming a bogus value in CBASER or something else going
		 * wrong from which we cannot easily recover.
		 * According to section 6.3.2 in the GICv3 spec we can just
		 * ignore that command then.
		 */
		if (!ret)
			vgic_its_handle_command(kvm, its, cmd_buf);

		its->creadr += ITS_CMD_SIZE;
		if (its->creadr == ITS_CMD_BUFFER_SIZE(its->cbaser))
			its->creadr = 0;
	}
}

/*
 * By writing to CWRITER the guest announces new commands to be processed.
 * To avoid any races in the first place, we take the its_cmd lock, which
 * protects our ring buffer variables, so that there is only one user
 * per ITS handling commands at a given time.
 */
static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its,
					gpa_t addr, unsigned int len,
					unsigned long val)
{
	u64 reg;

	if (!its)
		return;

	mutex_lock(&its->cmd_lock);

	reg = update_64bit_reg(its->cwriter, addr & 7, len, val);
	reg = ITS_CMD_OFFSET(reg);
	if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) {
		mutex_unlock(&its->cmd_lock);
		return;
	}
	its->cwriter = reg;

	vgic_its_process_commands(kvm, its);

	mutex_unlock(&its->cmd_lock);
}

static unsigned long vgic_mmio_read_its_cwriter(struct kvm *kvm,
						struct vgic_its *its,
						gpa_t addr, unsigned int len)
{
	return extract_bytes(its->cwriter, addr & 0x7, len);
}

static unsigned long vgic_mmio_read_its_creadr(struct kvm *kvm,
					       struct vgic_its *its,
					       gpa_t addr, unsigned int len)
{
	return extract_bytes(its->creadr, addr & 0x7, len);
}

static int vgic_mmio_uaccess_write_its_creadr(struct kvm *kvm,
					      struct vgic_its *its,
					      gpa_t addr, unsigned int len,
					      unsigned long val)
{
	u32 cmd_offset;
	int ret = 0;

	mutex_lock(&its->cmd_lock);

	if (its->enabled) {
		ret = -EBUSY;
		goto out;
	}

	cmd_offset = ITS_CMD_OFFSET(val);
	if (cmd_offset >= ITS_CMD_BUFFER_SIZE(its->cbaser)) {
		ret = -EINVAL;
		goto out;
	}

	its->creadr = cmd_offset;
out:
	mutex_unlock(&its->cmd_lock);
	return ret;
}

#define BASER_INDEX(addr) (((addr) / sizeof(u64)) & 0x7)
static unsigned long vgic_mmio_read_its_baser(struct kvm *kvm,
					      struct vgic_its *its,
					      gpa_t addr, unsigned int len)
{
	u64 reg;

	switch (BASER_INDEX(addr)) {
	case 0:
		reg = its->baser_device_table;
		break;
	case 1:
		reg = its->baser_coll_table;
		break;
	default:
		reg = 0;
		break;
	}

	return extract_bytes(reg, addr & 7, len);
}

#define GITS_BASER_RO_MASK	(GENMASK_ULL(52, 48) | GENMASK_ULL(58, 56))
static void vgic_mmio_write_its_baser(struct kvm *kvm,
				      struct vgic_its *its,
				      gpa_t addr, unsigned int len,
				      unsigned long val)
{
	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
	u64 entry_size, device_type;
	u64 reg, *regptr, clearbits = 0;

	/* When GITS_CTLR.Enable is 1, we ignore write accesses. */
	if (its->enabled)
		return;

	switch (BASER_INDEX(addr)) {
	case 0:
		regptr = &its->baser_device_table;
		entry_size = abi->dte_esz;
		device_type = GITS_BASER_TYPE_DEVICE;
		break;
	case 1:
		regptr = &its->baser_coll_table;
		entry_size = abi->cte_esz;
		device_type = GITS_BASER_TYPE_COLLECTION;
		clearbits = GITS_BASER_INDIRECT;
		break;
	default:
		return;
	}

	reg = update_64bit_reg(*regptr, addr & 7, len, val);
	reg &= ~GITS_BASER_RO_MASK;
	reg &= ~clearbits;

	reg |= (entry_size - 1) << GITS_BASER_ENTRY_SIZE_SHIFT;
	reg |= device_type << GITS_BASER_TYPE_SHIFT;
	reg = vgic_sanitise_its_baser(reg);

	*regptr = reg;
}

static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu,
					     struct vgic_its *its,
					     gpa_t addr, unsigned int len)
{
	u32 reg = 0;

	mutex_lock(&its->cmd_lock);
	if (its->creadr == its->cwriter)
		reg |= GITS_CTLR_QUIESCENT;
	if (its->enabled)
		reg |= GITS_CTLR_ENABLE;
	mutex_unlock(&its->cmd_lock);

	return reg;
}

static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its,
				     gpa_t addr, unsigned int len,
				     unsigned long val)
{
	mutex_lock(&its->cmd_lock);

	its->enabled = !!(val & GITS_CTLR_ENABLE);

	/*
	 * Try to process any pending commands. This function bails out early
	 * if the ITS is disabled or no commands have been queued.
	 */
	vgic_its_process_commands(kvm, its);

	mutex_unlock(&its->cmd_lock);
}

#define REGISTER_ITS_DESC(off, rd, wr, length, acc)		\
{								\
	.reg_offset = off,					\
	.len = length,						\
	.access_flags = acc,					\
	.its_read = rd,						\
	.its_write = wr,					\
}

#define REGISTER_ITS_DESC_UACCESS(off, rd, wr, uwr, length, acc)\
{								\
	.reg_offset = off,					\
	.len = length,						\
	.access_flags = acc,					\
	.its_read = rd,						\
	.its_write = wr,					\
	.uaccess_its_write = uwr,				\
}

static void its_mmio_write_wi(struct kvm *kvm, struct vgic_its *its,
			      gpa_t addr, unsigned int len, unsigned long val)
{
	/* Ignore */
}

static struct vgic_register_region its_registers[] = {
	REGISTER_ITS_DESC(GITS_CTLR,
		vgic_mmio_read_its_ctlr, vgic_mmio_write_its_ctlr, 4,
		VGIC_ACCESS_32bit),
	REGISTER_ITS_DESC_UACCESS(GITS_IIDR,
		vgic_mmio_read_its_iidr, its_mmio_write_wi,
		vgic_mmio_uaccess_write_its_iidr, 4,
		VGIC_ACCESS_32bit),
	REGISTER_ITS_DESC(GITS_TYPER,
		vgic_mmio_read_its_typer, its_mmio_write_wi, 8,
		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
	REGISTER_ITS_DESC(GITS_CBASER,
		vgic_mmio_read_its_cbaser, vgic_mmio_write_its_cbaser, 8,
		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
	REGISTER_ITS_DESC(GITS_CWRITER,
		vgic_mmio_read_its_cwriter, vgic_mmio_write_its_cwriter, 8,
		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
	REGISTER_ITS_DESC_UACCESS(GITS_CREADR,
		vgic_mmio_read_its_creadr, its_mmio_write_wi,
		vgic_mmio_uaccess_write_its_creadr, 8,
		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
	REGISTER_ITS_DESC(GITS_BASER,
		vgic_mmio_read_its_baser, vgic_mmio_write_its_baser, 0x40,
		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
	REGISTER_ITS_DESC(GITS_IDREGS_BASE,
		vgic_mmio_read_its_idregs, its_mmio_write_wi, 0x30,
		VGIC_ACCESS_32bit),
};

/* This is called on setting the LPI enable bit in the redistributor. */
void vgic_enable_lpis(struct kvm_vcpu *vcpu)
{
	if (!(vcpu->arch.vgic_cpu.pendbaser & GICR_PENDBASER_PTZ))
		its_sync_lpi_pending_table(vcpu);
}

static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its)
{
	struct vgic_io_device *iodev = &its->iodev;
	int ret;

	if (!its->initialized)
		return -EBUSY;

	if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base))
		return -ENXIO;

	iodev->regions = its_registers;
	iodev->nr_regions = ARRAY_SIZE(its_registers);
	kvm_iodevice_init(&iodev->dev, &kvm_io_gic_ops);

	iodev->base_addr = its->vgic_its_base;
	iodev->iodev_type = IODEV_ITS;
	iodev->its = its;
	mutex_lock(&kvm->slots_lock);
	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, iodev->base_addr,
				      KVM_VGIC_V3_ITS_SIZE, &iodev->dev);
	mutex_unlock(&kvm->slots_lock);

	return ret;
}

#define INITIAL_BASER_VALUE						  \
	(GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWb)		| \
	 GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, SameAsInner)		| \
	 GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)		| \
	 GITS_BASER_PAGE_SIZE_64K)

#define INITIAL_PROPBASER_VALUE						  \
	(GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWb)		| \
	 GIC_BASER_CACHEABILITY(GICR_PROPBASER, OUTER, SameAsInner)	| \
	 GIC_BASER_SHAREABILITY(GICR_PROPBASER, InnerShareable))

static int vgic_its_create(struct kvm_device *dev, u32 type)
{
	struct vgic_its *its;

	if (type != KVM_DEV_TYPE_ARM_VGIC_ITS)
		return -ENODEV;

	its = kzalloc(sizeof(struct vgic_its), GFP_KERNEL);
	if (!its)
		return -ENOMEM;

	mutex_init(&its->its_lock);
	mutex_init(&its->cmd_lock);

	its->vgic_its_base = VGIC_ADDR_UNDEF;

	INIT_LIST_HEAD(&its->device_list);
	INIT_LIST_HEAD(&its->collection_list);

	dev->kvm->arch.vgic.has_its = true;
	its->initialized = false;
	its->enabled = false;
	its->dev = dev;

	its->baser_device_table = INITIAL_BASER_VALUE			|
		((u64)GITS_BASER_TYPE_DEVICE << GITS_BASER_TYPE_SHIFT);
	its->baser_coll_table = INITIAL_BASER_VALUE |
		((u64)GITS_BASER_TYPE_COLLECTION << GITS_BASER_TYPE_SHIFT);
	dev->kvm->arch.vgic.propbaser = INITIAL_PROPBASER_VALUE;

	dev->private = its;

	return vgic_its_set_abi(its, NR_ITS_ABIS - 1);
}

static void vgic_its_destroy(struct kvm_device *kvm_dev)
{
	struct kvm *kvm = kvm_dev->kvm;
	struct vgic_its *its = kvm_dev->private;
	struct its_device *dev;
	struct its_ite *ite;
	struct list_head *dev_cur, *dev_temp;
	struct list_head *cur, *temp;

	/*
	 * We may end up here without the lists ever having been initialized.
	 * Check this and bail out early to avoid dereferencing a NULL pointer.
	 */
	if (!its->device_list.next)
		return;

	mutex_lock(&its->its_lock);
	list_for_each_safe(dev_cur, dev_temp, &its->device_list) {
		dev = container_of(dev_cur, struct its_device, dev_list);
		list_for_each_safe(cur, temp, &dev->itt_head) {
			ite = (container_of(cur, struct its_ite, ite_list));
			its_free_ite(kvm, ite);
		}
		list_del(dev_cur);
		kfree(dev);
	}

	list_for_each_safe(cur, temp, &its->collection_list) {
		list_del(cur);
		kfree(container_of(cur, struct its_collection, coll_list));
	}
	mutex_unlock(&its->its_lock);

	kfree(its);
}

int vgic_its_has_attr_regs(struct kvm_device *dev,
			   struct kvm_device_attr *attr)
{
	const struct vgic_register_region *region;
	gpa_t offset = attr->attr;
	int align;

	align = (offset < GITS_TYPER) || (offset >= GITS_PIDR4) ? 0x3 : 0x7;

	if (offset & align)
		return -EINVAL;

	region = vgic_find_mmio_region(its_registers,
				       ARRAY_SIZE(its_registers),
				       offset);
	if (!region)
		return -ENXIO;

	return 0;
}

int vgic_its_attr_regs_access(struct kvm_device *dev,
			      struct kvm_device_attr *attr,
			      u64 *reg, bool is_write)
{
	const struct vgic_register_region *region;
	struct vgic_its *its;
	gpa_t addr, offset;
	unsigned int len;
	int align, ret = 0;

	its = dev->private;
	offset = attr->attr;

	/*
	 * Although the spec supports upper/lower 32-bit accesses to
	 * 64-bit ITS registers, the userspace ABI requires 64-bit
	 * accesses to all 64-bit wide registers. We therefore only
	 * support 32-bit accesses to GITS_CTLR, GITS_IIDR and GITS ID
	 * registers
	 */
	if ((offset < GITS_TYPER) || (offset >= GITS_PIDR4))
		align = 0x3;
	else
		align = 0x7;

	if (offset & align)
		return -EINVAL;

	mutex_lock(&dev->kvm->lock);

	if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) {
		ret = -ENXIO;
		goto out;
	}

	region = vgic_find_mmio_region(its_registers,
				       ARRAY_SIZE(its_registers),
				       offset);
	if (!region) {
		ret = -ENXIO;
		goto out;
	}

	if (!lock_all_vcpus(dev->kvm)) {
		ret = -EBUSY;
		goto out;
	}

	addr = its->vgic_its_base + offset;

	len = region->access_flags & VGIC_ACCESS_64bit ? 8 : 4;

	if (is_write) {
		if (region->uaccess_its_write)
			ret = region->uaccess_its_write(dev->kvm, its, addr,
							len, *reg);
		else
			region->its_write(dev->kvm, its, addr, len, *reg);
	} else {
		*reg = region->its_read(dev->kvm, its, addr, len);
	}
	unlock_all_vcpus(dev->kvm);
out:
	mutex_unlock(&dev->kvm->lock);
	return ret;
}

/**
 * vgic_its_save_tables_v0 - Save the ITS tables into guest ARM
 * according to v0 ABI
 */
static int vgic_its_save_tables_v0(struct vgic_its *its)
{
	return -ENXIO;
}

/**
 * vgic_its_restore_tables_v0 - Restore the ITS tables from guest RAM
 * to internal data structs according to V0 ABI
 *
 */
static int vgic_its_restore_tables_v0(struct vgic_its *its)
{
	return -ENXIO;
}

static int vgic_its_commit_v0(struct vgic_its *its)
{
	const struct vgic_its_abi *abi;

	abi = vgic_its_get_abi(its);
	its->baser_coll_table &= ~GITS_BASER_ENTRY_SIZE_MASK;
	its->baser_device_table &= ~GITS_BASER_ENTRY_SIZE_MASK;

	its->baser_coll_table |= (GIC_ENCODE_SZ(abi->cte_esz, 5)
					<< GITS_BASER_ENTRY_SIZE_SHIFT);

	its->baser_device_table |= (GIC_ENCODE_SZ(abi->dte_esz, 5)
					<< GITS_BASER_ENTRY_SIZE_SHIFT);
	return 0;
}

static int vgic_its_has_attr(struct kvm_device *dev,
			     struct kvm_device_attr *attr)
{
	switch (attr->group) {
	case KVM_DEV_ARM_VGIC_GRP_ADDR:
		switch (attr->attr) {
		case KVM_VGIC_ITS_ADDR_TYPE:
			return 0;
		}
		break;
	case KVM_DEV_ARM_VGIC_GRP_CTRL:
		switch (attr->attr) {
		case KVM_DEV_ARM_VGIC_CTRL_INIT:
			return 0;
		}
		break;
	case KVM_DEV_ARM_VGIC_GRP_ITS_REGS:
		return vgic_its_has_attr_regs(dev, attr);
	}
	return -ENXIO;
}

static int vgic_its_set_attr(struct kvm_device *dev,
			     struct kvm_device_attr *attr)
{
	struct vgic_its *its = dev->private;
	int ret;

	switch (attr->group) {
	case KVM_DEV_ARM_VGIC_GRP_ADDR: {
		u64 __user *uaddr = (u64 __user *)(long)attr->addr;
		unsigned long type = (unsigned long)attr->attr;
		u64 addr;

		if (type != KVM_VGIC_ITS_ADDR_TYPE)
			return -ENODEV;

		if (copy_from_user(&addr, uaddr, sizeof(addr)))
			return -EFAULT;

		ret = vgic_check_ioaddr(dev->kvm, &its->vgic_its_base,
					addr, SZ_64K);
		if (ret)
			return ret;

		its->vgic_its_base = addr;

		return 0;
	}
	case KVM_DEV_ARM_VGIC_GRP_CTRL:
		switch (attr->attr) {
		case KVM_DEV_ARM_VGIC_CTRL_INIT:
			its->initialized = true;

			return 0;
		}
		break;
	case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: {
		u64 __user *uaddr = (u64 __user *)(long)attr->addr;
		u64 reg;

		if (get_user(reg, uaddr))
			return -EFAULT;

		return vgic_its_attr_regs_access(dev, attr, &reg, true);
	}
	}
	return -ENXIO;
}

static int vgic_its_get_attr(struct kvm_device *dev,
			     struct kvm_device_attr *attr)
{
	switch (attr->group) {
	case KVM_DEV_ARM_VGIC_GRP_ADDR: {
		struct vgic_its *its = dev->private;
		u64 addr = its->vgic_its_base;
		u64 __user *uaddr = (u64 __user *)(long)attr->addr;
		unsigned long type = (unsigned long)attr->attr;

		if (type != KVM_VGIC_ITS_ADDR_TYPE)
			return -ENODEV;

		if (copy_to_user(uaddr, &addr, sizeof(addr)))
			return -EFAULT;
		break;
	}
	case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: {
		u64 __user *uaddr = (u64 __user *)(long)attr->addr;
		u64 reg;
		int ret;

		ret = vgic_its_attr_regs_access(dev, attr, &reg, false);
		if (ret)
			return ret;
		return put_user(reg, uaddr);
	}
	default:
		return -ENXIO;
	}

	return 0;
}

static struct kvm_device_ops kvm_arm_vgic_its_ops = {
	.name = "kvm-arm-vgic-its",
	.create = vgic_its_create,
	.destroy = vgic_its_destroy,
	.set_attr = vgic_its_set_attr,
	.get_attr = vgic_its_get_attr,
	.has_attr = vgic_its_has_attr,
};

int kvm_vgic_register_its_device(void)
{
	return kvm_register_device_ops(&kvm_arm_vgic_its_ops,
				       KVM_DEV_TYPE_ARM_VGIC_ITS);
}

/*
 * Registers all ITSes with the kvm_io_bus framework.
 * To follow the existing VGIC initialization sequence, this has to be
 * done as late as possible, just before the first VCPU runs.
 */
int vgic_register_its_iodevs(struct kvm *kvm)
{
	struct kvm_device *dev;
	int ret = 0;

	list_for_each_entry(dev, &kvm->devices, vm_node) {
		if (dev->ops != &kvm_arm_vgic_its_ops)
			continue;

		ret = vgic_register_its_iodev(kvm, dev->private);
		if (ret)
			return ret;
		/*
		 * We don't need to care about tearing down previously
		 * registered ITSes, as the kvm_io_bus framework removes
		 * them for us if the VM gets destroyed.
		 */
	}

	return ret;
}