summaryrefslogtreecommitdiff
path: root/virt/kvm/arm/vgic.c
blob: 2efba823137512a691e0438270366d41ea22613d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
/*
 * Copyright (C) 2012 ARM Ltd.
 * Author: Marc Zyngier <marc.zyngier@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, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
 */

#include <linux/cpu.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
#include <linux/uaccess.h>

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

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

/*
 * How the whole thing works (courtesy of Christoffer Dall):
 *
 * - At any time, the dist->irq_pending_on_cpu is the oracle that knows if
 *   something is pending on the CPU interface.
 * - Interrupts that are pending on the distributor are stored on the
 *   vgic.irq_pending vgic bitmap (this bitmap is updated by both user land
 *   ioctls and guest mmio ops, and other in-kernel peripherals such as the
 *   arch. timers).
 * - Every time the bitmap changes, the irq_pending_on_cpu oracle is
 *   recalculated
 * - To calculate the oracle, we need info for each cpu from
 *   compute_pending_for_cpu, which considers:
 *   - PPI: dist->irq_pending & dist->irq_enable
 *   - SPI: dist->irq_pending & dist->irq_enable & dist->irq_spi_target
 *   - irq_spi_target is a 'formatted' version of the GICD_ITARGETSRn
 *     registers, stored on each vcpu. We only keep one bit of
 *     information per interrupt, making sure that only one vcpu can
 *     accept the interrupt.
 * - If any of the above state changes, we must recalculate the oracle.
 * - The same is true when injecting an interrupt, except that we only
 *   consider a single interrupt at a time. The irq_spi_cpu array
 *   contains the target CPU for each SPI.
 *
 * The handling of level interrupts adds some extra complexity. We
 * need to track when the interrupt has been EOIed, so we can sample
 * the 'line' again. This is achieved as such:
 *
 * - When a level interrupt is moved onto a vcpu, the corresponding
 *   bit in irq_queued is set. As long as this bit is set, the line
 *   will be ignored for further interrupts. The interrupt is injected
 *   into the vcpu with the GICH_LR_EOI bit set (generate a
 *   maintenance interrupt on EOI).
 * - When the interrupt is EOIed, the maintenance interrupt fires,
 *   and clears the corresponding bit in irq_queued. This allows the
 *   interrupt line to be sampled again.
 * - Note that level-triggered interrupts can also be set to pending from
 *   writes to GICD_ISPENDRn and lowering the external input line does not
 *   cause the interrupt to become inactive in such a situation.
 *   Conversely, writes to GICD_ICPENDRn do not cause the interrupt to become
 *   inactive as long as the external input line is held high.
 */

#include "vgic.h"

static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu);
static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr);
static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc);

static const struct vgic_ops *vgic_ops;
static const struct vgic_params *vgic;

static void add_sgi_source(struct kvm_vcpu *vcpu, int irq, int source)
{
	vcpu->kvm->arch.vgic.vm_ops.add_sgi_source(vcpu, irq, source);
}

static bool queue_sgi(struct kvm_vcpu *vcpu, int irq)
{
	return vcpu->kvm->arch.vgic.vm_ops.queue_sgi(vcpu, irq);
}

int kvm_vgic_map_resources(struct kvm *kvm)
{
	return kvm->arch.vgic.vm_ops.map_resources(kvm, vgic);
}

/*
 * struct vgic_bitmap contains a bitmap made of unsigned longs, but
 * extracts u32s out of them.
 *
 * This does not work on 64-bit BE systems, because the bitmap access
 * will store two consecutive 32-bit words with the higher-addressed
 * register's bits at the lower index and the lower-addressed register's
 * bits at the higher index.
 *
 * Therefore, swizzle the register index when accessing the 32-bit word
 * registers to access the right register's value.
 */
#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 64
#define REG_OFFSET_SWIZZLE	1
#else
#define REG_OFFSET_SWIZZLE	0
#endif

static int vgic_init_bitmap(struct vgic_bitmap *b, int nr_cpus, int nr_irqs)
{
	int nr_longs;

	nr_longs = nr_cpus + BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS);

	b->private = kzalloc(sizeof(unsigned long) * nr_longs, GFP_KERNEL);
	if (!b->private)
		return -ENOMEM;

	b->shared = b->private + nr_cpus;

	return 0;
}

static void vgic_free_bitmap(struct vgic_bitmap *b)
{
	kfree(b->private);
	b->private = NULL;
	b->shared = NULL;
}

/*
 * Call this function to convert a u64 value to an unsigned long * bitmask
 * in a way that works on both 32-bit and 64-bit LE and BE platforms.
 *
 * Warning: Calling this function may modify *val.
 */
static unsigned long *u64_to_bitmask(u64 *val)
{
#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 32
	*val = (*val >> 32) | (*val << 32);
#endif
	return (unsigned long *)val;
}

u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x, int cpuid, u32 offset)
{
	offset >>= 2;
	if (!offset)
		return (u32 *)(x->private + cpuid) + REG_OFFSET_SWIZZLE;
	else
		return (u32 *)(x->shared) + ((offset - 1) ^ REG_OFFSET_SWIZZLE);
}

static int vgic_bitmap_get_irq_val(struct vgic_bitmap *x,
				   int cpuid, int irq)
{
	if (irq < VGIC_NR_PRIVATE_IRQS)
		return test_bit(irq, x->private + cpuid);

	return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared);
}

void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
			     int irq, int val)
{
	unsigned long *reg;

	if (irq < VGIC_NR_PRIVATE_IRQS) {
		reg = x->private + cpuid;
	} else {
		reg = x->shared;
		irq -= VGIC_NR_PRIVATE_IRQS;
	}

	if (val)
		set_bit(irq, reg);
	else
		clear_bit(irq, reg);
}

static unsigned long *vgic_bitmap_get_cpu_map(struct vgic_bitmap *x, int cpuid)
{
	return x->private + cpuid;
}

unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x)
{
	return x->shared;
}

static int vgic_init_bytemap(struct vgic_bytemap *x, int nr_cpus, int nr_irqs)
{
	int size;

	size  = nr_cpus * VGIC_NR_PRIVATE_IRQS;
	size += nr_irqs - VGIC_NR_PRIVATE_IRQS;

	x->private = kzalloc(size, GFP_KERNEL);
	if (!x->private)
		return -ENOMEM;

	x->shared = x->private + nr_cpus * VGIC_NR_PRIVATE_IRQS / sizeof(u32);
	return 0;
}

static void vgic_free_bytemap(struct vgic_bytemap *b)
{
	kfree(b->private);
	b->private = NULL;
	b->shared = NULL;
}

u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset)
{
	u32 *reg;

	if (offset < VGIC_NR_PRIVATE_IRQS) {
		reg = x->private;
		offset += cpuid * VGIC_NR_PRIVATE_IRQS;
	} else {
		reg = x->shared;
		offset -= VGIC_NR_PRIVATE_IRQS;
	}

	return reg + (offset / sizeof(u32));
}

#define VGIC_CFG_LEVEL	0
#define VGIC_CFG_EDGE	1

static bool vgic_irq_is_edge(struct kvm_vcpu *vcpu, int irq)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
	int irq_val;

	irq_val = vgic_bitmap_get_irq_val(&dist->irq_cfg, vcpu->vcpu_id, irq);
	return irq_val == VGIC_CFG_EDGE;
}

static int vgic_irq_is_enabled(struct kvm_vcpu *vcpu, int irq)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	return vgic_bitmap_get_irq_val(&dist->irq_enabled, vcpu->vcpu_id, irq);
}

static int vgic_irq_is_queued(struct kvm_vcpu *vcpu, int irq)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	return vgic_bitmap_get_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq);
}

static void vgic_irq_set_queued(struct kvm_vcpu *vcpu, int irq)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 1);
}

static void vgic_irq_clear_queued(struct kvm_vcpu *vcpu, int irq)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 0);
}

static int vgic_dist_irq_get_level(struct kvm_vcpu *vcpu, int irq)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	return vgic_bitmap_get_irq_val(&dist->irq_level, vcpu->vcpu_id, irq);
}

static void vgic_dist_irq_set_level(struct kvm_vcpu *vcpu, int irq)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 1);
}

static void vgic_dist_irq_clear_level(struct kvm_vcpu *vcpu, int irq)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 0);
}

static int vgic_dist_irq_soft_pend(struct kvm_vcpu *vcpu, int irq)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	return vgic_bitmap_get_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq);
}

static void vgic_dist_irq_clear_soft_pend(struct kvm_vcpu *vcpu, int irq)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	vgic_bitmap_set_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq, 0);
}

static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	return vgic_bitmap_get_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq);
}

void vgic_dist_irq_set_pending(struct kvm_vcpu *vcpu, int irq)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 1);
}

void vgic_dist_irq_clear_pending(struct kvm_vcpu *vcpu, int irq)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 0);
}

static void vgic_cpu_irq_set(struct kvm_vcpu *vcpu, int irq)
{
	if (irq < VGIC_NR_PRIVATE_IRQS)
		set_bit(irq, vcpu->arch.vgic_cpu.pending_percpu);
	else
		set_bit(irq - VGIC_NR_PRIVATE_IRQS,
			vcpu->arch.vgic_cpu.pending_shared);
}

void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq)
{
	if (irq < VGIC_NR_PRIVATE_IRQS)
		clear_bit(irq, vcpu->arch.vgic_cpu.pending_percpu);
	else
		clear_bit(irq - VGIC_NR_PRIVATE_IRQS,
			  vcpu->arch.vgic_cpu.pending_shared);
}

static bool vgic_can_sample_irq(struct kvm_vcpu *vcpu, int irq)
{
	return vgic_irq_is_edge(vcpu, irq) || !vgic_irq_is_queued(vcpu, irq);
}

/**
 * vgic_reg_access - access vgic register
 * @mmio:   pointer to the data describing the mmio access
 * @reg:    pointer to the virtual backing of vgic distributor data
 * @offset: least significant 2 bits used for word offset
 * @mode:   ACCESS_ mode (see defines above)
 *
 * Helper to make vgic register access easier using one of the access
 * modes defined for vgic register access
 * (read,raz,write-ignored,setbit,clearbit,write)
 */
void vgic_reg_access(struct kvm_exit_mmio *mmio, u32 *reg,
		     phys_addr_t offset, int mode)
{
	int word_offset = (offset & 3) * 8;
	u32 mask = (1UL << (mmio->len * 8)) - 1;
	u32 regval;

	/*
	 * Any alignment fault should have been delivered to the guest
	 * directly (ARM ARM B3.12.7 "Prioritization of aborts").
	 */

	if (reg) {
		regval = *reg;
	} else {
		BUG_ON(mode != (ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED));
		regval = 0;
	}

	if (mmio->is_write) {
		u32 data = mmio_data_read(mmio, mask) << word_offset;
		switch (ACCESS_WRITE_MASK(mode)) {
		case ACCESS_WRITE_IGNORED:
			return;

		case ACCESS_WRITE_SETBIT:
			regval |= data;
			break;

		case ACCESS_WRITE_CLEARBIT:
			regval &= ~data;
			break;

		case ACCESS_WRITE_VALUE:
			regval = (regval & ~(mask << word_offset)) | data;
			break;
		}
		*reg = regval;
	} else {
		switch (ACCESS_READ_MASK(mode)) {
		case ACCESS_READ_RAZ:
			regval = 0;
			/* fall through */

		case ACCESS_READ_VALUE:
			mmio_data_write(mmio, mask, regval >> word_offset);
		}
	}
}

bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
			phys_addr_t offset)
{
	vgic_reg_access(mmio, NULL, offset,
			ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
	return false;
}

bool vgic_handle_enable_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
			    phys_addr_t offset, int vcpu_id, int access)
{
	u32 *reg;
	int mode = ACCESS_READ_VALUE | access;
	struct kvm_vcpu *target_vcpu = kvm_get_vcpu(kvm, vcpu_id);

	reg = vgic_bitmap_get_reg(&kvm->arch.vgic.irq_enabled, vcpu_id, offset);
	vgic_reg_access(mmio, reg, offset, mode);
	if (mmio->is_write) {
		if (access & ACCESS_WRITE_CLEARBIT) {
			if (offset < 4) /* Force SGI enabled */
				*reg |= 0xffff;
			vgic_retire_disabled_irqs(target_vcpu);
		}
		vgic_update_state(kvm);
		return true;
	}

	return false;
}

bool vgic_handle_set_pending_reg(struct kvm *kvm,
				 struct kvm_exit_mmio *mmio,
				 phys_addr_t offset, int vcpu_id)
{
	u32 *reg, orig;
	u32 level_mask;
	int mode = ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT;
	struct vgic_dist *dist = &kvm->arch.vgic;

	reg = vgic_bitmap_get_reg(&dist->irq_cfg, vcpu_id, offset);
	level_mask = (~(*reg));

	/* Mark both level and edge triggered irqs as pending */
	reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu_id, offset);
	orig = *reg;
	vgic_reg_access(mmio, reg, offset, mode);

	if (mmio->is_write) {
		/* Set the soft-pending flag only for level-triggered irqs */
		reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
					  vcpu_id, offset);
		vgic_reg_access(mmio, reg, offset, mode);
		*reg &= level_mask;

		/* Ignore writes to SGIs */
		if (offset < 2) {
			*reg &= ~0xffff;
			*reg |= orig & 0xffff;
		}

		vgic_update_state(kvm);
		return true;
	}

	return false;
}

bool vgic_handle_clear_pending_reg(struct kvm *kvm,
				   struct kvm_exit_mmio *mmio,
				   phys_addr_t offset, int vcpu_id)
{
	u32 *level_active;
	u32 *reg, orig;
	int mode = ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT;
	struct vgic_dist *dist = &kvm->arch.vgic;

	reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu_id, offset);
	orig = *reg;
	vgic_reg_access(mmio, reg, offset, mode);
	if (mmio->is_write) {
		/* Re-set level triggered level-active interrupts */
		level_active = vgic_bitmap_get_reg(&dist->irq_level,
					  vcpu_id, offset);
		reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu_id, offset);
		*reg |= *level_active;

		/* Ignore writes to SGIs */
		if (offset < 2) {
			*reg &= ~0xffff;
			*reg |= orig & 0xffff;
		}

		/* Clear soft-pending flags */
		reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
					  vcpu_id, offset);
		vgic_reg_access(mmio, reg, offset, mode);

		vgic_update_state(kvm);
		return true;
	}
	return false;
}

static u32 vgic_cfg_expand(u16 val)
{
	u32 res = 0;
	int i;

	/*
	 * Turn a 16bit value like abcd...mnop into a 32bit word
	 * a0b0c0d0...m0n0o0p0, which is what the HW cfg register is.
	 */
	for (i = 0; i < 16; i++)
		res |= ((val >> i) & VGIC_CFG_EDGE) << (2 * i + 1);

	return res;
}

static u16 vgic_cfg_compress(u32 val)
{
	u16 res = 0;
	int i;

	/*
	 * Turn a 32bit word a0b0c0d0...m0n0o0p0 into 16bit value like
	 * abcd...mnop which is what we really care about.
	 */
	for (i = 0; i < 16; i++)
		res |= ((val >> (i * 2 + 1)) & VGIC_CFG_EDGE) << i;

	return res;
}

/*
 * The distributor uses 2 bits per IRQ for the CFG register, but the
 * LSB is always 0. As such, we only keep the upper bit, and use the
 * two above functions to compress/expand the bits
 */
bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio,
			 phys_addr_t offset)
{
	u32 val;

	if (offset & 4)
		val = *reg >> 16;
	else
		val = *reg & 0xffff;

	val = vgic_cfg_expand(val);
	vgic_reg_access(mmio, &val, offset,
			ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
	if (mmio->is_write) {
		if (offset < 8) {
			*reg = ~0U; /* Force PPIs/SGIs to 1 */
			return false;
		}

		val = vgic_cfg_compress(val);
		if (offset & 4) {
			*reg &= 0xffff;
			*reg |= val << 16;
		} else {
			*reg &= 0xffff << 16;
			*reg |= val;
		}
	}

	return false;
}

/**
 * vgic_unqueue_irqs - move pending IRQs from LRs to the distributor
 * @vgic_cpu: Pointer to the vgic_cpu struct holding the LRs
 *
 * Move any pending IRQs that have already been assigned to LRs back to the
 * emulated distributor state so that the complete emulated state can be read
 * from the main emulation structures without investigating the LRs.
 *
 * Note that IRQs in the active state in the LRs get their pending state moved
 * to the distributor but the active state stays in the LRs, because we don't
 * track the active state on the distributor side.
 */
void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	int i;

	for_each_set_bit(i, vgic_cpu->lr_used, vgic_cpu->nr_lr) {
		struct vgic_lr lr = vgic_get_lr(vcpu, i);

		/*
		 * There are three options for the state bits:
		 *
		 * 01: pending
		 * 10: active
		 * 11: pending and active
		 *
		 * If the LR holds only an active interrupt (not pending) then
		 * just leave it alone.
		 */
		if ((lr.state & LR_STATE_MASK) == LR_STATE_ACTIVE)
			continue;

		/*
		 * Reestablish the pending state on the distributor and the
		 * CPU interface.  It may have already been pending, but that
		 * is fine, then we are only setting a few bits that were
		 * already set.
		 */
		vgic_dist_irq_set_pending(vcpu, lr.irq);
		if (lr.irq < VGIC_NR_SGIS)
			add_sgi_source(vcpu, lr.irq, lr.source);
		lr.state &= ~LR_STATE_PENDING;
		vgic_set_lr(vcpu, i, lr);

		/*
		 * If there's no state left on the LR (it could still be
		 * active), then the LR does not hold any useful info and can
		 * be marked as free for other use.
		 */
		if (!(lr.state & LR_STATE_MASK)) {
			vgic_retire_lr(i, lr.irq, vcpu);
			vgic_irq_clear_queued(vcpu, lr.irq);
		}

		/* Finally update the VGIC state. */
		vgic_update_state(vcpu->kvm);
	}
}

const
struct kvm_mmio_range *vgic_find_range(const struct kvm_mmio_range *ranges,
				       struct kvm_exit_mmio *mmio,
				       phys_addr_t offset)
{
	const struct kvm_mmio_range *r = ranges;

	while (r->len) {
		if (offset >= r->base &&
		    (offset + mmio->len) <= (r->base + r->len))
			return r;
		r++;
	}

	return NULL;
}

static bool vgic_validate_access(const struct vgic_dist *dist,
				 const struct kvm_mmio_range *range,
				 unsigned long offset)
{
	int irq;

	if (!range->bits_per_irq)
		return true;	/* Not an irq-based access */

	irq = offset * 8 / range->bits_per_irq;
	if (irq >= dist->nr_irqs)
		return false;

	return true;
}

/*
 * Call the respective handler function for the given range.
 * We split up any 64 bit accesses into two consecutive 32 bit
 * handler calls and merge the result afterwards.
 * We do this in a little endian fashion regardless of the host's
 * or guest's endianness, because the GIC is always LE and the rest of
 * the code (vgic_reg_access) also puts it in a LE fashion already.
 * At this point we have already identified the handle function, so
 * range points to that one entry and offset is relative to this.
 */
static bool call_range_handler(struct kvm_vcpu *vcpu,
			       struct kvm_exit_mmio *mmio,
			       unsigned long offset,
			       const struct kvm_mmio_range *range)
{
	u32 *data32 = (void *)mmio->data;
	struct kvm_exit_mmio mmio32;
	bool ret;

	if (likely(mmio->len <= 4))
		return range->handle_mmio(vcpu, mmio, offset);

	/*
	 * Any access bigger than 4 bytes (that we currently handle in KVM)
	 * is actually 8 bytes long, caused by a 64-bit access
	 */

	mmio32.len = 4;
	mmio32.is_write = mmio->is_write;
	mmio32.private = mmio->private;

	mmio32.phys_addr = mmio->phys_addr + 4;
	if (mmio->is_write)
		*(u32 *)mmio32.data = data32[1];
	ret = range->handle_mmio(vcpu, &mmio32, offset + 4);
	if (!mmio->is_write)
		data32[1] = *(u32 *)mmio32.data;

	mmio32.phys_addr = mmio->phys_addr;
	if (mmio->is_write)
		*(u32 *)mmio32.data = data32[0];
	ret |= range->handle_mmio(vcpu, &mmio32, offset);
	if (!mmio->is_write)
		data32[0] = *(u32 *)mmio32.data;

	return ret;
}

/**
 * vgic_handle_mmio_range - handle an in-kernel MMIO access
 * @vcpu:	pointer to the vcpu performing the access
 * @run:	pointer to the kvm_run structure
 * @mmio:	pointer to the data describing the access
 * @ranges:	array of MMIO ranges in a given region
 * @mmio_base:	base address of that region
 *
 * returns true if the MMIO access could be performed
 */
bool vgic_handle_mmio_range(struct kvm_vcpu *vcpu, struct kvm_run *run,
			    struct kvm_exit_mmio *mmio,
			    const struct kvm_mmio_range *ranges,
			    unsigned long mmio_base)
{
	const struct kvm_mmio_range *range;
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
	bool updated_state;
	unsigned long offset;

	offset = mmio->phys_addr - mmio_base;
	range = vgic_find_range(ranges, mmio, offset);
	if (unlikely(!range || !range->handle_mmio)) {
		pr_warn("Unhandled access %d %08llx %d\n",
			mmio->is_write, mmio->phys_addr, mmio->len);
		return false;
	}

	spin_lock(&vcpu->kvm->arch.vgic.lock);
	offset -= range->base;
	if (vgic_validate_access(dist, range, offset)) {
		updated_state = call_range_handler(vcpu, mmio, offset, range);
	} else {
		if (!mmio->is_write)
			memset(mmio->data, 0, mmio->len);
		updated_state = false;
	}
	spin_unlock(&vcpu->kvm->arch.vgic.lock);
	kvm_prepare_mmio(run, mmio);
	kvm_handle_mmio_return(vcpu, run);

	if (updated_state)
		vgic_kick_vcpus(vcpu->kvm);

	return true;
}

/**
 * vgic_handle_mmio - handle an in-kernel MMIO access for the GIC emulation
 * @vcpu:      pointer to the vcpu performing the access
 * @run:       pointer to the kvm_run structure
 * @mmio:      pointer to the data describing the access
 *
 * returns true if the MMIO access has been performed in kernel space,
 * and false if it needs to be emulated in user space.
 * Calls the actual handling routine for the selected VGIC model.
 */
bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
		      struct kvm_exit_mmio *mmio)
{
	if (!irqchip_in_kernel(vcpu->kvm))
		return false;

	/*
	 * This will currently call either vgic_v2_handle_mmio() or
	 * vgic_v3_handle_mmio(), which in turn will call
	 * vgic_handle_mmio_range() defined above.
	 */
	return vcpu->kvm->arch.vgic.vm_ops.handle_mmio(vcpu, run, mmio);
}

static int vgic_nr_shared_irqs(struct vgic_dist *dist)
{
	return dist->nr_irqs - VGIC_NR_PRIVATE_IRQS;
}

static int compute_pending_for_cpu(struct kvm_vcpu *vcpu)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
	unsigned long *pending, *enabled, *pend_percpu, *pend_shared;
	unsigned long pending_private, pending_shared;
	int nr_shared = vgic_nr_shared_irqs(dist);
	int vcpu_id;

	vcpu_id = vcpu->vcpu_id;
	pend_percpu = vcpu->arch.vgic_cpu.pending_percpu;
	pend_shared = vcpu->arch.vgic_cpu.pending_shared;

	pending = vgic_bitmap_get_cpu_map(&dist->irq_pending, vcpu_id);
	enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id);
	bitmap_and(pend_percpu, pending, enabled, VGIC_NR_PRIVATE_IRQS);

	pending = vgic_bitmap_get_shared_map(&dist->irq_pending);
	enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled);
	bitmap_and(pend_shared, pending, enabled, nr_shared);
	bitmap_and(pend_shared, pend_shared,
		   vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]),
		   nr_shared);

	pending_private = find_first_bit(pend_percpu, VGIC_NR_PRIVATE_IRQS);
	pending_shared = find_first_bit(pend_shared, nr_shared);
	return (pending_private < VGIC_NR_PRIVATE_IRQS ||
		pending_shared < vgic_nr_shared_irqs(dist));
}

/*
 * Update the interrupt state and determine which CPUs have pending
 * interrupts. Must be called with distributor lock held.
 */
void vgic_update_state(struct kvm *kvm)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct kvm_vcpu *vcpu;
	int c;

	if (!dist->enabled) {
		set_bit(0, dist->irq_pending_on_cpu);
		return;
	}

	kvm_for_each_vcpu(c, vcpu, kvm) {
		if (compute_pending_for_cpu(vcpu)) {
			pr_debug("CPU%d has pending interrupts\n", c);
			set_bit(c, dist->irq_pending_on_cpu);
		}
	}
}

static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr)
{
	return vgic_ops->get_lr(vcpu, lr);
}

static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr,
			       struct vgic_lr vlr)
{
	vgic_ops->set_lr(vcpu, lr, vlr);
}

static void vgic_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
			       struct vgic_lr vlr)
{
	vgic_ops->sync_lr_elrsr(vcpu, lr, vlr);
}

static inline u64 vgic_get_elrsr(struct kvm_vcpu *vcpu)
{
	return vgic_ops->get_elrsr(vcpu);
}

static inline u64 vgic_get_eisr(struct kvm_vcpu *vcpu)
{
	return vgic_ops->get_eisr(vcpu);
}

static inline u32 vgic_get_interrupt_status(struct kvm_vcpu *vcpu)
{
	return vgic_ops->get_interrupt_status(vcpu);
}

static inline void vgic_enable_underflow(struct kvm_vcpu *vcpu)
{
	vgic_ops->enable_underflow(vcpu);
}

static inline void vgic_disable_underflow(struct kvm_vcpu *vcpu)
{
	vgic_ops->disable_underflow(vcpu);
}

void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
{
	vgic_ops->get_vmcr(vcpu, vmcr);
}

void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
{
	vgic_ops->set_vmcr(vcpu, vmcr);
}

static inline void vgic_enable(struct kvm_vcpu *vcpu)
{
	vgic_ops->enable(vcpu);
}

static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	struct vgic_lr vlr = vgic_get_lr(vcpu, lr_nr);

	vlr.state = 0;
	vgic_set_lr(vcpu, lr_nr, vlr);
	clear_bit(lr_nr, vgic_cpu->lr_used);
	vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
}

/*
 * An interrupt may have been disabled after being made pending on the
 * CPU interface (the classic case is a timer running while we're
 * rebooting the guest - the interrupt would kick as soon as the CPU
 * interface gets enabled, with deadly consequences).
 *
 * The solution is to examine already active LRs, and check the
 * interrupt is still enabled. If not, just retire it.
 */
static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	int lr;

	for_each_set_bit(lr, vgic_cpu->lr_used, vgic->nr_lr) {
		struct vgic_lr vlr = vgic_get_lr(vcpu, lr);

		if (!vgic_irq_is_enabled(vcpu, vlr.irq)) {
			vgic_retire_lr(lr, vlr.irq, vcpu);
			if (vgic_irq_is_queued(vcpu, vlr.irq))
				vgic_irq_clear_queued(vcpu, vlr.irq);
		}
	}
}

/*
 * Queue an interrupt to a CPU virtual interface. Return true on success,
 * or false if it wasn't possible to queue it.
 * sgi_source must be zero for any non-SGI interrupts.
 */
bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
	struct vgic_lr vlr;
	int lr;

	/* Sanitize the input... */
	BUG_ON(sgi_source_id & ~7);
	BUG_ON(sgi_source_id && irq >= VGIC_NR_SGIS);
	BUG_ON(irq >= dist->nr_irqs);

	kvm_debug("Queue IRQ%d\n", irq);

	lr = vgic_cpu->vgic_irq_lr_map[irq];

	/* Do we have an active interrupt for the same CPUID? */
	if (lr != LR_EMPTY) {
		vlr = vgic_get_lr(vcpu, lr);
		if (vlr.source == sgi_source_id) {
			kvm_debug("LR%d piggyback for IRQ%d\n", lr, vlr.irq);
			BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
			vlr.state |= LR_STATE_PENDING;
			vgic_set_lr(vcpu, lr, vlr);
			return true;
		}
	}

	/* Try to use another LR for this interrupt */
	lr = find_first_zero_bit((unsigned long *)vgic_cpu->lr_used,
			       vgic->nr_lr);
	if (lr >= vgic->nr_lr)
		return false;

	kvm_debug("LR%d allocated for IRQ%d %x\n", lr, irq, sgi_source_id);
	vgic_cpu->vgic_irq_lr_map[irq] = lr;
	set_bit(lr, vgic_cpu->lr_used);

	vlr.irq = irq;
	vlr.source = sgi_source_id;
	vlr.state = LR_STATE_PENDING;
	if (!vgic_irq_is_edge(vcpu, irq))
		vlr.state |= LR_EOI_INT;

	vgic_set_lr(vcpu, lr, vlr);

	return true;
}

static bool vgic_queue_hwirq(struct kvm_vcpu *vcpu, int irq)
{
	if (!vgic_can_sample_irq(vcpu, irq))
		return true; /* level interrupt, already queued */

	if (vgic_queue_irq(vcpu, 0, irq)) {
		if (vgic_irq_is_edge(vcpu, irq)) {
			vgic_dist_irq_clear_pending(vcpu, irq);
			vgic_cpu_irq_clear(vcpu, irq);
		} else {
			vgic_irq_set_queued(vcpu, irq);
		}

		return true;
	}

	return false;
}

/*
 * Fill the list registers with pending interrupts before running the
 * guest.
 */
static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
	int i, vcpu_id;
	int overflow = 0;

	vcpu_id = vcpu->vcpu_id;

	/*
	 * We may not have any pending interrupt, or the interrupts
	 * may have been serviced from another vcpu. In all cases,
	 * move along.
	 */
	if (!kvm_vgic_vcpu_pending_irq(vcpu)) {
		pr_debug("CPU%d has no pending interrupt\n", vcpu_id);
		goto epilog;
	}

	/* SGIs */
	for_each_set_bit(i, vgic_cpu->pending_percpu, VGIC_NR_SGIS) {
		if (!queue_sgi(vcpu, i))
			overflow = 1;
	}

	/* PPIs */
	for_each_set_bit_from(i, vgic_cpu->pending_percpu, VGIC_NR_PRIVATE_IRQS) {
		if (!vgic_queue_hwirq(vcpu, i))
			overflow = 1;
	}

	/* SPIs */
	for_each_set_bit(i, vgic_cpu->pending_shared, vgic_nr_shared_irqs(dist)) {
		if (!vgic_queue_hwirq(vcpu, i + VGIC_NR_PRIVATE_IRQS))
			overflow = 1;
	}

epilog:
	if (overflow) {
		vgic_enable_underflow(vcpu);
	} else {
		vgic_disable_underflow(vcpu);
		/*
		 * We're about to run this VCPU, and we've consumed
		 * everything the distributor had in store for
		 * us. Claim we don't have anything pending. We'll
		 * adjust that if needed while exiting.
		 */
		clear_bit(vcpu_id, dist->irq_pending_on_cpu);
	}
}

static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
{
	u32 status = vgic_get_interrupt_status(vcpu);
	bool level_pending = false;

	kvm_debug("STATUS = %08x\n", status);

	if (status & INT_STATUS_EOI) {
		/*
		 * Some level interrupts have been EOIed. Clear their
		 * active bit.
		 */
		u64 eisr = vgic_get_eisr(vcpu);
		unsigned long *eisr_ptr = u64_to_bitmask(&eisr);
		int lr;

		for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) {
			struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
			WARN_ON(vgic_irq_is_edge(vcpu, vlr.irq));

			vgic_irq_clear_queued(vcpu, vlr.irq);
			WARN_ON(vlr.state & LR_STATE_MASK);
			vlr.state = 0;
			vgic_set_lr(vcpu, lr, vlr);

			/*
			 * If the IRQ was EOIed it was also ACKed and we we
			 * therefore assume we can clear the soft pending
			 * state (should it had been set) for this interrupt.
			 *
			 * Note: if the IRQ soft pending state was set after
			 * the IRQ was acked, it actually shouldn't be
			 * cleared, but we have no way of knowing that unless
			 * we start trapping ACKs when the soft-pending state
			 * is set.
			 */
			vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq);

			/* Any additional pending interrupt? */
			if (vgic_dist_irq_get_level(vcpu, vlr.irq)) {
				vgic_cpu_irq_set(vcpu, vlr.irq);
				level_pending = true;
			} else {
				vgic_dist_irq_clear_pending(vcpu, vlr.irq);
				vgic_cpu_irq_clear(vcpu, vlr.irq);
			}

			/*
			 * Despite being EOIed, the LR may not have
			 * been marked as empty.
			 */
			vgic_sync_lr_elrsr(vcpu, lr, vlr);
		}
	}

	if (status & INT_STATUS_UNDERFLOW)
		vgic_disable_underflow(vcpu);

	return level_pending;
}

/*
 * Sync back the VGIC state after a guest run. The distributor lock is
 * needed so we don't get preempted in the middle of the state processing.
 */
static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
	u64 elrsr;
	unsigned long *elrsr_ptr;
	int lr, pending;
	bool level_pending;

	level_pending = vgic_process_maintenance(vcpu);
	elrsr = vgic_get_elrsr(vcpu);
	elrsr_ptr = u64_to_bitmask(&elrsr);

	/* Clear mappings for empty LRs */
	for_each_set_bit(lr, elrsr_ptr, vgic->nr_lr) {
		struct vgic_lr vlr;

		if (!test_and_clear_bit(lr, vgic_cpu->lr_used))
			continue;

		vlr = vgic_get_lr(vcpu, lr);

		BUG_ON(vlr.irq >= dist->nr_irqs);
		vgic_cpu->vgic_irq_lr_map[vlr.irq] = LR_EMPTY;
	}

	/* Check if we still have something up our sleeve... */
	pending = find_first_zero_bit(elrsr_ptr, vgic->nr_lr);
	if (level_pending || pending < vgic->nr_lr)
		set_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
}

void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	if (!irqchip_in_kernel(vcpu->kvm))
		return;

	spin_lock(&dist->lock);
	__kvm_vgic_flush_hwstate(vcpu);
	spin_unlock(&dist->lock);
}

void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	if (!irqchip_in_kernel(vcpu->kvm))
		return;

	spin_lock(&dist->lock);
	__kvm_vgic_sync_hwstate(vcpu);
	spin_unlock(&dist->lock);
}

int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	if (!irqchip_in_kernel(vcpu->kvm))
		return 0;

	return test_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
}

void vgic_kick_vcpus(struct kvm *kvm)
{
	struct kvm_vcpu *vcpu;
	int c;

	/*
	 * We've injected an interrupt, time to find out who deserves
	 * a good kick...
	 */
	kvm_for_each_vcpu(c, vcpu, kvm) {
		if (kvm_vgic_vcpu_pending_irq(vcpu))
			kvm_vcpu_kick(vcpu);
	}
}

static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level)
{
	int edge_triggered = vgic_irq_is_edge(vcpu, irq);

	/*
	 * Only inject an interrupt if:
	 * - edge triggered and we have a rising edge
	 * - level triggered and we change level
	 */
	if (edge_triggered) {
		int state = vgic_dist_irq_is_pending(vcpu, irq);
		return level > state;
	} else {
		int state = vgic_dist_irq_get_level(vcpu, irq);
		return level != state;
	}
}

static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
				  unsigned int irq_num, bool level)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct kvm_vcpu *vcpu;
	int edge_triggered, level_triggered;
	int enabled;
	bool ret = true, can_inject = true;

	spin_lock(&dist->lock);

	vcpu = kvm_get_vcpu(kvm, cpuid);
	edge_triggered = vgic_irq_is_edge(vcpu, irq_num);
	level_triggered = !edge_triggered;

	if (!vgic_validate_injection(vcpu, irq_num, level)) {
		ret = false;
		goto out;
	}

	if (irq_num >= VGIC_NR_PRIVATE_IRQS) {
		cpuid = dist->irq_spi_cpu[irq_num - VGIC_NR_PRIVATE_IRQS];
		if (cpuid == VCPU_NOT_ALLOCATED) {
			/* Pretend we use CPU0, and prevent injection */
			cpuid = 0;
			can_inject = false;
		}
		vcpu = kvm_get_vcpu(kvm, cpuid);
	}

	kvm_debug("Inject IRQ%d level %d CPU%d\n", irq_num, level, cpuid);

	if (level) {
		if (level_triggered)
			vgic_dist_irq_set_level(vcpu, irq_num);
		vgic_dist_irq_set_pending(vcpu, irq_num);
	} else {
		if (level_triggered) {
			vgic_dist_irq_clear_level(vcpu, irq_num);
			if (!vgic_dist_irq_soft_pend(vcpu, irq_num))
				vgic_dist_irq_clear_pending(vcpu, irq_num);
		}

		ret = false;
		goto out;
	}

	enabled = vgic_irq_is_enabled(vcpu, irq_num);

	if (!enabled || !can_inject) {
		ret = false;
		goto out;
	}

	if (!vgic_can_sample_irq(vcpu, irq_num)) {
		/*
		 * Level interrupt in progress, will be picked up
		 * when EOId.
		 */
		ret = false;
		goto out;
	}

	if (level) {
		vgic_cpu_irq_set(vcpu, irq_num);
		set_bit(cpuid, dist->irq_pending_on_cpu);
	}

out:
	spin_unlock(&dist->lock);

	return ret ? cpuid : -EINVAL;
}

/**
 * kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic
 * @kvm:     The VM structure pointer
 * @cpuid:   The CPU for PPIs
 * @irq_num: The IRQ number that is assigned to the device
 * @level:   Edge-triggered:  true:  to trigger the interrupt
 *			      false: to ignore the call
 *	     Level-sensitive  true:  activates an interrupt
 *			      false: deactivates an interrupt
 *
 * The GIC is not concerned with devices being active-LOW or active-HIGH for
 * level-sensitive interrupts.  You can think of the level parameter as 1
 * being HIGH and 0 being LOW and all devices being active-HIGH.
 */
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
			bool level)
{
	int ret = 0;
	int vcpu_id;

	if (unlikely(!vgic_initialized(kvm))) {
		/*
		 * We only provide the automatic initialization of the VGIC
		 * for the legacy case of a GICv2. Any other type must
		 * be explicitly initialized once setup with the respective
		 * KVM device call.
		 */
		if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2) {
			ret = -EBUSY;
			goto out;
		}
		mutex_lock(&kvm->lock);
		ret = vgic_init(kvm);
		mutex_unlock(&kvm->lock);

		if (ret)
			goto out;
	}

	vcpu_id = vgic_update_irq_pending(kvm, cpuid, irq_num, level);
	if (vcpu_id >= 0) {
		/* kick the specified vcpu */
		kvm_vcpu_kick(kvm_get_vcpu(kvm, vcpu_id));
	}

out:
	return ret;
}

static irqreturn_t vgic_maintenance_handler(int irq, void *data)
{
	/*
	 * We cannot rely on the vgic maintenance interrupt to be
	 * delivered synchronously. This means we can only use it to
	 * exit the VM, and we perform the handling of EOIed
	 * interrupts on the exit path (see vgic_process_maintenance).
	 */
	return IRQ_HANDLED;
}

void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;

	kfree(vgic_cpu->pending_shared);
	kfree(vgic_cpu->vgic_irq_lr_map);
	vgic_cpu->pending_shared = NULL;
	vgic_cpu->vgic_irq_lr_map = NULL;
}

static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;

	int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8;
	vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL);
	vgic_cpu->vgic_irq_lr_map = kmalloc(nr_irqs, GFP_KERNEL);

	if (!vgic_cpu->pending_shared || !vgic_cpu->vgic_irq_lr_map) {
		kvm_vgic_vcpu_destroy(vcpu);
		return -ENOMEM;
	}

	memset(vgic_cpu->vgic_irq_lr_map, LR_EMPTY, nr_irqs);

	/*
	 * Store the number of LRs per vcpu, so we don't have to go
	 * all the way to the distributor structure to find out. Only
	 * assembly code should use this one.
	 */
	vgic_cpu->nr_lr = vgic->nr_lr;

	return 0;
}

/**
 * kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW
 *
 * The host's GIC naturally limits the maximum amount of VCPUs a guest
 * can use.
 */
int kvm_vgic_get_max_vcpus(void)
{
	return vgic->max_gic_vcpus;
}

void kvm_vgic_destroy(struct kvm *kvm)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct kvm_vcpu *vcpu;
	int i;

	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_vgic_vcpu_destroy(vcpu);

	vgic_free_bitmap(&dist->irq_enabled);
	vgic_free_bitmap(&dist->irq_level);
	vgic_free_bitmap(&dist->irq_pending);
	vgic_free_bitmap(&dist->irq_soft_pend);
	vgic_free_bitmap(&dist->irq_queued);
	vgic_free_bitmap(&dist->irq_cfg);
	vgic_free_bytemap(&dist->irq_priority);
	if (dist->irq_spi_target) {
		for (i = 0; i < dist->nr_cpus; i++)
			vgic_free_bitmap(&dist->irq_spi_target[i]);
	}
	kfree(dist->irq_sgi_sources);
	kfree(dist->irq_spi_cpu);
	kfree(dist->irq_spi_mpidr);
	kfree(dist->irq_spi_target);
	kfree(dist->irq_pending_on_cpu);
	dist->irq_sgi_sources = NULL;
	dist->irq_spi_cpu = NULL;
	dist->irq_spi_target = NULL;
	dist->irq_pending_on_cpu = NULL;
	dist->nr_cpus = 0;
}

/*
 * Allocate and initialize the various data structures. Must be called
 * with kvm->lock held!
 */
int vgic_init(struct kvm *kvm)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct kvm_vcpu *vcpu;
	int nr_cpus, nr_irqs;
	int ret, i, vcpu_id;

	if (vgic_initialized(kvm))
		return 0;

	nr_cpus = dist->nr_cpus = atomic_read(&kvm->online_vcpus);
	if (!nr_cpus)		/* No vcpus? Can't be good... */
		return -ENODEV;

	/*
	 * If nobody configured the number of interrupts, use the
	 * legacy one.
	 */
	if (!dist->nr_irqs)
		dist->nr_irqs = VGIC_NR_IRQS_LEGACY;

	nr_irqs = dist->nr_irqs;

	ret  = vgic_init_bitmap(&dist->irq_enabled, nr_cpus, nr_irqs);
	ret |= vgic_init_bitmap(&dist->irq_level, nr_cpus, nr_irqs);
	ret |= vgic_init_bitmap(&dist->irq_pending, nr_cpus, nr_irqs);
	ret |= vgic_init_bitmap(&dist->irq_soft_pend, nr_cpus, nr_irqs);
	ret |= vgic_init_bitmap(&dist->irq_queued, nr_cpus, nr_irqs);
	ret |= vgic_init_bitmap(&dist->irq_cfg, nr_cpus, nr_irqs);
	ret |= vgic_init_bytemap(&dist->irq_priority, nr_cpus, nr_irqs);

	if (ret)
		goto out;

	dist->irq_sgi_sources = kzalloc(nr_cpus * VGIC_NR_SGIS, GFP_KERNEL);
	dist->irq_spi_cpu = kzalloc(nr_irqs - VGIC_NR_PRIVATE_IRQS, GFP_KERNEL);
	dist->irq_spi_target = kzalloc(sizeof(*dist->irq_spi_target) * nr_cpus,
				       GFP_KERNEL);
	dist->irq_pending_on_cpu = kzalloc(BITS_TO_LONGS(nr_cpus) * sizeof(long),
					   GFP_KERNEL);
	if (!dist->irq_sgi_sources ||
	    !dist->irq_spi_cpu ||
	    !dist->irq_spi_target ||
	    !dist->irq_pending_on_cpu) {
		ret = -ENOMEM;
		goto out;
	}

	for (i = 0; i < nr_cpus; i++)
		ret |= vgic_init_bitmap(&dist->irq_spi_target[i],
					nr_cpus, nr_irqs);

	if (ret)
		goto out;

	ret = kvm->arch.vgic.vm_ops.init_model(kvm);
	if (ret)
		goto out;

	kvm_for_each_vcpu(vcpu_id, vcpu, kvm) {
		ret = vgic_vcpu_init_maps(vcpu, nr_irqs);
		if (ret) {
			kvm_err("VGIC: Failed to allocate vcpu memory\n");
			break;
		}

		for (i = 0; i < dist->nr_irqs; i++) {
			if (i < VGIC_NR_PPIS)
				vgic_bitmap_set_irq_val(&dist->irq_enabled,
							vcpu->vcpu_id, i, 1);
			if (i < VGIC_NR_PRIVATE_IRQS)
				vgic_bitmap_set_irq_val(&dist->irq_cfg,
							vcpu->vcpu_id, i,
							VGIC_CFG_EDGE);
		}

		vgic_enable(vcpu);
	}

out:
	if (ret)
		kvm_vgic_destroy(kvm);

	return ret;
}

static int init_vgic_model(struct kvm *kvm, int type)
{
	switch (type) {
	case KVM_DEV_TYPE_ARM_VGIC_V2:
		vgic_v2_init_emulation(kvm);
		break;
#ifdef CONFIG_ARM_GIC_V3
	case KVM_DEV_TYPE_ARM_VGIC_V3:
		vgic_v3_init_emulation(kvm);
		break;
#endif
	default:
		return -ENODEV;
	}

	if (atomic_read(&kvm->online_vcpus) > kvm->arch.max_vcpus)
		return -E2BIG;

	return 0;
}

int kvm_vgic_create(struct kvm *kvm, u32 type)
{
	int i, vcpu_lock_idx = -1, ret;
	struct kvm_vcpu *vcpu;

	mutex_lock(&kvm->lock);

	if (irqchip_in_kernel(kvm)) {
		ret = -EEXIST;
		goto out;
	}

	/*
	 * This function is also called by the KVM_CREATE_IRQCHIP handler,
	 * which had no chance yet to check the availability of the GICv2
	 * emulation. So check this here again. KVM_CREATE_DEVICE does
	 * the proper checks already.
	 */
	if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && !vgic->can_emulate_gicv2)
		return -ENODEV;

	/*
	 * Any time a vcpu is run, vcpu_load is called which tries to grab the
	 * vcpu->mutex.  By grabbing the vcpu->mutex of all VCPUs we ensure
	 * that no other VCPUs are run while we create the vgic.
	 */
	ret = -EBUSY;
	kvm_for_each_vcpu(i, vcpu, kvm) {
		if (!mutex_trylock(&vcpu->mutex))
			goto out_unlock;
		vcpu_lock_idx = i;
	}

	kvm_for_each_vcpu(i, vcpu, kvm) {
		if (vcpu->arch.has_run_once)
			goto out_unlock;
	}
	ret = 0;

	ret = init_vgic_model(kvm, type);
	if (ret)
		goto out_unlock;

	spin_lock_init(&kvm->arch.vgic.lock);
	kvm->arch.vgic.in_kernel = true;
	kvm->arch.vgic.vgic_model = type;
	kvm->arch.vgic.vctrl_base = vgic->vctrl_base;
	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
	kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
	kvm->arch.vgic.vgic_redist_base = VGIC_ADDR_UNDEF;

out_unlock:
	for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
		vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
		mutex_unlock(&vcpu->mutex);
	}

out:
	mutex_unlock(&kvm->lock);
	return ret;
}

static int vgic_ioaddr_overlap(struct kvm *kvm)
{
	phys_addr_t dist = kvm->arch.vgic.vgic_dist_base;
	phys_addr_t cpu = kvm->arch.vgic.vgic_cpu_base;

	if (IS_VGIC_ADDR_UNDEF(dist) || IS_VGIC_ADDR_UNDEF(cpu))
		return 0;
	if ((dist <= cpu && dist + KVM_VGIC_V2_DIST_SIZE > cpu) ||
	    (cpu <= dist && cpu + KVM_VGIC_V2_CPU_SIZE > dist))
		return -EBUSY;
	return 0;
}

static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr,
			      phys_addr_t addr, phys_addr_t size)
{
	int ret;

	if (addr & ~KVM_PHYS_MASK)
		return -E2BIG;

	if (addr & (SZ_4K - 1))
		return -EINVAL;

	if (!IS_VGIC_ADDR_UNDEF(*ioaddr))
		return -EEXIST;
	if (addr + size < addr)
		return -EINVAL;

	*ioaddr = addr;
	ret = vgic_ioaddr_overlap(kvm);
	if (ret)
		*ioaddr = VGIC_ADDR_UNDEF;

	return ret;
}

/**
 * kvm_vgic_addr - set or get vgic VM base addresses
 * @kvm:   pointer to the vm struct
 * @type:  the VGIC addr type, one of KVM_VGIC_V2_ADDR_TYPE_XXX
 * @addr:  pointer to address value
 * @write: if true set the address in the VM address space, if false read the
 *          address
 *
 * Set or get the vgic base addresses for the distributor and the virtual CPU
 * interface in the VM physical address space.  These addresses are properties
 * of the emulated core/SoC and therefore user space initially knows this
 * information.
 */
int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
{
	int r = 0;
	struct vgic_dist *vgic = &kvm->arch.vgic;

	mutex_lock(&kvm->lock);
	switch (type) {
	case KVM_VGIC_V2_ADDR_TYPE_DIST:
		if (write) {
			r = vgic_ioaddr_assign(kvm, &vgic->vgic_dist_base,
					       *addr, KVM_VGIC_V2_DIST_SIZE);
		} else {
			*addr = vgic->vgic_dist_base;
		}
		break;
	case KVM_VGIC_V2_ADDR_TYPE_CPU:
		if (write) {
			r = vgic_ioaddr_assign(kvm, &vgic->vgic_cpu_base,
					       *addr, KVM_VGIC_V2_CPU_SIZE);
		} else {
			*addr = vgic->vgic_cpu_base;
		}
		break;
	default:
		r = -ENODEV;
	}

	mutex_unlock(&kvm->lock);
	return r;
}

int vgic_set_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	int r;

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

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

		r = kvm_vgic_addr(dev->kvm, type, &addr, true);
		return (r == -ENODEV) ? -ENXIO : r;
	}
	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
		u32 val;
		int ret = 0;

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

		/*
		 * We require:
		 * - at least 32 SPIs on top of the 16 SGIs and 16 PPIs
		 * - at most 1024 interrupts
		 * - a multiple of 32 interrupts
		 */
		if (val < (VGIC_NR_PRIVATE_IRQS + 32) ||
		    val > VGIC_MAX_IRQS ||
		    (val & 31))
			return -EINVAL;

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

		if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_irqs)
			ret = -EBUSY;
		else
			dev->kvm->arch.vgic.nr_irqs = val;

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

		return ret;
	}
	case KVM_DEV_ARM_VGIC_GRP_CTRL: {
		switch (attr->attr) {
		case KVM_DEV_ARM_VGIC_CTRL_INIT:
			r = vgic_init(dev->kvm);
			return r;
		}
		break;
	}
	}

	return -ENXIO;
}

int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	int r = -ENXIO;

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

		r = kvm_vgic_addr(dev->kvm, type, &addr, false);
		if (r)
			return (r == -ENODEV) ? -ENXIO : r;

		if (copy_to_user(uaddr, &addr, sizeof(addr)))
			return -EFAULT;
		break;
	}
	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
		u32 __user *uaddr = (u32 __user *)(long)attr->addr;

		r = put_user(dev->kvm->arch.vgic.nr_irqs, uaddr);
		break;
	}

	}

	return r;
}

int vgic_has_attr_regs(const struct kvm_mmio_range *ranges, phys_addr_t offset)
{
	struct kvm_exit_mmio dev_attr_mmio;

	dev_attr_mmio.len = 4;
	if (vgic_find_range(ranges, &dev_attr_mmio, offset))
		return 0;
	else
		return -ENXIO;
}

static void vgic_init_maintenance_interrupt(void *info)
{
	enable_percpu_irq(vgic->maint_irq, 0);
}

static int vgic_cpu_notify(struct notifier_block *self,
			   unsigned long action, void *cpu)
{
	switch (action) {
	case CPU_STARTING:
	case CPU_STARTING_FROZEN:
		vgic_init_maintenance_interrupt(NULL);
		break;
	case CPU_DYING:
	case CPU_DYING_FROZEN:
		disable_percpu_irq(vgic->maint_irq);
		break;
	}

	return NOTIFY_OK;
}

static struct notifier_block vgic_cpu_nb = {
	.notifier_call = vgic_cpu_notify,
};

static const struct of_device_id vgic_ids[] = {
	{ .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, },
	{ .compatible = "arm,gic-v3", .data = vgic_v3_probe, },
	{},
};

int kvm_vgic_hyp_init(void)
{
	const struct of_device_id *matched_id;
	const int (*vgic_probe)(struct device_node *,const struct vgic_ops **,
				const struct vgic_params **);
	struct device_node *vgic_node;
	int ret;

	vgic_node = of_find_matching_node_and_match(NULL,
						    vgic_ids, &matched_id);
	if (!vgic_node) {
		kvm_err("error: no compatible GIC node found\n");
		return -ENODEV;
	}

	vgic_probe = matched_id->data;
	ret = vgic_probe(vgic_node, &vgic_ops, &vgic);
	if (ret)
		return ret;

	ret = request_percpu_irq(vgic->maint_irq, vgic_maintenance_handler,
				 "vgic", kvm_get_running_vcpus());
	if (ret) {
		kvm_err("Cannot register interrupt %d\n", vgic->maint_irq);
		return ret;
	}

	ret = __register_cpu_notifier(&vgic_cpu_nb);
	if (ret) {
		kvm_err("Cannot register vgic CPU notifier\n");
		goto out_free_irq;
	}

	/* Callback into for arch code for setup */
	vgic_arch_setup(vgic);

	on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);

	return 0;

out_free_irq:
	free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus());
	return ret;
}