aboutsummaryrefslogtreecommitdiff
path: root/arch/arm/kvm/vgic.c
blob: c9a17316e9fe75f2a8dec4fe3893816d3d0730c9 (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
/*
 * 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/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
 * - VGIC pending interrupts are stored on the vgic.irq_state 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) and indicate the 'wire' state.
 * - 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_state & dist->irq_enable
 *   - SPI: dist->irq_state & dist->irq_enable & dist->irq_spi_target
 *   - irq_spi_target is a 'formatted' version of the GICD_ICFGR
 *     registers, stored on each vcpu. We only keep one bit of
 *     information per interrupt, making sure that only one vcpu can
 *     accept the interrupt.
 * - 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_active 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_active. This allow the
 *   interrupt line to be sampled again.
 */

#define VGIC_ADDR_UNDEF		(-1)
#define IS_VGIC_ADDR_UNDEF(_x)  ((_x) == VGIC_ADDR_UNDEF)

/* Physical address of vgic virtual cpu interface */
static phys_addr_t vgic_vcpu_base;

/* Virtual control interface base address */
static void __iomem *vgic_vctrl_base;

static struct device_node *vgic_node;

#define ACCESS_READ_VALUE	(1 << 0)
#define ACCESS_READ_RAZ		(0 << 0)
#define ACCESS_READ_MASK(x)	((x) & (1 << 0))
#define ACCESS_WRITE_IGNORED	(0 << 1)
#define ACCESS_WRITE_SETBIT	(1 << 1)
#define ACCESS_WRITE_CLEARBIT	(2 << 1)
#define ACCESS_WRITE_VALUE	(3 << 1)
#define ACCESS_WRITE_MASK(x)	((x) & (3 << 1))

static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
static void vgic_update_state(struct kvm *kvm);
static void vgic_kick_vcpus(struct kvm *kvm);
static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg);
static u32 vgic_nr_lr;

static unsigned int vgic_maint_irq;

static u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x,
				int cpuid, u32 offset)
{
	offset >>= 2;
	if (!offset)
		return x->percpu[cpuid].reg;
	else
		return x->shared.reg + offset - 1;
}

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->percpu[cpuid].reg_ul);

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

static 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->percpu[cpuid].reg_ul;
	} else {
		reg =  x->shared.reg_ul;
		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)
{
	if (unlikely(cpuid >= VGIC_MAX_CPUS))
		return NULL;
	return x->percpu[cpuid].reg_ul;
}

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

static u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset)
{
	offset >>= 2;
	BUG_ON(offset > (VGIC_NR_IRQS / 4));
	if (offset < 4)
		return x->percpu[cpuid] + offset;
	else
		return x->shared + offset - 8;
}

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

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

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

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

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

	vgic_bitmap_set_irq_val(&dist->irq_active, 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_state, vcpu->vcpu_id, irq);
}

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

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

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

	vgic_bitmap_set_irq_val(&dist->irq_state, 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);
}

static 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 u32 mmio_data_read(struct kvm_exit_mmio *mmio, u32 mask)
{
	return *((u32 *)mmio->data) & mask;
}

static void mmio_data_write(struct kvm_exit_mmio *mmio, u32 mask, u32 value)
{
	*((u32 *)mmio->data) = value & mask;
}

/**
 * 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)
 */
static 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);
		}
	}
}

static bool handle_mmio_misc(struct kvm_vcpu *vcpu,
			     struct kvm_exit_mmio *mmio, phys_addr_t offset)
{
	u32 reg;
	u32 word_offset = offset & 3;

	switch (offset & ~3) {
	case 0:			/* CTLR */
		reg = vcpu->kvm->arch.vgic.enabled;
		vgic_reg_access(mmio, &reg, word_offset,
				ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
		if (mmio->is_write) {
			vcpu->kvm->arch.vgic.enabled = reg & 1;
			vgic_update_state(vcpu->kvm);
			return true;
		}
		break;

	case 4:			/* TYPER */
		reg  = (atomic_read(&vcpu->kvm->online_vcpus) - 1) << 5;
		reg |= (VGIC_NR_IRQS >> 5) - 1;
		vgic_reg_access(mmio, &reg, word_offset,
				ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
		break;

	case 8:			/* IIDR */
		reg = 0x4B00043B;
		vgic_reg_access(mmio, &reg, word_offset,
				ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
		break;
	}

	return false;
}

static 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;
}

static bool handle_mmio_set_enable_reg(struct kvm_vcpu *vcpu,
				       struct kvm_exit_mmio *mmio,
				       phys_addr_t offset)
{
	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_enabled,
				       vcpu->vcpu_id, offset);
	vgic_reg_access(mmio, reg, offset,
			ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
	if (mmio->is_write) {
		vgic_update_state(vcpu->kvm);
		return true;
	}

	return false;
}

static bool handle_mmio_clear_enable_reg(struct kvm_vcpu *vcpu,
					 struct kvm_exit_mmio *mmio,
					 phys_addr_t offset)
{
	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_enabled,
				       vcpu->vcpu_id, offset);
	vgic_reg_access(mmio, reg, offset,
			ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
	if (mmio->is_write) {
		if (offset < 4) /* Force SGI enabled */
			*reg |= 0xffff;
		vgic_retire_disabled_irqs(vcpu);
		vgic_update_state(vcpu->kvm);
		return true;
	}

	return false;
}

static bool handle_mmio_set_pending_reg(struct kvm_vcpu *vcpu,
					struct kvm_exit_mmio *mmio,
					phys_addr_t offset)
{
	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state,
				       vcpu->vcpu_id, offset);
	vgic_reg_access(mmio, reg, offset,
			ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
	if (mmio->is_write) {
		vgic_update_state(vcpu->kvm);
		return true;
	}

	return false;
}

static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu,
					  struct kvm_exit_mmio *mmio,
					  phys_addr_t offset)
{
	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state,
				       vcpu->vcpu_id, offset);
	vgic_reg_access(mmio, reg, offset,
			ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
	if (mmio->is_write) {
		vgic_update_state(vcpu->kvm);
		return true;
	}

	return false;
}

static bool handle_mmio_priority_reg(struct kvm_vcpu *vcpu,
				     struct kvm_exit_mmio *mmio,
				     phys_addr_t offset)
{
	u32 *reg = vgic_bytemap_get_reg(&vcpu->kvm->arch.vgic.irq_priority,
					vcpu->vcpu_id, offset);
	vgic_reg_access(mmio, reg, offset,
			ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
	return false;
}

#define GICD_ITARGETSR_SIZE	32
#define GICD_CPUTARGETS_BITS	8
#define GICD_IRQS_PER_ITARGETSR	(GICD_ITARGETSR_SIZE / GICD_CPUTARGETS_BITS)
static u32 vgic_get_target_reg(struct kvm *kvm, int irq)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct kvm_vcpu *vcpu;
	int i, c;
	unsigned long *bmap;
	u32 val = 0;

	irq -= VGIC_NR_PRIVATE_IRQS;

	kvm_for_each_vcpu(c, vcpu, kvm) {
		bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[c]);
		for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++)
			if (test_bit(irq + i, bmap))
				val |= 1 << (c + i * 8);
	}

	return val;
}

static void vgic_set_target_reg(struct kvm *kvm, u32 val, int irq)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct kvm_vcpu *vcpu;
	int i, c;
	unsigned long *bmap;
	u32 target;

	irq -= VGIC_NR_PRIVATE_IRQS;

	/*
	 * Pick the LSB in each byte. This ensures we target exactly
	 * one vcpu per IRQ. If the byte is null, assume we target
	 * CPU0.
	 */
	for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++) {
		int shift = i * GICD_CPUTARGETS_BITS;
		target = ffs((val >> shift) & 0xffU);
		target = target ? (target - 1) : 0;
		dist->irq_spi_cpu[irq + i] = target;
		kvm_for_each_vcpu(c, vcpu, kvm) {
			bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[c]);
			if (c == target)
				set_bit(irq + i, bmap);
			else
				clear_bit(irq + i, bmap);
		}
	}
}

static bool handle_mmio_target_reg(struct kvm_vcpu *vcpu,
				   struct kvm_exit_mmio *mmio,
				   phys_addr_t offset)
{
	u32 reg;

	/* We treat the banked interrupts targets as read-only */
	if (offset < 32) {
		u32 roreg = 1 << vcpu->vcpu_id;
		roreg |= roreg << 8;
		roreg |= roreg << 16;

		vgic_reg_access(mmio, &roreg, offset,
				ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
		return false;
	}

	reg = vgic_get_target_reg(vcpu->kvm, offset & ~3U);
	vgic_reg_access(mmio, &reg, offset,
			ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
	if (mmio->is_write) {
		vgic_set_target_reg(vcpu->kvm, reg, offset & ~3U);
		vgic_update_state(vcpu->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
 */
static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
				struct kvm_exit_mmio *mmio, phys_addr_t offset)
{
	u32 val;
	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
				       vcpu->vcpu_id, offset >> 1);
	if (offset & 2)
		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 < 4) {
			*reg = ~0U; /* Force PPIs/SGIs to 1 */
			return false;
		}

		val = vgic_cfg_compress(val);
		if (offset & 2) {
			*reg &= 0xffff;
			*reg |= val << 16;
		} else {
			*reg &= 0xffff << 16;
			*reg |= val;
		}
	}

	return false;
}

static bool handle_mmio_sgi_reg(struct kvm_vcpu *vcpu,
				struct kvm_exit_mmio *mmio, phys_addr_t offset)
{
	u32 reg;
	vgic_reg_access(mmio, &reg, offset,
			ACCESS_READ_RAZ | ACCESS_WRITE_VALUE);
	if (mmio->is_write) {
		vgic_dispatch_sgi(vcpu, reg);
		vgic_update_state(vcpu->kvm);
		return true;
	}

	return false;
}

/*
 * I would have liked to use the kvm_bus_io_*() API instead, but it
 * cannot cope with banked registers (only the VM pointer is passed
 * around, and we need the vcpu). One of these days, someone please
 * fix it!
 */
struct mmio_range {
	phys_addr_t base;
	unsigned long len;
	bool (*handle_mmio)(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
			    phys_addr_t offset);
};

static const struct mmio_range vgic_ranges[] = {
	{
		.base		= GIC_DIST_CTRL,
		.len		= 12,
		.handle_mmio	= handle_mmio_misc,
	},
	{
		.base		= GIC_DIST_IGROUP,
		.len		= VGIC_NR_IRQS / 8,
		.handle_mmio	= handle_mmio_raz_wi,
	},
	{
		.base		= GIC_DIST_ENABLE_SET,
		.len		= VGIC_NR_IRQS / 8,
		.handle_mmio	= handle_mmio_set_enable_reg,
	},
	{
		.base		= GIC_DIST_ENABLE_CLEAR,
		.len		= VGIC_NR_IRQS / 8,
		.handle_mmio	= handle_mmio_clear_enable_reg,
	},
	{
		.base		= GIC_DIST_PENDING_SET,
		.len		= VGIC_NR_IRQS / 8,
		.handle_mmio	= handle_mmio_set_pending_reg,
	},
	{
		.base		= GIC_DIST_PENDING_CLEAR,
		.len		= VGIC_NR_IRQS / 8,
		.handle_mmio	= handle_mmio_clear_pending_reg,
	},
	{
		.base		= GIC_DIST_ACTIVE_SET,
		.len		= VGIC_NR_IRQS / 8,
		.handle_mmio	= handle_mmio_raz_wi,
	},
	{
		.base		= GIC_DIST_ACTIVE_CLEAR,
		.len		= VGIC_NR_IRQS / 8,
		.handle_mmio	= handle_mmio_raz_wi,
	},
	{
		.base		= GIC_DIST_PRI,
		.len		= VGIC_NR_IRQS,
		.handle_mmio	= handle_mmio_priority_reg,
	},
	{
		.base		= GIC_DIST_TARGET,
		.len		= VGIC_NR_IRQS,
		.handle_mmio	= handle_mmio_target_reg,
	},
	{
		.base		= GIC_DIST_CONFIG,
		.len		= VGIC_NR_IRQS / 4,
		.handle_mmio	= handle_mmio_cfg_reg,
	},
	{
		.base		= GIC_DIST_SOFTINT,
		.len		= 4,
		.handle_mmio	= handle_mmio_sgi_reg,
	},
	{}
};

static const
struct mmio_range *find_matching_range(const struct mmio_range *ranges,
				       struct kvm_exit_mmio *mmio,
				       phys_addr_t base)
{
	const struct mmio_range *r = ranges;
	phys_addr_t addr = mmio->phys_addr - base;

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

	return NULL;
}

/**
 * vgic_handle_mmio - 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
 *
 * returns true if the MMIO access has been performed in kernel space,
 * and false if it needs to be emulated in user space.
 */
bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
		      struct kvm_exit_mmio *mmio)
{
	const struct mmio_range *range;
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
	unsigned long base = dist->vgic_dist_base;
	bool updated_state;
	unsigned long offset;

	if (!irqchip_in_kernel(vcpu->kvm) ||
	    mmio->phys_addr < base ||
	    (mmio->phys_addr + mmio->len) > (base + KVM_VGIC_V2_DIST_SIZE))
		return false;

	/* We don't support ldrd / strd or ldm / stm to the emulated vgic */
	if (mmio->len > 4) {
		kvm_inject_dabt(vcpu, mmio->phys_addr);
		return true;
	}

	range = find_matching_range(vgic_ranges, mmio, base);
	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 = mmio->phys_addr - range->base - base;
	updated_state = range->handle_mmio(vcpu, mmio, offset);
	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;
}

static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
{
	struct kvm *kvm = vcpu->kvm;
	struct vgic_dist *dist = &kvm->arch.vgic;
	int nrcpus = atomic_read(&kvm->online_vcpus);
	u8 target_cpus;
	int sgi, mode, c, vcpu_id;

	vcpu_id = vcpu->vcpu_id;

	sgi = reg & 0xf;
	target_cpus = (reg >> 16) & 0xff;
	mode = (reg >> 24) & 3;

	switch (mode) {
	case 0:
		if (!target_cpus)
			return;

	case 1:
		target_cpus = ((1 << nrcpus) - 1) & ~(1 << vcpu_id) & 0xff;
		break;

	case 2:
		target_cpus = 1 << vcpu_id;
		break;
	}

	kvm_for_each_vcpu(c, vcpu, kvm) {
		if (target_cpus & 1) {
			/* Flag the SGI as pending */
			vgic_dist_irq_set(vcpu, sgi);
			dist->irq_sgi_sources[c][sgi] |= 1 << vcpu_id;
			kvm_debug("SGI%d from CPU%d to CPU%d\n", sgi, vcpu_id, c);
		}

		target_cpus >>= 1;
	}
}

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

	pending_private = find_first_bit(pend_percpu, VGIC_NR_PRIVATE_IRQS);
	pending_shared = find_first_bit(pend_shared, VGIC_NR_SHARED_IRQS);
	return (pending_private < VGIC_NR_PRIVATE_IRQS ||
		pending_shared < VGIC_NR_SHARED_IRQS);
}

/*
 * Update the interrupt state and determine which CPUs have pending
 * interrupts. Must be called with distributor lock held.
 */
static 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);
		}
	}
}

#define LR_CPUID(lr)	\
	(((lr) & GICH_LR_PHYSID_CPUID) >> GICH_LR_PHYSID_CPUID_SHIFT)
#define MK_LR_PEND(src, irq)	\
	(GICH_LR_PENDING_BIT | ((src) << GICH_LR_PHYSID_CPUID_SHIFT) | (irq))

/*
 * 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_cpu->nr_lr) {
		int irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID;

		if (!vgic_irq_is_enabled(vcpu, irq)) {
			vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
			clear_bit(lr, vgic_cpu->lr_used);
			vgic_cpu->vgic_lr[lr] &= ~GICH_LR_STATE;
			if (vgic_irq_is_active(vcpu, irq))
				vgic_irq_clear_active(vcpu, irq);
		}
	}
}

/*
 * Queue an interrupt to a CPU virtual interface. Return true on success,
 * or false if it wasn't possible to queue it.
 */
static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	int lr;

	/* Sanitize the input... */
	BUG_ON(sgi_source_id & ~7);
	BUG_ON(sgi_source_id && irq >= VGIC_NR_SGIS);
	BUG_ON(irq >= VGIC_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 &&
	    (LR_CPUID(vgic_cpu->vgic_lr[lr]) == sgi_source_id)) {
		kvm_debug("LR%d piggyback for IRQ%d %x\n",
			  lr, irq, vgic_cpu->vgic_lr[lr]);
		BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
		vgic_cpu->vgic_lr[lr] |= GICH_LR_PENDING_BIT;

		goto out;
	}

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

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

out:
	if (!vgic_irq_is_edge(vcpu, irq))
		vgic_cpu->vgic_lr[lr] |= GICH_LR_EOI;

	return true;
}

static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
	unsigned long sources;
	int vcpu_id = vcpu->vcpu_id;
	int c;

	sources = dist->irq_sgi_sources[vcpu_id][irq];

	for_each_set_bit(c, &sources, VGIC_MAX_CPUS) {
		if (vgic_queue_irq(vcpu, c, irq))
			clear_bit(c, &sources);
	}

	dist->irq_sgi_sources[vcpu_id][irq] = sources;

	/*
	 * If the sources bitmap has been cleared it means that we
	 * could queue all the SGIs onto link registers (see the
	 * clear_bit above), and therefore we are done with them in
	 * our emulated gic and can get rid of them.
	 */
	if (!sources) {
		vgic_dist_irq_clear(vcpu, irq);
		vgic_cpu_irq_clear(vcpu, irq);
		return true;
	}

	return false;
}

static bool vgic_queue_hwirq(struct kvm_vcpu *vcpu, int irq)
{
	if (vgic_irq_is_active(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(vcpu, irq);
			vgic_cpu_irq_clear(vcpu, irq);
		} else {
			vgic_irq_set_active(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 (!vgic_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) {
		if (!vgic_queue_hwirq(vcpu, i + VGIC_NR_PRIVATE_IRQS))
			overflow = 1;
	}

epilog:
	if (overflow) {
		vgic_cpu->vgic_hcr |= GICH_HCR_UIE;
	} else {
		vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE;
		/*
		 * 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)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	bool level_pending = false;

	kvm_debug("MISR = %08x\n", vgic_cpu->vgic_misr);

	/*
	 * We do not need to take the distributor lock here, since the only
	 * action we perform is clearing the irq_active_bit for an EOIed
	 * level interrupt.  There is a potential race with
	 * the queuing of an interrupt in __kvm_vgic_flush_hwstate(), where we
	 * check if the interrupt is already active. Two possibilities:
	 *
	 * - The queuing is occurring on the same vcpu: cannot happen,
	 *   as we're already in the context of this vcpu, and
	 *   executing the handler
	 * - The interrupt has been migrated to another vcpu, and we
	 *   ignore this interrupt for this run. Big deal. It is still
	 *   pending though, and will get considered when this vcpu
	 *   exits.
	 */
	if (vgic_cpu->vgic_misr & GICH_MISR_EOI) {
		/*
		 * Some level interrupts have been EOIed. Clear their
		 * active bit.
		 */
		int lr, irq;

		for_each_set_bit(lr, (unsigned long *)vgic_cpu->vgic_eisr,
				 vgic_cpu->nr_lr) {
			irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID;

			vgic_irq_clear_active(vcpu, irq);
			vgic_cpu->vgic_lr[lr] &= ~GICH_LR_EOI;

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

	if (vgic_cpu->vgic_misr & GICH_MISR_U)
		vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE;

	return level_pending;
}

/*
 * Sync back the VGIC state after a guest run. We do not really touch
 * the distributor here (the irq_pending_on_cpu bit is safe to set),
 * so there is no need for taking its lock.
 */
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;
	int lr, pending;
	bool level_pending;

	level_pending = vgic_process_maintenance(vcpu);

	/* Clear mappings for empty LRs */
	for_each_set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr,
			 vgic_cpu->nr_lr) {
		int irq;

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

		irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID;

		BUG_ON(irq >= VGIC_NR_IRQS);
		vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
	}

	/* Check if we still have something up our sleeve... */
	pending = find_first_zero_bit((unsigned long *)vgic_cpu->vgic_elrsr,
				      vgic_cpu->nr_lr);
	if (level_pending || pending < vgic_cpu->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)
{
	if (!irqchip_in_kernel(vcpu->kvm))
		return;

	__kvm_vgic_sync_hwstate(vcpu);
}

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);
}

static 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 is_edge = vgic_irq_is_edge(vcpu, irq);
	int state = vgic_dist_irq_is_pending(vcpu, irq);

	/*
	 * Only inject an interrupt if:
	 * - edge triggered and we have a rising edge
	 * - level triggered and we change level
	 */
	if (is_edge)
		return level > state;
	else
		return level != state;
}

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

	spin_lock(&dist->lock);

	vcpu = kvm_get_vcpu(kvm, cpuid);
	is_edge = vgic_irq_is_edge(vcpu, irq_num);
	is_level = !is_edge;

	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];
		vcpu = kvm_get_vcpu(kvm, cpuid);
	}

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

	if (level)
		vgic_dist_irq_set(vcpu, irq_num);
	else
		vgic_dist_irq_clear(vcpu, irq_num);

	enabled = vgic_irq_is_enabled(vcpu, irq_num);

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

	if (is_level && vgic_irq_is_active(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;
}

/**
 * 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)
{
	if (vgic_update_irq_state(kvm, cpuid, irq_num, level))
		vgic_kick_vcpus(kvm);

	return 0;
}

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;
}

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

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

	if (vcpu->vcpu_id >= VGIC_MAX_CPUS)
		return -EBUSY;

	for (i = 0; i < VGIC_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_cpu->vgic_irq_lr_map[i] = LR_EMPTY;
	}

	/*
	 * By forcing VMCR to zero, the GIC will restore the binary
	 * points to their reset values. Anything else resets to zero
	 * anyway.
	 */
	vgic_cpu->vgic_vmcr = 0;

	vgic_cpu->nr_lr = vgic_nr_lr;
	vgic_cpu->vgic_hcr = GICH_HCR_EN; /* Get the show on the road... */

	return 0;
}

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,
};

int kvm_vgic_hyp_init(void)
{
	int ret;
	struct resource vctrl_res;
	struct resource vcpu_res;

	vgic_node = of_find_compatible_node(NULL, NULL, "arm,cortex-a15-gic");
	if (!vgic_node) {
		kvm_err("error: no compatible vgic node in DT\n");
		return -ENODEV;
	}

	vgic_maint_irq = irq_of_parse_and_map(vgic_node, 0);
	if (!vgic_maint_irq) {
		kvm_err("error getting vgic maintenance irq from DT\n");
		ret = -ENXIO;
		goto out;
	}

	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);
		goto out;
	}

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

	ret = of_address_to_resource(vgic_node, 2, &vctrl_res);
	if (ret) {
		kvm_err("Cannot obtain VCTRL resource\n");
		goto out_free_irq;
	}

	vgic_vctrl_base = of_iomap(vgic_node, 2);
	if (!vgic_vctrl_base) {
		kvm_err("Cannot ioremap VCTRL\n");
		ret = -ENOMEM;
		goto out_free_irq;
	}

	vgic_nr_lr = readl_relaxed(vgic_vctrl_base + GICH_VTR);
	vgic_nr_lr = (vgic_nr_lr & 0x3f) + 1;

	ret = create_hyp_io_mappings(vgic_vctrl_base,
				     vgic_vctrl_base + resource_size(&vctrl_res),
				     vctrl_res.start);
	if (ret) {
		kvm_err("Cannot map VCTRL into hyp\n");
		goto out_unmap;
	}

	kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
		 vctrl_res.start, vgic_maint_irq);
	on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);

	if (of_address_to_resource(vgic_node, 3, &vcpu_res)) {
		kvm_err("Cannot obtain VCPU resource\n");
		ret = -ENXIO;
		goto out_unmap;
	}
	vgic_vcpu_base = vcpu_res.start;

	goto out;

out_unmap:
	iounmap(vgic_vctrl_base);
out_free_irq:
	free_percpu_irq(vgic_maint_irq, kvm_get_running_vcpus());
out:
	of_node_put(vgic_node);
	return ret;
}

int kvm_vgic_init(struct kvm *kvm)
{
	int ret = 0, i;

	mutex_lock(&kvm->lock);

	if (vgic_initialized(kvm))
		goto out;

	if (IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_dist_base) ||
	    IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_cpu_base)) {
		kvm_err("Need to set vgic cpu and dist addresses first\n");
		ret = -ENXIO;
		goto out;
	}

	ret = kvm_phys_addr_ioremap(kvm, kvm->arch.vgic.vgic_cpu_base,
				    vgic_vcpu_base, KVM_VGIC_V2_CPU_SIZE);
	if (ret) {
		kvm_err("Unable to remap VGIC CPU to VCPU\n");
		goto out;
	}

	for (i = VGIC_NR_PRIVATE_IRQS; i < VGIC_NR_IRQS; i += 4)
		vgic_set_target_reg(kvm, 0, i);

	kvm_timer_init(kvm);
	kvm->arch.vgic.ready = true;
out:
	mutex_unlock(&kvm->lock);
	return ret;
}

int kvm_vgic_create(struct kvm *kvm)
{
	int ret = 0;

	mutex_lock(&kvm->lock);

	if (atomic_read(&kvm->online_vcpus) || kvm->arch.vgic.vctrl_base) {
		ret = -EEXIST;
		goto out;
	}

	spin_lock_init(&kvm->arch.vgic.lock);
	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;

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

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

	ret = vgic_ioaddr_overlap(kvm);
	if (ret)
		return ret;
	*ioaddr = addr;
	return ret;
}

int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr)
{
	int r = 0;
	struct vgic_dist *vgic = &kvm->arch.vgic;

	if (addr & ~KVM_PHYS_MASK)
		return -E2BIG;

	if (addr & ~PAGE_MASK)
		return -EINVAL;

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

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