summaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/mpic.c
blob: 23e9c2bd9f2710f653b985c35de2b316763ee092 (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
/*
 * OpenPIC emulation
 *
 * Copyright (c) 2004 Jocelyn Mayer
 *               2011 Alexander Graf
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

#include <linux/slab.h>
#include <linux/mutex.h>
#include <linux/kvm_host.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/anon_inodes.h>
#include <linux/uaccess.h>
#include <asm/mpic.h>
#include <asm/kvm_para.h>
#include <asm/kvm_ppc.h>
#include <kvm/iodev.h>

#define MAX_CPU     32
#define MAX_SRC     256
#define MAX_TMR     4
#define MAX_IPI     4
#define MAX_MSI     8
#define MAX_IRQ     (MAX_SRC + MAX_IPI + MAX_TMR)
#define VID         0x03	/* MPIC version ID */

/* OpenPIC capability flags */
#define OPENPIC_FLAG_IDR_CRIT     (1 << 0)
#define OPENPIC_FLAG_ILR          (2 << 0)

/* OpenPIC address map */
#define OPENPIC_REG_SIZE             0x40000
#define OPENPIC_GLB_REG_START        0x0
#define OPENPIC_GLB_REG_SIZE         0x10F0
#define OPENPIC_TMR_REG_START        0x10F0
#define OPENPIC_TMR_REG_SIZE         0x220
#define OPENPIC_MSI_REG_START        0x1600
#define OPENPIC_MSI_REG_SIZE         0x200
#define OPENPIC_SUMMARY_REG_START    0x3800
#define OPENPIC_SUMMARY_REG_SIZE     0x800
#define OPENPIC_SRC_REG_START        0x10000
#define OPENPIC_SRC_REG_SIZE         (MAX_SRC * 0x20)
#define OPENPIC_CPU_REG_START        0x20000
#define OPENPIC_CPU_REG_SIZE         (0x100 + ((MAX_CPU - 1) * 0x1000))

struct fsl_mpic_info {
	int max_ext;
};

static struct fsl_mpic_info fsl_mpic_20 = {
	.max_ext = 12,
};

static struct fsl_mpic_info fsl_mpic_42 = {
	.max_ext = 12,
};

#define FRR_NIRQ_SHIFT    16
#define FRR_NCPU_SHIFT     8
#define FRR_VID_SHIFT      0

#define VID_REVISION_1_2   2
#define VID_REVISION_1_3   3

#define VIR_GENERIC      0x00000000	/* Generic Vendor ID */

#define GCR_RESET        0x80000000
#define GCR_MODE_PASS    0x00000000
#define GCR_MODE_MIXED   0x20000000
#define GCR_MODE_PROXY   0x60000000

#define TBCR_CI           0x80000000	/* count inhibit */
#define TCCR_TOG          0x80000000	/* toggles when decrement to zero */

#define IDR_EP_SHIFT      31
#define IDR_EP_MASK       (1 << IDR_EP_SHIFT)
#define IDR_CI0_SHIFT     30
#define IDR_CI1_SHIFT     29
#define IDR_P1_SHIFT      1
#define IDR_P0_SHIFT      0

#define ILR_INTTGT_MASK   0x000000ff
#define ILR_INTTGT_INT    0x00
#define ILR_INTTGT_CINT   0x01	/* critical */
#define ILR_INTTGT_MCP    0x02	/* machine check */
#define NUM_OUTPUTS       3

#define MSIIR_OFFSET       0x140
#define MSIIR_SRS_SHIFT    29
#define MSIIR_SRS_MASK     (0x7 << MSIIR_SRS_SHIFT)
#define MSIIR_IBS_SHIFT    24
#define MSIIR_IBS_MASK     (0x1f << MSIIR_IBS_SHIFT)

static int get_current_cpu(void)
{
#if defined(CONFIG_KVM) && defined(CONFIG_BOOKE)
	struct kvm_vcpu *vcpu = current->thread.kvm_vcpu;
	return vcpu ? vcpu->arch.irq_cpu_id : -1;
#else
	/* XXX */
	return -1;
#endif
}

static int openpic_cpu_write_internal(void *opaque, gpa_t addr,
				      u32 val, int idx);
static int openpic_cpu_read_internal(void *opaque, gpa_t addr,
				     u32 *ptr, int idx);
static inline void write_IRQreg_idr(struct openpic *opp, int n_IRQ,
				    uint32_t val);

enum irq_type {
	IRQ_TYPE_NORMAL = 0,
	IRQ_TYPE_FSLINT,	/* FSL internal interrupt -- level only */
	IRQ_TYPE_FSLSPECIAL,	/* FSL timer/IPI interrupt, edge, no polarity */
};

struct irq_queue {
	/* Round up to the nearest 64 IRQs so that the queue length
	 * won't change when moving between 32 and 64 bit hosts.
	 */
	unsigned long queue[BITS_TO_LONGS((MAX_IRQ + 63) & ~63)];
	int next;
	int priority;
};

struct irq_source {
	uint32_t ivpr;		/* IRQ vector/priority register */
	uint32_t idr;		/* IRQ destination register */
	uint32_t destmask;	/* bitmap of CPU destinations */
	int last_cpu;
	int output;		/* IRQ level, e.g. ILR_INTTGT_INT */
	int pending;		/* TRUE if IRQ is pending */
	enum irq_type type;
	bool level:1;		/* level-triggered */
	bool nomask:1;	/* critical interrupts ignore mask on some FSL MPICs */
};

#define IVPR_MASK_SHIFT       31
#define IVPR_MASK_MASK        (1 << IVPR_MASK_SHIFT)
#define IVPR_ACTIVITY_SHIFT   30
#define IVPR_ACTIVITY_MASK    (1 << IVPR_ACTIVITY_SHIFT)
#define IVPR_MODE_SHIFT       29
#define IVPR_MODE_MASK        (1 << IVPR_MODE_SHIFT)
#define IVPR_POLARITY_SHIFT   23
#define IVPR_POLARITY_MASK    (1 << IVPR_POLARITY_SHIFT)
#define IVPR_SENSE_SHIFT      22
#define IVPR_SENSE_MASK       (1 << IVPR_SENSE_SHIFT)

#define IVPR_PRIORITY_MASK     (0xF << 16)
#define IVPR_PRIORITY(_ivprr_) ((int)(((_ivprr_) & IVPR_PRIORITY_MASK) >> 16))
#define IVPR_VECTOR(opp, _ivprr_) ((_ivprr_) & (opp)->vector_mask)

/* IDR[EP/CI] are only for FSL MPIC prior to v4.0 */
#define IDR_EP      0x80000000	/* external pin */
#define IDR_CI      0x40000000	/* critical interrupt */

struct irq_dest {
	struct kvm_vcpu *vcpu;

	int32_t ctpr;		/* CPU current task priority */
	struct irq_queue raised;
	struct irq_queue servicing;

	/* Count of IRQ sources asserting on non-INT outputs */
	uint32_t outputs_active[NUM_OUTPUTS];
};

#define MAX_MMIO_REGIONS 10

struct openpic {
	struct kvm *kvm;
	struct kvm_device *dev;
	struct kvm_io_device mmio;
	const struct mem_reg *mmio_regions[MAX_MMIO_REGIONS];
	int num_mmio_regions;

	gpa_t reg_base;
	spinlock_t lock;

	/* Behavior control */
	struct fsl_mpic_info *fsl;
	uint32_t model;
	uint32_t flags;
	uint32_t nb_irqs;
	uint32_t vid;
	uint32_t vir;		/* Vendor identification register */
	uint32_t vector_mask;
	uint32_t tfrr_reset;
	uint32_t ivpr_reset;
	uint32_t idr_reset;
	uint32_t brr1;
	uint32_t mpic_mode_mask;

	/* Global registers */
	uint32_t frr;		/* Feature reporting register */
	uint32_t gcr;		/* Global configuration register  */
	uint32_t pir;		/* Processor initialization register */
	uint32_t spve;		/* Spurious vector register */
	uint32_t tfrr;		/* Timer frequency reporting register */
	/* Source registers */
	struct irq_source src[MAX_IRQ];
	/* Local registers per output pin */
	struct irq_dest dst[MAX_CPU];
	uint32_t nb_cpus;
	/* Timer registers */
	struct {
		uint32_t tccr;	/* Global timer current count register */
		uint32_t tbcr;	/* Global timer base count register */
	} timers[MAX_TMR];
	/* Shared MSI registers */
	struct {
		uint32_t msir;	/* Shared Message Signaled Interrupt Register */
	} msi[MAX_MSI];
	uint32_t max_irq;
	uint32_t irq_ipi0;
	uint32_t irq_tim0;
	uint32_t irq_msi;
};


static void mpic_irq_raise(struct openpic *opp, struct irq_dest *dst,
			   int output)
{
	struct kvm_interrupt irq = {
		.irq = KVM_INTERRUPT_SET_LEVEL,
	};

	if (!dst->vcpu) {
		pr_debug("%s: destination cpu %d does not exist\n",
			 __func__, (int)(dst - &opp->dst[0]));
		return;
	}

	pr_debug("%s: cpu %d output %d\n", __func__, dst->vcpu->arch.irq_cpu_id,
		output);

	if (output != ILR_INTTGT_INT)	/* TODO */
		return;

	kvm_vcpu_ioctl_interrupt(dst->vcpu, &irq);
}

static void mpic_irq_lower(struct openpic *opp, struct irq_dest *dst,
			   int output)
{
	if (!dst->vcpu) {
		pr_debug("%s: destination cpu %d does not exist\n",
			 __func__, (int)(dst - &opp->dst[0]));
		return;
	}

	pr_debug("%s: cpu %d output %d\n", __func__, dst->vcpu->arch.irq_cpu_id,
		output);

	if (output != ILR_INTTGT_INT)	/* TODO */
		return;

	kvmppc_core_dequeue_external(dst->vcpu);
}

static inline void IRQ_setbit(struct irq_queue *q, int n_IRQ)
{
	set_bit(n_IRQ, q->queue);
}

static inline void IRQ_resetbit(struct irq_queue *q, int n_IRQ)
{
	clear_bit(n_IRQ, q->queue);
}

static void IRQ_check(struct openpic *opp, struct irq_queue *q)
{
	int irq = -1;
	int next = -1;
	int priority = -1;

	for (;;) {
		irq = find_next_bit(q->queue, opp->max_irq, irq + 1);
		if (irq == opp->max_irq)
			break;

		pr_debug("IRQ_check: irq %d set ivpr_pr=%d pr=%d\n",
			irq, IVPR_PRIORITY(opp->src[irq].ivpr), priority);

		if (IVPR_PRIORITY(opp->src[irq].ivpr) > priority) {
			next = irq;
			priority = IVPR_PRIORITY(opp->src[irq].ivpr);
		}
	}

	q->next = next;
	q->priority = priority;
}

static int IRQ_get_next(struct openpic *opp, struct irq_queue *q)
{
	/* XXX: optimize */
	IRQ_check(opp, q);

	return q->next;
}

static void IRQ_local_pipe(struct openpic *opp, int n_CPU, int n_IRQ,
			   bool active, bool was_active)
{
	struct irq_dest *dst;
	struct irq_source *src;
	int priority;

	dst = &opp->dst[n_CPU];
	src = &opp->src[n_IRQ];

	pr_debug("%s: IRQ %d active %d was %d\n",
		__func__, n_IRQ, active, was_active);

	if (src->output != ILR_INTTGT_INT) {
		pr_debug("%s: output %d irq %d active %d was %d count %d\n",
			__func__, src->output, n_IRQ, active, was_active,
			dst->outputs_active[src->output]);

		/* On Freescale MPIC, critical interrupts ignore priority,
		 * IACK, EOI, etc.  Before MPIC v4.1 they also ignore
		 * masking.
		 */
		if (active) {
			if (!was_active &&
			    dst->outputs_active[src->output]++ == 0) {
				pr_debug("%s: Raise OpenPIC output %d cpu %d irq %d\n",
					__func__, src->output, n_CPU, n_IRQ);
				mpic_irq_raise(opp, dst, src->output);
			}
		} else {
			if (was_active &&
			    --dst->outputs_active[src->output] == 0) {
				pr_debug("%s: Lower OpenPIC output %d cpu %d irq %d\n",
					__func__, src->output, n_CPU, n_IRQ);
				mpic_irq_lower(opp, dst, src->output);
			}
		}

		return;
	}

	priority = IVPR_PRIORITY(src->ivpr);

	/* Even if the interrupt doesn't have enough priority,
	 * it is still raised, in case ctpr is lowered later.
	 */
	if (active)
		IRQ_setbit(&dst->raised, n_IRQ);
	else
		IRQ_resetbit(&dst->raised, n_IRQ);

	IRQ_check(opp, &dst->raised);

	if (active && priority <= dst->ctpr) {
		pr_debug("%s: IRQ %d priority %d too low for ctpr %d on CPU %d\n",
			__func__, n_IRQ, priority, dst->ctpr, n_CPU);
		active = 0;
	}

	if (active) {
		if (IRQ_get_next(opp, &dst->servicing) >= 0 &&
		    priority <= dst->servicing.priority) {
			pr_debug("%s: IRQ %d is hidden by servicing IRQ %d on CPU %d\n",
				__func__, n_IRQ, dst->servicing.next, n_CPU);
		} else {
			pr_debug("%s: Raise OpenPIC INT output cpu %d irq %d/%d\n",
				__func__, n_CPU, n_IRQ, dst->raised.next);
			mpic_irq_raise(opp, dst, ILR_INTTGT_INT);
		}
	} else {
		IRQ_get_next(opp, &dst->servicing);
		if (dst->raised.priority > dst->ctpr &&
		    dst->raised.priority > dst->servicing.priority) {
			pr_debug("%s: IRQ %d inactive, IRQ %d prio %d above %d/%d, CPU %d\n",
				__func__, n_IRQ, dst->raised.next,
				dst->raised.priority, dst->ctpr,
				dst->servicing.priority, n_CPU);
			/* IRQ line stays asserted */
		} else {
			pr_debug("%s: IRQ %d inactive, current prio %d/%d, CPU %d\n",
				__func__, n_IRQ, dst->ctpr,
				dst->servicing.priority, n_CPU);
			mpic_irq_lower(opp, dst, ILR_INTTGT_INT);
		}
	}
}

/* update pic state because registers for n_IRQ have changed value */
static void openpic_update_irq(struct openpic *opp, int n_IRQ)
{
	struct irq_source *src;
	bool active, was_active;
	int i;

	src = &opp->src[n_IRQ];
	active = src->pending;

	if ((src->ivpr & IVPR_MASK_MASK) && !src->nomask) {
		/* Interrupt source is disabled */
		pr_debug("%s: IRQ %d is disabled\n", __func__, n_IRQ);
		active = false;
	}

	was_active = !!(src->ivpr & IVPR_ACTIVITY_MASK);

	/*
	 * We don't have a similar check for already-active because
	 * ctpr may have changed and we need to withdraw the interrupt.
	 */
	if (!active && !was_active) {
		pr_debug("%s: IRQ %d is already inactive\n", __func__, n_IRQ);
		return;
	}

	if (active)
		src->ivpr |= IVPR_ACTIVITY_MASK;
	else
		src->ivpr &= ~IVPR_ACTIVITY_MASK;

	if (src->destmask == 0) {
		/* No target */
		pr_debug("%s: IRQ %d has no target\n", __func__, n_IRQ);
		return;
	}

	if (src->destmask == (1 << src->last_cpu)) {
		/* Only one CPU is allowed to receive this IRQ */
		IRQ_local_pipe(opp, src->last_cpu, n_IRQ, active, was_active);
	} else if (!(src->ivpr & IVPR_MODE_MASK)) {
		/* Directed delivery mode */
		for (i = 0; i < opp->nb_cpus; i++) {
			if (src->destmask & (1 << i)) {
				IRQ_local_pipe(opp, i, n_IRQ, active,
					       was_active);
			}
		}
	} else {
		/* Distributed delivery mode */
		for (i = src->last_cpu + 1; i != src->last_cpu; i++) {
			if (i == opp->nb_cpus)
				i = 0;

			if (src->destmask & (1 << i)) {
				IRQ_local_pipe(opp, i, n_IRQ, active,
					       was_active);
				src->last_cpu = i;
				break;
			}
		}
	}
}

static void openpic_set_irq(void *opaque, int n_IRQ, int level)
{
	struct openpic *opp = opaque;
	struct irq_source *src;

	if (n_IRQ >= MAX_IRQ) {
		WARN_ONCE(1, "%s: IRQ %d out of range\n", __func__, n_IRQ);
		return;
	}

	src = &opp->src[n_IRQ];
	pr_debug("openpic: set irq %d = %d ivpr=0x%08x\n",
		n_IRQ, level, src->ivpr);
	if (src->level) {
		/* level-sensitive irq */
		src->pending = level;
		openpic_update_irq(opp, n_IRQ);
	} else {
		/* edge-sensitive irq */
		if (level) {
			src->pending = 1;
			openpic_update_irq(opp, n_IRQ);
		}

		if (src->output != ILR_INTTGT_INT) {
			/* Edge-triggered interrupts shouldn't be used
			 * with non-INT delivery, but just in case,
			 * try to make it do something sane rather than
			 * cause an interrupt storm.  This is close to
			 * what you'd probably see happen in real hardware.
			 */
			src->pending = 0;
			openpic_update_irq(opp, n_IRQ);
		}
	}
}

static void openpic_reset(struct openpic *opp)
{
	int i;

	opp->gcr = GCR_RESET;
	/* Initialise controller registers */
	opp->frr = ((opp->nb_irqs - 1) << FRR_NIRQ_SHIFT) |
	    (opp->vid << FRR_VID_SHIFT);

	opp->pir = 0;
	opp->spve = -1 & opp->vector_mask;
	opp->tfrr = opp->tfrr_reset;
	/* Initialise IRQ sources */
	for (i = 0; i < opp->max_irq; i++) {
		opp->src[i].ivpr = opp->ivpr_reset;

		switch (opp->src[i].type) {
		case IRQ_TYPE_NORMAL:
			opp->src[i].level =
			    !!(opp->ivpr_reset & IVPR_SENSE_MASK);
			break;

		case IRQ_TYPE_FSLINT:
			opp->src[i].ivpr |= IVPR_POLARITY_MASK;
			break;

		case IRQ_TYPE_FSLSPECIAL:
			break;
		}

		write_IRQreg_idr(opp, i, opp->idr_reset);
	}
	/* Initialise IRQ destinations */
	for (i = 0; i < MAX_CPU; i++) {
		opp->dst[i].ctpr = 15;
		memset(&opp->dst[i].raised, 0, sizeof(struct irq_queue));
		opp->dst[i].raised.next = -1;
		memset(&opp->dst[i].servicing, 0, sizeof(struct irq_queue));
		opp->dst[i].servicing.next = -1;
	}
	/* Initialise timers */
	for (i = 0; i < MAX_TMR; i++) {
		opp->timers[i].tccr = 0;
		opp->timers[i].tbcr = TBCR_CI;
	}
	/* Go out of RESET state */
	opp->gcr = 0;
}

static inline uint32_t read_IRQreg_idr(struct openpic *opp, int n_IRQ)
{
	return opp->src[n_IRQ].idr;
}

static inline uint32_t read_IRQreg_ilr(struct openpic *opp, int n_IRQ)
{
	if (opp->flags & OPENPIC_FLAG_ILR)
		return opp->src[n_IRQ].output;

	return 0xffffffff;
}

static inline uint32_t read_IRQreg_ivpr(struct openpic *opp, int n_IRQ)
{
	return opp->src[n_IRQ].ivpr;
}

static inline void write_IRQreg_idr(struct openpic *opp, int n_IRQ,
				    uint32_t val)
{
	struct irq_source *src = &opp->src[n_IRQ];
	uint32_t normal_mask = (1UL << opp->nb_cpus) - 1;
	uint32_t crit_mask = 0;
	uint32_t mask = normal_mask;
	int crit_shift = IDR_EP_SHIFT - opp->nb_cpus;
	int i;

	if (opp->flags & OPENPIC_FLAG_IDR_CRIT) {
		crit_mask = mask << crit_shift;
		mask |= crit_mask | IDR_EP;
	}

	src->idr = val & mask;
	pr_debug("Set IDR %d to 0x%08x\n", n_IRQ, src->idr);

	if (opp->flags & OPENPIC_FLAG_IDR_CRIT) {
		if (src->idr & crit_mask) {
			if (src->idr & normal_mask) {
				pr_debug("%s: IRQ configured for multiple output types, using critical\n",
					__func__);
			}

			src->output = ILR_INTTGT_CINT;
			src->nomask = true;
			src->destmask = 0;

			for (i = 0; i < opp->nb_cpus; i++) {
				int n_ci = IDR_CI0_SHIFT - i;

				if (src->idr & (1UL << n_ci))
					src->destmask |= 1UL << i;
			}
		} else {
			src->output = ILR_INTTGT_INT;
			src->nomask = false;
			src->destmask = src->idr & normal_mask;
		}
	} else {
		src->destmask = src->idr;
	}
}

static inline void write_IRQreg_ilr(struct openpic *opp, int n_IRQ,
				    uint32_t val)
{
	if (opp->flags & OPENPIC_FLAG_ILR) {
		struct irq_source *src = &opp->src[n_IRQ];

		src->output = val & ILR_INTTGT_MASK;
		pr_debug("Set ILR %d to 0x%08x, output %d\n", n_IRQ, src->idr,
			src->output);

		/* TODO: on MPIC v4.0 only, set nomask for non-INT */
	}
}

static inline void write_IRQreg_ivpr(struct openpic *opp, int n_IRQ,
				     uint32_t val)
{
	uint32_t mask;

	/* NOTE when implementing newer FSL MPIC models: starting with v4.0,
	 * the polarity bit is read-only on internal interrupts.
	 */
	mask = IVPR_MASK_MASK | IVPR_PRIORITY_MASK | IVPR_SENSE_MASK |
	    IVPR_POLARITY_MASK | opp->vector_mask;

	/* ACTIVITY bit is read-only */
	opp->src[n_IRQ].ivpr =
	    (opp->src[n_IRQ].ivpr & IVPR_ACTIVITY_MASK) | (val & mask);

	/* For FSL internal interrupts, The sense bit is reserved and zero,
	 * and the interrupt is always level-triggered.  Timers and IPIs
	 * have no sense or polarity bits, and are edge-triggered.
	 */
	switch (opp->src[n_IRQ].type) {
	case IRQ_TYPE_NORMAL:
		opp->src[n_IRQ].level =
		    !!(opp->src[n_IRQ].ivpr & IVPR_SENSE_MASK);
		break;

	case IRQ_TYPE_FSLINT:
		opp->src[n_IRQ].ivpr &= ~IVPR_SENSE_MASK;
		break;

	case IRQ_TYPE_FSLSPECIAL:
		opp->src[n_IRQ].ivpr &= ~(IVPR_POLARITY_MASK | IVPR_SENSE_MASK);
		break;
	}

	openpic_update_irq(opp, n_IRQ);
	pr_debug("Set IVPR %d to 0x%08x -> 0x%08x\n", n_IRQ, val,
		opp->src[n_IRQ].ivpr);
}

static void openpic_gcr_write(struct openpic *opp, uint64_t val)
{
	if (val & GCR_RESET) {
		openpic_reset(opp);
		return;
	}

	opp->gcr &= ~opp->mpic_mode_mask;
	opp->gcr |= val & opp->mpic_mode_mask;
}

static int openpic_gbl_write(void *opaque, gpa_t addr, u32 val)
{
	struct openpic *opp = opaque;
	int err = 0;

	pr_debug("%s: addr %#llx <= %08x\n", __func__, addr, val);
	if (addr & 0xF)
		return 0;

	switch (addr) {
	case 0x00:	/* Block Revision Register1 (BRR1) is Readonly */
		break;
	case 0x40:
	case 0x50:
	case 0x60:
	case 0x70:
	case 0x80:
	case 0x90:
	case 0xA0:
	case 0xB0:
		err = openpic_cpu_write_internal(opp, addr, val,
						 get_current_cpu());
		break;
	case 0x1000:		/* FRR */
		break;
	case 0x1020:		/* GCR */
		openpic_gcr_write(opp, val);
		break;
	case 0x1080:		/* VIR */
		break;
	case 0x1090:		/* PIR */
		/*
		 * This register is used to reset a CPU core --
		 * let userspace handle it.
		 */
		err = -ENXIO;
		break;
	case 0x10A0:		/* IPI_IVPR */
	case 0x10B0:
	case 0x10C0:
	case 0x10D0: {
		int idx;
		idx = (addr - 0x10A0) >> 4;
		write_IRQreg_ivpr(opp, opp->irq_ipi0 + idx, val);
		break;
	}
	case 0x10E0:		/* SPVE */
		opp->spve = val & opp->vector_mask;
		break;
	default:
		break;
	}

	return err;
}

static int openpic_gbl_read(void *opaque, gpa_t addr, u32 *ptr)
{
	struct openpic *opp = opaque;
	u32 retval;
	int err = 0;

	pr_debug("%s: addr %#llx\n", __func__, addr);
	retval = 0xFFFFFFFF;
	if (addr & 0xF)
		goto out;

	switch (addr) {
	case 0x1000:		/* FRR */
		retval = opp->frr;
		retval |= (opp->nb_cpus - 1) << FRR_NCPU_SHIFT;
		break;
	case 0x1020:		/* GCR */
		retval = opp->gcr;
		break;
	case 0x1080:		/* VIR */
		retval = opp->vir;
		break;
	case 0x1090:		/* PIR */
		retval = 0x00000000;
		break;
	case 0x00:		/* Block Revision Register1 (BRR1) */
		retval = opp->brr1;
		break;
	case 0x40:
	case 0x50:
	case 0x60:
	case 0x70:
	case 0x80:
	case 0x90:
	case 0xA0:
	case 0xB0:
		err = openpic_cpu_read_internal(opp, addr,
			&retval, get_current_cpu());
		break;
	case 0x10A0:		/* IPI_IVPR */
	case 0x10B0:
	case 0x10C0:
	case 0x10D0:
		{
			int idx;
			idx = (addr - 0x10A0) >> 4;
			retval = read_IRQreg_ivpr(opp, opp->irq_ipi0 + idx);
		}
		break;
	case 0x10E0:		/* SPVE */
		retval = opp->spve;
		break;
	default:
		break;
	}

out:
	pr_debug("%s: => 0x%08x\n", __func__, retval);
	*ptr = retval;
	return err;
}

static int openpic_tmr_write(void *opaque, gpa_t addr, u32 val)
{
	struct openpic *opp = opaque;
	int idx;

	addr += 0x10f0;

	pr_debug("%s: addr %#llx <= %08x\n", __func__, addr, val);
	if (addr & 0xF)
		return 0;

	if (addr == 0x10f0) {
		/* TFRR */
		opp->tfrr = val;
		return 0;
	}

	idx = (addr >> 6) & 0x3;
	addr = addr & 0x30;

	switch (addr & 0x30) {
	case 0x00:		/* TCCR */
		break;
	case 0x10:		/* TBCR */
		if ((opp->timers[idx].tccr & TCCR_TOG) != 0 &&
		    (val & TBCR_CI) == 0 &&
		    (opp->timers[idx].tbcr & TBCR_CI) != 0)
			opp->timers[idx].tccr &= ~TCCR_TOG;

		opp->timers[idx].tbcr = val;
		break;
	case 0x20:		/* TVPR */
		write_IRQreg_ivpr(opp, opp->irq_tim0 + idx, val);
		break;
	case 0x30:		/* TDR */
		write_IRQreg_idr(opp, opp->irq_tim0 + idx, val);
		break;
	}

	return 0;
}

static int openpic_tmr_read(void *opaque, gpa_t addr, u32 *ptr)
{
	struct openpic *opp = opaque;
	uint32_t retval = -1;
	int idx;

	pr_debug("%s: addr %#llx\n", __func__, addr);
	if (addr & 0xF)
		goto out;

	idx = (addr >> 6) & 0x3;
	if (addr == 0x0) {
		/* TFRR */
		retval = opp->tfrr;
		goto out;
	}

	switch (addr & 0x30) {
	case 0x00:		/* TCCR */
		retval = opp->timers[idx].tccr;
		break;
	case 0x10:		/* TBCR */
		retval = opp->timers[idx].tbcr;
		break;
	case 0x20:		/* TIPV */
		retval = read_IRQreg_ivpr(opp, opp->irq_tim0 + idx);
		break;
	case 0x30:		/* TIDE (TIDR) */
		retval = read_IRQreg_idr(opp, opp->irq_tim0 + idx);
		break;
	}

out:
	pr_debug("%s: => 0x%08x\n", __func__, retval);
	*ptr = retval;
	return 0;
}

static int openpic_src_write(void *opaque, gpa_t addr, u32 val)
{
	struct openpic *opp = opaque;
	int idx;

	pr_debug("%s: addr %#llx <= %08x\n", __func__, addr, val);

	addr = addr & 0xffff;
	idx = addr >> 5;

	switch (addr & 0x1f) {
	case 0x00:
		write_IRQreg_ivpr(opp, idx, val);
		break;
	case 0x10:
		write_IRQreg_idr(opp, idx, val);
		break;
	case 0x18:
		write_IRQreg_ilr(opp, idx, val);
		break;
	}

	return 0;
}

static int openpic_src_read(void *opaque, gpa_t addr, u32 *ptr)
{
	struct openpic *opp = opaque;
	uint32_t retval;
	int idx;

	pr_debug("%s: addr %#llx\n", __func__, addr);
	retval = 0xFFFFFFFF;

	addr = addr & 0xffff;
	idx = addr >> 5;

	switch (addr & 0x1f) {
	case 0x00:
		retval = read_IRQreg_ivpr(opp, idx);
		break;
	case 0x10:
		retval = read_IRQreg_idr(opp, idx);
		break;
	case 0x18:
		retval = read_IRQreg_ilr(opp, idx);
		break;
	}

	pr_debug("%s: => 0x%08x\n", __func__, retval);
	*ptr = retval;
	return 0;
}

static int openpic_msi_write(void *opaque, gpa_t addr, u32 val)
{
	struct openpic *opp = opaque;
	int idx = opp->irq_msi;
	int srs, ibs;

	pr_debug("%s: addr %#llx <= 0x%08x\n", __func__, addr, val);
	if (addr & 0xF)
		return 0;

	switch (addr) {
	case MSIIR_OFFSET:
		srs = val >> MSIIR_SRS_SHIFT;
		idx += srs;
		ibs = (val & MSIIR_IBS_MASK) >> MSIIR_IBS_SHIFT;
		opp->msi[srs].msir |= 1 << ibs;
		openpic_set_irq(opp, idx, 1);
		break;
	default:
		/* most registers are read-only, thus ignored */
		break;
	}

	return 0;
}

static int openpic_msi_read(void *opaque, gpa_t addr, u32 *ptr)
{
	struct openpic *opp = opaque;
	uint32_t r = 0;
	int i, srs;

	pr_debug("%s: addr %#llx\n", __func__, addr);
	if (addr & 0xF)
		return -ENXIO;

	srs = addr >> 4;

	switch (addr) {
	case 0x00:
	case 0x10:
	case 0x20:
	case 0x30:
	case 0x40:
	case 0x50:
	case 0x60:
	case 0x70:		/* MSIRs */
		r = opp->msi[srs].msir;
		/* Clear on read */
		opp->msi[srs].msir = 0;
		openpic_set_irq(opp, opp->irq_msi + srs, 0);
		break;
	case 0x120:		/* MSISR */
		for (i = 0; i < MAX_MSI; i++)
			r |= (opp->msi[i].msir ? 1 : 0) << i;
		break;
	}

	pr_debug("%s: => 0x%08x\n", __func__, r);
	*ptr = r;
	return 0;
}

static int openpic_summary_read(void *opaque, gpa_t addr, u32 *ptr)
{
	uint32_t r = 0;

	pr_debug("%s: addr %#llx\n", __func__, addr);

	/* TODO: EISR/EIMR */

	*ptr = r;
	return 0;
}

static int openpic_summary_write(void *opaque, gpa_t addr, u32 val)
{
	pr_debug("%s: addr %#llx <= 0x%08x\n", __func__, addr, val);

	/* TODO: EISR/EIMR */
	return 0;
}

static int openpic_cpu_write_internal(void *opaque, gpa_t addr,
				      u32 val, int idx)
{
	struct openpic *opp = opaque;
	struct irq_source *src;
	struct irq_dest *dst;
	int s_IRQ, n_IRQ;

	pr_debug("%s: cpu %d addr %#llx <= 0x%08x\n", __func__, idx,
		addr, val);

	if (idx < 0)
		return 0;

	if (addr & 0xF)
		return 0;

	dst = &opp->dst[idx];
	addr &= 0xFF0;
	switch (addr) {
	case 0x40:		/* IPIDR */
	case 0x50:
	case 0x60:
	case 0x70:
		idx = (addr - 0x40) >> 4;
		/* we use IDE as mask which CPUs to deliver the IPI to still. */
		opp->src[opp->irq_ipi0 + idx].destmask |= val;
		openpic_set_irq(opp, opp->irq_ipi0 + idx, 1);
		openpic_set_irq(opp, opp->irq_ipi0 + idx, 0);
		break;
	case 0x80:		/* CTPR */
		dst->ctpr = val & 0x0000000F;

		pr_debug("%s: set CPU %d ctpr to %d, raised %d servicing %d\n",
			__func__, idx, dst->ctpr, dst->raised.priority,
			dst->servicing.priority);

		if (dst->raised.priority <= dst->ctpr) {
			pr_debug("%s: Lower OpenPIC INT output cpu %d due to ctpr\n",
				__func__, idx);
			mpic_irq_lower(opp, dst, ILR_INTTGT_INT);
		} else if (dst->raised.priority > dst->servicing.priority) {
			pr_debug("%s: Raise OpenPIC INT output cpu %d irq %d\n",
				__func__, idx, dst->raised.next);
			mpic_irq_raise(opp, dst, ILR_INTTGT_INT);
		}

		break;
	case 0x90:		/* WHOAMI */
		/* Read-only register */
		break;
	case 0xA0:		/* IACK */
		/* Read-only register */
		break;
	case 0xB0: {		/* EOI */
		int notify_eoi;

		pr_debug("EOI\n");
		s_IRQ = IRQ_get_next(opp, &dst->servicing);

		if (s_IRQ < 0) {
			pr_debug("%s: EOI with no interrupt in service\n",
				__func__);
			break;
		}

		IRQ_resetbit(&dst->servicing, s_IRQ);
		/* Notify listeners that the IRQ is over */
		notify_eoi = s_IRQ;
		/* Set up next servicing IRQ */
		s_IRQ = IRQ_get_next(opp, &dst->servicing);
		/* Check queued interrupts. */
		n_IRQ = IRQ_get_next(opp, &dst->raised);
		src = &opp->src[n_IRQ];
		if (n_IRQ != -1 &&
		    (s_IRQ == -1 ||
		     IVPR_PRIORITY(src->ivpr) > dst->servicing.priority)) {
			pr_debug("Raise OpenPIC INT output cpu %d irq %d\n",
				idx, n_IRQ);
			mpic_irq_raise(opp, dst, ILR_INTTGT_INT);
		}

		spin_unlock(&opp->lock);
		kvm_notify_acked_irq(opp->kvm, 0, notify_eoi);
		spin_lock(&opp->lock);

		break;
	}
	default:
		break;
	}

	return 0;
}

static int openpic_cpu_write(void *opaque, gpa_t addr, u32 val)
{
	struct openpic *opp = opaque;

	return openpic_cpu_write_internal(opp, addr, val,
					 (addr & 0x1f000) >> 12);
}

static uint32_t openpic_iack(struct openpic *opp, struct irq_dest *dst,
			     int cpu)
{
	struct irq_source *src;
	int retval, irq;

	pr_debug("Lower OpenPIC INT output\n");
	mpic_irq_lower(opp, dst, ILR_INTTGT_INT);

	irq = IRQ_get_next(opp, &dst->raised);
	pr_debug("IACK: irq=%d\n", irq);

	if (irq == -1)
		/* No more interrupt pending */
		return opp->spve;

	src = &opp->src[irq];
	if (!(src->ivpr & IVPR_ACTIVITY_MASK) ||
	    !(IVPR_PRIORITY(src->ivpr) > dst->ctpr)) {
		pr_err("%s: bad raised IRQ %d ctpr %d ivpr 0x%08x\n",
			__func__, irq, dst->ctpr, src->ivpr);
		openpic_update_irq(opp, irq);
		retval = opp->spve;
	} else {
		/* IRQ enter servicing state */
		IRQ_setbit(&dst->servicing, irq);
		retval = IVPR_VECTOR(opp, src->ivpr);
	}

	if (!src->level) {
		/* edge-sensitive IRQ */
		src->ivpr &= ~IVPR_ACTIVITY_MASK;
		src->pending = 0;
		IRQ_resetbit(&dst->raised, irq);
	}

	if ((irq >= opp->irq_ipi0) && (irq < (opp->irq_ipi0 + MAX_IPI))) {
		src->destmask &= ~(1 << cpu);
		if (src->destmask && !src->level) {
			/* trigger on CPUs that didn't know about it yet */
			openpic_set_irq(opp, irq, 1);
			openpic_set_irq(opp, irq, 0);
			/* if all CPUs knew about it, set active bit again */
			src->ivpr |= IVPR_ACTIVITY_MASK;
		}
	}

	return retval;
}

void kvmppc_mpic_set_epr(struct kvm_vcpu *vcpu)
{
	struct openpic *opp = vcpu->arch.mpic;
	int cpu = vcpu->arch.irq_cpu_id;
	unsigned long flags;

	spin_lock_irqsave(&opp->lock, flags);

	if ((opp->gcr & opp->mpic_mode_mask) == GCR_MODE_PROXY)
		kvmppc_set_epr(vcpu, openpic_iack(opp, &opp->dst[cpu], cpu));

	spin_unlock_irqrestore(&opp->lock, flags);
}

static int openpic_cpu_read_internal(void *opaque, gpa_t addr,
				     u32 *ptr, int idx)
{
	struct openpic *opp = opaque;
	struct irq_dest *dst;
	uint32_t retval;

	pr_debug("%s: cpu %d addr %#llx\n", __func__, idx, addr);
	retval = 0xFFFFFFFF;

	if (idx < 0)
		goto out;

	if (addr & 0xF)
		goto out;

	dst = &opp->dst[idx];
	addr &= 0xFF0;
	switch (addr) {
	case 0x80:		/* CTPR */
		retval = dst->ctpr;
		break;
	case 0x90:		/* WHOAMI */
		retval = idx;
		break;
	case 0xA0:		/* IACK */
		retval = openpic_iack(opp, dst, idx);
		break;
	case 0xB0:		/* EOI */
		retval = 0;
		break;
	default:
		break;
	}
	pr_debug("%s: => 0x%08x\n", __func__, retval);

out:
	*ptr = retval;
	return 0;
}

static int openpic_cpu_read(void *opaque, gpa_t addr, u32 *ptr)
{
	struct openpic *opp = opaque;

	return openpic_cpu_read_internal(opp, addr, ptr,
					 (addr & 0x1f000) >> 12);
}

struct mem_reg {
	int (*read)(void *opaque, gpa_t addr, u32 *ptr);
	int (*write)(void *opaque, gpa_t addr, u32 val);
	gpa_t start_addr;
	int size;
};

static const struct mem_reg openpic_gbl_mmio = {
	.write = openpic_gbl_write,
	.read = openpic_gbl_read,
	.start_addr = OPENPIC_GLB_REG_START,
	.size = OPENPIC_GLB_REG_SIZE,
};

static const struct mem_reg openpic_tmr_mmio = {
	.write = openpic_tmr_write,
	.read = openpic_tmr_read,
	.start_addr = OPENPIC_TMR_REG_START,
	.size = OPENPIC_TMR_REG_SIZE,
};

static const struct mem_reg openpic_cpu_mmio = {
	.write = openpic_cpu_write,
	.read = openpic_cpu_read,
	.start_addr = OPENPIC_CPU_REG_START,
	.size = OPENPIC_CPU_REG_SIZE,
};

static const struct mem_reg openpic_src_mmio = {
	.write = openpic_src_write,
	.read = openpic_src_read,
	.start_addr = OPENPIC_SRC_REG_START,
	.size = OPENPIC_SRC_REG_SIZE,
};

static const struct mem_reg openpic_msi_mmio = {
	.read = openpic_msi_read,
	.write = openpic_msi_write,
	.start_addr = OPENPIC_MSI_REG_START,
	.size = OPENPIC_MSI_REG_SIZE,
};

static const struct mem_reg openpic_summary_mmio = {
	.read = openpic_summary_read,
	.write = openpic_summary_write,
	.start_addr = OPENPIC_SUMMARY_REG_START,
	.size = OPENPIC_SUMMARY_REG_SIZE,
};

static void add_mmio_region(struct openpic *opp, const struct mem_reg *mr)
{
	if (opp->num_mmio_regions >= MAX_MMIO_REGIONS) {
		WARN(1, "kvm mpic: too many mmio regions\n");
		return;
	}

	opp->mmio_regions[opp->num_mmio_regions++] = mr;
}

static void fsl_common_init(struct openpic *opp)
{
	int i;
	int virq = MAX_SRC;

	add_mmio_region(opp, &openpic_msi_mmio);
	add_mmio_region(opp, &openpic_summary_mmio);

	opp->vid = VID_REVISION_1_2;
	opp->vir = VIR_GENERIC;
	opp->vector_mask = 0xFFFF;
	opp->tfrr_reset = 0;
	opp->ivpr_reset = IVPR_MASK_MASK;
	opp->idr_reset = 1 << 0;
	opp->max_irq = MAX_IRQ;

	opp->irq_ipi0 = virq;
	virq += MAX_IPI;
	opp->irq_tim0 = virq;
	virq += MAX_TMR;

	BUG_ON(virq > MAX_IRQ);

	opp->irq_msi = 224;

	for (i = 0; i < opp->fsl->max_ext; i++)
		opp->src[i].level = false;

	/* Internal interrupts, including message and MSI */
	for (i = 16; i < MAX_SRC; i++) {
		opp->src[i].type = IRQ_TYPE_FSLINT;
		opp->src[i].level = true;
	}

	/* timers and IPIs */
	for (i = MAX_SRC; i < virq; i++) {
		opp->src[i].type = IRQ_TYPE_FSLSPECIAL;
		opp->src[i].level = false;
	}
}

static int kvm_mpic_read_internal(struct openpic *opp, gpa_t addr, u32 *ptr)
{
	int i;

	for (i = 0; i < opp->num_mmio_regions; i++) {
		const struct mem_reg *mr = opp->mmio_regions[i];

		if (mr->start_addr > addr || addr >= mr->start_addr + mr->size)
			continue;

		return mr->read(opp, addr - mr->start_addr, ptr);
	}

	return -ENXIO;
}

static int kvm_mpic_write_internal(struct openpic *opp, gpa_t addr, u32 val)
{
	int i;

	for (i = 0; i < opp->num_mmio_regions; i++) {
		const struct mem_reg *mr = opp->mmio_regions[i];

		if (mr->start_addr > addr || addr >= mr->start_addr + mr->size)
			continue;

		return mr->write(opp, addr - mr->start_addr, val);
	}

	return -ENXIO;
}

static int kvm_mpic_read(struct kvm_vcpu *vcpu,
			 struct kvm_io_device *this,
			 gpa_t addr, int len, void *ptr)
{
	struct openpic *opp = container_of(this, struct openpic, mmio);
	int ret;
	union {
		u32 val;
		u8 bytes[4];
	} u;

	if (addr & (len - 1)) {
		pr_debug("%s: bad alignment %llx/%d\n",
			 __func__, addr, len);
		return -EINVAL;
	}

	spin_lock_irq(&opp->lock);
	ret = kvm_mpic_read_internal(opp, addr - opp->reg_base, &u.val);
	spin_unlock_irq(&opp->lock);

	/*
	 * Technically only 32-bit accesses are allowed, but be nice to
	 * people dumping registers a byte at a time -- it works in real
	 * hardware (reads only, not writes).
	 */
	if (len == 4) {
		*(u32 *)ptr = u.val;
		pr_debug("%s: addr %llx ret %d len 4 val %x\n",
			 __func__, addr, ret, u.val);
	} else if (len == 1) {
		*(u8 *)ptr = u.bytes[addr & 3];
		pr_debug("%s: addr %llx ret %d len 1 val %x\n",
			 __func__, addr, ret, u.bytes[addr & 3]);
	} else {
		pr_debug("%s: bad length %d\n", __func__, len);
		return -EINVAL;
	}

	return ret;
}

static int kvm_mpic_write(struct kvm_vcpu *vcpu,
			  struct kvm_io_device *this,
			  gpa_t addr, int len, const void *ptr)
{
	struct openpic *opp = container_of(this, struct openpic, mmio);
	int ret;

	if (len != 4) {
		pr_debug("%s: bad length %d\n", __func__, len);
		return -EOPNOTSUPP;
	}
	if (addr & 3) {
		pr_debug("%s: bad alignment %llx/%d\n", __func__, addr, len);
		return -EOPNOTSUPP;
	}

	spin_lock_irq(&opp->lock);
	ret = kvm_mpic_write_internal(opp, addr - opp->reg_base,
				      *(const u32 *)ptr);
	spin_unlock_irq(&opp->lock);

	pr_debug("%s: addr %llx ret %d val %x\n",
		 __func__, addr, ret, *(const u32 *)ptr);

	return ret;
}

static const struct kvm_io_device_ops mpic_mmio_ops = {
	.read = kvm_mpic_read,
	.write = kvm_mpic_write,
};

static void map_mmio(struct openpic *opp)
{
	kvm_iodevice_init(&opp->mmio, &mpic_mmio_ops);

	kvm_io_bus_register_dev(opp->kvm, KVM_MMIO_BUS,
				opp->reg_base, OPENPIC_REG_SIZE,
				&opp->mmio);
}

static void unmap_mmio(struct openpic *opp)
{
	kvm_io_bus_unregister_dev(opp->kvm, KVM_MMIO_BUS, &opp->mmio);
}

static int set_base_addr(struct openpic *opp, struct kvm_device_attr *attr)
{
	u64 base;

	if (copy_from_user(&base, (u64 __user *)(long)attr->addr, sizeof(u64)))
		return -EFAULT;

	if (base & 0x3ffff) {
		pr_debug("kvm mpic %s: KVM_DEV_MPIC_BASE_ADDR %08llx not aligned\n",
			 __func__, base);
		return -EINVAL;
	}

	if (base == opp->reg_base)
		return 0;

	mutex_lock(&opp->kvm->slots_lock);

	unmap_mmio(opp);
	opp->reg_base = base;

	pr_debug("kvm mpic %s: KVM_DEV_MPIC_BASE_ADDR %08llx\n",
		 __func__, base);

	if (base == 0)
		goto out;

	map_mmio(opp);

out:
	mutex_unlock(&opp->kvm->slots_lock);
	return 0;
}

#define ATTR_SET		0
#define ATTR_GET		1

static int access_reg(struct openpic *opp, gpa_t addr, u32 *val, int type)
{
	int ret;

	if (addr & 3)
		return -ENXIO;

	spin_lock_irq(&opp->lock);

	if (type == ATTR_SET)
		ret = kvm_mpic_write_internal(opp, addr, *val);
	else
		ret = kvm_mpic_read_internal(opp, addr, val);

	spin_unlock_irq(&opp->lock);

	pr_debug("%s: type %d addr %llx val %x\n", __func__, type, addr, *val);

	return ret;
}

static int mpic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	struct openpic *opp = dev->private;
	u32 attr32;

	switch (attr->group) {
	case KVM_DEV_MPIC_GRP_MISC:
		switch (attr->attr) {
		case KVM_DEV_MPIC_BASE_ADDR:
			return set_base_addr(opp, attr);
		}

		break;

	case KVM_DEV_MPIC_GRP_REGISTER:
		if (get_user(attr32, (u32 __user *)(long)attr->addr))
			return -EFAULT;

		return access_reg(opp, attr->attr, &attr32, ATTR_SET);

	case KVM_DEV_MPIC_GRP_IRQ_ACTIVE:
		if (attr->attr > MAX_SRC)
			return -EINVAL;

		if (get_user(attr32, (u32 __user *)(long)attr->addr))
			return -EFAULT;

		if (attr32 != 0 && attr32 != 1)
			return -EINVAL;

		spin_lock_irq(&opp->lock);
		openpic_set_irq(opp, attr->attr, attr32);
		spin_unlock_irq(&opp->lock);
		return 0;
	}

	return -ENXIO;
}

static int mpic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	struct openpic *opp = dev->private;
	u64 attr64;
	u32 attr32;
	int ret;

	switch (attr->group) {
	case KVM_DEV_MPIC_GRP_MISC:
		switch (attr->attr) {
		case KVM_DEV_MPIC_BASE_ADDR:
			mutex_lock(&opp->kvm->slots_lock);
			attr64 = opp->reg_base;
			mutex_unlock(&opp->kvm->slots_lock);

			if (copy_to_user((u64 __user *)(long)attr->addr,
					 &attr64, sizeof(u64)))
				return -EFAULT;

			return 0;
		}

		break;

	case KVM_DEV_MPIC_GRP_REGISTER:
		ret = access_reg(opp, attr->attr, &attr32, ATTR_GET);
		if (ret)
			return ret;

		if (put_user(attr32, (u32 __user *)(long)attr->addr))
			return -EFAULT;

		return 0;

	case KVM_DEV_MPIC_GRP_IRQ_ACTIVE:
		if (attr->attr > MAX_SRC)
			return -EINVAL;

		spin_lock_irq(&opp->lock);
		attr32 = opp->src[attr->attr].pending;
		spin_unlock_irq(&opp->lock);

		if (put_user(attr32, (u32 __user *)(long)attr->addr))
			return -EFAULT;

		return 0;
	}

	return -ENXIO;
}

static int mpic_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	switch (attr->group) {
	case KVM_DEV_MPIC_GRP_MISC:
		switch (attr->attr) {
		case KVM_DEV_MPIC_BASE_ADDR:
			return 0;
		}

		break;

	case KVM_DEV_MPIC_GRP_REGISTER:
		return 0;

	case KVM_DEV_MPIC_GRP_IRQ_ACTIVE:
		if (attr->attr > MAX_SRC)
			break;

		return 0;
	}

	return -ENXIO;
}

static void mpic_destroy(struct kvm_device *dev)
{
	struct openpic *opp = dev->private;

	dev->kvm->arch.mpic = NULL;
	kfree(opp);
	kfree(dev);
}

static int mpic_set_default_irq_routing(struct openpic *opp)
{
	struct kvm_irq_routing_entry *routing;

	/* Create a nop default map, so that dereferencing it still works */
	routing = kzalloc((sizeof(*routing)), GFP_KERNEL);
	if (!routing)
		return -ENOMEM;

	kvm_set_irq_routing(opp->kvm, routing, 0, 0);

	kfree(routing);
	return 0;
}

static int mpic_create(struct kvm_device *dev, u32 type)
{
	struct openpic *opp;
	int ret;

	/* We only support one MPIC at a time for now */
	if (dev->kvm->arch.mpic)
		return -EINVAL;

	opp = kzalloc(sizeof(struct openpic), GFP_KERNEL);
	if (!opp)
		return -ENOMEM;

	dev->private = opp;
	opp->kvm = dev->kvm;
	opp->dev = dev;
	opp->model = type;
	spin_lock_init(&opp->lock);

	add_mmio_region(opp, &openpic_gbl_mmio);
	add_mmio_region(opp, &openpic_tmr_mmio);
	add_mmio_region(opp, &openpic_src_mmio);
	add_mmio_region(opp, &openpic_cpu_mmio);

	switch (opp->model) {
	case KVM_DEV_TYPE_FSL_MPIC_20:
		opp->fsl = &fsl_mpic_20;
		opp->brr1 = 0x00400200;
		opp->flags |= OPENPIC_FLAG_IDR_CRIT;
		opp->nb_irqs = 80;
		opp->mpic_mode_mask = GCR_MODE_MIXED;

		fsl_common_init(opp);

		break;

	case KVM_DEV_TYPE_FSL_MPIC_42:
		opp->fsl = &fsl_mpic_42;
		opp->brr1 = 0x00400402;
		opp->flags |= OPENPIC_FLAG_ILR;
		opp->nb_irqs = 196;
		opp->mpic_mode_mask = GCR_MODE_PROXY;

		fsl_common_init(opp);

		break;

	default:
		ret = -ENODEV;
		goto err;
	}

	ret = mpic_set_default_irq_routing(opp);
	if (ret)
		goto err;

	openpic_reset(opp);

	smp_wmb();
	dev->kvm->arch.mpic = opp;

	return 0;

err:
	kfree(opp);
	return ret;
}

struct kvm_device_ops kvm_mpic_ops = {
	.name = "kvm-mpic",
	.create = mpic_create,
	.destroy = mpic_destroy,
	.set_attr = mpic_set_attr,
	.get_attr = mpic_get_attr,
	.has_attr = mpic_has_attr,
};

int kvmppc_mpic_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu,
			     u32 cpu)
{
	struct openpic *opp = dev->private;
	int ret = 0;

	if (dev->ops != &kvm_mpic_ops)
		return -EPERM;
	if (opp->kvm != vcpu->kvm)
		return -EPERM;
	if (cpu < 0 || cpu >= MAX_CPU)
		return -EPERM;

	spin_lock_irq(&opp->lock);

	if (opp->dst[cpu].vcpu) {
		ret = -EEXIST;
		goto out;
	}
	if (vcpu->arch.irq_type) {
		ret = -EBUSY;
		goto out;
	}

	opp->dst[cpu].vcpu = vcpu;
	opp->nb_cpus = max(opp->nb_cpus, cpu + 1);

	vcpu->arch.mpic = opp;
	vcpu->arch.irq_cpu_id = cpu;
	vcpu->arch.irq_type = KVMPPC_IRQ_MPIC;

	/* This might need to be changed if GCR gets extended */
	if (opp->mpic_mode_mask == GCR_MODE_PROXY)
		vcpu->arch.epr_flags |= KVMPPC_EPR_KERNEL;

out:
	spin_unlock_irq(&opp->lock);
	return ret;
}

/*
 * This should only happen immediately before the mpic is destroyed,
 * so we shouldn't need to worry about anything still trying to
 * access the vcpu pointer.
 */
void kvmppc_mpic_disconnect_vcpu(struct openpic *opp, struct kvm_vcpu *vcpu)
{
	BUG_ON(!opp->dst[vcpu->arch.irq_cpu_id].vcpu);

	opp->dst[vcpu->arch.irq_cpu_id].vcpu = NULL;
}

/*
 * Return value:
 *  < 0   Interrupt was ignored (masked or not delivered for other reasons)
 *  = 0   Interrupt was coalesced (previous irq is still pending)
 *  > 0   Number of CPUs interrupt was delivered to
 */
static int mpic_set_irq(struct kvm_kernel_irq_routing_entry *e,
			struct kvm *kvm, int irq_source_id, int level,
			bool line_status)
{
	u32 irq = e->irqchip.pin;
	struct openpic *opp = kvm->arch.mpic;
	unsigned long flags;

	spin_lock_irqsave(&opp->lock, flags);
	openpic_set_irq(opp, irq, level);
	spin_unlock_irqrestore(&opp->lock, flags);

	/* All code paths we care about don't check for the return value */
	return 0;
}

int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
		struct kvm *kvm, int irq_source_id, int level, bool line_status)
{
	struct openpic *opp = kvm->arch.mpic;
	unsigned long flags;

	spin_lock_irqsave(&opp->lock, flags);

	/*
	 * XXX We ignore the target address for now, as we only support
	 *     a single MSI bank.
	 */
	openpic_msi_write(kvm->arch.mpic, MSIIR_OFFSET, e->msi.data);
	spin_unlock_irqrestore(&opp->lock, flags);

	/* All code paths we care about don't check for the return value */
	return 0;
}

int kvm_set_routing_entry(struct kvm *kvm,
			  struct kvm_kernel_irq_routing_entry *e,
			  const struct kvm_irq_routing_entry *ue)
{
	int r = -EINVAL;

	switch (ue->type) {
	case KVM_IRQ_ROUTING_IRQCHIP:
		e->set = mpic_set_irq;
		e->irqchip.irqchip = ue->u.irqchip.irqchip;
		e->irqchip.pin = ue->u.irqchip.pin;
		if (e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS)
			goto out;
		break;
	case KVM_IRQ_ROUTING_MSI:
		e->set = kvm_set_msi;
		e->msi.address_lo = ue->u.msi.address_lo;
		e->msi.address_hi = ue->u.msi.address_hi;
		e->msi.data = ue->u.msi.data;
		break;
	default:
		goto out;
	}

	r = 0;
out:
	return r;
}