aboutsummaryrefslogtreecommitdiff
path: root/hw/intc/xive.c
blob: d4c6e21703b3b719432697b9a782207c4f9ad817 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
/*
 * QEMU PowerPC XIVE interrupt controller model
 *
 * Copyright (c) 2017-2018, IBM Corporation.
 *
 * This code is licensed under the GPL version 2 or later. See the
 * COPYING file in the top-level directory.
 */

#include "qemu/osdep.h"
#include "qemu/log.h"
#include "qemu/module.h"
#include "qapi/error.h"
#include "target/ppc/cpu.h"
#include "sysemu/cpus.h"
#include "sysemu/dma.h"
#include "sysemu/reset.h"
#include "hw/qdev-properties.h"
#include "migration/vmstate.h"
#include "monitor/monitor.h"
#include "hw/irq.h"
#include "hw/ppc/xive.h"
#include "hw/ppc/xive_regs.h"

/*
 * XIVE Thread Interrupt Management context
 */

/*
 * Convert a priority number to an Interrupt Pending Buffer (IPB)
 * register, which indicates a pending interrupt at the priority
 * corresponding to the bit number
 */
static uint8_t priority_to_ipb(uint8_t priority)
{
    return priority > XIVE_PRIORITY_MAX ?
        0 : 1 << (XIVE_PRIORITY_MAX - priority);
}

/*
 * Convert an Interrupt Pending Buffer (IPB) register to a Pending
 * Interrupt Priority Register (PIPR), which contains the priority of
 * the most favored pending notification.
 */
static uint8_t ipb_to_pipr(uint8_t ibp)
{
    return ibp ? clz32((uint32_t)ibp << 24) : 0xff;
}

static uint8_t exception_mask(uint8_t ring)
{
    switch (ring) {
    case TM_QW1_OS:
        return TM_QW1_NSR_EO;
    case TM_QW3_HV_PHYS:
        return TM_QW3_NSR_HE;
    default:
        g_assert_not_reached();
    }
}

static qemu_irq xive_tctx_output(XiveTCTX *tctx, uint8_t ring)
{
        switch (ring) {
        case TM_QW0_USER:
                return 0; /* Not supported */
        case TM_QW1_OS:
                return tctx->os_output;
        case TM_QW2_HV_POOL:
        case TM_QW3_HV_PHYS:
                return tctx->hv_output;
        default:
                return 0;
        }
}

static uint64_t xive_tctx_accept(XiveTCTX *tctx, uint8_t ring)
{
    uint8_t *regs = &tctx->regs[ring];
    uint8_t nsr = regs[TM_NSR];
    uint8_t mask = exception_mask(ring);

    qemu_irq_lower(xive_tctx_output(tctx, ring));

    if (regs[TM_NSR] & mask) {
        uint8_t cppr = regs[TM_PIPR];

        regs[TM_CPPR] = cppr;

        /* Reset the pending buffer bit */
        regs[TM_IPB] &= ~priority_to_ipb(cppr);
        regs[TM_PIPR] = ipb_to_pipr(regs[TM_IPB]);

        /* Drop Exception bit */
        regs[TM_NSR] &= ~mask;
    }

    return (nsr << 8) | regs[TM_CPPR];
}

static void xive_tctx_notify(XiveTCTX *tctx, uint8_t ring)
{
    uint8_t *regs = &tctx->regs[ring];

    if (regs[TM_PIPR] < regs[TM_CPPR]) {
        switch (ring) {
        case TM_QW1_OS:
            regs[TM_NSR] |= TM_QW1_NSR_EO;
            break;
        case TM_QW3_HV_PHYS:
            regs[TM_NSR] |= (TM_QW3_NSR_HE_PHYS << 6);
            break;
        default:
            g_assert_not_reached();
        }
        qemu_irq_raise(xive_tctx_output(tctx, ring));
    }
}

static void xive_tctx_set_cppr(XiveTCTX *tctx, uint8_t ring, uint8_t cppr)
{
    if (cppr > XIVE_PRIORITY_MAX) {
        cppr = 0xff;
    }

    tctx->regs[ring + TM_CPPR] = cppr;

    /* CPPR has changed, check if we need to raise a pending exception */
    xive_tctx_notify(tctx, ring);
}

void xive_tctx_ipb_update(XiveTCTX *tctx, uint8_t ring, uint8_t ipb)
{
    uint8_t *regs = &tctx->regs[ring];

    regs[TM_IPB] |= ipb;
    regs[TM_PIPR] = ipb_to_pipr(regs[TM_IPB]);
    xive_tctx_notify(tctx, ring);
}

static inline uint32_t xive_tctx_word2(uint8_t *ring)
{
    return *((uint32_t *) &ring[TM_WORD2]);
}

/*
 * XIVE Thread Interrupt Management Area (TIMA)
 */

static void xive_tm_set_hv_cppr(XivePresenter *xptr, XiveTCTX *tctx,
                                hwaddr offset, uint64_t value, unsigned size)
{
    xive_tctx_set_cppr(tctx, TM_QW3_HV_PHYS, value & 0xff);
}

static uint64_t xive_tm_ack_hv_reg(XivePresenter *xptr, XiveTCTX *tctx,
                                   hwaddr offset, unsigned size)
{
    return xive_tctx_accept(tctx, TM_QW3_HV_PHYS);
}

static uint64_t xive_tm_pull_pool_ctx(XivePresenter *xptr, XiveTCTX *tctx,
                                      hwaddr offset, unsigned size)
{
    uint32_t qw2w2_prev = xive_tctx_word2(&tctx->regs[TM_QW2_HV_POOL]);
    uint32_t qw2w2;

    qw2w2 = xive_set_field32(TM_QW2W2_VP, qw2w2_prev, 0);
    memcpy(&tctx->regs[TM_QW2_HV_POOL + TM_WORD2], &qw2w2, 4);
    return qw2w2;
}

static void xive_tm_vt_push(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset,
                            uint64_t value, unsigned size)
{
    tctx->regs[TM_QW3_HV_PHYS + TM_WORD2] = value & 0xff;
}

static uint64_t xive_tm_vt_poll(XivePresenter *xptr, XiveTCTX *tctx,
                                hwaddr offset, unsigned size)
{
    return tctx->regs[TM_QW3_HV_PHYS + TM_WORD2] & 0xff;
}

/*
 * Define an access map for each page of the TIMA that we will use in
 * the memory region ops to filter values when doing loads and stores
 * of raw registers values
 *
 * Registers accessibility bits :
 *
 *    0x0 - no access
 *    0x1 - write only
 *    0x2 - read only
 *    0x3 - read/write
 */

static const uint8_t xive_tm_hw_view[] = {
    3, 0, 0, 0,   0, 0, 0, 0,   3, 3, 3, 3,   0, 0, 0, 0, /* QW-0 User */
    3, 3, 3, 3,   3, 3, 0, 2,   3, 3, 3, 3,   0, 0, 0, 0, /* QW-1 OS   */
    0, 0, 3, 3,   0, 0, 0, 0,   3, 3, 3, 3,   0, 0, 0, 0, /* QW-2 POOL */
    3, 3, 3, 3,   0, 3, 0, 2,   3, 0, 0, 3,   3, 3, 3, 0, /* QW-3 PHYS */
};

static const uint8_t xive_tm_hv_view[] = {
    3, 0, 0, 0,   0, 0, 0, 0,   3, 3, 3, 3,   0, 0, 0, 0, /* QW-0 User */
    3, 3, 3, 3,   3, 3, 0, 2,   3, 3, 3, 3,   0, 0, 0, 0, /* QW-1 OS   */
    0, 0, 3, 3,   0, 0, 0, 0,   0, 3, 3, 3,   0, 0, 0, 0, /* QW-2 POOL */
    3, 3, 3, 3,   0, 3, 0, 2,   3, 0, 0, 3,   0, 0, 0, 0, /* QW-3 PHYS */
};

static const uint8_t xive_tm_os_view[] = {
    3, 0, 0, 0,   0, 0, 0, 0,   3, 3, 3, 3,   0, 0, 0, 0, /* QW-0 User */
    2, 3, 2, 2,   2, 2, 0, 2,   0, 0, 0, 0,   0, 0, 0, 0, /* QW-1 OS   */
    0, 0, 0, 0,   0, 0, 0, 0,   0, 0, 0, 0,   0, 0, 0, 0, /* QW-2 POOL */
    0, 0, 0, 0,   0, 0, 0, 0,   0, 0, 0, 0,   0, 0, 0, 0, /* QW-3 PHYS */
};

static const uint8_t xive_tm_user_view[] = {
    3, 0, 0, 0,   0, 0, 0, 0,   0, 0, 0, 0,   0, 0, 0, 0, /* QW-0 User */
    0, 0, 0, 0,   0, 0, 0, 0,   0, 0, 0, 0,   0, 0, 0, 0, /* QW-1 OS   */
    0, 0, 0, 0,   0, 0, 0, 0,   0, 0, 0, 0,   0, 0, 0, 0, /* QW-2 POOL */
    0, 0, 0, 0,   0, 0, 0, 0,   0, 0, 0, 0,   0, 0, 0, 0, /* QW-3 PHYS */
};

/*
 * Overall TIMA access map for the thread interrupt management context
 * registers
 */
static const uint8_t *xive_tm_views[] = {
    [XIVE_TM_HW_PAGE]   = xive_tm_hw_view,
    [XIVE_TM_HV_PAGE]   = xive_tm_hv_view,
    [XIVE_TM_OS_PAGE]   = xive_tm_os_view,
    [XIVE_TM_USER_PAGE] = xive_tm_user_view,
};

/*
 * Computes a register access mask for a given offset in the TIMA
 */
static uint64_t xive_tm_mask(hwaddr offset, unsigned size, bool write)
{
    uint8_t page_offset = (offset >> TM_SHIFT) & 0x3;
    uint8_t reg_offset = offset & 0x3F;
    uint8_t reg_mask = write ? 0x1 : 0x2;
    uint64_t mask = 0x0;
    int i;

    for (i = 0; i < size; i++) {
        if (xive_tm_views[page_offset][reg_offset + i] & reg_mask) {
            mask |= (uint64_t) 0xff << (8 * (size - i - 1));
        }
    }

    return mask;
}

static void xive_tm_raw_write(XiveTCTX *tctx, hwaddr offset, uint64_t value,
                              unsigned size)
{
    uint8_t ring_offset = offset & 0x30;
    uint8_t reg_offset = offset & 0x3F;
    uint64_t mask = xive_tm_mask(offset, size, true);
    int i;

    /*
     * Only 4 or 8 bytes stores are allowed and the User ring is
     * excluded
     */
    if (size < 4 || !mask || ring_offset == TM_QW0_USER) {
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid write access at TIMA @%"
                      HWADDR_PRIx"\n", offset);
        return;
    }

    /*
     * Use the register offset for the raw values and filter out
     * reserved values
     */
    for (i = 0; i < size; i++) {
        uint8_t byte_mask = (mask >> (8 * (size - i - 1)));
        if (byte_mask) {
            tctx->regs[reg_offset + i] = (value >> (8 * (size - i - 1))) &
                byte_mask;
        }
    }
}

static uint64_t xive_tm_raw_read(XiveTCTX *tctx, hwaddr offset, unsigned size)
{
    uint8_t ring_offset = offset & 0x30;
    uint8_t reg_offset = offset & 0x3F;
    uint64_t mask = xive_tm_mask(offset, size, false);
    uint64_t ret;
    int i;

    /*
     * Only 4 or 8 bytes loads are allowed and the User ring is
     * excluded
     */
    if (size < 4 || !mask || ring_offset == TM_QW0_USER) {
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid read access at TIMA @%"
                      HWADDR_PRIx"\n", offset);
        return -1;
    }

    /* Use the register offset for the raw values */
    ret = 0;
    for (i = 0; i < size; i++) {
        ret |= (uint64_t) tctx->regs[reg_offset + i] << (8 * (size - i - 1));
    }

    /* filter out reserved values */
    return ret & mask;
}

/*
 * The TM context is mapped twice within each page. Stores and loads
 * to the first mapping below 2K write and read the specified values
 * without modification. The second mapping above 2K performs specific
 * state changes (side effects) in addition to setting/returning the
 * interrupt management area context of the processor thread.
 */
static uint64_t xive_tm_ack_os_reg(XivePresenter *xptr, XiveTCTX *tctx,
                                   hwaddr offset, unsigned size)
{
    return xive_tctx_accept(tctx, TM_QW1_OS);
}

static void xive_tm_set_os_cppr(XivePresenter *xptr, XiveTCTX *tctx,
                                hwaddr offset, uint64_t value, unsigned size)
{
    xive_tctx_set_cppr(tctx, TM_QW1_OS, value & 0xff);
}

/*
 * Adjust the IPB to allow a CPU to process event queues of other
 * priorities during one physical interrupt cycle.
 */
static void xive_tm_set_os_pending(XivePresenter *xptr, XiveTCTX *tctx,
                                   hwaddr offset, uint64_t value, unsigned size)
{
    xive_tctx_ipb_update(tctx, TM_QW1_OS, priority_to_ipb(value & 0xff));
}

static void xive_os_cam_decode(uint32_t cam, uint8_t *nvt_blk,
                               uint32_t *nvt_idx, bool *vo)
{
    if (nvt_blk) {
        *nvt_blk = xive_nvt_blk(cam);
    }
    if (nvt_idx) {
        *nvt_idx = xive_nvt_idx(cam);
    }
    if (vo) {
        *vo = !!(cam & TM_QW1W2_VO);
    }
}

static uint32_t xive_tctx_get_os_cam(XiveTCTX *tctx, uint8_t *nvt_blk,
                                     uint32_t *nvt_idx, bool *vo)
{
    uint32_t qw1w2 = xive_tctx_word2(&tctx->regs[TM_QW1_OS]);
    uint32_t cam = be32_to_cpu(qw1w2);

    xive_os_cam_decode(cam, nvt_blk, nvt_idx, vo);
    return qw1w2;
}

static void xive_tctx_set_os_cam(XiveTCTX *tctx, uint32_t qw1w2)
{
    memcpy(&tctx->regs[TM_QW1_OS + TM_WORD2], &qw1w2, 4);
}

static uint64_t xive_tm_pull_os_ctx(XivePresenter *xptr, XiveTCTX *tctx,
                                    hwaddr offset, unsigned size)
{
    uint32_t qw1w2;
    uint32_t qw1w2_new;
    uint8_t nvt_blk;
    uint32_t nvt_idx;
    bool vo;

    qw1w2 = xive_tctx_get_os_cam(tctx, &nvt_blk, &nvt_idx, &vo);

    if (!vo) {
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: pulling invalid NVT %x/%x !?\n",
                      nvt_blk, nvt_idx);
    }

    /* Invalidate CAM line */
    qw1w2_new = xive_set_field32(TM_QW1W2_VO, qw1w2, 0);
    xive_tctx_set_os_cam(tctx, qw1w2_new);
    return qw1w2;
}

static void xive_tctx_need_resend(XiveRouter *xrtr, XiveTCTX *tctx,
                                  uint8_t nvt_blk, uint32_t nvt_idx)
{
    XiveNVT nvt;
    uint8_t ipb;

    /*
     * Grab the associated NVT to pull the pending bits, and merge
     * them with the IPB of the thread interrupt context registers
     */
    if (xive_router_get_nvt(xrtr, nvt_blk, nvt_idx, &nvt)) {
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid NVT %x/%x\n",
                          nvt_blk, nvt_idx);
        return;
    }

    ipb = xive_get_field32(NVT_W4_IPB, nvt.w4);

    if (ipb) {
        /* Reset the NVT value */
        nvt.w4 = xive_set_field32(NVT_W4_IPB, nvt.w4, 0);
        xive_router_write_nvt(xrtr, nvt_blk, nvt_idx, &nvt, 4);

        /* Merge in current context */
        xive_tctx_ipb_update(tctx, TM_QW1_OS, ipb);
    }
}

/*
 * Updating the OS CAM line can trigger a resend of interrupt
 */
static void xive_tm_push_os_ctx(XivePresenter *xptr, XiveTCTX *tctx,
                                hwaddr offset, uint64_t value, unsigned size)
{
    uint32_t cam = value;
    uint32_t qw1w2 = cpu_to_be32(cam);
    uint8_t nvt_blk;
    uint32_t nvt_idx;
    bool vo;

    xive_os_cam_decode(cam, &nvt_blk, &nvt_idx, &vo);

    /* First update the registers */
    xive_tctx_set_os_cam(tctx, qw1w2);

    /* Check the interrupt pending bits */
    if (vo) {
        xive_tctx_need_resend(XIVE_ROUTER(xptr), tctx, nvt_blk, nvt_idx);
    }
}

/*
 * Define a mapping of "special" operations depending on the TIMA page
 * offset and the size of the operation.
 */
typedef struct XiveTmOp {
    uint8_t  page_offset;
    uint32_t op_offset;
    unsigned size;
    void     (*write_handler)(XivePresenter *xptr, XiveTCTX *tctx,
                              hwaddr offset,
                              uint64_t value, unsigned size);
    uint64_t (*read_handler)(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset,
                             unsigned size);
} XiveTmOp;

static const XiveTmOp xive_tm_operations[] = {
    /*
     * MMIOs below 2K : raw values and special operations without side
     * effects
     */
    { XIVE_TM_OS_PAGE, TM_QW1_OS + TM_CPPR,   1, xive_tm_set_os_cppr, NULL },
    { XIVE_TM_HV_PAGE, TM_QW1_OS + TM_WORD2,     4, xive_tm_push_os_ctx, NULL },
    { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_CPPR, 1, xive_tm_set_hv_cppr, NULL },
    { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_WORD2, 1, xive_tm_vt_push, NULL },
    { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_WORD2, 1, NULL, xive_tm_vt_poll },

    /* MMIOs above 2K : special operations with side effects */
    { XIVE_TM_OS_PAGE, TM_SPC_ACK_OS_REG,     2, NULL, xive_tm_ack_os_reg },
    { XIVE_TM_OS_PAGE, TM_SPC_SET_OS_PENDING, 1, xive_tm_set_os_pending, NULL },
    { XIVE_TM_HV_PAGE, TM_SPC_PULL_OS_CTX,    4, NULL, xive_tm_pull_os_ctx },
    { XIVE_TM_HV_PAGE, TM_SPC_PULL_OS_CTX,    8, NULL, xive_tm_pull_os_ctx },
    { XIVE_TM_HV_PAGE, TM_SPC_ACK_HV_REG,     2, NULL, xive_tm_ack_hv_reg },
    { XIVE_TM_HV_PAGE, TM_SPC_PULL_POOL_CTX,  4, NULL, xive_tm_pull_pool_ctx },
    { XIVE_TM_HV_PAGE, TM_SPC_PULL_POOL_CTX,  8, NULL, xive_tm_pull_pool_ctx },
};

static const XiveTmOp *xive_tm_find_op(hwaddr offset, unsigned size, bool write)
{
    uint8_t page_offset = (offset >> TM_SHIFT) & 0x3;
    uint32_t op_offset = offset & 0xFFF;
    int i;

    for (i = 0; i < ARRAY_SIZE(xive_tm_operations); i++) {
        const XiveTmOp *xto = &xive_tm_operations[i];

        /* Accesses done from a more privileged TIMA page is allowed */
        if (xto->page_offset >= page_offset &&
            xto->op_offset == op_offset &&
            xto->size == size &&
            ((write && xto->write_handler) || (!write && xto->read_handler))) {
            return xto;
        }
    }
    return NULL;
}

/*
 * TIMA MMIO handlers
 */
void xive_tctx_tm_write(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset,
                        uint64_t value, unsigned size)
{
    const XiveTmOp *xto;

    /*
     * TODO: check V bit in Q[0-3]W2
     */

    /*
     * First, check for special operations in the 2K region
     */
    if (offset & 0x800) {
        xto = xive_tm_find_op(offset, size, true);
        if (!xto) {
            qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid write access at TIMA "
                          "@%"HWADDR_PRIx"\n", offset);
        } else {
            xto->write_handler(xptr, tctx, offset, value, size);
        }
        return;
    }

    /*
     * Then, for special operations in the region below 2K.
     */
    xto = xive_tm_find_op(offset, size, true);
    if (xto) {
        xto->write_handler(xptr, tctx, offset, value, size);
        return;
    }

    /*
     * Finish with raw access to the register values
     */
    xive_tm_raw_write(tctx, offset, value, size);
}

uint64_t xive_tctx_tm_read(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset,
                           unsigned size)
{
    const XiveTmOp *xto;

    /*
     * TODO: check V bit in Q[0-3]W2
     */

    /*
     * First, check for special operations in the 2K region
     */
    if (offset & 0x800) {
        xto = xive_tm_find_op(offset, size, false);
        if (!xto) {
            qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid read access to TIMA"
                          "@%"HWADDR_PRIx"\n", offset);
            return -1;
        }
        return xto->read_handler(xptr, tctx, offset, size);
    }

    /*
     * Then, for special operations in the region below 2K.
     */
    xto = xive_tm_find_op(offset, size, false);
    if (xto) {
        return xto->read_handler(xptr, tctx, offset, size);
    }

    /*
     * Finish with raw access to the register values
     */
    return xive_tm_raw_read(tctx, offset, size);
}

static char *xive_tctx_ring_print(uint8_t *ring)
{
    uint32_t w2 = xive_tctx_word2(ring);

    return g_strdup_printf("%02x   %02x  %02x    %02x   %02x  "
                   "%02x  %02x   %02x  %08x",
                   ring[TM_NSR], ring[TM_CPPR], ring[TM_IPB], ring[TM_LSMFB],
                   ring[TM_ACK_CNT], ring[TM_INC], ring[TM_AGE], ring[TM_PIPR],
                   be32_to_cpu(w2));
}

static const char * const xive_tctx_ring_names[] = {
    "USER", "OS", "POOL", "PHYS",
};

void xive_tctx_pic_print_info(XiveTCTX *tctx, Monitor *mon)
{
    int cpu_index;
    int i;

    /* Skip partially initialized vCPUs. This can happen on sPAPR when vCPUs
     * are hot plugged or unplugged.
     */
    if (!tctx) {
        return;
    }

    cpu_index = tctx->cs ? tctx->cs->cpu_index : -1;

    if (kvm_irqchip_in_kernel()) {
        Error *local_err = NULL;

        kvmppc_xive_cpu_synchronize_state(tctx, &local_err);
        if (local_err) {
            error_report_err(local_err);
            return;
        }
    }

    monitor_printf(mon, "CPU[%04x]:   QW   NSR CPPR IPB LSMFB ACK# INC AGE PIPR"
                   "  W2\n", cpu_index);

    for (i = 0; i < XIVE_TM_RING_COUNT; i++) {
        char *s = xive_tctx_ring_print(&tctx->regs[i * XIVE_TM_RING_SIZE]);
        monitor_printf(mon, "CPU[%04x]: %4s    %s\n", cpu_index,
                       xive_tctx_ring_names[i], s);
        g_free(s);
    }
}

void xive_tctx_reset(XiveTCTX *tctx)
{
    memset(tctx->regs, 0, sizeof(tctx->regs));

    /* Set some defaults */
    tctx->regs[TM_QW1_OS + TM_LSMFB] = 0xFF;
    tctx->regs[TM_QW1_OS + TM_ACK_CNT] = 0xFF;
    tctx->regs[TM_QW1_OS + TM_AGE] = 0xFF;

    /*
     * Initialize PIPR to 0xFF to avoid phantom interrupts when the
     * CPPR is first set.
     */
    tctx->regs[TM_QW1_OS + TM_PIPR] =
        ipb_to_pipr(tctx->regs[TM_QW1_OS + TM_IPB]);
    tctx->regs[TM_QW3_HV_PHYS + TM_PIPR] =
        ipb_to_pipr(tctx->regs[TM_QW3_HV_PHYS + TM_IPB]);
}

static void xive_tctx_realize(DeviceState *dev, Error **errp)
{
    XiveTCTX *tctx = XIVE_TCTX(dev);
    PowerPCCPU *cpu;
    CPUPPCState *env;
    Error *local_err = NULL;

    assert(tctx->cs);

    cpu = POWERPC_CPU(tctx->cs);
    env = &cpu->env;
    switch (PPC_INPUT(env)) {
    case PPC_FLAGS_INPUT_POWER9:
        tctx->hv_output = env->irq_inputs[POWER9_INPUT_HINT];
        tctx->os_output = env->irq_inputs[POWER9_INPUT_INT];
        break;

    default:
        error_setg(errp, "XIVE interrupt controller does not support "
                   "this CPU bus model");
        return;
    }

    /* Connect the presenter to the VCPU (required for CPU hotplug) */
    if (kvm_irqchip_in_kernel()) {
        kvmppc_xive_cpu_connect(tctx, &local_err);
        if (local_err) {
            error_propagate(errp, local_err);
            return;
        }
    }
}

static int vmstate_xive_tctx_pre_save(void *opaque)
{
    Error *local_err = NULL;

    if (kvm_irqchip_in_kernel()) {
        kvmppc_xive_cpu_get_state(XIVE_TCTX(opaque), &local_err);
        if (local_err) {
            error_report_err(local_err);
            return -1;
        }
    }

    return 0;
}

static int vmstate_xive_tctx_post_load(void *opaque, int version_id)
{
    Error *local_err = NULL;

    if (kvm_irqchip_in_kernel()) {
        /*
         * Required for hotplugged CPU, for which the state comes
         * after all states of the machine.
         */
        kvmppc_xive_cpu_set_state(XIVE_TCTX(opaque), &local_err);
        if (local_err) {
            error_report_err(local_err);
            return -1;
        }
    }

    return 0;
}

static const VMStateDescription vmstate_xive_tctx = {
    .name = TYPE_XIVE_TCTX,
    .version_id = 1,
    .minimum_version_id = 1,
    .pre_save = vmstate_xive_tctx_pre_save,
    .post_load = vmstate_xive_tctx_post_load,
    .fields = (VMStateField[]) {
        VMSTATE_BUFFER(regs, XiveTCTX),
        VMSTATE_END_OF_LIST()
    },
};

static Property xive_tctx_properties[] = {
    DEFINE_PROP_LINK("cpu", XiveTCTX, cs, TYPE_CPU, CPUState *),
    DEFINE_PROP_END_OF_LIST(),
};

static void xive_tctx_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);

    dc->desc = "XIVE Interrupt Thread Context";
    dc->realize = xive_tctx_realize;
    dc->vmsd = &vmstate_xive_tctx;
    dc->props = xive_tctx_properties;
    /*
     * Reason: part of XIVE interrupt controller, needs to be wired up
     * by xive_tctx_create().
     */
    dc->user_creatable = false;
}

static const TypeInfo xive_tctx_info = {
    .name          = TYPE_XIVE_TCTX,
    .parent        = TYPE_DEVICE,
    .instance_size = sizeof(XiveTCTX),
    .class_init    = xive_tctx_class_init,
};

Object *xive_tctx_create(Object *cpu, XiveRouter *xrtr, Error **errp)
{
    Error *local_err = NULL;
    Object *obj;

    obj = object_new(TYPE_XIVE_TCTX);
    object_property_add_child(cpu, TYPE_XIVE_TCTX, obj, &error_abort);
    object_unref(obj);
    object_property_set_link(obj, cpu, "cpu", &error_abort);
    object_property_set_bool(obj, true, "realized", &local_err);
    if (local_err) {
        goto error;
    }

    return obj;

error:
    object_unparent(obj);
    error_propagate(errp, local_err);
    return NULL;
}

void xive_tctx_destroy(XiveTCTX *tctx)
{
    Object *obj = OBJECT(tctx);

    object_unparent(obj);
}

/*
 * XIVE ESB helpers
 */

static uint8_t xive_esb_set(uint8_t *pq, uint8_t value)
{
    uint8_t old_pq = *pq & 0x3;

    *pq &= ~0x3;
    *pq |= value & 0x3;

    return old_pq;
}

static bool xive_esb_trigger(uint8_t *pq)
{
    uint8_t old_pq = *pq & 0x3;

    switch (old_pq) {
    case XIVE_ESB_RESET:
        xive_esb_set(pq, XIVE_ESB_PENDING);
        return true;
    case XIVE_ESB_PENDING:
    case XIVE_ESB_QUEUED:
        xive_esb_set(pq, XIVE_ESB_QUEUED);
        return false;
    case XIVE_ESB_OFF:
        xive_esb_set(pq, XIVE_ESB_OFF);
        return false;
    default:
         g_assert_not_reached();
    }
}

static bool xive_esb_eoi(uint8_t *pq)
{
    uint8_t old_pq = *pq & 0x3;

    switch (old_pq) {
    case XIVE_ESB_RESET:
    case XIVE_ESB_PENDING:
        xive_esb_set(pq, XIVE_ESB_RESET);
        return false;
    case XIVE_ESB_QUEUED:
        xive_esb_set(pq, XIVE_ESB_PENDING);
        return true;
    case XIVE_ESB_OFF:
        xive_esb_set(pq, XIVE_ESB_OFF);
        return false;
    default:
         g_assert_not_reached();
    }
}

/*
 * XIVE Interrupt Source (or IVSE)
 */

uint8_t xive_source_esb_get(XiveSource *xsrc, uint32_t srcno)
{
    assert(srcno < xsrc->nr_irqs);

    return xsrc->status[srcno] & 0x3;
}

uint8_t xive_source_esb_set(XiveSource *xsrc, uint32_t srcno, uint8_t pq)
{
    assert(srcno < xsrc->nr_irqs);

    return xive_esb_set(&xsrc->status[srcno], pq);
}

/*
 * Returns whether the event notification should be forwarded.
 */
static bool xive_source_lsi_trigger(XiveSource *xsrc, uint32_t srcno)
{
    uint8_t old_pq = xive_source_esb_get(xsrc, srcno);

    xsrc->status[srcno] |= XIVE_STATUS_ASSERTED;

    switch (old_pq) {
    case XIVE_ESB_RESET:
        xive_source_esb_set(xsrc, srcno, XIVE_ESB_PENDING);
        return true;
    default:
        return false;
    }
}

/*
 * Returns whether the event notification should be forwarded.
 */
static bool xive_source_esb_trigger(XiveSource *xsrc, uint32_t srcno)
{
    bool ret;

    assert(srcno < xsrc->nr_irqs);

    ret = xive_esb_trigger(&xsrc->status[srcno]);

    if (xive_source_irq_is_lsi(xsrc, srcno) &&
        xive_source_esb_get(xsrc, srcno) == XIVE_ESB_QUEUED) {
        qemu_log_mask(LOG_GUEST_ERROR,
                      "XIVE: queued an event on LSI IRQ %d\n", srcno);
    }

    return ret;
}

/*
 * Returns whether the event notification should be forwarded.
 */
static bool xive_source_esb_eoi(XiveSource *xsrc, uint32_t srcno)
{
    bool ret;

    assert(srcno < xsrc->nr_irqs);

    ret = xive_esb_eoi(&xsrc->status[srcno]);

    /*
     * LSI sources do not set the Q bit but they can still be
     * asserted, in which case we should forward a new event
     * notification
     */
    if (xive_source_irq_is_lsi(xsrc, srcno) &&
        xsrc->status[srcno] & XIVE_STATUS_ASSERTED) {
        ret = xive_source_lsi_trigger(xsrc, srcno);
    }

    return ret;
}

/*
 * Forward the source event notification to the Router
 */
static void xive_source_notify(XiveSource *xsrc, int srcno)
{
    XiveNotifierClass *xnc = XIVE_NOTIFIER_GET_CLASS(xsrc->xive);

    if (xnc->notify) {
        xnc->notify(xsrc->xive, srcno);
    }
}

/*
 * In a two pages ESB MMIO setting, even page is the trigger page, odd
 * page is for management
 */
static inline bool addr_is_even(hwaddr addr, uint32_t shift)
{
    return !((addr >> shift) & 1);
}

static inline bool xive_source_is_trigger_page(XiveSource *xsrc, hwaddr addr)
{
    return xive_source_esb_has_2page(xsrc) &&
        addr_is_even(addr, xsrc->esb_shift - 1);
}

/*
 * ESB MMIO loads
 *                      Trigger page    Management/EOI page
 *
 * ESB MMIO setting     2 pages         1 or 2 pages
 *
 * 0x000 .. 0x3FF       -1              EOI and return 0|1
 * 0x400 .. 0x7FF       -1              EOI and return 0|1
 * 0x800 .. 0xBFF       -1              return PQ
 * 0xC00 .. 0xCFF       -1              return PQ and atomically PQ=00
 * 0xD00 .. 0xDFF       -1              return PQ and atomically PQ=01
 * 0xE00 .. 0xDFF       -1              return PQ and atomically PQ=10
 * 0xF00 .. 0xDFF       -1              return PQ and atomically PQ=11
 */
static uint64_t xive_source_esb_read(void *opaque, hwaddr addr, unsigned size)
{
    XiveSource *xsrc = XIVE_SOURCE(opaque);
    uint32_t offset = addr & 0xFFF;
    uint32_t srcno = addr >> xsrc->esb_shift;
    uint64_t ret = -1;

    /* In a two pages ESB MMIO setting, trigger page should not be read */
    if (xive_source_is_trigger_page(xsrc, addr)) {
        qemu_log_mask(LOG_GUEST_ERROR,
                      "XIVE: invalid load on IRQ %d trigger page at "
                      "0x%"HWADDR_PRIx"\n", srcno, addr);
        return -1;
    }

    switch (offset) {
    case XIVE_ESB_LOAD_EOI ... XIVE_ESB_LOAD_EOI + 0x7FF:
        ret = xive_source_esb_eoi(xsrc, srcno);

        /* Forward the source event notification for routing */
        if (ret) {
            xive_source_notify(xsrc, srcno);
        }
        break;

    case XIVE_ESB_GET ... XIVE_ESB_GET + 0x3FF:
        ret = xive_source_esb_get(xsrc, srcno);
        break;

    case XIVE_ESB_SET_PQ_00 ... XIVE_ESB_SET_PQ_00 + 0x0FF:
    case XIVE_ESB_SET_PQ_01 ... XIVE_ESB_SET_PQ_01 + 0x0FF:
    case XIVE_ESB_SET_PQ_10 ... XIVE_ESB_SET_PQ_10 + 0x0FF:
    case XIVE_ESB_SET_PQ_11 ... XIVE_ESB_SET_PQ_11 + 0x0FF:
        ret = xive_source_esb_set(xsrc, srcno, (offset >> 8) & 0x3);
        break;
    default:
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid ESB load addr %x\n",
                      offset);
    }

    return ret;
}

/*
 * ESB MMIO stores
 *                      Trigger page    Management/EOI page
 *
 * ESB MMIO setting     2 pages         1 or 2 pages
 *
 * 0x000 .. 0x3FF       Trigger         Trigger
 * 0x400 .. 0x7FF       Trigger         EOI
 * 0x800 .. 0xBFF       Trigger         undefined
 * 0xC00 .. 0xCFF       Trigger         PQ=00
 * 0xD00 .. 0xDFF       Trigger         PQ=01
 * 0xE00 .. 0xDFF       Trigger         PQ=10
 * 0xF00 .. 0xDFF       Trigger         PQ=11
 */
static void xive_source_esb_write(void *opaque, hwaddr addr,
                                  uint64_t value, unsigned size)
{
    XiveSource *xsrc = XIVE_SOURCE(opaque);
    uint32_t offset = addr & 0xFFF;
    uint32_t srcno = addr >> xsrc->esb_shift;
    bool notify = false;

    /* In a two pages ESB MMIO setting, trigger page only triggers */
    if (xive_source_is_trigger_page(xsrc, addr)) {
        notify = xive_source_esb_trigger(xsrc, srcno);
        goto out;
    }

    switch (offset) {
    case 0 ... 0x3FF:
        notify = xive_source_esb_trigger(xsrc, srcno);
        break;

    case XIVE_ESB_STORE_EOI ... XIVE_ESB_STORE_EOI + 0x3FF:
        if (!(xsrc->esb_flags & XIVE_SRC_STORE_EOI)) {
            qemu_log_mask(LOG_GUEST_ERROR,
                          "XIVE: invalid Store EOI for IRQ %d\n", srcno);
            return;
        }

        notify = xive_source_esb_eoi(xsrc, srcno);
        break;

    case XIVE_ESB_SET_PQ_00 ... XIVE_ESB_SET_PQ_00 + 0x0FF:
    case XIVE_ESB_SET_PQ_01 ... XIVE_ESB_SET_PQ_01 + 0x0FF:
    case XIVE_ESB_SET_PQ_10 ... XIVE_ESB_SET_PQ_10 + 0x0FF:
    case XIVE_ESB_SET_PQ_11 ... XIVE_ESB_SET_PQ_11 + 0x0FF:
        xive_source_esb_set(xsrc, srcno, (offset >> 8) & 0x3);
        break;

    default:
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid ESB write addr %x\n",
                      offset);
        return;
    }

out:
    /* Forward the source event notification for routing */
    if (notify) {
        xive_source_notify(xsrc, srcno);
    }
}

static const MemoryRegionOps xive_source_esb_ops = {
    .read = xive_source_esb_read,
    .write = xive_source_esb_write,
    .endianness = DEVICE_BIG_ENDIAN,
    .valid = {
        .min_access_size = 8,
        .max_access_size = 8,
    },
    .impl = {
        .min_access_size = 8,
        .max_access_size = 8,
    },
};

void xive_source_set_irq(void *opaque, int srcno, int val)
{
    XiveSource *xsrc = XIVE_SOURCE(opaque);
    bool notify = false;

    if (xive_source_irq_is_lsi(xsrc, srcno)) {
        if (val) {
            notify = xive_source_lsi_trigger(xsrc, srcno);
        } else {
            xsrc->status[srcno] &= ~XIVE_STATUS_ASSERTED;
        }
    } else {
        if (val) {
            notify = xive_source_esb_trigger(xsrc, srcno);
        }
    }

    /* Forward the source event notification for routing */
    if (notify) {
        xive_source_notify(xsrc, srcno);
    }
}

void xive_source_pic_print_info(XiveSource *xsrc, uint32_t offset, Monitor *mon)
{
    int i;

    for (i = 0; i < xsrc->nr_irqs; i++) {
        uint8_t pq = xive_source_esb_get(xsrc, i);

        if (pq == XIVE_ESB_OFF) {
            continue;
        }

        monitor_printf(mon, "  %08x %s %c%c%c\n", i + offset,
                       xive_source_irq_is_lsi(xsrc, i) ? "LSI" : "MSI",
                       pq & XIVE_ESB_VAL_P ? 'P' : '-',
                       pq & XIVE_ESB_VAL_Q ? 'Q' : '-',
                       xsrc->status[i] & XIVE_STATUS_ASSERTED ? 'A' : ' ');
    }
}

static void xive_source_reset(void *dev)
{
    XiveSource *xsrc = XIVE_SOURCE(dev);

    /* Do not clear the LSI bitmap */

    /* PQs are initialized to 0b01 (Q=1) which corresponds to "ints off" */
    memset(xsrc->status, XIVE_ESB_OFF, xsrc->nr_irqs);
}

static void xive_source_realize(DeviceState *dev, Error **errp)
{
    XiveSource *xsrc = XIVE_SOURCE(dev);

    assert(xsrc->xive);

    if (!xsrc->nr_irqs) {
        error_setg(errp, "Number of interrupt needs to be greater than 0");
        return;
    }

    if (xsrc->esb_shift != XIVE_ESB_4K &&
        xsrc->esb_shift != XIVE_ESB_4K_2PAGE &&
        xsrc->esb_shift != XIVE_ESB_64K &&
        xsrc->esb_shift != XIVE_ESB_64K_2PAGE) {
        error_setg(errp, "Invalid ESB shift setting");
        return;
    }

    xsrc->status = g_malloc0(xsrc->nr_irqs);
    xsrc->lsi_map = bitmap_new(xsrc->nr_irqs);

    if (!kvm_irqchip_in_kernel()) {
        memory_region_init_io(&xsrc->esb_mmio, OBJECT(xsrc),
                              &xive_source_esb_ops, xsrc, "xive.esb",
                              (1ull << xsrc->esb_shift) * xsrc->nr_irqs);
    }

    qemu_register_reset(xive_source_reset, dev);
}

static const VMStateDescription vmstate_xive_source = {
    .name = TYPE_XIVE_SOURCE,
    .version_id = 1,
    .minimum_version_id = 1,
    .fields = (VMStateField[]) {
        VMSTATE_UINT32_EQUAL(nr_irqs, XiveSource, NULL),
        VMSTATE_VBUFFER_UINT32(status, XiveSource, 1, NULL, nr_irqs),
        VMSTATE_END_OF_LIST()
    },
};

/*
 * The default XIVE interrupt source setting for the ESB MMIOs is two
 * 64k pages without Store EOI, to be in sync with KVM.
 */
static Property xive_source_properties[] = {
    DEFINE_PROP_UINT64("flags", XiveSource, esb_flags, 0),
    DEFINE_PROP_UINT32("nr-irqs", XiveSource, nr_irqs, 0),
    DEFINE_PROP_UINT32("shift", XiveSource, esb_shift, XIVE_ESB_64K_2PAGE),
    DEFINE_PROP_LINK("xive", XiveSource, xive, TYPE_XIVE_NOTIFIER,
                     XiveNotifier *),
    DEFINE_PROP_END_OF_LIST(),
};

static void xive_source_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);

    dc->desc    = "XIVE Interrupt Source";
    dc->props   = xive_source_properties;
    dc->realize = xive_source_realize;
    dc->vmsd    = &vmstate_xive_source;
    /*
     * Reason: part of XIVE interrupt controller, needs to be wired up,
     * e.g. by spapr_xive_instance_init().
     */
    dc->user_creatable = false;
}

static const TypeInfo xive_source_info = {
    .name          = TYPE_XIVE_SOURCE,
    .parent        = TYPE_DEVICE,
    .instance_size = sizeof(XiveSource),
    .class_init    = xive_source_class_init,
};

/*
 * XiveEND helpers
 */

void xive_end_queue_pic_print_info(XiveEND *end, uint32_t width, Monitor *mon)
{
    uint64_t qaddr_base = xive_end_qaddr(end);
    uint32_t qsize = xive_get_field32(END_W0_QSIZE, end->w0);
    uint32_t qindex = xive_get_field32(END_W1_PAGE_OFF, end->w1);
    uint32_t qentries = 1 << (qsize + 10);
    int i;

    /*
     * print out the [ (qindex - (width - 1)) .. (qindex + 1)] window
     */
    monitor_printf(mon, " [ ");
    qindex = (qindex - (width - 1)) & (qentries - 1);
    for (i = 0; i < width; i++) {
        uint64_t qaddr = qaddr_base + (qindex << 2);
        uint32_t qdata = -1;

        if (dma_memory_read(&address_space_memory, qaddr, &qdata,
                            sizeof(qdata))) {
            qemu_log_mask(LOG_GUEST_ERROR, "XIVE: failed to read EQ @0x%"
                          HWADDR_PRIx "\n", qaddr);
            return;
        }
        monitor_printf(mon, "%s%08x ", i == width - 1 ? "^" : "",
                       be32_to_cpu(qdata));
        qindex = (qindex + 1) & (qentries - 1);
    }
    monitor_printf(mon, "]");
}

void xive_end_pic_print_info(XiveEND *end, uint32_t end_idx, Monitor *mon)
{
    uint64_t qaddr_base = xive_end_qaddr(end);
    uint32_t qindex = xive_get_field32(END_W1_PAGE_OFF, end->w1);
    uint32_t qgen = xive_get_field32(END_W1_GENERATION, end->w1);
    uint32_t qsize = xive_get_field32(END_W0_QSIZE, end->w0);
    uint32_t qentries = 1 << (qsize + 10);

    uint32_t nvt_blk = xive_get_field32(END_W6_NVT_BLOCK, end->w6);
    uint32_t nvt_idx = xive_get_field32(END_W6_NVT_INDEX, end->w6);
    uint8_t priority = xive_get_field32(END_W7_F0_PRIORITY, end->w7);
    uint8_t pq;

    if (!xive_end_is_valid(end)) {
        return;
    }

    pq = xive_get_field32(END_W1_ESn, end->w1);

    monitor_printf(mon, "  %08x %c%c %c%c%c%c%c%c%c prio:%d nvt:%02x/%04x",
                   end_idx,
                   pq & XIVE_ESB_VAL_P ? 'P' : '-',
                   pq & XIVE_ESB_VAL_Q ? 'Q' : '-',
                   xive_end_is_valid(end)    ? 'v' : '-',
                   xive_end_is_enqueue(end)  ? 'q' : '-',
                   xive_end_is_notify(end)   ? 'n' : '-',
                   xive_end_is_backlog(end)  ? 'b' : '-',
                   xive_end_is_escalate(end) ? 'e' : '-',
                   xive_end_is_uncond_escalation(end)   ? 'u' : '-',
                   xive_end_is_silent_escalation(end)   ? 's' : '-',
                   priority, nvt_blk, nvt_idx);

    if (qaddr_base) {
        monitor_printf(mon, " eq:@%08"PRIx64"% 6d/%5d ^%d",
                       qaddr_base, qindex, qentries, qgen);
        xive_end_queue_pic_print_info(end, 6, mon);
    }
    monitor_printf(mon, "\n");
}

static void xive_end_enqueue(XiveEND *end, uint32_t data)
{
    uint64_t qaddr_base = xive_end_qaddr(end);
    uint32_t qsize = xive_get_field32(END_W0_QSIZE, end->w0);
    uint32_t qindex = xive_get_field32(END_W1_PAGE_OFF, end->w1);
    uint32_t qgen = xive_get_field32(END_W1_GENERATION, end->w1);

    uint64_t qaddr = qaddr_base + (qindex << 2);
    uint32_t qdata = cpu_to_be32((qgen << 31) | (data & 0x7fffffff));
    uint32_t qentries = 1 << (qsize + 10);

    if (dma_memory_write(&address_space_memory, qaddr, &qdata, sizeof(qdata))) {
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: failed to write END data @0x%"
                      HWADDR_PRIx "\n", qaddr);
        return;
    }

    qindex = (qindex + 1) & (qentries - 1);
    if (qindex == 0) {
        qgen ^= 1;
        end->w1 = xive_set_field32(END_W1_GENERATION, end->w1, qgen);
    }
    end->w1 = xive_set_field32(END_W1_PAGE_OFF, end->w1, qindex);
}

void xive_end_eas_pic_print_info(XiveEND *end, uint32_t end_idx,
                                   Monitor *mon)
{
    XiveEAS *eas = (XiveEAS *) &end->w4;
    uint8_t pq;

    if (!xive_end_is_escalate(end)) {
        return;
    }

    pq = xive_get_field32(END_W1_ESe, end->w1);

    monitor_printf(mon, "  %08x %c%c %c%c end:%02x/%04x data:%08x\n",
                   end_idx,
                   pq & XIVE_ESB_VAL_P ? 'P' : '-',
                   pq & XIVE_ESB_VAL_Q ? 'Q' : '-',
                   xive_eas_is_valid(eas) ? 'V' : ' ',
                   xive_eas_is_masked(eas) ? 'M' : ' ',
                   (uint8_t)  xive_get_field64(EAS_END_BLOCK, eas->w),
                   (uint32_t) xive_get_field64(EAS_END_INDEX, eas->w),
                   (uint32_t) xive_get_field64(EAS_END_DATA, eas->w));
}

/*
 * XIVE Router (aka. Virtualization Controller or IVRE)
 */

int xive_router_get_eas(XiveRouter *xrtr, uint8_t eas_blk, uint32_t eas_idx,
                        XiveEAS *eas)
{
    XiveRouterClass *xrc = XIVE_ROUTER_GET_CLASS(xrtr);

    return xrc->get_eas(xrtr, eas_blk, eas_idx, eas);
}

int xive_router_get_end(XiveRouter *xrtr, uint8_t end_blk, uint32_t end_idx,
                        XiveEND *end)
{
   XiveRouterClass *xrc = XIVE_ROUTER_GET_CLASS(xrtr);

   return xrc->get_end(xrtr, end_blk, end_idx, end);
}

int xive_router_write_end(XiveRouter *xrtr, uint8_t end_blk, uint32_t end_idx,
                          XiveEND *end, uint8_t word_number)
{
   XiveRouterClass *xrc = XIVE_ROUTER_GET_CLASS(xrtr);

   return xrc->write_end(xrtr, end_blk, end_idx, end, word_number);
}

int xive_router_get_nvt(XiveRouter *xrtr, uint8_t nvt_blk, uint32_t nvt_idx,
                        XiveNVT *nvt)
{
   XiveRouterClass *xrc = XIVE_ROUTER_GET_CLASS(xrtr);

   return xrc->get_nvt(xrtr, nvt_blk, nvt_idx, nvt);
}

int xive_router_write_nvt(XiveRouter *xrtr, uint8_t nvt_blk, uint32_t nvt_idx,
                        XiveNVT *nvt, uint8_t word_number)
{
   XiveRouterClass *xrc = XIVE_ROUTER_GET_CLASS(xrtr);

   return xrc->write_nvt(xrtr, nvt_blk, nvt_idx, nvt, word_number);
}

static int xive_router_get_block_id(XiveRouter *xrtr)
{
   XiveRouterClass *xrc = XIVE_ROUTER_GET_CLASS(xrtr);

   return xrc->get_block_id(xrtr);
}

/*
 * Encode the HW CAM line in the block group mode format :
 *
 *   chip << 19 | 0000000 0 0001 thread (7Bit)
 */
static uint32_t xive_tctx_hw_cam_line(XivePresenter *xptr, XiveTCTX *tctx)
{
    CPUPPCState *env = &POWERPC_CPU(tctx->cs)->env;
    uint32_t pir = env->spr_cb[SPR_PIR].default_value;
    uint8_t blk = xive_router_get_block_id(XIVE_ROUTER(xptr));

    return xive_nvt_cam_line(blk, 1 << 7 | (pir & 0x7f));
}

/*
 * The thread context register words are in big-endian format.
 */
int xive_presenter_tctx_match(XivePresenter *xptr, XiveTCTX *tctx,
                              uint8_t format,
                              uint8_t nvt_blk, uint32_t nvt_idx,
                              bool cam_ignore, uint32_t logic_serv)
{
    uint32_t cam = xive_nvt_cam_line(nvt_blk, nvt_idx);
    uint32_t qw3w2 = xive_tctx_word2(&tctx->regs[TM_QW3_HV_PHYS]);
    uint32_t qw2w2 = xive_tctx_word2(&tctx->regs[TM_QW2_HV_POOL]);
    uint32_t qw1w2 = xive_tctx_word2(&tctx->regs[TM_QW1_OS]);
    uint32_t qw0w2 = xive_tctx_word2(&tctx->regs[TM_QW0_USER]);

    /*
     * TODO (PowerNV): ignore mode. The low order bits of the NVT
     * identifier are ignored in the "CAM" match.
     */

    if (format == 0) {
        if (cam_ignore == true) {
            /*
             * F=0 & i=1: Logical server notification (bits ignored at
             * the end of the NVT identifier)
             */
            qemu_log_mask(LOG_UNIMP, "XIVE: no support for LS NVT %x/%x\n",
                          nvt_blk, nvt_idx);
             return -1;
        }

        /* F=0 & i=0: Specific NVT notification */

        /* PHYS ring */
        if ((be32_to_cpu(qw3w2) & TM_QW3W2_VT) &&
            cam == xive_tctx_hw_cam_line(xptr, tctx)) {
            return TM_QW3_HV_PHYS;
        }

        /* HV POOL ring */
        if ((be32_to_cpu(qw2w2) & TM_QW2W2_VP) &&
            cam == xive_get_field32(TM_QW2W2_POOL_CAM, qw2w2)) {
            return TM_QW2_HV_POOL;
        }

        /* OS ring */
        if ((be32_to_cpu(qw1w2) & TM_QW1W2_VO) &&
            cam == xive_get_field32(TM_QW1W2_OS_CAM, qw1w2)) {
            return TM_QW1_OS;
        }
    } else {
        /* F=1 : User level Event-Based Branch (EBB) notification */

        /* USER ring */
        if  ((be32_to_cpu(qw1w2) & TM_QW1W2_VO) &&
             (cam == xive_get_field32(TM_QW1W2_OS_CAM, qw1w2)) &&
             (be32_to_cpu(qw0w2) & TM_QW0W2_VU) &&
             (logic_serv == xive_get_field32(TM_QW0W2_LOGIC_SERV, qw0w2))) {
            return TM_QW0_USER;
        }
    }
    return -1;
}

/*
 * This is our simple Xive Presenter Engine model. It is merged in the
 * Router as it does not require an extra object.
 *
 * It receives notification requests sent by the IVRE to find one
 * matching NVT (or more) dispatched on the processor threads. In case
 * of a single NVT notification, the process is abreviated and the
 * thread is signaled if a match is found. In case of a logical server
 * notification (bits ignored at the end of the NVT identifier), the
 * IVPE and IVRE select a winning thread using different filters. This
 * involves 2 or 3 exchanges on the PowerBus that the model does not
 * support.
 *
 * The parameters represent what is sent on the PowerBus
 */
static bool xive_presenter_notify(uint8_t format,
                                  uint8_t nvt_blk, uint32_t nvt_idx,
                                  bool cam_ignore, uint8_t priority,
                                  uint32_t logic_serv)
{
    XiveFabric *xfb = XIVE_FABRIC(qdev_get_machine());
    XiveFabricClass *xfc = XIVE_FABRIC_GET_CLASS(xfb);
    XiveTCTXMatch match = { .tctx = NULL, .ring = 0 };
    int count;

    /*
     * Ask the machine to scan the interrupt controllers for a match
     */
    count = xfc->match_nvt(xfb, format, nvt_blk, nvt_idx, cam_ignore,
                           priority, logic_serv, &match);
    if (count < 0) {
        return false;
    }

    /* handle CPU exception delivery */
    if (count) {
        xive_tctx_ipb_update(match.tctx, match.ring, priority_to_ipb(priority));
    }

    return !!count;
}

/*
 * Notification using the END ESe/ESn bit (Event State Buffer for
 * escalation and notification). Profide futher coalescing in the
 * Router.
 */
static bool xive_router_end_es_notify(XiveRouter *xrtr, uint8_t end_blk,
                                      uint32_t end_idx, XiveEND *end,
                                      uint32_t end_esmask)
{
    uint8_t pq = xive_get_field32(end_esmask, end->w1);
    bool notify = xive_esb_trigger(&pq);

    if (pq != xive_get_field32(end_esmask, end->w1)) {
        end->w1 = xive_set_field32(end_esmask, end->w1, pq);
        xive_router_write_end(xrtr, end_blk, end_idx, end, 1);
    }

    /* ESe/n[Q]=1 : end of notification */
    return notify;
}

/*
 * An END trigger can come from an event trigger (IPI or HW) or from
 * another chip. We don't model the PowerBus but the END trigger
 * message has the same parameters than in the function below.
 */
static void xive_router_end_notify(XiveRouter *xrtr, uint8_t end_blk,
                                   uint32_t end_idx, uint32_t end_data)
{
    XiveEND end;
    uint8_t priority;
    uint8_t format;
    uint8_t nvt_blk;
    uint32_t nvt_idx;
    XiveNVT nvt;
    bool found;

    /* END cache lookup */
    if (xive_router_get_end(xrtr, end_blk, end_idx, &end)) {
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: No END %x/%x\n", end_blk,
                      end_idx);
        return;
    }

    if (!xive_end_is_valid(&end)) {
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: END %x/%x is invalid\n",
                      end_blk, end_idx);
        return;
    }

    if (xive_end_is_enqueue(&end)) {
        xive_end_enqueue(&end, end_data);
        /* Enqueuing event data modifies the EQ toggle and index */
        xive_router_write_end(xrtr, end_blk, end_idx, &end, 1);
    }

    /*
     * When the END is silent, we skip the notification part.
     */
    if (xive_end_is_silent_escalation(&end)) {
        goto do_escalation;
    }

    /*
     * The W7 format depends on the F bit in W6. It defines the type
     * of the notification :
     *
     *   F=0 : single or multiple NVT notification
     *   F=1 : User level Event-Based Branch (EBB) notification, no
     *         priority
     */
    format = xive_get_field32(END_W6_FORMAT_BIT, end.w6);
    priority = xive_get_field32(END_W7_F0_PRIORITY, end.w7);

    /* The END is masked */
    if (format == 0 && priority == 0xff) {
        return;
    }

    /*
     * Check the END ESn (Event State Buffer for notification) for
     * even futher coalescing in the Router
     */
    if (!xive_end_is_notify(&end)) {
        /* ESn[Q]=1 : end of notification */
        if (!xive_router_end_es_notify(xrtr, end_blk, end_idx,
                                       &end, END_W1_ESn)) {
            return;
        }
    }

    /*
     * Follows IVPE notification
     */
    nvt_blk = xive_get_field32(END_W6_NVT_BLOCK, end.w6);
    nvt_idx = xive_get_field32(END_W6_NVT_INDEX, end.w6);

    /* NVT cache lookup */
    if (xive_router_get_nvt(xrtr, nvt_blk, nvt_idx, &nvt)) {
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: no NVT %x/%x\n",
                      nvt_blk, nvt_idx);
        return;
    }

    if (!xive_nvt_is_valid(&nvt)) {
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: NVT %x/%x is invalid\n",
                      nvt_blk, nvt_idx);
        return;
    }

    found = xive_presenter_notify(format, nvt_blk, nvt_idx,
                          xive_get_field32(END_W7_F0_IGNORE, end.w7),
                          priority,
                          xive_get_field32(END_W7_F1_LOG_SERVER_ID, end.w7));

    /* TODO: Auto EOI. */

    if (found) {
        return;
    }

    /*
     * If no matching NVT is dispatched on a HW thread :
     * - specific VP: update the NVT structure if backlog is activated
     * - logical server : forward request to IVPE (not supported)
     */
    if (xive_end_is_backlog(&end)) {
        uint8_t ipb;

        if (format == 1) {
            qemu_log_mask(LOG_GUEST_ERROR,
                          "XIVE: END %x/%x invalid config: F1 & backlog\n",
                          end_blk, end_idx);
            return;
        }
        /*
         * Record the IPB in the associated NVT structure for later
         * use. The presenter will resend the interrupt when the vCPU
         * is dispatched again on a HW thread.
         */
        ipb = xive_get_field32(NVT_W4_IPB, nvt.w4) | priority_to_ipb(priority);
        nvt.w4 = xive_set_field32(NVT_W4_IPB, nvt.w4, ipb);
        xive_router_write_nvt(xrtr, nvt_blk, nvt_idx, &nvt, 4);

        /*
         * On HW, follows a "Broadcast Backlog" to IVPEs
         */
    }

do_escalation:
    /*
     * If activated, escalate notification using the ESe PQ bits and
     * the EAS in w4-5
     */
    if (!xive_end_is_escalate(&end)) {
        return;
    }

    /*
     * Check the END ESe (Event State Buffer for escalation) for even
     * futher coalescing in the Router
     */
    if (!xive_end_is_uncond_escalation(&end)) {
        /* ESe[Q]=1 : end of notification */
        if (!xive_router_end_es_notify(xrtr, end_blk, end_idx,
                                       &end, END_W1_ESe)) {
            return;
        }
    }

    /*
     * The END trigger becomes an Escalation trigger
     */
    xive_router_end_notify(xrtr,
                           xive_get_field32(END_W4_ESC_END_BLOCK, end.w4),
                           xive_get_field32(END_W4_ESC_END_INDEX, end.w4),
                           xive_get_field32(END_W5_ESC_END_DATA,  end.w5));
}

void xive_router_notify(XiveNotifier *xn, uint32_t lisn)
{
    XiveRouter *xrtr = XIVE_ROUTER(xn);
    uint8_t eas_blk = XIVE_EAS_BLOCK(lisn);
    uint32_t eas_idx = XIVE_EAS_INDEX(lisn);
    XiveEAS eas;

    /* EAS cache lookup */
    if (xive_router_get_eas(xrtr, eas_blk, eas_idx, &eas)) {
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: Unknown LISN %x\n", lisn);
        return;
    }

    /*
     * The IVRE checks the State Bit Cache at this point. We skip the
     * SBC lookup because the state bits of the sources are modeled
     * internally in QEMU.
     */

    if (!xive_eas_is_valid(&eas)) {
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid LISN %x\n", lisn);
        return;
    }

    if (xive_eas_is_masked(&eas)) {
        /* Notification completed */
        return;
    }

    /*
     * The event trigger becomes an END trigger
     */
    xive_router_end_notify(xrtr,
                           xive_get_field64(EAS_END_BLOCK, eas.w),
                           xive_get_field64(EAS_END_INDEX, eas.w),
                           xive_get_field64(EAS_END_DATA,  eas.w));
}

static void xive_router_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);
    XiveNotifierClass *xnc = XIVE_NOTIFIER_CLASS(klass);

    dc->desc    = "XIVE Router Engine";
    xnc->notify = xive_router_notify;
}

static const TypeInfo xive_router_info = {
    .name          = TYPE_XIVE_ROUTER,
    .parent        = TYPE_SYS_BUS_DEVICE,
    .abstract      = true,
    .class_size    = sizeof(XiveRouterClass),
    .class_init    = xive_router_class_init,
    .interfaces    = (InterfaceInfo[]) {
        { TYPE_XIVE_NOTIFIER },
        { TYPE_XIVE_PRESENTER },
        { }
    }
};

void xive_eas_pic_print_info(XiveEAS *eas, uint32_t lisn, Monitor *mon)
{
    if (!xive_eas_is_valid(eas)) {
        return;
    }

    monitor_printf(mon, "  %08x %s end:%02x/%04x data:%08x\n",
                   lisn, xive_eas_is_masked(eas) ? "M" : " ",
                   (uint8_t)  xive_get_field64(EAS_END_BLOCK, eas->w),
                   (uint32_t) xive_get_field64(EAS_END_INDEX, eas->w),
                   (uint32_t) xive_get_field64(EAS_END_DATA, eas->w));
}

/*
 * END ESB MMIO loads
 */
static uint64_t xive_end_source_read(void *opaque, hwaddr addr, unsigned size)
{
    XiveENDSource *xsrc = XIVE_END_SOURCE(opaque);
    uint32_t offset = addr & 0xFFF;
    uint8_t end_blk;
    uint32_t end_idx;
    XiveEND end;
    uint32_t end_esmask;
    uint8_t pq;
    uint64_t ret = -1;

    /*
     * The block id should be deduced from the load address on the END
     * ESB MMIO but our model only supports a single block per XIVE chip.
     */
    end_blk = xive_router_get_block_id(xsrc->xrtr);
    end_idx = addr >> (xsrc->esb_shift + 1);

    if (xive_router_get_end(xsrc->xrtr, end_blk, end_idx, &end)) {
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: No END %x/%x\n", end_blk,
                      end_idx);
        return -1;
    }

    if (!xive_end_is_valid(&end)) {
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: END %x/%x is invalid\n",
                      end_blk, end_idx);
        return -1;
    }

    end_esmask = addr_is_even(addr, xsrc->esb_shift) ? END_W1_ESn : END_W1_ESe;
    pq = xive_get_field32(end_esmask, end.w1);

    switch (offset) {
    case XIVE_ESB_LOAD_EOI ... XIVE_ESB_LOAD_EOI + 0x7FF:
        ret = xive_esb_eoi(&pq);

        /* Forward the source event notification for routing ?? */
        break;

    case XIVE_ESB_GET ... XIVE_ESB_GET + 0x3FF:
        ret = pq;
        break;

    case XIVE_ESB_SET_PQ_00 ... XIVE_ESB_SET_PQ_00 + 0x0FF:
    case XIVE_ESB_SET_PQ_01 ... XIVE_ESB_SET_PQ_01 + 0x0FF:
    case XIVE_ESB_SET_PQ_10 ... XIVE_ESB_SET_PQ_10 + 0x0FF:
    case XIVE_ESB_SET_PQ_11 ... XIVE_ESB_SET_PQ_11 + 0x0FF:
        ret = xive_esb_set(&pq, (offset >> 8) & 0x3);
        break;
    default:
        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid END ESB load addr %d\n",
                      offset);
        return -1;
    }

    if (pq != xive_get_field32(end_esmask, end.w1)) {
        end.w1 = xive_set_field32(end_esmask, end.w1, pq);
        xive_router_write_end(xsrc->xrtr, end_blk, end_idx, &end, 1);
    }

    return ret;
}

/*
 * END ESB MMIO stores are invalid
 */
static void xive_end_source_write(void *opaque, hwaddr addr,
                                  uint64_t value, unsigned size)
{
    qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid ESB write addr 0x%"
                  HWADDR_PRIx"\n", addr);
}

static const MemoryRegionOps xive_end_source_ops = {
    .read = xive_end_source_read,
    .write = xive_end_source_write,
    .endianness = DEVICE_BIG_ENDIAN,
    .valid = {
        .min_access_size = 8,
        .max_access_size = 8,
    },
    .impl = {
        .min_access_size = 8,
        .max_access_size = 8,
    },
};

static void xive_end_source_realize(DeviceState *dev, Error **errp)
{
    XiveENDSource *xsrc = XIVE_END_SOURCE(dev);

    assert(xsrc->xrtr);

    if (!xsrc->nr_ends) {
        error_setg(errp, "Number of interrupt needs to be greater than 0");
        return;
    }

    if (xsrc->esb_shift != XIVE_ESB_4K &&
        xsrc->esb_shift != XIVE_ESB_64K) {
        error_setg(errp, "Invalid ESB shift setting");
        return;
    }

    /*
     * Each END is assigned an even/odd pair of MMIO pages, the even page
     * manages the ESn field while the odd page manages the ESe field.
     */
    memory_region_init_io(&xsrc->esb_mmio, OBJECT(xsrc),
                          &xive_end_source_ops, xsrc, "xive.end",
                          (1ull << (xsrc->esb_shift + 1)) * xsrc->nr_ends);
}

static Property xive_end_source_properties[] = {
    DEFINE_PROP_UINT32("nr-ends", XiveENDSource, nr_ends, 0),
    DEFINE_PROP_UINT32("shift", XiveENDSource, esb_shift, XIVE_ESB_64K),
    DEFINE_PROP_LINK("xive", XiveENDSource, xrtr, TYPE_XIVE_ROUTER,
                     XiveRouter *),
    DEFINE_PROP_END_OF_LIST(),
};

static void xive_end_source_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);

    dc->desc    = "XIVE END Source";
    dc->props   = xive_end_source_properties;
    dc->realize = xive_end_source_realize;
    /*
     * Reason: part of XIVE interrupt controller, needs to be wired up,
     * e.g. by spapr_xive_instance_init().
     */
    dc->user_creatable = false;
}

static const TypeInfo xive_end_source_info = {
    .name          = TYPE_XIVE_END_SOURCE,
    .parent        = TYPE_DEVICE,
    .instance_size = sizeof(XiveENDSource),
    .class_init    = xive_end_source_class_init,
};

/*
 * XIVE Notifier
 */
static const TypeInfo xive_notifier_info = {
    .name = TYPE_XIVE_NOTIFIER,
    .parent = TYPE_INTERFACE,
    .class_size = sizeof(XiveNotifierClass),
};

/*
 * XIVE Presenter
 */
static const TypeInfo xive_presenter_info = {
    .name = TYPE_XIVE_PRESENTER,
    .parent = TYPE_INTERFACE,
    .class_size = sizeof(XivePresenterClass),
};

/*
 * XIVE Fabric
 */
static const TypeInfo xive_fabric_info = {
    .name = TYPE_XIVE_FABRIC,
    .parent = TYPE_INTERFACE,
    .class_size = sizeof(XiveFabricClass),
};

static void xive_register_types(void)
{
    type_register_static(&xive_fabric_info);
    type_register_static(&xive_source_info);
    type_register_static(&xive_notifier_info);
    type_register_static(&xive_presenter_info);
    type_register_static(&xive_router_info);
    type_register_static(&xive_end_source_info);
    type_register_static(&xive_tctx_info);
}

type_init(xive_register_types)