summaryrefslogtreecommitdiffstats
path: root/target-s390x/kvm.c
blob: c3be180de24898cd5cfdbc85a9298f91275f49f4 (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
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
/*
 * QEMU S390x KVM implementation
 *
 * Copyright (c) 2009 Alexander Graf <agraf@suse.de>
 * Copyright IBM Corp. 2012
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * Contributions after 2012-10-29 are licensed under the terms of the
 * GNU GPL, version 2 or (at your option) any later version.
 *
 * You should have received a copy of the GNU (Lesser) General Public
 * License along with this library; if not, see <http://www.gnu.org/licenses/>.
 */

#include <sys/types.h>
#include <sys/ioctl.h>
#include <sys/mman.h>

#include <linux/kvm.h>
#include <asm/ptrace.h>

#include "qemu-common.h"
#include "qemu/error-report.h"
#include "qemu/timer.h"
#include "sysemu/sysemu.h"
#include "sysemu/kvm.h"
#include "hw/hw.h"
#include "cpu.h"
#include "sysemu/device_tree.h"
#include "qapi/qmp/qjson.h"
#include "exec/gdbstub.h"
#include "exec/address-spaces.h"
#include "trace.h"
#include "qapi-event.h"
#include "hw/s390x/s390-pci-inst.h"
#include "hw/s390x/s390-pci-bus.h"
#include "hw/s390x/ipl.h"
#include "hw/s390x/ebcdic.h"
#include "exec/memattrs.h"

/* #define DEBUG_KVM */

#ifdef DEBUG_KVM
#define DPRINTF(fmt, ...) \
    do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...) \
    do { } while (0)
#endif

#define kvm_vm_check_mem_attr(s, attr) \
    kvm_vm_check_attr(s, KVM_S390_VM_MEM_CTRL, attr)

#define IPA0_DIAG                       0x8300
#define IPA0_SIGP                       0xae00
#define IPA0_B2                         0xb200
#define IPA0_B9                         0xb900
#define IPA0_EB                         0xeb00
#define IPA0_E3                         0xe300

#define PRIV_B2_SCLP_CALL               0x20
#define PRIV_B2_CSCH                    0x30
#define PRIV_B2_HSCH                    0x31
#define PRIV_B2_MSCH                    0x32
#define PRIV_B2_SSCH                    0x33
#define PRIV_B2_STSCH                   0x34
#define PRIV_B2_TSCH                    0x35
#define PRIV_B2_TPI                     0x36
#define PRIV_B2_SAL                     0x37
#define PRIV_B2_RSCH                    0x38
#define PRIV_B2_STCRW                   0x39
#define PRIV_B2_STCPS                   0x3a
#define PRIV_B2_RCHP                    0x3b
#define PRIV_B2_SCHM                    0x3c
#define PRIV_B2_CHSC                    0x5f
#define PRIV_B2_SIGA                    0x74
#define PRIV_B2_XSCH                    0x76

#define PRIV_EB_SQBS                    0x8a
#define PRIV_EB_PCISTB                  0xd0
#define PRIV_EB_SIC                     0xd1

#define PRIV_B9_EQBS                    0x9c
#define PRIV_B9_CLP                     0xa0
#define PRIV_B9_PCISTG                  0xd0
#define PRIV_B9_PCILG                   0xd2
#define PRIV_B9_RPCIT                   0xd3

#define PRIV_E3_MPCIFC                  0xd0
#define PRIV_E3_STPCIFC                 0xd4

#define DIAG_TIMEREVENT                 0x288
#define DIAG_IPL                        0x308
#define DIAG_KVM_HYPERCALL              0x500
#define DIAG_KVM_BREAKPOINT             0x501

#define ICPT_INSTRUCTION                0x04
#define ICPT_PROGRAM                    0x08
#define ICPT_EXT_INT                    0x14
#define ICPT_WAITPSW                    0x1c
#define ICPT_SOFT_INTERCEPT             0x24
#define ICPT_CPU_STOP                   0x28
#define ICPT_IO                         0x40

#define NR_LOCAL_IRQS 32
/*
 * Needs to be big enough to contain max_cpus emergency signals
 * and in addition NR_LOCAL_IRQS interrupts
 */
#define VCPU_IRQ_BUF_SIZE (sizeof(struct kvm_s390_irq) * \
                           (max_cpus + NR_LOCAL_IRQS))

static CPUWatchpoint hw_watchpoint;
/*
 * We don't use a list because this structure is also used to transmit the
 * hardware breakpoints to the kernel.
 */
static struct kvm_hw_breakpoint *hw_breakpoints;
static int nb_hw_breakpoints;

const KVMCapabilityInfo kvm_arch_required_capabilities[] = {
    KVM_CAP_LAST_INFO
};

static int cap_sync_regs;
static int cap_async_pf;
static int cap_mem_op;
static int cap_s390_irq;

static void *legacy_s390_alloc(size_t size, uint64_t *align);

static int kvm_s390_query_mem_limit(KVMState *s, uint64_t *memory_limit)
{
    struct kvm_device_attr attr = {
        .group = KVM_S390_VM_MEM_CTRL,
        .attr = KVM_S390_VM_MEM_LIMIT_SIZE,
        .addr = (uint64_t) memory_limit,
    };

    return kvm_vm_ioctl(s, KVM_GET_DEVICE_ATTR, &attr);
}

int kvm_s390_set_mem_limit(KVMState *s, uint64_t new_limit, uint64_t *hw_limit)
{
    int rc;

    struct kvm_device_attr attr = {
        .group = KVM_S390_VM_MEM_CTRL,
        .attr = KVM_S390_VM_MEM_LIMIT_SIZE,
        .addr = (uint64_t) &new_limit,
    };

    if (!kvm_vm_check_mem_attr(s, KVM_S390_VM_MEM_LIMIT_SIZE)) {
        return 0;
    }

    rc = kvm_s390_query_mem_limit(s, hw_limit);
    if (rc) {
        return rc;
    } else if (*hw_limit < new_limit) {
        return -E2BIG;
    }

    return kvm_vm_ioctl(s, KVM_SET_DEVICE_ATTR, &attr);
}

void kvm_s390_cmma_reset(void)
{
    int rc;
    struct kvm_device_attr attr = {
        .group = KVM_S390_VM_MEM_CTRL,
        .attr = KVM_S390_VM_MEM_CLR_CMMA,
    };

    rc = kvm_vm_ioctl(kvm_state, KVM_SET_DEVICE_ATTR, &attr);
    trace_kvm_clear_cmma(rc);
}

static void kvm_s390_enable_cmma(KVMState *s)
{
    int rc;
    struct kvm_device_attr attr = {
        .group = KVM_S390_VM_MEM_CTRL,
        .attr = KVM_S390_VM_MEM_ENABLE_CMMA,
    };

    if (!kvm_vm_check_mem_attr(s, KVM_S390_VM_MEM_ENABLE_CMMA) ||
        !kvm_vm_check_mem_attr(s, KVM_S390_VM_MEM_CLR_CMMA)) {
        return;
    }

    rc = kvm_vm_ioctl(s, KVM_SET_DEVICE_ATTR, &attr);
    trace_kvm_enable_cmma(rc);
}

static void kvm_s390_set_attr(uint64_t attr)
{
    struct kvm_device_attr attribute = {
        .group = KVM_S390_VM_CRYPTO,
        .attr  = attr,
    };

    int ret = kvm_vm_ioctl(kvm_state, KVM_SET_DEVICE_ATTR, &attribute);

    if (ret) {
        error_report("Failed to set crypto device attribute %lu: %s",
                     attr, strerror(-ret));
    }
}

static void kvm_s390_init_aes_kw(void)
{
    uint64_t attr = KVM_S390_VM_CRYPTO_DISABLE_AES_KW;

    if (object_property_get_bool(OBJECT(qdev_get_machine()), "aes-key-wrap",
                                 NULL)) {
            attr = KVM_S390_VM_CRYPTO_ENABLE_AES_KW;
    }

    if (kvm_vm_check_attr(kvm_state, KVM_S390_VM_CRYPTO, attr)) {
            kvm_s390_set_attr(attr);
    }
}

static void kvm_s390_init_dea_kw(void)
{
    uint64_t attr = KVM_S390_VM_CRYPTO_DISABLE_DEA_KW;

    if (object_property_get_bool(OBJECT(qdev_get_machine()), "dea-key-wrap",
                                 NULL)) {
            attr = KVM_S390_VM_CRYPTO_ENABLE_DEA_KW;
    }

    if (kvm_vm_check_attr(kvm_state, KVM_S390_VM_CRYPTO, attr)) {
            kvm_s390_set_attr(attr);
    }
}

void kvm_s390_crypto_reset(void)
{
    kvm_s390_init_aes_kw();
    kvm_s390_init_dea_kw();
}

int kvm_arch_init(MachineState *ms, KVMState *s)
{
    cap_sync_regs = kvm_check_extension(s, KVM_CAP_SYNC_REGS);
    cap_async_pf = kvm_check_extension(s, KVM_CAP_ASYNC_PF);
    cap_mem_op = kvm_check_extension(s, KVM_CAP_S390_MEM_OP);
    cap_s390_irq = kvm_check_extension(s, KVM_CAP_S390_INJECT_IRQ);

    kvm_s390_enable_cmma(s);

    if (!kvm_check_extension(s, KVM_CAP_S390_GMAP)
        || !kvm_check_extension(s, KVM_CAP_S390_COW)) {
        phys_mem_set_alloc(legacy_s390_alloc);
    }

    kvm_vm_enable_cap(s, KVM_CAP_S390_USER_SIGP, 0);
    kvm_vm_enable_cap(s, KVM_CAP_S390_VECTOR_REGISTERS, 0);
    kvm_vm_enable_cap(s, KVM_CAP_S390_USER_STSI, 0);

    return 0;
}

unsigned long kvm_arch_vcpu_id(CPUState *cpu)
{
    return cpu->cpu_index;
}

int kvm_arch_init_vcpu(CPUState *cs)
{
    S390CPU *cpu = S390_CPU(cs);
    kvm_s390_set_cpu_state(cpu, cpu->env.cpu_state);
    cpu->irqstate = g_malloc0(VCPU_IRQ_BUF_SIZE);
    return 0;
}

void kvm_s390_reset_vcpu(S390CPU *cpu)
{
    CPUState *cs = CPU(cpu);

    /* The initial reset call is needed here to reset in-kernel
     * vcpu data that we can't access directly from QEMU
     * (i.e. with older kernels which don't support sync_regs/ONE_REG).
     * Before this ioctl cpu_synchronize_state() is called in common kvm
     * code (kvm-all) */
    if (kvm_vcpu_ioctl(cs, KVM_S390_INITIAL_RESET, NULL)) {
        error_report("Initial CPU reset failed on CPU %i", cs->cpu_index);
    }
}

static int can_sync_regs(CPUState *cs, int regs)
{
    return cap_sync_regs && (cs->kvm_run->kvm_valid_regs & regs) == regs;
}

int kvm_arch_put_registers(CPUState *cs, int level)
{
    S390CPU *cpu = S390_CPU(cs);
    CPUS390XState *env = &cpu->env;
    struct kvm_sregs sregs;
    struct kvm_regs regs;
    struct kvm_fpu fpu = {};
    int r;
    int i;

    /* always save the PSW  and the GPRS*/
    cs->kvm_run->psw_addr = env->psw.addr;
    cs->kvm_run->psw_mask = env->psw.mask;

    if (can_sync_regs(cs, KVM_SYNC_GPRS)) {
        for (i = 0; i < 16; i++) {
            cs->kvm_run->s.regs.gprs[i] = env->regs[i];
            cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_GPRS;
        }
    } else {
        for (i = 0; i < 16; i++) {
            regs.gprs[i] = env->regs[i];
        }
        r = kvm_vcpu_ioctl(cs, KVM_SET_REGS, &regs);
        if (r < 0) {
            return r;
        }
    }

    if (can_sync_regs(cs, KVM_SYNC_VRS)) {
        for (i = 0; i < 32; i++) {
            cs->kvm_run->s.regs.vrs[i][0] = env->vregs[i][0].ll;
            cs->kvm_run->s.regs.vrs[i][1] = env->vregs[i][1].ll;
        }
        cs->kvm_run->s.regs.fpc = env->fpc;
        cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_VRS;
    } else {
        /* Floating point */
        for (i = 0; i < 16; i++) {
            fpu.fprs[i] = get_freg(env, i)->ll;
        }
        fpu.fpc = env->fpc;

        r = kvm_vcpu_ioctl(cs, KVM_SET_FPU, &fpu);
        if (r < 0) {
            return r;
        }
    }

    /* Do we need to save more than that? */
    if (level == KVM_PUT_RUNTIME_STATE) {
        return 0;
    }

    if (can_sync_regs(cs, KVM_SYNC_ARCH0)) {
        cs->kvm_run->s.regs.cputm = env->cputm;
        cs->kvm_run->s.regs.ckc = env->ckc;
        cs->kvm_run->s.regs.todpr = env->todpr;
        cs->kvm_run->s.regs.gbea = env->gbea;
        cs->kvm_run->s.regs.pp = env->pp;
        cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_ARCH0;
    } else {
        /*
         * These ONE_REGS are not protected by a capability. As they are only
         * necessary for migration we just trace a possible error, but don't
         * return with an error return code.
         */
        kvm_set_one_reg(cs, KVM_REG_S390_CPU_TIMER, &env->cputm);
        kvm_set_one_reg(cs, KVM_REG_S390_CLOCK_COMP, &env->ckc);
        kvm_set_one_reg(cs, KVM_REG_S390_TODPR, &env->todpr);
        kvm_set_one_reg(cs, KVM_REG_S390_GBEA, &env->gbea);
        kvm_set_one_reg(cs, KVM_REG_S390_PP, &env->pp);
    }

    /* pfault parameters */
    if (can_sync_regs(cs, KVM_SYNC_PFAULT)) {
        cs->kvm_run->s.regs.pft = env->pfault_token;
        cs->kvm_run->s.regs.pfs = env->pfault_select;
        cs->kvm_run->s.regs.pfc = env->pfault_compare;
        cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_PFAULT;
    } else if (cap_async_pf) {
        r = kvm_set_one_reg(cs, KVM_REG_S390_PFTOKEN, &env->pfault_token);
        if (r < 0) {
            return r;
        }
        r = kvm_set_one_reg(cs, KVM_REG_S390_PFCOMPARE, &env->pfault_compare);
        if (r < 0) {
            return r;
        }
        r = kvm_set_one_reg(cs, KVM_REG_S390_PFSELECT, &env->pfault_select);
        if (r < 0) {
            return r;
        }
    }

    /* access registers and control registers*/
    if (can_sync_regs(cs, KVM_SYNC_ACRS | KVM_SYNC_CRS)) {
        for (i = 0; i < 16; i++) {
            cs->kvm_run->s.regs.acrs[i] = env->aregs[i];
            cs->kvm_run->s.regs.crs[i] = env->cregs[i];
        }
        cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_ACRS;
        cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_CRS;
    } else {
        for (i = 0; i < 16; i++) {
            sregs.acrs[i] = env->aregs[i];
            sregs.crs[i] = env->cregs[i];
        }
        r = kvm_vcpu_ioctl(cs, KVM_SET_SREGS, &sregs);
        if (r < 0) {
            return r;
        }
    }

    /* Finally the prefix */
    if (can_sync_regs(cs, KVM_SYNC_PREFIX)) {
        cs->kvm_run->s.regs.prefix = env->psa;
        cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_PREFIX;
    } else {
        /* prefix is only supported via sync regs */
    }
    return 0;
}

int kvm_arch_get_registers(CPUState *cs)
{
    S390CPU *cpu = S390_CPU(cs);
    CPUS390XState *env = &cpu->env;
    struct kvm_sregs sregs;
    struct kvm_regs regs;
    struct kvm_fpu fpu;
    int i, r;

    /* get the PSW */
    env->psw.addr = cs->kvm_run->psw_addr;
    env->psw.mask = cs->kvm_run->psw_mask;

    /* the GPRS */
    if (can_sync_regs(cs, KVM_SYNC_GPRS)) {
        for (i = 0; i < 16; i++) {
            env->regs[i] = cs->kvm_run->s.regs.gprs[i];
        }
    } else {
        r = kvm_vcpu_ioctl(cs, KVM_GET_REGS, &regs);
        if (r < 0) {
            return r;
        }
         for (i = 0; i < 16; i++) {
            env->regs[i] = regs.gprs[i];
        }
    }

    /* The ACRS and CRS */
    if (can_sync_regs(cs, KVM_SYNC_ACRS | KVM_SYNC_CRS)) {
        for (i = 0; i < 16; i++) {
            env->aregs[i] = cs->kvm_run->s.regs.acrs[i];
            env->cregs[i] = cs->kvm_run->s.regs.crs[i];
        }
    } else {
        r = kvm_vcpu_ioctl(cs, KVM_GET_SREGS, &sregs);
        if (r < 0) {
            return r;
        }
         for (i = 0; i < 16; i++) {
            env->aregs[i] = sregs.acrs[i];
            env->cregs[i] = sregs.crs[i];
        }
    }

    /* Floating point and vector registers */
    if (can_sync_regs(cs, KVM_SYNC_VRS)) {
        for (i = 0; i < 32; i++) {
            env->vregs[i][0].ll = cs->kvm_run->s.regs.vrs[i][0];
            env->vregs[i][1].ll = cs->kvm_run->s.regs.vrs[i][1];
        }
        env->fpc = cs->kvm_run->s.regs.fpc;
    } else {
        r = kvm_vcpu_ioctl(cs, KVM_GET_FPU, &fpu);
        if (r < 0) {
            return r;
        }
        for (i = 0; i < 16; i++) {
            get_freg(env, i)->ll = fpu.fprs[i];
        }
        env->fpc = fpu.fpc;
    }

    /* The prefix */
    if (can_sync_regs(cs, KVM_SYNC_PREFIX)) {
        env->psa = cs->kvm_run->s.regs.prefix;
    }

    if (can_sync_regs(cs, KVM_SYNC_ARCH0)) {
        env->cputm = cs->kvm_run->s.regs.cputm;
        env->ckc = cs->kvm_run->s.regs.ckc;
        env->todpr = cs->kvm_run->s.regs.todpr;
        env->gbea = cs->kvm_run->s.regs.gbea;
        env->pp = cs->kvm_run->s.regs.pp;
    } else {
        /*
         * These ONE_REGS are not protected by a capability. As they are only
         * necessary for migration we just trace a possible error, but don't
         * return with an error return code.
         */
        kvm_get_one_reg(cs, KVM_REG_S390_CPU_TIMER, &env->cputm);
        kvm_get_one_reg(cs, KVM_REG_S390_CLOCK_COMP, &env->ckc);
        kvm_get_one_reg(cs, KVM_REG_S390_TODPR, &env->todpr);
        kvm_get_one_reg(cs, KVM_REG_S390_GBEA, &env->gbea);
        kvm_get_one_reg(cs, KVM_REG_S390_PP, &env->pp);
    }

    /* pfault parameters */
    if (can_sync_regs(cs, KVM_SYNC_PFAULT)) {
        env->pfault_token = cs->kvm_run->s.regs.pft;
        env->pfault_select = cs->kvm_run->s.regs.pfs;
        env->pfault_compare = cs->kvm_run->s.regs.pfc;
    } else if (cap_async_pf) {
        r = kvm_get_one_reg(cs, KVM_REG_S390_PFTOKEN, &env->pfault_token);
        if (r < 0) {
            return r;
        }
        r = kvm_get_one_reg(cs, KVM_REG_S390_PFCOMPARE, &env->pfault_compare);
        if (r < 0) {
            return r;
        }
        r = kvm_get_one_reg(cs, KVM_REG_S390_PFSELECT, &env->pfault_select);
        if (r < 0) {
            return r;
        }
    }

    return 0;
}

int kvm_s390_get_clock(uint8_t *tod_high, uint64_t *tod_low)
{
    int r;
    struct kvm_device_attr attr = {
        .group = KVM_S390_VM_TOD,
        .attr = KVM_S390_VM_TOD_LOW,
        .addr = (uint64_t)tod_low,
    };

    r = kvm_vm_ioctl(kvm_state, KVM_GET_DEVICE_ATTR, &attr);
    if (r) {
        return r;
    }

    attr.attr = KVM_S390_VM_TOD_HIGH;
    attr.addr = (uint64_t)tod_high;
    return kvm_vm_ioctl(kvm_state, KVM_GET_DEVICE_ATTR, &attr);
}

int kvm_s390_set_clock(uint8_t *tod_high, uint64_t *tod_low)
{
    int r;

    struct kvm_device_attr attr = {
        .group = KVM_S390_VM_TOD,
        .attr = KVM_S390_VM_TOD_LOW,
        .addr = (uint64_t)tod_low,
    };

    r = kvm_vm_ioctl(kvm_state, KVM_SET_DEVICE_ATTR, &attr);
    if (r) {
        return r;
    }

    attr.attr = KVM_S390_VM_TOD_HIGH;
    attr.addr = (uint64_t)tod_high;
    return kvm_vm_ioctl(kvm_state, KVM_SET_DEVICE_ATTR, &attr);
}

/**
 * kvm_s390_mem_op:
 * @addr:      the logical start address in guest memory
 * @ar:        the access register number
 * @hostbuf:   buffer in host memory. NULL = do only checks w/o copying
 * @len:       length that should be transferred
 * @is_write:  true = write, false = read
 * Returns:    0 on success, non-zero if an exception or error occurred
 *
 * Use KVM ioctl to read/write from/to guest memory. An access exception
 * is injected into the vCPU in case of translation errors.
 */
int kvm_s390_mem_op(S390CPU *cpu, vaddr addr, uint8_t ar, void *hostbuf,
                    int len, bool is_write)
{
    struct kvm_s390_mem_op mem_op = {
        .gaddr = addr,
        .flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION,
        .size = len,
        .op = is_write ? KVM_S390_MEMOP_LOGICAL_WRITE
                       : KVM_S390_MEMOP_LOGICAL_READ,
        .buf = (uint64_t)hostbuf,
        .ar = ar,
    };
    int ret;

    if (!cap_mem_op) {
        return -ENOSYS;
    }
    if (!hostbuf) {
        mem_op.flags |= KVM_S390_MEMOP_F_CHECK_ONLY;
    }

    ret = kvm_vcpu_ioctl(CPU(cpu), KVM_S390_MEM_OP, &mem_op);
    if (ret < 0) {
        error_printf("KVM_S390_MEM_OP failed: %s\n", strerror(-ret));
    }
    return ret;
}

/*
 * Legacy layout for s390:
 * Older S390 KVM requires the topmost vma of the RAM to be
 * smaller than an system defined value, which is at least 256GB.
 * Larger systems have larger values. We put the guest between
 * the end of data segment (system break) and this value. We
 * use 32GB as a base to have enough room for the system break
 * to grow. We also have to use MAP parameters that avoid
 * read-only mapping of guest pages.
 */
static void *legacy_s390_alloc(size_t size, uint64_t *align)
{
    void *mem;

    mem = mmap((void *) 0x800000000ULL, size,
               PROT_EXEC|PROT_READ|PROT_WRITE,
               MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
    return mem == MAP_FAILED ? NULL : mem;
}

/* DIAG 501 is used for sw breakpoints */
static const uint8_t diag_501[] = {0x83, 0x24, 0x05, 0x01};

int kvm_arch_insert_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp)
{

    if (cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)&bp->saved_insn,
                            sizeof(diag_501), 0) ||
        cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)diag_501,
                            sizeof(diag_501), 1)) {
        return -EINVAL;
    }
    return 0;
}

int kvm_arch_remove_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp)
{
    uint8_t t[sizeof(diag_501)];

    if (cpu_memory_rw_debug(cs, bp->pc, t, sizeof(diag_501), 0)) {
        return -EINVAL;
    } else if (memcmp(t, diag_501, sizeof(diag_501))) {
        return -EINVAL;
    } else if (cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)&bp->saved_insn,
                                   sizeof(diag_501), 1)) {
        return -EINVAL;
    }

    return 0;
}

static struct kvm_hw_breakpoint *find_hw_breakpoint(target_ulong addr,
                                                    int len, int type)
{
    int n;

    for (n = 0; n < nb_hw_breakpoints; n++) {
        if (hw_breakpoints[n].addr == addr && hw_breakpoints[n].type == type &&
            (hw_breakpoints[n].len == len || len == -1)) {
            return &hw_breakpoints[n];
        }
    }

    return NULL;
}

static int insert_hw_breakpoint(target_ulong addr, int len, int type)
{
    int size;

    if (find_hw_breakpoint(addr, len, type)) {
        return -EEXIST;
    }

    size = (nb_hw_breakpoints + 1) * sizeof(struct kvm_hw_breakpoint);

    if (!hw_breakpoints) {
        nb_hw_breakpoints = 0;
        hw_breakpoints = (struct kvm_hw_breakpoint *)g_try_malloc(size);
    } else {
        hw_breakpoints =
            (struct kvm_hw_breakpoint *)g_try_realloc(hw_breakpoints, size);
    }

    if (!hw_breakpoints) {
        nb_hw_breakpoints = 0;
        return -ENOMEM;
    }

    hw_breakpoints[nb_hw_breakpoints].addr = addr;
    hw_breakpoints[nb_hw_breakpoints].len = len;
    hw_breakpoints[nb_hw_breakpoints].type = type;

    nb_hw_breakpoints++;

    return 0;
}

int kvm_arch_insert_hw_breakpoint(target_ulong addr,
                                  target_ulong len, int type)
{
    switch (type) {
    case GDB_BREAKPOINT_HW:
        type = KVM_HW_BP;
        break;
    case GDB_WATCHPOINT_WRITE:
        if (len < 1) {
            return -EINVAL;
        }
        type = KVM_HW_WP_WRITE;
        break;
    default:
        return -ENOSYS;
    }
    return insert_hw_breakpoint(addr, len, type);
}

int kvm_arch_remove_hw_breakpoint(target_ulong addr,
                                  target_ulong len, int type)
{
    int size;
    struct kvm_hw_breakpoint *bp = find_hw_breakpoint(addr, len, type);

    if (bp == NULL) {
        return -ENOENT;
    }

    nb_hw_breakpoints--;
    if (nb_hw_breakpoints > 0) {
        /*
         * In order to trim the array, move the last element to the position to
         * be removed - if necessary.
         */
        if (bp != &hw_breakpoints[nb_hw_breakpoints]) {
            *bp = hw_breakpoints[nb_hw_breakpoints];
        }
        size = nb_hw_breakpoints * sizeof(struct kvm_hw_breakpoint);
        hw_breakpoints =
             (struct kvm_hw_breakpoint *)g_realloc(hw_breakpoints, size);
    } else {
        g_free(hw_breakpoints);
        hw_breakpoints = NULL;
    }

    return 0;
}

void kvm_arch_remove_all_hw_breakpoints(void)
{
    nb_hw_breakpoints = 0;
    g_free(hw_breakpoints);
    hw_breakpoints = NULL;
}

void kvm_arch_update_guest_debug(CPUState *cpu, struct kvm_guest_debug *dbg)
{
    int i;

    if (nb_hw_breakpoints > 0) {
        dbg->arch.nr_hw_bp = nb_hw_breakpoints;
        dbg->arch.hw_bp = hw_breakpoints;

        for (i = 0; i < nb_hw_breakpoints; ++i) {
            hw_breakpoints[i].phys_addr = s390_cpu_get_phys_addr_debug(cpu,
                                                       hw_breakpoints[i].addr);
        }
        dbg->control |= KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP;
    } else {
        dbg->arch.nr_hw_bp = 0;
        dbg->arch.hw_bp = NULL;
    }
}

void kvm_arch_pre_run(CPUState *cpu, struct kvm_run *run)
{
}

MemTxAttrs kvm_arch_post_run(CPUState *cs, struct kvm_run *run)
{
    return MEMTXATTRS_UNSPECIFIED;
}

int kvm_arch_process_async_events(CPUState *cs)
{
    return cs->halted;
}

static int s390_kvm_irq_to_interrupt(struct kvm_s390_irq *irq,
                                     struct kvm_s390_interrupt *interrupt)
{
    int r = 0;

    interrupt->type = irq->type;
    switch (irq->type) {
    case KVM_S390_INT_VIRTIO:
        interrupt->parm = irq->u.ext.ext_params;
        /* fall through */
    case KVM_S390_INT_PFAULT_INIT:
    case KVM_S390_INT_PFAULT_DONE:
        interrupt->parm64 = irq->u.ext.ext_params2;
        break;
    case KVM_S390_PROGRAM_INT:
        interrupt->parm = irq->u.pgm.code;
        break;
    case KVM_S390_SIGP_SET_PREFIX:
        interrupt->parm = irq->u.prefix.address;
        break;
    case KVM_S390_INT_SERVICE:
        interrupt->parm = irq->u.ext.ext_params;
        break;
    case KVM_S390_MCHK:
        interrupt->parm = irq->u.mchk.cr14;
        interrupt->parm64 = irq->u.mchk.mcic;
        break;
    case KVM_S390_INT_EXTERNAL_CALL:
        interrupt->parm = irq->u.extcall.code;
        break;
    case KVM_S390_INT_EMERGENCY:
        interrupt->parm = irq->u.emerg.code;
        break;
    case KVM_S390_SIGP_STOP:
    case KVM_S390_RESTART:
        break; /* These types have no parameters */
    case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
        interrupt->parm = irq->u.io.subchannel_id << 16;
        interrupt->parm |= irq->u.io.subchannel_nr;
        interrupt->parm64 = (uint64_t)irq->u.io.io_int_parm << 32;
        interrupt->parm64 |= irq->u.io.io_int_word;
        break;
    default:
        r = -EINVAL;
        break;
    }
    return r;
}

static void inject_vcpu_irq_legacy(CPUState *cs, struct kvm_s390_irq *irq)
{
    struct kvm_s390_interrupt kvmint = {};
    int r;

    r = s390_kvm_irq_to_interrupt(irq, &kvmint);
    if (r < 0) {
        fprintf(stderr, "%s called with bogus interrupt\n", __func__);
        exit(1);
    }

    r = kvm_vcpu_ioctl(cs, KVM_S390_INTERRUPT, &kvmint);
    if (r < 0) {
        fprintf(stderr, "KVM failed to inject interrupt\n");
        exit(1);
    }
}

void kvm_s390_vcpu_interrupt(S390CPU *cpu, struct kvm_s390_irq *irq)
{
    CPUState *cs = CPU(cpu);
    int r;

    if (cap_s390_irq) {
        r = kvm_vcpu_ioctl(cs, KVM_S390_IRQ, irq);
        if (!r) {
            return;
        }
        error_report("KVM failed to inject interrupt %llx", irq->type);
        exit(1);
    }

    inject_vcpu_irq_legacy(cs, irq);
}

static void __kvm_s390_floating_interrupt(struct kvm_s390_irq *irq)
{
    struct kvm_s390_interrupt kvmint = {};
    int r;

    r = s390_kvm_irq_to_interrupt(irq, &kvmint);
    if (r < 0) {
        fprintf(stderr, "%s called with bogus interrupt\n", __func__);
        exit(1);
    }

    r = kvm_vm_ioctl(kvm_state, KVM_S390_INTERRUPT, &kvmint);
    if (r < 0) {
        fprintf(stderr, "KVM failed to inject interrupt\n");
        exit(1);
    }
}

void kvm_s390_floating_interrupt(struct kvm_s390_irq *irq)
{
    static bool use_flic = true;
    int r;

    if (use_flic) {
        r = kvm_s390_inject_flic(irq);
        if (r == -ENOSYS) {
            use_flic = false;
        }
        if (!r) {
            return;
        }
    }
    __kvm_s390_floating_interrupt(irq);
}

void kvm_s390_virtio_irq(int config_change, uint64_t token)
{
    struct kvm_s390_irq irq = {
        .type = KVM_S390_INT_VIRTIO,
        .u.ext.ext_params = config_change,
        .u.ext.ext_params2 = token,
    };

    kvm_s390_floating_interrupt(&irq);
}

void kvm_s390_service_interrupt(uint32_t parm)
{
    struct kvm_s390_irq irq = {
        .type = KVM_S390_INT_SERVICE,
        .u.ext.ext_params = parm,
    };

    kvm_s390_floating_interrupt(&irq);
}

static void enter_pgmcheck(S390CPU *cpu, uint16_t code)
{
    struct kvm_s390_irq irq = {
        .type = KVM_S390_PROGRAM_INT,
        .u.pgm.code = code,
    };

    kvm_s390_vcpu_interrupt(cpu, &irq);
}

void kvm_s390_access_exception(S390CPU *cpu, uint16_t code, uint64_t te_code)
{
    struct kvm_s390_irq irq = {
        .type = KVM_S390_PROGRAM_INT,
        .u.pgm.code = code,
        .u.pgm.trans_exc_code = te_code,
        .u.pgm.exc_access_id = te_code & 3,
    };

    kvm_s390_vcpu_interrupt(cpu, &irq);
}

static int kvm_sclp_service_call(S390CPU *cpu, struct kvm_run *run,
                                 uint16_t ipbh0)
{
    CPUS390XState *env = &cpu->env;
    uint64_t sccb;
    uint32_t code;
    int r = 0;

    cpu_synchronize_state(CPU(cpu));
    sccb = env->regs[ipbh0 & 0xf];
    code = env->regs[(ipbh0 & 0xf0) >> 4];

    r = sclp_service_call(env, sccb, code);
    if (r < 0) {
        enter_pgmcheck(cpu, -r);
    } else {
        setcc(cpu, r);
    }

    return 0;
}

static int handle_b2(S390CPU *cpu, struct kvm_run *run, uint8_t ipa1)
{
    CPUS390XState *env = &cpu->env;
    int rc = 0;
    uint16_t ipbh0 = (run->s390_sieic.ipb & 0xffff0000) >> 16;

    cpu_synchronize_state(CPU(cpu));

    switch (ipa1) {
    case PRIV_B2_XSCH:
        ioinst_handle_xsch(cpu, env->regs[1]);
        break;
    case PRIV_B2_CSCH:
        ioinst_handle_csch(cpu, env->regs[1]);
        break;
    case PRIV_B2_HSCH:
        ioinst_handle_hsch(cpu, env->regs[1]);
        break;
    case PRIV_B2_MSCH:
        ioinst_handle_msch(cpu, env->regs[1], run->s390_sieic.ipb);
        break;
    case PRIV_B2_SSCH:
        ioinst_handle_ssch(cpu, env->regs[1], run->s390_sieic.ipb);
        break;
    case PRIV_B2_STCRW:
        ioinst_handle_stcrw(cpu, run->s390_sieic.ipb);
        break;
    case PRIV_B2_STSCH:
        ioinst_handle_stsch(cpu, env->regs[1], run->s390_sieic.ipb);
        break;
    case PRIV_B2_TSCH:
        /* We should only get tsch via KVM_EXIT_S390_TSCH. */
        fprintf(stderr, "Spurious tsch intercept\n");
        break;
    case PRIV_B2_CHSC:
        ioinst_handle_chsc(cpu, run->s390_sieic.ipb);
        break;
    case PRIV_B2_TPI:
        /* This should have been handled by kvm already. */
        fprintf(stderr, "Spurious tpi intercept\n");
        break;
    case PRIV_B2_SCHM:
        ioinst_handle_schm(cpu, env->regs[1], env->regs[2],
                           run->s390_sieic.ipb);
        break;
    case PRIV_B2_RSCH:
        ioinst_handle_rsch(cpu, env->regs[1]);
        break;
    case PRIV_B2_RCHP:
        ioinst_handle_rchp(cpu, env->regs[1]);
        break;
    case PRIV_B2_STCPS:
        /* We do not provide this instruction, it is suppressed. */
        break;
    case PRIV_B2_SAL:
        ioinst_handle_sal(cpu, env->regs[1]);
        break;
    case PRIV_B2_SIGA:
        /* Not provided, set CC = 3 for subchannel not operational */
        setcc(cpu, 3);
        break;
    case PRIV_B2_SCLP_CALL:
        rc = kvm_sclp_service_call(cpu, run, ipbh0);
        break;
    default:
        rc = -1;
        DPRINTF("KVM: unhandled PRIV: 0xb2%x\n", ipa1);
        break;
    }

    return rc;
}

static uint64_t get_base_disp_rxy(S390CPU *cpu, struct kvm_run *run,
                                  uint8_t *ar)
{
    CPUS390XState *env = &cpu->env;
    uint32_t x2 = (run->s390_sieic.ipa & 0x000f);
    uint32_t base2 = run->s390_sieic.ipb >> 28;
    uint32_t disp2 = ((run->s390_sieic.ipb & 0x0fff0000) >> 16) +
                     ((run->s390_sieic.ipb & 0xff00) << 4);

    if (disp2 & 0x80000) {
        disp2 += 0xfff00000;
    }
    if (ar) {
        *ar = base2;
    }

    return (base2 ? env->regs[base2] : 0) +
           (x2 ? env->regs[x2] : 0) + (long)(int)disp2;
}

static uint64_t get_base_disp_rsy(S390CPU *cpu, struct kvm_run *run,
                                  uint8_t *ar)
{
    CPUS390XState *env = &cpu->env;
    uint32_t base2 = run->s390_sieic.ipb >> 28;
    uint32_t disp2 = ((run->s390_sieic.ipb & 0x0fff0000) >> 16) +
                     ((run->s390_sieic.ipb & 0xff00) << 4);

    if (disp2 & 0x80000) {
        disp2 += 0xfff00000;
    }
    if (ar) {
        *ar = base2;
    }

    return (base2 ? env->regs[base2] : 0) + (long)(int)disp2;
}

static int kvm_clp_service_call(S390CPU *cpu, struct kvm_run *run)
{
    uint8_t r2 = (run->s390_sieic.ipb & 0x000f0000) >> 16;

    return clp_service_call(cpu, r2);
}

static int kvm_pcilg_service_call(S390CPU *cpu, struct kvm_run *run)
{
    uint8_t r1 = (run->s390_sieic.ipb & 0x00f00000) >> 20;
    uint8_t r2 = (run->s390_sieic.ipb & 0x000f0000) >> 16;

    return pcilg_service_call(cpu, r1, r2);
}

static int kvm_pcistg_service_call(S390CPU *cpu, struct kvm_run *run)
{
    uint8_t r1 = (run->s390_sieic.ipb & 0x00f00000) >> 20;
    uint8_t r2 = (run->s390_sieic.ipb & 0x000f0000) >> 16;

    return pcistg_service_call(cpu, r1, r2);
}

static int kvm_stpcifc_service_call(S390CPU *cpu, struct kvm_run *run)
{
    uint8_t r1 = (run->s390_sieic.ipa & 0x00f0) >> 4;
    uint64_t fiba;
    uint8_t ar;

    cpu_synchronize_state(CPU(cpu));
    fiba = get_base_disp_rxy(cpu, run, &ar);

    return stpcifc_service_call(cpu, r1, fiba, ar);
}

static int kvm_sic_service_call(S390CPU *cpu, struct kvm_run *run)
{
    /* NOOP */
    return 0;
}

static int kvm_rpcit_service_call(S390CPU *cpu, struct kvm_run *run)
{
    uint8_t r1 = (run->s390_sieic.ipb & 0x00f00000) >> 20;
    uint8_t r2 = (run->s390_sieic.ipb & 0x000f0000) >> 16;

    return rpcit_service_call(cpu, r1, r2);
}

static int kvm_pcistb_service_call(S390CPU *cpu, struct kvm_run *run)
{
    uint8_t r1 = (run->s390_sieic.ipa & 0x00f0) >> 4;
    uint8_t r3 = run->s390_sieic.ipa & 0x000f;
    uint64_t gaddr;
    uint8_t ar;

    cpu_synchronize_state(CPU(cpu));
    gaddr = get_base_disp_rsy(cpu, run, &ar);

    return pcistb_service_call(cpu, r1, r3, gaddr, ar);
}

static int kvm_mpcifc_service_call(S390CPU *cpu, struct kvm_run *run)
{
    uint8_t r1 = (run->s390_sieic.ipa & 0x00f0) >> 4;
    uint64_t fiba;
    uint8_t ar;

    cpu_synchronize_state(CPU(cpu));
    fiba = get_base_disp_rxy(cpu, run, &ar);

    return mpcifc_service_call(cpu, r1, fiba, ar);
}

static int handle_b9(S390CPU *cpu, struct kvm_run *run, uint8_t ipa1)
{
    int r = 0;

    switch (ipa1) {
    case PRIV_B9_CLP:
        r = kvm_clp_service_call(cpu, run);
        break;
    case PRIV_B9_PCISTG:
        r = kvm_pcistg_service_call(cpu, run);
        break;
    case PRIV_B9_PCILG:
        r = kvm_pcilg_service_call(cpu, run);
        break;
    case PRIV_B9_RPCIT:
        r = kvm_rpcit_service_call(cpu, run);
        break;
    case PRIV_B9_EQBS:
        /* just inject exception */
        r = -1;
        break;
    default:
        r = -1;
        DPRINTF("KVM: unhandled PRIV: 0xb9%x\n", ipa1);
        break;
    }

    return r;
}

static int handle_eb(S390CPU *cpu, struct kvm_run *run, uint8_t ipbl)
{
    int r = 0;

    switch (ipbl) {
    case PRIV_EB_PCISTB:
        r = kvm_pcistb_service_call(cpu, run);
        break;
    case PRIV_EB_SIC:
        r = kvm_sic_service_call(cpu, run);
        break;
    case PRIV_EB_SQBS:
        /* just inject exception */
        r = -1;
        break;
    default:
        r = -1;
        DPRINTF("KVM: unhandled PRIV: 0xeb%x\n", ipbl);
        break;
    }

    return r;
}

static int handle_e3(S390CPU *cpu, struct kvm_run *run, uint8_t ipbl)
{
    int r = 0;

    switch (ipbl) {
    case PRIV_E3_MPCIFC:
        r = kvm_mpcifc_service_call(cpu, run);
        break;
    case PRIV_E3_STPCIFC:
        r = kvm_stpcifc_service_call(cpu, run);
        break;
    default:
        r = -1;
        DPRINTF("KVM: unhandled PRIV: 0xe3%x\n", ipbl);
        break;
    }

    return r;
}

static int handle_hypercall(S390CPU *cpu, struct kvm_run *run)
{
    CPUS390XState *env = &cpu->env;
    int ret;

    cpu_synchronize_state(CPU(cpu));
    ret = s390_virtio_hypercall(env);
    if (ret == -EINVAL) {
        enter_pgmcheck(cpu, PGM_SPECIFICATION);
        return 0;
    }

    return ret;
}

static void kvm_handle_diag_288(S390CPU *cpu, struct kvm_run *run)
{
    uint64_t r1, r3;
    int rc;

    cpu_synchronize_state(CPU(cpu));
    r1 = (run->s390_sieic.ipa & 0x00f0) >> 4;
    r3 = run->s390_sieic.ipa & 0x000f;
    rc = handle_diag_288(&cpu->env, r1, r3);
    if (rc) {
        enter_pgmcheck(cpu, PGM_SPECIFICATION);
    }
}

static void kvm_handle_diag_308(S390CPU *cpu, struct kvm_run *run)
{
    uint64_t r1, r3;

    cpu_synchronize_state(CPU(cpu));
    r1 = (run->s390_sieic.ipa & 0x00f0) >> 4;
    r3 = run->s390_sieic.ipa & 0x000f;
    handle_diag_308(&cpu->env, r1, r3);
}

static int handle_sw_breakpoint(S390CPU *cpu, struct kvm_run *run)
{
    CPUS390XState *env = &cpu->env;
    unsigned long pc;

    cpu_synchronize_state(CPU(cpu));

    pc = env->psw.addr - 4;
    if (kvm_find_sw_breakpoint(CPU(cpu), pc)) {
        env->psw.addr = pc;
        return EXCP_DEBUG;
    }

    return -ENOENT;
}

#define DIAG_KVM_CODE_MASK 0x000000000000ffff

static int handle_diag(S390CPU *cpu, struct kvm_run *run, uint32_t ipb)
{
    int r = 0;
    uint16_t func_code;

    /*
     * For any diagnose call we support, bits 48-63 of the resulting
     * address specify the function code; the remainder is ignored.
     */
    func_code = decode_basedisp_rs(&cpu->env, ipb, NULL) & DIAG_KVM_CODE_MASK;
    switch (func_code) {
    case DIAG_TIMEREVENT:
        kvm_handle_diag_288(cpu, run);
        break;
    case DIAG_IPL:
        kvm_handle_diag_308(cpu, run);
        break;
    case DIAG_KVM_HYPERCALL:
        r = handle_hypercall(cpu, run);
        break;
    case DIAG_KVM_BREAKPOINT:
        r = handle_sw_breakpoint(cpu, run);
        break;
    default:
        DPRINTF("KVM: unknown DIAG: 0x%x\n", func_code);
        enter_pgmcheck(cpu, PGM_SPECIFICATION);
        break;
    }

    return r;
}

typedef struct SigpInfo {
    S390CPU *cpu;
    uint64_t param;
    int cc;
    uint64_t *status_reg;
} SigpInfo;

static void set_sigp_status(SigpInfo *si, uint64_t status)
{
    *si->status_reg &= 0xffffffff00000000ULL;
    *si->status_reg |= status;
    si->cc = SIGP_CC_STATUS_STORED;
}

static void sigp_start(void *arg)
{
    SigpInfo *si = arg;

    if (s390_cpu_get_state(si->cpu) != CPU_STATE_STOPPED) {
        si->cc = SIGP_CC_ORDER_CODE_ACCEPTED;
        return;
    }

    s390_cpu_set_state(CPU_STATE_OPERATING, si->cpu);
    si->cc = SIGP_CC_ORDER_CODE_ACCEPTED;
}

static void sigp_stop(void *arg)
{
    SigpInfo *si = arg;
    struct kvm_s390_irq irq = {
        .type = KVM_S390_SIGP_STOP,
    };

    if (s390_cpu_get_state(si->cpu) != CPU_STATE_OPERATING) {
        si->cc = SIGP_CC_ORDER_CODE_ACCEPTED;
        return;
    }

    /* disabled wait - sleeping in user space */
    if (CPU(si->cpu)->halted) {
        s390_cpu_set_state(CPU_STATE_STOPPED, si->cpu);
    } else {
        /* execute the stop function */
        si->cpu->env.sigp_order = SIGP_STOP;
        kvm_s390_vcpu_interrupt(si->cpu, &irq);
    }
    si->cc = SIGP_CC_ORDER_CODE_ACCEPTED;
}

#define ADTL_SAVE_AREA_SIZE 1024
static int kvm_s390_store_adtl_status(S390CPU *cpu, hwaddr addr)
{
    void *mem;
    hwaddr len = ADTL_SAVE_AREA_SIZE;

    mem = cpu_physical_memory_map(addr, &len, 1);
    if (!mem) {
        return -EFAULT;
    }
    if (len != ADTL_SAVE_AREA_SIZE) {
        cpu_physical_memory_unmap(mem, len, 1, 0);
        return -EFAULT;
    }

    memcpy(mem, &cpu->env.vregs, 512);

    cpu_physical_memory_unmap(mem, len, 1, len);

    return 0;
}

#define KVM_S390_STORE_STATUS_DEF_ADDR offsetof(LowCore, floating_pt_save_area)
#define SAVE_AREA_SIZE 512
static int kvm_s390_store_status(S390CPU *cpu, hwaddr addr, bool store_arch)
{
    static const uint8_t ar_id = 1;
    uint64_t ckc = cpu->env.ckc >> 8;
    void *mem;
    int i;
    hwaddr len = SAVE_AREA_SIZE;

    mem = cpu_physical_memory_map(addr, &len, 1);
    if (!mem) {
        return -EFAULT;
    }
    if (len != SAVE_AREA_SIZE) {
        cpu_physical_memory_unmap(mem, len, 1, 0);
        return -EFAULT;
    }

    if (store_arch) {
        cpu_physical_memory_write(offsetof(LowCore, ar_access_id), &ar_id, 1);
    }
    for (i = 0; i < 16; ++i) {
        *((uint64 *)mem + i) = get_freg(&cpu->env, i)->ll;
    }
    memcpy(mem + 128, &cpu->env.regs, 128);
    memcpy(mem + 256, &cpu->env.psw, 16);
    memcpy(mem + 280, &cpu->env.psa, 4);
    memcpy(mem + 284, &cpu->env.fpc, 4);
    memcpy(mem + 292, &cpu->env.todpr, 4);
    memcpy(mem + 296, &cpu->env.cputm, 8);
    memcpy(mem + 304, &ckc, 8);
    memcpy(mem + 320, &cpu->env.aregs, 64);
    memcpy(mem + 384, &cpu->env.cregs, 128);

    cpu_physical_memory_unmap(mem, len, 1, len);

    return 0;
}

static void sigp_stop_and_store_status(void *arg)
{
    SigpInfo *si = arg;
    struct kvm_s390_irq irq = {
        .type = KVM_S390_SIGP_STOP,
    };

    /* disabled wait - sleeping in user space */
    if (s390_cpu_get_state(si->cpu) == CPU_STATE_OPERATING &&
        CPU(si->cpu)->halted) {
        s390_cpu_set_state(CPU_STATE_STOPPED, si->cpu);
    }

    switch (s390_cpu_get_state(si->cpu)) {
    case CPU_STATE_OPERATING:
        si->cpu->env.sigp_order = SIGP_STOP_STORE_STATUS;
        kvm_s390_vcpu_interrupt(si->cpu, &irq);
        /* store will be performed when handling the stop intercept */
        break;
    case CPU_STATE_STOPPED:
        /* already stopped, just store the status */
        cpu_synchronize_state(CPU(si->cpu));
        kvm_s390_store_status(si->cpu, KVM_S390_STORE_STATUS_DEF_ADDR, true);
        break;
    }
    si->cc = SIGP_CC_ORDER_CODE_ACCEPTED;
}

static void sigp_store_status_at_address(void *arg)
{
    SigpInfo *si = arg;
    uint32_t address = si->param & 0x7ffffe00u;

    /* cpu has to be stopped */
    if (s390_cpu_get_state(si->cpu) != CPU_STATE_STOPPED) {
        set_sigp_status(si, SIGP_STAT_INCORRECT_STATE);
        return;
    }

    cpu_synchronize_state(CPU(si->cpu));

    if (kvm_s390_store_status(si->cpu, address, false)) {
        set_sigp_status(si, SIGP_STAT_INVALID_PARAMETER);
        return;
    }
    si->cc = SIGP_CC_ORDER_CODE_ACCEPTED;
}

static void sigp_store_adtl_status(void *arg)
{
    SigpInfo *si = arg;

    if (!kvm_check_extension(kvm_state, KVM_CAP_S390_VECTOR_REGISTERS)) {
        set_sigp_status(si, SIGP_STAT_INVALID_ORDER);
        return;
    }

    /* cpu has to be stopped */
    if (s390_cpu_get_state(si->cpu) != CPU_STATE_STOPPED) {
        set_sigp_status(si, SIGP_STAT_INCORRECT_STATE);
        return;
    }

    /* parameter must be aligned to 1024-byte boundary */
    if (si->param & 0x3ff) {
        set_sigp_status(si, SIGP_STAT_INVALID_PARAMETER);
        return;
    }

    cpu_synchronize_state(CPU(si->cpu));

    if (kvm_s390_store_adtl_status(si->cpu, si->param)) {
        set_sigp_status(si, SIGP_STAT_INVALID_PARAMETER);
        return;
    }
    si->cc = SIGP_CC_ORDER_CODE_ACCEPTED;
}

static void sigp_restart(void *arg)
{
    SigpInfo *si = arg;
    struct kvm_s390_irq irq = {
        .type = KVM_S390_RESTART,
    };

    switch (s390_cpu_get_state(si->cpu)) {
    case CPU_STATE_STOPPED:
        /* the restart irq has to be delivered prior to any other pending irq */
        cpu_synchronize_state(CPU(si->cpu));
        do_restart_interrupt(&si->cpu->env);
        s390_cpu_set_state(CPU_STATE_OPERATING, si->cpu);
        break;
    case CPU_STATE_OPERATING:
        kvm_s390_vcpu_interrupt(si->cpu, &irq);
        break;
    }
    si->cc = SIGP_CC_ORDER_CODE_ACCEPTED;
}

int kvm_s390_cpu_restart(S390CPU *cpu)
{
    SigpInfo si = {
        .cpu = cpu,
    };

    run_on_cpu(CPU(cpu), sigp_restart, &si);
    DPRINTF("DONE: KVM cpu restart: %p\n", &cpu->env);
    return 0;
}

static void sigp_initial_cpu_reset(void *arg)
{
    SigpInfo *si = arg;
    CPUState *cs = CPU(si->cpu);
    S390CPUClass *scc = S390_CPU_GET_CLASS(si->cpu);

    cpu_synchronize_state(cs);
    scc->initial_cpu_reset(cs);
    cpu_synchronize_post_reset(cs);
    si->cc = SIGP_CC_ORDER_CODE_ACCEPTED;
}

static void sigp_cpu_reset(void *arg)
{
    SigpInfo *si = arg;
    CPUState *cs = CPU(si->cpu);
    S390CPUClass *scc = S390_CPU_GET_CLASS(si->cpu);

    cpu_synchronize_state(cs);
    scc->cpu_reset(cs);
    cpu_synchronize_post_reset(cs);
    si->cc = SIGP_CC_ORDER_CODE_ACCEPTED;
}

static void sigp_set_prefix(void *arg)
{
    SigpInfo *si = arg;
    uint32_t addr = si->param & 0x7fffe000u;

    cpu_synchronize_state(CPU(si->cpu));

    if (!address_space_access_valid(&address_space_memory, addr,
                                    sizeof(struct LowCore), false)) {
        set_sigp_status(si, SIGP_STAT_INVALID_PARAMETER);
        return;
    }

    /* cpu has to be stopped */
    if (s390_cpu_get_state(si->cpu) != CPU_STATE_STOPPED) {
        set_sigp_status(si, SIGP_STAT_INCORRECT_STATE);
        return;
    }

    si->cpu->env.psa = addr;
    cpu_synchronize_post_init(CPU(si->cpu));
    si->cc = SIGP_CC_ORDER_CODE_ACCEPTED;
}

static int handle_sigp_single_dst(S390CPU *dst_cpu, uint8_t order,
                                  uint64_t param, uint64_t *status_reg)
{
    SigpInfo si = {
        .cpu = dst_cpu,
        .param = param,
        .status_reg = status_reg,
    };

    /* cpu available? */
    if (dst_cpu == NULL) {
        return SIGP_CC_NOT_OPERATIONAL;
    }

    /* only resets can break pending orders */
    if (dst_cpu->env.sigp_order != 0 &&
        order != SIGP_CPU_RESET &&
        order != SIGP_INITIAL_CPU_RESET) {
        return SIGP_CC_BUSY;
    }

    switch (order) {
    case SIGP_START:
        run_on_cpu(CPU(dst_cpu), sigp_start, &si);
        break;
    case SIGP_STOP:
        run_on_cpu(CPU(dst_cpu), sigp_stop, &si);
        break;
    case SIGP_RESTART:
        run_on_cpu(CPU(dst_cpu), sigp_restart, &si);
        break;
    case SIGP_STOP_STORE_STATUS:
        run_on_cpu(CPU(dst_cpu), sigp_stop_and_store_status, &si);
        break;
    case SIGP_STORE_STATUS_ADDR:
        run_on_cpu(CPU(dst_cpu), sigp_store_status_at_address, &si);
        break;
    case SIGP_STORE_ADTL_STATUS:
        run_on_cpu(CPU(dst_cpu), sigp_store_adtl_status, &si);
        break;
    case SIGP_SET_PREFIX:
        run_on_cpu(CPU(dst_cpu), sigp_set_prefix, &si);
        break;
    case SIGP_INITIAL_CPU_RESET:
        run_on_cpu(CPU(dst_cpu), sigp_initial_cpu_reset, &si);
        break;
    case SIGP_CPU_RESET:
        run_on_cpu(CPU(dst_cpu), sigp_cpu_reset, &si);
        break;
    default:
        DPRINTF("KVM: unknown SIGP: 0x%x\n", order);
        set_sigp_status(&si, SIGP_STAT_INVALID_ORDER);
    }

    return si.cc;
}

static int sigp_set_architecture(S390CPU *cpu, uint32_t param,
                                 uint64_t *status_reg)
{
    CPUState *cur_cs;
    S390CPU *cur_cpu;

    /* due to the BQL, we are the only active cpu */
    CPU_FOREACH(cur_cs) {
        cur_cpu = S390_CPU(cur_cs);
        if (cur_cpu->env.sigp_order != 0) {
            return SIGP_CC_BUSY;
        }
        cpu_synchronize_state(cur_cs);
        /* all but the current one have to be stopped */
        if (cur_cpu != cpu &&
            s390_cpu_get_state(cur_cpu) != CPU_STATE_STOPPED) {
            *status_reg &= 0xffffffff00000000ULL;
            *status_reg |= SIGP_STAT_INCORRECT_STATE;
            return SIGP_CC_STATUS_STORED;
        }
    }

    switch (param & 0xff) {
    case SIGP_MODE_ESA_S390:
        /* not supported */
        return SIGP_CC_NOT_OPERATIONAL;
    case SIGP_MODE_Z_ARCH_TRANS_ALL_PSW:
    case SIGP_MODE_Z_ARCH_TRANS_CUR_PSW:
        CPU_FOREACH(cur_cs) {
            cur_cpu = S390_CPU(cur_cs);
            cur_cpu->env.pfault_token = -1UL;
        }
        break;
    default:
        *status_reg &= 0xffffffff00000000ULL;
        *status_reg |= SIGP_STAT_INVALID_PARAMETER;
        return SIGP_CC_STATUS_STORED;
    }

    return SIGP_CC_ORDER_CODE_ACCEPTED;
}

#define SIGP_ORDER_MASK 0x000000ff

static int handle_sigp(S390CPU *cpu, struct kvm_run *run, uint8_t ipa1)
{
    CPUS390XState *env = &cpu->env;
    const uint8_t r1 = ipa1 >> 4;
    const uint8_t r3 = ipa1 & 0x0f;
    int ret;
    uint8_t order;
    uint64_t *status_reg;
    uint64_t param;
    S390CPU *dst_cpu = NULL;

    cpu_synchronize_state(CPU(cpu));

    /* get order code */
    order = decode_basedisp_rs(env, run->s390_sieic.ipb, NULL)
        & SIGP_ORDER_MASK;
    status_reg = &env->regs[r1];
    param = (r1 % 2) ? env->regs[r1] : env->regs[r1 + 1];

    switch (order) {
    case SIGP_SET_ARCH:
        ret = sigp_set_architecture(cpu, param, status_reg);
        break;
    default:
        /* all other sigp orders target a single vcpu */
        dst_cpu = s390_cpu_addr2state(env->regs[r3]);
        ret = handle_sigp_single_dst(dst_cpu, order, param, status_reg);
    }

    trace_kvm_sigp_finished(order, CPU(cpu)->cpu_index,
                            dst_cpu ? CPU(dst_cpu)->cpu_index : -1, ret);

    if (ret >= 0) {
        setcc(cpu, ret);
        return 0;
    }

    return ret;
}

static int handle_instruction(S390CPU *cpu, struct kvm_run *run)
{
    unsigned int ipa0 = (run->s390_sieic.ipa & 0xff00);
    uint8_t ipa1 = run->s390_sieic.ipa & 0x00ff;
    int r = -1;

    DPRINTF("handle_instruction 0x%x 0x%x\n",
            run->s390_sieic.ipa, run->s390_sieic.ipb);
    switch (ipa0) {
    case IPA0_B2:
        r = handle_b2(cpu, run, ipa1);
        break;
    case IPA0_B9:
        r = handle_b9(cpu, run, ipa1);
        break;
    case IPA0_EB:
        r = handle_eb(cpu, run, run->s390_sieic.ipb & 0xff);
        break;
    case IPA0_E3:
        r = handle_e3(cpu, run, run->s390_sieic.ipb & 0xff);
        break;
    case IPA0_DIAG:
        r = handle_diag(cpu, run, run->s390_sieic.ipb);
        break;
    case IPA0_SIGP:
        r = handle_sigp(cpu, run, ipa1);
        break;
    }

    if (r < 0) {
        r = 0;
        enter_pgmcheck(cpu, 0x0001);
    }

    return r;
}

static bool is_special_wait_psw(CPUState *cs)
{
    /* signal quiesce */
    return cs->kvm_run->psw_addr == 0xfffUL;
}

static void unmanageable_intercept(S390CPU *cpu, const char *str, int pswoffset)
{
    CPUState *cs = CPU(cpu);

    error_report("Unmanageable %s! CPU%i new PSW: 0x%016lx:%016lx",
                 str, cs->cpu_index, ldq_phys(cs->as, cpu->env.psa + pswoffset),
                 ldq_phys(cs->as, cpu->env.psa + pswoffset + 8));
    s390_cpu_halt(cpu);
    qemu_system_guest_panicked();
}

static int handle_intercept(S390CPU *cpu)
{
    CPUState *cs = CPU(cpu);
    struct kvm_run *run = cs->kvm_run;
    int icpt_code = run->s390_sieic.icptcode;
    int r = 0;

    DPRINTF("intercept: 0x%x (at 0x%lx)\n", icpt_code,
            (long)cs->kvm_run->psw_addr);
    switch (icpt_code) {
        case ICPT_INSTRUCTION:
            r = handle_instruction(cpu, run);
            break;
        case ICPT_PROGRAM:
            unmanageable_intercept(cpu, "program interrupt",
                                   offsetof(LowCore, program_new_psw));
            r = EXCP_HALTED;
            break;
        case ICPT_EXT_INT:
            unmanageable_intercept(cpu, "external interrupt",
                                   offsetof(LowCore, external_new_psw));
            r = EXCP_HALTED;
            break;
        case ICPT_WAITPSW:
            /* disabled wait, since enabled wait is handled in kernel */
            cpu_synchronize_state(cs);
            if (s390_cpu_halt(cpu) == 0) {
                if (is_special_wait_psw(cs)) {
                    qemu_system_shutdown_request();
                } else {
                    qemu_system_guest_panicked();
                }
            }
            r = EXCP_HALTED;
            break;
        case ICPT_CPU_STOP:
            if (s390_cpu_set_state(CPU_STATE_STOPPED, cpu) == 0) {
                qemu_system_shutdown_request();
            }
            if (cpu->env.sigp_order == SIGP_STOP_STORE_STATUS) {
                kvm_s390_store_status(cpu, KVM_S390_STORE_STATUS_DEF_ADDR,
                                      true);
            }
            cpu->env.sigp_order = 0;
            r = EXCP_HALTED;
            break;
        case ICPT_SOFT_INTERCEPT:
            fprintf(stderr, "KVM unimplemented icpt SOFT\n");
            exit(1);
            break;
        case ICPT_IO:
            fprintf(stderr, "KVM unimplemented icpt IO\n");
            exit(1);
            break;
        default:
            fprintf(stderr, "Unknown intercept code: %d\n", icpt_code);
            exit(1);
            break;
    }

    return r;
}

static int handle_tsch(S390CPU *cpu)
{
    CPUState *cs = CPU(cpu);
    struct kvm_run *run = cs->kvm_run;
    int ret;

    cpu_synchronize_state(cs);

    ret = ioinst_handle_tsch(cpu, cpu->env.regs[1], run->s390_tsch.ipb);
    if (ret < 0) {
        /*
         * Failure.
         * If an I/O interrupt had been dequeued, we have to reinject it.
         */
        if (run->s390_tsch.dequeued) {
            kvm_s390_io_interrupt(run->s390_tsch.subchannel_id,
                                  run->s390_tsch.subchannel_nr,
                                  run->s390_tsch.io_int_parm,
                                  run->s390_tsch.io_int_word);
        }
        ret = 0;
    }
    return ret;
}

static void insert_stsi_3_2_2(S390CPU *cpu, __u64 addr, uint8_t ar)
{
    struct sysib_322 sysib;
    int del;

    if (s390_cpu_virt_mem_read(cpu, addr, ar, &sysib, sizeof(sysib))) {
        return;
    }
    /* Shift the stack of Extended Names to prepare for our own data */
    memmove(&sysib.ext_names[1], &sysib.ext_names[0],
            sizeof(sysib.ext_names[0]) * (sysib.count - 1));
    /* First virt level, that doesn't provide Ext Names delimits stack. It is
     * assumed it's not capable of managing Extended Names for lower levels.
     */
    for (del = 1; del < sysib.count; del++) {
        if (!sysib.vm[del].ext_name_encoding || !sysib.ext_names[del][0]) {
            break;
        }
    }
    if (del < sysib.count) {
        memset(sysib.ext_names[del], 0,
               sizeof(sysib.ext_names[0]) * (sysib.count - del));
    }
    /* Insert short machine name in EBCDIC, padded with blanks */
    if (qemu_name) {
        memset(sysib.vm[0].name, 0x40, sizeof(sysib.vm[0].name));
        ebcdic_put(sysib.vm[0].name, qemu_name, MIN(sizeof(sysib.vm[0].name),
                                                    strlen(qemu_name)));
    }
    sysib.vm[0].ext_name_encoding = 2; /* 2 = UTF-8 */
    memset(sysib.ext_names[0], 0, sizeof(sysib.ext_names[0]));
    /* If hypervisor specifies zero Extended Name in STSI322 SYSIB, it's
     * considered by s390 as not capable of providing any Extended Name.
     * Therefore if no name was specified on qemu invocation, we go with the
     * same "KVMguest" default, which KVM has filled into short name field.
     */
    if (qemu_name) {
        strncpy((char *)sysib.ext_names[0], qemu_name,
                sizeof(sysib.ext_names[0]));
    } else {
        strcpy((char *)sysib.ext_names[0], "KVMguest");
    }
    /* Insert UUID */
    memcpy(sysib.vm[0].uuid, qemu_uuid, sizeof(sysib.vm[0].uuid));

    s390_cpu_virt_mem_write(cpu, addr, ar, &sysib, sizeof(sysib));
}

static int handle_stsi(S390CPU *cpu)
{
    CPUState *cs = CPU(cpu);
    struct kvm_run *run = cs->kvm_run;

    switch (run->s390_stsi.fc) {
    case 3:
        if (run->s390_stsi.sel1 != 2 || run->s390_stsi.sel2 != 2) {
            return 0;
        }
        /* Only sysib 3.2.2 needs post-handling for now. */
        insert_stsi_3_2_2(cpu, run->s390_stsi.addr, run->s390_stsi.ar);
        return 0;
    default:
        return 0;
    }
}

static int kvm_arch_handle_debug_exit(S390CPU *cpu)
{
    CPUState *cs = CPU(cpu);
    struct kvm_run *run = cs->kvm_run;

    int ret = 0;
    struct kvm_debug_exit_arch *arch_info = &run->debug.arch;

    switch (arch_info->type) {
    case KVM_HW_WP_WRITE:
        if (find_hw_breakpoint(arch_info->addr, -1, arch_info->type)) {
            cs->watchpoint_hit = &hw_watchpoint;
            hw_watchpoint.vaddr = arch_info->addr;
            hw_watchpoint.flags = BP_MEM_WRITE;
            ret = EXCP_DEBUG;
        }
        break;
    case KVM_HW_BP:
        if (find_hw_breakpoint(arch_info->addr, -1, arch_info->type)) {
            ret = EXCP_DEBUG;
        }
        break;
    case KVM_SINGLESTEP:
        if (cs->singlestep_enabled) {
            ret = EXCP_DEBUG;
        }
        break;
    default:
        ret = -ENOSYS;
    }

    return ret;
}

int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run)
{
    S390CPU *cpu = S390_CPU(cs);
    int ret = 0;

    qemu_mutex_lock_iothread();

    switch (run->exit_reason) {
        case KVM_EXIT_S390_SIEIC:
            ret = handle_intercept(cpu);
            break;
        case KVM_EXIT_S390_RESET:
            s390_reipl_request();
            break;
        case KVM_EXIT_S390_TSCH:
            ret = handle_tsch(cpu);
            break;
        case KVM_EXIT_S390_STSI:
            ret = handle_stsi(cpu);
            break;
        case KVM_EXIT_DEBUG:
            ret = kvm_arch_handle_debug_exit(cpu);
            break;
        default:
            fprintf(stderr, "Unknown KVM exit: %d\n", run->exit_reason);
            break;
    }
    qemu_mutex_unlock_iothread();

    if (ret == 0) {
        ret = EXCP_INTERRUPT;
    }
    return ret;
}

bool kvm_arch_stop_on_emulation_error(CPUState *cpu)
{
    return true;
}

int kvm_arch_on_sigbus_vcpu(CPUState *cpu, int code, void *addr)
{
    return 1;
}

int kvm_arch_on_sigbus(int code, void *addr)
{
    return 1;
}

void kvm_s390_io_interrupt(uint16_t subchannel_id,
                           uint16_t subchannel_nr, uint32_t io_int_parm,
                           uint32_t io_int_word)
{
    struct kvm_s390_irq irq = {
        .u.io.subchannel_id = subchannel_id,
        .u.io.subchannel_nr = subchannel_nr,
        .u.io.io_int_parm = io_int_parm,
        .u.io.io_int_word = io_int_word,
    };

    if (io_int_word & IO_INT_WORD_AI) {
        irq.type = KVM_S390_INT_IO(1, 0, 0, 0);
    } else {
        irq.type = ((subchannel_id & 0xff00) << 24) |
            ((subchannel_id & 0x00060) << 22) | (subchannel_nr << 16);
    }
    kvm_s390_floating_interrupt(&irq);
}

static uint64_t build_channel_report_mcic(void)
{
    uint64_t mcic;

    /* subclass: indicate channel report pending */
    mcic = MCIC_SC_CP |
    /* subclass modifiers: none */
    /* storage errors: none */
    /* validity bits: no damage */
        MCIC_VB_WP | MCIC_VB_MS | MCIC_VB_PM | MCIC_VB_IA | MCIC_VB_FP |
        MCIC_VB_GR | MCIC_VB_CR | MCIC_VB_ST | MCIC_VB_AR | MCIC_VB_PR |
        MCIC_VB_FC | MCIC_VB_CT | MCIC_VB_CC;
    if (kvm_check_extension(kvm_state, KVM_CAP_S390_VECTOR_REGISTERS)) {
        mcic |= MCIC_VB_VR;
    }
    return mcic;
}

void kvm_s390_crw_mchk(void)
{
    struct kvm_s390_irq irq = {
        .type = KVM_S390_MCHK,
        .u.mchk.cr14 = 1 << 28,
        .u.mchk.mcic = build_channel_report_mcic(),
    };
    kvm_s390_floating_interrupt(&irq);
}

void kvm_s390_enable_css_support(S390CPU *cpu)
{
    int r;

    /* Activate host kernel channel subsystem support. */
    r = kvm_vcpu_enable_cap(CPU(cpu), KVM_CAP_S390_CSS_SUPPORT, 0);
    assert(r == 0);
}

void kvm_arch_init_irq_routing(KVMState *s)
{
    /*
     * Note that while irqchip capabilities generally imply that cpustates
     * are handled in-kernel, it is not true for s390 (yet); therefore, we
     * have to override the common code kvm_halt_in_kernel_allowed setting.
     */
    if (kvm_check_extension(s, KVM_CAP_IRQ_ROUTING)) {
        kvm_gsi_routing_allowed = true;
        kvm_halt_in_kernel_allowed = false;
    }
}

int kvm_s390_assign_subch_ioeventfd(EventNotifier *notifier, uint32_t sch,
                                    int vq, bool assign)
{
    struct kvm_ioeventfd kick = {
        .flags = KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY |
        KVM_IOEVENTFD_FLAG_DATAMATCH,
        .fd = event_notifier_get_fd(notifier),
        .datamatch = vq,
        .addr = sch,
        .len = 8,
    };
    if (!kvm_check_extension(kvm_state, KVM_CAP_IOEVENTFD)) {
        return -ENOSYS;
    }
    if (!assign) {
        kick.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
    }
    return kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &kick);
}

int kvm_s390_get_memslot_count(KVMState *s)
{
    return kvm_check_extension(s, KVM_CAP_NR_MEMSLOTS);
}

int kvm_s390_set_cpu_state(S390CPU *cpu, uint8_t cpu_state)
{
    struct kvm_mp_state mp_state = {};
    int ret;

    /* the kvm part might not have been initialized yet */
    if (CPU(cpu)->kvm_state == NULL) {
        return 0;
    }

    switch (cpu_state) {
    case CPU_STATE_STOPPED:
        mp_state.mp_state = KVM_MP_STATE_STOPPED;
        break;
    case CPU_STATE_CHECK_STOP:
        mp_state.mp_state = KVM_MP_STATE_CHECK_STOP;
        break;
    case CPU_STATE_OPERATING:
        mp_state.mp_state = KVM_MP_STATE_OPERATING;
        break;
    case CPU_STATE_LOAD:
        mp_state.mp_state = KVM_MP_STATE_LOAD;
        break;
    default:
        error_report("Requested CPU state is not a valid S390 CPU state: %u",
                     cpu_state);
        exit(1);
    }

    ret = kvm_vcpu_ioctl(CPU(cpu), KVM_SET_MP_STATE, &mp_state);
    if (ret) {
        trace_kvm_failed_cpu_state_set(CPU(cpu)->cpu_index, cpu_state,
                                       strerror(-ret));
    }

    return ret;
}

void kvm_s390_vcpu_interrupt_pre_save(S390CPU *cpu)
{
    struct kvm_s390_irq_state irq_state;
    CPUState *cs = CPU(cpu);
    int32_t bytes;

    if (!kvm_check_extension(kvm_state, KVM_CAP_S390_IRQ_STATE)) {
        return;
    }

    irq_state.buf = (uint64_t) cpu->irqstate;
    irq_state.len = VCPU_IRQ_BUF_SIZE;

    bytes = kvm_vcpu_ioctl(cs, KVM_S390_GET_IRQ_STATE, &irq_state);
    if (bytes < 0) {
        cpu->irqstate_saved_size = 0;
        error_report("Migration of interrupt state failed");
        return;
    }

    cpu->irqstate_saved_size = bytes;
}

int kvm_s390_vcpu_interrupt_post_load(S390CPU *cpu)
{
    CPUState *cs = CPU(cpu);
    struct kvm_s390_irq_state irq_state;
    int r;

    if (cpu->irqstate_saved_size == 0) {
        return 0;
    }

    if (!kvm_check_extension(kvm_state, KVM_CAP_S390_IRQ_STATE)) {
        return -ENOSYS;
    }

    irq_state.buf = (uint64_t) cpu->irqstate;
    irq_state.len = cpu->irqstate_saved_size;

    r = kvm_vcpu_ioctl(cs, KVM_S390_SET_IRQ_STATE, &irq_state);
    if (r) {
        error_report("Setting interrupt state failed %d", r);
    }
    return r;
}

int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route,
                             uint64_t address, uint32_t data, PCIDevice *dev)
{
    S390PCIBusDevice *pbdev;
    uint32_t fid = data >> ZPCI_MSI_VEC_BITS;
    uint32_t vec = data & ZPCI_MSI_VEC_MASK;

    pbdev = s390_pci_find_dev_by_fid(fid);
    if (!pbdev) {
        DPRINTF("add_msi_route no dev\n");
        return -ENODEV;
    }

    pbdev->routes.adapter.ind_offset = vec;

    route->type = KVM_IRQ_ROUTING_S390_ADAPTER;
    route->flags = 0;
    route->u.adapter.summary_addr = pbdev->routes.adapter.summary_addr;
    route->u.adapter.ind_addr = pbdev->routes.adapter.ind_addr;
    route->u.adapter.summary_offset = pbdev->routes.adapter.summary_offset;
    route->u.adapter.ind_offset = pbdev->routes.adapter.ind_offset;
    route->u.adapter.adapter_id = pbdev->routes.adapter.adapter_id;
    return 0;
}

int kvm_arch_msi_data_to_gsi(uint32_t data)
{
    abort();
}
OpenPOWER on IntegriCloud