aboutsummaryrefslogtreecommitdiff
path: root/cpus.c
blob: af678264f6e2f477b3670d902e381a14fc123a0f (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
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
/*
 * QEMU System Emulator
 *
 * Copyright (c) 2003-2008 Fabrice Bellard
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

#include "qemu/osdep.h"
#include "qemu/config-file.h"
#include "cpu.h"
#include "monitor/monitor.h"
#include "qapi/error.h"
#include "qapi/qmp/qerror.h"
#include "qemu/error-report.h"
#include "sysemu/sysemu.h"
#include "sysemu/block-backend.h"
#include "exec/gdbstub.h"
#include "sysemu/dma.h"
#include "sysemu/hw_accel.h"
#include "sysemu/kvm.h"
#include "sysemu/hax.h"
#include "sysemu/hvf.h"
#include "sysemu/whpx.h"
#include "qmp-commands.h"
#include "exec/exec-all.h"

#include "qemu/thread.h"
#include "sysemu/cpus.h"
#include "sysemu/qtest.h"
#include "qemu/main-loop.h"
#include "qemu/option.h"
#include "qemu/bitmap.h"
#include "qemu/seqlock.h"
#include "tcg.h"
#include "qapi-event.h"
#include "hw/nmi.h"
#include "sysemu/replay.h"
#include "hw/boards.h"

#ifdef CONFIG_LINUX

#include <sys/prctl.h>

#ifndef PR_MCE_KILL
#define PR_MCE_KILL 33
#endif

#ifndef PR_MCE_KILL_SET
#define PR_MCE_KILL_SET 1
#endif

#ifndef PR_MCE_KILL_EARLY
#define PR_MCE_KILL_EARLY 1
#endif

#endif /* CONFIG_LINUX */

int64_t max_delay;
int64_t max_advance;

/* vcpu throttling controls */
static QEMUTimer *throttle_timer;
static unsigned int throttle_percentage;

#define CPU_THROTTLE_PCT_MIN 1
#define CPU_THROTTLE_PCT_MAX 99
#define CPU_THROTTLE_TIMESLICE_NS 10000000

bool cpu_is_stopped(CPUState *cpu)
{
    return cpu->stopped || !runstate_is_running();
}

static bool cpu_thread_is_idle(CPUState *cpu)
{
    if (cpu->stop || cpu->queued_work_first) {
        return false;
    }
    if (cpu_is_stopped(cpu)) {
        return true;
    }
    if (!cpu->halted || cpu_has_work(cpu) ||
        kvm_halt_in_kernel()) {
        return false;
    }
    return true;
}

static bool all_cpu_threads_idle(void)
{
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        if (!cpu_thread_is_idle(cpu)) {
            return false;
        }
    }
    return true;
}

/***********************************************************/
/* guest cycle counter */

/* Protected by TimersState seqlock */

static bool icount_sleep = true;
/* Conversion factor from emulated instructions to virtual clock ticks.  */
static int icount_time_shift;
/* Arbitrarily pick 1MIPS as the minimum allowable speed.  */
#define MAX_ICOUNT_SHIFT 10

typedef struct TimersState {
    /* Protected by BQL.  */
    int64_t cpu_ticks_prev;
    int64_t cpu_ticks_offset;

    /* cpu_clock_offset can be read out of BQL, so protect it with
     * this lock.
     */
    QemuSeqLock vm_clock_seqlock;
    int64_t cpu_clock_offset;
    int32_t cpu_ticks_enabled;
    int64_t dummy;

    /* Compensate for varying guest execution speed.  */
    int64_t qemu_icount_bias;
    /* Only written by TCG thread */
    int64_t qemu_icount;
    /* for adjusting icount */
    int64_t vm_clock_warp_start;
    QEMUTimer *icount_rt_timer;
    QEMUTimer *icount_vm_timer;
    QEMUTimer *icount_warp_timer;
} TimersState;

static TimersState timers_state;
bool mttcg_enabled;

/*
 * We default to false if we know other options have been enabled
 * which are currently incompatible with MTTCG. Otherwise when each
 * guest (target) has been updated to support:
 *   - atomic instructions
 *   - memory ordering primitives (barriers)
 * they can set the appropriate CONFIG flags in ${target}-softmmu.mak
 *
 * Once a guest architecture has been converted to the new primitives
 * there are two remaining limitations to check.
 *
 * - The guest can't be oversized (e.g. 64 bit guest on 32 bit host)
 * - The host must have a stronger memory order than the guest
 *
 * It may be possible in future to support strong guests on weak hosts
 * but that will require tagging all load/stores in a guest with their
 * implicit memory order requirements which would likely slow things
 * down a lot.
 */

static bool check_tcg_memory_orders_compatible(void)
{
#if defined(TCG_GUEST_DEFAULT_MO) && defined(TCG_TARGET_DEFAULT_MO)
    return (TCG_GUEST_DEFAULT_MO & ~TCG_TARGET_DEFAULT_MO) == 0;
#else
    return false;
#endif
}

static bool default_mttcg_enabled(void)
{
    if (use_icount || TCG_OVERSIZED_GUEST) {
        return false;
    } else {
#ifdef TARGET_SUPPORTS_MTTCG
        return check_tcg_memory_orders_compatible();
#else
        return false;
#endif
    }
}

void qemu_tcg_configure(QemuOpts *opts, Error **errp)
{
    const char *t = qemu_opt_get(opts, "thread");
    if (t) {
        if (strcmp(t, "multi") == 0) {
            if (TCG_OVERSIZED_GUEST) {
                error_setg(errp, "No MTTCG when guest word size > hosts");
            } else if (use_icount) {
                error_setg(errp, "No MTTCG when icount is enabled");
            } else {
#ifndef TARGET_SUPPORTS_MTTCG
                error_report("Guest not yet converted to MTTCG - "
                             "you may get unexpected results");
#endif
                if (!check_tcg_memory_orders_compatible()) {
                    error_report("Guest expects a stronger memory ordering "
                                 "than the host provides");
                    error_printf("This may cause strange/hard to debug errors\n");
                }
                mttcg_enabled = true;
            }
        } else if (strcmp(t, "single") == 0) {
            mttcg_enabled = false;
        } else {
            error_setg(errp, "Invalid 'thread' setting %s", t);
        }
    } else {
        mttcg_enabled = default_mttcg_enabled();
    }
}

/* The current number of executed instructions is based on what we
 * originally budgeted minus the current state of the decrementing
 * icount counters in extra/u16.low.
 */
static int64_t cpu_get_icount_executed(CPUState *cpu)
{
    return cpu->icount_budget - (cpu->icount_decr.u16.low + cpu->icount_extra);
}

/*
 * Update the global shared timer_state.qemu_icount to take into
 * account executed instructions. This is done by the TCG vCPU
 * thread so the main-loop can see time has moved forward.
 */
void cpu_update_icount(CPUState *cpu)
{
    int64_t executed = cpu_get_icount_executed(cpu);
    cpu->icount_budget -= executed;

#ifdef CONFIG_ATOMIC64
    atomic_set__nocheck(&timers_state.qemu_icount,
                        atomic_read__nocheck(&timers_state.qemu_icount) +
                        executed);
#else /* FIXME: we need 64bit atomics to do this safely */
    timers_state.qemu_icount += executed;
#endif
}

int64_t cpu_get_icount_raw(void)
{
    CPUState *cpu = current_cpu;

    if (cpu && cpu->running) {
        if (!cpu->can_do_io) {
            error_report("Bad icount read");
            exit(1);
        }
        /* Take into account what has run */
        cpu_update_icount(cpu);
    }
#ifdef CONFIG_ATOMIC64
    return atomic_read__nocheck(&timers_state.qemu_icount);
#else /* FIXME: we need 64bit atomics to do this safely */
    return timers_state.qemu_icount;
#endif
}

/* Return the virtual CPU time, based on the instruction counter.  */
static int64_t cpu_get_icount_locked(void)
{
    int64_t icount = cpu_get_icount_raw();
    return timers_state.qemu_icount_bias + cpu_icount_to_ns(icount);
}

int64_t cpu_get_icount(void)
{
    int64_t icount;
    unsigned start;

    do {
        start = seqlock_read_begin(&timers_state.vm_clock_seqlock);
        icount = cpu_get_icount_locked();
    } while (seqlock_read_retry(&timers_state.vm_clock_seqlock, start));

    return icount;
}

int64_t cpu_icount_to_ns(int64_t icount)
{
    return icount << icount_time_shift;
}

/* return the time elapsed in VM between vm_start and vm_stop.  Unless
 * icount is active, cpu_get_ticks() uses units of the host CPU cycle
 * counter.
 *
 * Caller must hold the BQL
 */
int64_t cpu_get_ticks(void)
{
    int64_t ticks;

    if (use_icount) {
        return cpu_get_icount();
    }

    ticks = timers_state.cpu_ticks_offset;
    if (timers_state.cpu_ticks_enabled) {
        ticks += cpu_get_host_ticks();
    }

    if (timers_state.cpu_ticks_prev > ticks) {
        /* Note: non increasing ticks may happen if the host uses
           software suspend */
        timers_state.cpu_ticks_offset += timers_state.cpu_ticks_prev - ticks;
        ticks = timers_state.cpu_ticks_prev;
    }

    timers_state.cpu_ticks_prev = ticks;
    return ticks;
}

static int64_t cpu_get_clock_locked(void)
{
    int64_t time;

    time = timers_state.cpu_clock_offset;
    if (timers_state.cpu_ticks_enabled) {
        time += get_clock();
    }

    return time;
}

/* Return the monotonic time elapsed in VM, i.e.,
 * the time between vm_start and vm_stop
 */
int64_t cpu_get_clock(void)
{
    int64_t ti;
    unsigned start;

    do {
        start = seqlock_read_begin(&timers_state.vm_clock_seqlock);
        ti = cpu_get_clock_locked();
    } while (seqlock_read_retry(&timers_state.vm_clock_seqlock, start));

    return ti;
}

/* enable cpu_get_ticks()
 * Caller must hold BQL which serves as mutex for vm_clock_seqlock.
 */
void cpu_enable_ticks(void)
{
    /* Here, the really thing protected by seqlock is cpu_clock_offset. */
    seqlock_write_begin(&timers_state.vm_clock_seqlock);
    if (!timers_state.cpu_ticks_enabled) {
        timers_state.cpu_ticks_offset -= cpu_get_host_ticks();
        timers_state.cpu_clock_offset -= get_clock();
        timers_state.cpu_ticks_enabled = 1;
    }
    seqlock_write_end(&timers_state.vm_clock_seqlock);
}

/* disable cpu_get_ticks() : the clock is stopped. You must not call
 * cpu_get_ticks() after that.
 * Caller must hold BQL which serves as mutex for vm_clock_seqlock.
 */
void cpu_disable_ticks(void)
{
    /* Here, the really thing protected by seqlock is cpu_clock_offset. */
    seqlock_write_begin(&timers_state.vm_clock_seqlock);
    if (timers_state.cpu_ticks_enabled) {
        timers_state.cpu_ticks_offset += cpu_get_host_ticks();
        timers_state.cpu_clock_offset = cpu_get_clock_locked();
        timers_state.cpu_ticks_enabled = 0;
    }
    seqlock_write_end(&timers_state.vm_clock_seqlock);
}

/* Correlation between real and virtual time is always going to be
   fairly approximate, so ignore small variation.
   When the guest is idle real and virtual time will be aligned in
   the IO wait loop.  */
#define ICOUNT_WOBBLE (NANOSECONDS_PER_SECOND / 10)

static void icount_adjust(void)
{
    int64_t cur_time;
    int64_t cur_icount;
    int64_t delta;

    /* Protected by TimersState mutex.  */
    static int64_t last_delta;

    /* If the VM is not running, then do nothing.  */
    if (!runstate_is_running()) {
        return;
    }

    seqlock_write_begin(&timers_state.vm_clock_seqlock);
    cur_time = cpu_get_clock_locked();
    cur_icount = cpu_get_icount_locked();

    delta = cur_icount - cur_time;
    /* FIXME: This is a very crude algorithm, somewhat prone to oscillation.  */
    if (delta > 0
        && last_delta + ICOUNT_WOBBLE < delta * 2
        && icount_time_shift > 0) {
        /* The guest is getting too far ahead.  Slow time down.  */
        icount_time_shift--;
    }
    if (delta < 0
        && last_delta - ICOUNT_WOBBLE > delta * 2
        && icount_time_shift < MAX_ICOUNT_SHIFT) {
        /* The guest is getting too far behind.  Speed time up.  */
        icount_time_shift++;
    }
    last_delta = delta;
    timers_state.qemu_icount_bias = cur_icount
                              - (timers_state.qemu_icount << icount_time_shift);
    seqlock_write_end(&timers_state.vm_clock_seqlock);
}

static void icount_adjust_rt(void *opaque)
{
    timer_mod(timers_state.icount_rt_timer,
              qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL_RT) + 1000);
    icount_adjust();
}

static void icount_adjust_vm(void *opaque)
{
    timer_mod(timers_state.icount_vm_timer,
                   qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
                   NANOSECONDS_PER_SECOND / 10);
    icount_adjust();
}

static int64_t qemu_icount_round(int64_t count)
{
    return (count + (1 << icount_time_shift) - 1) >> icount_time_shift;
}

static void icount_warp_rt(void)
{
    unsigned seq;
    int64_t warp_start;

    /* The icount_warp_timer is rescheduled soon after vm_clock_warp_start
     * changes from -1 to another value, so the race here is okay.
     */
    do {
        seq = seqlock_read_begin(&timers_state.vm_clock_seqlock);
        warp_start = timers_state.vm_clock_warp_start;
    } while (seqlock_read_retry(&timers_state.vm_clock_seqlock, seq));

    if (warp_start == -1) {
        return;
    }

    seqlock_write_begin(&timers_state.vm_clock_seqlock);
    if (runstate_is_running()) {
        int64_t clock = REPLAY_CLOCK(REPLAY_CLOCK_VIRTUAL_RT,
                                     cpu_get_clock_locked());
        int64_t warp_delta;

        warp_delta = clock - timers_state.vm_clock_warp_start;
        if (use_icount == 2) {
            /*
             * In adaptive mode, do not let QEMU_CLOCK_VIRTUAL run too
             * far ahead of real time.
             */
            int64_t cur_icount = cpu_get_icount_locked();
            int64_t delta = clock - cur_icount;
            warp_delta = MIN(warp_delta, delta);
        }
        timers_state.qemu_icount_bias += warp_delta;
    }
    timers_state.vm_clock_warp_start = -1;
    seqlock_write_end(&timers_state.vm_clock_seqlock);

    if (qemu_clock_expired(QEMU_CLOCK_VIRTUAL)) {
        qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
    }
}

static void icount_timer_cb(void *opaque)
{
    /* No need for a checkpoint because the timer already synchronizes
     * with CHECKPOINT_CLOCK_VIRTUAL_RT.
     */
    icount_warp_rt();
}

void qtest_clock_warp(int64_t dest)
{
    int64_t clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
    AioContext *aio_context;
    assert(qtest_enabled());
    aio_context = qemu_get_aio_context();
    while (clock < dest) {
        int64_t deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);
        int64_t warp = qemu_soonest_timeout(dest - clock, deadline);

        seqlock_write_begin(&timers_state.vm_clock_seqlock);
        timers_state.qemu_icount_bias += warp;
        seqlock_write_end(&timers_state.vm_clock_seqlock);

        qemu_clock_run_timers(QEMU_CLOCK_VIRTUAL);
        timerlist_run_timers(aio_context->tlg.tl[QEMU_CLOCK_VIRTUAL]);
        clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
    }
    qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
}

void qemu_start_warp_timer(void)
{
    int64_t clock;
    int64_t deadline;

    if (!use_icount) {
        return;
    }

    /* Nothing to do if the VM is stopped: QEMU_CLOCK_VIRTUAL timers
     * do not fire, so computing the deadline does not make sense.
     */
    if (!runstate_is_running()) {
        return;
    }

    /* warp clock deterministically in record/replay mode */
    if (!replay_checkpoint(CHECKPOINT_CLOCK_WARP_START)) {
        return;
    }

    if (!all_cpu_threads_idle()) {
        return;
    }

    if (qtest_enabled()) {
        /* When testing, qtest commands advance icount.  */
        return;
    }

    /* We want to use the earliest deadline from ALL vm_clocks */
    clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL_RT);
    deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);
    if (deadline < 0) {
        static bool notified;
        if (!icount_sleep && !notified) {
            warn_report("icount sleep disabled and no active timers");
            notified = true;
        }
        return;
    }

    if (deadline > 0) {
        /*
         * Ensure QEMU_CLOCK_VIRTUAL proceeds even when the virtual CPU goes to
         * sleep.  Otherwise, the CPU might be waiting for a future timer
         * interrupt to wake it up, but the interrupt never comes because
         * the vCPU isn't running any insns and thus doesn't advance the
         * QEMU_CLOCK_VIRTUAL.
         */
        if (!icount_sleep) {
            /*
             * We never let VCPUs sleep in no sleep icount mode.
             * If there is a pending QEMU_CLOCK_VIRTUAL timer we just advance
             * to the next QEMU_CLOCK_VIRTUAL event and notify it.
             * It is useful when we want a deterministic execution time,
             * isolated from host latencies.
             */
            seqlock_write_begin(&timers_state.vm_clock_seqlock);
            timers_state.qemu_icount_bias += deadline;
            seqlock_write_end(&timers_state.vm_clock_seqlock);
            qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
        } else {
            /*
             * We do stop VCPUs and only advance QEMU_CLOCK_VIRTUAL after some
             * "real" time, (related to the time left until the next event) has
             * passed. The QEMU_CLOCK_VIRTUAL_RT clock will do this.
             * This avoids that the warps are visible externally; for example,
             * you will not be sending network packets continuously instead of
             * every 100ms.
             */
            seqlock_write_begin(&timers_state.vm_clock_seqlock);
            if (timers_state.vm_clock_warp_start == -1
                || timers_state.vm_clock_warp_start > clock) {
                timers_state.vm_clock_warp_start = clock;
            }
            seqlock_write_end(&timers_state.vm_clock_seqlock);
            timer_mod_anticipate(timers_state.icount_warp_timer,
                                 clock + deadline);
        }
    } else if (deadline == 0) {
        qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
    }
}

static void qemu_account_warp_timer(void)
{
    if (!use_icount || !icount_sleep) {
        return;
    }

    /* Nothing to do if the VM is stopped: QEMU_CLOCK_VIRTUAL timers
     * do not fire, so computing the deadline does not make sense.
     */
    if (!runstate_is_running()) {
        return;
    }

    /* warp clock deterministically in record/replay mode */
    if (!replay_checkpoint(CHECKPOINT_CLOCK_WARP_ACCOUNT)) {
        return;
    }

    timer_del(timers_state.icount_warp_timer);
    icount_warp_rt();
}

static bool icount_state_needed(void *opaque)
{
    return use_icount;
}

static bool warp_timer_state_needed(void *opaque)
{
    TimersState *s = opaque;
    return s->icount_warp_timer != NULL;
}

static bool adjust_timers_state_needed(void *opaque)
{
    TimersState *s = opaque;
    return s->icount_rt_timer != NULL;
}

/*
 * Subsection for warp timer migration is optional, because may not be created
 */
static const VMStateDescription icount_vmstate_warp_timer = {
    .name = "timer/icount/warp_timer",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = warp_timer_state_needed,
    .fields = (VMStateField[]) {
        VMSTATE_INT64(vm_clock_warp_start, TimersState),
        VMSTATE_TIMER_PTR(icount_warp_timer, TimersState),
        VMSTATE_END_OF_LIST()
    }
};

static const VMStateDescription icount_vmstate_adjust_timers = {
    .name = "timer/icount/timers",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = adjust_timers_state_needed,
    .fields = (VMStateField[]) {
        VMSTATE_TIMER_PTR(icount_rt_timer, TimersState),
        VMSTATE_TIMER_PTR(icount_vm_timer, TimersState),
        VMSTATE_END_OF_LIST()
    }
};

/*
 * This is a subsection for icount migration.
 */
static const VMStateDescription icount_vmstate_timers = {
    .name = "timer/icount",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = icount_state_needed,
    .fields = (VMStateField[]) {
        VMSTATE_INT64(qemu_icount_bias, TimersState),
        VMSTATE_INT64(qemu_icount, TimersState),
        VMSTATE_END_OF_LIST()
    },
    .subsections = (const VMStateDescription*[]) {
        &icount_vmstate_warp_timer,
        &icount_vmstate_adjust_timers,
        NULL
    }
};

static const VMStateDescription vmstate_timers = {
    .name = "timer",
    .version_id = 2,
    .minimum_version_id = 1,
    .fields = (VMStateField[]) {
        VMSTATE_INT64(cpu_ticks_offset, TimersState),
        VMSTATE_INT64(dummy, TimersState),
        VMSTATE_INT64_V(cpu_clock_offset, TimersState, 2),
        VMSTATE_END_OF_LIST()
    },
    .subsections = (const VMStateDescription*[]) {
        &icount_vmstate_timers,
        NULL
    }
};

static void cpu_throttle_thread(CPUState *cpu, run_on_cpu_data opaque)
{
    double pct;
    double throttle_ratio;
    long sleeptime_ns;

    if (!cpu_throttle_get_percentage()) {
        return;
    }

    pct = (double)cpu_throttle_get_percentage()/100;
    throttle_ratio = pct / (1 - pct);
    sleeptime_ns = (long)(throttle_ratio * CPU_THROTTLE_TIMESLICE_NS);

    qemu_mutex_unlock_iothread();
    g_usleep(sleeptime_ns / 1000); /* Convert ns to us for usleep call */
    qemu_mutex_lock_iothread();
    atomic_set(&cpu->throttle_thread_scheduled, 0);
}

static void cpu_throttle_timer_tick(void *opaque)
{
    CPUState *cpu;
    double pct;

    /* Stop the timer if needed */
    if (!cpu_throttle_get_percentage()) {
        return;
    }
    CPU_FOREACH(cpu) {
        if (!atomic_xchg(&cpu->throttle_thread_scheduled, 1)) {
            async_run_on_cpu(cpu, cpu_throttle_thread,
                             RUN_ON_CPU_NULL);
        }
    }

    pct = (double)cpu_throttle_get_percentage()/100;
    timer_mod(throttle_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL_RT) +
                                   CPU_THROTTLE_TIMESLICE_NS / (1-pct));
}

void cpu_throttle_set(int new_throttle_pct)
{
    /* Ensure throttle percentage is within valid range */
    new_throttle_pct = MIN(new_throttle_pct, CPU_THROTTLE_PCT_MAX);
    new_throttle_pct = MAX(new_throttle_pct, CPU_THROTTLE_PCT_MIN);

    atomic_set(&throttle_percentage, new_throttle_pct);

    timer_mod(throttle_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL_RT) +
                                       CPU_THROTTLE_TIMESLICE_NS);
}

void cpu_throttle_stop(void)
{
    atomic_set(&throttle_percentage, 0);
}

bool cpu_throttle_active(void)
{
    return (cpu_throttle_get_percentage() != 0);
}

int cpu_throttle_get_percentage(void)
{
    return atomic_read(&throttle_percentage);
}

void cpu_ticks_init(void)
{
    seqlock_init(&timers_state.vm_clock_seqlock);
    vmstate_register(NULL, 0, &vmstate_timers, &timers_state);
    throttle_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL_RT,
                                           cpu_throttle_timer_tick, NULL);
}

void configure_icount(QemuOpts *opts, Error **errp)
{
    const char *option;
    char *rem_str = NULL;

    option = qemu_opt_get(opts, "shift");
    if (!option) {
        if (qemu_opt_get(opts, "align") != NULL) {
            error_setg(errp, "Please specify shift option when using align");
        }
        return;
    }

    icount_sleep = qemu_opt_get_bool(opts, "sleep", true);
    if (icount_sleep) {
        timers_state.icount_warp_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL_RT,
                                         icount_timer_cb, NULL);
    }

    icount_align_option = qemu_opt_get_bool(opts, "align", false);

    if (icount_align_option && !icount_sleep) {
        error_setg(errp, "align=on and sleep=off are incompatible");
    }
    if (strcmp(option, "auto") != 0) {
        errno = 0;
        icount_time_shift = strtol(option, &rem_str, 0);
        if (errno != 0 || *rem_str != '\0' || !strlen(option)) {
            error_setg(errp, "icount: Invalid shift value");
        }
        use_icount = 1;
        return;
    } else if (icount_align_option) {
        error_setg(errp, "shift=auto and align=on are incompatible");
    } else if (!icount_sleep) {
        error_setg(errp, "shift=auto and sleep=off are incompatible");
    }

    use_icount = 2;

    /* 125MIPS seems a reasonable initial guess at the guest speed.
       It will be corrected fairly quickly anyway.  */
    icount_time_shift = 3;

    /* Have both realtime and virtual time triggers for speed adjustment.
       The realtime trigger catches emulated time passing too slowly,
       the virtual time trigger catches emulated time passing too fast.
       Realtime triggers occur even when idle, so use them less frequently
       than VM triggers.  */
    timers_state.vm_clock_warp_start = -1;
    timers_state.icount_rt_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL_RT,
                                   icount_adjust_rt, NULL);
    timer_mod(timers_state.icount_rt_timer,
                   qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL_RT) + 1000);
    timers_state.icount_vm_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
                                        icount_adjust_vm, NULL);
    timer_mod(timers_state.icount_vm_timer,
                   qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
                   NANOSECONDS_PER_SECOND / 10);
}

/***********************************************************/
/* TCG vCPU kick timer
 *
 * The kick timer is responsible for moving single threaded vCPU
 * emulation on to the next vCPU. If more than one vCPU is running a
 * timer event with force a cpu->exit so the next vCPU can get
 * scheduled.
 *
 * The timer is removed if all vCPUs are idle and restarted again once
 * idleness is complete.
 */

static QEMUTimer *tcg_kick_vcpu_timer;
static CPUState *tcg_current_rr_cpu;

#define TCG_KICK_PERIOD (NANOSECONDS_PER_SECOND / 10)

static inline int64_t qemu_tcg_next_kick(void)
{
    return qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + TCG_KICK_PERIOD;
}

/* Kick the currently round-robin scheduled vCPU */
static void qemu_cpu_kick_rr_cpu(void)
{
    CPUState *cpu;
    do {
        cpu = atomic_mb_read(&tcg_current_rr_cpu);
        if (cpu) {
            cpu_exit(cpu);
        }
    } while (cpu != atomic_mb_read(&tcg_current_rr_cpu));
}

static void do_nothing(CPUState *cpu, run_on_cpu_data unused)
{
}

void qemu_timer_notify_cb(void *opaque, QEMUClockType type)
{
    if (!use_icount || type != QEMU_CLOCK_VIRTUAL) {
        qemu_notify_event();
        return;
    }

    if (!qemu_in_vcpu_thread() && first_cpu) {
        /* qemu_cpu_kick is not enough to kick a halted CPU out of
         * qemu_tcg_wait_io_event.  async_run_on_cpu, instead,
         * causes cpu_thread_is_idle to return false.  This way,
         * handle_icount_deadline can run.
         */
        async_run_on_cpu(first_cpu, do_nothing, RUN_ON_CPU_NULL);
    }
}

static void kick_tcg_thread(void *opaque)
{
    timer_mod(tcg_kick_vcpu_timer, qemu_tcg_next_kick());
    qemu_cpu_kick_rr_cpu();
}

static void start_tcg_kick_timer(void)
{
    assert(!mttcg_enabled);
    if (!tcg_kick_vcpu_timer && CPU_NEXT(first_cpu)) {
        tcg_kick_vcpu_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
                                           kick_tcg_thread, NULL);
        timer_mod(tcg_kick_vcpu_timer, qemu_tcg_next_kick());
    }
}

static void stop_tcg_kick_timer(void)
{
    assert(!mttcg_enabled);
    if (tcg_kick_vcpu_timer) {
        timer_del(tcg_kick_vcpu_timer);
        tcg_kick_vcpu_timer = NULL;
    }
}

/***********************************************************/
void hw_error(const char *fmt, ...)
{
    va_list ap;
    CPUState *cpu;

    va_start(ap, fmt);
    fprintf(stderr, "qemu: hardware error: ");
    vfprintf(stderr, fmt, ap);
    fprintf(stderr, "\n");
    CPU_FOREACH(cpu) {
        fprintf(stderr, "CPU #%d:\n", cpu->cpu_index);
        cpu_dump_state(cpu, stderr, fprintf, CPU_DUMP_FPU);
    }
    va_end(ap);
    abort();
}

void cpu_synchronize_all_states(void)
{
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        cpu_synchronize_state(cpu);
        /* TODO: move to cpu_synchronize_state() */
        if (hvf_enabled()) {
            hvf_cpu_synchronize_state(cpu);
        }
    }
}

void cpu_synchronize_all_post_reset(void)
{
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        cpu_synchronize_post_reset(cpu);
        /* TODO: move to cpu_synchronize_post_reset() */
        if (hvf_enabled()) {
            hvf_cpu_synchronize_post_reset(cpu);
        }
    }
}

void cpu_synchronize_all_post_init(void)
{
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        cpu_synchronize_post_init(cpu);
        /* TODO: move to cpu_synchronize_post_init() */
        if (hvf_enabled()) {
            hvf_cpu_synchronize_post_init(cpu);
        }
    }
}

void cpu_synchronize_all_pre_loadvm(void)
{
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        cpu_synchronize_pre_loadvm(cpu);
    }
}

static int do_vm_stop(RunState state)
{
    int ret = 0;

    if (runstate_is_running()) {
        cpu_disable_ticks();
        pause_all_vcpus();
        runstate_set(state);
        vm_state_notify(0, state);
        qapi_event_send_stop(&error_abort);
    }

    bdrv_drain_all();
    replay_disable_events();
    ret = bdrv_flush_all();

    return ret;
}

static bool cpu_can_run(CPUState *cpu)
{
    if (cpu->stop) {
        return false;
    }
    if (cpu_is_stopped(cpu)) {
        return false;
    }
    return true;
}

static void cpu_handle_guest_debug(CPUState *cpu)
{
    gdb_set_stop_cpu(cpu);
    qemu_system_debug_request();
    cpu->stopped = true;
}

#ifdef CONFIG_LINUX
static void sigbus_reraise(void)
{
    sigset_t set;
    struct sigaction action;

    memset(&action, 0, sizeof(action));
    action.sa_handler = SIG_DFL;
    if (!sigaction(SIGBUS, &action, NULL)) {
        raise(SIGBUS);
        sigemptyset(&set);
        sigaddset(&set, SIGBUS);
        pthread_sigmask(SIG_UNBLOCK, &set, NULL);
    }
    perror("Failed to re-raise SIGBUS!\n");
    abort();
}

static void sigbus_handler(int n, siginfo_t *siginfo, void *ctx)
{
    if (siginfo->si_code != BUS_MCEERR_AO && siginfo->si_code != BUS_MCEERR_AR) {
        sigbus_reraise();
    }

    if (current_cpu) {
        /* Called asynchronously in VCPU thread.  */
        if (kvm_on_sigbus_vcpu(current_cpu, siginfo->si_code, siginfo->si_addr)) {
            sigbus_reraise();
        }
    } else {
        /* Called synchronously (via signalfd) in main thread.  */
        if (kvm_on_sigbus(siginfo->si_code, siginfo->si_addr)) {
            sigbus_reraise();
        }
    }
}

static void qemu_init_sigbus(void)
{
    struct sigaction action;

    memset(&action, 0, sizeof(action));
    action.sa_flags = SA_SIGINFO;
    action.sa_sigaction = sigbus_handler;
    sigaction(SIGBUS, &action, NULL);

    prctl(PR_MCE_KILL, PR_MCE_KILL_SET, PR_MCE_KILL_EARLY, 0, 0);
}
#else /* !CONFIG_LINUX */
static void qemu_init_sigbus(void)
{
}
#endif /* !CONFIG_LINUX */

static QemuMutex qemu_global_mutex;

static QemuThread io_thread;

/* cpu creation */
static QemuCond qemu_cpu_cond;
/* system init */
static QemuCond qemu_pause_cond;

void qemu_init_cpu_loop(void)
{
    qemu_init_sigbus();
    qemu_cond_init(&qemu_cpu_cond);
    qemu_cond_init(&qemu_pause_cond);
    qemu_mutex_init(&qemu_global_mutex);

    qemu_thread_get_self(&io_thread);
}

void run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data)
{
    do_run_on_cpu(cpu, func, data, &qemu_global_mutex);
}

static void qemu_kvm_destroy_vcpu(CPUState *cpu)
{
    if (kvm_destroy_vcpu(cpu) < 0) {
        error_report("kvm_destroy_vcpu failed");
        exit(EXIT_FAILURE);
    }
}

static void qemu_tcg_destroy_vcpu(CPUState *cpu)
{
}

static void qemu_cpu_stop(CPUState *cpu, bool exit)
{
    g_assert(qemu_cpu_is_self(cpu));
    cpu->stop = false;
    cpu->stopped = true;
    if (exit) {
        cpu_exit(cpu);
    }
    qemu_cond_broadcast(&qemu_pause_cond);
}

static void qemu_wait_io_event_common(CPUState *cpu)
{
    atomic_mb_set(&cpu->thread_kicked, false);
    if (cpu->stop) {
        qemu_cpu_stop(cpu, false);
    }
    process_queued_cpu_work(cpu);
}

static void qemu_tcg_rr_wait_io_event(CPUState *cpu)
{
    while (all_cpu_threads_idle()) {
        stop_tcg_kick_timer();
        qemu_cond_wait(cpu->halt_cond, &qemu_global_mutex);
    }

    start_tcg_kick_timer();

    qemu_wait_io_event_common(cpu);
}

static void qemu_wait_io_event(CPUState *cpu)
{
    while (cpu_thread_is_idle(cpu)) {
        qemu_cond_wait(cpu->halt_cond, &qemu_global_mutex);
    }

#ifdef _WIN32
    /* Eat dummy APC queued by qemu_cpu_kick_thread.  */
    if (!tcg_enabled()) {
        SleepEx(0, TRUE);
    }
#endif
    qemu_wait_io_event_common(cpu);
}

static void *qemu_kvm_cpu_thread_fn(void *arg)
{
    CPUState *cpu = arg;
    int r;

    rcu_register_thread();

    qemu_mutex_lock_iothread();
    qemu_thread_get_self(cpu->thread);
    cpu->thread_id = qemu_get_thread_id();
    cpu->can_do_io = 1;
    current_cpu = cpu;

    r = kvm_init_vcpu(cpu);
    if (r < 0) {
        error_report("kvm_init_vcpu failed: %s", strerror(-r));
        exit(1);
    }

    kvm_init_cpu_signals(cpu);

    /* signal CPU creation */
    cpu->created = true;
    qemu_cond_signal(&qemu_cpu_cond);

    do {
        if (cpu_can_run(cpu)) {
            r = kvm_cpu_exec(cpu);
            if (r == EXCP_DEBUG) {
                cpu_handle_guest_debug(cpu);
            }
        }
        qemu_wait_io_event(cpu);
    } while (!cpu->unplug || cpu_can_run(cpu));

    qemu_kvm_destroy_vcpu(cpu);
    cpu->created = false;
    qemu_cond_signal(&qemu_cpu_cond);
    qemu_mutex_unlock_iothread();
    rcu_unregister_thread();
    return NULL;
}

static void *qemu_dummy_cpu_thread_fn(void *arg)
{
#ifdef _WIN32
    error_report("qtest is not supported under Windows");
    exit(1);
#else
    CPUState *cpu = arg;
    sigset_t waitset;
    int r;

    rcu_register_thread();

    qemu_mutex_lock_iothread();
    qemu_thread_get_self(cpu->thread);
    cpu->thread_id = qemu_get_thread_id();
    cpu->can_do_io = 1;
    current_cpu = cpu;

    sigemptyset(&waitset);
    sigaddset(&waitset, SIG_IPI);

    /* signal CPU creation */
    cpu->created = true;
    qemu_cond_signal(&qemu_cpu_cond);

    do {
        qemu_mutex_unlock_iothread();
        do {
            int sig;
            r = sigwait(&waitset, &sig);
        } while (r == -1 && (errno == EAGAIN || errno == EINTR));
        if (r == -1) {
            perror("sigwait");
            exit(1);
        }
        qemu_mutex_lock_iothread();
        qemu_wait_io_event(cpu);
    } while (!cpu->unplug);

    rcu_unregister_thread();
    return NULL;
#endif
}

static int64_t tcg_get_icount_limit(void)
{
    int64_t deadline;

    if (replay_mode != REPLAY_MODE_PLAY) {
        deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);

        /* Maintain prior (possibly buggy) behaviour where if no deadline
         * was set (as there is no QEMU_CLOCK_VIRTUAL timer) or it is more than
         * INT32_MAX nanoseconds ahead, we still use INT32_MAX
         * nanoseconds.
         */
        if ((deadline < 0) || (deadline > INT32_MAX)) {
            deadline = INT32_MAX;
        }

        return qemu_icount_round(deadline);
    } else {
        return replay_get_instructions();
    }
}

static void handle_icount_deadline(void)
{
    assert(qemu_in_vcpu_thread());
    if (use_icount) {
        int64_t deadline =
            qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);

        if (deadline == 0) {
            /* Wake up other AioContexts.  */
            qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
            qemu_clock_run_timers(QEMU_CLOCK_VIRTUAL);
        }
    }
}

static void prepare_icount_for_run(CPUState *cpu)
{
    if (use_icount) {
        int insns_left;

        /* These should always be cleared by process_icount_data after
         * each vCPU execution. However u16.high can be raised
         * asynchronously by cpu_exit/cpu_interrupt/tcg_handle_interrupt
         */
        g_assert(cpu->icount_decr.u16.low == 0);
        g_assert(cpu->icount_extra == 0);

        cpu->icount_budget = tcg_get_icount_limit();
        insns_left = MIN(0xffff, cpu->icount_budget);
        cpu->icount_decr.u16.low = insns_left;
        cpu->icount_extra = cpu->icount_budget - insns_left;
    }
}

static void process_icount_data(CPUState *cpu)
{
    if (use_icount) {
        /* Account for executed instructions */
        cpu_update_icount(cpu);

        /* Reset the counters */
        cpu->icount_decr.u16.low = 0;
        cpu->icount_extra = 0;
        cpu->icount_budget = 0;

        replay_account_executed_instructions();
    }
}


static int tcg_cpu_exec(CPUState *cpu)
{
    int ret;
#ifdef CONFIG_PROFILER
    int64_t ti;
#endif

#ifdef CONFIG_PROFILER
    ti = profile_getclock();
#endif
    qemu_mutex_unlock_iothread();
    cpu_exec_start(cpu);
    ret = cpu_exec(cpu);
    cpu_exec_end(cpu);
    qemu_mutex_lock_iothread();
#ifdef CONFIG_PROFILER
    tcg_time += profile_getclock() - ti;
#endif
    return ret;
}

/* Destroy any remaining vCPUs which have been unplugged and have
 * finished running
 */
static void deal_with_unplugged_cpus(void)
{
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        if (cpu->unplug && !cpu_can_run(cpu)) {
            qemu_tcg_destroy_vcpu(cpu);
            cpu->created = false;
            qemu_cond_signal(&qemu_cpu_cond);
            break;
        }
    }
}

/* Single-threaded TCG
 *
 * In the single-threaded case each vCPU is simulated in turn. If
 * there is more than a single vCPU we create a simple timer to kick
 * the vCPU and ensure we don't get stuck in a tight loop in one vCPU.
 * This is done explicitly rather than relying on side-effects
 * elsewhere.
 */

static void *qemu_tcg_rr_cpu_thread_fn(void *arg)
{
    CPUState *cpu = arg;

    rcu_register_thread();
    tcg_register_thread();

    qemu_mutex_lock_iothread();
    qemu_thread_get_self(cpu->thread);

    CPU_FOREACH(cpu) {
        cpu->thread_id = qemu_get_thread_id();
        cpu->created = true;
        cpu->can_do_io = 1;
    }
    qemu_cond_signal(&qemu_cpu_cond);

    /* wait for initial kick-off after machine start */
    while (first_cpu->stopped) {
        qemu_cond_wait(first_cpu->halt_cond, &qemu_global_mutex);

        /* process any pending work */
        CPU_FOREACH(cpu) {
            current_cpu = cpu;
            qemu_wait_io_event_common(cpu);
        }
    }

    start_tcg_kick_timer();

    cpu = first_cpu;

    /* process any pending work */
    cpu->exit_request = 1;

    while (1) {
        /* Account partial waits to QEMU_CLOCK_VIRTUAL.  */
        qemu_account_warp_timer();

        /* Run the timers here.  This is much more efficient than
         * waking up the I/O thread and waiting for completion.
         */
        handle_icount_deadline();

        if (!cpu) {
            cpu = first_cpu;
        }

        while (cpu && !cpu->queued_work_first && !cpu->exit_request) {

            atomic_mb_set(&tcg_current_rr_cpu, cpu);
            current_cpu = cpu;

            qemu_clock_enable(QEMU_CLOCK_VIRTUAL,
                              (cpu->singlestep_enabled & SSTEP_NOTIMER) == 0);

            if (cpu_can_run(cpu)) {
                int r;

                prepare_icount_for_run(cpu);

                r = tcg_cpu_exec(cpu);

                process_icount_data(cpu);

                if (r == EXCP_DEBUG) {
                    cpu_handle_guest_debug(cpu);
                    break;
                } else if (r == EXCP_ATOMIC) {
                    qemu_mutex_unlock_iothread();
                    cpu_exec_step_atomic(cpu);
                    qemu_mutex_lock_iothread();
                    break;
                }
            } else if (cpu->stop) {
                if (cpu->unplug) {
                    cpu = CPU_NEXT(cpu);
                }
                break;
            }

            cpu = CPU_NEXT(cpu);
        } /* while (cpu && !cpu->exit_request).. */

        /* Does not need atomic_mb_set because a spurious wakeup is okay.  */
        atomic_set(&tcg_current_rr_cpu, NULL);

        if (cpu && cpu->exit_request) {
            atomic_mb_set(&cpu->exit_request, 0);
        }

        qemu_tcg_rr_wait_io_event(cpu ? cpu : QTAILQ_FIRST(&cpus));
        deal_with_unplugged_cpus();
    }

    rcu_unregister_thread();
    return NULL;
}

static void *qemu_hax_cpu_thread_fn(void *arg)
{
    CPUState *cpu = arg;
    int r;

    rcu_register_thread();
    qemu_mutex_lock_iothread();
    qemu_thread_get_self(cpu->thread);

    cpu->thread_id = qemu_get_thread_id();
    cpu->created = true;
    cpu->halted = 0;
    current_cpu = cpu;

    hax_init_vcpu(cpu);
    qemu_cond_signal(&qemu_cpu_cond);

    do {
        if (cpu_can_run(cpu)) {
            r = hax_smp_cpu_exec(cpu);
            if (r == EXCP_DEBUG) {
                cpu_handle_guest_debug(cpu);
            }
        }

        qemu_wait_io_event(cpu);
    } while (!cpu->unplug || cpu_can_run(cpu));
    rcu_unregister_thread();
    return NULL;
}

/* The HVF-specific vCPU thread function. This one should only run when the host
 * CPU supports the VMX "unrestricted guest" feature. */
static void *qemu_hvf_cpu_thread_fn(void *arg)
{
    CPUState *cpu = arg;

    int r;

    assert(hvf_enabled());

    rcu_register_thread();

    qemu_mutex_lock_iothread();
    qemu_thread_get_self(cpu->thread);

    cpu->thread_id = qemu_get_thread_id();
    cpu->can_do_io = 1;
    current_cpu = cpu;

    hvf_init_vcpu(cpu);

    /* signal CPU creation */
    cpu->created = true;
    qemu_cond_signal(&qemu_cpu_cond);

    do {
        if (cpu_can_run(cpu)) {
            r = hvf_vcpu_exec(cpu);
            if (r == EXCP_DEBUG) {
                cpu_handle_guest_debug(cpu);
            }
        }
        qemu_wait_io_event(cpu);
    } while (!cpu->unplug || cpu_can_run(cpu));

    hvf_vcpu_destroy(cpu);
    cpu->created = false;
    qemu_cond_signal(&qemu_cpu_cond);
    qemu_mutex_unlock_iothread();
    rcu_unregister_thread();
    return NULL;
}

static void *qemu_whpx_cpu_thread_fn(void *arg)
{
    CPUState *cpu = arg;
    int r;

    rcu_register_thread();

    qemu_mutex_lock_iothread();
    qemu_thread_get_self(cpu->thread);
    cpu->thread_id = qemu_get_thread_id();
    current_cpu = cpu;

    r = whpx_init_vcpu(cpu);
    if (r < 0) {
        fprintf(stderr, "whpx_init_vcpu failed: %s\n", strerror(-r));
        exit(1);
    }

    /* signal CPU creation */
    cpu->created = true;
    qemu_cond_signal(&qemu_cpu_cond);

    do {
        if (cpu_can_run(cpu)) {
            r = whpx_vcpu_exec(cpu);
            if (r == EXCP_DEBUG) {
                cpu_handle_guest_debug(cpu);
            }
        }
        while (cpu_thread_is_idle(cpu)) {
            qemu_cond_wait(cpu->halt_cond, &qemu_global_mutex);
        }
        qemu_wait_io_event_common(cpu);
    } while (!cpu->unplug || cpu_can_run(cpu));

    whpx_destroy_vcpu(cpu);
    cpu->created = false;
    qemu_cond_signal(&qemu_cpu_cond);
    qemu_mutex_unlock_iothread();
    rcu_unregister_thread();
    return NULL;
}

#ifdef _WIN32
static void CALLBACK dummy_apc_func(ULONG_PTR unused)
{
}
#endif

/* Multi-threaded TCG
 *
 * In the multi-threaded case each vCPU has its own thread. The TLS
 * variable current_cpu can be used deep in the code to find the
 * current CPUState for a given thread.
 */

static void *qemu_tcg_cpu_thread_fn(void *arg)
{
    CPUState *cpu = arg;

    g_assert(!use_icount);

    rcu_register_thread();
    tcg_register_thread();

    qemu_mutex_lock_iothread();
    qemu_thread_get_self(cpu->thread);

    cpu->thread_id = qemu_get_thread_id();
    cpu->created = true;
    cpu->can_do_io = 1;
    current_cpu = cpu;
    qemu_cond_signal(&qemu_cpu_cond);

    /* process any pending work */
    cpu->exit_request = 1;

    while (1) {
        if (cpu_can_run(cpu)) {
            int r;
            r = tcg_cpu_exec(cpu);
            switch (r) {
            case EXCP_DEBUG:
                cpu_handle_guest_debug(cpu);
                break;
            case EXCP_HALTED:
                /* during start-up the vCPU is reset and the thread is
                 * kicked several times. If we don't ensure we go back
                 * to sleep in the halted state we won't cleanly
                 * start-up when the vCPU is enabled.
                 *
                 * cpu->halted should ensure we sleep in wait_io_event
                 */
                g_assert(cpu->halted);
                break;
            case EXCP_ATOMIC:
                qemu_mutex_unlock_iothread();
                cpu_exec_step_atomic(cpu);
                qemu_mutex_lock_iothread();
            default:
                /* Ignore everything else? */
                break;
            }
        }

        atomic_mb_set(&cpu->exit_request, 0);
        qemu_wait_io_event(cpu);
    } while (!cpu->unplug || cpu_can_run(cpu));

    qemu_tcg_destroy_vcpu(cpu);
    cpu->created = false;
    qemu_cond_signal(&qemu_cpu_cond);
    qemu_mutex_unlock_iothread();
    rcu_unregister_thread();
    return NULL;
}

static void qemu_cpu_kick_thread(CPUState *cpu)
{
#ifndef _WIN32
    int err;

    if (cpu->thread_kicked) {
        return;
    }
    cpu->thread_kicked = true;
    err = pthread_kill(cpu->thread->thread, SIG_IPI);
    if (err) {
        fprintf(stderr, "qemu:%s: %s", __func__, strerror(err));
        exit(1);
    }
#else /* _WIN32 */
    if (!qemu_cpu_is_self(cpu)) {
        if (whpx_enabled()) {
            whpx_vcpu_kick(cpu);
        } else if (!QueueUserAPC(dummy_apc_func, cpu->hThread, 0)) {
            fprintf(stderr, "%s: QueueUserAPC failed with error %lu\n",
                    __func__, GetLastError());
            exit(1);
        }
    }
#endif
}

void qemu_cpu_kick(CPUState *cpu)
{
    qemu_cond_broadcast(cpu->halt_cond);
    if (tcg_enabled()) {
        cpu_exit(cpu);
        /* NOP unless doing single-thread RR */
        qemu_cpu_kick_rr_cpu();
    } else {
        if (hax_enabled()) {
            /*
             * FIXME: race condition with the exit_request check in
             * hax_vcpu_hax_exec
             */
            cpu->exit_request = 1;
        }
        qemu_cpu_kick_thread(cpu);
    }
}

void qemu_cpu_kick_self(void)
{
    assert(current_cpu);
    qemu_cpu_kick_thread(current_cpu);
}

bool qemu_cpu_is_self(CPUState *cpu)
{
    return qemu_thread_is_self(cpu->thread);
}

bool qemu_in_vcpu_thread(void)
{
    return current_cpu && qemu_cpu_is_self(current_cpu);
}

static __thread bool iothread_locked = false;

bool qemu_mutex_iothread_locked(void)
{
    return iothread_locked;
}

void qemu_mutex_lock_iothread(void)
{
    g_assert(!qemu_mutex_iothread_locked());
    qemu_mutex_lock(&qemu_global_mutex);
    iothread_locked = true;
}

void qemu_mutex_unlock_iothread(void)
{
    g_assert(qemu_mutex_iothread_locked());
    iothread_locked = false;
    qemu_mutex_unlock(&qemu_global_mutex);
}

static bool all_vcpus_paused(void)
{
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        if (!cpu->stopped) {
            return false;
        }
    }

    return true;
}

void pause_all_vcpus(void)
{
    CPUState *cpu;

    qemu_clock_enable(QEMU_CLOCK_VIRTUAL, false);
    CPU_FOREACH(cpu) {
        if (qemu_cpu_is_self(cpu)) {
            qemu_cpu_stop(cpu, true);
        } else {
            cpu->stop = true;
            qemu_cpu_kick(cpu);
        }
    }

    while (!all_vcpus_paused()) {
        qemu_cond_wait(&qemu_pause_cond, &qemu_global_mutex);
        CPU_FOREACH(cpu) {
            qemu_cpu_kick(cpu);
        }
    }
}

void cpu_resume(CPUState *cpu)
{
    cpu->stop = false;
    cpu->stopped = false;
    qemu_cpu_kick(cpu);
}

void resume_all_vcpus(void)
{
    CPUState *cpu;

    qemu_clock_enable(QEMU_CLOCK_VIRTUAL, true);
    CPU_FOREACH(cpu) {
        cpu_resume(cpu);
    }
}

void cpu_remove_sync(CPUState *cpu)
{
    cpu->stop = true;
    cpu->unplug = true;
    qemu_cpu_kick(cpu);
    qemu_mutex_unlock_iothread();
    qemu_thread_join(cpu->thread);
    qemu_mutex_lock_iothread();
}

/* For temporary buffers for forming a name */
#define VCPU_THREAD_NAME_SIZE 16

static void qemu_tcg_init_vcpu(CPUState *cpu)
{
    char thread_name[VCPU_THREAD_NAME_SIZE];
    static QemuCond *single_tcg_halt_cond;
    static QemuThread *single_tcg_cpu_thread;
    static int tcg_region_inited;

    /*
     * Initialize TCG regions--once. Now is a good time, because:
     * (1) TCG's init context, prologue and target globals have been set up.
     * (2) qemu_tcg_mttcg_enabled() works now (TCG init code runs before the
     *     -accel flag is processed, so the check doesn't work then).
     */
    if (!tcg_region_inited) {
        tcg_region_inited = 1;
        tcg_region_init();
    }

    if (qemu_tcg_mttcg_enabled() || !single_tcg_cpu_thread) {
        cpu->thread = g_malloc0(sizeof(QemuThread));
        cpu->halt_cond = g_malloc0(sizeof(QemuCond));
        qemu_cond_init(cpu->halt_cond);

        if (qemu_tcg_mttcg_enabled()) {
            /* create a thread per vCPU with TCG (MTTCG) */
            parallel_cpus = true;
            snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/TCG",
                 cpu->cpu_index);

            qemu_thread_create(cpu->thread, thread_name, qemu_tcg_cpu_thread_fn,
                               cpu, QEMU_THREAD_JOINABLE);

        } else {
            /* share a single thread for all cpus with TCG */
            snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "ALL CPUs/TCG");
            qemu_thread_create(cpu->thread, thread_name,
                               qemu_tcg_rr_cpu_thread_fn,
                               cpu, QEMU_THREAD_JOINABLE);

            single_tcg_halt_cond = cpu->halt_cond;
            single_tcg_cpu_thread = cpu->thread;
        }
#ifdef _WIN32
        cpu->hThread = qemu_thread_get_handle(cpu->thread);
#endif
        while (!cpu->created) {
            qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
        }
    } else {
        /* For non-MTTCG cases we share the thread */
        cpu->thread = single_tcg_cpu_thread;
        cpu->halt_cond = single_tcg_halt_cond;
    }
}

static void qemu_hax_start_vcpu(CPUState *cpu)
{
    char thread_name[VCPU_THREAD_NAME_SIZE];

    cpu->thread = g_malloc0(sizeof(QemuThread));
    cpu->halt_cond = g_malloc0(sizeof(QemuCond));
    qemu_cond_init(cpu->halt_cond);

    snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/HAX",
             cpu->cpu_index);
    qemu_thread_create(cpu->thread, thread_name, qemu_hax_cpu_thread_fn,
                       cpu, QEMU_THREAD_JOINABLE);
#ifdef _WIN32
    cpu->hThread = qemu_thread_get_handle(cpu->thread);
#endif
    while (!cpu->created) {
        qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
    }
}

static void qemu_kvm_start_vcpu(CPUState *cpu)
{
    char thread_name[VCPU_THREAD_NAME_SIZE];

    cpu->thread = g_malloc0(sizeof(QemuThread));
    cpu->halt_cond = g_malloc0(sizeof(QemuCond));
    qemu_cond_init(cpu->halt_cond);
    snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/KVM",
             cpu->cpu_index);
    qemu_thread_create(cpu->thread, thread_name, qemu_kvm_cpu_thread_fn,
                       cpu, QEMU_THREAD_JOINABLE);
    while (!cpu->created) {
        qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
    }
}

static void qemu_hvf_start_vcpu(CPUState *cpu)
{
    char thread_name[VCPU_THREAD_NAME_SIZE];

    /* HVF currently does not support TCG, and only runs in
     * unrestricted-guest mode. */
    assert(hvf_enabled());

    cpu->thread = g_malloc0(sizeof(QemuThread));
    cpu->halt_cond = g_malloc0(sizeof(QemuCond));
    qemu_cond_init(cpu->halt_cond);

    snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/HVF",
             cpu->cpu_index);
    qemu_thread_create(cpu->thread, thread_name, qemu_hvf_cpu_thread_fn,
                       cpu, QEMU_THREAD_JOINABLE);
    while (!cpu->created) {
        qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
    }
}

static void qemu_whpx_start_vcpu(CPUState *cpu)
{
    char thread_name[VCPU_THREAD_NAME_SIZE];

    cpu->thread = g_malloc0(sizeof(QemuThread));
    cpu->halt_cond = g_malloc0(sizeof(QemuCond));
    qemu_cond_init(cpu->halt_cond);
    snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/WHPX",
             cpu->cpu_index);
    qemu_thread_create(cpu->thread, thread_name, qemu_whpx_cpu_thread_fn,
                       cpu, QEMU_THREAD_JOINABLE);
#ifdef _WIN32
    cpu->hThread = qemu_thread_get_handle(cpu->thread);
#endif
    while (!cpu->created) {
        qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
    }
}

static void qemu_dummy_start_vcpu(CPUState *cpu)
{
    char thread_name[VCPU_THREAD_NAME_SIZE];

    cpu->thread = g_malloc0(sizeof(QemuThread));
    cpu->halt_cond = g_malloc0(sizeof(QemuCond));
    qemu_cond_init(cpu->halt_cond);
    snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/DUMMY",
             cpu->cpu_index);
    qemu_thread_create(cpu->thread, thread_name, qemu_dummy_cpu_thread_fn, cpu,
                       QEMU_THREAD_JOINABLE);
    while (!cpu->created) {
        qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
    }
}

void qemu_init_vcpu(CPUState *cpu)
{
    cpu->nr_cores = smp_cores;
    cpu->nr_threads = smp_threads;
    cpu->stopped = true;

    if (!cpu->as) {
        /* If the target cpu hasn't set up any address spaces itself,
         * give it the default one.
         */
        cpu->num_ases = 1;
        cpu_address_space_init(cpu, 0, "cpu-memory", cpu->memory);
    }

    if (kvm_enabled()) {
        qemu_kvm_start_vcpu(cpu);
    } else if (hax_enabled()) {
        qemu_hax_start_vcpu(cpu);
    } else if (hvf_enabled()) {
        qemu_hvf_start_vcpu(cpu);
    } else if (tcg_enabled()) {
        qemu_tcg_init_vcpu(cpu);
    } else if (whpx_enabled()) {
        qemu_whpx_start_vcpu(cpu);
    } else {
        qemu_dummy_start_vcpu(cpu);
    }
}

void cpu_stop_current(void)
{
    if (current_cpu) {
        qemu_cpu_stop(current_cpu, true);
    }
}

int vm_stop(RunState state)
{
    if (qemu_in_vcpu_thread()) {
        qemu_system_vmstop_request_prepare();
        qemu_system_vmstop_request(state);
        /*
         * FIXME: should not return to device code in case
         * vm_stop() has been requested.
         */
        cpu_stop_current();
        return 0;
    }

    return do_vm_stop(state);
}

/**
 * Prepare for (re)starting the VM.
 * Returns -1 if the vCPUs are not to be restarted (e.g. if they are already
 * running or in case of an error condition), 0 otherwise.
 */
int vm_prepare_start(void)
{
    RunState requested;
    int res = 0;

    qemu_vmstop_requested(&requested);
    if (runstate_is_running() && requested == RUN_STATE__MAX) {
        return -1;
    }

    /* Ensure that a STOP/RESUME pair of events is emitted if a
     * vmstop request was pending.  The BLOCK_IO_ERROR event, for
     * example, according to documentation is always followed by
     * the STOP event.
     */
    if (runstate_is_running()) {
        qapi_event_send_stop(&error_abort);
        res = -1;
    } else {
        replay_enable_events();
        cpu_enable_ticks();
        runstate_set(RUN_STATE_RUNNING);
        vm_state_notify(1, RUN_STATE_RUNNING);
    }

    /* We are sending this now, but the CPUs will be resumed shortly later */
    qapi_event_send_resume(&error_abort);
    return res;
}

void vm_start(void)
{
    if (!vm_prepare_start()) {
        resume_all_vcpus();
    }
}

/* does a state transition even if the VM is already stopped,
   current state is forgotten forever */
int vm_stop_force_state(RunState state)
{
    if (runstate_is_running()) {
        return vm_stop(state);
    } else {
        runstate_set(state);

        bdrv_drain_all();
        /* Make sure to return an error if the flush in a previous vm_stop()
         * failed. */
        return bdrv_flush_all();
    }
}

void list_cpus(FILE *f, fprintf_function cpu_fprintf, const char *optarg)
{
    /* XXX: implement xxx_cpu_list for targets that still miss it */
#if defined(cpu_list)
    cpu_list(f, cpu_fprintf);
#endif
}

CpuInfoList *qmp_query_cpus(Error **errp)
{
    MachineState *ms = MACHINE(qdev_get_machine());
    MachineClass *mc = MACHINE_GET_CLASS(ms);
    CpuInfoList *head = NULL, *cur_item = NULL;
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        CpuInfoList *info;
#if defined(TARGET_I386)
        X86CPU *x86_cpu = X86_CPU(cpu);
        CPUX86State *env = &x86_cpu->env;
#elif defined(TARGET_PPC)
        PowerPCCPU *ppc_cpu = POWERPC_CPU(cpu);
        CPUPPCState *env = &ppc_cpu->env;
#elif defined(TARGET_SPARC)
        SPARCCPU *sparc_cpu = SPARC_CPU(cpu);
        CPUSPARCState *env = &sparc_cpu->env;
#elif defined(TARGET_MIPS)
        MIPSCPU *mips_cpu = MIPS_CPU(cpu);
        CPUMIPSState *env = &mips_cpu->env;
#elif defined(TARGET_TRICORE)
        TriCoreCPU *tricore_cpu = TRICORE_CPU(cpu);
        CPUTriCoreState *env = &tricore_cpu->env;
#elif defined(TARGET_S390X)
        S390CPU *s390_cpu = S390_CPU(cpu);
        CPUS390XState *env = &s390_cpu->env;
#endif

        cpu_synchronize_state(cpu);

        info = g_malloc0(sizeof(*info));
        info->value = g_malloc0(sizeof(*info->value));
        info->value->CPU = cpu->cpu_index;
        info->value->current = (cpu == first_cpu);
        info->value->halted = cpu->halted;
        info->value->qom_path = object_get_canonical_path(OBJECT(cpu));
        info->value->thread_id = cpu->thread_id;
#if defined(TARGET_I386)
        info->value->arch = CPU_INFO_ARCH_X86;
        info->value->u.x86.pc = env->eip + env->segs[R_CS].base;
#elif defined(TARGET_PPC)
        info->value->arch = CPU_INFO_ARCH_PPC;
        info->value->u.ppc.nip = env->nip;
#elif defined(TARGET_SPARC)
        info->value->arch = CPU_INFO_ARCH_SPARC;
        info->value->u.q_sparc.pc = env->pc;
        info->value->u.q_sparc.npc = env->npc;
#elif defined(TARGET_MIPS)
        info->value->arch = CPU_INFO_ARCH_MIPS;
        info->value->u.q_mips.PC = env->active_tc.PC;
#elif defined(TARGET_TRICORE)
        info->value->arch = CPU_INFO_ARCH_TRICORE;
        info->value->u.tricore.PC = env->PC;
#elif defined(TARGET_S390X)
        info->value->arch = CPU_INFO_ARCH_S390;
        info->value->u.s390.cpu_state = env->cpu_state;
#else
        info->value->arch = CPU_INFO_ARCH_OTHER;
#endif
        info->value->has_props = !!mc->cpu_index_to_instance_props;
        if (info->value->has_props) {
            CpuInstanceProperties *props;
            props = g_malloc0(sizeof(*props));
            *props = mc->cpu_index_to_instance_props(ms, cpu->cpu_index);
            info->value->props = props;
        }

        /* XXX: waiting for the qapi to support GSList */
        if (!cur_item) {
            head = cur_item = info;
        } else {
            cur_item->next = info;
            cur_item = info;
        }
    }

    return head;
}

/*
 * fast means: we NEVER interrupt vCPU threads to retrieve
 * information from KVM.
 */
CpuInfoFastList *qmp_query_cpus_fast(Error **errp)
{
    MachineState *ms = MACHINE(qdev_get_machine());
    MachineClass *mc = MACHINE_GET_CLASS(ms);
    CpuInfoFastList *head = NULL, *cur_item = NULL;
    CPUState *cpu;
#if defined(TARGET_S390X)
    S390CPU *s390_cpu;
    CPUS390XState *env;
#endif

    CPU_FOREACH(cpu) {
        CpuInfoFastList *info = g_malloc0(sizeof(*info));
        info->value = g_malloc0(sizeof(*info->value));

        info->value->cpu_index = cpu->cpu_index;
        info->value->qom_path = object_get_canonical_path(OBJECT(cpu));
        info->value->thread_id = cpu->thread_id;

        info->value->has_props = !!mc->cpu_index_to_instance_props;
        if (info->value->has_props) {
            CpuInstanceProperties *props;
            props = g_malloc0(sizeof(*props));
            *props = mc->cpu_index_to_instance_props(ms, cpu->cpu_index);
            info->value->props = props;
        }

#if defined(TARGET_S390X)
        s390_cpu = S390_CPU(cpu);
        env = &s390_cpu->env;
        info->value->arch = CPU_INFO_ARCH_S390;
        info->value->u.s390.cpu_state = env->cpu_state;
#endif
        if (!cur_item) {
            head = cur_item = info;
        } else {
            cur_item->next = info;
            cur_item = info;
        }
    }

    return head;
}

void qmp_memsave(int64_t addr, int64_t size, const char *filename,
                 bool has_cpu, int64_t cpu_index, Error **errp)
{
    FILE *f;
    uint32_t l;
    CPUState *cpu;
    uint8_t buf[1024];
    int64_t orig_addr = addr, orig_size = size;

    if (!has_cpu) {
        cpu_index = 0;
    }

    cpu = qemu_get_cpu(cpu_index);
    if (cpu == NULL) {
        error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "cpu-index",
                   "a CPU number");
        return;
    }

    f = fopen(filename, "wb");
    if (!f) {
        error_setg_file_open(errp, errno, filename);
        return;
    }

    while (size != 0) {
        l = sizeof(buf);
        if (l > size)
            l = size;
        if (cpu_memory_rw_debug(cpu, addr, buf, l, 0) != 0) {
            error_setg(errp, "Invalid addr 0x%016" PRIx64 "/size %" PRId64
                             " specified", orig_addr, orig_size);
            goto exit;
        }
        if (fwrite(buf, 1, l, f) != l) {
            error_setg(errp, QERR_IO_ERROR);
            goto exit;
        }
        addr += l;
        size -= l;
    }

exit:
    fclose(f);
}

void qmp_pmemsave(int64_t addr, int64_t size, const char *filename,
                  Error **errp)
{
    FILE *f;
    uint32_t l;
    uint8_t buf[1024];

    f = fopen(filename, "wb");
    if (!f) {
        error_setg_file_open(errp, errno, filename);
        return;
    }

    while (size != 0) {
        l = sizeof(buf);
        if (l > size)
            l = size;
        cpu_physical_memory_read(addr, buf, l);
        if (fwrite(buf, 1, l, f) != l) {
            error_setg(errp, QERR_IO_ERROR);
            goto exit;
        }
        addr += l;
        size -= l;
    }

exit:
    fclose(f);
}

void qmp_inject_nmi(Error **errp)
{
    nmi_monitor_handle(monitor_get_cpu_index(), errp);
}

void dump_drift_info(FILE *f, fprintf_function cpu_fprintf)
{
    if (!use_icount) {
        return;
    }

    cpu_fprintf(f, "Host - Guest clock  %"PRIi64" ms\n",
                (cpu_get_clock() - cpu_get_icount())/SCALE_MS);
    if (icount_align_option) {
        cpu_fprintf(f, "Max guest delay     %"PRIi64" ms\n", -max_delay/SCALE_MS);
        cpu_fprintf(f, "Max guest advance   %"PRIi64" ms\n", max_advance/SCALE_MS);
    } else {
        cpu_fprintf(f, "Max guest delay     NA\n");
        cpu_fprintf(f, "Max guest advance   NA\n");
    }
}