aboutsummaryrefslogtreecommitdiff
path: root/target-i386/kvm.c
blob: 8b868ad40a79f9f68d6fa89893a11b03c56ac374 (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
/*
 * QEMU KVM support
 *
 * Copyright (C) 2006-2008 Qumranet Technologies
 * Copyright IBM, Corp. 2008
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 *
 */

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

#include <linux/kvm.h>

#include "qemu-common.h"
#include "sysemu.h"
#include "kvm.h"
#include "cpu.h"
#include "gdbstub.h"
#include "host-utils.h"
#include "hw/pc.h"
#include "hw/apic.h"
#include "ioport.h"
#include "kvm_x86.h"

#ifdef CONFIG_KVM_PARA
#include <linux/kvm_para.h>
#endif
//
//#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 MSR_KVM_WALL_CLOCK  0x11
#define MSR_KVM_SYSTEM_TIME 0x12

#ifndef BUS_MCEERR_AR
#define BUS_MCEERR_AR 4
#endif
#ifndef BUS_MCEERR_AO
#define BUS_MCEERR_AO 5
#endif

static int lm_capable_kernel;

#ifdef KVM_CAP_EXT_CPUID

static struct kvm_cpuid2 *try_get_cpuid(KVMState *s, int max)
{
    struct kvm_cpuid2 *cpuid;
    int r, size;

    size = sizeof(*cpuid) + max * sizeof(*cpuid->entries);
    cpuid = (struct kvm_cpuid2 *)qemu_mallocz(size);
    cpuid->nent = max;
    r = kvm_ioctl(s, KVM_GET_SUPPORTED_CPUID, cpuid);
    if (r == 0 && cpuid->nent >= max) {
        r = -E2BIG;
    }
    if (r < 0) {
        if (r == -E2BIG) {
            qemu_free(cpuid);
            return NULL;
        } else {
            fprintf(stderr, "KVM_GET_SUPPORTED_CPUID failed: %s\n",
                    strerror(-r));
            exit(1);
        }
    }
    return cpuid;
}

uint32_t kvm_arch_get_supported_cpuid(CPUState *env, uint32_t function,
                                      uint32_t index, int reg)
{
    struct kvm_cpuid2 *cpuid;
    int i, max;
    uint32_t ret = 0;
    uint32_t cpuid_1_edx;

    if (!kvm_check_extension(env->kvm_state, KVM_CAP_EXT_CPUID)) {
        return -1U;
    }

    max = 1;
    while ((cpuid = try_get_cpuid(env->kvm_state, max)) == NULL) {
        max *= 2;
    }

    for (i = 0; i < cpuid->nent; ++i) {
        if (cpuid->entries[i].function == function &&
            cpuid->entries[i].index == index) {
            switch (reg) {
            case R_EAX:
                ret = cpuid->entries[i].eax;
                break;
            case R_EBX:
                ret = cpuid->entries[i].ebx;
                break;
            case R_ECX:
                ret = cpuid->entries[i].ecx;
                break;
            case R_EDX:
                ret = cpuid->entries[i].edx;
                switch (function) {
                case 1:
                    /* KVM before 2.6.30 misreports the following features */
                    ret |= CPUID_MTRR | CPUID_PAT | CPUID_MCE | CPUID_MCA;
                    break;
                case 0x80000001:
                    /* On Intel, kvm returns cpuid according to the Intel spec,
                     * so add missing bits according to the AMD spec:
                     */
                    cpuid_1_edx = kvm_arch_get_supported_cpuid(env, 1, 0, R_EDX);
                    ret |= cpuid_1_edx & 0x183f7ff;
                    break;
                }
                break;
            }
        }
    }

    qemu_free(cpuid);

    return ret;
}

#else

uint32_t kvm_arch_get_supported_cpuid(CPUState *env, uint32_t function,
                                      uint32_t index, int reg)
{
    return -1U;
}

#endif

#ifdef CONFIG_KVM_PARA
struct kvm_para_features {
        int cap;
        int feature;
} para_features[] = {
#ifdef KVM_CAP_CLOCKSOURCE
        { KVM_CAP_CLOCKSOURCE, KVM_FEATURE_CLOCKSOURCE },
#endif
#ifdef KVM_CAP_NOP_IO_DELAY
        { KVM_CAP_NOP_IO_DELAY, KVM_FEATURE_NOP_IO_DELAY },
#endif
#ifdef KVM_CAP_PV_MMU
        { KVM_CAP_PV_MMU, KVM_FEATURE_MMU_OP },
#endif
#ifdef KVM_CAP_ASYNC_PF
        { KVM_CAP_ASYNC_PF, KVM_FEATURE_ASYNC_PF },
#endif
        { -1, -1 }
};

static int get_para_features(CPUState *env)
{
        int i, features = 0;

        for (i = 0; i < ARRAY_SIZE(para_features) - 1; i++) {
                if (kvm_check_extension(env->kvm_state, para_features[i].cap))
                        features |= (1 << para_features[i].feature);
        }

        return features;
}
#endif

#ifdef KVM_CAP_MCE
static int kvm_get_mce_cap_supported(KVMState *s, uint64_t *mce_cap,
                                     int *max_banks)
{
    int r;

    r = kvm_check_extension(s, KVM_CAP_MCE);
    if (r > 0) {
        *max_banks = r;
        return kvm_ioctl(s, KVM_X86_GET_MCE_CAP_SUPPORTED, mce_cap);
    }
    return -ENOSYS;
}

static int kvm_setup_mce(CPUState *env, uint64_t *mcg_cap)
{
    return kvm_vcpu_ioctl(env, KVM_X86_SETUP_MCE, mcg_cap);
}

static int kvm_set_mce(CPUState *env, struct kvm_x86_mce *m)
{
    return kvm_vcpu_ioctl(env, KVM_X86_SET_MCE, m);
}

static int kvm_get_msr(CPUState *env, struct kvm_msr_entry *msrs, int n)
{
    struct kvm_msrs *kmsrs = qemu_malloc(sizeof *kmsrs + n * sizeof *msrs);
    int r;

    kmsrs->nmsrs = n;
    memcpy(kmsrs->entries, msrs, n * sizeof *msrs);
    r = kvm_vcpu_ioctl(env, KVM_GET_MSRS, kmsrs);
    memcpy(msrs, kmsrs->entries, n * sizeof *msrs);
    free(kmsrs);
    return r;
}

/* FIXME: kill this and kvm_get_msr, use env->mcg_status instead */
static int kvm_mce_in_exception(CPUState *env)
{
    struct kvm_msr_entry msr_mcg_status = {
        .index = MSR_MCG_STATUS,
    };
    int r;

    r = kvm_get_msr(env, &msr_mcg_status, 1);
    if (r == -1 || r == 0) {
        return -1;
    }
    return !!(msr_mcg_status.data & MCG_STATUS_MCIP);
}

struct kvm_x86_mce_data
{
    CPUState *env;
    struct kvm_x86_mce *mce;
    int abort_on_error;
};

static void kvm_do_inject_x86_mce(void *_data)
{
    struct kvm_x86_mce_data *data = _data;
    int r;

    /* If there is an MCE exception being processed, ignore this SRAO MCE */
    if ((data->env->mcg_cap & MCG_SER_P) &&
        !(data->mce->status & MCI_STATUS_AR)) {
        r = kvm_mce_in_exception(data->env);
        if (r == -1) {
            fprintf(stderr, "Failed to get MCE status\n");
        } else if (r) {
            return;
        }
    }

    r = kvm_set_mce(data->env, data->mce);
    if (r < 0) {
        perror("kvm_set_mce FAILED");
        if (data->abort_on_error) {
            abort();
        }
    }
}

static void kvm_mce_broadcast_rest(CPUState *env);
#endif

void kvm_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,
                        uint64_t mcg_status, uint64_t addr, uint64_t misc,
                        int flag)
{
#ifdef KVM_CAP_MCE
    struct kvm_x86_mce mce = {
        .bank = bank,
        .status = status,
        .mcg_status = mcg_status,
        .addr = addr,
        .misc = misc,
    };
    struct kvm_x86_mce_data data = {
            .env = cenv,
            .mce = &mce,
    };

    if (!cenv->mcg_cap) {
        fprintf(stderr, "MCE support is not enabled!\n");
        return;
    }

    if (flag & MCE_BROADCAST) {
        kvm_mce_broadcast_rest(cenv);
    }

    run_on_cpu(cenv, kvm_do_inject_x86_mce, &data);
#else
    if (flag & ABORT_ON_ERROR) {
        abort();
    }
#endif
}

int kvm_arch_init_vcpu(CPUState *env)
{
    struct {
        struct kvm_cpuid2 cpuid;
        struct kvm_cpuid_entry2 entries[100];
    } __attribute__((packed)) cpuid_data;
    uint32_t limit, i, j, cpuid_i;
    uint32_t unused;
    struct kvm_cpuid_entry2 *c;
#ifdef KVM_CPUID_SIGNATURE
    uint32_t signature[3];
#endif

    env->mp_state = KVM_MP_STATE_RUNNABLE;

    env->cpuid_features &= kvm_arch_get_supported_cpuid(env, 1, 0, R_EDX);

    i = env->cpuid_ext_features & CPUID_EXT_HYPERVISOR;
    env->cpuid_ext_features &= kvm_arch_get_supported_cpuid(env, 1, 0, R_ECX);
    env->cpuid_ext_features |= i;

    env->cpuid_ext2_features &= kvm_arch_get_supported_cpuid(env, 0x80000001,
                                                             0, R_EDX);
    env->cpuid_ext3_features &= kvm_arch_get_supported_cpuid(env, 0x80000001,
                                                             0, R_ECX);
    env->cpuid_svm_features  &= kvm_arch_get_supported_cpuid(env, 0x8000000A,
                                                             0, R_EDX);


    cpuid_i = 0;

#ifdef CONFIG_KVM_PARA
    /* Paravirtualization CPUIDs */
    memcpy(signature, "KVMKVMKVM\0\0\0", 12);
    c = &cpuid_data.entries[cpuid_i++];
    memset(c, 0, sizeof(*c));
    c->function = KVM_CPUID_SIGNATURE;
    c->eax = 0;
    c->ebx = signature[0];
    c->ecx = signature[1];
    c->edx = signature[2];

    c = &cpuid_data.entries[cpuid_i++];
    memset(c, 0, sizeof(*c));
    c->function = KVM_CPUID_FEATURES;
    c->eax = env->cpuid_kvm_features & get_para_features(env);
#endif

    cpu_x86_cpuid(env, 0, 0, &limit, &unused, &unused, &unused);

    for (i = 0; i <= limit; i++) {
        c = &cpuid_data.entries[cpuid_i++];

        switch (i) {
        case 2: {
            /* Keep reading function 2 till all the input is received */
            int times;

            c->function = i;
            c->flags = KVM_CPUID_FLAG_STATEFUL_FUNC |
                       KVM_CPUID_FLAG_STATE_READ_NEXT;
            cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx);
            times = c->eax & 0xff;

            for (j = 1; j < times; ++j) {
                c = &cpuid_data.entries[cpuid_i++];
                c->function = i;
                c->flags = KVM_CPUID_FLAG_STATEFUL_FUNC;
                cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx);
            }
            break;
        }
        case 4:
        case 0xb:
        case 0xd:
            for (j = 0; ; j++) {
                c->function = i;
                c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
                c->index = j;
                cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx);

                if (i == 4 && c->eax == 0)
                    break;
                if (i == 0xb && !(c->ecx & 0xff00))
                    break;
                if (i == 0xd && c->eax == 0)
                    break;

                c = &cpuid_data.entries[cpuid_i++];
            }
            break;
        default:
            c->function = i;
            c->flags = 0;
            cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx);
            break;
        }
    }
    cpu_x86_cpuid(env, 0x80000000, 0, &limit, &unused, &unused, &unused);

    for (i = 0x80000000; i <= limit; i++) {
        c = &cpuid_data.entries[cpuid_i++];

        c->function = i;
        c->flags = 0;
        cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx);
    }

    cpuid_data.cpuid.nent = cpuid_i;

#ifdef KVM_CAP_MCE
    if (((env->cpuid_version >> 8)&0xF) >= 6
        && (env->cpuid_features&(CPUID_MCE|CPUID_MCA)) == (CPUID_MCE|CPUID_MCA)
        && kvm_check_extension(env->kvm_state, KVM_CAP_MCE) > 0) {
        uint64_t mcg_cap;
        int banks;

        if (kvm_get_mce_cap_supported(env->kvm_state, &mcg_cap, &banks))
            perror("kvm_get_mce_cap_supported FAILED");
        else {
            if (banks > MCE_BANKS_DEF)
                banks = MCE_BANKS_DEF;
            mcg_cap &= MCE_CAP_DEF;
            mcg_cap |= banks;
            if (kvm_setup_mce(env, &mcg_cap))
                perror("kvm_setup_mce FAILED");
            else
                env->mcg_cap = mcg_cap;
        }
    }
#endif

    return kvm_vcpu_ioctl(env, KVM_SET_CPUID2, &cpuid_data);
}

void kvm_arch_reset_vcpu(CPUState *env)
{
    env->exception_injected = -1;
    env->interrupt_injected = -1;
    env->nmi_injected = 0;
    env->nmi_pending = 0;
    if (kvm_irqchip_in_kernel()) {
        env->mp_state = cpu_is_bsp(env) ? KVM_MP_STATE_RUNNABLE :
                                          KVM_MP_STATE_UNINITIALIZED;
    } else {
        env->mp_state = KVM_MP_STATE_RUNNABLE;
    }
}

int has_msr_star;
int has_msr_hsave_pa;

static void kvm_supported_msrs(CPUState *env)
{
    static int kvm_supported_msrs;
    int ret;

    /* first time */
    if (kvm_supported_msrs == 0) {
        struct kvm_msr_list msr_list, *kvm_msr_list;

        kvm_supported_msrs = -1;

        /* Obtain MSR list from KVM.  These are the MSRs that we must
         * save/restore */
        msr_list.nmsrs = 0;
        ret = kvm_ioctl(env->kvm_state, KVM_GET_MSR_INDEX_LIST, &msr_list);
        if (ret < 0 && ret != -E2BIG) {
            return;
        }
        /* Old kernel modules had a bug and could write beyond the provided
           memory. Allocate at least a safe amount of 1K. */
        kvm_msr_list = qemu_mallocz(MAX(1024, sizeof(msr_list) +
                                              msr_list.nmsrs *
                                              sizeof(msr_list.indices[0])));

        kvm_msr_list->nmsrs = msr_list.nmsrs;
        ret = kvm_ioctl(env->kvm_state, KVM_GET_MSR_INDEX_LIST, kvm_msr_list);
        if (ret >= 0) {
            int i;

            for (i = 0; i < kvm_msr_list->nmsrs; i++) {
                if (kvm_msr_list->indices[i] == MSR_STAR) {
                    has_msr_star = 1;
                    continue;
                }
                if (kvm_msr_list->indices[i] == MSR_VM_HSAVE_PA) {
                    has_msr_hsave_pa = 1;
                    continue;
                }
            }
        }

        free(kvm_msr_list);
    }

    return;
}

static int kvm_has_msr_hsave_pa(CPUState *env)
{
    kvm_supported_msrs(env);
    return has_msr_hsave_pa;
}

static int kvm_has_msr_star(CPUState *env)
{
    kvm_supported_msrs(env);
    return has_msr_star;
}

static int kvm_init_identity_map_page(KVMState *s)
{
#ifdef KVM_CAP_SET_IDENTITY_MAP_ADDR
    int ret;
    uint64_t addr = 0xfffbc000;

    if (!kvm_check_extension(s, KVM_CAP_SET_IDENTITY_MAP_ADDR)) {
        return 0;
    }

    ret = kvm_vm_ioctl(s, KVM_SET_IDENTITY_MAP_ADDR, &addr);
    if (ret < 0) {
        fprintf(stderr, "kvm_set_identity_map_addr: %s\n", strerror(ret));
        return ret;
    }
#endif
    return 0;
}

int kvm_arch_init(KVMState *s, int smp_cpus)
{
    int ret;

    struct utsname utsname;

    uname(&utsname);
    lm_capable_kernel = strcmp(utsname.machine, "x86_64") == 0;

    /* create vm86 tss.  KVM uses vm86 mode to emulate 16-bit code
     * directly.  In order to use vm86 mode, a TSS is needed.  Since this
     * must be part of guest physical memory, we need to allocate it.  Older
     * versions of KVM just assumed that it would be at the end of physical
     * memory but that doesn't work with more than 4GB of memory.  We simply
     * refuse to work with those older versions of KVM. */
    ret = kvm_check_extension(s, KVM_CAP_SET_TSS_ADDR);
    if (ret <= 0) {
        fprintf(stderr, "kvm does not support KVM_CAP_SET_TSS_ADDR\n");
        return ret;
    }

    /* this address is 3 pages before the bios, and the bios should present
     * as unavaible memory.  FIXME, need to ensure the e820 map deals with
     * this?
     */
    /*
     * Tell fw_cfg to notify the BIOS to reserve the range.
     */
    if (e820_add_entry(0xfffbc000, 0x4000, E820_RESERVED) < 0) {
        perror("e820_add_entry() table is full");
        exit(1);
    }
    ret = kvm_vm_ioctl(s, KVM_SET_TSS_ADDR, 0xfffbd000);
    if (ret < 0) {
        return ret;
    }

    return kvm_init_identity_map_page(s);
}
                    
static void set_v8086_seg(struct kvm_segment *lhs, const SegmentCache *rhs)
{
    lhs->selector = rhs->selector;
    lhs->base = rhs->base;
    lhs->limit = rhs->limit;
    lhs->type = 3;
    lhs->present = 1;
    lhs->dpl = 3;
    lhs->db = 0;
    lhs->s = 1;
    lhs->l = 0;
    lhs->g = 0;
    lhs->avl = 0;
    lhs->unusable = 0;
}

static void set_seg(struct kvm_segment *lhs, const SegmentCache *rhs)
{
    unsigned flags = rhs->flags;
    lhs->selector = rhs->selector;
    lhs->base = rhs->base;
    lhs->limit = rhs->limit;
    lhs->type = (flags >> DESC_TYPE_SHIFT) & 15;
    lhs->present = (flags & DESC_P_MASK) != 0;
    lhs->dpl = rhs->selector & 3;
    lhs->db = (flags >> DESC_B_SHIFT) & 1;
    lhs->s = (flags & DESC_S_MASK) != 0;
    lhs->l = (flags >> DESC_L_SHIFT) & 1;
    lhs->g = (flags & DESC_G_MASK) != 0;
    lhs->avl = (flags & DESC_AVL_MASK) != 0;
    lhs->unusable = 0;
}

static void get_seg(SegmentCache *lhs, const struct kvm_segment *rhs)
{
    lhs->selector = rhs->selector;
    lhs->base = rhs->base;
    lhs->limit = rhs->limit;
    lhs->flags =
	(rhs->type << DESC_TYPE_SHIFT)
	| (rhs->present * DESC_P_MASK)
	| (rhs->dpl << DESC_DPL_SHIFT)
	| (rhs->db << DESC_B_SHIFT)
	| (rhs->s * DESC_S_MASK)
	| (rhs->l << DESC_L_SHIFT)
	| (rhs->g * DESC_G_MASK)
	| (rhs->avl * DESC_AVL_MASK);
}

static void kvm_getput_reg(__u64 *kvm_reg, target_ulong *qemu_reg, int set)
{
    if (set)
        *kvm_reg = *qemu_reg;
    else
        *qemu_reg = *kvm_reg;
}

static int kvm_getput_regs(CPUState *env, int set)
{
    struct kvm_regs regs;
    int ret = 0;

    if (!set) {
        ret = kvm_vcpu_ioctl(env, KVM_GET_REGS, &regs);
        if (ret < 0)
            return ret;
    }

    kvm_getput_reg(&regs.rax, &env->regs[R_EAX], set);
    kvm_getput_reg(&regs.rbx, &env->regs[R_EBX], set);
    kvm_getput_reg(&regs.rcx, &env->regs[R_ECX], set);
    kvm_getput_reg(&regs.rdx, &env->regs[R_EDX], set);
    kvm_getput_reg(&regs.rsi, &env->regs[R_ESI], set);
    kvm_getput_reg(&regs.rdi, &env->regs[R_EDI], set);
    kvm_getput_reg(&regs.rsp, &env->regs[R_ESP], set);
    kvm_getput_reg(&regs.rbp, &env->regs[R_EBP], set);
#ifdef TARGET_X86_64
    kvm_getput_reg(&regs.r8, &env->regs[8], set);
    kvm_getput_reg(&regs.r9, &env->regs[9], set);
    kvm_getput_reg(&regs.r10, &env->regs[10], set);
    kvm_getput_reg(&regs.r11, &env->regs[11], set);
    kvm_getput_reg(&regs.r12, &env->regs[12], set);
    kvm_getput_reg(&regs.r13, &env->regs[13], set);
    kvm_getput_reg(&regs.r14, &env->regs[14], set);
    kvm_getput_reg(&regs.r15, &env->regs[15], set);
#endif

    kvm_getput_reg(&regs.rflags, &env->eflags, set);
    kvm_getput_reg(&regs.rip, &env->eip, set);

    if (set)
        ret = kvm_vcpu_ioctl(env, KVM_SET_REGS, &regs);

    return ret;
}

static int kvm_put_fpu(CPUState *env)
{
    struct kvm_fpu fpu;
    int i;

    memset(&fpu, 0, sizeof fpu);
    fpu.fsw = env->fpus & ~(7 << 11);
    fpu.fsw |= (env->fpstt & 7) << 11;
    fpu.fcw = env->fpuc;
    for (i = 0; i < 8; ++i)
	fpu.ftwx |= (!env->fptags[i]) << i;
    memcpy(fpu.fpr, env->fpregs, sizeof env->fpregs);
    memcpy(fpu.xmm, env->xmm_regs, sizeof env->xmm_regs);
    fpu.mxcsr = env->mxcsr;

    return kvm_vcpu_ioctl(env, KVM_SET_FPU, &fpu);
}

#ifdef KVM_CAP_XSAVE
#define XSAVE_CWD_RIP     2
#define XSAVE_CWD_RDP     4
#define XSAVE_MXCSR       6
#define XSAVE_ST_SPACE    8
#define XSAVE_XMM_SPACE   40
#define XSAVE_XSTATE_BV   128
#define XSAVE_YMMH_SPACE  144
#endif

static int kvm_put_xsave(CPUState *env)
{
#ifdef KVM_CAP_XSAVE
    int i, r;
    struct kvm_xsave* xsave;
    uint16_t cwd, swd, twd, fop;

    if (!kvm_has_xsave())
        return kvm_put_fpu(env);

    xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
    memset(xsave, 0, sizeof(struct kvm_xsave));
    cwd = swd = twd = fop = 0;
    swd = env->fpus & ~(7 << 11);
    swd |= (env->fpstt & 7) << 11;
    cwd = env->fpuc;
    for (i = 0; i < 8; ++i)
        twd |= (!env->fptags[i]) << i;
    xsave->region[0] = (uint32_t)(swd << 16) + cwd;
    xsave->region[1] = (uint32_t)(fop << 16) + twd;
    memcpy(&xsave->region[XSAVE_ST_SPACE], env->fpregs,
            sizeof env->fpregs);
    memcpy(&xsave->region[XSAVE_XMM_SPACE], env->xmm_regs,
            sizeof env->xmm_regs);
    xsave->region[XSAVE_MXCSR] = env->mxcsr;
    *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV] = env->xstate_bv;
    memcpy(&xsave->region[XSAVE_YMMH_SPACE], env->ymmh_regs,
            sizeof env->ymmh_regs);
    r = kvm_vcpu_ioctl(env, KVM_SET_XSAVE, xsave);
    qemu_free(xsave);
    return r;
#else
    return kvm_put_fpu(env);
#endif
}

static int kvm_put_xcrs(CPUState *env)
{
#ifdef KVM_CAP_XCRS
    struct kvm_xcrs xcrs;

    if (!kvm_has_xcrs())
        return 0;

    xcrs.nr_xcrs = 1;
    xcrs.flags = 0;
    xcrs.xcrs[0].xcr = 0;
    xcrs.xcrs[0].value = env->xcr0;
    return kvm_vcpu_ioctl(env, KVM_SET_XCRS, &xcrs);
#else
    return 0;
#endif
}

static int kvm_put_sregs(CPUState *env)
{
    struct kvm_sregs sregs;

    memset(sregs.interrupt_bitmap, 0, sizeof(sregs.interrupt_bitmap));
    if (env->interrupt_injected >= 0) {
        sregs.interrupt_bitmap[env->interrupt_injected / 64] |=
                (uint64_t)1 << (env->interrupt_injected % 64);
    }

    if ((env->eflags & VM_MASK)) {
	    set_v8086_seg(&sregs.cs, &env->segs[R_CS]);
	    set_v8086_seg(&sregs.ds, &env->segs[R_DS]);
	    set_v8086_seg(&sregs.es, &env->segs[R_ES]);
	    set_v8086_seg(&sregs.fs, &env->segs[R_FS]);
	    set_v8086_seg(&sregs.gs, &env->segs[R_GS]);
	    set_v8086_seg(&sregs.ss, &env->segs[R_SS]);
    } else {
	    set_seg(&sregs.cs, &env->segs[R_CS]);
	    set_seg(&sregs.ds, &env->segs[R_DS]);
	    set_seg(&sregs.es, &env->segs[R_ES]);
	    set_seg(&sregs.fs, &env->segs[R_FS]);
	    set_seg(&sregs.gs, &env->segs[R_GS]);
	    set_seg(&sregs.ss, &env->segs[R_SS]);

	    if (env->cr[0] & CR0_PE_MASK) {
		/* force ss cpl to cs cpl */
		sregs.ss.selector = (sregs.ss.selector & ~3) |
			(sregs.cs.selector & 3);
		sregs.ss.dpl = sregs.ss.selector & 3;
	    }
    }

    set_seg(&sregs.tr, &env->tr);
    set_seg(&sregs.ldt, &env->ldt);

    sregs.idt.limit = env->idt.limit;
    sregs.idt.base = env->idt.base;
    sregs.gdt.limit = env->gdt.limit;
    sregs.gdt.base = env->gdt.base;

    sregs.cr0 = env->cr[0];
    sregs.cr2 = env->cr[2];
    sregs.cr3 = env->cr[3];
    sregs.cr4 = env->cr[4];

    sregs.cr8 = cpu_get_apic_tpr(env->apic_state);
    sregs.apic_base = cpu_get_apic_base(env->apic_state);

    sregs.efer = env->efer;

    return kvm_vcpu_ioctl(env, KVM_SET_SREGS, &sregs);
}

static void kvm_msr_entry_set(struct kvm_msr_entry *entry,
                              uint32_t index, uint64_t value)
{
    entry->index = index;
    entry->data = value;
}

static int kvm_put_msrs(CPUState *env, int level)
{
    struct {
        struct kvm_msrs info;
        struct kvm_msr_entry entries[100];
    } msr_data;
    struct kvm_msr_entry *msrs = msr_data.entries;
    int n = 0;

    kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_CS, env->sysenter_cs);
    kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_ESP, env->sysenter_esp);
    kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_EIP, env->sysenter_eip);
    if (kvm_has_msr_star(env))
	kvm_msr_entry_set(&msrs[n++], MSR_STAR, env->star);
    if (kvm_has_msr_hsave_pa(env))
        kvm_msr_entry_set(&msrs[n++], MSR_VM_HSAVE_PA, env->vm_hsave);
#ifdef TARGET_X86_64
    if (lm_capable_kernel) {
        kvm_msr_entry_set(&msrs[n++], MSR_CSTAR, env->cstar);
        kvm_msr_entry_set(&msrs[n++], MSR_KERNELGSBASE, env->kernelgsbase);
        kvm_msr_entry_set(&msrs[n++], MSR_FMASK, env->fmask);
        kvm_msr_entry_set(&msrs[n++], MSR_LSTAR, env->lstar);
    }
#endif
    if (level == KVM_PUT_FULL_STATE) {
        /*
         * KVM is yet unable to synchronize TSC values of multiple VCPUs on
         * writeback. Until this is fixed, we only write the offset to SMP
         * guests after migration, desynchronizing the VCPUs, but avoiding
         * huge jump-backs that would occur without any writeback at all.
         */
        if (smp_cpus == 1 || env->tsc != 0) {
            kvm_msr_entry_set(&msrs[n++], MSR_IA32_TSC, env->tsc);
        }
        kvm_msr_entry_set(&msrs[n++], MSR_KVM_SYSTEM_TIME,
                          env->system_time_msr);
        kvm_msr_entry_set(&msrs[n++], MSR_KVM_WALL_CLOCK, env->wall_clock_msr);
#ifdef KVM_CAP_ASYNC_PF
        kvm_msr_entry_set(&msrs[n++], MSR_KVM_ASYNC_PF_EN, env->async_pf_en_msr);
#endif
    }
#ifdef KVM_CAP_MCE
    if (env->mcg_cap) {
        int i;
        if (level == KVM_PUT_RESET_STATE)
            kvm_msr_entry_set(&msrs[n++], MSR_MCG_STATUS, env->mcg_status);
        else if (level == KVM_PUT_FULL_STATE) {
            kvm_msr_entry_set(&msrs[n++], MSR_MCG_STATUS, env->mcg_status);
            kvm_msr_entry_set(&msrs[n++], MSR_MCG_CTL, env->mcg_ctl);
            for (i = 0; i < (env->mcg_cap & 0xff) * 4; i++)
                kvm_msr_entry_set(&msrs[n++], MSR_MC0_CTL + i, env->mce_banks[i]);
        }
    }
#endif

    msr_data.info.nmsrs = n;

    return kvm_vcpu_ioctl(env, KVM_SET_MSRS, &msr_data);

}


static int kvm_get_fpu(CPUState *env)
{
    struct kvm_fpu fpu;
    int i, ret;

    ret = kvm_vcpu_ioctl(env, KVM_GET_FPU, &fpu);
    if (ret < 0)
        return ret;

    env->fpstt = (fpu.fsw >> 11) & 7;
    env->fpus = fpu.fsw;
    env->fpuc = fpu.fcw;
    for (i = 0; i < 8; ++i)
	env->fptags[i] = !((fpu.ftwx >> i) & 1);
    memcpy(env->fpregs, fpu.fpr, sizeof env->fpregs);
    memcpy(env->xmm_regs, fpu.xmm, sizeof env->xmm_regs);
    env->mxcsr = fpu.mxcsr;

    return 0;
}

static int kvm_get_xsave(CPUState *env)
{
#ifdef KVM_CAP_XSAVE
    struct kvm_xsave* xsave;
    int ret, i;
    uint16_t cwd, swd, twd, fop;

    if (!kvm_has_xsave())
        return kvm_get_fpu(env);

    xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
    ret = kvm_vcpu_ioctl(env, KVM_GET_XSAVE, xsave);
    if (ret < 0) {
        qemu_free(xsave);
        return ret;
    }

    cwd = (uint16_t)xsave->region[0];
    swd = (uint16_t)(xsave->region[0] >> 16);
    twd = (uint16_t)xsave->region[1];
    fop = (uint16_t)(xsave->region[1] >> 16);
    env->fpstt = (swd >> 11) & 7;
    env->fpus = swd;
    env->fpuc = cwd;
    for (i = 0; i < 8; ++i)
        env->fptags[i] = !((twd >> i) & 1);
    env->mxcsr = xsave->region[XSAVE_MXCSR];
    memcpy(env->fpregs, &xsave->region[XSAVE_ST_SPACE],
            sizeof env->fpregs);
    memcpy(env->xmm_regs, &xsave->region[XSAVE_XMM_SPACE],
            sizeof env->xmm_regs);
    env->xstate_bv = *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV];
    memcpy(env->ymmh_regs, &xsave->region[XSAVE_YMMH_SPACE],
            sizeof env->ymmh_regs);
    qemu_free(xsave);
    return 0;
#else
    return kvm_get_fpu(env);
#endif
}

static int kvm_get_xcrs(CPUState *env)
{
#ifdef KVM_CAP_XCRS
    int i, ret;
    struct kvm_xcrs xcrs;

    if (!kvm_has_xcrs())
        return 0;

    ret = kvm_vcpu_ioctl(env, KVM_GET_XCRS, &xcrs);
    if (ret < 0)
        return ret;

    for (i = 0; i < xcrs.nr_xcrs; i++)
        /* Only support xcr0 now */
        if (xcrs.xcrs[0].xcr == 0) {
            env->xcr0 = xcrs.xcrs[0].value;
            break;
        }
    return 0;
#else
    return 0;
#endif
}

static int kvm_get_sregs(CPUState *env)
{
    struct kvm_sregs sregs;
    uint32_t hflags;
    int bit, i, ret;

    ret = kvm_vcpu_ioctl(env, KVM_GET_SREGS, &sregs);
    if (ret < 0)
        return ret;

    /* There can only be one pending IRQ set in the bitmap at a time, so try
       to find it and save its number instead (-1 for none). */
    env->interrupt_injected = -1;
    for (i = 0; i < ARRAY_SIZE(sregs.interrupt_bitmap); i++) {
        if (sregs.interrupt_bitmap[i]) {
            bit = ctz64(sregs.interrupt_bitmap[i]);
            env->interrupt_injected = i * 64 + bit;
            break;
        }
    }

    get_seg(&env->segs[R_CS], &sregs.cs);
    get_seg(&env->segs[R_DS], &sregs.ds);
    get_seg(&env->segs[R_ES], &sregs.es);
    get_seg(&env->segs[R_FS], &sregs.fs);
    get_seg(&env->segs[R_GS], &sregs.gs);
    get_seg(&env->segs[R_SS], &sregs.ss);

    get_seg(&env->tr, &sregs.tr);
    get_seg(&env->ldt, &sregs.ldt);

    env->idt.limit = sregs.idt.limit;
    env->idt.base = sregs.idt.base;
    env->gdt.limit = sregs.gdt.limit;
    env->gdt.base = sregs.gdt.base;

    env->cr[0] = sregs.cr0;
    env->cr[2] = sregs.cr2;
    env->cr[3] = sregs.cr3;
    env->cr[4] = sregs.cr4;

    cpu_set_apic_base(env->apic_state, sregs.apic_base);

    env->efer = sregs.efer;
    //cpu_set_apic_tpr(env->apic_state, sregs.cr8);

#define HFLAG_COPY_MASK ~( \
			HF_CPL_MASK | HF_PE_MASK | HF_MP_MASK | HF_EM_MASK | \
			HF_TS_MASK | HF_TF_MASK | HF_VM_MASK | HF_IOPL_MASK | \
			HF_OSFXSR_MASK | HF_LMA_MASK | HF_CS32_MASK | \
			HF_SS32_MASK | HF_CS64_MASK | HF_ADDSEG_MASK)



    hflags = (env->segs[R_CS].flags >> DESC_DPL_SHIFT) & HF_CPL_MASK;
    hflags |= (env->cr[0] & CR0_PE_MASK) << (HF_PE_SHIFT - CR0_PE_SHIFT);
    hflags |= (env->cr[0] << (HF_MP_SHIFT - CR0_MP_SHIFT)) &
	    (HF_MP_MASK | HF_EM_MASK | HF_TS_MASK);
    hflags |= (env->eflags & (HF_TF_MASK | HF_VM_MASK | HF_IOPL_MASK));
    hflags |= (env->cr[4] & CR4_OSFXSR_MASK) <<
	    (HF_OSFXSR_SHIFT - CR4_OSFXSR_SHIFT);

    if (env->efer & MSR_EFER_LMA) {
        hflags |= HF_LMA_MASK;
    }

    if ((hflags & HF_LMA_MASK) && (env->segs[R_CS].flags & DESC_L_MASK)) {
        hflags |= HF_CS32_MASK | HF_SS32_MASK | HF_CS64_MASK;
    } else {
        hflags |= (env->segs[R_CS].flags & DESC_B_MASK) >>
		(DESC_B_SHIFT - HF_CS32_SHIFT);
        hflags |= (env->segs[R_SS].flags & DESC_B_MASK) >>
		(DESC_B_SHIFT - HF_SS32_SHIFT);
        if (!(env->cr[0] & CR0_PE_MASK) ||
                   (env->eflags & VM_MASK) ||
                   !(hflags & HF_CS32_MASK)) {
                hflags |= HF_ADDSEG_MASK;
            } else {
                hflags |= ((env->segs[R_DS].base |
                                env->segs[R_ES].base |
                                env->segs[R_SS].base) != 0) <<
                    HF_ADDSEG_SHIFT;
            }
    }
    env->hflags = (env->hflags & HFLAG_COPY_MASK) | hflags;

    return 0;
}

static int kvm_get_msrs(CPUState *env)
{
    struct {
        struct kvm_msrs info;
        struct kvm_msr_entry entries[100];
    } msr_data;
    struct kvm_msr_entry *msrs = msr_data.entries;
    int ret, i, n;

    n = 0;
    msrs[n++].index = MSR_IA32_SYSENTER_CS;
    msrs[n++].index = MSR_IA32_SYSENTER_ESP;
    msrs[n++].index = MSR_IA32_SYSENTER_EIP;
    if (kvm_has_msr_star(env))
	msrs[n++].index = MSR_STAR;
    if (kvm_has_msr_hsave_pa(env))
        msrs[n++].index = MSR_VM_HSAVE_PA;
    msrs[n++].index = MSR_IA32_TSC;
#ifdef TARGET_X86_64
    if (lm_capable_kernel) {
        msrs[n++].index = MSR_CSTAR;
        msrs[n++].index = MSR_KERNELGSBASE;
        msrs[n++].index = MSR_FMASK;
        msrs[n++].index = MSR_LSTAR;
    }
#endif
    msrs[n++].index = MSR_KVM_SYSTEM_TIME;
    msrs[n++].index = MSR_KVM_WALL_CLOCK;
#ifdef KVM_CAP_ASYNC_PF
    msrs[n++].index = MSR_KVM_ASYNC_PF_EN;
#endif

#ifdef KVM_CAP_MCE
    if (env->mcg_cap) {
        msrs[n++].index = MSR_MCG_STATUS;
        msrs[n++].index = MSR_MCG_CTL;
        for (i = 0; i < (env->mcg_cap & 0xff) * 4; i++)
            msrs[n++].index = MSR_MC0_CTL + i;
    }
#endif

    msr_data.info.nmsrs = n;
    ret = kvm_vcpu_ioctl(env, KVM_GET_MSRS, &msr_data);
    if (ret < 0)
        return ret;

    for (i = 0; i < ret; i++) {
        switch (msrs[i].index) {
        case MSR_IA32_SYSENTER_CS:
            env->sysenter_cs = msrs[i].data;
            break;
        case MSR_IA32_SYSENTER_ESP:
            env->sysenter_esp = msrs[i].data;
            break;
        case MSR_IA32_SYSENTER_EIP:
            env->sysenter_eip = msrs[i].data;
            break;
        case MSR_STAR:
            env->star = msrs[i].data;
            break;
#ifdef TARGET_X86_64
        case MSR_CSTAR:
            env->cstar = msrs[i].data;
            break;
        case MSR_KERNELGSBASE:
            env->kernelgsbase = msrs[i].data;
            break;
        case MSR_FMASK:
            env->fmask = msrs[i].data;
            break;
        case MSR_LSTAR:
            env->lstar = msrs[i].data;
            break;
#endif
        case MSR_IA32_TSC:
            env->tsc = msrs[i].data;
            break;
        case MSR_VM_HSAVE_PA:
            env->vm_hsave = msrs[i].data;
            break;
        case MSR_KVM_SYSTEM_TIME:
            env->system_time_msr = msrs[i].data;
            break;
        case MSR_KVM_WALL_CLOCK:
            env->wall_clock_msr = msrs[i].data;
            break;
#ifdef KVM_CAP_MCE
        case MSR_MCG_STATUS:
            env->mcg_status = msrs[i].data;
            break;
        case MSR_MCG_CTL:
            env->mcg_ctl = msrs[i].data;
            break;
#endif
        default:
#ifdef KVM_CAP_MCE
            if (msrs[i].index >= MSR_MC0_CTL &&
                msrs[i].index < MSR_MC0_CTL + (env->mcg_cap & 0xff) * 4) {
                env->mce_banks[msrs[i].index - MSR_MC0_CTL] = msrs[i].data;
            }
#endif
            break;
#ifdef KVM_CAP_ASYNC_PF
        case MSR_KVM_ASYNC_PF_EN:
            env->async_pf_en_msr = msrs[i].data;
            break;
#endif
        }
    }

    return 0;
}

static int kvm_put_mp_state(CPUState *env)
{
    struct kvm_mp_state mp_state = { .mp_state = env->mp_state };

    return kvm_vcpu_ioctl(env, KVM_SET_MP_STATE, &mp_state);
}

static int kvm_get_mp_state(CPUState *env)
{
    struct kvm_mp_state mp_state;
    int ret;

    ret = kvm_vcpu_ioctl(env, KVM_GET_MP_STATE, &mp_state);
    if (ret < 0) {
        return ret;
    }
    env->mp_state = mp_state.mp_state;
    return 0;
}

static int kvm_put_vcpu_events(CPUState *env, int level)
{
#ifdef KVM_CAP_VCPU_EVENTS
    struct kvm_vcpu_events events;

    if (!kvm_has_vcpu_events()) {
        return 0;
    }

    events.exception.injected = (env->exception_injected >= 0);
    events.exception.nr = env->exception_injected;
    events.exception.has_error_code = env->has_error_code;
    events.exception.error_code = env->error_code;

    events.interrupt.injected = (env->interrupt_injected >= 0);
    events.interrupt.nr = env->interrupt_injected;
    events.interrupt.soft = env->soft_interrupt;

    events.nmi.injected = env->nmi_injected;
    events.nmi.pending = env->nmi_pending;
    events.nmi.masked = !!(env->hflags2 & HF2_NMI_MASK);

    events.sipi_vector = env->sipi_vector;

    events.flags = 0;
    if (level >= KVM_PUT_RESET_STATE) {
        events.flags |=
            KVM_VCPUEVENT_VALID_NMI_PENDING | KVM_VCPUEVENT_VALID_SIPI_VECTOR;
    }

    return kvm_vcpu_ioctl(env, KVM_SET_VCPU_EVENTS, &events);
#else
    return 0;
#endif
}

static int kvm_get_vcpu_events(CPUState *env)
{
#ifdef KVM_CAP_VCPU_EVENTS
    struct kvm_vcpu_events events;
    int ret;

    if (!kvm_has_vcpu_events()) {
        return 0;
    }

    ret = kvm_vcpu_ioctl(env, KVM_GET_VCPU_EVENTS, &events);
    if (ret < 0) {
       return ret;
    }
    env->exception_injected =
       events.exception.injected ? events.exception.nr : -1;
    env->has_error_code = events.exception.has_error_code;
    env->error_code = events.exception.error_code;

    env->interrupt_injected =
        events.interrupt.injected ? events.interrupt.nr : -1;
    env->soft_interrupt = events.interrupt.soft;

    env->nmi_injected = events.nmi.injected;
    env->nmi_pending = events.nmi.pending;
    if (events.nmi.masked) {
        env->hflags2 |= HF2_NMI_MASK;
    } else {
        env->hflags2 &= ~HF2_NMI_MASK;
    }

    env->sipi_vector = events.sipi_vector;
#endif

    return 0;
}

static int kvm_guest_debug_workarounds(CPUState *env)
{
    int ret = 0;
#ifdef KVM_CAP_SET_GUEST_DEBUG
    unsigned long reinject_trap = 0;

    if (!kvm_has_vcpu_events()) {
        if (env->exception_injected == 1) {
            reinject_trap = KVM_GUESTDBG_INJECT_DB;
        } else if (env->exception_injected == 3) {
            reinject_trap = KVM_GUESTDBG_INJECT_BP;
        }
        env->exception_injected = -1;
    }

    /*
     * Kernels before KVM_CAP_X86_ROBUST_SINGLESTEP overwrote flags.TF
     * injected via SET_GUEST_DEBUG while updating GP regs. Work around this
     * by updating the debug state once again if single-stepping is on.
     * Another reason to call kvm_update_guest_debug here is a pending debug
     * trap raise by the guest. On kernels without SET_VCPU_EVENTS we have to
     * reinject them via SET_GUEST_DEBUG.
     */
    if (reinject_trap ||
        (!kvm_has_robust_singlestep() && env->singlestep_enabled)) {
        ret = kvm_update_guest_debug(env, reinject_trap);
    }
#endif /* KVM_CAP_SET_GUEST_DEBUG */
    return ret;
}

static int kvm_put_debugregs(CPUState *env)
{
#ifdef KVM_CAP_DEBUGREGS
    struct kvm_debugregs dbgregs;
    int i;

    if (!kvm_has_debugregs()) {
        return 0;
    }

    for (i = 0; i < 4; i++) {
        dbgregs.db[i] = env->dr[i];
    }
    dbgregs.dr6 = env->dr[6];
    dbgregs.dr7 = env->dr[7];
    dbgregs.flags = 0;

    return kvm_vcpu_ioctl(env, KVM_SET_DEBUGREGS, &dbgregs);
#else
    return 0;
#endif
}

static int kvm_get_debugregs(CPUState *env)
{
#ifdef KVM_CAP_DEBUGREGS
    struct kvm_debugregs dbgregs;
    int i, ret;

    if (!kvm_has_debugregs()) {
        return 0;
    }

    ret = kvm_vcpu_ioctl(env, KVM_GET_DEBUGREGS, &dbgregs);
    if (ret < 0) {
       return ret;
    }
    for (i = 0; i < 4; i++) {
        env->dr[i] = dbgregs.db[i];
    }
    env->dr[4] = env->dr[6] = dbgregs.dr6;
    env->dr[5] = env->dr[7] = dbgregs.dr7;
#endif

    return 0;
}

int kvm_arch_put_registers(CPUState *env, int level)
{
    int ret;

    assert(cpu_is_stopped(env) || qemu_cpu_self(env));

    ret = kvm_getput_regs(env, 1);
    if (ret < 0)
        return ret;

    ret = kvm_put_xsave(env);
    if (ret < 0)
        return ret;

    ret = kvm_put_xcrs(env);
    if (ret < 0)
        return ret;

    ret = kvm_put_sregs(env);
    if (ret < 0)
        return ret;

    ret = kvm_put_msrs(env, level);
    if (ret < 0)
        return ret;

    if (level >= KVM_PUT_RESET_STATE) {
        ret = kvm_put_mp_state(env);
        if (ret < 0)
            return ret;
    }

    ret = kvm_put_vcpu_events(env, level);
    if (ret < 0)
        return ret;

    /* must be last */
    ret = kvm_guest_debug_workarounds(env);
    if (ret < 0)
        return ret;

    ret = kvm_put_debugregs(env);
    if (ret < 0)
        return ret;

    return 0;
}

int kvm_arch_get_registers(CPUState *env)
{
    int ret;

    assert(cpu_is_stopped(env) || qemu_cpu_self(env));

    ret = kvm_getput_regs(env, 0);
    if (ret < 0)
        return ret;

    ret = kvm_get_xsave(env);
    if (ret < 0)
        return ret;

    ret = kvm_get_xcrs(env);
    if (ret < 0)
        return ret;

    ret = kvm_get_sregs(env);
    if (ret < 0)
        return ret;

    ret = kvm_get_msrs(env);
    if (ret < 0)
        return ret;

    ret = kvm_get_mp_state(env);
    if (ret < 0)
        return ret;

    ret = kvm_get_vcpu_events(env);
    if (ret < 0)
        return ret;

    ret = kvm_get_debugregs(env);
    if (ret < 0)
        return ret;

    return 0;
}

int kvm_arch_pre_run(CPUState *env, struct kvm_run *run)
{
    /* Inject NMI */
    if (env->interrupt_request & CPU_INTERRUPT_NMI) {
        env->interrupt_request &= ~CPU_INTERRUPT_NMI;
        DPRINTF("injected NMI\n");
        kvm_vcpu_ioctl(env, KVM_NMI);
    }

    /* Try to inject an interrupt if the guest can accept it */
    if (run->ready_for_interrupt_injection &&
        (env->interrupt_request & CPU_INTERRUPT_HARD) &&
        (env->eflags & IF_MASK)) {
        int irq;

        env->interrupt_request &= ~CPU_INTERRUPT_HARD;
        irq = cpu_get_pic_interrupt(env);
        if (irq >= 0) {
            struct kvm_interrupt intr;
            intr.irq = irq;
            /* FIXME: errors */
            DPRINTF("injected interrupt %d\n", irq);
            kvm_vcpu_ioctl(env, KVM_INTERRUPT, &intr);
        }
    }

    /* If we have an interrupt but the guest is not ready to receive an
     * interrupt, request an interrupt window exit.  This will
     * cause a return to userspace as soon as the guest is ready to
     * receive interrupts. */
    if ((env->interrupt_request & CPU_INTERRUPT_HARD))
        run->request_interrupt_window = 1;
    else
        run->request_interrupt_window = 0;

    DPRINTF("setting tpr\n");
    run->cr8 = cpu_get_apic_tpr(env->apic_state);

    return 0;
}

int kvm_arch_post_run(CPUState *env, struct kvm_run *run)
{
    if (run->if_flag)
        env->eflags |= IF_MASK;
    else
        env->eflags &= ~IF_MASK;
    
    cpu_set_apic_tpr(env->apic_state, run->cr8);
    cpu_set_apic_base(env->apic_state, run->apic_base);

    return 0;
}

int kvm_arch_process_irqchip_events(CPUState *env)
{
    if (env->interrupt_request & CPU_INTERRUPT_INIT) {
        kvm_cpu_synchronize_state(env);
        do_cpu_init(env);
        env->exception_index = EXCP_HALTED;
    }

    if (env->interrupt_request & CPU_INTERRUPT_SIPI) {
        kvm_cpu_synchronize_state(env);
        do_cpu_sipi(env);
    }

    return env->halted;
}

static int kvm_handle_halt(CPUState *env)
{
    if (!((env->interrupt_request & CPU_INTERRUPT_HARD) &&
          (env->eflags & IF_MASK)) &&
        !(env->interrupt_request & CPU_INTERRUPT_NMI)) {
        env->halted = 1;
        env->exception_index = EXCP_HLT;
        return 0;
    }

    return 1;
}

int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)
{
    int ret = 0;

    switch (run->exit_reason) {
    case KVM_EXIT_HLT:
        DPRINTF("handle_hlt\n");
        ret = kvm_handle_halt(env);
        break;
    }

    return ret;
}

#ifdef KVM_CAP_SET_GUEST_DEBUG
int kvm_arch_insert_sw_breakpoint(CPUState *env, struct kvm_sw_breakpoint *bp)
{
    static const uint8_t int3 = 0xcc;

    if (cpu_memory_rw_debug(env, bp->pc, (uint8_t *)&bp->saved_insn, 1, 0) ||
        cpu_memory_rw_debug(env, bp->pc, (uint8_t *)&int3, 1, 1))
        return -EINVAL;
    return 0;
}

int kvm_arch_remove_sw_breakpoint(CPUState *env, struct kvm_sw_breakpoint *bp)
{
    uint8_t int3;

    if (cpu_memory_rw_debug(env, bp->pc, &int3, 1, 0) || int3 != 0xcc ||
        cpu_memory_rw_debug(env, bp->pc, (uint8_t *)&bp->saved_insn, 1, 1))
        return -EINVAL;
    return 0;
}

static struct {
    target_ulong addr;
    int len;
    int type;
} hw_breakpoint[4];

static int nb_hw_breakpoint;

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

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

int kvm_arch_insert_hw_breakpoint(target_ulong addr,
                                  target_ulong len, int type)
{
    switch (type) {
    case GDB_BREAKPOINT_HW:
        len = 1;
        break;
    case GDB_WATCHPOINT_WRITE:
    case GDB_WATCHPOINT_ACCESS:
        switch (len) {
        case 1:
            break;
        case 2:
        case 4:
        case 8:
            if (addr & (len - 1))
                return -EINVAL;
            break;
        default:
            return -EINVAL;
        }
        break;
    default:
        return -ENOSYS;
    }

    if (nb_hw_breakpoint == 4)
        return -ENOBUFS;

    if (find_hw_breakpoint(addr, len, type) >= 0)
        return -EEXIST;

    hw_breakpoint[nb_hw_breakpoint].addr = addr;
    hw_breakpoint[nb_hw_breakpoint].len = len;
    hw_breakpoint[nb_hw_breakpoint].type = type;
    nb_hw_breakpoint++;

    return 0;
}

int kvm_arch_remove_hw_breakpoint(target_ulong addr,
                                  target_ulong len, int type)
{
    int n;

    n = find_hw_breakpoint(addr, (type == GDB_BREAKPOINT_HW) ? 1 : len, type);
    if (n < 0)
        return -ENOENT;

    nb_hw_breakpoint--;
    hw_breakpoint[n] = hw_breakpoint[nb_hw_breakpoint];

    return 0;
}

void kvm_arch_remove_all_hw_breakpoints(void)
{
    nb_hw_breakpoint = 0;
}

static CPUWatchpoint hw_watchpoint;

int kvm_arch_debug(struct kvm_debug_exit_arch *arch_info)
{
    int handle = 0;
    int n;

    if (arch_info->exception == 1) {
        if (arch_info->dr6 & (1 << 14)) {
            if (cpu_single_env->singlestep_enabled)
                handle = 1;
        } else {
            for (n = 0; n < 4; n++)
                if (arch_info->dr6 & (1 << n))
                    switch ((arch_info->dr7 >> (16 + n*4)) & 0x3) {
                    case 0x0:
                        handle = 1;
                        break;
                    case 0x1:
                        handle = 1;
                        cpu_single_env->watchpoint_hit = &hw_watchpoint;
                        hw_watchpoint.vaddr = hw_breakpoint[n].addr;
                        hw_watchpoint.flags = BP_MEM_WRITE;
                        break;
                    case 0x3:
                        handle = 1;
                        cpu_single_env->watchpoint_hit = &hw_watchpoint;
                        hw_watchpoint.vaddr = hw_breakpoint[n].addr;
                        hw_watchpoint.flags = BP_MEM_ACCESS;
                        break;
                    }
        }
    } else if (kvm_find_sw_breakpoint(cpu_single_env, arch_info->pc))
        handle = 1;

    if (!handle) {
        cpu_synchronize_state(cpu_single_env);
        assert(cpu_single_env->exception_injected == -1);

        cpu_single_env->exception_injected = arch_info->exception;
        cpu_single_env->has_error_code = 0;
    }

    return handle;
}

void kvm_arch_update_guest_debug(CPUState *env, struct kvm_guest_debug *dbg)
{
    const uint8_t type_code[] = {
        [GDB_BREAKPOINT_HW] = 0x0,
        [GDB_WATCHPOINT_WRITE] = 0x1,
        [GDB_WATCHPOINT_ACCESS] = 0x3
    };
    const uint8_t len_code[] = {
        [1] = 0x0, [2] = 0x1, [4] = 0x3, [8] = 0x2
    };
    int n;

    if (kvm_sw_breakpoints_active(env))
        dbg->control |= KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP;

    if (nb_hw_breakpoint > 0) {
        dbg->control |= KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP;
        dbg->arch.debugreg[7] = 0x0600;
        for (n = 0; n < nb_hw_breakpoint; n++) {
            dbg->arch.debugreg[n] = hw_breakpoint[n].addr;
            dbg->arch.debugreg[7] |= (2 << (n * 2)) |
                (type_code[hw_breakpoint[n].type] << (16 + n*4)) |
                (len_code[hw_breakpoint[n].len] << (18 + n*4));
        }
    }
    /* Legal xcr0 for loading */
    env->xcr0 = 1;
}
#endif /* KVM_CAP_SET_GUEST_DEBUG */

bool kvm_arch_stop_on_emulation_error(CPUState *env)
{
      return !(env->cr[0] & CR0_PE_MASK) ||
              ((env->segs[R_CS].selector  & 3) != 3);
}

static void hardware_memory_error(void)
{
    fprintf(stderr, "Hardware memory error!\n");
    exit(1);
}

#ifdef KVM_CAP_MCE
static void kvm_mce_broadcast_rest(CPUState *env)
{
    CPUState *cenv;
    int family, model, cpuver = env->cpuid_version;

    family = (cpuver >> 8) & 0xf;
    model = ((cpuver >> 12) & 0xf0) + ((cpuver >> 4) & 0xf);

    /* Broadcast MCA signal for processor version 06H_EH and above */
    if ((family == 6 && model >= 14) || family > 6) {
        for (cenv = first_cpu; cenv != NULL; cenv = cenv->next_cpu) {
            if (cenv == env) {
                continue;
            }
            kvm_inject_x86_mce(cenv, 1, MCI_STATUS_VAL | MCI_STATUS_UC,
                               MCG_STATUS_MCIP | MCG_STATUS_RIPV, 0, 0,
                               ABORT_ON_ERROR);
        }
    }
}
#endif

int kvm_on_sigbus_vcpu(CPUState *env, int code, void *addr)
{
#if defined(KVM_CAP_MCE)
    struct kvm_x86_mce mce = {
            .bank = 9,
    };
    void *vaddr;
    ram_addr_t ram_addr;
    target_phys_addr_t paddr;
    int r;

    if ((env->mcg_cap & MCG_SER_P) && addr
        && (code == BUS_MCEERR_AR
            || code == BUS_MCEERR_AO)) {
        if (code == BUS_MCEERR_AR) {
            /* Fake an Intel architectural Data Load SRAR UCR */
            mce.status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN
                | MCI_STATUS_MISCV | MCI_STATUS_ADDRV | MCI_STATUS_S
                | MCI_STATUS_AR | 0x134;
            mce.misc = (MCM_ADDR_PHYS << 6) | 0xc;
            mce.mcg_status = MCG_STATUS_MCIP | MCG_STATUS_EIPV;
        } else {
            /*
             * If there is an MCE excpetion being processed, ignore
             * this SRAO MCE
             */
            r = kvm_mce_in_exception(env);
            if (r == -1) {
                fprintf(stderr, "Failed to get MCE status\n");
            } else if (r) {
                return 0;
            }
            /* Fake an Intel architectural Memory scrubbing UCR */
            mce.status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN
                | MCI_STATUS_MISCV | MCI_STATUS_ADDRV | MCI_STATUS_S
                | 0xc0;
            mce.misc = (MCM_ADDR_PHYS << 6) | 0xc;
            mce.mcg_status = MCG_STATUS_MCIP | MCG_STATUS_RIPV;
        }
        vaddr = (void *)addr;
        if (qemu_ram_addr_from_host(vaddr, &ram_addr) ||
            !kvm_physical_memory_addr_from_ram(env->kvm_state, ram_addr, &paddr)) {
            fprintf(stderr, "Hardware memory error for memory used by "
                    "QEMU itself instead of guest system!\n");
            /* Hope we are lucky for AO MCE */
            if (code == BUS_MCEERR_AO) {
                return 0;
            } else {
                hardware_memory_error();
            }
        }
        mce.addr = paddr;
        r = kvm_set_mce(env, &mce);
        if (r < 0) {
            fprintf(stderr, "kvm_set_mce: %s\n", strerror(errno));
            abort();
        }
        kvm_mce_broadcast_rest(env);
    } else
#endif
    {
        if (code == BUS_MCEERR_AO) {
            return 0;
        } else if (code == BUS_MCEERR_AR) {
            hardware_memory_error();
        } else {
            return 1;
        }
    }
    return 0;
}

int kvm_on_sigbus(int code, void *addr)
{
#if defined(KVM_CAP_MCE)
    if ((first_cpu->mcg_cap & MCG_SER_P) && addr && code == BUS_MCEERR_AO) {
        uint64_t status;
        void *vaddr;
        ram_addr_t ram_addr;
        target_phys_addr_t paddr;

        /* Hope we are lucky for AO MCE */
        vaddr = addr;
        if (qemu_ram_addr_from_host(vaddr, &ram_addr) ||
            !kvm_physical_memory_addr_from_ram(first_cpu->kvm_state, ram_addr, &paddr)) {
            fprintf(stderr, "Hardware memory error for memory used by "
                    "QEMU itself instead of guest system!: %p\n", addr);
            return 0;
        }
        status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN
            | MCI_STATUS_MISCV | MCI_STATUS_ADDRV | MCI_STATUS_S
            | 0xc0;
        kvm_inject_x86_mce(first_cpu, 9, status,
                           MCG_STATUS_MCIP | MCG_STATUS_RIPV, paddr,
                           (MCM_ADDR_PHYS << 6) | 0xc, ABORT_ON_ERROR);
        kvm_mce_broadcast_rest(first_cpu);
    } else
#endif
    {
        if (code == BUS_MCEERR_AO) {
            return 0;
        } else if (code == BUS_MCEERR_AR) {
            hardware_memory_error();
        } else {
            return 1;
        }
    }
    return 0;
}