aboutsummaryrefslogtreecommitdiff
path: root/hw/i386/pc.c
blob: ac7ac774e6dc8e770669b05dd3ed7c3612ceddfe (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
/*
 * QEMU PC System Emulator
 *
 * Copyright (c) 2003-2004 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 "hw/hw.h"
#include "hw/i386/pc.h"
#include "hw/char/serial.h"
#include "hw/i386/apic.h"
#include "hw/block/fdc.h"
#include "hw/ide.h"
#include "hw/pci/pci.h"
#include "monitor/monitor.h"
#include "hw/nvram/fw_cfg.h"
#include "hw/timer/hpet.h"
#include "hw/i386/smbios.h"
#include "hw/loader.h"
#include "elf.h"
#include "multiboot.h"
#include "hw/timer/mc146818rtc.h"
#include "hw/timer/i8254.h"
#include "hw/audio/pcspk.h"
#include "hw/pci/msi.h"
#include "hw/sysbus.h"
#include "sysemu/sysemu.h"
#include "sysemu/kvm.h"
#include "kvm_i386.h"
#include "hw/xen/xen.h"
#include "sysemu/blockdev.h"
#include "hw/block/block.h"
#include "ui/qemu-spice.h"
#include "exec/memory.h"
#include "exec/address-spaces.h"
#include "sysemu/arch_init.h"
#include "qemu/bitmap.h"
#include "qemu/config-file.h"
#include "hw/acpi/acpi.h"
#include "hw/acpi/cpu_hotplug.h"
#include "hw/cpu/icc_bus.h"
#include "hw/boards.h"
#include "hw/pci/pci_host.h"
#include "acpi-build.h"
#include "hw/mem/pc-dimm.h"
#include "trace.h"
#include "qapi/visitor.h"

/* debug PC/ISA interrupts */
//#define DEBUG_IRQ

#ifdef DEBUG_IRQ
#define DPRINTF(fmt, ...)                                       \
    do { printf("CPUIRQ: " fmt , ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...)
#endif

/* Leave a chunk of memory at the top of RAM for the BIOS ACPI tables.  */
#define ACPI_DATA_SIZE       0x10000
#define BIOS_CFG_IOPORT 0x510
#define FW_CFG_ACPI_TABLES (FW_CFG_ARCH_LOCAL + 0)
#define FW_CFG_SMBIOS_ENTRIES (FW_CFG_ARCH_LOCAL + 1)
#define FW_CFG_IRQ0_OVERRIDE (FW_CFG_ARCH_LOCAL + 2)
#define FW_CFG_E820_TABLE (FW_CFG_ARCH_LOCAL + 3)
#define FW_CFG_HPET (FW_CFG_ARCH_LOCAL + 4)

#define E820_NR_ENTRIES		16

struct e820_entry {
    uint64_t address;
    uint64_t length;
    uint32_t type;
} QEMU_PACKED __attribute((__aligned__(4)));

struct e820_table {
    uint32_t count;
    struct e820_entry entry[E820_NR_ENTRIES];
} QEMU_PACKED __attribute((__aligned__(4)));

static struct e820_table e820_reserve;
static struct e820_entry *e820_table;
static unsigned e820_entries;
struct hpet_fw_config hpet_cfg = {.count = UINT8_MAX};

void gsi_handler(void *opaque, int n, int level)
{
    GSIState *s = opaque;

    DPRINTF("pc: %s GSI %d\n", level ? "raising" : "lowering", n);
    if (n < ISA_NUM_IRQS) {
        qemu_set_irq(s->i8259_irq[n], level);
    }
    qemu_set_irq(s->ioapic_irq[n], level);
}

static void ioport80_write(void *opaque, hwaddr addr, uint64_t data,
                           unsigned size)
{
}

static uint64_t ioport80_read(void *opaque, hwaddr addr, unsigned size)
{
    return 0xffffffffffffffffULL;
}

/* MSDOS compatibility mode FPU exception support */
static qemu_irq ferr_irq;

void pc_register_ferr_irq(qemu_irq irq)
{
    ferr_irq = irq;
}

/* XXX: add IGNNE support */
void cpu_set_ferr(CPUX86State *s)
{
    qemu_irq_raise(ferr_irq);
}

static void ioportF0_write(void *opaque, hwaddr addr, uint64_t data,
                           unsigned size)
{
    qemu_irq_lower(ferr_irq);
}

static uint64_t ioportF0_read(void *opaque, hwaddr addr, unsigned size)
{
    return 0xffffffffffffffffULL;
}

/* TSC handling */
uint64_t cpu_get_tsc(CPUX86State *env)
{
    return cpu_get_ticks();
}

/* SMM support */

static cpu_set_smm_t smm_set;
static void *smm_arg;

void cpu_smm_register(cpu_set_smm_t callback, void *arg)
{
    assert(smm_set == NULL);
    assert(smm_arg == NULL);
    smm_set = callback;
    smm_arg = arg;
}

void cpu_smm_update(CPUX86State *env)
{
    if (smm_set && smm_arg && CPU(x86_env_get_cpu(env)) == first_cpu) {
        smm_set(!!(env->hflags & HF_SMM_MASK), smm_arg);
    }
}


/* IRQ handling */
int cpu_get_pic_interrupt(CPUX86State *env)
{
    X86CPU *cpu = x86_env_get_cpu(env);
    int intno;

    intno = apic_get_interrupt(cpu->apic_state);
    if (intno >= 0) {
        return intno;
    }
    /* read the irq from the PIC */
    if (!apic_accept_pic_intr(cpu->apic_state)) {
        return -1;
    }

    intno = pic_read_irq(isa_pic);
    return intno;
}

static void pic_irq_request(void *opaque, int irq, int level)
{
    CPUState *cs = first_cpu;
    X86CPU *cpu = X86_CPU(cs);

    DPRINTF("pic_irqs: %s irq %d\n", level? "raise" : "lower", irq);
    if (cpu->apic_state) {
        CPU_FOREACH(cs) {
            cpu = X86_CPU(cs);
            if (apic_accept_pic_intr(cpu->apic_state)) {
                apic_deliver_pic_intr(cpu->apic_state, level);
            }
        }
    } else {
        if (level) {
            cpu_interrupt(cs, CPU_INTERRUPT_HARD);
        } else {
            cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD);
        }
    }
}

/* PC cmos mappings */

#define REG_EQUIPMENT_BYTE          0x14

static int cmos_get_fd_drive_type(FDriveType fd0)
{
    int val;

    switch (fd0) {
    case FDRIVE_DRV_144:
        /* 1.44 Mb 3"5 drive */
        val = 4;
        break;
    case FDRIVE_DRV_288:
        /* 2.88 Mb 3"5 drive */
        val = 5;
        break;
    case FDRIVE_DRV_120:
        /* 1.2 Mb 5"5 drive */
        val = 2;
        break;
    case FDRIVE_DRV_NONE:
    default:
        val = 0;
        break;
    }
    return val;
}

static void cmos_init_hd(ISADevice *s, int type_ofs, int info_ofs,
                         int16_t cylinders, int8_t heads, int8_t sectors)
{
    rtc_set_memory(s, type_ofs, 47);
    rtc_set_memory(s, info_ofs, cylinders);
    rtc_set_memory(s, info_ofs + 1, cylinders >> 8);
    rtc_set_memory(s, info_ofs + 2, heads);
    rtc_set_memory(s, info_ofs + 3, 0xff);
    rtc_set_memory(s, info_ofs + 4, 0xff);
    rtc_set_memory(s, info_ofs + 5, 0xc0 | ((heads > 8) << 3));
    rtc_set_memory(s, info_ofs + 6, cylinders);
    rtc_set_memory(s, info_ofs + 7, cylinders >> 8);
    rtc_set_memory(s, info_ofs + 8, sectors);
}

/* convert boot_device letter to something recognizable by the bios */
static int boot_device2nibble(char boot_device)
{
    switch(boot_device) {
    case 'a':
    case 'b':
        return 0x01; /* floppy boot */
    case 'c':
        return 0x02; /* hard drive boot */
    case 'd':
        return 0x03; /* CD-ROM boot */
    case 'n':
        return 0x04; /* Network boot */
    }
    return 0;
}

static int set_boot_dev(ISADevice *s, const char *boot_device)
{
#define PC_MAX_BOOT_DEVICES 3
    int nbds, bds[3] = { 0, };
    int i;

    nbds = strlen(boot_device);
    if (nbds > PC_MAX_BOOT_DEVICES) {
        error_report("Too many boot devices for PC");
        return(1);
    }
    for (i = 0; i < nbds; i++) {
        bds[i] = boot_device2nibble(boot_device[i]);
        if (bds[i] == 0) {
            error_report("Invalid boot device for PC: '%c'",
                         boot_device[i]);
            return(1);
        }
    }
    rtc_set_memory(s, 0x3d, (bds[1] << 4) | bds[0]);
    rtc_set_memory(s, 0x38, (bds[2] << 4) | (fd_bootchk ? 0x0 : 0x1));
    return(0);
}

static int pc_boot_set(void *opaque, const char *boot_device)
{
    return set_boot_dev(opaque, boot_device);
}

typedef struct pc_cmos_init_late_arg {
    ISADevice *rtc_state;
    BusState *idebus[2];
} pc_cmos_init_late_arg;

static void pc_cmos_init_late(void *opaque)
{
    pc_cmos_init_late_arg *arg = opaque;
    ISADevice *s = arg->rtc_state;
    int16_t cylinders;
    int8_t heads, sectors;
    int val;
    int i, trans;

    val = 0;
    if (ide_get_geometry(arg->idebus[0], 0,
                         &cylinders, &heads, &sectors) >= 0) {
        cmos_init_hd(s, 0x19, 0x1b, cylinders, heads, sectors);
        val |= 0xf0;
    }
    if (ide_get_geometry(arg->idebus[0], 1,
                         &cylinders, &heads, &sectors) >= 0) {
        cmos_init_hd(s, 0x1a, 0x24, cylinders, heads, sectors);
        val |= 0x0f;
    }
    rtc_set_memory(s, 0x12, val);

    val = 0;
    for (i = 0; i < 4; i++) {
        /* NOTE: ide_get_geometry() returns the physical
           geometry.  It is always such that: 1 <= sects <= 63, 1
           <= heads <= 16, 1 <= cylinders <= 16383. The BIOS
           geometry can be different if a translation is done. */
        if (ide_get_geometry(arg->idebus[i / 2], i % 2,
                             &cylinders, &heads, &sectors) >= 0) {
            trans = ide_get_bios_chs_trans(arg->idebus[i / 2], i % 2) - 1;
            assert((trans & ~3) == 0);
            val |= trans << (i * 2);
        }
    }
    rtc_set_memory(s, 0x39, val);

    qemu_unregister_reset(pc_cmos_init_late, opaque);
}

typedef struct RTCCPUHotplugArg {
    Notifier cpu_added_notifier;
    ISADevice *rtc_state;
} RTCCPUHotplugArg;

static void rtc_notify_cpu_added(Notifier *notifier, void *data)
{
    RTCCPUHotplugArg *arg = container_of(notifier, RTCCPUHotplugArg,
                                         cpu_added_notifier);
    ISADevice *s = arg->rtc_state;

    /* increment the number of CPUs */
    rtc_set_memory(s, 0x5f, rtc_get_memory(s, 0x5f) + 1);
}

void pc_cmos_init(ram_addr_t ram_size, ram_addr_t above_4g_mem_size,
                  const char *boot_device,
                  ISADevice *floppy, BusState *idebus0, BusState *idebus1,
                  ISADevice *s)
{
    int val, nb, i;
    FDriveType fd_type[2] = { FDRIVE_DRV_NONE, FDRIVE_DRV_NONE };
    static pc_cmos_init_late_arg arg;
    static RTCCPUHotplugArg cpu_hotplug_cb;

    /* various important CMOS locations needed by PC/Bochs bios */

    /* memory size */
    /* base memory (first MiB) */
    val = MIN(ram_size / 1024, 640);
    rtc_set_memory(s, 0x15, val);
    rtc_set_memory(s, 0x16, val >> 8);
    /* extended memory (next 64MiB) */
    if (ram_size > 1024 * 1024) {
        val = (ram_size - 1024 * 1024) / 1024;
    } else {
        val = 0;
    }
    if (val > 65535)
        val = 65535;
    rtc_set_memory(s, 0x17, val);
    rtc_set_memory(s, 0x18, val >> 8);
    rtc_set_memory(s, 0x30, val);
    rtc_set_memory(s, 0x31, val >> 8);
    /* memory between 16MiB and 4GiB */
    if (ram_size > 16 * 1024 * 1024) {
        val = (ram_size - 16 * 1024 * 1024) / 65536;
    } else {
        val = 0;
    }
    if (val > 65535)
        val = 65535;
    rtc_set_memory(s, 0x34, val);
    rtc_set_memory(s, 0x35, val >> 8);
    /* memory above 4GiB */
    val = above_4g_mem_size / 65536;
    rtc_set_memory(s, 0x5b, val);
    rtc_set_memory(s, 0x5c, val >> 8);
    rtc_set_memory(s, 0x5d, val >> 16);

    /* set the number of CPU */
    rtc_set_memory(s, 0x5f, smp_cpus - 1);
    /* init CPU hotplug notifier */
    cpu_hotplug_cb.rtc_state = s;
    cpu_hotplug_cb.cpu_added_notifier.notify = rtc_notify_cpu_added;
    qemu_register_cpu_added_notifier(&cpu_hotplug_cb.cpu_added_notifier);

    if (set_boot_dev(s, boot_device)) {
        exit(1);
    }

    /* floppy type */
    if (floppy) {
        for (i = 0; i < 2; i++) {
            fd_type[i] = isa_fdc_get_drive_type(floppy, i);
        }
    }
    val = (cmos_get_fd_drive_type(fd_type[0]) << 4) |
        cmos_get_fd_drive_type(fd_type[1]);
    rtc_set_memory(s, 0x10, val);

    val = 0;
    nb = 0;
    if (fd_type[0] < FDRIVE_DRV_NONE) {
        nb++;
    }
    if (fd_type[1] < FDRIVE_DRV_NONE) {
        nb++;
    }
    switch (nb) {
    case 0:
        break;
    case 1:
        val |= 0x01; /* 1 drive, ready for boot */
        break;
    case 2:
        val |= 0x41; /* 2 drives, ready for boot */
        break;
    }
    val |= 0x02; /* FPU is there */
    val |= 0x04; /* PS/2 mouse installed */
    rtc_set_memory(s, REG_EQUIPMENT_BYTE, val);

    /* hard drives */
    arg.rtc_state = s;
    arg.idebus[0] = idebus0;
    arg.idebus[1] = idebus1;
    qemu_register_reset(pc_cmos_init_late, &arg);
}

#define TYPE_PORT92 "port92"
#define PORT92(obj) OBJECT_CHECK(Port92State, (obj), TYPE_PORT92)

/* port 92 stuff: could be split off */
typedef struct Port92State {
    ISADevice parent_obj;

    MemoryRegion io;
    uint8_t outport;
    qemu_irq *a20_out;
} Port92State;

static void port92_write(void *opaque, hwaddr addr, uint64_t val,
                         unsigned size)
{
    Port92State *s = opaque;
    int oldval = s->outport;

    DPRINTF("port92: write 0x%02x\n", val);
    s->outport = val;
    qemu_set_irq(*s->a20_out, (val >> 1) & 1);
    if ((val & 1) && !(oldval & 1)) {
        qemu_system_reset_request();
    }
}

static uint64_t port92_read(void *opaque, hwaddr addr,
                            unsigned size)
{
    Port92State *s = opaque;
    uint32_t ret;

    ret = s->outport;
    DPRINTF("port92: read 0x%02x\n", ret);
    return ret;
}

static void port92_init(ISADevice *dev, qemu_irq *a20_out)
{
    Port92State *s = PORT92(dev);

    s->a20_out = a20_out;
}

static const VMStateDescription vmstate_port92_isa = {
    .name = "port92",
    .version_id = 1,
    .minimum_version_id = 1,
    .fields = (VMStateField[]) {
        VMSTATE_UINT8(outport, Port92State),
        VMSTATE_END_OF_LIST()
    }
};

static void port92_reset(DeviceState *d)
{
    Port92State *s = PORT92(d);

    s->outport &= ~1;
}

static const MemoryRegionOps port92_ops = {
    .read = port92_read,
    .write = port92_write,
    .impl = {
        .min_access_size = 1,
        .max_access_size = 1,
    },
    .endianness = DEVICE_LITTLE_ENDIAN,
};

static void port92_initfn(Object *obj)
{
    Port92State *s = PORT92(obj);

    memory_region_init_io(&s->io, OBJECT(s), &port92_ops, s, "port92", 1);

    s->outport = 0;
}

static void port92_realizefn(DeviceState *dev, Error **errp)
{
    ISADevice *isadev = ISA_DEVICE(dev);
    Port92State *s = PORT92(dev);

    isa_register_ioport(isadev, &s->io, 0x92);
}

static void port92_class_initfn(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);

    dc->realize = port92_realizefn;
    dc->reset = port92_reset;
    dc->vmsd = &vmstate_port92_isa;
    /*
     * Reason: unlike ordinary ISA devices, this one needs additional
     * wiring: its A20 output line needs to be wired up by
     * port92_init().
     */
    dc->cannot_instantiate_with_device_add_yet = true;
}

static const TypeInfo port92_info = {
    .name          = TYPE_PORT92,
    .parent        = TYPE_ISA_DEVICE,
    .instance_size = sizeof(Port92State),
    .instance_init = port92_initfn,
    .class_init    = port92_class_initfn,
};

static void port92_register_types(void)
{
    type_register_static(&port92_info);
}

type_init(port92_register_types)

static void handle_a20_line_change(void *opaque, int irq, int level)
{
    X86CPU *cpu = opaque;

    /* XXX: send to all CPUs ? */
    /* XXX: add logic to handle multiple A20 line sources */
    x86_cpu_set_a20(cpu, level);
}

int e820_add_entry(uint64_t address, uint64_t length, uint32_t type)
{
    int index = le32_to_cpu(e820_reserve.count);
    struct e820_entry *entry;

    if (type != E820_RAM) {
        /* old FW_CFG_E820_TABLE entry -- reservations only */
        if (index >= E820_NR_ENTRIES) {
            return -EBUSY;
        }
        entry = &e820_reserve.entry[index++];

        entry->address = cpu_to_le64(address);
        entry->length = cpu_to_le64(length);
        entry->type = cpu_to_le32(type);

        e820_reserve.count = cpu_to_le32(index);
    }

    /* new "etc/e820" file -- include ram too */
    e820_table = g_realloc(e820_table,
                           sizeof(struct e820_entry) * (e820_entries+1));
    e820_table[e820_entries].address = cpu_to_le64(address);
    e820_table[e820_entries].length = cpu_to_le64(length);
    e820_table[e820_entries].type = cpu_to_le32(type);
    e820_entries++;

    return e820_entries;
}

int e820_get_num_entries(void)
{
    return e820_entries;
}

bool e820_get_entry(int idx, uint32_t type, uint64_t *address, uint64_t *length)
{
    if (idx < e820_entries && e820_table[idx].type == cpu_to_le32(type)) {
        *address = le64_to_cpu(e820_table[idx].address);
        *length = le64_to_cpu(e820_table[idx].length);
        return true;
    }
    return false;
}

/* Calculates the limit to CPU APIC ID values
 *
 * This function returns the limit for the APIC ID value, so that all
 * CPU APIC IDs are < pc_apic_id_limit().
 *
 * This is used for FW_CFG_MAX_CPUS. See comments on bochs_bios_init().
 */
static unsigned int pc_apic_id_limit(unsigned int max_cpus)
{
    return x86_cpu_apic_id_from_index(max_cpus - 1) + 1;
}

static FWCfgState *bochs_bios_init(void)
{
    FWCfgState *fw_cfg;
    uint8_t *smbios_tables, *smbios_anchor;
    size_t smbios_tables_len, smbios_anchor_len;
    uint64_t *numa_fw_cfg;
    int i, j;
    unsigned int apic_id_limit = pc_apic_id_limit(max_cpus);

    fw_cfg = fw_cfg_init(BIOS_CFG_IOPORT, BIOS_CFG_IOPORT + 1, 0, 0);
    /* FW_CFG_MAX_CPUS is a bit confusing/problematic on x86:
     *
     * SeaBIOS needs FW_CFG_MAX_CPUS for CPU hotplug, but the CPU hotplug
     * QEMU<->SeaBIOS interface is not based on the "CPU index", but on the APIC
     * ID of hotplugged CPUs[1]. This means that FW_CFG_MAX_CPUS is not the
     * "maximum number of CPUs", but the "limit to the APIC ID values SeaBIOS
     * may see".
     *
     * So, this means we must not use max_cpus, here, but the maximum possible
     * APIC ID value, plus one.
     *
     * [1] The only kind of "CPU identifier" used between SeaBIOS and QEMU is
     *     the APIC ID, not the "CPU index"
     */
    fw_cfg_add_i16(fw_cfg, FW_CFG_MAX_CPUS, (uint16_t)apic_id_limit);
    fw_cfg_add_i32(fw_cfg, FW_CFG_ID, 1);
    fw_cfg_add_i64(fw_cfg, FW_CFG_RAM_SIZE, (uint64_t)ram_size);
    fw_cfg_add_bytes(fw_cfg, FW_CFG_ACPI_TABLES,
                     acpi_tables, acpi_tables_len);
    fw_cfg_add_i32(fw_cfg, FW_CFG_IRQ0_OVERRIDE, kvm_allows_irq0_override());

    smbios_tables = smbios_get_table_legacy(&smbios_tables_len);
    if (smbios_tables) {
        fw_cfg_add_bytes(fw_cfg, FW_CFG_SMBIOS_ENTRIES,
                         smbios_tables, smbios_tables_len);
    }

    smbios_get_tables(&smbios_tables, &smbios_tables_len,
                      &smbios_anchor, &smbios_anchor_len);
    if (smbios_anchor) {
        fw_cfg_add_file(fw_cfg, "etc/smbios/smbios-tables",
                        smbios_tables, smbios_tables_len);
        fw_cfg_add_file(fw_cfg, "etc/smbios/smbios-anchor",
                        smbios_anchor, smbios_anchor_len);
    }

    fw_cfg_add_bytes(fw_cfg, FW_CFG_E820_TABLE,
                     &e820_reserve, sizeof(e820_reserve));
    fw_cfg_add_file(fw_cfg, "etc/e820", e820_table,
                    sizeof(struct e820_entry) * e820_entries);

    fw_cfg_add_bytes(fw_cfg, FW_CFG_HPET, &hpet_cfg, sizeof(hpet_cfg));
    /* allocate memory for the NUMA channel: one (64bit) word for the number
     * of nodes, one word for each VCPU->node and one word for each node to
     * hold the amount of memory.
     */
    numa_fw_cfg = g_new0(uint64_t, 1 + apic_id_limit + nb_numa_nodes);
    numa_fw_cfg[0] = cpu_to_le64(nb_numa_nodes);
    for (i = 0; i < max_cpus; i++) {
        unsigned int apic_id = x86_cpu_apic_id_from_index(i);
        assert(apic_id < apic_id_limit);
        for (j = 0; j < nb_numa_nodes; j++) {
            if (test_bit(i, numa_info[j].node_cpu)) {
                numa_fw_cfg[apic_id + 1] = cpu_to_le64(j);
                break;
            }
        }
    }
    for (i = 0; i < nb_numa_nodes; i++) {
        numa_fw_cfg[apic_id_limit + 1 + i] = cpu_to_le64(numa_info[i].node_mem);
    }
    fw_cfg_add_bytes(fw_cfg, FW_CFG_NUMA, numa_fw_cfg,
                     (1 + apic_id_limit + nb_numa_nodes) *
                     sizeof(*numa_fw_cfg));

    return fw_cfg;
}

static long get_file_size(FILE *f)
{
    long where, size;

    /* XXX: on Unix systems, using fstat() probably makes more sense */

    where = ftell(f);
    fseek(f, 0, SEEK_END);
    size = ftell(f);
    fseek(f, where, SEEK_SET);

    return size;
}

static void load_linux(FWCfgState *fw_cfg,
                       const char *kernel_filename,
                       const char *initrd_filename,
                       const char *kernel_cmdline,
                       hwaddr max_ram_size)
{
    uint16_t protocol;
    int setup_size, kernel_size, initrd_size = 0, cmdline_size;
    uint32_t initrd_max;
    uint8_t header[8192], *setup, *kernel, *initrd_data;
    hwaddr real_addr, prot_addr, cmdline_addr, initrd_addr = 0;
    FILE *f;
    char *vmode;

    /* Align to 16 bytes as a paranoia measure */
    cmdline_size = (strlen(kernel_cmdline)+16) & ~15;

    /* load the kernel header */
    f = fopen(kernel_filename, "rb");
    if (!f || !(kernel_size = get_file_size(f)) ||
        fread(header, 1, MIN(ARRAY_SIZE(header), kernel_size), f) !=
        MIN(ARRAY_SIZE(header), kernel_size)) {
        fprintf(stderr, "qemu: could not load kernel '%s': %s\n",
                kernel_filename, strerror(errno));
        exit(1);
    }

    /* kernel protocol version */
#if 0
    fprintf(stderr, "header magic: %#x\n", ldl_p(header+0x202));
#endif
    if (ldl_p(header+0x202) == 0x53726448) {
        protocol = lduw_p(header+0x206);
    } else {
        /* This looks like a multiboot kernel. If it is, let's stop
           treating it like a Linux kernel. */
        if (load_multiboot(fw_cfg, f, kernel_filename, initrd_filename,
                           kernel_cmdline, kernel_size, header)) {
            return;
        }
        protocol = 0;
    }

    if (protocol < 0x200 || !(header[0x211] & 0x01)) {
        /* Low kernel */
        real_addr    = 0x90000;
        cmdline_addr = 0x9a000 - cmdline_size;
        prot_addr    = 0x10000;
    } else if (protocol < 0x202) {
        /* High but ancient kernel */
        real_addr    = 0x90000;
        cmdline_addr = 0x9a000 - cmdline_size;
        prot_addr    = 0x100000;
    } else {
        /* High and recent kernel */
        real_addr    = 0x10000;
        cmdline_addr = 0x20000;
        prot_addr    = 0x100000;
    }

#if 0
    fprintf(stderr,
            "qemu: real_addr     = 0x" TARGET_FMT_plx "\n"
            "qemu: cmdline_addr  = 0x" TARGET_FMT_plx "\n"
            "qemu: prot_addr     = 0x" TARGET_FMT_plx "\n",
            real_addr,
            cmdline_addr,
            prot_addr);
#endif

    /* highest address for loading the initrd */
    if (protocol >= 0x203) {
        initrd_max = ldl_p(header+0x22c);
    } else {
        initrd_max = 0x37ffffff;
    }

    if (initrd_max >= max_ram_size-ACPI_DATA_SIZE)
    	initrd_max = max_ram_size-ACPI_DATA_SIZE-1;

    fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_ADDR, cmdline_addr);
    fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, strlen(kernel_cmdline)+1);
    fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, kernel_cmdline);

    if (protocol >= 0x202) {
        stl_p(header+0x228, cmdline_addr);
    } else {
        stw_p(header+0x20, 0xA33F);
        stw_p(header+0x22, cmdline_addr-real_addr);
    }

    /* handle vga= parameter */
    vmode = strstr(kernel_cmdline, "vga=");
    if (vmode) {
        unsigned int video_mode;
        /* skip "vga=" */
        vmode += 4;
        if (!strncmp(vmode, "normal", 6)) {
            video_mode = 0xffff;
        } else if (!strncmp(vmode, "ext", 3)) {
            video_mode = 0xfffe;
        } else if (!strncmp(vmode, "ask", 3)) {
            video_mode = 0xfffd;
        } else {
            video_mode = strtol(vmode, NULL, 0);
        }
        stw_p(header+0x1fa, video_mode);
    }

    /* loader type */
    /* High nybble = B reserved for QEMU; low nybble is revision number.
       If this code is substantially changed, you may want to consider
       incrementing the revision. */
    if (protocol >= 0x200) {
        header[0x210] = 0xB0;
    }
    /* heap */
    if (protocol >= 0x201) {
        header[0x211] |= 0x80;	/* CAN_USE_HEAP */
        stw_p(header+0x224, cmdline_addr-real_addr-0x200);
    }

    /* load initrd */
    if (initrd_filename) {
        if (protocol < 0x200) {
            fprintf(stderr, "qemu: linux kernel too old to load a ram disk\n");
            exit(1);
        }

        initrd_size = get_image_size(initrd_filename);
        if (initrd_size < 0) {
            fprintf(stderr, "qemu: error reading initrd %s: %s\n",
                    initrd_filename, strerror(errno));
            exit(1);
        }

        initrd_addr = (initrd_max-initrd_size) & ~4095;

        initrd_data = g_malloc(initrd_size);
        load_image(initrd_filename, initrd_data);

        fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_ADDR, initrd_addr);
        fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_SIZE, initrd_size);
        fw_cfg_add_bytes(fw_cfg, FW_CFG_INITRD_DATA, initrd_data, initrd_size);

        stl_p(header+0x218, initrd_addr);
        stl_p(header+0x21c, initrd_size);
    }

    /* load kernel and setup */
    setup_size = header[0x1f1];
    if (setup_size == 0) {
        setup_size = 4;
    }
    setup_size = (setup_size+1)*512;
    kernel_size -= setup_size;

    setup  = g_malloc(setup_size);
    kernel = g_malloc(kernel_size);
    fseek(f, 0, SEEK_SET);
    if (fread(setup, 1, setup_size, f) != setup_size) {
        fprintf(stderr, "fread() failed\n");
        exit(1);
    }
    if (fread(kernel, 1, kernel_size, f) != kernel_size) {
        fprintf(stderr, "fread() failed\n");
        exit(1);
    }
    fclose(f);
    memcpy(setup, header, MIN(sizeof(header), setup_size));

    fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_ADDR, prot_addr);
    fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_SIZE, kernel_size);
    fw_cfg_add_bytes(fw_cfg, FW_CFG_KERNEL_DATA, kernel, kernel_size);

    fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_ADDR, real_addr);
    fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_SIZE, setup_size);
    fw_cfg_add_bytes(fw_cfg, FW_CFG_SETUP_DATA, setup, setup_size);

    option_rom[nb_option_roms].name = "linuxboot.bin";
    option_rom[nb_option_roms].bootindex = 0;
    nb_option_roms++;
}

#define NE2000_NB_MAX 6

static const int ne2000_io[NE2000_NB_MAX] = { 0x300, 0x320, 0x340, 0x360,
                                              0x280, 0x380 };
static const int ne2000_irq[NE2000_NB_MAX] = { 9, 10, 11, 3, 4, 5 };

void pc_init_ne2k_isa(ISABus *bus, NICInfo *nd)
{
    static int nb_ne2k = 0;

    if (nb_ne2k == NE2000_NB_MAX)
        return;
    isa_ne2000_init(bus, ne2000_io[nb_ne2k],
                    ne2000_irq[nb_ne2k], nd);
    nb_ne2k++;
}

DeviceState *cpu_get_current_apic(void)
{
    if (current_cpu) {
        X86CPU *cpu = X86_CPU(current_cpu);
        return cpu->apic_state;
    } else {
        return NULL;
    }
}

void pc_acpi_smi_interrupt(void *opaque, int irq, int level)
{
    X86CPU *cpu = opaque;

    if (level) {
        cpu_interrupt(CPU(cpu), CPU_INTERRUPT_SMI);
    }
}

static X86CPU *pc_new_cpu(const char *cpu_model, int64_t apic_id,
                          DeviceState *icc_bridge, Error **errp)
{
    X86CPU *cpu;
    Error *local_err = NULL;

    cpu = cpu_x86_create(cpu_model, icc_bridge, &local_err);
    if (local_err != NULL) {
        error_propagate(errp, local_err);
        return NULL;
    }

    object_property_set_int(OBJECT(cpu), apic_id, "apic-id", &local_err);
    object_property_set_bool(OBJECT(cpu), true, "realized", &local_err);

    if (local_err) {
        error_propagate(errp, local_err);
        object_unref(OBJECT(cpu));
        cpu = NULL;
    }
    return cpu;
}

static const char *current_cpu_model;

void pc_hot_add_cpu(const int64_t id, Error **errp)
{
    DeviceState *icc_bridge;
    int64_t apic_id = x86_cpu_apic_id_from_index(id);

    if (id < 0) {
        error_setg(errp, "Invalid CPU id: %" PRIi64, id);
        return;
    }

    if (cpu_exists(apic_id)) {
        error_setg(errp, "Unable to add CPU: %" PRIi64
                   ", it already exists", id);
        return;
    }

    if (id >= max_cpus) {
        error_setg(errp, "Unable to add CPU: %" PRIi64
                   ", max allowed: %d", id, max_cpus - 1);
        return;
    }

    if (apic_id >= ACPI_CPU_HOTPLUG_ID_LIMIT) {
        error_setg(errp, "Unable to add CPU: %" PRIi64
                   ", resulting APIC ID (%" PRIi64 ") is too large",
                   id, apic_id);
        return;
    }

    icc_bridge = DEVICE(object_resolve_path_type("icc-bridge",
                                                 TYPE_ICC_BRIDGE, NULL));
    pc_new_cpu(current_cpu_model, apic_id, icc_bridge, errp);
}

void pc_cpus_init(const char *cpu_model, DeviceState *icc_bridge)
{
    int i;
    X86CPU *cpu = NULL;
    Error *error = NULL;
    unsigned long apic_id_limit;

    /* init CPUs */
    if (cpu_model == NULL) {
#ifdef TARGET_X86_64
        cpu_model = "qemu64";
#else
        cpu_model = "qemu32";
#endif
    }
    current_cpu_model = cpu_model;

    apic_id_limit = pc_apic_id_limit(max_cpus);
    if (apic_id_limit > ACPI_CPU_HOTPLUG_ID_LIMIT) {
        error_report("max_cpus is too large. APIC ID of last CPU is %lu",
                     apic_id_limit - 1);
        exit(1);
    }

    for (i = 0; i < smp_cpus; i++) {
        cpu = pc_new_cpu(cpu_model, x86_cpu_apic_id_from_index(i),
                         icc_bridge, &error);
        if (error) {
            error_report("%s", error_get_pretty(error));
            error_free(error);
            exit(1);
        }
    }

    /* map APIC MMIO area if CPU has APIC */
    if (cpu && cpu->apic_state) {
        /* XXX: what if the base changes? */
        sysbus_mmio_map_overlap(SYS_BUS_DEVICE(icc_bridge), 0,
                                APIC_DEFAULT_ADDRESS, 0x1000);
    }

    /* tell smbios about cpuid version and features */
    smbios_set_cpuid(cpu->env.cpuid_version, cpu->env.features[FEAT_1_EDX]);
}

/* pci-info ROM file. Little endian format */
typedef struct PcRomPciInfo {
    uint64_t w32_min;
    uint64_t w32_max;
    uint64_t w64_min;
    uint64_t w64_max;
} PcRomPciInfo;

static void pc_fw_cfg_guest_info(PcGuestInfo *guest_info)
{
    PcRomPciInfo *info;
    Object *pci_info;
    bool ambiguous = false;

    if (!guest_info->has_pci_info || !guest_info->fw_cfg) {
        return;
    }
    pci_info = object_resolve_path_type("", TYPE_PCI_HOST_BRIDGE, &ambiguous);
    g_assert(!ambiguous);
    if (!pci_info) {
        return;
    }

    info = g_malloc(sizeof *info);
    info->w32_min = cpu_to_le64(object_property_get_int(pci_info,
                                PCI_HOST_PROP_PCI_HOLE_START, NULL));
    info->w32_max = cpu_to_le64(object_property_get_int(pci_info,
                                PCI_HOST_PROP_PCI_HOLE_END, NULL));
    info->w64_min = cpu_to_le64(object_property_get_int(pci_info,
                                PCI_HOST_PROP_PCI_HOLE64_START, NULL));
    info->w64_max = cpu_to_le64(object_property_get_int(pci_info,
                                PCI_HOST_PROP_PCI_HOLE64_END, NULL));
    /* Pass PCI hole info to guest via a side channel.
     * Required so guest PCI enumeration does the right thing. */
    fw_cfg_add_file(guest_info->fw_cfg, "etc/pci-info", info, sizeof *info);
}

typedef struct PcGuestInfoState {
    PcGuestInfo info;
    Notifier machine_done;
} PcGuestInfoState;

static
void pc_guest_info_machine_done(Notifier *notifier, void *data)
{
    PcGuestInfoState *guest_info_state = container_of(notifier,
                                                      PcGuestInfoState,
                                                      machine_done);
    pc_fw_cfg_guest_info(&guest_info_state->info);
    acpi_setup(&guest_info_state->info);
}

PcGuestInfo *pc_guest_info_init(ram_addr_t below_4g_mem_size,
                                ram_addr_t above_4g_mem_size)
{
    PcGuestInfoState *guest_info_state = g_malloc0(sizeof *guest_info_state);
    PcGuestInfo *guest_info = &guest_info_state->info;
    int i, j;

    guest_info->ram_size_below_4g = below_4g_mem_size;
    guest_info->ram_size = below_4g_mem_size + above_4g_mem_size;
    guest_info->apic_id_limit = pc_apic_id_limit(max_cpus);
    guest_info->apic_xrupt_override = kvm_allows_irq0_override();
    guest_info->numa_nodes = nb_numa_nodes;
    guest_info->node_mem = g_malloc0(guest_info->numa_nodes *
                                    sizeof *guest_info->node_mem);
    for (i = 0; i < nb_numa_nodes; i++) {
        guest_info->node_mem[i] = numa_info[i].node_mem;
    }

    guest_info->node_cpu = g_malloc0(guest_info->apic_id_limit *
                                     sizeof *guest_info->node_cpu);

    for (i = 0; i < max_cpus; i++) {
        unsigned int apic_id = x86_cpu_apic_id_from_index(i);
        assert(apic_id < guest_info->apic_id_limit);
        for (j = 0; j < nb_numa_nodes; j++) {
            if (test_bit(i, numa_info[j].node_cpu)) {
                guest_info->node_cpu[apic_id] = j;
                break;
            }
        }
    }

    guest_info_state->machine_done.notify = pc_guest_info_machine_done;
    qemu_add_machine_init_done_notifier(&guest_info_state->machine_done);
    return guest_info;
}

/* setup pci memory address space mapping into system address space */
void pc_pci_as_mapping_init(Object *owner, MemoryRegion *system_memory,
                            MemoryRegion *pci_address_space)
{
    /* Set to lower priority than RAM */
    memory_region_add_subregion_overlap(system_memory, 0x0,
                                        pci_address_space, -1);
}

void pc_acpi_init(const char *default_dsdt)
{
    char *filename;

    if (acpi_tables != NULL) {
        /* manually set via -acpitable, leave it alone */
        return;
    }

    filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, default_dsdt);
    if (filename == NULL) {
        fprintf(stderr, "WARNING: failed to find %s\n", default_dsdt);
    } else {
        char *arg;
        QemuOpts *opts;
        Error *err = NULL;

        arg = g_strdup_printf("file=%s", filename);

        /* creates a deep copy of "arg" */
        opts = qemu_opts_parse(qemu_find_opts("acpi"), arg, 0);
        g_assert(opts != NULL);

        acpi_table_add_builtin(opts, &err);
        if (err) {
            error_report("WARNING: failed to load %s: %s", filename,
                         error_get_pretty(err));
            error_free(err);
        }
        g_free(arg);
        g_free(filename);
    }
}

FWCfgState *pc_memory_init(MemoryRegion *system_memory,
                           const char *kernel_filename,
                           const char *kernel_cmdline,
                           const char *initrd_filename,
                           ram_addr_t below_4g_mem_size,
                           ram_addr_t above_4g_mem_size,
                           MemoryRegion *rom_memory,
                           MemoryRegion **ram_memory,
                           PcGuestInfo *guest_info)
{
    int linux_boot, i;
    MemoryRegion *ram, *option_rom_mr;
    MemoryRegion *ram_below_4g, *ram_above_4g;
    FWCfgState *fw_cfg;
    ram_addr_t ram_size = below_4g_mem_size + above_4g_mem_size;
    MachineState *machine = MACHINE(qdev_get_machine());
    PCMachineState *pcms = PC_MACHINE(machine);

    linux_boot = (kernel_filename != NULL);

    /* Allocate RAM.  We allocate it as a single memory region and use
     * aliases to address portions of it, mostly for backwards compatibility
     * with older qemus that used qemu_ram_alloc().
     */
    ram = g_malloc(sizeof(*ram));
    memory_region_init_ram(ram, NULL, "pc.ram", ram_size);
    vmstate_register_ram_global(ram);
    *ram_memory = ram;
    ram_below_4g = g_malloc(sizeof(*ram_below_4g));
    memory_region_init_alias(ram_below_4g, NULL, "ram-below-4g", ram,
                             0, below_4g_mem_size);
    memory_region_add_subregion(system_memory, 0, ram_below_4g);
    e820_add_entry(0, below_4g_mem_size, E820_RAM);
    if (above_4g_mem_size > 0) {
        ram_above_4g = g_malloc(sizeof(*ram_above_4g));
        memory_region_init_alias(ram_above_4g, NULL, "ram-above-4g", ram,
                                 below_4g_mem_size, above_4g_mem_size);
        memory_region_add_subregion(system_memory, 0x100000000ULL,
                                    ram_above_4g);
        e820_add_entry(0x100000000ULL, above_4g_mem_size, E820_RAM);
    }

    if (!guest_info->has_reserved_memory &&
        (machine->ram_slots ||
         (machine->maxram_size > ram_size))) {
        MachineClass *mc = MACHINE_GET_CLASS(machine);

        error_report("\"-memory 'slots|maxmem'\" is not supported by: %s",
                     mc->name);
        exit(EXIT_FAILURE);
    }

    /* initialize hotplug memory address space */
    if (guest_info->has_reserved_memory &&
        (ram_size < machine->maxram_size)) {
        ram_addr_t hotplug_mem_size =
            machine->maxram_size - ram_size;

        if (machine->ram_slots > ACPI_MAX_RAM_SLOTS) {
            error_report("unsupported amount of memory slots: %"PRIu64,
                         machine->ram_slots);
            exit(EXIT_FAILURE);
        }

        pcms->hotplug_memory_base =
            ROUND_UP(0x100000000ULL + above_4g_mem_size, 1ULL << 30);

        if ((pcms->hotplug_memory_base + hotplug_mem_size) <
            hotplug_mem_size) {
            error_report("unsupported amount of maximum memory: " RAM_ADDR_FMT,
                         machine->maxram_size);
            exit(EXIT_FAILURE);
        }

        memory_region_init(&pcms->hotplug_memory, OBJECT(pcms),
                           "hotplug-memory", hotplug_mem_size);
        memory_region_add_subregion(system_memory, pcms->hotplug_memory_base,
                                    &pcms->hotplug_memory);
    }

    /* Initialize PC system firmware */
    pc_system_firmware_init(rom_memory, guest_info->isapc_ram_fw);

    option_rom_mr = g_malloc(sizeof(*option_rom_mr));
    memory_region_init_ram(option_rom_mr, NULL, "pc.rom", PC_ROM_SIZE);
    vmstate_register_ram_global(option_rom_mr);
    memory_region_add_subregion_overlap(rom_memory,
                                        PC_ROM_MIN_VGA,
                                        option_rom_mr,
                                        1);

    fw_cfg = bochs_bios_init();
    rom_set_fw(fw_cfg);

    if (guest_info->has_reserved_memory && pcms->hotplug_memory_base) {
        uint64_t *val = g_malloc(sizeof(*val));
        *val = cpu_to_le64(ROUND_UP(pcms->hotplug_memory_base, 0x1ULL << 30));
        fw_cfg_add_file(fw_cfg, "etc/reserved-memory-end", val, sizeof(*val));
    }

    if (linux_boot) {
        load_linux(fw_cfg, kernel_filename, initrd_filename, kernel_cmdline, below_4g_mem_size);
    }

    for (i = 0; i < nb_option_roms; i++) {
        rom_add_option(option_rom[i].name, option_rom[i].bootindex);
    }
    guest_info->fw_cfg = fw_cfg;
    return fw_cfg;
}

qemu_irq *pc_allocate_cpu_irq(void)
{
    return qemu_allocate_irqs(pic_irq_request, NULL, 1);
}

DeviceState *pc_vga_init(ISABus *isa_bus, PCIBus *pci_bus)
{
    DeviceState *dev = NULL;

    if (pci_bus) {
        PCIDevice *pcidev = pci_vga_init(pci_bus);
        dev = pcidev ? &pcidev->qdev : NULL;
    } else if (isa_bus) {
        ISADevice *isadev = isa_vga_init(isa_bus);
        dev = isadev ? DEVICE(isadev) : NULL;
    }
    return dev;
}

static void cpu_request_exit(void *opaque, int irq, int level)
{
    CPUState *cpu = current_cpu;

    if (cpu && level) {
        cpu_exit(cpu);
    }
}

static const MemoryRegionOps ioport80_io_ops = {
    .write = ioport80_write,
    .read = ioport80_read,
    .endianness = DEVICE_NATIVE_ENDIAN,
    .impl = {
        .min_access_size = 1,
        .max_access_size = 1,
    },
};

static const MemoryRegionOps ioportF0_io_ops = {
    .write = ioportF0_write,
    .read = ioportF0_read,
    .endianness = DEVICE_NATIVE_ENDIAN,
    .impl = {
        .min_access_size = 1,
        .max_access_size = 1,
    },
};

void pc_basic_device_init(ISABus *isa_bus, qemu_irq *gsi,
                          ISADevice **rtc_state,
                          ISADevice **floppy,
                          bool no_vmport,
                          uint32 hpet_irqs)
{
    int i;
    DriveInfo *fd[MAX_FD];
    DeviceState *hpet = NULL;
    int pit_isa_irq = 0;
    qemu_irq pit_alt_irq = NULL;
    qemu_irq rtc_irq = NULL;
    qemu_irq *a20_line;
    ISADevice *i8042, *port92, *vmmouse, *pit = NULL;
    qemu_irq *cpu_exit_irq;
    MemoryRegion *ioport80_io = g_new(MemoryRegion, 1);
    MemoryRegion *ioportF0_io = g_new(MemoryRegion, 1);

    memory_region_init_io(ioport80_io, NULL, &ioport80_io_ops, NULL, "ioport80", 1);
    memory_region_add_subregion(isa_bus->address_space_io, 0x80, ioport80_io);

    memory_region_init_io(ioportF0_io, NULL, &ioportF0_io_ops, NULL, "ioportF0", 1);
    memory_region_add_subregion(isa_bus->address_space_io, 0xf0, ioportF0_io);

    /*
     * Check if an HPET shall be created.
     *
     * Without KVM_CAP_PIT_STATE2, we cannot switch off the in-kernel PIT
     * when the HPET wants to take over. Thus we have to disable the latter.
     */
    if (!no_hpet && (!kvm_irqchip_in_kernel() || kvm_has_pit_state2())) {
        /* In order to set property, here not using sysbus_try_create_simple */
        hpet = qdev_try_create(NULL, TYPE_HPET);
        if (hpet) {
            /* For pc-piix-*, hpet's intcap is always IRQ2. For pc-q35-1.7
             * and earlier, use IRQ2 for compat. Otherwise, use IRQ16~23,
             * IRQ8 and IRQ2.
             */
            uint8_t compat = object_property_get_int(OBJECT(hpet),
                    HPET_INTCAP, NULL);
            if (!compat) {
                qdev_prop_set_uint32(hpet, HPET_INTCAP, hpet_irqs);
            }
            qdev_init_nofail(hpet);
            sysbus_mmio_map(SYS_BUS_DEVICE(hpet), 0, HPET_BASE);

            for (i = 0; i < GSI_NUM_PINS; i++) {
                sysbus_connect_irq(SYS_BUS_DEVICE(hpet), i, gsi[i]);
            }
            pit_isa_irq = -1;
            pit_alt_irq = qdev_get_gpio_in(hpet, HPET_LEGACY_PIT_INT);
            rtc_irq = qdev_get_gpio_in(hpet, HPET_LEGACY_RTC_INT);
        }
    }
    *rtc_state = rtc_init(isa_bus, 2000, rtc_irq);

    qemu_register_boot_set(pc_boot_set, *rtc_state);

    if (!xen_enabled()) {
        if (kvm_irqchip_in_kernel()) {
            pit = kvm_pit_init(isa_bus, 0x40);
        } else {
            pit = pit_init(isa_bus, 0x40, pit_isa_irq, pit_alt_irq);
        }
        if (hpet) {
            /* connect PIT to output control line of the HPET */
            qdev_connect_gpio_out(hpet, 0, qdev_get_gpio_in(DEVICE(pit), 0));
        }
        pcspk_init(isa_bus, pit);
    }

    for(i = 0; i < MAX_SERIAL_PORTS; i++) {
        if (serial_hds[i]) {
            serial_isa_init(isa_bus, i, serial_hds[i]);
        }
    }

    for(i = 0; i < MAX_PARALLEL_PORTS; i++) {
        if (parallel_hds[i]) {
            parallel_init(isa_bus, i, parallel_hds[i]);
        }
    }

    a20_line = qemu_allocate_irqs(handle_a20_line_change, first_cpu, 2);
    i8042 = isa_create_simple(isa_bus, "i8042");
    i8042_setup_a20_line(i8042, &a20_line[0]);
    if (!no_vmport) {
        vmport_init(isa_bus);
        vmmouse = isa_try_create(isa_bus, "vmmouse");
    } else {
        vmmouse = NULL;
    }
    if (vmmouse) {
        DeviceState *dev = DEVICE(vmmouse);
        qdev_prop_set_ptr(dev, "ps2_mouse", i8042);
        qdev_init_nofail(dev);
    }
    port92 = isa_create_simple(isa_bus, "port92");
    port92_init(port92, &a20_line[1]);

    cpu_exit_irq = qemu_allocate_irqs(cpu_request_exit, NULL, 1);
    DMA_init(0, cpu_exit_irq);

    for(i = 0; i < MAX_FD; i++) {
        fd[i] = drive_get(IF_FLOPPY, 0, i);
    }
    *floppy = fdctrl_init_isa(isa_bus, fd);
}

void pc_nic_init(ISABus *isa_bus, PCIBus *pci_bus)
{
    int i;

    for (i = 0; i < nb_nics; i++) {
        NICInfo *nd = &nd_table[i];

        if (!pci_bus || (nd->model && strcmp(nd->model, "ne2k_isa") == 0)) {
            pc_init_ne2k_isa(isa_bus, nd);
        } else {
            pci_nic_init_nofail(nd, pci_bus, "e1000", NULL);
        }
    }
}

void pc_pci_device_init(PCIBus *pci_bus)
{
    int max_bus;
    int bus;

    max_bus = drive_get_max_bus(IF_SCSI);
    for (bus = 0; bus <= max_bus; bus++) {
        pci_create_simple(pci_bus, -1, "lsi53c895a");
    }
}

void ioapic_init_gsi(GSIState *gsi_state, const char *parent_name)
{
    DeviceState *dev;
    SysBusDevice *d;
    unsigned int i;

    if (kvm_irqchip_in_kernel()) {
        dev = qdev_create(NULL, "kvm-ioapic");
    } else {
        dev = qdev_create(NULL, "ioapic");
    }
    if (parent_name) {
        object_property_add_child(object_resolve_path(parent_name, NULL),
                                  "ioapic", OBJECT(dev), NULL);
    }
    qdev_init_nofail(dev);
    d = SYS_BUS_DEVICE(dev);
    sysbus_mmio_map(d, 0, IO_APIC_DEFAULT_ADDRESS);

    for (i = 0; i < IOAPIC_NUM_PINS; i++) {
        gsi_state->ioapic_irq[i] = qdev_get_gpio_in(dev, i);
    }
}

static void pc_generic_machine_class_init(ObjectClass *oc, void *data)
{
    MachineClass *mc = MACHINE_CLASS(oc);
    QEMUMachine *qm = data;

    mc->name = qm->name;
    mc->alias = qm->alias;
    mc->desc = qm->desc;
    mc->init = qm->init;
    mc->reset = qm->reset;
    mc->hot_add_cpu = qm->hot_add_cpu;
    mc->kvm_type = qm->kvm_type;
    mc->block_default_type = qm->block_default_type;
    mc->max_cpus = qm->max_cpus;
    mc->no_serial = qm->no_serial;
    mc->no_parallel = qm->no_parallel;
    mc->use_virtcon = qm->use_virtcon;
    mc->use_sclp = qm->use_sclp;
    mc->no_floppy = qm->no_floppy;
    mc->no_cdrom = qm->no_cdrom;
    mc->no_sdcard = qm->no_sdcard;
    mc->is_default = qm->is_default;
    mc->default_machine_opts = qm->default_machine_opts;
    mc->default_boot_order = qm->default_boot_order;
    mc->compat_props = qm->compat_props;
    mc->hw_version = qm->hw_version;
}

void qemu_register_pc_machine(QEMUMachine *m)
{
    char *name = g_strconcat(m->name, TYPE_MACHINE_SUFFIX, NULL);
    TypeInfo ti = {
        .name       = name,
        .parent     = TYPE_PC_MACHINE,
        .class_init = pc_generic_machine_class_init,
        .class_data = (void *)m,
    };

    type_register(&ti);
    g_free(name);
}

static void pc_dimm_plug(HotplugHandler *hotplug_dev,
                         DeviceState *dev, Error **errp)
{
    int slot;
    HotplugHandlerClass *hhc;
    Error *local_err = NULL;
    PCMachineState *pcms = PC_MACHINE(hotplug_dev);
    MachineState *machine = MACHINE(hotplug_dev);
    PCDIMMDevice *dimm = PC_DIMM(dev);
    PCDIMMDeviceClass *ddc = PC_DIMM_GET_CLASS(dimm);
    MemoryRegion *mr = ddc->get_memory_region(dimm);
    uint64_t addr = object_property_get_int(OBJECT(dimm), PC_DIMM_ADDR_PROP,
                                            &local_err);
    if (local_err) {
        goto out;
    }

    addr = pc_dimm_get_free_addr(pcms->hotplug_memory_base,
                                 memory_region_size(&pcms->hotplug_memory),
                                 !addr ? NULL : &addr,
                                 memory_region_size(mr), &local_err);
    if (local_err) {
        goto out;
    }

    object_property_set_int(OBJECT(dev), addr, PC_DIMM_ADDR_PROP, &local_err);
    if (local_err) {
        goto out;
    }
    trace_mhp_pc_dimm_assigned_address(addr);

    slot = object_property_get_int(OBJECT(dev), PC_DIMM_SLOT_PROP, &local_err);
    if (local_err) {
        goto out;
    }

    slot = pc_dimm_get_free_slot(slot == PC_DIMM_UNASSIGNED_SLOT ? NULL : &slot,
                                 machine->ram_slots, &local_err);
    if (local_err) {
        goto out;
    }
    object_property_set_int(OBJECT(dev), slot, PC_DIMM_SLOT_PROP, &local_err);
    if (local_err) {
        goto out;
    }
    trace_mhp_pc_dimm_assigned_slot(slot);

    if (!pcms->acpi_dev) {
        error_setg(&local_err,
                   "memory hotplug is not enabled: missing acpi device");
        goto out;
    }

    memory_region_add_subregion(&pcms->hotplug_memory,
                                addr - pcms->hotplug_memory_base, mr);
    vmstate_register_ram(mr, dev);

    hhc = HOTPLUG_HANDLER_GET_CLASS(pcms->acpi_dev);
    hhc->plug(HOTPLUG_HANDLER(pcms->acpi_dev), dev, &local_err);
out:
    error_propagate(errp, local_err);
}

static void pc_machine_device_plug_cb(HotplugHandler *hotplug_dev,
                                      DeviceState *dev, Error **errp)
{
    if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
        pc_dimm_plug(hotplug_dev, dev, errp);
    }
}

static HotplugHandler *pc_get_hotpug_handler(MachineState *machine,
                                             DeviceState *dev)
{
    PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(machine);

    if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
        return HOTPLUG_HANDLER(machine);
    }

    return pcmc->get_hotplug_handler ?
        pcmc->get_hotplug_handler(machine, dev) : NULL;
}

static void
pc_machine_get_hotplug_memory_region_size(Object *obj, Visitor *v, void *opaque,
                                          const char *name, Error **errp)
{
    PCMachineState *pcms = PC_MACHINE(obj);
    int64_t value = memory_region_size(&pcms->hotplug_memory);

    visit_type_int(v, &value, name, errp);
}

static void pc_machine_initfn(Object *obj)
{
    object_property_add(obj, PC_MACHINE_MEMHP_REGION_SIZE, "int",
                        pc_machine_get_hotplug_memory_region_size,
                        NULL, NULL, NULL, NULL);
}

static void pc_machine_class_init(ObjectClass *oc, void *data)
{
    MachineClass *mc = MACHINE_CLASS(oc);
    PCMachineClass *pcmc = PC_MACHINE_CLASS(oc);
    HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc);

    pcmc->get_hotplug_handler = mc->get_hotplug_handler;
    mc->get_hotplug_handler = pc_get_hotpug_handler;
    hc->plug = pc_machine_device_plug_cb;
}

static const TypeInfo pc_machine_info = {
    .name = TYPE_PC_MACHINE,
    .parent = TYPE_MACHINE,
    .abstract = true,
    .instance_size = sizeof(PCMachineState),
    .instance_init = pc_machine_initfn,
    .class_size = sizeof(PCMachineClass),
    .class_init = pc_machine_class_init,
    .interfaces = (InterfaceInfo[]) {
         { TYPE_HOTPLUG_HANDLER },
         { }
    },
};

static void pc_machine_register_types(void)
{
    type_register_static(&pc_machine_info);
}

type_init(pc_machine_register_types)