aboutsummaryrefslogtreecommitdiff
path: root/hw/ppc/spapr.c
blob: 2b2cc0cfc791fbb37d3ae61f9ef5d36e7a760f19 (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
/*
 * QEMU PowerPC pSeries Logical Partition (aka sPAPR) hardware System Emulator
 *
 * Copyright (c) 2004-2007 Fabrice Bellard
 * Copyright (c) 2007 Jocelyn Mayer
 * Copyright (c) 2010 David Gibson, IBM Corporation.
 *
 * 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 "sysemu/sysemu.h"
#include "hw/hw.h"
#include "hw/fw-path-provider.h"
#include "elf.h"
#include "net/net.h"
#include "sysemu/block-backend.h"
#include "sysemu/cpus.h"
#include "sysemu/kvm.h"
#include "kvm_ppc.h"
#include "mmu-hash64.h"
#include "qom/cpu.h"

#include "hw/boards.h"
#include "hw/ppc/ppc.h"
#include "hw/loader.h"

#include "hw/ppc/spapr.h"
#include "hw/ppc/spapr_vio.h"
#include "hw/pci-host/spapr.h"
#include "hw/ppc/xics.h"
#include "hw/pci/msi.h"

#include "hw/pci/pci.h"
#include "hw/scsi/scsi.h"
#include "hw/virtio/virtio-scsi.h"

#include "exec/address-spaces.h"
#include "hw/usb.h"
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "trace.h"
#include "hw/nmi.h"

#include "hw/compat.h"

#include <libfdt.h>

/* SLOF memory layout:
 *
 * SLOF raw image loaded at 0, copies its romfs right below the flat
 * device-tree, then position SLOF itself 31M below that
 *
 * So we set FW_OVERHEAD to 40MB which should account for all of that
 * and more
 *
 * We load our kernel at 4M, leaving space for SLOF initial image
 */
#define FDT_MAX_SIZE            0x40000
#define RTAS_MAX_SIZE           0x10000
#define RTAS_MAX_ADDR           0x80000000 /* RTAS must stay below that */
#define FW_MAX_SIZE             0x400000
#define FW_FILE_NAME            "slof.bin"
#define FW_OVERHEAD             0x2800000
#define KERNEL_LOAD_ADDR        FW_MAX_SIZE

#define MIN_RMA_SLOF            128UL

#define TIMEBASE_FREQ           512000000ULL

#define MAX_CPUS                255

#define PHANDLE_XICP            0x00001111

#define HTAB_SIZE(spapr)        (1ULL << ((spapr)->htab_shift))

typedef struct sPAPRMachineState sPAPRMachineState;

#define TYPE_SPAPR_MACHINE      "spapr-machine"
#define SPAPR_MACHINE(obj) \
    OBJECT_CHECK(sPAPRMachineState, (obj), TYPE_SPAPR_MACHINE)

/**
 * sPAPRMachineState:
 */
struct sPAPRMachineState {
    /*< private >*/
    MachineState parent_obj;

    /*< public >*/
    char *kvm_type;
};

sPAPREnvironment *spapr;

static XICSState *try_create_xics(const char *type, int nr_servers,
                                  int nr_irqs)
{
    DeviceState *dev;

    dev = qdev_create(NULL, type);
    qdev_prop_set_uint32(dev, "nr_servers", nr_servers);
    qdev_prop_set_uint32(dev, "nr_irqs", nr_irqs);
    if (qdev_init(dev) < 0) {
        return NULL;
    }

    return XICS_COMMON(dev);
}

static XICSState *xics_system_init(int nr_servers, int nr_irqs)
{
    XICSState *icp = NULL;

    if (kvm_enabled()) {
        QemuOpts *machine_opts = qemu_get_machine_opts();
        bool irqchip_allowed = qemu_opt_get_bool(machine_opts,
                                                "kernel_irqchip", true);
        bool irqchip_required = qemu_opt_get_bool(machine_opts,
                                                  "kernel_irqchip", false);
        if (irqchip_allowed) {
            icp = try_create_xics(TYPE_KVM_XICS, nr_servers, nr_irqs);
        }

        if (irqchip_required && !icp) {
            perror("Failed to create in-kernel XICS\n");
            abort();
        }
    }

    if (!icp) {
        icp = try_create_xics(TYPE_XICS, nr_servers, nr_irqs);
    }

    if (!icp) {
        perror("Failed to create XICS\n");
        abort();
    }

    return icp;
}

static int spapr_fixup_cpu_smt_dt(void *fdt, int offset, PowerPCCPU *cpu,
                                  int smt_threads)
{
    int i, ret = 0;
    uint32_t servers_prop[smt_threads];
    uint32_t gservers_prop[smt_threads * 2];
    int index = ppc_get_vcpu_dt_id(cpu);

    if (cpu->cpu_version) {
        ret = fdt_setprop_cell(fdt, offset, "cpu-version", cpu->cpu_version);
        if (ret < 0) {
            return ret;
        }
    }

    /* Build interrupt servers and gservers properties */
    for (i = 0; i < smt_threads; i++) {
        servers_prop[i] = cpu_to_be32(index + i);
        /* Hack, direct the group queues back to cpu 0 */
        gservers_prop[i*2] = cpu_to_be32(index + i);
        gservers_prop[i*2 + 1] = 0;
    }
    ret = fdt_setprop(fdt, offset, "ibm,ppc-interrupt-server#s",
                      servers_prop, sizeof(servers_prop));
    if (ret < 0) {
        return ret;
    }
    ret = fdt_setprop(fdt, offset, "ibm,ppc-interrupt-gserver#s",
                      gservers_prop, sizeof(gservers_prop));

    return ret;
}

static int spapr_fixup_cpu_dt(void *fdt, sPAPREnvironment *spapr)
{
    int ret = 0, offset, cpus_offset;
    CPUState *cs;
    char cpu_model[32];
    int smt = kvmppc_smt_threads();
    uint32_t pft_size_prop[] = {0, cpu_to_be32(spapr->htab_shift)};

    CPU_FOREACH(cs) {
        PowerPCCPU *cpu = POWERPC_CPU(cs);
        DeviceClass *dc = DEVICE_GET_CLASS(cs);
        int index = ppc_get_vcpu_dt_id(cpu);
        uint32_t associativity[] = {cpu_to_be32(0x5),
                                    cpu_to_be32(0x0),
                                    cpu_to_be32(0x0),
                                    cpu_to_be32(0x0),
                                    cpu_to_be32(cs->numa_node),
                                    cpu_to_be32(index)};

        if ((index % smt) != 0) {
            continue;
        }

        snprintf(cpu_model, 32, "%s@%x", dc->fw_name, index);

        cpus_offset = fdt_path_offset(fdt, "/cpus");
        if (cpus_offset < 0) {
            cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"),
                                          "cpus");
            if (cpus_offset < 0) {
                return cpus_offset;
            }
        }
        offset = fdt_subnode_offset(fdt, cpus_offset, cpu_model);
        if (offset < 0) {
            offset = fdt_add_subnode(fdt, cpus_offset, cpu_model);
            if (offset < 0) {
                return offset;
            }
        }

        if (nb_numa_nodes > 1) {
            ret = fdt_setprop(fdt, offset, "ibm,associativity", associativity,
                              sizeof(associativity));
            if (ret < 0) {
                return ret;
            }
        }

        ret = fdt_setprop(fdt, offset, "ibm,pft-size",
                          pft_size_prop, sizeof(pft_size_prop));
        if (ret < 0) {
            return ret;
        }

        ret = spapr_fixup_cpu_smt_dt(fdt, offset, cpu,
                                     ppc_get_compat_smt_threads(cpu));
        if (ret < 0) {
            return ret;
        }
    }
    return ret;
}


static size_t create_page_sizes_prop(CPUPPCState *env, uint32_t *prop,
                                     size_t maxsize)
{
    size_t maxcells = maxsize / sizeof(uint32_t);
    int i, j, count;
    uint32_t *p = prop;

    for (i = 0; i < PPC_PAGE_SIZES_MAX_SZ; i++) {
        struct ppc_one_seg_page_size *sps = &env->sps.sps[i];

        if (!sps->page_shift) {
            break;
        }
        for (count = 0; count < PPC_PAGE_SIZES_MAX_SZ; count++) {
            if (sps->enc[count].page_shift == 0) {
                break;
            }
        }
        if ((p - prop) >= (maxcells - 3 - count * 2)) {
            break;
        }
        *(p++) = cpu_to_be32(sps->page_shift);
        *(p++) = cpu_to_be32(sps->slb_enc);
        *(p++) = cpu_to_be32(count);
        for (j = 0; j < count; j++) {
            *(p++) = cpu_to_be32(sps->enc[j].page_shift);
            *(p++) = cpu_to_be32(sps->enc[j].pte_enc);
        }
    }

    return (p - prop) * sizeof(uint32_t);
}

static hwaddr spapr_node0_size(void)
{
    if (nb_numa_nodes) {
        int i;
        for (i = 0; i < nb_numa_nodes; ++i) {
            if (numa_info[i].node_mem) {
                return MIN(pow2floor(numa_info[i].node_mem), ram_size);
            }
        }
    }
    return ram_size;
}

#define _FDT(exp) \
    do { \
        int ret = (exp);                                           \
        if (ret < 0) {                                             \
            fprintf(stderr, "qemu: error creating device tree: %s: %s\n", \
                    #exp, fdt_strerror(ret));                      \
            exit(1);                                               \
        }                                                          \
    } while (0)

static void add_str(GString *s, const gchar *s1)
{
    g_string_append_len(s, s1, strlen(s1) + 1);
}

static void *spapr_create_fdt_skel(hwaddr initrd_base,
                                   hwaddr initrd_size,
                                   hwaddr kernel_size,
                                   bool little_endian,
                                   const char *boot_device,
                                   const char *kernel_cmdline,
                                   uint32_t epow_irq)
{
    void *fdt;
    CPUState *cs;
    uint32_t start_prop = cpu_to_be32(initrd_base);
    uint32_t end_prop = cpu_to_be32(initrd_base + initrd_size);
    GString *hypertas = g_string_sized_new(256);
    GString *qemu_hypertas = g_string_sized_new(256);
    uint32_t refpoints[] = {cpu_to_be32(0x4), cpu_to_be32(0x4)};
    uint32_t interrupt_server_ranges_prop[] = {0, cpu_to_be32(smp_cpus)};
    int smt = kvmppc_smt_threads();
    unsigned char vec5[] = {0x0, 0x0, 0x0, 0x0, 0x0, 0x80};
    QemuOpts *opts = qemu_opts_find(qemu_find_opts("smp-opts"), NULL);
    unsigned sockets = opts ? qemu_opt_get_number(opts, "sockets", 0) : 0;
    uint32_t cpus_per_socket = sockets ? (smp_cpus / sockets) : 1;
    char *buf;

    add_str(hypertas, "hcall-pft");
    add_str(hypertas, "hcall-term");
    add_str(hypertas, "hcall-dabr");
    add_str(hypertas, "hcall-interrupt");
    add_str(hypertas, "hcall-tce");
    add_str(hypertas, "hcall-vio");
    add_str(hypertas, "hcall-splpar");
    add_str(hypertas, "hcall-bulk");
    add_str(hypertas, "hcall-set-mode");
    add_str(qemu_hypertas, "hcall-memop1");

    fdt = g_malloc0(FDT_MAX_SIZE);
    _FDT((fdt_create(fdt, FDT_MAX_SIZE)));

    if (kernel_size) {
        _FDT((fdt_add_reservemap_entry(fdt, KERNEL_LOAD_ADDR, kernel_size)));
    }
    if (initrd_size) {
        _FDT((fdt_add_reservemap_entry(fdt, initrd_base, initrd_size)));
    }
    _FDT((fdt_finish_reservemap(fdt)));

    /* Root node */
    _FDT((fdt_begin_node(fdt, "")));
    _FDT((fdt_property_string(fdt, "device_type", "chrp")));
    _FDT((fdt_property_string(fdt, "model", "IBM pSeries (emulated by qemu)")));
    _FDT((fdt_property_string(fdt, "compatible", "qemu,pseries")));

    /*
     * Add info to guest to indentify which host is it being run on
     * and what is the uuid of the guest
     */
    if (kvmppc_get_host_model(&buf)) {
        _FDT((fdt_property_string(fdt, "host-model", buf)));
        g_free(buf);
    }
    if (kvmppc_get_host_serial(&buf)) {
        _FDT((fdt_property_string(fdt, "host-serial", buf)));
        g_free(buf);
    }

    buf = g_strdup_printf(UUID_FMT, qemu_uuid[0], qemu_uuid[1],
                          qemu_uuid[2], qemu_uuid[3], qemu_uuid[4],
                          qemu_uuid[5], qemu_uuid[6], qemu_uuid[7],
                          qemu_uuid[8], qemu_uuid[9], qemu_uuid[10],
                          qemu_uuid[11], qemu_uuid[12], qemu_uuid[13],
                          qemu_uuid[14], qemu_uuid[15]);

    _FDT((fdt_property_string(fdt, "vm,uuid", buf)));
    g_free(buf);

    _FDT((fdt_property_cell(fdt, "#address-cells", 0x2)));
    _FDT((fdt_property_cell(fdt, "#size-cells", 0x2)));

    /* /chosen */
    _FDT((fdt_begin_node(fdt, "chosen")));

    /* Set Form1_affinity */
    _FDT((fdt_property(fdt, "ibm,architecture-vec-5", vec5, sizeof(vec5))));

    _FDT((fdt_property_string(fdt, "bootargs", kernel_cmdline)));
    _FDT((fdt_property(fdt, "linux,initrd-start",
                       &start_prop, sizeof(start_prop))));
    _FDT((fdt_property(fdt, "linux,initrd-end",
                       &end_prop, sizeof(end_prop))));
    if (kernel_size) {
        uint64_t kprop[2] = { cpu_to_be64(KERNEL_LOAD_ADDR),
                              cpu_to_be64(kernel_size) };

        _FDT((fdt_property(fdt, "qemu,boot-kernel", &kprop, sizeof(kprop))));
        if (little_endian) {
            _FDT((fdt_property(fdt, "qemu,boot-kernel-le", NULL, 0)));
        }
    }
    if (boot_device) {
        _FDT((fdt_property_string(fdt, "qemu,boot-device", boot_device)));
    }
    if (boot_menu) {
        _FDT((fdt_property_cell(fdt, "qemu,boot-menu", boot_menu)));
    }
    _FDT((fdt_property_cell(fdt, "qemu,graphic-width", graphic_width)));
    _FDT((fdt_property_cell(fdt, "qemu,graphic-height", graphic_height)));
    _FDT((fdt_property_cell(fdt, "qemu,graphic-depth", graphic_depth)));

    _FDT((fdt_end_node(fdt)));

    /* cpus */
    _FDT((fdt_begin_node(fdt, "cpus")));

    _FDT((fdt_property_cell(fdt, "#address-cells", 0x1)));
    _FDT((fdt_property_cell(fdt, "#size-cells", 0x0)));

    CPU_FOREACH(cs) {
        PowerPCCPU *cpu = POWERPC_CPU(cs);
        CPUPPCState *env = &cpu->env;
        DeviceClass *dc = DEVICE_GET_CLASS(cs);
        PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cs);
        int index = ppc_get_vcpu_dt_id(cpu);
        char *nodename;
        uint32_t segs[] = {cpu_to_be32(28), cpu_to_be32(40),
                           0xffffffff, 0xffffffff};
        uint32_t tbfreq = kvm_enabled() ? kvmppc_get_tbfreq() : TIMEBASE_FREQ;
        uint32_t cpufreq = kvm_enabled() ? kvmppc_get_clockfreq() : 1000000000;
        uint32_t page_sizes_prop[64];
        size_t page_sizes_prop_size;

        if ((index % smt) != 0) {
            continue;
        }

        nodename = g_strdup_printf("%s@%x", dc->fw_name, index);

        _FDT((fdt_begin_node(fdt, nodename)));

        g_free(nodename);

        _FDT((fdt_property_cell(fdt, "reg", index)));
        _FDT((fdt_property_string(fdt, "device_type", "cpu")));

        _FDT((fdt_property_cell(fdt, "cpu-version", env->spr[SPR_PVR])));
        _FDT((fdt_property_cell(fdt, "d-cache-block-size",
                                env->dcache_line_size)));
        _FDT((fdt_property_cell(fdt, "d-cache-line-size",
                                env->dcache_line_size)));
        _FDT((fdt_property_cell(fdt, "i-cache-block-size",
                                env->icache_line_size)));
        _FDT((fdt_property_cell(fdt, "i-cache-line-size",
                                env->icache_line_size)));

        if (pcc->l1_dcache_size) {
            _FDT((fdt_property_cell(fdt, "d-cache-size", pcc->l1_dcache_size)));
        } else {
            fprintf(stderr, "Warning: Unknown L1 dcache size for cpu\n");
        }
        if (pcc->l1_icache_size) {
            _FDT((fdt_property_cell(fdt, "i-cache-size", pcc->l1_icache_size)));
        } else {
            fprintf(stderr, "Warning: Unknown L1 icache size for cpu\n");
        }

        _FDT((fdt_property_cell(fdt, "timebase-frequency", tbfreq)));
        _FDT((fdt_property_cell(fdt, "clock-frequency", cpufreq)));
        _FDT((fdt_property_cell(fdt, "ibm,slb-size", env->slb_nr)));
        _FDT((fdt_property_string(fdt, "status", "okay")));
        _FDT((fdt_property(fdt, "64-bit", NULL, 0)));

        if (env->spr_cb[SPR_PURR].oea_read) {
            _FDT((fdt_property(fdt, "ibm,purr", NULL, 0)));
        }

        if (env->mmu_model & POWERPC_MMU_1TSEG) {
            _FDT((fdt_property(fdt, "ibm,processor-segment-sizes",
                               segs, sizeof(segs))));
        }

        /* Advertise VMX/VSX (vector extensions) if available
         *   0 / no property == no vector extensions
         *   1               == VMX / Altivec available
         *   2               == VSX available */
        if (env->insns_flags & PPC_ALTIVEC) {
            uint32_t vmx = (env->insns_flags2 & PPC2_VSX) ? 2 : 1;

            _FDT((fdt_property_cell(fdt, "ibm,vmx", vmx)));
        }

        /* Advertise DFP (Decimal Floating Point) if available
         *   0 / no property == no DFP
         *   1               == DFP available */
        if (env->insns_flags2 & PPC2_DFP) {
            _FDT((fdt_property_cell(fdt, "ibm,dfp", 1)));
        }

        page_sizes_prop_size = create_page_sizes_prop(env, page_sizes_prop,
                                                      sizeof(page_sizes_prop));
        if (page_sizes_prop_size) {
            _FDT((fdt_property(fdt, "ibm,segment-page-sizes",
                               page_sizes_prop, page_sizes_prop_size)));
        }

        _FDT((fdt_property_cell(fdt, "ibm,chip-id",
                                cs->cpu_index / cpus_per_socket)));

        _FDT((fdt_end_node(fdt)));
    }

    _FDT((fdt_end_node(fdt)));

    /* RTAS */
    _FDT((fdt_begin_node(fdt, "rtas")));

    if (!kvm_enabled() || kvmppc_spapr_use_multitce()) {
        add_str(hypertas, "hcall-multi-tce");
    }
    _FDT((fdt_property(fdt, "ibm,hypertas-functions", hypertas->str,
                       hypertas->len)));
    g_string_free(hypertas, TRUE);
    _FDT((fdt_property(fdt, "qemu,hypertas-functions", qemu_hypertas->str,
                       qemu_hypertas->len)));
    g_string_free(qemu_hypertas, TRUE);

    _FDT((fdt_property(fdt, "ibm,associativity-reference-points",
        refpoints, sizeof(refpoints))));

    _FDT((fdt_property_cell(fdt, "rtas-error-log-max", RTAS_ERROR_LOG_MAX)));

    /*
     * According to PAPR, rtas ibm,os-term does not guarantee a return
     * back to the guest cpu.
     *
     * While an additional ibm,extended-os-term property indicates that
     * rtas call return will always occur. Set this property.
     */
    _FDT((fdt_property(fdt, "ibm,extended-os-term", NULL, 0)));

    _FDT((fdt_end_node(fdt)));

    /* interrupt controller */
    _FDT((fdt_begin_node(fdt, "interrupt-controller")));

    _FDT((fdt_property_string(fdt, "device_type",
                              "PowerPC-External-Interrupt-Presentation")));
    _FDT((fdt_property_string(fdt, "compatible", "IBM,ppc-xicp")));
    _FDT((fdt_property(fdt, "interrupt-controller", NULL, 0)));
    _FDT((fdt_property(fdt, "ibm,interrupt-server-ranges",
                       interrupt_server_ranges_prop,
                       sizeof(interrupt_server_ranges_prop))));
    _FDT((fdt_property_cell(fdt, "#interrupt-cells", 2)));
    _FDT((fdt_property_cell(fdt, "linux,phandle", PHANDLE_XICP)));
    _FDT((fdt_property_cell(fdt, "phandle", PHANDLE_XICP)));

    _FDT((fdt_end_node(fdt)));

    /* vdevice */
    _FDT((fdt_begin_node(fdt, "vdevice")));

    _FDT((fdt_property_string(fdt, "device_type", "vdevice")));
    _FDT((fdt_property_string(fdt, "compatible", "IBM,vdevice")));
    _FDT((fdt_property_cell(fdt, "#address-cells", 0x1)));
    _FDT((fdt_property_cell(fdt, "#size-cells", 0x0)));
    _FDT((fdt_property_cell(fdt, "#interrupt-cells", 0x2)));
    _FDT((fdt_property(fdt, "interrupt-controller", NULL, 0)));

    _FDT((fdt_end_node(fdt)));

    /* event-sources */
    spapr_events_fdt_skel(fdt, epow_irq);

    /* /hypervisor node */
    if (kvm_enabled()) {
        uint8_t hypercall[16];

        /* indicate KVM hypercall interface */
        _FDT((fdt_begin_node(fdt, "hypervisor")));
        _FDT((fdt_property_string(fdt, "compatible", "linux,kvm")));
        if (kvmppc_has_cap_fixup_hcalls()) {
            /*
             * Older KVM versions with older guest kernels were broken with the
             * magic page, don't allow the guest to map it.
             */
            kvmppc_get_hypercall(first_cpu->env_ptr, hypercall,
                                 sizeof(hypercall));
            _FDT((fdt_property(fdt, "hcall-instructions", hypercall,
                              sizeof(hypercall))));
        }
        _FDT((fdt_end_node(fdt)));
    }

    _FDT((fdt_end_node(fdt))); /* close root node */
    _FDT((fdt_finish(fdt)));

    return fdt;
}

int spapr_h_cas_compose_response(target_ulong addr, target_ulong size)
{
    void *fdt, *fdt_skel;
    sPAPRDeviceTreeUpdateHeader hdr = { .version_id = 1 };

    size -= sizeof(hdr);

    /* Create sceleton */
    fdt_skel = g_malloc0(size);
    _FDT((fdt_create(fdt_skel, size)));
    _FDT((fdt_begin_node(fdt_skel, "")));
    _FDT((fdt_end_node(fdt_skel)));
    _FDT((fdt_finish(fdt_skel)));
    fdt = g_malloc0(size);
    _FDT((fdt_open_into(fdt_skel, fdt, size)));
    g_free(fdt_skel);

    /* Fix skeleton up */
    _FDT((spapr_fixup_cpu_dt(fdt, spapr)));

    /* Pack resulting tree */
    _FDT((fdt_pack(fdt)));

    if (fdt_totalsize(fdt) + sizeof(hdr) > size) {
        trace_spapr_cas_failed(size);
        return -1;
    }

    cpu_physical_memory_write(addr, &hdr, sizeof(hdr));
    cpu_physical_memory_write(addr + sizeof(hdr), fdt, fdt_totalsize(fdt));
    trace_spapr_cas_continue(fdt_totalsize(fdt) + sizeof(hdr));
    g_free(fdt);

    return 0;
}

static void spapr_populate_memory_node(void *fdt, int nodeid, hwaddr start,
                                       hwaddr size)
{
    uint32_t associativity[] = {
        cpu_to_be32(0x4), /* length */
        cpu_to_be32(0x0), cpu_to_be32(0x0),
        cpu_to_be32(0x0), cpu_to_be32(nodeid)
    };
    char mem_name[32];
    uint64_t mem_reg_property[2];
    int off;

    mem_reg_property[0] = cpu_to_be64(start);
    mem_reg_property[1] = cpu_to_be64(size);

    sprintf(mem_name, "memory@" TARGET_FMT_lx, start);
    off = fdt_add_subnode(fdt, 0, mem_name);
    _FDT(off);
    _FDT((fdt_setprop_string(fdt, off, "device_type", "memory")));
    _FDT((fdt_setprop(fdt, off, "reg", mem_reg_property,
                      sizeof(mem_reg_property))));
    _FDT((fdt_setprop(fdt, off, "ibm,associativity", associativity,
                      sizeof(associativity))));
}

static int spapr_populate_memory(sPAPREnvironment *spapr, void *fdt)
{
    hwaddr mem_start, node_size;
    int i, nb_nodes = nb_numa_nodes;
    NodeInfo *nodes = numa_info;
    NodeInfo ramnode;

    /* No NUMA nodes, assume there is just one node with whole RAM */
    if (!nb_numa_nodes) {
        nb_nodes = 1;
        ramnode.node_mem = ram_size;
        nodes = &ramnode;
    }

    for (i = 0, mem_start = 0; i < nb_nodes; ++i) {
        if (!nodes[i].node_mem) {
            continue;
        }
        if (mem_start >= ram_size) {
            node_size = 0;
        } else {
            node_size = nodes[i].node_mem;
            if (node_size > ram_size - mem_start) {
                node_size = ram_size - mem_start;
            }
        }
        if (!mem_start) {
            /* ppc_spapr_init() checks for rma_size <= node0_size already */
            spapr_populate_memory_node(fdt, i, 0, spapr->rma_size);
            mem_start += spapr->rma_size;
            node_size -= spapr->rma_size;
        }
        for ( ; node_size; ) {
            hwaddr sizetmp = pow2floor(node_size);

            /* mem_start != 0 here */
            if (ctzl(mem_start) < ctzl(sizetmp)) {
                sizetmp = 1ULL << ctzl(mem_start);
            }

            spapr_populate_memory_node(fdt, i, mem_start, sizetmp);
            node_size -= sizetmp;
            mem_start += sizetmp;
        }
    }

    return 0;
}

static void spapr_finalize_fdt(sPAPREnvironment *spapr,
                               hwaddr fdt_addr,
                               hwaddr rtas_addr,
                               hwaddr rtas_size)
{
    int ret, i;
    size_t cb = 0;
    char *bootlist;
    void *fdt;
    sPAPRPHBState *phb;

    fdt = g_malloc(FDT_MAX_SIZE);

    /* open out the base tree into a temp buffer for the final tweaks */
    _FDT((fdt_open_into(spapr->fdt_skel, fdt, FDT_MAX_SIZE)));

    ret = spapr_populate_memory(spapr, fdt);
    if (ret < 0) {
        fprintf(stderr, "couldn't setup memory nodes in fdt\n");
        exit(1);
    }

    ret = spapr_populate_vdevice(spapr->vio_bus, fdt);
    if (ret < 0) {
        fprintf(stderr, "couldn't setup vio devices in fdt\n");
        exit(1);
    }

    QLIST_FOREACH(phb, &spapr->phbs, list) {
        ret = spapr_populate_pci_dt(phb, PHANDLE_XICP, fdt);
    }

    if (ret < 0) {
        fprintf(stderr, "couldn't setup PCI devices in fdt\n");
        exit(1);
    }

    /* RTAS */
    ret = spapr_rtas_device_tree_setup(fdt, rtas_addr, rtas_size);
    if (ret < 0) {
        fprintf(stderr, "Couldn't set up RTAS device tree properties\n");
    }

    /* Advertise NUMA via ibm,associativity */
    ret = spapr_fixup_cpu_dt(fdt, spapr);
    if (ret < 0) {
        fprintf(stderr, "Couldn't finalize CPU device tree properties\n");
    }

    bootlist = get_boot_devices_list(&cb, true);
    if (cb && bootlist) {
        int offset = fdt_path_offset(fdt, "/chosen");
        if (offset < 0) {
            exit(1);
        }
        for (i = 0; i < cb; i++) {
            if (bootlist[i] == '\n') {
                bootlist[i] = ' ';
            }

        }
        ret = fdt_setprop_string(fdt, offset, "qemu,boot-list", bootlist);
    }

    if (!spapr->has_graphics) {
        spapr_populate_chosen_stdout(fdt, spapr->vio_bus);
    }

    _FDT((fdt_pack(fdt)));

    if (fdt_totalsize(fdt) > FDT_MAX_SIZE) {
        hw_error("FDT too big ! 0x%x bytes (max is 0x%x)\n",
                 fdt_totalsize(fdt), FDT_MAX_SIZE);
        exit(1);
    }

    cpu_physical_memory_write(fdt_addr, fdt, fdt_totalsize(fdt));

    g_free(bootlist);
    g_free(fdt);
}

static uint64_t translate_kernel_address(void *opaque, uint64_t addr)
{
    return (addr & 0x0fffffff) + KERNEL_LOAD_ADDR;
}

static void emulate_spapr_hypercall(PowerPCCPU *cpu)
{
    CPUPPCState *env = &cpu->env;

    if (msr_pr) {
        hcall_dprintf("Hypercall made with MSR[PR]=1\n");
        env->gpr[3] = H_PRIVILEGE;
    } else {
        env->gpr[3] = spapr_hypercall(cpu, env->gpr[3], &env->gpr[4]);
    }
}

#define HPTE(_table, _i)   (void *)(((uint64_t *)(_table)) + ((_i) * 2))
#define HPTE_VALID(_hpte)  (tswap64(*((uint64_t *)(_hpte))) & HPTE64_V_VALID)
#define HPTE_DIRTY(_hpte)  (tswap64(*((uint64_t *)(_hpte))) & HPTE64_V_HPTE_DIRTY)
#define CLEAN_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) &= tswap64(~HPTE64_V_HPTE_DIRTY))
#define DIRTY_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) |= tswap64(HPTE64_V_HPTE_DIRTY))

static void spapr_reset_htab(sPAPREnvironment *spapr)
{
    long shift;
    int index;

    /* allocate hash page table.  For now we always make this 16mb,
     * later we should probably make it scale to the size of guest
     * RAM */

    shift = kvmppc_reset_htab(spapr->htab_shift);

    if (shift > 0) {
        /* Kernel handles htab, we don't need to allocate one */
        spapr->htab_shift = shift;
        kvmppc_kern_htab = true;

        /* Tell readers to update their file descriptor */
        if (spapr->htab_fd >= 0) {
            spapr->htab_fd_stale = true;
        }
    } else {
        if (!spapr->htab) {
            /* Allocate an htab if we don't yet have one */
            spapr->htab = qemu_memalign(HTAB_SIZE(spapr), HTAB_SIZE(spapr));
        }

        /* And clear it */
        memset(spapr->htab, 0, HTAB_SIZE(spapr));

        for (index = 0; index < HTAB_SIZE(spapr) / HASH_PTE_SIZE_64; index++) {
            DIRTY_HPTE(HPTE(spapr->htab, index));
        }
    }

    /* Update the RMA size if necessary */
    if (spapr->vrma_adjust) {
        spapr->rma_size = kvmppc_rma_size(spapr_node0_size(),
                                          spapr->htab_shift);
    }
}

static int find_unknown_sysbus_device(SysBusDevice *sbdev, void *opaque)
{
    bool matched = false;

    if (object_dynamic_cast(OBJECT(sbdev), TYPE_SPAPR_PCI_HOST_BRIDGE)) {
        matched = true;
    }

    if (!matched) {
        error_report("Device %s is not supported by this machine yet.",
                     qdev_fw_name(DEVICE(sbdev)));
        exit(1);
    }

    return 0;
}

/*
 * A guest reset will cause spapr->htab_fd to become stale if being used.
 * Reopen the file descriptor to make sure the whole HTAB is properly read.
 */
static int spapr_check_htab_fd(sPAPREnvironment *spapr)
{
    int rc = 0;

    if (spapr->htab_fd_stale) {
        close(spapr->htab_fd);
        spapr->htab_fd = kvmppc_get_htab_fd(false);
        if (spapr->htab_fd < 0) {
            error_report("Unable to open fd for reading hash table from KVM: "
                    "%s", strerror(errno));
            rc = -1;
        }
        spapr->htab_fd_stale = false;
    }

    return rc;
}

static void ppc_spapr_reset(void)
{
    PowerPCCPU *first_ppc_cpu;
    uint32_t rtas_limit;

    /* Check for unknown sysbus devices */
    foreach_dynamic_sysbus_device(find_unknown_sysbus_device, NULL);

    /* Reset the hash table & recalc the RMA */
    spapr_reset_htab(spapr);

    qemu_devices_reset();

    /*
     * We place the device tree and RTAS just below either the top of the RMA,
     * or just below 2GB, whichever is lowere, so that it can be
     * processed with 32-bit real mode code if necessary
     */
    rtas_limit = MIN(spapr->rma_size, RTAS_MAX_ADDR);
    spapr->rtas_addr = rtas_limit - RTAS_MAX_SIZE;
    spapr->fdt_addr = spapr->rtas_addr - FDT_MAX_SIZE;

    /* Load the fdt */
    spapr_finalize_fdt(spapr, spapr->fdt_addr, spapr->rtas_addr,
                       spapr->rtas_size);

    /* Copy RTAS over */
    cpu_physical_memory_write(spapr->rtas_addr, spapr->rtas_blob,
                              spapr->rtas_size);

    /* Set up the entry state */
    first_ppc_cpu = POWERPC_CPU(first_cpu);
    first_ppc_cpu->env.gpr[3] = spapr->fdt_addr;
    first_ppc_cpu->env.gpr[5] = 0;
    first_cpu->halted = 0;
    first_ppc_cpu->env.nip = spapr->entry_point;

}

static void spapr_cpu_reset(void *opaque)
{
    PowerPCCPU *cpu = opaque;
    CPUState *cs = CPU(cpu);
    CPUPPCState *env = &cpu->env;

    cpu_reset(cs);

    /* All CPUs start halted.  CPU0 is unhalted from the machine level
     * reset code and the rest are explicitly started up by the guest
     * using an RTAS call */
    cs->halted = 1;

    env->spr[SPR_HIOR] = 0;

    env->external_htab = (uint8_t *)spapr->htab;
    if (kvm_enabled() && !env->external_htab) {
        /*
         * HV KVM, set external_htab to 1 so our ppc_hash64_load_hpte*
         * functions do the right thing.
         */
        env->external_htab = (void *)1;
    }
    env->htab_base = -1;
    /*
     * htab_mask is the mask used to normalize hash value to PTEG index.
     * htab_shift is log2 of hash table size.
     * We have 8 hpte per group, and each hpte is 16 bytes.
     * ie have 128 bytes per hpte entry.
     */
    env->htab_mask = (1ULL << ((spapr)->htab_shift - 7)) - 1;
    env->spr[SPR_SDR1] = (target_ulong)(uintptr_t)spapr->htab |
        (spapr->htab_shift - 18);
}

static void spapr_create_nvram(sPAPREnvironment *spapr)
{
    DeviceState *dev = qdev_create(&spapr->vio_bus->bus, "spapr-nvram");
    DriveInfo *dinfo = drive_get(IF_PFLASH, 0, 0);

    if (dinfo) {
        qdev_prop_set_drive_nofail(dev, "drive", blk_by_legacy_dinfo(dinfo));
    }

    qdev_init_nofail(dev);

    spapr->nvram = (struct sPAPRNVRAM *)dev;
}

/* Returns whether we want to use VGA or not */
static int spapr_vga_init(PCIBus *pci_bus)
{
    switch (vga_interface_type) {
    case VGA_NONE:
        return false;
    case VGA_DEVICE:
        return true;
    case VGA_STD:
        return pci_vga_init(pci_bus) != NULL;
    default:
        fprintf(stderr, "This vga model is not supported,"
                "currently it only supports -vga std\n");
        exit(0);
    }
}

static const VMStateDescription vmstate_spapr = {
    .name = "spapr",
    .version_id = 2,
    .minimum_version_id = 1,
    .fields = (VMStateField[]) {
        VMSTATE_UNUSED(4), /* used to be @next_irq */

        /* RTC offset */
        VMSTATE_UINT64(rtc_offset, sPAPREnvironment),
        VMSTATE_PPC_TIMEBASE_V(tb, sPAPREnvironment, 2),
        VMSTATE_END_OF_LIST()
    },
};

static int htab_save_setup(QEMUFile *f, void *opaque)
{
    sPAPREnvironment *spapr = opaque;

    /* "Iteration" header */
    qemu_put_be32(f, spapr->htab_shift);

    if (spapr->htab) {
        spapr->htab_save_index = 0;
        spapr->htab_first_pass = true;
    } else {
        assert(kvm_enabled());

        spapr->htab_fd = kvmppc_get_htab_fd(false);
        spapr->htab_fd_stale = false;
        if (spapr->htab_fd < 0) {
            fprintf(stderr, "Unable to open fd for reading hash table from KVM: %s\n",
                    strerror(errno));
            return -1;
        }
    }


    return 0;
}

static void htab_save_first_pass(QEMUFile *f, sPAPREnvironment *spapr,
                                 int64_t max_ns)
{
    int htabslots = HTAB_SIZE(spapr) / HASH_PTE_SIZE_64;
    int index = spapr->htab_save_index;
    int64_t starttime = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);

    assert(spapr->htab_first_pass);

    do {
        int chunkstart;

        /* Consume invalid HPTEs */
        while ((index < htabslots)
               && !HPTE_VALID(HPTE(spapr->htab, index))) {
            index++;
            CLEAN_HPTE(HPTE(spapr->htab, index));
        }

        /* Consume valid HPTEs */
        chunkstart = index;
        while ((index < htabslots) && (index - chunkstart < USHRT_MAX)
               && HPTE_VALID(HPTE(spapr->htab, index))) {
            index++;
            CLEAN_HPTE(HPTE(spapr->htab, index));
        }

        if (index > chunkstart) {
            int n_valid = index - chunkstart;

            qemu_put_be32(f, chunkstart);
            qemu_put_be16(f, n_valid);
            qemu_put_be16(f, 0);
            qemu_put_buffer(f, HPTE(spapr->htab, chunkstart),
                            HASH_PTE_SIZE_64 * n_valid);

            if ((qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - starttime) > max_ns) {
                break;
            }
        }
    } while ((index < htabslots) && !qemu_file_rate_limit(f));

    if (index >= htabslots) {
        assert(index == htabslots);
        index = 0;
        spapr->htab_first_pass = false;
    }
    spapr->htab_save_index = index;
}

static int htab_save_later_pass(QEMUFile *f, sPAPREnvironment *spapr,
                                int64_t max_ns)
{
    bool final = max_ns < 0;
    int htabslots = HTAB_SIZE(spapr) / HASH_PTE_SIZE_64;
    int examined = 0, sent = 0;
    int index = spapr->htab_save_index;
    int64_t starttime = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);

    assert(!spapr->htab_first_pass);

    do {
        int chunkstart, invalidstart;

        /* Consume non-dirty HPTEs */
        while ((index < htabslots)
               && !HPTE_DIRTY(HPTE(spapr->htab, index))) {
            index++;
            examined++;
        }

        chunkstart = index;
        /* Consume valid dirty HPTEs */
        while ((index < htabslots) && (index - chunkstart < USHRT_MAX)
               && HPTE_DIRTY(HPTE(spapr->htab, index))
               && HPTE_VALID(HPTE(spapr->htab, index))) {
            CLEAN_HPTE(HPTE(spapr->htab, index));
            index++;
            examined++;
        }

        invalidstart = index;
        /* Consume invalid dirty HPTEs */
        while ((index < htabslots) && (index - invalidstart < USHRT_MAX)
               && HPTE_DIRTY(HPTE(spapr->htab, index))
               && !HPTE_VALID(HPTE(spapr->htab, index))) {
            CLEAN_HPTE(HPTE(spapr->htab, index));
            index++;
            examined++;
        }

        if (index > chunkstart) {
            int n_valid = invalidstart - chunkstart;
            int n_invalid = index - invalidstart;

            qemu_put_be32(f, chunkstart);
            qemu_put_be16(f, n_valid);
            qemu_put_be16(f, n_invalid);
            qemu_put_buffer(f, HPTE(spapr->htab, chunkstart),
                            HASH_PTE_SIZE_64 * n_valid);
            sent += index - chunkstart;

            if (!final && (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - starttime) > max_ns) {
                break;
            }
        }

        if (examined >= htabslots) {
            break;
        }

        if (index >= htabslots) {
            assert(index == htabslots);
            index = 0;
        }
    } while ((examined < htabslots) && (!qemu_file_rate_limit(f) || final));

    if (index >= htabslots) {
        assert(index == htabslots);
        index = 0;
    }

    spapr->htab_save_index = index;

    return (examined >= htabslots) && (sent == 0) ? 1 : 0;
}

#define MAX_ITERATION_NS    5000000 /* 5 ms */
#define MAX_KVM_BUF_SIZE    2048

static int htab_save_iterate(QEMUFile *f, void *opaque)
{
    sPAPREnvironment *spapr = opaque;
    int rc = 0;

    /* Iteration header */
    qemu_put_be32(f, 0);

    if (!spapr->htab) {
        assert(kvm_enabled());

        rc = spapr_check_htab_fd(spapr);
        if (rc < 0) {
            return rc;
        }

        rc = kvmppc_save_htab(f, spapr->htab_fd,
                              MAX_KVM_BUF_SIZE, MAX_ITERATION_NS);
        if (rc < 0) {
            return rc;
        }
    } else  if (spapr->htab_first_pass) {
        htab_save_first_pass(f, spapr, MAX_ITERATION_NS);
    } else {
        rc = htab_save_later_pass(f, spapr, MAX_ITERATION_NS);
    }

    /* End marker */
    qemu_put_be32(f, 0);
    qemu_put_be16(f, 0);
    qemu_put_be16(f, 0);

    return rc;
}

static int htab_save_complete(QEMUFile *f, void *opaque)
{
    sPAPREnvironment *spapr = opaque;

    /* Iteration header */
    qemu_put_be32(f, 0);

    if (!spapr->htab) {
        int rc;

        assert(kvm_enabled());

        rc = spapr_check_htab_fd(spapr);
        if (rc < 0) {
            return rc;
        }

        rc = kvmppc_save_htab(f, spapr->htab_fd, MAX_KVM_BUF_SIZE, -1);
        if (rc < 0) {
            return rc;
        }
        close(spapr->htab_fd);
        spapr->htab_fd = -1;
    } else {
        htab_save_later_pass(f, spapr, -1);
    }

    /* End marker */
    qemu_put_be32(f, 0);
    qemu_put_be16(f, 0);
    qemu_put_be16(f, 0);

    return 0;
}

static int htab_load(QEMUFile *f, void *opaque, int version_id)
{
    sPAPREnvironment *spapr = opaque;
    uint32_t section_hdr;
    int fd = -1;

    if (version_id < 1 || version_id > 1) {
        fprintf(stderr, "htab_load() bad version\n");
        return -EINVAL;
    }

    section_hdr = qemu_get_be32(f);

    if (section_hdr) {
        /* First section, just the hash shift */
        if (spapr->htab_shift != section_hdr) {
            return -EINVAL;
        }
        return 0;
    }

    if (!spapr->htab) {
        assert(kvm_enabled());

        fd = kvmppc_get_htab_fd(true);
        if (fd < 0) {
            fprintf(stderr, "Unable to open fd to restore KVM hash table: %s\n",
                    strerror(errno));
        }
    }

    while (true) {
        uint32_t index;
        uint16_t n_valid, n_invalid;

        index = qemu_get_be32(f);
        n_valid = qemu_get_be16(f);
        n_invalid = qemu_get_be16(f);

        if ((index == 0) && (n_valid == 0) && (n_invalid == 0)) {
            /* End of Stream */
            break;
        }

        if ((index + n_valid + n_invalid) >
            (HTAB_SIZE(spapr) / HASH_PTE_SIZE_64)) {
            /* Bad index in stream */
            fprintf(stderr, "htab_load() bad index %d (%hd+%hd entries) "
                    "in htab stream (htab_shift=%d)\n", index, n_valid, n_invalid,
                    spapr->htab_shift);
            return -EINVAL;
        }

        if (spapr->htab) {
            if (n_valid) {
                qemu_get_buffer(f, HPTE(spapr->htab, index),
                                HASH_PTE_SIZE_64 * n_valid);
            }
            if (n_invalid) {
                memset(HPTE(spapr->htab, index + n_valid), 0,
                       HASH_PTE_SIZE_64 * n_invalid);
            }
        } else {
            int rc;

            assert(fd >= 0);

            rc = kvmppc_load_htab_chunk(f, fd, index, n_valid, n_invalid);
            if (rc < 0) {
                return rc;
            }
        }
    }

    if (!spapr->htab) {
        assert(fd >= 0);
        close(fd);
    }

    return 0;
}

static SaveVMHandlers savevm_htab_handlers = {
    .save_live_setup = htab_save_setup,
    .save_live_iterate = htab_save_iterate,
    .save_live_complete = htab_save_complete,
    .load_state = htab_load,
};

/* pSeries LPAR / sPAPR hardware init */
static void ppc_spapr_init(MachineState *machine)
{
    ram_addr_t ram_size = machine->ram_size;
    const char *cpu_model = machine->cpu_model;
    const char *kernel_filename = machine->kernel_filename;
    const char *kernel_cmdline = machine->kernel_cmdline;
    const char *initrd_filename = machine->initrd_filename;
    const char *boot_device = machine->boot_order;
    PowerPCCPU *cpu;
    CPUPPCState *env;
    PCIHostState *phb;
    int i;
    MemoryRegion *sysmem = get_system_memory();
    MemoryRegion *ram = g_new(MemoryRegion, 1);
    MemoryRegion *rma_region;
    void *rma = NULL;
    hwaddr rma_alloc_size;
    hwaddr node0_size = spapr_node0_size();
    uint32_t initrd_base = 0;
    long kernel_size = 0, initrd_size = 0;
    long load_limit, fw_size;
    bool kernel_le = false;
    char *filename;

    msi_supported = true;

    spapr = g_malloc0(sizeof(*spapr));
    QLIST_INIT(&spapr->phbs);

    cpu_ppc_hypercall = emulate_spapr_hypercall;

    /* Allocate RMA if necessary */
    rma_alloc_size = kvmppc_alloc_rma(&rma);

    if (rma_alloc_size == -1) {
        hw_error("qemu: Unable to create RMA\n");
        exit(1);
    }

    if (rma_alloc_size && (rma_alloc_size < node0_size)) {
        spapr->rma_size = rma_alloc_size;
    } else {
        spapr->rma_size = node0_size;

        /* With KVM, we don't actually know whether KVM supports an
         * unbounded RMA (PR KVM) or is limited by the hash table size
         * (HV KVM using VRMA), so we always assume the latter
         *
         * In that case, we also limit the initial allocations for RTAS
         * etc... to 256M since we have no way to know what the VRMA size
         * is going to be as it depends on the size of the hash table
         * isn't determined yet.
         */
        if (kvm_enabled()) {
            spapr->vrma_adjust = 1;
            spapr->rma_size = MIN(spapr->rma_size, 0x10000000);
        }
    }

    if (spapr->rma_size > node0_size) {
        fprintf(stderr, "Error: Numa node 0 has to span the RMA (%#08"HWADDR_PRIx")\n",
                spapr->rma_size);
        exit(1);
    }

    /* Setup a load limit for the ramdisk leaving room for SLOF and FDT */
    load_limit = MIN(spapr->rma_size, RTAS_MAX_ADDR) - FW_OVERHEAD;

    /* We aim for a hash table of size 1/128 the size of RAM.  The
     * normal rule of thumb is 1/64 the size of RAM, but that's much
     * more than needed for the Linux guests we support. */
    spapr->htab_shift = 18; /* Minimum architected size */
    while (spapr->htab_shift <= 46) {
        if ((1ULL << (spapr->htab_shift + 7)) >= ram_size) {
            break;
        }
        spapr->htab_shift++;
    }

    /* Set up Interrupt Controller before we create the VCPUs */
    spapr->icp = xics_system_init(smp_cpus * kvmppc_smt_threads() / smp_threads,
                                  XICS_IRQS);

    /* init CPUs */
    if (cpu_model == NULL) {
        cpu_model = kvm_enabled() ? "host" : "POWER7";
    }
    for (i = 0; i < smp_cpus; i++) {
        cpu = cpu_ppc_init(cpu_model);
        if (cpu == NULL) {
            fprintf(stderr, "Unable to find PowerPC CPU definition\n");
            exit(1);
        }
        env = &cpu->env;

        /* Set time-base frequency to 512 MHz */
        cpu_ppc_tb_init(env, TIMEBASE_FREQ);

        /* PAPR always has exception vectors in RAM not ROM. To ensure this,
         * MSR[IP] should never be set.
         */
        env->msr_mask &= ~(1 << 6);

        /* Tell KVM that we're in PAPR mode */
        if (kvm_enabled()) {
            kvmppc_set_papr(cpu);
        }

        if (cpu->max_compat) {
            if (ppc_set_compat(cpu, cpu->max_compat) < 0) {
                exit(1);
            }
        }

        xics_cpu_setup(spapr->icp, cpu);

        qemu_register_reset(spapr_cpu_reset, cpu);
    }

    /* allocate RAM */
    spapr->ram_limit = ram_size;
    memory_region_allocate_system_memory(ram, NULL, "ppc_spapr.ram",
                                         spapr->ram_limit);
    memory_region_add_subregion(sysmem, 0, ram);

    if (rma_alloc_size && rma) {
        rma_region = g_new(MemoryRegion, 1);
        memory_region_init_ram_ptr(rma_region, NULL, "ppc_spapr.rma",
                                   rma_alloc_size, rma);
        vmstate_register_ram_global(rma_region);
        memory_region_add_subregion(sysmem, 0, rma_region);
    }

    filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, "spapr-rtas.bin");
    spapr->rtas_size = get_image_size(filename);
    spapr->rtas_blob = g_malloc(spapr->rtas_size);
    if (load_image_size(filename, spapr->rtas_blob, spapr->rtas_size) < 0) {
        hw_error("qemu: could not load LPAR rtas '%s'\n", filename);
        exit(1);
    }
    if (spapr->rtas_size > RTAS_MAX_SIZE) {
        hw_error("RTAS too big ! 0x%zx bytes (max is 0x%x)\n",
                 (size_t)spapr->rtas_size, RTAS_MAX_SIZE);
        exit(1);
    }
    g_free(filename);

    /* Set up EPOW events infrastructure */
    spapr_events_init(spapr);

    /* Set up VIO bus */
    spapr->vio_bus = spapr_vio_bus_init();

    for (i = 0; i < MAX_SERIAL_PORTS; i++) {
        if (serial_hds[i]) {
            spapr_vty_create(spapr->vio_bus, serial_hds[i]);
        }
    }

    /* We always have at least the nvram device on VIO */
    spapr_create_nvram(spapr);

    /* Set up PCI */
    spapr_pci_rtas_init();

    phb = spapr_create_phb(spapr, 0);

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

        if (!nd->model) {
            nd->model = g_strdup("ibmveth");
        }

        if (strcmp(nd->model, "ibmveth") == 0) {
            spapr_vlan_create(spapr->vio_bus, nd);
        } else {
            pci_nic_init_nofail(&nd_table[i], phb->bus, nd->model, NULL);
        }
    }

    for (i = 0; i <= drive_get_max_bus(IF_SCSI); i++) {
        spapr_vscsi_create(spapr->vio_bus);
    }

    /* Graphics */
    if (spapr_vga_init(phb->bus)) {
        spapr->has_graphics = true;
    }

    if ((spapr->has_graphics && defaults_enabled()) || usb_enabled(false)) {
        pci_create_simple(phb->bus, -1, "pci-ohci");
        if (spapr->has_graphics) {
            usbdevice_create("keyboard");
            usbdevice_create("mouse");
        }
    }

    if (spapr->rma_size < (MIN_RMA_SLOF << 20)) {
        fprintf(stderr, "qemu: pSeries SLOF firmware requires >= "
                "%ldM guest RMA (Real Mode Area memory)\n", MIN_RMA_SLOF);
        exit(1);
    }

    if (kernel_filename) {
        uint64_t lowaddr = 0;

        kernel_size = load_elf(kernel_filename, translate_kernel_address, NULL,
                               NULL, &lowaddr, NULL, 1, ELF_MACHINE, 0);
        if (kernel_size == ELF_LOAD_WRONG_ENDIAN) {
            kernel_size = load_elf(kernel_filename,
                                   translate_kernel_address, NULL,
                                   NULL, &lowaddr, NULL, 0, ELF_MACHINE, 0);
            kernel_le = kernel_size > 0;
        }
        if (kernel_size < 0) {
            fprintf(stderr, "qemu: error loading %s: %s\n",
                    kernel_filename, load_elf_strerror(kernel_size));
            exit(1);
        }

        /* load initrd */
        if (initrd_filename) {
            /* Try to locate the initrd in the gap between the kernel
             * and the firmware. Add a bit of space just in case
             */
            initrd_base = (KERNEL_LOAD_ADDR + kernel_size + 0x1ffff) & ~0xffff;
            initrd_size = load_image_targphys(initrd_filename, initrd_base,
                                              load_limit - initrd_base);
            if (initrd_size < 0) {
                fprintf(stderr, "qemu: could not load initial ram disk '%s'\n",
                        initrd_filename);
                exit(1);
            }
        } else {
            initrd_base = 0;
            initrd_size = 0;
        }
    }

    if (bios_name == NULL) {
        bios_name = FW_FILE_NAME;
    }
    filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name);
    fw_size = load_image_targphys(filename, 0, FW_MAX_SIZE);
    if (fw_size < 0) {
        hw_error("qemu: could not load LPAR rtas '%s'\n", filename);
        exit(1);
    }
    g_free(filename);

    spapr->entry_point = 0x100;

    vmstate_register(NULL, 0, &vmstate_spapr, spapr);
    register_savevm_live(NULL, "spapr/htab", -1, 1,
                         &savevm_htab_handlers, spapr);

    /* Prepare the device tree */
    spapr->fdt_skel = spapr_create_fdt_skel(initrd_base, initrd_size,
                                            kernel_size, kernel_le,
                                            boot_device, kernel_cmdline,
                                            spapr->epow_irq);
    assert(spapr->fdt_skel != NULL);
}

static int spapr_kvm_type(const char *vm_type)
{
    if (!vm_type) {
        return 0;
    }

    if (!strcmp(vm_type, "HV")) {
        return 1;
    }

    if (!strcmp(vm_type, "PR")) {
        return 2;
    }

    error_report("Unknown kvm-type specified '%s'", vm_type);
    exit(1);
}

/*
 * Implementation of an interface to adjust firmware patch
 * for the bootindex property handling.
 */
static char *spapr_get_fw_dev_path(FWPathProvider *p, BusState *bus,
                                   DeviceState *dev)
{
#define CAST(type, obj, name) \
    ((type *)object_dynamic_cast(OBJECT(obj), (name)))
    SCSIDevice *d = CAST(SCSIDevice,  dev, TYPE_SCSI_DEVICE);
    sPAPRPHBState *phb = CAST(sPAPRPHBState, dev, TYPE_SPAPR_PCI_HOST_BRIDGE);

    if (d) {
        void *spapr = CAST(void, bus->parent, "spapr-vscsi");
        VirtIOSCSI *virtio = CAST(VirtIOSCSI, bus->parent, TYPE_VIRTIO_SCSI);
        USBDevice *usb = CAST(USBDevice, bus->parent, TYPE_USB_DEVICE);

        if (spapr) {
            /*
             * Replace "channel@0/disk@0,0" with "disk@8000000000000000":
             * We use SRP luns of the form 8000 | (bus << 8) | (id << 5) | lun
             * in the top 16 bits of the 64-bit LUN
             */
            unsigned id = 0x8000 | (d->id << 8) | d->lun;
            return g_strdup_printf("%s@%"PRIX64, qdev_fw_name(dev),
                                   (uint64_t)id << 48);
        } else if (virtio) {
            /*
             * We use SRP luns of the form 01000000 | (target << 8) | lun
             * in the top 32 bits of the 64-bit LUN
             * Note: the quote above is from SLOF and it is wrong,
             * the actual binding is:
             * swap 0100 or 10 << or 20 << ( target lun-id -- srplun )
             */
            unsigned id = 0x1000000 | (d->id << 16) | d->lun;
            return g_strdup_printf("%s@%"PRIX64, qdev_fw_name(dev),
                                   (uint64_t)id << 32);
        } else if (usb) {
            /*
             * We use SRP luns of the form 01000000 | (usb-port << 16) | lun
             * in the top 32 bits of the 64-bit LUN
             */
            unsigned usb_port = atoi(usb->port->path);
            unsigned id = 0x1000000 | (usb_port << 16) | d->lun;
            return g_strdup_printf("%s@%"PRIX64, qdev_fw_name(dev),
                                   (uint64_t)id << 32);
        }
    }

    if (phb) {
        /* Replace "pci" with "pci@800000020000000" */
        return g_strdup_printf("pci@%"PRIX64, phb->buid);
    }

    return NULL;
}

static char *spapr_get_kvm_type(Object *obj, Error **errp)
{
    sPAPRMachineState *sm = SPAPR_MACHINE(obj);

    return g_strdup(sm->kvm_type);
}

static void spapr_set_kvm_type(Object *obj, const char *value, Error **errp)
{
    sPAPRMachineState *sm = SPAPR_MACHINE(obj);

    g_free(sm->kvm_type);
    sm->kvm_type = g_strdup(value);
}

static void spapr_machine_initfn(Object *obj)
{
    object_property_add_str(obj, "kvm-type",
                            spapr_get_kvm_type, spapr_set_kvm_type, NULL);
    object_property_set_description(obj, "kvm-type",
                                    "Specifies the KVM virtualization mode (HV, PR)",
                                    NULL);
}

static void ppc_cpu_do_nmi_on_cpu(void *arg)
{
    CPUState *cs = arg;

    cpu_synchronize_state(cs);
    ppc_cpu_do_system_reset(cs);
}

static void spapr_nmi(NMIState *n, int cpu_index, Error **errp)
{
    CPUState *cs;

    CPU_FOREACH(cs) {
        async_run_on_cpu(cs, ppc_cpu_do_nmi_on_cpu, cs);
    }
}

static void spapr_machine_class_init(ObjectClass *oc, void *data)
{
    MachineClass *mc = MACHINE_CLASS(oc);
    FWPathProviderClass *fwc = FW_PATH_PROVIDER_CLASS(oc);
    NMIClass *nc = NMI_CLASS(oc);

    mc->init = ppc_spapr_init;
    mc->reset = ppc_spapr_reset;
    mc->block_default_type = IF_SCSI;
    mc->max_cpus = MAX_CPUS;
    mc->no_parallel = 1;
    mc->default_boot_order = NULL;
    mc->kvm_type = spapr_kvm_type;
    mc->has_dynamic_sysbus = true;

    fwc->get_dev_path = spapr_get_fw_dev_path;
    nc->nmi_monitor_handler = spapr_nmi;
}

static const TypeInfo spapr_machine_info = {
    .name          = TYPE_SPAPR_MACHINE,
    .parent        = TYPE_MACHINE,
    .abstract      = true,
    .instance_size = sizeof(sPAPRMachineState),
    .instance_init = spapr_machine_initfn,
    .class_init    = spapr_machine_class_init,
    .interfaces = (InterfaceInfo[]) {
        { TYPE_FW_PATH_PROVIDER },
        { TYPE_NMI },
        { }
    },
};

static void spapr_machine_2_1_class_init(ObjectClass *oc, void *data)
{
    MachineClass *mc = MACHINE_CLASS(oc);
    static GlobalProperty compat_props[] = {
        HW_COMPAT_2_1,
        { /* end of list */ }
    };

    mc->name = "pseries-2.1";
    mc->desc = "pSeries Logical Partition (PAPR compliant) v2.1";
    mc->compat_props = compat_props;
}

static const TypeInfo spapr_machine_2_1_info = {
    .name          = TYPE_SPAPR_MACHINE "2.1",
    .parent        = TYPE_SPAPR_MACHINE,
    .class_init    = spapr_machine_2_1_class_init,
};

static void spapr_machine_2_2_class_init(ObjectClass *oc, void *data)
{
    MachineClass *mc = MACHINE_CLASS(oc);

    mc->name = "pseries-2.2";
    mc->desc = "pSeries Logical Partition (PAPR compliant) v2.2";
    mc->alias = "pseries";
    mc->is_default = 1;
}

static const TypeInfo spapr_machine_2_2_info = {
    .name          = TYPE_SPAPR_MACHINE "2.2",
    .parent        = TYPE_SPAPR_MACHINE,
    .class_init    = spapr_machine_2_2_class_init,
};

static void spapr_machine_register_types(void)
{
    type_register_static(&spapr_machine_info);
    type_register_static(&spapr_machine_2_1_info);
    type_register_static(&spapr_machine_2_2_info);
}

type_init(spapr_machine_register_types)