aboutsummaryrefslogtreecommitdiff
path: root/hw/ppc/spapr.c
blob: e09c67eb7547c12e76a819921cdd096fec1343e0 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
/*
 * 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 "qemu/osdep.h"
#include "qemu-common.h"
#include "qapi/error.h"
#include "qapi/visitor.h"
#include "sysemu/sysemu.h"
#include "sysemu/hostmem.h"
#include "sysemu/numa.h"
#include "sysemu/qtest.h"
#include "sysemu/reset.h"
#include "sysemu/runstate.h"
#include "qemu/log.h"
#include "hw/fw-path-provider.h"
#include "elf.h"
#include "net/net.h"
#include "sysemu/device_tree.h"
#include "sysemu/cpus.h"
#include "sysemu/hw_accel.h"
#include "kvm_ppc.h"
#include "migration/misc.h"
#include "migration/qemu-file-types.h"
#include "migration/global_state.h"
#include "migration/register.h"
#include "mmu-hash64.h"
#include "mmu-book3s-v3.h"
#include "cpu-models.h"
#include "qom/cpu.h"

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

#include "hw/ppc/fdt.h"
#include "hw/ppc/spapr.h"
#include "hw/ppc/spapr_vio.h"
#include "hw/qdev-properties.h"
#include "hw/pci-host/spapr.h"
#include "hw/pci/msi.h"

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

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

#include "qemu/cutils.h"
#include "hw/ppc/spapr_cpu_core.h"
#include "hw/mem/memory-device.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            0x100000
#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 PHANDLE_INTC            0x00001111

/* These two functions implement the VCPU id numbering: one to compute them
 * all and one to identify thread 0 of a VCORE. Any change to the first one
 * is likely to have an impact on the second one, so let's keep them close.
 */
static int spapr_vcpu_id(SpaprMachineState *spapr, int cpu_index)
{
    MachineState *ms = MACHINE(spapr);
    unsigned int smp_threads = ms->smp.threads;

    assert(spapr->vsmt);
    return
        (cpu_index / smp_threads) * spapr->vsmt + cpu_index % smp_threads;
}
static bool spapr_is_thread0_in_vcore(SpaprMachineState *spapr,
                                      PowerPCCPU *cpu)
{
    assert(spapr->vsmt);
    return spapr_get_vcpu_id(cpu) % spapr->vsmt == 0;
}

static bool pre_2_10_vmstate_dummy_icp_needed(void *opaque)
{
    /* Dummy entries correspond to unused ICPState objects in older QEMUs,
     * and newer QEMUs don't even have them. In both cases, we don't want
     * to send anything on the wire.
     */
    return false;
}

static const VMStateDescription pre_2_10_vmstate_dummy_icp = {
    .name = "icp/server",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = pre_2_10_vmstate_dummy_icp_needed,
    .fields = (VMStateField[]) {
        VMSTATE_UNUSED(4), /* uint32_t xirr */
        VMSTATE_UNUSED(1), /* uint8_t pending_priority */
        VMSTATE_UNUSED(1), /* uint8_t mfrr */
        VMSTATE_END_OF_LIST()
    },
};

static void pre_2_10_vmstate_register_dummy_icp(int i)
{
    vmstate_register(NULL, i, &pre_2_10_vmstate_dummy_icp,
                     (void *)(uintptr_t) i);
}

static void pre_2_10_vmstate_unregister_dummy_icp(int i)
{
    vmstate_unregister(NULL, &pre_2_10_vmstate_dummy_icp,
                       (void *)(uintptr_t) i);
}

int spapr_max_server_number(SpaprMachineState *spapr)
{
    MachineState *ms = MACHINE(spapr);

    assert(spapr->vsmt);
    return DIV_ROUND_UP(ms->smp.max_cpus * spapr->vsmt, ms->smp.threads);
}

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 = spapr_get_vcpu_id(cpu);

    if (cpu->compat_pvr) {
        ret = fdt_setprop_cell(fdt, offset, "cpu-version", cpu->compat_pvr);
        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_numa_dt(void *fdt, int offset, PowerPCCPU *cpu)
{
    int index = spapr_get_vcpu_id(cpu);
    uint32_t associativity[] = {cpu_to_be32(0x5),
                                cpu_to_be32(0x0),
                                cpu_to_be32(0x0),
                                cpu_to_be32(0x0),
                                cpu_to_be32(cpu->node_id),
                                cpu_to_be32(index)};

    /* Advertise NUMA via ibm,associativity */
    return fdt_setprop(fdt, offset, "ibm,associativity", associativity,
                          sizeof(associativity));
}

/* Populate the "ibm,pa-features" property */
static void spapr_populate_pa_features(SpaprMachineState *spapr,
                                       PowerPCCPU *cpu,
                                       void *fdt, int offset,
                                       bool legacy_guest)
{
    uint8_t pa_features_206[] = { 6, 0,
        0xf6, 0x1f, 0xc7, 0x00, 0x80, 0xc0 };
    uint8_t pa_features_207[] = { 24, 0,
        0xf6, 0x1f, 0xc7, 0xc0, 0x80, 0xf0,
        0x80, 0x00, 0x00, 0x00, 0x00, 0x00,
        0x00, 0x00, 0x00, 0x00, 0x80, 0x00,
        0x80, 0x00, 0x80, 0x00, 0x00, 0x00 };
    uint8_t pa_features_300[] = { 66, 0,
        /* 0: MMU|FPU|SLB|RUN|DABR|NX, 1: fri[nzpm]|DABRX|SPRG3|SLB0|PP110 */
        /* 2: VPM|DS205|PPR|DS202|DS206, 3: LSD|URG, SSO, 5: LE|CFAR|EB|LSQ */
        0xf6, 0x1f, 0xc7, 0xc0, 0x80, 0xf0, /* 0 - 5 */
        /* 6: DS207 */
        0x80, 0x00, 0x00, 0x00, 0x00, 0x00, /* 6 - 11 */
        /* 16: Vector */
        0x00, 0x00, 0x00, 0x00, 0x80, 0x00, /* 12 - 17 */
        /* 18: Vec. Scalar, 20: Vec. XOR, 22: HTM */
        0x80, 0x00, 0x80, 0x00, 0x00, 0x00, /* 18 - 23 */
        /* 24: Ext. Dec, 26: 64 bit ftrs, 28: PM ftrs */
        0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 24 - 29 */
        /* 30: MMR, 32: LE atomic, 34: EBB + ext EBB */
        0x80, 0x00, 0x80, 0x00, 0xC0, 0x00, /* 30 - 35 */
        /* 36: SPR SO, 38: Copy/Paste, 40: Radix MMU */
        0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 36 - 41 */
        /* 42: PM, 44: PC RA, 46: SC vec'd */
        0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 42 - 47 */
        /* 48: SIMD, 50: QP BFP, 52: String */
        0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 48 - 53 */
        /* 54: DecFP, 56: DecI, 58: SHA */
        0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 54 - 59 */
        /* 60: NM atomic, 62: RNG */
        0x80, 0x00, 0x80, 0x00, 0x00, 0x00, /* 60 - 65 */
    };
    uint8_t *pa_features = NULL;
    size_t pa_size;

    if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_2_06, 0, cpu->compat_pvr)) {
        pa_features = pa_features_206;
        pa_size = sizeof(pa_features_206);
    }
    if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_2_07, 0, cpu->compat_pvr)) {
        pa_features = pa_features_207;
        pa_size = sizeof(pa_features_207);
    }
    if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_00, 0, cpu->compat_pvr)) {
        pa_features = pa_features_300;
        pa_size = sizeof(pa_features_300);
    }
    if (!pa_features) {
        return;
    }

    if (ppc_hash64_has(cpu, PPC_HASH64_CI_LARGEPAGE)) {
        /*
         * Note: we keep CI large pages off by default because a 64K capable
         * guest provisioned with large pages might otherwise try to map a qemu
         * framebuffer (or other kind of memory mapped PCI BAR) using 64K pages
         * even if that qemu runs on a 4k host.
         * We dd this bit back here if we are confident this is not an issue
         */
        pa_features[3] |= 0x20;
    }
    if ((spapr_get_cap(spapr, SPAPR_CAP_HTM) != 0) && pa_size > 24) {
        pa_features[24] |= 0x80;    /* Transactional memory support */
    }
    if (legacy_guest && pa_size > 40) {
        /* Workaround for broken kernels that attempt (guest) radix
         * mode when they can't handle it, if they see the radix bit set
         * in pa-features. So hide it from them. */
        pa_features[40 + 2] &= ~0x80; /* Radix MMU */
    }

    _FDT((fdt_setprop(fdt, offset, "ibm,pa-features", pa_features, pa_size)));
}

static int spapr_fixup_cpu_dt(void *fdt, SpaprMachineState *spapr)
{
    MachineState *ms = MACHINE(spapr);
    int ret = 0, offset, cpus_offset;
    CPUState *cs;
    char cpu_model[32];
    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 = spapr_get_vcpu_id(cpu);
        int compat_smt = MIN(ms->smp.threads, ppc_compat_max_vthreads(cpu));

        if (!spapr_is_thread0_in_vcore(spapr, cpu)) {
            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, 0, "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;
            }
        }

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

        if (nb_numa_nodes > 1) {
            ret = spapr_fixup_cpu_numa_dt(fdt, offset, cpu);
            if (ret < 0) {
                return ret;
            }
        }

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

        spapr_populate_pa_features(spapr, cpu, fdt, offset,
                                   spapr->cas_legacy_guest_workaround);
    }
    return ret;
}

static hwaddr spapr_node0_size(MachineState *machine)
{
    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),
                           machine->ram_size);
            }
        }
    }
    return machine->ram_size;
}

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

static int 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))));
    return off;
}

static int spapr_populate_memory(SpaprMachineState *spapr, void *fdt)
{
    MachineState *machine = MACHINE(spapr);
    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 = machine->ram_size;
        nodes = &ramnode;
    }

    for (i = 0, mem_start = 0; i < nb_nodes; ++i) {
        if (!nodes[i].node_mem) {
            continue;
        }
        if (mem_start >= machine->ram_size) {
            node_size = 0;
        } else {
            node_size = nodes[i].node_mem;
            if (node_size > machine->ram_size - mem_start) {
                node_size = machine->ram_size - mem_start;
            }
        }
        if (!mem_start) {
            /* spapr_machine_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_populate_cpu_dt(CPUState *cs, void *fdt, int offset,
                                  SpaprMachineState *spapr)
{
    MachineState *ms = MACHINE(spapr);
    PowerPCCPU *cpu = POWERPC_CPU(cs);
    CPUPPCState *env = &cpu->env;
    PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cs);
    int index = spapr_get_vcpu_id(cpu);
    uint32_t segs[] = {cpu_to_be32(28), cpu_to_be32(40),
                       0xffffffff, 0xffffffff};
    uint32_t tbfreq = kvm_enabled() ? kvmppc_get_tbfreq()
        : SPAPR_TIMEBASE_FREQ;
    uint32_t cpufreq = kvm_enabled() ? kvmppc_get_clockfreq() : 1000000000;
    uint32_t page_sizes_prop[64];
    size_t page_sizes_prop_size;
    unsigned int smp_threads = ms->smp.threads;
    uint32_t vcpus_per_socket = smp_threads * ms->smp.cores;
    uint32_t pft_size_prop[] = {0, cpu_to_be32(spapr->htab_shift)};
    int compat_smt = MIN(smp_threads, ppc_compat_max_vthreads(cpu));
    SpaprDrc *drc;
    int drc_index;
    uint32_t radix_AP_encodings[PPC_PAGE_SIZES_MAX_SZ];
    int i;

    drc = spapr_drc_by_id(TYPE_SPAPR_DRC_CPU, index);
    if (drc) {
        drc_index = spapr_drc_index(drc);
        _FDT((fdt_setprop_cell(fdt, offset, "ibm,my-drc-index", drc_index)));
    }

    _FDT((fdt_setprop_cell(fdt, offset, "reg", index)));
    _FDT((fdt_setprop_string(fdt, offset, "device_type", "cpu")));

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

    if (pcc->l1_dcache_size) {
        _FDT((fdt_setprop_cell(fdt, offset, "d-cache-size",
                               pcc->l1_dcache_size)));
    } else {
        warn_report("Unknown L1 dcache size for cpu");
    }
    if (pcc->l1_icache_size) {
        _FDT((fdt_setprop_cell(fdt, offset, "i-cache-size",
                               pcc->l1_icache_size)));
    } else {
        warn_report("Unknown L1 icache size for cpu");
    }

    _FDT((fdt_setprop_cell(fdt, offset, "timebase-frequency", tbfreq)));
    _FDT((fdt_setprop_cell(fdt, offset, "clock-frequency", cpufreq)));
    _FDT((fdt_setprop_cell(fdt, offset, "slb-size", cpu->hash64_opts->slb_size)));
    _FDT((fdt_setprop_cell(fdt, offset, "ibm,slb-size", cpu->hash64_opts->slb_size)));
    _FDT((fdt_setprop_string(fdt, offset, "status", "okay")));
    _FDT((fdt_setprop(fdt, offset, "64-bit", NULL, 0)));

    if (env->spr_cb[SPR_PURR].oea_read) {
        _FDT((fdt_setprop_cell(fdt, offset, "ibm,purr", 1)));
    }
    if (env->spr_cb[SPR_SPURR].oea_read) {
        _FDT((fdt_setprop_cell(fdt, offset, "ibm,spurr", 1)));
    }

    if (ppc_hash64_has(cpu, PPC_HASH64_1TSEG)) {
        _FDT((fdt_setprop(fdt, offset, "ibm,processor-segment-sizes",
                          segs, sizeof(segs))));
    }

    /* Advertise VSX (vector extensions) if available
     *   1               == VMX / Altivec available
     *   2               == VSX available
     *
     * Only CPUs for which we create core types in spapr_cpu_core.c
     * are possible, and all of those have VMX */
    if (spapr_get_cap(spapr, SPAPR_CAP_VSX) != 0) {
        _FDT((fdt_setprop_cell(fdt, offset, "ibm,vmx", 2)));
    } else {
        _FDT((fdt_setprop_cell(fdt, offset, "ibm,vmx", 1)));
    }

    /* Advertise DFP (Decimal Floating Point) if available
     *   0 / no property == no DFP
     *   1               == DFP available */
    if (spapr_get_cap(spapr, SPAPR_CAP_DFP) != 0) {
        _FDT((fdt_setprop_cell(fdt, offset, "ibm,dfp", 1)));
    }

    page_sizes_prop_size = ppc_create_page_sizes_prop(cpu, page_sizes_prop,
                                                      sizeof(page_sizes_prop));
    if (page_sizes_prop_size) {
        _FDT((fdt_setprop(fdt, offset, "ibm,segment-page-sizes",
                          page_sizes_prop, page_sizes_prop_size)));
    }

    spapr_populate_pa_features(spapr, cpu, fdt, offset, false);

    _FDT((fdt_setprop_cell(fdt, offset, "ibm,chip-id",
                           cs->cpu_index / vcpus_per_socket)));

    _FDT((fdt_setprop(fdt, offset, "ibm,pft-size",
                      pft_size_prop, sizeof(pft_size_prop))));

    if (nb_numa_nodes > 1) {
        _FDT(spapr_fixup_cpu_numa_dt(fdt, offset, cpu));
    }

    _FDT(spapr_fixup_cpu_smt_dt(fdt, offset, cpu, compat_smt));

    if (pcc->radix_page_info) {
        for (i = 0; i < pcc->radix_page_info->count; i++) {
            radix_AP_encodings[i] =
                cpu_to_be32(pcc->radix_page_info->entries[i]);
        }
        _FDT((fdt_setprop(fdt, offset, "ibm,processor-radix-AP-encodings",
                          radix_AP_encodings,
                          pcc->radix_page_info->count *
                          sizeof(radix_AP_encodings[0]))));
    }

    /*
     * We set this property to let the guest know that it can use the large
     * decrementer and its width in bits.
     */
    if (spapr_get_cap(spapr, SPAPR_CAP_LARGE_DECREMENTER) != SPAPR_CAP_OFF)
        _FDT((fdt_setprop_u32(fdt, offset, "ibm,dec-bits",
                              pcc->lrg_decr_bits)));
}

static void spapr_populate_cpus_dt_node(void *fdt, SpaprMachineState *spapr)
{
    CPUState **rev;
    CPUState *cs;
    int n_cpus;
    int cpus_offset;
    char *nodename;
    int i;

    cpus_offset = fdt_add_subnode(fdt, 0, "cpus");
    _FDT(cpus_offset);
    _FDT((fdt_setprop_cell(fdt, cpus_offset, "#address-cells", 0x1)));
    _FDT((fdt_setprop_cell(fdt, cpus_offset, "#size-cells", 0x0)));

    /*
     * We walk the CPUs in reverse order to ensure that CPU DT nodes
     * created by fdt_add_subnode() end up in the right order in FDT
     * for the guest kernel the enumerate the CPUs correctly.
     *
     * The CPU list cannot be traversed in reverse order, so we need
     * to do extra work.
     */
    n_cpus = 0;
    rev = NULL;
    CPU_FOREACH(cs) {
        rev = g_renew(CPUState *, rev, n_cpus + 1);
        rev[n_cpus++] = cs;
    }

    for (i = n_cpus - 1; i >= 0; i--) {
        CPUState *cs = rev[i];
        PowerPCCPU *cpu = POWERPC_CPU(cs);
        int index = spapr_get_vcpu_id(cpu);
        DeviceClass *dc = DEVICE_GET_CLASS(cs);
        int offset;

        if (!spapr_is_thread0_in_vcore(spapr, cpu)) {
            continue;
        }

        nodename = g_strdup_printf("%s@%x", dc->fw_name, index);
        offset = fdt_add_subnode(fdt, cpus_offset, nodename);
        g_free(nodename);
        _FDT(offset);
        spapr_populate_cpu_dt(cs, fdt, offset, spapr);
    }

    g_free(rev);
}

static int spapr_rng_populate_dt(void *fdt)
{
    int node;
    int ret;

    node = qemu_fdt_add_subnode(fdt, "/ibm,platform-facilities");
    if (node <= 0) {
        return -1;
    }
    ret = fdt_setprop_string(fdt, node, "device_type",
                             "ibm,platform-facilities");
    ret |= fdt_setprop_cell(fdt, node, "#address-cells", 0x1);
    ret |= fdt_setprop_cell(fdt, node, "#size-cells", 0x0);

    node = fdt_add_subnode(fdt, node, "ibm,random-v1");
    if (node <= 0) {
        return -1;
    }
    ret |= fdt_setprop_string(fdt, node, "compatible", "ibm,random");

    return ret ? -1 : 0;
}

static uint32_t spapr_pc_dimm_node(MemoryDeviceInfoList *list, ram_addr_t addr)
{
    MemoryDeviceInfoList *info;

    for (info = list; info; info = info->next) {
        MemoryDeviceInfo *value = info->value;

        if (value && value->type == MEMORY_DEVICE_INFO_KIND_DIMM) {
            PCDIMMDeviceInfo *pcdimm_info = value->u.dimm.data;

            if (addr >= pcdimm_info->addr &&
                addr < (pcdimm_info->addr + pcdimm_info->size)) {
                return pcdimm_info->node;
            }
        }
    }

    return -1;
}

struct sPAPRDrconfCellV2 {
     uint32_t seq_lmbs;
     uint64_t base_addr;
     uint32_t drc_index;
     uint32_t aa_index;
     uint32_t flags;
} QEMU_PACKED;

typedef struct DrconfCellQueue {
    struct sPAPRDrconfCellV2 cell;
    QSIMPLEQ_ENTRY(DrconfCellQueue) entry;
} DrconfCellQueue;

static DrconfCellQueue *
spapr_get_drconf_cell(uint32_t seq_lmbs, uint64_t base_addr,
                      uint32_t drc_index, uint32_t aa_index,
                      uint32_t flags)
{
    DrconfCellQueue *elem;

    elem = g_malloc0(sizeof(*elem));
    elem->cell.seq_lmbs = cpu_to_be32(seq_lmbs);
    elem->cell.base_addr = cpu_to_be64(base_addr);
    elem->cell.drc_index = cpu_to_be32(drc_index);
    elem->cell.aa_index = cpu_to_be32(aa_index);
    elem->cell.flags = cpu_to_be32(flags);

    return elem;
}

/* ibm,dynamic-memory-v2 */
static int spapr_populate_drmem_v2(SpaprMachineState *spapr, void *fdt,
                                   int offset, MemoryDeviceInfoList *dimms)
{
    MachineState *machine = MACHINE(spapr);
    uint8_t *int_buf, *cur_index;
    int ret;
    uint64_t lmb_size = SPAPR_MEMORY_BLOCK_SIZE;
    uint64_t addr, cur_addr, size;
    uint32_t nr_boot_lmbs = (machine->device_memory->base / lmb_size);
    uint64_t mem_end = machine->device_memory->base +
                       memory_region_size(&machine->device_memory->mr);
    uint32_t node, buf_len, nr_entries = 0;
    SpaprDrc *drc;
    DrconfCellQueue *elem, *next;
    MemoryDeviceInfoList *info;
    QSIMPLEQ_HEAD(, DrconfCellQueue) drconf_queue
        = QSIMPLEQ_HEAD_INITIALIZER(drconf_queue);

    /* Entry to cover RAM and the gap area */
    elem = spapr_get_drconf_cell(nr_boot_lmbs, 0, 0, -1,
                                 SPAPR_LMB_FLAGS_RESERVED |
                                 SPAPR_LMB_FLAGS_DRC_INVALID);
    QSIMPLEQ_INSERT_TAIL(&drconf_queue, elem, entry);
    nr_entries++;

    cur_addr = machine->device_memory->base;
    for (info = dimms; info; info = info->next) {
        PCDIMMDeviceInfo *di = info->value->u.dimm.data;

        addr = di->addr;
        size = di->size;
        node = di->node;

        /* Entry for hot-pluggable area */
        if (cur_addr < addr) {
            drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, cur_addr / lmb_size);
            g_assert(drc);
            elem = spapr_get_drconf_cell((addr - cur_addr) / lmb_size,
                                         cur_addr, spapr_drc_index(drc), -1, 0);
            QSIMPLEQ_INSERT_TAIL(&drconf_queue, elem, entry);
            nr_entries++;
        }

        /* Entry for DIMM */
        drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, addr / lmb_size);
        g_assert(drc);
        elem = spapr_get_drconf_cell(size / lmb_size, addr,
                                     spapr_drc_index(drc), node,
                                     SPAPR_LMB_FLAGS_ASSIGNED);
        QSIMPLEQ_INSERT_TAIL(&drconf_queue, elem, entry);
        nr_entries++;
        cur_addr = addr + size;
    }

    /* Entry for remaining hotpluggable area */
    if (cur_addr < mem_end) {
        drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, cur_addr / lmb_size);
        g_assert(drc);
        elem = spapr_get_drconf_cell((mem_end - cur_addr) / lmb_size,
                                     cur_addr, spapr_drc_index(drc), -1, 0);
        QSIMPLEQ_INSERT_TAIL(&drconf_queue, elem, entry);
        nr_entries++;
    }

    buf_len = nr_entries * sizeof(struct sPAPRDrconfCellV2) + sizeof(uint32_t);
    int_buf = cur_index = g_malloc0(buf_len);
    *(uint32_t *)int_buf = cpu_to_be32(nr_entries);
    cur_index += sizeof(nr_entries);

    QSIMPLEQ_FOREACH_SAFE(elem, &drconf_queue, entry, next) {
        memcpy(cur_index, &elem->cell, sizeof(elem->cell));
        cur_index += sizeof(elem->cell);
        QSIMPLEQ_REMOVE(&drconf_queue, elem, DrconfCellQueue, entry);
        g_free(elem);
    }

    ret = fdt_setprop(fdt, offset, "ibm,dynamic-memory-v2", int_buf, buf_len);
    g_free(int_buf);
    if (ret < 0) {
        return -1;
    }
    return 0;
}

/* ibm,dynamic-memory */
static int spapr_populate_drmem_v1(SpaprMachineState *spapr, void *fdt,
                                   int offset, MemoryDeviceInfoList *dimms)
{
    MachineState *machine = MACHINE(spapr);
    int i, ret;
    uint64_t lmb_size = SPAPR_MEMORY_BLOCK_SIZE;
    uint32_t device_lmb_start = machine->device_memory->base / lmb_size;
    uint32_t nr_lmbs = (machine->device_memory->base +
                       memory_region_size(&machine->device_memory->mr)) /
                       lmb_size;
    uint32_t *int_buf, *cur_index, buf_len;

    /*
     * Allocate enough buffer size to fit in ibm,dynamic-memory
     */
    buf_len = (nr_lmbs * SPAPR_DR_LMB_LIST_ENTRY_SIZE + 1) * sizeof(uint32_t);
    cur_index = int_buf = g_malloc0(buf_len);
    int_buf[0] = cpu_to_be32(nr_lmbs);
    cur_index++;
    for (i = 0; i < nr_lmbs; i++) {
        uint64_t addr = i * lmb_size;
        uint32_t *dynamic_memory = cur_index;

        if (i >= device_lmb_start) {
            SpaprDrc *drc;

            drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, i);
            g_assert(drc);

            dynamic_memory[0] = cpu_to_be32(addr >> 32);
            dynamic_memory[1] = cpu_to_be32(addr & 0xffffffff);
            dynamic_memory[2] = cpu_to_be32(spapr_drc_index(drc));
            dynamic_memory[3] = cpu_to_be32(0); /* reserved */
            dynamic_memory[4] = cpu_to_be32(spapr_pc_dimm_node(dimms, addr));
            if (memory_region_present(get_system_memory(), addr)) {
                dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_ASSIGNED);
            } else {
                dynamic_memory[5] = cpu_to_be32(0);
            }
        } else {
            /*
             * LMB information for RMA, boot time RAM and gap b/n RAM and
             * device memory region -- all these are marked as reserved
             * and as having no valid DRC.
             */
            dynamic_memory[0] = cpu_to_be32(addr >> 32);
            dynamic_memory[1] = cpu_to_be32(addr & 0xffffffff);
            dynamic_memory[2] = cpu_to_be32(0);
            dynamic_memory[3] = cpu_to_be32(0); /* reserved */
            dynamic_memory[4] = cpu_to_be32(-1);
            dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_RESERVED |
                                            SPAPR_LMB_FLAGS_DRC_INVALID);
        }

        cur_index += SPAPR_DR_LMB_LIST_ENTRY_SIZE;
    }
    ret = fdt_setprop(fdt, offset, "ibm,dynamic-memory", int_buf, buf_len);
    g_free(int_buf);
    if (ret < 0) {
        return -1;
    }
    return 0;
}

/*
 * Adds ibm,dynamic-reconfiguration-memory node.
 * Refer to docs/specs/ppc-spapr-hotplug.txt for the documentation
 * of this device tree node.
 */
static int spapr_populate_drconf_memory(SpaprMachineState *spapr, void *fdt)
{
    MachineState *machine = MACHINE(spapr);
    int ret, i, offset;
    uint64_t lmb_size = SPAPR_MEMORY_BLOCK_SIZE;
    uint32_t prop_lmb_size[] = {0, cpu_to_be32(lmb_size)};
    uint32_t *int_buf, *cur_index, buf_len;
    int nr_nodes = nb_numa_nodes ? nb_numa_nodes : 1;
    MemoryDeviceInfoList *dimms = NULL;

    /*
     * Don't create the node if there is no device memory
     */
    if (machine->ram_size == machine->maxram_size) {
        return 0;
    }

    offset = fdt_add_subnode(fdt, 0, "ibm,dynamic-reconfiguration-memory");

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

    ret = fdt_setprop_cell(fdt, offset, "ibm,memory-flags-mask", 0xff);
    if (ret < 0) {
        return ret;
    }

    ret = fdt_setprop_cell(fdt, offset, "ibm,memory-preservation-time", 0x0);
    if (ret < 0) {
        return ret;
    }

    /* ibm,dynamic-memory or ibm,dynamic-memory-v2 */
    dimms = qmp_memory_device_list();
    if (spapr_ovec_test(spapr->ov5_cas, OV5_DRMEM_V2)) {
        ret = spapr_populate_drmem_v2(spapr, fdt, offset, dimms);
    } else {
        ret = spapr_populate_drmem_v1(spapr, fdt, offset, dimms);
    }
    qapi_free_MemoryDeviceInfoList(dimms);

    if (ret < 0) {
        return ret;
    }

    /* ibm,associativity-lookup-arrays */
    buf_len = (nr_nodes * 4 + 2) * sizeof(uint32_t);
    cur_index = int_buf = g_malloc0(buf_len);
    int_buf[0] = cpu_to_be32(nr_nodes);
    int_buf[1] = cpu_to_be32(4); /* Number of entries per associativity list */
    cur_index += 2;
    for (i = 0; i < nr_nodes; i++) {
        uint32_t associativity[] = {
            cpu_to_be32(0x0),
            cpu_to_be32(0x0),
            cpu_to_be32(0x0),
            cpu_to_be32(i)
        };
        memcpy(cur_index, associativity, sizeof(associativity));
        cur_index += 4;
    }
    ret = fdt_setprop(fdt, offset, "ibm,associativity-lookup-arrays", int_buf,
            (cur_index - int_buf) * sizeof(uint32_t));
    g_free(int_buf);

    return ret;
}

static int spapr_dt_cas_updates(SpaprMachineState *spapr, void *fdt,
                                SpaprOptionVector *ov5_updates)
{
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
    int ret = 0, offset;

    /* Generate ibm,dynamic-reconfiguration-memory node if required */
    if (spapr_ovec_test(ov5_updates, OV5_DRCONF_MEMORY)) {
        g_assert(smc->dr_lmb_enabled);
        ret = spapr_populate_drconf_memory(spapr, fdt);
        if (ret) {
            goto out;
        }
    }

    offset = fdt_path_offset(fdt, "/chosen");
    if (offset < 0) {
        offset = fdt_add_subnode(fdt, 0, "chosen");
        if (offset < 0) {
            return offset;
        }
    }
    ret = spapr_ovec_populate_dt(fdt, offset, spapr->ov5_cas,
                                 "ibm,architecture-vec-5");

out:
    return ret;
}

static bool spapr_hotplugged_dev_before_cas(void)
{
    Object *drc_container, *obj;
    ObjectProperty *prop;
    ObjectPropertyIterator iter;

    drc_container = container_get(object_get_root(), "/dr-connector");
    object_property_iter_init(&iter, drc_container);
    while ((prop = object_property_iter_next(&iter))) {
        if (!strstart(prop->type, "link<", NULL)) {
            continue;
        }
        obj = object_property_get_link(drc_container, prop->name, NULL);
        if (spapr_drc_needed(obj)) {
            return true;
        }
    }
    return false;
}

int spapr_h_cas_compose_response(SpaprMachineState *spapr,
                                 target_ulong addr, target_ulong size,
                                 SpaprOptionVector *ov5_updates)
{
    void *fdt, *fdt_skel;
    SpaprDeviceTreeUpdateHeader hdr = { .version_id = 1 };

    if (spapr_hotplugged_dev_before_cas()) {
        return 1;
    }

    if (size < sizeof(hdr) || size > FW_MAX_SIZE) {
        error_report("SLOF provided an unexpected CAS buffer size "
                     TARGET_FMT_lu " (min: %zu, max: %u)",
                     size, sizeof(hdr), FW_MAX_SIZE);
        exit(EXIT_FAILURE);
    }

    size -= sizeof(hdr);

    /* Create skeleton */
    fdt_skel = g_malloc0(size);
    _FDT((fdt_create(fdt_skel, size)));
    _FDT((fdt_finish_reservemap(fdt_skel)));
    _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);

    /* Fixup cpu nodes */
    _FDT((spapr_fixup_cpu_dt(fdt, spapr)));

    if (spapr_dt_cas_updates(spapr, fdt, ov5_updates)) {
        return -1;
    }

    /* 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_dt_rtas(SpaprMachineState *spapr, void *fdt)
{
    MachineState *ms = MACHINE(spapr);
    int rtas;
    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) };
    uint64_t max_device_addr = MACHINE(spapr)->device_memory->base +
        memory_region_size(&MACHINE(spapr)->device_memory->mr);
    uint32_t lrdr_capacity[] = {
        cpu_to_be32(max_device_addr >> 32),
        cpu_to_be32(max_device_addr & 0xffffffff),
        0, cpu_to_be32(SPAPR_MEMORY_BLOCK_SIZE),
        cpu_to_be32(ms->smp.max_cpus / ms->smp.threads),
    };
    uint32_t maxdomain = cpu_to_be32(spapr->gpu_numa_id > 1 ? 1 : 0);
    uint32_t maxdomains[] = {
        cpu_to_be32(4),
        maxdomain,
        maxdomain,
        maxdomain,
        cpu_to_be32(spapr->gpu_numa_id),
    };

    _FDT(rtas = fdt_add_subnode(fdt, 0, "rtas"));

    /* hypertas */
    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(hypertas, "hcall-sprg0");
    add_str(hypertas, "hcall-copy");
    add_str(hypertas, "hcall-debug");
    add_str(hypertas, "hcall-vphn");
    add_str(qemu_hypertas, "hcall-memop1");

    if (!kvm_enabled() || kvmppc_spapr_use_multitce()) {
        add_str(hypertas, "hcall-multi-tce");
    }

    if (spapr->resize_hpt != SPAPR_RESIZE_HPT_DISABLED) {
        add_str(hypertas, "hcall-hpt-resize");
    }

    _FDT(fdt_setprop(fdt, rtas, "ibm,hypertas-functions",
                     hypertas->str, hypertas->len));
    g_string_free(hypertas, TRUE);
    _FDT(fdt_setprop(fdt, rtas, "qemu,hypertas-functions",
                     qemu_hypertas->str, qemu_hypertas->len));
    g_string_free(qemu_hypertas, TRUE);

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

    _FDT(fdt_setprop(fdt, rtas, "ibm,max-associativity-domains",
                     maxdomains, sizeof(maxdomains)));

    _FDT(fdt_setprop_cell(fdt, rtas, "rtas-error-log-max",
                          RTAS_ERROR_LOG_MAX));
    _FDT(fdt_setprop_cell(fdt, rtas, "rtas-event-scan-rate",
                          RTAS_EVENT_SCAN_RATE));

    g_assert(msi_nonbroken);
    _FDT(fdt_setprop(fdt, rtas, "ibm,change-msix-capable", NULL, 0));

    /*
     * 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_setprop(fdt, rtas, "ibm,extended-os-term", NULL, 0));

    _FDT(fdt_setprop(fdt, rtas, "ibm,lrdr-capacity",
                     lrdr_capacity, sizeof(lrdr_capacity)));

    spapr_dt_rtas_tokens(fdt, rtas);
}

/*
 * Prepare ibm,arch-vec-5-platform-support, which indicates the MMU
 * and the XIVE features that the guest may request and thus the valid
 * values for bytes 23..26 of option vector 5:
 */
static void spapr_dt_ov5_platform_support(SpaprMachineState *spapr, void *fdt,
                                          int chosen)
{
    PowerPCCPU *first_ppc_cpu = POWERPC_CPU(first_cpu);

    char val[2 * 4] = {
        23, spapr->irq->ov5, /* Xive mode. */
        24, 0x00, /* Hash/Radix, filled in below. */
        25, 0x00, /* Hash options: Segment Tables == no, GTSE == no. */
        26, 0x40, /* Radix options: GTSE == yes. */
    };

    if (!ppc_check_compat(first_ppc_cpu, CPU_POWERPC_LOGICAL_3_00, 0,
                          first_ppc_cpu->compat_pvr)) {
        /*
         * If we're in a pre POWER9 compat mode then the guest should
         * do hash and use the legacy interrupt mode
         */
        val[1] = 0x00; /* XICS */
        val[3] = 0x00; /* Hash */
    } else if (kvm_enabled()) {
        if (kvmppc_has_cap_mmu_radix() && kvmppc_has_cap_mmu_hash_v3()) {
            val[3] = 0x80; /* OV5_MMU_BOTH */
        } else if (kvmppc_has_cap_mmu_radix()) {
            val[3] = 0x40; /* OV5_MMU_RADIX_300 */
        } else {
            val[3] = 0x00; /* Hash */
        }
    } else {
        /* V3 MMU supports both hash and radix in tcg (with dynamic switching) */
        val[3] = 0xC0;
    }
    _FDT(fdt_setprop(fdt, chosen, "ibm,arch-vec-5-platform-support",
                     val, sizeof(val)));
}

static void spapr_dt_chosen(SpaprMachineState *spapr, void *fdt)
{
    MachineState *machine = MACHINE(spapr);
    int chosen;
    const char *boot_device = machine->boot_order;
    char *stdout_path = spapr_vio_stdout_path(spapr->vio_bus);
    size_t cb = 0;
    char *bootlist = get_boot_devices_list(&cb);

    _FDT(chosen = fdt_add_subnode(fdt, 0, "chosen"));

    _FDT(fdt_setprop_string(fdt, chosen, "bootargs", machine->kernel_cmdline));
    _FDT(fdt_setprop_cell(fdt, chosen, "linux,initrd-start",
                          spapr->initrd_base));
    _FDT(fdt_setprop_cell(fdt, chosen, "linux,initrd-end",
                          spapr->initrd_base + spapr->initrd_size));

    if (spapr->kernel_size) {
        uint64_t kprop[2] = { cpu_to_be64(KERNEL_LOAD_ADDR),
                              cpu_to_be64(spapr->kernel_size) };

        _FDT(fdt_setprop(fdt, chosen, "qemu,boot-kernel",
                         &kprop, sizeof(kprop)));
        if (spapr->kernel_le) {
            _FDT(fdt_setprop(fdt, chosen, "qemu,boot-kernel-le", NULL, 0));
        }
    }
    if (boot_menu) {
        _FDT((fdt_setprop_cell(fdt, chosen, "qemu,boot-menu", boot_menu)));
    }
    _FDT(fdt_setprop_cell(fdt, chosen, "qemu,graphic-width", graphic_width));
    _FDT(fdt_setprop_cell(fdt, chosen, "qemu,graphic-height", graphic_height));
    _FDT(fdt_setprop_cell(fdt, chosen, "qemu,graphic-depth", graphic_depth));

    if (cb && bootlist) {
        int i;

        for (i = 0; i < cb; i++) {
            if (bootlist[i] == '\n') {
                bootlist[i] = ' ';
            }
        }
        _FDT(fdt_setprop_string(fdt, chosen, "qemu,boot-list", bootlist));
    }

    if (boot_device && strlen(boot_device)) {
        _FDT(fdt_setprop_string(fdt, chosen, "qemu,boot-device", boot_device));
    }

    if (!spapr->has_graphics && stdout_path) {
        /*
         * "linux,stdout-path" and "stdout" properties are deprecated by linux
         * kernel. New platforms should only use the "stdout-path" property. Set
         * the new property and continue using older property to remain
         * compatible with the existing firmware.
         */
        _FDT(fdt_setprop_string(fdt, chosen, "linux,stdout-path", stdout_path));
        _FDT(fdt_setprop_string(fdt, chosen, "stdout-path", stdout_path));
    }

    spapr_dt_ov5_platform_support(spapr, fdt, chosen);

    g_free(stdout_path);
    g_free(bootlist);
}

static void spapr_dt_hypervisor(SpaprMachineState *spapr, void *fdt)
{
    /* The /hypervisor node isn't in PAPR - this is a hack to allow PR
     * KVM to work under pHyp with some guest co-operation */
    int hypervisor;
    uint8_t hypercall[16];

    _FDT(hypervisor = fdt_add_subnode(fdt, 0, "hypervisor"));
    /* indicate KVM hypercall interface */
    _FDT(fdt_setprop_string(fdt, hypervisor, "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.
         */
        if (!kvmppc_get_hypercall(first_cpu->env_ptr, hypercall,
                                  sizeof(hypercall))) {
            _FDT(fdt_setprop(fdt, hypervisor, "hcall-instructions",
                             hypercall, sizeof(hypercall)));
        }
    }
}

static void *spapr_build_fdt(SpaprMachineState *spapr)
{
    MachineState *machine = MACHINE(spapr);
    MachineClass *mc = MACHINE_GET_CLASS(machine);
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(machine);
    int ret;
    void *fdt;
    SpaprPhbState *phb;
    char *buf;

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

    /* Root node */
    _FDT(fdt_setprop_string(fdt, 0, "device_type", "chrp"));
    _FDT(fdt_setprop_string(fdt, 0, "model", "IBM pSeries (emulated by qemu)"));
    _FDT(fdt_setprop_string(fdt, 0, "compatible", "qemu,pseries"));

    /* Guest UUID & Name*/
    buf = qemu_uuid_unparse_strdup(&qemu_uuid);
    _FDT(fdt_setprop_string(fdt, 0, "vm,uuid", buf));
    if (qemu_uuid_set) {
        _FDT(fdt_setprop_string(fdt, 0, "system-id", buf));
    }
    g_free(buf);

    if (qemu_get_vm_name()) {
        _FDT(fdt_setprop_string(fdt, 0, "ibm,partition-name",
                                qemu_get_vm_name()));
    }

    /* Host Model & Serial Number */
    if (spapr->host_model) {
        _FDT(fdt_setprop_string(fdt, 0, "host-model", spapr->host_model));
    } else if (smc->broken_host_serial_model && kvmppc_get_host_model(&buf)) {
        _FDT(fdt_setprop_string(fdt, 0, "host-model", buf));
        g_free(buf);
    }

    if (spapr->host_serial) {
        _FDT(fdt_setprop_string(fdt, 0, "host-serial", spapr->host_serial));
    } else if (smc->broken_host_serial_model && kvmppc_get_host_serial(&buf)) {
        _FDT(fdt_setprop_string(fdt, 0, "host-serial", buf));
        g_free(buf);
    }

    _FDT(fdt_setprop_cell(fdt, 0, "#address-cells", 2));
    _FDT(fdt_setprop_cell(fdt, 0, "#size-cells", 2));

    /* /interrupt controller */
    spapr->irq->dt_populate(spapr, spapr_max_server_number(spapr), fdt,
                          PHANDLE_INTC);

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

    /* /vdevice */
    spapr_dt_vdevice(spapr->vio_bus, fdt);

    if (object_resolve_path_type("", TYPE_SPAPR_RNG, NULL)) {
        ret = spapr_rng_populate_dt(fdt);
        if (ret < 0) {
            error_report("could not set up rng device in the fdt");
            exit(1);
        }
    }

    QLIST_FOREACH(phb, &spapr->phbs, list) {
        ret = spapr_dt_phb(phb, PHANDLE_INTC, fdt, spapr->irq->nr_msis, NULL);
        if (ret < 0) {
            error_report("couldn't setup PCI devices in fdt");
            exit(1);
        }
    }

    /* cpus */
    spapr_populate_cpus_dt_node(fdt, spapr);

    if (smc->dr_lmb_enabled) {
        _FDT(spapr_dt_drc(fdt, 0, NULL, SPAPR_DR_CONNECTOR_TYPE_LMB));
    }

    if (mc->has_hotpluggable_cpus) {
        int offset = fdt_path_offset(fdt, "/cpus");
        ret = spapr_dt_drc(fdt, offset, NULL, SPAPR_DR_CONNECTOR_TYPE_CPU);
        if (ret < 0) {
            error_report("Couldn't set up CPU DR device tree properties");
            exit(1);
        }
    }

    /* /event-sources */
    spapr_dt_events(spapr, fdt);

    /* /rtas */
    spapr_dt_rtas(spapr, fdt);

    /* /chosen */
    spapr_dt_chosen(spapr, fdt);

    /* /hypervisor */
    if (kvm_enabled()) {
        spapr_dt_hypervisor(spapr, fdt);
    }

    /* Build memory reserve map */
    if (spapr->kernel_size) {
        _FDT((fdt_add_mem_rsv(fdt, KERNEL_LOAD_ADDR, spapr->kernel_size)));
    }
    if (spapr->initrd_size) {
        _FDT((fdt_add_mem_rsv(fdt, spapr->initrd_base, spapr->initrd_size)));
    }

    /* ibm,client-architecture-support updates */
    ret = spapr_dt_cas_updates(spapr, fdt, spapr->ov5_cas);
    if (ret < 0) {
        error_report("couldn't setup CAS properties fdt");
        exit(1);
    }

    if (smc->dr_phb_enabled) {
        ret = spapr_dt_drc(fdt, 0, NULL, SPAPR_DR_CONNECTOR_TYPE_PHB);
        if (ret < 0) {
            error_report("Couldn't set up PHB DR device tree properties");
            exit(1);
        }
    }

    return fdt;
}

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

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

    /* The TCG path should also be holding the BQL at this point */
    g_assert(qemu_mutex_iothread_locked());

    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]);
    }
}

struct LPCRSyncState {
    target_ulong value;
    target_ulong mask;
};

static void do_lpcr_sync(CPUState *cs, run_on_cpu_data arg)
{
    struct LPCRSyncState *s = arg.host_ptr;
    PowerPCCPU *cpu = POWERPC_CPU(cs);
    CPUPPCState *env = &cpu->env;
    target_ulong lpcr;

    cpu_synchronize_state(cs);
    lpcr = env->spr[SPR_LPCR];
    lpcr &= ~s->mask;
    lpcr |= s->value;
    ppc_store_lpcr(cpu, lpcr);
}

void spapr_set_all_lpcrs(target_ulong value, target_ulong mask)
{
    CPUState *cs;
    struct LPCRSyncState s = {
        .value = value,
        .mask = mask
    };
    CPU_FOREACH(cs) {
        run_on_cpu(cs, do_lpcr_sync, RUN_ON_CPU_HOST_PTR(&s));
    }
}

static void spapr_get_pate(PPCVirtualHypervisor *vhyp, ppc_v3_pate_t *entry)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);

    /* Copy PATE1:GR into PATE0:HR */
    entry->dw0 = spapr->patb_entry & PATE0_HR;
    entry->dw1 = spapr->patb_entry;
}

#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))

/*
 * Get the fd to access the kernel htab, re-opening it if necessary
 */
static int get_htab_fd(SpaprMachineState *spapr)
{
    Error *local_err = NULL;

    if (spapr->htab_fd >= 0) {
        return spapr->htab_fd;
    }

    spapr->htab_fd = kvmppc_get_htab_fd(false, 0, &local_err);
    if (spapr->htab_fd < 0) {
        error_report_err(local_err);
    }

    return spapr->htab_fd;
}

void close_htab_fd(SpaprMachineState *spapr)
{
    if (spapr->htab_fd >= 0) {
        close(spapr->htab_fd);
    }
    spapr->htab_fd = -1;
}

static hwaddr spapr_hpt_mask(PPCVirtualHypervisor *vhyp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);

    return HTAB_SIZE(spapr) / HASH_PTEG_SIZE_64 - 1;
}

static target_ulong spapr_encode_hpt_for_kvm_pr(PPCVirtualHypervisor *vhyp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);

    assert(kvm_enabled());

    if (!spapr->htab) {
        return 0;
    }

    return (target_ulong)(uintptr_t)spapr->htab | (spapr->htab_shift - 18);
}

static const ppc_hash_pte64_t *spapr_map_hptes(PPCVirtualHypervisor *vhyp,
                                                hwaddr ptex, int n)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);
    hwaddr pte_offset = ptex * HASH_PTE_SIZE_64;

    if (!spapr->htab) {
        /*
         * HTAB is controlled by KVM. Fetch into temporary buffer
         */
        ppc_hash_pte64_t *hptes = g_malloc(n * HASH_PTE_SIZE_64);
        kvmppc_read_hptes(hptes, ptex, n);
        return hptes;
    }

    /*
     * HTAB is controlled by QEMU. Just point to the internally
     * accessible PTEG.
     */
    return (const ppc_hash_pte64_t *)(spapr->htab + pte_offset);
}

static void spapr_unmap_hptes(PPCVirtualHypervisor *vhyp,
                              const ppc_hash_pte64_t *hptes,
                              hwaddr ptex, int n)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);

    if (!spapr->htab) {
        g_free((void *)hptes);
    }

    /* Nothing to do for qemu managed HPT */
}

void spapr_store_hpte(PowerPCCPU *cpu, hwaddr ptex,
                      uint64_t pte0, uint64_t pte1)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(cpu->vhyp);
    hwaddr offset = ptex * HASH_PTE_SIZE_64;

    if (!spapr->htab) {
        kvmppc_write_hpte(ptex, pte0, pte1);
    } else {
        if (pte0 & HPTE64_V_VALID) {
            stq_p(spapr->htab + offset + HASH_PTE_SIZE_64 / 2, pte1);
            /*
             * When setting valid, we write PTE1 first. This ensures
             * proper synchronization with the reading code in
             * ppc_hash64_pteg_search()
             */
            smp_wmb();
            stq_p(spapr->htab + offset, pte0);
        } else {
            stq_p(spapr->htab + offset, pte0);
            /*
             * When clearing it we set PTE0 first. This ensures proper
             * synchronization with the reading code in
             * ppc_hash64_pteg_search()
             */
            smp_wmb();
            stq_p(spapr->htab + offset + HASH_PTE_SIZE_64 / 2, pte1);
        }
    }
}

static void spapr_hpte_set_c(PPCVirtualHypervisor *vhyp, hwaddr ptex,
                             uint64_t pte1)
{
    hwaddr offset = ptex * HASH_PTE_SIZE_64 + 15;
    SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);

    if (!spapr->htab) {
        /* There should always be a hash table when this is called */
        error_report("spapr_hpte_set_c called with no hash table !");
        return;
    }

    /* The HW performs a non-atomic byte update */
    stb_p(spapr->htab + offset, (pte1 & 0xff) | 0x80);
}

static void spapr_hpte_set_r(PPCVirtualHypervisor *vhyp, hwaddr ptex,
                             uint64_t pte1)
{
    hwaddr offset = ptex * HASH_PTE_SIZE_64 + 14;
    SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);

    if (!spapr->htab) {
        /* There should always be a hash table when this is called */
        error_report("spapr_hpte_set_r called with no hash table !");
        return;
    }

    /* The HW performs a non-atomic byte update */
    stb_p(spapr->htab + offset, ((pte1 >> 8) & 0xff) | 0x01);
}

int spapr_hpt_shift_for_ramsize(uint64_t ramsize)
{
    int shift;

    /* We aim for a hash table of size 1/128 the size of RAM (rounded
     * up).  The PAPR recommendation is actually 1/64 of RAM size, but
     * that's much more than is needed for Linux guests */
    shift = ctz64(pow2ceil(ramsize)) - 7;
    shift = MAX(shift, 18); /* Minimum architected size */
    shift = MIN(shift, 46); /* Maximum architected size */
    return shift;
}

void spapr_free_hpt(SpaprMachineState *spapr)
{
    g_free(spapr->htab);
    spapr->htab = NULL;
    spapr->htab_shift = 0;
    close_htab_fd(spapr);
}

void spapr_reallocate_hpt(SpaprMachineState *spapr, int shift,
                          Error **errp)
{
    long rc;

    /* Clean up any HPT info from a previous boot */
    spapr_free_hpt(spapr);

    rc = kvmppc_reset_htab(shift);
    if (rc < 0) {
        /* kernel-side HPT needed, but couldn't allocate one */
        error_setg_errno(errp, errno,
                         "Failed to allocate KVM HPT of order %d (try smaller maxmem?)",
                         shift);
        /* This is almost certainly fatal, but if the caller really
         * wants to carry on with shift == 0, it's welcome to try */
    } else if (rc > 0) {
        /* kernel-side HPT allocated */
        if (rc != shift) {
            error_setg(errp,
                       "Requested order %d HPT, but kernel allocated order %ld (try smaller maxmem?)",
                       shift, rc);
        }

        spapr->htab_shift = shift;
        spapr->htab = NULL;
    } else {
        /* kernel-side HPT not needed, allocate in userspace instead */
        size_t size = 1ULL << shift;
        int i;

        spapr->htab = qemu_memalign(size, size);
        if (!spapr->htab) {
            error_setg_errno(errp, errno,
                             "Could not allocate HPT of order %d", shift);
            return;
        }

        memset(spapr->htab, 0, size);
        spapr->htab_shift = shift;

        for (i = 0; i < size / HASH_PTE_SIZE_64; i++) {
            DIRTY_HPTE(HPTE(spapr->htab, i));
        }
    }
    /* We're setting up a hash table, so that means we're not radix */
    spapr->patb_entry = 0;
    spapr_set_all_lpcrs(0, LPCR_HR | LPCR_UPRT);
}

void spapr_setup_hpt_and_vrma(SpaprMachineState *spapr)
{
    int hpt_shift;

    if ((spapr->resize_hpt == SPAPR_RESIZE_HPT_DISABLED)
        || (spapr->cas_reboot
            && !spapr_ovec_test(spapr->ov5_cas, OV5_HPT_RESIZE))) {
        hpt_shift = spapr_hpt_shift_for_ramsize(MACHINE(spapr)->maxram_size);
    } else {
        uint64_t current_ram_size;

        current_ram_size = MACHINE(spapr)->ram_size + get_plugged_memory_size();
        hpt_shift = spapr_hpt_shift_for_ramsize(current_ram_size);
    }
    spapr_reallocate_hpt(spapr, hpt_shift, &error_fatal);

    if (spapr->vrma_adjust) {
        spapr->rma_size = kvmppc_rma_size(spapr_node0_size(MACHINE(spapr)),
                                          spapr->htab_shift);
    }
}

static int spapr_reset_drcs(Object *child, void *opaque)
{
    SpaprDrc *drc =
        (SpaprDrc *) object_dynamic_cast(child,
                                                 TYPE_SPAPR_DR_CONNECTOR);

    if (drc) {
        spapr_drc_reset(drc);
    }

    return 0;
}

static void spapr_machine_reset(MachineState *machine)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(machine);
    PowerPCCPU *first_ppc_cpu;
    uint32_t rtas_limit;
    hwaddr rtas_addr, fdt_addr;
    void *fdt;
    int rc;

    spapr_caps_apply(spapr);

    first_ppc_cpu = POWERPC_CPU(first_cpu);
    if (kvm_enabled() && kvmppc_has_cap_mmu_radix() &&
        ppc_type_check_compat(machine->cpu_type, CPU_POWERPC_LOGICAL_3_00, 0,
                              spapr->max_compat_pvr)) {
        /*
         * If using KVM with radix mode available, VCPUs can be started
         * without a HPT because KVM will start them in radix mode.
         * Set the GR bit in PATE so that we know there is no HPT.
         */
        spapr->patb_entry = PATE1_GR;
        spapr_set_all_lpcrs(LPCR_HR | LPCR_UPRT, LPCR_HR | LPCR_UPRT);
    } else {
        spapr_setup_hpt_and_vrma(spapr);
    }

    /*
     * NVLink2-connected GPU RAM needs to be placed on a separate NUMA node.
     * We assign a new numa ID per GPU in spapr_pci_collect_nvgpu() which is
     * called from vPHB reset handler so we initialize the counter here.
     * If no NUMA is configured from the QEMU side, we start from 1 as GPU RAM
     * must be equally distant from any other node.
     * The final value of spapr->gpu_numa_id is going to be written to
     * max-associativity-domains in spapr_build_fdt().
     */
    spapr->gpu_numa_id = MAX(1, nb_numa_nodes);
    qemu_devices_reset();

    /*
     * If this reset wasn't generated by CAS, we should reset our
     * negotiated options and start from scratch
     */
    if (!spapr->cas_reboot) {
        spapr_ovec_cleanup(spapr->ov5_cas);
        spapr->ov5_cas = spapr_ovec_new();

        ppc_set_compat(first_ppc_cpu, spapr->max_compat_pvr, &error_fatal);
    }

    if (!SPAPR_MACHINE_GET_CLASS(spapr)->legacy_irq_allocation) {
        spapr_irq_msi_reset(spapr);
    }

    /*
     * This is fixing some of the default configuration of the XIVE
     * devices. To be called after the reset of the machine devices.
     */
    spapr_irq_reset(spapr, &error_fatal);

    /*
     * There is no CAS under qtest. Simulate one to please the code that
     * depends on spapr->ov5_cas. This is especially needed to test device
     * unplug, so we do that before resetting the DRCs.
     */
    if (qtest_enabled()) {
        spapr_ovec_cleanup(spapr->ov5_cas);
        spapr->ov5_cas = spapr_ovec_clone(spapr->ov5);
    }

    /* DRC reset may cause a device to be unplugged. This will cause troubles
     * if this device is used by another device (eg, a running vhost backend
     * will crash QEMU if the DIMM holding the vring goes away). To avoid such
     * situations, we reset DRCs after all devices have been reset.
     */
    object_child_foreach_recursive(object_get_root(), spapr_reset_drcs, NULL);

    spapr_clear_pending_events(spapr);

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

    fdt = spapr_build_fdt(spapr);

    spapr_load_rtas(spapr, fdt, rtas_addr);

    rc = fdt_pack(fdt);

    /* Should only fail if we've built a corrupted tree */
    assert(rc == 0);

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

    /* Load the fdt */
    qemu_fdt_dumpdtb(fdt, fdt_totalsize(fdt));
    cpu_physical_memory_write(fdt_addr, fdt, fdt_totalsize(fdt));
    g_free(spapr->fdt_blob);
    spapr->fdt_size = fdt_totalsize(fdt);
    spapr->fdt_initial_size = spapr->fdt_size;
    spapr->fdt_blob = fdt;

    /* Set up the entry state */
    spapr_cpu_set_entry_state(first_ppc_cpu, SPAPR_ENTRY_POINT, fdt_addr);
    first_ppc_cpu->env.gpr[5] = 0;

    spapr->cas_reboot = false;
}

static void spapr_create_nvram(SpaprMachineState *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(dev, "drive", blk_by_legacy_dinfo(dinfo),
                            &error_fatal);
    }

    qdev_init_nofail(dev);

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

static void spapr_rtc_create(SpaprMachineState *spapr)
{
    object_initialize_child(OBJECT(spapr), "rtc",
                            &spapr->rtc, sizeof(spapr->rtc), TYPE_SPAPR_RTC,
                            &error_fatal, NULL);
    object_property_set_bool(OBJECT(&spapr->rtc), true, "realized",
                              &error_fatal);
    object_property_add_alias(OBJECT(spapr), "rtc-time", OBJECT(&spapr->rtc),
                              "date", &error_fatal);
}

/* Returns whether we want to use VGA or not */
static bool spapr_vga_init(PCIBus *pci_bus, Error **errp)
{
    switch (vga_interface_type) {
    case VGA_NONE:
        return false;
    case VGA_DEVICE:
        return true;
    case VGA_STD:
    case VGA_VIRTIO:
    case VGA_CIRRUS:
        return pci_vga_init(pci_bus) != NULL;
    default:
        error_setg(errp,
                   "Unsupported VGA mode, only -vga std or -vga virtio is supported");
        return false;
    }
}

static int spapr_pre_load(void *opaque)
{
    int rc;

    rc = spapr_caps_pre_load(opaque);
    if (rc) {
        return rc;
    }

    return 0;
}

static int spapr_post_load(void *opaque, int version_id)
{
    SpaprMachineState *spapr = (SpaprMachineState *)opaque;
    int err = 0;

    err = spapr_caps_post_migration(spapr);
    if (err) {
        return err;
    }

    /*
     * In earlier versions, there was no separate qdev for the PAPR
     * RTC, so the RTC offset was stored directly in sPAPREnvironment.
     * So when migrating from those versions, poke the incoming offset
     * value into the RTC device
     */
    if (version_id < 3) {
        err = spapr_rtc_import_offset(&spapr->rtc, spapr->rtc_offset);
        if (err) {
            return err;
        }
    }

    if (kvm_enabled() && spapr->patb_entry) {
        PowerPCCPU *cpu = POWERPC_CPU(first_cpu);
        bool radix = !!(spapr->patb_entry & PATE1_GR);
        bool gtse = !!(cpu->env.spr[SPR_LPCR] & LPCR_GTSE);

        /*
         * Update LPCR:HR and UPRT as they may not be set properly in
         * the stream
         */
        spapr_set_all_lpcrs(radix ? (LPCR_HR | LPCR_UPRT) : 0,
                            LPCR_HR | LPCR_UPRT);

        err = kvmppc_configure_v3_mmu(cpu, radix, gtse, spapr->patb_entry);
        if (err) {
            error_report("Process table config unsupported by the host");
            return -EINVAL;
        }
    }

    err = spapr_irq_post_load(spapr, version_id);
    if (err) {
        return err;
    }

    return err;
}

static int spapr_pre_save(void *opaque)
{
    int rc;

    rc = spapr_caps_pre_save(opaque);
    if (rc) {
        return rc;
    }

    return 0;
}

static bool version_before_3(void *opaque, int version_id)
{
    return version_id < 3;
}

static bool spapr_pending_events_needed(void *opaque)
{
    SpaprMachineState *spapr = (SpaprMachineState *)opaque;
    return !QTAILQ_EMPTY(&spapr->pending_events);
}

static const VMStateDescription vmstate_spapr_event_entry = {
    .name = "spapr_event_log_entry",
    .version_id = 1,
    .minimum_version_id = 1,
    .fields = (VMStateField[]) {
        VMSTATE_UINT32(summary, SpaprEventLogEntry),
        VMSTATE_UINT32(extended_length, SpaprEventLogEntry),
        VMSTATE_VBUFFER_ALLOC_UINT32(extended_log, SpaprEventLogEntry, 0,
                                     NULL, extended_length),
        VMSTATE_END_OF_LIST()
    },
};

static const VMStateDescription vmstate_spapr_pending_events = {
    .name = "spapr_pending_events",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = spapr_pending_events_needed,
    .fields = (VMStateField[]) {
        VMSTATE_QTAILQ_V(pending_events, SpaprMachineState, 1,
                         vmstate_spapr_event_entry, SpaprEventLogEntry, next),
        VMSTATE_END_OF_LIST()
    },
};

static bool spapr_ov5_cas_needed(void *opaque)
{
    SpaprMachineState *spapr = opaque;
    SpaprOptionVector *ov5_mask = spapr_ovec_new();
    SpaprOptionVector *ov5_legacy = spapr_ovec_new();
    SpaprOptionVector *ov5_removed = spapr_ovec_new();
    bool cas_needed;

    /* Prior to the introduction of SpaprOptionVector, we had two option
     * vectors we dealt with: OV5_FORM1_AFFINITY, and OV5_DRCONF_MEMORY.
     * Both of these options encode machine topology into the device-tree
     * in such a way that the now-booted OS should still be able to interact
     * appropriately with QEMU regardless of what options were actually
     * negotiatied on the source side.
     *
     * As such, we can avoid migrating the CAS-negotiated options if these
     * are the only options available on the current machine/platform.
     * Since these are the only options available for pseries-2.7 and
     * earlier, this allows us to maintain old->new/new->old migration
     * compatibility.
     *
     * For QEMU 2.8+, there are additional CAS-negotiatable options available
     * via default pseries-2.8 machines and explicit command-line parameters.
     * Some of these options, like OV5_HP_EVT, *do* require QEMU to be aware
     * of the actual CAS-negotiated values to continue working properly. For
     * example, availability of memory unplug depends on knowing whether
     * OV5_HP_EVT was negotiated via CAS.
     *
     * Thus, for any cases where the set of available CAS-negotiatable
     * options extends beyond OV5_FORM1_AFFINITY and OV5_DRCONF_MEMORY, we
     * include the CAS-negotiated options in the migration stream, unless
     * if they affect boot time behaviour only.
     */
    spapr_ovec_set(ov5_mask, OV5_FORM1_AFFINITY);
    spapr_ovec_set(ov5_mask, OV5_DRCONF_MEMORY);
    spapr_ovec_set(ov5_mask, OV5_DRMEM_V2);

    /* spapr_ovec_diff returns true if bits were removed. we avoid using
     * the mask itself since in the future it's possible "legacy" bits may be
     * removed via machine options, which could generate a false positive
     * that breaks migration.
     */
    spapr_ovec_intersect(ov5_legacy, spapr->ov5, ov5_mask);
    cas_needed = spapr_ovec_diff(ov5_removed, spapr->ov5, ov5_legacy);

    spapr_ovec_cleanup(ov5_mask);
    spapr_ovec_cleanup(ov5_legacy);
    spapr_ovec_cleanup(ov5_removed);

    return cas_needed;
}

static const VMStateDescription vmstate_spapr_ov5_cas = {
    .name = "spapr_option_vector_ov5_cas",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = spapr_ov5_cas_needed,
    .fields = (VMStateField[]) {
        VMSTATE_STRUCT_POINTER_V(ov5_cas, SpaprMachineState, 1,
                                 vmstate_spapr_ovec, SpaprOptionVector),
        VMSTATE_END_OF_LIST()
    },
};

static bool spapr_patb_entry_needed(void *opaque)
{
    SpaprMachineState *spapr = opaque;

    return !!spapr->patb_entry;
}

static const VMStateDescription vmstate_spapr_patb_entry = {
    .name = "spapr_patb_entry",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = spapr_patb_entry_needed,
    .fields = (VMStateField[]) {
        VMSTATE_UINT64(patb_entry, SpaprMachineState),
        VMSTATE_END_OF_LIST()
    },
};

static bool spapr_irq_map_needed(void *opaque)
{
    SpaprMachineState *spapr = opaque;

    return spapr->irq_map && !bitmap_empty(spapr->irq_map, spapr->irq_map_nr);
}

static const VMStateDescription vmstate_spapr_irq_map = {
    .name = "spapr_irq_map",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = spapr_irq_map_needed,
    .fields = (VMStateField[]) {
        VMSTATE_BITMAP(irq_map, SpaprMachineState, 0, irq_map_nr),
        VMSTATE_END_OF_LIST()
    },
};

static bool spapr_dtb_needed(void *opaque)
{
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(opaque);

    return smc->update_dt_enabled;
}

static int spapr_dtb_pre_load(void *opaque)
{
    SpaprMachineState *spapr = (SpaprMachineState *)opaque;

    g_free(spapr->fdt_blob);
    spapr->fdt_blob = NULL;
    spapr->fdt_size = 0;

    return 0;
}

static const VMStateDescription vmstate_spapr_dtb = {
    .name = "spapr_dtb",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = spapr_dtb_needed,
    .pre_load = spapr_dtb_pre_load,
    .fields = (VMStateField[]) {
        VMSTATE_UINT32(fdt_initial_size, SpaprMachineState),
        VMSTATE_UINT32(fdt_size, SpaprMachineState),
        VMSTATE_VBUFFER_ALLOC_UINT32(fdt_blob, SpaprMachineState, 0, NULL,
                                     fdt_size),
        VMSTATE_END_OF_LIST()
    },
};

static const VMStateDescription vmstate_spapr = {
    .name = "spapr",
    .version_id = 3,
    .minimum_version_id = 1,
    .pre_load = spapr_pre_load,
    .post_load = spapr_post_load,
    .pre_save = spapr_pre_save,
    .fields = (VMStateField[]) {
        /* used to be @next_irq */
        VMSTATE_UNUSED_BUFFER(version_before_3, 0, 4),

        /* RTC offset */
        VMSTATE_UINT64_TEST(rtc_offset, SpaprMachineState, version_before_3),

        VMSTATE_PPC_TIMEBASE_V(tb, SpaprMachineState, 2),
        VMSTATE_END_OF_LIST()
    },
    .subsections = (const VMStateDescription*[]) {
        &vmstate_spapr_ov5_cas,
        &vmstate_spapr_patb_entry,
        &vmstate_spapr_pending_events,
        &vmstate_spapr_cap_htm,
        &vmstate_spapr_cap_vsx,
        &vmstate_spapr_cap_dfp,
        &vmstate_spapr_cap_cfpc,
        &vmstate_spapr_cap_sbbc,
        &vmstate_spapr_cap_ibs,
        &vmstate_spapr_cap_hpt_maxpagesize,
        &vmstate_spapr_irq_map,
        &vmstate_spapr_cap_nested_kvm_hv,
        &vmstate_spapr_dtb,
        &vmstate_spapr_cap_large_decr,
        &vmstate_spapr_cap_ccf_assist,
        NULL
    }
};

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

    /* "Iteration" header */
    if (!spapr->htab_shift) {
        qemu_put_be32(f, -1);
    } else {
        qemu_put_be32(f, spapr->htab_shift);
    }

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


    return 0;
}

static void htab_save_chunk(QEMUFile *f, SpaprMachineState *spapr,
                            int chunkstart, int n_valid, int n_invalid)
{
    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);
}

static void htab_save_end_marker(QEMUFile *f)
{
    qemu_put_be32(f, 0);
    qemu_put_be16(f, 0);
    qemu_put_be16(f, 0);
}

static void htab_save_first_pass(QEMUFile *f, SpaprMachineState *spapr,
                                 int64_t max_ns)
{
    bool has_timeout = max_ns != -1;
    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))) {
            CLEAN_HPTE(HPTE(spapr->htab, index));
            index++;
        }

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

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

            htab_save_chunk(f, spapr, chunkstart, n_valid, 0);

            if (has_timeout &&
                (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, SpaprMachineState *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;

            htab_save_chunk(f, spapr, chunkstart, n_valid, n_invalid);
            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)
{
    SpaprMachineState *spapr = opaque;
    int fd;
    int rc = 0;

    /* Iteration header */
    if (!spapr->htab_shift) {
        qemu_put_be32(f, -1);
        return 1;
    } else {
        qemu_put_be32(f, 0);
    }

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

        fd = get_htab_fd(spapr);
        if (fd < 0) {
            return fd;
        }

        rc = kvmppc_save_htab(f, 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);
    }

    htab_save_end_marker(f);

    return rc;
}

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

    /* Iteration header */
    if (!spapr->htab_shift) {
        qemu_put_be32(f, -1);
        return 0;
    } else {
        qemu_put_be32(f, 0);
    }

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

        assert(kvm_enabled());

        fd = get_htab_fd(spapr);
        if (fd < 0) {
            return fd;
        }

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

    /* End marker */
    htab_save_end_marker(f);

    return 0;
}

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

    if (version_id < 1 || version_id > 1) {
        error_report("htab_load() bad version");
        return -EINVAL;
    }

    section_hdr = qemu_get_be32(f);

    if (section_hdr == -1) {
        spapr_free_hpt(spapr);
        return 0;
    }

    if (section_hdr) {
        /* First section gives the htab size */
        spapr_reallocate_hpt(spapr, section_hdr, &local_err);
        if (local_err) {
            error_report_err(local_err);
            return -EINVAL;
        }
        return 0;
    }

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

        fd = kvmppc_get_htab_fd(true, 0, &local_err);
        if (fd < 0) {
            error_report_err(local_err);
            return fd;
        }
    }

    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 */
            error_report(
                "htab_load() bad index %d (%hd+%hd entries) in htab stream (htab_shift=%d)",
                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 void htab_save_cleanup(void *opaque)
{
    SpaprMachineState *spapr = opaque;

    close_htab_fd(spapr);
}

static SaveVMHandlers savevm_htab_handlers = {
    .save_setup = htab_save_setup,
    .save_live_iterate = htab_save_iterate,
    .save_live_complete_precopy = htab_save_complete,
    .save_cleanup = htab_save_cleanup,
    .load_state = htab_load,
};

static void spapr_boot_set(void *opaque, const char *boot_device,
                           Error **errp)
{
    MachineState *machine = MACHINE(opaque);
    machine->boot_order = g_strdup(boot_device);
}

static void spapr_create_lmb_dr_connectors(SpaprMachineState *spapr)
{
    MachineState *machine = MACHINE(spapr);
    uint64_t lmb_size = SPAPR_MEMORY_BLOCK_SIZE;
    uint32_t nr_lmbs = (machine->maxram_size - machine->ram_size)/lmb_size;
    int i;

    for (i = 0; i < nr_lmbs; i++) {
        uint64_t addr;

        addr = i * lmb_size + machine->device_memory->base;
        spapr_dr_connector_new(OBJECT(spapr), TYPE_SPAPR_DRC_LMB,
                               addr / lmb_size);
    }
}

/*
 * If RAM size, maxmem size and individual node mem sizes aren't aligned
 * to SPAPR_MEMORY_BLOCK_SIZE(256MB), then refuse to start the guest
 * since we can't support such unaligned sizes with DRCONF_MEMORY.
 */
static void spapr_validate_node_memory(MachineState *machine, Error **errp)
{
    int i;

    if (machine->ram_size % SPAPR_MEMORY_BLOCK_SIZE) {
        error_setg(errp, "Memory size 0x" RAM_ADDR_FMT
                   " is not aligned to %" PRIu64 " MiB",
                   machine->ram_size,
                   SPAPR_MEMORY_BLOCK_SIZE / MiB);
        return;
    }

    if (machine->maxram_size % SPAPR_MEMORY_BLOCK_SIZE) {
        error_setg(errp, "Maximum memory size 0x" RAM_ADDR_FMT
                   " is not aligned to %" PRIu64 " MiB",
                   machine->ram_size,
                   SPAPR_MEMORY_BLOCK_SIZE / MiB);
        return;
    }

    for (i = 0; i < nb_numa_nodes; i++) {
        if (numa_info[i].node_mem % SPAPR_MEMORY_BLOCK_SIZE) {
            error_setg(errp,
                       "Node %d memory size 0x%" PRIx64
                       " is not aligned to %" PRIu64 " MiB",
                       i, numa_info[i].node_mem,
                       SPAPR_MEMORY_BLOCK_SIZE / MiB);
            return;
        }
    }
}

/* find cpu slot in machine->possible_cpus by core_id */
static CPUArchId *spapr_find_cpu_slot(MachineState *ms, uint32_t id, int *idx)
{
    int index = id / ms->smp.threads;

    if (index >= ms->possible_cpus->len) {
        return NULL;
    }
    if (idx) {
        *idx = index;
    }
    return &ms->possible_cpus->cpus[index];
}

static void spapr_set_vsmt_mode(SpaprMachineState *spapr, Error **errp)
{
    MachineState *ms = MACHINE(spapr);
    Error *local_err = NULL;
    bool vsmt_user = !!spapr->vsmt;
    int kvm_smt = kvmppc_smt_threads();
    int ret;
    unsigned int smp_threads = ms->smp.threads;

    if (!kvm_enabled() && (smp_threads > 1)) {
        error_setg(&local_err, "TCG cannot support more than 1 thread/core "
                     "on a pseries machine");
        goto out;
    }
    if (!is_power_of_2(smp_threads)) {
        error_setg(&local_err, "Cannot support %d threads/core on a pseries "
                     "machine because it must be a power of 2", smp_threads);
        goto out;
    }

    /* Detemine the VSMT mode to use: */
    if (vsmt_user) {
        if (spapr->vsmt < smp_threads) {
            error_setg(&local_err, "Cannot support VSMT mode %d"
                         " because it must be >= threads/core (%d)",
                         spapr->vsmt, smp_threads);
            goto out;
        }
        /* In this case, spapr->vsmt has been set by the command line */
    } else {
        /*
         * Default VSMT value is tricky, because we need it to be as
         * consistent as possible (for migration), but this requires
         * changing it for at least some existing cases.  We pick 8 as
         * the value that we'd get with KVM on POWER8, the
         * overwhelmingly common case in production systems.
         */
        spapr->vsmt = MAX(8, smp_threads);
    }

    /* KVM: If necessary, set the SMT mode: */
    if (kvm_enabled() && (spapr->vsmt != kvm_smt)) {
        ret = kvmppc_set_smt_threads(spapr->vsmt);
        if (ret) {
            /* Looks like KVM isn't able to change VSMT mode */
            error_setg(&local_err,
                       "Failed to set KVM's VSMT mode to %d (errno %d)",
                       spapr->vsmt, ret);
            /* We can live with that if the default one is big enough
             * for the number of threads, and a submultiple of the one
             * we want.  In this case we'll waste some vcpu ids, but
             * behaviour will be correct */
            if ((kvm_smt >= smp_threads) && ((spapr->vsmt % kvm_smt) == 0)) {
                warn_report_err(local_err);
                local_err = NULL;
                goto out;
            } else {
                if (!vsmt_user) {
                    error_append_hint(&local_err,
                                      "On PPC, a VM with %d threads/core"
                                      " on a host with %d threads/core"
                                      " requires the use of VSMT mode %d.\n",
                                      smp_threads, kvm_smt, spapr->vsmt);
                }
                kvmppc_hint_smt_possible(&local_err);
                goto out;
            }
        }
    }
    /* else TCG: nothing to do currently */
out:
    error_propagate(errp, local_err);
}

static void spapr_init_cpus(SpaprMachineState *spapr)
{
    MachineState *machine = MACHINE(spapr);
    MachineClass *mc = MACHINE_GET_CLASS(machine);
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(machine);
    const char *type = spapr_get_cpu_core_type(machine->cpu_type);
    const CPUArchIdList *possible_cpus;
    unsigned int smp_cpus = machine->smp.cpus;
    unsigned int smp_threads = machine->smp.threads;
    unsigned int max_cpus = machine->smp.max_cpus;
    int boot_cores_nr = smp_cpus / smp_threads;
    int i;

    possible_cpus = mc->possible_cpu_arch_ids(machine);
    if (mc->has_hotpluggable_cpus) {
        if (smp_cpus % smp_threads) {
            error_report("smp_cpus (%u) must be multiple of threads (%u)",
                         smp_cpus, smp_threads);
            exit(1);
        }
        if (max_cpus % smp_threads) {
            error_report("max_cpus (%u) must be multiple of threads (%u)",
                         max_cpus, smp_threads);
            exit(1);
        }
    } else {
        if (max_cpus != smp_cpus) {
            error_report("This machine version does not support CPU hotplug");
            exit(1);
        }
        boot_cores_nr = possible_cpus->len;
    }

    if (smc->pre_2_10_has_unused_icps) {
        int i;

        for (i = 0; i < spapr_max_server_number(spapr); i++) {
            /* Dummy entries get deregistered when real ICPState objects
             * are registered during CPU core hotplug.
             */
            pre_2_10_vmstate_register_dummy_icp(i);
        }
    }

    for (i = 0; i < possible_cpus->len; i++) {
        int core_id = i * smp_threads;

        if (mc->has_hotpluggable_cpus) {
            spapr_dr_connector_new(OBJECT(spapr), TYPE_SPAPR_DRC_CPU,
                                   spapr_vcpu_id(spapr, core_id));
        }

        if (i < boot_cores_nr) {
            Object *core  = object_new(type);
            int nr_threads = smp_threads;

            /* Handle the partially filled core for older machine types */
            if ((i + 1) * smp_threads >= smp_cpus) {
                nr_threads = smp_cpus - i * smp_threads;
            }

            object_property_set_int(core, nr_threads, "nr-threads",
                                    &error_fatal);
            object_property_set_int(core, core_id, CPU_CORE_PROP_CORE_ID,
                                    &error_fatal);
            object_property_set_bool(core, true, "realized", &error_fatal);

            object_unref(core);
        }
    }
}

static PCIHostState *spapr_create_default_phb(void)
{
    DeviceState *dev;

    dev = qdev_create(NULL, TYPE_SPAPR_PCI_HOST_BRIDGE);
    qdev_prop_set_uint32(dev, "index", 0);
    qdev_init_nofail(dev);

    return PCI_HOST_BRIDGE(dev);
}

/* pSeries LPAR / sPAPR hardware init */
static void spapr_machine_init(MachineState *machine)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(machine);
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(machine);
    const char *kernel_filename = machine->kernel_filename;
    const char *initrd_filename = machine->initrd_filename;
    PCIHostState *phb;
    int i;
    MemoryRegion *sysmem = get_system_memory();
    MemoryRegion *ram = g_new(MemoryRegion, 1);
    hwaddr node0_size = spapr_node0_size(machine);
    long load_limit, fw_size;
    char *filename;
    Error *resize_hpt_err = NULL;

    msi_nonbroken = true;

    QLIST_INIT(&spapr->phbs);
    QTAILQ_INIT(&spapr->pending_dimm_unplugs);

    /* Determine capabilities to run with */
    spapr_caps_init(spapr);

    kvmppc_check_papr_resize_hpt(&resize_hpt_err);
    if (spapr->resize_hpt == SPAPR_RESIZE_HPT_DEFAULT) {
        /*
         * If the user explicitly requested a mode we should either
         * supply it, or fail completely (which we do below).  But if
         * it's not set explicitly, we reset our mode to something
         * that works
         */
        if (resize_hpt_err) {
            spapr->resize_hpt = SPAPR_RESIZE_HPT_DISABLED;
            error_free(resize_hpt_err);
            resize_hpt_err = NULL;
        } else {
            spapr->resize_hpt = smc->resize_hpt_default;
        }
    }

    assert(spapr->resize_hpt != SPAPR_RESIZE_HPT_DEFAULT);

    if ((spapr->resize_hpt != SPAPR_RESIZE_HPT_DISABLED) && resize_hpt_err) {
        /*
         * User requested HPT resize, but this host can't supply it.  Bail out
         */
        error_report_err(resize_hpt_err);
        exit(1);
    }

    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
     * which isn't determined yet.
     */
    if (kvm_enabled()) {
        spapr->vrma_adjust = 1;
        spapr->rma_size = MIN(spapr->rma_size, 0x10000000);
    }

    /* Actually we don't support unbounded RMA anymore since we added
     * proper emulation of HV mode. The max we can get is 16G which
     * also happens to be what we configure for PAPR mode so make sure
     * we don't do anything bigger than that
     */
    spapr->rma_size = MIN(spapr->rma_size, 0x400000000ull);

    if (spapr->rma_size > node0_size) {
        error_report("Numa node 0 has to span the RMA (%#08"HWADDR_PRIx")",
                     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;

    /*
     * VSMT must be set in order to be able to compute VCPU ids, ie to
     * call spapr_max_server_number() or spapr_vcpu_id().
     */
    spapr_set_vsmt_mode(spapr, &error_fatal);

    /* Set up Interrupt Controller before we create the VCPUs */
    spapr_irq_init(spapr, &error_fatal);

    /* Set up containers for ibm,client-architecture-support negotiated options
     */
    spapr->ov5 = spapr_ovec_new();
    spapr->ov5_cas = spapr_ovec_new();

    if (smc->dr_lmb_enabled) {
        spapr_ovec_set(spapr->ov5, OV5_DRCONF_MEMORY);
        spapr_validate_node_memory(machine, &error_fatal);
    }

    spapr_ovec_set(spapr->ov5, OV5_FORM1_AFFINITY);

    /* advertise support for dedicated HP event source to guests */
    if (spapr->use_hotplug_event_source) {
        spapr_ovec_set(spapr->ov5, OV5_HP_EVT);
    }

    /* advertise support for HPT resizing */
    if (spapr->resize_hpt != SPAPR_RESIZE_HPT_DISABLED) {
        spapr_ovec_set(spapr->ov5, OV5_HPT_RESIZE);
    }

    /* advertise support for ibm,dyamic-memory-v2 */
    spapr_ovec_set(spapr->ov5, OV5_DRMEM_V2);

    /* advertise XIVE on POWER9 machines */
    if (spapr->irq->ov5 & (SPAPR_OV5_XIVE_EXPLOIT | SPAPR_OV5_XIVE_BOTH)) {
        spapr_ovec_set(spapr->ov5, OV5_XIVE_EXPLOIT);
    }

    /* init CPUs */
    spapr_init_cpus(spapr);

    if ((!kvm_enabled() || kvmppc_has_cap_mmu_radix()) &&
        ppc_type_check_compat(machine->cpu_type, CPU_POWERPC_LOGICAL_3_00, 0,
                              spapr->max_compat_pvr)) {
        /* KVM and TCG always allow GTSE with radix... */
        spapr_ovec_set(spapr->ov5, OV5_MMU_RADIX_GTSE);
    }
    /* ... but not with hash (currently). */

    if (kvm_enabled()) {
        /* Enable H_LOGICAL_CI_* so SLOF can talk to in-kernel devices */
        kvmppc_enable_logical_ci_hcalls();
        kvmppc_enable_set_mode_hcall();

        /* H_CLEAR_MOD/_REF are mandatory in PAPR, but off by default */
        kvmppc_enable_clear_ref_mod_hcalls();

        /* Enable H_PAGE_INIT */
        kvmppc_enable_h_page_init();
    }

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

    /* always allocate the device memory information */
    machine->device_memory = g_malloc0(sizeof(*machine->device_memory));

    /* initialize hotplug memory address space */
    if (machine->ram_size < machine->maxram_size) {
        ram_addr_t device_mem_size = machine->maxram_size - machine->ram_size;
        /*
         * Limit the number of hotpluggable memory slots to half the number
         * slots that KVM supports, leaving the other half for PCI and other
         * devices. However ensure that number of slots doesn't drop below 32.
         */
        int max_memslots = kvm_enabled() ? kvm_get_max_memslots() / 2 :
                           SPAPR_MAX_RAM_SLOTS;

        if (max_memslots < SPAPR_MAX_RAM_SLOTS) {
            max_memslots = SPAPR_MAX_RAM_SLOTS;
        }
        if (machine->ram_slots > max_memslots) {
            error_report("Specified number of memory slots %"
                         PRIu64" exceeds max supported %d",
                         machine->ram_slots, max_memslots);
            exit(1);
        }

        machine->device_memory->base = ROUND_UP(machine->ram_size,
                                                SPAPR_DEVICE_MEM_ALIGN);
        memory_region_init(&machine->device_memory->mr, OBJECT(spapr),
                           "device-memory", device_mem_size);
        memory_region_add_subregion(sysmem, machine->device_memory->base,
                                    &machine->device_memory->mr);
    }

    if (smc->dr_lmb_enabled) {
        spapr_create_lmb_dr_connectors(spapr);
    }

    filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, "spapr-rtas.bin");
    if (!filename) {
        error_report("Could not find LPAR rtas '%s'", "spapr-rtas.bin");
        exit(1);
    }
    spapr->rtas_size = get_image_size(filename);
    if (spapr->rtas_size < 0) {
        error_report("Could not get size of LPAR rtas '%s'", filename);
        exit(1);
    }
    spapr->rtas_blob = g_malloc(spapr->rtas_size);
    if (load_image_size(filename, spapr->rtas_blob, spapr->rtas_size) < 0) {
        error_report("Could not load LPAR rtas '%s'", filename);
        exit(1);
    }
    if (spapr->rtas_size > RTAS_MAX_SIZE) {
        error_report("RTAS too big ! 0x%zx bytes (max is 0x%x)",
                     (size_t)spapr->rtas_size, RTAS_MAX_SIZE);
        exit(1);
    }
    g_free(filename);

    /* Set up RTAS event infrastructure */
    spapr_events_init(spapr);

    /* Set up the RTC RTAS interfaces */
    spapr_rtc_create(spapr);

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

    for (i = 0; i < serial_max_hds(); i++) {
        if (serial_hd(i)) {
            spapr_vty_create(spapr->vio_bus, serial_hd(i));
        }
    }

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

    /*
     * Setup hotplug / dynamic-reconfiguration connectors. top-level
     * connectors (described in root DT node's "ibm,drc-types" property)
     * are pre-initialized here. additional child connectors (such as
     * connectors for a PHBs PCI slots) are added as needed during their
     * parent's realization.
     */
    if (smc->dr_phb_enabled) {
        for (i = 0; i < SPAPR_MAX_PHBS; i++) {
            spapr_dr_connector_new(OBJECT(machine), TYPE_SPAPR_DRC_PHB, i);
        }
    }

    /* Set up PCI */
    spapr_pci_rtas_init();

    phb = spapr_create_default_phb();

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

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

        if (g_str_equal(nd->model, "spapr-vlan") ||
            g_str_equal(nd->model, "ibmveth")) {
            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, &error_fatal)) {
        spapr->has_graphics = true;
        machine->usb |= defaults_enabled() && !machine->usb_disabled;
    }

    if (machine->usb) {
        if (smc->use_ohci_by_default) {
            pci_create_simple(phb->bus, -1, "pci-ohci");
        } else {
            pci_create_simple(phb->bus, -1, "nec-usb-xhci");
        }

        if (spapr->has_graphics) {
            USBBus *usb_bus = usb_bus_find(-1);

            usb_create_simple(usb_bus, "usb-kbd");
            usb_create_simple(usb_bus, "usb-mouse");
        }
    }

    if (spapr->rma_size < (MIN_RMA_SLOF * MiB)) {
        error_report(
            "pSeries SLOF firmware requires >= %ldM guest RMA (Real Mode Area memory)",
            MIN_RMA_SLOF);
        exit(1);
    }

    if (kernel_filename) {
        uint64_t lowaddr = 0;

        spapr->kernel_size = load_elf(kernel_filename, NULL,
                                      translate_kernel_address, NULL,
                                      NULL, &lowaddr, NULL, 1,
                                      PPC_ELF_MACHINE, 0, 0);
        if (spapr->kernel_size == ELF_LOAD_WRONG_ENDIAN) {
            spapr->kernel_size = load_elf(kernel_filename, NULL,
                                          translate_kernel_address, NULL, NULL,
                                          &lowaddr, NULL, 0, PPC_ELF_MACHINE,
                                          0, 0);
            spapr->kernel_le = spapr->kernel_size > 0;
        }
        if (spapr->kernel_size < 0) {
            error_report("error loading %s: %s", kernel_filename,
                         load_elf_strerror(spapr->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
             */
            spapr->initrd_base = (KERNEL_LOAD_ADDR + spapr->kernel_size
                                  + 0x1ffff) & ~0xffff;
            spapr->initrd_size = load_image_targphys(initrd_filename,
                                                     spapr->initrd_base,
                                                     load_limit
                                                     - spapr->initrd_base);
            if (spapr->initrd_size < 0) {
                error_report("could not load initial ram disk '%s'",
                             initrd_filename);
                exit(1);
            }
        }
    }

    if (bios_name == NULL) {
        bios_name = FW_FILE_NAME;
    }
    filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name);
    if (!filename) {
        error_report("Could not find LPAR firmware '%s'", bios_name);
        exit(1);
    }
    fw_size = load_image_targphys(filename, 0, FW_MAX_SIZE);
    if (fw_size <= 0) {
        error_report("Could not load LPAR firmware '%s'", filename);
        exit(1);
    }
    g_free(filename);

    /* FIXME: Should register things through the MachineState's qdev
     * interface, this is a legacy from the sPAPREnvironment structure
     * which predated MachineState but had a similar function */
    vmstate_register(NULL, 0, &vmstate_spapr, spapr);
    register_savevm_live(NULL, "spapr/htab", -1, 1,
                         &savevm_htab_handlers, spapr);

    qbus_set_hotplug_handler(sysbus_get_default(), OBJECT(machine),
                             &error_fatal);

    qemu_register_boot_set(spapr_boot_set, spapr);

    if (kvm_enabled()) {
        /* to stop and start vmclock */
        qemu_add_vm_change_state_handler(cpu_ppc_clock_vm_state_change,
                                         &spapr->tb);

        kvmppc_spapr_enable_inkernel_multitce();
    }
}

static int spapr_kvm_type(MachineState *machine, 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 path
 * 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);
    VHostSCSICommon *vsc = CAST(VHostSCSICommon, dev, TYPE_VHOST_SCSI_COMMON);

    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":
             * In the top 16 bits of the 64-bit LUN, we use SRP luns of the form
             * 0x8000 | (target << 8) | (bus << 5) | lun
             * (see the "Logical unit addressing format" table in SAM5)
             */
            unsigned id = 0x8000 | (d->id << 8) | (d->channel << 5) | 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;
            if (d->lun >= 256) {
                /* Use the LUN "flat space addressing method" */
                id |= 0x4000;
            }
            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);
        }
    }

    /*
     * SLOF probes the USB devices, and if it recognizes that the device is a
     * storage device, it changes its name to "storage" instead of "usb-host",
     * and additionally adds a child node for the SCSI LUN, so the correct
     * boot path in SLOF is something like .../storage@1/disk@xxx" instead.
     */
    if (strcmp("usb-host", qdev_fw_name(dev)) == 0) {
        USBDevice *usbdev = CAST(USBDevice, dev, TYPE_USB_DEVICE);
        if (usb_host_dev_is_scsi_storage(usbdev)) {
            return g_strdup_printf("storage@%s/disk", usbdev->port->path);
        }
    }

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

    if (vsc) {
        /* Same logic as virtio above */
        unsigned id = 0x1000000 | (vsc->target << 16) | vsc->lun;
        return g_strdup_printf("disk@%"PRIX64, (uint64_t)id << 32);
    }

    if (g_str_equal("pci-bridge", qdev_fw_name(dev))) {
        /* SLOF uses "pci" instead of "pci-bridge" for PCI bridges */
        PCIDevice *pcidev = CAST(PCIDevice, dev, TYPE_PCI_DEVICE);
        return g_strdup_printf("pci@%x", PCI_SLOT(pcidev->devfn));
    }

    return NULL;
}

static char *spapr_get_kvm_type(Object *obj, Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);

    return g_strdup(spapr->kvm_type);
}

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

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

static bool spapr_get_modern_hotplug_events(Object *obj, Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);

    return spapr->use_hotplug_event_source;
}

static void spapr_set_modern_hotplug_events(Object *obj, bool value,
                                            Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);

    spapr->use_hotplug_event_source = value;
}

static bool spapr_get_msix_emulation(Object *obj, Error **errp)
{
    return true;
}

static char *spapr_get_resize_hpt(Object *obj, Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);

    switch (spapr->resize_hpt) {
    case SPAPR_RESIZE_HPT_DEFAULT:
        return g_strdup("default");
    case SPAPR_RESIZE_HPT_DISABLED:
        return g_strdup("disabled");
    case SPAPR_RESIZE_HPT_ENABLED:
        return g_strdup("enabled");
    case SPAPR_RESIZE_HPT_REQUIRED:
        return g_strdup("required");
    }
    g_assert_not_reached();
}

static void spapr_set_resize_hpt(Object *obj, const char *value, Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);

    if (strcmp(value, "default") == 0) {
        spapr->resize_hpt = SPAPR_RESIZE_HPT_DEFAULT;
    } else if (strcmp(value, "disabled") == 0) {
        spapr->resize_hpt = SPAPR_RESIZE_HPT_DISABLED;
    } else if (strcmp(value, "enabled") == 0) {
        spapr->resize_hpt = SPAPR_RESIZE_HPT_ENABLED;
    } else if (strcmp(value, "required") == 0) {
        spapr->resize_hpt = SPAPR_RESIZE_HPT_REQUIRED;
    } else {
        error_setg(errp, "Bad value for \"resize-hpt\" property");
    }
}

static void spapr_get_vsmt(Object *obj, Visitor *v, const char *name,
                                   void *opaque, Error **errp)
{
    visit_type_uint32(v, name, (uint32_t *)opaque, errp);
}

static void spapr_set_vsmt(Object *obj, Visitor *v, const char *name,
                                   void *opaque, Error **errp)
{
    visit_type_uint32(v, name, (uint32_t *)opaque, errp);
}

static char *spapr_get_ic_mode(Object *obj, Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);

    if (spapr->irq == &spapr_irq_xics_legacy) {
        return g_strdup("legacy");
    } else if (spapr->irq == &spapr_irq_xics) {
        return g_strdup("xics");
    } else if (spapr->irq == &spapr_irq_xive) {
        return g_strdup("xive");
    } else if (spapr->irq == &spapr_irq_dual) {
        return g_strdup("dual");
    }
    g_assert_not_reached();
}

static void spapr_set_ic_mode(Object *obj, const char *value, Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);

    if (SPAPR_MACHINE_GET_CLASS(spapr)->legacy_irq_allocation) {
        error_setg(errp, "This machine only uses the legacy XICS backend, don't pass ic-mode");
        return;
    }

    /* The legacy IRQ backend can not be set */
    if (strcmp(value, "xics") == 0) {
        spapr->irq = &spapr_irq_xics;
    } else if (strcmp(value, "xive") == 0) {
        spapr->irq = &spapr_irq_xive;
    } else if (strcmp(value, "dual") == 0) {
        spapr->irq = &spapr_irq_dual;
    } else {
        error_setg(errp, "Bad value for \"ic-mode\" property");
    }
}

static char *spapr_get_host_model(Object *obj, Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);

    return g_strdup(spapr->host_model);
}

static void spapr_set_host_model(Object *obj, const char *value, Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);

    g_free(spapr->host_model);
    spapr->host_model = g_strdup(value);
}

static char *spapr_get_host_serial(Object *obj, Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);

    return g_strdup(spapr->host_serial);
}

static void spapr_set_host_serial(Object *obj, const char *value, Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);

    g_free(spapr->host_serial);
    spapr->host_serial = g_strdup(value);
}

static void spapr_instance_init(Object *obj)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);

    spapr->htab_fd = -1;
    spapr->use_hotplug_event_source = true;
    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);
    object_property_add_bool(obj, "modern-hotplug-events",
                            spapr_get_modern_hotplug_events,
                            spapr_set_modern_hotplug_events,
                            NULL);
    object_property_set_description(obj, "modern-hotplug-events",
                                    "Use dedicated hotplug event mechanism in"
                                    " place of standard EPOW events when possible"
                                    " (required for memory hot-unplug support)",
                                    NULL);
    ppc_compat_add_property(obj, "max-cpu-compat", &spapr->max_compat_pvr,
                            "Maximum permitted CPU compatibility mode",
                            &error_fatal);

    object_property_add_str(obj, "resize-hpt",
                            spapr_get_resize_hpt, spapr_set_resize_hpt, NULL);
    object_property_set_description(obj, "resize-hpt",
                                    "Resizing of the Hash Page Table (enabled, disabled, required)",
                                    NULL);
    object_property_add(obj, "vsmt", "uint32", spapr_get_vsmt,
                        spapr_set_vsmt, NULL, &spapr->vsmt, &error_abort);
    object_property_set_description(obj, "vsmt",
                                    "Virtual SMT: KVM behaves as if this were"
                                    " the host's SMT mode", &error_abort);
    object_property_add_bool(obj, "vfio-no-msix-emulation",
                             spapr_get_msix_emulation, NULL, NULL);

    /* The machine class defines the default interrupt controller mode */
    spapr->irq = smc->irq;
    object_property_add_str(obj, "ic-mode", spapr_get_ic_mode,
                            spapr_set_ic_mode, NULL);
    object_property_set_description(obj, "ic-mode",
                 "Specifies the interrupt controller mode (xics, xive, dual)",
                 NULL);

    object_property_add_str(obj, "host-model",
        spapr_get_host_model, spapr_set_host_model,
        &error_abort);
    object_property_set_description(obj, "host-model",
        "Host model to advertise in guest device tree", &error_abort);
    object_property_add_str(obj, "host-serial",
        spapr_get_host_serial, spapr_set_host_serial,
        &error_abort);
    object_property_set_description(obj, "host-serial",
        "Host serial number to advertise in guest device tree", &error_abort);
}

static void spapr_machine_finalizefn(Object *obj)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);

    g_free(spapr->kvm_type);
}

void spapr_do_system_reset_on_cpu(CPUState *cs, run_on_cpu_data 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, spapr_do_system_reset_on_cpu, RUN_ON_CPU_NULL);
    }
}

int spapr_lmb_dt_populate(SpaprDrc *drc, SpaprMachineState *spapr,
                          void *fdt, int *fdt_start_offset, Error **errp)
{
    uint64_t addr;
    uint32_t node;

    addr = spapr_drc_index(drc) * SPAPR_MEMORY_BLOCK_SIZE;
    node = object_property_get_uint(OBJECT(drc->dev), PC_DIMM_NODE_PROP,
                                    &error_abort);
    *fdt_start_offset = spapr_populate_memory_node(fdt, node, addr,
                                                   SPAPR_MEMORY_BLOCK_SIZE);
    return 0;
}

static void spapr_add_lmbs(DeviceState *dev, uint64_t addr_start, uint64_t size,
                           bool dedicated_hp_event_source, Error **errp)
{
    SpaprDrc *drc;
    uint32_t nr_lmbs = size/SPAPR_MEMORY_BLOCK_SIZE;
    int i;
    uint64_t addr = addr_start;
    bool hotplugged = spapr_drc_hotplugged(dev);
    Error *local_err = NULL;

    for (i = 0; i < nr_lmbs; i++) {
        drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB,
                              addr / SPAPR_MEMORY_BLOCK_SIZE);
        g_assert(drc);

        spapr_drc_attach(drc, dev, &local_err);
        if (local_err) {
            while (addr > addr_start) {
                addr -= SPAPR_MEMORY_BLOCK_SIZE;
                drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB,
                                      addr / SPAPR_MEMORY_BLOCK_SIZE);
                spapr_drc_detach(drc);
            }
            error_propagate(errp, local_err);
            return;
        }
        if (!hotplugged) {
            spapr_drc_reset(drc);
        }
        addr += SPAPR_MEMORY_BLOCK_SIZE;
    }
    /* send hotplug notification to the
     * guest only in case of hotplugged memory
     */
    if (hotplugged) {
        if (dedicated_hp_event_source) {
            drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB,
                                  addr_start / SPAPR_MEMORY_BLOCK_SIZE);
            spapr_hotplug_req_add_by_count_indexed(SPAPR_DR_CONNECTOR_TYPE_LMB,
                                                   nr_lmbs,
                                                   spapr_drc_index(drc));
        } else {
            spapr_hotplug_req_add_by_count(SPAPR_DR_CONNECTOR_TYPE_LMB,
                                           nr_lmbs);
        }
    }
}

static void spapr_memory_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
                              Error **errp)
{
    Error *local_err = NULL;
    SpaprMachineState *ms = SPAPR_MACHINE(hotplug_dev);
    PCDIMMDevice *dimm = PC_DIMM(dev);
    uint64_t size, addr;

    size = memory_device_get_region_size(MEMORY_DEVICE(dev), &error_abort);

    pc_dimm_plug(dimm, MACHINE(ms), &local_err);
    if (local_err) {
        goto out;
    }

    addr = object_property_get_uint(OBJECT(dimm),
                                    PC_DIMM_ADDR_PROP, &local_err);
    if (local_err) {
        goto out_unplug;
    }

    spapr_add_lmbs(dev, addr, size, spapr_ovec_test(ms->ov5_cas, OV5_HP_EVT),
                   &local_err);
    if (local_err) {
        goto out_unplug;
    }

    return;

out_unplug:
    pc_dimm_unplug(dimm, MACHINE(ms));
out:
    error_propagate(errp, local_err);
}

static void spapr_memory_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
                                  Error **errp)
{
    const SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(hotplug_dev);
    SpaprMachineState *spapr = SPAPR_MACHINE(hotplug_dev);
    PCDIMMDevice *dimm = PC_DIMM(dev);
    Error *local_err = NULL;
    uint64_t size;
    Object *memdev;
    hwaddr pagesize;

    if (!smc->dr_lmb_enabled) {
        error_setg(errp, "Memory hotplug not supported for this machine");
        return;
    }

    size = memory_device_get_region_size(MEMORY_DEVICE(dimm), &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return;
    }

    if (size % SPAPR_MEMORY_BLOCK_SIZE) {
        error_setg(errp, "Hotplugged memory size must be a multiple of "
                      "%" PRIu64 " MB", SPAPR_MEMORY_BLOCK_SIZE / MiB);
        return;
    }

    memdev = object_property_get_link(OBJECT(dimm), PC_DIMM_MEMDEV_PROP,
                                      &error_abort);
    pagesize = host_memory_backend_pagesize(MEMORY_BACKEND(memdev));
    spapr_check_pagesize(spapr, pagesize, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return;
    }

    pc_dimm_pre_plug(dimm, MACHINE(hotplug_dev), NULL, errp);
}

struct SpaprDimmState {
    PCDIMMDevice *dimm;
    uint32_t nr_lmbs;
    QTAILQ_ENTRY(SpaprDimmState) next;
};

static SpaprDimmState *spapr_pending_dimm_unplugs_find(SpaprMachineState *s,
                                                       PCDIMMDevice *dimm)
{
    SpaprDimmState *dimm_state = NULL;

    QTAILQ_FOREACH(dimm_state, &s->pending_dimm_unplugs, next) {
        if (dimm_state->dimm == dimm) {
            break;
        }
    }
    return dimm_state;
}

static SpaprDimmState *spapr_pending_dimm_unplugs_add(SpaprMachineState *spapr,
                                                      uint32_t nr_lmbs,
                                                      PCDIMMDevice *dimm)
{
    SpaprDimmState *ds = NULL;

    /*
     * If this request is for a DIMM whose removal had failed earlier
     * (due to guest's refusal to remove the LMBs), we would have this
     * dimm already in the pending_dimm_unplugs list. In that
     * case don't add again.
     */
    ds = spapr_pending_dimm_unplugs_find(spapr, dimm);
    if (!ds) {
        ds = g_malloc0(sizeof(SpaprDimmState));
        ds->nr_lmbs = nr_lmbs;
        ds->dimm = dimm;
        QTAILQ_INSERT_HEAD(&spapr->pending_dimm_unplugs, ds, next);
    }
    return ds;
}

static void spapr_pending_dimm_unplugs_remove(SpaprMachineState *spapr,
                                              SpaprDimmState *dimm_state)
{
    QTAILQ_REMOVE(&spapr->pending_dimm_unplugs, dimm_state, next);
    g_free(dimm_state);
}

static SpaprDimmState *spapr_recover_pending_dimm_state(SpaprMachineState *ms,
                                                        PCDIMMDevice *dimm)
{
    SpaprDrc *drc;
    uint64_t size = memory_device_get_region_size(MEMORY_DEVICE(dimm),
                                                  &error_abort);
    uint32_t nr_lmbs = size / SPAPR_MEMORY_BLOCK_SIZE;
    uint32_t avail_lmbs = 0;
    uint64_t addr_start, addr;
    int i;

    addr_start = object_property_get_int(OBJECT(dimm), PC_DIMM_ADDR_PROP,
                                         &error_abort);

    addr = addr_start;
    for (i = 0; i < nr_lmbs; i++) {
        drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB,
                              addr / SPAPR_MEMORY_BLOCK_SIZE);
        g_assert(drc);
        if (drc->dev) {
            avail_lmbs++;
        }
        addr += SPAPR_MEMORY_BLOCK_SIZE;
    }

    return spapr_pending_dimm_unplugs_add(ms, avail_lmbs, dimm);
}

/* Callback to be called during DRC release. */
void spapr_lmb_release(DeviceState *dev)
{
    HotplugHandler *hotplug_ctrl = qdev_get_hotplug_handler(dev);
    SpaprMachineState *spapr = SPAPR_MACHINE(hotplug_ctrl);
    SpaprDimmState *ds = spapr_pending_dimm_unplugs_find(spapr, PC_DIMM(dev));

    /* This information will get lost if a migration occurs
     * during the unplug process. In this case recover it. */
    if (ds == NULL) {
        ds = spapr_recover_pending_dimm_state(spapr, PC_DIMM(dev));
        g_assert(ds);
        /* The DRC being examined by the caller at least must be counted */
        g_assert(ds->nr_lmbs);
    }

    if (--ds->nr_lmbs) {
        return;
    }

    /*
     * Now that all the LMBs have been removed by the guest, call the
     * unplug handler chain. This can never fail.
     */
    hotplug_handler_unplug(hotplug_ctrl, dev, &error_abort);
    object_unparent(OBJECT(dev));
}

static void spapr_memory_unplug(HotplugHandler *hotplug_dev, DeviceState *dev)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(hotplug_dev);
    SpaprDimmState *ds = spapr_pending_dimm_unplugs_find(spapr, PC_DIMM(dev));

    pc_dimm_unplug(PC_DIMM(dev), MACHINE(hotplug_dev));
    object_property_set_bool(OBJECT(dev), false, "realized", NULL);
    spapr_pending_dimm_unplugs_remove(spapr, ds);
}

static void spapr_memory_unplug_request(HotplugHandler *hotplug_dev,
                                        DeviceState *dev, Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(hotplug_dev);
    Error *local_err = NULL;
    PCDIMMDevice *dimm = PC_DIMM(dev);
    uint32_t nr_lmbs;
    uint64_t size, addr_start, addr;
    int i;
    SpaprDrc *drc;

    size = memory_device_get_region_size(MEMORY_DEVICE(dimm), &error_abort);
    nr_lmbs = size / SPAPR_MEMORY_BLOCK_SIZE;

    addr_start = object_property_get_uint(OBJECT(dimm), PC_DIMM_ADDR_PROP,
                                         &local_err);
    if (local_err) {
        goto out;
    }

    /*
     * An existing pending dimm state for this DIMM means that there is an
     * unplug operation in progress, waiting for the spapr_lmb_release
     * callback to complete the job (BQL can't cover that far). In this case,
     * bail out to avoid detaching DRCs that were already released.
     */
    if (spapr_pending_dimm_unplugs_find(spapr, dimm)) {
        error_setg(&local_err,
                   "Memory unplug already in progress for device %s",
                   dev->id);
        goto out;
    }

    spapr_pending_dimm_unplugs_add(spapr, nr_lmbs, dimm);

    addr = addr_start;
    for (i = 0; i < nr_lmbs; i++) {
        drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB,
                              addr / SPAPR_MEMORY_BLOCK_SIZE);
        g_assert(drc);

        spapr_drc_detach(drc);
        addr += SPAPR_MEMORY_BLOCK_SIZE;
    }

    drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB,
                          addr_start / SPAPR_MEMORY_BLOCK_SIZE);
    spapr_hotplug_req_remove_by_count_indexed(SPAPR_DR_CONNECTOR_TYPE_LMB,
                                              nr_lmbs, spapr_drc_index(drc));
out:
    error_propagate(errp, local_err);
}

/* Callback to be called during DRC release. */
void spapr_core_release(DeviceState *dev)
{
    HotplugHandler *hotplug_ctrl = qdev_get_hotplug_handler(dev);

    /* Call the unplug handler chain. This can never fail. */
    hotplug_handler_unplug(hotplug_ctrl, dev, &error_abort);
    object_unparent(OBJECT(dev));
}

static void spapr_core_unplug(HotplugHandler *hotplug_dev, DeviceState *dev)
{
    MachineState *ms = MACHINE(hotplug_dev);
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(ms);
    CPUCore *cc = CPU_CORE(dev);
    CPUArchId *core_slot = spapr_find_cpu_slot(ms, cc->core_id, NULL);

    if (smc->pre_2_10_has_unused_icps) {
        SpaprCpuCore *sc = SPAPR_CPU_CORE(OBJECT(dev));
        int i;

        for (i = 0; i < cc->nr_threads; i++) {
            CPUState *cs = CPU(sc->threads[i]);

            pre_2_10_vmstate_register_dummy_icp(cs->cpu_index);
        }
    }

    assert(core_slot);
    core_slot->cpu = NULL;
    object_property_set_bool(OBJECT(dev), false, "realized", NULL);
}

static
void spapr_core_unplug_request(HotplugHandler *hotplug_dev, DeviceState *dev,
                               Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(OBJECT(hotplug_dev));
    int index;
    SpaprDrc *drc;
    CPUCore *cc = CPU_CORE(dev);

    if (!spapr_find_cpu_slot(MACHINE(hotplug_dev), cc->core_id, &index)) {
        error_setg(errp, "Unable to find CPU core with core-id: %d",
                   cc->core_id);
        return;
    }
    if (index == 0) {
        error_setg(errp, "Boot CPU core may not be unplugged");
        return;
    }

    drc = spapr_drc_by_id(TYPE_SPAPR_DRC_CPU,
                          spapr_vcpu_id(spapr, cc->core_id));
    g_assert(drc);

    spapr_drc_detach(drc);

    spapr_hotplug_req_remove_by_index(drc);
}

int spapr_core_dt_populate(SpaprDrc *drc, SpaprMachineState *spapr,
                           void *fdt, int *fdt_start_offset, Error **errp)
{
    SpaprCpuCore *core = SPAPR_CPU_CORE(drc->dev);
    CPUState *cs = CPU(core->threads[0]);
    PowerPCCPU *cpu = POWERPC_CPU(cs);
    DeviceClass *dc = DEVICE_GET_CLASS(cs);
    int id = spapr_get_vcpu_id(cpu);
    char *nodename;
    int offset;

    nodename = g_strdup_printf("%s@%x", dc->fw_name, id);
    offset = fdt_add_subnode(fdt, 0, nodename);
    g_free(nodename);

    spapr_populate_cpu_dt(cs, fdt, offset, spapr);

    *fdt_start_offset = offset;
    return 0;
}

static void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
                            Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(OBJECT(hotplug_dev));
    MachineClass *mc = MACHINE_GET_CLASS(spapr);
    SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
    SpaprCpuCore *core = SPAPR_CPU_CORE(OBJECT(dev));
    CPUCore *cc = CPU_CORE(dev);
    CPUState *cs;
    SpaprDrc *drc;
    Error *local_err = NULL;
    CPUArchId *core_slot;
    int index;
    bool hotplugged = spapr_drc_hotplugged(dev);

    core_slot = spapr_find_cpu_slot(MACHINE(hotplug_dev), cc->core_id, &index);
    if (!core_slot) {
        error_setg(errp, "Unable to find CPU core with core-id: %d",
                   cc->core_id);
        return;
    }
    drc = spapr_drc_by_id(TYPE_SPAPR_DRC_CPU,
                          spapr_vcpu_id(spapr, cc->core_id));

    g_assert(drc || !mc->has_hotpluggable_cpus);

    if (drc) {
        spapr_drc_attach(drc, dev, &local_err);
        if (local_err) {
            error_propagate(errp, local_err);
            return;
        }

        if (hotplugged) {
            /*
             * Send hotplug notification interrupt to the guest only
             * in case of hotplugged CPUs.
             */
            spapr_hotplug_req_add_by_index(drc);
        } else {
            spapr_drc_reset(drc);
        }
    }

    core_slot->cpu = OBJECT(dev);

    if (smc->pre_2_10_has_unused_icps) {
        int i;

        for (i = 0; i < cc->nr_threads; i++) {
            cs = CPU(core->threads[i]);
            pre_2_10_vmstate_unregister_dummy_icp(cs->cpu_index);
        }
    }
}

static void spapr_core_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
                                Error **errp)
{
    MachineState *machine = MACHINE(OBJECT(hotplug_dev));
    MachineClass *mc = MACHINE_GET_CLASS(hotplug_dev);
    Error *local_err = NULL;
    CPUCore *cc = CPU_CORE(dev);
    const char *base_core_type = spapr_get_cpu_core_type(machine->cpu_type);
    const char *type = object_get_typename(OBJECT(dev));
    CPUArchId *core_slot;
    int index;
    unsigned int smp_threads = machine->smp.threads;

    if (dev->hotplugged && !mc->has_hotpluggable_cpus) {
        error_setg(&local_err, "CPU hotplug not supported for this machine");
        goto out;
    }

    if (strcmp(base_core_type, type)) {
        error_setg(&local_err, "CPU core type should be %s", base_core_type);
        goto out;
    }

    if (cc->core_id % smp_threads) {
        error_setg(&local_err, "invalid core id %d", cc->core_id);
        goto out;
    }

    /*
     * In general we should have homogeneous threads-per-core, but old
     * (pre hotplug support) machine types allow the last core to have
     * reduced threads as a compatibility hack for when we allowed
     * total vcpus not a multiple of threads-per-core.
     */
    if (mc->has_hotpluggable_cpus && (cc->nr_threads != smp_threads)) {
        error_setg(&local_err, "invalid nr-threads %d, must be %d",
                   cc->nr_threads, smp_threads);
        goto out;
    }

    core_slot = spapr_find_cpu_slot(MACHINE(hotplug_dev), cc->core_id, &index);
    if (!core_slot) {
        error_setg(&local_err, "core id %d out of range", cc->core_id);
        goto out;
    }

    if (core_slot->cpu) {
        error_setg(&local_err, "core %d already populated", cc->core_id);
        goto out;
    }

    numa_cpu_pre_plug(core_slot, dev, &local_err);

out:
    error_propagate(errp, local_err);
}

int spapr_phb_dt_populate(SpaprDrc *drc, SpaprMachineState *spapr,
                          void *fdt, int *fdt_start_offset, Error **errp)
{
    SpaprPhbState *sphb = SPAPR_PCI_HOST_BRIDGE(drc->dev);
    int intc_phandle;

    intc_phandle = spapr_irq_get_phandle(spapr, spapr->fdt_blob, errp);
    if (intc_phandle <= 0) {
        return -1;
    }

    if (spapr_dt_phb(sphb, intc_phandle, fdt, spapr->irq->nr_msis,
                     fdt_start_offset)) {
        error_setg(errp, "unable to create FDT node for PHB %d", sphb->index);
        return -1;
    }

    /* generally SLOF creates these, for hotplug it's up to QEMU */
    _FDT(fdt_setprop_string(fdt, *fdt_start_offset, "name", "pci"));

    return 0;
}

static void spapr_phb_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
                               Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(OBJECT(hotplug_dev));
    SpaprPhbState *sphb = SPAPR_PCI_HOST_BRIDGE(dev);
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
    const unsigned windows_supported = spapr_phb_windows_supported(sphb);

    if (dev->hotplugged && !smc->dr_phb_enabled) {
        error_setg(errp, "PHB hotplug not supported for this machine");
        return;
    }

    if (sphb->index == (uint32_t)-1) {
        error_setg(errp, "\"index\" for PAPR PHB is mandatory");
        return;
    }

    /*
     * This will check that sphb->index doesn't exceed the maximum number of
     * PHBs for the current machine type.
     */
    smc->phb_placement(spapr, sphb->index,
                       &sphb->buid, &sphb->io_win_addr,
                       &sphb->mem_win_addr, &sphb->mem64_win_addr,
                       windows_supported, sphb->dma_liobn,
                       &sphb->nv2_gpa_win_addr, &sphb->nv2_atsd_win_addr,
                       errp);
}

static void spapr_phb_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
                           Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(OBJECT(hotplug_dev));
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
    SpaprPhbState *sphb = SPAPR_PCI_HOST_BRIDGE(dev);
    SpaprDrc *drc;
    bool hotplugged = spapr_drc_hotplugged(dev);
    Error *local_err = NULL;

    if (!smc->dr_phb_enabled) {
        return;
    }

    drc = spapr_drc_by_id(TYPE_SPAPR_DRC_PHB, sphb->index);
    /* hotplug hooks should check it's enabled before getting this far */
    assert(drc);

    spapr_drc_attach(drc, DEVICE(dev), &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return;
    }

    if (hotplugged) {
        spapr_hotplug_req_add_by_index(drc);
    } else {
        spapr_drc_reset(drc);
    }
}

void spapr_phb_release(DeviceState *dev)
{
    HotplugHandler *hotplug_ctrl = qdev_get_hotplug_handler(dev);

    hotplug_handler_unplug(hotplug_ctrl, dev, &error_abort);
    object_unparent(OBJECT(dev));
}

static void spapr_phb_unplug(HotplugHandler *hotplug_dev, DeviceState *dev)
{
    object_property_set_bool(OBJECT(dev), false, "realized", NULL);
}

static void spapr_phb_unplug_request(HotplugHandler *hotplug_dev,
                                     DeviceState *dev, Error **errp)
{
    SpaprPhbState *sphb = SPAPR_PCI_HOST_BRIDGE(dev);
    SpaprDrc *drc;

    drc = spapr_drc_by_id(TYPE_SPAPR_DRC_PHB, sphb->index);
    assert(drc);

    if (!spapr_drc_unplug_requested(drc)) {
        spapr_drc_detach(drc);
        spapr_hotplug_req_remove_by_index(drc);
    }
}

static void spapr_machine_device_plug(HotplugHandler *hotplug_dev,
                                      DeviceState *dev, Error **errp)
{
    if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
        spapr_memory_plug(hotplug_dev, dev, errp);
    } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE)) {
        spapr_core_plug(hotplug_dev, dev, errp);
    } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_PCI_HOST_BRIDGE)) {
        spapr_phb_plug(hotplug_dev, dev, errp);
    }
}

static void spapr_machine_device_unplug(HotplugHandler *hotplug_dev,
                                        DeviceState *dev, Error **errp)
{
    if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
        spapr_memory_unplug(hotplug_dev, dev);
    } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE)) {
        spapr_core_unplug(hotplug_dev, dev);
    } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_PCI_HOST_BRIDGE)) {
        spapr_phb_unplug(hotplug_dev, dev);
    }
}

static void spapr_machine_device_unplug_request(HotplugHandler *hotplug_dev,
                                                DeviceState *dev, Error **errp)
{
    SpaprMachineState *sms = SPAPR_MACHINE(OBJECT(hotplug_dev));
    MachineClass *mc = MACHINE_GET_CLASS(sms);
    SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);

    if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
        if (spapr_ovec_test(sms->ov5_cas, OV5_HP_EVT)) {
            spapr_memory_unplug_request(hotplug_dev, dev, errp);
        } else {
            /* NOTE: this means there is a window after guest reset, prior to
             * CAS negotiation, where unplug requests will fail due to the
             * capability not being detected yet. This is a bit different than
             * the case with PCI unplug, where the events will be queued and
             * eventually handled by the guest after boot
             */
            error_setg(errp, "Memory hot unplug not supported for this guest");
        }
    } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE)) {
        if (!mc->has_hotpluggable_cpus) {
            error_setg(errp, "CPU hot unplug not supported on this machine");
            return;
        }
        spapr_core_unplug_request(hotplug_dev, dev, errp);
    } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_PCI_HOST_BRIDGE)) {
        if (!smc->dr_phb_enabled) {
            error_setg(errp, "PHB hot unplug not supported on this machine");
            return;
        }
        spapr_phb_unplug_request(hotplug_dev, dev, errp);
    }
}

static void spapr_machine_device_pre_plug(HotplugHandler *hotplug_dev,
                                          DeviceState *dev, Error **errp)
{
    if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
        spapr_memory_pre_plug(hotplug_dev, dev, errp);
    } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE)) {
        spapr_core_pre_plug(hotplug_dev, dev, errp);
    } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_PCI_HOST_BRIDGE)) {
        spapr_phb_pre_plug(hotplug_dev, dev, errp);
    }
}

static HotplugHandler *spapr_get_hotplug_handler(MachineState *machine,
                                                 DeviceState *dev)
{
    if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) ||
        object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE) ||
        object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_PCI_HOST_BRIDGE)) {
        return HOTPLUG_HANDLER(machine);
    }
    if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
        PCIDevice *pcidev = PCI_DEVICE(dev);
        PCIBus *root = pci_device_root_bus(pcidev);
        SpaprPhbState *phb =
            (SpaprPhbState *)object_dynamic_cast(OBJECT(BUS(root)->parent),
                                                 TYPE_SPAPR_PCI_HOST_BRIDGE);

        if (phb) {
            return HOTPLUG_HANDLER(phb);
        }
    }
    return NULL;
}

static CpuInstanceProperties
spapr_cpu_index_to_props(MachineState *machine, unsigned cpu_index)
{
    CPUArchId *core_slot;
    MachineClass *mc = MACHINE_GET_CLASS(machine);

    /* make sure possible_cpu are intialized */
    mc->possible_cpu_arch_ids(machine);
    /* get CPU core slot containing thread that matches cpu_index */
    core_slot = spapr_find_cpu_slot(machine, cpu_index, NULL);
    assert(core_slot);
    return core_slot->props;
}

static int64_t spapr_get_default_cpu_node_id(const MachineState *ms, int idx)
{
    return idx / ms->smp.cores % nb_numa_nodes;
}

static const CPUArchIdList *spapr_possible_cpu_arch_ids(MachineState *machine)
{
    int i;
    unsigned int smp_threads = machine->smp.threads;
    unsigned int smp_cpus = machine->smp.cpus;
    const char *core_type;
    int spapr_max_cores = machine->smp.max_cpus / smp_threads;
    MachineClass *mc = MACHINE_GET_CLASS(machine);

    if (!mc->has_hotpluggable_cpus) {
        spapr_max_cores = QEMU_ALIGN_UP(smp_cpus, smp_threads) / smp_threads;
    }
    if (machine->possible_cpus) {
        assert(machine->possible_cpus->len == spapr_max_cores);
        return machine->possible_cpus;
    }

    core_type = spapr_get_cpu_core_type(machine->cpu_type);
    if (!core_type) {
        error_report("Unable to find sPAPR CPU Core definition");
        exit(1);
    }

    machine->possible_cpus = g_malloc0(sizeof(CPUArchIdList) +
                             sizeof(CPUArchId) * spapr_max_cores);
    machine->possible_cpus->len = spapr_max_cores;
    for (i = 0; i < machine->possible_cpus->len; i++) {
        int core_id = i * smp_threads;

        machine->possible_cpus->cpus[i].type = core_type;
        machine->possible_cpus->cpus[i].vcpus_count = smp_threads;
        machine->possible_cpus->cpus[i].arch_id = core_id;
        machine->possible_cpus->cpus[i].props.has_core_id = true;
        machine->possible_cpus->cpus[i].props.core_id = core_id;
    }
    return machine->possible_cpus;
}

static void spapr_phb_placement(SpaprMachineState *spapr, uint32_t index,
                                uint64_t *buid, hwaddr *pio,
                                hwaddr *mmio32, hwaddr *mmio64,
                                unsigned n_dma, uint32_t *liobns,
                                hwaddr *nv2gpa, hwaddr *nv2atsd, Error **errp)
{
    /*
     * New-style PHB window placement.
     *
     * Goals: Gives large (1TiB), naturally aligned 64-bit MMIO window
     * for each PHB, in addition to 2GiB 32-bit MMIO and 64kiB PIO
     * windows.
     *
     * Some guest kernels can't work with MMIO windows above 1<<46
     * (64TiB), so we place up to 31 PHBs in the area 32TiB..64TiB
     *
     * 32TiB..(33TiB+1984kiB) contains the 64kiB PIO windows for each
     * PHB stacked together.  (32TiB+2GiB)..(32TiB+64GiB) contains the
     * 2GiB 32-bit MMIO windows for each PHB.  Then 33..64TiB has the
     * 1TiB 64-bit MMIO windows for each PHB.
     */
    const uint64_t base_buid = 0x800000020000000ULL;
    int i;

    /* Sanity check natural alignments */
    QEMU_BUILD_BUG_ON((SPAPR_PCI_BASE % SPAPR_PCI_MEM64_WIN_SIZE) != 0);
    QEMU_BUILD_BUG_ON((SPAPR_PCI_LIMIT % SPAPR_PCI_MEM64_WIN_SIZE) != 0);
    QEMU_BUILD_BUG_ON((SPAPR_PCI_MEM64_WIN_SIZE % SPAPR_PCI_MEM32_WIN_SIZE) != 0);
    QEMU_BUILD_BUG_ON((SPAPR_PCI_MEM32_WIN_SIZE % SPAPR_PCI_IO_WIN_SIZE) != 0);
    /* Sanity check bounds */
    QEMU_BUILD_BUG_ON((SPAPR_MAX_PHBS * SPAPR_PCI_IO_WIN_SIZE) >
                      SPAPR_PCI_MEM32_WIN_SIZE);
    QEMU_BUILD_BUG_ON((SPAPR_MAX_PHBS * SPAPR_PCI_MEM32_WIN_SIZE) >
                      SPAPR_PCI_MEM64_WIN_SIZE);

    if (index >= SPAPR_MAX_PHBS) {
        error_setg(errp, "\"index\" for PAPR PHB is too large (max %llu)",
                   SPAPR_MAX_PHBS - 1);
        return;
    }

    *buid = base_buid + index;
    for (i = 0; i < n_dma; ++i) {
        liobns[i] = SPAPR_PCI_LIOBN(index, i);
    }

    *pio = SPAPR_PCI_BASE + index * SPAPR_PCI_IO_WIN_SIZE;
    *mmio32 = SPAPR_PCI_BASE + (index + 1) * SPAPR_PCI_MEM32_WIN_SIZE;
    *mmio64 = SPAPR_PCI_BASE + (index + 1) * SPAPR_PCI_MEM64_WIN_SIZE;

    *nv2gpa = SPAPR_PCI_NV2RAM64_WIN_BASE + index * SPAPR_PCI_NV2RAM64_WIN_SIZE;
    *nv2atsd = SPAPR_PCI_NV2ATSD_WIN_BASE + index * SPAPR_PCI_NV2ATSD_WIN_SIZE;
}

static ICSState *spapr_ics_get(XICSFabric *dev, int irq)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(dev);

    return ics_valid_irq(spapr->ics, irq) ? spapr->ics : NULL;
}

static void spapr_ics_resend(XICSFabric *dev)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(dev);

    ics_resend(spapr->ics);
}

static ICPState *spapr_icp_get(XICSFabric *xi, int vcpu_id)
{
    PowerPCCPU *cpu = spapr_find_cpu(vcpu_id);

    return cpu ? spapr_cpu_state(cpu)->icp : NULL;
}

static void spapr_pic_print_info(InterruptStatsProvider *obj,
                                 Monitor *mon)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);

    spapr->irq->print_info(spapr, mon);
}

int spapr_get_vcpu_id(PowerPCCPU *cpu)
{
    return cpu->vcpu_id;
}

void spapr_set_vcpu_id(PowerPCCPU *cpu, int cpu_index, Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
    MachineState *ms = MACHINE(spapr);
    int vcpu_id;

    vcpu_id = spapr_vcpu_id(spapr, cpu_index);

    if (kvm_enabled() && !kvm_vcpu_id_is_valid(vcpu_id)) {
        error_setg(errp, "Can't create CPU with id %d in KVM", vcpu_id);
        error_append_hint(errp, "Adjust the number of cpus to %d "
                          "or try to raise the number of threads per core\n",
                          vcpu_id * ms->smp.threads / spapr->vsmt);
        return;
    }

    cpu->vcpu_id = vcpu_id;
}

PowerPCCPU *spapr_find_cpu(int vcpu_id)
{
    CPUState *cs;

    CPU_FOREACH(cs) {
        PowerPCCPU *cpu = POWERPC_CPU(cs);

        if (spapr_get_vcpu_id(cpu) == vcpu_id) {
            return cpu;
        }
    }

    return NULL;
}

static void spapr_machine_class_init(ObjectClass *oc, void *data)
{
    MachineClass *mc = MACHINE_CLASS(oc);
    SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(oc);
    FWPathProviderClass *fwc = FW_PATH_PROVIDER_CLASS(oc);
    NMIClass *nc = NMI_CLASS(oc);
    HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc);
    PPCVirtualHypervisorClass *vhc = PPC_VIRTUAL_HYPERVISOR_CLASS(oc);
    XICSFabricClass *xic = XICS_FABRIC_CLASS(oc);
    InterruptStatsProviderClass *ispc = INTERRUPT_STATS_PROVIDER_CLASS(oc);

    mc->desc = "pSeries Logical Partition (PAPR compliant)";
    mc->ignore_boot_device_suffixes = true;

    /*
     * We set up the default / latest behaviour here.  The class_init
     * functions for the specific versioned machine types can override
     * these details for backwards compatibility
     */
    mc->init = spapr_machine_init;
    mc->reset = spapr_machine_reset;
    mc->block_default_type = IF_SCSI;
    mc->max_cpus = 1024;
    mc->no_parallel = 1;
    mc->default_boot_order = "";
    mc->default_ram_size = 512 * MiB;
    mc->default_display = "std";
    mc->kvm_type = spapr_kvm_type;
    machine_class_allow_dynamic_sysbus_dev(mc, TYPE_SPAPR_PCI_HOST_BRIDGE);
    mc->pci_allow_0_address = true;
    assert(!mc->get_hotplug_handler);
    mc->get_hotplug_handler = spapr_get_hotplug_handler;
    hc->pre_plug = spapr_machine_device_pre_plug;
    hc->plug = spapr_machine_device_plug;
    mc->cpu_index_to_instance_props = spapr_cpu_index_to_props;
    mc->get_default_cpu_node_id = spapr_get_default_cpu_node_id;
    mc->possible_cpu_arch_ids = spapr_possible_cpu_arch_ids;
    hc->unplug_request = spapr_machine_device_unplug_request;
    hc->unplug = spapr_machine_device_unplug;

    smc->dr_lmb_enabled = true;
    smc->update_dt_enabled = true;
    mc->default_cpu_type = POWERPC_CPU_TYPE_NAME("power9_v2.0");
    mc->has_hotpluggable_cpus = true;
    smc->resize_hpt_default = SPAPR_RESIZE_HPT_ENABLED;
    fwc->get_dev_path = spapr_get_fw_dev_path;
    nc->nmi_monitor_handler = spapr_nmi;
    smc->phb_placement = spapr_phb_placement;
    vhc->hypercall = emulate_spapr_hypercall;
    vhc->hpt_mask = spapr_hpt_mask;
    vhc->map_hptes = spapr_map_hptes;
    vhc->unmap_hptes = spapr_unmap_hptes;
    vhc->hpte_set_c = spapr_hpte_set_c;
    vhc->hpte_set_r = spapr_hpte_set_r;
    vhc->get_pate = spapr_get_pate;
    vhc->encode_hpt_for_kvm_pr = spapr_encode_hpt_for_kvm_pr;
    xic->ics_get = spapr_ics_get;
    xic->ics_resend = spapr_ics_resend;
    xic->icp_get = spapr_icp_get;
    ispc->print_info = spapr_pic_print_info;
    /* Force NUMA node memory size to be a multiple of
     * SPAPR_MEMORY_BLOCK_SIZE (256M) since that's the granularity
     * in which LMBs are represented and hot-added
     */
    mc->numa_mem_align_shift = 28;
    mc->numa_mem_supported = true;

    smc->default_caps.caps[SPAPR_CAP_HTM] = SPAPR_CAP_OFF;
    smc->default_caps.caps[SPAPR_CAP_VSX] = SPAPR_CAP_ON;
    smc->default_caps.caps[SPAPR_CAP_DFP] = SPAPR_CAP_ON;
    smc->default_caps.caps[SPAPR_CAP_CFPC] = SPAPR_CAP_WORKAROUND;
    smc->default_caps.caps[SPAPR_CAP_SBBC] = SPAPR_CAP_WORKAROUND;
    smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_WORKAROUND;
    smc->default_caps.caps[SPAPR_CAP_HPT_MAXPAGESIZE] = 16; /* 64kiB */
    smc->default_caps.caps[SPAPR_CAP_NESTED_KVM_HV] = SPAPR_CAP_OFF;
    smc->default_caps.caps[SPAPR_CAP_LARGE_DECREMENTER] = SPAPR_CAP_ON;
    smc->default_caps.caps[SPAPR_CAP_CCF_ASSIST] = SPAPR_CAP_OFF;
    spapr_caps_add_properties(smc, &error_abort);
    smc->irq = &spapr_irq_dual;
    smc->dr_phb_enabled = true;
}

static const TypeInfo spapr_machine_info = {
    .name          = TYPE_SPAPR_MACHINE,
    .parent        = TYPE_MACHINE,
    .abstract      = true,
    .instance_size = sizeof(SpaprMachineState),
    .instance_init = spapr_instance_init,
    .instance_finalize = spapr_machine_finalizefn,
    .class_size    = sizeof(SpaprMachineClass),
    .class_init    = spapr_machine_class_init,
    .interfaces = (InterfaceInfo[]) {
        { TYPE_FW_PATH_PROVIDER },
        { TYPE_NMI },
        { TYPE_HOTPLUG_HANDLER },
        { TYPE_PPC_VIRTUAL_HYPERVISOR },
        { TYPE_XICS_FABRIC },
        { TYPE_INTERRUPT_STATS_PROVIDER },
        { }
    },
};

#define DEFINE_SPAPR_MACHINE(suffix, verstr, latest)                 \
    static void spapr_machine_##suffix##_class_init(ObjectClass *oc, \
                                                    void *data)      \
    {                                                                \
        MachineClass *mc = MACHINE_CLASS(oc);                        \
        spapr_machine_##suffix##_class_options(mc);                  \
        if (latest) {                                                \
            mc->alias = "pseries";                                   \
            mc->is_default = 1;                                      \
        }                                                            \
    }                                                                \
    static const TypeInfo spapr_machine_##suffix##_info = {          \
        .name = MACHINE_TYPE_NAME("pseries-" verstr),                \
        .parent = TYPE_SPAPR_MACHINE,                                \
        .class_init = spapr_machine_##suffix##_class_init,           \
    };                                                               \
    static void spapr_machine_register_##suffix(void)                \
    {                                                                \
        type_register(&spapr_machine_##suffix##_info);               \
    }                                                                \
    type_init(spapr_machine_register_##suffix)

/*
 * pseries-4.1
 */
static void spapr_machine_4_1_class_options(MachineClass *mc)
{
    /* Defaults for the latest behaviour inherited from the base class */
}

DEFINE_SPAPR_MACHINE(4_1, "4.1", true);

/*
 * pseries-4.0
 */
static void phb_placement_4_0(SpaprMachineState *spapr, uint32_t index,
                              uint64_t *buid, hwaddr *pio,
                              hwaddr *mmio32, hwaddr *mmio64,
                              unsigned n_dma, uint32_t *liobns,
                              hwaddr *nv2gpa, hwaddr *nv2atsd, Error **errp)
{
    spapr_phb_placement(spapr, index, buid, pio, mmio32, mmio64, n_dma, liobns,
                        nv2gpa, nv2atsd, errp);
    *nv2gpa = 0;
    *nv2atsd = 0;
}

static void spapr_machine_4_0_class_options(MachineClass *mc)
{
    SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);

    spapr_machine_4_1_class_options(mc);
    compat_props_add(mc->compat_props, hw_compat_4_0, hw_compat_4_0_len);
    smc->phb_placement = phb_placement_4_0;
    smc->irq = &spapr_irq_xics;
    smc->pre_4_1_migration = true;
}

DEFINE_SPAPR_MACHINE(4_0, "4.0", false);

/*
 * pseries-3.1
 */
static void spapr_machine_3_1_class_options(MachineClass *mc)
{
    SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);

    spapr_machine_4_0_class_options(mc);
    compat_props_add(mc->compat_props, hw_compat_3_1, hw_compat_3_1_len);

    mc->default_cpu_type = POWERPC_CPU_TYPE_NAME("power8_v2.0");
    smc->update_dt_enabled = false;
    smc->dr_phb_enabled = false;
    smc->broken_host_serial_model = true;
    smc->default_caps.caps[SPAPR_CAP_CFPC] = SPAPR_CAP_BROKEN;
    smc->default_caps.caps[SPAPR_CAP_SBBC] = SPAPR_CAP_BROKEN;
    smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_BROKEN;
    smc->default_caps.caps[SPAPR_CAP_LARGE_DECREMENTER] = SPAPR_CAP_OFF;
}

DEFINE_SPAPR_MACHINE(3_1, "3.1", false);

/*
 * pseries-3.0
 */

static void spapr_machine_3_0_class_options(MachineClass *mc)
{
    SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);

    spapr_machine_3_1_class_options(mc);
    compat_props_add(mc->compat_props, hw_compat_3_0, hw_compat_3_0_len);

    smc->legacy_irq_allocation = true;
    smc->irq = &spapr_irq_xics_legacy;
}

DEFINE_SPAPR_MACHINE(3_0, "3.0", false);

/*
 * pseries-2.12
 */
static void spapr_machine_2_12_class_options(MachineClass *mc)
{
    SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
    static GlobalProperty compat[] = {
        { TYPE_POWERPC_CPU, "pre-3.0-migration", "on" },
        { TYPE_SPAPR_CPU_CORE, "pre-3.0-migration", "on" },
    };

    spapr_machine_3_0_class_options(mc);
    compat_props_add(mc->compat_props, hw_compat_2_12, hw_compat_2_12_len);
    compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));

    /* We depend on kvm_enabled() to choose a default value for the
     * hpt-max-page-size capability. Of course we can't do it here
     * because this is too early and the HW accelerator isn't initialzed
     * yet. Postpone this to machine init (see default_caps_with_cpu()).
     */
    smc->default_caps.caps[SPAPR_CAP_HPT_MAXPAGESIZE] = 0;
}

DEFINE_SPAPR_MACHINE(2_12, "2.12", false);

static void spapr_machine_2_12_sxxm_class_options(MachineClass *mc)
{
    SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);

    spapr_machine_2_12_class_options(mc);
    smc->default_caps.caps[SPAPR_CAP_CFPC] = SPAPR_CAP_WORKAROUND;
    smc->default_caps.caps[SPAPR_CAP_SBBC] = SPAPR_CAP_WORKAROUND;
    smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_FIXED_CCD;
}

DEFINE_SPAPR_MACHINE(2_12_sxxm, "2.12-sxxm", false);

/*
 * pseries-2.11
 */

static void spapr_machine_2_11_class_options(MachineClass *mc)
{
    SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);

    spapr_machine_2_12_class_options(mc);
    smc->default_caps.caps[SPAPR_CAP_HTM] = SPAPR_CAP_ON;
    compat_props_add(mc->compat_props, hw_compat_2_11, hw_compat_2_11_len);
}

DEFINE_SPAPR_MACHINE(2_11, "2.11", false);

/*
 * pseries-2.10
 */

static void spapr_machine_2_10_class_options(MachineClass *mc)
{
    spapr_machine_2_11_class_options(mc);
    compat_props_add(mc->compat_props, hw_compat_2_10, hw_compat_2_10_len);
}

DEFINE_SPAPR_MACHINE(2_10, "2.10", false);

/*
 * pseries-2.9
 */

static void spapr_machine_2_9_class_options(MachineClass *mc)
{
    SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
    static GlobalProperty compat[] = {
        { TYPE_POWERPC_CPU, "pre-2.10-migration", "on" },
    };

    spapr_machine_2_10_class_options(mc);
    compat_props_add(mc->compat_props, hw_compat_2_9, hw_compat_2_9_len);
    compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
    mc->numa_auto_assign_ram = numa_legacy_auto_assign_ram;
    smc->pre_2_10_has_unused_icps = true;
    smc->resize_hpt_default = SPAPR_RESIZE_HPT_DISABLED;
}

DEFINE_SPAPR_MACHINE(2_9, "2.9", false);

/*
 * pseries-2.8
 */

static void spapr_machine_2_8_class_options(MachineClass *mc)
{
    static GlobalProperty compat[] = {
        { TYPE_SPAPR_PCI_HOST_BRIDGE, "pcie-extended-configuration-space", "off" },
    };

    spapr_machine_2_9_class_options(mc);
    compat_props_add(mc->compat_props, hw_compat_2_8, hw_compat_2_8_len);
    compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
    mc->numa_mem_align_shift = 23;
}

DEFINE_SPAPR_MACHINE(2_8, "2.8", false);

/*
 * pseries-2.7
 */

static void phb_placement_2_7(SpaprMachineState *spapr, uint32_t index,
                              uint64_t *buid, hwaddr *pio,
                              hwaddr *mmio32, hwaddr *mmio64,
                              unsigned n_dma, uint32_t *liobns,
                              hwaddr *nv2gpa, hwaddr *nv2atsd, Error **errp)
{
    /* Legacy PHB placement for pseries-2.7 and earlier machine types */
    const uint64_t base_buid = 0x800000020000000ULL;
    const hwaddr phb_spacing = 0x1000000000ULL; /* 64 GiB */
    const hwaddr mmio_offset = 0xa0000000; /* 2 GiB + 512 MiB */
    const hwaddr pio_offset = 0x80000000; /* 2 GiB */
    const uint32_t max_index = 255;
    const hwaddr phb0_alignment = 0x10000000000ULL; /* 1 TiB */

    uint64_t ram_top = MACHINE(spapr)->ram_size;
    hwaddr phb0_base, phb_base;
    int i;

    /* Do we have device memory? */
    if (MACHINE(spapr)->maxram_size > ram_top) {
        /* Can't just use maxram_size, because there may be an
         * alignment gap between normal and device memory regions
         */
        ram_top = MACHINE(spapr)->device_memory->base +
            memory_region_size(&MACHINE(spapr)->device_memory->mr);
    }

    phb0_base = QEMU_ALIGN_UP(ram_top, phb0_alignment);

    if (index > max_index) {
        error_setg(errp, "\"index\" for PAPR PHB is too large (max %u)",
                   max_index);
        return;
    }

    *buid = base_buid + index;
    for (i = 0; i < n_dma; ++i) {
        liobns[i] = SPAPR_PCI_LIOBN(index, i);
    }

    phb_base = phb0_base + index * phb_spacing;
    *pio = phb_base + pio_offset;
    *mmio32 = phb_base + mmio_offset;
    /*
     * We don't set the 64-bit MMIO window, relying on the PHB's
     * fallback behaviour of automatically splitting a large "32-bit"
     * window into contiguous 32-bit and 64-bit windows
     */

    *nv2gpa = 0;
    *nv2atsd = 0;
}

static void spapr_machine_2_7_class_options(MachineClass *mc)
{
    SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
    static GlobalProperty compat[] = {
        { TYPE_SPAPR_PCI_HOST_BRIDGE, "mem_win_size", "0xf80000000", },
        { TYPE_SPAPR_PCI_HOST_BRIDGE, "mem64_win_size", "0", },
        { TYPE_POWERPC_CPU, "pre-2.8-migration", "on", },
        { TYPE_SPAPR_PCI_HOST_BRIDGE, "pre-2.8-migration", "on", },
    };

    spapr_machine_2_8_class_options(mc);
    mc->default_cpu_type = POWERPC_CPU_TYPE_NAME("power7_v2.3");
    mc->default_machine_opts = "modern-hotplug-events=off";
    compat_props_add(mc->compat_props, hw_compat_2_7, hw_compat_2_7_len);
    compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
    smc->phb_placement = phb_placement_2_7;
}

DEFINE_SPAPR_MACHINE(2_7, "2.7", false);

/*
 * pseries-2.6
 */

static void spapr_machine_2_6_class_options(MachineClass *mc)
{
    static GlobalProperty compat[] = {
        { TYPE_SPAPR_PCI_HOST_BRIDGE, "ddw", "off" },
    };

    spapr_machine_2_7_class_options(mc);
    mc->has_hotpluggable_cpus = false;
    compat_props_add(mc->compat_props, hw_compat_2_6, hw_compat_2_6_len);
    compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
}

DEFINE_SPAPR_MACHINE(2_6, "2.6", false);

/*
 * pseries-2.5
 */

static void spapr_machine_2_5_class_options(MachineClass *mc)
{
    SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
    static GlobalProperty compat[] = {
        { "spapr-vlan", "use-rx-buffer-pools", "off" },
    };

    spapr_machine_2_6_class_options(mc);
    smc->use_ohci_by_default = true;
    compat_props_add(mc->compat_props, hw_compat_2_5, hw_compat_2_5_len);
    compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
}

DEFINE_SPAPR_MACHINE(2_5, "2.5", false);

/*
 * pseries-2.4
 */

static void spapr_machine_2_4_class_options(MachineClass *mc)
{
    SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);

    spapr_machine_2_5_class_options(mc);
    smc->dr_lmb_enabled = false;
    compat_props_add(mc->compat_props, hw_compat_2_4, hw_compat_2_4_len);
}

DEFINE_SPAPR_MACHINE(2_4, "2.4", false);

/*
 * pseries-2.3
 */

static void spapr_machine_2_3_class_options(MachineClass *mc)
{
    static GlobalProperty compat[] = {
        { "spapr-pci-host-bridge", "dynamic-reconfiguration", "off" },
    };
    spapr_machine_2_4_class_options(mc);
    compat_props_add(mc->compat_props, hw_compat_2_3, hw_compat_2_3_len);
    compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
}
DEFINE_SPAPR_MACHINE(2_3, "2.3", false);

/*
 * pseries-2.2
 */

static void spapr_machine_2_2_class_options(MachineClass *mc)
{
    static GlobalProperty compat[] = {
        { TYPE_SPAPR_PCI_HOST_BRIDGE, "mem_win_size", "0x20000000" },
    };

    spapr_machine_2_3_class_options(mc);
    compat_props_add(mc->compat_props, hw_compat_2_2, hw_compat_2_2_len);
    compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
    mc->default_machine_opts = "modern-hotplug-events=off,suppress-vmdesc=on";
}
DEFINE_SPAPR_MACHINE(2_2, "2.2", false);

/*
 * pseries-2.1
 */

static void spapr_machine_2_1_class_options(MachineClass *mc)
{
    spapr_machine_2_2_class_options(mc);
    compat_props_add(mc->compat_props, hw_compat_2_1, hw_compat_2_1_len);
}
DEFINE_SPAPR_MACHINE(2_1, "2.1", false);

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

type_init(spapr_machine_register_types)