summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kvm/book3s_hv.c
blob: df81caab738339c5b8dfe7c2def731bb9ba640d1 (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
/*
 * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
 * Copyright (C) 2009. SUSE Linux Products GmbH. All rights reserved.
 *
 * Authors:
 *    Paul Mackerras <paulus@au1.ibm.com>
 *    Alexander Graf <agraf@suse.de>
 *    Kevin Wolf <mail@kevin-wolf.de>
 *
 * Description: KVM functions specific to running on Book 3S
 * processors in hypervisor mode (specifically POWER7 and later).
 *
 * This file is derived from arch/powerpc/kvm/book3s.c,
 * by Alexander Graf <agraf@suse.de>.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License, version 2, as
 * published by the Free Software Foundation.
 */

#include <linux/kvm_host.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/preempt.h>
#include <linux/sched.h>
#include <linux/delay.h>
#include <linux/export.h>
#include <linux/fs.h>
#include <linux/anon_inodes.h>
#include <linux/cpumask.h>
#include <linux/spinlock.h>
#include <linux/page-flags.h>
#include <linux/srcu.h>
#include <linux/miscdevice.h>
#include <linux/debugfs.h>

#include <asm/reg.h>
#include <asm/cputable.h>
#include <asm/cache.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/mmu_context.h>
#include <asm/lppaca.h>
#include <asm/processor.h>
#include <asm/cputhreads.h>
#include <asm/page.h>
#include <asm/hvcall.h>
#include <asm/switch_to.h>
#include <asm/smp.h>
#include <asm/dbell.h>
#include <linux/gfp.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/module.h>

#include "book3s.h"

#define CREATE_TRACE_POINTS
#include "trace_hv.h"

/* #define EXIT_DEBUG */
/* #define EXIT_DEBUG_SIMPLE */
/* #define EXIT_DEBUG_INT */

/* Used to indicate that a guest page fault needs to be handled */
#define RESUME_PAGE_FAULT	(RESUME_GUEST | RESUME_FLAG_ARCH1)

/* Used as a "null" value for timebase values */
#define TB_NIL	(~(u64)0)

static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);

#if defined(CONFIG_PPC_64K_PAGES)
#define MPP_BUFFER_ORDER	0
#elif defined(CONFIG_PPC_4K_PAGES)
#define MPP_BUFFER_ORDER	3
#endif


static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);

static bool kvmppc_ipi_thread(int cpu)
{
	/* On POWER8 for IPIs to threads in the same core, use msgsnd */
	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
		preempt_disable();
		if (cpu_first_thread_sibling(cpu) ==
		    cpu_first_thread_sibling(smp_processor_id())) {
			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
			msg |= cpu_thread_in_core(cpu);
			smp_mb();
			__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
			preempt_enable();
			return true;
		}
		preempt_enable();
	}

#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
	if (cpu >= 0 && cpu < nr_cpu_ids && paca[cpu].kvm_hstate.xics_phys) {
		xics_wake_cpu(cpu);
		return true;
	}
#endif

	return false;
}

static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
{
	int cpu = vcpu->cpu;
	wait_queue_head_t *wqp;

	wqp = kvm_arch_vcpu_wq(vcpu);
	if (waitqueue_active(wqp)) {
		wake_up_interruptible(wqp);
		++vcpu->stat.halt_wakeup;
	}

	if (kvmppc_ipi_thread(cpu + vcpu->arch.ptid))
		return;

	/* CPU points to the first thread of the core */
	if (cpu >= 0 && cpu < nr_cpu_ids && cpu_online(cpu))
		smp_send_reschedule(cpu);
}

/*
 * We use the vcpu_load/put functions to measure stolen time.
 * Stolen time is counted as time when either the vcpu is able to
 * run as part of a virtual core, but the task running the vcore
 * is preempted or sleeping, or when the vcpu needs something done
 * in the kernel by the task running the vcpu, but that task is
 * preempted or sleeping.  Those two things have to be counted
 * separately, since one of the vcpu tasks will take on the job
 * of running the core, and the other vcpu tasks in the vcore will
 * sleep waiting for it to do that, but that sleep shouldn't count
 * as stolen time.
 *
 * Hence we accumulate stolen time when the vcpu can run as part of
 * a vcore using vc->stolen_tb, and the stolen time when the vcpu
 * needs its task to do other things in the kernel (for example,
 * service a page fault) in busy_stolen.  We don't accumulate
 * stolen time for a vcore when it is inactive, or for a vcpu
 * when it is in state RUNNING or NOTREADY.  NOTREADY is a bit of
 * a misnomer; it means that the vcpu task is not executing in
 * the KVM_VCPU_RUN ioctl, i.e. it is in userspace or elsewhere in
 * the kernel.  We don't have any way of dividing up that time
 * between time that the vcpu is genuinely stopped, time that
 * the task is actively working on behalf of the vcpu, and time
 * that the task is preempted, so we don't count any of it as
 * stolen.
 *
 * Updates to busy_stolen are protected by arch.tbacct_lock;
 * updates to vc->stolen_tb are protected by the vcore->stoltb_lock
 * lock.  The stolen times are measured in units of timebase ticks.
 * (Note that the != TB_NIL checks below are purely defensive;
 * they should never fail.)
 */

static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
{
	struct kvmppc_vcore *vc = vcpu->arch.vcore;
	unsigned long flags;

	/*
	 * We can test vc->runner without taking the vcore lock,
	 * because only this task ever sets vc->runner to this
	 * vcpu, and once it is set to this vcpu, only this task
	 * ever sets it to NULL.
	 */
	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE) {
		spin_lock_irqsave(&vc->stoltb_lock, flags);
		if (vc->preempt_tb != TB_NIL) {
			vc->stolen_tb += mftb() - vc->preempt_tb;
			vc->preempt_tb = TB_NIL;
		}
		spin_unlock_irqrestore(&vc->stoltb_lock, flags);
	}
	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
	if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST &&
	    vcpu->arch.busy_preempt != TB_NIL) {
		vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt;
		vcpu->arch.busy_preempt = TB_NIL;
	}
	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
}

static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
{
	struct kvmppc_vcore *vc = vcpu->arch.vcore;
	unsigned long flags;

	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE) {
		spin_lock_irqsave(&vc->stoltb_lock, flags);
		vc->preempt_tb = mftb();
		spin_unlock_irqrestore(&vc->stoltb_lock, flags);
	}
	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
	if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST)
		vcpu->arch.busy_preempt = mftb();
	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
}

static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
{
	vcpu->arch.shregs.msr = msr;
	kvmppc_end_cede(vcpu);
}

void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
{
	vcpu->arch.pvr = pvr;
}

int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
{
	unsigned long pcr = 0;
	struct kvmppc_vcore *vc = vcpu->arch.vcore;

	if (arch_compat) {
		switch (arch_compat) {
		case PVR_ARCH_205:
			/*
			 * If an arch bit is set in PCR, all the defined
			 * higher-order arch bits also have to be set.
			 */
			pcr = PCR_ARCH_206 | PCR_ARCH_205;
			break;
		case PVR_ARCH_206:
		case PVR_ARCH_206p:
			pcr = PCR_ARCH_206;
			break;
		case PVR_ARCH_207:
			break;
		default:
			return -EINVAL;
		}

		if (!cpu_has_feature(CPU_FTR_ARCH_207S)) {
			/* POWER7 can't emulate POWER8 */
			if (!(pcr & PCR_ARCH_206))
				return -EINVAL;
			pcr &= ~PCR_ARCH_206;
		}
	}

	spin_lock(&vc->lock);
	vc->arch_compat = arch_compat;
	vc->pcr = pcr;
	spin_unlock(&vc->lock);

	return 0;
}

void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
{
	int r;

	pr_err("vcpu %p (%d):\n", vcpu, vcpu->vcpu_id);
	pr_err("pc  = %.16lx  msr = %.16llx  trap = %x\n",
	       vcpu->arch.pc, vcpu->arch.shregs.msr, vcpu->arch.trap);
	for (r = 0; r < 16; ++r)
		pr_err("r%2d = %.16lx  r%d = %.16lx\n",
		       r, kvmppc_get_gpr(vcpu, r),
		       r+16, kvmppc_get_gpr(vcpu, r+16));
	pr_err("ctr = %.16lx  lr  = %.16lx\n",
	       vcpu->arch.ctr, vcpu->arch.lr);
	pr_err("srr0 = %.16llx srr1 = %.16llx\n",
	       vcpu->arch.shregs.srr0, vcpu->arch.shregs.srr1);
	pr_err("sprg0 = %.16llx sprg1 = %.16llx\n",
	       vcpu->arch.shregs.sprg0, vcpu->arch.shregs.sprg1);
	pr_err("sprg2 = %.16llx sprg3 = %.16llx\n",
	       vcpu->arch.shregs.sprg2, vcpu->arch.shregs.sprg3);
	pr_err("cr = %.8x  xer = %.16lx  dsisr = %.8x\n",
	       vcpu->arch.cr, vcpu->arch.xer, vcpu->arch.shregs.dsisr);
	pr_err("dar = %.16llx\n", vcpu->arch.shregs.dar);
	pr_err("fault dar = %.16lx dsisr = %.8x\n",
	       vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
	pr_err("SLB (%d entries):\n", vcpu->arch.slb_max);
	for (r = 0; r < vcpu->arch.slb_max; ++r)
		pr_err("  ESID = %.16llx VSID = %.16llx\n",
		       vcpu->arch.slb[r].orige, vcpu->arch.slb[r].origv);
	pr_err("lpcr = %.16lx sdr1 = %.16lx last_inst = %.8x\n",
	       vcpu->arch.vcore->lpcr, vcpu->kvm->arch.sdr1,
	       vcpu->arch.last_inst);
}

struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
{
	int r;
	struct kvm_vcpu *v, *ret = NULL;

	mutex_lock(&kvm->lock);
	kvm_for_each_vcpu(r, v, kvm) {
		if (v->vcpu_id == id) {
			ret = v;
			break;
		}
	}
	mutex_unlock(&kvm->lock);
	return ret;
}

static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
{
	vpa->__old_status |= LPPACA_OLD_SHARED_PROC;
	vpa->yield_count = cpu_to_be32(1);
}

static int set_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *v,
		   unsigned long addr, unsigned long len)
{
	/* check address is cacheline aligned */
	if (addr & (L1_CACHE_BYTES - 1))
		return -EINVAL;
	spin_lock(&vcpu->arch.vpa_update_lock);
	if (v->next_gpa != addr || v->len != len) {
		v->next_gpa = addr;
		v->len = addr ? len : 0;
		v->update_pending = 1;
	}
	spin_unlock(&vcpu->arch.vpa_update_lock);
	return 0;
}

/* Length for a per-processor buffer is passed in at offset 4 in the buffer */
struct reg_vpa {
	u32 dummy;
	union {
		__be16 hword;
		__be32 word;
	} length;
};

static int vpa_is_registered(struct kvmppc_vpa *vpap)
{
	if (vpap->update_pending)
		return vpap->next_gpa != 0;
	return vpap->pinned_addr != NULL;
}

static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
				       unsigned long flags,
				       unsigned long vcpuid, unsigned long vpa)
{
	struct kvm *kvm = vcpu->kvm;
	unsigned long len, nb;
	void *va;
	struct kvm_vcpu *tvcpu;
	int err;
	int subfunc;
	struct kvmppc_vpa *vpap;

	tvcpu = kvmppc_find_vcpu(kvm, vcpuid);
	if (!tvcpu)
		return H_PARAMETER;

	subfunc = (flags >> H_VPA_FUNC_SHIFT) & H_VPA_FUNC_MASK;
	if (subfunc == H_VPA_REG_VPA || subfunc == H_VPA_REG_DTL ||
	    subfunc == H_VPA_REG_SLB) {
		/* Registering new area - address must be cache-line aligned */
		if ((vpa & (L1_CACHE_BYTES - 1)) || !vpa)
			return H_PARAMETER;

		/* convert logical addr to kernel addr and read length */
		va = kvmppc_pin_guest_page(kvm, vpa, &nb);
		if (va == NULL)
			return H_PARAMETER;
		if (subfunc == H_VPA_REG_VPA)
			len = be16_to_cpu(((struct reg_vpa *)va)->length.hword);
		else
			len = be32_to_cpu(((struct reg_vpa *)va)->length.word);
		kvmppc_unpin_guest_page(kvm, va, vpa, false);

		/* Check length */
		if (len > nb || len < sizeof(struct reg_vpa))
			return H_PARAMETER;
	} else {
		vpa = 0;
		len = 0;
	}

	err = H_PARAMETER;
	vpap = NULL;
	spin_lock(&tvcpu->arch.vpa_update_lock);

	switch (subfunc) {
	case H_VPA_REG_VPA:		/* register VPA */
		if (len < sizeof(struct lppaca))
			break;
		vpap = &tvcpu->arch.vpa;
		err = 0;
		break;

	case H_VPA_REG_DTL:		/* register DTL */
		if (len < sizeof(struct dtl_entry))
			break;
		len -= len % sizeof(struct dtl_entry);

		/* Check that they have previously registered a VPA */
		err = H_RESOURCE;
		if (!vpa_is_registered(&tvcpu->arch.vpa))
			break;

		vpap = &tvcpu->arch.dtl;
		err = 0;
		break;

	case H_VPA_REG_SLB:		/* register SLB shadow buffer */
		/* Check that they have previously registered a VPA */
		err = H_RESOURCE;
		if (!vpa_is_registered(&tvcpu->arch.vpa))
			break;

		vpap = &tvcpu->arch.slb_shadow;
		err = 0;
		break;

	case H_VPA_DEREG_VPA:		/* deregister VPA */
		/* Check they don't still have a DTL or SLB buf registered */
		err = H_RESOURCE;
		if (vpa_is_registered(&tvcpu->arch.dtl) ||
		    vpa_is_registered(&tvcpu->arch.slb_shadow))
			break;

		vpap = &tvcpu->arch.vpa;
		err = 0;
		break;

	case H_VPA_DEREG_DTL:		/* deregister DTL */
		vpap = &tvcpu->arch.dtl;
		err = 0;
		break;

	case H_VPA_DEREG_SLB:		/* deregister SLB shadow buffer */
		vpap = &tvcpu->arch.slb_shadow;
		err = 0;
		break;
	}

	if (vpap) {
		vpap->next_gpa = vpa;
		vpap->len = len;
		vpap->update_pending = 1;
	}

	spin_unlock(&tvcpu->arch.vpa_update_lock);

	return err;
}

static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
{
	struct kvm *kvm = vcpu->kvm;
	void *va;
	unsigned long nb;
	unsigned long gpa;

	/*
	 * We need to pin the page pointed to by vpap->next_gpa,
	 * but we can't call kvmppc_pin_guest_page under the lock
	 * as it does get_user_pages() and down_read().  So we
	 * have to drop the lock, pin the page, then get the lock
	 * again and check that a new area didn't get registered
	 * in the meantime.
	 */
	for (;;) {
		gpa = vpap->next_gpa;
		spin_unlock(&vcpu->arch.vpa_update_lock);
		va = NULL;
		nb = 0;
		if (gpa)
			va = kvmppc_pin_guest_page(kvm, gpa, &nb);
		spin_lock(&vcpu->arch.vpa_update_lock);
		if (gpa == vpap->next_gpa)
			break;
		/* sigh... unpin that one and try again */
		if (va)
			kvmppc_unpin_guest_page(kvm, va, gpa, false);
	}

	vpap->update_pending = 0;
	if (va && nb < vpap->len) {
		/*
		 * If it's now too short, it must be that userspace
		 * has changed the mappings underlying guest memory,
		 * so unregister the region.
		 */
		kvmppc_unpin_guest_page(kvm, va, gpa, false);
		va = NULL;
	}
	if (vpap->pinned_addr)
		kvmppc_unpin_guest_page(kvm, vpap->pinned_addr, vpap->gpa,
					vpap->dirty);
	vpap->gpa = gpa;
	vpap->pinned_addr = va;
	vpap->dirty = false;
	if (va)
		vpap->pinned_end = va + vpap->len;
}

static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
{
	if (!(vcpu->arch.vpa.update_pending ||
	      vcpu->arch.slb_shadow.update_pending ||
	      vcpu->arch.dtl.update_pending))
		return;

	spin_lock(&vcpu->arch.vpa_update_lock);
	if (vcpu->arch.vpa.update_pending) {
		kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
		if (vcpu->arch.vpa.pinned_addr)
			init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
	}
	if (vcpu->arch.dtl.update_pending) {
		kvmppc_update_vpa(vcpu, &vcpu->arch.dtl);
		vcpu->arch.dtl_ptr = vcpu->arch.dtl.pinned_addr;
		vcpu->arch.dtl_index = 0;
	}
	if (vcpu->arch.slb_shadow.update_pending)
		kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow);
	spin_unlock(&vcpu->arch.vpa_update_lock);
}

/*
 * Return the accumulated stolen time for the vcore up until `now'.
 * The caller should hold the vcore lock.
 */
static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now)
{
	u64 p;
	unsigned long flags;

	spin_lock_irqsave(&vc->stoltb_lock, flags);
	p = vc->stolen_tb;
	if (vc->vcore_state != VCORE_INACTIVE &&
	    vc->preempt_tb != TB_NIL)
		p += now - vc->preempt_tb;
	spin_unlock_irqrestore(&vc->stoltb_lock, flags);
	return p;
}

static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
				    struct kvmppc_vcore *vc)
{
	struct dtl_entry *dt;
	struct lppaca *vpa;
	unsigned long stolen;
	unsigned long core_stolen;
	u64 now;

	dt = vcpu->arch.dtl_ptr;
	vpa = vcpu->arch.vpa.pinned_addr;
	now = mftb();
	core_stolen = vcore_stolen_time(vc, now);
	stolen = core_stolen - vcpu->arch.stolen_logged;
	vcpu->arch.stolen_logged = core_stolen;
	spin_lock_irq(&vcpu->arch.tbacct_lock);
	stolen += vcpu->arch.busy_stolen;
	vcpu->arch.busy_stolen = 0;
	spin_unlock_irq(&vcpu->arch.tbacct_lock);
	if (!dt || !vpa)
		return;
	memset(dt, 0, sizeof(struct dtl_entry));
	dt->dispatch_reason = 7;
	dt->processor_id = cpu_to_be16(vc->pcpu + vcpu->arch.ptid);
	dt->timebase = cpu_to_be64(now + vc->tb_offset);
	dt->enqueue_to_dispatch_time = cpu_to_be32(stolen);
	dt->srr0 = cpu_to_be64(kvmppc_get_pc(vcpu));
	dt->srr1 = cpu_to_be64(vcpu->arch.shregs.msr);
	++dt;
	if (dt == vcpu->arch.dtl.pinned_end)
		dt = vcpu->arch.dtl.pinned_addr;
	vcpu->arch.dtl_ptr = dt;
	/* order writing *dt vs. writing vpa->dtl_idx */
	smp_wmb();
	vpa->dtl_idx = cpu_to_be64(++vcpu->arch.dtl_index);
	vcpu->arch.dtl.dirty = true;
}

static bool kvmppc_power8_compatible(struct kvm_vcpu *vcpu)
{
	if (vcpu->arch.vcore->arch_compat >= PVR_ARCH_207)
		return true;
	if ((!vcpu->arch.vcore->arch_compat) &&
	    cpu_has_feature(CPU_FTR_ARCH_207S))
		return true;
	return false;
}

static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
			     unsigned long resource, unsigned long value1,
			     unsigned long value2)
{
	switch (resource) {
	case H_SET_MODE_RESOURCE_SET_CIABR:
		if (!kvmppc_power8_compatible(vcpu))
			return H_P2;
		if (value2)
			return H_P4;
		if (mflags)
			return H_UNSUPPORTED_FLAG_START;
		/* Guests can't breakpoint the hypervisor */
		if ((value1 & CIABR_PRIV) == CIABR_PRIV_HYPER)
			return H_P3;
		vcpu->arch.ciabr  = value1;
		return H_SUCCESS;
	case H_SET_MODE_RESOURCE_SET_DAWR:
		if (!kvmppc_power8_compatible(vcpu))
			return H_P2;
		if (mflags)
			return H_UNSUPPORTED_FLAG_START;
		if (value2 & DABRX_HYP)
			return H_P4;
		vcpu->arch.dawr  = value1;
		vcpu->arch.dawrx = value2;
		return H_SUCCESS;
	default:
		return H_TOO_HARD;
	}
}

static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target)
{
	struct kvmppc_vcore *vcore = target->arch.vcore;

	/*
	 * We expect to have been called by the real mode handler
	 * (kvmppc_rm_h_confer()) which would have directly returned
	 * H_SUCCESS if the source vcore wasn't idle (e.g. if it may
	 * have useful work to do and should not confer) so we don't
	 * recheck that here.
	 */

	spin_lock(&vcore->lock);
	if (target->arch.state == KVMPPC_VCPU_RUNNABLE &&
	    vcore->vcore_state != VCORE_INACTIVE)
		target = vcore->runner;
	spin_unlock(&vcore->lock);

	return kvm_vcpu_yield_to(target);
}

static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu)
{
	int yield_count = 0;
	struct lppaca *lppaca;

	spin_lock(&vcpu->arch.vpa_update_lock);
	lppaca = (struct lppaca *)vcpu->arch.vpa.pinned_addr;
	if (lppaca)
		yield_count = be32_to_cpu(lppaca->yield_count);
	spin_unlock(&vcpu->arch.vpa_update_lock);
	return yield_count;
}

int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
{
	unsigned long req = kvmppc_get_gpr(vcpu, 3);
	unsigned long target, ret = H_SUCCESS;
	int yield_count;
	struct kvm_vcpu *tvcpu;
	int idx, rc;

	if (req <= MAX_HCALL_OPCODE &&
	    !test_bit(req/4, vcpu->kvm->arch.enabled_hcalls))
		return RESUME_HOST;

	switch (req) {
	case H_CEDE:
		break;
	case H_PROD:
		target = kvmppc_get_gpr(vcpu, 4);
		tvcpu = kvmppc_find_vcpu(vcpu->kvm, target);
		if (!tvcpu) {
			ret = H_PARAMETER;
			break;
		}
		tvcpu->arch.prodded = 1;
		smp_mb();
		if (vcpu->arch.ceded) {
			if (waitqueue_active(&vcpu->wq)) {
				wake_up_interruptible(&vcpu->wq);
				vcpu->stat.halt_wakeup++;
			}
		}
		break;
	case H_CONFER:
		target = kvmppc_get_gpr(vcpu, 4);
		if (target == -1)
			break;
		tvcpu = kvmppc_find_vcpu(vcpu->kvm, target);
		if (!tvcpu) {
			ret = H_PARAMETER;
			break;
		}
		yield_count = kvmppc_get_gpr(vcpu, 5);
		if (kvmppc_get_yield_count(tvcpu) != yield_count)
			break;
		kvm_arch_vcpu_yield_to(tvcpu);
		break;
	case H_REGISTER_VPA:
		ret = do_h_register_vpa(vcpu, kvmppc_get_gpr(vcpu, 4),
					kvmppc_get_gpr(vcpu, 5),
					kvmppc_get_gpr(vcpu, 6));
		break;
	case H_RTAS:
		if (list_empty(&vcpu->kvm->arch.rtas_tokens))
			return RESUME_HOST;

		idx = srcu_read_lock(&vcpu->kvm->srcu);
		rc = kvmppc_rtas_hcall(vcpu);
		srcu_read_unlock(&vcpu->kvm->srcu, idx);

		if (rc == -ENOENT)
			return RESUME_HOST;
		else if (rc == 0)
			break;

		/* Send the error out to userspace via KVM_RUN */
		return rc;
	case H_LOGICAL_CI_LOAD:
		ret = kvmppc_h_logical_ci_load(vcpu);
		if (ret == H_TOO_HARD)
			return RESUME_HOST;
		break;
	case H_LOGICAL_CI_STORE:
		ret = kvmppc_h_logical_ci_store(vcpu);
		if (ret == H_TOO_HARD)
			return RESUME_HOST;
		break;
	case H_SET_MODE:
		ret = kvmppc_h_set_mode(vcpu, kvmppc_get_gpr(vcpu, 4),
					kvmppc_get_gpr(vcpu, 5),
					kvmppc_get_gpr(vcpu, 6),
					kvmppc_get_gpr(vcpu, 7));
		if (ret == H_TOO_HARD)
			return RESUME_HOST;
		break;
	case H_XIRR:
	case H_CPPR:
	case H_EOI:
	case H_IPI:
	case H_IPOLL:
	case H_XIRR_X:
		if (kvmppc_xics_enabled(vcpu)) {
			ret = kvmppc_xics_hcall(vcpu, req);
			break;
		} /* fallthrough */
	default:
		return RESUME_HOST;
	}
	kvmppc_set_gpr(vcpu, 3, ret);
	vcpu->arch.hcall_needed = 0;
	return RESUME_GUEST;
}

static int kvmppc_hcall_impl_hv(unsigned long cmd)
{
	switch (cmd) {
	case H_CEDE:
	case H_PROD:
	case H_CONFER:
	case H_REGISTER_VPA:
	case H_SET_MODE:
	case H_LOGICAL_CI_LOAD:
	case H_LOGICAL_CI_STORE:
#ifdef CONFIG_KVM_XICS
	case H_XIRR:
	case H_CPPR:
	case H_EOI:
	case H_IPI:
	case H_IPOLL:
	case H_XIRR_X:
#endif
		return 1;
	}

	/* See if it's in the real-mode table */
	return kvmppc_hcall_impl_hv_realmode(cmd);
}

static int kvmppc_emulate_debug_inst(struct kvm_run *run,
					struct kvm_vcpu *vcpu)
{
	u32 last_inst;

	if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst) !=
					EMULATE_DONE) {
		/*
		 * Fetch failed, so return to guest and
		 * try executing it again.
		 */
		return RESUME_GUEST;
	}

	if (last_inst == KVMPPC_INST_SW_BREAKPOINT) {
		run->exit_reason = KVM_EXIT_DEBUG;
		run->debug.arch.address = kvmppc_get_pc(vcpu);
		return RESUME_HOST;
	} else {
		kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
		return RESUME_GUEST;
	}
}

static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
				 struct task_struct *tsk)
{
	int r = RESUME_HOST;

	vcpu->stat.sum_exits++;

	run->exit_reason = KVM_EXIT_UNKNOWN;
	run->ready_for_interrupt_injection = 1;
	switch (vcpu->arch.trap) {
	/* We're good on these - the host merely wanted to get our attention */
	case BOOK3S_INTERRUPT_HV_DECREMENTER:
		vcpu->stat.dec_exits++;
		r = RESUME_GUEST;
		break;
	case BOOK3S_INTERRUPT_EXTERNAL:
	case BOOK3S_INTERRUPT_H_DOORBELL:
		vcpu->stat.ext_intr_exits++;
		r = RESUME_GUEST;
		break;
	/* HMI is hypervisor interrupt and host has handled it. Resume guest.*/
	case BOOK3S_INTERRUPT_HMI:
	case BOOK3S_INTERRUPT_PERFMON:
		r = RESUME_GUEST;
		break;
	case BOOK3S_INTERRUPT_MACHINE_CHECK:
		/*
		 * Deliver a machine check interrupt to the guest.
		 * We have to do this, even if the host has handled the
		 * machine check, because machine checks use SRR0/1 and
		 * the interrupt might have trashed guest state in them.
		 */
		kvmppc_book3s_queue_irqprio(vcpu,
					    BOOK3S_INTERRUPT_MACHINE_CHECK);
		r = RESUME_GUEST;
		break;
	case BOOK3S_INTERRUPT_PROGRAM:
	{
		ulong flags;
		/*
		 * Normally program interrupts are delivered directly
		 * to the guest by the hardware, but we can get here
		 * as a result of a hypervisor emulation interrupt
		 * (e40) getting turned into a 700 by BML RTAS.
		 */
		flags = vcpu->arch.shregs.msr & 0x1f0000ull;
		kvmppc_core_queue_program(vcpu, flags);
		r = RESUME_GUEST;
		break;
	}
	case BOOK3S_INTERRUPT_SYSCALL:
	{
		/* hcall - punt to userspace */
		int i;

		/* hypercall with MSR_PR has already been handled in rmode,
		 * and never reaches here.
		 */

		run->papr_hcall.nr = kvmppc_get_gpr(vcpu, 3);
		for (i = 0; i < 9; ++i)
			run->papr_hcall.args[i] = kvmppc_get_gpr(vcpu, 4 + i);
		run->exit_reason = KVM_EXIT_PAPR_HCALL;
		vcpu->arch.hcall_needed = 1;
		r = RESUME_HOST;
		break;
	}
	/*
	 * We get these next two if the guest accesses a page which it thinks
	 * it has mapped but which is not actually present, either because
	 * it is for an emulated I/O device or because the corresonding
	 * host page has been paged out.  Any other HDSI/HISI interrupts
	 * have been handled already.
	 */
	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
		r = RESUME_PAGE_FAULT;
		break;
	case BOOK3S_INTERRUPT_H_INST_STORAGE:
		vcpu->arch.fault_dar = kvmppc_get_pc(vcpu);
		vcpu->arch.fault_dsisr = 0;
		r = RESUME_PAGE_FAULT;
		break;
	/*
	 * This occurs if the guest executes an illegal instruction.
	 * If the guest debug is disabled, generate a program interrupt
	 * to the guest. If guest debug is enabled, we need to check
	 * whether the instruction is a software breakpoint instruction.
	 * Accordingly return to Guest or Host.
	 */
	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
		if (vcpu->arch.emul_inst != KVM_INST_FETCH_FAILED)
			vcpu->arch.last_inst = kvmppc_need_byteswap(vcpu) ?
				swab32(vcpu->arch.emul_inst) :
				vcpu->arch.emul_inst;
		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) {
			r = kvmppc_emulate_debug_inst(run, vcpu);
		} else {
			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
			r = RESUME_GUEST;
		}
		break;
	/*
	 * This occurs if the guest (kernel or userspace), does something that
	 * is prohibited by HFSCR.  We just generate a program interrupt to
	 * the guest.
	 */
	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
		kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
		r = RESUME_GUEST;
		break;
	default:
		kvmppc_dump_regs(vcpu);
		printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
			vcpu->arch.trap, kvmppc_get_pc(vcpu),
			vcpu->arch.shregs.msr);
		run->hw.hardware_exit_reason = vcpu->arch.trap;
		r = RESUME_HOST;
		break;
	}

	return r;
}

static int kvm_arch_vcpu_ioctl_get_sregs_hv(struct kvm_vcpu *vcpu,
					    struct kvm_sregs *sregs)
{
	int i;

	memset(sregs, 0, sizeof(struct kvm_sregs));
	sregs->pvr = vcpu->arch.pvr;
	for (i = 0; i < vcpu->arch.slb_max; i++) {
		sregs->u.s.ppc64.slb[i].slbe = vcpu->arch.slb[i].orige;
		sregs->u.s.ppc64.slb[i].slbv = vcpu->arch.slb[i].origv;
	}

	return 0;
}

static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu,
					    struct kvm_sregs *sregs)
{
	int i, j;

	/* Only accept the same PVR as the host's, since we can't spoof it */
	if (sregs->pvr != vcpu->arch.pvr)
		return -EINVAL;

	j = 0;
	for (i = 0; i < vcpu->arch.slb_nr; i++) {
		if (sregs->u.s.ppc64.slb[i].slbe & SLB_ESID_V) {
			vcpu->arch.slb[j].orige = sregs->u.s.ppc64.slb[i].slbe;
			vcpu->arch.slb[j].origv = sregs->u.s.ppc64.slb[i].slbv;
			++j;
		}
	}
	vcpu->arch.slb_max = j;

	return 0;
}

static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
		bool preserve_top32)
{
	struct kvm *kvm = vcpu->kvm;
	struct kvmppc_vcore *vc = vcpu->arch.vcore;
	u64 mask;

	mutex_lock(&kvm->lock);
	spin_lock(&vc->lock);
	/*
	 * If ILE (interrupt little-endian) has changed, update the
	 * MSR_LE bit in the intr_msr for each vcpu in this vcore.
	 */
	if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) {
		struct kvm_vcpu *vcpu;
		int i;

		kvm_for_each_vcpu(i, vcpu, kvm) {
			if (vcpu->arch.vcore != vc)
				continue;
			if (new_lpcr & LPCR_ILE)
				vcpu->arch.intr_msr |= MSR_LE;
			else
				vcpu->arch.intr_msr &= ~MSR_LE;
		}
	}

	/*
	 * Userspace can only modify DPFD (default prefetch depth),
	 * ILE (interrupt little-endian) and TC (translation control).
	 * On POWER8 userspace can also modify AIL (alt. interrupt loc.)
	 */
	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC;
	if (cpu_has_feature(CPU_FTR_ARCH_207S))
		mask |= LPCR_AIL;

	/* Broken 32-bit version of LPCR must not clear top bits */
	if (preserve_top32)
		mask &= 0xFFFFFFFF;
	vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
	spin_unlock(&vc->lock);
	mutex_unlock(&kvm->lock);
}

static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
				 union kvmppc_one_reg *val)
{
	int r = 0;
	long int i;

	switch (id) {
	case KVM_REG_PPC_DEBUG_INST:
		*val = get_reg_val(id, KVMPPC_INST_SW_BREAKPOINT);
		break;
	case KVM_REG_PPC_HIOR:
		*val = get_reg_val(id, 0);
		break;
	case KVM_REG_PPC_DABR:
		*val = get_reg_val(id, vcpu->arch.dabr);
		break;
	case KVM_REG_PPC_DABRX:
		*val = get_reg_val(id, vcpu->arch.dabrx);
		break;
	case KVM_REG_PPC_DSCR:
		*val = get_reg_val(id, vcpu->arch.dscr);
		break;
	case KVM_REG_PPC_PURR:
		*val = get_reg_val(id, vcpu->arch.purr);
		break;
	case KVM_REG_PPC_SPURR:
		*val = get_reg_val(id, vcpu->arch.spurr);
		break;
	case KVM_REG_PPC_AMR:
		*val = get_reg_val(id, vcpu->arch.amr);
		break;
	case KVM_REG_PPC_UAMOR:
		*val = get_reg_val(id, vcpu->arch.uamor);
		break;
	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
		i = id - KVM_REG_PPC_MMCR0;
		*val = get_reg_val(id, vcpu->arch.mmcr[i]);
		break;
	case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
		i = id - KVM_REG_PPC_PMC1;
		*val = get_reg_val(id, vcpu->arch.pmc[i]);
		break;
	case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
		i = id - KVM_REG_PPC_SPMC1;
		*val = get_reg_val(id, vcpu->arch.spmc[i]);
		break;
	case KVM_REG_PPC_SIAR:
		*val = get_reg_val(id, vcpu->arch.siar);
		break;
	case KVM_REG_PPC_SDAR:
		*val = get_reg_val(id, vcpu->arch.sdar);
		break;
	case KVM_REG_PPC_SIER:
		*val = get_reg_val(id, vcpu->arch.sier);
		break;
	case KVM_REG_PPC_IAMR:
		*val = get_reg_val(id, vcpu->arch.iamr);
		break;
	case KVM_REG_PPC_PSPB:
		*val = get_reg_val(id, vcpu->arch.pspb);
		break;
	case KVM_REG_PPC_DPDES:
		*val = get_reg_val(id, vcpu->arch.vcore->dpdes);
		break;
	case KVM_REG_PPC_DAWR:
		*val = get_reg_val(id, vcpu->arch.dawr);
		break;
	case KVM_REG_PPC_DAWRX:
		*val = get_reg_val(id, vcpu->arch.dawrx);
		break;
	case KVM_REG_PPC_CIABR:
		*val = get_reg_val(id, vcpu->arch.ciabr);
		break;
	case KVM_REG_PPC_CSIGR:
		*val = get_reg_val(id, vcpu->arch.csigr);
		break;
	case KVM_REG_PPC_TACR:
		*val = get_reg_val(id, vcpu->arch.tacr);
		break;
	case KVM_REG_PPC_TCSCR:
		*val = get_reg_val(id, vcpu->arch.tcscr);
		break;
	case KVM_REG_PPC_PID:
		*val = get_reg_val(id, vcpu->arch.pid);
		break;
	case KVM_REG_PPC_ACOP:
		*val = get_reg_val(id, vcpu->arch.acop);
		break;
	case KVM_REG_PPC_WORT:
		*val = get_reg_val(id, vcpu->arch.wort);
		break;
	case KVM_REG_PPC_VPA_ADDR:
		spin_lock(&vcpu->arch.vpa_update_lock);
		*val = get_reg_val(id, vcpu->arch.vpa.next_gpa);
		spin_unlock(&vcpu->arch.vpa_update_lock);
		break;
	case KVM_REG_PPC_VPA_SLB:
		spin_lock(&vcpu->arch.vpa_update_lock);
		val->vpaval.addr = vcpu->arch.slb_shadow.next_gpa;
		val->vpaval.length = vcpu->arch.slb_shadow.len;
		spin_unlock(&vcpu->arch.vpa_update_lock);
		break;
	case KVM_REG_PPC_VPA_DTL:
		spin_lock(&vcpu->arch.vpa_update_lock);
		val->vpaval.addr = vcpu->arch.dtl.next_gpa;
		val->vpaval.length = vcpu->arch.dtl.len;
		spin_unlock(&vcpu->arch.vpa_update_lock);
		break;
	case KVM_REG_PPC_TB_OFFSET:
		*val = get_reg_val(id, vcpu->arch.vcore->tb_offset);
		break;
	case KVM_REG_PPC_LPCR:
	case KVM_REG_PPC_LPCR_64:
		*val = get_reg_val(id, vcpu->arch.vcore->lpcr);
		break;
	case KVM_REG_PPC_PPR:
		*val = get_reg_val(id, vcpu->arch.ppr);
		break;
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
	case KVM_REG_PPC_TFHAR:
		*val = get_reg_val(id, vcpu->arch.tfhar);
		break;
	case KVM_REG_PPC_TFIAR:
		*val = get_reg_val(id, vcpu->arch.tfiar);
		break;
	case KVM_REG_PPC_TEXASR:
		*val = get_reg_val(id, vcpu->arch.texasr);
		break;
	case KVM_REG_PPC_TM_GPR0 ... KVM_REG_PPC_TM_GPR31:
		i = id - KVM_REG_PPC_TM_GPR0;
		*val = get_reg_val(id, vcpu->arch.gpr_tm[i]);
		break;
	case KVM_REG_PPC_TM_VSR0 ... KVM_REG_PPC_TM_VSR63:
	{
		int j;
		i = id - KVM_REG_PPC_TM_VSR0;
		if (i < 32)
			for (j = 0; j < TS_FPRWIDTH; j++)
				val->vsxval[j] = vcpu->arch.fp_tm.fpr[i][j];
		else {
			if (cpu_has_feature(CPU_FTR_ALTIVEC))
				val->vval = vcpu->arch.vr_tm.vr[i-32];
			else
				r = -ENXIO;
		}
		break;
	}
	case KVM_REG_PPC_TM_CR:
		*val = get_reg_val(id, vcpu->arch.cr_tm);
		break;
	case KVM_REG_PPC_TM_LR:
		*val = get_reg_val(id, vcpu->arch.lr_tm);
		break;
	case KVM_REG_PPC_TM_CTR:
		*val = get_reg_val(id, vcpu->arch.ctr_tm);
		break;
	case KVM_REG_PPC_TM_FPSCR:
		*val = get_reg_val(id, vcpu->arch.fp_tm.fpscr);
		break;
	case KVM_REG_PPC_TM_AMR:
		*val = get_reg_val(id, vcpu->arch.amr_tm);
		break;
	case KVM_REG_PPC_TM_PPR:
		*val = get_reg_val(id, vcpu->arch.ppr_tm);
		break;
	case KVM_REG_PPC_TM_VRSAVE:
		*val = get_reg_val(id, vcpu->arch.vrsave_tm);
		break;
	case KVM_REG_PPC_TM_VSCR:
		if (cpu_has_feature(CPU_FTR_ALTIVEC))
			*val = get_reg_val(id, vcpu->arch.vr_tm.vscr.u[3]);
		else
			r = -ENXIO;
		break;
	case KVM_REG_PPC_TM_DSCR:
		*val = get_reg_val(id, vcpu->arch.dscr_tm);
		break;
	case KVM_REG_PPC_TM_TAR:
		*val = get_reg_val(id, vcpu->arch.tar_tm);
		break;
#endif
	case KVM_REG_PPC_ARCH_COMPAT:
		*val = get_reg_val(id, vcpu->arch.vcore->arch_compat);
		break;
	default:
		r = -EINVAL;
		break;
	}

	return r;
}

static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
				 union kvmppc_one_reg *val)
{
	int r = 0;
	long int i;
	unsigned long addr, len;

	switch (id) {
	case KVM_REG_PPC_HIOR:
		/* Only allow this to be set to zero */
		if (set_reg_val(id, *val))
			r = -EINVAL;
		break;
	case KVM_REG_PPC_DABR:
		vcpu->arch.dabr = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_DABRX:
		vcpu->arch.dabrx = set_reg_val(id, *val) & ~DABRX_HYP;
		break;
	case KVM_REG_PPC_DSCR:
		vcpu->arch.dscr = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_PURR:
		vcpu->arch.purr = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_SPURR:
		vcpu->arch.spurr = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_AMR:
		vcpu->arch.amr = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_UAMOR:
		vcpu->arch.uamor = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
		i = id - KVM_REG_PPC_MMCR0;
		vcpu->arch.mmcr[i] = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
		i = id - KVM_REG_PPC_PMC1;
		vcpu->arch.pmc[i] = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
		i = id - KVM_REG_PPC_SPMC1;
		vcpu->arch.spmc[i] = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_SIAR:
		vcpu->arch.siar = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_SDAR:
		vcpu->arch.sdar = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_SIER:
		vcpu->arch.sier = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_IAMR:
		vcpu->arch.iamr = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_PSPB:
		vcpu->arch.pspb = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_DPDES:
		vcpu->arch.vcore->dpdes = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_DAWR:
		vcpu->arch.dawr = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_DAWRX:
		vcpu->arch.dawrx = set_reg_val(id, *val) & ~DAWRX_HYP;
		break;
	case KVM_REG_PPC_CIABR:
		vcpu->arch.ciabr = set_reg_val(id, *val);
		/* Don't allow setting breakpoints in hypervisor code */
		if ((vcpu->arch.ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
			vcpu->arch.ciabr &= ~CIABR_PRIV;	/* disable */
		break;
	case KVM_REG_PPC_CSIGR:
		vcpu->arch.csigr = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_TACR:
		vcpu->arch.tacr = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_TCSCR:
		vcpu->arch.tcscr = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_PID:
		vcpu->arch.pid = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_ACOP:
		vcpu->arch.acop = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_WORT:
		vcpu->arch.wort = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_VPA_ADDR:
		addr = set_reg_val(id, *val);
		r = -EINVAL;
		if (!addr && (vcpu->arch.slb_shadow.next_gpa ||
			      vcpu->arch.dtl.next_gpa))
			break;
		r = set_vpa(vcpu, &vcpu->arch.vpa, addr, sizeof(struct lppaca));
		break;
	case KVM_REG_PPC_VPA_SLB:
		addr = val->vpaval.addr;
		len = val->vpaval.length;
		r = -EINVAL;
		if (addr && !vcpu->arch.vpa.next_gpa)
			break;
		r = set_vpa(vcpu, &vcpu->arch.slb_shadow, addr, len);
		break;
	case KVM_REG_PPC_VPA_DTL:
		addr = val->vpaval.addr;
		len = val->vpaval.length;
		r = -EINVAL;
		if (addr && (len < sizeof(struct dtl_entry) ||
			     !vcpu->arch.vpa.next_gpa))
			break;
		len -= len % sizeof(struct dtl_entry);
		r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len);
		break;
	case KVM_REG_PPC_TB_OFFSET:
		/* round up to multiple of 2^24 */
		vcpu->arch.vcore->tb_offset =
			ALIGN(set_reg_val(id, *val), 1UL << 24);
		break;
	case KVM_REG_PPC_LPCR:
		kvmppc_set_lpcr(vcpu, set_reg_val(id, *val), true);
		break;
	case KVM_REG_PPC_LPCR_64:
		kvmppc_set_lpcr(vcpu, set_reg_val(id, *val), false);
		break;
	case KVM_REG_PPC_PPR:
		vcpu->arch.ppr = set_reg_val(id, *val);
		break;
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
	case KVM_REG_PPC_TFHAR:
		vcpu->arch.tfhar = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_TFIAR:
		vcpu->arch.tfiar = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_TEXASR:
		vcpu->arch.texasr = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_TM_GPR0 ... KVM_REG_PPC_TM_GPR31:
		i = id - KVM_REG_PPC_TM_GPR0;
		vcpu->arch.gpr_tm[i] = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_TM_VSR0 ... KVM_REG_PPC_TM_VSR63:
	{
		int j;
		i = id - KVM_REG_PPC_TM_VSR0;
		if (i < 32)
			for (j = 0; j < TS_FPRWIDTH; j++)
				vcpu->arch.fp_tm.fpr[i][j] = val->vsxval[j];
		else
			if (cpu_has_feature(CPU_FTR_ALTIVEC))
				vcpu->arch.vr_tm.vr[i-32] = val->vval;
			else
				r = -ENXIO;
		break;
	}
	case KVM_REG_PPC_TM_CR:
		vcpu->arch.cr_tm = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_TM_LR:
		vcpu->arch.lr_tm = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_TM_CTR:
		vcpu->arch.ctr_tm = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_TM_FPSCR:
		vcpu->arch.fp_tm.fpscr = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_TM_AMR:
		vcpu->arch.amr_tm = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_TM_PPR:
		vcpu->arch.ppr_tm = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_TM_VRSAVE:
		vcpu->arch.vrsave_tm = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_TM_VSCR:
		if (cpu_has_feature(CPU_FTR_ALTIVEC))
			vcpu->arch.vr.vscr.u[3] = set_reg_val(id, *val);
		else
			r = - ENXIO;
		break;
	case KVM_REG_PPC_TM_DSCR:
		vcpu->arch.dscr_tm = set_reg_val(id, *val);
		break;
	case KVM_REG_PPC_TM_TAR:
		vcpu->arch.tar_tm = set_reg_val(id, *val);
		break;
#endif
	case KVM_REG_PPC_ARCH_COMPAT:
		r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val));
		break;
	default:
		r = -EINVAL;
		break;
	}

	return r;
}

static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
{
	struct kvmppc_vcore *vcore;

	vcore = kzalloc(sizeof(struct kvmppc_vcore), GFP_KERNEL);

	if (vcore == NULL)
		return NULL;

	INIT_LIST_HEAD(&vcore->runnable_threads);
	spin_lock_init(&vcore->lock);
	spin_lock_init(&vcore->stoltb_lock);
	init_waitqueue_head(&vcore->wq);
	vcore->preempt_tb = TB_NIL;
	vcore->lpcr = kvm->arch.lpcr;
	vcore->first_vcpuid = core * threads_per_subcore;
	vcore->kvm = kvm;

	vcore->mpp_buffer_is_valid = false;

	if (cpu_has_feature(CPU_FTR_ARCH_207S))
		vcore->mpp_buffer = (void *)__get_free_pages(
			GFP_KERNEL|__GFP_ZERO,
			MPP_BUFFER_ORDER);

	return vcore;
}

#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
static struct debugfs_timings_element {
	const char *name;
	size_t offset;
} timings[] = {
	{"rm_entry",	offsetof(struct kvm_vcpu, arch.rm_entry)},
	{"rm_intr",	offsetof(struct kvm_vcpu, arch.rm_intr)},
	{"rm_exit",	offsetof(struct kvm_vcpu, arch.rm_exit)},
	{"guest",	offsetof(struct kvm_vcpu, arch.guest_time)},
	{"cede",	offsetof(struct kvm_vcpu, arch.cede_time)},
};

#define N_TIMINGS	(sizeof(timings) / sizeof(timings[0]))

struct debugfs_timings_state {
	struct kvm_vcpu	*vcpu;
	unsigned int	buflen;
	char		buf[N_TIMINGS * 100];
};

static int debugfs_timings_open(struct inode *inode, struct file *file)
{
	struct kvm_vcpu *vcpu = inode->i_private;
	struct debugfs_timings_state *p;

	p = kzalloc(sizeof(*p), GFP_KERNEL);
	if (!p)
		return -ENOMEM;

	kvm_get_kvm(vcpu->kvm);
	p->vcpu = vcpu;
	file->private_data = p;

	return nonseekable_open(inode, file);
}

static int debugfs_timings_release(struct inode *inode, struct file *file)
{
	struct debugfs_timings_state *p = file->private_data;

	kvm_put_kvm(p->vcpu->kvm);
	kfree(p);
	return 0;
}

static ssize_t debugfs_timings_read(struct file *file, char __user *buf,
				    size_t len, loff_t *ppos)
{
	struct debugfs_timings_state *p = file->private_data;
	struct kvm_vcpu *vcpu = p->vcpu;
	char *s, *buf_end;
	struct kvmhv_tb_accumulator tb;
	u64 count;
	loff_t pos;
	ssize_t n;
	int i, loops;
	bool ok;

	if (!p->buflen) {
		s = p->buf;
		buf_end = s + sizeof(p->buf);
		for (i = 0; i < N_TIMINGS; ++i) {
			struct kvmhv_tb_accumulator *acc;

			acc = (struct kvmhv_tb_accumulator *)
				((unsigned long)vcpu + timings[i].offset);
			ok = false;
			for (loops = 0; loops < 1000; ++loops) {
				count = acc->seqcount;
				if (!(count & 1)) {
					smp_rmb();
					tb = *acc;
					smp_rmb();
					if (count == acc->seqcount) {
						ok = true;
						break;
					}
				}
				udelay(1);
			}
			if (!ok)
				snprintf(s, buf_end - s, "%s: stuck\n",
					timings[i].name);
			else
				snprintf(s, buf_end - s,
					"%s: %llu %llu %llu %llu\n",
					timings[i].name, count / 2,
					tb_to_ns(tb.tb_total),
					tb_to_ns(tb.tb_min),
					tb_to_ns(tb.tb_max));
			s += strlen(s);
		}
		p->buflen = s - p->buf;
	}

	pos = *ppos;
	if (pos >= p->buflen)
		return 0;
	if (len > p->buflen - pos)
		len = p->buflen - pos;
	n = copy_to_user(buf, p->buf + pos, len);
	if (n) {
		if (n == len)
			return -EFAULT;
		len -= n;
	}
	*ppos = pos + len;
	return len;
}

static ssize_t debugfs_timings_write(struct file *file, const char __user *buf,
				     size_t len, loff_t *ppos)
{
	return -EACCES;
}

static const struct file_operations debugfs_timings_ops = {
	.owner	 = THIS_MODULE,
	.open	 = debugfs_timings_open,
	.release = debugfs_timings_release,
	.read	 = debugfs_timings_read,
	.write	 = debugfs_timings_write,
	.llseek	 = generic_file_llseek,
};

/* Create a debugfs directory for the vcpu */
static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
{
	char buf[16];
	struct kvm *kvm = vcpu->kvm;

	snprintf(buf, sizeof(buf), "vcpu%u", id);
	if (IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
		return;
	vcpu->arch.debugfs_dir = debugfs_create_dir(buf, kvm->arch.debugfs_dir);
	if (IS_ERR_OR_NULL(vcpu->arch.debugfs_dir))
		return;
	vcpu->arch.debugfs_timings =
		debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir,
				    vcpu, &debugfs_timings_ops);
}

#else /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
{
}
#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */

static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
						   unsigned int id)
{
	struct kvm_vcpu *vcpu;
	int err = -EINVAL;
	int core;
	struct kvmppc_vcore *vcore;

	core = id / threads_per_subcore;
	if (core >= KVM_MAX_VCORES)
		goto out;

	err = -ENOMEM;
	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
	if (!vcpu)
		goto out;

	err = kvm_vcpu_init(vcpu, kvm, id);
	if (err)
		goto free_vcpu;

	vcpu->arch.shared = &vcpu->arch.shregs;
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
	/*
	 * The shared struct is never shared on HV,
	 * so we can always use host endianness
	 */
#ifdef __BIG_ENDIAN__
	vcpu->arch.shared_big_endian = true;
#else
	vcpu->arch.shared_big_endian = false;
#endif
#endif
	vcpu->arch.mmcr[0] = MMCR0_FC;
	vcpu->arch.ctrl = CTRL_RUNLATCH;
	/* default to host PVR, since we can't spoof it */
	kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR));
	spin_lock_init(&vcpu->arch.vpa_update_lock);
	spin_lock_init(&vcpu->arch.tbacct_lock);
	vcpu->arch.busy_preempt = TB_NIL;
	vcpu->arch.intr_msr = MSR_SF | MSR_ME;

	kvmppc_mmu_book3s_hv_init(vcpu);

	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;

	init_waitqueue_head(&vcpu->arch.cpu_run);

	mutex_lock(&kvm->lock);
	vcore = kvm->arch.vcores[core];
	if (!vcore) {
		vcore = kvmppc_vcore_create(kvm, core);
		kvm->arch.vcores[core] = vcore;
		kvm->arch.online_vcores++;
	}
	mutex_unlock(&kvm->lock);

	if (!vcore)
		goto free_vcpu;

	spin_lock(&vcore->lock);
	++vcore->num_threads;
	spin_unlock(&vcore->lock);
	vcpu->arch.vcore = vcore;
	vcpu->arch.ptid = vcpu->vcpu_id - vcore->first_vcpuid;

	vcpu->arch.cpu_type = KVM_CPU_3S_64;
	kvmppc_sanity_check(vcpu);

	debugfs_vcpu_init(vcpu, id);

	return vcpu;

free_vcpu:
	kmem_cache_free(kvm_vcpu_cache, vcpu);
out:
	return ERR_PTR(err);
}

static void unpin_vpa(struct kvm *kvm, struct kvmppc_vpa *vpa)
{
	if (vpa->pinned_addr)
		kvmppc_unpin_guest_page(kvm, vpa->pinned_addr, vpa->gpa,
					vpa->dirty);
}

static void kvmppc_core_vcpu_free_hv(struct kvm_vcpu *vcpu)
{
	spin_lock(&vcpu->arch.vpa_update_lock);
	unpin_vpa(vcpu->kvm, &vcpu->arch.dtl);
	unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow);
	unpin_vpa(vcpu->kvm, &vcpu->arch.vpa);
	spin_unlock(&vcpu->arch.vpa_update_lock);
	kvm_vcpu_uninit(vcpu);
	kmem_cache_free(kvm_vcpu_cache, vcpu);
}

static int kvmppc_core_check_requests_hv(struct kvm_vcpu *vcpu)
{
	/* Indicate we want to get back into the guest */
	return 1;
}

static void kvmppc_set_timer(struct kvm_vcpu *vcpu)
{
	unsigned long dec_nsec, now;

	now = get_tb();
	if (now > vcpu->arch.dec_expires) {
		/* decrementer has already gone negative */
		kvmppc_core_queue_dec(vcpu);
		kvmppc_core_prepare_to_enter(vcpu);
		return;
	}
	dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC
		   / tb_ticks_per_sec;
	hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec),
		      HRTIMER_MODE_REL);
	vcpu->arch.timer_running = 1;
}

static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
{
	vcpu->arch.ceded = 0;
	if (vcpu->arch.timer_running) {
		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
		vcpu->arch.timer_running = 0;
	}
}

extern void __kvmppc_vcore_entry(void);

static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
				   struct kvm_vcpu *vcpu)
{
	u64 now;

	if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
		return;
	spin_lock_irq(&vcpu->arch.tbacct_lock);
	now = mftb();
	vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) -
		vcpu->arch.stolen_logged;
	vcpu->arch.busy_preempt = now;
	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
	spin_unlock_irq(&vcpu->arch.tbacct_lock);
	--vc->n_runnable;
	list_del(&vcpu->arch.run_list);
}

static int kvmppc_grab_hwthread(int cpu)
{
	struct paca_struct *tpaca;
	long timeout = 10000;

	tpaca = &paca[cpu];

	/* Ensure the thread won't go into the kernel if it wakes */
	tpaca->kvm_hstate.kvm_vcpu = NULL;
	tpaca->kvm_hstate.napping = 0;
	smp_wmb();
	tpaca->kvm_hstate.hwthread_req = 1;

	/*
	 * If the thread is already executing in the kernel (e.g. handling
	 * a stray interrupt), wait for it to get back to nap mode.
	 * The smp_mb() is to ensure that our setting of hwthread_req
	 * is visible before we look at hwthread_state, so if this
	 * races with the code at system_reset_pSeries and the thread
	 * misses our setting of hwthread_req, we are sure to see its
	 * setting of hwthread_state, and vice versa.
	 */
	smp_mb();
	while (tpaca->kvm_hstate.hwthread_state == KVM_HWTHREAD_IN_KERNEL) {
		if (--timeout <= 0) {
			pr_err("KVM: couldn't grab cpu %d\n", cpu);
			return -EBUSY;
		}
		udelay(1);
	}
	return 0;
}

static void kvmppc_release_hwthread(int cpu)
{
	struct paca_struct *tpaca;

	tpaca = &paca[cpu];
	tpaca->kvm_hstate.hwthread_req = 0;
	tpaca->kvm_hstate.kvm_vcpu = NULL;
}

static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
{
	int cpu;
	struct paca_struct *tpaca;
	struct kvmppc_vcore *vc = vcpu->arch.vcore;

	if (vcpu->arch.timer_running) {
		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
		vcpu->arch.timer_running = 0;
	}
	cpu = vc->pcpu + vcpu->arch.ptid;
	tpaca = &paca[cpu];
	tpaca->kvm_hstate.kvm_vcore = vc;
	tpaca->kvm_hstate.ptid = vcpu->arch.ptid;
	vcpu->cpu = vc->pcpu;
	/* Order stores to hstate.kvm_vcore etc. before store to kvm_vcpu */
	smp_wmb();
	tpaca->kvm_hstate.kvm_vcpu = vcpu;
	if (cpu != smp_processor_id())
		kvmppc_ipi_thread(cpu);
}

static void kvmppc_wait_for_nap(void)
{
	int cpu = smp_processor_id();
	int i, loops;

	for (loops = 0; loops < 1000000; ++loops) {
		/*
		 * Check if all threads are finished.
		 * We set the vcpu pointer when starting a thread
		 * and the thread clears it when finished, so we look
		 * for any threads that still have a non-NULL vcpu ptr.
		 */
		for (i = 1; i < threads_per_subcore; ++i)
			if (paca[cpu + i].kvm_hstate.kvm_vcpu)
				break;
		if (i == threads_per_subcore) {
			HMT_medium();
			return;
		}
		HMT_low();
	}
	HMT_medium();
	for (i = 1; i < threads_per_subcore; ++i)
		if (paca[cpu + i].kvm_hstate.kvm_vcpu)
			pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
}

/*
 * Check that we are on thread 0 and that any other threads in
 * this core are off-line.  Then grab the threads so they can't
 * enter the kernel.
 */
static int on_primary_thread(void)
{
	int cpu = smp_processor_id();
	int thr;

	/* Are we on a primary subcore? */
	if (cpu_thread_in_subcore(cpu))
		return 0;

	thr = 0;
	while (++thr < threads_per_subcore)
		if (cpu_online(cpu + thr))
			return 0;

	/* Grab all hw threads so they can't go into the kernel */
	for (thr = 1; thr < threads_per_subcore; ++thr) {
		if (kvmppc_grab_hwthread(cpu + thr)) {
			/* Couldn't grab one; let the others go */
			do {
				kvmppc_release_hwthread(cpu + thr);
			} while (--thr > 0);
			return 0;
		}
	}
	return 1;
}

static void kvmppc_start_saving_l2_cache(struct kvmppc_vcore *vc)
{
	phys_addr_t phy_addr, mpp_addr;

	phy_addr = (phys_addr_t)virt_to_phys(vc->mpp_buffer);
	mpp_addr = phy_addr & PPC_MPPE_ADDRESS_MASK;

	mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_ABORT);
	logmpp(mpp_addr | PPC_LOGMPP_LOG_L2);

	vc->mpp_buffer_is_valid = true;
}

static void kvmppc_start_restoring_l2_cache(const struct kvmppc_vcore *vc)
{
	phys_addr_t phy_addr, mpp_addr;

	phy_addr = virt_to_phys(vc->mpp_buffer);
	mpp_addr = phy_addr & PPC_MPPE_ADDRESS_MASK;

	/* We must abort any in-progress save operations to ensure
	 * the table is valid so that prefetch engine knows when to
	 * stop prefetching. */
	logmpp(mpp_addr | PPC_LOGMPP_LOG_ABORT);
	mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_WHOLE_TABLE);
}

static void prepare_threads(struct kvmppc_vcore *vc)
{
	struct kvm_vcpu *vcpu, *vnext;

	list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
				 arch.run_list) {
		if (signal_pending(vcpu->arch.run_task))
			vcpu->arch.ret = -EINTR;
		else if (vcpu->arch.vpa.update_pending ||
			 vcpu->arch.slb_shadow.update_pending ||
			 vcpu->arch.dtl.update_pending)
			vcpu->arch.ret = RESUME_GUEST;
		else
			continue;
		kvmppc_remove_runnable(vc, vcpu);
		wake_up(&vcpu->arch.cpu_run);
	}
}

static void post_guest_process(struct kvmppc_vcore *vc)
{
	u64 now;
	long ret;
	struct kvm_vcpu *vcpu, *vnext;

	now = get_tb();
	list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
				 arch.run_list) {
		/* cancel pending dec exception if dec is positive */
		if (now < vcpu->arch.dec_expires &&
		    kvmppc_core_pending_dec(vcpu))
			kvmppc_core_dequeue_dec(vcpu);

		trace_kvm_guest_exit(vcpu);

		ret = RESUME_GUEST;
		if (vcpu->arch.trap)
			ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
						    vcpu->arch.run_task);

		vcpu->arch.ret = ret;
		vcpu->arch.trap = 0;

		if (vcpu->arch.ceded) {
			if (!is_kvmppc_resume_guest(ret))
				kvmppc_end_cede(vcpu);
			else
				kvmppc_set_timer(vcpu);
		}
		if (!is_kvmppc_resume_guest(vcpu->arch.ret)) {
			kvmppc_remove_runnable(vc, vcpu);
			wake_up(&vcpu->arch.cpu_run);
		}
	}
}

/*
 * Run a set of guest threads on a physical core.
 * Called with vc->lock held.
 */
static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
{
	struct kvm_vcpu *vcpu, *vnext;
	int i;
	int srcu_idx;

	/*
	 * Remove from the list any threads that have a signal pending
	 * or need a VPA update done
	 */
	prepare_threads(vc);

	/* if the runner is no longer runnable, let the caller pick a new one */
	if (vc->runner->arch.state != KVMPPC_VCPU_RUNNABLE)
		return;

	/*
	 * Initialize *vc.
	 */
	vc->entry_exit_map = 0;
	vc->preempt_tb = TB_NIL;
	vc->in_guest = 0;
	vc->napping_threads = 0;
	vc->conferring_threads = 0;

	/*
	 * Make sure we are running on primary threads, and that secondary
	 * threads are offline.  Also check if the number of threads in this
	 * guest are greater than the current system threads per guest.
	 */
	if ((threads_per_core > 1) &&
	    ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
		list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
					 arch.run_list) {
			vcpu->arch.ret = -EBUSY;
			kvmppc_remove_runnable(vc, vcpu);
			wake_up(&vcpu->arch.cpu_run);
		}
		goto out;
	}


	vc->pcpu = smp_processor_id();
	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
		kvmppc_start_thread(vcpu);
		kvmppc_create_dtl_entry(vcpu, vc);
		trace_kvm_guest_enter(vcpu);
	}

	/* Set this explicitly in case thread 0 doesn't have a vcpu */
	get_paca()->kvm_hstate.kvm_vcore = vc;
	get_paca()->kvm_hstate.ptid = 0;

	vc->vcore_state = VCORE_RUNNING;
	preempt_disable();

	trace_kvmppc_run_core(vc, 0);

	spin_unlock(&vc->lock);

	kvm_guest_enter();

	srcu_idx = srcu_read_lock(&vc->kvm->srcu);

	if (vc->mpp_buffer_is_valid)
		kvmppc_start_restoring_l2_cache(vc);

	__kvmppc_vcore_entry();

	spin_lock(&vc->lock);

	if (vc->mpp_buffer)
		kvmppc_start_saving_l2_cache(vc);

	/* disable sending of IPIs on virtual external irqs */
	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
		vcpu->cpu = -1;
	/* wait for secondary threads to finish writing their state to memory */
	kvmppc_wait_for_nap();
	for (i = 0; i < threads_per_subcore; ++i)
		kvmppc_release_hwthread(vc->pcpu + i);
	/* prevent other vcpu threads from doing kvmppc_start_thread() now */
	vc->vcore_state = VCORE_EXITING;
	spin_unlock(&vc->lock);

	srcu_read_unlock(&vc->kvm->srcu, srcu_idx);

	/* make sure updates to secondary vcpu structs are visible now */
	smp_mb();
	kvm_guest_exit();

	preempt_enable();

	spin_lock(&vc->lock);
	post_guest_process(vc);

 out:
	vc->vcore_state = VCORE_INACTIVE;
	trace_kvmppc_run_core(vc, 1);
}

/*
 * Wait for some other vcpu thread to execute us, and
 * wake us up when we need to handle something in the host.
 */
static void kvmppc_wait_for_exec(struct kvm_vcpu *vcpu, int wait_state)
{
	DEFINE_WAIT(wait);

	prepare_to_wait(&vcpu->arch.cpu_run, &wait, wait_state);
	if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE)
		schedule();
	finish_wait(&vcpu->arch.cpu_run, &wait);
}

/*
 * All the vcpus in this vcore are idle, so wait for a decrementer
 * or external interrupt to one of the vcpus.  vc->lock is held.
 */
static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
{
	struct kvm_vcpu *vcpu;
	int do_sleep = 1;

	DEFINE_WAIT(wait);

	prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);

	/*
	 * Check one last time for pending exceptions and ceded state after
	 * we put ourselves on the wait queue
	 */
	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
		if (vcpu->arch.pending_exceptions || !vcpu->arch.ceded) {
			do_sleep = 0;
			break;
		}
	}

	if (!do_sleep) {
		finish_wait(&vc->wq, &wait);
		return;
	}

	vc->vcore_state = VCORE_SLEEPING;
	trace_kvmppc_vcore_blocked(vc, 0);
	spin_unlock(&vc->lock);
	schedule();
	finish_wait(&vc->wq, &wait);
	spin_lock(&vc->lock);
	vc->vcore_state = VCORE_INACTIVE;
	trace_kvmppc_vcore_blocked(vc, 1);
}

static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
{
	int n_ceded;
	struct kvmppc_vcore *vc;
	struct kvm_vcpu *v, *vn;

	trace_kvmppc_run_vcpu_enter(vcpu);

	kvm_run->exit_reason = 0;
	vcpu->arch.ret = RESUME_GUEST;
	vcpu->arch.trap = 0;
	kvmppc_update_vpas(vcpu);

	/*
	 * Synchronize with other threads in this virtual core
	 */
	vc = vcpu->arch.vcore;
	spin_lock(&vc->lock);
	vcpu->arch.ceded = 0;
	vcpu->arch.run_task = current;
	vcpu->arch.kvm_run = kvm_run;
	vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb());
	vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
	vcpu->arch.busy_preempt = TB_NIL;
	list_add_tail(&vcpu->arch.run_list, &vc->runnable_threads);
	++vc->n_runnable;

	/*
	 * This happens the first time this is called for a vcpu.
	 * If the vcore is already running, we may be able to start
	 * this thread straight away and have it join in.
	 */
	if (!signal_pending(current)) {
		if (vc->vcore_state == VCORE_RUNNING && !VCORE_IS_EXITING(vc)) {
			kvmppc_create_dtl_entry(vcpu, vc);
			kvmppc_start_thread(vcpu);
			trace_kvm_guest_enter(vcpu);
		} else if (vc->vcore_state == VCORE_SLEEPING) {
			wake_up(&vc->wq);
		}

	}

	while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
	       !signal_pending(current)) {
		if (vc->vcore_state != VCORE_INACTIVE) {
			spin_unlock(&vc->lock);
			kvmppc_wait_for_exec(vcpu, TASK_INTERRUPTIBLE);
			spin_lock(&vc->lock);
			continue;
		}
		list_for_each_entry_safe(v, vn, &vc->runnable_threads,
					 arch.run_list) {
			kvmppc_core_prepare_to_enter(v);
			if (signal_pending(v->arch.run_task)) {
				kvmppc_remove_runnable(vc, v);
				v->stat.signal_exits++;
				v->arch.kvm_run->exit_reason = KVM_EXIT_INTR;
				v->arch.ret = -EINTR;
				wake_up(&v->arch.cpu_run);
			}
		}
		if (!vc->n_runnable || vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
			break;
		n_ceded = 0;
		list_for_each_entry(v, &vc->runnable_threads, arch.run_list) {
			if (!v->arch.pending_exceptions)
				n_ceded += v->arch.ceded;
			else
				v->arch.ceded = 0;
		}
		vc->runner = vcpu;
		if (n_ceded == vc->n_runnable) {
			kvmppc_vcore_blocked(vc);
		} else if (should_resched()) {
			vc->vcore_state = VCORE_PREEMPT;
			/* Let something else run */
			cond_resched_lock(&vc->lock);
			vc->vcore_state = VCORE_INACTIVE;
		} else {
			kvmppc_run_core(vc);
		}
		vc->runner = NULL;
	}

	while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
	       (vc->vcore_state == VCORE_RUNNING ||
		vc->vcore_state == VCORE_EXITING)) {
		spin_unlock(&vc->lock);
		kvmppc_wait_for_exec(vcpu, TASK_UNINTERRUPTIBLE);
		spin_lock(&vc->lock);
	}

	if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
		kvmppc_remove_runnable(vc, vcpu);
		vcpu->stat.signal_exits++;
		kvm_run->exit_reason = KVM_EXIT_INTR;
		vcpu->arch.ret = -EINTR;
	}

	if (vc->n_runnable && vc->vcore_state == VCORE_INACTIVE) {
		/* Wake up some vcpu to run the core */
		v = list_first_entry(&vc->runnable_threads,
				     struct kvm_vcpu, arch.run_list);
		wake_up(&v->arch.cpu_run);
	}

	trace_kvmppc_run_vcpu_exit(vcpu, kvm_run);
	spin_unlock(&vc->lock);
	return vcpu->arch.ret;
}

static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
{
	int r;
	int srcu_idx;

	if (!vcpu->arch.sane) {
		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		return -EINVAL;
	}

	kvmppc_core_prepare_to_enter(vcpu);

	/* No need to go into the guest when all we'll do is come back out */
	if (signal_pending(current)) {
		run->exit_reason = KVM_EXIT_INTR;
		return -EINTR;
	}

	atomic_inc(&vcpu->kvm->arch.vcpus_running);
	/* Order vcpus_running vs. hpte_setup_done, see kvmppc_alloc_reset_hpt */
	smp_mb();

	/* On the first time here, set up HTAB and VRMA */
	if (!vcpu->kvm->arch.hpte_setup_done) {
		r = kvmppc_hv_setup_htab_rma(vcpu);
		if (r)
			goto out;
	}

	flush_fp_to_thread(current);
	flush_altivec_to_thread(current);
	flush_vsx_to_thread(current);
	vcpu->arch.wqp = &vcpu->arch.vcore->wq;
	vcpu->arch.pgdir = current->mm->pgd;
	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;

	do {
		r = kvmppc_run_vcpu(run, vcpu);

		if (run->exit_reason == KVM_EXIT_PAPR_HCALL &&
		    !(vcpu->arch.shregs.msr & MSR_PR)) {
			trace_kvm_hcall_enter(vcpu);
			r = kvmppc_pseries_do_hcall(vcpu);
			trace_kvm_hcall_exit(vcpu, r);
			kvmppc_core_prepare_to_enter(vcpu);
		} else if (r == RESUME_PAGE_FAULT) {
			srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
			r = kvmppc_book3s_hv_page_fault(run, vcpu,
				vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
			srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
		}
	} while (is_kvmppc_resume_guest(r));

 out:
	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
	atomic_dec(&vcpu->kvm->arch.vcpus_running);
	return r;
}

static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps,
				     int linux_psize)
{
	struct mmu_psize_def *def = &mmu_psize_defs[linux_psize];

	if (!def->shift)
		return;
	(*sps)->page_shift = def->shift;
	(*sps)->slb_enc = def->sllp;
	(*sps)->enc[0].page_shift = def->shift;
	(*sps)->enc[0].pte_enc = def->penc[linux_psize];
	/*
	 * Add 16MB MPSS support if host supports it
	 */
	if (linux_psize != MMU_PAGE_16M && def->penc[MMU_PAGE_16M] != -1) {
		(*sps)->enc[1].page_shift = 24;
		(*sps)->enc[1].pte_enc = def->penc[MMU_PAGE_16M];
	}
	(*sps)++;
}

static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm,
					 struct kvm_ppc_smmu_info *info)
{
	struct kvm_ppc_one_seg_page_size *sps;

	info->flags = KVM_PPC_PAGE_SIZES_REAL;
	if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
		info->flags |= KVM_PPC_1T_SEGMENTS;
	info->slb_size = mmu_slb_size;

	/* We only support these sizes for now, and no muti-size segments */
	sps = &info->sps[0];
	kvmppc_add_seg_page_size(&sps, MMU_PAGE_4K);
	kvmppc_add_seg_page_size(&sps, MMU_PAGE_64K);
	kvmppc_add_seg_page_size(&sps, MMU_PAGE_16M);

	return 0;
}

/*
 * Get (and clear) the dirty memory log for a memory slot.
 */
static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm,
					 struct kvm_dirty_log *log)
{
	struct kvm_memory_slot *memslot;
	int r;
	unsigned long n;

	mutex_lock(&kvm->slots_lock);

	r = -EINVAL;
	if (log->slot >= KVM_USER_MEM_SLOTS)
		goto out;

	memslot = id_to_memslot(kvm->memslots, log->slot);
	r = -ENOENT;
	if (!memslot->dirty_bitmap)
		goto out;

	n = kvm_dirty_bitmap_bytes(memslot);
	memset(memslot->dirty_bitmap, 0, n);

	r = kvmppc_hv_get_dirty_log(kvm, memslot, memslot->dirty_bitmap);
	if (r)
		goto out;

	r = -EFAULT;
	if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n))
		goto out;

	r = 0;
out:
	mutex_unlock(&kvm->slots_lock);
	return r;
}

static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free,
					struct kvm_memory_slot *dont)
{
	if (!dont || free->arch.rmap != dont->arch.rmap) {
		vfree(free->arch.rmap);
		free->arch.rmap = NULL;
	}
}

static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot,
					 unsigned long npages)
{
	slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap));
	if (!slot->arch.rmap)
		return -ENOMEM;

	return 0;
}

static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm,
					struct kvm_memory_slot *memslot,
					struct kvm_userspace_memory_region *mem)
{
	return 0;
}

static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem,
				const struct kvm_memory_slot *old)
{
	unsigned long npages = mem->memory_size >> PAGE_SHIFT;
	struct kvm_memory_slot *memslot;

	if (npages && old->npages) {
		/*
		 * If modifying a memslot, reset all the rmap dirty bits.
		 * If this is a new memslot, we don't need to do anything
		 * since the rmap array starts out as all zeroes,
		 * i.e. no pages are dirty.
		 */
		memslot = id_to_memslot(kvm->memslots, mem->slot);
		kvmppc_hv_get_dirty_log(kvm, memslot, NULL);
	}
}

/*
 * Update LPCR values in kvm->arch and in vcores.
 * Caller must hold kvm->lock.
 */
void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask)
{
	long int i;
	u32 cores_done = 0;

	if ((kvm->arch.lpcr & mask) == lpcr)
		return;

	kvm->arch.lpcr = (kvm->arch.lpcr & ~mask) | lpcr;

	for (i = 0; i < KVM_MAX_VCORES; ++i) {
		struct kvmppc_vcore *vc = kvm->arch.vcores[i];
		if (!vc)
			continue;
		spin_lock(&vc->lock);
		vc->lpcr = (vc->lpcr & ~mask) | lpcr;
		spin_unlock(&vc->lock);
		if (++cores_done >= kvm->arch.online_vcores)
			break;
	}
}

static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu)
{
	return;
}

static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
{
	int err = 0;
	struct kvm *kvm = vcpu->kvm;
	unsigned long hva;
	struct kvm_memory_slot *memslot;
	struct vm_area_struct *vma;
	unsigned long lpcr = 0, senc;
	unsigned long psize, porder;
	int srcu_idx;

	mutex_lock(&kvm->lock);
	if (kvm->arch.hpte_setup_done)
		goto out;	/* another vcpu beat us to it */

	/* Allocate hashed page table (if not done already) and reset it */
	if (!kvm->arch.hpt_virt) {
		err = kvmppc_alloc_hpt(kvm, NULL);
		if (err) {
			pr_err("KVM: Couldn't alloc HPT\n");
			goto out;
		}
	}

	/* Look up the memslot for guest physical address 0 */
	srcu_idx = srcu_read_lock(&kvm->srcu);
	memslot = gfn_to_memslot(kvm, 0);

	/* We must have some memory at 0 by now */
	err = -EINVAL;
	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
		goto out_srcu;

	/* Look up the VMA for the start of this memory slot */
	hva = memslot->userspace_addr;
	down_read(&current->mm->mmap_sem);
	vma = find_vma(current->mm, hva);
	if (!vma || vma->vm_start > hva || (vma->vm_flags & VM_IO))
		goto up_out;

	psize = vma_kernel_pagesize(vma);
	porder = __ilog2(psize);

	up_read(&current->mm->mmap_sem);

	/* We can handle 4k, 64k or 16M pages in the VRMA */
	err = -EINVAL;
	if (!(psize == 0x1000 || psize == 0x10000 ||
	      psize == 0x1000000))
		goto out_srcu;

	/* Update VRMASD field in the LPCR */
	senc = slb_pgsize_encoding(psize);
	kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
		(VRMA_VSID << SLB_VSID_SHIFT_1T);
	/* the -4 is to account for senc values starting at 0x10 */
	lpcr = senc << (LPCR_VRMASD_SH - 4);

	/* Create HPTEs in the hash page table for the VRMA */
	kvmppc_map_vrma(vcpu, memslot, porder);

	kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);

	/* Order updates to kvm->arch.lpcr etc. vs. hpte_setup_done */
	smp_wmb();
	kvm->arch.hpte_setup_done = 1;
	err = 0;
 out_srcu:
	srcu_read_unlock(&kvm->srcu, srcu_idx);
 out:
	mutex_unlock(&kvm->lock);
	return err;

 up_out:
	up_read(&current->mm->mmap_sem);
	goto out_srcu;
}

static int kvmppc_core_init_vm_hv(struct kvm *kvm)
{
	unsigned long lpcr, lpid;
	char buf[32];

	/* Allocate the guest's logical partition ID */

	lpid = kvmppc_alloc_lpid();
	if ((long)lpid < 0)
		return -ENOMEM;
	kvm->arch.lpid = lpid;

	/*
	 * Since we don't flush the TLB when tearing down a VM,
	 * and this lpid might have previously been used,
	 * make sure we flush on each core before running the new VM.
	 */
	cpumask_setall(&kvm->arch.need_tlb_flush);

	/* Start out with the default set of hcalls enabled */
	memcpy(kvm->arch.enabled_hcalls, default_enabled_hcalls,
	       sizeof(kvm->arch.enabled_hcalls));

	kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);

	/* Init LPCR for virtual RMA mode */
	kvm->arch.host_lpid = mfspr(SPRN_LPID);
	kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR);
	lpcr &= LPCR_PECE | LPCR_LPES;
	lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE |
		LPCR_VPM0 | LPCR_VPM1;
	kvm->arch.vrma_slb_v = SLB_VSID_B_1T |
		(VRMA_VSID << SLB_VSID_SHIFT_1T);
	/* On POWER8 turn on online bit to enable PURR/SPURR */
	if (cpu_has_feature(CPU_FTR_ARCH_207S))
		lpcr |= LPCR_ONL;
	kvm->arch.lpcr = lpcr;

	/*
	 * Track that we now have a HV mode VM active. This blocks secondary
	 * CPU threads from coming online.
	 */
	kvm_hv_vm_activated();

	/*
	 * Create a debugfs directory for the VM
	 */
	snprintf(buf, sizeof(buf), "vm%d", current->pid);
	kvm->arch.debugfs_dir = debugfs_create_dir(buf, kvm_debugfs_dir);
	if (!IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
		kvmppc_mmu_debugfs_init(kvm);

	return 0;
}

static void kvmppc_free_vcores(struct kvm *kvm)
{
	long int i;

	for (i = 0; i < KVM_MAX_VCORES; ++i) {
		if (kvm->arch.vcores[i] && kvm->arch.vcores[i]->mpp_buffer) {
			struct kvmppc_vcore *vc = kvm->arch.vcores[i];
			free_pages((unsigned long)vc->mpp_buffer,
				   MPP_BUFFER_ORDER);
		}
		kfree(kvm->arch.vcores[i]);
	}
	kvm->arch.online_vcores = 0;
}

static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
{
	debugfs_remove_recursive(kvm->arch.debugfs_dir);

	kvm_hv_vm_deactivated();

	kvmppc_free_vcores(kvm);

	kvmppc_free_hpt(kvm);
}

/* We don't need to emulate any privileged instructions or dcbz */
static int kvmppc_core_emulate_op_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
				     unsigned int inst, int *advance)
{
	return EMULATE_FAIL;
}

static int kvmppc_core_emulate_mtspr_hv(struct kvm_vcpu *vcpu, int sprn,
					ulong spr_val)
{
	return EMULATE_FAIL;
}

static int kvmppc_core_emulate_mfspr_hv(struct kvm_vcpu *vcpu, int sprn,
					ulong *spr_val)
{
	return EMULATE_FAIL;
}

static int kvmppc_core_check_processor_compat_hv(void)
{
	if (!cpu_has_feature(CPU_FTR_HVMODE) ||
	    !cpu_has_feature(CPU_FTR_ARCH_206))
		return -EIO;
	return 0;
}

static long kvm_arch_vm_ioctl_hv(struct file *filp,
				 unsigned int ioctl, unsigned long arg)
{
	struct kvm *kvm __maybe_unused = filp->private_data;
	void __user *argp = (void __user *)arg;
	long r;

	switch (ioctl) {

	case KVM_PPC_ALLOCATE_HTAB: {
		u32 htab_order;

		r = -EFAULT;
		if (get_user(htab_order, (u32 __user *)argp))
			break;
		r = kvmppc_alloc_reset_hpt(kvm, &htab_order);
		if (r)
			break;
		r = -EFAULT;
		if (put_user(htab_order, (u32 __user *)argp))
			break;
		r = 0;
		break;
	}

	case KVM_PPC_GET_HTAB_FD: {
		struct kvm_get_htab_fd ghf;

		r = -EFAULT;
		if (copy_from_user(&ghf, argp, sizeof(ghf)))
			break;
		r = kvm_vm_ioctl_get_htab_fd(kvm, &ghf);
		break;
	}

	default:
		r = -ENOTTY;
	}

	return r;
}

/*
 * List of hcall numbers to enable by default.
 * For compatibility with old userspace, we enable by default
 * all hcalls that were implemented before the hcall-enabling
 * facility was added.  Note this list should not include H_RTAS.
 */
static unsigned int default_hcall_list[] = {
	H_REMOVE,
	H_ENTER,
	H_READ,
	H_PROTECT,
	H_BULK_REMOVE,
	H_GET_TCE,
	H_PUT_TCE,
	H_SET_DABR,
	H_SET_XDABR,
	H_CEDE,
	H_PROD,
	H_CONFER,
	H_REGISTER_VPA,
#ifdef CONFIG_KVM_XICS
	H_EOI,
	H_CPPR,
	H_IPI,
	H_IPOLL,
	H_XIRR,
	H_XIRR_X,
#endif
	0
};

static void init_default_hcalls(void)
{
	int i;
	unsigned int hcall;

	for (i = 0; default_hcall_list[i]; ++i) {
		hcall = default_hcall_list[i];
		WARN_ON(!kvmppc_hcall_impl_hv(hcall));
		__set_bit(hcall / 4, default_enabled_hcalls);
	}
}

static struct kvmppc_ops kvm_ops_hv = {
	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
	.get_one_reg = kvmppc_get_one_reg_hv,
	.set_one_reg = kvmppc_set_one_reg_hv,
	.vcpu_load   = kvmppc_core_vcpu_load_hv,
	.vcpu_put    = kvmppc_core_vcpu_put_hv,
	.set_msr     = kvmppc_set_msr_hv,
	.vcpu_run    = kvmppc_vcpu_run_hv,
	.vcpu_create = kvmppc_core_vcpu_create_hv,
	.vcpu_free   = kvmppc_core_vcpu_free_hv,
	.check_requests = kvmppc_core_check_requests_hv,
	.get_dirty_log  = kvm_vm_ioctl_get_dirty_log_hv,
	.flush_memslot  = kvmppc_core_flush_memslot_hv,
	.prepare_memory_region = kvmppc_core_prepare_memory_region_hv,
	.commit_memory_region  = kvmppc_core_commit_memory_region_hv,
	.unmap_hva = kvm_unmap_hva_hv,
	.unmap_hva_range = kvm_unmap_hva_range_hv,
	.age_hva  = kvm_age_hva_hv,
	.test_age_hva = kvm_test_age_hva_hv,
	.set_spte_hva = kvm_set_spte_hva_hv,
	.mmu_destroy  = kvmppc_mmu_destroy_hv,
	.free_memslot = kvmppc_core_free_memslot_hv,
	.create_memslot = kvmppc_core_create_memslot_hv,
	.init_vm =  kvmppc_core_init_vm_hv,
	.destroy_vm = kvmppc_core_destroy_vm_hv,
	.get_smmu_info = kvm_vm_ioctl_get_smmu_info_hv,
	.emulate_op = kvmppc_core_emulate_op_hv,
	.emulate_mtspr = kvmppc_core_emulate_mtspr_hv,
	.emulate_mfspr = kvmppc_core_emulate_mfspr_hv,
	.fast_vcpu_kick = kvmppc_fast_vcpu_kick_hv,
	.arch_vm_ioctl  = kvm_arch_vm_ioctl_hv,
	.hcall_implemented = kvmppc_hcall_impl_hv,
};

static int kvmppc_book3s_init_hv(void)
{
	int r;
	/*
	 * FIXME!! Do we need to check on all cpus ?
	 */
	r = kvmppc_core_check_processor_compat_hv();
	if (r < 0)
		return -ENODEV;

	kvm_ops_hv.owner = THIS_MODULE;
	kvmppc_hv_ops = &kvm_ops_hv;

	init_default_hcalls();

	r = kvmppc_mmu_hv_init();
	return r;
}

static void kvmppc_book3s_exit_hv(void)
{
	kvmppc_hv_ops = NULL;
}

module_init(kvmppc_book3s_init_hv);
module_exit(kvmppc_book3s_exit_hv);
MODULE_LICENSE("GPL");
MODULE_ALIAS_MISCDEV(KVM_MINOR);
MODULE_ALIAS("devname:kvm");
OpenPOWER on IntegriCloud