summaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/book3s.c
blob: e316847c08c0b85d3472bd1377c67f50077234d0 (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
/*
 * Copyright (C) 2009. SUSE Linux Products GmbH. All rights reserved.
 *
 * Authors:
 *    Alexander Graf <agraf@suse.de>
 *    Kevin Wolf <mail@kevin-wolf.de>
 *
 * Description:
 * This file is derived from arch/powerpc/kvm/44x.c,
 * by Hollis Blanchard <hollisb@us.ibm.com>.
 *
 * 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 "trace.h"

#include <asm/reg.h>
#include <asm/cputable.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 <linux/gfp.h>
#include <linux/sched.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>

#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU

/* #define EXIT_DEBUG */
/* #define DEBUG_EXT */

static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
			     ulong msr);

/* Some compatibility defines */
#ifdef CONFIG_PPC_BOOK3S_32
#define MSR_USER32 MSR_USER
#define MSR_USER64 MSR_USER
#define HW_PAGE_SIZE PAGE_SIZE
#endif

struct kvm_stats_debugfs_item debugfs_entries[] = {
	{ "exits",       VCPU_STAT(sum_exits) },
	{ "mmio",        VCPU_STAT(mmio_exits) },
	{ "sig",         VCPU_STAT(signal_exits) },
	{ "sysc",        VCPU_STAT(syscall_exits) },
	{ "inst_emu",    VCPU_STAT(emulated_inst_exits) },
	{ "dec",         VCPU_STAT(dec_exits) },
	{ "ext_intr",    VCPU_STAT(ext_intr_exits) },
	{ "queue_intr",  VCPU_STAT(queue_intr) },
	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
	{ "pf_storage",  VCPU_STAT(pf_storage) },
	{ "sp_storage",  VCPU_STAT(sp_storage) },
	{ "pf_instruc",  VCPU_STAT(pf_instruc) },
	{ "sp_instruc",  VCPU_STAT(sp_instruc) },
	{ "ld",          VCPU_STAT(ld) },
	{ "ld_slow",     VCPU_STAT(ld_slow) },
	{ "st",          VCPU_STAT(st) },
	{ "st_slow",     VCPU_STAT(st_slow) },
	{ NULL }
};

void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu)
{
}

void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
{
}

void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
#ifdef CONFIG_PPC_BOOK3S_64
	memcpy(to_svcpu(vcpu)->slb, to_book3s(vcpu)->slb_shadow, sizeof(to_svcpu(vcpu)->slb));
	memcpy(&get_paca()->shadow_vcpu, to_book3s(vcpu)->shadow_vcpu,
	       sizeof(get_paca()->shadow_vcpu));
	to_svcpu(vcpu)->slb_max = to_book3s(vcpu)->slb_shadow_max;
#endif

#ifdef CONFIG_PPC_BOOK3S_32
	current->thread.kvm_shadow_vcpu = to_book3s(vcpu)->shadow_vcpu;
#endif
}

void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_PPC_BOOK3S_64
	memcpy(to_book3s(vcpu)->slb_shadow, to_svcpu(vcpu)->slb, sizeof(to_svcpu(vcpu)->slb));
	memcpy(to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu,
	       sizeof(get_paca()->shadow_vcpu));
	to_book3s(vcpu)->slb_shadow_max = to_svcpu(vcpu)->slb_max;
#endif

	kvmppc_giveup_ext(vcpu, MSR_FP);
	kvmppc_giveup_ext(vcpu, MSR_VEC);
	kvmppc_giveup_ext(vcpu, MSR_VSX);
}

static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
{
	ulong smsr = vcpu->arch.shared->msr;

	/* Guest MSR values */
	smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE | MSR_DE;
	/* Process MSR values */
	smsr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR | MSR_EE;
	/* External providers the guest reserved */
	smsr |= (vcpu->arch.shared->msr & vcpu->arch.guest_owned_ext);
	/* 64-bit Process MSR values */
#ifdef CONFIG_PPC_BOOK3S_64
	smsr |= MSR_ISF | MSR_HV;
#endif
	vcpu->arch.shadow_msr = smsr;
}

void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
{
	ulong old_msr = vcpu->arch.shared->msr;

#ifdef EXIT_DEBUG
	printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr);
#endif

	msr &= to_book3s(vcpu)->msr_mask;
	vcpu->arch.shared->msr = msr;
	kvmppc_recalc_shadow_msr(vcpu);

	if (msr & MSR_POW) {
		if (!vcpu->arch.pending_exceptions) {
			kvm_vcpu_block(vcpu);
			vcpu->stat.halt_wakeup++;

			/* Unset POW bit after we woke up */
			msr &= ~MSR_POW;
			vcpu->arch.shared->msr = msr;
		}
	}

	if ((vcpu->arch.shared->msr & (MSR_PR|MSR_IR|MSR_DR)) !=
		   (old_msr & (MSR_PR|MSR_IR|MSR_DR))) {
		kvmppc_mmu_flush_segments(vcpu);
		kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));

		/* Preload magic page segment when in kernel mode */
		if (!(msr & MSR_PR) && vcpu->arch.magic_page_pa) {
			struct kvm_vcpu_arch *a = &vcpu->arch;

			if (msr & MSR_DR)
				kvmppc_mmu_map_segment(vcpu, a->magic_page_ea);
			else
				kvmppc_mmu_map_segment(vcpu, a->magic_page_pa);
		}
	}

	/* Preload FPU if it's enabled */
	if (vcpu->arch.shared->msr & MSR_FP)
		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
}

void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
{
	vcpu->arch.shared->srr0 = kvmppc_get_pc(vcpu);
	vcpu->arch.shared->srr1 = vcpu->arch.shared->msr | flags;
	kvmppc_set_pc(vcpu, to_book3s(vcpu)->hior + vec);
	vcpu->arch.mmu.reset_msr(vcpu);
}

static int kvmppc_book3s_vec2irqprio(unsigned int vec)
{
	unsigned int prio;

	switch (vec) {
	case 0x100: prio = BOOK3S_IRQPRIO_SYSTEM_RESET;		break;
	case 0x200: prio = BOOK3S_IRQPRIO_MACHINE_CHECK;	break;
	case 0x300: prio = BOOK3S_IRQPRIO_DATA_STORAGE;		break;
	case 0x380: prio = BOOK3S_IRQPRIO_DATA_SEGMENT;		break;
	case 0x400: prio = BOOK3S_IRQPRIO_INST_STORAGE;		break;
	case 0x480: prio = BOOK3S_IRQPRIO_INST_SEGMENT;		break;
	case 0x500: prio = BOOK3S_IRQPRIO_EXTERNAL;		break;
	case 0x501: prio = BOOK3S_IRQPRIO_EXTERNAL_LEVEL;	break;
	case 0x600: prio = BOOK3S_IRQPRIO_ALIGNMENT;		break;
	case 0x700: prio = BOOK3S_IRQPRIO_PROGRAM;		break;
	case 0x800: prio = BOOK3S_IRQPRIO_FP_UNAVAIL;		break;
	case 0x900: prio = BOOK3S_IRQPRIO_DECREMENTER;		break;
	case 0xc00: prio = BOOK3S_IRQPRIO_SYSCALL;		break;
	case 0xd00: prio = BOOK3S_IRQPRIO_DEBUG;		break;
	case 0xf20: prio = BOOK3S_IRQPRIO_ALTIVEC;		break;
	case 0xf40: prio = BOOK3S_IRQPRIO_VSX;			break;
	default:    prio = BOOK3S_IRQPRIO_MAX;			break;
	}

	return prio;
}

static void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu,
					  unsigned int vec)
{
	clear_bit(kvmppc_book3s_vec2irqprio(vec),
		  &vcpu->arch.pending_exceptions);

	if (!vcpu->arch.pending_exceptions)
		vcpu->arch.shared->int_pending = 0;
}

void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
{
	vcpu->stat.queue_intr++;

	set_bit(kvmppc_book3s_vec2irqprio(vec),
		&vcpu->arch.pending_exceptions);
#ifdef EXIT_DEBUG
	printk(KERN_INFO "Queueing interrupt %x\n", vec);
#endif
}


void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags)
{
	to_book3s(vcpu)->prog_flags = flags;
	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_PROGRAM);
}

void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu)
{
	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER);
}

int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu)
{
	return test_bit(BOOK3S_INTERRUPT_DECREMENTER >> 7, &vcpu->arch.pending_exceptions);
}

void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu)
{
	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER);
}

void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                struct kvm_interrupt *irq)
{
	unsigned int vec = BOOK3S_INTERRUPT_EXTERNAL;

	if (irq->irq == KVM_INTERRUPT_SET_LEVEL)
		vec = BOOK3S_INTERRUPT_EXTERNAL_LEVEL;

	kvmppc_book3s_queue_irqprio(vcpu, vec);
}

void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
                                  struct kvm_interrupt *irq)
{
	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
}

int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
{
	int deliver = 1;
	int vec = 0;
	ulong flags = 0ULL;
	ulong crit_raw = vcpu->arch.shared->critical;
	ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
	bool crit;

	/* Truncate crit indicators in 32 bit mode */
	if (!(vcpu->arch.shared->msr & MSR_SF)) {
		crit_raw &= 0xffffffff;
		crit_r1 &= 0xffffffff;
	}

	/* Critical section when crit == r1 */
	crit = (crit_raw == crit_r1);
	/* ... and we're in supervisor mode */
	crit = crit && !(vcpu->arch.shared->msr & MSR_PR);

	switch (priority) {
	case BOOK3S_IRQPRIO_DECREMENTER:
		deliver = (vcpu->arch.shared->msr & MSR_EE) && !crit;
		vec = BOOK3S_INTERRUPT_DECREMENTER;
		break;
	case BOOK3S_IRQPRIO_EXTERNAL:
	case BOOK3S_IRQPRIO_EXTERNAL_LEVEL:
		deliver = (vcpu->arch.shared->msr & MSR_EE) && !crit;
		vec = BOOK3S_INTERRUPT_EXTERNAL;
		break;
	case BOOK3S_IRQPRIO_SYSTEM_RESET:
		vec = BOOK3S_INTERRUPT_SYSTEM_RESET;
		break;
	case BOOK3S_IRQPRIO_MACHINE_CHECK:
		vec = BOOK3S_INTERRUPT_MACHINE_CHECK;
		break;
	case BOOK3S_IRQPRIO_DATA_STORAGE:
		vec = BOOK3S_INTERRUPT_DATA_STORAGE;
		break;
	case BOOK3S_IRQPRIO_INST_STORAGE:
		vec = BOOK3S_INTERRUPT_INST_STORAGE;
		break;
	case BOOK3S_IRQPRIO_DATA_SEGMENT:
		vec = BOOK3S_INTERRUPT_DATA_SEGMENT;
		break;
	case BOOK3S_IRQPRIO_INST_SEGMENT:
		vec = BOOK3S_INTERRUPT_INST_SEGMENT;
		break;
	case BOOK3S_IRQPRIO_ALIGNMENT:
		vec = BOOK3S_INTERRUPT_ALIGNMENT;
		break;
	case BOOK3S_IRQPRIO_PROGRAM:
		vec = BOOK3S_INTERRUPT_PROGRAM;
		flags = to_book3s(vcpu)->prog_flags;
		break;
	case BOOK3S_IRQPRIO_VSX:
		vec = BOOK3S_INTERRUPT_VSX;
		break;
	case BOOK3S_IRQPRIO_ALTIVEC:
		vec = BOOK3S_INTERRUPT_ALTIVEC;
		break;
	case BOOK3S_IRQPRIO_FP_UNAVAIL:
		vec = BOOK3S_INTERRUPT_FP_UNAVAIL;
		break;
	case BOOK3S_IRQPRIO_SYSCALL:
		vec = BOOK3S_INTERRUPT_SYSCALL;
		break;
	case BOOK3S_IRQPRIO_DEBUG:
		vec = BOOK3S_INTERRUPT_TRACE;
		break;
	case BOOK3S_IRQPRIO_PERFORMANCE_MONITOR:
		vec = BOOK3S_INTERRUPT_PERFMON;
		break;
	default:
		deliver = 0;
		printk(KERN_ERR "KVM: Unknown interrupt: 0x%x\n", priority);
		break;
	}

#if 0
	printk(KERN_INFO "Deliver interrupt 0x%x? %x\n", vec, deliver);
#endif

	if (deliver)
		kvmppc_inject_interrupt(vcpu, vec, flags);

	return deliver;
}

/*
 * This function determines if an irqprio should be cleared once issued.
 */
static bool clear_irqprio(struct kvm_vcpu *vcpu, unsigned int priority)
{
	switch (priority) {
		case BOOK3S_IRQPRIO_DECREMENTER:
			/* DEC interrupts get cleared by mtdec */
			return false;
		case BOOK3S_IRQPRIO_EXTERNAL_LEVEL:
			/* External interrupts get cleared by userspace */
			return false;
	}

	return true;
}

void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
{
	unsigned long *pending = &vcpu->arch.pending_exceptions;
	unsigned long old_pending = vcpu->arch.pending_exceptions;
	unsigned int priority;

#ifdef EXIT_DEBUG
	if (vcpu->arch.pending_exceptions)
		printk(KERN_EMERG "KVM: Check pending: %lx\n", vcpu->arch.pending_exceptions);
#endif
	priority = __ffs(*pending);
	while (priority < BOOK3S_IRQPRIO_MAX) {
		if (kvmppc_book3s_irqprio_deliver(vcpu, priority) &&
		    clear_irqprio(vcpu, priority)) {
			clear_bit(priority, &vcpu->arch.pending_exceptions);
			break;
		}

		priority = find_next_bit(pending,
					 BITS_PER_BYTE * sizeof(*pending),
					 priority + 1);
	}

	/* Tell the guest about our interrupt status */
	if (*pending)
		vcpu->arch.shared->int_pending = 1;
	else if (old_pending)
		vcpu->arch.shared->int_pending = 0;
}

void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
{
	u32 host_pvr;

	vcpu->arch.hflags &= ~BOOK3S_HFLAG_SLB;
	vcpu->arch.pvr = pvr;
#ifdef CONFIG_PPC_BOOK3S_64
	if ((pvr >= 0x330000) && (pvr < 0x70330000)) {
		kvmppc_mmu_book3s_64_init(vcpu);
		to_book3s(vcpu)->hior = 0xfff00000;
		to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL;
	} else
#endif
	{
		kvmppc_mmu_book3s_32_init(vcpu);
		to_book3s(vcpu)->hior = 0;
		to_book3s(vcpu)->msr_mask = 0xffffffffULL;
	}

	/* If we are in hypervisor level on 970, we can tell the CPU to
	 * treat DCBZ as 32 bytes store */
	vcpu->arch.hflags &= ~BOOK3S_HFLAG_DCBZ32;
	if (vcpu->arch.mmu.is_dcbz32(vcpu) && (mfmsr() & MSR_HV) &&
	    !strcmp(cur_cpu_spec->platform, "ppc970"))
		vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;

	/* Cell performs badly if MSR_FEx are set. So let's hope nobody
	   really needs them in a VM on Cell and force disable them. */
	if (!strcmp(cur_cpu_spec->platform, "ppc-cell-be"))
		to_book3s(vcpu)->msr_mask &= ~(MSR_FE0 | MSR_FE1);

#ifdef CONFIG_PPC_BOOK3S_32
	/* 32 bit Book3S always has 32 byte dcbz */
	vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;
#endif

	/* On some CPUs we can execute paired single operations natively */
	asm ( "mfpvr %0" : "=r"(host_pvr));
	switch (host_pvr) {
	case 0x00080200:	/* lonestar 2.0 */
	case 0x00088202:	/* lonestar 2.2 */
	case 0x70000100:	/* gekko 1.0 */
	case 0x00080100:	/* gekko 2.0 */
	case 0x00083203:	/* gekko 2.3a */
	case 0x00083213:	/* gekko 2.3b */
	case 0x00083204:	/* gekko 2.4 */
	case 0x00083214:	/* gekko 2.4e (8SE) - retail HW2 */
	case 0x00087200:	/* broadway */
		vcpu->arch.hflags |= BOOK3S_HFLAG_NATIVE_PS;
		/* Enable HID2.PSE - in case we need it later */
		mtspr(SPRN_HID2_GEKKO, mfspr(SPRN_HID2_GEKKO) | (1 << 29));
	}
}

pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	ulong mp_pa = vcpu->arch.magic_page_pa;

	/* Magic page override */
	if (unlikely(mp_pa) &&
	    unlikely(((gfn << PAGE_SHIFT) & KVM_PAM) ==
		     ((mp_pa & PAGE_MASK) & KVM_PAM))) {
		ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK;
		pfn_t pfn;

		pfn = (pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT;
		get_page(pfn_to_page(pfn));
		return pfn;
	}

	return gfn_to_pfn(vcpu->kvm, gfn);
}

/* Book3s_32 CPUs always have 32 bytes cache line size, which Linux assumes. To
 * make Book3s_32 Linux work on Book3s_64, we have to make sure we trap dcbz to
 * emulate 32 bytes dcbz length.
 *
 * The Book3s_64 inventors also realized this case and implemented a special bit
 * in the HID5 register, which is a hypervisor ressource. Thus we can't use it.
 *
 * My approach here is to patch the dcbz instruction on executing pages.
 */
static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
{
	struct page *hpage;
	u64 hpage_offset;
	u32 *page;
	int i;

	hpage = gfn_to_page(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
	if (is_error_page(hpage)) {
		kvm_release_page_clean(hpage);
		return;
	}

	hpage_offset = pte->raddr & ~PAGE_MASK;
	hpage_offset &= ~0xFFFULL;
	hpage_offset /= 4;

	get_page(hpage);
	page = kmap_atomic(hpage, KM_USER0);

	/* patch dcbz into reserved instruction, so we trap */
	for (i=hpage_offset; i < hpage_offset + (HW_PAGE_SIZE / 4); i++)
		if ((page[i] & 0xff0007ff) == INS_DCBZ)
			page[i] &= 0xfffffff7;

	kunmap_atomic(page, KM_USER0);
	put_page(hpage);
}

static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data,
			 struct kvmppc_pte *pte)
{
	int relocated = (vcpu->arch.shared->msr & (data ? MSR_DR : MSR_IR));
	int r;

	if (relocated) {
		r = vcpu->arch.mmu.xlate(vcpu, eaddr, pte, data);
	} else {
		pte->eaddr = eaddr;
		pte->raddr = eaddr & KVM_PAM;
		pte->vpage = VSID_REAL | eaddr >> 12;
		pte->may_read = true;
		pte->may_write = true;
		pte->may_execute = true;
		r = 0;
	}

	return r;
}

static hva_t kvmppc_bad_hva(void)
{
	return PAGE_OFFSET;
}

static hva_t kvmppc_pte_to_hva(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte,
			       bool read)
{
	hva_t hpage;

	if (read && !pte->may_read)
		goto err;

	if (!read && !pte->may_write)
		goto err;

	hpage = gfn_to_hva(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
	if (kvm_is_error_hva(hpage))
		goto err;

	return hpage | (pte->raddr & ~PAGE_MASK);
err:
	return kvmppc_bad_hva();
}

int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
	      bool data)
{
	struct kvmppc_pte pte;

	vcpu->stat.st++;

	if (kvmppc_xlate(vcpu, *eaddr, data, &pte))
		return -ENOENT;

	*eaddr = pte.raddr;

	if (!pte.may_write)
		return -EPERM;

	if (kvm_write_guest(vcpu->kvm, pte.raddr, ptr, size))
		return EMULATE_DO_MMIO;

	return EMULATE_DONE;
}

int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
		      bool data)
{
	struct kvmppc_pte pte;
	hva_t hva = *eaddr;

	vcpu->stat.ld++;

	if (kvmppc_xlate(vcpu, *eaddr, data, &pte))
		goto nopte;

	*eaddr = pte.raddr;

	hva = kvmppc_pte_to_hva(vcpu, &pte, true);
	if (kvm_is_error_hva(hva))
		goto mmio;

	if (copy_from_user(ptr, (void __user *)hva, size)) {
		printk(KERN_INFO "kvmppc_ld at 0x%lx failed\n", hva);
		goto mmio;
	}

	return EMULATE_DONE;

nopte:
	return -ENOENT;
mmio:
	return EMULATE_DO_MMIO;
}

static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	ulong mp_pa = vcpu->arch.magic_page_pa;

	if (unlikely(mp_pa) &&
	    unlikely((mp_pa & KVM_PAM) >> PAGE_SHIFT == gfn)) {
		return 1;
	}

	return kvm_is_visible_gfn(vcpu->kvm, gfn);
}

int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
			    ulong eaddr, int vec)
{
	bool data = (vec == BOOK3S_INTERRUPT_DATA_STORAGE);
	int r = RESUME_GUEST;
	int relocated;
	int page_found = 0;
	struct kvmppc_pte pte;
	bool is_mmio = false;
	bool dr = (vcpu->arch.shared->msr & MSR_DR) ? true : false;
	bool ir = (vcpu->arch.shared->msr & MSR_IR) ? true : false;
	u64 vsid;

	relocated = data ? dr : ir;

	/* Resolve real address if translation turned on */
	if (relocated) {
		page_found = vcpu->arch.mmu.xlate(vcpu, eaddr, &pte, data);
	} else {
		pte.may_execute = true;
		pte.may_read = true;
		pte.may_write = true;
		pte.raddr = eaddr & KVM_PAM;
		pte.eaddr = eaddr;
		pte.vpage = eaddr >> 12;
	}

	switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
	case 0:
		pte.vpage |= ((u64)VSID_REAL << (SID_SHIFT - 12));
		break;
	case MSR_DR:
	case MSR_IR:
		vcpu->arch.mmu.esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid);

		if ((vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) == MSR_DR)
			pte.vpage |= ((u64)VSID_REAL_DR << (SID_SHIFT - 12));
		else
			pte.vpage |= ((u64)VSID_REAL_IR << (SID_SHIFT - 12));
		pte.vpage |= vsid;

		if (vsid == -1)
			page_found = -EINVAL;
		break;
	}

	if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
	   (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) {
		/*
		 * If we do the dcbz hack, we have to NX on every execution,
		 * so we can patch the executing code. This renders our guest
		 * NX-less.
		 */
		pte.may_execute = !data;
	}

	if (page_found == -ENOENT) {
		/* Page not found in guest PTE entries */
		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
		vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
		vcpu->arch.shared->msr |=
			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
		kvmppc_book3s_queue_irqprio(vcpu, vec);
	} else if (page_found == -EPERM) {
		/* Storage protection */
		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
		vcpu->arch.shared->dsisr =
			to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE;
		vcpu->arch.shared->dsisr |= DSISR_PROTFAULT;
		vcpu->arch.shared->msr |=
			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
		kvmppc_book3s_queue_irqprio(vcpu, vec);
	} else if (page_found == -EINVAL) {
		/* Page not found in guest SLB */
		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
		kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80);
	} else if (!is_mmio &&
		   kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) {
		/* The guest's PTE is not mapped yet. Map on the host */
		kvmppc_mmu_map_page(vcpu, &pte);
		if (data)
			vcpu->stat.sp_storage++;
		else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
			(!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32)))
			kvmppc_patch_dcbz(vcpu, &pte);
	} else {
		/* MMIO */
		vcpu->stat.mmio_exits++;
		vcpu->arch.paddr_accessed = pte.raddr;
		r = kvmppc_emulate_mmio(run, vcpu);
		if ( r == RESUME_HOST_NV )
			r = RESUME_HOST;
	}

	return r;
}

static inline int get_fpr_index(int i)
{
#ifdef CONFIG_VSX
	i *= 2;
#endif
	return i;
}

/* Give up external provider (FPU, Altivec, VSX) */
void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
{
	struct thread_struct *t = &current->thread;
	u64 *vcpu_fpr = vcpu->arch.fpr;
#ifdef CONFIG_VSX
	u64 *vcpu_vsx = vcpu->arch.vsr;
#endif
	u64 *thread_fpr = (u64*)t->fpr;
	int i;

	if (!(vcpu->arch.guest_owned_ext & msr))
		return;

#ifdef DEBUG_EXT
	printk(KERN_INFO "Giving up ext 0x%lx\n", msr);
#endif

	switch (msr) {
	case MSR_FP:
		giveup_fpu(current);
		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
			vcpu_fpr[i] = thread_fpr[get_fpr_index(i)];

		vcpu->arch.fpscr = t->fpscr.val;
		break;
	case MSR_VEC:
#ifdef CONFIG_ALTIVEC
		giveup_altivec(current);
		memcpy(vcpu->arch.vr, t->vr, sizeof(vcpu->arch.vr));
		vcpu->arch.vscr = t->vscr;
#endif
		break;
	case MSR_VSX:
#ifdef CONFIG_VSX
		__giveup_vsx(current);
		for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr); i++)
			vcpu_vsx[i] = thread_fpr[get_fpr_index(i) + 1];
#endif
		break;
	default:
		BUG();
	}

	vcpu->arch.guest_owned_ext &= ~msr;
	current->thread.regs->msr &= ~msr;
	kvmppc_recalc_shadow_msr(vcpu);
}

static int kvmppc_read_inst(struct kvm_vcpu *vcpu)
{
	ulong srr0 = kvmppc_get_pc(vcpu);
	u32 last_inst = kvmppc_get_last_inst(vcpu);
	int ret;

	ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false);
	if (ret == -ENOENT) {
		ulong msr = vcpu->arch.shared->msr;

		msr = kvmppc_set_field(msr, 33, 33, 1);
		msr = kvmppc_set_field(msr, 34, 36, 0);
		vcpu->arch.shared->msr = kvmppc_set_field(msr, 42, 47, 0);
		kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_STORAGE);
		return EMULATE_AGAIN;
	}

	return EMULATE_DONE;
}

static int kvmppc_check_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr)
{

	/* Need to do paired single emulation? */
	if (!(vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE))
		return EMULATE_DONE;

	/* Read out the instruction */
	if (kvmppc_read_inst(vcpu) == EMULATE_DONE)
		/* Need to emulate */
		return EMULATE_FAIL;

	return EMULATE_AGAIN;
}

/* Handle external providers (FPU, Altivec, VSX) */
static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
			     ulong msr)
{
	struct thread_struct *t = &current->thread;
	u64 *vcpu_fpr = vcpu->arch.fpr;
#ifdef CONFIG_VSX
	u64 *vcpu_vsx = vcpu->arch.vsr;
#endif
	u64 *thread_fpr = (u64*)t->fpr;
	int i;

	/* When we have paired singles, we emulate in software */
	if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)
		return RESUME_GUEST;

	if (!(vcpu->arch.shared->msr & msr)) {
		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
		return RESUME_GUEST;
	}

	/* We already own the ext */
	if (vcpu->arch.guest_owned_ext & msr) {
		return RESUME_GUEST;
	}

#ifdef DEBUG_EXT
	printk(KERN_INFO "Loading up ext 0x%lx\n", msr);
#endif

	current->thread.regs->msr |= msr;

	switch (msr) {
	case MSR_FP:
		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
			thread_fpr[get_fpr_index(i)] = vcpu_fpr[i];

		t->fpscr.val = vcpu->arch.fpscr;
		t->fpexc_mode = 0;
		kvmppc_load_up_fpu();
		break;
	case MSR_VEC:
#ifdef CONFIG_ALTIVEC
		memcpy(t->vr, vcpu->arch.vr, sizeof(vcpu->arch.vr));
		t->vscr = vcpu->arch.vscr;
		t->vrsave = -1;
		kvmppc_load_up_altivec();
#endif
		break;
	case MSR_VSX:
#ifdef CONFIG_VSX
		for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr); i++)
			thread_fpr[get_fpr_index(i) + 1] = vcpu_vsx[i];
		kvmppc_load_up_vsx();
#endif
		break;
	default:
		BUG();
	}

	vcpu->arch.guest_owned_ext |= msr;

	kvmppc_recalc_shadow_msr(vcpu);

	return RESUME_GUEST;
}

int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
                       unsigned int exit_nr)
{
	int r = RESUME_HOST;

	vcpu->stat.sum_exits++;

	run->exit_reason = KVM_EXIT_UNKNOWN;
	run->ready_for_interrupt_injection = 1;

	trace_kvm_book3s_exit(exit_nr, vcpu);
	kvm_resched(vcpu);
	switch (exit_nr) {
	case BOOK3S_INTERRUPT_INST_STORAGE:
		vcpu->stat.pf_instruc++;

#ifdef CONFIG_PPC_BOOK3S_32
		/* We set segments as unused segments when invalidating them. So
		 * treat the respective fault as segment fault. */
		if (to_svcpu(vcpu)->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT]
		    == SR_INVALID) {
			kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
			r = RESUME_GUEST;
			break;
		}
#endif

		/* only care about PTEG not found errors, but leave NX alone */
		if (to_svcpu(vcpu)->shadow_srr1 & 0x40000000) {
			r = kvmppc_handle_pagefault(run, vcpu, kvmppc_get_pc(vcpu), exit_nr);
			vcpu->stat.sp_instruc++;
		} else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
			  (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) {
			/*
			 * XXX If we do the dcbz hack we use the NX bit to flush&patch the page,
			 *     so we can't use the NX bit inside the guest. Let's cross our fingers,
			 *     that no guest that needs the dcbz hack does NX.
			 */
			kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
			r = RESUME_GUEST;
		} else {
			vcpu->arch.shared->msr |=
				to_svcpu(vcpu)->shadow_srr1 & 0x58000000;
			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
			r = RESUME_GUEST;
		}
		break;
	case BOOK3S_INTERRUPT_DATA_STORAGE:
	{
		ulong dar = kvmppc_get_fault_dar(vcpu);
		vcpu->stat.pf_storage++;

#ifdef CONFIG_PPC_BOOK3S_32
		/* We set segments as unused segments when invalidating them. So
		 * treat the respective fault as segment fault. */
		if ((to_svcpu(vcpu)->sr[dar >> SID_SHIFT]) == SR_INVALID) {
			kvmppc_mmu_map_segment(vcpu, dar);
			r = RESUME_GUEST;
			break;
		}
#endif

		/* The only case we need to handle is missing shadow PTEs */
		if (to_svcpu(vcpu)->fault_dsisr & DSISR_NOHPTE) {
			r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
		} else {
			vcpu->arch.shared->dar = dar;
			vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
			r = RESUME_GUEST;
		}
		break;
	}
	case BOOK3S_INTERRUPT_DATA_SEGMENT:
		if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_fault_dar(vcpu)) < 0) {
			vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
			kvmppc_book3s_queue_irqprio(vcpu,
				BOOK3S_INTERRUPT_DATA_SEGMENT);
		}
		r = RESUME_GUEST;
		break;
	case BOOK3S_INTERRUPT_INST_SEGMENT:
		if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)) < 0) {
			kvmppc_book3s_queue_irqprio(vcpu,
				BOOK3S_INTERRUPT_INST_SEGMENT);
		}
		r = RESUME_GUEST;
		break;
	/* We're good on these - the host merely wanted to get our attention */
	case BOOK3S_INTERRUPT_DECREMENTER:
		vcpu->stat.dec_exits++;
		r = RESUME_GUEST;
		break;
	case BOOK3S_INTERRUPT_EXTERNAL:
		vcpu->stat.ext_intr_exits++;
		r = RESUME_GUEST;
		break;
	case BOOK3S_INTERRUPT_PERFMON:
		r = RESUME_GUEST;
		break;
	case BOOK3S_INTERRUPT_PROGRAM:
	{
		enum emulation_result er;
		ulong flags;

program_interrupt:
		flags = to_svcpu(vcpu)->shadow_srr1 & 0x1f0000ull;

		if (vcpu->arch.shared->msr & MSR_PR) {
#ifdef EXIT_DEBUG
			printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu));
#endif
			if ((kvmppc_get_last_inst(vcpu) & 0xff0007ff) !=
			    (INS_DCBZ & 0xfffffff7)) {
				kvmppc_core_queue_program(vcpu, flags);
				r = RESUME_GUEST;
				break;
			}
		}

		vcpu->stat.emulated_inst_exits++;
		er = kvmppc_emulate_instruction(run, vcpu);
		switch (er) {
		case EMULATE_DONE:
			r = RESUME_GUEST_NV;
			break;
		case EMULATE_AGAIN:
			r = RESUME_GUEST;
			break;
		case EMULATE_FAIL:
			printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
			       __func__, kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu));
			kvmppc_core_queue_program(vcpu, flags);
			r = RESUME_GUEST;
			break;
		case EMULATE_DO_MMIO:
			run->exit_reason = KVM_EXIT_MMIO;
			r = RESUME_HOST_NV;
			break;
		default:
			BUG();
		}
		break;
	}
	case BOOK3S_INTERRUPT_SYSCALL:
		if (vcpu->arch.osi_enabled &&
		    (((u32)kvmppc_get_gpr(vcpu, 3)) == OSI_SC_MAGIC_R3) &&
		    (((u32)kvmppc_get_gpr(vcpu, 4)) == OSI_SC_MAGIC_R4)) {
			/* MOL hypercalls */
			u64 *gprs = run->osi.gprs;
			int i;

			run->exit_reason = KVM_EXIT_OSI;
			for (i = 0; i < 32; i++)
				gprs[i] = kvmppc_get_gpr(vcpu, i);
			vcpu->arch.osi_needed = 1;
			r = RESUME_HOST_NV;
		} else if (!(vcpu->arch.shared->msr & MSR_PR) &&
		    (((u32)kvmppc_get_gpr(vcpu, 0)) == KVM_SC_MAGIC_R0)) {
			/* KVM PV hypercalls */
			kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu));
			r = RESUME_GUEST;
		} else {
			/* Guest syscalls */
			vcpu->stat.syscall_exits++;
			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
			r = RESUME_GUEST;
		}
		break;
	case BOOK3S_INTERRUPT_FP_UNAVAIL:
	case BOOK3S_INTERRUPT_ALTIVEC:
	case BOOK3S_INTERRUPT_VSX:
	{
		int ext_msr = 0;

		switch (exit_nr) {
		case BOOK3S_INTERRUPT_FP_UNAVAIL: ext_msr = MSR_FP;  break;
		case BOOK3S_INTERRUPT_ALTIVEC:    ext_msr = MSR_VEC; break;
		case BOOK3S_INTERRUPT_VSX:        ext_msr = MSR_VSX; break;
		}

		switch (kvmppc_check_ext(vcpu, exit_nr)) {
		case EMULATE_DONE:
			/* everything ok - let's enable the ext */
			r = kvmppc_handle_ext(vcpu, exit_nr, ext_msr);
			break;
		case EMULATE_FAIL:
			/* we need to emulate this instruction */
			goto program_interrupt;
			break;
		default:
			/* nothing to worry about - go again */
			break;
		}
		break;
	}
	case BOOK3S_INTERRUPT_ALIGNMENT:
		if (kvmppc_read_inst(vcpu) == EMULATE_DONE) {
			vcpu->arch.shared->dsisr = kvmppc_alignment_dsisr(vcpu,
				kvmppc_get_last_inst(vcpu));
			vcpu->arch.shared->dar = kvmppc_alignment_dar(vcpu,
				kvmppc_get_last_inst(vcpu));
			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
		}
		r = RESUME_GUEST;
		break;
	case BOOK3S_INTERRUPT_MACHINE_CHECK:
	case BOOK3S_INTERRUPT_TRACE:
		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
		r = RESUME_GUEST;
		break;
	default:
		/* Ugh - bork here! What did we get? */
		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n",
			exit_nr, kvmppc_get_pc(vcpu), to_svcpu(vcpu)->shadow_srr1);
		r = RESUME_HOST;
		BUG();
		break;
	}


	if (!(r & RESUME_HOST)) {
		/* To avoid clobbering exit_reason, only check for signals if
		 * we aren't already exiting to userspace for some other
		 * reason. */
		if (signal_pending(current)) {
#ifdef EXIT_DEBUG
			printk(KERN_EMERG "KVM: Going back to host\n");
#endif
			vcpu->stat.signal_exits++;
			run->exit_reason = KVM_EXIT_INTR;
			r = -EINTR;
		} else {
			/* In case an interrupt came in that was triggered
			 * from userspace (like DEC), we need to check what
			 * to inject now! */
			kvmppc_core_deliver_interrupts(vcpu);
		}
	}

	trace_kvm_book3s_reenter(r, vcpu);

	return r;
}

int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
	return 0;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	int i;

	regs->pc = kvmppc_get_pc(vcpu);
	regs->cr = kvmppc_get_cr(vcpu);
	regs->ctr = kvmppc_get_ctr(vcpu);
	regs->lr = kvmppc_get_lr(vcpu);
	regs->xer = kvmppc_get_xer(vcpu);
	regs->msr = vcpu->arch.shared->msr;
	regs->srr0 = vcpu->arch.shared->srr0;
	regs->srr1 = vcpu->arch.shared->srr1;
	regs->pid = vcpu->arch.pid;
	regs->sprg0 = vcpu->arch.shared->sprg0;
	regs->sprg1 = vcpu->arch.shared->sprg1;
	regs->sprg2 = vcpu->arch.shared->sprg2;
	regs->sprg3 = vcpu->arch.shared->sprg3;
	regs->sprg5 = vcpu->arch.sprg4;
	regs->sprg6 = vcpu->arch.sprg5;
	regs->sprg7 = vcpu->arch.sprg6;

	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
		regs->gpr[i] = kvmppc_get_gpr(vcpu, i);

	return 0;
}

int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	int i;

	kvmppc_set_pc(vcpu, regs->pc);
	kvmppc_set_cr(vcpu, regs->cr);
	kvmppc_set_ctr(vcpu, regs->ctr);
	kvmppc_set_lr(vcpu, regs->lr);
	kvmppc_set_xer(vcpu, regs->xer);
	kvmppc_set_msr(vcpu, regs->msr);
	vcpu->arch.shared->srr0 = regs->srr0;
	vcpu->arch.shared->srr1 = regs->srr1;
	vcpu->arch.shared->sprg0 = regs->sprg0;
	vcpu->arch.shared->sprg1 = regs->sprg1;
	vcpu->arch.shared->sprg2 = regs->sprg2;
	vcpu->arch.shared->sprg3 = regs->sprg3;
	vcpu->arch.sprg5 = regs->sprg4;
	vcpu->arch.sprg6 = regs->sprg5;
	vcpu->arch.sprg7 = regs->sprg6;

	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
		kvmppc_set_gpr(vcpu, i, regs->gpr[i]);

	return 0;
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
                                  struct kvm_sregs *sregs)
{
	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
	int i;

	sregs->pvr = vcpu->arch.pvr;

	sregs->u.s.sdr1 = to_book3s(vcpu)->sdr1;
	if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) {
		for (i = 0; i < 64; i++) {
			sregs->u.s.ppc64.slb[i].slbe = vcpu3s->slb[i].orige | i;
			sregs->u.s.ppc64.slb[i].slbv = vcpu3s->slb[i].origv;
		}
	} else {
		for (i = 0; i < 16; i++)
			sregs->u.s.ppc32.sr[i] = vcpu->arch.shared->sr[i];

		for (i = 0; i < 8; i++) {
			sregs->u.s.ppc32.ibat[i] = vcpu3s->ibat[i].raw;
			sregs->u.s.ppc32.dbat[i] = vcpu3s->dbat[i].raw;
		}
	}

	return 0;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
                                  struct kvm_sregs *sregs)
{
	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
	int i;

	kvmppc_set_pvr(vcpu, sregs->pvr);

	vcpu3s->sdr1 = sregs->u.s.sdr1;
	if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) {
		for (i = 0; i < 64; i++) {
			vcpu->arch.mmu.slbmte(vcpu, sregs->u.s.ppc64.slb[i].slbv,
						    sregs->u.s.ppc64.slb[i].slbe);
		}
	} else {
		for (i = 0; i < 16; i++) {
			vcpu->arch.mmu.mtsrin(vcpu, i, sregs->u.s.ppc32.sr[i]);
		}
		for (i = 0; i < 8; i++) {
			kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), false,
				       (u32)sregs->u.s.ppc32.ibat[i]);
			kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), true,
				       (u32)(sregs->u.s.ppc32.ibat[i] >> 32));
			kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), false,
				       (u32)sregs->u.s.ppc32.dbat[i]);
			kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), true,
				       (u32)(sregs->u.s.ppc32.dbat[i] >> 32));
		}
	}

	/* Flush the MMU after messing with the segments */
	kvmppc_mmu_pte_flush(vcpu, 0, 0);

	return 0;
}

int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	return -ENOTSUPP;
}

int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	return -ENOTSUPP;
}

int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
                                  struct kvm_translation *tr)
{
	return 0;
}

/*
 * Get (and clear) the dirty memory log for a memory slot.
 */
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
				      struct kvm_dirty_log *log)
{
	struct kvm_memory_slot *memslot;
	struct kvm_vcpu *vcpu;
	ulong ga, ga_end;
	int is_dirty = 0;
	int r;
	unsigned long n;

	mutex_lock(&kvm->slots_lock);

	r = kvm_get_dirty_log(kvm, log, &is_dirty);
	if (r)
		goto out;

	/* If nothing is dirty, don't bother messing with page tables. */
	if (is_dirty) {
		memslot = &kvm->memslots->memslots[log->slot];

		ga = memslot->base_gfn << PAGE_SHIFT;
		ga_end = ga + (memslot->npages << PAGE_SHIFT);

		kvm_for_each_vcpu(n, vcpu, kvm)
			kvmppc_mmu_pte_pflush(vcpu, ga, ga_end);

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

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

int kvmppc_core_check_processor_compat(void)
{
	return 0;
}

struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
{
	struct kvmppc_vcpu_book3s *vcpu_book3s;
	struct kvm_vcpu *vcpu;
	int err = -ENOMEM;
	unsigned long p;

	vcpu_book3s = vmalloc(sizeof(struct kvmppc_vcpu_book3s));
	if (!vcpu_book3s)
		goto out;

	memset(vcpu_book3s, 0, sizeof(struct kvmppc_vcpu_book3s));

	vcpu_book3s->shadow_vcpu = (struct kvmppc_book3s_shadow_vcpu *)
		kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL);
	if (!vcpu_book3s->shadow_vcpu)
		goto free_vcpu;

	vcpu = &vcpu_book3s->vcpu;
	err = kvm_vcpu_init(vcpu, kvm, id);
	if (err)
		goto free_shadow_vcpu;

	p = __get_free_page(GFP_KERNEL|__GFP_ZERO);
	/* the real shared page fills the last 4k of our page */
	vcpu->arch.shared = (void*)(p + PAGE_SIZE - 4096);
	if (!p)
		goto uninit_vcpu;

	vcpu->arch.host_retip = kvm_return_point;
	vcpu->arch.host_msr = mfmsr();
#ifdef CONFIG_PPC_BOOK3S_64
	/* default to book3s_64 (970fx) */
	vcpu->arch.pvr = 0x3C0301;
#else
	/* default to book3s_32 (750) */
	vcpu->arch.pvr = 0x84202;
#endif
	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
	vcpu_book3s->slb_nr = 64;

	/* remember where some real-mode handlers are */
	vcpu->arch.trampoline_lowmem = kvmppc_trampoline_lowmem;
	vcpu->arch.trampoline_enter = kvmppc_trampoline_enter;
	vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem;
#ifdef CONFIG_PPC_BOOK3S_64
	vcpu->arch.rmcall = *(ulong*)kvmppc_rmcall;
#else
	vcpu->arch.rmcall = (ulong)kvmppc_rmcall;
#endif

	vcpu->arch.shadow_msr = MSR_USER64;

	err = kvmppc_mmu_init(vcpu);
	if (err < 0)
		goto uninit_vcpu;

	return vcpu;

uninit_vcpu:
	kvm_vcpu_uninit(vcpu);
free_shadow_vcpu:
	kfree(vcpu_book3s->shadow_vcpu);
free_vcpu:
	vfree(vcpu_book3s);
out:
	return ERR_PTR(err);
}

void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
{
	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);

	free_page((unsigned long)vcpu->arch.shared & PAGE_MASK);
	kvm_vcpu_uninit(vcpu);
	kfree(vcpu_book3s->shadow_vcpu);
	vfree(vcpu_book3s);
}

extern int __kvmppc_vcpu_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
{
	int ret;
	double fpr[32][TS_FPRWIDTH];
	unsigned int fpscr;
	int fpexc_mode;
#ifdef CONFIG_ALTIVEC
	vector128 vr[32];
	vector128 vscr;
	unsigned long uninitialized_var(vrsave);
	int used_vr;
#endif
#ifdef CONFIG_VSX
	int used_vsr;
#endif
	ulong ext_msr;

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

	/* Save FPU state in stack */
	if (current->thread.regs->msr & MSR_FP)
		giveup_fpu(current);
	memcpy(fpr, current->thread.fpr, sizeof(current->thread.fpr));
	fpscr = current->thread.fpscr.val;
	fpexc_mode = current->thread.fpexc_mode;

#ifdef CONFIG_ALTIVEC
	/* Save Altivec state in stack */
	used_vr = current->thread.used_vr;
	if (used_vr) {
		if (current->thread.regs->msr & MSR_VEC)
			giveup_altivec(current);
		memcpy(vr, current->thread.vr, sizeof(current->thread.vr));
		vscr = current->thread.vscr;
		vrsave = current->thread.vrsave;
	}
#endif

#ifdef CONFIG_VSX
	/* Save VSX state in stack */
	used_vsr = current->thread.used_vsr;
	if (used_vsr && (current->thread.regs->msr & MSR_VSX))
			__giveup_vsx(current);
#endif

	/* Remember the MSR with disabled extensions */
	ext_msr = current->thread.regs->msr;

	/* XXX we get called with irq disabled - change that! */
	local_irq_enable();

	/* Preload FPU if it's enabled */
	if (vcpu->arch.shared->msr & MSR_FP)
		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);

	ret = __kvmppc_vcpu_entry(kvm_run, vcpu);

	local_irq_disable();

	current->thread.regs->msr = ext_msr;

	/* Make sure we save the guest FPU/Altivec/VSX state */
	kvmppc_giveup_ext(vcpu, MSR_FP);
	kvmppc_giveup_ext(vcpu, MSR_VEC);
	kvmppc_giveup_ext(vcpu, MSR_VSX);

	/* Restore FPU state from stack */
	memcpy(current->thread.fpr, fpr, sizeof(current->thread.fpr));
	current->thread.fpscr.val = fpscr;
	current->thread.fpexc_mode = fpexc_mode;

#ifdef CONFIG_ALTIVEC
	/* Restore Altivec state from stack */
	if (used_vr && current->thread.used_vr) {
		memcpy(current->thread.vr, vr, sizeof(current->thread.vr));
		current->thread.vscr = vscr;
		current->thread.vrsave = vrsave;
	}
	current->thread.used_vr = used_vr;
#endif

#ifdef CONFIG_VSX
	current->thread.used_vsr = used_vsr;
#endif

	return ret;
}

static int kvmppc_book3s_init(void)
{
	int r;

	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), 0,
		     THIS_MODULE);

	if (r)
		return r;

	r = kvmppc_mmu_hpte_sysinit();

	return r;
}

static void kvmppc_book3s_exit(void)
{
	kvmppc_mmu_hpte_sysexit();
	kvm_exit();
}

module_init(kvmppc_book3s_init);
module_exit(kvmppc_book3s_exit);